1706 files changed, 64532 insertions, 6611 deletions

diff --git a/Documentation/ABI/testing/debugfs-aufs b/Documentation/ABI/testing/debugfs-aufs
new file mode 100644
index 000000000000..99642d1055a2
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-aufs
@@ -0,0 +1,50 @@
+What:		/debug/aufs/si_<id>/
+Date:		March 2009
+Contact:	J. R. Okajima <hooanon05g@gmail.com>
+Description:
+		Under /debug/aufs, a directory named si_<id> is created
+		per aufs mount, where <id> is a unique id generated
+		internally.
+
+What:		/debug/aufs/si_<id>/plink
+Date:		Apr 2013
+Contact:	J. R. Okajima <hooanon05g@gmail.com>
+Description:
+		It has three lines and shows the information about the
+		pseudo-link. The first line is a single number
+		representing a number of buckets. The second line is a
+		number of pseudo-links per buckets (separated by a
+		blank). The last line is a single number representing a
+		total number of psedo-links.
+		When the aufs mount option 'noplink' is specified, it
+		will show "1\n0\n0\n".
+
+What:		/debug/aufs/si_<id>/xib
+Date:		March 2009
+Contact:	J. R. Okajima <hooanon05g@gmail.com>
+Description:
+		It shows the consumed blocks by xib (External Inode Number
+		Bitmap), its block size and file size.
+		When the aufs mount option 'noxino' is specified, it
+		will be empty. About XINO files, see the aufs manual.
+
+What:		/debug/aufs/si_<id>/xino0, xino1 ... xinoN
+Date:		March 2009
+Contact:	J. R. Okajima <hooanon05g@gmail.com>
+Description:
+		It shows the consumed blocks by xino (External Inode Number
+		Translation Table), its link count, block size and file
+		size.
+		When the aufs mount option 'noxino' is specified, it
+		will be empty. About XINO files, see the aufs manual.
+
+What:		/debug/aufs/si_<id>/xigen
+Date:		March 2009
+Contact:	J. R. Okajima <hooanon05g@gmail.com>
+Description:
+		It shows the consumed blocks by xigen (External Inode
+		Generation Table), its block size and file size.
+		If CONFIG_AUFS_EXPORT is disabled, this entry will not
+		be created.
+		When the aufs mount option 'noxino' is specified, it
+		will be empty. About XINO files, see the aufs manual.
diff --git a/Documentation/ABI/testing/sysfs-aufs b/Documentation/ABI/testing/sysfs-aufs
new file mode 100644
index 000000000000..82f9518495ea
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-aufs
@@ -0,0 +1,31 @@
+What:		/sys/fs/aufs/si_<id>/
+Date:		March 2009
+Contact:	J. R. Okajima <hooanon05g@gmail.com>
+Description:
+		Under /sys/fs/aufs, a directory named si_<id> is created
+		per aufs mount, where <id> is a unique id generated
+		internally.
+
+What:		/sys/fs/aufs/si_<id>/br0, br1 ... brN
+Date:		March 2009
+Contact:	J. R. Okajima <hooanon05g@gmail.com>
+Description:
+		It shows the abolute path of a member directory (which
+		is called branch) in aufs, and its permission.
+
+What:		/sys/fs/aufs/si_<id>/brid0, brid1 ... bridN
+Date:		July 2013
+Contact:	J. R. Okajima <hooanon05g@gmail.com>
+Description:
+		It shows the id of a member directory (which is called
+		branch) in aufs.
+
+What:		/sys/fs/aufs/si_<id>/xi_path
+Date:		March 2009
+Contact:	J. R. Okajima <hooanon05g@gmail.com>
+Description:
+		It shows the abolute path of XINO (External Inode Number
+		Bitmap, Translation Table and Generation Table) file
+		even if it is the default path.
+		When the aufs mount option 'noxino' is specified, it
+		will be empty. About XINO files, see the aufs manual.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 64e65450f483..e21e2ca3e4f9 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -1524,7 +1524,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_voc_raw
 KernelVersion:	4.3
 Contact:	linux-iio@vger.kernel.org
 Description:
-		Raw (unscaled no offset etc.) percentage reading of a substance.
+		Raw (unscaled no offset etc.) reading of a substance. Units
+		after application of scale and offset are percents.
 
 What:		/sys/bus/iio/devices/iio:deviceX/in_resistance_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_resistanceX_raw
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 9ebca6a750f3..5abe1cc9f068 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -381,6 +381,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 		/sys/devices/system/cpu/vulnerabilities/l1tf
 		/sys/devices/system/cpu/vulnerabilities/mds
+		/sys/devices/system/cpu/vulnerabilities/srbds
 		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
 		/sys/devices/system/cpu/vulnerabilities/itlb_multihit
 Date:		January 2018
diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst
index 0795e3c2643f..ca4dbdd9016d 100644
--- a/Documentation/admin-guide/hw-vuln/index.rst
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@@ -14,3 +14,4 @@ are configurable at compile, boot or run time.
    mds
    tsx_async_abort
    multihit.rst
+   special-register-buffer-data-sampling.rst
diff --git a/Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst b/Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst
new file mode 100644
index 000000000000..47b1b3afac99
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst
@@ -0,0 +1,149 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+SRBDS - Special Register Buffer Data Sampling
+=============================================
+
+SRBDS is a hardware vulnerability that allows MDS :doc:`mds` techniques to
+infer values returned from special register accesses.  Special register
+accesses are accesses to off core registers.  According to Intel's evaluation,
+the special register reads that have a security expectation of privacy are
+RDRAND, RDSEED and SGX EGETKEY.
+
+When RDRAND, RDSEED and EGETKEY instructions are used, the data is moved
+to the core through the special register mechanism that is susceptible
+to MDS attacks.
+
+Affected processors
+--------------------
+Core models (desktop, mobile, Xeon-E3) that implement RDRAND and/or RDSEED may
+be affected.
+
+A processor is affected by SRBDS if its Family_Model and stepping is
+in the following list, with the exception of the listed processors
+exporting MDS_NO while Intel TSX is available yet not enabled. The
+latter class of processors are only affected when Intel TSX is enabled
+by software using TSX_CTRL_MSR otherwise they are not affected.
+
+  =============  ============  ========
+  common name    Family_Model  Stepping
+  =============  ============  ========
+  IvyBridge      06_3AH        All
+
+  Haswell        06_3CH        All
+  Haswell_L      06_45H        All
+  Haswell_G      06_46H        All
+
+  Broadwell_G    06_47H        All
+  Broadwell      06_3DH        All
+
+  Skylake_L      06_4EH        All
+  Skylake        06_5EH        All
+
+  Kabylake_L     06_8EH        <= 0xC
+  Kabylake       06_9EH        <= 0xD
+  =============  ============  ========
+
+Related CVEs
+------------
+
+The following CVE entry is related to this SRBDS issue:
+
+    ==============  =====  =====================================
+    CVE-2020-0543   SRBDS  Special Register Buffer Data Sampling
+    ==============  =====  =====================================
+
+Attack scenarios
+----------------
+An unprivileged user can extract values returned from RDRAND and RDSEED
+executed on another core or sibling thread using MDS techniques.
+
+
+Mitigation mechanism
+-------------------
+Intel will release microcode updates that modify the RDRAND, RDSEED, and
+EGETKEY instructions to overwrite secret special register data in the shared
+staging buffer before the secret data can be accessed by another logical
+processor.
+
+During execution of the RDRAND, RDSEED, or EGETKEY instructions, off-core
+accesses from other logical processors will be delayed until the special
+register read is complete and the secret data in the shared staging buffer is
+overwritten.
+
+This has three effects on performance:
+
+#. RDRAND, RDSEED, or EGETKEY instructions have higher latency.
+
+#. Executing RDRAND at the same time on multiple logical processors will be
+   serialized, resulting in an overall reduction in the maximum RDRAND
+   bandwidth.
+
+#. Executing RDRAND, RDSEED or EGETKEY will delay memory accesses from other
+   logical processors that miss their core caches, with an impact similar to
+   legacy locked cache-line-split accesses.
+
+The microcode updates provide an opt-out mechanism (RNGDS_MITG_DIS) to disable
+the mitigation for RDRAND and RDSEED instructions executed outside of Intel
+Software Guard Extensions (Intel SGX) enclaves. On logical processors that
+disable the mitigation using this opt-out mechanism, RDRAND and RDSEED do not
+take longer to execute and do not impact performance of sibling logical
+processors memory accesses. The opt-out mechanism does not affect Intel SGX
+enclaves (including execution of RDRAND or RDSEED inside an enclave, as well
+as EGETKEY execution).
+
+IA32_MCU_OPT_CTRL MSR Definition
+--------------------------------
+Along with the mitigation for this issue, Intel added a new thread-scope
+IA32_MCU_OPT_CTRL MSR, (address 0x123). The presence of this MSR and
+RNGDS_MITG_DIS (bit 0) is enumerated by CPUID.(EAX=07H,ECX=0).EDX[SRBDS_CTRL =
+9]==1. This MSR is introduced through the microcode update.
+
+Setting IA32_MCU_OPT_CTRL[0] (RNGDS_MITG_DIS) to 1 for a logical processor
+disables the mitigation for RDRAND and RDSEED executed outside of an Intel SGX
+enclave on that logical processor. Opting out of the mitigation for a
+particular logical processor does not affect the RDRAND and RDSEED mitigations
+for other logical processors.
+
+Note that inside of an Intel SGX enclave, the mitigation is applied regardless
+of the value of RNGDS_MITG_DS.
+
+Mitigation control on the kernel command line
+---------------------------------------------
+The kernel command line allows control over the SRBDS mitigation at boot time
+with the option "srbds=".  The option for this is:
+
+  ============= =============================================================
+  off           This option disables SRBDS mitigation for RDRAND and RDSEED on
+                affected platforms.
+  ============= =============================================================
+
+SRBDS System Information
+-----------------------
+The Linux kernel provides vulnerability status information through sysfs.  For
+SRBDS this can be accessed by the following sysfs file:
+/sys/devices/system/cpu/vulnerabilities/srbds
+
+The possible values contained in this file are:
+
+ ============================== =============================================
+ Not affected                   Processor not vulnerable
+ Vulnerable                     Processor vulnerable and mitigation disabled
+ Vulnerable: No microcode       Processor vulnerable and microcode is missing
+                                mitigation
+ Mitigation: Microcode          Processor is vulnerable and mitigation is in
+                                effect.
+ Mitigation: TSX disabled       Processor is only vulnerable when TSX is
+                                enabled while this system was booted with TSX
+                                disabled.
+ Unknown: Dependent on
+ hypervisor status              Running on virtual guest processor that is
+                                affected but with no way to know if host
+                                processor is mitigated or vulnerable.
+ ============================== =============================================
+
+SRBDS Default mitigation
+------------------------
+This new microcode serializes processor access during execution of RDRAND,
+RDSEED ensures that the shared buffer is overwritten before it is released for
+reuse.  Use the "srbds=off" kernel command line to disable the mitigation for
+RDRAND and RDSEED.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index ae51b1b7b67f..dc96e7f10ebc 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4234,6 +4234,26 @@
 	spia_pedr=
 	spia_peddr=
 
+	srbds=		[X86,INTEL]
+			Control the Special Register Buffer Data Sampling
+			(SRBDS) mitigation.
+
+			Certain CPUs are vulnerable to an MDS-like
+			exploit which can leak bits from the random
+			number generator.
+
+			By default, this issue is mitigated by
+			microcode.  However, the microcode fix can cause
+			the RDRAND and RDSEED instructions to become
+			much slower.  Among other effects, this will
+			result in reduced throughput from /dev/urandom.
+
+			The microcode mitigation can be disabled with
+			the following option:
+
+			off:    Disable mitigation and remove
+				performance impact to RDRAND and RDSEED
+
 	srcutree.counter_wrap_check [KNL]
 			Specifies how frequently to check for
 			grace-period sequence counter wrap for the
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt
index b6a7e7397b8b..b944fe067188 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt
@@ -16,6 +16,9 @@ Required properties:
   Documentation/devicetree/bindings/graph.txt. This port should be connected
   to the input port of an attached HDMI or LVDS encoder chip.
 
+Optional properties:
+- pinctrl-names: Contain "default" and "sleep".
+
 Example:
 
 dpi0: dpi@1401d000 {
@@ -26,6 +29,9 @@ dpi0: dpi@1401d000 {
 		 <&mmsys CLK_MM_DPI_ENGINE>,
 		 <&apmixedsys CLK_APMIXED_TVDPLL>;
 	clock-names = "pixel", "engine", "pll";
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&dpi_pin_func>;
+	pinctrl-1 = <&dpi_pin_idle>;
 
 	port {
 		dpi0_out: endpoint {
diff --git a/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt b/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt
index c82794002595..89647d714387 100644
--- a/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt
+++ b/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt
@@ -21,7 +21,7 @@ controller state. The mux controller state is described in
 
 Example:
 	mux: mux-controller {
-		compatible = "mux-gpio";
+		compatible = "gpio-mux";
 		#mux-control-cells = <0>;
 
 		mux-gpios = <&pioA 0 GPIO_ACTIVE_HIGH>,
diff --git a/Documentation/devicetree/bindings/sound/wm8994.txt b/Documentation/devicetree/bindings/sound/wm8994.txt
index 68c4e8d96bed..b309de00cd83 100644
--- a/Documentation/devicetree/bindings/sound/wm8994.txt
+++ b/Documentation/devicetree/bindings/sound/wm8994.txt
@@ -14,9 +14,15 @@ Required properties:
   - #gpio-cells : Must be 2. The first cell is the pin number and the
     second cell is used to specify optional parameters (currently unused).
 
-  - AVDD2-supply, DBVDD1-supply, DBVDD2-supply, DBVDD3-supply, CPVDD-supply,
-    SPKVDD1-supply, SPKVDD2-supply : power supplies for the device, as covered
-    in Documentation/devicetree/bindings/regulator/regulator.txt
+  - power supplies for the device, as covered in
+    Documentation/devicetree/bindings/regulator/regulator.txt, depending
+    on compatible:
+    - for wlf,wm1811 and wlf,wm8958:
+      AVDD1-supply, AVDD2-supply, DBVDD1-supply, DBVDD2-supply, DBVDD3-supply,
+      DCVDD-supply, CPVDD-supply, SPKVDD1-supply, SPKVDD2-supply
+    - for wlf,wm8994:
+      AVDD1-supply, AVDD2-supply, DBVDD-supply, DCVDD-supply, CPVDD-supply,
+      SPKVDD1-supply, SPKVDD2-supply
 
 Optional properties:
 
@@ -68,11 +74,11 @@ codec: wm8994@1a {
 
 	lineout1-se;
 
+	AVDD1-supply = <&regulator>;
 	AVDD2-supply = <&regulator>;
 	CPVDD-supply = <&regulator>;
-	DBVDD1-supply = <&regulator>;
-	DBVDD2-supply = <&regulator>;
-	DBVDD3-supply = <&regulator>;
+	DBVDD-supply = <&regulator>;
+	DCVDD-supply = <&regulator>;
 	SPKVDD1-supply = <&regulator>;
 	SPKVDD2-supply = <&regulator>;
 };
diff --git a/Documentation/devicetree/bindings/usb/dwc3.txt b/Documentation/devicetree/bindings/usb/dwc3.txt
index 44e8bab159ad..baee73134d03 100644
--- a/Documentation/devicetree/bindings/usb/dwc3.txt
+++ b/Documentation/devicetree/bindings/usb/dwc3.txt
@@ -47,6 +47,8 @@ Optional properties:
 			from P0 to P1/P2/P3 without delay.
  - snps,dis-tx-ipgap-linecheck-quirk: when set, disable u2mac linestate check
 			during HS transmit.
+ - snps,parkmode-disable-ss-quirk: when set, all SuperSpeed bus instances in
+			park mode are disabled.
  - snps,dis_metastability_quirk: when set, disable metastability workaround.
 			CAUTION: use only if you are absolutely sure of it.
  - snps,is-utmi-l1-suspend: true when DWC3 asserts output signal
diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst
index 4adc056f7635..01ae89efa2bd 100644
--- a/Documentation/driver-api/libata.rst
+++ b/Documentation/driver-api/libata.rst
@@ -251,7 +251,7 @@ High-level taskfile hooks
 
 ::
 
-    void (*qc_prep) (struct ata_queued_cmd *qc);
+    enum ata_completion_errors (*qc_prep) (struct ata_queued_cmd *qc);
     int (*qc_issue) (struct ata_queued_cmd *qc);
 
 
diff --git a/Documentation/driver-api/mtdnand.rst b/Documentation/driver-api/mtdnand.rst
index 2a5191b6d445..15449334b124 100644
--- a/Documentation/driver-api/mtdnand.rst
+++ b/Documentation/driver-api/mtdnand.rst
@@ -277,7 +277,7 @@ unregisters the partitions in the MTD layer.
     static void __exit board_cleanup (void)
     {
         /* Release resources, unregister device */
-        nand_release (board_mtd);
+        nand_release (mtd_to_nand(board_mtd));
 
         /* unmap physical address */
         iounmap(baseaddr);
diff --git a/Documentation/filesystems/affs.txt b/Documentation/filesystems/affs.txt
index 71b63c2b9841..a8f1a58e3692 100644
--- a/Documentation/filesystems/affs.txt
+++ b/Documentation/filesystems/affs.txt
@@ -93,13 +93,15 @@ The Amiga protection flags RWEDRWEDHSPARWED are handled as follows:
 
   - R maps to r for user, group and others. On directories, R implies x.
 
-  - If both W and D are allowed, w will be set.
+  - W maps to w.
 
   - E maps to x.
 
-  - H and P are always retained and ignored under Linux.
+  - D is ignored.
 
-  - A is always reset when a file is written to.
+  - H, S and P are always retained and ignored under Linux.
+
+  - A is cleared when a file is written to.
 
 User id and group id will be used unless set[gu]id are given as mount
 options. Since most of the Amiga file systems are single user systems
@@ -111,11 +113,13 @@ Linux -> Amiga:
 
 The Linux rwxrwxrwx file mode is handled as follows:
 
-  - r permission will set R for user, group and others.
+  - r permission will allow R for user, group and others.
+
+  - w permission will allow W for user, group and others.
 
-  - w permission will set W and D for user, group and others.
+  - x permission of the user will allow E for plain files.
 
-  - x permission of the user will set E for plain files.
+  - D will be allowed for user, group and others.
 
   - All other flags (suid, sgid, ...) are ignored and will
     not be retained.
diff --git a/Documentation/filesystems/aufs/README b/Documentation/filesystems/aufs/README
new file mode 100644
index 000000000000..fa82b6394f69
--- /dev/null
+++ b/Documentation/filesystems/aufs/README
@@ -0,0 +1,393 @@
+
+Aufs4 -- advanced multi layered unification filesystem version 4.x
+http://aufs.sf.net
+Junjiro R. Okajima
+
+
+0. Introduction
+----------------------------------------
+In the early days, aufs was entirely re-designed and re-implemented
+Unionfs Version 1.x series. Adding many original ideas, approaches,
+improvements and implementations, it becomes totally different from
+Unionfs while keeping the basic features.
+Recently, Unionfs Version 2.x series begin taking some of the same
+approaches to aufs1's.
+Unionfs is being developed by Professor Erez Zadok at Stony Brook
+University and his team.
+
+Aufs4 supports linux-4.0 and later, and for linux-3.x series try aufs3.
+If you want older kernel version support, try aufs2-2.6.git or
+aufs2-standalone.git repository, aufs1 from CVS on SourceForge.
+
+Note: it becomes clear that "Aufs was rejected. Let's give it up."
+      According to Christoph Hellwig, linux rejects all union-type
+      filesystems but UnionMount.
+<http://marc.info/?l=linux-kernel&m=123938533724484&w=2>
+
+PS. Al Viro seems have a plan to merge aufs as well as overlayfs and
+    UnionMount, and he pointed out an issue around a directory mutex
+    lock and aufs addressed it. But it is still unsure whether aufs will
+    be merged (or any other union solution).
+<http://marc.info/?l=linux-kernel&m=136312705029295&w=1>
+
+
+1. Features
+----------------------------------------
+- unite several directories into a single virtual filesystem. The member
+  directory is called as a branch.
+- you can specify the permission flags to the branch, which are 'readonly',
+  'readwrite' and 'whiteout-able.'
+- by upper writable branch, internal copyup and whiteout, files/dirs on
+  readonly branch are modifiable logically.
+- dynamic branch manipulation, add, del.
+- etc...
+
+Also there are many enhancements in aufs, such as:
+- test only the highest one for the directory permission (dirperm1)
+- copyup on open (coo=)
+- 'move' policy for copy-up between two writable branches, after
+  checking free space.
+- xattr, acl
+- readdir(3) in userspace.
+- keep inode number by external inode number table
+- keep the timestamps of file/dir in internal copyup operation
+- seekable directory, supporting NFS readdir.
+- whiteout is hardlinked in order to reduce the consumption of inodes
+  on branch
+- do not copyup, nor create a whiteout when it is unnecessary
+- revert a single systemcall when an error occurs in aufs
+- remount interface instead of ioctl
+- maintain /etc/mtab by an external command, /sbin/mount.aufs.
+- loopback mounted filesystem as a branch
+- kernel thread for removing the dir who has a plenty of whiteouts
+- support copyup sparse file (a file which has a 'hole' in it)
+- default permission flags for branches
+- selectable permission flags for ro branch, whether whiteout can
+  exist or not
+- export via NFS.
+- support <sysfs>/fs/aufs and <debugfs>/aufs.
+- support multiple writable branches, some policies to select one
+  among multiple writable branches.
+- a new semantics for link(2) and rename(2) to support multiple
+  writable branches.
+- no glibc changes are required.
+- pseudo hardlink (hardlink over branches)
+- allow a direct access manually to a file on branch, e.g. bypassing aufs.
+  including NFS or remote filesystem branch.
+- userspace wrapper for pathconf(3)/fpathconf(3) with _PC_LINK_MAX.
+- and more...
+
+Currently these features are dropped temporary from aufs4.
+See design/08plan.txt in detail.
+- nested mount, i.e. aufs as readonly no-whiteout branch of another aufs
+  (robr)
+- statistics of aufs thread (/sys/fs/aufs/stat)
+
+Features or just an idea in the future (see also design/*.txt),
+- reorder the branch index without del/re-add.
+- permanent xino files for NFSD
+- an option for refreshing the opened files after add/del branches
+- light version, without branch manipulation. (unnecessary?)
+- copyup in userspace
+- inotify in userspace
+- readv/writev
+
+
+2. Download
+----------------------------------------
+There are three GIT trees for aufs4, aufs4-linux.git,
+aufs4-standalone.git, and aufs-util.git. Note that there is no "4" in
+"aufs-util.git."
+While the aufs-util is always necessary, you need either of aufs4-linux
+or aufs4-standalone.
+
+The aufs4-linux tree includes the whole linux mainline GIT tree,
+git://git.kernel.org/.../torvalds/linux.git.
+And you cannot select CONFIG_AUFS_FS=m for this version, eg. you cannot
+build aufs4 as an external kernel module.
+Several extra patches are not included in this tree. Only
+aufs4-standalone tree contains them. They are described in the later
+section "Configuration and Compilation."
+
+On the other hand, the aufs4-standalone tree has only aufs source files
+and necessary patches, and you can select CONFIG_AUFS_FS=m.
+But you need to apply all aufs patches manually.
+
+You will find GIT branches whose name is in form of "aufs4.x" where "x"
+represents the linux kernel version, "linux-4.x". For instance,
+"aufs4.0" is for linux-4.0. For latest "linux-4.x-rcN", use
+"aufs4.x-rcN" branch.
+
+o aufs4-linux tree
+$ git clone --reference /your/linux/git/tree \
+	git://github.com/sfjro/aufs4-linux.git aufs4-linux.git
+- if you don't have linux GIT tree, then remove "--reference ..."
+$ cd aufs4-linux.git
+$ git checkout origin/aufs4.0
+
+Or You may want to directly git-pull aufs into your linux GIT tree, and
+leave the patch-work to GIT.
+$ cd /your/linux/git/tree
+$ git remote add aufs4 git://github.com/sfjro/aufs4-linux.git
+$ git fetch aufs4
+$ git checkout -b my4.0 v4.0
+$ (add your local change...)
+$ git pull aufs4 aufs4.0
+- now you have v4.0 + your_changes + aufs4.0 in you my4.0 branch.
+- you may need to solve some conflicts between your_changes and
+  aufs4.0. in this case, git-rerere is recommended so that you can
+  solve the similar conflicts automatically when you upgrade to 4.1 or
+  later in the future.
+
+o aufs4-standalone tree
+$ git clone git://github.com/sfjro/aufs4-standalone.git aufs4-standalone.git
+$ cd aufs4-standalone.git
+$ git checkout origin/aufs4.0
+
+o aufs-util tree
+$ git clone git://git.code.sf.net/p/aufs/aufs-util aufs-util.git
+- note that the public aufs-util.git is on SourceForge instead of
+  GitHUB.
+$ cd aufs-util.git
+$ git checkout origin/aufs4.0
+
+Note: The 4.x-rcN branch is to be used with `rc' kernel versions ONLY.
+The minor version number, 'x' in '4.x', of aufs may not always
+follow the minor version number of the kernel.
+Because changes in the kernel that cause the use of a new
+minor version number do not always require changes to aufs-util.
+
+Since aufs-util has its own minor version number, you may not be
+able to find a GIT branch in aufs-util for your kernel's
+exact minor version number.
+In this case, you should git-checkout the branch for the
+nearest lower number.
+
+For (an unreleased) example:
+If you are using "linux-4.10" and the "aufs4.10" branch
+does not exist in aufs-util repository, then "aufs4.9", "aufs4.8"
+or something numerically smaller is the branch for your kernel.
+
+Also you can view all branches by
+	$ git branch -a
+
+
+3. Configuration and Compilation
+----------------------------------------
+Make sure you have git-checkout'ed the correct branch.
+
+For aufs4-linux tree,
+- enable CONFIG_AUFS_FS.
+- set other aufs configurations if necessary.
+
+For aufs4-standalone tree,
+There are several ways to build.
+
+1.
+- apply ./aufs4-kbuild.patch to your kernel source files.
+- apply ./aufs4-base.patch too.
+- apply ./aufs4-mmap.patch too.
+- apply ./aufs4-standalone.patch too, if you have a plan to set
+  CONFIG_AUFS_FS=m. otherwise you don't need ./aufs4-standalone.patch.
+- copy ./{Documentation,fs,include/uapi/linux/aufs_type.h} files to your
+  kernel source tree. Never copy $PWD/include/uapi/linux/Kbuild.
+- enable CONFIG_AUFS_FS, you can select either
+  =m or =y.
+- and build your kernel as usual.
+- install the built kernel.
+  Note: Since linux-3.9, every filesystem module requires an alias
+  "fs-<fsname>". You should make sure that "fs-aufs" is listed in your
+  modules.aliases file if you set CONFIG_AUFS_FS=m.
+- install the header files too by "make headers_install" to the
+  directory where you specify. By default, it is $PWD/usr.
+  "make help" shows a brief note for headers_install.
+- and reboot your system.
+
+2.
+- module only (CONFIG_AUFS_FS=m).
+- apply ./aufs4-base.patch to your kernel source files.
+- apply ./aufs4-mmap.patch too.
+- apply ./aufs4-standalone.patch too.
+- build your kernel, don't forget "make headers_install", and reboot.
+- edit ./config.mk and set other aufs configurations if necessary.
+  Note: You should read $PWD/fs/aufs/Kconfig carefully which describes
+  every aufs configurations.
+- build the module by simple "make".
+  Note: Since linux-3.9, every filesystem module requires an alias
+  "fs-<fsname>". You should make sure that "fs-aufs" is listed in your
+  modules.aliases file.
+- you can specify ${KDIR} make variable which points to your kernel
+  source tree.
+- install the files
+  + run "make install" to install the aufs module, or copy the built
+    $PWD/aufs.ko to /lib/modules/... and run depmod -a (or reboot simply).
+  + run "make install_headers" (instead of headers_install) to install
+    the modified aufs header file (you can specify DESTDIR which is
+    available in aufs standalone version's Makefile only), or copy
+    $PWD/usr/include/linux/aufs_type.h to /usr/include/linux or wherever
+    you like manually. By default, the target directory is $PWD/usr.
+- no need to apply aufs4-kbuild.patch, nor copying source files to your
+  kernel source tree.
+
+Note: The header file aufs_type.h is necessary to build aufs-util
+      as well as "make headers_install" in the kernel source tree.
+      headers_install is subject to be forgotten, but it is essentially
+      necessary, not only for building aufs-util.
+      You may not meet problems without headers_install in some older
+      version though.
+
+And then,
+- read README in aufs-util, build and install it
+- note that your distribution may contain an obsoleted version of
+  aufs_type.h in /usr/include/linux or something. When you build aufs
+  utilities, make sure that your compiler refers the correct aufs header
+  file which is built by "make headers_install."
+- if you want to use readdir(3) in userspace or pathconf(3) wrapper,
+  then run "make install_ulib" too. And refer to the aufs manual in
+  detail.
+
+There several other patches in aufs4-standalone.git. They are all
+optional. When you meet some problems, they will help you.
+- aufs4-loopback.patch
+  Supports a nested loopback mount in a branch-fs. This patch is
+  unnecessary until aufs produces a message like "you may want to try
+  another patch for loopback file".
+- vfs-ino.patch
+  Modifies a system global kernel internal function get_next_ino() in
+  order to stop assigning 0 for an inode-number. Not directly related to
+  aufs, but recommended generally.
+- tmpfs-idr.patch
+  Keeps the tmpfs inode number as the lowest value. Effective to reduce
+  the size of aufs XINO files for tmpfs branch. Also it prevents the
+  duplication of inode number, which is important for backup tools and
+  other utilities. When you find aufs XINO files for tmpfs branch
+  growing too much, try this patch.
+- lockdep-debug.patch
+  Because aufs is not only an ordinary filesystem (callee of VFS), but
+  also a caller of VFS functions for branch filesystems, subclassing of
+  the internal locks for LOCKDEP is necessary. LOCKDEP is a debugging
+  feature of linux kernel. If you enable CONFIG_LOCKDEP, then you will
+  need to apply this debug patch to expand several constant values.
+  If don't know what LOCKDEP, then you don't have apply this patch.
+
+
+4. Usage
+----------------------------------------
+At first, make sure aufs-util are installed, and please read the aufs
+manual, aufs.5 in aufs-util.git tree.
+$ man -l aufs.5
+
+And then,
+$ mkdir /tmp/rw /tmp/aufs
+# mount -t aufs -o br=/tmp/rw:${HOME} none /tmp/aufs
+
+Here is another example. The result is equivalent.
+# mount -t aufs -o br=/tmp/rw=rw:${HOME}=ro none /tmp/aufs
+  Or
+# mount -t aufs -o br:/tmp/rw none /tmp/aufs
+# mount -o remount,append:${HOME} /tmp/aufs
+
+Then, you can see whole tree of your home dir through /tmp/aufs. If
+you modify a file under /tmp/aufs, the one on your home directory is
+not affected, instead the same named file will be newly created under
+/tmp/rw. And all of your modification to a file will be applied to
+the one under /tmp/rw. This is called the file based Copy on Write
+(COW) method.
+Aufs mount options are described in aufs.5.
+If you run chroot or something and make your aufs as a root directory,
+then you need to customize the shutdown script. See the aufs manual in
+detail.
+
+Additionally, there are some sample usages of aufs which are a
+diskless system with network booting, and LiveCD over NFS.
+See sample dir in CVS tree on SourceForge.
+
+
+5. Contact
+----------------------------------------
+When you have any problems or strange behaviour in aufs, please let me
+know with:
+- /proc/mounts (instead of the output of mount(8))
+- /sys/module/aufs/*
+- /sys/fs/aufs/* (if you have them)
+- /debug/aufs/* (if you have them)
+- linux kernel version
+  if your kernel is not plain, for example modified by distributor,
+  the url where i can download its source is necessary too.
+- aufs version which was printed at loading the module or booting the
+  system, instead of the date you downloaded.
+- configuration (define/undefine CONFIG_AUFS_xxx)
+- kernel configuration or /proc/config.gz (if you have it)
+- behaviour which you think to be incorrect
+- actual operation, reproducible one is better
+- mailto: aufs-users at lists.sourceforge.net
+
+Usually, I don't watch the Public Areas(Bugs, Support Requests, Patches,
+and Feature Requests) on SourceForge. Please join and write to
+aufs-users ML.
+
+
+6. Acknowledgements
+----------------------------------------
+Thanks to everyone who have tried and are using aufs, whoever
+have reported a bug or any feedback.
+
+Especially donators:
+Tomas Matejicek(slax.org) made a donation (much more than once).
+	Since Apr 2010, Tomas M (the author of Slax and Linux Live
+	scripts) is making "doubling" donations.
+	Unfortunately I cannot list all of the donators, but I really
+	appreciate.
+	It ends Aug 2010, but the ordinary donation URL is still available.
+	<http://sourceforge.net/donate/index.php?group_id=167503>
+Dai Itasaka made a donation (2007/8).
+Chuck Smith made a donation (2008/4, 10 and 12).
+Henk Schoneveld made a donation (2008/9).
+Chih-Wei Huang, ASUS, CTC donated Eee PC 4G (2008/10).
+Francois Dupoux made a donation (2008/11).
+Bruno Cesar Ribas and Luis Carlos Erpen de Bona, C3SL serves public
+	aufs2 GIT tree (2009/2).
+William Grant made a donation (2009/3).
+Patrick Lane made a donation (2009/4).
+The Mail Archive (mail-archive.com) made donations (2009/5).
+Nippy Networks (Ed Wildgoose) made a donation (2009/7).
+New Dream Network, LLC (www.dreamhost.com) made a donation (2009/11).
+Pavel Pronskiy made a donation (2011/2).
+Iridium and Inmarsat satellite phone retailer (www.mailasail.com), Nippy
+	Networks (Ed Wildgoose) made a donation for hardware (2011/3).
+Max Lekomcev (DOM-TV project) made a donation (2011/7, 12, 2012/3, 6 and
+11).
+Sam Liddicott made a donation (2011/9).
+Era Scarecrow made a donation (2013/4).
+Bor Ratajc made a donation (2013/4).
+Alessandro Gorreta made a donation (2013/4).
+POIRETTE Marc made a donation (2013/4).
+Alessandro Gorreta made a donation (2013/4).
+lauri kasvandik made a donation (2013/5).
+"pemasu from Finland" made a donation (2013/7).
+The Parted Magic Project made a donation (2013/9 and 11).
+Pavel Barta made a donation (2013/10).
+Nikolay Pertsev made a donation (2014/5).
+James B made a donation (2014/7 and 2015/7).
+Stefano Di Biase made a donation (2014/8).
+Daniel Epellei made a donation (2015/1).
+OmegaPhil made a donation (2016/1).
+Tomasz Szewczyk made a donation (2016/4).
+James Burry made a donation (2016/12).
+
+Thank you very much.
+Donations are always, including future donations, very important and
+helpful for me to keep on developing aufs.
+
+
+7.
+----------------------------------------
+If you are an experienced user, no explanation is needed. Aufs is
+just a linux filesystem.
+
+
+Enjoy!
+
+# Local variables: ;
+# mode: text;
+# End: ;
diff --git a/Documentation/filesystems/aufs/design/01intro.txt b/Documentation/filesystems/aufs/design/01intro.txt
new file mode 100644
index 000000000000..ae16191bd918
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/01intro.txt
@@ -0,0 +1,171 @@
+
+# Copyright (C) 2005-2017 Junjiro R. Okajima
+# 
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Introduction
+----------------------------------------
+
+aufs [ei ju: ef es] | /ey-yoo-ef-es/ | [a u f s]
+1. abbrev. for "advanced multi-layered unification filesystem".
+2. abbrev. for "another unionfs".
+3. abbrev. for "auf das" in German which means "on the" in English.
+   Ex. "Butter aufs Brot"(G) means "butter onto bread"(E).
+   But "Filesystem aufs Filesystem" is hard to understand.
+4. abbrev. for "African Urban Fashion Show".
+
+AUFS is a filesystem with features:
+- multi layered stackable unification filesystem, the member directory
+  is called as a branch.
+- branch permission and attribute, 'readonly', 'real-readonly',
+  'readwrite', 'whiteout-able', 'link-able whiteout', etc. and their
+  combination.
+- internal "file copy-on-write".
+- logical deletion, whiteout.
+- dynamic branch manipulation, adding, deleting and changing permission.
+- allow bypassing aufs, user's direct branch access.
+- external inode number translation table and bitmap which maintains the
+  persistent aufs inode number.
+- seekable directory, including NFS readdir.
+- file mapping, mmap and sharing pages.
+- pseudo-link, hardlink over branches.
+- loopback mounted filesystem as a branch.
+- several policies to select one among multiple writable branches.
+- revert a single systemcall when an error occurs in aufs.
+- and more...
+
+
+Multi Layered Stackable Unification Filesystem
+----------------------------------------------------------------------
+Most people already knows what it is.
+It is a filesystem which unifies several directories and provides a
+merged single directory. When users access a file, the access will be
+passed/re-directed/converted (sorry, I am not sure which English word is
+correct) to the real file on the member filesystem. The member
+filesystem is called 'lower filesystem' or 'branch' and has a mode
+'readonly' and 'readwrite.' And the deletion for a file on the lower
+readonly branch is handled by creating 'whiteout' on the upper writable
+branch.
+
+On LKML, there have been discussions about UnionMount (Jan Blunck,
+Bharata B Rao and Valerie Aurora) and Unionfs (Erez Zadok). They took
+different approaches to implement the merged-view.
+The former tries putting it into VFS, and the latter implements as a
+separate filesystem.
+(If I misunderstand about these implementations, please let me know and
+I shall correct it. Because it is a long time ago when I read their
+source files last time).
+
+UnionMount's approach will be able to small, but may be hard to share
+branches between several UnionMount since the whiteout in it is
+implemented in the inode on branch filesystem and always
+shared. According to Bharata's post, readdir does not seems to be
+finished yet.
+There are several missing features known in this implementations such as
+- for users, the inode number may change silently. eg. copy-up.
+- link(2) may break by copy-up.
+- read(2) may get an obsoleted filedata (fstat(2) too).
+- fcntl(F_SETLK) may be broken by copy-up.
+- unnecessary copy-up may happen, for example mmap(MAP_PRIVATE) after
+  open(O_RDWR).
+
+In linux-3.18, "overlay" filesystem (formerly known as "overlayfs") was
+merged into mainline. This is another implementation of UnionMount as a
+separated filesystem. All the limitations and known problems which
+UnionMount are equally inherited to "overlay" filesystem.
+
+Unionfs has a longer history. When I started implementing a stackable
+filesystem (Aug 2005), it already existed. It has virtual super_block,
+inode, dentry and file objects and they have an array pointing lower
+same kind objects. After contributing many patches for Unionfs, I
+re-started my project AUFS (Jun 2006).
+
+In AUFS, the structure of filesystem resembles to Unionfs, but I
+implemented my own ideas, approaches and enhancements and it became
+totally different one.
+
+Comparing DM snapshot and fs based implementation
+- the number of bytes to be copied between devices is much smaller.
+- the type of filesystem must be one and only.
+- the fs must be writable, no readonly fs, even for the lower original
+  device. so the compression fs will not be usable. but if we use
+  loopback mount, we may address this issue.
+  for instance,
+	mount /cdrom/squashfs.img /sq
+	losetup /sq/ext2.img
+	losetup /somewhere/cow
+	dmsetup "snapshot /dev/loop0 /dev/loop1 ..."
+- it will be difficult (or needs more operations) to extract the
+  difference between the original device and COW.
+- DM snapshot-merge may help a lot when users try merging. in the
+  fs-layer union, users will use rsync(1).
+
+You may want to read my old paper "Filesystems in LiveCD"
+(http://aufs.sourceforge.net/aufs2/report/sq/sq.pdf).
+
+
+Several characters/aspects/persona of aufs
+----------------------------------------------------------------------
+
+Aufs has several characters, aspects or persona.
+1. a filesystem, callee of VFS helper
+2. sub-VFS, caller of VFS helper for branches
+3. a virtual filesystem which maintains persistent inode number
+4. reader/writer of files on branches such like an application
+
+1. Callee of VFS Helper
+As an ordinary linux filesystem, aufs is a callee of VFS. For instance,
+unlink(2) from an application reaches sys_unlink() kernel function and
+then vfs_unlink() is called. vfs_unlink() is one of VFS helper and it
+calls filesystem specific unlink operation. Actually aufs implements the
+unlink operation but it behaves like a redirector.
+
+2. Caller of VFS Helper for Branches
+aufs_unlink() passes the unlink request to the branch filesystem as if
+it were called from VFS. So the called unlink operation of the branch
+filesystem acts as usual. As a caller of VFS helper, aufs should handle
+every necessary pre/post operation for the branch filesystem.
+- acquire the lock for the parent dir on a branch
+- lookup in a branch
+- revalidate dentry on a branch
+- mnt_want_write() for a branch
+- vfs_unlink() for a branch
+- mnt_drop_write() for a branch
+- release the lock on a branch
+
+3. Persistent Inode Number
+One of the most important issue for a filesystem is to maintain inode
+numbers. This is particularly important to support exporting a
+filesystem via NFS. Aufs is a virtual filesystem which doesn't have a
+backend block device for its own. But some storage is necessary to
+keep and maintain the inode numbers. It may be a large space and may not
+suit to keep in memory. Aufs rents some space from its first writable
+branch filesystem (by default) and creates file(s) on it. These files
+are created by aufs internally and removed soon (currently) keeping
+opened.
+Note: Because these files are removed, they are totally gone after
+      unmounting aufs. It means the inode numbers are not persistent
+      across unmount or reboot. I have a plan to make them really
+      persistent which will be important for aufs on NFS server.
+
+4. Read/Write Files Internally (copy-on-write)
+Because a branch can be readonly, when you write a file on it, aufs will
+"copy-up" it to the upper writable branch internally. And then write the
+originally requested thing to the file. Generally kernel doesn't
+open/read/write file actively. In aufs, even a single write may cause a
+internal "file copy". This behaviour is very similar to cp(1) command.
+
+Some people may think it is better to pass such work to user space
+helper, instead of doing in kernel space. Actually I am still thinking
+about it. But currently I have implemented it in kernel space.
diff --git a/Documentation/filesystems/aufs/design/02struct.txt b/Documentation/filesystems/aufs/design/02struct.txt
new file mode 100644
index 000000000000..1d1ccde5de21
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/02struct.txt
@@ -0,0 +1,258 @@
+
+# Copyright (C) 2005-2017 Junjiro R. Okajima
+# 
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Basic Aufs Internal Structure
+
+Superblock/Inode/Dentry/File Objects
+----------------------------------------------------------------------
+As like an ordinary filesystem, aufs has its own
+superblock/inode/dentry/file objects. All these objects have a
+dynamically allocated array and store the same kind of pointers to the
+lower filesystem, branch.
+For example, when you build a union with one readwrite branch and one
+readonly, mounted /au, /rw and /ro respectively.
+- /au = /rw + /ro
+- /ro/fileA exists but /rw/fileA
+
+Aufs lookup operation finds /ro/fileA and gets dentry for that. These
+pointers are stored in a aufs dentry. The array in aufs dentry will be,
+- [0] = NULL (because /rw/fileA doesn't exist)
+- [1] = /ro/fileA
+
+This style of an array is essentially same to the aufs
+superblock/inode/dentry/file objects.
+
+Because aufs supports manipulating branches, ie. add/delete/change
+branches dynamically, these objects has its own generation. When
+branches are changed, the generation in aufs superblock is
+incremented. And a generation in other object are compared when it is
+accessed. When a generation in other objects are obsoleted, aufs
+refreshes the internal array.
+
+
+Superblock
+----------------------------------------------------------------------
+Additionally aufs superblock has some data for policies to select one
+among multiple writable branches, XIB files, pseudo-links and kobject.
+See below in detail.
+About the policies which supports copy-down a directory, see
+wbr_policy.txt too.
+
+
+Branch and XINO(External Inode Number Translation Table)
+----------------------------------------------------------------------
+Every branch has its own xino (external inode number translation table)
+file. The xino file is created and unlinked by aufs internally. When two
+members of a union exist on the same filesystem, they share the single
+xino file.
+The struct of a xino file is simple, just a sequence of aufs inode
+numbers which is indexed by the lower inode number.
+In the above sample, assume the inode number of /ro/fileA is i111 and
+aufs assigns the inode number i999 for fileA. Then aufs writes 999 as
+4(8) bytes at 111 * 4(8) bytes offset in the xino file.
+
+When the inode numbers are not contiguous, the xino file will be sparse
+which has a hole in it and doesn't consume as much disk space as it
+might appear. If your branch filesystem consumes disk space for such
+holes, then you should specify 'xino=' option at mounting aufs.
+
+Aufs has a mount option to free the disk blocks for such holes in XINO
+files on tmpfs or ramdisk. But it is not so effective actually. If you
+meet a problem of disk shortage due to XINO files, then you should try
+"tmpfs-ino.patch" (and "vfs-ino.patch" too) in aufs4-standalone.git.
+The patch localizes the assignment inumbers per tmpfs-mount and avoid
+the holes in XINO files.
+
+Also a writable branch has three kinds of "whiteout bases". All these
+are existed when the branch is joined to aufs, and their names are
+whiteout-ed doubly, so that users will never see their names in aufs
+hierarchy.
+1. a regular file which will be hardlinked to all whiteouts.
+2. a directory to store a pseudo-link.
+3. a directory to store an "orphan"-ed file temporary.
+
+1. Whiteout Base
+   When you remove a file on a readonly branch, aufs handles it as a
+   logical deletion and creates a whiteout on the upper writable branch
+   as a hardlink of this file in order not to consume inode on the
+   writable branch.
+2. Pseudo-link Dir
+   See below, Pseudo-link.
+3. Step-Parent Dir
+   When "fileC" exists on the lower readonly branch only and it is
+   opened and removed with its parent dir, and then user writes
+   something into it, then aufs copies-up fileC to this
+   directory. Because there is no other dir to store fileC. After
+   creating a file under this dir, the file is unlinked.
+
+Because aufs supports manipulating branches, ie. add/delete/change
+dynamically, a branch has its own id. When the branch order changes,
+aufs finds the new index by searching the branch id.
+
+
+Pseudo-link
+----------------------------------------------------------------------
+Assume "fileA" exists on the lower readonly branch only and it is
+hardlinked to "fileB" on the branch. When you write something to fileA,
+aufs copies-up it to the upper writable branch. Additionally aufs
+creates a hardlink under the Pseudo-link Directory of the writable
+branch. The inode of a pseudo-link is kept in aufs super_block as a
+simple list. If fileB is read after unlinking fileA, aufs returns
+filedata from the pseudo-link instead of the lower readonly
+branch. Because the pseudo-link is based upon the inode, to keep the
+inode number by xino (see above) is essentially necessary.
+
+All the hardlinks under the Pseudo-link Directory of the writable branch
+should be restored in a proper location later. Aufs provides a utility
+to do this. The userspace helpers executed at remounting and unmounting
+aufs by default.
+During this utility is running, it puts aufs into the pseudo-link
+maintenance mode. In this mode, only the process which began the
+maintenance mode (and its child processes) is allowed to operate in
+aufs. Some other processes which are not related to the pseudo-link will
+be allowed to run too, but the rest have to return an error or wait
+until the maintenance mode ends. If a process already acquires an inode
+mutex (in VFS), it has to return an error.
+
+
+XIB(external inode number bitmap)
+----------------------------------------------------------------------
+Addition to the xino file per a branch, aufs has an external inode number
+bitmap in a superblock object. It is also an internal file such like a
+xino file.
+It is a simple bitmap to mark whether the aufs inode number is in-use or
+not.
+To reduce the file I/O, aufs prepares a single memory page to cache xib.
+
+As well as XINO files, aufs has a feature to truncate/refresh XIB to
+reduce the number of consumed disk blocks for these files.
+
+
+Virtual or Vertical Dir, and Readdir in Userspace
+----------------------------------------------------------------------
+In order to support multiple layers (branches), aufs readdir operation
+constructs a virtual dir block on memory. For readdir, aufs calls
+vfs_readdir() internally for each dir on branches, merges their entries
+with eliminating the whiteout-ed ones, and sets it to file (dir)
+object. So the file object has its entry list until it is closed. The
+entry list will be updated when the file position is zero and becomes
+obsoleted. This decision is made in aufs automatically.
+
+The dynamically allocated memory block for the name of entries has a
+unit of 512 bytes (by default) and stores the names contiguously (no
+padding). Another block for each entry is handled by kmem_cache too.
+During building dir blocks, aufs creates hash list and judging whether
+the entry is whiteouted by its upper branch or already listed.
+The merged result is cached in the corresponding inode object and
+maintained by a customizable life-time option.
+
+Some people may call it can be a security hole or invite DoS attack
+since the opened and once readdir-ed dir (file object) holds its entry
+list and becomes a pressure for system memory. But I'd say it is similar
+to files under /proc or /sys. The virtual files in them also holds a
+memory page (generally) while they are opened. When an idea to reduce
+memory for them is introduced, it will be applied to aufs too.
+For those who really hate this situation, I've developed readdir(3)
+library which operates this merging in userspace. You just need to set
+LD_PRELOAD environment variable, and aufs will not consume no memory in
+kernel space for readdir(3).
+
+
+Workqueue
+----------------------------------------------------------------------
+Aufs sometimes requires privilege access to a branch. For instance,
+in copy-up/down operation. When a user process is going to make changes
+to a file which exists in the lower readonly branch only, and the mode
+of one of ancestor directories may not be writable by a user
+process. Here aufs copy-up the file with its ancestors and they may
+require privilege to set its owner/group/mode/etc.
+This is a typical case of a application character of aufs (see
+Introduction).
+
+Aufs uses workqueue synchronously for this case. It creates its own
+workqueue. The workqueue is a kernel thread and has privilege. Aufs
+passes the request to call mkdir or write (for example), and wait for
+its completion. This approach solves a problem of a signal handler
+simply.
+If aufs didn't adopt the workqueue and changed the privilege of the
+process, then the process may receive the unexpected SIGXFSZ or other
+signals.
+
+Also aufs uses the system global workqueue ("events" kernel thread) too
+for asynchronous tasks, such like handling inotify/fsnotify, re-creating a
+whiteout base and etc. This is unrelated to a privilege.
+Most of aufs operation tries acquiring a rw_semaphore for aufs
+superblock at the beginning, at the same time waits for the completion
+of all queued asynchronous tasks.
+
+
+Whiteout
+----------------------------------------------------------------------
+The whiteout in aufs is very similar to Unionfs's. That is represented
+by its filename. UnionMount takes an approach of a file mode, but I am
+afraid several utilities (find(1) or something) will have to support it.
+
+Basically the whiteout represents "logical deletion" which stops aufs to
+lookup further, but also it represents "dir is opaque" which also stop
+further lookup.
+
+In aufs, rmdir(2) and rename(2) for dir uses whiteout alternatively.
+In order to make several functions in a single systemcall to be
+revertible, aufs adopts an approach to rename a directory to a temporary
+unique whiteouted name.
+For example, in rename(2) dir where the target dir already existed, aufs
+renames the target dir to a temporary unique whiteouted name before the
+actual rename on a branch, and then handles other actions (make it opaque,
+update the attributes, etc). If an error happens in these actions, aufs
+simply renames the whiteouted name back and returns an error. If all are
+succeeded, aufs registers a function to remove the whiteouted unique
+temporary name completely and asynchronously to the system global
+workqueue.
+
+
+Copy-up
+----------------------------------------------------------------------
+It is a well-known feature or concept.
+When user modifies a file on a readonly branch, aufs operate "copy-up"
+internally and makes change to the new file on the upper writable branch.
+When the trigger systemcall does not update the timestamps of the parent
+dir, aufs reverts it after copy-up.
+
+
+Move-down (aufs3.9 and later)
+----------------------------------------------------------------------
+"Copy-up" is one of the essential feature in aufs. It copies a file from
+the lower readonly branch to the upper writable branch when a user
+changes something about the file.
+"Move-down" is an opposite action of copy-up. Basically this action is
+ran manually instead of automatically and internally.
+For desgin and implementation, aufs has to consider these issues.
+- whiteout for the file may exist on the lower branch.
+- ancestor directories may not exist on the lower branch.
+- diropq for the ancestor directories may exist on the upper branch.
+- free space on the lower branch will reduce.
+- another access to the file may happen during moving-down, including
+  UDBA (see "Revalidate Dentry and UDBA").
+- the file should not be hard-linked nor pseudo-linked. they should be
+  handled by auplink utility later.
+
+Sometimes users want to move-down a file from the upper writable branch
+to the lower readonly or writable branch. For instance,
+- the free space of the upper writable branch is going to run out.
+- create a new intermediate branch between the upper and lower branch.
+- etc.
+
+For this purpose, use "aumvdown" command in aufs-util.git.
diff --git a/Documentation/filesystems/aufs/design/03atomic_open.txt b/Documentation/filesystems/aufs/design/03atomic_open.txt
new file mode 100644
index 000000000000..5f0aca4421a6
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/03atomic_open.txt
@@ -0,0 +1,85 @@
+
+# Copyright (C) 2015-2017 Junjiro R. Okajima
+# 
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Support for a branch who has its ->atomic_open()
+----------------------------------------------------------------------
+The filesystems who implement its ->atomic_open() are not majority. For
+example NFSv4 does, and aufs should call NFSv4 ->atomic_open,
+particularly for open(O_CREAT|O_EXCL, 0400) case. Other than
+->atomic_open(), NFSv4 returns an error for this open(2). While I am not
+sure whether all filesystems who have ->atomic_open() behave like this,
+but NFSv4 surely returns the error.
+
+In order to support ->atomic_open() for aufs, there are a few
+approaches.
+
+A. Introduce aufs_atomic_open()
+   - calls one of VFS:do_last(), lookup_open() or atomic_open() for
+     branch fs.
+B. Introduce aufs_atomic_open() calling create, open and chmod. this is
+   an aufs user Pip Cet's approach
+   - calls aufs_create(), VFS finish_open() and notify_change().
+   - pass fake-mode to finish_open(), and then correct the mode by
+     notify_change().
+C. Extend aufs_open() to call branch fs's ->atomic_open()
+   - no aufs_atomic_open().
+   - aufs_lookup() registers the TID to an aufs internal object.
+   - aufs_create() does nothing when the matching TID is registered, but
+     registers the mode.
+   - aufs_open() calls branch fs's ->atomic_open() when the matching
+     TID is registered.
+D. Extend aufs_open() to re-try branch fs's ->open() with superuser's
+   credential
+   - no aufs_atomic_open().
+   - aufs_create() registers the TID to an internal object. this info
+     represents "this process created this file just now."
+   - when aufs gets EACCES from branch fs's ->open(), then confirm the
+     registered TID and re-try open() with superuser's credential.
+
+Pros and cons for each approach.
+
+A.
+   - straightforward but highly depends upon VFS internal.
+   - the atomic behavaiour is kept.
+   - some of parameters such as nameidata are hard to reproduce for
+     branch fs.
+   - large overhead.
+B.
+   - easy to implement.
+   - the atomic behavaiour is lost.
+C.
+   - the atomic behavaiour is kept.
+   - dirty and tricky.
+   - VFS checks whether the file is created correctly after calling
+     ->create(), which means this approach doesn't work.
+D.
+   - easy to implement.
+   - the atomic behavaiour is lost.
+   - to open a file with superuser's credential and give it to a user
+     process is a bad idea, since the file object keeps the credential
+     in it. It may affect LSM or something. This approach doesn't work
+     either.
+
+The approach A is ideal, but it hard to implement. So here is a
+variation of A, which is to be implemented.
+
+A-1. Introduce aufs_atomic_open()
+     - calls branch fs ->atomic_open() if exists. otherwise calls
+       vfs_create() and finish_open().
+     - the demerit is that the several checks after branch fs
+       ->atomic_open() are lost. in the ordinary case, the checks are
+       done by VFS:do_last(), lookup_open() and atomic_open(). some can
+       be implemented in aufs, but not all I am afraid.
diff --git a/Documentation/filesystems/aufs/design/03lookup.txt b/Documentation/filesystems/aufs/design/03lookup.txt
new file mode 100644
index 000000000000..8b8ac6e0e273
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/03lookup.txt
@@ -0,0 +1,113 @@
+
+# Copyright (C) 2005-2017 Junjiro R. Okajima
+# 
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Lookup in a Branch
+----------------------------------------------------------------------
+Since aufs has a character of sub-VFS (see Introduction), it operates
+lookup for branches as VFS does. It may be a heavy work. But almost all
+lookup operation in aufs is the simplest case, ie. lookup only an entry
+directly connected to its parent. Digging down the directory hierarchy
+is unnecessary. VFS has a function lookup_one_len() for that use, and
+aufs calls it.
+
+When a branch is a remote filesystem, aufs basically relies upon its
+->d_revalidate(), also aufs forces the hardest revalidate tests for
+them.
+For d_revalidate, aufs implements three levels of revalidate tests. See
+"Revalidate Dentry and UDBA" in detail.
+
+
+Test Only the Highest One for the Directory Permission (dirperm1 option)
+----------------------------------------------------------------------
+Let's try case study.
+- aufs has two branches, upper readwrite and lower readonly.
+  /au = /rw + /ro
+- "dirA" exists under /ro, but /rw. and its mode is 0700.
+- user invoked "chmod a+rx /au/dirA"
+- the internal copy-up is activated and "/rw/dirA" is created and its
+  permission bits are set to world readable.
+- then "/au/dirA" becomes world readable?
+
+In this case, /ro/dirA is still 0700 since it exists in readonly branch,
+or it may be a natively readonly filesystem. If aufs respects the lower
+branch, it should not respond readdir request from other users. But user
+allowed it by chmod. Should really aufs rejects showing the entries
+under /ro/dirA?
+
+To be honest, I don't have a good solution for this case. So aufs
+implements 'dirperm1' and 'nodirperm1' mount options, and leave it to
+users.
+When dirperm1 is specified, aufs checks only the highest one for the
+directory permission, and shows the entries. Otherwise, as usual, checks
+every dir existing on all branches and rejects the request.
+
+As a side effect, dirperm1 option improves the performance of aufs
+because the number of permission check is reduced when the number of
+branch is many.
+
+
+Revalidate Dentry and UDBA (User's Direct Branch Access)
+----------------------------------------------------------------------
+Generally VFS helpers re-validate a dentry as a part of lookup.
+0. digging down the directory hierarchy.
+1. lock the parent dir by its i_mutex.
+2. lookup the final (child) entry.
+3. revalidate it.
+4. call the actual operation (create, unlink, etc.)
+5. unlock the parent dir
+
+If the filesystem implements its ->d_revalidate() (step 3), then it is
+called. Actually aufs implements it and checks the dentry on a branch is
+still valid.
+But it is not enough. Because aufs has to release the lock for the
+parent dir on a branch at the end of ->lookup() (step 2) and
+->d_revalidate() (step 3) while the i_mutex of the aufs dir is still
+held by VFS.
+If the file on a branch is changed directly, eg. bypassing aufs, after
+aufs released the lock, then the subsequent operation may cause
+something unpleasant result.
+
+This situation is a result of VFS architecture, ->lookup() and
+->d_revalidate() is separated. But I never say it is wrong. It is a good
+design from VFS's point of view. It is just not suitable for sub-VFS
+character in aufs.
+
+Aufs supports such case by three level of revalidation which is
+selectable by user.
+1. Simple Revalidate
+   Addition to the native flow in VFS's, confirm the child-parent
+   relationship on the branch just after locking the parent dir on the
+   branch in the "actual operation" (step 4). When this validation
+   fails, aufs returns EBUSY. ->d_revalidate() (step 3) in aufs still
+   checks the validation of the dentry on branches.
+2. Monitor Changes Internally by Inotify/Fsnotify
+   Addition to above, in the "actual operation" (step 4) aufs re-lookup
+   the dentry on the branch, and returns EBUSY if it finds different
+   dentry.
+   Additionally, aufs sets the inotify/fsnotify watch for every dir on branches
+   during it is in cache. When the event is notified, aufs registers a
+   function to kernel 'events' thread by schedule_work(). And the
+   function sets some special status to the cached aufs dentry and inode
+   private data. If they are not cached, then aufs has nothing to
+   do. When the same file is accessed through aufs (step 0-3) later,
+   aufs will detect the status and refresh all necessary data.
+   In this mode, aufs has to ignore the event which is fired by aufs
+   itself.
+3. No Extra Validation
+   This is the simplest test and doesn't add any additional revalidation
+   test, and skip the revalidation in step 4. It is useful and improves
+   aufs performance when system surely hide the aufs branches from user,
+   by over-mounting something (or another method).
diff --git a/Documentation/filesystems/aufs/design/04branch.txt b/Documentation/filesystems/aufs/design/04branch.txt
new file mode 100644
index 000000000000..5604ff8eb616
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/04branch.txt
@@ -0,0 +1,74 @@
+
+# Copyright (C) 2005-2017 Junjiro R. Okajima
+# 
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Branch Manipulation
+
+Since aufs supports dynamic branch manipulation, ie. add/remove a branch
+and changing its permission/attribute, there are a lot of works to do.
+
+
+Add a Branch
+----------------------------------------------------------------------
+o Confirm the adding dir exists outside of aufs, including loopback
+  mount, and its various attributes.
+o Initialize the xino file and whiteout bases if necessary.
+  See struct.txt.
+
+o Check the owner/group/mode of the directory
+  When the owner/group/mode of the adding directory differs from the
+  existing branch, aufs issues a warning because it may impose a
+  security risk.
+  For example, when a upper writable branch has a world writable empty
+  top directory, a malicious user can create any files on the writable
+  branch directly, like copy-up and modify manually. If something like
+  /etc/{passwd,shadow} exists on the lower readonly branch but the upper
+  writable branch, and the writable branch is world-writable, then a
+  malicious guy may create /etc/passwd on the writable branch directly
+  and the infected file will be valid in aufs.
+  I am afraid it can be a security issue, but aufs can do nothing except
+  producing a warning.
+
+
+Delete a Branch
+----------------------------------------------------------------------
+o Confirm the deleting branch is not busy
+  To be general, there is one merit to adopt "remount" interface to
+  manipulate branches. It is to discard caches. At deleting a branch,
+  aufs checks the still cached (and connected) dentries and inodes. If
+  there are any, then they are all in-use. An inode without its
+  corresponding dentry can be alive alone (for example, inotify/fsnotify case).
+
+  For the cached one, aufs checks whether the same named entry exists on
+  other branches.
+  If the cached one is a directory, because aufs provides a merged view
+  to users, as long as one dir is left on any branch aufs can show the
+  dir to users. In this case, the branch can be removed from aufs.
+  Otherwise aufs rejects deleting the branch.
+
+  If any file on the deleting branch is opened by aufs, then aufs
+  rejects deleting.
+
+
+Modify the Permission of a Branch
+----------------------------------------------------------------------
+o Re-initialize or remove the xino file and whiteout bases if necessary.
+  See struct.txt.
+
+o rw --> ro: Confirm the modifying branch is not busy
+  Aufs rejects the request if any of these conditions are true.
+  - a file on the branch is mmap-ed.
+  - a regular file on the branch is opened for write and there is no
+    same named entry on the upper branch.
diff --git a/Documentation/filesystems/aufs/design/05wbr_policy.txt b/Documentation/filesystems/aufs/design/05wbr_policy.txt
new file mode 100644
index 000000000000..1578469b32e9
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/05wbr_policy.txt
@@ -0,0 +1,64 @@
+
+# Copyright (C) 2005-2017 Junjiro R. Okajima
+# 
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Policies to Select One among Multiple Writable Branches
+----------------------------------------------------------------------
+When the number of writable branch is more than one, aufs has to decide
+the target branch for file creation or copy-up. By default, the highest
+writable branch which has the parent (or ancestor) dir of the target
+file is chosen (top-down-parent policy).
+By user's request, aufs implements some other policies to select the
+writable branch, for file creation several policies, round-robin,
+most-free-space, and other policies. For copy-up, top-down-parent,
+bottom-up-parent, bottom-up and others.
+
+As expected, the round-robin policy selects the branch in circular. When
+you have two writable branches and creates 10 new files, 5 files will be
+created for each branch. mkdir(2) systemcall is an exception. When you
+create 10 new directories, all will be created on the same branch.
+And the most-free-space policy selects the one which has most free
+space among the writable branches. The amount of free space will be
+checked by aufs internally, and users can specify its time interval.
+
+The policies for copy-up is more simple,
+top-down-parent is equivalent to the same named on in create policy,
+bottom-up-parent selects the writable branch where the parent dir
+exists and the nearest upper one from the copyup-source,
+bottom-up selects the nearest upper writable branch from the
+copyup-source, regardless the existence of the parent dir.
+
+There are some rules or exceptions to apply these policies.
+- If there is a readonly branch above the policy-selected branch and
+  the parent dir is marked as opaque (a variation of whiteout), or the
+  target (creating) file is whiteout-ed on the upper readonly branch,
+  then the result of the policy is ignored and the target file will be
+  created on the nearest upper writable branch than the readonly branch.
+- If there is a writable branch above the policy-selected branch and
+  the parent dir is marked as opaque or the target file is whiteouted
+  on the branch, then the result of the policy is ignored and the target
+  file will be created on the highest one among the upper writable
+  branches who has diropq or whiteout. In case of whiteout, aufs removes
+  it as usual.
+- link(2) and rename(2) systemcalls are exceptions in every policy.
+  They try selecting the branch where the source exists as possible
+  since copyup a large file will take long time. If it can't be,
+  ie. the branch where the source exists is readonly, then they will
+  follow the copyup policy.
+- There is an exception for rename(2) when the target exists.
+  If the rename target exists, aufs compares the index of the branches
+  where the source and the target exists and selects the higher
+  one. If the selected branch is readonly, then aufs follows the
+  copyup policy.
diff --git a/Documentation/filesystems/aufs/design/06fhsm.txt b/Documentation/filesystems/aufs/design/06fhsm.txt
new file mode 100644
index 000000000000..9216478d803d
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/06fhsm.txt
@@ -0,0 +1,120 @@
+
+# Copyright (C) 2011-2017 Junjiro R. Okajima
+# 
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+
+
+File-based Hierarchical Storage Management (FHSM)
+----------------------------------------------------------------------
+Hierarchical Storage Management (or HSM) is a well-known feature in the
+storage world. Aufs provides this feature as file-based with multiple
+writable branches, based upon the principle of "Colder, the Lower".
+Here the word "colder" means that the less used files, and "lower" means
+that the position in the order of the stacked branches vertically.
+These multiple writable branches are prioritized, ie. the topmost one
+should be the fastest drive and be used heavily.
+
+o Characters in aufs FHSM story
+- aufs itself and a new branch attribute.
+- a new ioctl interface to move-down and to establish a connection with
+  the daemon ("move-down" is a converse of "copy-up").
+- userspace tool and daemon.
+
+The userspace daemon establishes a connection with aufs and waits for
+the notification. The notified information is very similar to struct
+statfs containing the number of consumed blocks and inodes.
+When the consumed blocks/inodes of a branch exceeds the user-specified
+upper watermark, the daemon activates its move-down process until the
+consumed blocks/inodes reaches the user-specified lower watermark.
+
+The actual move-down is done by aufs based upon the request from
+user-space since we need to maintain the inode number and the internal
+pointer arrays in aufs.
+
+Currently aufs FHSM handles the regular files only. Additionally they
+must not be hard-linked nor pseudo-linked.
+
+
+o Cowork of aufs and the user-space daemon
+  During the userspace daemon established the connection, aufs sends a
+  small notification to it whenever aufs writes something into the
+  writable branch. But it may cost high since aufs issues statfs(2)
+  internally. So user can specify a new option to cache the
+  info. Actually the notification is controlled by these factors.
+  + the specified cache time.
+  + classified as "force" by aufs internally.
+  Until the specified time expires, aufs doesn't send the info
+  except the forced cases. When aufs decide forcing, the info is always
+  notified to userspace.
+  For example, the number of free inodes is generally large enough and
+  the shortage of it happens rarely. So aufs doesn't force the
+  notification when creating a new file, directory and others. This is
+  the typical case which aufs doesn't force.
+  When aufs writes the actual filedata and the files consumes any of new
+  blocks, the aufs forces notifying.
+
+
+o Interfaces in aufs
+- New branch attribute.
+  + fhsm
+    Specifies that the branch is managed by FHSM feature. In other word,
+    participant in the FHSM.
+    When nofhsm is set to the branch, it will not be the source/target
+    branch of the move-down operation. This attribute is set
+    independently from coo and moo attributes, and if you want full
+    FHSM, you should specify them as well.
+- New mount option.
+  + fhsm_sec
+    Specifies a second to suppress many less important info to be
+    notified.
+- New ioctl.
+  + AUFS_CTL_FHSM_FD
+    create a new file descriptor which userspace can read the notification
+    (a subset of struct statfs) from aufs.
+- Module parameter 'brs'
+  It has to be set to 1. Otherwise the new mount option 'fhsm' will not
+  be set.
+- mount helpers /sbin/mount.aufs and /sbin/umount.aufs
+  When there are two or more branches with fhsm attributes,
+  /sbin/mount.aufs invokes the user-space daemon and /sbin/umount.aufs
+  terminates it. As a result of remounting and branch-manipulation, the
+  number of branches with fhsm attribute can be one. In this case,
+  /sbin/mount.aufs will terminate the user-space daemon.
+
+
+Finally the operation is done as these steps in kernel-space.
+- make sure that,
+  + no one else is using the file.
+  + the file is not hard-linked.
+  + the file is not pseudo-linked.
+  + the file is a regular file.
+  + the parent dir is not opaqued.
+- find the target writable branch.
+- make sure the file is not whiteout-ed by the upper (than the target)
+  branch.
+- make the parent dir on the target branch.
+- mutex lock the inode on the branch.
+- unlink the whiteout on the target branch (if exists).
+- lookup and create the whiteout-ed temporary name on the target branch.
+- copy the file as the whiteout-ed temporary name on the target branch.
+- rename the whiteout-ed temporary name to the original name.
+- unlink the file on the source branch.
+- maintain the internal pointer array and the external inode number
+  table (XINO).
+- maintain the timestamps and other attributes of the parent dir and the
+  file.
+
+And of course, in every step, an error may happen. So the operation
+should restore the original file state after an error happens.
diff --git a/Documentation/filesystems/aufs/design/06mmap.txt b/Documentation/filesystems/aufs/design/06mmap.txt
new file mode 100644
index 000000000000..8fe4b6cd379d
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/06mmap.txt
@@ -0,0 +1,72 @@
+
+# Copyright (C) 2005-2017 Junjiro R. Okajima
+# 
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+mmap(2) -- File Memory Mapping
+----------------------------------------------------------------------
+In aufs, the file-mapped pages are handled by a branch fs directly, no
+interaction with aufs. It means aufs_mmap() calls the branch fs's
+->mmap().
+This approach is simple and good, but there is one problem.
+Under /proc, several entries show the mmapped files by its path (with
+device and inode number), and the printed path will be the path on the
+branch fs's instead of virtual aufs's.
+This is not a problem in most cases, but some utilities lsof(1) (and its
+user) may expect the path on aufs.
+
+To address this issue, aufs adds a new member called vm_prfile in struct
+vm_area_struct (and struct vm_region). The original vm_file points to
+the file on the branch fs in order to handle everything correctly as
+usual. The new vm_prfile points to a virtual file in aufs, and the
+show-functions in procfs refers to vm_prfile if it is set.
+Also we need to maintain several other places where touching vm_file
+such like
+- fork()/clone() copies vma and the reference count of vm_file is
+  incremented.
+- merging vma maintains the ref count too.
+
+This is not a good approach. It just fakes the printed path. But it
+leaves all behaviour around f_mapping unchanged. This is surely an
+advantage.
+Actually aufs had adopted another complicated approach which calls
+generic_file_mmap() and handles struct vm_operations_struct. In this
+approach, aufs met a hard problem and I could not solve it without
+switching the approach.
+
+There may be one more another approach which is
+- bind-mount the branch-root onto the aufs-root internally
+- grab the new vfsmount (ie. struct mount)
+- lazy-umount the branch-root internally
+- in open(2) the aufs-file, open the branch-file with the hidden
+  vfsmount (instead of the original branch's vfsmount)
+- ideally this "bind-mount and lazy-umount" should be done atomically,
+  but it may be possible from userspace by the mount helper.
+
+Adding the internal hidden vfsmount and using it in opening a file, the
+file path under /proc will be printed correctly. This approach looks
+smarter, but is not possible I am afraid.
+- aufs-root may be bind-mount later. when it happens, another hidden
+  vfsmount will be required.
+- it is hard to get the chance to bind-mount and lazy-umount
+  + in kernel-space, FS can have vfsmount in open(2) via
+    file->f_path, and aufs can know its vfsmount. But several locks are
+    already acquired, and if aufs tries to bind-mount and lazy-umount
+    here, then it may cause a deadlock.
+  + in user-space, bind-mount doesn't invoke the mount helper.
+- since /proc shows dev and ino, aufs has to give vma these info. it
+  means a new member vm_prinode will be necessary. this is essentially
+  equivalent to vm_prfile described above.
+
+I have to give up this "looks-smater" approach.
diff --git a/Documentation/filesystems/aufs/design/06xattr.txt b/Documentation/filesystems/aufs/design/06xattr.txt
new file mode 100644
index 000000000000..37cdb4e795e4
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/06xattr.txt
@@ -0,0 +1,96 @@
+
+# Copyright (C) 2014-2017 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+
+
+Listing XATTR/EA and getting the value
+----------------------------------------------------------------------
+For the inode standard attributes (owner, group, timestamps, etc.), aufs
+shows the values from the topmost existing file. This behaviour is good
+for the non-dir entries since the bahaviour exactly matches the shown
+information. But for the directories, aufs considers all the same named
+entries on the lower branches. Which means, if one of the lower entry
+rejects readdir call, then aufs returns an error even if the topmost
+entry allows it. This behaviour is necessary to respect the branch fs's
+security, but can make users confused since the user-visible standard
+attributes don't match the behaviour.
+To address this issue, aufs has a mount option called dirperm1 which
+checks the permission for the topmost entry only, and ignores the lower
+entry's permission.
+
+A similar issue can happen around XATTR.
+getxattr(2) and listxattr(2) families behave as if dirperm1 option is
+always set. Otherwise these very unpleasant situation would happen.
+- listxattr(2) may return the duplicated entries.
+- users may not be able to remove or reset the XATTR forever,
+
+
+XATTR/EA support in the internal (copy,move)-(up,down)
+----------------------------------------------------------------------
+Generally the extended attributes of inode are categorized as these.
+- "security" for LSM and capability.
+- "system" for posix ACL, 'acl' mount option is required for the branch
+  fs generally.
+- "trusted" for userspace, CAP_SYS_ADMIN is required.
+- "user" for userspace, 'user_xattr' mount option is required for the
+  branch fs generally.
+
+Moreover there are some other categories. Aufs handles these rather
+unpopular categories as the ordinary ones, ie. there is no special
+condition nor exception.
+
+In copy-up, the support for XATTR on the dst branch may differ from the
+src branch. In this case, the copy-up operation will get an error and
+the original user operation which triggered the copy-up will fail. It
+can happen that even all copy-up will fail.
+When both of src and dst branches support XATTR and if an error occurs
+during copying XATTR, then the copy-up should fail obviously. That is a
+good reason and aufs should return an error to userspace. But when only
+the src branch support that XATTR, aufs should not return an error.
+For example, the src branch supports ACL but the dst branch doesn't
+because the dst branch may natively un-support it or temporary
+un-support it due to "noacl" mount option. Of course, the dst branch fs
+may NOT return an error even if the XATTR is not supported. It is
+totally up to the branch fs.
+
+Anyway when the aufs internal copy-up gets an error from the dst branch
+fs, then aufs tries removing the just copied entry and returns the error
+to the userspace. The worst case of this situation will be all copy-up
+will fail.
+
+For the copy-up operation, there two basic approaches.
+- copy the specified XATTR only (by category above), and return the
+  error unconditionally if it happens.
+- copy all XATTR, and ignore the error on the specified category only.
+
+In order to support XATTR and to implement the correct behaviour, aufs
+chooses the latter approach and introduces some new branch attributes,
+"icexsec", "icexsys", "icextr", "icexusr", and "icexoth".
+They correspond to the XATTR namespaces (see above). Additionally, to be
+convenient, "icex" is also provided which means all "icex*" attributes
+are set (here the word "icex" stands for "ignore copy-error on XATTR").
+
+The meaning of these attributes is to ignore the error from setting
+XATTR on that branch.
+Note that aufs tries copying all XATTR unconditionally, and ignores the
+error from the dst branch according to the specified attributes.
+
+Some XATTR may have its default value. The default value may come from
+the parent dir or the environment. If the default value is set at the
+file creating-time, it will be overwritten by copy-up.
+Some contradiction may happen I am afraid.
+Do we need another attribute to stop copying XATTR? I am unsure. For
+now, aufs implements the branch attributes to ignore the error.
diff --git a/Documentation/filesystems/aufs/design/07export.txt b/Documentation/filesystems/aufs/design/07export.txt
new file mode 100644
index 000000000000..cd4ee6b61833
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/07export.txt
@@ -0,0 +1,58 @@
+
+# Copyright (C) 2005-2017 Junjiro R. Okajima
+# 
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Export Aufs via NFS
+----------------------------------------------------------------------
+Here is an approach.
+- like xino/xib, add a new file 'xigen' which stores aufs inode
+  generation.
+- iget_locked(): initialize aufs inode generation for a new inode, and
+  store it in xigen file.
+- destroy_inode(): increment aufs inode generation and store it in xigen
+  file. it is necessary even if it is not unlinked, because any data of
+  inode may be changed by UDBA.
+- encode_fh(): for a root dir, simply return FILEID_ROOT. otherwise
+  build file handle by
+  + branch id (4 bytes)
+  + superblock generation (4 bytes)
+  + inode number (4 or 8 bytes)
+  + parent dir inode number (4 or 8 bytes)
+  + inode generation (4 bytes))
+  + return value of exportfs_encode_fh() for the parent on a branch (4
+    bytes)
+  + file handle for a branch (by exportfs_encode_fh())
+- fh_to_dentry():
+  + find the index of a branch from its id in handle, and check it is
+    still exist in aufs.
+  + 1st level: get the inode number from handle and search it in cache.
+  + 2nd level: if not found in cache, get the parent inode number from
+    the handle and search it in cache. and then open the found parent
+    dir, find the matching inode number by vfs_readdir() and get its
+    name, and call lookup_one_len() for the target dentry.
+  + 3rd level: if the parent dir is not cached, call
+    exportfs_decode_fh() for a branch and get the parent on a branch,
+    build a pathname of it, convert it a pathname in aufs, call
+    path_lookup(). now aufs gets a parent dir dentry, then handle it as
+    the 2nd level.
+  + to open the dir, aufs needs struct vfsmount. aufs keeps vfsmount
+    for every branch, but not itself. to get this, (currently) aufs
+    searches in current->nsproxy->mnt_ns list. it may not be a good
+    idea, but I didn't get other approach.
+  + test the generation of the gotten inode.
+- every inode operation: they may get EBUSY due to UDBA. in this case,
+  convert it into ESTALE for NFSD.
+- readdir(): call lockdep_on/off() because filldir in NFSD calls
+  lookup_one_len(), vfs_getattr(), encode_fh() and others.
diff --git a/Documentation/filesystems/aufs/design/08shwh.txt b/Documentation/filesystems/aufs/design/08shwh.txt
new file mode 100644
index 000000000000..7e07e2609ec3
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/08shwh.txt
@@ -0,0 +1,52 @@
+
+# Copyright (C) 2005-2017 Junjiro R. Okajima
+# 
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Show Whiteout Mode (shwh)
+----------------------------------------------------------------------
+Generally aufs hides the name of whiteouts. But in some cases, to show
+them is very useful for users. For instance, creating a new middle layer
+(branch) by merging existing layers.
+
+(borrowing aufs1 HOW-TO from a user, Michael Towers)
+When you have three branches,
+- Bottom: 'system', squashfs (underlying base system), read-only
+- Middle: 'mods', squashfs, read-only
+- Top: 'overlay', ram (tmpfs), read-write
+
+The top layer is loaded at boot time and saved at shutdown, to preserve
+the changes made to the system during the session.
+When larger changes have been made, or smaller changes have accumulated,
+the size of the saved top layer data grows. At this point, it would be
+nice to be able to merge the two overlay branches ('mods' and 'overlay')
+and rewrite the 'mods' squashfs, clearing the top layer and thus
+restoring save and load speed.
+
+This merging is simplified by the use of another aufs mount, of just the
+two overlay branches using the 'shwh' option.
+# mount -t aufs -o ro,shwh,br:/livesys/overlay=ro+wh:/livesys/mods=rr+wh \
+	aufs /livesys/merge_union
+
+A merged view of these two branches is then available at
+/livesys/merge_union, and the new feature is that the whiteouts are
+visible!
+Note that in 'shwh' mode the aufs mount must be 'ro', which will disable
+writing to all branches. Also the default mode for all branches is 'ro'.
+It is now possible to save the combined contents of the two overlay
+branches to a new squashfs, e.g.:
+# mksquashfs /livesys/merge_union /path/to/newmods.squash
+
+This new squashfs archive can be stored on the boot device and the
+initramfs will use it to replace the old one at the next boot.
diff --git a/Documentation/filesystems/aufs/design/10dynop.txt b/Documentation/filesystems/aufs/design/10dynop.txt
new file mode 100644
index 000000000000..b7ba75d8843a
--- /dev/null
+++ b/Documentation/filesystems/aufs/design/10dynop.txt
@@ -0,0 +1,47 @@
+
+# Copyright (C) 2010-2017 Junjiro R. Okajima
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Dynamically customizable FS operations
+----------------------------------------------------------------------
+Generally FS operations (struct inode_operations, struct
+address_space_operations, struct file_operations, etc.) are defined as
+"static const", but it never means that FS have only one set of
+operation. Some FS have multiple sets of them. For instance, ext2 has
+three sets, one for XIP, for NOBH, and for normal.
+Since aufs overrides and redirects these operations, sometimes aufs has
+to change its behaviour according to the branch FS type. More importantly
+VFS acts differently if a function (member in the struct) is set or
+not. It means aufs should have several sets of operations and select one
+among them according to the branch FS definition.
+
+In order to solve this problem and not to affect the behaviour of VFS,
+aufs defines these operations dynamically. For instance, aufs defines
+dummy direct_IO function for struct address_space_operations, but it may
+not be set to the address_space_operations actually. When the branch FS
+doesn't have it, aufs doesn't set it to its address_space_operations
+while the function definition itself is still alive. So the behaviour
+itself will not change, and it will return an error when direct_IO is
+not set.
+
+The lifetime of these dynamically generated operation object is
+maintained by aufs branch object. When the branch is removed from aufs,
+the reference counter of the object is decremented. When it reaches
+zero, the dynamically generated operation object will be freed.
+
+This approach is designed to support AIO (io_submit), Direct I/O and
+XIP (DAX) mainly.
+Currently this approach is applied to address_space_operations for
+regular files only.
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index f67ed33d1054..81a8802cea88 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3737,9 +3737,11 @@ EOI was received.
 #define KVM_EXIT_HYPERV_SYNIC          1
 #define KVM_EXIT_HYPERV_HCALL          2
 			__u32 type;
+			__u32 pad1;
 			union {
 				struct {
 					__u32 msr;
+					__u32 pad2;
 					__u64 control;
 					__u64 evt_page;
 					__u64 msg_page;
diff --git a/MAINTAINERS b/MAINTAINERS
index e2dd302345c2..0230a119f052 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2465,6 +2465,19 @@ F:	include/linux/audit.h
 F:	include/uapi/linux/audit.h
 F:	kernel/audit*
 
+AUFS (advanced multi layered unification filesystem) FILESYSTEM
+M:	"J. R. Okajima" <hooanon05g@gmail.com>
+L:	linux-unionfs@vger.kernel.org
+L:	aufs-users@lists.sourceforge.net (members only)
+W:	http://aufs.sourceforge.net
+T:	git://github.com/sfjro/aufs4-linux.git
+S:	Supported
+F:	Documentation/filesystems/aufs/
+F:	Documentation/ABI/testing/debugfs-aufs
+F:	Documentation/ABI/testing/sysfs-aufs
+F:	fs/aufs/
+F:	include/uapi/linux/aufs_type.h
+
 AUXILIARY DISPLAY DRIVERS
 M:	Miguel Ojeda Sandonis <miguel.ojeda.sandonis@gmail.com>
 W:	http://miguelojeda.es/auxdisplay.htm
diff --git a/Makefile b/Makefile
index 591582e26a57..058375d90dae 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 14
-SUBLEVEL = 182
+SUBLEVEL = 202
 EXTRAVERSION =
 NAME = Petit Gorille
 
@@ -450,7 +450,7 @@ export MODVERDIR := $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/).tmp_ve
 # Files to ignore in find ... statements
 
 export RCS_FIND_IGNORE := \( -name SCCS -o -name BitKeeper -o -name .svn -o    \
-			  -name CVS -o -name .pc -o -name .hg -o -name .git \) \
+			  -name CVS -o -name .pc -o -name .hg -o -name .git -o -name meta \) \
 			  -prune -o
 export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn \
 			 --exclude CVS --exclude .pc --exclude .hg --exclude .git
@@ -482,7 +482,7 @@ ifeq ($(cc-name),clang)
 ifneq ($(CROSS_COMPILE),)
 CLANG_FLAGS	+= --target=$(notdir $(CROSS_COMPILE:%-=%))
 GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit))
-CLANG_FLAGS	+= --prefix=$(GCC_TOOLCHAIN_DIR)
+CLANG_FLAGS	+= --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE))
 GCC_TOOLCHAIN	:= $(realpath $(GCC_TOOLCHAIN_DIR)/..)
 endif
 ifneq ($(GCC_TOOLCHAIN),)
@@ -542,12 +542,8 @@ KBUILD_MODULES :=
 KBUILD_BUILTIN := 1
 
 # If we have only "make modules", don't compile built-in objects.
-# When we're building modules with modversions, we need to consider
-# the built-in objects during the descend as well, in order to
-# make sure the checksums are up to date before we record them.
-
 ifeq ($(MAKECMDGOALS),modules)
-  KBUILD_BUILTIN := $(if $(CONFIG_MODVERSIONS),1)
+  KBUILD_BUILTIN :=
 endif
 
 # If we have "make <whatever> modules", compile modules
@@ -1249,6 +1245,13 @@ ifdef CONFIG_MODULES
 
 all: modules
 
+# When we're building modules with modversions, we need to consider
+# the built-in objects during the descend as well, in order to
+# make sure the checksums are up to date before we record them.
+ifdef CONFIG_MODVERSIONS
+  KBUILD_BUILTIN := 1
+endif
+
 # Build modules
 #
 # A module can be listed more than once in obj-m resulting in
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index d123ff90f7a8..9995bed6e92e 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -493,10 +493,10 @@ extern inline void writeq(u64 b, volatile void __iomem *addr)
 }
 #endif
 
-#define ioread16be(p) be16_to_cpu(ioread16(p))
-#define ioread32be(p) be32_to_cpu(ioread32(p))
-#define iowrite16be(v,p) iowrite16(cpu_to_be16(v), (p))
-#define iowrite32be(v,p) iowrite32(cpu_to_be32(v), (p))
+#define ioread16be(p) swab16(ioread16(p))
+#define ioread32be(p) swab32(ioread32(p))
+#define iowrite16be(v,p) iowrite16(swab16(v), (p))
+#define iowrite32be(v,p) iowrite32(swab32(v), (p))
 
 #define inb_p		inb
 #define inw_p		inw
diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index 87d8c4f0307d..7295967b5028 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -30,11 +30,13 @@
  * Address valid if:
  *  - "addr" doesn't have any high-bits set
  *  - AND "size" doesn't have any high-bits set
- *  - AND "addr+size" doesn't have any high-bits set
+ *  - AND "addr+size-(size != 0)" doesn't have any high-bits set
  *  - OR we are in kernel mode.
  */
-#define __access_ok(addr, size) \
-	((get_fs().seg & (addr | size | (addr+size))) == 0)
+#define __access_ok(addr, size) ({				\
+	unsigned long __ao_a = (addr), __ao_b = (size);		\
+	unsigned long __ao_end = __ao_a + __ao_b - !!__ao_b;	\
+	(get_fs().seg & (__ao_a | __ao_b | __ao_end)) == 0; })
 
 #define access_ok(type, addr, size)			\
 ({							\
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 57d81c6aa379..75aa3a8f9fdc 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -79,6 +79,8 @@
 
 	arcpct: pct {
 		compatible = "snps,archs-pct";
+		interrupt-parent = <&cpu_intc>;
+		interrupts = <20>;
 	};
 
 	/* TIMER0 with interrupt for clockevent */
@@ -161,7 +163,7 @@
 			reg = <0x8000 0x2000>;
 			interrupts = <10>;
 			interrupt-names = "macirq";
-			phy-mode = "rgmii";
+			phy-mode = "rgmii-id";
 			snps,pbl = <32>;
 			snps,multicast-filter-bins = <256>;
 			clocks = <&gmacclk>;
@@ -177,7 +179,7 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				compatible = "snps,dwmac-mdio";
-				phy0: ethernet-phy@0 {
+				phy0: ethernet-phy@0 { /* Micrel KSZ9031 */
 					reg = <0>;
 					ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>;
 					ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>;
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index aa2d6da9d187..12c74e826530 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -26,7 +26,7 @@
 #define  R_ARC_32_PCREL		0x31
 
 /*to set parameters in the core dumps */
-#define ELF_ARCH		EM_ARCOMPACT
+#define ELF_ARCH		EM_ARC_INUSE
 #define ELF_CLASS		ELFCLASS32
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 85d9ea4a0acc..705a68208423 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -156,7 +156,6 @@ END(EV_Extension)
 tracesys:
 	; save EFA in case tracer wants the PC of traced task
 	; using ERET won't work since next-PC has already committed
-	lr  r12, [efa]
 	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r11
 	st  r12, [r11, THREAD_FAULT_ADDR]	; thread.fault_address
 
@@ -199,15 +198,9 @@ tracesys_exit:
 ; Breakpoint TRAP
 ; ---------------------------------------------
 trap_with_param:
-
-	; stop_pc info by gdb needs this info
-	lr  r0, [efa]
+	mov r0, r12	; EFA in case ptracer/gdb wants stop_pc
 	mov r1, sp
 
-	; Now that we have read EFA, it is safe to do "fake" rtie
-	;   and get out of CPU exception mode
-	FAKE_RET_FROM_EXCPN
-
 	; Save callee regs in case gdb wants to have a look
 	; SP will grow up by size of CALLEE Reg-File
 	; NOTE: clobbers r12
@@ -234,6 +227,10 @@ ENTRY(EV_Trap)
 
 	EXCEPTION_PROLOGUE
 
+	lr  r12, [efa]
+
+	FAKE_RET_FROM_EXCPN
+
 	;============ TRAP 1   :breakpoints
 	; Check ECR for trap with arg (PROLOGUE ensures r9 has ECR)
 	bmsk.f 0, r9, 7
@@ -241,9 +238,6 @@ ENTRY(EV_Trap)
 
 	;============ TRAP  (no param): syscall top level
 
-	; First return from Exception to pure K mode (Exception/IRQs renabled)
-	FAKE_RET_FROM_EXCPN
-
 	; If syscall tracing ongoing, invoke pre-post-hooks
 	GET_CURR_THR_INFO_FLAGS   r10
 	btst r10, TIF_SYSCALL_TRACE
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 6b8d106e0d53..11c2c4a3fe69 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -15,6 +15,7 @@
 #include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <linux/cpu.h>
 #include <linux/of_fdt.h>
 #include <linux/of.h>
@@ -355,12 +356,12 @@ static void arc_chk_core_config(void)
 	if ((unsigned int)__arc_dccm_base != cpu->dccm.base_addr)
 		panic("Linux built with incorrect DCCM Base address\n");
 
-	if (CONFIG_ARC_DCCM_SZ != cpu->dccm.sz)
+	if (CONFIG_ARC_DCCM_SZ * SZ_1K != cpu->dccm.sz)
 		panic("Linux built with incorrect DCCM Size\n");
 #endif
 
 #ifdef CONFIG_ARC_HAS_ICCM
-	if (CONFIG_ARC_ICCM_SZ != cpu->iccm.sz)
+	if (CONFIG_ARC_ICCM_SZ * SZ_1K != cpu->iccm.sz)
 		panic("Linux built with incorrect ICCM Size\n");
 #endif
 
diff --git a/arch/arc/plat-eznps/Kconfig b/arch/arc/plat-eznps/Kconfig
index ce908e2c5282..71378bfec8d0 100644
--- a/arch/arc/plat-eznps/Kconfig
+++ b/arch/arc/plat-eznps/Kconfig
@@ -6,6 +6,7 @@
 
 menuconfig ARC_PLAT_EZNPS
 	bool "\"EZchip\" ARC dev platform"
+	depends on ISA_ARCOMPACT
 	select CPU_BIG_ENDIAN
 	select CLKSRC_NPS if !PHYS_ADDR_T_64BIT
 	select EZNPS_GIC
diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h
index 4f6a1673b3a6..ddfca2c3357a 100644
--- a/arch/arc/plat-eznps/include/plat/ctop.h
+++ b/arch/arc/plat-eznps/include/plat/ctop.h
@@ -43,7 +43,6 @@
 #define CTOP_AUX_DPC				(CTOP_AUX_BASE + 0x02C)
 #define CTOP_AUX_LPC				(CTOP_AUX_BASE + 0x030)
 #define CTOP_AUX_EFLAGS				(CTOP_AUX_BASE + 0x080)
-#define CTOP_AUX_IACK				(CTOP_AUX_BASE + 0x088)
 #define CTOP_AUX_GPA1				(CTOP_AUX_BASE + 0x08C)
 #define CTOP_AUX_UDMC				(CTOP_AUX_BASE + 0x300)
 
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 234ee43b4438..f546c1606acc 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -334,6 +334,9 @@ PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
 bootpImage uImage: zImage
 zImage: Image
 
+# These targets cannot be built in parallel
+.NOTPARALLEL: $(BOOT_TARGETS)
+
 $(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 	@$(kecho) '  Kernel: $(boot)/$@ is ready'
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 50f8d1be7fcb..1af29e09a0fc 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -57,6 +57,10 @@ $(obj)/zImage:	$(obj)/compressed/vmlinux FORCE
 
 endif
 
+ifeq ($(CONFIG_ARCH_VEXPRESS), y)
+LOADADDR=0x04080000
+endif
+
 ifneq ($(LOADADDR),)
   UIMAGE_LOADADDR=$(LOADADDR)
 else
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index 1792192001a2..e975f9cabe84 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -249,10 +249,10 @@
 			status = "disabled";
 		};
 
-		mailbox: mailbox@25000 {
+		mailbox: mailbox@25c00 {
 			compatible = "brcm,iproc-fa2-mbox";
-			reg = <0x25000 0x445>;
-			interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>;
+			reg = <0x25c00 0x400>;
+			interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>;
 			#mbox-cells = <1>;
 			brcm,rx-status-len = <32>;
 			brcm,use-bcm-hdr;
diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
index e5f2cca86f04..120776d45441 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
@@ -25,7 +25,7 @@
 
 	leds {
 		act {
-			gpios = <&gpio 47 GPIO_ACTIVE_HIGH>;
+			gpios = <&gpio 47 GPIO_ACTIVE_LOW>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 501877e87a5b..dffa8b9bd536 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -426,7 +426,7 @@
 	};
 
 	spi@18029200 {
-		compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+		compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 		reg = <0x18029200 0x184>,
 		      <0x18029000 0x124>,
 		      <0x1811b408 0x004>,
diff --git a/arch/arm/boot/dts/imx6q-b450v3.dts b/arch/arm/boot/dts/imx6q-b450v3.dts
index 404a93d9596b..dc7d65da7d01 100644
--- a/arch/arm/boot/dts/imx6q-b450v3.dts
+++ b/arch/arm/boot/dts/imx6q-b450v3.dts
@@ -65,13 +65,6 @@
 	};
 };
 
-&clks {
-	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
-	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>,
-				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
-};
-
 &ldb {
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/imx6q-b650v3.dts b/arch/arm/boot/dts/imx6q-b650v3.dts
index 7f9f176901d4..101d61f93070 100644
--- a/arch/arm/boot/dts/imx6q-b650v3.dts
+++ b/arch/arm/boot/dts/imx6q-b650v3.dts
@@ -65,13 +65,6 @@
 	};
 };
 
-&clks {
-	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
-	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>,
-				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
-};
-
 &ldb {
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/imx6q-b850v3.dts b/arch/arm/boot/dts/imx6q-b850v3.dts
index 46bdc6722715..8fc831dc3156 100644
--- a/arch/arm/boot/dts/imx6q-b850v3.dts
+++ b/arch/arm/boot/dts/imx6q-b850v3.dts
@@ -53,17 +53,6 @@
 	};
 };
 
-&clks {
-	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>,
-			  <&clks IMX6QDL_CLK_IPU1_DI0_PRE_SEL>,
-			  <&clks IMX6QDL_CLK_IPU2_DI0_PRE_SEL>;
-	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
-				 <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
-				 <&clks IMX6QDL_CLK_PLL2_PFD2_396M>,
-				 <&clks IMX6QDL_CLK_PLL2_PFD2_396M>;
-};
-
 &ldb {
 	fsl,dual-channel;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
index 1015e55ca8f7..f3c2c5587616 100644
--- a/arch/arm/boot/dts/imx6q-bx50v3.dtsi
+++ b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
@@ -92,6 +92,56 @@
 		mux-int-port = <1>;
 		mux-ext-port = <4>;
 	};
+
+	aliases {
+		mdio-gpio0 = &mdio0;
+	};
+
+	mdio0: mdio-gpio {
+		compatible = "virtual,mdio-gpio";
+		gpios = <&gpio2 5 GPIO_ACTIVE_HIGH>, /* mdc */
+			<&gpio2 7 GPIO_ACTIVE_HIGH>; /* mdio */
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		switch@0 {
+			compatible = "marvell,mv88e6085"; /* 88e6240*/
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+
+			switch_ports: ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+
+			mdio {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				switchphy0: switchphy@0 {
+					reg = <0>;
+				};
+
+				switchphy1: switchphy@1 {
+					reg = <1>;
+				};
+
+				switchphy2: switchphy@2 {
+					reg = <2>;
+				};
+
+				switchphy3: switchphy@3 {
+					reg = <3>;
+				};
+
+				switchphy4: switchphy@4 {
+					reg = <4>;
+				};
+			};
+		};
+	};
 };
 
 &ecspi5 {
@@ -326,3 +376,30 @@
 		tcxo-clock-frequency = <26000000>;
 	};
 };
+
+&pcie {
+	/* Synopsys, Inc. Device */
+	pci_root: root@0,0 {
+		compatible = "pci16c3,abcd";
+		reg = <0x00000000 0 0 0 0>;
+
+		#address-cells = <3>;
+		#size-cells = <2>;
+		#interrupt-cells = <1>;
+	};
+};
+
+&clks {
+	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
+			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>,
+			  <&clks IMX6QDL_CLK_IPU1_DI0_PRE_SEL>,
+			  <&clks IMX6QDL_CLK_IPU1_DI1_PRE_SEL>,
+			  <&clks IMX6QDL_CLK_IPU2_DI0_PRE_SEL>,
+			  <&clks IMX6QDL_CLK_IPU2_DI1_PRE_SEL>;
+	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
+				 <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>;
+};
diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
index bcced922b280..b4779b0ece96 100644
--- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
+++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
@@ -16,8 +16,10 @@
 		#interrupt-cells = <2>;
 		#address-cells = <1>;
 		#size-cells = <0>;
-		spi-max-frequency = <3000000>;
+		spi-max-frequency = <9600000>;
 		spi-cs-high;
+		spi-cpol;
+		spi-cpha;
 
 		cpcap_adc: adc {
 			compatible = "motorola,mapphone-cpcap-adc";
diff --git a/arch/arm/boot/dts/rk3228-evb.dts b/arch/arm/boot/dts/rk3228-evb.dts
index 1be9daacc4f9..b69c842d8306 100644
--- a/arch/arm/boot/dts/rk3228-evb.dts
+++ b/arch/arm/boot/dts/rk3228-evb.dts
@@ -84,7 +84,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		phy: phy@0 {
+		phy: ethernet-phy@0 {
 			compatible = "ethernet-phy-id1234.d400", "ethernet-phy-ieee802.3-c22";
 			reg = <0>;
 			clocks = <&cru SCLK_MAC_PHY>;
diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi
index f59f7cc62be6..0c60dbc4b46a 100644
--- a/arch/arm/boot/dts/rk322x.dtsi
+++ b/arch/arm/boot/dts/rk322x.dtsi
@@ -950,7 +950,7 @@
 			};
 		};
 
-		spi-0 {
+		spi0 {
 			spi0_clk: spi0-clk {
 				rockchip,pins = <0 9 RK_FUNC_2 &pcfg_pull_up>;
 			};
@@ -968,7 +968,7 @@
 			};
 		};
 
-		spi-1 {
+		spi1 {
 			spi1_clk: spi1-clk {
 				rockchip,pins = <0 23 RK_FUNC_2 &pcfg_pull_up>;
 			};
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index 10d2fa183a9f..7ee99e11508c 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/arch/arm/boot/dts/socfpga.dtsi
@@ -706,7 +706,7 @@
 			};
 		};
 
-		L2: l2-cache@fffef000 {
+		L2: cache-controller@fffef000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xfffef000 0x1000>;
 			interrupts = <0 38 0x04>;
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index bd1985694bca..64f30676b285 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -606,7 +606,7 @@
 			reg = <0xffcfb100 0x80>;
 		};
 
-		L2: l2-cache@fffff000 {
+		L2: cache-controller@fffff000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xfffff000 0x1000>;
 			interrupts = <0 18 IRQ_TYPE_LEVEL_HIGH>;
@@ -779,7 +779,7 @@
 		timer3: timer3@ffd00100 {
 			compatible = "snps,dw-apb-timer";
 			interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>;
-			reg = <0xffd01000 0x100>;
+			reg = <0xffd00100 0x100>;
 			clocks = <&l4_sys_free_clk>;
 			clock-names = "timer";
 		};
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index 5d654b5b4ce6..53142ae1dba5 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -527,7 +527,7 @@
 			};
 
 			ocotp: ocotp@400a5000 {
-				compatible = "fsl,vf610-ocotp";
+				compatible = "fsl,vf610-ocotp", "syscon";
 				reg = <0x400a5000 0x1000>;
 				clocks = <&clks VF610_CLK_OCOTP>;
 			};
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 88286dd483ff..1935b580f0e8 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -21,11 +21,11 @@
 #endif
 
 #include <asm/ptrace.h>
-#include <asm/domain.h>
 #include <asm/opcodes-virt.h>
 #include <asm/asm-offsets.h>
 #include <asm/page.h>
 #include <asm/thread_info.h>
+#include <asm/uaccess-asm.h>
 
 #define IOMEM(x)	(x)
 
@@ -374,9 +374,9 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort, t=TUSER()
 9999:
 	.if	\inc == 1
-	\instr\cond\()b\()\t\().w \reg, [\ptr, #\off]
+	\instr\()b\t\cond\().w \reg, [\ptr, #\off]
 	.elseif	\inc == 4
-	\instr\cond\()\t\().w \reg, [\ptr, #\off]
+	\instr\t\cond\().w \reg, [\ptr, #\off]
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -415,9 +415,9 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.rept	\rept
 9999:
 	.if	\inc == 1
-	\instr\cond\()b\()\t \reg, [\ptr], #\inc
+	\instr\()b\t\cond \reg, [\ptr], #\inc
 	.elseif	\inc == 4
-	\instr\cond\()\t \reg, [\ptr], #\inc
+	\instr\t\cond \reg, [\ptr], #\inc
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -447,79 +447,6 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.size \name , . - \name
 	.endm
 
-	.macro	csdb
-#ifdef CONFIG_THUMB2_KERNEL
-	.inst.w	0xf3af8014
-#else
-	.inst	0xe320f014
-#endif
-	.endm
-
-	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
-#ifndef CONFIG_CPU_USE_DOMAINS
-	adds	\tmp, \addr, #\size - 1
-	sbcccs	\tmp, \tmp, \limit
-	bcs	\bad
-#ifdef CONFIG_CPU_SPECTRE
-	movcs	\addr, #0
-	csdb
-#endif
-#endif
-	.endm
-
-	.macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req
-#ifdef CONFIG_CPU_SPECTRE
-	sub	\tmp, \limit, #1
-	subs	\tmp, \tmp, \addr	@ tmp = limit - 1 - addr
-	addhs	\tmp, \tmp, #1		@ if (tmp >= 0) {
-	subhss	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
-	movlo	\addr, #0		@ if (tmp < 0) addr = NULL
-	csdb
-#endif
-	.endm
-
-	.macro	uaccess_disable, tmp, isb=1
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	/*
-	 * Whenever we re-enter userspace, the domains should always be
-	 * set appropriately.
-	 */
-	mov	\tmp, #DACR_UACCESS_DISABLE
-	mcr	p15, 0, \tmp, c3, c0, 0		@ Set domain register
-	.if	\isb
-	instr_sync
-	.endif
-#endif
-	.endm
-
-	.macro	uaccess_enable, tmp, isb=1
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	/*
-	 * Whenever we re-enter userspace, the domains should always be
-	 * set appropriately.
-	 */
-	mov	\tmp, #DACR_UACCESS_ENABLE
-	mcr	p15, 0, \tmp, c3, c0, 0
-	.if	\isb
-	instr_sync
-	.endif
-#endif
-	.endm
-
-	.macro	uaccess_save, tmp
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	mrc	p15, 0, \tmp, c3, c0, 0
-	str	\tmp, [sp, #SVC_DACR]
-#endif
-	.endm
-
-	.macro	uaccess_restore
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	ldr	r0, [sp, #SVC_DACR]
-	mcr	p15, 0, r0, c3, c0, 0
-#endif
-	.endm
-
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
 #if __LINUX_ARM_ARCH__ < 6
diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h
index a89b4076cde4..72821b4721ad 100644
--- a/arch/arm/include/asm/percpu.h
+++ b/arch/arm/include/asm/percpu.h
@@ -16,6 +16,8 @@
 #ifndef _ASM_ARM_PERCPU_H_
 #define _ASM_ARM_PERCPU_H_
 
+#include <asm/thread_info.h>
+
 /*
  * Same as asm-generic/percpu.h, except that we store the per cpu offset
  * in the TPIDRPRW. TPIDRPRW only exists on V6K and V7
diff --git a/arch/arm/include/asm/uaccess-asm.h b/arch/arm/include/asm/uaccess-asm.h
new file mode 100644
index 000000000000..907571fd05c6
--- /dev/null
+++ b/arch/arm/include/asm/uaccess-asm.h
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_UACCESS_ASM_H__
+#define __ASM_UACCESS_ASM_H__
+
+#include <asm/asm-offsets.h>
+#include <asm/domain.h>
+#include <asm/memory.h>
+#include <asm/thread_info.h>
+
+	.macro	csdb
+#ifdef CONFIG_THUMB2_KERNEL
+	.inst.w	0xf3af8014
+#else
+	.inst	0xe320f014
+#endif
+	.endm
+
+	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
+#ifndef CONFIG_CPU_USE_DOMAINS
+	adds	\tmp, \addr, #\size - 1
+	sbcscc	\tmp, \tmp, \limit
+	bcs	\bad
+#ifdef CONFIG_CPU_SPECTRE
+	movcs	\addr, #0
+	csdb
+#endif
+#endif
+	.endm
+
+	.macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req
+#ifdef CONFIG_CPU_SPECTRE
+	sub	\tmp, \limit, #1
+	subs	\tmp, \tmp, \addr	@ tmp = limit - 1 - addr
+	addhs	\tmp, \tmp, #1		@ if (tmp >= 0) {
+	subshs	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
+	movlo	\addr, #0		@ if (tmp < 0) addr = NULL
+	csdb
+#endif
+	.endm
+
+	.macro	uaccess_disable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_DISABLE
+	mcr	p15, 0, \tmp, c3, c0, 0		@ Set domain register
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+	.macro	uaccess_enable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_ENABLE
+	mcr	p15, 0, \tmp, c3, c0, 0
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+#if defined(CONFIG_CPU_SW_DOMAIN_PAN) || defined(CONFIG_CPU_USE_DOMAINS)
+#define DACR(x...)	x
+#else
+#define DACR(x...)
+#endif
+
+	/*
+	 * Save the address limit on entry to a privileged exception.
+	 *
+	 * If we are using the DACR for kernel access by the user accessors
+	 * (CONFIG_CPU_USE_DOMAINS=y), always reset the DACR kernel domain
+	 * back to client mode, whether or not \disable is set.
+	 *
+	 * If we are using SW PAN, set the DACR user domain to no access
+	 * if \disable is set.
+	 */
+	.macro	uaccess_entry, tsk, tmp0, tmp1, tmp2, disable
+	ldr	\tmp1, [\tsk, #TI_ADDR_LIMIT]
+	mov	\tmp2, #TASK_SIZE
+	str	\tmp2, [\tsk, #TI_ADDR_LIMIT]
+ DACR(	mrc	p15, 0, \tmp0, c3, c0, 0)
+ DACR(	str	\tmp0, [sp, #SVC_DACR])
+	str	\tmp1, [sp, #SVC_ADDR_LIMIT]
+	.if \disable && IS_ENABLED(CONFIG_CPU_SW_DOMAIN_PAN)
+	/* kernel=client, user=no access */
+	mov	\tmp2, #DACR_UACCESS_DISABLE
+	mcr	p15, 0, \tmp2, c3, c0, 0
+	instr_sync
+	.elseif IS_ENABLED(CONFIG_CPU_USE_DOMAINS)
+	/* kernel=client */
+	bic	\tmp2, \tmp0, #domain_mask(DOMAIN_KERNEL)
+	orr	\tmp2, \tmp2, #domain_val(DOMAIN_KERNEL, DOMAIN_CLIENT)
+	mcr	p15, 0, \tmp2, c3, c0, 0
+	instr_sync
+	.endif
+	.endm
+
+	/* Restore the user access state previously saved by uaccess_entry */
+	.macro	uaccess_exit, tsk, tmp0, tmp1
+	ldr	\tmp1, [sp, #SVC_ADDR_LIMIT]
+ DACR(	ldr	\tmp0, [sp, #SVC_DACR])
+	str	\tmp1, [\tsk, #TI_ADDR_LIMIT]
+ DACR(	mcr	p15, 0, \tmp0, c3, c0, 0)
+	.endm
+
+#undef DACR
+
+#endif /* __ASM_UACCESS_ASM_H__ */
diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h
index ef5dfedacd8d..628c336e8e3b 100644
--- a/arch/arm/include/asm/vfpmacros.h
+++ b/arch/arm/include/asm/vfpmacros.h
@@ -29,13 +29,13 @@
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
 	tst	\tmp, #HWCAP_VFPD32
-	ldcnel	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	ldclne	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
 	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
 	cmp	\tmp, #2			    @ 32 x 64bit registers?
-	ldceql	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	ldcleq	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
 #endif
@@ -53,13 +53,13 @@
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
 	tst	\tmp, #HWCAP_VFPD32
-	stcnel	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	stclne	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
 	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
 	cmp	\tmp, #2			    @ 32 x 64bit registers?
-	stceql	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	stcleq	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
 #endif
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index fbc707626b3e..f3de76f7ad43 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -30,6 +30,7 @@
 #include <asm/unistd.h>
 #include <asm/tls.h>
 #include <asm/system_info.h>
+#include <asm/uaccess-asm.h>
 
 #include "entry-header.S"
 #include <asm/entry-macro-multi.S>
@@ -186,15 +187,7 @@ ENDPROC(__und_invalid)
 	stmia	r7, {r2 - r6}
 
 	get_thread_info tsk
-	ldr	r0, [tsk, #TI_ADDR_LIMIT]
-	mov	r1, #TASK_SIZE
-	str	r1, [tsk, #TI_ADDR_LIMIT]
-	str	r0, [sp, #SVC_ADDR_LIMIT]
-
-	uaccess_save r0
-	.if \uaccess
-	uaccess_disable r0
-	.endif
+	uaccess_entry tsk, r0, r1, r2, \uaccess
 
 	.if \trace
 #ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 08a7132f5600..f64aca22f621 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -338,7 +338,8 @@ ENTRY(\sym)
  */
 	syscall_table_start sys_call_table
 #define COMPAT(nr, native, compat) syscall nr, native
-#ifdef CONFIG_AEABI
+
+#if defined(CONFIG_AEABI) && !defined(CONFIG_OABI_COMPAT)
 #include <calls-eabi.S>
 #else
 #include <calls-oabi.S>
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 62db1c9746cb..7b595f2d4a28 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -6,6 +6,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/errno.h>
 #include <asm/thread_info.h>
+#include <asm/uaccess-asm.h>
 #include <asm/v7m.h>
 
 @ Bad Abort numbers
@@ -217,9 +218,7 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
-	ldr	r1, [sp, #SVC_ADDR_LIMIT]
-	uaccess_restore
-	str	r1, [tsk, #TI_ADDR_LIMIT]
+	uaccess_exit tsk, r0, r1
 
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode SVC restore
@@ -263,9 +262,7 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
-	ldr	r1, [sp, #SVC_ADDR_LIMIT]
-	uaccess_restore
-	str	r1, [tsk, #TI_ADDR_LIMIT]
+	uaccess_exit tsk, r0, r1
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode restore
 	mov	r0, sp
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 7e662bdd5cb3..932b2244e709 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -101,6 +101,7 @@ __mmap_switched:
 	str	r2, [r6]			@ Save atags pointer
 	cmp	r7, #0
 	strne	r0, [r7]			@ Save control register values
+	mov	lr, #0
 	b	start_kernel
 ENDPROC(__mmap_switched)
 
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index af2a7f1e3103..a30f656f791f 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -688,6 +688,12 @@ static void disable_single_step(struct perf_event *bp)
 	arch_install_hw_breakpoint(bp);
 }
 
+static int watchpoint_fault_on_uaccess(struct pt_regs *regs,
+				       struct arch_hw_breakpoint *info)
+{
+	return !user_mode(regs) && info->ctrl.privilege == ARM_BREAKPOINT_USER;
+}
+
 static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 			       struct pt_regs *regs)
 {
@@ -747,16 +753,27 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 		}
 
 		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
+
+		/*
+		 * If we triggered a user watchpoint from a uaccess routine,
+		 * then handle the stepping ourselves since userspace really
+		 * can't help us with this.
+		 */
+		if (watchpoint_fault_on_uaccess(regs, info))
+			goto step;
+
 		perf_bp_event(wp, regs);
 
 		/*
-		 * If no overflow handler is present, insert a temporary
-		 * mismatch breakpoint so we can single-step over the
-		 * watchpoint trigger.
+		 * Defer stepping to the overflow handler if one is installed.
+		 * Otherwise, insert a temporary mismatch breakpoint so that
+		 * we can single-step over the watchpoint trigger.
 		 */
-		if (is_default_overflow_handler(wp))
-			enable_single_step(wp, instruction_pointer(regs));
+		if (!is_default_overflow_handler(wp))
+			goto unlock;
 
+step:
+		enable_single_step(wp, instruction_pointer(regs));
 unlock:
 		rcu_read_unlock();
 	}
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 58e3771e4c5b..368b4b404985 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -228,8 +228,8 @@ static struct undef_hook arm_break_hook = {
 };
 
 static struct undef_hook thumb_break_hook = {
-	.instr_mask	= 0xffff,
-	.instr_val	= 0xde01,
+	.instr_mask	= 0xffffffff,
+	.instr_val	= 0x0000de01,
 	.cpsr_mask	= PSR_T_BIT,
 	.cpsr_val	= PSR_T_BIT,
 	.fn		= break_trap,
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 65228bf4c6df..ba9b9a77bcd2 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -20,6 +20,19 @@
  * A simple function epilogue looks like this:
  *	ldm	sp, {fp, sp, pc}
  *
+ * When compiled with clang, pc and sp are not pushed. A simple function
+ * prologue looks like this when built with clang:
+ *
+ *	stmdb	{..., fp, lr}
+ *	add	fp, sp, #x
+ *	sub	sp, sp, #y
+ *
+ * A simple function epilogue looks like this when built with clang:
+ *
+ *	sub	sp, fp, #x
+ *	ldm	{..., fp, pc}
+ *
+ *
  * Note that with framepointer enabled, even the leaf functions have the same
  * prologue and epilogue, therefore we can ignore the LR value in this case.
  */
@@ -32,6 +45,16 @@ int notrace unwind_frame(struct stackframe *frame)
 	low = frame->sp;
 	high = ALIGN(low, THREAD_SIZE);
 
+#ifdef CONFIG_CC_IS_CLANG
+	/* check current frame pointer is within bounds */
+	if (fp < low + 4 || fp > high - 4)
+		return -EINVAL;
+
+	frame->sp = frame->fp;
+	frame->fp = *(unsigned long *)(fp);
+	frame->pc = frame->lr;
+	frame->lr = *(unsigned long *)(fp + 4);
+#else
 	/* check current frame pointer is within bounds */
 	if (fp < low + 12 || fp > high - 4)
 		return -EINVAL;
@@ -40,6 +63,7 @@ int notrace unwind_frame(struct stackframe *frame)
 	frame->fp = *(unsigned long *)(fp - 12);
 	frame->sp = *(unsigned long *)(fp - 8);
 	frame->pc = *(unsigned long *)(fp - 4);
+#endif
 
 	return 0;
 }
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index 93cddab73072..95bd35991288 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -7,7 +7,7 @@
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
 	and	r3, r0, #31		@ Get bit offset
 	mov	r0, r0, lsr #5
@@ -32,7 +32,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
 	and	r3, r0, #31		@ Get bit offset
 	mov	r0, r0, lsr #5
@@ -62,7 +62,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	and	r2, r0, #31
 	mov	r0, r0, lsr #5
 	mov	r3, #1
@@ -89,7 +89,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	and	r3, r0, #31
 	mov	r0, r0, lsr #5
 	save_and_disable_irqs ip
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 849014c01cf4..bebaa0b0aef4 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -456,13 +456,13 @@ static void __init at91_pm_sram_init(void)
 	sram_pool = gen_pool_get(&pdev->dev, NULL);
 	if (!sram_pool) {
 		pr_warn("%s: sram pool unavailable!\n", __func__);
-		return;
+		goto out_put_device;
 	}
 
 	sram_base = gen_pool_alloc(sram_pool, at91_pm_suspend_in_sram_sz);
 	if (!sram_base) {
 		pr_warn("%s: unable to alloc sram!\n", __func__);
-		return;
+		goto out_put_device;
 	}
 
 	sram_pbase = gen_pool_virt_to_phys(sram_pool, sram_base);
@@ -470,12 +470,17 @@ static void __init at91_pm_sram_init(void)
 					at91_pm_suspend_in_sram_sz, false);
 	if (!at91_suspend_sram_fn) {
 		pr_warn("SRAM: Could not map\n");
-		return;
+		goto out_put_device;
 	}
 
 	/* Copy the pm suspend handler to SRAM */
 	at91_suspend_sram_fn = fncpy(at91_suspend_sram_fn,
 			&at91_pm_suspend_in_sram, at91_pm_suspend_in_sram_sz);
+	return;
+
+out_put_device:
+	put_device(&pdev->dev);
+	return;
 }
 
 static void __init at91_pm_backup_init(void)
diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c
index 868781fd460c..14c630c899c5 100644
--- a/arch/arm/mach-imx/pm-imx5.c
+++ b/arch/arm/mach-imx/pm-imx5.c
@@ -301,14 +301,14 @@ static int __init imx_suspend_alloc_ocram(
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_base = gen_pool_alloc(ocram_pool, size);
 	if (!ocram_base) {
 		pr_warn("%s: unable to alloc ocram!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	phys = gen_pool_virt_to_phys(ocram_pool, ocram_base);
@@ -318,6 +318,8 @@ static int __init imx_suspend_alloc_ocram(
 	if (virt_out)
 		*virt_out = virt;
 
+put_device:
+	put_device(&pdev->dev);
 put_node:
 	of_node_put(node);
 
diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c
index 6078bcc9f594..c7dcb0b20730 100644
--- a/arch/arm/mach-imx/pm-imx6.c
+++ b/arch/arm/mach-imx/pm-imx6.c
@@ -483,14 +483,14 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_base = gen_pool_alloc(ocram_pool, MX6Q_SUSPEND_OCRAM_SIZE);
 	if (!ocram_base) {
 		pr_warn("%s: unable to alloc ocram!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base);
@@ -513,7 +513,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
 	ret = imx6_pm_get_base(&pm_info->mmdc_base, socdata->mmdc_compat);
 	if (ret) {
 		pr_warn("%s: failed to get mmdc base %d!\n", __func__, ret);
-		goto put_node;
+		goto put_device;
 	}
 
 	ret = imx6_pm_get_base(&pm_info->src_base, socdata->src_compat);
@@ -560,7 +560,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
 		&imx6_suspend,
 		MX6Q_SUSPEND_OCRAM_SIZE - sizeof(*pm_info));
 
-	goto put_node;
+	goto put_device;
 
 pl310_cache_map_failed:
 	iounmap(pm_info->gpc_base.vbase);
@@ -570,6 +570,8 @@ iomuxc_map_failed:
 	iounmap(pm_info->src_base.vbase);
 src_map_failed:
 	iounmap(pm_info->mmdc_base.vbase);
+put_device:
+	put_device(&pdev->dev);
 put_node:
 	of_node_put(node);
 
diff --git a/arch/arm/mach-integrator/Kconfig b/arch/arm/mach-integrator/Kconfig
index cefe44f6889b..ba124f8704fa 100644
--- a/arch/arm/mach-integrator/Kconfig
+++ b/arch/arm/mach-integrator/Kconfig
@@ -3,6 +3,8 @@ menuconfig ARCH_INTEGRATOR
 	depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 || ARCH_MULTI_V6
 	select ARM_AMBA
 	select COMMON_CLK_VERSATILE
+	select CMA
+	select DMA_CMA
 	select HAVE_TCM
 	select ICST
 	select MFD_SYSCON
@@ -34,14 +36,13 @@ config INTEGRATOR_IMPD1
 	select ARM_VIC
 	select GPIO_PL061
 	select GPIOLIB
+	select REGULATOR
+	select REGULATOR_FIXED_VOLTAGE
 	help
 	  The IM-PD1 is an add-on logic module for the Integrator which
 	  allows ARM(R) Ltd PrimeCells to be developed and evaluated.
 	  The IM-PD1 can be found on the Integrator/PP2 platform.
 
-	  To compile this driver as a module, choose M here: the
-	  module will be called impd1.
-
 config INTEGRATOR_CM7TDMI
 	bool "Integrator/CM7TDMI core module"
 	depends on ARCH_INTEGRATOR_AP
diff --git a/arch/arm/mach-socfpga/pm.c b/arch/arm/mach-socfpga/pm.c
index c378ab0c2431..93f2245c9775 100644
--- a/arch/arm/mach-socfpga/pm.c
+++ b/arch/arm/mach-socfpga/pm.c
@@ -60,14 +60,14 @@ static int socfpga_setup_ocram_self_refresh(void)
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_base = gen_pool_alloc(ocram_pool, socfpga_sdram_self_refresh_sz);
 	if (!ocram_base) {
 		pr_warn("%s: unable to alloc ocram!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base);
@@ -78,7 +78,7 @@ static int socfpga_setup_ocram_self_refresh(void)
 	if (!suspend_ocram_base) {
 		pr_warn("%s: __arm_ioremap_exec failed!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	/* Copy the code that puts DDR in self refresh to ocram */
@@ -92,6 +92,8 @@ static int socfpga_setup_ocram_self_refresh(void)
 	if (!socfpga_sdram_self_refresh_in_ocram)
 		ret = -EFAULT;
 
+put_device:
+	put_device(&pdev->dev);
 put_node:
 	of_node_put(np);
 
diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c
index 02e712d2ea30..bbc2926bd12b 100644
--- a/arch/arm/mach-tegra/tegra.c
+++ b/arch/arm/mach-tegra/tegra.c
@@ -108,8 +108,8 @@ static const char * const tegra_dt_board_compat[] = {
 };
 
 DT_MACHINE_START(TEGRA_DT, "NVIDIA Tegra SoC (Flattened Device Tree)")
-	.l2c_aux_val	= 0x3c400001,
-	.l2c_aux_mask	= 0xc20fc3fe,
+	.l2c_aux_val	= 0x3c400000,
+	.l2c_aux_mask	= 0xc20fc3ff,
 	.smp		= smp_ops(tegra_smp_ops),
 	.map_io		= tegra_map_common_io,
 	.init_early	= tegra_init_early,
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 9bb446cc135d..76541eb76f42 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -455,8 +455,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 
 	if (pud_none(*pud_k))
 		goto bad_area;
-	if (!pud_present(*pud))
+	if (!pud_present(*pud)) {
 		set_pud(pud, *pud_k);
+		/*
+		 * There is a small window during free_pgtables() where the
+		 * user *pud entry is 0 but the TLB has not been invalidated
+		 * and we get a level 2 (pmd) translation fault caused by the
+		 * intermediate TLB caching of the old level 1 (pud) entry.
+		 */
+		flush_tlb_kernel_page(addr);
+	}
 
 	pmd = pmd_offset(pud, addr);
 	pmd_k = pmd_offset(pud_k, addr);
@@ -479,8 +487,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 #endif
 	if (pmd_none(pmd_k[index]))
 		goto bad_area;
+	if (!pmd_present(pmd[index]))
+		copy_pmd(pmd, pmd_k);
 
-	copy_pmd(pmd, pmd_k);
 	return 0;
 
 bad_area:
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 5461d589a1e2..60ac7c5999a9 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -5,6 +5,7 @@
  *  VMA_VM_FLAGS
  *  VM_EXEC
  */
+#include <linux/const.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 
@@ -30,7 +31,7 @@
  * act_mm - get current->active_mm
  */
 	.macro	act_mm, rd
-	bic	\rd, sp, #8128
+	bic	\rd, sp, #(THREAD_SIZE - 1) & ~63
 	bic	\rd, \rd, #63
 	ldr	\rd, [\rd, #TI_TASK]
 	.if (TSK_ACTIVE_MM > IMM12_MASK)
diff --git a/arch/arm/tools/gen-mach-types b/arch/arm/tools/gen-mach-types
index cbe1c33bb871..cb2b69f2a39d 100644
--- a/arch/arm/tools/gen-mach-types
+++ b/arch/arm/tools/gen-mach-types
@@ -1,4 +1,4 @@
-#!/bin/awk
+#!/usr/bin/awk
 # SPDX-License-Identifier: GPL-2.0
 #
 # Awk script to generate include/generated/mach-types.h
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 3c3057944960..3ee6c4bae08f 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -245,6 +245,11 @@
 	};
 };
 
+&hwrng {
+	clocks = <&clkc CLKID_RNG0>;
+	clock-names = "core";
+};
+
 &i2c_A {
 	clocks = <&clkc CLKID_I2C>;
 };
diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
index 0b72094bcf5a..05f82819ae2d 100644
--- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
@@ -745,7 +745,7 @@
 		};
 
 		qspi: spi@66470200 {
-			compatible = "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi";
+			compatible = "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi";
 			reg = <0x66470200 0x184>,
 				<0x66470000 0x124>,
 				<0x67017408 0x004>,
diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
index 4a8b1fb51243..c8824b918693 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
+++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
@@ -155,6 +155,7 @@
 				regulator-min-microvolt = <700000>;
 				regulator-max-microvolt = <1150000>;
 				regulator-enable-ramp-delay = <125>;
+				regulator-always-on;
 			};
 
 			ldo8_reg: LDO8 {
diff --git a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
index e9f87cb61ade..8587912e1eb0 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
@@ -210,6 +210,17 @@
 		status = "ok";
 		compatible = "adi,adv7533";
 		reg = <0x39>;
+		adi,dsi-lanes = <4>;
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			port@0 {
+				reg = <0>;
+			};
+			port@1 {
+				reg = <1>;
+			};
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index 6887cc1a743d..f78e6468b02f 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -513,7 +513,7 @@
 		reg = <0x39>;
 		interrupt-parent = <&gpio1>;
 		interrupts = <1 2>;
-		pd-gpio = <&gpio0 4 0>;
+		pd-gpios = <&gpio0 4 0>;
 		adi,dsi-lanes = <4>;
 		#sound-dai-cells = <0>;
 
diff --git a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi
index 4cb0b5834143..b24493ad44b0 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi
@@ -542,7 +542,7 @@
 				pins = "gpio63", "gpio64", "gpio65", "gpio66",
 				       "gpio67", "gpio68";
 				drive-strength = <8>;
-				bias-pull-none;
+				bias-disable;
 			};
 		};
 		cdc_pdm_lines_sus: pdm_lines_off {
@@ -555,7 +555,7 @@
 				pins = "gpio63", "gpio64", "gpio65", "gpio66",
 				       "gpio67", "gpio68";
 				drive-strength = <2>;
-				bias-disable;
+				bias-pull-down;
 			};
 		};
 	};
@@ -571,7 +571,7 @@
 				pins = "gpio113", "gpio114", "gpio115",
 				       "gpio116";
 				drive-strength = <8>;
-				bias-pull-none;
+				bias-disable;
 			};
 		};
 
@@ -599,7 +599,7 @@
 			pinconf {
 				pins = "gpio110";
 				drive-strength = <8>;
-				bias-pull-none;
+				bias-disable;
 			};
 		};
 
@@ -625,7 +625,7 @@
 			pinconf {
 				pins = "gpio116";
 				drive-strength = <8>;
-				bias-pull-none;
+				bias-disable;
 			};
 		};
 		ext_mclk_tlmm_lines_sus: mclk_lines_off {
@@ -653,7 +653,7 @@
 				pins = "gpio112", "gpio117", "gpio118",
 					"gpio119";
 				drive-strength = <8>;
-				bias-pull-none;
+				bias-disable;
 			};
 		};
 		ext_sec_tlmm_lines_sus: tlmm_lines_off {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
index 1fc5060d7027..0d5679380b2a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
@@ -138,7 +138,7 @@
 
 	vcc5v0_host: vcc5v0-host-regulator {
 		compatible = "regulator-fixed";
-		gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_HIGH>;
+		gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_LOW>;
 		enable-active-low;
 		pinctrl-names = "default";
 		pinctrl-0 = <&vcc5v0_host_en>;
@@ -193,7 +193,7 @@
 	phy-mode = "rgmii";
 	pinctrl-names = "default";
 	pinctrl-0 = <&rgmii_pins>;
-	snps,reset-gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_HIGH>;
+	snps,reset-gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_LOW>;
 	snps,reset-active-low;
 	snps,reset-delays-us = <0 10000 50000>;
 	tx_delay = <0x10>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index ff8df7fd44a7..b63d9653ff55 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -1691,10 +1691,10 @@
 	gpu: gpu@ff9a0000 {
 		compatible = "rockchip,rk3399-mali", "arm,mali-t860";
 		reg = <0x0 0xff9a0000 0x0 0x10000>;
-		interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>;
-		interrupt-names = "gpu", "job", "mmu";
+		interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupt-names = "job", "mmu", "gpu";
 		clocks = <&cru ACLK_GPU>;
 		power-domains = <&power RK3399_PD_GPU>;
 		status = "disabled";
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 4ed869845a23..3abb2dacb43f 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -68,13 +68,13 @@ void apply_alternatives(void *start, size_t length);
 	".pushsection .altinstructions,\"a\"\n"				\
 	ALTINSTR_ENTRY(feature)						\
 	".popsection\n"							\
-	".pushsection .altinstr_replacement, \"a\"\n"			\
+	".subsection 1\n"						\
 	"663:\n\t"							\
 	newinstr "\n"							\
 	"664:\n\t"							\
-	".popsection\n\t"						\
 	".org	. - (664b-663b) + (662b-661b)\n\t"			\
-	".org	. - (662b-661b) + (664b-663b)\n"			\
+	".org	. - (662b-661b) + (664b-663b)\n\t"			\
+	".previous\n"							\
 	".endif\n"
 
 #define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb)	\
@@ -112,9 +112,9 @@ void apply_alternatives(void *start, size_t length);
 662:	.pushsection .altinstructions, "a"
 	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
 	.popsection
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 663:	\insn2
-664:	.popsection
+664:	.previous
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
 	.endif
@@ -155,7 +155,7 @@ void apply_alternatives(void *start, size_t length);
 	.pushsection .altinstructions, "a"
 	altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
 	.popsection
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 	.align 2	/* So GAS knows label 661 is suitably aligned */
 661:
 .endm
@@ -174,9 +174,9 @@ void apply_alternatives(void *start, size_t length);
 .macro alternative_else
 662:
 	.if .Lasm_alt_mode==0
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 	.else
-	.popsection
+	.previous
 	.endif
 663:
 .endm
@@ -187,7 +187,7 @@ void apply_alternatives(void *start, size_t length);
 .macro alternative_endif
 664:
 	.if .Lasm_alt_mode==0
-	.popsection
+	.previous
 	.endif
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index 0b6f5a7d4027..fd11e0d70e44 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -30,16 +30,17 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 {
 	__uint128_t tmp;
 	u64 sum;
+	int n = ihl; /* we want it signed */
 
 	tmp = *(const __uint128_t *)iph;
 	iph += 16;
-	ihl -= 4;
+	n -= 4;
 	tmp += ((tmp >> 64) | (tmp << 64));
 	sum = tmp >> 64;
 	do {
 		sum += *(const u32 *)iph;
 		iph += 4;
-	} while (--ihl);
+	} while (--n > 0);
 
 	sum += ((sum >> 32) | (sum << 32));
 	return csum_fold((__force u32)(sum >> 32));
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index a44cf5225429..41b065f1be88 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -119,6 +119,8 @@ void disable_debug_monitors(enum dbg_active_el el);
 
 void user_rewind_single_step(struct task_struct *task);
 void user_fastforward_single_step(struct task_struct *task);
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task);
 
 void kernel_enable_single_step(struct pt_regs *regs);
 void kernel_disable_single_step(void);
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 1d6d980f80ac..f88611e241f0 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -78,10 +78,11 @@
  * IMO:		Override CPSR.I and enable signaling with VI
  * FMO:		Override CPSR.F and enable signaling with VF
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
+ * PTW:		Take a stage2 fault if a stage1 walk steps in device memory
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
 			 HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \
-			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW)
+			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_PTW)
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
 #define HCR_INT_OVERRIDE   (HCR_FMO | HCR_IMO)
 #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index c59e81b65132..b0f0fb81f5f5 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -83,6 +83,34 @@ extern u32 __init_stage2_translation(void);
 		*__hyp_this_cpu_ptr(sym);				\
 	 })
 
+#define __KVM_EXTABLE(from, to)						\
+	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
+	"	.align		3\n"					\
+	"	.long		(" #from " - .), (" #to " - .)\n"	\
+	"	.popsection\n"
+
+
+#define __kvm_at(at_op, addr)						\
+( { 									\
+	int __kvm_at_err = 0;						\
+	u64 spsr, elr;							\
+	asm volatile(							\
+	"	mrs	%1, spsr_el2\n"					\
+	"	mrs	%2, elr_el2\n"					\
+	"1:	at	"at_op", %3\n"					\
+	"	isb\n"							\
+	"	b	9f\n"						\
+	"2:	msr	spsr_el2, %1\n"					\
+	"	msr	elr_el2, %2\n"					\
+	"	mov	%w0, %4\n"					\
+	"9:\n"								\
+	__KVM_EXTABLE(1b, 2b)						\
+	: "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr)		\
+	: "r" (addr), "i" (-EFAULT));					\
+	__kvm_at_err;							\
+} )
+
+
 #else /* __ASSEMBLY__ */
 
 .macro hyp_adr_this_cpu reg, sym, tmp
@@ -107,6 +135,21 @@ extern u32 __init_stage2_translation(void);
 	kern_hyp_va	\vcpu
 .endm
 
+/*
+ * KVM extable for unexpected exceptions.
+ * In the same format _asm_extable, but output to a different section so that
+ * it can be mapped to EL2. The KVM version is not sorted. The caller must
+ * ensure:
+ * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented
+ * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup.
+ */
+.macro	_kvm_extable, from, to
+	.pushsection	__kvm_ex_table, "a"
+	.align		3
+	.long		(\from - .), (\to - .)
+	.popsection
+.endm
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f982c9d1d10b..87615facf959 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -292,8 +292,10 @@ struct kvm_vcpu_arch {
  * CP14 and CP15 live in the same array, as they are backed by the
  * same system registers.
  */
-#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r)])
-#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r)])
+#define CPx_BIAS		IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)
+
+#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
+#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
 #define vcpu_cp15_64_high(v,r)	vcpu_cp15((v),(r))
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 26efe251f076..6415677ffe8d 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -65,7 +65,7 @@
 #define PAGE_HYP		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
 #define PAGE_HYP_EXEC		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
 #define PAGE_HYP_RO		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
-#define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
+#define PAGE_HYP_DEVICE		__pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN)
 
 #define PAGE_S2			__pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
 #define PAGE_S2_DEVICE		__pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 5c4bce4ac381..4c385763c361 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -44,20 +44,8 @@ struct alt_region {
  */
 static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 {
-	unsigned long replptr;
-
-	if (kernel_text_address(pc))
-		return 1;
-
-	replptr = (unsigned long)ALT_REPL_PTR(alt);
-	if (pc >= replptr && pc <= (replptr + alt->alt_len))
-		return 0;
-
-	/*
-	 * Branching into *another* alternate sequence is doomed, and
-	 * we're not even trying to fix it up.
-	 */
-	BUG();
+	unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt);
+	return !(pc >= replptr && pc <= (replptr + alt->alt_len));
 }
 
 #define align_down(x, a)	((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 6b3bb67596ae..174aa12fb8b1 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -136,11 +136,10 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
-	/* Linux doesn't care about the EL3 */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
 	ARM64_FTR_END,
 };
 
@@ -273,7 +272,7 @@ static const struct arm64_ftr_bits ftr_id_pfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_dfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
+	/* [31:28] TraceFilt */
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf),	/* PerfMon */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0),
@@ -627,9 +626,6 @@ void update_cpu_features(int cpu,
 	taint |= check_update_ftr_reg(SYS_ID_AA64MMFR2_EL1, cpu,
 				      info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2);
 
-	/*
-	 * EL3 is not our concern.
-	 */
 	taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu,
 				      info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0);
 	taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu,
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index edb63bf2ac1c..2ccd0a99d8b3 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -150,17 +150,20 @@ postcore_initcall(debug_monitors_init);
 /*
  * Single step API and exception handling.
  */
-static void set_regs_spsr_ss(struct pt_regs *regs)
+static void set_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate |= DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(set_regs_spsr_ss);
+NOKPROBE_SYMBOL(set_user_regs_spsr_ss);
 
-static void clear_regs_spsr_ss(struct pt_regs *regs)
+static void clear_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate &= ~DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(clear_regs_spsr_ss);
+NOKPROBE_SYMBOL(clear_user_regs_spsr_ss);
+
+#define set_regs_spsr_ss(r)	set_user_regs_spsr_ss(&(r)->user_regs)
+#define clear_regs_spsr_ss(r)	clear_user_regs_spsr_ss(&(r)->user_regs)
 
 /* EL1 Single Step Handler hooks */
 static LIST_HEAD(step_hook);
@@ -386,17 +389,26 @@ void user_rewind_single_step(struct task_struct *task)
 	 * If single step is active for this thread, then set SPSR.SS
 	 * to 1 to avoid returning to the active-pending state.
 	 */
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		set_regs_spsr_ss(task_pt_regs(task));
 }
 NOKPROBE_SYMBOL(user_rewind_single_step);
 
 void user_fastforward_single_step(struct task_struct *task)
 {
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		clear_regs_spsr_ss(task_pt_regs(task));
 }
 
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
+		set_user_regs_spsr_ss(regs);
+	else
+		clear_user_regs_spsr_ss(regs);
+}
+
 /* Kernel API */
 void kernel_enable_single_step(struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 95697a9c1245..6e96cea99a4e 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -738,6 +738,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val,
 		return 0;
 }
 
+static int watchpoint_report(struct perf_event *wp, unsigned long addr,
+			     struct pt_regs *regs)
+{
+	int step = is_default_overflow_handler(wp);
+	struct arch_hw_breakpoint *info = counter_arch_bp(wp);
+
+	info->trigger = addr;
+
+	/*
+	 * If we triggered a user watchpoint from a uaccess routine, then
+	 * handle the stepping ourselves since userspace really can't help
+	 * us with this.
+	 */
+	if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0)
+		step = 1;
+	else
+		perf_bp_event(wp, regs);
+
+	return step;
+}
+
 static int watchpoint_handler(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
@@ -747,7 +768,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 	u64 val;
 	struct perf_event *wp, **slots;
 	struct debug_info *debug_info;
-	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
 	slots = this_cpu_ptr(wp_on_reg);
@@ -785,25 +805,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 		if (dist != 0)
 			continue;
 
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
-
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
+		step = watchpoint_report(wp, addr, regs);
 	}
-	if (min_dist > 0 && min_dist != -1) {
-		/* No exact match found. */
-		wp = slots[closest_match];
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
 
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
-	}
+	/* No exact match found? */
+	if (min_dist > 0 && min_dist != -1)
+		step = watchpoint_report(slots[closest_match], addr, regs);
+
 	rcu_read_unlock();
 
 	if (!step)
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 470afb3a04ca..7fd7a9cd8616 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -258,7 +258,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 	if (user_mode(regs) || !kgdb_single_step)
 		return DBG_HOOK_ERROR;
 
-	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 1d091d048d04..0819db91ca94 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 		return 0;
 
 	/*
-	 * Compat (i.e. 32 bit) mode:
-	 * - PC has been set in the pt_regs struct in kernel_entry,
-	 * - Handle SP and LR here.
+	 * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but
+	 * we're stuck with it for ABI compatability reasons.
+	 *
+	 * For a 32-bit consumer inspecting a 32-bit task, then it will look at
+	 * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h).
+	 * These correspond directly to a prefix of the registers saved in our
+	 * 'struct pt_regs', with the exception of the PC, so we copy that down
+	 * (x15 corresponds to SP_hyp in the architecture).
+	 *
+	 * So far, so good.
+	 *
+	 * The oddity arises when a 64-bit consumer looks at a 32-bit task and
+	 * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return
+	 * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and
+	 * PC registers would normally live. The initial idea was to allow a
+	 * 64-bit unwinder to unwind a 32-bit task and, although it's not clear
+	 * how well that works in practice, somebody might be relying on it.
+	 *
+	 * At the time we make a sample, we don't know whether the consumer is
+	 * 32-bit or 64-bit, so we have to cater for both possibilities.
 	 */
 	if (compat_user_mode(regs)) {
 		if ((u32)idx == PERF_REG_ARM64_SP)
 			return regs->compat_sp;
 		if ((u32)idx == PERF_REG_ARM64_LR)
 			return regs->compat_lr;
+		if (idx == 15)
+			return regs->pc;
 	}
 
 	if ((u32)idx == PERF_REG_ARM64_SP)
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index e8574b95bda8..947dbe5be43f 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1496,8 +1496,8 @@ static int valid_native_regs(struct user_pt_regs *regs)
  */
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task)
 {
-	if (!test_tsk_thread_flag(task, TIF_SINGLESTEP))
-		regs->pstate &= ~DBG_SPSR_SS;
+	/* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */
+	user_regs_reset_single_step(regs, task);
 
 	if (is_compat_thread(task_thread_info(task)))
 		return valid_compat_regs(regs);
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 6edfdf5b061d..4c11d3e64aef 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -24,6 +24,13 @@ ENTRY(_text)
 
 jiffies = jiffies_64;
 
+
+#define HYPERVISOR_EXTABLE					\
+	. = ALIGN(SZ_8);					\
+	VMLINUX_SYMBOL(__start___kvm_ex_table) = .;		\
+	*(__kvm_ex_table)					\
+	VMLINUX_SYMBOL(__stop___kvm_ex_table) = .;
+
 #define HYPERVISOR_TEXT					\
 	/*						\
 	 * Align to 4 KB so that			\
@@ -39,6 +46,7 @@ jiffies = jiffies_64;
 	VMLINUX_SYMBOL(__hyp_idmap_text_end) = .;	\
 	VMLINUX_SYMBOL(__hyp_text_start) = .;		\
 	*(.hyp.text)					\
+	HYPERVISOR_EXTABLE				\
 	VMLINUX_SYMBOL(__hyp_text_end) = .;
 
 #define IDMAP_TEXT					\
@@ -154,9 +162,6 @@ SECTIONS
 		*(.altinstructions)
 		__alt_instructions_end = .;
 	}
-	.altinstr_replacement : {
-		*(.altinstr_replacement)
-	}
 
 	. = ALIGN(PAGE_SIZE);
 	__inittext_end = .;
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index dea20651a5f1..cb28c12d0a64 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -147,11 +147,15 @@ ENTRY(__kvm_handle_stub_hvc)
 
 1:	cmp	x0, #HVC_RESET_VECTORS
 	b.ne	1f
-reset:
+
 	/*
-	 * Reset kvm back to the hyp stub. Do not clobber x0-x4 in
-	 * case we coming via HVC_SOFT_RESTART.
+	 * Set the HVC_RESET_VECTORS return code before entering the common
+	 * path so that we do not clobber x0-x2 in case we are coming via
+	 * HVC_SOFT_RESTART.
 	 */
+	mov	x0, xzr
+reset:
+	/* Reset kvm back to the hyp stub. */
 	mrs	x5, sctlr_el2
 	ldr	x6, =SCTLR_ELx_FLAGS
 	bic	x5, x5, x6		// Clear SCTL_M and etc
@@ -162,7 +166,6 @@ reset:
 	/* Install stub vectors */
 	adr_l	x5, __hyp_stub_vectors
 	msr	vbar_el2, x5
-	mov	x0, xzr
 	eret
 
 1:	/* Bad stub call */
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index a360ac6e89e9..4e0eac361f87 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -17,6 +17,7 @@
 
 #include <linux/linkage.h>
 
+#include <asm/alternative.h>
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
 #include <asm/fpsimdmacros.h>
@@ -62,6 +63,15 @@ ENTRY(__guest_enter)
 	// Store the host regs
 	save_callee_saved_regs x1
 
+	// Now the host state is stored if we have a pending RAS SError it must
+	// affect the host. If any asynchronous exception is pending we defer
+	// the guest entry.
+	mrs	x1, isr_el1
+	cbz	x1,  1f
+	mov	x0, #ARM_EXCEPTION_IRQ
+	ret
+
+1:
 	add	x18, x0, #VCPU_CONTEXT
 
 	// Restore guest regs x0-x17
@@ -135,18 +145,22 @@ ENTRY(__guest_exit)
 	// This is our single instruction exception window. A pending
 	// SError is guaranteed to occur at the earliest when we unmask
 	// it, and at the latest just after the ISB.
-	.global	abort_guest_exit_start
 abort_guest_exit_start:
 
 	isb
 
-	.global	abort_guest_exit_end
 abort_guest_exit_end:
+	msr	daifset, #4	// Mask aborts
+	ret
+
+	_kvm_extable	abort_guest_exit_start, 9997f
+	_kvm_extable	abort_guest_exit_end, 9997f
+9997:
+	msr	daifset, #4	// Mask aborts
+	mov	x0, #(1 << ARM_EXIT_WITH_SERROR_BIT)
 
-	// If the exception took place, restore the EL1 exception
-	// context so that we can report some information.
-	// Merge the exception code with the SError pending bit.
-	tbz	x0, #ARM_EXIT_WITH_SERROR_BIT, 1f
+	// restore the EL1 exception context so that we can report some
+	// information. Merge the exception code with the SError pending bit.
 	msr	elr_el2, x2
 	msr	esr_el2, x3
 	msr	spsr_el2, x4
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 3c283fd8c8f5..5e041eabdd03 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -25,6 +25,30 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmu.h>
 
+.macro save_caller_saved_regs_vect
+	stp	x0, x1,   [sp, #-16]!
+	stp	x2, x3,   [sp, #-16]!
+	stp	x4, x5,   [sp, #-16]!
+	stp	x6, x7,   [sp, #-16]!
+	stp	x8, x9,   [sp, #-16]!
+	stp	x10, x11, [sp, #-16]!
+	stp	x12, x13, [sp, #-16]!
+	stp	x14, x15, [sp, #-16]!
+	stp	x16, x17, [sp, #-16]!
+.endm
+
+.macro restore_caller_saved_regs_vect
+	ldp	x16, x17, [sp], #16
+	ldp	x14, x15, [sp], #16
+	ldp	x12, x13, [sp], #16
+	ldp	x10, x11, [sp], #16
+	ldp	x8, x9,   [sp], #16
+	ldp	x6, x7,   [sp], #16
+	ldp	x4, x5,   [sp], #16
+	ldp	x2, x3,   [sp], #16
+	ldp	x0, x1,   [sp], #16
+.endm
+
 	.text
 	.pushsection	.hyp.text, "ax"
 
@@ -183,26 +207,24 @@ el1_error:
 	mov	x0, #ARM_EXCEPTION_EL1_SERROR
 	b	__guest_exit
 
+el2_sync:
+	save_caller_saved_regs_vect
+	stp     x29, x30, [sp, #-16]!
+	bl	kvm_unexpected_el2_exception
+	ldp     x29, x30, [sp], #16
+	restore_caller_saved_regs_vect
+
+	eret
+
 el2_error:
-	/*
-	 * Only two possibilities:
-	 * 1) Either we come from the exit path, having just unmasked
-	 *    PSTATE.A: change the return code to an EL2 fault, and
-	 *    carry on, as we're already in a sane state to handle it.
-	 * 2) Or we come from anywhere else, and that's a bug: we panic.
-	 *
-	 * For (1), x0 contains the original return code and x1 doesn't
-	 * contain anything meaningful at that stage. We can reuse them
-	 * as temp registers.
-	 * For (2), who cares?
-	 */
-	mrs	x0, elr_el2
-	adr	x1, abort_guest_exit_start
-	cmp	x0, x1
-	adr	x1, abort_guest_exit_end
-	ccmp	x0, x1, #4, ne
-	b.ne	__hyp_panic
-	mov	x0, #(1 << ARM_EXIT_WITH_SERROR_BIT)
+	save_caller_saved_regs_vect
+	stp     x29, x30, [sp, #-16]!
+
+	bl	kvm_unexpected_el2_exception
+
+	ldp     x29, x30, [sp], #16
+	restore_caller_saved_regs_vect
+
 	eret
 
 ENTRY(__hyp_do_panic)
@@ -231,7 +253,6 @@ ENDPROC(\label)
 	invalid_vector	el2t_irq_invalid
 	invalid_vector	el2t_fiq_invalid
 	invalid_vector	el2t_error_invalid
-	invalid_vector	el2h_sync_invalid
 	invalid_vector	el2h_irq_invalid
 	invalid_vector	el2h_fiq_invalid
 	invalid_vector	el1_sync_invalid
@@ -248,7 +269,7 @@ ENTRY(__kvm_hyp_vector)
 	ventry	el2t_fiq_invalid		// FIQ EL2t
 	ventry	el2t_error_invalid		// Error EL2t
 
-	ventry	el2h_sync_invalid		// Synchronous EL2h
+	ventry	el2_sync			// Synchronous EL2h
 	ventry	el2h_irq_invalid		// IRQ EL2h
 	ventry	el2h_fiq_invalid		// FIQ EL2h
 	ventry	el2_error			// Error EL2h
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 4a8fdbb29286..99ae75a43985 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -22,11 +22,15 @@
 
 #include <kvm/arm_psci.h>
 
+#include <asm/extable.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 #include <asm/fpsimd.h>
 
+extern struct exception_table_entry __start___kvm_ex_table;
+extern struct exception_table_entry __stop___kvm_ex_table;
+
 static bool __hyp_text __fpsimd_enabled_nvhe(void)
 {
 	return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP);
@@ -216,10 +220,10 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
 	 * saved the guest context yet, and we may return early...
 	 */
 	par = read_sysreg(par_el1);
-	asm volatile("at s1e1r, %0" : : "r" (far));
-	isb();
-
-	tmp = read_sysreg(par_el1);
+	if (!__kvm_at("s1e1r", far))
+		tmp = read_sysreg(par_el1);
+	else
+		tmp = 1; /* back to the guest */
 	write_sysreg(par, par_el1);
 
 	if (unlikely(tmp & 1))
@@ -444,7 +448,7 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
 	 * making sure it is a kernel address and not a PC-relative
 	 * reference.
 	 */
-	asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va));
+	asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string));
 
 	__hyp_do_panic(str_va,
 		       spsr,  elr,
@@ -486,3 +490,30 @@ void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
 
 	unreachable();
 }
+
+asmlinkage void __hyp_text kvm_unexpected_el2_exception(void)
+{
+	unsigned long addr, fixup;
+	struct kvm_cpu_context *host_ctxt;
+	struct exception_table_entry *entry, *end;
+	unsigned long elr_el2 = read_sysreg(elr_el2);
+
+	entry = hyp_symbol_addr(__start___kvm_ex_table);
+	end = hyp_symbol_addr(__stop___kvm_ex_table);
+	host_ctxt = __hyp_this_cpu_ptr(kvm_host_cpu_state);
+
+	while (entry < end) {
+		addr = (unsigned long)&entry->insn + entry->insn;
+		fixup = (unsigned long)&entry->fixup + entry->fixup;
+
+		if (addr != elr_el2) {
+			entry++;
+			continue;
+		}
+
+		write_sysreg(fixup, elr_el2);
+		return;
+	}
+
+	hyp_panic(host_ctxt);
+}
diff --git a/arch/m68k/coldfire/pci.c b/arch/m68k/coldfire/pci.c
index 3097fa2ca746..1e428d18d268 100644
--- a/arch/m68k/coldfire/pci.c
+++ b/arch/m68k/coldfire/pci.c
@@ -316,8 +316,10 @@ static int __init mcf_pci_init(void)
 
 	/* Keep a virtual mapping to IO/config space active */
 	iospace = (unsigned long) ioremap(PCI_IO_PA, PCI_IO_SIZE);
-	if (iospace == 0)
+	if (iospace == 0) {
+		pci_free_host_bridge(bridge);
 		return -ENODEV;
+	}
 	pr_info("Coldfire: PCI IO/config window mapped to 0x%x\n",
 		(u32) iospace);
 
diff --git a/arch/m68k/include/asm/m53xxacr.h b/arch/m68k/include/asm/m53xxacr.h
index 9138a624c5c8..692f90e7fecc 100644
--- a/arch/m68k/include/asm/m53xxacr.h
+++ b/arch/m68k/include/asm/m53xxacr.h
@@ -89,9 +89,9 @@
  * coherency though in all cases. And for copyback caches we will need
  * to push cached data as well.
  */
-#define CACHE_INIT	  CACR_CINVA
-#define CACHE_INVALIDATE  CACR_CINVA
-#define CACHE_INVALIDATED CACR_CINVA
+#define CACHE_INIT        (CACHE_MODE + CACR_CINVA - CACR_EC)
+#define CACHE_INVALIDATE  (CACHE_MODE + CACR_CINVA)
+#define CACHE_INVALIDATED (CACHE_MODE + CACR_CINVA)
 
 #define ACR0_MODE	((CONFIG_RAMBASE & 0xff000000) + \
 			 (0x000f0000) + \
diff --git a/arch/m68k/include/asm/mac_via.h b/arch/m68k/include/asm/mac_via.h
index de1470c4d829..1149251ea58d 100644
--- a/arch/m68k/include/asm/mac_via.h
+++ b/arch/m68k/include/asm/mac_via.h
@@ -257,6 +257,7 @@ extern int rbv_present,via_alt_mapping;
 
 struct irq_desc;
 
+extern void via_l2_flush(int writeback);
 extern void via_register_interrupts(void);
 extern void via_irq_enable(int);
 extern void via_irq_disable(int);
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 2004b3f72d80..3ea7450c51f2 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -61,7 +61,6 @@ extern void iop_preinit(void);
 extern void iop_init(void);
 extern void via_init(void);
 extern void via_init_clock(irq_handler_t func);
-extern void via_flush_cache(void);
 extern void oss_init(void);
 extern void psc_init(void);
 extern void baboon_init(void);
@@ -132,21 +131,6 @@ int __init mac_parse_bootinfo(const struct bi_record *record)
 	return unknown;
 }
 
-/*
- * Flip into 24bit mode for an instant - flushes the L2 cache card. We
- * have to disable interrupts for this. Our IRQ handlers will crap
- * themselves if they take an IRQ in 24bit mode!
- */
-
-static void mac_cache_card_flush(int writeback)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	via_flush_cache();
-	local_irq_restore(flags);
-}
-
 void __init config_mac(void)
 {
 	if (!MACH_IS_MAC)
@@ -179,9 +163,8 @@ void __init config_mac(void)
 	 * not.
 	 */
 
-	if (macintosh_config->ident == MAC_MODEL_IICI
-	    || macintosh_config->ident == MAC_MODEL_IIFX)
-		mach_l2_flush = mac_cache_card_flush;
+	if (macintosh_config->ident == MAC_MODEL_IICI)
+		mach_l2_flush = via_l2_flush;
 }
 
 
diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c
index 4c1e606e7d03..0b94f6672c5f 100644
--- a/arch/m68k/mac/iop.c
+++ b/arch/m68k/mac/iop.c
@@ -183,7 +183,7 @@ static __inline__ void iop_writeb(volatile struct mac_iop *iop, __u16 addr, __u8
 
 static __inline__ void iop_stop(volatile struct mac_iop *iop)
 {
-	iop->status_ctrl &= ~IOP_RUN;
+	iop->status_ctrl = IOP_AUTOINC;
 }
 
 static __inline__ void iop_start(volatile struct mac_iop *iop)
@@ -191,14 +191,9 @@ static __inline__ void iop_start(volatile struct mac_iop *iop)
 	iop->status_ctrl = IOP_RUN | IOP_AUTOINC;
 }
 
-static __inline__ void iop_bypass(volatile struct mac_iop *iop)
-{
-	iop->status_ctrl |= IOP_BYPASS;
-}
-
 static __inline__ void iop_interrupt(volatile struct mac_iop *iop)
 {
-	iop->status_ctrl |= IOP_IRQ;
+	iop->status_ctrl = IOP_IRQ | IOP_RUN | IOP_AUTOINC;
 }
 
 static int iop_alive(volatile struct mac_iop *iop)
@@ -244,7 +239,6 @@ void __init iop_preinit(void)
 		} else {
 			iop_base[IOP_NUM_SCC] = (struct mac_iop *) SCC_IOP_BASE_QUADRA;
 		}
-		iop_base[IOP_NUM_SCC]->status_ctrl = 0x87;
 		iop_scc_present = 1;
 	} else {
 		iop_base[IOP_NUM_SCC] = NULL;
@@ -256,7 +250,7 @@ void __init iop_preinit(void)
 		} else {
 			iop_base[IOP_NUM_ISM] = (struct mac_iop *) ISM_IOP_BASE_QUADRA;
 		}
-		iop_base[IOP_NUM_ISM]->status_ctrl = 0;
+		iop_stop(iop_base[IOP_NUM_ISM]);
 		iop_ism_present = 1;
 	} else {
 		iop_base[IOP_NUM_ISM] = NULL;
@@ -416,7 +410,8 @@ static void iop_handle_send(uint iop_num, uint chan)
 	msg->status = IOP_MSGSTATUS_UNUSED;
 	msg = msg->next;
 	iop_send_queue[iop_num][chan] = msg;
-	if (msg) iop_do_send(msg);
+	if (msg && iop_readb(iop, IOP_ADDR_SEND_STATE + chan) == IOP_MSG_IDLE)
+		iop_do_send(msg);
 }
 
 /*
@@ -490,16 +485,12 @@ int iop_send_message(uint iop_num, uint chan, void *privdata,
 
 	if (!(q = iop_send_queue[iop_num][chan])) {
 		iop_send_queue[iop_num][chan] = msg;
+		iop_do_send(msg);
 	} else {
 		while (q->next) q = q->next;
 		q->next = msg;
 	}
 
-	if (iop_readb(iop_base[iop_num],
-	    IOP_ADDR_SEND_STATE + chan) == IOP_MSG_IDLE) {
-		iop_do_send(msg);
-	}
-
 	return 0;
 }
 
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index 863806e6775a..6ab6a1d54b37 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -300,10 +300,14 @@ void via_debug_dump(void)
  * the system into 24-bit mode for an instant.
  */
 
-void via_flush_cache(void)
+void via_l2_flush(int writeback)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	via2[gBufB] &= ~VIA2B_vMode32;
 	via2[gBufB] |= VIA2B_vMode32;
+	local_irq_restore(flags);
 }
 
 /*
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index 71c0867ecf20..7fdf4e7799bc 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -303,6 +303,7 @@ static int q40_get_rtc_pll(struct rtc_pll_info *pll)
 {
 	int tmp = Q40_RTC_CTRL;
 
+	pll->pll_ctrl = 0;
 	pll->pll_value = tmp & Q40_RTC_PLL_MASK;
 	if (tmp & Q40_RTC_PLL_SIGN)
 		pll->pll_value = -pll->pll_value;
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 7e267d657c56..49c540790fd2 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -856,6 +856,7 @@ config SNI_RM
 	select I8253
 	select I8259
 	select ISA
+	select MIPS_L1_CACHE_SHIFT_6
 	select SWAP_IO_SPACE if CPU_BIG_ENDIAN
 	select SYS_HAS_CPU_R4X00
 	select SYS_HAS_CPU_R5000
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 5977884b008e..a4a06d173858 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -279,12 +279,23 @@ ifdef CONFIG_64BIT
   endif
 endif
 
+# When linking a 32-bit executable the LLVM linker cannot cope with a
+# 32-bit load address that has been sign-extended to 64 bits.  Simply
+# remove the upper 32 bits then, as it is safe to do so with other
+# linkers.
+ifdef CONFIG_64BIT
+	load-ld			= $(load-y)
+else
+	load-ld			= $(subst 0xffffffff,0x,$(load-y))
+endif
+
 KBUILD_AFLAGS	+= $(cflags-y)
 KBUILD_CFLAGS	+= $(cflags-y)
-KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y)
+KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y) -DLINKER_LOAD_ADDRESS=$(load-ld)
 KBUILD_CPPFLAGS += -DDATAOFFSET=$(if $(dataoffset-y),$(dataoffset-y),0)
 
 bootvars-y	= VMLINUX_LOAD_ADDRESS=$(load-y) \
+		  LINKER_LOAD_ADDRESS=$(load-ld) \
 		  VMLINUX_ENTRY_ADDRESS=$(entry-y) \
 		  PLATFORM="$(platform-y)" \
 		  ITS_INPUTS="$(its-y)"
diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile
index baa34e4deb78..516e593a8ee9 100644
--- a/arch/mips/boot/compressed/Makefile
+++ b/arch/mips/boot/compressed/Makefile
@@ -87,7 +87,7 @@ ifneq ($(zload-y),)
 VMLINUZ_LOAD_ADDRESS := $(zload-y)
 else
 VMLINUZ_LOAD_ADDRESS = $(shell $(obj)/calc_vmlinuz_load_addr \
-		$(obj)/vmlinux.bin $(VMLINUX_LOAD_ADDRESS))
+		$(obj)/vmlinux.bin $(LINKER_LOAD_ADDRESS))
 endif
 UIMAGE_LOADADDR = $(VMLINUZ_LOAD_ADDRESS)
 
diff --git a/arch/mips/cavium-octeon/octeon-usb.c b/arch/mips/cavium-octeon/octeon-usb.c
index bfdfaf32d2c4..75189ff2f3c7 100644
--- a/arch/mips/cavium-octeon/octeon-usb.c
+++ b/arch/mips/cavium-octeon/octeon-usb.c
@@ -517,6 +517,7 @@ static int __init dwc3_octeon_device_init(void)
 
 			res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 			if (res == NULL) {
+				put_device(&pdev->dev);
 				dev_err(&pdev->dev, "No memory resources\n");
 				return -ENXIO;
 			}
@@ -528,8 +529,10 @@ static int __init dwc3_octeon_device_init(void)
 			 * know the difference.
 			 */
 			base = devm_ioremap_resource(&pdev->dev, res);
-			if (IS_ERR(base))
+			if (IS_ERR(base)) {
+				put_device(&pdev->dev);
 				return PTR_ERR(base);
+			}
 
 			mutex_lock(&dwc3_octeon_clocks_mutex);
 			dwc3_octeon_clocks_start(&pdev->dev, (u64)base);
diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index 324dfee23dfb..c871e40b8878 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -250,7 +250,7 @@ CONFIG_MEDIA_CAMERA_SUPPORT=y
 CONFIG_MEDIA_USB_SUPPORT=y
 CONFIG_USB_VIDEO_CLASS=m
 CONFIG_DRM=y
-CONFIG_DRM_RADEON=y
+CONFIG_DRM_RADEON=m
 CONFIG_FB_RADEON=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_PLATFORM=m
diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h
index a45af3de075d..d43e4ab20b23 100644
--- a/arch/mips/include/asm/cpu-type.h
+++ b/arch/mips/include/asm/cpu-type.h
@@ -47,6 +47,7 @@ static inline int __pure __get_cpu_type(const int cpu_type)
 	case CPU_34K:
 	case CPU_1004K:
 	case CPU_74K:
+	case CPU_1074K:
 	case CPU_M14KC:
 	case CPU_M14KEC:
 	case CPU_INTERAPTIV:
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 673049bf29b6..f21dd4cb33ad 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -274,8 +274,12 @@ enum emulation_result {
 #define MIPS3_PG_SHIFT		6
 #define MIPS3_PG_FRAME		0x3fffffc0
 
+#if defined(CONFIG_64BIT)
+#define VPN2_MASK		GENMASK(cpu_vmbits - 1, 13)
+#else
 #define VPN2_MASK		0xffffe000
-#define KVM_ENTRYHI_ASID	MIPS_ENTRYHI_ASID
+#endif
+#define KVM_ENTRYHI_ASID	cpu_asid_mask(&boot_cpu_data)
 #define TLB_IS_GLOBAL(x)	((x).tlb_lo[0] & (x).tlb_lo[1] & ENTRYLO_G)
 #define TLB_VPN2(x)		((x).tlb_hi & VPN2_MASK)
 #define TLB_ASID(x)		((x).tlb_hi & KVM_ENTRYHI_ASID)
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index a6810923b3f0..a7f9acb42034 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -737,7 +737,7 @@
 
 /* MAAR bit definitions */
 #define MIPS_MAAR_VH		(_U64CAST_(1) << 63)
-#define MIPS_MAAR_ADDR		((BIT_ULL(BITS_PER_LONG - 12) - 1) << 12)
+#define MIPS_MAAR_ADDR		GENMASK_ULL(55, 12)
 #define MIPS_MAAR_ADDR_SHIFT	12
 #define MIPS_MAAR_S		(_ULCAST_(1) << 1)
 #define MIPS_MAAR_VL		(_ULCAST_(1) << 0)
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index f10e1e15e1c6..c97388229391 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -2,6 +2,10 @@
 #
 # Makefile for the Linux/MIPS kernel.
 #
+CFLAGS_signal.o		+= $(call cc-disable-warning, attribute-alias)
+CFLAGS_syscall.o	+= $(call cc-disable-warning, attribute-alias)
+CFLAGS_linux32.o	+= $(call cc-disable-warning, attribute-alias)
+CFLAGS_signal32.o	+= $(call cc-disable-warning, attribute-alias)
 
 extra-y		:= head.o vmlinux.lds
 
@@ -124,11 +128,11 @@ obj-$(CONFIG_MIPS_CPS_PM)	+= pm-cps.o
 ifeq ($(CONFIG_CPU_MIPSR2), y)
 CFLAGS_DSP 			= -DHAVE_AS_DSP
 
-CFLAGS_signal.o			= $(CFLAGS_DSP)
-CFLAGS_signal32.o		= $(CFLAGS_DSP)
-CFLAGS_process.o		= $(CFLAGS_DSP)
-CFLAGS_branch.o			= $(CFLAGS_DSP)
-CFLAGS_ptrace.o			= $(CFLAGS_DSP)
+CFLAGS_signal.o			+= $(CFLAGS_DSP)
+CFLAGS_signal32.o		+= $(CFLAGS_DSP)
+CFLAGS_process.o		+= $(CFLAGS_DSP)
+CFLAGS_branch.o			+= $(CFLAGS_DSP)
+CFLAGS_ptrace.o			+= $(CFLAGS_DSP)
 endif
 
 CPPFLAGS_vmlinux.lds		:= $(KBUILD_CFLAGS)
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index 37b9383eacd3..cf74a963839f 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -431,20 +431,20 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	.endm
 
 	.macro	__build_clear_fpe
+	CLI
+	TRACE_IRQS_OFF
 	.set	push
 	/* gas fails to assemble cfc1 for some archs (octeon).*/ \
 	.set	mips1
 	SET_HARDFLOAT
 	cfc1	a1, fcr31
 	.set	pop
-	CLI
-	TRACE_IRQS_OFF
 	.endm
 
 	.macro	__build_clear_msa_fpe
-	_cfcmsa	a1, MSA_CSR
 	CLI
 	TRACE_IRQS_OFF
+	_cfcmsa	a1, MSA_CSR
 	.endm
 
 	.macro	__build_clear_ade
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index 7f3f136572de..50d3d74001cb 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -123,9 +123,9 @@ static char *cm2_causes[32] = {
 	"COH_RD_ERR", "MMIO_WR_ERR", "MMIO_RD_ERR", "0x07",
 	"0x08", "0x09", "0x0a", "0x0b",
 	"0x0c", "0x0d", "0x0e", "0x0f",
-	"0x10", "0x11", "0x12", "0x13",
-	"0x14", "0x15", "0x16", "INTVN_WR_ERR",
-	"INTVN_RD_ERR", "0x19", "0x1a", "0x1b",
+	"0x10", "INTVN_WR_ERR", "INTVN_RD_ERR", "0x13",
+	"0x14", "0x15", "0x16", "0x17",
+	"0x18", "0x19", "0x1a", "0x1b",
 	"0x1c", "0x1d", "0x1e", "0x1f"
 };
 
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 05ed4ed411c7..abd7ee9e90ab 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -911,7 +911,17 @@ static void __init arch_mem_init(char **cmdline_p)
 				BOOTMEM_DEFAULT);
 #endif
 	device_tree_init();
+
+	/*
+	 * In order to reduce the possibility of kernel panic when failed to
+	 * get IO TLB memory under CONFIG_SWIOTLB, it is better to allocate
+	 * low memory as small as possible before plat_swiotlb_setup(), so
+	 * make sparse_init() using top-down allocation.
+	 */
+	memblock_set_bottom_up(false);
 	sparse_init();
+	memblock_set_bottom_up(true);
+
 	plat_swiotlb_setup();
 
 	dma_contiguous_reserve(PFN_PHYS(max_low_pfn));
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 45fbcbbf2504..3018582794ef 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -240,6 +240,8 @@ static int bmips_boot_secondary(int cpu, struct task_struct *idle)
  */
 static void bmips_init_secondary(void)
 {
+	bmips_cpu_setup();
+
 	switch (current_cpu_type()) {
 	case CPU_BMIPS4350:
 	case CPU_BMIPS4380:
diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c
index a6ebc8135112..79ebf349aab4 100644
--- a/arch/mips/kernel/time.c
+++ b/arch/mips/kernel/time.c
@@ -22,12 +22,77 @@
 #include <linux/smp.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
+#include <linux/cpufreq.h>
+#include <linux/delay.h>
 
 #include <asm/cpu-features.h>
 #include <asm/cpu-type.h>
 #include <asm/div64.h>
 #include <asm/time.h>
 
+#ifdef CONFIG_CPU_FREQ
+
+static DEFINE_PER_CPU(unsigned long, pcp_lpj_ref);
+static DEFINE_PER_CPU(unsigned long, pcp_lpj_ref_freq);
+static unsigned long glb_lpj_ref;
+static unsigned long glb_lpj_ref_freq;
+
+static int cpufreq_callback(struct notifier_block *nb,
+			    unsigned long val, void *data)
+{
+	int cpu;
+	struct cpufreq_freqs *freq = data;
+
+	/*
+	 * Skip lpj numbers adjustment if the CPU-freq transition is safe for
+	 * the loops delay. (Is this possible?)
+	 */
+	if (freq->flags & CPUFREQ_CONST_LOOPS)
+		return NOTIFY_OK;
+
+	/* Save the initial values of the lpjes for future scaling. */
+	if (!glb_lpj_ref) {
+		glb_lpj_ref = boot_cpu_data.udelay_val;
+		glb_lpj_ref_freq = freq->old;
+
+		for_each_online_cpu(cpu) {
+			per_cpu(pcp_lpj_ref, cpu) =
+				cpu_data[cpu].udelay_val;
+			per_cpu(pcp_lpj_ref_freq, cpu) = freq->old;
+		}
+	}
+
+	cpu = freq->cpu;
+	/*
+	 * Adjust global lpj variable and per-CPU udelay_val number in
+	 * accordance with the new CPU frequency.
+	 */
+	if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
+	    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
+		loops_per_jiffy = cpufreq_scale(glb_lpj_ref,
+						glb_lpj_ref_freq,
+						freq->new);
+
+		cpu_data[cpu].udelay_val = cpufreq_scale(per_cpu(pcp_lpj_ref, cpu),
+					   per_cpu(pcp_lpj_ref_freq, cpu), freq->new);
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block cpufreq_notifier = {
+	.notifier_call  = cpufreq_callback,
+};
+
+static int __init register_cpufreq_notifier(void)
+{
+	return cpufreq_register_notifier(&cpufreq_notifier,
+					 CPUFREQ_TRANSITION_NOTIFIER);
+}
+core_initcall(register_cpufreq_notifier);
+
+#endif /* CONFIG_CPU_FREQ */
+
 /*
  * forward reference
  */
diff --git a/arch/mips/kernel/topology.c b/arch/mips/kernel/topology.c
index cd3e1f82e1a5..08ad6371fbe0 100644
--- a/arch/mips/kernel/topology.c
+++ b/arch/mips/kernel/topology.c
@@ -20,7 +20,7 @@ static int __init topology_init(void)
 	for_each_present_cpu(i) {
 		struct cpu *c = &per_cpu(cpu_devices, i);
 
-		c->hotpluggable = 1;
+		c->hotpluggable = !!i;
 		ret = register_cpu(c, i);
 		if (ret)
 			printk(KERN_WARNING "topology_init: register_cpu %d "
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 583aed906933..4a23d89e251c 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2135,6 +2135,7 @@ static void configure_status(void)
 
 	change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX,
 			 status_set);
+	back_to_back_c0_hazard();
 }
 
 unsigned int hwrena;
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 36f2e860ba3e..be63fff95b2a 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -50,7 +50,7 @@ SECTIONS
 	/* . = 0xa800000000300000; */
 	. = 0xffffffff80300000;
 #endif
-	. = VMLINUX_LOAD_ADDRESS;
+	. = LINKER_LOAD_ADDRESS;
 	/* read-only */
 	_text = .;	/* Text and read-only data */
 	.text : {
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index aa6c365f2559..8614225e92eb 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -131,6 +131,8 @@ void kvm_arch_check_processor_compat(void *rtn)
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	switch (type) {
+	case KVM_VM_MIPS_AUTO:
+		break;
 #ifdef CONFIG_KVM_MIPS_VZ
 	case KVM_VM_MIPS_VZ:
 #else
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index c463bdad45c7..b7f9ef80dac7 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -2,6 +2,7 @@
 #
 # Makefile for the Linux/MIPS-specific parts of the memory manager.
 #
+CFLAGS_cache.o			+= $(call cc-disable-warning, attribute-alias)
 
 obj-y				+= cache.o dma-default.o extable.o fault.o \
 				   gup.o init.o mmap.o page.o page-funcs.o \
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index bacd67f5d71d..e4de107bf7fd 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1781,7 +1781,11 @@ static void setup_scache(void)
 				printk("MIPS secondary cache %ldkB, %s, linesize %d bytes.\n",
 				       scache_size >> 10,
 				       way_string[c->scache.ways], c->scache.linesz);
+
+				if (current_cpu_type() == CPU_BMIPS5000)
+					c->options |= MIPS_CPU_INCLUSIVE_CACHES;
 			}
+
 #else
 			if (!(c->scache.flags & MIPS_CACHE_NOT_PRESENT))
 				panic("Dunno how to handle MIPS32 / MIPS64 second level cache");
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index b55c74a7f7a4..91fd469f782d 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -489,6 +489,7 @@ static void __maybe_unused build_tlb_probe_entry(u32 **p)
 	case CPU_R4700:
 	case CPU_R5000:
 	case CPU_NEVADA:
+	case CPU_4KC:
 		uasm_i_nop(p);
 		uasm_i_tlbp(p);
 		break;
@@ -537,6 +538,7 @@ void build_tlb_write_entry(u32 **p, struct uasm_label **l,
 
 	case CPU_R4600:
 	case CPU_R4700:
+	case CPU_4KC:
 		uasm_i_nop(p);
 		tlbw(p);
 		uasm_i_nop(p);
@@ -562,7 +564,6 @@ void build_tlb_write_entry(u32 **p, struct uasm_label **l,
 	case CPU_R12000:
 	case CPU_R14000:
 	case CPU_R16000:
-	case CPU_4KC:
 	case CPU_4KEC:
 	case CPU_M14KC:
 	case CPU_M14KEC:
diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c
index f9407e170476..c6af7047eb0d 100644
--- a/arch/mips/sni/a20r.c
+++ b/arch/mips/sni/a20r.c
@@ -143,7 +143,10 @@ static struct platform_device sc26xx_pdev = {
 	},
 };
 
-static u32 a20r_ack_hwint(void)
+/*
+ * Trigger chipset to update CPU's CAUSE IP field
+ */
+static u32 a20r_update_cause_ip(void)
 {
 	u32 status = read_c0_status();
 
@@ -205,12 +208,14 @@ static void a20r_hwint(void)
 	int irq;
 
 	clear_c0_status(IE_IRQ0);
-	status = a20r_ack_hwint();
+	status = a20r_update_cause_ip();
 	cause = read_c0_cause();
 
 	irq = ffs(((cause & status) >> 8) & 0xf8);
 	if (likely(irq > 0))
 		do_IRQ(SNI_A20R_IRQ_BASE + irq - 1);
+
+	a20r_update_cause_ip();
 	set_c0_status(IE_IRQ0);
 }
 
diff --git a/arch/mips/vdso/genvdso.c b/arch/mips/vdso/genvdso.c
index 530a36f465ce..afcc86726448 100644
--- a/arch/mips/vdso/genvdso.c
+++ b/arch/mips/vdso/genvdso.c
@@ -126,6 +126,7 @@ static void *map_vdso(const char *path, size_t *_size)
 	if (fstat(fd, &stat) != 0) {
 		fprintf(stderr, "%s: Failed to stat '%s': %s\n", program_name,
 			path, strerror(errno));
+		close(fd);
 		return NULL;
 	}
 
@@ -134,6 +135,7 @@ static void *map_vdso(const char *path, size_t *_size)
 	if (addr == MAP_FAILED) {
 		fprintf(stderr, "%s: Failed to map '%s': %s\n", program_name,
 			path, strerror(errno));
+		close(fd);
 		return NULL;
 	}
 
@@ -143,6 +145,7 @@ static void *map_vdso(const char *path, size_t *_size)
 	if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0) {
 		fprintf(stderr, "%s: '%s' is not an ELF file\n", program_name,
 			path);
+		close(fd);
 		return NULL;
 	}
 
@@ -154,6 +157,7 @@ static void *map_vdso(const char *path, size_t *_size)
 	default:
 		fprintf(stderr, "%s: '%s' has invalid ELF class\n",
 			program_name, path);
+		close(fd);
 		return NULL;
 	}
 
@@ -165,6 +169,7 @@ static void *map_vdso(const char *path, size_t *_size)
 	default:
 		fprintf(stderr, "%s: '%s' has invalid ELF data order\n",
 			program_name, path);
+		close(fd);
 		return NULL;
 	}
 
@@ -172,15 +177,18 @@ static void *map_vdso(const char *path, size_t *_size)
 		fprintf(stderr,
 			"%s: '%s' has invalid ELF machine (expected EM_MIPS)\n",
 			program_name, path);
+		close(fd);
 		return NULL;
 	} else if (swap_uint16(ehdr->e_type) != ET_DYN) {
 		fprintf(stderr,
 			"%s: '%s' has invalid ELF type (expected ET_DYN)\n",
 			program_name, path);
+		close(fd);
 		return NULL;
 	}
 
 	*_size = stat.st_size;
+	close(fd);
 	return addr;
 }
 
@@ -284,10 +292,12 @@ int main(int argc, char **argv)
 	/* Calculate and write symbol offsets to <output file> */
 	if (!get_symbols(dbg_vdso_path, dbg_vdso)) {
 		unlink(out_path);
+		fclose(out_file);
 		return EXIT_FAILURE;
 	}
 
 	fprintf(out_file, "};\n");
+	fclose(out_file);
 
 	return EXIT_SUCCESS;
 }
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index bbf5c79cce7a..8b204cd1f531 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -58,8 +58,12 @@
 /* Ensure that addr is below task's addr_limit */
 #define __addr_ok(addr) ((unsigned long) addr < get_fs())
 
-#define access_ok(type, addr, size) \
-	__range_ok((unsigned long)addr, (unsigned long)size)
+#define access_ok(type, addr, size)						\
+({ 									\
+	unsigned long __ao_addr = (unsigned long)(addr);		\
+	unsigned long __ao_size = (unsigned long)(size);		\
+	__range_ok(__ao_addr, __ao_size);				\
+})
 
 /*
  * These are the main single-value transfer routines.  They automatically
diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S
index 1107d34e45bf..0fdfa7142f4b 100644
--- a/arch/openrisc/kernel/entry.S
+++ b/arch/openrisc/kernel/entry.S
@@ -1102,13 +1102,13 @@ ENTRY(__sys_clone)
 	l.movhi	r29,hi(sys_clone)
 	l.ori	r29,r29,lo(sys_clone)
 	l.j	_fork_save_extra_regs_and_call
-	 l.addi	r7,r1,0
+	 l.nop
 
 ENTRY(__sys_fork)
 	l.movhi	r29,hi(sys_fork)
 	l.ori	r29,r29,lo(sys_fork)
 	l.j	_fork_save_extra_regs_and_call
-	 l.addi	r3,r1,0
+	 l.nop
 
 ENTRY(sys_rt_sigreturn)
 	l.jal	_sys_rt_sigreturn
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index bc54addd589f..614bcc7673f5 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -258,6 +258,8 @@ atomic64_set(atomic64_t *v, s64 i)
 	_atomic_spin_unlock_irqrestore(v, flags);
 }
 
+#define atomic64_set_release(v, i)	atomic64_set((v), (i))
+
 static __inline__ s64
 atomic64_read(const atomic64_t *v)
 {
diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h
index dbaaca84f27f..640d46edf32e 100644
--- a/arch/parisc/include/asm/barrier.h
+++ b/arch/parisc/include/asm/barrier.h
@@ -26,6 +26,67 @@
 #define __smp_rmb()	mb()
 #define __smp_wmb()	mb()
 
+#define __smp_store_release(p, v)					\
+do {									\
+	typeof(p) __p = (p);						\
+        union { typeof(*p) __val; char __c[1]; } __u =			\
+                { .__val = (__force typeof(*p)) (v) };			\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile("stb,ma %0,0(%1)"				\
+				: : "r"(*(__u8 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile("sth,ma %0,0(%1)"				\
+				: : "r"(*(__u16 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile("stw,ma %0,0(%1)"				\
+				: : "r"(*(__u32 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		if (IS_ENABLED(CONFIG_64BIT))				\
+			asm volatile("std,ma %0,0(%1)"			\
+				: : "r"(*(__u64 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	}								\
+} while (0)
+
+#define __smp_load_acquire(p)						\
+({									\
+	union { typeof(*p) __val; char __c[1]; } __u;			\
+	typeof(p) __p = (p);						\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile("ldb,ma 0(%1),%0"				\
+				: "=r"(*(__u8 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile("ldh,ma 0(%1),%0"				\
+				: "=r"(*(__u16 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile("ldw,ma 0(%1),%0"				\
+				: "=r"(*(__u32 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		if (IS_ENABLED(CONFIG_64BIT))				\
+			asm volatile("ldd,ma 0(%1),%0"			\
+				: "=r"(*(__u64 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	}								\
+	__u.__val;							\
+})
 #include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index ab5c215cf46c..068958575871 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -60,6 +60,7 @@ extern void __cmpxchg_called_with_bad_pointer(void);
 extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old,
 				   unsigned int new_);
 extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_);
+extern u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new_);
 
 /* don't worry...optimizer will get rid of most of this */
 static inline unsigned long
@@ -71,6 +72,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
 #endif
 	case 4: return __cmpxchg_u32((unsigned int *)ptr,
 				     (unsigned int)old, (unsigned int)new_);
+	case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_);
 	}
 	__cmpxchg_called_with_bad_pointer();
 	return old;
diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c
index 70ffbcf889b8..2e4d1f05a926 100644
--- a/arch/parisc/lib/bitops.c
+++ b/arch/parisc/lib/bitops.c
@@ -79,3 +79,15 @@ unsigned long __cmpxchg_u32(volatile unsigned int *ptr, unsigned int old, unsign
 	_atomic_spin_unlock_irqrestore(ptr, flags);
 	return (unsigned long)prev;
 }
+
+u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new)
+{
+	unsigned long flags;
+	u8 prev;
+
+	_atomic_spin_lock_irqsave(ptr, flags);
+	if ((prev = *ptr) == old)
+		*ptr = new;
+	_atomic_spin_unlock_irqrestore(ptr, flags);
+	return prev;
+}
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index cc700f7dda54..8be075f81ce6 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -608,7 +608,7 @@ void __init mem_init(void)
 			> BITS_PER_LONG);
 
 	high_memory = __va((max_pfn << PAGE_SHIFT));
-	set_max_mapnr(page_to_pfn(virt_to_page(high_memory - 1)) + 1);
+	set_max_mapnr(max_low_pfn);
 	free_all_bootmem();
 
 #ifdef CONFIG_PA11
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 9c78ef298257..85a2362d3ed2 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -291,6 +291,9 @@ PHONY += $(BOOT_TARGETS1) $(BOOT_TARGETS2)
 
 boot := arch/$(ARCH)/boot
 
+# These targets cannot be built in parallel
+.NOTPARALLEL: $(BOOT_TARGETS)
+
 $(BOOT_TARGETS1): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
 $(BOOT_TARGETS2): vmlinux
@@ -392,7 +395,7 @@ endif
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 
-archprepare: checkbin
+archprepare: checkbin arch/powerpc/lib/crtsavres.o
 
 # Use the file '.tmp_gas_check' for binutils tests, as gas won't output
 # to stdout and these checks are run even on install targets.
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 5807c9d8e56d..82b975da1e03 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -24,7 +24,7 @@ compress-$(CONFIG_KERNEL_GZIP) := CONFIG_KERNEL_GZIP
 compress-$(CONFIG_KERNEL_XZ)   := CONFIG_KERNEL_XZ
 
 BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
-		 -fno-strict-aliasing -Os -msoft-float -mno-altivec -mno-vsx \
+		 -fno-strict-aliasing -msoft-float -mno-altivec -mno-vsx \
 		 -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
 		 -D$(compress-y)
 
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index 6daa56f8895c..5f743db4c9f8 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -111,7 +111,6 @@ CONFIG_FB_NVIDIA=y
 CONFIG_FB_NVIDIA_I2C=y
 CONFIG_FB_RADEON=y
 # CONFIG_LCD_CLASS_DEVICE is not set
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
 CONFIG_SOUND=y
 CONFIG_SND=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index da0e8d535eb8..b1b072a3f789 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -781,7 +781,6 @@ CONFIG_FB_TRIDENT=m
 CONFIG_FB_SM501=m
 CONFIG_FB_IBM_GXT4500=y
 CONFIG_LCD_PLATFORM=m
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
 CONFIG_LOGO=y
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index bcb79a96a6c8..618ee2c0ed53 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -898,10 +898,25 @@ extern struct page *pgd_page(pgd_t pgd);
 #define pud_page_vaddr(pud)	__va(pud_val(pud) & ~PUD_MASKED_BITS)
 #define pgd_page_vaddr(pgd)	__va(pgd_val(pgd) & ~PGD_MASKED_BITS)
 
-#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1))
-#define pud_index(address) (((address) >> (PUD_SHIFT)) & (PTRS_PER_PUD - 1))
-#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1))
-#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1))
+static inline unsigned long pgd_index(unsigned long address)
+{
+	return (address >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1);
+}
+
+static inline unsigned long pud_index(unsigned long address)
+{
+	return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
+}
+
+static inline unsigned long pmd_index(unsigned long address)
+{
+	return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
+}
+
+static inline unsigned long pte_index(unsigned long address)
+{
+	return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
+}
 
 /*
  * Find an entry in a page-table-directory.  We combine the address region
diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h
index dce863a7635c..8e5b7d0b851c 100644
--- a/arch/powerpc/include/asm/percpu.h
+++ b/arch/powerpc/include/asm/percpu.h
@@ -10,8 +10,6 @@
 
 #ifdef CONFIG_SMP
 
-#include <asm/paca.h>
-
 #define __my_cpu_offset local_paca->data_offset
 
 #endif /* CONFIG_SMP */
@@ -19,4 +17,6 @@
 
 #include <asm-generic/percpu.h>
 
+#include <asm/paca.h>
+
 #endif /* _ASM_POWERPC_PERCPU_H_ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 681f966b7211..b9e457d4dc66 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -3,7 +3,9 @@
 # Makefile for the linux kernel.
 #
 
-CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
+CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"' $(call cc-disable-warning, attribute-alias)
+CFLAGS_ptrace.o		+= $(call cc-disable-warning, array-bounds)
+CFLAGS_syscalls.o	+= $(call cc-disable-warning, attribute-alias)
 
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 9daede99c131..f52e2c55a12b 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -189,7 +189,7 @@ __init_LPCR_ISA300:
 
 __init_FSCR:
 	mfspr	r3,SPRN_FSCR
-	ori	r3,r3,FSCR_TAR|FSCR_DSCR|FSCR_EBB
+	ori	r3,r3,FSCR_TAR|FSCR_EBB
 	mtspr	SPRN_FSCR,r3
 	blr
 
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 66f33e7f8d40..a39a1a0d844e 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -100,7 +100,8 @@ static u64 dma_iommu_get_required_mask(struct device *dev)
 	if (!tbl)
 		return 0;
 
-	mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1);
+	mask = 1ULL << (fls_long(tbl->it_offset + tbl->it_size) +
+			tbl->it_page_shift - 1);
 	mask += mask - 1;
 
 	return mask;
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 7ed2b1b6643c..09134df01bfd 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -385,6 +385,14 @@ static int __init feat_enable_dscr(struct dt_cpu_feature *f)
 {
 	u64 lpcr;
 
+	/*
+	 * Linux relies on FSCR[DSCR] being clear, so that we can take the
+	 * facility unavailable interrupt and track the task's usage of DSCR.
+	 * See facility_unavailable_exception().
+	 * Clear the bit here so that feat_enable() doesn't set it.
+	 */
+	f->fscr_bit_nr = -1;
+
 	feat_enable(f);
 
 	lpcr = mfspr(SPRN_LPCR);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index d2ba7936d0d3..7b46576962bf 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -506,7 +506,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	rc = 1;
 	if (pe->state & EEH_PE_ISOLATED) {
 		pe->check_count++;
-		if (pe->check_count % EEH_MAX_FAILS == 0) {
+		if (pe->check_count == EEH_MAX_FAILS) {
 			dn = pci_device_to_OF_node(dev);
 			if (dn)
 				location = of_get_property(dn, "ibm,loc-code",
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index 9dafd7af39b8..cb4d6cd949fc 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -113,11 +113,12 @@ void machine_kexec(struct kimage *image)
 
 void __init reserve_crashkernel(void)
 {
-	unsigned long long crash_size, crash_base;
+	unsigned long long crash_size, crash_base, total_mem_sz;
 	int ret;
 
+	total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size();
 	/* use common parsing */
-	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, total_mem_sz,
 			&crash_size, &crash_base);
 	if (ret == 0 && crash_size > 0) {
 		crashk_res.start = crash_base;
@@ -176,6 +177,7 @@ void __init reserve_crashkernel(void)
 	/* Crash kernel trumps memory limit */
 	if (memory_limit && memory_limit <= crashk_res.end) {
 		memory_limit = crashk_res.end + 1;
+		total_mem_sz = memory_limit;
 		printk("Adjusted memory limit for crashkernel, now 0x%llx\n",
 		       memory_limit);
 	}
@@ -184,7 +186,7 @@ void __init reserve_crashkernel(void)
 			"for crashkernel (System RAM: %ldMB)\n",
 			(unsigned long)(crash_size >> 20),
 			(unsigned long)(crashk_res.start >> 20),
-			(unsigned long)(memblock_phys_mem_size() >> 20));
+			(unsigned long)(total_mem_sz >> 20));
 
 	if (!memblock_is_region_memory(crashk_res.start, crash_size) ||
 	    memblock_reserve(crashk_res.start, crash_size)) {
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index d96b28415090..bbe9c57dd1a3 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -658,6 +658,23 @@ static void __init early_reserve_mem(void)
 #endif
 }
 
+#ifdef CONFIG_PPC64
+static void __init save_fscr_to_task(void)
+{
+	/*
+	 * Ensure the init_task (pid 0, aka swapper) uses the value of FSCR we
+	 * have configured via the device tree features or via __init_FSCR().
+	 * That value will then be propagated to pid 1 (init) and all future
+	 * processes.
+	 */
+	if (early_cpu_has_feature(CPU_FTR_ARCH_207S))
+		init_task.thread.fscr = mfspr(SPRN_FSCR);
+}
+#else
+static inline void save_fscr_to_task(void) {};
+#endif
+
+
 void __init early_init_devtree(void *params)
 {
 	phys_addr_t limit;
@@ -743,6 +760,8 @@ void __init early_init_devtree(void *params)
 		BUG();
 	}
 
+	save_fscr_to_task();
+
 #if defined(CONFIG_SMP) && defined(CONFIG_PPC64)
 	/* We'll later wait for secondaries to check in; there are
 	 * NCPUS-1 non-boot CPUs  :-)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 3c9457420aee..0f1a888c04a8 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -357,11 +357,11 @@ out:
 #ifdef CONFIG_PPC_BOOK3S_64
 	BUG_ON(get_paca()->in_nmi == 0);
 	if (get_paca()->in_nmi > 1)
-		nmi_panic(regs, "Unrecoverable nested System Reset");
+		die("Unrecoverable nested System Reset", regs, SIGABRT);
 #endif
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
-		nmi_panic(regs, "Unrecoverable System Reset");
+		die("Unrecoverable System Reset", regs, SIGABRT);
 
 	if (!nested)
 		nmi_exit();
@@ -701,7 +701,7 @@ void machine_check_exception(struct pt_regs *regs)
 
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
-		nmi_panic(regs, "Unrecoverable Machine check");
+		die("Unrecoverable Machine check", regs, SIGBUS);
 
 	return;
 
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 22b01a3962f0..3edaee28b638 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -704,7 +704,7 @@ int vdso_getcpu_init(void)
 	node = cpu_to_node(cpu);
 	WARN_ON_ONCE(node > 0xffff);
 
-	val = (cpu & 0xfff) | ((node & 0xffff) << 16);
+	val = (cpu & 0xffff) | ((node & 0xffff) << 16);
 	mtspr(SPRN_SPRG_VDSO_WRITE, val);
 	get_paca()->sprg_vdso = val;
 
diff --git a/arch/powerpc/kernel/vdso32/sigtramp.S b/arch/powerpc/kernel/vdso32/sigtramp.S
index cf0c9c9c24f9..78c88af3890b 100644
--- a/arch/powerpc/kernel/vdso32/sigtramp.S
+++ b/arch/powerpc/kernel/vdso32/sigtramp.S
@@ -251,6 +251,40 @@ V_FUNCTION_END(__kernel_sigtramp_rt32)
   vsave_msr1 (31);							\
   vsave_msr2 (33, 32*16+12);						\
   vsave      (32, 32*16)
+#elif defined(CONFIG_SPE)
+#define EH_FRAME_VMX \
+  rsave (113, VREGS);							\
+  rsave (114, VREGS + 1*4);						\
+  rsave (115, VREGS + 2*4);						\
+  rsave (116, VREGS + 3*4);						\
+  rsave (117, VREGS + 4*4);						\
+  rsave (118, VREGS + 5*4);						\
+  rsave (119, VREGS + 6*4);						\
+  rsave (120, VREGS + 7*4);						\
+  rsave (121, VREGS + 8*4);						\
+  rsave (122, VREGS + 9*4);						\
+  rsave (123, VREGS + 10*4);						\
+  rsave (124, VREGS + 11*4);						\
+  rsave (125, VREGS + 12*4);						\
+  rsave (126, VREGS + 13*4);						\
+  rsave (127, VREGS + 14*4);						\
+  rsave (128, VREGS + 15*4);						\
+  rsave (129, VREGS + 16*4);						\
+  rsave (130, VREGS + 17*4);						\
+  rsave (131, VREGS + 18*4);						\
+  rsave (132, VREGS + 19*4);						\
+  rsave (133, VREGS + 20*4);						\
+  rsave (134, VREGS + 21*4);						\
+  rsave (135, VREGS + 22*4);						\
+  rsave (136, VREGS + 23*4);						\
+  rsave (137, VREGS + 24*4);						\
+  rsave (138, VREGS + 25*4);						\
+  rsave (139, VREGS + 26*4);						\
+  rsave (140, VREGS + 27*4);						\
+  rsave (141, VREGS + 28*4);						\
+  rsave (142, VREGS + 29*4);						\
+  rsave (143, VREGS + 30*4);						\
+  rsave (144, VREGS + 31*4);
 #else
 #define EH_FRAME_VMX
 #endif
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 5fc8a010fdf0..ebe97e5500ee 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -22,6 +22,7 @@
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <linux/pagemap.h>
 #include <linux/ptrace.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
@@ -66,15 +67,11 @@ static inline bool notify_page_fault(struct pt_regs *regs)
 }
 
 /*
- * Check whether the instruction at regs->nip is a store using
+ * Check whether the instruction inst is a store using
  * an update addressing form which will update r1.
  */
-static bool store_updates_sp(struct pt_regs *regs)
+static bool store_updates_sp(unsigned int inst)
 {
-	unsigned int inst;
-
-	if (get_user(inst, (unsigned int __user *)regs->nip))
-		return false;
 	/* check for 1 in the rA field */
 	if (((inst >> 16) & 0x1f) != 1)
 		return false;
@@ -227,20 +224,24 @@ static bool bad_kernel_fault(bool is_exec, unsigned long error_code,
 	return is_exec || (address >= TASK_SIZE);
 }
 
+// This comes from 64-bit struct rt_sigframe + __SIGNAL_FRAMESIZE
+#define SIGFRAME_MAX_SIZE	(4096 + 128)
+
 static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
-				struct vm_area_struct *vma,
-				bool store_update_sp)
+				struct vm_area_struct *vma, unsigned int flags,
+				bool *must_retry)
 {
 	/*
 	 * N.B. The POWER/Open ABI allows programs to access up to
 	 * 288 bytes below the stack pointer.
-	 * The kernel signal delivery code writes up to about 1.5kB
+	 * The kernel signal delivery code writes a bit over 4KB
 	 * below the stack pointer (r1) before decrementing it.
 	 * The exec code can write slightly over 640kB to the stack
 	 * before setting the user r1.  Thus we allow the stack to
 	 * expand to 1MB without further checks.
 	 */
 	if (address + 0x100000 < vma->vm_end) {
+		unsigned int __user *nip = (unsigned int __user *)regs->nip;
 		/* get user regs even if this fault is in kernel mode */
 		struct pt_regs *uregs = current->thread.regs;
 		if (uregs == NULL)
@@ -258,8 +259,22 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
 		 * between the last mapped region and the stack will
 		 * expand the stack rather than segfaulting.
 		 */
-		if (address + 2048 < uregs->gpr[1] && !store_update_sp)
-			return true;
+		if (address + SIGFRAME_MAX_SIZE >= uregs->gpr[1])
+			return false;
+
+		if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) &&
+		    access_ok(VERIFY_READ, nip, sizeof(*nip))) {
+			unsigned int inst;
+			int res;
+
+			pagefault_disable();
+			res = __get_user_inatomic(inst, nip);
+			pagefault_enable();
+			if (!res)
+				return !store_updates_sp(inst);
+			*must_retry = true;
+		}
+		return true;
 	}
 	return false;
 }
@@ -392,7 +407,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	int is_user = user_mode(regs);
 	int is_write = page_fault_is_write(error_code);
 	int fault, major = 0;
-	bool store_update_sp = false;
+	bool must_retry = false;
 
 	if (notify_page_fault(regs))
 		return 0;
@@ -439,9 +454,6 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * can result in fault, which will cause a deadlock when called with
 	 * mmap_sem held
 	 */
-	if (is_write && is_user)
-		store_update_sp = store_updates_sp(regs);
-
 	if (is_user)
 		flags |= FAULT_FLAG_USER;
 	if (is_write)
@@ -488,8 +500,17 @@ retry:
 		return bad_area(regs, address);
 
 	/* The stack is being expanded, check if it's valid */
-	if (unlikely(bad_stack_expansion(regs, address, vma, store_update_sp)))
-		return bad_area(regs, address);
+	if (unlikely(bad_stack_expansion(regs, address, vma, flags,
+					 &must_retry))) {
+		if (!must_retry)
+			return bad_area(regs, address);
+
+		up_read(&mm->mmap_sem);
+		if (fault_in_pages_readable((const char __user *)regs->nip,
+					    sizeof(unsigned int)))
+			return bad_area_nosemaphore(regs, address);
+		goto retry;
+	}
 
 	/* Try to expand it */
 	if (unlikely(expand_stack(vma, address)))
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 2502fe3bfb54..e696b8eac920 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -324,6 +324,7 @@ void slb_initialize(void)
 	asm volatile("isync":::"memory");
 	asm volatile("slbmte  %0,%0"::"r" (0) : "memory");
 	asm volatile("isync; slbia; isync":::"memory");
+	mb();
 	create_shadowed_slbe(PAGE_OFFSET, mmu_kernel_ssize, lflags, LINEAR_INDEX);
 	create_shadowed_slbe(VMALLOC_START, mmu_kernel_ssize, vflags, VMALLOC_INDEX);
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 3188040022c4..78f75e48dfe7 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2096,6 +2096,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 
 		if (perf_event_overflow(event, &data, regs))
 			power_pmu_stop(event, 0);
+	} else if (period) {
+		/* Account for interrupt in case of invalid SIAR */
+		if (perf_event_account_interrupt(event))
+			power_pmu_stop(event, 0);
 	}
 }
 
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 72238eedc360..2bb798918483 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -1413,16 +1413,6 @@ static void h_24x7_event_read(struct perf_event *event)
 			h24x7hw = &get_cpu_var(hv_24x7_hw);
 			h24x7hw->events[i] = event;
 			put_cpu_var(h24x7hw);
-			/*
-			 * Clear the event count so we can compute the _change_
-			 * in the 24x7 raw counter value at the end of the txn.
-			 *
-			 * Note that we could alternatively read the 24x7 value
-			 * now and save its value in event->hw.prev_count. But
-			 * that would require issuing a hcall, which would then
-			 * defeat the purpose of using the txn interface.
-			 */
-			local64_set(&event->count, 0);
 		}
 
 		put_cpu_var(hv_24x7_reqb);
diff --git a/arch/powerpc/platforms/4xx/pci.c b/arch/powerpc/platforms/4xx/pci.c
index 73e6b36bcd51..256943af58aa 100644
--- a/arch/powerpc/platforms/4xx/pci.c
+++ b/arch/powerpc/platforms/4xx/pci.c
@@ -1242,7 +1242,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port)
 	if (mbase == NULL) {
 		printk(KERN_ERR "%pOF: Can't map internal config space !",
 			port->node);
-		goto done;
+		return;
 	}
 
 	while (attempt && (0 == (in_le32(mbase + PECFG_460SX_DLLSTA)
@@ -1252,9 +1252,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port)
 	}
 	if (attempt)
 		port->link = 1;
-done:
 	iounmap(mbase);
-
 }
 
 static struct ppc4xx_pciex_hwops ppc460sx_pcie_hwops __initdata = {
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 9f5958f16923..741a8fa8a3e6 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -46,6 +46,7 @@ config SPU_FS
 	tristate "SPU file system"
 	default m
 	depends on PPC_CELL
+	depends on COREDUMP
 	select SPU_BASE
 	help
 	  The SPU file system is used to access Synergistic Processing
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 5ffcdeb1eb17..9d9fffaedeef 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -1988,8 +1988,9 @@ static ssize_t __spufs_mbox_info_read(struct spu_context *ctx,
 static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf,
 				   size_t len, loff_t *pos)
 {
-	int ret;
 	struct spu_context *ctx = file->private_data;
+	u32 stat, data;
+	int ret;
 
 	if (!access_ok(VERIFY_WRITE, buf, len))
 		return -EFAULT;
@@ -1998,11 +1999,16 @@ static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 	spin_lock(&ctx->csa.register_lock);
-	ret = __spufs_mbox_info_read(ctx, buf, len, pos);
+	stat = ctx->csa.prob.mb_stat_R;
+	data = ctx->csa.prob.pu_mb_R;
 	spin_unlock(&ctx->csa.register_lock);
 	spu_release_saved(ctx);
 
-	return ret;
+	/* EOF if there's no entry in the mbox */
+	if (!(stat & 0x0000ff))
+		return 0;
+
+	return simple_read_from_buffer(buf, len, pos, &data, sizeof(data));
 }
 
 static const struct file_operations spufs_mbox_info_fops = {
@@ -2029,6 +2035,7 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf,
 				   size_t len, loff_t *pos)
 {
 	struct spu_context *ctx = file->private_data;
+	u32 stat, data;
 	int ret;
 
 	if (!access_ok(VERIFY_WRITE, buf, len))
@@ -2038,11 +2045,16 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 	spin_lock(&ctx->csa.register_lock);
-	ret = __spufs_ibox_info_read(ctx, buf, len, pos);
+	stat = ctx->csa.prob.mb_stat_R;
+	data = ctx->csa.priv2.puint_mb_R;
 	spin_unlock(&ctx->csa.register_lock);
 	spu_release_saved(ctx);
 
-	return ret;
+	/* EOF if there's no entry in the ibox */
+	if (!(stat & 0xff0000))
+		return 0;
+
+	return simple_read_from_buffer(buf, len, pos, &data, sizeof(data));
 }
 
 static const struct file_operations spufs_ibox_info_fops = {
@@ -2051,6 +2063,11 @@ static const struct file_operations spufs_ibox_info_fops = {
 	.llseek  = generic_file_llseek,
 };
 
+static size_t spufs_wbox_info_cnt(struct spu_context *ctx)
+{
+	return (4 - ((ctx->csa.prob.mb_stat_R & 0x00ff00) >> 8)) * sizeof(u32);
+}
+
 static ssize_t __spufs_wbox_info_read(struct spu_context *ctx,
 			char __user *buf, size_t len, loff_t *pos)
 {
@@ -2059,7 +2076,7 @@ static ssize_t __spufs_wbox_info_read(struct spu_context *ctx,
 	u32 wbox_stat;
 
 	wbox_stat = ctx->csa.prob.mb_stat_R;
-	cnt = 4 - ((wbox_stat & 0x00ff00) >> 8);
+	cnt = spufs_wbox_info_cnt(ctx);
 	for (i = 0; i < cnt; i++) {
 		data[i] = ctx->csa.spu_mailbox_data[i];
 	}
@@ -2072,7 +2089,8 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf,
 				   size_t len, loff_t *pos)
 {
 	struct spu_context *ctx = file->private_data;
-	int ret;
+	u32 data[ARRAY_SIZE(ctx->csa.spu_mailbox_data)];
+	int ret, count;
 
 	if (!access_ok(VERIFY_WRITE, buf, len))
 		return -EFAULT;
@@ -2081,11 +2099,13 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 	spin_lock(&ctx->csa.register_lock);
-	ret = __spufs_wbox_info_read(ctx, buf, len, pos);
+	count = spufs_wbox_info_cnt(ctx);
+	memcpy(&data, &ctx->csa.spu_mailbox_data, sizeof(data));
 	spin_unlock(&ctx->csa.register_lock);
 	spu_release_saved(ctx);
 
-	return ret;
+	return simple_read_from_buffer(buf, len, pos, &data,
+				count * sizeof(u32));
 }
 
 static const struct file_operations spufs_wbox_info_fops = {
@@ -2094,27 +2114,33 @@ static const struct file_operations spufs_wbox_info_fops = {
 	.llseek  = generic_file_llseek,
 };
 
-static ssize_t __spufs_dma_info_read(struct spu_context *ctx,
-			char __user *buf, size_t len, loff_t *pos)
+static void spufs_get_dma_info(struct spu_context *ctx,
+		struct spu_dma_info *info)
 {
-	struct spu_dma_info info;
-	struct mfc_cq_sr *qp, *spuqp;
 	int i;
 
-	info.dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW;
-	info.dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0];
-	info.dma_info_status = ctx->csa.spu_chnldata_RW[24];
-	info.dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25];
-	info.dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27];
+	info->dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW;
+	info->dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0];
+	info->dma_info_status = ctx->csa.spu_chnldata_RW[24];
+	info->dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25];
+	info->dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27];
 	for (i = 0; i < 16; i++) {
-		qp = &info.dma_info_command_data[i];
-		spuqp = &ctx->csa.priv2.spuq[i];
+		struct mfc_cq_sr *qp = &info->dma_info_command_data[i];
+		struct mfc_cq_sr *spuqp = &ctx->csa.priv2.spuq[i];
 
 		qp->mfc_cq_data0_RW = spuqp->mfc_cq_data0_RW;
 		qp->mfc_cq_data1_RW = spuqp->mfc_cq_data1_RW;
 		qp->mfc_cq_data2_RW = spuqp->mfc_cq_data2_RW;
 		qp->mfc_cq_data3_RW = spuqp->mfc_cq_data3_RW;
 	}
+}
+
+static ssize_t __spufs_dma_info_read(struct spu_context *ctx,
+			char __user *buf, size_t len, loff_t *pos)
+{
+	struct spu_dma_info info;
+
+	spufs_get_dma_info(ctx, &info);
 
 	return simple_read_from_buffer(buf, len, pos, &info,
 				sizeof info);
@@ -2124,6 +2150,7 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf,
 			      size_t len, loff_t *pos)
 {
 	struct spu_context *ctx = file->private_data;
+	struct spu_dma_info info;
 	int ret;
 
 	if (!access_ok(VERIFY_WRITE, buf, len))
@@ -2133,11 +2160,12 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 	spin_lock(&ctx->csa.register_lock);
-	ret = __spufs_dma_info_read(ctx, buf, len, pos);
+	spufs_get_dma_info(ctx, &info);
 	spin_unlock(&ctx->csa.register_lock);
 	spu_release_saved(ctx);
 
-	return ret;
+	return simple_read_from_buffer(buf, len, pos, &info,
+				sizeof(info));
 }
 
 static const struct file_operations spufs_dma_info_fops = {
@@ -2146,13 +2174,31 @@ static const struct file_operations spufs_dma_info_fops = {
 	.llseek = no_llseek,
 };
 
+static void spufs_get_proxydma_info(struct spu_context *ctx,
+		struct spu_proxydma_info *info)
+{
+	int i;
+
+	info->proxydma_info_type = ctx->csa.prob.dma_querytype_RW;
+	info->proxydma_info_mask = ctx->csa.prob.dma_querymask_RW;
+	info->proxydma_info_status = ctx->csa.prob.dma_tagstatus_R;
+
+	for (i = 0; i < 8; i++) {
+		struct mfc_cq_sr *qp = &info->proxydma_info_command_data[i];
+		struct mfc_cq_sr *puqp = &ctx->csa.priv2.puq[i];
+
+		qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW;
+		qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW;
+		qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW;
+		qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW;
+	}
+}
+
 static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx,
 			char __user *buf, size_t len, loff_t *pos)
 {
 	struct spu_proxydma_info info;
-	struct mfc_cq_sr *qp, *puqp;
 	int ret = sizeof info;
-	int i;
 
 	if (len < ret)
 		return -EINVAL;
@@ -2160,18 +2206,7 @@ static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx,
 	if (!access_ok(VERIFY_WRITE, buf, len))
 		return -EFAULT;
 
-	info.proxydma_info_type = ctx->csa.prob.dma_querytype_RW;
-	info.proxydma_info_mask = ctx->csa.prob.dma_querymask_RW;
-	info.proxydma_info_status = ctx->csa.prob.dma_tagstatus_R;
-	for (i = 0; i < 8; i++) {
-		qp = &info.proxydma_info_command_data[i];
-		puqp = &ctx->csa.priv2.puq[i];
-
-		qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW;
-		qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW;
-		qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW;
-		qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW;
-	}
+	spufs_get_proxydma_info(ctx, &info);
 
 	return simple_read_from_buffer(buf, len, pos, &info,
 				sizeof info);
@@ -2181,17 +2216,19 @@ static ssize_t spufs_proxydma_info_read(struct file *file, char __user *buf,
 				   size_t len, loff_t *pos)
 {
 	struct spu_context *ctx = file->private_data;
+	struct spu_proxydma_info info;
 	int ret;
 
 	ret = spu_acquire_saved(ctx);
 	if (ret)
 		return ret;
 	spin_lock(&ctx->csa.register_lock);
-	ret = __spufs_proxydma_info_read(ctx, buf, len, pos);
+	spufs_get_proxydma_info(ctx, &info);
 	spin_unlock(&ctx->csa.register_lock);
 	spu_release_saved(ctx);
 
-	return ret;
+	return simple_read_from_buffer(buf, len, pos, &info,
+				sizeof(info));
 }
 
 static const struct file_operations spufs_proxydma_info_fops = {
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index b0f34663b1ae..19bae78b1f25 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -212,13 +212,14 @@ void ps3_mm_vas_destroy(void)
 {
 	int result;
 
-	DBG("%s:%d: map.vas_id    = %llu\n", __func__, __LINE__, map.vas_id);
-
 	if (map.vas_id) {
 		result = lv1_select_virtual_address_space(0);
-		BUG_ON(result);
-		result = lv1_destruct_virtual_address_space(map.vas_id);
-		BUG_ON(result);
+		result += lv1_destruct_virtual_address_space(map.vas_id);
+
+		if (result) {
+			lv1_panic(0);
+		}
+
 		map.vas_id = 0;
 	}
 }
@@ -316,19 +317,20 @@ static void ps3_mm_region_destroy(struct mem_region *r)
 	int result;
 
 	if (!r->destroy) {
-		pr_info("%s:%d: Not destroying high region: %llxh %llxh\n",
-			__func__, __LINE__, r->base, r->size);
 		return;
 	}
 
-	DBG("%s:%d: r->base = %llxh\n", __func__, __LINE__, r->base);
-
 	if (r->base) {
 		result = lv1_release_memory(r->base);
-		BUG_ON(result);
+
+		if (result) {
+			lv1_panic(0);
+		}
+
 		r->size = r->base = r->offset = 0;
 		map.total = map.rm.size;
 	}
+
 	ps3_mm_set_repository_highmem(NULL);
 }
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index a0847be0b035..1a3cffdaa1e8 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -30,7 +30,7 @@ static bool rtas_hp_event;
 unsigned long pseries_memory_block_size(void)
 {
 	struct device_node *np;
-	unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE;
+	u64 memblock_size = MIN_MEMORY_BLOCK_SIZE;
 	struct resource r;
 
 	np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 99d1152ae224..8d20d49b252a 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -115,7 +115,6 @@ static void handle_system_shutdown(char event_modifier)
 	case EPOW_SHUTDOWN_ON_UPS:
 		pr_emerg("Loss of system power detected. System is running on"
 			 " UPS/battery. Check RTAS error log for details\n");
-		orderly_poweroff(true);
 		break;
 
 	case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS:
@@ -325,10 +324,11 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
 /*
  * Some versions of FWNMI place the buffer inside the 4kB page starting at
  * 0x7000. Other versions place it inside the rtas buffer. We check both.
+ * Minimum size of the buffer is 16 bytes.
  */
 #define VALID_FWNMI_BUFFER(A) \
-	((((A) >= 0x7000) && ((A) < 0x7ff0)) || \
-	(((A) >= rtas.base) && ((A) < (rtas.base + rtas.size - 16))))
+	((((A) >= 0x7000) && ((A) <= 0x8000 - 16)) || \
+	(((A) >= rtas.base) && ((A) <= (rtas.base + rtas.size - 16))))
 
 /*
  * Get the error information for errors coming through the
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index b7ae5a027714..f8181c8af32d 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/msi.h>
+#include <linux/vmalloc.h>
 
 #include <asm/prom.h>
 #include <asm/io.h>
@@ -932,12 +933,16 @@ EXPORT_SYMBOL_GPL(is_xive_irq);
 void xive_cleanup_irq_data(struct xive_irq_data *xd)
 {
 	if (xd->eoi_mmio) {
+		unmap_kernel_range((unsigned long)xd->eoi_mmio,
+				   1u << xd->esb_shift);
 		iounmap(xd->eoi_mmio);
 		if (xd->eoi_mmio == xd->trig_mmio)
 			xd->trig_mmio = NULL;
 		xd->eoi_mmio = NULL;
 	}
 	if (xd->trig_mmio) {
+		unmap_kernel_range((unsigned long)xd->trig_mmio,
+				   1u << xd->esb_shift);
 		iounmap(xd->trig_mmio);
 		xd->trig_mmio = NULL;
 	}
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 30cdcbfa1c04..b0e96f4b728c 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -22,6 +22,7 @@
 #include <linux/delay.h>
 #include <linux/cpumask.h>
 #include <linux/mm.h>
+#include <linux/kmemleak.h>
 
 #include <asm/prom.h>
 #include <asm/io.h>
@@ -630,6 +631,7 @@ static bool xive_native_provision_pages(void)
 			pr_err("Failed to allocate provisioning page\n");
 			return false;
 		}
+		kmemleak_ignore(p);
 		opal_xive_donate_page(chip, __pa(p));
 	}
 	return true;
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 3fdc0bb974d9..82d76ac71d2e 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -33,12 +33,12 @@
 #define KVM_USER_MEM_SLOTS 32
 
 /*
- * These seem to be used for allocating ->chip in the routing table,
- * which we don't use. 4096 is an out-of-thin-air value. If we need
- * to look at ->chip later on, we'll need to revisit this.
+ * These seem to be used for allocating ->chip in the routing table, which we
+ * don't use. 1 is as small as we can get to reduce the needed memory. If we
+ * need to look at ->chip later on, we'll need to revisit this.
  */
 #define KVM_NR_IRQCHIPS 1
-#define KVM_IRQCHIP_NUM_PINS 4096
+#define KVM_IRQCHIP_NUM_PINS 1
 #define KVM_HALT_POLL_NS_DEFAULT 80000
 
 /* s390-specific vcpu->requests bit members */
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 0095ddb58ff6..50f6661ba566 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -29,7 +29,7 @@
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ old__, new__, prev__;				\
 	pcp_op_T__ *ptr__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	prev__ = *ptr__;						\
 	do {								\
@@ -37,7 +37,7 @@
 		new__ = old__ op (val);					\
 		prev__ = cmpxchg(ptr__, old__, new__);			\
 	} while (prev__ != old__);					\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	new__;								\
 })
 
@@ -68,7 +68,7 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp)); 				\
 	if (__builtin_constant_p(val__) &&				\
 	    ((szcast)val__ > -129) && ((szcast)val__ < 128)) {		\
@@ -84,7 +84,7 @@
 			: [val__] "d" (val__)				\
 			: "cc");					\
 	}								\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 }
 
 #define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int)
@@ -95,14 +95,14 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
 		: [val__] "d" (val__)					\
 		: "cc");						\
-	preempt_enable();						\
+	preempt_enable_notrace();						\
 	old__ + val__;							\
 })
 
@@ -114,14 +114,14 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
 		: [val__] "d" (val__)					\
 		: "cc");						\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 }
 
 #define this_cpu_and_4(pcp, val)	arch_this_cpu_to_op(pcp, val, "lan")
@@ -136,10 +136,10 @@
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ ret__;						\
 	pcp_op_T__ *ptr__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = cmpxchg(ptr__, oval, nval);				\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 
@@ -152,10 +152,10 @@
 ({									\
 	typeof(pcp) *ptr__;						\
 	typeof(pcp) ret__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = xchg(ptr__, nval);					\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 
@@ -171,11 +171,11 @@
 	typeof(pcp1) *p1__;						\
 	typeof(pcp2) *p2__;						\
 	int ret__;							\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	p1__ = raw_cpu_ptr(&(pcp1));					\
 	p2__ = raw_cpu_ptr(&(pcp2));					\
 	ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__);	\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 6bc941be6921..166fbd74e316 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -41,7 +41,17 @@ static inline void syscall_rollback(struct task_struct *task,
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
-	return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0;
+	unsigned long error = regs->gprs[2];
+#ifdef CONFIG_COMPAT
+	if (test_tsk_thread_flag(task, TIF_31BIT)) {
+		/*
+		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
+		 * and will match correctly in comparisons.
+		 */
+		error = (long)(int)error;
+	}
+#endif
+	return IS_ERR_VALUE(error) ? error : 0;
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 4ba5ad44a21a..73045142febf 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -317,6 +317,8 @@ static noinline __init void setup_lowcore_early(void)
 	psw_t psw;
 
 	psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA;
+	if (IS_ENABLED(CONFIG_KASAN))
+		psw.mask |= PSW_MASK_DAT;
 	psw.addr = (unsigned long) s390_base_ext_handler;
 	S390_lowcore.external_new_psw = psw;
 	psw.addr = (unsigned long) s390_base_pgm_handler;
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 0cfd5a83a1da..151f001a90ff 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -40,6 +40,7 @@ EXPORT_SYMBOL(_mcount)
 ENTRY(ftrace_caller)
 	.globl	ftrace_regs_caller
 	.set	ftrace_regs_caller,ftrace_caller
+	stg	%r14,(__SF_GPRS+8*8)(%r15)	# save traced function caller
 	lgr	%r1,%r15
 #ifndef CC_USING_HOTPATCH
 	aghi	%r0,MCOUNT_RETURN_FIXUP
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 56e0190d6e65..42e4cd20fbbe 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -322,6 +322,25 @@ static inline void __poke_user_per(struct task_struct *child,
 		child->thread.per_user.end = data;
 }
 
+static void fixup_int_code(struct task_struct *child, addr_t data)
+{
+	struct pt_regs *regs = task_pt_regs(child);
+	int ilc = regs->int_code >> 16;
+	u16 insn;
+
+	if (ilc > 6)
+		return;
+
+	if (ptrace_access_vm(child, regs->psw.addr - (regs->int_code >> 16),
+			&insn, sizeof(insn), FOLL_FORCE) != sizeof(insn))
+		return;
+
+	/* double check that tracee stopped on svc instruction */
+	if ((insn >> 8) != 0xa)
+		return;
+
+	regs->int_code = 0x20000 | (data & 0xffff);
+}
 /*
  * Write a word to the user area of a process at location addr. This
  * operation does have an additional problem compared to peek_user.
@@ -333,7 +352,9 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 	struct user *dummy = NULL;
 	addr_t offset;
 
+
 	if (addr < (addr_t) &dummy->regs.acrs) {
+		struct pt_regs *regs = task_pt_regs(child);
 		/*
 		 * psw and gprs are stored on the stack
 		 */
@@ -351,7 +372,11 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 				/* Invalid addressing mode bits */
 				return -EINVAL;
 		}
-		*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
+
+		if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
+			addr == offsetof(struct user, regs.gprs[2]))
+			fixup_int_code(child, data);
+		*(addr_t *)((addr_t) &regs->psw + addr) = data;
 
 	} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
 		/*
@@ -717,6 +742,10 @@ static int __poke_user_compat(struct task_struct *child,
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) |
 				(__u64)(tmp & PSW32_ADDR_AMODE);
 		} else {
+
+			if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
+				addr == offsetof(struct compat_user, regs.gprs[2]))
+				fixup_int_code(child, data);
 			/* gpr 0-15 */
 			*(__u32*)((addr_t) &regs->psw + addr*2 + 4) = tmp;
 		}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 5c2558cc6977..42025e33a4e0 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -540,7 +540,7 @@ static struct notifier_block kdump_mem_nb = {
 /*
  * Make sure that the area behind memory_end is protected
  */
-static void reserve_memory_end(void)
+static void __init reserve_memory_end(void)
 {
 #ifdef CONFIG_CRASH_DUMP
 	if (ipl_info.type == IPL_TYPE_FCP_DUMP &&
@@ -558,7 +558,7 @@ static void reserve_memory_end(void)
 /*
  * Make sure that oldmem, where the dump is stored, is protected
  */
-static void reserve_oldmem(void)
+static void __init reserve_oldmem(void)
 {
 #ifdef CONFIG_CRASH_DUMP
 	if (OLDMEM_BASE)
@@ -570,7 +570,7 @@ static void reserve_oldmem(void)
 /*
  * Make sure that oldmem, where the dump is stored, is protected
  */
-static void remove_oldmem(void)
+static void __init remove_oldmem(void)
 {
 #ifdef CONFIG_CRASH_DUMP
 	if (OLDMEM_BASE)
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index e19ea9ebe960..777a4418693f 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -117,7 +117,7 @@ static inline pte_t __rste_to_pte(unsigned long rste)
 					     _PAGE_YOUNG);
 #ifdef CONFIG_MEM_SOFT_DIRTY
 		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY,
-					     _PAGE_DIRTY);
+					     _PAGE_SOFT_DIRTY);
 #endif
 		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_NOEXEC,
 					     _PAGE_NOEXEC);
diff --git a/arch/sh/boards/mach-landisk/setup.c b/arch/sh/boards/mach-landisk/setup.c
index f1147caebacf..af69fb7fef7c 100644
--- a/arch/sh/boards/mach-landisk/setup.c
+++ b/arch/sh/boards/mach-landisk/setup.c
@@ -85,6 +85,9 @@ device_initcall(landisk_devices_setup);
 
 static void __init landisk_setup(char **cmdline_p)
 {
+	/* I/O port identity mapping */
+	__set_io_port_base(0);
+
 	/* LED ON */
 	__raw_writeb(__raw_readb(PA_LED) | 0x03, PA_LED);
 
diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h
index 32eb56e00c11..6e7816360a75 100644
--- a/arch/sh/include/asm/uaccess.h
+++ b/arch/sh/include/asm/uaccess.h
@@ -16,8 +16,11 @@
  * sum := addr + size;  carry? --> flag = true;
  * if (sum >= addr_limit) flag = true;
  */
-#define __access_ok(addr, size)		\
-	(__addr_ok((addr) + (size)))
+#define __access_ok(addr, size)	({				\
+	unsigned long __ao_a = (addr), __ao_b = (size);		\
+	unsigned long __ao_end = __ao_a + __ao_b - !!__ao_b;	\
+	__ao_end >= __ao_a && __addr_ok(__ao_end); })
+
 #define access_ok(type, addr, size)	\
 	(__chk_user_ptr(addr),		\
 	 __access_ok((unsigned long __force)(addr), (size)))
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index 28cc61216b64..ed5b758c650d 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -203,7 +203,7 @@ syscall_trace_entry:
 	mov.l	@(OFF_R7,r15), r7   ! arg3
 	mov.l	@(OFF_R3,r15), r3   ! syscall_nr
 	!
-	mov.l	2f, r10			! Number of syscalls
+	mov.l	6f, r10			! Number of syscalls
 	cmp/hs	r10, r3
 	bf	syscall_call
 	mov	#-ENOSYS, r0
@@ -357,7 +357,7 @@ ENTRY(system_call)
 	tst	r9, r8
 	bf	syscall_trace_entry
 	!
-	mov.l	2f, r8			! Number of syscalls
+	mov.l	6f, r8			! Number of syscalls
 	cmp/hs	r8, r3
 	bt	syscall_badsys
 	!
@@ -396,7 +396,7 @@ syscall_exit:
 #if !defined(CONFIG_CPU_SH2)
 1:	.long	TRA
 #endif
-2:	.long	NR_syscalls
+6:	.long	NR_syscalls
 3:	.long	sys_call_table
 7:	.long	do_syscall_trace_enter
 8:	.long	do_syscall_trace_leave
diff --git a/arch/sh/tools/gen-mach-types b/arch/sh/tools/gen-mach-types
index 6d7c2d8eaf55..2a4a42a6d70c 100644
--- a/arch/sh/tools/gen-mach-types
+++ b/arch/sh/tools/gen-mach-types
@@ -1,4 +1,4 @@
-#!/bin/awk
+#!/usr/bin/awk
 # SPDX-License-Identifier: GPL-2.0
 #
 # Awk script to generate include/generated/machtypes.h
diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c
index 16b50afe7b52..646dd58169ec 100644
--- a/arch/sparc/kernel/ptrace_32.c
+++ b/arch/sparc/kernel/ptrace_32.c
@@ -46,82 +46,79 @@ enum sparc_regset {
 	REGSET_FP,
 };
 
+static int regwindow32_get(struct task_struct *target,
+			   const struct pt_regs *regs,
+			   u32 *uregs)
+{
+	unsigned long reg_window = regs->u_regs[UREG_I6];
+	int size = 16 * sizeof(u32);
+
+	if (target == current) {
+		if (copy_from_user(uregs, (void __user *)reg_window, size))
+			return -EFAULT;
+	} else {
+		if (access_process_vm(target, reg_window, uregs, size,
+				      FOLL_FORCE) != size)
+			return -EFAULT;
+	}
+	return 0;
+}
+
+static int regwindow32_set(struct task_struct *target,
+			   const struct pt_regs *regs,
+			   u32 *uregs)
+{
+	unsigned long reg_window = regs->u_regs[UREG_I6];
+	int size = 16 * sizeof(u32);
+
+	if (target == current) {
+		if (copy_to_user((void __user *)reg_window, uregs, size))
+			return -EFAULT;
+	} else {
+		if (access_process_vm(target, reg_window, uregs, size,
+				      FOLL_FORCE | FOLL_WRITE) != size)
+			return -EFAULT;
+	}
+	return 0;
+}
+
 static int genregs32_get(struct task_struct *target,
 			 const struct user_regset *regset,
 			 unsigned int pos, unsigned int count,
 			 void *kbuf, void __user *ubuf)
 {
 	const struct pt_regs *regs = target->thread.kregs;
-	unsigned long __user *reg_window;
-	unsigned long *k = kbuf;
-	unsigned long __user *u = ubuf;
-	unsigned long reg;
+	u32 uregs[16];
+	int ret;
 
 	if (target == current)
 		flush_user_windows();
 
-	pos /= sizeof(reg);
-	count /= sizeof(reg);
-
-	if (kbuf) {
-		for (; count > 0 && pos < 16; count--)
-			*k++ = regs->u_regs[pos++];
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (get_user(*k++, &reg_window[pos++]))
-				return -EFAULT;
-		}
-	} else {
-		for (; count > 0 && pos < 16; count--) {
-			if (put_user(regs->u_regs[pos++], u++))
-				return -EFAULT;
-		}
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (get_user(reg, &reg_window[pos++]) ||
-			    put_user(reg, u++))
-				return -EFAULT;
-		}
-	}
-	while (count > 0) {
-		switch (pos) {
-		case 32: /* PSR */
-			reg = regs->psr;
-			break;
-		case 33: /* PC */
-			reg = regs->pc;
-			break;
-		case 34: /* NPC */
-			reg = regs->npc;
-			break;
-		case 35: /* Y */
-			reg = regs->y;
-			break;
-		case 36: /* WIM */
-		case 37: /* TBR */
-			reg = 0;
-			break;
-		default:
-			goto finish;
-		}
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  regs->u_regs,
+				  0, 16 * sizeof(u32));
+	if (ret || !count)
+		return ret;
 
-		if (kbuf)
-			*k++ = reg;
-		else if (put_user(reg, u++))
+	if (pos < 32 * sizeof(u32)) {
+		if (regwindow32_get(target, regs, uregs))
 			return -EFAULT;
-		pos++;
-		count--;
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+					  uregs,
+					  16 * sizeof(u32), 32 * sizeof(u32));
+		if (ret || !count)
+			return ret;
 	}
-finish:
-	pos *= sizeof(reg);
-	count *= sizeof(reg);
 
-	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
-					38 * sizeof(reg), -1);
+	uregs[0] = regs->psr;
+	uregs[1] = regs->pc;
+	uregs[2] = regs->npc;
+	uregs[3] = regs->y;
+	uregs[4] = 0;	/* WIM */
+	uregs[5] = 0;	/* TBR */
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  uregs,
+				  32 * sizeof(u32), 38 * sizeof(u32));
 }
 
 static int genregs32_set(struct task_struct *target,
@@ -130,82 +127,58 @@ static int genregs32_set(struct task_struct *target,
 			 const void *kbuf, const void __user *ubuf)
 {
 	struct pt_regs *regs = target->thread.kregs;
-	unsigned long __user *reg_window;
-	const unsigned long *k = kbuf;
-	const unsigned long __user *u = ubuf;
-	unsigned long reg;
+	u32 uregs[16];
+	u32 psr;
+	int ret;
 
 	if (target == current)
 		flush_user_windows();
 
-	pos /= sizeof(reg);
-	count /= sizeof(reg);
-
-	if (kbuf) {
-		for (; count > 0 && pos < 16; count--)
-			regs->u_regs[pos++] = *k++;
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (put_user(*k++, &reg_window[pos++]))
-				return -EFAULT;
-		}
-	} else {
-		for (; count > 0 && pos < 16; count--) {
-			if (get_user(reg, u++))
-				return -EFAULT;
-			regs->u_regs[pos++] = reg;
-		}
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (get_user(reg, u++) ||
-			    put_user(reg, &reg_window[pos++]))
-				return -EFAULT;
-		}
-	}
-	while (count > 0) {
-		unsigned long psr;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 regs->u_regs,
+				 0, 16 * sizeof(u32));
+	if (ret || !count)
+		return ret;
 
-		if (kbuf)
-			reg = *k++;
-		else if (get_user(reg, u++))
+	if (pos < 32 * sizeof(u32)) {
+		if (regwindow32_get(target, regs, uregs))
 			return -EFAULT;
-
-		switch (pos) {
-		case 32: /* PSR */
-			psr = regs->psr;
-			psr &= ~(PSR_ICC | PSR_SYSCALL);
-			psr |= (reg & (PSR_ICC | PSR_SYSCALL));
-			regs->psr = psr;
-			break;
-		case 33: /* PC */
-			regs->pc = reg;
-			break;
-		case 34: /* NPC */
-			regs->npc = reg;
-			break;
-		case 35: /* Y */
-			regs->y = reg;
-			break;
-		case 36: /* WIM */
-		case 37: /* TBR */
-			break;
-		default:
-			goto finish;
-		}
-
-		pos++;
-		count--;
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 uregs,
+					 16 * sizeof(u32), 32 * sizeof(u32));
+		if (ret)
+			return ret;
+		if (regwindow32_set(target, regs, uregs))
+			return -EFAULT;
+		if (!count)
+			return 0;
 	}
-finish:
-	pos *= sizeof(reg);
-	count *= sizeof(reg);
-
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &psr,
+				 32 * sizeof(u32), 33 * sizeof(u32));
+	if (ret)
+		return ret;
+	regs->psr = (regs->psr & ~(PSR_ICC | PSR_SYSCALL)) |
+		    (psr & (PSR_ICC | PSR_SYSCALL));
+	if (!count)
+		return 0;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->pc,
+				 33 * sizeof(u32), 34 * sizeof(u32));
+	if (ret || !count)
+		return ret;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->npc,
+				 34 * sizeof(u32), 35 * sizeof(u32));
+	if (ret || !count)
+		return ret;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->y,
+				 35 * sizeof(u32), 36 * sizeof(u32));
+	if (ret || !count)
+		return ret;
 	return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
-					 38 * sizeof(reg), -1);
+					 36 * sizeof(u32), 38 * sizeof(u32));
 }
 
 static int fpregs32_get(struct task_struct *target,
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index e1d965e90e16..0c478c85e380 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -571,19 +571,13 @@ static int genregs32_get(struct task_struct *target,
 			for (; count > 0 && pos < 32; count--) {
 				if (access_process_vm(target,
 						      (unsigned long)
-						      &reg_window[pos],
+						      &reg_window[pos++],
 						      &reg, sizeof(reg),
 						      FOLL_FORCE)
 				    != sizeof(reg))
 					return -EFAULT;
-				if (access_process_vm(target,
-						      (unsigned long) u,
-						      &reg, sizeof(reg),
-						      FOLL_FORCE | FOLL_WRITE)
-				    != sizeof(reg))
+				if (put_user(reg, u++))
 					return -EFAULT;
-				pos++;
-				u++;
 			}
 		}
 	}
@@ -683,12 +677,7 @@ static int genregs32_set(struct task_struct *target,
 			}
 		} else {
 			for (; count > 0 && pos < 32; count--) {
-				if (access_process_vm(target,
-						      (unsigned long)
-						      u,
-						      &reg, sizeof(reg),
-						      FOLL_FORCE)
-				    != sizeof(reg))
+				if (get_user(reg, u++))
 					return -EFAULT;
 				if (access_process_vm(target,
 						      (unsigned long)
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 1c060748c813..f38ffcc610d2 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -87,7 +87,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
 
 SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
 
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 01d628ea3402..c6c4b877f3d2 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -49,16 +49,17 @@
  * Position Independent Executable (PIE) so that linker won't optimize
  * R_386_GOT32X relocation to its fixed symbol address.  Older
  * linkers generate R_386_32 relocations against locally defined symbols,
- * _bss, _ebss, _got and _egot, in PIE.  It isn't wrong, just less
+ * _bss, _ebss, _got, _egot and _end, in PIE.  It isn't wrong, just less
  * optimal than R_386_RELATIVE.  But the x86 kernel fails to properly handle
  * R_386_32 relocations when relocating the kernel.  To generate
- * R_386_RELATIVE relocations, we mark _bss, _ebss, _got and _egot as
+ * R_386_RELATIVE relocations, we mark _bss, _ebss, _got, _egot and _end as
  * hidden:
  */
 	.hidden _bss
 	.hidden _ebss
 	.hidden _got
 	.hidden _egot
+	.hidden _end
 
 	__HEAD
 ENTRY(startup_32)
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index a25127916e67..7ab1c6bcc66a 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -41,6 +41,7 @@
 	.hidden _ebss
 	.hidden _got
 	.hidden _egot
+	.hidden _end
 
 	__HEAD
 	.code32
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 0eb9f92f3717..136972a4c454 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -217,7 +217,6 @@ CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_EFI=y
 # CONFIG_LCD_CLASS_DEVICE is not set
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
@@ -247,6 +246,7 @@ CONFIG_USB_HIDDEV=y
 CONFIG_USB=y
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 CONFIG_USB_MON=y
+CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_TT_NEWSCHED=y
 CONFIG_USB_OHCI_HCD=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index e32fc1f274d8..d387193ef7fc 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -213,7 +213,6 @@ CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_EFI=y
 # CONFIG_LCD_CLASS_DEVICE is not set
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
@@ -243,6 +242,7 @@ CONFIG_USB_HIDDEV=y
 CONFIG_USB=y
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 CONFIG_USB_MON=y
+CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_TT_NEWSCHED=y
 CONFIG_USB_OHCI_HCD=y
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index 5f6a5af9c489..77043a82da51 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -127,10 +127,6 @@ ddq_add_8:
 
 /* generate a unique variable for ddq_add_x */
 
-.macro setddq n
-	var_ddq_add = ddq_add_\n
-.endm
-
 /* generate a unique variable for xmm register */
 .macro setxdata n
 	var_xdata = %xmm\n
@@ -140,9 +136,7 @@ ddq_add_8:
 
 .macro club name, id
 .altmacro
-	.if \name == DDQ_DATA
-		setddq %\id
-	.elseif \name == XDATA
+	.if \name == XDATA
 		setxdata %\id
 	.endif
 .noaltmacro
@@ -165,9 +159,8 @@ ddq_add_8:
 
 	.set i, 1
 	.rept (by - 1)
-		club DDQ_DATA, i
 		club XDATA, i
-		vpaddq	var_ddq_add(%rip), xcounter, var_xdata
+		vpaddq	(ddq_add_1 + 16 * (i - 1))(%rip), xcounter, var_xdata
 		vptest	ddq_low_msk(%rip), var_xdata
 		jnz 1f
 		vpaddq	ddq_high_add_1(%rip), var_xdata, var_xdata
@@ -180,8 +173,7 @@ ddq_add_8:
 	vmovdqa	1*16(p_keys), xkeyA
 
 	vpxor	xkey0, xdata0, xdata0
-	club DDQ_DATA, by
-	vpaddq	var_ddq_add(%rip), xcounter, xcounter
+	vpaddq	(ddq_add_1 + 16 * (by - 1))(%rip), xcounter, xcounter
 	vptest	ddq_low_msk(%rip), xcounter
 	jnz	1f
 	vpaddq	ddq_high_add_1(%rip), xcounter, xcounter
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index baeba0567126..884466592943 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -9,6 +9,33 @@
 
 #include <linux/mod_devicetable.h>
 
+#define X86_STEPPINGS(mins, maxs)    GENMASK(maxs, mins)
+
+/**
+ * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
+ * @_vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
+ *		The name is expanded to X86_VENDOR_@_vendor
+ * @_family:	The family number or X86_FAMILY_ANY
+ * @_model:	The model number, model constant or X86_MODEL_ANY
+ * @_steppings:	Bitmask for steppings, stepping constant or X86_STEPPING_ANY
+ * @_feature:	A X86_FEATURE bit or X86_FEATURE_ANY
+ * @_data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is casted to unsigned long internally.
+ *
+ * Backport version to keep the SRBDS pile consistant. No shorter variants
+ * required for this.
+ */
+#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
+						    _steppings, _feature, _data) { \
+	.vendor		= X86_VENDOR_##_vendor,				\
+	.family		= _family,					\
+	.model		= _model,					\
+	.steppings	= _steppings,					\
+	.feature	= _feature,					\
+	.driver_data	= (unsigned long) _data				\
+}
+
 extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
 
 #endif
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 157cfaf1064c..e08866cd2287 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -291,6 +291,7 @@
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_STIBP_ALWAYS_ON	(13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
@@ -346,6 +347,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_SRBDS_CTRL		(18*32+ 9) /* "" SRBDS mitigation MSR available */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
@@ -390,5 +392,6 @@
 #define X86_BUG_SWAPGS			X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
 #define X86_BUG_TAA			X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
+#define X86_BUG_SRBDS			X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index 00f7cf45e699..8e95aa4b0d17 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -74,7 +74,7 @@
 #define MAX_DMA_PFN   ((16UL * 1024 * 1024) >> PAGE_SHIFT)
 
 /* 4GB broken PCI/AGP hardware bus master zone */
-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
+#define MAX_DMA32_PFN (1UL << (32 - PAGE_SHIFT))
 
 #ifdef CONFIG_X86_32
 /* The maximum address that we can perform a DMA transfer to on this platform */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9529fe69e1d9..ecb6009a2c8a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1060,7 +1060,7 @@ struct kvm_x86_ops {
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
-	int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 5761a86b88e0..9dc445ac7f19 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -110,6 +110,10 @@
 #define TSX_CTRL_RTM_DISABLE		BIT(0)	/* Disable RTM feature */
 #define TSX_CTRL_CPUID_CLEAR		BIT(1)	/* Disable TSX enumeration */
 
+/* SRBDS support */
+#define MSR_IA32_MCU_OPT_CTRL		0x00000123
+#define RNGDS_MITG_DIS			BIT(0)
+
 #define MSR_IA32_SYSENTER_CS		0x00000174
 #define MSR_IA32_SYSENTER_ESP		0x00000175
 #define MSR_IA32_SYSENTER_EIP		0x00000176
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index b73a16a56e4f..270448b178a7 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -232,6 +232,7 @@ enum spectre_v2_mitigation {
 enum spectre_v2_user_mitigation {
 	SPECTRE_V2_USER_NONE,
 	SPECTRE_V2_USER_STRICT,
+	SPECTRE_V2_USER_STRICT_PREFERRED,
 	SPECTRE_V2_USER_PRCTL,
 	SPECTRE_V2_USER_SECCOMP,
 };
@@ -329,7 +330,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
  * combination with microcode which triggers a CPU buffer flush when the
  * instruction is executed.
  */
-static inline void mds_clear_cpu_buffers(void)
+static __always_inline void mds_clear_cpu_buffers(void)
 {
 	static const u16 ds = __KERNEL_DS;
 
@@ -350,7 +351,7 @@ static inline void mds_clear_cpu_buffers(void)
  *
  * Clear CPU buffers if the corresponding static key is enabled
  */
-static inline void mds_user_clear_cpu_buffers(void)
+static __always_inline void mds_user_clear_cpu_buffers(void)
 {
 	if (static_branch_likely(&mds_user_clear))
 		mds_clear_cpu_buffers();
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 98a337e3835d..2f7a4018b6e4 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -234,6 +234,7 @@ static inline int pmd_large(pmd_t pte)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */
 static inline int pmd_trans_huge(pmd_t pmd)
 {
 	return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index 851c04b7a092..1572a436bc08 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -4,6 +4,11 @@
 
 #define ARCH_DEFAULT_PKEY	0
 
+/*
+ * If more than 16 keys are ever supported, a thorough audit
+ * will be necessary to ensure that the types that store key
+ * numbers and masks have sufficient capacity.
+ */
 #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1)
 
 extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6a87eda9691e..56a89519dc14 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -344,7 +344,7 @@ struct x86_hw_tss {
 #define INVALID_IO_BITMAP_OFFSET	0x8000
 
 struct entry_stack {
-	unsigned long		words[64];
+	char	stack[PAGE_SIZE];
 };
 
 struct entry_stack_page {
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 971830341061..82b0ff6cac97 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -711,7 +711,17 @@ extern struct movsl_mask {
  * checking before using them, but you have to surround them with the
  * user_access_begin/end() pair.
  */
-#define user_access_begin()	__uaccess_begin()
+static __must_check inline bool user_access_begin(int type,
+						  const void __user *ptr,
+						  size_t len)
+{
+	if (unlikely(!access_ok(type, ptr, len)))
+		return 0;
+	__uaccess_begin_nospec();
+	return 1;
+}
+
+#define user_access_begin(a, b, c)	user_access_begin(a, b, c)
 #define user_access_end()	__uaccess_end()
 
 #define unsafe_put_user(x, ptr, err_label)					\
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 48ab5fdd1044..ee33f0951322 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1915,7 +1915,7 @@ void __init init_apic_mappings(void)
 	unsigned int new_apicid;
 
 	if (apic_validate_deadline_timer())
-		pr_debug("TSC deadline timer available\n");
+		pr_info("TSC deadline timer available\n");
 
 	if (x2apic_mode) {
 		boot_cpu_physical_apicid = read_apic_id();
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 2271adbc3c42..be226cdd08d3 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2160,6 +2160,7 @@ static inline void __init check_timer(void)
 	legacy_pic->init(0);
 	legacy_pic->make_irq(0);
 	apic_write(APIC_LVT0, APIC_DM_EXTINT);
+	legacy_pic->unmask(0);
 
 	unlock_ExtINT_logic();
 
@@ -2233,12 +2234,12 @@ static int mp_irqdomain_create(int ioapic)
 	ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops,
 						 (void *)(long)ioapic);
 
-	/* Release fw handle if it was allocated above */
-	if (!cfg->dev)
-		irq_domain_free_fwnode(fn);
-
-	if (!ip->irqdomain)
+	if (!ip->irqdomain) {
+		/* Release fw handle if it was allocated above */
+		if (!cfg->dev)
+			irq_domain_free_fwnode(fn);
 		return -ENOMEM;
+	}
 
 	ip->irqdomain->parent = parent;
 
@@ -2252,8 +2253,13 @@ static int mp_irqdomain_create(int ioapic)
 
 static void ioapic_destroy_irqdomain(int idx)
 {
+	struct ioapic_domain_cfg *cfg = &ioapics[idx].irqdomain_cfg;
+	struct fwnode_handle *fn = ioapics[idx].irqdomain->fwnode;
+
 	if (ioapics[idx].irqdomain) {
 		irq_domain_remove(ioapics[idx].irqdomain);
+		if (!cfg->dev)
+			irq_domain_free_fwnode(fn);
 		ioapics[idx].irqdomain = NULL;
 	}
 }
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index f10e7f93b0e2..8c102d62b859 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -149,10 +149,11 @@ void __init arch_init_msi_domain(struct irq_domain *parent)
 		msi_default_domain =
 			pci_msi_create_irq_domain(fn, &pci_msi_domain_info,
 						  parent);
-		irq_domain_free_fwnode(fn);
 	}
-	if (!msi_default_domain)
+	if (!msi_default_domain) {
+		irq_domain_free_fwnode(fn);
 		pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
+	}
 }
 
 #ifdef CONFIG_IRQ_REMAP
@@ -185,7 +186,8 @@ struct irq_domain *arch_create_remap_msi_irq_domain(struct irq_domain *parent,
 	if (!fn)
 		return NULL;
 	d = pci_msi_create_irq_domain(fn, &pci_msi_ir_domain_info, parent);
-	irq_domain_free_fwnode(fn);
+	if (!d)
+		irq_domain_free_fwnode(fn);
 	return d;
 }
 #endif
@@ -248,7 +250,8 @@ static struct irq_domain *dmar_get_irq_domain(void)
 	if (fn) {
 		dmar_domain = msi_create_irq_domain(fn, &dmar_msi_domain_info,
 						    x86_vector_domain);
-		irq_domain_free_fwnode(fn);
+		if (!dmar_domain)
+			irq_domain_free_fwnode(fn);
 	}
 out:
 	mutex_unlock(&dmar_lock);
@@ -373,7 +376,10 @@ struct irq_domain *hpet_create_irq_domain(int hpet_id)
 	}
 
 	d = msi_create_irq_domain(fn, domain_info, parent);
-	irq_domain_free_fwnode(fn);
+	if (!d) {
+		irq_domain_free_fwnode(fn);
+		kfree(domain_info);
+	}
 	return d;
 }
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index b958082c74a7..637cf4dfccc9 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -368,6 +368,10 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		irq_data->chip = &lapic_controller;
 		irq_data->chip_data = data;
 		irq_data->hwirq = virq + i;
+
+		/* Don't invoke affinity setter on deactivated interrupts */
+		irqd_set_affinity_on_activate(irq_data);
+
 		err = assign_irq_vector_policy(virq + i, node, data, info,
 					       irq_data);
 		if (err) {
@@ -457,7 +461,6 @@ int __init arch_early_irq_init(void)
 	x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops,
 						   NULL);
 	BUG_ON(x86_vector_domain == NULL);
-	irq_domain_free_fwnode(fn);
 	irq_set_default_host(x86_vector_domain);
 
 	arch_init_msi_domain(x86_vector_domain);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 7896a34f53b5..245184152892 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -41,6 +41,7 @@ static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
 static void __init mds_print_mitigation(void);
 static void __init taa_select_mitigation(void);
+static void __init srbds_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
 u64 x86_spec_ctrl_base;
@@ -60,7 +61,7 @@ static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS;
 u64 __ro_after_init x86_amd_ls_cfg_base;
 u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask;
 
-/* Control conditional STIPB in switch_to() */
+/* Control conditional STIBP in switch_to() */
 DEFINE_STATIC_KEY_FALSE(switch_to_cond_stibp);
 /* Control conditional IBPB in switch_mm() */
 DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
@@ -108,6 +109,7 @@ void __init check_bugs(void)
 	l1tf_select_mitigation();
 	mds_select_mitigation();
 	taa_select_mitigation();
+	srbds_select_mitigation();
 
 	/*
 	 * As MDS and TAA mitigations are inter-related, print MDS
@@ -391,6 +393,97 @@ static int __init tsx_async_abort_parse_cmdline(char *str)
 early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"SRBDS: " fmt
+
+enum srbds_mitigations {
+	SRBDS_MITIGATION_OFF,
+	SRBDS_MITIGATION_UCODE_NEEDED,
+	SRBDS_MITIGATION_FULL,
+	SRBDS_MITIGATION_TSX_OFF,
+	SRBDS_MITIGATION_HYPERVISOR,
+};
+
+static enum srbds_mitigations srbds_mitigation __ro_after_init = SRBDS_MITIGATION_FULL;
+
+static const char * const srbds_strings[] = {
+	[SRBDS_MITIGATION_OFF]		= "Vulnerable",
+	[SRBDS_MITIGATION_UCODE_NEEDED]	= "Vulnerable: No microcode",
+	[SRBDS_MITIGATION_FULL]		= "Mitigation: Microcode",
+	[SRBDS_MITIGATION_TSX_OFF]	= "Mitigation: TSX disabled",
+	[SRBDS_MITIGATION_HYPERVISOR]	= "Unknown: Dependent on hypervisor status",
+};
+
+static bool srbds_off;
+
+void update_srbds_msr(void)
+{
+	u64 mcu_ctrl;
+
+	if (!boot_cpu_has_bug(X86_BUG_SRBDS))
+		return;
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return;
+
+	if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED)
+		return;
+
+	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+
+	switch (srbds_mitigation) {
+	case SRBDS_MITIGATION_OFF:
+	case SRBDS_MITIGATION_TSX_OFF:
+		mcu_ctrl |= RNGDS_MITG_DIS;
+		break;
+	case SRBDS_MITIGATION_FULL:
+		mcu_ctrl &= ~RNGDS_MITG_DIS;
+		break;
+	default:
+		break;
+	}
+
+	wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+}
+
+static void __init srbds_select_mitigation(void)
+{
+	u64 ia32_cap;
+
+	if (!boot_cpu_has_bug(X86_BUG_SRBDS))
+		return;
+
+	/*
+	 * Check to see if this is one of the MDS_NO systems supporting
+	 * TSX that are only exposed to SRBDS when TSX is enabled.
+	 */
+	ia32_cap = x86_read_arch_cap_msr();
+	if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM))
+		srbds_mitigation = SRBDS_MITIGATION_TSX_OFF;
+	else if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR;
+	else if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL))
+		srbds_mitigation = SRBDS_MITIGATION_UCODE_NEEDED;
+	else if (cpu_mitigations_off() || srbds_off)
+		srbds_mitigation = SRBDS_MITIGATION_OFF;
+
+	update_srbds_msr();
+	pr_info("%s\n", srbds_strings[srbds_mitigation]);
+}
+
+static int __init srbds_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!boot_cpu_has_bug(X86_BUG_SRBDS))
+		return 0;
+
+	srbds_off = !strcmp(str, "off");
+	return 0;
+}
+early_param("srbds", srbds_parse_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V1 : " fmt
 
 enum spectre_v1_mitigation {
@@ -488,7 +581,9 @@ early_param("nospectre_v1", nospectre_v1_cmdline);
 static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
 	SPECTRE_V2_NONE;
 
-static enum spectre_v2_user_mitigation spectre_v2_user __ro_after_init =
+static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init =
+	SPECTRE_V2_USER_NONE;
+static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init =
 	SPECTRE_V2_USER_NONE;
 
 #ifdef CONFIG_RETPOLINE
@@ -540,10 +635,11 @@ enum spectre_v2_user_cmd {
 };
 
 static const char * const spectre_v2_user_strings[] = {
-	[SPECTRE_V2_USER_NONE]		= "User space: Vulnerable",
-	[SPECTRE_V2_USER_STRICT]	= "User space: Mitigation: STIBP protection",
-	[SPECTRE_V2_USER_PRCTL]		= "User space: Mitigation: STIBP via prctl",
-	[SPECTRE_V2_USER_SECCOMP]	= "User space: Mitigation: STIBP via seccomp and prctl",
+	[SPECTRE_V2_USER_NONE]			= "User space: Vulnerable",
+	[SPECTRE_V2_USER_STRICT]		= "User space: Mitigation: STIBP protection",
+	[SPECTRE_V2_USER_STRICT_PREFERRED]	= "User space: Mitigation: STIBP always-on protection",
+	[SPECTRE_V2_USER_PRCTL]			= "User space: Mitigation: STIBP via prctl",
+	[SPECTRE_V2_USER_SECCOMP]		= "User space: Mitigation: STIBP via seccomp and prctl",
 };
 
 static const struct {
@@ -655,23 +751,36 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 		pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
 			static_key_enabled(&switch_mm_always_ibpb) ?
 			"always-on" : "conditional");
+
+		spectre_v2_user_ibpb = mode;
 	}
 
-	/* If enhanced IBRS is enabled no STIPB required */
-	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
+	/*
+	 * If enhanced IBRS is enabled or SMT impossible, STIBP is not
+	 * required.
+	 */
+	if (!smt_possible || spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
 		return;
 
 	/*
-	 * If SMT is not possible or STIBP is not available clear the STIPB
-	 * mode.
+	 * At this point, an STIBP mode other than "off" has been set.
+	 * If STIBP support is not being forced, check if STIBP always-on
+	 * is preferred.
 	 */
-	if (!smt_possible || !boot_cpu_has(X86_FEATURE_STIBP))
+	if (mode != SPECTRE_V2_USER_STRICT &&
+	    boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
+		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
+
+	/*
+	 * If STIBP is not available, clear the STIBP mode.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_STIBP))
 		mode = SPECTRE_V2_USER_NONE;
+
+	spectre_v2_user_stibp = mode;
+
 set_mode:
-	spectre_v2_user = mode;
-	/* Only print the STIBP mode when SMT possible */
-	if (smt_possible)
-		pr_info("%s\n", spectre_v2_user_strings[mode]);
+	pr_info("%s\n", spectre_v2_user_strings[mode]);
 }
 
 static const char * const spectre_v2_strings[] = {
@@ -902,10 +1011,11 @@ void arch_smt_update(void)
 {
 	mutex_lock(&spec_ctrl_mutex);
 
-	switch (spectre_v2_user) {
+	switch (spectre_v2_user_stibp) {
 	case SPECTRE_V2_USER_NONE:
 		break;
 	case SPECTRE_V2_USER_STRICT:
+	case SPECTRE_V2_USER_STRICT_PREFERRED:
 		update_stibp_strict();
 		break;
 	case SPECTRE_V2_USER_PRCTL:
@@ -1134,13 +1244,19 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 {
 	switch (ctrl) {
 	case PR_SPEC_ENABLE:
-		if (spectre_v2_user == SPECTRE_V2_USER_NONE)
+		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 			return 0;
 		/*
 		 * Indirect branch speculation is always disabled in strict
-		 * mode.
+		 * mode. It can neither be enabled if it was force-disabled
+		 * by a  previous prctl call.
+
 		 */
-		if (spectre_v2_user == SPECTRE_V2_USER_STRICT)
+		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ||
+		    task_spec_ib_force_disable(task))
 			return -EPERM;
 		task_clear_spec_ib_disable(task);
 		task_update_spec_tif(task);
@@ -1151,9 +1267,12 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		 * Indirect branch speculation is always allowed when
 		 * mitigation is force disabled.
 		 */
-		if (spectre_v2_user == SPECTRE_V2_USER_NONE)
+		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 			return -EPERM;
-		if (spectre_v2_user == SPECTRE_V2_USER_STRICT)
+		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
 			return 0;
 		task_set_spec_ib_disable(task);
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
@@ -1184,7 +1303,8 @@ void arch_seccomp_spec_mitigate(struct task_struct *task)
 {
 	if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP)
 		ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
-	if (spectre_v2_user == SPECTRE_V2_USER_SECCOMP)
+	if (spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP)
 		ib_prctl_set(task, PR_SPEC_FORCE_DISABLE);
 }
 #endif
@@ -1213,21 +1333,24 @@ static int ib_prctl_get(struct task_struct *task)
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return PR_SPEC_NOT_AFFECTED;
 
-	switch (spectre_v2_user) {
-	case SPECTRE_V2_USER_NONE:
+	if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 		return PR_SPEC_ENABLE;
-	case SPECTRE_V2_USER_PRCTL:
-	case SPECTRE_V2_USER_SECCOMP:
+	else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+		return PR_SPEC_DISABLE;
+	else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
+	    spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) {
 		if (task_spec_ib_force_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
 		if (task_spec_ib_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
 		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
-	case SPECTRE_V2_USER_STRICT:
-		return PR_SPEC_DISABLE;
-	default:
+	} else
 		return PR_SPEC_NOT_AFFECTED;
-	}
 }
 
 int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
@@ -1466,11 +1589,13 @@ static char *stibp_state(void)
 	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
 		return "";
 
-	switch (spectre_v2_user) {
+	switch (spectre_v2_user_stibp) {
 	case SPECTRE_V2_USER_NONE:
 		return ", STIBP: disabled";
 	case SPECTRE_V2_USER_STRICT:
 		return ", STIBP: forced";
+	case SPECTRE_V2_USER_STRICT_PREFERRED:
+		return ", STIBP: always-on";
 	case SPECTRE_V2_USER_PRCTL:
 	case SPECTRE_V2_USER_SECCOMP:
 		if (static_key_enabled(&switch_to_cond_stibp))
@@ -1491,6 +1616,11 @@ static char *ibpb_state(void)
 	return "";
 }
 
+static ssize_t srbds_show_state(char *buf)
+{
+	return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]);
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -1532,6 +1662,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_ITLB_MULTIHIT:
 		return itlb_multihit_show_state(buf);
 
+	case X86_BUG_SRBDS:
+		return srbds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -1578,4 +1711,9 @@ ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT);
 }
+
+ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7b4141889919..64066a2497e4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -854,6 +854,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
 		c->x86_phys_bits = 36;
 #endif
+	c->x86_cache_bits = c->x86_phys_bits;
 
 	if (c->extended_cpuid_level >= 0x8000000a)
 		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
@@ -894,7 +895,6 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 			}
 		}
 #endif
-	c->x86_cache_bits = c->x86_phys_bits;
 }
 
 #define NO_SPECULATION		BIT(0)
@@ -964,9 +964,30 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	{}
 };
 
-static bool __init cpu_matches(unsigned long which)
+#define VULNBL_INTEL_STEPPINGS(model, steppings, issues)		   \
+	X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6,		   \
+					    INTEL_FAM6_##model, steppings, \
+					    X86_FEATURE_ANY, issues)
+
+#define SRBDS		BIT(0)
+
+static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
+	VULNBL_INTEL_STEPPINGS(IVYBRIDGE,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(HASWELL_CORE,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(HASWELL_ULT,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(HASWELL_GT3E,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(BROADWELL_GT3E,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(BROADWELL_CORE,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_MOBILE,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_DESKTOP,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_MOBILE,	X86_STEPPINGS(0x0, 0xC),	SRBDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_DESKTOP,X86_STEPPINGS(0x0, 0xD),	SRBDS),
+	{}
+};
+
+static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long which)
 {
-	const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist);
+	const struct x86_cpu_id *m = x86_match_cpu(table);
 
 	return m && !!(m->driver_data & which);
 }
@@ -986,29 +1007,32 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	u64 ia32_cap = x86_read_arch_cap_msr();
 
 	/* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */
-	if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
+	if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) &&
+	    !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
 		setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT);
 
-	if (cpu_matches(NO_SPECULATION))
+	if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
 
-	if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
+	if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) &&
+	    !(ia32_cap & ARCH_CAP_SSB_NO) &&
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
 	if (ia32_cap & ARCH_CAP_IBRS_ALL)
 		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
 
-	if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) {
+	if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) &&
+	    !(ia32_cap & ARCH_CAP_MDS_NO)) {
 		setup_force_cpu_bug(X86_BUG_MDS);
-		if (cpu_matches(MSBDS_ONLY))
+		if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY))
 			setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
 	}
 
-	if (!cpu_matches(NO_SWAPGS))
+	if (!cpu_matches(cpu_vuln_whitelist, NO_SWAPGS))
 		setup_force_cpu_bug(X86_BUG_SWAPGS);
 
 	/*
@@ -1026,7 +1050,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	     (ia32_cap & ARCH_CAP_TSX_CTRL_MSR)))
 		setup_force_cpu_bug(X86_BUG_TAA);
 
-	if (cpu_matches(NO_MELTDOWN))
+	/*
+	 * SRBDS affects CPUs which support RDRAND or RDSEED and are listed
+	 * in the vulnerability blacklist.
+	 */
+	if ((cpu_has(c, X86_FEATURE_RDRAND) ||
+	     cpu_has(c, X86_FEATURE_RDSEED)) &&
+	    cpu_matches(cpu_vuln_blacklist, SRBDS))
+		    setup_force_cpu_bug(X86_BUG_SRBDS);
+
+	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
 	/* Rogue Data Cache Load? No! */
@@ -1035,7 +1068,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 
-	if (cpu_matches(NO_L1TF))
+	if (cpu_matches(cpu_vuln_whitelist, NO_L1TF))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_L1TF);
@@ -1451,6 +1484,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 	mtrr_ap_init();
 	validate_apic_and_package_id(c);
 	x86_spec_ctrl_setup_ap();
+	update_srbds_msr();
 }
 
 static __init int setup_noclflush(char *arg)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index db10a63687d3..432058e5e44b 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -69,6 +69,7 @@ extern int detect_ht_early(struct cpuinfo_x86 *c);
 unsigned int aperfmperf_get_khz(int cpu);
 
 extern void x86_spec_ctrl_setup_ap(void);
+extern void update_srbds_msr(void);
 
 extern u64 x86_read_arch_cap_msr(void);
 
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 3fed38812eea..751e59057466 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -34,13 +34,18 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 	const struct x86_cpu_id *m;
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	for (m = match; m->vendor | m->family | m->model | m->feature; m++) {
+	for (m = match;
+	     m->vendor | m->family | m->model | m->steppings | m->feature;
+	     m++) {
 		if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor)
 			continue;
 		if (m->family != X86_FAMILY_ANY && c->x86 != m->family)
 			continue;
 		if (m->model != X86_MODEL_ANY && c->x86_model != m->model)
 			continue;
+		if (m->steppings != X86_STEPPING_ANY &&
+		    !(BIT(c->x86_stepping) & m->steppings))
+			continue;
 		if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature))
 			continue;
 		return m;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index e57b59762f9f..94aa91b09c28 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -518,7 +518,7 @@ static void do_inject(void)
 	 */
 	if (inj_type == DFR_INT_INJ) {
 		i_mce.status |= MCI_STATUS_DEFERRED;
-		i_mce.status |= (i_mce.status & ~MCI_STATUS_UC);
+		i_mce.status &= ~MCI_STATUS_UC;
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index d805202c63cd..153407d8451f 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -21,6 +21,7 @@
  *
  */
 
+#include <linux/jiffies.h>
 #include <linux/dmi.h>
 #include <linux/init.h>
 #include <linux/export.h>
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 87a57b7642d3..601a5da1d196 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -907,8 +907,6 @@ const void *get_xsave_field_ptr(int xsave_state)
 
 #ifdef CONFIG_ARCH_HAS_PKEYS
 
-#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2)
-#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1)
 /*
  * This will go out and modify PKRU register to set the access
  * rights for @pkey to @init_val.
@@ -927,6 +925,13 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))
 		return -EINVAL;
 
+	/*
+	 * This code should only be called with valid 'pkey'
+	 * values originating from in-kernel users.  Complain
+	 * if a bad value is observed.
+	 */
+	WARN_ON_ONCE(pkey >= arch_max_pkey());
+
 	/* Set the bits we need in PKRU:  */
 	if (init_val & PKEY_DISABLE_ACCESS)
 		new_pkru_bits |= PKRU_AD_BIT;
@@ -964,18 +969,31 @@ static inline bool xfeatures_mxcsr_quirk(u64 xfeatures)
 	return true;
 }
 
-/*
- * This is similar to user_regset_copyout(), but will not add offset to
- * the source data pointer or increment pos, count, kbuf, and ubuf.
- */
-static inline void
-__copy_xstate_to_kernel(void *kbuf, const void *data,
-			unsigned int offset, unsigned int size, unsigned int size_total)
+static void fill_gap(unsigned to, void **kbuf, unsigned *pos, unsigned *count)
 {
-	if (offset < size_total) {
-		unsigned int copy = min(size, size_total - offset);
+	if (*pos < to) {
+		unsigned size = to - *pos;
+
+		if (size > *count)
+			size = *count;
+		memcpy(*kbuf, (void *)&init_fpstate.xsave + *pos, size);
+		*kbuf += size;
+		*pos += size;
+		*count -= size;
+	}
+}
 
-		memcpy(kbuf + offset, data, copy);
+static void copy_part(unsigned offset, unsigned size, void *from,
+			void **kbuf, unsigned *pos, unsigned *count)
+{
+	fill_gap(offset, kbuf, pos, count);
+	if (size > *count)
+		size = *count;
+	if (size) {
+		memcpy(*kbuf, from, size);
+		*kbuf += size;
+		*pos += size;
+		*count -= size;
 	}
 }
 
@@ -988,8 +1006,9 @@ __copy_xstate_to_kernel(void *kbuf, const void *data,
  */
 int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total)
 {
-	unsigned int offset, size;
 	struct xstate_header header;
+	const unsigned off_mxcsr = offsetof(struct fxregs_state, mxcsr);
+	unsigned count = size_total;
 	int i;
 
 	/*
@@ -1005,46 +1024,42 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
 	header.xfeatures = xsave->header.xfeatures;
 	header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
 
+	if (header.xfeatures & XFEATURE_MASK_FP)
+		copy_part(0, off_mxcsr,
+			  &xsave->i387, &kbuf, &offset_start, &count);
+	if (header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM))
+		copy_part(off_mxcsr, MXCSR_AND_FLAGS_SIZE,
+			  &xsave->i387.mxcsr, &kbuf, &offset_start, &count);
+	if (header.xfeatures & XFEATURE_MASK_FP)
+		copy_part(offsetof(struct fxregs_state, st_space), 128,
+			  &xsave->i387.st_space, &kbuf, &offset_start, &count);
+	if (header.xfeatures & XFEATURE_MASK_SSE)
+		copy_part(xstate_offsets[XFEATURE_SSE], 256,
+			  &xsave->i387.xmm_space, &kbuf, &offset_start, &count);
+	/*
+	 * Fill xsave->i387.sw_reserved value for ptrace frame:
+	 */
+	copy_part(offsetof(struct fxregs_state, sw_reserved), 48,
+		  xstate_fx_sw_bytes, &kbuf, &offset_start, &count);
 	/*
 	 * Copy xregs_state->header:
 	 */
-	offset = offsetof(struct xregs_state, header);
-	size = sizeof(header);
-
-	__copy_xstate_to_kernel(kbuf, &header, offset, size, size_total);
+	copy_part(offsetof(struct xregs_state, header), sizeof(header),
+		  &header, &kbuf, &offset_start, &count);
 
-	for (i = 0; i < XFEATURE_MAX; i++) {
+	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
 		/*
 		 * Copy only in-use xstates:
 		 */
 		if ((header.xfeatures >> i) & 1) {
 			void *src = __raw_xsave_addr(xsave, 1 << i);
 
-			offset = xstate_offsets[i];
-			size = xstate_sizes[i];
-
-			/* The next component has to fit fully into the output buffer: */
-			if (offset + size > size_total)
-				break;
-
-			__copy_xstate_to_kernel(kbuf, src, offset, size, size_total);
+			copy_part(xstate_offsets[i], xstate_sizes[i],
+				  src, &kbuf, &offset_start, &count);
 		}
 
 	}
-
-	if (xfeatures_mxcsr_quirk(header.xfeatures)) {
-		offset = offsetof(struct fxregs_state, mxcsr);
-		size = MXCSR_AND_FLAGS_SIZE;
-		__copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total);
-	}
-
-	/*
-	 * Fill xsave->i387.sw_reserved value for ptrace frame:
-	 */
-	offset = offsetof(struct fxregs_state, sw_reserved);
-	size = sizeof(xstate_fx_sw_bytes);
-
-	__copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total);
+	fill_gap(size_total, &kbuf, &offset_start, &count);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 02abc134367f..f7833ae4e3f1 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -206,7 +206,7 @@ spurious_8259A_irq:
 		 * lets ACK and report it. [once per IRQ]
 		 */
 		if (!(spurious_irq_mask & irqmask)) {
-			printk(KERN_DEBUG
+			printk_deferred(KERN_DEBUG
 			       "spurious 8259A interrupt: IRQ%d.\n", irq);
 			spurious_irq_mask |= irqmask;
 		}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 9d7bb8de2917..02665ffef050 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -744,16 +744,11 @@ asm(
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
-static struct kprobe kretprobe_kprobe = {
-	.addr = (void *)kretprobe_trampoline,
-};
-
 /*
  * Called from kretprobe_trampoline
  */
 __visible __used void *trampoline_handler(struct pt_regs *regs)
 {
-	struct kprobe_ctlblk *kcb;
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
 	struct hlist_node *tmp;
@@ -763,16 +758,12 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
 	void *frame_pointer;
 	bool skipped = false;
 
-	preempt_disable();
-
 	/*
 	 * Set a dummy kprobe for avoiding kretprobe recursion.
 	 * Since kretprobe never run in kprobe handler, kprobe must not
 	 * be running at this point.
 	 */
-	kcb = get_kprobe_ctlblk();
-	__this_cpu_write(current_kprobe, &kretprobe_kprobe);
-	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+	kprobe_busy_begin();
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
@@ -851,7 +842,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
 			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, &kretprobe_kprobe);
+			__this_cpu_write(current_kprobe, &kprobe_busy);
 		}
 
 		recycle_rp_inst(ri, &empty_rp);
@@ -867,8 +858,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_hash_unlock(current, &flags);
 
-	__this_cpu_write(current_kprobe, NULL);
-	preempt_enable();
+	kprobe_busy_end();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index d2ef967bfafb..a07b09f68e7e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -414,28 +414,20 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp,
 	u64 msr = x86_spec_ctrl_base;
 	bool updmsr = false;
 
-	/*
-	 * If TIF_SSBD is different, select the proper mitigation
-	 * method. Note that if SSBD mitigation is disabled or permanentely
-	 * enabled this branch can't be taken because nothing can set
-	 * TIF_SSBD.
-	 */
-	if (tif_diff & _TIF_SSBD) {
-		if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) {
+	/* Handle change of TIF_SSBD depending on the mitigation method. */
+	if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) {
+		if (tif_diff & _TIF_SSBD)
 			amd_set_ssb_virt_state(tifn);
-		} else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) {
+	} else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) {
+		if (tif_diff & _TIF_SSBD)
 			amd_set_core_ssb_state(tifn);
-		} else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
-			   static_cpu_has(X86_FEATURE_AMD_SSBD)) {
-			msr |= ssbd_tif_to_spec_ctrl(tifn);
-			updmsr  = true;
-		}
+	} else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+		   static_cpu_has(X86_FEATURE_AMD_SSBD)) {
+		updmsr |= !!(tif_diff & _TIF_SSBD);
+		msr |= ssbd_tif_to_spec_ctrl(tifn);
 	}
 
-	/*
-	 * Only evaluate TIF_SPEC_IB if conditional STIBP is enabled,
-	 * otherwise avoid the MSR write.
-	 */
+	/* Only evaluate TIF_SPEC_IB if conditional STIBP is enabled. */
 	if (IS_ENABLED(CONFIG_SMP) &&
 	    static_branch_unlikely(&switch_to_cond_stibp)) {
 		updmsr |= !!(tif_diff & _TIF_SPEC_IB);
diff --git a/arch/x86/kernel/process.h b/arch/x86/kernel/process.h
index 898e97cf6629..320ab978fb1f 100644
--- a/arch/x86/kernel/process.h
+++ b/arch/x86/kernel/process.h
@@ -19,7 +19,7 @@ static inline void switch_to_extra(struct task_struct *prev,
 	if (IS_ENABLED(CONFIG_SMP)) {
 		/*
 		 * Avoid __switch_to_xtra() invocation when conditional
-		 * STIPB is disabled and the only different bit is
+		 * STIBP is disabled and the only different bit is
 		 * TIF_SPEC_IB. For CONFIG_SMP=n TIF_SPEC_IB is not
 		 * in the TIF_WORK_CTXSW masks.
 		 */
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 734549492a18..dc4d27000aa3 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -374,7 +374,7 @@ static unsigned long task_seg_base(struct task_struct *task,
 		 */
 		mutex_lock(&task->mm->context.lock);
 		ldt = task->mm->context.ldt;
-		if (unlikely(idx >= ldt->nr_entries))
+		if (unlikely(!ldt || idx >= ldt->nr_entries))
 			base = 0;
 		else
 			base = get_desc_base(ldt->entries + idx);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index c663d5fcff2e..b7663a1f89ee 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -197,6 +197,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"),
 		},
 	},
+	{	/* Handle problems with rebooting on Apple MacBook6,1 */
+		.callback = set_pci_reboot,
+		.ident = "Apple MacBook6,1",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "MacBook6,1"),
+		},
+	},
 	{	/* Handle problems with rebooting on Apple MacBookPro5 */
 		.callback = set_pci_reboot,
 		.ident = "Apple MacBookPro5",
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index ab0176ae985b..12f90f17f4f6 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -24,10 +24,6 @@
 #include <asm/hpet.h>
 #include <asm/time.h>
 
-#ifdef CONFIG_X86_64
-__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES;
-#endif
-
 unsigned long profile_pc(struct pt_regs *regs)
 {
 	unsigned long pc = instruction_pointer(regs);
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index a9a55e76a43f..a5e2ce931f69 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -346,8 +346,11 @@ bool unwind_next_frame(struct unwind_state *state)
 	/*
 	 * Find the orc_entry associated with the text address.
 	 *
-	 * Decrement call return addresses by one so they work for sibling
-	 * calls and calls to noreturn functions.
+	 * For a call frame (as opposed to a signal frame), state->ip points to
+	 * the instruction after the call.  That instruction's stack layout
+	 * could be different from the call instruction's layout, for example
+	 * if the call was to a noreturn function.  So get the ORC data for the
+	 * call instruction itself.
 	 */
 	orc = orc_find(state->signal ? state->ip : state->ip - 1);
 	if (!orc || orc->sp_reg == ORC_REG_UNDEFINED)
@@ -550,6 +553,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		state->sp = task->thread.sp;
 		state->bp = READ_ONCE_NOCHECK(frame->bp);
 		state->ip = READ_ONCE_NOCHECK(frame->ret_addr);
+		state->signal = (void *)state->ip == ret_from_fork;
 	}
 
 	if (get_stack_info((unsigned long *)state->sp, state->task,
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 2384a2ae5ec3..d3dc8bc6b3ad 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -36,13 +36,13 @@ OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
 #ifdef CONFIG_X86_32
 OUTPUT_ARCH(i386)
 ENTRY(phys_startup_32)
-jiffies = jiffies_64;
 #else
 OUTPUT_ARCH(i386:x86-64)
 ENTRY(phys_startup_64)
-jiffies_64 = jiffies;
 #endif
 
+jiffies = jiffies_64;
+
 #if defined(CONFIG_X86_64)
 /*
  * On 64-bit, align RODATA to 2MB so we retain large page mappings for
@@ -352,7 +352,8 @@ SECTIONS
 	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
 		__bss_start = .;
 		*(.bss..page_aligned)
-		*(.bss)
+		. = ALIGN(PAGE_SIZE);
+		*(BSS_MAIN)
 		. = ALIGN(PAGE_SIZE);
 		__bss_stop = .;
 	}
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index f500293dad8d..ce4a9f1f845e 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -5,7 +5,7 @@
 #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
 #define KVM_POSSIBLE_CR4_GUEST_BITS				  \
 	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR  \
-	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
+	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD)
 
 static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu,
 					      enum kvm_reg reg)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 537c36b55b5d..d4fdf0e52144 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1918,7 +1918,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
+	if (!kvm_apic_present(vcpu) || apic_lvtt_oneshot(apic) ||
 			apic_lvtt_period(apic))
 		return;
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e5af08b58132..1cceee0ed580 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -263,6 +263,11 @@ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
  */
 static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
 
+/*
+ * The number of non-reserved physical address bits irrespective of features
+ * that repurpose legal bits, e.g. MKTME.
+ */
+static u8 __read_mostly shadow_phys_bits;
 
 static void mmu_spte_set(u64 *sptep, u64 spte);
 static void mmu_free_roots(struct kvm_vcpu *vcpu);
@@ -275,11 +280,18 @@ static bool is_executable_pte(u64 spte);
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value)
 {
 	BUG_ON((mmio_mask & mmio_value) != mmio_value);
+	WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len));
+	WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);
 	shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK;
 	shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
 
+static bool is_mmio_spte(u64 spte)
+{
+	return (spte & shadow_mmio_mask) == shadow_mmio_value;
+}
+
 static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
 {
 	return sp->role.ad_disabled;
@@ -287,7 +299,7 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
 
 static inline bool spte_ad_enabled(u64 spte)
 {
-	MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value);
+	MMU_WARN_ON(is_mmio_spte(spte));
 	return !(spte & shadow_acc_track_value);
 }
 
@@ -298,13 +310,13 @@ static bool is_nx_huge_page_enabled(void)
 
 static inline u64 spte_shadow_accessed_mask(u64 spte)
 {
-	MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value);
+	MMU_WARN_ON(is_mmio_spte(spte));
 	return spte_ad_enabled(spte) ? shadow_accessed_mask : 0;
 }
 
 static inline u64 spte_shadow_dirty_mask(u64 spte)
 {
-	MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value);
+	MMU_WARN_ON(is_mmio_spte(spte));
 	return spte_ad_enabled(spte) ? shadow_dirty_mask : 0;
 }
 
@@ -374,11 +386,6 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
 	mmu_spte_set(sptep, mask);
 }
 
-static bool is_mmio_spte(u64 spte)
-{
-	return (spte & shadow_mmio_mask) == shadow_mmio_value;
-}
-
 static gfn_t get_mmio_spte_gfn(u64 spte)
 {
 	u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
@@ -443,6 +450,21 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
+static u8 kvm_get_shadow_phys_bits(void)
+{
+	/*
+	 * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected
+	 * in CPU detection code, but MKTME treats those reduced bits as
+	 * 'keyID' thus they are not reserved bits. Therefore for MKTME
+	 * we should still return physical address bits reported by CPUID.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_TME) ||
+	    WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008))
+		return boot_cpu_data.x86_phys_bits;
+
+	return cpuid_eax(0x80000008) & 0xff;
+}
+
 static void kvm_mmu_reset_all_pte_masks(void)
 {
 	u8 low_phys_bits;
@@ -456,20 +478,29 @@ static void kvm_mmu_reset_all_pte_masks(void)
 	shadow_present_mask = 0;
 	shadow_acc_track_mask = 0;
 
+	shadow_phys_bits = kvm_get_shadow_phys_bits();
+
 	/*
 	 * If the CPU has 46 or less physical address bits, then set an
 	 * appropriate mask to guard against L1TF attacks. Otherwise, it is
 	 * assumed that the CPU is not vulnerable to L1TF.
+	 *
+	 * Some Intel CPUs address the L1 cache using more PA bits than are
+	 * reported by CPUID. Use the PA width of the L1 cache when possible
+	 * to achieve more effective mitigation, e.g. if system RAM overlaps
+	 * the most significant bits of legal physical address space.
 	 */
+	shadow_nonpresent_or_rsvd_mask = 0;
 	low_phys_bits = boot_cpu_data.x86_phys_bits;
-	if (boot_cpu_data.x86_phys_bits <
-	    52 - shadow_nonpresent_or_rsvd_mask_len) {
+	if (boot_cpu_has_bug(X86_BUG_L1TF) &&
+	    !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >=
+			  52 - shadow_nonpresent_or_rsvd_mask_len)) {
+		low_phys_bits = boot_cpu_data.x86_cache_bits
+			- shadow_nonpresent_or_rsvd_mask_len;
 		shadow_nonpresent_or_rsvd_mask =
-			rsvd_bits(boot_cpu_data.x86_phys_bits -
-				  shadow_nonpresent_or_rsvd_mask_len,
-				  boot_cpu_data.x86_phys_bits - 1);
-		low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
+			rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1);
 	}
+
 	shadow_nonpresent_or_rsvd_lower_gfn_mask =
 		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
 }
@@ -1682,10 +1713,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
  * Emulate arch specific page modification logging for the
  * nested hypervisor
  */
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa)
 {
 	if (kvm_x86_ops->write_log_dirty)
-		return kvm_x86_ops->write_log_dirty(vcpu);
+		return kvm_x86_ops->write_log_dirty(vcpu, l2_gpa);
 
 	return 0;
 }
@@ -4213,7 +4244,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | gbpages_bit_rsvd |
+			gbpages_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
@@ -4305,7 +4336,7 @@ reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 	 */
 	shadow_zero_check = &context->shadow_zero_check;
 	__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
-				boot_cpu_data.x86_phys_bits,
+				shadow_phys_bits,
 				context->shadow_root_level, uses_nx,
 				guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES),
 				is_pse(vcpu), true);
@@ -4342,13 +4373,13 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 
 	if (boot_cpu_is_amd())
 		__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
-					boot_cpu_data.x86_phys_bits,
+					shadow_phys_bits,
 					context->shadow_root_level, false,
 					boot_cpu_has(X86_FEATURE_GBPAGES),
 					true, true);
 	else
 		__reset_rsvds_bits_mask_ept(shadow_zero_check,
-					    boot_cpu_data.x86_phys_bits,
+					    shadow_phys_bits,
 					    false);
 
 	if (!shadow_me_mask)
@@ -4369,7 +4400,7 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 				struct kvm_mmu *context, bool execonly)
 {
 	__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
-				    boot_cpu_data.x86_phys_bits, execonly);
+				    shadow_phys_bits, execonly);
 }
 
 #define BYTE_MASK(access) \
@@ -5666,6 +5697,25 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
 	return 0;
 }
 
+static void kvm_set_mmio_spte_mask(void)
+{
+	u64 mask;
+
+	/*
+	 * Set a reserved PA bit in MMIO SPTEs to generate page faults with
+	 * PFEC.RSVD=1 on MMIO accesses.  64-bit PTEs (PAE, x86-64, and EPT
+	 * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports
+	 * 52-bit physical addresses then there are no reserved PA bits in the
+	 * PTEs and so the reserved PA approach must be disabled.
+	 */
+	if (shadow_phys_bits < 52)
+		mask = BIT_ULL(51) | PT_PRESENT_MASK;
+	else
+		mask = 0;
+
+	kvm_mmu_set_mmio_spte_mask(mask, mask);
+}
+
 int kvm_mmu_module_init(void)
 {
 	if (nx_huge_pages == -1)
@@ -5673,6 +5723,8 @@ int kvm_mmu_module_init(void)
 
 	kvm_mmu_reset_all_pte_masks();
 
+	kvm_set_mmio_spte_mask();
+
 	pte_list_desc_cache = kmem_cache_create("pte_list_desc",
 					    sizeof(struct pte_list_desc),
 					    0, SLAB_ACCOUNT, NULL);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 068feab64acf..816a626b6250 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -194,7 +194,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn);
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 int kvm_mmu_post_init_vm(struct kvm *kvm);
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm);
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index 918b0d5bf272..1c1c2649829b 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -339,7 +339,7 @@ TRACE_EVENT(
 		/* These depend on page entry type, so compute them now.  */
 		__field(bool, r)
 		__field(bool, x)
-		__field(u8, u)
+		__field(signed char, u)
 	),
 
 	TP_fast_assign(
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 8cf7a09bdd73..7260a165488d 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -202,7 +202,7 @@ static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, u64 gpte)
 static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 					     struct kvm_mmu *mmu,
 					     struct guest_walker *walker,
-					     int write_fault)
+					     gpa_t addr, int write_fault)
 {
 	unsigned level, index;
 	pt_element_t pte, orig_pte;
@@ -227,7 +227,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 				!(pte & PT_GUEST_DIRTY_MASK)) {
 			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
 #if PTTYPE == PTTYPE_EPT
-			if (kvm_arch_write_log_dirty(vcpu))
+			if (kvm_arch_write_log_dirty(vcpu, addr))
 				return -EINVAL;
 #endif
 			pte |= PT_GUEST_DIRTY_MASK;
@@ -424,7 +424,8 @@ retry_walk:
 			(PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
-		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
+		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker,
+							addr, write_fault);
 		if (unlikely(ret < 0))
 			goto error;
 		else if (ret)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d63621386418..78826d123fb8 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2757,8 +2757,8 @@ static int nested_svm_exit_special(struct vcpu_svm *svm)
 			return NESTED_EXIT_HOST;
 		break;
 	case SVM_EXIT_EXCP_BASE + PF_VECTOR:
-		/* When we're shadowing, trap PFs, but not async PF */
-		if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0)
+		/* Trap async PF even if not shadowing */
+		if (!npt_enabled || svm->vcpu.arch.apf.host_apf_reason)
 			return NESTED_EXIT_HOST;
 		break;
 	default:
@@ -2847,7 +2847,7 @@ static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *fr
 	dst->iopm_base_pa         = from->iopm_base_pa;
 	dst->msrpm_base_pa        = from->msrpm_base_pa;
 	dst->tsc_offset           = from->tsc_offset;
-	dst->asid                 = from->asid;
+	/* asid not copied, it is handled manually for svm->vmcb.  */
 	dst->tlb_ctl              = from->tlb_ctl;
 	dst->int_ctl              = from->int_ctl;
 	dst->int_vector           = from->int_vector;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c139dedec12b..396d41f192ca 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5592,6 +5592,8 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 
 static void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
 {
+	BUILD_BUG_ON(KVM_CR4_GUEST_OWNED_BITS & ~KVM_POSSIBLE_CR4_GUEST_BITS);
+
 	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
 	if (enable_ept)
 		vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
@@ -8711,7 +8713,7 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
 				KVM_ISA_VMX);
 
-	switch (exit_reason) {
+	switch ((u16)exit_reason) {
 	case EXIT_REASON_EXCEPTION_NMI:
 		if (is_nmi(intr_info))
 			return false;
@@ -9142,6 +9144,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
 			exit_reason != EXIT_REASON_PML_FULL &&
+			exit_reason != EXIT_REASON_APIC_ACCESS &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -9280,15 +9283,16 @@ static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 	if (!lapic_in_kernel(vcpu))
 		return;
 
+	if (!flexpriority_enabled &&
+	    !cpu_has_vmx_virtualize_x2apic_mode())
+		return;
+
 	/* Postpone execution until vmcs01 is the current VMCS. */
 	if (is_guest_mode(vcpu)) {
 		to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true;
 		return;
 	}
 
-	if (!cpu_need_tpr_shadow(vcpu))
-		return;
-
 	sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
 	sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 			      SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
@@ -12461,11 +12465,10 @@ static void vmx_flush_log_dirty(struct kvm *kvm)
 	kvm_flush_pml_buffers(kvm);
 }
 
-static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
 	struct vmcs12 *vmcs12;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gpa_t gpa;
 	struct page *page = NULL;
 	u64 *pml_address;
 
@@ -12486,7 +12489,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
 			return 1;
 		}
 
-		gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+		gpa &= ~0xFFFull;
 
 		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->pml_address);
 		if (is_error_page(page))
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1477e23827c2..79fa55de635c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -806,6 +806,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE))
 			return 1;
+		if ((cr4 ^ old_cr4) & X86_CR4_LA57)
+			return 1;
 	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
 		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
@@ -2344,7 +2346,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		return kvm_mtrr_set_msr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
 		return kvm_set_apic_base(vcpu, msr_info);
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_write(vcpu, msr, data);
 	case MSR_IA32_TSCDEADLINE:
 		kvm_set_lapic_tscdeadline_msr(vcpu, data);
@@ -2629,7 +2631,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_APICBASE:
 		msr_info->data = kvm_get_apic_base(vcpu);
 		break;
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
 		break;
 	case MSR_IA32_TSCDEADLINE:
@@ -3073,6 +3075,9 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
+	if (vcpu->arch.st.steal.preempted)
+		return;
+
 	vcpu->arch.st.steal.preempted = 1;
 
 	kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
@@ -4365,10 +4370,13 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&u.ps, argp, sizeof u.ps))
 			goto out;
+		mutex_lock(&kvm->lock);
 		r = -ENXIO;
 		if (!kvm->arch.vpit)
-			goto out;
+			goto set_pit_out;
 		r = kvm_vm_ioctl_set_pit(kvm, &u.ps);
+set_pit_out:
+		mutex_unlock(&kvm->lock);
 		break;
 	}
 	case KVM_GET_PIT2: {
@@ -4388,10 +4396,13 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&u.ps2, argp, sizeof(u.ps2)))
 			goto out;
+		mutex_lock(&kvm->lock);
 		r = -ENXIO;
 		if (!kvm->arch.vpit)
-			goto out;
+			goto set_pit2_out;
 		r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2);
+set_pit2_out:
+		mutex_unlock(&kvm->lock);
 		break;
 	}
 	case KVM_REINJECT_CONTROL: {
@@ -6291,35 +6302,6 @@ void kvm_after_handle_nmi(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_after_handle_nmi);
 
-static void kvm_set_mmio_spte_mask(void)
-{
-	u64 mask;
-	int maxphyaddr = boot_cpu_data.x86_phys_bits;
-
-	/*
-	 * Set the reserved bits and the present bit of an paging-structure
-	 * entry to generate page fault with PFER.RSV = 1.
-	 */
-
-	/*
-	 * Mask the uppermost physical address bit, which would be reserved as
-	 * long as the supported physical address width is less than 52.
-	 */
-	mask = 1ull << 51;
-
-	/* Set the present bit. */
-	mask |= 1ull;
-
-	/*
-	 * If reserved bit is not supported, clear the present bit to disable
-	 * mmio page fault.
-	 */
-	if (maxphyaddr == 52)
-		mask &= ~1ull;
-
-	kvm_mmu_set_mmio_spte_mask(mask, mask);
-}
-
 #ifdef CONFIG_X86_64
 static void pvclock_gtod_update_fn(struct work_struct *work)
 {
@@ -6397,8 +6379,6 @@ int kvm_arch_init(void *opaque)
 	if (r)
 		goto out_free_percpu;
 
-	kvm_set_mmio_spte_mask();
-
 	kvm_x86_ops = ops;
 
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 75d3776123cc..2c3b4bcbe8f2 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -118,7 +118,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
 	 */
 	if (size < 8) {
 		if (!IS_ALIGNED(dest, 4) || size != 4)
-			clean_cache_range(dst, 1);
+			clean_cache_range(dst, size);
 	} else {
 		if (!IS_ALIGNED(dest, 8)) {
 			dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S
index f031c0e19356..515cdee90df7 100644
--- a/arch/x86/math-emu/wm_sqrt.S
+++ b/arch/x86/math-emu/wm_sqrt.S
@@ -209,7 +209,7 @@ sqrt_stage_2_finish:
 
 #ifdef PARANOID
 /* It should be possible to get here only if the arg is ffff....ffff */
-	cmp	$0xffffffff,FPU_fsqrt_arg_1
+	cmpl	$0xffffffff,FPU_fsqrt_arg_1
 	jnz	sqrt_stage_2_error
 #endif /* PARANOID */
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 32bb38f6fc18..8039a951db8f 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -112,8 +112,6 @@ __ref void *alloc_low_pages(unsigned int num)
 	} else {
 		pfn = pgt_buf_end;
 		pgt_buf_end += num;
-		printk(KERN_DEBUG "BRK [%#010lx, %#010lx] PGTABLE\n",
-			pfn << PAGE_SHIFT, (pgt_buf_end << PAGE_SHIFT) - 1);
 	}
 
 	for (i = 0; i < num; i++) {
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 4d434ddb75db..f140b2d39319 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -385,7 +385,7 @@ static void enter_uniprocessor(void)
 	int cpu;
 	int err;
 
-	if (downed_cpus == NULL &&
+	if (!cpumask_available(downed_cpus) &&
 	    !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) {
 		pr_notice("Failed to allocate mask\n");
 		goto out;
@@ -415,7 +415,7 @@ static void leave_uniprocessor(void)
 	int cpu;
 	int err;
 
-	if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0)
+	if (!cpumask_available(downed_cpus) || cpumask_weight(downed_cpus) == 0)
 		return;
 	pr_notice("Re-enabling CPUs...\n");
 	for_each_cpu(cpu, downed_cpus) {
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 33e9b4f1ce20..c177da94fc79 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -572,6 +572,10 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa1ec, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa1ed, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26c, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26d, pci_invalid_bar);
 
 /*
  * Device [1022:7808]
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 03fc397335b7..c9fc725a1dcf 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -171,9 +171,10 @@ static struct irq_domain *uv_get_irq_domain(void)
 		goto out;
 
 	uv_domain = irq_domain_create_tree(fn, &uv_domain_ops, NULL);
-	irq_domain_free_fwnode(fn);
 	if (uv_domain)
 		uv_domain->parent = x86_vector_domain;
+	else
+		irq_domain_free_fwnode(fn);
 out:
 	mutex_unlock(&uv_lock);
 
diff --git a/arch/x86/tools/distill.awk b/arch/x86/tools/distill.awk
index e0edeccc1429..c71b45fd68a5 100644
--- a/arch/x86/tools/distill.awk
+++ b/arch/x86/tools/distill.awk
@@ -1,4 +1,4 @@
-#!/bin/awk -f
+#!/usr/bin/awk -f
 # SPDX-License-Identifier: GPL-2.0
 # Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len
 # Distills the disassembly as follows:
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index a42015b305f4..1c2832e9f77d 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -1,4 +1,4 @@
-#!/bin/awk -f
+#!/usr/bin/awk -f
 # SPDX-License-Identifier: GPL-2.0
 # gen-insn-attr-x86.awk: Instruction attribute table generator
 # Written by Masami Hiramatsu <mhiramat@redhat.com>
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index ff1d81385ed7..768e1f7ab871 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -404,7 +404,7 @@ static struct pmu xtensa_pmu = {
 	.read = xtensa_pmu_read,
 };
 
-static int xtensa_pmu_setup(int cpu)
+static int xtensa_pmu_setup(unsigned int cpu)
 {
 	unsigned i;
 
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 92fb20777bb0..a19c61b26142 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -711,7 +711,8 @@ c_start(struct seq_file *f, loff_t *pos)
 static void *
 c_next(struct seq_file *f, void *v, loff_t *pos)
 {
-	return NULL;
+	++*pos;
+	return c_start(f, pos);
 }
 
 static void
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index dc7b470a423a..58b79e2ea569 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -82,13 +82,13 @@ void __xtensa_libgcc_window_spill(void)
 }
 EXPORT_SYMBOL(__xtensa_libgcc_window_spill);
 
-unsigned long __sync_fetch_and_and_4(unsigned long *p, unsigned long v)
+unsigned int __sync_fetch_and_and_4(volatile void *p, unsigned int v)
 {
 	BUG();
 }
 EXPORT_SYMBOL(__sync_fetch_and_and_4);
 
-unsigned long __sync_fetch_and_or_4(unsigned long *p, unsigned long v)
+unsigned int __sync_fetch_and_or_4(volatile void *p, unsigned int v)
 {
 	BUG();
 }
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index c45b90bb9339..c75e75932807 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -21,7 +21,6 @@
 #include <platform/simcall.h>
 
 #define SIMDISK_MAJOR 240
-#define SECTOR_SHIFT 9
 #define SIMDISK_MINORS 1
 #define MAX_SIMDISK_COUNT 10
 
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 7f8010662437..d3df44c3b43a 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -315,7 +315,6 @@ bool bio_integrity_prep(struct bio *bio)
 
 		if (ret == 0) {
 			printk(KERN_ERR "could not attach integrity payload\n");
-			kfree(buf);
 			status = BLK_STS_RESOURCE;
 			goto err_end_io;
 		}
diff --git a/block/blk-core.c b/block/blk-core.c
index 4e04c79aa2c2..2407c898ba7d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -852,6 +852,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	q->backing_dev_info->ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
+	q->backing_dev_info->io_pages =
+			(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
 	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
 	q->backing_dev_info->name = "block";
 	q->node = node_id;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 9d53f476c517..cf56bdad2e06 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2738,6 +2738,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_freeze_queue(q);
+	/*
+	 * Sync with blk_mq_queue_tag_busy_iter.
+	 */
+	synchronize_rcu();
 
 	set->nr_hw_queues = nr_hw_queues;
 	blk_mq_update_queue_map(set);
@@ -2748,10 +2752,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_unfreeze_queue(q);
-	/*
-	 * Sync with blk_mq_queue_tag_busy_iter.
-	 */
-	synchronize_rcu();
 }
 
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 0679c35adf55..3f3b57f80bdb 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -133,21 +133,15 @@ EXPORT_SYMBOL_GPL(af_alg_release);
 void af_alg_release_parent(struct sock *sk)
 {
 	struct alg_sock *ask = alg_sk(sk);
-	unsigned int nokey = ask->nokey_refcnt;
-	bool last = nokey && !ask->refcnt;
+	unsigned int nokey = atomic_read(&ask->nokey_refcnt);
 
 	sk = ask->parent;
 	ask = alg_sk(sk);
 
-	local_bh_disable();
-	bh_lock_sock(sk);
-	ask->nokey_refcnt -= nokey;
-	if (!last)
-		last = !--ask->refcnt;
-	bh_unlock_sock(sk);
-	local_bh_enable();
+	if (nokey)
+		atomic_dec(&ask->nokey_refcnt);
 
-	if (last)
+	if (atomic_dec_and_test(&ask->refcnt))
 		sock_put(sk);
 }
 EXPORT_SYMBOL_GPL(af_alg_release_parent);
@@ -192,7 +186,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	err = -EBUSY;
 	lock_sock(sk);
-	if (ask->refcnt | ask->nokey_refcnt)
+	if (atomic_read(&ask->refcnt))
 		goto unlock;
 
 	swap(ask->type, type);
@@ -241,7 +235,7 @@ static int alg_setsockopt(struct socket *sock, int level, int optname,
 	int err = -EBUSY;
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (atomic_read(&ask->refcnt) != atomic_read(&ask->nokey_refcnt))
 		goto unlock;
 
 	type = ask->type;
@@ -308,12 +302,14 @@ int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern)
 
 	sk2->sk_family = PF_ALG;
 
-	if (nokey || !ask->refcnt++)
+	if (atomic_inc_return_relaxed(&ask->refcnt) == 1)
 		sock_hold(sk);
-	ask->nokey_refcnt += nokey;
+	if (nokey) {
+		atomic_inc(&ask->nokey_refcnt);
+		atomic_set(&alg_sk(sk2)->nokey_refcnt, 1);
+	}
 	alg_sk(sk2)->parent = sk;
 	alg_sk(sk2)->type = type;
-	alg_sk(sk2)->nokey_refcnt = nokey;
 
 	newsock->ops = type->ops;
 	newsock->state = SS_CONNECTED;
diff --git a/crypto/algboss.c b/crypto/algboss.c
index 960d8548171b..9d253e1016b1 100644
--- a/crypto/algboss.c
+++ b/crypto/algboss.c
@@ -194,8 +194,6 @@ static int cryptomgr_schedule_probe(struct crypto_larval *larval)
 	if (IS_ERR(thread))
 		goto err_put_larval;
 
-	wait_for_completion_interruptible(&larval->completion);
-
 	return NOTIFY_STOP;
 
 err_put_larval:
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index f138af18b500..379e83c8aa52 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -389,7 +389,7 @@ static int aead_check_key(struct socket *sock)
 	struct alg_sock *ask = alg_sk(sk);
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (!atomic_read(&ask->nokey_refcnt))
 		goto unlock_child;
 
 	psk = ask->parent;
@@ -401,11 +401,8 @@ static int aead_check_key(struct socket *sock)
 	if (!tfm->has_key)
 		goto unlock;
 
-	if (!pask->refcnt++)
-		sock_hold(psk);
-
-	ask->refcnt = 1;
-	sock_put(psk);
+	atomic_dec(&pask->nokey_refcnt);
+	atomic_set(&ask->nokey_refcnt, 0);
 
 	err = 0;
 
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 39cebd3256bf..d987e2c90d74 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -309,7 +309,7 @@ static int hash_check_key(struct socket *sock)
 	struct alg_sock *ask = alg_sk(sk);
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (!atomic_read(&ask->nokey_refcnt))
 		goto unlock_child;
 
 	psk = ask->parent;
@@ -321,11 +321,8 @@ static int hash_check_key(struct socket *sock)
 	if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
 		goto unlock;
 
-	if (!pask->refcnt++)
-		sock_hold(psk);
-
-	ask->refcnt = 1;
-	sock_put(psk);
+	atomic_dec(&pask->nokey_refcnt);
+	atomic_set(&ask->nokey_refcnt, 0);
 
 	err = 0;
 
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 90bc4e0f0785..d9ec5dca8672 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -85,14 +85,10 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 		return PTR_ERR(areq);
 
 	/* convert iovecs of output buffers into RX SGL */
-	err = af_alg_get_rsgl(sk, msg, flags, areq, -1, &len);
+	err = af_alg_get_rsgl(sk, msg, flags, areq, ctx->used, &len);
 	if (err)
 		goto free;
 
-	/* Process only as much RX buffers for which we have TX data */
-	if (len > ctx->used)
-		len = ctx->used;
-
 	/*
 	 * If more buffers are to be expected to be processed, process only
 	 * full block size buffers.
@@ -227,7 +223,7 @@ static int skcipher_check_key(struct socket *sock)
 	struct alg_sock *ask = alg_sk(sk);
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (!atomic_read(&ask->nokey_refcnt))
 		goto unlock_child;
 
 	psk = ask->parent;
@@ -239,11 +235,8 @@ static int skcipher_check_key(struct socket *sock)
 	if (!tfm->has_key)
 		goto unlock;
 
-	if (!pask->refcnt++)
-		sock_hold(psk);
-
-	ask->refcnt = 1;
-	sock_put(psk);
+	atomic_dec(&pask->nokey_refcnt);
+	atomic_set(&ask->nokey_refcnt, 0);
 
 	err = 0;
 
diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c
index 8de060664204..e23f3d54bb31 100644
--- a/drivers/acpi/acpica/exprep.c
+++ b/drivers/acpi/acpica/exprep.c
@@ -507,10 +507,6 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info)
 				    (u8)access_byte_width;
 			}
 		}
-		/* An additional reference for the container */
-
-		acpi_ut_add_reference(obj_desc->field.region_obj);
-
 		ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
 				  "RegionField: BitOff %X, Off %X, Gran %X, Region %p\n",
 				  obj_desc->field.start_field_bit_offset,
diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c
index c6eb9fae70f9..61a979d0fbc5 100644
--- a/drivers/acpi/acpica/utdelete.c
+++ b/drivers/acpi/acpica/utdelete.c
@@ -593,11 +593,6 @@ acpi_ut_update_object_reference(union acpi_operand_object *object, u16 action)
 			next_object = object->buffer_field.buffer_obj;
 			break;
 
-		case ACPI_TYPE_LOCAL_REGION_FIELD:
-
-			next_object = object->field.region_obj;
-			break;
-
 		case ACPI_TYPE_LOCAL_BANK_FIELD:
 
 			next_object = object->bank_field.bank_obj;
@@ -638,6 +633,7 @@ acpi_ut_update_object_reference(union acpi_operand_object *object, u16 action)
 			}
 			break;
 
+		case ACPI_TYPE_LOCAL_REGION_FIELD:
 		case ACPI_TYPE_REGION:
 		default:
 
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 7bf1948b1223..732549ee1fe3 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -800,6 +800,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 			"acpi_cppc");
 	if (ret) {
 		per_cpu(cpc_desc_ptr, pr->id) = NULL;
+		kobject_put(&cpc_ptr->kobj);
 		goto out_free;
 	}
 
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index afb1bc104a6f..6681174caf84 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -172,7 +172,7 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 		 * possibly drop references to the power resources in use.
 		 */
 		state = ACPI_STATE_D3_HOT;
-		/* If _PR3 is not available, use D3hot as the target state. */
+		/* If D3cold is not supported, use D3hot as the target state. */
 		if (!device->power.states[ACPI_STATE_D3_COLD].flags.valid)
 			target_state = state;
 	} else if (!device->power.states[state].flags.valid) {
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index ebfc06f29f7b..37aacb39e692 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1063,28 +1063,20 @@ void acpi_ec_unblock_transactions(void)
                                 Event Management
    -------------------------------------------------------------------------- */
 static struct acpi_ec_query_handler *
-acpi_ec_get_query_handler(struct acpi_ec_query_handler *handler)
-{
-	if (handler)
-		kref_get(&handler->kref);
-	return handler;
-}
-
-static struct acpi_ec_query_handler *
 acpi_ec_get_query_handler_by_value(struct acpi_ec *ec, u8 value)
 {
 	struct acpi_ec_query_handler *handler;
-	bool found = false;
 
 	mutex_lock(&ec->mutex);
 	list_for_each_entry(handler, &ec->list, node) {
 		if (value == handler->query_bit) {
-			found = true;
-			break;
+			kref_get(&handler->kref);
+			mutex_unlock(&ec->mutex);
+			return handler;
 		}
 	}
 	mutex_unlock(&ec->mutex);
-	return found ? acpi_ec_get_query_handler(handler) : NULL;
+	return NULL;
 }
 
 static void acpi_ec_query_handler_release(struct kref *kref)
diff --git a/drivers/acpi/evged.c b/drivers/acpi/evged.c
index 46f060356a22..339e6d3dba7c 100644
--- a/drivers/acpi/evged.c
+++ b/drivers/acpi/evged.c
@@ -82,6 +82,8 @@ static acpi_status acpi_ged_request_interrupt(struct acpi_resource *ares,
 	struct resource r;
 	struct acpi_resource_irq *p = &ares->data.irq;
 	struct acpi_resource_extended_irq *pext = &ares->data.extended_irq;
+	char ev_name[5];
+	u8 trigger;
 
 	if (ares->type == ACPI_RESOURCE_TYPE_END_TAG)
 		return AE_OK;
@@ -90,14 +92,28 @@ static acpi_status acpi_ged_request_interrupt(struct acpi_resource *ares,
 		dev_err(dev, "unable to parse IRQ resource\n");
 		return AE_ERROR;
 	}
-	if (ares->type == ACPI_RESOURCE_TYPE_IRQ)
+	if (ares->type == ACPI_RESOURCE_TYPE_IRQ) {
 		gsi = p->interrupts[0];
-	else
+		trigger = p->triggering;
+	} else {
 		gsi = pext->interrupts[0];
+		trigger = pext->triggering;
+	}
 
 	irq = r.start;
 
-	if (ACPI_FAILURE(acpi_get_handle(handle, "_EVT", &evt_handle))) {
+	switch (gsi) {
+	case 0 ... 255:
+		sprintf(ev_name, "_%c%02hhX",
+			trigger == ACPI_EDGE_SENSITIVE ? 'E' : 'L', gsi);
+
+		if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle)))
+			break;
+		/* fall through */
+	default:
+		if (ACPI_SUCCESS(acpi_get_handle(handle, "_EVT", &evt_handle)))
+			break;
+
 		dev_err(dev, "cannot locate _EVT method\n");
 		return AE_ERROR;
 	}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 2eddbb1fae6a..8bc1a778b3a4 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -920,12 +920,9 @@ static void acpi_bus_init_power_state(struct acpi_device *device, int state)
 
 		if (buffer.length && package
 		    && package->type == ACPI_TYPE_PACKAGE
-		    && package->package.count) {
-			int err = acpi_extract_power_resources(package, 0,
-							       &ps->resources);
-			if (!err)
-				device->power.flags.power_resources = 1;
-		}
+		    && package->package.count)
+			acpi_extract_power_resources(package, 0, &ps->resources);
+
 		ACPI_FREE(buffer.pointer);
 	}
 
@@ -972,14 +969,27 @@ static void acpi_bus_get_power_flags(struct acpi_device *device)
 		acpi_bus_init_power_state(device, i);
 
 	INIT_LIST_HEAD(&device->power.states[ACPI_STATE_D3_COLD].resources);
-	if (!list_empty(&device->power.states[ACPI_STATE_D3_HOT].resources))
-		device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1;
 
-	/* Set defaults for D0 and D3hot states (always valid) */
+	/* Set the defaults for D0 and D3hot (always supported). */
 	device->power.states[ACPI_STATE_D0].flags.valid = 1;
 	device->power.states[ACPI_STATE_D0].power = 100;
 	device->power.states[ACPI_STATE_D3_HOT].flags.valid = 1;
 
+	/*
+	 * Use power resources only if the D0 list of them is populated, because
+	 * some platforms may provide _PR3 only to indicate D3cold support and
+	 * in those cases the power resources list returned by it may be bogus.
+	 */
+	if (!list_empty(&device->power.states[ACPI_STATE_D0].resources)) {
+		device->power.flags.power_resources = 1;
+		/*
+		 * D3cold is supported if the D3hot list of power resources is
+		 * not empty.
+		 */
+		if (!list_empty(&device->power.states[ACPI_STATE_D3_HOT].resources))
+			device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1;
+	}
+
 	if (acpi_bus_init_power(device))
 		device->flags.power_manageable = 0;
 }
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 0fd57bf33524..3b7e23866b42 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -942,13 +942,13 @@ static void __exit interrupt_stats_exit(void)
 }
 
 static ssize_t
-acpi_show_profile(struct device *dev, struct device_attribute *attr,
+acpi_show_profile(struct kobject *kobj, struct kobj_attribute *attr,
 		  char *buf)
 {
 	return sprintf(buf, "%d\n", acpi_gbl_FADT.preferred_profile);
 }
 
-static const struct device_attribute pm_profile_attr =
+static const struct kobj_attribute pm_profile_attr =
 	__ATTR(pm_profile, S_IRUGO, acpi_show_profile, NULL);
 
 static ssize_t hotplug_enabled_show(struct kobject *kobj,
@@ -997,8 +997,10 @@ void acpi_sysfs_add_hotplug_profile(struct acpi_hotplug_profile *hotplug,
 
 	error = kobject_init_and_add(&hotplug->kobj,
 		&acpi_hotplug_profile_ktype, hotplug_kobj, "%s", name);
-	if (error)
+	if (error) {
+		kobject_put(&hotplug->kobj);
 		goto err_out;
+	}
 
 	kobject_uevent(&hotplug->kobj, KOBJ_ADD);
 	return;
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 214c4e2e8ade..ab1da5e6e7e3 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -328,6 +328,25 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "Precision 7510"),
 		},
 	},
+	{
+	 .callback = video_detect_force_native,
+	 .ident = "Acer Aspire 5738z",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"),
+		DMI_MATCH(DMI_BOARD_NAME, "JV50"),
+		},
+	},
+	{
+	 /* https://bugzilla.kernel.org/show_bug.cgi?id=207835 */
+	 .callback = video_detect_force_native,
+	 .ident = "Acer TravelMate 5735Z",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 5735Z"),
+		DMI_MATCH(DMI_BOARD_NAME, "BA51_MV"),
+		},
+	},
 
 	/*
 	 * Desktops which falsely report a backlight and which our heuristics
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 05e75d18b4d9..bd74a29cf86c 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2813,6 +2813,12 @@ static void binder_transaction(struct binder_proc *proc,
 			goto err_dead_binder;
 		}
 		e->to_node = target_node->debug_id;
+		if (WARN_ON(proc == target_proc)) {
+			return_error = BR_FAILED_REPLY;
+			return_error_param = -EINVAL;
+			return_error_line = __LINE__;
+			goto err_invalid_target_handle;
+		}
 		if (security_binder_transaction(proc->tsk,
 						target_proc->tsk) < 0) {
 			return_error = BR_FAILED_REPLY;
@@ -3288,10 +3294,17 @@ static int binder_thread_write(struct binder_proc *proc,
 				struct binder_node *ctx_mgr_node;
 				mutex_lock(&context->context_mgr_node_lock);
 				ctx_mgr_node = context->binder_context_mgr_node;
-				if (ctx_mgr_node)
+				if (ctx_mgr_node) {
+					if (ctx_mgr_node->proc == proc) {
+						binder_user_error("%d:%d context manager tried to acquire desc 0\n",
+								  proc->pid, thread->pid);
+						mutex_unlock(&context->context_mgr_node_lock);
+						return -EINVAL;
+					}
 					ret = binder_inc_ref_for_node(
 							proc, ctx_mgr_node,
 							strong, NULL, &rdata);
+				}
 				mutex_unlock(&context->context_mgr_node_lock);
 			}
 			if (ret)
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 41474eec2181..f89ea0866892 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -968,7 +968,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 		trace_binder_unmap_user_end(alloc, index);
 	}
 	up_read(&mm->mmap_sem);
-	mmput(mm);
+	mmput_async(mm);
 
 	trace_binder_unmap_kernel_start(alloc, index);
 
diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c
index 940ddbc59aa7..572848d93363 100644
--- a/drivers/ata/acard-ahci.c
+++ b/drivers/ata/acard-ahci.c
@@ -72,7 +72,7 @@ struct acard_sg {
 	__le32			size;	 /* bit 31 (EOT) max==0x10000 (64k) */
 };
 
-static void acard_ahci_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc);
 static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc);
 static int acard_ahci_port_start(struct ata_port *ap);
 static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
@@ -257,7 +257,7 @@ static unsigned int acard_ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl)
 	return si;
 }
 
-static void acard_ahci_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct ahci_port_priv *pp = ap->private_data;
@@ -295,6 +295,8 @@ static void acard_ahci_qc_prep(struct ata_queued_cmd *qc)
 		opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH;
 
 	ahci_fill_cmd_slot(pp, qc->tag, opts);
+
+	return AC_ERR_OK;
 }
 
 static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 7473ff46de66..1fe18a4983f0 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -73,7 +73,7 @@ static int ahci_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
 static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc);
 static int ahci_port_start(struct ata_port *ap);
 static void ahci_port_stop(struct ata_port *ap);
-static void ahci_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc);
 static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc);
 static void ahci_freeze(struct ata_port *ap);
 static void ahci_thaw(struct ata_port *ap);
@@ -1626,7 +1626,7 @@ static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc)
 		return sata_pmp_qc_defer_cmd_switch(qc);
 }
 
-static void ahci_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct ahci_port_priv *pp = ap->private_data;
@@ -1662,6 +1662,8 @@ static void ahci_qc_prep(struct ata_queued_cmd *qc)
 		opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH;
 
 	ahci_fill_cmd_slot(pp, qc->tag, opts);
+
+	return AC_ERR_OK;
 }
 
 static void ahci_fbs_dec_intr(struct ata_port *ap)
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 33eb5e342a7a..c28b0ca24907 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -57,7 +57,6 @@
 #include <linux/workqueue.h>
 #include <linux/scatterlist.h>
 #include <linux/io.h>
-#include <linux/async.h>
 #include <linux/log2.h>
 #include <linux/slab.h>
 #include <linux/glob.h>
@@ -4489,9 +4488,8 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */
 	{ "C300-CTFDDAC128MAG",	"0001",		ATA_HORKAGE_NONCQ, },
 
-	/* Some Sandisk SSDs lock up hard with NCQ enabled.  Reported on
-	   SD7SN6S256G and SD8SN8U256G */
-	{ "SanDisk SD[78]SN*G",	NULL,		ATA_HORKAGE_NONCQ, },
+	/* Sandisk SD7/8/9s lock up hard on large trims */
+	{ "SanDisk SD[789]*",	NULL,		ATA_HORKAGE_MAX_TRIM_128M, },
 
 	/* devices which puke on READ_NATIVE_MAX */
 	{ "HDS724040KLSA80",	"KFAOA20N",	ATA_HORKAGE_BROKEN_HPA, },
@@ -4988,7 +4986,10 @@ int ata_std_qc_defer(struct ata_queued_cmd *qc)
 	return ATA_DEFER_LINK;
 }
 
-void ata_noop_qc_prep(struct ata_queued_cmd *qc) { }
+enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc)
+{
+	return AC_ERR_OK;
+}
 
 /**
  *	ata_sg_init - Associate command with scatter-gather table.
@@ -5441,7 +5442,9 @@ void ata_qc_issue(struct ata_queued_cmd *qc)
 		return;
 	}
 
-	ap->ops->qc_prep(qc);
+	qc->err_mask |= ap->ops->qc_prep(qc);
+	if (unlikely(qc->err_mask))
+		goto err;
 	trace_ata_qc_issue(qc);
 	qc->err_mask |= ap->ops->qc_issue(qc);
 	if (unlikely(qc->err_mask))
@@ -6536,7 +6539,7 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 	/* perform each probe asynchronously */
 	for (i = 0; i < host->n_ports; i++) {
 		struct ata_port *ap = host->ports[i];
-		async_schedule(async_port_probe, ap);
+		ap->cookie = async_schedule(async_port_probe, ap);
 	}
 
 	return 0;
@@ -6676,11 +6679,11 @@ void ata_host_detach(struct ata_host *host)
 {
 	int i;
 
-	/* Ensure ata_port probe has completed */
-	async_synchronize_full();
-
-	for (i = 0; i < host->n_ports; i++)
+	for (i = 0; i < host->n_ports; i++) {
+		/* Ensure ata_port probe has completed */
+		async_synchronize_cookie(host->ports[i]->cookie + 1);
 		ata_port_detach(host->ports[i]);
+	}
 
 	/* the host is dead now, dissociate ACPI */
 	ata_acpi_dissociate(host);
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 2f81d6534270..4b299efbd804 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2392,6 +2392,7 @@ static unsigned int ata_scsiop_inq_89(struct ata_scsi_args *args, u8 *rbuf)
 
 static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf)
 {
+	struct ata_device *dev = args->dev;
 	u16 min_io_sectors;
 
 	rbuf[1] = 0xb0;
@@ -2417,7 +2418,12 @@ static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf)
 	 * with the unmap bit set.
 	 */
 	if (ata_id_has_trim(args->id)) {
-		put_unaligned_be64(65535 * ATA_MAX_TRIM_RNUM, &rbuf[36]);
+		u64 max_blocks = 65535 * ATA_MAX_TRIM_RNUM;
+
+		if (dev->horkage & ATA_HORKAGE_MAX_TRIM_128M)
+			max_blocks = 128 << (20 - SECTOR_SHIFT);
+
+		put_unaligned_be64(max_blocks, &rbuf[36]);
 		put_unaligned_be32(1, &rbuf[28]);
 	}
 
@@ -3996,12 +4002,13 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)
 {
 	struct scsi_cmnd *scmd = qc->scsicmd;
 	const u8 *cdb = scmd->cmnd;
-	const u8 *p;
 	u8 pg, spg;
 	unsigned six_byte, pg_len, hdr_len, bd_len;
 	int len;
 	u16 fp = (u16)-1;
 	u8 bp = 0xff;
+	u8 buffer[64];
+	const u8 *p = buffer;
 
 	VPRINTK("ENTER\n");
 
@@ -4035,12 +4042,14 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)
 	if (!scsi_sg_count(scmd) || scsi_sglist(scmd)->length < len)
 		goto invalid_param_len;
 
-	p = page_address(sg_page(scsi_sglist(scmd)));
-
 	/* Move past header and block descriptors.  */
 	if (len < hdr_len)
 		goto invalid_param_len;
 
+	if (!sg_copy_to_buffer(scsi_sglist(scmd), scsi_sg_count(scmd),
+			       buffer, sizeof(buffer)))
+		goto invalid_param_len;
+
 	if (six_byte)
 		bd_len = p[3];
 	else
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 8c36ff0c2dd4..7057630ccf52 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -2725,12 +2725,14 @@ static void ata_bmdma_fill_sg_dumb(struct ata_queued_cmd *qc)
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  */
-void ata_bmdma_qc_prep(struct ata_queued_cmd *qc)
+enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	ata_bmdma_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep);
 
@@ -2743,12 +2745,14 @@ EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep);
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  */
-void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc)
+enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	ata_bmdma_fill_sg_dumb(qc);
+
+	return AC_ERR_OK;
 }
 EXPORT_SYMBOL_GPL(ata_bmdma_dumb_qc_prep);
 
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index 0adcb40d2794..054a88ecd5ba 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -507,7 +507,7 @@ static int pata_macio_cable_detect(struct ata_port *ap)
 	return ATA_CBL_PATA40;
 }
 
-static void pata_macio_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)
 {
 	unsigned int write = (qc->tf.flags & ATA_TFLAG_WRITE);
 	struct ata_port *ap = qc->ap;
@@ -520,7 +520,7 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc)
 		   __func__, qc, qc->flags, write, qc->dev->devno);
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	table = (struct dbdma_cmd *) priv->dma_table_cpu;
 
@@ -565,6 +565,8 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc)
 	table->command = cpu_to_le16(DBDMA_STOP);
 
 	dev_dbgdma(priv->dev, "%s: %d DMA list entries\n", __func__, pi);
+
+	return AC_ERR_OK;
 }
 
 
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index f6c46e9a4dc0..d7186a503e35 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -59,25 +59,27 @@ static void pxa_ata_dma_irq(void *d)
 /*
  * Prepare taskfile for submission.
  */
-static void pxa_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pxa_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct pata_pxa_data *pd = qc->ap->private_data;
 	struct dma_async_tx_descriptor *tx;
 	enum dma_transfer_direction dir;
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	dir = (qc->dma_dir == DMA_TO_DEVICE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM);
 	tx = dmaengine_prep_slave_sg(pd->dma_chan, qc->sg, qc->n_elem, dir,
 				     DMA_PREP_INTERRUPT);
 	if (!tx) {
 		ata_dev_err(qc->dev, "prep_slave_sg() failed\n");
-		return;
+		return AC_ERR_OK;
 	}
 	tx->callback = pxa_ata_dma_irq;
 	tx->callback_param = pd;
 	pd->dma_cookie = dmaengine_submit(tx);
+
+	return AC_ERR_OK;
 }
 
 /*
diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c
index f1e873a37465..096b4771b19d 100644
--- a/drivers/ata/pdc_adma.c
+++ b/drivers/ata/pdc_adma.c
@@ -132,7 +132,7 @@ static int adma_ata_init_one(struct pci_dev *pdev,
 				const struct pci_device_id *ent);
 static int adma_port_start(struct ata_port *ap);
 static void adma_port_stop(struct ata_port *ap);
-static void adma_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int adma_qc_issue(struct ata_queued_cmd *qc);
 static int adma_check_atapi_dma(struct ata_queued_cmd *qc);
 static void adma_freeze(struct ata_port *ap);
@@ -311,7 +311,7 @@ static int adma_fill_sg(struct ata_queued_cmd *qc)
 	return i;
 }
 
-static void adma_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct adma_port_priv *pp = qc->ap->private_data;
 	u8  *buf = pp->pkt;
@@ -322,7 +322,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc)
 
 	adma_enter_reg_mode(qc->ap);
 	if (qc->tf.protocol != ATA_PROT_DMA)
-		return;
+		return AC_ERR_OK;
 
 	buf[i++] = 0;	/* Response flags */
 	buf[i++] = 0;	/* reserved */
@@ -387,6 +387,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc)
 			printk("%s\n", obuf);
 	}
 #endif
+	return AC_ERR_OK;
 }
 
 static inline void adma_packet_start(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 95bf3abda6f6..5a94659064b4 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -513,7 +513,7 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc,
 	return num_prde;
 }
 
-static void sata_fsl_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct sata_fsl_port_priv *pp = ap->private_data;
@@ -559,6 +559,8 @@ static void sata_fsl_qc_prep(struct ata_queued_cmd *qc)
 
 	VPRINTK("SATA FSL : xx_qc_prep, di = 0x%x, ttl = %d, num_prde = %d\n",
 		desc_info, ttl_dwords, num_prde);
+
+	return AC_ERR_OK;
 }
 
 static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c
index 9b6d7930d1c7..6c7ddc037fce 100644
--- a/drivers/ata/sata_inic162x.c
+++ b/drivers/ata/sata_inic162x.c
@@ -472,7 +472,7 @@ static void inic_fill_sg(struct inic_prd *prd, struct ata_queued_cmd *qc)
 	prd[-1].flags |= PRD_END;
 }
 
-static void inic_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors inic_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct inic_port_priv *pp = qc->ap->private_data;
 	struct inic_pkt *pkt = pp->pkt;
@@ -532,6 +532,8 @@ static void inic_qc_prep(struct ata_queued_cmd *qc)
 		inic_fill_sg(prd, qc);
 
 	pp->cpb_tbl[0] = pp->pkt_dma;
+
+	return AC_ERR_OK;
 }
 
 static unsigned int inic_qc_issue(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 3b2246dded74..d85965bab2e2 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -605,8 +605,8 @@ static int mv5_scr_write(struct ata_link *link, unsigned int sc_reg_in, u32 val)
 static int mv_port_start(struct ata_port *ap);
 static void mv_port_stop(struct ata_port *ap);
 static int mv_qc_defer(struct ata_queued_cmd *qc);
-static void mv_qc_prep(struct ata_queued_cmd *qc);
-static void mv_qc_prep_iie(struct ata_queued_cmd *qc);
+static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc);
 static unsigned int mv_qc_issue(struct ata_queued_cmd *qc);
 static int mv_hardreset(struct ata_link *link, unsigned int *class,
 			unsigned long deadline);
@@ -2044,7 +2044,7 @@ static void mv_rw_multi_errata_sata24(struct ata_queued_cmd *qc)
  *      LOCKING:
  *      Inherited from caller.
  */
-static void mv_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct mv_port_priv *pp = ap->private_data;
@@ -2056,15 +2056,15 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
 	switch (tf->protocol) {
 	case ATA_PROT_DMA:
 		if (tf->command == ATA_CMD_DSM)
-			return;
+			return AC_ERR_OK;
 		/* fall-thru */
 	case ATA_PROT_NCQ:
 		break;	/* continue below */
 	case ATA_PROT_PIO:
 		mv_rw_multi_errata_sata24(qc);
-		return;
+		return AC_ERR_OK;
 	default:
-		return;
+		return AC_ERR_OK;
 	}
 
 	/* Fill in command request block
@@ -2111,12 +2111,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
 		 * non-NCQ mode are: [RW] STREAM DMA and W DMA FUA EXT, none
 		 * of which are defined/used by Linux.  If we get here, this
 		 * driver needs work.
-		 *
-		 * FIXME: modify libata to give qc_prep a return value and
-		 * return error here.
 		 */
-		BUG_ON(tf->command);
-		break;
+		ata_port_err(ap, "%s: unsupported command: %.2x\n", __func__,
+				tf->command);
+		return AC_ERR_INVALID;
 	}
 	mv_crqb_pack_cmd(cw++, tf->nsect, ATA_REG_NSECT, 0);
 	mv_crqb_pack_cmd(cw++, tf->hob_lbal, ATA_REG_LBAL, 0);
@@ -2129,8 +2127,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
 	mv_crqb_pack_cmd(cw++, tf->command, ATA_REG_CMD, 1);	/* last */
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 	mv_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 /**
@@ -2145,7 +2145,7 @@ static void mv_qc_prep(struct ata_queued_cmd *qc)
  *      LOCKING:
  *      Inherited from caller.
  */
-static void mv_qc_prep_iie(struct ata_queued_cmd *qc)
+static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct mv_port_priv *pp = ap->private_data;
@@ -2156,9 +2156,9 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc)
 
 	if ((tf->protocol != ATA_PROT_DMA) &&
 	    (tf->protocol != ATA_PROT_NCQ))
-		return;
+		return AC_ERR_OK;
 	if (tf->command == ATA_CMD_DSM)
-		return;  /* use bmdma for this */
+		return AC_ERR_OK;  /* use bmdma for this */
 
 	/* Fill in Gen IIE command request block */
 	if (!(tf->flags & ATA_TFLAG_WRITE))
@@ -2199,8 +2199,10 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc)
 		);
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 	mv_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 /**
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 8c683ddd0f58..efd5a0592855 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -313,7 +313,7 @@ static void nv_ck804_freeze(struct ata_port *ap);
 static void nv_ck804_thaw(struct ata_port *ap);
 static int nv_adma_slave_config(struct scsi_device *sdev);
 static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc);
-static void nv_adma_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc);
 static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance);
 static void nv_adma_irq_clear(struct ata_port *ap);
@@ -335,7 +335,7 @@ static void nv_mcp55_freeze(struct ata_port *ap);
 static void nv_swncq_error_handler(struct ata_port *ap);
 static int nv_swncq_slave_config(struct scsi_device *sdev);
 static int nv_swncq_port_start(struct ata_port *ap);
-static void nv_swncq_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc);
 static void nv_swncq_fill_sg(struct ata_queued_cmd *qc);
 static unsigned int nv_swncq_qc_issue(struct ata_queued_cmd *qc);
 static void nv_swncq_irq_clear(struct ata_port *ap, u16 fis);
@@ -1382,7 +1382,7 @@ static int nv_adma_use_reg_mode(struct ata_queued_cmd *qc)
 	return 1;
 }
 
-static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct nv_adma_port_priv *pp = qc->ap->private_data;
 	struct nv_adma_cpb *cpb = &pp->cpb[qc->tag];
@@ -1394,7 +1394,7 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
 			(qc->flags & ATA_QCFLAG_DMAMAP));
 		nv_adma_register_mode(qc->ap);
 		ata_bmdma_qc_prep(qc);
-		return;
+		return AC_ERR_OK;
 	}
 
 	cpb->resp_flags = NV_CPB_RESP_DONE;
@@ -1426,6 +1426,8 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
 	cpb->ctl_flags = ctl_flags;
 	wmb();
 	cpb->resp_flags = 0;
+
+	return AC_ERR_OK;
 }
 
 static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc)
@@ -1989,17 +1991,19 @@ static int nv_swncq_port_start(struct ata_port *ap)
 	return 0;
 }
 
-static void nv_swncq_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (qc->tf.protocol != ATA_PROT_NCQ) {
 		ata_bmdma_qc_prep(qc);
-		return;
+		return AC_ERR_OK;
 	}
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	nv_swncq_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static void nv_swncq_fill_sg(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index d032bf657f70..29d2bb465f60 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -155,7 +155,7 @@ static int pdc_sata_scr_write(struct ata_link *link, unsigned int sc_reg, u32 va
 static int pdc_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static int pdc_common_port_start(struct ata_port *ap);
 static int pdc_sata_port_start(struct ata_port *ap);
-static void pdc_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc);
 static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static int pdc_check_atapi_dma(struct ata_queued_cmd *qc);
@@ -649,7 +649,7 @@ static void pdc_fill_sg(struct ata_queued_cmd *qc)
 	prd[idx - 1].flags_len |= cpu_to_le32(ATA_PRD_EOT);
 }
 
-static void pdc_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct pdc_port_priv *pp = qc->ap->private_data;
 	unsigned int i;
@@ -681,6 +681,8 @@ static void pdc_qc_prep(struct ata_queued_cmd *qc)
 	default:
 		break;
 	}
+
+	return AC_ERR_OK;
 }
 
 static int pdc_is_sataii_tx4(unsigned long flags)
diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c
index 1fe941688e95..a66d10628c18 100644
--- a/drivers/ata/sata_qstor.c
+++ b/drivers/ata/sata_qstor.c
@@ -116,7 +116,7 @@ static int qs_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
 static int qs_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static int qs_port_start(struct ata_port *ap);
 static void qs_host_stop(struct ata_host *host);
-static void qs_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int qs_qc_issue(struct ata_queued_cmd *qc);
 static int qs_check_atapi_dma(struct ata_queued_cmd *qc);
 static void qs_freeze(struct ata_port *ap);
@@ -276,7 +276,7 @@ static unsigned int qs_fill_sg(struct ata_queued_cmd *qc)
 	return si;
 }
 
-static void qs_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct qs_port_priv *pp = qc->ap->private_data;
 	u8 dflags = QS_DF_PORD, *buf = pp->pkt;
@@ -288,7 +288,7 @@ static void qs_qc_prep(struct ata_queued_cmd *qc)
 
 	qs_enter_reg_mode(qc->ap);
 	if (qc->tf.protocol != ATA_PROT_DMA)
-		return;
+		return AC_ERR_OK;
 
 	nelem = qs_fill_sg(qc);
 
@@ -311,6 +311,8 @@ static void qs_qc_prep(struct ata_queued_cmd *qc)
 
 	/* frame information structure (FIS) */
 	ata_tf_to_fis(&qc->tf, 0, 1, &buf[32]);
+
+	return AC_ERR_OK;
 }
 
 static inline void qs_packet_start(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 3e82a4ac239e..a443c6943473 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -551,12 +551,14 @@ static void sata_rcar_bmdma_fill_sg(struct ata_queued_cmd *qc)
 	prd[si - 1].addr |= cpu_to_le32(SATA_RCAR_DTEND);
 }
 
-static void sata_rcar_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sata_rcar_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	sata_rcar_bmdma_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static void sata_rcar_bmdma_setup(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index ed76f070d21e..82adaf02887f 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -119,7 +119,7 @@ static void sil_dev_config(struct ata_device *dev);
 static int sil_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val);
 static int sil_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
 static int sil_set_mode(struct ata_link *link, struct ata_device **r_failed);
-static void sil_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc);
 static void sil_bmdma_setup(struct ata_queued_cmd *qc);
 static void sil_bmdma_start(struct ata_queued_cmd *qc);
 static void sil_bmdma_stop(struct ata_queued_cmd *qc);
@@ -333,12 +333,14 @@ static void sil_fill_sg(struct ata_queued_cmd *qc)
 		last_prd->flags_len |= cpu_to_le32(ATA_PRD_EOT);
 }
 
-static void sil_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	sil_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static unsigned char sil_get_device_cache_line(struct pci_dev *pdev)
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index 4b1995e2d044..ffa3bf724054 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -336,7 +336,7 @@ static void sil24_dev_config(struct ata_device *dev);
 static int sil24_scr_read(struct ata_link *link, unsigned sc_reg, u32 *val);
 static int sil24_scr_write(struct ata_link *link, unsigned sc_reg, u32 val);
 static int sil24_qc_defer(struct ata_queued_cmd *qc);
-static void sil24_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc);
 static bool sil24_qc_fill_rtf(struct ata_queued_cmd *qc);
 static void sil24_pmp_attach(struct ata_port *ap);
@@ -840,7 +840,7 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc)
 	return ata_std_qc_defer(qc);
 }
 
-static void sil24_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct sil24_port_priv *pp = ap->private_data;
@@ -884,6 +884,8 @@ static void sil24_qc_prep(struct ata_queued_cmd *qc)
 
 	if (qc->flags & ATA_QCFLAG_DMAMAP)
 		sil24_fill_sg(qc, sge);
+
+	return AC_ERR_OK;
 }
 
 static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc)
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index 405e606a234d..0d742457925e 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -218,7 +218,7 @@ static void pdc_error_handler(struct ata_port *ap);
 static void pdc_freeze(struct ata_port *ap);
 static void pdc_thaw(struct ata_port *ap);
 static int pdc_port_start(struct ata_port *ap);
-static void pdc20621_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc);
 static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static unsigned int pdc20621_dimm_init(struct ata_host *host);
@@ -546,7 +546,7 @@ static void pdc20621_nodata_prep(struct ata_queued_cmd *qc)
 	VPRINTK("ata pkt buf ofs %u, mmio copied\n", i);
 }
 
-static void pdc20621_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc)
 {
 	switch (qc->tf.protocol) {
 	case ATA_PROT_DMA:
@@ -558,6 +558,8 @@ static void pdc20621_qc_prep(struct ata_queued_cmd *qc)
 	default:
 		break;
 	}
+
+	return AC_ERR_OK;
 }
 
 static void __pdc20621_push_hdma(struct ata_queued_cmd *qc,
diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
index afebeb1c3e1e..723bad1201cc 100644
--- a/drivers/atm/atmtcp.c
+++ b/drivers/atm/atmtcp.c
@@ -432,9 +432,15 @@ static int atmtcp_remove_persistent(int itf)
 		return -EMEDIUMTYPE;
 	}
 	dev_data = PRIV(dev);
-	if (!dev_data->persist) return 0;
+	if (!dev_data->persist) {
+		atm_dev_put(dev);
+		return 0;
+	}
 	dev_data->persist = 0;
-	if (PRIV(dev)->vcc) return 0;
+	if (PRIV(dev)->vcc) {
+		atm_dev_put(dev);
+		return 0;
+	}
 	kfree(dev_data);
 	atm_dev_put(dev);
 	atm_dev_deregister(dev);
diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index a106d15f6def..ba549d945479 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -2243,7 +2243,7 @@ static int eni_init_one(struct pci_dev *pci_dev,
 
 	rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32));
 	if (rc < 0)
-		goto out;
+		goto err_disable;
 
 	rc = -ENOMEM;
 	eni_dev = kmalloc(sizeof(struct eni_dev), GFP_KERNEL);
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index 0e449ee11ac7..e7cffd0cc361 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -1013,6 +1013,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 				error = make_rate (pcr, r, &tmc0, NULL);
 				if (error) {
 					kfree(tc);
+					kfree(vcc);
 					return error;
 				}
 			}
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 93c2fc58013e..3c14f0c4ef87 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -3074,9 +3074,9 @@ static inline bool fwnode_is_primary(struct fwnode_handle *fwnode)
  */
 void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
 {
-	if (fwnode) {
-		struct fwnode_handle *fn = dev->fwnode;
+	struct fwnode_handle *fn = dev->fwnode;
 
+	if (fwnode) {
 		if (fwnode_is_primary(fn))
 			fn = fn->secondary;
 
@@ -3086,8 +3086,12 @@ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
 		}
 		dev->fwnode = fwnode;
 	} else {
-		dev->fwnode = fwnode_is_primary(dev->fwnode) ?
-			dev->fwnode->secondary : NULL;
+		if (fwnode_is_primary(fn)) {
+			dev->fwnode = fn->secondary;
+			fn->secondary = NULL;
+		} else {
+			dev->fwnode = NULL;
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(set_primary_fwnode);
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 0272f66db5ac..c800de86200d 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -552,6 +552,12 @@ ssize_t __weak cpu_show_itlb_multihit(struct device *dev,
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_srbds(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
@@ -560,6 +566,7 @@ static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
 static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL);
 static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL);
 static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL);
+static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -570,6 +577,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_mds.attr,
 	&dev_attr_tsx_async_abort.attr,
 	&dev_attr_itlb_multihit.attr,
+	&dev_attr_srbds.attr,
 	NULL
 };
 
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index aa1a2d32360f..392e2b462560 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -377,7 +377,8 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 		 drv->bus->name, __func__, drv->name, dev_name(dev));
 	if (!list_empty(&dev->devres_head)) {
 		dev_crit(dev, "Resources present before probing\n");
-		return -EBUSY;
+		ret = -EBUSY;
+		goto done;
 	}
 
 re_probe:
@@ -486,7 +487,7 @@ pinctrl_bind_failed:
 	ret = 0;
 done:
 	atomic_dec(&probe_count);
-	wake_up(&probe_waitqueue);
+	wake_up_all(&probe_waitqueue);
 	return ret;
 }
 
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index bcb6519fe211..0ee3cab88f70 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -702,6 +702,8 @@ int __init_or_module __platform_driver_probe(struct platform_driver *drv,
 	/* temporary section violation during probe() */
 	drv->probe = probe;
 	retval = code = __platform_driver_register(drv, module);
+	if (retval)
+		return retval;
 
 	/*
 	 * Fixup that section violation, being paranoid about code scanning
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 0e7fa1f27ad4..4fd49d55bc3e 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1500,13 +1500,17 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	}
 
 	/*
-	 * If a device configured to wake up the system from sleep states
-	 * has been suspended at run time and there's a resume request pending
-	 * for it, this is equivalent to the device signaling wakeup, so the
-	 * system suspend operation should be aborted.
+	 * Wait for possible runtime PM transitions of the device in progress
+	 * to complete and if there's a runtime resume request pending for it,
+	 * resume it before proceeding with invoking the system-wide suspend
+	 * callbacks for it.
+	 *
+	 * If the system-wide suspend callbacks below change the configuration
+	 * of the device, they must disable runtime PM for it or otherwise
+	 * ensure that its runtime-resume callbacks will not be confused by that
+	 * change in case they are invoked going forward.
 	 */
-	if (pm_runtime_barrier(dev) && device_may_wakeup(dev))
-		pm_wakeup_event(dev, 0);
+	pm_runtime_barrier(dev);
 
 	if (pm_wakeup_pending()) {
 		dev->power.direct_complete = false;
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 36ce3511c733..7d0c83b47259 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -204,6 +204,9 @@ static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
+	if (count > (PAGE_SIZE << (MAX_ORDER - 1)))
+		count = PAGE_SIZE << (MAX_ORDER - 1);
+
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
@@ -352,6 +355,9 @@ static ssize_t regmap_reg_ranges_read_file(struct file *file,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
+	if (count > (PAGE_SIZE << (MAX_ORDER - 1)))
+		count = PAGE_SIZE << (MAX_ORDER - 1);
+
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 013d0a2b3ba0..4e0cc40ad9ce 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1242,7 +1242,7 @@ static int dev_get_regmap_match(struct device *dev, void *res, void *data)
 
 	/* If the user didn't specify a name match any */
 	if (data)
-		return (*r)->name == data;
+		return !strcmp((*r)->name, data);
 	else
 		return 1;
 }
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 0129b1921cb3..78287f029cf0 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -28,7 +28,6 @@
 
 #include <linux/uaccess.h>
 
-#define SECTOR_SHIFT		9
 #define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 453e3728e657..489e091e9e2e 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -720,6 +720,24 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	return error;
 }
 
+/*
+ * for AUFS
+ * no get/put for file.
+ */
+struct file *loop_backing_file(struct super_block *sb)
+{
+	struct file *ret;
+	struct loop_device *l;
+
+	ret = NULL;
+	if (MAJOR(sb->s_dev) == LOOP_MAJOR) {
+		l = sb->s_bdev->bd_disk->private_data;
+		ret = l->lo_backing_file;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(loop_backing_file);
+
 /* loop sysfs attributes */
 
 static ssize_t loop_attr_show(struct device *dev, char *page,
@@ -1110,7 +1128,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if (lo->lo_offset != info->lo_offset ||
 	    lo->lo_sizelimit != info->lo_sizelimit) {
 		sync_blockdev(lo->lo_device);
-		kill_bdev(lo->lo_device);
+		invalidate_bdev(lo->lo_device);
 	}
 
 	/* I/O need to be drained during transfer transition */
@@ -1380,12 +1398,12 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 
 	if (lo->lo_queue->limits.logical_block_size != arg) {
 		sync_blockdev(lo->lo_device);
-		kill_bdev(lo->lo_device);
+		invalidate_bdev(lo->lo_device);
 	}
 
 	blk_mq_freeze_queue(lo->lo_queue);
 
-	/* kill_bdev should have truncated all the pages */
+	/* invalidate_bdev should have truncated all the pages */
 	if (lo->lo_queue->limits.logical_block_size != arg &&
 			lo->lo_device->bd_inode->i_mapping->nrpages) {
 		err = -EAGAIN;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 8f56e6b2f114..f22fad977c91 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -960,25 +960,26 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	     test_bit(NBD_BOUND, &config->runtime_flags))) {
 		dev_err(disk_to_dev(nbd->disk),
 			"Device being setup by another task");
-		sockfd_put(sock);
-		return -EBUSY;
+		err = -EBUSY;
+		goto put_socket;
+	}
+
+	nsock = kzalloc(sizeof(*nsock), GFP_KERNEL);
+	if (!nsock) {
+		err = -ENOMEM;
+		goto put_socket;
 	}
 
 	socks = krealloc(config->socks, (config->num_connections + 1) *
 			 sizeof(struct nbd_sock *), GFP_KERNEL);
 	if (!socks) {
-		sockfd_put(sock);
-		return -ENOMEM;
+		kfree(nsock);
+		err = -ENOMEM;
+		goto put_socket;
 	}
 
 	config->socks = socks;
 
-	nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL);
-	if (!nsock) {
-		sockfd_put(sock);
-		return -ENOMEM;
-	}
-
 	nsock->fallback_index = -1;
 	nsock->dead = false;
 	mutex_init(&nsock->tx_lock);
@@ -990,6 +991,10 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	atomic_inc(&config->live_connections);
 
 	return 0;
+
+put_socket:
+	sockfd_put(sock);
+	return err;
 }
 
 static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index b12e373aa956..b499e72b2847 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -16,10 +16,8 @@
 #include <linux/configfs.h>
 #include <linux/badblocks.h>
 
-#define SECTOR_SHIFT		9
 #define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)
-#define SECTOR_SIZE		(1 << SECTOR_SHIFT)
 #define SECTOR_MASK		(PAGE_SECTORS - 1)
 
 #define FREE_BATCH		16
@@ -1135,7 +1133,7 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 		len = bvec.bv_len;
 		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
 				     op_is_write(req_op(rq)), sector,
-				     req_op(rq) & REQ_FUA);
+				     rq->cmd_flags & REQ_FUA);
 		if (err) {
 			spin_unlock_irq(&nullb->lock);
 			return err;
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 075662f2cf46..d20f66d57804 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -468,7 +468,6 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	blk_queue_bounce_limit(queue, BLK_BOUNCE_HIGH);
 
 	blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9);
-	blk_queue_segment_boundary(queue, -1UL);
 	blk_queue_dma_alignment(queue, dev->blk_size-1);
 	blk_queue_logical_block_size(queue, dev->blk_size);
 
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 557cf52f674b..a4725ac1d409 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -51,15 +51,6 @@
 #define RBD_DEBUG	/* Activate rbd_assert() calls */
 
 /*
- * The basic unit of block I/O is a sector.  It is interpreted in a
- * number of contexts in Linux (blk, bio, genhd), but the default is
- * universally 512 bytes.  These symbols are just slightly more
- * meaningful than the bare numbers they represent.
- */
-#define	SECTOR_SHIFT	9
-#define	SECTOR_SIZE	(1ULL << SECTOR_SHIFT)
-
-/*
  * Increment the given counter and return its updated value.
  * If the counter is already 0 it will not be incremented.
  * If the counter is already at its maximum value returns
@@ -4543,6 +4534,9 @@ static ssize_t rbd_config_info_show(struct device *dev,
 {
 	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	return sprintf(buf, "%s\n", rbd_dev->config_info);
 }
 
@@ -4644,6 +4638,9 @@ static ssize_t rbd_image_refresh(struct device *dev,
 	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	ret = rbd_dev_refresh(rbd_dev);
 	if (ret)
 		return ret;
@@ -6168,6 +6165,9 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	bool read_only;
 	int rc;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (!try_module_get(THIS_MODULE))
 		return -ENODEV;
 
@@ -6320,6 +6320,9 @@ static ssize_t do_rbd_remove(struct bus_type *bus,
 	bool force = false;
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	dev_id = -1;
 	opt_buf[0] = '\0';
 	sscanf(buf, "%d %5s", &dev_id, opt_buf);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 0e18eed62c57..2f15e38fb3f8 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -879,6 +879,7 @@ out_put_disk:
 	put_disk(vblk->disk);
 out_free_vq:
 	vdev->config->del_vqs(vdev);
+	kfree(vblk->vqs);
 out_free_vblk:
 	kfree(vblk);
 out_free_index:
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 1b4e195c0d3c..0d906ca8d4f5 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1648,7 +1648,8 @@ static ssize_t hot_add_show(struct class *class,
 		return ret;
 	return scnprintf(buf, PAGE_SIZE, "%d\n", ret);
 }
-static CLASS_ATTR_RO(hot_add);
+static struct class_attribute class_attr_hot_add =
+	__ATTR(hot_add, 0400, hot_add_show, NULL);
 
 static ssize_t hot_remove_store(struct class *class,
 			struct class_attribute *attr,
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 31762db861e3..1e9bf65c0bfb 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -37,7 +37,6 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
 
 /*-- End of configurable params */
 
-#define SECTOR_SHIFT		9
 #define SECTORS_PER_PAGE_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define SECTORS_PER_PAGE	(1 << SECTORS_PER_PAGE_SHIFT)
 #define ZRAM_LOGICAL_BLOCK_SHIFT 12
diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c
index 69c00a3db538..72cf2d97b682 100644
--- a/drivers/bluetooth/hci_serdev.c
+++ b/drivers/bluetooth/hci_serdev.c
@@ -361,7 +361,8 @@ void hci_uart_unregister_device(struct hci_uart *hu)
 	struct hci_dev *hdev = hu->hdev;
 
 	clear_bit(HCI_UART_PROTO_READY, &hu->flags);
-	hci_unregister_dev(hdev);
+	if (test_bit(HCI_UART_REGISTERED, &hu->flags))
+		hci_unregister_dev(hdev);
 	hci_free_dev(hdev);
 
 	cancel_work_sync(&hu->write_work);
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index dde7caac7f9f..34cc853772bc 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -304,8 +304,10 @@ static int intel_gtt_setup_scratch_page(void)
 	if (intel_private.needs_dmar) {
 		dma_addr = pci_map_page(intel_private.pcidev, page, 0,
 				    PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-		if (pci_dma_mapping_error(intel_private.pcidev, dma_addr))
+		if (pci_dma_mapping_error(intel_private.pcidev, dma_addr)) {
+			__free_page(page);
 			return -EINVAL;
+		}
 
 		intel_private.scratch_page_dma = dma_addr;
 	} else
@@ -846,6 +848,7 @@ void intel_gtt_insert_page(dma_addr_t addr,
 			   unsigned int flags)
 {
 	intel_private.driver->write_entry(addr, pg, flags);
+	readl(intel_private.gtt + pg);
 	if (intel_private.driver->chipset_flush)
 		intel_private.driver->chipset_flush();
 }
@@ -871,7 +874,7 @@ void intel_gtt_insert_sg_entries(struct sg_table *st,
 			j++;
 		}
 	}
-	wmb();
+	readl(intel_private.gtt + j - 1);
 	if (intel_private.driver->chipset_flush)
 		intel_private.driver->chipset_flush();
 }
@@ -1105,6 +1108,7 @@ static void i9xx_cleanup(void)
 
 static void i9xx_chipset_flush(void)
 {
+	wmb();
 	if (intel_private.i9xx_flush_page)
 		writel(1, intel_private.i9xx_flush_page);
 }
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 868d2620b7ac..b202f66fc383 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1246,6 +1246,7 @@ void add_interrupt_randomness(int irq, int irq_flags)
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
+	this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]);
 
 	if (unlikely(crng_init == 0)) {
 		if ((fast_pool->count >= 64) &&
diff --git a/drivers/char/tlclk.c b/drivers/char/tlclk.c
index 6210bff46341..52fadc46e7a9 100644
--- a/drivers/char/tlclk.c
+++ b/drivers/char/tlclk.c
@@ -777,17 +777,21 @@ static int __init tlclk_init(void)
 {
 	int ret;
 
+	telclk_interrupt = (inb(TLCLK_REG7) & 0x0f);
+
+	alarm_events = kzalloc( sizeof(struct tlclk_alarms), GFP_KERNEL);
+	if (!alarm_events) {
+		ret = -ENOMEM;
+		goto out1;
+	}
+
 	ret = register_chrdev(tlclk_major, "telco_clock", &tlclk_fops);
 	if (ret < 0) {
 		printk(KERN_ERR "tlclk: can't get major %d.\n", tlclk_major);
+		kfree(alarm_events);
 		return ret;
 	}
 	tlclk_major = ret;
-	alarm_events = kzalloc( sizeof(struct tlclk_alarms), GFP_KERNEL);
-	if (!alarm_events) {
-		ret = -ENOMEM;
-		goto out1;
-	}
 
 	/* Read telecom clock IRQ number (Set by BIOS) */
 	if (!request_region(TLCLK_BASE, 8, "telco_clock")) {
@@ -796,7 +800,6 @@ static int __init tlclk_init(void)
 		ret = -EBUSY;
 		goto out2;
 	}
-	telclk_interrupt = (inb(TLCLK_REG7) & 0x0f);
 
 	if (0x0F == telclk_interrupt ) { /* not MCPBL0010 ? */
 		printk(KERN_ERR "telclk_interrupt = 0x%x non-mcpbl0010 hw.\n",
@@ -837,8 +840,8 @@ out3:
 	release_region(TLCLK_BASE, 8);
 out2:
 	kfree(alarm_events);
-out1:
 	unregister_chrdev(tlclk_major, "telco_clock");
+out1:
 	return ret;
 }
 
diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index dcf5bb153495..11ec5c2715a9 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -247,13 +247,8 @@ struct tpm_chip *tpm_chip_alloc(struct device *pdev,
 	chip->cdev.owner = THIS_MODULE;
 	chip->cdevs.owner = THIS_MODULE;
 
-	chip->work_space.context_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!chip->work_space.context_buf) {
-		rc = -ENOMEM;
-		goto out;
-	}
-	chip->work_space.session_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!chip->work_space.session_buf) {
+	rc = tpm2_init_space(&chip->work_space, TPM2_SPACE_BUFFER_SIZE);
+	if (rc) {
 		rc = -ENOMEM;
 		goto out;
 	}
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index d53d12f3df6d..019fe80fedd8 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -174,6 +174,7 @@ struct tpm_space {
 	u8 *context_buf;
 	u32 session_tbl[3];
 	u8 *session_buf;
+	u32 buf_size;
 };
 
 enum tpm_chip_flags {
@@ -261,6 +262,9 @@ struct tpm_output_header {
 
 #define TPM_TAG_RQU_COMMAND 193
 
+/* TPM2 specific constants. */
+#define TPM2_SPACE_BUFFER_SIZE		16384 /* 16 kB */
+
 struct	stclear_flags_t {
 	__be16	tag;
 	u8	deactivated;
@@ -583,7 +587,7 @@ void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type);
 unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal);
 int tpm2_probe(struct tpm_chip *chip);
 int tpm2_find_cc(struct tpm_chip *chip, u32 cc);
-int tpm2_init_space(struct tpm_space *space);
+int tpm2_init_space(struct tpm_space *space, unsigned int buf_size);
 void tpm2_del_space(struct tpm_chip *chip, struct tpm_space *space);
 int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u32 cc,
 		       u8 *cmd);
diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c
index dabb2ae4e779..115f0fb32179 100644
--- a/drivers/char/tpm/tpm2-space.c
+++ b/drivers/char/tpm/tpm2-space.c
@@ -44,18 +44,21 @@ static void tpm2_flush_sessions(struct tpm_chip *chip, struct tpm_space *space)
 	}
 }
 
-int tpm2_init_space(struct tpm_space *space)
+int tpm2_init_space(struct tpm_space *space, unsigned int buf_size)
 {
-	space->context_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	space->context_buf = kzalloc(buf_size, GFP_KERNEL);
 	if (!space->context_buf)
 		return -ENOMEM;
 
-	space->session_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	space->session_buf = kzalloc(buf_size, GFP_KERNEL);
 	if (space->session_buf == NULL) {
 		kfree(space->context_buf);
+		/* Prevent caller getting a dangling pointer. */
+		space->context_buf = NULL;
 		return -ENOMEM;
 	}
 
+	space->buf_size = buf_size;
 	return 0;
 }
 
@@ -278,8 +281,10 @@ int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u32 cc,
 	       sizeof(space->context_tbl));
 	memcpy(&chip->work_space.session_tbl, &space->session_tbl,
 	       sizeof(space->session_tbl));
-	memcpy(chip->work_space.context_buf, space->context_buf, PAGE_SIZE);
-	memcpy(chip->work_space.session_buf, space->session_buf, PAGE_SIZE);
+	memcpy(chip->work_space.context_buf, space->context_buf,
+	       space->buf_size);
+	memcpy(chip->work_space.session_buf, space->session_buf,
+	       space->buf_size);
 
 	rc = tpm2_load_space(chip);
 	if (rc) {
@@ -459,7 +464,7 @@ static int tpm2_save_space(struct tpm_chip *chip)
 			continue;
 
 		rc = tpm2_save_context(chip, space->context_tbl[i],
-				       space->context_buf, PAGE_SIZE,
+				       space->context_buf, space->buf_size,
 				       &offset);
 		if (rc == -ENOENT) {
 			space->context_tbl[i] = 0;
@@ -478,9 +483,8 @@ static int tpm2_save_space(struct tpm_chip *chip)
 			continue;
 
 		rc = tpm2_save_context(chip, space->session_tbl[i],
-				       space->session_buf, PAGE_SIZE,
+				       space->session_buf, space->buf_size,
 				       &offset);
-
 		if (rc == -ENOENT) {
 			/* handle error saving session, just forget it */
 			space->session_tbl[i] = 0;
@@ -526,8 +530,10 @@ int tpm2_commit_space(struct tpm_chip *chip, struct tpm_space *space,
 	       sizeof(space->context_tbl));
 	memcpy(&space->session_tbl, &chip->work_space.session_tbl,
 	       sizeof(space->session_tbl));
-	memcpy(space->context_buf, chip->work_space.context_buf, PAGE_SIZE);
-	memcpy(space->session_buf, chip->work_space.session_buf, PAGE_SIZE);
+	memcpy(space->context_buf, chip->work_space.context_buf,
+	       space->buf_size);
+	memcpy(space->session_buf, chip->work_space.session_buf,
+	       space->buf_size);
 
 	return 0;
 }
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index 569e93e1f06c..3ba67bc6baba 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -588,6 +588,7 @@ static irqreturn_t ibmvtpm_interrupt(int irq, void *vtpm_instance)
 	 */
 	while ((crq = ibmvtpm_crq_get_next(ibmvtpm)) != NULL) {
 		ibmvtpm_crq_process(crq, ibmvtpm);
+		wake_up_interruptible(&ibmvtpm->crq_queue.wq);
 		crq->valid = 0;
 		smp_wmb();
 	}
@@ -635,6 +636,7 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev,
 	}
 
 	crq_q->num_entry = CRQ_RES_BUF_SIZE / sizeof(*crq_q->crq_addr);
+	init_waitqueue_head(&crq_q->wq);
 	ibmvtpm->crq_dma_handle = dma_map_single(dev, crq_q->crq_addr,
 						 CRQ_RES_BUF_SIZE,
 						 DMA_BIDIRECTIONAL);
@@ -687,6 +689,13 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev,
 	if (rc)
 		goto init_irq_cleanup;
 
+	if (!wait_event_timeout(ibmvtpm->crq_queue.wq,
+				ibmvtpm->rtce_buf != NULL,
+				HZ)) {
+		dev_err(dev, "CRQ response timed out\n");
+		goto init_irq_cleanup;
+	}
+
 	return tpm_chip_register(chip);
 init_irq_cleanup:
 	do {
diff --git a/drivers/char/tpm/tpm_ibmvtpm.h b/drivers/char/tpm/tpm_ibmvtpm.h
index 91dfe766d080..4f6a124601db 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.h
+++ b/drivers/char/tpm/tpm_ibmvtpm.h
@@ -31,6 +31,7 @@ struct ibmvtpm_crq_queue {
 	struct ibmvtpm_crq *crq_addr;
 	u32 index;
 	u32 num_entry;
+	wait_queue_head_t wq;
 };
 
 struct ibmvtpm_dev {
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 9b1116501f20..c028ffd95332 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -897,7 +897,7 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
 
 	return 0;
 out_err:
-	if ((chip->ops != NULL) && (chip->ops->clk_enable != NULL))
+	if (chip->ops->clk_enable != NULL)
 		chip->ops->clk_enable(chip, false);
 
 	tpm_tis_remove(chip);
diff --git a/drivers/char/tpm/tpmrm-dev.c b/drivers/char/tpm/tpmrm-dev.c
index 1a0e97a5da5a..162fb16243d0 100644
--- a/drivers/char/tpm/tpmrm-dev.c
+++ b/drivers/char/tpm/tpmrm-dev.c
@@ -22,7 +22,7 @@ static int tpmrm_open(struct inode *inode, struct file *file)
 	if (priv == NULL)
 		return -ENOMEM;
 
-	rc = tpm2_init_space(&priv->space);
+	rc = tpm2_init_space(&priv->space, TPM2_SPACE_BUFFER_SIZE);
 	if (rc) {
 		kfree(priv);
 		return -ENOMEM;
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 5200772ab0bd..6a57237e46db 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -2158,6 +2158,7 @@ static struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_CONSOLE, VIRTIO_DEV_ANY_ID },
 	{ 0 },
 };
+MODULE_DEVICE_TABLE(virtio, id_table);
 
 static unsigned int features[] = {
 	VIRTIO_CONSOLE_F_SIZE,
@@ -2170,6 +2171,7 @@ static struct virtio_device_id rproc_serial_id_table[] = {
 #endif
 	{ 0 },
 };
+MODULE_DEVICE_TABLE(virtio, rproc_serial_id_table);
 
 static unsigned int rproc_serial_features[] = {
 };
@@ -2322,6 +2324,5 @@ static void __exit fini(void)
 module_init(init);
 module_exit(fini);
 
-MODULE_DEVICE_TABLE(virtio, id_table);
 MODULE_DESCRIPTION("Virtio console driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c
index 5f8082d89131..6db4204e5d5d 100644
--- a/drivers/clk/bcm/clk-bcm2835.c
+++ b/drivers/clk/bcm/clk-bcm2835.c
@@ -1483,13 +1483,13 @@ static struct clk_hw *bcm2835_register_clock(struct bcm2835_cprman *cprman,
 	return &clock->hw;
 }
 
-static struct clk *bcm2835_register_gate(struct bcm2835_cprman *cprman,
+static struct clk_hw *bcm2835_register_gate(struct bcm2835_cprman *cprman,
 					 const struct bcm2835_gate_data *data)
 {
-	return clk_register_gate(cprman->dev, data->name, data->parent,
-				 CLK_IGNORE_UNUSED | CLK_SET_RATE_GATE,
-				 cprman->regs + data->ctl_reg,
-				 CM_GATE_BIT, 0, &cprman->regs_lock);
+	return clk_hw_register_gate(cprman->dev, data->name, data->parent,
+				    CLK_IGNORE_UNUSED | CLK_SET_RATE_GATE,
+				    cprman->regs + data->ctl_reg,
+				    CM_GATE_BIT, 0, &cprman->regs_lock);
 }
 
 typedef struct clk_hw *(*bcm2835_clk_register)(struct bcm2835_cprman *cprman,
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 44b6f23cc851..4289c519af1b 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -39,6 +39,17 @@ static HLIST_HEAD(clk_root_list);
 static HLIST_HEAD(clk_orphan_list);
 static LIST_HEAD(clk_notifier_list);
 
+static struct hlist_head *all_lists[] = {
+	&clk_root_list,
+	&clk_orphan_list,
+	NULL,
+};
+
+static struct hlist_head *orphan_list[] = {
+	&clk_orphan_list,
+	NULL,
+};
+
 /***    private data structures    ***/
 
 struct clk_core {
@@ -1993,17 +2004,6 @@ static int inited = 0;
 static DEFINE_MUTEX(clk_debug_lock);
 static HLIST_HEAD(clk_debug_list);
 
-static struct hlist_head *all_lists[] = {
-	&clk_root_list,
-	&clk_orphan_list,
-	NULL,
-};
-
-static struct hlist_head *orphan_list[] = {
-	&clk_orphan_list,
-	NULL,
-};
-
 static void clk_summary_show_one(struct seq_file *s, struct clk_core *c,
 				 int level)
 {
@@ -2735,6 +2735,34 @@ static const struct clk_ops clk_nodrv_ops = {
 	.set_parent	= clk_nodrv_set_parent,
 };
 
+static void clk_core_evict_parent_cache_subtree(struct clk_core *root,
+						struct clk_core *target)
+{
+	int i;
+	struct clk_core *child;
+
+	for (i = 0; i < root->num_parents; i++)
+		if (root->parents[i] == target)
+			root->parents[i] = NULL;
+
+	hlist_for_each_entry(child, &root->children, child_node)
+		clk_core_evict_parent_cache_subtree(child, target);
+}
+
+/* Remove this clk from all parent caches */
+static void clk_core_evict_parent_cache(struct clk_core *core)
+{
+	struct hlist_head **lists;
+	struct clk_core *root;
+
+	lockdep_assert_held(&prepare_lock);
+
+	for (lists = all_lists; *lists; lists++)
+		hlist_for_each_entry(root, *lists, child_node)
+			clk_core_evict_parent_cache_subtree(root, core);
+
+}
+
 /**
  * clk_unregister - unregister a currently registered clock
  * @clk: clock to unregister
@@ -2773,6 +2801,8 @@ void clk_unregister(struct clk *clk)
 			clk_core_set_parent(child, NULL);
 	}
 
+	clk_core_evict_parent_cache(clk->core);
+
 	hlist_del_init(&clk->core->child_node);
 
 	if (clk->core->prepare_count)
diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c
index 2057809219f4..7426d910e079 100644
--- a/drivers/clk/qcom/gcc-msm8916.c
+++ b/drivers/clk/qcom/gcc-msm8916.c
@@ -270,7 +270,7 @@ static struct clk_pll gpll0 = {
 	.l_reg = 0x21004,
 	.m_reg = 0x21008,
 	.n_reg = 0x2100c,
-	.config_reg = 0x21014,
+	.config_reg = 0x21010,
 	.mode_reg = 0x21000,
 	.status_reg = 0x2101c,
 	.status_bit = 17,
@@ -297,7 +297,7 @@ static struct clk_pll gpll1 = {
 	.l_reg = 0x20004,
 	.m_reg = 0x20008,
 	.n_reg = 0x2000c,
-	.config_reg = 0x20014,
+	.config_reg = 0x20010,
 	.mode_reg = 0x20000,
 	.status_reg = 0x2001c,
 	.status_bit = 17,
@@ -324,7 +324,7 @@ static struct clk_pll gpll2 = {
 	.l_reg = 0x4a004,
 	.m_reg = 0x4a008,
 	.n_reg = 0x4a00c,
-	.config_reg = 0x4a014,
+	.config_reg = 0x4a010,
 	.mode_reg = 0x4a000,
 	.status_reg = 0x4a01c,
 	.status_bit = 17,
@@ -351,7 +351,7 @@ static struct clk_pll bimc_pll = {
 	.l_reg = 0x23004,
 	.m_reg = 0x23008,
 	.n_reg = 0x2300c,
-	.config_reg = 0x23014,
+	.config_reg = 0x23010,
 	.mode_reg = 0x23000,
 	.status_reg = 0x2301c,
 	.status_bit = 17,
diff --git a/drivers/clk/rockchip/clk-rk3228.c b/drivers/clk/rockchip/clk-rk3228.c
index 04f4f3739e3b..8d11d76e1db7 100644
--- a/drivers/clk/rockchip/clk-rk3228.c
+++ b/drivers/clk/rockchip/clk-rk3228.c
@@ -144,7 +144,7 @@ PNAME(mux_usb480m_p)		= { "usb480m_phy", "xin24m" };
 PNAME(mux_hdmiphy_p)		= { "hdmiphy_phy", "xin24m" };
 PNAME(mux_aclk_cpu_src_p)	= { "cpll_aclk_cpu", "gpll_aclk_cpu", "hdmiphy_aclk_cpu" };
 
-PNAME(mux_pll_src_4plls_p)	= { "cpll", "gpll", "hdmiphy" "usb480m" };
+PNAME(mux_pll_src_4plls_p)	= { "cpll", "gpll", "hdmiphy", "usb480m" };
 PNAME(mux_pll_src_3plls_p)	= { "cpll", "gpll", "hdmiphy" };
 PNAME(mux_pll_src_2plls_p)	= { "cpll", "gpll" };
 PNAME(mux_sclk_hdmi_cec_p)	= { "cpll", "gpll", "xin24m" };
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index 3d3026221927..2d269cc6a668 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -1075,7 +1075,7 @@ static const struct samsung_gate_clock exynos4210_gate_clks[] __initconst = {
 	GATE(CLK_PCIE, "pcie", "aclk133", GATE_IP_FSYS, 14, 0, 0),
 	GATE(CLK_SMMU_PCIE, "smmu_pcie", "aclk133", GATE_IP_FSYS, 18, 0, 0),
 	GATE(CLK_MODEMIF, "modemif", "aclk100", GATE_IP_PERIL, 28, 0, 0),
-	GATE(CLK_CHIPID, "chipid", "aclk100", E4210_GATE_IP_PERIR, 0, 0, 0),
+	GATE(CLK_CHIPID, "chipid", "aclk100", E4210_GATE_IP_PERIR, 0, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SYSREG, "sysreg", "aclk100", E4210_GATE_IP_PERIR, 0,
 			CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_HDMI_CEC, "hdmi_cec", "aclk100", E4210_GATE_IP_PERIR, 11, 0,
@@ -1116,7 +1116,7 @@ static const struct samsung_gate_clock exynos4x12_gate_clks[] __initconst = {
 		0),
 	GATE(CLK_TSADC, "tsadc", "aclk133", E4X12_GATE_BUS_FSYS1, 16, 0, 0),
 	GATE(CLK_MIPI_HSI, "mipi_hsi", "aclk133", GATE_IP_FSYS, 10, 0, 0),
-	GATE(CLK_CHIPID, "chipid", "aclk100", E4X12_GATE_IP_PERIR, 0, 0, 0),
+	GATE(CLK_CHIPID, "chipid", "aclk100", E4X12_GATE_IP_PERIR, 0, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SYSREG, "sysreg", "aclk100", E4X12_GATE_IP_PERIR, 1,
 			CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_HDMI_CEC, "hdmi_cec", "aclk100", E4X12_GATE_IP_PERIR, 11, 0,
diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c
index 1d2265f9ee97..1c327d5de98c 100644
--- a/drivers/clk/samsung/clk-exynos5433.c
+++ b/drivers/clk/samsung/clk-exynos5433.c
@@ -1674,7 +1674,8 @@ static const struct samsung_gate_clock peric_gate_clks[] __initconst = {
 	GATE(CLK_SCLK_PCM1, "sclk_pcm1", "sclk_pcm1_peric",
 			ENABLE_SCLK_PERIC, 7, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_I2S1, "sclk_i2s1", "sclk_i2s1_peric",
-			ENABLE_SCLK_PERIC, 6, CLK_SET_RATE_PARENT, 0),
+			ENABLE_SCLK_PERIC, 6,
+			CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_SPI2, "sclk_spi2", "sclk_spi2_peric", ENABLE_SCLK_PERIC,
 			5, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_SPI1, "sclk_spi1", "sclk_spi1_peric", ENABLE_SCLK_PERIC,
diff --git a/drivers/clk/sirf/clk-atlas6.c b/drivers/clk/sirf/clk-atlas6.c
index 665fa681b2e1..1e6bdf22c3b6 100644
--- a/drivers/clk/sirf/clk-atlas6.c
+++ b/drivers/clk/sirf/clk-atlas6.c
@@ -136,7 +136,7 @@ static void __init atlas6_clk_init(struct device_node *np)
 
 	for (i = pll1; i < maxclk; i++) {
 		atlas6_clks[i] = clk_register(NULL, atlas6_clk_hw_array[i]);
-		BUG_ON(!atlas6_clks[i]);
+		BUG_ON(IS_ERR(atlas6_clks[i]));
 	}
 	clk_register_clkdev(atlas6_clks[cpu], NULL, "cpu");
 	clk_register_clkdev(atlas6_clks[io],  NULL, "io");
diff --git a/drivers/clk/st/clk-flexgen.c b/drivers/clk/st/clk-flexgen.c
index 918ba3164da9..cd856210db58 100644
--- a/drivers/clk/st/clk-flexgen.c
+++ b/drivers/clk/st/clk-flexgen.c
@@ -373,6 +373,7 @@ static void __init st_of_flexgen_setup(struct device_node *np)
 			break;
 		}
 
+		flex_flags &= ~CLK_IS_CRITICAL;
 		of_clk_detect_critical(np, i, &flex_flags);
 
 		/*
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index aa4add580516..0b5e091742f9 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -98,7 +98,7 @@ static void sun6i_a31_get_pll1_factors(struct factors_request *req)
 	 * Round down the frequency to the closest multiple of either
 	 * 6 or 16
 	 */
-	u32 round_freq_6 = round_down(freq_mhz, 6);
+	u32 round_freq_6 = rounddown(freq_mhz, 6);
 	u32 round_freq_16 = round_down(freq_mhz, 16);
 
 	if (round_freq_6 > round_freq_16)
diff --git a/drivers/clk/ti/adpll.c b/drivers/clk/ti/adpll.c
index d6036c788fab..2738ecb1511b 100644
--- a/drivers/clk/ti/adpll.c
+++ b/drivers/clk/ti/adpll.c
@@ -193,15 +193,8 @@ static const char *ti_adpll_clk_get_name(struct ti_adpll_data *d,
 		if (err)
 			return NULL;
 	} else {
-		const char *base_name = "adpll";
-		char *buf;
-
-		buf = devm_kzalloc(d->dev, 8 + 1 + strlen(base_name) + 1 +
-				    strlen(postfix), GFP_KERNEL);
-		if (!buf)
-			return NULL;
-		sprintf(buf, "%08lx.%s.%s", d->pa, base_name, postfix);
-		name = buf;
+		name = devm_kasprintf(d->dev, GFP_KERNEL, "%08lx.adpll.%s",
+				      d->pa, postfix);
 	}
 
 	return name;
diff --git a/drivers/clk/ti/composite.c b/drivers/clk/ti/composite.c
index beea89463ca2..4ea5c08a1eb6 100644
--- a/drivers/clk/ti/composite.c
+++ b/drivers/clk/ti/composite.c
@@ -240,6 +240,7 @@ cleanup:
 		if (!cclk->comp_clks[i])
 			continue;
 		list_del(&cclk->comp_clks[i]->link);
+		kfree(cclk->comp_clks[i]->parent_names);
 		kfree(cclk->comp_clks[i]);
 	}
 
diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c
index 1f5f734e4919..a018199575e3 100644
--- a/drivers/clocksource/dw_apb_timer.c
+++ b/drivers/clocksource/dw_apb_timer.c
@@ -225,7 +225,8 @@ static int apbt_next_event(unsigned long delta,
 /**
  * dw_apb_clockevent_init() - use an APB timer as a clock_event_device
  *
- * @cpu:	The CPU the events will be targeted at.
+ * @cpu:	The CPU the events will be targeted at or -1 if CPU affiliation
+ *		isn't required.
  * @name:	The name used for the timer and the IRQ for it.
  * @rating:	The rating to give the timer.
  * @base:	I/O base for the timer registers.
@@ -260,7 +261,7 @@ dw_apb_clockevent_init(int cpu, const char *name, unsigned rating,
 	dw_ced->ced.max_delta_ticks = 0x7fffffff;
 	dw_ced->ced.min_delta_ns = clockevent_delta2ns(5000, &dw_ced->ced);
 	dw_ced->ced.min_delta_ticks = 5000;
-	dw_ced->ced.cpumask = cpumask_of(cpu);
+	dw_ced->ced.cpumask = cpu < 0 ? cpu_possible_mask : cpumask_of(cpu);
 	dw_ced->ced.features = CLOCK_EVT_FEAT_PERIODIC |
 				CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_DYNIRQ;
 	dw_ced->ced.set_state_shutdown = apbt_shutdown;
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index 69866cd8f4bb..3e4d0e5733d3 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -146,10 +146,6 @@ static int num_called;
 static int __init dw_apb_timer_init(struct device_node *timer)
 {
 	switch (num_called) {
-	case 0:
-		pr_debug("%s: found clockevent timer\n", __func__);
-		add_clockevent(timer);
-		break;
 	case 1:
 		pr_debug("%s: found clocksource timer\n", __func__);
 		add_clocksource(timer);
@@ -160,6 +156,8 @@ static int __init dw_apb_timer_init(struct device_node *timer)
 #endif
 		break;
 	default:
+		pr_debug("%s: found clockevent timer\n", __func__);
+		add_clockevent(timer);
 		break;
 	}
 
diff --git a/drivers/clocksource/h8300_timer8.c b/drivers/clocksource/h8300_timer8.c
index 1d740a8c42ab..47114c2a7cb5 100644
--- a/drivers/clocksource/h8300_timer8.c
+++ b/drivers/clocksource/h8300_timer8.c
@@ -169,7 +169,7 @@ static int __init h8300_8timer_init(struct device_node *node)
 		return PTR_ERR(clk);
 	}
 
-	ret = ENXIO;
+	ret = -ENXIO;
 	base = of_iomap(node, 0);
 	if (!base) {
 		pr_err("failed to map registers for clockevent\n");
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 1aa0b05c8cbd..be1a7bb0b401 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1378,6 +1378,7 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 
 		intel_pstate_get_hwp_max(cpu->cpu, &phy_max, &current_max);
 		cpu->pstate.turbo_freq = phy_max * cpu->pstate.scaling;
+		cpu->pstate.turbo_pstate = phy_max;
 	} else {
 		cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
 	}
@@ -2097,9 +2098,15 @@ static int intel_pstate_update_status(const char *buf, size_t size)
 {
 	int ret;
 
-	if (size == 3 && !strncmp(buf, "off", size))
-		return intel_pstate_driver ?
-			intel_pstate_unregister_driver() : -EINVAL;
+	if (size == 3 && !strncmp(buf, "off", size)) {
+		if (!intel_pstate_driver)
+			return -EINVAL;
+
+		if (hwp_active)
+			return -EBUSY;
+
+		return intel_pstate_unregister_driver();
+	}
 
 	if (size == 6 && !strncmp(buf, "active", size)) {
 		if (intel_pstate_driver) {
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 25c9a6cdd861..dc81fc2bf801 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -864,6 +864,7 @@ static struct notifier_block powernv_cpufreq_reboot_nb = {
 void powernv_cpufreq_work_fn(struct work_struct *work)
 {
 	struct chip *chip = container_of(work, struct chip, throttle);
+	struct cpufreq_policy *policy;
 	unsigned int cpu;
 	cpumask_t mask;
 
@@ -878,12 +879,14 @@ void powernv_cpufreq_work_fn(struct work_struct *work)
 	chip->restore = false;
 	for_each_cpu(cpu, &mask) {
 		int index;
-		struct cpufreq_policy policy;
 
-		cpufreq_get_policy(&policy, cpu);
-		index = cpufreq_table_find_index_c(&policy, policy.cur);
-		powernv_cpufreq_target_index(&policy, index);
-		cpumask_andnot(&mask, &mask, policy.cpus);
+		policy = cpufreq_cpu_get(cpu);
+		if (!policy)
+			continue;
+		index = cpufreq_table_find_index_c(policy, policy->cur);
+		powernv_cpufreq_target_index(policy, index);
+		cpumask_andnot(&mask, &mask, policy->cpus);
+		cpufreq_cpu_put(policy);
 	}
 out:
 	put_online_cpus();
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index ed4df58a855e..da9eb38d79d9 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -144,7 +144,8 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv,
 	 */
 	stop_critical_timings();
 	drv->states[index].enter_s2idle(dev, drv, index);
-	WARN_ON(!irqs_disabled());
+	if (WARN_ON_ONCE(!irqs_disabled()))
+		local_irq_disable();
 	/*
 	 * timekeeping_resume() that will be called by tick_unfreeze() for the
 	 * first CPU executing it calls functions containing RCU read-side
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index ae948b1da93a..909bd2255978 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -414,7 +414,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device)
 		ret = kobject_init_and_add(&kobj->kobj, &ktype_state_cpuidle,
 					   &kdev->kobj, "state%d", i);
 		if (ret) {
-			kfree(kobj);
+			kobject_put(&kobj->kobj);
 			goto error_state;
 		}
 		kobject_uevent(&kobj->kobj, KOBJ_ADD);
@@ -544,7 +544,7 @@ static int cpuidle_add_driver_sysfs(struct cpuidle_device *dev)
 	ret = kobject_init_and_add(&kdrv->kobj, &ktype_driver_cpuidle,
 				   &kdev->kobj, "driver");
 	if (ret) {
-		kfree(kdrv);
+		kobject_put(&kdrv->kobj);
 		return ret;
 	}
 
@@ -638,7 +638,7 @@ int cpuidle_add_sysfs(struct cpuidle_device *dev)
 	error = kobject_init_and_add(&kdev->kobj, &ktype_cpuidle, &cpu_dev->kobj,
 				   "cpuidle");
 	if (error) {
-		kfree(kdev);
+		kobject_put(&kdev->kobj);
 		return error;
 	}
 
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index 279e907590e9..af6119b3b6b7 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -2981,7 +2981,6 @@ static int aead_gcm_ccm_setkey(struct crypto_aead *cipher,
 
 	ctx->enckeylen = keylen;
 	ctx->authkeylen = 0;
-	memcpy(ctx->enckey, key, ctx->enckeylen);
 
 	switch (ctx->enckeylen) {
 	case AES_KEYSIZE_128:
@@ -2997,6 +2996,8 @@ static int aead_gcm_ccm_setkey(struct crypto_aead *cipher,
 		goto badkey;
 	}
 
+	memcpy(ctx->enckey, key, ctx->enckeylen);
+
 	flow_log("  enckeylen:%u authkeylen:%u\n", ctx->enckeylen,
 		 ctx->authkeylen);
 	flow_dump("  enc: ", ctx->enckey, ctx->enckeylen);
@@ -3057,6 +3058,10 @@ static int aead_gcm_esp_setkey(struct crypto_aead *cipher,
 	struct iproc_ctx_s *ctx = crypto_aead_ctx(cipher);
 
 	flow_log("%s\n", __func__);
+
+	if (keylen < GCM_ESP_SALT_SIZE)
+		return -EINVAL;
+
 	ctx->salt_len = GCM_ESP_SALT_SIZE;
 	ctx->salt_offset = GCM_ESP_SALT_OFFSET;
 	memcpy(ctx->salt, key + keylen - GCM_ESP_SALT_SIZE, GCM_ESP_SALT_SIZE);
@@ -3085,6 +3090,10 @@ static int rfc4543_gcm_esp_setkey(struct crypto_aead *cipher,
 	struct iproc_ctx_s *ctx = crypto_aead_ctx(cipher);
 
 	flow_log("%s\n", __func__);
+
+	if (keylen < GCM_ESP_SALT_SIZE)
+		return -EINVAL;
+
 	ctx->salt_len = GCM_ESP_SALT_SIZE;
 	ctx->salt_offset = GCM_ESP_SALT_OFFSET;
 	memcpy(ctx->salt, key + keylen - GCM_ESP_SALT_SIZE, GCM_ESP_SALT_SIZE);
@@ -3114,6 +3123,10 @@ static int aead_ccm_esp_setkey(struct crypto_aead *cipher,
 	struct iproc_ctx_s *ctx = crypto_aead_ctx(cipher);
 
 	flow_log("%s\n", __func__);
+
+	if (keylen < CCM_ESP_SALT_SIZE)
+		return -EINVAL;
+
 	ctx->salt_len = CCM_ESP_SALT_SIZE;
 	ctx->salt_offset = CCM_ESP_SALT_OFFSET;
 	memcpy(ctx->salt, key + keylen - CCM_ESP_SALT_SIZE, CCM_ESP_SALT_SIZE);
diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.c b/drivers/crypto/cavium/cpt/cptvf_algs.c
index df21d996db7e..2d1b28c29a8e 100644
--- a/drivers/crypto/cavium/cpt/cptvf_algs.c
+++ b/drivers/crypto/cavium/cpt/cptvf_algs.c
@@ -205,6 +205,7 @@ static inline int cvm_enc_dec(struct ablkcipher_request *req, u32 enc)
 	int status;
 
 	memset(req_info, 0, sizeof(struct cpt_request_info));
+	req_info->may_sleep = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) != 0;
 	memset(fctx, 0, sizeof(struct fc_context));
 	create_input_list(req, enc, enc_iv_len);
 	create_output_list(req, enc_iv_len);
diff --git a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
index b0ba4331944b..43fe69d0981a 100644
--- a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
+++ b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
@@ -136,7 +136,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf,
 
 	/* Setup gather (input) components */
 	g_sz_bytes = ((req->incnt + 3) / 4) * sizeof(struct sglist_component);
-	info->gather_components = kzalloc(g_sz_bytes, GFP_KERNEL);
+	info->gather_components = kzalloc(g_sz_bytes, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (!info->gather_components) {
 		ret = -ENOMEM;
 		goto  scatter_gather_clean;
@@ -153,7 +153,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf,
 
 	/* Setup scatter (output) components */
 	s_sz_bytes = ((req->outcnt + 3) / 4) * sizeof(struct sglist_component);
-	info->scatter_components = kzalloc(s_sz_bytes, GFP_KERNEL);
+	info->scatter_components = kzalloc(s_sz_bytes, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (!info->scatter_components) {
 		ret = -ENOMEM;
 		goto  scatter_gather_clean;
@@ -170,7 +170,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf,
 
 	/* Create and initialize DPTR */
 	info->dlen = g_sz_bytes + s_sz_bytes + SG_LIST_HDR_SIZE;
-	info->in_buffer = kzalloc(info->dlen, GFP_KERNEL);
+	info->in_buffer = kzalloc(info->dlen, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (!info->in_buffer) {
 		ret = -ENOMEM;
 		goto  scatter_gather_clean;
@@ -198,7 +198,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf,
 	}
 
 	/* Create and initialize RPTR */
-	info->out_buffer = kzalloc(COMPLETION_CODE_SIZE, GFP_KERNEL);
+	info->out_buffer = kzalloc(COMPLETION_CODE_SIZE, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (!info->out_buffer) {
 		ret = -ENOMEM;
 		goto scatter_gather_clean;
@@ -434,7 +434,7 @@ int process_request(struct cpt_vf *cptvf, struct cpt_request_info *req)
 	struct cpt_vq_command vq_cmd;
 	union cpt_inst_s cptinst;
 
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	info = kzalloc(sizeof(*info), req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (unlikely(!info)) {
 		dev_err(&pdev->dev, "Unable to allocate memory for info_buffer\n");
 		return -ENOMEM;
@@ -456,7 +456,7 @@ int process_request(struct cpt_vf *cptvf, struct cpt_request_info *req)
 	 * Get buffer for union cpt_res_s response
 	 * structure and its physical address
 	 */
-	info->completion_addr = kzalloc(sizeof(union cpt_res_s), GFP_KERNEL);
+	info->completion_addr = kzalloc(sizeof(union cpt_res_s), req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (unlikely(!info->completion_addr)) {
 		dev_err(&pdev->dev, "Unable to allocate memory for completion_addr\n");
 		ret = -ENOMEM;
diff --git a/drivers/crypto/cavium/cpt/request_manager.h b/drivers/crypto/cavium/cpt/request_manager.h
index 80ee074c6e0c..09930d95ad24 100644
--- a/drivers/crypto/cavium/cpt/request_manager.h
+++ b/drivers/crypto/cavium/cpt/request_manager.h
@@ -65,6 +65,8 @@ struct cpt_request_info {
 	union ctrl_info ctrl; /* User control information */
 	struct cptvf_request req; /* Request Information (Core specific) */
 
+	bool may_sleep;
+
 	struct buf_ptr in[MAX_BUF_CNT];
 	struct buf_ptr out[MAX_BUF_CNT];
 
diff --git a/drivers/crypto/cavium/nitrox/nitrox_main.c b/drivers/crypto/cavium/nitrox/nitrox_main.c
index fee7cb2ce747..a81f3c7e941d 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_main.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_main.c
@@ -183,7 +183,7 @@ static void nitrox_remove_from_devlist(struct nitrox_device *ndev)
 
 struct nitrox_device *nitrox_get_first_device(void)
 {
-	struct nitrox_device *ndev = NULL;
+	struct nitrox_device *ndev;
 
 	mutex_lock(&devlist_lock);
 	list_for_each_entry(ndev, &ndevlist, list) {
@@ -191,7 +191,7 @@ struct nitrox_device *nitrox_get_first_device(void)
 			break;
 	}
 	mutex_unlock(&devlist_lock);
-	if (!ndev)
+	if (&ndev->list == &ndevlist)
 		return NULL;
 
 	refcount_inc(&ndev->refcnt);
diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig
index 6d626606b9c5..898dcf3200c3 100644
--- a/drivers/crypto/ccp/Kconfig
+++ b/drivers/crypto/ccp/Kconfig
@@ -8,10 +8,9 @@ config CRYPTO_DEV_CCP_DD
 config CRYPTO_DEV_SP_CCP
 	bool "Cryptographic Coprocessor device"
 	default y
-	depends on CRYPTO_DEV_CCP_DD
+	depends on CRYPTO_DEV_CCP_DD && DMADEVICES
 	select HW_RANDOM
 	select DMA_ENGINE
-	select DMADEVICES
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	help
diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h
index 7442b0422f8a..bd43b5c1450c 100644
--- a/drivers/crypto/ccp/ccp-dev.h
+++ b/drivers/crypto/ccp/ccp-dev.h
@@ -471,6 +471,7 @@ struct ccp_sg_workarea {
 	unsigned int sg_used;
 
 	struct scatterlist *dma_sg;
+	struct scatterlist *dma_sg_head;
 	struct device *dma_dev;
 	unsigned int dma_count;
 	enum dma_data_direction dma_dir;
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index 330853a2702f..626b643d610e 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -67,7 +67,7 @@ static u32 ccp_gen_jobid(struct ccp_device *ccp)
 static void ccp_sg_free(struct ccp_sg_workarea *wa)
 {
 	if (wa->dma_count)
-		dma_unmap_sg(wa->dma_dev, wa->dma_sg, wa->nents, wa->dma_dir);
+		dma_unmap_sg(wa->dma_dev, wa->dma_sg_head, wa->nents, wa->dma_dir);
 
 	wa->dma_count = 0;
 }
@@ -96,6 +96,7 @@ static int ccp_init_sg_workarea(struct ccp_sg_workarea *wa, struct device *dev,
 		return 0;
 
 	wa->dma_sg = sg;
+	wa->dma_sg_head = sg;
 	wa->dma_dev = dev;
 	wa->dma_dir = dma_dir;
 	wa->dma_count = dma_map_sg(dev, sg, wa->nents, dma_dir);
@@ -108,14 +109,28 @@ static int ccp_init_sg_workarea(struct ccp_sg_workarea *wa, struct device *dev,
 static void ccp_update_sg_workarea(struct ccp_sg_workarea *wa, unsigned int len)
 {
 	unsigned int nbytes = min_t(u64, len, wa->bytes_left);
+	unsigned int sg_combined_len = 0;
 
 	if (!wa->sg)
 		return;
 
 	wa->sg_used += nbytes;
 	wa->bytes_left -= nbytes;
-	if (wa->sg_used == wa->sg->length) {
-		wa->sg = sg_next(wa->sg);
+	if (wa->sg_used == sg_dma_len(wa->dma_sg)) {
+		/* Advance to the next DMA scatterlist entry */
+		wa->dma_sg = sg_next(wa->dma_sg);
+
+		/* In the case that the DMA mapped scatterlist has entries
+		 * that have been merged, the non-DMA mapped scatterlist
+		 * must be advanced multiple times for each merged entry.
+		 * This ensures that the current non-DMA mapped entry
+		 * corresponds to the current DMA mapped entry.
+		 */
+		do {
+			sg_combined_len += wa->sg->length;
+			wa->sg = sg_next(wa->sg);
+		} while (wa->sg_used > sg_combined_len);
+
 		wa->sg_used = 0;
 	}
 }
@@ -304,7 +319,7 @@ static unsigned int ccp_queue_buf(struct ccp_data *data, unsigned int from)
 	/* Update the structures and generate the count */
 	buf_count = 0;
 	while (sg_wa->bytes_left && (buf_count < dm_wa->length)) {
-		nbytes = min(sg_wa->sg->length - sg_wa->sg_used,
+		nbytes = min(sg_dma_len(sg_wa->dma_sg) - sg_wa->sg_used,
 			     dm_wa->length - buf_count);
 		nbytes = min_t(u64, sg_wa->bytes_left, nbytes);
 
@@ -336,11 +351,11 @@ static void ccp_prepare_data(struct ccp_data *src, struct ccp_data *dst,
 	 * and destination. The resulting len values will always be <= UINT_MAX
 	 * because the dma length is an unsigned int.
 	 */
-	sg_src_len = sg_dma_len(src->sg_wa.sg) - src->sg_wa.sg_used;
+	sg_src_len = sg_dma_len(src->sg_wa.dma_sg) - src->sg_wa.sg_used;
 	sg_src_len = min_t(u64, src->sg_wa.bytes_left, sg_src_len);
 
 	if (dst) {
-		sg_dst_len = sg_dma_len(dst->sg_wa.sg) - dst->sg_wa.sg_used;
+		sg_dst_len = sg_dma_len(dst->sg_wa.dma_sg) - dst->sg_wa.sg_used;
 		sg_dst_len = min_t(u64, src->sg_wa.bytes_left, sg_dst_len);
 		op_len = min(sg_src_len, sg_dst_len);
 	} else {
@@ -370,7 +385,7 @@ static void ccp_prepare_data(struct ccp_data *src, struct ccp_data *dst,
 		/* Enough data in the sg element, but we need to
 		 * adjust for any previously copied data
 		 */
-		op->src.u.dma.address = sg_dma_address(src->sg_wa.sg);
+		op->src.u.dma.address = sg_dma_address(src->sg_wa.dma_sg);
 		op->src.u.dma.offset = src->sg_wa.sg_used;
 		op->src.u.dma.length = op_len & ~(block_size - 1);
 
@@ -391,7 +406,7 @@ static void ccp_prepare_data(struct ccp_data *src, struct ccp_data *dst,
 			/* Enough room in the sg element, but we need to
 			 * adjust for any previously used area
 			 */
-			op->dst.u.dma.address = sg_dma_address(dst->sg_wa.sg);
+			op->dst.u.dma.address = sg_dma_address(dst->sg_wa.dma_sg);
 			op->dst.u.dma.offset = dst->sg_wa.sg_used;
 			op->dst.u.dma.length = op->src.u.dma.length;
 		}
@@ -1783,8 +1798,9 @@ ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 			       LSB_ITEM_SIZE);
 			break;
 		default:
+			kfree(hmac_buf);
 			ret = -EINVAL;
-			goto e_ctx;
+			goto e_data;
 		}
 
 		memset(&hmac_cmd, 0, sizeof(hmac_cmd));
@@ -2033,7 +2049,7 @@ ccp_run_passthru_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	dst.sg_wa.sg_used = 0;
 	for (i = 1; i <= src.sg_wa.dma_count; i++) {
 		if (!dst.sg_wa.sg ||
-		    (dst.sg_wa.sg->length < src.sg_wa.sg->length)) {
+		    (sg_dma_len(dst.sg_wa.sg) < sg_dma_len(src.sg_wa.sg))) {
 			ret = -EINVAL;
 			goto e_dst;
 		}
@@ -2059,8 +2075,8 @@ ccp_run_passthru_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 			goto e_dst;
 		}
 
-		dst.sg_wa.sg_used += src.sg_wa.sg->length;
-		if (dst.sg_wa.sg_used == dst.sg_wa.sg->length) {
+		dst.sg_wa.sg_used += sg_dma_len(src.sg_wa.sg);
+		if (dst.sg_wa.sg_used == sg_dma_len(dst.sg_wa.sg)) {
 			dst.sg_wa.sg = sg_next(dst.sg_wa.sg);
 			dst.sg_wa.sg_used = 0;
 		}
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 8d39f3a07bf8..99c3827855c7 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -2201,7 +2201,7 @@ static void fill_sec_cpl_for_aead(struct cpl_tx_sec_pdu *sec_cpl,
 	unsigned int mac_mode = CHCR_SCMD_AUTH_MODE_CBCMAC;
 	unsigned int c_id = chcrctx->dev->rx_channel_id;
 	unsigned int ccm_xtra;
-	unsigned char tag_offset = 0, auth_offset = 0;
+	unsigned int tag_offset = 0, auth_offset = 0;
 	unsigned int assoclen;
 
 	if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309)
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index c1f8da958c78..4e38b87c3228 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -168,8 +168,6 @@ struct omap_sham_hmac_ctx {
 };
 
 struct omap_sham_ctx {
-	struct omap_sham_dev	*dd;
-
 	unsigned long		flags;
 
 	/* fallback stuff */
@@ -916,27 +914,35 @@ static int omap_sham_update_dma_stop(struct omap_sham_dev *dd)
 	return 0;
 }
 
+struct omap_sham_dev *omap_sham_find_dev(struct omap_sham_reqctx *ctx)
+{
+	struct omap_sham_dev *dd;
+
+	if (ctx->dd)
+		return ctx->dd;
+
+	spin_lock_bh(&sham.lock);
+	dd = list_first_entry(&sham.dev_list, struct omap_sham_dev, list);
+	list_move_tail(&dd->list, &sham.dev_list);
+	ctx->dd = dd;
+	spin_unlock_bh(&sham.lock);
+
+	return dd;
+}
+
 static int omap_sham_init(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 	struct omap_sham_ctx *tctx = crypto_ahash_ctx(tfm);
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(req);
-	struct omap_sham_dev *dd = NULL, *tmp;
+	struct omap_sham_dev *dd;
 	int bs = 0;
 
-	spin_lock_bh(&sham.lock);
-	if (!tctx->dd) {
-		list_for_each_entry(tmp, &sham.dev_list, list) {
-			dd = tmp;
-			break;
-		}
-		tctx->dd = dd;
-	} else {
-		dd = tctx->dd;
-	}
-	spin_unlock_bh(&sham.lock);
+	ctx->dd = NULL;
 
-	ctx->dd = dd;
+	dd = omap_sham_find_dev(ctx);
+	if (!dd)
+		return -ENODEV;
 
 	ctx->flags = 0;
 
@@ -1186,8 +1192,7 @@ err1:
 static int omap_sham_enqueue(struct ahash_request *req, unsigned int op)
 {
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(req);
-	struct omap_sham_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
-	struct omap_sham_dev *dd = tctx->dd;
+	struct omap_sham_dev *dd = ctx->dd;
 
 	ctx->op = op;
 
@@ -1197,7 +1202,7 @@ static int omap_sham_enqueue(struct ahash_request *req, unsigned int op)
 static int omap_sham_update(struct ahash_request *req)
 {
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(req);
-	struct omap_sham_dev *dd = ctx->dd;
+	struct omap_sham_dev *dd = omap_sham_find_dev(ctx);
 
 	if (!req->nbytes)
 		return 0;
@@ -1302,21 +1307,8 @@ static int omap_sham_setkey(struct crypto_ahash *tfm, const u8 *key,
 	struct omap_sham_hmac_ctx *bctx = tctx->base;
 	int bs = crypto_shash_blocksize(bctx->shash);
 	int ds = crypto_shash_digestsize(bctx->shash);
-	struct omap_sham_dev *dd = NULL, *tmp;
 	int err, i;
 
-	spin_lock_bh(&sham.lock);
-	if (!tctx->dd) {
-		list_for_each_entry(tmp, &sham.dev_list, list) {
-			dd = tmp;
-			break;
-		}
-		tctx->dd = dd;
-	} else {
-		dd = tctx->dd;
-	}
-	spin_unlock_bh(&sham.lock);
-
 	err = crypto_shash_setkey(tctx->fallback, key, keylen);
 	if (err)
 		return err;
@@ -1334,7 +1326,7 @@ static int omap_sham_setkey(struct crypto_ahash *tfm, const u8 *key,
 
 	memset(bctx->ipad + keylen, 0, bs - keylen);
 
-	if (!test_bit(FLAGS_AUTO_XOR, &dd->flags)) {
+	if (!test_bit(FLAGS_AUTO_XOR, &sham.flags)) {
 		memcpy(bctx->opad, bctx->ipad, bs);
 
 		for (i = 0; i < bs; i++) {
@@ -2073,6 +2065,7 @@ static int omap_sham_probe(struct platform_device *pdev)
 	}
 
 	dd->flags |= dd->pdata->flags;
+	sham.flags |= dd->pdata->flags;
 
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_set_autosuspend_delay(dev, DEFAULT_AUTOSUSPEND_DELAY);
@@ -2098,6 +2091,9 @@ static int omap_sham_probe(struct platform_device *pdev)
 	spin_unlock(&sham.lock);
 
 	for (i = 0; i < dd->pdata->algs_info_size; i++) {
+		if (dd->pdata->algs_info[i].registered)
+			break;
+
 		for (j = 0; j < dd->pdata->algs_info[i].size; j++) {
 			struct ahash_alg *alg;
 
@@ -2143,9 +2139,11 @@ static int omap_sham_remove(struct platform_device *pdev)
 	list_del(&dd->list);
 	spin_unlock(&sham.lock);
 	for (i = dd->pdata->algs_info_size - 1; i >= 0; i--)
-		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
+		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--) {
 			crypto_unregister_ahash(
 					&dd->pdata->algs_info[i].algs_list[j]);
+			dd->pdata->algs_info[i].registered--;
+		}
 	tasklet_kill(&dd->done_task);
 	pm_runtime_disable(&pdev->dev);
 
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index baffae817259..bb875245644f 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -825,6 +825,11 @@ static int qat_alg_aead_dec(struct aead_request *areq)
 	struct icp_qat_fw_la_bulk_req *msg;
 	int digst_size = crypto_aead_authsize(aead_tfm);
 	int ret, ctr = 0;
+	u32 cipher_len;
+
+	cipher_len = areq->cryptlen - digst_size;
+	if (cipher_len % AES_BLOCK_SIZE != 0)
+		return -EINVAL;
 
 	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->src, areq->dst, qat_req);
 	if (unlikely(ret))
@@ -839,7 +844,7 @@ static int qat_alg_aead_dec(struct aead_request *areq)
 	qat_req->req.comn_mid.src_data_addr = qat_req->buf.blp;
 	qat_req->req.comn_mid.dest_data_addr = qat_req->buf.bloutp;
 	cipher_param = (void *)&qat_req->req.serv_specif_rqpars;
-	cipher_param->cipher_length = areq->cryptlen - digst_size;
+	cipher_param->cipher_length = cipher_len;
 	cipher_param->cipher_offset = areq->assoclen;
 	memcpy(cipher_param->u.cipher_IV_array, areq->iv, AES_BLOCK_SIZE);
 	auth_param = (void *)((uint8_t *)cipher_param + sizeof(*cipher_param));
@@ -868,6 +873,9 @@ static int qat_alg_aead_enc(struct aead_request *areq)
 	uint8_t *iv = areq->iv;
 	int ret, ctr = 0;
 
+	if (areq->cryptlen % AES_BLOCK_SIZE != 0)
+		return -EINVAL;
+
 	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->src, areq->dst, qat_req);
 	if (unlikely(ret))
 		return ret;
diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/qat/qat_common/qat_uclo.c
index e2454d90d949..4f1cd83bf56f 100644
--- a/drivers/crypto/qat/qat_common/qat_uclo.c
+++ b/drivers/crypto/qat/qat_common/qat_uclo.c
@@ -332,13 +332,18 @@ static int qat_uclo_create_batch_init_list(struct icp_qat_fw_loader_handle
 	}
 	return 0;
 out_err:
+	/* Do not free the list head unless we allocated it. */
+	tail_old = tail_old->next;
+	if (flag) {
+		kfree(*init_tab_base);
+		*init_tab_base = NULL;
+	}
+
 	while (tail_old) {
 		mem_init = tail_old->next;
 		kfree(tail_old);
 		tail_old = mem_init;
 	}
-	if (flag)
-		kfree(*init_tab_base);
 	return -ENOMEM;
 }
 
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index fef2b306cdee..6c8a03a1132f 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -2636,7 +2636,6 @@ static struct talitos_alg_template driver_algs[] = {
 			.cra_ablkcipher = {
 				.min_keysize = AES_MIN_KEY_SIZE,
 				.max_keysize = AES_MAX_KEY_SIZE,
-				.ivsize = AES_BLOCK_SIZE,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2670,6 +2669,7 @@ static struct talitos_alg_template driver_algs[] = {
 			.cra_ablkcipher = {
 				.min_keysize = AES_MIN_KEY_SIZE,
 				.max_keysize = AES_MAX_KEY_SIZE,
+				.ivsize = AES_BLOCK_SIZE,
 				.setkey = ablkcipher_aes_setkey,
 			}
 		},
diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_algs.c
index e2231a1a05a1..e6b889ce395e 100644
--- a/drivers/crypto/virtio/virtio_crypto_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_algs.c
@@ -354,13 +354,18 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 	int err;
 	unsigned long flags;
 	struct scatterlist outhdr, iv_sg, status_sg, **sgs;
-	int i;
 	u64 dst_len;
 	unsigned int num_out = 0, num_in = 0;
 	int sg_total;
 	uint8_t *iv;
+	struct scatterlist *sg;
 
 	src_nents = sg_nents_for_len(req->src, req->nbytes);
+	if (src_nents < 0) {
+		pr_err("Invalid number of src SG.\n");
+		return src_nents;
+	}
+
 	dst_nents = sg_nents(req->dst);
 
 	pr_debug("virtio_crypto: Number of sgs (src_nents: %d, dst_nents: %d)\n",
@@ -406,6 +411,7 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 		goto free;
 	}
 
+	dst_len = min_t(unsigned int, req->nbytes, dst_len);
 	pr_debug("virtio_crypto: src_len: %u, dst_len: %llu\n",
 			req->nbytes, dst_len);
 
@@ -441,12 +447,12 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 	vc_sym_req->iv = iv;
 
 	/* Source data */
-	for (i = 0; i < src_nents; i++)
-		sgs[num_out++] = &req->src[i];
+	for (sg = req->src; src_nents; sg = sg_next(sg), src_nents--)
+		sgs[num_out++] = sg;
 
 	/* Destination data */
-	for (i = 0; i < dst_nents; i++)
-		sgs[num_out + num_in++] = &req->dst[i];
+	for (sg = req->dst; sg; sg = sg_next(sg))
+		sgs[num_out + num_in++] = sg;
 
 	/* Status */
 	sg_init_one(&status_sg, &vc_req->status, sizeof(vc_req->status));
@@ -569,10 +575,11 @@ static void virtio_crypto_ablkcipher_finalize_req(
 	struct ablkcipher_request *req,
 	int err)
 {
-	crypto_finalize_cipher_request(vc_sym_req->base.dataq->engine,
-					req, err);
 	kzfree(vc_sym_req->iv);
 	virtcrypto_clear_request(&vc_sym_req->base);
+
+	crypto_finalize_cipher_request(vc_sym_req->base.dataq->engine,
+					   req, err);
 }
 
 static struct crypto_alg virtio_crypto_algs[] = { {
diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c
index 6627a7dce95c..f6a2dd6b188f 100644
--- a/drivers/devfreq/tegra-devfreq.c
+++ b/drivers/devfreq/tegra-devfreq.c
@@ -79,6 +79,8 @@
 
 #define KHZ							1000
 
+#define KHZ_MAX						(ULONG_MAX / KHZ)
+
 /* Assume that the bus is saturated if the utilization is 25% */
 #define BUS_SATURATION_RATIO					25
 
@@ -179,7 +181,7 @@ struct tegra_actmon_emc_ratio {
 };
 
 static struct tegra_actmon_emc_ratio actmon_emc_ratios[] = {
-	{ 1400000, ULONG_MAX },
+	{ 1400000,    KHZ_MAX },
 	{ 1200000,    750000 },
 	{ 1100000,    600000 },
 	{ 1000000,    500000 },
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index 4a748c3435d7..8d99c84361cb 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -131,11 +131,13 @@ static void acpi_dma_parse_csrt(struct acpi_device *adev, struct acpi_dma *adma)
 		if (ret < 0) {
 			dev_warn(&adev->dev,
 				 "error in parsing resource group\n");
-			return;
+			break;
 		}
 
 		grp = (struct acpi_csrt_group *)((void *)grp + grp->length);
 	}
+
+	acpi_put_table((struct acpi_table_header *)csrt);
 }
 
 /**
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 21ed0e20c5d9..cf3225a22989 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -1677,6 +1677,8 @@ static struct dma_chan *at_dma_xlate(struct of_phandle_args *dma_spec,
 		return NULL;
 
 	dmac_pdev = of_find_device_by_node(dma_spec->np);
+	if (!dmac_pdev)
+		return NULL;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index c7568869284e..0d2c6e13a01f 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -682,6 +682,13 @@ static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
 			fsl_chan = &fsl_edma->chans[ch];
 
 			spin_lock(&fsl_chan->vchan.lock);
+
+			if (!fsl_chan->edesc) {
+				/* terminate_all called before */
+				spin_unlock(&fsl_chan->vchan.lock);
+				continue;
+			}
+
 			if (!fsl_chan->edesc->iscyclic) {
 				list_del(&fsl_chan->edesc->vdesc.node);
 				vchan_cookie_complete(&fsl_chan->edesc->vdesc);
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index e3899ae429e0..4c2b41beaf63 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -38,6 +38,18 @@
 
 #include "../dmaengine.h"
 
+int completion_timeout = 200;
+module_param(completion_timeout, int, 0644);
+MODULE_PARM_DESC(completion_timeout,
+		"set ioat completion timeout [msec] (default 200 [msec])");
+int idle_timeout = 2000;
+module_param(idle_timeout, int, 0644);
+MODULE_PARM_DESC(idle_timeout,
+		"set ioat idel timeout [msec] (default 2000 [msec])");
+
+#define IDLE_TIMEOUT msecs_to_jiffies(idle_timeout)
+#define COMPLETION_TIMEOUT msecs_to_jiffies(completion_timeout)
+
 static char *chanerr_str[] = {
 	"DMA Transfer Source Address Error",
 	"DMA Transfer Destination Address Error",
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 56200eefcf5e..01f929957230 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -111,8 +111,6 @@ struct ioatdma_chan {
 	#define IOAT_RUN 5
 	#define IOAT_CHAN_ACTIVE 6
 	struct timer_list timer;
-	#define COMPLETION_TIMEOUT msecs_to_jiffies(100)
-	#define IDLE_TIMEOUT msecs_to_jiffies(2000)
 	#define RESET_DELAY msecs_to_jiffies(100)
 	struct ioatdma_device *ioat_dma;
 	dma_addr_t completion_dma;
diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c
index 91fd395c90c4..8344a60c2131 100644
--- a/drivers/dma/of-dma.c
+++ b/drivers/dma/of-dma.c
@@ -72,12 +72,12 @@ static struct dma_chan *of_dma_router_xlate(struct of_phandle_args *dma_spec,
 		return NULL;
 
 	chan = ofdma_target->of_dma_xlate(&dma_spec_target, ofdma_target);
-	if (chan) {
-		chan->router = ofdma->dma_router;
-		chan->route_data = route_data;
-	} else {
+	if (IS_ERR_OR_NULL(chan)) {
 		ofdma->dma_router->route_free(ofdma->dma_router->dev,
 					      route_data);
+	} else {
+		chan->router = ofdma->dma_router;
+		chan->route_data = route_data;
 	}
 
 	/*
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index b4fa555a243f..ff8b7042d28f 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2661,6 +2661,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
 	while (burst != (1 << desc->rqcfg.brst_size))
 		desc->rqcfg.brst_size++;
 
+	desc->rqcfg.brst_len = get_burst_len(desc, len);
 	/*
 	 * If burst size is smaller than bus width then make sure we only
 	 * transfer one at a time to avoid a burst stradling an MFIFO entry.
@@ -2668,7 +2669,6 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
 	if (desc->rqcfg.brst_size * 8 < pl330->pcfg.data_bus_width)
 		desc->rqcfg.brst_len = 1;
 
-	desc->rqcfg.brst_len = get_burst_len(desc, len);
 	desc->bytes_requested = len;
 
 	desc->txd.flags = flags;
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 3402494cadf9..78e098b4bd89 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -1208,8 +1208,7 @@ static void tegra_dma_free_chan_resources(struct dma_chan *dc)
 
 	dev_dbg(tdc2dev(tdc), "Freeing channel %d\n", tdc->id);
 
-	if (tdc->busy)
-		tegra_dma_terminate_all(dc);
+	tegra_dma_terminate_all(dc);
 
 	spin_lock_irqsave(&tdc->lock, flags);
 	list_splice_init(&tdc->pending_sg_req, &sg_req_list);
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 045351f3549c..86b45198fb96 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -583,6 +583,7 @@ static int tegra_adma_alloc_chan_resources(struct dma_chan *dc)
 
 	ret = pm_runtime_get_sync(tdc2dev(tdc));
 	if (ret < 0) {
+		pm_runtime_put_noidle(tdc2dev(tdc));
 		free_irq(tdc->irq, tdc);
 		return ret;
 	}
@@ -764,8 +765,10 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 
 	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(&pdev->dev);
 		goto rpm_disable;
+	}
 
 	ret = tegra_adma_init(tdma);
 	if (ret)
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index 6d86d05e53aa..66d6640766ed 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -125,10 +125,12 @@
 /* Max transfer size per descriptor */
 #define ZYNQMP_DMA_MAX_TRANS_LEN	0x40000000
 
+/* Max burst lengths */
+#define ZYNQMP_DMA_MAX_DST_BURST_LEN    32768U
+#define ZYNQMP_DMA_MAX_SRC_BURST_LEN    32768U
+
 /* Reset values for data attributes */
 #define ZYNQMP_DMA_AXCACHE_VAL		0xF
-#define ZYNQMP_DMA_ARLEN_RST_VAL	0xF
-#define ZYNQMP_DMA_AWLEN_RST_VAL	0xF
 
 #define ZYNQMP_DMA_SRC_ISSUE_RST_VAL	0x1F
 
@@ -527,17 +529,19 @@ static void zynqmp_dma_handle_ovfl_int(struct zynqmp_dma_chan *chan, u32 status)
 
 static void zynqmp_dma_config(struct zynqmp_dma_chan *chan)
 {
-	u32 val;
+	u32 val, burst_val;
 
 	val = readl(chan->regs + ZYNQMP_DMA_CTRL0);
 	val |= ZYNQMP_DMA_POINT_TYPE_SG;
 	writel(val, chan->regs + ZYNQMP_DMA_CTRL0);
 
 	val = readl(chan->regs + ZYNQMP_DMA_DATA_ATTR);
+	burst_val = __ilog2_u32(chan->src_burst_len);
 	val = (val & ~ZYNQMP_DMA_ARLEN) |
-		(chan->src_burst_len << ZYNQMP_DMA_ARLEN_OFST);
+		((burst_val << ZYNQMP_DMA_ARLEN_OFST) & ZYNQMP_DMA_ARLEN);
+	burst_val = __ilog2_u32(chan->dst_burst_len);
 	val = (val & ~ZYNQMP_DMA_AWLEN) |
-		(chan->dst_burst_len << ZYNQMP_DMA_AWLEN_OFST);
+		((burst_val << ZYNQMP_DMA_AWLEN_OFST) & ZYNQMP_DMA_AWLEN);
 	writel(val, chan->regs + ZYNQMP_DMA_DATA_ATTR);
 }
 
@@ -551,8 +555,10 @@ static int zynqmp_dma_device_config(struct dma_chan *dchan,
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
 
-	chan->src_burst_len = config->src_maxburst;
-	chan->dst_burst_len = config->dst_maxburst;
+	chan->src_burst_len = clamp(config->src_maxburst, 1U,
+		ZYNQMP_DMA_MAX_SRC_BURST_LEN);
+	chan->dst_burst_len = clamp(config->dst_maxburst, 1U,
+		ZYNQMP_DMA_MAX_DST_BURST_LEN);
 
 	return 0;
 }
@@ -873,8 +879,8 @@ static int zynqmp_dma_chan_probe(struct zynqmp_dma_device *zdev,
 		return PTR_ERR(chan->regs);
 
 	chan->bus_width = ZYNQMP_DMA_BUS_WIDTH_64;
-	chan->dst_burst_len = ZYNQMP_DMA_AWLEN_RST_VAL;
-	chan->src_burst_len = ZYNQMP_DMA_ARLEN_RST_VAL;
+	chan->dst_burst_len = ZYNQMP_DMA_MAX_DST_BURST_LEN;
+	chan->src_burst_len = ZYNQMP_DMA_MAX_SRC_BURST_LEN;
 	err = of_property_read_u32(node, "xlnx,bus-width", &chan->bus_width);
 	if (err < 0) {
 		dev_err(&pdev->dev, "missing xlnx,bus-width property\n");
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index b36abd253786..21c5f95596be 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -261,6 +261,8 @@ static int get_scrub_rate(struct mem_ctl_info *mci)
 
 		if (pvt->model == 0x60)
 			amd64_read_pci_cfg(pvt->F2, F15H_M60H_SCRCTRL, &scrubval);
+		else
+			amd64_read_pci_cfg(pvt->F3, SCRCTRL, &scrubval);
 		break;
 
 	case 0x17:
diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c
index 0e7ea3591b78..5e7593753799 100644
--- a/drivers/edac/edac_device_sysfs.c
+++ b/drivers/edac/edac_device_sysfs.c
@@ -275,6 +275,7 @@ int edac_device_register_sysfs_main_kobj(struct edac_device_ctl_info *edac_dev)
 
 	/* Error exit stack */
 err_kobj_reg:
+	kobject_put(&edac_dev->kobj);
 	module_put(edac_dev->owner);
 
 err_out:
diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c
index 72c9eb9fdffb..53042af7262e 100644
--- a/drivers/edac/edac_pci_sysfs.c
+++ b/drivers/edac/edac_pci_sysfs.c
@@ -386,7 +386,7 @@ static int edac_pci_main_kobj_setup(void)
 
 	/* Error unwind statck */
 kobject_init_and_add_fail:
-	kfree(edac_pci_top_main_kobj);
+	kobject_put(edac_pci_top_main_kobj);
 
 kzalloc_fail:
 	module_put(THIS_MODULE);
diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c
index aac9b9b360b8..9e4781a807cf 100644
--- a/drivers/edac/ie31200_edac.c
+++ b/drivers/edac/ie31200_edac.c
@@ -147,6 +147,8 @@
 	(n << (28 + (2 * skl) - PAGE_SHIFT))
 
 static int nr_channels;
+static struct pci_dev *mci_pdev;
+static int ie31200_registered = 1;
 
 struct ie31200_priv {
 	void __iomem *window;
@@ -518,12 +520,16 @@ fail_free:
 static int ie31200_init_one(struct pci_dev *pdev,
 			    const struct pci_device_id *ent)
 {
-	edac_dbg(0, "MC:\n");
+	int rc;
 
+	edac_dbg(0, "MC:\n");
 	if (pci_enable_device(pdev) < 0)
 		return -EIO;
+	rc = ie31200_probe1(pdev, ent->driver_data);
+	if (rc == 0 && !mci_pdev)
+		mci_pdev = pci_dev_get(pdev);
 
-	return ie31200_probe1(pdev, ent->driver_data);
+	return rc;
 }
 
 static void ie31200_remove_one(struct pci_dev *pdev)
@@ -532,6 +538,8 @@ static void ie31200_remove_one(struct pci_dev *pdev)
 	struct ie31200_priv *priv;
 
 	edac_dbg(0, "\n");
+	pci_dev_put(mci_pdev);
+	mci_pdev = NULL;
 	mci = edac_mc_del_mc(&pdev->dev);
 	if (!mci)
 		return;
@@ -583,17 +591,53 @@ static struct pci_driver ie31200_driver = {
 
 static int __init ie31200_init(void)
 {
+	int pci_rc, i;
+
 	edac_dbg(3, "MC:\n");
 	/* Ensure that the OPSTATE is set correctly for POLL or NMI */
 	opstate_init();
 
-	return pci_register_driver(&ie31200_driver);
+	pci_rc = pci_register_driver(&ie31200_driver);
+	if (pci_rc < 0)
+		goto fail0;
+
+	if (!mci_pdev) {
+		ie31200_registered = 0;
+		for (i = 0; ie31200_pci_tbl[i].vendor != 0; i++) {
+			mci_pdev = pci_get_device(ie31200_pci_tbl[i].vendor,
+						  ie31200_pci_tbl[i].device,
+						  NULL);
+			if (mci_pdev)
+				break;
+		}
+		if (!mci_pdev) {
+			edac_dbg(0, "ie31200 pci_get_device fail\n");
+			pci_rc = -ENODEV;
+			goto fail1;
+		}
+		pci_rc = ie31200_init_one(mci_pdev, &ie31200_pci_tbl[i]);
+		if (pci_rc < 0) {
+			edac_dbg(0, "ie31200 init fail\n");
+			pci_rc = -ENODEV;
+			goto fail1;
+		}
+	}
+	return 0;
+
+fail1:
+	pci_unregister_driver(&ie31200_driver);
+fail0:
+	pci_dev_put(mci_pdev);
+
+	return pci_rc;
 }
 
 static void __exit ie31200_exit(void)
 {
 	edac_dbg(3, "MC:\n");
 	pci_unregister_driver(&ie31200_driver);
+	if (!ie31200_registered)
+		ie31200_remove_one(mci_pdev);
 }
 
 module_init(ie31200_init);
diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c
index 6f6537ab0a79..59e6ca685be8 100644
--- a/drivers/extcon/extcon-adc-jack.c
+++ b/drivers/extcon/extcon-adc-jack.c
@@ -128,7 +128,7 @@ static int adc_jack_probe(struct platform_device *pdev)
 	for (i = 0; data->adc_conditions[i].id != EXTCON_NONE; i++);
 	data->num_conditions = i;
 
-	data->chan = iio_channel_get(&pdev->dev, pdata->consumer_channel);
+	data->chan = devm_iio_channel_get(&pdev->dev, pdata->consumer_channel);
 	if (IS_ERR(data->chan))
 		return PTR_ERR(data->chan);
 
@@ -170,7 +170,6 @@ static int adc_jack_remove(struct platform_device *pdev)
 
 	free_irq(data->irq, data);
 	cancel_work_sync(&data->handler.work);
-	iio_channel_release(data->chan);
 
 	return 0;
 }
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 86210f75d233..a4fadd42221d 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -164,6 +164,17 @@ config RESET_ATTACK_MITIGATION
 	  have been evicted, since otherwise it will trigger even on clean
 	  reboots.
 
+config EFI_CUSTOM_SSDT_OVERLAYS
+	bool "Load custom ACPI SSDT overlay from an EFI variable"
+	depends on EFI_VARS && ACPI
+	default ACPI_TABLE_UPGRADE
+	help
+	  Allow loading of an ACPI SSDT overlay from an EFI variable specified
+	  by a kernel command line option.
+
+	  See Documentation/admin-guide/acpi/ssdt-overlays.rst for more
+	  information.endmenu
+
 endmenu
 
 config UEFI_CPER
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index b39b7e6d4e4d..a3dc6cb7326a 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -221,7 +221,7 @@ static void generic_ops_unregister(void)
 	efivars_unregister(&generic_efivars);
 }
 
-#if IS_ENABLED(CONFIG_ACPI)
+#ifdef CONFIG_EFI_CUSTOM_SSDT_OVERLAYS
 #define EFIVAR_SSDT_NAME_MAX	16
 static char efivar_ssdt[EFIVAR_SSDT_NAME_MAX] __initdata;
 static int __init efivar_ssdt_setup(char *str)
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 1c65f5ac4368..6529addd1e82 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -586,8 +586,10 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 	ret = kobject_init_and_add(&new_var->kobj, &efivar_ktype,
 				   NULL, "%s", short_name);
 	kfree(short_name);
-	if (ret)
+	if (ret) {
+		kobject_put(&new_var->kobj);
 		return ret;
+	}
 
 	kobject_uevent(&new_var->kobj, KOBJ_ADD);
 	if (efivar_entry_add(new_var, &efivar_sysfs_list)) {
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index f3c28777b8c6..deb1d8f3bdc8 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -180,7 +180,7 @@ static int esre_create_sysfs_entry(void *esre, int entry_num)
 		rc = kobject_init_and_add(&entry->kobj, &esre1_ktype, NULL,
 					  "entry%d", entry_num);
 		if (rc) {
-			kfree(entry);
+			kobject_put(&entry->kobj);
 			return rc;
 		}
 	}
diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c
index d4e6ba0301bc..694674dfbf82 100644
--- a/drivers/gpio/gpio-arizona.c
+++ b/drivers/gpio/gpio-arizona.c
@@ -69,6 +69,7 @@ static int arizona_gpio_get(struct gpio_chip *chip, unsigned offset)
 		ret = pm_runtime_get_sync(chip->parent);
 		if (ret < 0) {
 			dev_err(chip->parent, "Failed to resume: %d\n", ret);
+			pm_runtime_put_autosuspend(chip->parent);
 			return ret;
 		}
 
@@ -77,12 +78,15 @@ static int arizona_gpio_get(struct gpio_chip *chip, unsigned offset)
 		if (ret < 0) {
 			dev_err(chip->parent, "Failed to drop cache: %d\n",
 				ret);
+			pm_runtime_put_autosuspend(chip->parent);
 			return ret;
 		}
 
 		ret = regmap_read(arizona->regmap, reg, &val);
-		if (ret < 0)
+		if (ret < 0) {
+			pm_runtime_put_autosuspend(chip->parent);
 			return ret;
+		}
 
 		pm_runtime_mark_last_busy(chip->parent);
 		pm_runtime_put_autosuspend(chip->parent);
@@ -111,6 +115,7 @@ static int arizona_gpio_direction_out(struct gpio_chip *chip,
 		ret = pm_runtime_get_sync(chip->parent);
 		if (ret < 0) {
 			dev_err(chip->parent, "Failed to resume: %d\n", ret);
+			pm_runtime_put(chip->parent);
 			return ret;
 		}
 	}
diff --git a/drivers/gpio/gpio-exar.c b/drivers/gpio/gpio-exar.c
index a09d2f9ebacc..695c19901eff 100644
--- a/drivers/gpio/gpio-exar.c
+++ b/drivers/gpio/gpio-exar.c
@@ -148,8 +148,10 @@ static int gpio_exar_probe(struct platform_device *pdev)
 	mutex_init(&exar_gpio->lock);
 
 	index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL);
-	if (index < 0)
-		goto err_destroy;
+	if (index < 0) {
+		ret = index;
+		goto err_mutex_destroy;
+	}
 
 	sprintf(exar_gpio->name, "exar_gpio%d", index);
 	exar_gpio->gpio_chip.label = exar_gpio->name;
@@ -176,6 +178,7 @@ static int gpio_exar_probe(struct platform_device *pdev)
 
 err_destroy:
 	ida_simple_remove(&ida_index, index);
+err_mutex_destroy:
 	mutex_destroy(&exar_gpio->lock);
 	return ret;
 }
diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c
index 433b45ef332e..6dd2ee89bca4 100644
--- a/drivers/gpio/gpio-tc3589x.c
+++ b/drivers/gpio/gpio-tc3589x.c
@@ -209,7 +209,7 @@ static void tc3589x_gpio_irq_sync_unlock(struct irq_data *d)
 				continue;
 
 			tc3589x_gpio->oldregs[i][j] = new;
-			tc3589x_reg_write(tc3589x, regmap[i] + j * 8, new);
+			tc3589x_reg_write(tc3589x, regmap[i] + j, new);
 		}
 	}
 
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 1eb857e2f62f..dd801f5d5253 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -356,6 +356,7 @@ static void tegra_gpio_irq_shutdown(struct irq_data *d)
 	struct tegra_gpio_info *tgi = bank->tgi;
 	unsigned int gpio = d->hwirq;
 
+	tegra_gpio_irq_mask(d);
 	gpiochip_unlock_as_irq(&tgi->gc, gpio);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 1eff36a87595..3992e1cbb61c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -734,8 +734,10 @@ amdgpu_connector_lvds_detect(struct drm_connector *connector, bool force)
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (encoder) {
@@ -872,8 +874,10 @@ amdgpu_connector_vga_detect(struct drm_connector *connector, bool force)
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	encoder = amdgpu_connector_best_single_encoder(connector);
@@ -996,8 +1000,10 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) {
@@ -1371,8 +1377,10 @@ amdgpu_connector_dp_detect(struct drm_connector *connector, bool force)
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 6ad243293a78..eea17a8511b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -269,7 +269,7 @@ int amdgpu_crtc_set_config(struct drm_mode_set *set,
 
 	ret = pm_runtime_get_sync(dev->dev);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	ret = drm_crtc_helper_set_config(set, ctx);
 
@@ -293,6 +293,7 @@ int amdgpu_crtc_set_config(struct drm_mode_set *set,
 		adev->have_disp_power_ref = false;
 	}
 
+out:
 	/* drop the power reference we got coming in here */
 	pm_runtime_put_autosuspend(dev->dev);
 	return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 4894d8a87c04..465ece90e63a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -728,7 +728,6 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 	drm_kms_helper_poll_disable(drm_dev);
-	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_OFF);
 
 	ret = amdgpu_device_suspend(drm_dev, false, false);
 	pci_save_state(pdev);
@@ -765,7 +764,6 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 
 	ret = amdgpu_device_resume(drm_dev, false, false);
 	drm_kms_helper_poll_enable(drm_dev);
-	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON);
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
 	return 0;
 }
@@ -803,11 +801,12 @@ long amdgpu_drm_ioctl(struct file *filp,
 	dev = file_priv->minor->dev;
 	ret = pm_runtime_get_sync(dev->dev);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	ret = drm_ioctl(filp, cmd, arg);
 
 	pm_runtime_mark_last_busy(dev->dev);
+out:
 	pm_runtime_put_autosuspend(dev->dev);
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index c93e72d8ac5f..df5ed16f7fb7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -502,8 +502,12 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		 * in the bitfields */
 		if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK)
 			se_num = 0xffffffff;
+		else if (se_num >= AMDGPU_GFX_MAX_SE)
+			return -EINVAL;
 		if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK)
 			sh_num = 0xffffffff;
+		else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE)
+			return -EINVAL;
 
 		if (info->read_mmr_reg.count > 128)
 			return -EINVAL;
@@ -527,8 +531,9 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		return n ? -EFAULT : 0;
 	}
 	case AMDGPU_INFO_DEV_INFO: {
-		struct drm_amdgpu_info_device dev_info = {};
+		struct drm_amdgpu_info_device dev_info;
 
+		memset(&dev_info, 0, sizeof(dev_info));
 		dev_info.device_id = dev->pdev->device;
 		dev_info.chip_rev = adev->rev_id;
 		dev_info.external_rev = adev->external_rev_id;
@@ -784,7 +789,7 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 
 	r = pm_runtime_get_sync(dev->dev);
 	if (r < 0)
-		return r;
+		goto pm_put;
 
 	fpriv = kzalloc(sizeof(*fpriv), GFP_KERNEL);
 	if (unlikely(!fpriv)) {
@@ -823,6 +828,7 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 
 out_suspend:
 	pm_runtime_mark_last_busy(dev->dev);
+pm_put:
 	pm_runtime_put_autosuspend(dev->dev);
 
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index bc746131987f..ae700e445fbc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -727,6 +727,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm)
 
 release_sg:
 	kfree(ttm->sg);
+	ttm->sg = NULL;
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c
index d69aa2e179bb..e4874cc209ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/atom.c
+++ b/drivers/gpu/drm/amd/amdgpu/atom.c
@@ -742,8 +742,8 @@ static void atom_op_jump(atom_exec_context *ctx, int *ptr, int arg)
 			cjiffies = jiffies;
 			if (time_after(cjiffies, ctx->last_jump_jiffies)) {
 				cjiffies -= ctx->last_jump_jiffies;
-				if ((jiffies_to_msecs(cjiffies) > 5000)) {
-					DRM_ERROR("atombios stuck in loop for more than 5secs aborting\n");
+				if ((jiffies_to_msecs(cjiffies) > 10000)) {
+					DRM_ERROR("atombios stuck in loop for more than 10secs aborting\n");
 					ctx->abort = true;
 				}
 			} else {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index e0b78fd9804d..ab79c1030f00 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -821,8 +821,10 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev,
 
 	ret = kobject_init_and_add(dev->kobj_node, &node_type,
 			sys_props.kobj_nodes, "%d", id);
-	if (ret < 0)
+	if (ret < 0) {
+		kobject_put(dev->kobj_node);
 		return ret;
+	}
 
 	dev->kobj_mem = kobject_create_and_add("mem_banks", dev->kobj_node);
 	if (!dev->kobj_mem)
@@ -865,8 +867,10 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev,
 			return -ENOMEM;
 		ret = kobject_init_and_add(mem->kobj, &mem_type,
 				dev->kobj_mem, "%d", i);
-		if (ret < 0)
+		if (ret < 0) {
+			kobject_put(mem->kobj);
 			return ret;
+		}
 
 		mem->attr.name = "properties";
 		mem->attr.mode = KFD_SYSFS_FILE_MODE;
@@ -884,8 +888,10 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev,
 			return -ENOMEM;
 		ret = kobject_init_and_add(cache->kobj, &cache_type,
 				dev->kobj_cache, "%d", i);
-		if (ret < 0)
+		if (ret < 0) {
+			kobject_put(cache->kobj);
 			return ret;
+		}
 
 		cache->attr.name = "properties";
 		cache->attr.mode = KFD_SYSFS_FILE_MODE;
@@ -903,8 +909,10 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev,
 			return -ENOMEM;
 		ret = kobject_init_and_add(iolink->kobj, &iolink_type,
 				dev->kobj_iolink, "%d", i);
-		if (ret < 0)
+		if (ret < 0) {
+			kobject_put(iolink->kobj);
 			return ret;
+		}
 
 		iolink->attr.name = "properties";
 		iolink->attr.mode = KFD_SYSFS_FILE_MODE;
@@ -956,8 +964,10 @@ static int kfd_topology_update_sysfs(void)
 		ret = kobject_init_and_add(sys_props.kobj_topology,
 				&sysprops_type,  &kfd_device->kobj,
 				"topology");
-		if (ret < 0)
+		if (ret < 0) {
+			kobject_put(sys_props.kobj_topology);
 			return ret;
+		}
 
 		sys_props.kobj_nodes = kobject_create_and_add("nodes",
 				sys_props.kobj_topology);
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 16b8b310ae5c..7072d738b072 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -369,7 +369,7 @@ int malidp_de_planes_init(struct drm_device *drm)
 	const struct malidp_hw_regmap *map = &malidp->dev->map;
 	struct malidp_plane *plane = NULL;
 	enum drm_plane_type plane_type;
-	unsigned long crtcs = 1 << drm->mode_config.num_crtc;
+	unsigned long crtcs = BIT(drm->mode_config.num_crtc);
 	unsigned long flags = DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_180 |
 			      DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y;
 	u32 *formats;
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
index 67469c26bae8..45a027d7a1e4 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
@@ -20,13 +20,15 @@ static void adv7511_calc_cts_n(unsigned int f_tmds, unsigned int fs,
 {
 	switch (fs) {
 	case 32000:
-		*n = 4096;
+	case 48000:
+	case 96000:
+	case 192000:
+		*n = fs * 128 / 1000;
 		break;
 	case 44100:
-		*n = 6272;
-		break;
-	case 48000:
-		*n = 6144;
+	case 88200:
+	case 176400:
+		*n = fs * 128 / 900;
 		break;
 	}
 
diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c
index 0cb69ee94ac1..b93486892f4a 100644
--- a/drivers/gpu/drm/bridge/sil-sii8620.c
+++ b/drivers/gpu/drm/bridge/sil-sii8620.c
@@ -167,7 +167,7 @@ static void sii8620_read_buf(struct sii8620 *ctx, u16 addr, u8 *buf, int len)
 
 static u8 sii8620_readb(struct sii8620 *ctx, u16 addr)
 {
-	u8 ret;
+	u8 ret = 0;
 
 	sii8620_read_buf(ctx, addr, &ret, 1);
 	return ret;
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index c1807d5754b2..454deba13ee5 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -250,13 +250,13 @@ static ssize_t connector_write(struct file *file, const char __user *ubuf,
 
 	buf[len] = '\0';
 
-	if (!strcmp(buf, "on"))
+	if (sysfs_streq(buf, "on"))
 		connector->force = DRM_FORCE_ON;
-	else if (!strcmp(buf, "digital"))
+	else if (sysfs_streq(buf, "digital"))
 		connector->force = DRM_FORCE_ON_DIGITAL;
-	else if (!strcmp(buf, "off"))
+	else if (sysfs_streq(buf, "off"))
 		connector->force = DRM_FORCE_OFF;
-	else if (!strcmp(buf, "unspecified"))
+	else if (sysfs_streq(buf, "unspecified"))
 		connector->force = DRM_FORCE_UNSPECIFIED;
 	else
 		return -EINVAL;
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 42eaeae86bb8..e52381c9d04e 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -29,6 +29,7 @@
 #include <linux/i2c.h>
 #include <drm/drm_dp_mst_helper.h>
 #include <drm/drmP.h>
+#include <linux/iopoll.h>
 
 #include <drm/drm_fixed.h>
 #include <drm/drm_atomic.h>
@@ -2751,6 +2752,17 @@ fail:
 	return ret;
 }
 
+static int do_get_act_status(struct drm_dp_aux *aux)
+{
+	int ret;
+	u8 status;
+
+	ret = drm_dp_dpcd_readb(aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, &status);
+	if (ret < 0)
+		return ret;
+
+	return status;
+}
 
 /**
  * drm_dp_check_act_status() - Check ACT handled status.
@@ -2760,33 +2772,29 @@ fail:
  */
 int drm_dp_check_act_status(struct drm_dp_mst_topology_mgr *mgr)
 {
-	u8 status;
-	int ret;
-	int count = 0;
-
-	do {
-		ret = drm_dp_dpcd_readb(mgr->aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, &status);
-
-		if (ret < 0) {
-			DRM_DEBUG_KMS("failed to read payload table status %d\n", ret);
-			goto fail;
-		}
-
-		if (status & DP_PAYLOAD_ACT_HANDLED)
-			break;
-		count++;
-		udelay(100);
-
-	} while (count < 30);
-
-	if (!(status & DP_PAYLOAD_ACT_HANDLED)) {
-		DRM_DEBUG_KMS("failed to get ACT bit %d after %d retries\n", status, count);
-		ret = -EINVAL;
-		goto fail;
+	/*
+	 * There doesn't seem to be any recommended retry count or timeout in
+	 * the MST specification. Since some hubs have been observed to take
+	 * over 1 second to update their payload allocations under certain
+	 * conditions, we use a rather large timeout value.
+	 */
+	const int timeout_ms = 3000;
+	int ret, status;
+
+	ret = readx_poll_timeout(do_get_act_status, mgr->aux, status,
+				 status & DP_PAYLOAD_ACT_HANDLED || status < 0,
+				 200, timeout_ms * USEC_PER_MSEC);
+	if (ret < 0 && status >= 0) {
+		DRM_DEBUG_KMS("Failed to get ACT after %dms, last status: %02x\n",
+			      timeout_ms, status);
+		return -EINVAL;
+	} else if (status < 0) {
+		DRM_DEBUG_KMS("Failed to read payload table status: %d\n",
+			      status);
+		return status;
 	}
+
 	return 0;
-fail:
-	return ret;
 }
 EXPORT_SYMBOL(drm_dp_check_act_status);
 
diff --git a/drivers/gpu/drm/drm_encoder_slave.c b/drivers/gpu/drm/drm_encoder_slave.c
index cf804389f5ec..d50a7884e69e 100644
--- a/drivers/gpu/drm/drm_encoder_slave.c
+++ b/drivers/gpu/drm/drm_encoder_slave.c
@@ -84,7 +84,7 @@ int drm_i2c_encoder_init(struct drm_device *dev,
 
 	err = encoder_drv->encoder_init(client, dev, encoder);
 	if (err)
-		goto fail_unregister;
+		goto fail_module_put;
 
 	if (info->platform_data)
 		encoder->slave_funcs->set_config(&encoder->base,
@@ -92,9 +92,10 @@ int drm_i2c_encoder_init(struct drm_device *dev,
 
 	return 0;
 
+fail_module_put:
+	module_put(module);
 fail_unregister:
 	i2c_unregister_device(client);
-	module_put(module);
 fail:
 	return err;
 }
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index d2c042af36b8..470a79eef254 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -730,9 +730,6 @@ err:
  * @file_priv: drm file-private structure
  *
  * Open an object using the global name, returning a handle and the size.
- *
- * This handle (of course) holds a reference to the object, so the object
- * will not go away until the handle is deleted.
  */
 int
 drm_gem_open_ioctl(struct drm_device *dev, void *data,
@@ -757,14 +754,15 @@ drm_gem_open_ioctl(struct drm_device *dev, void *data,
 
 	/* drm_gem_handle_create_tail unlocks dev->object_name_lock. */
 	ret = drm_gem_handle_create_tail(file_priv, obj, &handle);
-	drm_gem_object_put_unlocked(obj);
 	if (ret)
-		return ret;
+		goto err;
 
 	args->handle = handle;
 	args->size = obj->size;
 
-	return 0;
+err:
+	drm_gem_object_put_unlocked(obj);
+	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index 4b47226b90d4..6f0de951b75d 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -1029,11 +1029,11 @@ EXPORT_SYMBOL(mipi_dsi_dcs_set_pixel_format);
  */
 int mipi_dsi_dcs_set_tear_scanline(struct mipi_dsi_device *dsi, u16 scanline)
 {
-	u8 payload[3] = { MIPI_DCS_SET_TEAR_SCANLINE, scanline >> 8,
-			  scanline & 0xff };
+	u8 payload[2] = { scanline >> 8, scanline & 0xff };
 	ssize_t err;
 
-	err = mipi_dsi_generic_write(dsi, payload, sizeof(payload));
+	err = mipi_dsi_dcs_write(dsi, MIPI_DCS_SET_TEAR_SCANLINE, payload,
+				 sizeof(payload));
 	if (err < 0)
 		return err;
 
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 889c95d4feec..3f71bc3d93fe 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -355,7 +355,6 @@ static int drm_syncobj_handle_to_fd(struct drm_file *file_private,
 		return PTR_ERR(file);
 	}
 
-	drm_syncobj_get(syncobj);
 	fd_install(fd, file);
 
 	*p_fd = fd;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index ba4a32b132ba..59ce068b152f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -267,8 +267,10 @@ static void mic_pre_enable(struct drm_bridge *bridge)
 		goto unlock;
 
 	ret = pm_runtime_get_sync(mic->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(mic->dev);
 		goto unlock;
+	}
 
 	mic_set_path(mic, 1);
 
diff --git a/drivers/gpu/drm/gma500/cdv_intel_display.c b/drivers/gpu/drm/gma500/cdv_intel_display.c
index 17db4b4749d5..2e8479744ca4 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_display.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_display.c
@@ -415,6 +415,8 @@ static bool cdv_intel_find_dp_pll(const struct gma_limit_t *limit,
 	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct gma_clock_t clock;
 
+	memset(&clock, 0, sizeof(clock));
+
 	switch (refclk) {
 	case 27000:
 		if (target < 200000) {
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index e4b9eb1f6b60..f6b81f3256cf 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -570,6 +570,9 @@ struct drm_i915_reg_descriptor {
 #define REG32(_reg, ...) \
 	{ .addr = (_reg), __VA_ARGS__ }
 
+#define REG32_IDX(_reg, idx) \
+	{ .addr = _reg(idx) }
+
 /*
  * Convenience macro for adding 64-bit registers.
  *
@@ -667,6 +670,7 @@ static const struct drm_i915_reg_descriptor gen9_blt_regs[] = {
 	REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
 	REG32(BCS_SWCTRL),
 	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
+	REG32_IDX(RING_CTX_TIMESTAMP, BLT_RING_BASE),
 	REG64_IDX(BCS_GPR, 0),
 	REG64_IDX(BCS_GPR, 1),
 	REG64_IDX(BCS_GPR, 2),
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index d99d05a91032..bf13299ebb55 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1566,7 +1566,9 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb)
 		 * happened we would make the mistake of assuming that the
 		 * relocations were valid.
 		 */
-		user_access_begin();
+		if (!user_access_begin(VERIFY_WRITE, urelocs, size))
+			goto end_user;
+
 		for (copied = 0; copied < nreloc; copied++)
 			unsafe_put_user(-1,
 					&urelocs[copied].presumed_offset,
@@ -2601,6 +2603,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 	struct drm_i915_gem_execbuffer2 *args = data;
 	struct drm_i915_gem_exec_object2 *exec2_list;
 	struct drm_syncobj **fences = NULL;
+	const size_t count = args->buffer_count;
 	int err;
 
 	if (args->buffer_count < 1 || args->buffer_count > SIZE_MAX / sz - 1) {
@@ -2649,7 +2652,17 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		unsigned int i;
 
 		/* Copy the new buffer offsets back to the user's exec list. */
-		user_access_begin();
+		/*
+		 * Note: count * sizeof(*user_exec_list) does not overflow,
+		 * because we checked 'count' in check_buffer_count().
+		 *
+		 * And this range already got effectively checked earlier
+		 * when we did the "copy_from_user()" above.
+		 */
+		if (!user_access_begin(VERIFY_WRITE, user_exec_list,
+				       count * sizeof(*user_exec_list)))
+			goto end_user;
+
 		for (i = 0; i < args->buffer_count; i++) {
 			if (!(exec2_list[i].offset & UPDATE))
 				continue;
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 4f2e6c7e04c1..d38648a7ef2d 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -311,18 +311,19 @@ static void imx_ldb_encoder_disable(struct drm_encoder *encoder)
 {
 	struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder);
 	struct imx_ldb *ldb = imx_ldb_ch->ldb;
+	int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN;
 	int mux, ret;
 
 	drm_panel_disable(imx_ldb_ch->panel);
 
-	if (imx_ldb_ch == &ldb->channel[0])
+	if (imx_ldb_ch == &ldb->channel[0] || dual)
 		ldb->ldb_ctrl &= ~LDB_CH0_MODE_EN_MASK;
-	else if (imx_ldb_ch == &ldb->channel[1])
+	if (imx_ldb_ch == &ldb->channel[1] || dual)
 		ldb->ldb_ctrl &= ~LDB_CH1_MODE_EN_MASK;
 
 	regmap_write(ldb->regmap, IOMUXC_GPR2, ldb->ldb_ctrl);
 
-	if (ldb->ldb_ctrl & LDB_SPLIT_MODE_EN) {
+	if (dual) {
 		clk_disable_unprepare(ldb->clk[0]);
 		clk_disable_unprepare(ldb->clk[1]);
 	}
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index bc27c2699464..c22c3e6e9b7a 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -498,6 +498,13 @@ static int imx_tve_register(struct drm_device *drm, struct imx_tve *tve)
 	return 0;
 }
 
+static void imx_tve_disable_regulator(void *data)
+{
+	struct imx_tve *tve = data;
+
+	regulator_disable(tve->dac_reg);
+}
+
 static bool imx_tve_readable_reg(struct device *dev, unsigned int reg)
 {
 	return (reg % 4 == 0) && (reg <= 0xdc);
@@ -622,6 +629,9 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data)
 		ret = regulator_enable(tve->dac_reg);
 		if (ret)
 			return ret;
+		ret = devm_add_action_or_reset(dev, imx_tve_disable_regulator, tve);
+		if (ret)
+			return ret;
 	}
 
 	tve->clk = devm_clk_get(dev, "tve");
@@ -668,18 +678,8 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data)
 	return 0;
 }
 
-static void imx_tve_unbind(struct device *dev, struct device *master,
-	void *data)
-{
-	struct imx_tve *tve = dev_get_drvdata(dev);
-
-	if (!IS_ERR(tve->dac_reg))
-		regulator_disable(tve->dac_reg);
-}
-
 static const struct component_ops imx_tve_ops = {
 	.bind	= imx_tve_bind,
-	.unbind	= imx_tve_unbind,
 };
 
 static int imx_tve_probe(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 670662128edd..f32645a33cc9 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -538,8 +538,13 @@ err_pm:
 	pm_runtime_disable(dev);
 err_node:
 	of_node_put(private->mutex_node);
-	for (i = 0; i < DDP_COMPONENT_ID_MAX; i++)
+	for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) {
 		of_node_put(private->comp_node[i]);
+		if (private->ddp_comp[i]) {
+			put_device(private->ddp_comp[i]->larb_dev);
+			private->ddp_comp[i] = NULL;
+		}
+	}
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 3c69c73fbd47..f1a376c34e71 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1476,25 +1476,30 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
 		dev_err(dev,
 			"Failed to get system configuration registers: %d\n",
 			ret);
-		return ret;
+		goto put_device;
 	}
 	hdmi->sys_regmap = regmap;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	hdmi->regs = devm_ioremap_resource(dev, mem);
-	if (IS_ERR(hdmi->regs))
-		return PTR_ERR(hdmi->regs);
+	if (IS_ERR(hdmi->regs)) {
+		ret = PTR_ERR(hdmi->regs);
+		goto put_device;
+	}
 
 	remote = of_graph_get_remote_node(np, 1, 0);
-	if (!remote)
-		return -EINVAL;
+	if (!remote) {
+		ret = -EINVAL;
+		goto put_device;
+	}
 
 	if (!of_device_is_compatible(remote, "hdmi-connector")) {
 		hdmi->next_bridge = of_drm_find_bridge(remote);
 		if (!hdmi->next_bridge) {
 			dev_err(dev, "Waiting for external bridge\n");
 			of_node_put(remote);
-			return -EPROBE_DEFER;
+			ret = -EPROBE_DEFER;
+			goto put_device;
 		}
 	}
 
@@ -1503,7 +1508,8 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
 		dev_err(dev, "Failed to find ddc-i2c-bus node in %pOF\n",
 			remote);
 		of_node_put(remote);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_device;
 	}
 	of_node_put(remote);
 
@@ -1511,10 +1517,14 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
 	of_node_put(i2c_np);
 	if (!hdmi->ddc_adpt) {
 		dev_err(dev, "Failed to get ddc i2c adapter by node\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_device;
 	}
 
 	return 0;
+put_device:
+	put_device(hdmi->cec_dev);
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index f7c0698fec40..791a74b9907d 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -972,7 +972,8 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
 
 	return 0;
 fail:
-	mdp5_destroy(pdev);
+	if (mdp5_kms)
+		mdp5_destroy(pdev);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index d9c0687435a0..c59240b566d8 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1134,6 +1134,13 @@ static int msm_pdev_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static void msm_pdev_shutdown(struct platform_device *pdev)
+{
+	struct drm_device *drm = platform_get_drvdata(pdev);
+
+	drm_atomic_helper_shutdown(drm);
+}
+
 static const struct of_device_id dt_match[] = {
 	{ .compatible = "qcom,mdp4", .data = (void *)4 },	/* MDP4 */
 	{ .compatible = "qcom,mdss", .data = (void *)5 },	/* MDP5 MDSS */
@@ -1144,6 +1151,7 @@ MODULE_DEVICE_TABLE(of, dt_match);
 static struct platform_driver msm_platform_driver = {
 	.probe      = msm_pdev_probe,
 	.remove     = msm_pdev_remove,
+	.shutdown   = msm_pdev_shutdown,
 	.driver     = {
 		.name   = "msm",
 		.of_match_table = dt_match,
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 4a7d50a96d36..b5c8219c5455 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -580,8 +580,10 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 		pm_runtime_get_noresume(dev->dev);
 	} else {
 		ret = pm_runtime_get_sync(dev->dev);
-		if (ret < 0 && ret != -EACCES)
+		if (ret < 0 && ret != -EACCES) {
+			pm_runtime_put_autosuspend(dev->dev);
 			return conn_status;
+		}
 	}
 
 	nv_encoder = nouveau_connector_ddc_detect(connector);
diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
index 9635704a1d86..4561a786fab0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c
+++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
@@ -161,8 +161,11 @@ nouveau_debugfs_pstate_set(struct file *file, const char __user *ubuf,
 	}
 
 	ret = pm_runtime_get_sync(drm->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(drm->dev);
 		return ret;
+	}
+
 	ret = nvif_mthd(ctrl, NVIF_CONTROL_PSTATE_USER, &args, sizeof(args));
 	pm_runtime_put_autosuspend(drm->dev);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 70a8d0b0c4f1..fb6b1d0f7fef 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -754,7 +754,6 @@ nouveau_pmops_runtime_suspend(struct device *dev)
 	}
 
 	drm_kms_helper_poll_disable(drm_dev);
-	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_OFF);
 	nouveau_switcheroo_optimus_dsm();
 	ret = nouveau_do_suspend(drm_dev, true);
 	pci_save_state(pdev);
@@ -789,7 +788,6 @@ nouveau_pmops_runtime_resume(struct device *dev)
 
 	/* do magic */
 	nvif_mask(&device->object, 0x088488, (1 << 25), (1 << 25));
-	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON);
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
 
 	/* Monitors may have been connected / disconnected during suspend */
@@ -842,8 +840,10 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 
 	/* need to bring up power immediately if opening device */
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	get_task_comm(tmpname, current);
 	snprintf(name, sizeof(name), "%s[%d]", tmpname, pid_nr(fpriv->pid));
@@ -932,8 +932,10 @@ nouveau_drm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	long ret;
 
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	switch (_IOC_NR(cmd) - DRM_COMMAND_BASE) {
 	case DRM_NOUVEAU_NVIF:
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 2b12d82aac15..cae1beabcd05 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -184,8 +184,10 @@ nouveau_fbcon_open(struct fb_info *info, int user)
 	struct nouveau_fbdev *fbcon = info->par;
 	struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
 	int ret = pm_runtime_get_sync(drm->dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put(drm->dev->dev);
 		return ret;
+	}
 	return 0;
 }
 
@@ -310,7 +312,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper,
 	struct nouveau_framebuffer *fb;
 	struct nouveau_channel *chan;
 	struct nouveau_bo *nvbo;
-	struct drm_mode_fb_cmd2 mode_cmd;
+	struct drm_mode_fb_cmd2 mode_cmd = {};
 	int ret;
 
 	mode_cmd.width = sizes->surface_width;
@@ -543,6 +545,7 @@ fini:
 	drm_fb_helper_fini(&fbcon->helper);
 free:
 	kfree(fbcon);
+	drm->fbcon = NULL;
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 60ffb70bb908..c6149b5be073 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -42,8 +42,10 @@ nouveau_gem_object_del(struct drm_gem_object *gem)
 	int ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (WARN_ON(ret < 0 && ret != -EACCES))
+	if (WARN_ON(ret < 0 && ret != -EACCES)) {
+		pm_runtime_put_autosuspend(dev);
 		return;
+	}
 
 	if (gem->import_attach)
 		drm_prime_gem_destroy(gem, nvbo->bo.sg);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
index c8ab1b5741a3..db7769cb33eb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
@@ -118,10 +118,10 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		if (retries)
 			udelay(400);
 
-		/* transaction request, wait up to 1ms for it to complete */
+		/* transaction request, wait up to 2ms for it to complete */
 		nvkm_wr32(device, 0x00e4e4 + base, 0x00010000 | ctrl);
 
-		timeout = 1000;
+		timeout = 2000;
 		do {
 			ctrl = nvkm_rd32(device, 0x00e4e4 + base);
 			udelay(1);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
index 7ef60895f43a..edb6148cbca0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
@@ -118,10 +118,10 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		if (retries)
 			udelay(400);
 
-		/* transaction request, wait up to 1ms for it to complete */
+		/* transaction request, wait up to 2ms for it to complete */
 		nvkm_wr32(device, 0x00d954 + base, 0x00010000 | ctrl);
 
-		timeout = 1000;
+		timeout = 2000;
 		do {
 			ctrl = nvkm_rd32(device, 0x00d954 + base);
 			udelay(1);
diff --git a/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c b/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c
index bf626acae271..cd8e9b799b9a 100644
--- a/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c
+++ b/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c
@@ -193,7 +193,7 @@ static int __init omapdss_boot_init(void)
 	dss = of_find_matching_node(NULL, omapdss_of_match);
 
 	if (dss == NULL || !of_device_is_available(dss))
-		return 0;
+		goto put_node;
 
 	omapdss_walk_device(dss, true);
 
@@ -218,6 +218,8 @@ static int __init omapdss_boot_init(void)
 		kfree(n);
 	}
 
+put_node:
+	of_node_put(dss);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index c1daed3fe842..6df312ba1826 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1253,7 +1253,7 @@ static const struct drm_display_mode lg_lb070wv8_mode = {
 static const struct panel_desc lg_lb070wv8 = {
 	.modes = &lg_lb070wv8_mode,
 	.num_modes = 1,
-	.bpc = 16,
+	.bpc = 8,
 	.size = {
 		.width = 151,
 		.height = 91,
diff --git a/drivers/gpu/drm/qxl/qxl_kms.c b/drivers/gpu/drm/qxl/qxl_kms.c
index c5716a0ca3b8..20ca0a75e685 100644
--- a/drivers/gpu/drm/qxl/qxl_kms.c
+++ b/drivers/gpu/drm/qxl/qxl_kms.c
@@ -181,7 +181,7 @@ int qxl_device_init(struct qxl_device *qdev,
 				&(qdev->ram_header->cursor_ring_hdr),
 				sizeof(struct qxl_command),
 				QXL_CURSOR_RING_SIZE,
-				qdev->io_base + QXL_IO_NOTIFY_CMD,
+				qdev->io_base + QXL_IO_NOTIFY_CURSOR,
 				false,
 				&qdev->cursor_event);
 
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index c97fbb2ab48b..81bc2b89222f 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -4342,7 +4342,7 @@ static int ci_set_mc_special_registers(struct radeon_device *rdev,
 					table->mc_reg_table_entry[k].mc_data[j] |= 0x100;
 			}
 			j++;
-			if (j > SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 
 			if (!pi->mem_gddr5) {
@@ -5551,6 +5551,7 @@ static int ci_parse_power_table(struct radeon_device *rdev)
 	if (!rdev->pm.dpm.ps)
 		return -ENOMEM;
 	power_state_offset = (u8 *)state_array->states;
+	rdev->pm.dpm.num_ps = 0;
 	for (i = 0; i < state_array->ucNumEntries; i++) {
 		u8 *idx;
 		power_state = (union pplib_power_state *)power_state_offset;
@@ -5560,10 +5561,8 @@ static int ci_parse_power_table(struct radeon_device *rdev)
 		if (!rdev->pm.power_state[i].clock_info)
 			return -EINVAL;
 		ps = kzalloc(sizeof(struct ci_ps), GFP_KERNEL);
-		if (ps == NULL) {
-			kfree(rdev->pm.dpm.ps);
+		if (ps == NULL)
 			return -ENOMEM;
-		}
 		rdev->pm.dpm.ps[i].ps_priv = ps;
 		ci_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i],
 					      non_clock_info,
@@ -5585,8 +5584,8 @@ static int ci_parse_power_table(struct radeon_device *rdev)
 			k++;
 		}
 		power_state_offset += 2 + power_state->v2.ucNumDPMLevels;
+		rdev->pm.dpm.num_ps = i + 1;
 	}
-	rdev->pm.dpm.num_ps = state_array->ucNumEntries;
 
 	/* fill in the vce power states */
 	for (i = 0; i < RADEON_MAX_VCE_LEVELS; i++) {
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index 9416e72f86aa..d491b3aa124f 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -2126,7 +2126,7 @@ static int ni_init_smc_spll_table(struct radeon_device *rdev)
 		if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT))
 			ret = -EINVAL;
 
-		if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT))
+		if (fb_div & ~(SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_SHIFT))
 			ret = -EINVAL;
 
 		if (clk_v & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_SHIFT))
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 48f752cf7a92..fc021b8e4077 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -895,8 +895,10 @@ radeon_lvds_detect(struct drm_connector *connector, bool force)
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (encoder) {
@@ -1041,8 +1043,10 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	encoder = radeon_best_single_encoder(connector);
@@ -1179,8 +1183,10 @@ radeon_tv_detect(struct drm_connector *connector, bool force)
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	encoder = radeon_best_single_encoder(connector);
@@ -1263,8 +1269,10 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (radeon_connector->detected_hpd_without_ddc) {
@@ -1704,8 +1712,10 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 
 	if (!drm_kms_helper_is_poll_worker()) {
 		r = pm_runtime_get_sync(connector->dev->dev);
-		if (r < 0)
+		if (r < 0) {
+			pm_runtime_put_autosuspend(connector->dev->dev);
 			return connector_status_disconnected;
+		}
 	}
 
 	if (!force && radeon_check_hpd_status_unchanged(connector)) {
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index d86110cdf085..b2334349799d 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -627,8 +627,10 @@ radeon_crtc_set_config(struct drm_mode_set *set,
 	dev = set->crtc->dev;
 
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	ret = drm_crtc_helper_set_config(set, ctx);
 
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index f4becad0a78c..41e8abd09978 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -424,7 +424,6 @@ static int radeon_pmops_runtime_suspend(struct device *dev)
 
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 	drm_kms_helper_poll_disable(drm_dev);
-	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_OFF);
 
 	ret = radeon_suspend_kms(drm_dev, false, false, false);
 	pci_save_state(pdev);
@@ -461,7 +460,6 @@ static int radeon_pmops_runtime_resume(struct device *dev)
 
 	ret = radeon_resume_kms(drm_dev, false, false);
 	drm_kms_helper_poll_enable(drm_dev);
-	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON);
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
 	return 0;
 }
@@ -498,8 +496,10 @@ long radeon_drm_ioctl(struct file *filp,
 	long ret;
 	dev = file_priv->minor->dev;
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	ret = drm_ioctl(filp, cmd, arg);
 	
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index dfee8f7d94ae..2e28cf811840 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -659,8 +659,10 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 	file_priv->driver_priv = NULL;
 
 	r = pm_runtime_get_sync(dev->dev);
-	if (r < 0)
+	if (r < 0) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return r;
+	}
 
 	/* new gpu have virtual address space support */
 	if (rdev->family >= CHIP_CAYMAN) {
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h
index a1f8cba251a2..3d9148eb40a7 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h
@@ -143,7 +143,7 @@
 #define SUN4I_HDMI_DDC_CMD_IMPLICIT_WRITE	3
 
 #define SUN4I_HDMI_DDC_CLK_REG		0x528
-#define SUN4I_HDMI_DDC_CLK_M(m)			(((m) & 0x7) << 3)
+#define SUN4I_HDMI_DDC_CLK_M(m)			(((m) & 0xf) << 3)
 #define SUN4I_HDMI_DDC_CLK_N(n)			((n) & 0x7)
 
 #define SUN4I_HDMI_DDC_LINE_CTRL_REG	0x540
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c
index 4692e8c345ed..58d9557a774f 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c
@@ -32,7 +32,7 @@ static unsigned long sun4i_ddc_calc_divider(unsigned long rate,
 	unsigned long best_rate = 0;
 	u8 best_m = 0, best_n = 0, _m, _n;
 
-	for (_m = 0; _m < 8; _m++) {
+	for (_m = 0; _m < 16; _m++) {
 		for (_n = 0; _n < 8; _n++) {
 			unsigned long tmp_rate;
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index 298d6a8bab12..c9f1a8cd5f2a 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -214,9 +214,8 @@ sun4i_hdmi_connector_detect(struct drm_connector *connector, bool force)
 	struct sun4i_hdmi *hdmi = drm_connector_to_sun4i_hdmi(connector);
 	unsigned long reg;
 
-	if (readl_poll_timeout(hdmi->base + SUN4I_HDMI_HPD_REG, reg,
-			       reg & SUN4I_HDMI_HPD_HIGH,
-			       0, 500000)) {
+	reg = readl(hdmi->base + SUN4I_HDMI_HPD_REG);
+	if (!(reg & SUN4I_HDMI_HPD_HIGH)) {
 		cec_phys_addr_invalidate(hdmi->cec_adap);
 		return connector_status_disconnected;
 	}
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index cb193c5f1686..519610e0bf66 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -235,7 +235,7 @@ static struct regmap_config sun8i_mixer_regmap_config = {
 	.reg_bits	= 32,
 	.val_bits	= 32,
 	.reg_stride	= 4,
-	.max_register	= 0xbfffc, /* guessed */
+	.max_register	= 0xffffc, /* guessed */
 };
 
 static int sun8i_mixer_bind(struct device *dev, struct device *master,
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
index 1813a3623ce6..0484b2cf0e2b 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
@@ -152,12 +152,16 @@ static int panel_connector_get_modes(struct drm_connector *connector)
 	int i;
 
 	for (i = 0; i < timings->num_timings; i++) {
-		struct drm_display_mode *mode = drm_mode_create(dev);
+		struct drm_display_mode *mode;
 		struct videomode vm;
 
 		if (videomode_from_timings(timings, &vm, i))
 			break;
 
+		mode = drm_mode_create(dev);
+		if (!mode)
+			break;
+
 		drm_display_mode_from_videomode(&vm, mode);
 
 		mode->type = DRM_MODE_TYPE_DRIVER;
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 8f71157a2b06..3020ae7a8f6b 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -1115,6 +1115,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *hdmi)
 	card->num_links = 1;
 	card->name = "vc4-hdmi";
 	card->dev = dev;
+	card->owner = THIS_MODULE;
 
 	/*
 	 * Be careful, snd_soc_register_card() calls dev_set_drvdata() and
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index aa592277d510..67037eb9a80e 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -220,32 +220,6 @@ static int vgem_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 	return 0;
 }
 
-static int vgem_gem_dumb_map(struct drm_file *file, struct drm_device *dev,
-			     uint32_t handle, uint64_t *offset)
-{
-	struct drm_gem_object *obj;
-	int ret;
-
-	obj = drm_gem_object_lookup(file, handle);
-	if (!obj)
-		return -ENOENT;
-
-	if (!obj->filp) {
-		ret = -EINVAL;
-		goto unref;
-	}
-
-	ret = drm_gem_create_mmap_offset(obj);
-	if (ret)
-		goto unref;
-
-	*offset = drm_vma_node_offset_addr(&obj->vma_node);
-unref:
-	drm_gem_object_put_unlocked(obj);
-
-	return ret;
-}
-
 static struct drm_ioctl_desc vgem_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(VGEM_FENCE_ATTACH, vgem_fence_attach_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(VGEM_FENCE_SIGNAL, vgem_fence_signal_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
@@ -439,7 +413,6 @@ static struct drm_driver vgem_driver = {
 	.fops				= &vgem_driver_fops,
 
 	.dumb_create			= vgem_gem_dumb_create,
-	.dumb_map_offset		= vgem_gem_dumb_map,
 
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 11f1c30ead54..848c9d009be2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -2707,7 +2707,7 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
 		++i;
 	}
 
-	if (i != unit) {
+	if (&con->head == &dev_priv->dev->mode_config.connector_list) {
 		DRM_ERROR("Could not find initial display unit.\n");
 		return -EINVAL;
 	}
@@ -2729,13 +2729,13 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
 			break;
 	}
 
-	if (mode->type & DRM_MODE_TYPE_PREFERRED)
-		*p_mode = mode;
-	else {
+	if (&mode->head == &con->modes) {
 		WARN_ONCE(true, "Could not find initial preferred mode.\n");
 		*p_mode = list_first_entry(&con->modes,
 					   struct drm_display_mode,
 					   head);
+	} else {
+		*p_mode = mode;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index 3824595fece1..39f4ad0dab8d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -79,7 +79,7 @@ static int vmw_ldu_commit_list(struct vmw_private *dev_priv)
 	struct vmw_legacy_display_unit *entry;
 	struct drm_framebuffer *fb = NULL;
 	struct drm_crtc *crtc = NULL;
-	int i = 0;
+	int i;
 
 	/* If there is no display topology the host just assumes
 	 * that the guest will set the same layout as the host.
@@ -90,12 +90,11 @@ static int vmw_ldu_commit_list(struct vmw_private *dev_priv)
 			crtc = &entry->base.crtc;
 			w = max(w, crtc->x + crtc->mode.hdisplay);
 			h = max(h, crtc->y + crtc->mode.vdisplay);
-			i++;
 		}
 
 		if (crtc == NULL)
 			return 0;
-		fb = entry->base.crtc.primary->state->fb;
+		fb = crtc->primary->state->fb;
 
 		return vmw_kms_write_svga(dev_priv, w, h, fb->pitches[0],
 					  fb->format->cpp[0] * 8,
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index f9cde03030fd..c2a9dcf6f490 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -615,8 +615,17 @@ EXPORT_SYMBOL(host1x_driver_register_full);
  */
 void host1x_driver_unregister(struct host1x_driver *driver)
 {
+	struct host1x *host1x;
+
 	driver_unregister(&driver->driver);
 
+	mutex_lock(&devices_lock);
+
+	list_for_each_entry(host1x, &devices, list)
+		host1x_detach_driver(host1x, driver);
+
+	mutex_unlock(&devices_lock);
+
 	mutex_lock(&drivers_lock);
 	list_del_init(&driver->list);
 	mutex_unlock(&drivers_lock);
diff --git a/drivers/gpu/host1x/debug.c b/drivers/gpu/host1x/debug.c
index 2aae0e63214c..0b8c23c399c2 100644
--- a/drivers/gpu/host1x/debug.c
+++ b/drivers/gpu/host1x/debug.c
@@ -25,6 +25,8 @@
 #include "debug.h"
 #include "channel.h"
 
+static DEFINE_MUTEX(debug_lock);
+
 unsigned int host1x_debug_trace_cmdbuf;
 
 static pid_t host1x_debug_force_timeout_pid;
@@ -49,12 +51,14 @@ static int show_channel(struct host1x_channel *ch, void *data, bool show_fifo)
 	struct output *o = data;
 
 	mutex_lock(&ch->cdma.lock);
+	mutex_lock(&debug_lock);
 
 	if (show_fifo)
 		host1x_hw_show_channel_fifo(m, ch, o);
 
 	host1x_hw_show_channel_cdma(m, ch, o);
 
+	mutex_unlock(&debug_lock);
 	mutex_unlock(&ch->cdma.lock);
 
 	return 0;
diff --git a/drivers/gpu/ipu-v3/ipu-image-convert.c b/drivers/gpu/ipu-v3/ipu-image-convert.c
index a5e33d58e02f..d2f9e6552267 100644
--- a/drivers/gpu/ipu-v3/ipu-image-convert.c
+++ b/drivers/gpu/ipu-v3/ipu-image-convert.c
@@ -992,9 +992,10 @@ done:
 	return IRQ_WAKE_THREAD;
 }
 
-static irqreturn_t norotate_irq(int irq, void *data)
+static irqreturn_t eof_irq(int irq, void *data)
 {
 	struct ipu_image_convert_chan *chan = data;
+	struct ipu_image_convert_priv *priv = chan->priv;
 	struct ipu_image_convert_ctx *ctx;
 	struct ipu_image_convert_run *run;
 	unsigned long flags;
@@ -1011,45 +1012,26 @@ static irqreturn_t norotate_irq(int irq, void *data)
 
 	ctx = run->ctx;
 
-	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
-		/* this is a rotation operation, just ignore */
-		spin_unlock_irqrestore(&chan->irqlock, flags);
-		return IRQ_HANDLED;
-	}
-
-	ret = do_irq(run);
-out:
-	spin_unlock_irqrestore(&chan->irqlock, flags);
-	return ret;
-}
-
-static irqreturn_t rotate_irq(int irq, void *data)
-{
-	struct ipu_image_convert_chan *chan = data;
-	struct ipu_image_convert_priv *priv = chan->priv;
-	struct ipu_image_convert_ctx *ctx;
-	struct ipu_image_convert_run *run;
-	unsigned long flags;
-	irqreturn_t ret;
-
-	spin_lock_irqsave(&chan->irqlock, flags);
-
-	/* get current run and its context */
-	run = chan->current_run;
-	if (!run) {
+	if (irq == chan->out_eof_irq) {
+		if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
+			/* this is a rotation op, just ignore */
+			ret = IRQ_HANDLED;
+			goto out;
+		}
+	} else if (irq == chan->rot_out_eof_irq) {
+		if (!ipu_rot_mode_is_irt(ctx->rot_mode)) {
+			/* this was NOT a rotation op, shouldn't happen */
+			dev_err(priv->ipu->dev,
+				"Unexpected rotation interrupt\n");
+			ret = IRQ_HANDLED;
+			goto out;
+		}
+	} else {
+		dev_err(priv->ipu->dev, "Received unknown irq %d\n", irq);
 		ret = IRQ_NONE;
 		goto out;
 	}
 
-	ctx = run->ctx;
-
-	if (!ipu_rot_mode_is_irt(ctx->rot_mode)) {
-		/* this was NOT a rotation operation, shouldn't happen */
-		dev_err(priv->ipu->dev, "Unexpected rotation interrupt\n");
-		spin_unlock_irqrestore(&chan->irqlock, flags);
-		return IRQ_HANDLED;
-	}
-
 	ret = do_irq(run);
 out:
 	spin_unlock_irqrestore(&chan->irqlock, flags);
@@ -1142,7 +1124,7 @@ static int get_ipu_resources(struct ipu_image_convert_chan *chan)
 						  chan->out_chan,
 						  IPU_IRQ_EOF);
 
-	ret = request_threaded_irq(chan->out_eof_irq, norotate_irq, do_bh,
+	ret = request_threaded_irq(chan->out_eof_irq, eof_irq, do_bh,
 				   0, "ipu-ic", chan);
 	if (ret < 0) {
 		dev_err(priv->ipu->dev, "could not acquire irq %d\n",
@@ -1155,7 +1137,7 @@ static int get_ipu_resources(struct ipu_image_convert_chan *chan)
 						     chan->rotation_out_chan,
 						     IPU_IRQ_EOF);
 
-	ret = request_threaded_irq(chan->rot_out_eof_irq, rotate_irq, do_bh,
+	ret = request_threaded_irq(chan->rot_out_eof_irq, eof_irq, do_bh,
 				   0, "ipu-ic", chan);
 	if (ret < 0) {
 		dev_err(priv->ipu->dev, "could not acquire irq %d\n",
diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index 3cd153c6d271..f188c85b3b7a 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -92,7 +92,8 @@
  * struct vga_switcheroo_client - registered client
  * @pdev: client pci device
  * @fb_info: framebuffer to which console is remapped on switching
- * @pwr_state: current power state
+ * @pwr_state: current power state if manual power control is used.
+ *	For driver power control, call vga_switcheroo_pwr_state().
  * @ops: client callbacks
  * @id: client identifier. Determining the id requires the handler,
  *	so gpus are initially assigned VGA_SWITCHEROO_UNKNOWN_ID
@@ -104,8 +105,7 @@
  * @list: client list
  *
  * Registered client. A client can be either a GPU or an audio device on a GPU.
- * For audio clients, the @fb_info, @active and @driver_power_control members
- * are bogus.
+ * For audio clients, the @fb_info and @active members are bogus.
  */
 struct vga_switcheroo_client {
 	struct pci_dev *pdev;
@@ -331,8 +331,8 @@ EXPORT_SYMBOL(vga_switcheroo_register_client);
  * @ops: client callbacks
  * @id: client identifier
  *
- * Register audio client (audio device on a GPU). The power state of the
- * client is assumed to be ON. Beforehand, vga_switcheroo_client_probe_defer()
+ * Register audio client (audio device on a GPU). The client is assumed
+ * to use runtime PM. Beforehand, vga_switcheroo_client_probe_defer()
  * shall be called to ensure that all prerequisites are met.
  *
  * Return: 0 on success, -ENOMEM on memory allocation error.
@@ -341,7 +341,7 @@ int vga_switcheroo_register_audio_client(struct pci_dev *pdev,
 			const struct vga_switcheroo_client_ops *ops,
 			enum vga_switcheroo_client_id id)
 {
-	return register_client(pdev, ops, id | ID_BIT_AUDIO, false, false);
+	return register_client(pdev, ops, id | ID_BIT_AUDIO, false, true);
 }
 EXPORT_SYMBOL(vga_switcheroo_register_audio_client);
 
@@ -406,6 +406,19 @@ bool vga_switcheroo_client_probe_defer(struct pci_dev *pdev)
 }
 EXPORT_SYMBOL(vga_switcheroo_client_probe_defer);
 
+static enum vga_switcheroo_state
+vga_switcheroo_pwr_state(struct vga_switcheroo_client *client)
+{
+	if (client->driver_power_control)
+		if (pm_runtime_enabled(&client->pdev->dev) &&
+		    pm_runtime_active(&client->pdev->dev))
+			return VGA_SWITCHEROO_ON;
+		else
+			return VGA_SWITCHEROO_OFF;
+	else
+		return client->pwr_state;
+}
+
 /**
  * vga_switcheroo_get_client_state() - obtain power state of a given client
  * @pdev: client pci device
@@ -425,7 +438,7 @@ enum vga_switcheroo_state vga_switcheroo_get_client_state(struct pci_dev *pdev)
 	if (!client)
 		ret = VGA_SWITCHEROO_NOT_FOUND;
 	else
-		ret = client->pwr_state;
+		ret = vga_switcheroo_pwr_state(client);
 	mutex_unlock(&vgasr_mutex);
 	return ret;
 }
@@ -598,7 +611,7 @@ static int vga_switcheroo_show(struct seq_file *m, void *v)
 			   client_is_vga(client) ? "" : "-Audio",
 			   client->active ? '+' : ' ',
 			   client->driver_power_control ? "Dyn" : "",
-			   client->pwr_state ? "Pwr" : "Off",
+			   vga_switcheroo_pwr_state(client) ? "Pwr" : "Off",
 			   pci_name(client->pdev));
 		i++;
 	}
@@ -641,10 +654,8 @@ static void set_audio_state(enum vga_switcheroo_client_id id,
 	struct vga_switcheroo_client *client;
 
 	client = find_client_from_id(&vgasr_priv.clients, id | ID_BIT_AUDIO);
-	if (client && client->pwr_state != state) {
+	if (client)
 		client->ops->set_gpu_state(client->pdev, state);
-		client->pwr_state = state;
-	}
 }
 
 /* stage one happens before delay */
@@ -656,7 +667,7 @@ static int vga_switchto_stage1(struct vga_switcheroo_client *new_client)
 	if (!active)
 		return 0;
 
-	if (new_client->pwr_state == VGA_SWITCHEROO_OFF)
+	if (vga_switcheroo_pwr_state(new_client) == VGA_SWITCHEROO_OFF)
 		vga_switchon(new_client);
 
 	vga_set_default_device(new_client->pdev);
@@ -695,7 +706,7 @@ static int vga_switchto_stage2(struct vga_switcheroo_client *new_client)
 	if (new_client->ops->reprobe)
 		new_client->ops->reprobe(new_client->pdev);
 
-	if (active->pwr_state == VGA_SWITCHEROO_ON)
+	if (vga_switcheroo_pwr_state(active) == VGA_SWITCHEROO_ON)
 		vga_switchoff(active);
 
 	set_audio_state(new_client->id, VGA_SWITCHEROO_ON);
@@ -939,11 +950,6 @@ EXPORT_SYMBOL(vga_switcheroo_process_delayed_switch);
  * Specifying nouveau.runpm=0, radeon.runpm=0 or amdgpu.runpm=0 on the kernel
  * command line disables it.
  *
- * When the driver decides to power up or down, it notifies vga_switcheroo
- * thereof so that it can (a) power the audio device on the GPU up or down,
- * and (b) update its internal power state representation for the device.
- * This is achieved by vga_switcheroo_set_dynamic_switch().
- *
  * After the GPU has been suspended, the handler needs to be called to cut
  * power to the GPU. Likewise it needs to reinstate power before the GPU
  * can resume. This is achieved by vga_switcheroo_init_domain_pm_ops(),
@@ -951,8 +957,9 @@ EXPORT_SYMBOL(vga_switcheroo_process_delayed_switch);
  * calls to the handler.
  *
  * When the audio device resumes, the GPU needs to be woken. This is achieved
- * by vga_switcheroo_init_domain_pm_optimus_hdmi_audio(), which augments the
- * audio device's resume function.
+ * by a PCI quirk which calls device_link_add() to declare a dependency on the
+ * GPU. That way, the GPU is kept awake whenever and as long as the audio
+ * device is in use.
  *
  * On muxed machines, if the mux is initially switched to the discrete GPU,
  * the user ends up with a black screen when the GPU powers down after boot.
@@ -978,35 +985,6 @@ static void vga_switcheroo_power_switch(struct pci_dev *pdev,
 	vgasr_priv.handler->power_state(client->id, state);
 }
 
-/**
- * vga_switcheroo_set_dynamic_switch() - helper for driver power control
- * @pdev: client pci device
- * @dynamic: new power state
- *
- * Helper for GPUs whose power state is controlled by the driver's runtime pm.
- * When the driver decides to power up or down, it notifies vga_switcheroo
- * thereof using this helper so that it can (a) power the audio device on
- * the GPU up or down, and (b) update its internal power state representation
- * for the device.
- */
-void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev,
-				       enum vga_switcheroo_state dynamic)
-{
-	struct vga_switcheroo_client *client;
-
-	mutex_lock(&vgasr_mutex);
-	client = find_client_from_pci(&vgasr_priv.clients, pdev);
-	if (!client || !client->driver_power_control) {
-		mutex_unlock(&vgasr_mutex);
-		return;
-	}
-
-	client->pwr_state = dynamic;
-	set_audio_state(client->id, dynamic);
-	mutex_unlock(&vgasr_mutex);
-}
-EXPORT_SYMBOL(vga_switcheroo_set_dynamic_switch);
-
 /* switcheroo power domain */
 static int vga_switcheroo_runtime_suspend(struct device *dev)
 {
@@ -1076,69 +1054,3 @@ void vga_switcheroo_fini_domain_pm_ops(struct device *dev)
 	dev_pm_domain_set(dev, NULL);
 }
 EXPORT_SYMBOL(vga_switcheroo_fini_domain_pm_ops);
-
-static int vga_switcheroo_runtime_resume_hdmi_audio(struct device *dev)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct vga_switcheroo_client *client;
-	struct device *video_dev = NULL;
-	int ret;
-
-	/* we need to check if we have to switch back on the video
-	 * device so the audio device can come back
-	 */
-	mutex_lock(&vgasr_mutex);
-	list_for_each_entry(client, &vgasr_priv.clients, list) {
-		if (PCI_SLOT(client->pdev->devfn) == PCI_SLOT(pdev->devfn) &&
-		    client_is_vga(client)) {
-			video_dev = &client->pdev->dev;
-			break;
-		}
-	}
-	mutex_unlock(&vgasr_mutex);
-
-	if (video_dev) {
-		ret = pm_runtime_get_sync(video_dev);
-		if (ret && ret != 1)
-			return ret;
-	}
-	ret = dev->bus->pm->runtime_resume(dev);
-
-	/* put the reference for the gpu */
-	if (video_dev) {
-		pm_runtime_mark_last_busy(video_dev);
-		pm_runtime_put_autosuspend(video_dev);
-	}
-	return ret;
-}
-
-/**
- * vga_switcheroo_init_domain_pm_optimus_hdmi_audio() - helper for driver
- *	power control
- * @dev: audio client device
- * @domain: power domain
- *
- * Helper for GPUs whose power state is controlled by the driver's runtime pm.
- * When the audio device resumes, the GPU needs to be woken. This helper
- * augments the audio device's resume function to do that.
- *
- * Return: 0 on success, -EINVAL if no power management operations are
- * defined for this device.
- */
-int
-vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev,
-						 struct dev_pm_domain *domain)
-{
-	/* copy over all the bus versions */
-	if (dev->bus && dev->bus->pm) {
-		domain->ops = *dev->bus->pm;
-		domain->ops.runtime_resume =
-			vga_switcheroo_runtime_resume_hdmi_audio;
-
-		dev_pm_domain_set(dev, domain);
-		return 0;
-	}
-	dev_pm_domain_set(dev, NULL);
-	return -EINVAL;
-}
-EXPORT_SYMBOL(vga_switcheroo_init_domain_pm_optimus_hdmi_audio);
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 8ab8f2350bbc..b58ab769aa7b 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -57,6 +57,7 @@ MODULE_PARM_DESC(swap_opt_cmd, "Swap the Option (\"Alt\") and Command (\"Flag\")
 struct apple_sc {
 	unsigned long quirks;
 	unsigned int fn_on;
+	unsigned int fn_found;
 	DECLARE_BITMAP(pressed_numlock, KEY_CNT);
 };
 
@@ -342,12 +343,15 @@ static int apple_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 		struct hid_field *field, struct hid_usage *usage,
 		unsigned long **bit, int *max)
 {
+	struct apple_sc *asc = hid_get_drvdata(hdev);
+
 	if (usage->hid == (HID_UP_CUSTOM | 0x0003) ||
 			usage->hid == (HID_UP_MSVENDOR | 0x0003) ||
 			usage->hid == (HID_UP_HPVENDOR2 | 0x0003)) {
 		/* The fn key on Apple USB keyboards */
 		set_bit(EV_REP, hi->input->evbit);
 		hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_FN);
+		asc->fn_found = true;
 		apple_setup_input(hi->input);
 		return 1;
 	}
@@ -374,6 +378,19 @@ static int apple_input_mapped(struct hid_device *hdev, struct hid_input *hi,
 	return 0;
 }
 
+static int apple_input_configured(struct hid_device *hdev,
+		struct hid_input *hidinput)
+{
+	struct apple_sc *asc = hid_get_drvdata(hdev);
+
+	if ((asc->quirks & APPLE_HAS_FN) && !asc->fn_found) {
+		hid_info(hdev, "Fn key not found (Apple Wireless Keyboard clone?), disabling Fn key handling\n");
+		asc->quirks = 0;
+	}
+
+	return 0;
+}
+
 static int apple_probe(struct hid_device *hdev,
 		const struct hid_device_id *id)
 {
@@ -588,6 +605,7 @@ static struct hid_driver apple_driver = {
 	.event = apple_event,
 	.input_mapping = apple_input_mapping,
 	.input_mapped = apple_input_mapped,
+	.input_configured = apple_input_configured,
 };
 module_hid_driver(apple_driver);
 
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 75b0a337114d..ff6e327cbd02 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1427,6 +1427,17 @@ static void hid_output_field(const struct hid_device *hid,
 }
 
 /*
+ * Compute the size of a report.
+ */
+static size_t hid_compute_report_size(struct hid_report *report)
+{
+	if (report->size)
+		return ((report->size - 1) >> 3) + 1;
+
+	return 0;
+}
+
+/*
  * Create a report. 'data' has to be allocated using
  * hid_alloc_report_buf() so that it has proper size.
  */
@@ -1438,7 +1449,7 @@ void hid_output_report(struct hid_report *report, __u8 *data)
 	if (report->id > 0)
 		*data++ = report->id;
 
-	memset(data, 0, ((report->size - 1) >> 3) + 1);
+	memset(data, 0, hid_compute_report_size(report));
 	for (n = 0; n < report->maxfield; n++)
 		hid_output_field(report->device, report->field[n], data);
 }
@@ -1565,7 +1576,7 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size,
 		csize--;
 	}
 
-	rsize = ((report->size - 1) >> 3) + 1;
+	rsize = hid_compute_report_size(report);
 
 	if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE)
 		rsize = HID_MAX_BUFFER_SIZE - 1;
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 14e4003fde4d..3624d6e3384f 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -362,13 +362,13 @@ static int hidinput_query_battery_capacity(struct hid_device *dev)
 	u8 *buf;
 	int ret;
 
-	buf = kmalloc(2, GFP_KERNEL);
+	buf = kmalloc(4, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 2,
+	ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 4,
 				 dev->battery_report_type, HID_REQ_GET_REPORT);
-	if (ret != 2) {
+	if (ret < 2) {
 		kfree(buf);
 		return -ENODATA;
 	}
@@ -1116,6 +1116,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 	}
 
 mapped:
+	/* Mapping failed, bail out */
+	if (!bit)
+		return;
+
 	if (device->driver->input_mapped &&
 	    device->driver->input_mapped(device, hidinput, field, usage,
 					 &bit, &max) < 0) {
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 20b40ad26325..8c993f95e3ba 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -451,6 +451,12 @@ static int magicmouse_setup_input(struct input_dev *input, struct hid_device *hd
 		__set_bit(MSC_RAW, input->mscbit);
 	}
 
+	/*
+	 * hid-input may mark device as using autorepeat, but neither
+	 * the trackpad, nor the mouse actually want it.
+	 */
+	__clear_bit(EV_REP, input->evbit);
+
 	return 0;
 }
 
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index db29bf539a4b..ac31998f93a8 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -616,6 +616,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 		    (usage->hid & HID_USAGE) > 1)
 			code--;
 		hid_map_usage(hi, usage, bit, max, EV_KEY, code);
+		if (!*bit)
+			return -1;
 		input_set_capability(hi->input, EV_KEY, code);
 		return 1;
 
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index c8b07a182c0b..f8fb8a61fb90 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -837,6 +837,23 @@ static u8 *sony_report_fixup(struct hid_device *hdev, u8 *rdesc,
 	if (sc->quirks & PS3REMOTE)
 		return ps3remote_fixup(hdev, rdesc, rsize);
 
+	/*
+	 * Some knock-off USB dongles incorrectly report their button count
+	 * as 13 instead of 16 causing three non-functional buttons.
+	 */
+	if ((sc->quirks & SIXAXIS_CONTROLLER_USB) && *rsize >= 45 &&
+		/* Report Count (13) */
+		rdesc[23] == 0x95 && rdesc[24] == 0x0D &&
+		/* Usage Maximum (13) */
+		rdesc[37] == 0x29 && rdesc[38] == 0x0D &&
+		/* Report Count (3) */
+		rdesc[43] == 0x95 && rdesc[44] == 0x03) {
+		hid_info(hdev, "Fixing up USB dongle report descriptor\n");
+		rdesc[24] = 0x10;
+		rdesc[38] = 0x10;
+		rdesc[44] = 0x00;
+	}
+
 	return rdesc;
 }
 
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 7842d76aa813..0294cac4c856 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -406,6 +406,19 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state)
 		dev_err(&client->dev, "failed to change power setting.\n");
 
 set_pwr_exit:
+
+	/*
+	 * The HID over I2C specification states that if a DEVICE needs time
+	 * after the PWR_ON request, it should utilise CLOCK stretching.
+	 * However, it has been observered that the Windows driver provides a
+	 * 1ms sleep between the PWR_ON and RESET requests.
+	 * According to Goodix Windows even waits 60 ms after (other?)
+	 * PWR_ON requests. Testing has confirmed that several devices
+	 * will not work properly without a delay after a PWR_ON request.
+	 */
+	if (!ret && power_state == I2C_HID_PWR_ON)
+		msleep(60);
+
 	return ret;
 }
 
@@ -427,15 +440,6 @@ static int i2c_hid_hwreset(struct i2c_client *client)
 	if (ret)
 		goto out_unlock;
 
-	/*
-	 * The HID over I2C specification states that if a DEVICE needs time
-	 * after the PWR_ON request, it should utilise CLOCK stretching.
-	 * However, it has been observered that the Windows driver provides a
-	 * 1ms sleep between the PWR_ON and RESET requests and that some devices
-	 * rely on this.
-	 */
-	usleep_range(1000, 5000);
-
 	i2c_hid_dbg(ihid, "resetting...\n");
 
 	ret = i2c_hid_command(client, &hid_reset_cmd, NULL, 0);
diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
index 95052373a828..f98c1e1b1dbd 100644
--- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
+++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
@@ -374,6 +374,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = {
 		.driver_data = (void *)&sipodev_desc
 	},
 	{
+		.ident = "Mediacom FlexBook edge 13",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "MEDIACOM"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "FlexBook_edge13-M-FBE13"),
+		},
+		.driver_data = (void *)&sipodev_desc
+	},
+	{
 		.ident = "Odys Winbook 13",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AXDIA International GmbH"),
@@ -381,6 +389,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = {
 		},
 		.driver_data = (void *)&sipodev_desc
 	},
+	{
+		.ident = "Schneider SCL142ALM",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SCHNEIDER"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SCL142ALM"),
+		},
+		.driver_data = (void *)&sipodev_desc
+	},
 	{ }	/* Terminate list */
 };
 
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index d9602f3a359e..5f56feb468c1 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -532,12 +532,16 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd,
 
 		switch (cmd) {
 		case HIDIOCGUSAGE:
+			if (uref->usage_index >= field->report_count)
+				goto inval;
 			uref->value = field->value[uref->usage_index];
 			if (copy_to_user(user_arg, uref, sizeof(*uref)))
 				goto fault;
 			goto goodreturn;
 
 		case HIDIOCSUSAGE:
+			if (uref->usage_index >= field->report_count)
+				goto inval;
 			field->value[uref->usage_index] = uref->value;
 			goto goodreturn;
 
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 43eaf54736f4..5bf633c15cd4 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -774,7 +774,7 @@ static void vmbus_wait_for_unload(void)
 	void *page_addr;
 	struct hv_message *msg;
 	struct vmbus_channel_message_header *hdr;
-	u32 message_type;
+	u32 message_type, i;
 
 	/*
 	 * CHANNELMSG_UNLOAD_RESPONSE is always delivered to the CPU which was
@@ -784,8 +784,11 @@ static void vmbus_wait_for_unload(void)
 	 * functional and vmbus_unload_response() will complete
 	 * vmbus_connection.unload_event. If not, the last thing we can do is
 	 * read message pages for all CPUs directly.
+	 *
+	 * Wait no more than 10 seconds so that the panic path can't get
+	 * hung forever in case the response message isn't seen.
 	 */
-	while (1) {
+	for (i = 0; i < 1000; i++) {
 		if (completion_done(&vmbus_connection.unload_event))
 			break;
 
@@ -1228,6 +1231,8 @@ channel_message_table[CHANNELMSG_COUNT] = {
 	{ CHANNELMSG_19,			0, NULL },
 	{ CHANNELMSG_20,			0, NULL },
 	{ CHANNELMSG_TL_CONNECT_REQUEST,	0, NULL },
+	{ CHANNELMSG_22,			0, NULL },
+	{ CHANNELMSG_TL_CONNECT_RESULT,		0, NULL },
 };
 
 /*
@@ -1239,23 +1244,14 @@ void vmbus_onmessage(void *context)
 {
 	struct hv_message *msg = context;
 	struct vmbus_channel_message_header *hdr;
-	int size;
 
 	hdr = (struct vmbus_channel_message_header *)msg->u.payload;
-	size = msg->header.payload_size;
-
-	if (hdr->msgtype >= CHANNELMSG_COUNT) {
-		pr_err("Received invalid channel message type %d size %d\n",
-			   hdr->msgtype, size);
-		print_hex_dump_bytes("", DUMP_PREFIX_NONE,
-				     (unsigned char *)msg->u.payload, size);
-		return;
-	}
 
-	if (channel_message_table[hdr->msgtype].message_handler)
-		channel_message_table[hdr->msgtype].message_handler(hdr);
-	else
-		pr_err("Unhandled channel message type %d\n", hdr->msgtype);
+	/*
+	 * vmbus_on_msg_dpc() makes sure the hdr->msgtype here can not go
+	 * out of bound and the message_handler pointer can not be NULL.
+	 */
+	channel_message_table[hdr->msgtype].message_handler(hdr);
 }
 
 /*
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 1fd812ed679b..45b8ccdfb085 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -890,6 +890,10 @@ void vmbus_on_msg_dpc(unsigned long data)
 	}
 
 	entry = &channel_message_table[hdr->msgtype];
+
+	if (!entry->message_handler)
+		goto msg_handled;
+
 	if (entry->handler_type	== VMHT_BLOCKING) {
 		ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
 		if (ctx == NULL)
diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c
index ba3af4505d8f..e40d8907853b 100644
--- a/drivers/hwmon/acpi_power_meter.c
+++ b/drivers/hwmon/acpi_power_meter.c
@@ -895,7 +895,7 @@ static int acpi_power_meter_add(struct acpi_device *device)
 
 	res = setup_attrs(resource);
 	if (res)
-		goto exit_free;
+		goto exit_free_capability;
 
 	resource->hwmon_dev = hwmon_device_register(&device->dev);
 	if (IS_ERR(resource->hwmon_dev)) {
@@ -908,6 +908,8 @@ static int acpi_power_meter_add(struct acpi_device *device)
 
 exit_remove:
 	remove_attrs(resource);
+exit_free_capability:
+	free_capabilities(resource);
 exit_free:
 	kfree(resource);
 exit:
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index 5c677ba44014..b201129a9bea 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -760,15 +760,18 @@ static ssize_t applesmc_light_show(struct device *dev,
 	}
 
 	ret = applesmc_read_key(LIGHT_SENSOR_LEFT_KEY, buffer, data_length);
+	if (ret)
+		goto out;
 	/* newer macbooks report a single 10-bit bigendian value */
 	if (data_length == 10) {
 		left = be16_to_cpu(*(__be16 *)(buffer + 6)) >> 2;
 		goto out;
 	}
 	left = buffer[2];
+
+	ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length);
 	if (ret)
 		goto out;
-	ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length);
 	right = buffer[2];
 
 out:
@@ -817,12 +820,11 @@ static ssize_t applesmc_show_fan_speed(struct device *dev,
 		  to_index(attr));
 
 	ret = applesmc_read_key(newkey, buffer, 2);
-	speed = ((buffer[0] << 8 | buffer[1]) >> 2);
-
 	if (ret)
 		return ret;
-	else
-		return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed);
+
+	speed = ((buffer[0] << 8 | buffer[1]) >> 2);
+	return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed);
 }
 
 static ssize_t applesmc_store_fan_speed(struct device *dev,
@@ -858,12 +860,11 @@ static ssize_t applesmc_show_fan_manual(struct device *dev,
 	u8 buffer[2];
 
 	ret = applesmc_read_key(FANS_MANUAL, buffer, 2);
-	manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01;
-
 	if (ret)
 		return ret;
-	else
-		return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual);
+
+	manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01;
+	return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual);
 }
 
 static ssize_t applesmc_store_fan_manual(struct device *dev,
@@ -879,10 +880,11 @@ static ssize_t applesmc_store_fan_manual(struct device *dev,
 		return -EINVAL;
 
 	ret = applesmc_read_key(FANS_MANUAL, buffer, 2);
-	val = (buffer[0] << 8 | buffer[1]);
 	if (ret)
 		goto out;
 
+	val = (buffer[0] << 8 | buffer[1]);
+
 	if (input)
 		val = val | (0x01 << to_index(attr));
 	else
@@ -958,13 +960,12 @@ static ssize_t applesmc_key_count_show(struct device *dev,
 	u32 count;
 
 	ret = applesmc_read_key(KEY_COUNT_KEY, buffer, 4);
-	count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) +
-						((u32)buffer[2]<<8) + buffer[3];
-
 	if (ret)
 		return ret;
-	else
-		return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count);
+
+	count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) +
+						((u32)buffer[2]<<8) + buffer[3];
+	return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count);
 }
 
 static ssize_t applesmc_key_at_index_read_show(struct device *dev,
diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c
index 69b97d45e3cb..e4337e9dda44 100644
--- a/drivers/hwmon/aspeed-pwm-tacho.c
+++ b/drivers/hwmon/aspeed-pwm-tacho.c
@@ -878,6 +878,8 @@ static int aspeed_create_fan(struct device *dev,
 	ret = of_property_read_u32(child, "reg", &pwm_port);
 	if (ret)
 		return ret;
+	if (pwm_port >= ARRAY_SIZE(pwm_port_params))
+		return -EINVAL;
 	aspeed_create_pwm_port(priv, (u8)pwm_port);
 
 	ret = of_property_count_u8_elems(child, "cooling-levels");
diff --git a/drivers/hwmon/emc2103.c b/drivers/hwmon/emc2103.c
index 1ed9a7aa953d..f4985622b179 100644
--- a/drivers/hwmon/emc2103.c
+++ b/drivers/hwmon/emc2103.c
@@ -454,7 +454,7 @@ static ssize_t pwm1_enable_store(struct device *dev,
 	}
 
 	result = read_u8_from_i2c(client, REG_FAN_CONF1, &conf_reg);
-	if (result) {
+	if (result < 0) {
 		count = result;
 		goto err;
 	}
diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c
index 221fd1492057..6df28fe0577d 100644
--- a/drivers/hwmon/max6697.c
+++ b/drivers/hwmon/max6697.c
@@ -47,8 +47,9 @@ static const u8 MAX6697_REG_CRIT[] = {
  * Map device tree / platform data register bit map to chip bit map.
  * Applies to alert register and over-temperature register.
  */
-#define MAX6697_MAP_BITS(reg)	((((reg) & 0x7e) >> 1) | \
+#define MAX6697_ALERT_MAP_BITS(reg)	((((reg) & 0x7e) >> 1) | \
 				 (((reg) & 0x01) << 6) | ((reg) & 0x80))
+#define MAX6697_OVERT_MAP_BITS(reg) (((reg) >> 1) | (((reg) & 0x01) << 7))
 
 #define MAX6697_REG_STAT(n)		(0x44 + (n))
 
@@ -587,12 +588,12 @@ static int max6697_init_chip(struct max6697_data *data,
 		return ret;
 
 	ret = i2c_smbus_write_byte_data(client, MAX6697_REG_ALERT_MASK,
-					MAX6697_MAP_BITS(pdata->alert_mask));
+				MAX6697_ALERT_MAP_BITS(pdata->alert_mask));
 	if (ret < 0)
 		return ret;
 
 	ret = i2c_smbus_write_byte_data(client, MAX6697_REG_OVERT_MASK,
-				MAX6697_MAP_BITS(pdata->over_temperature_mask));
+			MAX6697_OVERT_MAP_BITS(pdata->over_temperature_mask));
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
index 0a00f4e941fb..9bddbfbfbe03 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
@@ -587,15 +587,14 @@ int tmc_read_unprepare_etb(struct tmc_drvdata *drvdata)
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 
-	/* There is no point in reading a TMC in HW FIFO mode */
-	mode = readl_relaxed(drvdata->base + TMC_MODE);
-	if (mode != TMC_MODE_CIRCULAR_BUFFER) {
-		spin_unlock_irqrestore(&drvdata->spinlock, flags);
-		return -EINVAL;
-	}
-
 	/* Re-enable the TMC if need be */
 	if (drvdata->mode == CS_MODE_SYSFS) {
+		/* There is no point in reading a TMC in HW FIFO mode */
+		mode = readl_relaxed(drvdata->base + TMC_MODE);
+		if (mode != TMC_MODE_CIRCULAR_BUFFER) {
+			spin_unlock_irqrestore(&drvdata->spinlock, flags);
+			return -EINVAL;
+		}
 		/*
 		 * The trace run will continue with the same allocated trace
 		 * buffer. As such zero-out the buffer so that we don't end
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index b8cbd26b60e1..99ef61de9b1e 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -214,11 +214,21 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
 	{
+		/* Tiger Lake PCH-H */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x43a6),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
 		/* Jasper Lake PCH */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
 	{
+		/* Jasper Lake CPU */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4e29),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
 		/* Elkhart Lake CPU */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4529),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
@@ -228,6 +238,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4b26),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Emmitsburg PCH */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x1bcc),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{ 0 },
 };
 
diff --git a/drivers/i2c/algos/i2c-algo-pca.c b/drivers/i2c/algos/i2c-algo-pca.c
index e370804ec8bc..1886588b9ea3 100644
--- a/drivers/i2c/algos/i2c-algo-pca.c
+++ b/drivers/i2c/algos/i2c-algo-pca.c
@@ -50,8 +50,22 @@ static void pca_reset(struct i2c_algo_pca_data *adap)
 		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_IPRESET);
 		pca_outw(adap, I2C_PCA_IND, 0xA5);
 		pca_outw(adap, I2C_PCA_IND, 0x5A);
+
+		/*
+		 * After a reset we need to re-apply any configuration
+		 * (calculated in pca_init) to get the bus in a working state.
+		 */
+		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_IMODE);
+		pca_outw(adap, I2C_PCA_IND, adap->bus_settings.mode);
+		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_ISCLL);
+		pca_outw(adap, I2C_PCA_IND, adap->bus_settings.tlow);
+		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_ISCLH);
+		pca_outw(adap, I2C_PCA_IND, adap->bus_settings.thi);
+
+		pca_set_con(adap, I2C_PCA_CON_ENSIO);
 	} else {
 		adap->reset_chip(adap->data);
+		pca_set_con(adap, I2C_PCA_CON_ENSIO | adap->bus_settings.clock_freq);
 	}
 }
 
@@ -326,7 +340,8 @@ static int pca_xfer(struct i2c_adapter *i2c_adap,
 			DEB2("BUS ERROR - SDA Stuck low\n");
 			pca_reset(adap);
 			goto out;
-		case 0x90: /* Bus error - SCL stuck low */
+		case 0x78: /* Bus error - SCL stuck low (PCA9665) */
+		case 0x90: /* Bus error - SCL stuck low (PCA9564) */
 			DEB2("BUS ERROR - SCL Stuck low\n");
 			pca_reset(adap);
 			goto out;
@@ -434,13 +449,14 @@ static int pca_init(struct i2c_adapter *adap)
 				" Use the nominal frequency.\n", adap->name);
 		}
 
-		pca_reset(pca_data);
-
 		clock = pca_clock(pca_data);
 		printk(KERN_INFO "%s: Clock frequency is %dkHz\n",
 		     adap->name, freqs[clock]);
 
-		pca_set_con(pca_data, I2C_PCA_CON_ENSIO | clock);
+		/* Store settings as these will be needed when the PCA chip is reset */
+		pca_data->bus_settings.clock_freq = clock;
+
+		pca_reset(pca_data);
 	} else {
 		int clock;
 		int mode;
@@ -507,19 +523,15 @@ static int pca_init(struct i2c_adapter *adap)
 			thi = tlow * min_thi / min_tlow;
 		}
 
+		/* Store settings as these will be needed when the PCA chip is reset */
+		pca_data->bus_settings.mode = mode;
+		pca_data->bus_settings.tlow = tlow;
+		pca_data->bus_settings.thi = thi;
+
 		pca_reset(pca_data);
 
 		printk(KERN_INFO
 		     "%s: Clock frequency is %dHz\n", adap->name, clock * 100);
-
-		pca_outw(pca_data, I2C_PCA_INDPTR, I2C_PCA_IMODE);
-		pca_outw(pca_data, I2C_PCA_IND, mode);
-		pca_outw(pca_data, I2C_PCA_INDPTR, I2C_PCA_ISCLL);
-		pca_outw(pca_data, I2C_PCA_IND, tlow);
-		pca_outw(pca_data, I2C_PCA_INDPTR, I2C_PCA_ISCLH);
-		pca_outw(pca_data, I2C_PCA_IND, thi);
-
-		pca_set_con(pca_data, I2C_PCA_CON_ENSIO);
 	}
 	udelay(500); /* 500 us for oscillator to stabilise */
 
diff --git a/drivers/i2c/busses/i2c-altera.c b/drivers/i2c/busses/i2c-altera.c
index 8915ee30a5b4..1d59eede537b 100644
--- a/drivers/i2c/busses/i2c-altera.c
+++ b/drivers/i2c/busses/i2c-altera.c
@@ -81,6 +81,7 @@
  * @isr_mask: cached copy of local ISR enables.
  * @isr_status: cached copy of local ISR status.
  * @lock: spinlock for IRQ synchronization.
+ * @isr_mutex: mutex for IRQ thread.
  */
 struct altr_i2c_dev {
 	void __iomem *base;
@@ -97,6 +98,7 @@ struct altr_i2c_dev {
 	u32 isr_mask;
 	u32 isr_status;
 	spinlock_t lock;	/* IRQ synchronization */
+	struct mutex isr_mutex;
 };
 
 static void
@@ -256,10 +258,11 @@ static irqreturn_t altr_i2c_isr(int irq, void *_dev)
 	struct altr_i2c_dev *idev = _dev;
 	u32 status = idev->isr_status;
 
+	mutex_lock(&idev->isr_mutex);
 	if (!idev->msg) {
 		dev_warn(idev->dev, "unexpected interrupt\n");
 		altr_i2c_int_clear(idev, ALTR_I2C_ALL_IRQ);
-		return IRQ_HANDLED;
+		goto out;
 	}
 	read = (idev->msg->flags & I2C_M_RD) != 0;
 
@@ -312,6 +315,8 @@ static irqreturn_t altr_i2c_isr(int irq, void *_dev)
 		complete(&idev->msg_complete);
 		dev_dbg(idev->dev, "Message Complete\n");
 	}
+out:
+	mutex_unlock(&idev->isr_mutex);
 
 	return IRQ_HANDLED;
 }
@@ -323,6 +328,7 @@ static int altr_i2c_xfer_msg(struct altr_i2c_dev *idev, struct i2c_msg *msg)
 	u32 value;
 	u8 addr = i2c_8bit_addr_from_msg(msg);
 
+	mutex_lock(&idev->isr_mutex);
 	idev->msg = msg;
 	idev->msg_len = msg->len;
 	idev->buf = msg->buf;
@@ -347,6 +353,7 @@ static int altr_i2c_xfer_msg(struct altr_i2c_dev *idev, struct i2c_msg *msg)
 		altr_i2c_int_enable(idev, imask, true);
 		altr_i2c_fill_tx_fifo(idev);
 	}
+	mutex_unlock(&idev->isr_mutex);
 
 	time_left = wait_for_completion_timeout(&idev->msg_complete,
 						ALTR_I2C_XFER_TIMEOUT);
@@ -420,6 +427,7 @@ static int altr_i2c_probe(struct platform_device *pdev)
 	idev->dev = &pdev->dev;
 	init_completion(&idev->msg_complete);
 	spin_lock_init(&idev->lock);
+	mutex_init(&idev->isr_mutex);
 
 	ret = device_property_read_u32(idev->dev, "fifo-size",
 				       &idev->fifo_size);
diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c
index d917cefc5a19..b13605718291 100644
--- a/drivers/i2c/busses/i2c-cadence.c
+++ b/drivers/i2c/busses/i2c-cadence.c
@@ -382,10 +382,8 @@ static void cdns_i2c_mrecv(struct cdns_i2c *id)
 	 * Check for the message size against FIFO depth and set the
 	 * 'hold bus' bit if it is greater than FIFO depth.
 	 */
-	if ((id->recv_count > CDNS_I2C_FIFO_DEPTH)  || id->bus_hold_flag)
+	if (id->recv_count > CDNS_I2C_FIFO_DEPTH)
 		ctrl_reg |= CDNS_I2C_CR_HOLD;
-	else
-		ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD;
 
 	cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET);
 
@@ -442,11 +440,8 @@ static void cdns_i2c_msend(struct cdns_i2c *id)
 	 * Check for the message size against FIFO depth and set the
 	 * 'hold bus' bit if it is greater than FIFO depth.
 	 */
-	if ((id->send_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag)
+	if (id->send_count > CDNS_I2C_FIFO_DEPTH)
 		ctrl_reg |= CDNS_I2C_CR_HOLD;
-	else
-		ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD;
-
 	cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET);
 
 	/* Clear the interrupts in interrupt status register. */
diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c
index 8a8ca945561b..7eba874a981d 100644
--- a/drivers/i2c/busses/i2c-cpm.c
+++ b/drivers/i2c/busses/i2c-cpm.c
@@ -74,6 +74,9 @@ struct i2c_ram {
 	char    res1[4];	/* Reserved */
 	ushort  rpbase;		/* Relocation pointer */
 	char    res2[2];	/* Reserved */
+	/* The following elements are only for CPM2 */
+	char    res3[4];	/* Reserved */
+	uint    sdmatmp;	/* Internal */
 };
 
 #define I2COM_START	0x80
diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c
index bdeab0174fec..0b6567d1aa39 100644
--- a/drivers/i2c/busses/i2c-eg20t.c
+++ b/drivers/i2c/busses/i2c-eg20t.c
@@ -189,6 +189,7 @@ static const struct pci_device_id pch_pcidev_id[] = {
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7831_I2C), 1, },
 	{0,}
 };
+MODULE_DEVICE_TABLE(pci, pch_pcidev_id);
 
 static irqreturn_t pch_i2c_handler(int irq, void *pData);
 
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 06debfa903b9..21cf2b7dd0f2 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1499,6 +1499,16 @@ static inline int i801_acpi_probe(struct i801_priv *priv) { return 0; }
 static inline void i801_acpi_remove(struct i801_priv *priv) { }
 #endif
 
+static unsigned char i801_setup_hstcfg(struct i801_priv *priv)
+{
+	unsigned char hstcfg = priv->original_hstcfg;
+
+	hstcfg &= ~SMBHSTCFG_I2C_EN;	/* SMBus timing */
+	hstcfg |= SMBHSTCFG_HST_EN;
+	pci_write_config_byte(priv->pci_dev, SMBHSTCFG, hstcfg);
+	return hstcfg;
+}
+
 static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
 	unsigned char temp;
@@ -1602,14 +1612,10 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		return err;
 	}
 
-	pci_read_config_byte(priv->pci_dev, SMBHSTCFG, &temp);
-	priv->original_hstcfg = temp;
-	temp &= ~SMBHSTCFG_I2C_EN;	/* SMBus timing */
-	if (!(temp & SMBHSTCFG_HST_EN)) {
+	pci_read_config_byte(priv->pci_dev, SMBHSTCFG, &priv->original_hstcfg);
+	temp = i801_setup_hstcfg(priv);
+	if (!(priv->original_hstcfg & SMBHSTCFG_HST_EN))
 		dev_info(&dev->dev, "Enabling SMBus device\n");
-		temp |= SMBHSTCFG_HST_EN;
-	}
-	pci_write_config_byte(priv->pci_dev, SMBHSTCFG, temp);
 
 	if (temp & SMBHSTCFG_SMB_SMI_EN) {
 		dev_dbg(&dev->dev, "SMBus using interrupt SMI#\n");
@@ -1736,6 +1742,7 @@ static int i801_resume(struct device *dev)
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct i801_priv *priv = pci_get_drvdata(pci_dev);
 
+	i801_setup_hstcfg(priv);
 	i801_enable_host_notify(&priv->adapter);
 
 	return 0;
diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c
index 88d15b92ec35..efde272c0bf6 100644
--- a/drivers/i2c/busses/i2c-meson.c
+++ b/drivers/i2c/busses/i2c-meson.c
@@ -8,6 +8,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/i2c.h>
@@ -39,6 +40,12 @@
 #define REG_CTRL_CLKDIVEXT_SHIFT 28
 #define REG_CTRL_CLKDIVEXT_MASK	GENMASK(29, 28)
 
+#define REG_SLV_ADDR		GENMASK(7, 0)
+#define REG_SLV_SDA_FILTER	GENMASK(10, 8)
+#define REG_SLV_SCL_FILTER	GENMASK(13, 11)
+#define REG_SLV_SCL_LOW		GENMASK(27, 16)
+#define REG_SLV_SCL_LOW_EN	BIT(28)
+
 #define I2C_TIMEOUT_MS		500
 
 enum {
@@ -142,6 +149,9 @@ static void meson_i2c_set_clk_div(struct meson_i2c *i2c, unsigned int freq)
 	meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIVEXT_MASK,
 			   (div >> 10) << REG_CTRL_CLKDIVEXT_SHIFT);
 
+	/* Disable HIGH/LOW mode */
+	meson_i2c_set_mask(i2c, REG_SLAVE_ADDR, REG_SLV_SCL_LOW_EN, 0);
+
 	dev_dbg(i2c->dev, "%s: clk %lu, freq %u, div %u\n", __func__,
 		clk_rate, freq, div);
 }
@@ -269,7 +279,10 @@ static void meson_i2c_do_start(struct meson_i2c *i2c, struct i2c_msg *msg)
 	token = (msg->flags & I2C_M_RD) ? TOKEN_SLAVE_ADDR_READ :
 		TOKEN_SLAVE_ADDR_WRITE;
 
-	writel(msg->addr << 1, i2c->regs + REG_SLAVE_ADDR);
+
+	meson_i2c_set_mask(i2c, REG_SLAVE_ADDR, REG_SLV_ADDR,
+			   FIELD_PREP(REG_SLV_ADDR, msg->addr << 1));
+
 	meson_i2c_add_token(i2c, TOKEN_START);
 	meson_i2c_add_token(i2c, token);
 }
@@ -425,6 +438,10 @@ static int meson_i2c_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/* Disable filtering */
+	meson_i2c_set_mask(i2c, REG_SLAVE_ADDR,
+			   REG_SLV_SDA_FILTER | REG_SLV_SCL_FILTER, 0);
+
 	meson_i2c_set_clk_div(i2c, timings.bus_freq_hz);
 
 	return 0;
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 4b81dc231b18..5345b731bb7c 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -960,7 +960,8 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	}
 
 	if (dev->vendor == PCI_VENDOR_ID_AMD &&
-	    dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS) {
+	    (dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS ||
+	     dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS)) {
 		retval = piix4_setup_sb800(dev, id, 1);
 	}
 
diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c
index 600d264e080c..e300f9530f19 100644
--- a/drivers/i2c/busses/i2c-pxa.c
+++ b/drivers/i2c/busses/i2c-pxa.c
@@ -315,11 +315,10 @@ static void i2c_pxa_scream_blue_murder(struct pxa_i2c *i2c, const char *why)
 	dev_err(dev, "IBMR: %08x IDBR: %08x ICR: %08x ISR: %08x\n",
 		readl(_IBMR(i2c)), readl(_IDBR(i2c)), readl(_ICR(i2c)),
 		readl(_ISR(i2c)));
-	dev_dbg(dev, "log: ");
+	dev_err(dev, "log:");
 	for (i = 0; i < i2c->irqlogidx; i++)
-		pr_debug("[%08x:%08x] ", i2c->isrlog[i], i2c->icrlog[i]);
-
-	pr_debug("\n");
+		pr_cont(" [%03x:%05x]", i2c->isrlog[i], i2c->icrlog[i]);
+	pr_cont("\n");
 }
 
 #else /* ifdef DEBUG */
@@ -709,11 +708,9 @@ static inline void i2c_pxa_stop_message(struct pxa_i2c *i2c)
 {
 	u32 icr;
 
-	/*
-	 * Clear the STOP and ACK flags
-	 */
+	/* Clear the START, STOP, ACK, TB and MA flags */
 	icr = readl(_ICR(i2c));
-	icr &= ~(ICR_STOP | ICR_ACKNAK);
+	icr &= ~(ICR_START | ICR_STOP | ICR_ACKNAK | ICR_TB | ICR_MA);
 	writel(icr, _ICR(i2c));
 }
 
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 132c4a405bf8..d5d0809a6283 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -538,13 +538,15 @@ static bool rcar_i2c_slave_irq(struct rcar_i2c_priv *priv)
 			rcar_i2c_write(priv, ICSIER, SDR | SSR | SAR);
 		}
 
-		rcar_i2c_write(priv, ICSSR, ~SAR & 0xff);
+		/* Clear SSR, too, because of old STOPs to other clients than us */
+		rcar_i2c_write(priv, ICSSR, ~(SAR | SSR) & 0xff);
 	}
 
 	/* master sent stop */
 	if (ssr_filtered & SSR) {
 		i2c_slave_event(priv->slave, I2C_SLAVE_STOP, &value);
-		rcar_i2c_write(priv, ICSIER, SAR | SSR);
+		rcar_i2c_write(priv, ICSCR, SIE | SDBS); /* clear our NACK */
+		rcar_i2c_write(priv, ICSIER, SAR);
 		rcar_i2c_write(priv, ICSSR, ~SSR & 0xff);
 	}
 
@@ -802,7 +804,7 @@ static int rcar_reg_slave(struct i2c_client *slave)
 	priv->slave = slave;
 	rcar_i2c_write(priv, ICSAR, slave->addr);
 	rcar_i2c_write(priv, ICSSR, 0);
-	rcar_i2c_write(priv, ICSIER, SAR | SSR);
+	rcar_i2c_write(priv, ICSIER, SAR);
 	rcar_i2c_write(priv, ICSCR, SIE | SDBS);
 
 	return 0;
@@ -814,11 +816,14 @@ static int rcar_unreg_slave(struct i2c_client *slave)
 
 	WARN_ON(!priv->slave);
 
-	/* disable irqs and ensure none is running before clearing ptr */
+	/* ensure no irq is running before clearing ptr */
+	disable_irq(priv->irq);
 	rcar_i2c_write(priv, ICSIER, 0);
-	rcar_i2c_write(priv, ICSCR, 0);
+	rcar_i2c_write(priv, ICSSR, 0);
+	enable_irq(priv->irq);
+	rcar_i2c_write(priv, ICSCR, SDBS);
+	rcar_i2c_write(priv, ICSAR, 0); /* Gen2: must be 0 if not using slave */
 
-	synchronize_irq(priv->irq);
 	priv->slave = NULL;
 
 	pm_runtime_put(rcar_i2c_priv_to_dev(priv));
@@ -914,6 +919,8 @@ static int rcar_i2c_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto out_pm_put;
 
+	rcar_i2c_write(priv, ICSAR, 0); /* Gen2: must be 0 if not using slave */
+
 	if (priv->devtype == I2C_RCAR_GEN3) {
 		priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
 		if (!IS_ERR(priv->rstc)) {
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 7b961c9c62ef..9f2aa45560e6 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -1280,8 +1280,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 
 	/* create pre-declared device nodes */
 	of_i2c_register_devices(adap);
-	i2c_acpi_register_devices(adap);
 	i2c_acpi_install_space_handler(adap);
+	i2c_acpi_register_devices(adap);
 
 	if (adap->nr < __i2c_first_dynamic_bus_num)
 		i2c_scan_static_board_info(adap);
diff --git a/drivers/i2c/i2c-core-slave.c b/drivers/i2c/i2c-core-slave.c
index 4a78c65e9971..d89bc31e0622 100644
--- a/drivers/i2c/i2c-core-slave.c
+++ b/drivers/i2c/i2c-core-slave.c
@@ -22,10 +22,8 @@ int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb)
 {
 	int ret;
 
-	if (!client || !slave_cb) {
-		WARN(1, "insufficient data\n");
+	if (WARN(IS_ERR_OR_NULL(client) || !slave_cb, "insufficient data\n"))
 		return -EINVAL;
-	}
 
 	if (!(client->flags & I2C_CLIENT_SLAVE))
 		dev_warn(&client->dev, "%s: client slave flag not set. You might see address collisions\n",
@@ -64,6 +62,9 @@ int i2c_slave_unregister(struct i2c_client *client)
 {
 	int ret;
 
+	if (IS_ERR_OR_NULL(client))
+		return -EINVAL;
+
 	if (!client->adapter->algo->unreg_slave) {
 		dev_err(&client->dev, "%s: not supported by adapter\n", __func__);
 		return -EOPNOTSUPP;
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 4de45db76756..5aed1de845d0 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -712,7 +712,7 @@ static ide_startstop_t cdrom_start_rw(ide_drive_t *drive, struct request *rq)
 	struct request_queue *q = drive->queue;
 	int write = rq_data_dir(rq) == WRITE;
 	unsigned short sectors_per_frame =
-		queue_logical_block_size(q) >> SECTOR_BITS;
+		queue_logical_block_size(q) >> SECTOR_SHIFT;
 
 	ide_debug_log(IDE_DBG_RQ, "rq->cmd[0]: 0x%x, rq->cmd_flags: 0x%x, "
 				  "secs_per_frame: %u",
@@ -919,7 +919,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
 	 * end up being bogus.
 	 */
 	blocklen = be32_to_cpu(capbuf.blocklen);
-	blocklen = (blocklen >> SECTOR_BITS) << SECTOR_BITS;
+	blocklen = (blocklen >> SECTOR_SHIFT) << SECTOR_SHIFT;
 	switch (blocklen) {
 	case 512:
 	case 1024:
@@ -935,7 +935,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
 	}
 
 	*capacity = 1 + be32_to_cpu(capbuf.lba);
-	*sectors_per_frame = blocklen >> SECTOR_BITS;
+	*sectors_per_frame = blocklen >> SECTOR_SHIFT;
 
 	ide_debug_log(IDE_DBG_PROBE, "cap: %lu, sectors_per_frame: %lu",
 				     *capacity, *sectors_per_frame);
@@ -1012,7 +1012,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	drive->probed_capacity = toc->capacity * sectors_per_frame;
 
 	blk_queue_logical_block_size(drive->queue,
-				     sectors_per_frame << SECTOR_BITS);
+				     sectors_per_frame << SECTOR_SHIFT);
 
 	/* first read just the header, so we know how long the TOC is */
 	stat = cdrom_read_tocentry(drive, 0, 1, 0, (char *) &toc->hdr,
diff --git a/drivers/ide/ide-cd.h b/drivers/ide/ide-cd.h
index 264e822eba58..04f0f310a856 100644
--- a/drivers/ide/ide-cd.h
+++ b/drivers/ide/ide-cd.h
@@ -21,11 +21,7 @@
 
 /************************************************************************/
 
-#define SECTOR_BITS 		9
-#ifndef SECTOR_SIZE
-#define SECTOR_SIZE		(1 << SECTOR_BITS)
-#endif
-#define SECTORS_PER_FRAME	(CD_FRAMESIZE >> SECTOR_BITS)
+#define SECTORS_PER_FRAME	(CD_FRAMESIZE >> SECTOR_SHIFT)
 #define SECTOR_BUFFER_SIZE	(CD_FRAMESIZE * 32)
 
 /* Capabilities Page size including 8 bytes of Mode Page Header */
diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c
index 7e86a5b7ec4e..0d40c32b56ce 100644
--- a/drivers/iio/accel/bmc150-accel-core.c
+++ b/drivers/iio/accel/bmc150-accel-core.c
@@ -197,6 +197,14 @@ struct bmc150_accel_data {
 	struct mutex mutex;
 	u8 fifo_mode, watermark;
 	s16 buffer[8];
+	/*
+	 * Ensure there is sufficient space and correct alignment for
+	 * the timestamp if enabled
+	 */
+	struct {
+		__le16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 	u8 bw_bits;
 	u32 slope_dur;
 	u32 slope_thres;
@@ -933,15 +941,16 @@ static int __bmc150_accel_fifo_flush(struct iio_dev *indio_dev,
 	 * now.
 	 */
 	for (i = 0; i < count; i++) {
-		u16 sample[8];
 		int j, bit;
 
 		j = 0;
 		for_each_set_bit(bit, indio_dev->active_scan_mask,
 				 indio_dev->masklength)
-			memcpy(&sample[j++], &buffer[i * 3 + bit], 2);
+			memcpy(&data->scan.channels[j++], &buffer[i * 3 + bit],
+			       sizeof(data->scan.channels[0]));
 
-		iio_push_to_buffers_with_timestamp(indio_dev, sample, tstamp);
+		iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
+						   tstamp);
 
 		tstamp += sample_period;
 	}
diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 9af60ac70738..1bda730a71c0 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -212,14 +212,20 @@ static irqreturn_t kxsd9_trigger_handler(int irq, void *p)
 	const struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct kxsd9_state *st = iio_priv(indio_dev);
+	/*
+	 * Ensure correct positioning and alignment of timestamp.
+	 * No need to zero initialize as all elements written.
+	 */
+	struct {
+		__be16 chan[4];
+		s64 ts __aligned(8);
+	} hw_values;
 	int ret;
-	/* 4 * 16bit values AND timestamp */
-	__be16 hw_values[8];
 
 	ret = regmap_bulk_read(st->map,
 			       KXSD9_REG_X,
-			       &hw_values,
-			       8);
+			       hw_values.chan,
+			       sizeof(hw_values.chan));
 	if (ret) {
 		dev_err(st->dev,
 			"error reading data\n");
@@ -227,7 +233,7 @@ static irqreturn_t kxsd9_trigger_handler(int irq, void *p)
 	}
 
 	iio_push_to_buffers_with_timestamp(indio_dev,
-					   hw_values,
+					   &hw_values,
 					   iio_get_time_ns(indio_dev));
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/iio/accel/mma7455_core.c b/drivers/iio/accel/mma7455_core.c
index 6551085bedd7..f7804e56cc27 100644
--- a/drivers/iio/accel/mma7455_core.c
+++ b/drivers/iio/accel/mma7455_core.c
@@ -55,6 +55,14 @@
 
 struct mma7455_data {
 	struct regmap *regmap;
+	/*
+	 * Used to reorganize data.  Will ensure correct alignment of
+	 * the timestamp if present
+	 */
+	struct {
+		__le16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 static int mma7455_drdy(struct mma7455_data *mma7455)
@@ -85,19 +93,19 @@ static irqreturn_t mma7455_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct mma7455_data *mma7455 = iio_priv(indio_dev);
-	u8 buf[16]; /* 3 x 16-bit channels + padding + ts */
 	int ret;
 
 	ret = mma7455_drdy(mma7455);
 	if (ret)
 		goto done;
 
-	ret = regmap_bulk_read(mma7455->regmap, MMA7455_REG_XOUTL, buf,
-			       sizeof(__le16) * 3);
+	ret = regmap_bulk_read(mma7455->regmap, MMA7455_REG_XOUTL,
+			       mma7455->scan.channels,
+			       sizeof(mma7455->scan.channels));
 	if (ret)
 		goto done;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &mma7455->scan,
 					   iio_get_time_ns(indio_dev));
 
 done:
diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c
index eb6e3dc789b2..200ac4dad799 100644
--- a/drivers/iio/accel/mma8452.c
+++ b/drivers/iio/accel/mma8452.c
@@ -105,6 +105,12 @@ struct mma8452_data {
 	u8 ctrl_reg1;
 	u8 data_cfg;
 	const struct mma_chip_info *chip_info;
+
+	/* Ensure correct alignment of time stamp when present */
+	struct {
+		__be16 channels[3];
+		s64 ts __aligned(8);
+	} buffer;
 };
 
 /**
@@ -1003,14 +1009,13 @@ static irqreturn_t mma8452_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct mma8452_data *data = iio_priv(indio_dev);
-	u8 buffer[16]; /* 3 16-bit channels + padding + ts */
 	int ret;
 
-	ret = mma8452_read(data, (__be16 *)buffer);
+	ret = mma8452_read(data, data->buffer.channels);
 	if (ret < 0)
 		goto done;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->buffer,
 					   iio_get_time_ns(indio_dev));
 
 done:
@@ -1583,10 +1588,13 @@ static int mma8452_probe(struct i2c_client *client,
 
 	ret = mma8452_set_freefall_mode(data, false);
 	if (ret < 0)
-		goto buffer_cleanup;
+		goto unregister_device;
 
 	return 0;
 
+unregister_device:
+	iio_device_unregister(indio_dev);
+
 buffer_cleanup:
 	iio_triggered_buffer_cleanup(indio_dev);
 
diff --git a/drivers/iio/adc/ina2xx-adc.c b/drivers/iio/adc/ina2xx-adc.c
index d5b9f831eba7..e87c7db53e09 100644
--- a/drivers/iio/adc/ina2xx-adc.c
+++ b/drivers/iio/adc/ina2xx-adc.c
@@ -133,6 +133,11 @@ struct ina2xx_chip_info {
 	int int_time_vbus; /* Bus voltage integration time uS */
 	int int_time_vshunt; /* Shunt voltage integration time uS */
 	bool allow_async_readout;
+	/* data buffer needs space for channel data and timestamp */
+	struct {
+		u16 chan[4];
+		u64 ts __aligned(8);
+	} scan;
 };
 
 static const struct ina2xx_config ina2xx_config[] = {
@@ -598,7 +603,6 @@ static const struct iio_chan_spec ina219_channels[] = {
 static int ina2xx_work_buffer(struct iio_dev *indio_dev)
 {
 	struct ina2xx_chip_info *chip = iio_priv(indio_dev);
-	unsigned short data[8];
 	int bit, ret, i = 0;
 	s64 time_a, time_b;
 	unsigned int alert;
@@ -648,7 +652,7 @@ static int ina2xx_work_buffer(struct iio_dev *indio_dev)
 		if (ret < 0)
 			return ret;
 
-		data[i++] = val;
+		chip->scan.chan[i++] = val;
 
 		if (INA2XX_SHUNT_VOLTAGE + bit == INA2XX_POWER)
 			cnvr_need_clear = 0;
@@ -665,8 +669,7 @@ static int ina2xx_work_buffer(struct iio_dev *indio_dev)
 
 	time_b = iio_get_time_ns(indio_dev);
 
-	iio_push_to_buffers_with_timestamp(indio_dev,
-					   (unsigned int *)data, time_a);
+	iio_push_to_buffers_with_timestamp(indio_dev, &chip->scan, time_a);
 
 	return (unsigned long)(time_b - time_a) / 1000;
 };
diff --git a/drivers/iio/adc/max1118.c b/drivers/iio/adc/max1118.c
index 2e9648a078c4..3dca3cf18d87 100644
--- a/drivers/iio/adc/max1118.c
+++ b/drivers/iio/adc/max1118.c
@@ -38,6 +38,11 @@ struct max1118 {
 	struct spi_device *spi;
 	struct mutex lock;
 	struct regulator *reg;
+	/* Ensure natural alignment of buffer elements */
+	struct {
+		u8 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 
 	u8 data ____cacheline_aligned;
 };
@@ -163,7 +168,6 @@ static irqreturn_t max1118_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct max1118 *adc = iio_priv(indio_dev);
-	u8 data[16] = { }; /* 2x 8-bit ADC data + padding + 8 bytes timestamp */
 	int scan_index;
 	int i = 0;
 
@@ -181,10 +185,10 @@ static irqreturn_t max1118_trigger_handler(int irq, void *p)
 			goto out;
 		}
 
-		data[i] = ret;
+		adc->scan.channels[i] = ret;
 		i++;
 	}
-	iio_push_to_buffers_with_timestamp(indio_dev, data,
+	iio_push_to_buffers_with_timestamp(indio_dev, &adc->scan,
 					   iio_get_time_ns(indio_dev));
 out:
 	mutex_unlock(&adc->lock);
diff --git a/drivers/iio/adc/mcp3422.c b/drivers/iio/adc/mcp3422.c
index 63de705086ed..9ac2becde8f2 100644
--- a/drivers/iio/adc/mcp3422.c
+++ b/drivers/iio/adc/mcp3422.c
@@ -99,16 +99,12 @@ static int mcp3422_update_config(struct mcp3422 *adc, u8 newconfig)
 {
 	int ret;
 
-	mutex_lock(&adc->lock);
-
 	ret = i2c_master_send(adc->i2c, &newconfig, 1);
 	if (ret > 0) {
 		adc->config = newconfig;
 		ret = 0;
 	}
 
-	mutex_unlock(&adc->lock);
-
 	return ret;
 }
 
@@ -141,6 +137,8 @@ static int mcp3422_read_channel(struct mcp3422 *adc,
 	u8 config;
 	u8 req_channel = channel->channel;
 
+	mutex_lock(&adc->lock);
+
 	if (req_channel != MCP3422_CHANNEL(adc->config)) {
 		config = adc->config;
 		config &= ~MCP3422_CHANNEL_MASK;
@@ -148,12 +146,18 @@ static int mcp3422_read_channel(struct mcp3422 *adc,
 		config &= ~MCP3422_PGA_MASK;
 		config |= MCP3422_PGA_VALUE(adc->pga[req_channel]);
 		ret = mcp3422_update_config(adc, config);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&adc->lock);
 			return ret;
+		}
 		msleep(mcp3422_read_times[MCP3422_SAMPLE_RATE(adc->config)]);
 	}
 
-	return mcp3422_read(adc, value, &config);
+	ret = mcp3422_read(adc, value, &config);
+
+	mutex_unlock(&adc->lock);
+
+	return ret;
 }
 
 static int mcp3422_read_raw(struct iio_dev *iio,
diff --git a/drivers/iio/adc/ti-adc081c.c b/drivers/iio/adc/ti-adc081c.c
index 319172cf7da8..d9bfe79c1747 100644
--- a/drivers/iio/adc/ti-adc081c.c
+++ b/drivers/iio/adc/ti-adc081c.c
@@ -36,6 +36,12 @@ struct adc081c {
 
 	/* 8, 10 or 12 */
 	int bits;
+
+	/* Ensure natural alignment of buffer elements */
+	struct {
+		u16 channel;
+		s64 ts __aligned(8);
+	} scan;
 };
 
 #define REG_CONV_RES 0x00
@@ -132,14 +138,13 @@ static irqreturn_t adc081c_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct adc081c *data = iio_priv(indio_dev);
-	u16 buf[8]; /* 2 bytes data + 6 bytes padding + 8 bytes timestamp */
 	int ret;
 
 	ret = i2c_smbus_read_word_swapped(data->i2c, REG_CONV_RES);
 	if (ret < 0)
 		goto out;
-	buf[0] = ret;
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	data->scan.channel = ret;
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
 out:
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/adc/ti-adc084s021.c b/drivers/iio/adc/ti-adc084s021.c
index a355121c11a4..f3ad1d024c75 100644
--- a/drivers/iio/adc/ti-adc084s021.c
+++ b/drivers/iio/adc/ti-adc084s021.c
@@ -28,6 +28,11 @@ struct adc084s021 {
 	struct spi_transfer spi_trans;
 	struct regulator *reg;
 	struct mutex lock;
+	/* Buffer used to align data */
+	struct {
+		__be16 channels[4];
+		s64 ts __aligned(8);
+	} scan;
 	/*
 	 * DMA (thus cache coherency maintenance) requires the
 	 * transfer buffers to live in their own cache line.
@@ -143,14 +148,13 @@ static irqreturn_t adc084s021_buffer_trigger_handler(int irq, void *pollfunc)
 	struct iio_poll_func *pf = pollfunc;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct adc084s021 *adc = iio_priv(indio_dev);
-	__be16 data[8] = {0}; /* 4 * 16-bit words of data + 8 bytes timestamp */
 
 	mutex_lock(&adc->lock);
 
-	if (adc084s021_adc_conversion(adc, &data) < 0)
+	if (adc084s021_adc_conversion(adc, adc->scan.channels) < 0)
 		dev_err(&adc->spi->dev, "Failed to read data\n");
 
-	iio_push_to_buffers_with_timestamp(indio_dev, data,
+	iio_push_to_buffers_with_timestamp(indio_dev, &adc->scan,
 					   iio_get_time_ns(indio_dev));
 	mutex_unlock(&adc->lock);
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c
index 9ac2fb032df6..df71c6105353 100644
--- a/drivers/iio/adc/ti-ads1015.c
+++ b/drivers/iio/adc/ti-ads1015.c
@@ -312,6 +312,7 @@ static const struct iio_chan_spec ads1115_channels[] = {
 	IIO_CHAN_SOFT_TIMESTAMP(ADS1015_TIMESTAMP),
 };
 
+#ifdef CONFIG_PM
 static int ads1015_set_power_state(struct ads1015_data *data, bool on)
 {
 	int ret;
@@ -329,6 +330,15 @@ static int ads1015_set_power_state(struct ads1015_data *data, bool on)
 	return ret < 0 ? ret : 0;
 }
 
+#else /* !CONFIG_PM */
+
+static int ads1015_set_power_state(struct ads1015_data *data, bool on)
+{
+	return 0;
+}
+
+#endif /* !CONFIG_PM */
+
 static
 int ads1015_get_adc_result(struct ads1015_data *data, int chan, int *val)
 {
diff --git a/drivers/iio/chemical/ccs811.c b/drivers/iio/chemical/ccs811.c
index 9dd0e1cd93dd..9f80cc18ef7f 100644
--- a/drivers/iio/chemical/ccs811.c
+++ b/drivers/iio/chemical/ccs811.c
@@ -73,6 +73,11 @@ struct ccs811_data {
 	struct i2c_client *client;
 	struct mutex lock; /* Protect readings */
 	struct ccs811_reading buffer;
+	/* Ensures correct alignment of timestamp if present */
+	struct {
+		s16 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 static const struct iio_chan_spec ccs811_channels[] = {
@@ -275,17 +280,17 @@ static irqreturn_t ccs811_trigger_handler(int irq, void *p)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ccs811_data *data = iio_priv(indio_dev);
 	struct i2c_client *client = data->client;
-	s16 buf[8]; /* s16 eCO2 + s16 TVOC + padding + 8 byte timestamp */
 	int ret;
 
-	ret = i2c_smbus_read_i2c_block_data(client, CCS811_ALG_RESULT_DATA, 4,
-					    (u8 *)&buf);
+	ret = i2c_smbus_read_i2c_block_data(client, CCS811_ALG_RESULT_DATA,
+					    sizeof(data->scan.channels),
+					    (u8 *)data->scan.channels);
 	if (ret != 4) {
 		dev_err(&client->dev, "cannot read sensor data\n");
 		goto err;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
 
 err:
diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c
index 69bde5909854..5c998ac8c840 100644
--- a/drivers/iio/dac/ad5592r-base.c
+++ b/drivers/iio/dac/ad5592r-base.c
@@ -417,7 +417,7 @@ static int ad5592r_read_raw(struct iio_dev *iio_dev,
 			s64 tmp = *val * (3767897513LL / 25LL);
 			*val = div_s64_rem(tmp, 1000000000LL, val2);
 
-			ret = IIO_VAL_INT_PLUS_MICRO;
+			return IIO_VAL_INT_PLUS_MICRO;
 		} else {
 			int mult;
 
@@ -448,7 +448,7 @@ static int ad5592r_read_raw(struct iio_dev *iio_dev,
 		ret =  IIO_VAL_INT;
 		break;
 	default:
-		ret = -EINVAL;
+		return -EINVAL;
 	}
 
 unlock:
diff --git a/drivers/iio/health/afe4403.c b/drivers/iio/health/afe4403.c
index 6bb23a49e81e..2f07c4d1398c 100644
--- a/drivers/iio/health/afe4403.c
+++ b/drivers/iio/health/afe4403.c
@@ -71,6 +71,7 @@ static const struct reg_field afe4403_reg_fields[] = {
  * @regulator: Pointer to the regulator for the IC
  * @trig: IIO trigger for this device
  * @irq: ADC_RDY line interrupt number
+ * @buffer: Used to construct data layout to push into IIO buffer.
  */
 struct afe4403_data {
 	struct device *dev;
@@ -80,6 +81,8 @@ struct afe4403_data {
 	struct regulator *regulator;
 	struct iio_trigger *trig;
 	int irq;
+	/* Ensure suitable alignment for timestamp */
+	s32 buffer[8] __aligned(8);
 };
 
 enum afe4403_chan_id {
@@ -318,7 +321,6 @@ static irqreturn_t afe4403_trigger_handler(int irq, void *private)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct afe4403_data *afe = iio_priv(indio_dev);
 	int ret, bit, i = 0;
-	s32 buffer[8];
 	u8 tx[4] = {AFE440X_CONTROL0, 0x0, 0x0, AFE440X_CONTROL0_READ};
 	u8 rx[3];
 
@@ -335,9 +337,9 @@ static irqreturn_t afe4403_trigger_handler(int irq, void *private)
 		if (ret)
 			goto err;
 
-		buffer[i++] = (rx[0] << 16) |
-				(rx[1] << 8) |
-				(rx[2]);
+		afe->buffer[i++] = (rx[0] << 16) |
+				   (rx[1] << 8) |
+				   (rx[2]);
 	}
 
 	/* Disable reading from the device */
@@ -346,7 +348,8 @@ static irqreturn_t afe4403_trigger_handler(int irq, void *private)
 	if (ret)
 		goto err;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer, pf->timestamp);
+	iio_push_to_buffers_with_timestamp(indio_dev, afe->buffer,
+					   pf->timestamp);
 err:
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/iio/health/afe4404.c b/drivers/iio/health/afe4404.c
index 964f5231a831..5e256b11ac87 100644
--- a/drivers/iio/health/afe4404.c
+++ b/drivers/iio/health/afe4404.c
@@ -91,6 +91,7 @@ static const struct reg_field afe4404_reg_fields[] = {
  * @regulator: Pointer to the regulator for the IC
  * @trig: IIO trigger for this device
  * @irq: ADC_RDY line interrupt number
+ * @buffer: Used to construct a scan to push to the iio buffer.
  */
 struct afe4404_data {
 	struct device *dev;
@@ -99,6 +100,7 @@ struct afe4404_data {
 	struct regulator *regulator;
 	struct iio_trigger *trig;
 	int irq;
+	s32 buffer[10] __aligned(8);
 };
 
 enum afe4404_chan_id {
@@ -337,17 +339,17 @@ static irqreturn_t afe4404_trigger_handler(int irq, void *private)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct afe4404_data *afe = iio_priv(indio_dev);
 	int ret, bit, i = 0;
-	s32 buffer[10];
 
 	for_each_set_bit(bit, indio_dev->active_scan_mask,
 			 indio_dev->masklength) {
 		ret = regmap_read(afe->regmap, afe4404_channel_values[bit],
-				  &buffer[i++]);
+				  &afe->buffer[i++]);
 		if (ret)
 			goto err;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer, pf->timestamp);
+	iio_push_to_buffers_with_timestamp(indio_dev, afe->buffer,
+					   pf->timestamp);
 err:
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c
index b470cb8132da..273eb0612a5d 100644
--- a/drivers/iio/humidity/hdc100x.c
+++ b/drivers/iio/humidity/hdc100x.c
@@ -46,6 +46,11 @@ struct hdc100x_data {
 
 	/* integration time of the sensor */
 	int adc_int_us[2];
+	/* Ensure natural alignment of timestamp */
+	struct {
+		__be16 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 /* integration time in us */
@@ -327,7 +332,6 @@ static irqreturn_t hdc100x_trigger_handler(int irq, void *p)
 	struct i2c_client *client = data->client;
 	int delay = data->adc_int_us[0] + data->adc_int_us[1];
 	int ret;
-	s16 buf[8];  /* 2x s16 + padding + 8 byte timestamp */
 
 	/* dual read starts at temp register */
 	mutex_lock(&data->lock);
@@ -338,13 +342,13 @@ static irqreturn_t hdc100x_trigger_handler(int irq, void *p)
 	}
 	usleep_range(delay, delay + 1000);
 
-	ret = i2c_master_recv(client, (u8 *)buf, 4);
+	ret = i2c_master_recv(client, (u8 *)data->scan.channels, 4);
 	if (ret < 0) {
 		dev_err(&client->dev, "cannot read sensor data\n");
 		goto err;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
 err:
 	mutex_unlock(&data->lock);
diff --git a/drivers/iio/imu/adis16400_buffer.c b/drivers/iio/imu/adis16400_buffer.c
index e70a5339acb1..3fc11aec98b9 100644
--- a/drivers/iio/imu/adis16400_buffer.c
+++ b/drivers/iio/imu/adis16400_buffer.c
@@ -38,8 +38,11 @@ int adis16400_update_scan_mode(struct iio_dev *indio_dev,
 		return -ENOMEM;
 
 	adis->buffer = kzalloc(burst_length + sizeof(u16), GFP_KERNEL);
-	if (!adis->buffer)
+	if (!adis->buffer) {
+		kfree(adis->xfer);
+		adis->xfer = NULL;
 		return -ENOMEM;
+	}
 
 	tx = adis->buffer + burst_length;
 	tx[0] = ADIS_READ_REG(ADIS16400_GLOB_CMD);
diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c
index 67838edd8b37..7a9358049659 100644
--- a/drivers/iio/light/ltr501.c
+++ b/drivers/iio/light/ltr501.c
@@ -1249,13 +1249,16 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ltr501_data *data = iio_priv(indio_dev);
-	u16 buf[8];
+	struct {
+		u16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 	__le16 als_buf[2];
 	u8 mask = 0;
 	int j = 0;
 	int ret, psdata;
 
-	memset(buf, 0, sizeof(buf));
+	memset(&scan, 0, sizeof(scan));
 
 	/* figure out which data needs to be ready */
 	if (test_bit(0, indio_dev->active_scan_mask) ||
@@ -1274,9 +1277,9 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p)
 		if (ret < 0)
 			return ret;
 		if (test_bit(0, indio_dev->active_scan_mask))
-			buf[j++] = le16_to_cpu(als_buf[1]);
+			scan.channels[j++] = le16_to_cpu(als_buf[1]);
 		if (test_bit(1, indio_dev->active_scan_mask))
-			buf[j++] = le16_to_cpu(als_buf[0]);
+			scan.channels[j++] = le16_to_cpu(als_buf[0]);
 	}
 
 	if (mask & LTR501_STATUS_PS_RDY) {
@@ -1284,10 +1287,10 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p)
 				       &psdata, 2);
 		if (ret < 0)
 			goto done;
-		buf[j++] = psdata & LTR501_PS_DATA_MASK;
+		scan.channels[j++] = psdata & LTR501_PS_DATA_MASK;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &scan,
 					   iio_get_time_ns(indio_dev));
 
 done:
diff --git a/drivers/iio/light/max44000.c b/drivers/iio/light/max44000.c
index 81bd8e8da4a6..255b932fc21d 100644
--- a/drivers/iio/light/max44000.c
+++ b/drivers/iio/light/max44000.c
@@ -78,6 +78,11 @@
 struct max44000_data {
 	struct mutex lock;
 	struct regmap *regmap;
+	/* Ensure naturally aligned timestamp */
+	struct {
+		u16 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 /* Default scale is set to the minimum of 0.03125 or 1 / (1 << 5) lux */
@@ -492,7 +497,6 @@ static irqreturn_t max44000_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct max44000_data *data = iio_priv(indio_dev);
-	u16 buf[8]; /* 2x u16 + padding + 8 bytes timestamp */
 	int index = 0;
 	unsigned int regval;
 	int ret;
@@ -502,17 +506,17 @@ static irqreturn_t max44000_trigger_handler(int irq, void *p)
 		ret = max44000_read_alsval(data);
 		if (ret < 0)
 			goto out_unlock;
-		buf[index++] = ret;
+		data->scan.channels[index++] = ret;
 	}
 	if (test_bit(MAX44000_SCAN_INDEX_PRX, indio_dev->active_scan_mask)) {
 		ret = regmap_read(data->regmap, MAX44000_REG_PRX_DATA, &regval);
 		if (ret < 0)
 			goto out_unlock;
-		buf[index] = regval;
+		data->scan.channels[index] = regval;
 	}
 	mutex_unlock(&data->lock);
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
 	iio_trigger_notify_done(indio_dev->trig);
 	return IRQ_HANDLED;
diff --git a/drivers/iio/light/vcnl4000.c b/drivers/iio/light/vcnl4000.c
index 360b6e98137a..5a3a532937ba 100644
--- a/drivers/iio/light/vcnl4000.c
+++ b/drivers/iio/light/vcnl4000.c
@@ -61,7 +61,6 @@ static int vcnl4000_measure(struct vcnl4000_data *data, u8 req_mask,
 				u8 rdy_mask, u8 data_reg, int *val)
 {
 	int tries = 20;
-	__be16 buf;
 	int ret;
 
 	mutex_lock(&data->lock);
@@ -88,13 +87,12 @@ static int vcnl4000_measure(struct vcnl4000_data *data, u8 req_mask,
 		goto fail;
 	}
 
-	ret = i2c_smbus_read_i2c_block_data(data->client,
-		data_reg, sizeof(buf), (u8 *) &buf);
+	ret = i2c_smbus_read_word_swapped(data->client, data_reg);
 	if (ret < 0)
 		goto fail;
 
 	mutex_unlock(&data->lock);
-	*val = be16_to_cpu(buf);
+	*val = ret;
 
 	return 0;
 
diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c
index 283ecd4ea800..11b9cc42bc09 100644
--- a/drivers/iio/magnetometer/ak8974.c
+++ b/drivers/iio/magnetometer/ak8974.c
@@ -184,6 +184,11 @@ struct ak8974 {
 	bool drdy_irq;
 	struct completion drdy_complete;
 	bool drdy_active_low;
+	/* Ensure timestamp is naturally aligned */
+	struct {
+		__le16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 static const char ak8974_reg_avdd[] = "avdd";
@@ -580,7 +585,6 @@ static void ak8974_fill_buffer(struct iio_dev *indio_dev)
 {
 	struct ak8974 *ak8974 = iio_priv(indio_dev);
 	int ret;
-	__le16 hw_values[8]; /* Three axes + 64bit padding */
 
 	pm_runtime_get_sync(&ak8974->i2c->dev);
 	mutex_lock(&ak8974->lock);
@@ -590,13 +594,13 @@ static void ak8974_fill_buffer(struct iio_dev *indio_dev)
 		dev_err(&ak8974->i2c->dev, "error triggering measure\n");
 		goto out_unlock;
 	}
-	ret = ak8974_getresult(ak8974, hw_values);
+	ret = ak8974_getresult(ak8974, ak8974->scan.channels);
 	if (ret) {
 		dev_err(&ak8974->i2c->dev, "error getting measures\n");
 		goto out_unlock;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, hw_values,
+	iio_push_to_buffers_with_timestamp(indio_dev, &ak8974->scan,
 					   iio_get_time_ns(indio_dev));
 
  out_unlock:
@@ -765,19 +769,21 @@ static int ak8974_probe(struct i2c_client *i2c,
 	ak8974->map = devm_regmap_init_i2c(i2c, &ak8974_regmap_config);
 	if (IS_ERR(ak8974->map)) {
 		dev_err(&i2c->dev, "failed to allocate register map\n");
+		pm_runtime_put_noidle(&i2c->dev);
+		pm_runtime_disable(&i2c->dev);
 		return PTR_ERR(ak8974->map);
 	}
 
 	ret = ak8974_set_power(ak8974, AK8974_PWR_ON);
 	if (ret) {
 		dev_err(&i2c->dev, "could not power on\n");
-		goto power_off;
+		goto disable_pm;
 	}
 
 	ret = ak8974_detect(ak8974);
 	if (ret) {
 		dev_err(&i2c->dev, "neither AK8974 nor AMI30x found\n");
-		goto power_off;
+		goto disable_pm;
 	}
 
 	ret = ak8974_selftest(ak8974);
@@ -787,14 +793,9 @@ static int ak8974_probe(struct i2c_client *i2c,
 	ret = ak8974_reset(ak8974);
 	if (ret) {
 		dev_err(&i2c->dev, "AK8974 reset failed\n");
-		goto power_off;
+		goto disable_pm;
 	}
 
-	pm_runtime_set_autosuspend_delay(&i2c->dev,
-					 AK8974_AUTOSUSPEND_DELAY);
-	pm_runtime_use_autosuspend(&i2c->dev);
-	pm_runtime_put(&i2c->dev);
-
 	indio_dev->dev.parent = &i2c->dev;
 	indio_dev->channels = ak8974_channels;
 	indio_dev->num_channels = ARRAY_SIZE(ak8974_channels);
@@ -847,6 +848,11 @@ no_irq:
 		goto cleanup_buffer;
 	}
 
+	pm_runtime_set_autosuspend_delay(&i2c->dev,
+					 AK8974_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(&i2c->dev);
+	pm_runtime_put(&i2c->dev);
+
 	return 0;
 
 cleanup_buffer:
@@ -855,7 +861,6 @@ disable_pm:
 	pm_runtime_put_noidle(&i2c->dev);
 	pm_runtime_disable(&i2c->dev);
 	ak8974_set_power(ak8974, AK8974_PWR_OFF);
-power_off:
 	regulator_bulk_disable(ARRAY_SIZE(ak8974->regs), ak8974->regs);
 
 	return ret;
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index 4ff883942f7b..b08bd9929569 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -381,6 +381,12 @@ struct ak8975_data {
 	struct iio_mount_matrix orientation;
 	struct regulator	*vdd;
 	struct regulator	*vid;
+
+	/* Ensure natural alignment of timestamp */
+	struct {
+		s16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 /* Enable attached power regulator if any. */
@@ -815,7 +821,6 @@ static void ak8975_fill_buffer(struct iio_dev *indio_dev)
 	const struct i2c_client *client = data->client;
 	const struct ak_def *def = data->def;
 	int ret;
-	s16 buff[8]; /* 3 x 16 bits axis values + 1 aligned 64 bits timestamp */
 	__le16 fval[3];
 
 	mutex_lock(&data->lock);
@@ -838,12 +843,13 @@ static void ak8975_fill_buffer(struct iio_dev *indio_dev)
 	mutex_unlock(&data->lock);
 
 	/* Clamp to valid range. */
-	buff[0] = clamp_t(s16, le16_to_cpu(fval[0]), -def->range, def->range);
-	buff[1] = clamp_t(s16, le16_to_cpu(fval[1]), -def->range, def->range);
-	buff[2] = clamp_t(s16, le16_to_cpu(fval[2]), -def->range, def->range);
+	data->scan.channels[0] = clamp_t(s16, le16_to_cpu(fval[0]), -def->range, def->range);
+	data->scan.channels[1] = clamp_t(s16, le16_to_cpu(fval[1]), -def->range, def->range);
+	data->scan.channels[2] = clamp_t(s16, le16_to_cpu(fval[2]), -def->range, def->range);
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buff,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
+
 	return;
 
 unlock:
diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index 5f625ffa2a88..ae415b4e381a 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -182,6 +182,8 @@ static u32 bmp280_compensate_humidity(struct bmp280_data *data,
 		+ (s32)2097152) * H2 + 8192) >> 14);
 	var -= ((((var >> 15) * (var >> 15)) >> 7) * (s32)H1) >> 4;
 
+	var = clamp_val(var, 0, 419430400);
+
 	return var >> 12;
 };
 
@@ -651,7 +653,7 @@ static int bmp180_measure(struct bmp280_data *data, u8 ctrl_meas)
 	unsigned int ctrl;
 
 	if (data->use_eoc)
-		init_completion(&data->done);
+		reinit_completion(&data->done);
 
 	ret = regmap_write(data->regmap, BMP280_REG_CTRL_MEAS, ctrl_meas);
 	if (ret)
@@ -907,6 +909,9 @@ static int bmp085_fetch_eoc_irq(struct device *dev,
 			"trying to enforce it\n");
 		irq_trig = IRQF_TRIGGER_RISING;
 	}
+
+	init_completion(&data->done);
+
 	ret = devm_request_threaded_irq(dev,
 			irq,
 			bmp085_eoc_irq,
diff --git a/drivers/iio/pressure/ms5611_core.c b/drivers/iio/pressure/ms5611_core.c
index 2a77a2f15752..b4b343c3bd87 100644
--- a/drivers/iio/pressure/ms5611_core.c
+++ b/drivers/iio/pressure/ms5611_core.c
@@ -215,16 +215,21 @@ static irqreturn_t ms5611_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ms5611_state *st = iio_priv(indio_dev);
-	s32 buf[4]; /* s32 (pressure) + s32 (temp) + 2 * s32 (timestamp) */
+	/* Ensure buffer elements are naturally aligned */
+	struct {
+		s32 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 	int ret;
 
 	mutex_lock(&st->lock);
-	ret = ms5611_read_temp_and_pressure(indio_dev, &buf[1], &buf[0]);
+	ret = ms5611_read_temp_and_pressure(indio_dev, &scan.channels[1],
+					    &scan.channels[0]);
 	mutex_unlock(&st->lock);
 	if (ret < 0)
 		goto err;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &scan,
 					   iio_get_time_ns(indio_dev));
 
 err:
diff --git a/drivers/iio/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c
index 91431454eb85..7ffc4a6d80cd 100644
--- a/drivers/iio/pressure/zpa2326.c
+++ b/drivers/iio/pressure/zpa2326.c
@@ -672,8 +672,10 @@ static int zpa2326_resume(const struct iio_dev *indio_dev)
 	int err;
 
 	err = pm_runtime_get_sync(indio_dev->dev.parent);
-	if (err < 0)
+	if (err < 0) {
+		pm_runtime_put(indio_dev->dev.parent);
 		return err;
+	}
 
 	if (err > 0) {
 		/*
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index d901591db9c8..6e8af2b91492 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1482,6 +1482,8 @@ static struct rdma_id_private *cma_find_listener(
 {
 	struct rdma_id_private *id_priv, *id_priv_dev;
 
+	lockdep_assert_held(&lock);
+
 	if (!bind_list)
 		return ERR_PTR(-EINVAL);
 
@@ -1530,6 +1532,7 @@ static struct rdma_id_private *cma_id_from_event(struct ib_cm_id *cm_id,
 		}
 	}
 
+	mutex_lock(&lock);
 	/*
 	 * Net namespace might be getting deleted while route lookup,
 	 * cm_id lookup is in progress. Therefore, perform netdevice
@@ -1571,6 +1574,7 @@ static struct rdma_id_private *cma_id_from_event(struct ib_cm_id *cm_id,
 	id_priv = cma_find_listener(bind_list, cm_id, ib_event, &req, *net_dev);
 err:
 	rcu_read_unlock();
+	mutex_unlock(&lock);
 	if (IS_ERR(id_priv) && *net_dev) {
 		dev_put(*net_dev);
 		*net_dev = NULL;
@@ -2287,6 +2291,8 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
 	struct net *net = id_priv->id.route.addr.dev_addr.net;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
 		return;
 
@@ -2993,6 +2999,8 @@ static void cma_bind_port(struct rdma_bind_list *bind_list,
 	u64 sid, mask;
 	__be16 port;
 
+	lockdep_assert_held(&lock);
+
 	addr = cma_src_addr(id_priv);
 	port = htons(bind_list->port);
 
@@ -3021,6 +3029,8 @@ static int cma_alloc_port(enum rdma_port_space ps,
 	struct rdma_bind_list *bind_list;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL);
 	if (!bind_list)
 		return -ENOMEM;
@@ -3047,6 +3057,8 @@ static int cma_port_is_unique(struct rdma_bind_list *bind_list,
 	struct sockaddr  *saddr = cma_src_addr(id_priv);
 	__be16 dport = cma_port(daddr);
 
+	lockdep_assert_held(&lock);
+
 	hlist_for_each_entry(cur_id, &bind_list->owners, node) {
 		struct sockaddr  *cur_daddr = cma_dst_addr(cur_id);
 		struct sockaddr  *cur_saddr = cma_src_addr(cur_id);
@@ -3086,6 +3098,8 @@ static int cma_alloc_any_port(enum rdma_port_space ps,
 	unsigned int rover;
 	struct net *net = id_priv->id.route.addr.dev_addr.net;
 
+	lockdep_assert_held(&lock);
+
 	inet_get_local_port_range(net, &low, &high);
 	remaining = (high - low) + 1;
 	rover = prandom_u32() % remaining + low;
@@ -3133,6 +3147,8 @@ static int cma_check_port(struct rdma_bind_list *bind_list,
 	struct rdma_id_private *cur_id;
 	struct sockaddr *addr, *cur_addr;
 
+	lockdep_assert_held(&lock);
+
 	addr = cma_src_addr(id_priv);
 	hlist_for_each_entry(cur_id, &bind_list->owners, node) {
 		if (id_priv == cur_id)
@@ -3163,6 +3179,8 @@ static int cma_use_port(enum rdma_port_space ps,
 	unsigned short snum;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	snum = ntohs(cma_port(cma_src_addr(id_priv)));
 	if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
 		return -EACCES;
diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c
index 54076a3e8007..ac47e8a1dfbf 100644
--- a/drivers/infiniband/core/cma_configfs.c
+++ b/drivers/infiniband/core/cma_configfs.c
@@ -319,8 +319,21 @@ fail:
 	return ERR_PTR(err);
 }
 
+static void drop_cma_dev(struct config_group *cgroup, struct config_item *item)
+{
+	struct config_group *group =
+		container_of(item, struct config_group, cg_item);
+	struct cma_dev_group *cma_dev_group =
+		container_of(group, struct cma_dev_group, device_group);
+
+	configfs_remove_default_groups(&cma_dev_group->ports_group);
+	configfs_remove_default_groups(&cma_dev_group->device_group);
+	config_item_put(item);
+}
+
 static struct configfs_group_operations cma_subsys_group_ops = {
 	.make_group	= make_cma_dev,
+	.drop_item	= drop_cma_dev,
 };
 
 static struct config_item_type cma_subsys_type = {
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 6072ac7023cb..08d2e9cc28eb 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -2907,6 +2907,7 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 						 DMA_FROM_DEVICE);
 		if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device,
 						  sg_list.addr))) {
+			kfree(mad_priv);
 			ret = -ENOMEM;
 			break;
 		}
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index c3e5f921da12..4002a8ddf6d0 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -1315,13 +1315,13 @@ static ssize_t ucma_set_option(struct ucma_file *file, const char __user *inbuf,
 	if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
 		return -EFAULT;
 
+	if (unlikely(cmd.optlen > KMALLOC_MAX_SIZE))
+		return -EINVAL;
+
 	ctx = ucma_get_ctx(file, cmd.id);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	if (unlikely(cmd.optlen > KMALLOC_MAX_SIZE))
-		return -EINVAL;
-
 	optval = memdup_user((void __user *) (unsigned long) cmd.optval,
 			     cmd.optlen);
 	if (IS_ERR(optval)) {
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 57b41125b146..688ce1846911 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -306,7 +306,8 @@ int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem,
 		vma = find_vma(mm, ib_umem_start(umem));
 		if (!vma || !is_vm_hugetlb_page(vma)) {
 			up_read(&mm->mmap_sem);
-			return -EINVAL;
+			ret_val = -EINVAL;
+			goto out_mm;
 		}
 		h = hstate_vma(vma);
 		umem->page_shift = huge_page_shift(h);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index d21c86dd27d8..01f02b3cb835 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1343,7 +1343,7 @@ int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width)
 
 	dev_put(netdev);
 
-	if (!rc) {
+	if (!rc && lksettings.base.speed != (u32)SPEED_UNKNOWN) {
 		netdev_speed = lksettings.base.speed;
 	} else {
 		netdev_speed = SPEED_1000;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 7eb1cc1b1aa0..5aa545f9a423 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -3265,7 +3265,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		if (raddr->sin_addr.s_addr == htonl(INADDR_ANY)) {
 			err = pick_local_ipaddrs(dev, cm_id);
 			if (err)
-				goto fail2;
+				goto fail3;
 		}
 
 		/* find a route */
@@ -3287,7 +3287,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		if (ipv6_addr_type(&raddr6->sin6_addr) == IPV6_ADDR_ANY) {
 			err = pick_local_ip6addrs(dev, cm_id);
 			if (err)
-				goto fail2;
+				goto fail3;
 		}
 
 		/* find a route */
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index 880c63579ba8..adec03412506 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -2052,9 +2052,9 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev,
 	dst = i40iw_get_dst_ipv6(&src_addr, &dst_addr);
 	if (!dst || dst->error) {
 		if (dst) {
-			dst_release(dst);
 			i40iw_pr_err("ip6_route_output returned dst->error = %d\n",
 				     dst->error);
+			dst_release(dst);
 		}
 		return rc;
 	}
diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c
index d831f3e61ae8..2626205780ee 100644
--- a/drivers/infiniband/hw/qib/qib_sysfs.c
+++ b/drivers/infiniband/hw/qib/qib_sysfs.c
@@ -756,7 +756,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 			"Skipping linkcontrol sysfs info, (err %d) port %u\n",
 			ret, port_num);
-		goto bail;
+		goto bail_link;
 	}
 	kobject_uevent(&ppd->pport_kobj, KOBJ_ADD);
 
@@ -766,7 +766,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 			"Skipping sl2vl sysfs info, (err %d) port %u\n",
 			ret, port_num);
-		goto bail_link;
+		goto bail_sl;
 	}
 	kobject_uevent(&ppd->sl2vl_kobj, KOBJ_ADD);
 
@@ -776,7 +776,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 			"Skipping diag_counters sysfs info, (err %d) port %u\n",
 			ret, port_num);
-		goto bail_sl;
+		goto bail_diagc;
 	}
 	kobject_uevent(&ppd->diagc_kobj, KOBJ_ADD);
 
@@ -789,7 +789,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 		 "Skipping Congestion Control sysfs info, (err %d) port %u\n",
 		 ret, port_num);
-		goto bail_diagc;
+		goto bail_cc;
 	}
 
 	kobject_uevent(&ppd->pport_cc_kobj, KOBJ_ADD);
@@ -871,6 +871,7 @@ void qib_verbs_unregister_sysfs(struct qib_devdata *dd)
 				&cc_table_bin_attr);
 			kobject_put(&ppd->pport_cc_kobj);
 		}
+		kobject_put(&ppd->diagc_kobj);
 		kobject_put(&ppd->sl2vl_kobj);
 		kobject_put(&ppd->pport_kobj);
 	}
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index d549c9ffadcb..867303235f57 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -774,7 +774,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
 	    !(pci_resource_flags(pdev, 1) & IORESOURCE_MEM)) {
 		dev_err(&pdev->dev, "PCI BAR region not MMIO\n");
 		ret = -ENOMEM;
-		goto err_free_device;
+		goto err_disable_pdev;
 	}
 
 	ret = pci_request_regions(pdev, DRV_NAME);
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index 8c3d30b3092d..e6770e5c1432 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -126,6 +126,8 @@ static int rxe_init_device_param(struct rxe_dev *rxe)
 	rxe->attr.max_fast_reg_page_list_len	= RXE_MAX_FMR_PAGE_LIST_LEN;
 	rxe->attr.max_pkeys			= RXE_MAX_PKEYS;
 	rxe->attr.local_ca_ack_delay		= RXE_LOCAL_CA_ACK_DELAY;
+	addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid,
+			rxe->ndev->dev_addr);
 
 	rxe->max_ucontext			= RXE_MAX_UCONTEXT;
 
@@ -170,9 +172,6 @@ static int rxe_init_ports(struct rxe_dev *rxe)
 
 	rxe_init_port_param(port);
 
-	if (!port->attr.pkey_tbl_len || !port->attr.gid_tbl_len)
-		return -EINVAL;
-
 	port->pkey_tbl = kcalloc(port->attr.pkey_tbl_len,
 			sizeof(*port->pkey_tbl), GFP_KERNEL);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 5c2684bf430f..a0d2a2350c7e 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -203,6 +203,7 @@ int rxe_mem_init_user(struct rxe_dev *rxe, struct rxe_pd *pd, u64 start,
 			vaddr = page_address(sg_page(sg));
 			if (!vaddr) {
 				pr_warn("null vaddr\n");
+				ib_umem_release(umem);
 				err = -ENOMEM;
 				goto err1;
 			}
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index 25055a68a2c0..ef7fd5dfad46 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -593,15 +593,16 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask,
 	struct ib_gid_attr sgid_attr;
 
 	if (mask & IB_QP_MAX_QP_RD_ATOMIC) {
-		int max_rd_atomic = __roundup_pow_of_two(attr->max_rd_atomic);
+		int max_rd_atomic = attr->max_rd_atomic ?
+			roundup_pow_of_two(attr->max_rd_atomic) : 0;
 
 		qp->attr.max_rd_atomic = max_rd_atomic;
 		atomic_set(&qp->req.rd_atomic, max_rd_atomic);
 	}
 
 	if (mask & IB_QP_MAX_DEST_RD_ATOMIC) {
-		int max_dest_rd_atomic =
-			__roundup_pow_of_two(attr->max_dest_rd_atomic);
+		int max_dest_rd_atomic = attr->max_dest_rd_atomic ?
+			roundup_pow_of_two(attr->max_dest_rd_atomic) : 0;
 
 		qp->attr.max_dest_rd_atomic = max_dest_rd_atomic;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 1cbf4e407afa..bbd4378e7a96 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -1178,7 +1178,7 @@ static ssize_t parent_show(struct device *device,
 	struct rxe_dev *rxe = container_of(device, struct rxe_dev,
 					   ib_dev.dev);
 
-	return snprintf(buf, 16, "%s\n", rxe_parent_name(rxe, 1));
+	return scnprintf(buf, PAGE_SIZE, "%s\n", rxe_parent_name(rxe, 1));
 }
 
 static DEVICE_ATTR_RO(parent);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 4a5c7a07a631..268e23ba4a63 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -509,7 +509,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev);
 
 int ipoib_ib_dev_open_default(struct net_device *dev);
 int ipoib_ib_dev_open(struct net_device *dev);
-int ipoib_ib_dev_stop(struct net_device *dev);
+void ipoib_ib_dev_stop(struct net_device *dev);
 void ipoib_ib_dev_up(struct net_device *dev);
 void ipoib_ib_dev_down(struct net_device *dev);
 int ipoib_ib_dev_stop_default(struct net_device *dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index d77e8e2ae05f..8e1f48fe6f2e 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -809,7 +809,7 @@ timeout:
 	return 0;
 }
 
-int ipoib_ib_dev_stop(struct net_device *dev)
+void ipoib_ib_dev_stop(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 
@@ -817,8 +817,6 @@ int ipoib_ib_dev_stop(struct net_device *dev)
 
 	clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
 	ipoib_flush_ah(dev);
-
-	return 0;
 }
 
 void ipoib_ib_tx_timer_func(unsigned long ctx)
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index 925571475005..2463d02e3f99 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -342,20 +342,6 @@ static int evdev_fasync(int fd, struct file *file, int on)
 	return fasync_helper(fd, file, on, &client->fasync);
 }
 
-static int evdev_flush(struct file *file, fl_owner_t id)
-{
-	struct evdev_client *client = file->private_data;
-	struct evdev *evdev = client->evdev;
-
-	mutex_lock(&evdev->mutex);
-
-	if (evdev->exist && !client->revoked)
-		input_flush_device(&evdev->handle, file);
-
-	mutex_unlock(&evdev->mutex);
-	return 0;
-}
-
 static void evdev_free(struct device *dev)
 {
 	struct evdev *evdev = container_of(dev, struct evdev, dev);
@@ -469,6 +455,10 @@ static int evdev_release(struct inode *inode, struct file *file)
 	unsigned int i;
 
 	mutex_lock(&evdev->mutex);
+
+	if (evdev->exist && !client->revoked)
+		input_flush_device(&evdev->handle, file);
+
 	evdev_ungrab(evdev, client);
 	mutex_unlock(&evdev->mutex);
 
@@ -1331,7 +1321,6 @@ static const struct file_operations evdev_fops = {
 	.compat_ioctl	= evdev_ioctl_compat,
 #endif
 	.fasync		= evdev_fasync,
-	.flush		= evdev_flush,
 	.llseek		= no_llseek,
 };
 
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 26476a64e663..54a6691d7d87 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -476,6 +476,16 @@ static const u8 xboxone_fw2015_init[] = {
 };
 
 /*
+ * This packet is required for Xbox One S (0x045e:0x02ea)
+ * and Xbox One Elite Series 2 (0x045e:0x0b00) pads to
+ * initialize the controller that was previously used in
+ * Bluetooth mode.
+ */
+static const u8 xboxone_s_init[] = {
+	0x05, 0x20, 0x00, 0x0f, 0x06
+};
+
+/*
  * This packet is required for the Titanfall 2 Xbox One pads
  * (0x0e6f:0x0165) to finish initialization and for Hori pads
  * (0x0f0d:0x0067) to make the analog sticks work.
@@ -533,6 +543,8 @@ static const struct xboxone_init_packet xboxone_init_packets[] = {
 	XBOXONE_INIT_PKT(0x0e6f, 0x0165, xboxone_hori_init),
 	XBOXONE_INIT_PKT(0x0f0d, 0x0067, xboxone_hori_init),
 	XBOXONE_INIT_PKT(0x0000, 0x0000, xboxone_fw2015_init),
+	XBOXONE_INIT_PKT(0x045e, 0x02ea, xboxone_s_init),
+	XBOXONE_INIT_PKT(0x045e, 0x0b00, xboxone_s_init),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_init1),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_init2),
 	XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init),
diff --git a/drivers/input/keyboard/dlink-dir685-touchkeys.c b/drivers/input/keyboard/dlink-dir685-touchkeys.c
index 88e321b76397..6fe4062e3ac2 100644
--- a/drivers/input/keyboard/dlink-dir685-touchkeys.c
+++ b/drivers/input/keyboard/dlink-dir685-touchkeys.c
@@ -142,7 +142,7 @@ MODULE_DEVICE_TABLE(of, dir685_tk_of_match);
 
 static struct i2c_driver dir685_tk_i2c_driver = {
 	.driver = {
-		.name	= "dlin-dir685-touchkeys",
+		.name	= "dlink-dir685-touchkeys",
 		.of_match_table = of_match_ptr(dir685_tk_of_match),
 	},
 	.probe		= dir685_tk_probe,
diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c
index 8ac9e03c05b4..ca8f726dab2e 100644
--- a/drivers/input/mouse/psmouse-base.c
+++ b/drivers/input/mouse/psmouse-base.c
@@ -2012,7 +2012,7 @@ static int psmouse_get_maxproto(char *buffer, const struct kernel_param *kp)
 {
 	int type = *((unsigned int *)kp->arg);
 
-	return sprintf(buffer, "%s", psmouse_protocol_by_type(type)->name);
+	return sprintf(buffer, "%s\n", psmouse_protocol_by_type(type)->name);
 }
 
 static int __init psmouse_init(void)
diff --git a/drivers/input/mouse/sentelic.c b/drivers/input/mouse/sentelic.c
index 11c32ac8234b..779d0b9341c0 100644
--- a/drivers/input/mouse/sentelic.c
+++ b/drivers/input/mouse/sentelic.c
@@ -454,7 +454,7 @@ static ssize_t fsp_attr_set_setreg(struct psmouse *psmouse, void *data,
 
 	fsp_reg_write_enable(psmouse, false);
 
-	return count;
+	return retval;
 }
 
 PSMOUSE_DEFINE_WO_ATTR(setreg, S_IWUSR, NULL, fsp_attr_set_setreg);
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 2bca84f4c2b2..0714d572e49a 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -173,6 +173,7 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN005b", /* P50 */
 	"LEN005e", /* T560 */
 	"LEN006c", /* T470s */
+	"LEN007a", /* T470s */
 	"LEN0071", /* T480 */
 	"LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */
 	"LEN0073", /* X1 Carbon G5 (Elantech) */
@@ -181,6 +182,7 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN0093", /* T480 */
 	"LEN0096", /* X280 */
 	"LEN0097", /* X280 -> ALPS trackpoint */
+	"LEN0099", /* X1 Extreme 1st */
 	"LEN009b", /* T580 */
 	"LEN200f", /* T450s */
 	"LEN2044", /* L470  */
diff --git a/drivers/input/mouse/trackpoint.c b/drivers/input/mouse/trackpoint.c
index bbd29220dbe9..673bfbb01ca2 100644
--- a/drivers/input/mouse/trackpoint.c
+++ b/drivers/input/mouse/trackpoint.c
@@ -20,10 +20,12 @@
 #include "trackpoint.h"
 
 static const char * const trackpoint_variants[] = {
-	[TP_VARIANT_IBM]	= "IBM",
-	[TP_VARIANT_ALPS]	= "ALPS",
-	[TP_VARIANT_ELAN]	= "Elan",
-	[TP_VARIANT_NXP]	= "NXP",
+	[TP_VARIANT_IBM]		= "IBM",
+	[TP_VARIANT_ALPS]		= "ALPS",
+	[TP_VARIANT_ELAN]		= "Elan",
+	[TP_VARIANT_NXP]		= "NXP",
+	[TP_VARIANT_JYT_SYNAPTICS]	= "JYT_Synaptics",
+	[TP_VARIANT_SYNAPTICS]		= "Synaptics",
 };
 
 /*
@@ -295,6 +297,8 @@ static int trackpoint_start_protocol(struct psmouse *psmouse,
 	case TP_VARIANT_ALPS:
 	case TP_VARIANT_ELAN:
 	case TP_VARIANT_NXP:
+	case TP_VARIANT_JYT_SYNAPTICS:
+	case TP_VARIANT_SYNAPTICS:
 		if (variant_id)
 			*variant_id = param[0];
 		if (firmware_id)
diff --git a/drivers/input/mouse/trackpoint.h b/drivers/input/mouse/trackpoint.h
index 538986e5ac5b..4ebcdf802e9a 100644
--- a/drivers/input/mouse/trackpoint.h
+++ b/drivers/input/mouse/trackpoint.h
@@ -27,10 +27,12 @@
  * 0x01 was the original IBM trackpoint, others implement very limited
  * subset of trackpoint features.
  */
-#define TP_VARIANT_IBM		0x01
-#define TP_VARIANT_ALPS		0x02
-#define TP_VARIANT_ELAN		0x03
-#define TP_VARIANT_NXP		0x04
+#define TP_VARIANT_IBM			0x01
+#define TP_VARIANT_ALPS			0x02
+#define TP_VARIANT_ELAN			0x03
+#define TP_VARIANT_NXP			0x04
+#define TP_VARIANT_JYT_SYNAPTICS	0x05
+#define TP_VARIANT_SYNAPTICS		0x06
 
 /*
  * Commands
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index 997ccae7ee05..30a8d816c45c 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -232,7 +232,7 @@ static irqreturn_t rmi_irq_fn(int irq, void *dev_id)
 
 	if (count) {
 		kfree(attn_data.data);
-		attn_data.data = NULL;
+		drvdata->attn_data.data = NULL;
 	}
 
 	if (!kfifo_is_empty(&drvdata->attn_fifo))
@@ -1220,7 +1220,8 @@ static int rmi_driver_probe(struct device *dev)
 	if (data->input) {
 		rmi_driver_set_input_name(rmi_dev, data->input);
 		if (!rmi_dev->xport->input) {
-			if (input_register_device(data->input)) {
+			retval = input_register_device(data->input);
+			if (retval) {
 				dev_err(dev, "%s: Failed to register input device.\n",
 					__func__);
 				goto err_destroy_functions;
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 0d0f977a2f39..51bd2ebaa342 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -430,6 +430,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 		},
 	},
 	{
+		/* Lenovo XiaoXin Air 12 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "80UN"),
+		},
+	},
+	{
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 1360"),
@@ -545,6 +552,14 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"),
 		},
 	},
+	{
+		/* Entroware Proteus */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Entroware"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"),
+		},
+	},
 	{ }
 };
 
@@ -666,6 +681,21 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"),
 		},
 	},
+	{
+		/* Lenovo ThinkPad Twist S230u */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"),
+		},
+	},
+	{
+		/* Entroware Proteus */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Entroware"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"),
+		},
+	},
 	{ }
 };
 
@@ -695,6 +725,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nopnp_table[] = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"),
 		},
 	},
+	{
+		/* Acer Aspire 5 A515 */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "Grumpy_PK"),
+			DMI_MATCH(DMI_BOARD_VENDOR, "PK"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c
index 2c41107240de..499402a975b3 100644
--- a/drivers/input/touchscreen/usbtouchscreen.c
+++ b/drivers/input/touchscreen/usbtouchscreen.c
@@ -197,6 +197,7 @@ static const struct usb_device_id usbtouch_devices[] = {
 #endif
 
 #ifdef CONFIG_TOUCHSCREEN_USB_IRTOUCH
+	{USB_DEVICE(0x255e, 0x0001), .driver_info = DEVTYPE_IRTOUCH},
 	{USB_DEVICE(0x595a, 0x0001), .driver_info = DEVTYPE_IRTOUCH},
 	{USB_DEVICE(0x6615, 0x0001), .driver_info = DEVTYPE_IRTOUCH},
 	{USB_DEVICE(0x6615, 0x0012), .driver_info = DEVTYPE_IRTOUCH_HIRES},
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 778f167be2d3..494caaa265af 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -4394,9 +4394,10 @@ int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
 	if (!fn)
 		return -ENOMEM;
 	iommu->ir_domain = irq_domain_create_tree(fn, &amd_ir_domain_ops, iommu);
-	irq_domain_free_fwnode(fn);
-	if (!iommu->ir_domain)
+	if (!iommu->ir_domain) {
+		irq_domain_free_fwnode(fn);
 		return -ENOMEM;
+	}
 
 	iommu->ir_domain->parent = arch_get_ir_parent_domain();
 	iommu->msi_domain = arch_create_remap_msi_irq_domain(iommu->ir_domain,
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 13485a40dd46..f4ebef29c644 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -1296,13 +1296,17 @@ static int exynos_iommu_of_xlate(struct device *dev,
 		return -ENODEV;
 
 	data = platform_get_drvdata(sysmmu);
-	if (!data)
+	if (!data) {
+		put_device(&sysmmu->dev);
 		return -ENODEV;
+	}
 
 	if (!owner) {
 		owner = kzalloc(sizeof(*owner), GFP_KERNEL);
-		if (!owner)
+		if (!owner) {
+			put_device(&sysmmu->dev);
 			return -ENOMEM;
+		}
 
 		INIT_LIST_HEAD(&owner->controllers);
 		mutex_init(&owner->rpm_lock);
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 25842b566c39..09c6b17aaf80 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -479,12 +479,18 @@ static void iommu_enable_irq_remapping(struct intel_iommu *iommu)
 
 	/* Enable interrupt-remapping */
 	iommu->gcmd |= DMA_GCMD_IRE;
-	iommu->gcmd &= ~DMA_GCMD_CFI;  /* Block compatibility-format MSIs */
 	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
-
 	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
 		      readl, (sts & DMA_GSTS_IRES), sts);
 
+	/* Block compatibility-format MSIs */
+	if (sts & DMA_GSTS_CFIS) {
+		iommu->gcmd &= ~DMA_GCMD_CFI;
+		writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+		IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+			      readl, !(sts & DMA_GSTS_CFIS), sts);
+	}
+
 	/*
 	 * With CFI clear in the Global Command register, we should be
 	 * protected from dangerous (i.e. compatibility) interrupts
@@ -536,8 +542,8 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 					    0, INTR_REMAP_TABLE_ENTRIES,
 					    fn, &intel_ir_domain_ops,
 					    iommu);
-	irq_domain_free_fwnode(fn);
 	if (!iommu->ir_domain) {
+		irq_domain_free_fwnode(fn);
 		pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id);
 		goto out_free_bitmap;
 	}
@@ -601,13 +607,21 @@ out_free_table:
 
 static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
 {
+	struct fwnode_handle *fn;
+
 	if (iommu && iommu->ir_table) {
 		if (iommu->ir_msi_domain) {
+			fn = iommu->ir_msi_domain->fwnode;
+
 			irq_domain_remove(iommu->ir_msi_domain);
+			irq_domain_free_fwnode(fn);
 			iommu->ir_msi_domain = NULL;
 		}
 		if (iommu->ir_domain) {
+			fn = iommu->ir_domain->fwnode;
+
 			irq_domain_remove(iommu->ir_domain);
+			irq_domain_free_fwnode(fn);
 			iommu->ir_domain = NULL;
 		}
 		free_pages((unsigned long)iommu->ir_table->base,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 2c48a9d6d91e..e0a6ae6a5796 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -359,7 +359,7 @@ struct iommu_group *iommu_group_alloc(void)
 				   NULL, "%d", group->id);
 	if (ret) {
 		ida_simple_remove(&iommu_group_ida, group->id);
-		kfree(group);
+		kobject_put(&group->kobj);
 		return ERR_PTR(ret);
 	}
 
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 4edf65dbbcab..2c97d2552c5b 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -845,7 +845,9 @@ iova_magazine_free_pfns(struct iova_magazine *mag, struct iova_domain *iovad)
 	for (i = 0 ; i < mag->size; ++i) {
 		struct iova *iova = private_find_iova(iovad, mag->pfns[i]);
 
-		BUG_ON(!iova);
+		if (WARN_ON(!iova))
+			continue;
+
 		private_free_iova(iovad, iova);
 	}
 
diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c
index 505548aafeff..cec33e90e399 100644
--- a/drivers/iommu/omap-iommu-debug.c
+++ b/drivers/iommu/omap-iommu-debug.c
@@ -101,8 +101,11 @@ static ssize_t debug_read_regs(struct file *file, char __user *userbuf,
 	mutex_lock(&iommu_debug_lock);
 
 	bytes = omap_iommu_dump_ctx(obj, p, count);
+	if (bytes < 0)
+		goto err;
 	bytes = simple_read_from_buffer(userbuf, count, ppos, buf, bytes);
 
+err:
 	mutex_unlock(&iommu_debug_lock);
 	kfree(buf);
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 84b23d902d5b..1d2267c6d31a 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2199,6 +2199,7 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 {
 	msi_alloc_info_t *info = args;
 	struct its_device *its_dev = info->scratchpad[0].ptr;
+	struct irq_data *irqd;
 	irq_hw_number_t hwirq;
 	int err;
 	int i;
@@ -2214,7 +2215,9 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 
 		irq_domain_set_hwirq_and_chip(domain, virq + i,
 					      hwirq + i, &its_irq_chip, its_dev);
-		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq + i)));
+		irqd = irq_get_irq_data(virq + i);
+		irqd_set_single_target(irqd);
+		irqd_set_affinity_on_activate(irqd);
 		pr_debug("ID:%d pID:%d vID:%d\n",
 			 (int)(hwirq + i - its_dev->event_map.lpi_base),
 			 (int)(hwirq + i), virq + i);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 651d726e8b12..eef4f8192068 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -324,10 +324,8 @@ static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
-	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
-	unsigned int cpu, shift = (gic_irq(d) % 4) * 8;
-	u32 val, mask, bit;
-	unsigned long flags;
+	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + gic_irq(d);
+	unsigned int cpu;
 
 	if (!force)
 		cpu = cpumask_any_and(mask_val, cpu_online_mask);
@@ -337,13 +335,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
-	gic_lock_irqsave(flags);
-	mask = 0xff << shift;
-	bit = gic_cpu_map[cpu] << shift;
-	val = readl_relaxed(reg) & ~mask;
-	writel_relaxed(val | bit, reg);
-	gic_unlock_irqrestore(flags);
-
+	writeb_relaxed(gic_cpu_map[cpu], reg);
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
 	return IRQ_SET_MASK_OK_DONE;
diff --git a/drivers/irqchip/irq-mtk-sysirq.c b/drivers/irqchip/irq-mtk-sysirq.c
index 90aaf190157f..42455f31b061 100644
--- a/drivers/irqchip/irq-mtk-sysirq.c
+++ b/drivers/irqchip/irq-mtk-sysirq.c
@@ -23,7 +23,7 @@
 #include <linux/spinlock.h>
 
 struct mtk_sysirq_chip_data {
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	u32 nr_intpol_bases;
 	void __iomem **intpol_bases;
 	u32 *intpol_words;
@@ -45,7 +45,7 @@ static int mtk_sysirq_set_type(struct irq_data *data, unsigned int type)
 	reg_index = chip_data->which_word[hwirq];
 	offset = hwirq & 0x1f;
 
-	spin_lock_irqsave(&chip_data->lock, flags);
+	raw_spin_lock_irqsave(&chip_data->lock, flags);
 	value = readl_relaxed(base + reg_index * 4);
 	if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_EDGE_FALLING) {
 		if (type == IRQ_TYPE_LEVEL_LOW)
@@ -61,7 +61,7 @@ static int mtk_sysirq_set_type(struct irq_data *data, unsigned int type)
 
 	data = data->parent_data;
 	ret = data->chip->irq_set_type(data, type);
-	spin_unlock_irqrestore(&chip_data->lock, flags);
+	raw_spin_unlock_irqrestore(&chip_data->lock, flags);
 	return ret;
 }
 
@@ -220,7 +220,7 @@ static int __init mtk_sysirq_of_init(struct device_node *node,
 		ret = -ENOMEM;
 		goto out_free_which_word;
 	}
-	spin_lock_init(&chip_data->lock);
+	raw_spin_lock_init(&chip_data->lock);
 
 	return 0;
 
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index b0e2d55acbd6..6c7269fcfa77 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -173,6 +173,7 @@ void led_classdev_suspend(struct led_classdev *led_cdev)
 {
 	led_cdev->flags |= LED_SUSPENDED;
 	led_set_brightness_nopm(led_cdev, 0);
+	flush_work(&led_cdev->set_brightness_work);
 }
 EXPORT_SYMBOL_GPL(led_classdev_suspend);
 
diff --git a/drivers/leds/leds-88pm860x.c b/drivers/leds/leds-88pm860x.c
index 77a104d2b124..13f414ff6fd0 100644
--- a/drivers/leds/leds-88pm860x.c
+++ b/drivers/leds/leds-88pm860x.c
@@ -207,21 +207,33 @@ static int pm860x_led_probe(struct platform_device *pdev)
 	data->cdev.brightness_set_blocking = pm860x_led_set;
 	mutex_init(&data->lock);
 
-	ret = devm_led_classdev_register(chip->dev, &data->cdev);
+	ret = led_classdev_register(chip->dev, &data->cdev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to register LED: %d\n", ret);
 		return ret;
 	}
 	pm860x_led_set(&data->cdev, 0);
+
+	platform_set_drvdata(pdev, data);
+
 	return 0;
 }
 
+static int pm860x_led_remove(struct platform_device *pdev)
+{
+	struct pm860x_led *data = platform_get_drvdata(pdev);
+
+	led_classdev_unregister(&data->cdev);
+
+	return 0;
+}
 
 static struct platform_driver pm860x_led_driver = {
 	.driver	= {
 		.name	= "88pm860x-led",
 	},
 	.probe	= pm860x_led_probe,
+	.remove	= pm860x_led_remove,
 };
 
 module_platform_driver(pm860x_led_driver);
diff --git a/drivers/leds/leds-da903x.c b/drivers/leds/leds-da903x.c
index 5ff7d72f73aa..ecc265bb69a0 100644
--- a/drivers/leds/leds-da903x.c
+++ b/drivers/leds/leds-da903x.c
@@ -113,12 +113,23 @@ static int da903x_led_probe(struct platform_device *pdev)
 	led->flags = pdata->flags;
 	led->master = pdev->dev.parent;
 
-	ret = devm_led_classdev_register(led->master, &led->cdev);
+	ret = led_classdev_register(led->master, &led->cdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register LED %d\n", id);
 		return ret;
 	}
 
+	platform_set_drvdata(pdev, led);
+
+	return 0;
+}
+
+static int da903x_led_remove(struct platform_device *pdev)
+{
+	struct da903x_led *led = platform_get_drvdata(pdev);
+
+	led_classdev_unregister(&led->cdev);
+
 	return 0;
 }
 
@@ -127,6 +138,7 @@ static struct platform_driver da903x_led_driver = {
 		.name	= "da903x-led",
 	},
 	.probe		= da903x_led_probe,
+	.remove		= da903x_led_remove,
 };
 
 module_platform_driver(da903x_led_driver);
diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c
index 72224b599ffc..c1e562a4d6ad 100644
--- a/drivers/leds/leds-lm3533.c
+++ b/drivers/leds/leds-lm3533.c
@@ -698,7 +698,7 @@ static int lm3533_led_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, led);
 
-	ret = devm_led_classdev_register(pdev->dev.parent, &led->cdev);
+	ret = led_classdev_register(pdev->dev.parent, &led->cdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register LED %d\n", pdev->id);
 		return ret;
@@ -708,13 +708,18 @@ static int lm3533_led_probe(struct platform_device *pdev)
 
 	ret = lm3533_led_setup(led, pdata);
 	if (ret)
-		return ret;
+		goto err_deregister;
 
 	ret = lm3533_ctrlbank_enable(&led->cb);
 	if (ret)
-		return ret;
+		goto err_deregister;
 
 	return 0;
+
+err_deregister:
+	led_classdev_unregister(&led->cdev);
+
+	return ret;
 }
 
 static int lm3533_led_remove(struct platform_device *pdev)
@@ -724,6 +729,7 @@ static int lm3533_led_remove(struct platform_device *pdev)
 	dev_dbg(&pdev->dev, "%s\n", __func__);
 
 	lm3533_ctrlbank_disable(&led->cb);
+	led_classdev_unregister(&led->cdev);
 
 	return 0;
 }
diff --git a/drivers/leds/leds-lm355x.c b/drivers/leds/leds-lm355x.c
index 6cb94f9a2f3f..b9c60dd2b132 100644
--- a/drivers/leds/leds-lm355x.c
+++ b/drivers/leds/leds-lm355x.c
@@ -168,18 +168,19 @@ static int lm355x_chip_init(struct lm355x_chip_data *chip)
 	/* input and output pins configuration */
 	switch (chip->type) {
 	case CHIP_LM3554:
-		reg_val = pdata->pin_tx2 | pdata->ntc_pin;
+		reg_val = (u32)pdata->pin_tx2 | (u32)pdata->ntc_pin;
 		ret = regmap_update_bits(chip->regmap, 0xE0, 0x28, reg_val);
 		if (ret < 0)
 			goto out;
-		reg_val = pdata->pass_mode;
+		reg_val = (u32)pdata->pass_mode;
 		ret = regmap_update_bits(chip->regmap, 0xA0, 0x04, reg_val);
 		if (ret < 0)
 			goto out;
 		break;
 
 	case CHIP_LM3556:
-		reg_val = pdata->pin_tx2 | pdata->ntc_pin | pdata->pass_mode;
+		reg_val = (u32)pdata->pin_tx2 | (u32)pdata->ntc_pin |
+		          (u32)pdata->pass_mode;
 		ret = regmap_update_bits(chip->regmap, 0x0A, 0xC4, reg_val);
 		if (ret < 0)
 			goto out;
diff --git a/drivers/leds/leds-wm831x-status.c b/drivers/leds/leds-wm831x-status.c
index be93b20e792a..4f0ba19c3577 100644
--- a/drivers/leds/leds-wm831x-status.c
+++ b/drivers/leds/leds-wm831x-status.c
@@ -283,12 +283,23 @@ static int wm831x_status_probe(struct platform_device *pdev)
 	drvdata->cdev.blink_set = wm831x_status_blink_set;
 	drvdata->cdev.groups = wm831x_status_groups;
 
-	ret = devm_led_classdev_register(wm831x->dev, &drvdata->cdev);
+	ret = led_classdev_register(wm831x->dev, &drvdata->cdev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to register LED: %d\n", ret);
 		return ret;
 	}
 
+	platform_set_drvdata(pdev, drvdata);
+
+	return 0;
+}
+
+static int wm831x_status_remove(struct platform_device *pdev)
+{
+	struct wm831x_status *drvdata = platform_get_drvdata(pdev);
+
+	led_classdev_unregister(&drvdata->cdev);
+
 	return 0;
 }
 
@@ -297,6 +308,7 @@ static struct platform_driver wm831x_status_driver = {
 		   .name = "wm831x-status",
 		   },
 	.probe = wm831x_status_probe,
+	.remove = wm831x_status_remove,
 };
 
 module_platform_driver(wm831x_status_driver);
diff --git a/drivers/macintosh/windfarm_pm112.c b/drivers/macintosh/windfarm_pm112.c
index 96d16fca68b2..088ca17a843d 100644
--- a/drivers/macintosh/windfarm_pm112.c
+++ b/drivers/macintosh/windfarm_pm112.c
@@ -133,14 +133,6 @@ static int create_cpu_loop(int cpu)
 	s32 tmax;
 	int fmin;
 
-	/* Get PID params from the appropriate SAT */
-	hdr = smu_sat_get_sdb_partition(chip, 0xC8 + core, NULL);
-	if (hdr == NULL) {
-		printk(KERN_WARNING"windfarm: can't get CPU PID fan config\n");
-		return -EINVAL;
-	}
-	piddata = (struct smu_sdbp_cpupiddata *)&hdr[1];
-
 	/* Get FVT params to get Tmax; if not found, assume default */
 	hdr = smu_sat_get_sdb_partition(chip, 0xC4 + core, NULL);
 	if (hdr) {
@@ -153,6 +145,16 @@ static int create_cpu_loop(int cpu)
 	if (tmax < cpu_all_tmax)
 		cpu_all_tmax = tmax;
 
+	kfree(hdr);
+
+	/* Get PID params from the appropriate SAT */
+	hdr = smu_sat_get_sdb_partition(chip, 0xC8 + core, NULL);
+	if (hdr == NULL) {
+		printk(KERN_WARNING"windfarm: can't get CPU PID fan config\n");
+		return -EINVAL;
+	}
+	piddata = (struct smu_sdbp_cpupiddata *)&hdr[1];
+
 	/*
 	 * Darwin has a minimum fan speed of 1000 rpm for the 4-way and
 	 * 515 for the 2-way.  That appears to be overkill, so for now,
@@ -175,6 +177,9 @@ static int create_cpu_loop(int cpu)
 		pid.min = fmin;
 
 	wf_cpu_pid_init(&cpu_pid[cpu], &pid);
+
+	kfree(hdr);
+
 	return 0;
 }
 
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index e4a3f692057b..a3763d664a67 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -548,6 +548,7 @@ struct cache_set {
 	 */
 	wait_queue_head_t	btree_cache_wait;
 	struct task_struct	*btree_cache_alloc_lock;
+	spinlock_t		btree_cannibalize_lock;
 
 	/*
 	 * When we free a btree node, we increment the gen of the bucket the
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 1edf9515345e..03fb06c61e1c 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -319,7 +319,7 @@ int bch_btree_keys_alloc(struct btree_keys *b, unsigned page_order, gfp_t gfp)
 
 	b->page_order = page_order;
 
-	t->data = (void *) __get_free_pages(gfp, b->page_order);
+	t->data = (void *) __get_free_pages(__GFP_COMP|gfp, b->page_order);
 	if (!t->data)
 		goto err;
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 96a6583e7b52..fba0fff8040d 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -794,7 +794,7 @@ int bch_btree_cache_alloc(struct cache_set *c)
 	mutex_init(&c->verify_lock);
 
 	c->verify_ondisk = (void *)
-		__get_free_pages(GFP_KERNEL, ilog2(bucket_pages(c)));
+		__get_free_pages(GFP_KERNEL|__GFP_COMP, ilog2(bucket_pages(c)));
 
 	c->verify_data = mca_bucket_alloc(c, &ZERO_KEY, GFP_KERNEL);
 
@@ -840,15 +840,17 @@ out:
 
 static int mca_cannibalize_lock(struct cache_set *c, struct btree_op *op)
 {
-	struct task_struct *old;
-
-	old = cmpxchg(&c->btree_cache_alloc_lock, NULL, current);
-	if (old && old != current) {
+	spin_lock(&c->btree_cannibalize_lock);
+	if (likely(c->btree_cache_alloc_lock == NULL)) {
+		c->btree_cache_alloc_lock = current;
+	} else if (c->btree_cache_alloc_lock != current) {
 		if (op)
 			prepare_to_wait(&c->btree_cache_wait, &op->wait,
 					TASK_UNINTERRUPTIBLE);
+		spin_unlock(&c->btree_cannibalize_lock);
 		return -EINTR;
 	}
+	spin_unlock(&c->btree_cannibalize_lock);
 
 	return 0;
 }
@@ -883,10 +885,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op,
  */
 static void bch_cannibalize_unlock(struct cache_set *c)
 {
+	spin_lock(&c->btree_cannibalize_lock);
 	if (c->btree_cache_alloc_lock == current) {
 		c->btree_cache_alloc_lock = NULL;
 		wake_up(&c->btree_cache_wait);
 	}
+	spin_unlock(&c->btree_cannibalize_lock);
 }
 
 static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op,
@@ -1374,7 +1378,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 			if (__set_blocks(n1, n1->keys + n2->keys,
 					 block_bytes(b->c)) >
 			    btree_blocks(new_nodes[i]))
-				goto out_nocoalesce;
+				goto out_unlock_nocoalesce;
 
 			keys = n2->keys;
 			/* Take the key of the node we're getting rid of */
@@ -1403,7 +1407,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 
 		if (__bch_keylist_realloc(&keylist,
 					  bkey_u64s(&new_nodes[i]->key)))
-			goto out_nocoalesce;
+			goto out_unlock_nocoalesce;
 
 		bch_btree_node_write(new_nodes[i], &cl);
 		bch_keylist_add(&keylist, &new_nodes[i]->key);
@@ -1449,6 +1453,10 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 	/* Invalidated our iterator */
 	return -EINTR;
 
+out_unlock_nocoalesce:
+	for (i = 0; i < nodes; i++)
+		mutex_unlock(&new_nodes[i]->write_lock);
+
 out_nocoalesce:
 	closure_sync(&cl);
 	bch_keylist_free(&keylist);
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 6394be5ee9a8..6aafda26903c 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -838,8 +838,8 @@ int bch_journal_alloc(struct cache_set *c)
 	j->w[1].c = c;
 
 	if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
-	    !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) ||
-	    !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)))
+	    !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS)) ||
+	    !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS)))
 		return -ENOMEM;
 
 	return 0;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 690aeb09bbf5..6bf1559a1f0d 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1468,7 +1468,7 @@ void bch_cache_set_unregister(struct cache_set *c)
 }
 
 #define alloc_bucket_pages(gfp, c)			\
-	((void *) __get_free_pages(__GFP_ZERO|gfp, ilog2(bucket_pages(c))))
+	((void *) __get_free_pages(__GFP_ZERO|__GFP_COMP|gfp, ilog2(bucket_pages(c))))
 
 struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 {
@@ -1510,6 +1510,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	sema_init(&c->sb_write_mutex, 1);
 	mutex_init(&c->bucket_lock);
 	init_waitqueue_head(&c->btree_cache_wait);
+	spin_lock_init(&c->btree_cannibalize_lock);
 	init_waitqueue_head(&c->bucket_wait);
 	init_waitqueue_head(&c->gc_wait);
 	sema_init(&c->uuid_write_mutex, 1);
@@ -1780,7 +1781,14 @@ found:
 	    sysfs_create_link(&c->kobj, &ca->kobj, buf))
 		goto err;
 
-	if (ca->sb.seq > c->sb.seq) {
+	/*
+	 * A special case is both ca->sb.seq and c->sb.seq are 0,
+	 * such condition happens on a new created cache device whose
+	 * super block is never flushed yet. In this case c->sb.version
+	 * and other members should be updated too, otherwise we will
+	 * have a mistaken super block version in cache set.
+	 */
+	if (ca->sb.seq > c->sb.seq || c->sb.seq == 0) {
 		c->sb.version		= ca->sb.version;
 		memcpy(c->sb.set_uuid, ca->sb.set_uuid, 16);
 		c->sb.flags             = ca->sb.flags;
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 394e53afc259..0acd10d3b7bf 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -536,12 +536,16 @@ static int __create_persistent_data_objects(struct dm_cache_metadata *cmd,
 					  CACHE_MAX_CONCURRENT_LOCKS);
 	if (IS_ERR(cmd->bm)) {
 		DMERR("could not create block manager");
-		return PTR_ERR(cmd->bm);
+		r = PTR_ERR(cmd->bm);
+		cmd->bm = NULL;
+		return r;
 	}
 
 	r = __open_or_format_metadata(cmd, may_format_device);
-	if (r)
+	if (r) {
 		dm_block_manager_destroy(cmd->bm);
+		cmd->bm = NULL;
+	}
 
 	return r;
 }
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 69cdb29ef6be..280873b13e74 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -410,7 +410,6 @@ struct cache {
 	spinlock_t lock;
 	struct list_head deferred_cells;
 	struct bio_list deferred_bios;
-	struct bio_list deferred_writethrough_bios;
 	sector_t migration_threshold;
 	wait_queue_head_t migration_wait;
 	atomic_t nr_allocated_migrations;
@@ -446,10 +445,10 @@ struct cache {
 	struct dm_kcopyd_client *copier;
 	struct workqueue_struct *wq;
 	struct work_struct deferred_bio_worker;
-	struct work_struct deferred_writethrough_worker;
 	struct work_struct migration_worker;
 	struct delayed_work waker;
 	struct dm_bio_prison_v2 *prison;
+	struct bio_set *bs;
 
 	mempool_t *migration_pool;
 
@@ -490,15 +489,6 @@ struct per_bio_data {
 	struct dm_bio_prison_cell_v2 *cell;
 	struct dm_hook_info hook_info;
 	sector_t len;
-
-	/*
-	 * writethrough fields.  These MUST remain at the end of this
-	 * structure and the 'cache' member must be the first as it
-	 * is used to determine the offset of the writethrough fields.
-	 */
-	struct cache *cache;
-	dm_cblock_t cblock;
-	struct dm_bio_details bio_details;
 };
 
 struct dm_cache_migration {
@@ -515,19 +505,19 @@ struct dm_cache_migration {
 
 /*----------------------------------------------------------------*/
 
-static bool writethrough_mode(struct cache_features *f)
+static bool writethrough_mode(struct cache *cache)
 {
-	return f->io_mode == CM_IO_WRITETHROUGH;
+	return cache->features.io_mode == CM_IO_WRITETHROUGH;
 }
 
-static bool writeback_mode(struct cache_features *f)
+static bool writeback_mode(struct cache *cache)
 {
-	return f->io_mode == CM_IO_WRITEBACK;
+	return cache->features.io_mode == CM_IO_WRITEBACK;
 }
 
-static inline bool passthrough_mode(struct cache_features *f)
+static inline bool passthrough_mode(struct cache *cache)
 {
-	return unlikely(f->io_mode == CM_IO_PASSTHROUGH);
+	return unlikely(cache->features.io_mode == CM_IO_PASSTHROUGH);
 }
 
 /*----------------------------------------------------------------*/
@@ -537,14 +527,9 @@ static void wake_deferred_bio_worker(struct cache *cache)
 	queue_work(cache->wq, &cache->deferred_bio_worker);
 }
 
-static void wake_deferred_writethrough_worker(struct cache *cache)
-{
-	queue_work(cache->wq, &cache->deferred_writethrough_worker);
-}
-
 static void wake_migration_worker(struct cache *cache)
 {
-	if (passthrough_mode(&cache->features))
+	if (passthrough_mode(cache))
 		return;
 
 	queue_work(cache->wq, &cache->migration_worker);
@@ -618,15 +603,9 @@ static unsigned lock_level(struct bio *bio)
  * Per bio data
  *--------------------------------------------------------------*/
 
-/*
- * If using writeback, leave out struct per_bio_data's writethrough fields.
- */
-#define PB_DATA_SIZE_WB (offsetof(struct per_bio_data, cache))
-#define PB_DATA_SIZE_WT (sizeof(struct per_bio_data))
-
 static size_t get_per_bio_data_size(struct cache *cache)
 {
-	return writethrough_mode(&cache->features) ? PB_DATA_SIZE_WT : PB_DATA_SIZE_WB;
+	return sizeof(struct per_bio_data);
 }
 
 static struct per_bio_data *get_per_bio_data(struct bio *bio, size_t data_size)
@@ -868,16 +847,23 @@ static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio)
 	spin_unlock_irqrestore(&cache->lock, flags);
 }
 
-static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio,
-					  dm_oblock_t oblock)
+static void __remap_to_origin_clear_discard(struct cache *cache, struct bio *bio,
+					    dm_oblock_t oblock, bool bio_has_pbd)
 {
-	// FIXME: this is called way too much.
-	check_if_tick_bio_needed(cache, bio);
+	if (bio_has_pbd)
+		check_if_tick_bio_needed(cache, bio);
 	remap_to_origin(cache, bio);
 	if (bio_data_dir(bio) == WRITE)
 		clear_discard(cache, oblock_to_dblock(cache, oblock));
 }
 
+static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio,
+					  dm_oblock_t oblock)
+{
+	// FIXME: check_if_tick_bio_needed() is called way too much through this interface
+	__remap_to_origin_clear_discard(cache, bio, oblock, true);
+}
+
 static void remap_to_cache_dirty(struct cache *cache, struct bio *bio,
 				 dm_oblock_t oblock, dm_cblock_t cblock)
 {
@@ -937,57 +923,26 @@ static void issue_op(struct bio *bio, void *context)
 	accounted_request(cache, bio);
 }
 
-static void defer_writethrough_bio(struct cache *cache, struct bio *bio)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cache->lock, flags);
-	bio_list_add(&cache->deferred_writethrough_bios, bio);
-	spin_unlock_irqrestore(&cache->lock, flags);
-
-	wake_deferred_writethrough_worker(cache);
-}
-
-static void writethrough_endio(struct bio *bio)
-{
-	struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT);
-
-	dm_unhook_bio(&pb->hook_info, bio);
-
-	if (bio->bi_status) {
-		bio_endio(bio);
-		return;
-	}
-
-	dm_bio_restore(&pb->bio_details, bio);
-	remap_to_cache(pb->cache, bio, pb->cblock);
-
-	/*
-	 * We can't issue this bio directly, since we're in interrupt
-	 * context.  So it gets put on a bio list for processing by the
-	 * worker thread.
-	 */
-	defer_writethrough_bio(pb->cache, bio);
-}
-
 /*
- * FIXME: send in parallel, huge latency as is.
  * When running in writethrough mode we need to send writes to clean blocks
- * to both the cache and origin devices.  In future we'd like to clone the
- * bio and send them in parallel, but for now we're doing them in
- * series as this is easier.
+ * to both the cache and origin devices.  Clone the bio and send them in parallel.
  */
-static void remap_to_origin_then_cache(struct cache *cache, struct bio *bio,
-				       dm_oblock_t oblock, dm_cblock_t cblock)
+static void remap_to_origin_and_cache(struct cache *cache, struct bio *bio,
+				      dm_oblock_t oblock, dm_cblock_t cblock)
 {
-	struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT);
+	struct bio *origin_bio = bio_clone_fast(bio, GFP_NOIO, cache->bs);
 
-	pb->cache = cache;
-	pb->cblock = cblock;
-	dm_hook_bio(&pb->hook_info, bio, writethrough_endio, NULL);
-	dm_bio_record(&pb->bio_details, bio);
+	BUG_ON(!origin_bio);
 
-	remap_to_origin_clear_discard(pb->cache, bio, oblock);
+	bio_chain(origin_bio, bio);
+	/*
+	 * Passing false to __remap_to_origin_clear_discard() skips
+	 * all code that might use per_bio_data (since clone doesn't have it)
+	 */
+	__remap_to_origin_clear_discard(cache, origin_bio, oblock, false);
+	submit_bio(origin_bio);
+
+	remap_to_cache(cache, bio, cblock);
 }
 
 /*----------------------------------------------------------------
@@ -1209,7 +1164,7 @@ static bool bio_writes_complete_block(struct cache *cache, struct bio *bio)
 
 static bool optimisable_bio(struct cache *cache, struct bio *bio, dm_oblock_t block)
 {
-	return writeback_mode(&cache->features) &&
+	return writeback_mode(cache) &&
 		(is_discarded_oblock(cache, block) || bio_writes_complete_block(cache, bio));
 }
 
@@ -1862,7 +1817,7 @@ static int map_bio(struct cache *cache, struct bio *bio, dm_oblock_t block,
 		 * Passthrough always maps to the origin, invalidating any
 		 * cache blocks that are written to.
 		 */
-		if (passthrough_mode(&cache->features)) {
+		if (passthrough_mode(cache)) {
 			if (bio_data_dir(bio) == WRITE) {
 				bio_drop_shared_lock(cache, bio);
 				atomic_inc(&cache->stats.demotion);
@@ -1871,9 +1826,9 @@ static int map_bio(struct cache *cache, struct bio *bio, dm_oblock_t block,
 				remap_to_origin_clear_discard(cache, bio, block);
 
 		} else {
-			if (bio_data_dir(bio) == WRITE && writethrough_mode(&cache->features) &&
+			if (bio_data_dir(bio) == WRITE && writethrough_mode(cache) &&
 			    !is_dirty(cache, cblock)) {
-				remap_to_origin_then_cache(cache, bio, block, cblock);
+				remap_to_origin_and_cache(cache, bio, block, cblock);
 				accounted_begin(cache, bio);
 			} else
 				remap_to_cache_dirty(cache, bio, block, cblock);
@@ -2003,28 +1958,6 @@ static void process_deferred_bios(struct work_struct *ws)
 		schedule_commit(&cache->committer);
 }
 
-static void process_deferred_writethrough_bios(struct work_struct *ws)
-{
-	struct cache *cache = container_of(ws, struct cache, deferred_writethrough_worker);
-
-	unsigned long flags;
-	struct bio_list bios;
-	struct bio *bio;
-
-	bio_list_init(&bios);
-
-	spin_lock_irqsave(&cache->lock, flags);
-	bio_list_merge(&bios, &cache->deferred_writethrough_bios);
-	bio_list_init(&cache->deferred_writethrough_bios);
-	spin_unlock_irqrestore(&cache->lock, flags);
-
-	/*
-	 * These bios have already been through accounted_begin()
-	 */
-	while ((bio = bio_list_pop(&bios)))
-		generic_make_request(bio);
-}
-
 /*----------------------------------------------------------------
  * Main worker loop
  *--------------------------------------------------------------*/
@@ -2132,6 +2065,9 @@ static void destroy(struct cache *cache)
 		kfree(cache->ctr_args[i]);
 	kfree(cache->ctr_args);
 
+	if (cache->bs)
+		bioset_free(cache->bs);
+
 	kfree(cache);
 }
 
@@ -2589,6 +2525,13 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	cache->features = ca->features;
 	ti->per_io_data_size = get_per_bio_data_size(cache);
 
+	if (writethrough_mode(cache)) {
+		/* Create bioset for writethrough bios issued to origin */
+		cache->bs = bioset_create(BIO_POOL_SIZE, 0, 0);
+		if (!cache->bs)
+			goto bad;
+	}
+
 	cache->callbacks.congested_fn = cache_is_congested;
 	dm_table_add_target_callbacks(ti->table, &cache->callbacks);
 
@@ -2649,7 +2592,7 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 		goto bad;
 	}
 
-	if (passthrough_mode(&cache->features)) {
+	if (passthrough_mode(cache)) {
 		bool all_clean;
 
 		r = dm_cache_metadata_all_clean(cache->cmd, &all_clean);
@@ -2670,7 +2613,6 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	spin_lock_init(&cache->lock);
 	INIT_LIST_HEAD(&cache->deferred_cells);
 	bio_list_init(&cache->deferred_bios);
-	bio_list_init(&cache->deferred_writethrough_bios);
 	atomic_set(&cache->nr_allocated_migrations, 0);
 	atomic_set(&cache->nr_io_migrations, 0);
 	init_waitqueue_head(&cache->migration_wait);
@@ -2709,8 +2651,6 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 		goto bad;
 	}
 	INIT_WORK(&cache->deferred_bio_worker, process_deferred_bios);
-	INIT_WORK(&cache->deferred_writethrough_worker,
-		  process_deferred_writethrough_bios);
 	INIT_WORK(&cache->migration_worker, check_migrations);
 	INIT_DELAYED_WORK(&cache->waker, do_waker);
 
@@ -3279,13 +3219,13 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 		else
 			DMEMIT("1 ");
 
-		if (writethrough_mode(&cache->features))
+		if (writethrough_mode(cache))
 			DMEMIT("writethrough ");
 
-		else if (passthrough_mode(&cache->features))
+		else if (passthrough_mode(cache))
 			DMEMIT("passthrough ");
 
-		else if (writeback_mode(&cache->features))
+		else if (writeback_mode(cache))
 			DMEMIT("writeback ");
 
 		else {
@@ -3451,7 +3391,7 @@ static int process_invalidate_cblocks_message(struct cache *cache, unsigned coun
 	unsigned i;
 	struct cblock_range range;
 
-	if (!passthrough_mode(&cache->features)) {
+	if (!passthrough_mode(cache)) {
 		DMERR("%s: cache has to be in passthrough mode for invalidation",
 		      cache_device_name(cache));
 		return -EPERM;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index d9a67759fdb5..5e38ceb36000 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -3088,7 +3088,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	limits->max_segment_size = PAGE_SIZE;
 
 	limits->logical_block_size =
-		max_t(unsigned short, limits->logical_block_size, cc->sector_size);
+		max_t(unsigned, limits->logical_block_size, cc->sector_size);
 	limits->physical_block_size =
 		max_t(unsigned, limits->physical_block_size, cc->sector_size);
 	limits->io_min = max_t(unsigned, limits->io_min, cc->sector_size);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 8b7328666eaa..7c60aace8d25 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1815,7 +1815,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
 	int r;
 
 	current_pgpath = READ_ONCE(m->current_pgpath);
-	if (!current_pgpath)
+	if (!current_pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags))
 		current_pgpath = choose_pgpath(m, 0);
 
 	if (current_pgpath) {
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index eadfcfd106ff..cac8ec16e603 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -95,9 +95,6 @@ static void dm_old_stop_queue(struct request_queue *q)
 
 static void dm_mq_stop_queue(struct request_queue *q)
 {
-	if (blk_mq_queue_stopped(q))
-		return;
-
 	blk_mq_quiesce_queue(q);
 }
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 8f070debe498..777343cff5f1 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -547,14 +547,14 @@ static int adjoin(struct dm_table *table, struct dm_target *ti)
  * On the other hand, dm-switch needs to process bulk data using messages and
  * excessive use of GFP_NOIO could cause trouble.
  */
-static char **realloc_argv(unsigned *array_size, char **old_argv)
+static char **realloc_argv(unsigned *size, char **old_argv)
 {
 	char **argv;
 	unsigned new_size;
 	gfp_t gfp;
 
-	if (*array_size) {
-		new_size = *array_size * 2;
+	if (*size) {
+		new_size = *size * 2;
 		gfp = GFP_KERNEL;
 	} else {
 		new_size = 8;
@@ -562,8 +562,8 @@ static char **realloc_argv(unsigned *array_size, char **old_argv)
 	}
 	argv = kmalloc(new_size * sizeof(*argv), gfp);
 	if (argv) {
-		memcpy(argv, old_argv, *array_size * sizeof(*argv));
-		*array_size = new_size;
+		memcpy(argv, old_argv, *size * sizeof(*argv));
+		*size = new_size;
 	}
 
 	kfree(old_argv);
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index b85a66f42814..29f8a632b42b 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -698,12 +698,16 @@ static int __create_persistent_data_objects(struct dm_pool_metadata *pmd, bool f
 					  THIN_MAX_CONCURRENT_LOCKS);
 	if (IS_ERR(pmd->bm)) {
 		DMERR("could not create block manager");
-		return PTR_ERR(pmd->bm);
+		r = PTR_ERR(pmd->bm);
+		pmd->bm = NULL;
+		return r;
 	}
 
 	r = __open_or_format_metadata(pmd, format_device);
-	if (r)
+	if (r) {
 		dm_block_manager_destroy(pmd->bm);
+		pmd->bm = NULL;
+	}
 
 	return r;
 }
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 4d658a0c6025..c6d3a4bc811c 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -1580,7 +1580,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd)
 			return dzone;
 	}
 
-	return ERR_PTR(-EBUSY);
+	return NULL;
 }
 
 /*
@@ -1600,7 +1600,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd)
 			return zone;
 	}
 
-	return ERR_PTR(-EBUSY);
+	return NULL;
 }
 
 /*
diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c
index 2fad512dce98..1015b200330b 100644
--- a/drivers/md/dm-zoned-reclaim.c
+++ b/drivers/md/dm-zoned-reclaim.c
@@ -350,8 +350,8 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc)
 
 	/* Get a data zone */
 	dzone = dmz_get_zone_for_reclaim(zmd);
-	if (IS_ERR(dzone))
-		return PTR_ERR(dzone);
+	if (!dzone)
+		return -EBUSY;
 
 	start = jiffies;
 
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 497a2bc5da51..9d8d453b2735 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -789,7 +789,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	/* Set target (no write same support) */
-	ti->max_io_len = dev->zone_nr_sectors << 9;
+	ti->max_io_len = dev->zone_nr_sectors;
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
 	ti->num_write_zeroes_bios = 1;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 02ba6849f89d..6e741f19a732 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/blkpg.h>
 #include <linux/bio.h>
@@ -2665,17 +2666,25 @@ EXPORT_SYMBOL_GPL(dm_internal_resume_fast);
 int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
 		       unsigned cookie)
 {
+	int r;
+	unsigned noio_flag;
 	char udev_cookie[DM_COOKIE_LENGTH];
 	char *envp[] = { udev_cookie, NULL };
 
+	noio_flag = memalloc_noio_save();
+
 	if (!cookie)
-		return kobject_uevent(&disk_to_dev(md->disk)->kobj, action);
+		r = kobject_uevent(&disk_to_dev(md->disk)->kobj, action);
 	else {
 		snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u",
 			 DM_COOKIE_ENV_VAR_NAME, cookie);
-		return kobject_uevent_env(&disk_to_dev(md->disk)->kobj,
-					  action, envp);
+		r = kobject_uevent_env(&disk_to_dev(md->disk)->kobj,
+				       action, envp);
 	}
+
+	memalloc_noio_restore(noio_flag);
+
+	return r;
 }
 
 uint32_t dm_next_uevent_seq(struct mapped_device *md)
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 10057ac85476..035d5ec8e677 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -1423,6 +1423,7 @@ static void unlock_all_bitmaps(struct mddev *mddev)
 			}
 		}
 		kfree(cinfo->other_bitmap_lockres);
+		cinfo->other_bitmap_lockres = NULL;
 	}
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index b942c74f1ce8..702a7d2c7e1e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1168,6 +1168,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 			mddev->new_layout = mddev->layout;
 			mddev->new_chunk_sectors = mddev->chunk_sectors;
 		}
+		if (mddev->level == 0)
+			mddev->layout = -1;
 
 		if (sb->state & (1<<MD_SB_CLEAN))
 			mddev->recovery_cp = MaxSector;
@@ -1584,6 +1586,10 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		rdev->ppl.sector = rdev->sb_start + rdev->ppl.offset;
 	}
 
+	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT) &&
+	    sb->level != 0)
+		return -EINVAL;
+
 	if (!refdev) {
 		ret = 1;
 	} else {
@@ -1694,6 +1700,10 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 			mddev->new_chunk_sectors = mddev->chunk_sectors;
 		}
 
+		if (mddev->level == 0 &&
+		    !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT))
+			mddev->layout = -1;
+
 		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
 			set_bit(MD_HAS_JOURNAL, &mddev->flags);
 
@@ -6757,6 +6767,9 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info)
 	mddev->external	     = 0;
 
 	mddev->layout        = info->layout;
+	if (mddev->level == 0)
+		/* Cannot trust RAID0 layout info here */
+		mddev->layout = -1;
 	mddev->chunk_sectors = info->chunk_size >> 9;
 
 	if (mddev->persistent) {
@@ -7411,7 +7424,8 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 		 */
 		mddev_put(mddev);
 		/* Wait until bdev->bd_disk is definitely gone */
-		flush_workqueue(md_misc_wq);
+		if (work_pending(&mddev->del_work))
+			flush_workqueue(md_misc_wq);
 		/* Then retry the open from the top */
 		return -ERESTARTSYS;
 	}
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index cdafa5e0ea6d..e179c121c030 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -152,6 +152,9 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 
 	if (conf->nr_strip_zones == 1) {
 		conf->layout = RAID0_ORIG_LAYOUT;
+	} else if (mddev->layout == RAID0_ORIG_LAYOUT ||
+		   mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = mddev->layout;
 	} else if (default_layout == RAID0_ORIG_LAYOUT ||
 		   default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
 		conf->layout = default_layout;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d5c14d56a714..cd055664dce3 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3593,6 +3593,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 	 * is missing/faulty, then we need to read everything we can.
 	 */
 	if (sh->raid_conf->level != 6 &&
+	    sh->raid_conf->rmw_level != PARITY_DISABLE_RMW &&
 	    sh->sector < sh->raid_conf->mddev->recovery_cp)
 		/* reconstruct-write isn't being forced */
 		return 0;
@@ -4829,7 +4830,7 @@ static void handle_stripe(struct stripe_head *sh)
 	 * or to load a block that is being partially written.
 	 */
 	if (s.to_read || s.non_overwrite
-	    || (conf->level == 6 && s.to_write && s.failed)
+	    || (s.to_write && s.failed)
 	    || (s.syncing && (s.uptodate + s.compute < disks))
 	    || s.replacing
 	    || s.expanding)
diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c
index 0d7d687aeea0..061b7824f698 100644
--- a/drivers/media/cec/cec-adap.c
+++ b/drivers/media/cec/cec-adap.c
@@ -1624,6 +1624,10 @@ int __cec_s_log_addrs(struct cec_adapter *adap,
 		unsigned j;
 
 		log_addrs->log_addr[i] = CEC_LOG_ADDR_INVALID;
+		if (log_addrs->log_addr_type[i] > CEC_LOG_ADDR_TYPE_UNREGISTERED) {
+			dprintk(1, "unknown logical address type\n");
+			return -EINVAL;
+		}
 		if (type_mask & (1 << log_addrs->log_addr_type[i])) {
 			dprintk(1, "duplicate logical address type\n");
 			return -EINVAL;
@@ -1644,10 +1648,6 @@ int __cec_s_log_addrs(struct cec_adapter *adap,
 			dprintk(1, "invalid primary device type\n");
 			return -EINVAL;
 		}
-		if (log_addrs->log_addr_type[i] > CEC_LOG_ADDR_TYPE_UNREGISTERED) {
-			dprintk(1, "unknown logical address type\n");
-			return -EINVAL;
-		}
 		for (j = 0; j < feature_sz; j++) {
 			if ((features[j] & 0x80) == 0) {
 				if (op_is_dev_features)
diff --git a/drivers/media/cec/cec-api.c b/drivers/media/cec/cec-api.c
index 21a5f45e0259..66ef06f4670c 100644
--- a/drivers/media/cec/cec-api.c
+++ b/drivers/media/cec/cec-api.c
@@ -159,7 +159,13 @@ static long cec_adap_g_log_addrs(struct cec_adapter *adap,
 	struct cec_log_addrs log_addrs;
 
 	mutex_lock(&adap->lock);
-	log_addrs = adap->log_addrs;
+	/*
+	 * We use memcpy here instead of assignment since there is a
+	 * hole at the end of struct cec_log_addrs that an assignment
+	 * might ignore. So when we do copy_to_user() we could leak
+	 * one byte of memory.
+	 */
+	memcpy(&log_addrs, &adap->log_addrs, sizeof(log_addrs));
 	if (!adap->is_configured)
 		memset(log_addrs.log_addr, CEC_LOG_ADDR_INVALID,
 		       sizeof(log_addrs.log_addr));
diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c
index a59f4fd09df6..27466b0d0be8 100644
--- a/drivers/media/dvb-frontends/tda10071.c
+++ b/drivers/media/dvb-frontends/tda10071.c
@@ -483,10 +483,11 @@ static int tda10071_read_status(struct dvb_frontend *fe, enum fe_status *status)
 			goto error;
 
 		if (dev->delivery_system == SYS_DVBS) {
-			dev->dvbv3_ber = buf[0] << 24 | buf[1] << 16 |
-					 buf[2] << 8 | buf[3] << 0;
-			dev->post_bit_error += buf[0] << 24 | buf[1] << 16 |
-					       buf[2] << 8 | buf[3] << 0;
+			u32 bit_error = buf[0] << 24 | buf[1] << 16 |
+					buf[2] << 8 | buf[3] << 0;
+
+			dev->dvbv3_ber = bit_error;
+			dev->post_bit_error += bit_error;
 			c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
 			c->post_bit_error.stat[0].uvalue = dev->post_bit_error;
 			dev->block_error += buf[4] << 8 | buf[5] << 0;
diff --git a/drivers/media/firewire/firedtv-fw.c b/drivers/media/firewire/firedtv-fw.c
index 247f0e7cb5f7..5d634706a7ea 100644
--- a/drivers/media/firewire/firedtv-fw.c
+++ b/drivers/media/firewire/firedtv-fw.c
@@ -271,6 +271,8 @@ static int node_probe(struct fw_unit *unit, const struct ieee1394_device_id *id)
 
 	name_len = fw_csr_string(unit->directory, CSR_MODEL,
 				 name, sizeof(name));
+	if (name_len < 0)
+		return name_len;
 	for (i = ARRAY_SIZE(model_names); --i; )
 		if (strlen(model_names[i]) <= name_len &&
 		    strncmp(name, model_names[i], name_len) == 0)
diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 69f564b0837a..eb0331b8a583 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -2298,8 +2298,8 @@ static int ov5640_probe(struct i2c_client *client,
 free_ctrls:
 	v4l2_ctrl_handler_free(&sensor->ctrls.handler);
 entity_cleanup:
-	mutex_destroy(&sensor->lock);
 	media_entity_cleanup(&sensor->sd.entity);
+	mutex_destroy(&sensor->lock);
 	return ret;
 }
 
@@ -2309,9 +2309,9 @@ static int ov5640_remove(struct i2c_client *client)
 	struct ov5640_dev *sensor = to_ov5640_dev(sd);
 
 	v4l2_async_unregister_subdev(&sensor->sd);
-	mutex_destroy(&sensor->lock);
 	media_entity_cleanup(&sensor->sd.entity);
 	v4l2_ctrl_handler_free(&sensor->ctrls.handler);
+	mutex_destroy(&sensor->lock);
 
 	return 0;
 }
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index e4d7f2febf00..05b3974bd920 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -2338,11 +2338,12 @@ smiapp_sysfs_nvm_read(struct device *dev, struct device_attribute *attr,
 		if (rval < 0) {
 			if (rval != -EBUSY && rval != -EAGAIN)
 				pm_runtime_set_active(&client->dev);
-			pm_runtime_put(&client->dev);
+			pm_runtime_put_noidle(&client->dev);
 			return -ENODEV;
 		}
 
 		if (smiapp_read_nvm(sensor, sensor->nvm)) {
+			pm_runtime_put(&client->dev);
 			dev_err(&client->dev, "nvm read failed\n");
 			return -ENODEV;
 		}
diff --git a/drivers/media/pci/cx23885/cx23888-ir.c b/drivers/media/pci/cx23885/cx23888-ir.c
index 040323b0f945..f63a7e6f272c 100644
--- a/drivers/media/pci/cx23885/cx23888-ir.c
+++ b/drivers/media/pci/cx23885/cx23888-ir.c
@@ -1178,8 +1178,11 @@ int cx23888_ir_probe(struct cx23885_dev *dev)
 		return -ENOMEM;
 
 	spin_lock_init(&state->rx_kfifo_lock);
-	if (kfifo_alloc(&state->rx_kfifo, CX23888_IR_RX_KFIFO_SIZE, GFP_KERNEL))
+	if (kfifo_alloc(&state->rx_kfifo, CX23888_IR_RX_KFIFO_SIZE,
+			GFP_KERNEL)) {
+		kfree(state);
 		return -ENOMEM;
+	}
 
 	state->dev = dev;
 	sd = &state->sd;
diff --git a/drivers/media/pci/ttpci/av7110.c b/drivers/media/pci/ttpci/av7110.c
index f46947d8adf8..fcc053d95ae4 100644
--- a/drivers/media/pci/ttpci/av7110.c
+++ b/drivers/media/pci/ttpci/av7110.c
@@ -423,14 +423,15 @@ static void debiirq(unsigned long cookie)
 	case DATA_CI_GET:
 	{
 		u8 *data = av7110->debi_virt;
+		u8 data_0 = data[0];
 
-		if ((data[0] < 2) && data[2] == 0xff) {
+		if (data_0 < 2 && data[2] == 0xff) {
 			int flags = 0;
 			if (data[5] > 0)
 				flags |= CA_CI_MODULE_PRESENT;
 			if (data[5] > 5)
 				flags |= CA_CI_MODULE_READY;
-			av7110->ci_slot[data[0]].flags = flags;
+			av7110->ci_slot[data_0].flags = flags;
 		} else
 			ci_get_data(&av7110->ci_rbuffer,
 				    av7110->debi_virt,
diff --git a/drivers/media/pci/ttpci/budget-core.c b/drivers/media/pci/ttpci/budget-core.c
index 97499b2af714..20524376b83b 100644
--- a/drivers/media/pci/ttpci/budget-core.c
+++ b/drivers/media/pci/ttpci/budget-core.c
@@ -383,20 +383,25 @@ static int budget_register(struct budget *budget)
 	ret = dvbdemux->dmx.add_frontend(&dvbdemux->dmx, &budget->hw_frontend);
 
 	if (ret < 0)
-		return ret;
+		goto err_release_dmx;
 
 	budget->mem_frontend.source = DMX_MEMORY_FE;
 	ret = dvbdemux->dmx.add_frontend(&dvbdemux->dmx, &budget->mem_frontend);
 	if (ret < 0)
-		return ret;
+		goto err_release_dmx;
 
 	ret = dvbdemux->dmx.connect_frontend(&dvbdemux->dmx, &budget->hw_frontend);
 	if (ret < 0)
-		return ret;
+		goto err_release_dmx;
 
 	dvb_net_init(&budget->dvb_adapter, &budget->dvb_net, &dvbdemux->dmx);
 
 	return 0;
+
+err_release_dmx:
+	dvb_dmxdev_release(&budget->dmxdev);
+	dvb_dmx_release(&budget->demux);
+	return ret;
 }
 
 static void budget_unregister(struct budget *budget)
diff --git a/drivers/media/platform/davinci/vpif_capture.c b/drivers/media/platform/davinci/vpif_capture.c
index dc8fc2120b63..acc52d28c5c4 100644
--- a/drivers/media/platform/davinci/vpif_capture.c
+++ b/drivers/media/platform/davinci/vpif_capture.c
@@ -1489,8 +1489,6 @@ probe_out:
 		/* Unregister video device */
 		video_unregister_device(&ch->video_dev);
 	}
-	kfree(vpif_obj.sd);
-	v4l2_device_unregister(&vpif_obj.v4l2_dev);
 
 	return err;
 }
diff --git a/drivers/media/platform/davinci/vpss.c b/drivers/media/platform/davinci/vpss.c
index 2ee4cd9e6d80..d984f45c0314 100644
--- a/drivers/media/platform/davinci/vpss.c
+++ b/drivers/media/platform/davinci/vpss.c
@@ -514,19 +514,31 @@ static void vpss_exit(void)
 
 static int __init vpss_init(void)
 {
+	int ret;
+
 	if (!request_mem_region(VPSS_CLK_CTRL, 4, "vpss_clock_control"))
 		return -EBUSY;
 
 	oper_cfg.vpss_regs_base2 = ioremap(VPSS_CLK_CTRL, 4);
 	if (unlikely(!oper_cfg.vpss_regs_base2)) {
-		release_mem_region(VPSS_CLK_CTRL, 4);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_ioremap;
 	}
 
 	writel(VPSS_CLK_CTRL_VENCCLKEN |
-		     VPSS_CLK_CTRL_DACCLKEN, oper_cfg.vpss_regs_base2);
+	       VPSS_CLK_CTRL_DACCLKEN, oper_cfg.vpss_regs_base2);
+
+	ret = platform_driver_register(&vpss_driver);
+	if (ret)
+		goto err_pd_register;
+
+	return 0;
 
-	return platform_driver_register(&vpss_driver);
+err_pd_register:
+	iounmap(oper_cfg.vpss_regs_base2);
+err_ioremap:
+	release_mem_region(VPSS_CLK_CTRL, 4);
+	return ret;
 }
 subsys_initcall(vpss_init);
 module_exit(vpss_exit);
diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c
index b2eb830c0360..f772c9b92d9b 100644
--- a/drivers/media/platform/exynos4-is/media-dev.c
+++ b/drivers/media/platform/exynos4-is/media-dev.c
@@ -1258,6 +1258,9 @@ static int fimc_md_get_pinctrl(struct fimc_md *fmd)
 
 	pctl->state_idle = pinctrl_lookup_state(pctl->pinctrl,
 					PINCTRL_STATE_IDLE);
+	if (IS_ERR(pctl->state_idle))
+		return PTR_ERR(pctl->state_idle);
+
 	return 0;
 }
 
diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c
index e981eb2330f1..ac005ae4d21b 100644
--- a/drivers/media/platform/omap3isp/isppreview.c
+++ b/drivers/media/platform/omap3isp/isppreview.c
@@ -2290,7 +2290,7 @@ static int preview_init_entities(struct isp_prev_device *prev)
 	me->ops = &preview_media_ops;
 	ret = media_entity_pads_init(me, PREV_PADS_NUM, pads);
 	if (ret < 0)
-		return ret;
+		goto error_handler_free;
 
 	preview_init_formats(sd, NULL);
 
@@ -2323,6 +2323,8 @@ error_video_out:
 	omap3isp_video_cleanup(&prev->video_in);
 error_video_in:
 	media_entity_cleanup(&prev->subdev.entity);
+error_handler_free:
+	v4l2_ctrl_handler_free(&prev->ctrls);
 	return ret;
 }
 
diff --git a/drivers/media/platform/rcar-fcp.c b/drivers/media/platform/rcar-fcp.c
index 2988031d285d..0047d144c932 100644
--- a/drivers/media/platform/rcar-fcp.c
+++ b/drivers/media/platform/rcar-fcp.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -24,6 +25,7 @@
 struct rcar_fcp_device {
 	struct list_head list;
 	struct device *dev;
+	struct device_dma_parameters dma_parms;
 };
 
 static LIST_HEAD(fcp_devices);
@@ -139,6 +141,9 @@ static int rcar_fcp_probe(struct platform_device *pdev)
 
 	fcp->dev = &pdev->dev;
 
+	fcp->dev->dma_parms = &fcp->dma_parms;
+	dma_set_max_seg_size(fcp->dev, DMA_BIT_MASK(32));
+
 	pm_runtime_enable(&pdev->dev);
 
 	mutex_lock(&fcp_lock);
diff --git a/drivers/media/platform/ti-vpe/cal.c b/drivers/media/platform/ti-vpe/cal.c
index b6dcae1ecc1b..ad344e642ddb 100644
--- a/drivers/media/platform/ti-vpe/cal.c
+++ b/drivers/media/platform/ti-vpe/cal.c
@@ -687,12 +687,13 @@ static void pix_proc_config(struct cal_ctx *ctx)
 }
 
 static void cal_wr_dma_config(struct cal_ctx *ctx,
-			      unsigned int width)
+			      unsigned int width, unsigned int height)
 {
 	u32 val;
 
 	val = reg_read(ctx->dev, CAL_WR_DMA_CTRL(ctx->csi2_port));
 	set_field(&val, ctx->csi2_port, CAL_WR_DMA_CTRL_CPORT_MASK);
+	set_field(&val, height, CAL_WR_DMA_CTRL_YSIZE_MASK);
 	set_field(&val, CAL_WR_DMA_CTRL_DTAG_PIX_DAT,
 		  CAL_WR_DMA_CTRL_DTAG_MASK);
 	set_field(&val, CAL_WR_DMA_CTRL_MODE_CONST,
@@ -1318,7 +1319,8 @@ static int cal_start_streaming(struct vb2_queue *vq, unsigned int count)
 	csi2_lane_config(ctx);
 	csi2_ctx_config(ctx);
 	pix_proc_config(ctx);
-	cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline);
+	cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline,
+			  ctx->v_fmt.fmt.pix.height);
 	cal_wr_dma_addr(ctx, addr);
 	csi2_ppi_enable(ctx);
 
diff --git a/drivers/media/rc/gpio-ir-tx.c b/drivers/media/rc/gpio-ir-tx.c
index cd476cab9782..4e70b67ccd18 100644
--- a/drivers/media/rc/gpio-ir-tx.c
+++ b/drivers/media/rc/gpio-ir-tx.c
@@ -87,13 +87,8 @@ static int gpio_ir_tx(struct rc_dev *dev, unsigned int *txbuf,
 			// space
 			edge = ktime_add_us(edge, txbuf[i]);
 			delta = ktime_us_delta(edge, ktime_get());
-			if (delta > 10) {
-				spin_unlock_irqrestore(&gpio_ir->lock, flags);
-				usleep_range(delta, delta + 10);
-				spin_lock_irqsave(&gpio_ir->lock, flags);
-			} else if (delta > 0) {
+			if (delta > 0)
 				udelay(delta);
-			}
 		} else {
 			// pulse
 			ktime_t last = ktime_add_us(edge, txbuf[i]);
diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c
index e35b1faf0ddc..c826997f5433 100644
--- a/drivers/media/tuners/si2157.c
+++ b/drivers/media/tuners/si2157.c
@@ -84,24 +84,23 @@ static int si2157_init(struct dvb_frontend *fe)
 	struct si2157_cmd cmd;
 	const struct firmware *fw;
 	const char *fw_name;
-	unsigned int uitmp, chip_id;
+	unsigned int chip_id, xtal_trim;
 
 	dev_dbg(&client->dev, "\n");
 
-	/* Returned IF frequency is garbage when firmware is not running */
-	memcpy(cmd.args, "\x15\x00\x06\x07", 4);
+	/* Try to get Xtal trim property, to verify tuner still running */
+	memcpy(cmd.args, "\x15\x00\x04\x02", 4);
 	cmd.wlen = 4;
 	cmd.rlen = 4;
 	ret = si2157_cmd_execute(client, &cmd);
-	if (ret)
-		goto err;
 
-	uitmp = cmd.args[2] << 0 | cmd.args[3] << 8;
-	dev_dbg(&client->dev, "if_frequency kHz=%u\n", uitmp);
+	xtal_trim = cmd.args[2] | (cmd.args[3] << 8);
 
-	if (uitmp == dev->if_frequency / 1000)
+	if (ret == 0 && xtal_trim < 16)
 		goto warm;
 
+	dev->if_frequency = 0; /* we no longer know current tuner state */
+
 	/* power up */
 	if (dev->chiptype == SI2157_CHIPTYPE_SI2146) {
 		memcpy(cmd.args, "\xc0\x05\x01\x00\x00\x0b\x00\x00\x01", 9);
diff --git a/drivers/media/usb/dvb-usb/dibusb-mb.c b/drivers/media/usb/dvb-usb/dibusb-mb.c
index a0057641cc86..c55180912c3a 100644
--- a/drivers/media/usb/dvb-usb/dibusb-mb.c
+++ b/drivers/media/usb/dvb-usb/dibusb-mb.c
@@ -84,7 +84,7 @@ static int dibusb_tuner_probe_and_attach(struct dvb_usb_adapter *adap)
 
 	if (i2c_transfer(&adap->dev->i2c_adap, msg, 2) != 2) {
 		err("tuner i2c write failed.");
-		ret = -EREMOTEIO;
+		return -EREMOTEIO;
 	}
 
 	if (adap->fe_adap[0].fe->ops.i2c_gate_ctrl)
diff --git a/drivers/media/usb/go7007/go7007-usb.c b/drivers/media/usb/go7007/go7007-usb.c
index ed9bcaf08d5e..ddfaabd4c081 100644
--- a/drivers/media/usb/go7007/go7007-usb.c
+++ b/drivers/media/usb/go7007/go7007-usb.c
@@ -1052,6 +1052,7 @@ static int go7007_usb_probe(struct usb_interface *intf,
 	struct go7007_usb *usb;
 	const struct go7007_usb_board *board;
 	struct usb_device *usbdev = interface_to_usbdev(intf);
+	struct usb_host_endpoint *ep;
 	unsigned num_i2c_devs;
 	char *name;
 	int video_pipe, i, v_urb_len;
@@ -1147,7 +1148,8 @@ static int go7007_usb_probe(struct usb_interface *intf,
 	if (usb->intr_urb->transfer_buffer == NULL)
 		goto allocfail;
 
-	if (go->board_id == GO7007_BOARDID_SENSORAY_2250)
+	ep = usb->usbdev->ep_in[4];
+	if (usb_endpoint_type(&ep->desc) == USB_ENDPOINT_XFER_BULK)
 		usb_fill_bulk_urb(usb->intr_urb, usb->usbdev,
 			usb_rcvbulkpipe(usb->usbdev, 4),
 			usb->intr_urb->transfer_buffer, 2*sizeof(u16),
diff --git a/drivers/media/usb/go7007/snd-go7007.c b/drivers/media/usb/go7007/snd-go7007.c
index c618764480c6..a19c01083124 100644
--- a/drivers/media/usb/go7007/snd-go7007.c
+++ b/drivers/media/usb/go7007/snd-go7007.c
@@ -243,22 +243,18 @@ int go7007_snd_init(struct go7007 *go)
 	gosnd->capturing = 0;
 	ret = snd_card_new(go->dev, index[dev], id[dev], THIS_MODULE, 0,
 			   &gosnd->card);
-	if (ret < 0) {
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_snd;
+
 	ret = snd_device_new(gosnd->card, SNDRV_DEV_LOWLEVEL, go,
 			&go7007_snd_device_ops);
-	if (ret < 0) {
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_card;
+
 	ret = snd_pcm_new(gosnd->card, "go7007", 0, 0, 1, &gosnd->pcm);
-	if (ret < 0) {
-		snd_card_free(gosnd->card);
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_card;
+
 	strlcpy(gosnd->card->driver, "go7007", sizeof(gosnd->card->driver));
 	strlcpy(gosnd->card->shortname, go->name, sizeof(gosnd->card->driver));
 	strlcpy(gosnd->card->longname, gosnd->card->shortname,
@@ -269,11 +265,8 @@ int go7007_snd_init(struct go7007 *go)
 			&go7007_snd_capture_ops);
 
 	ret = snd_card_register(gosnd->card);
-	if (ret < 0) {
-		snd_card_free(gosnd->card);
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_card;
 
 	gosnd->substream = NULL;
 	go->snd_context = gosnd;
@@ -281,6 +274,12 @@ int go7007_snd_init(struct go7007 *go)
 	++dev;
 
 	return 0;
+
+free_card:
+	snd_card_free(gosnd->card);
+free_snd:
+	kfree(gosnd);
+	return ret;
 }
 EXPORT_SYMBOL(go7007_snd_init);
 
diff --git a/drivers/media/usb/usbtv/usbtv-core.c b/drivers/media/usb/usbtv/usbtv-core.c
index 50a61143898b..bf0e3908cdc4 100644
--- a/drivers/media/usb/usbtv/usbtv-core.c
+++ b/drivers/media/usb/usbtv/usbtv-core.c
@@ -113,7 +113,8 @@ static int usbtv_probe(struct usb_interface *intf,
 
 usbtv_audio_fail:
 	/* we must not free at this point */
-	usb_get_dev(usbtv->udev);
+	v4l2_device_get(&usbtv->v4l2_dev);
+	/* this will undo the v4l2_device_get() */
 	usbtv_video_free(usbtv);
 
 usbtv_video_fail:
diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index 6ba07c7feb92..2af7ae13449d 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -118,8 +118,6 @@ int 		mptscsih_suspend(struct pci_dev *pdev, pm_message_t state);
 int 		mptscsih_resume(struct pci_dev *pdev);
 #endif
 
-#define SNS_LEN(scp)	SCSI_SENSE_BUFFERSIZE
-
 
 /*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
 /*
@@ -2420,7 +2418,7 @@ mptscsih_copy_sense_data(struct scsi_cmnd *sc, MPT_SCSI_HOST *hd, MPT_FRAME_HDR
 		/* Copy the sense received into the scsi command block. */
 		req_index = le16_to_cpu(mf->u.frame.hwhdr.msgctxu.fld.req_idx);
 		sense_data = ((u8 *)ioc->sense_buf_pool + (req_index * MPT_SENSE_BUFFER_ALLOC));
-		memcpy(sc->sense_buffer, sense_data, SNS_LEN(sc));
+		memcpy(sc->sense_buffer, sense_data, MPT_SENSE_BUFFER_ALLOC);
 
 		/* Log SMART data (asc = 0x5D, non-IM case only) if required.
 		 */
diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c
index ad8a5296c50b..9aa33141e7f1 100644
--- a/drivers/mfd/arizona-core.c
+++ b/drivers/mfd/arizona-core.c
@@ -1528,6 +1528,15 @@ err_irq:
 	arizona_irq_exit(arizona);
 err_pm:
 	pm_runtime_disable(arizona->dev);
+
+	switch (arizona->pdata.clk32k_src) {
+	case ARIZONA_32KZ_MCLK1:
+	case ARIZONA_32KZ_MCLK2:
+		arizona_clk32k_disable(arizona);
+		break;
+	default:
+		break;
+	}
 err_reset:
 	arizona_enable_reset(arizona);
 	regulator_disable(arizona->dcvdd);
@@ -1550,6 +1559,15 @@ int arizona_dev_exit(struct arizona *arizona)
 	regulator_disable(arizona->dcvdd);
 	regulator_put(arizona->dcvdd);
 
+	switch (arizona->pdata.clk32k_src) {
+	case ARIZONA_32KZ_MCLK1:
+	case ARIZONA_32KZ_MCLK2:
+		arizona_clk32k_disable(arizona);
+		break;
+	default:
+		break;
+	}
+
 	mfd_remove_devices(arizona->dev);
 	arizona_free_irq(arizona, ARIZONA_IRQ_UNDERCLOCKED, arizona);
 	arizona_free_irq(arizona, ARIZONA_IRQ_OVERCLOCKED, arizona);
diff --git a/drivers/mfd/dln2.c b/drivers/mfd/dln2.c
index 672831d5ee32..97a69cd6f127 100644
--- a/drivers/mfd/dln2.c
+++ b/drivers/mfd/dln2.c
@@ -294,7 +294,11 @@ static void dln2_rx(struct urb *urb)
 	len = urb->actual_length - sizeof(struct dln2_header);
 
 	if (handle == DLN2_HANDLE_EVENT) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&dln2->event_cb_lock, flags);
 		dln2_run_event_callbacks(dln2, id, echo, data, len);
+		spin_unlock_irqrestore(&dln2->event_cb_lock, flags);
 	} else {
 		/* URB will be re-submitted in _dln2_transfer (free_rx_slot) */
 		if (dln2_transfer_complete(dln2, urb, handle, echo))
diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index 0504761516f7..a12bb8ed2040 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -176,6 +176,9 @@ static const struct pci_device_id intel_lpss_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x1ac4), (kernel_ulong_t)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x1ac6), (kernel_ulong_t)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x1aee), (kernel_ulong_t)&bxt_uart_info },
+	/* EBG */
+	{ PCI_VDEVICE(INTEL, 0x1bad), (kernel_ulong_t)&bxt_uart_info },
+	{ PCI_VDEVICE(INTEL, 0x1bae), (kernel_ulong_t)&bxt_uart_info },
 	/* GLK */
 	{ PCI_VDEVICE(INTEL, 0x31ac), (kernel_ulong_t)&glk_i2c_info },
 	{ PCI_VDEVICE(INTEL, 0x31ae), (kernel_ulong_t)&glk_i2c_info },
diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index 5c8ed2150c8b..fb687368ac98 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -32,6 +32,11 @@ int mfd_cell_enable(struct platform_device *pdev)
 	const struct mfd_cell *cell = mfd_get_cell(pdev);
 	int err = 0;
 
+	if (!cell->enable) {
+		dev_dbg(&pdev->dev, "No .enable() call-back registered\n");
+		return 0;
+	}
+
 	/* only call enable hook if the cell wasn't previously enabled */
 	if (atomic_inc_return(cell->usage_count) == 1)
 		err = cell->enable(pdev);
@@ -49,6 +54,11 @@ int mfd_cell_disable(struct platform_device *pdev)
 	const struct mfd_cell *cell = mfd_get_cell(pdev);
 	int err = 0;
 
+	if (!cell->disable) {
+		dev_dbg(&pdev->dev, "No .disable() call-back registered\n");
+		return 0;
+	}
+
 	/* only disable if no other clients are using it */
 	if (atomic_dec_return(cell->usage_count) == 0)
 		err = cell->disable(pdev);
diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index 953d0790ffd5..3259fb82d3c4 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -696,3 +696,4 @@ module_i2c_driver(wm8994_i2c_driver);
 MODULE_DESCRIPTION("Core support for the WM8994 audio CODEC");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>");
+MODULE_SOFTDEP("pre: wm8994_regulator");
diff --git a/drivers/misc/atmel-ssc.c b/drivers/misc/atmel-ssc.c
index d8e3cc2dc747..f9caf233e2cc 100644
--- a/drivers/misc/atmel-ssc.c
+++ b/drivers/misc/atmel-ssc.c
@@ -13,7 +13,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/atmel-ssc.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -23,7 +23,7 @@
 #include "../../sound/soc/atmel/atmel_ssc_dai.h"
 
 /* Serialize access to ssc_list and user count */
-static DEFINE_SPINLOCK(user_lock);
+static DEFINE_MUTEX(user_lock);
 static LIST_HEAD(ssc_list);
 
 struct ssc_device *ssc_request(unsigned int ssc_num)
@@ -31,7 +31,7 @@ struct ssc_device *ssc_request(unsigned int ssc_num)
 	int ssc_valid = 0;
 	struct ssc_device *ssc;
 
-	spin_lock(&user_lock);
+	mutex_lock(&user_lock);
 	list_for_each_entry(ssc, &ssc_list, list) {
 		if (ssc->pdev->dev.of_node) {
 			if (of_alias_get_id(ssc->pdev->dev.of_node, "ssc")
@@ -47,18 +47,18 @@ struct ssc_device *ssc_request(unsigned int ssc_num)
 	}
 
 	if (!ssc_valid) {
-		spin_unlock(&user_lock);
+		mutex_unlock(&user_lock);
 		pr_err("ssc: ssc%d platform device is missing\n", ssc_num);
 		return ERR_PTR(-ENODEV);
 	}
 
 	if (ssc->user) {
-		spin_unlock(&user_lock);
+		mutex_unlock(&user_lock);
 		dev_dbg(&ssc->pdev->dev, "module busy\n");
 		return ERR_PTR(-EBUSY);
 	}
 	ssc->user++;
-	spin_unlock(&user_lock);
+	mutex_unlock(&user_lock);
 
 	clk_prepare(ssc->clk);
 
@@ -70,14 +70,14 @@ void ssc_free(struct ssc_device *ssc)
 {
 	bool disable_clk = true;
 
-	spin_lock(&user_lock);
+	mutex_lock(&user_lock);
 	if (ssc->user)
 		ssc->user--;
 	else {
 		disable_clk = false;
 		dev_dbg(&ssc->pdev->dev, "device already free\n");
 	}
-	spin_unlock(&user_lock);
+	mutex_unlock(&user_lock);
 
 	if (disable_clk)
 		clk_unprepare(ssc->clk);
@@ -240,9 +240,9 @@ static int ssc_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	spin_lock(&user_lock);
+	mutex_lock(&user_lock);
 	list_add_tail(&ssc->list, &ssc_list);
-	spin_unlock(&user_lock);
+	mutex_unlock(&user_lock);
 
 	platform_set_drvdata(pdev, ssc);
 
@@ -261,9 +261,9 @@ static int ssc_remove(struct platform_device *pdev)
 
 	ssc_sound_dai_remove(ssc);
 
-	spin_lock(&user_lock);
+	mutex_lock(&user_lock);
 	list_del(&ssc->list);
-	spin_unlock(&user_lock);
+	mutex_unlock(&user_lock);
 
 	return 0;
 }
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index 393a80bdb846..b0285c5d8d38 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -606,7 +606,7 @@ static struct afu_config_record *cxl_sysfs_afu_new_cr(struct cxl_afu *afu, int c
 	rc = kobject_init_and_add(&cr->kobj, &afu_config_record_type,
 				  &afu->dev.kobj, "cr%i", cr->cr);
 	if (rc)
-		goto err;
+		goto err1;
 
 	rc = sysfs_create_bin_file(&cr->kobj, &cr->config_attr);
 	if (rc)
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 8f6ab516041b..73a93e3fc18d 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -722,9 +722,8 @@ static int mei_cl_device_remove(struct device *dev)
 	mei_cldev_unregister_callbacks(cldev);
 
 	module_put(THIS_MODULE);
-	dev->driver = NULL;
-	return ret;
 
+	return ret;
 }
 
 static ssize_t name_show(struct device *dev, struct device_attribute *a,
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 916b88ee2de4..cbb72b460755 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -2333,8 +2333,8 @@ static int mmc_rpmb_chrdev_release(struct inode *inode, struct file *filp)
 	struct mmc_rpmb_data *rpmb = container_of(inode->i_cdev,
 						  struct mmc_rpmb_data, chrdev);
 
-	put_device(&rpmb->dev);
 	mmc_blk_put(rpmb->md);
+	put_device(&rpmb->dev);
 
 	return 0;
 }
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 814a04e8fdd7..2be2313f5950 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -300,7 +300,7 @@ static void mmc_manage_enhanced_area(struct mmc_card *card, u8 *ext_csd)
 	}
 }
 
-static void mmc_part_add(struct mmc_card *card, unsigned int size,
+static void mmc_part_add(struct mmc_card *card, u64 size,
 			 unsigned int part_cfg, char *name, int idx, bool ro,
 			 int area_type)
 {
@@ -316,7 +316,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd)
 {
 	int idx;
 	u8 hc_erase_grp_sz, hc_wp_grp_sz;
-	unsigned int part_size;
+	u64 part_size;
 
 	/*
 	 * General purpose partition feature support --
@@ -346,8 +346,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd)
 				(ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 1]
 				<< 8) +
 				ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3];
-			part_size *= (size_t)(hc_erase_grp_sz *
-				hc_wp_grp_sz);
+			part_size *= (hc_erase_grp_sz * hc_wp_grp_sz);
 			mmc_part_add(card, part_size << 19,
 				EXT_CSD_PART_CONFIG_ACC_GP0 + idx,
 				"gp%d", idx, false,
@@ -365,7 +364,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd)
 static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 {
 	int err = 0, idx;
-	unsigned int part_size;
+	u64 part_size;
 	struct device_node *np;
 	bool broken_hpi = false;
 
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index f74f9ef460cc..218472879d9c 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -143,7 +143,7 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 	q->limits.discard_granularity = card->pref_erase << 9;
 	/* granularity must not be greater than max. discard */
 	if (card->pref_erase > max_discard)
-		q->limits.discard_granularity = 0;
+		q->limits.discard_granularity = SECTOR_SIZE;
 	if (mmc_can_secure_erase_trim(card))
 		queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, q);
 }
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index 7ee8c9082021..7568cea55922 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -717,9 +717,8 @@ try_again:
 			/* Retry init sequence, but without R4_18V_PRESENT. */
 			retries = 0;
 			goto try_again;
-		} else {
-			goto remove;
 		}
+		return err;
 	}
 
 	/*
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 8c0b80a54e4d..6d1ac9443eb2 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -79,7 +79,7 @@
 #define ESDHC_STD_TUNING_EN		(1 << 24)
 /* NOTE: the minimum valid tuning start tap for mx6sl is 1 */
 #define ESDHC_TUNING_START_TAP_DEFAULT	0x1
-#define ESDHC_TUNING_START_TAP_MASK	0xff
+#define ESDHC_TUNING_START_TAP_MASK	0x7f
 #define ESDHC_TUNING_STEP_MASK		0x00070000
 #define ESDHC_TUNING_STEP_SHIFT		16
 
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 192844b50c69..ff3f9a01e443 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -837,7 +837,7 @@ static void sdhci_msm_set_cdr(struct sdhci_host *host, bool enable)
 static int sdhci_msm_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
-	int tuning_seq_cnt = 3;
+	int tuning_seq_cnt = 10;
 	u8 phase, tuned_phases[16], tuned_phase_cnt = 0;
 	int rc;
 	struct mmc_ios ios = host->mmc->ios;
@@ -861,6 +861,12 @@ static int sdhci_msm_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	msm_host->use_cdr = true;
 
 	/*
+	 * Clear tuning_done flag before tuning to ensure proper
+	 * HS400 settings.
+	 */
+	msm_host->tuning_done = 0;
+
+	/*
 	 * For HS400 tuning in HS200 timing requires:
 	 * - select MCLK/2 in VENDOR_SPEC
 	 * - program MCLK to 400MHz (or nearest supported) in GCC
@@ -895,6 +901,22 @@ retry:
 	} while (++phase < ARRAY_SIZE(tuned_phases));
 
 	if (tuned_phase_cnt) {
+		if (tuned_phase_cnt == ARRAY_SIZE(tuned_phases)) {
+			/*
+			 * All phases valid is _almost_ as bad as no phases
+			 * valid.  Probably all phases are not really reliable
+			 * but we didn't detect where the unreliable place is.
+			 * That means we'll essentially be guessing and hoping
+			 * we get a good phase.  Better to try a few times.
+			 */
+			dev_dbg(mmc_dev(mmc), "%s: All phases valid; try again\n",
+				mmc_hostname(mmc));
+			if (--tuning_seq_cnt) {
+				tuned_phase_cnt = 0;
+				goto retry;
+			}
+		}
+
 		rc = msm_find_most_appropriate_phase(host, tuned_phases,
 						     tuned_phase_cnt);
 		if (rc < 0)
@@ -1162,7 +1184,9 @@ static const struct sdhci_pltfm_data sdhci_msm_pdata = {
 	.quirks = SDHCI_QUIRK_BROKEN_CARD_DETECTION |
 		  SDHCI_QUIRK_NO_CARD_NO_RESET |
 		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
-		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN |
+		  SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
+
 	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 	.ops = &sdhci_msm_ops,
 };
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 4f1c884c0b50..33028099d3a0 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -133,7 +133,7 @@ static void sdhci_set_card_detection(struct sdhci_host *host, bool enable)
 	u32 present;
 
 	if ((host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) ||
-	    !mmc_card_is_removable(host->mmc))
+	    !mmc_card_is_removable(host->mmc) || mmc_can_gpio_cd(host->mmc))
 		return;
 
 	if (enable) {
diff --git a/drivers/mmc/host/via-sdmmc.c b/drivers/mmc/host/via-sdmmc.c
index a838bf5480d8..a863a345fc59 100644
--- a/drivers/mmc/host/via-sdmmc.c
+++ b/drivers/mmc/host/via-sdmmc.c
@@ -323,6 +323,8 @@ struct via_crdr_mmc_host {
 /* some devices need a very long delay for power to stabilize */
 #define VIA_CRDR_QUIRK_300MS_PWRDELAY	0x0001
 
+#define VIA_CMD_TIMEOUT_MS		1000
+
 static const struct pci_device_id via_ids[] = {
 	{PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_9530,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0,},
@@ -555,14 +557,17 @@ static void via_sdc_send_command(struct via_crdr_mmc_host *host,
 {
 	void __iomem *addrbase;
 	struct mmc_data *data;
+	unsigned int timeout_ms;
 	u32 cmdctrl = 0;
 
 	WARN_ON(host->cmd);
 
 	data = cmd->data;
-	mod_timer(&host->timer, jiffies + HZ);
 	host->cmd = cmd;
 
+	timeout_ms = cmd->busy_timeout ? cmd->busy_timeout : VIA_CMD_TIMEOUT_MS;
+	mod_timer(&host->timer, jiffies + msecs_to_jiffies(timeout_ms));
+
 	/*Command index*/
 	cmdctrl = cmd->opcode << 8;
 
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index 1f0d83086cb0..870d1f1331b1 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -726,7 +726,6 @@ static struct mtd_info *cfi_amdstd_setup(struct mtd_info *mtd)
 	kfree(mtd->eraseregions);
 	kfree(mtd);
 	kfree(cfi->cmdset_priv);
-	kfree(cfi->cfiq);
 	return NULL;
 }
 
diff --git a/drivers/mtd/cmdlinepart.c b/drivers/mtd/cmdlinepart.c
index fbd5affc0acf..04fd845de05f 100644
--- a/drivers/mtd/cmdlinepart.c
+++ b/drivers/mtd/cmdlinepart.c
@@ -228,12 +228,29 @@ static int mtdpart_setup_real(char *s)
 		struct cmdline_mtd_partition *this_mtd;
 		struct mtd_partition *parts;
 		int mtd_id_len, num_parts;
-		char *p, *mtd_id;
+		char *p, *mtd_id, *semicol;
+
+		/*
+		 * Replace the first ';' by a NULL char so strrchr can work
+		 * properly.
+		 */
+		semicol = strchr(s, ';');
+		if (semicol)
+			*semicol = '\0';
 
 		mtd_id = s;
 
-		/* fetch <mtd-id> */
-		p = strchr(s, ':');
+		/*
+		 * fetch <mtd-id>. We use strrchr to ignore all ':' that could
+		 * be present in the MTD name, only the last one is interpreted
+		 * as an <mtd-id>/<part-definition> separator.
+		 */
+		p = strrchr(s, ':');
+
+		/* Restore the ';' now. */
+		if (semicol)
+			*semicol = ';';
+
 		if (!p) {
 			pr_err("no mtd-id\n");
 			return -EINVAL;
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index fa4d12217652..18dd333f2d40 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -372,9 +372,6 @@ static int mtdchar_writeoob(struct file *file, struct mtd_info *mtd,
 	uint32_t retlen;
 	int ret = 0;
 
-	if (!(file->f_mode & FMODE_WRITE))
-		return -EPERM;
-
 	if (length > 4096)
 		return -EINVAL;
 
@@ -681,6 +678,48 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg)
 			return -EFAULT;
 	}
 
+	/*
+	 * Check the file mode to require "dangerous" commands to have write
+	 * permissions.
+	 */
+	switch (cmd) {
+	/* "safe" commands */
+	case MEMGETREGIONCOUNT:
+	case MEMGETREGIONINFO:
+	case MEMGETINFO:
+	case MEMREADOOB:
+	case MEMREADOOB64:
+	case MEMLOCK:
+	case MEMUNLOCK:
+	case MEMISLOCKED:
+	case MEMGETOOBSEL:
+	case MEMGETBADBLOCK:
+	case MEMSETBADBLOCK:
+	case OTPSELECT:
+	case OTPGETREGIONCOUNT:
+	case OTPGETREGIONINFO:
+	case OTPLOCK:
+	case ECCGETLAYOUT:
+	case ECCGETSTATS:
+	case MTDFILEMODE:
+	case BLKPG:
+	case BLKRRPART:
+		break;
+
+	/* "dangerous" commands */
+	case MEMERASE:
+	case MEMERASE64:
+	case MEMWRITEOOB:
+	case MEMWRITEOOB64:
+	case MEMWRITE:
+		if (!(file->f_mode & FMODE_WRITE))
+			return -EPERM;
+		break;
+
+	default:
+		return -ENOTTY;
+	}
+
 	switch (cmd) {
 	case MEMGETREGIONCOUNT:
 		if (copy_to_user(argp, &(mtd->numeraseregions), sizeof(int)))
@@ -728,9 +767,6 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg)
 	{
 		struct erase_info *erase;
 
-		if(!(file->f_mode & FMODE_WRITE))
-			return -EPERM;
-
 		erase=kzalloc(sizeof(struct erase_info),GFP_KERNEL);
 		if (!erase)
 			ret = -ENOMEM;
@@ -1051,9 +1087,6 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg)
 		ret = 0;
 		break;
 	}
-
-	default:
-		ret = -ENOTTY;
 	}
 
 	return ret;
@@ -1097,6 +1130,11 @@ static long mtdchar_compat_ioctl(struct file *file, unsigned int cmd,
 		struct mtd_oob_buf32 buf;
 		struct mtd_oob_buf32 __user *buf_user = argp;
 
+		if (!(file->f_mode & FMODE_WRITE)) {
+			ret = -EPERM;
+			break;
+		}
+
 		if (copy_from_user(&buf, argp, sizeof(buf)))
 			ret = -EFAULT;
 		else
diff --git a/drivers/mtd/nand/ams-delta.c b/drivers/mtd/nand/ams-delta.c
index dcec9cf4983f..e22a9ffa9cb7 100644
--- a/drivers/mtd/nand/ams-delta.c
+++ b/drivers/mtd/nand/ams-delta.c
@@ -263,7 +263,7 @@ static int ams_delta_cleanup(struct platform_device *pdev)
 	void __iomem *io_base = platform_get_drvdata(pdev);
 
 	/* Release resources, unregister device */
-	nand_release(ams_delta_mtd);
+	nand_release(mtd_to_nand(ams_delta_mtd));
 
 	gpio_free_array(_mandatory_gpio, ARRAY_SIZE(_mandatory_gpio));
 	gpio_free(AMS_DELTA_GPIO_PIN_NAND_RB);
diff --git a/drivers/mtd/nand/au1550nd.c b/drivers/mtd/nand/au1550nd.c
index 9d4a28fa6b73..99c738be2545 100644
--- a/drivers/mtd/nand/au1550nd.c
+++ b/drivers/mtd/nand/au1550nd.c
@@ -496,7 +496,7 @@ static int au1550nd_remove(struct platform_device *pdev)
 	struct au1550nd_ctx *ctx = platform_get_drvdata(pdev);
 	struct resource *r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
-	nand_release(nand_to_mtd(&ctx->chip));
+	nand_release(&ctx->chip);
 	iounmap(ctx->base);
 	release_mem_region(r->start, 0x1000);
 	kfree(ctx);
diff --git a/drivers/mtd/nand/bcm47xxnflash/main.c b/drivers/mtd/nand/bcm47xxnflash/main.c
index fb31429b70a9..d79694160845 100644
--- a/drivers/mtd/nand/bcm47xxnflash/main.c
+++ b/drivers/mtd/nand/bcm47xxnflash/main.c
@@ -65,7 +65,7 @@ static int bcm47xxnflash_remove(struct platform_device *pdev)
 {
 	struct bcm47xxnflash *nflash = platform_get_drvdata(pdev);
 
-	nand_release(nand_to_mtd(&nflash->nand_chip));
+	nand_release(&nflash->nand_chip);
 
 	return 0;
 }
diff --git a/drivers/mtd/nand/bf5xx_nand.c b/drivers/mtd/nand/bf5xx_nand.c
index 5655dca6ce43..ebcbcbaa8b54 100644
--- a/drivers/mtd/nand/bf5xx_nand.c
+++ b/drivers/mtd/nand/bf5xx_nand.c
@@ -688,7 +688,7 @@ static int bf5xx_nand_remove(struct platform_device *pdev)
 	 * and their partitions, then go through freeing the
 	 * resources used
 	 */
-	nand_release(nand_to_mtd(&info->chip));
+	nand_release(&info->chip);
 
 	peripheral_free_list(bfin_nfc_pin_req);
 	bf5xx_nand_dma_remove(info);
diff --git a/drivers/mtd/nand/brcmnand/brcmnand.c b/drivers/mtd/nand/brcmnand/brcmnand.c
index 2a978d9832a7..c65724d0c725 100644
--- a/drivers/mtd/nand/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/brcmnand/brcmnand.c
@@ -491,8 +491,9 @@ static int brcmnand_revision_init(struct brcmnand_controller *ctrl)
 	} else {
 		ctrl->cs_offsets = brcmnand_cs_offsets;
 
-		/* v5.0 and earlier has a different CS0 offset layout */
-		if (ctrl->nand_version <= 0x0500)
+		/* v3.3-5.0 have a different CS0 offset layout */
+		if (ctrl->nand_version >= 0x0303 &&
+		    ctrl->nand_version <= 0x0500)
 			ctrl->cs0_offsets = brcmnand_cs_offsets_cs0;
 	}
 
@@ -911,11 +912,14 @@ static int brcmnand_hamming_ooblayout_free(struct mtd_info *mtd, int section,
 		if (!section) {
 			/*
 			 * Small-page NAND use byte 6 for BBI while large-page
-			 * NAND use byte 0.
+			 * NAND use bytes 0 and 1.
 			 */
-			if (cfg->page_size > 512)
-				oobregion->offset++;
-			oobregion->length--;
+			if (cfg->page_size > 512) {
+				oobregion->offset += 2;
+				oobregion->length -= 2;
+			} else {
+				oobregion->length--;
+			}
 		}
 	}
 
@@ -2594,7 +2598,7 @@ int brcmnand_remove(struct platform_device *pdev)
 	struct brcmnand_host *host;
 
 	list_for_each_entry(host, &ctrl->host_list, node)
-		nand_release(nand_to_mtd(&host->chip));
+		nand_release(&host->chip);
 
 	clk_disable_unprepare(ctrl->clk);
 
diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c
index bc558c438a57..98c013094fa2 100644
--- a/drivers/mtd/nand/cafe_nand.c
+++ b/drivers/mtd/nand/cafe_nand.c
@@ -826,7 +826,7 @@ static void cafe_nand_remove(struct pci_dev *pdev)
 	/* Disable NAND IRQ in global IRQ mask register */
 	cafe_writel(cafe, ~1 & cafe_readl(cafe, GLOBAL_IRQ_MASK), GLOBAL_IRQ_MASK);
 	free_irq(pdev->irq, mtd);
-	nand_release(mtd);
+	nand_release(chip);
 	free_rs(cafe->rs);
 	pci_iounmap(pdev, cafe->mmio);
 	dma_free_coherent(&cafe->pdev->dev,
diff --git a/drivers/mtd/nand/cmx270_nand.c b/drivers/mtd/nand/cmx270_nand.c
index 1fc435f994e1..7b824ae88ab0 100644
--- a/drivers/mtd/nand/cmx270_nand.c
+++ b/drivers/mtd/nand/cmx270_nand.c
@@ -230,7 +230,7 @@ module_init(cmx270_init);
 static void __exit cmx270_cleanup(void)
 {
 	/* Release resources, unregister device */
-	nand_release(cmx270_nand_mtd);
+	nand_release(mtd_to_nand(cmx270_nand_mtd));
 
 	gpio_free(GPIO_NAND_RB);
 	gpio_free(GPIO_NAND_CS);
diff --git a/drivers/mtd/nand/cs553x_nand.c b/drivers/mtd/nand/cs553x_nand.c
index d48877540f14..647d4ee69345 100644
--- a/drivers/mtd/nand/cs553x_nand.c
+++ b/drivers/mtd/nand/cs553x_nand.c
@@ -338,7 +338,7 @@ static void __exit cs553x_cleanup(void)
 		mmio_base = this->IO_ADDR_R;
 
 		/* Release resources, unregister device */
-		nand_release(mtd);
+		nand_release(this);
 		kfree(mtd->name);
 		cs553x_mtd[i] = NULL;
 
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index ccc8c43abcff..e66f1385b49e 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -854,7 +854,7 @@ static int nand_davinci_remove(struct platform_device *pdev)
 		ecc4_busy = false;
 	spin_unlock_irq(&davinci_nand_lock);
 
-	nand_release(nand_to_mtd(&info->chip));
+	nand_release(&info->chip);
 
 	clk_disable_unprepare(info->clk);
 
diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c
index 3087b0ba7b7f..390a18ad68ee 100644
--- a/drivers/mtd/nand/denali.c
+++ b/drivers/mtd/nand/denali.c
@@ -1444,9 +1444,7 @@ EXPORT_SYMBOL(denali_init);
 /* driver exit point */
 void denali_remove(struct denali_nand_info *denali)
 {
-	struct mtd_info *mtd = nand_to_mtd(&denali->nand);
-
-	nand_release(mtd);
+	nand_release(&denali->nand);
 	kfree(denali->buf);
 	denali_disable_irq(denali);
 }
diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c
index c3aa53caab5c..4f48a9b4f9e3 100644
--- a/drivers/mtd/nand/diskonchip.c
+++ b/drivers/mtd/nand/diskonchip.c
@@ -1605,13 +1605,10 @@ static int __init doc_probe(unsigned long physadr)
 		numchips = doc2001_init(mtd);
 
 	if ((ret = nand_scan(mtd, numchips)) || (ret = doc->late_init(mtd))) {
-		/* DBB note: i believe nand_release is necessary here, as
+		/* DBB note: i believe nand_cleanup is necessary here, as
 		   buffers may have been allocated in nand_base.  Check with
 		   Thomas. FIX ME! */
-		/* nand_release will call mtd_device_unregister, but we
-		   haven't yet added it.  This is handled without incident by
-		   mtd_device_unregister, as far as I can tell. */
-		nand_release(mtd);
+		nand_cleanup(nand);
 		kfree(nand);
 		goto fail;
 	}
@@ -1644,7 +1641,7 @@ static void release_nanddoc(void)
 		doc = nand_get_controller_data(nand);
 
 		nextmtd = doc->nextdoc;
-		nand_release(mtd);
+		nand_release(nand);
 		iounmap(doc->virtadr);
 		release_mem_region(doc->physadr, DOC_IOREMAP_LEN);
 		kfree(nand);
diff --git a/drivers/mtd/nand/docg4.c b/drivers/mtd/nand/docg4.c
index 2436cbc71662..53fdf491d8c0 100644
--- a/drivers/mtd/nand/docg4.c
+++ b/drivers/mtd/nand/docg4.c
@@ -1376,7 +1376,7 @@ static int __init probe_docg4(struct platform_device *pdev)
 	return 0;
 
 fail:
-	nand_release(mtd); /* deletes partitions and mtd devices */
+	nand_release(nand); /* deletes partitions and mtd devices */
 	free_bch(doc->bch);
 	kfree(nand);
 
@@ -1389,7 +1389,7 @@ fail_unmap:
 static int __exit cleanup_docg4(struct platform_device *pdev)
 {
 	struct docg4_priv *doc = platform_get_drvdata(pdev);
-	nand_release(doc->mtd);
+	nand_release(mtd_to_nand(doc->mtd));
 	free_bch(doc->bch);
 	kfree(mtd_to_nand(doc->mtd));
 	iounmap(doc->virtadr);
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index 17db2f90aa2c..0f70bd961234 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -813,7 +813,7 @@ static int fsl_elbc_chip_remove(struct fsl_elbc_mtd *priv)
 	struct fsl_elbc_fcm_ctrl *elbc_fcm_ctrl = priv->ctrl->nand;
 	struct mtd_info *mtd = nand_to_mtd(&priv->chip);
 
-	nand_release(mtd);
+	nand_release(&priv->chip);
 
 	kfree(mtd->name);
 
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index 16deba1a2385..0d4928161439 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -927,7 +927,7 @@ static int fsl_ifc_chip_remove(struct fsl_ifc_mtd *priv)
 {
 	struct mtd_info *mtd = nand_to_mtd(&priv->chip);
 
-	nand_release(mtd);
+	nand_release(&priv->chip);
 
 	kfree(mtd->name);
 
diff --git a/drivers/mtd/nand/fsl_upm.c b/drivers/mtd/nand/fsl_upm.c
index a88e2cf66e0f..009e96fb92ae 100644
--- a/drivers/mtd/nand/fsl_upm.c
+++ b/drivers/mtd/nand/fsl_upm.c
@@ -326,7 +326,7 @@ static int fun_remove(struct platform_device *ofdev)
 	struct mtd_info *mtd = nand_to_mtd(&fun->chip);
 	int i;
 
-	nand_release(mtd);
+	nand_release(&fun->chip);
 	kfree(mtd->name);
 
 	for (i = 0; i < fun->mchip_count; i++) {
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index eac15d9bf49e..3be80e15e400 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -1118,7 +1118,7 @@ static int fsmc_nand_remove(struct platform_device *pdev)
 	struct fsmc_nand_data *host = platform_get_drvdata(pdev);
 
 	if (host) {
-		nand_release(nand_to_mtd(&host->nand));
+		nand_release(&host->nand);
 
 		if (host->mode == USE_DMA_ACCESS) {
 			dma_release_channel(host->write_dma_chan);
diff --git a/drivers/mtd/nand/gpio.c b/drivers/mtd/nand/gpio.c
index fd3648952b5a..81b02b81e984 100644
--- a/drivers/mtd/nand/gpio.c
+++ b/drivers/mtd/nand/gpio.c
@@ -199,7 +199,7 @@ static int gpio_nand_remove(struct platform_device *pdev)
 {
 	struct gpiomtd *gpiomtd = platform_get_drvdata(pdev);
 
-	nand_release(nand_to_mtd(&gpiomtd->nand_chip));
+	nand_release(&gpiomtd->nand_chip);
 
 	if (gpio_is_valid(gpiomtd->plat.gpio_nwp))
 		gpio_set_value(gpiomtd->plat.gpio_nwp, 0);
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
index d4d824ef64e9..c7d0d2eed6c2 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
@@ -2135,7 +2135,7 @@ static int gpmi_nand_remove(struct platform_device *pdev)
 {
 	struct gpmi_nand_data *this = platform_get_drvdata(pdev);
 
-	nand_release(nand_to_mtd(&this->nand));
+	nand_release(&this->nand);
 	gpmi_free_dma_buffer(this);
 	release_resources(this);
 	return 0;
diff --git a/drivers/mtd/nand/hisi504_nand.c b/drivers/mtd/nand/hisi504_nand.c
index d9ee1a7e6956..1d1b541489f8 100644
--- a/drivers/mtd/nand/hisi504_nand.c
+++ b/drivers/mtd/nand/hisi504_nand.c
@@ -823,7 +823,7 @@ static int hisi_nfc_probe(struct platform_device *pdev)
 	return 0;
 
 err_mtd:
-	nand_release(mtd);
+	nand_release(chip);
 err_res:
 	return ret;
 }
@@ -831,9 +831,8 @@ err_res:
 static int hisi_nfc_remove(struct platform_device *pdev)
 {
 	struct hinfc_host *host = platform_get_drvdata(pdev);
-	struct mtd_info *mtd = nand_to_mtd(&host->chip);
 
-	nand_release(mtd);
+	nand_release(&host->chip);
 
 	return 0;
 }
diff --git a/drivers/mtd/nand/jz4740_nand.c b/drivers/mtd/nand/jz4740_nand.c
index ad827d4af3e9..62ddea88edce 100644
--- a/drivers/mtd/nand/jz4740_nand.c
+++ b/drivers/mtd/nand/jz4740_nand.c
@@ -480,7 +480,7 @@ static int jz_nand_probe(struct platform_device *pdev)
 	return 0;
 
 err_nand_release:
-	nand_release(mtd);
+	nand_release(chip);
 err_unclaim_banks:
 	while (chipnr--) {
 		unsigned char bank = nand->banks[chipnr];
@@ -500,7 +500,7 @@ static int jz_nand_remove(struct platform_device *pdev)
 	struct jz_nand *nand = platform_get_drvdata(pdev);
 	size_t i;
 
-	nand_release(nand_to_mtd(&nand->chip));
+	nand_release(&nand->chip);
 
 	/* Deassert and disable all chips */
 	writel(0, nand->base + JZ_REG_NAND_CTRL);
diff --git a/drivers/mtd/nand/jz4780_nand.c b/drivers/mtd/nand/jz4780_nand.c
index e69f6ae4c539..86ff46eb7925 100644
--- a/drivers/mtd/nand/jz4780_nand.c
+++ b/drivers/mtd/nand/jz4780_nand.c
@@ -293,7 +293,7 @@ static int jz4780_nand_init_chip(struct platform_device *pdev,
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
-		nand_release(mtd);
+		nand_release(chip);
 		return ret;
 	}
 
@@ -308,7 +308,7 @@ static void jz4780_nand_cleanup_chips(struct jz4780_nand_controller *nfc)
 
 	while (!list_empty(&nfc->chips)) {
 		chip = list_first_entry(&nfc->chips, struct jz4780_nand_chip, chip_list);
-		nand_release(nand_to_mtd(&chip->chip));
+		nand_release(&chip->chip);
 		list_del(&chip->chip_list);
 	}
 }
diff --git a/drivers/mtd/nand/lpc32xx_mlc.c b/drivers/mtd/nand/lpc32xx_mlc.c
index 5796468db653..d19d07931c2b 100644
--- a/drivers/mtd/nand/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/lpc32xx_mlc.c
@@ -805,7 +805,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	if (!res)
 		return res;
 
-	nand_release(mtd);
+	nand_release(nand_chip);
 
 err_exit4:
 	free_irq(host->irq, host);
@@ -829,9 +829,8 @@ err_exit1:
 static int lpc32xx_nand_remove(struct platform_device *pdev)
 {
 	struct lpc32xx_nand_host *host = platform_get_drvdata(pdev);
-	struct mtd_info *mtd = nand_to_mtd(&host->nand_chip);
 
-	nand_release(mtd);
+	nand_release(&host->nand_chip);
 	free_irq(host->irq, host);
 	if (use_dma)
 		dma_release_channel(host->dma_chan);
diff --git a/drivers/mtd/nand/lpc32xx_slc.c b/drivers/mtd/nand/lpc32xx_slc.c
index b61f28a1554d..1be4aaa3d6e0 100644
--- a/drivers/mtd/nand/lpc32xx_slc.c
+++ b/drivers/mtd/nand/lpc32xx_slc.c
@@ -935,7 +935,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	if (!res)
 		return res;
 
-	nand_release(mtd);
+	nand_release(chip);
 
 err_exit3:
 	dma_release_channel(host->dma_chan);
@@ -954,9 +954,8 @@ static int lpc32xx_nand_remove(struct platform_device *pdev)
 {
 	uint32_t tmp;
 	struct lpc32xx_nand_host *host = platform_get_drvdata(pdev);
-	struct mtd_info *mtd = nand_to_mtd(&host->nand_chip);
 
-	nand_release(mtd);
+	nand_release(&host->nand_chip);
 	dma_release_channel(host->dma_chan);
 
 	/* Force CE high */
diff --git a/drivers/mtd/nand/mpc5121_nfc.c b/drivers/mtd/nand/mpc5121_nfc.c
index b6b97cc9fba6..b8a93b47a290 100644
--- a/drivers/mtd/nand/mpc5121_nfc.c
+++ b/drivers/mtd/nand/mpc5121_nfc.c
@@ -829,7 +829,7 @@ static int mpc5121_nfc_remove(struct platform_device *op)
 	struct device *dev = &op->dev;
 	struct mtd_info *mtd = dev_get_drvdata(dev);
 
-	nand_release(mtd);
+	nand_release(mtd_to_nand(mtd));
 	mpc5121_nfc_free(dev, mtd);
 
 	return 0;
diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c
index e17f838b9b81..ff314ce104e5 100644
--- a/drivers/mtd/nand/mtk_nand.c
+++ b/drivers/mtd/nand/mtk_nand.c
@@ -1357,7 +1357,7 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 	ret = mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
 	if (ret) {
 		dev_err(dev, "mtd parse partition error\n");
-		nand_release(mtd);
+		nand_cleanup(nand);
 		return ret;
 	}
 
@@ -1514,7 +1514,7 @@ static int mtk_nfc_remove(struct platform_device *pdev)
 	while (!list_empty(&nfc->chips)) {
 		chip = list_first_entry(&nfc->chips, struct mtk_nfc_nand_chip,
 					node);
-		nand_release(nand_to_mtd(&chip->nand));
+		nand_release(&chip->nand);
 		list_del(&chip->node);
 	}
 
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index fcb575d55b89..808d85bde9f2 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -1834,7 +1834,7 @@ static int mxcnd_remove(struct platform_device *pdev)
 {
 	struct mxc_nand_host *host = platform_get_drvdata(pdev);
 
-	nand_release(nand_to_mtd(&host->nand));
+	nand_release(&host->nand);
 	if (host->clk_act)
 		clk_disable_unprepare(host->clk);
 
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index d410de331854..e953eca67608 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -5046,12 +5046,12 @@ EXPORT_SYMBOL_GPL(nand_cleanup);
 /**
  * nand_release - [NAND Interface] Unregister the MTD device and free resources
  *		  held by the NAND device
- * @mtd: MTD device structure
+ * @chip: NAND chip object
  */
-void nand_release(struct mtd_info *mtd)
+void nand_release(struct nand_chip *chip)
 {
-	mtd_device_unregister(mtd);
-	nand_cleanup(mtd_to_nand(mtd));
+	mtd_device_unregister(nand_to_mtd(chip));
+	nand_cleanup(chip);
 }
 EXPORT_SYMBOL_GPL(nand_release);
 
diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c
index 44322a363ba5..dbb0e47f5197 100644
--- a/drivers/mtd/nand/nandsim.c
+++ b/drivers/mtd/nand/nandsim.c
@@ -2356,7 +2356,7 @@ static int __init ns_init_module(void)
 
 err_exit:
 	free_nandsim(nand);
-	nand_release(nsmtd);
+	nand_release(chip);
 	for (i = 0;i < ARRAY_SIZE(nand->partitions); ++i)
 		kfree(nand->partitions[i].name);
 error:
@@ -2378,7 +2378,7 @@ static void __exit ns_cleanup_module(void)
 	int i;
 
 	free_nandsim(ns);    /* Free nandsim private resources */
-	nand_release(nsmtd); /* Unregister driver */
+	nand_release(chip); /* Unregister driver */
 	for (i = 0;i < ARRAY_SIZE(ns->partitions); ++i)
 		kfree(ns->partitions[i].name);
 	kfree(mtd_to_nand(nsmtd));        /* Free other structures */
diff --git a/drivers/mtd/nand/ndfc.c b/drivers/mtd/nand/ndfc.c
index d8a806894937..eb84328d9bde 100644
--- a/drivers/mtd/nand/ndfc.c
+++ b/drivers/mtd/nand/ndfc.c
@@ -258,7 +258,7 @@ static int ndfc_remove(struct platform_device *ofdev)
 	struct ndfc_controller *ndfc = dev_get_drvdata(&ofdev->dev);
 	struct mtd_info *mtd = nand_to_mtd(&ndfc->chip);
 
-	nand_release(mtd);
+	nand_release(&ndfc->chip);
 	kfree(mtd->name);
 
 	return 0;
diff --git a/drivers/mtd/nand/nuc900_nand.c b/drivers/mtd/nand/nuc900_nand.c
index 7bb4d2ea9342..a79f88c6d010 100644
--- a/drivers/mtd/nand/nuc900_nand.c
+++ b/drivers/mtd/nand/nuc900_nand.c
@@ -284,7 +284,7 @@ static int nuc900_nand_remove(struct platform_device *pdev)
 {
 	struct nuc900_nand *nuc900_nand = platform_get_drvdata(pdev);
 
-	nand_release(nand_to_mtd(&nuc900_nand->chip));
+	nand_release(&nuc900_nand->chip);
 	clk_disable(nuc900_nand->clk);
 
 	return 0;
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 9f98f74ff221..110c0726c665 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -2306,7 +2306,7 @@ static int omap_nand_remove(struct platform_device *pdev)
 	}
 	if (info->dma)
 		dma_release_channel(info->dma);
-	nand_release(mtd);
+	nand_release(nand_chip);
 	return 0;
 }
 
diff --git a/drivers/mtd/nand/omap_elm.c b/drivers/mtd/nand/omap_elm.c
index a3f32f939cc1..6736777a4156 100644
--- a/drivers/mtd/nand/omap_elm.c
+++ b/drivers/mtd/nand/omap_elm.c
@@ -421,6 +421,7 @@ static int elm_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 	if (pm_runtime_get_sync(&pdev->dev) < 0) {
 		ret = -EINVAL;
+		pm_runtime_put_sync(&pdev->dev);
 		pm_runtime_disable(&pdev->dev);
 		dev_err(&pdev->dev, "can't enable clock\n");
 		return ret;
diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c
index 5a5aa1f07d07..df07f9b4cf03 100644
--- a/drivers/mtd/nand/orion_nand.c
+++ b/drivers/mtd/nand/orion_nand.c
@@ -186,7 +186,7 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 	mtd->name = "orion_nand";
 	ret = mtd_device_register(mtd, board->parts, board->nr_parts);
 	if (ret) {
-		nand_release(mtd);
+		nand_cleanup(nc);
 		goto no_dev;
 	}
 
@@ -201,9 +201,8 @@ static int orion_nand_remove(struct platform_device *pdev)
 {
 	struct orion_nand_info *info = platform_get_drvdata(pdev);
 	struct nand_chip *chip = &info->chip;
-	struct mtd_info *mtd = nand_to_mtd(chip);
 
-	nand_release(mtd);
+	nand_release(chip);
 
 	clk_disable_unprepare(info->clk);
 
diff --git a/drivers/mtd/nand/oxnas_nand.c b/drivers/mtd/nand/oxnas_nand.c
index d649d5944826..08b6ae364f2b 100644
--- a/drivers/mtd/nand/oxnas_nand.c
+++ b/drivers/mtd/nand/oxnas_nand.c
@@ -36,6 +36,7 @@ struct oxnas_nand_ctrl {
 	void __iomem *io_base;
 	struct clk *clk;
 	struct nand_chip *chips[OXNAS_NAND_MAX_CHIPS];
+	unsigned int nchips;
 };
 
 static uint8_t oxnas_nand_read_byte(struct mtd_info *mtd)
@@ -86,9 +87,9 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 	struct nand_chip *chip;
 	struct mtd_info *mtd;
 	struct resource *res;
-	int nchips = 0;
 	int count = 0;
 	int err = 0;
+	int i;
 
 	/* Allocate memory for the device structure (and zero it) */
 	oxnas = devm_kzalloc(&pdev->dev, sizeof(*oxnas),
@@ -123,7 +124,7 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 				    GFP_KERNEL);
 		if (!chip) {
 			err = -ENOMEM;
-			goto err_clk_unprepare;
+			goto err_release_child;
 		}
 
 		chip->controller = &oxnas->base;
@@ -144,20 +145,18 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 		/* Scan to find existence of the device */
 		err = nand_scan(mtd, 1);
 		if (err)
-			goto err_clk_unprepare;
+			goto err_release_child;
 
 		err = mtd_device_register(mtd, NULL, 0);
-		if (err) {
-			nand_release(mtd);
-			goto err_clk_unprepare;
-		}
+		if (err)
+			goto err_cleanup_nand;
 
-		oxnas->chips[nchips] = chip;
-		++nchips;
+		oxnas->chips[oxnas->nchips] = chip;
+		++oxnas->nchips;
 	}
 
 	/* Exit if no chips found */
-	if (!nchips) {
+	if (!oxnas->nchips) {
 		err = -ENODEV;
 		goto err_clk_unprepare;
 	}
@@ -166,6 +165,17 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_cleanup_nand:
+	nand_cleanup(chip);
+err_release_child:
+	of_node_put(nand_np);
+
+	for (i = 0; i < oxnas->nchips; i++) {
+		chip = oxnas->chips[i];
+		WARN_ON(mtd_device_unregister(nand_to_mtd(chip)));
+		nand_cleanup(chip);
+	}
+
 err_clk_unprepare:
 	clk_disable_unprepare(oxnas->clk);
 	return err;
@@ -174,9 +184,13 @@ err_clk_unprepare:
 static int oxnas_nand_remove(struct platform_device *pdev)
 {
 	struct oxnas_nand_ctrl *oxnas = platform_get_drvdata(pdev);
+	struct nand_chip *chip;
+	int i;
 
-	if (oxnas->chips[0])
-		nand_release(nand_to_mtd(oxnas->chips[0]));
+	for (i = 0; i < oxnas->nchips; i++) {
+		chip = oxnas->chips[i];
+		nand_release(chip);
+	}
 
 	clk_disable_unprepare(oxnas->clk);
 
diff --git a/drivers/mtd/nand/pasemi_nand.c b/drivers/mtd/nand/pasemi_nand.c
index a47a7e4bd25a..f0f4ff960965 100644
--- a/drivers/mtd/nand/pasemi_nand.c
+++ b/drivers/mtd/nand/pasemi_nand.c
@@ -163,7 +163,7 @@ static int pasemi_nand_probe(struct platform_device *ofdev)
 	if (mtd_device_register(pasemi_nand_mtd, NULL, 0)) {
 		dev_err(dev, "Unable to register MTD device\n");
 		err = -ENODEV;
-		goto out_lpc;
+		goto out_cleanup_nand;
 	}
 
 	dev_info(dev, "PA Semi NAND flash at %pR, control at I/O %x\n", &res,
@@ -171,6 +171,8 @@ static int pasemi_nand_probe(struct platform_device *ofdev)
 
 	return 0;
 
+ out_cleanup_nand:
+	nand_cleanup(chip);
  out_lpc:
 	release_region(lpcctl, 4);
  out_ior:
@@ -191,7 +193,7 @@ static int pasemi_nand_remove(struct platform_device *ofdev)
 	chip = mtd_to_nand(pasemi_nand_mtd);
 
 	/* Release resources, unregister device */
-	nand_release(pasemi_nand_mtd);
+	nand_release(chip);
 
 	release_region(lpcctl, 4);
 
diff --git a/drivers/mtd/nand/plat_nand.c b/drivers/mtd/nand/plat_nand.c
index 925a1323604d..8c2d1c5c9569 100644
--- a/drivers/mtd/nand/plat_nand.c
+++ b/drivers/mtd/nand/plat_nand.c
@@ -99,7 +99,7 @@ static int plat_nand_probe(struct platform_device *pdev)
 	if (!err)
 		return err;
 
-	nand_release(mtd);
+	nand_cleanup(&data->chip);
 out:
 	if (pdata->ctrl.remove)
 		pdata->ctrl.remove(pdev);
@@ -114,7 +114,7 @@ static int plat_nand_remove(struct platform_device *pdev)
 	struct plat_nand_data *data = platform_get_drvdata(pdev);
 	struct platform_nand_data *pdata = dev_get_platdata(&pdev->dev);
 
-	nand_release(nand_to_mtd(&data->chip));
+	nand_release(&data->chip);
 	if (pdata->ctrl.remove)
 		pdata->ctrl.remove(pdev);
 
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index 125b744c9c28..df62f99979f3 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -1915,7 +1915,7 @@ static int pxa3xx_nand_remove(struct platform_device *pdev)
 	clk_disable_unprepare(info->clk);
 
 	for (cs = 0; cs < pdata->num_cs; cs++)
-		nand_release(nand_to_mtd(&info->host[cs]->chip));
+		nand_release(&info->host[cs]->chip);
 	return 0;
 }
 
diff --git a/drivers/mtd/nand/qcom_nandc.c b/drivers/mtd/nand/qcom_nandc.c
index 09d5f7df6023..b57678970033 100644
--- a/drivers/mtd/nand/qcom_nandc.c
+++ b/drivers/mtd/nand/qcom_nandc.c
@@ -435,11 +435,13 @@ struct qcom_nand_host {
  * among different NAND controllers.
  * @ecc_modes - ecc mode for NAND
  * @is_bam - whether NAND controller is using BAM
+ * @is_qpic - whether NAND CTRL is part of qpic IP
  * @dev_cmd_reg_start - NAND_DEV_CMD_* registers starting offset
  */
 struct qcom_nandc_props {
 	u32 ecc_modes;
 	bool is_bam;
+	bool is_qpic;
 	u32 dev_cmd_reg_start;
 };
 
@@ -2508,7 +2510,8 @@ static int qcom_nandc_setup(struct qcom_nand_controller *nandc)
 	u32 nand_ctrl;
 
 	/* kill onenand */
-	nandc_write(nandc, SFLASHC_BURST_CFG, 0);
+	if (!nandc->props->is_qpic)
+		nandc_write(nandc, SFLASHC_BURST_CFG, 0);
 	nandc_write(nandc, dev_cmd_reg_addr(nandc, NAND_DEV_CMD_VLD),
 		    NAND_DEV_CMD_VLD_VAL);
 
@@ -2760,7 +2763,7 @@ static int qcom_nandc_remove(struct platform_device *pdev)
 	struct qcom_nand_host *host;
 
 	list_for_each_entry(host, &nandc->host_list, node)
-		nand_release(nand_to_mtd(&host->chip));
+		nand_release(&host->chip);
 
 	qcom_nandc_unalloc(nandc);
 
@@ -2779,12 +2782,14 @@ static const struct qcom_nandc_props ipq806x_nandc_props = {
 static const struct qcom_nandc_props ipq4019_nandc_props = {
 	.ecc_modes = (ECC_BCH_4BIT | ECC_BCH_8BIT),
 	.is_bam = true,
+	.is_qpic = true,
 	.dev_cmd_reg_start = 0x0,
 };
 
 static const struct qcom_nandc_props ipq8074_nandc_props = {
 	.ecc_modes = (ECC_BCH_4BIT | ECC_BCH_8BIT),
 	.is_bam = true,
+	.is_qpic = true,
 	.dev_cmd_reg_start = 0x7000,
 };
 
diff --git a/drivers/mtd/nand/r852.c b/drivers/mtd/nand/r852.c
index fc9287af4614..2cfa54941395 100644
--- a/drivers/mtd/nand/r852.c
+++ b/drivers/mtd/nand/r852.c
@@ -656,7 +656,7 @@ static int r852_register_nand_device(struct r852_device *dev)
 	dev->card_registred = 1;
 	return 0;
 error3:
-	nand_release(mtd);
+	nand_release(dev->chip);
 error1:
 	/* Force card redetect */
 	dev->card_detected = 0;
@@ -675,7 +675,7 @@ static void r852_unregister_nand_device(struct r852_device *dev)
 		return;
 
 	device_remove_file(&mtd->dev, &dev_attr_media_type);
-	nand_release(mtd);
+	nand_release(dev->chip);
 	r852_engine_disable(dev);
 	dev->card_registred = 0;
 }
diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c
index 4c383eeec6f6..f60de68bfabc 100644
--- a/drivers/mtd/nand/s3c2410.c
+++ b/drivers/mtd/nand/s3c2410.c
@@ -784,7 +784,7 @@ static int s3c24xx_nand_remove(struct platform_device *pdev)
 
 		for (mtdno = 0; mtdno < info->mtd_count; mtdno++, ptr++) {
 			pr_debug("releasing mtd %d (%p)\n", mtdno, ptr);
-			nand_release(nand_to_mtd(&ptr->chip));
+			nand_release(&ptr->chip);
 		}
 	}
 
diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index 43db80e5d994..f2ed03ee3035 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -1231,7 +1231,7 @@ static int flctl_remove(struct platform_device *pdev)
 	struct sh_flctl *flctl = platform_get_drvdata(pdev);
 
 	flctl_release_dma(flctl);
-	nand_release(nand_to_mtd(&flctl->chip));
+	nand_release(&flctl->chip);
 	pm_runtime_disable(&pdev->dev);
 
 	return 0;
diff --git a/drivers/mtd/nand/sharpsl.c b/drivers/mtd/nand/sharpsl.c
index f59c455d9f51..c245d66609c1 100644
--- a/drivers/mtd/nand/sharpsl.c
+++ b/drivers/mtd/nand/sharpsl.c
@@ -192,7 +192,7 @@ static int sharpsl_nand_probe(struct platform_device *pdev)
 	return 0;
 
 err_add:
-	nand_release(mtd);
+	nand_cleanup(this);
 
 err_scan:
 	iounmap(sharpsl->io);
@@ -210,7 +210,7 @@ static int sharpsl_nand_remove(struct platform_device *pdev)
 	struct sharpsl_nand *sharpsl = platform_get_drvdata(pdev);
 
 	/* Release resources, unregister device */
-	nand_release(nand_to_mtd(&sharpsl->chip));
+	nand_release(&sharpsl->chip);
 
 	iounmap(sharpsl->io);
 
diff --git a/drivers/mtd/nand/socrates_nand.c b/drivers/mtd/nand/socrates_nand.c
index 575997d0ef8a..8d4f0cd7197d 100644
--- a/drivers/mtd/nand/socrates_nand.c
+++ b/drivers/mtd/nand/socrates_nand.c
@@ -195,7 +195,7 @@ static int socrates_nand_probe(struct platform_device *ofdev)
 	if (!res)
 		return res;
 
-	nand_release(mtd);
+	nand_cleanup(nand_chip);
 
 out:
 	iounmap(host->io_base);
@@ -208,9 +208,8 @@ out:
 static int socrates_nand_remove(struct platform_device *ofdev)
 {
 	struct socrates_nand_host *host = dev_get_drvdata(&ofdev->dev);
-	struct mtd_info *mtd = nand_to_mtd(&host->nand_chip);
 
-	nand_release(mtd);
+	nand_release(&host->nand_chip);
 
 	iounmap(host->io_base);
 
diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c
index 8e5231482397..916e0ccd1e27 100644
--- a/drivers/mtd/nand/sunxi_nand.c
+++ b/drivers/mtd/nand/sunxi_nand.c
@@ -2125,7 +2125,7 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "failed to register mtd device: %d\n", ret);
-		nand_release(mtd);
+		nand_cleanup(nand);
 		return ret;
 	}
 
@@ -2164,7 +2164,7 @@ static void sunxi_nand_chips_cleanup(struct sunxi_nfc *nfc)
 	while (!list_empty(&nfc->chips)) {
 		chip = list_first_entry(&nfc->chips, struct sunxi_nand_chip,
 					node);
-		nand_release(nand_to_mtd(&chip->nand));
+		nand_release(&chip->nand);
 		sunxi_nand_ecc_cleanup(&chip->nand.ecc);
 		list_del(&chip->node);
 	}
diff --git a/drivers/mtd/nand/tango_nand.c b/drivers/mtd/nand/tango_nand.c
index ce366816a7ef..1ab16a90ea29 100644
--- a/drivers/mtd/nand/tango_nand.c
+++ b/drivers/mtd/nand/tango_nand.c
@@ -619,7 +619,7 @@ static int tango_nand_remove(struct platform_device *pdev)
 
 	for (cs = 0; cs < MAX_CS; ++cs) {
 		if (nfc->chips[cs])
-			nand_release(nand_to_mtd(&nfc->chips[cs]->nand_chip));
+			nand_release(&nfc->chips[cs]->nand_chip);
 	}
 
 	return 0;
diff --git a/drivers/mtd/nand/tmio_nand.c b/drivers/mtd/nand/tmio_nand.c
index 84dbf32332e1..51f12b9f90ba 100644
--- a/drivers/mtd/nand/tmio_nand.c
+++ b/drivers/mtd/nand/tmio_nand.c
@@ -448,7 +448,7 @@ static int tmio_probe(struct platform_device *dev)
 	if (!retval)
 		return retval;
 
-	nand_release(mtd);
+	nand_cleanup(nand_chip);
 
 err_irq:
 	tmio_hw_stop(dev, tmio);
@@ -459,7 +459,7 @@ static int tmio_remove(struct platform_device *dev)
 {
 	struct tmio_nand *tmio = platform_get_drvdata(dev);
 
-	nand_release(nand_to_mtd(&tmio->chip));
+	nand_release(&tmio->chip);
 	tmio_hw_stop(dev, tmio);
 	return 0;
 }
diff --git a/drivers/mtd/nand/txx9ndfmc.c b/drivers/mtd/nand/txx9ndfmc.c
index b567d212fe7d..236181b2985a 100644
--- a/drivers/mtd/nand/txx9ndfmc.c
+++ b/drivers/mtd/nand/txx9ndfmc.c
@@ -390,7 +390,7 @@ static int __exit txx9ndfmc_remove(struct platform_device *dev)
 		chip = mtd_to_nand(mtd);
 		txx9_priv = nand_get_controller_data(chip);
 
-		nand_release(mtd);
+		nand_release(chip);
 		kfree(txx9_priv->mtdname);
 		kfree(txx9_priv);
 	}
diff --git a/drivers/mtd/nand/vf610_nfc.c b/drivers/mtd/nand/vf610_nfc.c
index e2583a539b41..688393526b5a 100644
--- a/drivers/mtd/nand/vf610_nfc.c
+++ b/drivers/mtd/nand/vf610_nfc.c
@@ -794,7 +794,7 @@ static int vf610_nfc_remove(struct platform_device *pdev)
 	struct mtd_info *mtd = platform_get_drvdata(pdev);
 	struct vf610_nfc *nfc = mtd_to_nfc(mtd);
 
-	nand_release(mtd);
+	nand_release(mtd_to_nand(mtd));
 	clk_disable_unprepare(nfc->clk);
 	return 0;
 }
diff --git a/drivers/mtd/nand/xway_nand.c b/drivers/mtd/nand/xway_nand.c
index 9926b4e3d69d..176a94fa31d7 100644
--- a/drivers/mtd/nand/xway_nand.c
+++ b/drivers/mtd/nand/xway_nand.c
@@ -211,7 +211,7 @@ static int xway_nand_probe(struct platform_device *pdev)
 
 	err = mtd_device_register(mtd, NULL, 0);
 	if (err)
-		nand_release(mtd);
+		nand_cleanup(&data->chip);
 
 	return err;
 }
@@ -223,7 +223,7 @@ static int xway_nand_remove(struct platform_device *pdev)
 {
 	struct xway_nand_data *data = platform_get_drvdata(pdev);
 
-	nand_release(nand_to_mtd(&data->chip));
+	nand_release(&data->chip);
 
 	return 0;
 }
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index fef599eb822b..6aaf1196d9a5 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1129,6 +1129,7 @@ static void bond_setup_by_slave(struct net_device *bond_dev,
 
 	bond_dev->type		    = slave_dev->type;
 	bond_dev->hard_header_len   = slave_dev->hard_header_len;
+	bond_dev->needed_headroom   = slave_dev->needed_headroom;
 	bond_dev->addr_len	    = slave_dev->addr_len;
 
 	memcpy(bond_dev->broadcast, slave_dev->broadcast,
@@ -2010,7 +2011,8 @@ static int  bond_release_and_destroy(struct net_device *bond_dev,
 	int ret;
 
 	ret = __bond_release_one(bond_dev, slave_dev, false, true);
-	if (ret == 0 && !bond_has_slaves(bond)) {
+	if (ret == 0 && !bond_has_slaves(bond) &&
+	    bond_dev->reg_state != NETREG_UNREGISTERING) {
 		bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
 		netdev_info(bond_dev, "Destroying bond %s\n",
 			    bond_dev->name);
@@ -2752,6 +2754,9 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 			if (bond_time_in_interval(bond, last_rx, 1)) {
 				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
+			} else if (slave->link == BOND_LINK_BACK) {
+				bond_propose_link_state(slave, BOND_LINK_FAIL);
+				commit++;
 			}
 			continue;
 		}
@@ -2862,6 +2867,19 @@ static void bond_ab_arp_commit(struct bonding *bond)
 
 			continue;
 
+		case BOND_LINK_FAIL:
+			bond_set_slave_link_state(slave, BOND_LINK_FAIL,
+						  BOND_SLAVE_NOTIFY_NOW);
+			bond_set_slave_inactive_flags(slave,
+						      BOND_SLAVE_NOTIFY_NOW);
+
+			/* A slave has just been enslaved and has become
+			 * the current active slave.
+			 */
+			if (rtnl_dereference(bond->curr_active_slave))
+				RCU_INIT_POINTER(bond->current_arp_slave, NULL);
+			continue;
+
 		default:
 			netdev_err(bond->dev, "impossible: new_link %d on slave %s\n",
 				   slave->link_new_state, slave->dev->name);
@@ -2911,8 +2929,6 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 			return should_notify_rtnl;
 	}
 
-	bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER);
-
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (!found && !before && bond_slave_is_up(slave))
 			before = slave;
@@ -4156,13 +4172,23 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
+static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed)
+{
+	if (speed == 0 || speed == SPEED_UNKNOWN)
+		speed = slave->speed;
+	else
+		speed = min(speed, slave->speed);
+
+	return speed;
+}
+
 static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
 					   struct ethtool_link_ksettings *cmd)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	unsigned long speed = 0;
 	struct list_head *iter;
 	struct slave *slave;
+	u32 speed = 0;
 
 	cmd->base.duplex = DUPLEX_UNKNOWN;
 	cmd->base.port = PORT_OTHER;
@@ -4174,8 +4200,13 @@ static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
 	 */
 	bond_for_each_slave(bond, slave, iter) {
 		if (bond_slave_can_tx(slave)) {
-			if (slave->speed != SPEED_UNKNOWN)
-				speed += slave->speed;
+			if (slave->speed != SPEED_UNKNOWN) {
+				if (BOND_MODE(bond) == BOND_MODE_BROADCAST)
+					speed = bond_mode_bcast_speed(slave,
+								      speed);
+				else
+					speed += slave->speed;
+			}
 			if (cmd->base.duplex == DUPLEX_UNKNOWN &&
 			    slave->duplex != DUPLEX_UNKNOWN)
 				cmd->base.duplex = slave->duplex;
@@ -4773,15 +4804,19 @@ int bond_create(struct net *net, const char *name)
 	bond_dev->rtnl_link_ops = &bond_link_ops;
 
 	res = register_netdevice(bond_dev);
+	if (res < 0) {
+		free_netdev(bond_dev);
+		rtnl_unlock();
+
+		return res;
+	}
 
 	netif_carrier_off(bond_dev);
 
 	bond_work_init_all(bond);
 
 	rtnl_unlock();
-	if (res < 0)
-		free_netdev(bond_dev);
-	return res;
+	return 0;
 }
 
 static int __net_init bond_net_init(struct net *net)
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 77babf1417a7..0e95eeb822ea 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -451,11 +451,10 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
 		return err;
 
 	err = register_netdevice(bond_dev);
-
-	netif_carrier_off(bond_dev);
 	if (!err) {
 		struct bonding *bond = netdev_priv(bond_dev);
 
+		netif_carrier_off(bond_dev);
 		bond_work_init_all(bond);
 	}
 
diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c
index 641a532b67cb..3f756fa2f603 100644
--- a/drivers/net/bonding/bond_sysfs_slave.c
+++ b/drivers/net/bonding/bond_sysfs_slave.c
@@ -153,8 +153,10 @@ int bond_sysfs_slave_add(struct slave *slave)
 
 	err = kobject_init_and_add(&slave->kobj, &slave_ktype,
 				   &(slave->dev->dev.kobj), "bonding_slave");
-	if (err)
+	if (err) {
+		kobject_put(&slave->kobj);
 		return err;
+	}
 
 	for (a = slave_attrs; *a; ++a) {
 		err = sysfs_create_file(&slave->kobj, &((*a)->attr));
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index daed57d3d209..2b994bbf85ca 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -791,7 +791,7 @@ static int kvaser_usb_simple_msg_async(struct kvaser_usb_net_priv *priv,
 	if (!urb)
 		return -ENOMEM;
 
-	buf = kmalloc(sizeof(struct kvaser_msg), GFP_ATOMIC);
+	buf = kzalloc(sizeof(struct kvaser_msg), GFP_ATOMIC);
 	if (!buf) {
 		usb_free_urb(urb);
 		return -ENOMEM;
@@ -1459,7 +1459,7 @@ static int kvaser_usb_set_opt_mode(const struct kvaser_usb_net_priv *priv)
 	struct kvaser_msg *msg;
 	int rc;
 
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
+	msg = kzalloc(sizeof(*msg), GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
 
@@ -1592,7 +1592,7 @@ static int kvaser_usb_flush_queue(struct kvaser_usb_net_priv *priv)
 	struct kvaser_msg *msg;
 	int rc;
 
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
+	msg = kzalloc(sizeof(*msg), GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
 
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 274d36915110..5c3fa0be8844 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1160,6 +1160,8 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 		return ret;
 
 	switch (ret) {
+	case -ETIMEDOUT:
+		return ret;
 	case -ENOSPC:
 		dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n",
 			addr, vid);
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index b40ebc27e1ec..9f355673f630 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1175,6 +1175,8 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	 */
 	set_bit(0, priv->cfp.used);
 
+	/* Balance of_node_put() done by of_find_node_by_name() */
+	of_node_get(dn);
 	ports = of_find_node_by_name(dn, "ports");
 	if (ports) {
 		bcm_sf2_identify_ports(priv, ports);
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 10ea01459a36..f4268f032266 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2450,7 +2450,6 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
-	.port_set_jumbo_size = mv88e6165_port_set_jumbo_size,
 	.port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting,
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 3143de45baaa..c458b81ba63a 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -433,7 +433,7 @@ static void emac_timeout(struct net_device *dev)
 /* Hardware start transmission.
  * Send a packet to media from the upper layer.
  */
-static int emac_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t emac_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct emac_board_info *db = netdev_priv(dev);
 	unsigned long channel;
@@ -441,7 +441,7 @@ static int emac_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	channel = db->tx_fifo_stat & 3;
 	if (channel == 3)
-		return 1;
+		return NETDEV_TX_BUSY;
 
 	channel = (channel == 1 ? 1 : 0);
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index dc9149a32f41..bb1710ff910a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -2131,6 +2131,9 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
 		rss->hash_key;
 	int rc;
 
+	if (unlikely(!func))
+		return -EINVAL;
+
 	rc = ena_com_get_feature_ex(ena_dev, &get_resp,
 				    ENA_ADMIN_RSS_HASH_FUNCTION,
 				    rss->hash_key_dma_addr,
@@ -2143,8 +2146,7 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
 	if (rss->hash_func)
 		rss->hash_func--;
 
-	if (func)
-		*func = rss->hash_func;
+	*func = rss->hash_func;
 
 	if (key)
 		memcpy(key, hash_key->key, (size_t)(hash_key->keys_num) << 2);
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index eac740c476ce..a8b462e1beba 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -1187,7 +1187,7 @@ bmac_get_station_address(struct net_device *dev, unsigned char *ea)
 	int i;
 	unsigned short data;
 
-	for (i = 0; i < 6; i++)
+	for (i = 0; i < 3; i++)
 		{
 			reset_and_select_srom(dev);
 			data = read_srom(dev, i + EnetAddressOffset/2, SROMAddressBits);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index b83ee74d2839..77e5c6926814 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -746,7 +746,7 @@ static int hw_atl_a0_hw_multicast_list_set(struct aq_hw_s *self,
 	int err = 0;
 
 	if (count > (HW_ATL_A0_MAC_MAX - HW_ATL_A0_MAC_MIN)) {
-		err = EBADRQC;
+		err = -EBADRQC;
 		goto err_exit;
 	}
 	for (self->aq_nic_cfg->mc_list_count = 0U;
diff --git a/drivers/net/ethernet/arc/emac_mdio.c b/drivers/net/ethernet/arc/emac_mdio.c
index 0187dbf3b87d..54cdafdd067d 100644
--- a/drivers/net/ethernet/arc/emac_mdio.c
+++ b/drivers/net/ethernet/arc/emac_mdio.c
@@ -153,6 +153,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv)
 	if (IS_ERR(data->reset_gpio)) {
 		error = PTR_ERR(data->reset_gpio);
 		dev_err(priv->dev, "Failed to request gpio: %d\n", error);
+		mdiobus_free(bus);
 		return error;
 	}
 
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 5e5022fa1d04..85029d43da75 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1250,8 +1250,12 @@ out_disable_adv_intr:
 
 static void __alx_stop(struct alx_priv *alx)
 {
-	alx_halt(alx);
 	alx_free_irq(alx);
+
+	cancel_work_sync(&alx->link_check_wk);
+	cancel_work_sync(&alx->reset_wk);
+
+	alx_halt(alx);
 	alx_free_rings(alx);
 	alx_free_napis(alx);
 }
@@ -1863,9 +1867,6 @@ static void alx_remove(struct pci_dev *pdev)
 	struct alx_priv *alx = pci_get_drvdata(pdev);
 	struct alx_hw *hw = &alx->hw;
 
-	cancel_work_sync(&alx->link_check_wk);
-	cancel_work_sync(&alx->reset_wk);
-
 	/* restore permanent mac address */
 	alx_set_macaddr(hw, hw->perm_addr);
 
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 123ee5c11bc0..11eb393497a2 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2087,8 +2087,10 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 	priv->tx_rings = devm_kcalloc(&pdev->dev, txq,
 				      sizeof(struct bcm_sysport_tx_ring),
 				      GFP_KERNEL);
-	if (!priv->tx_rings)
-		return -ENOMEM;
+	if (!priv->tx_rings) {
+		ret = -ENOMEM;
+		goto err_free_netdev;
+	}
 
 	priv->is_lite = params->is_lite;
 	priv->num_rx_desc_words = params->num_rx_desc_words;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a189061d8f97..a03239ba1a32 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6378,14 +6378,14 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		}
 	}
 
-	bnxt_enable_napi(bp);
-
 	rc = bnxt_init_nic(bp, irq_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
-		goto open_err;
+		goto open_err_irq;
 	}
 
+	bnxt_enable_napi(bp);
+
 	if (link_re_init) {
 		mutex_lock(&bp->link_lock);
 		rc = bnxt_update_phy_setting(bp);
@@ -6410,9 +6410,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		bnxt_vf_reps_open(bp);
 	return 0;
 
-open_err:
-	bnxt_disable_napi(bp);
-
 open_err_irq:
 	bnxt_del_napi(bp);
 
@@ -8251,6 +8248,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	bnxt_parse_log_pcie_link(bp);
 
+	pci_save_state(pdev);
 	return 0;
 
 init_err_cleanup_tc:
@@ -8412,6 +8410,8 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 			"Cannot re-enable PCI device after reset.\n");
 	} else {
 		pci_set_master(pdev);
+		pci_restore_state(pdev);
+		pci_save_state(pdev);
 
 		err = bnxt_hwrm_func_reset(bp);
 		if (!err && netif_running(netdev))
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 3c78cd1cdd6f..cc2ecbbfd4bd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1264,9 +1264,12 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 	if (!BNXT_SINGLE_PF(bp))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&bp->link_lock);
 	if (epause->autoneg) {
-		if (!(link_info->autoneg & BNXT_AUTONEG_SPEED))
-			return -EINVAL;
+		if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
+			rc = -EINVAL;
+			goto pause_exit;
+		}
 
 		link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL;
 		if (bp->hwrm_spec_code >= 0x10201)
@@ -1289,6 +1292,9 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 
 	if (netif_running(dev))
 		rc = bnxt_hwrm_set_pause(bp);
+
+pause_exit:
+	mutex_unlock(&bp->link_lock);
 	return rc;
 }
 
@@ -1758,6 +1764,9 @@ static int bnxt_get_nvram_directory(struct net_device *dev, u32 len, u8 *data)
 	if (rc != 0)
 		return rc;
 
+	if (!dir_entries || !entry_length)
+		return -EIO;
+
 	/* Insert 2 bytes of directory info (count and size of entries) */
 	if (len < 2)
 		return -EINVAL;
@@ -1971,8 +1980,7 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	struct bnxt *bp = netdev_priv(dev);
 	struct ethtool_eee *eee = &bp->eee;
 	struct bnxt_link_info *link_info = &bp->link_info;
-	u32 advertising =
-		 _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
+	u32 advertising;
 	int rc = 0;
 
 	if (!BNXT_SINGLE_PF(bp))
@@ -1981,19 +1989,23 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	if (!(bp->flags & BNXT_FLAG_EEE_CAP))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&bp->link_lock);
+	advertising = _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
 	if (!edata->eee_enabled)
 		goto eee_ok;
 
 	if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
 		netdev_warn(dev, "EEE requires autoneg\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto eee_exit;
 	}
 	if (edata->tx_lpi_enabled) {
 		if (bp->lpi_tmr_hi && (edata->tx_lpi_timer > bp->lpi_tmr_hi ||
 				       edata->tx_lpi_timer < bp->lpi_tmr_lo)) {
 			netdev_warn(dev, "Valid LPI timer range is %d and %d microsecs\n",
 				    bp->lpi_tmr_lo, bp->lpi_tmr_hi);
-			return -EINVAL;
+			rc = -EINVAL;
+			goto eee_exit;
 		} else if (!bp->lpi_tmr_hi) {
 			edata->tx_lpi_timer = eee->tx_lpi_timer;
 		}
@@ -2003,7 +2015,8 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	} else if (edata->advertised & ~advertising) {
 		netdev_warn(dev, "EEE advertised %x must be a subset of autoneg advertised speeds %x\n",
 			    edata->advertised, advertising);
-		return -EINVAL;
+		rc = -EINVAL;
+		goto eee_exit;
 	}
 
 	eee->advertised = edata->advertised;
@@ -2015,6 +2028,8 @@ eee_ok:
 	if (netif_running(dev))
 		rc = bnxt_hwrm_set_link_setting(bp, false, true);
 
+eee_exit:
+	mutex_unlock(&bp->link_lock);
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index cef59b3b77a3..f0bc8f5246c0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -344,6 +344,7 @@ static void bnxt_free_vf_resources(struct bnxt *bp)
 		}
 	}
 
+	bp->pf.active_vfs = 0;
 	kfree(bp->pf.vf);
 	bp->pf.vf = NULL;
 }
@@ -608,7 +609,6 @@ void bnxt_sriov_disable(struct bnxt *bp)
 
 	bnxt_free_vf_resources(bp);
 
-	bp->pf.active_vfs = 0;
 	/* Reclaim all resources for the PF. */
 	rtnl_lock();
 	bnxt_restore_pf_fw_resources(bp);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 38391230ca86..8bfa2523e253 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -72,6 +72,9 @@
 #define GENET_RDMA_REG_OFF	(priv->hw_params->rdma_offset + \
 				TOTAL_DESC * DMA_DESC_SIZE)
 
+/* Forward declarations */
+static void bcmgenet_set_rx_mode(struct net_device *dev);
+
 static inline void bcmgenet_writel(u32 value, void __iomem *offset)
 {
 	/* MIPS chips strapped for BE will automagically configure the
@@ -1564,11 +1567,6 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto out;
 	}
 
-	if (skb_padto(skb, ETH_ZLEN)) {
-		ret = NETDEV_TX_OK;
-		goto out;
-	}
-
 	/* Retain how many bytes will be sent on the wire, without TSB inserted
 	 * by transmit checksum offload
 	 */
@@ -1618,6 +1616,9 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		len_stat = (size << DMA_BUFLENGTH_SHIFT) |
 			   (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT);
 
+		/* Note: if we ever change from DMA_TX_APPEND_CRC below we
+		 * will need to restore software padding of "runt" packets
+		 */
 		if (!i) {
 			len_stat |= DMA_TX_APPEND_CRC | DMA_SOP;
 			if (skb->ip_summed == CHECKSUM_PARTIAL)
@@ -2858,6 +2859,7 @@ static void bcmgenet_netif_start(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
 	/* Start the network engine */
+	bcmgenet_set_rx_mode(dev);
 	bcmgenet_enable_rx_napi(priv);
 	bcmgenet_enable_tx_napi(priv);
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index bc0221eafe5c..480179ddc45b 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7204,8 +7204,8 @@ static inline void tg3_reset_task_schedule(struct tg3 *tp)
 
 static inline void tg3_reset_task_cancel(struct tg3 *tp)
 {
-	cancel_work_sync(&tp->reset_task);
-	tg3_flag_clear(tp, RESET_TASK_PENDING);
+	if (test_and_clear_bit(TG3_FLAG_RESET_TASK_PENDING, tp->tg3_flags))
+		cancel_work_sync(&tp->reset_task);
 	tg3_flag_clear(tp, TX_RECOVERY_PENDING);
 }
 
@@ -11182,18 +11182,27 @@ static void tg3_reset_task(struct work_struct *work)
 
 	tg3_halt(tp, RESET_KIND_SHUTDOWN, 0);
 	err = tg3_init_hw(tp, true);
-	if (err)
+	if (err) {
+		tg3_full_unlock(tp);
+		tp->irq_sync = 0;
+		tg3_napi_enable(tp);
+		/* Clear this flag so that tg3_reset_task_cancel() will not
+		 * call cancel_work_sync() and wait forever.
+		 */
+		tg3_flag_clear(tp, RESET_TASK_PENDING);
+		dev_close(tp->dev);
 		goto out;
+	}
 
 	tg3_netif_start(tp);
 
-out:
 	tg3_full_unlock(tp);
 
 	if (!err)
 		tg3_phy_start(tp);
 
 	tg3_flag_clear(tp, RESET_TASK_PENDING);
+out:
 	rtnl_unlock();
 }
 
@@ -18179,8 +18188,8 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 
 	rtnl_lock();
 
-	/* We probably don't have netdev yet */
-	if (!netdev || !netif_running(netdev))
+	/* Could be second call or maybe we don't have netdev yet */
+	if (!netdev || tp->pcierr_recovery || !netif_running(netdev))
 		goto done;
 
 	/* We needn't recover from permanent error */
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index b01b242c2bf0..4d2a996ba446 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3516,7 +3516,7 @@ static int macb_probe(struct platform_device *pdev)
 	bp->wol = 0;
 	if (of_get_property(np, "magic-packet", NULL))
 		bp->wol |= MACB_WOL_HAS_MAGIC_PACKET;
-	device_init_wakeup(&pdev->dev, bp->wol & MACB_WOL_HAS_MAGIC_PACKET);
+	device_set_wakeup_capable(&pdev->dev, bp->wol & MACB_WOL_HAS_MAGIC_PACKET);
 
 	spin_lock_init(&bp->lock);
 
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 2e089b5ff8f3..30f0e54f658e 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -1167,7 +1167,7 @@ static int cn23xx_get_pf_num(struct octeon_device *oct)
 		oct->pf_num = ((fdl_bit >> CN23XX_PCIE_SRIOV_FDL_BIT_POS) &
 			       CN23XX_PCIE_SRIOV_FDL_MASK);
 	} else {
-		ret = EINVAL;
+		ret = -EINVAL;
 
 		/* Under some virtual environments, extended PCI regs are
 		 * inaccessible, in which case the above read will have failed.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
index 48970ba08bdc..de5804ddefbd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
@@ -47,7 +47,7 @@ static int fill_match_fields(struct adapter *adap,
 			     bool next_header)
 {
 	unsigned int i, j;
-	u32 val, mask;
+	__be32 val, mask;
 	int off, err;
 	bool found;
 
@@ -217,7 +217,7 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 		const struct cxgb4_next_header *next;
 		bool found = false;
 		unsigned int i, j;
-		u32 val, mask;
+		__be32 val, mask;
 		int off;
 
 		if (t->table[link_uhtid - 1].link_handle) {
@@ -231,10 +231,10 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 
 		/* Try to find matches that allow jumps to next header. */
 		for (i = 0; next[i].jump; i++) {
-			if (next[i].offoff != cls->knode.sel->offoff ||
-			    next[i].shift != cls->knode.sel->offshift ||
-			    next[i].mask != cls->knode.sel->offmask ||
-			    next[i].offset != cls->knode.sel->off)
+			if (next[i].sel.offoff != cls->knode.sel->offoff ||
+			    next[i].sel.offshift != cls->knode.sel->offshift ||
+			    next[i].sel.offmask != cls->knode.sel->offmask ||
+			    next[i].sel.off != cls->knode.sel->off)
 				continue;
 
 			/* Found a possible candidate.  Find a key that
@@ -246,9 +246,9 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 				val = cls->knode.sel->keys[j].val;
 				mask = cls->knode.sel->keys[j].mask;
 
-				if (next[i].match_off == off &&
-				    next[i].match_val == val &&
-				    next[i].match_mask == mask) {
+				if (next[i].key.off == off &&
+				    next[i].key.val == val &&
+				    next[i].key.mask == mask) {
 					found = true;
 					break;
 				}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
index a4b99edcc339..141085e159e5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
@@ -38,12 +38,12 @@
 struct cxgb4_match_field {
 	int off; /* Offset from the beginning of the header to match */
 	/* Fill the value/mask pair in the spec if matched */
-	int (*val)(struct ch_filter_specification *f, u32 val, u32 mask);
+	int (*val)(struct ch_filter_specification *f, __be32 val, __be32 mask);
 };
 
 /* IPv4 match fields */
 static inline int cxgb4_fill_ipv4_tos(struct ch_filter_specification *f,
-				      u32 val, u32 mask)
+				      __be32 val, __be32 mask)
 {
 	f->val.tos  = (ntohl(val)  >> 16) & 0x000000FF;
 	f->mask.tos = (ntohl(mask) >> 16) & 0x000000FF;
@@ -52,7 +52,7 @@ static inline int cxgb4_fill_ipv4_tos(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_frag(struct ch_filter_specification *f,
-				       u32 val, u32 mask)
+				       __be32 val, __be32 mask)
 {
 	u32 mask_val;
 	u8 frag_val;
@@ -74,7 +74,7 @@ static inline int cxgb4_fill_ipv4_frag(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_proto(struct ch_filter_specification *f,
-					u32 val, u32 mask)
+					__be32 val, __be32 mask)
 {
 	f->val.proto  = (ntohl(val)  >> 16) & 0x000000FF;
 	f->mask.proto = (ntohl(mask) >> 16) & 0x000000FF;
@@ -83,7 +83,7 @@ static inline int cxgb4_fill_ipv4_proto(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_src_ip(struct ch_filter_specification *f,
-					 u32 val, u32 mask)
+					 __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[0], &mask, sizeof(u32));
@@ -92,7 +92,7 @@ static inline int cxgb4_fill_ipv4_src_ip(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_dst_ip(struct ch_filter_specification *f,
-					 u32 val, u32 mask)
+					 __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[0], &mask, sizeof(u32));
@@ -111,7 +111,7 @@ static const struct cxgb4_match_field cxgb4_ipv4_fields[] = {
 
 /* IPv6 match fields */
 static inline int cxgb4_fill_ipv6_tos(struct ch_filter_specification *f,
-				      u32 val, u32 mask)
+				      __be32 val, __be32 mask)
 {
 	f->val.tos  = (ntohl(val)  >> 20) & 0x000000FF;
 	f->mask.tos = (ntohl(mask) >> 20) & 0x000000FF;
@@ -120,7 +120,7 @@ static inline int cxgb4_fill_ipv6_tos(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_proto(struct ch_filter_specification *f,
-					u32 val, u32 mask)
+					__be32 val, __be32 mask)
 {
 	f->val.proto  = (ntohl(val)  >> 8) & 0x000000FF;
 	f->mask.proto = (ntohl(mask) >> 8) & 0x000000FF;
@@ -129,7 +129,7 @@ static inline int cxgb4_fill_ipv6_proto(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip0(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[0], &mask, sizeof(u32));
@@ -138,7 +138,7 @@ static inline int cxgb4_fill_ipv6_src_ip0(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip1(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[4],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[4], &mask, sizeof(u32));
@@ -147,7 +147,7 @@ static inline int cxgb4_fill_ipv6_src_ip1(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip2(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[8],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[8], &mask, sizeof(u32));
@@ -156,7 +156,7 @@ static inline int cxgb4_fill_ipv6_src_ip2(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip3(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[12],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[12], &mask, sizeof(u32));
@@ -165,7 +165,7 @@ static inline int cxgb4_fill_ipv6_src_ip3(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip0(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[0], &mask, sizeof(u32));
@@ -174,7 +174,7 @@ static inline int cxgb4_fill_ipv6_dst_ip0(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip1(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[4],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[4], &mask, sizeof(u32));
@@ -183,7 +183,7 @@ static inline int cxgb4_fill_ipv6_dst_ip1(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip2(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[8],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[8], &mask, sizeof(u32));
@@ -192,7 +192,7 @@ static inline int cxgb4_fill_ipv6_dst_ip2(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip3(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[12],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[12], &mask, sizeof(u32));
@@ -216,7 +216,7 @@ static const struct cxgb4_match_field cxgb4_ipv6_fields[] = {
 
 /* TCP/UDP match */
 static inline int cxgb4_fill_l4_ports(struct ch_filter_specification *f,
-				      u32 val, u32 mask)
+				      __be32 val, __be32 mask)
 {
 	f->val.fport  = ntohl(val)  >> 16;
 	f->mask.fport = ntohl(mask) >> 16;
@@ -237,19 +237,13 @@ static const struct cxgb4_match_field cxgb4_udp_fields[] = {
 };
 
 struct cxgb4_next_header {
-	unsigned int offset; /* Offset to next header */
-	/* offset, shift, and mask added to offset above
+	/* Offset, shift, and mask added to beginning of the header
 	 * to get to next header.  Useful when using a header
 	 * field's value to jump to next header such as IHL field
 	 * in IPv4 header.
 	 */
-	unsigned int offoff;
-	u32 shift;
-	u32 mask;
-	/* match criteria to make this jump */
-	unsigned int match_off;
-	u32 match_val;
-	u32 match_mask;
+	struct tc_u32_sel sel;
+	struct tc_u32_key key;
 	/* location of jump to make */
 	const struct cxgb4_match_field *jump;
 };
@@ -258,26 +252,74 @@ struct cxgb4_next_header {
  * IPv4 header.
  */
 static const struct cxgb4_next_header cxgb4_ipv4_jumps[] = {
-	{ .offset = 0, .offoff = 0, .shift = 6, .mask = 0xF,
-	  .match_off = 8, .match_val = 0x600, .match_mask = 0xFF00,
-	  .jump = cxgb4_tcp_fields },
-	{ .offset = 0, .offoff = 0, .shift = 6, .mask = 0xF,
-	  .match_off = 8, .match_val = 0x1100, .match_mask = 0xFF00,
-	  .jump = cxgb4_udp_fields },
-	{ .jump = NULL }
+	{
+		/* TCP Jump */
+		.sel = {
+			.off = 0,
+			.offoff = 0,
+			.offshift = 6,
+			.offmask = cpu_to_be16(0x0f00),
+		},
+		.key = {
+			.off = 8,
+			.val = cpu_to_be32(0x00060000),
+			.mask = cpu_to_be32(0x00ff0000),
+		},
+		.jump = cxgb4_tcp_fields,
+	},
+	{
+		/* UDP Jump */
+		.sel = {
+			.off = 0,
+			.offoff = 0,
+			.offshift = 6,
+			.offmask = cpu_to_be16(0x0f00),
+		},
+		.key = {
+			.off = 8,
+			.val = cpu_to_be32(0x00110000),
+			.mask = cpu_to_be32(0x00ff0000),
+		},
+		.jump = cxgb4_udp_fields,
+	},
+	{ .jump = NULL },
 };
 
 /* Accept a rule with a jump directly past the 40 Bytes of IPv6 fixed header
  * to get to transport layer header.
  */
 static const struct cxgb4_next_header cxgb4_ipv6_jumps[] = {
-	{ .offset = 0x28, .offoff = 0, .shift = 0, .mask = 0,
-	  .match_off = 4, .match_val = 0x60000, .match_mask = 0xFF0000,
-	  .jump = cxgb4_tcp_fields },
-	{ .offset = 0x28, .offoff = 0, .shift = 0, .mask = 0,
-	  .match_off = 4, .match_val = 0x110000, .match_mask = 0xFF0000,
-	  .jump = cxgb4_udp_fields },
-	{ .jump = NULL }
+	{
+		/* TCP Jump */
+		.sel = {
+			.off = 40,
+			.offoff = 0,
+			.offshift = 0,
+			.offmask = 0,
+		},
+		.key = {
+			.off = 4,
+			.val = cpu_to_be32(0x00000600),
+			.mask = cpu_to_be32(0x0000ff00),
+		},
+		.jump = cxgb4_tcp_fields,
+	},
+	{
+		/* UDP Jump */
+		.sel = {
+			.off = 40,
+			.offoff = 0,
+			.offshift = 0,
+			.offmask = 0,
+		},
+		.key = {
+			.off = 4,
+			.val = cpu_to_be32(0x00001100),
+			.mask = cpu_to_be32(0x0000ff00),
+		},
+		.jump = cxgb4_udp_fields,
+	},
+	{ .jump = NULL },
 };
 
 struct cxgb4_link {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 4ef68f69b58c..006f8b8aaa7d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1812,6 +1812,7 @@ static inline int uld_send(struct adapter *adap, struct sk_buff *skb,
 	txq_info = adap->sge.uld_txq_info[tx_uld_type];
 	if (unlikely(!txq_info)) {
 		WARN_ON(true);
+		kfree_skb(skb);
 		return NET_XMIT_DROP;
 	}
 
@@ -2088,7 +2089,7 @@ static noinline int t4_systim_to_hwstamp(struct adapter *adapter,
 
 	hwtstamps = skb_hwtstamps(skb);
 	memset(hwtstamps, 0, sizeof(*hwtstamps));
-	hwtstamps->hwtstamp = ns_to_ktime(be64_to_cpu(*((u64 *)data)));
+	hwtstamps->hwtstamp = ns_to_ktime(get_unaligned_be64(data));
 
 	return RX_PTP_PKT_SUC;
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 0f126ce4645f..ecb8ef4a756f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -3361,7 +3361,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info,
 	drv_fw = &fw_info->fw_hdr;
 
 	/* Read the header of the firmware on the card */
-	ret = -t4_read_flash(adap, FLASH_FW_START,
+	ret = t4_read_flash(adap, FLASH_FW_START,
 			    sizeof(*card_fw) / sizeof(uint32_t),
 			    (uint32_t *)card_fw, 1);
 	if (ret == 0) {
@@ -3390,8 +3390,8 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info,
 		   should_install_fs_fw(adap, card_fw_usable,
 					be32_to_cpu(fs_fw->fw_ver),
 					be32_to_cpu(card_fw->fw_ver))) {
-		ret = -t4_fw_upgrade(adap, adap->mbox, fw_data,
-				     fw_size, 0);
+		ret = t4_fw_upgrade(adap, adap->mbox, fw_data,
+				    fw_size, 0);
 		if (ret != 0) {
 			dev_err(adap->pdev_dev,
 				"failed to install firmware: %d\n", ret);
@@ -3422,7 +3422,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info,
 			FW_HDR_FW_VER_MICRO_G(c), FW_HDR_FW_VER_BUILD_G(c),
 			FW_HDR_FW_VER_MAJOR_G(k), FW_HDR_FW_VER_MINOR_G(k),
 			FW_HDR_FW_VER_MICRO_G(k), FW_HDR_FW_VER_BUILD_G(k));
-		ret = EINVAL;
+		ret = -EINVAL;
 		goto bye;
 	}
 
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index c87b8cc42963..6ca15c595f54 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -91,7 +91,7 @@ MODULE_PARM_DESC (rx_copybreak, "de2104x Breakpoint at which Rx packets are copi
 #define DSL			CONFIG_DE2104X_DSL
 #endif
 
-#define DE_RX_RING_SIZE		64
+#define DE_RX_RING_SIZE		128
 #define DE_TX_RING_SIZE		64
 #define DE_RING_BYTES		\
 		((sizeof(struct de_desc) * DE_RX_RING_SIZE) +	\
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index 6e490fd2345d..71f0640200bc 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -76,6 +76,7 @@ config UCC_GETH
 	depends on QUICC_ENGINE
 	select FSL_PQ_MDIO
 	select PHYLIB
+	select FIXED_PHY
 	---help---
 	  This driver supports the Gigabit Ethernet mode of the QUICC Engine,
 	  which is available on some Freescale SOCs.
@@ -89,6 +90,7 @@ config GIANFAR
 	depends on HAS_DMA
 	select FSL_PQ_MDIO
 	select PHYLIB
+	select FIXED_PHY
 	select CRC32
 	---help---
 	  This driver supports the Gigabit TSEC on the MPC83xx, MPC85xx,
diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig b/drivers/net/ethernet/freescale/dpaa/Kconfig
index a654736237a9..8fec41e57178 100644
--- a/drivers/net/ethernet/freescale/dpaa/Kconfig
+++ b/drivers/net/ethernet/freescale/dpaa/Kconfig
@@ -2,6 +2,7 @@ menuconfig FSL_DPAA_ETH
 	tristate "DPAA Ethernet"
 	depends on FSL_DPAA && FSL_FMAN
 	select PHYLIB
+	select FIXED_PHY
 	select FSL_FMAN_MAC
 	---help---
 	  Data Path Acceleration Architecture Ethernet driver,
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8ba915cc4c2e..22f964ef859e 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3536,11 +3536,11 @@ failed_mii_init:
 failed_irq:
 failed_init:
 	fec_ptp_stop(pdev);
-	if (fep->reg_phy)
-		regulator_disable(fep->reg_phy);
 failed_reset:
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+	if (fep->reg_phy)
+		regulator_disable(fep->reg_phy);
 failed_regulator:
 	clk_disable_unprepare(fep->clk_ahb);
 failed_clk_ahb:
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index 9080d2332d03..cdd48b1cc84a 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -1396,8 +1396,7 @@ static void enable_time_stamp(struct fman *fman)
 {
 	struct fman_fpm_regs __iomem *fpm_rg = fman->fpm_regs;
 	u16 fm_clk_freq = fman->state->fm_clk_freq;
-	u32 tmp, intgr, ts_freq;
-	u64 frac;
+	u32 tmp, intgr, ts_freq, frac;
 
 	ts_freq = (u32)(1 << fman->state->count1_micro_bit);
 	/* configure timestamp so that bit 8 will count 1 microsecond
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
index 7af31ddd093f..61238b3af204 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
@@ -1159,7 +1159,7 @@ int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr)
 		list_for_each(pos,
 			      &dtsec->multicast_addr_hash->lsts[bucket]) {
 			hash_entry = ETH_HASH_ENTRY_OBJ(pos);
-			if (hash_entry->addr == addr) {
+			if (hash_entry && hash_entry->addr == addr) {
 				list_del_init(&hash_entry->node);
 				kfree(hash_entry);
 				break;
@@ -1172,7 +1172,7 @@ int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr)
 		list_for_each(pos,
 			      &dtsec->unicast_addr_hash->lsts[bucket]) {
 			hash_entry = ETH_HASH_ENTRY_OBJ(pos);
-			if (hash_entry->addr == addr) {
+			if (hash_entry && hash_entry->addr == addr) {
 				list_del_init(&hash_entry->node);
 				kfree(hash_entry);
 				break;
diff --git a/drivers/net/ethernet/freescale/fman/fman_mac.h b/drivers/net/ethernet/freescale/fman/fman_mac.h
index dd6d0526f6c1..19f327efdaff 100644
--- a/drivers/net/ethernet/freescale/fman/fman_mac.h
+++ b/drivers/net/ethernet/freescale/fman/fman_mac.h
@@ -252,7 +252,7 @@ static inline struct eth_hash_t *alloc_hash_table(u16 size)
 	struct eth_hash_t *hash;
 
 	/* Allocate address hash table */
-	hash = kmalloc_array(size, sizeof(struct eth_hash_t *), GFP_KERNEL);
+	hash = kmalloc(sizeof(*hash), GFP_KERNEL);
 	if (!hash)
 		return NULL;
 
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index b33650a897f1..460f9e58e987 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -855,7 +855,6 @@ int memac_set_tx_pause_frames(struct fman_mac *memac, u8 priority,
 
 	tmp = ioread32be(&regs->command_config);
 	tmp &= ~CMD_CFG_PFC_MODE;
-	priority = 0;
 
 	iowrite32be(tmp, &regs->command_config);
 
@@ -957,7 +956,7 @@ int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr)
 
 	list_for_each(pos, &memac->multicast_addr_hash->lsts[hash]) {
 		hash_entry = ETH_HASH_ENTRY_OBJ(pos);
-		if (hash_entry->addr == addr) {
+		if (hash_entry && hash_entry->addr == addr) {
 			list_del_init(&hash_entry->node);
 			kfree(hash_entry);
 			break;
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index 495190764155..ac3d791f5282 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -1744,6 +1744,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	struct fman_port *port;
 	struct fman *fman;
 	struct device_node *fm_node, *port_node;
+	struct platform_device *fm_pdev;
 	struct resource res;
 	struct resource *dev_res;
 	u32 val;
@@ -1768,8 +1769,14 @@ static int fman_port_probe(struct platform_device *of_dev)
 		goto return_err;
 	}
 
-	fman = dev_get_drvdata(&of_find_device_by_node(fm_node)->dev);
+	fm_pdev = of_find_device_by_node(fm_node);
 	of_node_put(fm_node);
+	if (!fm_pdev) {
+		err = -EINVAL;
+		goto return_err;
+	}
+
+	fman = dev_get_drvdata(&fm_pdev->dev);
 	if (!fman) {
 		err = -EINVAL;
 		goto return_err;
diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c
index e575259d20f4..c8ad9b8a75f8 100644
--- a/drivers/net/ethernet/freescale/fman/fman_tgec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c
@@ -585,7 +585,7 @@ int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr)
 
 	list_for_each(pos, &tgec->multicast_addr_hash->lsts[hash]) {
 		hash_entry = ETH_HASH_ENTRY_OBJ(pos);
-		if (hash_entry->addr == addr) {
+		if (hash_entry && hash_entry->addr == addr) {
 			list_del_init(&hash_entry->node);
 			kfree(hash_entry);
 			break;
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index e4a2c74a9b47..6b95334e172d 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -844,8 +844,10 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 				continue;
 
 			err = gfar_parse_group(child, priv, model);
-			if (err)
+			if (err) {
+				of_node_put(child);
 				goto err_grp_init;
+			}
 		}
 	} else { /* SQ_SG_MODE */
 		err = gfar_parse_group(np, priv, model);
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index bddf4c25ee6e..7c2a9fd4dc1a 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -45,6 +45,7 @@
 #include <soc/fsl/qe/ucc.h>
 #include <soc/fsl/qe/ucc_fast.h>
 #include <asm/machdep.h>
+#include <net/sch_generic.h>
 
 #include "ucc_geth.h"
 
@@ -1551,11 +1552,8 @@ static int ugeth_disable(struct ucc_geth_private *ugeth, enum comm_dir mode)
 
 static void ugeth_quiesce(struct ucc_geth_private *ugeth)
 {
-	/* Prevent any further xmits, plus detach the device. */
-	netif_device_detach(ugeth->ndev);
-
-	/* Wait for any current xmits to finish. */
-	netif_tx_disable(ugeth->ndev);
+	/* Prevent any further xmits */
+	netif_tx_stop_all_queues(ugeth->ndev);
 
 	/* Disable the interrupt to avoid NAPI rescheduling. */
 	disable_irq(ugeth->ug_info->uf_info.irq);
@@ -1568,7 +1566,10 @@ static void ugeth_activate(struct ucc_geth_private *ugeth)
 {
 	napi_enable(&ugeth->napi);
 	enable_irq(ugeth->ug_info->uf_info.irq);
-	netif_device_attach(ugeth->ndev);
+
+	/* allow to xmit again  */
+	netif_tx_wake_all_queues(ugeth->ndev);
+	__netdev_watchdog_up(ugeth->ndev);
 }
 
 /* Called every time the controller might need to be made
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 7d0f3cd8a002..9e1e2d5b80dc 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -2770,7 +2770,7 @@ static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port)
 	struct hns_mac_cb *mac_cb;
 	u8 addr[ETH_ALEN] = {0};
 	u8 port_num;
-	u16 mskid;
+	int mskid;
 
 	/* promisc use vague table match with vlanid = 0 & macaddr = 0 */
 	hns_dsaf_set_mac_key(dsaf_dev, &mac_key, 0x00, port, addr);
@@ -3142,6 +3142,9 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 		dsaf_set_bit(credit, DSAF_SBM_ROCEE_CFG_CRD_EN_B, 1);
 		dsaf_write_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG, credit);
 	}
+
+	put_device(&pdev->dev);
+
 	return 0;
 }
 EXPORT_SYMBOL(hns_dsaf_roce_reset);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 0733745f4be6..af832929ae28 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -2433,8 +2433,10 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 			priv->enet_ver = AE_VERSION_1;
 		else if (acpi_dev_found(hns_enet_acpi_match[1].id))
 			priv->enet_ver = AE_VERSION_2;
-		else
-			return -ENXIO;
+		else {
+			ret = -ENXIO;
+			goto out_read_prop_fail;
+		}
 
 		/* try to find port-idx-in-ae first */
 		ret = acpi_node_get_property_reference(dev->fwnode,
@@ -2446,7 +2448,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 		priv->fwnode = acpi_fwnode_handle(args.adev);
 	} else {
 		dev_err(dev, "cannot read cfg data from OF or acpi\n");
-		return -ENXIO;
+		ret = -ENXIO;
+		goto out_read_prop_fail;
 	}
 
 	ret = device_property_read_u32(dev, "port-idx-in-ae", &port_id);
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 880d925438c1..b43aebfc7f5b 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1695,7 +1695,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	}
 
 	netdev->min_mtu = IBMVETH_MIN_MTU;
-	netdev->max_mtu = ETH_MAX_MTU;
+	netdev->max_mtu = ETH_MAX_MTU - IBMVETH_BUFF_OH;
 
 	memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN);
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 956fbb164e6f..8b8a0c4fbc99 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2324,7 +2324,7 @@ req_rx_irq_failed:
 req_tx_irq_failed:
 	for (j = 0; j < i; j++) {
 		free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
-		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+		irq_dispose_mapping(adapter->tx_scrq[j]->irq);
 	}
 	release_sub_crqs(adapter);
 	return rc;
@@ -3560,12 +3560,10 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			dev_err(dev, "Error %ld in VERSION_EXCHG_RSP\n", rc);
 			break;
 		}
-		dev_info(dev, "Partner protocol version is %d\n",
-			 crq->version_exchange_rsp.version);
-		if (be16_to_cpu(crq->version_exchange_rsp.version) <
-		    ibmvnic_version)
-			ibmvnic_version =
+		ibmvnic_version =
 			    be16_to_cpu(crq->version_exchange_rsp.version);
+		dev_info(dev, "Partner protocol version is %d\n",
+			 ibmvnic_version);
 		send_cap_queries(adapter);
 		break;
 	case QUERY_CAPABILITY_RSP:
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 3dd4aeb2706d..8cc0e4873815 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -567,8 +567,13 @@ void e1000_reinit_locked(struct e1000_adapter *adapter)
 	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->flags))
 		msleep(1);
-	e1000_down(adapter);
-	e1000_up(adapter);
+
+	/* only run the task if not already down */
+	if (!test_bit(__E1000_DOWN, &adapter->flags)) {
+		e1000_down(adapter);
+		e1000_up(adapter);
+	}
+
 	clear_bit(__E1000_RESETTING, &adapter->flags);
 }
 
@@ -1458,10 +1463,15 @@ int e1000_close(struct net_device *netdev)
 	struct e1000_hw *hw = &adapter->hw;
 	int count = E1000_CHECK_RESET_COUNT;
 
-	while (test_bit(__E1000_RESETTING, &adapter->flags) && count--)
+	while (test_and_set_bit(__E1000_RESETTING, &adapter->flags) && count--)
 		usleep_range(10000, 20000);
 
-	WARN_ON(test_bit(__E1000_RESETTING, &adapter->flags));
+	WARN_ON(count < 0);
+
+	/* signal that we're down so that the reset task will no longer run */
+	set_bit(__E1000_DOWN, &adapter->flags);
+	clear_bit(__E1000_RESETTING, &adapter->flags);
+
 	e1000_down(adapter);
 	e1000_power_down_phy(adapter);
 	e1000_free_irq(adapter);
@@ -3169,8 +3179,9 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 		hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
 		if (skb->data_len && hdr_len == len) {
 			switch (hw->mac_type) {
+			case e1000_82544: {
 				unsigned int pull_size;
-			case e1000_82544:
+
 				/* Make sure we have room to chop off 4 bytes,
 				 * and that the end alignment will work out to
 				 * this hardware's requirements
@@ -3191,6 +3202,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 				}
 				len = skb_headlen(skb);
 				break;
+			}
 			default:
 				/* do nothing */
 				break;
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 98e68888abb1..e0ef6007c275 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -596,7 +596,6 @@ static inline u32 __er32(struct e1000_hw *hw, unsigned long reg)
 
 #define er32(reg)	__er32(hw, E1000_##reg)
 
-s32 __ew32_prepare(struct e1000_hw *hw);
 void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val);
 
 #define ew32(reg, val)	__ew32(hw, E1000_##reg, (val))
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 1ad345796e80..fff55f0bed30 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -137,14 +137,12 @@ static const struct e1000_reg_info e1000_reg_info_tbl[] = {
  * has bit 24 set while ME is accessing MAC CSR registers, wait if it is set
  * and try again a number of times.
  **/
-s32 __ew32_prepare(struct e1000_hw *hw)
+static void __ew32_prepare(struct e1000_hw *hw)
 {
 	s32 i = E1000_ICH_FWSM_PCIM2PCI_COUNT;
 
 	while ((er32(FWSM) & E1000_ICH_FWSM_PCIM2PCI) && --i)
 		udelay(50);
-
-	return i;
 }
 
 void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val)
@@ -625,11 +623,11 @@ static void e1000e_update_rdt_wa(struct e1000_ring *rx_ring, unsigned int i)
 {
 	struct e1000_adapter *adapter = rx_ring->adapter;
 	struct e1000_hw *hw = &adapter->hw;
-	s32 ret_val = __ew32_prepare(hw);
 
+	__ew32_prepare(hw);
 	writel(i, rx_ring->tail);
 
-	if (unlikely(!ret_val && (i != readl(rx_ring->tail)))) {
+	if (unlikely(i != readl(rx_ring->tail))) {
 		u32 rctl = er32(RCTL);
 
 		ew32(RCTL, rctl & ~E1000_RCTL_EN);
@@ -642,11 +640,11 @@ static void e1000e_update_tdt_wa(struct e1000_ring *tx_ring, unsigned int i)
 {
 	struct e1000_adapter *adapter = tx_ring->adapter;
 	struct e1000_hw *hw = &adapter->hw;
-	s32 ret_val = __ew32_prepare(hw);
 
+	__ew32_prepare(hw);
 	writel(i, tx_ring->tail);
 
-	if (unlikely(!ret_val && (i != readl(tx_ring->tail)))) {
+	if (unlikely(i != readl(tx_ring->tail))) {
 		u32 tctl = er32(TCTL);
 
 		ew32(TCTL, tctl & ~E1000_TCTL_EN);
@@ -5271,6 +5269,10 @@ static void e1000_watchdog_task(struct work_struct *work)
 					/* oops */
 					break;
 				}
+				if (hw->mac.type == e1000_pch_spt) {
+					netdev->features &= ~NETIF_F_TSO;
+					netdev->features &= ~NETIF_F_TSO6;
+				}
 			}
 
 			/* enable transmits in the hardware, need to do this
@@ -6326,11 +6328,17 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
-	u32 ctrl, ctrl_ext, rctl, status;
-	/* Runtime suspend should only enable wakeup for link changes */
-	u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
+	u32 ctrl, ctrl_ext, rctl, status, wufc;
 	int retval = 0;
 
+	/* Runtime suspend should only enable wakeup for link changes */
+	if (runtime)
+		wufc = E1000_WUFC_LNKC;
+	else if (device_may_wakeup(&pdev->dev))
+		wufc = adapter->wol;
+	else
+		wufc = 0;
+
 	status = er32(STATUS);
 	if (status & E1000_STATUS_LU)
 		wufc &= ~E1000_WUFC_LNKC;
@@ -6387,7 +6395,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 	if (adapter->hw.phy.type == e1000_phy_igp_3) {
 		e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw);
 	} else if (hw->mac.type >= e1000_pch_lpt) {
-		if (!(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC)))
+		if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC)))
 			/* ULP does not support wake from unicast, multicast
 			 * or broadcast.
 			 */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 5d5f422cbae5..f82da2b47d9a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -1175,7 +1175,7 @@ struct i40e_aqc_set_vsi_promiscuous_modes {
 #define I40E_AQC_SET_VSI_PROMISC_BROADCAST	0x04
 #define I40E_AQC_SET_VSI_DEFAULT		0x08
 #define I40E_AQC_SET_VSI_PROMISC_VLAN		0x10
-#define I40E_AQC_SET_VSI_PROMISC_TX		0x8000
+#define I40E_AQC_SET_VSI_PROMISC_RX_ONLY	0x8000
 	__le16	seid;
 #define I40E_AQC_VSI_PROM_CMD_SEID_MASK		0x3FF
 	__le16	vlan_tag;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 111426ba5fbc..3fd2dfaf2bd5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1915,6 +1915,21 @@ i40e_status i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags,
 }
 
 /**
+ * i40e_is_aq_api_ver_ge
+ * @aq: pointer to AdminQ info containing HW API version to compare
+ * @maj: API major value
+ * @min: API minor value
+ *
+ * Assert whether current HW API version is greater/equal than provided.
+ **/
+static bool i40e_is_aq_api_ver_ge(struct i40e_adminq_info *aq, u16 maj,
+				  u16 min)
+{
+	return (aq->api_maj_ver > maj ||
+		(aq->api_maj_ver == maj && aq->api_min_ver >= min));
+}
+
+/**
  * i40e_aq_add_vsi
  * @hw: pointer to the hw struct
  * @vsi_ctx: pointer to a vsi context struct
@@ -2039,18 +2054,16 @@ i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw,
 
 	if (set) {
 		flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
-		if (rx_only_promisc &&
-		    (((hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver >= 5)) ||
-		     (hw->aq.api_maj_ver > 1)))
-			flags |= I40E_AQC_SET_VSI_PROMISC_TX;
+		if (rx_only_promisc && i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+			flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY;
 	}
 
 	cmd->promiscuous_flags = cpu_to_le16(flags);
 
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST);
-	if (((hw->aq.api_maj_ver >= 1) && (hw->aq.api_min_ver >= 5)) ||
-	    (hw->aq.api_maj_ver > 1))
-		cmd->valid_flags |= cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_TX);
+	if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+		cmd->valid_flags |=
+			cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY);
 
 	cmd->seid = cpu_to_le16(seid);
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -2147,11 +2160,17 @@ enum i40e_status_code i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw,
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_vsi_promiscuous_modes);
 
-	if (enable)
+	if (enable) {
 		flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
+		if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+			flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY;
+	}
 
 	cmd->promiscuous_flags = cpu_to_le16(flags);
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST);
+	if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5))
+		cmd->valid_flags |=
+			cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY);
 	cmd->seid = cpu_to_le16(seid);
 	cmd->vlan_tag = cpu_to_le16(vid | I40E_AQC_SET_VSI_VLAN_VALID);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index aa2b446d6ad0..f4475cbf8ce8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11822,6 +11822,9 @@ static void i40e_remove(struct pci_dev *pdev)
 	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0);
 	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
 
+	while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+		usleep_range(1000, 2000);
+
 	/* no more scheduling of any task */
 	set_bit(__I40E_SUSPENDED, pf->state);
 	set_bit(__I40E_DOWN, pf->state);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 82028ce355fb..ff2be34bff39 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -163,7 +163,8 @@ static int igb_get_link_ksettings(struct net_device *netdev,
 	u32 speed;
 	u32 supported, advertising;
 
-	status = rd32(E1000_STATUS);
+	status = pm_runtime_suspended(&adapter->pdev->dev) ?
+		 0 : rd32(E1000_STATUS);
 	if (hw->phy.media_type == e1000_media_type_copper) {
 
 		supported = (SUPPORTED_10baseT_Half |
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 9c7e75b3b6c7..50fa0401c701 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -5487,9 +5487,18 @@ static void igb_reset_task(struct work_struct *work)
 	struct igb_adapter *adapter;
 	adapter = container_of(work, struct igb_adapter, reset_task);
 
+	rtnl_lock();
+	/* If we're already down or resetting, just bail */
+	if (test_bit(__IGB_DOWN, &adapter->state) ||
+	    test_bit(__IGB_RESETTING, &adapter->state)) {
+		rtnl_unlock();
+		return;
+	}
+
 	igb_dump(adapter);
 	netdev_err(adapter->netdev, "Reset adapter\n");
 	igb_reinit_locked(adapter);
+	rtnl_unlock();
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 815284fe9324..6b5662674c75 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -2267,7 +2267,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw)
 	}
 
 	/* Configure pause time (2 TCs per register) */
-	reg = hw->fc.pause_time * 0x00010001;
+	reg = hw->fc.pause_time * 0x00010001U;
 	for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++)
 		IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index f1bfae0c41d0..3cf8b3ea43b0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -917,7 +917,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 			ring->queue_index = txr_idx;
 
 		/* assign ring to adapter */
-		adapter->tx_ring[txr_idx] = ring;
+		WRITE_ONCE(adapter->tx_ring[txr_idx], ring);
 
 		/* update count and index */
 		txr_count--;
@@ -944,7 +944,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 		set_ring_xdp(ring);
 
 		/* assign ring to adapter */
-		adapter->xdp_ring[xdp_idx] = ring;
+		WRITE_ONCE(adapter->xdp_ring[xdp_idx], ring);
 
 		/* update count and index */
 		xdp_count--;
@@ -991,7 +991,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 			ring->queue_index = rxr_idx;
 
 		/* assign ring to adapter */
-		adapter->rx_ring[rxr_idx] = ring;
+		WRITE_ONCE(adapter->rx_ring[rxr_idx], ring);
 
 		/* update count and index */
 		rxr_count--;
@@ -1020,13 +1020,13 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx)
 
 	ixgbe_for_each_ring(ring, q_vector->tx) {
 		if (ring_is_xdp(ring))
-			adapter->xdp_ring[ring->queue_index] = NULL;
+			WRITE_ONCE(adapter->xdp_ring[ring->queue_index], NULL);
 		else
-			adapter->tx_ring[ring->queue_index] = NULL;
+			WRITE_ONCE(adapter->tx_ring[ring->queue_index], NULL);
 	}
 
 	ixgbe_for_each_ring(ring, q_vector->rx)
-		adapter->rx_ring[ring->queue_index] = NULL;
+		WRITE_ONCE(adapter->rx_ring[ring->queue_index], NULL);
 
 	adapter->q_vector[v_idx] = NULL;
 	napi_hash_del(&q_vector->napi);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ba184287e11f..9c3fa0b55551 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2274,7 +2274,8 @@ static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring,
 	rx_buffer->page_offset ^= truesize;
 #else
 	unsigned int truesize = ring_uses_build_skb(rx_ring) ?
-				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) :
+				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) +
+				SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
 				SKB_DATA_ALIGN(size);
 
 	rx_buffer->page_offset += truesize;
@@ -6841,7 +6842,10 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	}
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
-		struct ixgbe_ring *rx_ring = adapter->rx_ring[i];
+		struct ixgbe_ring *rx_ring = READ_ONCE(adapter->rx_ring[i]);
+
+		if (!rx_ring)
+			continue;
 		non_eop_descs += rx_ring->rx_stats.non_eop_descs;
 		alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed;
 		alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed;
@@ -6860,15 +6864,20 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	packets = 0;
 	/* gather some stats to the adapter struct that are per queue */
 	for (i = 0; i < adapter->num_tx_queues; i++) {
-		struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
+		struct ixgbe_ring *tx_ring = READ_ONCE(adapter->tx_ring[i]);
+
+		if (!tx_ring)
+			continue;
 		restart_queue += tx_ring->tx_stats.restart_queue;
 		tx_busy += tx_ring->tx_stats.tx_busy;
 		bytes += tx_ring->stats.bytes;
 		packets += tx_ring->stats.packets;
 	}
 	for (i = 0; i < adapter->num_xdp_queues; i++) {
-		struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i];
+		struct ixgbe_ring *xdp_ring = READ_ONCE(adapter->xdp_ring[i]);
 
+		if (!xdp_ring)
+			continue;
 		restart_queue += xdp_ring->tx_stats.restart_queue;
 		tx_busy += xdp_ring->tx_stats.tx_busy;
 		bytes += xdp_ring->stats.bytes;
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index b6ff143c9cff..024688c90aa9 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -319,15 +319,25 @@ static int orion_mdio_probe(struct platform_device *pdev)
 
 	init_waitqueue_head(&dev->smi_busy_wait);
 
-	for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
-		dev->clk[i] = of_clk_get(pdev->dev.of_node, i);
-		if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) {
+	if (pdev->dev.of_node) {
+		for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
+			dev->clk[i] = of_clk_get(pdev->dev.of_node, i);
+			if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) {
+				ret = -EPROBE_DEFER;
+				goto out_clk;
+			}
+			if (IS_ERR(dev->clk[i]))
+				break;
+			clk_prepare_enable(dev->clk[i]);
+		}
+	} else {
+		dev->clk[0] = clk_get(&pdev->dev, NULL);
+		if (PTR_ERR(dev->clk[0]) == -EPROBE_DEFER) {
 			ret = -EPROBE_DEFER;
 			goto out_clk;
 		}
-		if (IS_ERR(dev->clk[i]))
-			break;
-		clk_prepare_enable(dev->clk[i]);
+		if (!IS_ERR(dev->clk[0]))
+			clk_prepare_enable(dev->clk[0]);
 	}
 
 	dev->err_interrupt = platform_get_irq(pdev, 0);
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 5046efdad539..34ae4bf6e716 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -215,7 +215,7 @@ io_error:
 
 static inline u16 gm_phy_read(struct sky2_hw *hw, unsigned port, u16 reg)
 {
-	u16 v;
+	u16 v = 0;
 	__gm_phy_read(hw, port, reg, &v);
 	return v;
 }
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 9ba699cbdbc5..a52909db67f6 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2452,6 +2452,8 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	eth->netdev[id]->irq = eth->irq[0];
 	eth->netdev[id]->dev.of_node = np;
 
+	eth->netdev[id]->max_mtu = MTK_MAX_RX_LENGTH - MTK_RX_ETH_HLEN;
+
 	return 0;
 
 free_netdev:
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 7440c769b30f..8aecc4f4f123 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -2715,7 +2715,7 @@ void mlx4_opreq_action(struct work_struct *work)
 		if (err) {
 			mlx4_err(dev, "Failed to retrieve required operation: %d\n",
 				 err);
-			return;
+			goto out;
 		}
 		MLX4_GET(modifier, outbox, GET_OP_REQ_MODIFIER_OFFSET);
 		MLX4_GET(token, outbox, GET_OP_REQ_TOKEN_OFFSET);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index cf9011bb6e0f..c6660b61e836 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -4190,12 +4190,14 @@ end:
 static void mlx4_shutdown(struct pci_dev *pdev)
 {
 	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
+	struct mlx4_dev *dev = persist->dev;
 
 	mlx4_info(persist->dev, "mlx4_shutdown was called\n");
 	mutex_lock(&persist->interface_state_mutex);
 	if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
 		mlx4_unload_one(pdev);
 	mutex_unlock(&persist->interface_state_mutex);
+	mlx4_pci_disable_device(dev);
 }
 
 static const struct pci_error_handlers mlx4_err_handler = {
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 20043f82c1d8..7c212d661864 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -114,7 +114,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order)
 		goto err_out;
 
 	for (i = 0; i <= buddy->max_order; ++i) {
-		s = BITS_TO_LONGS(1 << (buddy->max_order - i));
+		s = BITS_TO_LONGS(1UL << (buddy->max_order - i));
 		buddy->bits[i] = kvmalloc_array(s, sizeof(long), GFP_KERNEL | __GFP_ZERO);
 		if (!buddy->bits[i])
 			goto err_out_free;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 950ea980808b..6ae9a1987371 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -804,6 +804,7 @@ static void cmd_work_handler(struct work_struct *work)
 	int alloc_ret;
 	int cmd_mode;
 
+	complete(&ent->handling);
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
 	if (!ent->page_queue) {
@@ -922,6 +923,11 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int err;
 
+	if (!wait_for_completion_timeout(&ent->handling, timeout) &&
+	    cancel_work_sync(&ent->work)) {
+		ent->ret = -ECANCELED;
+		goto out_err;
+	}
 	if (cmd->mode == CMD_MODE_POLLING || ent->polling) {
 		wait_for_completion(&ent->done);
 	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
@@ -929,12 +935,17 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 	}
 
+out_err:
 	err = ent->ret;
 
 	if (err == -ETIMEDOUT) {
 		mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 			       mlx5_command_str(msg_to_opcode(ent->in)),
 			       msg_to_opcode(ent->in));
+	} else if (err == -ECANCELED) {
+		mlx5_core_warn(dev, "%s(0x%x) canceled on out of queue timeout.\n",
+			       mlx5_command_str(msg_to_opcode(ent->in)),
+			       msg_to_opcode(ent->in));
 	}
 	mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n",
 		      err, deliv_status_to_str(ent->status), ent->status);
@@ -970,6 +981,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	ent->token = token;
 	ent->polling = force_polling;
 
+	init_completion(&ent->handling);
 	if (!callback)
 		init_completion(&ent->done);
 
@@ -989,6 +1001,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	err = wait_func(dev, ent);
 	if (err == -ETIMEDOUT)
 		goto out;
+	if (err == -ECANCELED)
+		goto out_free;
 
 	ds = ent->ts2 - ent->ts1;
 	op = MLX5_GET(mbox_in, in->first.data, opcode);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index e69674d38f16..a3107d133b40 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -180,7 +180,7 @@ int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 
-	if (esw->mode == SRIOV_NONE)
+	if (esw->mode != SRIOV_OFFLOADS)
 		return -EOPNOTSUPP;
 
 	switch (attr->id) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index d560047c0bf9..abdb444c6ed0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -496,8 +496,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 {
 	struct mlx5e_tx_wqe_info *wi;
+	u32 nbytes = 0;
+	u16 ci, npkts = 0;
 	struct sk_buff *skb;
-	u16 ci;
 	int i;
 
 	while (sq->cc != sq->pc) {
@@ -518,8 +519,11 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 		}
 
 		dev_kfree_skb_any(skb);
+		npkts++;
+		nbytes += wi->num_bytes;
 		sq->cc += wi->num_wqebbs;
 	}
+	netdev_tx_completed_queue(sq->txq, npkts, nbytes);
 }
 
 #ifdef CONFIG_MLX5_CORE_IPOIB
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index fad26046e159..dc12ab33afff 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -619,7 +619,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 	err = mlxsw_core_trap_register(mlxsw_core, &mlxsw_emad_rx_listener,
 				       mlxsw_core);
 	if (err)
-		return err;
+		goto err_trap_register;
 
 	err = mlxsw_core->driver->basic_trap_groups_set(mlxsw_core);
 	if (err)
@@ -631,6 +631,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 err_emad_trap_set:
 	mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_emad_rx_listener,
 				   mlxsw_core);
+err_trap_register:
 	destroy_workqueue(mlxsw_core->emad_wq);
 	return err;
 }
@@ -1360,7 +1361,7 @@ static int mlxsw_core_reg_access_emad(struct mlxsw_core *mlxsw_core,
 	err = mlxsw_emad_reg_access(mlxsw_core, reg, payload, type, trans,
 				    bulk_list, cb, cb_priv, tid);
 	if (err) {
-		kfree(trans);
+		kfree_rcu(trans, rcu);
 		return err;
 	}
 	return 0;
@@ -1573,11 +1574,13 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 			break;
 		}
 	}
-	rcu_read_unlock();
-	if (!found)
+	if (!found) {
+		rcu_read_unlock();
 		goto drop;
+	}
 
 	rxl->func(skb, local_port, rxl_item->priv);
+	rcu_read_unlock();
 	return;
 
 drop:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 05a2006a20b9..d9cd86c67556 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4932,7 +4932,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 		return NOTIFY_DONE;
 
 	fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
-	if (WARN_ON(!fib_work))
+	if (!fib_work)
 		return NOTIFY_BAD;
 
 	router = container_of(nb, struct mlxsw_sp_router, fib_nb);
diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c
index f831238d9793..84b6ad76f5bc 100644
--- a/drivers/net/ethernet/microchip/encx24j600.c
+++ b/drivers/net/ethernet/microchip/encx24j600.c
@@ -1075,7 +1075,7 @@ static int encx24j600_spi_probe(struct spi_device *spi)
 	if (unlikely(ret)) {
 		netif_err(priv, probe, ndev, "Error %d initializing card encx24j600 card\n",
 			  ret);
-		goto out_free;
+		goto out_stop;
 	}
 
 	eidled = encx24j600_read_reg(priv, EIDLED);
@@ -1093,6 +1093,8 @@ static int encx24j600_spi_probe(struct spi_device *spi)
 
 out_unregister:
 	unregister_netdev(priv->ndev);
+out_stop:
+	kthread_stop(priv->kworker_task);
 out_free:
 	free_netdev(ndev);
 
@@ -1105,6 +1107,7 @@ static int encx24j600_spi_remove(struct spi_device *spi)
 	struct encx24j600_priv *priv = dev_get_drvdata(&spi->dev);
 
 	unregister_netdev(priv->ndev);
+	kthread_stop(priv->kworker_task);
 
 	free_netdev(priv->ndev);
 
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 41d30f55c946..6bd6c261f2ba 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -845,7 +845,8 @@ static int lpc_mii_init(struct netdata_local *pldat)
 	if (mdiobus_register(pldat->mii_bus))
 		goto err_out_unregister_bus;
 
-	if (lpc_mii_probe(pldat->ndev) != 0)
+	err = lpc_mii_probe(pldat->ndev);
+	if (err)
 		goto err_out_unregister_bus;
 
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 27ba476f761d..4fc3468f6f38 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -396,7 +396,7 @@ static void qed_cxt_qm_iids(struct qed_hwfn *p_hwfn,
 		vf_tids += segs[NUM_TASK_PF_SEGMENTS].count;
 	}
 
-	iids->vf_cids += vf_cids * p_mngr->vf_count;
+	iids->vf_cids = vf_cids;
 	iids->tids += vf_tids * p_mngr->vf_count;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_ILT,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index c5d9f290ec4c..f8d1d02a3cd4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -1015,7 +1015,8 @@ static int qed_int_attentions(struct qed_hwfn *p_hwfn)
 			index, attn_bits, attn_acks, asserted_bits,
 			deasserted_bits, p_sb_attn_sw->known_attn);
 	} else if (asserted_bits == 0x100) {
-		DP_INFO(p_hwfn, "MFW indication via attention\n");
+		DP_VERBOSE(p_hwfn, NETIF_MSG_INTR,
+			   "MFW indication via attention\n");
 	} else {
 		DP_VERBOSE(p_hwfn, NETIF_MSG_INTR,
 			   "MFW indication [deassertion]\n");
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 65a53d409e77..bc9eec1bcbf1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -96,6 +96,7 @@ static int qed_sp_vf_start(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf)
 		p_ramrod->personality = PERSONALITY_ETH;
 		break;
 	case QED_PCI_ETH_ROCE:
+	case QED_PCI_ETH_IWARP:
 		p_ramrod->personality = PERSONALITY_RDMA_AND_ETH;
 		break;
 	default:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index a2a9921b467b..693f2a039383 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -81,12 +81,17 @@ static void qed_vf_pf_req_end(struct qed_hwfn *p_hwfn, int req_status)
 	mutex_unlock(&(p_hwfn->vf_iov_info->mutex));
 }
 
+#define QED_VF_CHANNEL_USLEEP_ITERATIONS	90
+#define QED_VF_CHANNEL_USLEEP_DELAY		100
+#define QED_VF_CHANNEL_MSLEEP_ITERATIONS	10
+#define QED_VF_CHANNEL_MSLEEP_DELAY		25
+
 static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
 {
 	union vfpf_tlvs *p_req = p_hwfn->vf_iov_info->vf2pf_request;
 	struct ustorm_trigger_vf_zone trigger;
 	struct ustorm_vf_zone *zone_data;
-	int rc = 0, time = 100;
+	int iter, rc = 0;
 
 	zone_data = (struct ustorm_vf_zone *)PXP_VF_BAR0_START_USDM_ZONE_B;
 
@@ -126,11 +131,19 @@ static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
 	REG_WR(p_hwfn, (uintptr_t)&zone_data->trigger, *((u32 *)&trigger));
 
 	/* When PF would be done with the response, it would write back to the
-	 * `done' address. Poll until then.
+	 * `done' address from a coherent DMA zone. Poll until then.
 	 */
-	while ((!*done) && time) {
-		msleep(25);
-		time--;
+
+	iter = QED_VF_CHANNEL_USLEEP_ITERATIONS;
+	while (!*done && iter--) {
+		udelay(QED_VF_CHANNEL_USLEEP_DELAY);
+		dma_rmb();
+	}
+
+	iter = QED_VF_CHANNEL_MSLEEP_ITERATIONS;
+	while (!*done && iter--) {
+		msleep(QED_VF_CHANNEL_MSLEEP_DELAY);
+		dma_rmb();
 	}
 
 	if (!*done) {
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index a80531b5aecc..c132b08cefde 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -528,12 +528,14 @@ void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq);
 #define RX_RING_SIZE		((u16)BIT(RX_RING_SIZE_POW))
 #define NUM_RX_BDS_MAX		(RX_RING_SIZE - 1)
 #define NUM_RX_BDS_MIN		128
+#define NUM_RX_BDS_KDUMP_MIN	63
 #define NUM_RX_BDS_DEF		((u16)BIT(10) - 1)
 
 #define TX_RING_SIZE_POW	13
 #define TX_RING_SIZE		((u16)BIT(TX_RING_SIZE_POW))
 #define NUM_TX_BDS_MAX		(TX_RING_SIZE - 1)
 #define NUM_TX_BDS_MIN		128
+#define NUM_TX_BDS_KDUMP_MIN	63
 #define NUM_TX_BDS_DEF		NUM_TX_BDS_MAX
 
 #define QEDE_MIN_PKT_LEN		64
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index dab202f343c6..8bb734486bf3 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -29,6 +29,7 @@
  * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
+#include <linux/crash_dump.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/version.h>
@@ -624,8 +625,14 @@ static struct qede_dev *qede_alloc_etherdev(struct qed_dev *cdev,
 	edev->dp_module = dp_module;
 	edev->dp_level = dp_level;
 	edev->ops = qed_ops;
-	edev->q_num_rx_buffers = NUM_RX_BDS_DEF;
-	edev->q_num_tx_buffers = NUM_TX_BDS_DEF;
+
+	if (is_kdump_kernel()) {
+		edev->q_num_rx_buffers = NUM_RX_BDS_KDUMP_MIN;
+		edev->q_num_tx_buffers = NUM_TX_BDS_KDUMP_MIN;
+	} else {
+		edev->q_num_rx_buffers = NUM_RX_BDS_DEF;
+		edev->q_num_tx_buffers = NUM_TX_BDS_DEF;
+	}
 
 	DP_INFO(edev, "Allocated netdev with %d tx queues and %d rx queues\n",
 		info->num_queues, info->num_queues);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 1fc84d8f891b..aae81226a0a4 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -3650,7 +3650,7 @@ int qlcnic_83xx_interrupt_test(struct net_device *netdev)
 	ahw->diag_cnt = 0;
 	ret = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_INTRPT_TEST);
 	if (ret)
-		goto fail_diag_irq;
+		goto fail_mbx_args;
 
 	if (adapter->flags & QLCNIC_MSIX_ENABLED)
 		intrpt_id = ahw->intr_tbl[0].id;
@@ -3680,6 +3680,8 @@ int qlcnic_83xx_interrupt_test(struct net_device *netdev)
 
 done:
 	qlcnic_free_mbx_args(&cmd);
+
+fail_mbx_args:
 	qlcnic_83xx_diag_free_res(netdev, drv_sds_rings);
 
 fail_diag_irq:
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 759543512117..5ab83751a471 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -493,13 +493,24 @@ static int emac_clks_phase1_init(struct platform_device *pdev,
 
 	ret = clk_prepare_enable(adpt->clk[EMAC_CLK_CFG_AHB]);
 	if (ret)
-		return ret;
+		goto disable_clk_axi;
 
 	ret = clk_set_rate(adpt->clk[EMAC_CLK_HIGH_SPEED], 19200000);
 	if (ret)
-		return ret;
+		goto disable_clk_cfg_ahb;
+
+	ret = clk_prepare_enable(adpt->clk[EMAC_CLK_HIGH_SPEED]);
+	if (ret)
+		goto disable_clk_cfg_ahb;
 
-	return clk_prepare_enable(adpt->clk[EMAC_CLK_HIGH_SPEED]);
+	return 0;
+
+disable_clk_cfg_ahb:
+	clk_disable_unprepare(adpt->clk[EMAC_CLK_CFG_AHB]);
+disable_clk_axi:
+	clk_disable_unprepare(adpt->clk[EMAC_CLK_AXI]);
+
+	return ret;
 }
 
 /* Enable clocks; needs emac_clks_phase1_init to be called before */
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index d73617cc3b15..9f4d93a16b7e 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1482,6 +1482,7 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 	struct ravb_private *priv = container_of(work, struct ravb_private,
 						 work);
 	struct net_device *ndev = priv->ndev;
+	int error;
 
 	netif_tx_stop_all_queues(ndev);
 
@@ -1490,15 +1491,36 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 		ravb_ptp_stop(ndev);
 
 	/* Wait for DMA stopping */
-	ravb_stop_dma(ndev);
+	if (ravb_stop_dma(ndev)) {
+		/* If ravb_stop_dma() fails, the hardware is still operating
+		 * for TX and/or RX. So, this should not call the following
+		 * functions because ravb_dmac_init() is possible to fail too.
+		 * Also, this should not retry ravb_stop_dma() again and again
+		 * here because it's possible to wait forever. So, this just
+		 * re-enables the TX and RX and skip the following
+		 * re-initialization procedure.
+		 */
+		ravb_rcv_snd_enable(ndev);
+		goto out;
+	}
 
 	ravb_ring_free(ndev, RAVB_BE);
 	ravb_ring_free(ndev, RAVB_NC);
 
 	/* Device init */
-	ravb_dmac_init(ndev);
+	error = ravb_dmac_init(ndev);
+	if (error) {
+		/* If ravb_dmac_init() fails, descriptors are freed. So, this
+		 * should return here to avoid re-enabling the TX and RX in
+		 * ravb_emac_init().
+		 */
+		netdev_err(ndev, "%s: ravb_dmac_init() failed, error %d\n",
+			   __func__, error);
+		return;
+	}
 	ravb_emac_init(ndev);
 
+out:
 	/* Initialise PTP Clock driver */
 	if (priv->chip_id == RCAR_GEN2)
 		ravb_ptp_init(ndev, priv->pdev);
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 056cb6093630..8ad05e500829 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -651,10 +651,10 @@ static int rocker_dma_rings_init(struct rocker *rocker)
 err_dma_event_ring_bufs_alloc:
 	rocker_dma_ring_destroy(rocker, &rocker->event_ring);
 err_dma_event_ring_create:
+	rocker_dma_cmd_ring_waits_free(rocker);
+err_dma_cmd_ring_waits_alloc:
 	rocker_dma_ring_bufs_free(rocker, &rocker->cmd_ring,
 				  PCI_DMA_BIDIRECTIONAL);
-err_dma_cmd_ring_waits_alloc:
-	rocker_dma_cmd_ring_waits_free(rocker);
 err_dma_cmd_ring_bufs_alloc:
 	rocker_dma_ring_destroy(rocker, &rocker->cmd_ring);
 	return err;
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 96ac0d3af6f5..f570a37c68c2 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2294,7 +2294,7 @@ static int smc_drv_probe(struct platform_device *pdev)
 		ret = try_toggle_control_gpio(&pdev->dev, &lp->power_gpio,
 					      "power", 0, 0, 100);
 		if (ret)
-			return ret;
+			goto out_free_netdev;
 
 		/*
 		 * Optional reset GPIO configured? Minimum 100 ns reset needed
@@ -2303,7 +2303,7 @@ static int smc_drv_probe(struct platform_device *pdev)
 		ret = try_toggle_control_gpio(&pdev->dev, &lp->reset_gpio,
 					      "reset", 0, 0, 100);
 		if (ret)
-			return ret;
+			goto out_free_netdev;
 
 		/*
 		 * Need to wait for optional EEPROM to load, max 750 us according
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index ce4bfecc26c7..ae80a223975d 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -2515,20 +2515,20 @@ static int smsc911x_drv_probe(struct platform_device *pdev)
 
 	retval = smsc911x_init(dev);
 	if (retval < 0)
-		goto out_disable_resources;
+		goto out_init_fail;
 
 	netif_carrier_off(dev);
 
 	retval = smsc911x_mii_init(pdev, dev);
 	if (retval) {
 		SMSC_WARN(pdata, probe, "Error %i initialising mii", retval);
-		goto out_disable_resources;
+		goto out_init_fail;
 	}
 
 	retval = register_netdev(dev);
 	if (retval) {
 		SMSC_WARN(pdata, probe, "Error %i registering device", retval);
-		goto out_disable_resources;
+		goto out_init_fail;
 	} else {
 		SMSC_TRACE(pdata, probe,
 			   "Network interface: \"%s\"", dev->name);
@@ -2569,9 +2569,10 @@ static int smsc911x_drv_probe(struct platform_device *pdev)
 
 	return 0;
 
-out_disable_resources:
+out_init_fail:
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+out_disable_resources:
 	(void)smsc911x_disable_resources(pdev);
 out_enable_resources_fail:
 	smsc911x_free_resources(pdev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 11a4a81b0397..1924788d28da 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -330,6 +330,19 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 	/* Enable PTP clock */
 	regmap_read(gmac->nss_common, NSS_COMMON_CLK_GATE, &val);
 	val |= NSS_COMMON_CLK_GATE_PTP_EN(gmac->id);
+	switch (gmac->phy_mode) {
+	case PHY_INTERFACE_MODE_RGMII:
+		val |= NSS_COMMON_CLK_GATE_RGMII_RX_EN(gmac->id) |
+			NSS_COMMON_CLK_GATE_RGMII_TX_EN(gmac->id);
+		break;
+	case PHY_INTERFACE_MODE_SGMII:
+		val |= NSS_COMMON_CLK_GATE_GMII_RX_EN(gmac->id) |
+				NSS_COMMON_CLK_GATE_GMII_TX_EN(gmac->id);
+		break;
+	default:
+		/* We don't get here; the switch above will have errored out */
+		unreachable();
+	}
 	regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val);
 
 	if (gmac->phy_mode == PHY_INTERFACE_MODE_SGMII) {
@@ -349,6 +362,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 	plat_dat->has_gmac = true;
 	plat_dat->bsp_priv = gmac;
 	plat_dat->fix_mac_speed = ipq806x_gmac_fix_mac_speed;
+	plat_dat->multicast_filter_bins = 0;
 
 	err = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (err)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index f76d4a7281af..f07d9d3456a4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -176,6 +176,9 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
 		value = GMAC_FRAME_FILTER_PR;
 	} else if (dev->flags & IFF_ALLMULTI) {
 		value = GMAC_FRAME_FILTER_PM;	/* pass all multi */
+	} else if (!netdev_mc_empty(dev) && (mcbitslog2 == 0)) {
+		/* Fall back to all multicast if we've no filter */
+		value = GMAC_FRAME_FILTER_PM;
 	} else if (!netdev_mc_empty(dev)) {
 		struct netdev_hw_addr *ha;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 8c7109008185..5105e1f724fb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -677,23 +677,16 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev,
 	struct stmmac_priv *priv = netdev_priv(dev);
 	int ret;
 
-	if (!edata->eee_enabled) {
+	if (!priv->dma_cap.eee)
+		return -EOPNOTSUPP;
+
+	if (!edata->eee_enabled)
 		stmmac_disable_eee_mode(priv);
-	} else {
-		/* We are asking for enabling the EEE but it is safe
-		 * to verify all by invoking the eee_init function.
-		 * In case of failure it will return an error.
-		 */
-		edata->eee_enabled = stmmac_eee_init(priv);
-		if (!edata->eee_enabled)
-			return -EOPNOTSUPP;
-	}
 
 	ret = phy_ethtool_set_eee(dev->phydev, edata);
 	if (ret)
 		return ret;
 
-	priv->eee_enabled = edata->eee_enabled;
 	priv->tx_lpi_timer = edata->tx_lpi_timer;
 	return 0;
 }
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 382993c1561c..7e5c0f182770 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -4983,7 +4983,7 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 					  cas_cacheline_size)) {
 			dev_err(&pdev->dev, "Could not set PCI cache "
 			       "line size\n");
-			goto err_write_cacheline;
+			goto err_out_free_res;
 		}
 	}
 #endif
@@ -5158,7 +5158,6 @@ err_out_iounmap:
 err_out_free_res:
 	pci_release_regions(pdev);
 
-err_write_cacheline:
 	/* Try to restore it in case the error occurred after we
 	 * set it.
 	 */
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index da136b8843dd..a0fed9035f53 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -296,8 +296,8 @@ spider_net_free_chain(struct spider_net_card *card,
 		descr = descr->next;
 	} while (descr != chain->ring);
 
-	dma_free_coherent(&card->pdev->dev, chain->num_desc,
-	    chain->hwring, chain->dma_addr);
+	dma_free_coherent(&card->pdev->dev, chain->num_desc * sizeof(struct spider_net_hw_descr),
+			  chain->hwring, chain->dma_addr);
 }
 
 /**
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 6d3fa36b1616..f48006c22a8a 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -716,7 +716,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 				       struct net_device *dev,
 				       struct geneve_sock *gs4,
 				       struct flowi4 *fl4,
-				       const struct ip_tunnel_info *info)
+				       const struct ip_tunnel_info *info,
+				       __be16 dport, __be16 sport)
 {
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct geneve_dev *geneve = netdev_priv(dev);
@@ -732,6 +733,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 	fl4->flowi4_proto = IPPROTO_UDP;
 	fl4->daddr = info->key.u.ipv4.dst;
 	fl4->saddr = info->key.u.ipv4.src;
+	fl4->fl4_dport = dport;
+	fl4->fl4_sport = sport;
 
 	tos = info->key.tos;
 	if ((tos == 1) && !geneve->collect_md) {
@@ -766,7 +769,8 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 					   struct net_device *dev,
 					   struct geneve_sock *gs6,
 					   struct flowi6 *fl6,
-					   const struct ip_tunnel_info *info)
+					   const struct ip_tunnel_info *info,
+					   __be16 dport, __be16 sport)
 {
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct geneve_dev *geneve = netdev_priv(dev);
@@ -782,6 +786,9 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 	fl6->flowi6_proto = IPPROTO_UDP;
 	fl6->daddr = info->key.u.ipv6.dst;
 	fl6->saddr = info->key.u.ipv6.src;
+	fl6->fl6_dport = dport;
+	fl6->fl6_sport = sport;
+
 	prio = info->key.tos;
 	if ((prio == 1) && !geneve->collect_md) {
 		prio = ip_tunnel_get_dsfield(ip_hdr(skb), skb);
@@ -828,7 +835,9 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 df;
 	int err;
 
-	rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
+	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
+			      geneve->info.key.tp_dst, sport);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
@@ -839,7 +848,6 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		skb_dst_update_pmtu(skb, mtu);
 	}
 
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	if (geneve->collect_md) {
 		tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
@@ -874,7 +882,9 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
-	dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info);
+	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
+				geneve->info.key.tp_dst, sport);
 	if (IS_ERR(dst))
 		return PTR_ERR(dst);
 
@@ -885,7 +895,6 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		skb_dst_update_pmtu(skb, mtu);
 	}
 
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	if (geneve->collect_md) {
 		prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
@@ -915,9 +924,10 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (geneve->collect_md) {
 		info = skb_tunnel_info(skb);
 		if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
-			err = -EINVAL;
 			netdev_dbg(dev, "no tunnel metadata\n");
-			goto tx_error;
+			dev_kfree_skb(skb);
+			dev->stats.tx_dropped++;
+			return NETDEV_TX_OK;
 		}
 	} else {
 		info = &geneve->info;
@@ -934,7 +944,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (likely(!err))
 		return NETDEV_TX_OK;
-tx_error:
+
 	dev_kfree_skb(skb);
 
 	if (err == -ELOOP)
@@ -962,13 +972,18 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ip_tunnel_info *info = skb_tunnel_info(skb);
 	struct geneve_dev *geneve = netdev_priv(dev);
+	__be16 sport;
 
 	if (ip_tunnel_info_af(info) == AF_INET) {
 		struct rtable *rt;
 		struct flowi4 fl4;
+
 		struct geneve_sock *gs4 = rcu_dereference(geneve->sock4);
+		sport = udp_flow_src_port(geneve->net, skb,
+					  1, USHRT_MAX, true);
 
-		rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
+		rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
+				      geneve->info.key.tp_dst, sport);
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 
@@ -978,9 +993,13 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 	} else if (ip_tunnel_info_af(info) == AF_INET6) {
 		struct dst_entry *dst;
 		struct flowi6 fl6;
+
 		struct geneve_sock *gs6 = rcu_dereference(geneve->sock6);
+		sport = udp_flow_src_port(geneve->net, skb,
+					  1, USHRT_MAX, true);
 
-		dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info);
+		dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
+					geneve->info.key.tp_dst, sport);
 		if (IS_ERR(dst))
 			return PTR_ERR(dst);
 
@@ -991,8 +1010,7 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 		return -EINVAL;
 	}
 
-	info->key.tp_src = udp_flow_src_port(geneve->net, skb,
-					     1, USHRT_MAX, true);
+	info->key.tp_src = sport;
 	info->key.tp_dst = geneve->info.key.tp_dst;
 	return 0;
 }
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 090607e725a2..d3ccd6929579 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1187,6 +1187,7 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
 		goto nlmsg_failure;
 
 	if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) ||
+	    nla_put_u32(skb, GTPA_LINK, pctx->dev->ifindex) ||
 	    nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer_addr_ip4.s_addr) ||
 	    nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr))
 		goto nla_put_failure;
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 16a6e1193912..b74c735a423d 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -1162,6 +1162,7 @@ static int __init yam_init_driver(void)
 		err = register_netdev(dev);
 		if (err) {
 			printk(KERN_WARNING "yam: cannot register net device %s\n", dev->name);
+			free_netdev(dev);
 			goto error;
 		}
 		yam_devs[i] = dev;
diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c
index d7ba2b813eff..40ef4aeb0ef0 100644
--- a/drivers/net/hippi/rrunner.c
+++ b/drivers/net/hippi/rrunner.c
@@ -1250,7 +1250,7 @@ static int rr_open(struct net_device *dev)
 		rrpriv->info = NULL;
 	}
 	if (rrpriv->rx_ctrl) {
-		pci_free_consistent(pdev, sizeof(struct ring_ctrl),
+		pci_free_consistent(pdev, 256 * sizeof(struct ring_ctrl),
 				    rrpriv->rx_ctrl, rrpriv->rx_ctrl_dma);
 		rrpriv->rx_ctrl = NULL;
 	}
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 14451e14d99d..17a7ef679bab 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -365,7 +365,7 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	}
 	rcu_read_unlock();
 
-	while (unlikely(txq >= ndev->real_num_tx_queues))
+	while (txq >= ndev->real_num_tx_queues)
 		txq -= ndev->real_num_tx_queues;
 
 	return txq;
@@ -500,7 +500,7 @@ static int netvsc_vf_xmit(struct net_device *net, struct net_device *vf_netdev,
 	int rc;
 
 	skb->dev = vf_netdev;
-	skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping;
+	skb_record_rx_queue(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping);
 
 	rc = dev_queue_xmit(skb);
 	if (likely(rc == NET_XMIT_SUCCESS || rc == NET_XMIT_CN)) {
@@ -532,12 +532,13 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	u32 hash;
 	struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
 
-	/* if VF is present and up then redirect packets
-	 * already called with rcu_read_lock_bh
+	/* If VF is present and up then redirect packets to it.
+	 * Skip the VF if it is marked down or has no carrier.
+	 * If netpoll is in uses, then VF can not be used either.
 	 */
 	vf_netdev = rcu_dereference_bh(net_device_ctx->vf_netdev);
 	if (vf_netdev && netif_running(vf_netdev) &&
-	    !netpoll_tx_running(net))
+	    netif_carrier_ok(vf_netdev) && !netpoll_tx_running(net))
 		return netvsc_vf_xmit(net, vf_netdev, skb);
 
 	/* We will atmost need two pages to describe the rndis
diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c
index 46b42de13d76..3510eb26ccd5 100644
--- a/drivers/net/ieee802154/adf7242.c
+++ b/drivers/net/ieee802154/adf7242.c
@@ -834,7 +834,9 @@ static int adf7242_rx(struct adf7242_local *lp)
 	int ret;
 	u8 lqi, len_u8, *data;
 
-	adf7242_read_reg(lp, 0, &len_u8);
+	ret = adf7242_read_reg(lp, 0, &len_u8);
+	if (ret)
+		return ret;
 
 	len = len_u8;
 
diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index 3a58962babd4..368369469e32 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -2924,6 +2924,7 @@ static int ca8210_dev_com_init(struct ca8210_priv *priv)
 	);
 	if (!priv->irq_workqueue) {
 		dev_crit(&priv->spi->dev, "alloc of irq_workqueue failed!\n");
+		destroy_workqueue(priv->mlme_workqueue);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index cd32d6623f6a..11b7006142ce 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -187,12 +187,21 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	kfree(port);
 }
 
+#define IPVLAN_ALWAYS_ON_OFLOADS \
+	(NETIF_F_SG | NETIF_F_HW_CSUM | \
+	 NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL)
+
+#define IPVLAN_ALWAYS_ON \
+	(IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED)
+
 #define IPVLAN_FEATURES \
-	(NETIF_F_SG | NETIF_F_CSUM_MASK | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
+	(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
 	 NETIF_F_GSO | NETIF_F_TSO | NETIF_F_GSO_ROBUST | \
 	 NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \
 	 NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)
 
+	/* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */
+
 #define IPVLAN_STATE_MASK \
 	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
 
@@ -205,7 +214,9 @@ static int ipvlan_init(struct net_device *dev)
 	dev->state = (dev->state & ~IPVLAN_STATE_MASK) |
 		     (phy_dev->state & IPVLAN_STATE_MASK);
 	dev->features = phy_dev->features & IPVLAN_FEATURES;
-	dev->features |= NETIF_F_LLTX;
+	dev->features |= IPVLAN_ALWAYS_ON;
+	dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES;
+	dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS;
 	dev->gso_max_size = phy_dev->gso_max_size;
 	dev->gso_max_segs = phy_dev->gso_max_segs;
 	dev->hard_header_len = phy_dev->hard_header_len;
@@ -293,7 +304,14 @@ static netdev_features_t ipvlan_fix_features(struct net_device *dev,
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 
-	return features & (ipvlan->sfeatures | ~IPVLAN_FEATURES);
+	features |= NETIF_F_ALL_FOR_ALL;
+	features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES);
+	features = netdev_increment_features(ipvlan->phy_dev->features,
+					     features, features);
+	features |= IPVLAN_ALWAYS_ON;
+	features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON);
+
+	return features;
 }
 
 static void ipvlan_change_rx_flags(struct net_device *dev, int change)
@@ -743,10 +761,9 @@ static int ipvlan_device_event(struct notifier_block *unused,
 
 	case NETDEV_FEAT_CHANGE:
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
-			ipvlan->dev->features = dev->features & IPVLAN_FEATURES;
 			ipvlan->dev->gso_max_size = dev->gso_max_size;
 			ipvlan->dev->gso_max_segs = dev->gso_max_segs;
-			netdev_features_change(ipvlan->dev);
+			netdev_update_features(ipvlan->dev);
 		}
 		break;
 
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 4a92160394c0..834fa544d6d9 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1081,6 +1081,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 	struct macsec_rx_sa *rx_sa;
 	struct macsec_rxh_data *rxd;
 	struct macsec_dev *macsec;
+	unsigned int len;
 	sci_t sci;
 	u32 pn;
 	bool cbit;
@@ -1236,9 +1237,10 @@ deliver:
 	macsec_rxsc_put(rx_sc);
 
 	skb_orphan(skb);
+	len = skb->len;
 	ret = gro_cells_receive(&macsec->gro_cells, skb);
 	if (ret == NET_RX_SUCCESS)
-		count_rx(dev, skb->len);
+		count_rx(dev, len);
 	else
 		macsec->secy.netdev->stats.rx_dropped++;
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 3072fc902eca..b7f41c52766f 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -449,6 +449,10 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 	int ret;
 	rx_handler_result_t handle_res;
 
+	/* Packets from dev_loopback_xmit() do not have L2 header, bail out */
+	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
+		return RX_HANDLER_PASS;
+
 	port = macvlan_port_get_rcu(skb->dev);
 	if (is_multicast_ether_addr(eth->h_dest)) {
 		unsigned int hash;
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index cd931cf9dcc2..e08d82233834 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -146,6 +146,7 @@ config MDIO_THUNDER
 	depends on 64BIT
 	depends on PCI
 	select MDIO_CAVIUM
+	select MDIO_DEVRES
 	help
 	  This driver supports the MDIO interfaces found on Cavium
 	  ThunderX SoCs when the MDIO bus device appears as a PCI
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index c52c016676af..5752280fdb40 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1339,6 +1339,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V1;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
@@ -1346,6 +1347,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
@@ -1353,6 +1355,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
@@ -1360,6 +1363,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4 | PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c
index 52703bbd4d66..df75efa96a7d 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -237,6 +237,8 @@ static int unimac_mdio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!r)
+		return -EINVAL;
 
 	/* Just ioremap, as this MDIO block is usually integrated into an
 	 * Ethernet MAC controller register range
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 27f1f0b5b8f6..b51bca051c47 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1121,7 +1121,8 @@ void phy_detach(struct phy_device *phydev)
 
 	phy_led_triggers_unregister(phydev);
 
-	module_put(phydev->mdio.dev.driver->owner);
+	if (phydev->mdio.dev.driver)
+		module_put(phydev->mdio.dev.driver->owner);
 
 	/* If the device had no specific driver before (i.e. - it
 	 * was using the generic driver), we unbind the device
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index fa7121dcab67..202a0f415e1e 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -497,6 +497,9 @@ static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb)
 		goto out;
 
+	if (skb->pkt_type != PACKET_HOST)
+		goto abort;
+
 	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
 		goto abort;
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 396a8c6cb999..d36d0882874b 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -299,7 +299,7 @@ inst_rollback:
 	for (i--; i >= 0; i--)
 		__team_option_inst_del_option(team, dst_opts[i]);
 
-	i = option_count - 1;
+	i = option_count;
 alloc_rollback:
 	for (i--; i >= 0; i--)
 		kfree(dst_opts[i]);
@@ -2078,6 +2078,7 @@ static void team_setup_by_port(struct net_device *dev,
 	dev->header_ops	= port_dev->header_ops;
 	dev->type = port_dev->type;
 	dev->hard_header_len = port_dev->hard_header_len;
+	dev->needed_headroom = port_dev->needed_headroom;
 	dev->addr_len = port_dev->addr_len;
 	dev->mtu = port_dev->mtu;
 	memcpy(dev->broadcast, port_dev->broadcast, port_dev->addr_len);
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index e9fcf6ef716a..9bf18127e63a 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -309,7 +309,7 @@ int asix_read_phy_addr(struct usbnet *dev, int internal)
 
 	netdev_dbg(dev->net, "asix_get_phy_addr()\n");
 
-	if (ret < 0) {
+	if (ret < 2) {
 		netdev_err(dev->net, "Error reading PHYID register: %02x\n", ret);
 		goto out;
 	}
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index 914cac55a7ae..909755ef71ac 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -210,6 +210,7 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf)
 	ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0);
 	if (ret < ETH_ALEN) {
 		netdev_err(dev->net, "Failed to read MAC address: %d\n", ret);
+		ret = -EIO;
 		goto free;
 	}
 	memcpy(dev->net->dev_addr, buf, ETH_ALEN);
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index 0f69b77e8502..e7193a541244 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1400,10 +1400,10 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		}
 
 		if (pkt_cnt == 0) {
-			/* Skip IP alignment psudo header */
-			skb_pull(skb, 2);
 			skb->len = pkt_len;
-			skb_set_tail_pointer(skb, pkt_len);
+			/* Skip IP alignment pseudo header */
+			skb_pull(skb, 2);
+			skb_set_tail_pointer(skb, skb->len);
 			skb->truesize = pkt_len + sizeof(struct sk_buff);
 			ax88179_rx_checksum(skb, pkt_hdr);
 			return 1;
@@ -1412,8 +1412,9 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		ax_skb = skb_clone(skb, GFP_ATOMIC);
 		if (ax_skb) {
 			ax_skb->len = pkt_len;
-			ax_skb->data = skb->data + 2;
-			skb_set_tail_pointer(ax_skb, pkt_len);
+			/* Skip IP alignment pseudo header */
+			skb_pull(ax_skb, 2);
+			skb_set_tail_pointer(ax_skb, ax_skb->len);
 			ax_skb->truesize = pkt_len + sizeof(struct sk_buff);
 			ax88179_rx_checksum(ax_skb, pkt_hdr);
 			usbnet_skb_return(dev, ax_skb);
@@ -1735,6 +1736,7 @@ static const struct driver_info belkin_info = {
 	.status = ax88179_status,
 	.link_reset = ax88179_link_reset,
 	.reset	= ax88179_reset,
+	.stop	= ax88179_stop,
 	.flags	= FLAG_ETHER | FLAG_FRAMING_AX,
 	.rx_fixup = ax88179_rx_fixup,
 	.tx_fixup = ax88179_tx_fixup,
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 6c7a169d906a..f3def96d35d4 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -821,14 +821,21 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
-/* Microsoft Surface 3 dock (based on Realtek RTL8153) */
+/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07c6, USB_CLASS_COMM,
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
 	.driver_info = 0,
 },
 
-	/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
+/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153B) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x0927, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
+/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, 0x0601, USB_CLASS_COMM,
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index b91f92e4e5f2..915ac75b55fc 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -625,6 +625,10 @@ static const struct usb_device_id products[] = {
 	 USB_DEVICE(0x0a46, 0x1269),	/* DM9621A USB to Fast Ethernet Adapter */
 	 .driver_info = (unsigned long)&dm9601_info,
 	},
+	{
+	 USB_DEVICE(0x0586, 0x3427),	/* ZyXEL Keenetic Plus DSL xDSL modem */
+	 .driver_info = (unsigned long)&dm9601_info,
+	},
 	{},			// END
 };
 
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 6597d1f8d68c..0e3d13e192e3 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -1402,8 +1402,9 @@ static void hso_serial_set_termios(struct tty_struct *tty, struct ktermios *old)
 	unsigned long flags;
 
 	if (old)
-		hso_dbg(0x16, "Termios called with: cflags new[%d] - old[%d]\n",
-			tty->termios.c_cflag, old->c_cflag);
+		hso_dbg(0x16, "Termios called with: cflags new[%u] - old[%u]\n",
+			(unsigned int)tty->termios.c_cflag,
+			(unsigned int)old->c_cflag);
 
 	/* the actual setup */
 	spin_lock_irqsave(&serial->serial_lock, flags);
@@ -2271,12 +2272,14 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
 
 	minor = get_free_serial_index();
 	if (minor < 0)
-		goto exit;
+		goto exit2;
 
 	/* register our minor number */
 	serial->parent->dev = tty_port_register_device_attr(&serial->port,
 			tty_drv, minor, &serial->parent->interface->dev,
 			serial->parent, hso_serial_dev_groups);
+	if (IS_ERR(serial->parent->dev))
+		goto exit2;
 	dev = serial->parent->dev;
 
 	/* fill in specific data for later use */
@@ -2322,6 +2325,7 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
 	return 0;
 exit:
 	hso_serial_tty_unregister(serial);
+exit2:
 	hso_serial_common_free(serial);
 	return -1;
 }
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index b179a96ea08c..120e99914fd6 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -363,10 +363,6 @@ struct lan78xx_net {
 	struct tasklet_struct	bh;
 	struct delayed_work	wq;
 
-	struct usb_host_endpoint *ep_blkin;
-	struct usb_host_endpoint *ep_blkout;
-	struct usb_host_endpoint *ep_intr;
-
 	int			msg_enable;
 
 	struct urb		*urb_intr;
@@ -2751,78 +2747,12 @@ lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net)
 	return NETDEV_TX_OK;
 }
 
-static int
-lan78xx_get_endpoints(struct lan78xx_net *dev, struct usb_interface *intf)
-{
-	int tmp;
-	struct usb_host_interface *alt = NULL;
-	struct usb_host_endpoint *in = NULL, *out = NULL;
-	struct usb_host_endpoint *status = NULL;
-
-	for (tmp = 0; tmp < intf->num_altsetting; tmp++) {
-		unsigned ep;
-
-		in = NULL;
-		out = NULL;
-		status = NULL;
-		alt = intf->altsetting + tmp;
-
-		for (ep = 0; ep < alt->desc.bNumEndpoints; ep++) {
-			struct usb_host_endpoint *e;
-			int intr = 0;
-
-			e = alt->endpoint + ep;
-			switch (e->desc.bmAttributes) {
-			case USB_ENDPOINT_XFER_INT:
-				if (!usb_endpoint_dir_in(&e->desc))
-					continue;
-				intr = 1;
-				/* FALLTHROUGH */
-			case USB_ENDPOINT_XFER_BULK:
-				break;
-			default:
-				continue;
-			}
-			if (usb_endpoint_dir_in(&e->desc)) {
-				if (!intr && !in)
-					in = e;
-				else if (intr && !status)
-					status = e;
-			} else {
-				if (!out)
-					out = e;
-			}
-		}
-		if (in && out)
-			break;
-	}
-	if (!alt || !in || !out)
-		return -EINVAL;
-
-	dev->pipe_in = usb_rcvbulkpipe(dev->udev,
-				       in->desc.bEndpointAddress &
-				       USB_ENDPOINT_NUMBER_MASK);
-	dev->pipe_out = usb_sndbulkpipe(dev->udev,
-					out->desc.bEndpointAddress &
-					USB_ENDPOINT_NUMBER_MASK);
-	dev->ep_intr = status;
-
-	return 0;
-}
-
 static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 {
 	struct lan78xx_priv *pdata = NULL;
 	int ret;
 	int i;
 
-	ret = lan78xx_get_endpoints(dev, intf);
-	if (ret) {
-		netdev_warn(dev->net, "lan78xx_get_endpoints failed: %d\n",
-			    ret);
-		return ret;
-	}
-
 	dev->data[0] = (unsigned long)kzalloc(sizeof(*pdata), GFP_KERNEL);
 
 	pdata = (struct lan78xx_priv *)(dev->data[0]);
@@ -3567,6 +3497,7 @@ static void lan78xx_stat_monitor(unsigned long param)
 static int lan78xx_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
+	struct usb_host_endpoint *ep_blkin, *ep_blkout, *ep_intr;
 	struct lan78xx_net *dev;
 	struct net_device *netdev;
 	struct usb_device *udev;
@@ -3617,6 +3548,34 @@ static int lan78xx_probe(struct usb_interface *intf,
 
 	mutex_init(&dev->stats.access_lock);
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 3) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE);
+	ep_blkin = usb_pipe_endpoint(udev, dev->pipe_in);
+	if (!ep_blkin || !usb_endpoint_is_bulk_in(&ep_blkin->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE);
+	ep_blkout = usb_pipe_endpoint(udev, dev->pipe_out);
+	if (!ep_blkout || !usb_endpoint_is_bulk_out(&ep_blkout->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	ep_intr = &intf->cur_altsetting->endpoint[2];
+	if (!usb_endpoint_is_int_in(&ep_intr->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_intr = usb_rcvintpipe(dev->udev,
+					usb_endpoint_num(&ep_intr->desc));
+
 	ret = lan78xx_bind(dev, intf);
 	if (ret < 0)
 		goto out2;
@@ -3629,18 +3588,7 @@ static int lan78xx_probe(struct usb_interface *intf,
 	netdev->max_mtu = MAX_SINGLE_PACKET_SIZE;
 	netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER);
 
-	dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0;
-	dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1;
-	dev->ep_intr = (intf->cur_altsetting)->endpoint + 2;
-
-	dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE);
-	dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE);
-
-	dev->pipe_intr = usb_rcvintpipe(dev->udev,
-					dev->ep_intr->desc.bEndpointAddress &
-					USB_ENDPOINT_NUMBER_MASK);
-	period = dev->ep_intr->desc.bInterval;
-
+	period = ep_intr->desc.bInterval;
 	maxp = usb_maxpacket(dev->udev, dev->pipe_intr, 0);
 	buf = kmalloc(maxp, GFP_KERNEL);
 	if (buf) {
@@ -3653,6 +3601,7 @@ static int lan78xx_probe(struct usb_interface *intf,
 			usb_fill_int_urb(dev->urb_intr, dev->udev,
 					 dev->pipe_intr, buf, maxp,
 					 intr_complete, dev, period);
+			dev->urb_intr->transfer_flags |= URB_FREE_BUFFER;
 		}
 	}
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 820feeda1f35..3e3dca59b7a6 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1216,6 +1216,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
 	{QMI_FIXED_INTF(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
 	{QMI_FIXED_INTF(0x2001, 0x7e35, 4)},	/* D-Link DWM-222 */
+	{QMI_FIXED_INTF(0x2001, 0x7e3d, 4)},	/* D-Link DWM-222 A2 */
 	{QMI_FIXED_INTF(0x2020, 0x2031, 4)},	/* Olicard 600 */
 	{QMI_FIXED_INTF(0x2020, 0x2033, 4)},	/* BroadMobi BM806U */
 	{QMI_FIXED_INTF(0x2020, 0x2060, 4)},	/* BroadMobi BM818 */
@@ -1249,7 +1250,9 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
@@ -1293,6 +1296,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)},	/* SIMCom 7100E, 7230E, 7600E ++ */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
+	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)},	/* Quectel EG95 */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 	{QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)},	/* Fibocom NL678 series */
 	{QMI_FIXED_INTF(0x0489, 0xe0b4, 0)},	/* Foxconn T77W968 LTE */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index cadf5ded45a9..e30792380812 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -5329,6 +5329,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x304f)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x3062)},
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index b807c91abe1d..a22ae3137a3f 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -213,7 +213,7 @@ int rndis_command(struct usbnet *dev, struct rndis_msg_hdr *buf, int buflen)
 			dev_dbg(&info->control->dev,
 				"rndis response error, code %d\n", retval);
 		}
-		msleep(20);
+		msleep(40);
 	}
 	dev_dbg(&info->control->dev, "rndis response timeout\n");
 	return -ETIMEDOUT;
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 48ba80a8ca5c..3f4fc78498e0 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -277,12 +277,20 @@ static int write_mii_word(rtl8150_t * dev, u8 phy, __u8 indx, u16 reg)
 		return 1;
 }
 
-static inline void set_ethernet_addr(rtl8150_t * dev)
+static void set_ethernet_addr(rtl8150_t *dev)
 {
-	u8 node_id[6];
+	u8 node_id[ETH_ALEN];
+	int ret;
+
+	ret = get_registers(dev, IDR, sizeof(node_id), node_id);
 
-	get_registers(dev, IDR, sizeof(node_id), node_id);
-	memcpy(dev->netdev->dev_addr, node_id, sizeof(node_id));
+	if (ret == sizeof(node_id)) {
+		ether_addr_copy(dev->netdev->dev_addr, node_id);
+	} else {
+		eth_hw_addr_random(dev->netdev);
+		netdev_notice(dev->netdev, "Assigned a random MAC address: %pM\n",
+			      dev->netdev->dev_addr);
+	}
 }
 
 static int rtl8150_set_mac_address(struct net_device *netdev, void *p)
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index fc48da1c702d..bc6bcea67bff 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1301,11 +1301,14 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 
 	/* Init all registers */
 	ret = smsc95xx_reset(dev);
+	if (ret)
+		goto free_pdata;
 
 	/* detect device revision as different features may be available */
 	ret = smsc95xx_read_reg(dev, ID_REV, &val);
 	if (ret < 0)
-		return ret;
+		goto free_pdata;
+
 	val >>= 16;
 	pdata->chip_id = val;
 	pdata->mdix_ctrl = get_mdix_status(dev->net);
@@ -1331,6 +1334,10 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 	schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY);
 
 	return 0;
+
+free_pdata:
+	kfree(pdata);
+	return ret;
 }
 
 static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf)
@@ -1338,7 +1345,7 @@ static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf)
 	struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
 
 	if (pdata) {
-		cancel_delayed_work(&pdata->carrier_check);
+		cancel_delayed_work_sync(&pdata->carrier_check);
 		netif_dbg(dev, ifdown, dev->net, "free pdata\n");
 		kfree(pdata);
 		pdata = NULL;
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 2ff27314e047..66c6c07c7a16 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -692,6 +692,8 @@ vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key, u8 *hfunc)
 		*hfunc = ETH_RSS_HASH_TOP;
 	if (!p)
 		return 0;
+	if (n > UPT1_RSS_MAX_IND_TABLE_SIZE)
+		return 0;
 	while (n--)
 		p[n] = rssConf->indTable[n];
 	return 0;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 9bca97d5f063..82efa5bbf568 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -974,6 +974,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 	for (h = 0; h < FDB_HASH_SIZE; ++h) {
 		struct vxlan_fdb *f;
 
+		rcu_read_lock();
 		hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) {
 			struct vxlan_rdst *rd;
 
@@ -986,12 +987,15 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 						     cb->nlh->nlmsg_seq,
 						     RTM_NEWNEIGH,
 						     NLM_F_MULTI, rd);
-				if (err < 0)
+				if (err < 0) {
+					rcu_read_unlock();
 					goto out;
+				}
 skip:
 				*idx += 1;
 			}
 		}
+		rcu_read_unlock();
 	}
 out:
 	return err;
@@ -1610,6 +1614,10 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	ns_olen = request->len - skb_network_offset(request) -
 		sizeof(struct ipv6hdr) - sizeof(*ns);
 	for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
+		if (!ns->opt[i + 1]) {
+			kfree_skb(reply);
+			return NULL;
+		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
 			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
@@ -2214,7 +2222,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			skb_dst_update_pmtu(skb, mtu);
 		}
 
-		tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
+		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
 		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
 		err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr),
 				      vni, md, flags, udp_sum);
@@ -2255,7 +2263,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			skb_dst_update_pmtu(skb, mtu);
 		}
 
-		tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
+		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
 		ttl = ttl ? : ip6_dst_hoplimit(ndst);
 		skb_scrub_packet(skb, xnet);
 		err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c
index a408abc25512..1587789ba934 100644
--- a/drivers/net/wan/hdlc_cisco.c
+++ b/drivers/net/wan/hdlc_cisco.c
@@ -120,6 +120,7 @@ static void cisco_keepalive_send(struct net_device *dev, u32 type,
 	skb_put(skb, sizeof(struct cisco_packet));
 	skb->priority = TC_PRIO_CONTROL;
 	skb->dev = dev;
+	skb->protocol = htons(ETH_P_HDLC);
 	skb_reset_network_header(skb);
 
 	dev_queue_xmit(skb);
@@ -377,6 +378,7 @@ static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr)
 		memcpy(&state(hdlc)->settings, &new_settings, size);
 		spin_lock_init(&state(hdlc)->lock);
 		dev->header_ops = &cisco_header_ops;
+		dev->hard_header_len = sizeof(struct hdlc_header);
 		dev->type = ARPHRD_CISCO;
 		call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev);
 		netif_dormant_on(dev);
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index 78596e42a3f3..5a8dbeaf1a42 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -435,6 +435,8 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev)
 			if (pvc->state.fecn) /* TX Congestion counter */
 				dev->stats.tx_compressed++;
 			skb->dev = pvc->frad;
+			skb->protocol = htons(ETH_P_HDLC);
+			skb_reset_network_header(skb);
 			dev_queue_xmit(skb);
 			return NETDEV_TX_OK;
 		}
@@ -557,6 +559,7 @@ static void fr_lmi_send(struct net_device *dev, int fullrep)
 	skb_put(skb, i);
 	skb->priority = TC_PRIO_CONTROL;
 	skb->dev = dev;
+	skb->protocol = htons(ETH_P_HDLC);
 	skb_reset_network_header(skb);
 
 	dev_queue_xmit(skb);
@@ -1045,7 +1048,7 @@ static void pvc_setup(struct net_device *dev)
 {
 	dev->type = ARPHRD_DLCI;
 	dev->flags = IFF_POINTOPOINT;
-	dev->hard_header_len = 10;
+	dev->hard_header_len = 0;
 	dev->addr_len = 2;
 	netif_keep_dst(dev);
 }
@@ -1097,6 +1100,7 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
 	dev->mtu = HDLC_MAX_MTU;
 	dev->min_mtu = 68;
 	dev->max_mtu = HDLC_MAX_MTU;
+	dev->needed_headroom = 10;
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->ml_priv = pvc;
 
diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index f3c1d5245978..4381e7310be0 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -254,6 +254,7 @@ static void ppp_tx_cp(struct net_device *dev, u16 pid, u8 code,
 
 	skb->priority = TC_PRIO_CONTROL;
 	skb->dev = dev;
+	skb->protocol = htons(ETH_P_HDLC);
 	skb_reset_network_header(skb);
 	skb_queue_tail(&tx_queue, skb);
 }
@@ -386,11 +387,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 	}
 
 	for (opt = data; len; len -= opt[1], opt += opt[1]) {
-		if (len < 2 || len < opt[1]) {
-			dev->stats.rx_errors++;
-			kfree(out);
-			return; /* bad packet, drop silently */
-		}
+		if (len < 2 || opt[1] < 2 || len < opt[1])
+			goto err_out;
 
 		if (pid == PID_LCP)
 			switch (opt[0]) {
@@ -398,6 +396,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 				continue; /* MRU always OK and > 1500 bytes? */
 
 			case LCP_OPTION_ACCM: /* async control character map */
+				if (opt[1] < sizeof(valid_accm))
+					goto err_out;
 				if (!memcmp(opt, valid_accm,
 					    sizeof(valid_accm)))
 					continue;
@@ -409,6 +409,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 				}
 				break;
 			case LCP_OPTION_MAGIC:
+				if (len < 6)
+					goto err_out;
 				if (opt[1] != 6 || (!opt[2] && !opt[3] &&
 						    !opt[4] && !opt[5]))
 					break; /* reject invalid magic number */
@@ -427,6 +429,11 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 		ppp_cp_event(dev, pid, RCR_GOOD, CP_CONF_ACK, id, req_len, data);
 
 	kfree(out);
+	return;
+
+err_out:
+	dev->stats.rx_errors++;
+	kfree(out);
 }
 
 static int ppp_rx(struct sk_buff *skb)
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 0e3f8ed84660..e5fc1b95cea6 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -160,6 +160,12 @@ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb,
 	if (!netif_running(dev))
 		goto drop;
 
+	/* There should be a pseudo header of 1 byte added by upper layers.
+	 * Check to make sure it is there before reading it.
+	 */
+	if (skb->len < 1)
+		goto drop;
+
 	switch (skb->data[0]) {
 	case X25_IFACE_DATA:
 		break;
@@ -195,8 +201,6 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb)
 	struct net_device *dev;
 	int size = skb->len;
 
-	skb->protocol = htons(ETH_P_X25);
-
 	ptr = skb_push(skb, 2);
 
 	*ptr++ = size % 256;
@@ -207,6 +211,10 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb)
 
 	skb->dev = dev = lapbeth->ethdev;
 
+	skb->protocol = htons(ETH_P_DEC);
+
+	skb_reset_network_header(skb);
+
 	dev_hard_header(skb, dev, ETH_P_DEC, bcast_addr, NULL, 0);
 
 	dev_queue_xmit(skb);
@@ -308,7 +316,7 @@ static void lapbeth_setup(struct net_device *dev)
 	dev->netdev_ops	     = &lapbeth_netdev_ops;
 	dev->needs_free_netdev = true;
 	dev->type            = ARPHRD_X25;
-	dev->hard_header_len = 3;
+	dev->hard_header_len = 0;
 	dev->mtu             = 1000;
 	dev->addr_len        = 0;
 }
@@ -329,6 +337,16 @@ static int lapbeth_new_device(struct net_device *dev)
 	if (!ndev)
 		goto out;
 
+	/* When transmitting data:
+	 * first this driver removes a pseudo header of 1 byte,
+	 * then the lapb module prepends an LAPB header of at most 3 bytes,
+	 * then this driver prepends a length field of 2 bytes,
+	 * then the underlying Ethernet device prepends its own header.
+	 */
+	ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len
+					   + dev->needed_headroom;
+	ndev->needed_tailroom = dev->needed_tailroom;
+
 	lapbeth = netdev_priv(ndev);
 	lapbeth->axdev = ndev;
 
diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index 3eaefecd4448..229cab00c4b0 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -183,7 +183,7 @@ static inline void x25_asy_unlock(struct x25_asy *sl)
 	netif_wake_queue(sl->dev);
 }
 
-/* Send one completely decapsulated IP datagram to the IP layer. */
+/* Send an LAPB frame to the LAPB module to process. */
 
 static void x25_asy_bump(struct x25_asy *sl)
 {
@@ -195,13 +195,12 @@ static void x25_asy_bump(struct x25_asy *sl)
 	count = sl->rcount;
 	dev->stats.rx_bytes += count;
 
-	skb = dev_alloc_skb(count+1);
+	skb = dev_alloc_skb(count);
 	if (skb == NULL) {
 		netdev_warn(sl->dev, "memory squeeze, dropping packet\n");
 		dev->stats.rx_dropped++;
 		return;
 	}
-	skb_push(skb, 1);	/* LAPB internal control */
 	skb_put_data(skb, sl->rbuff, count);
 	skb->protocol = x25_type_trans(skb, sl->dev);
 	err = lapb_data_received(skb->dev, skb);
@@ -209,7 +208,6 @@ static void x25_asy_bump(struct x25_asy *sl)
 		kfree_skb(skb);
 		printk(KERN_DEBUG "x25_asy: data received err - %d\n", err);
 	} else {
-		netif_rx(skb);
 		dev->stats.rx_packets++;
 	}
 }
@@ -355,12 +353,21 @@ static netdev_tx_t x25_asy_xmit(struct sk_buff *skb,
  */
 
 /*
- *	Called when I frame data arrives. We did the work above - throw it
- *	at the net layer.
+ *	Called when I frame data arrive. We add a pseudo header for upper
+ *	layers and pass it to upper layers.
  */
 
 static int x25_asy_data_indication(struct net_device *dev, struct sk_buff *skb)
 {
+	if (skb_cow(skb, 1)) {
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+	skb_push(skb, 1);
+	skb->data[0] = X25_IFACE_DATA;
+
+	skb->protocol = x25_type_trans(skb, dev);
+
 	return netif_rx(skb);
 }
 
@@ -656,7 +663,7 @@ static void x25_asy_unesc(struct x25_asy *sl, unsigned char s)
 	switch (s) {
 	case X25_END:
 		if (!test_and_clear_bit(SLF_ERROR, &sl->flags) &&
-		    sl->rcount > 2)
+		    sl->rcount >= 2)
 			x25_asy_bump(sl);
 		clear_bit(SLF_ESCAPE, &sl->flags);
 		sl->rcount = 0;
diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c
index ad4a1efc57c9..e1a1d27427cc 100644
--- a/drivers/net/wireless/ath/ar5523/ar5523.c
+++ b/drivers/net/wireless/ath/ar5523/ar5523.c
@@ -1771,6 +1771,8 @@ static const struct usb_device_id ar5523_id_table[] = {
 	AR5523_DEVICE_UX(0x0846, 0x4300),	/* Netgear / WG111U */
 	AR5523_DEVICE_UG(0x0846, 0x4250),	/* Netgear / WG111T */
 	AR5523_DEVICE_UG(0x0846, 0x5f00),	/* Netgear / WPN111 */
+	AR5523_DEVICE_UG(0x083a, 0x4506),	/* SMC / EZ Connect
+						   SMCWUSBT-G2 */
 	AR5523_DEVICE_UG(0x157e, 0x3006),	/* Umedia / AR5523_1 */
 	AR5523_DEVICE_UX(0x157e, 0x3205),	/* Umedia / AR5523_2 */
 	AR5523_DEVICE_UG(0x157e, 0x3006),	/* Umedia / TEW444UBEU */
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index 0c089f6dd3d9..6a8c5f71787a 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -702,7 +702,7 @@ ath10k_rx_desc_get_l3_pad_bytes(struct ath10k_hw_params *hw,
 
 #define TARGET_10_4_TX_DBG_LOG_SIZE		1024
 #define TARGET_10_4_NUM_WDS_ENTRIES		32
-#define TARGET_10_4_DMA_BURST_SIZE		0
+#define TARGET_10_4_DMA_BURST_SIZE		1
 #define TARGET_10_4_MAC_AGGR_DELIM		0
 #define TARGET_10_4_RX_SKIP_DEFRAG_TIMEOUT_DUP_DETECTION_CHECK 1
 #define TARGET_10_4_VOW_CONFIG			0
diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index f49b21b137c1..fef313099e08 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -1564,23 +1564,33 @@ static int ath10k_sdio_hif_diag_read(struct ath10k *ar, u32 address, void *buf,
 				     size_t buf_len)
 {
 	int ret;
+	void *mem;
+
+	mem = kzalloc(buf_len, GFP_KERNEL);
+	if (!mem)
+		return -ENOMEM;
 
 	/* set window register to start read cycle */
 	ret = ath10k_sdio_write32(ar, MBOX_WINDOW_READ_ADDR_ADDRESS, address);
 	if (ret) {
 		ath10k_warn(ar, "failed to set mbox window read address: %d", ret);
-		return ret;
+		goto out;
 	}
 
 	/* read the data */
-	ret = ath10k_sdio_read(ar, MBOX_WINDOW_DATA_ADDRESS, buf, buf_len);
+	ret = ath10k_sdio_read(ar, MBOX_WINDOW_DATA_ADDRESS, mem, buf_len);
 	if (ret) {
 		ath10k_warn(ar, "failed to read from mbox window data address: %d\n",
 			    ret);
-		return ret;
+		goto out;
 	}
 
-	return 0;
+	memcpy(buf, mem, buf_len);
+
+out:
+	kfree(mem);
+
+	return ret;
 }
 
 static int ath10k_sdio_hif_diag_read32(struct ath10k *ar, u32 address,
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index 6f669166c263..e80d509bc541 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -610,6 +610,11 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev,
 			hif_dev->remain_skb = nskb;
 			spin_unlock(&hif_dev->rx_lock);
 		} else {
+			if (pool_index == MAX_PKT_NUM_IN_TRANSFER) {
+				dev_err(&hif_dev->udev->dev,
+					"ath9k_htc: over RX MAX_PKT_NUM\n");
+				goto err;
+			}
 			nskb = __dev_alloc_skb(pkt_len + 32, GFP_ATOMIC);
 			if (!nskb) {
 				dev_err(&hif_dev->udev->dev,
@@ -636,9 +641,9 @@ err:
 
 static void ath9k_hif_usb_rx_cb(struct urb *urb)
 {
-	struct sk_buff *skb = (struct sk_buff *) urb->context;
-	struct hif_device_usb *hif_dev =
-		usb_get_intfdata(usb_ifnum_to_if(urb->dev, 0));
+	struct rx_buf *rx_buf = (struct rx_buf *)urb->context;
+	struct hif_device_usb *hif_dev = rx_buf->hif_dev;
+	struct sk_buff *skb = rx_buf->skb;
 	int ret;
 
 	if (!skb)
@@ -678,14 +683,15 @@ resubmit:
 	return;
 free:
 	kfree_skb(skb);
+	kfree(rx_buf);
 }
 
 static void ath9k_hif_usb_reg_in_cb(struct urb *urb)
 {
-	struct sk_buff *skb = (struct sk_buff *) urb->context;
+	struct rx_buf *rx_buf = (struct rx_buf *)urb->context;
+	struct hif_device_usb *hif_dev = rx_buf->hif_dev;
+	struct sk_buff *skb = rx_buf->skb;
 	struct sk_buff *nskb;
-	struct hif_device_usb *hif_dev =
-		usb_get_intfdata(usb_ifnum_to_if(urb->dev, 0));
 	int ret;
 
 	if (!skb)
@@ -725,11 +731,13 @@ static void ath9k_hif_usb_reg_in_cb(struct urb *urb)
 			return;
 		}
 
+		rx_buf->skb = nskb;
+
 		usb_fill_int_urb(urb, hif_dev->udev,
 				 usb_rcvintpipe(hif_dev->udev,
 						 USB_REG_IN_PIPE),
 				 nskb->data, MAX_REG_IN_BUF_SIZE,
-				 ath9k_hif_usb_reg_in_cb, nskb, 1);
+				 ath9k_hif_usb_reg_in_cb, rx_buf, 1);
 	}
 
 resubmit:
@@ -743,6 +751,7 @@ resubmit:
 	return;
 free:
 	kfree_skb(skb);
+	kfree(rx_buf);
 	urb->context = NULL;
 }
 
@@ -788,7 +797,7 @@ static int ath9k_hif_usb_alloc_tx_urbs(struct hif_device_usb *hif_dev)
 	init_usb_anchor(&hif_dev->mgmt_submitted);
 
 	for (i = 0; i < MAX_TX_URB_NUM; i++) {
-		tx_buf = kzalloc(sizeof(struct tx_buf), GFP_KERNEL);
+		tx_buf = kzalloc(sizeof(*tx_buf), GFP_KERNEL);
 		if (!tx_buf)
 			goto err;
 
@@ -825,8 +834,9 @@ static void ath9k_hif_usb_dealloc_rx_urbs(struct hif_device_usb *hif_dev)
 
 static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
 {
-	struct urb *urb = NULL;
+	struct rx_buf *rx_buf = NULL;
 	struct sk_buff *skb = NULL;
+	struct urb *urb = NULL;
 	int i, ret;
 
 	init_usb_anchor(&hif_dev->rx_submitted);
@@ -834,6 +844,12 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
 
 	for (i = 0; i < MAX_RX_URB_NUM; i++) {
 
+		rx_buf = kzalloc(sizeof(*rx_buf), GFP_KERNEL);
+		if (!rx_buf) {
+			ret = -ENOMEM;
+			goto err_rxb;
+		}
+
 		/* Allocate URB */
 		urb = usb_alloc_urb(0, GFP_KERNEL);
 		if (urb == NULL) {
@@ -848,11 +864,14 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
 			goto err_skb;
 		}
 
+		rx_buf->hif_dev = hif_dev;
+		rx_buf->skb = skb;
+
 		usb_fill_bulk_urb(urb, hif_dev->udev,
 				  usb_rcvbulkpipe(hif_dev->udev,
 						  USB_WLAN_RX_PIPE),
 				  skb->data, MAX_RX_BUF_SIZE,
-				  ath9k_hif_usb_rx_cb, skb);
+				  ath9k_hif_usb_rx_cb, rx_buf);
 
 		/* Anchor URB */
 		usb_anchor_urb(urb, &hif_dev->rx_submitted);
@@ -878,6 +897,8 @@ err_submit:
 err_skb:
 	usb_free_urb(urb);
 err_urb:
+	kfree(rx_buf);
+err_rxb:
 	ath9k_hif_usb_dealloc_rx_urbs(hif_dev);
 	return ret;
 }
@@ -889,14 +910,21 @@ static void ath9k_hif_usb_dealloc_reg_in_urbs(struct hif_device_usb *hif_dev)
 
 static int ath9k_hif_usb_alloc_reg_in_urbs(struct hif_device_usb *hif_dev)
 {
-	struct urb *urb = NULL;
+	struct rx_buf *rx_buf = NULL;
 	struct sk_buff *skb = NULL;
+	struct urb *urb = NULL;
 	int i, ret;
 
 	init_usb_anchor(&hif_dev->reg_in_submitted);
 
 	for (i = 0; i < MAX_REG_IN_URB_NUM; i++) {
 
+		rx_buf = kzalloc(sizeof(*rx_buf), GFP_KERNEL);
+		if (!rx_buf) {
+			ret = -ENOMEM;
+			goto err_rxb;
+		}
+
 		/* Allocate URB */
 		urb = usb_alloc_urb(0, GFP_KERNEL);
 		if (urb == NULL) {
@@ -911,11 +939,14 @@ static int ath9k_hif_usb_alloc_reg_in_urbs(struct hif_device_usb *hif_dev)
 			goto err_skb;
 		}
 
+		rx_buf->hif_dev = hif_dev;
+		rx_buf->skb = skb;
+
 		usb_fill_int_urb(urb, hif_dev->udev,
 				  usb_rcvintpipe(hif_dev->udev,
 						  USB_REG_IN_PIPE),
 				  skb->data, MAX_REG_IN_BUF_SIZE,
-				  ath9k_hif_usb_reg_in_cb, skb, 1);
+				  ath9k_hif_usb_reg_in_cb, rx_buf, 1);
 
 		/* Anchor URB */
 		usb_anchor_urb(urb, &hif_dev->reg_in_submitted);
@@ -941,6 +972,8 @@ err_submit:
 err_skb:
 	usb_free_urb(urb);
 err_urb:
+	kfree(rx_buf);
+err_rxb:
 	ath9k_hif_usb_dealloc_reg_in_urbs(hif_dev);
 	return ret;
 }
@@ -971,7 +1004,7 @@ err:
 	return -ENOMEM;
 }
 
-static void ath9k_hif_usb_dealloc_urbs(struct hif_device_usb *hif_dev)
+void ath9k_hif_usb_dealloc_urbs(struct hif_device_usb *hif_dev)
 {
 	usb_kill_anchored_urbs(&hif_dev->regout_submitted);
 	ath9k_hif_usb_dealloc_reg_in_urbs(hif_dev);
@@ -1339,8 +1372,9 @@ static void ath9k_hif_usb_disconnect(struct usb_interface *interface)
 
 	if (hif_dev->flags & HIF_USB_READY) {
 		ath9k_htc_hw_deinit(hif_dev->htc_handle, unplugged);
-		ath9k_htc_hw_free(hif_dev->htc_handle);
 		ath9k_hif_usb_dev_deinit(hif_dev);
+		ath9k_destoy_wmi(hif_dev->htc_handle->drv_priv);
+		ath9k_htc_hw_free(hif_dev->htc_handle);
 	}
 
 	usb_set_intfdata(interface, NULL);
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.h b/drivers/net/wireless/ath/ath9k/hif_usb.h
index 7846916aa01d..5985aa15ca93 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.h
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.h
@@ -86,6 +86,11 @@ struct tx_buf {
 	struct list_head list;
 };
 
+struct rx_buf {
+	struct sk_buff *skb;
+	struct hif_device_usb *hif_dev;
+};
+
 #define HIF_USB_TX_STOP  BIT(0)
 #define HIF_USB_TX_FLUSH BIT(1)
 
@@ -133,5 +138,6 @@ struct hif_device_usb {
 
 int ath9k_hif_usb_init(void);
 void ath9k_hif_usb_exit(void);
+void ath9k_hif_usb_dealloc_urbs(struct hif_device_usb *hif_dev);
 
 #endif /* HTC_USB_H */
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
index da2164b0cccc..66ef5cf16450 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
@@ -933,8 +933,9 @@ err_init:
 int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev,
 			   u16 devid, char *product, u32 drv_info)
 {
-	struct ieee80211_hw *hw;
+	struct hif_device_usb *hif_dev;
 	struct ath9k_htc_priv *priv;
+	struct ieee80211_hw *hw;
 	int ret;
 
 	hw = ieee80211_alloc_hw(sizeof(struct ath9k_htc_priv), &ath9k_htc_ops);
@@ -969,7 +970,10 @@ int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev,
 	return 0;
 
 err_init:
-	ath9k_deinit_wmi(priv);
+	ath9k_stop_wmi(priv);
+	hif_dev = (struct hif_device_usb *)htc_handle->hif_dev;
+	ath9k_hif_usb_dealloc_urbs(hif_dev);
+	ath9k_destoy_wmi(priv);
 err_free:
 	ieee80211_free_hw(hw);
 	return ret;
@@ -984,7 +988,7 @@ void ath9k_htc_disconnect_device(struct htc_target *htc_handle, bool hotunplug)
 			htc_handle->drv_priv->ah->ah_flags |= AH_UNPLUGGED;
 
 		ath9k_deinit_device(htc_handle->drv_priv);
-		ath9k_deinit_wmi(htc_handle->drv_priv);
+		ath9k_stop_wmi(htc_handle->drv_priv);
 		ieee80211_free_hw(htc_handle->drv_priv->hw);
 	}
 }
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
index 4748f557c753..11d06021b5e4 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
@@ -999,9 +999,9 @@ static bool ath9k_rx_prepare(struct ath9k_htc_priv *priv,
 	 * which are not PHY_ERROR (short radar pulses have a length of 3)
 	 */
 	if (unlikely(!rs_datalen || (rs_datalen < 10 && !is_phyerr))) {
-		ath_warn(common,
-			 "Short RX data len, dropping (dlen: %d)\n",
-			 rs_datalen);
+		ath_dbg(common, ANY,
+			"Short RX data len, dropping (dlen: %d)\n",
+			rs_datalen);
 		goto rx_next;
 	}
 
diff --git a/drivers/net/wireless/ath/ath9k/htc_hst.c b/drivers/net/wireless/ath/ath9k/htc_hst.c
index 1bf63a4efb4c..f705f0e1cb5b 100644
--- a/drivers/net/wireless/ath/ath9k/htc_hst.c
+++ b/drivers/net/wireless/ath/ath9k/htc_hst.c
@@ -113,6 +113,9 @@ static void htc_process_conn_rsp(struct htc_target *target,
 
 	if (svc_rspmsg->status == HTC_SERVICE_SUCCESS) {
 		epid = svc_rspmsg->endpoint_id;
+		if (epid < 0 || epid >= ENDPOINT_MAX)
+			return;
+
 		service_id = be16_to_cpu(svc_rspmsg->service_id);
 		max_msglen = be16_to_cpu(svc_rspmsg->max_msg_len);
 		endpoint = &target->endpoint[epid];
@@ -170,6 +173,7 @@ static int htc_config_pipe_credits(struct htc_target *target)
 	time_left = wait_for_completion_timeout(&target->cmd_wait, HZ);
 	if (!time_left) {
 		dev_err(target->dev, "HTC credit config timeout\n");
+		kfree_skb(skb);
 		return -ETIMEDOUT;
 	}
 
@@ -205,6 +209,7 @@ static int htc_setup_complete(struct htc_target *target)
 	time_left = wait_for_completion_timeout(&target->cmd_wait, HZ);
 	if (!time_left) {
 		dev_err(target->dev, "HTC start timeout\n");
+		kfree_skb(skb);
 		return -ETIMEDOUT;
 	}
 
@@ -277,6 +282,7 @@ int htc_connect_service(struct htc_target *target,
 	if (!time_left) {
 		dev_err(target->dev, "Service connection timeout for: %d\n",
 			service_connreq->service_id);
+		kfree_skb(skb);
 		return -ETIMEDOUT;
 	}
 
diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c
index 64a354fa78ab..4b68804f3742 100644
--- a/drivers/net/wireless/ath/ath9k/wmi.c
+++ b/drivers/net/wireless/ath/ath9k/wmi.c
@@ -112,14 +112,17 @@ struct wmi *ath9k_init_wmi(struct ath9k_htc_priv *priv)
 	return wmi;
 }
 
-void ath9k_deinit_wmi(struct ath9k_htc_priv *priv)
+void ath9k_stop_wmi(struct ath9k_htc_priv *priv)
 {
 	struct wmi *wmi = priv->wmi;
 
 	mutex_lock(&wmi->op_mutex);
 	wmi->stopped = true;
 	mutex_unlock(&wmi->op_mutex);
+}
 
+void ath9k_destoy_wmi(struct ath9k_htc_priv *priv)
+{
 	kfree(priv->wmi);
 }
 
@@ -335,6 +338,7 @@ int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id,
 		ath_dbg(common, WMI, "Timeout waiting for WMI command: %s\n",
 			wmi_cmd_to_name(cmd_id));
 		mutex_unlock(&wmi->op_mutex);
+		kfree_skb(skb);
 		return -ETIMEDOUT;
 	}
 
diff --git a/drivers/net/wireless/ath/ath9k/wmi.h b/drivers/net/wireless/ath/ath9k/wmi.h
index 380175d5ecd7..d8b912206232 100644
--- a/drivers/net/wireless/ath/ath9k/wmi.h
+++ b/drivers/net/wireless/ath/ath9k/wmi.h
@@ -179,7 +179,6 @@ struct wmi {
 };
 
 struct wmi *ath9k_init_wmi(struct ath9k_htc_priv *priv);
-void ath9k_deinit_wmi(struct ath9k_htc_priv *priv);
 int ath9k_wmi_connect(struct htc_target *htc, struct wmi *wmi,
 		      enum htc_endpoint_id *wmi_ctrl_epid);
 int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id,
@@ -189,6 +188,8 @@ int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id,
 void ath9k_wmi_event_tasklet(unsigned long data);
 void ath9k_fatal_work(struct work_struct *work);
 void ath9k_wmi_event_drain(struct ath9k_htc_priv *priv);
+void ath9k_stop_wmi(struct ath9k_htc_priv *priv);
+void ath9k_destoy_wmi(struct ath9k_htc_priv *priv);
 
 #define WMI_CMD(_wmi_cmd)						\
 	do {								\
diff --git a/drivers/net/wireless/ath/carl9170/fw.c b/drivers/net/wireless/ath/carl9170/fw.c
index 88045f93a76c..62ed0977f32c 100644
--- a/drivers/net/wireless/ath/carl9170/fw.c
+++ b/drivers/net/wireless/ath/carl9170/fw.c
@@ -351,9 +351,7 @@ static int carl9170_fw(struct ar9170 *ar, const __u8 *data, size_t len)
 		ar->hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_ADHOC);
 
 		if (SUPP(CARL9170FW_WLANTX_CAB)) {
-			if_comb_types |=
-				BIT(NL80211_IFTYPE_AP) |
-				BIT(NL80211_IFTYPE_P2P_GO);
+			if_comb_types |= BIT(NL80211_IFTYPE_AP);
 
 #ifdef CONFIG_MAC80211_MESH
 			if_comb_types |=
diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c
index 988c8857d78c..80312b2fddb1 100644
--- a/drivers/net/wireless/ath/carl9170/main.c
+++ b/drivers/net/wireless/ath/carl9170/main.c
@@ -582,11 +582,10 @@ static int carl9170_init_interface(struct ar9170 *ar,
 	ar->disable_offload |= ((vif->type != NL80211_IFTYPE_STATION) &&
 	    (vif->type != NL80211_IFTYPE_AP));
 
-	/* While the driver supports HW offload in a single
-	 * P2P client configuration, it doesn't support HW
-	 * offload in the favourit, concurrent P2P GO+CLIENT
-	 * configuration. Hence, HW offload will always be
-	 * disabled for P2P.
+	/* The driver used to have P2P GO+CLIENT support,
+	 * but since this was dropped and we don't know if
+	 * there are any gremlins lurking in the shadows,
+	 * so best we keep HW offload disabled for P2P.
 	 */
 	ar->disable_offload |= vif->p2p;
 
@@ -639,18 +638,6 @@ static int carl9170_op_add_interface(struct ieee80211_hw *hw,
 			if (vif->type == NL80211_IFTYPE_STATION)
 				break;
 
-			/* P2P GO [master] use-case
-			 * Because the P2P GO station is selected dynamically
-			 * by all participating peers of a WIFI Direct network,
-			 * the driver has be able to change the main interface
-			 * operating mode on the fly.
-			 */
-			if (main_vif->p2p && vif->p2p &&
-			    vif->type == NL80211_IFTYPE_AP) {
-				old_main = main_vif;
-				break;
-			}
-
 			err = -EBUSY;
 			rcu_read_unlock();
 
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index af37c19dbfd7..688152bcfc15 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -1280,7 +1280,7 @@ static int wcn36xx_probe(struct platform_device *pdev)
 	if (addr && ret != ETH_ALEN) {
 		wcn36xx_err("invalid local-mac-address\n");
 		ret = -EINVAL;
-		goto out_wq;
+		goto out_destroy_ept;
 	} else if (addr) {
 		wcn36xx_info("mac address: %pM\n", addr);
 		SET_IEEE80211_PERM_ADDR(wcn->hw, addr);
@@ -1288,7 +1288,7 @@ static int wcn36xx_probe(struct platform_device *pdev)
 
 	ret = wcn36xx_platform_get_resources(wcn, pdev);
 	if (ret)
-		goto out_wq;
+		goto out_destroy_ept;
 
 	wcn36xx_init_ieee80211(wcn);
 	ret = ieee80211_register_hw(wcn->hw);
@@ -1300,6 +1300,8 @@ static int wcn36xx_probe(struct platform_device *pdev)
 out_unmap:
 	iounmap(wcn->ccu_base);
 	iounmap(wcn->dxe_base);
+out_destroy_ept:
+	rpmsg_destroy_ept(wcn->smd_channel);
 out_wq:
 	ieee80211_free_hw(hw);
 out_err:
diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c
index b37e7391f55d..8a226a9d755e 100644
--- a/drivers/net/wireless/broadcom/b43/main.c
+++ b/drivers/net/wireless/broadcom/b43/main.c
@@ -5596,7 +5596,7 @@ static struct b43_wl *b43_wireless_init(struct b43_bus_dev *dev)
 	/* fill hw info */
 	ieee80211_hw_set(hw, RX_INCLUDES_FCS);
 	ieee80211_hw_set(hw, SIGNAL_DBM);
-
+	ieee80211_hw_set(hw, MFP_CAPABLE);
 	hw->wiphy->interface_modes =
 		BIT(NL80211_IFTYPE_AP) |
 		BIT(NL80211_IFTYPE_MESH_POINT) |
diff --git a/drivers/net/wireless/broadcom/b43legacy/main.c b/drivers/net/wireless/broadcom/b43legacy/main.c
index f435bd0f8b5b..6f123a52ae2d 100644
--- a/drivers/net/wireless/broadcom/b43legacy/main.c
+++ b/drivers/net/wireless/broadcom/b43legacy/main.c
@@ -3835,6 +3835,7 @@ static int b43legacy_wireless_init(struct ssb_device *dev)
 	/* fill hw info */
 	ieee80211_hw_set(hw, RX_INCLUDES_FCS);
 	ieee80211_hw_set(hw, SIGNAL_DBM);
+	ieee80211_hw_set(hw, MFP_CAPABLE); /* Allow WPA3 in software */
 
 	hw->wiphy->interface_modes =
 		BIT(NL80211_IFTYPE_AP) |
diff --git a/drivers/net/wireless/broadcom/b43legacy/xmit.c b/drivers/net/wireless/broadcom/b43legacy/xmit.c
index 35ccf400b02c..87045e30e585 100644
--- a/drivers/net/wireless/broadcom/b43legacy/xmit.c
+++ b/drivers/net/wireless/broadcom/b43legacy/xmit.c
@@ -571,6 +571,7 @@ void b43legacy_rx(struct b43legacy_wldev *dev,
 	default:
 		b43legacywarn(dev->wl, "Unexpected value for chanstat (0x%X)\n",
 		       chanstat);
+		goto drop;
 	}
 
 	memcpy(IEEE80211_SKB_RXCB(skb), &status, sizeof(status));
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
index 53ae30259989..473b2b3cb6f5 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
@@ -192,13 +192,14 @@ void brcmf_feat_attach(struct brcmf_pub *drvr)
 	if (!err)
 		ifp->drvr->feat_flags |= BIT(BRCMF_FEAT_SCAN_RANDOM_MAC);
 
+	brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_FWSUP, "sup_wpa");
+
 	if (drvr->settings->feature_disable) {
 		brcmf_dbg(INFO, "Features: 0x%02x, disable: 0x%02x\n",
 			  ifp->drvr->feat_flags,
 			  drvr->settings->feature_disable);
 		ifp->drvr->feat_flags &= ~drvr->settings->feature_disable;
 	}
-	brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_FWSUP, "sup_wpa");
 
 	/* set chip related quirks */
 	switch (drvr->bus_if->chip) {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
index e0d22fedb2b4..05bd636011ec 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
@@ -30,7 +30,7 @@
 #define BRCMF_ARP_OL_PEER_AUTO_REPLY	0x00000008
 
 #define	BRCMF_BSS_INFO_VERSION	109 /* curr ver of brcmf_bss_info_le struct */
-#define BRCMF_BSS_RSSI_ON_CHANNEL	0x0002
+#define BRCMF_BSS_RSSI_ON_CHANNEL	0x0004
 
 #define BRCMF_STA_WME              0x00000002      /* WMM association */
 #define BRCMF_STA_AUTHE            0x00000008      /* Authenticated */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
index 2370060ef980..080733128489 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
@@ -653,6 +653,7 @@ static inline int brcmf_fws_hanger_poppkt(struct brcmf_fws_hanger *h,
 static void brcmf_fws_psq_flush(struct brcmf_fws_info *fws, struct pktq *q,
 				int ifidx)
 {
+	struct brcmf_fws_hanger_item *hi;
 	bool (*matchfn)(struct sk_buff *, void *) = NULL;
 	struct sk_buff *skb;
 	int prec;
@@ -664,6 +665,9 @@ static void brcmf_fws_psq_flush(struct brcmf_fws_info *fws, struct pktq *q,
 		skb = brcmu_pktq_pdeq_match(q, prec, matchfn, &ifidx);
 		while (skb) {
 			hslot = brcmf_skb_htod_tag_get_field(skb, HSLOT);
+			hi = &fws->hanger.items[hslot];
+			WARN_ON(skb != hi->pkt);
+			hi->state = BRCMF_FWS_HANGER_ITEM_STATE_FREE;
 			brcmf_fws_hanger_poppkt(&fws->hanger, hslot, &skb,
 						true);
 			brcmu_pkt_buf_free_skb(skb);
diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index f3f20abbe269..d06dc446a393 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -1928,6 +1928,10 @@ static netdev_tx_t mpi_start_xmit(struct sk_buff *skb,
 		airo_print_err(dev->name, "%s: skb == NULL!",__func__);
 		return NETDEV_TX_OK;
 	}
+	if (skb_padto(skb, ETH_ZLEN)) {
+		dev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
 	npacks = skb_queue_len (&ai->txq);
 
 	if (npacks >= MAXTXQ - 1) {
@@ -2130,6 +2134,10 @@ static netdev_tx_t airo_start_xmit(struct sk_buff *skb,
 		airo_print_err(dev->name, "%s: skb == NULL!", __func__);
 		return NETDEV_TX_OK;
 	}
+	if (skb_padto(skb, ETH_ZLEN)) {
+		dev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
 
 	/* Find a vacant FID */
 	for( i = 0; i < MAX_FIDS / 2 && (fids[i] & 0xffff0000); i++ );
@@ -2204,6 +2212,10 @@ static netdev_tx_t airo_start_xmit11(struct sk_buff *skb,
 		airo_print_err(dev->name, "%s: skb == NULL!", __func__);
 		return NETDEV_TX_OK;
 	}
+	if (skb_padto(skb, ETH_ZLEN)) {
+		dev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
 
 	/* Find a vacant FID */
 	for( i = MAX_FIDS / 2; i < MAX_FIDS && (fids[i] & 0xffff0000); i++ );
diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c
index 6e6b124f0d5e..3ca84577803c 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.c
+++ b/drivers/net/wireless/intel/iwlegacy/common.c
@@ -4302,8 +4302,8 @@ il_apm_init(struct il_priv *il)
 	 *    power savings, even without L1.
 	 */
 	if (il->cfg->set_l0s) {
-		pcie_capability_read_word(il->pci_dev, PCI_EXP_LNKCTL, &lctl);
-		if (lctl & PCI_EXP_LNKCTL_ASPM_L1) {
+		ret = pcie_capability_read_word(il->pci_dev, PCI_EXP_LNKCTL, &lctl);
+		if (!ret && (lctl & PCI_EXP_LNKCTL_ASPM_L1)) {
 			/* L1-ASPM enabled; disable(!) L0S  */
 			il_set_bit(il, CSR_GIO_REG,
 				   CSR_GIO_REG_VAL_L0S_ENABLED);
diff --git a/drivers/net/wireless/intersil/p54/p54usb.c b/drivers/net/wireless/intersil/p54/p54usb.c
index 15661da6eedc..39cfabf968d4 100644
--- a/drivers/net/wireless/intersil/p54/p54usb.c
+++ b/drivers/net/wireless/intersil/p54/p54usb.c
@@ -64,6 +64,7 @@ static const struct usb_device_id p54u_table[] = {
 	{USB_DEVICE(0x0db0, 0x6826)},	/* MSI UB54G (MS-6826) */
 	{USB_DEVICE(0x107b, 0x55f2)},	/* Gateway WGU-210 (Gemtek) */
 	{USB_DEVICE(0x124a, 0x4023)},	/* Shuttle PN15, Airvast WM168g, IOGear GWU513 */
+	{USB_DEVICE(0x124a, 0x4026)},	/* AirVasT USB wireless device */
 	{USB_DEVICE(0x1435, 0x0210)},	/* Inventel UR054G */
 	{USB_DEVICE(0x15a9, 0x0002)},	/* Gemtek WUBI-100GW 802.11g */
 	{USB_DEVICE(0x1630, 0x0005)},	/* 2Wire 802.11g USB (v1) / Z-Com */
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 5e8e34a08b2d..79c50aebffc4 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -1451,7 +1451,8 @@ mwifiex_cfg80211_dump_station(struct wiphy *wiphy, struct net_device *dev,
 			      int idx, u8 *mac, struct station_info *sinfo)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
-	static struct mwifiex_sta_node *node;
+	struct mwifiex_sta_node *node;
+	int i;
 
 	if ((GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_STA) &&
 	    priv->media_connected && idx == 0) {
@@ -1461,13 +1462,10 @@ mwifiex_cfg80211_dump_station(struct wiphy *wiphy, struct net_device *dev,
 		mwifiex_send_cmd(priv, HOST_CMD_APCMD_STA_LIST,
 				 HostCmd_ACT_GEN_GET, 0, NULL, true);
 
-		if (node && (&node->list == &priv->sta_list)) {
-			node = NULL;
-			return -ENOENT;
-		}
-
-		node = list_prepare_entry(node, &priv->sta_list, list);
-		list_for_each_entry_continue(node, &priv->sta_list, list) {
+		i = 0;
+		list_for_each_entry(node, &priv->sta_list, list) {
+			if (i++ != idx)
+				continue;
 			ether_addr_copy(mac, node->mac_addr);
 			return mwifiex_dump_station_info(priv, node, sinfo);
 		}
diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index 342555ebafd7..1d86d29b64cc 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -938,7 +938,7 @@ struct mwifiex_tkip_param {
 struct mwifiex_aes_param {
 	u8 pn[WPA_PN_SIZE];
 	__le16 key_len;
-	u8 key[WLAN_KEY_LEN_CCMP];
+	u8 key[WLAN_KEY_LEN_CCMP_256];
 } __packed;
 
 struct mwifiex_wapi_param {
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
index 0fba5b10ef2d..1aeb8cf6dff9 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
@@ -585,6 +585,11 @@ static int mwifiex_ret_802_11_key_material_v1(struct mwifiex_private *priv,
 {
 	struct host_cmd_ds_802_11_key_material *key =
 						&resp->params.key_material;
+	int len;
+
+	len = le16_to_cpu(key->key_param_set.key_len);
+	if (len > sizeof(key->key_param_set.key))
+		return -EINVAL;
 
 	if (le16_to_cpu(key->action) == HostCmd_ACT_GEN_SET) {
 		if ((le16_to_cpu(key->key_param_set.key_info) & KEY_MCAST)) {
@@ -598,9 +603,8 @@ static int mwifiex_ret_802_11_key_material_v1(struct mwifiex_private *priv,
 
 	memset(priv->aes_key.key_param_set.key, 0,
 	       sizeof(key->key_param_set.key));
-	priv->aes_key.key_param_set.key_len = key->key_param_set.key_len;
-	memcpy(priv->aes_key.key_param_set.key, key->key_param_set.key,
-	       le16_to_cpu(priv->aes_key.key_param_set.key_len));
+	priv->aes_key.key_param_set.key_len = cpu_to_le16(len);
+	memcpy(priv->aes_key.key_param_set.key, key->key_param_set.key, len);
 
 	return 0;
 }
@@ -615,9 +619,14 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv,
 					      struct host_cmd_ds_command *resp)
 {
 	struct host_cmd_ds_802_11_key_material_v2 *key_v2;
-	__le16 len;
+	int len;
 
 	key_v2 = &resp->params.key_material_v2;
+
+	len = le16_to_cpu(key_v2->key_param_set.key_params.aes.key_len);
+	if (len > sizeof(key_v2->key_param_set.key_params.aes.key))
+		return -EINVAL;
+
 	if (le16_to_cpu(key_v2->action) == HostCmd_ACT_GEN_SET) {
 		if ((le16_to_cpu(key_v2->key_param_set.key_info) & KEY_MCAST)) {
 			mwifiex_dbg(priv->adapter, INFO, "info: key: GTK is set\n");
@@ -631,12 +640,11 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv,
 		return 0;
 
 	memset(priv->aes_key_v2.key_param_set.key_params.aes.key, 0,
-	       WLAN_KEY_LEN_CCMP);
+	       sizeof(key_v2->key_param_set.key_params.aes.key));
 	priv->aes_key_v2.key_param_set.key_params.aes.key_len =
-				key_v2->key_param_set.key_params.aes.key_len;
-	len = priv->aes_key_v2.key_param_set.key_params.aes.key_len;
+				cpu_to_le16(len);
 	memcpy(priv->aes_key_v2.key_param_set.key_params.aes.key,
-	       key_v2->key_param_set.key_params.aes.key, le16_to_cpu(len));
+	       key_v2->key_param_set.key_params.aes.key, len);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c
index 93eda23f0123..4fa4d877f913 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.c
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.c
@@ -739,8 +739,11 @@ static int _rtl_usb_receive(struct ieee80211_hw *hw)
 
 		usb_anchor_urb(urb, &rtlusb->rx_submitted);
 		err = usb_submit_urb(urb, GFP_KERNEL);
-		if (err)
+		if (err) {
+			usb_unanchor_urb(urb);
+			usb_free_urb(urb);
 			goto err_out;
+		}
 		usb_free_urb(urb);
 	}
 	return 0;
@@ -910,10 +913,8 @@ static struct urb *_rtl_usb_tx_urb_setup(struct ieee80211_hw *hw,
 
 	WARN_ON(NULL == skb);
 	_urb = usb_alloc_urb(0, GFP_ATOMIC);
-	if (!_urb) {
-		kfree_skb(skb);
+	if (!_urb)
 		return NULL;
-	}
 	_rtl_install_trx_info(rtlusb, skb, ep_num);
 	usb_fill_bulk_urb(_urb, rtlusb->udev, usb_sndbulkpipe(rtlusb->udev,
 			  ep_num), skb->data, skb->len, _rtl_tx_complete, skb);
@@ -927,7 +928,6 @@ static void _rtl_usb_transmit(struct ieee80211_hw *hw, struct sk_buff *skb,
 	struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw));
 	u32 ep_num;
 	struct urb *_urb = NULL;
-	struct sk_buff *_skb = NULL;
 
 	WARN_ON(NULL == rtlusb->usb_tx_aggregate_hdl);
 	if (unlikely(IS_USB_STOP(rtlusb))) {
@@ -936,8 +936,7 @@ static void _rtl_usb_transmit(struct ieee80211_hw *hw, struct sk_buff *skb,
 		return;
 	}
 	ep_num = rtlusb->ep_map.ep_mapping[qnum];
-	_skb = skb;
-	_urb = _rtl_usb_tx_urb_setup(hw, _skb, ep_num);
+	_urb = _rtl_usb_tx_urb_setup(hw, skb, ep_num);
 	if (unlikely(!_urb)) {
 		pr_err("Can't allocate urb. Drop skb!\n");
 		kfree_skb(skb);
diff --git a/drivers/net/wireless/ti/wl1251/event.c b/drivers/net/wireless/ti/wl1251/event.c
index f5acd24d0e2b..988abb49771f 100644
--- a/drivers/net/wireless/ti/wl1251/event.c
+++ b/drivers/net/wireless/ti/wl1251/event.c
@@ -84,7 +84,7 @@ static int wl1251_event_ps_report(struct wl1251 *wl,
 		break;
 	}
 
-	return 0;
+	return ret;
 }
 
 static void wl1251_event_mbox_dump(struct event_mailbox *mbox)
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 91bf86cee273..1131397454bd 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -63,6 +63,8 @@ module_param_named(max_queues, xennet_max_queues, uint, 0644);
 MODULE_PARM_DESC(max_queues,
 		 "Maximum number of queues per virtual interface");
 
+#define XENNET_TIMEOUT  (5 * HZ)
+
 static const struct ethtool_ops xennet_ethtool_ops;
 
 struct netfront_cb {
@@ -1336,12 +1338,15 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 
 	netif_carrier_off(netdev);
 
-	xenbus_switch_state(dev, XenbusStateInitialising);
-	wait_event(module_wq,
-		   xenbus_read_driver_state(dev->otherend) !=
-		   XenbusStateClosed &&
-		   xenbus_read_driver_state(dev->otherend) !=
-		   XenbusStateUnknown);
+	do {
+		xenbus_switch_state(dev, XenbusStateInitialising);
+		err = wait_event_timeout(module_wq,
+				 xenbus_read_driver_state(dev->otherend) !=
+				 XenbusStateClosed &&
+				 xenbus_read_driver_state(dev->otherend) !=
+				 XenbusStateUnknown, XENNET_TIMEOUT);
+	} while (!err);
+
 	return netdev;
 
  exit:
@@ -2142,28 +2147,43 @@ static const struct attribute_group xennet_dev_group = {
 };
 #endif /* CONFIG_SYSFS */
 
-static int xennet_remove(struct xenbus_device *dev)
+static void xennet_bus_close(struct xenbus_device *dev)
 {
-	struct netfront_info *info = dev_get_drvdata(&dev->dev);
-
-	dev_dbg(&dev->dev, "%s\n", dev->nodename);
+	int ret;
 
-	if (xenbus_read_driver_state(dev->otherend) != XenbusStateClosed) {
+	if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
+		return;
+	do {
 		xenbus_switch_state(dev, XenbusStateClosing);
-		wait_event(module_wq,
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateClosing ||
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateUnknown);
+		ret = wait_event_timeout(module_wq,
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateClosing ||
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateClosed ||
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateUnknown,
+				   XENNET_TIMEOUT);
+	} while (!ret);
+
+	if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
+		return;
 
+	do {
 		xenbus_switch_state(dev, XenbusStateClosed);
-		wait_event(module_wq,
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateClosed ||
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateUnknown);
-	}
+		ret = wait_event_timeout(module_wq,
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateClosed ||
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateUnknown,
+				   XENNET_TIMEOUT);
+	} while (!ret);
+}
+
+static int xennet_remove(struct xenbus_device *dev)
+{
+	struct netfront_info *info = dev_get_drvdata(&dev->dev);
 
+	xennet_bus_close(dev);
 	xennet_disconnect_backend(info);
 
 	if (info->netdev->reg_state == NETREG_REGISTERED)
diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c
index 9d9c8d57a042..64b58455e620 100644
--- a/drivers/nfc/s3fwrn5/core.c
+++ b/drivers/nfc/s3fwrn5/core.c
@@ -209,6 +209,7 @@ int s3fwrn5_recv_frame(struct nci_dev *ndev, struct sk_buff *skb,
 	case S3FWRN5_MODE_FW:
 		return s3fwrn5_fw_recv_frame(ndev, skb);
 	default:
+		kfree_skb(skb);
 		return -ENODEV;
 	}
 }
diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c
index fd08be2917e6..7399eb2c5e1d 100644
--- a/drivers/nfc/st21nfca/dep.c
+++ b/drivers/nfc/st21nfca/dep.c
@@ -184,8 +184,10 @@ static int st21nfca_tm_send_atr_res(struct nfc_hci_dev *hdev,
 		memcpy(atr_res->gbi, atr_req->gbi, gb_len);
 		r = nfc_set_remote_general_bytes(hdev->ndev, atr_res->gbi,
 						  gb_len);
-		if (r < 0)
+		if (r < 0) {
+			kfree_skb(skb);
 			return r;
+		}
 	}
 
 	info->dep_info.curr_nfc_dep_pni = 0;
diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c
index 01acb6e53365..c4b6e29c0719 100644
--- a/drivers/nfc/st95hf/core.c
+++ b/drivers/nfc/st95hf/core.c
@@ -981,7 +981,7 @@ static int st95hf_in_send_cmd(struct nfc_digital_dev *ddev,
 	rc = down_killable(&stcontext->exchange_lock);
 	if (rc) {
 		WARN(1, "Semaphore is not found up in st95hf_in_send_cmd\n");
-		return rc;
+		goto free_skb_resp;
 	}
 
 	rc = st95hf_spi_send(&stcontext->spicontext, skb->data,
diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c
index 03b80d89b980..b75ec229b39a 100644
--- a/drivers/ntb/ntb.c
+++ b/drivers/ntb/ntb.c
@@ -216,10 +216,8 @@ int ntb_default_port_number(struct ntb_dev *ntb)
 	case NTB_TOPO_B2B_DSD:
 		return NTB_PORT_SEC_DSD;
 	default:
-		break;
+		return 0;
 	}
-
-	return -EINVAL;
 }
 EXPORT_SYMBOL(ntb_default_port_number);
 
@@ -242,10 +240,8 @@ int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx)
 	case NTB_TOPO_B2B_DSD:
 		return NTB_PORT_PRI_USD;
 	default:
-		break;
+		return 0;
 	}
-
-	return -EINVAL;
 }
 EXPORT_SYMBOL(ntb_default_peer_port_number);
 
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index c46b7e1b0132..3c68ea878ad0 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -399,9 +399,9 @@ static int btt_flog_write(struct arena_info *arena, u32 lane, u32 sub,
 	arena->freelist[lane].sub = 1 - arena->freelist[lane].sub;
 	if (++(arena->freelist[lane].seq) == 4)
 		arena->freelist[lane].seq = 1;
-	if (ent_e_flag(ent->old_map))
+	if (ent_e_flag(le32_to_cpu(ent->old_map)))
 		arena->freelist[lane].has_err = 1;
-	arena->freelist[lane].block = le32_to_cpu(ent_lba(ent->old_map));
+	arena->freelist[lane].block = ent_lba(le32_to_cpu(ent->old_map));
 
 	return ret;
 }
@@ -567,8 +567,8 @@ static int btt_freelist_init(struct arena_info *arena)
 		 * FIXME: if error clearing fails during init, we want to make
 		 * the BTT read-only
 		 */
-		if (ent_e_flag(log_new.old_map) &&
-				!ent_normal(log_new.old_map)) {
+		if (ent_e_flag(le32_to_cpu(log_new.old_map)) &&
+		    !ent_normal(le32_to_cpu(log_new.old_map))) {
 			arena->freelist[i].has_err = 1;
 			ret = arena_clear_freelist_error(arena, i);
 			if (ret)
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index ace9958f2905..6ed3b4ed27dd 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -1978,7 +1978,7 @@ struct device *create_namespace_pmem(struct nd_region *nd_region,
 		nd_mapping = &nd_region->mapping[i];
 		label_ent = list_first_entry_or_null(&nd_mapping->labels,
 				typeof(*label_ent), list);
-		label0 = label_ent ? label_ent->label : 0;
+		label0 = label_ent ? label_ent->label : NULL;
 
 		if (!label0) {
 			WARN_ON(1);
@@ -2315,8 +2315,9 @@ static struct device **scan_labels(struct nd_region *nd_region)
 			continue;
 
 		/* skip labels that describe extents outside of the region */
-		if (nd_label->dpa < nd_mapping->start || nd_label->dpa > map_end)
-			continue;
+		if (__le64_to_cpu(nd_label->dpa) < nd_mapping->start ||
+		    __le64_to_cpu(nd_label->dpa) > map_end)
+				continue;
 
 		i = add_namespace_resource(nd_region, nd_label, devs, count);
 		if (i < 0)
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index e3f060f0b83e..dd3cb5384629 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -29,7 +29,6 @@ enum {
 	 * BTT instance
 	 */
 	ND_MAX_LANES = 256,
-	SECTOR_SHIFT = 9,
 	INT_LBASIZE_ALIGNMENT = 64,
 	NVDIMM_IO_ATOMIC = 1,
 };
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index a760c449f4a9..2d95755092e3 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -758,6 +758,19 @@ void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_stop_keep_alive);
 
+/*
+ * In NVMe 1.0 the CNS field was just a binary controller or namespace
+ * flag, thus sending any new CNS opcodes has a big chance of not working.
+ * Qemu unfortunately had that bug after reporting a 1.1 version compliance
+ * (but not for any later version).
+ */
+static bool nvme_ctrl_limited_cns(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)
+		return ctrl->vs < NVME_VS(1, 2, 0);
+	return ctrl->vs < NVME_VS(1, 1, 0);
+}
+
 static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 {
 	struct nvme_command c = { };
@@ -2538,8 +2551,7 @@ static void nvme_scan_work(struct work_struct *work)
 		return;
 
 	nn = le32_to_cpu(id->nn);
-	if (ctrl->vs >= NVME_VS(1, 1, 0) &&
-	    !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
+	if (!nvme_ctrl_limited_cns(ctrl)) {
 		if (!nvme_scan_ns_list(ctrl, nn))
 			goto done;
 	}
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 058d542647dd..7e3f3055a677 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1492,7 +1492,7 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl,
 	if (fc_dma_mapping_error(ctrl->lport->dev, op->fcp_req.cmddma)) {
 		dev_err(ctrl->dev,
 			"FCP Op failed - cmdiu dma mapping failed.\n");
-		ret = EFAULT;
+		ret = -EFAULT;
 		goto out_on_error;
 	}
 
@@ -1502,7 +1502,7 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl,
 	if (fc_dma_mapping_error(ctrl->lport->dev, op->fcp_req.rspdma)) {
 		dev_err(ctrl->dev,
 			"FCP Op failed - rspiu dma mapping failed.\n");
-		ret = EFAULT;
+		ret = -EFAULT;
 	}
 
 	atomic_set(&op->state, FCPOP_STATE_IDLE);
@@ -1566,6 +1566,7 @@ nvme_fc_term_aen_ops(struct nvme_fc_ctrl *ctrl)
 	struct nvme_fc_fcp_op *aen_op;
 	int i;
 
+	cancel_work_sync(&ctrl->ctrl.async_event_work);
 	aen_op = ctrl->aen_ops;
 	for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) {
 		if (!aen_op->fcp_req.private)
@@ -3011,12 +3012,14 @@ nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts)
 	spin_lock_irqsave(&nvme_fc_lock, flags);
 	list_for_each_entry(lport, &nvme_fc_lport_list, port_list) {
 		if (lport->localport.node_name != laddr.nn ||
-		    lport->localport.port_name != laddr.pn)
+		    lport->localport.port_name != laddr.pn ||
+		    lport->localport.port_state != FC_OBJSTATE_ONLINE)
 			continue;
 
 		list_for_each_entry(rport, &lport->endp_list, endp_list) {
 			if (rport->remoteport.node_name != raddr.nn ||
-			    rport->remoteport.port_name != raddr.pn)
+			    rport->remoteport.port_name != raddr.pn ||
+			    rport->remoteport.port_state != FC_OBJSTATE_ONLINE)
 				continue;
 
 			/* if fail to get reference fall through. Will error */
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 9fffe41ead50..c91bfd839cab 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -470,7 +470,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
 	 * Spread I/O queues completion vectors according their queue index.
 	 * Admin queues can always go on completion vector 0.
 	 */
-	comp_vector = idx == 0 ? idx : idx - 1;
+	comp_vector = (idx == 0 ? idx : idx - 1) % ibdev->num_comp_vectors;
 
 	/* +1 for ib_stop_cq */
 	queue->ib_cq = ib_alloc_cq(ibdev, queue,
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 09a39f4aaf82..d0be85d0c289 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -208,6 +208,9 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 
 static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
+	if (unlikely(ctrl->kato == 0))
+		return;
+
 	pr_debug("ctrl %d start keep-alive timer for %d secs\n",
 		ctrl->cntlid, ctrl->kato);
 
@@ -217,6 +220,9 @@ static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 
 static void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
+	if (unlikely(ctrl->kato == 0))
+		return;
+
 	pr_debug("ctrl %d stop keep-alive\n", ctrl->cntlid);
 
 	cancel_delayed_work_sync(&ctrl->ka_work);
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index b7a5d1065378..df1c6dee255b 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1994,9 +1994,9 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
 			return;
 		if (fcpreq->fcp_error ||
 		    fcpreq->transferred_length != fcpreq->transfer_length) {
-			spin_lock(&fod->flock);
+			spin_lock_irqsave(&fod->flock, flags);
 			fod->abort = true;
-			spin_unlock(&fod->flock);
+			spin_unlock_irqrestore(&fod->flock, flags);
 
 			nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
 			return;
diff --git a/drivers/nvmem/qfprom.c b/drivers/nvmem/qfprom.c
index 2bdb6c389328..d3e08496e49b 100644
--- a/drivers/nvmem/qfprom.c
+++ b/drivers/nvmem/qfprom.c
@@ -30,19 +30,6 @@ static int qfprom_reg_read(void *context,
 	return 0;
 }
 
-static int qfprom_reg_write(void *context,
-			 unsigned int reg, void *_val, size_t bytes)
-{
-	void __iomem *base = context;
-	u8 *val = _val;
-	int i = 0, words = bytes;
-
-	while (words--)
-		writeb(*val++, base + reg + i++);
-
-	return 0;
-}
-
 static int qfprom_remove(struct platform_device *pdev)
 {
 	struct nvmem_device *nvmem = platform_get_drvdata(pdev);
@@ -56,7 +43,6 @@ static struct nvmem_config econfig = {
 	.stride = 1,
 	.word_size = 1,
 	.reg_read = qfprom_reg_read,
-	.reg_write = qfprom_reg_write,
 };
 
 static int qfprom_probe(struct platform_device *pdev)
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 69da2f6896da..8b7d3e64b8ca 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -256,10 +256,15 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 				 child->name, addr);
 
 			if (of_mdiobus_child_is_phy(child)) {
+				/* -ENODEV is the return code that PHYLIB has
+				 * standardized on to indicate that bus
+				 * scanning should continue.
+				 */
 				rc = of_mdiobus_register_phy(mdio, child, addr);
-				if (rc && rc != -ENODEV)
+				if (!rc)
+					break;
+				if (rc != -ENODEV)
 					goto unregister;
-				break;
 			}
 		}
 	}
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 5468490d2298..55b3274328eb 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -1291,7 +1291,7 @@ sba_ioc_init_pluto(struct parisc_device *sba, struct ioc *ioc, int ioc_num)
 	** (one that doesn't overlap memory or LMMIO space) in the
 	** IBASE and IMASK registers.
 	*/
-	ioc->ibase = READ_REG(ioc->ioc_hpa + IOC_IBASE);
+	ioc->ibase = READ_REG(ioc->ioc_hpa + IOC_IBASE) & ~0x1fffffULL;
 	iova_space_size = ~(READ_REG(ioc->ioc_hpa + IOC_IMASK) & 0xFFFFFFFFUL) + 1;
 
 	if ((ioc->ibase < 0xfed00000UL) && ((ioc->ibase + iova_space_size) > 0xfee00000UL)) {
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 913d6722ece9..8c585e7ca520 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -205,17 +205,13 @@ EXPORT_SYMBOL(pci_bus_set_ops);
 static DECLARE_WAIT_QUEUE_HEAD(pci_cfg_wait);
 
 static noinline void pci_wait_cfg(struct pci_dev *dev)
+	__must_hold(&pci_lock)
 {
-	DECLARE_WAITQUEUE(wait, current);
-
-	__add_wait_queue(&pci_cfg_wait, &wait);
 	do {
-		set_current_state(TASK_UNINTERRUPTIBLE);
 		raw_spin_unlock_irq(&pci_lock);
-		schedule();
+		wait_event(pci_cfg_wait, !dev->block_cfg_access);
 		raw_spin_lock_irq(&pci_lock);
 	} while (dev->block_cfg_access);
-	__remove_wait_queue(&pci_cfg_wait, &wait);
 }
 
 /* Returns 0 on success, negative values indicate error. */
diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c
index 5f3048e75bec..c1db09fbbe04 100644
--- a/drivers/pci/host/pci-aardvark.c
+++ b/drivers/pci/host/pci-aardvark.c
@@ -365,10 +365,6 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 
 	advk_pcie_wait_for_link(pcie);
 
-	reg = PCIE_CORE_LINK_L0S_ENTRY |
-		(1 << PCIE_CORE_LINK_WIDTH_SHIFT);
-	advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG);
-
 	reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
 	reg |= PCIE_CORE_CMD_MEM_ACCESS_EN |
 		PCIE_CORE_CMD_IO_ACCESS_EN |
diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c
index 2b0a1f3b8265..0077afca2493 100644
--- a/drivers/pci/host/pcie-rcar.c
+++ b/drivers/pci/host/pcie-rcar.c
@@ -328,11 +328,12 @@ static struct pci_ops rcar_pcie_ops = {
 };
 
 static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie,
-				   struct resource *res)
+				   struct resource_entry *window)
 {
 	/* Setup PCIe address space mappings for each resource */
 	resource_size_t size;
 	resource_size_t res_start;
+	struct resource *res = window->res;
 	u32 mask;
 
 	rcar_pci_write_reg(pcie, 0x00000000, PCIEPTCTLR(win));
@@ -346,9 +347,9 @@ static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie,
 	rcar_pci_write_reg(pcie, mask << 7, PCIEPAMR(win));
 
 	if (res->flags & IORESOURCE_IO)
-		res_start = pci_pio_to_address(res->start);
+		res_start = pci_pio_to_address(res->start) - window->offset;
 	else
-		res_start = res->start;
+		res_start = res->start - window->offset;
 
 	rcar_pci_write_reg(pcie, upper_32_bits(res_start), PCIEPAUR(win));
 	rcar_pci_write_reg(pcie, lower_32_bits(res_start) & ~0x7F,
@@ -377,7 +378,7 @@ static int rcar_pcie_setup(struct list_head *resource, struct rcar_pcie *pci)
 		switch (resource_type(res)) {
 		case IORESOURCE_IO:
 		case IORESOURCE_MEM:
-			rcar_pcie_setup_window(i, pci, res);
+			rcar_pcie_setup_window(i, pci, win);
 			i++;
 			break;
 		case IORESOURCE_BUS:
diff --git a/drivers/pci/host/vmd.c b/drivers/pci/host/vmd.c
index af6d5da10ea5..79d56638878c 100644
--- a/drivers/pci/host/vmd.c
+++ b/drivers/pci/host/vmd.c
@@ -638,9 +638,10 @@ static int vmd_enable_domain(struct vmd_dev *vmd)
 
 	vmd->irq_domain = pci_msi_create_irq_domain(fn, &vmd_msi_domain_info,
 						    x86_vector_domain);
-	irq_domain_free_fwnode(fn);
-	if (!vmd->irq_domain)
+	if (!vmd->irq_domain) {
+		irq_domain_free_fwnode(fn);
 		return -ENODEV;
+	}
 
 	pci_add_resource(&resources, &vmd->resources[0]);
 	pci_add_resource(&resources, &vmd->resources[1]);
@@ -650,6 +651,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd)
 	if (!vmd->bus) {
 		pci_free_resource_list(&resources);
 		irq_domain_remove(vmd->irq_domain);
+		irq_domain_free_fwnode(fn);
 		return -ENODEV;
 	}
 
@@ -752,6 +754,7 @@ static void vmd_cleanup_srcu(struct vmd_dev *vmd)
 static void vmd_remove(struct pci_dev *dev)
 {
 	struct vmd_dev *vmd = pci_get_drvdata(dev);
+	struct fwnode_handle *fn = vmd->irq_domain->fwnode;
 
 	sysfs_remove_link(&vmd->dev->dev.kobj, "domain");
 	pci_stop_root_bus(vmd->bus);
@@ -760,6 +763,7 @@ static void vmd_remove(struct pci_dev *dev)
 	vmd_teardown_dma_ops(vmd);
 	vmd_detach_resources(vmd);
 	irq_domain_remove(vmd->irq_domain);
+	irq_domain_free_fwnode(fn);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 711875afdd70..f2c1008e0f76 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -136,13 +136,21 @@ static struct acpiphp_context *acpiphp_grab_context(struct acpi_device *adev)
 	struct acpiphp_context *context;
 
 	acpi_lock_hp_context();
+
 	context = acpiphp_get_context(adev);
-	if (!context || context->func.parent->is_going_away) {
-		acpi_unlock_hp_context();
-		return NULL;
+	if (!context)
+		goto unlock;
+
+	if (context->func.parent->is_going_away) {
+		acpiphp_put_context(context);
+		context = NULL;
+		goto unlock;
 	}
+
 	get_bridge(context->func.parent);
 	acpiphp_put_context(context);
+
+unlock:
 	acpi_unlock_hp_context();
 	return context;
 }
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 400031622b76..f41c105adfbd 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -584,16 +584,6 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 
 	/* Setup initial capable state. Will be updated later */
 	link->aspm_capable = link->aspm_support;
-	/*
-	 * If the downstream component has pci bridge function, don't
-	 * do ASPM for now.
-	 */
-	list_for_each_entry(child, &linkbus->devices, bus_list) {
-		if (pci_pcie_type(child) == PCI_EXP_TYPE_PCI_BRIDGE) {
-			link->aspm_disable = ASPM_STATE_ALL;
-			break;
-		}
-	}
 
 	/* Get and check endpoint acceptable latencies */
 	list_for_each_entry(child, &linkbus->devices, bus_list) {
@@ -1121,6 +1111,7 @@ static int pcie_aspm_get_policy(char *buffer, struct kernel_param *kp)
 			cnt += sprintf(buffer + cnt, "[%s] ", policy_str[i]);
 		else
 			cnt += sprintf(buffer + cnt, "%s ", policy_str[i]);
+	cnt += sprintf(buffer + cnt, "\n");
 	return cnt;
 }
 
diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c
index 3008bba360f3..ec6f6213960b 100644
--- a/drivers/pci/pcie/ptm.c
+++ b/drivers/pci/pcie/ptm.c
@@ -47,10 +47,6 @@ void pci_ptm_init(struct pci_dev *dev)
 	if (!pci_is_pcie(dev))
 		return;
 
-	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_PTM);
-	if (!pos)
-		return;
-
 	/*
 	 * Enable PTM only on interior devices (root ports, switch ports,
 	 * etc.) on the assumption that it causes no link traffic until an
@@ -60,6 +56,23 @@ void pci_ptm_init(struct pci_dev *dev)
 	     pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END))
 		return;
 
+	/*
+	 * Switch Downstream Ports are not permitted to have a PTM
+	 * capability; their PTM behavior is controlled by the Upstream
+	 * Port (PCIe r5.0, sec 7.9.16).
+	 */
+	ups = pci_upstream_bridge(dev);
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM &&
+	    ups && ups->ptm_enabled) {
+		dev->ptm_granularity = ups->ptm_granularity;
+		dev->ptm_enabled = 1;
+		return;
+	}
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_PTM);
+	if (!pos)
+		return;
+
 	pci_read_config_dword(dev, pos + PCI_PTM_CAP, &cap);
 	local_clock = (cap & PCI_PTM_GRANULARITY_MASK) >> 8;
 
@@ -69,7 +82,6 @@ void pci_ptm_init(struct pci_dev *dev)
 	 * the spec recommendation (PCIe r3.1, sec 7.32.3), select the
 	 * furthest upstream Time Source as the PTM Root.
 	 */
-	ups = pci_upstream_bridge(dev);
 	if (ups && ups->ptm_enabled) {
 		ctrl = PCI_PTM_CTRL_ENABLE;
 		if (ups->ptm_granularity == 0)
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index e23bfd9845b1..55ece07e584a 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -792,9 +792,10 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 		goto free;
 
 	err = device_register(&bridge->dev);
-	if (err)
+	if (err) {
 		put_device(&bridge->dev);
-
+		goto free;
+	}
 	bus->bridge = get_device(&bridge->dev);
 	device_enable_async_suspend(bus->bridge);
 	pci_set_bus_of_node(bus);
@@ -1446,7 +1447,7 @@ int pci_setup_device(struct pci_dev *dev)
 	/* device class may be changed after fixup */
 	class = dev->class >> 8;
 
-	if (dev->non_compliant_bars) {
+	if (dev->non_compliant_bars && !dev->mmio_always_on) {
 		pci_read_config_word(dev, PCI_COMMAND, &cmd);
 		if (cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
 			dev_info(&dev->dev, "device has non-compliant BARs; disabling IO/MEM decoding\n");
@@ -1557,13 +1558,33 @@ static void pci_configure_mps(struct pci_dev *dev)
 	struct pci_dev *bridge = pci_upstream_bridge(dev);
 	int mps, p_mps, rc;
 
-	if (!pci_is_pcie(dev) || !bridge || !pci_is_pcie(bridge))
+	if (!pci_is_pcie(dev))
 		return;
 
 	/* MPS and MRRS fields are of type 'RsvdP' for VFs, short-circuit out */
 	if (dev->is_virtfn)
 		return;
 
+	/*
+	 * For Root Complex Integrated Endpoints, program the maximum
+	 * supported value unless limited by the PCIE_BUS_PEER2PEER case.
+	 */
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) {
+		if (pcie_bus_config == PCIE_BUS_PEER2PEER)
+			mps = 128;
+		else
+			mps = 128 << dev->pcie_mpss;
+		rc = pcie_set_mps(dev, mps);
+		if (rc) {
+			pci_warn(dev, "can't set Max Payload Size to %d; if necessary, use \"pci=pcie_bus_safe\" and report a bug\n",
+				 mps);
+		}
+		return;
+	}
+
+	if (!bridge || !pci_is_pcie(bridge))
+		return;
+
 	mps = pcie_get_mps(dev);
 	p_mps = pcie_get_mps(bridge);
 
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index e7ed051ec125..da790f26d295 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -27,6 +27,7 @@
 #include <linux/ktime.h>
 #include <linux/mm.h>
 #include <linux/platform_data/x86/apple.h>
+#include <linux/pm_runtime.h>
 #include <asm/dma.h>	/* isa_dma_bridge_buggy */
 #include "pci.h"
 
@@ -2085,6 +2086,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s);
 
+static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev)
+{
+	pci_info(dev, "Disabling ASPM L0s/L1\n");
+	pci_disable_link_state(dev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1);
+}
+
+/*
+ * ASM1083/1085 PCIe-PCI bridge devices cause AER timeout errors on the
+ * upstream PCIe root port when ASPM is enabled. At least L0s mode is affected;
+ * disable both L0s and L1 for now to be safe.
+ */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x1080, quirk_disable_aspm_l0s_l1);
+
 /*
  * Some Pericom PCIe-to-PCI bridges in reverse mode need the PCIe Retrain
  * Link bit cleared after starting the link retrain process to allow this
@@ -4236,6 +4250,24 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID,
 			 quirk_chelsio_T5_disable_root_port_attributes);
 
 /*
+ * pci_acs_ctrl_enabled - compare desired ACS controls with those provided
+ *			  by a device
+ * @acs_ctrl_req: Bitmask of desired ACS controls
+ * @acs_ctrl_ena: Bitmask of ACS controls enabled or provided implicitly by
+ *		  the hardware design
+ *
+ * Return 1 if all ACS controls in the @acs_ctrl_req bitmask are included
+ * in @acs_ctrl_ena, i.e., the device provides all the access controls the
+ * caller desires.  Return 0 otherwise.
+ */
+static int pci_acs_ctrl_enabled(u16 acs_ctrl_req, u16 acs_ctrl_ena)
+{
+	if ((acs_ctrl_req & acs_ctrl_ena) == acs_ctrl_req)
+		return 1;
+	return 0;
+}
+
+/*
  * AMD has indicated that the devices below do not support peer-to-peer
  * in any system where they are found in the southbridge with an AMD
  * IOMMU in the system.  Multifunction devices that do not support
@@ -4275,10 +4307,12 @@ static int pci_quirk_amd_sb_acs(struct pci_dev *dev, u16 acs_flags)
 	if (ACPI_FAILURE(status))
 		return -ENODEV;
 
+	acpi_put_table(header);
+
 	/* Filter out flags not applicable to multifunction */
 	acs_flags &= (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC | PCI_ACS_DT);
 
-	return acs_flags & ~(PCI_ACS_RR | PCI_ACS_CR) ? 0 : 1;
+	return pci_acs_ctrl_enabled(acs_flags, PCI_ACS_RR | PCI_ACS_CR);
 #else
 	return -ENODEV;
 #endif
@@ -4305,20 +4339,19 @@ static bool pci_quirk_cavium_acs_match(struct pci_dev *dev)
 
 static int pci_quirk_cavium_acs(struct pci_dev *dev, u16 acs_flags)
 {
+	if (!pci_quirk_cavium_acs_match(dev))
+		return -ENOTTY;
+
 	/*
-	 * Cavium root ports don't advertise an ACS capability.  However,
+	 * Cavium Root Ports don't advertise an ACS capability.  However,
 	 * the RTL internally implements similar protection as if ACS had
-	 * Request Redirection, Completion Redirection, Source Validation,
+	 * Source Validation, Request Redirection, Completion Redirection,
 	 * and Upstream Forwarding features enabled.  Assert that the
 	 * hardware implements and enables equivalent ACS functionality for
 	 * these flags.
 	 */
-	acs_flags &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_SV | PCI_ACS_UF);
-
-	if (!pci_quirk_cavium_acs_match(dev))
-		return -ENOTTY;
-
-	return acs_flags ? 0 : 1;
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 }
 
 static int pci_quirk_xgene_acs(struct pci_dev *dev, u16 acs_flags)
@@ -4328,13 +4361,12 @@ static int pci_quirk_xgene_acs(struct pci_dev *dev, u16 acs_flags)
 	 * transactions with others, allowing masking out these bits as if they
 	 * were unimplemented in the ACS capability.
 	 */
-	acs_flags &= ~(PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
-
-	return acs_flags ? 0 : 1;
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 }
 
 /*
- * Many Intel PCH root ports do provide ACS-like features to disable peer
+ * Many Intel PCH Root Ports do provide ACS-like features to disable peer
  * transactions and validate bus numbers in requests, but do not provide an
  * actual PCIe ACS capability.  This is the list of device IDs known to fall
  * into that category as provided by Intel in Red Hat bugzilla 1037684.
@@ -4382,37 +4414,32 @@ static bool pci_quirk_intel_pch_acs_match(struct pci_dev *dev)
 	return false;
 }
 
-#define INTEL_PCH_ACS_FLAGS (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_SV)
-
 static int pci_quirk_intel_pch_acs(struct pci_dev *dev, u16 acs_flags)
 {
-	u16 flags = dev->dev_flags & PCI_DEV_FLAGS_ACS_ENABLED_QUIRK ?
-		    INTEL_PCH_ACS_FLAGS : 0;
-
 	if (!pci_quirk_intel_pch_acs_match(dev))
 		return -ENOTTY;
 
-	return acs_flags & ~flags ? 0 : 1;
+	if (dev->dev_flags & PCI_DEV_FLAGS_ACS_ENABLED_QUIRK)
+		return pci_acs_ctrl_enabled(acs_flags,
+			PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
+
+	return pci_acs_ctrl_enabled(acs_flags, 0);
 }
 
 /*
- * These QCOM root ports do provide ACS-like features to disable peer
+ * These QCOM Root Ports do provide ACS-like features to disable peer
  * transactions and validate bus numbers in requests, but do not provide an
  * actual PCIe ACS capability.  Hardware supports source validation but it
  * will report the issue as Completer Abort instead of ACS Violation.
- * Hardware doesn't support peer-to-peer and each root port is a root
- * complex with unique segment numbers.  It is not possible for one root
- * port to pass traffic to another root port.  All PCIe transactions are
- * terminated inside the root port.
+ * Hardware doesn't support peer-to-peer and each Root Port is a Root
+ * Complex with unique segment numbers.  It is not possible for one Root
+ * Port to pass traffic to another Root Port.  All PCIe transactions are
+ * terminated inside the Root Port.
  */
 static int pci_quirk_qcom_rp_acs(struct pci_dev *dev, u16 acs_flags)
 {
-	u16 flags = (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_SV);
-	int ret = acs_flags & ~flags ? 0 : 1;
-
-	dev_info(&dev->dev, "Using QCOM ACS Quirk (%d)\n", ret);
-
-	return ret;
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 }
 
 /*
@@ -4495,7 +4522,7 @@ static int pci_quirk_intel_spt_pch_acs(struct pci_dev *dev, u16 acs_flags)
 
 	pci_read_config_dword(dev, pos + INTEL_SPT_ACS_CTRL, &ctrl);
 
-	return acs_flags & ~ctrl ? 0 : 1;
+	return pci_acs_ctrl_enabled(acs_flags, ctrl);
 }
 
 static int pci_quirk_mf_endpoint_acs(struct pci_dev *dev, u16 acs_flags)
@@ -4509,10 +4536,35 @@ static int pci_quirk_mf_endpoint_acs(struct pci_dev *dev, u16 acs_flags)
 	 * perform peer-to-peer with other functions, allowing us to mask out
 	 * these bits as if they were unimplemented in the ACS capability.
 	 */
-	acs_flags &= ~(PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR |
-		       PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_DT);
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR |
+		PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_DT);
+}
+
+static int pci_quirk_rciep_acs(struct pci_dev *dev, u16 acs_flags)
+{
+	/*
+	 * Intel RCiEP's are required to allow p2p only on translated
+	 * addresses.  Refer to Intel VT-d specification, r3.1, sec 3.16,
+	 * "Root-Complex Peer to Peer Considerations".
+	 */
+	if (pci_pcie_type(dev) != PCI_EXP_TYPE_RC_END)
+		return -ENOTTY;
 
-	return acs_flags ? 0 : 1;
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
+}
+
+static int pci_quirk_brcm_acs(struct pci_dev *dev, u16 acs_flags)
+{
+	/*
+	 * iProc PAXB Root Ports don't advertise an ACS capability, but
+	 * they do not allow peer-to-peer transactions between Root Ports.
+	 * Allow each Root Port to be in a separate IOMMU group by masking
+	 * SV/RR/CR/UF bits.
+	 */
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 }
 
 static const struct pci_dev_acs_enabled {
@@ -4585,6 +4637,7 @@ static const struct pci_dev_acs_enabled {
 	/* I219 */
 	{ PCI_VENDOR_ID_INTEL, 0x15b7, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_INTEL, 0x15b8, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_rciep_acs },
 	/* QCOM QDF2xxx root ports */
 	{ 0x17cb, 0x400, pci_quirk_qcom_rp_acs },
 	{ 0x17cb, 0x401, pci_quirk_qcom_rp_acs },
@@ -4597,9 +4650,30 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_CAVIUM, PCI_ANY_ID, pci_quirk_cavium_acs },
 	/* APM X-Gene */
 	{ PCI_VENDOR_ID_AMCC, 0xE004, pci_quirk_xgene_acs },
+	/* Ampere Computing */
+	{ PCI_VENDOR_ID_AMPERE, 0xE005, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE006, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE007, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE008, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE009, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE00A, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE00B, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs },
 	{ 0 }
 };
 
+/*
+ * pci_dev_specific_acs_enabled - check whether device provides ACS controls
+ * @dev:	PCI device
+ * @acs_flags:	Bitmask of desired ACS controls
+ *
+ * Returns:
+ *   -ENOTTY:	No quirk applies to this device; we can't tell whether the
+ *		device provides the desired controls
+ *   0:		Device does not provide all the desired controls
+ *   >0:	Device provides all the controls in @acs_flags
+ */
 int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags)
 {
 	const struct pci_dev_acs_enabled *i;
@@ -4869,13 +4943,25 @@ static void quirk_intel_qat_vf_cap(struct pci_dev *pdev)
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x443, quirk_intel_qat_vf_cap);
 
-/* FLR may cause some 82579 devices to hang. */
-static void quirk_intel_no_flr(struct pci_dev *dev)
+/*
+ * FLR may cause the following to devices to hang:
+ *
+ * AMD Starship/Matisse HD Audio Controller 0x1487
+ * AMD Starship USB 3.0 Host Controller 0x148c
+ * AMD Matisse USB 3.0 Host Controller 0x149c
+ * Intel 82579LM Gigabit Ethernet Controller 0x1502
+ * Intel 82579V Gigabit Ethernet Controller 0x1503
+ *
+ */
+static void quirk_no_flr(struct pci_dev *dev)
 {
 	dev->dev_flags |= PCI_DEV_FLAGS_NO_FLR_RESET;
 }
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_intel_no_flr);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_intel_no_flr);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1487, quirk_no_flr);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x148c, quirk_no_flr);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x149c, quirk_no_flr);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_no_flr);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_no_flr);
 
 static void quirk_no_ext_tags(struct pci_dev *pdev)
 {
@@ -4912,3 +4998,63 @@ static void quirk_no_ats(struct pci_dev *pdev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_no_ats);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_no_ats);
 #endif /* CONFIG_PCI_ATS */
+
+/* Freescale PCIe doesn't support MSI in RC mode */
+static void quirk_fsl_no_msi(struct pci_dev *pdev)
+{
+	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT)
+		pdev->no_msi = 1;
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_FREESCALE, PCI_ANY_ID, quirk_fsl_no_msi);
+
+/*
+ * Although not allowed by the spec, some multi-function devices have
+ * dependencies of one function (consumer) on another (supplier).  For the
+ * consumer to work in D0, the supplier must also be in D0.  Create a
+ * device link from the consumer to the supplier to enforce this
+ * dependency.  Runtime PM is allowed by default on the consumer to prevent
+ * it from permanently keeping the supplier awake.
+ */
+static void pci_create_device_link(struct pci_dev *pdev, unsigned int consumer,
+				   unsigned int supplier, unsigned int class,
+				   unsigned int class_shift)
+{
+	struct pci_dev *supplier_pdev;
+
+	if (PCI_FUNC(pdev->devfn) != consumer)
+		return;
+
+	supplier_pdev = pci_get_domain_bus_and_slot(pci_domain_nr(pdev->bus),
+				pdev->bus->number,
+				PCI_DEVFN(PCI_SLOT(pdev->devfn), supplier));
+	if (!supplier_pdev || (supplier_pdev->class >> class_shift) != class) {
+		pci_dev_put(supplier_pdev);
+		return;
+	}
+
+	if (device_link_add(&pdev->dev, &supplier_pdev->dev,
+			    DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME))
+		pci_info(pdev, "D0 power state depends on %s\n",
+			 pci_name(supplier_pdev));
+	else
+		pci_err(pdev, "Cannot enforce power dependency on %s\n",
+			pci_name(supplier_pdev));
+
+	pm_runtime_allow(&pdev->dev);
+	pci_dev_put(supplier_pdev);
+}
+
+/*
+ * Create device link for GPUs with integrated HDA controller for streaming
+ * audio to attached displays.
+ */
+static void quirk_gpu_hda(struct pci_dev *hda)
+{
+	pci_create_device_link(hda, 1, 0, PCI_BASE_CLASS_DISPLAY, 16);
+}
+DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_ATI, PCI_ANY_ID,
+			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
+DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_AMD, PCI_ANY_ID,
+			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
+DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
+			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index e42909524dee..379925fc49d4 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -303,13 +303,16 @@ placeholder:
 	slot_name = make_slot_name(name);
 	if (!slot_name) {
 		err = -ENOMEM;
+		kfree(slot);
 		goto err;
 	}
 
 	err = kobject_init_and_add(&slot->kobj, &pci_slot_ktype, NULL,
 				   "%s", slot_name);
-	if (err)
+	if (err) {
+		kobject_put(&slot->kobj);
 		goto err;
+	}
 
 	INIT_LIST_HEAD(&slot->list);
 	list_add(&slot->list, &parent->slots);
@@ -328,7 +331,6 @@ out:
 	mutex_unlock(&pci_slot_mutex);
 	return slot;
 err:
-	kfree(slot);
 	slot = ERR_PTR(err);
 	goto out;
 }
diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c
index 46d60a3bf260..d6e47dee78b5 100644
--- a/drivers/phy/allwinner/phy-sun4i-usb.c
+++ b/drivers/phy/allwinner/phy-sun4i-usb.c
@@ -549,13 +549,14 @@ static void sun4i_usb_phy0_id_vbus_det_scan(struct work_struct *work)
 	struct sun4i_usb_phy_data *data =
 		container_of(work, struct sun4i_usb_phy_data, detect.work);
 	struct phy *phy0 = data->phys[0].phy;
-	struct sun4i_usb_phy *phy = phy_get_drvdata(phy0);
+	struct sun4i_usb_phy *phy;
 	bool force_session_end, id_notify = false, vbus_notify = false;
 	int id_det, vbus_det;
 
-	if (phy0 == NULL)
+	if (!phy0)
 		return;
 
+	phy = phy_get_drvdata(phy0);
 	id_det = sun4i_usb_phy0_get_id_det(data);
 	vbus_det = sun4i_usb_phy0_get_vbus_det(data);
 
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.c b/drivers/phy/qualcomm/phy-qcom-qmp.c
index 2526971f9929..3eeaf57e6d93 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.c
@@ -102,6 +102,8 @@
 #define QSERDES_COM_CORECLK_DIV_MODE1			0x1bc
 
 /* QMP PHY TX registers */
+#define QSERDES_TX_EMP_POST1_LVL			0x018
+#define QSERDES_TX_SLEW_CNTL				0x040
 #define QSERDES_TX_RES_CODE_LANE_OFFSET			0x054
 #define QSERDES_TX_DEBUG_BUS_SEL			0x064
 #define QSERDES_TX_HIGHZ_TRANSCEIVEREN_BIAS_DRVR_EN	0x068
@@ -394,8 +396,8 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_BG_TRIM, 0xf),
 	QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP_EN, 0x1),
 	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_MAP, 0x0),
-	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER1, 0x1f),
-	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER2, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER1, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER2, 0x1f),
 	QMP_PHY_INIT_CFG(QSERDES_COM_CMN_CONFIG, 0x6),
 	QMP_PHY_INIT_CFG(QSERDES_COM_PLL_IVCO, 0xf),
 	QMP_PHY_INIT_CFG(QSERDES_COM_HSCLK_SEL, 0x0),
@@ -421,7 +423,6 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN1_MODE0, 0x0),
 	QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN0_MODE0, 0x80),
 	QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CTRL_BY_PSM, 0x1),
-	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_CTRL, 0xa),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_EN_CENTER, 0x1),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER1, 0x31),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER2, 0x1),
@@ -430,7 +431,6 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE1, 0x2f),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE2, 0x19),
 	QMP_PHY_INIT_CFG(QSERDES_COM_CLK_EP_DIV, 0x19),
-	QMP_PHY_INIT_CFG(QSERDES_RX_SIGDET_CNTRL, 0x7),
 };
 
 static const struct qmp_phy_init_tbl ipq8074_pcie_tx_tbl[] = {
@@ -438,6 +438,8 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_tx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_TX_LANE_MODE, 0x6),
 	QMP_PHY_INIT_CFG(QSERDES_TX_RES_CODE_LANE_OFFSET, 0x2),
 	QMP_PHY_INIT_CFG(QSERDES_TX_RCV_DETECT_LVL_2, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_TX_EMP_POST1_LVL, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_TX_SLEW_CNTL, 0x0a),
 };
 
 static const struct qmp_phy_init_tbl ipq8074_pcie_rx_tbl[] = {
@@ -448,7 +450,6 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_rx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL4, 0xdb),
 	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x4b),
 	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN, 0x4),
-	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN_HALF, 0x4),
 };
 
 static const struct qmp_phy_init_tbl ipq8074_pcie_pcs_tbl[] = {
@@ -665,6 +666,9 @@ static const struct qmp_phy_cfg msm8996_usb3phy_cfg = {
 	.mask_pcs_ready		= PHYSTATUS,
 };
 
+static const char * const ipq8074_pciephy_clk_l[] = {
+	"aux", "cfg_ahb",
+};
 /* list of resets */
 static const char * const ipq8074_pciephy_reset_l[] = {
 	"phy", "common",
@@ -682,8 +686,8 @@ static const struct qmp_phy_cfg ipq8074_pciephy_cfg = {
 	.rx_tbl_num		= ARRAY_SIZE(ipq8074_pcie_rx_tbl),
 	.pcs_tbl		= ipq8074_pcie_pcs_tbl,
 	.pcs_tbl_num		= ARRAY_SIZE(ipq8074_pcie_pcs_tbl),
-	.clk_list		= NULL,
-	.num_clks		= 0,
+	.clk_list		= ipq8074_pciephy_clk_l,
+	.num_clks		= ARRAY_SIZE(ipq8074_pciephy_clk_l),
 	.reset_list		= ipq8074_pciephy_reset_l,
 	.num_resets		= ARRAY_SIZE(ipq8074_pciephy_reset_l),
 	.vreg_list		= NULL,
diff --git a/drivers/phy/samsung/phy-s5pv210-usb2.c b/drivers/phy/samsung/phy-s5pv210-usb2.c
index f6f72339bbc3..bb7fdf491c1c 100644
--- a/drivers/phy/samsung/phy-s5pv210-usb2.c
+++ b/drivers/phy/samsung/phy-s5pv210-usb2.c
@@ -142,6 +142,10 @@ static void s5pv210_phy_pwr(struct samsung_usb2_phy_instance *inst, bool on)
 		udelay(10);
 		rst &= ~rstbits;
 		writel(rst, drv->reg_phy + S5PV210_UPHYRST);
+		/* The following delay is necessary for the reset sequence to be
+		 * completed
+		 */
+		udelay(80);
 	} else {
 		pwr = readl(drv->reg_phy + S5PV210_UPHYPWR);
 		pwr |= phypwr;
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 17f2c5a505b2..ec0119e1e781 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -661,16 +661,6 @@ static int imx_pinctrl_probe_dt(struct platform_device *pdev,
 	return 0;
 }
 
-/*
- * imx_free_resources() - free memory used by this driver
- * @info: info driver instance
- */
-static void imx_free_resources(struct imx_pinctrl *ipctl)
-{
-	if (ipctl->pctl)
-		pinctrl_unregister(ipctl->pctl);
-}
-
 int imx_pinctrl_probe(struct platform_device *pdev,
 		      struct imx_pinctrl_soc_info *info)
 {
@@ -761,21 +751,16 @@ int imx_pinctrl_probe(struct platform_device *pdev,
 					     &ipctl->pctl);
 	if (ret) {
 		dev_err(&pdev->dev, "could not register IMX pinctrl driver\n");
-		goto free;
+		return ret;
 	}
 
 	ret = imx_pinctrl_probe_dt(pdev, ipctl);
 	if (ret) {
 		dev_err(&pdev->dev, "fail to probe dt properties\n");
-		goto free;
+		return ret;
 	}
 
 	dev_info(&pdev->dev, "initialized IMX pinctrl driver\n");
 
 	return pinctrl_enable(ipctl->pctl);
-
-free:
-	imx_free_resources(ipctl);
-
-	return ret;
 }
diff --git a/drivers/pinctrl/freescale/pinctrl-imx1-core.c b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
index e2cca91fd266..68108c4c3969 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx1-core.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
@@ -642,7 +642,6 @@ int imx1_pinctrl_core_probe(struct platform_device *pdev,
 
 	ret = of_platform_populate(pdev->dev.of_node, NULL, NULL, &pdev->dev);
 	if (ret) {
-		pinctrl_unregister(ipctl->pctl);
 		dev_err(&pdev->dev, "Failed to populate subdevices\n");
 		return ret;
 	}
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-xp.c b/drivers/pinctrl/mvebu/pinctrl-armada-xp.c
index b854f1ee5de5..4ef3618bca93 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-xp.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-xp.c
@@ -418,7 +418,7 @@ static struct mvebu_mpp_mode mv98dx3236_mpp_modes[] = {
 		 MPP_VAR_FUNCTION(0x1, "i2c0", "sck",        V_98DX3236_PLUS)),
 	MPP_MODE(15,
 		 MPP_VAR_FUNCTION(0x0, "gpio", NULL,         V_98DX3236_PLUS),
-		 MPP_VAR_FUNCTION(0x4, "i2c0", "sda",        V_98DX3236_PLUS)),
+		 MPP_VAR_FUNCTION(0x1, "i2c0", "sda",        V_98DX3236_PLUS)),
 	MPP_MODE(16,
 		 MPP_VAR_FUNCTION(0x0, "gpo", NULL,          V_98DX3236_PLUS),
 		 MPP_VAR_FUNCTION(0x4, "dev", "oe",          V_98DX3236_PLUS)),
diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h
index 8fa453a59da5..884f48f7a6a3 100644
--- a/drivers/pinctrl/pinctrl-amd.h
+++ b/drivers/pinctrl/pinctrl-amd.h
@@ -252,7 +252,7 @@ static const struct amd_pingroup kerncz_groups[] = {
 	{
 		.name = "uart0",
 		.pins = uart0_pins,
-		.npins = 9,
+		.npins = 5,
 	},
 	{
 		.name = "uart1",
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index b8b3d932cd73..f751b5c3bf7e 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -888,7 +888,7 @@ static int pcs_parse_pinconf(struct pcs_device *pcs, struct device_node *np,
 
 	/* If pinconf isn't supported, don't parse properties in below. */
 	if (!PCS_HAS_PINCONF)
-		return 0;
+		return -ENOTSUPP;
 
 	/* cacluate how much properties are supported in current node */
 	for (i = 0; i < ARRAY_SIZE(prop2); i++) {
@@ -900,7 +900,7 @@ static int pcs_parse_pinconf(struct pcs_device *pcs, struct device_node *np,
 			nconfs++;
 	}
 	if (!nconfs)
-		return 0;
+		return -ENOTSUPP;
 
 	func->conf = devm_kzalloc(pcs->dev,
 				  sizeof(struct pcs_conf_vals) * nconfs,
@@ -1024,9 +1024,12 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs,
 
 	if (PCS_HAS_PINCONF) {
 		res = pcs_parse_pinconf(pcs, np, function, map);
-		if (res)
+		if (res == 0)
+			*num_maps = 2;
+		else if (res == -ENOTSUPP)
+			*num_maps = 1;
+		else
 			goto free_pingroups;
-		*num_maps = 2;
 	} else {
 		*num_maps = 1;
 	}
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 1c534d823fd7..6925a3d969e2 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -266,6 +266,7 @@ struct exynos_eint_gpio_save {
 	u32 eint_con;
 	u32 eint_fltcon0;
 	u32 eint_fltcon1;
+	u32 eint_mask;
 };
 
 /*
@@ -561,10 +562,13 @@ static void exynos_pinctrl_suspend_bank(
 						+ 2 * bank->eint_offset);
 	save->eint_fltcon1 = readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
 						+ 2 * bank->eint_offset + 4);
+	save->eint_mask = readl(regs + bank->irq_chip->eint_mask
+						+ bank->eint_offset);
 
 	pr_debug("%s: save     con %#010x\n", bank->name, save->eint_con);
 	pr_debug("%s: save fltcon0 %#010x\n", bank->name, save->eint_fltcon0);
 	pr_debug("%s: save fltcon1 %#010x\n", bank->name, save->eint_fltcon1);
+	pr_debug("%s: save    mask %#010x\n", bank->name, save->eint_mask);
 }
 
 void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata)
@@ -593,6 +597,9 @@ static void exynos_pinctrl_resume_bank(
 	pr_debug("%s: fltcon1 %#010x => %#010x\n", bank->name,
 			readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
 			+ 2 * bank->eint_offset + 4), save->eint_fltcon1);
+	pr_debug("%s:    mask %#010x => %#010x\n", bank->name,
+			readl(regs + bank->irq_chip->eint_mask
+			+ bank->eint_offset), save->eint_mask);
 
 	writel(save->eint_con, regs + EXYNOS_GPIO_ECON_OFFSET
 						+ bank->eint_offset);
@@ -600,6 +607,8 @@ static void exynos_pinctrl_resume_bank(
 						+ 2 * bank->eint_offset);
 	writel(save->eint_fltcon1, regs + EXYNOS_GPIO_EFLTCON_OFFSET
 						+ 2 * bank->eint_offset + 4);
+	writel(save->eint_mask, regs + bank->irq_chip->eint_mask
+						+ bank->eint_offset);
 }
 
 void exynos_pinctrl_resume(struct samsung_pinctrl_drv_data *drvdata)
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 09035705d0a0..4f872e62508a 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -183,6 +183,7 @@ config FUJITSU_LAPTOP
 	depends on BACKLIGHT_CLASS_DEVICE
 	depends on ACPI_VIDEO || ACPI_VIDEO = n
 	select INPUT_SPARSEKMAP
+	select NEW_LEDS
 	select LEDS_CLASS
 	---help---
 	  This is a driver for laptops built by Fujitsu:
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index 06a3c1ef8eee..952544ca0d84 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -474,8 +474,14 @@ static ssize_t postcode_show(struct device *dev, struct device_attribute *attr,
 static ssize_t als_store(struct device *dev, struct device_attribute *attr,
 			 const char *buf, size_t count)
 {
-	u32 tmp = simple_strtoul(buf, NULL, 10);
-	int ret = hp_wmi_perform_query(HPWMI_ALS_QUERY, HPWMI_WRITE, &tmp,
+	u32 tmp;
+	int ret;
+
+	ret = kstrtou32(buf, 10, &tmp);
+	if (ret)
+		return ret;
+
+	ret = hp_wmi_perform_query(HPWMI_ALS_QUERY, HPWMI_WRITE, &tmp,
 				       sizeof(tmp), sizeof(tmp));
 	if (ret)
 		return ret < 0 ? ret : -EINVAL;
diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index e34fd70b67af..3add7b3f9658 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -366,7 +366,7 @@ check_acpi_dev(acpi_handle handle, u32 lvl, void *context, void **rv)
 		return AE_OK;
 
 	if (acpi_match_device_ids(dev, ids) == 0)
-		if (acpi_create_platform_device(dev, NULL))
+		if (!IS_ERR_OR_NULL(acpi_create_platform_device(dev, NULL)))
 			dev_info(&dev->dev,
 				 "intel-hid: created platform device\n");
 
diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c
index 58c5ff36523a..d7fa2b88d27a 100644
--- a/drivers/platform/x86/intel-vbtn.c
+++ b/drivers/platform/x86/intel-vbtn.c
@@ -178,7 +178,7 @@ check_acpi_dev(acpi_handle handle, u32 lvl, void *context, void **rv)
 		return AE_OK;
 
 	if (acpi_match_device_ids(dev, ids) == 0)
-		if (acpi_create_platform_device(dev, NULL))
+		if (!IS_ERR_OR_NULL(acpi_create_platform_device(dev, NULL)))
 			dev_info(&dev->dev,
 				 "intel-vbtn: created platform device\n");
 
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index c3fb9d66b768..ffaaccded34e 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -2477,7 +2477,7 @@ static void hotkey_compare_and_issue_event(struct tp_nvram_state *oldn,
  */
 static int hotkey_kthread(void *data)
 {
-	struct tp_nvram_state s[2];
+	struct tp_nvram_state s[2] = { 0 };
 	u32 poll_mask, event_mask;
 	unsigned int si, so;
 	unsigned long t;
@@ -6749,8 +6749,10 @@ static int __init tpacpi_query_bcl_levels(acpi_handle handle)
 	list_for_each_entry(child, &device->children, node) {
 		acpi_status status = acpi_evaluate_object(child->handle, "_BCL",
 							  NULL, &buffer);
-		if (ACPI_FAILURE(status))
+		if (ACPI_FAILURE(status)) {
+			buffer.length = ACPI_ALLOCATE_BUFFER;
 			continue;
+		}
 
 		obj = (union acpi_object *)buffer.pointer;
 		if (!obj || (obj->type != ACPI_TYPE_PACKAGE)) {
diff --git a/drivers/power/reset/vexpress-poweroff.c b/drivers/power/reset/vexpress-poweroff.c
index e9e749f87517..8fb43c4438e6 100644
--- a/drivers/power/reset/vexpress-poweroff.c
+++ b/drivers/power/reset/vexpress-poweroff.c
@@ -150,6 +150,7 @@ static struct platform_driver vexpress_reset_driver = {
 	.driver = {
 		.name = "vexpress-reset",
 		.of_match_table = vexpress_reset_of_match,
+		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/power/supply/88pm860x_battery.c b/drivers/power/supply/88pm860x_battery.c
index 63c57dc82ac1..4eda5065b5bb 100644
--- a/drivers/power/supply/88pm860x_battery.c
+++ b/drivers/power/supply/88pm860x_battery.c
@@ -436,7 +436,7 @@ static void pm860x_init_battery(struct pm860x_battery_info *info)
 	int ret;
 	int data;
 	int bat_remove;
-	int soc;
+	int soc = 0;
 
 	/* measure enable on GPADC1 */
 	data = MEAS1_GP1;
@@ -499,7 +499,9 @@ static void pm860x_init_battery(struct pm860x_battery_info *info)
 	}
 	mutex_unlock(&info->lock);
 
-	calc_soc(info, OCV_MODE_ACTIVE, &soc);
+	ret = calc_soc(info, OCV_MODE_ACTIVE, &soc);
+	if (ret < 0)
+		goto out;
 
 	data = pm860x_reg_read(info->i2c, PM8607_POWER_UP_LOG);
 	bat_remove = data & BAT_WU_LOG;
diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index 5ab90c1f3f7c..24163cf8612c 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -530,7 +530,7 @@ config CHARGER_BQ24257
 	tristate "TI BQ24250/24251/24257 battery charger driver"
 	depends on I2C
 	depends on GPIOLIB || COMPILE_TEST
-	depends on REGMAP_I2C
+	select REGMAP_I2C
 	help
 	  Say Y to enable support for the TI BQ24250, BQ24251, and BQ24257 battery
 	  chargers.
diff --git a/drivers/power/supply/lp8788-charger.c b/drivers/power/supply/lp8788-charger.c
index 0f3432795f3c..b8f7dac7ac3f 100644
--- a/drivers/power/supply/lp8788-charger.c
+++ b/drivers/power/supply/lp8788-charger.c
@@ -600,27 +600,14 @@ static void lp8788_setup_adc_channel(struct device *dev,
 		return;
 
 	/* ADC channel for battery voltage */
-	chan = iio_channel_get(dev, pdata->adc_vbatt);
+	chan = devm_iio_channel_get(dev, pdata->adc_vbatt);
 	pchg->chan[LP8788_VBATT] = IS_ERR(chan) ? NULL : chan;
 
 	/* ADC channel for battery temperature */
-	chan = iio_channel_get(dev, pdata->adc_batt_temp);
+	chan = devm_iio_channel_get(dev, pdata->adc_batt_temp);
 	pchg->chan[LP8788_BATT_TEMP] = IS_ERR(chan) ? NULL : chan;
 }
 
-static void lp8788_release_adc_channel(struct lp8788_charger *pchg)
-{
-	int i;
-
-	for (i = 0; i < LP8788_NUM_CHG_ADC; i++) {
-		if (!pchg->chan[i])
-			continue;
-
-		iio_channel_release(pchg->chan[i]);
-		pchg->chan[i] = NULL;
-	}
-}
-
 static ssize_t lp8788_show_charger_status(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -747,7 +734,6 @@ static int lp8788_charger_remove(struct platform_device *pdev)
 	lp8788_irq_unregister(pdev, pchg);
 	sysfs_remove_group(&pdev->dev.kobj, &lp8788_attr_group);
 	lp8788_psy_unregister(pchg);
-	lp8788_release_adc_channel(pchg);
 
 	return 0;
 }
diff --git a/drivers/power/supply/max17040_battery.c b/drivers/power/supply/max17040_battery.c
index 33c40f79d23d..2c35c13ad546 100644
--- a/drivers/power/supply/max17040_battery.c
+++ b/drivers/power/supply/max17040_battery.c
@@ -109,7 +109,7 @@ static void max17040_get_vcell(struct i2c_client *client)
 
 	vcell = max17040_read_reg(client, MAX17040_VCELL);
 
-	chip->vcell = vcell;
+	chip->vcell = (vcell >> 4) * 1250;
 }
 
 static void max17040_get_soc(struct i2c_client *client)
diff --git a/drivers/power/supply/smb347-charger.c b/drivers/power/supply/smb347-charger.c
index 072c5189bd6d..0655dbdc7000 100644
--- a/drivers/power/supply/smb347-charger.c
+++ b/drivers/power/supply/smb347-charger.c
@@ -1141,6 +1141,7 @@ static bool smb347_volatile_reg(struct device *dev, unsigned int reg)
 	switch (reg) {
 	case IRQSTAT_A:
 	case IRQSTAT_C:
+	case IRQSTAT_D:
 	case IRQSTAT_E:
 	case IRQSTAT_F:
 	case STAT_A:
diff --git a/drivers/pwm/pwm-bcm-iproc.c b/drivers/pwm/pwm-bcm-iproc.c
index 31b01035d0ab..8cfba3614e60 100644
--- a/drivers/pwm/pwm-bcm-iproc.c
+++ b/drivers/pwm/pwm-bcm-iproc.c
@@ -85,8 +85,6 @@ static void iproc_pwmc_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
 	u64 tmp, multi, rate;
 	u32 value, prescale;
 
-	rate = clk_get_rate(ip->clk);
-
 	value = readl(ip->base + IPROC_PWM_CTRL_OFFSET);
 
 	if (value & BIT(IPROC_PWM_CTRL_EN_SHIFT(pwm->hwpwm)))
@@ -99,6 +97,13 @@ static void iproc_pwmc_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
 	else
 		state->polarity = PWM_POLARITY_INVERSED;
 
+	rate = clk_get_rate(ip->clk);
+	if (rate == 0) {
+		state->period = 0;
+		state->duty_cycle = 0;
+		return;
+	}
+
 	value = readl(ip->base + IPROC_PWM_PRESCALE_OFFSET);
 	prescale = value >> IPROC_PWM_PRESCALE_SHIFT(pwm->hwpwm);
 	prescale &= IPROC_PWM_PRESCALE_MAX;
diff --git a/drivers/rapidio/Kconfig b/drivers/rapidio/Kconfig
index d6d2f20c4597..21df2816def7 100644
--- a/drivers/rapidio/Kconfig
+++ b/drivers/rapidio/Kconfig
@@ -25,7 +25,7 @@ config RAPIDIO_ENABLE_RX_TX_PORTS
 config RAPIDIO_DMA_ENGINE
 	bool "DMA Engine support for RapidIO"
 	depends on RAPIDIO
-	select DMADEVICES
+	depends on DMADEVICES
 	select DMA_ENGINE
 	help
 	  Say Y here if you want to use DMA Engine frameork for RapidIO data
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index f15f6d1e1070..f207f8725993 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -2464,13 +2464,6 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport)
 	cdev_init(&md->cdev, &mport_fops);
 	md->cdev.owner = THIS_MODULE;
 
-	ret = cdev_device_add(&md->cdev, &md->dev);
-	if (ret) {
-		rmcd_error("Failed to register mport %d (err=%d)",
-		       mport->id, ret);
-		goto err_cdev;
-	}
-
 	INIT_LIST_HEAD(&md->doorbells);
 	spin_lock_init(&md->db_lock);
 	INIT_LIST_HEAD(&md->portwrites);
@@ -2490,6 +2483,13 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport)
 #else
 	md->properties.transfer_mode |= RIO_TRANSFER_MODE_TRANSFER;
 #endif
+
+	ret = cdev_device_add(&md->cdev, &md->dev);
+	if (ret) {
+		rmcd_error("Failed to register mport %d (err=%d)",
+		       mport->id, ret);
+		goto err_cdev;
+	}
 	ret = rio_query_mport(mport, &attr);
 	if (!ret) {
 		md->properties.flags = attr.flags;
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index b2cb4f497ef6..bd6991a99593 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1192,7 +1192,7 @@ static int set_consumer_device_supply(struct regulator_dev *rdev,
 				      const char *consumer_dev_name,
 				      const char *supply)
 {
-	struct regulator_map *node;
+	struct regulator_map *node, *new_node;
 	int has_dev;
 
 	if (supply == NULL)
@@ -1203,6 +1203,22 @@ static int set_consumer_device_supply(struct regulator_dev *rdev,
 	else
 		has_dev = 0;
 
+	new_node = kzalloc(sizeof(struct regulator_map), GFP_KERNEL);
+	if (new_node == NULL)
+		return -ENOMEM;
+
+	new_node->regulator = rdev;
+	new_node->supply = supply;
+
+	if (has_dev) {
+		new_node->dev_name = kstrdup(consumer_dev_name, GFP_KERNEL);
+		if (new_node->dev_name == NULL) {
+			kfree(new_node);
+			return -ENOMEM;
+		}
+	}
+
+	mutex_lock(&regulator_list_mutex);
 	list_for_each_entry(node, &regulator_map_list, list) {
 		if (node->dev_name && consumer_dev_name) {
 			if (strcmp(node->dev_name, consumer_dev_name) != 0)
@@ -1220,26 +1236,19 @@ static int set_consumer_device_supply(struct regulator_dev *rdev,
 			 node->regulator->desc->name,
 			 supply,
 			 dev_name(&rdev->dev), rdev_get_name(rdev));
-		return -EBUSY;
+		goto fail;
 	}
 
-	node = kzalloc(sizeof(struct regulator_map), GFP_KERNEL);
-	if (node == NULL)
-		return -ENOMEM;
-
-	node->regulator = rdev;
-	node->supply = supply;
-
-	if (has_dev) {
-		node->dev_name = kstrdup(consumer_dev_name, GFP_KERNEL);
-		if (node->dev_name == NULL) {
-			kfree(node);
-			return -ENOMEM;
-		}
-	}
+	list_add(&new_node->list, &regulator_map_list);
+	mutex_unlock(&regulator_list_mutex);
 
-	list_add(&node->list, &regulator_map_list);
 	return 0;
+
+fail:
+	mutex_unlock(&regulator_list_mutex);
+	kfree(new_node->dev_name);
+	kfree(new_node);
+	return -EBUSY;
 }
 
 static void unset_regulator_supplies(struct regulator_dev *rdev)
@@ -4095,19 +4104,16 @@ regulator_register(const struct regulator_desc *regulator_desc,
 
 	/* add consumers devices */
 	if (init_data) {
-		mutex_lock(&regulator_list_mutex);
 		for (i = 0; i < init_data->num_consumer_supplies; i++) {
 			ret = set_consumer_device_supply(rdev,
 				init_data->consumer_supplies[i].dev_name,
 				init_data->consumer_supplies[i].supply);
 			if (ret < 0) {
-				mutex_unlock(&regulator_list_mutex);
 				dev_err(dev, "Failed to set supply %s\n",
 					init_data->consumer_supplies[i].supply);
 				goto unset_supplies;
 			}
 		}
-		mutex_unlock(&regulator_list_mutex);
 	}
 
 	if (!rdev->desc->ops->get_voltage &&
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 8f4fa1a52f05..d6372470e5be 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1432,6 +1432,7 @@ struct rproc *rproc_alloc(struct device *dev, const char *name,
 	rproc->dev.type = &rproc_type;
 	rproc->dev.class = &rproc_class;
 	rproc->dev.driver_data = rproc;
+	idr_init(&rproc->notifyids);
 
 	/* Assign a unique device index and name */
 	rproc->index = ida_simple_get(&rproc_dev_index, 0, 0, GFP_KERNEL);
@@ -1450,8 +1451,6 @@ struct rproc *rproc_alloc(struct device *dev, const char *name,
 
 	mutex_init(&rproc->lock);
 
-	idr_init(&rproc->notifyids);
-
 	INIT_LIST_HEAD(&rproc->carveouts);
 	INIT_LIST_HEAD(&rproc->mappings);
 	INIT_LIST_HEAD(&rproc->traces);
diff --git a/drivers/rtc/rtc-ds1374.c b/drivers/rtc/rtc-ds1374.c
index 38a2e9e684df..77a106e90124 100644
--- a/drivers/rtc/rtc-ds1374.c
+++ b/drivers/rtc/rtc-ds1374.c
@@ -620,6 +620,10 @@ static int ds1374_probe(struct i2c_client *client,
 	if (!ds1374)
 		return -ENOMEM;
 
+	ds1374->rtc = devm_rtc_allocate_device(&client->dev);
+	if (IS_ERR(ds1374->rtc))
+		return PTR_ERR(ds1374->rtc);
+
 	ds1374->client = client;
 	i2c_set_clientdata(client, ds1374);
 
@@ -641,12 +645,11 @@ static int ds1374_probe(struct i2c_client *client,
 		device_set_wakeup_capable(&client->dev, 1);
 	}
 
-	ds1374->rtc = devm_rtc_device_register(&client->dev, client->name,
-						&ds1374_rtc_ops, THIS_MODULE);
-	if (IS_ERR(ds1374->rtc)) {
-		dev_err(&client->dev, "unable to register the class device\n");
-		return PTR_ERR(ds1374->rtc);
-	}
+	ds1374->rtc->ops = &ds1374_rtc_ops;
+
+	ret = rtc_register_device(ds1374->rtc);
+	if (ret)
+		return ret;
 
 #ifdef CONFIG_RTC_DRV_DS1374_WDT
 	save_client = client;
diff --git a/drivers/rtc/rtc-goldfish.c b/drivers/rtc/rtc-goldfish.c
index a1c44d0c8557..30cbe22c57a8 100644
--- a/drivers/rtc/rtc-goldfish.c
+++ b/drivers/rtc/rtc-goldfish.c
@@ -87,6 +87,7 @@ static int goldfish_rtc_set_alarm(struct device *dev,
 		rtc_alarm64 = rtc_alarm * NSEC_PER_SEC;
 		writel((rtc_alarm64 >> 32), base + TIMER_ALARM_HIGH);
 		writel(rtc_alarm64, base + TIMER_ALARM_LOW);
+		writel(1, base + TIMER_IRQ_ENABLED);
 	} else {
 		/*
 		 * if this function was called with enabled=0
diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c
index 6168ccdb389c..91a569c10dea 100644
--- a/drivers/s390/block/dasd_fba.c
+++ b/drivers/s390/block/dasd_fba.c
@@ -39,6 +39,7 @@
 MODULE_LICENSE("GPL");
 
 static struct dasd_discipline dasd_fba_discipline;
+static void *dasd_fba_zero_page;
 
 struct dasd_fba_private {
 	struct dasd_fba_characteristics rdc_data;
@@ -269,7 +270,7 @@ static void ccw_write_zero(struct ccw1 *ccw, int count)
 	ccw->cmd_code = DASD_FBA_CCW_WRITE;
 	ccw->flags |= CCW_FLAG_SLI;
 	ccw->count = count;
-	ccw->cda = (__u32) (addr_t) page_to_phys(ZERO_PAGE(0));
+	ccw->cda = (__u32) (addr_t) dasd_fba_zero_page;
 }
 
 /*
@@ -808,6 +809,11 @@ dasd_fba_init(void)
 	int ret;
 
 	ASCEBC(dasd_fba_discipline.ebcname, 4);
+
+	dasd_fba_zero_page = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!dasd_fba_zero_page)
+		return -ENOMEM;
+
 	ret = ccw_driver_register(&dasd_fba_driver);
 	if (!ret)
 		wait_for_device_probe();
@@ -819,6 +825,7 @@ static void __exit
 dasd_fba_cleanup(void)
 {
 	ccw_driver_unregister(&dasd_fba_driver);
+	free_page((unsigned long)dasd_fba_zero_page);
 }
 
 module_init(dasd_fba_init);
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index dadff1838fec..e2026d54dd37 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -581,6 +581,11 @@ static int slow_eval_known_fn(struct subchannel *sch, void *data)
 		rc = css_evaluate_known_subchannel(sch, 1);
 		if (rc == -EAGAIN)
 			css_schedule_eval(sch->schid);
+		/*
+		 * The loop might take long time for platforms with lots of
+		 * known devices. Allow scheduling here.
+		 */
+		cond_resched();
 	}
 	return 0;
 }
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index 29d6b5222f1c..0f8d13288611 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -377,7 +377,6 @@ static inline int multicast_outbound(struct qdio_q *q)
 extern u64 last_ai_time;
 
 /* prototypes for thin interrupt */
-void qdio_setup_thinint(struct qdio_irq *irq_ptr);
 int qdio_establish_thinint(struct qdio_irq *irq_ptr);
 void qdio_shutdown_thinint(struct qdio_irq *irq_ptr);
 void tiqdio_add_input_queues(struct qdio_irq *irq_ptr);
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index d0090c5c88e7..a64615a10352 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -479,7 +479,6 @@ int qdio_setup_irq(struct qdio_initialize *init_data)
 	setup_queues(irq_ptr, init_data);
 
 	setup_qib(irq_ptr, init_data);
-	qdio_setup_thinint(irq_ptr);
 	set_impl_params(irq_ptr, init_data->qib_param_field_format,
 			init_data->qib_param_field,
 			init_data->input_slib_elements,
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index 831a3a0a2837..4dc1108069d4 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -270,17 +270,19 @@ int __init tiqdio_register_thinints(void)
 
 int qdio_establish_thinint(struct qdio_irq *irq_ptr)
 {
+	int rc;
+
 	if (!is_thinint_irq(irq_ptr))
 		return 0;
-	return set_subchannel_ind(irq_ptr, 0);
-}
 
-void qdio_setup_thinint(struct qdio_irq *irq_ptr)
-{
-	if (!is_thinint_irq(irq_ptr))
-		return;
 	irq_ptr->dsci = get_indicator();
 	DBF_HEX(&irq_ptr->dsci, sizeof(void *));
+
+	rc = set_subchannel_ind(irq_ptr, 0);
+	if (rc)
+		put_indicator(irq_ptr->dsci);
+
+	return rc;
 }
 
 void qdio_shutdown_thinint(struct qdio_irq *irq_ptr)
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 6fa07c246915..ae310d5ced10 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1559,6 +1559,10 @@ static void qeth_bridge_state_change(struct qeth_card *card,
 	int extrasize;
 
 	QETH_CARD_TEXT(card, 2, "brstchng");
+	if (qports->num_entries == 0) {
+		QETH_CARD_TEXT(card, 2, "BPempty");
+		return;
+	}
 	if (qports->entry_length != sizeof(struct qeth_sbp_port_entry)) {
 		QETH_CARD_TEXT_(card, 2, "BPsz%04x", qports->entry_length);
 		return;
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 94d1bcc83fa2..119238faf1ac 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -1594,6 +1594,7 @@ int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 {
 	struct zfcp_qdio *qdio = wka_port->adapter->qdio;
 	struct zfcp_fsf_req *req;
+	unsigned long req_id = 0;
 	int retval = -EIO;
 
 	spin_lock_irq(&qdio->req_q_lock);
@@ -1616,6 +1617,8 @@ int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 	hton24(req->qtcb->bottom.support.d_id, wka_port->d_id);
 	req->data = wka_port;
 
+	req_id = req->req_id;
+
 	zfcp_fsf_start_timer(req, ZFCP_FSF_REQUEST_TIMEOUT);
 	retval = zfcp_fsf_req_send(req);
 	if (retval)
@@ -1623,7 +1626,7 @@ int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 out:
 	spin_unlock_irq(&qdio->req_q_lock);
 	if (!retval)
-		zfcp_dbf_rec_run_wka("fsowp_1", wka_port, req->req_id);
+		zfcp_dbf_rec_run_wka("fsowp_1", wka_port, req_id);
 	return retval;
 }
 
@@ -1649,6 +1652,7 @@ int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 {
 	struct zfcp_qdio *qdio = wka_port->adapter->qdio;
 	struct zfcp_fsf_req *req;
+	unsigned long req_id = 0;
 	int retval = -EIO;
 
 	spin_lock_irq(&qdio->req_q_lock);
@@ -1671,6 +1675,8 @@ int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 	req->data = wka_port;
 	req->qtcb->header.port_handle = wka_port->handle;
 
+	req_id = req->req_id;
+
 	zfcp_fsf_start_timer(req, ZFCP_FSF_REQUEST_TIMEOUT);
 	retval = zfcp_fsf_req_send(req);
 	if (retval)
@@ -1678,7 +1684,7 @@ int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 out:
 	spin_unlock_irq(&qdio->req_q_lock);
 	if (!retval)
-		zfcp_dbf_rec_run_wka("fscwp_1", wka_port, req->req_id);
+		zfcp_dbf_rec_run_wka("fscwp_1", wka_port, req_id);
 	return retval;
 }
 
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 7173ae53c526..ba1131356881 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -2322,13 +2322,13 @@ static int aac_read(struct scsi_cmnd * scsicmd)
 		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
 			SAM_STAT_CHECK_CONDITION;
 		set_sense(&dev->fsa_dev[cid].sense_data,
-			  HARDWARE_ERROR, SENCODE_INTERNAL_TARGET_FAILURE,
+			  ILLEGAL_REQUEST, SENCODE_LBA_OUT_OF_RANGE,
 			  ASENCODE_INTERNAL_TARGET_FAILURE, 0, 0);
 		memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data,
 		       min_t(size_t, sizeof(dev->fsa_dev[cid].sense_data),
 			     SCSI_SENSE_BUFFERSIZE));
 		scsicmd->scsi_done(scsicmd);
-		return 1;
+		return 0;
 	}
 
 	dprintk((KERN_DEBUG "aac_read[cpu %d]: lba = %llu, t = %ld.\n",
@@ -2414,13 +2414,13 @@ static int aac_write(struct scsi_cmnd * scsicmd)
 		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
 			SAM_STAT_CHECK_CONDITION;
 		set_sense(&dev->fsa_dev[cid].sense_data,
-			  HARDWARE_ERROR, SENCODE_INTERNAL_TARGET_FAILURE,
+			  ILLEGAL_REQUEST, SENCODE_LBA_OUT_OF_RANGE,
 			  ASENCODE_INTERNAL_TARGET_FAILURE, 0, 0);
 		memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data,
 		       min_t(size_t, sizeof(dev->fsa_dev[cid].sense_data),
 			     SCSI_SENSE_BUFFERSIZE));
 		scsicmd->scsi_done(scsicmd);
-		return 1;
+		return 0;
 	}
 
 	dprintk((KERN_DEBUG "aac_write[cpu %d]: lba = %llu, t = %ld.\n",
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index a284527999c5..65a5cd6a5f96 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -771,7 +771,7 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback,
 		hbacmd->request_id =
 			cpu_to_le32((((u32)(fibptr - dev->fibs)) << 2) + 1);
 		fibptr->flags |= FIB_CONTEXT_FLAG_SCSI_CMD;
-	} else if (command != HBA_IU_TYPE_SCSI_TM_REQ)
+	} else
 		return -EINVAL;
 
 
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 053a31c5485f..e0e728d0dd5e 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -736,7 +736,11 @@ static int aac_eh_abort(struct scsi_cmnd* cmd)
 		status = aac_hba_send(HBA_IU_TYPE_SCSI_TM_REQ, fib,
 				  (fib_callback) aac_hba_callback,
 				  (void *) cmd);
-
+		if (status != -EINPROGRESS) {
+			aac_fib_complete(fib);
+			aac_fib_free(fib);
+			return ret;
+		}
 		/* Wait up to 15 secs for completion */
 		for (count = 0; count < 15; ++count) {
 			if (cmd->SCp.sent_command) {
@@ -915,11 +919,11 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd)
 
 	info = &aac->hba_map[bus][cid];
 
-	if (info->devtype != AAC_DEVTYPE_NATIVE_RAW &&
-	    info->reset_state > 0)
+	if (!(info->devtype == AAC_DEVTYPE_NATIVE_RAW &&
+	 !(info->reset_state > 0)))
 		return FAILED;
 
-	pr_err("%s: Host adapter reset request. SCSI hang ?\n",
+	pr_err("%s: Host device reset request. SCSI hang ?\n",
 	       AAC_DRIVERNAME);
 
 	fib = aac_fib_alloc(aac);
@@ -934,7 +938,12 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd)
 	status = aac_hba_send(command, fib,
 			      (fib_callback) aac_tmf_callback,
 			      (void *) info);
-
+	if (status != -EINPROGRESS) {
+		info->reset_state = 0;
+		aac_fib_complete(fib);
+		aac_fib_free(fib);
+		return ret;
+	}
 	/* Wait up to 15 seconds for completion */
 	for (count = 0; count < 15; ++count) {
 		if (info->reset_state == 0) {
@@ -973,11 +982,11 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd)
 
 	info = &aac->hba_map[bus][cid];
 
-	if (info->devtype != AAC_DEVTYPE_NATIVE_RAW &&
-	    info->reset_state > 0)
+	if (!(info->devtype == AAC_DEVTYPE_NATIVE_RAW &&
+	 !(info->reset_state > 0)))
 		return FAILED;
 
-	pr_err("%s: Host adapter reset request. SCSI hang ?\n",
+	pr_err("%s: Host target reset request. SCSI hang ?\n",
 	       AAC_DRIVERNAME);
 
 	fib = aac_fib_alloc(aac);
@@ -994,6 +1003,13 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd)
 			      (fib_callback) aac_tmf_callback,
 			      (void *) info);
 
+	if (status != -EINPROGRESS) {
+		info->reset_state = 0;
+		aac_fib_complete(fib);
+		aac_fib_free(fib);
+		return ret;
+	}
+
 	/* Wait up to 15 seconds for completion */
 	for (count = 0; count < 15; ++count) {
 		if (info->reset_state <= 0) {
@@ -1046,7 +1062,7 @@ static int aac_eh_bus_reset(struct scsi_cmnd* cmd)
 		}
 	}
 
-	pr_err("%s: Host adapter reset request. SCSI hang ?\n", AAC_DRIVERNAME);
+	pr_err("%s: Host bus reset request. SCSI hang ?\n", AAC_DRIVERNAME);
 
 	/*
 	 * Check the health of the controller
diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c
index 421fe869a11e..ef9d907f2df5 100644
--- a/drivers/scsi/arm/acornscsi.c
+++ b/drivers/scsi/arm/acornscsi.c
@@ -2914,8 +2914,10 @@ static int acornscsi_probe(struct expansion_card *ec, const struct ecard_id *id)
 
 	ashost->base = ecardm_iomap(ec, ECARD_RES_MEMC, 0, 0);
 	ashost->fast = ecardm_iomap(ec, ECARD_RES_IOCFAST, 0, 0);
-	if (!ashost->base || !ashost->fast)
+	if (!ashost->base || !ashost->fast) {
+		ret = -ENOMEM;
 		goto out_put;
+	}
 
 	host->irq = ec->irq;
 	ashost->host = host;
diff --git a/drivers/scsi/arm/cumana_2.c b/drivers/scsi/arm/cumana_2.c
index edce5f3cfdba..93ba83e3148e 100644
--- a/drivers/scsi/arm/cumana_2.c
+++ b/drivers/scsi/arm/cumana_2.c
@@ -454,7 +454,7 @@ static int cumanascsi2_probe(struct expansion_card *ec,
 
 	if (info->info.scsi.dma != NO_DMA)
 		free_dma(info->info.scsi.dma);
-	free_irq(ec->irq, host);
+	free_irq(ec->irq, info);
 
  out_release:
 	fas216_release(host);
diff --git a/drivers/scsi/arm/eesox.c b/drivers/scsi/arm/eesox.c
index e93e047f4316..65bb34ce93b9 100644
--- a/drivers/scsi/arm/eesox.c
+++ b/drivers/scsi/arm/eesox.c
@@ -575,7 +575,7 @@ static int eesoxscsi_probe(struct expansion_card *ec, const struct ecard_id *id)
 
 	if (info->info.scsi.dma != NO_DMA)
 		free_dma(info->info.scsi.dma);
-	free_irq(ec->irq, host);
+	free_irq(ec->irq, info);
 
  out_remove:
 	fas216_remove(host);
diff --git a/drivers/scsi/arm/powertec.c b/drivers/scsi/arm/powertec.c
index 79aa88911b7f..b5e4a25ea1ef 100644
--- a/drivers/scsi/arm/powertec.c
+++ b/drivers/scsi/arm/powertec.c
@@ -382,7 +382,7 @@ static int powertecscsi_probe(struct expansion_card *ec,
 
 	if (info->info.scsi.dma != NO_DMA)
 		free_dma(info->info.scsi.dma);
-	free_irq(ec->irq, host);
+	free_irq(ec->irq, info);
 
  out_release:
 	fas216_release(host);
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index d95ba1a07ba3..eaab59afd90c 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -267,9 +267,9 @@ static void fcoe_sysfs_fcf_del(struct fcoe_fcf *new)
 		WARN_ON(!fcf_dev);
 		new->fcf_dev = NULL;
 		fcoe_fcf_device_delete(fcf_dev);
-		kfree(new);
 		mutex_unlock(&cdev->lock);
 	}
+	kfree(new);
 }
 
 /**
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index d79ac0b24f5a..04c25ca2be45 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -1034,7 +1034,8 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic,
 		atomic64_inc(&fnic_stats->io_stats.io_completions);
 
 
-	io_duration_time = jiffies_to_msecs(jiffies) - jiffies_to_msecs(io_req->start_time);
+	io_duration_time = jiffies_to_msecs(jiffies) -
+						jiffies_to_msecs(start_time);
 
 	if(io_duration_time <= 10)
 		atomic64_inc(&fnic_stats->io_stats.io_btw_0_to_10_msec);
diff --git a/drivers/scsi/gdth.h b/drivers/scsi/gdth.h
index 95fc720c1b30..e6e5ccb1e0f3 100644
--- a/drivers/scsi/gdth.h
+++ b/drivers/scsi/gdth.h
@@ -178,9 +178,6 @@
 #define MSG_SIZE        34                      /* size of message structure */
 #define MSG_REQUEST     0                       /* async. event: message */
 
-/* cacheservice defines */
-#define SECTOR_SIZE     0x200                   /* always 512 bytes per sec. */
-
 /* DPMEM constants */
 #define DPMEM_MAGIC     0xC0FFEE11
 #define IC_HEADER_BYTES 48
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index b167411580ba..dd918c5d5cb8 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -655,12 +655,13 @@ static void hisi_sas_port_notify_formed(struct asd_sas_phy *sas_phy)
 	struct hisi_hba *hisi_hba = sas_ha->lldd_ha;
 	struct hisi_sas_phy *phy = sas_phy->lldd_phy;
 	struct asd_sas_port *sas_port = sas_phy->port;
-	struct hisi_sas_port *port = to_hisi_sas_port(sas_port);
+	struct hisi_sas_port *port;
 	unsigned long flags;
 
 	if (!sas_port)
 		return;
 
+	port = to_hisi_sas_port(sas_port);
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	port->port_attached = 1;
 	port->id = phy->port_id;
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 83645a1c6f82..aff868afe68d 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -429,6 +429,8 @@ static int ibmvscsi_reenable_crq_queue(struct crq_queue *queue,
 	int rc = 0;
 	struct vio_dev *vdev = to_vio_dev(hostdata->dev);
 
+	set_adapter_info(hostdata);
+
 	/* Re-enable the CRQ */
 	do {
 		if (rc)
diff --git a/drivers/scsi/iscsi_boot_sysfs.c b/drivers/scsi/iscsi_boot_sysfs.c
index d453667612f8..15d64f96e623 100644
--- a/drivers/scsi/iscsi_boot_sysfs.c
+++ b/drivers/scsi/iscsi_boot_sysfs.c
@@ -360,7 +360,7 @@ iscsi_boot_create_kobj(struct iscsi_boot_kset *boot_kset,
 	boot_kobj->kobj.kset = boot_kset->kset;
 	if (kobject_init_and_add(&boot_kobj->kobj, &iscsi_boot_ktype,
 				 NULL, name, index)) {
-		kfree(boot_kobj);
+		kobject_put(&boot_kobj->kobj);
 		return NULL;
 	}
 	boot_kobj->data = data;
diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index 28b50ab2fbb0..0db0d0ad9f96 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -605,8 +605,12 @@ static void fc_disc_gpn_id_resp(struct fc_seq *sp, struct fc_frame *fp,
 
 	if (PTR_ERR(fp) == -FC_EX_CLOSED)
 		goto out;
-	if (IS_ERR(fp))
-		goto redisc;
+	if (IS_ERR(fp)) {
+		mutex_lock(&disc->disc_mutex);
+		fc_disc_restart(disc);
+		mutex_unlock(&disc->disc_mutex);
+		goto out;
+	}
 
 	cp = fc_frame_payload_get(fp, sizeof(*cp));
 	if (!cp)
@@ -633,7 +637,7 @@ static void fc_disc_gpn_id_resp(struct fc_seq *sp, struct fc_frame *fp,
 				new_rdata->disc_id = disc->disc_id;
 				fc_rport_login(new_rdata);
 			}
-			goto out;
+			goto free_fp;
 		}
 		rdata->disc_id = disc->disc_id;
 		mutex_unlock(&rdata->rp_mutex);
@@ -650,10 +654,10 @@ redisc:
 		fc_disc_restart(disc);
 		mutex_unlock(&disc->disc_mutex);
 	}
+free_fp:
+	fc_frame_free(fp);
 out:
 	kref_put(&rdata->kref, fc_rport_destroy);
-	if (!IS_ERR(fp))
-		fc_frame_free(fp);
 }
 
 /**
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 0e964ce75406..669cf3553a77 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -145,8 +145,10 @@ struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id)
 	size_t rport_priv_size = sizeof(*rdata);
 
 	rdata = fc_rport_lookup(lport, port_id);
-	if (rdata)
+	if (rdata) {
+		kref_put(&rdata->kref, fc_rport_destroy);
 		return rdata;
+	}
 
 	if (lport->rport_priv_size > 0)
 		rport_priv_size = lport->rport_priv_size;
@@ -493,10 +495,11 @@ static void fc_rport_enter_delete(struct fc_rport_priv *rdata,
 
 	fc_rport_state_enter(rdata, RPORT_ST_DELETE);
 
-	kref_get(&rdata->kref);
-	if (rdata->event == RPORT_EV_NONE &&
-	    !queue_work(rport_event_queue, &rdata->event_work))
-		kref_put(&rdata->kref, fc_rport_destroy);
+	if (rdata->event == RPORT_EV_NONE) {
+		kref_get(&rdata->kref);
+		if (!queue_work(rport_event_queue, &rdata->event_work))
+			kref_put(&rdata->kref, fc_rport_destroy);
+	}
 
 	rdata->event = event;
 }
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 70be4425ae0b..470e11b42820 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -227,7 +227,10 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 		task->num_scatter = si;
 	}
 
-	task->data_dir = qc->dma_dir;
+	if (qc->tf.protocol == ATA_PROT_NODATA)
+		task->data_dir = DMA_NONE;
+	else
+		task->data_dir = qc->dma_dir;
 	task->scatter = qc->sg;
 	task->ata_task.retry_count = 1;
 	task->task_state_flags = SAS_TASK_STATE_PENDING;
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 601a4ee60de8..e193fa5963d8 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -1714,8 +1714,8 @@ lpfc_fdmi_hba_attr_wwnn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_def *ad)
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, sizeof(struct lpfc_name));
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrWWN, &vport->fc_sparam.nodeName,
 	       sizeof(struct lpfc_name));
@@ -1731,8 +1731,8 @@ lpfc_fdmi_hba_attr_manufacturer(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	/* This string MUST be consistent with other FC platforms
 	 * supported by Broadcom.
@@ -1756,8 +1756,8 @@ lpfc_fdmi_hba_attr_sn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_def *ad)
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, phba->SerialNumber,
 		sizeof(ae->un.AttrString));
@@ -1778,8 +1778,8 @@ lpfc_fdmi_hba_attr_model(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, phba->ModelName,
 		sizeof(ae->un.AttrString));
@@ -1799,8 +1799,8 @@ lpfc_fdmi_hba_attr_description(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, phba->ModelDesc,
 		sizeof(ae->un.AttrString));
@@ -1822,8 +1822,8 @@ lpfc_fdmi_hba_attr_hdw_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t i, j, incr, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	/* Convert JEDEC ID to ascii for hardware version */
 	incr = vp->rev.biuRev;
@@ -1852,8 +1852,8 @@ lpfc_fdmi_hba_attr_drvr_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, lpfc_release_version,
 		sizeof(ae->un.AttrString));
@@ -1874,8 +1874,8 @@ lpfc_fdmi_hba_attr_rom_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	if (phba->sli_rev == LPFC_SLI_REV4)
 		lpfc_decode_firmware_rev(phba, ae->un.AttrString, 1);
@@ -1899,8 +1899,8 @@ lpfc_fdmi_hba_attr_fmw_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	lpfc_decode_firmware_rev(phba, ae->un.AttrString, 1);
 	len = strnlen(ae->un.AttrString,
@@ -1919,8 +1919,8 @@ lpfc_fdmi_hba_attr_os_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s %s %s",
 		 init_utsname()->sysname,
@@ -1942,7 +1942,7 @@ lpfc_fdmi_hba_attr_ct_len(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	ae->un.AttrInt =  cpu_to_be32(LPFC_MAX_CT_SIZE);
 	size = FOURBYTES + sizeof(uint32_t);
@@ -1958,8 +1958,8 @@ lpfc_fdmi_hba_attr_symbolic_name(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	len = lpfc_vport_symbolic_node_name(vport,
 				ae->un.AttrString, 256);
@@ -1977,7 +1977,7 @@ lpfc_fdmi_hba_attr_vendor_info(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	/* Nothing is defined for this currently */
 	ae->un.AttrInt =  cpu_to_be32(0);
@@ -1994,7 +1994,7 @@ lpfc_fdmi_hba_attr_num_ports(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	/* Each driver instance corresponds to a single port */
 	ae->un.AttrInt =  cpu_to_be32(1);
@@ -2011,8 +2011,8 @@ lpfc_fdmi_hba_attr_fabric_wwnn(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, sizeof(struct lpfc_name));
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrWWN, &vport->fabric_nodename,
 	       sizeof(struct lpfc_name));
@@ -2030,8 +2030,8 @@ lpfc_fdmi_hba_attr_bios_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	lpfc_decode_firmware_rev(phba, ae->un.AttrString, 1);
 	len = strnlen(ae->un.AttrString,
@@ -2050,7 +2050,7 @@ lpfc_fdmi_hba_attr_bios_state(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	/* Driver doesn't have access to this information */
 	ae->un.AttrInt =  cpu_to_be32(0);
@@ -2067,8 +2067,8 @@ lpfc_fdmi_hba_attr_vendor_id(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, "EMULEX",
 		sizeof(ae->un.AttrString));
@@ -2089,8 +2089,8 @@ lpfc_fdmi_port_attr_fc4type(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 32);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	ae->un.AttrTypes[3] = 0x02; /* Type 0x1 - ELS */
 	ae->un.AttrTypes[2] = 0x01; /* Type 0x8 - FCP */
@@ -2111,7 +2111,7 @@ lpfc_fdmi_port_attr_support_speed(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	ae->un.AttrInt = 0;
 	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
@@ -2161,7 +2161,7 @@ lpfc_fdmi_port_attr_speed(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
 		switch (phba->fc_linkspeed) {
@@ -2225,7 +2225,7 @@ lpfc_fdmi_port_attr_max_frame(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	hsp = (struct serv_parm *)&vport->fc_sparam;
 	ae->un.AttrInt = (((uint32_t) hsp->cmn.bbRcvSizeMsb) << 8) |
@@ -2245,8 +2245,8 @@ lpfc_fdmi_port_attr_os_devname(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	snprintf(ae->un.AttrString, sizeof(ae->un.AttrString),
 		 "/sys/class/scsi_host/host%d", shost->host_no);
@@ -2266,8 +2266,8 @@ lpfc_fdmi_port_attr_host_name(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s",
 		 init_utsname()->nodename);
@@ -2287,8 +2287,8 @@ lpfc_fdmi_port_attr_wwnn(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0,  sizeof(struct lpfc_name));
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrWWN, &vport->fc_sparam.nodeName,
 	       sizeof(struct lpfc_name));
@@ -2305,8 +2305,8 @@ lpfc_fdmi_port_attr_wwpn(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0,  sizeof(struct lpfc_name));
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrWWN, &vport->fc_sparam.portName,
 	       sizeof(struct lpfc_name));
@@ -2323,8 +2323,8 @@ lpfc_fdmi_port_attr_symbolic_name(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	len = lpfc_vport_symbolic_port_name(vport, ae->un.AttrString, 256);
 	len += (len & 3) ? (4 - (len & 3)) : 4;
@@ -2342,7 +2342,7 @@ lpfc_fdmi_port_attr_port_type(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	if (phba->fc_topology == LPFC_TOPOLOGY_LOOP)
 		ae->un.AttrInt =  cpu_to_be32(LPFC_FDMI_PORTTYPE_NLPORT);
 	else
@@ -2360,7 +2360,7 @@ lpfc_fdmi_port_attr_class(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	ae->un.AttrInt = cpu_to_be32(FC_COS_CLASS2 | FC_COS_CLASS3);
 	size = FOURBYTES + sizeof(uint32_t);
 	ad->AttrLen = cpu_to_be16(size);
@@ -2375,8 +2375,8 @@ lpfc_fdmi_port_attr_fabric_wwpn(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0,  sizeof(struct lpfc_name));
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrWWN, &vport->fabric_portname,
 	       sizeof(struct lpfc_name));
@@ -2393,8 +2393,8 @@ lpfc_fdmi_port_attr_active_fc4type(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 32);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	ae->un.AttrTypes[3] = 0x02; /* Type 0x1 - ELS */
 	ae->un.AttrTypes[2] = 0x01; /* Type 0x8 - FCP */
@@ -2414,7 +2414,7 @@ lpfc_fdmi_port_attr_port_state(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	/* Link Up - operational */
 	ae->un.AttrInt =  cpu_to_be32(LPFC_FDMI_PORTSTATE_ONLINE);
 	size = FOURBYTES + sizeof(uint32_t);
@@ -2430,7 +2430,7 @@ lpfc_fdmi_port_attr_num_disc(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	vport->fdmi_num_disc = lpfc_find_map_node(vport);
 	ae->un.AttrInt = cpu_to_be32(vport->fdmi_num_disc);
 	size = FOURBYTES + sizeof(uint32_t);
@@ -2446,7 +2446,7 @@ lpfc_fdmi_port_attr_nportid(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	ae->un.AttrInt =  cpu_to_be32(vport->fc_myDID);
 	size = FOURBYTES + sizeof(uint32_t);
 	ad->AttrLen = cpu_to_be16(size);
@@ -2461,8 +2461,8 @@ lpfc_fdmi_smart_attr_service(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, "Smart SAN Initiator",
 		sizeof(ae->un.AttrString));
@@ -2482,8 +2482,8 @@ lpfc_fdmi_smart_attr_guid(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrString, &vport->fc_sparam.nodeName,
 	       sizeof(struct lpfc_name));
@@ -2503,8 +2503,8 @@ lpfc_fdmi_smart_attr_version(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, "Smart SAN Version 2.0",
 		sizeof(ae->un.AttrString));
@@ -2525,8 +2525,8 @@ lpfc_fdmi_smart_attr_model(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, phba->ModelName,
 		sizeof(ae->un.AttrString));
@@ -2545,7 +2545,7 @@ lpfc_fdmi_smart_attr_port_info(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	/* SRIOV (type 3) is not supported */
 	if (vport->vpi)
@@ -2565,7 +2565,7 @@ lpfc_fdmi_smart_attr_qos(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	ae->un.AttrInt =  cpu_to_be32(0);
 	size = FOURBYTES + sizeof(uint32_t);
 	ad->AttrLen = cpu_to_be16(size);
@@ -2580,7 +2580,7 @@ lpfc_fdmi_smart_attr_security(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	ae->un.AttrInt =  cpu_to_be32(1);
 	size = FOURBYTES + sizeof(uint32_t);
 	ad->AttrLen = cpu_to_be16(size);
@@ -2728,7 +2728,8 @@ lpfc_fdmi_cmd(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			/* Registered Port List */
 			/* One entry (port) per adapter */
 			rh->rpl.EntryCnt = cpu_to_be32(1);
-			memcpy(&rh->rpl.pe, &phba->pport->fc_sparam.portName,
+			memcpy(&rh->rpl.pe.PortName,
+			       &phba->pport->fc_sparam.portName,
 			       sizeof(struct lpfc_name));
 
 			/* point to the HBA attribute block */
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 4c84c2ae1112..566e8d07cb05 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -4104,7 +4104,9 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 out:
 	if (ndlp && NLP_CHK_NODE_ACT(ndlp) && shost) {
 		spin_lock_irq(shost->host_lock);
-		ndlp->nlp_flag &= ~(NLP_ACC_REGLOGIN | NLP_RM_DFLT_RPI);
+		if (mbox)
+			ndlp->nlp_flag &= ~NLP_ACC_REGLOGIN;
+		ndlp->nlp_flag &= ~NLP_RM_DFLT_RPI;
 		spin_unlock_irq(shost->host_lock);
 
 		/* If the node is not being used by another discovery thread,
@@ -7913,6 +7915,8 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	spin_lock_irq(shost->host_lock);
 	if (ndlp->nlp_flag & NLP_IN_DEV_LOSS) {
 		spin_unlock_irq(shost->host_lock);
+		if (newnode)
+			lpfc_nlp_put(ndlp);
 		goto dropit;
 	}
 	spin_unlock_irq(shost->host_lock);
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index bdc1f184f67a..12e033bbe607 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -1326,25 +1326,8 @@ struct fc_rdp_res_frame {
 /* lpfc_sli_ct_request defines the CT_IU preamble for FDMI commands */
 #define  SLI_CT_FDMI_Subtypes     0x10	/* Management Service Subtype */
 
-/*
- * Registered Port List Format
- */
-struct lpfc_fdmi_reg_port_list {
-	uint32_t EntryCnt;
-	uint32_t pe;		/* Variable-length array */
-};
-
-
 /* Definitions for HBA / Port attribute entries */
 
-struct lpfc_fdmi_attr_def { /* Defined in TLV format */
-	/* Structure is in Big Endian format */
-	uint32_t AttrType:16;
-	uint32_t AttrLen:16;
-	uint32_t AttrValue;  /* Marks start of Value (ATTRIBUTE_ENTRY) */
-};
-
-
 /* Attribute Entry */
 struct lpfc_fdmi_attr_entry {
 	union {
@@ -1355,7 +1338,13 @@ struct lpfc_fdmi_attr_entry {
 	} un;
 };
 
-#define LPFC_FDMI_MAX_AE_SIZE	sizeof(struct lpfc_fdmi_attr_entry)
+struct lpfc_fdmi_attr_def { /* Defined in TLV format */
+	/* Structure is in Big Endian format */
+	uint32_t AttrType:16;
+	uint32_t AttrLen:16;
+	/* Marks start of Value (ATTRIBUTE_ENTRY) */
+	struct lpfc_fdmi_attr_entry AttrValue;
+} __packed;
 
 /*
  * HBA Attribute Block
@@ -1380,12 +1369,19 @@ struct lpfc_fdmi_hba_ident {
 };
 
 /*
+ * Registered Port List Format
+ */
+struct lpfc_fdmi_reg_port_list {
+	uint32_t EntryCnt;
+	struct lpfc_fdmi_port_entry pe;
+} __packed;
+
+/*
  * Register HBA(RHBA)
  */
 struct lpfc_fdmi_reg_hba {
 	struct lpfc_fdmi_hba_ident hi;
-	struct lpfc_fdmi_reg_port_list rpl;	/* variable-length array */
-/* struct lpfc_fdmi_attr_block   ab; */
+	struct lpfc_fdmi_reg_port_list rpl;
 };
 
 /*
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 480d2d467f7a..45445dafc80c 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -17038,6 +17038,10 @@ lpfc_prep_seq(struct lpfc_vport *vport, struct hbq_dmabuf *seq_dmabuf)
 			list_add_tail(&iocbq->list, &first_iocbq->list);
 		}
 	}
+	/* Free the sequence's header buffer */
+	if (!first_iocbq)
+		lpfc_in_buf_free(vport->phba, &seq_dmabuf->dbuf);
+
 	return first_iocbq;
 }
 
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index c714482bf4c5..9c738e201f46 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -644,27 +644,16 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
 		    vport->port_state < LPFC_VPORT_READY)
 			return -EAGAIN;
 	}
+
 	/*
-	 * This is a bit of a mess.  We want to ensure the shost doesn't get
-	 * torn down until we're done with the embedded lpfc_vport structure.
-	 *
-	 * Beyond holding a reference for this function, we also need a
-	 * reference for outstanding I/O requests we schedule during delete
-	 * processing.  But once we scsi_remove_host() we can no longer obtain
-	 * a reference through scsi_host_get().
-	 *
-	 * So we take two references here.  We release one reference at the
-	 * bottom of the function -- after delinking the vport.  And we
-	 * release the other at the completion of the unreg_vpi that get's
-	 * initiated after we've disposed of all other resources associated
-	 * with the port.
+	 * Take early refcount for outstanding I/O requests we schedule during
+	 * delete processing for unreg_vpi.  Always keep this before
+	 * scsi_remove_host() as we can no longer obtain a reference through
+	 * scsi_host_get() after scsi_host_remove as shost is set to SHOST_DEL.
 	 */
 	if (!scsi_host_get(shost))
 		return VPORT_INVAL;
-	if (!scsi_host_get(shost)) {
-		scsi_host_put(shost);
-		return VPORT_INVAL;
-	}
+
 	lpfc_free_sysfs_attr(vport);
 
 	lpfc_debugfs_terminate(vport);
@@ -811,8 +800,9 @@ skip_logo:
 		if (!(vport->vpi_state & LPFC_VPI_REGISTERED) ||
 				lpfc_mbx_unreg_vpi(vport))
 			scsi_host_put(shost);
-	} else
+	} else {
 		scsi_host_put(shost);
+	}
 
 	lpfc_free_vpi(phba, vport->vpi);
 	vport->work_port_events = 0;
diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c
index 1753e42826dd..a880abf5abaa 100644
--- a/drivers/scsi/mesh.c
+++ b/drivers/scsi/mesh.c
@@ -1044,6 +1044,8 @@ static void handle_error(struct mesh_state *ms)
 		while ((in_8(&mr->bus_status1) & BS1_RST) != 0)
 			udelay(1);
 		printk("done\n");
+		if (ms->dma_started)
+			halt_dma(ms);
 		handle_reset(ms);
 		/* request_q is empty, no point in mesh_start() */
 		return;
@@ -1356,7 +1358,8 @@ static void halt_dma(struct mesh_state *ms)
 		       ms->conn_tgt, ms->data_ptr, scsi_bufflen(cmd),
 		       ms->tgts[ms->conn_tgt].data_goes_out);
 	}
-	scsi_dma_unmap(cmd);
+	if (cmd)
+		scsi_dma_unmap(cmd);
 	ms->dma_started = 0;
 }
 
@@ -1711,6 +1714,9 @@ static int mesh_host_reset(struct scsi_cmnd *cmd)
 
 	spin_lock_irqsave(ms->host->host_lock, flags);
 
+	if (ms->dma_started)
+		halt_dma(ms);
+
 	/* Reset the controller & dbdma channel */
 	out_le32(&md->control, (RUN|PAUSE|FLUSH|WAKE) << 16);	/* stop dma */
 	out_8(&mr->exception, 0xff);	/* clear all exception bits */
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 817a7963a038..556971c5f0b0 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -3263,7 +3263,9 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc)
 		ioc->scsi_lookup = NULL;
 	}
 	kfree(ioc->hpr_lookup);
+	ioc->hpr_lookup = NULL;
 	kfree(ioc->internal_lookup);
+	ioc->internal_lookup = NULL;
 	if (ioc->chain_lookup) {
 		for (i = 0; i < ioc->chain_depth; i++) {
 			if (ioc->chain_lookup[i].chain_buffer)
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index e64a13f0bce1..61a2da30f94b 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -795,7 +795,7 @@ pm8001_exec_internal_task_abort(struct pm8001_hba_info *pm8001_ha,
 
 		res = pm8001_tag_alloc(pm8001_ha, &ccb_tag);
 		if (res)
-			return res;
+			goto ex_err;
 		ccb = &pm8001_ha->ccb_info[ccb_tag];
 		ccb->device = pm8001_dev;
 		ccb->ccb_tag = ccb_tag;
diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c
index 94f3829b1974..4d7971c3f339 100644
--- a/drivers/scsi/qedi/qedi_iscsi.c
+++ b/drivers/scsi/qedi/qedi_iscsi.c
@@ -1007,7 +1007,8 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep)
 	if (qedi_ep->state == EP_STATE_OFLDCONN_START)
 		goto ep_exit_recover;
 
-	flush_work(&qedi_ep->offload_work);
+	if (qedi_ep->state != EP_STATE_OFLDCONN_NONE)
+		flush_work(&qedi_ep->offload_work);
 
 	if (qedi_ep->conn) {
 		qedi_conn = qedi_ep->conn;
@@ -1071,6 +1072,9 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep)
 		break;
 	}
 
+	if (!abrt_conn)
+		wait_delay += qedi->pf_params.iscsi_pf_params.two_msl_timer;
+
 	qedi_ep->state = EP_STATE_DISCONN_START;
 	ret = qedi_ops->destroy_conn(qedi->cdev, qedi_ep->handle, abrt_conn);
 	if (ret) {
@@ -1224,6 +1228,10 @@ static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data)
 	}
 
 	iscsi_cid = (u32)path_data->handle;
+	if (iscsi_cid >= qedi->max_active_conns) {
+		ret = -EINVAL;
+		goto set_path_exit;
+	}
 	qedi_ep = qedi->ep_tbl[iscsi_cid];
 	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
 		  "iscsi_cid=0x%x, qedi_ep=%p\n", iscsi_cid, qedi_ep);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index d4024015f859..ea60c6e603c0 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -5824,6 +5824,7 @@ qla2x00_do_dpc(void *data)
 
 			if (do_reset && !(test_and_set_bit(ABORT_ISP_ACTIVE,
 			    &base_vha->dpc_flags))) {
+				base_vha->flags.online = 1;
 				ql_dbg(ql_dbg_dpc, base_vha, 0x4007,
 				    "ISP abort scheduled.\n");
 				if (ha->isp_ops->abort_isp(base_vha)) {
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index e08ac431bc49..e7aee067b056 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -937,6 +937,7 @@ static ssize_t tcm_qla2xxx_tpg_enable_store(struct config_item *item,
 
 		atomic_set(&tpg->lport_tpg_enabled, 0);
 		qlt_stop_phase1(vha->vha_tgt.qla_tgt);
+		qlt_stop_phase2(vha->vha_tgt.qla_tgt);
 	}
 
 	return count;
@@ -1101,6 +1102,7 @@ static ssize_t tcm_qla2xxx_npiv_tpg_enable_store(struct config_item *item,
 
 		atomic_set(&tpg->lport_tpg_enabled, 0);
 		qlt_stop_phase1(vha->vha_tgt.qla_tgt);
+		qlt_stop_phase2(vha->vha_tgt.qla_tgt);
 	}
 
 	return count;
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index ac936b5ca74e..aba1a3396890 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -4993,6 +4993,12 @@ static int __init scsi_debug_init(void)
 		pr_err("submit_queues must be 1 or more\n");
 		return -EINVAL;
 	}
+
+	if ((sdebug_max_queue > SDEBUG_CANQUEUE) || (sdebug_max_queue < 1)) {
+		pr_err("max_queue must be in range [1, %d]\n", SDEBUG_CANQUEUE);
+		return -EINVAL;
+	}
+
 	sdebug_q_arr = kcalloc(submit_queues, sizeof(struct sdebug_queue),
 			       GFP_KERNEL);
 	if (sdebug_q_arr == NULL)
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index 022fcd2e4702..6748e82c6352 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -392,8 +392,8 @@ EXPORT_SYMBOL(scsi_dev_info_list_add_keyed);
 
 /**
  * scsi_dev_info_list_find - find a matching dev_info list entry.
- * @vendor:	vendor string
- * @model:	model (product) string
+ * @vendor:	full vendor string
+ * @model:	full model (product) string
  * @key:	specify list to use
  *
  * Description:
@@ -408,7 +408,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor,
 	struct scsi_dev_info_list *devinfo;
 	struct scsi_dev_info_list_table *devinfo_table =
 		scsi_devinfo_lookup_by_key(key);
-	size_t vmax, mmax;
+	size_t vmax, mmax, mlen;
 	const char *vskip, *mskip;
 
 	if (IS_ERR(devinfo_table))
@@ -447,15 +447,19 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor,
 			    dev_info_list) {
 		if (devinfo->compatible) {
 			/*
-			 * Behave like the older version of get_device_flags.
+			 * vendor strings must be an exact match
 			 */
-			if (memcmp(devinfo->vendor, vskip, vmax) ||
-					(vmax < sizeof(devinfo->vendor) &&
-						devinfo->vendor[vmax]))
+			if (vmax != strnlen(devinfo->vendor,
+					    sizeof(devinfo->vendor)) ||
+			    memcmp(devinfo->vendor, vskip, vmax))
 				continue;
-			if (memcmp(devinfo->model, mskip, mmax) ||
-					(mmax < sizeof(devinfo->model) &&
-						devinfo->model[mmax]))
+
+			/*
+			 * @model specifies the full string, and
+			 * must be larger or equal to devinfo->model
+			 */
+			mlen = strnlen(devinfo->model, sizeof(devinfo->model));
+			if (mmax < mlen || memcmp(devinfo->model, mskip, mlen))
 				continue;
 			return devinfo;
 		} else {
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 958901523469..c3170500a1a1 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -3172,7 +3172,7 @@ static int iscsi_set_flashnode_param(struct iscsi_transport *transport,
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.set_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_set_fnode;
 	}
 
 	idx = ev->u.set_flashnode.flashnode_idx;
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index d0219e36080c..e626fc2cc781 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -349,7 +349,7 @@ store_spi_transport_##field(struct device *dev, 			\
 	struct spi_transport_attrs *tp					\
 		= (struct spi_transport_attrs *)&starget->starget_data;	\
 									\
-	if (i->f->set_##field)						\
+	if (!i->f->set_##field)						\
 		return -EINVAL;						\
 	val = simple_strtoul(buf, NULL, 0);				\
 	if (val > tp->max_##field)					\
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index d0389b20574d..5be3d6b7991b 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -748,7 +748,7 @@ static int sr_probe(struct device *dev)
 	cd->cdi.disk = disk;
 
 	if (register_cdrom(&cd->cdi))
-		goto fail_put;
+		goto fail_minor;
 
 	/*
 	 * Initialize block layer runtime PM stuffs before the
@@ -766,6 +766,10 @@ static int sr_probe(struct device *dev)
 
 	return 0;
 
+fail_minor:
+	spin_lock(&sr_index_lock);
+	clear_bit(minor, sr_index_bits);
+	spin_unlock(&sr_index_lock);
 fail_put:
 	put_disk(disk);
 fail_free:
diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c
index f2b8de195d8a..ee3589ac64ab 100644
--- a/drivers/scsi/ufs/ufs-qcom.c
+++ b/drivers/scsi/ufs/ufs-qcom.c
@@ -1649,11 +1649,11 @@ static void ufs_qcom_dump_dbg_regs(struct ufs_hba *hba)
 
 	/* sleep a bit intermittently as we are dumping too much data */
 	ufs_qcom_print_hw_debug_reg_all(hba, NULL, ufs_qcom_dump_regs_wrapper);
-	usleep_range(1000, 1100);
+	udelay(1000);
 	ufs_qcom_testbus_read(hba);
-	usleep_range(1000, 1100);
+	udelay(1000);
 	ufs_qcom_print_unipro_testbus(hba);
-	usleep_range(1000, 1100);
+	udelay(1000);
 }
 
 /**
diff --git a/drivers/scsi/ufs/ufs_quirks.h b/drivers/scsi/ufs/ufs_quirks.h
index 71f73d1d1ad1..6c944fbefd40 100644
--- a/drivers/scsi/ufs/ufs_quirks.h
+++ b/drivers/scsi/ufs/ufs_quirks.h
@@ -21,6 +21,7 @@
 #define UFS_ANY_VENDOR 0xFFFF
 #define UFS_ANY_MODEL  "ANY_MODEL"
 
+#define UFS_VENDOR_MICRON      0x12C
 #define UFS_VENDOR_TOSHIBA     0x198
 #define UFS_VENDOR_SAMSUNG     0x1CE
 #define UFS_VENDOR_SKHYNIX     0x1AD
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 78d9c2c48236..c1792f271ac5 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -189,6 +189,8 @@ ufs_get_desired_pm_lvl_for_dev_link_state(enum ufs_dev_pwr_mode dev_state,
 
 static struct ufs_dev_fix ufs_fixups[] = {
 	/* UFS cards deviations table */
+	UFS_FIX(UFS_VENDOR_MICRON, UFS_ANY_MODEL,
+		UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM),
 	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
 		UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM),
 	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL, UFS_DEVICE_NO_VCCQ),
@@ -1423,6 +1425,7 @@ unblock_reqs:
 int ufshcd_hold(struct ufs_hba *hba, bool async)
 {
 	int rc = 0;
+	bool flush_result;
 	unsigned long flags;
 
 	if (!ufshcd_is_clkgating_allowed(hba))
@@ -1454,7 +1457,9 @@ start:
 				break;
 			}
 			spin_unlock_irqrestore(hba->host->host_lock, flags);
-			flush_work(&hba->clk_gating.ungate_work);
+			flush_result = flush_work(&hba->clk_gating.ungate_work);
+			if (hba->clk_gating.is_suspended && !flush_result)
+				goto out;
 			spin_lock_irqsave(hba->host->host_lock, flags);
 			goto start;
 		}
@@ -2365,6 +2370,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 
 	err = ufshcd_map_sg(hba, lrbp);
 	if (err) {
+		ufshcd_release(hba);
 		lrbp->cmd = NULL;
 		clear_bit_unlock(tag, &hba->lrb_in_use);
 		goto out;
@@ -4889,7 +4895,6 @@ static int ufshcd_bkops_ctrl(struct ufs_hba *hba,
 		err = ufshcd_enable_auto_bkops(hba);
 	else
 		err = ufshcd_disable_auto_bkops(hba);
-	hba->urgent_bkops_lvl = curr_status;
 out:
 	return err;
 }
@@ -5368,7 +5373,7 @@ static void ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
  */
 static irqreturn_t ufshcd_intr(int irq, void *__hba)
 {
-	u32 intr_status, enabled_intr_status;
+	u32 intr_status, enabled_intr_status = 0;
 	irqreturn_t retval = IRQ_NONE;
 	struct ufs_hba *hba = __hba;
 	int retries = hba->nutrs;
@@ -5382,7 +5387,7 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba)
 	 * read, make sure we handle them by checking the interrupt status
 	 * again in a loop until we process all of the reqs before returning.
 	 */
-	do {
+	while (intr_status && retries--) {
 		enabled_intr_status =
 			intr_status & ufshcd_readl(hba, REG_INTERRUPT_ENABLE);
 		if (intr_status)
@@ -5393,7 +5398,7 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba)
 		}
 
 		intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS);
-	} while (intr_status && --retries);
+	}
 
 	spin_unlock(hba->host->host_lock);
 	return retval;
@@ -5689,7 +5694,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 			/* command completed already */
 			dev_err(hba->dev, "%s: cmd at tag %d successfully cleared from DB.\n",
 				__func__, tag);
-			goto out;
+			goto cleanup;
 		} else {
 			dev_err(hba->dev,
 				"%s: no response from device. tag = %d, err %d\n",
@@ -5723,6 +5728,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 		goto out;
 	}
 
+cleanup:
 	scsi_dma_unmap(cmd);
 
 	spin_lock_irqsave(host->host_lock, flags);
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index a75f2a2cf780..4b6a1629969f 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -827,4 +827,7 @@ config SPI_SLAVE_SYSTEM_CONTROL
 
 endif # SPI_SLAVE
 
+config SPI_DYNAMIC
+	def_bool ACPI || OF_DYNAMIC || SPI_SLAVE
+
 endif # SPI
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 0316fae20cfe..7c86a8ee03aa 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -683,7 +683,7 @@ static void read_from_hw(struct bcm_qspi *qspi, int slots)
 			if (buf)
 				buf[tp.byte] = read_rxram_slot_u8(qspi, slot);
 			dev_dbg(&qspi->pdev->dev, "RD %02x\n",
-				buf ? buf[tp.byte] : 0xff);
+				buf ? buf[tp.byte] : 0x0);
 		} else {
 			u16 *buf = tp.trans->rx_buf;
 
@@ -691,7 +691,7 @@ static void read_from_hw(struct bcm_qspi *qspi, int slots)
 				buf[tp.byte / 2] = read_rxram_slot_u16(qspi,
 								      slot);
 			dev_dbg(&qspi->pdev->dev, "RD %04x\n",
-				buf ? buf[tp.byte] : 0xffff);
+				buf ? buf[tp.byte / 2] : 0x0);
 		}
 
 		update_qspi_trans_byte_count(qspi, &tp,
@@ -746,13 +746,13 @@ static int write_to_hw(struct bcm_qspi *qspi, struct spi_device *spi)
 	while (!tstatus && slot < MSPI_NUM_CDRAM) {
 		if (tp.trans->bits_per_word <= 8) {
 			const u8 *buf = tp.trans->tx_buf;
-			u8 val = buf ? buf[tp.byte] : 0xff;
+			u8 val = buf ? buf[tp.byte] : 0x00;
 
 			write_txram_slot_u8(qspi, slot, val);
 			dev_dbg(&qspi->pdev->dev, "WR %02x\n", val);
 		} else {
 			const u16 *buf = tp.trans->tx_buf;
-			u16 val = buf ? buf[tp.byte / 2] : 0xffff;
+			u16 val = buf ? buf[tp.byte / 2] : 0x0000;
 
 			write_txram_slot_u16(qspi, slot, val);
 			dev_dbg(&qspi->pdev->dev, "WR %04x\n", val);
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index eab27d41ba83..df6abc75bc16 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -793,7 +793,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev)
 		goto out_clk_disable;
 	}
 
-	err = devm_spi_register_master(&pdev->dev, master);
+	err = spi_register_master(master);
 	if (err) {
 		dev_err(&pdev->dev, "could not register SPI master: %d\n", err);
 		goto out_clk_disable;
@@ -813,6 +813,8 @@ static int bcm2835_spi_remove(struct platform_device *pdev)
 	struct spi_master *master = platform_get_drvdata(pdev);
 	struct bcm2835_spi *bs = spi_master_get_devdata(master);
 
+	spi_unregister_master(master);
+
 	/* Clear FIFOs, and disable the HW block */
 	bcm2835_wr(bs, BCM2835_SPI_CS,
 		   BCM2835_SPI_CS_CLEAR_RX | BCM2835_SPI_CS_CLEAR_TX);
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index e075712c501e..b7f78e6d9bec 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -485,7 +485,7 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev)
 		goto out_clk_disable;
 	}
 
-	err = devm_spi_register_master(&pdev->dev, master);
+	err = spi_register_master(master);
 	if (err) {
 		dev_err(&pdev->dev, "could not register SPI master: %d\n", err);
 		goto out_clk_disable;
@@ -505,6 +505,8 @@ static int bcm2835aux_spi_remove(struct platform_device *pdev)
 	struct spi_master *master = platform_get_drvdata(pdev);
 	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
 
+	spi_unregister_master(master);
+
 	bcm2835aux_spi_reset_hw(bs);
 
 	/* disable the HW block by releasing the clock */
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 837cb8d0bac6..cb268cc4ba2b 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -155,6 +155,7 @@ static struct dma_async_tx_descriptor *dw_spi_dma_prepare_tx(struct dw_spi *dws,
 	if (!xfer->tx_buf)
 		return NULL;
 
+	memset(&txconf, 0, sizeof(txconf));
 	txconf.direction = DMA_MEM_TO_DEV;
 	txconf.dst_addr = dws->dma_addr;
 	txconf.dst_maxburst = 16;
@@ -201,6 +202,7 @@ static struct dma_async_tx_descriptor *dw_spi_dma_prepare_rx(struct dw_spi *dws,
 	if (!xfer->rx_buf)
 		return NULL;
 
+	memset(&rxconf, 0, sizeof(rxconf));
 	rxconf.direction = DMA_DEV_TO_MEM;
 	rxconf.src_addr = dws->dma_addr;
 	rxconf.src_maxburst = 16;
@@ -226,19 +228,23 @@ static struct dma_async_tx_descriptor *dw_spi_dma_prepare_rx(struct dw_spi *dws,
 
 static int mid_spi_dma_setup(struct dw_spi *dws, struct spi_transfer *xfer)
 {
-	u16 dma_ctrl = 0;
+	u16 imr = 0, dma_ctrl = 0;
 
 	dw_writel(dws, DW_SPI_DMARDLR, 0xf);
 	dw_writel(dws, DW_SPI_DMATDLR, 0x10);
 
-	if (xfer->tx_buf)
+	if (xfer->tx_buf) {
 		dma_ctrl |= SPI_DMA_TDMAE;
-	if (xfer->rx_buf)
+		imr |= SPI_INT_TXOI;
+	}
+	if (xfer->rx_buf) {
 		dma_ctrl |= SPI_DMA_RDMAE;
+		imr |= SPI_INT_RXUI | SPI_INT_RXOI;
+	}
 	dw_writel(dws, DW_SPI_DMACR, dma_ctrl);
 
 	/* Set the interrupt mask */
-	spi_umask_intr(dws, SPI_INT_TXOI | SPI_INT_RXUI | SPI_INT_RXOI);
+	spi_umask_intr(dws, imr);
 
 	dws->transfer_handler = dma_transfer;
 
@@ -268,7 +274,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, struct spi_transfer *xfer)
 		dma_async_issue_pending(dws->txchan);
 	}
 
-	return 0;
+	return 1;
 }
 
 static void mid_spi_dma_stop(struct dw_spi *dws)
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index b461200871f8..d2428a8809c1 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -305,6 +305,9 @@ static int dw_spi_transfer_one(struct spi_master *master,
 	dws->len = transfer->len;
 	spin_unlock_irqrestore(&dws->buf_lock, flags);
 
+	/* Ensure dw->rx and dw->rx_end are visible */
+	smp_mb();
+
 	spi_enable_chip(dws, 0);
 
 	/* Handle per transfer options for bpw and speed */
@@ -381,11 +384,8 @@ static int dw_spi_transfer_one(struct spi_master *master,
 
 	spi_enable_chip(dws, 1);
 
-	if (dws->dma_mapped) {
-		ret = dws->dma_ops->dma_transfer(dws, transfer);
-		if (ret < 0)
-			return ret;
-	}
+	if (dws->dma_mapped)
+		return dws->dma_ops->dma_transfer(dws, transfer);
 
 	if (chip->poll_mode)
 		return poll_transfer(dws);
@@ -496,6 +496,8 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 	dws->dma_addr = (dma_addr_t)(dws->paddr + DW_SPI_DR);
 	spin_lock_init(&dws->buf_lock);
 
+	spi_master_set_devdata(master, dws);
+
 	ret = request_irq(dws->irq, dw_spi_irq, IRQF_SHARED, dev_name(dev),
 			  master);
 	if (ret < 0) {
@@ -526,11 +528,11 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 			dws->dma_inited = 0;
 		} else {
 			master->can_dma = dws->dma_ops->can_dma;
+			master->flags |= SPI_CONTROLLER_MUST_TX;
 		}
 	}
 
-	spi_master_set_devdata(master, dws);
-	ret = devm_spi_register_master(dev, master);
+	ret = spi_register_master(master);
 	if (ret) {
 		dev_err(&master->dev, "problem registering spi master\n");
 		goto err_dma_exit;
@@ -554,6 +556,8 @@ void dw_spi_remove_host(struct dw_spi *dws)
 {
 	dw_spi_debugfs_remove(dws);
 
+	spi_unregister_master(dws->master);
+
 	if (dws->dma_ops && dws->dma_ops->dma_exit)
 		dws->dma_ops->dma_exit(dws);
 
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index ca013dd4ff6b..befabddf897a 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -49,6 +49,9 @@
 #define SPI_MCR_PCSIS		(0x3F << 16)
 #define SPI_MCR_CLR_TXF	(1 << 11)
 #define SPI_MCR_CLR_RXF	(1 << 10)
+#define SPI_MCR_DIS_TXF		(1 << 13)
+#define SPI_MCR_DIS_RXF		(1 << 12)
+#define SPI_MCR_HALT		(1 << 0)
 
 #define SPI_TCR			0x08
 #define SPI_TCR_GET_TCNT(x)	(((x) & 0xffff0000) >> 16)
@@ -73,7 +76,7 @@
 #define SPI_SR			0x2c
 #define SPI_SR_EOQF		0x10000000
 #define SPI_SR_TCFQF		0x80000000
-#define SPI_SR_CLEAR		0xdaad0000
+#define SPI_SR_CLEAR		0x9aaf0000
 
 #define SPI_RSER_TFFFE		BIT(25)
 #define SPI_RSER_TFFFD		BIT(24)
@@ -883,9 +886,11 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 					trans_mode);
 			}
 		}
+
+		return IRQ_HANDLED;
 	}
 
-	return IRQ_HANDLED;
+	return IRQ_NONE;
 }
 
 static const struct of_device_id fsl_dspi_dt_ids[] = {
@@ -903,6 +908,8 @@ static int dspi_suspend(struct device *dev)
 	struct spi_master *master = dev_get_drvdata(dev);
 	struct fsl_dspi *dspi = spi_master_get_devdata(master);
 
+	if (dspi->irq)
+		disable_irq(dspi->irq);
 	spi_master_suspend(master);
 	clk_disable_unprepare(dspi->clk);
 
@@ -923,6 +930,8 @@ static int dspi_resume(struct device *dev)
 	if (ret)
 		return ret;
 	spi_master_resume(master);
+	if (dspi->irq)
+		enable_irq(dspi->irq);
 
 	return 0;
 }
@@ -1024,8 +1033,8 @@ static int dspi_probe(struct platform_device *pdev)
 		goto out_clk_put;
 	}
 
-	ret = devm_request_irq(&pdev->dev, dspi->irq, dspi_interrupt, 0,
-			pdev->name, dspi);
+	ret = request_threaded_irq(dspi->irq, dspi_interrupt, NULL,
+				   IRQF_SHARED, pdev->name, dspi);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Unable to attach DSPI interrupt\n");
 		goto out_clk_put;
@@ -1035,7 +1044,7 @@ static int dspi_probe(struct platform_device *pdev)
 		ret = dspi_request_dma(dspi, res->start);
 		if (ret < 0) {
 			dev_err(&pdev->dev, "can't get dma channels\n");
-			goto out_clk_put;
+			goto out_free_irq;
 		}
 	}
 
@@ -1048,11 +1057,14 @@ static int dspi_probe(struct platform_device *pdev)
 	ret = spi_register_master(master);
 	if (ret != 0) {
 		dev_err(&pdev->dev, "Problem registering DSPI master\n");
-		goto out_clk_put;
+		goto out_free_irq;
 	}
 
 	return ret;
 
+out_free_irq:
+	if (dspi->irq)
+		free_irq(dspi->irq, dspi);
 out_clk_put:
 	clk_disable_unprepare(dspi->clk);
 out_master_put:
@@ -1067,13 +1079,29 @@ static int dspi_remove(struct platform_device *pdev)
 	struct fsl_dspi *dspi = spi_master_get_devdata(master);
 
 	/* Disconnect from the SPI framework */
+	spi_unregister_controller(dspi->master);
+
+	/* Disable RX and TX */
+	regmap_update_bits(dspi->regmap, SPI_MCR,
+			   SPI_MCR_DIS_TXF | SPI_MCR_DIS_RXF,
+			   SPI_MCR_DIS_TXF | SPI_MCR_DIS_RXF);
+
+	/* Stop Running */
+	regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_HALT, SPI_MCR_HALT);
+
 	dspi_release_dma(dspi);
+	if (dspi->irq)
+		free_irq(dspi->irq, dspi);
 	clk_disable_unprepare(dspi->clk);
-	spi_unregister_master(dspi->master);
 
 	return 0;
 }
 
+static void dspi_shutdown(struct platform_device *pdev)
+{
+	dspi_remove(pdev);
+}
+
 static struct platform_driver fsl_dspi_driver = {
 	.driver.name    = DRIVER_NAME,
 	.driver.of_match_table = fsl_dspi_dt_ids,
@@ -1081,6 +1109,7 @@ static struct platform_driver fsl_dspi_driver = {
 	.driver.pm = &dspi_pm,
 	.probe          = dspi_probe,
 	.remove		= dspi_remove,
+	.shutdown	= dspi_shutdown,
 };
 module_platform_driver(fsl_dspi_driver);
 
diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c
index 1d332e23f6ed..6a39ba5840c2 100644
--- a/drivers/spi/spi-fsl-espi.c
+++ b/drivers/spi/spi-fsl-espi.c
@@ -556,13 +556,14 @@ static void fsl_espi_cpu_irq(struct fsl_espi *espi, u32 events)
 static irqreturn_t fsl_espi_irq(s32 irq, void *context_data)
 {
 	struct fsl_espi *espi = context_data;
-	u32 events;
+	u32 events, mask;
 
 	spin_lock(&espi->lock);
 
 	/* Get interrupt events(tx/rx) */
 	events = fsl_espi_read_reg(espi, ESPI_SPIE);
-	if (!events) {
+	mask = fsl_espi_read_reg(espi, ESPI_SPIM);
+	if (!(events & mask)) {
 		spin_unlock(&espi->lock);
 		return IRQ_NONE;
 	}
diff --git a/drivers/spi/spi-lantiq-ssc.c b/drivers/spi/spi-lantiq-ssc.c
index d5976615d924..dc740b5f720b 100644
--- a/drivers/spi/spi-lantiq-ssc.c
+++ b/drivers/spi/spi-lantiq-ssc.c
@@ -187,6 +187,7 @@ struct lantiq_ssc_spi {
 	unsigned int			tx_fifo_size;
 	unsigned int			rx_fifo_size;
 	unsigned int			base_cs;
+	unsigned int			fdx_tx_level;
 };
 
 static u32 lantiq_ssc_readl(const struct lantiq_ssc_spi *spi, u32 reg)
@@ -484,6 +485,7 @@ static void tx_fifo_write(struct lantiq_ssc_spi *spi)
 	u32 data;
 	unsigned int tx_free = tx_fifo_free(spi);
 
+	spi->fdx_tx_level = 0;
 	while (spi->tx_todo && tx_free) {
 		switch (spi->bits_per_word) {
 		case 2 ... 8:
@@ -512,6 +514,7 @@ static void tx_fifo_write(struct lantiq_ssc_spi *spi)
 
 		lantiq_ssc_writel(spi, data, LTQ_SPI_TB);
 		tx_free--;
+		spi->fdx_tx_level++;
 	}
 }
 
@@ -523,6 +526,13 @@ static void rx_fifo_read_full_duplex(struct lantiq_ssc_spi *spi)
 	u32 data;
 	unsigned int rx_fill = rx_fifo_level(spi);
 
+	/*
+	 * Wait until all expected data to be shifted in.
+	 * Otherwise, rx overrun may occur.
+	 */
+	while (rx_fill != spi->fdx_tx_level)
+		rx_fill = rx_fifo_level(spi);
+
 	while (rx_fill) {
 		data = lantiq_ssc_readl(spi, LTQ_SPI_RB);
 
diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c
index bed7403bb6b3..b9a7117b6dce 100644
--- a/drivers/spi/spi-loopback-test.c
+++ b/drivers/spi/spi-loopback-test.c
@@ -99,7 +99,7 @@ static struct spi_test spi_tests[] = {
 	{
 		.description	= "tx/rx-transfer - crossing PAGE_SIZE",
 		.fill_option	= FILL_COUNT_8,
-		.iterate_len    = { ITERATE_MAX_LEN },
+		.iterate_len    = { ITERATE_LEN },
 		.iterate_tx_align = ITERATE_ALIGN,
 		.iterate_rx_align = ITERATE_ALIGN,
 		.transfer_count = 1,
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 0c2867deb36f..da28c52c9da1 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -41,7 +41,6 @@
 #define SPI_CFG0_SCK_LOW_OFFSET           8
 #define SPI_CFG0_CS_HOLD_OFFSET           16
 #define SPI_CFG0_CS_SETUP_OFFSET          24
-#define SPI_ADJUST_CFG0_SCK_LOW_OFFSET    16
 #define SPI_ADJUST_CFG0_CS_HOLD_OFFSET    0
 #define SPI_ADJUST_CFG0_CS_SETUP_OFFSET   16
 
@@ -53,6 +52,8 @@
 #define SPI_CFG1_CS_IDLE_MASK             0xff
 #define SPI_CFG1_PACKET_LOOP_MASK         0xff00
 #define SPI_CFG1_PACKET_LENGTH_MASK       0x3ff0000
+#define SPI_CFG2_SCK_HIGH_OFFSET          0
+#define SPI_CFG2_SCK_LOW_OFFSET           16
 
 #define SPI_CMD_ACT                  BIT(0)
 #define SPI_CMD_RESUME               BIT(1)
@@ -259,7 +260,7 @@ static void mtk_spi_set_cs(struct spi_device *spi, bool enable)
 static void mtk_spi_prepare_transfer(struct spi_master *master,
 				     struct spi_transfer *xfer)
 {
-	u32 spi_clk_hz, div, sck_time, cs_time, reg_val = 0;
+	u32 spi_clk_hz, div, sck_time, cs_time, reg_val;
 	struct mtk_spi *mdata = spi_master_get_devdata(master);
 
 	spi_clk_hz = clk_get_rate(mdata->spi_clk);
@@ -272,18 +273,18 @@ static void mtk_spi_prepare_transfer(struct spi_master *master,
 	cs_time = sck_time * 2;
 
 	if (mdata->dev_comp->enhance_timing) {
+		reg_val = (((sck_time - 1) & 0xffff)
+			   << SPI_CFG2_SCK_HIGH_OFFSET);
 		reg_val |= (((sck_time - 1) & 0xffff)
-			   << SPI_CFG0_SCK_HIGH_OFFSET);
-		reg_val |= (((sck_time - 1) & 0xffff)
-			   << SPI_ADJUST_CFG0_SCK_LOW_OFFSET);
+			   << SPI_CFG2_SCK_LOW_OFFSET);
 		writel(reg_val, mdata->base + SPI_CFG2_REG);
-		reg_val |= (((cs_time - 1) & 0xffff)
+		reg_val = (((cs_time - 1) & 0xffff)
 			   << SPI_ADJUST_CFG0_CS_HOLD_OFFSET);
 		reg_val |= (((cs_time - 1) & 0xffff)
 			   << SPI_ADJUST_CFG0_CS_SETUP_OFFSET);
 		writel(reg_val, mdata->base + SPI_CFG0_REG);
 	} else {
-		reg_val |= (((sck_time - 1) & 0xff)
+		reg_val = (((sck_time - 1) & 0xff)
 			   << SPI_CFG0_SCK_HIGH_OFFSET);
 		reg_val |= (((sck_time - 1) & 0xff) << SPI_CFG0_SCK_LOW_OFFSET);
 		reg_val |= (((cs_time - 1) & 0xff) << SPI_CFG0_CS_HOLD_OFFSET);
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 5160e16d3a98..1579eb2bc29f 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -156,6 +156,7 @@ static const struct lpss_config lpss_platforms[] = {
 		.tx_threshold_hi = 48,
 		.cs_sel_shift = 8,
 		.cs_sel_mask = 3 << 8,
+		.cs_clk_stays_gated = true,
 	},
 	{	/* LPSS_CNL_SSP */
 		.offset = 0x200,
@@ -1826,7 +1827,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 
 	/* Register with the SPI framework */
 	platform_set_drvdata(pdev, drv_data);
-	status = devm_spi_register_master(&pdev->dev, master);
+	status = spi_register_master(master);
 	if (status != 0) {
 		dev_err(&pdev->dev, "problem registering spi master\n");
 		goto out_error_clock_enabled;
@@ -1856,6 +1857,8 @@ static int pxa2xx_spi_remove(struct platform_device *pdev)
 
 	pm_runtime_get_sync(&pdev->dev);
 
+	spi_unregister_master(drv_data->master);
+
 	/* Disable the SSP at the peripheral and SOC level */
 	pxa2xx_spi_write(drv_data, SSCR0, 0);
 	clk_disable_unprepare(ssp->clk);
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index ba9743fa2326..179749f354c3 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -254,7 +254,8 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz)
 {
 	u32 div, mbrdiv;
 
-	div = DIV_ROUND_UP(spi->clk_rate, speed_hz);
+	/* Ensure spi->clk_rate is even */
+	div = DIV_ROUND_UP(spi->clk_rate & ~0x1, speed_hz);
 
 	/*
 	 * SPI framework set xfer->speed_hz to master->max_speed_hz if
diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index 8533f4edd00a..21a22d42818c 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -202,7 +202,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 				  struct spi_transfer *tfr)
 {
 	struct sun6i_spi *sspi = spi_master_get_devdata(master);
-	unsigned int mclk_rate, div, timeout;
+	unsigned int mclk_rate, div, div_cdr1, div_cdr2, timeout;
 	unsigned int start, end, tx_time;
 	unsigned int trig_level;
 	unsigned int tx_len = 0;
@@ -291,14 +291,12 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	 * First try CDR2, and if we can't reach the expected
 	 * frequency, fall back to CDR1.
 	 */
-	div = mclk_rate / (2 * tfr->speed_hz);
-	if (div <= (SUN6I_CLK_CTL_CDR2_MASK + 1)) {
-		if (div > 0)
-			div--;
-
-		reg = SUN6I_CLK_CTL_CDR2(div) | SUN6I_CLK_CTL_DRS;
+	div_cdr1 = DIV_ROUND_UP(mclk_rate, tfr->speed_hz);
+	div_cdr2 = DIV_ROUND_UP(div_cdr1, 2);
+	if (div_cdr2 <= (SUN6I_CLK_CTL_CDR2_MASK + 1)) {
+		reg = SUN6I_CLK_CTL_CDR2(div_cdr2 - 1) | SUN6I_CLK_CTL_DRS;
 	} else {
-		div = ilog2(mclk_rate) - ilog2(tfr->speed_hz);
+		div = min(SUN6I_CLK_CTL_CDR1_MASK, order_base_2(div_cdr1));
 		reg = SUN6I_CLK_CTL_CDR1(div);
 	}
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 56035637d8f6..acc8eeed73f0 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -428,6 +428,12 @@ static LIST_HEAD(spi_controller_list);
  */
 static DEFINE_MUTEX(board_lock);
 
+/*
+ * Prevents addition of devices with same chip select and
+ * addition of devices below an unregistering controller.
+ */
+static DEFINE_MUTEX(spi_add_lock);
+
 /**
  * spi_alloc_device - Allocate a new SPI device
  * @ctlr: Controller to which device is connected
@@ -506,7 +512,6 @@ static int spi_dev_check(struct device *dev, void *data)
  */
 int spi_add_device(struct spi_device *spi)
 {
-	static DEFINE_MUTEX(spi_add_lock);
 	struct spi_controller *ctlr = spi->controller;
 	struct device *dev = ctlr->dev.parent;
 	int status;
@@ -534,6 +539,13 @@ int spi_add_device(struct spi_device *spi)
 		goto done;
 	}
 
+	/* Controller may unregister concurrently */
+	if (IS_ENABLED(CONFIG_SPI_DYNAMIC) &&
+	    !device_is_registered(&ctlr->dev)) {
+		status = -ENODEV;
+		goto done;
+	}
+
 	if (ctlr->cs_gpios)
 		spi->cs_gpio = ctlr->cs_gpios[spi->chip_select];
 
@@ -1113,8 +1125,6 @@ out:
 	if (msg->status && ctlr->handle_err)
 		ctlr->handle_err(ctlr, msg);
 
-	spi_res_release(ctlr, msg);
-
 	spi_finalize_current_message(ctlr);
 
 	return ret;
@@ -1372,6 +1382,13 @@ void spi_finalize_current_message(struct spi_controller *ctlr)
 
 	spi_unmap_msg(ctlr, mesg);
 
+	/* In the prepare_messages callback the spi bus has the opportunity to
+	 * split a transfer to smaller chunks.
+	 * Release splited transfers here since spi_map_msg is done on the
+	 * splited transfers.
+	 */
+	spi_res_release(ctlr, mesg);
+
 	if (ctlr->cur_msg_prepared && ctlr->unprepare_message) {
 		ret = ctlr->unprepare_message(ctlr, mesg);
 		if (ret) {
@@ -2264,7 +2281,12 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 {
 	struct spi_controller *found;
 	int id = ctlr->bus_num;
-	int dummy;
+
+	/* Prevent addition of new devices, unregister existing ones */
+	if (IS_ENABLED(CONFIG_SPI_DYNAMIC))
+		mutex_lock(&spi_add_lock);
+
+	device_for_each_child(&ctlr->dev, NULL, __unregister);
 
 	/* First make sure that this controller was ever added */
 	mutex_lock(&board_lock);
@@ -2278,13 +2300,15 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 	list_del(&ctlr->list);
 	mutex_unlock(&board_lock);
 
-	dummy = device_for_each_child(&ctlr->dev, NULL, __unregister);
 	device_unregister(&ctlr->dev);
 	/* free bus id */
 	mutex_lock(&board_lock);
 	if (found == ctlr)
 		idr_remove(&spi_master_idr, id);
 	mutex_unlock(&board_lock);
+
+	if (IS_ENABLED(CONFIG_SPI_DYNAMIC))
+		mutex_unlock(&spi_add_lock);
 }
 EXPORT_SYMBOL_GPL(spi_unregister_controller);
 
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 028725573e63..e444e7cc6968 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -232,6 +232,11 @@ static int spidev_message(struct spidev_data *spidev,
 	for (n = n_xfers, k_tmp = k_xfers, u_tmp = u_xfers;
 			n;
 			n--, k_tmp++, u_tmp++) {
+		/* Ensure that also following allocations from rx_buf/tx_buf will meet
+		 * DMA alignment requirements.
+		 */
+		unsigned int len_aligned = ALIGN(u_tmp->len, ARCH_KMALLOC_MINALIGN);
+
 		k_tmp->len = u_tmp->len;
 
 		total += k_tmp->len;
@@ -247,17 +252,17 @@ static int spidev_message(struct spidev_data *spidev,
 
 		if (u_tmp->rx_buf) {
 			/* this transfer needs space in RX bounce buffer */
-			rx_total += k_tmp->len;
+			rx_total += len_aligned;
 			if (rx_total > bufsiz) {
 				status = -EMSGSIZE;
 				goto done;
 			}
 			k_tmp->rx_buf = rx_buf;
-			rx_buf += k_tmp->len;
+			rx_buf += len_aligned;
 		}
 		if (u_tmp->tx_buf) {
 			/* this transfer needs space in TX bounce buffer */
-			tx_total += k_tmp->len;
+			tx_total += len_aligned;
 			if (tx_total > bufsiz) {
 				status = -EMSGSIZE;
 				goto done;
@@ -267,7 +272,7 @@ static int spidev_message(struct spidev_data *spidev,
 						(uintptr_t) u_tmp->tx_buf,
 					u_tmp->len))
 				goto done;
-			tx_buf += k_tmp->len;
+			tx_buf += len_aligned;
 		}
 
 		k_tmp->cs_change = !!u_tmp->cs_change;
@@ -297,16 +302,16 @@ static int spidev_message(struct spidev_data *spidev,
 		goto done;
 
 	/* copy any rx data out of bounce buffer */
-	rx_buf = spidev->rx_buffer;
-	for (n = n_xfers, u_tmp = u_xfers; n; n--, u_tmp++) {
+	for (n = n_xfers, k_tmp = k_xfers, u_tmp = u_xfers;
+			n;
+			n--, k_tmp++, u_tmp++) {
 		if (u_tmp->rx_buf) {
 			if (copy_to_user((u8 __user *)
-					(uintptr_t) u_tmp->rx_buf, rx_buf,
+					(uintptr_t) u_tmp->rx_buf, k_tmp->rx_buf,
 					u_tmp->len)) {
 				status = -EFAULT;
 				goto done;
 			}
-			rx_buf += u_tmp->len;
 		}
 	}
 	status = total;
@@ -607,15 +612,20 @@ err_find_dev:
 static int spidev_release(struct inode *inode, struct file *filp)
 {
 	struct spidev_data	*spidev;
+	int			dofree;
 
 	mutex_lock(&device_list_lock);
 	spidev = filp->private_data;
 	filp->private_data = NULL;
 
+	spin_lock_irq(&spidev->spi_lock);
+	/* ... after we unbound from the underlying device? */
+	dofree = (spidev->spi == NULL);
+	spin_unlock_irq(&spidev->spi_lock);
+
 	/* last close? */
 	spidev->users--;
 	if (!spidev->users) {
-		int		dofree;
 
 		kfree(spidev->tx_buffer);
 		spidev->tx_buffer = NULL;
@@ -623,19 +633,14 @@ static int spidev_release(struct inode *inode, struct file *filp)
 		kfree(spidev->rx_buffer);
 		spidev->rx_buffer = NULL;
 
-		spin_lock_irq(&spidev->spi_lock);
-		if (spidev->spi)
-			spidev->speed_hz = spidev->spi->max_speed_hz;
-
-		/* ... after we unbound from the underlying device? */
-		dofree = (spidev->spi == NULL);
-		spin_unlock_irq(&spidev->spi_lock);
-
 		if (dofree)
 			kfree(spidev);
+		else
+			spidev->speed_hz = spidev->spi->max_speed_hz;
 	}
 #ifdef CONFIG_SPI_SLAVE
-	spi_slave_abort(spidev->spi);
+	if (!dofree)
+		spi_slave_abort(spidev->spi);
 #endif
 	mutex_unlock(&device_list_lock);
 
@@ -782,13 +787,13 @@ static int spidev_remove(struct spi_device *spi)
 {
 	struct spidev_data	*spidev = spi_get_drvdata(spi);
 
+	/* prevent new opens */
+	mutex_lock(&device_list_lock);
 	/* make sure ops on existing fds can abort cleanly */
 	spin_lock_irq(&spidev->spi_lock);
 	spidev->spi = NULL;
 	spin_unlock_irq(&spidev->spi_lock);
 
-	/* prevent new opens */
-	mutex_lock(&device_list_lock);
 	list_del(&spidev->device_entry);
 	device_destroy(spidev_class, spidev->devt);
 	clear_bit(MINOR(spidev->devt), minors);
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 9481c0b23386..22cae548df49 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -100,6 +100,15 @@ static DEFINE_MUTEX(ashmem_mutex);
 static struct kmem_cache *ashmem_area_cachep __read_mostly;
 static struct kmem_cache *ashmem_range_cachep __read_mostly;
 
+/*
+ * A separate lockdep class for the backing shmem inodes to resolve the lockdep
+ * warning about the race between kswapd taking fs_reclaim before inode_lock
+ * and write syscall taking inode_lock and then fs_reclaim.
+ * Note that such race is impossible because ashmem does not support write
+ * syscalls operating on the backing shmem.
+ */
+static struct lock_class_key backing_shmem_inode_class;
+
 static inline unsigned long range_size(struct ashmem_range *range)
 {
 	return range->pgend - range->pgstart + 1;
@@ -406,6 +415,7 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!asma->file) {
 		char *name = ASHMEM_NAME_DEF;
 		struct file *vmfile;
+		struct inode *inode;
 
 		if (asma->name[ASHMEM_NAME_PREFIX_LEN] != '\0')
 			name = asma->name;
@@ -417,6 +427,8 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 			goto out;
 		}
 		vmfile->f_mode |= FMODE_LSEEK;
+		inode = file_inode(vmfile);
+		lockdep_set_class(&inode->i_rwsem, &backing_shmem_inode_class);
 		asma->file = vmfile;
 		/*
 		 * override mmap operation of the vmfile so that it can't be
diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c
index babbd94c32d9..33a9777e7a99 100644
--- a/drivers/staging/android/ion/ion_heap.c
+++ b/drivers/staging/android/ion/ion_heap.c
@@ -105,12 +105,12 @@ int ion_heap_map_user(struct ion_heap *heap, struct ion_buffer *buffer,
 
 static int ion_heap_clear_pages(struct page **pages, int num, pgprot_t pgprot)
 {
-	void *addr = vm_map_ram(pages, num, -1, pgprot);
+	void *addr = vmap(pages, num, VM_MAP, pgprot);
 
 	if (!addr)
 		return -ENOMEM;
 	memset(addr, 0, PAGE_SIZE * num);
-	vm_unmap_ram(addr, num);
+	vunmap(addr);
 
 	return 0;
 }
diff --git a/drivers/staging/comedi/drivers/addi_apci_1032.c b/drivers/staging/comedi/drivers/addi_apci_1032.c
index ccd1a91290bf..536a135cd00b 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1032.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1032.c
@@ -115,14 +115,22 @@ static int apci1032_cos_insn_config(struct comedi_device *dev,
 				    unsigned int *data)
 {
 	struct apci1032_private *devpriv = dev->private;
-	unsigned int shift, oldmask;
+	unsigned int shift, oldmask, himask, lomask;
 
 	switch (data[0]) {
 	case INSN_CONFIG_DIGITAL_TRIG:
 		if (data[1] != 0)
 			return -EINVAL;
 		shift = data[3];
-		oldmask = (1U << shift) - 1;
+		if (shift < 32) {
+			oldmask = (1U << shift) - 1;
+			himask = data[4] << shift;
+			lomask = data[5] << shift;
+		} else {
+			oldmask = 0xffffffffu;
+			himask = 0;
+			lomask = 0;
+		}
 		switch (data[2]) {
 		case COMEDI_DIGITAL_TRIG_DISABLE:
 			devpriv->ctrl = 0;
@@ -145,8 +153,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev,
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS:
 			if (devpriv->ctrl != (APCI1032_CTRL_INT_ENA |
@@ -163,8 +171,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev,
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		default:
 			return -EINVAL;
diff --git a/drivers/staging/comedi/drivers/addi_apci_1500.c b/drivers/staging/comedi/drivers/addi_apci_1500.c
index 63991c49ff23..c4e36fb6df9d 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1500.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1500.c
@@ -461,13 +461,14 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev,
 	struct apci1500_private *devpriv = dev->private;
 	unsigned int trig = data[1];
 	unsigned int shift = data[3];
-	unsigned int hi_mask = data[4] << shift;
-	unsigned int lo_mask = data[5] << shift;
-	unsigned int chan_mask = hi_mask | lo_mask;
-	unsigned int old_mask = (1 << shift) - 1;
-	unsigned int pm = devpriv->pm[trig] & old_mask;
-	unsigned int pt = devpriv->pt[trig] & old_mask;
-	unsigned int pp = devpriv->pp[trig] & old_mask;
+	unsigned int hi_mask;
+	unsigned int lo_mask;
+	unsigned int chan_mask;
+	unsigned int old_mask;
+	unsigned int pm;
+	unsigned int pt;
+	unsigned int pp;
+	unsigned int invalid_chan;
 
 	if (trig > 1) {
 		dev_dbg(dev->class_dev,
@@ -475,11 +476,28 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev,
 		return -EINVAL;
 	}
 
-	if (chan_mask > 0xffff) {
+	if (shift <= 16) {
+		hi_mask = data[4] << shift;
+		lo_mask = data[5] << shift;
+		old_mask = (1U << shift) - 1;
+		invalid_chan = (data[4] | data[5]) >> (16 - shift);
+	} else {
+		hi_mask = 0;
+		lo_mask = 0;
+		old_mask = 0xffff;
+		invalid_chan = data[4] | data[5];
+	}
+	chan_mask = hi_mask | lo_mask;
+
+	if (invalid_chan) {
 		dev_dbg(dev->class_dev, "invalid digital trigger channel\n");
 		return -EINVAL;
 	}
 
+	pm = devpriv->pm[trig] & old_mask;
+	pt = devpriv->pt[trig] & old_mask;
+	pp = devpriv->pp[trig] & old_mask;
+
 	switch (data[2]) {
 	case COMEDI_DIGITAL_TRIG_DISABLE:
 		/* clear trigger configuration */
diff --git a/drivers/staging/comedi/drivers/addi_apci_1564.c b/drivers/staging/comedi/drivers/addi_apci_1564.c
index 9bfb79c2e5c8..1b4ba19d599e 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1564.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1564.c
@@ -340,14 +340,22 @@ static int apci1564_cos_insn_config(struct comedi_device *dev,
 				    unsigned int *data)
 {
 	struct apci1564_private *devpriv = dev->private;
-	unsigned int shift, oldmask;
+	unsigned int shift, oldmask, himask, lomask;
 
 	switch (data[0]) {
 	case INSN_CONFIG_DIGITAL_TRIG:
 		if (data[1] != 0)
 			return -EINVAL;
 		shift = data[3];
-		oldmask = (1U << shift) - 1;
+		if (shift < 32) {
+			oldmask = (1U << shift) - 1;
+			himask = data[4] << shift;
+			lomask = data[5] << shift;
+		} else {
+			oldmask = 0xffffffffu;
+			himask = 0;
+			lomask = 0;
+		}
 		switch (data[2]) {
 		case COMEDI_DIGITAL_TRIG_DISABLE:
 			devpriv->ctrl = 0;
@@ -371,8 +379,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev,
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS:
 			if (devpriv->ctrl != (APCI1564_DI_IRQ_ENA |
@@ -389,8 +397,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev,
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		default:
 			return -EINVAL;
diff --git a/drivers/staging/comedi/drivers/ni_6527.c b/drivers/staging/comedi/drivers/ni_6527.c
index 84c62e256094..6e411b634015 100644
--- a/drivers/staging/comedi/drivers/ni_6527.c
+++ b/drivers/staging/comedi/drivers/ni_6527.c
@@ -341,7 +341,7 @@ static int ni6527_intr_insn_config(struct comedi_device *dev,
 		case COMEDI_DIGITAL_TRIG_ENABLE_EDGES:
 			/* check shift amount */
 			shift = data[3];
-			if (shift >= s->n_chan) {
+			if (shift >= 32) {
 				mask = 0;
 				rising = 0;
 				falling = 0;
diff --git a/drivers/staging/comedi/drivers/vmk80xx.c b/drivers/staging/comedi/drivers/vmk80xx.c
index 1800eb3ae017..cdf86284dd04 100644
--- a/drivers/staging/comedi/drivers/vmk80xx.c
+++ b/drivers/staging/comedi/drivers/vmk80xx.c
@@ -676,6 +676,9 @@ static int vmk80xx_find_usb_endpoints(struct comedi_device *dev)
 	if (!devpriv->ep_rx || !devpriv->ep_tx)
 		return -ENODEV;
 
+	if (!usb_endpoint_maxp(devpriv->ep_rx) || !usb_endpoint_maxp(devpriv->ep_tx))
+		return -EINVAL;
+
 	return 0;
 }
 
diff --git a/drivers/staging/greybus/audio_topology.c b/drivers/staging/greybus/audio_topology.c
index 07fac3948f3a..dcb4e6c69f16 100644
--- a/drivers/staging/greybus/audio_topology.c
+++ b/drivers/staging/greybus/audio_topology.c
@@ -461,6 +461,15 @@ static int gbcodec_mixer_dapm_ctl_put(struct snd_kcontrol *kcontrol,
 	val = ucontrol->value.integer.value[0] & mask;
 	connect = !!val;
 
+	ret = gb_pm_runtime_get_sync(bundle);
+	if (ret)
+		return ret;
+
+	ret = gb_audio_gb_get_control(module->mgmt_connection, data->ctl_id,
+				      GB_AUDIO_INVALID_INDEX, &gbvalue);
+	if (ret)
+		goto exit;
+
 	/* update ucontrol */
 	if (gbvalue.value.integer_value[0] != val) {
 		for (wi = 0; wi < wlist->num_widgets; wi++) {
@@ -474,25 +483,17 @@ static int gbcodec_mixer_dapm_ctl_put(struct snd_kcontrol *kcontrol,
 		gbvalue.value.integer_value[0] =
 			cpu_to_le32(ucontrol->value.integer.value[0]);
 
-		ret = gb_pm_runtime_get_sync(bundle);
-		if (ret)
-			return ret;
-
 		ret = gb_audio_gb_set_control(module->mgmt_connection,
 					      data->ctl_id,
 					      GB_AUDIO_INVALID_INDEX, &gbvalue);
-
-		gb_pm_runtime_put_autosuspend(bundle);
-
-		if (ret) {
-			dev_err_ratelimited(codec->dev,
-					    "%d:Error in %s for %s\n", ret,
-					    __func__, kcontrol->id.name);
-			return ret;
-		}
 	}
 
-	return 0;
+exit:
+	gb_pm_runtime_put_autosuspend(bundle);
+	if (ret)
+		dev_err_ratelimited(codec_dev, "%d:Error in %s for %s\n", ret,
+				    __func__, kcontrol->id.name);
+	return ret;
 }
 
 #define SOC_DAPM_MIXER_GB(xname, kcount, data) \
diff --git a/drivers/staging/greybus/light.c b/drivers/staging/greybus/light.c
index 4e7575147775..9fab0e2751aa 100644
--- a/drivers/staging/greybus/light.c
+++ b/drivers/staging/greybus/light.c
@@ -1033,7 +1033,8 @@ static int gb_lights_light_config(struct gb_lights *glights, u8 id)
 
 	light->channels_count = conf.channel_count;
 	light->name = kstrndup(conf.name, NAMES_MAX, GFP_KERNEL);
-
+	if (!light->name)
+		return -ENOMEM;
 	light->channels = kcalloc(light->channels_count,
 				  sizeof(struct gb_channel), GFP_KERNEL);
 	if (!light->channels)
diff --git a/drivers/staging/greybus/sdio.c b/drivers/staging/greybus/sdio.c
index 101ca5097fc9..93e2c091c565 100644
--- a/drivers/staging/greybus/sdio.c
+++ b/drivers/staging/greybus/sdio.c
@@ -412,6 +412,7 @@ static int gb_sdio_command(struct gb_sdio_host *host, struct mmc_command *cmd)
 	struct gb_sdio_command_request request = {0};
 	struct gb_sdio_command_response response;
 	struct mmc_data *data = host->mrq->data;
+	unsigned int timeout_ms;
 	u8 cmd_flags;
 	u8 cmd_type;
 	int i;
@@ -470,9 +471,12 @@ static int gb_sdio_command(struct gb_sdio_host *host, struct mmc_command *cmd)
 		request.data_blksz = cpu_to_le16(data->blksz);
 	}
 
-	ret = gb_operation_sync(host->connection, GB_SDIO_TYPE_COMMAND,
-				&request, sizeof(request), &response,
-				sizeof(response));
+	timeout_ms = cmd->busy_timeout ? cmd->busy_timeout :
+		GB_OPERATION_TIMEOUT_DEFAULT;
+
+	ret = gb_operation_sync_timeout(host->connection, GB_SDIO_TYPE_COMMAND,
+					&request, sizeof(request), &response,
+					sizeof(response), timeout_ms);
 	if (ret < 0)
 		goto out;
 
diff --git a/drivers/staging/media/imx/imx-media-capture.c b/drivers/staging/media/imx/imx-media-capture.c
index ea145bafb880..8ff8843df514 100644
--- a/drivers/staging/media/imx/imx-media-capture.c
+++ b/drivers/staging/media/imx/imx-media-capture.c
@@ -685,7 +685,7 @@ int imx_media_capture_device_register(struct imx_media_video_dev *vdev)
 	/* setup default format */
 	fmt_src.pad = priv->src_sd_pad;
 	fmt_src.which = V4L2_SUBDEV_FORMAT_ACTIVE;
-	v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt_src);
+	ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt_src);
 	if (ret) {
 		v4l2_err(sd, "failed to get src_sd format\n");
 		goto unreg;
diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c
index 31f35025d19e..af9da2508e93 100644
--- a/drivers/staging/octeon/ethernet-tx.c
+++ b/drivers/staging/octeon/ethernet-tx.c
@@ -264,6 +264,9 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 	pko_command.s.n2 = 1;	/* Don't pollute L2 with the outgoing packet */
 	pko_command.s.segs = 1;
 	pko_command.s.total_bytes = skb->len;
+#if GCC_VERSION >= 80000
+	barrier();
+#endif
 	pko_command.s.size0 = CVMX_FAU_OP_SIZE_32;
 	pko_command.s.subone0 = 1;
 
diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c
index afb9dadc1cfe..77685bae21ed 100644
--- a/drivers/staging/rtl8188eu/core/rtw_recv.c
+++ b/drivers/staging/rtl8188eu/core/rtw_recv.c
@@ -1541,21 +1541,14 @@ static int amsdu_to_msdu(struct adapter *padapter, struct recv_frame *prframe)
 
 		/* Allocate new skb for releasing to upper layer */
 		sub_skb = dev_alloc_skb(nSubframe_Length + 12);
-		if (sub_skb) {
-			skb_reserve(sub_skb, 12);
-			skb_put_data(sub_skb, pdata, nSubframe_Length);
-		} else {
-			sub_skb = skb_clone(prframe->pkt, GFP_ATOMIC);
-			if (sub_skb) {
-				sub_skb->data = pdata;
-				sub_skb->len = nSubframe_Length;
-				skb_set_tail_pointer(sub_skb, nSubframe_Length);
-			} else {
-				DBG_88E("skb_clone() Fail!!! , nr_subframes=%d\n", nr_subframes);
-				break;
-			}
+		if (!sub_skb) {
+			DBG_88E("dev_alloc_skb() Fail!!! , nr_subframes=%d\n", nr_subframes);
+			break;
 		}
 
+		skb_reserve(sub_skb, 12);
+		skb_put_data(sub_skb, pdata, nSubframe_Length);
+
 		subframes[nr_subframes++] = sub_skb;
 
 		if (nr_subframes >= MAX_SUBFRAME_COUNT) {
diff --git a/drivers/staging/rtl8192u/r8192U_core.c b/drivers/staging/rtl8192u/r8192U_core.c
index fbbd1b59dc11..b5941ae410d9 100644
--- a/drivers/staging/rtl8192u/r8192U_core.c
+++ b/drivers/staging/rtl8192u/r8192U_core.c
@@ -2519,7 +2519,7 @@ static int rtl8192_read_eeprom_info(struct net_device *dev)
 				ret = eprom_read(dev, (EEPROM_TxPwIndex_CCK >> 1));
 				if (ret < 0)
 					return ret;
-				priv->EEPROMTxPowerLevelCCK = ((u16)ret & 0xff) >> 8;
+				priv->EEPROMTxPowerLevelCCK = ((u16)ret & 0xff00) >> 8;
 			} else
 				priv->EEPROMTxPowerLevelCCK = 0x10;
 			RT_TRACE(COMP_EPROM, "CCK Tx Power Levl: 0x%02x\n", priv->EEPROMTxPowerLevelCCK);
diff --git a/drivers/staging/rtl8712/wifi.h b/drivers/staging/rtl8712/wifi.h
index 0ed2f44ab4e9..14b899fcd97c 100644
--- a/drivers/staging/rtl8712/wifi.h
+++ b/drivers/staging/rtl8712/wifi.h
@@ -468,7 +468,7 @@ static inline unsigned char *get_hdr_bssid(unsigned char *pframe)
 /* block-ack parameters */
 #define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002
 #define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C
-#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFA0
+#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0
 #define IEEE80211_DELBA_PARAM_TID_MASK 0xF000
 #define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800
 
@@ -562,13 +562,6 @@ struct ieee80211_ht_addt_info {
 #define IEEE80211_HT_IE_NON_GF_STA_PRSNT	0x0004
 #define IEEE80211_HT_IE_NON_HT_STA_PRSNT	0x0010
 
-/* block-ack parameters */
-#define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002
-#define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C
-#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFA0
-#define IEEE80211_DELBA_PARAM_TID_MASK 0xF000
-#define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800
-
 /*
  * A-PMDU buffer sizes
  * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
diff --git a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c
index f485f541e36d..d6de62ee681e 100644
--- a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c
+++ b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c
@@ -1904,12 +1904,14 @@ int update_sta_support_rate(struct adapter *padapter, u8 *pvar_ie, uint var_ie_l
 	pIE = (struct ndis_80211_var_ie *)rtw_get_ie(pvar_ie, _SUPPORTEDRATES_IE_, &ie_len, var_ie_len);
 	if (pIE == NULL)
 		return _FAIL;
+	if (ie_len > sizeof(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates))
+		return _FAIL;
 
 	memcpy(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates, pIE->data, ie_len);
 	supportRateNum = ie_len;
 
 	pIE = (struct ndis_80211_var_ie *)rtw_get_ie(pvar_ie, _EXT_SUPPORTEDRATES_IE_, &ie_len, var_ie_len);
-	if (pIE)
+	if (pIE && (ie_len <= sizeof(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates) - supportRateNum))
 		memcpy((pmlmeinfo->FW_sta_info[cam_idx].SupportedRates + supportRateNum), pIE->data, ie_len);
 
 	return _SUCCESS;
diff --git a/drivers/staging/sm750fb/sm750.c b/drivers/staging/sm750fb/sm750.c
index 67207b0554cd..5d6f3686c0de 100644
--- a/drivers/staging/sm750fb/sm750.c
+++ b/drivers/staging/sm750fb/sm750.c
@@ -899,6 +899,7 @@ static int lynxfb_set_fbinfo(struct fb_info *info, int index)
 		fix->visual = FB_VISUAL_PSEUDOCOLOR;
 		break;
 	case 16:
+	case 24:
 	case 32:
 		fix->visual = FB_VISUAL_TRUECOLOR;
 		break;
diff --git a/drivers/staging/wlan-ng/hfa384x_usb.c b/drivers/staging/wlan-ng/hfa384x_usb.c
index fb1a76c4c927..292ebbce50dc 100644
--- a/drivers/staging/wlan-ng/hfa384x_usb.c
+++ b/drivers/staging/wlan-ng/hfa384x_usb.c
@@ -531,13 +531,8 @@ static void hfa384x_usb_defer(struct work_struct *data)
  */
 void hfa384x_create(struct hfa384x *hw, struct usb_device *usb)
 {
-	memset(hw, 0, sizeof(*hw));
 	hw->usb = usb;
 
-	/* set up the endpoints */
-	hw->endp_in = usb_rcvbulkpipe(usb, 1);
-	hw->endp_out = usb_sndbulkpipe(usb, 2);
-
 	/* Set up the waitq */
 	init_waitqueue_head(&hw->cmdq);
 
diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c
index d8d86761b790..9eee72aff723 100644
--- a/drivers/staging/wlan-ng/prism2usb.c
+++ b/drivers/staging/wlan-ng/prism2usb.c
@@ -61,11 +61,16 @@ static int prism2sta_probe_usb(struct usb_interface *interface,
 			       const struct usb_device_id *id)
 {
 	struct usb_device *dev;
-
+	struct usb_endpoint_descriptor *bulk_in, *bulk_out;
+	struct usb_host_interface *iface_desc = interface->cur_altsetting;
 	struct wlandevice *wlandev = NULL;
 	struct hfa384x *hw = NULL;
 	int result = 0;
 
+	result = usb_find_common_endpoints(iface_desc, &bulk_in, &bulk_out, NULL, NULL);
+	if (result)
+		goto failed;
+
 	dev = interface_to_usbdev(interface);
 	wlandev = create_wlan();
 	if (!wlandev) {
@@ -82,6 +87,8 @@ static int prism2sta_probe_usb(struct usb_interface *interface,
 	}
 
 	/* Initialize the hw data */
+	hw->endp_in = usb_rcvbulkpipe(dev, bulk_in->bEndpointAddress);
+	hw->endp_out = usb_sndbulkpipe(dev, bulk_out->bEndpointAddress);
 	hfa384x_create(hw, dev);
 	hw->wlandev = wlandev;
 
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index ee49b227dc12..da80c03de6ea 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1382,14 +1382,27 @@ static u32 iscsit_do_crypto_hash_sg(
 	sg = cmd->first_data_sg;
 	page_off = cmd->first_data_sg_off;
 
+	if (data_length && page_off) {
+		struct scatterlist first_sg;
+		u32 len = min_t(u32, data_length, sg->length - page_off);
+
+		sg_init_table(&first_sg, 1);
+		sg_set_page(&first_sg, sg_page(sg), len, sg->offset + page_off);
+
+		ahash_request_set_crypt(hash, &first_sg, NULL, len);
+		crypto_ahash_update(hash);
+
+		data_length -= len;
+		sg = sg_next(sg);
+	}
+
 	while (data_length) {
-		u32 cur_len = min_t(u32, data_length, (sg->length - page_off));
+		u32 cur_len = min_t(u32, data_length, sg->length);
 
 		ahash_request_set_crypt(hash, sg, NULL, cur_len);
 		crypto_ahash_update(hash);
 
 		data_length -= cur_len;
-		page_off = 0;
 		/* iscsit_map_iovec has already checked for invalid sg pointers */
 		sg = sg_next(sg);
 	}
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 55df6f99e669..c36d98e901a9 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -1158,7 +1158,7 @@ iscsit_conn_set_transport(struct iscsi_conn *conn, struct iscsit_transport *t)
 }
 
 void iscsi_target_login_sess_out(struct iscsi_conn *conn,
-		struct iscsi_np *np, bool zero_tsih, bool new_sess)
+				 bool zero_tsih, bool new_sess)
 {
 	if (!new_sess)
 		goto old_sess_out;
@@ -1180,7 +1180,6 @@ void iscsi_target_login_sess_out(struct iscsi_conn *conn,
 	conn->sess = NULL;
 
 old_sess_out:
-	iscsi_stop_login_thread_timer(np);
 	/*
 	 * If login negotiation fails check if the Time2Retain timer
 	 * needs to be restarted.
@@ -1440,8 +1439,9 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 new_sess_out:
 	new_sess = true;
 old_sess_out:
+	iscsi_stop_login_thread_timer(np);
 	tpg_np = conn->tpg_np;
-	iscsi_target_login_sess_out(conn, np, zero_tsih, new_sess);
+	iscsi_target_login_sess_out(conn, zero_tsih, new_sess);
 	new_sess = false;
 
 	if (tpg) {
diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h
index c2495e03625c..9b08b24d223d 100644
--- a/drivers/target/iscsi/iscsi_target_login.h
+++ b/drivers/target/iscsi/iscsi_target_login.h
@@ -22,8 +22,7 @@ extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32);
 extern void iscsit_free_conn(struct iscsi_np *, struct iscsi_conn *);
 extern int iscsit_start_kthreads(struct iscsi_conn *);
 extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
-extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *,
-				bool, bool);
+extern void iscsi_target_login_sess_out(struct iscsi_conn *, bool, bool);
 extern int iscsi_target_login_thread(void *);
 
 #endif   /*** ISCSI_TARGET_LOGIN_H ***/
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 87248a2512e5..07335357418c 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -554,12 +554,11 @@ static bool iscsi_target_sk_check_and_clear(struct iscsi_conn *conn, unsigned in
 
 static void iscsi_target_login_drop(struct iscsi_conn *conn, struct iscsi_login *login)
 {
-	struct iscsi_np *np = login->np;
 	bool zero_tsih = login->zero_tsih;
 
 	iscsi_remove_failed_auth_entry(conn);
 	iscsi_target_nego_release(conn);
-	iscsi_target_login_sess_out(conn, np, zero_tsih, true);
+	iscsi_target_login_sess_out(conn, zero_tsih, true);
 }
 
 static void iscsi_target_login_timeout(unsigned long data)
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index c4a5fb6f038f..96601fda47b1 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -997,7 +997,14 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev)
 		struct tcmu_cmd_entry *entry = (void *) mb + CMDR_OFF + udev->cmdr_last_cleaned;
 		struct tcmu_cmd *cmd;
 
-		tcmu_flush_dcache_range(entry, sizeof(*entry));
+		/*
+		 * Flush max. up to end of cmd ring since current entry might
+		 * be a padding that is shorter than sizeof(*entry)
+		 */
+		size_t ring_left = head_to_end(udev->cmdr_last_cleaned,
+					       udev->cmdr_size);
+		tcmu_flush_dcache_range(entry, ring_left < sizeof(*entry) ?
+					ring_left : sizeof(*entry));
 
 		if (tcmu_hdr_get_op(entry->hdr.len_op) == TCMU_OP_PAD) {
 			UPDATE_HEAD(udev->cmdr_last_cleaned,
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index aed995ec2c90..4896fd8c9c11 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -280,11 +280,11 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev,
 	int i;
 	struct freq_table *freq_table = cpufreq_cdev->freq_table;
 
-	for (i = 1; i <= cpufreq_cdev->max_level; i++)
-		if (power > freq_table[i].power)
+	for (i = 0; i < cpufreq_cdev->max_level; i++)
+		if (power >= freq_table[i].power)
 			break;
 
-	return freq_table[i - 1].frequency;
+	return freq_table[i].frequency;
 }
 
 /**
diff --git a/drivers/thermal/mtk_thermal.c b/drivers/thermal/mtk_thermal.c
index 76b92083744c..1e61c09153c9 100644
--- a/drivers/thermal/mtk_thermal.c
+++ b/drivers/thermal/mtk_thermal.c
@@ -407,8 +407,7 @@ static int mtk_thermal_bank_temperature(struct mtk_thermal_bank *bank)
 	u32 raw;
 
 	for (i = 0; i < conf->bank_data[bank->id].num_sensors; i++) {
-		raw = readl(mt->thermal_base +
-			    conf->msr[conf->bank_data[bank->id].sensors[i]]);
+		raw = readl(mt->thermal_base + conf->msr[i]);
 
 		temp = raw_to_mcelsius(mt,
 				       conf->bank_data[bank->id].sensors[i],
@@ -545,8 +544,7 @@ static void mtk_thermal_init_bank(struct mtk_thermal *mt, int num,
 
 	for (i = 0; i < conf->bank_data[num].num_sensors; i++)
 		writel(conf->sensor_mux_values[conf->bank_data[num].sensors[i]],
-		       mt->thermal_base +
-		       conf->adcpnp[conf->bank_data[num].sensors[i]]);
+		       mt->thermal_base + conf->adcpnp[i]);
 
 	writel((1 << conf->bank_data[num].num_sensors) - 1,
 	       mt->thermal_base + TEMP_MONCTL0);
diff --git a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
index fd1113360603..0c3141746edf 100644
--- a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
+++ b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
@@ -49,20 +49,21 @@ static struct temp_sensor_data omap4430_mpu_temp_sensor_data = {
 
 /*
  * Temperature values in milli degree celsius
- * ADC code values from 530 to 923
+ * ADC code values from 13 to 107, see TRM
+ * "18.4.10.2.3 ADC Codes Versus Temperature".
  */
 static const int
 omap4430_adc_to_temp[OMAP4430_ADC_END_VALUE - OMAP4430_ADC_START_VALUE + 1] = {
-	-38000, -35000, -34000, -32000, -30000, -28000, -26000, -24000, -22000,
-	-20000, -18000, -17000, -15000, -13000, -12000, -10000, -8000, -6000,
-	-5000, -3000, -1000, 0, 2000, 3000, 5000, 6000, 8000, 10000, 12000,
-	13000, 15000, 17000, 19000, 21000, 23000, 25000, 27000, 28000, 30000,
-	32000, 33000, 35000, 37000, 38000, 40000, 42000, 43000, 45000, 47000,
-	48000, 50000, 52000, 53000, 55000, 57000, 58000, 60000, 62000, 64000,
-	66000, 68000, 70000, 71000, 73000, 75000, 77000, 78000, 80000, 82000,
-	83000, 85000, 87000, 88000, 90000, 92000, 93000, 95000, 97000, 98000,
-	100000, 102000, 103000, 105000, 107000, 109000, 111000, 113000, 115000,
-	117000, 118000, 120000, 122000, 123000,
+	-40000, -38000, -35000, -34000, -32000, -30000, -28000, -26000, -24000,
+	-22000,	-20000, -18500, -17000, -15000, -13500, -12000, -10000, -8000,
+	-6500, -5000, -3500, -1500, 0, 2000, 3500, 5000, 6500, 8500, 10000,
+	12000, 13500, 15000, 17000, 19000, 21000, 23000, 25000, 27000, 28500,
+	30000, 32000, 33500, 35000, 37000, 38500, 40000, 42000, 43500, 45000,
+	47000, 48500, 50000, 52000, 53500, 55000, 57000, 58500, 60000, 62000,
+	64000, 66000, 68000, 70000, 71500, 73500, 75000, 77000, 78500, 80000,
+	82000, 83500, 85000, 87000, 88500, 90000, 92000, 93500, 95000, 97000,
+	98500, 100000, 102000, 103500, 105000, 107000, 109000, 111000, 113000,
+	115000, 117000, 118500, 120000, 122000, 123500, 125000,
 };
 
 /* OMAP4430 data */
diff --git a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
index 6f2de3a3356d..86850082b24b 100644
--- a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
+++ b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
@@ -67,9 +67,13 @@
  * and thresholds for OMAP4430.
  */
 
-/* ADC conversion table limits */
-#define OMAP4430_ADC_START_VALUE			0
-#define OMAP4430_ADC_END_VALUE				127
+/*
+ * ADC conversion table limits. Ignore values outside the TRM listed
+ * range to avoid bogus thermal shutdowns. See omap4430 TRM chapter
+ * "18.4.10.2.3 ADC Codes Versus Temperature".
+ */
+#define OMAP4430_ADC_START_VALUE			13
+#define OMAP4430_ADC_END_VALUE				107
 /* bandgap clock limits (no control on 4430) */
 #define OMAP4430_MAX_FREQ				32768
 #define OMAP4430_MIN_FREQ				32768
diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
index c211a8e4a210..d43fbe4ad767 100644
--- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
+++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
@@ -183,7 +183,7 @@ int ti_thermal_expose_sensor(struct ti_bandgap *bgp, int id,
 
 	data = ti_bandgap_get_sensor_data(bgp, id);
 
-	if (!data || IS_ERR(data))
+	if (IS_ERR_OR_NULL(data))
 		data = ti_thermal_build_data(bgp, id);
 
 	if (!data)
@@ -210,7 +210,7 @@ int ti_thermal_remove_sensor(struct ti_bandgap *bgp, int id)
 
 	data = ti_bandgap_get_sensor_data(bgp, id);
 
-	if (data && data->ti_thermal) {
+	if (!IS_ERR_OR_NULL(data) && data->ti_thermal) {
 		if (data->our_zone)
 			thermal_zone_device_unregister(data->ti_thermal);
 	}
@@ -276,7 +276,7 @@ int ti_thermal_unregister_cpu_cooling(struct ti_bandgap *bgp, int id)
 
 	data = ti_bandgap_get_sensor_data(bgp, id);
 
-	if (data) {
+	if (!IS_ERR_OR_NULL(data)) {
 		cpufreq_cooling_unregister(data->cool_dev);
 		cpufreq_cpu_put(data->policy);
 	}
diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index fc0ef13f2616..d52221ae1b85 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -357,15 +357,14 @@ static int hvc_open(struct tty_struct *tty, struct file * filp)
 	 * tty fields and return the kref reference.
 	 */
 	if (rc) {
-		tty_port_tty_set(&hp->port, NULL);
-		tty->driver_data = NULL;
-		tty_port_put(&hp->port);
 		printk(KERN_ERR "hvc_open: request_irq failed with rc %d.\n", rc);
-	} else
+	} else {
 		/* We are ready... raise DTR/RTS */
 		if (C_BAUD(tty))
 			if (hp->ops->dtr_rts)
 				hp->ops->dtr_rts(hp, 1);
+		tty_port_set_initialized(&hp->port, true);
+	}
 
 	/* Force wakeup of the polling thread */
 	hvc_kick();
@@ -375,22 +374,12 @@ static int hvc_open(struct tty_struct *tty, struct file * filp)
 
 static void hvc_close(struct tty_struct *tty, struct file * filp)
 {
-	struct hvc_struct *hp;
+	struct hvc_struct *hp = tty->driver_data;
 	unsigned long flags;
 
 	if (tty_hung_up_p(filp))
 		return;
 
-	/*
-	 * No driver_data means that this close was issued after a failed
-	 * hvc_open by the tty layer's release_dev() function and we can just
-	 * exit cleanly because the kref reference wasn't made.
-	 */
-	if (!tty->driver_data)
-		return;
-
-	hp = tty->driver_data;
-
 	spin_lock_irqsave(&hp->port.lock, flags);
 
 	if (--hp->port.count == 0) {
@@ -398,6 +387,9 @@ static void hvc_close(struct tty_struct *tty, struct file * filp)
 		/* We are done with the tty pointer now. */
 		tty_port_tty_set(&hp->port, NULL);
 
+		if (!tty_port_initialized(&hp->port))
+			return;
+
 		if (C_HUPCL(tty))
 			if (hp->ops->dtr_rts)
 				hp->ops->dtr_rts(hp, 0);
@@ -414,6 +406,7 @@ static void hvc_close(struct tty_struct *tty, struct file * filp)
 		 * waking periodically to check chars_in_buffer().
 		 */
 		tty_wait_until_sent(tty, HVC_CLOSE_WAIT);
+		tty_port_set_initialized(&hp->port, false);
 	} else {
 		if (hp->port.count < 0)
 			printk(KERN_ERR "hvc_close %X: oops, count is %d\n",
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index f46bd1af7a10..c70e79a0e9f2 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -677,11 +677,10 @@ static struct gsm_msg *gsm_data_alloc(struct gsm_mux *gsm, u8 addr, int len,
  *	FIXME: lock against link layer control transmissions
  */
 
-static void gsm_data_kick(struct gsm_mux *gsm)
+static void gsm_data_kick(struct gsm_mux *gsm, struct gsm_dlci *dlci)
 {
 	struct gsm_msg *msg, *nmsg;
 	int len;
-	int skip_sof = 0;
 
 	list_for_each_entry_safe(msg, nmsg, &gsm->tx_list, list) {
 		if (gsm->constipated && msg->addr)
@@ -703,18 +702,23 @@ static void gsm_data_kick(struct gsm_mux *gsm)
 			print_hex_dump_bytes("gsm_data_kick: ",
 					     DUMP_PREFIX_OFFSET,
 					     gsm->txframe, len);
-
-		if (gsm->output(gsm, gsm->txframe + skip_sof,
-						len - skip_sof) < 0)
+		if (gsm->output(gsm, gsm->txframe, len) < 0)
 			break;
 		/* FIXME: Can eliminate one SOF in many more cases */
 		gsm->tx_bytes -= msg->len;
-		/* For a burst of frames skip the extra SOF within the
-		   burst */
-		skip_sof = 1;
 
 		list_del(&msg->list);
 		kfree(msg);
+
+		if (dlci) {
+			tty_port_tty_wakeup(&dlci->port);
+		} else {
+			int i = 0;
+
+			for (i = 0; i < NUM_DLCI; i++)
+				if (gsm->dlci[i])
+					tty_port_tty_wakeup(&gsm->dlci[i]->port);
+		}
 	}
 }
 
@@ -766,7 +770,7 @@ static void __gsm_data_queue(struct gsm_dlci *dlci, struct gsm_msg *msg)
 	/* Add to the actual output queue */
 	list_add_tail(&msg->list, &gsm->tx_list);
 	gsm->tx_bytes += msg->len;
-	gsm_data_kick(gsm);
+	gsm_data_kick(gsm, dlci);
 }
 
 /**
@@ -1227,7 +1231,7 @@ static void gsm_control_message(struct gsm_mux *gsm, unsigned int command,
 		gsm_control_reply(gsm, CMD_FCON, NULL, 0);
 		/* Kick the link in case it is idling */
 		spin_lock_irqsave(&gsm->tx_lock, flags);
-		gsm_data_kick(gsm);
+		gsm_data_kick(gsm, NULL);
 		spin_unlock_irqrestore(&gsm->tx_lock, flags);
 		break;
 	case CMD_FCOFF:
@@ -2426,7 +2430,7 @@ static void gsmld_write_wakeup(struct tty_struct *tty)
 	/* Queue poll */
 	clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
 	spin_lock_irqsave(&gsm->tx_lock, flags);
-	gsm_data_kick(gsm);
+	gsm_data_kick(gsm, NULL);
 	if (gsm->tx_bytes < TX_THRESH_LO) {
 		gsm_dlci_data_sweep(gsm);
 	}
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 5017a0f46b82..8d46bd612888 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -534,6 +534,7 @@ static void __init serial8250_isa_init_ports(void)
 		 */
 		up->mcr_mask = ~ALPHA_KLUDGE_MCR;
 		up->mcr_force = ALPHA_KLUDGE_MCR;
+		serial8250_set_defaults(up);
 	}
 
 	/* chain base port ops to support Remote Supervisor Adapter */
@@ -557,7 +558,6 @@ static void __init serial8250_isa_init_ports(void)
 		port->membase  = old_serial_port[i].iomem_base;
 		port->iotype   = old_serial_port[i].io_type;
 		port->regshift = old_serial_port[i].iomem_reg_shift;
-		serial8250_set_defaults(up);
 
 		port->irqflags |= irqflag;
 		if (serial8250_isa_config != NULL)
@@ -1065,8 +1065,10 @@ int serial8250_register_8250_port(struct uart_8250_port *up)
 			serial8250_apply_quirks(uart);
 			ret = uart_add_one_port(&serial8250_reg,
 						&uart->port);
-			if (ret == 0)
-				ret = uart->port.line;
+			if (ret)
+				goto err;
+
+			ret = uart->port.line;
 		} else {
 			dev_info(uart->port.dev,
 				"skipping CIR port at 0x%lx / 0x%llx, IRQ %d\n",
@@ -1091,6 +1093,11 @@ int serial8250_register_8250_port(struct uart_8250_port *up)
 	mutex_unlock(&serial_mutex);
 
 	return ret;
+
+err:
+	uart->port.dev = NULL;
+	mutex_unlock(&serial_mutex);
+	return ret;
 }
 EXPORT_SYMBOL(serial8250_register_8250_port);
 
diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c
index 899f36b59af7..fd7d9aa1de9a 100644
--- a/drivers/tty/serial/8250/8250_exar.c
+++ b/drivers/tty/serial/8250/8250_exar.c
@@ -229,7 +229,17 @@ static void setup_gpio(struct pci_dev *pcidev, u8 __iomem *p)
 	 * devices will export them as GPIOs, so we pre-configure them safely
 	 * as inputs.
 	 */
-	u8 dir = pcidev->vendor == PCI_VENDOR_ID_EXAR ? 0xff : 0x00;
+
+	u8 dir = 0x00;
+
+	if  ((pcidev->vendor == PCI_VENDOR_ID_EXAR) &&
+		(pcidev->subsystem_vendor != PCI_VENDOR_ID_SEALEVEL)) {
+		// Configure GPIO as inputs for Commtech adapters
+		dir = 0xff;
+	} else {
+		// Configure GPIO as outputs for SeaLevel adapters
+		dir = 0x00;
+	}
 
 	writeb(0x00, p + UART_EXAR_MPIOINT_7_0);
 	writeb(0x00, p + UART_EXAR_MPIOLVL_7_0);
@@ -619,6 +629,24 @@ static const struct exar8250_board pbn_exar_XR17V35x = {
 	.exit		= pci_xr17v35x_exit,
 };
 
+static const struct exar8250_board pbn_fastcom35x_2 = {
+	.num_ports	= 2,
+	.setup		= pci_xr17v35x_setup,
+	.exit		= pci_xr17v35x_exit,
+};
+
+static const struct exar8250_board pbn_fastcom35x_4 = {
+	.num_ports	= 4,
+	.setup		= pci_xr17v35x_setup,
+	.exit		= pci_xr17v35x_exit,
+};
+
+static const struct exar8250_board pbn_fastcom35x_8 = {
+	.num_ports	= 8,
+	.setup		= pci_xr17v35x_setup,
+	.exit		= pci_xr17v35x_exit,
+};
+
 static const struct exar8250_board pbn_exar_XR17V4358 = {
 	.num_ports	= 12,
 	.has_slave	= true,
@@ -691,9 +719,9 @@ static const struct pci_device_id exar_pci_tbl[] = {
 	EXAR_DEVICE(EXAR, EXAR_XR17V358, pbn_exar_XR17V35x),
 	EXAR_DEVICE(EXAR, EXAR_XR17V4358, pbn_exar_XR17V4358),
 	EXAR_DEVICE(EXAR, EXAR_XR17V8358, pbn_exar_XR17V8358),
-	EXAR_DEVICE(COMMTECH, COMMTECH_4222PCIE, pbn_exar_XR17V35x),
-	EXAR_DEVICE(COMMTECH, COMMTECH_4224PCIE, pbn_exar_XR17V35x),
-	EXAR_DEVICE(COMMTECH, COMMTECH_4228PCIE, pbn_exar_XR17V35x),
+	EXAR_DEVICE(COMMTECH, COMMTECH_4222PCIE, pbn_fastcom35x_2),
+	EXAR_DEVICE(COMMTECH, COMMTECH_4224PCIE, pbn_fastcom35x_4),
+	EXAR_DEVICE(COMMTECH, COMMTECH_4228PCIE, pbn_fastcom35x_8),
 
 	EXAR_DEVICE(COMMTECH, COMMTECH_4222PCI335, pbn_fastcom335_2),
 	EXAR_DEVICE(COMMTECH, COMMTECH_4224PCI335, pbn_fastcom335_4),
diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c
index fa909fa3c4cd..b1363114d538 100644
--- a/drivers/tty/serial/8250/8250_mtk.c
+++ b/drivers/tty/serial/8250/8250_mtk.c
@@ -45,8 +45,21 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios,
 	unsigned long flags;
 	unsigned int baud, quot;
 
+	/*
+	 * Store the requested baud rate before calling the generic 8250
+	 * set_termios method. Standard 8250 port expects bauds to be
+	 * no higher than (uartclk / 16) so the baud will be clamped if it
+	 * gets out of that bound. Mediatek 8250 port supports speed
+	 * higher than that, therefore we'll get original baud rate back
+	 * after calling the generic set_termios method and recalculate
+	 * the speed later in this method.
+	 */
+	baud = tty_termios_baud_rate(termios);
+
 	serial8250_do_set_termios(port, termios, old);
 
+	tty_termios_encode_baud_rate(termios, baud, baud);
+
 	/*
 	 * Mediatek UARTs use an extra highspeed register (UART_MTK_HIGHS)
 	 *
@@ -85,6 +98,11 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios,
 	 */
 	spin_lock_irqsave(&port->lock, flags);
 
+	/*
+	 * Update the per-port timeout.
+	 */
+	uart_update_timeout(port, termios->c_cflag, baud);
+
 	/* set DLAB we have cval saved in up->lcr from the call to the core */
 	serial_port_out(port, UART_LCR, up->lcr | UART_LCR_DLAB);
 	serial_dl_write(up, quot);
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index da04ba1ecf68..726852ebef85 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -773,7 +773,10 @@ static void __dma_rx_do_complete(struct uart_8250_port *p)
 	dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state);
 
 	count = dma->rx_size - state.residue;
-
+	if (count < dma->rx_size)
+		dmaengine_terminate_async(dma->rxchan);
+	if (!count)
+		goto unlock;
 	ret = tty_insert_flip_string(tty_port, dma->rx_buf, count);
 
 	p->port.icount.rx += ret;
@@ -833,7 +836,6 @@ static void omap_8250_rx_dma_flush(struct uart_8250_port *p)
 	spin_unlock_irqrestore(&priv->rx_dma_lock, flags);
 
 	__dma_rx_do_complete(p);
-	dmaengine_terminate_all(dma->rxchan);
 }
 
 static int omap_8250_rx_dma(struct uart_8250_port *p)
@@ -1216,11 +1218,11 @@ static int omap8250_probe(struct platform_device *pdev)
 	spin_lock_init(&priv->rx_dma_lock);
 
 	device_init_wakeup(&pdev->dev, true);
+	pm_runtime_enable(&pdev->dev);
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_set_autosuspend_delay(&pdev->dev, -1);
 
 	pm_runtime_irq_safe(&pdev->dev);
-	pm_runtime_enable(&pdev->dev);
 
 	pm_runtime_get_sync(&pdev->dev);
 
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index b31fed7f1679..071ee37399b7 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -5247,6 +5247,17 @@ static const struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_wch384_4 },
 
+	/*
+	 * Realtek RealManage
+	 */
+	{	PCI_VENDOR_ID_REALTEK, 0x816a,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0, pbn_b0_1_115200 },
+
+	{	PCI_VENDOR_ID_REALTEK, 0x816b,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0, pbn_b0_1_115200 },
+
 	/* Fintek PCI serial cards */
 	{ PCI_DEVICE(0x1c29, 0x1104), .driver_data = pbn_fintek_4 },
 	{ PCI_DEVICE(0x1c29, 0x1108), .driver_data = pbn_fintek_8 },
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 90a93c001e16..9880a50d664f 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -1865,6 +1865,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
 	unsigned char status;
 	unsigned long flags;
 	struct uart_8250_port *up = up_to_u8250p(port);
+	bool skip_rx = false;
 
 	if (iir & UART_IIR_NO_INT)
 		return 0;
@@ -1873,7 +1874,20 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
 
 	status = serial_port_in(port, UART_LSR);
 
-	if (status & (UART_LSR_DR | UART_LSR_BI)) {
+	/*
+	 * If port is stopped and there are no error conditions in the
+	 * FIFO, then don't drain the FIFO, as this may lead to TTY buffer
+	 * overflow. Not servicing, RX FIFO would trigger auto HW flow
+	 * control when FIFO occupancy reaches preset threshold, thus
+	 * halting RX. This only works when auto HW flow control is
+	 * available.
+	 */
+	if (!(status & (UART_LSR_FIFOE | UART_LSR_BRK_ERROR_BITS)) &&
+	    (port->status & (UPSTAT_AUTOCTS | UPSTAT_AUTORTS)) &&
+	    !(port->read_status_mask & UART_LSR_DR))
+		skip_rx = true;
+
+	if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) {
 		if (!up->dma || handle_rx_dma(up, iir))
 			status = serial8250_rx_chars(up, status);
 	}
@@ -2264,6 +2278,10 @@ int serial8250_do_startup(struct uart_port *port)
 
 	if (port->irq && !(up->port.flags & UPF_NO_THRE_TEST)) {
 		unsigned char iir1;
+
+		if (port->irqflags & IRQF_SHARED)
+			disable_irq_nosync(port->irq);
+
 		/*
 		 * Test for UARTs that do not reassert THRE when the
 		 * transmitter is idle and the interrupt has already
@@ -2273,8 +2291,6 @@ int serial8250_do_startup(struct uart_port *port)
 		 * allow register changes to become visible.
 		 */
 		spin_lock_irqsave(&port->lock, flags);
-		if (up->port.irqflags & IRQF_SHARED)
-			disable_irq_nosync(port->irq);
 
 		wait_for_xmitr(up, UART_LSR_THRE);
 		serial_port_out_sync(port, UART_IER, UART_IER_THRI);
@@ -2286,9 +2302,10 @@ int serial8250_do_startup(struct uart_port *port)
 		iir = serial_port_in(port, UART_IIR);
 		serial_port_out(port, UART_IER, 0);
 
+		spin_unlock_irqrestore(&port->lock, flags);
+
 		if (port->irqflags & IRQF_SHARED)
 			enable_irq(port->irq);
-		spin_unlock_irqrestore(&port->lock, flags);
 
 		/*
 		 * If the interrupt is not reasserted, or we otherwise
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 637f72fb6427..49bdd0f8d06a 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2272,9 +2272,8 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
 	clk_disable(uap->clk);
 }
 
-static void __init
-pl011_console_get_options(struct uart_amba_port *uap, int *baud,
-			     int *parity, int *bits)
+static void pl011_console_get_options(struct uart_amba_port *uap, int *baud,
+				      int *parity, int *bits)
 {
 	if (pl011_read(uap, REG_CR) & UART01x_CR_UARTEN) {
 		unsigned int lcr_h, ibrd, fbrd;
@@ -2307,7 +2306,7 @@ pl011_console_get_options(struct uart_amba_port *uap, int *baud,
 	}
 }
 
-static int __init pl011_console_setup(struct console *co, char *options)
+static int pl011_console_setup(struct console *co, char *options)
 {
 	struct uart_amba_port *uap;
 	int baud = 38400;
@@ -2375,8 +2374,8 @@ static int __init pl011_console_setup(struct console *co, char *options)
  *
  *	Returns 0 if console matches; otherwise non-zero to use default matching
  */
-static int __init pl011_console_match(struct console *co, char *name, int idx,
-				      char *options)
+static int pl011_console_match(struct console *co, char *name, int idx,
+			       char *options)
 {
 	unsigned char iotype;
 	resource_size_t addr;
@@ -2605,6 +2604,7 @@ static int pl011_setup_port(struct device *dev, struct uart_amba_port *uap,
 	uap->port.fifosize = uap->fifosize;
 	uap->port.flags = UPF_BOOT_AUTOCONF;
 	uap->port.line = index;
+	spin_lock_init(&uap->port.lock);
 
 	amba_ports[index] = uap;
 
@@ -2613,7 +2613,7 @@ static int pl011_setup_port(struct device *dev, struct uart_amba_port *uap,
 
 static int pl011_register_port(struct uart_amba_port *uap)
 {
-	int ret;
+	int ret, i;
 
 	/* Ensure interrupts from this UART are masked and cleared */
 	pl011_write(0, uap, REG_IMSC);
@@ -2624,6 +2624,9 @@ static int pl011_register_port(struct uart_amba_port *uap)
 		if (ret < 0) {
 			dev_err(uap->port.dev,
 				"Failed to register AMBA-PL011 driver\n");
+			for (i = 0; i < ARRAY_SIZE(amba_ports); i++)
+				if (amba_ports[i] == uap)
+					amba_ports[i] = NULL;
 			return ret;
 		}
 	}
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 630065b551f5..dfa2db6ed322 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -538,6 +538,11 @@ static void dma_tx_callback(void *data)
 
 	if (!uart_circ_empty(xmit) && !uart_tx_stopped(&sport->port))
 		imx_dma_tx(sport);
+	else if (sport->port.rs485.flags & SER_RS485_ENABLED) {
+		temp = readl(sport->port.membase + UCR4);
+		temp |= UCR4_TCEN;
+		writel(temp, sport->port.membase + UCR4);
+	}
 
 	spin_unlock_irqrestore(&sport->port.lock, flags);
 }
@@ -555,6 +560,10 @@ static void imx_dma_tx(struct imx_port *sport)
 	if (sport->dma_is_txing)
 		return;
 
+	temp = readl(sport->port.membase + UCR4);
+	temp &= ~UCR4_TCEN;
+	writel(temp, sport->port.membase + UCR4);
+
 	sport->tx_bytes = uart_circ_chars_pending(xmit);
 
 	if (xmit->tail < xmit->head || xmit->head == 0) {
@@ -617,10 +626,15 @@ static void imx_start_tx(struct uart_port *port)
 		if (!(port->rs485.flags & SER_RS485_RX_DURING_TX))
 			imx_stop_rx(port);
 
-		/* enable transmitter and shifter empty irq */
-		temp = readl(port->membase + UCR4);
-		temp |= UCR4_TCEN;
-		writel(temp, port->membase + UCR4);
+		/*
+		 * Enable transmitter and shifter empty irq only if DMA is off.
+		 * In the DMA case this is done in the tx-callback.
+		 */
+		if (!sport->dma_is_enabled) {
+			temp = readl(port->membase + UCR4);
+			temp |= UCR4_TCEN;
+			writel(temp, port->membase + UCR4);
+		}
 	}
 
 	if (!sport->dma_is_enabled) {
diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index 808373d4e37a..70d29b697e82 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -1165,14 +1165,14 @@ static unsigned int s3c24xx_serial_getclk(struct s3c24xx_uart_port *ourport,
 	struct s3c24xx_uart_info *info = ourport->info;
 	struct clk *clk;
 	unsigned long rate;
-	unsigned int cnt, baud, quot, clk_sel, best_quot = 0;
+	unsigned int cnt, baud, quot, best_quot = 0;
 	char clkname[MAX_CLK_NAME_LENGTH];
 	int calc_deviation, deviation = (1 << 30) - 1;
 
-	clk_sel = (ourport->cfg->clk_sel) ? ourport->cfg->clk_sel :
-			ourport->info->def_clk_sel;
 	for (cnt = 0; cnt < info->num_clks; cnt++) {
-		if (!(clk_sel & (1 << cnt)))
+		/* Keep selected clock if provided */
+		if (ourport->cfg->clk_sel &&
+			!(ourport->cfg->clk_sel & (1 << cnt)))
 			continue;
 
 		sprintf(clkname, "clk_uart_baud%d", cnt);
@@ -1733,9 +1733,11 @@ static int s3c24xx_serial_init_port(struct s3c24xx_uart_port *ourport,
 		ourport->tx_irq = ret + 1;
 	}
 
-	ret = platform_get_irq(platdev, 1);
-	if (ret > 0)
-		ourport->tx_irq = ret;
+	if (!s3c24xx_serial_has_interrupt_mask(port)) {
+		ret = platform_get_irq(platdev, 1);
+		if (ret > 0)
+			ourport->tx_irq = ret;
+	}
 	/*
 	 * DMA is currently supported only on DT platforms, if DMA properties
 	 * are specified.
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index c1655aba131f..590acca60134 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1524,10 +1524,12 @@ static int __init sc16is7xx_init(void)
 #endif
 	return ret;
 
+#ifdef CONFIG_SERIAL_SC16IS7XX_SPI
 err_spi:
 #ifdef CONFIG_SERIAL_SC16IS7XX_I2C
 	i2c_del_driver(&sc16is7xx_i2c_uart_driver);
 #endif
+#endif
 err_i2c:
 	uart_unregister_driver(&sc16is7xx_uart);
 	return ret;
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index 81657f09761c..00a740b8ad27 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1282,6 +1282,7 @@ static int cdns_uart_console_setup(struct console *co, char *options)
 	int bits = 8;
 	int parity = 'n';
 	int flow = 'n';
+	unsigned long time_out;
 
 	if (co->index < 0 || co->index >= CDNS_UART_NR_PORTS)
 		return -EINVAL;
@@ -1295,6 +1296,13 @@ static int cdns_uart_console_setup(struct console *co, char *options)
 	if (options)
 		uart_parse_options(options, &baud, &parity, &bits, &flow);
 
+	/* Wait for tx_empty before setting up the console */
+	time_out = jiffies + usecs_to_jiffies(TX_TIMEOUT);
+
+	while (time_before(jiffies, time_out) &&
+	       cdns_uart_tx_empty(port) != TIOCSER_TEMT)
+		cpu_relax();
+
 	return uart_set_options(port, co, baud, parity, bits, flow);
 }
 
diff --git a/drivers/tty/vcc.c b/drivers/tty/vcc.c
index ef01d24858cd..4e795353192b 100644
--- a/drivers/tty/vcc.c
+++ b/drivers/tty/vcc.c
@@ -612,6 +612,7 @@ static int vcc_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	port->index = vcc_table_add(port);
 	if (port->index == -1) {
 		pr_err("VCC: no more TTY indices left for allocation\n");
+		rv = -ENOMEM;
 		goto free_ldc;
 	}
 
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index b9ec4e2828e2..610cb8338d53 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -126,7 +126,11 @@ static DEFINE_SPINLOCK(func_buf_lock); /* guard 'func_buf'  and friends */
 static unsigned long key_down[BITS_TO_LONGS(KEY_CNT)];	/* keyboard key bitmap */
 static unsigned char shift_down[NR_SHIFT];		/* shift state counters.. */
 static bool dead_key_next;
-static int npadch = -1;					/* -1 or number assembled on pad */
+
+/* Handles a number being assembled on the number pad */
+static bool npadch_active;
+static unsigned int npadch_value;
+
 static unsigned int diacr;
 static char rep;					/* flag telling character repeat */
 
@@ -816,12 +820,12 @@ static void k_shift(struct vc_data *vc, unsigned char value, char up_flag)
 		shift_state &= ~(1 << value);
 
 	/* kludge */
-	if (up_flag && shift_state != old_state && npadch != -1) {
+	if (up_flag && shift_state != old_state && npadch_active) {
 		if (kbd->kbdmode == VC_UNICODE)
-			to_utf8(vc, npadch);
+			to_utf8(vc, npadch_value);
 		else
-			put_queue(vc, npadch & 0xff);
-		npadch = -1;
+			put_queue(vc, npadch_value & 0xff);
+		npadch_active = false;
 	}
 }
 
@@ -839,7 +843,7 @@ static void k_meta(struct vc_data *vc, unsigned char value, char up_flag)
 
 static void k_ascii(struct vc_data *vc, unsigned char value, char up_flag)
 {
-	int base;
+	unsigned int base;
 
 	if (up_flag)
 		return;
@@ -853,10 +857,12 @@ static void k_ascii(struct vc_data *vc, unsigned char value, char up_flag)
 		base = 16;
 	}
 
-	if (npadch == -1)
-		npadch = value;
-	else
-		npadch = npadch * base + value;
+	if (!npadch_active) {
+		npadch_value = 0;
+		npadch_active = true;
+	}
+
+	npadch_value = npadch_value * base + value;
 }
 
 static void k_lock(struct vc_data *vc, unsigned char value, char up_flag)
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 8a4e7879a7a6..781d95113742 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -762,10 +762,19 @@ static const struct tty_port_operations vc_port_ops = {
 	.destruct = vc_port_destruct,
 };
 
+/*
+ * Change # of rows and columns (0 means unchanged/the size of fg_console)
+ * [this is to be used together with some user program
+ * like resize that changes the hardware videomode]
+ */
+#define VC_MAXCOL (32767)
+#define VC_MAXROW (32767)
+
 int vc_allocate(unsigned int currcons)	/* return 0 on success */
 {
 	struct vt_notifier_param param;
 	struct vc_data *vc;
+	int err;
 
 	WARN_CONSOLE_UNLOCKED();
 
@@ -795,6 +804,11 @@ int vc_allocate(unsigned int currcons)	/* return 0 on success */
 	if (!*vc->vc_uni_pagedir_loc)
 		con_set_default_unimap(vc);
 
+	err = -EINVAL;
+	if (vc->vc_cols > VC_MAXCOL || vc->vc_rows > VC_MAXROW ||
+	    vc->vc_screenbuf_size > KMALLOC_MAX_SIZE || !vc->vc_screenbuf_size)
+		goto err_free;
+	err = -ENOMEM;
 	vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_KERNEL);
 	if (!vc->vc_screenbuf)
 		goto err_free;
@@ -812,7 +826,7 @@ int vc_allocate(unsigned int currcons)	/* return 0 on success */
 err_free:
 	kfree(vc);
 	vc_cons[currcons].d = NULL;
-	return -ENOMEM;
+	return err;
 }
 
 static inline int resize_screen(struct vc_data *vc, int width, int height,
@@ -827,14 +841,6 @@ static inline int resize_screen(struct vc_data *vc, int width, int height,
 	return err;
 }
 
-/*
- * Change # of rows and columns (0 means unchanged/the size of fg_console)
- * [this is to be used together with some user program
- * like resize that changes the hardware videomode]
- */
-#define VC_RESIZE_MAXCOL (32767)
-#define VC_RESIZE_MAXROW (32767)
-
 /**
  *	vc_do_resize	-	resizing method for the tty
  *	@tty: tty being resized
@@ -859,7 +865,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	unsigned int old_rows, old_row_size;
 	unsigned int new_cols, new_rows, new_row_size, new_screen_size;
 	unsigned int user;
-	unsigned short *newscreen;
+	unsigned short *oldscreen, *newscreen;
 
 	WARN_CONSOLE_UNLOCKED();
 
@@ -869,7 +875,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	user = vc->vc_resize_user;
 	vc->vc_resize_user = 0;
 
-	if (cols > VC_RESIZE_MAXCOL || lines > VC_RESIZE_MAXROW)
+	if (cols > VC_MAXCOL || lines > VC_MAXROW)
 		return -EINVAL;
 
 	new_cols = (cols ? cols : vc->vc_cols);
@@ -880,7 +886,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	if (new_cols == vc->vc_cols && new_rows == vc->vc_rows)
 		return 0;
 
-	if (new_screen_size > KMALLOC_MAX_SIZE)
+	if (new_screen_size > KMALLOC_MAX_SIZE || !new_screen_size)
 		return -EINVAL;
 	newscreen = kzalloc(new_screen_size, GFP_USER);
 	if (!newscreen)
@@ -941,10 +947,11 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	if (new_scr_end > new_origin)
 		scr_memsetw((void *)new_origin, vc->vc_video_erase_char,
 			    new_scr_end - new_origin);
-	kfree(vc->vc_screenbuf);
+	oldscreen = vc->vc_screenbuf;
 	vc->vc_screenbuf = newscreen;
 	vc->vc_screenbuf_size = new_screen_size;
 	set_origin(vc);
+	kfree(oldscreen);
 
 	/* do part of a reset_terminal() */
 	vc->vc_top = 0;
@@ -3031,6 +3038,7 @@ static int __init con_init(void)
 		INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK);
 		tty_port_init(&vc->port);
 		visual_init(vc, currcons, 1);
+		/* Assuming vc->vc_{cols,rows,screenbuf_size} are sane here. */
 		vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_NOWAIT);
 		vc_init(vc, vc->vc_rows, vc->vc_cols,
 			currcons || !vc->vc_sw->con_save_screen);
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index 699ad55e3ec6..1184105b2a17 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -893,12 +893,22 @@ int vt_ioctl(struct tty_struct *tty,
 			console_lock();
 			vcp = vc_cons[i].d;
 			if (vcp) {
+				int ret;
+				int save_scan_lines = vcp->vc_scan_lines;
+				int save_font_height = vcp->vc_font.height;
+
 				if (v.v_vlin)
 					vcp->vc_scan_lines = v.v_vlin;
 				if (v.v_clin)
 					vcp->vc_font.height = v.v_clin;
 				vcp->vc_resize_user = 1;
-				vc_resize(vcp, v.v_cols, v.v_rows);
+				ret = vc_resize(vcp, v.v_cols, v.v_rows);
+				if (ret) {
+					vcp->vc_scan_lines = save_scan_lines;
+					vcp->vc_font.height = save_font_height;
+					console_unlock();
+					return ret;
+				}
 			}
 			console_unlock();
 		}
diff --git a/drivers/uio/uio_pdrv_genirq.c b/drivers/uio/uio_pdrv_genirq.c
index f598ecddc8a7..b58a504240c4 100644
--- a/drivers/uio/uio_pdrv_genirq.c
+++ b/drivers/uio/uio_pdrv_genirq.c
@@ -148,7 +148,7 @@ static int uio_pdrv_genirq_probe(struct platform_device *pdev)
 	if (!uioinfo->irq) {
 		ret = platform_get_irq(pdev, 0);
 		uioinfo->irq = ret;
-		if (ret == -ENXIO && pdev->dev.of_node)
+		if (ret == -ENXIO)
 			uioinfo->irq = UIO_IRQ_NONE;
 		else if (ret < 0) {
 			dev_err(&pdev->dev, "failed to get IRQ\n");
diff --git a/drivers/usb/c67x00/c67x00-sched.c b/drivers/usb/c67x00/c67x00-sched.c
index 7311ed61e99a..029c8bc54b7a 100644
--- a/drivers/usb/c67x00/c67x00-sched.c
+++ b/drivers/usb/c67x00/c67x00-sched.c
@@ -500,7 +500,7 @@ c67x00_giveback_urb(struct c67x00_hcd *c67x00, struct urb *urb, int status)
 	c67x00_release_urb(c67x00, urb);
 	usb_hcd_unlink_urb_from_ep(c67x00_hcd_to_hcd(c67x00), urb);
 	spin_unlock(&c67x00->lock);
-	usb_hcd_giveback_urb(c67x00_hcd_to_hcd(c67x00), urb, urbp->status);
+	usb_hcd_giveback_urb(c67x00_hcd_to_hcd(c67x00), urb, status);
 	spin_lock(&c67x00->lock);
 }
 
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 70306ae039c0..77410fb42eab 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -1159,6 +1159,29 @@ static void ci_controller_suspend(struct ci_hdrc *ci)
 	enable_irq(ci->irq);
 }
 
+/*
+ * Handle the wakeup interrupt triggered by extcon connector
+ * We need to call ci_irq again for extcon since the first
+ * interrupt (wakeup int) only let the controller be out of
+ * low power mode, but not handle any interrupts.
+ */
+static void ci_extcon_wakeup_int(struct ci_hdrc *ci)
+{
+	struct ci_hdrc_cable *cable_id, *cable_vbus;
+	u32 otgsc = hw_read_otgsc(ci, ~0);
+
+	cable_id = &ci->platdata->id_extcon;
+	cable_vbus = &ci->platdata->vbus_extcon;
+
+	if (!IS_ERR(cable_id->edev) && ci->is_otg &&
+		(otgsc & OTGSC_IDIE) && (otgsc & OTGSC_IDIS))
+		ci_irq(ci->irq, ci);
+
+	if (!IS_ERR(cable_vbus->edev) && ci->is_otg &&
+		(otgsc & OTGSC_BSVIE) && (otgsc & OTGSC_BSVIS))
+		ci_irq(ci->irq, ci);
+}
+
 static int ci_controller_resume(struct device *dev)
 {
 	struct ci_hdrc *ci = dev_get_drvdata(dev);
@@ -1191,6 +1214,7 @@ static int ci_controller_resume(struct device *dev)
 		enable_irq(ci->irq);
 		if (ci_otg_is_fsm_mode(ci))
 			ci_otg_fsm_wakeup_by_srp(ci);
+		ci_extcon_wakeup_int(ci);
 	}
 
 	return 0;
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 38709bee4c20..b3e4b014a1cc 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -390,21 +390,19 @@ static void acm_ctrl_irq(struct urb *urb)
 	if (current_size < expected_size) {
 		/* notification is transmitted fragmented, reassemble */
 		if (acm->nb_size < expected_size) {
-			if (acm->nb_size) {
-				kfree(acm->notification_buffer);
-				acm->nb_size = 0;
-			}
+			u8 *new_buffer;
 			alloc_size = roundup_pow_of_two(expected_size);
-			/*
-			 * kmalloc ensures a valid notification_buffer after a
-			 * use of kfree in case the previous allocation was too
-			 * small. Final freeing is done on disconnect.
-			 */
-			acm->notification_buffer =
-				kmalloc(alloc_size, GFP_ATOMIC);
-			if (!acm->notification_buffer)
+			/* Final freeing is done on disconnect. */
+			new_buffer = krealloc(acm->notification_buffer,
+					      alloc_size, GFP_ATOMIC);
+			if (!new_buffer) {
+				acm->nb_index = 0;
 				goto exit;
+			}
+
+			acm->notification_buffer = new_buffer;
 			acm->nb_size = alloc_size;
+			dr = (struct usb_cdc_notification *)acm->notification_buffer;
 		}
 
 		copy_size = min(current_size,
@@ -602,7 +600,7 @@ static void acm_softint(struct work_struct *work)
 	}
 
 	if (test_and_clear_bit(ACM_ERROR_DELAY, &acm->flags)) {
-		for (i = 0; i < ACM_NR; i++)
+		for (i = 0; i < acm->rx_buflimit; i++)
 			if (test_and_clear_bit(i, &acm->urbs_in_error_delay))
 					acm_submit_read_urb(acm, i, GFP_NOIO);
 	}
@@ -1734,6 +1732,8 @@ static int acm_pre_reset(struct usb_interface *intf)
 
 static const struct usb_device_id acm_ids[] = {
 	/* quirky and broken devices */
+	{ USB_DEVICE(0x0424, 0x274e), /* Microchip Technology, Inc. (formerly SMSC) */
+	  .driver_info = DISABLE_ECHO, }, /* DISABLE ECHO in termios flag */
 	{ USB_DEVICE(0x076d, 0x0006), /* Denso Cradle CU-321 */
 	.driver_info = NO_UNION_NORMAL, },/* has no union descriptor */
 	{ USB_DEVICE(0x17ef, 0x7000), /* Lenovo USB modem */
diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index 5e456a83779d..9775b5c8a313 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -481,7 +481,8 @@ static int usblp_release(struct inode *inode, struct file *file)
 	usb_autopm_put_interface(usblp->intf);
 
 	if (!usblp->present)		/* finish cleanup from disconnect */
-		usblp_cleanup(usblp);
+		usblp_cleanup(usblp);	/* any URBs must be dead */
+
 	mutex_unlock(&usblp_mutex);
 	return 0;
 }
@@ -839,6 +840,11 @@ static ssize_t usblp_read(struct file *file, char __user *buffer, size_t len, lo
 	if (rv < 0)
 		return rv;
 
+	if (!usblp->present) {
+		count = -ENODEV;
+		goto done;
+	}
+
 	if ((avail = usblp->rstatus) < 0) {
 		printk(KERN_ERR "usblp%d: error %d reading from printer\n",
 		    usblp->minor, (int)avail);
@@ -1388,9 +1394,11 @@ static void usblp_disconnect(struct usb_interface *intf)
 
 	usblp_unlink_urbs(usblp);
 	mutex_unlock(&usblp->mut);
+	usb_poison_anchored_urbs(&usblp->urbs);
 
 	if (!usblp->used)
 		usblp_cleanup(usblp);
+
 	mutex_unlock(&usblp_mutex);
 }
 
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 298c91f83aee..7337d8f317aa 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -1143,6 +1143,34 @@ void usb_disable_interface(struct usb_device *dev, struct usb_interface *intf,
 	}
 }
 
+/*
+ * usb_disable_device_endpoints -- Disable all endpoints for a device
+ * @dev: the device whose endpoints are being disabled
+ * @skip_ep0: 0 to disable endpoint 0, 1 to skip it.
+ */
+static void usb_disable_device_endpoints(struct usb_device *dev, int skip_ep0)
+{
+	struct usb_hcd *hcd = bus_to_hcd(dev->bus);
+	int i;
+
+	if (hcd->driver->check_bandwidth) {
+		/* First pass: Cancel URBs, leave endpoint pointers intact. */
+		for (i = skip_ep0; i < 16; ++i) {
+			usb_disable_endpoint(dev, i, false);
+			usb_disable_endpoint(dev, i + USB_DIR_IN, false);
+		}
+		/* Remove endpoints from the host controller internal state */
+		mutex_lock(hcd->bandwidth_mutex);
+		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
+		mutex_unlock(hcd->bandwidth_mutex);
+	}
+	/* Second pass: remove endpoint pointers */
+	for (i = skip_ep0; i < 16; ++i) {
+		usb_disable_endpoint(dev, i, true);
+		usb_disable_endpoint(dev, i + USB_DIR_IN, true);
+	}
+}
+
 /**
  * usb_disable_device - Disable all the endpoints for a USB device
  * @dev: the device whose endpoints are being disabled
@@ -1156,7 +1184,6 @@ void usb_disable_interface(struct usb_device *dev, struct usb_interface *intf,
 void usb_disable_device(struct usb_device *dev, int skip_ep0)
 {
 	int i;
-	struct usb_hcd *hcd = bus_to_hcd(dev->bus);
 
 	/* getting rid of interfaces will disconnect
 	 * any drivers bound to them (a key side effect)
@@ -1202,22 +1229,8 @@ void usb_disable_device(struct usb_device *dev, int skip_ep0)
 
 	dev_dbg(&dev->dev, "%s nuking %s URBs\n", __func__,
 		skip_ep0 ? "non-ep0" : "all");
-	if (hcd->driver->check_bandwidth) {
-		/* First pass: Cancel URBs, leave endpoint pointers intact. */
-		for (i = skip_ep0; i < 16; ++i) {
-			usb_disable_endpoint(dev, i, false);
-			usb_disable_endpoint(dev, i + USB_DIR_IN, false);
-		}
-		/* Remove endpoints from the host controller internal state */
-		mutex_lock(hcd->bandwidth_mutex);
-		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
-		mutex_unlock(hcd->bandwidth_mutex);
-		/* Second pass: remove endpoint pointers */
-	}
-	for (i = skip_ep0; i < 16; ++i) {
-		usb_disable_endpoint(dev, i, true);
-		usb_disable_endpoint(dev, i + USB_DIR_IN, true);
-	}
+
+	usb_disable_device_endpoints(dev, skip_ep0);
 }
 
 /**
@@ -1460,6 +1473,9 @@ EXPORT_SYMBOL_GPL(usb_set_interface);
  * The caller must own the device lock.
  *
  * Return: Zero on success, else a negative error code.
+ *
+ * If this routine fails the device will probably be in an unusable state
+ * with endpoints disabled, and interfaces only partially enabled.
  */
 int usb_reset_configuration(struct usb_device *dev)
 {
@@ -1475,10 +1491,7 @@ int usb_reset_configuration(struct usb_device *dev)
 	 * calls during probe() are fine
 	 */
 
-	for (i = 1; i < 16; ++i) {
-		usb_disable_endpoint(dev, i, true);
-		usb_disable_endpoint(dev, i + USB_DIR_IN, true);
-	}
+	usb_disable_device_endpoints(dev, 1); /* skip ep0*/
 
 	config = dev->actconfig;
 	retval = 0;
@@ -1491,34 +1504,10 @@ int usb_reset_configuration(struct usb_device *dev)
 		mutex_unlock(hcd->bandwidth_mutex);
 		return -ENOMEM;
 	}
-	/* Make sure we have enough bandwidth for each alternate setting 0 */
-	for (i = 0; i < config->desc.bNumInterfaces; i++) {
-		struct usb_interface *intf = config->interface[i];
-		struct usb_host_interface *alt;
 
-		alt = usb_altnum_to_altsetting(intf, 0);
-		if (!alt)
-			alt = &intf->altsetting[0];
-		if (alt != intf->cur_altsetting)
-			retval = usb_hcd_alloc_bandwidth(dev, NULL,
-					intf->cur_altsetting, alt);
-		if (retval < 0)
-			break;
-	}
-	/* If not, reinstate the old alternate settings */
+	/* xHCI adds all endpoints in usb_hcd_alloc_bandwidth */
+	retval = usb_hcd_alloc_bandwidth(dev, config, NULL, NULL);
 	if (retval < 0) {
-reset_old_alts:
-		for (i--; i >= 0; i--) {
-			struct usb_interface *intf = config->interface[i];
-			struct usb_host_interface *alt;
-
-			alt = usb_altnum_to_altsetting(intf, 0);
-			if (!alt)
-				alt = &intf->altsetting[0];
-			if (alt != intf->cur_altsetting)
-				usb_hcd_alloc_bandwidth(dev, NULL,
-						alt, intf->cur_altsetting);
-		}
 		usb_enable_lpm(dev);
 		mutex_unlock(hcd->bandwidth_mutex);
 		return retval;
@@ -1527,8 +1516,12 @@ reset_old_alts:
 			USB_REQ_SET_CONFIGURATION, 0,
 			config->desc.bConfigurationValue, 0,
 			NULL, 0, USB_CTRL_SET_TIMEOUT);
-	if (retval < 0)
-		goto reset_old_alts;
+	if (retval < 0) {
+		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
+		usb_enable_lpm(dev);
+		mutex_unlock(hcd->bandwidth_mutex);
+		return retval;
+	}
 	mutex_unlock(hcd->bandwidth_mutex);
 
 	/* re-init hc/hcd interface/endpoint state */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 27d05f0134de..dd72e85f2e17 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -73,11 +73,12 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Logitech HD Webcam C270 */
 	{ USB_DEVICE(0x046d, 0x0825), .driver_info = USB_QUIRK_RESET_RESUME },
 
-	/* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */
+	/* Logitech HD Pro Webcams C920, C920-C, C922, C925e and C930e */
 	{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
 	{ USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT },
 	{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
 	{ USB_DEVICE(0x046d, 0x085b), .driver_info = USB_QUIRK_DELAY_INIT },
+	{ USB_DEVICE(0x046d, 0x085c), .driver_info = USB_QUIRK_DELAY_INIT },
 
 	/* Logitech ConferenceCam CC3000e */
 	{ USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT },
@@ -235,6 +236,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Generic RTL8153 based ethernet adapters */
 	{ USB_DEVICE(0x0bda, 0x8153), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* SONiX USB DEVICE Touchpad */
+	{ USB_DEVICE(0x0c45, 0x7056), .driver_info =
+			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
 	/* Action Semiconductor flash disk */
 	{ USB_DEVICE(0x10d6, 0x2200), .driver_info =
 			USB_QUIRK_STRING_FETCH_255 },
@@ -298,6 +303,8 @@ static const struct usb_device_id usb_quirk_list[] = {
 
 	{ USB_DEVICE(0x2386, 0x3119), .driver_info = USB_QUIRK_NO_LPM },
 
+	{ USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* DJI CineSSD */
 	{ USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM },
 
diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
index 15c19863f7b3..e97834c35092 100644
--- a/drivers/usb/core/sysfs.c
+++ b/drivers/usb/core/sysfs.c
@@ -865,7 +865,11 @@ read_descriptors(struct file *filp, struct kobject *kobj,
 	size_t srclen, n;
 	int cfgno;
 	void *src;
+	int retval;
 
+	retval = usb_lock_device_interruptible(udev);
+	if (retval < 0)
+		return -EINTR;
 	/* The binary attribute begins with the device descriptor.
 	 * Following that are the raw descriptor entries for all the
 	 * configurations (config plus subsidiary descriptors).
@@ -890,6 +894,7 @@ read_descriptors(struct file *filp, struct kobject *kobj,
 			off -= srclen;
 		}
 	}
+	usb_unlock_device(udev);
 	return count - nleft;
 }
 
diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c
index b8bcb007c92a..e3e0a3ab31da 100644
--- a/drivers/usb/dwc2/core_intr.c
+++ b/drivers/usb/dwc2/core_intr.c
@@ -364,10 +364,13 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg)
 			if (ret && (ret != -ENOTSUPP))
 				dev_err(hsotg->dev, "exit hibernation failed\n");
 
+			/* Change to L0 state */
+			hsotg->lx_state = DWC2_L0;
 			call_gadget(hsotg, resume);
+		} else {
+			/* Change to L0 state */
+			hsotg->lx_state = DWC2_L0;
 		}
-		/* Change to L0 state */
-		hsotg->lx_state = DWC2_L0;
 	} else {
 		if (hsotg->params.hibernation)
 			return;
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index aeb6f7c84ea0..03bc479d04e0 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -4723,12 +4723,6 @@ int dwc2_gadget_init(struct dwc2_hsotg *hsotg, int irq)
 					  epnum, 0);
 	}
 
-	ret = usb_add_gadget_udc(dev, &hsotg->gadget);
-	if (ret) {
-		dwc2_hsotg_ep_free_request(&hsotg->eps_out[0]->ep,
-					   hsotg->ctrl_req);
-		return ret;
-	}
 	dwc2_hsotg_dump(hsotg);
 
 	return 0;
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index daf0d37acb37..405dccf92a31 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -338,7 +338,8 @@ static void dwc2_driver_shutdown(struct platform_device *dev)
 {
 	struct dwc2_hsotg *hsotg = platform_get_drvdata(dev);
 
-	disable_irq(hsotg->irq);
+	dwc2_disable_global_interrupts(hsotg);
+	synchronize_irq(hsotg->irq);
 }
 
 /**
@@ -452,10 +453,23 @@ static int dwc2_driver_probe(struct platform_device *dev)
 	if (hsotg->dr_mode == USB_DR_MODE_PERIPHERAL)
 		dwc2_lowlevel_hw_disable(hsotg);
 
+#if IS_ENABLED(CONFIG_USB_DWC2_PERIPHERAL) || \
+	IS_ENABLED(CONFIG_USB_DWC2_DUAL_ROLE)
+	/* Postponed adding a new gadget to the udc class driver list */
+	if (hsotg->gadget_enabled) {
+		retval = usb_add_gadget_udc(hsotg->dev, &hsotg->gadget);
+		if (retval) {
+			hsotg->gadget.udc = NULL;
+			dwc2_hsotg_remove(hsotg);
+			goto error;
+		}
+	}
+#endif /* CONFIG_USB_DWC2_PERIPHERAL || CONFIG_USB_DWC2_DUAL_ROLE */
 	return 0;
 
 error:
-	dwc2_lowlevel_hw_disable(hsotg);
+	if (hsotg->dr_mode != USB_DR_MODE_PERIPHERAL)
+		dwc2_lowlevel_hw_disable(hsotg);
 	return retval;
 }
 
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 4149d751719e..4a4236873464 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -276,7 +276,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned cmd,
 {
 	const struct usb_endpoint_descriptor *desc = dep->endpoint.desc;
 	struct dwc3		*dwc = dep->dwc;
-	u32			timeout = 1000;
+	u32			timeout = 5000;
 	u32			saved_config = 0;
 	u32			reg;
 
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index c1f037af9702..7d2715e899bb 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -100,40 +100,43 @@ function_descriptors(struct usb_function *f,
 }
 
 /**
- * next_ep_desc() - advance to the next EP descriptor
+ * next_desc() - advance to the next desc_type descriptor
  * @t: currect pointer within descriptor array
+ * @desc_type: descriptor type
  *
- * Return: next EP descriptor or NULL
+ * Return: next desc_type descriptor or NULL
  *
- * Iterate over @t until either EP descriptor found or
+ * Iterate over @t until either desc_type descriptor found or
  * NULL (that indicates end of list) encountered
  */
 static struct usb_descriptor_header**
-next_ep_desc(struct usb_descriptor_header **t)
+next_desc(struct usb_descriptor_header **t, u8 desc_type)
 {
 	for (; *t; t++) {
-		if ((*t)->bDescriptorType == USB_DT_ENDPOINT)
+		if ((*t)->bDescriptorType == desc_type)
 			return t;
 	}
 	return NULL;
 }
 
 /*
- * for_each_ep_desc()- iterate over endpoint descriptors in the
- *		descriptors list
- * @start:	pointer within descriptor array.
- * @ep_desc:	endpoint descriptor to use as the loop cursor
+ * for_each_desc() - iterate over desc_type descriptors in the
+ * descriptors list
+ * @start: pointer within descriptor array.
+ * @iter_desc: desc_type descriptor to use as the loop cursor
+ * @desc_type: wanted descriptr type
  */
-#define for_each_ep_desc(start, ep_desc) \
-	for (ep_desc = next_ep_desc(start); \
-	      ep_desc; ep_desc = next_ep_desc(ep_desc+1))
+#define for_each_desc(start, iter_desc, desc_type) \
+	for (iter_desc = next_desc(start, desc_type); \
+	     iter_desc; iter_desc = next_desc(iter_desc + 1, desc_type))
 
 /**
- * config_ep_by_speed() - configures the given endpoint
+ * config_ep_by_speed_and_alt() - configures the given endpoint
  * according to gadget speed.
  * @g: pointer to the gadget
  * @f: usb function
  * @_ep: the endpoint to configure
+ * @alt: alternate setting number
  *
  * Return: error code, 0 on success
  *
@@ -146,11 +149,13 @@ next_ep_desc(struct usb_descriptor_header **t)
  * Note: the supplied function should hold all the descriptors
  * for supported speeds
  */
-int config_ep_by_speed(struct usb_gadget *g,
-			struct usb_function *f,
-			struct usb_ep *_ep)
+int config_ep_by_speed_and_alt(struct usb_gadget *g,
+				struct usb_function *f,
+				struct usb_ep *_ep,
+				u8 alt)
 {
 	struct usb_endpoint_descriptor *chosen_desc = NULL;
+	struct usb_interface_descriptor *int_desc = NULL;
 	struct usb_descriptor_header **speed_desc = NULL;
 
 	struct usb_ss_ep_comp_descriptor *comp_desc = NULL;
@@ -186,8 +191,21 @@ int config_ep_by_speed(struct usb_gadget *g,
 	default:
 		speed_desc = f->fs_descriptors;
 	}
+
+	/* find correct alternate setting descriptor */
+	for_each_desc(speed_desc, d_spd, USB_DT_INTERFACE) {
+		int_desc = (struct usb_interface_descriptor *)*d_spd;
+
+		if (int_desc->bAlternateSetting == alt) {
+			speed_desc = d_spd;
+			goto intf_found;
+		}
+	}
+	return -EIO;
+
+intf_found:
 	/* find descriptors */
-	for_each_ep_desc(speed_desc, d_spd) {
+	for_each_desc(speed_desc, d_spd, USB_DT_ENDPOINT) {
 		chosen_desc = (struct usb_endpoint_descriptor *)*d_spd;
 		if (chosen_desc->bEndpointAddress == _ep->address)
 			goto ep_found;
@@ -240,6 +258,32 @@ ep_found:
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(config_ep_by_speed_and_alt);
+
+/**
+ * config_ep_by_speed() - configures the given endpoint
+ * according to gadget speed.
+ * @g: pointer to the gadget
+ * @f: usb function
+ * @_ep: the endpoint to configure
+ *
+ * Return: error code, 0 on success
+ *
+ * This function chooses the right descriptors for a given
+ * endpoint according to gadget speed and saves it in the
+ * endpoint desc field. If the endpoint already has a descriptor
+ * assigned to it - overwrites it with currently corresponding
+ * descriptor. The endpoint maxpacket field is updated according
+ * to the chosen descriptor.
+ * Note: the supplied function should hold all the descriptors
+ * for supported speeds
+ */
+int config_ep_by_speed(struct usb_gadget *g,
+			struct usb_function *f,
+			struct usb_ep *_ep)
+{
+	return config_ep_by_speed_and_alt(g, f, _ep, 0);
+}
 EXPORT_SYMBOL_GPL(config_ep_by_speed);
 
 /**
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 5c2d39232bb0..f62cdf1238d7 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -1202,9 +1202,11 @@ static int ncm_unwrap_ntb(struct gether *port,
 	int		ndp_index;
 	unsigned	dg_len, dg_len2;
 	unsigned	ndp_len;
+	unsigned	block_len;
 	struct sk_buff	*skb2;
 	int		ret = -EINVAL;
-	unsigned	max_size = le32_to_cpu(ntb_parameters.dwNtbOutMaxSize);
+	unsigned	ntb_max = le32_to_cpu(ntb_parameters.dwNtbOutMaxSize);
+	unsigned	frame_max = le16_to_cpu(ecm_desc.wMaxSegmentSize);
 	const struct ndp_parser_opts *opts = ncm->parser_opts;
 	unsigned	crc_len = ncm->is_crc ? sizeof(uint32_t) : 0;
 	int		dgram_counter;
@@ -1226,8 +1228,9 @@ static int ncm_unwrap_ntb(struct gether *port,
 	}
 	tmp++; /* skip wSequence */
 
+	block_len = get_ncm(&tmp, opts->block_length);
 	/* (d)wBlockLength */
-	if (get_ncm(&tmp, opts->block_length) > max_size) {
+	if (block_len > ntb_max) {
 		INFO(port->func.config->cdev, "OUT size exceeded\n");
 		goto err;
 	}
@@ -1236,15 +1239,23 @@ static int ncm_unwrap_ntb(struct gether *port,
 
 	/* Run through all the NDP's in the NTB */
 	do {
-		/* NCM 3.2 */
-		if (((ndp_index % 4) != 0) &&
-				(ndp_index < opts->nth_size)) {
+		/*
+		 * NCM 3.2
+		 * dwNdpIndex
+		 */
+		if (((ndp_index % 4) != 0) ||
+				(ndp_index < opts->nth_size) ||
+				(ndp_index > (block_len -
+					      opts->ndp_size))) {
 			INFO(port->func.config->cdev, "Bad index: %#X\n",
 			     ndp_index);
 			goto err;
 		}
 
-		/* walk through NDP */
+		/*
+		 * walk through NDP
+		 * dwSignature
+		 */
 		tmp = (void *)(skb->data + ndp_index);
 		if (get_unaligned_le32(tmp) != ncm->ndp_sign) {
 			INFO(port->func.config->cdev, "Wrong NDP SIGN\n");
@@ -1255,14 +1266,15 @@ static int ncm_unwrap_ntb(struct gether *port,
 		ndp_len = get_unaligned_le16(tmp++);
 		/*
 		 * NCM 3.3.1
+		 * wLength
 		 * entry is 2 items
 		 * item size is 16/32 bits, opts->dgram_item_len * 2 bytes
 		 * minimal: struct usb_cdc_ncm_ndpX + normal entry + zero entry
 		 * Each entry is a dgram index and a dgram length.
 		 */
 		if ((ndp_len < opts->ndp_size
-				+ 2 * 2 * (opts->dgram_item_len * 2))
-				|| (ndp_len % opts->ndplen_align != 0)) {
+				+ 2 * 2 * (opts->dgram_item_len * 2)) ||
+				(ndp_len % opts->ndplen_align != 0)) {
 			INFO(port->func.config->cdev, "Bad NDP length: %#X\n",
 			     ndp_len);
 			goto err;
@@ -1279,8 +1291,21 @@ static int ncm_unwrap_ntb(struct gether *port,
 
 		do {
 			index = index2;
+			/* wDatagramIndex[0] */
+			if ((index < opts->nth_size) ||
+					(index > block_len - opts->dpe_size)) {
+				INFO(port->func.config->cdev,
+				     "Bad index: %#X\n", index);
+				goto err;
+			}
+
 			dg_len = dg_len2;
-			if (dg_len < 14 + crc_len) { /* ethernet hdr + crc */
+			/*
+			 * wDatagramLength[0]
+			 * ethernet hdr + crc or larger than max frame size
+			 */
+			if ((dg_len < 14 + crc_len) ||
+					(dg_len > frame_max)) {
 				INFO(port->func.config->cdev,
 				     "Bad dgram length: %#X\n", dg_len);
 				goto err;
@@ -1304,6 +1329,13 @@ static int ncm_unwrap_ntb(struct gether *port,
 			index2 = get_ncm(&tmp, opts->dgram_item_len);
 			dg_len2 = get_ncm(&tmp, opts->dgram_item_len);
 
+			/* wDatagramIndex[1] */
+			if (index2 > block_len - opts->dpe_size) {
+				INFO(port->func.config->cdev,
+				     "Bad index: %#X\n", index2);
+				goto err;
+			}
+
 			/*
 			 * Copy the data into a new skb.
 			 * This ensures the truesize is correct
@@ -1320,7 +1352,6 @@ static int ncm_unwrap_ntb(struct gether *port,
 			ndp_len -= 2 * (opts->dgram_item_len * 2);
 
 			dgram_counter++;
-
 			if (index2 == 0 || dg_len2 == 0)
 				break;
 		} while (ndp_len > 2 * (opts->dgram_item_len * 2));
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index a82e2bd5ea34..c41d09166a1d 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -751,12 +751,13 @@ static int uasp_alloc_stream_res(struct f_uas *fu, struct uas_stream *stream)
 		goto err_sts;
 
 	return 0;
+
 err_sts:
-	usb_ep_free_request(fu->ep_status, stream->req_status);
-	stream->req_status = NULL;
-err_out:
 	usb_ep_free_request(fu->ep_out, stream->req_out);
 	stream->req_out = NULL;
+err_out:
+	usb_ep_free_request(fu->ep_in, stream->req_in);
+	stream->req_in = NULL;
 out:
 	return -ENOMEM;
 }
diff --git a/drivers/usb/gadget/function/f_uac1_legacy.c b/drivers/usb/gadget/function/f_uac1_legacy.c
index 5d229e72912e..3092fa1ca239 100644
--- a/drivers/usb/gadget/function/f_uac1_legacy.c
+++ b/drivers/usb/gadget/function/f_uac1_legacy.c
@@ -339,7 +339,9 @@ static int f_audio_out_ep_complete(struct usb_ep *ep, struct usb_request *req)
 
 	/* Copy buffer is full, add it to the play_queue */
 	if (audio_buf_size - copy_buf->actual < req->actual) {
+		spin_lock_irq(&audio->lock);
 		list_add_tail(&copy_buf->list, &audio->play_queue);
+		spin_unlock_irq(&audio->lock);
 		schedule_work(&audio->playback_work);
 		copy_buf = f_audio_buffer_alloc(audio_buf_size);
 		if (IS_ERR(copy_buf))
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 5c28bee327e1..e431a8bc3a9d 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -1364,7 +1364,6 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 
 	req->buf = dev->rbuf;
 	req->context = NULL;
-	value = -EOPNOTSUPP;
 	switch (ctrl->bRequest) {
 
 	case USB_REQ_GET_DESCRIPTOR:
@@ -1788,7 +1787,7 @@ static ssize_t
 dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 {
 	struct dev_data		*dev = fd->private_data;
-	ssize_t			value = len, length = len;
+	ssize_t			value, length = len;
 	unsigned		total;
 	u32			tag;
 	char			*kbuf;
diff --git a/drivers/usb/gadget/u_f.h b/drivers/usb/gadget/u_f.h
index 2f03334c6874..d150a6795f48 100644
--- a/drivers/usb/gadget/u_f.h
+++ b/drivers/usb/gadget/u_f.h
@@ -17,6 +17,7 @@
 #define __U_F_H__
 
 #include <linux/usb/gadget.h>
+#include <linux/overflow.h>
 
 /* Variable Length Array Macros **********************************************/
 #define vla_group(groupname) size_t groupname##__next = 0
@@ -24,21 +25,36 @@
 
 #define vla_item(groupname, type, name, n) \
 	size_t groupname##_##name##__offset = ({			       \
-		size_t align_mask = __alignof__(type) - 1;		       \
-		size_t offset = (groupname##__next + align_mask) & ~align_mask;\
-		size_t size = (n) * sizeof(type);			       \
-		groupname##__next = offset + size;			       \
+		size_t offset = 0;					       \
+		if (groupname##__next != SIZE_MAX) {			       \
+			size_t align_mask = __alignof__(type) - 1;	       \
+			size_t size = array_size(n, sizeof(type));	       \
+			offset = (groupname##__next + align_mask) &	       \
+				  ~align_mask;				       \
+			if (check_add_overflow(offset, size,		       \
+					       &groupname##__next)) {          \
+				groupname##__next = SIZE_MAX;		       \
+				offset = 0;				       \
+			}						       \
+		}							       \
 		offset;							       \
 	})
 
 #define vla_item_with_sz(groupname, type, name, n) \
-	size_t groupname##_##name##__sz = (n) * sizeof(type);		       \
-	size_t groupname##_##name##__offset = ({			       \
-		size_t align_mask = __alignof__(type) - 1;		       \
-		size_t offset = (groupname##__next + align_mask) & ~align_mask;\
-		size_t size = groupname##_##name##__sz;			       \
-		groupname##__next = offset + size;			       \
-		offset;							       \
+	size_t groupname##_##name##__sz = array_size(n, sizeof(type));	        \
+	size_t groupname##_##name##__offset = ({			        \
+		size_t offset = 0;						\
+		if (groupname##__next != SIZE_MAX) {				\
+			size_t align_mask = __alignof__(type) - 1;		\
+			offset = (groupname##__next + align_mask) &		\
+				  ~align_mask;					\
+			if (check_add_overflow(offset, groupname##_##name##__sz,\
+							&groupname##__next)) {	\
+				groupname##__next = SIZE_MAX;			\
+				offset = 0;					\
+			}							\
+		}								\
+		offset;								\
 	})
 
 #define vla_ptr(ptr, groupname, name) \
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 39676824a2c6..8540e52c28a9 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -912,7 +912,7 @@ static int usba_ep_dequeue(struct usb_ep *_ep, struct usb_request *_req)
 	u32 status;
 
 	DBG(DBG_GADGET | DBG_QUEUE, "ep_dequeue: %s, req %p\n",
-			ep->ep.name, req);
+			ep->ep.name, _req);
 
 	spin_lock_irqsave(&udc->lock, flags);
 
diff --git a/drivers/usb/gadget/udc/bdc/bdc_core.c b/drivers/usb/gadget/udc/bdc/bdc_core.c
index 7a8af4b916cf..58ba04d858ba 100644
--- a/drivers/usb/gadget/udc/bdc/bdc_core.c
+++ b/drivers/usb/gadget/udc/bdc/bdc_core.c
@@ -288,6 +288,7 @@ static void bdc_mem_init(struct bdc *bdc, bool reinit)
 	 * in that case reinit is passed as 1
 	 */
 	if (reinit) {
+		int i;
 		/* Enable interrupts */
 		temp = bdc_readl(bdc->regs, BDC_BDCSC);
 		temp |= BDC_GIE;
@@ -297,6 +298,9 @@ static void bdc_mem_init(struct bdc *bdc, bool reinit)
 		/* Initialize SRR to 0 */
 		memset(bdc->srr.sr_bds, 0,
 					NUM_SR_ENTRIES * sizeof(struct bdc_bd));
+		/* clear ep flags to avoid post disconnect stops/deconfigs */
+		for (i = 1; i < bdc->num_eps; ++i)
+			bdc->bdc_ep_array[i]->flags = 0;
 	} else {
 		/* One time initiaization only */
 		/* Enable status report function pointers */
@@ -609,9 +613,14 @@ static int bdc_remove(struct platform_device *pdev)
 static int bdc_suspend(struct device *dev)
 {
 	struct bdc *bdc = dev_get_drvdata(dev);
+	int ret;
 
-	clk_disable_unprepare(bdc->clk);
-	return 0;
+	/* Halt the controller */
+	ret = bdc_stop(bdc);
+	if (!ret)
+		clk_disable_unprepare(bdc->clk);
+
+	return ret;
 }
 
 static int bdc_resume(struct device *dev)
diff --git a/drivers/usb/gadget/udc/bdc/bdc_ep.c b/drivers/usb/gadget/udc/bdc/bdc_ep.c
index be9f40bc9c12..bb2d5ebd97b5 100644
--- a/drivers/usb/gadget/udc/bdc/bdc_ep.c
+++ b/drivers/usb/gadget/udc/bdc/bdc_ep.c
@@ -621,7 +621,6 @@ int bdc_ep_enable(struct bdc_ep *ep)
 	}
 	bdc_dbg_bd_list(bdc, ep);
 	/* only for ep0: config ep is called for ep0 from connect event */
-	ep->flags |= BDC_EP_ENABLED;
 	if (ep->ep_num == 1)
 		return ret;
 
@@ -765,10 +764,13 @@ static int ep_dequeue(struct bdc_ep *ep, struct bdc_req *req)
 					__func__, ep->name, start_bdi, end_bdi);
 	dev_dbg(bdc->dev, "ep_dequeue ep=%p ep->desc=%p\n",
 						ep, (void *)ep->usb_ep.desc);
-	/* Stop the ep to see where the HW is ? */
-	ret = bdc_stop_ep(bdc, ep->ep_num);
-	/* if there is an issue with stopping ep, then no need to go further */
-	if (ret)
+	/* if still connected, stop the ep to see where the HW is ? */
+	if (!(bdc_readl(bdc->regs, BDC_USPC) & BDC_PST_MASK)) {
+		ret = bdc_stop_ep(bdc, ep->ep_num);
+		/* if there is an issue, then no need to go further */
+		if (ret)
+			return 0;
+	} else
 		return 0;
 
 	/*
@@ -1917,7 +1919,9 @@ static int bdc_gadget_ep_disable(struct usb_ep *_ep)
 		__func__, ep->name, ep->flags);
 
 	if (!(ep->flags & BDC_EP_ENABLED)) {
-		dev_warn(bdc->dev, "%s is already disabled\n", ep->name);
+		if (bdc->gadget.speed != USB_SPEED_UNKNOWN)
+			dev_warn(bdc->dev, "%s is already disabled\n",
+				 ep->name);
 		return 0;
 	}
 	spin_lock_irqsave(&bdc->lock, flags);
diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c
index feb73a1c42ef..be094f4e116b 100644
--- a/drivers/usb/gadget/udc/gr_udc.c
+++ b/drivers/usb/gadget/udc/gr_udc.c
@@ -2000,9 +2000,12 @@ static int gr_ep_init(struct gr_udc *dev, int num, int is_in, u32 maxplimit)
 
 	if (num == 0) {
 		_req = gr_alloc_request(&ep->ep, GFP_ATOMIC);
+		if (!_req)
+			return -ENOMEM;
+
 		buf = devm_kzalloc(dev->dev, PAGE_SIZE, GFP_DMA | GFP_ATOMIC);
-		if (!_req || !buf) {
-			/* possible _req freed by gr_probe via gr_remove */
+		if (!buf) {
+			gr_free_request(&ep->ep, _req);
 			return -ENOMEM;
 		}
 
diff --git a/drivers/usb/gadget/udc/lpc32xx_udc.c b/drivers/usb/gadget/udc/lpc32xx_udc.c
index ac2aa04ca657..710793161795 100644
--- a/drivers/usb/gadget/udc/lpc32xx_udc.c
+++ b/drivers/usb/gadget/udc/lpc32xx_udc.c
@@ -1615,17 +1615,17 @@ static int lpc32xx_ep_enable(struct usb_ep *_ep,
 			     const struct usb_endpoint_descriptor *desc)
 {
 	struct lpc32xx_ep *ep = container_of(_ep, struct lpc32xx_ep, ep);
-	struct lpc32xx_udc *udc = ep->udc;
+	struct lpc32xx_udc *udc;
 	u16 maxpacket;
 	u32 tmp;
 	unsigned long flags;
 
 	/* Verify EP data */
 	if ((!_ep) || (!ep) || (!desc) ||
-	    (desc->bDescriptorType != USB_DT_ENDPOINT)) {
-		dev_dbg(udc->dev, "bad ep or descriptor\n");
+	    (desc->bDescriptorType != USB_DT_ENDPOINT))
 		return -EINVAL;
-	}
+
+	udc = ep->udc;
 	maxpacket = usb_endpoint_maxp(desc);
 	if ((maxpacket == 0) || (maxpacket > ep->maxpacket)) {
 		dev_dbg(udc->dev, "bad ep descriptor's packet size\n");
@@ -1873,7 +1873,7 @@ static int lpc32xx_ep_dequeue(struct usb_ep *_ep, struct usb_request *_req)
 static int lpc32xx_ep_set_halt(struct usb_ep *_ep, int value)
 {
 	struct lpc32xx_ep *ep = container_of(_ep, struct lpc32xx_ep, ep);
-	struct lpc32xx_udc *udc = ep->udc;
+	struct lpc32xx_udc *udc;
 	unsigned long flags;
 
 	if ((!ep) || (ep->hwep_num <= 1))
@@ -1883,6 +1883,7 @@ static int lpc32xx_ep_set_halt(struct usb_ep *_ep, int value)
 	if (ep->is_in)
 		return -EAGAIN;
 
+	udc = ep->udc;
 	spin_lock_irqsave(&udc->lock, flags);
 
 	if (value == 1) {
diff --git a/drivers/usb/gadget/udc/m66592-udc.c b/drivers/usb/gadget/udc/m66592-udc.c
index 46ce7bc15f2b..53abad98af6d 100644
--- a/drivers/usb/gadget/udc/m66592-udc.c
+++ b/drivers/usb/gadget/udc/m66592-udc.c
@@ -1672,7 +1672,7 @@ static int m66592_probe(struct platform_device *pdev)
 
 err_add_udc:
 	m66592_free_request(&m66592->ep[0].ep, m66592->ep0_req);
-
+	m66592->ep0_req = NULL;
 clean_up3:
 	if (m66592->pdata->on_chip) {
 		clk_disable(m66592->clk);
diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c
index 4103bf7cf52a..62fad60d0c06 100644
--- a/drivers/usb/gadget/udc/mv_udc_core.c
+++ b/drivers/usb/gadget/udc/mv_udc_core.c
@@ -2317,7 +2317,8 @@ static int mv_udc_probe(struct platform_device *pdev)
 	return 0;
 
 err_create_workqueue:
-	destroy_workqueue(udc->qwork);
+	if (udc->qwork)
+		destroy_workqueue(udc->qwork);
 err_destroy_dma:
 	dma_pool_destroy(udc->dtd_pool);
 err_free_dma:
diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c
index 170327f84ea1..f1ac9a49e2bf 100644
--- a/drivers/usb/gadget/udc/net2280.c
+++ b/drivers/usb/gadget/udc/net2280.c
@@ -3786,8 +3786,10 @@ static int net2280_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return 0;
 
 done:
-	if (dev)
+	if (dev) {
 		net2280_remove(pdev);
+		kfree(dev);
+	}
 	return retval;
 }
 
diff --git a/drivers/usb/gadget/udc/s3c2410_udc.c b/drivers/usb/gadget/udc/s3c2410_udc.c
index 394abd5d65c0..cf12ca567e69 100644
--- a/drivers/usb/gadget/udc/s3c2410_udc.c
+++ b/drivers/usb/gadget/udc/s3c2410_udc.c
@@ -268,10 +268,6 @@ static void s3c2410_udc_done(struct s3c2410_ep *ep,
 static void s3c2410_udc_nuke(struct s3c2410_udc *udc,
 		struct s3c2410_ep *ep, int status)
 {
-	/* Sanity check */
-	if (&ep->queue == NULL)
-		return;
-
 	while (!list_empty(&ep->queue)) {
 		struct s3c2410_request *req;
 		req = list_entry(ep->queue.next, struct s3c2410_request,
diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c
index 26b641100639..be72a625dc21 100644
--- a/drivers/usb/host/ehci-exynos.c
+++ b/drivers/usb/host/ehci-exynos.c
@@ -199,9 +199,8 @@ skip_phy:
 	hcd->rsrc_len = resource_size(res);
 
 	irq = platform_get_irq(pdev, 0);
-	if (!irq) {
-		dev_err(&pdev->dev, "Failed to get IRQ\n");
-		err = -ENODEV;
+	if (irq < 0) {
+		err = irq;
 		goto fail_io;
 	}
 
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 6e834b83a104..44b7066b1246 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -35,6 +35,7 @@
 #include <linux/interrupt.h>
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
+#include <linux/usb/otg.h>
 #include <linux/moduleparam.h>
 #include <linux/dma-mapping.h>
 #include <linux/debugfs.h>
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index 37ef2ac9cdae..c144172a09a4 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -27,7 +27,6 @@
  */
 
 /*-------------------------------------------------------------------------*/
-#include <linux/usb/otg.h>
 
 #define	PORT_WAKE_BITS	(PORT_WKOC_E|PORT_WKDISC_E|PORT_WKCONN_E)
 
diff --git a/drivers/usb/host/ehci-mv.c b/drivers/usb/host/ehci-mv.c
index 849806a75f1c..b29610899c9f 100644
--- a/drivers/usb/host/ehci-mv.c
+++ b/drivers/usb/host/ehci-mv.c
@@ -196,12 +196,10 @@ static int mv_ehci_probe(struct platform_device *pdev)
 	hcd->rsrc_len = resource_size(r);
 	hcd->regs = ehci_mv->op_regs;
 
-	hcd->irq = platform_get_irq(pdev, 0);
-	if (!hcd->irq) {
-		dev_err(&pdev->dev, "Cannot get irq.");
-		retval = -ENODEV;
+	retval = platform_get_irq(pdev, 0);
+	if (retval < 0)
 		goto err_disable_clk;
-	}
+	hcd->irq = retval;
 
 	ehci = hcd_to_ehci(hcd);
 	ehci->caps = (struct ehci_caps *) ehci_mv->cap_regs;
diff --git a/drivers/usb/host/ehci-mxc.c b/drivers/usb/host/ehci-mxc.c
index c7a9b31eeaef..637079a35003 100644
--- a/drivers/usb/host/ehci-mxc.c
+++ b/drivers/usb/host/ehci-mxc.c
@@ -63,6 +63,8 @@ static int ehci_mxc_drv_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
 
 	hcd = usb_create_hcd(&ehci_mxc_hc_driver, dev, dev_name(dev));
 	if (!hcd)
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index 93326974ff4b..265c9af1d2b5 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -229,6 +229,13 @@ static int ehci_pci_setup(struct usb_hcd *hcd)
 		ehci_info(ehci, "applying MosChip frame-index workaround\n");
 		ehci->frame_index_bug = 1;
 		break;
+	case PCI_VENDOR_ID_HUAWEI:
+		/* Synopsys HC bug */
+		if (pdev->device == 0xa239) {
+			ehci_info(ehci, "applying Synopsys HC workaround\n");
+			ehci->has_synopsys_hc_bug = 1;
+		}
+		break;
 	}
 
 	/* optional debug port, normally in the first BAR */
diff --git a/drivers/usb/host/ohci-exynos.c b/drivers/usb/host/ohci-exynos.c
index 6865b919403f..2ed062a2e93b 100644
--- a/drivers/usb/host/ohci-exynos.c
+++ b/drivers/usb/host/ohci-exynos.c
@@ -166,9 +166,8 @@ skip_phy:
 	hcd->rsrc_len = resource_size(res);
 
 	irq = platform_get_irq(pdev, 0);
-	if (!irq) {
-		dev_err(&pdev->dev, "Failed to get IRQ\n");
-		err = -ENODEV;
+	if (irq < 0) {
+		err = irq;
 		goto fail_io;
 	}
 
diff --git a/drivers/usb/host/ohci-sm501.c b/drivers/usb/host/ohci-sm501.c
index d4e0f7cd96fa..b5592fb518e3 100644
--- a/drivers/usb/host/ohci-sm501.c
+++ b/drivers/usb/host/ohci-sm501.c
@@ -195,6 +195,7 @@ static int ohci_hcd_sm501_drv_remove(struct platform_device *pdev)
 	struct resource	*mem;
 
 	usb_remove_hcd(hcd);
+	iounmap(hcd->regs);
 	release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
 	usb_put_hcd(hcd);
 	dma_release_declared_memory(&pdev->dev);
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index f5f2c83a2c66..dcfb412460c7 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -633,6 +633,9 @@ EXPORT_SYMBOL_GPL(usb_amd_pt_check_port);
  */
 void uhci_reset_hc(struct pci_dev *pdev, unsigned long base)
 {
+#ifdef CONFIG_MIPS_MALTA
+	int timeout = 10;
+#endif
 	/* Turn off PIRQ enable and SMI enable.  (This also turns off the
 	 * BIOS's USB Legacy Support.)  Turn off all the R/WC bits too.
 	 */
@@ -646,9 +649,16 @@ void uhci_reset_hc(struct pci_dev *pdev, unsigned long base)
 	outw(UHCI_USBCMD_HCRESET, base + UHCI_USBCMD);
 	mb();
 	udelay(5);
-	if (inw(base + UHCI_USBCMD) & UHCI_USBCMD_HCRESET)
-		dev_warn(&pdev->dev, "HCRESET not completed yet!\n");
 
+#ifdef CONFIG_MIPS_MALTA
+	while (inw(base + UHCI_USBCMD) & UHCI_USBCMD_HCRESET) {
+	        if (--timeout < 0) {
+			dev_warn(&pdev->dev, "HCRESET timed out!\n");
+			break;
+		}
+		udelay(5);
+	}
+#endif
 	/* Just to be safe, disable interrupt requests and
 	 * make sure the controller is stopped.
 	 */
diff --git a/drivers/usb/host/uhci-q.c b/drivers/usb/host/uhci-q.c
index 49d4edc03cc2..651ff928b970 100644
--- a/drivers/usb/host/uhci-q.c
+++ b/drivers/usb/host/uhci-q.c
@@ -72,7 +72,9 @@ static void uhci_fsbr_off(struct uhci_hcd *uhci)
 static void uhci_add_fsbr(struct uhci_hcd *uhci, struct urb *urb)
 {
 	struct urb_priv *urbp = urb->hcpriv;
-
+#ifdef CONFIG_MIPS_MALTA
+       return;
+#endif
 	if (!(urb->transfer_flags & URB_NO_FSBR))
 		urbp->fsbr = 1;
 }
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 3bb38d9dc45b..592f8183af28 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -750,15 +750,6 @@ static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci,
 {
 	u32 pls = status_reg & PORT_PLS_MASK;
 
-	/* resume state is a xHCI internal state.
-	 * Do not report it to usb core, instead, pretend to be U3,
-	 * thus usb core knows it's not ready for transfer
-	 */
-	if (pls == XDEV_RESUME) {
-		*status |= USB_SS_PORT_LS_U3;
-		return;
-	}
-
 	/* When the CAS bit is set then warm reset
 	 * should be performed on port
 	 */
@@ -781,6 +772,16 @@ static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci,
 		pls |= USB_PORT_STAT_CONNECTION;
 	} else {
 		/*
+		 * Resume state is an xHCI internal state.  Do not report it to
+		 * usb core, instead, pretend to be U3, thus usb core knows
+		 * it's not ready for transfer.
+		 */
+		if (pls == XDEV_RESUME) {
+			*status |= USB_SS_PORT_LS_U3;
+			return;
+		}
+
+		/*
 		 * If CAS bit isn't set but the Port is already at
 		 * Compliance Mode, fake a connection so the USB core
 		 * notices the Compliance state and resets the port.
diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c
index defaf950e631..7120dbfaacab 100644
--- a/drivers/usb/host/xhci-mtk-sch.c
+++ b/drivers/usb/host/xhci-mtk-sch.c
@@ -284,6 +284,10 @@ static bool need_bw_sch(struct usb_host_endpoint *ep,
 	if (is_fs_or_ls(speed) && !has_tt)
 		return false;
 
+	/* skip endpoint with zero maxpkt */
+	if (usb_endpoint_maxp(&ep->desc) == 0)
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c
index 35aecbcac6f7..945e108cffb8 100644
--- a/drivers/usb/host/xhci-mtk.c
+++ b/drivers/usb/host/xhci-mtk.c
@@ -726,6 +726,9 @@ static int xhci_mtk_remove(struct platform_device *dev)
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	struct usb_hcd  *shared_hcd = xhci->shared_hcd;
 
+	pm_runtime_put_noidle(&dev->dev);
+	pm_runtime_disable(&dev->dev);
+
 	usb_remove_hcd(shared_hcd);
 	xhci->shared_hcd = NULL;
 	xhci_mtk_phy_power_off(mtk);
@@ -738,8 +741,6 @@ static int xhci_mtk_remove(struct platform_device *dev)
 	xhci_mtk_sch_exit(mtk);
 	xhci_mtk_clks_disable(mtk);
 	xhci_mtk_ldos_disable(mtk);
-	pm_runtime_put_sync(&dev->dev);
-	pm_runtime_disable(&dev->dev);
 
 	return 0;
 }
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index c01a0d1e8b5c..72c3ba0824f7 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -59,7 +59,10 @@
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3			0x43ba
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_2			0x43bb
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_1			0x43bc
+#define PCI_DEVICE_ID_ASMEDIA_1042_XHCI			0x1042
 #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI		0x1142
+#define PCI_DEVICE_ID_ASMEDIA_1142_XHCI			0x1242
+#define PCI_DEVICE_ID_ASMEDIA_2142_XHCI			0x2142
 
 static const char hcd_name[] = "xhci_hcd";
 
@@ -230,11 +233,15 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
-			pdev->device == 0x1042)
+		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
-			pdev->device == 0x1142)
+		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI)
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
+	    (pdev->device == PCI_DEVICE_ID_ASMEDIA_1142_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_ASMEDIA_2142_XHCI))
+		xhci->quirks |= XHCI_NO_64BIT_SUPPORT;
 
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
 		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI)
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 6c0a0ca316d3..cdf1c9155403 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1346,6 +1346,7 @@ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id,
 				xhci->devs[slot_id]->out_ctx, ep_index);
 
 		ep_ctx = xhci_get_ep_ctx(xhci, command->in_ctx, ep_index);
+		ep_ctx->ep_info &= cpu_to_le32(~EP_STATE_MASK);/* must clear */
 		ep_ctx->ep_info2 &= cpu_to_le32(~MAX_PACKET_MASK);
 		ep_ctx->ep_info2 |= cpu_to_le32(MAX_PACKET(max_packet_size));
 
@@ -4225,6 +4226,9 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd,
 			mutex_lock(hcd->bandwidth_mutex);
 			xhci_change_max_exit_latency(xhci, udev, 0);
 			mutex_unlock(hcd->bandwidth_mutex);
+			readl_poll_timeout(port_array[port_num], pm_val,
+					   (pm_val & PORT_PLS_MASK) == XDEV_U0,
+					   100, 10000);
 			return 0;
 		}
 	}
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index db1af99d53bd..8b52a7773bc8 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -718,7 +718,7 @@ struct xhci_ep_ctx {
  * 4 - TRB error
  * 5-7 - reserved
  */
-#define EP_STATE_MASK		(0xf)
+#define EP_STATE_MASK		(0x7)
 #define EP_STATE_DISABLED	0
 #define EP_STATE_RUNNING	1
 #define EP_STATE_HALTED		2
diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index 1ec32e5aa004..27e1ab9e1b07 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -1,8 +1,9 @@
 /*
  *  Native support for the I/O-Warrior USB devices
  *
- *  Copyright (c) 2003-2005  Code Mercenaries GmbH
- *  written by Christian Lucht <lucht@codemercs.com>
+ *  Copyright (c) 2003-2005, 2020  Code Mercenaries GmbH
+ *  written by Christian Lucht <lucht@codemercs.com> and
+ *  Christoph Jung <jung@codemercs.com>
  *
  *  based on
 
@@ -821,14 +822,28 @@ static int iowarrior_probe(struct usb_interface *interface,
 
 	/* we have to check the report_size often, so remember it in the endianness suitable for our machine */
 	dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint);
-	if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) &&
-	    ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
-	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) ||
-	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) ||
-	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) ||
-	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100)))
-		/* IOWarrior56 has wMaxPacketSize different from report size */
-		dev->report_size = 7;
+
+	/*
+	 * Some devices need the report size to be different than the
+	 * endpoint size.
+	 */
+	if (dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) {
+		switch (dev->product_id) {
+		case USB_DEVICE_ID_CODEMERCS_IOW56:
+		case USB_DEVICE_ID_CODEMERCS_IOW56AM:
+			dev->report_size = 7;
+			break;
+
+		case USB_DEVICE_ID_CODEMERCS_IOW28:
+		case USB_DEVICE_ID_CODEMERCS_IOW28L:
+			dev->report_size = 4;
+			break;
+
+		case USB_DEVICE_ID_CODEMERCS_IOW100:
+			dev->report_size = 13;
+			break;
+		}
+	}
 
 	/* create the urb and buffer for reading */
 	dev->int_in_urb = usb_alloc_urb(0, GFP_KERNEL);
diff --git a/drivers/usb/misc/lvstest.c b/drivers/usb/misc/lvstest.c
index ddddd6387f66..e4a7510f9b0e 100644
--- a/drivers/usb/misc/lvstest.c
+++ b/drivers/usb/misc/lvstest.c
@@ -432,7 +432,7 @@ static int lvs_rh_probe(struct usb_interface *intf,
 			USB_DT_SS_HUB_SIZE, USB_CTRL_GET_TIMEOUT);
 	if (ret < (USB_DT_HUB_NONVAR_SIZE + 2)) {
 		dev_err(&hdev->dev, "wrong root hub descriptor read %d\n", ret);
-		return ret;
+		return ret < 0 ? ret : -EINVAL;
 	}
 
 	/* submit urb to poll interrupt endpoint */
diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c
index a6f88442a53a..a020d5eafb4a 100644
--- a/drivers/usb/misc/sisusbvga/sisusb.c
+++ b/drivers/usb/misc/sisusbvga/sisusb.c
@@ -760,7 +760,7 @@ static int sisusb_write_mem_bulk(struct sisusb_usb_data *sisusb, u32 addr,
 	u8   swap8, fromkern = kernbuffer ? 1 : 0;
 	u16  swap16;
 	u32  swap32, flag = (length >> 28) & 1;
-	char buf[4];
+	u8 buf[4];
 
 	/* if neither kernbuffer not userbuffer are given, assume
 	 * data in obuf
diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c
index b3fc602b2e24..49476c0304b2 100644
--- a/drivers/usb/misc/usbtest.c
+++ b/drivers/usb/misc/usbtest.c
@@ -2769,6 +2769,7 @@ static void usbtest_disconnect(struct usb_interface *intf)
 
 	usb_set_intfdata(intf, NULL);
 	dev_dbg(&intf->dev, "disconnect\n");
+	kfree(dev->buf);
 	kfree(dev);
 }
 
diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index ec42f6b75564..cf4a7ef4e663 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -496,7 +496,7 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer,
 	prepare_to_wait(&dev->waitq, &wait, TASK_INTERRUPTIBLE);
 	dev_dbg(&dev->interface->dev, "%s - submit %c\n", __func__,
 		dev->cntl_buffer[0]);
-	retval = usb_submit_urb(dev->cntl_urb, GFP_KERNEL);
+	retval = usb_submit_urb(dev->cntl_urb, GFP_ATOMIC);
 	if (retval >= 0)
 		timeout = schedule_timeout(YUREX_WRITE_TIMEOUT);
 	finish_wait(&dev->waitq, &wait);
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index dca39c9a13b0..962bf792f658 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -2749,6 +2749,13 @@ static int musb_resume(struct device *dev)
 	musb_enable_interrupts(musb);
 	musb_platform_enable(musb);
 
+	/* session might be disabled in suspend */
+	if (musb->port_mode == MUSB_HOST &&
+	    !(musb->ops->quirks & MUSB_PRESERVE_SESSION)) {
+		devctl |= MUSB_DEVCTL_SESSION;
+		musb_writeb(musb->mregs, MUSB_DEVCTL, devctl);
+	}
+
 	spin_lock_irqsave(&musb->lock, flags);
 	error = musb_run_resume_work(musb);
 	if (error)
diff --git a/drivers/usb/musb/musb_debugfs.c b/drivers/usb/musb/musb_debugfs.c
index 952733ceaac8..480b2119f1e7 100644
--- a/drivers/usb/musb/musb_debugfs.c
+++ b/drivers/usb/musb/musb_debugfs.c
@@ -206,6 +206,11 @@ static ssize_t musb_test_mode_write(struct file *file,
 	u8			test;
 	char			buf[24];
 
+	memset(buf, 0x00, sizeof(buf));
+
+	if (copy_from_user(buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
+		return -EFAULT;
+
 	pm_runtime_get_sync(musb->controller);
 	test = musb_readb(musb->mregs, MUSB_TESTMODE);
 	if (test) {
@@ -214,11 +219,6 @@ static ssize_t musb_test_mode_write(struct file *file,
 		goto ret;
 	}
 
-	memset(buf, 0x00, sizeof(buf));
-
-	if (copy_from_user(buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
-		return -EFAULT;
-
 	if (strstarts(buf, "force host full-speed"))
 		test = MUSB_TEST_FORCE_HOST | MUSB_TEST_FORCE_FS;
 
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index 31cd798d2dac..d45a3f4e752c 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -84,6 +84,7 @@
 
 static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x4348, 0x5523) },
+	{ USB_DEVICE(0x1a86, 0x7522) },
 	{ USB_DEVICE(0x1a86, 0x7523) },
 	{ USB_DEVICE(0x1a86, 0x5523) },
 	{ },
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 8dd9852f399d..630c8338d791 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -271,6 +271,8 @@ static struct usb_serial_driver cp210x_device = {
 	.break_ctl		= cp210x_break_ctl,
 	.set_termios		= cp210x_set_termios,
 	.tx_empty		= cp210x_tx_empty,
+	.throttle		= usb_serial_generic_throttle,
+	.unthrottle		= usb_serial_generic_unthrottle,
 	.tiocmget		= cp210x_tiocmget,
 	.tiocmset		= cp210x_tiocmset,
 	.attach			= cp210x_attach,
@@ -925,6 +927,7 @@ static void cp210x_get_termios_port(struct usb_serial_port *port,
 	u32 baud;
 	u16 bits;
 	u32 ctl_hs;
+	u32 flow_repl;
 
 	cp210x_read_u32_reg(port, CP210X_GET_BAUDRATE, &baud);
 
@@ -1025,6 +1028,22 @@ static void cp210x_get_termios_port(struct usb_serial_port *port,
 	ctl_hs = le32_to_cpu(flow_ctl.ulControlHandshake);
 	if (ctl_hs & CP210X_SERIAL_CTS_HANDSHAKE) {
 		dev_dbg(dev, "%s - flow control = CRTSCTS\n", __func__);
+		/*
+		 * When the port is closed, the CP210x hardware disables
+		 * auto-RTS and RTS is deasserted but it leaves auto-CTS when
+		 * in hardware flow control mode. When re-opening the port, if
+		 * auto-CTS is enabled on the cp210x, then auto-RTS must be
+		 * re-enabled in the driver.
+		 */
+		flow_repl = le32_to_cpu(flow_ctl.ulFlowReplace);
+		flow_repl &= ~CP210X_SERIAL_RTS_MASK;
+		flow_repl |= CP210X_SERIAL_RTS_SHIFT(CP210X_SERIAL_RTS_FLOW_CTL);
+		flow_ctl.ulFlowReplace = cpu_to_le32(flow_repl);
+		cp210x_write_reg_block(port,
+				CP210X_SET_FLOW,
+				&flow_ctl,
+				sizeof(flow_ctl));
+
 		cflag |= CRTSCTS;
 	} else {
 		dev_dbg(dev, "%s - flow control = NONE\n", __func__);
diff --git a/drivers/usb/serial/cypress_m8.c b/drivers/usb/serial/cypress_m8.c
index d0aa4c853f56..a1b5d20a56b9 100644
--- a/drivers/usb/serial/cypress_m8.c
+++ b/drivers/usb/serial/cypress_m8.c
@@ -63,6 +63,7 @@ static const struct usb_device_id id_table_earthmate[] = {
 
 static const struct usb_device_id id_table_cyphidcomrs232[] = {
 	{ USB_DEVICE(VENDOR_ID_CYPRESS, PRODUCT_ID_CYPHIDCOM) },
+	{ USB_DEVICE(VENDOR_ID_SAI, PRODUCT_ID_CYPHIDCOM) },
 	{ USB_DEVICE(VENDOR_ID_POWERCOM, PRODUCT_ID_UPS) },
 	{ USB_DEVICE(VENDOR_ID_FRWD, PRODUCT_ID_CYPHIDCOM_FRWD) },
 	{ }						/* Terminating entry */
@@ -77,6 +78,7 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(VENDOR_ID_DELORME, PRODUCT_ID_EARTHMATEUSB) },
 	{ USB_DEVICE(VENDOR_ID_DELORME, PRODUCT_ID_EARTHMATEUSB_LT20) },
 	{ USB_DEVICE(VENDOR_ID_CYPRESS, PRODUCT_ID_CYPHIDCOM) },
+	{ USB_DEVICE(VENDOR_ID_SAI, PRODUCT_ID_CYPHIDCOM) },
 	{ USB_DEVICE(VENDOR_ID_POWERCOM, PRODUCT_ID_UPS) },
 	{ USB_DEVICE(VENDOR_ID_FRWD, PRODUCT_ID_CYPHIDCOM_FRWD) },
 	{ USB_DEVICE(VENDOR_ID_DAZZLE, PRODUCT_ID_CA42) },
diff --git a/drivers/usb/serial/cypress_m8.h b/drivers/usb/serial/cypress_m8.h
index 35e223751c0e..16b7410ad057 100644
--- a/drivers/usb/serial/cypress_m8.h
+++ b/drivers/usb/serial/cypress_m8.h
@@ -25,6 +25,9 @@
 #define VENDOR_ID_CYPRESS		0x04b4
 #define PRODUCT_ID_CYPHIDCOM		0x5500
 
+/* Simply Automated HID->COM UPB PIM (using Cypress PID 0x5500) */
+#define VENDOR_ID_SAI			0x17dd
+
 /* FRWD Dongle - a GPS sports watch */
 #define VENDOR_ID_FRWD			0x6737
 #define PRODUCT_ID_CYPHIDCOM_FRWD	0x0001
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index a962065227c4..8ed84338a626 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -708,6 +708,7 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(XSENS_VID, XSENS_AWINDA_STATION_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_MTDEVBOARD_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_MTIUSBCONVERTER_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_MTW_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_OMNI1509) },
 	{ USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) },
@@ -1031,6 +1032,11 @@ static const struct usb_device_id id_table_combined[] = {
 	/* U-Blox devices */
 	{ USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ZED_PID) },
 	{ USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ODIN_PID) },
+	/* FreeCalypso USB adapters */
+	{ USB_DEVICE(FTDI_VID, FTDI_FALCONIA_JTAG_BUF_PID),
+		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+	{ USB_DEVICE(FTDI_VID, FTDI_FALCONIA_JTAG_UNBUF_PID),
+		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ }					/* Terminating entry */
 };
 
@@ -2042,12 +2048,11 @@ static int ftdi_prepare_write_buffer(struct usb_serial_port *port,
 #define FTDI_RS_ERR_MASK (FTDI_RS_BI | FTDI_RS_PE | FTDI_RS_FE | FTDI_RS_OE)
 
 static int ftdi_process_packet(struct usb_serial_port *port,
-		struct ftdi_private *priv, char *packet, int len)
+		struct ftdi_private *priv, unsigned char *buf, int len)
 {
+	unsigned char status;
 	int i;
-	char status;
 	char flag;
-	char *ch;
 
 	if (len < 2) {
 		dev_dbg(&port->dev, "malformed packet\n");
@@ -2057,7 +2062,7 @@ static int ftdi_process_packet(struct usb_serial_port *port,
 	/* Compare new line status to the old one, signal if different/
 	   N.B. packet may be processed more than once, but differences
 	   are only processed once.  */
-	status = packet[0] & FTDI_STATUS_B0_MASK;
+	status = buf[0] & FTDI_STATUS_B0_MASK;
 	if (status != priv->prev_status) {
 		char diff_status = status ^ priv->prev_status;
 
@@ -2083,13 +2088,12 @@ static int ftdi_process_packet(struct usb_serial_port *port,
 	}
 
 	/* save if the transmitter is empty or not */
-	if (packet[1] & FTDI_RS_TEMT)
+	if (buf[1] & FTDI_RS_TEMT)
 		priv->transmit_empty = 1;
 	else
 		priv->transmit_empty = 0;
 
-	len -= 2;
-	if (!len)
+	if (len == 2)
 		return 0;	/* status only */
 
 	/*
@@ -2097,40 +2101,41 @@ static int ftdi_process_packet(struct usb_serial_port *port,
 	 * data payload to avoid over-reporting.
 	 */
 	flag = TTY_NORMAL;
-	if (packet[1] & FTDI_RS_ERR_MASK) {
+	if (buf[1] & FTDI_RS_ERR_MASK) {
 		/* Break takes precedence over parity, which takes precedence
 		 * over framing errors */
-		if (packet[1] & FTDI_RS_BI) {
+		if (buf[1] & FTDI_RS_BI) {
 			flag = TTY_BREAK;
 			port->icount.brk++;
 			usb_serial_handle_break(port);
-		} else if (packet[1] & FTDI_RS_PE) {
+		} else if (buf[1] & FTDI_RS_PE) {
 			flag = TTY_PARITY;
 			port->icount.parity++;
-		} else if (packet[1] & FTDI_RS_FE) {
+		} else if (buf[1] & FTDI_RS_FE) {
 			flag = TTY_FRAME;
 			port->icount.frame++;
 		}
 		/* Overrun is special, not associated with a char */
-		if (packet[1] & FTDI_RS_OE) {
+		if (buf[1] & FTDI_RS_OE) {
 			port->icount.overrun++;
 			tty_insert_flip_char(&port->port, 0, TTY_OVERRUN);
 		}
 	}
 
-	port->icount.rx += len;
-	ch = packet + 2;
+	port->icount.rx += len - 2;
 
 	if (port->port.console && port->sysrq) {
-		for (i = 0; i < len; i++, ch++) {
-			if (!usb_serial_handle_sysrq_char(port, *ch))
-				tty_insert_flip_char(&port->port, *ch, flag);
+		for (i = 2; i < len; i++) {
+			if (usb_serial_handle_sysrq_char(port, buf[i]))
+				continue;
+			tty_insert_flip_char(&port->port, buf[i], flag);
 		}
 	} else {
-		tty_insert_flip_string_fixed_flag(&port->port, ch, flag, len);
+		tty_insert_flip_string_fixed_flag(&port->port, buf + 2, flag,
+				len - 2);
 	}
 
-	return len;
+	return len - 2;
 }
 
 static void ftdi_process_read_urb(struct urb *urb)
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index e8373528264c..3d47c6d72256 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -39,6 +39,13 @@
 
 #define FTDI_LUMEL_PD12_PID	0x6002
 
+/*
+ * Custom USB adapters made by Falconia Partners LLC
+ * for FreeCalypso project, ID codes allocated to Falconia by FTDI.
+ */
+#define FTDI_FALCONIA_JTAG_BUF_PID	0x7150
+#define FTDI_FALCONIA_JTAG_UNBUF_PID	0x7151
+
 /* Sienna Serial Interface by Secyourit GmbH */
 #define FTDI_SIENNA_PID		0x8348
 
@@ -160,6 +167,7 @@
 #define XSENS_AWINDA_DONGLE_PID 0x0102
 #define XSENS_MTW_PID		0x0200	/* Xsens MTw */
 #define XSENS_MTDEVBOARD_PID	0x0300	/* Motion Tracker Development Board */
+#define XSENS_MTIUSBCONVERTER_PID	0x0301	/* MTi USB converter */
 #define XSENS_CONVERTER_PID	0xD00D	/* Xsens USB-serial converter */
 
 /* Xsens devices using FTDI VID */
diff --git a/drivers/usb/serial/iuu_phoenix.c b/drivers/usb/serial/iuu_phoenix.c
index 18fc992a245f..0c9e24b217f7 100644
--- a/drivers/usb/serial/iuu_phoenix.c
+++ b/drivers/usb/serial/iuu_phoenix.c
@@ -359,10 +359,11 @@ static void iuu_led_activity_on(struct urb *urb)
 	struct usb_serial_port *port = urb->context;
 	int result;
 	char *buf_ptr = port->write_urb->transfer_buffer;
-	*buf_ptr++ = IUU_SET_LED;
+
 	if (xmas) {
-		get_random_bytes(buf_ptr, 6);
-		*(buf_ptr+7) = 1;
+		buf_ptr[0] = IUU_SET_LED;
+		get_random_bytes(buf_ptr + 1, 6);
+		buf_ptr[7] = 1;
 	} else {
 		iuu_rgbf_fill_buffer(buf_ptr, 255, 255, 0, 0, 0, 0, 255);
 	}
@@ -380,13 +381,14 @@ static void iuu_led_activity_off(struct urb *urb)
 	struct usb_serial_port *port = urb->context;
 	int result;
 	char *buf_ptr = port->write_urb->transfer_buffer;
+
 	if (xmas) {
 		iuu_rxcmd(urb);
 		return;
-	} else {
-		*buf_ptr++ = IUU_SET_LED;
-		iuu_rgbf_fill_buffer(buf_ptr, 0, 0, 255, 255, 0, 0, 255);
 	}
+
+	iuu_rgbf_fill_buffer(buf_ptr, 0, 0, 255, 255, 0, 0, 255);
+
 	usb_fill_bulk_urb(port->write_urb, port->serial->dev,
 			  usb_sndbulkpipe(port->serial->dev,
 					  port->bulk_out_endpointAddress),
@@ -704,14 +706,16 @@ static int iuu_uart_write(struct tty_struct *tty, struct usb_serial_port *port,
 	struct iuu_private *priv = usb_get_serial_port_data(port);
 	unsigned long flags;
 
-	if (count > 256)
-		return -ENOMEM;
-
 	spin_lock_irqsave(&priv->lock, flags);
 
+	count = min(count, 256 - priv->writelen);
+	if (count == 0)
+		goto out;
+
 	/* fill the buffer */
 	memcpy(priv->writebuf + priv->writelen, buf, count);
 	priv->writelen += count;
+out:
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return count;
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 3621bde2a0ed..3fc14b377464 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -248,6 +248,7 @@ static void option_instat_callback(struct urb *urb);
 /* These Quectel products use Quectel's vendor ID */
 #define QUECTEL_PRODUCT_EC21			0x0121
 #define QUECTEL_PRODUCT_EC25			0x0125
+#define QUECTEL_PRODUCT_EG95			0x0195
 #define QUECTEL_PRODUCT_BG96			0x0296
 #define QUECTEL_PRODUCT_EP06			0x0306
 #define QUECTEL_PRODUCT_EM12			0x0512
@@ -530,6 +531,7 @@ static void option_instat_callback(struct urb *urb);
 /* Cellient products */
 #define CELLIENT_VENDOR_ID			0x2692
 #define CELLIENT_PRODUCT_MEN200			0x9005
+#define CELLIENT_PRODUCT_MPL200			0x9025
 
 /* Hyundai Petatel Inc. products */
 #define PETATEL_VENDOR_ID			0x1ff4
@@ -1096,12 +1098,18 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R410M),
 	  .driver_info = RSVD(1) | RSVD(3) },
 	/* Quectel products using Quectel vendor ID */
-	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
-	  .driver_info = RSVD(4) },
-	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25),
-	  .driver_info = RSVD(4) },
-	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96),
-	  .driver_info = RSVD(4) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
@@ -1160,6 +1168,10 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1031, 0xff),	/* Telit LE910C1-EUX */
+	 .driver_info = NCTRL(0) | RSVD(3) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1033, 0xff),	/* Telit LE910C1-EUX (ECM) */
+	 .driver_info = NCTRL(0) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0),
 	  .driver_info = RSVD(0) | RSVD(1) | NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG1),
@@ -1178,6 +1190,8 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1053, 0xff),	/* Telit FN980 (ECM) */
 	  .driver_info = NCTRL(0) | RSVD(1) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1054, 0xff),	/* Telit FT980-KS */
+	  .driver_info = NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
@@ -1815,6 +1829,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9003, 0xff) },	/* Simcom SIM7500/SIM7600 MBIM mode */
 	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9011, 0xff),	/* Simcom SIM7500/SIM7600 RNDIS mode */
 	  .driver_info = RSVD(7) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9205, 0xff) },	/* Simcom SIM7070/SIM7080/SIM7090 AT+ECM mode */
+	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9206, 0xff) },	/* Simcom SIM7070/SIM7080/SIM7090 AT-only mode */
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200),
 	  .driver_info = NCTRL(0) | NCTRL(1) | RSVD(4) },
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X220_X500D),
@@ -1972,6 +1988,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_4COM2, 0xff, 0x02, 0x01) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_4COM2, 0xff, 0x00, 0x00) },
 	{ USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MEN200) },
+	{ USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MPL200),
+	  .driver_info = RSVD(1) | RSVD(4) },
 	{ USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T_600A) },
 	{ USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T_600E) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, TPLINK_PRODUCT_LTE, 0xff, 0x00, 0x00) },	/* TP-Link LTE Module */
@@ -2026,6 +2044,9 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(4) | RSVD(5) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff),			/* Fibocom NL678 series */
 	  .driver_info = RSVD(6) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) },			/* GosunCn GM500 RNDIS */
+	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) },			/* GosunCn GM500 MBIM */
+	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) },			/* GosunCn GM500 ECM/NCM */
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 5051b1dad09e..7fb62dd77317 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -97,6 +97,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LD220_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LD220TA_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LD381_PRODUCT_ID) },
+	{ USB_DEVICE(HP_VENDOR_ID, HP_LD381GC_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LD960_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LD960TA_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LCM220_PRODUCT_ID) },
diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index f0a9eeb6272d..c01b31a2a5d2 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -126,6 +126,7 @@
 
 /* Hewlett-Packard POS Pole Displays */
 #define HP_VENDOR_ID		0x03f0
+#define HP_LD381GC_PRODUCT_ID	0x0183
 #define HP_LM920_PRODUCT_ID	0x026b
 #define HP_TD620_PRODUCT_ID	0x0956
 #define HP_LD960_PRODUCT_ID	0x0b39
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index cdfc65ca8cd9..7662b2eb50d8 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -159,6 +159,7 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x1199, 0x9056)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9060)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9061)},	/* Sierra Wireless Modem */
+	{DEVICE_SWI(0x1199, 0x9062)},	/* Sierra Wireless EM7305 QDL */
 	{DEVICE_SWI(0x1199, 0x9063)},	/* Sierra Wireless EM7305 */
 	{DEVICE_SWI(0x1199, 0x9070)},	/* Sierra Wireless MC74xx */
 	{DEVICE_SWI(0x1199, 0x9071)},	/* Sierra Wireless MC74xx */
@@ -177,6 +178,7 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x413c, 0x81b3)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{DEVICE_SWI(0x413c, 0x81b5)},	/* Dell Wireless 5811e QDL */
 	{DEVICE_SWI(0x413c, 0x81b6)},	/* Dell Wireless 5811e QDL */
+	{DEVICE_SWI(0x413c, 0x81cb)},	/* Dell Wireless 5816e QDL */
 	{DEVICE_SWI(0x413c, 0x81cc)},	/* Dell Wireless 5816e */
 	{DEVICE_SWI(0x413c, 0x81cf)},   /* Dell Wireless 5819 */
 	{DEVICE_SWI(0x413c, 0x81d0)},   /* Dell Wireless 5819 */
diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c
index 95e9576c2fe6..4fab7ec9cd3f 100644
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -302,6 +302,10 @@ static void usb_wwan_indat_callback(struct urb *urb)
 	if (status) {
 		dev_dbg(dev, "%s: nonzero status: %d on endpoint %02x.\n",
 			__func__, status, endpoint);
+
+		/* don't resubmit on fatal errors */
+		if (status == -ESHUTDOWN || status == -ENOENT)
+			return;
 	} else {
 		if (urb->actual_length) {
 			tty_insert_flip_string(&port->port, data,
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 20dd8df864c4..6234cee50a88 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -670,8 +670,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 	if (devinfo->resetting) {
 		cmnd->result = DID_ERROR << 16;
 		cmnd->scsi_done(cmnd);
-		spin_unlock_irqrestore(&devinfo->lock, flags);
-		return 0;
+		goto zombie;
 	}
 
 	/* Find a free uas-tag */
@@ -706,6 +705,16 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 		cmdinfo->state &= ~(SUBMIT_DATA_IN_URB | SUBMIT_DATA_OUT_URB);
 
 	err = uas_submit_urbs(cmnd, devinfo);
+	/*
+	 * in case of fatal errors the SCSI layer is peculiar
+	 * a command that has finished is a success for the purpose
+	 * of queueing, no matter how fatal the error
+	 */
+	if (err == -ENODEV) {
+		cmnd->result = DID_ERROR << 16;
+		cmnd->scsi_done(cmnd);
+		goto zombie;
+	}
 	if (err) {
 		/* If we did nothing, give up now */
 		if (cmdinfo->state & SUBMIT_STATUS_URB) {
@@ -716,6 +725,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 	}
 
 	devinfo->cmnd[idx] = cmnd;
+zombie:
 	spin_unlock_irqrestore(&devinfo->lock, flags);
 	return 0;
 }
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 5c3f2eaf59e8..e77140a5b672 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2347,7 +2347,7 @@ UNUSUAL_DEV(  0x357d, 0x7788, 0x0114, 0x0114,
 		"JMicron",
 		"USB to ATA/ATAPI Bridge",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
-		US_FL_BROKEN_FUA ),
+		US_FL_BROKEN_FUA | US_FL_IGNORE_UAS ),
 
 /* Reported by Andrey Rahmatullin <wrar@altlinux.org> */
 UNUSUAL_DEV(  0x4102, 0x1020, 0x0100,  0x0100,
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 4df15faa66d7..018b0663d610 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -41,6 +41,13 @@
  * and don't forget to CC: the USB development list <linux-usb@vger.kernel.org>
  */
 
+/* Reported-by: Till Dörges <doerges@pre-sense.de> */
+UNUSUAL_DEV(0x054c, 0x087d, 0x0000, 0x9999,
+		"Sony",
+		"PSZ-HA*",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_OPCODES),
+
 /* Reported-by: Julian Groß <julian.g@posteo.de> */
 UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999,
 		"LaCie",
@@ -156,6 +163,13 @@ UNUSUAL_DEV(0x152d, 0x0578, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_BROKEN_FUA),
 
+/* Reported-by: Thinh Nguyen <thinhn@synopsys.com> */
+UNUSUAL_DEV(0x154b, 0xf00d, 0x0000, 0x9999,
+		"PNY",
+		"Pro Elite SSD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
 /* Reported-by: Hans de Goede <hdegoede@redhat.com> */
 UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999,
 		"VIA",
diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index 494d2a49203a..d5e17dd6773a 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -67,11 +67,15 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data)
 
 static int ucsi_acpi_probe(struct platform_device *pdev)
 {
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
 	struct ucsi_acpi *ua;
 	struct resource *res;
 	acpi_status status;
 	int ret;
 
+	if (adev->dep_unmet)
+		return -EPROBE_DEFER;
+
 	ua = devm_kzalloc(&pdev->dev, sizeof(*ua), GFP_KERNEL);
 	if (!ua)
 		return -ENOMEM;
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index 802df210929b..7e474e41c85e 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -113,7 +113,7 @@ struct mdev_type *add_mdev_supported_type(struct mdev_parent *parent,
 				   "%s-%s", dev_driver_string(parent->dev),
 				   group->name);
 	if (ret) {
-		kfree(type);
+		kobject_put(&type->kobj);
 		return ERR_PTR(ret);
 	}
 
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 550ab7707b57..ac1c54bcfe8f 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -29,6 +29,7 @@
 #include <linux/vfio.h>
 #include <linux/vgaarb.h>
 #include <linux/nospec.h>
+#include <linux/sched/mm.h>
 
 #include "vfio_pci_private.h"
 
@@ -181,6 +182,7 @@ no_mmap:
 
 static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);
 static void vfio_pci_disable(struct vfio_pci_device *vdev);
+static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data);
 
 /*
  * INTx masking requires the ability to disable INTx signaling via PCI_COMMAND
@@ -397,6 +399,19 @@ static void vfio_pci_release(void *device_data)
 	if (!(--vdev->refcnt)) {
 		vfio_spapr_pci_eeh_release(vdev->pdev);
 		vfio_pci_disable(vdev);
+		mutex_lock(&vdev->igate);
+		if (vdev->err_trigger) {
+			eventfd_ctx_put(vdev->err_trigger);
+			vdev->err_trigger = NULL;
+		}
+		mutex_unlock(&vdev->igate);
+
+		mutex_lock(&vdev->igate);
+		if (vdev->req_trigger) {
+			eventfd_ctx_put(vdev->req_trigger);
+			vdev->req_trigger = NULL;
+		}
+		mutex_unlock(&vdev->igate);
 	}
 
 	mutex_unlock(&driver_lock);
@@ -644,6 +659,12 @@ int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
 	return 0;
 }
 
+struct vfio_devices {
+	struct vfio_device **devices;
+	int cur_index;
+	int max_index;
+};
+
 static long vfio_pci_ioctl(void *device_data,
 			   unsigned int cmd, unsigned long arg)
 {
@@ -717,7 +738,7 @@ static long vfio_pci_ioctl(void *device_data,
 		{
 			void __iomem *io;
 			size_t size;
-			u16 orig_cmd;
+			u16 cmd;
 
 			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
 			info.flags = 0;
@@ -737,10 +758,7 @@ static long vfio_pci_ioctl(void *device_data,
 			 * Is it really there?  Enable memory decode for
 			 * implicit access in pci_map_rom().
 			 */
-			pci_read_config_word(pdev, PCI_COMMAND, &orig_cmd);
-			pci_write_config_word(pdev, PCI_COMMAND,
-					      orig_cmd | PCI_COMMAND_MEMORY);
-
+			cmd = vfio_pci_memory_lock_and_enable(vdev);
 			io = pci_map_rom(pdev, &size);
 			if (io) {
 				info.flags = VFIO_REGION_INFO_FLAG_READ;
@@ -748,8 +766,8 @@ static long vfio_pci_ioctl(void *device_data,
 			} else {
 				info.size = 0;
 			}
+			vfio_pci_memory_unlock_and_restore(vdev, cmd);
 
-			pci_write_config_word(pdev, PCI_COMMAND, orig_cmd);
 			break;
 		}
 		case VFIO_PCI_VGA_REGION_INDEX:
@@ -885,8 +903,16 @@ static long vfio_pci_ioctl(void *device_data,
 		return ret;
 
 	} else if (cmd == VFIO_DEVICE_RESET) {
-		return vdev->reset_works ?
-			pci_try_reset_function(vdev->pdev) : -EINVAL;
+		int ret;
+
+		if (!vdev->reset_works)
+			return -EINVAL;
+
+		vfio_pci_zap_and_down_write_memory_lock(vdev);
+		ret = pci_try_reset_function(vdev->pdev);
+		up_write(&vdev->memory_lock);
+
+		return ret;
 
 	} else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) {
 		struct vfio_pci_hot_reset_info hdr;
@@ -966,8 +992,9 @@ reset_info_exit:
 		int32_t *group_fds;
 		struct vfio_pci_group_entry *groups;
 		struct vfio_pci_group_info info;
+		struct vfio_devices devs = { .cur_index = 0 };
 		bool slot = false;
-		int i, count = 0, ret = 0;
+		int i, group_idx, mem_idx = 0, count = 0, ret = 0;
 
 		minsz = offsetofend(struct vfio_pci_hot_reset, count);
 
@@ -1019,9 +1046,9 @@ reset_info_exit:
 		 * user interface and store the group and iommu ID.  This
 		 * ensures the group is held across the reset.
 		 */
-		for (i = 0; i < hdr.count; i++) {
+		for (group_idx = 0; group_idx < hdr.count; group_idx++) {
 			struct vfio_group *group;
-			struct fd f = fdget(group_fds[i]);
+			struct fd f = fdget(group_fds[group_idx]);
 			if (!f.file) {
 				ret = -EBADF;
 				break;
@@ -1034,8 +1061,9 @@ reset_info_exit:
 				break;
 			}
 
-			groups[i].group = group;
-			groups[i].id = vfio_external_user_iommu_id(group);
+			groups[group_idx].group = group;
+			groups[group_idx].id =
+					vfio_external_user_iommu_id(group);
 		}
 
 		kfree(group_fds);
@@ -1054,14 +1082,65 @@ reset_info_exit:
 		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
 						    vfio_pci_validate_devs,
 						    &info, slot);
-		if (!ret)
-			/* User has access, do the reset */
-			ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
-				     pci_try_reset_bus(vdev->pdev->bus);
+
+		if (ret)
+			goto hot_reset_release;
+
+		devs.max_index = count;
+		devs.devices = kcalloc(count, sizeof(struct vfio_device *),
+				       GFP_KERNEL);
+		if (!devs.devices) {
+			ret = -ENOMEM;
+			goto hot_reset_release;
+		}
+
+		/*
+		 * We need to get memory_lock for each device, but devices
+		 * can share mmap_sem, therefore we need to zap and hold
+		 * the vma_lock for each device, and only then get each
+		 * memory_lock.
+		 */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+					    vfio_pci_try_zap_and_vma_lock_cb,
+					    &devs, slot);
+		if (ret)
+			goto hot_reset_release;
+
+		for (; mem_idx < devs.cur_index; mem_idx++) {
+			struct vfio_pci_device *tmp;
+
+			tmp = vfio_device_data(devs.devices[mem_idx]);
+
+			ret = down_write_trylock(&tmp->memory_lock);
+			if (!ret) {
+				ret = -EBUSY;
+				goto hot_reset_release;
+			}
+			mutex_unlock(&tmp->vma_lock);
+		}
+
+		/* User has access, do the reset */
+		ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
+				pci_try_reset_bus(vdev->pdev->bus);
 
 hot_reset_release:
-		for (i--; i >= 0; i--)
-			vfio_group_put_external_user(groups[i].group);
+		for (i = 0; i < devs.cur_index; i++) {
+			struct vfio_device *device;
+			struct vfio_pci_device *tmp;
+
+			device = devs.devices[i];
+			tmp = vfio_device_data(device);
+
+			if (i < mem_idx)
+				up_write(&tmp->memory_lock);
+			else
+				mutex_unlock(&tmp->vma_lock);
+			vfio_device_put(device);
+		}
+		kfree(devs.devices);
+
+		for (group_idx--; group_idx >= 0; group_idx--)
+			vfio_group_put_external_user(groups[group_idx].group);
 
 		kfree(groups);
 		return ret;
@@ -1120,6 +1199,202 @@ static ssize_t vfio_pci_write(void *device_data, const char __user *buf,
 	return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true);
 }
 
+/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */
+static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try)
+{
+	struct vfio_pci_mmap_vma *mmap_vma, *tmp;
+
+	/*
+	 * Lock ordering:
+	 * vma_lock is nested under mmap_sem for vm_ops callback paths.
+	 * The memory_lock semaphore is used by both code paths calling
+	 * into this function to zap vmas and the vm_ops.fault callback
+	 * to protect the memory enable state of the device.
+	 *
+	 * When zapping vmas we need to maintain the mmap_sem => vma_lock
+	 * ordering, which requires using vma_lock to walk vma_list to
+	 * acquire an mm, then dropping vma_lock to get the mmap_sem and
+	 * reacquiring vma_lock.  This logic is derived from similar
+	 * requirements in uverbs_user_mmap_disassociate().
+	 *
+	 * mmap_sem must always be the top-level lock when it is taken.
+	 * Therefore we can only hold the memory_lock write lock when
+	 * vma_list is empty, as we'd need to take mmap_sem to clear
+	 * entries.  vma_list can only be guaranteed empty when holding
+	 * vma_lock, thus memory_lock is nested under vma_lock.
+	 *
+	 * This enables the vm_ops.fault callback to acquire vma_lock,
+	 * followed by memory_lock read lock, while already holding
+	 * mmap_sem without risk of deadlock.
+	 */
+	while (1) {
+		struct mm_struct *mm = NULL;
+
+		if (try) {
+			if (!mutex_trylock(&vdev->vma_lock))
+				return 0;
+		} else {
+			mutex_lock(&vdev->vma_lock);
+		}
+		while (!list_empty(&vdev->vma_list)) {
+			mmap_vma = list_first_entry(&vdev->vma_list,
+						    struct vfio_pci_mmap_vma,
+						    vma_next);
+			mm = mmap_vma->vma->vm_mm;
+			if (mmget_not_zero(mm))
+				break;
+
+			list_del(&mmap_vma->vma_next);
+			kfree(mmap_vma);
+			mm = NULL;
+		}
+		if (!mm)
+			return 1;
+		mutex_unlock(&vdev->vma_lock);
+
+		if (try) {
+			if (!down_read_trylock(&mm->mmap_sem)) {
+				mmput(mm);
+				return 0;
+			}
+		} else {
+			down_read(&mm->mmap_sem);
+		}
+		if (mmget_still_valid(mm)) {
+			if (try) {
+				if (!mutex_trylock(&vdev->vma_lock)) {
+					up_read(&mm->mmap_sem);
+					mmput(mm);
+					return 0;
+				}
+			} else {
+				mutex_lock(&vdev->vma_lock);
+			}
+			list_for_each_entry_safe(mmap_vma, tmp,
+						 &vdev->vma_list, vma_next) {
+				struct vm_area_struct *vma = mmap_vma->vma;
+
+				if (vma->vm_mm != mm)
+					continue;
+
+				list_del(&mmap_vma->vma_next);
+				kfree(mmap_vma);
+
+				zap_vma_ptes(vma, vma->vm_start,
+					     vma->vm_end - vma->vm_start);
+			}
+			mutex_unlock(&vdev->vma_lock);
+		}
+		up_read(&mm->mmap_sem);
+		mmput(mm);
+	}
+}
+
+void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device *vdev)
+{
+	vfio_pci_zap_and_vma_lock(vdev, false);
+	down_write(&vdev->memory_lock);
+	mutex_unlock(&vdev->vma_lock);
+}
+
+u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev)
+{
+	u16 cmd;
+
+	down_write(&vdev->memory_lock);
+	pci_read_config_word(vdev->pdev, PCI_COMMAND, &cmd);
+	if (!(cmd & PCI_COMMAND_MEMORY))
+		pci_write_config_word(vdev->pdev, PCI_COMMAND,
+				      cmd | PCI_COMMAND_MEMORY);
+
+	return cmd;
+}
+
+void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev, u16 cmd)
+{
+	pci_write_config_word(vdev->pdev, PCI_COMMAND, cmd);
+	up_write(&vdev->memory_lock);
+}
+
+/* Caller holds vma_lock */
+static int __vfio_pci_add_vma(struct vfio_pci_device *vdev,
+			      struct vm_area_struct *vma)
+{
+	struct vfio_pci_mmap_vma *mmap_vma;
+
+	mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL);
+	if (!mmap_vma)
+		return -ENOMEM;
+
+	mmap_vma->vma = vma;
+	list_add(&mmap_vma->vma_next, &vdev->vma_list);
+
+	return 0;
+}
+
+/*
+ * Zap mmaps on open so that we can fault them in on access and therefore
+ * our vma_list only tracks mappings accessed since last zap.
+ */
+static void vfio_pci_mmap_open(struct vm_area_struct *vma)
+{
+	zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
+}
+
+static void vfio_pci_mmap_close(struct vm_area_struct *vma)
+{
+	struct vfio_pci_device *vdev = vma->vm_private_data;
+	struct vfio_pci_mmap_vma *mmap_vma;
+
+	mutex_lock(&vdev->vma_lock);
+	list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) {
+		if (mmap_vma->vma == vma) {
+			list_del(&mmap_vma->vma_next);
+			kfree(mmap_vma);
+			break;
+		}
+	}
+	mutex_unlock(&vdev->vma_lock);
+}
+
+static int vfio_pci_mmap_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct vfio_pci_device *vdev = vma->vm_private_data;
+	int ret = VM_FAULT_NOPAGE;
+
+	mutex_lock(&vdev->vma_lock);
+	down_read(&vdev->memory_lock);
+
+	if (!__vfio_pci_memory_enabled(vdev)) {
+		ret = VM_FAULT_SIGBUS;
+		mutex_unlock(&vdev->vma_lock);
+		goto up_out;
+	}
+
+	if (__vfio_pci_add_vma(vdev, vma)) {
+		ret = VM_FAULT_OOM;
+		mutex_unlock(&vdev->vma_lock);
+		goto up_out;
+	}
+
+	mutex_unlock(&vdev->vma_lock);
+
+	if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			    vma->vm_end - vma->vm_start, vma->vm_page_prot))
+		ret = VM_FAULT_SIGBUS;
+
+up_out:
+	up_read(&vdev->memory_lock);
+	return ret;
+}
+
+static const struct vm_operations_struct vfio_pci_mmap_ops = {
+	.open = vfio_pci_mmap_open,
+	.close = vfio_pci_mmap_close,
+	.fault = vfio_pci_mmap_fault,
+};
+
 static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 {
 	struct vfio_pci_device *vdev = device_data;
@@ -1185,8 +1460,14 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff;
 
-	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
-			       req_len, vma->vm_page_prot);
+	/*
+	 * See remap_pfn_range(), called from vfio_pci_fault() but we can't
+	 * change vm_flags within the fault handler.  Set them now.
+	 */
+	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_ops = &vfio_pci_mmap_ops;
+
+	return 0;
 }
 
 static void vfio_pci_request(void *device_data, unsigned int count)
@@ -1243,6 +1524,9 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	vdev->irq_type = VFIO_PCI_NUM_IRQS;
 	mutex_init(&vdev->igate);
 	spin_lock_init(&vdev->irqlock);
+	mutex_init(&vdev->vma_lock);
+	INIT_LIST_HEAD(&vdev->vma_list);
+	init_rwsem(&vdev->memory_lock);
 
 	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
 	if (ret) {
@@ -1337,12 +1621,6 @@ static struct pci_driver vfio_pci_driver = {
 	.err_handler	= &vfio_err_handlers,
 };
 
-struct vfio_devices {
-	struct vfio_device **devices;
-	int cur_index;
-	int max_index;
-};
-
 static int vfio_pci_get_devs(struct pci_dev *pdev, void *data)
 {
 	struct vfio_devices *devs = data;
@@ -1364,6 +1642,39 @@ static int vfio_pci_get_devs(struct pci_dev *pdev, void *data)
 	return 0;
 }
 
+static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data)
+{
+	struct vfio_devices *devs = data;
+	struct vfio_device *device;
+	struct vfio_pci_device *vdev;
+
+	if (devs->cur_index == devs->max_index)
+		return -ENOSPC;
+
+	device = vfio_device_get_from_dev(&pdev->dev);
+	if (!device)
+		return -EINVAL;
+
+	if (pci_dev_driver(pdev) != &vfio_pci_driver) {
+		vfio_device_put(device);
+		return -EBUSY;
+	}
+
+	vdev = vfio_device_data(device);
+
+	/*
+	 * Locking multiple devices is prone to deadlock, runaway and
+	 * unwind if we hit contention.
+	 */
+	if (!vfio_pci_zap_and_vma_lock(vdev, true)) {
+		vfio_device_put(device);
+		return -EBUSY;
+	}
+
+	devs->devices[devs->cur_index++] = device;
+	return 0;
+}
+
 /*
  * Attempt to do a bus/slot reset if there are devices affected by a reset for
  * this device that are needs_reset and all of the affected devices are unused
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 423ea1f98441..a1a26465d224 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -398,6 +398,20 @@ static inline void p_setd(struct perm_bits *p, int off, u32 virt, u32 write)
 	*(__le32 *)(&p->write[off]) = cpu_to_le32(write);
 }
 
+/* Caller should hold memory_lock semaphore */
+bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]);
+
+	/*
+	 * SR-IOV VF memory enable is handled by the MSE bit in the
+	 * PF SR-IOV capability, there's therefore no need to trigger
+	 * faults based on the virtual value.
+	 */
+	return pdev->is_virtfn || (cmd & PCI_COMMAND_MEMORY);
+}
+
 /*
  * Restore the *real* BARs after we detect a FLR or backdoor reset.
  * (backdoor = some device specific technique that we didn't catch)
@@ -558,13 +572,18 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 
 		new_cmd = le32_to_cpu(val);
 
+		phys_io = !!(phys_cmd & PCI_COMMAND_IO);
+		virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO);
+		new_io = !!(new_cmd & PCI_COMMAND_IO);
+
 		phys_mem = !!(phys_cmd & PCI_COMMAND_MEMORY);
 		virt_mem = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_MEMORY);
 		new_mem = !!(new_cmd & PCI_COMMAND_MEMORY);
 
-		phys_io = !!(phys_cmd & PCI_COMMAND_IO);
-		virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO);
-		new_io = !!(new_cmd & PCI_COMMAND_IO);
+		if (!new_mem)
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
+		else
+			down_write(&vdev->memory_lock);
 
 		/*
 		 * If the user is writing mem/io enable (new_mem/io) and we
@@ -581,8 +600,11 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 	}
 
 	count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
-	if (count < 0)
+	if (count < 0) {
+		if (offset == PCI_COMMAND)
+			up_write(&vdev->memory_lock);
 		return count;
+	}
 
 	/*
 	 * Save current memory/io enable bits in vconfig to allow for
@@ -593,6 +615,8 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 
 		*virt_cmd &= cpu_to_le16(~mask);
 		*virt_cmd |= cpu_to_le16(new_cmd & mask);
+
+		up_write(&vdev->memory_lock);
 	}
 
 	/* Emulate INTx disable */
@@ -830,8 +854,11 @@ static int vfio_exp_config_write(struct vfio_pci_device *vdev, int pos,
 						 pos - offset + PCI_EXP_DEVCAP,
 						 &cap);
 
-		if (!ret && (cap & PCI_EXP_DEVCAP_FLR))
+		if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) {
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
 			pci_try_reset_function(vdev->pdev);
+			up_write(&vdev->memory_lock);
+		}
 	}
 
 	/*
@@ -909,8 +936,11 @@ static int vfio_af_config_write(struct vfio_pci_device *vdev, int pos,
 						pos - offset + PCI_AF_CAP,
 						&cap);
 
-		if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP))
+		if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) {
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
 			pci_try_reset_function(vdev->pdev);
+			up_write(&vdev->memory_lock);
+		}
 	}
 
 	return count;
@@ -1464,7 +1494,12 @@ static int vfio_cap_init(struct vfio_pci_device *vdev)
 		if (ret)
 			return ret;
 
-		if (cap <= PCI_CAP_ID_MAX) {
+		/*
+		 * ID 0 is a NULL capability, conflicting with our fake
+		 * PCI_CAP_ID_BASIC.  As it has no content, consider it
+		 * hidden for now.
+		 */
+		if (cap && cap <= PCI_CAP_ID_MAX) {
 			len = pci_cap_length[cap];
 			if (len == 0xFF) { /* Variable length */
 				len = vfio_cap_len(vdev, cap, pos);
@@ -1703,6 +1738,15 @@ int vfio_config_init(struct vfio_pci_device *vdev)
 				 vconfig[PCI_INTERRUPT_PIN]);
 
 		vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */
+
+		/*
+		 * VFs do no implement the memory enable bit of the COMMAND
+		 * register therefore we'll not have it set in our initial
+		 * copy of config space after pci_enable_device().  For
+		 * consistency with PFs, set the virtual enable bit here.
+		 */
+		*(__le16 *)&vconfig[PCI_COMMAND] |=
+					cpu_to_le16(PCI_COMMAND_MEMORY);
 	}
 
 	if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx)
@@ -1732,8 +1776,11 @@ void vfio_config_free(struct vfio_pci_device *vdev)
 	vdev->vconfig = NULL;
 	kfree(vdev->pci_config_map);
 	vdev->pci_config_map = NULL;
-	kfree(vdev->msi_perm);
-	vdev->msi_perm = NULL;
+	if (vdev->msi_perm) {
+		free_perm_bits(vdev->msi_perm);
+		kfree(vdev->msi_perm);
+		vdev->msi_perm = NULL;
+	}
 }
 
 /*
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 94594dc63c41..bdfdd506bc58 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -252,6 +252,7 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
 	struct pci_dev *pdev = vdev->pdev;
 	unsigned int flag = msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
 	int ret;
+	u16 cmd;
 
 	if (!is_irq_none(vdev))
 		return -EINVAL;
@@ -261,13 +262,16 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
 		return -ENOMEM;
 
 	/* return the number of supported vectors if we can't get all: */
+	cmd = vfio_pci_memory_lock_and_enable(vdev);
 	ret = pci_alloc_irq_vectors(pdev, 1, nvec, flag);
 	if (ret < nvec) {
 		if (ret > 0)
 			pci_free_irq_vectors(pdev);
+		vfio_pci_memory_unlock_and_restore(vdev, cmd);
 		kfree(vdev->ctx);
 		return ret;
 	}
+	vfio_pci_memory_unlock_and_restore(vdev, cmd);
 
 	vdev->num_ctx = nvec;
 	vdev->irq_type = msix ? VFIO_PCI_MSIX_IRQ_INDEX :
@@ -290,6 +294,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 	struct pci_dev *pdev = vdev->pdev;
 	struct eventfd_ctx *trigger;
 	int irq, ret;
+	u16 cmd;
 
 	if (vector < 0 || vector >= vdev->num_ctx)
 		return -EINVAL;
@@ -298,7 +303,11 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 
 	if (vdev->ctx[vector].trigger) {
 		irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
+
+		cmd = vfio_pci_memory_lock_and_enable(vdev);
 		free_irq(irq, vdev->ctx[vector].trigger);
+		vfio_pci_memory_unlock_and_restore(vdev, cmd);
+
 		kfree(vdev->ctx[vector].name);
 		eventfd_ctx_put(vdev->ctx[vector].trigger);
 		vdev->ctx[vector].trigger = NULL;
@@ -326,6 +335,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 	 * such a reset it would be unsuccessful. To avoid this, restore the
 	 * cached value of the message prior to enabling.
 	 */
+	cmd = vfio_pci_memory_lock_and_enable(vdev);
 	if (msix) {
 		struct msi_msg msg;
 
@@ -335,6 +345,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 
 	ret = request_irq(irq, vfio_msihandler, 0,
 			  vdev->ctx[vector].name, trigger);
+	vfio_pci_memory_unlock_and_restore(vdev, cmd);
 	if (ret) {
 		kfree(vdev->ctx[vector].name);
 		eventfd_ctx_put(trigger);
@@ -379,6 +390,7 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
 {
 	struct pci_dev *pdev = vdev->pdev;
 	int i;
+	u16 cmd;
 
 	for (i = 0; i < vdev->num_ctx; i++) {
 		vfio_virqfd_disable(&vdev->ctx[i].unmask);
@@ -387,7 +399,9 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
 
 	vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
 
+	cmd = vfio_pci_memory_lock_and_enable(vdev);
 	pci_free_irq_vectors(pdev);
+	vfio_pci_memory_unlock_and_restore(vdev, cmd);
 
 	/*
 	 * Both disable paths above use pci_intx_for_msi() to clear DisINTx
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index f561ac1c78a0..f896cebb5c2c 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -63,6 +63,11 @@ struct vfio_pci_dummy_resource {
 	struct list_head	res_next;
 };
 
+struct vfio_pci_mmap_vma {
+	struct vm_area_struct	*vma;
+	struct list_head	vma_next;
+};
+
 struct vfio_pci_device {
 	struct pci_dev		*pdev;
 	void __iomem		*barmap[PCI_STD_RESOURCE_END + 1];
@@ -95,6 +100,9 @@ struct vfio_pci_device {
 	struct eventfd_ctx	*err_trigger;
 	struct eventfd_ctx	*req_trigger;
 	struct list_head	dummy_resources_list;
+	struct mutex		vma_lock;
+	struct list_head	vma_list;
+	struct rw_semaphore	memory_lock;
 };
 
 #define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)
@@ -130,6 +138,14 @@ extern int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
 					unsigned int type, unsigned int subtype,
 					const struct vfio_pci_regops *ops,
 					size_t size, u32 flags, void *data);
+
+extern bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev);
+extern void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device
+						    *vdev);
+extern u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev);
+extern void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev,
+					       u16 cmd);
+
 #ifdef CONFIG_VFIO_PCI_IGD
 extern int vfio_pci_igd_init(struct vfio_pci_device *vdev);
 #else
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 357243d76f10..6445461a5601 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -122,6 +122,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 	size_t x_start = 0, x_end = 0;
 	resource_size_t end;
 	void __iomem *io;
+	struct resource *res = &vdev->pdev->resource[bar];
 	ssize_t done;
 
 	if (pci_resource_start(pdev, bar))
@@ -137,6 +138,14 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 
 	count = min(count, (size_t)(end - pos));
 
+	if (res->flags & IORESOURCE_MEM) {
+		down_read(&vdev->memory_lock);
+		if (!__vfio_pci_memory_enabled(vdev)) {
+			up_read(&vdev->memory_lock);
+			return -EIO;
+		}
+	}
+
 	if (bar == PCI_ROM_RESOURCE) {
 		/*
 		 * The ROM can fill less space than the BAR, so we start the
@@ -144,20 +153,21 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 		 * filling large ROM BARs much faster.
 		 */
 		io = pci_map_rom(pdev, &x_start);
-		if (!io)
-			return -ENOMEM;
+		if (!io) {
+			done = -ENOMEM;
+			goto out;
+		}
 		x_end = end;
 	} else if (!vdev->barmap[bar]) {
-		int ret;
-
-		ret = pci_request_selected_regions(pdev, 1 << bar, "vfio");
-		if (ret)
-			return ret;
+		done = pci_request_selected_regions(pdev, 1 << bar, "vfio");
+		if (done)
+			goto out;
 
 		io = pci_iomap(pdev, bar, 0);
 		if (!io) {
 			pci_release_selected_regions(pdev, 1 << bar);
-			return -ENOMEM;
+			done = -ENOMEM;
+			goto out;
 		}
 
 		vdev->barmap[bar] = io;
@@ -176,6 +186,9 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 
 	if (bar == PCI_ROM_RESOURCE)
 		pci_unmap_rom(pdev, io);
+out:
+	if (res->flags & IORESOURCE_MEM)
+		up_read(&vdev->memory_lock);
 
 	return done;
 }
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 35a3750a6ddd..9c8ed9d7f9aa 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -336,6 +336,32 @@ static int put_pfn(unsigned long pfn, int prot)
 	return 0;
 }
 
+static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm,
+			    unsigned long vaddr, unsigned long *pfn,
+			    bool write_fault)
+{
+	int ret;
+
+	ret = follow_pfn(vma, vaddr, pfn);
+	if (ret) {
+		bool unlocked = false;
+
+		ret = fixup_user_fault(NULL, mm, vaddr,
+				       FAULT_FLAG_REMOTE |
+				       (write_fault ?  FAULT_FLAG_WRITE : 0),
+				       &unlocked);
+		if (unlocked)
+			return -EAGAIN;
+
+		if (ret)
+			return ret;
+
+		ret = follow_pfn(vma, vaddr, pfn);
+	}
+
+	return ret;
+}
+
 static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 			 int prot, unsigned long *pfn)
 {
@@ -375,12 +401,16 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 
 	down_read(&mm->mmap_sem);
 
+retry:
 	vma = find_vma_intersection(mm, vaddr, vaddr + 1);
 
 	if (vma && vma->vm_flags & VM_PFNMAP) {
-		if (!follow_pfn(vma, vaddr, pfn) &&
-		    is_invalid_reserved_pfn(*pfn))
-			ret = 0;
+		ret = follow_fault_pfn(vma, mm, vaddr, pfn, prot & IOMMU_WRITE);
+		if (ret == -EAGAIN)
+			goto retry;
+
+		if (!ret && !is_invalid_reserved_pfn(*pfn))
+			ret = -EFAULT;
 	}
 
 	up_read(&mm->mmap_sem);
@@ -1086,13 +1116,16 @@ static int vfio_bus_type(struct device *dev, void *data)
 static int vfio_iommu_replay(struct vfio_iommu *iommu,
 			     struct vfio_domain *domain)
 {
-	struct vfio_domain *d;
+	struct vfio_domain *d = NULL;
 	struct rb_node *n;
 	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 	int ret;
 
 	/* Arbitrarily pick the first domain in the list for lookups */
-	d = list_first_entry(&iommu->domain_list, struct vfio_domain, next);
+	if (!list_empty(&iommu->domain_list))
+		d = list_first_entry(&iommu->domain_list,
+				     struct vfio_domain, next);
+
 	n = rb_first(&iommu->dma_list);
 
 	for (; n; n = rb_next(n)) {
@@ -1110,6 +1143,11 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 				phys_addr_t p;
 				dma_addr_t i;
 
+				if (WARN_ON(!d)) { /* mapped w/o a domain?! */
+					ret = -EINVAL;
+					goto unwind;
+				}
+
 				phys = iommu_iova_to_phys(d->domain, iova);
 
 				if (WARN_ON(!phys)) {
@@ -1139,7 +1177,7 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 				if (npage <= 0) {
 					WARN_ON(!npage);
 					ret = (int)npage;
-					return ret;
+					goto unwind;
 				}
 
 				phys = pfn << PAGE_SHIFT;
@@ -1148,14 +1186,67 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 
 			ret = iommu_map(domain->domain, iova, phys,
 					size, dma->prot | domain->prot);
-			if (ret)
-				return ret;
+			if (ret) {
+				if (!dma->iommu_mapped)
+					vfio_unpin_pages_remote(dma, iova,
+							phys >> PAGE_SHIFT,
+							size >> PAGE_SHIFT,
+							true);
+				goto unwind;
+			}
 
 			iova += size;
 		}
+	}
+
+	/* All dmas are now mapped, defer to second tree walk for unwind */
+	for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) {
+		struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
+
 		dma->iommu_mapped = true;
 	}
+
 	return 0;
+
+unwind:
+	for (; n; n = rb_prev(n)) {
+		struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node);
+		dma_addr_t iova;
+
+		if (dma->iommu_mapped) {
+			iommu_unmap(domain->domain, dma->iova, dma->size);
+			continue;
+		}
+
+		iova = dma->iova;
+		while (iova < dma->iova + dma->size) {
+			phys_addr_t phys, p;
+			size_t size;
+			dma_addr_t i;
+
+			phys = iommu_iova_to_phys(domain->domain, iova);
+			if (!phys) {
+				iova += PAGE_SIZE;
+				continue;
+			}
+
+			size = PAGE_SIZE;
+			p = phys + size;
+			i = iova + size;
+			while (i < dma->iova + dma->size &&
+			       p == iommu_iova_to_phys(domain->domain, i)) {
+				size += PAGE_SIZE;
+				p += PAGE_SIZE;
+				i += PAGE_SIZE;
+			}
+
+			iommu_unmap(domain->domain, iova, size);
+			vfio_unpin_pages_remote(dma, iova, phys >> PAGE_SHIFT,
+						size >> PAGE_SHIFT, true);
+		}
+	}
+
+	return ret;
 }
 
 /*
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 3f2f34ebf51f..27f3b471c95b 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -383,6 +383,52 @@ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock)
 	return val < vq->num;
 }
 
+static struct virtio_transport vhost_transport = {
+	.transport = {
+		.get_local_cid            = vhost_transport_get_local_cid,
+
+		.init                     = virtio_transport_do_socket_init,
+		.destruct                 = virtio_transport_destruct,
+		.release                  = virtio_transport_release,
+		.connect                  = virtio_transport_connect,
+		.shutdown                 = virtio_transport_shutdown,
+		.cancel_pkt               = vhost_transport_cancel_pkt,
+
+		.dgram_enqueue            = virtio_transport_dgram_enqueue,
+		.dgram_dequeue            = virtio_transport_dgram_dequeue,
+		.dgram_bind               = virtio_transport_dgram_bind,
+		.dgram_allow              = virtio_transport_dgram_allow,
+
+		.stream_enqueue           = virtio_transport_stream_enqueue,
+		.stream_dequeue           = virtio_transport_stream_dequeue,
+		.stream_has_data          = virtio_transport_stream_has_data,
+		.stream_has_space         = virtio_transport_stream_has_space,
+		.stream_rcvhiwat          = virtio_transport_stream_rcvhiwat,
+		.stream_is_active         = virtio_transport_stream_is_active,
+		.stream_allow             = virtio_transport_stream_allow,
+
+		.notify_poll_in           = virtio_transport_notify_poll_in,
+		.notify_poll_out          = virtio_transport_notify_poll_out,
+		.notify_recv_init         = virtio_transport_notify_recv_init,
+		.notify_recv_pre_block    = virtio_transport_notify_recv_pre_block,
+		.notify_recv_pre_dequeue  = virtio_transport_notify_recv_pre_dequeue,
+		.notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue,
+		.notify_send_init         = virtio_transport_notify_send_init,
+		.notify_send_pre_block    = virtio_transport_notify_send_pre_block,
+		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
+		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
+
+		.set_buffer_size          = virtio_transport_set_buffer_size,
+		.set_min_buffer_size      = virtio_transport_set_min_buffer_size,
+		.set_max_buffer_size      = virtio_transport_set_max_buffer_size,
+		.get_buffer_size          = virtio_transport_get_buffer_size,
+		.get_min_buffer_size      = virtio_transport_get_min_buffer_size,
+		.get_max_buffer_size      = virtio_transport_get_max_buffer_size,
+	},
+
+	.send_pkt = vhost_transport_send_pkt,
+};
+
 static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 {
 	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
@@ -439,7 +485,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid &&
 		    le64_to_cpu(pkt->hdr.dst_cid) ==
 		    vhost_transport_get_local_cid())
-			virtio_transport_recv_pkt(pkt);
+			virtio_transport_recv_pkt(&vhost_transport, pkt);
 		else
 			virtio_transport_free_pkt(pkt);
 
@@ -780,52 +826,6 @@ static struct miscdevice vhost_vsock_misc = {
 	.fops = &vhost_vsock_fops,
 };
 
-static struct virtio_transport vhost_transport = {
-	.transport = {
-		.get_local_cid            = vhost_transport_get_local_cid,
-
-		.init                     = virtio_transport_do_socket_init,
-		.destruct                 = virtio_transport_destruct,
-		.release                  = virtio_transport_release,
-		.connect                  = virtio_transport_connect,
-		.shutdown                 = virtio_transport_shutdown,
-		.cancel_pkt               = vhost_transport_cancel_pkt,
-
-		.dgram_enqueue            = virtio_transport_dgram_enqueue,
-		.dgram_dequeue            = virtio_transport_dgram_dequeue,
-		.dgram_bind               = virtio_transport_dgram_bind,
-		.dgram_allow              = virtio_transport_dgram_allow,
-
-		.stream_enqueue           = virtio_transport_stream_enqueue,
-		.stream_dequeue           = virtio_transport_stream_dequeue,
-		.stream_has_data          = virtio_transport_stream_has_data,
-		.stream_has_space         = virtio_transport_stream_has_space,
-		.stream_rcvhiwat          = virtio_transport_stream_rcvhiwat,
-		.stream_is_active         = virtio_transport_stream_is_active,
-		.stream_allow             = virtio_transport_stream_allow,
-
-		.notify_poll_in           = virtio_transport_notify_poll_in,
-		.notify_poll_out          = virtio_transport_notify_poll_out,
-		.notify_recv_init         = virtio_transport_notify_recv_init,
-		.notify_recv_pre_block    = virtio_transport_notify_recv_pre_block,
-		.notify_recv_pre_dequeue  = virtio_transport_notify_recv_pre_dequeue,
-		.notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue,
-		.notify_send_init         = virtio_transport_notify_send_init,
-		.notify_send_pre_block    = virtio_transport_notify_send_pre_block,
-		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
-		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
-
-		.set_buffer_size          = virtio_transport_set_buffer_size,
-		.set_min_buffer_size      = virtio_transport_set_min_buffer_size,
-		.set_max_buffer_size      = virtio_transport_set_max_buffer_size,
-		.get_buffer_size          = virtio_transport_get_buffer_size,
-		.get_min_buffer_size      = virtio_transport_get_min_buffer_size,
-		.get_max_buffer_size      = virtio_transport_get_max_buffer_size,
-	},
-
-	.send_pkt = vhost_transport_send_pkt,
-};
-
 static int __init vhost_vsock_init(void)
 {
 	int ret;
diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index 939f057836e1..4cdc7a3f6dc5 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -460,7 +460,7 @@ static int lp855x_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 		ret = regulator_enable(lp->enable);
 		if (ret < 0) {
 			dev_err(lp->dev, "failed to enable vddio: %d\n", ret);
-			return ret;
+			goto disable_supply;
 		}
 
 		/*
@@ -475,24 +475,34 @@ static int lp855x_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 	ret = lp855x_configure(lp);
 	if (ret) {
 		dev_err(lp->dev, "device config err: %d", ret);
-		return ret;
+		goto disable_vddio;
 	}
 
 	ret = lp855x_backlight_register(lp);
 	if (ret) {
 		dev_err(lp->dev,
 			"failed to register backlight. err: %d\n", ret);
-		return ret;
+		goto disable_vddio;
 	}
 
 	ret = sysfs_create_group(&lp->dev->kobj, &lp855x_attr_group);
 	if (ret) {
 		dev_err(lp->dev, "failed to register sysfs. err: %d\n", ret);
-		return ret;
+		goto disable_vddio;
 	}
 
 	backlight_update_status(lp->bl);
+
 	return 0;
+
+disable_vddio:
+	if (lp->enable)
+		regulator_disable(lp->enable);
+disable_supply:
+	if (lp->supply)
+		regulator_disable(lp->supply);
+
+	return ret;
 }
 
 static int lp855x_remove(struct i2c_client *cl)
@@ -501,6 +511,8 @@ static int lp855x_remove(struct i2c_client *cl)
 
 	lp->bl->props.brightness = 0;
 	backlight_update_status(lp->bl);
+	if (lp->enable)
+		regulator_disable(lp->enable);
 	if (lp->supply)
 		regulator_disable(lp->supply);
 	sysfs_remove_group(&lp->dev->kobj, &lp855x_attr_group);
diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
index 7f1f1fbcef9e..7434320168e0 100644
--- a/drivers/video/console/Kconfig
+++ b/drivers/video/console/Kconfig
@@ -22,52 +22,6 @@ config VGA_CONSOLE
 
 	  Say Y.
 
-config VGACON_SOFT_SCROLLBACK
-       bool "Enable Scrollback Buffer in System RAM"
-       depends on VGA_CONSOLE
-       default n
-       help
-         The scrollback buffer of the standard VGA console is located in
-	 the VGA RAM.  The size of this RAM is fixed and is quite small.
-	 If you require a larger scrollback buffer, this can be placed in
-	 System RAM which is dynamically allocated during initialization.
-	 Placing the scrollback buffer in System RAM will slightly slow
-	 down the console.
-
-	 If you want this feature, say 'Y' here and enter the amount of
-	 RAM to allocate for this buffer.  If unsure, say 'N'.
-
-config VGACON_SOFT_SCROLLBACK_SIZE
-       int "Scrollback Buffer Size (in KB)"
-       depends on VGACON_SOFT_SCROLLBACK
-       range 1 1024
-       default "64"
-       help
-	  Enter the amount of System RAM to allocate for scrollback
-	  buffers of VGA consoles. Each 64KB will give you approximately
-	  16 80x25 screenfuls of scrollback buffer.
-
-config VGACON_SOFT_SCROLLBACK_PERSISTENT_ENABLE_BY_DEFAULT
-	bool "Persistent Scrollback History for each console by default"
-	depends on VGACON_SOFT_SCROLLBACK
-	default n
-	help
-	  Say Y here if the scrollback history should persist by default when
-	  switching between consoles. Otherwise, the scrollback history will be
-	  flushed each time the console is switched. This feature can also be
-	  enabled using the boot command line parameter
-	  'vgacon.scrollback_persistent=1'.
-
-	  This feature might break your tool of choice to flush the scrollback
-	  buffer, e.g. clear(1) will work fine but Debian's clear_console(1)
-	  will be broken, which might cause security issues.
-	  You can use the escape sequence \e[3J instead if this feature is
-	  activated.
-
-	  Note that a buffer of VGACON_SOFT_SCROLLBACK_SIZE is taken for each
-	  created tty device.
-	  So if you use a RAM-constrained system, say N here.
-
 config MDA_CONSOLE
 	depends on !M68K && !PARISC && ISA
 	tristate "MDA text console (dual-headed)"
diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c
index 42d02a206059..07d69d26fd36 100644
--- a/drivers/video/console/newport_con.c
+++ b/drivers/video/console/newport_con.c
@@ -31,17 +31,14 @@
 #include <linux/linux_logo.h>
 #include <linux/font.h>
 
-#define FONT_DATA ((unsigned char *)font_vga_8x16.data)
+#define NEWPORT_LEN	0x10000
 
-/* borrowed from fbcon.c */
-#define REFCOUNT(fd)	(((int *)(fd))[-1])
-#define FNTSIZE(fd)	(((int *)(fd))[-2])
-#define FNTCHARCNT(fd)	(((int *)(fd))[-3])
-#define FONT_EXTRA_WORDS 3
+#define FONT_DATA ((unsigned char *)font_vga_8x16.data)
 
 static unsigned char *font_data[MAX_NR_CONSOLES];
 
 static struct newport_regs *npregs;
+static unsigned long newport_addr;
 
 static int logo_active;
 static int topscan;
@@ -519,6 +516,7 @@ static int newport_set_font(int unit, struct console_font *op)
 	FNTSIZE(new_data) = size;
 	FNTCHARCNT(new_data) = op->charcount;
 	REFCOUNT(new_data) = 0;	/* usage counter */
+	FNTSUM(new_data) = 0;
 
 	p = new_data;
 	for (i = 0; i < op->charcount; i++) {
@@ -701,7 +699,6 @@ const struct consw newport_con = {
 static int newport_probe(struct gio_device *dev,
 			 const struct gio_device_id *id)
 {
-	unsigned long newport_addr;
 	int err;
 
 	if (!dev->resource.start)
@@ -711,7 +708,7 @@ static int newport_probe(struct gio_device *dev,
 		return -EBUSY; /* we only support one Newport as console */
 
 	newport_addr = dev->resource.start + 0xF0000;
-	if (!request_mem_region(newport_addr, 0x10000, "Newport"))
+	if (!request_mem_region(newport_addr, NEWPORT_LEN, "Newport"))
 		return -ENODEV;
 
 	npregs = (struct newport_regs *)/* ioremap cannot fail */
@@ -719,6 +716,11 @@ static int newport_probe(struct gio_device *dev,
 	console_lock();
 	err = do_take_over_console(&newport_con, 0, MAX_NR_CONSOLES - 1, 1);
 	console_unlock();
+
+	if (err) {
+		iounmap((void *)npregs);
+		release_mem_region(newport_addr, NEWPORT_LEN);
+	}
 	return err;
 }
 
@@ -726,6 +728,7 @@ static void newport_remove(struct gio_device *dev)
 {
 	give_up_console(&newport_con);
 	iounmap((void *)npregs);
+	release_mem_region(newport_addr, NEWPORT_LEN);
 }
 
 static struct gio_device_id newport_ids[] = {
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index ff6612a3ddc8..a054af74c38f 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -160,209 +160,6 @@ static inline void vga_set_mem_top(struct vc_data *c)
 	write_vga(12, (c->vc_visible_origin - vga_vram_base) / 2);
 }
 
-#ifdef CONFIG_VGACON_SOFT_SCROLLBACK
-/* software scrollback */
-struct vgacon_scrollback_info {
-	void *data;
-	int tail;
-	int size;
-	int rows;
-	int cnt;
-	int cur;
-	int save;
-	int restore;
-};
-
-static struct vgacon_scrollback_info *vgacon_scrollback_cur;
-static struct vgacon_scrollback_info vgacon_scrollbacks[MAX_NR_CONSOLES];
-static bool scrollback_persistent = \
-	IS_ENABLED(CONFIG_VGACON_SOFT_SCROLLBACK_PERSISTENT_ENABLE_BY_DEFAULT);
-module_param_named(scrollback_persistent, scrollback_persistent, bool, 0000);
-MODULE_PARM_DESC(scrollback_persistent, "Enable persistent scrollback for all vga consoles");
-
-static void vgacon_scrollback_reset(int vc_num, size_t reset_size)
-{
-	struct vgacon_scrollback_info *scrollback = &vgacon_scrollbacks[vc_num];
-
-	if (scrollback->data && reset_size > 0)
-		memset(scrollback->data, 0, reset_size);
-
-	scrollback->cnt  = 0;
-	scrollback->tail = 0;
-	scrollback->cur  = 0;
-}
-
-static void vgacon_scrollback_init(int vc_num)
-{
-	int pitch = vga_video_num_columns * 2;
-	size_t size = CONFIG_VGACON_SOFT_SCROLLBACK_SIZE * 1024;
-	int rows = size / pitch;
-	void *data;
-
-	data = kmalloc_array(CONFIG_VGACON_SOFT_SCROLLBACK_SIZE, 1024,
-			     GFP_NOWAIT);
-
-	vgacon_scrollbacks[vc_num].data = data;
-	vgacon_scrollback_cur = &vgacon_scrollbacks[vc_num];
-
-	vgacon_scrollback_cur->rows = rows - 1;
-	vgacon_scrollback_cur->size = rows * pitch;
-
-	vgacon_scrollback_reset(vc_num, size);
-}
-
-static void vgacon_scrollback_switch(int vc_num)
-{
-	if (!scrollback_persistent)
-		vc_num = 0;
-
-	if (!vgacon_scrollbacks[vc_num].data) {
-		vgacon_scrollback_init(vc_num);
-	} else {
-		if (scrollback_persistent) {
-			vgacon_scrollback_cur = &vgacon_scrollbacks[vc_num];
-		} else {
-			size_t size = CONFIG_VGACON_SOFT_SCROLLBACK_SIZE * 1024;
-
-			vgacon_scrollback_reset(vc_num, size);
-		}
-	}
-}
-
-static void vgacon_scrollback_startup(void)
-{
-	vgacon_scrollback_cur = &vgacon_scrollbacks[0];
-	vgacon_scrollback_init(0);
-}
-
-static void vgacon_scrollback_update(struct vc_data *c, int t, int count)
-{
-	void *p;
-
-	if (!vgacon_scrollback_cur->data || !vgacon_scrollback_cur->size ||
-	    c->vc_num != fg_console)
-		return;
-
-	p = (void *) (c->vc_origin + t * c->vc_size_row);
-
-	while (count--) {
-		scr_memcpyw(vgacon_scrollback_cur->data +
-			    vgacon_scrollback_cur->tail,
-			    p, c->vc_size_row);
-
-		vgacon_scrollback_cur->cnt++;
-		p += c->vc_size_row;
-		vgacon_scrollback_cur->tail += c->vc_size_row;
-
-		if (vgacon_scrollback_cur->tail >= vgacon_scrollback_cur->size)
-			vgacon_scrollback_cur->tail = 0;
-
-		if (vgacon_scrollback_cur->cnt > vgacon_scrollback_cur->rows)
-			vgacon_scrollback_cur->cnt = vgacon_scrollback_cur->rows;
-
-		vgacon_scrollback_cur->cur = vgacon_scrollback_cur->cnt;
-	}
-}
-
-static void vgacon_restore_screen(struct vc_data *c)
-{
-	vgacon_scrollback_cur->save = 0;
-
-	if (!vga_is_gfx && !vgacon_scrollback_cur->restore) {
-		scr_memcpyw((u16 *) c->vc_origin, (u16 *) c->vc_screenbuf,
-			    c->vc_screenbuf_size > vga_vram_size ?
-			    vga_vram_size : c->vc_screenbuf_size);
-		vgacon_scrollback_cur->restore = 1;
-		vgacon_scrollback_cur->cur = vgacon_scrollback_cur->cnt;
-	}
-}
-
-static void vgacon_scrolldelta(struct vc_data *c, int lines)
-{
-	int start, end, count, soff;
-
-	if (!lines) {
-		c->vc_visible_origin = c->vc_origin;
-		vga_set_mem_top(c);
-		return;
-	}
-
-	if (!vgacon_scrollback_cur->data)
-		return;
-
-	if (!vgacon_scrollback_cur->save) {
-		vgacon_cursor(c, CM_ERASE);
-		vgacon_save_screen(c);
-		vgacon_scrollback_cur->save = 1;
-	}
-
-	vgacon_scrollback_cur->restore = 0;
-	start = vgacon_scrollback_cur->cur + lines;
-	end = start + abs(lines);
-
-	if (start < 0)
-		start = 0;
-
-	if (start > vgacon_scrollback_cur->cnt)
-		start = vgacon_scrollback_cur->cnt;
-
-	if (end < 0)
-		end = 0;
-
-	if (end > vgacon_scrollback_cur->cnt)
-		end = vgacon_scrollback_cur->cnt;
-
-	vgacon_scrollback_cur->cur = start;
-	count = end - start;
-	soff = vgacon_scrollback_cur->tail -
-		((vgacon_scrollback_cur->cnt - end) * c->vc_size_row);
-	soff -= count * c->vc_size_row;
-
-	if (soff < 0)
-		soff += vgacon_scrollback_cur->size;
-
-	count = vgacon_scrollback_cur->cnt - start;
-
-	if (count > c->vc_rows)
-		count = c->vc_rows;
-
-	if (count) {
-		int copysize;
-
-		int diff = c->vc_rows - count;
-		void *d = (void *) c->vc_origin;
-		void *s = (void *) c->vc_screenbuf;
-
-		count *= c->vc_size_row;
-		/* how much memory to end of buffer left? */
-		copysize = min(count, vgacon_scrollback_cur->size - soff);
-		scr_memcpyw(d, vgacon_scrollback_cur->data + soff, copysize);
-		d += copysize;
-		count -= copysize;
-
-		if (count) {
-			scr_memcpyw(d, vgacon_scrollback_cur->data, count);
-			d += count;
-		}
-
-		if (diff)
-			scr_memcpyw(d, s, diff * c->vc_size_row);
-	} else
-		vgacon_cursor(c, CM_MOVE);
-}
-
-static void vgacon_flush_scrollback(struct vc_data *c)
-{
-	size_t size = CONFIG_VGACON_SOFT_SCROLLBACK_SIZE * 1024;
-
-	vgacon_scrollback_reset(c->vc_num, size);
-}
-#else
-#define vgacon_scrollback_startup(...) do { } while (0)
-#define vgacon_scrollback_init(...)    do { } while (0)
-#define vgacon_scrollback_update(...)  do { } while (0)
-#define vgacon_scrollback_switch(...)  do { } while (0)
-
 static void vgacon_restore_screen(struct vc_data *c)
 {
 	if (c->vc_origin != c->vc_visible_origin)
@@ -376,11 +173,6 @@ static void vgacon_scrolldelta(struct vc_data *c, int lines)
 	vga_set_mem_top(c);
 }
 
-static void vgacon_flush_scrollback(struct vc_data *c)
-{
-}
-#endif /* CONFIG_VGACON_SOFT_SCROLLBACK */
-
 static const char *vgacon_startup(void)
 {
 	const char *display_desc = NULL;
@@ -563,10 +355,7 @@ static const char *vgacon_startup(void)
 	vgacon_xres = screen_info.orig_video_cols * VGA_FONTWIDTH;
 	vgacon_yres = vga_scan_lines;
 
-	if (!vga_init_done) {
-		vgacon_scrollback_startup();
-		vga_init_done = true;
-	}
+	vga_init_done = true;
 
 	return display_desc;
 }
@@ -857,7 +646,6 @@ static int vgacon_switch(struct vc_data *c)
 			vgacon_doresize(c, c->vc_cols, c->vc_rows);
 	}
 
-	vgacon_scrollback_switch(c->vc_num);
 	return 0;		/* Redrawing not needed */
 }
 
@@ -1373,7 +1161,6 @@ static bool vgacon_scroll(struct vc_data *c, unsigned int t, unsigned int b,
 	oldo = c->vc_origin;
 	delta = lines * c->vc_size_row;
 	if (dir == SM_UP) {
-		vgacon_scrollback_update(c, t, lines);
 		if (c->vc_scr_end + delta >= vga_vram_end) {
 			scr_memcpyw((u16 *) vga_vram_base,
 				    (u16 *) (oldo + delta),
@@ -1438,7 +1225,6 @@ const struct consw vga_con = {
 	.con_save_screen = vgacon_save_screen,
 	.con_build_attr = vgacon_build_attr,
 	.con_invert_region = vgacon_invert_region,
-	.con_flush_scrollback = vgacon_flush_scrollback,
 };
 EXPORT_SYMBOL(vga_con);
 
diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c
index 790900d646c0..33408c1994a6 100644
--- a/drivers/video/fbdev/core/bitblit.c
+++ b/drivers/video/fbdev/core/bitblit.c
@@ -216,7 +216,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dx = info->var.xoffset + rs;
 		region.dy = 0;
 		region.width = rw;
@@ -224,7 +224,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dx = info->var.xoffset;
 		region.dy = info->var.yoffset + bs;
 		region.width = rs;
@@ -234,7 +234,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 }
 
 static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode,
-		       int softback_lines, int fg, int bg)
+		       int fg, int bg)
 {
 	struct fb_cursor cursor;
 	struct fbcon_ops *ops = info->fbcon_par;
@@ -247,15 +247,6 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 
 	cursor.set = 0;
 
-	if (softback_lines) {
-		if (y + softback_lines >= vc->vc_rows) {
-			mode = CM_ERASE;
-			ops->cursor_flash = 0;
-			return;
-		} else
-			y += softback_lines;
-	}
-
  	c = scr_readw((u16 *) vc->vc_pos);
 	attribute = get_attribute(info, c);
 	src = vc->vc_font.data + ((c & charmask) * (w * vc->vc_font.height));
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 41360caff17f..6bdf9ca787fb 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -102,12 +102,6 @@ static int logo_lines;
 /* logo_shown is an index to vc_cons when >= 0; otherwise follows FBCON_LOGO
    enums.  */
 static int logo_shown = FBCON_LOGO_CANSHOW;
-/* Software scrollback */
-static int fbcon_softback_size = 32768;
-static unsigned long softback_buf, softback_curr;
-static unsigned long softback_in;
-static unsigned long softback_top, softback_end;
-static int softback_lines;
 /* console mappings */
 static int first_fb_vc;
 static int last_fb_vc = MAX_NR_CONSOLES - 1;
@@ -142,8 +136,6 @@ static int margin_color;
 
 static const struct consw fb_con;
 
-#define CM_SOFTBACK	(8)
-
 #define advance_row(p, delta) (unsigned short *)((unsigned long)(p) + (delta) * vc->vc_size_row)
 
 static int fbcon_set_origin(struct vc_data *);
@@ -349,18 +341,6 @@ static int get_color(struct vc_data *vc, struct fb_info *info,
 	return color;
 }
 
-static void fbcon_update_softback(struct vc_data *vc)
-{
-	int l = fbcon_softback_size / vc->vc_size_row;
-
-	if (l > 5)
-		softback_end = softback_buf + l * vc->vc_size_row;
-	else
-		/* Smaller scrollback makes no sense, and 0 would screw
-		   the operation totally */
-		softback_top = 0;
-}
-
 static void fb_flashcursor(struct work_struct *work)
 {
 	struct fb_info *info = container_of(work, struct fb_info, queue);
@@ -390,7 +370,7 @@ static void fb_flashcursor(struct work_struct *work)
 	c = scr_readw((u16 *) vc->vc_pos);
 	mode = (!ops->cursor_flash || ops->cursor_state.enable) ?
 		CM_ERASE : CM_DRAW;
-	ops->cursor(vc, info, mode, softback_lines, get_color(vc, info, c, 1),
+	ops->cursor(vc, info, mode, get_color(vc, info, c, 1),
 		    get_color(vc, info, c, 0));
 	console_unlock();
 }
@@ -448,13 +428,7 @@ static int __init fb_console_setup(char *this_opt)
 		}
 		
 		if (!strncmp(options, "scrollback:", 11)) {
-			options += 11;
-			if (*options) {
-				fbcon_softback_size = simple_strtoul(options, &options, 0);
-				if (*options == 'k' || *options == 'K') {
-					fbcon_softback_size *= 1024;
-				}
-			}
+			pr_warn("Ignoring scrollback size option\n");
 			continue;
 		}
 		
@@ -969,31 +943,6 @@ static const char *fbcon_startup(void)
 		p->con_rotate = fbcon_platform_get_rotate(info);
 	set_blitting_type(vc, info);
 
-	if (info->fix.type != FB_TYPE_TEXT) {
-		if (fbcon_softback_size) {
-			if (!softback_buf) {
-				softback_buf =
-				    (unsigned long)
-				    kmalloc(fbcon_softback_size,
-					    GFP_KERNEL);
-				if (!softback_buf) {
-					fbcon_softback_size = 0;
-					softback_top = 0;
-				}
-			}
-		} else {
-			if (softback_buf) {
-				kfree((void *) softback_buf);
-				softback_buf = 0;
-				softback_top = 0;
-			}
-		}
-		if (softback_buf)
-			softback_in = softback_top = softback_curr =
-			    softback_buf;
-		softback_lines = 0;
-	}
-
 	/* Setup default font */
 	if (!p->fontdata && !vc->vc_font.data) {
 		if (!fontname[0] || !(font = find_font(fontname)))
@@ -1159,9 +1108,6 @@ static void fbcon_init(struct vc_data *vc, int init)
 	if (logo)
 		fbcon_prepare_logo(vc, info, cols, rows, new_cols, new_rows);
 
-	if (vc == svc && softback_buf)
-		fbcon_update_softback(vc);
-
 	if (ops->rotate_font && ops->rotate_font(info, vc)) {
 		ops->rotate = FB_ROTATE_UR;
 		set_blitting_type(vc, info);
@@ -1324,7 +1270,6 @@ static void fbcon_cursor(struct vc_data *vc, int mode)
 {
 	struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]];
 	struct fbcon_ops *ops = info->fbcon_par;
-	int y;
  	int c = scr_readw((u16 *) vc->vc_pos);
 
 	ops->cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms);
@@ -1338,16 +1283,8 @@ static void fbcon_cursor(struct vc_data *vc, int mode)
 		fbcon_add_cursor_timer(info);
 
 	ops->cursor_flash = (mode == CM_ERASE) ? 0 : 1;
-	if (mode & CM_SOFTBACK) {
-		mode &= ~CM_SOFTBACK;
-		y = softback_lines;
-	} else {
-		if (softback_lines)
-			fbcon_set_origin(vc);
-		y = 0;
-	}
 
-	ops->cursor(vc, info, mode, y, get_color(vc, info, c, 1),
+	ops->cursor(vc, info, mode, get_color(vc, info, c, 1),
 		    get_color(vc, info, c, 0));
 }
 
@@ -1418,8 +1355,6 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var,
 
 	if (con_is_visible(vc)) {
 		update_screen(vc);
-		if (softback_buf)
-			fbcon_update_softback(vc);
 	}
 }
 
@@ -1557,99 +1492,6 @@ static __inline__ void ypan_down_redraw(struct vc_data *vc, int t, int count)
 	scrollback_current = 0;
 }
 
-static void fbcon_redraw_softback(struct vc_data *vc, struct display *p,
-				  long delta)
-{
-	int count = vc->vc_rows;
-	unsigned short *d, *s;
-	unsigned long n;
-	int line = 0;
-
-	d = (u16 *) softback_curr;
-	if (d == (u16 *) softback_in)
-		d = (u16 *) vc->vc_origin;
-	n = softback_curr + delta * vc->vc_size_row;
-	softback_lines -= delta;
-	if (delta < 0) {
-		if (softback_curr < softback_top && n < softback_buf) {
-			n += softback_end - softback_buf;
-			if (n < softback_top) {
-				softback_lines -=
-				    (softback_top - n) / vc->vc_size_row;
-				n = softback_top;
-			}
-		} else if (softback_curr >= softback_top
-			   && n < softback_top) {
-			softback_lines -=
-			    (softback_top - n) / vc->vc_size_row;
-			n = softback_top;
-		}
-	} else {
-		if (softback_curr > softback_in && n >= softback_end) {
-			n += softback_buf - softback_end;
-			if (n > softback_in) {
-				n = softback_in;
-				softback_lines = 0;
-			}
-		} else if (softback_curr <= softback_in && n > softback_in) {
-			n = softback_in;
-			softback_lines = 0;
-		}
-	}
-	if (n == softback_curr)
-		return;
-	softback_curr = n;
-	s = (u16 *) softback_curr;
-	if (s == (u16 *) softback_in)
-		s = (u16 *) vc->vc_origin;
-	while (count--) {
-		unsigned short *start;
-		unsigned short *le;
-		unsigned short c;
-		int x = 0;
-		unsigned short attr = 1;
-
-		start = s;
-		le = advance_row(s, 1);
-		do {
-			c = scr_readw(s);
-			if (attr != (c & 0xff00)) {
-				attr = c & 0xff00;
-				if (s > start) {
-					fbcon_putcs(vc, start, s - start,
-						    line, x);
-					x += s - start;
-					start = s;
-				}
-			}
-			if (c == scr_readw(d)) {
-				if (s > start) {
-					fbcon_putcs(vc, start, s - start,
-						    line, x);
-					x += s - start + 1;
-					start = s + 1;
-				} else {
-					x++;
-					start++;
-				}
-			}
-			s++;
-			d++;
-		} while (s < le);
-		if (s > start)
-			fbcon_putcs(vc, start, s - start, line, x);
-		line++;
-		if (d == (u16 *) softback_end)
-			d = (u16 *) softback_buf;
-		if (d == (u16 *) softback_in)
-			d = (u16 *) vc->vc_origin;
-		if (s == (u16 *) softback_end)
-			s = (u16 *) softback_buf;
-		if (s == (u16 *) softback_in)
-			s = (u16 *) vc->vc_origin;
-	}
-}
-
 static void fbcon_redraw_move(struct vc_data *vc, struct display *p,
 			      int line, int count, int dy)
 {
@@ -1789,31 +1631,6 @@ static void fbcon_redraw(struct vc_data *vc, struct display *p,
 	}
 }
 
-static inline void fbcon_softback_note(struct vc_data *vc, int t,
-				       int count)
-{
-	unsigned short *p;
-
-	if (vc->vc_num != fg_console)
-		return;
-	p = (unsigned short *) (vc->vc_origin + t * vc->vc_size_row);
-
-	while (count) {
-		scr_memcpyw((u16 *) softback_in, p, vc->vc_size_row);
-		count--;
-		p = advance_row(p, 1);
-		softback_in += vc->vc_size_row;
-		if (softback_in == softback_end)
-			softback_in = softback_buf;
-		if (softback_in == softback_top) {
-			softback_top += vc->vc_size_row;
-			if (softback_top == softback_end)
-				softback_top = softback_buf;
-		}
-	}
-	softback_curr = softback_in;
-}
-
 static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b,
 		enum con_scroll dir, unsigned int count)
 {
@@ -1836,8 +1653,6 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b,
 	case SM_UP:
 		if (count > vc->vc_rows)	/* Maximum realistic size */
 			count = vc->vc_rows;
-		if (softback_top)
-			fbcon_softback_note(vc, t, count);
 		if (logo_shown >= 0)
 			goto redraw_up;
 		switch (p->scrollmode) {
@@ -2130,6 +1945,9 @@ static void updatescrollmode(struct display *p,
 	}
 }
 
+#define PITCH(w) (((w) + 7) >> 3)
+#define CALC_FONTSZ(h, p, c) ((h) * (p) * (c)) /* size = height * pitch * charcount */
+
 static int fbcon_resize(struct vc_data *vc, unsigned int width, 
 			unsigned int height, unsigned int user)
 {
@@ -2139,6 +1957,24 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width,
 	struct fb_var_screeninfo var = info->var;
 	int x_diff, y_diff, virt_w, virt_h, virt_fw, virt_fh;
 
+	if (p->userfont && FNTSIZE(vc->vc_font.data)) {
+		int size;
+		int pitch = PITCH(vc->vc_font.width);
+
+		/*
+		 * If user font, ensure that a possible change to user font
+		 * height or width will not allow a font data out-of-bounds access.
+		 * NOTE: must use original charcount in calculation as font
+		 * charcount can change and cannot be used to determine the
+		 * font data allocated size.
+		 */
+		if (pitch <= 0)
+			return -EINVAL;
+		size = CALC_FONTSZ(vc->vc_font.height, pitch, FNTCHARCNT(vc->vc_font.data));
+		if (size > FNTSIZE(vc->vc_font.data))
+			return -EINVAL;
+	}
+
 	virt_w = FBCON_SWAP(ops->rotate, width, height);
 	virt_h = FBCON_SWAP(ops->rotate, height, width);
 	virt_fw = FBCON_SWAP(ops->rotate, vc->vc_font.width,
@@ -2187,14 +2023,6 @@ static int fbcon_switch(struct vc_data *vc)
 	info = registered_fb[con2fb_map[vc->vc_num]];
 	ops = info->fbcon_par;
 
-	if (softback_top) {
-		if (softback_lines)
-			fbcon_set_origin(vc);
-		softback_top = softback_curr = softback_in = softback_buf;
-		softback_lines = 0;
-		fbcon_update_softback(vc);
-	}
-
 	if (logo_shown >= 0) {
 		struct vc_data *conp2 = vc_cons[logo_shown].d;
 
@@ -2420,6 +2248,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font)
 
 	if (font->width <= 8) {
 		j = vc->vc_font.height;
+		if (font->charcount * j > FNTSIZE(fontdata))
+			return -EINVAL;
+
 		for (i = 0; i < font->charcount; i++) {
 			memcpy(data, fontdata, j);
 			memset(data + j, 0, 32 - j);
@@ -2428,6 +2259,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font)
 		}
 	} else if (font->width <= 16) {
 		j = vc->vc_font.height * 2;
+		if (font->charcount * j > FNTSIZE(fontdata))
+			return -EINVAL;
+
 		for (i = 0; i < font->charcount; i++) {
 			memcpy(data, fontdata, j);
 			memset(data + j, 0, 64 - j);
@@ -2435,6 +2269,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font)
 			fontdata += j;
 		}
 	} else if (font->width <= 24) {
+		if (font->charcount * (vc->vc_font.height * sizeof(u32)) > FNTSIZE(fontdata))
+			return -EINVAL;
+
 		for (i = 0; i < font->charcount; i++) {
 			for (j = 0; j < vc->vc_font.height; j++) {
 				*data++ = fontdata[0];
@@ -2447,6 +2284,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font)
 		}
 	} else {
 		j = vc->vc_font.height * 4;
+		if (font->charcount * j > FNTSIZE(fontdata))
+			return -EINVAL;
+
 		for (i = 0; i < font->charcount; i++) {
 			memcpy(data, fontdata, j);
 			memset(data + j, 0, 128 - j);
@@ -2528,9 +2368,6 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h,
 	int cnt;
 	char *old_data = NULL;
 
-	if (con_is_visible(vc) && softback_lines)
-		fbcon_set_origin(vc);
-
 	resize = (w != vc->vc_font.width) || (h != vc->vc_font.height);
 	if (p->userfont)
 		old_data = vc->vc_font.data;
@@ -2556,8 +2393,6 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h,
 		cols /= w;
 		rows /= h;
 		vc_resize(vc, cols, rows);
-		if (con_is_visible(vc) && softback_buf)
-			fbcon_update_softback(vc);
 	} else if (con_is_visible(vc)
 		   && vc->vc_mode == KD_TEXT) {
 		fbcon_clear_margins(vc, 0);
@@ -2600,7 +2435,7 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, unsigne
 	int size;
 	int i, csum;
 	u8 *new_data, *data = font->data;
-	int pitch = (font->width+7) >> 3;
+	int pitch = PITCH(font->width);
 
 	/* Is there a reason why fbconsole couldn't handle any charcount >256?
 	 * If not this check should be changed to charcount < 256 */
@@ -2616,7 +2451,7 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, unsigne
 	if (fbcon_invalid_charcount(info, charcount))
 		return -EINVAL;
 
-	size = h * pitch * charcount;
+	size = CALC_FONTSZ(h, pitch, charcount);
 
 	new_data = kmalloc(FONT_EXTRA_WORDS * sizeof(int) + size, GFP_USER);
 
@@ -2715,19 +2550,7 @@ static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table)
 
 static u16 *fbcon_screen_pos(struct vc_data *vc, int offset)
 {
-	unsigned long p;
-	int line;
-	
-	if (vc->vc_num != fg_console || !softback_lines)
-		return (u16 *) (vc->vc_origin + offset);
-	line = offset / vc->vc_size_row;
-	if (line >= softback_lines)
-		return (u16 *) (vc->vc_origin + offset -
-				softback_lines * vc->vc_size_row);
-	p = softback_curr + offset;
-	if (p >= softback_end)
-		p += softback_buf - softback_end;
-	return (u16 *) p;
+	return (u16 *) (vc->vc_origin + offset);
 }
 
 static unsigned long fbcon_getxy(struct vc_data *vc, unsigned long pos,
@@ -2741,22 +2564,7 @@ static unsigned long fbcon_getxy(struct vc_data *vc, unsigned long pos,
 
 		x = offset % vc->vc_cols;
 		y = offset / vc->vc_cols;
-		if (vc->vc_num == fg_console)
-			y += softback_lines;
 		ret = pos + (vc->vc_cols - x) * 2;
-	} else if (vc->vc_num == fg_console && softback_lines) {
-		unsigned long offset = pos - softback_curr;
-
-		if (pos < softback_curr)
-			offset += softback_end - softback_buf;
-		offset /= 2;
-		x = offset % vc->vc_cols;
-		y = offset / vc->vc_cols;
-		ret = pos + (vc->vc_cols - x) * 2;
-		if (ret == softback_end)
-			ret = softback_buf;
-		if (ret == softback_in)
-			ret = vc->vc_origin;
 	} else {
 		/* Should not happen */
 		x = y = 0;
@@ -2784,106 +2592,11 @@ static void fbcon_invert_region(struct vc_data *vc, u16 * p, int cnt)
 			a = ((a) & 0x88ff) | (((a) & 0x7000) >> 4) |
 			    (((a) & 0x0700) << 4);
 		scr_writew(a, p++);
-		if (p == (u16 *) softback_end)
-			p = (u16 *) softback_buf;
-		if (p == (u16 *) softback_in)
-			p = (u16 *) vc->vc_origin;
 	}
 }
 
-static void fbcon_scrolldelta(struct vc_data *vc, int lines)
-{
-	struct fb_info *info = registered_fb[con2fb_map[fg_console]];
-	struct fbcon_ops *ops = info->fbcon_par;
-	struct display *disp = &fb_display[fg_console];
-	int offset, limit, scrollback_old;
-
-	if (softback_top) {
-		if (vc->vc_num != fg_console)
-			return;
-		if (vc->vc_mode != KD_TEXT || !lines)
-			return;
-		if (logo_shown >= 0) {
-			struct vc_data *conp2 = vc_cons[logo_shown].d;
-
-			if (conp2->vc_top == logo_lines
-			    && conp2->vc_bottom == conp2->vc_rows)
-				conp2->vc_top = 0;
-			if (logo_shown == vc->vc_num) {
-				unsigned long p, q;
-				int i;
-
-				p = softback_in;
-				q = vc->vc_origin +
-				    logo_lines * vc->vc_size_row;
-				for (i = 0; i < logo_lines; i++) {
-					if (p == softback_top)
-						break;
-					if (p == softback_buf)
-						p = softback_end;
-					p -= vc->vc_size_row;
-					q -= vc->vc_size_row;
-					scr_memcpyw((u16 *) q, (u16 *) p,
-						    vc->vc_size_row);
-				}
-				softback_in = softback_curr = p;
-				update_region(vc, vc->vc_origin,
-					      logo_lines * vc->vc_cols);
-			}
-			logo_shown = FBCON_LOGO_CANSHOW;
-		}
-		fbcon_cursor(vc, CM_ERASE | CM_SOFTBACK);
-		fbcon_redraw_softback(vc, disp, lines);
-		fbcon_cursor(vc, CM_DRAW | CM_SOFTBACK);
-		return;
-	}
-
-	if (!scrollback_phys_max)
-		return;
-
-	scrollback_old = scrollback_current;
-	scrollback_current -= lines;
-	if (scrollback_current < 0)
-		scrollback_current = 0;
-	else if (scrollback_current > scrollback_max)
-		scrollback_current = scrollback_max;
-	if (scrollback_current == scrollback_old)
-		return;
-
-	if (fbcon_is_inactive(vc, info))
-		return;
-
-	fbcon_cursor(vc, CM_ERASE);
-
-	offset = disp->yscroll - scrollback_current;
-	limit = disp->vrows;
-	switch (disp->scrollmode) {
-	case SCROLL_WRAP_MOVE:
-		info->var.vmode |= FB_VMODE_YWRAP;
-		break;
-	case SCROLL_PAN_MOVE:
-	case SCROLL_PAN_REDRAW:
-		limit -= vc->vc_rows;
-		info->var.vmode &= ~FB_VMODE_YWRAP;
-		break;
-	}
-	if (offset < 0)
-		offset += limit;
-	else if (offset >= limit)
-		offset -= limit;
-
-	ops->var.xoffset = 0;
-	ops->var.yoffset = offset * vc->vc_font.height;
-	ops->update_start(info);
-
-	if (!scrollback_current)
-		fbcon_cursor(vc, CM_DRAW);
-}
-
 static int fbcon_set_origin(struct vc_data *vc)
 {
-	if (softback_lines)
-		fbcon_scrolldelta(vc, softback_lines);
 	return 0;
 }
 
@@ -2947,8 +2660,6 @@ static void fbcon_modechanged(struct fb_info *info)
 
 		fbcon_set_palette(vc, color_table);
 		update_screen(vc);
-		if (softback_buf)
-			fbcon_update_softback(vc);
 	}
 }
 
@@ -3368,7 +3079,6 @@ static const struct consw fb_con = {
 	.con_font_default	= fbcon_set_def_font,
 	.con_font_copy 		= fbcon_copy_font,
 	.con_set_palette 	= fbcon_set_palette,
-	.con_scrolldelta 	= fbcon_scrolldelta,
 	.con_set_origin 	= fbcon_set_origin,
 	.con_invert_region 	= fbcon_invert_region,
 	.con_screen_pos 	= fbcon_screen_pos,
@@ -3577,9 +3287,6 @@ static void fbcon_exit(void)
 	if (fbcon_has_exited)
 		return;
 
-	kfree((void *)softback_buf);
-	softback_buf = 0UL;
-
 	for (i = 0; i < FB_MAX; i++) {
 		int pending = 0;
 
diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h
index 18f3ac144237..35128c1e191f 100644
--- a/drivers/video/fbdev/core/fbcon.h
+++ b/drivers/video/fbdev/core/fbcon.h
@@ -62,7 +62,7 @@ struct fbcon_ops {
 	void (*clear_margins)(struct vc_data *vc, struct fb_info *info,
 			      int color, int bottom_only);
 	void (*cursor)(struct vc_data *vc, struct fb_info *info, int mode,
-		       int softback_lines, int fg, int bg);
+		       int fg, int bg);
 	int  (*update_start)(struct fb_info *info);
 	int  (*rotate_font)(struct fb_info *info, struct vc_data *vc);
 	struct fb_var_screeninfo var;  /* copy of the current fb_var_screeninfo */
@@ -151,13 +151,6 @@ static inline int attr_col_ec(int shift, struct vc_data *vc,
 #define attr_bgcol_ec(bgshift, vc, info) attr_col_ec(bgshift, vc, info, 0)
 #define attr_fgcol_ec(fgshift, vc, info) attr_col_ec(fgshift, vc, info, 1)
 
-/* Font */
-#define REFCOUNT(fd)	(((int *)(fd))[-1])
-#define FNTSIZE(fd)	(((int *)(fd))[-2])
-#define FNTCHARCNT(fd)	(((int *)(fd))[-3])
-#define FNTSUM(fd)	(((int *)(fd))[-4])
-#define FONT_EXTRA_WORDS 4
-
     /*
      *  Scroll Method
      */
diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c
index 37a8b0b22566..be6103bedf2e 100644
--- a/drivers/video/fbdev/core/fbcon_ccw.c
+++ b/drivers/video/fbdev/core/fbcon_ccw.c
@@ -201,7 +201,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info,
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dx = 0;
 		region.dy = info->var.yoffset;
 		region.height = rw;
@@ -209,7 +209,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info,
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dx = info->var.xoffset + bs;
 		region.dy = 0;
                 region.height = info->var.yres_virtual;
@@ -219,7 +219,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info,
 }
 
 static void ccw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
-		       int softback_lines, int fg, int bg)
+		       int fg, int bg)
 {
 	struct fb_cursor cursor;
 	struct fbcon_ops *ops = info->fbcon_par;
@@ -236,15 +236,6 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 
 	cursor.set = 0;
 
-	if (softback_lines) {
-		if (y + softback_lines >= vc->vc_rows) {
-			mode = CM_ERASE;
-			ops->cursor_flash = 0;
-			return;
-		} else
-			y += softback_lines;
-	}
-
  	c = scr_readw((u16 *) vc->vc_pos);
 	attribute = get_attribute(info, c);
 	src = ops->fontbuffer + ((c & charmask) * (w * vc->vc_font.width));
diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c
index 1888f8c866e8..dab93bb1ba42 100644
--- a/drivers/video/fbdev/core/fbcon_cw.c
+++ b/drivers/video/fbdev/core/fbcon_cw.c
@@ -184,7 +184,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info,
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dx = 0;
 		region.dy = info->var.yoffset + rs;
 		region.height = rw;
@@ -192,7 +192,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info,
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dx = info->var.xoffset;
 		region.dy = info->var.yoffset;
                 region.height = info->var.yres;
@@ -202,7 +202,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info,
 }
 
 static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
-		      int softback_lines, int fg, int bg)
+		      int fg, int bg)
 {
 	struct fb_cursor cursor;
 	struct fbcon_ops *ops = info->fbcon_par;
@@ -219,15 +219,6 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 
 	cursor.set = 0;
 
-	if (softback_lines) {
-		if (y + softback_lines >= vc->vc_rows) {
-			mode = CM_ERASE;
-			ops->cursor_flash = 0;
-			return;
-		} else
-			y += softback_lines;
-	}
-
  	c = scr_readw((u16 *) vc->vc_pos);
 	attribute = get_attribute(info, c);
 	src = ops->fontbuffer + ((c & charmask) * (w * vc->vc_font.width));
diff --git a/drivers/video/fbdev/core/fbcon_rotate.c b/drivers/video/fbdev/core/fbcon_rotate.c
index 8a51e4d95cc5..e9a5c6a4b562 100644
--- a/drivers/video/fbdev/core/fbcon_rotate.c
+++ b/drivers/video/fbdev/core/fbcon_rotate.c
@@ -14,6 +14,7 @@
 #include <linux/fb.h>
 #include <linux/vt_kern.h>
 #include <linux/console.h>
+#include <linux/font.h>
 #include <asm/types.h>
 #include "fbcon.h"
 #include "fbcon_rotate.h"
diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c
index f98eee263597..dfed90bf0768 100644
--- a/drivers/video/fbdev/core/fbcon_ud.c
+++ b/drivers/video/fbdev/core/fbcon_ud.c
@@ -231,7 +231,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info,
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dy = 0;
 		region.dx = info->var.xoffset;
 		region.width  = rw;
@@ -239,7 +239,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info,
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dy = info->var.yoffset;
 		region.dx = info->var.xoffset;
                 region.height  = bh;
@@ -249,7 +249,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info,
 }
 
 static void ud_cursor(struct vc_data *vc, struct fb_info *info, int mode,
-		      int softback_lines, int fg, int bg)
+		      int fg, int bg)
 {
 	struct fb_cursor cursor;
 	struct fbcon_ops *ops = info->fbcon_par;
@@ -267,15 +267,6 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 
 	cursor.set = 0;
 
-	if (softback_lines) {
-		if (y + softback_lines >= vc->vc_rows) {
-			mode = CM_ERASE;
-			ops->cursor_flash = 0;
-			return;
-		} else
-			y += softback_lines;
-	}
-
  	c = scr_readw((u16 *) vc->vc_pos);
 	attribute = get_attribute(info, c);
 	src = ops->fontbuffer + ((c & charmask) * (w * vc->vc_font.height));
diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c
index 93390312957f..adff8d6ffe6f 100644
--- a/drivers/video/fbdev/core/tileblit.c
+++ b/drivers/video/fbdev/core/tileblit.c
@@ -13,6 +13,7 @@
 #include <linux/fb.h>
 #include <linux/vt_kern.h>
 #include <linux/console.h>
+#include <linux/font.h>
 #include <asm/types.h>
 #include "fbcon.h"
 
@@ -80,7 +81,7 @@ static void tile_clear_margins(struct vc_data *vc, struct fb_info *info,
 }
 
 static void tile_cursor(struct vc_data *vc, struct fb_info *info, int mode,
-			int softback_lines, int fg, int bg)
+			int fg, int bg)
 {
 	struct fb_tilecursor cursor;
 	int use_sw = (vc->vc_cursor_type & 0x10);
diff --git a/drivers/video/fbdev/neofb.c b/drivers/video/fbdev/neofb.c
index 5d3a444083f7..2018e1ca33eb 100644
--- a/drivers/video/fbdev/neofb.c
+++ b/drivers/video/fbdev/neofb.c
@@ -1820,6 +1820,7 @@ static int neo_scan_monitor(struct fb_info *info)
 #else
 		printk(KERN_ERR
 		       "neofb: Only 640x480, 800x600/480 and 1024x768 panels are currently supported\n");
+		kfree(info->monspecs.modedb);
 		return -1;
 #endif
 	default:
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
index 7a75dfda9845..00f5a54aaf9b 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
@@ -531,8 +531,11 @@ int dispc_runtime_get(void)
 	DSSDBG("dispc_runtime_get\n");
 
 	r = pm_runtime_get_sync(&dispc.pdev->dev);
-	WARN_ON(r < 0);
-	return r < 0 ? r : 0;
+	if (WARN_ON(r < 0)) {
+		pm_runtime_put_sync(&dispc.pdev->dev);
+		return r;
+	}
+	return 0;
 }
 EXPORT_SYMBOL(dispc_runtime_get);
 
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dsi.c b/drivers/video/fbdev/omap2/omapfb/dss/dsi.c
index 30d49f3800b3..2bfd9063cdfc 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dsi.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dsi.c
@@ -1148,8 +1148,11 @@ static int dsi_runtime_get(struct platform_device *dsidev)
 	DSSDBG("dsi_runtime_get\n");
 
 	r = pm_runtime_get_sync(&dsi->pdev->dev);
-	WARN_ON(r < 0);
-	return r < 0 ? r : 0;
+	if (WARN_ON(r < 0)) {
+		pm_runtime_put_sync(&dsi->pdev->dev);
+		return r;
+	}
+	return 0;
 }
 
 static void dsi_runtime_put(struct platform_device *dsidev)
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss.c b/drivers/video/fbdev/omap2/omapfb/dss/dss.c
index 48c6500c24e1..acecee5b1c10 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dss.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dss.c
@@ -778,8 +778,11 @@ int dss_runtime_get(void)
 	DSSDBG("dss_runtime_get\n");
 
 	r = pm_runtime_get_sync(&dss.pdev->dev);
-	WARN_ON(r < 0);
-	return r < 0 ? r : 0;
+	if (WARN_ON(r < 0)) {
+		pm_runtime_put_sync(&dss.pdev->dev);
+		return r;
+	}
+	return 0;
 }
 
 void dss_runtime_put(void)
@@ -843,7 +846,7 @@ static const struct dss_features omap34xx_dss_feats = {
 };
 
 static const struct dss_features omap3630_dss_feats = {
-	.fck_div_max		=	32,
+	.fck_div_max		=	31,
 	.dss_fck_multiplier	=	1,
 	.parent_clk_name	=	"dpll4_ck",
 	.dpi_select_source	=	&dss_dpi_select_source_omap2_omap3,
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c
index ec78d61bc551..e2d571ca8590 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c
@@ -50,9 +50,10 @@ static int hdmi_runtime_get(void)
 	DSSDBG("hdmi_runtime_get\n");
 
 	r = pm_runtime_get_sync(&hdmi.pdev->dev);
-	WARN_ON(r < 0);
-	if (r < 0)
+	if (WARN_ON(r < 0)) {
+		pm_runtime_put_sync(&hdmi.pdev->dev);
 		return r;
+	}
 
 	return 0;
 }
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5.c
index 2e2fcc3d6d4f..13f3a5ce5529 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5.c
@@ -54,9 +54,10 @@ static int hdmi_runtime_get(void)
 	DSSDBG("hdmi_runtime_get\n");
 
 	r = pm_runtime_get_sync(&hdmi.pdev->dev);
-	WARN_ON(r < 0);
-	if (r < 0)
+	if (WARN_ON(r < 0)) {
+		pm_runtime_put_sync(&hdmi.pdev->dev);
 		return r;
+	}
 
 	return 0;
 }
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/venc.c b/drivers/video/fbdev/omap2/omapfb/dss/venc.c
index 392464da12e4..96714b4596d2 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/venc.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/venc.c
@@ -402,8 +402,11 @@ static int venc_runtime_get(void)
 	DSSDBG("venc_runtime_get\n");
 
 	r = pm_runtime_get_sync(&venc.pdev->dev);
-	WARN_ON(r < 0);
-	return r < 0 ? r : 0;
+	if (WARN_ON(r < 0)) {
+		pm_runtime_put_sync(&venc.pdev->dev);
+		return r;
+	}
+	return 0;
 }
 
 static void venc_runtime_put(void)
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index 29f00eccdd01..08ee77d5df8b 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -2449,8 +2449,8 @@ static int pxafb_remove(struct platform_device *dev)
 
 	free_pages_exact(fbi->video_mem, fbi->video_mem_size);
 
-	dma_free_wc(&dev->dev, fbi->dma_buff_size, fbi->dma_buff,
-		    fbi->dma_buff_phys);
+	dma_free_coherent(&dev->dev, fbi->dma_buff_size, fbi->dma_buff,
+			  fbi->dma_buff_phys);
 
 	iounmap(fbi->mmio_base);
 
diff --git a/drivers/video/fbdev/sm712fb.c b/drivers/video/fbdev/sm712fb.c
index f1dcc6766d1e..1781ca697f66 100644
--- a/drivers/video/fbdev/sm712fb.c
+++ b/drivers/video/fbdev/sm712fb.c
@@ -1429,6 +1429,8 @@ static int smtc_map_smem(struct smtcfb_info *sfb,
 static void smtc_unmap_smem(struct smtcfb_info *sfb)
 {
 	if (sfb && sfb->fb->screen_base) {
+		if (sfb->chip_id == 0x720)
+			sfb->fb->screen_base -= 0x00200000;
 		iounmap(sfb->fb->screen_base);
 		sfb->fb->screen_base = NULL;
 	}
diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c
index c592ca513115..2e88f01cddac 100644
--- a/drivers/video/fbdev/uvesafb.c
+++ b/drivers/video/fbdev/uvesafb.c
@@ -43,6 +43,7 @@ static const struct fb_fix_screeninfo uvesafb_fix = {
 	.visual = FB_VISUAL_TRUECOLOR,
 };
 
+static int task_timeout = UVESAFB_TIMEOUT; /* timeout [ms] of task execution */
 static int mtrr		= 3;	/* enable mtrr by default */
 static bool blank	= 1;	/* enable blanking by default */
 static int ypan		= 1;	/* 0: scroll, 1: ypan, 2: ywrap */
@@ -146,7 +147,9 @@ static int uvesafb_exec(struct uvesafb_ktask *task)
 	struct cn_msg *m;
 	int err;
 	int len = sizeof(task->t) + task->t.buf_len;
-
+	int forever_wait = task_timeout < 0 ? 1 : 0;
+	/* For infinite wait case, set interval to the legacy 5000 ms */
+	int timeout = forever_wait ? 5000 : task_timeout;
 	/*
 	 * Check whether the message isn't longer than the maximum
 	 * allowed by connector.
@@ -212,9 +215,21 @@ static int uvesafb_exec(struct uvesafb_ktask *task)
 	} else if (err == -ENOBUFS)
 		err = 0;
 
-	if (!err && !(task->t.flags & TF_EXIT))
-		err = !wait_for_completion_timeout(task->done,
-				msecs_to_jiffies(UVESAFB_TIMEOUT));
+	if (!err && !(task->t.flags & TF_EXIT)) {
+		do {
+			err = !wait_for_completion_timeout(task->done,
+					msecs_to_jiffies(timeout));
+			if (err)
+				printk_ratelimited(
+						KERN_WARNING
+						"uvesafb: %u ms task timeout%s\n",
+						timeout,
+						forever_wait ?
+						", infinitely waiting." : ".");
+			else
+				break;
+		} while (forever_wait);
+	}
 
 	mutex_lock(&uvfb_lock);
 	uvfb_tasks[seq] = NULL;
@@ -1815,6 +1830,8 @@ static int uvesafb_setup(char *options)
 	while ((this_opt = strsep(&options, ",")) != NULL) {
 		if (!*this_opt) continue;
 
+		if (!strncmp(this_opt, "task_timeout", 12))
+			task_timeout = simple_strtol(this_opt+12, NULL, 0);
 		if (!strcmp(this_opt, "redraw"))
 			ypan = 0;
 		else if (!strcmp(this_opt, "ypan"))
@@ -1958,6 +1975,9 @@ static const struct kernel_param_ops param_ops_scroll = {
 };
 #define param_check_scroll(name, p) __param_check(name, p, void)
 
+module_param(task_timeout, int, 0400);
+MODULE_PARM_DESC(task_timeout,
+	"Timeout [ms] of a task's completion, or set to any negative value to infinitely wait");
 module_param_named(scroll, ypan, scroll, 0);
 MODULE_PARM_DESC(scroll,
 	"Scrolling mode, set to 'redraw', 'ypan', or 'ywrap'");
diff --git a/drivers/video/fbdev/vga16fb.c b/drivers/video/fbdev/vga16fb.c
index 5f0690c8fc93..ee6957a799bb 100644
--- a/drivers/video/fbdev/vga16fb.c
+++ b/drivers/video/fbdev/vga16fb.c
@@ -1122,7 +1122,7 @@ static void vga_8planes_imageblit(struct fb_info *info, const struct fb_image *i
         char oldop = setop(0);
         char oldsr = setsr(0);
         char oldmask = selectmask();
-        const char *cdat = image->data;
+	const unsigned char *cdat = image->data;
 	u32 dx = image->dx;
         char __iomem *where;
         int y;
diff --git a/drivers/video/fbdev/w100fb.c b/drivers/video/fbdev/w100fb.c
index d570e19a2864..ffda1d68fb05 100644
--- a/drivers/video/fbdev/w100fb.c
+++ b/drivers/video/fbdev/w100fb.c
@@ -583,6 +583,7 @@ static void w100fb_restore_vidmem(struct w100fb_par *par)
 		memsize=par->mach->mem->size;
 		memcpy_toio(remapped_fbuf + (W100_FB_BASE-MEM_WINDOW_BASE), par->saved_extmem, memsize);
 		vfree(par->saved_extmem);
+		par->saved_extmem = NULL;
 	}
 	if (par->saved_intmem) {
 		memsize=MEM_INT_SIZE;
@@ -591,6 +592,7 @@ static void w100fb_restore_vidmem(struct w100fb_par *par)
 		else
 			memcpy_toio(remapped_fbuf + (W100_FB_BASE-MEM_WINDOW_BASE), par->saved_intmem, memsize);
 		vfree(par->saved_intmem);
+		par->saved_intmem = NULL;
 	}
 }
 
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index b82bb0b08161..51278f8bd3ab 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -829,6 +829,9 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
+	if (unlikely(vq->broken))
+		return false;
+
 	virtio_mb(vq->weak_barriers);
 	return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
 }
diff --git a/drivers/w1/masters/omap_hdq.c b/drivers/w1/masters/omap_hdq.c
index 3099052e1243..0667bc6e7d23 100644
--- a/drivers/w1/masters/omap_hdq.c
+++ b/drivers/w1/masters/omap_hdq.c
@@ -176,7 +176,7 @@ static int hdq_write_byte(struct hdq_data *hdq_data, u8 val, u8 *status)
 	/* check irqstatus */
 	if (!(*status & OMAP_HDQ_INT_STATUS_TXCOMPLETE)) {
 		dev_dbg(hdq_data->dev, "timeout waiting for"
-			" TXCOMPLETE/RXCOMPLETE, %x", *status);
+			" TXCOMPLETE/RXCOMPLETE, %x\n", *status);
 		ret = -ETIMEDOUT;
 		goto out;
 	}
@@ -187,7 +187,7 @@ static int hdq_write_byte(struct hdq_data *hdq_data, u8 val, u8 *status)
 			OMAP_HDQ_FLAG_CLEAR, &tmp_status);
 	if (ret) {
 		dev_dbg(hdq_data->dev, "timeout waiting GO bit"
-			" return to zero, %x", tmp_status);
+			" return to zero, %x\n", tmp_status);
 	}
 
 out:
@@ -203,7 +203,7 @@ static irqreturn_t hdq_isr(int irq, void *_hdq)
 	spin_lock_irqsave(&hdq_data->hdq_spinlock, irqflags);
 	hdq_data->hdq_irqstatus = hdq_reg_in(hdq_data, OMAP_HDQ_INT_STATUS);
 	spin_unlock_irqrestore(&hdq_data->hdq_spinlock, irqflags);
-	dev_dbg(hdq_data->dev, "hdq_isr: %x", hdq_data->hdq_irqstatus);
+	dev_dbg(hdq_data->dev, "hdq_isr: %x\n", hdq_data->hdq_irqstatus);
 
 	if (hdq_data->hdq_irqstatus &
 		(OMAP_HDQ_INT_STATUS_TXCOMPLETE | OMAP_HDQ_INT_STATUS_RXCOMPLETE
@@ -311,7 +311,7 @@ static int omap_hdq_break(struct hdq_data *hdq_data)
 	tmp_status = hdq_data->hdq_irqstatus;
 	/* check irqstatus */
 	if (!(tmp_status & OMAP_HDQ_INT_STATUS_TIMEOUT)) {
-		dev_dbg(hdq_data->dev, "timeout waiting for TIMEOUT, %x",
+		dev_dbg(hdq_data->dev, "timeout waiting for TIMEOUT, %x\n",
 				tmp_status);
 		ret = -ETIMEDOUT;
 		goto out;
@@ -338,7 +338,7 @@ static int omap_hdq_break(struct hdq_data *hdq_data)
 			&tmp_status);
 	if (ret)
 		dev_dbg(hdq_data->dev, "timeout waiting INIT&GO bits"
-			" return to zero, %x", tmp_status);
+			" return to zero, %x\n", tmp_status);
 
 out:
 	mutex_unlock(&hdq_data->hdq_mutex);
diff --git a/drivers/watchdog/da9062_wdt.c b/drivers/watchdog/da9062_wdt.c
index 79383ff62019..1443386bb590 100644
--- a/drivers/watchdog/da9062_wdt.c
+++ b/drivers/watchdog/da9062_wdt.c
@@ -94,11 +94,6 @@ static int da9062_wdt_update_timeout_register(struct da9062_watchdog *wdt,
 					      unsigned int regval)
 {
 	struct da9062 *chip = wdt->hw;
-	int ret;
-
-	ret = da9062_reset_watchdog_timer(wdt);
-	if (ret)
-		return ret;
 
 	return regmap_update_bits(chip->regmap,
 				  DA9062AA_CONTROL_D,
diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c
index 88cd2a52d8d3..ae4974701e5c 100644
--- a/drivers/watchdog/f71808e_wdt.c
+++ b/drivers/watchdog/f71808e_wdt.c
@@ -688,9 +688,9 @@ static int __init watchdog_init(int sioaddr)
 	 * into the module have been registered yet.
 	 */
 	watchdog.sioaddr = sioaddr;
-	watchdog.ident.options = WDIOC_SETTIMEOUT
-				| WDIOF_MAGICCLOSE
-				| WDIOF_KEEPALIVEPING;
+	watchdog.ident.options = WDIOF_MAGICCLOSE
+				| WDIOF_KEEPALIVEPING
+				| WDIOF_CARDRESET;
 
 	snprintf(watchdog.ident.identity,
 		sizeof(watchdog.ident.identity), "%s watchdog",
@@ -704,6 +704,13 @@ static int __init watchdog_init(int sioaddr)
 	wdt_conf = superio_inb(sioaddr, F71808FG_REG_WDT_CONF);
 	watchdog.caused_reboot = wdt_conf & BIT(F71808FG_FLAG_WDTMOUT_STS);
 
+	/*
+	 * We don't want WDTMOUT_STS to stick around till regular reboot.
+	 * Write 1 to the bit to clear it to zero.
+	 */
+	superio_outb(sioaddr, F71808FG_REG_WDT_CONF,
+		     wdt_conf | BIT(F71808FG_FLAG_WDTMOUT_STS));
+
 	superio_exit(sioaddr);
 
 	err = watchdog_set_timeout(timeout);
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 3f9260af701f..a8e0836dffd4 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -633,11 +633,13 @@ static int add_ballooned_pages(int nr_pages)
 	if (xen_hotplug_unpopulated) {
 		st = reserve_additional_memory();
 		if (st != BP_ECANCELED) {
+			int rc;
+
 			mutex_unlock(&balloon_mutex);
-			wait_event(balloon_wq,
+			rc = wait_event_interruptible(balloon_wq,
 				   !list_empty(&ballooned_pages));
 			mutex_lock(&balloon_mutex);
-			return 0;
+			return rc ? -ENOMEM : 0;
 		}
 	}
 
@@ -695,6 +697,12 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages)
  out_undo:
 	mutex_unlock(&balloon_mutex);
 	free_xenballooned_pages(pgno, pages);
+	/*
+	 * NB: free_xenballooned_pages will only subtract pgno pages, but since
+	 * target_unpopulated is incremented with nr_pages at the start we need
+	 * to remove the remaining ones also, or accounting will be screwed.
+	 */
+	balloon_stats.target_unpopulated -= nr_pages - pgno;
 	return ret;
 }
 EXPORT_SYMBOL(alloc_xenballooned_pages);
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 8d49b91d92cd..95e5a9300ff0 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -154,7 +154,7 @@ int get_evtchn_to_irq(unsigned evtchn)
 /* Get info for IRQ */
 struct irq_info *info_for_irq(unsigned irq)
 {
-	return irq_get_handler_data(irq);
+	return irq_get_chip_data(irq);
 }
 
 /* Constructors for packed IRQ information. */
@@ -375,7 +375,7 @@ static void xen_irq_init(unsigned irq)
 	info->type = IRQT_UNBOUND;
 	info->refcnt = -1;
 
-	irq_set_handler_data(irq, info);
+	irq_set_chip_data(irq, info);
 
 	list_add_tail(&info->list, &xen_irq_list_head);
 }
@@ -424,14 +424,14 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi)
 
 static void xen_free_irq(unsigned irq)
 {
-	struct irq_info *info = irq_get_handler_data(irq);
+	struct irq_info *info = irq_get_chip_data(irq);
 
 	if (WARN_ON(!info))
 		return;
 
 	list_del(&info->list);
 
-	irq_set_handler_data(irq, NULL);
+	irq_set_chip_data(irq, NULL);
 
 	WARN_ON(info->refcnt > 0);
 
@@ -601,7 +601,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
 static void __unbind_from_irq(unsigned int irq)
 {
 	int evtchn = evtchn_from_irq(irq);
-	struct irq_info *info = irq_get_handler_data(irq);
+	struct irq_info *info = irq_get_chip_data(irq);
 
 	if (info->refcnt > 0) {
 		info->refcnt--;
@@ -1105,7 +1105,7 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
 
 void unbind_from_irqhandler(unsigned int irq, void *dev_id)
 {
-	struct irq_info *info = irq_get_handler_data(irq);
+	struct irq_info *info = irq_get_chip_data(irq);
 
 	if (WARN_ON(!info))
 		return;
@@ -1139,7 +1139,7 @@ int evtchn_make_refcounted(unsigned int evtchn)
 	if (irq == -1)
 		return -ENOENT;
 
-	info = irq_get_handler_data(irq);
+	info = irq_get_chip_data(irq);
 
 	if (!info)
 		return -ENOENT;
@@ -1167,7 +1167,7 @@ int evtchn_get(unsigned int evtchn)
 	if (irq == -1)
 		goto done;
 
-	info = irq_get_handler_data(irq);
+	info = irq_get_chip_data(irq);
 
 	if (!info)
 		goto done;
diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c
index 5f6b77ea34fb..128375ff80b8 100644
--- a/drivers/xen/preempt.c
+++ b/drivers/xen/preempt.c
@@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
 asmlinkage __visible void xen_maybe_preempt_hcall(void)
 {
 	if (unlikely(__this_cpu_read(xen_in_preemptible_hcall)
-		     && need_resched())) {
+		     && need_resched() && !preempt_count())) {
 		/*
 		 * Clear flag as we may be rescheduled on a different
 		 * cpu.
diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c
index 58be15c27b6d..62a0c4111dc4 100644
--- a/drivers/xen/pvcalls-back.c
+++ b/drivers/xen/pvcalls-back.c
@@ -1104,7 +1104,8 @@ static void set_backend_state(struct xenbus_device *dev,
 		case XenbusStateInitialised:
 			switch (state) {
 			case XenbusStateConnected:
-				backend_connect(dev);
+				if (backend_connect(dev))
+					return;
 				xenbus_switch_state(dev, XenbusStateConnected);
 				break;
 			case XenbusStateClosing:
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index e94a61eaeceb..f7b553faadb1 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -365,8 +365,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr,
 	int i, j;
 
 	for (i = 0; i < nr_pages; i++) {
-		err = gnttab_grant_foreign_access(dev->otherend_id,
-						  virt_to_gfn(vaddr), 0);
+		unsigned long gfn;
+
+		if (is_vmalloc_addr(vaddr))
+			gfn = pfn_to_gfn(vmalloc_to_pfn(vaddr));
+		else
+			gfn = virt_to_gfn(vaddr);
+
+		err = gnttab_grant_foreign_access(dev->otherend_id, gfn, 0);
 		if (err < 0) {
 			xenbus_dev_fatal(dev, err,
 					 "granting access to ring page");
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index c52f10efdc9c..b4dbe7b71151 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -513,10 +513,9 @@ void v9fs_session_close(struct v9fs_session_info *v9ses)
 	}
 
 #ifdef CONFIG_9P_FSCACHE
-	if (v9ses->fscache) {
+	if (v9ses->fscache)
 		v9fs_cache_session_put_cookie(v9ses);
-		kfree(v9ses->cachetag);
-	}
+	kfree(v9ses->cachetag);
 #endif
 	kfree(v9ses->uname);
 	kfree(v9ses->aname);
diff --git a/fs/Kconfig b/fs/Kconfig
index 7aee6d699fd6..07e22c243b42 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -232,6 +232,7 @@ source "fs/hfsplus/Kconfig"
 source "fs/befs/Kconfig"
 source "fs/bfs/Kconfig"
 source "fs/efs/Kconfig"
+source "fs/yaffs2/Kconfig"
 source "fs/jffs2/Kconfig"
 # UBIFS File system configuration
 source "fs/ubifs/Kconfig"
@@ -248,6 +249,7 @@ source "fs/pstore/Kconfig"
 source "fs/sysv/Kconfig"
 source "fs/ufs/Kconfig"
 source "fs/exofs/Kconfig"
+source "fs/aufs/Kconfig"
 
 endif # MISC_FILESYSTEMS
 
diff --git a/fs/Makefile b/fs/Makefile
index ef772f1eaff8..659904f398c7 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -129,3 +129,6 @@ obj-y				+= exofs/ # Multiple modules
 obj-$(CONFIG_CEPH_FS)		+= ceph/
 obj-$(CONFIG_PSTORE)		+= pstore/
 obj-$(CONFIG_EFIVAR_FS)		+= efivarfs/
+obj-$(CONFIG_YAFFS_FS)		+= yaffs2/
+obj-$(CONFIG_AUFS_FS)           += aufs/
+
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 185d5ab7e986..a80ce75b5bad 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -419,24 +419,51 @@ affs_mode_to_prot(struct inode *inode)
 	u32 prot = AFFS_I(inode)->i_protect;
 	umode_t mode = inode->i_mode;
 
+	/*
+	 * First, clear all RWED bits for owner, group, other.
+	 * Then, recalculate them afresh.
+	 *
+	 * We'll always clear the delete-inhibit bit for the owner, as that is
+	 * the classic single-user mode AmigaOS protection bit and we need to
+	 * stay compatible with all scenarios.
+	 *
+	 * Since multi-user AmigaOS is an extension, we'll only set the
+	 * delete-allow bit if any of the other bits in the same user class
+	 * (group/other) are used.
+	 */
+	prot &= ~(FIBF_NOEXECUTE | FIBF_NOREAD
+		  | FIBF_NOWRITE | FIBF_NODELETE
+		  | FIBF_GRP_EXECUTE | FIBF_GRP_READ
+		  | FIBF_GRP_WRITE   | FIBF_GRP_DELETE
+		  | FIBF_OTR_EXECUTE | FIBF_OTR_READ
+		  | FIBF_OTR_WRITE   | FIBF_OTR_DELETE);
+
+	/* Classic single-user AmigaOS flags. These are inverted. */
 	if (!(mode & 0100))
 		prot |= FIBF_NOEXECUTE;
 	if (!(mode & 0400))
 		prot |= FIBF_NOREAD;
 	if (!(mode & 0200))
 		prot |= FIBF_NOWRITE;
+
+	/* Multi-user extended flags. Not inverted. */
 	if (mode & 0010)
 		prot |= FIBF_GRP_EXECUTE;
 	if (mode & 0040)
 		prot |= FIBF_GRP_READ;
 	if (mode & 0020)
 		prot |= FIBF_GRP_WRITE;
+	if (mode & 0070)
+		prot |= FIBF_GRP_DELETE;
+
 	if (mode & 0001)
 		prot |= FIBF_OTR_EXECUTE;
 	if (mode & 0004)
 		prot |= FIBF_OTR_READ;
 	if (mode & 0002)
 		prot |= FIBF_OTR_WRITE;
+	if (mode & 0007)
+		prot |= FIBF_OTR_DELETE;
 
 	AFFS_I(inode)->i_protect = prot;
 }
diff --git a/fs/affs/file.c b/fs/affs/file.c
index a85817f54483..ba084b0b214b 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -428,6 +428,24 @@ static int affs_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
+static int affs_write_end(struct file *file, struct address_space *mapping,
+			  loff_t pos, unsigned int len, unsigned int copied,
+			  struct page *page, void *fsdata)
+{
+	struct inode *inode = mapping->host;
+	int ret;
+
+	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+	/* Clear Archived bit on file writes, as AmigaOS would do */
+	if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) {
+		AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED;
+		mark_inode_dirty(inode);
+	}
+
+	return ret;
+}
+
 static sector_t _affs_bmap(struct address_space *mapping, sector_t block)
 {
 	return generic_block_bmap(mapping,block,affs_get_block);
@@ -437,7 +455,7 @@ const struct address_space_operations affs_aops = {
 	.readpage = affs_readpage,
 	.writepage = affs_writepage,
 	.write_begin = affs_write_begin,
-	.write_end = generic_write_end,
+	.write_end = affs_write_end,
 	.direct_IO = affs_direct_IO,
 	.bmap = _affs_bmap
 };
@@ -794,6 +812,12 @@ done:
 	if (tmp > inode->i_size)
 		inode->i_size = AFFS_I(inode)->mmu_private = tmp;
 
+	/* Clear Archived bit on file writes, as AmigaOS would do */
+	if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) {
+		AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED;
+		mark_inode_dirty(inode);
+	}
+
 err_first_bh:
 	unlock_page(page);
 	put_page(page);
diff --git a/fs/aufs/Kconfig b/fs/aufs/Kconfig
new file mode 100644
index 000000000000..63560ceda3a4
--- /dev/null
+++ b/fs/aufs/Kconfig
@@ -0,0 +1,185 @@
+config AUFS_FS
+	tristate "Aufs (Advanced multi layered unification filesystem) support"
+	help
+	Aufs is a stackable unification filesystem such as Unionfs,
+	which unifies several directories and provides a merged single
+	directory.
+	In the early days, aufs was entirely re-designed and
+	re-implemented Unionfs Version 1.x series. Introducing many
+	original ideas, approaches and improvements, it becomes totally
+	different from Unionfs while keeping the basic features.
+
+if AUFS_FS
+choice
+	prompt "Maximum number of branches"
+	default AUFS_BRANCH_MAX_127
+	help
+	Specifies the maximum number of branches (or member directories)
+	in a single aufs. The larger value consumes more system
+	resources and has a minor impact to performance.
+config AUFS_BRANCH_MAX_127
+	bool "127"
+	help
+	Specifies the maximum number of branches (or member directories)
+	in a single aufs. The larger value consumes more system
+	resources and has a minor impact to performance.
+config AUFS_BRANCH_MAX_511
+	bool "511"
+	help
+	Specifies the maximum number of branches (or member directories)
+	in a single aufs. The larger value consumes more system
+	resources and has a minor impact to performance.
+config AUFS_BRANCH_MAX_1023
+	bool "1023"
+	help
+	Specifies the maximum number of branches (or member directories)
+	in a single aufs. The larger value consumes more system
+	resources and has a minor impact to performance.
+config AUFS_BRANCH_MAX_32767
+	bool "32767"
+	help
+	Specifies the maximum number of branches (or member directories)
+	in a single aufs. The larger value consumes more system
+	resources and has a minor impact to performance.
+endchoice
+
+config AUFS_SBILIST
+	bool
+	depends on AUFS_MAGIC_SYSRQ || PROC_FS
+	default y
+	help
+	Automatic configuration for internal use.
+	When aufs supports Magic SysRq or /proc, enabled automatically.
+
+config AUFS_HNOTIFY
+	bool "Detect direct branch access (bypassing aufs)"
+	help
+	If you want to modify files on branches directly, eg. bypassing aufs,
+	and want aufs to detect the changes of them fully, then enable this
+	option and use 'udba=notify' mount option.
+	Currently there is only one available configuration, "fsnotify".
+	It will have a negative impact to the performance.
+	See detail in aufs.5.
+
+choice
+	prompt "method" if AUFS_HNOTIFY
+	default AUFS_HFSNOTIFY
+config AUFS_HFSNOTIFY
+	bool "fsnotify"
+	select FSNOTIFY
+endchoice
+
+config AUFS_EXPORT
+	bool "NFS-exportable aufs"
+	depends on EXPORTFS
+	help
+	If you want to export your mounted aufs via NFS, then enable this
+	option. There are several requirements for this configuration.
+	See detail in aufs.5.
+
+config AUFS_INO_T_64
+	bool
+	depends on AUFS_EXPORT
+	depends on 64BIT && !(ALPHA || S390)
+	default y
+	help
+	Automatic configuration for internal use.
+	/* typedef unsigned long/int __kernel_ino_t */
+	/* alpha and s390x are int */
+
+config AUFS_XATTR
+	bool "support for XATTR/EA (including Security Labels)"
+	help
+	If your branch fs supports XATTR/EA and you want to make them
+	available in aufs too, then enable this opsion and specify the
+	branch attributes for EA.
+	See detail in aufs.5.
+
+config AUFS_FHSM
+	bool "File-based Hierarchical Storage Management"
+	help
+	Hierarchical Storage Management (or HSM) is a well-known feature
+	in the storage world. Aufs provides this feature as file-based.
+	with multiple branches.
+	These multiple branches are prioritized, ie. the topmost one
+	should be the fastest drive and be used heavily.
+
+config AUFS_RDU
+	bool "Readdir in userspace"
+	help
+	Aufs has two methods to provide a merged view for a directory,
+	by a user-space library and by kernel-space natively. The latter
+	is always enabled but sometimes large and slow.
+	If you enable this option, install the library in aufs2-util
+	package, and set some environment variables for your readdir(3),
+	then the work will be handled in user-space which generally
+	shows better performance in most cases.
+	See detail in aufs.5.
+
+config AUFS_SHWH
+	bool "Show whiteouts"
+	help
+	If you want to make the whiteouts in aufs visible, then enable
+	this option and specify 'shwh' mount option. Although it may
+	sounds like philosophy or something, but in technically it
+	simply shows the name of whiteout with keeping its behaviour.
+
+config AUFS_BR_RAMFS
+	bool "Ramfs (initramfs/rootfs) as an aufs branch"
+	help
+	If you want to use ramfs as an aufs branch fs, then enable this
+	option. Generally tmpfs is recommended.
+	Aufs prohibited them to be a branch fs by default, because
+	initramfs becomes unusable after switch_root or something
+	generally. If you sets initramfs as an aufs branch and boot your
+	system by switch_root, you will meet a problem easily since the
+	files in initramfs may be inaccessible.
+	Unless you are going to use ramfs as an aufs branch fs without
+	switch_root or something, leave it N.
+
+config AUFS_BR_FUSE
+	bool "Fuse fs as an aufs branch"
+	depends on FUSE_FS
+	select AUFS_POLL
+	help
+	If you want to use fuse-based userspace filesystem as an aufs
+	branch fs, then enable this option.
+	It implements the internal poll(2) operation which is
+	implemented by fuse only (curretnly).
+
+config AUFS_POLL
+	bool
+	help
+	Automatic configuration for internal use.
+
+config AUFS_BR_HFSPLUS
+	bool "Hfsplus as an aufs branch"
+	depends on HFSPLUS_FS
+	default y
+	help
+	If you want to use hfsplus fs as an aufs branch fs, then enable
+	this option. This option introduces a small overhead at
+	copying-up a file on hfsplus.
+
+config AUFS_BDEV_LOOP
+	bool
+	depends on BLK_DEV_LOOP
+	default y
+	help
+	Automatic configuration for internal use.
+	Convert =[ym] into =y.
+
+config AUFS_DEBUG
+	bool "Debug aufs"
+	help
+	Enable this to compile aufs internal debug code.
+	It will have a negative impact to the performance.
+
+config AUFS_MAGIC_SYSRQ
+	bool
+	depends on AUFS_DEBUG && MAGIC_SYSRQ
+	default y
+	help
+	Automatic configuration for internal use.
+	When aufs supports Magic SysRq, enabled automatically.
+endif
diff --git a/fs/aufs/Makefile b/fs/aufs/Makefile
new file mode 100644
index 000000000000..c7a501e3718e
--- /dev/null
+++ b/fs/aufs/Makefile
@@ -0,0 +1,44 @@
+
+include ${src}/magic.mk
+ifeq (${CONFIG_AUFS_FS},m)
+include ${src}/conf.mk
+endif
+-include ${src}/priv_def.mk
+
+# cf. include/linux/kernel.h
+# enable pr_debug
+ccflags-y += -DDEBUG
+# sparse requires the full pathname
+ifdef M
+ccflags-y += -include ${M}/../../include/uapi/linux/aufs_type.h
+else
+ccflags-y += -include ${srctree}/include/uapi/linux/aufs_type.h
+endif
+
+obj-$(CONFIG_AUFS_FS) += aufs.o
+aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o \
+	wkq.o vfsub.o dcsub.o \
+	cpup.o whout.o wbr_policy.o \
+	dinfo.o dentry.o \
+	dynop.o \
+	finfo.o file.o f_op.o \
+	dir.o vdir.o \
+	iinfo.o inode.o i_op.o i_op_add.o i_op_del.o i_op_ren.o \
+	mvdown.o ioctl.o
+
+# all are boolean
+aufs-$(CONFIG_PROC_FS) += procfs.o plink.o
+aufs-$(CONFIG_SYSFS) += sysfs.o
+aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o
+aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o
+aufs-$(CONFIG_AUFS_HNOTIFY) += hnotify.o
+aufs-$(CONFIG_AUFS_HFSNOTIFY) += hfsnotify.o
+aufs-$(CONFIG_AUFS_EXPORT) += export.o
+aufs-$(CONFIG_AUFS_XATTR) += xattr.o
+aufs-$(CONFIG_FS_POSIX_ACL) += posix_acl.o
+aufs-$(CONFIG_AUFS_FHSM) += fhsm.o
+aufs-$(CONFIG_AUFS_POLL) += poll.o
+aufs-$(CONFIG_AUFS_RDU) += rdu.o
+aufs-$(CONFIG_AUFS_BR_HFSPLUS) += hfsplus.o
+aufs-$(CONFIG_AUFS_DEBUG) += debug.o
+aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o
diff --git a/fs/aufs/aufs.h b/fs/aufs/aufs.h
new file mode 100644
index 000000000000..7f5eb7890bc0
--- /dev/null
+++ b/fs/aufs/aufs.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * all header files
+ */
+
+#ifndef __AUFS_H__
+#define __AUFS_H__
+
+#ifdef __KERNEL__
+
+#define AuStub(type, name, body, ...) \
+	static inline type name(__VA_ARGS__) { body; }
+
+#define AuStubVoid(name, ...) \
+	AuStub(void, name, , __VA_ARGS__)
+#define AuStubInt0(name, ...) \
+	AuStub(int, name, return 0, __VA_ARGS__)
+
+#include "debug.h"
+
+#include "branch.h"
+#include "cpup.h"
+#include "dcsub.h"
+#include "dbgaufs.h"
+#include "dentry.h"
+#include "dir.h"
+#include "dynop.h"
+#include "file.h"
+#include "fstype.h"
+#include "inode.h"
+#include "loop.h"
+#include "module.h"
+#include "opts.h"
+#include "rwsem.h"
+#include "spl.h"
+#include "super.h"
+#include "sysaufs.h"
+#include "vfsub.h"
+#include "whout.h"
+#include "wkq.h"
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_H__ */
diff --git a/fs/aufs/branch.c b/fs/aufs/branch.c
new file mode 100644
index 000000000000..70f0e86e09f1
--- /dev/null
+++ b/fs/aufs/branch.c
@@ -0,0 +1,1421 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * branch management
+ */
+
+#include <linux/compat.h>
+#include <linux/statfs.h>
+#include "aufs.h"
+
+/*
+ * free a single branch
+ */
+static void au_br_do_free(struct au_branch *br)
+{
+	int i;
+	struct au_wbr *wbr;
+	struct au_dykey **key;
+
+	au_hnotify_fin_br(br);
+
+	if (br->br_xino.xi_file)
+		fput(br->br_xino.xi_file);
+	for (i = br->br_xino.xi_nondir.total - 1; i >= 0; i--)
+		AuDebugOn(br->br_xino.xi_nondir.array[i]);
+	kfree(br->br_xino.xi_nondir.array);
+
+	AuDebugOn(au_br_count(br));
+	au_br_count_fin(br);
+
+	wbr = br->br_wbr;
+	if (wbr) {
+		for (i = 0; i < AuBrWh_Last; i++)
+			dput(wbr->wbr_wh[i]);
+		AuDebugOn(atomic_read(&wbr->wbr_wh_running));
+		AuRwDestroy(&wbr->wbr_wh_rwsem);
+	}
+
+	if (br->br_fhsm) {
+		au_br_fhsm_fin(br->br_fhsm);
+		kfree(br->br_fhsm);
+	}
+
+	key = br->br_dykey;
+	for (i = 0; i < AuBrDynOp; i++, key++)
+		if (*key)
+			au_dy_put(*key);
+		else
+			break;
+
+	/* recursive lock, s_umount of branch's */
+	lockdep_off();
+	path_put(&br->br_path);
+	lockdep_on();
+	kfree(wbr);
+	kfree(br);
+}
+
+/*
+ * frees all branches
+ */
+void au_br_free(struct au_sbinfo *sbinfo)
+{
+	aufs_bindex_t bmax;
+	struct au_branch **br;
+
+	AuRwMustWriteLock(&sbinfo->si_rwsem);
+
+	bmax = sbinfo->si_bbot + 1;
+	br = sbinfo->si_branch;
+	while (bmax--)
+		au_br_do_free(*br++);
+}
+
+/*
+ * find the index of a branch which is specified by @br_id.
+ */
+int au_br_index(struct super_block *sb, aufs_bindex_t br_id)
+{
+	aufs_bindex_t bindex, bbot;
+
+	bbot = au_sbbot(sb);
+	for (bindex = 0; bindex <= bbot; bindex++)
+		if (au_sbr_id(sb, bindex) == br_id)
+			return bindex;
+	return -1;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * add a branch
+ */
+
+static int test_overlap(struct super_block *sb, struct dentry *h_adding,
+			struct dentry *h_root)
+{
+	if (unlikely(h_adding == h_root
+		     || au_test_loopback_overlap(sb, h_adding)))
+		return 1;
+	if (h_adding->d_sb != h_root->d_sb)
+		return 0;
+	return au_test_subdir(h_adding, h_root)
+		|| au_test_subdir(h_root, h_adding);
+}
+
+/*
+ * returns a newly allocated branch. @new_nbranch is a number of branches
+ * after adding a branch.
+ */
+static struct au_branch *au_br_alloc(struct super_block *sb, int new_nbranch,
+				     int perm)
+{
+	struct au_branch *add_branch;
+	struct dentry *root;
+	struct inode *inode;
+	int err;
+
+	err = -ENOMEM;
+	add_branch = kzalloc(sizeof(*add_branch), GFP_NOFS);
+	if (unlikely(!add_branch))
+		goto out;
+	add_branch->br_xino.xi_nondir.total = 8; /* initial size */
+	add_branch->br_xino.xi_nondir.array
+		= kcalloc(sizeof(ino_t), add_branch->br_xino.xi_nondir.total,
+			  GFP_NOFS);
+	if (unlikely(!add_branch->br_xino.xi_nondir.array))
+		goto out_br;
+
+	err = au_hnotify_init_br(add_branch, perm);
+	if (unlikely(err))
+		goto out_xinondir;
+
+	if (au_br_writable(perm)) {
+		/* may be freed separately at changing the branch permission */
+		add_branch->br_wbr = kzalloc(sizeof(*add_branch->br_wbr),
+					     GFP_NOFS);
+		if (unlikely(!add_branch->br_wbr))
+			goto out_hnotify;
+	}
+
+	if (au_br_fhsm(perm)) {
+		err = au_fhsm_br_alloc(add_branch);
+		if (unlikely(err))
+			goto out_wbr;
+	}
+
+	root = sb->s_root;
+	err = au_sbr_realloc(au_sbi(sb), new_nbranch, /*may_shrink*/0);
+	if (!err)
+		err = au_di_realloc(au_di(root), new_nbranch, /*may_shrink*/0);
+	if (!err) {
+		inode = d_inode(root);
+		err = au_hinode_realloc(au_ii(inode), new_nbranch,
+					/*may_shrink*/0);
+	}
+	if (!err)
+		return add_branch; /* success */
+
+out_wbr:
+	kfree(add_branch->br_wbr);
+out_hnotify:
+	au_hnotify_fin_br(add_branch);
+out_xinondir:
+	kfree(add_branch->br_xino.xi_nondir.array);
+out_br:
+	kfree(add_branch);
+out:
+	return ERR_PTR(err);
+}
+
+/*
+ * test if the branch permission is legal or not.
+ */
+static int test_br(struct inode *inode, int brperm, char *path)
+{
+	int err;
+
+	err = (au_br_writable(brperm) && IS_RDONLY(inode));
+	if (!err)
+		goto out;
+
+	err = -EINVAL;
+	pr_err("write permission for readonly mount or inode, %s\n", path);
+
+out:
+	return err;
+}
+
+/*
+ * returns:
+ * 0: success, the caller will add it
+ * plus: success, it is already unified, the caller should ignore it
+ * minus: error
+ */
+static int test_add(struct super_block *sb, struct au_opt_add *add, int remount)
+{
+	int err;
+	aufs_bindex_t bbot, bindex;
+	struct dentry *root, *h_dentry;
+	struct inode *inode, *h_inode;
+
+	root = sb->s_root;
+	bbot = au_sbbot(sb);
+	if (unlikely(bbot >= 0
+		     && au_find_dbindex(root, add->path.dentry) >= 0)) {
+		err = 1;
+		if (!remount) {
+			err = -EINVAL;
+			pr_err("%s duplicated\n", add->pathname);
+		}
+		goto out;
+	}
+
+	err = -ENOSPC; /* -E2BIG; */
+	if (unlikely(AUFS_BRANCH_MAX <= add->bindex
+		     || AUFS_BRANCH_MAX - 1 <= bbot)) {
+		pr_err("number of branches exceeded %s\n", add->pathname);
+		goto out;
+	}
+
+	err = -EDOM;
+	if (unlikely(add->bindex < 0 || bbot + 1 < add->bindex)) {
+		pr_err("bad index %d\n", add->bindex);
+		goto out;
+	}
+
+	inode = d_inode(add->path.dentry);
+	err = -ENOENT;
+	if (unlikely(!inode->i_nlink)) {
+		pr_err("no existence %s\n", add->pathname);
+		goto out;
+	}
+
+	err = -EINVAL;
+	if (unlikely(inode->i_sb == sb)) {
+		pr_err("%s must be outside\n", add->pathname);
+		goto out;
+	}
+
+	if (unlikely(au_test_fs_unsuppoted(inode->i_sb))) {
+		pr_err("unsupported filesystem, %s (%s)\n",
+		       add->pathname, au_sbtype(inode->i_sb));
+		goto out;
+	}
+
+	if (unlikely(inode->i_sb->s_stack_depth)) {
+		pr_err("already stacked, %s (%s)\n",
+		       add->pathname, au_sbtype(inode->i_sb));
+		goto out;
+	}
+
+	err = test_br(d_inode(add->path.dentry), add->perm, add->pathname);
+	if (unlikely(err))
+		goto out;
+
+	if (bbot < 0)
+		return 0; /* success */
+
+	err = -EINVAL;
+	for (bindex = 0; bindex <= bbot; bindex++)
+		if (unlikely(test_overlap(sb, add->path.dentry,
+					  au_h_dptr(root, bindex)))) {
+			pr_err("%s is overlapped\n", add->pathname);
+			goto out;
+		}
+
+	err = 0;
+	if (au_opt_test(au_mntflags(sb), WARN_PERM)) {
+		h_dentry = au_h_dptr(root, 0);
+		h_inode = d_inode(h_dentry);
+		if ((h_inode->i_mode & S_IALLUGO) != (inode->i_mode & S_IALLUGO)
+		    || !uid_eq(h_inode->i_uid, inode->i_uid)
+		    || !gid_eq(h_inode->i_gid, inode->i_gid))
+			pr_warn("uid/gid/perm %s %u/%u/0%o, %u/%u/0%o\n",
+				add->pathname,
+				i_uid_read(inode), i_gid_read(inode),
+				(inode->i_mode & S_IALLUGO),
+				i_uid_read(h_inode), i_gid_read(h_inode),
+				(h_inode->i_mode & S_IALLUGO));
+	}
+
+out:
+	return err;
+}
+
+/*
+ * initialize or clean the whiteouts for an adding branch
+ */
+static int au_br_init_wh(struct super_block *sb, struct au_branch *br,
+			 int new_perm)
+{
+	int err, old_perm;
+	aufs_bindex_t bindex;
+	struct inode *h_inode;
+	struct au_wbr *wbr;
+	struct au_hinode *hdir;
+	struct dentry *h_dentry;
+
+	err = vfsub_mnt_want_write(au_br_mnt(br));
+	if (unlikely(err))
+		goto out;
+
+	wbr = br->br_wbr;
+	old_perm = br->br_perm;
+	br->br_perm = new_perm;
+	hdir = NULL;
+	h_inode = NULL;
+	bindex = au_br_index(sb, br->br_id);
+	if (0 <= bindex) {
+		hdir = au_hi(d_inode(sb->s_root), bindex);
+		au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT);
+	} else {
+		h_dentry = au_br_dentry(br);
+		h_inode = d_inode(h_dentry);
+		inode_lock_nested(h_inode, AuLsc_I_PARENT);
+	}
+	if (!wbr)
+		err = au_wh_init(br, sb);
+	else {
+		wbr_wh_write_lock(wbr);
+		err = au_wh_init(br, sb);
+		wbr_wh_write_unlock(wbr);
+	}
+	if (hdir)
+		au_hn_inode_unlock(hdir);
+	else
+		inode_unlock(h_inode);
+	vfsub_mnt_drop_write(au_br_mnt(br));
+	br->br_perm = old_perm;
+
+	if (!err && wbr && !au_br_writable(new_perm)) {
+		kfree(wbr);
+		br->br_wbr = NULL;
+	}
+
+out:
+	return err;
+}
+
+static int au_wbr_init(struct au_branch *br, struct super_block *sb,
+		       int perm)
+{
+	int err;
+	struct kstatfs kst;
+	struct au_wbr *wbr;
+
+	wbr = br->br_wbr;
+	au_rw_init(&wbr->wbr_wh_rwsem);
+	atomic_set(&wbr->wbr_wh_running, 0);
+
+	/*
+	 * a limit for rmdir/rename a dir
+	 * cf. AUFS_MAX_NAMELEN in include/uapi/linux/aufs_type.h
+	 */
+	err = vfs_statfs(&br->br_path, &kst);
+	if (unlikely(err))
+		goto out;
+	err = -EINVAL;
+	if (kst.f_namelen >= NAME_MAX)
+		err = au_br_init_wh(sb, br, perm);
+	else
+		pr_err("%pd(%s), unsupported namelen %ld\n",
+		       au_br_dentry(br),
+		       au_sbtype(au_br_dentry(br)->d_sb), kst.f_namelen);
+
+out:
+	return err;
+}
+
+/* initialize a new branch */
+static int au_br_init(struct au_branch *br, struct super_block *sb,
+		      struct au_opt_add *add)
+{
+	int err;
+	struct inode *h_inode;
+
+	err = 0;
+	spin_lock_init(&br->br_xino.xi_nondir.spin);
+	init_waitqueue_head(&br->br_xino.xi_nondir.wqh);
+	br->br_perm = add->perm;
+	br->br_path = add->path; /* set first, path_get() later */
+	spin_lock_init(&br->br_dykey_lock);
+	au_br_count_init(br);
+	atomic_set(&br->br_xino_running, 0);
+	br->br_id = au_new_br_id(sb);
+	AuDebugOn(br->br_id < 0);
+
+	if (au_br_writable(add->perm)) {
+		err = au_wbr_init(br, sb, add->perm);
+		if (unlikely(err))
+			goto out_err;
+	}
+
+	if (au_opt_test(au_mntflags(sb), XINO)) {
+		h_inode = d_inode(add->path.dentry);
+		err = au_xino_br(sb, br, h_inode->i_ino,
+				 au_sbr(sb, 0)->br_xino.xi_file, /*do_test*/1);
+		if (unlikely(err)) {
+			AuDebugOn(br->br_xino.xi_file);
+			goto out_err;
+		}
+	}
+
+	sysaufs_br_init(br);
+	path_get(&br->br_path);
+	goto out; /* success */
+
+out_err:
+	memset(&br->br_path, 0, sizeof(br->br_path));
+out:
+	return err;
+}
+
+static void au_br_do_add_brp(struct au_sbinfo *sbinfo, aufs_bindex_t bindex,
+			     struct au_branch *br, aufs_bindex_t bbot,
+			     aufs_bindex_t amount)
+{
+	struct au_branch **brp;
+
+	AuRwMustWriteLock(&sbinfo->si_rwsem);
+
+	brp = sbinfo->si_branch + bindex;
+	memmove(brp + 1, brp, sizeof(*brp) * amount);
+	*brp = br;
+	sbinfo->si_bbot++;
+	if (unlikely(bbot < 0))
+		sbinfo->si_bbot = 0;
+}
+
+static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex,
+			     aufs_bindex_t bbot, aufs_bindex_t amount)
+{
+	struct au_hdentry *hdp;
+
+	AuRwMustWriteLock(&dinfo->di_rwsem);
+
+	hdp = au_hdentry(dinfo, bindex);
+	memmove(hdp + 1, hdp, sizeof(*hdp) * amount);
+	au_h_dentry_init(hdp);
+	dinfo->di_bbot++;
+	if (unlikely(bbot < 0))
+		dinfo->di_btop = 0;
+}
+
+static void au_br_do_add_hip(struct au_iinfo *iinfo, aufs_bindex_t bindex,
+			     aufs_bindex_t bbot, aufs_bindex_t amount)
+{
+	struct au_hinode *hip;
+
+	AuRwMustWriteLock(&iinfo->ii_rwsem);
+
+	hip = au_hinode(iinfo, bindex);
+	memmove(hip + 1, hip, sizeof(*hip) * amount);
+	au_hinode_init(hip);
+	iinfo->ii_bbot++;
+	if (unlikely(bbot < 0))
+		iinfo->ii_btop = 0;
+}
+
+static void au_br_do_add(struct super_block *sb, struct au_branch *br,
+			 aufs_bindex_t bindex)
+{
+	struct dentry *root, *h_dentry;
+	struct inode *root_inode, *h_inode;
+	aufs_bindex_t bbot, amount;
+
+	root = sb->s_root;
+	root_inode = d_inode(root);
+	bbot = au_sbbot(sb);
+	amount = bbot + 1 - bindex;
+	h_dentry = au_br_dentry(br);
+	au_sbilist_lock();
+	au_br_do_add_brp(au_sbi(sb), bindex, br, bbot, amount);
+	au_br_do_add_hdp(au_di(root), bindex, bbot, amount);
+	au_br_do_add_hip(au_ii(root_inode), bindex, bbot, amount);
+	au_set_h_dptr(root, bindex, dget(h_dentry));
+	h_inode = d_inode(h_dentry);
+	au_set_h_iptr(root_inode, bindex, au_igrab(h_inode), /*flags*/0);
+	au_sbilist_unlock();
+}
+
+int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount)
+{
+	int err;
+	aufs_bindex_t bbot, add_bindex;
+	struct dentry *root, *h_dentry;
+	struct inode *root_inode;
+	struct au_branch *add_branch;
+
+	root = sb->s_root;
+	root_inode = d_inode(root);
+	IMustLock(root_inode);
+	IiMustWriteLock(root_inode);
+	err = test_add(sb, add, remount);
+	if (unlikely(err < 0))
+		goto out;
+	if (err) {
+		err = 0;
+		goto out; /* success */
+	}
+
+	bbot = au_sbbot(sb);
+	add_branch = au_br_alloc(sb, bbot + 2, add->perm);
+	err = PTR_ERR(add_branch);
+	if (IS_ERR(add_branch))
+		goto out;
+
+	err = au_br_init(add_branch, sb, add);
+	if (unlikely(err)) {
+		au_br_do_free(add_branch);
+		goto out;
+	}
+
+	add_bindex = add->bindex;
+	if (!remount)
+		au_br_do_add(sb, add_branch, add_bindex);
+	else {
+		sysaufs_brs_del(sb, add_bindex);
+		au_br_do_add(sb, add_branch, add_bindex);
+		sysaufs_brs_add(sb, add_bindex);
+	}
+
+	h_dentry = add->path.dentry;
+	if (!add_bindex) {
+		au_cpup_attr_all(root_inode, /*force*/1);
+		sb->s_maxbytes = h_dentry->d_sb->s_maxbytes;
+	} else
+		au_add_nlink(root_inode, d_inode(h_dentry));
+
+	/*
+	 * this test/set prevents aufs from handling unnecesary notify events
+	 * of xino files, in case of re-adding a writable branch which was
+	 * once detached from aufs.
+	 */
+	if (au_xino_brid(sb) < 0
+	    && au_br_writable(add_branch->br_perm)
+	    && !au_test_fs_bad_xino(h_dentry->d_sb)
+	    && add_branch->br_xino.xi_file
+	    && add_branch->br_xino.xi_file->f_path.dentry->d_parent == h_dentry)
+		au_xino_brid_set(sb, add_branch->br_id);
+
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static unsigned long long au_farray_cb(struct super_block *sb, void *a,
+				       unsigned long long max __maybe_unused,
+				       void *arg)
+{
+	unsigned long long n;
+	struct file **p, *f;
+	struct au_sphlhead *files;
+	struct au_finfo *finfo;
+
+	n = 0;
+	p = a;
+	files = &au_sbi(sb)->si_files;
+	spin_lock(&files->spin);
+	hlist_for_each_entry(finfo, &files->head, fi_hlist) {
+		f = finfo->fi_file;
+		if (file_count(f)
+		    && !special_file(file_inode(f)->i_mode)) {
+			get_file(f);
+			*p++ = f;
+			n++;
+			AuDebugOn(n > max);
+		}
+	}
+	spin_unlock(&files->spin);
+
+	return n;
+}
+
+static struct file **au_farray_alloc(struct super_block *sb,
+				     unsigned long long *max)
+{
+	*max = au_nfiles(sb);
+	return au_array_alloc(max, au_farray_cb, sb, /*arg*/NULL);
+}
+
+static void au_farray_free(struct file **a, unsigned long long max)
+{
+	unsigned long long ull;
+
+	for (ull = 0; ull < max; ull++)
+		if (a[ull])
+			fput(a[ull]);
+	kvfree(a);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * delete a branch
+ */
+
+/* to show the line number, do not make it inlined function */
+#define AuVerbose(do_info, fmt, ...) do { \
+	if (do_info) \
+		pr_info(fmt, ##__VA_ARGS__); \
+} while (0)
+
+static int au_test_ibusy(struct inode *inode, aufs_bindex_t btop,
+			 aufs_bindex_t bbot)
+{
+	return (inode && !S_ISDIR(inode->i_mode)) || btop == bbot;
+}
+
+static int au_test_dbusy(struct dentry *dentry, aufs_bindex_t btop,
+			 aufs_bindex_t bbot)
+{
+	return au_test_ibusy(d_inode(dentry), btop, bbot);
+}
+
+/*
+ * test if the branch is deletable or not.
+ */
+static int test_dentry_busy(struct dentry *root, aufs_bindex_t bindex,
+			    unsigned int sigen, const unsigned int verbose)
+{
+	int err, i, j, ndentry;
+	aufs_bindex_t btop, bbot;
+	struct au_dcsub_pages dpages;
+	struct au_dpage *dpage;
+	struct dentry *d;
+
+	err = au_dpages_init(&dpages, GFP_NOFS);
+	if (unlikely(err))
+		goto out;
+	err = au_dcsub_pages(&dpages, root, NULL, NULL);
+	if (unlikely(err))
+		goto out_dpages;
+
+	for (i = 0; !err && i < dpages.ndpage; i++) {
+		dpage = dpages.dpages + i;
+		ndentry = dpage->ndentry;
+		for (j = 0; !err && j < ndentry; j++) {
+			d = dpage->dentries[j];
+			AuDebugOn(au_dcount(d) <= 0);
+			if (!au_digen_test(d, sigen)) {
+				di_read_lock_child(d, AuLock_IR);
+				if (unlikely(au_dbrange_test(d))) {
+					di_read_unlock(d, AuLock_IR);
+					continue;
+				}
+			} else {
+				di_write_lock_child(d);
+				if (unlikely(au_dbrange_test(d))) {
+					di_write_unlock(d);
+					continue;
+				}
+				err = au_reval_dpath(d, sigen);
+				if (!err)
+					di_downgrade_lock(d, AuLock_IR);
+				else {
+					di_write_unlock(d);
+					break;
+				}
+			}
+
+			/* AuDbgDentry(d); */
+			btop = au_dbtop(d);
+			bbot = au_dbbot(d);
+			if (btop <= bindex
+			    && bindex <= bbot
+			    && au_h_dptr(d, bindex)
+			    && au_test_dbusy(d, btop, bbot)) {
+				err = -EBUSY;
+				AuVerbose(verbose, "busy %pd\n", d);
+				AuDbgDentry(d);
+			}
+			di_read_unlock(d, AuLock_IR);
+		}
+	}
+
+out_dpages:
+	au_dpages_free(&dpages);
+out:
+	return err;
+}
+
+static int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex,
+			   unsigned int sigen, const unsigned int verbose)
+{
+	int err;
+	unsigned long long max, ull;
+	struct inode *i, **array;
+	aufs_bindex_t btop, bbot;
+
+	array = au_iarray_alloc(sb, &max);
+	err = PTR_ERR(array);
+	if (IS_ERR(array))
+		goto out;
+
+	err = 0;
+	AuDbg("b%d\n", bindex);
+	for (ull = 0; !err && ull < max; ull++) {
+		i = array[ull];
+		if (unlikely(!i))
+			break;
+		if (i->i_ino == AUFS_ROOT_INO)
+			continue;
+
+		/* AuDbgInode(i); */
+		if (au_iigen(i, NULL) == sigen)
+			ii_read_lock_child(i);
+		else {
+			ii_write_lock_child(i);
+			err = au_refresh_hinode_self(i);
+			au_iigen_dec(i);
+			if (!err)
+				ii_downgrade_lock(i);
+			else {
+				ii_write_unlock(i);
+				break;
+			}
+		}
+
+		btop = au_ibtop(i);
+		bbot = au_ibbot(i);
+		if (btop <= bindex
+		    && bindex <= bbot
+		    && au_h_iptr(i, bindex)
+		    && au_test_ibusy(i, btop, bbot)) {
+			err = -EBUSY;
+			AuVerbose(verbose, "busy i%lu\n", i->i_ino);
+			AuDbgInode(i);
+		}
+		ii_read_unlock(i);
+	}
+	au_iarray_free(array, max);
+
+out:
+	return err;
+}
+
+static int test_children_busy(struct dentry *root, aufs_bindex_t bindex,
+			      const unsigned int verbose)
+{
+	int err;
+	unsigned int sigen;
+
+	sigen = au_sigen(root->d_sb);
+	DiMustNoWaiters(root);
+	IiMustNoWaiters(d_inode(root));
+	di_write_unlock(root);
+	err = test_dentry_busy(root, bindex, sigen, verbose);
+	if (!err)
+		err = test_inode_busy(root->d_sb, bindex, sigen, verbose);
+	di_write_lock_child(root); /* aufs_write_lock() calls ..._child() */
+
+	return err;
+}
+
+static int test_dir_busy(struct file *file, aufs_bindex_t br_id,
+			 struct file **to_free, int *idx)
+{
+	int err;
+	unsigned char matched, root;
+	aufs_bindex_t bindex, bbot;
+	struct au_fidir *fidir;
+	struct au_hfile *hfile;
+
+	err = 0;
+	root = IS_ROOT(file->f_path.dentry);
+	if (root) {
+		get_file(file);
+		to_free[*idx] = file;
+		(*idx)++;
+		goto out;
+	}
+
+	matched = 0;
+	fidir = au_fi(file)->fi_hdir;
+	AuDebugOn(!fidir);
+	bbot = au_fbbot_dir(file);
+	for (bindex = au_fbtop(file); bindex <= bbot; bindex++) {
+		hfile = fidir->fd_hfile + bindex;
+		if (!hfile->hf_file)
+			continue;
+
+		if (hfile->hf_br->br_id == br_id) {
+			matched = 1;
+			break;
+		}
+	}
+	if (matched)
+		err = -EBUSY;
+
+out:
+	return err;
+}
+
+static int test_file_busy(struct super_block *sb, aufs_bindex_t br_id,
+			  struct file **to_free, int opened)
+{
+	int err, idx;
+	unsigned long long ull, max;
+	aufs_bindex_t btop;
+	struct file *file, **array;
+	struct dentry *root;
+	struct au_hfile *hfile;
+
+	array = au_farray_alloc(sb, &max);
+	err = PTR_ERR(array);
+	if (IS_ERR(array))
+		goto out;
+
+	err = 0;
+	idx = 0;
+	root = sb->s_root;
+	di_write_unlock(root);
+	for (ull = 0; ull < max; ull++) {
+		file = array[ull];
+		if (unlikely(!file))
+			break;
+
+		/* AuDbg("%pD\n", file); */
+		fi_read_lock(file);
+		btop = au_fbtop(file);
+		if (!d_is_dir(file->f_path.dentry)) {
+			hfile = &au_fi(file)->fi_htop;
+			if (hfile->hf_br->br_id == br_id)
+				err = -EBUSY;
+		} else
+			err = test_dir_busy(file, br_id, to_free, &idx);
+		fi_read_unlock(file);
+		if (unlikely(err))
+			break;
+	}
+	di_write_lock_child(root);
+	au_farray_free(array, max);
+	AuDebugOn(idx > opened);
+
+out:
+	return err;
+}
+
+static void br_del_file(struct file **to_free, unsigned long long opened,
+			  aufs_bindex_t br_id)
+{
+	unsigned long long ull;
+	aufs_bindex_t bindex, btop, bbot, bfound;
+	struct file *file;
+	struct au_fidir *fidir;
+	struct au_hfile *hfile;
+
+	for (ull = 0; ull < opened; ull++) {
+		file = to_free[ull];
+		if (unlikely(!file))
+			break;
+
+		/* AuDbg("%pD\n", file); */
+		AuDebugOn(!d_is_dir(file->f_path.dentry));
+		bfound = -1;
+		fidir = au_fi(file)->fi_hdir;
+		AuDebugOn(!fidir);
+		fi_write_lock(file);
+		btop = au_fbtop(file);
+		bbot = au_fbbot_dir(file);
+		for (bindex = btop; bindex <= bbot; bindex++) {
+			hfile = fidir->fd_hfile + bindex;
+			if (!hfile->hf_file)
+				continue;
+
+			if (hfile->hf_br->br_id == br_id) {
+				bfound = bindex;
+				break;
+			}
+		}
+		AuDebugOn(bfound < 0);
+		au_set_h_fptr(file, bfound, NULL);
+		if (bfound == btop) {
+			for (btop++; btop <= bbot; btop++)
+				if (au_hf_dir(file, btop)) {
+					au_set_fbtop(file, btop);
+					break;
+				}
+		}
+		fi_write_unlock(file);
+	}
+}
+
+static void au_br_do_del_brp(struct au_sbinfo *sbinfo,
+			     const aufs_bindex_t bindex,
+			     const aufs_bindex_t bbot)
+{
+	struct au_branch **brp, **p;
+
+	AuRwMustWriteLock(&sbinfo->si_rwsem);
+
+	brp = sbinfo->si_branch + bindex;
+	if (bindex < bbot)
+		memmove(brp, brp + 1, sizeof(*brp) * (bbot - bindex));
+	sbinfo->si_branch[0 + bbot] = NULL;
+	sbinfo->si_bbot--;
+
+	p = au_krealloc(sbinfo->si_branch, sizeof(*p) * bbot, AuGFP_SBILIST,
+			/*may_shrink*/1);
+	if (p)
+		sbinfo->si_branch = p;
+	/* harmless error */
+}
+
+static void au_br_do_del_hdp(struct au_dinfo *dinfo, const aufs_bindex_t bindex,
+			     const aufs_bindex_t bbot)
+{
+	struct au_hdentry *hdp, *p;
+
+	AuRwMustWriteLock(&dinfo->di_rwsem);
+
+	hdp = au_hdentry(dinfo, bindex);
+	if (bindex < bbot)
+		memmove(hdp, hdp + 1, sizeof(*hdp) * (bbot - bindex));
+	/* au_h_dentry_init(au_hdentry(dinfo, bbot); */
+	dinfo->di_bbot--;
+
+	p = au_krealloc(dinfo->di_hdentry, sizeof(*p) * bbot, AuGFP_SBILIST,
+			/*may_shrink*/1);
+	if (p)
+		dinfo->di_hdentry = p;
+	/* harmless error */
+}
+
+static void au_br_do_del_hip(struct au_iinfo *iinfo, const aufs_bindex_t bindex,
+			     const aufs_bindex_t bbot)
+{
+	struct au_hinode *hip, *p;
+
+	AuRwMustWriteLock(&iinfo->ii_rwsem);
+
+	hip = au_hinode(iinfo, bindex);
+	if (bindex < bbot)
+		memmove(hip, hip + 1, sizeof(*hip) * (bbot - bindex));
+	/* au_hinode_init(au_hinode(iinfo, bbot)); */
+	iinfo->ii_bbot--;
+
+	p = au_krealloc(iinfo->ii_hinode, sizeof(*p) * bbot, AuGFP_SBILIST,
+			/*may_shrink*/1);
+	if (p)
+		iinfo->ii_hinode = p;
+	/* harmless error */
+}
+
+static void au_br_do_del(struct super_block *sb, aufs_bindex_t bindex,
+			 struct au_branch *br)
+{
+	aufs_bindex_t bbot;
+	struct au_sbinfo *sbinfo;
+	struct dentry *root, *h_root;
+	struct inode *inode, *h_inode;
+	struct au_hinode *hinode;
+
+	SiMustWriteLock(sb);
+
+	root = sb->s_root;
+	inode = d_inode(root);
+	sbinfo = au_sbi(sb);
+	bbot = sbinfo->si_bbot;
+
+	h_root = au_h_dptr(root, bindex);
+	hinode = au_hi(inode, bindex);
+	h_inode = au_igrab(hinode->hi_inode);
+	au_hiput(hinode);
+
+	au_sbilist_lock();
+	au_br_do_del_brp(sbinfo, bindex, bbot);
+	au_br_do_del_hdp(au_di(root), bindex, bbot);
+	au_br_do_del_hip(au_ii(inode), bindex, bbot);
+	au_sbilist_unlock();
+
+	dput(h_root);
+	iput(h_inode);
+	au_br_do_free(br);
+}
+
+static unsigned long long empty_cb(struct super_block *sb, void *array,
+				   unsigned long long max, void *arg)
+{
+	return max;
+}
+
+int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount)
+{
+	int err, rerr, i;
+	unsigned long long opened;
+	unsigned int mnt_flags;
+	aufs_bindex_t bindex, bbot, br_id;
+	unsigned char do_wh, verbose;
+	struct au_branch *br;
+	struct au_wbr *wbr;
+	struct dentry *root;
+	struct file **to_free;
+
+	err = 0;
+	opened = 0;
+	to_free = NULL;
+	root = sb->s_root;
+	bindex = au_find_dbindex(root, del->h_path.dentry);
+	if (bindex < 0) {
+		if (remount)
+			goto out; /* success */
+		err = -ENOENT;
+		pr_err("%s no such branch\n", del->pathname);
+		goto out;
+	}
+	AuDbg("bindex b%d\n", bindex);
+
+	err = -EBUSY;
+	mnt_flags = au_mntflags(sb);
+	verbose = !!au_opt_test(mnt_flags, VERBOSE);
+	bbot = au_sbbot(sb);
+	if (unlikely(!bbot)) {
+		AuVerbose(verbose, "no more branches left\n");
+		goto out;
+	}
+	br = au_sbr(sb, bindex);
+	AuDebugOn(!path_equal(&br->br_path, &del->h_path));
+
+	br_id = br->br_id;
+	opened = au_br_count(br);
+	if (unlikely(opened)) {
+		to_free = au_array_alloc(&opened, empty_cb, sb, NULL);
+		err = PTR_ERR(to_free);
+		if (IS_ERR(to_free))
+			goto out;
+
+		err = test_file_busy(sb, br_id, to_free, opened);
+		if (unlikely(err)) {
+			AuVerbose(verbose, "%llu file(s) opened\n", opened);
+			goto out;
+		}
+	}
+
+	wbr = br->br_wbr;
+	do_wh = wbr && (wbr->wbr_whbase || wbr->wbr_plink || wbr->wbr_orph);
+	if (do_wh) {
+		/* instead of WbrWhMustWriteLock(wbr) */
+		SiMustWriteLock(sb);
+		for (i = 0; i < AuBrWh_Last; i++) {
+			dput(wbr->wbr_wh[i]);
+			wbr->wbr_wh[i] = NULL;
+		}
+	}
+
+	err = test_children_busy(root, bindex, verbose);
+	if (unlikely(err)) {
+		if (do_wh)
+			goto out_wh;
+		goto out;
+	}
+
+	err = 0;
+	if (to_free) {
+		/*
+		 * now we confirmed the branch is deletable.
+		 * let's free the remaining opened dirs on the branch.
+		 */
+		di_write_unlock(root);
+		br_del_file(to_free, opened, br_id);
+		di_write_lock_child(root);
+	}
+
+	if (!remount)
+		au_br_do_del(sb, bindex, br);
+	else {
+		sysaufs_brs_del(sb, bindex);
+		au_br_do_del(sb, bindex, br);
+		sysaufs_brs_add(sb, bindex);
+	}
+
+	if (!bindex) {
+		au_cpup_attr_all(d_inode(root), /*force*/1);
+		sb->s_maxbytes = au_sbr_sb(sb, 0)->s_maxbytes;
+	} else
+		au_sub_nlink(d_inode(root), d_inode(del->h_path.dentry));
+	if (au_opt_test(mnt_flags, PLINK))
+		au_plink_half_refresh(sb, br_id);
+
+	if (au_xino_brid(sb) == br_id)
+		au_xino_brid_set(sb, -1);
+	goto out; /* success */
+
+out_wh:
+	/* revert */
+	rerr = au_br_init_wh(sb, br, br->br_perm);
+	if (rerr)
+		pr_warn("failed re-creating base whiteout, %s. (%d)\n",
+			del->pathname, rerr);
+out:
+	if (to_free)
+		au_farray_free(to_free, opened);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_ibusy(struct super_block *sb, struct aufs_ibusy __user *arg)
+{
+	int err;
+	aufs_bindex_t btop, bbot;
+	struct aufs_ibusy ibusy;
+	struct inode *inode, *h_inode;
+
+	err = -EPERM;
+	if (unlikely(!capable(CAP_SYS_ADMIN)))
+		goto out;
+
+	err = copy_from_user(&ibusy, arg, sizeof(ibusy));
+	if (!err)
+		err = !access_ok(VERIFY_WRITE, &arg->h_ino, sizeof(arg->h_ino));
+	if (unlikely(err)) {
+		err = -EFAULT;
+		AuTraceErr(err);
+		goto out;
+	}
+
+	err = -EINVAL;
+	si_read_lock(sb, AuLock_FLUSH);
+	if (unlikely(ibusy.bindex < 0 || ibusy.bindex > au_sbbot(sb)))
+		goto out_unlock;
+
+	err = 0;
+	ibusy.h_ino = 0; /* invalid */
+	inode = ilookup(sb, ibusy.ino);
+	if (!inode
+	    || inode->i_ino == AUFS_ROOT_INO
+	    || au_is_bad_inode(inode))
+		goto out_unlock;
+
+	ii_read_lock_child(inode);
+	btop = au_ibtop(inode);
+	bbot = au_ibbot(inode);
+	if (btop <= ibusy.bindex && ibusy.bindex <= bbot) {
+		h_inode = au_h_iptr(inode, ibusy.bindex);
+		if (h_inode && au_test_ibusy(inode, btop, bbot))
+			ibusy.h_ino = h_inode->i_ino;
+	}
+	ii_read_unlock(inode);
+	iput(inode);
+
+out_unlock:
+	si_read_unlock(sb);
+	if (!err) {
+		err = __put_user(ibusy.h_ino, &arg->h_ino);
+		if (unlikely(err)) {
+			err = -EFAULT;
+			AuTraceErr(err);
+		}
+	}
+out:
+	return err;
+}
+
+long au_ibusy_ioctl(struct file *file, unsigned long arg)
+{
+	return au_ibusy(file->f_path.dentry->d_sb, (void __user *)arg);
+}
+
+#ifdef CONFIG_COMPAT
+long au_ibusy_compat_ioctl(struct file *file, unsigned long arg)
+{
+	return au_ibusy(file->f_path.dentry->d_sb, compat_ptr(arg));
+}
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * change a branch permission
+ */
+
+static void au_warn_ima(void)
+{
+#ifdef CONFIG_IMA
+	/* since it doesn't support mark_files_ro() */
+	AuWarn1("RW -> RO makes IMA to produce wrong message\n");
+#endif
+}
+
+static int do_need_sigen_inc(int a, int b)
+{
+	return au_br_whable(a) && !au_br_whable(b);
+}
+
+static int need_sigen_inc(int old, int new)
+{
+	return do_need_sigen_inc(old, new)
+		|| do_need_sigen_inc(new, old);
+}
+
+static int au_br_mod_files_ro(struct super_block *sb, aufs_bindex_t bindex)
+{
+	int err, do_warn;
+	unsigned int mnt_flags;
+	unsigned long long ull, max;
+	aufs_bindex_t br_id;
+	unsigned char verbose, writer;
+	struct file *file, *hf, **array;
+	struct au_hfile *hfile;
+
+	mnt_flags = au_mntflags(sb);
+	verbose = !!au_opt_test(mnt_flags, VERBOSE);
+
+	array = au_farray_alloc(sb, &max);
+	err = PTR_ERR(array);
+	if (IS_ERR(array))
+		goto out;
+
+	do_warn = 0;
+	br_id = au_sbr_id(sb, bindex);
+	for (ull = 0; ull < max; ull++) {
+		file = array[ull];
+		if (unlikely(!file))
+			break;
+
+		/* AuDbg("%pD\n", file); */
+		fi_read_lock(file);
+		if (unlikely(au_test_mmapped(file))) {
+			err = -EBUSY;
+			AuVerbose(verbose, "mmapped %pD\n", file);
+			AuDbgFile(file);
+			FiMustNoWaiters(file);
+			fi_read_unlock(file);
+			goto out_array;
+		}
+
+		hfile = &au_fi(file)->fi_htop;
+		hf = hfile->hf_file;
+		if (!d_is_reg(file->f_path.dentry)
+		    || !(file->f_mode & FMODE_WRITE)
+		    || hfile->hf_br->br_id != br_id
+		    || !(hf->f_mode & FMODE_WRITE))
+			array[ull] = NULL;
+		else {
+			do_warn = 1;
+			get_file(file);
+		}
+
+		FiMustNoWaiters(file);
+		fi_read_unlock(file);
+		fput(file);
+	}
+
+	err = 0;
+	if (do_warn)
+		au_warn_ima();
+
+	for (ull = 0; ull < max; ull++) {
+		file = array[ull];
+		if (!file)
+			continue;
+
+		/* todo: already flushed? */
+		/*
+		 * fs/super.c:mark_files_ro() is gone, but aufs keeps its
+		 * approach which resets f_mode and calls mnt_drop_write() and
+		 * file_release_write() for each file, because the branch
+		 * attribute in aufs world is totally different from the native
+		 * fs rw/ro mode.
+		*/
+		/* fi_read_lock(file); */
+		hfile = &au_fi(file)->fi_htop;
+		hf = hfile->hf_file;
+		/* fi_read_unlock(file); */
+		spin_lock(&hf->f_lock);
+		writer = !!(hf->f_mode & FMODE_WRITER);
+		hf->f_mode &= ~(FMODE_WRITE | FMODE_WRITER);
+		spin_unlock(&hf->f_lock);
+		if (writer) {
+			put_write_access(file_inode(hf));
+			__mnt_drop_write(hf->f_path.mnt);
+		}
+	}
+
+out_array:
+	au_farray_free(array, max);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount,
+	      int *do_refresh)
+{
+	int err, rerr;
+	aufs_bindex_t bindex;
+	struct dentry *root;
+	struct au_branch *br;
+	struct au_br_fhsm *bf;
+
+	root = sb->s_root;
+	bindex = au_find_dbindex(root, mod->h_root);
+	if (bindex < 0) {
+		if (remount)
+			return 0; /* success */
+		err = -ENOENT;
+		pr_err("%s no such branch\n", mod->path);
+		goto out;
+	}
+	AuDbg("bindex b%d\n", bindex);
+
+	err = test_br(d_inode(mod->h_root), mod->perm, mod->path);
+	if (unlikely(err))
+		goto out;
+
+	br = au_sbr(sb, bindex);
+	AuDebugOn(mod->h_root != au_br_dentry(br));
+	if (br->br_perm == mod->perm)
+		return 0; /* success */
+
+	/* pre-allocate for non-fhsm --> fhsm */
+	bf = NULL;
+	if (!au_br_fhsm(br->br_perm) && au_br_fhsm(mod->perm)) {
+		err = au_fhsm_br_alloc(br);
+		if (unlikely(err))
+			goto out;
+		bf = br->br_fhsm;
+		br->br_fhsm = NULL;
+	}
+
+	if (au_br_writable(br->br_perm)) {
+		/* remove whiteout base */
+		err = au_br_init_wh(sb, br, mod->perm);
+		if (unlikely(err))
+			goto out_bf;
+
+		if (!au_br_writable(mod->perm)) {
+			/* rw --> ro, file might be mmapped */
+			DiMustNoWaiters(root);
+			IiMustNoWaiters(d_inode(root));
+			di_write_unlock(root);
+			err = au_br_mod_files_ro(sb, bindex);
+			/* aufs_write_lock() calls ..._child() */
+			di_write_lock_child(root);
+
+			if (unlikely(err)) {
+				rerr = -ENOMEM;
+				br->br_wbr = kzalloc(sizeof(*br->br_wbr),
+						     GFP_NOFS);
+				if (br->br_wbr)
+					rerr = au_wbr_init(br, sb, br->br_perm);
+				if (unlikely(rerr)) {
+					AuIOErr("nested error %d (%d)\n",
+						rerr, err);
+					br->br_perm = mod->perm;
+				}
+			}
+		}
+	} else if (au_br_writable(mod->perm)) {
+		/* ro --> rw */
+		err = -ENOMEM;
+		br->br_wbr = kzalloc(sizeof(*br->br_wbr), GFP_NOFS);
+		if (br->br_wbr) {
+			err = au_wbr_init(br, sb, mod->perm);
+			if (unlikely(err)) {
+				kfree(br->br_wbr);
+				br->br_wbr = NULL;
+			}
+		}
+	}
+	if (unlikely(err))
+		goto out_bf;
+
+	if (au_br_fhsm(br->br_perm)) {
+		if (!au_br_fhsm(mod->perm)) {
+			/* fhsm --> non-fhsm */
+			au_br_fhsm_fin(br->br_fhsm);
+			kfree(br->br_fhsm);
+			br->br_fhsm = NULL;
+		}
+	} else if (au_br_fhsm(mod->perm))
+		/* non-fhsm --> fhsm */
+		br->br_fhsm = bf;
+
+	*do_refresh |= need_sigen_inc(br->br_perm, mod->perm);
+	br->br_perm = mod->perm;
+	goto out; /* success */
+
+out_bf:
+	kfree(bf);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs)
+{
+	int err;
+	struct kstatfs kstfs;
+
+	err = vfs_statfs(&br->br_path, &kstfs);
+	if (!err) {
+		stfs->f_blocks = kstfs.f_blocks;
+		stfs->f_bavail = kstfs.f_bavail;
+		stfs->f_files = kstfs.f_files;
+		stfs->f_ffree = kstfs.f_ffree;
+	}
+
+	return err;
+}
diff --git a/fs/aufs/branch.h b/fs/aufs/branch.h
new file mode 100644
index 000000000000..e9591cfa2568
--- /dev/null
+++ b/fs/aufs/branch.h
@@ -0,0 +1,321 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * branch filesystems and xino for them
+ */
+
+#ifndef __AUFS_BRANCH_H__
+#define __AUFS_BRANCH_H__
+
+#ifdef __KERNEL__
+
+#include <linux/mount.h>
+#include "dynop.h"
+#include "rwsem.h"
+#include "super.h"
+
+/* ---------------------------------------------------------------------- */
+
+/* a xino file */
+struct au_xino_file {
+	struct file		*xi_file;
+	struct {
+		spinlock_t		spin;
+		ino_t			*array;
+		int			total;
+		/* reserved for future use */
+		/* unsigned long	*bitmap; */
+		wait_queue_head_t	wqh;
+	} xi_nondir;
+
+	/* todo: make xino files an array to support huge inode number */
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry		 *xi_dbgaufs;
+#endif
+};
+
+/* File-based Hierarchical Storage Management */
+struct au_br_fhsm {
+#ifdef CONFIG_AUFS_FHSM
+	struct mutex		bf_lock;
+	unsigned long		bf_jiffy;
+	struct aufs_stfs	bf_stfs;
+	int			bf_readable;
+#endif
+};
+
+/* members for writable branch only */
+enum {AuBrWh_BASE, AuBrWh_PLINK, AuBrWh_ORPH, AuBrWh_Last};
+struct au_wbr {
+	struct au_rwsem		wbr_wh_rwsem;
+	struct dentry		*wbr_wh[AuBrWh_Last];
+	atomic_t		wbr_wh_running;
+#define wbr_whbase		wbr_wh[AuBrWh_BASE]	/* whiteout base */
+#define wbr_plink		wbr_wh[AuBrWh_PLINK]	/* pseudo-link dir */
+#define wbr_orph		wbr_wh[AuBrWh_ORPH]	/* dir for orphans */
+
+	/* mfs mode */
+	unsigned long long	wbr_bytes;
+};
+
+/* ext2 has 3 types of operations at least, ext3 has 4 */
+#define AuBrDynOp (AuDyLast * 4)
+
+#ifdef CONFIG_AUFS_HFSNOTIFY
+/* support for asynchronous destruction */
+struct au_br_hfsnotify {
+	struct fsnotify_group	*hfsn_group;
+};
+#endif
+
+/* sysfs entries */
+struct au_brsysfs {
+	char			name[16];
+	struct attribute	attr;
+};
+
+enum {
+	AuBrSysfs_BR,
+	AuBrSysfs_BRID,
+	AuBrSysfs_Last
+};
+
+/* protected by superblock rwsem */
+struct au_branch {
+	struct au_xino_file	br_xino;
+
+	aufs_bindex_t		br_id;
+
+	int			br_perm;
+	struct path		br_path;
+	spinlock_t		br_dykey_lock;
+	struct au_dykey		*br_dykey[AuBrDynOp];
+	struct percpu_counter	br_count;
+
+	struct au_wbr		*br_wbr;
+	struct au_br_fhsm	*br_fhsm;
+
+	/* xino truncation */
+	atomic_t		br_xino_running;
+
+#ifdef CONFIG_AUFS_HFSNOTIFY
+	struct au_br_hfsnotify	*br_hfsn;
+#endif
+
+#ifdef CONFIG_SYSFS
+	/* entries under sysfs per mount-point */
+	struct au_brsysfs	br_sysfs[AuBrSysfs_Last];
+#endif
+};
+
+/* ---------------------------------------------------------------------- */
+
+static inline struct vfsmount *au_br_mnt(struct au_branch *br)
+{
+	return br->br_path.mnt;
+}
+
+static inline struct dentry *au_br_dentry(struct au_branch *br)
+{
+	return br->br_path.dentry;
+}
+
+static inline struct super_block *au_br_sb(struct au_branch *br)
+{
+	return au_br_mnt(br)->mnt_sb;
+}
+
+static inline void au_br_get(struct au_branch *br)
+{
+	percpu_counter_inc(&br->br_count);
+}
+
+static inline void au_br_put(struct au_branch *br)
+{
+	percpu_counter_dec(&br->br_count);
+}
+
+static inline s64 au_br_count(struct au_branch *br)
+{
+	return percpu_counter_sum(&br->br_count);
+}
+
+static inline void au_br_count_init(struct au_branch *br)
+{
+	percpu_counter_init(&br->br_count, 0, GFP_NOFS);
+}
+
+static inline void au_br_count_fin(struct au_branch *br)
+{
+	percpu_counter_destroy(&br->br_count);
+}
+
+static inline int au_br_rdonly(struct au_branch *br)
+{
+	return ((au_br_sb(br)->s_flags & MS_RDONLY)
+		|| !au_br_writable(br->br_perm))
+		? -EROFS : 0;
+}
+
+static inline int au_br_hnotifyable(int brperm __maybe_unused)
+{
+#ifdef CONFIG_AUFS_HNOTIFY
+	return !(brperm & AuBrPerm_RR);
+#else
+	return 0;
+#endif
+}
+
+static inline int au_br_test_oflag(int oflag, struct au_branch *br)
+{
+	int err, exec_flag;
+
+	err = 0;
+	exec_flag = oflag & __FMODE_EXEC;
+	if (unlikely(exec_flag && path_noexec(&br->br_path)))
+		err = -EACCES;
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* branch.c */
+struct au_sbinfo;
+void au_br_free(struct au_sbinfo *sinfo);
+int au_br_index(struct super_block *sb, aufs_bindex_t br_id);
+struct au_opt_add;
+int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount);
+struct au_opt_del;
+int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount);
+long au_ibusy_ioctl(struct file *file, unsigned long arg);
+#ifdef CONFIG_COMPAT
+long au_ibusy_compat_ioctl(struct file *file, unsigned long arg);
+#endif
+struct au_opt_mod;
+int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount,
+	      int *do_refresh);
+struct aufs_stfs;
+int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs);
+
+/* xino.c */
+static const loff_t au_loff_max = LLONG_MAX;
+
+int au_xib_trunc(struct super_block *sb);
+ssize_t xino_fread(vfs_readf_t func, struct file *file, void *buf, size_t size,
+		   loff_t *pos);
+ssize_t xino_fwrite(vfs_writef_t func, struct file *file, void *buf,
+		    size_t size, loff_t *pos);
+struct file *au_xino_create2(struct file *base_file, struct file *copy_src);
+struct file *au_xino_create(struct super_block *sb, char *fname, int silent);
+ino_t au_xino_new_ino(struct super_block *sb);
+void au_xino_delete_inode(struct inode *inode, const int unlinked);
+int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+		  ino_t ino);
+int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+		 ino_t *ino);
+int au_xino_br(struct super_block *sb, struct au_branch *br, ino_t hino,
+	       struct file *base_file, int do_test);
+int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex);
+
+struct au_opt_xino;
+int au_xino_set(struct super_block *sb, struct au_opt_xino *xino, int remount);
+void au_xino_clr(struct super_block *sb);
+struct file *au_xino_def(struct super_block *sb);
+int au_xino_path(struct seq_file *seq, struct file *file);
+
+void au_xinondir_leave(struct super_block *sb, aufs_bindex_t bindex,
+		       ino_t h_ino, int idx);
+int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+		      int *idx);
+
+/* ---------------------------------------------------------------------- */
+
+/* Superblock to branch */
+static inline
+aufs_bindex_t au_sbr_id(struct super_block *sb, aufs_bindex_t bindex)
+{
+	return au_sbr(sb, bindex)->br_id;
+}
+
+static inline
+struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex)
+{
+	return au_br_mnt(au_sbr(sb, bindex));
+}
+
+static inline
+struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex)
+{
+	return au_br_sb(au_sbr(sb, bindex));
+}
+
+static inline void au_sbr_get(struct super_block *sb, aufs_bindex_t bindex)
+{
+	au_br_get(au_sbr(sb, bindex));
+}
+
+static inline void au_sbr_put(struct super_block *sb, aufs_bindex_t bindex)
+{
+	au_br_put(au_sbr(sb, bindex));
+}
+
+static inline int au_sbr_perm(struct super_block *sb, aufs_bindex_t bindex)
+{
+	return au_sbr(sb, bindex)->br_perm;
+}
+
+static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex)
+{
+	return au_br_whable(au_sbr_perm(sb, bindex));
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * wbr_wh_read_lock, wbr_wh_write_lock
+ * wbr_wh_read_unlock, wbr_wh_write_unlock, wbr_wh_downgrade_lock
+ */
+AuSimpleRwsemFuncs(wbr_wh, struct au_wbr *wbr, &wbr->wbr_wh_rwsem);
+
+#define WbrWhMustNoWaiters(wbr)	AuRwMustNoWaiters(&wbr->wbr_wh_rwsem)
+#define WbrWhMustAnyLock(wbr)	AuRwMustAnyLock(&wbr->wbr_wh_rwsem)
+#define WbrWhMustWriteLock(wbr)	AuRwMustWriteLock(&wbr->wbr_wh_rwsem)
+
+/* ---------------------------------------------------------------------- */
+
+#ifdef CONFIG_AUFS_FHSM
+static inline void au_br_fhsm_init(struct au_br_fhsm *brfhsm)
+{
+	mutex_init(&brfhsm->bf_lock);
+	brfhsm->bf_jiffy = 0;
+	brfhsm->bf_readable = 0;
+}
+
+static inline void au_br_fhsm_fin(struct au_br_fhsm *brfhsm)
+{
+	mutex_destroy(&brfhsm->bf_lock);
+}
+#else
+AuStubVoid(au_br_fhsm_init, struct au_br_fhsm *brfhsm)
+AuStubVoid(au_br_fhsm_fin, struct au_br_fhsm *brfhsm)
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_BRANCH_H__ */
diff --git a/fs/aufs/conf.mk b/fs/aufs/conf.mk
new file mode 100644
index 000000000000..0bbb2d3a5285
--- /dev/null
+++ b/fs/aufs/conf.mk
@@ -0,0 +1,38 @@
+
+AuConfStr = CONFIG_AUFS_FS=${CONFIG_AUFS_FS}
+
+define AuConf
+ifdef ${1}
+AuConfStr += ${1}=${${1}}
+endif
+endef
+
+AuConfAll = BRANCH_MAX_127 BRANCH_MAX_511 BRANCH_MAX_1023 BRANCH_MAX_32767 \
+	SBILIST \
+	HNOTIFY HFSNOTIFY \
+	EXPORT INO_T_64 \
+	XATTR \
+	FHSM \
+	RDU \
+	SHWH \
+	BR_RAMFS \
+	BR_FUSE POLL \
+	BR_HFSPLUS \
+	BDEV_LOOP \
+	DEBUG MAGIC_SYSRQ
+$(foreach i, ${AuConfAll}, \
+	$(eval $(call AuConf,CONFIG_AUFS_${i})))
+
+AuConfName = ${obj}/conf.str
+${AuConfName}.tmp: FORCE
+	@echo ${AuConfStr} | tr ' ' '\n' | sed -e 's/^/"/' -e 's/$$/\\n"/' > $@
+${AuConfName}: ${AuConfName}.tmp
+	@diff -q $< $@ > /dev/null 2>&1 || { \
+	echo '  GEN    ' $@; \
+	cp -p $< $@; \
+	}
+FORCE:
+clean-files += ${AuConfName} ${AuConfName}.tmp
+${obj}/sysfs.o: ${AuConfName}
+
+-include ${srctree}/${src}/conf_priv.mk
diff --git a/fs/aufs/cpup.c b/fs/aufs/cpup.c
new file mode 100644
index 000000000000..d201fc056979
--- /dev/null
+++ b/fs/aufs/cpup.c
@@ -0,0 +1,1443 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * copy-up functions, see wbr_policy.c for copy-down
+ */
+
+#include <linux/fs_stack.h>
+#include <linux/mm.h>
+#include <linux/task_work.h>
+#include "aufs.h"
+
+void au_cpup_attr_flags(struct inode *dst, unsigned int iflags)
+{
+	const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE
+		| S_NOATIME | S_NOCMTIME | S_AUTOMOUNT;
+
+	BUILD_BUG_ON(sizeof(iflags) != sizeof(dst->i_flags));
+
+	dst->i_flags |= iflags & ~mask;
+	if (au_test_fs_notime(dst->i_sb))
+		dst->i_flags |= S_NOATIME | S_NOCMTIME;
+}
+
+void au_cpup_attr_timesizes(struct inode *inode)
+{
+	struct inode *h_inode;
+
+	h_inode = au_h_iptr(inode, au_ibtop(inode));
+	fsstack_copy_attr_times(inode, h_inode);
+	fsstack_copy_inode_size(inode, h_inode);
+}
+
+void au_cpup_attr_nlink(struct inode *inode, int force)
+{
+	struct inode *h_inode;
+	struct super_block *sb;
+	aufs_bindex_t bindex, bbot;
+
+	sb = inode->i_sb;
+	bindex = au_ibtop(inode);
+	h_inode = au_h_iptr(inode, bindex);
+	if (!force
+	    && !S_ISDIR(h_inode->i_mode)
+	    && au_opt_test(au_mntflags(sb), PLINK)
+	    && au_plink_test(inode))
+		return;
+
+	/*
+	 * 0 can happen in revalidating.
+	 * h_inode->i_mutex may not be held here, but it is harmless since once
+	 * i_nlink reaches 0, it will never become positive except O_TMPFILE
+	 * case.
+	 * todo: O_TMPFILE+linkat(AT_SYMLINK_FOLLOW) bypassing aufs may cause
+	 *	 the incorrect link count.
+	 */
+	set_nlink(inode, h_inode->i_nlink);
+
+	/*
+	 * fewer nlink makes find(1) noisy, but larger nlink doesn't.
+	 * it may includes whplink directory.
+	 */
+	if (S_ISDIR(h_inode->i_mode)) {
+		bbot = au_ibbot(inode);
+		for (bindex++; bindex <= bbot; bindex++) {
+			h_inode = au_h_iptr(inode, bindex);
+			if (h_inode)
+				au_add_nlink(inode, h_inode);
+		}
+	}
+}
+
+void au_cpup_attr_changeable(struct inode *inode)
+{
+	struct inode *h_inode;
+
+	h_inode = au_h_iptr(inode, au_ibtop(inode));
+	inode->i_mode = h_inode->i_mode;
+	inode->i_uid = h_inode->i_uid;
+	inode->i_gid = h_inode->i_gid;
+	au_cpup_attr_timesizes(inode);
+	au_cpup_attr_flags(inode, h_inode->i_flags);
+}
+
+void au_cpup_igen(struct inode *inode, struct inode *h_inode)
+{
+	struct au_iinfo *iinfo = au_ii(inode);
+
+	IiMustWriteLock(inode);
+
+	iinfo->ii_higen = h_inode->i_generation;
+	iinfo->ii_hsb1 = h_inode->i_sb;
+}
+
+void au_cpup_attr_all(struct inode *inode, int force)
+{
+	struct inode *h_inode;
+
+	h_inode = au_h_iptr(inode, au_ibtop(inode));
+	au_cpup_attr_changeable(inode);
+	if (inode->i_nlink > 0)
+		au_cpup_attr_nlink(inode, force);
+	inode->i_rdev = h_inode->i_rdev;
+	inode->i_blkbits = h_inode->i_blkbits;
+	au_cpup_igen(inode, h_inode);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */
+
+/* keep the timestamps of the parent dir when cpup */
+void au_dtime_store(struct au_dtime *dt, struct dentry *dentry,
+		    struct path *h_path)
+{
+	struct inode *h_inode;
+
+	dt->dt_dentry = dentry;
+	dt->dt_h_path = *h_path;
+	h_inode = d_inode(h_path->dentry);
+	dt->dt_atime = h_inode->i_atime;
+	dt->dt_mtime = h_inode->i_mtime;
+	/* smp_mb(); */
+}
+
+void au_dtime_revert(struct au_dtime *dt)
+{
+	struct iattr attr;
+	int err;
+
+	attr.ia_atime = dt->dt_atime;
+	attr.ia_mtime = dt->dt_mtime;
+	attr.ia_valid = ATTR_FORCE | ATTR_MTIME | ATTR_MTIME_SET
+		| ATTR_ATIME | ATTR_ATIME_SET;
+
+	/* no delegation since this is a directory */
+	err = vfsub_notify_change(&dt->dt_h_path, &attr, /*delegated*/NULL);
+	if (unlikely(err))
+		pr_warn("restoring timestamps failed(%d). ignored\n", err);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* internal use only */
+struct au_cpup_reg_attr {
+	int		valid;
+	struct kstat	st;
+	unsigned int	iflags; /* inode->i_flags */
+};
+
+static noinline_for_stack
+int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src,
+	       struct au_cpup_reg_attr *h_src_attr)
+{
+	int err, sbits, icex;
+	unsigned int mnt_flags;
+	unsigned char verbose;
+	struct iattr ia;
+	struct path h_path;
+	struct inode *h_isrc, *h_idst;
+	struct kstat *h_st;
+	struct au_branch *br;
+
+	h_path.dentry = au_h_dptr(dst, bindex);
+	h_idst = d_inode(h_path.dentry);
+	br = au_sbr(dst->d_sb, bindex);
+	h_path.mnt = au_br_mnt(br);
+	h_isrc = d_inode(h_src);
+	ia.ia_valid = ATTR_FORCE | ATTR_UID | ATTR_GID
+		| ATTR_ATIME | ATTR_MTIME
+		| ATTR_ATIME_SET | ATTR_MTIME_SET;
+	if (h_src_attr && h_src_attr->valid) {
+		h_st = &h_src_attr->st;
+		ia.ia_uid = h_st->uid;
+		ia.ia_gid = h_st->gid;
+		ia.ia_atime = h_st->atime;
+		ia.ia_mtime = h_st->mtime;
+		if (h_idst->i_mode != h_st->mode
+		    && !S_ISLNK(h_idst->i_mode)) {
+			ia.ia_valid |= ATTR_MODE;
+			ia.ia_mode = h_st->mode;
+		}
+		sbits = !!(h_st->mode & (S_ISUID | S_ISGID));
+		au_cpup_attr_flags(h_idst, h_src_attr->iflags);
+	} else {
+		ia.ia_uid = h_isrc->i_uid;
+		ia.ia_gid = h_isrc->i_gid;
+		ia.ia_atime = h_isrc->i_atime;
+		ia.ia_mtime = h_isrc->i_mtime;
+		if (h_idst->i_mode != h_isrc->i_mode
+		    && !S_ISLNK(h_idst->i_mode)) {
+			ia.ia_valid |= ATTR_MODE;
+			ia.ia_mode = h_isrc->i_mode;
+		}
+		sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID));
+		au_cpup_attr_flags(h_idst, h_isrc->i_flags);
+	}
+	/* no delegation since it is just created */
+	err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL);
+
+	/* is this nfs only? */
+	if (!err && sbits && au_test_nfs(h_path.dentry->d_sb)) {
+		ia.ia_valid = ATTR_FORCE | ATTR_MODE;
+		ia.ia_mode = h_isrc->i_mode;
+		err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL);
+	}
+
+	icex = br->br_perm & AuBrAttr_ICEX;
+	if (!err) {
+		mnt_flags = au_mntflags(dst->d_sb);
+		verbose = !!au_opt_test(mnt_flags, VERBOSE);
+		err = au_cpup_xattr(h_path.dentry, h_src, icex, verbose);
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_do_copy_file(struct file *dst, struct file *src, loff_t len,
+			   char *buf, unsigned long blksize)
+{
+	int err;
+	size_t sz, rbytes, wbytes;
+	unsigned char all_zero;
+	char *p, *zp;
+	struct inode *h_inode;
+	/* reduce stack usage */
+	struct iattr *ia;
+
+	zp = page_address(ZERO_PAGE(0));
+	if (unlikely(!zp))
+		return -ENOMEM; /* possible? */
+
+	err = 0;
+	all_zero = 0;
+	while (len) {
+		AuDbg("len %lld\n", len);
+		sz = blksize;
+		if (len < blksize)
+			sz = len;
+
+		rbytes = 0;
+		/* todo: signal_pending? */
+		while (!rbytes || err == -EAGAIN || err == -EINTR) {
+			rbytes = vfsub_read_k(src, buf, sz, &src->f_pos);
+			err = rbytes;
+		}
+		if (unlikely(err < 0))
+			break;
+
+		all_zero = 0;
+		if (len >= rbytes && rbytes == blksize)
+			all_zero = !memcmp(buf, zp, rbytes);
+		if (!all_zero) {
+			wbytes = rbytes;
+			p = buf;
+			while (wbytes) {
+				size_t b;
+
+				b = vfsub_write_k(dst, p, wbytes, &dst->f_pos);
+				err = b;
+				/* todo: signal_pending? */
+				if (unlikely(err == -EAGAIN || err == -EINTR))
+					continue;
+				if (unlikely(err < 0))
+					break;
+				wbytes -= b;
+				p += b;
+			}
+			if (unlikely(err < 0))
+				break;
+		} else {
+			loff_t res;
+
+			AuLabel(hole);
+			res = vfsub_llseek(dst, rbytes, SEEK_CUR);
+			err = res;
+			if (unlikely(res < 0))
+				break;
+		}
+		len -= rbytes;
+		err = 0;
+	}
+
+	/* the last block may be a hole */
+	if (!err && all_zero) {
+		AuLabel(last hole);
+
+		err = 1;
+		if (au_test_nfs(dst->f_path.dentry->d_sb)) {
+			/* nfs requires this step to make last hole */
+			/* is this only nfs? */
+			do {
+				/* todo: signal_pending? */
+				err = vfsub_write_k(dst, "\0", 1, &dst->f_pos);
+			} while (err == -EAGAIN || err == -EINTR);
+			if (err == 1)
+				dst->f_pos--;
+		}
+
+		if (err == 1) {
+			ia = (void *)buf;
+			ia->ia_size = dst->f_pos;
+			ia->ia_valid = ATTR_SIZE | ATTR_FILE;
+			ia->ia_file = dst;
+			h_inode = file_inode(dst);
+			inode_lock_nested(h_inode, AuLsc_I_CHILD2);
+			/* no delegation since it is just created */
+			err = vfsub_notify_change(&dst->f_path, ia,
+						  /*delegated*/NULL);
+			inode_unlock(h_inode);
+		}
+	}
+
+	return err;
+}
+
+int au_copy_file(struct file *dst, struct file *src, loff_t len)
+{
+	int err;
+	unsigned long blksize;
+	unsigned char do_kfree;
+	char *buf;
+
+	err = -ENOMEM;
+	blksize = dst->f_path.dentry->d_sb->s_blocksize;
+	if (!blksize || PAGE_SIZE < blksize)
+		blksize = PAGE_SIZE;
+	AuDbg("blksize %lu\n", blksize);
+	do_kfree = (blksize != PAGE_SIZE && blksize >= sizeof(struct iattr *));
+	if (do_kfree)
+		buf = kmalloc(blksize, GFP_NOFS);
+	else
+		buf = (void *)__get_free_page(GFP_NOFS);
+	if (unlikely(!buf))
+		goto out;
+
+	if (len > (1 << 22))
+		AuDbg("copying a large file %lld\n", (long long)len);
+
+	src->f_pos = 0;
+	dst->f_pos = 0;
+	err = au_do_copy_file(dst, src, len, buf, blksize);
+	if (do_kfree)
+		kfree(buf);
+	else
+		free_page((unsigned long)buf);
+
+out:
+	return err;
+}
+
+static int au_do_copy(struct file *dst, struct file *src, loff_t len)
+{
+	int err;
+	struct super_block *h_src_sb;
+	struct inode *h_src_inode;
+
+	h_src_inode = file_inode(src);
+	h_src_sb = h_src_inode->i_sb;
+
+	/* XFS acquires inode_lock */
+	if (!au_test_xfs(h_src_sb))
+		err = au_copy_file(dst, src, len);
+	else {
+		inode_unlock_shared(h_src_inode);
+		err = au_copy_file(dst, src, len);
+		vfsub_inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD);
+	}
+
+	return err;
+}
+
+static int au_clone_or_copy(struct file *dst, struct file *src, loff_t len)
+{
+	int err;
+	struct super_block *h_src_sb;
+	struct inode *h_src_inode;
+
+	h_src_inode = file_inode(src);
+	h_src_sb = h_src_inode->i_sb;
+	if (h_src_sb != file_inode(dst)->i_sb
+	    || !dst->f_op->clone_file_range) {
+		err = au_do_copy(dst, src, len);
+		goto out;
+	}
+
+	if (!au_test_nfs(h_src_sb)) {
+		inode_unlock_shared(h_src_inode);
+		err = vfsub_clone_file_range(src, dst, len);
+		vfsub_inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD);
+	} else
+		err = vfsub_clone_file_range(src, dst, len);
+	/* older XFS has a condition in cloning */
+	if (unlikely(err != -EOPNOTSUPP))
+		goto out;
+
+	/* the backend fs on NFS may not support cloning */
+	err = au_do_copy(dst, src, len);
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/*
+ * to support a sparse file which is opened with O_APPEND,
+ * we need to close the file.
+ */
+static int au_cp_regular(struct au_cp_generic *cpg)
+{
+	int err, i;
+	enum { SRC, DST };
+	struct {
+		aufs_bindex_t bindex;
+		unsigned int flags;
+		struct dentry *dentry;
+		int force_wr;
+		struct file *file;
+		void *label;
+	} *f, file[] = {
+		{
+			.bindex = cpg->bsrc,
+			.flags = O_RDONLY | O_NOATIME | O_LARGEFILE,
+			.label = &&out
+		},
+		{
+			.bindex = cpg->bdst,
+			.flags = O_WRONLY | O_NOATIME | O_LARGEFILE,
+			.force_wr = !!au_ftest_cpup(cpg->flags, RWDST),
+			.label = &&out_src
+		}
+	};
+	struct super_block *sb, *h_src_sb;
+	struct inode *h_src_inode;
+	struct task_struct *tsk = current;
+
+	/* bsrc branch can be ro/rw. */
+	sb = cpg->dentry->d_sb;
+	f = file;
+	for (i = 0; i < 2; i++, f++) {
+		f->dentry = au_h_dptr(cpg->dentry, f->bindex);
+		f->file = au_h_open(cpg->dentry, f->bindex, f->flags,
+				    /*file*/NULL, f->force_wr);
+		err = PTR_ERR(f->file);
+		if (IS_ERR(f->file))
+			goto *f->label;
+	}
+
+	/* try stopping to update while we copyup */
+	h_src_inode = d_inode(file[SRC].dentry);
+	h_src_sb = h_src_inode->i_sb;
+	if (!au_test_nfs(h_src_sb))
+		IMustLock(h_src_inode);
+	err = au_clone_or_copy(file[DST].file, file[SRC].file, cpg->len);
+
+	/* i wonder if we had O_NO_DELAY_FPUT flag */
+	if (tsk->flags & PF_KTHREAD)
+		__fput_sync(file[DST].file);
+	else {
+		WARN(1, "%pD\nPlease report this warning to aufs-users ML",
+		     file[DST].file);
+		fput(file[DST].file);
+		/*
+		 * too bad.
+		 * we have to call both since we don't know which place the file
+		 * was added to.
+		 */
+		task_work_run();
+		flush_delayed_fput();
+	}
+	au_sbr_put(sb, file[DST].bindex);
+
+out_src:
+	fput(file[SRC].file);
+	au_sbr_put(sb, file[SRC].bindex);
+out:
+	return err;
+}
+
+static int au_do_cpup_regular(struct au_cp_generic *cpg,
+			      struct au_cpup_reg_attr *h_src_attr)
+{
+	int err, rerr;
+	loff_t l;
+	struct path h_path;
+	struct inode *h_src_inode, *h_dst_inode;
+
+	err = 0;
+	h_src_inode = au_h_iptr(d_inode(cpg->dentry), cpg->bsrc);
+	l = i_size_read(h_src_inode);
+	if (cpg->len == -1 || l < cpg->len)
+		cpg->len = l;
+	if (cpg->len) {
+		/* try stopping to update while we are referencing */
+		vfsub_inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD);
+		au_pin_hdir_unlock(cpg->pin);
+
+		h_path.dentry = au_h_dptr(cpg->dentry, cpg->bsrc);
+		h_path.mnt = au_sbr_mnt(cpg->dentry->d_sb, cpg->bsrc);
+		h_src_attr->iflags = h_src_inode->i_flags;
+		if (!au_test_nfs(h_src_inode->i_sb))
+			err = vfsub_getattr(&h_path, &h_src_attr->st);
+		else {
+			inode_unlock_shared(h_src_inode);
+			err = vfsub_getattr(&h_path, &h_src_attr->st);
+			vfsub_inode_lock_shared_nested(h_src_inode,
+						       AuLsc_I_CHILD);
+		}
+		if (unlikely(err)) {
+			inode_unlock_shared(h_src_inode);
+			goto out;
+		}
+		h_src_attr->valid = 1;
+		if (!au_test_nfs(h_src_inode->i_sb)) {
+			err = au_cp_regular(cpg);
+			inode_unlock_shared(h_src_inode);
+		} else {
+			inode_unlock_shared(h_src_inode);
+			err = au_cp_regular(cpg);
+		}
+		rerr = au_pin_hdir_relock(cpg->pin);
+		if (!err && rerr)
+			err = rerr;
+	}
+	if (!err && (h_src_inode->i_state & I_LINKABLE)) {
+		h_path.dentry = au_h_dptr(cpg->dentry, cpg->bdst);
+		h_dst_inode = d_inode(h_path.dentry);
+		spin_lock(&h_dst_inode->i_lock);
+		h_dst_inode->i_state |= I_LINKABLE;
+		spin_unlock(&h_dst_inode->i_lock);
+	}
+
+out:
+	return err;
+}
+
+static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src,
+			      struct inode *h_dir)
+{
+	int err, symlen;
+	mm_segment_t old_fs;
+	union {
+		char *k;
+		char __user *u;
+	} sym;
+
+	err = -ENOMEM;
+	sym.k = (void *)__get_free_page(GFP_NOFS);
+	if (unlikely(!sym.k))
+		goto out;
+
+	/* unnecessary to support mmap_sem since symlink is not mmap-able */
+	old_fs = get_fs();
+	set_fs(KERNEL_DS);
+	symlen = vfs_readlink(h_src, sym.u, PATH_MAX);
+	err = symlen;
+	set_fs(old_fs);
+
+	if (symlen > 0) {
+		sym.k[symlen] = 0;
+		err = vfsub_symlink(h_dir, h_path, sym.k);
+	}
+	free_page((unsigned long)sym.k);
+
+out:
+	return err;
+}
+
+/*
+ * regardless 'acl' option, reset all ACL.
+ * All ACL will be copied up later from the original entry on the lower branch.
+ */
+static int au_reset_acl(struct inode *h_dir, struct path *h_path, umode_t mode)
+{
+	int err;
+	struct dentry *h_dentry;
+	struct inode *h_inode;
+
+	h_dentry = h_path->dentry;
+	h_inode = d_inode(h_dentry);
+	/* forget_all_cached_acls(h_inode)); */
+	err = vfsub_removexattr(h_dentry, XATTR_NAME_POSIX_ACL_ACCESS);
+	AuTraceErr(err);
+	if (err == -EOPNOTSUPP)
+		err = 0;
+	if (!err)
+		err = vfsub_acl_chmod(h_inode, mode);
+
+	AuTraceErr(err);
+	return err;
+}
+
+static int au_do_cpup_dir(struct au_cp_generic *cpg, struct dentry *dst_parent,
+			  struct inode *h_dir, struct path *h_path)
+{
+	int err;
+	struct inode *dir, *inode;
+
+	err = vfsub_removexattr(h_path->dentry, XATTR_NAME_POSIX_ACL_DEFAULT);
+	AuTraceErr(err);
+	if (err == -EOPNOTSUPP)
+		err = 0;
+	if (unlikely(err))
+		goto out;
+
+	/*
+	 * strange behaviour from the users view,
+	 * particularry setattr case
+	 */
+	dir = d_inode(dst_parent);
+	if (au_ibtop(dir) == cpg->bdst)
+		au_cpup_attr_nlink(dir, /*force*/1);
+	inode = d_inode(cpg->dentry);
+	au_cpup_attr_nlink(inode, /*force*/1);
+
+out:
+	return err;
+}
+
+static noinline_for_stack
+int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent,
+	       struct au_cpup_reg_attr *h_src_attr)
+{
+	int err;
+	umode_t mode;
+	unsigned int mnt_flags;
+	unsigned char isdir, isreg, force;
+	const unsigned char do_dt = !!au_ftest_cpup(cpg->flags, DTIME);
+	struct au_dtime dt;
+	struct path h_path;
+	struct dentry *h_src, *h_dst, *h_parent;
+	struct inode *h_inode, *h_dir;
+	struct super_block *sb;
+
+	/* bsrc branch can be ro/rw. */
+	h_src = au_h_dptr(cpg->dentry, cpg->bsrc);
+	h_inode = d_inode(h_src);
+	AuDebugOn(h_inode != au_h_iptr(d_inode(cpg->dentry), cpg->bsrc));
+
+	/* try stopping to be referenced while we are creating */
+	h_dst = au_h_dptr(cpg->dentry, cpg->bdst);
+	if (au_ftest_cpup(cpg->flags, RENAME))
+		AuDebugOn(strncmp(h_dst->d_name.name, AUFS_WH_PFX,
+				  AUFS_WH_PFX_LEN));
+	h_parent = h_dst->d_parent; /* dir inode is locked */
+	h_dir = d_inode(h_parent);
+	IMustLock(h_dir);
+	AuDebugOn(h_parent != h_dst->d_parent);
+
+	sb = cpg->dentry->d_sb;
+	h_path.mnt = au_sbr_mnt(sb, cpg->bdst);
+	if (do_dt) {
+		h_path.dentry = h_parent;
+		au_dtime_store(&dt, dst_parent, &h_path);
+	}
+	h_path.dentry = h_dst;
+
+	isreg = 0;
+	isdir = 0;
+	mode = h_inode->i_mode;
+	switch (mode & S_IFMT) {
+	case S_IFREG:
+		isreg = 1;
+		err = vfsub_create(h_dir, &h_path, S_IRUSR | S_IWUSR,
+				   /*want_excl*/true);
+		if (!err)
+			err = au_do_cpup_regular(cpg, h_src_attr);
+		break;
+	case S_IFDIR:
+		isdir = 1;
+		err = vfsub_mkdir(h_dir, &h_path, mode);
+		if (!err)
+			err = au_do_cpup_dir(cpg, dst_parent, h_dir, &h_path);
+		break;
+	case S_IFLNK:
+		err = au_do_cpup_symlink(&h_path, h_src, h_dir);
+		break;
+	case S_IFCHR:
+	case S_IFBLK:
+		AuDebugOn(!capable(CAP_MKNOD));
+		/*FALLTHROUGH*/
+	case S_IFIFO:
+	case S_IFSOCK:
+		err = vfsub_mknod(h_dir, &h_path, mode, h_inode->i_rdev);
+		break;
+	default:
+		AuIOErr("Unknown inode type 0%o\n", mode);
+		err = -EIO;
+	}
+	if (!err)
+		err = au_reset_acl(h_dir, &h_path, mode);
+
+	mnt_flags = au_mntflags(sb);
+	if (!au_opt_test(mnt_flags, UDBA_NONE)
+	    && !isdir
+	    && au_opt_test(mnt_flags, XINO)
+	    && (h_inode->i_nlink == 1
+		|| (h_inode->i_state & I_LINKABLE))
+	    /* todo: unnecessary? */
+	    /* && d_inode(cpg->dentry)->i_nlink == 1 */
+	    && cpg->bdst < cpg->bsrc
+	    && !au_ftest_cpup(cpg->flags, KEEPLINO))
+		au_xino_write(sb, cpg->bsrc, h_inode->i_ino, /*ino*/0);
+		/* ignore this error */
+
+	if (!err) {
+		force = 0;
+		if (isreg) {
+			force = !!cpg->len;
+			if (cpg->len == -1)
+				force = !!i_size_read(h_inode);
+		}
+		au_fhsm_wrote(sb, cpg->bdst, force);
+	}
+
+	if (do_dt)
+		au_dtime_revert(&dt);
+	return err;
+}
+
+static int au_do_ren_after_cpup(struct au_cp_generic *cpg, struct path *h_path)
+{
+	int err;
+	struct dentry *dentry, *h_dentry, *h_parent, *parent;
+	struct inode *h_dir;
+	aufs_bindex_t bdst;
+
+	dentry = cpg->dentry;
+	bdst = cpg->bdst;
+	h_dentry = au_h_dptr(dentry, bdst);
+	if (!au_ftest_cpup(cpg->flags, OVERWRITE)) {
+		dget(h_dentry);
+		au_set_h_dptr(dentry, bdst, NULL);
+		err = au_lkup_neg(dentry, bdst, /*wh*/0);
+		if (!err)
+			h_path->dentry = dget(au_h_dptr(dentry, bdst));
+		au_set_h_dptr(dentry, bdst, h_dentry);
+	} else {
+		err = 0;
+		parent = dget_parent(dentry);
+		h_parent = au_h_dptr(parent, bdst);
+		dput(parent);
+		h_path->dentry = vfsub_lkup_one(&dentry->d_name, h_parent);
+		if (IS_ERR(h_path->dentry))
+			err = PTR_ERR(h_path->dentry);
+	}
+	if (unlikely(err))
+		goto out;
+
+	h_parent = h_dentry->d_parent; /* dir inode is locked */
+	h_dir = d_inode(h_parent);
+	IMustLock(h_dir);
+	AuDbg("%pd %pd\n", h_dentry, h_path->dentry);
+	/* no delegation since it is just created */
+	err = vfsub_rename(h_dir, h_dentry, h_dir, h_path, /*delegated*/NULL,
+			   /*flags*/0);
+	dput(h_path->dentry);
+
+out:
+	return err;
+}
+
+/*
+ * copyup the @dentry from @bsrc to @bdst.
+ * the caller must set the both of lower dentries.
+ * @len is for truncating when it is -1 copyup the entire file.
+ * in link/rename cases, @dst_parent may be different from the real one.
+ * basic->bsrc can be larger than basic->bdst.
+ * aufs doesn't touch the credential so
+ * security_inode_copy_up{,_xattr}() are unnecrssary.
+ */
+static int au_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent)
+{
+	int err, rerr;
+	aufs_bindex_t old_ibtop;
+	unsigned char isdir, plink;
+	struct dentry *h_src, *h_dst, *h_parent;
+	struct inode *dst_inode, *h_dir, *inode, *delegated, *src_inode;
+	struct super_block *sb;
+	struct au_branch *br;
+	/* to reuduce stack size */
+	struct {
+		struct au_dtime dt;
+		struct path h_path;
+		struct au_cpup_reg_attr h_src_attr;
+	} *a;
+
+	err = -ENOMEM;
+	a = kmalloc(sizeof(*a), GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+	a->h_src_attr.valid = 0;
+
+	sb = cpg->dentry->d_sb;
+	br = au_sbr(sb, cpg->bdst);
+	a->h_path.mnt = au_br_mnt(br);
+	h_dst = au_h_dptr(cpg->dentry, cpg->bdst);
+	h_parent = h_dst->d_parent; /* dir inode is locked */
+	h_dir = d_inode(h_parent);
+	IMustLock(h_dir);
+
+	h_src = au_h_dptr(cpg->dentry, cpg->bsrc);
+	inode = d_inode(cpg->dentry);
+
+	if (!dst_parent)
+		dst_parent = dget_parent(cpg->dentry);
+	else
+		dget(dst_parent);
+
+	plink = !!au_opt_test(au_mntflags(sb), PLINK);
+	dst_inode = au_h_iptr(inode, cpg->bdst);
+	if (dst_inode) {
+		if (unlikely(!plink)) {
+			err = -EIO;
+			AuIOErr("hi%lu(i%lu) exists on b%d "
+				"but plink is disabled\n",
+				dst_inode->i_ino, inode->i_ino, cpg->bdst);
+			goto out_parent;
+		}
+
+		if (dst_inode->i_nlink) {
+			const int do_dt = au_ftest_cpup(cpg->flags, DTIME);
+
+			h_src = au_plink_lkup(inode, cpg->bdst);
+			err = PTR_ERR(h_src);
+			if (IS_ERR(h_src))
+				goto out_parent;
+			if (unlikely(d_is_negative(h_src))) {
+				err = -EIO;
+				AuIOErr("i%lu exists on b%d "
+					"but not pseudo-linked\n",
+					inode->i_ino, cpg->bdst);
+				dput(h_src);
+				goto out_parent;
+			}
+
+			if (do_dt) {
+				a->h_path.dentry = h_parent;
+				au_dtime_store(&a->dt, dst_parent, &a->h_path);
+			}
+
+			a->h_path.dentry = h_dst;
+			delegated = NULL;
+			err = vfsub_link(h_src, h_dir, &a->h_path, &delegated);
+			if (!err && au_ftest_cpup(cpg->flags, RENAME))
+				err = au_do_ren_after_cpup(cpg, &a->h_path);
+			if (do_dt)
+				au_dtime_revert(&a->dt);
+			if (unlikely(err == -EWOULDBLOCK)) {
+				pr_warn("cannot retry for NFSv4 delegation"
+					" for an internal link\n");
+				iput(delegated);
+			}
+			dput(h_src);
+			goto out_parent;
+		} else
+			/* todo: cpup_wh_file? */
+			/* udba work */
+			au_update_ibrange(inode, /*do_put_zero*/1);
+	}
+
+	isdir = S_ISDIR(inode->i_mode);
+	old_ibtop = au_ibtop(inode);
+	err = cpup_entry(cpg, dst_parent, &a->h_src_attr);
+	if (unlikely(err))
+		goto out_rev;
+	dst_inode = d_inode(h_dst);
+	inode_lock_nested(dst_inode, AuLsc_I_CHILD2);
+	/* todo: necessary? */
+	/* au_pin_hdir_unlock(cpg->pin); */
+
+	err = cpup_iattr(cpg->dentry, cpg->bdst, h_src, &a->h_src_attr);
+	if (unlikely(err)) {
+		/* todo: necessary? */
+		/* au_pin_hdir_relock(cpg->pin); */ /* ignore an error */
+		inode_unlock(dst_inode);
+		goto out_rev;
+	}
+
+	if (cpg->bdst < old_ibtop) {
+		if (S_ISREG(inode->i_mode)) {
+			err = au_dy_iaop(inode, cpg->bdst, dst_inode);
+			if (unlikely(err)) {
+				/* ignore an error */
+				/* au_pin_hdir_relock(cpg->pin); */
+				inode_unlock(dst_inode);
+				goto out_rev;
+			}
+		}
+		au_set_ibtop(inode, cpg->bdst);
+	} else
+		au_set_ibbot(inode, cpg->bdst);
+	au_set_h_iptr(inode, cpg->bdst, au_igrab(dst_inode),
+		      au_hi_flags(inode, isdir));
+
+	/* todo: necessary? */
+	/* err = au_pin_hdir_relock(cpg->pin); */
+	inode_unlock(dst_inode);
+	if (unlikely(err))
+		goto out_rev;
+
+	src_inode = d_inode(h_src);
+	if (!isdir
+	    && (src_inode->i_nlink > 1
+		|| src_inode->i_state & I_LINKABLE)
+	    && plink)
+		au_plink_append(inode, cpg->bdst, h_dst);
+
+	if (au_ftest_cpup(cpg->flags, RENAME)) {
+		a->h_path.dentry = h_dst;
+		err = au_do_ren_after_cpup(cpg, &a->h_path);
+	}
+	if (!err)
+		goto out_parent; /* success */
+
+	/* revert */
+out_rev:
+	a->h_path.dentry = h_parent;
+	au_dtime_store(&a->dt, dst_parent, &a->h_path);
+	a->h_path.dentry = h_dst;
+	rerr = 0;
+	if (d_is_positive(h_dst)) {
+		if (!isdir) {
+			/* no delegation since it is just created */
+			rerr = vfsub_unlink(h_dir, &a->h_path,
+					    /*delegated*/NULL, /*force*/0);
+		} else
+			rerr = vfsub_rmdir(h_dir, &a->h_path);
+	}
+	au_dtime_revert(&a->dt);
+	if (rerr) {
+		AuIOErr("failed removing broken entry(%d, %d)\n", err, rerr);
+		err = -EIO;
+	}
+out_parent:
+	dput(dst_parent);
+	kfree(a);
+out:
+	return err;
+}
+
+#if 0 /* reserved */
+struct au_cpup_single_args {
+	int *errp;
+	struct au_cp_generic *cpg;
+	struct dentry *dst_parent;
+};
+
+static void au_call_cpup_single(void *args)
+{
+	struct au_cpup_single_args *a = args;
+
+	au_pin_hdir_acquire_nest(a->cpg->pin);
+	*a->errp = au_cpup_single(a->cpg, a->dst_parent);
+	au_pin_hdir_release(a->cpg->pin);
+}
+#endif
+
+/*
+ * prevent SIGXFSZ in copy-up.
+ * testing CAP_MKNOD is for generic fs,
+ * but CAP_FSETID is for xfs only, currently.
+ */
+static int au_cpup_sio_test(struct au_pin *pin, umode_t mode)
+{
+	int do_sio;
+	struct super_block *sb;
+	struct inode *h_dir;
+
+	do_sio = 0;
+	sb = au_pinned_parent(pin)->d_sb;
+	if (!au_wkq_test()
+	    && (!au_sbi(sb)->si_plink_maint_pid
+		|| au_plink_maint(sb, AuLock_NOPLM))) {
+		switch (mode & S_IFMT) {
+		case S_IFREG:
+			/* no condition about RLIMIT_FSIZE and the file size */
+			do_sio = 1;
+			break;
+		case S_IFCHR:
+		case S_IFBLK:
+			do_sio = !capable(CAP_MKNOD);
+			break;
+		}
+		if (!do_sio)
+			do_sio = ((mode & (S_ISUID | S_ISGID))
+				  && !capable(CAP_FSETID));
+		/* this workaround may be removed in the future */
+		if (!do_sio) {
+			h_dir = au_pinned_h_dir(pin);
+			do_sio = h_dir->i_mode & S_ISVTX;
+		}
+	}
+
+	return do_sio;
+}
+
+#if 0 /* reserved */
+int au_sio_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent)
+{
+	int err, wkq_err;
+	struct dentry *h_dentry;
+
+	h_dentry = au_h_dptr(cpg->dentry, cpg->bsrc);
+	if (!au_cpup_sio_test(pin, d_inode(h_dentry)->i_mode))
+		err = au_cpup_single(cpg, dst_parent);
+	else {
+		struct au_cpup_single_args args = {
+			.errp		= &err,
+			.cpg		= cpg,
+			.dst_parent	= dst_parent
+		};
+		wkq_err = au_wkq_wait(au_call_cpup_single, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+	}
+
+	return err;
+}
+#endif
+
+/*
+ * copyup the @dentry from the first active lower branch to @bdst,
+ * using au_cpup_single().
+ */
+static int au_cpup_simple(struct au_cp_generic *cpg)
+{
+	int err;
+	unsigned int flags_orig;
+	struct dentry *dentry;
+
+	AuDebugOn(cpg->bsrc < 0);
+
+	dentry = cpg->dentry;
+	DiMustWriteLock(dentry);
+
+	err = au_lkup_neg(dentry, cpg->bdst, /*wh*/1);
+	if (!err) {
+		flags_orig = cpg->flags;
+		au_fset_cpup(cpg->flags, RENAME);
+		err = au_cpup_single(cpg, NULL);
+		cpg->flags = flags_orig;
+		if (!err)
+			return 0; /* success */
+
+		/* revert */
+		au_set_h_dptr(dentry, cpg->bdst, NULL);
+		au_set_dbtop(dentry, cpg->bsrc);
+	}
+
+	return err;
+}
+
+struct au_cpup_simple_args {
+	int *errp;
+	struct au_cp_generic *cpg;
+};
+
+static void au_call_cpup_simple(void *args)
+{
+	struct au_cpup_simple_args *a = args;
+
+	au_pin_hdir_acquire_nest(a->cpg->pin);
+	*a->errp = au_cpup_simple(a->cpg);
+	au_pin_hdir_release(a->cpg->pin);
+}
+
+static int au_do_sio_cpup_simple(struct au_cp_generic *cpg)
+{
+	int err, wkq_err;
+	struct dentry *dentry, *parent;
+	struct file *h_file;
+	struct inode *h_dir;
+
+	dentry = cpg->dentry;
+	h_file = NULL;
+	if (au_ftest_cpup(cpg->flags, HOPEN)) {
+		AuDebugOn(cpg->bsrc < 0);
+		h_file = au_h_open_pre(dentry, cpg->bsrc, /*force_wr*/0);
+		err = PTR_ERR(h_file);
+		if (IS_ERR(h_file))
+			goto out;
+	}
+
+	parent = dget_parent(dentry);
+	h_dir = au_h_iptr(d_inode(parent), cpg->bdst);
+	if (!au_test_h_perm_sio(h_dir, MAY_EXEC | MAY_WRITE)
+	    && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode))
+		err = au_cpup_simple(cpg);
+	else {
+		struct au_cpup_simple_args args = {
+			.errp		= &err,
+			.cpg		= cpg
+		};
+		wkq_err = au_wkq_wait(au_call_cpup_simple, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+	}
+
+	dput(parent);
+	if (h_file)
+		au_h_open_post(dentry, cpg->bsrc, h_file);
+
+out:
+	return err;
+}
+
+int au_sio_cpup_simple(struct au_cp_generic *cpg)
+{
+	aufs_bindex_t bsrc, bbot;
+	struct dentry *dentry, *h_dentry;
+
+	if (cpg->bsrc < 0) {
+		dentry = cpg->dentry;
+		bbot = au_dbbot(dentry);
+		for (bsrc = cpg->bdst + 1; bsrc <= bbot; bsrc++) {
+			h_dentry = au_h_dptr(dentry, bsrc);
+			if (h_dentry) {
+				AuDebugOn(d_is_negative(h_dentry));
+				break;
+			}
+		}
+		AuDebugOn(bsrc > bbot);
+		cpg->bsrc = bsrc;
+	}
+	AuDebugOn(cpg->bsrc <= cpg->bdst);
+	return au_do_sio_cpup_simple(cpg);
+}
+
+int au_sio_cpdown_simple(struct au_cp_generic *cpg)
+{
+	AuDebugOn(cpg->bdst <= cpg->bsrc);
+	return au_do_sio_cpup_simple(cpg);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * copyup the deleted file for writing.
+ */
+static int au_do_cpup_wh(struct au_cp_generic *cpg, struct dentry *wh_dentry,
+			 struct file *file)
+{
+	int err;
+	unsigned int flags_orig;
+	aufs_bindex_t bsrc_orig;
+	struct au_dinfo *dinfo;
+	struct {
+		struct au_hdentry *hd;
+		struct dentry *h_dentry;
+	} hdst, hsrc;
+
+	dinfo = au_di(cpg->dentry);
+	AuRwMustWriteLock(&dinfo->di_rwsem);
+
+	bsrc_orig = cpg->bsrc;
+	cpg->bsrc = dinfo->di_btop;
+	hdst.hd = au_hdentry(dinfo, cpg->bdst);
+	hdst.h_dentry = hdst.hd->hd_dentry;
+	hdst.hd->hd_dentry = wh_dentry;
+	dinfo->di_btop = cpg->bdst;
+
+	hsrc.h_dentry = NULL;
+	if (file) {
+		hsrc.hd = au_hdentry(dinfo, cpg->bsrc);
+		hsrc.h_dentry = hsrc.hd->hd_dentry;
+		hsrc.hd->hd_dentry = au_hf_top(file)->f_path.dentry;
+	}
+	flags_orig = cpg->flags;
+	cpg->flags = !AuCpup_DTIME;
+	err = au_cpup_single(cpg, /*h_parent*/NULL);
+	cpg->flags = flags_orig;
+	if (file) {
+		if (!err)
+			err = au_reopen_nondir(file);
+		hsrc.hd->hd_dentry = hsrc.h_dentry;
+	}
+	hdst.hd->hd_dentry = hdst.h_dentry;
+	dinfo->di_btop = cpg->bsrc;
+	cpg->bsrc = bsrc_orig;
+
+	return err;
+}
+
+static int au_cpup_wh(struct au_cp_generic *cpg, struct file *file)
+{
+	int err;
+	aufs_bindex_t bdst;
+	struct au_dtime dt;
+	struct dentry *dentry, *parent, *h_parent, *wh_dentry;
+	struct au_branch *br;
+	struct path h_path;
+
+	dentry = cpg->dentry;
+	bdst = cpg->bdst;
+	br = au_sbr(dentry->d_sb, bdst);
+	parent = dget_parent(dentry);
+	h_parent = au_h_dptr(parent, bdst);
+	wh_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name);
+	err = PTR_ERR(wh_dentry);
+	if (IS_ERR(wh_dentry))
+		goto out;
+
+	h_path.dentry = h_parent;
+	h_path.mnt = au_br_mnt(br);
+	au_dtime_store(&dt, parent, &h_path);
+	err = au_do_cpup_wh(cpg, wh_dentry, file);
+	if (unlikely(err))
+		goto out_wh;
+
+	dget(wh_dentry);
+	h_path.dentry = wh_dentry;
+	if (!d_is_dir(wh_dentry)) {
+		/* no delegation since it is just created */
+		err = vfsub_unlink(d_inode(h_parent), &h_path,
+				   /*delegated*/NULL, /*force*/0);
+	} else
+		err = vfsub_rmdir(d_inode(h_parent), &h_path);
+	if (unlikely(err)) {
+		AuIOErr("failed remove copied-up tmp file %pd(%d)\n",
+			wh_dentry, err);
+		err = -EIO;
+	}
+	au_dtime_revert(&dt);
+	au_set_hi_wh(d_inode(dentry), bdst, wh_dentry);
+
+out_wh:
+	dput(wh_dentry);
+out:
+	dput(parent);
+	return err;
+}
+
+struct au_cpup_wh_args {
+	int *errp;
+	struct au_cp_generic *cpg;
+	struct file *file;
+};
+
+static void au_call_cpup_wh(void *args)
+{
+	struct au_cpup_wh_args *a = args;
+
+	au_pin_hdir_acquire_nest(a->cpg->pin);
+	*a->errp = au_cpup_wh(a->cpg, a->file);
+	au_pin_hdir_release(a->cpg->pin);
+}
+
+int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file)
+{
+	int err, wkq_err;
+	aufs_bindex_t bdst;
+	struct dentry *dentry, *parent, *h_orph, *h_parent;
+	struct inode *dir, *h_dir, *h_tmpdir;
+	struct au_wbr *wbr;
+	struct au_pin wh_pin, *pin_orig;
+
+	dentry = cpg->dentry;
+	bdst = cpg->bdst;
+	parent = dget_parent(dentry);
+	dir = d_inode(parent);
+	h_orph = NULL;
+	h_parent = NULL;
+	h_dir = au_igrab(au_h_iptr(dir, bdst));
+	h_tmpdir = h_dir;
+	pin_orig = NULL;
+	if (!h_dir->i_nlink) {
+		wbr = au_sbr(dentry->d_sb, bdst)->br_wbr;
+		h_orph = wbr->wbr_orph;
+
+		h_parent = dget(au_h_dptr(parent, bdst));
+		au_set_h_dptr(parent, bdst, dget(h_orph));
+		h_tmpdir = d_inode(h_orph);
+		au_set_h_iptr(dir, bdst, au_igrab(h_tmpdir), /*flags*/0);
+
+		inode_lock_nested(h_tmpdir, AuLsc_I_PARENT3);
+		/* todo: au_h_open_pre()? */
+
+		pin_orig = cpg->pin;
+		au_pin_init(&wh_pin, dentry, bdst, AuLsc_DI_PARENT,
+			    AuLsc_I_PARENT3, cpg->pin->udba, AuPin_DI_LOCKED);
+		cpg->pin = &wh_pin;
+	}
+
+	if (!au_test_h_perm_sio(h_tmpdir, MAY_EXEC | MAY_WRITE)
+	    && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode))
+		err = au_cpup_wh(cpg, file);
+	else {
+		struct au_cpup_wh_args args = {
+			.errp	= &err,
+			.cpg	= cpg,
+			.file	= file
+		};
+		wkq_err = au_wkq_wait(au_call_cpup_wh, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+	}
+
+	if (h_orph) {
+		inode_unlock(h_tmpdir);
+		/* todo: au_h_open_post()? */
+		au_set_h_iptr(dir, bdst, au_igrab(h_dir), /*flags*/0);
+		au_set_h_dptr(parent, bdst, h_parent);
+		AuDebugOn(!pin_orig);
+		cpg->pin = pin_orig;
+	}
+	iput(h_dir);
+	dput(parent);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * generic routine for both of copy-up and copy-down.
+ */
+/* cf. revalidate function in file.c */
+int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst,
+	       int (*cp)(struct dentry *dentry, aufs_bindex_t bdst,
+			 struct au_pin *pin,
+			 struct dentry *h_parent, void *arg),
+	       void *arg)
+{
+	int err;
+	struct au_pin pin;
+	struct dentry *d, *parent, *h_parent, *real_parent, *h_dentry;
+
+	err = 0;
+	parent = dget_parent(dentry);
+	if (IS_ROOT(parent))
+		goto out;
+
+	au_pin_init(&pin, dentry, bdst, AuLsc_DI_PARENT2, AuLsc_I_PARENT2,
+		    au_opt_udba(dentry->d_sb), AuPin_MNT_WRITE);
+
+	/* do not use au_dpage */
+	real_parent = parent;
+	while (1) {
+		dput(parent);
+		parent = dget_parent(dentry);
+		h_parent = au_h_dptr(parent, bdst);
+		if (h_parent)
+			goto out; /* success */
+
+		/* find top dir which is necessary to cpup */
+		do {
+			d = parent;
+			dput(parent);
+			parent = dget_parent(d);
+			di_read_lock_parent3(parent, !AuLock_IR);
+			h_parent = au_h_dptr(parent, bdst);
+			di_read_unlock(parent, !AuLock_IR);
+		} while (!h_parent);
+
+		if (d != real_parent)
+			di_write_lock_child3(d);
+
+		/* somebody else might create while we were sleeping */
+		h_dentry = au_h_dptr(d, bdst);
+		if (!h_dentry || d_is_negative(h_dentry)) {
+			if (h_dentry)
+				au_update_dbtop(d);
+
+			au_pin_set_dentry(&pin, d);
+			err = au_do_pin(&pin);
+			if (!err) {
+				err = cp(d, bdst, &pin, h_parent, arg);
+				au_unpin(&pin);
+			}
+		}
+
+		if (d != real_parent)
+			di_write_unlock(d);
+		if (unlikely(err))
+			break;
+	}
+
+out:
+	dput(parent);
+	return err;
+}
+
+static int au_cpup_dir(struct dentry *dentry, aufs_bindex_t bdst,
+		       struct au_pin *pin,
+		       struct dentry *h_parent __maybe_unused,
+		       void *arg __maybe_unused)
+{
+	struct au_cp_generic cpg = {
+		.dentry	= dentry,
+		.bdst	= bdst,
+		.bsrc	= -1,
+		.len	= 0,
+		.pin	= pin,
+		.flags	= AuCpup_DTIME
+	};
+	return au_sio_cpup_simple(&cpg);
+}
+
+int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst)
+{
+	return au_cp_dirs(dentry, bdst, au_cpup_dir, NULL);
+}
+
+int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst)
+{
+	int err;
+	struct dentry *parent;
+	struct inode *dir;
+
+	parent = dget_parent(dentry);
+	dir = d_inode(parent);
+	err = 0;
+	if (au_h_iptr(dir, bdst))
+		goto out;
+
+	di_read_unlock(parent, AuLock_IR);
+	di_write_lock_parent(parent);
+	/* someone else might change our inode while we were sleeping */
+	if (!au_h_iptr(dir, bdst))
+		err = au_cpup_dirs(dentry, bdst);
+	di_downgrade_lock(parent, AuLock_IR);
+
+out:
+	dput(parent);
+	return err;
+}
diff --git a/fs/aufs/cpup.h b/fs/aufs/cpup.h
new file mode 100644
index 000000000000..9c20116cc413
--- /dev/null
+++ b/fs/aufs/cpup.h
@@ -0,0 +1,94 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * copy-up/down functions
+ */
+
+#ifndef __AUFS_CPUP_H__
+#define __AUFS_CPUP_H__
+
+#ifdef __KERNEL__
+
+#include <linux/path.h>
+
+struct inode;
+struct file;
+struct au_pin;
+
+void au_cpup_attr_flags(struct inode *dst, unsigned int iflags);
+void au_cpup_attr_timesizes(struct inode *inode);
+void au_cpup_attr_nlink(struct inode *inode, int force);
+void au_cpup_attr_changeable(struct inode *inode);
+void au_cpup_igen(struct inode *inode, struct inode *h_inode);
+void au_cpup_attr_all(struct inode *inode, int force);
+
+/* ---------------------------------------------------------------------- */
+
+struct au_cp_generic {
+	struct dentry	*dentry;
+	aufs_bindex_t	bdst, bsrc;
+	loff_t		len;
+	struct au_pin	*pin;
+	unsigned int	flags;
+};
+
+/* cpup flags */
+#define AuCpup_DTIME		1		/* do dtime_store/revert */
+#define AuCpup_KEEPLINO		(1 << 1)	/* do not clear the lower xino,
+						   for link(2) */
+#define AuCpup_RENAME		(1 << 2)	/* rename after cpup */
+#define AuCpup_HOPEN		(1 << 3)	/* call h_open_pre/post() in
+						   cpup */
+#define AuCpup_OVERWRITE	(1 << 4)	/* allow overwriting the
+						   existing entry */
+#define AuCpup_RWDST		(1 << 5)	/* force write target even if
+						   the branch is marked as RO */
+
+#define au_ftest_cpup(flags, name)	((flags) & AuCpup_##name)
+#define au_fset_cpup(flags, name) \
+	do { (flags) |= AuCpup_##name; } while (0)
+#define au_fclr_cpup(flags, name) \
+	do { (flags) &= ~AuCpup_##name; } while (0)
+
+int au_copy_file(struct file *dst, struct file *src, loff_t len);
+int au_sio_cpup_simple(struct au_cp_generic *cpg);
+int au_sio_cpdown_simple(struct au_cp_generic *cpg);
+int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file);
+
+int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst,
+	       int (*cp)(struct dentry *dentry, aufs_bindex_t bdst,
+			 struct au_pin *pin,
+			 struct dentry *h_parent, void *arg),
+	       void *arg);
+int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst);
+int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst);
+
+/* ---------------------------------------------------------------------- */
+
+/* keep timestamps when copyup */
+struct au_dtime {
+	struct dentry *dt_dentry;
+	struct path dt_h_path;
+	struct timespec dt_atime, dt_mtime;
+};
+void au_dtime_store(struct au_dtime *dt, struct dentry *dentry,
+		    struct path *h_path);
+void au_dtime_revert(struct au_dtime *dt);
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_CPUP_H__ */
diff --git a/fs/aufs/dbgaufs.c b/fs/aufs/dbgaufs.c
new file mode 100644
index 000000000000..dde0f9151a0a
--- /dev/null
+++ b/fs/aufs/dbgaufs.c
@@ -0,0 +1,438 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * debugfs interface
+ */
+
+#include <linux/debugfs.h>
+#include "aufs.h"
+
+#ifndef CONFIG_SYSFS
+#error DEBUG_FS depends upon SYSFS
+#endif
+
+static struct dentry *dbgaufs;
+static const mode_t dbgaufs_mode = S_IRUSR | S_IRGRP | S_IROTH;
+
+/* 20 is max digits length of ulong 64 */
+struct dbgaufs_arg {
+	int n;
+	char a[20 * 4];
+};
+
+/*
+ * common function for all XINO files
+ */
+static int dbgaufs_xi_release(struct inode *inode __maybe_unused,
+			      struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static int dbgaufs_xi_open(struct file *xf, struct file *file, int do_fcnt)
+{
+	int err;
+	struct kstat st;
+	struct dbgaufs_arg *p;
+
+	err = -ENOMEM;
+	p = kmalloc(sizeof(*p), GFP_NOFS);
+	if (unlikely(!p))
+		goto out;
+
+	err = 0;
+	p->n = 0;
+	file->private_data = p;
+	if (!xf)
+		goto out;
+
+	err = vfsub_getattr(&xf->f_path, &st);
+	if (!err) {
+		if (do_fcnt)
+			p->n = snprintf
+				(p->a, sizeof(p->a), "%ld, %llux%u %lld\n",
+				 (long)file_count(xf), st.blocks, st.blksize,
+				 (long long)st.size);
+		else
+			p->n = snprintf(p->a, sizeof(p->a), "%llux%u %lld\n",
+					st.blocks, st.blksize,
+					(long long)st.size);
+		AuDebugOn(p->n >= sizeof(p->a));
+	} else {
+		p->n = snprintf(p->a, sizeof(p->a), "err %d\n", err);
+		err = 0;
+	}
+
+out:
+	return err;
+
+}
+
+static ssize_t dbgaufs_xi_read(struct file *file, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	struct dbgaufs_arg *p;
+
+	p = file->private_data;
+	return simple_read_from_buffer(buf, count, ppos, p->a, p->n);
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct dbgaufs_plink_arg {
+	int n;
+	char a[];
+};
+
+static int dbgaufs_plink_release(struct inode *inode __maybe_unused,
+				 struct file *file)
+{
+	free_page((unsigned long)file->private_data);
+	return 0;
+}
+
+static int dbgaufs_plink_open(struct inode *inode, struct file *file)
+{
+	int err, i, limit;
+	unsigned long n, sum;
+	struct dbgaufs_plink_arg *p;
+	struct au_sbinfo *sbinfo;
+	struct super_block *sb;
+	struct au_sphlhead *sphl;
+
+	err = -ENOMEM;
+	p = (void *)get_zeroed_page(GFP_NOFS);
+	if (unlikely(!p))
+		goto out;
+
+	err = -EFBIG;
+	sbinfo = inode->i_private;
+	sb = sbinfo->si_sb;
+	si_noflush_read_lock(sb);
+	if (au_opt_test(au_mntflags(sb), PLINK)) {
+		limit = PAGE_SIZE - sizeof(p->n);
+
+		/* the number of buckets */
+		n = snprintf(p->a + p->n, limit, "%d\n", AuPlink_NHASH);
+		p->n += n;
+		limit -= n;
+
+		sum = 0;
+		for (i = 0, sphl = sbinfo->si_plink;
+		     i < AuPlink_NHASH;
+		     i++, sphl++) {
+			n = au_sphl_count(sphl);
+			sum += n;
+
+			n = snprintf(p->a + p->n, limit, "%lu ", n);
+			p->n += n;
+			limit -= n;
+			if (unlikely(limit <= 0))
+				goto out_free;
+		}
+		p->a[p->n - 1] = '\n';
+
+		/* the sum of plinks */
+		n = snprintf(p->a + p->n, limit, "%lu\n", sum);
+		p->n += n;
+		limit -= n;
+		if (unlikely(limit <= 0))
+			goto out_free;
+	} else {
+#define str "1\n0\n0\n"
+		p->n = sizeof(str) - 1;
+		strcpy(p->a, str);
+#undef str
+	}
+	si_read_unlock(sb);
+
+	err = 0;
+	file->private_data = p;
+	goto out; /* success */
+
+out_free:
+	free_page((unsigned long)p);
+out:
+	return err;
+}
+
+static ssize_t dbgaufs_plink_read(struct file *file, char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct dbgaufs_plink_arg *p;
+
+	p = file->private_data;
+	return simple_read_from_buffer(buf, count, ppos, p->a, p->n);
+}
+
+static const struct file_operations dbgaufs_plink_fop = {
+	.owner		= THIS_MODULE,
+	.open		= dbgaufs_plink_open,
+	.release	= dbgaufs_plink_release,
+	.read		= dbgaufs_plink_read
+};
+
+/* ---------------------------------------------------------------------- */
+
+static int dbgaufs_xib_open(struct inode *inode, struct file *file)
+{
+	int err;
+	struct au_sbinfo *sbinfo;
+	struct super_block *sb;
+
+	sbinfo = inode->i_private;
+	sb = sbinfo->si_sb;
+	si_noflush_read_lock(sb);
+	err = dbgaufs_xi_open(sbinfo->si_xib, file, /*do_fcnt*/0);
+	si_read_unlock(sb);
+	return err;
+}
+
+static const struct file_operations dbgaufs_xib_fop = {
+	.owner		= THIS_MODULE,
+	.open		= dbgaufs_xib_open,
+	.release	= dbgaufs_xi_release,
+	.read		= dbgaufs_xi_read
+};
+
+/* ---------------------------------------------------------------------- */
+
+#define DbgaufsXi_PREFIX "xi"
+
+static int dbgaufs_xino_open(struct inode *inode, struct file *file)
+{
+	int err;
+	long l;
+	struct au_sbinfo *sbinfo;
+	struct super_block *sb;
+	struct file *xf;
+	struct qstr *name;
+
+	err = -ENOENT;
+	xf = NULL;
+	name = &file->f_path.dentry->d_name;
+	if (unlikely(name->len < sizeof(DbgaufsXi_PREFIX)
+		     || memcmp(name->name, DbgaufsXi_PREFIX,
+			       sizeof(DbgaufsXi_PREFIX) - 1)))
+		goto out;
+	err = kstrtol(name->name + sizeof(DbgaufsXi_PREFIX) - 1, 10, &l);
+	if (unlikely(err))
+		goto out;
+
+	sbinfo = inode->i_private;
+	sb = sbinfo->si_sb;
+	si_noflush_read_lock(sb);
+	if (l <= au_sbbot(sb)) {
+		xf = au_sbr(sb, (aufs_bindex_t)l)->br_xino.xi_file;
+		err = dbgaufs_xi_open(xf, file, /*do_fcnt*/1);
+	} else
+		err = -ENOENT;
+	si_read_unlock(sb);
+
+out:
+	return err;
+}
+
+static const struct file_operations dbgaufs_xino_fop = {
+	.owner		= THIS_MODULE,
+	.open		= dbgaufs_xino_open,
+	.release	= dbgaufs_xi_release,
+	.read		= dbgaufs_xi_read
+};
+
+void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex)
+{
+	aufs_bindex_t bbot;
+	struct au_branch *br;
+	struct au_xino_file *xi;
+
+	if (!au_sbi(sb)->si_dbgaufs)
+		return;
+
+	bbot = au_sbbot(sb);
+	for (; bindex <= bbot; bindex++) {
+		br = au_sbr(sb, bindex);
+		xi = &br->br_xino;
+		/* debugfs acquires the parent i_mutex */
+		lockdep_off();
+		debugfs_remove(xi->xi_dbgaufs);
+		lockdep_on();
+		xi->xi_dbgaufs = NULL;
+	}
+}
+
+void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex)
+{
+	struct au_sbinfo *sbinfo;
+	struct dentry *parent;
+	struct au_branch *br;
+	struct au_xino_file *xi;
+	aufs_bindex_t bbot;
+	char name[sizeof(DbgaufsXi_PREFIX) + 5]; /* "xi" bindex NULL */
+
+	sbinfo = au_sbi(sb);
+	parent = sbinfo->si_dbgaufs;
+	if (!parent)
+		return;
+
+	bbot = au_sbbot(sb);
+	for (; bindex <= bbot; bindex++) {
+		snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d", bindex);
+		br = au_sbr(sb, bindex);
+		xi = &br->br_xino;
+		AuDebugOn(xi->xi_dbgaufs);
+		/* debugfs acquires the parent i_mutex */
+		lockdep_off();
+		xi->xi_dbgaufs = debugfs_create_file(name, dbgaufs_mode, parent,
+						     sbinfo, &dbgaufs_xino_fop);
+		lockdep_on();
+		/* ignore an error */
+		if (unlikely(!xi->xi_dbgaufs))
+			AuWarn1("failed %s under debugfs\n", name);
+	}
+}
+
+/* ---------------------------------------------------------------------- */
+
+#ifdef CONFIG_AUFS_EXPORT
+static int dbgaufs_xigen_open(struct inode *inode, struct file *file)
+{
+	int err;
+	struct au_sbinfo *sbinfo;
+	struct super_block *sb;
+
+	sbinfo = inode->i_private;
+	sb = sbinfo->si_sb;
+	si_noflush_read_lock(sb);
+	err = dbgaufs_xi_open(sbinfo->si_xigen, file, /*do_fcnt*/0);
+	si_read_unlock(sb);
+	return err;
+}
+
+static const struct file_operations dbgaufs_xigen_fop = {
+	.owner		= THIS_MODULE,
+	.open		= dbgaufs_xigen_open,
+	.release	= dbgaufs_xi_release,
+	.read		= dbgaufs_xi_read
+};
+
+static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo)
+{
+	int err;
+
+	/*
+	 * This function is a dynamic '__init' function actually,
+	 * so the tiny check for si_rwsem is unnecessary.
+	 */
+	/* AuRwMustWriteLock(&sbinfo->si_rwsem); */
+
+	err = -EIO;
+	sbinfo->si_dbgaufs_xigen = debugfs_create_file
+		("xigen", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo,
+		 &dbgaufs_xigen_fop);
+	if (sbinfo->si_dbgaufs_xigen)
+		err = 0;
+
+	return err;
+}
+#else
+static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo)
+{
+	return 0;
+}
+#endif /* CONFIG_AUFS_EXPORT */
+
+/* ---------------------------------------------------------------------- */
+
+void dbgaufs_si_fin(struct au_sbinfo *sbinfo)
+{
+	/*
+	 * This function is a dynamic '__fin' function actually,
+	 * so the tiny check for si_rwsem is unnecessary.
+	 */
+	/* AuRwMustWriteLock(&sbinfo->si_rwsem); */
+
+	debugfs_remove_recursive(sbinfo->si_dbgaufs);
+	sbinfo->si_dbgaufs = NULL;
+	kobject_put(&sbinfo->si_kobj);
+}
+
+int dbgaufs_si_init(struct au_sbinfo *sbinfo)
+{
+	int err;
+	char name[SysaufsSiNameLen];
+
+	/*
+	 * This function is a dynamic '__init' function actually,
+	 * so the tiny check for si_rwsem is unnecessary.
+	 */
+	/* AuRwMustWriteLock(&sbinfo->si_rwsem); */
+
+	err = -ENOENT;
+	if (!dbgaufs) {
+		AuErr1("/debug/aufs is uninitialized\n");
+		goto out;
+	}
+
+	err = -EIO;
+	sysaufs_name(sbinfo, name);
+	sbinfo->si_dbgaufs = debugfs_create_dir(name, dbgaufs);
+	if (unlikely(!sbinfo->si_dbgaufs))
+		goto out;
+	kobject_get(&sbinfo->si_kobj);
+
+	sbinfo->si_dbgaufs_xib = debugfs_create_file
+		("xib", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo,
+		 &dbgaufs_xib_fop);
+	if (unlikely(!sbinfo->si_dbgaufs_xib))
+		goto out_dir;
+
+	sbinfo->si_dbgaufs_plink = debugfs_create_file
+		("plink", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo,
+		 &dbgaufs_plink_fop);
+	if (unlikely(!sbinfo->si_dbgaufs_plink))
+		goto out_dir;
+
+	err = dbgaufs_xigen_init(sbinfo);
+	if (!err)
+		goto out; /* success */
+
+out_dir:
+	dbgaufs_si_fin(sbinfo);
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void dbgaufs_fin(void)
+{
+	debugfs_remove(dbgaufs);
+}
+
+int __init dbgaufs_init(void)
+{
+	int err;
+
+	err = -EIO;
+	dbgaufs = debugfs_create_dir(AUFS_NAME, NULL);
+	if (dbgaufs)
+		err = 0;
+	return err;
+}
diff --git a/fs/aufs/dbgaufs.h b/fs/aufs/dbgaufs.h
new file mode 100644
index 000000000000..d0c01c89c878
--- /dev/null
+++ b/fs/aufs/dbgaufs.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * debugfs interface
+ */
+
+#ifndef __DBGAUFS_H__
+#define __DBGAUFS_H__
+
+#ifdef __KERNEL__
+
+struct super_block;
+struct au_sbinfo;
+
+#ifdef CONFIG_DEBUG_FS
+/* dbgaufs.c */
+void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex);
+void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex);
+void dbgaufs_si_fin(struct au_sbinfo *sbinfo);
+int dbgaufs_si_init(struct au_sbinfo *sbinfo);
+void dbgaufs_fin(void);
+int __init dbgaufs_init(void);
+#else
+AuStubVoid(dbgaufs_brs_del, struct super_block *sb, aufs_bindex_t bindex)
+AuStubVoid(dbgaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex)
+AuStubVoid(dbgaufs_si_fin, struct au_sbinfo *sbinfo)
+AuStubInt0(dbgaufs_si_init, struct au_sbinfo *sbinfo)
+AuStubVoid(dbgaufs_fin, void)
+AuStubInt0(__init dbgaufs_init, void)
+#endif /* CONFIG_DEBUG_FS */
+
+#endif /* __KERNEL__ */
+#endif /* __DBGAUFS_H__ */
diff --git a/fs/aufs/dcsub.c b/fs/aufs/dcsub.c
new file mode 100644
index 000000000000..0e02131bd6f3
--- /dev/null
+++ b/fs/aufs/dcsub.c
@@ -0,0 +1,225 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * sub-routines for dentry cache
+ */
+
+#include "aufs.h"
+
+static void au_dpage_free(struct au_dpage *dpage)
+{
+	int i;
+	struct dentry **p;
+
+	p = dpage->dentries;
+	for (i = 0; i < dpage->ndentry; i++)
+		dput(*p++);
+	free_page((unsigned long)dpage->dentries);
+}
+
+int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp)
+{
+	int err;
+	void *p;
+
+	err = -ENOMEM;
+	dpages->dpages = kmalloc(sizeof(*dpages->dpages), gfp);
+	if (unlikely(!dpages->dpages))
+		goto out;
+
+	p = (void *)__get_free_page(gfp);
+	if (unlikely(!p))
+		goto out_dpages;
+
+	dpages->dpages[0].ndentry = 0;
+	dpages->dpages[0].dentries = p;
+	dpages->ndpage = 1;
+	return 0; /* success */
+
+out_dpages:
+	kfree(dpages->dpages);
+out:
+	return err;
+}
+
+void au_dpages_free(struct au_dcsub_pages *dpages)
+{
+	int i;
+	struct au_dpage *p;
+
+	p = dpages->dpages;
+	for (i = 0; i < dpages->ndpage; i++)
+		au_dpage_free(p++);
+	kfree(dpages->dpages);
+}
+
+static int au_dpages_append(struct au_dcsub_pages *dpages,
+			    struct dentry *dentry, gfp_t gfp)
+{
+	int err, sz;
+	struct au_dpage *dpage;
+	void *p;
+
+	dpage = dpages->dpages + dpages->ndpage - 1;
+	sz = PAGE_SIZE / sizeof(dentry);
+	if (unlikely(dpage->ndentry >= sz)) {
+		AuLabel(new dpage);
+		err = -ENOMEM;
+		sz = dpages->ndpage * sizeof(*dpages->dpages);
+		p = au_kzrealloc(dpages->dpages, sz,
+				 sz + sizeof(*dpages->dpages), gfp,
+				 /*may_shrink*/0);
+		if (unlikely(!p))
+			goto out;
+
+		dpages->dpages = p;
+		dpage = dpages->dpages + dpages->ndpage;
+		p = (void *)__get_free_page(gfp);
+		if (unlikely(!p))
+			goto out;
+
+		dpage->ndentry = 0;
+		dpage->dentries = p;
+		dpages->ndpage++;
+	}
+
+	AuDebugOn(au_dcount(dentry) <= 0);
+	dpage->dentries[dpage->ndentry++] = dget_dlock(dentry);
+	return 0; /* success */
+
+out:
+	return err;
+}
+
+/* todo: BAD approach */
+/* copied from linux/fs/dcache.c */
+enum d_walk_ret {
+	D_WALK_CONTINUE,
+	D_WALK_QUIT,
+	D_WALK_NORETRY,
+	D_WALK_SKIP,
+};
+
+extern void d_walk(struct dentry *parent, void *data,
+		   enum d_walk_ret (*enter)(void *, struct dentry *),
+		   void (*finish)(void *));
+
+struct ac_dpages_arg {
+	int err;
+	struct au_dcsub_pages *dpages;
+	struct super_block *sb;
+	au_dpages_test test;
+	void *arg;
+};
+
+static enum d_walk_ret au_call_dpages_append(void *_arg, struct dentry *dentry)
+{
+	enum d_walk_ret ret;
+	struct ac_dpages_arg *arg = _arg;
+
+	ret = D_WALK_CONTINUE;
+	if (dentry->d_sb == arg->sb
+	    && !IS_ROOT(dentry)
+	    && au_dcount(dentry) > 0
+	    && au_di(dentry)
+	    && (!arg->test || arg->test(dentry, arg->arg))) {
+		arg->err = au_dpages_append(arg->dpages, dentry, GFP_ATOMIC);
+		if (unlikely(arg->err))
+			ret = D_WALK_QUIT;
+	}
+
+	return ret;
+}
+
+int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root,
+		   au_dpages_test test, void *arg)
+{
+	struct ac_dpages_arg args = {
+		.err	= 0,
+		.dpages	= dpages,
+		.sb	= root->d_sb,
+		.test	= test,
+		.arg	= arg
+	};
+
+	d_walk(root, &args, au_call_dpages_append, NULL);
+
+	return args.err;
+}
+
+int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry,
+		       int do_include, au_dpages_test test, void *arg)
+{
+	int err;
+
+	err = 0;
+	write_seqlock(&rename_lock);
+	spin_lock(&dentry->d_lock);
+	if (do_include
+	    && au_dcount(dentry) > 0
+	    && (!test || test(dentry, arg)))
+		err = au_dpages_append(dpages, dentry, GFP_ATOMIC);
+	spin_unlock(&dentry->d_lock);
+	if (unlikely(err))
+		goto out;
+
+	/*
+	 * RCU for vfsmount is unnecessary since this is a traverse in a single
+	 * mount
+	 */
+	while (!IS_ROOT(dentry)) {
+		dentry = dentry->d_parent; /* rename_lock is locked */
+		spin_lock(&dentry->d_lock);
+		if (au_dcount(dentry) > 0
+		    && (!test || test(dentry, arg)))
+			err = au_dpages_append(dpages, dentry, GFP_ATOMIC);
+		spin_unlock(&dentry->d_lock);
+		if (unlikely(err))
+			break;
+	}
+
+out:
+	write_sequnlock(&rename_lock);
+	return err;
+}
+
+static inline int au_dcsub_dpages_aufs(struct dentry *dentry, void *arg)
+{
+	return au_di(dentry) && dentry->d_sb == arg;
+}
+
+int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages,
+			    struct dentry *dentry, int do_include)
+{
+	return au_dcsub_pages_rev(dpages, dentry, do_include,
+				  au_dcsub_dpages_aufs, dentry->d_sb);
+}
+
+int au_test_subdir(struct dentry *d1, struct dentry *d2)
+{
+	struct path path[2] = {
+		{
+			.dentry = d1
+		},
+		{
+			.dentry = d2
+		}
+	};
+
+	return path_is_under(path + 0, path + 1);
+}
diff --git a/fs/aufs/dcsub.h b/fs/aufs/dcsub.h
new file mode 100644
index 000000000000..92d6f91107d1
--- /dev/null
+++ b/fs/aufs/dcsub.h
@@ -0,0 +1,136 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * sub-routines for dentry cache
+ */
+
+#ifndef __AUFS_DCSUB_H__
+#define __AUFS_DCSUB_H__
+
+#ifdef __KERNEL__
+
+#include <linux/dcache.h>
+#include <linux/fs.h>
+
+struct au_dpage {
+	int ndentry;
+	struct dentry **dentries;
+};
+
+struct au_dcsub_pages {
+	int ndpage;
+	struct au_dpage *dpages;
+};
+
+/* ---------------------------------------------------------------------- */
+
+/* dcsub.c */
+int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp);
+void au_dpages_free(struct au_dcsub_pages *dpages);
+typedef int (*au_dpages_test)(struct dentry *dentry, void *arg);
+int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root,
+		   au_dpages_test test, void *arg);
+int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry,
+		       int do_include, au_dpages_test test, void *arg);
+int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages,
+			    struct dentry *dentry, int do_include);
+int au_test_subdir(struct dentry *d1, struct dentry *d2);
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * todo: in linux-3.13, several similar (but faster) helpers are added to
+ * include/linux/dcache.h. Try them (in the future).
+ */
+
+static inline int au_d_hashed_positive(struct dentry *d)
+{
+	int err;
+	struct inode *inode = d_inode(d);
+
+	err = 0;
+	if (unlikely(d_unhashed(d)
+		     || d_is_negative(d)
+		     || !inode->i_nlink))
+		err = -ENOENT;
+	return err;
+}
+
+static inline int au_d_linkable(struct dentry *d)
+{
+	int err;
+	struct inode *inode = d_inode(d);
+
+	err = au_d_hashed_positive(d);
+	if (err
+	    && d_is_positive(d)
+	    && (inode->i_state & I_LINKABLE))
+		err = 0;
+	return err;
+}
+
+static inline int au_d_alive(struct dentry *d)
+{
+	int err;
+	struct inode *inode;
+
+	err = 0;
+	if (!IS_ROOT(d))
+		err = au_d_hashed_positive(d);
+	else {
+		inode = d_inode(d);
+		if (unlikely(d_unlinked(d)
+			     || d_is_negative(d)
+			     || !inode->i_nlink))
+			err = -ENOENT;
+	}
+	return err;
+}
+
+static inline int au_alive_dir(struct dentry *d)
+{
+	int err;
+
+	err = au_d_alive(d);
+	if (unlikely(err || IS_DEADDIR(d_inode(d))))
+		err = -ENOENT;
+	return err;
+}
+
+static inline int au_qstreq(struct qstr *a, struct qstr *b)
+{
+	return a->len == b->len
+		&& !memcmp(a->name, b->name, a->len);
+}
+
+/*
+ * by the commit
+ * 360f547 2015-01-25 dcache: let the dentry count go down to zero without
+ *			taking d_lock
+ * the type of d_lockref.count became int, but the inlined function d_count()
+ * still returns unsigned int.
+ * I don't know why. Maybe it is for every d_count() users?
+ * Anyway au_dcount() lives on.
+ */
+static inline int au_dcount(struct dentry *d)
+{
+	return (int)d_count(d);
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DCSUB_H__ */
diff --git a/fs/aufs/debug.c b/fs/aufs/debug.c
new file mode 100644
index 000000000000..6cfcb14945f6
--- /dev/null
+++ b/fs/aufs/debug.c
@@ -0,0 +1,440 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * debug print functions
+ */
+
+#include "aufs.h"
+
+/* Returns 0, or -errno.  arg is in kp->arg. */
+static int param_atomic_t_set(const char *val, const struct kernel_param *kp)
+{
+	int err, n;
+
+	err = kstrtoint(val, 0, &n);
+	if (!err) {
+		if (n > 0)
+			au_debug_on();
+		else
+			au_debug_off();
+	}
+	return err;
+}
+
+/* Returns length written or -errno.  Buffer is 4k (ie. be short!) */
+static int param_atomic_t_get(char *buffer, const struct kernel_param *kp)
+{
+	atomic_t *a;
+
+	a = kp->arg;
+	return sprintf(buffer, "%d", atomic_read(a));
+}
+
+static struct kernel_param_ops param_ops_atomic_t = {
+	.set = param_atomic_t_set,
+	.get = param_atomic_t_get
+	/* void (*free)(void *arg) */
+};
+
+atomic_t aufs_debug = ATOMIC_INIT(0);
+MODULE_PARM_DESC(debug, "debug print");
+module_param_named(debug, aufs_debug, atomic_t, S_IRUGO | S_IWUSR | S_IWGRP);
+
+DEFINE_MUTEX(au_dbg_mtx);	/* just to serialize the dbg msgs */
+char *au_plevel = KERN_DEBUG;
+#define dpri(fmt, ...) do {					\
+	if ((au_plevel						\
+	     && strcmp(au_plevel, KERN_DEBUG))			\
+	    || au_debug_test())					\
+		printk("%s" fmt, au_plevel, ##__VA_ARGS__);	\
+} while (0)
+
+/* ---------------------------------------------------------------------- */
+
+void au_dpri_whlist(struct au_nhash *whlist)
+{
+	unsigned long ul, n;
+	struct hlist_head *head;
+	struct au_vdir_wh *pos;
+
+	n = whlist->nh_num;
+	head = whlist->nh_head;
+	for (ul = 0; ul < n; ul++) {
+		hlist_for_each_entry(pos, head, wh_hash)
+			dpri("b%d, %.*s, %d\n",
+			     pos->wh_bindex,
+			     pos->wh_str.len, pos->wh_str.name,
+			     pos->wh_str.len);
+		head++;
+	}
+}
+
+void au_dpri_vdir(struct au_vdir *vdir)
+{
+	unsigned long ul;
+	union au_vdir_deblk_p p;
+	unsigned char *o;
+
+	if (!vdir || IS_ERR(vdir)) {
+		dpri("err %ld\n", PTR_ERR(vdir));
+		return;
+	}
+
+	dpri("deblk %u, nblk %lu, deblk %p, last{%lu, %p}, ver %lu\n",
+	     vdir->vd_deblk_sz, vdir->vd_nblk, vdir->vd_deblk,
+	     vdir->vd_last.ul, vdir->vd_last.p.deblk, vdir->vd_version);
+	for (ul = 0; ul < vdir->vd_nblk; ul++) {
+		p.deblk = vdir->vd_deblk[ul];
+		o = p.deblk;
+		dpri("[%lu]: %p\n", ul, o);
+	}
+}
+
+static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode, int hn,
+			struct dentry *wh)
+{
+	char *n = NULL;
+	int l = 0;
+
+	if (!inode || IS_ERR(inode)) {
+		dpri("i%d: err %ld\n", bindex, PTR_ERR(inode));
+		return -1;
+	}
+
+	/* the type of i_blocks depends upon CONFIG_LBDAF */
+	BUILD_BUG_ON(sizeof(inode->i_blocks) != sizeof(unsigned long)
+		     && sizeof(inode->i_blocks) != sizeof(u64));
+	if (wh) {
+		n = (void *)wh->d_name.name;
+		l = wh->d_name.len;
+	}
+
+	dpri("i%d: %p, i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu,"
+	     " hn %d, ct %lld, np %lu, st 0x%lx, f 0x%x, v %llu, g %x%s%.*s\n",
+	     bindex, inode,
+	     inode->i_ino, inode->i_sb ? au_sbtype(inode->i_sb) : "??",
+	     atomic_read(&inode->i_count), inode->i_nlink, inode->i_mode,
+	     i_size_read(inode), (unsigned long long)inode->i_blocks,
+	     hn, (long long)timespec_to_ns(&inode->i_ctime) & 0x0ffff,
+	     inode->i_mapping ? inode->i_mapping->nrpages : 0,
+	     inode->i_state, inode->i_flags, inode->i_version,
+	     inode->i_generation,
+	     l ? ", wh " : "", l, n);
+	return 0;
+}
+
+void au_dpri_inode(struct inode *inode)
+{
+	struct au_iinfo *iinfo;
+	struct au_hinode *hi;
+	aufs_bindex_t bindex;
+	int err, hn;
+
+	err = do_pri_inode(-1, inode, -1, NULL);
+	if (err || !au_test_aufs(inode->i_sb) || au_is_bad_inode(inode))
+		return;
+
+	iinfo = au_ii(inode);
+	dpri("i-1: btop %d, bbot %d, gen %d\n",
+	     iinfo->ii_btop, iinfo->ii_bbot, au_iigen(inode, NULL));
+	if (iinfo->ii_btop < 0)
+		return;
+	hn = 0;
+	for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot; bindex++) {
+		hi = au_hinode(iinfo, bindex);
+		hn = !!au_hn(hi);
+		do_pri_inode(bindex, hi->hi_inode, hn, hi->hi_whdentry);
+	}
+}
+
+void au_dpri_dalias(struct inode *inode)
+{
+	struct dentry *d;
+
+	spin_lock(&inode->i_lock);
+	hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias)
+		au_dpri_dentry(d);
+	spin_unlock(&inode->i_lock);
+}
+
+static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry)
+{
+	struct dentry *wh = NULL;
+	int hn;
+	struct inode *inode;
+	struct au_iinfo *iinfo;
+	struct au_hinode *hi;
+
+	if (!dentry || IS_ERR(dentry)) {
+		dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry));
+		return -1;
+	}
+	/* do not call dget_parent() here */
+	/* note: access d_xxx without d_lock */
+	dpri("d%d: %p, %pd2?, %s, cnt %d, flags 0x%x, %shashed\n",
+	     bindex, dentry, dentry,
+	     dentry->d_sb ? au_sbtype(dentry->d_sb) : "??",
+	     au_dcount(dentry), dentry->d_flags,
+	     d_unhashed(dentry) ? "un" : "");
+	hn = -1;
+	inode = NULL;
+	if (d_is_positive(dentry))
+		inode = d_inode(dentry);
+	if (inode
+	    && au_test_aufs(dentry->d_sb)
+	    && bindex >= 0
+	    && !au_is_bad_inode(inode)) {
+		iinfo = au_ii(inode);
+		hi = au_hinode(iinfo, bindex);
+		hn = !!au_hn(hi);
+		wh = hi->hi_whdentry;
+	}
+	do_pri_inode(bindex, inode, hn, wh);
+	return 0;
+}
+
+void au_dpri_dentry(struct dentry *dentry)
+{
+	struct au_dinfo *dinfo;
+	aufs_bindex_t bindex;
+	int err;
+
+	err = do_pri_dentry(-1, dentry);
+	if (err || !au_test_aufs(dentry->d_sb))
+		return;
+
+	dinfo = au_di(dentry);
+	if (!dinfo)
+		return;
+	dpri("d-1: btop %d, bbot %d, bwh %d, bdiropq %d, gen %d, tmp %d\n",
+	     dinfo->di_btop, dinfo->di_bbot,
+	     dinfo->di_bwh, dinfo->di_bdiropq, au_digen(dentry),
+	     dinfo->di_tmpfile);
+	if (dinfo->di_btop < 0)
+		return;
+	for (bindex = dinfo->di_btop; bindex <= dinfo->di_bbot; bindex++)
+		do_pri_dentry(bindex, au_hdentry(dinfo, bindex)->hd_dentry);
+}
+
+static int do_pri_file(aufs_bindex_t bindex, struct file *file)
+{
+	char a[32];
+
+	if (!file || IS_ERR(file)) {
+		dpri("f%d: err %ld\n", bindex, PTR_ERR(file));
+		return -1;
+	}
+	a[0] = 0;
+	if (bindex < 0
+	    && !IS_ERR_OR_NULL(file->f_path.dentry)
+	    && au_test_aufs(file->f_path.dentry->d_sb)
+	    && au_fi(file))
+		snprintf(a, sizeof(a), ", gen %d, mmapped %d",
+			 au_figen(file), atomic_read(&au_fi(file)->fi_mmapped));
+	dpri("f%d: mode 0x%x, flags 0%o, cnt %ld, v %llu, pos %llu%s\n",
+	     bindex, file->f_mode, file->f_flags, (long)file_count(file),
+	     file->f_version, file->f_pos, a);
+	if (!IS_ERR_OR_NULL(file->f_path.dentry))
+		do_pri_dentry(bindex, file->f_path.dentry);
+	return 0;
+}
+
+void au_dpri_file(struct file *file)
+{
+	struct au_finfo *finfo;
+	struct au_fidir *fidir;
+	struct au_hfile *hfile;
+	aufs_bindex_t bindex;
+	int err;
+
+	err = do_pri_file(-1, file);
+	if (err
+	    || IS_ERR_OR_NULL(file->f_path.dentry)
+	    || !au_test_aufs(file->f_path.dentry->d_sb))
+		return;
+
+	finfo = au_fi(file);
+	if (!finfo)
+		return;
+	if (finfo->fi_btop < 0)
+		return;
+	fidir = finfo->fi_hdir;
+	if (!fidir)
+		do_pri_file(finfo->fi_btop, finfo->fi_htop.hf_file);
+	else
+		for (bindex = finfo->fi_btop;
+		     bindex >= 0 && bindex <= fidir->fd_bbot;
+		     bindex++) {
+			hfile = fidir->fd_hfile + bindex;
+			do_pri_file(bindex, hfile ? hfile->hf_file : NULL);
+		}
+}
+
+static int do_pri_br(aufs_bindex_t bindex, struct au_branch *br)
+{
+	struct vfsmount *mnt;
+	struct super_block *sb;
+
+	if (!br || IS_ERR(br))
+		goto out;
+	mnt = au_br_mnt(br);
+	if (!mnt || IS_ERR(mnt))
+		goto out;
+	sb = mnt->mnt_sb;
+	if (!sb || IS_ERR(sb))
+		goto out;
+
+	dpri("s%d: {perm 0x%x, id %d, cnt %lld, wbr %p}, "
+	     "%s, dev 0x%02x%02x, flags 0x%lx, cnt %d, active %d, "
+	     "xino %d\n",
+	     bindex, br->br_perm, br->br_id, au_br_count(br),
+	     br->br_wbr, au_sbtype(sb), MAJOR(sb->s_dev), MINOR(sb->s_dev),
+	     sb->s_flags, sb->s_count,
+	     atomic_read(&sb->s_active), !!br->br_xino.xi_file);
+	return 0;
+
+out:
+	dpri("s%d: err %ld\n", bindex, PTR_ERR(br));
+	return -1;
+}
+
+void au_dpri_sb(struct super_block *sb)
+{
+	struct au_sbinfo *sbinfo;
+	aufs_bindex_t bindex;
+	int err;
+	/* to reuduce stack size */
+	struct {
+		struct vfsmount mnt;
+		struct au_branch fake;
+	} *a;
+
+	/* this function can be called from magic sysrq */
+	a = kzalloc(sizeof(*a), GFP_ATOMIC);
+	if (unlikely(!a)) {
+		dpri("no memory\n");
+		return;
+	}
+
+	a->mnt.mnt_sb = sb;
+	a->fake.br_path.mnt = &a->mnt;
+	au_br_count_init(&a->fake);
+	err = do_pri_br(-1, &a->fake);
+	au_br_count_fin(&a->fake);
+	kfree(a);
+	dpri("dev 0x%x\n", sb->s_dev);
+	if (err || !au_test_aufs(sb))
+		return;
+
+	sbinfo = au_sbi(sb);
+	if (!sbinfo)
+		return;
+	dpri("nw %d, gen %u, kobj %d\n",
+	     atomic_read(&sbinfo->si_nowait.nw_len), sbinfo->si_generation,
+	     kref_read(&sbinfo->si_kobj.kref));
+	for (bindex = 0; bindex <= sbinfo->si_bbot; bindex++)
+		do_pri_br(bindex, sbinfo->si_branch[0 + bindex]);
+}
+
+/* ---------------------------------------------------------------------- */
+
+void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line)
+{
+	struct inode *h_inode, *inode = d_inode(dentry);
+	struct dentry *h_dentry;
+	aufs_bindex_t bindex, bbot, bi;
+
+	if (!inode /* || au_di(dentry)->di_lsc == AuLsc_DI_TMP */)
+		return;
+
+	bbot = au_dbbot(dentry);
+	bi = au_ibbot(inode);
+	if (bi < bbot)
+		bbot = bi;
+	bindex = au_dbtop(dentry);
+	bi = au_ibtop(inode);
+	if (bi > bindex)
+		bindex = bi;
+
+	for (; bindex <= bbot; bindex++) {
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (!h_dentry)
+			continue;
+		h_inode = au_h_iptr(inode, bindex);
+		if (unlikely(h_inode != d_inode(h_dentry))) {
+			au_debug_on();
+			AuDbg("b%d, %s:%d\n", bindex, func, line);
+			AuDbgDentry(dentry);
+			AuDbgInode(inode);
+			au_debug_off();
+			BUG();
+		}
+	}
+}
+
+void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen)
+{
+	int err, i, j;
+	struct au_dcsub_pages dpages;
+	struct au_dpage *dpage;
+	struct dentry **dentries;
+
+	err = au_dpages_init(&dpages, GFP_NOFS);
+	AuDebugOn(err);
+	err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/1);
+	AuDebugOn(err);
+	for (i = dpages.ndpage - 1; !err && i >= 0; i--) {
+		dpage = dpages.dpages + i;
+		dentries = dpage->dentries;
+		for (j = dpage->ndentry - 1; !err && j >= 0; j--)
+			AuDebugOn(au_digen_test(dentries[j], sigen));
+	}
+	au_dpages_free(&dpages);
+}
+
+void au_dbg_verify_kthread(void)
+{
+	if (au_wkq_test()) {
+		au_dbg_blocked();
+		/*
+		 * It may be recursive, but udba=notify between two aufs mounts,
+		 * where a single ro branch is shared, is not a problem.
+		 */
+		/* WARN_ON(1); */
+	}
+}
+
+/* ---------------------------------------------------------------------- */
+
+int __init au_debug_init(void)
+{
+	aufs_bindex_t bindex;
+	struct au_vdir_destr destr;
+
+	bindex = -1;
+	AuDebugOn(bindex >= 0);
+
+	destr.len = -1;
+	AuDebugOn(destr.len < NAME_MAX);
+
+#ifdef CONFIG_4KSTACKS
+	pr_warn("CONFIG_4KSTACKS is defined.\n");
+#endif
+
+	return 0;
+}
diff --git a/fs/aufs/debug.h b/fs/aufs/debug.h
new file mode 100644
index 000000000000..270628d747bb
--- /dev/null
+++ b/fs/aufs/debug.h
@@ -0,0 +1,225 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * debug print functions
+ */
+
+#ifndef __AUFS_DEBUG_H__
+#define __AUFS_DEBUG_H__
+
+#ifdef __KERNEL__
+
+#include <linux/atomic.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/sysrq.h>
+
+#ifdef CONFIG_AUFS_DEBUG
+#define AuDebugOn(a)		BUG_ON(a)
+
+/* module parameter */
+extern atomic_t aufs_debug;
+static inline void au_debug_on(void)
+{
+	atomic_inc(&aufs_debug);
+}
+static inline void au_debug_off(void)
+{
+	atomic_dec_if_positive(&aufs_debug);
+}
+
+static inline int au_debug_test(void)
+{
+	return atomic_read(&aufs_debug) > 0;
+}
+#else
+#define AuDebugOn(a)		do {} while (0)
+AuStubVoid(au_debug_on, void)
+AuStubVoid(au_debug_off, void)
+AuStubInt0(au_debug_test, void)
+#endif /* CONFIG_AUFS_DEBUG */
+
+#define param_check_atomic_t(name, p) __param_check(name, p, atomic_t)
+
+/* ---------------------------------------------------------------------- */
+
+/* debug print */
+
+#define AuDbg(fmt, ...) do { \
+	if (au_debug_test()) \
+		pr_debug("DEBUG: " fmt, ##__VA_ARGS__); \
+} while (0)
+#define AuLabel(l)		AuDbg(#l "\n")
+#define AuIOErr(fmt, ...)	pr_err("I/O Error, " fmt, ##__VA_ARGS__)
+#define AuWarn1(fmt, ...) do { \
+	static unsigned char _c; \
+	if (!_c++) \
+		pr_warn(fmt, ##__VA_ARGS__); \
+} while (0)
+
+#define AuErr1(fmt, ...) do { \
+	static unsigned char _c; \
+	if (!_c++) \
+		pr_err(fmt, ##__VA_ARGS__); \
+} while (0)
+
+#define AuIOErr1(fmt, ...) do { \
+	static unsigned char _c; \
+	if (!_c++) \
+		AuIOErr(fmt, ##__VA_ARGS__); \
+} while (0)
+
+#define AuUnsupportMsg	"This operation is not supported." \
+			" Please report this application to aufs-users ML."
+#define AuUnsupport(fmt, ...) do { \
+	pr_err(AuUnsupportMsg "\n" fmt, ##__VA_ARGS__); \
+	dump_stack(); \
+} while (0)
+
+#define AuTraceErr(e) do { \
+	if (unlikely((e) < 0)) \
+		AuDbg("err %d\n", (int)(e)); \
+} while (0)
+
+#define AuTraceErrPtr(p) do { \
+	if (IS_ERR(p)) \
+		AuDbg("err %ld\n", PTR_ERR(p)); \
+} while (0)
+
+/* dirty macros for debug print, use with "%.*s" and caution */
+#define AuLNPair(qstr)		(qstr)->len, (qstr)->name
+
+/* ---------------------------------------------------------------------- */
+
+struct dentry;
+#ifdef CONFIG_AUFS_DEBUG
+extern struct mutex au_dbg_mtx;
+extern char *au_plevel;
+struct au_nhash;
+void au_dpri_whlist(struct au_nhash *whlist);
+struct au_vdir;
+void au_dpri_vdir(struct au_vdir *vdir);
+struct inode;
+void au_dpri_inode(struct inode *inode);
+void au_dpri_dalias(struct inode *inode);
+void au_dpri_dentry(struct dentry *dentry);
+struct file;
+void au_dpri_file(struct file *filp);
+struct super_block;
+void au_dpri_sb(struct super_block *sb);
+
+#define au_dbg_verify_dinode(d) __au_dbg_verify_dinode(d, __func__, __LINE__)
+void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line);
+void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen);
+void au_dbg_verify_kthread(void);
+
+int __init au_debug_init(void);
+
+#define AuDbgWhlist(w) do { \
+	mutex_lock(&au_dbg_mtx); \
+	AuDbg(#w "\n"); \
+	au_dpri_whlist(w); \
+	mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgVdir(v) do { \
+	mutex_lock(&au_dbg_mtx); \
+	AuDbg(#v "\n"); \
+	au_dpri_vdir(v); \
+	mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgInode(i) do { \
+	mutex_lock(&au_dbg_mtx); \
+	AuDbg(#i "\n"); \
+	au_dpri_inode(i); \
+	mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgDAlias(i) do { \
+	mutex_lock(&au_dbg_mtx); \
+	AuDbg(#i "\n"); \
+	au_dpri_dalias(i); \
+	mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgDentry(d) do { \
+	mutex_lock(&au_dbg_mtx); \
+	AuDbg(#d "\n"); \
+	au_dpri_dentry(d); \
+	mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgFile(f) do { \
+	mutex_lock(&au_dbg_mtx); \
+	AuDbg(#f "\n"); \
+	au_dpri_file(f); \
+	mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgSb(sb) do { \
+	mutex_lock(&au_dbg_mtx); \
+	AuDbg(#sb "\n"); \
+	au_dpri_sb(sb); \
+	mutex_unlock(&au_dbg_mtx); \
+} while (0)
+
+#define AuDbgSym(addr) do {				\
+	char sym[KSYM_SYMBOL_LEN];			\
+	sprint_symbol(sym, (unsigned long)addr);	\
+	AuDbg("%s\n", sym);				\
+} while (0)
+#else
+AuStubVoid(au_dbg_verify_dinode, struct dentry *dentry)
+AuStubVoid(au_dbg_verify_gen, struct dentry *parent, unsigned int sigen)
+AuStubVoid(au_dbg_verify_kthread, void)
+AuStubInt0(__init au_debug_init, void)
+
+#define AuDbgWhlist(w)		do {} while (0)
+#define AuDbgVdir(v)		do {} while (0)
+#define AuDbgInode(i)		do {} while (0)
+#define AuDbgDAlias(i)		do {} while (0)
+#define AuDbgDentry(d)		do {} while (0)
+#define AuDbgFile(f)		do {} while (0)
+#define AuDbgSb(sb)		do {} while (0)
+#define AuDbgSym(addr)		do {} while (0)
+#endif /* CONFIG_AUFS_DEBUG */
+
+/* ---------------------------------------------------------------------- */
+
+#ifdef CONFIG_AUFS_MAGIC_SYSRQ
+int __init au_sysrq_init(void);
+void au_sysrq_fin(void);
+
+#ifdef CONFIG_HW_CONSOLE
+#define au_dbg_blocked() do { \
+	WARN_ON(1); \
+	handle_sysrq('w'); \
+} while (0)
+#else
+AuStubVoid(au_dbg_blocked, void)
+#endif
+
+#else
+AuStubInt0(__init au_sysrq_init, void)
+AuStubVoid(au_sysrq_fin, void)
+AuStubVoid(au_dbg_blocked, void)
+#endif /* CONFIG_AUFS_MAGIC_SYSRQ */
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DEBUG_H__ */
diff --git a/fs/aufs/dentry.c b/fs/aufs/dentry.c
new file mode 100644
index 000000000000..95ae92aab1fe
--- /dev/null
+++ b/fs/aufs/dentry.c
@@ -0,0 +1,1130 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * lookup and dentry operations
+ */
+
+#include <linux/namei.h>
+#include "aufs.h"
+
+struct au_do_lookup_args {
+	unsigned int		flags;
+	mode_t			type;
+};
+
+/*
+ * returns positive/negative dentry, NULL or an error.
+ * NULL means whiteout-ed or not-found.
+ */
+static struct dentry*
+au_do_lookup(struct dentry *h_parent, struct dentry *dentry,
+	     aufs_bindex_t bindex, struct qstr *wh_name,
+	     struct au_do_lookup_args *args)
+{
+	struct dentry *h_dentry;
+	struct inode *h_inode;
+	struct au_branch *br;
+	int wh_found, opq;
+	unsigned char wh_able;
+	const unsigned char allow_neg = !!au_ftest_lkup(args->flags, ALLOW_NEG);
+	const unsigned char ignore_perm = !!au_ftest_lkup(args->flags,
+							  IGNORE_PERM);
+
+	wh_found = 0;
+	br = au_sbr(dentry->d_sb, bindex);
+	wh_able = !!au_br_whable(br->br_perm);
+	if (wh_able)
+		wh_found = au_wh_test(h_parent, wh_name, ignore_perm);
+	h_dentry = ERR_PTR(wh_found);
+	if (!wh_found)
+		goto real_lookup;
+	if (unlikely(wh_found < 0))
+		goto out;
+
+	/* We found a whiteout */
+	/* au_set_dbbot(dentry, bindex); */
+	au_set_dbwh(dentry, bindex);
+	if (!allow_neg)
+		return NULL; /* success */
+
+real_lookup:
+	if (!ignore_perm)
+		h_dentry = vfsub_lkup_one(&dentry->d_name, h_parent);
+	else
+		h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent);
+	if (IS_ERR(h_dentry)) {
+		if (PTR_ERR(h_dentry) == -ENAMETOOLONG
+		    && !allow_neg)
+			h_dentry = NULL;
+		goto out;
+	}
+
+	h_inode = d_inode(h_dentry);
+	if (d_is_negative(h_dentry)) {
+		if (!allow_neg)
+			goto out_neg;
+	} else if (wh_found
+		   || (args->type && args->type != (h_inode->i_mode & S_IFMT)))
+		goto out_neg;
+
+	if (au_dbbot(dentry) <= bindex)
+		au_set_dbbot(dentry, bindex);
+	if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry))
+		au_set_dbtop(dentry, bindex);
+	au_set_h_dptr(dentry, bindex, h_dentry);
+
+	if (!d_is_dir(h_dentry)
+	    || !wh_able
+	    || (d_really_is_positive(dentry) && !d_is_dir(dentry)))
+		goto out; /* success */
+
+	vfsub_inode_lock_shared_nested(h_inode, AuLsc_I_CHILD);
+	opq = au_diropq_test(h_dentry);
+	inode_unlock_shared(h_inode);
+	if (opq > 0)
+		au_set_dbdiropq(dentry, bindex);
+	else if (unlikely(opq < 0)) {
+		au_set_h_dptr(dentry, bindex, NULL);
+		h_dentry = ERR_PTR(opq);
+	}
+	goto out;
+
+out_neg:
+	dput(h_dentry);
+	h_dentry = NULL;
+out:
+	return h_dentry;
+}
+
+static int au_test_shwh(struct super_block *sb, const struct qstr *name)
+{
+	if (unlikely(!au_opt_test(au_mntflags(sb), SHWH)
+		     && !strncmp(name->name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)))
+		return -EPERM;
+	return 0;
+}
+
+/*
+ * returns the number of lower positive dentries,
+ * otherwise an error.
+ * can be called at unlinking with @type is zero.
+ */
+int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop,
+		   unsigned int flags)
+{
+	int npositive, err;
+	aufs_bindex_t bindex, btail, bdiropq;
+	unsigned char isdir, dirperm1;
+	struct qstr whname;
+	struct au_do_lookup_args args = {
+		.flags		= flags
+	};
+	const struct qstr *name = &dentry->d_name;
+	struct dentry *parent;
+	struct super_block *sb;
+
+	sb = dentry->d_sb;
+	err = au_test_shwh(sb, name);
+	if (unlikely(err))
+		goto out;
+
+	err = au_wh_name_alloc(&whname, name);
+	if (unlikely(err))
+		goto out;
+
+	isdir = !!d_is_dir(dentry);
+	dirperm1 = !!au_opt_test(au_mntflags(sb), DIRPERM1);
+
+	npositive = 0;
+	parent = dget_parent(dentry);
+	btail = au_dbtaildir(parent);
+	for (bindex = btop; bindex <= btail; bindex++) {
+		struct dentry *h_parent, *h_dentry;
+		struct inode *h_inode, *h_dir;
+
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (h_dentry) {
+			if (d_is_positive(h_dentry))
+				npositive++;
+			break;
+		}
+		h_parent = au_h_dptr(parent, bindex);
+		if (!h_parent || !d_is_dir(h_parent))
+			continue;
+
+		h_dir = d_inode(h_parent);
+		vfsub_inode_lock_shared_nested(h_dir, AuLsc_I_PARENT);
+		h_dentry = au_do_lookup(h_parent, dentry, bindex, &whname,
+					&args);
+		inode_unlock_shared(h_dir);
+		err = PTR_ERR(h_dentry);
+		if (IS_ERR(h_dentry))
+			goto out_parent;
+		if (h_dentry)
+			au_fclr_lkup(args.flags, ALLOW_NEG);
+		if (dirperm1)
+			au_fset_lkup(args.flags, IGNORE_PERM);
+
+		if (au_dbwh(dentry) == bindex)
+			break;
+		if (!h_dentry)
+			continue;
+		if (d_is_negative(h_dentry))
+			continue;
+		h_inode = d_inode(h_dentry);
+		npositive++;
+		if (!args.type)
+			args.type = h_inode->i_mode & S_IFMT;
+		if (args.type != S_IFDIR)
+			break;
+		else if (isdir) {
+			/* the type of lower may be different */
+			bdiropq = au_dbdiropq(dentry);
+			if (bdiropq >= 0 && bdiropq <= bindex)
+				break;
+		}
+	}
+
+	if (npositive) {
+		AuLabel(positive);
+		au_update_dbtop(dentry);
+	}
+	err = npositive;
+	if (unlikely(!au_opt_test(au_mntflags(sb), UDBA_NONE)
+		     && au_dbtop(dentry) < 0)) {
+		err = -EIO;
+		AuIOErr("both of real entry and whiteout found, %pd, err %d\n",
+			dentry, err);
+	}
+
+out_parent:
+	dput(parent);
+	kfree(whname.name);
+out:
+	return err;
+}
+
+struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent)
+{
+	struct dentry *dentry;
+	int wkq_err;
+
+	if (!au_test_h_perm_sio(d_inode(parent), MAY_EXEC))
+		dentry = vfsub_lkup_one(name, parent);
+	else {
+		struct vfsub_lkup_one_args args = {
+			.errp	= &dentry,
+			.name	= name,
+			.parent	= parent
+		};
+
+		wkq_err = au_wkq_wait(vfsub_call_lkup_one, &args);
+		if (unlikely(wkq_err))
+			dentry = ERR_PTR(wkq_err);
+	}
+
+	return dentry;
+}
+
+/*
+ * lookup @dentry on @bindex which should be negative.
+ */
+int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh)
+{
+	int err;
+	struct dentry *parent, *h_parent, *h_dentry;
+	struct au_branch *br;
+
+	parent = dget_parent(dentry);
+	h_parent = au_h_dptr(parent, bindex);
+	br = au_sbr(dentry->d_sb, bindex);
+	if (wh)
+		h_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name);
+	else
+		h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent);
+	err = PTR_ERR(h_dentry);
+	if (IS_ERR(h_dentry))
+		goto out;
+	if (unlikely(d_is_positive(h_dentry))) {
+		err = -EIO;
+		AuIOErr("%pd should be negative on b%d.\n", h_dentry, bindex);
+		dput(h_dentry);
+		goto out;
+	}
+
+	err = 0;
+	if (bindex < au_dbtop(dentry))
+		au_set_dbtop(dentry, bindex);
+	if (au_dbbot(dentry) < bindex)
+		au_set_dbbot(dentry, bindex);
+	au_set_h_dptr(dentry, bindex, h_dentry);
+
+out:
+	dput(parent);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* subset of struct inode */
+struct au_iattr {
+	unsigned long		i_ino;
+	/* unsigned int		i_nlink; */
+	kuid_t			i_uid;
+	kgid_t			i_gid;
+	u64			i_version;
+/*
+	loff_t			i_size;
+	blkcnt_t		i_blocks;
+*/
+	umode_t			i_mode;
+};
+
+static void au_iattr_save(struct au_iattr *ia, struct inode *h_inode)
+{
+	ia->i_ino = h_inode->i_ino;
+	/* ia->i_nlink = h_inode->i_nlink; */
+	ia->i_uid = h_inode->i_uid;
+	ia->i_gid = h_inode->i_gid;
+	ia->i_version = h_inode->i_version;
+/*
+	ia->i_size = h_inode->i_size;
+	ia->i_blocks = h_inode->i_blocks;
+*/
+	ia->i_mode = (h_inode->i_mode & S_IFMT);
+}
+
+static int au_iattr_test(struct au_iattr *ia, struct inode *h_inode)
+{
+	return ia->i_ino != h_inode->i_ino
+		/* || ia->i_nlink != h_inode->i_nlink */
+		|| !uid_eq(ia->i_uid, h_inode->i_uid)
+		|| !gid_eq(ia->i_gid, h_inode->i_gid)
+		|| ia->i_version != h_inode->i_version
+/*
+		|| ia->i_size != h_inode->i_size
+		|| ia->i_blocks != h_inode->i_blocks
+*/
+		|| ia->i_mode != (h_inode->i_mode & S_IFMT);
+}
+
+static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent,
+			      struct au_branch *br)
+{
+	int err;
+	struct au_iattr ia;
+	struct inode *h_inode;
+	struct dentry *h_d;
+	struct super_block *h_sb;
+
+	err = 0;
+	memset(&ia, -1, sizeof(ia));
+	h_sb = h_dentry->d_sb;
+	h_inode = NULL;
+	if (d_is_positive(h_dentry)) {
+		h_inode = d_inode(h_dentry);
+		au_iattr_save(&ia, h_inode);
+	} else if (au_test_nfs(h_sb) || au_test_fuse(h_sb))
+		/* nfs d_revalidate may return 0 for negative dentry */
+		/* fuse d_revalidate always return 0 for negative dentry */
+		goto out;
+
+	/* main purpose is namei.c:cached_lookup() and d_revalidate */
+	h_d = vfsub_lkup_one(&h_dentry->d_name, h_parent);
+	err = PTR_ERR(h_d);
+	if (IS_ERR(h_d))
+		goto out;
+
+	err = 0;
+	if (unlikely(h_d != h_dentry
+		     || d_inode(h_d) != h_inode
+		     || (h_inode && au_iattr_test(&ia, h_inode))))
+		err = au_busy_or_stale();
+	dput(h_d);
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir,
+		struct dentry *h_parent, struct au_branch *br)
+{
+	int err;
+
+	err = 0;
+	if (udba == AuOpt_UDBA_REVAL
+	    && !au_test_fs_remote(h_dentry->d_sb)) {
+		IMustLock(h_dir);
+		err = (d_inode(h_dentry->d_parent) != h_dir);
+	} else if (udba != AuOpt_UDBA_NONE)
+		err = au_h_verify_dentry(h_dentry, h_parent, br);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_do_refresh_hdentry(struct dentry *dentry, struct dentry *parent)
+{
+	int err;
+	aufs_bindex_t new_bindex, bindex, bbot, bwh, bdiropq;
+	struct au_hdentry tmp, *p, *q;
+	struct au_dinfo *dinfo;
+	struct super_block *sb;
+
+	DiMustWriteLock(dentry);
+
+	sb = dentry->d_sb;
+	dinfo = au_di(dentry);
+	bbot = dinfo->di_bbot;
+	bwh = dinfo->di_bwh;
+	bdiropq = dinfo->di_bdiropq;
+	bindex = dinfo->di_btop;
+	p = au_hdentry(dinfo, bindex);
+	for (; bindex <= bbot; bindex++, p++) {
+		if (!p->hd_dentry)
+			continue;
+
+		new_bindex = au_br_index(sb, p->hd_id);
+		if (new_bindex == bindex)
+			continue;
+
+		if (dinfo->di_bwh == bindex)
+			bwh = new_bindex;
+		if (dinfo->di_bdiropq == bindex)
+			bdiropq = new_bindex;
+		if (new_bindex < 0) {
+			au_hdput(p);
+			p->hd_dentry = NULL;
+			continue;
+		}
+
+		/* swap two lower dentries, and loop again */
+		q = au_hdentry(dinfo, new_bindex);
+		tmp = *q;
+		*q = *p;
+		*p = tmp;
+		if (tmp.hd_dentry) {
+			bindex--;
+			p--;
+		}
+	}
+
+	dinfo->di_bwh = -1;
+	if (bwh >= 0 && bwh <= au_sbbot(sb) && au_sbr_whable(sb, bwh))
+		dinfo->di_bwh = bwh;
+
+	dinfo->di_bdiropq = -1;
+	if (bdiropq >= 0
+	    && bdiropq <= au_sbbot(sb)
+	    && au_sbr_whable(sb, bdiropq))
+		dinfo->di_bdiropq = bdiropq;
+
+	err = -EIO;
+	dinfo->di_btop = -1;
+	dinfo->di_bbot = -1;
+	bbot = au_dbbot(parent);
+	bindex = 0;
+	p = au_hdentry(dinfo, bindex);
+	for (; bindex <= bbot; bindex++, p++)
+		if (p->hd_dentry) {
+			dinfo->di_btop = bindex;
+			break;
+		}
+
+	if (dinfo->di_btop >= 0) {
+		bindex = bbot;
+		p = au_hdentry(dinfo, bindex);
+		for (; bindex >= 0; bindex--, p--)
+			if (p->hd_dentry) {
+				dinfo->di_bbot = bindex;
+				err = 0;
+				break;
+			}
+	}
+
+	return err;
+}
+
+static void au_do_hide(struct dentry *dentry)
+{
+	struct inode *inode;
+
+	if (d_really_is_positive(dentry)) {
+		inode = d_inode(dentry);
+		if (!d_is_dir(dentry)) {
+			if (inode->i_nlink && !d_unhashed(dentry))
+				drop_nlink(inode);
+		} else {
+			clear_nlink(inode);
+			/* stop next lookup */
+			inode->i_flags |= S_DEAD;
+		}
+		smp_mb(); /* necessary? */
+	}
+	d_drop(dentry);
+}
+
+static int au_hide_children(struct dentry *parent)
+{
+	int err, i, j, ndentry;
+	struct au_dcsub_pages dpages;
+	struct au_dpage *dpage;
+	struct dentry *dentry;
+
+	err = au_dpages_init(&dpages, GFP_NOFS);
+	if (unlikely(err))
+		goto out;
+	err = au_dcsub_pages(&dpages, parent, NULL, NULL);
+	if (unlikely(err))
+		goto out_dpages;
+
+	/* in reverse order */
+	for (i = dpages.ndpage - 1; i >= 0; i--) {
+		dpage = dpages.dpages + i;
+		ndentry = dpage->ndentry;
+		for (j = ndentry - 1; j >= 0; j--) {
+			dentry = dpage->dentries[j];
+			if (dentry != parent)
+				au_do_hide(dentry);
+		}
+	}
+
+out_dpages:
+	au_dpages_free(&dpages);
+out:
+	return err;
+}
+
+static void au_hide(struct dentry *dentry)
+{
+	int err;
+
+	AuDbgDentry(dentry);
+	if (d_is_dir(dentry)) {
+		/* shrink_dcache_parent(dentry); */
+		err = au_hide_children(dentry);
+		if (unlikely(err))
+			AuIOErr("%pd, failed hiding children, ignored %d\n",
+				dentry, err);
+	}
+	au_do_hide(dentry);
+}
+
+/*
+ * By adding a dirty branch, a cached dentry may be affected in various ways.
+ *
+ * a dirty branch is added
+ * - on the top of layers
+ * - in the middle of layers
+ * - to the bottom of layers
+ *
+ * on the added branch there exists
+ * - a whiteout
+ * - a diropq
+ * - a same named entry
+ *   + exist
+ *     * negative --> positive
+ *     * positive --> positive
+ *	 - type is unchanged
+ *	 - type is changed
+ *   + doesn't exist
+ *     * negative --> negative
+ *     * positive --> negative (rejected by au_br_del() for non-dir case)
+ * - none
+ */
+static int au_refresh_by_dinfo(struct dentry *dentry, struct au_dinfo *dinfo,
+			       struct au_dinfo *tmp)
+{
+	int err;
+	aufs_bindex_t bindex, bbot;
+	struct {
+		struct dentry *dentry;
+		struct inode *inode;
+		mode_t mode;
+	} orig_h, tmp_h = {
+		.dentry = NULL
+	};
+	struct au_hdentry *hd;
+	struct inode *inode, *h_inode;
+	struct dentry *h_dentry;
+
+	err = 0;
+	AuDebugOn(dinfo->di_btop < 0);
+	orig_h.mode = 0;
+	orig_h.dentry = au_hdentry(dinfo, dinfo->di_btop)->hd_dentry;
+	orig_h.inode = NULL;
+	if (d_is_positive(orig_h.dentry)) {
+		orig_h.inode = d_inode(orig_h.dentry);
+		orig_h.mode = orig_h.inode->i_mode & S_IFMT;
+	}
+	if (tmp->di_btop >= 0) {
+		tmp_h.dentry = au_hdentry(tmp, tmp->di_btop)->hd_dentry;
+		if (d_is_positive(tmp_h.dentry)) {
+			tmp_h.inode = d_inode(tmp_h.dentry);
+			tmp_h.mode = tmp_h.inode->i_mode & S_IFMT;
+		}
+	}
+
+	inode = NULL;
+	if (d_really_is_positive(dentry))
+		inode = d_inode(dentry);
+	if (!orig_h.inode) {
+		AuDbg("nagative originally\n");
+		if (inode) {
+			au_hide(dentry);
+			goto out;
+		}
+		AuDebugOn(inode);
+		AuDebugOn(dinfo->di_btop != dinfo->di_bbot);
+		AuDebugOn(dinfo->di_bdiropq != -1);
+
+		if (!tmp_h.inode) {
+			AuDbg("negative --> negative\n");
+			/* should have only one negative lower */
+			if (tmp->di_btop >= 0
+			    && tmp->di_btop < dinfo->di_btop) {
+				AuDebugOn(tmp->di_btop != tmp->di_bbot);
+				AuDebugOn(dinfo->di_btop != dinfo->di_bbot);
+				au_set_h_dptr(dentry, dinfo->di_btop, NULL);
+				au_di_cp(dinfo, tmp);
+				hd = au_hdentry(tmp, tmp->di_btop);
+				au_set_h_dptr(dentry, tmp->di_btop,
+					      dget(hd->hd_dentry));
+			}
+			au_dbg_verify_dinode(dentry);
+		} else {
+			AuDbg("negative --> positive\n");
+			/*
+			 * similar to the behaviour of creating with bypassing
+			 * aufs.
+			 * unhash it in order to force an error in the
+			 * succeeding create operation.
+			 * we should not set S_DEAD here.
+			 */
+			d_drop(dentry);
+			/* au_di_swap(tmp, dinfo); */
+			au_dbg_verify_dinode(dentry);
+		}
+	} else {
+		AuDbg("positive originally\n");
+		/* inode may be NULL */
+		AuDebugOn(inode && (inode->i_mode & S_IFMT) != orig_h.mode);
+		if (!tmp_h.inode) {
+			AuDbg("positive --> negative\n");
+			/* or bypassing aufs */
+			au_hide(dentry);
+			if (tmp->di_bwh >= 0 && tmp->di_bwh <= dinfo->di_btop)
+				dinfo->di_bwh = tmp->di_bwh;
+			if (inode)
+				err = au_refresh_hinode_self(inode);
+			au_dbg_verify_dinode(dentry);
+		} else if (orig_h.mode == tmp_h.mode) {
+			AuDbg("positive --> positive, same type\n");
+			if (!S_ISDIR(orig_h.mode)
+			    && dinfo->di_btop > tmp->di_btop) {
+				/*
+				 * similar to the behaviour of removing and
+				 * creating.
+				 */
+				au_hide(dentry);
+				if (inode)
+					err = au_refresh_hinode_self(inode);
+				au_dbg_verify_dinode(dentry);
+			} else {
+				/* fill empty slots */
+				if (dinfo->di_btop > tmp->di_btop)
+					dinfo->di_btop = tmp->di_btop;
+				if (dinfo->di_bbot < tmp->di_bbot)
+					dinfo->di_bbot = tmp->di_bbot;
+				dinfo->di_bwh = tmp->di_bwh;
+				dinfo->di_bdiropq = tmp->di_bdiropq;
+				bbot = dinfo->di_bbot;
+				bindex = tmp->di_btop;
+				hd = au_hdentry(tmp, bindex);
+				for (; bindex <= bbot; bindex++, hd++) {
+					if (au_h_dptr(dentry, bindex))
+						continue;
+					h_dentry = hd->hd_dentry;
+					if (!h_dentry)
+						continue;
+					AuDebugOn(d_is_negative(h_dentry));
+					h_inode = d_inode(h_dentry);
+					AuDebugOn(orig_h.mode
+						  != (h_inode->i_mode
+						      & S_IFMT));
+					au_set_h_dptr(dentry, bindex,
+						      dget(h_dentry));
+				}
+				if (inode)
+					err = au_refresh_hinode(inode, dentry);
+				au_dbg_verify_dinode(dentry);
+			}
+		} else {
+			AuDbg("positive --> positive, different type\n");
+			/* similar to the behaviour of removing and creating */
+			au_hide(dentry);
+			if (inode)
+				err = au_refresh_hinode_self(inode);
+			au_dbg_verify_dinode(dentry);
+		}
+	}
+
+out:
+	return err;
+}
+
+void au_refresh_dop(struct dentry *dentry, int force_reval)
+{
+	const struct dentry_operations *dop
+		= force_reval ? &aufs_dop : dentry->d_sb->s_d_op;
+	static const unsigned int mask
+		= DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE;
+
+	BUILD_BUG_ON(sizeof(mask) != sizeof(dentry->d_flags));
+
+	if (dentry->d_op == dop)
+		return;
+
+	AuDbg("%pd\n", dentry);
+	spin_lock(&dentry->d_lock);
+	if (dop == &aufs_dop)
+		dentry->d_flags |= mask;
+	else
+		dentry->d_flags &= ~mask;
+	dentry->d_op = dop;
+	spin_unlock(&dentry->d_lock);
+}
+
+int au_refresh_dentry(struct dentry *dentry, struct dentry *parent)
+{
+	int err, ebrange, nbr;
+	unsigned int sigen;
+	struct au_dinfo *dinfo, *tmp;
+	struct super_block *sb;
+	struct inode *inode;
+
+	DiMustWriteLock(dentry);
+	AuDebugOn(IS_ROOT(dentry));
+	AuDebugOn(d_really_is_negative(parent));
+
+	sb = dentry->d_sb;
+	sigen = au_sigen(sb);
+	err = au_digen_test(parent, sigen);
+	if (unlikely(err))
+		goto out;
+
+	nbr = au_sbbot(sb) + 1;
+	dinfo = au_di(dentry);
+	err = au_di_realloc(dinfo, nbr, /*may_shrink*/0);
+	if (unlikely(err))
+		goto out;
+	ebrange = au_dbrange_test(dentry);
+	if (!ebrange)
+		ebrange = au_do_refresh_hdentry(dentry, parent);
+
+	if (d_unhashed(dentry) || ebrange /* || dinfo->di_tmpfile */) {
+		AuDebugOn(au_dbtop(dentry) < 0 && au_dbbot(dentry) >= 0);
+		if (d_really_is_positive(dentry)) {
+			inode = d_inode(dentry);
+			err = au_refresh_hinode_self(inode);
+		}
+		au_dbg_verify_dinode(dentry);
+		if (!err)
+			goto out_dgen; /* success */
+		goto out;
+	}
+
+	/* temporary dinfo */
+	AuDbgDentry(dentry);
+	err = -ENOMEM;
+	tmp = au_di_alloc(sb, AuLsc_DI_TMP);
+	if (unlikely(!tmp))
+		goto out;
+	au_di_swap(tmp, dinfo);
+	/* returns the number of positive dentries */
+	/*
+	 * if current working dir is removed, it returns an error.
+	 * but the dentry is legal.
+	 */
+	err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG);
+	AuDbgDentry(dentry);
+	au_di_swap(tmp, dinfo);
+	if (err == -ENOENT)
+		err = 0;
+	if (err >= 0) {
+		/* compare/refresh by dinfo */
+		AuDbgDentry(dentry);
+		err = au_refresh_by_dinfo(dentry, dinfo, tmp);
+		au_dbg_verify_dinode(dentry);
+		AuTraceErr(err);
+	}
+	au_di_realloc(dinfo, nbr, /*may_shrink*/1); /* harmless if err */
+	au_rw_write_unlock(&tmp->di_rwsem);
+	au_di_free(tmp);
+	if (unlikely(err))
+		goto out;
+
+out_dgen:
+	au_update_digen(dentry);
+out:
+	if (unlikely(err && !(dentry->d_flags & DCACHE_NFSFS_RENAMED))) {
+		AuIOErr("failed refreshing %pd, %d\n", dentry, err);
+		AuDbgDentry(dentry);
+	}
+	AuTraceErr(err);
+	return err;
+}
+
+static int au_do_h_d_reval(struct dentry *h_dentry, unsigned int flags,
+			   struct dentry *dentry, aufs_bindex_t bindex)
+{
+	int err, valid;
+
+	err = 0;
+	if (!(h_dentry->d_flags & DCACHE_OP_REVALIDATE))
+		goto out;
+
+	AuDbg("b%d\n", bindex);
+	/*
+	 * gave up supporting LOOKUP_CREATE/OPEN for lower fs,
+	 * due to whiteout and branch permission.
+	 */
+	flags &= ~(/*LOOKUP_PARENT |*/ LOOKUP_OPEN | LOOKUP_CREATE
+		   | LOOKUP_FOLLOW | LOOKUP_EXCL);
+	/* it may return tri-state */
+	valid = h_dentry->d_op->d_revalidate(h_dentry, flags);
+
+	if (unlikely(valid < 0))
+		err = valid;
+	else if (!valid)
+		err = -EINVAL;
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/* todo: remove this */
+static int h_d_revalidate(struct dentry *dentry, struct inode *inode,
+			  unsigned int flags, int do_udba)
+{
+	int err;
+	umode_t mode, h_mode;
+	aufs_bindex_t bindex, btail, btop, ibs, ibe;
+	unsigned char plus, unhashed, is_root, h_plus, h_nfs, tmpfile;
+	struct inode *h_inode, *h_cached_inode;
+	struct dentry *h_dentry;
+	struct qstr *name, *h_name;
+
+	err = 0;
+	plus = 0;
+	mode = 0;
+	ibs = -1;
+	ibe = -1;
+	unhashed = !!d_unhashed(dentry);
+	is_root = !!IS_ROOT(dentry);
+	name = &dentry->d_name;
+	tmpfile = au_di(dentry)->di_tmpfile;
+
+	/*
+	 * Theoretically, REVAL test should be unnecessary in case of
+	 * {FS,I}NOTIFY.
+	 * But {fs,i}notify doesn't fire some necessary events,
+	 *	IN_ATTRIB for atime/nlink/pageio
+	 * Let's do REVAL test too.
+	 */
+	if (do_udba && inode) {
+		mode = (inode->i_mode & S_IFMT);
+		plus = (inode->i_nlink > 0);
+		ibs = au_ibtop(inode);
+		ibe = au_ibbot(inode);
+	}
+
+	btop = au_dbtop(dentry);
+	btail = btop;
+	if (inode && S_ISDIR(inode->i_mode))
+		btail = au_dbtaildir(dentry);
+	for (bindex = btop; bindex <= btail; bindex++) {
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (!h_dentry)
+			continue;
+
+		AuDbg("b%d, %pd\n", bindex, h_dentry);
+		h_nfs = !!au_test_nfs(h_dentry->d_sb);
+		spin_lock(&h_dentry->d_lock);
+		h_name = &h_dentry->d_name;
+		if (unlikely(do_udba
+			     && !is_root
+			     && ((!h_nfs
+				  && (unhashed != !!d_unhashed(h_dentry)
+				      || (!tmpfile
+					  && !au_qstreq(name, h_name))
+					  ))
+				 || (h_nfs
+				     && !(flags & LOOKUP_OPEN)
+				     && (h_dentry->d_flags
+					 & DCACHE_NFSFS_RENAMED)))
+			    )) {
+			int h_unhashed;
+
+			h_unhashed = d_unhashed(h_dentry);
+			spin_unlock(&h_dentry->d_lock);
+			AuDbg("unhash 0x%x 0x%x, %pd %pd\n",
+			      unhashed, h_unhashed, dentry, h_dentry);
+			goto err;
+		}
+		spin_unlock(&h_dentry->d_lock);
+
+		err = au_do_h_d_reval(h_dentry, flags, dentry, bindex);
+		if (unlikely(err))
+			/* do not goto err, to keep the errno */
+			break;
+
+		/* todo: plink too? */
+		if (!do_udba)
+			continue;
+
+		/* UDBA tests */
+		if (unlikely(!!inode != d_is_positive(h_dentry)))
+			goto err;
+
+		h_inode = NULL;
+		if (d_is_positive(h_dentry))
+			h_inode = d_inode(h_dentry);
+		h_plus = plus;
+		h_mode = mode;
+		h_cached_inode = h_inode;
+		if (h_inode) {
+			h_mode = (h_inode->i_mode & S_IFMT);
+			h_plus = (h_inode->i_nlink > 0);
+		}
+		if (inode && ibs <= bindex && bindex <= ibe)
+			h_cached_inode = au_h_iptr(inode, bindex);
+
+		if (!h_nfs) {
+			if (unlikely(plus != h_plus && !tmpfile))
+				goto err;
+		} else {
+			if (unlikely(!(h_dentry->d_flags & DCACHE_NFSFS_RENAMED)
+				     && !is_root
+				     && !IS_ROOT(h_dentry)
+				     && unhashed != d_unhashed(h_dentry)))
+				goto err;
+		}
+		if (unlikely(mode != h_mode
+			     || h_cached_inode != h_inode))
+			goto err;
+		continue;
+
+err:
+		err = -EINVAL;
+		break;
+	}
+
+	AuTraceErr(err);
+	return err;
+}
+
+/* todo: consolidate with do_refresh() and au_reval_for_attr() */
+static int simple_reval_dpath(struct dentry *dentry, unsigned int sigen)
+{
+	int err;
+	struct dentry *parent;
+
+	if (!au_digen_test(dentry, sigen))
+		return 0;
+
+	parent = dget_parent(dentry);
+	di_read_lock_parent(parent, AuLock_IR);
+	AuDebugOn(au_digen_test(parent, sigen));
+	au_dbg_verify_gen(parent, sigen);
+	err = au_refresh_dentry(dentry, parent);
+	di_read_unlock(parent, AuLock_IR);
+	dput(parent);
+	AuTraceErr(err);
+	return err;
+}
+
+int au_reval_dpath(struct dentry *dentry, unsigned int sigen)
+{
+	int err;
+	struct dentry *d, *parent;
+
+	if (!au_ftest_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR))
+		return simple_reval_dpath(dentry, sigen);
+
+	/* slow loop, keep it simple and stupid */
+	/* cf: au_cpup_dirs() */
+	err = 0;
+	parent = NULL;
+	while (au_digen_test(dentry, sigen)) {
+		d = dentry;
+		while (1) {
+			dput(parent);
+			parent = dget_parent(d);
+			if (!au_digen_test(parent, sigen))
+				break;
+			d = parent;
+		}
+
+		if (d != dentry)
+			di_write_lock_child2(d);
+
+		/* someone might update our dentry while we were sleeping */
+		if (au_digen_test(d, sigen)) {
+			/*
+			 * todo: consolidate with simple_reval_dpath(),
+			 * do_refresh() and au_reval_for_attr().
+			 */
+			di_read_lock_parent(parent, AuLock_IR);
+			err = au_refresh_dentry(d, parent);
+			di_read_unlock(parent, AuLock_IR);
+		}
+
+		if (d != dentry)
+			di_write_unlock(d);
+		dput(parent);
+		if (unlikely(err))
+			break;
+	}
+
+	return err;
+}
+
+/*
+ * if valid returns 1, otherwise 0.
+ */
+static int aufs_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	int valid, err;
+	unsigned int sigen;
+	unsigned char do_udba;
+	struct super_block *sb;
+	struct inode *inode;
+
+	/* todo: support rcu-walk? */
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	valid = 0;
+	if (unlikely(!au_di(dentry)))
+		goto out;
+
+	valid = 1;
+	sb = dentry->d_sb;
+	/*
+	 * todo: very ugly
+	 * i_mutex of parent dir may be held,
+	 * but we should not return 'invalid' due to busy.
+	 */
+	err = aufs_read_lock(dentry, AuLock_FLUSH | AuLock_DW | AuLock_NOPLM);
+	if (unlikely(err)) {
+		valid = err;
+		AuTraceErr(err);
+		goto out;
+	}
+	inode = NULL;
+	if (d_really_is_positive(dentry))
+		inode = d_inode(dentry);
+	if (unlikely(inode && au_is_bad_inode(inode))) {
+		err = -EINVAL;
+		AuTraceErr(err);
+		goto out_dgrade;
+	}
+	if (unlikely(au_dbrange_test(dentry))) {
+		err = -EINVAL;
+		AuTraceErr(err);
+		goto out_dgrade;
+	}
+
+	sigen = au_sigen(sb);
+	if (au_digen_test(dentry, sigen)) {
+		AuDebugOn(IS_ROOT(dentry));
+		err = au_reval_dpath(dentry, sigen);
+		if (unlikely(err)) {
+			AuTraceErr(err);
+			goto out_dgrade;
+		}
+	}
+	di_downgrade_lock(dentry, AuLock_IR);
+
+	err = -EINVAL;
+	if (!(flags & (LOOKUP_OPEN | LOOKUP_EMPTY))
+	    && inode
+	    && !(inode->i_state && I_LINKABLE)
+	    && (IS_DEADDIR(inode) || !inode->i_nlink)) {
+		AuTraceErr(err);
+		goto out_inval;
+	}
+
+	do_udba = !au_opt_test(au_mntflags(sb), UDBA_NONE);
+	if (do_udba && inode) {
+		aufs_bindex_t btop = au_ibtop(inode);
+		struct inode *h_inode;
+
+		if (btop >= 0) {
+			h_inode = au_h_iptr(inode, btop);
+			if (h_inode && au_test_higen(inode, h_inode)) {
+				AuTraceErr(err);
+				goto out_inval;
+			}
+		}
+	}
+
+	err = h_d_revalidate(dentry, inode, flags, do_udba);
+	if (unlikely(!err && do_udba && au_dbtop(dentry) < 0)) {
+		err = -EIO;
+		AuDbg("both of real entry and whiteout found, %p, err %d\n",
+		      dentry, err);
+	}
+	goto out_inval;
+
+out_dgrade:
+	di_downgrade_lock(dentry, AuLock_IR);
+out_inval:
+	aufs_read_unlock(dentry, AuLock_IR);
+	AuTraceErr(err);
+	valid = !err;
+out:
+	if (!valid) {
+		AuDbg("%pd invalid, %d\n", dentry, valid);
+		d_drop(dentry);
+	}
+	return valid;
+}
+
+static void aufs_d_release(struct dentry *dentry)
+{
+	if (au_di(dentry)) {
+		au_di_fin(dentry);
+		au_hn_di_reinit(dentry);
+	}
+}
+
+const struct dentry_operations aufs_dop = {
+	.d_revalidate		= aufs_d_revalidate,
+	.d_weak_revalidate	= aufs_d_revalidate,
+	.d_release		= aufs_d_release
+};
+
+/* aufs_dop without d_revalidate */
+const struct dentry_operations aufs_dop_noreval = {
+	.d_release		= aufs_d_release
+};
diff --git a/fs/aufs/dentry.h b/fs/aufs/dentry.h
new file mode 100644
index 000000000000..adb40ed5918e
--- /dev/null
+++ b/fs/aufs/dentry.h
@@ -0,0 +1,252 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * lookup and dentry operations
+ */
+
+#ifndef __AUFS_DENTRY_H__
+#define __AUFS_DENTRY_H__
+
+#ifdef __KERNEL__
+
+#include <linux/dcache.h>
+#include "rwsem.h"
+
+struct au_hdentry {
+	struct dentry		*hd_dentry;
+	aufs_bindex_t		hd_id;
+};
+
+struct au_dinfo {
+	atomic_t		di_generation;
+
+	struct au_rwsem		di_rwsem;
+	aufs_bindex_t		di_btop, di_bbot, di_bwh, di_bdiropq;
+	unsigned char		di_tmpfile; /* to allow the different name */
+	struct au_hdentry	*di_hdentry;
+} ____cacheline_aligned_in_smp;
+
+/* ---------------------------------------------------------------------- */
+
+/* flags for au_lkup_dentry() */
+#define AuLkup_ALLOW_NEG	1
+#define AuLkup_IGNORE_PERM	(1 << 1)
+#define au_ftest_lkup(flags, name)	((flags) & AuLkup_##name)
+#define au_fset_lkup(flags, name) \
+	do { (flags) |= AuLkup_##name; } while (0)
+#define au_fclr_lkup(flags, name) \
+	do { (flags) &= ~AuLkup_##name; } while (0)
+
+/* ---------------------------------------------------------------------- */
+
+/* dentry.c */
+extern const struct dentry_operations aufs_dop, aufs_dop_noreval;
+struct au_branch;
+struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent);
+int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir,
+		struct dentry *h_parent, struct au_branch *br);
+
+int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop,
+		   unsigned int flags);
+int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh);
+int au_refresh_dentry(struct dentry *dentry, struct dentry *parent);
+int au_reval_dpath(struct dentry *dentry, unsigned int sigen);
+void au_refresh_dop(struct dentry *dentry, int force_reval);
+
+/* dinfo.c */
+void au_di_init_once(void *_di);
+struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc);
+void au_di_free(struct au_dinfo *dinfo);
+void au_di_swap(struct au_dinfo *a, struct au_dinfo *b);
+void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src);
+int au_di_init(struct dentry *dentry);
+void au_di_fin(struct dentry *dentry);
+int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink);
+
+void di_read_lock(struct dentry *d, int flags, unsigned int lsc);
+void di_read_unlock(struct dentry *d, int flags);
+void di_downgrade_lock(struct dentry *d, int flags);
+void di_write_lock(struct dentry *d, unsigned int lsc);
+void di_write_unlock(struct dentry *d);
+void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir);
+void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir);
+void di_write_unlock2(struct dentry *d1, struct dentry *d2);
+
+struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex);
+struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex);
+aufs_bindex_t au_dbtail(struct dentry *dentry);
+aufs_bindex_t au_dbtaildir(struct dentry *dentry);
+
+void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex,
+		   struct dentry *h_dentry);
+int au_digen_test(struct dentry *dentry, unsigned int sigen);
+int au_dbrange_test(struct dentry *dentry);
+void au_update_digen(struct dentry *dentry);
+void au_update_dbrange(struct dentry *dentry, int do_put_zero);
+void au_update_dbtop(struct dentry *dentry);
+void au_update_dbbot(struct dentry *dentry);
+int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry);
+
+/* ---------------------------------------------------------------------- */
+
+static inline struct au_dinfo *au_di(struct dentry *dentry)
+{
+	return dentry->d_fsdata;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* lock subclass for dinfo */
+enum {
+	AuLsc_DI_CHILD,		/* child first */
+	AuLsc_DI_CHILD2,	/* rename(2), link(2), and cpup at hnotify */
+	AuLsc_DI_CHILD3,	/* copyup dirs */
+	AuLsc_DI_PARENT,
+	AuLsc_DI_PARENT2,
+	AuLsc_DI_PARENT3,
+	AuLsc_DI_TMP		/* temp for replacing dinfo */
+};
+
+/*
+ * di_read_lock_child, di_write_lock_child,
+ * di_read_lock_child2, di_write_lock_child2,
+ * di_read_lock_child3, di_write_lock_child3,
+ * di_read_lock_parent, di_write_lock_parent,
+ * di_read_lock_parent2, di_write_lock_parent2,
+ * di_read_lock_parent3, di_write_lock_parent3,
+ */
+#define AuReadLockFunc(name, lsc) \
+static inline void di_read_lock_##name(struct dentry *d, int flags) \
+{ di_read_lock(d, flags, AuLsc_DI_##lsc); }
+
+#define AuWriteLockFunc(name, lsc) \
+static inline void di_write_lock_##name(struct dentry *d) \
+{ di_write_lock(d, AuLsc_DI_##lsc); }
+
+#define AuRWLockFuncs(name, lsc) \
+	AuReadLockFunc(name, lsc) \
+	AuWriteLockFunc(name, lsc)
+
+AuRWLockFuncs(child, CHILD);
+AuRWLockFuncs(child2, CHILD2);
+AuRWLockFuncs(child3, CHILD3);
+AuRWLockFuncs(parent, PARENT);
+AuRWLockFuncs(parent2, PARENT2);
+AuRWLockFuncs(parent3, PARENT3);
+
+#undef AuReadLockFunc
+#undef AuWriteLockFunc
+#undef AuRWLockFuncs
+
+#define DiMustNoWaiters(d)	AuRwMustNoWaiters(&au_di(d)->di_rwsem)
+#define DiMustAnyLock(d)	AuRwMustAnyLock(&au_di(d)->di_rwsem)
+#define DiMustWriteLock(d)	AuRwMustWriteLock(&au_di(d)->di_rwsem)
+
+/* ---------------------------------------------------------------------- */
+
+/* todo: memory barrier? */
+static inline unsigned int au_digen(struct dentry *d)
+{
+	return atomic_read(&au_di(d)->di_generation);
+}
+
+static inline void au_h_dentry_init(struct au_hdentry *hdentry)
+{
+	hdentry->hd_dentry = NULL;
+}
+
+static inline struct au_hdentry *au_hdentry(struct au_dinfo *di,
+					    aufs_bindex_t bindex)
+{
+	return di->di_hdentry + bindex;
+}
+
+static inline void au_hdput(struct au_hdentry *hd)
+{
+	if (hd)
+		dput(hd->hd_dentry);
+}
+
+static inline aufs_bindex_t au_dbtop(struct dentry *dentry)
+{
+	DiMustAnyLock(dentry);
+	return au_di(dentry)->di_btop;
+}
+
+static inline aufs_bindex_t au_dbbot(struct dentry *dentry)
+{
+	DiMustAnyLock(dentry);
+	return au_di(dentry)->di_bbot;
+}
+
+static inline aufs_bindex_t au_dbwh(struct dentry *dentry)
+{
+	DiMustAnyLock(dentry);
+	return au_di(dentry)->di_bwh;
+}
+
+static inline aufs_bindex_t au_dbdiropq(struct dentry *dentry)
+{
+	DiMustAnyLock(dentry);
+	return au_di(dentry)->di_bdiropq;
+}
+
+/* todo: hard/soft set? */
+static inline void au_set_dbtop(struct dentry *dentry, aufs_bindex_t bindex)
+{
+	DiMustWriteLock(dentry);
+	au_di(dentry)->di_btop = bindex;
+}
+
+static inline void au_set_dbbot(struct dentry *dentry, aufs_bindex_t bindex)
+{
+	DiMustWriteLock(dentry);
+	au_di(dentry)->di_bbot = bindex;
+}
+
+static inline void au_set_dbwh(struct dentry *dentry, aufs_bindex_t bindex)
+{
+	DiMustWriteLock(dentry);
+	/* dbwh can be outside of btop - bbot range */
+	au_di(dentry)->di_bwh = bindex;
+}
+
+static inline void au_set_dbdiropq(struct dentry *dentry, aufs_bindex_t bindex)
+{
+	DiMustWriteLock(dentry);
+	au_di(dentry)->di_bdiropq = bindex;
+}
+
+/* ---------------------------------------------------------------------- */
+
+#ifdef CONFIG_AUFS_HNOTIFY
+static inline void au_digen_dec(struct dentry *d)
+{
+	atomic_dec(&au_di(d)->di_generation);
+}
+
+static inline void au_hn_di_reinit(struct dentry *dentry)
+{
+	dentry->d_fsdata = NULL;
+}
+#else
+AuStubVoid(au_hn_di_reinit, struct dentry *dentry __maybe_unused)
+#endif /* CONFIG_AUFS_HNOTIFY */
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DENTRY_H__ */
diff --git a/fs/aufs/dinfo.c b/fs/aufs/dinfo.c
new file mode 100644
index 000000000000..8b19f94c5654
--- /dev/null
+++ b/fs/aufs/dinfo.c
@@ -0,0 +1,553 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * dentry private data
+ */
+
+#include "aufs.h"
+
+void au_di_init_once(void *_dinfo)
+{
+	struct au_dinfo *dinfo = _dinfo;
+
+	au_rw_init(&dinfo->di_rwsem);
+}
+
+struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc)
+{
+	struct au_dinfo *dinfo;
+	int nbr, i;
+
+	dinfo = au_cache_alloc_dinfo();
+	if (unlikely(!dinfo))
+		goto out;
+
+	nbr = au_sbbot(sb) + 1;
+	if (nbr <= 0)
+		nbr = 1;
+	dinfo->di_hdentry = kcalloc(nbr, sizeof(*dinfo->di_hdentry), GFP_NOFS);
+	if (dinfo->di_hdentry) {
+		au_rw_write_lock_nested(&dinfo->di_rwsem, lsc);
+		dinfo->di_btop = -1;
+		dinfo->di_bbot = -1;
+		dinfo->di_bwh = -1;
+		dinfo->di_bdiropq = -1;
+		dinfo->di_tmpfile = 0;
+		for (i = 0; i < nbr; i++)
+			dinfo->di_hdentry[i].hd_id = -1;
+		goto out;
+	}
+
+	au_cache_free_dinfo(dinfo);
+	dinfo = NULL;
+
+out:
+	return dinfo;
+}
+
+void au_di_free(struct au_dinfo *dinfo)
+{
+	struct au_hdentry *p;
+	aufs_bindex_t bbot, bindex;
+
+	/* dentry may not be revalidated */
+	bindex = dinfo->di_btop;
+	if (bindex >= 0) {
+		bbot = dinfo->di_bbot;
+		p = au_hdentry(dinfo, bindex);
+		while (bindex++ <= bbot)
+			au_hdput(p++);
+	}
+	kfree(dinfo->di_hdentry);
+	au_cache_free_dinfo(dinfo);
+}
+
+void au_di_swap(struct au_dinfo *a, struct au_dinfo *b)
+{
+	struct au_hdentry *p;
+	aufs_bindex_t bi;
+
+	AuRwMustWriteLock(&a->di_rwsem);
+	AuRwMustWriteLock(&b->di_rwsem);
+
+#define DiSwap(v, name)				\
+	do {					\
+		v = a->di_##name;		\
+		a->di_##name = b->di_##name;	\
+		b->di_##name = v;		\
+	} while (0)
+
+	DiSwap(p, hdentry);
+	DiSwap(bi, btop);
+	DiSwap(bi, bbot);
+	DiSwap(bi, bwh);
+	DiSwap(bi, bdiropq);
+	/* smp_mb(); */
+
+#undef DiSwap
+}
+
+void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src)
+{
+	AuRwMustWriteLock(&dst->di_rwsem);
+	AuRwMustWriteLock(&src->di_rwsem);
+
+	dst->di_btop = src->di_btop;
+	dst->di_bbot = src->di_bbot;
+	dst->di_bwh = src->di_bwh;
+	dst->di_bdiropq = src->di_bdiropq;
+	/* smp_mb(); */
+}
+
+int au_di_init(struct dentry *dentry)
+{
+	int err;
+	struct super_block *sb;
+	struct au_dinfo *dinfo;
+
+	err = 0;
+	sb = dentry->d_sb;
+	dinfo = au_di_alloc(sb, AuLsc_DI_CHILD);
+	if (dinfo) {
+		atomic_set(&dinfo->di_generation, au_sigen(sb));
+		/* smp_mb(); */ /* atomic_set */
+		dentry->d_fsdata = dinfo;
+	} else
+		err = -ENOMEM;
+
+	return err;
+}
+
+void au_di_fin(struct dentry *dentry)
+{
+	struct au_dinfo *dinfo;
+
+	dinfo = au_di(dentry);
+	AuRwDestroy(&dinfo->di_rwsem);
+	au_di_free(dinfo);
+}
+
+int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink)
+{
+	int err, sz;
+	struct au_hdentry *hdp;
+
+	AuRwMustWriteLock(&dinfo->di_rwsem);
+
+	err = -ENOMEM;
+	sz = sizeof(*hdp) * (dinfo->di_bbot + 1);
+	if (!sz)
+		sz = sizeof(*hdp);
+	hdp = au_kzrealloc(dinfo->di_hdentry, sz, sizeof(*hdp) * nbr, GFP_NOFS,
+			   may_shrink);
+	if (hdp) {
+		dinfo->di_hdentry = hdp;
+		err = 0;
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void do_ii_write_lock(struct inode *inode, unsigned int lsc)
+{
+	switch (lsc) {
+	case AuLsc_DI_CHILD:
+		ii_write_lock_child(inode);
+		break;
+	case AuLsc_DI_CHILD2:
+		ii_write_lock_child2(inode);
+		break;
+	case AuLsc_DI_CHILD3:
+		ii_write_lock_child3(inode);
+		break;
+	case AuLsc_DI_PARENT:
+		ii_write_lock_parent(inode);
+		break;
+	case AuLsc_DI_PARENT2:
+		ii_write_lock_parent2(inode);
+		break;
+	case AuLsc_DI_PARENT3:
+		ii_write_lock_parent3(inode);
+		break;
+	default:
+		BUG();
+	}
+}
+
+static void do_ii_read_lock(struct inode *inode, unsigned int lsc)
+{
+	switch (lsc) {
+	case AuLsc_DI_CHILD:
+		ii_read_lock_child(inode);
+		break;
+	case AuLsc_DI_CHILD2:
+		ii_read_lock_child2(inode);
+		break;
+	case AuLsc_DI_CHILD3:
+		ii_read_lock_child3(inode);
+		break;
+	case AuLsc_DI_PARENT:
+		ii_read_lock_parent(inode);
+		break;
+	case AuLsc_DI_PARENT2:
+		ii_read_lock_parent2(inode);
+		break;
+	case AuLsc_DI_PARENT3:
+		ii_read_lock_parent3(inode);
+		break;
+	default:
+		BUG();
+	}
+}
+
+void di_read_lock(struct dentry *d, int flags, unsigned int lsc)
+{
+	struct inode *inode;
+
+	au_rw_read_lock_nested(&au_di(d)->di_rwsem, lsc);
+	if (d_really_is_positive(d)) {
+		inode = d_inode(d);
+		if (au_ftest_lock(flags, IW))
+			do_ii_write_lock(inode, lsc);
+		else if (au_ftest_lock(flags, IR))
+			do_ii_read_lock(inode, lsc);
+	}
+}
+
+void di_read_unlock(struct dentry *d, int flags)
+{
+	struct inode *inode;
+
+	if (d_really_is_positive(d)) {
+		inode = d_inode(d);
+		if (au_ftest_lock(flags, IW)) {
+			au_dbg_verify_dinode(d);
+			ii_write_unlock(inode);
+		} else if (au_ftest_lock(flags, IR)) {
+			au_dbg_verify_dinode(d);
+			ii_read_unlock(inode);
+		}
+	}
+	au_rw_read_unlock(&au_di(d)->di_rwsem);
+}
+
+void di_downgrade_lock(struct dentry *d, int flags)
+{
+	if (d_really_is_positive(d) && au_ftest_lock(flags, IR))
+		ii_downgrade_lock(d_inode(d));
+	au_rw_dgrade_lock(&au_di(d)->di_rwsem);
+}
+
+void di_write_lock(struct dentry *d, unsigned int lsc)
+{
+	au_rw_write_lock_nested(&au_di(d)->di_rwsem, lsc);
+	if (d_really_is_positive(d))
+		do_ii_write_lock(d_inode(d), lsc);
+}
+
+void di_write_unlock(struct dentry *d)
+{
+	au_dbg_verify_dinode(d);
+	if (d_really_is_positive(d))
+		ii_write_unlock(d_inode(d));
+	au_rw_write_unlock(&au_di(d)->di_rwsem);
+}
+
+void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir)
+{
+	AuDebugOn(d1 == d2
+		  || d_inode(d1) == d_inode(d2)
+		  || d1->d_sb != d2->d_sb);
+
+	if ((isdir && au_test_subdir(d1, d2))
+	    || d1 < d2) {
+		di_write_lock_child(d1);
+		di_write_lock_child2(d2);
+	} else {
+		di_write_lock_child(d2);
+		di_write_lock_child2(d1);
+	}
+}
+
+void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir)
+{
+	AuDebugOn(d1 == d2
+		  || d_inode(d1) == d_inode(d2)
+		  || d1->d_sb != d2->d_sb);
+
+	if ((isdir && au_test_subdir(d1, d2))
+	    || d1 < d2) {
+		di_write_lock_parent(d1);
+		di_write_lock_parent2(d2);
+	} else {
+		di_write_lock_parent(d2);
+		di_write_lock_parent2(d1);
+	}
+}
+
+void di_write_unlock2(struct dentry *d1, struct dentry *d2)
+{
+	di_write_unlock(d1);
+	if (d_inode(d1) == d_inode(d2))
+		au_rw_write_unlock(&au_di(d2)->di_rwsem);
+	else
+		di_write_unlock(d2);
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex)
+{
+	struct dentry *d;
+
+	DiMustAnyLock(dentry);
+
+	if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry))
+		return NULL;
+	AuDebugOn(bindex < 0);
+	d = au_hdentry(au_di(dentry), bindex)->hd_dentry;
+	AuDebugOn(d && au_dcount(d) <= 0);
+	return d;
+}
+
+/*
+ * extended version of au_h_dptr().
+ * returns a hashed and positive (or linkable) h_dentry in bindex, NULL, or
+ * error.
+ */
+struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex)
+{
+	struct dentry *h_dentry;
+	struct inode *inode, *h_inode;
+
+	AuDebugOn(d_really_is_negative(dentry));
+
+	h_dentry = NULL;
+	if (au_dbtop(dentry) <= bindex
+	    && bindex <= au_dbbot(dentry))
+		h_dentry = au_h_dptr(dentry, bindex);
+	if (h_dentry && !au_d_linkable(h_dentry)) {
+		dget(h_dentry);
+		goto out; /* success */
+	}
+
+	inode = d_inode(dentry);
+	AuDebugOn(bindex < au_ibtop(inode));
+	AuDebugOn(au_ibbot(inode) < bindex);
+	h_inode = au_h_iptr(inode, bindex);
+	h_dentry = d_find_alias(h_inode);
+	if (h_dentry) {
+		if (!IS_ERR(h_dentry)) {
+			if (!au_d_linkable(h_dentry))
+				goto out; /* success */
+			dput(h_dentry);
+		} else
+			goto out;
+	}
+
+	if (au_opt_test(au_mntflags(dentry->d_sb), PLINK)) {
+		h_dentry = au_plink_lkup(inode, bindex);
+		AuDebugOn(!h_dentry);
+		if (!IS_ERR(h_dentry)) {
+			if (!au_d_hashed_positive(h_dentry))
+				goto out; /* success */
+			dput(h_dentry);
+			h_dentry = NULL;
+		}
+	}
+
+out:
+	AuDbgDentry(h_dentry);
+	return h_dentry;
+}
+
+aufs_bindex_t au_dbtail(struct dentry *dentry)
+{
+	aufs_bindex_t bbot, bwh;
+
+	bbot = au_dbbot(dentry);
+	if (0 <= bbot) {
+		bwh = au_dbwh(dentry);
+		if (!bwh)
+			return bwh;
+		if (0 < bwh && bwh < bbot)
+			return bwh - 1;
+	}
+	return bbot;
+}
+
+aufs_bindex_t au_dbtaildir(struct dentry *dentry)
+{
+	aufs_bindex_t bbot, bopq;
+
+	bbot = au_dbtail(dentry);
+	if (0 <= bbot) {
+		bopq = au_dbdiropq(dentry);
+		if (0 <= bopq && bopq < bbot)
+			bbot = bopq;
+	}
+	return bbot;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex,
+		   struct dentry *h_dentry)
+{
+	struct au_dinfo *dinfo;
+	struct au_hdentry *hd;
+	struct au_branch *br;
+
+	DiMustWriteLock(dentry);
+
+	dinfo = au_di(dentry);
+	hd = au_hdentry(dinfo, bindex);
+	au_hdput(hd);
+	hd->hd_dentry = h_dentry;
+	if (h_dentry) {
+		br = au_sbr(dentry->d_sb, bindex);
+		hd->hd_id = br->br_id;
+	}
+}
+
+int au_dbrange_test(struct dentry *dentry)
+{
+	int err;
+	aufs_bindex_t btop, bbot;
+
+	err = 0;
+	btop = au_dbtop(dentry);
+	bbot = au_dbbot(dentry);
+	if (btop >= 0)
+		AuDebugOn(bbot < 0 && btop > bbot);
+	else {
+		err = -EIO;
+		AuDebugOn(bbot >= 0);
+	}
+
+	return err;
+}
+
+int au_digen_test(struct dentry *dentry, unsigned int sigen)
+{
+	int err;
+
+	err = 0;
+	if (unlikely(au_digen(dentry) != sigen
+		     || au_iigen_test(d_inode(dentry), sigen)))
+		err = -EIO;
+
+	return err;
+}
+
+void au_update_digen(struct dentry *dentry)
+{
+	atomic_set(&au_di(dentry)->di_generation, au_sigen(dentry->d_sb));
+	/* smp_mb(); */ /* atomic_set */
+}
+
+void au_update_dbrange(struct dentry *dentry, int do_put_zero)
+{
+	struct au_dinfo *dinfo;
+	struct dentry *h_d;
+	struct au_hdentry *hdp;
+	aufs_bindex_t bindex, bbot;
+
+	DiMustWriteLock(dentry);
+
+	dinfo = au_di(dentry);
+	if (!dinfo || dinfo->di_btop < 0)
+		return;
+
+	if (do_put_zero) {
+		bbot = dinfo->di_bbot;
+		bindex = dinfo->di_btop;
+		hdp = au_hdentry(dinfo, bindex);
+		for (; bindex <= bbot; bindex++, hdp++) {
+			h_d = hdp->hd_dentry;
+			if (h_d && d_is_negative(h_d))
+				au_set_h_dptr(dentry, bindex, NULL);
+		}
+	}
+
+	dinfo->di_btop = 0;
+	hdp = au_hdentry(dinfo, dinfo->di_btop);
+	for (; dinfo->di_btop <= dinfo->di_bbot; dinfo->di_btop++, hdp++)
+		if (hdp->hd_dentry)
+			break;
+	if (dinfo->di_btop > dinfo->di_bbot) {
+		dinfo->di_btop = -1;
+		dinfo->di_bbot = -1;
+		return;
+	}
+
+	hdp = au_hdentry(dinfo, dinfo->di_bbot);
+	for (; dinfo->di_bbot >= 0; dinfo->di_bbot--, hdp--)
+		if (hdp->hd_dentry)
+			break;
+	AuDebugOn(dinfo->di_btop > dinfo->di_bbot || dinfo->di_bbot < 0);
+}
+
+void au_update_dbtop(struct dentry *dentry)
+{
+	aufs_bindex_t bindex, bbot;
+	struct dentry *h_dentry;
+
+	bbot = au_dbbot(dentry);
+	for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) {
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (!h_dentry)
+			continue;
+		if (d_is_positive(h_dentry)) {
+			au_set_dbtop(dentry, bindex);
+			return;
+		}
+		au_set_h_dptr(dentry, bindex, NULL);
+	}
+}
+
+void au_update_dbbot(struct dentry *dentry)
+{
+	aufs_bindex_t bindex, btop;
+	struct dentry *h_dentry;
+
+	btop = au_dbtop(dentry);
+	for (bindex = au_dbbot(dentry); bindex >= btop; bindex--) {
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (!h_dentry)
+			continue;
+		if (d_is_positive(h_dentry)) {
+			au_set_dbbot(dentry, bindex);
+			return;
+		}
+		au_set_h_dptr(dentry, bindex, NULL);
+	}
+}
+
+int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry)
+{
+	aufs_bindex_t bindex, bbot;
+
+	bbot = au_dbbot(dentry);
+	for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++)
+		if (au_h_dptr(dentry, bindex) == h_dentry)
+			return bindex;
+	return -1;
+}
diff --git a/fs/aufs/dir.c b/fs/aufs/dir.c
new file mode 100644
index 000000000000..3ac1e885884b
--- /dev/null
+++ b/fs/aufs/dir.c
@@ -0,0 +1,759 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * directory operations
+ */
+
+#include <linux/fs_stack.h>
+#include "aufs.h"
+
+void au_add_nlink(struct inode *dir, struct inode *h_dir)
+{
+	unsigned int nlink;
+
+	AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode));
+
+	nlink = dir->i_nlink;
+	nlink += h_dir->i_nlink - 2;
+	if (h_dir->i_nlink < 2)
+		nlink += 2;
+	smp_mb(); /* for i_nlink */
+	/* 0 can happen in revaliding */
+	set_nlink(dir, nlink);
+}
+
+void au_sub_nlink(struct inode *dir, struct inode *h_dir)
+{
+	unsigned int nlink;
+
+	AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode));
+
+	nlink = dir->i_nlink;
+	nlink -= h_dir->i_nlink - 2;
+	if (h_dir->i_nlink < 2)
+		nlink -= 2;
+	smp_mb(); /* for i_nlink */
+	/* nlink == 0 means the branch-fs is broken */
+	set_nlink(dir, nlink);
+}
+
+loff_t au_dir_size(struct file *file, struct dentry *dentry)
+{
+	loff_t sz;
+	aufs_bindex_t bindex, bbot;
+	struct file *h_file;
+	struct dentry *h_dentry;
+
+	sz = 0;
+	if (file) {
+		AuDebugOn(!d_is_dir(file->f_path.dentry));
+
+		bbot = au_fbbot_dir(file);
+		for (bindex = au_fbtop(file);
+		     bindex <= bbot && sz < KMALLOC_MAX_SIZE;
+		     bindex++) {
+			h_file = au_hf_dir(file, bindex);
+			if (h_file && file_inode(h_file))
+				sz += vfsub_f_size_read(h_file);
+		}
+	} else {
+		AuDebugOn(!dentry);
+		AuDebugOn(!d_is_dir(dentry));
+
+		bbot = au_dbtaildir(dentry);
+		for (bindex = au_dbtop(dentry);
+		     bindex <= bbot && sz < KMALLOC_MAX_SIZE;
+		     bindex++) {
+			h_dentry = au_h_dptr(dentry, bindex);
+			if (h_dentry && d_is_positive(h_dentry))
+				sz += i_size_read(d_inode(h_dentry));
+		}
+	}
+	if (sz < KMALLOC_MAX_SIZE)
+		sz = roundup_pow_of_two(sz);
+	if (sz > KMALLOC_MAX_SIZE)
+		sz = KMALLOC_MAX_SIZE;
+	else if (sz < NAME_MAX) {
+		BUILD_BUG_ON(AUFS_RDBLK_DEF < NAME_MAX);
+		sz = AUFS_RDBLK_DEF;
+	}
+	return sz;
+}
+
+struct au_dir_ts_arg {
+	struct dentry *dentry;
+	aufs_bindex_t brid;
+};
+
+static void au_do_dir_ts(void *arg)
+{
+	struct au_dir_ts_arg *a = arg;
+	struct au_dtime dt;
+	struct path h_path;
+	struct inode *dir, *h_dir;
+	struct super_block *sb;
+	struct au_branch *br;
+	struct au_hinode *hdir;
+	int err;
+	aufs_bindex_t btop, bindex;
+
+	sb = a->dentry->d_sb;
+	if (d_really_is_negative(a->dentry))
+		goto out;
+	/* no dir->i_mutex lock */
+	aufs_read_lock(a->dentry, AuLock_DW); /* noflush */
+
+	dir = d_inode(a->dentry);
+	btop = au_ibtop(dir);
+	bindex = au_br_index(sb, a->brid);
+	if (bindex < btop)
+		goto out_unlock;
+
+	br = au_sbr(sb, bindex);
+	h_path.dentry = au_h_dptr(a->dentry, bindex);
+	if (!h_path.dentry)
+		goto out_unlock;
+	h_path.mnt = au_br_mnt(br);
+	au_dtime_store(&dt, a->dentry, &h_path);
+
+	br = au_sbr(sb, btop);
+	if (!au_br_writable(br->br_perm))
+		goto out_unlock;
+	h_path.dentry = au_h_dptr(a->dentry, btop);
+	h_path.mnt = au_br_mnt(br);
+	err = vfsub_mnt_want_write(h_path.mnt);
+	if (err)
+		goto out_unlock;
+	hdir = au_hi(dir, btop);
+	au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT);
+	h_dir = au_h_iptr(dir, btop);
+	if (h_dir->i_nlink
+	    && timespec_compare(&h_dir->i_mtime, &dt.dt_mtime) < 0) {
+		dt.dt_h_path = h_path;
+		au_dtime_revert(&dt);
+	}
+	au_hn_inode_unlock(hdir);
+	vfsub_mnt_drop_write(h_path.mnt);
+	au_cpup_attr_timesizes(dir);
+
+out_unlock:
+	aufs_read_unlock(a->dentry, AuLock_DW);
+out:
+	dput(a->dentry);
+	au_nwt_done(&au_sbi(sb)->si_nowait);
+	kfree(arg);
+}
+
+void au_dir_ts(struct inode *dir, aufs_bindex_t bindex)
+{
+	int perm, wkq_err;
+	aufs_bindex_t btop;
+	struct au_dir_ts_arg *arg;
+	struct dentry *dentry;
+	struct super_block *sb;
+
+	IMustLock(dir);
+
+	dentry = d_find_any_alias(dir);
+	AuDebugOn(!dentry);
+	sb = dentry->d_sb;
+	btop = au_ibtop(dir);
+	if (btop == bindex) {
+		au_cpup_attr_timesizes(dir);
+		goto out;
+	}
+
+	perm = au_sbr_perm(sb, btop);
+	if (!au_br_writable(perm))
+		goto out;
+
+	arg = kmalloc(sizeof(*arg), GFP_NOFS);
+	if (!arg)
+		goto out;
+
+	arg->dentry = dget(dentry); /* will be dput-ted by au_do_dir_ts() */
+	arg->brid = au_sbr_id(sb, bindex);
+	wkq_err = au_wkq_nowait(au_do_dir_ts, arg, sb, /*flags*/0);
+	if (unlikely(wkq_err)) {
+		pr_err("wkq %d\n", wkq_err);
+		dput(dentry);
+		kfree(arg);
+	}
+
+out:
+	dput(dentry);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int reopen_dir(struct file *file)
+{
+	int err;
+	unsigned int flags;
+	aufs_bindex_t bindex, btail, btop;
+	struct dentry *dentry, *h_dentry;
+	struct file *h_file;
+
+	/* open all lower dirs */
+	dentry = file->f_path.dentry;
+	btop = au_dbtop(dentry);
+	for (bindex = au_fbtop(file); bindex < btop; bindex++)
+		au_set_h_fptr(file, bindex, NULL);
+	au_set_fbtop(file, btop);
+
+	btail = au_dbtaildir(dentry);
+	for (bindex = au_fbbot_dir(file); btail < bindex; bindex--)
+		au_set_h_fptr(file, bindex, NULL);
+	au_set_fbbot_dir(file, btail);
+
+	flags = vfsub_file_flags(file);
+	for (bindex = btop; bindex <= btail; bindex++) {
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (!h_dentry)
+			continue;
+		h_file = au_hf_dir(file, bindex);
+		if (h_file)
+			continue;
+
+		h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
+		err = PTR_ERR(h_file);
+		if (IS_ERR(h_file))
+			goto out; /* close all? */
+		au_set_h_fptr(file, bindex, h_file);
+	}
+	au_update_figen(file);
+	/* todo: necessary? */
+	/* file->f_ra = h_file->f_ra; */
+	err = 0;
+
+out:
+	return err;
+}
+
+static int do_open_dir(struct file *file, int flags, struct file *h_file)
+{
+	int err;
+	aufs_bindex_t bindex, btail;
+	struct dentry *dentry, *h_dentry;
+	struct vfsmount *mnt;
+
+	FiMustWriteLock(file);
+	AuDebugOn(h_file);
+
+	err = 0;
+	mnt = file->f_path.mnt;
+	dentry = file->f_path.dentry;
+	file->f_version = d_inode(dentry)->i_version;
+	bindex = au_dbtop(dentry);
+	au_set_fbtop(file, bindex);
+	btail = au_dbtaildir(dentry);
+	au_set_fbbot_dir(file, btail);
+	for (; !err && bindex <= btail; bindex++) {
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (!h_dentry)
+			continue;
+
+		err = vfsub_test_mntns(mnt, h_dentry->d_sb);
+		if (unlikely(err))
+			break;
+		h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
+		if (IS_ERR(h_file)) {
+			err = PTR_ERR(h_file);
+			break;
+		}
+		au_set_h_fptr(file, bindex, h_file);
+	}
+	au_update_figen(file);
+	/* todo: necessary? */
+	/* file->f_ra = h_file->f_ra; */
+	if (!err)
+		return 0; /* success */
+
+	/* close all */
+	for (bindex = au_fbtop(file); bindex <= btail; bindex++)
+		au_set_h_fptr(file, bindex, NULL);
+	au_set_fbtop(file, -1);
+	au_set_fbbot_dir(file, -1);
+
+	return err;
+}
+
+static int aufs_open_dir(struct inode *inode __maybe_unused,
+			 struct file *file)
+{
+	int err;
+	struct super_block *sb;
+	struct au_fidir *fidir;
+
+	err = -ENOMEM;
+	sb = file->f_path.dentry->d_sb;
+	si_read_lock(sb, AuLock_FLUSH);
+	fidir = au_fidir_alloc(sb);
+	if (fidir) {
+		struct au_do_open_args args = {
+			.open	= do_open_dir,
+			.fidir	= fidir
+		};
+		err = au_do_open(file, &args);
+		if (unlikely(err))
+			kfree(fidir);
+	}
+	si_read_unlock(sb);
+	return err;
+}
+
+static int aufs_release_dir(struct inode *inode __maybe_unused,
+			    struct file *file)
+{
+	struct au_vdir *vdir_cache;
+	struct au_finfo *finfo;
+	struct au_fidir *fidir;
+	struct au_hfile *hf;
+	aufs_bindex_t bindex, bbot;
+
+	finfo = au_fi(file);
+	fidir = finfo->fi_hdir;
+	if (fidir) {
+		au_sphl_del(&finfo->fi_hlist,
+			    &au_sbi(file->f_path.dentry->d_sb)->si_files);
+		vdir_cache = fidir->fd_vdir_cache; /* lock-free */
+		if (vdir_cache)
+			au_vdir_free(vdir_cache);
+
+		bindex = finfo->fi_btop;
+		if (bindex >= 0) {
+			hf = fidir->fd_hfile + bindex;
+			/*
+			 * calls fput() instead of filp_close(),
+			 * since no dnotify or lock for the lower file.
+			 */
+			bbot = fidir->fd_bbot;
+			for (; bindex <= bbot; bindex++, hf++)
+				if (hf->hf_file)
+					au_hfput(hf, /*execed*/0);
+		}
+		kfree(fidir);
+		finfo->fi_hdir = NULL;
+	}
+	au_finfo_fin(file);
+	return 0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_do_flush_dir(struct file *file, fl_owner_t id)
+{
+	int err;
+	aufs_bindex_t bindex, bbot;
+	struct file *h_file;
+
+	err = 0;
+	bbot = au_fbbot_dir(file);
+	for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) {
+		h_file = au_hf_dir(file, bindex);
+		if (h_file)
+			err = vfsub_flush(h_file, id);
+	}
+	return err;
+}
+
+static int aufs_flush_dir(struct file *file, fl_owner_t id)
+{
+	return au_do_flush(file, id, au_do_flush_dir);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync)
+{
+	int err;
+	aufs_bindex_t bbot, bindex;
+	struct inode *inode;
+	struct super_block *sb;
+
+	err = 0;
+	sb = dentry->d_sb;
+	inode = d_inode(dentry);
+	IMustLock(inode);
+	bbot = au_dbbot(dentry);
+	for (bindex = au_dbtop(dentry); !err && bindex <= bbot; bindex++) {
+		struct path h_path;
+
+		if (au_test_ro(sb, bindex, inode))
+			continue;
+		h_path.dentry = au_h_dptr(dentry, bindex);
+		if (!h_path.dentry)
+			continue;
+
+		h_path.mnt = au_sbr_mnt(sb, bindex);
+		err = vfsub_fsync(NULL, &h_path, datasync);
+	}
+
+	return err;
+}
+
+static int au_do_fsync_dir(struct file *file, int datasync)
+{
+	int err;
+	aufs_bindex_t bbot, bindex;
+	struct file *h_file;
+	struct super_block *sb;
+	struct inode *inode;
+
+	err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0);
+	if (unlikely(err))
+		goto out;
+
+	inode = file_inode(file);
+	sb = inode->i_sb;
+	bbot = au_fbbot_dir(file);
+	for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) {
+		h_file = au_hf_dir(file, bindex);
+		if (!h_file || au_test_ro(sb, bindex, inode))
+			continue;
+
+		err = vfsub_fsync(h_file, &h_file->f_path, datasync);
+	}
+
+out:
+	return err;
+}
+
+/*
+ * @file may be NULL
+ */
+static int aufs_fsync_dir(struct file *file, loff_t start, loff_t end,
+			  int datasync)
+{
+	int err;
+	struct dentry *dentry;
+	struct inode *inode;
+	struct super_block *sb;
+
+	err = 0;
+	dentry = file->f_path.dentry;
+	inode = d_inode(dentry);
+	inode_lock(inode);
+	sb = dentry->d_sb;
+	si_noflush_read_lock(sb);
+	if (file)
+		err = au_do_fsync_dir(file, datasync);
+	else {
+		di_write_lock_child(dentry);
+		err = au_do_fsync_dir_no_file(dentry, datasync);
+	}
+	au_cpup_attr_timesizes(inode);
+	di_write_unlock(dentry);
+	if (file)
+		fi_write_unlock(file);
+
+	si_read_unlock(sb);
+	inode_unlock(inode);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int aufs_iterate_shared(struct file *file, struct dir_context *ctx)
+{
+	int err;
+	struct dentry *dentry;
+	struct inode *inode, *h_inode;
+	struct super_block *sb;
+
+	AuDbg("%pD, ctx{%pf, %llu}\n", file, ctx->actor, ctx->pos);
+
+	dentry = file->f_path.dentry;
+	inode = d_inode(dentry);
+	IMustLock(inode);
+
+	sb = dentry->d_sb;
+	si_read_lock(sb, AuLock_FLUSH);
+	err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0);
+	if (unlikely(err))
+		goto out;
+	err = au_alive_dir(dentry);
+	if (!err)
+		err = au_vdir_init(file);
+	di_downgrade_lock(dentry, AuLock_IR);
+	if (unlikely(err))
+		goto out_unlock;
+
+	h_inode = au_h_iptr(inode, au_ibtop(inode));
+	if (!au_test_nfsd()) {
+		err = au_vdir_fill_de(file, ctx);
+		fsstack_copy_attr_atime(inode, h_inode);
+	} else {
+		/*
+		 * nfsd filldir may call lookup_one_len(), vfs_getattr(),
+		 * encode_fh() and others.
+		 */
+		atomic_inc(&h_inode->i_count);
+		di_read_unlock(dentry, AuLock_IR);
+		si_read_unlock(sb);
+		err = au_vdir_fill_de(file, ctx);
+		fsstack_copy_attr_atime(inode, h_inode);
+		fi_write_unlock(file);
+		iput(h_inode);
+
+		AuTraceErr(err);
+		return err;
+	}
+
+out_unlock:
+	di_read_unlock(dentry, AuLock_IR);
+	fi_write_unlock(file);
+out:
+	si_read_unlock(sb);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+#define AuTestEmpty_WHONLY	1
+#define AuTestEmpty_CALLED	(1 << 1)
+#define AuTestEmpty_SHWH	(1 << 2)
+#define au_ftest_testempty(flags, name)	((flags) & AuTestEmpty_##name)
+#define au_fset_testempty(flags, name) \
+	do { (flags) |= AuTestEmpty_##name; } while (0)
+#define au_fclr_testempty(flags, name) \
+	do { (flags) &= ~AuTestEmpty_##name; } while (0)
+
+#ifndef CONFIG_AUFS_SHWH
+#undef AuTestEmpty_SHWH
+#define AuTestEmpty_SHWH	0
+#endif
+
+struct test_empty_arg {
+	struct dir_context ctx;
+	struct au_nhash *whlist;
+	unsigned int flags;
+	int err;
+	aufs_bindex_t bindex;
+};
+
+static int test_empty_cb(struct dir_context *ctx, const char *__name,
+			 int namelen, loff_t offset __maybe_unused, u64 ino,
+			 unsigned int d_type)
+{
+	struct test_empty_arg *arg = container_of(ctx, struct test_empty_arg,
+						  ctx);
+	char *name = (void *)__name;
+
+	arg->err = 0;
+	au_fset_testempty(arg->flags, CALLED);
+	/* smp_mb(); */
+	if (name[0] == '.'
+	    && (namelen == 1 || (name[1] == '.' && namelen == 2)))
+		goto out; /* success */
+
+	if (namelen <= AUFS_WH_PFX_LEN
+	    || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) {
+		if (au_ftest_testempty(arg->flags, WHONLY)
+		    && !au_nhash_test_known_wh(arg->whlist, name, namelen))
+			arg->err = -ENOTEMPTY;
+		goto out;
+	}
+
+	name += AUFS_WH_PFX_LEN;
+	namelen -= AUFS_WH_PFX_LEN;
+	if (!au_nhash_test_known_wh(arg->whlist, name, namelen))
+		arg->err = au_nhash_append_wh
+			(arg->whlist, name, namelen, ino, d_type, arg->bindex,
+			 au_ftest_testempty(arg->flags, SHWH));
+
+out:
+	/* smp_mb(); */
+	AuTraceErr(arg->err);
+	return arg->err;
+}
+
+static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg)
+{
+	int err;
+	struct file *h_file;
+
+	h_file = au_h_open(dentry, arg->bindex,
+			   O_RDONLY | O_NONBLOCK | O_DIRECTORY | O_LARGEFILE,
+			   /*file*/NULL, /*force_wr*/0);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	err = 0;
+	if (!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE)
+	    && !file_inode(h_file)->i_nlink)
+		goto out_put;
+
+	do {
+		arg->err = 0;
+		au_fclr_testempty(arg->flags, CALLED);
+		/* smp_mb(); */
+		err = vfsub_iterate_dir(h_file, &arg->ctx);
+		if (err >= 0)
+			err = arg->err;
+	} while (!err && au_ftest_testempty(arg->flags, CALLED));
+
+out_put:
+	fput(h_file);
+	au_sbr_put(dentry->d_sb, arg->bindex);
+out:
+	return err;
+}
+
+struct do_test_empty_args {
+	int *errp;
+	struct dentry *dentry;
+	struct test_empty_arg *arg;
+};
+
+static void call_do_test_empty(void *args)
+{
+	struct do_test_empty_args *a = args;
+	*a->errp = do_test_empty(a->dentry, a->arg);
+}
+
+static int sio_test_empty(struct dentry *dentry, struct test_empty_arg *arg)
+{
+	int err, wkq_err;
+	struct dentry *h_dentry;
+	struct inode *h_inode;
+
+	h_dentry = au_h_dptr(dentry, arg->bindex);
+	h_inode = d_inode(h_dentry);
+	/* todo: i_mode changes anytime? */
+	vfsub_inode_lock_shared_nested(h_inode, AuLsc_I_CHILD);
+	err = au_test_h_perm_sio(h_inode, MAY_EXEC | MAY_READ);
+	inode_unlock_shared(h_inode);
+	if (!err)
+		err = do_test_empty(dentry, arg);
+	else {
+		struct do_test_empty_args args = {
+			.errp	= &err,
+			.dentry	= dentry,
+			.arg	= arg
+		};
+		unsigned int flags = arg->flags;
+
+		wkq_err = au_wkq_wait(call_do_test_empty, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+		arg->flags = flags;
+	}
+
+	return err;
+}
+
+int au_test_empty_lower(struct dentry *dentry)
+{
+	int err;
+	unsigned int rdhash;
+	aufs_bindex_t bindex, btop, btail;
+	struct au_nhash whlist;
+	struct test_empty_arg arg = {
+		.ctx = {
+			.actor = test_empty_cb
+		}
+	};
+	int (*test_empty)(struct dentry *dentry, struct test_empty_arg *arg);
+
+	SiMustAnyLock(dentry->d_sb);
+
+	rdhash = au_sbi(dentry->d_sb)->si_rdhash;
+	if (!rdhash)
+		rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, dentry));
+	err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS);
+	if (unlikely(err))
+		goto out;
+
+	arg.flags = 0;
+	arg.whlist = &whlist;
+	btop = au_dbtop(dentry);
+	if (au_opt_test(au_mntflags(dentry->d_sb), SHWH))
+		au_fset_testempty(arg.flags, SHWH);
+	test_empty = do_test_empty;
+	if (au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1))
+		test_empty = sio_test_empty;
+	arg.bindex = btop;
+	err = test_empty(dentry, &arg);
+	if (unlikely(err))
+		goto out_whlist;
+
+	au_fset_testempty(arg.flags, WHONLY);
+	btail = au_dbtaildir(dentry);
+	for (bindex = btop + 1; !err && bindex <= btail; bindex++) {
+		struct dentry *h_dentry;
+
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (h_dentry && d_is_positive(h_dentry)) {
+			arg.bindex = bindex;
+			err = test_empty(dentry, &arg);
+		}
+	}
+
+out_whlist:
+	au_nhash_wh_free(&whlist);
+out:
+	return err;
+}
+
+int au_test_empty(struct dentry *dentry, struct au_nhash *whlist)
+{
+	int err;
+	struct test_empty_arg arg = {
+		.ctx = {
+			.actor = test_empty_cb
+		}
+	};
+	aufs_bindex_t bindex, btail;
+
+	err = 0;
+	arg.whlist = whlist;
+	arg.flags = AuTestEmpty_WHONLY;
+	if (au_opt_test(au_mntflags(dentry->d_sb), SHWH))
+		au_fset_testempty(arg.flags, SHWH);
+	btail = au_dbtaildir(dentry);
+	for (bindex = au_dbtop(dentry); !err && bindex <= btail; bindex++) {
+		struct dentry *h_dentry;
+
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (h_dentry && d_is_positive(h_dentry)) {
+			arg.bindex = bindex;
+			err = sio_test_empty(dentry, &arg);
+		}
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+const struct file_operations aufs_dir_fop = {
+	.owner		= THIS_MODULE,
+	.llseek		= default_llseek,
+	.read		= generic_read_dir,
+	.iterate_shared	= aufs_iterate_shared,
+	.unlocked_ioctl	= aufs_ioctl_dir,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= aufs_compat_ioctl_dir,
+#endif
+	.open		= aufs_open_dir,
+	.release	= aufs_release_dir,
+	.flush		= aufs_flush_dir,
+	.fsync		= aufs_fsync_dir
+};
diff --git a/fs/aufs/dir.h b/fs/aufs/dir.h
new file mode 100644
index 000000000000..b107309a3d60
--- /dev/null
+++ b/fs/aufs/dir.h
@@ -0,0 +1,131 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * directory operations
+ */
+
+#ifndef __AUFS_DIR_H__
+#define __AUFS_DIR_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+
+/* ---------------------------------------------------------------------- */
+
+/* need to be faster and smaller */
+
+struct au_nhash {
+	unsigned int		nh_num;
+	struct hlist_head	*nh_head;
+};
+
+struct au_vdir_destr {
+	unsigned char	len;
+	unsigned char	name[0];
+} __packed;
+
+struct au_vdir_dehstr {
+	struct hlist_node	hash;
+	struct au_vdir_destr	*str;
+} ____cacheline_aligned_in_smp;
+
+struct au_vdir_de {
+	ino_t			de_ino;
+	unsigned char		de_type;
+	/* caution: packed */
+	struct au_vdir_destr	de_str;
+} __packed;
+
+struct au_vdir_wh {
+	struct hlist_node	wh_hash;
+#ifdef CONFIG_AUFS_SHWH
+	ino_t			wh_ino;
+	aufs_bindex_t		wh_bindex;
+	unsigned char		wh_type;
+#else
+	aufs_bindex_t		wh_bindex;
+#endif
+	/* caution: packed */
+	struct au_vdir_destr	wh_str;
+} __packed;
+
+union au_vdir_deblk_p {
+	unsigned char		*deblk;
+	struct au_vdir_de	*de;
+};
+
+struct au_vdir {
+	unsigned char	**vd_deblk;
+	unsigned long	vd_nblk;
+	struct {
+		unsigned long		ul;
+		union au_vdir_deblk_p	p;
+	} vd_last;
+
+	unsigned long	vd_version;
+	unsigned int	vd_deblk_sz;
+	unsigned long		vd_jiffy;
+} ____cacheline_aligned_in_smp;
+
+/* ---------------------------------------------------------------------- */
+
+/* dir.c */
+extern const struct file_operations aufs_dir_fop;
+void au_add_nlink(struct inode *dir, struct inode *h_dir);
+void au_sub_nlink(struct inode *dir, struct inode *h_dir);
+loff_t au_dir_size(struct file *file, struct dentry *dentry);
+void au_dir_ts(struct inode *dir, aufs_bindex_t bsrc);
+int au_test_empty_lower(struct dentry *dentry);
+int au_test_empty(struct dentry *dentry, struct au_nhash *whlist);
+
+/* vdir.c */
+unsigned int au_rdhash_est(loff_t sz);
+int au_nhash_alloc(struct au_nhash *nhash, unsigned int num_hash, gfp_t gfp);
+void au_nhash_wh_free(struct au_nhash *whlist);
+int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt,
+			    int limit);
+int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen);
+int au_nhash_append_wh(struct au_nhash *whlist, char *name, int nlen, ino_t ino,
+		       unsigned int d_type, aufs_bindex_t bindex,
+		       unsigned char shwh);
+void au_vdir_free(struct au_vdir *vdir);
+int au_vdir_init(struct file *file);
+int au_vdir_fill_de(struct file *file, struct dir_context *ctx);
+
+/* ioctl.c */
+long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg);
+
+#ifdef CONFIG_AUFS_RDU
+/* rdu.c */
+long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+#ifdef CONFIG_COMPAT
+long au_rdu_compat_ioctl(struct file *file, unsigned int cmd,
+			 unsigned long arg);
+#endif
+#else
+AuStub(long, au_rdu_ioctl, return -EINVAL, struct file *file,
+       unsigned int cmd, unsigned long arg)
+#ifdef CONFIG_COMPAT
+AuStub(long, au_rdu_compat_ioctl, return -EINVAL, struct file *file,
+       unsigned int cmd, unsigned long arg)
+#endif
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DIR_H__ */
diff --git a/fs/aufs/dynop.c b/fs/aufs/dynop.c
new file mode 100644
index 000000000000..443791a76239
--- /dev/null
+++ b/fs/aufs/dynop.c
@@ -0,0 +1,371 @@
+/*
+ * Copyright (C) 2010-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * dynamically customizable operations for regular files
+ */
+
+#include "aufs.h"
+
+#define DyPrSym(key)	AuDbgSym(key->dk_op.dy_hop)
+
+/*
+ * How large will these lists be?
+ * Usually just a few elements, 20-30 at most for each, I guess.
+ */
+static struct au_sphlhead dynop[AuDyLast];
+
+static struct au_dykey *dy_gfind_get(struct au_sphlhead *sphl, const void *h_op)
+{
+	struct au_dykey *key, *tmp;
+	struct hlist_head *head;
+
+	key = NULL;
+	head = &sphl->head;
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp, head, dk_hnode)
+		if (tmp->dk_op.dy_hop == h_op) {
+			key = tmp;
+			kref_get(&key->dk_kref);
+			break;
+		}
+	rcu_read_unlock();
+
+	return key;
+}
+
+static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key)
+{
+	struct au_dykey **k, *found;
+	const void *h_op = key->dk_op.dy_hop;
+	int i;
+
+	found = NULL;
+	k = br->br_dykey;
+	for (i = 0; i < AuBrDynOp; i++)
+		if (k[i]) {
+			if (k[i]->dk_op.dy_hop == h_op) {
+				found = k[i];
+				break;
+			}
+		} else
+			break;
+	if (!found) {
+		spin_lock(&br->br_dykey_lock);
+		for (; i < AuBrDynOp; i++)
+			if (k[i]) {
+				if (k[i]->dk_op.dy_hop == h_op) {
+					found = k[i];
+					break;
+				}
+			} else {
+				k[i] = key;
+				break;
+			}
+		spin_unlock(&br->br_dykey_lock);
+		BUG_ON(i == AuBrDynOp); /* expand the array */
+	}
+
+	return found;
+}
+
+/* kref_get() if @key is already added */
+static struct au_dykey *dy_gadd(struct au_sphlhead *sphl, struct au_dykey *key)
+{
+	struct au_dykey *tmp, *found;
+	struct hlist_head *head;
+	const void *h_op = key->dk_op.dy_hop;
+
+	found = NULL;
+	head = &sphl->head;
+	spin_lock(&sphl->spin);
+	hlist_for_each_entry(tmp, head, dk_hnode)
+		if (tmp->dk_op.dy_hop == h_op) {
+			kref_get(&tmp->dk_kref);
+			found = tmp;
+			break;
+		}
+	if (!found)
+		hlist_add_head_rcu(&key->dk_hnode, head);
+	spin_unlock(&sphl->spin);
+
+	if (!found)
+		DyPrSym(key);
+	return found;
+}
+
+static void dy_free_rcu(struct rcu_head *rcu)
+{
+	struct au_dykey *key;
+
+	key = container_of(rcu, struct au_dykey, dk_rcu);
+	DyPrSym(key);
+	kfree(key);
+}
+
+static void dy_free(struct kref *kref)
+{
+	struct au_dykey *key;
+	struct au_sphlhead *sphl;
+
+	key = container_of(kref, struct au_dykey, dk_kref);
+	sphl = dynop + key->dk_op.dy_type;
+	au_sphl_del_rcu(&key->dk_hnode, sphl);
+	call_rcu(&key->dk_rcu, dy_free_rcu);
+}
+
+void au_dy_put(struct au_dykey *key)
+{
+	kref_put(&key->dk_kref, dy_free);
+}
+
+/* ---------------------------------------------------------------------- */
+
+#define DyDbgSize(cnt, op)	AuDebugOn(cnt != sizeof(op)/sizeof(void *))
+
+#ifdef CONFIG_AUFS_DEBUG
+#define DyDbgDeclare(cnt)	unsigned int cnt = 0
+#define DyDbgInc(cnt)		do { cnt++; } while (0)
+#else
+#define DyDbgDeclare(cnt)	do {} while (0)
+#define DyDbgInc(cnt)		do {} while (0)
+#endif
+
+#define DySet(func, dst, src, h_op, h_sb) do {				\
+	DyDbgInc(cnt);							\
+	if (h_op->func) {						\
+		if (src.func)						\
+			dst.func = src.func;				\
+		else							\
+			AuDbg("%s %s\n", au_sbtype(h_sb), #func);	\
+	}								\
+} while (0)
+
+#define DySetForce(func, dst, src) do {		\
+	AuDebugOn(!src.func);			\
+	DyDbgInc(cnt);				\
+	dst.func = src.func;			\
+} while (0)
+
+#define DySetAop(func) \
+	DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb)
+#define DySetAopForce(func) \
+	DySetForce(func, dyaop->da_op, aufs_aop)
+
+static void dy_aop(struct au_dykey *key, const void *h_op,
+		   struct super_block *h_sb __maybe_unused)
+{
+	struct au_dyaop *dyaop = (void *)key;
+	const struct address_space_operations *h_aop = h_op;
+	DyDbgDeclare(cnt);
+
+	AuDbg("%s\n", au_sbtype(h_sb));
+
+	DySetAop(writepage);
+	DySetAopForce(readpage);	/* force */
+	DySetAop(writepages);
+	DySetAop(set_page_dirty);
+	DySetAop(readpages);
+	DySetAop(write_begin);
+	DySetAop(write_end);
+	DySetAop(bmap);
+	DySetAop(invalidatepage);
+	DySetAop(releasepage);
+	DySetAop(freepage);
+	/* this one will be changed according to an aufs mount option */
+	DySetAop(direct_IO);
+	DySetAop(migratepage);
+	DySetAop(isolate_page);
+	DySetAop(putback_page);
+	DySetAop(launder_page);
+	DySetAop(is_partially_uptodate);
+	DySetAop(is_dirty_writeback);
+	DySetAop(error_remove_page);
+	DySetAop(swap_activate);
+	DySetAop(swap_deactivate);
+
+	DyDbgSize(cnt, *h_aop);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void dy_bug(struct kref *kref)
+{
+	BUG();
+}
+
+static struct au_dykey *dy_get(struct au_dynop *op, struct au_branch *br)
+{
+	struct au_dykey *key, *old;
+	struct au_sphlhead *sphl;
+	struct op {
+		unsigned int sz;
+		void (*set)(struct au_dykey *key, const void *h_op,
+			    struct super_block *h_sb __maybe_unused);
+	};
+	static const struct op a[] = {
+		[AuDy_AOP] = {
+			.sz	= sizeof(struct au_dyaop),
+			.set	= dy_aop
+		}
+	};
+	const struct op *p;
+
+	sphl = dynop + op->dy_type;
+	key = dy_gfind_get(sphl, op->dy_hop);
+	if (key)
+		goto out_add; /* success */
+
+	p = a + op->dy_type;
+	key = kzalloc(p->sz, GFP_NOFS);
+	if (unlikely(!key)) {
+		key = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	key->dk_op.dy_hop = op->dy_hop;
+	kref_init(&key->dk_kref);
+	p->set(key, op->dy_hop, au_br_sb(br));
+	old = dy_gadd(sphl, key);
+	if (old) {
+		kfree(key);
+		key = old;
+	}
+
+out_add:
+	old = dy_bradd(br, key);
+	if (old)
+		/* its ref-count should never be zero here */
+		kref_put(&key->dk_kref, dy_bug);
+out:
+	return key;
+}
+
+/* ---------------------------------------------------------------------- */
+/*
+ * Aufs prohibits O_DIRECT by defaut even if the branch supports it.
+ * This behaviour is necessary to return an error from open(O_DIRECT) instead
+ * of the succeeding I/O. The dio mount option enables O_DIRECT and makes
+ * open(O_DIRECT) always succeed, but the succeeding I/O may return an error.
+ * See the aufs manual in detail.
+ */
+static void dy_adx(struct au_dyaop *dyaop, int do_dx)
+{
+	if (!do_dx)
+		dyaop->da_op.direct_IO = NULL;
+	else
+		dyaop->da_op.direct_IO = aufs_aop.direct_IO;
+}
+
+static struct au_dyaop *dy_aget(struct au_branch *br,
+				const struct address_space_operations *h_aop,
+				int do_dx)
+{
+	struct au_dyaop *dyaop;
+	struct au_dynop op;
+
+	op.dy_type = AuDy_AOP;
+	op.dy_haop = h_aop;
+	dyaop = (void *)dy_get(&op, br);
+	if (IS_ERR(dyaop))
+		goto out;
+	dy_adx(dyaop, do_dx);
+
+out:
+	return dyaop;
+}
+
+int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex,
+		struct inode *h_inode)
+{
+	int err, do_dx;
+	struct super_block *sb;
+	struct au_branch *br;
+	struct au_dyaop *dyaop;
+
+	AuDebugOn(!S_ISREG(h_inode->i_mode));
+	IiMustWriteLock(inode);
+
+	sb = inode->i_sb;
+	br = au_sbr(sb, bindex);
+	do_dx = !!au_opt_test(au_mntflags(sb), DIO);
+	dyaop = dy_aget(br, h_inode->i_mapping->a_ops, do_dx);
+	err = PTR_ERR(dyaop);
+	if (IS_ERR(dyaop))
+		/* unnecessary to call dy_fput() */
+		goto out;
+
+	err = 0;
+	inode->i_mapping->a_ops = &dyaop->da_op;
+
+out:
+	return err;
+}
+
+/*
+ * Is it safe to replace a_ops during the inode/file is in operation?
+ * Yes, I hope so.
+ */
+int au_dy_irefresh(struct inode *inode)
+{
+	int err;
+	aufs_bindex_t btop;
+	struct inode *h_inode;
+
+	err = 0;
+	if (S_ISREG(inode->i_mode)) {
+		btop = au_ibtop(inode);
+		h_inode = au_h_iptr(inode, btop);
+		err = au_dy_iaop(inode, btop, h_inode);
+	}
+	return err;
+}
+
+void au_dy_arefresh(int do_dx)
+{
+	struct au_sphlhead *sphl;
+	struct hlist_head *head;
+	struct au_dykey *key;
+
+	sphl = dynop + AuDy_AOP;
+	head = &sphl->head;
+	spin_lock(&sphl->spin);
+	hlist_for_each_entry(key, head, dk_hnode)
+		dy_adx((void *)key, do_dx);
+	spin_unlock(&sphl->spin);
+}
+
+/* ---------------------------------------------------------------------- */
+
+void __init au_dy_init(void)
+{
+	int i;
+
+	/* make sure that 'struct au_dykey *' can be any type */
+	BUILD_BUG_ON(offsetof(struct au_dyaop, da_key));
+
+	for (i = 0; i < AuDyLast; i++)
+		au_sphl_init(dynop + i);
+}
+
+void au_dy_fin(void)
+{
+	int i;
+
+	for (i = 0; i < AuDyLast; i++)
+		WARN_ON(!hlist_empty(&dynop[i].head));
+}
diff --git a/fs/aufs/dynop.h b/fs/aufs/dynop.h
new file mode 100644
index 000000000000..c19c675d60a9
--- /dev/null
+++ b/fs/aufs/dynop.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright (C) 2010-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * dynamically customizable operations (for regular files only)
+ */
+
+#ifndef __AUFS_DYNOP_H__
+#define __AUFS_DYNOP_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/kref.h>
+
+enum {AuDy_AOP, AuDyLast};
+
+struct au_dynop {
+	int						dy_type;
+	union {
+		const void				*dy_hop;
+		const struct address_space_operations	*dy_haop;
+	};
+};
+
+struct au_dykey {
+	union {
+		struct hlist_node	dk_hnode;
+		struct rcu_head		dk_rcu;
+	};
+	struct au_dynop		dk_op;
+
+	/*
+	 * during I am in the branch local array, kref is gotten. when the
+	 * branch is removed, kref is put.
+	 */
+	struct kref		dk_kref;
+};
+
+/* stop unioning since their sizes are very different from each other */
+struct au_dyaop {
+	struct au_dykey			da_key;
+	struct address_space_operations	da_op; /* not const */
+};
+
+/* ---------------------------------------------------------------------- */
+
+/* dynop.c */
+struct au_branch;
+void au_dy_put(struct au_dykey *key);
+int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex,
+		struct inode *h_inode);
+int au_dy_irefresh(struct inode *inode);
+void au_dy_arefresh(int do_dio);
+
+void __init au_dy_init(void);
+void au_dy_fin(void);
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_DYNOP_H__ */
diff --git a/fs/aufs/export.c b/fs/aufs/export.c
new file mode 100644
index 000000000000..34b391c0dc47
--- /dev/null
+++ b/fs/aufs/export.c
@@ -0,0 +1,836 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * export via nfs
+ */
+
+#include <linux/exportfs.h>
+#include <linux/fs_struct.h>
+#include <linux/namei.h>
+#include <linux/nsproxy.h>
+#include <linux/random.h>
+#include <linux/writeback.h>
+#include "aufs.h"
+
+union conv {
+#ifdef CONFIG_AUFS_INO_T_64
+	__u32 a[2];
+#else
+	__u32 a[1];
+#endif
+	ino_t ino;
+};
+
+static ino_t decode_ino(__u32 *a)
+{
+	union conv u;
+
+	BUILD_BUG_ON(sizeof(u.ino) != sizeof(u.a));
+	u.a[0] = a[0];
+#ifdef CONFIG_AUFS_INO_T_64
+	u.a[1] = a[1];
+#endif
+	return u.ino;
+}
+
+static void encode_ino(__u32 *a, ino_t ino)
+{
+	union conv u;
+
+	u.ino = ino;
+	a[0] = u.a[0];
+#ifdef CONFIG_AUFS_INO_T_64
+	a[1] = u.a[1];
+#endif
+}
+
+/* NFS file handle */
+enum {
+	Fh_br_id,
+	Fh_sigen,
+#ifdef CONFIG_AUFS_INO_T_64
+	/* support 64bit inode number */
+	Fh_ino1,
+	Fh_ino2,
+	Fh_dir_ino1,
+	Fh_dir_ino2,
+#else
+	Fh_ino1,
+	Fh_dir_ino1,
+#endif
+	Fh_igen,
+	Fh_h_type,
+	Fh_tail,
+
+	Fh_ino = Fh_ino1,
+	Fh_dir_ino = Fh_dir_ino1
+};
+
+static int au_test_anon(struct dentry *dentry)
+{
+	/* note: read d_flags without d_lock */
+	return !!(dentry->d_flags & DCACHE_DISCONNECTED);
+}
+
+int au_test_nfsd(void)
+{
+	int ret;
+	struct task_struct *tsk = current;
+	char comm[sizeof(tsk->comm)];
+
+	ret = 0;
+	if (tsk->flags & PF_KTHREAD) {
+		get_task_comm(comm, tsk);
+		ret = !strcmp(comm, "nfsd");
+	}
+
+	return ret;
+}
+
+/* ---------------------------------------------------------------------- */
+/* inode generation external table */
+
+void au_xigen_inc(struct inode *inode)
+{
+	loff_t pos;
+	ssize_t sz;
+	__u32 igen;
+	struct super_block *sb;
+	struct au_sbinfo *sbinfo;
+
+	sb = inode->i_sb;
+	AuDebugOn(!au_opt_test(au_mntflags(sb), XINO));
+
+	sbinfo = au_sbi(sb);
+	pos = inode->i_ino;
+	pos *= sizeof(igen);
+	igen = inode->i_generation + 1;
+	sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xigen, &igen,
+			 sizeof(igen), &pos);
+	if (sz == sizeof(igen))
+		return; /* success */
+
+	if (unlikely(sz >= 0))
+		AuIOErr("xigen error (%zd)\n", sz);
+}
+
+int au_xigen_new(struct inode *inode)
+{
+	int err;
+	loff_t pos;
+	ssize_t sz;
+	struct super_block *sb;
+	struct au_sbinfo *sbinfo;
+	struct file *file;
+
+	err = 0;
+	/* todo: dirty, at mount time */
+	if (inode->i_ino == AUFS_ROOT_INO)
+		goto out;
+	sb = inode->i_sb;
+	SiMustAnyLock(sb);
+	if (unlikely(!au_opt_test(au_mntflags(sb), XINO)))
+		goto out;
+
+	err = -EFBIG;
+	pos = inode->i_ino;
+	if (unlikely(au_loff_max / sizeof(inode->i_generation) - 1 < pos)) {
+		AuIOErr1("too large i%lld\n", pos);
+		goto out;
+	}
+	pos *= sizeof(inode->i_generation);
+
+	err = 0;
+	sbinfo = au_sbi(sb);
+	file = sbinfo->si_xigen;
+	BUG_ON(!file);
+
+	if (vfsub_f_size_read(file)
+	    < pos + sizeof(inode->i_generation)) {
+		inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next);
+		sz = xino_fwrite(sbinfo->si_xwrite, file, &inode->i_generation,
+				 sizeof(inode->i_generation), &pos);
+	} else
+		sz = xino_fread(sbinfo->si_xread, file, &inode->i_generation,
+				sizeof(inode->i_generation), &pos);
+	if (sz == sizeof(inode->i_generation))
+		goto out; /* success */
+
+	err = sz;
+	if (unlikely(sz >= 0)) {
+		err = -EIO;
+		AuIOErr("xigen error (%zd)\n", sz);
+	}
+
+out:
+	return err;
+}
+
+int au_xigen_set(struct super_block *sb, struct file *base)
+{
+	int err;
+	struct au_sbinfo *sbinfo;
+	struct file *file;
+
+	SiMustWriteLock(sb);
+
+	sbinfo = au_sbi(sb);
+	file = au_xino_create2(base, sbinfo->si_xigen);
+	err = PTR_ERR(file);
+	if (IS_ERR(file))
+		goto out;
+	err = 0;
+	if (sbinfo->si_xigen)
+		fput(sbinfo->si_xigen);
+	sbinfo->si_xigen = file;
+
+out:
+	return err;
+}
+
+void au_xigen_clr(struct super_block *sb)
+{
+	struct au_sbinfo *sbinfo;
+
+	SiMustWriteLock(sb);
+
+	sbinfo = au_sbi(sb);
+	if (sbinfo->si_xigen) {
+		fput(sbinfo->si_xigen);
+		sbinfo->si_xigen = NULL;
+	}
+}
+
+/* ---------------------------------------------------------------------- */
+
+static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino,
+				    ino_t dir_ino)
+{
+	struct dentry *dentry, *d;
+	struct inode *inode;
+	unsigned int sigen;
+
+	dentry = NULL;
+	inode = ilookup(sb, ino);
+	if (!inode)
+		goto out;
+
+	dentry = ERR_PTR(-ESTALE);
+	sigen = au_sigen(sb);
+	if (unlikely(au_is_bad_inode(inode)
+		     || IS_DEADDIR(inode)
+		     || sigen != au_iigen(inode, NULL)))
+		goto out_iput;
+
+	dentry = NULL;
+	if (!dir_ino || S_ISDIR(inode->i_mode))
+		dentry = d_find_alias(inode);
+	else {
+		spin_lock(&inode->i_lock);
+		hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) {
+			spin_lock(&d->d_lock);
+			if (!au_test_anon(d)
+			    && d_inode(d->d_parent)->i_ino == dir_ino) {
+				dentry = dget_dlock(d);
+				spin_unlock(&d->d_lock);
+				break;
+			}
+			spin_unlock(&d->d_lock);
+		}
+		spin_unlock(&inode->i_lock);
+	}
+	if (unlikely(dentry && au_digen_test(dentry, sigen))) {
+		/* need to refresh */
+		dput(dentry);
+		dentry = NULL;
+	}
+
+out_iput:
+	iput(inode);
+out:
+	AuTraceErrPtr(dentry);
+	return dentry;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* todo: dirty? */
+/* if exportfs_decode_fh() passed vfsmount*, we could be happy */
+
+struct au_compare_mnt_args {
+	/* input */
+	struct super_block *sb;
+
+	/* output */
+	struct vfsmount *mnt;
+};
+
+static int au_compare_mnt(struct vfsmount *mnt, void *arg)
+{
+	struct au_compare_mnt_args *a = arg;
+
+	if (mnt->mnt_sb != a->sb)
+		return 0;
+	a->mnt = mntget(mnt);
+	return 1;
+}
+
+static struct vfsmount *au_mnt_get(struct super_block *sb)
+{
+	int err;
+	struct path root;
+	struct au_compare_mnt_args args = {
+		.sb = sb
+	};
+
+	get_fs_root(current->fs, &root);
+	rcu_read_lock();
+	err = iterate_mounts(au_compare_mnt, &args, root.mnt);
+	rcu_read_unlock();
+	path_put(&root);
+	AuDebugOn(!err);
+	AuDebugOn(!args.mnt);
+	return args.mnt;
+}
+
+struct au_nfsd_si_lock {
+	unsigned int sigen;
+	aufs_bindex_t bindex, br_id;
+	unsigned char force_lock;
+};
+
+static int si_nfsd_read_lock(struct super_block *sb,
+			     struct au_nfsd_si_lock *nsi_lock)
+{
+	int err;
+	aufs_bindex_t bindex;
+
+	si_read_lock(sb, AuLock_FLUSH);
+
+	/* branch id may be wrapped around */
+	err = 0;
+	bindex = au_br_index(sb, nsi_lock->br_id);
+	if (bindex >= 0 && nsi_lock->sigen + AUFS_BRANCH_MAX > au_sigen(sb))
+		goto out; /* success */
+
+	err = -ESTALE;
+	bindex = -1;
+	if (!nsi_lock->force_lock)
+		si_read_unlock(sb);
+
+out:
+	nsi_lock->bindex = bindex;
+	return err;
+}
+
+struct find_name_by_ino {
+	struct dir_context ctx;
+	int called, found;
+	ino_t ino;
+	char *name;
+	int namelen;
+};
+
+static int
+find_name_by_ino(struct dir_context *ctx, const char *name, int namelen,
+		 loff_t offset, u64 ino, unsigned int d_type)
+{
+	struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino,
+						  ctx);
+
+	a->called++;
+	if (a->ino != ino)
+		return 0;
+
+	memcpy(a->name, name, namelen);
+	a->namelen = namelen;
+	a->found = 1;
+	return 1;
+}
+
+static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino,
+				     struct au_nfsd_si_lock *nsi_lock)
+{
+	struct dentry *dentry, *parent;
+	struct file *file;
+	struct inode *dir;
+	struct find_name_by_ino arg = {
+		.ctx = {
+			.actor = find_name_by_ino
+		}
+	};
+	int err;
+
+	parent = path->dentry;
+	if (nsi_lock)
+		si_read_unlock(parent->d_sb);
+	file = vfsub_dentry_open(path, au_dir_roflags);
+	dentry = (void *)file;
+	if (IS_ERR(file))
+		goto out;
+
+	dentry = ERR_PTR(-ENOMEM);
+	arg.name = (void *)__get_free_page(GFP_NOFS);
+	if (unlikely(!arg.name))
+		goto out_file;
+	arg.ino = ino;
+	arg.found = 0;
+	do {
+		arg.called = 0;
+		/* smp_mb(); */
+		err = vfsub_iterate_dir(file, &arg.ctx);
+	} while (!err && !arg.found && arg.called);
+	dentry = ERR_PTR(err);
+	if (unlikely(err))
+		goto out_name;
+	/* instead of ENOENT */
+	dentry = ERR_PTR(-ESTALE);
+	if (!arg.found)
+		goto out_name;
+
+	/* do not call vfsub_lkup_one() */
+	dir = d_inode(parent);
+	dentry = vfsub_lookup_one_len_unlocked(arg.name, parent, arg.namelen);
+	AuTraceErrPtr(dentry);
+	if (IS_ERR(dentry))
+		goto out_name;
+	AuDebugOn(au_test_anon(dentry));
+	if (unlikely(d_really_is_negative(dentry))) {
+		dput(dentry);
+		dentry = ERR_PTR(-ENOENT);
+	}
+
+out_name:
+	free_page((unsigned long)arg.name);
+out_file:
+	fput(file);
+out:
+	if (unlikely(nsi_lock
+		     && si_nfsd_read_lock(parent->d_sb, nsi_lock) < 0))
+		if (!IS_ERR(dentry)) {
+			dput(dentry);
+			dentry = ERR_PTR(-ESTALE);
+		}
+	AuTraceErrPtr(dentry);
+	return dentry;
+}
+
+static struct dentry *decode_by_dir_ino(struct super_block *sb, ino_t ino,
+					ino_t dir_ino,
+					struct au_nfsd_si_lock *nsi_lock)
+{
+	struct dentry *dentry;
+	struct path path;
+
+	if (dir_ino != AUFS_ROOT_INO) {
+		path.dentry = decode_by_ino(sb, dir_ino, 0);
+		dentry = path.dentry;
+		if (!path.dentry || IS_ERR(path.dentry))
+			goto out;
+		AuDebugOn(au_test_anon(path.dentry));
+	} else
+		path.dentry = dget(sb->s_root);
+
+	path.mnt = au_mnt_get(sb);
+	dentry = au_lkup_by_ino(&path, ino, nsi_lock);
+	path_put(&path);
+
+out:
+	AuTraceErrPtr(dentry);
+	return dentry;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int h_acceptable(void *expv, struct dentry *dentry)
+{
+	return 1;
+}
+
+static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath,
+			   char *buf, int len, struct super_block *sb)
+{
+	char *p;
+	int n;
+	struct path path;
+
+	p = d_path(h_rootpath, buf, len);
+	if (IS_ERR(p))
+		goto out;
+	n = strlen(p);
+
+	path.mnt = h_rootpath->mnt;
+	path.dentry = h_parent;
+	p = d_path(&path, buf, len);
+	if (IS_ERR(p))
+		goto out;
+	if (n != 1)
+		p += n;
+
+	path.mnt = au_mnt_get(sb);
+	path.dentry = sb->s_root;
+	p = d_path(&path, buf, len - strlen(p));
+	mntput(path.mnt);
+	if (IS_ERR(p))
+		goto out;
+	if (n != 1)
+		p[strlen(p)] = '/';
+
+out:
+	AuTraceErrPtr(p);
+	return p;
+}
+
+static
+struct dentry *decode_by_path(struct super_block *sb, ino_t ino, __u32 *fh,
+			      int fh_len, struct au_nfsd_si_lock *nsi_lock)
+{
+	struct dentry *dentry, *h_parent, *root;
+	struct super_block *h_sb;
+	char *pathname, *p;
+	struct vfsmount *h_mnt;
+	struct au_branch *br;
+	int err;
+	struct path path;
+
+	br = au_sbr(sb, nsi_lock->bindex);
+	h_mnt = au_br_mnt(br);
+	h_sb = h_mnt->mnt_sb;
+	/* todo: call lower fh_to_dentry()? fh_to_parent()? */
+	lockdep_off();
+	h_parent = exportfs_decode_fh(h_mnt, (void *)(fh + Fh_tail),
+				      fh_len - Fh_tail, fh[Fh_h_type],
+				      h_acceptable, /*context*/NULL);
+	lockdep_on();
+	dentry = h_parent;
+	if (unlikely(!h_parent || IS_ERR(h_parent))) {
+		AuWarn1("%s decode_fh failed, %ld\n",
+			au_sbtype(h_sb), PTR_ERR(h_parent));
+		goto out;
+	}
+	dentry = NULL;
+	if (unlikely(au_test_anon(h_parent))) {
+		AuWarn1("%s decode_fh returned a disconnected dentry\n",
+			au_sbtype(h_sb));
+		goto out_h_parent;
+	}
+
+	dentry = ERR_PTR(-ENOMEM);
+	pathname = (void *)__get_free_page(GFP_NOFS);
+	if (unlikely(!pathname))
+		goto out_h_parent;
+
+	root = sb->s_root;
+	path.mnt = h_mnt;
+	di_read_lock_parent(root, !AuLock_IR);
+	path.dentry = au_h_dptr(root, nsi_lock->bindex);
+	di_read_unlock(root, !AuLock_IR);
+	p = au_build_path(h_parent, &path, pathname, PAGE_SIZE, sb);
+	dentry = (void *)p;
+	if (IS_ERR(p))
+		goto out_pathname;
+
+	si_read_unlock(sb);
+	err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
+	dentry = ERR_PTR(err);
+	if (unlikely(err))
+		goto out_relock;
+
+	dentry = ERR_PTR(-ENOENT);
+	AuDebugOn(au_test_anon(path.dentry));
+	if (unlikely(d_really_is_negative(path.dentry)))
+		goto out_path;
+
+	if (ino != d_inode(path.dentry)->i_ino)
+		dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL);
+	else
+		dentry = dget(path.dentry);
+
+out_path:
+	path_put(&path);
+out_relock:
+	if (unlikely(si_nfsd_read_lock(sb, nsi_lock) < 0))
+		if (!IS_ERR(dentry)) {
+			dput(dentry);
+			dentry = ERR_PTR(-ESTALE);
+		}
+out_pathname:
+	free_page((unsigned long)pathname);
+out_h_parent:
+	dput(h_parent);
+out:
+	AuTraceErrPtr(dentry);
+	return dentry;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static struct dentry *
+aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len,
+		  int fh_type)
+{
+	struct dentry *dentry;
+	__u32 *fh = fid->raw;
+	struct au_branch *br;
+	ino_t ino, dir_ino;
+	struct au_nfsd_si_lock nsi_lock = {
+		.force_lock	= 0
+	};
+
+	dentry = ERR_PTR(-ESTALE);
+	/* it should never happen, but the file handle is unreliable */
+	if (unlikely(fh_len < Fh_tail))
+		goto out;
+	nsi_lock.sigen = fh[Fh_sigen];
+	nsi_lock.br_id = fh[Fh_br_id];
+
+	/* branch id may be wrapped around */
+	br = NULL;
+	if (unlikely(si_nfsd_read_lock(sb, &nsi_lock)))
+		goto out;
+	nsi_lock.force_lock = 1;
+
+	/* is this inode still cached? */
+	ino = decode_ino(fh + Fh_ino);
+	/* it should never happen */
+	if (unlikely(ino == AUFS_ROOT_INO))
+		goto out_unlock;
+
+	dir_ino = decode_ino(fh + Fh_dir_ino);
+	dentry = decode_by_ino(sb, ino, dir_ino);
+	if (IS_ERR(dentry))
+		goto out_unlock;
+	if (dentry)
+		goto accept;
+
+	/* is the parent dir cached? */
+	br = au_sbr(sb, nsi_lock.bindex);
+	au_br_get(br);
+	dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock);
+	if (IS_ERR(dentry))
+		goto out_unlock;
+	if (dentry)
+		goto accept;
+
+	/* lookup path */
+	dentry = decode_by_path(sb, ino, fh, fh_len, &nsi_lock);
+	if (IS_ERR(dentry))
+		goto out_unlock;
+	if (unlikely(!dentry))
+		/* todo?: make it ESTALE */
+		goto out_unlock;
+
+accept:
+	if (!au_digen_test(dentry, au_sigen(sb))
+	    && d_inode(dentry)->i_generation == fh[Fh_igen])
+		goto out_unlock; /* success */
+
+	dput(dentry);
+	dentry = ERR_PTR(-ESTALE);
+out_unlock:
+	if (br)
+		au_br_put(br);
+	si_read_unlock(sb);
+out:
+	AuTraceErrPtr(dentry);
+	return dentry;
+}
+
+#if 0 /* reserved for future use */
+/* support subtreecheck option */
+static struct dentry *aufs_fh_to_parent(struct super_block *sb, struct fid *fid,
+					int fh_len, int fh_type)
+{
+	struct dentry *parent;
+	__u32 *fh = fid->raw;
+	ino_t dir_ino;
+
+	dir_ino = decode_ino(fh + Fh_dir_ino);
+	parent = decode_by_ino(sb, dir_ino, 0);
+	if (IS_ERR(parent))
+		goto out;
+	if (!parent)
+		parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]),
+					dir_ino, fh, fh_len);
+
+out:
+	AuTraceErrPtr(parent);
+	return parent;
+}
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+static int aufs_encode_fh(struct inode *inode, __u32 *fh, int *max_len,
+			  struct inode *dir)
+{
+	int err;
+	aufs_bindex_t bindex;
+	struct super_block *sb, *h_sb;
+	struct dentry *dentry, *parent, *h_parent;
+	struct inode *h_dir;
+	struct au_branch *br;
+
+	err = -ENOSPC;
+	if (unlikely(*max_len <= Fh_tail)) {
+		AuWarn1("NFSv2 client (max_len %d)?\n", *max_len);
+		goto out;
+	}
+
+	err = FILEID_ROOT;
+	if (inode->i_ino == AUFS_ROOT_INO) {
+		AuDebugOn(inode->i_ino != AUFS_ROOT_INO);
+		goto out;
+	}
+
+	h_parent = NULL;
+	sb = inode->i_sb;
+	err = si_read_lock(sb, AuLock_FLUSH);
+	if (unlikely(err))
+		goto out;
+
+#ifdef CONFIG_AUFS_DEBUG
+	if (unlikely(!au_opt_test(au_mntflags(sb), XINO)))
+		AuWarn1("NFS-exporting requires xino\n");
+#endif
+	err = -EIO;
+	parent = NULL;
+	ii_read_lock_child(inode);
+	bindex = au_ibtop(inode);
+	if (!dir) {
+		dentry = d_find_any_alias(inode);
+		if (unlikely(!dentry))
+			goto out_unlock;
+		AuDebugOn(au_test_anon(dentry));
+		parent = dget_parent(dentry);
+		dput(dentry);
+		if (unlikely(!parent))
+			goto out_unlock;
+		if (d_really_is_positive(parent))
+			dir = d_inode(parent);
+	}
+
+	ii_read_lock_parent(dir);
+	h_dir = au_h_iptr(dir, bindex);
+	ii_read_unlock(dir);
+	if (unlikely(!h_dir))
+		goto out_parent;
+	h_parent = d_find_any_alias(h_dir);
+	if (unlikely(!h_parent))
+		goto out_hparent;
+
+	err = -EPERM;
+	br = au_sbr(sb, bindex);
+	h_sb = au_br_sb(br);
+	if (unlikely(!h_sb->s_export_op)) {
+		AuErr1("%s branch is not exportable\n", au_sbtype(h_sb));
+		goto out_hparent;
+	}
+
+	fh[Fh_br_id] = br->br_id;
+	fh[Fh_sigen] = au_sigen(sb);
+	encode_ino(fh + Fh_ino, inode->i_ino);
+	encode_ino(fh + Fh_dir_ino, dir->i_ino);
+	fh[Fh_igen] = inode->i_generation;
+
+	*max_len -= Fh_tail;
+	fh[Fh_h_type] = exportfs_encode_fh(h_parent, (void *)(fh + Fh_tail),
+					   max_len,
+					   /*connectable or subtreecheck*/0);
+	err = fh[Fh_h_type];
+	*max_len += Fh_tail;
+	/* todo: macros? */
+	if (err != FILEID_INVALID)
+		err = 99;
+	else
+		AuWarn1("%s encode_fh failed\n", au_sbtype(h_sb));
+
+out_hparent:
+	dput(h_parent);
+out_parent:
+	dput(parent);
+out_unlock:
+	ii_read_unlock(inode);
+	si_read_unlock(sb);
+out:
+	if (unlikely(err < 0))
+		err = FILEID_INVALID;
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int aufs_commit_metadata(struct inode *inode)
+{
+	int err;
+	aufs_bindex_t bindex;
+	struct super_block *sb;
+	struct inode *h_inode;
+	int (*f)(struct inode *inode);
+
+	sb = inode->i_sb;
+	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+	ii_write_lock_child(inode);
+	bindex = au_ibtop(inode);
+	AuDebugOn(bindex < 0);
+	h_inode = au_h_iptr(inode, bindex);
+
+	f = h_inode->i_sb->s_export_op->commit_metadata;
+	if (f)
+		err = f(h_inode);
+	else {
+		struct writeback_control wbc = {
+			.sync_mode	= WB_SYNC_ALL,
+			.nr_to_write	= 0 /* metadata only */
+		};
+
+		err = sync_inode(h_inode, &wbc);
+	}
+
+	au_cpup_attr_timesizes(inode);
+	ii_write_unlock(inode);
+	si_read_unlock(sb);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static struct export_operations aufs_export_op = {
+	.fh_to_dentry		= aufs_fh_to_dentry,
+	/* .fh_to_parent	= aufs_fh_to_parent, */
+	.encode_fh		= aufs_encode_fh,
+	.commit_metadata	= aufs_commit_metadata
+};
+
+void au_export_init(struct super_block *sb)
+{
+	struct au_sbinfo *sbinfo;
+	__u32 u;
+
+	BUILD_BUG_ON_MSG(IS_BUILTIN(CONFIG_AUFS_FS)
+			 && IS_MODULE(CONFIG_EXPORTFS),
+			 AUFS_NAME ": unsupported configuration "
+			 "CONFIG_EXPORTFS=m and CONFIG_AUFS_FS=y");
+
+	sb->s_export_op = &aufs_export_op;
+	sbinfo = au_sbi(sb);
+	sbinfo->si_xigen = NULL;
+	get_random_bytes(&u, sizeof(u));
+	BUILD_BUG_ON(sizeof(u) != sizeof(int));
+	atomic_set(&sbinfo->si_xigen_next, u);
+}
diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c
new file mode 100644
index 000000000000..bf9f7bb005bb
--- /dev/null
+++ b/fs/aufs/f_op.c
@@ -0,0 +1,817 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * file and vm operations
+ */
+
+#include <linux/aio.h>
+#include <linux/fs_stack.h>
+#include <linux/mman.h>
+#include <linux/security.h>
+#include "aufs.h"
+
+int au_do_open_nondir(struct file *file, int flags, struct file *h_file)
+{
+	int err;
+	aufs_bindex_t bindex;
+	struct dentry *dentry, *h_dentry;
+	struct au_finfo *finfo;
+	struct inode *h_inode;
+
+	FiMustWriteLock(file);
+
+	err = 0;
+	dentry = file->f_path.dentry;
+	AuDebugOn(IS_ERR_OR_NULL(dentry));
+	finfo = au_fi(file);
+	memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop));
+	atomic_set(&finfo->fi_mmapped, 0);
+	bindex = au_dbtop(dentry);
+	if (!h_file) {
+		h_dentry = au_h_dptr(dentry, bindex);
+		err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
+		if (unlikely(err))
+			goto out;
+		h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
+	} else {
+		h_dentry = h_file->f_path.dentry;
+		err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
+		if (unlikely(err))
+			goto out;
+		get_file(h_file);
+	}
+	if (IS_ERR(h_file))
+		err = PTR_ERR(h_file);
+	else {
+		if ((flags & __O_TMPFILE)
+		    && !(flags & O_EXCL)) {
+			h_inode = file_inode(h_file);
+			spin_lock(&h_inode->i_lock);
+			h_inode->i_state |= I_LINKABLE;
+			spin_unlock(&h_inode->i_lock);
+		}
+		au_set_fbtop(file, bindex);
+		au_set_h_fptr(file, bindex, h_file);
+		au_update_figen(file);
+		/* todo: necessary? */
+		/* file->f_ra = h_file->f_ra; */
+	}
+
+out:
+	return err;
+}
+
+static int aufs_open_nondir(struct inode *inode __maybe_unused,
+			    struct file *file)
+{
+	int err;
+	struct super_block *sb;
+	struct au_do_open_args args = {
+		.open	= au_do_open_nondir
+	};
+
+	AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n",
+	      file, vfsub_file_flags(file), file->f_mode);
+
+	sb = file->f_path.dentry->d_sb;
+	si_read_lock(sb, AuLock_FLUSH);
+	err = au_do_open(file, &args);
+	si_read_unlock(sb);
+	return err;
+}
+
+int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file)
+{
+	struct au_finfo *finfo;
+	aufs_bindex_t bindex;
+
+	finfo = au_fi(file);
+	au_sphl_del(&finfo->fi_hlist,
+		    &au_sbi(file->f_path.dentry->d_sb)->si_files);
+	bindex = finfo->fi_btop;
+	if (bindex >= 0)
+		au_set_h_fptr(file, bindex, NULL);
+
+	au_finfo_fin(file);
+	return 0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_do_flush_nondir(struct file *file, fl_owner_t id)
+{
+	int err;
+	struct file *h_file;
+
+	err = 0;
+	h_file = au_hf_top(file);
+	if (h_file)
+		err = vfsub_flush(h_file, id);
+	return err;
+}
+
+static int aufs_flush_nondir(struct file *file, fl_owner_t id)
+{
+	return au_do_flush(file, id, au_do_flush_nondir);
+}
+
+/* ---------------------------------------------------------------------- */
+/*
+ * read and write functions acquire [fdi]_rwsem once, but release before
+ * mmap_sem. This is because to stop a race condition between mmap(2).
+ * Releasing these aufs-rwsem should be safe, no branch-mamagement (by keeping
+ * si_rwsem), no harmful copy-up should happen. Actually copy-up may happen in
+ * read functions after [fdi]_rwsem are released, but it should be harmless.
+ */
+
+/* Callers should call au_read_post() or fput() in the end */
+struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc)
+{
+	struct file *h_file;
+	int err;
+
+	err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0, lsc);
+	if (!err) {
+		di_read_unlock(file->f_path.dentry, AuLock_IR);
+		h_file = au_hf_top(file);
+		get_file(h_file);
+		if (!keep_fi)
+			fi_read_unlock(file);
+	} else
+		h_file = ERR_PTR(err);
+
+	return h_file;
+}
+
+static void au_read_post(struct inode *inode, struct file *h_file)
+{
+	/* update without lock, I don't think it a problem */
+	fsstack_copy_attr_atime(inode, file_inode(h_file));
+	fput(h_file);
+}
+
+struct au_write_pre {
+	/* input */
+	unsigned int lsc;
+
+	/* output */
+	blkcnt_t blks;
+	aufs_bindex_t btop;
+};
+
+/*
+ * return with iinfo is write-locked
+ * callers should call au_write_post() or iinfo_write_unlock() + fput() in the
+ * end
+ */
+static struct file *au_write_pre(struct file *file, int do_ready,
+				 struct au_write_pre *wpre)
+{
+	struct file *h_file;
+	struct dentry *dentry;
+	int err;
+	unsigned int lsc;
+	struct au_pin pin;
+
+	lsc = 0;
+	if (wpre)
+		lsc = wpre->lsc;
+	err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, lsc);
+	h_file = ERR_PTR(err);
+	if (unlikely(err))
+		goto out;
+
+	dentry = file->f_path.dentry;
+	if (do_ready) {
+		err = au_ready_to_write(file, -1, &pin);
+		if (unlikely(err)) {
+			h_file = ERR_PTR(err);
+			di_write_unlock(dentry);
+			goto out_fi;
+		}
+	}
+
+	di_downgrade_lock(dentry, /*flags*/0);
+	if (wpre)
+		wpre->btop = au_fbtop(file);
+	h_file = au_hf_top(file);
+	get_file(h_file);
+	if (wpre)
+		wpre->blks = file_inode(h_file)->i_blocks;
+	if (do_ready)
+		au_unpin(&pin);
+	di_read_unlock(dentry, /*flags*/0);
+
+out_fi:
+	fi_write_unlock(file);
+out:
+	return h_file;
+}
+
+static void au_write_post(struct inode *inode, struct file *h_file,
+			  struct au_write_pre *wpre, ssize_t written)
+{
+	struct inode *h_inode;
+
+	au_cpup_attr_timesizes(inode);
+	AuDebugOn(au_ibtop(inode) != wpre->btop);
+	h_inode = file_inode(h_file);
+	inode->i_mode = h_inode->i_mode;
+	ii_write_unlock(inode);
+	/* AuDbg("blks %llu, %llu\n", (u64)blks, (u64)h_inode->i_blocks); */
+	if (written > 0)
+		au_fhsm_wrote(inode->i_sb, wpre->btop,
+			      /*force*/h_inode->i_blocks > wpre->blks);
+	fput(h_file);
+}
+
+static ssize_t aufs_read(struct file *file, char __user *buf, size_t count,
+			 loff_t *ppos)
+{
+	ssize_t err;
+	struct inode *inode;
+	struct file *h_file;
+	struct super_block *sb;
+
+	inode = file_inode(file);
+	sb = inode->i_sb;
+	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
+	h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	/* filedata may be obsoleted by concurrent copyup, but no problem */
+	err = vfsub_read_u(h_file, buf, count, ppos);
+	/* todo: necessary? */
+	/* file->f_ra = h_file->f_ra; */
+	au_read_post(inode, h_file);
+
+out:
+	si_read_unlock(sb);
+	return err;
+}
+
+/*
+ * todo: very ugly
+ * it locks both of i_mutex and si_rwsem for read in safe.
+ * if the plink maintenance mode continues forever (that is the problem),
+ * may loop forever.
+ */
+static void au_mtx_and_read_lock(struct inode *inode)
+{
+	int err;
+	struct super_block *sb = inode->i_sb;
+
+	while (1) {
+		inode_lock(inode);
+		err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
+		if (!err)
+			break;
+		inode_unlock(inode);
+		si_read_lock(sb, AuLock_NOPLMW);
+		si_read_unlock(sb);
+	}
+}
+
+static ssize_t aufs_write(struct file *file, const char __user *ubuf,
+			  size_t count, loff_t *ppos)
+{
+	ssize_t err;
+	struct au_write_pre wpre;
+	struct inode *inode;
+	struct file *h_file;
+	char __user *buf = (char __user *)ubuf;
+
+	inode = file_inode(file);
+	au_mtx_and_read_lock(inode);
+
+	wpre.lsc = 0;
+	h_file = au_write_pre(file, /*do_ready*/1, &wpre);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	err = vfsub_write_u(h_file, buf, count, ppos);
+	au_write_post(inode, h_file, &wpre, err);
+
+out:
+	si_read_unlock(inode->i_sb);
+	inode_unlock(inode);
+	return err;
+}
+
+static ssize_t au_do_iter(struct file *h_file, int rw, struct kiocb *kio,
+			  struct iov_iter *iov_iter)
+{
+	ssize_t err;
+	struct file *file;
+	ssize_t (*iter)(struct kiocb *, struct iov_iter *);
+
+	err = security_file_permission(h_file, rw);
+	if (unlikely(err))
+		goto out;
+
+	err = -ENOSYS;
+	iter = NULL;
+	if (rw == MAY_READ)
+		iter = h_file->f_op->read_iter;
+	else if (rw == MAY_WRITE)
+		iter = h_file->f_op->write_iter;
+
+	file = kio->ki_filp;
+	kio->ki_filp = h_file;
+	if (iter) {
+		lockdep_off();
+		err = iter(kio, iov_iter);
+		lockdep_on();
+	} else
+		/* currently there is no such fs */
+		WARN_ON_ONCE(1);
+	kio->ki_filp = file;
+
+out:
+	return err;
+}
+
+static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter)
+{
+	ssize_t err;
+	struct file *file, *h_file;
+	struct inode *inode;
+	struct super_block *sb;
+
+	file = kio->ki_filp;
+	inode = file_inode(file);
+	sb = inode->i_sb;
+	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
+	h_file = au_read_pre(file, /*keep_fi*/1, /*lsc*/0);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	if (au_test_loopback_kthread()) {
+		au_warn_loopback(h_file->f_path.dentry->d_sb);
+		if (file->f_mapping != h_file->f_mapping) {
+			file->f_mapping = h_file->f_mapping;
+			smp_mb(); /* unnecessary? */
+		}
+	}
+	fi_read_unlock(file);
+
+	err = au_do_iter(h_file, MAY_READ, kio, iov_iter);
+	/* todo: necessary? */
+	/* file->f_ra = h_file->f_ra; */
+	au_read_post(inode, h_file);
+
+out:
+	si_read_unlock(sb);
+	return err;
+}
+
+static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter)
+{
+	ssize_t err;
+	struct au_write_pre wpre;
+	struct inode *inode;
+	struct file *file, *h_file;
+
+	file = kio->ki_filp;
+	inode = file_inode(file);
+	au_mtx_and_read_lock(inode);
+
+	wpre.lsc = 0;
+	h_file = au_write_pre(file, /*do_ready*/1, &wpre);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	err = au_do_iter(h_file, MAY_WRITE, kio, iov_iter);
+	au_write_post(inode, h_file, &wpre, err);
+
+out:
+	si_read_unlock(inode->i_sb);
+	inode_unlock(inode);
+	return err;
+}
+
+static ssize_t aufs_splice_read(struct file *file, loff_t *ppos,
+				struct pipe_inode_info *pipe, size_t len,
+				unsigned int flags)
+{
+	ssize_t err;
+	struct file *h_file;
+	struct inode *inode;
+	struct super_block *sb;
+
+	inode = file_inode(file);
+	sb = inode->i_sb;
+	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
+	h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	err = vfsub_splice_to(h_file, ppos, pipe, len, flags);
+	/* todo: necessasry? */
+	/* file->f_ra = h_file->f_ra; */
+	au_read_post(inode, h_file);
+
+out:
+	si_read_unlock(sb);
+	return err;
+}
+
+static ssize_t
+aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos,
+		  size_t len, unsigned int flags)
+{
+	ssize_t err;
+	struct au_write_pre wpre;
+	struct inode *inode;
+	struct file *h_file;
+
+	inode = file_inode(file);
+	au_mtx_and_read_lock(inode);
+
+	wpre.lsc = 0;
+	h_file = au_write_pre(file, /*do_ready*/1, &wpre);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	err = vfsub_splice_from(pipe, h_file, ppos, len, flags);
+	au_write_post(inode, h_file, &wpre, err);
+
+out:
+	si_read_unlock(inode->i_sb);
+	inode_unlock(inode);
+	return err;
+}
+
+static long aufs_fallocate(struct file *file, int mode, loff_t offset,
+			   loff_t len)
+{
+	long err;
+	struct au_write_pre wpre;
+	struct inode *inode;
+	struct file *h_file;
+
+	inode = file_inode(file);
+	au_mtx_and_read_lock(inode);
+
+	wpre.lsc = 0;
+	h_file = au_write_pre(file, /*do_ready*/1, &wpre);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	lockdep_off();
+	err = vfs_fallocate(h_file, mode, offset, len);
+	lockdep_on();
+	au_write_post(inode, h_file, &wpre, /*written*/1);
+
+out:
+	si_read_unlock(inode->i_sb);
+	inode_unlock(inode);
+	return err;
+}
+
+static ssize_t aufs_copy_file_range(struct file *src, loff_t src_pos,
+				    struct file *dst, loff_t dst_pos,
+				    size_t len, unsigned int flags)
+{
+	ssize_t err;
+	struct au_write_pre wpre;
+	enum { SRC, DST };
+	struct {
+		struct inode *inode;
+		struct file *h_file;
+		struct super_block *h_sb;
+	} a[2];
+#define a_src	a[SRC]
+#define a_dst	a[DST]
+
+	err = -EINVAL;
+	a_src.inode = file_inode(src);
+	if (unlikely(!S_ISREG(a_src.inode->i_mode)))
+		goto out;
+	a_dst.inode = file_inode(dst);
+	if (unlikely(!S_ISREG(a_dst.inode->i_mode)))
+		goto out;
+
+	au_mtx_and_read_lock(a_dst.inode);
+	/*
+	 * in order to match the order in di_write_lock2_{child,parent}(),
+	 * use f_path.dentry for this comparision.
+	 */
+	if (src->f_path.dentry < dst->f_path.dentry) {
+		a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_1);
+		err = PTR_ERR(a_src.h_file);
+		if (IS_ERR(a_src.h_file))
+			goto out_si;
+
+		wpre.lsc = AuLsc_FI_2;
+		a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre);
+		err = PTR_ERR(a_dst.h_file);
+		if (IS_ERR(a_dst.h_file)) {
+			au_read_post(a_src.inode, a_src.h_file);
+			goto out_si;
+		}
+	} else {
+		wpre.lsc = AuLsc_FI_1;
+		a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre);
+		err = PTR_ERR(a_dst.h_file);
+		if (IS_ERR(a_dst.h_file))
+			goto out_si;
+
+		a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_2);
+		err = PTR_ERR(a_src.h_file);
+		if (IS_ERR(a_src.h_file)) {
+			au_write_post(a_dst.inode, a_dst.h_file, &wpre,
+				      /*written*/0);
+			goto out_si;
+		}
+	}
+
+	err = -EXDEV;
+	a_src.h_sb = file_inode(a_src.h_file)->i_sb;
+	a_dst.h_sb = file_inode(a_dst.h_file)->i_sb;
+	if (unlikely(a_src.h_sb != a_dst.h_sb)) {
+		AuDbgFile(src);
+		AuDbgFile(dst);
+		goto out_file;
+	}
+
+	err = vfsub_copy_file_range(a_src.h_file, src_pos, a_dst.h_file,
+				    dst_pos, len, flags);
+
+out_file:
+	au_write_post(a_dst.inode, a_dst.h_file, &wpre, err);
+	fi_read_unlock(src);
+	au_read_post(a_src.inode, a_src.h_file);
+out_si:
+	si_read_unlock(a_dst.inode->i_sb);
+	inode_unlock(a_dst.inode);
+out:
+	return err;
+#undef a_src
+#undef a_dst
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * The locking order around current->mmap_sem.
+ * - in most and regular cases
+ *   file I/O syscall -- aufs_read() or something
+ *	-- si_rwsem for read -- mmap_sem
+ *	(Note that [fdi]i_rwsem are released before mmap_sem).
+ * - in mmap case
+ *   mmap(2) -- mmap_sem -- aufs_mmap() -- si_rwsem for read -- [fdi]i_rwsem
+ * This AB-BA order is definitly bad, but is not a problem since "si_rwsem for
+ * read" allows muliple processes to acquire it and [fdi]i_rwsem are not held in
+ * file I/O. Aufs needs to stop lockdep in aufs_mmap() though.
+ * It means that when aufs acquires si_rwsem for write, the process should never
+ * acquire mmap_sem.
+ *
+ * Actually aufs_iterate() holds [fdi]i_rwsem before mmap_sem, but this is not a
+ * problem either since any directory is not able to be mmap-ed.
+ * The similar scenario is applied to aufs_readlink() too.
+ */
+
+#if 0 /* stop calling security_file_mmap() */
+/* cf. linux/include/linux/mman.h: calc_vm_prot_bits() */
+#define AuConv_VM_PROT(f, b)	_calc_vm_trans(f, VM_##b, PROT_##b)
+
+static unsigned long au_arch_prot_conv(unsigned long flags)
+{
+	/* currently ppc64 only */
+#ifdef CONFIG_PPC64
+	/* cf. linux/arch/powerpc/include/asm/mman.h */
+	AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO);
+	return AuConv_VM_PROT(flags, SAO);
+#else
+	AuDebugOn(arch_calc_vm_prot_bits(-1));
+	return 0;
+#endif
+}
+
+static unsigned long au_prot_conv(unsigned long flags)
+{
+	return AuConv_VM_PROT(flags, READ)
+		| AuConv_VM_PROT(flags, WRITE)
+		| AuConv_VM_PROT(flags, EXEC)
+		| au_arch_prot_conv(flags);
+}
+
+/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */
+#define AuConv_VM_MAP(f, b)	_calc_vm_trans(f, VM_##b, MAP_##b)
+
+static unsigned long au_flag_conv(unsigned long flags)
+{
+	return AuConv_VM_MAP(flags, GROWSDOWN)
+		| AuConv_VM_MAP(flags, DENYWRITE)
+		| AuConv_VM_MAP(flags, LOCKED);
+}
+#endif
+
+static int aufs_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int err;
+	const unsigned char wlock
+		= (file->f_mode & FMODE_WRITE) && (vma->vm_flags & VM_SHARED);
+	struct super_block *sb;
+	struct file *h_file;
+	struct inode *inode;
+
+	AuDbgVmRegion(file, vma);
+
+	inode = file_inode(file);
+	sb = inode->i_sb;
+	lockdep_off();
+	si_read_lock(sb, AuLock_NOPLMW);
+
+	h_file = au_write_pre(file, wlock, /*wpre*/NULL);
+	lockdep_on();
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	err = 0;
+	au_set_mmapped(file);
+	au_vm_file_reset(vma, h_file);
+	/*
+	 * we cannot call security_mmap_file() here since it may acquire
+	 * mmap_sem or i_mutex.
+	 *
+	 * err = security_mmap_file(h_file, au_prot_conv(vma->vm_flags),
+	 *			 au_flag_conv(vma->vm_flags));
+	 */
+	if (!err)
+		err = call_mmap(h_file, vma);
+	if (!err) {
+		au_vm_prfile_set(vma, file);
+		fsstack_copy_attr_atime(inode, file_inode(h_file));
+		goto out_fput; /* success */
+	}
+	au_unset_mmapped(file);
+	au_vm_file_reset(vma, file);
+
+out_fput:
+	lockdep_off();
+	ii_write_unlock(inode);
+	lockdep_on();
+	fput(h_file);
+out:
+	lockdep_off();
+	si_read_unlock(sb);
+	lockdep_on();
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end,
+			     int datasync)
+{
+	int err;
+	struct au_write_pre wpre;
+	struct inode *inode;
+	struct file *h_file;
+
+	err = 0; /* -EBADF; */ /* posix? */
+	if (unlikely(!(file->f_mode & FMODE_WRITE)))
+		goto out;
+
+	inode = file_inode(file);
+	au_mtx_and_read_lock(inode);
+
+	wpre.lsc = 0;
+	h_file = au_write_pre(file, /*do_ready*/1, &wpre);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out_unlock;
+
+	err = vfsub_fsync(h_file, &h_file->f_path, datasync);
+	au_write_post(inode, h_file, &wpre, /*written*/0);
+
+out_unlock:
+	si_read_unlock(inode->i_sb);
+	inode_unlock(inode);
+out:
+	return err;
+}
+
+static int aufs_fasync(int fd, struct file *file, int flag)
+{
+	int err;
+	struct file *h_file;
+	struct super_block *sb;
+
+	sb = file->f_path.dentry->d_sb;
+	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
+	h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	if (h_file->f_op->fasync)
+		err = h_file->f_op->fasync(fd, h_file, flag);
+	fput(h_file); /* instead of au_read_post() */
+
+out:
+	si_read_unlock(sb);
+	return err;
+}
+
+static int aufs_setfl(struct file *file, unsigned long arg)
+{
+	int err;
+	struct file *h_file;
+	struct super_block *sb;
+
+	sb = file->f_path.dentry->d_sb;
+	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
+	h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	/* stop calling h_file->fasync */
+	arg |= vfsub_file_flags(file) & FASYNC;
+	err = setfl(/*unused fd*/-1, h_file, arg);
+	fput(h_file); /* instead of au_read_post() */
+
+out:
+	si_read_unlock(sb);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* no one supports this operation, currently */
+#if 0
+static ssize_t aufs_sendpage(struct file *file, struct page *page, int offset,
+			     size_t len, loff_t *pos, int more)
+{
+}
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+const struct file_operations aufs_file_fop = {
+	.owner		= THIS_MODULE,
+
+	.llseek		= default_llseek,
+
+	.read		= aufs_read,
+	.write		= aufs_write,
+	.read_iter	= aufs_read_iter,
+	.write_iter	= aufs_write_iter,
+
+#ifdef CONFIG_AUFS_POLL
+	.poll		= aufs_poll,
+#endif
+	.unlocked_ioctl	= aufs_ioctl_nondir,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= aufs_compat_ioctl_nondir,
+#endif
+	.mmap		= aufs_mmap,
+	.open		= aufs_open_nondir,
+	.flush		= aufs_flush_nondir,
+	.release	= aufs_release_nondir,
+	.fsync		= aufs_fsync_nondir,
+	.fasync		= aufs_fasync,
+	/* .sendpage	= aufs_sendpage, */
+	.setfl		= aufs_setfl,
+	.splice_write	= aufs_splice_write,
+	.splice_read	= aufs_splice_read,
+#if 0
+	.aio_splice_write = aufs_aio_splice_write,
+	.aio_splice_read  = aufs_aio_splice_read,
+#endif
+	.fallocate	= aufs_fallocate,
+	.copy_file_range = aufs_copy_file_range
+};
diff --git a/fs/aufs/fhsm.c b/fs/aufs/fhsm.c
new file mode 100644
index 000000000000..ef6f99e985c8
--- /dev/null
+++ b/fs/aufs/fhsm.c
@@ -0,0 +1,426 @@
+/*
+ * Copyright (C) 2011-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+/*
+ * File-based Hierarchy Storage Management
+ */
+
+#include <linux/anon_inodes.h>
+#include <linux/poll.h>
+#include <linux/seq_file.h>
+#include <linux/statfs.h>
+#include "aufs.h"
+
+static aufs_bindex_t au_fhsm_bottom(struct super_block *sb)
+{
+	struct au_sbinfo *sbinfo;
+	struct au_fhsm *fhsm;
+
+	SiMustAnyLock(sb);
+
+	sbinfo = au_sbi(sb);
+	fhsm = &sbinfo->si_fhsm;
+	AuDebugOn(!fhsm);
+	return fhsm->fhsm_bottom;
+}
+
+void au_fhsm_set_bottom(struct super_block *sb, aufs_bindex_t bindex)
+{
+	struct au_sbinfo *sbinfo;
+	struct au_fhsm *fhsm;
+
+	SiMustWriteLock(sb);
+
+	sbinfo = au_sbi(sb);
+	fhsm = &sbinfo->si_fhsm;
+	AuDebugOn(!fhsm);
+	fhsm->fhsm_bottom = bindex;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_fhsm_test_jiffy(struct au_sbinfo *sbinfo, struct au_branch *br)
+{
+	struct au_br_fhsm *bf;
+
+	bf = br->br_fhsm;
+	MtxMustLock(&bf->bf_lock);
+
+	return !bf->bf_readable
+		|| time_after(jiffies,
+			      bf->bf_jiffy + sbinfo->si_fhsm.fhsm_expire);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void au_fhsm_notify(struct super_block *sb, int val)
+{
+	struct au_sbinfo *sbinfo;
+	struct au_fhsm *fhsm;
+
+	SiMustAnyLock(sb);
+
+	sbinfo = au_sbi(sb);
+	fhsm = &sbinfo->si_fhsm;
+	if (au_fhsm_pid(fhsm)
+	    && atomic_read(&fhsm->fhsm_readable) != -1) {
+		atomic_set(&fhsm->fhsm_readable, val);
+		if (val)
+			wake_up(&fhsm->fhsm_wqh);
+	}
+}
+
+static int au_fhsm_stfs(struct super_block *sb, aufs_bindex_t bindex,
+			struct aufs_stfs *rstfs, int do_lock, int do_notify)
+{
+	int err;
+	struct au_branch *br;
+	struct au_br_fhsm *bf;
+
+	br = au_sbr(sb, bindex);
+	AuDebugOn(au_br_rdonly(br));
+	bf = br->br_fhsm;
+	AuDebugOn(!bf);
+
+	if (do_lock)
+		mutex_lock(&bf->bf_lock);
+	else
+		MtxMustLock(&bf->bf_lock);
+
+	/* sb->s_root for NFS is unreliable */
+	err = au_br_stfs(br, &bf->bf_stfs);
+	if (unlikely(err)) {
+		AuErr1("FHSM failed (%d), b%d, ignored.\n", bindex, err);
+		goto out;
+	}
+
+	bf->bf_jiffy = jiffies;
+	bf->bf_readable = 1;
+	if (do_notify)
+		au_fhsm_notify(sb, /*val*/1);
+	if (rstfs)
+		*rstfs = bf->bf_stfs;
+
+out:
+	if (do_lock)
+		mutex_unlock(&bf->bf_lock);
+	au_fhsm_notify(sb, /*val*/1);
+
+	return err;
+}
+
+void au_fhsm_wrote(struct super_block *sb, aufs_bindex_t bindex, int force)
+{
+	int err;
+	struct au_sbinfo *sbinfo;
+	struct au_fhsm *fhsm;
+	struct au_branch *br;
+	struct au_br_fhsm *bf;
+
+	AuDbg("b%d, force %d\n", bindex, force);
+	SiMustAnyLock(sb);
+
+	sbinfo = au_sbi(sb);
+	fhsm = &sbinfo->si_fhsm;
+	if (!au_ftest_si(sbinfo, FHSM)
+	    || fhsm->fhsm_bottom == bindex)
+		return;
+
+	br = au_sbr(sb, bindex);
+	bf = br->br_fhsm;
+	AuDebugOn(!bf);
+	mutex_lock(&bf->bf_lock);
+	if (force
+	    || au_fhsm_pid(fhsm)
+	    || au_fhsm_test_jiffy(sbinfo, br))
+		err = au_fhsm_stfs(sb, bindex, /*rstfs*/NULL, /*do_lock*/0,
+				  /*do_notify*/1);
+	mutex_unlock(&bf->bf_lock);
+}
+
+void au_fhsm_wrote_all(struct super_block *sb, int force)
+{
+	aufs_bindex_t bindex, bbot;
+	struct au_branch *br;
+
+	/* exclude the bottom */
+	bbot = au_fhsm_bottom(sb);
+	for (bindex = 0; bindex < bbot; bindex++) {
+		br = au_sbr(sb, bindex);
+		if (au_br_fhsm(br->br_perm))
+			au_fhsm_wrote(sb, bindex, force);
+	}
+}
+
+/* ---------------------------------------------------------------------- */
+
+static unsigned int au_fhsm_poll(struct file *file,
+				 struct poll_table_struct *wait)
+{
+	unsigned int mask;
+	struct au_sbinfo *sbinfo;
+	struct au_fhsm *fhsm;
+
+	mask = 0;
+	sbinfo = file->private_data;
+	fhsm = &sbinfo->si_fhsm;
+	poll_wait(file, &fhsm->fhsm_wqh, wait);
+	if (atomic_read(&fhsm->fhsm_readable))
+		mask = POLLIN /* | POLLRDNORM */;
+
+	AuTraceErr((int)mask);
+	return mask;
+}
+
+static int au_fhsm_do_read_one(struct aufs_stbr __user *stbr,
+			      struct aufs_stfs *stfs, __s16 brid)
+{
+	int err;
+
+	err = copy_to_user(&stbr->stfs, stfs, sizeof(*stfs));
+	if (!err)
+		err = __put_user(brid, &stbr->brid);
+	if (unlikely(err))
+		err = -EFAULT;
+
+	return err;
+}
+
+static ssize_t au_fhsm_do_read(struct super_block *sb,
+			       struct aufs_stbr __user *stbr, size_t count)
+{
+	ssize_t err;
+	int nstbr;
+	aufs_bindex_t bindex, bbot;
+	struct au_branch *br;
+	struct au_br_fhsm *bf;
+
+	/* except the bottom branch */
+	err = 0;
+	nstbr = 0;
+	bbot = au_fhsm_bottom(sb);
+	for (bindex = 0; !err && bindex < bbot; bindex++) {
+		br = au_sbr(sb, bindex);
+		if (!au_br_fhsm(br->br_perm))
+			continue;
+
+		bf = br->br_fhsm;
+		mutex_lock(&bf->bf_lock);
+		if (bf->bf_readable) {
+			err = -EFAULT;
+			if (count >= sizeof(*stbr))
+				err = au_fhsm_do_read_one(stbr++, &bf->bf_stfs,
+							  br->br_id);
+			if (!err) {
+				bf->bf_readable = 0;
+				count -= sizeof(*stbr);
+				nstbr++;
+			}
+		}
+		mutex_unlock(&bf->bf_lock);
+	}
+	if (!err)
+		err = sizeof(*stbr) * nstbr;
+
+	return err;
+}
+
+static ssize_t au_fhsm_read(struct file *file, char __user *buf, size_t count,
+			   loff_t *pos)
+{
+	ssize_t err;
+	int readable;
+	aufs_bindex_t nfhsm, bindex, bbot;
+	struct au_sbinfo *sbinfo;
+	struct au_fhsm *fhsm;
+	struct au_branch *br;
+	struct super_block *sb;
+
+	err = 0;
+	sbinfo = file->private_data;
+	fhsm = &sbinfo->si_fhsm;
+need_data:
+	spin_lock_irq(&fhsm->fhsm_wqh.lock);
+	if (!atomic_read(&fhsm->fhsm_readable)) {
+		if (vfsub_file_flags(file) & O_NONBLOCK)
+			err = -EAGAIN;
+		else
+			err = wait_event_interruptible_locked_irq
+				(fhsm->fhsm_wqh,
+				 atomic_read(&fhsm->fhsm_readable));
+	}
+	spin_unlock_irq(&fhsm->fhsm_wqh.lock);
+	if (unlikely(err))
+		goto out;
+
+	/* sb may already be dead */
+	au_rw_read_lock(&sbinfo->si_rwsem);
+	readable = atomic_read(&fhsm->fhsm_readable);
+	if (readable > 0) {
+		sb = sbinfo->si_sb;
+		AuDebugOn(!sb);
+		/* exclude the bottom branch */
+		nfhsm = 0;
+		bbot = au_fhsm_bottom(sb);
+		for (bindex = 0; bindex < bbot; bindex++) {
+			br = au_sbr(sb, bindex);
+			if (au_br_fhsm(br->br_perm))
+				nfhsm++;
+		}
+		err = -EMSGSIZE;
+		if (nfhsm * sizeof(struct aufs_stbr) <= count) {
+			atomic_set(&fhsm->fhsm_readable, 0);
+			err = au_fhsm_do_read(sbinfo->si_sb, (void __user *)buf,
+					     count);
+		}
+	}
+	au_rw_read_unlock(&sbinfo->si_rwsem);
+	if (!readable)
+		goto need_data;
+
+out:
+	return err;
+}
+
+static int au_fhsm_release(struct inode *inode, struct file *file)
+{
+	struct au_sbinfo *sbinfo;
+	struct au_fhsm *fhsm;
+
+	/* sb may already be dead */
+	sbinfo = file->private_data;
+	fhsm = &sbinfo->si_fhsm;
+	spin_lock(&fhsm->fhsm_spin);
+	fhsm->fhsm_pid = 0;
+	spin_unlock(&fhsm->fhsm_spin);
+	kobject_put(&sbinfo->si_kobj);
+
+	return 0;
+}
+
+static const struct file_operations au_fhsm_fops = {
+	.owner		= THIS_MODULE,
+	.llseek		= noop_llseek,
+	.read		= au_fhsm_read,
+	.poll		= au_fhsm_poll,
+	.release	= au_fhsm_release
+};
+
+int au_fhsm_fd(struct super_block *sb, int oflags)
+{
+	int err, fd;
+	struct au_sbinfo *sbinfo;
+	struct au_fhsm *fhsm;
+
+	err = -EPERM;
+	if (unlikely(!capable(CAP_SYS_ADMIN)))
+		goto out;
+
+	err = -EINVAL;
+	if (unlikely(oflags & ~(O_CLOEXEC | O_NONBLOCK)))
+		goto out;
+
+	err = 0;
+	sbinfo = au_sbi(sb);
+	fhsm = &sbinfo->si_fhsm;
+	spin_lock(&fhsm->fhsm_spin);
+	if (!fhsm->fhsm_pid)
+		fhsm->fhsm_pid = current->pid;
+	else
+		err = -EBUSY;
+	spin_unlock(&fhsm->fhsm_spin);
+	if (unlikely(err))
+		goto out;
+
+	oflags |= O_RDONLY;
+	/* oflags |= FMODE_NONOTIFY; */
+	fd = anon_inode_getfd("[aufs_fhsm]", &au_fhsm_fops, sbinfo, oflags);
+	err = fd;
+	if (unlikely(fd < 0))
+		goto out_pid;
+
+	/* succeed reglardless 'fhsm' status */
+	kobject_get(&sbinfo->si_kobj);
+	si_noflush_read_lock(sb);
+	if (au_ftest_si(sbinfo, FHSM))
+		au_fhsm_wrote_all(sb, /*force*/0);
+	si_read_unlock(sb);
+	goto out; /* success */
+
+out_pid:
+	spin_lock(&fhsm->fhsm_spin);
+	fhsm->fhsm_pid = 0;
+	spin_unlock(&fhsm->fhsm_spin);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int au_fhsm_br_alloc(struct au_branch *br)
+{
+	int err;
+
+	err = 0;
+	br->br_fhsm = kmalloc(sizeof(*br->br_fhsm), GFP_NOFS);
+	if (br->br_fhsm)
+		au_br_fhsm_init(br->br_fhsm);
+	else
+		err = -ENOMEM;
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_fhsm_fin(struct super_block *sb)
+{
+	au_fhsm_notify(sb, /*val*/-1);
+}
+
+void au_fhsm_init(struct au_sbinfo *sbinfo)
+{
+	struct au_fhsm *fhsm;
+
+	fhsm = &sbinfo->si_fhsm;
+	spin_lock_init(&fhsm->fhsm_spin);
+	init_waitqueue_head(&fhsm->fhsm_wqh);
+	atomic_set(&fhsm->fhsm_readable, 0);
+	fhsm->fhsm_expire
+		= msecs_to_jiffies(AUFS_FHSM_CACHE_DEF_SEC * MSEC_PER_SEC);
+	fhsm->fhsm_bottom = -1;
+}
+
+void au_fhsm_set(struct au_sbinfo *sbinfo, unsigned int sec)
+{
+	sbinfo->si_fhsm.fhsm_expire
+		= msecs_to_jiffies(sec * MSEC_PER_SEC);
+}
+
+void au_fhsm_show(struct seq_file *seq, struct au_sbinfo *sbinfo)
+{
+	unsigned int u;
+
+	if (!au_ftest_si(sbinfo, FHSM))
+		return;
+
+	u = jiffies_to_msecs(sbinfo->si_fhsm.fhsm_expire) / MSEC_PER_SEC;
+	if (u != AUFS_FHSM_CACHE_DEF_SEC)
+		seq_printf(seq, ",fhsm_sec=%u", u);
+}
diff --git a/fs/aufs/file.c b/fs/aufs/file.c
new file mode 100644
index 000000000000..4f540866a3b3
--- /dev/null
+++ b/fs/aufs/file.c
@@ -0,0 +1,845 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * handling file/dir, and address_space operation
+ */
+
+#ifdef CONFIG_AUFS_DEBUG
+#include <linux/migrate.h>
+#endif
+#include <linux/pagemap.h>
+#include "aufs.h"
+
+/* drop flags for writing */
+unsigned int au_file_roflags(unsigned int flags)
+{
+	flags &= ~(O_WRONLY | O_RDWR | O_APPEND | O_CREAT | O_TRUNC);
+	flags |= O_RDONLY | O_NOATIME;
+	return flags;
+}
+
+/* common functions to regular file and dir */
+struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags,
+		       struct file *file, int force_wr)
+{
+	struct file *h_file;
+	struct dentry *h_dentry;
+	struct inode *h_inode;
+	struct super_block *sb;
+	struct au_branch *br;
+	struct path h_path;
+	int err;
+
+	/* a race condition can happen between open and unlink/rmdir */
+	h_file = ERR_PTR(-ENOENT);
+	h_dentry = au_h_dptr(dentry, bindex);
+	if (au_test_nfsd() && (!h_dentry || d_is_negative(h_dentry)))
+		goto out;
+	h_inode = d_inode(h_dentry);
+	spin_lock(&h_dentry->d_lock);
+	err = (!d_unhashed(dentry) && d_unlinked(h_dentry))
+		/* || !d_inode(dentry)->i_nlink */
+		;
+	spin_unlock(&h_dentry->d_lock);
+	if (unlikely(err))
+		goto out;
+
+	sb = dentry->d_sb;
+	br = au_sbr(sb, bindex);
+	err = au_br_test_oflag(flags, br);
+	h_file = ERR_PTR(err);
+	if (unlikely(err))
+		goto out;
+
+	/* drop flags for writing */
+	if (au_test_ro(sb, bindex, d_inode(dentry))) {
+		if (force_wr && !(flags & O_WRONLY))
+			force_wr = 0;
+		flags = au_file_roflags(flags);
+		if (force_wr) {
+			h_file = ERR_PTR(-EROFS);
+			flags = au_file_roflags(flags);
+			if (unlikely(vfsub_native_ro(h_inode)
+				     || IS_APPEND(h_inode)))
+				goto out;
+			flags &= ~O_ACCMODE;
+			flags |= O_WRONLY;
+		}
+	}
+	flags &= ~O_CREAT;
+	au_br_get(br);
+	h_path.dentry = h_dentry;
+	h_path.mnt = au_br_mnt(br);
+	h_file = vfsub_dentry_open(&h_path, flags);
+	if (IS_ERR(h_file))
+		goto out_br;
+
+	if (flags & __FMODE_EXEC) {
+		err = deny_write_access(h_file);
+		if (unlikely(err)) {
+			fput(h_file);
+			h_file = ERR_PTR(err);
+			goto out_br;
+		}
+	}
+	fsnotify_open(h_file);
+	goto out; /* success */
+
+out_br:
+	au_br_put(br);
+out:
+	return h_file;
+}
+
+static int au_cmoo(struct dentry *dentry)
+{
+	int err, cmoo;
+	unsigned int udba;
+	struct path h_path;
+	struct au_pin pin;
+	struct au_cp_generic cpg = {
+		.dentry	= dentry,
+		.bdst	= -1,
+		.bsrc	= -1,
+		.len	= -1,
+		.pin	= &pin,
+		.flags	= AuCpup_DTIME | AuCpup_HOPEN
+	};
+	struct inode *delegated;
+	struct super_block *sb;
+	struct au_sbinfo *sbinfo;
+	struct au_fhsm *fhsm;
+	pid_t pid;
+	struct au_branch *br;
+	struct dentry *parent;
+	struct au_hinode *hdir;
+
+	DiMustWriteLock(dentry);
+	IiMustWriteLock(d_inode(dentry));
+
+	err = 0;
+	if (IS_ROOT(dentry))
+		goto out;
+	cpg.bsrc = au_dbtop(dentry);
+	if (!cpg.bsrc)
+		goto out;
+
+	sb = dentry->d_sb;
+	sbinfo = au_sbi(sb);
+	fhsm = &sbinfo->si_fhsm;
+	pid = au_fhsm_pid(fhsm);
+	if (pid
+	    && (current->pid == pid
+		|| current->real_parent->pid == pid))
+		goto out;
+
+	br = au_sbr(sb, cpg.bsrc);
+	cmoo = au_br_cmoo(br->br_perm);
+	if (!cmoo)
+		goto out;
+	if (!d_is_reg(dentry))
+		cmoo &= AuBrAttr_COO_ALL;
+	if (!cmoo)
+		goto out;
+
+	parent = dget_parent(dentry);
+	di_write_lock_parent(parent);
+	err = au_wbr_do_copyup_bu(dentry, cpg.bsrc - 1);
+	cpg.bdst = err;
+	if (unlikely(err < 0)) {
+		err = 0;	/* there is no upper writable branch */
+		goto out_dgrade;
+	}
+	AuDbg("bsrc %d, bdst %d\n", cpg.bsrc, cpg.bdst);
+
+	/* do not respect the coo attrib for the target branch */
+	err = au_cpup_dirs(dentry, cpg.bdst);
+	if (unlikely(err))
+		goto out_dgrade;
+
+	di_downgrade_lock(parent, AuLock_IR);
+	udba = au_opt_udba(sb);
+	err = au_pin(&pin, dentry, cpg.bdst, udba,
+		     AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+	if (unlikely(err))
+		goto out_parent;
+
+	err = au_sio_cpup_simple(&cpg);
+	au_unpin(&pin);
+	if (unlikely(err))
+		goto out_parent;
+	if (!(cmoo & AuBrWAttr_MOO))
+		goto out_parent; /* success */
+
+	err = au_pin(&pin, dentry, cpg.bsrc, udba,
+		     AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+	if (unlikely(err))
+		goto out_parent;
+
+	h_path.mnt = au_br_mnt(br);
+	h_path.dentry = au_h_dptr(dentry, cpg.bsrc);
+	hdir = au_hi(d_inode(parent), cpg.bsrc);
+	delegated = NULL;
+	err = vfsub_unlink(hdir->hi_inode, &h_path, &delegated, /*force*/1);
+	au_unpin(&pin);
+	/* todo: keep h_dentry or not? */
+	if (unlikely(err == -EWOULDBLOCK)) {
+		pr_warn("cannot retry for NFSv4 delegation"
+			" for an internal unlink\n");
+		iput(delegated);
+	}
+	if (unlikely(err)) {
+		pr_err("unlink %pd after coo failed (%d), ignored\n",
+		       dentry, err);
+		err = 0;
+	}
+	goto out_parent; /* success */
+
+out_dgrade:
+	di_downgrade_lock(parent, AuLock_IR);
+out_parent:
+	di_read_unlock(parent, AuLock_IR);
+	dput(parent);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+int au_do_open(struct file *file, struct au_do_open_args *args)
+{
+	int err, aopen = args->aopen;
+	struct dentry *dentry;
+	struct au_finfo *finfo;
+
+	if (!aopen)
+		err = au_finfo_init(file, args->fidir);
+	else {
+		lockdep_off();
+		err = au_finfo_init(file, args->fidir);
+		lockdep_on();
+	}
+	if (unlikely(err))
+		goto out;
+
+	dentry = file->f_path.dentry;
+	AuDebugOn(IS_ERR_OR_NULL(dentry));
+	di_write_lock_child(dentry);
+	err = au_cmoo(dentry);
+	di_downgrade_lock(dentry, AuLock_IR);
+	if (!err)
+		err = args->open(file, vfsub_file_flags(file), NULL);
+	di_read_unlock(dentry, AuLock_IR);
+
+	finfo = au_fi(file);
+	if (!err) {
+		finfo->fi_file = file;
+		au_sphl_add(&finfo->fi_hlist,
+			    &au_sbi(file->f_path.dentry->d_sb)->si_files);
+	}
+	if (!aopen)
+		fi_write_unlock(file);
+	else {
+		lockdep_off();
+		fi_write_unlock(file);
+		lockdep_on();
+	}
+	if (unlikely(err)) {
+		finfo->fi_hdir = NULL;
+		au_finfo_fin(file);
+	}
+
+out:
+	return err;
+}
+
+int au_reopen_nondir(struct file *file)
+{
+	int err;
+	aufs_bindex_t btop;
+	struct dentry *dentry;
+	struct file *h_file, *h_file_tmp;
+
+	dentry = file->f_path.dentry;
+	btop = au_dbtop(dentry);
+	h_file_tmp = NULL;
+	if (au_fbtop(file) == btop) {
+		h_file = au_hf_top(file);
+		if (file->f_mode == h_file->f_mode)
+			return 0; /* success */
+		h_file_tmp = h_file;
+		get_file(h_file_tmp);
+		au_set_h_fptr(file, btop, NULL);
+	}
+	AuDebugOn(au_fi(file)->fi_hdir);
+	/*
+	 * it can happen
+	 * file exists on both of rw and ro
+	 * open --> dbtop and fbtop are both 0
+	 * prepend a branch as rw, "rw" become ro
+	 * remove rw/file
+	 * delete the top branch, "rw" becomes rw again
+	 *	--> dbtop is 1, fbtop is still 0
+	 * write --> fbtop is 0 but dbtop is 1
+	 */
+	/* AuDebugOn(au_fbtop(file) < btop); */
+
+	h_file = au_h_open(dentry, btop, vfsub_file_flags(file) & ~O_TRUNC,
+			   file, /*force_wr*/0);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file)) {
+		if (h_file_tmp) {
+			au_sbr_get(dentry->d_sb, btop);
+			au_set_h_fptr(file, btop, h_file_tmp);
+			h_file_tmp = NULL;
+		}
+		goto out; /* todo: close all? */
+	}
+
+	err = 0;
+	au_set_fbtop(file, btop);
+	au_set_h_fptr(file, btop, h_file);
+	au_update_figen(file);
+	/* todo: necessary? */
+	/* file->f_ra = h_file->f_ra; */
+
+out:
+	if (h_file_tmp)
+		fput(h_file_tmp);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_reopen_wh(struct file *file, aufs_bindex_t btgt,
+			struct dentry *hi_wh)
+{
+	int err;
+	aufs_bindex_t btop;
+	struct au_dinfo *dinfo;
+	struct dentry *h_dentry;
+	struct au_hdentry *hdp;
+
+	dinfo = au_di(file->f_path.dentry);
+	AuRwMustWriteLock(&dinfo->di_rwsem);
+
+	btop = dinfo->di_btop;
+	dinfo->di_btop = btgt;
+	hdp = au_hdentry(dinfo, btgt);
+	h_dentry = hdp->hd_dentry;
+	hdp->hd_dentry = hi_wh;
+	err = au_reopen_nondir(file);
+	hdp->hd_dentry = h_dentry;
+	dinfo->di_btop = btop;
+
+	return err;
+}
+
+static int au_ready_to_write_wh(struct file *file, loff_t len,
+				aufs_bindex_t bcpup, struct au_pin *pin)
+{
+	int err;
+	struct inode *inode, *h_inode;
+	struct dentry *h_dentry, *hi_wh;
+	struct au_cp_generic cpg = {
+		.dentry	= file->f_path.dentry,
+		.bdst	= bcpup,
+		.bsrc	= -1,
+		.len	= len,
+		.pin	= pin
+	};
+
+	au_update_dbtop(cpg.dentry);
+	inode = d_inode(cpg.dentry);
+	h_inode = NULL;
+	if (au_dbtop(cpg.dentry) <= bcpup
+	    && au_dbbot(cpg.dentry) >= bcpup) {
+		h_dentry = au_h_dptr(cpg.dentry, bcpup);
+		if (h_dentry && d_is_positive(h_dentry))
+			h_inode = d_inode(h_dentry);
+	}
+	hi_wh = au_hi_wh(inode, bcpup);
+	if (!hi_wh && !h_inode)
+		err = au_sio_cpup_wh(&cpg, file);
+	else
+		/* already copied-up after unlink */
+		err = au_reopen_wh(file, bcpup, hi_wh);
+
+	if (!err
+	    && (inode->i_nlink > 1
+		|| (inode->i_state & I_LINKABLE))
+	    && au_opt_test(au_mntflags(cpg.dentry->d_sb), PLINK))
+		au_plink_append(inode, bcpup, au_h_dptr(cpg.dentry, bcpup));
+
+	return err;
+}
+
+/*
+ * prepare the @file for writing.
+ */
+int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin)
+{
+	int err;
+	aufs_bindex_t dbtop;
+	struct dentry *parent;
+	struct inode *inode;
+	struct super_block *sb;
+	struct file *h_file;
+	struct au_cp_generic cpg = {
+		.dentry	= file->f_path.dentry,
+		.bdst	= -1,
+		.bsrc	= -1,
+		.len	= len,
+		.pin	= pin,
+		.flags	= AuCpup_DTIME
+	};
+
+	sb = cpg.dentry->d_sb;
+	inode = d_inode(cpg.dentry);
+	cpg.bsrc = au_fbtop(file);
+	err = au_test_ro(sb, cpg.bsrc, inode);
+	if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) {
+		err = au_pin(pin, cpg.dentry, cpg.bsrc, AuOpt_UDBA_NONE,
+			     /*flags*/0);
+		goto out;
+	}
+
+	/* need to cpup or reopen */
+	parent = dget_parent(cpg.dentry);
+	di_write_lock_parent(parent);
+	err = AuWbrCopyup(au_sbi(sb), cpg.dentry);
+	cpg.bdst = err;
+	if (unlikely(err < 0))
+		goto out_dgrade;
+	err = 0;
+
+	if (!d_unhashed(cpg.dentry) && !au_h_dptr(parent, cpg.bdst)) {
+		err = au_cpup_dirs(cpg.dentry, cpg.bdst);
+		if (unlikely(err))
+			goto out_dgrade;
+	}
+
+	err = au_pin(pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE,
+		     AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+	if (unlikely(err))
+		goto out_dgrade;
+
+	dbtop = au_dbtop(cpg.dentry);
+	if (dbtop <= cpg.bdst)
+		cpg.bsrc = cpg.bdst;
+
+	if (dbtop <= cpg.bdst		/* just reopen */
+	    || !d_unhashed(cpg.dentry)	/* copyup and reopen */
+		) {
+		h_file = au_h_open_pre(cpg.dentry, cpg.bsrc, /*force_wr*/0);
+		if (IS_ERR(h_file))
+			err = PTR_ERR(h_file);
+		else {
+			di_downgrade_lock(parent, AuLock_IR);
+			if (dbtop > cpg.bdst)
+				err = au_sio_cpup_simple(&cpg);
+			if (!err)
+				err = au_reopen_nondir(file);
+			au_h_open_post(cpg.dentry, cpg.bsrc, h_file);
+		}
+	} else {			/* copyup as wh and reopen */
+		/*
+		 * since writable hfsplus branch is not supported,
+		 * h_open_pre/post() are unnecessary.
+		 */
+		err = au_ready_to_write_wh(file, len, cpg.bdst, pin);
+		di_downgrade_lock(parent, AuLock_IR);
+	}
+
+	if (!err) {
+		au_pin_set_parent_lflag(pin, /*lflag*/0);
+		goto out_dput; /* success */
+	}
+	au_unpin(pin);
+	goto out_unlock;
+
+out_dgrade:
+	di_downgrade_lock(parent, AuLock_IR);
+out_unlock:
+	di_read_unlock(parent, AuLock_IR);
+out_dput:
+	dput(parent);
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int au_do_flush(struct file *file, fl_owner_t id,
+		int (*flush)(struct file *file, fl_owner_t id))
+{
+	int err;
+	struct super_block *sb;
+	struct inode *inode;
+
+	inode = file_inode(file);
+	sb = inode->i_sb;
+	si_noflush_read_lock(sb);
+	fi_read_lock(file);
+	ii_read_lock_child(inode);
+
+	err = flush(file, id);
+	au_cpup_attr_timesizes(inode);
+
+	ii_read_unlock(inode);
+	fi_read_unlock(file);
+	si_read_unlock(sb);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_file_refresh_by_inode(struct file *file, int *need_reopen)
+{
+	int err;
+	struct au_pin pin;
+	struct au_finfo *finfo;
+	struct dentry *parent, *hi_wh;
+	struct inode *inode;
+	struct super_block *sb;
+	struct au_cp_generic cpg = {
+		.dentry	= file->f_path.dentry,
+		.bdst	= -1,
+		.bsrc	= -1,
+		.len	= -1,
+		.pin	= &pin,
+		.flags	= AuCpup_DTIME
+	};
+
+	FiMustWriteLock(file);
+
+	err = 0;
+	finfo = au_fi(file);
+	sb = cpg.dentry->d_sb;
+	inode = d_inode(cpg.dentry);
+	cpg.bdst = au_ibtop(inode);
+	if (cpg.bdst == finfo->fi_btop || IS_ROOT(cpg.dentry))
+		goto out;
+
+	parent = dget_parent(cpg.dentry);
+	if (au_test_ro(sb, cpg.bdst, inode)) {
+		di_read_lock_parent(parent, !AuLock_IR);
+		err = AuWbrCopyup(au_sbi(sb), cpg.dentry);
+		cpg.bdst = err;
+		di_read_unlock(parent, !AuLock_IR);
+		if (unlikely(err < 0))
+			goto out_parent;
+		err = 0;
+	}
+
+	di_read_lock_parent(parent, AuLock_IR);
+	hi_wh = au_hi_wh(inode, cpg.bdst);
+	if (!S_ISDIR(inode->i_mode)
+	    && au_opt_test(au_mntflags(sb), PLINK)
+	    && au_plink_test(inode)
+	    && !d_unhashed(cpg.dentry)
+	    && cpg.bdst < au_dbtop(cpg.dentry)) {
+		err = au_test_and_cpup_dirs(cpg.dentry, cpg.bdst);
+		if (unlikely(err))
+			goto out_unlock;
+
+		/* always superio. */
+		err = au_pin(&pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE,
+			     AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+		if (!err) {
+			err = au_sio_cpup_simple(&cpg);
+			au_unpin(&pin);
+		}
+	} else if (hi_wh) {
+		/* already copied-up after unlink */
+		err = au_reopen_wh(file, cpg.bdst, hi_wh);
+		*need_reopen = 0;
+	}
+
+out_unlock:
+	di_read_unlock(parent, AuLock_IR);
+out_parent:
+	dput(parent);
+out:
+	return err;
+}
+
+static void au_do_refresh_dir(struct file *file)
+{
+	aufs_bindex_t bindex, bbot, new_bindex, brid;
+	struct au_hfile *p, tmp, *q;
+	struct au_finfo *finfo;
+	struct super_block *sb;
+	struct au_fidir *fidir;
+
+	FiMustWriteLock(file);
+
+	sb = file->f_path.dentry->d_sb;
+	finfo = au_fi(file);
+	fidir = finfo->fi_hdir;
+	AuDebugOn(!fidir);
+	p = fidir->fd_hfile + finfo->fi_btop;
+	brid = p->hf_br->br_id;
+	bbot = fidir->fd_bbot;
+	for (bindex = finfo->fi_btop; bindex <= bbot; bindex++, p++) {
+		if (!p->hf_file)
+			continue;
+
+		new_bindex = au_br_index(sb, p->hf_br->br_id);
+		if (new_bindex == bindex)
+			continue;
+		if (new_bindex < 0) {
+			au_set_h_fptr(file, bindex, NULL);
+			continue;
+		}
+
+		/* swap two lower inode, and loop again */
+		q = fidir->fd_hfile + new_bindex;
+		tmp = *q;
+		*q = *p;
+		*p = tmp;
+		if (tmp.hf_file) {
+			bindex--;
+			p--;
+		}
+	}
+
+	p = fidir->fd_hfile;
+	if (!au_test_mmapped(file) && !d_unlinked(file->f_path.dentry)) {
+		bbot = au_sbbot(sb);
+		for (finfo->fi_btop = 0; finfo->fi_btop <= bbot;
+		     finfo->fi_btop++, p++)
+			if (p->hf_file) {
+				if (file_inode(p->hf_file))
+					break;
+				au_hfput(p, /*execed*/0);
+			}
+	} else {
+		bbot = au_br_index(sb, brid);
+		for (finfo->fi_btop = 0; finfo->fi_btop < bbot;
+		     finfo->fi_btop++, p++)
+			if (p->hf_file)
+				au_hfput(p, /*execed*/0);
+		bbot = au_sbbot(sb);
+	}
+
+	p = fidir->fd_hfile + bbot;
+	for (fidir->fd_bbot = bbot; fidir->fd_bbot >= finfo->fi_btop;
+	     fidir->fd_bbot--, p--)
+		if (p->hf_file) {
+			if (file_inode(p->hf_file))
+				break;
+			au_hfput(p, /*execed*/0);
+		}
+	AuDebugOn(fidir->fd_bbot < finfo->fi_btop);
+}
+
+/*
+ * after branch manipulating, refresh the file.
+ */
+static int refresh_file(struct file *file, int (*reopen)(struct file *file))
+{
+	int err, need_reopen, nbr;
+	aufs_bindex_t bbot, bindex;
+	struct dentry *dentry;
+	struct super_block *sb;
+	struct au_finfo *finfo;
+	struct au_hfile *hfile;
+
+	dentry = file->f_path.dentry;
+	sb = dentry->d_sb;
+	nbr = au_sbbot(sb) + 1;
+	finfo = au_fi(file);
+	if (!finfo->fi_hdir) {
+		hfile = &finfo->fi_htop;
+		AuDebugOn(!hfile->hf_file);
+		bindex = au_br_index(sb, hfile->hf_br->br_id);
+		AuDebugOn(bindex < 0);
+		if (bindex != finfo->fi_btop)
+			au_set_fbtop(file, bindex);
+	} else {
+		err = au_fidir_realloc(finfo, nbr, /*may_shrink*/0);
+		if (unlikely(err))
+			goto out;
+		au_do_refresh_dir(file);
+	}
+
+	err = 0;
+	need_reopen = 1;
+	if (!au_test_mmapped(file))
+		err = au_file_refresh_by_inode(file, &need_reopen);
+	if (finfo->fi_hdir)
+		/* harmless if err */
+		au_fidir_realloc(finfo, nbr, /*may_shrink*/1);
+	if (!err && need_reopen && !d_unlinked(dentry))
+		err = reopen(file);
+	if (!err) {
+		au_update_figen(file);
+		goto out; /* success */
+	}
+
+	/* error, close all lower files */
+	if (finfo->fi_hdir) {
+		bbot = au_fbbot_dir(file);
+		for (bindex = au_fbtop(file); bindex <= bbot; bindex++)
+			au_set_h_fptr(file, bindex, NULL);
+	}
+
+out:
+	return err;
+}
+
+/* common function to regular file and dir */
+int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file),
+			  int wlock, unsigned int fi_lsc)
+{
+	int err;
+	unsigned int sigen, figen;
+	aufs_bindex_t btop;
+	unsigned char pseudo_link;
+	struct dentry *dentry;
+	struct inode *inode;
+
+	err = 0;
+	dentry = file->f_path.dentry;
+	inode = d_inode(dentry);
+	sigen = au_sigen(dentry->d_sb);
+	fi_write_lock_nested(file, fi_lsc);
+	figen = au_figen(file);
+	if (!fi_lsc)
+		di_write_lock_child(dentry);
+	else
+		di_write_lock_child2(dentry);
+	btop = au_dbtop(dentry);
+	pseudo_link = (btop != au_ibtop(inode));
+	if (sigen == figen && !pseudo_link && au_fbtop(file) == btop) {
+		if (!wlock) {
+			di_downgrade_lock(dentry, AuLock_IR);
+			fi_downgrade_lock(file);
+		}
+		goto out; /* success */
+	}
+
+	AuDbg("sigen %d, figen %d\n", sigen, figen);
+	if (au_digen_test(dentry, sigen)) {
+		err = au_reval_dpath(dentry, sigen);
+		AuDebugOn(!err && au_digen_test(dentry, sigen));
+	}
+
+	if (!err)
+		err = refresh_file(file, reopen);
+	if (!err) {
+		if (!wlock) {
+			di_downgrade_lock(dentry, AuLock_IR);
+			fi_downgrade_lock(file);
+		}
+	} else {
+		di_write_unlock(dentry);
+		fi_write_unlock(file);
+	}
+
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* cf. aufs_nopage() */
+/* for madvise(2) */
+static int aufs_readpage(struct file *file __maybe_unused, struct page *page)
+{
+	unlock_page(page);
+	return 0;
+}
+
+/* it will never be called, but necessary to support O_DIRECT */
+static ssize_t aufs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+{ BUG(); return 0; }
+
+/* they will never be called. */
+#ifdef CONFIG_AUFS_DEBUG
+static int aufs_write_begin(struct file *file, struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned flags,
+			    struct page **pagep, void **fsdata)
+{ AuUnsupport(); return 0; }
+static int aufs_write_end(struct file *file, struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct page *page, void *fsdata)
+{ AuUnsupport(); return 0; }
+static int aufs_writepage(struct page *page, struct writeback_control *wbc)
+{ AuUnsupport(); return 0; }
+
+static int aufs_set_page_dirty(struct page *page)
+{ AuUnsupport(); return 0; }
+static void aufs_invalidatepage(struct page *page, unsigned int offset,
+				unsigned int length)
+{ AuUnsupport(); }
+static int aufs_releasepage(struct page *page, gfp_t gfp)
+{ AuUnsupport(); return 0; }
+#if 0 /* called by memory compaction regardless file */
+static int aufs_migratepage(struct address_space *mapping, struct page *newpage,
+			    struct page *page, enum migrate_mode mode)
+{ AuUnsupport(); return 0; }
+#endif
+static bool aufs_isolate_page(struct page *page, isolate_mode_t mode)
+{ AuUnsupport(); return true; }
+static void aufs_putback_page(struct page *page)
+{ AuUnsupport(); }
+static int aufs_launder_page(struct page *page)
+{ AuUnsupport(); return 0; }
+static int aufs_is_partially_uptodate(struct page *page,
+				      unsigned long from,
+				      unsigned long count)
+{ AuUnsupport(); return 0; }
+static void aufs_is_dirty_writeback(struct page *page, bool *dirty,
+				    bool *writeback)
+{ AuUnsupport(); }
+static int aufs_error_remove_page(struct address_space *mapping,
+				  struct page *page)
+{ AuUnsupport(); return 0; }
+static int aufs_swap_activate(struct swap_info_struct *sis, struct file *file,
+			      sector_t *span)
+{ AuUnsupport(); return 0; }
+static void aufs_swap_deactivate(struct file *file)
+{ AuUnsupport(); }
+#endif /* CONFIG_AUFS_DEBUG */
+
+const struct address_space_operations aufs_aop = {
+	.readpage		= aufs_readpage,
+	.direct_IO		= aufs_direct_IO,
+#ifdef CONFIG_AUFS_DEBUG
+	.writepage		= aufs_writepage,
+	/* no writepages, because of writepage */
+	.set_page_dirty		= aufs_set_page_dirty,
+	/* no readpages, because of readpage */
+	.write_begin		= aufs_write_begin,
+	.write_end		= aufs_write_end,
+	/* no bmap, no block device */
+	.invalidatepage		= aufs_invalidatepage,
+	.releasepage		= aufs_releasepage,
+	/* is fallback_migrate_page ok? */
+	/* .migratepage		= aufs_migratepage, */
+	.isolate_page		= aufs_isolate_page,
+	.putback_page		= aufs_putback_page,
+	.launder_page		= aufs_launder_page,
+	.is_partially_uptodate	= aufs_is_partially_uptodate,
+	.is_dirty_writeback	= aufs_is_dirty_writeback,
+	.error_remove_page	= aufs_error_remove_page,
+	.swap_activate		= aufs_swap_activate,
+	.swap_deactivate	= aufs_swap_deactivate
+#endif /* CONFIG_AUFS_DEBUG */
+};
diff --git a/fs/aufs/file.h b/fs/aufs/file.h
new file mode 100644
index 000000000000..65b3a3f927e4
--- /dev/null
+++ b/fs/aufs/file.h
@@ -0,0 +1,331 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * file operations
+ */
+
+#ifndef __AUFS_FILE_H__
+#define __AUFS_FILE_H__
+
+#ifdef __KERNEL__
+
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/mm_types.h>
+#include <linux/poll.h>
+#include "rwsem.h"
+
+struct au_branch;
+struct au_hfile {
+	struct file		*hf_file;
+	struct au_branch	*hf_br;
+};
+
+struct au_vdir;
+struct au_fidir {
+	aufs_bindex_t		fd_bbot;
+	aufs_bindex_t		fd_nent;
+	struct au_vdir		*fd_vdir_cache;
+	struct au_hfile		fd_hfile[];
+};
+
+static inline int au_fidir_sz(int nent)
+{
+	AuDebugOn(nent < 0);
+	return sizeof(struct au_fidir) + sizeof(struct au_hfile) * nent;
+}
+
+struct au_finfo {
+	atomic_t		fi_generation;
+
+	struct au_rwsem		fi_rwsem;
+	aufs_bindex_t		fi_btop;
+
+	/* do not union them */
+	struct {				/* for non-dir */
+		struct au_hfile			fi_htop;
+		atomic_t			fi_mmapped;
+	};
+	struct au_fidir		*fi_hdir;	/* for dir only */
+
+	struct hlist_node	fi_hlist;
+	struct file		*fi_file;	/* very ugly */
+} ____cacheline_aligned_in_smp;
+
+/* ---------------------------------------------------------------------- */
+
+/* file.c */
+extern const struct address_space_operations aufs_aop;
+unsigned int au_file_roflags(unsigned int flags);
+struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags,
+		       struct file *file, int force_wr);
+struct au_do_open_args {
+	int		aopen;
+	int		(*open)(struct file *file, int flags,
+				struct file *h_file);
+	struct au_fidir	*fidir;
+	struct file	*h_file;
+};
+int au_do_open(struct file *file, struct au_do_open_args *args);
+int au_reopen_nondir(struct file *file);
+struct au_pin;
+int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin);
+int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file),
+			  int wlock, unsigned int fi_lsc);
+int au_do_flush(struct file *file, fl_owner_t id,
+		int (*flush)(struct file *file, fl_owner_t id));
+
+/* poll.c */
+#ifdef CONFIG_AUFS_POLL
+unsigned int aufs_poll(struct file *file, poll_table *wait);
+#endif
+
+#ifdef CONFIG_AUFS_BR_HFSPLUS
+/* hfsplus.c */
+struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex,
+			   int force_wr);
+void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex,
+		    struct file *h_file);
+#else
+AuStub(struct file *, au_h_open_pre, return NULL, struct dentry *dentry,
+       aufs_bindex_t bindex, int force_wr)
+AuStubVoid(au_h_open_post, struct dentry *dentry, aufs_bindex_t bindex,
+	   struct file *h_file);
+#endif
+
+/* f_op.c */
+extern const struct file_operations aufs_file_fop;
+int au_do_open_nondir(struct file *file, int flags, struct file *h_file);
+int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file);
+struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc);
+
+/* finfo.c */
+void au_hfput(struct au_hfile *hf, int execed);
+void au_set_h_fptr(struct file *file, aufs_bindex_t bindex,
+		   struct file *h_file);
+
+void au_update_figen(struct file *file);
+struct au_fidir *au_fidir_alloc(struct super_block *sb);
+int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink);
+
+void au_fi_init_once(void *_fi);
+void au_finfo_fin(struct file *file);
+int au_finfo_init(struct file *file, struct au_fidir *fidir);
+
+/* ioctl.c */
+long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg);
+#ifdef CONFIG_COMPAT
+long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd,
+			   unsigned long arg);
+long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd,
+			      unsigned long arg);
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+static inline struct au_finfo *au_fi(struct file *file)
+{
+	return file->private_data;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * fi_read_lock, fi_write_lock,
+ * fi_read_unlock, fi_write_unlock, fi_downgrade_lock
+ */
+AuSimpleRwsemFuncs(fi, struct file *f, &au_fi(f)->fi_rwsem);
+
+/* lock subclass for finfo */
+enum {
+	AuLsc_FI_1,
+	AuLsc_FI_2
+};
+
+static inline void fi_read_lock_nested(struct file *f, unsigned int lsc)
+{
+	au_rw_read_lock_nested(&au_fi(f)->fi_rwsem, lsc);
+}
+
+static inline void fi_write_lock_nested(struct file *f, unsigned int lsc)
+{
+	au_rw_write_lock_nested(&au_fi(f)->fi_rwsem, lsc);
+}
+
+/*
+ * fi_read_lock_1, fi_write_lock_1,
+ * fi_read_lock_2, fi_write_lock_2
+ */
+#define AuReadLockFunc(name) \
+static inline void fi_read_lock_##name(struct file *f) \
+{ fi_read_lock_nested(f, AuLsc_FI_##name); }
+
+#define AuWriteLockFunc(name) \
+static inline void fi_write_lock_##name(struct file *f) \
+{ fi_write_lock_nested(f, AuLsc_FI_##name); }
+
+#define AuRWLockFuncs(name) \
+	AuReadLockFunc(name) \
+	AuWriteLockFunc(name)
+
+AuRWLockFuncs(1);
+AuRWLockFuncs(2);
+
+#undef AuReadLockFunc
+#undef AuWriteLockFunc
+#undef AuRWLockFuncs
+
+#define FiMustNoWaiters(f)	AuRwMustNoWaiters(&au_fi(f)->fi_rwsem)
+#define FiMustAnyLock(f)	AuRwMustAnyLock(&au_fi(f)->fi_rwsem)
+#define FiMustWriteLock(f)	AuRwMustWriteLock(&au_fi(f)->fi_rwsem)
+
+/* ---------------------------------------------------------------------- */
+
+/* todo: hard/soft set? */
+static inline aufs_bindex_t au_fbtop(struct file *file)
+{
+	FiMustAnyLock(file);
+	return au_fi(file)->fi_btop;
+}
+
+static inline aufs_bindex_t au_fbbot_dir(struct file *file)
+{
+	FiMustAnyLock(file);
+	AuDebugOn(!au_fi(file)->fi_hdir);
+	return au_fi(file)->fi_hdir->fd_bbot;
+}
+
+static inline struct au_vdir *au_fvdir_cache(struct file *file)
+{
+	FiMustAnyLock(file);
+	AuDebugOn(!au_fi(file)->fi_hdir);
+	return au_fi(file)->fi_hdir->fd_vdir_cache;
+}
+
+static inline void au_set_fbtop(struct file *file, aufs_bindex_t bindex)
+{
+	FiMustWriteLock(file);
+	au_fi(file)->fi_btop = bindex;
+}
+
+static inline void au_set_fbbot_dir(struct file *file, aufs_bindex_t bindex)
+{
+	FiMustWriteLock(file);
+	AuDebugOn(!au_fi(file)->fi_hdir);
+	au_fi(file)->fi_hdir->fd_bbot = bindex;
+}
+
+static inline void au_set_fvdir_cache(struct file *file,
+				      struct au_vdir *vdir_cache)
+{
+	FiMustWriteLock(file);
+	AuDebugOn(!au_fi(file)->fi_hdir);
+	au_fi(file)->fi_hdir->fd_vdir_cache = vdir_cache;
+}
+
+static inline struct file *au_hf_top(struct file *file)
+{
+	FiMustAnyLock(file);
+	AuDebugOn(au_fi(file)->fi_hdir);
+	return au_fi(file)->fi_htop.hf_file;
+}
+
+static inline struct file *au_hf_dir(struct file *file, aufs_bindex_t bindex)
+{
+	FiMustAnyLock(file);
+	AuDebugOn(!au_fi(file)->fi_hdir);
+	return au_fi(file)->fi_hdir->fd_hfile[0 + bindex].hf_file;
+}
+
+/* todo: memory barrier? */
+static inline unsigned int au_figen(struct file *f)
+{
+	return atomic_read(&au_fi(f)->fi_generation);
+}
+
+static inline void au_set_mmapped(struct file *f)
+{
+	if (atomic_inc_return(&au_fi(f)->fi_mmapped))
+		return;
+	pr_warn("fi_mmapped wrapped around\n");
+	while (!atomic_inc_return(&au_fi(f)->fi_mmapped))
+		;
+}
+
+static inline void au_unset_mmapped(struct file *f)
+{
+	atomic_dec(&au_fi(f)->fi_mmapped);
+}
+
+static inline int au_test_mmapped(struct file *f)
+{
+	return atomic_read(&au_fi(f)->fi_mmapped);
+}
+
+/* customize vma->vm_file */
+
+static inline void au_do_vm_file_reset(struct vm_area_struct *vma,
+				       struct file *file)
+{
+	struct file *f;
+
+	f = vma->vm_file;
+	get_file(file);
+	vma->vm_file = file;
+	fput(f);
+}
+
+#ifdef CONFIG_MMU
+#define AuDbgVmRegion(file, vma) do {} while (0)
+
+static inline void au_vm_file_reset(struct vm_area_struct *vma,
+				    struct file *file)
+{
+	au_do_vm_file_reset(vma, file);
+}
+#else
+#define AuDbgVmRegion(file, vma) \
+	AuDebugOn((vma)->vm_region && (vma)->vm_region->vm_file != (file))
+
+static inline void au_vm_file_reset(struct vm_area_struct *vma,
+				    struct file *file)
+{
+	struct file *f;
+
+	au_do_vm_file_reset(vma, file);
+	f = vma->vm_region->vm_file;
+	get_file(file);
+	vma->vm_region->vm_file = file;
+	fput(f);
+}
+#endif /* CONFIG_MMU */
+
+/* handle vma->vm_prfile */
+static inline void au_vm_prfile_set(struct vm_area_struct *vma,
+				    struct file *file)
+{
+	get_file(file);
+	vma->vm_prfile = file;
+#ifndef CONFIG_MMU
+	get_file(file);
+	vma->vm_region->vm_prfile = file;
+#endif
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_FILE_H__ */
diff --git a/fs/aufs/finfo.c b/fs/aufs/finfo.c
new file mode 100644
index 000000000000..3a8131d43a86
--- /dev/null
+++ b/fs/aufs/finfo.c
@@ -0,0 +1,148 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * file private data
+ */
+
+#include "aufs.h"
+
+void au_hfput(struct au_hfile *hf, int execed)
+{
+	if (execed)
+		allow_write_access(hf->hf_file);
+	fput(hf->hf_file);
+	hf->hf_file = NULL;
+	au_br_put(hf->hf_br);
+	hf->hf_br = NULL;
+}
+
+void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, struct file *val)
+{
+	struct au_finfo *finfo = au_fi(file);
+	struct au_hfile *hf;
+	struct au_fidir *fidir;
+
+	fidir = finfo->fi_hdir;
+	if (!fidir) {
+		AuDebugOn(finfo->fi_btop != bindex);
+		hf = &finfo->fi_htop;
+	} else
+		hf = fidir->fd_hfile + bindex;
+
+	if (hf && hf->hf_file)
+		au_hfput(hf, vfsub_file_execed(file));
+	if (val) {
+		FiMustWriteLock(file);
+		AuDebugOn(IS_ERR_OR_NULL(file->f_path.dentry));
+		hf->hf_file = val;
+		hf->hf_br = au_sbr(file->f_path.dentry->d_sb, bindex);
+	}
+}
+
+void au_update_figen(struct file *file)
+{
+	atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_path.dentry));
+	/* smp_mb(); */ /* atomic_set */
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct au_fidir *au_fidir_alloc(struct super_block *sb)
+{
+	struct au_fidir *fidir;
+	int nbr;
+
+	nbr = au_sbbot(sb) + 1;
+	if (nbr < 2)
+		nbr = 2; /* initial allocate for 2 branches */
+	fidir = kzalloc(au_fidir_sz(nbr), GFP_NOFS);
+	if (fidir) {
+		fidir->fd_bbot = -1;
+		fidir->fd_nent = nbr;
+	}
+
+	return fidir;
+}
+
+int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink)
+{
+	int err;
+	struct au_fidir *fidir, *p;
+
+	AuRwMustWriteLock(&finfo->fi_rwsem);
+	fidir = finfo->fi_hdir;
+	AuDebugOn(!fidir);
+
+	err = -ENOMEM;
+	p = au_kzrealloc(fidir, au_fidir_sz(fidir->fd_nent), au_fidir_sz(nbr),
+			 GFP_NOFS, may_shrink);
+	if (p) {
+		p->fd_nent = nbr;
+		finfo->fi_hdir = p;
+		err = 0;
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_finfo_fin(struct file *file)
+{
+	struct au_finfo *finfo;
+
+	au_nfiles_dec(file->f_path.dentry->d_sb);
+
+	finfo = au_fi(file);
+	AuDebugOn(finfo->fi_hdir);
+	AuRwDestroy(&finfo->fi_rwsem);
+	au_cache_free_finfo(finfo);
+}
+
+void au_fi_init_once(void *_finfo)
+{
+	struct au_finfo *finfo = _finfo;
+
+	au_rw_init(&finfo->fi_rwsem);
+}
+
+int au_finfo_init(struct file *file, struct au_fidir *fidir)
+{
+	int err;
+	struct au_finfo *finfo;
+	struct dentry *dentry;
+
+	err = -ENOMEM;
+	dentry = file->f_path.dentry;
+	finfo = au_cache_alloc_finfo();
+	if (unlikely(!finfo))
+		goto out;
+
+	err = 0;
+	au_nfiles_inc(dentry->d_sb);
+	au_rw_write_lock(&finfo->fi_rwsem);
+	finfo->fi_btop = -1;
+	finfo->fi_hdir = fidir;
+	atomic_set(&finfo->fi_generation, au_digen(dentry));
+	/* smp_mb(); */ /* atomic_set */
+
+	file->private_data = finfo;
+
+out:
+	return err;
+}
diff --git a/fs/aufs/fstype.h b/fs/aufs/fstype.h
new file mode 100644
index 000000000000..4624f1ef222f
--- /dev/null
+++ b/fs/aufs/fstype.h
@@ -0,0 +1,400 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * judging filesystem type
+ */
+
+#ifndef __AUFS_FSTYPE_H__
+#define __AUFS_FSTYPE_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/magic.h>
+#include <linux/nfs_fs.h>
+#include <linux/romfs_fs.h>
+
+static inline int au_test_aufs(struct super_block *sb)
+{
+	return sb->s_magic == AUFS_SUPER_MAGIC;
+}
+
+static inline const char *au_sbtype(struct super_block *sb)
+{
+	return sb->s_type->name;
+}
+
+static inline int au_test_iso9660(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_ISO9660_FS)
+	return sb->s_magic == ISOFS_SUPER_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_romfs(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_ROMFS_FS)
+	return sb->s_magic == ROMFS_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_cramfs(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_CRAMFS)
+	return sb->s_magic == CRAMFS_MAGIC;
+#endif
+	return 0;
+}
+
+static inline int au_test_nfs(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_NFS_FS)
+	return sb->s_magic == NFS_SUPER_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_fuse(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_FUSE_FS)
+	return sb->s_magic == FUSE_SUPER_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_xfs(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_XFS_FS)
+	return sb->s_magic == XFS_SB_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_tmpfs(struct super_block *sb __maybe_unused)
+{
+#ifdef CONFIG_TMPFS
+	return sb->s_magic == TMPFS_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_ecryptfs(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_ECRYPT_FS)
+	return !strcmp(au_sbtype(sb), "ecryptfs");
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_ramfs(struct super_block *sb)
+{
+	return sb->s_magic == RAMFS_MAGIC;
+}
+
+static inline int au_test_ubifs(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_UBIFS_FS)
+	return sb->s_magic == UBIFS_SUPER_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_procfs(struct super_block *sb __maybe_unused)
+{
+#ifdef CONFIG_PROC_FS
+	return sb->s_magic == PROC_SUPER_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_sysfs(struct super_block *sb __maybe_unused)
+{
+#ifdef CONFIG_SYSFS
+	return sb->s_magic == SYSFS_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_configfs(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_CONFIGFS_FS)
+	return sb->s_magic == CONFIGFS_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_minix(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_MINIX_FS)
+	return sb->s_magic == MINIX3_SUPER_MAGIC
+		|| sb->s_magic == MINIX2_SUPER_MAGIC
+		|| sb->s_magic == MINIX2_SUPER_MAGIC2
+		|| sb->s_magic == MINIX_SUPER_MAGIC
+		|| sb->s_magic == MINIX_SUPER_MAGIC2;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_fat(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_FAT_FS)
+	return sb->s_magic == MSDOS_SUPER_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_msdos(struct super_block *sb)
+{
+	return au_test_fat(sb);
+}
+
+static inline int au_test_vfat(struct super_block *sb)
+{
+	return au_test_fat(sb);
+}
+
+static inline int au_test_securityfs(struct super_block *sb __maybe_unused)
+{
+#ifdef CONFIG_SECURITYFS
+	return sb->s_magic == SECURITYFS_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_squashfs(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_SQUASHFS)
+	return sb->s_magic == SQUASHFS_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_btrfs(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_BTRFS_FS)
+	return sb->s_magic == BTRFS_SUPER_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_xenfs(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_XENFS)
+	return sb->s_magic == XENFS_SUPER_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_debugfs(struct super_block *sb __maybe_unused)
+{
+#ifdef CONFIG_DEBUG_FS
+	return sb->s_magic == DEBUGFS_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_nilfs(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_NILFS)
+	return sb->s_magic == NILFS_SUPER_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+static inline int au_test_hfsplus(struct super_block *sb __maybe_unused)
+{
+#if IS_ENABLED(CONFIG_HFSPLUS_FS)
+	return sb->s_magic == HFSPLUS_SUPER_MAGIC;
+#else
+	return 0;
+#endif
+}
+
+/* ---------------------------------------------------------------------- */
+/*
+ * they can't be an aufs branch.
+ */
+static inline int au_test_fs_unsuppoted(struct super_block *sb)
+{
+	return
+#ifndef CONFIG_AUFS_BR_RAMFS
+		au_test_ramfs(sb) ||
+#endif
+		au_test_procfs(sb)
+		|| au_test_sysfs(sb)
+		|| au_test_configfs(sb)
+		|| au_test_debugfs(sb)
+		|| au_test_securityfs(sb)
+		|| au_test_xenfs(sb)
+		|| au_test_ecryptfs(sb)
+		/* || !strcmp(au_sbtype(sb), "unionfs") */
+		|| au_test_aufs(sb); /* will be supported in next version */
+}
+
+static inline int au_test_fs_remote(struct super_block *sb)
+{
+	return !au_test_tmpfs(sb)
+#ifdef CONFIG_AUFS_BR_RAMFS
+		&& !au_test_ramfs(sb)
+#endif
+		&& !(sb->s_type->fs_flags & FS_REQUIRES_DEV);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * Note: these functions (below) are created after reading ->getattr() in all
+ * filesystems under linux/fs. it means we have to do so in every update...
+ */
+
+/*
+ * some filesystems require getattr to refresh the inode attributes before
+ * referencing.
+ * in most cases, we can rely on the inode attribute in NFS (or every remote fs)
+ * and leave the work for d_revalidate()
+ */
+static inline int au_test_fs_refresh_iattr(struct super_block *sb)
+{
+	return au_test_nfs(sb)
+		|| au_test_fuse(sb)
+		/* || au_test_btrfs(sb) */	/* untested */
+		;
+}
+
+/*
+ * filesystems which don't maintain i_size or i_blocks.
+ */
+static inline int au_test_fs_bad_iattr_size(struct super_block *sb)
+{
+	return au_test_xfs(sb)
+		|| au_test_btrfs(sb)
+		|| au_test_ubifs(sb)
+		|| au_test_hfsplus(sb)	/* maintained, but incorrect */
+		/* || au_test_minix(sb) */	/* untested */
+		;
+}
+
+/*
+ * filesystems which don't store the correct value in some of their inode
+ * attributes.
+ */
+static inline int au_test_fs_bad_iattr(struct super_block *sb)
+{
+	return au_test_fs_bad_iattr_size(sb)
+		|| au_test_fat(sb)
+		|| au_test_msdos(sb)
+		|| au_test_vfat(sb);
+}
+
+/* they don't check i_nlink in link(2) */
+static inline int au_test_fs_no_limit_nlink(struct super_block *sb)
+{
+	return au_test_tmpfs(sb)
+#ifdef CONFIG_AUFS_BR_RAMFS
+		|| au_test_ramfs(sb)
+#endif
+		|| au_test_ubifs(sb)
+		|| au_test_hfsplus(sb);
+}
+
+/*
+ * filesystems which sets S_NOATIME and S_NOCMTIME.
+ */
+static inline int au_test_fs_notime(struct super_block *sb)
+{
+	return au_test_nfs(sb)
+		|| au_test_fuse(sb)
+		|| au_test_ubifs(sb)
+		;
+}
+
+/* temporary support for i#1 in cramfs */
+static inline int au_test_fs_unique_ino(struct inode *inode)
+{
+	if (au_test_cramfs(inode->i_sb))
+		return inode->i_ino != 1;
+	return 1;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * the filesystem where the xino files placed must support i/o after unlink and
+ * maintain i_size and i_blocks.
+ */
+static inline int au_test_fs_bad_xino(struct super_block *sb)
+{
+	return au_test_fs_remote(sb)
+		|| au_test_fs_bad_iattr_size(sb)
+		/* don't want unnecessary work for xino */
+		|| au_test_aufs(sb)
+		|| au_test_ecryptfs(sb)
+		|| au_test_nilfs(sb);
+}
+
+static inline int au_test_fs_trunc_xino(struct super_block *sb)
+{
+	return au_test_tmpfs(sb)
+		|| au_test_ramfs(sb);
+}
+
+/*
+ * test if the @sb is real-readonly.
+ */
+static inline int au_test_fs_rr(struct super_block *sb)
+{
+	return au_test_squashfs(sb)
+		|| au_test_iso9660(sb)
+		|| au_test_cramfs(sb)
+		|| au_test_romfs(sb);
+}
+
+/*
+ * test if the @inode is nfs with 'noacl' option
+ * NFS always sets MS_POSIXACL regardless its mount option 'noacl.'
+ */
+static inline int au_test_nfs_noacl(struct inode *inode)
+{
+	return au_test_nfs(inode->i_sb)
+		/* && IS_POSIXACL(inode) */
+		&& !nfs_server_capable(inode, NFS_CAP_ACLS);
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_FSTYPE_H__ */
diff --git a/fs/aufs/hfsnotify.c b/fs/aufs/hfsnotify.c
new file mode 100644
index 000000000000..e2a16478e84e
--- /dev/null
+++ b/fs/aufs/hfsnotify.c
@@ -0,0 +1,289 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * fsnotify for the lower directories
+ */
+
+#include "aufs.h"
+
+/* FS_IN_IGNORED is unnecessary */
+static const __u32 AuHfsnMask = (FS_MOVED_TO | FS_MOVED_FROM | FS_DELETE
+				 | FS_CREATE | FS_EVENT_ON_CHILD);
+static DECLARE_WAIT_QUEUE_HEAD(au_hfsn_wq);
+static __cacheline_aligned_in_smp atomic64_t au_hfsn_ifree = ATOMIC64_INIT(0);
+
+static void au_hfsn_free_mark(struct fsnotify_mark *mark)
+{
+	struct au_hnotify *hn = container_of(mark, struct au_hnotify,
+					     hn_mark);
+	/* AuDbg("here\n"); */
+	au_cache_free_hnotify(hn);
+	smp_mb__before_atomic(); /* for atomic64_dec */
+	if (atomic64_dec_and_test(&au_hfsn_ifree))
+		wake_up(&au_hfsn_wq);
+}
+
+static int au_hfsn_alloc(struct au_hinode *hinode)
+{
+	int err;
+	struct au_hnotify *hn;
+	struct super_block *sb;
+	struct au_branch *br;
+	struct fsnotify_mark *mark;
+	aufs_bindex_t bindex;
+
+	hn = hinode->hi_notify;
+	sb = hn->hn_aufs_inode->i_sb;
+	bindex = au_br_index(sb, hinode->hi_id);
+	br = au_sbr(sb, bindex);
+	AuDebugOn(!br->br_hfsn);
+
+	mark = &hn->hn_mark;
+	fsnotify_init_mark(mark, br->br_hfsn->hfsn_group);
+	mark->mask = AuHfsnMask;
+	/*
+	 * by udba rename or rmdir, aufs assign a new inode to the known
+	 * h_inode, so specify 1 to allow dups.
+	 */
+	lockdep_off();
+	err = fsnotify_add_mark(mark, hinode->hi_inode, /*mnt*/NULL,
+				/*allow_dups*/1);
+	lockdep_on();
+
+	return err;
+}
+
+static int au_hfsn_free(struct au_hinode *hinode, struct au_hnotify *hn)
+{
+	struct fsnotify_mark *mark;
+	unsigned long long ull;
+	struct fsnotify_group *group;
+
+	ull = atomic64_inc_return(&au_hfsn_ifree);
+	BUG_ON(!ull);
+
+	mark = &hn->hn_mark;
+	spin_lock(&mark->lock);
+	group = mark->group;
+	fsnotify_get_group(group);
+	spin_unlock(&mark->lock);
+	lockdep_off();
+	fsnotify_destroy_mark(mark, group);
+	fsnotify_put_mark(mark);
+	fsnotify_put_group(group);
+	lockdep_on();
+
+	/* free hn by myself */
+	return 0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void au_hfsn_ctl(struct au_hinode *hinode, int do_set)
+{
+	struct fsnotify_mark *mark;
+
+	mark = &hinode->hi_notify->hn_mark;
+	spin_lock(&mark->lock);
+	if (do_set) {
+		AuDebugOn(mark->mask & AuHfsnMask);
+		mark->mask |= AuHfsnMask;
+	} else {
+		AuDebugOn(!(mark->mask & AuHfsnMask));
+		mark->mask &= ~AuHfsnMask;
+	}
+	spin_unlock(&mark->lock);
+	/* fsnotify_recalc_inode_mask(hinode->hi_inode); */
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* #define AuDbgHnotify */
+#ifdef AuDbgHnotify
+static char *au_hfsn_name(u32 mask)
+{
+#ifdef CONFIG_AUFS_DEBUG
+#define test_ret(flag)				\
+	do {					\
+		if (mask & flag)		\
+			return #flag;		\
+	} while (0)
+	test_ret(FS_ACCESS);
+	test_ret(FS_MODIFY);
+	test_ret(FS_ATTRIB);
+	test_ret(FS_CLOSE_WRITE);
+	test_ret(FS_CLOSE_NOWRITE);
+	test_ret(FS_OPEN);
+	test_ret(FS_MOVED_FROM);
+	test_ret(FS_MOVED_TO);
+	test_ret(FS_CREATE);
+	test_ret(FS_DELETE);
+	test_ret(FS_DELETE_SELF);
+	test_ret(FS_MOVE_SELF);
+	test_ret(FS_UNMOUNT);
+	test_ret(FS_Q_OVERFLOW);
+	test_ret(FS_IN_IGNORED);
+	test_ret(FS_ISDIR);
+	test_ret(FS_IN_ONESHOT);
+	test_ret(FS_EVENT_ON_CHILD);
+	return "";
+#undef test_ret
+#else
+	return "??";
+#endif
+}
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+static void au_hfsn_free_group(struct fsnotify_group *group)
+{
+	struct au_br_hfsnotify *hfsn = group->private;
+
+	/* AuDbg("here\n"); */
+	kfree(hfsn);
+}
+
+static int au_hfsn_handle_event(struct fsnotify_group *group,
+				struct inode *inode,
+				struct fsnotify_mark *inode_mark,
+				struct fsnotify_mark *vfsmount_mark,
+				u32 mask, const void *data, int data_type,
+				const unsigned char *file_name, u32 cookie,
+				struct fsnotify_iter_info *iter_info)
+{
+	int err;
+	struct au_hnotify *hnotify;
+	struct inode *h_dir, *h_inode;
+	struct qstr h_child_qstr = QSTR_INIT(file_name, strlen(file_name));
+
+	AuDebugOn(data_type != FSNOTIFY_EVENT_INODE);
+
+	err = 0;
+	/* if FS_UNMOUNT happens, there must be another bug */
+	AuDebugOn(mask & FS_UNMOUNT);
+	if (mask & (FS_IN_IGNORED | FS_UNMOUNT))
+		goto out;
+
+	h_dir = inode;
+	h_inode = NULL;
+#ifdef AuDbgHnotify
+	au_debug_on();
+	if (1 || h_child_qstr.len != sizeof(AUFS_XINO_FNAME) - 1
+	    || strncmp(h_child_qstr.name, AUFS_XINO_FNAME, h_child_qstr.len)) {
+		AuDbg("i%lu, mask 0x%x %s, hcname %.*s, hi%lu\n",
+		      h_dir->i_ino, mask, au_hfsn_name(mask),
+		      AuLNPair(&h_child_qstr), h_inode ? h_inode->i_ino : 0);
+		/* WARN_ON(1); */
+	}
+	au_debug_off();
+#endif
+
+	AuDebugOn(!inode_mark);
+	hnotify = container_of(inode_mark, struct au_hnotify, hn_mark);
+	err = au_hnotify(h_dir, hnotify, mask, &h_child_qstr, h_inode);
+
+out:
+	return err;
+}
+
+static struct fsnotify_ops au_hfsn_ops = {
+	.handle_event		= au_hfsn_handle_event,
+	.free_group_priv	= au_hfsn_free_group,
+	.free_mark		= au_hfsn_free_mark
+};
+
+/* ---------------------------------------------------------------------- */
+
+static void au_hfsn_fin_br(struct au_branch *br)
+{
+	struct au_br_hfsnotify *hfsn;
+
+	hfsn = br->br_hfsn;
+	if (hfsn) {
+		lockdep_off();
+		fsnotify_put_group(hfsn->hfsn_group);
+		lockdep_on();
+	}
+}
+
+static int au_hfsn_init_br(struct au_branch *br, int perm)
+{
+	int err;
+	struct fsnotify_group *group;
+	struct au_br_hfsnotify *hfsn;
+
+	err = 0;
+	br->br_hfsn = NULL;
+	if (!au_br_hnotifyable(perm))
+		goto out;
+
+	err = -ENOMEM;
+	hfsn = kmalloc(sizeof(*hfsn), GFP_NOFS);
+	if (unlikely(!hfsn))
+		goto out;
+
+	err = 0;
+	group = fsnotify_alloc_group(&au_hfsn_ops);
+	if (IS_ERR(group)) {
+		err = PTR_ERR(group);
+		pr_err("fsnotify_alloc_group() failed, %d\n", err);
+		goto out_hfsn;
+	}
+
+	group->private = hfsn;
+	hfsn->hfsn_group = group;
+	br->br_hfsn = hfsn;
+	goto out; /* success */
+
+out_hfsn:
+	kfree(hfsn);
+out:
+	return err;
+}
+
+static int au_hfsn_reset_br(unsigned int udba, struct au_branch *br, int perm)
+{
+	int err;
+
+	err = 0;
+	if (!br->br_hfsn)
+		err = au_hfsn_init_br(br, perm);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void au_hfsn_fin(void)
+{
+	AuDbg("au_hfsn_ifree %lld\n", (long long)atomic64_read(&au_hfsn_ifree));
+	wait_event(au_hfsn_wq, !atomic64_read(&au_hfsn_ifree));
+}
+
+const struct au_hnotify_op au_hnotify_op = {
+	.ctl		= au_hfsn_ctl,
+	.alloc		= au_hfsn_alloc,
+	.free		= au_hfsn_free,
+
+	.fin		= au_hfsn_fin,
+
+	.reset_br	= au_hfsn_reset_br,
+	.fin_br		= au_hfsn_fin_br,
+	.init_br	= au_hfsn_init_br
+};
diff --git a/fs/aufs/hfsplus.c b/fs/aufs/hfsplus.c
new file mode 100644
index 000000000000..b5b6547024e5
--- /dev/null
+++ b/fs/aufs/hfsplus.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 2010-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * special support for filesystems which aqucires an inode mutex
+ * at final closing a file, eg, hfsplus.
+ *
+ * This trick is very simple and stupid, just to open the file before really
+ * neceeary open to tell hfsplus that this is not the final closing.
+ * The caller should call au_h_open_pre() after acquiring the inode mutex,
+ * and au_h_open_post() after releasing it.
+ */
+
+#include "aufs.h"
+
+struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex,
+			   int force_wr)
+{
+	struct file *h_file;
+	struct dentry *h_dentry;
+
+	h_dentry = au_h_dptr(dentry, bindex);
+	AuDebugOn(!h_dentry);
+	AuDebugOn(d_is_negative(h_dentry));
+
+	h_file = NULL;
+	if (au_test_hfsplus(h_dentry->d_sb)
+	    && d_is_reg(h_dentry))
+		h_file = au_h_open(dentry, bindex,
+				   O_RDONLY | O_NOATIME | O_LARGEFILE,
+				   /*file*/NULL, force_wr);
+	return h_file;
+}
+
+void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex,
+		    struct file *h_file)
+{
+	if (h_file) {
+		fput(h_file);
+		au_sbr_put(dentry->d_sb, bindex);
+	}
+}
diff --git a/fs/aufs/hnotify.c b/fs/aufs/hnotify.c
new file mode 100644
index 000000000000..9dde1ace6761
--- /dev/null
+++ b/fs/aufs/hnotify.c
@@ -0,0 +1,711 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * abstraction to notify the direct changes on lower directories
+ */
+
+#include "aufs.h"
+
+int au_hn_alloc(struct au_hinode *hinode, struct inode *inode)
+{
+	int err;
+	struct au_hnotify *hn;
+
+	err = -ENOMEM;
+	hn = au_cache_alloc_hnotify();
+	if (hn) {
+		hn->hn_aufs_inode = inode;
+		hinode->hi_notify = hn;
+		err = au_hnotify_op.alloc(hinode);
+		AuTraceErr(err);
+		if (unlikely(err)) {
+			hinode->hi_notify = NULL;
+			au_cache_free_hnotify(hn);
+			/*
+			 * The upper dir was removed by udba, but the same named
+			 * dir left. In this case, aufs assignes a new inode
+			 * number and set the monitor again.
+			 * For the lower dir, the old monitnor is still left.
+			 */
+			if (err == -EEXIST)
+				err = 0;
+		}
+	}
+
+	AuTraceErr(err);
+	return err;
+}
+
+void au_hn_free(struct au_hinode *hinode)
+{
+	struct au_hnotify *hn;
+
+	hn = hinode->hi_notify;
+	if (hn) {
+		hinode->hi_notify = NULL;
+		if (au_hnotify_op.free(hinode, hn))
+			au_cache_free_hnotify(hn);
+	}
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_hn_ctl(struct au_hinode *hinode, int do_set)
+{
+	if (hinode->hi_notify)
+		au_hnotify_op.ctl(hinode, do_set);
+}
+
+void au_hn_reset(struct inode *inode, unsigned int flags)
+{
+	aufs_bindex_t bindex, bbot;
+	struct inode *hi;
+	struct dentry *iwhdentry;
+
+	bbot = au_ibbot(inode);
+	for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) {
+		hi = au_h_iptr(inode, bindex);
+		if (!hi)
+			continue;
+
+		/* inode_lock_nested(hi, AuLsc_I_CHILD); */
+		iwhdentry = au_hi_wh(inode, bindex);
+		if (iwhdentry)
+			dget(iwhdentry);
+		au_igrab(hi);
+		au_set_h_iptr(inode, bindex, NULL, 0);
+		au_set_h_iptr(inode, bindex, au_igrab(hi),
+			      flags & ~AuHi_XINO);
+		iput(hi);
+		dput(iwhdentry);
+		/* inode_unlock(hi); */
+	}
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int hn_xino(struct inode *inode, struct inode *h_inode)
+{
+	int err;
+	aufs_bindex_t bindex, bbot, bfound, btop;
+	struct inode *h_i;
+
+	err = 0;
+	if (unlikely(inode->i_ino == AUFS_ROOT_INO)) {
+		pr_warn("branch root dir was changed\n");
+		goto out;
+	}
+
+	bfound = -1;
+	bbot = au_ibbot(inode);
+	btop = au_ibtop(inode);
+#if 0 /* reserved for future use */
+	if (bindex == bbot) {
+		/* keep this ino in rename case */
+		goto out;
+	}
+#endif
+	for (bindex = btop; bindex <= bbot; bindex++)
+		if (au_h_iptr(inode, bindex) == h_inode) {
+			bfound = bindex;
+			break;
+		}
+	if (bfound < 0)
+		goto out;
+
+	for (bindex = btop; bindex <= bbot; bindex++) {
+		h_i = au_h_iptr(inode, bindex);
+		if (!h_i)
+			continue;
+
+		err = au_xino_write(inode->i_sb, bindex, h_i->i_ino, /*ino*/0);
+		/* ignore this error */
+		/* bad action? */
+	}
+
+	/* children inode number will be broken */
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+static int hn_gen_tree(struct dentry *dentry)
+{
+	int err, i, j, ndentry;
+	struct au_dcsub_pages dpages;
+	struct au_dpage *dpage;
+	struct dentry **dentries;
+
+	err = au_dpages_init(&dpages, GFP_NOFS);
+	if (unlikely(err))
+		goto out;
+	err = au_dcsub_pages(&dpages, dentry, NULL, NULL);
+	if (unlikely(err))
+		goto out_dpages;
+
+	for (i = 0; i < dpages.ndpage; i++) {
+		dpage = dpages.dpages + i;
+		dentries = dpage->dentries;
+		ndentry = dpage->ndentry;
+		for (j = 0; j < ndentry; j++) {
+			struct dentry *d;
+
+			d = dentries[j];
+			if (IS_ROOT(d))
+				continue;
+
+			au_digen_dec(d);
+			if (d_really_is_positive(d))
+				/* todo: reset children xino?
+				   cached children only? */
+				au_iigen_dec(d_inode(d));
+		}
+	}
+
+out_dpages:
+	au_dpages_free(&dpages);
+
+#if 0
+	/* discard children */
+	dentry_unhash(dentry);
+	dput(dentry);
+#endif
+out:
+	return err;
+}
+
+/*
+ * return 0 if processed.
+ */
+static int hn_gen_by_inode(char *name, unsigned int nlen, struct inode *inode,
+			   const unsigned int isdir)
+{
+	int err;
+	struct dentry *d;
+	struct qstr *dname;
+
+	err = 1;
+	if (unlikely(inode->i_ino == AUFS_ROOT_INO)) {
+		pr_warn("branch root dir was changed\n");
+		err = 0;
+		goto out;
+	}
+
+	if (!isdir) {
+		AuDebugOn(!name);
+		au_iigen_dec(inode);
+		spin_lock(&inode->i_lock);
+		hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) {
+			spin_lock(&d->d_lock);
+			dname = &d->d_name;
+			if (dname->len != nlen
+			    && memcmp(dname->name, name, nlen)) {
+				spin_unlock(&d->d_lock);
+				continue;
+			}
+			err = 0;
+			au_digen_dec(d);
+			spin_unlock(&d->d_lock);
+			break;
+		}
+		spin_unlock(&inode->i_lock);
+	} else {
+		au_fset_si(au_sbi(inode->i_sb), FAILED_REFRESH_DIR);
+		d = d_find_any_alias(inode);
+		if (!d) {
+			au_iigen_dec(inode);
+			goto out;
+		}
+
+		spin_lock(&d->d_lock);
+		dname = &d->d_name;
+		if (dname->len == nlen && !memcmp(dname->name, name, nlen)) {
+			spin_unlock(&d->d_lock);
+			err = hn_gen_tree(d);
+			spin_lock(&d->d_lock);
+		}
+		spin_unlock(&d->d_lock);
+		dput(d);
+	}
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+static int hn_gen_by_name(struct dentry *dentry, const unsigned int isdir)
+{
+	int err;
+
+	if (IS_ROOT(dentry)) {
+		pr_warn("branch root dir was changed\n");
+		return 0;
+	}
+
+	err = 0;
+	if (!isdir) {
+		au_digen_dec(dentry);
+		if (d_really_is_positive(dentry))
+			au_iigen_dec(d_inode(dentry));
+	} else {
+		au_fset_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR);
+		if (d_really_is_positive(dentry))
+			err = hn_gen_tree(dentry);
+	}
+
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* hnotify job flags */
+#define AuHnJob_XINO0		1
+#define AuHnJob_GEN		(1 << 1)
+#define AuHnJob_DIRENT		(1 << 2)
+#define AuHnJob_ISDIR		(1 << 3)
+#define AuHnJob_TRYXINO0	(1 << 4)
+#define AuHnJob_MNTPNT		(1 << 5)
+#define au_ftest_hnjob(flags, name)	((flags) & AuHnJob_##name)
+#define au_fset_hnjob(flags, name) \
+	do { (flags) |= AuHnJob_##name; } while (0)
+#define au_fclr_hnjob(flags, name) \
+	do { (flags) &= ~AuHnJob_##name; } while (0)
+
+enum {
+	AuHn_CHILD,
+	AuHn_PARENT,
+	AuHnLast
+};
+
+struct au_hnotify_args {
+	struct inode *h_dir, *dir, *h_child_inode;
+	u32 mask;
+	unsigned int flags[AuHnLast];
+	unsigned int h_child_nlen;
+	char h_child_name[];
+};
+
+struct hn_job_args {
+	unsigned int flags;
+	struct inode *inode, *h_inode, *dir, *h_dir;
+	struct dentry *dentry;
+	char *h_name;
+	int h_nlen;
+};
+
+static int hn_job(struct hn_job_args *a)
+{
+	const unsigned int isdir = au_ftest_hnjob(a->flags, ISDIR);
+	int e;
+
+	/* reset xino */
+	if (au_ftest_hnjob(a->flags, XINO0) && a->inode)
+		hn_xino(a->inode, a->h_inode); /* ignore this error */
+
+	if (au_ftest_hnjob(a->flags, TRYXINO0)
+	    && a->inode
+	    && a->h_inode) {
+		vfsub_inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD);
+		if (!a->h_inode->i_nlink
+		    && !(a->h_inode->i_state & I_LINKABLE))
+			hn_xino(a->inode, a->h_inode); /* ignore this error */
+		inode_unlock_shared(a->h_inode);
+	}
+
+	/* make the generation obsolete */
+	if (au_ftest_hnjob(a->flags, GEN)) {
+		e = -1;
+		if (a->inode)
+			e = hn_gen_by_inode(a->h_name, a->h_nlen, a->inode,
+					      isdir);
+		if (e && a->dentry)
+			hn_gen_by_name(a->dentry, isdir);
+		/* ignore this error */
+	}
+
+	/* make dir entries obsolete */
+	if (au_ftest_hnjob(a->flags, DIRENT) && a->inode) {
+		struct au_vdir *vdir;
+
+		vdir = au_ivdir(a->inode);
+		if (vdir)
+			vdir->vd_jiffy = 0;
+		/* IMustLock(a->inode); */
+		/* a->inode->i_version++; */
+	}
+
+	/* can do nothing but warn */
+	if (au_ftest_hnjob(a->flags, MNTPNT)
+	    && a->dentry
+	    && d_mountpoint(a->dentry))
+		pr_warn("mount-point %pd is removed or renamed\n", a->dentry);
+
+	return 0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static struct dentry *lookup_wlock_by_name(char *name, unsigned int nlen,
+					   struct inode *dir)
+{
+	struct dentry *dentry, *d, *parent;
+	struct qstr *dname;
+
+	parent = d_find_any_alias(dir);
+	if (!parent)
+		return NULL;
+
+	dentry = NULL;
+	spin_lock(&parent->d_lock);
+	list_for_each_entry(d, &parent->d_subdirs, d_child) {
+		/* AuDbg("%pd\n", d); */
+		spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
+		dname = &d->d_name;
+		if (dname->len != nlen || memcmp(dname->name, name, nlen))
+			goto cont_unlock;
+		if (au_di(d))
+			au_digen_dec(d);
+		else
+			goto cont_unlock;
+		if (au_dcount(d) > 0) {
+			dentry = dget_dlock(d);
+			spin_unlock(&d->d_lock);
+			break;
+		}
+
+cont_unlock:
+		spin_unlock(&d->d_lock);
+	}
+	spin_unlock(&parent->d_lock);
+	dput(parent);
+
+	if (dentry)
+		di_write_lock_child(dentry);
+
+	return dentry;
+}
+
+static struct inode *lookup_wlock_by_ino(struct super_block *sb,
+					 aufs_bindex_t bindex, ino_t h_ino)
+{
+	struct inode *inode;
+	ino_t ino;
+	int err;
+
+	inode = NULL;
+	err = au_xino_read(sb, bindex, h_ino, &ino);
+	if (!err && ino)
+		inode = ilookup(sb, ino);
+	if (!inode)
+		goto out;
+
+	if (unlikely(inode->i_ino == AUFS_ROOT_INO)) {
+		pr_warn("wrong root branch\n");
+		iput(inode);
+		inode = NULL;
+		goto out;
+	}
+
+	ii_write_lock_child(inode);
+
+out:
+	return inode;
+}
+
+static void au_hn_bh(void *_args)
+{
+	struct au_hnotify_args *a = _args;
+	struct super_block *sb;
+	aufs_bindex_t bindex, bbot, bfound;
+	unsigned char xino, try_iput;
+	int err;
+	struct inode *inode;
+	ino_t h_ino;
+	struct hn_job_args args;
+	struct dentry *dentry;
+	struct au_sbinfo *sbinfo;
+
+	AuDebugOn(!_args);
+	AuDebugOn(!a->h_dir);
+	AuDebugOn(!a->dir);
+	AuDebugOn(!a->mask);
+	AuDbg("mask 0x%x, i%lu, hi%lu, hci%lu\n",
+	      a->mask, a->dir->i_ino, a->h_dir->i_ino,
+	      a->h_child_inode ? a->h_child_inode->i_ino : 0);
+
+	inode = NULL;
+	dentry = NULL;
+	/*
+	 * do not lock a->dir->i_mutex here
+	 * because of d_revalidate() may cause a deadlock.
+	 */
+	sb = a->dir->i_sb;
+	AuDebugOn(!sb);
+	sbinfo = au_sbi(sb);
+	AuDebugOn(!sbinfo);
+	si_write_lock(sb, AuLock_NOPLMW);
+
+	ii_read_lock_parent(a->dir);
+	bfound = -1;
+	bbot = au_ibbot(a->dir);
+	for (bindex = au_ibtop(a->dir); bindex <= bbot; bindex++)
+		if (au_h_iptr(a->dir, bindex) == a->h_dir) {
+			bfound = bindex;
+			break;
+		}
+	ii_read_unlock(a->dir);
+	if (unlikely(bfound < 0))
+		goto out;
+
+	xino = !!au_opt_test(au_mntflags(sb), XINO);
+	h_ino = 0;
+	if (a->h_child_inode)
+		h_ino = a->h_child_inode->i_ino;
+
+	if (a->h_child_nlen
+	    && (au_ftest_hnjob(a->flags[AuHn_CHILD], GEN)
+		|| au_ftest_hnjob(a->flags[AuHn_CHILD], MNTPNT)))
+		dentry = lookup_wlock_by_name(a->h_child_name, a->h_child_nlen,
+					      a->dir);
+	try_iput = 0;
+	if (dentry && d_really_is_positive(dentry))
+		inode = d_inode(dentry);
+	if (xino && !inode && h_ino
+	    && (au_ftest_hnjob(a->flags[AuHn_CHILD], XINO0)
+		|| au_ftest_hnjob(a->flags[AuHn_CHILD], TRYXINO0)
+		|| au_ftest_hnjob(a->flags[AuHn_CHILD], GEN))) {
+		inode = lookup_wlock_by_ino(sb, bfound, h_ino);
+		try_iput = 1;
+	}
+
+	args.flags = a->flags[AuHn_CHILD];
+	args.dentry = dentry;
+	args.inode = inode;
+	args.h_inode = a->h_child_inode;
+	args.dir = a->dir;
+	args.h_dir = a->h_dir;
+	args.h_name = a->h_child_name;
+	args.h_nlen = a->h_child_nlen;
+	err = hn_job(&args);
+	if (dentry) {
+		if (au_di(dentry))
+			di_write_unlock(dentry);
+		dput(dentry);
+	}
+	if (inode && try_iput) {
+		ii_write_unlock(inode);
+		iput(inode);
+	}
+
+	ii_write_lock_parent(a->dir);
+	args.flags = a->flags[AuHn_PARENT];
+	args.dentry = NULL;
+	args.inode = a->dir;
+	args.h_inode = a->h_dir;
+	args.dir = NULL;
+	args.h_dir = NULL;
+	args.h_name = NULL;
+	args.h_nlen = 0;
+	err = hn_job(&args);
+	ii_write_unlock(a->dir);
+
+out:
+	iput(a->h_child_inode);
+	iput(a->h_dir);
+	iput(a->dir);
+	si_write_unlock(sb);
+	au_nwt_done(&sbinfo->si_nowait);
+	kfree(a);
+}
+
+/* ---------------------------------------------------------------------- */
+
+int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask,
+	       struct qstr *h_child_qstr, struct inode *h_child_inode)
+{
+	int err, len;
+	unsigned int flags[AuHnLast], f;
+	unsigned char isdir, isroot, wh;
+	struct inode *dir;
+	struct au_hnotify_args *args;
+	char *p, *h_child_name;
+
+	err = 0;
+	AuDebugOn(!hnotify || !hnotify->hn_aufs_inode);
+	dir = igrab(hnotify->hn_aufs_inode);
+	if (!dir)
+		goto out;
+
+	isroot = (dir->i_ino == AUFS_ROOT_INO);
+	wh = 0;
+	h_child_name = (void *)h_child_qstr->name;
+	len = h_child_qstr->len;
+	if (h_child_name) {
+		if (len > AUFS_WH_PFX_LEN
+		    && !memcmp(h_child_name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) {
+			h_child_name += AUFS_WH_PFX_LEN;
+			len -= AUFS_WH_PFX_LEN;
+			wh = 1;
+		}
+	}
+
+	isdir = 0;
+	if (h_child_inode)
+		isdir = !!S_ISDIR(h_child_inode->i_mode);
+	flags[AuHn_PARENT] = AuHnJob_ISDIR;
+	flags[AuHn_CHILD] = 0;
+	if (isdir)
+		flags[AuHn_CHILD] = AuHnJob_ISDIR;
+	au_fset_hnjob(flags[AuHn_PARENT], DIRENT);
+	au_fset_hnjob(flags[AuHn_CHILD], GEN);
+	switch (mask & FS_EVENTS_POSS_ON_CHILD) {
+	case FS_MOVED_FROM:
+	case FS_MOVED_TO:
+		au_fset_hnjob(flags[AuHn_CHILD], XINO0);
+		au_fset_hnjob(flags[AuHn_CHILD], MNTPNT);
+		/*FALLTHROUGH*/
+	case FS_CREATE:
+		AuDebugOn(!h_child_name);
+		break;
+
+	case FS_DELETE:
+		/*
+		 * aufs never be able to get this child inode.
+		 * revalidation should be in d_revalidate()
+		 * by checking i_nlink, i_generation or d_unhashed().
+		 */
+		AuDebugOn(!h_child_name);
+		au_fset_hnjob(flags[AuHn_CHILD], TRYXINO0);
+		au_fset_hnjob(flags[AuHn_CHILD], MNTPNT);
+		break;
+
+	default:
+		AuDebugOn(1);
+	}
+
+	if (wh)
+		h_child_inode = NULL;
+
+	err = -ENOMEM;
+	/* iput() and kfree() will be called in au_hnotify() */
+	args = kmalloc(sizeof(*args) + len + 1, GFP_NOFS);
+	if (unlikely(!args)) {
+		AuErr1("no memory\n");
+		iput(dir);
+		goto out;
+	}
+	args->flags[AuHn_PARENT] = flags[AuHn_PARENT];
+	args->flags[AuHn_CHILD] = flags[AuHn_CHILD];
+	args->mask = mask;
+	args->dir = dir;
+	args->h_dir = igrab(h_dir);
+	if (h_child_inode)
+		h_child_inode = igrab(h_child_inode); /* can be NULL */
+	args->h_child_inode = h_child_inode;
+	args->h_child_nlen = len;
+	if (len) {
+		p = (void *)args;
+		p += sizeof(*args);
+		memcpy(p, h_child_name, len);
+		p[len] = 0;
+	}
+
+	/* NFS fires the event for silly-renamed one from kworker */
+	f = 0;
+	if (!dir->i_nlink
+	    || (au_test_nfs(h_dir->i_sb) && (mask & FS_DELETE)))
+		f = AuWkq_NEST;
+	err = au_wkq_nowait(au_hn_bh, args, dir->i_sb, f);
+	if (unlikely(err)) {
+		pr_err("wkq %d\n", err);
+		iput(args->h_child_inode);
+		iput(args->h_dir);
+		iput(args->dir);
+		kfree(args);
+	}
+
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm)
+{
+	int err;
+
+	AuDebugOn(!(udba & AuOptMask_UDBA));
+
+	err = 0;
+	if (au_hnotify_op.reset_br)
+		err = au_hnotify_op.reset_br(udba, br, perm);
+
+	return err;
+}
+
+int au_hnotify_init_br(struct au_branch *br, int perm)
+{
+	int err;
+
+	err = 0;
+	if (au_hnotify_op.init_br)
+		err = au_hnotify_op.init_br(br, perm);
+
+	return err;
+}
+
+void au_hnotify_fin_br(struct au_branch *br)
+{
+	if (au_hnotify_op.fin_br)
+		au_hnotify_op.fin_br(br);
+}
+
+static void au_hn_destroy_cache(void)
+{
+	kmem_cache_destroy(au_cache[AuCache_HNOTIFY]);
+	au_cache[AuCache_HNOTIFY] = NULL;
+}
+
+int __init au_hnotify_init(void)
+{
+	int err;
+
+	err = -ENOMEM;
+	au_cache[AuCache_HNOTIFY] = AuCache(au_hnotify);
+	if (au_cache[AuCache_HNOTIFY]) {
+		err = 0;
+		if (au_hnotify_op.init)
+			err = au_hnotify_op.init();
+		if (unlikely(err))
+			au_hn_destroy_cache();
+	}
+	AuTraceErr(err);
+	return err;
+}
+
+void au_hnotify_fin(void)
+{
+	if (au_hnotify_op.fin)
+		au_hnotify_op.fin();
+
+	/* cf. au_cache_fin() */
+	if (au_cache[AuCache_HNOTIFY])
+		au_hn_destroy_cache();
+}
diff --git a/fs/aufs/i_op.c b/fs/aufs/i_op.c
new file mode 100644
index 000000000000..0573825d6257
--- /dev/null
+++ b/fs/aufs/i_op.c
@@ -0,0 +1,1460 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * inode operations (except add/del/rename)
+ */
+
+#include <linux/device_cgroup.h>
+#include <linux/fs_stack.h>
+#include <linux/namei.h>
+#include <linux/security.h>
+#include "aufs.h"
+
+static int h_permission(struct inode *h_inode, int mask,
+			struct path *h_path, int brperm)
+{
+	int err;
+	const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
+
+	err = -EPERM;
+	if (write_mask && IS_IMMUTABLE(h_inode))
+		goto out;
+
+	err = -EACCES;
+	if (((mask & MAY_EXEC)
+	     && S_ISREG(h_inode->i_mode)
+	     && (path_noexec(h_path)
+		 || !(h_inode->i_mode & S_IXUGO))))
+		goto out;
+
+	/*
+	 * - skip the lower fs test in the case of write to ro branch.
+	 * - nfs dir permission write check is optimized, but a policy for
+	 *   link/rename requires a real check.
+	 * - nfs always sets MS_POSIXACL regardless its mount option 'noacl.'
+	 *   in this case, generic_permission() returns -EOPNOTSUPP.
+	 */
+	if ((write_mask && !au_br_writable(brperm))
+	    || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode)
+		&& write_mask && !(mask & MAY_READ))
+	    || !h_inode->i_op->permission) {
+		/* AuLabel(generic_permission); */
+		/* AuDbg("get_acl %pf\n", h_inode->i_op->get_acl); */
+		err = generic_permission(h_inode, mask);
+		if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode))
+			err = h_inode->i_op->permission(h_inode, mask);
+		AuTraceErr(err);
+	} else {
+		/* AuLabel(h_inode->permission); */
+		err = h_inode->i_op->permission(h_inode, mask);
+		AuTraceErr(err);
+	}
+
+	if (!err)
+		err = devcgroup_inode_permission(h_inode, mask);
+	if (!err)
+		err = security_inode_permission(h_inode, mask);
+
+#if 0
+	if (!err) {
+		/* todo: do we need to call ima_path_check()? */
+		struct path h_path = {
+			.dentry	=
+			.mnt	= h_mnt
+		};
+		err = ima_path_check(&h_path,
+				     mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
+				     IMA_COUNT_LEAVE);
+	}
+#endif
+
+out:
+	return err;
+}
+
+static int aufs_permission(struct inode *inode, int mask)
+{
+	int err;
+	aufs_bindex_t bindex, bbot;
+	const unsigned char isdir = !!S_ISDIR(inode->i_mode),
+		write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
+	struct inode *h_inode;
+	struct super_block *sb;
+	struct au_branch *br;
+
+	/* todo: support rcu-walk? */
+	if (mask & MAY_NOT_BLOCK)
+		return -ECHILD;
+
+	sb = inode->i_sb;
+	si_read_lock(sb, AuLock_FLUSH);
+	ii_read_lock_child(inode);
+#if 0
+	err = au_iigen_test(inode, au_sigen(sb));
+	if (unlikely(err))
+		goto out;
+#endif
+
+	if (!isdir
+	    || write_mask
+	    || au_opt_test(au_mntflags(sb), DIRPERM1)) {
+		err = au_busy_or_stale();
+		h_inode = au_h_iptr(inode, au_ibtop(inode));
+		if (unlikely(!h_inode
+			     || (h_inode->i_mode & S_IFMT)
+			     != (inode->i_mode & S_IFMT)))
+			goto out;
+
+		err = 0;
+		bindex = au_ibtop(inode);
+		br = au_sbr(sb, bindex);
+		err = h_permission(h_inode, mask, &br->br_path, br->br_perm);
+		if (write_mask
+		    && !err
+		    && !special_file(h_inode->i_mode)) {
+			/* test whether the upper writable branch exists */
+			err = -EROFS;
+			for (; bindex >= 0; bindex--)
+				if (!au_br_rdonly(au_sbr(sb, bindex))) {
+					err = 0;
+					break;
+				}
+		}
+		goto out;
+	}
+
+	/* non-write to dir */
+	err = 0;
+	bbot = au_ibbot(inode);
+	for (bindex = au_ibtop(inode); !err && bindex <= bbot; bindex++) {
+		h_inode = au_h_iptr(inode, bindex);
+		if (h_inode) {
+			err = au_busy_or_stale();
+			if (unlikely(!S_ISDIR(h_inode->i_mode)))
+				break;
+
+			br = au_sbr(sb, bindex);
+			err = h_permission(h_inode, mask, &br->br_path,
+					   br->br_perm);
+		}
+	}
+
+out:
+	ii_read_unlock(inode);
+	si_read_unlock(sb);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry,
+				  unsigned int flags)
+{
+	struct dentry *ret, *parent;
+	struct inode *inode;
+	struct super_block *sb;
+	int err, npositive;
+
+	IMustLock(dir);
+
+	/* todo: support rcu-walk? */
+	ret = ERR_PTR(-ECHILD);
+	if (flags & LOOKUP_RCU)
+		goto out;
+
+	ret = ERR_PTR(-ENAMETOOLONG);
+	if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
+		goto out;
+
+	sb = dir->i_sb;
+	err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
+	ret = ERR_PTR(err);
+	if (unlikely(err))
+		goto out;
+
+	err = au_di_init(dentry);
+	ret = ERR_PTR(err);
+	if (unlikely(err))
+		goto out_si;
+
+	inode = NULL;
+	npositive = 0; /* suppress a warning */
+	parent = dentry->d_parent; /* dir inode is locked */
+	di_read_lock_parent(parent, AuLock_IR);
+	err = au_alive_dir(parent);
+	if (!err)
+		err = au_digen_test(parent, au_sigen(sb));
+	if (!err) {
+		/* regardless LOOKUP_CREATE, always ALLOW_NEG */
+		npositive = au_lkup_dentry(dentry, au_dbtop(parent),
+					   AuLkup_ALLOW_NEG);
+		err = npositive;
+	}
+	di_read_unlock(parent, AuLock_IR);
+	ret = ERR_PTR(err);
+	if (unlikely(err < 0))
+		goto out_unlock;
+
+	if (npositive) {
+		inode = au_new_inode(dentry, /*must_new*/0);
+		if (IS_ERR(inode)) {
+			ret = (void *)inode;
+			inode = NULL;
+			goto out_unlock;
+		}
+	}
+
+	if (inode)
+		atomic_inc(&inode->i_count);
+	ret = d_splice_alias(inode, dentry);
+#if 0
+	if (unlikely(d_need_lookup(dentry))) {
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
+		spin_unlock(&dentry->d_lock);
+	} else
+#endif
+	if (inode) {
+		if (!IS_ERR(ret)) {
+			iput(inode);
+			if (ret && ret != dentry)
+				ii_write_unlock(inode);
+		} else {
+			ii_write_unlock(inode);
+			iput(inode);
+			inode = NULL;
+		}
+	}
+
+out_unlock:
+	di_write_unlock(dentry);
+out_si:
+	si_read_unlock(sb);
+out:
+	return ret;
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct aopen_node {
+	struct hlist_node hlist;
+	struct file *file, *h_file;
+};
+
+static int au_do_aopen(struct inode *inode, struct file *file)
+{
+	struct au_sphlhead *aopen;
+	struct aopen_node *node;
+	struct au_do_open_args args = {
+		.aopen	= 1,
+		.open	= au_do_open_nondir
+	};
+
+	aopen = &au_sbi(inode->i_sb)->si_aopen;
+	spin_lock(&aopen->spin);
+	hlist_for_each_entry(node, &aopen->head, hlist)
+		if (node->file == file) {
+			args.h_file = node->h_file;
+			break;
+		}
+	spin_unlock(&aopen->spin);
+	/* AuDebugOn(!args.h_file); */
+
+	return au_do_open(file, &args);
+}
+
+static int aufs_atomic_open(struct inode *dir, struct dentry *dentry,
+			    struct file *file, unsigned int open_flag,
+			    umode_t create_mode, int *opened)
+{
+	int err, unlocked, h_opened = *opened;
+	unsigned int lkup_flags;
+	struct dentry *parent, *d;
+	struct au_sphlhead *aopen;
+	struct vfsub_aopen_args args = {
+		.open_flag	= open_flag,
+		.create_mode	= create_mode,
+		.opened		= &h_opened
+	};
+	struct aopen_node aopen_node = {
+		.file	= file
+	};
+
+	IMustLock(dir);
+	AuDbg("open_flag 0%o\n", open_flag);
+	AuDbgDentry(dentry);
+
+	err = 0;
+	if (!au_di(dentry)) {
+		lkup_flags = LOOKUP_OPEN;
+		if (open_flag & O_CREAT)
+			lkup_flags |= LOOKUP_CREATE;
+		d = aufs_lookup(dir, dentry, lkup_flags);
+		if (IS_ERR(d)) {
+			err = PTR_ERR(d);
+			AuTraceErr(err);
+			goto out;
+		} else if (d) {
+			/*
+			 * obsoleted dentry found.
+			 * another error will be returned later.
+			 */
+			d_drop(d);
+			AuDbgDentry(d);
+			dput(d);
+		}
+		AuDbgDentry(dentry);
+	}
+
+	if (d_is_positive(dentry)
+	    || d_unhashed(dentry)
+	    || d_unlinked(dentry)
+	    || !(open_flag & O_CREAT))
+		goto out_no_open;
+
+	unlocked = 0;
+	err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
+	if (unlikely(err))
+		goto out;
+
+	parent = dentry->d_parent;	/* dir is locked */
+	di_write_lock_parent(parent);
+	err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG);
+	if (unlikely(err))
+		goto out_unlock;
+
+	AuDbgDentry(dentry);
+	if (d_is_positive(dentry))
+		goto out_unlock;
+
+	args.file = get_empty_filp();
+	err = PTR_ERR(args.file);
+	if (IS_ERR(args.file))
+		goto out_unlock;
+
+	args.file->f_flags = file->f_flags;
+	err = au_aopen_or_create(dir, dentry, &args);
+	AuTraceErr(err);
+	AuDbgFile(args.file);
+	if (unlikely(err < 0)) {
+		if (h_opened & FILE_OPENED)
+			fput(args.file);
+		else
+			put_filp(args.file);
+		goto out_unlock;
+	}
+	di_write_unlock(parent);
+	di_write_unlock(dentry);
+	unlocked = 1;
+
+	/* some filesystems don't set FILE_CREATED while succeeded? */
+	*opened |= FILE_CREATED;
+	if (h_opened & FILE_OPENED)
+		aopen_node.h_file = args.file;
+	else {
+		put_filp(args.file);
+		args.file = NULL;
+	}
+	aopen = &au_sbi(dir->i_sb)->si_aopen;
+	au_sphl_add(&aopen_node.hlist, aopen);
+	err = finish_open(file, dentry, au_do_aopen, opened);
+	au_sphl_del(&aopen_node.hlist, aopen);
+	AuTraceErr(err);
+	AuDbgFile(file);
+	if (aopen_node.h_file)
+		fput(aopen_node.h_file);
+
+out_unlock:
+	if (unlocked)
+		si_read_unlock(dentry->d_sb);
+	else {
+		di_write_unlock(parent);
+		aufs_read_unlock(dentry, AuLock_DW);
+	}
+	AuDbgDentry(dentry);
+	if (unlikely(err < 0))
+		goto out;
+out_no_open:
+	if (err >= 0 && !(*opened & FILE_CREATED)) {
+		AuLabel(out_no_open);
+		dget(dentry);
+		err = finish_no_open(file, dentry);
+	}
+out:
+	AuDbg("%pd%s%s\n", dentry,
+	      (*opened & FILE_CREATED) ? " created" : "",
+	      (*opened & FILE_OPENED) ? " opened" : "");
+	AuTraceErr(err);
+	return err;
+}
+
+
+/* ---------------------------------------------------------------------- */
+
+static int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent,
+			  const unsigned char add_entry, aufs_bindex_t bcpup,
+			  aufs_bindex_t btop)
+{
+	int err;
+	struct dentry *h_parent;
+	struct inode *h_dir;
+
+	if (add_entry)
+		IMustLock(d_inode(parent));
+	else
+		di_write_lock_parent(parent);
+
+	err = 0;
+	if (!au_h_dptr(parent, bcpup)) {
+		if (btop > bcpup)
+			err = au_cpup_dirs(dentry, bcpup);
+		else if (btop < bcpup)
+			err = au_cpdown_dirs(dentry, bcpup);
+		else
+			BUG();
+	}
+	if (!err && add_entry && !au_ftest_wrdir(add_entry, TMPFILE)) {
+		h_parent = au_h_dptr(parent, bcpup);
+		h_dir = d_inode(h_parent);
+		vfsub_inode_lock_shared_nested(h_dir, AuLsc_I_PARENT);
+		err = au_lkup_neg(dentry, bcpup, /*wh*/0);
+		/* todo: no unlock here */
+		inode_unlock_shared(h_dir);
+
+		AuDbg("bcpup %d\n", bcpup);
+		if (!err) {
+			if (d_really_is_negative(dentry))
+				au_set_h_dptr(dentry, btop, NULL);
+			au_update_dbrange(dentry, /*do_put_zero*/0);
+		}
+	}
+
+	if (!add_entry)
+		di_write_unlock(parent);
+	if (!err)
+		err = bcpup; /* success */
+
+	AuTraceErr(err);
+	return err;
+}
+
+/*
+ * decide the branch and the parent dir where we will create a new entry.
+ * returns new bindex or an error.
+ * copyup the parent dir if needed.
+ */
+int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry,
+	      struct au_wr_dir_args *args)
+{
+	int err;
+	unsigned int flags;
+	aufs_bindex_t bcpup, btop, src_btop;
+	const unsigned char add_entry
+		= au_ftest_wrdir(args->flags, ADD_ENTRY)
+		| au_ftest_wrdir(args->flags, TMPFILE);
+	struct super_block *sb;
+	struct dentry *parent;
+	struct au_sbinfo *sbinfo;
+
+	sb = dentry->d_sb;
+	sbinfo = au_sbi(sb);
+	parent = dget_parent(dentry);
+	btop = au_dbtop(dentry);
+	bcpup = btop;
+	if (args->force_btgt < 0) {
+		if (src_dentry) {
+			src_btop = au_dbtop(src_dentry);
+			if (src_btop < btop)
+				bcpup = src_btop;
+		} else if (add_entry) {
+			flags = 0;
+			if (au_ftest_wrdir(args->flags, ISDIR))
+				au_fset_wbr(flags, DIR);
+			err = AuWbrCreate(sbinfo, dentry, flags);
+			bcpup = err;
+		}
+
+		if (bcpup < 0 || au_test_ro(sb, bcpup, d_inode(dentry))) {
+			if (add_entry)
+				err = AuWbrCopyup(sbinfo, dentry);
+			else {
+				if (!IS_ROOT(dentry)) {
+					di_read_lock_parent(parent, !AuLock_IR);
+					err = AuWbrCopyup(sbinfo, dentry);
+					di_read_unlock(parent, !AuLock_IR);
+				} else
+					err = AuWbrCopyup(sbinfo, dentry);
+			}
+			bcpup = err;
+			if (unlikely(err < 0))
+				goto out;
+		}
+	} else {
+		bcpup = args->force_btgt;
+		AuDebugOn(au_test_ro(sb, bcpup, d_inode(dentry)));
+	}
+
+	AuDbg("btop %d, bcpup %d\n", btop, bcpup);
+	err = bcpup;
+	if (bcpup == btop)
+		goto out; /* success */
+
+	/* copyup the new parent into the branch we process */
+	err = au_wr_dir_cpup(dentry, parent, add_entry, bcpup, btop);
+	if (err >= 0) {
+		if (d_really_is_negative(dentry)) {
+			au_set_h_dptr(dentry, btop, NULL);
+			au_set_dbtop(dentry, bcpup);
+			au_set_dbbot(dentry, bcpup);
+		}
+		AuDebugOn(add_entry
+			  && !au_ftest_wrdir(args->flags, TMPFILE)
+			  && !au_h_dptr(dentry, bcpup));
+	}
+
+out:
+	dput(parent);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_pin_hdir_unlock(struct au_pin *p)
+{
+	if (p->hdir)
+		au_hn_inode_unlock(p->hdir);
+}
+
+int au_pin_hdir_lock(struct au_pin *p)
+{
+	int err;
+
+	err = 0;
+	if (!p->hdir)
+		goto out;
+
+	/* even if an error happens later, keep this lock */
+	au_hn_inode_lock_nested(p->hdir, p->lsc_hi);
+
+	err = -EBUSY;
+	if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent)))
+		goto out;
+
+	err = 0;
+	if (p->h_dentry)
+		err = au_h_verify(p->h_dentry, p->udba, p->hdir->hi_inode,
+				  p->h_parent, p->br);
+
+out:
+	return err;
+}
+
+int au_pin_hdir_relock(struct au_pin *p)
+{
+	int err, i;
+	struct inode *h_i;
+	struct dentry *h_d[] = {
+		p->h_dentry,
+		p->h_parent
+	};
+
+	err = au_pin_hdir_lock(p);
+	if (unlikely(err))
+		goto out;
+
+	for (i = 0; !err && i < sizeof(h_d)/sizeof(*h_d); i++) {
+		if (!h_d[i])
+			continue;
+		if (d_is_positive(h_d[i])) {
+			h_i = d_inode(h_d[i]);
+			err = !h_i->i_nlink;
+		}
+	}
+
+out:
+	return err;
+}
+
+static void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task)
+{
+#if !defined(CONFIG_RWSEM_GENERIC_SPINLOCK) && defined(CONFIG_RWSEM_SPIN_ON_OWNER)
+	p->hdir->hi_inode->i_rwsem.owner = task;
+#endif
+}
+
+void au_pin_hdir_acquire_nest(struct au_pin *p)
+{
+	if (p->hdir) {
+		rwsem_acquire_nest(&p->hdir->hi_inode->i_rwsem.dep_map,
+				   p->lsc_hi, 0, NULL, _RET_IP_);
+		au_pin_hdir_set_owner(p, current);
+	}
+}
+
+void au_pin_hdir_release(struct au_pin *p)
+{
+	if (p->hdir) {
+		au_pin_hdir_set_owner(p, p->task);
+		rwsem_release(&p->hdir->hi_inode->i_rwsem.dep_map, 1, _RET_IP_);
+	}
+}
+
+struct dentry *au_pinned_h_parent(struct au_pin *pin)
+{
+	if (pin && pin->parent)
+		return au_h_dptr(pin->parent, pin->bindex);
+	return NULL;
+}
+
+void au_unpin(struct au_pin *p)
+{
+	if (p->hdir)
+		au_pin_hdir_unlock(p);
+	if (p->h_mnt && au_ftest_pin(p->flags, MNT_WRITE))
+		vfsub_mnt_drop_write(p->h_mnt);
+	if (!p->hdir)
+		return;
+
+	if (!au_ftest_pin(p->flags, DI_LOCKED))
+		di_read_unlock(p->parent, AuLock_IR);
+	iput(p->hdir->hi_inode);
+	dput(p->parent);
+	p->parent = NULL;
+	p->hdir = NULL;
+	p->h_mnt = NULL;
+	/* do not clear p->task */
+}
+
+int au_do_pin(struct au_pin *p)
+{
+	int err;
+	struct super_block *sb;
+	struct inode *h_dir;
+
+	err = 0;
+	sb = p->dentry->d_sb;
+	p->br = au_sbr(sb, p->bindex);
+	if (IS_ROOT(p->dentry)) {
+		if (au_ftest_pin(p->flags, MNT_WRITE)) {
+			p->h_mnt = au_br_mnt(p->br);
+			err = vfsub_mnt_want_write(p->h_mnt);
+			if (unlikely(err)) {
+				au_fclr_pin(p->flags, MNT_WRITE);
+				goto out_err;
+			}
+		}
+		goto out;
+	}
+
+	p->h_dentry = NULL;
+	if (p->bindex <= au_dbbot(p->dentry))
+		p->h_dentry = au_h_dptr(p->dentry, p->bindex);
+
+	p->parent = dget_parent(p->dentry);
+	if (!au_ftest_pin(p->flags, DI_LOCKED))
+		di_read_lock(p->parent, AuLock_IR, p->lsc_di);
+
+	h_dir = NULL;
+	p->h_parent = au_h_dptr(p->parent, p->bindex);
+	p->hdir = au_hi(d_inode(p->parent), p->bindex);
+	if (p->hdir)
+		h_dir = p->hdir->hi_inode;
+
+	/*
+	 * udba case, or
+	 * if DI_LOCKED is not set, then p->parent may be different
+	 * and h_parent can be NULL.
+	 */
+	if (unlikely(!p->hdir || !h_dir || !p->h_parent)) {
+		err = -EBUSY;
+		if (!au_ftest_pin(p->flags, DI_LOCKED))
+			di_read_unlock(p->parent, AuLock_IR);
+		dput(p->parent);
+		p->parent = NULL;
+		goto out_err;
+	}
+
+	if (au_ftest_pin(p->flags, MNT_WRITE)) {
+		p->h_mnt = au_br_mnt(p->br);
+		err = vfsub_mnt_want_write(p->h_mnt);
+		if (unlikely(err)) {
+			au_fclr_pin(p->flags, MNT_WRITE);
+			if (!au_ftest_pin(p->flags, DI_LOCKED))
+				di_read_unlock(p->parent, AuLock_IR);
+			dput(p->parent);
+			p->parent = NULL;
+			goto out_err;
+		}
+	}
+
+	au_igrab(h_dir);
+	err = au_pin_hdir_lock(p);
+	if (!err)
+		goto out; /* success */
+
+	au_unpin(p);
+
+out_err:
+	pr_err("err %d\n", err);
+	err = au_busy_or_stale();
+out:
+	return err;
+}
+
+void au_pin_init(struct au_pin *p, struct dentry *dentry,
+		 aufs_bindex_t bindex, int lsc_di, int lsc_hi,
+		 unsigned int udba, unsigned char flags)
+{
+	p->dentry = dentry;
+	p->udba = udba;
+	p->lsc_di = lsc_di;
+	p->lsc_hi = lsc_hi;
+	p->flags = flags;
+	p->bindex = bindex;
+
+	p->parent = NULL;
+	p->hdir = NULL;
+	p->h_mnt = NULL;
+
+	p->h_dentry = NULL;
+	p->h_parent = NULL;
+	p->br = NULL;
+	p->task = current;
+}
+
+int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
+	   unsigned int udba, unsigned char flags)
+{
+	au_pin_init(pin, dentry, bindex, AuLsc_DI_PARENT, AuLsc_I_PARENT2,
+		    udba, flags);
+	return au_do_pin(pin);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * ->setattr() and ->getattr() are called in various cases.
+ * chmod, stat: dentry is revalidated.
+ * fchmod, fstat: file and dentry are not revalidated, additionally they may be
+ *		  unhashed.
+ * for ->setattr(), ia->ia_file is passed from ftruncate only.
+ */
+/* todo: consolidate with do_refresh() and simple_reval_dpath() */
+int au_reval_for_attr(struct dentry *dentry, unsigned int sigen)
+{
+	int err;
+	struct dentry *parent;
+
+	err = 0;
+	if (au_digen_test(dentry, sigen)) {
+		parent = dget_parent(dentry);
+		di_read_lock_parent(parent, AuLock_IR);
+		err = au_refresh_dentry(dentry, parent);
+		di_read_unlock(parent, AuLock_IR);
+		dput(parent);
+	}
+
+	AuTraceErr(err);
+	return err;
+}
+
+int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
+		     struct au_icpup_args *a)
+{
+	int err;
+	loff_t sz;
+	aufs_bindex_t btop, ibtop;
+	struct dentry *hi_wh, *parent;
+	struct inode *inode;
+	struct au_wr_dir_args wr_dir_args = {
+		.force_btgt	= -1,
+		.flags		= 0
+	};
+
+	if (d_is_dir(dentry))
+		au_fset_wrdir(wr_dir_args.flags, ISDIR);
+	/* plink or hi_wh() case */
+	btop = au_dbtop(dentry);
+	inode = d_inode(dentry);
+	ibtop = au_ibtop(inode);
+	if (btop != ibtop && !au_test_ro(inode->i_sb, ibtop, inode))
+		wr_dir_args.force_btgt = ibtop;
+	err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args);
+	if (unlikely(err < 0))
+		goto out;
+	a->btgt = err;
+	if (err != btop)
+		au_fset_icpup(a->flags, DID_CPUP);
+
+	err = 0;
+	a->pin_flags = AuPin_MNT_WRITE;
+	parent = NULL;
+	if (!IS_ROOT(dentry)) {
+		au_fset_pin(a->pin_flags, DI_LOCKED);
+		parent = dget_parent(dentry);
+		di_write_lock_parent(parent);
+	}
+
+	err = au_pin(&a->pin, dentry, a->btgt, a->udba, a->pin_flags);
+	if (unlikely(err))
+		goto out_parent;
+
+	sz = -1;
+	a->h_path.dentry = au_h_dptr(dentry, btop);
+	a->h_inode = d_inode(a->h_path.dentry);
+	if (ia && (ia->ia_valid & ATTR_SIZE)) {
+		vfsub_inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD);
+		if (ia->ia_size < i_size_read(a->h_inode))
+			sz = ia->ia_size;
+		inode_unlock_shared(a->h_inode);
+	}
+
+	hi_wh = NULL;
+	if (au_ftest_icpup(a->flags, DID_CPUP) && d_unlinked(dentry)) {
+		hi_wh = au_hi_wh(inode, a->btgt);
+		if (!hi_wh) {
+			struct au_cp_generic cpg = {
+				.dentry	= dentry,
+				.bdst	= a->btgt,
+				.bsrc	= -1,
+				.len	= sz,
+				.pin	= &a->pin
+			};
+			err = au_sio_cpup_wh(&cpg, /*file*/NULL);
+			if (unlikely(err))
+				goto out_unlock;
+			hi_wh = au_hi_wh(inode, a->btgt);
+			/* todo: revalidate hi_wh? */
+		}
+	}
+
+	if (parent) {
+		au_pin_set_parent_lflag(&a->pin, /*lflag*/0);
+		di_downgrade_lock(parent, AuLock_IR);
+		dput(parent);
+		parent = NULL;
+	}
+	if (!au_ftest_icpup(a->flags, DID_CPUP))
+		goto out; /* success */
+
+	if (!d_unhashed(dentry)) {
+		struct au_cp_generic cpg = {
+			.dentry	= dentry,
+			.bdst	= a->btgt,
+			.bsrc	= btop,
+			.len	= sz,
+			.pin	= &a->pin,
+			.flags	= AuCpup_DTIME | AuCpup_HOPEN
+		};
+		err = au_sio_cpup_simple(&cpg);
+		if (!err)
+			a->h_path.dentry = au_h_dptr(dentry, a->btgt);
+	} else if (!hi_wh)
+		a->h_path.dentry = au_h_dptr(dentry, a->btgt);
+	else
+		a->h_path.dentry = hi_wh; /* do not dget here */
+
+out_unlock:
+	a->h_inode = d_inode(a->h_path.dentry);
+	if (!err)
+		goto out; /* success */
+	au_unpin(&a->pin);
+out_parent:
+	if (parent) {
+		di_write_unlock(parent);
+		dput(parent);
+	}
+out:
+	if (!err)
+		inode_lock_nested(a->h_inode, AuLsc_I_CHILD);
+	return err;
+}
+
+static int aufs_setattr(struct dentry *dentry, struct iattr *ia)
+{
+	int err;
+	struct inode *inode, *delegated;
+	struct super_block *sb;
+	struct file *file;
+	struct au_icpup_args *a;
+
+	inode = d_inode(dentry);
+	IMustLock(inode);
+
+	err = setattr_prepare(dentry, ia);
+	if (unlikely(err))
+		goto out;
+
+	err = -ENOMEM;
+	a = kzalloc(sizeof(*a), GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+
+	if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
+		ia->ia_valid &= ~ATTR_MODE;
+
+	file = NULL;
+	sb = dentry->d_sb;
+	err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
+	if (unlikely(err))
+		goto out_kfree;
+
+	if (ia->ia_valid & ATTR_FILE) {
+		/* currently ftruncate(2) only */
+		AuDebugOn(!d_is_reg(dentry));
+		file = ia->ia_file;
+		err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1,
+					    /*fi_lsc*/0);
+		if (unlikely(err))
+			goto out_si;
+		ia->ia_file = au_hf_top(file);
+		a->udba = AuOpt_UDBA_NONE;
+	} else {
+		/* fchmod() doesn't pass ia_file */
+		a->udba = au_opt_udba(sb);
+		di_write_lock_child(dentry);
+		/* no d_unlinked(), to set UDBA_NONE for root */
+		if (d_unhashed(dentry))
+			a->udba = AuOpt_UDBA_NONE;
+		if (a->udba != AuOpt_UDBA_NONE) {
+			AuDebugOn(IS_ROOT(dentry));
+			err = au_reval_for_attr(dentry, au_sigen(sb));
+			if (unlikely(err))
+				goto out_dentry;
+		}
+	}
+
+	err = au_pin_and_icpup(dentry, ia, a);
+	if (unlikely(err < 0))
+		goto out_dentry;
+	if (au_ftest_icpup(a->flags, DID_CPUP)) {
+		ia->ia_file = NULL;
+		ia->ia_valid &= ~ATTR_FILE;
+	}
+
+	a->h_path.mnt = au_sbr_mnt(sb, a->btgt);
+	if ((ia->ia_valid & (ATTR_MODE | ATTR_CTIME))
+	    == (ATTR_MODE | ATTR_CTIME)) {
+		err = security_path_chmod(&a->h_path, ia->ia_mode);
+		if (unlikely(err))
+			goto out_unlock;
+	} else if ((ia->ia_valid & (ATTR_UID | ATTR_GID))
+		   && (ia->ia_valid & ATTR_CTIME)) {
+		err = security_path_chown(&a->h_path, ia->ia_uid, ia->ia_gid);
+		if (unlikely(err))
+			goto out_unlock;
+	}
+
+	if (ia->ia_valid & ATTR_SIZE) {
+		struct file *f;
+
+		if (ia->ia_size < i_size_read(inode))
+			/* unmap only */
+			truncate_setsize(inode, ia->ia_size);
+
+		f = NULL;
+		if (ia->ia_valid & ATTR_FILE)
+			f = ia->ia_file;
+		inode_unlock(a->h_inode);
+		err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f);
+		inode_lock_nested(a->h_inode, AuLsc_I_CHILD);
+	} else {
+		delegated = NULL;
+		while (1) {
+			err = vfsub_notify_change(&a->h_path, ia, &delegated);
+			if (delegated) {
+				err = break_deleg_wait(&delegated);
+				if (!err)
+					continue;
+			}
+			break;
+		}
+	}
+	/*
+	 * regardless aufs 'acl' option setting.
+	 * why don't all acl-aware fs call this func from their ->setattr()?
+	 */
+	if (!err && (ia->ia_valid & ATTR_MODE))
+		err = vfsub_acl_chmod(a->h_inode, ia->ia_mode);
+	if (!err)
+		au_cpup_attr_changeable(inode);
+
+out_unlock:
+	inode_unlock(a->h_inode);
+	au_unpin(&a->pin);
+	if (unlikely(err))
+		au_update_dbtop(dentry);
+out_dentry:
+	di_write_unlock(dentry);
+	if (file) {
+		fi_write_unlock(file);
+		ia->ia_file = file;
+		ia->ia_valid |= ATTR_FILE;
+	}
+out_si:
+	si_read_unlock(sb);
+out_kfree:
+	kfree(a);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL)
+static int au_h_path_to_set_attr(struct dentry *dentry,
+				 struct au_icpup_args *a, struct path *h_path)
+{
+	int err;
+	struct super_block *sb;
+
+	sb = dentry->d_sb;
+	a->udba = au_opt_udba(sb);
+	/* no d_unlinked(), to set UDBA_NONE for root */
+	if (d_unhashed(dentry))
+		a->udba = AuOpt_UDBA_NONE;
+	if (a->udba != AuOpt_UDBA_NONE) {
+		AuDebugOn(IS_ROOT(dentry));
+		err = au_reval_for_attr(dentry, au_sigen(sb));
+		if (unlikely(err))
+			goto out;
+	}
+	err = au_pin_and_icpup(dentry, /*ia*/NULL, a);
+	if (unlikely(err < 0))
+		goto out;
+
+	h_path->dentry = a->h_path.dentry;
+	h_path->mnt = au_sbr_mnt(sb, a->btgt);
+
+out:
+	return err;
+}
+
+ssize_t au_sxattr(struct dentry *dentry, struct inode *inode,
+		  struct au_sxattr *arg)
+{
+	int err;
+	struct path h_path;
+	struct super_block *sb;
+	struct au_icpup_args *a;
+	struct inode *h_inode;
+
+	IMustLock(inode);
+
+	err = -ENOMEM;
+	a = kzalloc(sizeof(*a), GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+
+	sb = dentry->d_sb;
+	err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
+	if (unlikely(err))
+		goto out_kfree;
+
+	h_path.dentry = NULL;	/* silence gcc */
+	di_write_lock_child(dentry);
+	err = au_h_path_to_set_attr(dentry, a, &h_path);
+	if (unlikely(err))
+		goto out_di;
+
+	inode_unlock(a->h_inode);
+	switch (arg->type) {
+	case AU_XATTR_SET:
+		AuDebugOn(d_is_negative(h_path.dentry));
+		err = vfsub_setxattr(h_path.dentry,
+				     arg->u.set.name, arg->u.set.value,
+				     arg->u.set.size, arg->u.set.flags);
+		break;
+	case AU_ACL_SET:
+		err = -EOPNOTSUPP;
+		h_inode = d_inode(h_path.dentry);
+		if (h_inode->i_op->set_acl)
+			/* this will call posix_acl_update_mode */
+			err = h_inode->i_op->set_acl(h_inode,
+						     arg->u.acl_set.acl,
+						     arg->u.acl_set.type);
+		break;
+	}
+	if (!err)
+		au_cpup_attr_timesizes(inode);
+
+	au_unpin(&a->pin);
+	if (unlikely(err))
+		au_update_dbtop(dentry);
+
+out_di:
+	di_write_unlock(dentry);
+	si_read_unlock(sb);
+out_kfree:
+	kfree(a);
+out:
+	AuTraceErr(err);
+	return err;
+}
+#endif
+
+static void au_refresh_iattr(struct inode *inode, struct kstat *st,
+			     unsigned int nlink)
+{
+	unsigned int n;
+
+	inode->i_mode = st->mode;
+	/* don't i_[ug]id_write() here */
+	inode->i_uid = st->uid;
+	inode->i_gid = st->gid;
+	inode->i_atime = st->atime;
+	inode->i_mtime = st->mtime;
+	inode->i_ctime = st->ctime;
+
+	au_cpup_attr_nlink(inode, /*force*/0);
+	if (S_ISDIR(inode->i_mode)) {
+		n = inode->i_nlink;
+		n -= nlink;
+		n += st->nlink;
+		smp_mb(); /* for i_nlink */
+		/* 0 can happen */
+		set_nlink(inode, n);
+	}
+
+	spin_lock(&inode->i_lock);
+	inode->i_blocks = st->blocks;
+	i_size_write(inode, st->size);
+	spin_unlock(&inode->i_lock);
+}
+
+/*
+ * common routine for aufs_getattr() and au_getxattr().
+ * returns zero or negative (an error).
+ * @dentry will be read-locked in success.
+ */
+int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path,
+		      int locked)
+{
+	int err;
+	unsigned int mnt_flags, sigen;
+	unsigned char udba_none;
+	aufs_bindex_t bindex;
+	struct super_block *sb, *h_sb;
+	struct inode *inode;
+
+	h_path->mnt = NULL;
+	h_path->dentry = NULL;
+
+	err = 0;
+	sb = dentry->d_sb;
+	mnt_flags = au_mntflags(sb);
+	udba_none = !!au_opt_test(mnt_flags, UDBA_NONE);
+
+	if (unlikely(locked))
+		goto body; /* skip locking dinfo */
+
+	/* support fstat(2) */
+	if (!d_unlinked(dentry) && !udba_none) {
+		sigen = au_sigen(sb);
+		err = au_digen_test(dentry, sigen);
+		if (!err) {
+			di_read_lock_child(dentry, AuLock_IR);
+			err = au_dbrange_test(dentry);
+			if (unlikely(err)) {
+				di_read_unlock(dentry, AuLock_IR);
+				goto out;
+			}
+		} else {
+			AuDebugOn(IS_ROOT(dentry));
+			di_write_lock_child(dentry);
+			err = au_dbrange_test(dentry);
+			if (!err)
+				err = au_reval_for_attr(dentry, sigen);
+			if (!err)
+				di_downgrade_lock(dentry, AuLock_IR);
+			else {
+				di_write_unlock(dentry);
+				goto out;
+			}
+		}
+	} else
+		di_read_lock_child(dentry, AuLock_IR);
+
+body:
+	inode = d_inode(dentry);
+	bindex = au_ibtop(inode);
+	h_path->mnt = au_sbr_mnt(sb, bindex);
+	h_sb = h_path->mnt->mnt_sb;
+	if (!force
+	    && !au_test_fs_bad_iattr(h_sb)
+	    && udba_none)
+		goto out; /* success */
+
+	if (au_dbtop(dentry) == bindex)
+		h_path->dentry = au_h_dptr(dentry, bindex);
+	else if (au_opt_test(mnt_flags, PLINK) && au_plink_test(inode)) {
+		h_path->dentry = au_plink_lkup(inode, bindex);
+		if (IS_ERR(h_path->dentry))
+			/* pretending success */
+			h_path->dentry = NULL;
+		else
+			dput(h_path->dentry);
+	}
+
+out:
+	return err;
+}
+
+static int aufs_getattr(const struct path *path, struct kstat *st,
+			u32 request, unsigned int query)
+{
+	int err;
+	unsigned char positive;
+	struct path h_path;
+	struct dentry *dentry;
+	struct inode *inode;
+	struct super_block *sb;
+
+	dentry = path->dentry;
+	inode = d_inode(dentry);
+	sb = dentry->d_sb;
+	err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
+	if (unlikely(err))
+		goto out;
+	err = au_h_path_getattr(dentry, /*force*/0, &h_path, /*locked*/0);
+	if (unlikely(err))
+		goto out_si;
+	if (unlikely(!h_path.dentry))
+		/* illegally overlapped or something */
+		goto out_fill; /* pretending success */
+
+	positive = d_is_positive(h_path.dentry);
+	if (positive)
+		/* no vfsub version */
+		err = vfs_getattr(&h_path, st, request, query);
+	if (!err) {
+		if (positive)
+			au_refresh_iattr(inode, st,
+					 d_inode(h_path.dentry)->i_nlink);
+		goto out_fill; /* success */
+	}
+	AuTraceErr(err);
+	goto out_di;
+
+out_fill:
+	generic_fillattr(inode, st);
+out_di:
+	di_read_unlock(dentry, AuLock_IR);
+out_si:
+	si_read_unlock(sb);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static const char *aufs_get_link(struct dentry *dentry, struct inode *inode,
+				 struct delayed_call *done)
+{
+	const char *ret;
+	struct dentry *h_dentry;
+	struct inode *h_inode;
+	int err;
+	aufs_bindex_t bindex;
+
+	ret = NULL; /* suppress a warning */
+	err = -ECHILD;
+	if (!dentry)
+		goto out;
+
+	err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN);
+	if (unlikely(err))
+		goto out;
+
+	err = au_d_hashed_positive(dentry);
+	if (unlikely(err))
+		goto out_unlock;
+
+	err = -EINVAL;
+	inode = d_inode(dentry);
+	bindex = au_ibtop(inode);
+	h_inode = au_h_iptr(inode, bindex);
+	if (unlikely(!h_inode->i_op->get_link))
+		goto out_unlock;
+
+	err = -EBUSY;
+	h_dentry = NULL;
+	if (au_dbtop(dentry) <= bindex) {
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (h_dentry)
+			dget(h_dentry);
+	}
+	if (!h_dentry) {
+		h_dentry = d_find_any_alias(h_inode);
+		if (IS_ERR(h_dentry)) {
+			err = PTR_ERR(h_dentry);
+			goto out_unlock;
+		}
+	}
+	if (unlikely(!h_dentry))
+		goto out_unlock;
+
+	err = 0;
+	AuDbg("%pf\n", h_inode->i_op->get_link);
+	AuDbgDentry(h_dentry);
+	ret = vfs_get_link(h_dentry, done);
+	dput(h_dentry);
+	if (IS_ERR(ret))
+		err = PTR_ERR(ret);
+
+out_unlock:
+	aufs_read_unlock(dentry, AuLock_IR);
+out:
+	if (unlikely(err))
+		ret = ERR_PTR(err);
+	AuTraceErrPtr(ret);
+	return ret;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_is_special(struct inode *inode)
+{
+	return (inode->i_mode & (S_IFBLK | S_IFCHR | S_IFIFO | S_IFSOCK));
+}
+
+static int aufs_update_time(struct inode *inode, struct timespec *ts, int flags)
+{
+	int err;
+	aufs_bindex_t bindex;
+	struct super_block *sb;
+	struct inode *h_inode;
+	struct vfsmount *h_mnt;
+
+	sb = inode->i_sb;
+	WARN_ONCE((flags & S_ATIME) && !IS_NOATIME(inode),
+		  "unexpected s_flags 0x%lx", sb->s_flags);
+
+	/* mmap_sem might be acquired already, cf. aufs_mmap() */
+	lockdep_off();
+	si_read_lock(sb, AuLock_FLUSH);
+	ii_write_lock_child(inode);
+	lockdep_on();
+
+	err = 0;
+	bindex = au_ibtop(inode);
+	h_inode = au_h_iptr(inode, bindex);
+	if (!au_test_ro(sb, bindex, inode)) {
+		h_mnt = au_sbr_mnt(sb, bindex);
+		err = vfsub_mnt_want_write(h_mnt);
+		if (!err) {
+			err = vfsub_update_time(h_inode, ts, flags);
+			vfsub_mnt_drop_write(h_mnt);
+		}
+	} else if (au_is_special(h_inode)) {
+		/*
+		 * Never copy-up here.
+		 * These special files may already be opened and used for
+		 * communicating. If we copied it up, then the communication
+		 * would be corrupted.
+		 */
+		AuWarn1("timestamps for i%lu are ignored "
+			"since it is on readonly branch (hi%lu).\n",
+			inode->i_ino, h_inode->i_ino);
+	} else if (flags & ~S_ATIME) {
+		err = -EIO;
+		AuIOErr1("unexpected flags 0x%x\n", flags);
+		AuDebugOn(1);
+	}
+
+	lockdep_off();
+	if (!err)
+		au_cpup_attr_timesizes(inode);
+	ii_write_unlock(inode);
+	si_read_unlock(sb);
+	lockdep_on();
+
+	if (!err && (flags & S_VERSION))
+		inode_inc_iversion(inode);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* no getattr version will be set by module.c:aufs_init() */
+struct inode_operations aufs_iop_nogetattr[AuIop_Last],
+	aufs_iop[] = {
+	[AuIop_SYMLINK] = {
+		.permission	= aufs_permission,
+#ifdef CONFIG_FS_POSIX_ACL
+		.get_acl	= aufs_get_acl,
+		.set_acl	= aufs_set_acl, /* unsupport for symlink? */
+#endif
+
+		.setattr	= aufs_setattr,
+		.getattr	= aufs_getattr,
+
+#ifdef CONFIG_AUFS_XATTR
+		.listxattr	= aufs_listxattr,
+#endif
+
+		.get_link	= aufs_get_link,
+
+		/* .update_time	= aufs_update_time */
+	},
+	[AuIop_DIR] = {
+		.create		= aufs_create,
+		.lookup		= aufs_lookup,
+		.link		= aufs_link,
+		.unlink		= aufs_unlink,
+		.symlink	= aufs_symlink,
+		.mkdir		= aufs_mkdir,
+		.rmdir		= aufs_rmdir,
+		.mknod		= aufs_mknod,
+		.rename		= aufs_rename,
+
+		.permission	= aufs_permission,
+#ifdef CONFIG_FS_POSIX_ACL
+		.get_acl	= aufs_get_acl,
+		.set_acl	= aufs_set_acl,
+#endif
+
+		.setattr	= aufs_setattr,
+		.getattr	= aufs_getattr,
+
+#ifdef CONFIG_AUFS_XATTR
+		.listxattr	= aufs_listxattr,
+#endif
+
+		.update_time	= aufs_update_time,
+		.atomic_open	= aufs_atomic_open,
+		.tmpfile	= aufs_tmpfile
+	},
+	[AuIop_OTHER] = {
+		.permission	= aufs_permission,
+#ifdef CONFIG_FS_POSIX_ACL
+		.get_acl	= aufs_get_acl,
+		.set_acl	= aufs_set_acl,
+#endif
+
+		.setattr	= aufs_setattr,
+		.getattr	= aufs_getattr,
+
+#ifdef CONFIG_AUFS_XATTR
+		.listxattr	= aufs_listxattr,
+#endif
+
+		.update_time	= aufs_update_time
+	}
+};
diff --git a/fs/aufs/i_op_add.c b/fs/aufs/i_op_add.c
new file mode 100644
index 000000000000..a678e723c6a0
--- /dev/null
+++ b/fs/aufs/i_op_add.c
@@ -0,0 +1,920 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * inode operations (add entry)
+ */
+
+#include "aufs.h"
+
+/*
+ * final procedure of adding a new entry, except link(2).
+ * remove whiteout, instantiate, copyup the parent dir's times and size
+ * and update version.
+ * if it failed, re-create the removed whiteout.
+ */
+static int epilog(struct inode *dir, aufs_bindex_t bindex,
+		  struct dentry *wh_dentry, struct dentry *dentry)
+{
+	int err, rerr;
+	aufs_bindex_t bwh;
+	struct path h_path;
+	struct super_block *sb;
+	struct inode *inode, *h_dir;
+	struct dentry *wh;
+
+	bwh = -1;
+	sb = dir->i_sb;
+	if (wh_dentry) {
+		h_dir = d_inode(wh_dentry->d_parent); /* dir inode is locked */
+		IMustLock(h_dir);
+		AuDebugOn(au_h_iptr(dir, bindex) != h_dir);
+		bwh = au_dbwh(dentry);
+		h_path.dentry = wh_dentry;
+		h_path.mnt = au_sbr_mnt(sb, bindex);
+		err = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path,
+					  dentry);
+		if (unlikely(err))
+			goto out;
+	}
+
+	inode = au_new_inode(dentry, /*must_new*/1);
+	if (!IS_ERR(inode)) {
+		d_instantiate(dentry, inode);
+		dir = d_inode(dentry->d_parent); /* dir inode is locked */
+		IMustLock(dir);
+		au_dir_ts(dir, bindex);
+		dir->i_version++;
+		au_fhsm_wrote(sb, bindex, /*force*/0);
+		return 0; /* success */
+	}
+
+	err = PTR_ERR(inode);
+	if (!wh_dentry)
+		goto out;
+
+	/* revert */
+	/* dir inode is locked */
+	wh = au_wh_create(dentry, bwh, wh_dentry->d_parent);
+	rerr = PTR_ERR(wh);
+	if (IS_ERR(wh)) {
+		AuIOErr("%pd reverting whiteout failed(%d, %d)\n",
+			dentry, err, rerr);
+		err = -EIO;
+	} else
+		dput(wh);
+
+out:
+	return err;
+}
+
+static int au_d_may_add(struct dentry *dentry)
+{
+	int err;
+
+	err = 0;
+	if (unlikely(d_unhashed(dentry)))
+		err = -ENOENT;
+	if (unlikely(d_really_is_positive(dentry)))
+		err = -EEXIST;
+	return err;
+}
+
+/*
+ * simple tests for the adding inode operations.
+ * following the checks in vfs, plus the parent-child relationship.
+ */
+int au_may_add(struct dentry *dentry, aufs_bindex_t bindex,
+	       struct dentry *h_parent, int isdir)
+{
+	int err;
+	umode_t h_mode;
+	struct dentry *h_dentry;
+	struct inode *h_inode;
+
+	err = -ENAMETOOLONG;
+	if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
+		goto out;
+
+	h_dentry = au_h_dptr(dentry, bindex);
+	if (d_really_is_negative(dentry)) {
+		err = -EEXIST;
+		if (unlikely(d_is_positive(h_dentry)))
+			goto out;
+	} else {
+		/* rename(2) case */
+		err = -EIO;
+		if (unlikely(d_is_negative(h_dentry)))
+			goto out;
+		h_inode = d_inode(h_dentry);
+		if (unlikely(!h_inode->i_nlink))
+			goto out;
+
+		h_mode = h_inode->i_mode;
+		if (!isdir) {
+			err = -EISDIR;
+			if (unlikely(S_ISDIR(h_mode)))
+				goto out;
+		} else if (unlikely(!S_ISDIR(h_mode))) {
+			err = -ENOTDIR;
+			goto out;
+		}
+	}
+
+	err = 0;
+	/* expected parent dir is locked */
+	if (unlikely(h_parent != h_dentry->d_parent))
+		err = -EIO;
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/*
+ * initial procedure of adding a new entry.
+ * prepare writable branch and the parent dir, lock it,
+ * and lookup whiteout for the new entry.
+ */
+static struct dentry*
+lock_hdir_lkup_wh(struct dentry *dentry, struct au_dtime *dt,
+		  struct dentry *src_dentry, struct au_pin *pin,
+		  struct au_wr_dir_args *wr_dir_args)
+{
+	struct dentry *wh_dentry, *h_parent;
+	struct super_block *sb;
+	struct au_branch *br;
+	int err;
+	unsigned int udba;
+	aufs_bindex_t bcpup;
+
+	AuDbg("%pd\n", dentry);
+
+	err = au_wr_dir(dentry, src_dentry, wr_dir_args);
+	bcpup = err;
+	wh_dentry = ERR_PTR(err);
+	if (unlikely(err < 0))
+		goto out;
+
+	sb = dentry->d_sb;
+	udba = au_opt_udba(sb);
+	err = au_pin(pin, dentry, bcpup, udba,
+		     AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+	wh_dentry = ERR_PTR(err);
+	if (unlikely(err))
+		goto out;
+
+	h_parent = au_pinned_h_parent(pin);
+	if (udba != AuOpt_UDBA_NONE
+	    && au_dbtop(dentry) == bcpup)
+		err = au_may_add(dentry, bcpup, h_parent,
+				 au_ftest_wrdir(wr_dir_args->flags, ISDIR));
+	else if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
+		err = -ENAMETOOLONG;
+	wh_dentry = ERR_PTR(err);
+	if (unlikely(err))
+		goto out_unpin;
+
+	br = au_sbr(sb, bcpup);
+	if (dt) {
+		struct path tmp = {
+			.dentry	= h_parent,
+			.mnt	= au_br_mnt(br)
+		};
+		au_dtime_store(dt, au_pinned_parent(pin), &tmp);
+	}
+
+	wh_dentry = NULL;
+	if (bcpup != au_dbwh(dentry))
+		goto out; /* success */
+
+	/*
+	 * ENAMETOOLONG here means that if we allowed create such name, then it
+	 * would not be able to removed in the future. So we don't allow such
+	 * name here and we don't handle ENAMETOOLONG differently here.
+	 */
+	wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, br);
+
+out_unpin:
+	if (IS_ERR(wh_dentry))
+		au_unpin(pin);
+out:
+	return wh_dentry;
+}
+
+/* ---------------------------------------------------------------------- */
+
+enum { Mknod, Symlink, Creat };
+struct simple_arg {
+	int type;
+	union {
+		struct {
+			umode_t			mode;
+			bool			want_excl;
+			bool			try_aopen;
+			struct vfsub_aopen_args	*aopen;
+		} c;
+		struct {
+			const char *symname;
+		} s;
+		struct {
+			umode_t mode;
+			dev_t dev;
+		} m;
+	} u;
+};
+
+static int add_simple(struct inode *dir, struct dentry *dentry,
+		      struct simple_arg *arg)
+{
+	int err, rerr;
+	aufs_bindex_t btop;
+	unsigned char created;
+	const unsigned char try_aopen
+		= (arg->type == Creat && arg->u.c.try_aopen);
+	struct dentry *wh_dentry, *parent;
+	struct inode *h_dir;
+	struct super_block *sb;
+	struct au_branch *br;
+	/* to reuduce stack size */
+	struct {
+		struct au_dtime dt;
+		struct au_pin pin;
+		struct path h_path;
+		struct au_wr_dir_args wr_dir_args;
+	} *a;
+
+	AuDbg("%pd\n", dentry);
+	IMustLock(dir);
+
+	err = -ENOMEM;
+	a = kmalloc(sizeof(*a), GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+	a->wr_dir_args.force_btgt = -1;
+	a->wr_dir_args.flags = AuWrDir_ADD_ENTRY;
+
+	parent = dentry->d_parent; /* dir inode is locked */
+	if (!try_aopen) {
+		err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
+		if (unlikely(err))
+			goto out_free;
+	}
+	err = au_d_may_add(dentry);
+	if (unlikely(err))
+		goto out_unlock;
+	if (!try_aopen)
+		di_write_lock_parent(parent);
+	wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL,
+				      &a->pin, &a->wr_dir_args);
+	err = PTR_ERR(wh_dentry);
+	if (IS_ERR(wh_dentry))
+		goto out_parent;
+
+	btop = au_dbtop(dentry);
+	sb = dentry->d_sb;
+	br = au_sbr(sb, btop);
+	a->h_path.dentry = au_h_dptr(dentry, btop);
+	a->h_path.mnt = au_br_mnt(br);
+	h_dir = au_pinned_h_dir(&a->pin);
+	switch (arg->type) {
+	case Creat:
+		err = 0;
+		if (!try_aopen || !h_dir->i_op->atomic_open)
+			err = vfsub_create(h_dir, &a->h_path, arg->u.c.mode,
+					   arg->u.c.want_excl);
+		else
+			err = vfsub_atomic_open(h_dir, a->h_path.dentry,
+						arg->u.c.aopen, br);
+		break;
+	case Symlink:
+		err = vfsub_symlink(h_dir, &a->h_path, arg->u.s.symname);
+		break;
+	case Mknod:
+		err = vfsub_mknod(h_dir, &a->h_path, arg->u.m.mode,
+				  arg->u.m.dev);
+		break;
+	default:
+		BUG();
+	}
+	created = !err;
+	if (!err)
+		err = epilog(dir, btop, wh_dentry, dentry);
+
+	/* revert */
+	if (unlikely(created && err && d_is_positive(a->h_path.dentry))) {
+		/* no delegation since it is just created */
+		rerr = vfsub_unlink(h_dir, &a->h_path, /*delegated*/NULL,
+				    /*force*/0);
+		if (rerr) {
+			AuIOErr("%pd revert failure(%d, %d)\n",
+				dentry, err, rerr);
+			err = -EIO;
+		}
+		au_dtime_revert(&a->dt);
+	}
+
+	if (!err && try_aopen && !h_dir->i_op->atomic_open)
+		*arg->u.c.aopen->opened |= FILE_CREATED;
+
+	au_unpin(&a->pin);
+	dput(wh_dentry);
+
+out_parent:
+	if (!try_aopen)
+		di_write_unlock(parent);
+out_unlock:
+	if (unlikely(err)) {
+		au_update_dbtop(dentry);
+		d_drop(dentry);
+	}
+	if (!try_aopen)
+		aufs_read_unlock(dentry, AuLock_DW);
+out_free:
+	kfree(a);
+out:
+	return err;
+}
+
+int aufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
+	       dev_t dev)
+{
+	struct simple_arg arg = {
+		.type = Mknod,
+		.u.m = {
+			.mode	= mode,
+			.dev	= dev
+		}
+	};
+	return add_simple(dir, dentry, &arg);
+}
+
+int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+{
+	struct simple_arg arg = {
+		.type = Symlink,
+		.u.s.symname = symname
+	};
+	return add_simple(dir, dentry, &arg);
+}
+
+int aufs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+		bool want_excl)
+{
+	struct simple_arg arg = {
+		.type = Creat,
+		.u.c = {
+			.mode		= mode,
+			.want_excl	= want_excl
+		}
+	};
+	return add_simple(dir, dentry, &arg);
+}
+
+int au_aopen_or_create(struct inode *dir, struct dentry *dentry,
+		       struct vfsub_aopen_args *aopen_args)
+{
+	struct simple_arg arg = {
+		.type = Creat,
+		.u.c = {
+			.mode		= aopen_args->create_mode,
+			.want_excl	= aopen_args->open_flag & O_EXCL,
+			.try_aopen	= true,
+			.aopen		= aopen_args
+		}
+	};
+	return add_simple(dir, dentry, &arg);
+}
+
+int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	int err;
+	aufs_bindex_t bindex;
+	struct super_block *sb;
+	struct dentry *parent, *h_parent, *h_dentry;
+	struct inode *h_dir, *inode;
+	struct vfsmount *h_mnt;
+	struct au_wr_dir_args wr_dir_args = {
+		.force_btgt	= -1,
+		.flags		= AuWrDir_TMPFILE
+	};
+
+	/* copy-up may happen */
+	inode_lock(dir);
+
+	sb = dir->i_sb;
+	err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
+	if (unlikely(err))
+		goto out;
+
+	err = au_di_init(dentry);
+	if (unlikely(err))
+		goto out_si;
+
+	err = -EBUSY;
+	parent = d_find_any_alias(dir);
+	AuDebugOn(!parent);
+	di_write_lock_parent(parent);
+	if (unlikely(d_inode(parent) != dir))
+		goto out_parent;
+
+	err = au_digen_test(parent, au_sigen(sb));
+	if (unlikely(err))
+		goto out_parent;
+
+	bindex = au_dbtop(parent);
+	au_set_dbtop(dentry, bindex);
+	au_set_dbbot(dentry, bindex);
+	err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args);
+	bindex = err;
+	if (unlikely(err < 0))
+		goto out_parent;
+
+	err = -EOPNOTSUPP;
+	h_dir = au_h_iptr(dir, bindex);
+	if (unlikely(!h_dir->i_op->tmpfile))
+		goto out_parent;
+
+	h_mnt = au_sbr_mnt(sb, bindex);
+	err = vfsub_mnt_want_write(h_mnt);
+	if (unlikely(err))
+		goto out_parent;
+
+	h_parent = au_h_dptr(parent, bindex);
+	h_dentry = vfs_tmpfile(h_parent, mode, /*open_flag*/0);
+	if (IS_ERR(h_dentry)) {
+		err = PTR_ERR(h_dentry);
+		goto out_mnt;
+	}
+
+	au_set_dbtop(dentry, bindex);
+	au_set_dbbot(dentry, bindex);
+	au_set_h_dptr(dentry, bindex, dget(h_dentry));
+	inode = au_new_inode(dentry, /*must_new*/1);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		au_set_h_dptr(dentry, bindex, NULL);
+		au_set_dbtop(dentry, -1);
+		au_set_dbbot(dentry, -1);
+	} else {
+		if (!inode->i_nlink)
+			set_nlink(inode, 1);
+		d_tmpfile(dentry, inode);
+		au_di(dentry)->di_tmpfile = 1;
+
+		/* update without i_mutex */
+		if (au_ibtop(dir) == au_dbtop(dentry))
+			au_cpup_attr_timesizes(dir);
+	}
+	dput(h_dentry);
+
+out_mnt:
+	vfsub_mnt_drop_write(h_mnt);
+out_parent:
+	di_write_unlock(parent);
+	dput(parent);
+	di_write_unlock(dentry);
+	if (unlikely(err)) {
+		au_di_fin(dentry);
+		dentry->d_fsdata = NULL;
+	}
+out_si:
+	si_read_unlock(sb);
+out:
+	inode_unlock(dir);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct au_link_args {
+	aufs_bindex_t bdst, bsrc;
+	struct au_pin pin;
+	struct path h_path;
+	struct dentry *src_parent, *parent;
+};
+
+static int au_cpup_before_link(struct dentry *src_dentry,
+			       struct au_link_args *a)
+{
+	int err;
+	struct dentry *h_src_dentry;
+	struct au_cp_generic cpg = {
+		.dentry	= src_dentry,
+		.bdst	= a->bdst,
+		.bsrc	= a->bsrc,
+		.len	= -1,
+		.pin	= &a->pin,
+		.flags	= AuCpup_DTIME | AuCpup_HOPEN /* | AuCpup_KEEPLINO */
+	};
+
+	di_read_lock_parent(a->src_parent, AuLock_IR);
+	err = au_test_and_cpup_dirs(src_dentry, a->bdst);
+	if (unlikely(err))
+		goto out;
+
+	h_src_dentry = au_h_dptr(src_dentry, a->bsrc);
+	err = au_pin(&a->pin, src_dentry, a->bdst,
+		     au_opt_udba(src_dentry->d_sb),
+		     AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+	if (unlikely(err))
+		goto out;
+
+	err = au_sio_cpup_simple(&cpg);
+	au_unpin(&a->pin);
+
+out:
+	di_read_unlock(a->src_parent, AuLock_IR);
+	return err;
+}
+
+static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry,
+			   struct au_link_args *a)
+{
+	int err;
+	unsigned char plink;
+	aufs_bindex_t bbot;
+	struct dentry *h_src_dentry;
+	struct inode *h_inode, *inode, *delegated;
+	struct super_block *sb;
+	struct file *h_file;
+
+	plink = 0;
+	h_inode = NULL;
+	sb = src_dentry->d_sb;
+	inode = d_inode(src_dentry);
+	if (au_ibtop(inode) <= a->bdst)
+		h_inode = au_h_iptr(inode, a->bdst);
+	if (!h_inode || !h_inode->i_nlink) {
+		/* copyup src_dentry as the name of dentry. */
+		bbot = au_dbbot(dentry);
+		if (bbot < a->bsrc)
+			au_set_dbbot(dentry, a->bsrc);
+		au_set_h_dptr(dentry, a->bsrc,
+			      dget(au_h_dptr(src_dentry, a->bsrc)));
+		dget(a->h_path.dentry);
+		au_set_h_dptr(dentry, a->bdst, NULL);
+		AuDbg("temporary d_inode...\n");
+		spin_lock(&dentry->d_lock);
+		dentry->d_inode = d_inode(src_dentry); /* tmp */
+		spin_unlock(&dentry->d_lock);
+		h_file = au_h_open_pre(dentry, a->bsrc, /*force_wr*/0);
+		if (IS_ERR(h_file))
+			err = PTR_ERR(h_file);
+		else {
+			struct au_cp_generic cpg = {
+				.dentry	= dentry,
+				.bdst	= a->bdst,
+				.bsrc	= -1,
+				.len	= -1,
+				.pin	= &a->pin,
+				.flags	= AuCpup_KEEPLINO
+			};
+			err = au_sio_cpup_simple(&cpg);
+			au_h_open_post(dentry, a->bsrc, h_file);
+			if (!err) {
+				dput(a->h_path.dentry);
+				a->h_path.dentry = au_h_dptr(dentry, a->bdst);
+			} else
+				au_set_h_dptr(dentry, a->bdst,
+					      a->h_path.dentry);
+		}
+		spin_lock(&dentry->d_lock);
+		dentry->d_inode = NULL; /* restore */
+		spin_unlock(&dentry->d_lock);
+		AuDbg("temporary d_inode...done\n");
+		au_set_h_dptr(dentry, a->bsrc, NULL);
+		au_set_dbbot(dentry, bbot);
+	} else {
+		/* the inode of src_dentry already exists on a.bdst branch */
+		h_src_dentry = d_find_alias(h_inode);
+		if (!h_src_dentry && au_plink_test(inode)) {
+			plink = 1;
+			h_src_dentry = au_plink_lkup(inode, a->bdst);
+			err = PTR_ERR(h_src_dentry);
+			if (IS_ERR(h_src_dentry))
+				goto out;
+
+			if (unlikely(d_is_negative(h_src_dentry))) {
+				dput(h_src_dentry);
+				h_src_dentry = NULL;
+			}
+
+		}
+		if (h_src_dentry) {
+			delegated = NULL;
+			err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
+					 &a->h_path, &delegated);
+			if (unlikely(err == -EWOULDBLOCK)) {
+				pr_warn("cannot retry for NFSv4 delegation"
+					" for an internal link\n");
+				iput(delegated);
+			}
+			dput(h_src_dentry);
+		} else {
+			AuIOErr("no dentry found for hi%lu on b%d\n",
+				h_inode->i_ino, a->bdst);
+			err = -EIO;
+		}
+	}
+
+	if (!err && !plink)
+		au_plink_append(inode, a->bdst, a->h_path.dentry);
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+int aufs_link(struct dentry *src_dentry, struct inode *dir,
+	      struct dentry *dentry)
+{
+	int err, rerr;
+	struct au_dtime dt;
+	struct au_link_args *a;
+	struct dentry *wh_dentry, *h_src_dentry;
+	struct inode *inode, *delegated;
+	struct super_block *sb;
+	struct au_wr_dir_args wr_dir_args = {
+		/* .force_btgt	= -1, */
+		.flags		= AuWrDir_ADD_ENTRY
+	};
+
+	IMustLock(dir);
+	inode = d_inode(src_dentry);
+	IMustLock(inode);
+
+	err = -ENOMEM;
+	a = kzalloc(sizeof(*a), GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+
+	a->parent = dentry->d_parent; /* dir inode is locked */
+	err = aufs_read_and_write_lock2(dentry, src_dentry,
+					AuLock_NOPLM | AuLock_GEN);
+	if (unlikely(err))
+		goto out_kfree;
+	err = au_d_linkable(src_dentry);
+	if (unlikely(err))
+		goto out_unlock;
+	err = au_d_may_add(dentry);
+	if (unlikely(err))
+		goto out_unlock;
+
+	a->src_parent = dget_parent(src_dentry);
+	wr_dir_args.force_btgt = au_ibtop(inode);
+
+	di_write_lock_parent(a->parent);
+	wr_dir_args.force_btgt = au_wbr(dentry, wr_dir_args.force_btgt);
+	wh_dentry = lock_hdir_lkup_wh(dentry, &dt, src_dentry, &a->pin,
+				      &wr_dir_args);
+	err = PTR_ERR(wh_dentry);
+	if (IS_ERR(wh_dentry))
+		goto out_parent;
+
+	err = 0;
+	sb = dentry->d_sb;
+	a->bdst = au_dbtop(dentry);
+	a->h_path.dentry = au_h_dptr(dentry, a->bdst);
+	a->h_path.mnt = au_sbr_mnt(sb, a->bdst);
+	a->bsrc = au_ibtop(inode);
+	h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
+	if (!h_src_dentry && au_di(src_dentry)->di_tmpfile)
+		h_src_dentry = dget(au_hi_wh(inode, a->bsrc));
+	if (!h_src_dentry) {
+		a->bsrc = au_dbtop(src_dentry);
+		h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
+		AuDebugOn(!h_src_dentry);
+	} else if (IS_ERR(h_src_dentry)) {
+		err = PTR_ERR(h_src_dentry);
+		goto out_parent;
+	}
+
+	/*
+	 * aufs doesn't touch the credential so
+	 * security_dentry_create_files_as() is unnecrssary.
+	 */
+	if (au_opt_test(au_mntflags(sb), PLINK)) {
+		if (a->bdst < a->bsrc
+		    /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */)
+			err = au_cpup_or_link(src_dentry, dentry, a);
+		else {
+			delegated = NULL;
+			err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
+					 &a->h_path, &delegated);
+			if (unlikely(err == -EWOULDBLOCK)) {
+				pr_warn("cannot retry for NFSv4 delegation"
+					" for an internal link\n");
+				iput(delegated);
+			}
+		}
+		dput(h_src_dentry);
+	} else {
+		/*
+		 * copyup src_dentry to the branch we process,
+		 * and then link(2) to it.
+		 */
+		dput(h_src_dentry);
+		if (a->bdst < a->bsrc
+		    /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) {
+			au_unpin(&a->pin);
+			di_write_unlock(a->parent);
+			err = au_cpup_before_link(src_dentry, a);
+			di_write_lock_parent(a->parent);
+			if (!err)
+				err = au_pin(&a->pin, dentry, a->bdst,
+					     au_opt_udba(sb),
+					     AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+			if (unlikely(err))
+				goto out_wh;
+		}
+		if (!err) {
+			h_src_dentry = au_h_dptr(src_dentry, a->bdst);
+			err = -ENOENT;
+			if (h_src_dentry && d_is_positive(h_src_dentry)) {
+				delegated = NULL;
+				err = vfsub_link(h_src_dentry,
+						 au_pinned_h_dir(&a->pin),
+						 &a->h_path, &delegated);
+				if (unlikely(err == -EWOULDBLOCK)) {
+					pr_warn("cannot retry"
+						" for NFSv4 delegation"
+						" for an internal link\n");
+					iput(delegated);
+				}
+			}
+		}
+	}
+	if (unlikely(err))
+		goto out_unpin;
+
+	if (wh_dentry) {
+		a->h_path.dentry = wh_dentry;
+		err = au_wh_unlink_dentry(au_pinned_h_dir(&a->pin), &a->h_path,
+					  dentry);
+		if (unlikely(err))
+			goto out_revert;
+	}
+
+	au_dir_ts(dir, a->bdst);
+	dir->i_version++;
+	inc_nlink(inode);
+	inode->i_ctime = dir->i_ctime;
+	d_instantiate(dentry, au_igrab(inode));
+	if (d_unhashed(a->h_path.dentry))
+		/* some filesystem calls d_drop() */
+		d_drop(dentry);
+	/* some filesystems consume an inode even hardlink */
+	au_fhsm_wrote(sb, a->bdst, /*force*/0);
+	goto out_unpin; /* success */
+
+out_revert:
+	/* no delegation since it is just created */
+	rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path,
+			    /*delegated*/NULL, /*force*/0);
+	if (unlikely(rerr)) {
+		AuIOErr("%pd reverting failed(%d, %d)\n", dentry, err, rerr);
+		err = -EIO;
+	}
+	au_dtime_revert(&dt);
+out_unpin:
+	au_unpin(&a->pin);
+out_wh:
+	dput(wh_dentry);
+out_parent:
+	di_write_unlock(a->parent);
+	dput(a->src_parent);
+out_unlock:
+	if (unlikely(err)) {
+		au_update_dbtop(dentry);
+		d_drop(dentry);
+	}
+	aufs_read_and_write_unlock2(dentry, src_dentry);
+out_kfree:
+	kfree(a);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	int err, rerr;
+	aufs_bindex_t bindex;
+	unsigned char diropq;
+	struct path h_path;
+	struct dentry *wh_dentry, *parent, *opq_dentry;
+	struct inode *h_inode;
+	struct super_block *sb;
+	struct {
+		struct au_pin pin;
+		struct au_dtime dt;
+	} *a; /* reduce the stack usage */
+	struct au_wr_dir_args wr_dir_args = {
+		.force_btgt	= -1,
+		.flags		= AuWrDir_ADD_ENTRY | AuWrDir_ISDIR
+	};
+
+	IMustLock(dir);
+
+	err = -ENOMEM;
+	a = kmalloc(sizeof(*a), GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+
+	err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
+	if (unlikely(err))
+		goto out_free;
+	err = au_d_may_add(dentry);
+	if (unlikely(err))
+		goto out_unlock;
+
+	parent = dentry->d_parent; /* dir inode is locked */
+	di_write_lock_parent(parent);
+	wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL,
+				      &a->pin, &wr_dir_args);
+	err = PTR_ERR(wh_dentry);
+	if (IS_ERR(wh_dentry))
+		goto out_parent;
+
+	sb = dentry->d_sb;
+	bindex = au_dbtop(dentry);
+	h_path.dentry = au_h_dptr(dentry, bindex);
+	h_path.mnt = au_sbr_mnt(sb, bindex);
+	err = vfsub_mkdir(au_pinned_h_dir(&a->pin), &h_path, mode);
+	if (unlikely(err))
+		goto out_unpin;
+
+	/* make the dir opaque */
+	diropq = 0;
+	h_inode = d_inode(h_path.dentry);
+	if (wh_dentry
+	    || au_opt_test(au_mntflags(sb), ALWAYS_DIROPQ)) {
+		inode_lock_nested(h_inode, AuLsc_I_CHILD);
+		opq_dentry = au_diropq_create(dentry, bindex);
+		inode_unlock(h_inode);
+		err = PTR_ERR(opq_dentry);
+		if (IS_ERR(opq_dentry))
+			goto out_dir;
+		dput(opq_dentry);
+		diropq = 1;
+	}
+
+	err = epilog(dir, bindex, wh_dentry, dentry);
+	if (!err) {
+		inc_nlink(dir);
+		goto out_unpin; /* success */
+	}
+
+	/* revert */
+	if (diropq) {
+		AuLabel(revert opq);
+		inode_lock_nested(h_inode, AuLsc_I_CHILD);
+		rerr = au_diropq_remove(dentry, bindex);
+		inode_unlock(h_inode);
+		if (rerr) {
+			AuIOErr("%pd reverting diropq failed(%d, %d)\n",
+				dentry, err, rerr);
+			err = -EIO;
+		}
+	}
+
+out_dir:
+	AuLabel(revert dir);
+	rerr = vfsub_rmdir(au_pinned_h_dir(&a->pin), &h_path);
+	if (rerr) {
+		AuIOErr("%pd reverting dir failed(%d, %d)\n",
+			dentry, err, rerr);
+		err = -EIO;
+	}
+	au_dtime_revert(&a->dt);
+out_unpin:
+	au_unpin(&a->pin);
+	dput(wh_dentry);
+out_parent:
+	di_write_unlock(parent);
+out_unlock:
+	if (unlikely(err)) {
+		au_update_dbtop(dentry);
+		d_drop(dentry);
+	}
+	aufs_read_unlock(dentry, AuLock_DW);
+out_free:
+	kfree(a);
+out:
+	return err;
+}
diff --git a/fs/aufs/i_op_del.c b/fs/aufs/i_op_del.c
new file mode 100644
index 000000000000..f67b74b2eb3a
--- /dev/null
+++ b/fs/aufs/i_op_del.c
@@ -0,0 +1,511 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * inode operations (del entry)
+ */
+
+#include "aufs.h"
+
+/*
+ * decide if a new whiteout for @dentry is necessary or not.
+ * when it is necessary, prepare the parent dir for the upper branch whose
+ * branch index is @bcpup for creation. the actual creation of the whiteout will
+ * be done by caller.
+ * return value:
+ * 0: wh is unnecessary
+ * plus: wh is necessary
+ * minus: error
+ */
+int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup)
+{
+	int need_wh, err;
+	aufs_bindex_t btop;
+	struct super_block *sb;
+
+	sb = dentry->d_sb;
+	btop = au_dbtop(dentry);
+	if (*bcpup < 0) {
+		*bcpup = btop;
+		if (au_test_ro(sb, btop, d_inode(dentry))) {
+			err = AuWbrCopyup(au_sbi(sb), dentry);
+			*bcpup = err;
+			if (unlikely(err < 0))
+				goto out;
+		}
+	} else
+		AuDebugOn(btop < *bcpup
+			  || au_test_ro(sb, *bcpup, d_inode(dentry)));
+	AuDbg("bcpup %d, btop %d\n", *bcpup, btop);
+
+	if (*bcpup != btop) {
+		err = au_cpup_dirs(dentry, *bcpup);
+		if (unlikely(err))
+			goto out;
+		need_wh = 1;
+	} else {
+		struct au_dinfo *dinfo, *tmp;
+
+		need_wh = -ENOMEM;
+		dinfo = au_di(dentry);
+		tmp = au_di_alloc(sb, AuLsc_DI_TMP);
+		if (tmp) {
+			au_di_cp(tmp, dinfo);
+			au_di_swap(tmp, dinfo);
+			/* returns the number of positive dentries */
+			need_wh = au_lkup_dentry(dentry, btop + 1,
+						 /* AuLkup_IGNORE_PERM */ 0);
+			au_di_swap(tmp, dinfo);
+			au_rw_write_unlock(&tmp->di_rwsem);
+			au_di_free(tmp);
+		}
+	}
+	AuDbg("need_wh %d\n", need_wh);
+	err = need_wh;
+
+out:
+	return err;
+}
+
+/*
+ * simple tests for the del-entry operations.
+ * following the checks in vfs, plus the parent-child relationship.
+ */
+int au_may_del(struct dentry *dentry, aufs_bindex_t bindex,
+	       struct dentry *h_parent, int isdir)
+{
+	int err;
+	umode_t h_mode;
+	struct dentry *h_dentry, *h_latest;
+	struct inode *h_inode;
+
+	h_dentry = au_h_dptr(dentry, bindex);
+	if (d_really_is_positive(dentry)) {
+		err = -ENOENT;
+		if (unlikely(d_is_negative(h_dentry)))
+			goto out;
+		h_inode = d_inode(h_dentry);
+		if (unlikely(!h_inode->i_nlink))
+			goto out;
+
+		h_mode = h_inode->i_mode;
+		if (!isdir) {
+			err = -EISDIR;
+			if (unlikely(S_ISDIR(h_mode)))
+				goto out;
+		} else if (unlikely(!S_ISDIR(h_mode))) {
+			err = -ENOTDIR;
+			goto out;
+		}
+	} else {
+		/* rename(2) case */
+		err = -EIO;
+		if (unlikely(d_is_positive(h_dentry)))
+			goto out;
+	}
+
+	err = -ENOENT;
+	/* expected parent dir is locked */
+	if (unlikely(h_parent != h_dentry->d_parent))
+		goto out;
+	err = 0;
+
+	/*
+	 * rmdir a dir may break the consistency on some filesystem.
+	 * let's try heavy test.
+	 */
+	err = -EACCES;
+	if (unlikely(!au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1)
+		     && au_test_h_perm(d_inode(h_parent),
+				       MAY_EXEC | MAY_WRITE)))
+		goto out;
+
+	h_latest = au_sio_lkup_one(&dentry->d_name, h_parent);
+	err = -EIO;
+	if (IS_ERR(h_latest))
+		goto out;
+	if (h_latest == h_dentry)
+		err = 0;
+	dput(h_latest);
+
+out:
+	return err;
+}
+
+/*
+ * decide the branch where we operate for @dentry. the branch index will be set
+ * @rbcpup. after diciding it, 'pin' it and store the timestamps of the parent
+ * dir for reverting.
+ * when a new whiteout is necessary, create it.
+ */
+static struct dentry*
+lock_hdir_create_wh(struct dentry *dentry, int isdir, aufs_bindex_t *rbcpup,
+		    struct au_dtime *dt, struct au_pin *pin)
+{
+	struct dentry *wh_dentry;
+	struct super_block *sb;
+	struct path h_path;
+	int err, need_wh;
+	unsigned int udba;
+	aufs_bindex_t bcpup;
+
+	need_wh = au_wr_dir_need_wh(dentry, isdir, rbcpup);
+	wh_dentry = ERR_PTR(need_wh);
+	if (unlikely(need_wh < 0))
+		goto out;
+
+	sb = dentry->d_sb;
+	udba = au_opt_udba(sb);
+	bcpup = *rbcpup;
+	err = au_pin(pin, dentry, bcpup, udba,
+		     AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+	wh_dentry = ERR_PTR(err);
+	if (unlikely(err))
+		goto out;
+
+	h_path.dentry = au_pinned_h_parent(pin);
+	if (udba != AuOpt_UDBA_NONE
+	    && au_dbtop(dentry) == bcpup) {
+		err = au_may_del(dentry, bcpup, h_path.dentry, isdir);
+		wh_dentry = ERR_PTR(err);
+		if (unlikely(err))
+			goto out_unpin;
+	}
+
+	h_path.mnt = au_sbr_mnt(sb, bcpup);
+	au_dtime_store(dt, au_pinned_parent(pin), &h_path);
+	wh_dentry = NULL;
+	if (!need_wh)
+		goto out; /* success, no need to create whiteout */
+
+	wh_dentry = au_wh_create(dentry, bcpup, h_path.dentry);
+	if (IS_ERR(wh_dentry))
+		goto out_unpin;
+
+	/* returns with the parent is locked and wh_dentry is dget-ed */
+	goto out; /* success */
+
+out_unpin:
+	au_unpin(pin);
+out:
+	return wh_dentry;
+}
+
+/*
+ * when removing a dir, rename it to a unique temporary whiteout-ed name first
+ * in order to be revertible and save time for removing many child whiteouts
+ * under the dir.
+ * returns 1 when there are too many child whiteout and caller should remove
+ * them asynchronously. returns 0 when the number of children is enough small to
+ * remove now or the branch fs is a remote fs.
+ * otherwise return an error.
+ */
+static int renwh_and_rmdir(struct dentry *dentry, aufs_bindex_t bindex,
+			   struct au_nhash *whlist, struct inode *dir)
+{
+	int rmdir_later, err, dirwh;
+	struct dentry *h_dentry;
+	struct super_block *sb;
+	struct inode *inode;
+
+	sb = dentry->d_sb;
+	SiMustAnyLock(sb);
+	h_dentry = au_h_dptr(dentry, bindex);
+	err = au_whtmp_ren(h_dentry, au_sbr(sb, bindex));
+	if (unlikely(err))
+		goto out;
+
+	/* stop monitoring */
+	inode = d_inode(dentry);
+	au_hn_free(au_hi(inode, bindex));
+
+	if (!au_test_fs_remote(h_dentry->d_sb)) {
+		dirwh = au_sbi(sb)->si_dirwh;
+		rmdir_later = (dirwh <= 1);
+		if (!rmdir_later)
+			rmdir_later = au_nhash_test_longer_wh(whlist, bindex,
+							      dirwh);
+		if (rmdir_later)
+			return rmdir_later;
+	}
+
+	err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist);
+	if (unlikely(err)) {
+		AuIOErr("rmdir %pd, b%d failed, %d. ignored\n",
+			h_dentry, bindex, err);
+		err = 0;
+	}
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/*
+ * final procedure for deleting a entry.
+ * maintain dentry and iattr.
+ */
+static void epilog(struct inode *dir, struct dentry *dentry,
+		   aufs_bindex_t bindex)
+{
+	struct inode *inode;
+
+	inode = d_inode(dentry);
+	d_drop(dentry);
+	inode->i_ctime = dir->i_ctime;
+
+	au_dir_ts(dir, bindex);
+	dir->i_version++;
+}
+
+/*
+ * when an error happened, remove the created whiteout and revert everything.
+ */
+static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex,
+		     aufs_bindex_t bwh, struct dentry *wh_dentry,
+		     struct dentry *dentry, struct au_dtime *dt)
+{
+	int rerr;
+	struct path h_path = {
+		.dentry	= wh_dentry,
+		.mnt	= au_sbr_mnt(dir->i_sb, bindex)
+	};
+
+	rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry);
+	if (!rerr) {
+		au_set_dbwh(dentry, bwh);
+		au_dtime_revert(dt);
+		return 0;
+	}
+
+	AuIOErr("%pd reverting whiteout failed(%d, %d)\n", dentry, err, rerr);
+	return -EIO;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int aufs_unlink(struct inode *dir, struct dentry *dentry)
+{
+	int err;
+	aufs_bindex_t bwh, bindex, btop;
+	struct inode *inode, *h_dir, *delegated;
+	struct dentry *parent, *wh_dentry;
+	/* to reuduce stack size */
+	struct {
+		struct au_dtime dt;
+		struct au_pin pin;
+		struct path h_path;
+	} *a;
+
+	IMustLock(dir);
+
+	err = -ENOMEM;
+	a = kmalloc(sizeof(*a), GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+
+	err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
+	if (unlikely(err))
+		goto out_free;
+	err = au_d_hashed_positive(dentry);
+	if (unlikely(err))
+		goto out_unlock;
+	inode = d_inode(dentry);
+	IMustLock(inode);
+	err = -EISDIR;
+	if (unlikely(d_is_dir(dentry)))
+		goto out_unlock; /* possible? */
+
+	btop = au_dbtop(dentry);
+	bwh = au_dbwh(dentry);
+	bindex = -1;
+	parent = dentry->d_parent; /* dir inode is locked */
+	di_write_lock_parent(parent);
+	wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &a->dt,
+					&a->pin);
+	err = PTR_ERR(wh_dentry);
+	if (IS_ERR(wh_dentry))
+		goto out_parent;
+
+	a->h_path.mnt = au_sbr_mnt(dentry->d_sb, btop);
+	a->h_path.dentry = au_h_dptr(dentry, btop);
+	dget(a->h_path.dentry);
+	if (bindex == btop) {
+		h_dir = au_pinned_h_dir(&a->pin);
+		delegated = NULL;
+		err = vfsub_unlink(h_dir, &a->h_path, &delegated, /*force*/0);
+		if (unlikely(err == -EWOULDBLOCK)) {
+			pr_warn("cannot retry for NFSv4 delegation"
+				" for an internal unlink\n");
+			iput(delegated);
+		}
+	} else {
+		/* dir inode is locked */
+		h_dir = d_inode(wh_dentry->d_parent);
+		IMustLock(h_dir);
+		err = 0;
+	}
+
+	if (!err) {
+		vfsub_drop_nlink(inode);
+		epilog(dir, dentry, bindex);
+
+		/* update target timestamps */
+		if (bindex == btop) {
+			vfsub_update_h_iattr(&a->h_path, /*did*/NULL);
+			/*ignore*/
+			inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime;
+		} else
+			/* todo: this timestamp may be reverted later */
+			inode->i_ctime = h_dir->i_ctime;
+		goto out_unpin; /* success */
+	}
+
+	/* revert */
+	if (wh_dentry) {
+		int rerr;
+
+		rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
+				 &a->dt);
+		if (rerr)
+			err = rerr;
+	}
+
+out_unpin:
+	au_unpin(&a->pin);
+	dput(wh_dentry);
+	dput(a->h_path.dentry);
+out_parent:
+	di_write_unlock(parent);
+out_unlock:
+	aufs_read_unlock(dentry, AuLock_DW);
+out_free:
+	kfree(a);
+out:
+	return err;
+}
+
+int aufs_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	int err, rmdir_later;
+	aufs_bindex_t bwh, bindex, btop;
+	struct inode *inode;
+	struct dentry *parent, *wh_dentry, *h_dentry;
+	struct au_whtmp_rmdir *args;
+	/* to reuduce stack size */
+	struct {
+		struct au_dtime dt;
+		struct au_pin pin;
+	} *a;
+
+	IMustLock(dir);
+
+	err = -ENOMEM;
+	a = kmalloc(sizeof(*a), GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+
+	err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
+	if (unlikely(err))
+		goto out_free;
+	err = au_alive_dir(dentry);
+	if (unlikely(err))
+		goto out_unlock;
+	inode = d_inode(dentry);
+	IMustLock(inode);
+	err = -ENOTDIR;
+	if (unlikely(!d_is_dir(dentry)))
+		goto out_unlock; /* possible? */
+
+	err = -ENOMEM;
+	args = au_whtmp_rmdir_alloc(dir->i_sb, GFP_NOFS);
+	if (unlikely(!args))
+		goto out_unlock;
+
+	parent = dentry->d_parent; /* dir inode is locked */
+	di_write_lock_parent(parent);
+	err = au_test_empty(dentry, &args->whlist);
+	if (unlikely(err))
+		goto out_parent;
+
+	btop = au_dbtop(dentry);
+	bwh = au_dbwh(dentry);
+	bindex = -1;
+	wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &a->dt,
+					&a->pin);
+	err = PTR_ERR(wh_dentry);
+	if (IS_ERR(wh_dentry))
+		goto out_parent;
+
+	h_dentry = au_h_dptr(dentry, btop);
+	dget(h_dentry);
+	rmdir_later = 0;
+	if (bindex == btop) {
+		err = renwh_and_rmdir(dentry, btop, &args->whlist, dir);
+		if (err > 0) {
+			rmdir_later = err;
+			err = 0;
+		}
+	} else {
+		/* stop monitoring */
+		au_hn_free(au_hi(inode, btop));
+
+		/* dir inode is locked */
+		IMustLock(d_inode(wh_dentry->d_parent));
+		err = 0;
+	}
+
+	if (!err) {
+		vfsub_dead_dir(inode);
+		au_set_dbdiropq(dentry, -1);
+		epilog(dir, dentry, bindex);
+
+		if (rmdir_later) {
+			au_whtmp_kick_rmdir(dir, btop, h_dentry, args);
+			args = NULL;
+		}
+
+		goto out_unpin; /* success */
+	}
+
+	/* revert */
+	AuLabel(revert);
+	if (wh_dentry) {
+		int rerr;
+
+		rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
+				 &a->dt);
+		if (rerr)
+			err = rerr;
+	}
+
+out_unpin:
+	au_unpin(&a->pin);
+	dput(wh_dentry);
+	dput(h_dentry);
+out_parent:
+	di_write_unlock(parent);
+	if (args)
+		au_whtmp_rmdir_free(args);
+out_unlock:
+	aufs_read_unlock(dentry, AuLock_DW);
+out_free:
+	kfree(a);
+out:
+	AuTraceErr(err);
+	return err;
+}
diff --git a/fs/aufs/i_op_ren.c b/fs/aufs/i_op_ren.c
new file mode 100644
index 000000000000..9a0b8f843fdf
--- /dev/null
+++ b/fs/aufs/i_op_ren.c
@@ -0,0 +1,1166 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * inode operation (rename entry)
+ * todo: this is crazy monster
+ */
+
+#include "aufs.h"
+
+enum { AuSRC, AuDST, AuSrcDst };
+enum { AuPARENT, AuCHILD, AuParentChild };
+
+#define AuRen_ISDIR_SRC		1
+#define AuRen_ISDIR_DST		(1 << 1)
+#define AuRen_ISSAMEDIR		(1 << 2)
+#define AuRen_WHSRC		(1 << 3)
+#define AuRen_WHDST		(1 << 4)
+#define AuRen_MNT_WRITE		(1 << 5)
+#define AuRen_DT_DSTDIR		(1 << 6)
+#define AuRen_DIROPQ_SRC	(1 << 7)
+#define AuRen_DIROPQ_DST	(1 << 8)
+#define au_ftest_ren(flags, name)	((flags) & AuRen_##name)
+#define au_fset_ren(flags, name) \
+	do { (flags) |= AuRen_##name; } while (0)
+#define au_fclr_ren(flags, name) \
+	do { (flags) &= ~AuRen_##name; } while (0)
+
+struct au_ren_args {
+	struct {
+		struct dentry *dentry, *h_dentry, *parent, *h_parent,
+			*wh_dentry;
+		struct inode *dir, *inode;
+		struct au_hinode *hdir, *hinode;
+		struct au_dtime dt[AuParentChild];
+		aufs_bindex_t btop, bdiropq;
+	} sd[AuSrcDst];
+
+#define src_dentry	sd[AuSRC].dentry
+#define src_dir		sd[AuSRC].dir
+#define src_inode	sd[AuSRC].inode
+#define src_h_dentry	sd[AuSRC].h_dentry
+#define src_parent	sd[AuSRC].parent
+#define src_h_parent	sd[AuSRC].h_parent
+#define src_wh_dentry	sd[AuSRC].wh_dentry
+#define src_hdir	sd[AuSRC].hdir
+#define src_hinode	sd[AuSRC].hinode
+#define src_h_dir	sd[AuSRC].hdir->hi_inode
+#define src_dt		sd[AuSRC].dt
+#define src_btop	sd[AuSRC].btop
+#define src_bdiropq	sd[AuSRC].bdiropq
+
+#define dst_dentry	sd[AuDST].dentry
+#define dst_dir		sd[AuDST].dir
+#define dst_inode	sd[AuDST].inode
+#define dst_h_dentry	sd[AuDST].h_dentry
+#define dst_parent	sd[AuDST].parent
+#define dst_h_parent	sd[AuDST].h_parent
+#define dst_wh_dentry	sd[AuDST].wh_dentry
+#define dst_hdir	sd[AuDST].hdir
+#define dst_hinode	sd[AuDST].hinode
+#define dst_h_dir	sd[AuDST].hdir->hi_inode
+#define dst_dt		sd[AuDST].dt
+#define dst_btop	sd[AuDST].btop
+#define dst_bdiropq	sd[AuDST].bdiropq
+
+	struct dentry *h_trap;
+	struct au_branch *br;
+	struct path h_path;
+	struct au_nhash whlist;
+	aufs_bindex_t btgt, src_bwh;
+
+	struct {
+		unsigned short auren_flags;
+		unsigned char flags;	/* syscall parameter */
+		unsigned char exchange;
+	} __packed;
+
+	struct au_whtmp_rmdir *thargs;
+	struct dentry *h_dst;
+};
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * functions for reverting.
+ * when an error happened in a single rename systemcall, we should revert
+ * everything as if nothing happened.
+ * we don't need to revert the copied-up/down the parent dir since they are
+ * harmless.
+ */
+
+#define RevertFailure(fmt, ...) do { \
+	AuIOErr("revert failure: " fmt " (%d, %d)\n", \
+		##__VA_ARGS__, err, rerr); \
+	err = -EIO; \
+} while (0)
+
+static void au_ren_do_rev_diropq(int err, struct au_ren_args *a, int idx)
+{
+	int rerr;
+	struct dentry *d;
+#define src_or_dst(member) a->sd[idx].member
+
+	d = src_or_dst(dentry); /* {src,dst}_dentry */
+	au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD);
+	rerr = au_diropq_remove(d, a->btgt);
+	au_hn_inode_unlock(src_or_dst(hinode));
+	au_set_dbdiropq(d, src_or_dst(bdiropq));
+	if (rerr)
+		RevertFailure("remove diropq %pd", d);
+
+#undef src_or_dst_
+}
+
+static void au_ren_rev_diropq(int err, struct au_ren_args *a)
+{
+	if (au_ftest_ren(a->auren_flags, DIROPQ_SRC))
+		au_ren_do_rev_diropq(err, a, AuSRC);
+	if (au_ftest_ren(a->auren_flags, DIROPQ_DST))
+		au_ren_do_rev_diropq(err, a, AuDST);
+}
+
+static void au_ren_rev_rename(int err, struct au_ren_args *a)
+{
+	int rerr;
+	struct inode *delegated;
+
+	a->h_path.dentry = vfsub_lkup_one(&a->src_dentry->d_name,
+					  a->src_h_parent);
+	rerr = PTR_ERR(a->h_path.dentry);
+	if (IS_ERR(a->h_path.dentry)) {
+		RevertFailure("lkup one %pd", a->src_dentry);
+		return;
+	}
+
+	delegated = NULL;
+	rerr = vfsub_rename(a->dst_h_dir,
+			    au_h_dptr(a->src_dentry, a->btgt),
+			    a->src_h_dir, &a->h_path, &delegated, a->flags);
+	if (unlikely(rerr == -EWOULDBLOCK)) {
+		pr_warn("cannot retry for NFSv4 delegation"
+			" for an internal rename\n");
+		iput(delegated);
+	}
+	d_drop(a->h_path.dentry);
+	dput(a->h_path.dentry);
+	/* au_set_h_dptr(a->src_dentry, a->btgt, NULL); */
+	if (rerr)
+		RevertFailure("rename %pd", a->src_dentry);
+}
+
+static void au_ren_rev_whtmp(int err, struct au_ren_args *a)
+{
+	int rerr;
+	struct inode *delegated;
+
+	a->h_path.dentry = vfsub_lkup_one(&a->dst_dentry->d_name,
+					  a->dst_h_parent);
+	rerr = PTR_ERR(a->h_path.dentry);
+	if (IS_ERR(a->h_path.dentry)) {
+		RevertFailure("lkup one %pd", a->dst_dentry);
+		return;
+	}
+	if (d_is_positive(a->h_path.dentry)) {
+		d_drop(a->h_path.dentry);
+		dput(a->h_path.dentry);
+		return;
+	}
+
+	delegated = NULL;
+	rerr = vfsub_rename(a->dst_h_dir, a->h_dst, a->dst_h_dir, &a->h_path,
+			    &delegated, a->flags);
+	if (unlikely(rerr == -EWOULDBLOCK)) {
+		pr_warn("cannot retry for NFSv4 delegation"
+			" for an internal rename\n");
+		iput(delegated);
+	}
+	d_drop(a->h_path.dentry);
+	dput(a->h_path.dentry);
+	if (!rerr)
+		au_set_h_dptr(a->dst_dentry, a->btgt, dget(a->h_dst));
+	else
+		RevertFailure("rename %pd", a->h_dst);
+}
+
+static void au_ren_rev_whsrc(int err, struct au_ren_args *a)
+{
+	int rerr;
+
+	a->h_path.dentry = a->src_wh_dentry;
+	rerr = au_wh_unlink_dentry(a->src_h_dir, &a->h_path, a->src_dentry);
+	au_set_dbwh(a->src_dentry, a->src_bwh);
+	if (rerr)
+		RevertFailure("unlink %pd", a->src_wh_dentry);
+}
+#undef RevertFailure
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * when we have to copyup the renaming entry, do it with the rename-target name
+ * in order to minimize the cost (the later actual rename is unnecessary).
+ * otherwise rename it on the target branch.
+ */
+static int au_ren_or_cpup(struct au_ren_args *a)
+{
+	int err;
+	struct dentry *d;
+	struct inode *delegated;
+
+	d = a->src_dentry;
+	if (au_dbtop(d) == a->btgt) {
+		a->h_path.dentry = a->dst_h_dentry;
+		AuDebugOn(au_dbtop(d) != a->btgt);
+		delegated = NULL;
+		err = vfsub_rename(a->src_h_dir, au_h_dptr(d, a->btgt),
+				   a->dst_h_dir, &a->h_path, &delegated,
+				   a->flags);
+		if (unlikely(err == -EWOULDBLOCK)) {
+			pr_warn("cannot retry for NFSv4 delegation"
+				" for an internal rename\n");
+			iput(delegated);
+		}
+	} else
+		BUG();
+
+	if (!err && a->h_dst)
+		/* it will be set to dinfo later */
+		dget(a->h_dst);
+
+	return err;
+}
+
+/* cf. aufs_rmdir() */
+static int au_ren_del_whtmp(struct au_ren_args *a)
+{
+	int err;
+	struct inode *dir;
+
+	dir = a->dst_dir;
+	SiMustAnyLock(dir->i_sb);
+	if (!au_nhash_test_longer_wh(&a->whlist, a->btgt,
+				     au_sbi(dir->i_sb)->si_dirwh)
+	    || au_test_fs_remote(a->h_dst->d_sb)) {
+		err = au_whtmp_rmdir(dir, a->btgt, a->h_dst, &a->whlist);
+		if (unlikely(err))
+			pr_warn("failed removing whtmp dir %pd (%d), "
+				"ignored.\n", a->h_dst, err);
+	} else {
+		au_nhash_wh_free(&a->thargs->whlist);
+		a->thargs->whlist = a->whlist;
+		a->whlist.nh_num = 0;
+		au_whtmp_kick_rmdir(dir, a->btgt, a->h_dst, a->thargs);
+		dput(a->h_dst);
+		a->thargs = NULL;
+	}
+
+	return 0;
+}
+
+/* make it 'opaque' dir. */
+static int au_ren_do_diropq(struct au_ren_args *a, int idx)
+{
+	int err;
+	struct dentry *d, *diropq;
+#define src_or_dst(member) a->sd[idx].member
+
+	err = 0;
+	d = src_or_dst(dentry); /* {src,dst}_dentry */
+	src_or_dst(bdiropq) = au_dbdiropq(d);
+	src_or_dst(hinode) = au_hi(src_or_dst(inode), a->btgt);
+	au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD);
+	diropq = au_diropq_create(d, a->btgt);
+	au_hn_inode_unlock(src_or_dst(hinode));
+	if (IS_ERR(diropq))
+		err = PTR_ERR(diropq);
+	else
+		dput(diropq);
+
+#undef src_or_dst_
+	return err;
+}
+
+static int au_ren_diropq(struct au_ren_args *a)
+{
+	int err;
+	unsigned char always;
+	struct dentry *d;
+
+	err = 0;
+	d = a->dst_dentry; /* already renamed on the branch */
+	always = !!au_opt_test(au_mntflags(d->d_sb), ALWAYS_DIROPQ);
+	if (au_ftest_ren(a->auren_flags, ISDIR_SRC)
+	    && a->btgt != au_dbdiropq(a->src_dentry)
+	    && (a->dst_wh_dentry
+		|| a->btgt <= au_dbdiropq(d)
+		/* hide the lower to keep xino */
+		/* the lowers may not be a dir, but we hide them anyway */
+		|| a->btgt < au_dbbot(d)
+		|| always)) {
+		AuDbg("here\n");
+		err = au_ren_do_diropq(a, AuSRC);
+		if (unlikely(err))
+			goto out;
+		au_fset_ren(a->auren_flags, DIROPQ_SRC);
+	}
+	if (!a->exchange)
+		goto out; /* success */
+
+	d = a->src_dentry; /* already renamed on the branch */
+	if (au_ftest_ren(a->auren_flags, ISDIR_DST)
+	    && a->btgt != au_dbdiropq(a->dst_dentry)
+	    && (a->btgt < au_dbdiropq(d)
+		|| a->btgt < au_dbbot(d)
+		|| always)) {
+		AuDbgDentry(a->src_dentry);
+		AuDbgDentry(a->dst_dentry);
+		err = au_ren_do_diropq(a, AuDST);
+		if (unlikely(err))
+			goto out_rev_src;
+		au_fset_ren(a->auren_flags, DIROPQ_DST);
+	}
+	goto out; /* success */
+
+out_rev_src:
+	AuDbg("err %d, reverting src\n", err);
+	au_ren_rev_diropq(err, a);
+out:
+	return err;
+}
+
+static int do_rename(struct au_ren_args *a)
+{
+	int err;
+	struct dentry *d, *h_d;
+
+	if (!a->exchange) {
+		/* prepare workqueue args for asynchronous rmdir */
+		h_d = a->dst_h_dentry;
+		if (au_ftest_ren(a->auren_flags, ISDIR_DST)
+		    && d_is_positive(h_d)) {
+			err = -ENOMEM;
+			a->thargs = au_whtmp_rmdir_alloc(a->src_dentry->d_sb,
+							 GFP_NOFS);
+			if (unlikely(!a->thargs))
+				goto out;
+			a->h_dst = dget(h_d);
+		}
+
+		/* create whiteout for src_dentry */
+		if (au_ftest_ren(a->auren_flags, WHSRC)) {
+			a->src_bwh = au_dbwh(a->src_dentry);
+			AuDebugOn(a->src_bwh >= 0);
+			a->src_wh_dentry = au_wh_create(a->src_dentry, a->btgt,
+							a->src_h_parent);
+			err = PTR_ERR(a->src_wh_dentry);
+			if (IS_ERR(a->src_wh_dentry))
+				goto out_thargs;
+		}
+
+		/* lookup whiteout for dentry */
+		if (au_ftest_ren(a->auren_flags, WHDST)) {
+			h_d = au_wh_lkup(a->dst_h_parent,
+					 &a->dst_dentry->d_name, a->br);
+			err = PTR_ERR(h_d);
+			if (IS_ERR(h_d))
+				goto out_whsrc;
+			if (d_is_negative(h_d))
+				dput(h_d);
+			else
+				a->dst_wh_dentry = h_d;
+		}
+
+		/* rename dentry to tmpwh */
+		if (a->thargs) {
+			err = au_whtmp_ren(a->dst_h_dentry, a->br);
+			if (unlikely(err))
+				goto out_whdst;
+
+			d = a->dst_dentry;
+			au_set_h_dptr(d, a->btgt, NULL);
+			err = au_lkup_neg(d, a->btgt, /*wh*/0);
+			if (unlikely(err))
+				goto out_whtmp;
+			a->dst_h_dentry = au_h_dptr(d, a->btgt);
+		}
+	}
+
+	BUG_ON(d_is_positive(a->dst_h_dentry) && a->src_btop != a->btgt);
+
+	/* rename by vfs_rename or cpup */
+	err = au_ren_or_cpup(a);
+	if (unlikely(err))
+		/* leave the copied-up one */
+		goto out_whtmp;
+
+	/* make dir opaque */
+	err = au_ren_diropq(a);
+	if (unlikely(err))
+		goto out_rename;
+
+	/* update target timestamps */
+	if (a->exchange) {
+		AuDebugOn(au_dbtop(a->dst_dentry) != a->btgt);
+		a->h_path.dentry = au_h_dptr(a->dst_dentry, a->btgt);
+		vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/
+		a->dst_inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime;
+	}
+	AuDebugOn(au_dbtop(a->src_dentry) != a->btgt);
+	a->h_path.dentry = au_h_dptr(a->src_dentry, a->btgt);
+	vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/
+	a->src_inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime;
+
+	if (!a->exchange) {
+		/* remove whiteout for dentry */
+		if (a->dst_wh_dentry) {
+			a->h_path.dentry = a->dst_wh_dentry;
+			err = au_wh_unlink_dentry(a->dst_h_dir, &a->h_path,
+						  a->dst_dentry);
+			if (unlikely(err))
+				goto out_diropq;
+		}
+
+		/* remove whtmp */
+		if (a->thargs)
+			au_ren_del_whtmp(a); /* ignore this error */
+
+		au_fhsm_wrote(a->src_dentry->d_sb, a->btgt, /*force*/0);
+	}
+	err = 0;
+	goto out_success;
+
+out_diropq:
+	au_ren_rev_diropq(err, a);
+out_rename:
+	au_ren_rev_rename(err, a);
+	dput(a->h_dst);
+out_whtmp:
+	if (a->thargs)
+		au_ren_rev_whtmp(err, a);
+out_whdst:
+	dput(a->dst_wh_dentry);
+	a->dst_wh_dentry = NULL;
+out_whsrc:
+	if (a->src_wh_dentry)
+		au_ren_rev_whsrc(err, a);
+out_success:
+	dput(a->src_wh_dentry);
+	dput(a->dst_wh_dentry);
+out_thargs:
+	if (a->thargs) {
+		dput(a->h_dst);
+		au_whtmp_rmdir_free(a->thargs);
+		a->thargs = NULL;
+	}
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * test if @dentry dir can be rename destination or not.
+ * success means, it is a logically empty dir.
+ */
+static int may_rename_dstdir(struct dentry *dentry, struct au_nhash *whlist)
+{
+	return au_test_empty(dentry, whlist);
+}
+
+/*
+ * test if @dentry dir can be rename source or not.
+ * if it can, return 0 and @children is filled.
+ * success means,
+ * - it is a logically empty dir.
+ * - or, it exists on writable branch and has no children including whiteouts
+ *       on the lower branch.
+ */
+static int may_rename_srcdir(struct dentry *dentry, aufs_bindex_t btgt)
+{
+	int err;
+	unsigned int rdhash;
+	aufs_bindex_t btop;
+
+	btop = au_dbtop(dentry);
+	if (btop != btgt) {
+		struct au_nhash whlist;
+
+		SiMustAnyLock(dentry->d_sb);
+		rdhash = au_sbi(dentry->d_sb)->si_rdhash;
+		if (!rdhash)
+			rdhash = au_rdhash_est(au_dir_size(/*file*/NULL,
+							   dentry));
+		err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS);
+		if (unlikely(err))
+			goto out;
+		err = au_test_empty(dentry, &whlist);
+		au_nhash_wh_free(&whlist);
+		goto out;
+	}
+
+	if (btop == au_dbtaildir(dentry))
+		return 0; /* success */
+
+	err = au_test_empty_lower(dentry);
+
+out:
+	if (err == -ENOTEMPTY) {
+		AuWarn1("renaming dir who has child(ren) on multiple branches,"
+			" is not supported\n");
+		err = -EXDEV;
+	}
+	return err;
+}
+
+/* side effect: sets whlist and h_dentry */
+static int au_ren_may_dir(struct au_ren_args *a)
+{
+	int err;
+	unsigned int rdhash;
+	struct dentry *d;
+
+	d = a->dst_dentry;
+	SiMustAnyLock(d->d_sb);
+
+	err = 0;
+	if (au_ftest_ren(a->auren_flags, ISDIR_DST) && a->dst_inode) {
+		rdhash = au_sbi(d->d_sb)->si_rdhash;
+		if (!rdhash)
+			rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, d));
+		err = au_nhash_alloc(&a->whlist, rdhash, GFP_NOFS);
+		if (unlikely(err))
+			goto out;
+
+		if (!a->exchange) {
+			au_set_dbtop(d, a->dst_btop);
+			err = may_rename_dstdir(d, &a->whlist);
+			au_set_dbtop(d, a->btgt);
+		} else
+			err = may_rename_srcdir(d, a->btgt);
+	}
+	a->dst_h_dentry = au_h_dptr(d, au_dbtop(d));
+	if (unlikely(err))
+		goto out;
+
+	d = a->src_dentry;
+	a->src_h_dentry = au_h_dptr(d, au_dbtop(d));
+	if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) {
+		err = may_rename_srcdir(d, a->btgt);
+		if (unlikely(err)) {
+			au_nhash_wh_free(&a->whlist);
+			a->whlist.nh_num = 0;
+		}
+	}
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * simple tests for rename.
+ * following the checks in vfs, plus the parent-child relationship.
+ */
+static int au_may_ren(struct au_ren_args *a)
+{
+	int err, isdir;
+	struct inode *h_inode;
+
+	if (a->src_btop == a->btgt) {
+		err = au_may_del(a->src_dentry, a->btgt, a->src_h_parent,
+				 au_ftest_ren(a->auren_flags, ISDIR_SRC));
+		if (unlikely(err))
+			goto out;
+		err = -EINVAL;
+		if (unlikely(a->src_h_dentry == a->h_trap))
+			goto out;
+	}
+
+	err = 0;
+	if (a->dst_btop != a->btgt)
+		goto out;
+
+	err = -ENOTEMPTY;
+	if (unlikely(a->dst_h_dentry == a->h_trap))
+		goto out;
+
+	err = -EIO;
+	isdir = !!au_ftest_ren(a->auren_flags, ISDIR_DST);
+	if (d_really_is_negative(a->dst_dentry)) {
+		if (d_is_negative(a->dst_h_dentry))
+			err = au_may_add(a->dst_dentry, a->btgt,
+					 a->dst_h_parent, isdir);
+	} else {
+		if (unlikely(d_is_negative(a->dst_h_dentry)))
+			goto out;
+		h_inode = d_inode(a->dst_h_dentry);
+		if (h_inode->i_nlink)
+			err = au_may_del(a->dst_dentry, a->btgt,
+					 a->dst_h_parent, isdir);
+	}
+
+out:
+	if (unlikely(err == -ENOENT || err == -EEXIST))
+		err = -EIO;
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * locking order
+ * (VFS)
+ * - src_dir and dir by lock_rename()
+ * - inode if exitsts
+ * (aufs)
+ * - lock all
+ *   + src_dentry and dentry by aufs_read_and_write_lock2() which calls,
+ *     + si_read_lock
+ *     + di_write_lock2_child()
+ *       + di_write_lock_child()
+ *	   + ii_write_lock_child()
+ *       + di_write_lock_child2()
+ *	   + ii_write_lock_child2()
+ *     + src_parent and parent
+ *       + di_write_lock_parent()
+ *	   + ii_write_lock_parent()
+ *       + di_write_lock_parent2()
+ *	   + ii_write_lock_parent2()
+ *   + lower src_dir and dir by vfsub_lock_rename()
+ *   + verify the every relationships between child and parent. if any
+ *     of them failed, unlock all and return -EBUSY.
+ */
+static void au_ren_unlock(struct au_ren_args *a)
+{
+	vfsub_unlock_rename(a->src_h_parent, a->src_hdir,
+			    a->dst_h_parent, a->dst_hdir);
+	if (au_ftest_ren(a->auren_flags, MNT_WRITE))
+		vfsub_mnt_drop_write(au_br_mnt(a->br));
+}
+
+static int au_ren_lock(struct au_ren_args *a)
+{
+	int err;
+	unsigned int udba;
+
+	err = 0;
+	a->src_h_parent = au_h_dptr(a->src_parent, a->btgt);
+	a->src_hdir = au_hi(a->src_dir, a->btgt);
+	a->dst_h_parent = au_h_dptr(a->dst_parent, a->btgt);
+	a->dst_hdir = au_hi(a->dst_dir, a->btgt);
+
+	err = vfsub_mnt_want_write(au_br_mnt(a->br));
+	if (unlikely(err))
+		goto out;
+	au_fset_ren(a->auren_flags, MNT_WRITE);
+	a->h_trap = vfsub_lock_rename(a->src_h_parent, a->src_hdir,
+				      a->dst_h_parent, a->dst_hdir);
+	udba = au_opt_udba(a->src_dentry->d_sb);
+	if (unlikely(a->src_hdir->hi_inode != d_inode(a->src_h_parent)
+		     || a->dst_hdir->hi_inode != d_inode(a->dst_h_parent)))
+		err = au_busy_or_stale();
+	if (!err && au_dbtop(a->src_dentry) == a->btgt)
+		err = au_h_verify(a->src_h_dentry, udba,
+				  d_inode(a->src_h_parent), a->src_h_parent,
+				  a->br);
+	if (!err && au_dbtop(a->dst_dentry) == a->btgt)
+		err = au_h_verify(a->dst_h_dentry, udba,
+				  d_inode(a->dst_h_parent), a->dst_h_parent,
+				  a->br);
+	if (!err)
+		goto out; /* success */
+
+	err = au_busy_or_stale();
+	au_ren_unlock(a);
+
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void au_ren_refresh_dir(struct au_ren_args *a)
+{
+	struct inode *dir;
+
+	dir = a->dst_dir;
+	dir->i_version++;
+	if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) {
+		/* is this updating defined in POSIX? */
+		au_cpup_attr_timesizes(a->src_inode);
+		au_cpup_attr_nlink(dir, /*force*/1);
+	}
+	au_dir_ts(dir, a->btgt);
+
+	if (a->exchange) {
+		dir = a->src_dir;
+		dir->i_version++;
+		if (au_ftest_ren(a->auren_flags, ISDIR_DST)) {
+			/* is this updating defined in POSIX? */
+			au_cpup_attr_timesizes(a->dst_inode);
+			au_cpup_attr_nlink(dir, /*force*/1);
+		}
+		au_dir_ts(dir, a->btgt);
+	}
+
+	if (au_ftest_ren(a->auren_flags, ISSAMEDIR))
+		return;
+
+	dir = a->src_dir;
+	dir->i_version++;
+	if (au_ftest_ren(a->auren_flags, ISDIR_SRC))
+		au_cpup_attr_nlink(dir, /*force*/1);
+	au_dir_ts(dir, a->btgt);
+}
+
+static void au_ren_refresh(struct au_ren_args *a)
+{
+	aufs_bindex_t bbot, bindex;
+	struct dentry *d, *h_d;
+	struct inode *i, *h_i;
+	struct super_block *sb;
+
+	d = a->dst_dentry;
+	d_drop(d);
+	if (a->h_dst)
+		/* already dget-ed by au_ren_or_cpup() */
+		au_set_h_dptr(d, a->btgt, a->h_dst);
+
+	i = a->dst_inode;
+	if (i) {
+		if (!a->exchange) {
+			if (!au_ftest_ren(a->auren_flags, ISDIR_DST))
+				vfsub_drop_nlink(i);
+			else {
+				vfsub_dead_dir(i);
+				au_cpup_attr_timesizes(i);
+			}
+			au_update_dbrange(d, /*do_put_zero*/1);
+		} else
+			au_cpup_attr_nlink(i, /*force*/1);
+	} else {
+		bbot = a->btgt;
+		for (bindex = au_dbtop(d); bindex < bbot; bindex++)
+			au_set_h_dptr(d, bindex, NULL);
+		bbot = au_dbbot(d);
+		for (bindex = a->btgt + 1; bindex <= bbot; bindex++)
+			au_set_h_dptr(d, bindex, NULL);
+		au_update_dbrange(d, /*do_put_zero*/0);
+	}
+
+	d = a->src_dentry;
+	if (!a->exchange) {
+		au_set_dbwh(d, -1);
+		bbot = au_dbbot(d);
+		for (bindex = a->btgt + 1; bindex <= bbot; bindex++) {
+			h_d = au_h_dptr(d, bindex);
+			if (h_d)
+				au_set_h_dptr(d, bindex, NULL);
+		}
+		au_set_dbbot(d, a->btgt);
+
+		sb = d->d_sb;
+		i = a->src_inode;
+		if (au_opt_test(au_mntflags(sb), PLINK) && au_plink_test(i))
+			return; /* success */
+
+		bbot = au_ibbot(i);
+		for (bindex = a->btgt + 1; bindex <= bbot; bindex++) {
+			h_i = au_h_iptr(i, bindex);
+			if (h_i) {
+				au_xino_write(sb, bindex, h_i->i_ino, /*ino*/0);
+				/* ignore this error */
+				au_set_h_iptr(i, bindex, NULL, 0);
+			}
+		}
+		au_set_ibbot(i, a->btgt);
+	}
+		d_drop(a->src_dentry);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* mainly for link(2) and rename(2) */
+int au_wbr(struct dentry *dentry, aufs_bindex_t btgt)
+{
+	aufs_bindex_t bdiropq, bwh;
+	struct dentry *parent;
+	struct au_branch *br;
+
+	parent = dentry->d_parent;
+	IMustLock(d_inode(parent)); /* dir is locked */
+
+	bdiropq = au_dbdiropq(parent);
+	bwh = au_dbwh(dentry);
+	br = au_sbr(dentry->d_sb, btgt);
+	if (au_br_rdonly(br)
+	    || (0 <= bdiropq && bdiropq < btgt)
+	    || (0 <= bwh && bwh < btgt))
+		btgt = -1;
+
+	AuDbg("btgt %d\n", btgt);
+	return btgt;
+}
+
+/* sets src_btop, dst_btop and btgt */
+static int au_ren_wbr(struct au_ren_args *a)
+{
+	int err;
+	struct au_wr_dir_args wr_dir_args = {
+		/* .force_btgt	= -1, */
+		.flags		= AuWrDir_ADD_ENTRY
+	};
+
+	a->src_btop = au_dbtop(a->src_dentry);
+	a->dst_btop = au_dbtop(a->dst_dentry);
+	if (au_ftest_ren(a->auren_flags, ISDIR_SRC)
+	    || au_ftest_ren(a->auren_flags, ISDIR_DST))
+		au_fset_wrdir(wr_dir_args.flags, ISDIR);
+	wr_dir_args.force_btgt = a->src_btop;
+	if (a->dst_inode && a->dst_btop < a->src_btop)
+		wr_dir_args.force_btgt = a->dst_btop;
+	wr_dir_args.force_btgt = au_wbr(a->dst_dentry, wr_dir_args.force_btgt);
+	err = au_wr_dir(a->dst_dentry, a->src_dentry, &wr_dir_args);
+	a->btgt = err;
+	if (a->exchange)
+		au_update_dbtop(a->dst_dentry);
+
+	return err;
+}
+
+static void au_ren_dt(struct au_ren_args *a)
+{
+	a->h_path.dentry = a->src_h_parent;
+	au_dtime_store(a->src_dt + AuPARENT, a->src_parent, &a->h_path);
+	if (!au_ftest_ren(a->auren_flags, ISSAMEDIR)) {
+		a->h_path.dentry = a->dst_h_parent;
+		au_dtime_store(a->dst_dt + AuPARENT, a->dst_parent, &a->h_path);
+	}
+
+	au_fclr_ren(a->auren_flags, DT_DSTDIR);
+	if (!au_ftest_ren(a->auren_flags, ISDIR_SRC)
+	    && !a->exchange)
+		return;
+
+	a->h_path.dentry = a->src_h_dentry;
+	au_dtime_store(a->src_dt + AuCHILD, a->src_dentry, &a->h_path);
+	if (d_is_positive(a->dst_h_dentry)) {
+		au_fset_ren(a->auren_flags, DT_DSTDIR);
+		a->h_path.dentry = a->dst_h_dentry;
+		au_dtime_store(a->dst_dt + AuCHILD, a->dst_dentry, &a->h_path);
+	}
+}
+
+static void au_ren_rev_dt(int err, struct au_ren_args *a)
+{
+	struct dentry *h_d;
+	struct inode *h_inode;
+
+	au_dtime_revert(a->src_dt + AuPARENT);
+	if (!au_ftest_ren(a->auren_flags, ISSAMEDIR))
+		au_dtime_revert(a->dst_dt + AuPARENT);
+
+	if (au_ftest_ren(a->auren_flags, ISDIR_SRC) && err != -EIO) {
+		h_d = a->src_dt[AuCHILD].dt_h_path.dentry;
+		h_inode = d_inode(h_d);
+		inode_lock_nested(h_inode, AuLsc_I_CHILD);
+		au_dtime_revert(a->src_dt + AuCHILD);
+		inode_unlock(h_inode);
+
+		if (au_ftest_ren(a->auren_flags, DT_DSTDIR)) {
+			h_d = a->dst_dt[AuCHILD].dt_h_path.dentry;
+			h_inode = d_inode(h_d);
+			inode_lock_nested(h_inode, AuLsc_I_CHILD);
+			au_dtime_revert(a->dst_dt + AuCHILD);
+			inode_unlock(h_inode);
+		}
+	}
+}
+
+/* ---------------------------------------------------------------------- */
+
+int aufs_rename(struct inode *_src_dir, struct dentry *_src_dentry,
+		struct inode *_dst_dir, struct dentry *_dst_dentry,
+		unsigned int _flags)
+{
+	int err, lock_flags;
+	/* reduce stack space */
+	struct au_ren_args *a;
+	struct au_pin pin;
+
+	AuDbg("%pd, %pd, 0x%x\n", _src_dentry, _dst_dentry, _flags);
+	IMustLock(_src_dir);
+	IMustLock(_dst_dir);
+
+	err = -EINVAL;
+	if (unlikely(_flags & RENAME_WHITEOUT))
+		goto out;
+
+	err = -ENOMEM;
+	BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE);
+	a = kzalloc(sizeof(*a), GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+
+	a->flags = _flags;
+	a->exchange = _flags & RENAME_EXCHANGE;
+	a->src_dir = _src_dir;
+	a->src_dentry = _src_dentry;
+	a->src_inode = NULL;
+	if (d_really_is_positive(a->src_dentry))
+		a->src_inode = d_inode(a->src_dentry);
+	a->src_parent = a->src_dentry->d_parent; /* dir inode is locked */
+	a->dst_dir = _dst_dir;
+	a->dst_dentry = _dst_dentry;
+	a->dst_inode = NULL;
+	if (d_really_is_positive(a->dst_dentry))
+		a->dst_inode = d_inode(a->dst_dentry);
+	a->dst_parent = a->dst_dentry->d_parent; /* dir inode is locked */
+	if (a->dst_inode) {
+		/*
+		 * if EXCHANGE && src is non-dir && dst is dir,
+		 * dst is not locked.
+		 */
+		/* IMustLock(a->dst_inode); */
+		au_igrab(a->dst_inode);
+	}
+
+	err = -ENOTDIR;
+	lock_flags = AuLock_FLUSH | AuLock_NOPLM | AuLock_GEN;
+	if (d_is_dir(a->src_dentry)) {
+		au_fset_ren(a->auren_flags, ISDIR_SRC);
+		if (unlikely(!a->exchange
+			     && d_really_is_positive(a->dst_dentry)
+			     && !d_is_dir(a->dst_dentry)))
+			goto out_free;
+		lock_flags |= AuLock_DIRS;
+	}
+	if (a->dst_inode && d_is_dir(a->dst_dentry)) {
+		au_fset_ren(a->auren_flags, ISDIR_DST);
+		if (unlikely(!a->exchange
+			     && d_really_is_positive(a->src_dentry)
+			     && !d_is_dir(a->src_dentry)))
+			goto out_free;
+		lock_flags |= AuLock_DIRS;
+	}
+	err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry,
+					lock_flags);
+	if (unlikely(err))
+		goto out_free;
+
+	err = au_d_hashed_positive(a->src_dentry);
+	if (unlikely(err))
+		goto out_unlock;
+	err = -ENOENT;
+	if (a->dst_inode) {
+		/*
+		 * If it is a dir, VFS unhash it before this
+		 * function. It means we cannot rely upon d_unhashed().
+		 */
+		if (unlikely(!a->dst_inode->i_nlink))
+			goto out_unlock;
+		if (!au_ftest_ren(a->auren_flags, ISDIR_DST)) {
+			err = au_d_hashed_positive(a->dst_dentry);
+			if (unlikely(err && !a->exchange))
+				goto out_unlock;
+		} else if (unlikely(IS_DEADDIR(a->dst_inode)))
+			goto out_unlock;
+	} else if (unlikely(d_unhashed(a->dst_dentry)))
+		goto out_unlock;
+
+	/*
+	 * is it possible?
+	 * yes, it happened (in linux-3.3-rcN) but I don't know why.
+	 * there may exist a problem somewhere else.
+	 */
+	err = -EINVAL;
+	if (unlikely(d_inode(a->dst_parent) == d_inode(a->src_dentry)))
+		goto out_unlock;
+
+	au_fset_ren(a->auren_flags, ISSAMEDIR); /* temporary */
+	di_write_lock_parent(a->dst_parent);
+
+	/* which branch we process */
+	err = au_ren_wbr(a);
+	if (unlikely(err < 0))
+		goto out_parent;
+	a->br = au_sbr(a->dst_dentry->d_sb, a->btgt);
+	a->h_path.mnt = au_br_mnt(a->br);
+
+	/* are they available to be renamed */
+	err = au_ren_may_dir(a);
+	if (unlikely(err))
+		goto out_children;
+
+	/* prepare the writable parent dir on the same branch */
+	if (a->dst_btop == a->btgt) {
+		au_fset_ren(a->auren_flags, WHDST);
+	} else {
+		err = au_cpup_dirs(a->dst_dentry, a->btgt);
+		if (unlikely(err))
+			goto out_children;
+	}
+
+	err = 0;
+	if (!a->exchange) {
+		if (a->src_dir != a->dst_dir) {
+			/*
+			 * this temporary unlock is safe,
+			 * because both dir->i_mutex are locked.
+			 */
+			di_write_unlock(a->dst_parent);
+			di_write_lock_parent(a->src_parent);
+			err = au_wr_dir_need_wh(a->src_dentry,
+						au_ftest_ren(a->auren_flags,
+							     ISDIR_SRC),
+						&a->btgt);
+			di_write_unlock(a->src_parent);
+			di_write_lock2_parent(a->src_parent, a->dst_parent,
+					      /*isdir*/1);
+			au_fclr_ren(a->auren_flags, ISSAMEDIR);
+		} else
+			err = au_wr_dir_need_wh(a->src_dentry,
+						au_ftest_ren(a->auren_flags,
+							     ISDIR_SRC),
+						&a->btgt);
+	}
+	if (unlikely(err < 0))
+		goto out_children;
+	if (err)
+		au_fset_ren(a->auren_flags, WHSRC);
+
+	/* cpup src */
+	if (a->src_btop != a->btgt) {
+		err = au_pin(&pin, a->src_dentry, a->btgt,
+			     au_opt_udba(a->src_dentry->d_sb),
+			     AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+		if (!err) {
+			struct au_cp_generic cpg = {
+				.dentry	= a->src_dentry,
+				.bdst	= a->btgt,
+				.bsrc	= a->src_btop,
+				.len	= -1,
+				.pin	= &pin,
+				.flags	= AuCpup_DTIME | AuCpup_HOPEN
+			};
+			AuDebugOn(au_dbtop(a->src_dentry) != a->src_btop);
+			err = au_sio_cpup_simple(&cpg);
+			au_unpin(&pin);
+		}
+		if (unlikely(err))
+			goto out_children;
+		a->src_btop = a->btgt;
+		a->src_h_dentry = au_h_dptr(a->src_dentry, a->btgt);
+		if (!a->exchange)
+			au_fset_ren(a->auren_flags, WHSRC);
+	}
+
+	/* cpup dst */
+	if (a->exchange && a->dst_inode
+	    && a->dst_btop != a->btgt) {
+		err = au_pin(&pin, a->dst_dentry, a->btgt,
+			     au_opt_udba(a->dst_dentry->d_sb),
+			     AuPin_DI_LOCKED | AuPin_MNT_WRITE);
+		if (!err) {
+			struct au_cp_generic cpg = {
+				.dentry	= a->dst_dentry,
+				.bdst	= a->btgt,
+				.bsrc	= a->dst_btop,
+				.len	= -1,
+				.pin	= &pin,
+				.flags	= AuCpup_DTIME | AuCpup_HOPEN
+			};
+			err = au_sio_cpup_simple(&cpg);
+			au_unpin(&pin);
+		}
+		if (unlikely(err))
+			goto out_children;
+		a->dst_btop = a->btgt;
+		a->dst_h_dentry = au_h_dptr(a->dst_dentry, a->btgt);
+	}
+
+	/* lock them all */
+	err = au_ren_lock(a);
+	if (unlikely(err))
+		/* leave the copied-up one */
+		goto out_children;
+
+	if (!a->exchange) {
+		if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE))
+			err = au_may_ren(a);
+		else if (unlikely(a->dst_dentry->d_name.len > AUFS_MAX_NAMELEN))
+			err = -ENAMETOOLONG;
+		if (unlikely(err))
+			goto out_hdir;
+	}
+
+	/* store timestamps to be revertible */
+	au_ren_dt(a);
+
+	/* here we go */
+	err = do_rename(a);
+	if (unlikely(err))
+		goto out_dt;
+
+	/* update dir attributes */
+	au_ren_refresh_dir(a);
+
+	/* dput/iput all lower dentries */
+	au_ren_refresh(a);
+
+	goto out_hdir; /* success */
+
+out_dt:
+	au_ren_rev_dt(err, a);
+out_hdir:
+	au_ren_unlock(a);
+out_children:
+	au_nhash_wh_free(&a->whlist);
+	if (err && a->dst_inode && a->dst_btop != a->btgt) {
+		AuDbg("btop %d, btgt %d\n", a->dst_btop, a->btgt);
+		au_set_h_dptr(a->dst_dentry, a->btgt, NULL);
+		au_set_dbtop(a->dst_dentry, a->dst_btop);
+	}
+out_parent:
+	if (!err) {
+		if (!a->exchange)
+			d_move(a->src_dentry, a->dst_dentry);
+		else
+			d_exchange(a->src_dentry, a->dst_dentry);
+	} else {
+		au_update_dbtop(a->dst_dentry);
+		if (!a->dst_inode)
+			d_drop(a->dst_dentry);
+	}
+	if (au_ftest_ren(a->auren_flags, ISSAMEDIR))
+		di_write_unlock(a->dst_parent);
+	else
+		di_write_unlock2(a->src_parent, a->dst_parent);
+out_unlock:
+	aufs_read_and_write_unlock2(a->dst_dentry, a->src_dentry);
+out_free:
+	iput(a->dst_inode);
+	if (a->thargs)
+		au_whtmp_rmdir_free(a->thargs);
+	kfree(a);
+out:
+	AuTraceErr(err);
+	return err;
+}
diff --git a/fs/aufs/iinfo.c b/fs/aufs/iinfo.c
new file mode 100644
index 000000000000..4d3a55cb196a
--- /dev/null
+++ b/fs/aufs/iinfo.c
@@ -0,0 +1,285 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * inode private data
+ */
+
+#include "aufs.h"
+
+struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex)
+{
+	struct inode *h_inode;
+	struct au_hinode *hinode;
+
+	IiMustAnyLock(inode);
+
+	hinode = au_hinode(au_ii(inode), bindex);
+	h_inode = hinode->hi_inode;
+	AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0);
+	return h_inode;
+}
+
+/* todo: hard/soft set? */
+void au_hiput(struct au_hinode *hinode)
+{
+	au_hn_free(hinode);
+	dput(hinode->hi_whdentry);
+	iput(hinode->hi_inode);
+}
+
+unsigned int au_hi_flags(struct inode *inode, int isdir)
+{
+	unsigned int flags;
+	const unsigned int mnt_flags = au_mntflags(inode->i_sb);
+
+	flags = 0;
+	if (au_opt_test(mnt_flags, XINO))
+		au_fset_hi(flags, XINO);
+	if (isdir && au_opt_test(mnt_flags, UDBA_HNOTIFY))
+		au_fset_hi(flags, HNOTIFY);
+	return flags;
+}
+
+void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex,
+		   struct inode *h_inode, unsigned int flags)
+{
+	struct au_hinode *hinode;
+	struct inode *hi;
+	struct au_iinfo *iinfo = au_ii(inode);
+
+	IiMustWriteLock(inode);
+
+	hinode = au_hinode(iinfo, bindex);
+	hi = hinode->hi_inode;
+	AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0);
+
+	if (hi)
+		au_hiput(hinode);
+	hinode->hi_inode = h_inode;
+	if (h_inode) {
+		int err;
+		struct super_block *sb = inode->i_sb;
+		struct au_branch *br;
+
+		AuDebugOn(inode->i_mode
+			  && (h_inode->i_mode & S_IFMT)
+			  != (inode->i_mode & S_IFMT));
+		if (bindex == iinfo->ii_btop)
+			au_cpup_igen(inode, h_inode);
+		br = au_sbr(sb, bindex);
+		hinode->hi_id = br->br_id;
+		if (au_ftest_hi(flags, XINO)) {
+			err = au_xino_write(sb, bindex, h_inode->i_ino,
+					    inode->i_ino);
+			if (unlikely(err))
+				AuIOErr1("failed au_xino_write() %d\n", err);
+		}
+
+		if (au_ftest_hi(flags, HNOTIFY)
+		    && au_br_hnotifyable(br->br_perm)) {
+			err = au_hn_alloc(hinode, inode);
+			if (unlikely(err))
+				AuIOErr1("au_hn_alloc() %d\n", err);
+		}
+	}
+}
+
+void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex,
+		  struct dentry *h_wh)
+{
+	struct au_hinode *hinode;
+
+	IiMustWriteLock(inode);
+
+	hinode = au_hinode(au_ii(inode), bindex);
+	AuDebugOn(hinode->hi_whdentry);
+	hinode->hi_whdentry = h_wh;
+}
+
+void au_update_iigen(struct inode *inode, int half)
+{
+	struct au_iinfo *iinfo;
+	struct au_iigen *iigen;
+	unsigned int sigen;
+
+	sigen = au_sigen(inode->i_sb);
+	iinfo = au_ii(inode);
+	iigen = &iinfo->ii_generation;
+	spin_lock(&iigen->ig_spin);
+	iigen->ig_generation = sigen;
+	if (half)
+		au_ig_fset(iigen->ig_flags, HALF_REFRESHED);
+	else
+		au_ig_fclr(iigen->ig_flags, HALF_REFRESHED);
+	spin_unlock(&iigen->ig_spin);
+}
+
+/* it may be called at remount time, too */
+void au_update_ibrange(struct inode *inode, int do_put_zero)
+{
+	struct au_iinfo *iinfo;
+	aufs_bindex_t bindex, bbot;
+
+	AuDebugOn(au_is_bad_inode(inode));
+	IiMustWriteLock(inode);
+
+	iinfo = au_ii(inode);
+	if (do_put_zero && iinfo->ii_btop >= 0) {
+		for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot;
+		     bindex++) {
+			struct inode *h_i;
+
+			h_i = au_hinode(iinfo, bindex)->hi_inode;
+			if (h_i
+			    && !h_i->i_nlink
+			    && !(h_i->i_state & I_LINKABLE))
+				au_set_h_iptr(inode, bindex, NULL, 0);
+		}
+	}
+
+	iinfo->ii_btop = -1;
+	iinfo->ii_bbot = -1;
+	bbot = au_sbbot(inode->i_sb);
+	for (bindex = 0; bindex <= bbot; bindex++)
+		if (au_hinode(iinfo, bindex)->hi_inode) {
+			iinfo->ii_btop = bindex;
+			break;
+		}
+	if (iinfo->ii_btop >= 0)
+		for (bindex = bbot; bindex >= iinfo->ii_btop; bindex--)
+			if (au_hinode(iinfo, bindex)->hi_inode) {
+				iinfo->ii_bbot = bindex;
+				break;
+			}
+	AuDebugOn(iinfo->ii_btop > iinfo->ii_bbot);
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_icntnr_init_once(void *_c)
+{
+	struct au_icntnr *c = _c;
+	struct au_iinfo *iinfo = &c->iinfo;
+
+	spin_lock_init(&iinfo->ii_generation.ig_spin);
+	au_rw_init(&iinfo->ii_rwsem);
+	inode_init_once(&c->vfs_inode);
+}
+
+void au_hinode_init(struct au_hinode *hinode)
+{
+	hinode->hi_inode = NULL;
+	hinode->hi_id = -1;
+	au_hn_init(hinode);
+	hinode->hi_whdentry = NULL;
+}
+
+int au_iinfo_init(struct inode *inode)
+{
+	struct au_iinfo *iinfo;
+	struct super_block *sb;
+	struct au_hinode *hi;
+	int nbr, i;
+
+	sb = inode->i_sb;
+	iinfo = &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo);
+	nbr = au_sbbot(sb) + 1;
+	if (unlikely(nbr <= 0))
+		nbr = 1;
+	hi = kmalloc_array(nbr, sizeof(*iinfo->ii_hinode), GFP_NOFS);
+	if (hi) {
+		au_ninodes_inc(sb);
+
+		iinfo->ii_hinode = hi;
+		for (i = 0; i < nbr; i++, hi++)
+			au_hinode_init(hi);
+
+		iinfo->ii_generation.ig_generation = au_sigen(sb);
+		iinfo->ii_btop = -1;
+		iinfo->ii_bbot = -1;
+		iinfo->ii_vdir = NULL;
+		return 0;
+	}
+	return -ENOMEM;
+}
+
+int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink)
+{
+	int err, i;
+	struct au_hinode *hip;
+
+	AuRwMustWriteLock(&iinfo->ii_rwsem);
+
+	err = -ENOMEM;
+	hip = au_krealloc(iinfo->ii_hinode, sizeof(*hip) * nbr, GFP_NOFS,
+			  may_shrink);
+	if (hip) {
+		iinfo->ii_hinode = hip;
+		i = iinfo->ii_bbot + 1;
+		hip += i;
+		for (; i < nbr; i++, hip++)
+			au_hinode_init(hip);
+		err = 0;
+	}
+
+	return err;
+}
+
+void au_iinfo_fin(struct inode *inode)
+{
+	struct au_iinfo *iinfo;
+	struct au_hinode *hi;
+	struct super_block *sb;
+	aufs_bindex_t bindex, bbot;
+	const unsigned char unlinked = !inode->i_nlink;
+
+	AuDebugOn(au_is_bad_inode(inode));
+
+	sb = inode->i_sb;
+	au_ninodes_dec(sb);
+	if (si_pid_test(sb))
+		au_xino_delete_inode(inode, unlinked);
+	else {
+		/*
+		 * it is safe to hide the dependency between sbinfo and
+		 * sb->s_umount.
+		 */
+		lockdep_off();
+		si_noflush_read_lock(sb);
+		au_xino_delete_inode(inode, unlinked);
+		si_read_unlock(sb);
+		lockdep_on();
+	}
+
+	iinfo = au_ii(inode);
+	if (iinfo->ii_vdir)
+		au_vdir_free(iinfo->ii_vdir);
+
+	bindex = iinfo->ii_btop;
+	if (bindex >= 0) {
+		hi = au_hinode(iinfo, bindex);
+		bbot = iinfo->ii_bbot;
+		while (bindex++ <= bbot) {
+			if (hi->hi_inode)
+				au_hiput(hi);
+			hi++;
+		}
+	}
+	kfree(iinfo->ii_hinode);
+	AuRwDestroy(&iinfo->ii_rwsem);
+}
diff --git a/fs/aufs/inode.c b/fs/aufs/inode.c
new file mode 100644
index 000000000000..d361e25280dc
--- /dev/null
+++ b/fs/aufs/inode.c
@@ -0,0 +1,527 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * inode functions
+ */
+
+#include "aufs.h"
+
+struct inode *au_igrab(struct inode *inode)
+{
+	if (inode) {
+		AuDebugOn(!atomic_read(&inode->i_count));
+		ihold(inode);
+	}
+	return inode;
+}
+
+static void au_refresh_hinode_attr(struct inode *inode, int do_version)
+{
+	au_cpup_attr_all(inode, /*force*/0);
+	au_update_iigen(inode, /*half*/1);
+	if (do_version)
+		inode->i_version++;
+}
+
+static int au_ii_refresh(struct inode *inode, int *update)
+{
+	int err, e, nbr;
+	umode_t type;
+	aufs_bindex_t bindex, new_bindex;
+	struct super_block *sb;
+	struct au_iinfo *iinfo;
+	struct au_hinode *p, *q, tmp;
+
+	AuDebugOn(au_is_bad_inode(inode));
+	IiMustWriteLock(inode);
+
+	*update = 0;
+	sb = inode->i_sb;
+	nbr = au_sbbot(sb) + 1;
+	type = inode->i_mode & S_IFMT;
+	iinfo = au_ii(inode);
+	err = au_hinode_realloc(iinfo, nbr, /*may_shrink*/0);
+	if (unlikely(err))
+		goto out;
+
+	AuDebugOn(iinfo->ii_btop < 0);
+	p = au_hinode(iinfo, iinfo->ii_btop);
+	for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot;
+	     bindex++, p++) {
+		if (!p->hi_inode)
+			continue;
+
+		AuDebugOn(type != (p->hi_inode->i_mode & S_IFMT));
+		new_bindex = au_br_index(sb, p->hi_id);
+		if (new_bindex == bindex)
+			continue;
+
+		if (new_bindex < 0) {
+			*update = 1;
+			au_hiput(p);
+			p->hi_inode = NULL;
+			continue;
+		}
+
+		if (new_bindex < iinfo->ii_btop)
+			iinfo->ii_btop = new_bindex;
+		if (iinfo->ii_bbot < new_bindex)
+			iinfo->ii_bbot = new_bindex;
+		/* swap two lower inode, and loop again */
+		q = au_hinode(iinfo, new_bindex);
+		tmp = *q;
+		*q = *p;
+		*p = tmp;
+		if (tmp.hi_inode) {
+			bindex--;
+			p--;
+		}
+	}
+	au_update_ibrange(inode, /*do_put_zero*/0);
+	au_hinode_realloc(iinfo, nbr, /*may_shrink*/1); /* harmless if err */
+	e = au_dy_irefresh(inode);
+	if (unlikely(e && !err))
+		err = e;
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+void au_refresh_iop(struct inode *inode, int force_getattr)
+{
+	int type;
+	struct au_sbinfo *sbi = au_sbi(inode->i_sb);
+	const struct inode_operations *iop
+		= force_getattr ? aufs_iop : sbi->si_iop_array;
+
+	if (inode->i_op == iop)
+		return;
+
+	switch (inode->i_mode & S_IFMT) {
+	case S_IFDIR:
+		type = AuIop_DIR;
+		break;
+	case S_IFLNK:
+		type = AuIop_SYMLINK;
+		break;
+	default:
+		type = AuIop_OTHER;
+		break;
+	}
+
+	inode->i_op = iop + type;
+	/* unnecessary smp_wmb() */
+}
+
+int au_refresh_hinode_self(struct inode *inode)
+{
+	int err, update;
+
+	err = au_ii_refresh(inode, &update);
+	if (!err)
+		au_refresh_hinode_attr(inode, update && S_ISDIR(inode->i_mode));
+
+	AuTraceErr(err);
+	return err;
+}
+
+int au_refresh_hinode(struct inode *inode, struct dentry *dentry)
+{
+	int err, e, update;
+	unsigned int flags;
+	umode_t mode;
+	aufs_bindex_t bindex, bbot;
+	unsigned char isdir;
+	struct au_hinode *p;
+	struct au_iinfo *iinfo;
+
+	err = au_ii_refresh(inode, &update);
+	if (unlikely(err))
+		goto out;
+
+	update = 0;
+	iinfo = au_ii(inode);
+	p = au_hinode(iinfo, iinfo->ii_btop);
+	mode = (inode->i_mode & S_IFMT);
+	isdir = S_ISDIR(mode);
+	flags = au_hi_flags(inode, isdir);
+	bbot = au_dbbot(dentry);
+	for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) {
+		struct inode *h_i, *h_inode;
+		struct dentry *h_d;
+
+		h_d = au_h_dptr(dentry, bindex);
+		if (!h_d || d_is_negative(h_d))
+			continue;
+
+		h_inode = d_inode(h_d);
+		AuDebugOn(mode != (h_inode->i_mode & S_IFMT));
+		if (iinfo->ii_btop <= bindex && bindex <= iinfo->ii_bbot) {
+			h_i = au_h_iptr(inode, bindex);
+			if (h_i) {
+				if (h_i == h_inode)
+					continue;
+				err = -EIO;
+				break;
+			}
+		}
+		if (bindex < iinfo->ii_btop)
+			iinfo->ii_btop = bindex;
+		if (iinfo->ii_bbot < bindex)
+			iinfo->ii_bbot = bindex;
+		au_set_h_iptr(inode, bindex, au_igrab(h_inode), flags);
+		update = 1;
+	}
+	au_update_ibrange(inode, /*do_put_zero*/0);
+	e = au_dy_irefresh(inode);
+	if (unlikely(e && !err))
+		err = e;
+	if (!err)
+		au_refresh_hinode_attr(inode, update && isdir);
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+static int set_inode(struct inode *inode, struct dentry *dentry)
+{
+	int err;
+	unsigned int flags;
+	umode_t mode;
+	aufs_bindex_t bindex, btop, btail;
+	unsigned char isdir;
+	struct dentry *h_dentry;
+	struct inode *h_inode;
+	struct au_iinfo *iinfo;
+	struct inode_operations *iop;
+
+	IiMustWriteLock(inode);
+
+	err = 0;
+	isdir = 0;
+	iop = au_sbi(inode->i_sb)->si_iop_array;
+	btop = au_dbtop(dentry);
+	h_dentry = au_h_dptr(dentry, btop);
+	h_inode = d_inode(h_dentry);
+	mode = h_inode->i_mode;
+	switch (mode & S_IFMT) {
+	case S_IFREG:
+		btail = au_dbtail(dentry);
+		inode->i_op = iop + AuIop_OTHER;
+		inode->i_fop = &aufs_file_fop;
+		err = au_dy_iaop(inode, btop, h_inode);
+		if (unlikely(err))
+			goto out;
+		break;
+	case S_IFDIR:
+		isdir = 1;
+		btail = au_dbtaildir(dentry);
+		inode->i_op = iop + AuIop_DIR;
+		inode->i_fop = &aufs_dir_fop;
+		break;
+	case S_IFLNK:
+		btail = au_dbtail(dentry);
+		inode->i_op = iop + AuIop_SYMLINK;
+		break;
+	case S_IFBLK:
+	case S_IFCHR:
+	case S_IFIFO:
+	case S_IFSOCK:
+		btail = au_dbtail(dentry);
+		inode->i_op = iop + AuIop_OTHER;
+		init_special_inode(inode, mode, h_inode->i_rdev);
+		break;
+	default:
+		AuIOErr("Unknown file type 0%o\n", mode);
+		err = -EIO;
+		goto out;
+	}
+
+	/* do not set hnotify for whiteouted dirs (SHWH mode) */
+	flags = au_hi_flags(inode, isdir);
+	if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)
+	    && au_ftest_hi(flags, HNOTIFY)
+	    && dentry->d_name.len > AUFS_WH_PFX_LEN
+	    && !memcmp(dentry->d_name.name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))
+		au_fclr_hi(flags, HNOTIFY);
+	iinfo = au_ii(inode);
+	iinfo->ii_btop = btop;
+	iinfo->ii_bbot = btail;
+	for (bindex = btop; bindex <= btail; bindex++) {
+		h_dentry = au_h_dptr(dentry, bindex);
+		if (h_dentry)
+			au_set_h_iptr(inode, bindex,
+				      au_igrab(d_inode(h_dentry)), flags);
+	}
+	au_cpup_attr_all(inode, /*force*/1);
+	/*
+	 * to force calling aufs_get_acl() every time,
+	 * do not call cache_no_acl() for aufs inode.
+	 */
+
+out:
+	return err;
+}
+
+/*
+ * successful returns with iinfo write_locked
+ * minus: errno
+ * zero: success, matched
+ * plus: no error, but unmatched
+ */
+static int reval_inode(struct inode *inode, struct dentry *dentry)
+{
+	int err;
+	unsigned int gen, igflags;
+	aufs_bindex_t bindex, bbot;
+	struct inode *h_inode, *h_dinode;
+	struct dentry *h_dentry;
+
+	/*
+	 * before this function, if aufs got any iinfo lock, it must be only
+	 * one, the parent dir.
+	 * it can happen by UDBA and the obsoleted inode number.
+	 */
+	err = -EIO;
+	if (unlikely(inode->i_ino == parent_ino(dentry)))
+		goto out;
+
+	err = 1;
+	ii_write_lock_new_child(inode);
+	h_dentry = au_h_dptr(dentry, au_dbtop(dentry));
+	h_dinode = d_inode(h_dentry);
+	bbot = au_ibbot(inode);
+	for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) {
+		h_inode = au_h_iptr(inode, bindex);
+		if (!h_inode || h_inode != h_dinode)
+			continue;
+
+		err = 0;
+		gen = au_iigen(inode, &igflags);
+		if (gen == au_digen(dentry)
+		    && !au_ig_ftest(igflags, HALF_REFRESHED))
+			break;
+
+		/* fully refresh inode using dentry */
+		err = au_refresh_hinode(inode, dentry);
+		if (!err)
+			au_update_iigen(inode, /*half*/0);
+		break;
+	}
+
+	if (unlikely(err))
+		ii_write_unlock(inode);
+out:
+	return err;
+}
+
+int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+	   unsigned int d_type, ino_t *ino)
+{
+	int err, idx;
+	const int isnondir = d_type != DT_DIR;
+
+	/* prevent hardlinked inode number from race condition */
+	if (isnondir) {
+		err = au_xinondir_enter(sb, bindex, h_ino, &idx);
+		if (unlikely(err))
+			goto out;
+	}
+
+	err = au_xino_read(sb, bindex, h_ino, ino);
+	if (unlikely(err))
+		goto out_xinondir;
+
+	if (!*ino) {
+		err = -EIO;
+		*ino = au_xino_new_ino(sb);
+		if (unlikely(!*ino))
+			goto out_xinondir;
+		err = au_xino_write(sb, bindex, h_ino, *ino);
+		if (unlikely(err))
+			goto out_xinondir;
+	}
+
+out_xinondir:
+	if (isnondir && idx >= 0)
+		au_xinondir_leave(sb, bindex, h_ino, idx);
+out:
+	return err;
+}
+
+/* successful returns with iinfo write_locked */
+/* todo: return with unlocked? */
+struct inode *au_new_inode(struct dentry *dentry, int must_new)
+{
+	struct inode *inode, *h_inode;
+	struct dentry *h_dentry;
+	struct super_block *sb;
+	ino_t h_ino, ino;
+	int err, idx, hlinked;
+	aufs_bindex_t btop;
+
+	sb = dentry->d_sb;
+	btop = au_dbtop(dentry);
+	h_dentry = au_h_dptr(dentry, btop);
+	h_inode = d_inode(h_dentry);
+	h_ino = h_inode->i_ino;
+	hlinked = !d_is_dir(h_dentry) && h_inode->i_nlink > 1;
+
+new_ino:
+	/*
+	 * stop 'race'-ing between hardlinks under different
+	 * parents.
+	 */
+	if (hlinked) {
+		err = au_xinondir_enter(sb, btop, h_ino, &idx);
+		inode = ERR_PTR(err);
+		if (unlikely(err))
+			goto out;
+	}
+
+	err = au_xino_read(sb, btop, h_ino, &ino);
+	inode = ERR_PTR(err);
+	if (unlikely(err))
+		goto out_xinondir;
+
+	if (!ino) {
+		ino = au_xino_new_ino(sb);
+		if (unlikely(!ino)) {
+			inode = ERR_PTR(-EIO);
+			goto out_xinondir;
+		}
+	}
+
+	AuDbg("i%lu\n", (unsigned long)ino);
+	inode = au_iget_locked(sb, ino);
+	err = PTR_ERR(inode);
+	if (IS_ERR(inode))
+		goto out_xinondir;
+
+	AuDbg("%lx, new %d\n", inode->i_state, !!(inode->i_state & I_NEW));
+	if (inode->i_state & I_NEW) {
+		ii_write_lock_new_child(inode);
+		err = set_inode(inode, dentry);
+		if (!err) {
+			unlock_new_inode(inode);
+			goto out_xinondir; /* success */
+		}
+
+		/*
+		 * iget_failed() calls iput(), but we need to call
+		 * ii_write_unlock() after iget_failed(). so dirty hack for
+		 * i_count.
+		 */
+		atomic_inc(&inode->i_count);
+		iget_failed(inode);
+		ii_write_unlock(inode);
+		au_xino_write(sb, btop, h_ino, /*ino*/0);
+		/* ignore this error */
+		goto out_iput;
+	} else if (!must_new && !IS_DEADDIR(inode) && inode->i_nlink) {
+		/*
+		 * horrible race condition between lookup, readdir and copyup
+		 * (or something).
+		 */
+		if (hlinked && idx >= 0)
+			au_xinondir_leave(sb, btop, h_ino, idx);
+		err = reval_inode(inode, dentry);
+		if (unlikely(err < 0)) {
+			hlinked = 0;
+			goto out_iput;
+		}
+		if (!err)
+			goto out; /* success */
+		else if (hlinked && idx >= 0) {
+			err = au_xinondir_enter(sb, btop, h_ino, &idx);
+			if (unlikely(err)) {
+				iput(inode);
+				inode = ERR_PTR(err);
+				goto out;
+			}
+		}
+	}
+
+	if (unlikely(au_test_fs_unique_ino(h_inode)))
+		AuWarn1("Warning: Un-notified UDBA or repeatedly renamed dir,"
+			" b%d, %s, %pd, hi%lu, i%lu.\n",
+			btop, au_sbtype(h_dentry->d_sb), dentry,
+			(unsigned long)h_ino, (unsigned long)ino);
+	ino = 0;
+	err = au_xino_write(sb, btop, h_ino, /*ino*/0);
+	if (!err) {
+		iput(inode);
+		if (hlinked && idx >= 0)
+			au_xinondir_leave(sb, btop, h_ino, idx);
+		goto new_ino;
+	}
+
+out_iput:
+	iput(inode);
+	inode = ERR_PTR(err);
+out_xinondir:
+	if (hlinked && idx >= 0)
+		au_xinondir_leave(sb, btop, h_ino, idx);
+out:
+	return inode;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int au_test_ro(struct super_block *sb, aufs_bindex_t bindex,
+	       struct inode *inode)
+{
+	int err;
+	struct inode *hi;
+
+	err = au_br_rdonly(au_sbr(sb, bindex));
+
+	/* pseudo-link after flushed may happen out of bounds */
+	if (!err
+	    && inode
+	    && au_ibtop(inode) <= bindex
+	    && bindex <= au_ibbot(inode)) {
+		/*
+		 * permission check is unnecessary since vfsub routine
+		 * will be called later
+		 */
+		hi = au_h_iptr(inode, bindex);
+		if (hi)
+			err = IS_IMMUTABLE(hi) ? -EROFS : 0;
+	}
+
+	return err;
+}
+
+int au_test_h_perm(struct inode *h_inode, int mask)
+{
+	if (uid_eq(current_fsuid(), GLOBAL_ROOT_UID))
+		return 0;
+	return inode_permission(h_inode, mask);
+}
+
+int au_test_h_perm_sio(struct inode *h_inode, int mask)
+{
+	if (au_test_nfs(h_inode->i_sb)
+	    && (mask & MAY_WRITE)
+	    && S_ISDIR(h_inode->i_mode))
+		mask |= MAY_READ; /* force permission check */
+	return au_test_h_perm(h_inode, mask);
+}
diff --git a/fs/aufs/inode.h b/fs/aufs/inode.h
new file mode 100644
index 000000000000..318154be7245
--- /dev/null
+++ b/fs/aufs/inode.h
@@ -0,0 +1,694 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * inode operations
+ */
+
+#ifndef __AUFS_INODE_H__
+#define __AUFS_INODE_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fsnotify.h>
+#include "rwsem.h"
+#include "vfsub.h"
+
+struct vfsmount;
+
+struct au_hnotify {
+#ifdef CONFIG_AUFS_HNOTIFY
+#ifdef CONFIG_AUFS_HFSNOTIFY
+	/* never use fsnotify_add_vfsmount_mark() */
+	struct fsnotify_mark		hn_mark;
+#endif
+	struct inode		*hn_aufs_inode;	/* no get/put */
+#endif
+} ____cacheline_aligned_in_smp;
+
+struct au_hinode {
+	struct inode		*hi_inode;
+	aufs_bindex_t		hi_id;
+#ifdef CONFIG_AUFS_HNOTIFY
+	struct au_hnotify	*hi_notify;
+#endif
+
+	/* reference to the copied-up whiteout with get/put */
+	struct dentry		*hi_whdentry;
+};
+
+/* ig_flags */
+#define AuIG_HALF_REFRESHED		1
+#define au_ig_ftest(flags, name)	((flags) & AuIG_##name)
+#define au_ig_fset(flags, name) \
+	do { (flags) |= AuIG_##name; } while (0)
+#define au_ig_fclr(flags, name) \
+	do { (flags) &= ~AuIG_##name; } while (0)
+
+struct au_iigen {
+	spinlock_t	ig_spin;
+	__u32		ig_generation, ig_flags;
+};
+
+struct au_vdir;
+struct au_iinfo {
+	struct au_iigen		ii_generation;
+	struct super_block	*ii_hsb1;	/* no get/put */
+
+	struct au_rwsem		ii_rwsem;
+	aufs_bindex_t		ii_btop, ii_bbot;
+	__u32			ii_higen;
+	struct au_hinode	*ii_hinode;
+	struct au_vdir		*ii_vdir;
+};
+
+struct au_icntnr {
+	struct au_iinfo iinfo;
+	struct inode vfs_inode;
+	struct hlist_node plink;
+} ____cacheline_aligned_in_smp;
+
+/* au_pin flags */
+#define AuPin_DI_LOCKED		1
+#define AuPin_MNT_WRITE		(1 << 1)
+#define au_ftest_pin(flags, name)	((flags) & AuPin_##name)
+#define au_fset_pin(flags, name) \
+	do { (flags) |= AuPin_##name; } while (0)
+#define au_fclr_pin(flags, name) \
+	do { (flags) &= ~AuPin_##name; } while (0)
+
+struct au_pin {
+	/* input */
+	struct dentry *dentry;
+	unsigned int udba;
+	unsigned char lsc_di, lsc_hi, flags;
+	aufs_bindex_t bindex;
+
+	/* output */
+	struct dentry *parent;
+	struct au_hinode *hdir;
+	struct vfsmount *h_mnt;
+
+	/* temporary unlock/relock for copyup */
+	struct dentry *h_dentry, *h_parent;
+	struct au_branch *br;
+	struct task_struct *task;
+};
+
+void au_pin_hdir_unlock(struct au_pin *p);
+int au_pin_hdir_lock(struct au_pin *p);
+int au_pin_hdir_relock(struct au_pin *p);
+void au_pin_hdir_acquire_nest(struct au_pin *p);
+void au_pin_hdir_release(struct au_pin *p);
+
+/* ---------------------------------------------------------------------- */
+
+static inline struct au_iinfo *au_ii(struct inode *inode)
+{
+	BUG_ON(is_bad_inode(inode));
+	return &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* inode.c */
+struct inode *au_igrab(struct inode *inode);
+void au_refresh_iop(struct inode *inode, int force_getattr);
+int au_refresh_hinode_self(struct inode *inode);
+int au_refresh_hinode(struct inode *inode, struct dentry *dentry);
+int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+	   unsigned int d_type, ino_t *ino);
+struct inode *au_new_inode(struct dentry *dentry, int must_new);
+int au_test_ro(struct super_block *sb, aufs_bindex_t bindex,
+	       struct inode *inode);
+int au_test_h_perm(struct inode *h_inode, int mask);
+int au_test_h_perm_sio(struct inode *h_inode, int mask);
+
+static inline int au_wh_ino(struct super_block *sb, aufs_bindex_t bindex,
+			    ino_t h_ino, unsigned int d_type, ino_t *ino)
+{
+#ifdef CONFIG_AUFS_SHWH
+	return au_ino(sb, bindex, h_ino, d_type, ino);
+#else
+	return 0;
+#endif
+}
+
+/* i_op.c */
+enum {
+	AuIop_SYMLINK,
+	AuIop_DIR,
+	AuIop_OTHER,
+	AuIop_Last
+};
+extern struct inode_operations aufs_iop[AuIop_Last],
+	aufs_iop_nogetattr[AuIop_Last];
+
+/* au_wr_dir flags */
+#define AuWrDir_ADD_ENTRY	1
+#define AuWrDir_ISDIR		(1 << 1)
+#define AuWrDir_TMPFILE		(1 << 2)
+#define au_ftest_wrdir(flags, name)	((flags) & AuWrDir_##name)
+#define au_fset_wrdir(flags, name) \
+	do { (flags) |= AuWrDir_##name; } while (0)
+#define au_fclr_wrdir(flags, name) \
+	do { (flags) &= ~AuWrDir_##name; } while (0)
+
+struct au_wr_dir_args {
+	aufs_bindex_t force_btgt;
+	unsigned char flags;
+};
+int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry,
+	      struct au_wr_dir_args *args);
+
+struct dentry *au_pinned_h_parent(struct au_pin *pin);
+void au_pin_init(struct au_pin *pin, struct dentry *dentry,
+		 aufs_bindex_t bindex, int lsc_di, int lsc_hi,
+		 unsigned int udba, unsigned char flags);
+int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
+	   unsigned int udba, unsigned char flags) __must_check;
+int au_do_pin(struct au_pin *pin) __must_check;
+void au_unpin(struct au_pin *pin);
+int au_reval_for_attr(struct dentry *dentry, unsigned int sigen);
+
+#define AuIcpup_DID_CPUP	1
+#define au_ftest_icpup(flags, name)	((flags) & AuIcpup_##name)
+#define au_fset_icpup(flags, name) \
+	do { (flags) |= AuIcpup_##name; } while (0)
+#define au_fclr_icpup(flags, name) \
+	do { (flags) &= ~AuIcpup_##name; } while (0)
+
+struct au_icpup_args {
+	unsigned char flags;
+	unsigned char pin_flags;
+	aufs_bindex_t btgt;
+	unsigned int udba;
+	struct au_pin pin;
+	struct path h_path;
+	struct inode *h_inode;
+};
+
+int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
+		     struct au_icpup_args *a);
+
+int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path,
+		      int locked);
+
+/* i_op_add.c */
+int au_may_add(struct dentry *dentry, aufs_bindex_t bindex,
+	       struct dentry *h_parent, int isdir);
+int aufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
+	       dev_t dev);
+int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname);
+int aufs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+		bool want_excl);
+struct vfsub_aopen_args;
+int au_aopen_or_create(struct inode *dir, struct dentry *dentry,
+		       struct vfsub_aopen_args *args);
+int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode);
+int aufs_link(struct dentry *src_dentry, struct inode *dir,
+	      struct dentry *dentry);
+int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
+
+/* i_op_del.c */
+int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup);
+int au_may_del(struct dentry *dentry, aufs_bindex_t bindex,
+	       struct dentry *h_parent, int isdir);
+int aufs_unlink(struct inode *dir, struct dentry *dentry);
+int aufs_rmdir(struct inode *dir, struct dentry *dentry);
+
+/* i_op_ren.c */
+int au_wbr(struct dentry *dentry, aufs_bindex_t btgt);
+int aufs_rename(struct inode *src_dir, struct dentry *src_dentry,
+		struct inode *dir, struct dentry *dentry,
+		unsigned int flags);
+
+/* iinfo.c */
+struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex);
+void au_hiput(struct au_hinode *hinode);
+void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex,
+		  struct dentry *h_wh);
+unsigned int au_hi_flags(struct inode *inode, int isdir);
+
+/* hinode flags */
+#define AuHi_XINO	1
+#define AuHi_HNOTIFY	(1 << 1)
+#define au_ftest_hi(flags, name)	((flags) & AuHi_##name)
+#define au_fset_hi(flags, name) \
+	do { (flags) |= AuHi_##name; } while (0)
+#define au_fclr_hi(flags, name) \
+	do { (flags) &= ~AuHi_##name; } while (0)
+
+#ifndef CONFIG_AUFS_HNOTIFY
+#undef AuHi_HNOTIFY
+#define AuHi_HNOTIFY	0
+#endif
+
+void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex,
+		   struct inode *h_inode, unsigned int flags);
+
+void au_update_iigen(struct inode *inode, int half);
+void au_update_ibrange(struct inode *inode, int do_put_zero);
+
+void au_icntnr_init_once(void *_c);
+void au_hinode_init(struct au_hinode *hinode);
+int au_iinfo_init(struct inode *inode);
+void au_iinfo_fin(struct inode *inode);
+int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink);
+
+#ifdef CONFIG_PROC_FS
+/* plink.c */
+int au_plink_maint(struct super_block *sb, int flags);
+struct au_sbinfo;
+void au_plink_maint_leave(struct au_sbinfo *sbinfo);
+int au_plink_maint_enter(struct super_block *sb);
+#ifdef CONFIG_AUFS_DEBUG
+void au_plink_list(struct super_block *sb);
+#else
+AuStubVoid(au_plink_list, struct super_block *sb)
+#endif
+int au_plink_test(struct inode *inode);
+struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex);
+void au_plink_append(struct inode *inode, aufs_bindex_t bindex,
+		     struct dentry *h_dentry);
+void au_plink_put(struct super_block *sb, int verbose);
+void au_plink_clean(struct super_block *sb, int verbose);
+void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id);
+#else
+AuStubInt0(au_plink_maint, struct super_block *sb, int flags);
+AuStubVoid(au_plink_maint_leave, struct au_sbinfo *sbinfo);
+AuStubInt0(au_plink_maint_enter, struct super_block *sb);
+AuStubVoid(au_plink_list, struct super_block *sb);
+AuStubInt0(au_plink_test, struct inode *inode);
+AuStub(struct dentry *, au_plink_lkup, return NULL,
+       struct inode *inode, aufs_bindex_t bindex);
+AuStubVoid(au_plink_append, struct inode *inode, aufs_bindex_t bindex,
+	   struct dentry *h_dentry);
+AuStubVoid(au_plink_put, struct super_block *sb, int verbose);
+AuStubVoid(au_plink_clean, struct super_block *sb, int verbose);
+AuStubVoid(au_plink_half_refresh, struct super_block *sb, aufs_bindex_t br_id);
+#endif /* CONFIG_PROC_FS */
+
+#ifdef CONFIG_AUFS_XATTR
+/* xattr.c */
+int au_cpup_xattr(struct dentry *h_dst, struct dentry *h_src, int ignore_flags,
+		  unsigned int verbose);
+ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size);
+void au_xattr_init(struct super_block *sb);
+#else
+AuStubInt0(au_cpup_xattr, struct dentry *h_dst, struct dentry *h_src,
+	   int ignore_flags, unsigned int verbose);
+AuStubVoid(au_xattr_init, struct super_block *sb);
+#endif
+
+#ifdef CONFIG_FS_POSIX_ACL
+struct posix_acl *aufs_get_acl(struct inode *inode, int type);
+int aufs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+#endif
+
+#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL)
+enum {
+	AU_XATTR_SET,
+	AU_ACL_SET
+};
+
+struct au_sxattr {
+	int type;
+	union {
+		struct {
+			const char	*name;
+			const void	*value;
+			size_t		size;
+			int		flags;
+		} set;
+		struct {
+			struct posix_acl *acl;
+			int		type;
+		} acl_set;
+	} u;
+};
+ssize_t au_sxattr(struct dentry *dentry, struct inode *inode,
+		  struct au_sxattr *arg);
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+/* lock subclass for iinfo */
+enum {
+	AuLsc_II_CHILD,		/* child first */
+	AuLsc_II_CHILD2,	/* rename(2), link(2), and cpup at hnotify */
+	AuLsc_II_CHILD3,	/* copyup dirs */
+	AuLsc_II_PARENT,	/* see AuLsc_I_PARENT in vfsub.h */
+	AuLsc_II_PARENT2,
+	AuLsc_II_PARENT3,	/* copyup dirs */
+	AuLsc_II_NEW_CHILD
+};
+
+/*
+ * ii_read_lock_child, ii_write_lock_child,
+ * ii_read_lock_child2, ii_write_lock_child2,
+ * ii_read_lock_child3, ii_write_lock_child3,
+ * ii_read_lock_parent, ii_write_lock_parent,
+ * ii_read_lock_parent2, ii_write_lock_parent2,
+ * ii_read_lock_parent3, ii_write_lock_parent3,
+ * ii_read_lock_new_child, ii_write_lock_new_child,
+ */
+#define AuReadLockFunc(name, lsc) \
+static inline void ii_read_lock_##name(struct inode *i) \
+{ \
+	au_rw_read_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \
+}
+
+#define AuWriteLockFunc(name, lsc) \
+static inline void ii_write_lock_##name(struct inode *i) \
+{ \
+	au_rw_write_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \
+}
+
+#define AuRWLockFuncs(name, lsc) \
+	AuReadLockFunc(name, lsc) \
+	AuWriteLockFunc(name, lsc)
+
+AuRWLockFuncs(child, CHILD);
+AuRWLockFuncs(child2, CHILD2);
+AuRWLockFuncs(child3, CHILD3);
+AuRWLockFuncs(parent, PARENT);
+AuRWLockFuncs(parent2, PARENT2);
+AuRWLockFuncs(parent3, PARENT3);
+AuRWLockFuncs(new_child, NEW_CHILD);
+
+#undef AuReadLockFunc
+#undef AuWriteLockFunc
+#undef AuRWLockFuncs
+
+/*
+ * ii_read_unlock, ii_write_unlock, ii_downgrade_lock
+ */
+AuSimpleUnlockRwsemFuncs(ii, struct inode *i, &au_ii(i)->ii_rwsem);
+
+#define IiMustNoWaiters(i)	AuRwMustNoWaiters(&au_ii(i)->ii_rwsem)
+#define IiMustAnyLock(i)	AuRwMustAnyLock(&au_ii(i)->ii_rwsem)
+#define IiMustWriteLock(i)	AuRwMustWriteLock(&au_ii(i)->ii_rwsem)
+
+/* ---------------------------------------------------------------------- */
+
+static inline void au_icntnr_init(struct au_icntnr *c)
+{
+#ifdef CONFIG_AUFS_DEBUG
+	c->vfs_inode.i_mode = 0;
+#endif
+}
+
+static inline unsigned int au_iigen(struct inode *inode, unsigned int *igflags)
+{
+	unsigned int gen;
+	struct au_iinfo *iinfo;
+	struct au_iigen *iigen;
+
+	iinfo = au_ii(inode);
+	iigen = &iinfo->ii_generation;
+	spin_lock(&iigen->ig_spin);
+	if (igflags)
+		*igflags = iigen->ig_flags;
+	gen = iigen->ig_generation;
+	spin_unlock(&iigen->ig_spin);
+
+	return gen;
+}
+
+/* tiny test for inode number */
+/* tmpfs generation is too rough */
+static inline int au_test_higen(struct inode *inode, struct inode *h_inode)
+{
+	struct au_iinfo *iinfo;
+
+	iinfo = au_ii(inode);
+	AuRwMustAnyLock(&iinfo->ii_rwsem);
+	return !(iinfo->ii_hsb1 == h_inode->i_sb
+		 && iinfo->ii_higen == h_inode->i_generation);
+}
+
+static inline void au_iigen_dec(struct inode *inode)
+{
+	struct au_iinfo *iinfo;
+	struct au_iigen *iigen;
+
+	iinfo = au_ii(inode);
+	iigen = &iinfo->ii_generation;
+	spin_lock(&iigen->ig_spin);
+	iigen->ig_generation--;
+	spin_unlock(&iigen->ig_spin);
+}
+
+static inline int au_iigen_test(struct inode *inode, unsigned int sigen)
+{
+	int err;
+
+	err = 0;
+	if (unlikely(inode && au_iigen(inode, NULL) != sigen))
+		err = -EIO;
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static inline struct au_hinode *au_hinode(struct au_iinfo *iinfo,
+					  aufs_bindex_t bindex)
+{
+	return iinfo->ii_hinode + bindex;
+}
+
+static inline int au_is_bad_inode(struct inode *inode)
+{
+	return !!(is_bad_inode(inode) || !au_hinode(au_ii(inode), 0));
+}
+
+static inline aufs_bindex_t au_ii_br_id(struct inode *inode,
+					aufs_bindex_t bindex)
+{
+	IiMustAnyLock(inode);
+	return au_hinode(au_ii(inode), bindex)->hi_id;
+}
+
+static inline aufs_bindex_t au_ibtop(struct inode *inode)
+{
+	IiMustAnyLock(inode);
+	return au_ii(inode)->ii_btop;
+}
+
+static inline aufs_bindex_t au_ibbot(struct inode *inode)
+{
+	IiMustAnyLock(inode);
+	return au_ii(inode)->ii_bbot;
+}
+
+static inline struct au_vdir *au_ivdir(struct inode *inode)
+{
+	IiMustAnyLock(inode);
+	return au_ii(inode)->ii_vdir;
+}
+
+static inline struct dentry *au_hi_wh(struct inode *inode, aufs_bindex_t bindex)
+{
+	IiMustAnyLock(inode);
+	return au_hinode(au_ii(inode), bindex)->hi_whdentry;
+}
+
+static inline void au_set_ibtop(struct inode *inode, aufs_bindex_t bindex)
+{
+	IiMustWriteLock(inode);
+	au_ii(inode)->ii_btop = bindex;
+}
+
+static inline void au_set_ibbot(struct inode *inode, aufs_bindex_t bindex)
+{
+	IiMustWriteLock(inode);
+	au_ii(inode)->ii_bbot = bindex;
+}
+
+static inline void au_set_ivdir(struct inode *inode, struct au_vdir *vdir)
+{
+	IiMustWriteLock(inode);
+	au_ii(inode)->ii_vdir = vdir;
+}
+
+static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex)
+{
+	IiMustAnyLock(inode);
+	return au_hinode(au_ii(inode), bindex);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static inline struct dentry *au_pinned_parent(struct au_pin *pin)
+{
+	if (pin)
+		return pin->parent;
+	return NULL;
+}
+
+static inline struct inode *au_pinned_h_dir(struct au_pin *pin)
+{
+	if (pin && pin->hdir)
+		return pin->hdir->hi_inode;
+	return NULL;
+}
+
+static inline struct au_hinode *au_pinned_hdir(struct au_pin *pin)
+{
+	if (pin)
+		return pin->hdir;
+	return NULL;
+}
+
+static inline void au_pin_set_dentry(struct au_pin *pin, struct dentry *dentry)
+{
+	if (pin)
+		pin->dentry = dentry;
+}
+
+static inline void au_pin_set_parent_lflag(struct au_pin *pin,
+					   unsigned char lflag)
+{
+	if (pin) {
+		if (lflag)
+			au_fset_pin(pin->flags, DI_LOCKED);
+		else
+			au_fclr_pin(pin->flags, DI_LOCKED);
+	}
+}
+
+#if 0 /* reserved */
+static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent)
+{
+	if (pin) {
+		dput(pin->parent);
+		pin->parent = dget(parent);
+	}
+}
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+struct au_branch;
+#ifdef CONFIG_AUFS_HNOTIFY
+struct au_hnotify_op {
+	void (*ctl)(struct au_hinode *hinode, int do_set);
+	int (*alloc)(struct au_hinode *hinode);
+
+	/*
+	 * if it returns true, the the caller should free hinode->hi_notify,
+	 * otherwise ->free() frees it.
+	 */
+	int (*free)(struct au_hinode *hinode,
+		    struct au_hnotify *hn) __must_check;
+
+	void (*fin)(void);
+	int (*init)(void);
+
+	int (*reset_br)(unsigned int udba, struct au_branch *br, int perm);
+	void (*fin_br)(struct au_branch *br);
+	int (*init_br)(struct au_branch *br, int perm);
+};
+
+/* hnotify.c */
+int au_hn_alloc(struct au_hinode *hinode, struct inode *inode);
+void au_hn_free(struct au_hinode *hinode);
+void au_hn_ctl(struct au_hinode *hinode, int do_set);
+void au_hn_reset(struct inode *inode, unsigned int flags);
+int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask,
+	       struct qstr *h_child_qstr, struct inode *h_child_inode);
+int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm);
+int au_hnotify_init_br(struct au_branch *br, int perm);
+void au_hnotify_fin_br(struct au_branch *br);
+int __init au_hnotify_init(void);
+void au_hnotify_fin(void);
+
+/* hfsnotify.c */
+extern const struct au_hnotify_op au_hnotify_op;
+
+static inline
+void au_hn_init(struct au_hinode *hinode)
+{
+	hinode->hi_notify = NULL;
+}
+
+static inline struct au_hnotify *au_hn(struct au_hinode *hinode)
+{
+	return hinode->hi_notify;
+}
+
+#else
+AuStub(int, au_hn_alloc, return -EOPNOTSUPP,
+       struct au_hinode *hinode __maybe_unused,
+       struct inode *inode __maybe_unused)
+AuStub(struct au_hnotify *, au_hn, return NULL, struct au_hinode *hinode)
+AuStubVoid(au_hn_free, struct au_hinode *hinode __maybe_unused)
+AuStubVoid(au_hn_ctl, struct au_hinode *hinode __maybe_unused,
+	   int do_set __maybe_unused)
+AuStubVoid(au_hn_reset, struct inode *inode __maybe_unused,
+	   unsigned int flags __maybe_unused)
+AuStubInt0(au_hnotify_reset_br, unsigned int udba __maybe_unused,
+	   struct au_branch *br __maybe_unused,
+	   int perm __maybe_unused)
+AuStubInt0(au_hnotify_init_br, struct au_branch *br __maybe_unused,
+	   int perm __maybe_unused)
+AuStubVoid(au_hnotify_fin_br, struct au_branch *br __maybe_unused)
+AuStubInt0(__init au_hnotify_init, void)
+AuStubVoid(au_hnotify_fin, void)
+AuStubVoid(au_hn_init, struct au_hinode *hinode __maybe_unused)
+#endif /* CONFIG_AUFS_HNOTIFY */
+
+static inline void au_hn_suspend(struct au_hinode *hdir)
+{
+	au_hn_ctl(hdir, /*do_set*/0);
+}
+
+static inline void au_hn_resume(struct au_hinode *hdir)
+{
+	au_hn_ctl(hdir, /*do_set*/1);
+}
+
+static inline void au_hn_inode_lock(struct au_hinode *hdir)
+{
+	inode_lock(hdir->hi_inode);
+	au_hn_suspend(hdir);
+}
+
+static inline void au_hn_inode_lock_nested(struct au_hinode *hdir,
+					  unsigned int sc __maybe_unused)
+{
+	inode_lock_nested(hdir->hi_inode, sc);
+	au_hn_suspend(hdir);
+}
+
+static inline void au_hn_inode_lock_shared_nested(struct au_hinode *hdir,
+						  unsigned int sc)
+{
+	vfsub_inode_lock_shared_nested(hdir->hi_inode, sc);
+	au_hn_suspend(hdir);
+}
+
+static inline void au_hn_inode_unlock(struct au_hinode *hdir)
+{
+	au_hn_resume(hdir);
+	inode_unlock(hdir->hi_inode);
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_INODE_H__ */
diff --git a/fs/aufs/ioctl.c b/fs/aufs/ioctl.c
new file mode 100644
index 000000000000..5e501c5d4ead
--- /dev/null
+++ b/fs/aufs/ioctl.c
@@ -0,0 +1,219 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * ioctl
+ * plink-management and readdir in userspace.
+ * assist the pathconf(3) wrapper library.
+ * move-down
+ * File-based Hierarchical Storage Management.
+ */
+
+#include <linux/compat.h>
+#include <linux/file.h>
+#include "aufs.h"
+
+static int au_wbr_fd(struct path *path, struct aufs_wbr_fd __user *arg)
+{
+	int err, fd;
+	aufs_bindex_t wbi, bindex, bbot;
+	struct file *h_file;
+	struct super_block *sb;
+	struct dentry *root;
+	struct au_branch *br;
+	struct aufs_wbr_fd wbrfd = {
+		.oflags	= au_dir_roflags,
+		.brid	= -1
+	};
+	const int valid = O_RDONLY | O_NONBLOCK | O_LARGEFILE | O_DIRECTORY
+		| O_NOATIME | O_CLOEXEC;
+
+	AuDebugOn(wbrfd.oflags & ~valid);
+
+	if (arg) {
+		err = copy_from_user(&wbrfd, arg, sizeof(wbrfd));
+		if (unlikely(err)) {
+			err = -EFAULT;
+			goto out;
+		}
+
+		err = -EINVAL;
+		AuDbg("wbrfd{0%o, %d}\n", wbrfd.oflags, wbrfd.brid);
+		wbrfd.oflags |= au_dir_roflags;
+		AuDbg("0%o\n", wbrfd.oflags);
+		if (unlikely(wbrfd.oflags & ~valid))
+			goto out;
+	}
+
+	fd = get_unused_fd_flags(0);
+	err = fd;
+	if (unlikely(fd < 0))
+		goto out;
+
+	h_file = ERR_PTR(-EINVAL);
+	wbi = 0;
+	br = NULL;
+	sb = path->dentry->d_sb;
+	root = sb->s_root;
+	aufs_read_lock(root, AuLock_IR);
+	bbot = au_sbbot(sb);
+	if (wbrfd.brid >= 0) {
+		wbi = au_br_index(sb, wbrfd.brid);
+		if (unlikely(wbi < 0 || wbi > bbot))
+			goto out_unlock;
+	}
+
+	h_file = ERR_PTR(-ENOENT);
+	br = au_sbr(sb, wbi);
+	if (!au_br_writable(br->br_perm)) {
+		if (arg)
+			goto out_unlock;
+
+		bindex = wbi + 1;
+		wbi = -1;
+		for (; bindex <= bbot; bindex++) {
+			br = au_sbr(sb, bindex);
+			if (au_br_writable(br->br_perm)) {
+				wbi = bindex;
+				br = au_sbr(sb, wbi);
+				break;
+			}
+		}
+	}
+	AuDbg("wbi %d\n", wbi);
+	if (wbi >= 0)
+		h_file = au_h_open(root, wbi, wbrfd.oflags, NULL,
+				   /*force_wr*/0);
+
+out_unlock:
+	aufs_read_unlock(root, AuLock_IR);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out_fd;
+
+	au_br_put(br); /* cf. au_h_open() */
+	fd_install(fd, h_file);
+	err = fd;
+	goto out; /* success */
+
+out_fd:
+	put_unused_fd(fd);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	long err;
+	struct dentry *dentry;
+
+	switch (cmd) {
+	case AUFS_CTL_RDU:
+	case AUFS_CTL_RDU_INO:
+		err = au_rdu_ioctl(file, cmd, arg);
+		break;
+
+	case AUFS_CTL_WBR_FD:
+		err = au_wbr_fd(&file->f_path, (void __user *)arg);
+		break;
+
+	case AUFS_CTL_IBUSY:
+		err = au_ibusy_ioctl(file, arg);
+		break;
+
+	case AUFS_CTL_BRINFO:
+		err = au_brinfo_ioctl(file, arg);
+		break;
+
+	case AUFS_CTL_FHSM_FD:
+		dentry = file->f_path.dentry;
+		if (IS_ROOT(dentry))
+			err = au_fhsm_fd(dentry->d_sb, arg);
+		else
+			err = -ENOTTY;
+		break;
+
+	default:
+		/* do not call the lower */
+		AuDbg("0x%x\n", cmd);
+		err = -ENOTTY;
+	}
+
+	AuTraceErr(err);
+	return err;
+}
+
+long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	long err;
+
+	switch (cmd) {
+	case AUFS_CTL_MVDOWN:
+		err = au_mvdown(file->f_path.dentry, (void __user *)arg);
+		break;
+
+	case AUFS_CTL_WBR_FD:
+		err = au_wbr_fd(&file->f_path, (void __user *)arg);
+		break;
+
+	default:
+		/* do not call the lower */
+		AuDbg("0x%x\n", cmd);
+		err = -ENOTTY;
+	}
+
+	AuTraceErr(err);
+	return err;
+}
+
+#ifdef CONFIG_COMPAT
+long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd,
+			   unsigned long arg)
+{
+	long err;
+
+	switch (cmd) {
+	case AUFS_CTL_RDU:
+	case AUFS_CTL_RDU_INO:
+		err = au_rdu_compat_ioctl(file, cmd, arg);
+		break;
+
+	case AUFS_CTL_IBUSY:
+		err = au_ibusy_compat_ioctl(file, arg);
+		break;
+
+	case AUFS_CTL_BRINFO:
+		err = au_brinfo_compat_ioctl(file, arg);
+		break;
+
+	default:
+		err = aufs_ioctl_dir(file, cmd, arg);
+	}
+
+	AuTraceErr(err);
+	return err;
+}
+
+long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd,
+			      unsigned long arg)
+{
+	return aufs_ioctl_nondir(file, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
diff --git a/fs/aufs/loop.c b/fs/aufs/loop.c
new file mode 100644
index 000000000000..1acb82f0bf07
--- /dev/null
+++ b/fs/aufs/loop.c
@@ -0,0 +1,147 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * support for loopback block device as a branch
+ */
+
+#include "aufs.h"
+
+/* added into drivers/block/loop.c */
+static struct file *(*backing_file_func)(struct super_block *sb);
+
+/*
+ * test if two lower dentries have overlapping branches.
+ */
+int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding)
+{
+	struct super_block *h_sb;
+	struct file *backing_file;
+
+	if (unlikely(!backing_file_func)) {
+		/* don't load "loop" module here */
+		backing_file_func = symbol_get(loop_backing_file);
+		if (unlikely(!backing_file_func))
+			/* "loop" module is not loaded */
+			return 0;
+	}
+
+	h_sb = h_adding->d_sb;
+	backing_file = backing_file_func(h_sb);
+	if (!backing_file)
+		return 0;
+
+	h_adding = backing_file->f_path.dentry;
+	/*
+	 * h_adding can be local NFS.
+	 * in this case aufs cannot detect the loop.
+	 */
+	if (unlikely(h_adding->d_sb == sb))
+		return 1;
+	return !!au_test_subdir(h_adding, sb->s_root);
+}
+
+/* true if a kernel thread named 'loop[0-9].*' accesses a file */
+int au_test_loopback_kthread(void)
+{
+	int ret;
+	struct task_struct *tsk = current;
+	char c, comm[sizeof(tsk->comm)];
+
+	ret = 0;
+	if (tsk->flags & PF_KTHREAD) {
+		get_task_comm(comm, tsk);
+		c = comm[4];
+		ret = ('0' <= c && c <= '9'
+		       && !strncmp(comm, "loop", 4));
+	}
+
+	return ret;
+}
+
+/* ---------------------------------------------------------------------- */
+
+#define au_warn_loopback_step	16
+static int au_warn_loopback_nelem = au_warn_loopback_step;
+static unsigned long *au_warn_loopback_array;
+
+void au_warn_loopback(struct super_block *h_sb)
+{
+	int i, new_nelem;
+	unsigned long *a, magic;
+	static DEFINE_SPINLOCK(spin);
+
+	magic = h_sb->s_magic;
+	spin_lock(&spin);
+	a = au_warn_loopback_array;
+	for (i = 0; i < au_warn_loopback_nelem && *a; i++)
+		if (a[i] == magic) {
+			spin_unlock(&spin);
+			return;
+		}
+
+	/* h_sb is new to us, print it */
+	if (i < au_warn_loopback_nelem) {
+		a[i] = magic;
+		goto pr;
+	}
+
+	/* expand the array */
+	new_nelem = au_warn_loopback_nelem + au_warn_loopback_step;
+	a = au_kzrealloc(au_warn_loopback_array,
+			 au_warn_loopback_nelem * sizeof(unsigned long),
+			 new_nelem * sizeof(unsigned long), GFP_ATOMIC,
+			 /*may_shrink*/0);
+	if (a) {
+		au_warn_loopback_nelem = new_nelem;
+		au_warn_loopback_array = a;
+		a[i] = magic;
+		goto pr;
+	}
+
+	spin_unlock(&spin);
+	AuWarn1("realloc failed, ignored\n");
+	return;
+
+pr:
+	spin_unlock(&spin);
+	pr_warn("you may want to try another patch for loopback file "
+		"on %s(0x%lx) branch\n", au_sbtype(h_sb), magic);
+}
+
+int au_loopback_init(void)
+{
+	int err;
+	struct super_block *sb __maybe_unused;
+
+	BUILD_BUG_ON(sizeof(sb->s_magic) != sizeof(unsigned long));
+
+	err = 0;
+	au_warn_loopback_array = kcalloc(au_warn_loopback_step,
+					 sizeof(unsigned long), GFP_NOFS);
+	if (unlikely(!au_warn_loopback_array))
+		err = -ENOMEM;
+
+	return err;
+}
+
+void au_loopback_fin(void)
+{
+	if (backing_file_func)
+		symbol_put(loop_backing_file);
+	kfree(au_warn_loopback_array);
+}
diff --git a/fs/aufs/loop.h b/fs/aufs/loop.h
new file mode 100644
index 000000000000..9b02d32905f4
--- /dev/null
+++ b/fs/aufs/loop.h
@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * support for loopback mount as a branch
+ */
+
+#ifndef __AUFS_LOOP_H__
+#define __AUFS_LOOP_H__
+
+#ifdef __KERNEL__
+
+struct dentry;
+struct super_block;
+
+#ifdef CONFIG_AUFS_BDEV_LOOP
+/* drivers/block/loop.c */
+struct file *loop_backing_file(struct super_block *sb);
+
+/* loop.c */
+int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding);
+int au_test_loopback_kthread(void);
+void au_warn_loopback(struct super_block *h_sb);
+
+int au_loopback_init(void);
+void au_loopback_fin(void);
+#else
+AuStubInt0(au_test_loopback_overlap, struct super_block *sb,
+	   struct dentry *h_adding)
+AuStubInt0(au_test_loopback_kthread, void)
+AuStubVoid(au_warn_loopback, struct super_block *h_sb)
+
+AuStubInt0(au_loopback_init, void)
+AuStubVoid(au_loopback_fin, void)
+#endif /* BLK_DEV_LOOP */
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_LOOP_H__ */
diff --git a/fs/aufs/magic.mk b/fs/aufs/magic.mk
new file mode 100644
index 000000000000..4f83bdf1dd12
--- /dev/null
+++ b/fs/aufs/magic.mk
@@ -0,0 +1,30 @@
+
+# defined in ${srctree}/fs/fuse/inode.c
+# tristate
+ifdef CONFIG_FUSE_FS
+ccflags-y += -DFUSE_SUPER_MAGIC=0x65735546
+endif
+
+# defined in ${srctree}/fs/xfs/xfs_sb.h
+# tristate
+ifdef CONFIG_XFS_FS
+ccflags-y += -DXFS_SB_MAGIC=0x58465342
+endif
+
+# defined in ${srctree}/fs/configfs/mount.c
+# tristate
+ifdef CONFIG_CONFIGFS_FS
+ccflags-y += -DCONFIGFS_MAGIC=0x62656570
+endif
+
+# defined in ${srctree}/fs/ubifs/ubifs.h
+# tristate
+ifdef CONFIG_UBIFS_FS
+ccflags-y += -DUBIFS_SUPER_MAGIC=0x24051905
+endif
+
+# defined in ${srctree}/fs/hfsplus/hfsplus_raw.h
+# tristate
+ifdef CONFIG_HFSPLUS_FS
+ccflags-y += -DHFSPLUS_SUPER_MAGIC=0x482b
+endif
diff --git a/fs/aufs/module.c b/fs/aufs/module.c
new file mode 100644
index 000000000000..3ca7c705b2dd
--- /dev/null
+++ b/fs/aufs/module.c
@@ -0,0 +1,266 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * module global variables and operations
+ */
+
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include "aufs.h"
+
+/* shrinkable realloc */
+void *au_krealloc(void *p, unsigned int new_sz, gfp_t gfp, int may_shrink)
+{
+	size_t sz;
+	int diff;
+
+	sz = 0;
+	diff = -1;
+	if (p) {
+#if 0 /* unused */
+		if (!new_sz) {
+			kfree(p);
+			p = NULL;
+			goto out;
+		}
+#else
+		AuDebugOn(!new_sz);
+#endif
+		sz = ksize(p);
+		diff = au_kmidx_sub(sz, new_sz);
+	}
+	if (sz && !diff)
+		goto out;
+
+	if (sz < new_sz)
+		/* expand or SLOB */
+		p = krealloc(p, new_sz, gfp);
+	else if (new_sz < sz && may_shrink) {
+		/* shrink */
+		void *q;
+
+		q = kmalloc(new_sz, gfp);
+		if (q) {
+			if (p) {
+				memcpy(q, p, new_sz);
+				kfree(p);
+			}
+			p = q;
+		} else
+			p = NULL;
+	}
+
+out:
+	return p;
+}
+
+void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp,
+		   int may_shrink)
+{
+	p = au_krealloc(p, new_sz, gfp, may_shrink);
+	if (p && new_sz > nused)
+		memset(p + nused, 0, new_sz - nused);
+	return p;
+}
+
+/* ---------------------------------------------------------------------- */
+/*
+ * aufs caches
+ */
+struct kmem_cache *au_cache[AuCache_Last];
+
+static void au_cache_fin(void)
+{
+	int i;
+
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
+
+	/* excluding AuCache_HNOTIFY */
+	BUILD_BUG_ON(AuCache_HNOTIFY + 1 != AuCache_Last);
+	for (i = 0; i < AuCache_HNOTIFY; i++) {
+		kmem_cache_destroy(au_cache[i]);
+		au_cache[i] = NULL;
+	}
+}
+
+static int __init au_cache_init(void)
+{
+	au_cache[AuCache_DINFO] = AuCacheCtor(au_dinfo, au_di_init_once);
+	if (au_cache[AuCache_DINFO])
+		/* SLAB_DESTROY_BY_RCU */
+		au_cache[AuCache_ICNTNR] = AuCacheCtor(au_icntnr,
+						       au_icntnr_init_once);
+	if (au_cache[AuCache_ICNTNR])
+		au_cache[AuCache_FINFO] = AuCacheCtor(au_finfo,
+						      au_fi_init_once);
+	if (au_cache[AuCache_FINFO])
+		au_cache[AuCache_VDIR] = AuCache(au_vdir);
+	if (au_cache[AuCache_VDIR])
+		au_cache[AuCache_DEHSTR] = AuCache(au_vdir_dehstr);
+	if (au_cache[AuCache_DEHSTR])
+		return 0;
+
+	au_cache_fin();
+	return -ENOMEM;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int au_dir_roflags;
+
+#ifdef CONFIG_AUFS_SBILIST
+/*
+ * iterate_supers_type() doesn't protect us from
+ * remounting (branch management)
+ */
+struct au_sphlhead au_sbilist;
+#endif
+
+/*
+ * functions for module interface.
+ */
+MODULE_LICENSE("GPL");
+/* MODULE_LICENSE("GPL v2"); */
+MODULE_AUTHOR("Junjiro R. Okajima <aufs-users@lists.sourceforge.net>");
+MODULE_DESCRIPTION(AUFS_NAME
+	" -- Advanced multi layered unification filesystem");
+MODULE_VERSION(AUFS_VERSION);
+MODULE_ALIAS_FS(AUFS_NAME);
+
+/* this module parameter has no meaning when SYSFS is disabled */
+int sysaufs_brs = 1;
+MODULE_PARM_DESC(brs, "use <sysfs>/fs/aufs/si_*/brN");
+module_param_named(brs, sysaufs_brs, int, S_IRUGO);
+
+/* this module parameter has no meaning when USER_NS is disabled */
+bool au_userns;
+MODULE_PARM_DESC(allow_userns, "allow unprivileged to mount under userns");
+module_param_named(allow_userns, au_userns, bool, S_IRUGO);
+
+/* ---------------------------------------------------------------------- */
+
+static char au_esc_chars[0x20 + 3]; /* 0x01-0x20, backslash, del, and NULL */
+
+int au_seq_path(struct seq_file *seq, struct path *path)
+{
+	int err;
+
+	err = seq_path(seq, path, au_esc_chars);
+	if (err >= 0)
+		err = 0;
+	else
+		err = -ENOMEM;
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int __init aufs_init(void)
+{
+	int err, i;
+	char *p;
+
+	p = au_esc_chars;
+	for (i = 1; i <= ' '; i++)
+		*p++ = i;
+	*p++ = '\\';
+	*p++ = '\x7f';
+	*p = 0;
+
+	au_dir_roflags = au_file_roflags(O_DIRECTORY | O_LARGEFILE);
+
+	memcpy(aufs_iop_nogetattr, aufs_iop, sizeof(aufs_iop));
+	for (i = 0; i < AuIop_Last; i++)
+		aufs_iop_nogetattr[i].getattr = NULL;
+
+	memset(au_cache, 0, sizeof(au_cache));	/* including hnotify */
+
+	au_sbilist_init();
+	sysaufs_brs_init();
+	au_debug_init();
+	au_dy_init();
+	err = sysaufs_init();
+	if (unlikely(err))
+		goto out;
+	err = au_procfs_init();
+	if (unlikely(err))
+		goto out_sysaufs;
+	err = au_wkq_init();
+	if (unlikely(err))
+		goto out_procfs;
+	err = au_loopback_init();
+	if (unlikely(err))
+		goto out_wkq;
+	err = au_hnotify_init();
+	if (unlikely(err))
+		goto out_loopback;
+	err = au_sysrq_init();
+	if (unlikely(err))
+		goto out_hin;
+	err = au_cache_init();
+	if (unlikely(err))
+		goto out_sysrq;
+
+	aufs_fs_type.fs_flags |= au_userns ? FS_USERNS_MOUNT : 0;
+	err = register_filesystem(&aufs_fs_type);
+	if (unlikely(err))
+		goto out_cache;
+
+	/* since we define pr_fmt, call printk directly */
+	printk(KERN_INFO AUFS_NAME " " AUFS_VERSION "\n");
+	goto out; /* success */
+
+out_cache:
+	au_cache_fin();
+out_sysrq:
+	au_sysrq_fin();
+out_hin:
+	au_hnotify_fin();
+out_loopback:
+	au_loopback_fin();
+out_wkq:
+	au_wkq_fin();
+out_procfs:
+	au_procfs_fin();
+out_sysaufs:
+	sysaufs_fin();
+	au_dy_fin();
+out:
+	return err;
+}
+
+static void __exit aufs_exit(void)
+{
+	unregister_filesystem(&aufs_fs_type);
+	au_cache_fin();
+	au_sysrq_fin();
+	au_hnotify_fin();
+	au_loopback_fin();
+	au_wkq_fin();
+	au_procfs_fin();
+	sysaufs_fin();
+	au_dy_fin();
+}
+
+module_init(aufs_init);
+module_exit(aufs_exit);
diff --git a/fs/aufs/module.h b/fs/aufs/module.h
new file mode 100644
index 000000000000..4f5727cb8088
--- /dev/null
+++ b/fs/aufs/module.h
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * module initialization and module-global
+ */
+
+#ifndef __AUFS_MODULE_H__
+#define __AUFS_MODULE_H__
+
+#ifdef __KERNEL__
+
+#include <linux/slab.h>
+
+struct path;
+struct seq_file;
+
+/* module parameters */
+extern int sysaufs_brs;
+extern bool au_userns;
+
+/* ---------------------------------------------------------------------- */
+
+extern int au_dir_roflags;
+
+void *au_krealloc(void *p, unsigned int new_sz, gfp_t gfp, int may_shrink);
+void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp,
+		   int may_shrink);
+
+static inline int au_kmidx_sub(size_t sz, size_t new_sz)
+{
+#ifndef CONFIG_SLOB
+	return kmalloc_index(sz) - kmalloc_index(new_sz);
+#else
+	return -1; /* SLOB is untested */
+#endif
+}
+
+int au_seq_path(struct seq_file *seq, struct path *path);
+
+#ifdef CONFIG_PROC_FS
+/* procfs.c */
+int __init au_procfs_init(void);
+void au_procfs_fin(void);
+#else
+AuStubInt0(au_procfs_init, void);
+AuStubVoid(au_procfs_fin, void);
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+/* kmem cache */
+enum {
+	AuCache_DINFO,
+	AuCache_ICNTNR,
+	AuCache_FINFO,
+	AuCache_VDIR,
+	AuCache_DEHSTR,
+	AuCache_HNOTIFY, /* must be last */
+	AuCache_Last
+};
+
+extern struct kmem_cache *au_cache[AuCache_Last];
+
+#define AuCacheFlags		(SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD)
+#define AuCache(type)		KMEM_CACHE(type, AuCacheFlags)
+#define AuCacheCtor(type, ctor)	\
+	kmem_cache_create(#type, sizeof(struct type), \
+			  __alignof__(struct type), AuCacheFlags, ctor)
+
+#define AuCacheFuncs(name, index) \
+static inline struct au_##name *au_cache_alloc_##name(void) \
+{ return kmem_cache_alloc(au_cache[AuCache_##index], GFP_NOFS); } \
+static inline void au_cache_free_##name(struct au_##name *p) \
+{ kmem_cache_free(au_cache[AuCache_##index], p); }
+
+AuCacheFuncs(dinfo, DINFO);
+AuCacheFuncs(icntnr, ICNTNR);
+AuCacheFuncs(finfo, FINFO);
+AuCacheFuncs(vdir, VDIR);
+AuCacheFuncs(vdir_dehstr, DEHSTR);
+#ifdef CONFIG_AUFS_HNOTIFY
+AuCacheFuncs(hnotify, HNOTIFY);
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_MODULE_H__ */
diff --git a/fs/aufs/mvdown.c b/fs/aufs/mvdown.c
new file mode 100644
index 000000000000..0fb18b841e94
--- /dev/null
+++ b/fs/aufs/mvdown.c
@@ -0,0 +1,704 @@
+/*
+ * Copyright (C) 2011-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * move-down, opposite of copy-up
+ */
+
+#include "aufs.h"
+
+struct au_mvd_args {
+	struct {
+		struct super_block *h_sb;
+		struct dentry *h_parent;
+		struct au_hinode *hdir;
+		struct inode *h_dir, *h_inode;
+		struct au_pin pin;
+	} info[AUFS_MVDOWN_NARRAY];
+
+	struct aufs_mvdown mvdown;
+	struct dentry *dentry, *parent;
+	struct inode *inode, *dir;
+	struct super_block *sb;
+	aufs_bindex_t bopq, bwh, bfound;
+	unsigned char rename_lock;
+};
+
+#define mvd_errno		mvdown.au_errno
+#define mvd_bsrc		mvdown.stbr[AUFS_MVDOWN_UPPER].bindex
+#define mvd_src_brid		mvdown.stbr[AUFS_MVDOWN_UPPER].brid
+#define mvd_bdst		mvdown.stbr[AUFS_MVDOWN_LOWER].bindex
+#define mvd_dst_brid		mvdown.stbr[AUFS_MVDOWN_LOWER].brid
+
+#define mvd_h_src_sb		info[AUFS_MVDOWN_UPPER].h_sb
+#define mvd_h_src_parent	info[AUFS_MVDOWN_UPPER].h_parent
+#define mvd_hdir_src		info[AUFS_MVDOWN_UPPER].hdir
+#define mvd_h_src_dir		info[AUFS_MVDOWN_UPPER].h_dir
+#define mvd_h_src_inode		info[AUFS_MVDOWN_UPPER].h_inode
+#define mvd_pin_src		info[AUFS_MVDOWN_UPPER].pin
+
+#define mvd_h_dst_sb		info[AUFS_MVDOWN_LOWER].h_sb
+#define mvd_h_dst_parent	info[AUFS_MVDOWN_LOWER].h_parent
+#define mvd_hdir_dst		info[AUFS_MVDOWN_LOWER].hdir
+#define mvd_h_dst_dir		info[AUFS_MVDOWN_LOWER].h_dir
+#define mvd_h_dst_inode		info[AUFS_MVDOWN_LOWER].h_inode
+#define mvd_pin_dst		info[AUFS_MVDOWN_LOWER].pin
+
+#define AU_MVD_PR(flag, ...) do {			\
+		if (flag)				\
+			pr_err(__VA_ARGS__);		\
+	} while (0)
+
+static int find_lower_writable(struct au_mvd_args *a)
+{
+	struct super_block *sb;
+	aufs_bindex_t bindex, bbot;
+	struct au_branch *br;
+
+	sb = a->sb;
+	bindex = a->mvd_bsrc;
+	bbot = au_sbbot(sb);
+	if (a->mvdown.flags & AUFS_MVDOWN_FHSM_LOWER)
+		for (bindex++; bindex <= bbot; bindex++) {
+			br = au_sbr(sb, bindex);
+			if (au_br_fhsm(br->br_perm)
+			    && (!(au_br_sb(br)->s_flags & MS_RDONLY)))
+				return bindex;
+		}
+	else if (!(a->mvdown.flags & AUFS_MVDOWN_ROLOWER))
+		for (bindex++; bindex <= bbot; bindex++) {
+			br = au_sbr(sb, bindex);
+			if (!au_br_rdonly(br))
+				return bindex;
+		}
+	else
+		for (bindex++; bindex <= bbot; bindex++) {
+			br = au_sbr(sb, bindex);
+			if (!(au_br_sb(br)->s_flags & MS_RDONLY)) {
+				if (au_br_rdonly(br))
+					a->mvdown.flags
+						|= AUFS_MVDOWN_ROLOWER_R;
+				return bindex;
+			}
+		}
+
+	return -1;
+}
+
+/* make the parent dir on bdst */
+static int au_do_mkdir(const unsigned char dmsg, struct au_mvd_args *a)
+{
+	int err;
+
+	err = 0;
+	a->mvd_hdir_src = au_hi(a->dir, a->mvd_bsrc);
+	a->mvd_hdir_dst = au_hi(a->dir, a->mvd_bdst);
+	a->mvd_h_src_parent = au_h_dptr(a->parent, a->mvd_bsrc);
+	a->mvd_h_dst_parent = NULL;
+	if (au_dbbot(a->parent) >= a->mvd_bdst)
+		a->mvd_h_dst_parent = au_h_dptr(a->parent, a->mvd_bdst);
+	if (!a->mvd_h_dst_parent) {
+		err = au_cpdown_dirs(a->dentry, a->mvd_bdst);
+		if (unlikely(err)) {
+			AU_MVD_PR(dmsg, "cpdown_dirs failed\n");
+			goto out;
+		}
+		a->mvd_h_dst_parent = au_h_dptr(a->parent, a->mvd_bdst);
+	}
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/* lock them all */
+static int au_do_lock(const unsigned char dmsg, struct au_mvd_args *a)
+{
+	int err;
+	struct dentry *h_trap;
+
+	a->mvd_h_src_sb = au_sbr_sb(a->sb, a->mvd_bsrc);
+	a->mvd_h_dst_sb = au_sbr_sb(a->sb, a->mvd_bdst);
+	err = au_pin(&a->mvd_pin_dst, a->dentry, a->mvd_bdst,
+		     au_opt_udba(a->sb),
+		     AuPin_MNT_WRITE | AuPin_DI_LOCKED);
+	AuTraceErr(err);
+	if (unlikely(err)) {
+		AU_MVD_PR(dmsg, "pin_dst failed\n");
+		goto out;
+	}
+
+	if (a->mvd_h_src_sb != a->mvd_h_dst_sb) {
+		a->rename_lock = 0;
+		au_pin_init(&a->mvd_pin_src, a->dentry, a->mvd_bsrc,
+			    AuLsc_DI_PARENT, AuLsc_I_PARENT3,
+			    au_opt_udba(a->sb),
+			    AuPin_MNT_WRITE | AuPin_DI_LOCKED);
+		err = au_do_pin(&a->mvd_pin_src);
+		AuTraceErr(err);
+		a->mvd_h_src_dir = d_inode(a->mvd_h_src_parent);
+		if (unlikely(err)) {
+			AU_MVD_PR(dmsg, "pin_src failed\n");
+			goto out_dst;
+		}
+		goto out; /* success */
+	}
+
+	a->rename_lock = 1;
+	au_pin_hdir_unlock(&a->mvd_pin_dst);
+	err = au_pin(&a->mvd_pin_src, a->dentry, a->mvd_bsrc,
+		     au_opt_udba(a->sb),
+		     AuPin_MNT_WRITE | AuPin_DI_LOCKED);
+	AuTraceErr(err);
+	a->mvd_h_src_dir = d_inode(a->mvd_h_src_parent);
+	if (unlikely(err)) {
+		AU_MVD_PR(dmsg, "pin_src failed\n");
+		au_pin_hdir_lock(&a->mvd_pin_dst);
+		goto out_dst;
+	}
+	au_pin_hdir_unlock(&a->mvd_pin_src);
+	h_trap = vfsub_lock_rename(a->mvd_h_src_parent, a->mvd_hdir_src,
+				   a->mvd_h_dst_parent, a->mvd_hdir_dst);
+	if (h_trap) {
+		err = (h_trap != a->mvd_h_src_parent);
+		if (err)
+			err = (h_trap != a->mvd_h_dst_parent);
+	}
+	BUG_ON(err); /* it should never happen */
+	if (unlikely(a->mvd_h_src_dir != au_pinned_h_dir(&a->mvd_pin_src))) {
+		err = -EBUSY;
+		AuTraceErr(err);
+		vfsub_unlock_rename(a->mvd_h_src_parent, a->mvd_hdir_src,
+				    a->mvd_h_dst_parent, a->mvd_hdir_dst);
+		au_pin_hdir_lock(&a->mvd_pin_src);
+		au_unpin(&a->mvd_pin_src);
+		au_pin_hdir_lock(&a->mvd_pin_dst);
+		goto out_dst;
+	}
+	goto out; /* success */
+
+out_dst:
+	au_unpin(&a->mvd_pin_dst);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+static void au_do_unlock(const unsigned char dmsg, struct au_mvd_args *a)
+{
+	if (!a->rename_lock)
+		au_unpin(&a->mvd_pin_src);
+	else {
+		vfsub_unlock_rename(a->mvd_h_src_parent, a->mvd_hdir_src,
+				    a->mvd_h_dst_parent, a->mvd_hdir_dst);
+		au_pin_hdir_lock(&a->mvd_pin_src);
+		au_unpin(&a->mvd_pin_src);
+		au_pin_hdir_lock(&a->mvd_pin_dst);
+	}
+	au_unpin(&a->mvd_pin_dst);
+}
+
+/* copy-down the file */
+static int au_do_cpdown(const unsigned char dmsg, struct au_mvd_args *a)
+{
+	int err;
+	struct au_cp_generic cpg = {
+		.dentry	= a->dentry,
+		.bdst	= a->mvd_bdst,
+		.bsrc	= a->mvd_bsrc,
+		.len	= -1,
+		.pin	= &a->mvd_pin_dst,
+		.flags	= AuCpup_DTIME | AuCpup_HOPEN
+	};
+
+	AuDbg("b%d, b%d\n", cpg.bsrc, cpg.bdst);
+	if (a->mvdown.flags & AUFS_MVDOWN_OWLOWER)
+		au_fset_cpup(cpg.flags, OVERWRITE);
+	if (a->mvdown.flags & AUFS_MVDOWN_ROLOWER)
+		au_fset_cpup(cpg.flags, RWDST);
+	err = au_sio_cpdown_simple(&cpg);
+	if (unlikely(err))
+		AU_MVD_PR(dmsg, "cpdown failed\n");
+
+	AuTraceErr(err);
+	return err;
+}
+
+/*
+ * unlink the whiteout on bdst if exist which may be created by UDBA while we
+ * were sleeping
+ */
+static int au_do_unlink_wh(const unsigned char dmsg, struct au_mvd_args *a)
+{
+	int err;
+	struct path h_path;
+	struct au_branch *br;
+	struct inode *delegated;
+
+	br = au_sbr(a->sb, a->mvd_bdst);
+	h_path.dentry = au_wh_lkup(a->mvd_h_dst_parent, &a->dentry->d_name, br);
+	err = PTR_ERR(h_path.dentry);
+	if (IS_ERR(h_path.dentry)) {
+		AU_MVD_PR(dmsg, "wh_lkup failed\n");
+		goto out;
+	}
+
+	err = 0;
+	if (d_is_positive(h_path.dentry)) {
+		h_path.mnt = au_br_mnt(br);
+		delegated = NULL;
+		err = vfsub_unlink(d_inode(a->mvd_h_dst_parent), &h_path,
+				   &delegated, /*force*/0);
+		if (unlikely(err == -EWOULDBLOCK)) {
+			pr_warn("cannot retry for NFSv4 delegation"
+				" for an internal unlink\n");
+			iput(delegated);
+		}
+		if (unlikely(err))
+			AU_MVD_PR(dmsg, "wh_unlink failed\n");
+	}
+	dput(h_path.dentry);
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/*
+ * unlink the topmost h_dentry
+ */
+static int au_do_unlink(const unsigned char dmsg, struct au_mvd_args *a)
+{
+	int err;
+	struct path h_path;
+	struct inode *delegated;
+
+	h_path.mnt = au_sbr_mnt(a->sb, a->mvd_bsrc);
+	h_path.dentry = au_h_dptr(a->dentry, a->mvd_bsrc);
+	delegated = NULL;
+	err = vfsub_unlink(a->mvd_h_src_dir, &h_path, &delegated, /*force*/0);
+	if (unlikely(err == -EWOULDBLOCK)) {
+		pr_warn("cannot retry for NFSv4 delegation"
+			" for an internal unlink\n");
+		iput(delegated);
+	}
+	if (unlikely(err))
+		AU_MVD_PR(dmsg, "unlink failed\n");
+
+	AuTraceErr(err);
+	return err;
+}
+
+/* Since mvdown succeeded, we ignore an error of this function */
+static void au_do_stfs(const unsigned char dmsg, struct au_mvd_args *a)
+{
+	int err;
+	struct au_branch *br;
+
+	a->mvdown.flags |= AUFS_MVDOWN_STFS_FAILED;
+	br = au_sbr(a->sb, a->mvd_bsrc);
+	err = au_br_stfs(br, &a->mvdown.stbr[AUFS_MVDOWN_UPPER].stfs);
+	if (!err) {
+		br = au_sbr(a->sb, a->mvd_bdst);
+		a->mvdown.stbr[AUFS_MVDOWN_LOWER].brid = br->br_id;
+		err = au_br_stfs(br, &a->mvdown.stbr[AUFS_MVDOWN_LOWER].stfs);
+	}
+	if (!err)
+		a->mvdown.flags &= ~AUFS_MVDOWN_STFS_FAILED;
+	else
+		AU_MVD_PR(dmsg, "statfs failed (%d), ignored\n", err);
+}
+
+/*
+ * copy-down the file and unlink the bsrc file.
+ * - unlink the bdst whout if exist
+ * - copy-down the file (with whtmp name and rename)
+ * - unlink the bsrc file
+ */
+static int au_do_mvdown(const unsigned char dmsg, struct au_mvd_args *a)
+{
+	int err;
+
+	err = au_do_mkdir(dmsg, a);
+	if (!err)
+		err = au_do_lock(dmsg, a);
+	if (unlikely(err))
+		goto out;
+
+	/*
+	 * do not revert the activities we made on bdst since they should be
+	 * harmless in aufs.
+	 */
+
+	err = au_do_cpdown(dmsg, a);
+	if (!err)
+		err = au_do_unlink_wh(dmsg, a);
+	if (!err && !(a->mvdown.flags & AUFS_MVDOWN_KUPPER))
+		err = au_do_unlink(dmsg, a);
+	if (unlikely(err))
+		goto out_unlock;
+
+	AuDbg("%pd2, 0x%x, %d --> %d\n",
+	      a->dentry, a->mvdown.flags, a->mvd_bsrc, a->mvd_bdst);
+	if (find_lower_writable(a) < 0)
+		a->mvdown.flags |= AUFS_MVDOWN_BOTTOM;
+
+	if (a->mvdown.flags & AUFS_MVDOWN_STFS)
+		au_do_stfs(dmsg, a);
+
+	/* maintain internal array */
+	if (!(a->mvdown.flags & AUFS_MVDOWN_KUPPER)) {
+		au_set_h_dptr(a->dentry, a->mvd_bsrc, NULL);
+		au_set_dbtop(a->dentry, a->mvd_bdst);
+		au_set_h_iptr(a->inode, a->mvd_bsrc, NULL, /*flags*/0);
+		au_set_ibtop(a->inode, a->mvd_bdst);
+	} else {
+		/* hide the lower */
+		au_set_h_dptr(a->dentry, a->mvd_bdst, NULL);
+		au_set_dbbot(a->dentry, a->mvd_bsrc);
+		au_set_h_iptr(a->inode, a->mvd_bdst, NULL, /*flags*/0);
+		au_set_ibbot(a->inode, a->mvd_bsrc);
+	}
+	if (au_dbbot(a->dentry) < a->mvd_bdst)
+		au_set_dbbot(a->dentry, a->mvd_bdst);
+	if (au_ibbot(a->inode) < a->mvd_bdst)
+		au_set_ibbot(a->inode, a->mvd_bdst);
+
+out_unlock:
+	au_do_unlock(dmsg, a);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* make sure the file is idle */
+static int au_mvd_args_busy(const unsigned char dmsg, struct au_mvd_args *a)
+{
+	int err, plinked;
+
+	err = 0;
+	plinked = !!au_opt_test(au_mntflags(a->sb), PLINK);
+	if (au_dbtop(a->dentry) == a->mvd_bsrc
+	    && au_dcount(a->dentry) == 1
+	    && atomic_read(&a->inode->i_count) == 1
+	    /* && a->mvd_h_src_inode->i_nlink == 1 */
+	    && (!plinked || !au_plink_test(a->inode))
+	    && a->inode->i_nlink == 1)
+		goto out;
+
+	err = -EBUSY;
+	AU_MVD_PR(dmsg,
+		  "b%d, d{b%d, c%d?}, i{c%d?, l%u}, hi{l%u}, p{%d, %d}\n",
+		  a->mvd_bsrc, au_dbtop(a->dentry), au_dcount(a->dentry),
+		  atomic_read(&a->inode->i_count), a->inode->i_nlink,
+		  a->mvd_h_src_inode->i_nlink,
+		  plinked, plinked ? au_plink_test(a->inode) : 0);
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/* make sure the parent dir is fine */
+static int au_mvd_args_parent(const unsigned char dmsg,
+			      struct au_mvd_args *a)
+{
+	int err;
+	aufs_bindex_t bindex;
+
+	err = 0;
+	if (unlikely(au_alive_dir(a->parent))) {
+		err = -ENOENT;
+		AU_MVD_PR(dmsg, "parent dir is dead\n");
+		goto out;
+	}
+
+	a->bopq = au_dbdiropq(a->parent);
+	bindex = au_wbr_nonopq(a->dentry, a->mvd_bdst);
+	AuDbg("b%d\n", bindex);
+	if (unlikely((bindex >= 0 && bindex < a->mvd_bdst)
+		     || (a->bopq != -1 && a->bopq < a->mvd_bdst))) {
+		err = -EINVAL;
+		a->mvd_errno = EAU_MVDOWN_OPAQUE;
+		AU_MVD_PR(dmsg, "ancestor is opaque b%d, b%d\n",
+			  a->bopq, a->mvd_bdst);
+	}
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+static int au_mvd_args_intermediate(const unsigned char dmsg,
+				    struct au_mvd_args *a)
+{
+	int err;
+	struct au_dinfo *dinfo, *tmp;
+
+	/* lookup the next lower positive entry */
+	err = -ENOMEM;
+	tmp = au_di_alloc(a->sb, AuLsc_DI_TMP);
+	if (unlikely(!tmp))
+		goto out;
+
+	a->bfound = -1;
+	a->bwh = -1;
+	dinfo = au_di(a->dentry);
+	au_di_cp(tmp, dinfo);
+	au_di_swap(tmp, dinfo);
+
+	/* returns the number of positive dentries */
+	err = au_lkup_dentry(a->dentry, a->mvd_bsrc + 1,
+			     /* AuLkup_IGNORE_PERM */ 0);
+	if (!err)
+		a->bwh = au_dbwh(a->dentry);
+	else if (err > 0)
+		a->bfound = au_dbtop(a->dentry);
+
+	au_di_swap(tmp, dinfo);
+	au_rw_write_unlock(&tmp->di_rwsem);
+	au_di_free(tmp);
+	if (unlikely(err < 0))
+		AU_MVD_PR(dmsg, "failed look-up lower\n");
+
+	/*
+	 * here, we have these cases.
+	 * bfound == -1
+	 *	no positive dentry under bsrc. there are more sub-cases.
+	 *	bwh < 0
+	 *		there no whiteout, we can safely move-down.
+	 *	bwh <= bsrc
+	 *		impossible
+	 *	bsrc < bwh && bwh < bdst
+	 *		there is a whiteout on RO branch. cannot proceed.
+	 *	bwh == bdst
+	 *		there is a whiteout on the RW target branch. it should
+	 *		be removed.
+	 *	bdst < bwh
+	 *		there is a whiteout somewhere unrelated branch.
+	 * -1 < bfound && bfound <= bsrc
+	 *	impossible.
+	 * bfound < bdst
+	 *	found, but it is on RO branch between bsrc and bdst. cannot
+	 *	proceed.
+	 * bfound == bdst
+	 *	found, replace it if AUFS_MVDOWN_FORCE is set. otherwise return
+	 *	error.
+	 * bdst < bfound
+	 *	found, after we create the file on bdst, it will be hidden.
+	 */
+
+	AuDebugOn(a->bfound == -1
+		  && a->bwh != -1
+		  && a->bwh <= a->mvd_bsrc);
+	AuDebugOn(-1 < a->bfound
+		  && a->bfound <= a->mvd_bsrc);
+
+	err = -EINVAL;
+	if (a->bfound == -1
+	    && a->mvd_bsrc < a->bwh
+	    && a->bwh != -1
+	    && a->bwh < a->mvd_bdst) {
+		a->mvd_errno = EAU_MVDOWN_WHITEOUT;
+		AU_MVD_PR(dmsg, "bsrc %d, bdst %d, bfound %d, bwh %d\n",
+			  a->mvd_bsrc, a->mvd_bdst, a->bfound, a->bwh);
+		goto out;
+	} else if (a->bfound != -1 && a->bfound < a->mvd_bdst) {
+		a->mvd_errno = EAU_MVDOWN_UPPER;
+		AU_MVD_PR(dmsg, "bdst %d, bfound %d\n",
+			  a->mvd_bdst, a->bfound);
+		goto out;
+	}
+
+	err = 0; /* success */
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+static int au_mvd_args_exist(const unsigned char dmsg, struct au_mvd_args *a)
+{
+	int err;
+
+	err = 0;
+	if (!(a->mvdown.flags & AUFS_MVDOWN_OWLOWER)
+	    && a->bfound == a->mvd_bdst)
+		err = -EEXIST;
+	AuTraceErr(err);
+	return err;
+}
+
+static int au_mvd_args(const unsigned char dmsg, struct au_mvd_args *a)
+{
+	int err;
+	struct au_branch *br;
+
+	err = -EISDIR;
+	if (unlikely(S_ISDIR(a->inode->i_mode)))
+		goto out;
+
+	err = -EINVAL;
+	if (!(a->mvdown.flags & AUFS_MVDOWN_BRID_UPPER))
+		a->mvd_bsrc = au_ibtop(a->inode);
+	else {
+		a->mvd_bsrc = au_br_index(a->sb, a->mvd_src_brid);
+		if (unlikely(a->mvd_bsrc < 0
+			     || (a->mvd_bsrc < au_dbtop(a->dentry)
+				 || au_dbbot(a->dentry) < a->mvd_bsrc
+				 || !au_h_dptr(a->dentry, a->mvd_bsrc))
+			     || (a->mvd_bsrc < au_ibtop(a->inode)
+				 || au_ibbot(a->inode) < a->mvd_bsrc
+				 || !au_h_iptr(a->inode, a->mvd_bsrc)))) {
+			a->mvd_errno = EAU_MVDOWN_NOUPPER;
+			AU_MVD_PR(dmsg, "no upper\n");
+			goto out;
+		}
+	}
+	if (unlikely(a->mvd_bsrc == au_sbbot(a->sb))) {
+		a->mvd_errno = EAU_MVDOWN_BOTTOM;
+		AU_MVD_PR(dmsg, "on the bottom\n");
+		goto out;
+	}
+	a->mvd_h_src_inode = au_h_iptr(a->inode, a->mvd_bsrc);
+	br = au_sbr(a->sb, a->mvd_bsrc);
+	err = au_br_rdonly(br);
+	if (!(a->mvdown.flags & AUFS_MVDOWN_ROUPPER)) {
+		if (unlikely(err))
+			goto out;
+	} else if (!(vfsub_native_ro(a->mvd_h_src_inode)
+		     || IS_APPEND(a->mvd_h_src_inode))) {
+		if (err)
+			a->mvdown.flags |= AUFS_MVDOWN_ROUPPER_R;
+		/* go on */
+	} else
+		goto out;
+
+	err = -EINVAL;
+	if (!(a->mvdown.flags & AUFS_MVDOWN_BRID_LOWER)) {
+		a->mvd_bdst = find_lower_writable(a);
+		if (unlikely(a->mvd_bdst < 0)) {
+			a->mvd_errno = EAU_MVDOWN_BOTTOM;
+			AU_MVD_PR(dmsg, "no writable lower branch\n");
+			goto out;
+		}
+	} else {
+		a->mvd_bdst = au_br_index(a->sb, a->mvd_dst_brid);
+		if (unlikely(a->mvd_bdst < 0
+			     || au_sbbot(a->sb) < a->mvd_bdst)) {
+			a->mvd_errno = EAU_MVDOWN_NOLOWERBR;
+			AU_MVD_PR(dmsg, "no lower brid\n");
+			goto out;
+		}
+	}
+
+	err = au_mvd_args_busy(dmsg, a);
+	if (!err)
+		err = au_mvd_args_parent(dmsg, a);
+	if (!err)
+		err = au_mvd_args_intermediate(dmsg, a);
+	if (!err)
+		err = au_mvd_args_exist(dmsg, a);
+	if (!err)
+		AuDbg("b%d, b%d\n", a->mvd_bsrc, a->mvd_bdst);
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *uarg)
+{
+	int err, e;
+	unsigned char dmsg;
+	struct au_mvd_args *args;
+	struct inode *inode;
+
+	inode = d_inode(dentry);
+	err = -EPERM;
+	if (unlikely(!capable(CAP_SYS_ADMIN)))
+		goto out;
+
+	err = -ENOMEM;
+	args = kmalloc(sizeof(*args), GFP_NOFS);
+	if (unlikely(!args))
+		goto out;
+
+	err = copy_from_user(&args->mvdown, uarg, sizeof(args->mvdown));
+	if (!err)
+		err = !access_ok(VERIFY_WRITE, uarg, sizeof(*uarg));
+	if (unlikely(err)) {
+		err = -EFAULT;
+		AuTraceErr(err);
+		goto out_free;
+	}
+	AuDbg("flags 0x%x\n", args->mvdown.flags);
+	args->mvdown.flags &= ~(AUFS_MVDOWN_ROLOWER_R | AUFS_MVDOWN_ROUPPER_R);
+	args->mvdown.au_errno = 0;
+	args->dentry = dentry;
+	args->inode = inode;
+	args->sb = dentry->d_sb;
+
+	err = -ENOENT;
+	dmsg = !!(args->mvdown.flags & AUFS_MVDOWN_DMSG);
+	args->parent = dget_parent(dentry);
+	args->dir = d_inode(args->parent);
+	inode_lock_nested(args->dir, I_MUTEX_PARENT);
+	dput(args->parent);
+	if (unlikely(args->parent != dentry->d_parent)) {
+		AU_MVD_PR(dmsg, "parent dir is moved\n");
+		goto out_dir;
+	}
+
+	inode_lock_nested(inode, I_MUTEX_CHILD);
+	err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_NOPLMW);
+	if (unlikely(err))
+		goto out_inode;
+
+	di_write_lock_parent(args->parent);
+	err = au_mvd_args(dmsg, args);
+	if (unlikely(err))
+		goto out_parent;
+
+	err = au_do_mvdown(dmsg, args);
+	if (unlikely(err))
+		goto out_parent;
+
+	au_cpup_attr_timesizes(args->dir);
+	au_cpup_attr_timesizes(inode);
+	if (!(args->mvdown.flags & AUFS_MVDOWN_KUPPER))
+		au_cpup_igen(inode, au_h_iptr(inode, args->mvd_bdst));
+	/* au_digen_dec(dentry); */
+
+out_parent:
+	di_write_unlock(args->parent);
+	aufs_read_unlock(dentry, AuLock_DW);
+out_inode:
+	inode_unlock(inode);
+out_dir:
+	inode_unlock(args->dir);
+out_free:
+	e = copy_to_user(uarg, &args->mvdown, sizeof(args->mvdown));
+	if (unlikely(e))
+		err = -EFAULT;
+	kfree(args);
+out:
+	AuTraceErr(err);
+	return err;
+}
diff --git a/fs/aufs/opts.c b/fs/aufs/opts.c
new file mode 100644
index 000000000000..717cb282868c
--- /dev/null
+++ b/fs/aufs/opts.c
@@ -0,0 +1,1846 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * mount options/flags
+ */
+
+#include <linux/namei.h>
+#include <linux/types.h> /* a distribution requires */
+#include <linux/parser.h>
+#include "aufs.h"
+
+/* ---------------------------------------------------------------------- */
+
+enum {
+	Opt_br,
+	Opt_add, Opt_del, Opt_mod, Opt_append, Opt_prepend,
+	Opt_idel, Opt_imod,
+	Opt_dirwh, Opt_rdcache, Opt_rdblk, Opt_rdhash,
+	Opt_rdblk_def, Opt_rdhash_def,
+	Opt_xino, Opt_noxino,
+	Opt_trunc_xino, Opt_trunc_xino_v, Opt_notrunc_xino,
+	Opt_trunc_xino_path, Opt_itrunc_xino,
+	Opt_trunc_xib, Opt_notrunc_xib,
+	Opt_shwh, Opt_noshwh,
+	Opt_plink, Opt_noplink, Opt_list_plink,
+	Opt_udba,
+	Opt_dio, Opt_nodio,
+	Opt_diropq_a, Opt_diropq_w,
+	Opt_warn_perm, Opt_nowarn_perm,
+	Opt_wbr_copyup, Opt_wbr_create,
+	Opt_fhsm_sec,
+	Opt_verbose, Opt_noverbose,
+	Opt_sum, Opt_nosum, Opt_wsum,
+	Opt_dirperm1, Opt_nodirperm1,
+	Opt_acl, Opt_noacl,
+	Opt_tail, Opt_ignore, Opt_ignore_silent, Opt_err
+};
+
+static match_table_t options = {
+	{Opt_br, "br=%s"},
+	{Opt_br, "br:%s"},
+
+	{Opt_add, "add=%d:%s"},
+	{Opt_add, "add:%d:%s"},
+	{Opt_add, "ins=%d:%s"},
+	{Opt_add, "ins:%d:%s"},
+	{Opt_append, "append=%s"},
+	{Opt_append, "append:%s"},
+	{Opt_prepend, "prepend=%s"},
+	{Opt_prepend, "prepend:%s"},
+
+	{Opt_del, "del=%s"},
+	{Opt_del, "del:%s"},
+	/* {Opt_idel, "idel:%d"}, */
+	{Opt_mod, "mod=%s"},
+	{Opt_mod, "mod:%s"},
+	/* {Opt_imod, "imod:%d:%s"}, */
+
+	{Opt_dirwh, "dirwh=%d"},
+
+	{Opt_xino, "xino=%s"},
+	{Opt_noxino, "noxino"},
+	{Opt_trunc_xino, "trunc_xino"},
+	{Opt_trunc_xino_v, "trunc_xino_v=%d:%d"},
+	{Opt_notrunc_xino, "notrunc_xino"},
+	{Opt_trunc_xino_path, "trunc_xino=%s"},
+	{Opt_itrunc_xino, "itrunc_xino=%d"},
+	/* {Opt_zxino, "zxino=%s"}, */
+	{Opt_trunc_xib, "trunc_xib"},
+	{Opt_notrunc_xib, "notrunc_xib"},
+
+#ifdef CONFIG_PROC_FS
+	{Opt_plink, "plink"},
+#else
+	{Opt_ignore_silent, "plink"},
+#endif
+
+	{Opt_noplink, "noplink"},
+
+#ifdef CONFIG_AUFS_DEBUG
+	{Opt_list_plink, "list_plink"},
+#endif
+
+	{Opt_udba, "udba=%s"},
+
+	{Opt_dio, "dio"},
+	{Opt_nodio, "nodio"},
+
+#ifdef CONFIG_AUFS_FHSM
+	{Opt_fhsm_sec, "fhsm_sec=%d"},
+#else
+	{Opt_ignore_silent, "fhsm_sec=%d"},
+#endif
+
+	{Opt_diropq_a, "diropq=always"},
+	{Opt_diropq_a, "diropq=a"},
+	{Opt_diropq_w, "diropq=whiteouted"},
+	{Opt_diropq_w, "diropq=w"},
+
+	{Opt_warn_perm, "warn_perm"},
+	{Opt_nowarn_perm, "nowarn_perm"},
+
+	/* keep them temporary */
+	{Opt_ignore_silent, "nodlgt"},
+	{Opt_ignore_silent, "clean_plink"},
+
+#ifdef CONFIG_AUFS_SHWH
+	{Opt_shwh, "shwh"},
+#endif
+	{Opt_noshwh, "noshwh"},
+
+	{Opt_dirperm1, "dirperm1"},
+	{Opt_nodirperm1, "nodirperm1"},
+
+	{Opt_verbose, "verbose"},
+	{Opt_verbose, "v"},
+	{Opt_noverbose, "noverbose"},
+	{Opt_noverbose, "quiet"},
+	{Opt_noverbose, "q"},
+	{Opt_noverbose, "silent"},
+
+	{Opt_sum, "sum"},
+	{Opt_nosum, "nosum"},
+	{Opt_wsum, "wsum"},
+
+	{Opt_rdcache, "rdcache=%d"},
+	{Opt_rdblk, "rdblk=%d"},
+	{Opt_rdblk_def, "rdblk=def"},
+	{Opt_rdhash, "rdhash=%d"},
+	{Opt_rdhash_def, "rdhash=def"},
+
+	{Opt_wbr_create, "create=%s"},
+	{Opt_wbr_create, "create_policy=%s"},
+	{Opt_wbr_copyup, "cpup=%s"},
+	{Opt_wbr_copyup, "copyup=%s"},
+	{Opt_wbr_copyup, "copyup_policy=%s"},
+
+	/* generic VFS flag */
+#ifdef CONFIG_FS_POSIX_ACL
+	{Opt_acl, "acl"},
+	{Opt_noacl, "noacl"},
+#else
+	{Opt_ignore_silent, "acl"},
+	{Opt_ignore_silent, "noacl"},
+#endif
+
+	/* internal use for the scripts */
+	{Opt_ignore_silent, "si=%s"},
+
+	{Opt_br, "dirs=%s"},
+	{Opt_ignore, "debug=%d"},
+	{Opt_ignore, "delete=whiteout"},
+	{Opt_ignore, "delete=all"},
+	{Opt_ignore, "imap=%s"},
+
+	/* temporary workaround, due to old mount(8)? */
+	{Opt_ignore_silent, "relatime"},
+
+	{Opt_err, NULL}
+};
+
+/* ---------------------------------------------------------------------- */
+
+static const char *au_parser_pattern(int val, match_table_t tbl)
+{
+	struct match_token *p;
+
+	p = tbl;
+	while (p->pattern) {
+		if (p->token == val)
+			return p->pattern;
+		p++;
+	}
+	BUG();
+	return "??";
+}
+
+static const char *au_optstr(int *val, match_table_t tbl)
+{
+	struct match_token *p;
+	int v;
+
+	v = *val;
+	if (!v)
+		goto out;
+	p = tbl;
+	while (p->pattern) {
+		if (p->token
+		    && (v & p->token) == p->token) {
+			*val &= ~p->token;
+			return p->pattern;
+		}
+		p++;
+	}
+
+out:
+	return NULL;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static match_table_t brperm = {
+	{AuBrPerm_RO, AUFS_BRPERM_RO},
+	{AuBrPerm_RR, AUFS_BRPERM_RR},
+	{AuBrPerm_RW, AUFS_BRPERM_RW},
+	{0, NULL}
+};
+
+static match_table_t brattr = {
+	/* general */
+	{AuBrAttr_COO_REG, AUFS_BRATTR_COO_REG},
+	{AuBrAttr_COO_ALL, AUFS_BRATTR_COO_ALL},
+	/* 'unpin' attrib is meaningless since linux-3.18-rc1 */
+	{AuBrAttr_UNPIN, AUFS_BRATTR_UNPIN},
+#ifdef CONFIG_AUFS_FHSM
+	{AuBrAttr_FHSM, AUFS_BRATTR_FHSM},
+#endif
+#ifdef CONFIG_AUFS_XATTR
+	{AuBrAttr_ICEX, AUFS_BRATTR_ICEX},
+	{AuBrAttr_ICEX_SEC, AUFS_BRATTR_ICEX_SEC},
+	{AuBrAttr_ICEX_SYS, AUFS_BRATTR_ICEX_SYS},
+	{AuBrAttr_ICEX_TR, AUFS_BRATTR_ICEX_TR},
+	{AuBrAttr_ICEX_USR, AUFS_BRATTR_ICEX_USR},
+	{AuBrAttr_ICEX_OTH, AUFS_BRATTR_ICEX_OTH},
+#endif
+
+	/* ro/rr branch */
+	{AuBrRAttr_WH, AUFS_BRRATTR_WH},
+
+	/* rw branch */
+	{AuBrWAttr_MOO, AUFS_BRWATTR_MOO},
+	{AuBrWAttr_NoLinkWH, AUFS_BRWATTR_NLWH},
+
+	{0, NULL}
+};
+
+static int br_attr_val(char *str, match_table_t table, substring_t args[])
+{
+	int attr, v;
+	char *p;
+
+	attr = 0;
+	do {
+		p = strchr(str, '+');
+		if (p)
+			*p = 0;
+		v = match_token(str, table, args);
+		if (v) {
+			if (v & AuBrAttr_CMOO_Mask)
+				attr &= ~AuBrAttr_CMOO_Mask;
+			attr |= v;
+		} else {
+			if (p)
+				*p = '+';
+			pr_warn("ignored branch attribute %s\n", str);
+			break;
+		}
+		if (p)
+			str = p + 1;
+	} while (p);
+
+	return attr;
+}
+
+static int au_do_optstr_br_attr(au_br_perm_str_t *str, int perm)
+{
+	int sz;
+	const char *p;
+	char *q;
+
+	q = str->a;
+	*q = 0;
+	p = au_optstr(&perm, brattr);
+	if (p) {
+		sz = strlen(p);
+		memcpy(q, p, sz + 1);
+		q += sz;
+	} else
+		goto out;
+
+	do {
+		p = au_optstr(&perm, brattr);
+		if (p) {
+			*q++ = '+';
+			sz = strlen(p);
+			memcpy(q, p, sz + 1);
+			q += sz;
+		}
+	} while (p);
+
+out:
+	return q - str->a;
+}
+
+static int noinline_for_stack br_perm_val(char *perm)
+{
+	int val, bad, sz;
+	char *p;
+	substring_t args[MAX_OPT_ARGS];
+	au_br_perm_str_t attr;
+
+	p = strchr(perm, '+');
+	if (p)
+		*p = 0;
+	val = match_token(perm, brperm, args);
+	if (!val) {
+		if (p)
+			*p = '+';
+		pr_warn("ignored branch permission %s\n", perm);
+		val = AuBrPerm_RO;
+		goto out;
+	}
+	if (!p)
+		goto out;
+
+	val |= br_attr_val(p + 1, brattr, args);
+
+	bad = 0;
+	switch (val & AuBrPerm_Mask) {
+	case AuBrPerm_RO:
+	case AuBrPerm_RR:
+		bad = val & AuBrWAttr_Mask;
+		val &= ~AuBrWAttr_Mask;
+		break;
+	case AuBrPerm_RW:
+		bad = val & AuBrRAttr_Mask;
+		val &= ~AuBrRAttr_Mask;
+		break;
+	}
+
+	/*
+	 * 'unpin' attrib becomes meaningless since linux-3.18-rc1, but aufs
+	 * does not treat it as an error, just warning.
+	 * this is a tiny guard for the user operation.
+	 */
+	if (val & AuBrAttr_UNPIN) {
+		bad |= AuBrAttr_UNPIN;
+		val &= ~AuBrAttr_UNPIN;
+	}
+
+	if (unlikely(bad)) {
+		sz = au_do_optstr_br_attr(&attr, bad);
+		AuDebugOn(!sz);
+		pr_warn("ignored branch attribute %s\n", attr.a);
+	}
+
+out:
+	return val;
+}
+
+void au_optstr_br_perm(au_br_perm_str_t *str, int perm)
+{
+	au_br_perm_str_t attr;
+	const char *p;
+	char *q;
+	int sz;
+
+	q = str->a;
+	p = au_optstr(&perm, brperm);
+	AuDebugOn(!p || !*p);
+	sz = strlen(p);
+	memcpy(q, p, sz + 1);
+	q += sz;
+
+	sz = au_do_optstr_br_attr(&attr, perm);
+	if (sz) {
+		*q++ = '+';
+		memcpy(q, attr.a, sz + 1);
+	}
+
+	AuDebugOn(strlen(str->a) >= sizeof(str->a));
+}
+
+/* ---------------------------------------------------------------------- */
+
+static match_table_t udbalevel = {
+	{AuOpt_UDBA_REVAL, "reval"},
+	{AuOpt_UDBA_NONE, "none"},
+#ifdef CONFIG_AUFS_HNOTIFY
+	{AuOpt_UDBA_HNOTIFY, "notify"}, /* abstraction */
+#ifdef CONFIG_AUFS_HFSNOTIFY
+	{AuOpt_UDBA_HNOTIFY, "fsnotify"},
+#endif
+#endif
+	{-1, NULL}
+};
+
+static int noinline_for_stack udba_val(char *str)
+{
+	substring_t args[MAX_OPT_ARGS];
+
+	return match_token(str, udbalevel, args);
+}
+
+const char *au_optstr_udba(int udba)
+{
+	return au_parser_pattern(udba, udbalevel);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static match_table_t au_wbr_create_policy = {
+	{AuWbrCreate_TDP, "tdp"},
+	{AuWbrCreate_TDP, "top-down-parent"},
+	{AuWbrCreate_RR, "rr"},
+	{AuWbrCreate_RR, "round-robin"},
+	{AuWbrCreate_MFS, "mfs"},
+	{AuWbrCreate_MFS, "most-free-space"},
+	{AuWbrCreate_MFSV, "mfs:%d"},
+	{AuWbrCreate_MFSV, "most-free-space:%d"},
+
+	/* top-down regardless the parent, and then mfs */
+	{AuWbrCreate_TDMFS, "tdmfs:%d"},
+	{AuWbrCreate_TDMFSV, "tdmfs:%d:%d"},
+
+	{AuWbrCreate_MFSRR, "mfsrr:%d"},
+	{AuWbrCreate_MFSRRV, "mfsrr:%d:%d"},
+	{AuWbrCreate_PMFS, "pmfs"},
+	{AuWbrCreate_PMFSV, "pmfs:%d"},
+	{AuWbrCreate_PMFSRR, "pmfsrr:%d"},
+	{AuWbrCreate_PMFSRRV, "pmfsrr:%d:%d"},
+
+	{-1, NULL}
+};
+
+static int au_wbr_mfs_wmark(substring_t *arg, char *str,
+			    struct au_opt_wbr_create *create)
+{
+	int err;
+	unsigned long long ull;
+
+	err = 0;
+	if (!match_u64(arg, &ull))
+		create->mfsrr_watermark = ull;
+	else {
+		pr_err("bad integer in %s\n", str);
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+static int au_wbr_mfs_sec(substring_t *arg, char *str,
+			  struct au_opt_wbr_create *create)
+{
+	int n, err;
+
+	err = 0;
+	if (!match_int(arg, &n) && 0 <= n && n <= AUFS_MFS_MAX_SEC)
+		create->mfs_second = n;
+	else {
+		pr_err("bad integer in %s\n", str);
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+static int noinline_for_stack
+au_wbr_create_val(char *str, struct au_opt_wbr_create *create)
+{
+	int err, e;
+	substring_t args[MAX_OPT_ARGS];
+
+	err = match_token(str, au_wbr_create_policy, args);
+	create->wbr_create = err;
+	switch (err) {
+	case AuWbrCreate_MFSRRV:
+	case AuWbrCreate_TDMFSV:
+	case AuWbrCreate_PMFSRRV:
+		e = au_wbr_mfs_wmark(&args[0], str, create);
+		if (!e)
+			e = au_wbr_mfs_sec(&args[1], str, create);
+		if (unlikely(e))
+			err = e;
+		break;
+	case AuWbrCreate_MFSRR:
+	case AuWbrCreate_TDMFS:
+	case AuWbrCreate_PMFSRR:
+		e = au_wbr_mfs_wmark(&args[0], str, create);
+		if (unlikely(e)) {
+			err = e;
+			break;
+		}
+		/*FALLTHROUGH*/
+	case AuWbrCreate_MFS:
+	case AuWbrCreate_PMFS:
+		create->mfs_second = AUFS_MFS_DEF_SEC;
+		break;
+	case AuWbrCreate_MFSV:
+	case AuWbrCreate_PMFSV:
+		e = au_wbr_mfs_sec(&args[0], str, create);
+		if (unlikely(e))
+			err = e;
+		break;
+	}
+
+	return err;
+}
+
+const char *au_optstr_wbr_create(int wbr_create)
+{
+	return au_parser_pattern(wbr_create, au_wbr_create_policy);
+}
+
+static match_table_t au_wbr_copyup_policy = {
+	{AuWbrCopyup_TDP, "tdp"},
+	{AuWbrCopyup_TDP, "top-down-parent"},
+	{AuWbrCopyup_BUP, "bup"},
+	{AuWbrCopyup_BUP, "bottom-up-parent"},
+	{AuWbrCopyup_BU, "bu"},
+	{AuWbrCopyup_BU, "bottom-up"},
+	{-1, NULL}
+};
+
+static int noinline_for_stack au_wbr_copyup_val(char *str)
+{
+	substring_t args[MAX_OPT_ARGS];
+
+	return match_token(str, au_wbr_copyup_policy, args);
+}
+
+const char *au_optstr_wbr_copyup(int wbr_copyup)
+{
+	return au_parser_pattern(wbr_copyup, au_wbr_copyup_policy);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static const int lkup_dirflags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
+
+static void dump_opts(struct au_opts *opts)
+{
+#ifdef CONFIG_AUFS_DEBUG
+	/* reduce stack space */
+	union {
+		struct au_opt_add *add;
+		struct au_opt_del *del;
+		struct au_opt_mod *mod;
+		struct au_opt_xino *xino;
+		struct au_opt_xino_itrunc *xino_itrunc;
+		struct au_opt_wbr_create *create;
+	} u;
+	struct au_opt *opt;
+
+	opt = opts->opt;
+	while (opt->type != Opt_tail) {
+		switch (opt->type) {
+		case Opt_add:
+			u.add = &opt->add;
+			AuDbg("add {b%d, %s, 0x%x, %p}\n",
+				  u.add->bindex, u.add->pathname, u.add->perm,
+				  u.add->path.dentry);
+			break;
+		case Opt_del:
+		case Opt_idel:
+			u.del = &opt->del;
+			AuDbg("del {%s, %p}\n",
+			      u.del->pathname, u.del->h_path.dentry);
+			break;
+		case Opt_mod:
+		case Opt_imod:
+			u.mod = &opt->mod;
+			AuDbg("mod {%s, 0x%x, %p}\n",
+				  u.mod->path, u.mod->perm, u.mod->h_root);
+			break;
+		case Opt_append:
+			u.add = &opt->add;
+			AuDbg("append {b%d, %s, 0x%x, %p}\n",
+				  u.add->bindex, u.add->pathname, u.add->perm,
+				  u.add->path.dentry);
+			break;
+		case Opt_prepend:
+			u.add = &opt->add;
+			AuDbg("prepend {b%d, %s, 0x%x, %p}\n",
+				  u.add->bindex, u.add->pathname, u.add->perm,
+				  u.add->path.dentry);
+			break;
+		case Opt_dirwh:
+			AuDbg("dirwh %d\n", opt->dirwh);
+			break;
+		case Opt_rdcache:
+			AuDbg("rdcache %d\n", opt->rdcache);
+			break;
+		case Opt_rdblk:
+			AuDbg("rdblk %u\n", opt->rdblk);
+			break;
+		case Opt_rdblk_def:
+			AuDbg("rdblk_def\n");
+			break;
+		case Opt_rdhash:
+			AuDbg("rdhash %u\n", opt->rdhash);
+			break;
+		case Opt_rdhash_def:
+			AuDbg("rdhash_def\n");
+			break;
+		case Opt_xino:
+			u.xino = &opt->xino;
+			AuDbg("xino {%s %pD}\n", u.xino->path, u.xino->file);
+			break;
+		case Opt_trunc_xino:
+			AuLabel(trunc_xino);
+			break;
+		case Opt_notrunc_xino:
+			AuLabel(notrunc_xino);
+			break;
+		case Opt_trunc_xino_path:
+		case Opt_itrunc_xino:
+			u.xino_itrunc = &opt->xino_itrunc;
+			AuDbg("trunc_xino %d\n", u.xino_itrunc->bindex);
+			break;
+		case Opt_noxino:
+			AuLabel(noxino);
+			break;
+		case Opt_trunc_xib:
+			AuLabel(trunc_xib);
+			break;
+		case Opt_notrunc_xib:
+			AuLabel(notrunc_xib);
+			break;
+		case Opt_shwh:
+			AuLabel(shwh);
+			break;
+		case Opt_noshwh:
+			AuLabel(noshwh);
+			break;
+		case Opt_dirperm1:
+			AuLabel(dirperm1);
+			break;
+		case Opt_nodirperm1:
+			AuLabel(nodirperm1);
+			break;
+		case Opt_plink:
+			AuLabel(plink);
+			break;
+		case Opt_noplink:
+			AuLabel(noplink);
+			break;
+		case Opt_list_plink:
+			AuLabel(list_plink);
+			break;
+		case Opt_udba:
+			AuDbg("udba %d, %s\n",
+				  opt->udba, au_optstr_udba(opt->udba));
+			break;
+		case Opt_dio:
+			AuLabel(dio);
+			break;
+		case Opt_nodio:
+			AuLabel(nodio);
+			break;
+		case Opt_diropq_a:
+			AuLabel(diropq_a);
+			break;
+		case Opt_diropq_w:
+			AuLabel(diropq_w);
+			break;
+		case Opt_warn_perm:
+			AuLabel(warn_perm);
+			break;
+		case Opt_nowarn_perm:
+			AuLabel(nowarn_perm);
+			break;
+		case Opt_verbose:
+			AuLabel(verbose);
+			break;
+		case Opt_noverbose:
+			AuLabel(noverbose);
+			break;
+		case Opt_sum:
+			AuLabel(sum);
+			break;
+		case Opt_nosum:
+			AuLabel(nosum);
+			break;
+		case Opt_wsum:
+			AuLabel(wsum);
+			break;
+		case Opt_wbr_create:
+			u.create = &opt->wbr_create;
+			AuDbg("create %d, %s\n", u.create->wbr_create,
+				  au_optstr_wbr_create(u.create->wbr_create));
+			switch (u.create->wbr_create) {
+			case AuWbrCreate_MFSV:
+			case AuWbrCreate_PMFSV:
+				AuDbg("%d sec\n", u.create->mfs_second);
+				break;
+			case AuWbrCreate_MFSRR:
+			case AuWbrCreate_TDMFS:
+				AuDbg("%llu watermark\n",
+					  u.create->mfsrr_watermark);
+				break;
+			case AuWbrCreate_MFSRRV:
+			case AuWbrCreate_TDMFSV:
+			case AuWbrCreate_PMFSRRV:
+				AuDbg("%llu watermark, %d sec\n",
+					  u.create->mfsrr_watermark,
+					  u.create->mfs_second);
+				break;
+			}
+			break;
+		case Opt_wbr_copyup:
+			AuDbg("copyup %d, %s\n", opt->wbr_copyup,
+				  au_optstr_wbr_copyup(opt->wbr_copyup));
+			break;
+		case Opt_fhsm_sec:
+			AuDbg("fhsm_sec %u\n", opt->fhsm_second);
+			break;
+		case Opt_acl:
+			AuLabel(acl);
+			break;
+		case Opt_noacl:
+			AuLabel(noacl);
+			break;
+		default:
+			BUG();
+		}
+		opt++;
+	}
+#endif
+}
+
+void au_opts_free(struct au_opts *opts)
+{
+	struct au_opt *opt;
+
+	opt = opts->opt;
+	while (opt->type != Opt_tail) {
+		switch (opt->type) {
+		case Opt_add:
+		case Opt_append:
+		case Opt_prepend:
+			path_put(&opt->add.path);
+			break;
+		case Opt_del:
+		case Opt_idel:
+			path_put(&opt->del.h_path);
+			break;
+		case Opt_mod:
+		case Opt_imod:
+			dput(opt->mod.h_root);
+			break;
+		case Opt_xino:
+			fput(opt->xino.file);
+			break;
+		}
+		opt++;
+	}
+}
+
+static int opt_add(struct au_opt *opt, char *opt_str, unsigned long sb_flags,
+		   aufs_bindex_t bindex)
+{
+	int err;
+	struct au_opt_add *add = &opt->add;
+	char *p;
+
+	add->bindex = bindex;
+	add->perm = AuBrPerm_RO;
+	add->pathname = opt_str;
+	p = strchr(opt_str, '=');
+	if (p) {
+		*p++ = 0;
+		if (*p)
+			add->perm = br_perm_val(p);
+	}
+
+	err = vfsub_kern_path(add->pathname, lkup_dirflags, &add->path);
+	if (!err) {
+		if (!p) {
+			add->perm = AuBrPerm_RO;
+			if (au_test_fs_rr(add->path.dentry->d_sb))
+				add->perm = AuBrPerm_RR;
+			else if (!bindex && !(sb_flags & MS_RDONLY))
+				add->perm = AuBrPerm_RW;
+		}
+		opt->type = Opt_add;
+		goto out;
+	}
+	pr_err("lookup failed %s (%d)\n", add->pathname, err);
+	err = -EINVAL;
+
+out:
+	return err;
+}
+
+static int au_opts_parse_del(struct au_opt_del *del, substring_t args[])
+{
+	int err;
+
+	del->pathname = args[0].from;
+	AuDbg("del path %s\n", del->pathname);
+
+	err = vfsub_kern_path(del->pathname, lkup_dirflags, &del->h_path);
+	if (unlikely(err))
+		pr_err("lookup failed %s (%d)\n", del->pathname, err);
+
+	return err;
+}
+
+#if 0 /* reserved for future use */
+static int au_opts_parse_idel(struct super_block *sb, aufs_bindex_t bindex,
+			      struct au_opt_del *del, substring_t args[])
+{
+	int err;
+	struct dentry *root;
+
+	err = -EINVAL;
+	root = sb->s_root;
+	aufs_read_lock(root, AuLock_FLUSH);
+	if (bindex < 0 || au_sbbot(sb) < bindex) {
+		pr_err("out of bounds, %d\n", bindex);
+		goto out;
+	}
+
+	err = 0;
+	del->h_path.dentry = dget(au_h_dptr(root, bindex));
+	del->h_path.mnt = mntget(au_sbr_mnt(sb, bindex));
+
+out:
+	aufs_read_unlock(root, !AuLock_IR);
+	return err;
+}
+#endif
+
+static int noinline_for_stack
+au_opts_parse_mod(struct au_opt_mod *mod, substring_t args[])
+{
+	int err;
+	struct path path;
+	char *p;
+
+	err = -EINVAL;
+	mod->path = args[0].from;
+	p = strchr(mod->path, '=');
+	if (unlikely(!p)) {
+		pr_err("no permssion %s\n", args[0].from);
+		goto out;
+	}
+
+	*p++ = 0;
+	err = vfsub_kern_path(mod->path, lkup_dirflags, &path);
+	if (unlikely(err)) {
+		pr_err("lookup failed %s (%d)\n", mod->path, err);
+		goto out;
+	}
+
+	mod->perm = br_perm_val(p);
+	AuDbg("mod path %s, perm 0x%x, %s\n", mod->path, mod->perm, p);
+	mod->h_root = dget(path.dentry);
+	path_put(&path);
+
+out:
+	return err;
+}
+
+#if 0 /* reserved for future use */
+static int au_opts_parse_imod(struct super_block *sb, aufs_bindex_t bindex,
+			      struct au_opt_mod *mod, substring_t args[])
+{
+	int err;
+	struct dentry *root;
+
+	err = -EINVAL;
+	root = sb->s_root;
+	aufs_read_lock(root, AuLock_FLUSH);
+	if (bindex < 0 || au_sbbot(sb) < bindex) {
+		pr_err("out of bounds, %d\n", bindex);
+		goto out;
+	}
+
+	err = 0;
+	mod->perm = br_perm_val(args[1].from);
+	AuDbg("mod path %s, perm 0x%x, %s\n",
+	      mod->path, mod->perm, args[1].from);
+	mod->h_root = dget(au_h_dptr(root, bindex));
+
+out:
+	aufs_read_unlock(root, !AuLock_IR);
+	return err;
+}
+#endif
+
+static int au_opts_parse_xino(struct super_block *sb, struct au_opt_xino *xino,
+			      substring_t args[])
+{
+	int err;
+	struct file *file;
+
+	file = au_xino_create(sb, args[0].from, /*silent*/0);
+	err = PTR_ERR(file);
+	if (IS_ERR(file))
+		goto out;
+
+	err = -EINVAL;
+	if (unlikely(file->f_path.dentry->d_sb == sb)) {
+		fput(file);
+		pr_err("%s must be outside\n", args[0].from);
+		goto out;
+	}
+
+	err = 0;
+	xino->file = file;
+	xino->path = args[0].from;
+
+out:
+	return err;
+}
+
+static int noinline_for_stack
+au_opts_parse_xino_itrunc_path(struct super_block *sb,
+			       struct au_opt_xino_itrunc *xino_itrunc,
+			       substring_t args[])
+{
+	int err;
+	aufs_bindex_t bbot, bindex;
+	struct path path;
+	struct dentry *root;
+
+	err = vfsub_kern_path(args[0].from, lkup_dirflags, &path);
+	if (unlikely(err)) {
+		pr_err("lookup failed %s (%d)\n", args[0].from, err);
+		goto out;
+	}
+
+	xino_itrunc->bindex = -1;
+	root = sb->s_root;
+	aufs_read_lock(root, AuLock_FLUSH);
+	bbot = au_sbbot(sb);
+	for (bindex = 0; bindex <= bbot; bindex++) {
+		if (au_h_dptr(root, bindex) == path.dentry) {
+			xino_itrunc->bindex = bindex;
+			break;
+		}
+	}
+	aufs_read_unlock(root, !AuLock_IR);
+	path_put(&path);
+
+	if (unlikely(xino_itrunc->bindex < 0)) {
+		pr_err("no such branch %s\n", args[0].from);
+		err = -EINVAL;
+	}
+
+out:
+	return err;
+}
+
+/* called without aufs lock */
+int au_opts_parse(struct super_block *sb, char *str, struct au_opts *opts)
+{
+	int err, n, token;
+	aufs_bindex_t bindex;
+	unsigned char skipped;
+	struct dentry *root;
+	struct au_opt *opt, *opt_tail;
+	char *opt_str;
+	/* reduce the stack space */
+	union {
+		struct au_opt_xino_itrunc *xino_itrunc;
+		struct au_opt_wbr_create *create;
+	} u;
+	struct {
+		substring_t args[MAX_OPT_ARGS];
+	} *a;
+
+	err = -ENOMEM;
+	a = kmalloc(sizeof(*a), GFP_NOFS);
+	if (unlikely(!a))
+		goto out;
+
+	root = sb->s_root;
+	err = 0;
+	bindex = 0;
+	opt = opts->opt;
+	opt_tail = opt + opts->max_opt - 1;
+	opt->type = Opt_tail;
+	while (!err && (opt_str = strsep(&str, ",")) && *opt_str) {
+		err = -EINVAL;
+		skipped = 0;
+		token = match_token(opt_str, options, a->args);
+		switch (token) {
+		case Opt_br:
+			err = 0;
+			while (!err && (opt_str = strsep(&a->args[0].from, ":"))
+			       && *opt_str) {
+				err = opt_add(opt, opt_str, opts->sb_flags,
+					      bindex++);
+				if (unlikely(!err && ++opt > opt_tail)) {
+					err = -E2BIG;
+					break;
+				}
+				opt->type = Opt_tail;
+				skipped = 1;
+			}
+			break;
+		case Opt_add:
+			if (unlikely(match_int(&a->args[0], &n))) {
+				pr_err("bad integer in %s\n", opt_str);
+				break;
+			}
+			bindex = n;
+			err = opt_add(opt, a->args[1].from, opts->sb_flags,
+				      bindex);
+			if (!err)
+				opt->type = token;
+			break;
+		case Opt_append:
+			err = opt_add(opt, a->args[0].from, opts->sb_flags,
+				      /*dummy bindex*/1);
+			if (!err)
+				opt->type = token;
+			break;
+		case Opt_prepend:
+			err = opt_add(opt, a->args[0].from, opts->sb_flags,
+				      /*bindex*/0);
+			if (!err)
+				opt->type = token;
+			break;
+		case Opt_del:
+			err = au_opts_parse_del(&opt->del, a->args);
+			if (!err)
+				opt->type = token;
+			break;
+#if 0 /* reserved for future use */
+		case Opt_idel:
+			del->pathname = "(indexed)";
+			if (unlikely(match_int(&args[0], &n))) {
+				pr_err("bad integer in %s\n", opt_str);
+				break;
+			}
+			err = au_opts_parse_idel(sb, n, &opt->del, a->args);
+			if (!err)
+				opt->type = token;
+			break;
+#endif
+		case Opt_mod:
+			err = au_opts_parse_mod(&opt->mod, a->args);
+			if (!err)
+				opt->type = token;
+			break;
+#ifdef IMOD /* reserved for future use */
+		case Opt_imod:
+			u.mod->path = "(indexed)";
+			if (unlikely(match_int(&a->args[0], &n))) {
+				pr_err("bad integer in %s\n", opt_str);
+				break;
+			}
+			err = au_opts_parse_imod(sb, n, &opt->mod, a->args);
+			if (!err)
+				opt->type = token;
+			break;
+#endif
+		case Opt_xino:
+			err = au_opts_parse_xino(sb, &opt->xino, a->args);
+			if (!err)
+				opt->type = token;
+			break;
+
+		case Opt_trunc_xino_path:
+			err = au_opts_parse_xino_itrunc_path
+				(sb, &opt->xino_itrunc, a->args);
+			if (!err)
+				opt->type = token;
+			break;
+
+		case Opt_itrunc_xino:
+			u.xino_itrunc = &opt->xino_itrunc;
+			if (unlikely(match_int(&a->args[0], &n))) {
+				pr_err("bad integer in %s\n", opt_str);
+				break;
+			}
+			u.xino_itrunc->bindex = n;
+			aufs_read_lock(root, AuLock_FLUSH);
+			if (n < 0 || au_sbbot(sb) < n) {
+				pr_err("out of bounds, %d\n", n);
+				aufs_read_unlock(root, !AuLock_IR);
+				break;
+			}
+			aufs_read_unlock(root, !AuLock_IR);
+			err = 0;
+			opt->type = token;
+			break;
+
+		case Opt_dirwh:
+			if (unlikely(match_int(&a->args[0], &opt->dirwh)))
+				break;
+			err = 0;
+			opt->type = token;
+			break;
+
+		case Opt_rdcache:
+			if (unlikely(match_int(&a->args[0], &n))) {
+				pr_err("bad integer in %s\n", opt_str);
+				break;
+			}
+			if (unlikely(n > AUFS_RDCACHE_MAX)) {
+				pr_err("rdcache must be smaller than %d\n",
+				       AUFS_RDCACHE_MAX);
+				break;
+			}
+			opt->rdcache = n;
+			err = 0;
+			opt->type = token;
+			break;
+		case Opt_rdblk:
+			if (unlikely(match_int(&a->args[0], &n)
+				     || n < 0
+				     || n > KMALLOC_MAX_SIZE)) {
+				pr_err("bad integer in %s\n", opt_str);
+				break;
+			}
+			if (unlikely(n && n < NAME_MAX)) {
+				pr_err("rdblk must be larger than %d\n",
+				       NAME_MAX);
+				break;
+			}
+			opt->rdblk = n;
+			err = 0;
+			opt->type = token;
+			break;
+		case Opt_rdhash:
+			if (unlikely(match_int(&a->args[0], &n)
+				     || n < 0
+				     || n * sizeof(struct hlist_head)
+				     > KMALLOC_MAX_SIZE)) {
+				pr_err("bad integer in %s\n", opt_str);
+				break;
+			}
+			opt->rdhash = n;
+			err = 0;
+			opt->type = token;
+			break;
+
+		case Opt_trunc_xino:
+		case Opt_notrunc_xino:
+		case Opt_noxino:
+		case Opt_trunc_xib:
+		case Opt_notrunc_xib:
+		case Opt_shwh:
+		case Opt_noshwh:
+		case Opt_dirperm1:
+		case Opt_nodirperm1:
+		case Opt_plink:
+		case Opt_noplink:
+		case Opt_list_plink:
+		case Opt_dio:
+		case Opt_nodio:
+		case Opt_diropq_a:
+		case Opt_diropq_w:
+		case Opt_warn_perm:
+		case Opt_nowarn_perm:
+		case Opt_verbose:
+		case Opt_noverbose:
+		case Opt_sum:
+		case Opt_nosum:
+		case Opt_wsum:
+		case Opt_rdblk_def:
+		case Opt_rdhash_def:
+		case Opt_acl:
+		case Opt_noacl:
+			err = 0;
+			opt->type = token;
+			break;
+
+		case Opt_udba:
+			opt->udba = udba_val(a->args[0].from);
+			if (opt->udba >= 0) {
+				err = 0;
+				opt->type = token;
+			} else
+				pr_err("wrong value, %s\n", opt_str);
+			break;
+
+		case Opt_wbr_create:
+			u.create = &opt->wbr_create;
+			u.create->wbr_create
+				= au_wbr_create_val(a->args[0].from, u.create);
+			if (u.create->wbr_create >= 0) {
+				err = 0;
+				opt->type = token;
+			} else
+				pr_err("wrong value, %s\n", opt_str);
+			break;
+		case Opt_wbr_copyup:
+			opt->wbr_copyup = au_wbr_copyup_val(a->args[0].from);
+			if (opt->wbr_copyup >= 0) {
+				err = 0;
+				opt->type = token;
+			} else
+				pr_err("wrong value, %s\n", opt_str);
+			break;
+
+		case Opt_fhsm_sec:
+			if (unlikely(match_int(&a->args[0], &n)
+				     || n < 0)) {
+				pr_err("bad integer in %s\n", opt_str);
+				break;
+			}
+			if (sysaufs_brs) {
+				opt->fhsm_second = n;
+				opt->type = token;
+			} else
+				pr_warn("ignored %s\n", opt_str);
+			err = 0;
+			break;
+
+		case Opt_ignore:
+			pr_warn("ignored %s\n", opt_str);
+			/*FALLTHROUGH*/
+		case Opt_ignore_silent:
+			skipped = 1;
+			err = 0;
+			break;
+		case Opt_err:
+			pr_err("unknown option %s\n", opt_str);
+			break;
+		}
+
+		if (!err && !skipped) {
+			if (unlikely(++opt > opt_tail)) {
+				err = -E2BIG;
+				opt--;
+				opt->type = Opt_tail;
+				break;
+			}
+			opt->type = Opt_tail;
+		}
+	}
+
+	kfree(a);
+	dump_opts(opts);
+	if (unlikely(err))
+		au_opts_free(opts);
+
+out:
+	return err;
+}
+
+static int au_opt_wbr_create(struct super_block *sb,
+			     struct au_opt_wbr_create *create)
+{
+	int err;
+	struct au_sbinfo *sbinfo;
+
+	SiMustWriteLock(sb);
+
+	err = 1; /* handled */
+	sbinfo = au_sbi(sb);
+	if (sbinfo->si_wbr_create_ops->fin) {
+		err = sbinfo->si_wbr_create_ops->fin(sb);
+		if (!err)
+			err = 1;
+	}
+
+	sbinfo->si_wbr_create = create->wbr_create;
+	sbinfo->si_wbr_create_ops = au_wbr_create_ops + create->wbr_create;
+	switch (create->wbr_create) {
+	case AuWbrCreate_MFSRRV:
+	case AuWbrCreate_MFSRR:
+	case AuWbrCreate_TDMFS:
+	case AuWbrCreate_TDMFSV:
+	case AuWbrCreate_PMFSRR:
+	case AuWbrCreate_PMFSRRV:
+		sbinfo->si_wbr_mfs.mfsrr_watermark = create->mfsrr_watermark;
+		/*FALLTHROUGH*/
+	case AuWbrCreate_MFS:
+	case AuWbrCreate_MFSV:
+	case AuWbrCreate_PMFS:
+	case AuWbrCreate_PMFSV:
+		sbinfo->si_wbr_mfs.mfs_expire
+			= msecs_to_jiffies(create->mfs_second * MSEC_PER_SEC);
+		break;
+	}
+
+	if (sbinfo->si_wbr_create_ops->init)
+		sbinfo->si_wbr_create_ops->init(sb); /* ignore */
+
+	return err;
+}
+
+/*
+ * returns,
+ * plus: processed without an error
+ * zero: unprocessed
+ */
+static int au_opt_simple(struct super_block *sb, struct au_opt *opt,
+			 struct au_opts *opts)
+{
+	int err;
+	struct au_sbinfo *sbinfo;
+
+	SiMustWriteLock(sb);
+
+	err = 1; /* handled */
+	sbinfo = au_sbi(sb);
+	switch (opt->type) {
+	case Opt_udba:
+		sbinfo->si_mntflags &= ~AuOptMask_UDBA;
+		sbinfo->si_mntflags |= opt->udba;
+		opts->given_udba |= opt->udba;
+		break;
+
+	case Opt_plink:
+		au_opt_set(sbinfo->si_mntflags, PLINK);
+		break;
+	case Opt_noplink:
+		if (au_opt_test(sbinfo->si_mntflags, PLINK))
+			au_plink_put(sb, /*verbose*/1);
+		au_opt_clr(sbinfo->si_mntflags, PLINK);
+		break;
+	case Opt_list_plink:
+		if (au_opt_test(sbinfo->si_mntflags, PLINK))
+			au_plink_list(sb);
+		break;
+
+	case Opt_dio:
+		au_opt_set(sbinfo->si_mntflags, DIO);
+		au_fset_opts(opts->flags, REFRESH_DYAOP);
+		break;
+	case Opt_nodio:
+		au_opt_clr(sbinfo->si_mntflags, DIO);
+		au_fset_opts(opts->flags, REFRESH_DYAOP);
+		break;
+
+	case Opt_fhsm_sec:
+		au_fhsm_set(sbinfo, opt->fhsm_second);
+		break;
+
+	case Opt_diropq_a:
+		au_opt_set(sbinfo->si_mntflags, ALWAYS_DIROPQ);
+		break;
+	case Opt_diropq_w:
+		au_opt_clr(sbinfo->si_mntflags, ALWAYS_DIROPQ);
+		break;
+
+	case Opt_warn_perm:
+		au_opt_set(sbinfo->si_mntflags, WARN_PERM);
+		break;
+	case Opt_nowarn_perm:
+		au_opt_clr(sbinfo->si_mntflags, WARN_PERM);
+		break;
+
+	case Opt_verbose:
+		au_opt_set(sbinfo->si_mntflags, VERBOSE);
+		break;
+	case Opt_noverbose:
+		au_opt_clr(sbinfo->si_mntflags, VERBOSE);
+		break;
+
+	case Opt_sum:
+		au_opt_set(sbinfo->si_mntflags, SUM);
+		break;
+	case Opt_wsum:
+		au_opt_clr(sbinfo->si_mntflags, SUM);
+		au_opt_set(sbinfo->si_mntflags, SUM_W);
+	case Opt_nosum:
+		au_opt_clr(sbinfo->si_mntflags, SUM);
+		au_opt_clr(sbinfo->si_mntflags, SUM_W);
+		break;
+
+	case Opt_wbr_create:
+		err = au_opt_wbr_create(sb, &opt->wbr_create);
+		break;
+	case Opt_wbr_copyup:
+		sbinfo->si_wbr_copyup = opt->wbr_copyup;
+		sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + opt->wbr_copyup;
+		break;
+
+	case Opt_dirwh:
+		sbinfo->si_dirwh = opt->dirwh;
+		break;
+
+	case Opt_rdcache:
+		sbinfo->si_rdcache
+			= msecs_to_jiffies(opt->rdcache * MSEC_PER_SEC);
+		break;
+	case Opt_rdblk:
+		sbinfo->si_rdblk = opt->rdblk;
+		break;
+	case Opt_rdblk_def:
+		sbinfo->si_rdblk = AUFS_RDBLK_DEF;
+		break;
+	case Opt_rdhash:
+		sbinfo->si_rdhash = opt->rdhash;
+		break;
+	case Opt_rdhash_def:
+		sbinfo->si_rdhash = AUFS_RDHASH_DEF;
+		break;
+
+	case Opt_shwh:
+		au_opt_set(sbinfo->si_mntflags, SHWH);
+		break;
+	case Opt_noshwh:
+		au_opt_clr(sbinfo->si_mntflags, SHWH);
+		break;
+
+	case Opt_dirperm1:
+		au_opt_set(sbinfo->si_mntflags, DIRPERM1);
+		break;
+	case Opt_nodirperm1:
+		au_opt_clr(sbinfo->si_mntflags, DIRPERM1);
+		break;
+
+	case Opt_trunc_xino:
+		au_opt_set(sbinfo->si_mntflags, TRUNC_XINO);
+		break;
+	case Opt_notrunc_xino:
+		au_opt_clr(sbinfo->si_mntflags, TRUNC_XINO);
+		break;
+
+	case Opt_trunc_xino_path:
+	case Opt_itrunc_xino:
+		err = au_xino_trunc(sb, opt->xino_itrunc.bindex);
+		if (!err)
+			err = 1;
+		break;
+
+	case Opt_trunc_xib:
+		au_fset_opts(opts->flags, TRUNC_XIB);
+		break;
+	case Opt_notrunc_xib:
+		au_fclr_opts(opts->flags, TRUNC_XIB);
+		break;
+
+	case Opt_acl:
+		sb->s_flags |= MS_POSIXACL;
+		break;
+	case Opt_noacl:
+		sb->s_flags &= ~MS_POSIXACL;
+		break;
+
+	default:
+		err = 0;
+		break;
+	}
+
+	return err;
+}
+
+/*
+ * returns tri-state.
+ * plus: processed without an error
+ * zero: unprocessed
+ * minus: error
+ */
+static int au_opt_br(struct super_block *sb, struct au_opt *opt,
+		     struct au_opts *opts)
+{
+	int err, do_refresh;
+
+	err = 0;
+	switch (opt->type) {
+	case Opt_append:
+		opt->add.bindex = au_sbbot(sb) + 1;
+		if (opt->add.bindex < 0)
+			opt->add.bindex = 0;
+		goto add;
+	case Opt_prepend:
+		opt->add.bindex = 0;
+	add: /* indented label */
+	case Opt_add:
+		err = au_br_add(sb, &opt->add,
+				au_ftest_opts(opts->flags, REMOUNT));
+		if (!err) {
+			err = 1;
+			au_fset_opts(opts->flags, REFRESH);
+		}
+		break;
+
+	case Opt_del:
+	case Opt_idel:
+		err = au_br_del(sb, &opt->del,
+				au_ftest_opts(opts->flags, REMOUNT));
+		if (!err) {
+			err = 1;
+			au_fset_opts(opts->flags, TRUNC_XIB);
+			au_fset_opts(opts->flags, REFRESH);
+		}
+		break;
+
+	case Opt_mod:
+	case Opt_imod:
+		err = au_br_mod(sb, &opt->mod,
+				au_ftest_opts(opts->flags, REMOUNT),
+				&do_refresh);
+		if (!err) {
+			err = 1;
+			if (do_refresh)
+				au_fset_opts(opts->flags, REFRESH);
+		}
+		break;
+	}
+	return err;
+}
+
+static int au_opt_xino(struct super_block *sb, struct au_opt *opt,
+		       struct au_opt_xino **opt_xino,
+		       struct au_opts *opts)
+{
+	int err;
+	aufs_bindex_t bbot, bindex;
+	struct dentry *root, *parent, *h_root;
+
+	err = 0;
+	switch (opt->type) {
+	case Opt_xino:
+		err = au_xino_set(sb, &opt->xino,
+				  !!au_ftest_opts(opts->flags, REMOUNT));
+		if (unlikely(err))
+			break;
+
+		*opt_xino = &opt->xino;
+		au_xino_brid_set(sb, -1);
+
+		/* safe d_parent access */
+		parent = opt->xino.file->f_path.dentry->d_parent;
+		root = sb->s_root;
+		bbot = au_sbbot(sb);
+		for (bindex = 0; bindex <= bbot; bindex++) {
+			h_root = au_h_dptr(root, bindex);
+			if (h_root == parent) {
+				au_xino_brid_set(sb, au_sbr_id(sb, bindex));
+				break;
+			}
+		}
+		break;
+
+	case Opt_noxino:
+		au_xino_clr(sb);
+		au_xino_brid_set(sb, -1);
+		*opt_xino = (void *)-1;
+		break;
+	}
+
+	return err;
+}
+
+int au_opts_verify(struct super_block *sb, unsigned long sb_flags,
+		   unsigned int pending)
+{
+	int err, fhsm;
+	aufs_bindex_t bindex, bbot;
+	unsigned char do_plink, skip, do_free, can_no_dreval;
+	struct au_branch *br;
+	struct au_wbr *wbr;
+	struct dentry *root, *dentry;
+	struct inode *dir, *h_dir;
+	struct au_sbinfo *sbinfo;
+	struct au_hinode *hdir;
+
+	SiMustAnyLock(sb);
+
+	sbinfo = au_sbi(sb);
+	AuDebugOn(!(sbinfo->si_mntflags & AuOptMask_UDBA));
+
+	if (!(sb_flags & MS_RDONLY)) {
+		if (unlikely(!au_br_writable(au_sbr_perm(sb, 0))))
+			pr_warn("first branch should be rw\n");
+		if (unlikely(au_opt_test(sbinfo->si_mntflags, SHWH)))
+			pr_warn_once("shwh should be used with ro\n");
+	}
+
+	if (au_opt_test((sbinfo->si_mntflags | pending), UDBA_HNOTIFY)
+	    && !au_opt_test(sbinfo->si_mntflags, XINO))
+		pr_warn_once("udba=*notify requires xino\n");
+
+	if (au_opt_test(sbinfo->si_mntflags, DIRPERM1))
+		pr_warn_once("dirperm1 breaks the protection"
+			     " by the permission bits on the lower branch\n");
+
+	err = 0;
+	fhsm = 0;
+	root = sb->s_root;
+	dir = d_inode(root);
+	do_plink = !!au_opt_test(sbinfo->si_mntflags, PLINK);
+	can_no_dreval = !!au_opt_test((sbinfo->si_mntflags | pending),
+				      UDBA_NONE);
+	bbot = au_sbbot(sb);
+	for (bindex = 0; !err && bindex <= bbot; bindex++) {
+		skip = 0;
+		h_dir = au_h_iptr(dir, bindex);
+		br = au_sbr(sb, bindex);
+
+		if ((br->br_perm & AuBrAttr_ICEX)
+		    && !h_dir->i_op->listxattr)
+			br->br_perm &= ~AuBrAttr_ICEX;
+#if 0
+		if ((br->br_perm & AuBrAttr_ICEX_SEC)
+		    && (au_br_sb(br)->s_flags & MS_NOSEC))
+			br->br_perm &= ~AuBrAttr_ICEX_SEC;
+#endif
+
+		do_free = 0;
+		wbr = br->br_wbr;
+		if (wbr)
+			wbr_wh_read_lock(wbr);
+
+		if (!au_br_writable(br->br_perm)) {
+			do_free = !!wbr;
+			skip = (!wbr
+				|| (!wbr->wbr_whbase
+				    && !wbr->wbr_plink
+				    && !wbr->wbr_orph));
+		} else if (!au_br_wh_linkable(br->br_perm)) {
+			/* skip = (!br->br_whbase && !br->br_orph); */
+			skip = (!wbr || !wbr->wbr_whbase);
+			if (skip && wbr) {
+				if (do_plink)
+					skip = !!wbr->wbr_plink;
+				else
+					skip = !wbr->wbr_plink;
+			}
+		} else {
+			/* skip = (br->br_whbase && br->br_ohph); */
+			skip = (wbr && wbr->wbr_whbase);
+			if (skip) {
+				if (do_plink)
+					skip = !!wbr->wbr_plink;
+				else
+					skip = !wbr->wbr_plink;
+			}
+		}
+		if (wbr)
+			wbr_wh_read_unlock(wbr);
+
+		if (can_no_dreval) {
+			dentry = br->br_path.dentry;
+			spin_lock(&dentry->d_lock);
+			if (dentry->d_flags &
+			    (DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE))
+				can_no_dreval = 0;
+			spin_unlock(&dentry->d_lock);
+		}
+
+		if (au_br_fhsm(br->br_perm)) {
+			fhsm++;
+			AuDebugOn(!br->br_fhsm);
+		}
+
+		if (skip)
+			continue;
+
+		hdir = au_hi(dir, bindex);
+		au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT);
+		if (wbr)
+			wbr_wh_write_lock(wbr);
+		err = au_wh_init(br, sb);
+		if (wbr)
+			wbr_wh_write_unlock(wbr);
+		au_hn_inode_unlock(hdir);
+
+		if (!err && do_free) {
+			kfree(wbr);
+			br->br_wbr = NULL;
+		}
+	}
+
+	if (can_no_dreval)
+		au_fset_si(sbinfo, NO_DREVAL);
+	else
+		au_fclr_si(sbinfo, NO_DREVAL);
+
+	if (fhsm >= 2) {
+		au_fset_si(sbinfo, FHSM);
+		for (bindex = bbot; bindex >= 0; bindex--) {
+			br = au_sbr(sb, bindex);
+			if (au_br_fhsm(br->br_perm)) {
+				au_fhsm_set_bottom(sb, bindex);
+				break;
+			}
+		}
+	} else {
+		au_fclr_si(sbinfo, FHSM);
+		au_fhsm_set_bottom(sb, -1);
+	}
+
+	return err;
+}
+
+int au_opts_mount(struct super_block *sb, struct au_opts *opts)
+{
+	int err;
+	unsigned int tmp;
+	aufs_bindex_t bindex, bbot;
+	struct au_opt *opt;
+	struct au_opt_xino *opt_xino, xino;
+	struct au_sbinfo *sbinfo;
+	struct au_branch *br;
+	struct inode *dir;
+
+	SiMustWriteLock(sb);
+
+	err = 0;
+	opt_xino = NULL;
+	opt = opts->opt;
+	while (err >= 0 && opt->type != Opt_tail)
+		err = au_opt_simple(sb, opt++, opts);
+	if (err > 0)
+		err = 0;
+	else if (unlikely(err < 0))
+		goto out;
+
+	/* disable xino and udba temporary */
+	sbinfo = au_sbi(sb);
+	tmp = sbinfo->si_mntflags;
+	au_opt_clr(sbinfo->si_mntflags, XINO);
+	au_opt_set_udba(sbinfo->si_mntflags, UDBA_REVAL);
+
+	opt = opts->opt;
+	while (err >= 0 && opt->type != Opt_tail)
+		err = au_opt_br(sb, opt++, opts);
+	if (err > 0)
+		err = 0;
+	else if (unlikely(err < 0))
+		goto out;
+
+	bbot = au_sbbot(sb);
+	if (unlikely(bbot < 0)) {
+		err = -EINVAL;
+		pr_err("no branches\n");
+		goto out;
+	}
+
+	if (au_opt_test(tmp, XINO))
+		au_opt_set(sbinfo->si_mntflags, XINO);
+	opt = opts->opt;
+	while (!err && opt->type != Opt_tail)
+		err = au_opt_xino(sb, opt++, &opt_xino, opts);
+	if (unlikely(err))
+		goto out;
+
+	err = au_opts_verify(sb, sb->s_flags, tmp);
+	if (unlikely(err))
+		goto out;
+
+	/* restore xino */
+	if (au_opt_test(tmp, XINO) && !opt_xino) {
+		xino.file = au_xino_def(sb);
+		err = PTR_ERR(xino.file);
+		if (IS_ERR(xino.file))
+			goto out;
+
+		err = au_xino_set(sb, &xino, /*remount*/0);
+		fput(xino.file);
+		if (unlikely(err))
+			goto out;
+	}
+
+	/* restore udba */
+	tmp &= AuOptMask_UDBA;
+	sbinfo->si_mntflags &= ~AuOptMask_UDBA;
+	sbinfo->si_mntflags |= tmp;
+	bbot = au_sbbot(sb);
+	for (bindex = 0; bindex <= bbot; bindex++) {
+		br = au_sbr(sb, bindex);
+		err = au_hnotify_reset_br(tmp, br, br->br_perm);
+		if (unlikely(err))
+			AuIOErr("hnotify failed on br %d, %d, ignored\n",
+				bindex, err);
+		/* go on even if err */
+	}
+	if (au_opt_test(tmp, UDBA_HNOTIFY)) {
+		dir = d_inode(sb->s_root);
+		au_hn_reset(dir, au_hi_flags(dir, /*isdir*/1) & ~AuHi_XINO);
+	}
+
+out:
+	return err;
+}
+
+int au_opts_remount(struct super_block *sb, struct au_opts *opts)
+{
+	int err, rerr;
+	unsigned char no_dreval;
+	struct inode *dir;
+	struct au_opt_xino *opt_xino;
+	struct au_opt *opt;
+	struct au_sbinfo *sbinfo;
+
+	SiMustWriteLock(sb);
+
+	err = 0;
+	dir = d_inode(sb->s_root);
+	sbinfo = au_sbi(sb);
+	opt_xino = NULL;
+	opt = opts->opt;
+	while (err >= 0 && opt->type != Opt_tail) {
+		err = au_opt_simple(sb, opt, opts);
+		if (!err)
+			err = au_opt_br(sb, opt, opts);
+		if (!err)
+			err = au_opt_xino(sb, opt, &opt_xino, opts);
+		opt++;
+	}
+	if (err > 0)
+		err = 0;
+	AuTraceErr(err);
+	/* go on even err */
+
+	no_dreval = !!au_ftest_si(sbinfo, NO_DREVAL);
+	rerr = au_opts_verify(sb, opts->sb_flags, /*pending*/0);
+	if (unlikely(rerr && !err))
+		err = rerr;
+
+	if (no_dreval != !!au_ftest_si(sbinfo, NO_DREVAL))
+		au_fset_opts(opts->flags, REFRESH_IDOP);
+
+	if (au_ftest_opts(opts->flags, TRUNC_XIB)) {
+		rerr = au_xib_trunc(sb);
+		if (unlikely(rerr && !err))
+			err = rerr;
+	}
+
+	/* will be handled by the caller */
+	if (!au_ftest_opts(opts->flags, REFRESH)
+	    && (opts->given_udba
+		|| au_opt_test(sbinfo->si_mntflags, XINO)
+		|| au_ftest_opts(opts->flags, REFRESH_IDOP)
+		    ))
+		au_fset_opts(opts->flags, REFRESH);
+
+	AuDbg("status 0x%x\n", opts->flags);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+unsigned int au_opt_udba(struct super_block *sb)
+{
+	return au_mntflags(sb) & AuOptMask_UDBA;
+}
diff --git a/fs/aufs/opts.h b/fs/aufs/opts.h
new file mode 100644
index 000000000000..c156995a9bb8
--- /dev/null
+++ b/fs/aufs/opts.h
@@ -0,0 +1,213 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * mount options/flags
+ */
+
+#ifndef __AUFS_OPTS_H__
+#define __AUFS_OPTS_H__
+
+#ifdef __KERNEL__
+
+#include <linux/path.h>
+
+struct file;
+
+/* ---------------------------------------------------------------------- */
+
+/* mount flags */
+#define AuOpt_XINO		1		/* external inode number bitmap
+						   and translation table */
+#define AuOpt_TRUNC_XINO	(1 << 1)	/* truncate xino files */
+#define AuOpt_UDBA_NONE		(1 << 2)	/* users direct branch access */
+#define AuOpt_UDBA_REVAL	(1 << 3)
+#define AuOpt_UDBA_HNOTIFY	(1 << 4)
+#define AuOpt_SHWH		(1 << 5)	/* show whiteout */
+#define AuOpt_PLINK		(1 << 6)	/* pseudo-link */
+#define AuOpt_DIRPERM1		(1 << 7)	/* ignore the lower dir's perm
+						   bits */
+#define AuOpt_ALWAYS_DIROPQ	(1 << 9)	/* policy to creating diropq */
+#define AuOpt_SUM		(1 << 10)	/* summation for statfs(2) */
+#define AuOpt_SUM_W		(1 << 11)	/* unimplemented */
+#define AuOpt_WARN_PERM		(1 << 12)	/* warn when add-branch */
+#define AuOpt_VERBOSE		(1 << 13)	/* busy inode when del-branch */
+#define AuOpt_DIO		(1 << 14)	/* direct io */
+
+#ifndef CONFIG_AUFS_HNOTIFY
+#undef AuOpt_UDBA_HNOTIFY
+#define AuOpt_UDBA_HNOTIFY	0
+#endif
+#ifndef CONFIG_AUFS_SHWH
+#undef AuOpt_SHWH
+#define AuOpt_SHWH		0
+#endif
+
+#define AuOpt_Def	(AuOpt_XINO \
+			 | AuOpt_UDBA_REVAL \
+			 | AuOpt_PLINK \
+			 /* | AuOpt_DIRPERM1 */ \
+			 | AuOpt_WARN_PERM)
+#define AuOptMask_UDBA	(AuOpt_UDBA_NONE \
+			 | AuOpt_UDBA_REVAL \
+			 | AuOpt_UDBA_HNOTIFY)
+
+#define au_opt_test(flags, name)	(flags & AuOpt_##name)
+#define au_opt_set(flags, name) do { \
+	BUILD_BUG_ON(AuOpt_##name & AuOptMask_UDBA); \
+	((flags) |= AuOpt_##name); \
+} while (0)
+#define au_opt_set_udba(flags, name) do { \
+	(flags) &= ~AuOptMask_UDBA; \
+	((flags) |= AuOpt_##name); \
+} while (0)
+#define au_opt_clr(flags, name) do { \
+	((flags) &= ~AuOpt_##name); \
+} while (0)
+
+static inline unsigned int au_opts_plink(unsigned int mntflags)
+{
+#ifdef CONFIG_PROC_FS
+	return mntflags;
+#else
+	return mntflags & ~AuOpt_PLINK;
+#endif
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* policies to select one among multiple writable branches */
+enum {
+	AuWbrCreate_TDP,	/* top down parent */
+	AuWbrCreate_RR,		/* round robin */
+	AuWbrCreate_MFS,	/* most free space */
+	AuWbrCreate_MFSV,	/* mfs with seconds */
+	AuWbrCreate_MFSRR,	/* mfs then rr */
+	AuWbrCreate_MFSRRV,	/* mfs then rr with seconds */
+	AuWbrCreate_TDMFS,	/* top down regardless parent and mfs */
+	AuWbrCreate_TDMFSV,	/* top down regardless parent and mfs */
+	AuWbrCreate_PMFS,	/* parent and mfs */
+	AuWbrCreate_PMFSV,	/* parent and mfs with seconds */
+	AuWbrCreate_PMFSRR,	/* parent, mfs and round-robin */
+	AuWbrCreate_PMFSRRV,	/* plus seconds */
+
+	AuWbrCreate_Def = AuWbrCreate_TDP
+};
+
+enum {
+	AuWbrCopyup_TDP,	/* top down parent */
+	AuWbrCopyup_BUP,	/* bottom up parent */
+	AuWbrCopyup_BU,		/* bottom up */
+
+	AuWbrCopyup_Def = AuWbrCopyup_TDP
+};
+
+/* ---------------------------------------------------------------------- */
+
+struct au_opt_add {
+	aufs_bindex_t	bindex;
+	char		*pathname;
+	int		perm;
+	struct path	path;
+};
+
+struct au_opt_del {
+	char		*pathname;
+	struct path	h_path;
+};
+
+struct au_opt_mod {
+	char		*path;
+	int		perm;
+	struct dentry	*h_root;
+};
+
+struct au_opt_xino {
+	char		*path;
+	struct file	*file;
+};
+
+struct au_opt_xino_itrunc {
+	aufs_bindex_t	bindex;
+};
+
+struct au_opt_wbr_create {
+	int			wbr_create;
+	int			mfs_second;
+	unsigned long long	mfsrr_watermark;
+};
+
+struct au_opt {
+	int type;
+	union {
+		struct au_opt_xino	xino;
+		struct au_opt_xino_itrunc xino_itrunc;
+		struct au_opt_add	add;
+		struct au_opt_del	del;
+		struct au_opt_mod	mod;
+		int			dirwh;
+		int			rdcache;
+		unsigned int		rdblk;
+		unsigned int		rdhash;
+		int			udba;
+		struct au_opt_wbr_create wbr_create;
+		int			wbr_copyup;
+		unsigned int		fhsm_second;
+	};
+};
+
+/* opts flags */
+#define AuOpts_REMOUNT		1
+#define AuOpts_REFRESH		(1 << 1)
+#define AuOpts_TRUNC_XIB	(1 << 2)
+#define AuOpts_REFRESH_DYAOP	(1 << 3)
+#define AuOpts_REFRESH_IDOP	(1 << 4)
+#define au_ftest_opts(flags, name)	((flags) & AuOpts_##name)
+#define au_fset_opts(flags, name) \
+	do { (flags) |= AuOpts_##name; } while (0)
+#define au_fclr_opts(flags, name) \
+	do { (flags) &= ~AuOpts_##name; } while (0)
+
+struct au_opts {
+	struct au_opt	*opt;
+	int		max_opt;
+
+	unsigned int	given_udba;
+	unsigned int	flags;
+	unsigned long	sb_flags;
+};
+
+/* ---------------------------------------------------------------------- */
+
+/* opts.c */
+void au_optstr_br_perm(au_br_perm_str_t *str, int perm);
+const char *au_optstr_udba(int udba);
+const char *au_optstr_wbr_copyup(int wbr_copyup);
+const char *au_optstr_wbr_create(int wbr_create);
+
+void au_opts_free(struct au_opts *opts);
+struct super_block;
+int au_opts_parse(struct super_block *sb, char *str, struct au_opts *opts);
+int au_opts_verify(struct super_block *sb, unsigned long sb_flags,
+		   unsigned int pending);
+int au_opts_mount(struct super_block *sb, struct au_opts *opts);
+int au_opts_remount(struct super_block *sb, struct au_opts *opts);
+
+unsigned int au_opt_udba(struct super_block *sb);
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_OPTS_H__ */
diff --git a/fs/aufs/plink.c b/fs/aufs/plink.c
new file mode 100644
index 000000000000..5fde5211e557
--- /dev/null
+++ b/fs/aufs/plink.c
@@ -0,0 +1,514 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * pseudo-link
+ */
+
+#include "aufs.h"
+
+/*
+ * the pseudo-link maintenance mode.
+ * during a user process maintains the pseudo-links,
+ * prohibit adding a new plink and branch manipulation.
+ *
+ * Flags
+ * NOPLM:
+ *	For entry functions which will handle plink, and i_mutex is already held
+ *	in VFS.
+ *	They cannot wait and should return an error at once.
+ *	Callers has to check the error.
+ * NOPLMW:
+ *	For entry functions which will handle plink, but i_mutex is not held
+ *	in VFS.
+ *	They can wait the plink maintenance mode to finish.
+ *
+ * They behave like F_SETLK and F_SETLKW.
+ * If the caller never handle plink, then both flags are unnecessary.
+ */
+
+int au_plink_maint(struct super_block *sb, int flags)
+{
+	int err;
+	pid_t pid, ppid;
+	struct task_struct *parent, *prev;
+	struct au_sbinfo *sbi;
+
+	SiMustAnyLock(sb);
+
+	err = 0;
+	if (!au_opt_test(au_mntflags(sb), PLINK))
+		goto out;
+
+	sbi = au_sbi(sb);
+	pid = sbi->si_plink_maint_pid;
+	if (!pid || pid == current->pid)
+		goto out;
+
+	/* todo: it highly depends upon /sbin/mount.aufs */
+	prev = NULL;
+	parent = current;
+	ppid = 0;
+	rcu_read_lock();
+	while (1) {
+		parent = rcu_dereference(parent->real_parent);
+		if (parent == prev)
+			break;
+		ppid = task_pid_vnr(parent);
+		if (pid == ppid) {
+			rcu_read_unlock();
+			goto out;
+		}
+		prev = parent;
+	}
+	rcu_read_unlock();
+
+	if (au_ftest_lock(flags, NOPLMW)) {
+		/* if there is no i_mutex lock in VFS, we don't need to wait */
+		/* AuDebugOn(!lockdep_depth(current)); */
+		while (sbi->si_plink_maint_pid) {
+			si_read_unlock(sb);
+			/* gave up wake_up_bit() */
+			wait_event(sbi->si_plink_wq, !sbi->si_plink_maint_pid);
+
+			if (au_ftest_lock(flags, FLUSH))
+				au_nwt_flush(&sbi->si_nowait);
+			si_noflush_read_lock(sb);
+		}
+	} else if (au_ftest_lock(flags, NOPLM)) {
+		AuDbg("ppid %d, pid %d\n", ppid, pid);
+		err = -EAGAIN;
+	}
+
+out:
+	return err;
+}
+
+void au_plink_maint_leave(struct au_sbinfo *sbinfo)
+{
+	spin_lock(&sbinfo->si_plink_maint_lock);
+	sbinfo->si_plink_maint_pid = 0;
+	spin_unlock(&sbinfo->si_plink_maint_lock);
+	wake_up_all(&sbinfo->si_plink_wq);
+}
+
+int au_plink_maint_enter(struct super_block *sb)
+{
+	int err;
+	struct au_sbinfo *sbinfo;
+
+	err = 0;
+	sbinfo = au_sbi(sb);
+	/* make sure i am the only one in this fs */
+	si_write_lock(sb, AuLock_FLUSH);
+	if (au_opt_test(au_mntflags(sb), PLINK)) {
+		spin_lock(&sbinfo->si_plink_maint_lock);
+		if (!sbinfo->si_plink_maint_pid)
+			sbinfo->si_plink_maint_pid = current->pid;
+		else
+			err = -EBUSY;
+		spin_unlock(&sbinfo->si_plink_maint_lock);
+	}
+	si_write_unlock(sb);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+#ifdef CONFIG_AUFS_DEBUG
+void au_plink_list(struct super_block *sb)
+{
+	int i;
+	struct au_sbinfo *sbinfo;
+	struct hlist_head *plink_hlist;
+	struct au_icntnr *icntnr;
+
+	SiMustAnyLock(sb);
+
+	sbinfo = au_sbi(sb);
+	AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK));
+	AuDebugOn(au_plink_maint(sb, AuLock_NOPLM));
+
+	for (i = 0; i < AuPlink_NHASH; i++) {
+		plink_hlist = &sbinfo->si_plink[i].head;
+		rcu_read_lock();
+		hlist_for_each_entry_rcu(icntnr, plink_hlist, plink)
+			AuDbg("%lu\n", icntnr->vfs_inode.i_ino);
+		rcu_read_unlock();
+	}
+}
+#endif
+
+/* is the inode pseudo-linked? */
+int au_plink_test(struct inode *inode)
+{
+	int found, i;
+	struct au_sbinfo *sbinfo;
+	struct hlist_head *plink_hlist;
+	struct au_icntnr *icntnr;
+
+	sbinfo = au_sbi(inode->i_sb);
+	AuRwMustAnyLock(&sbinfo->si_rwsem);
+	AuDebugOn(!au_opt_test(au_mntflags(inode->i_sb), PLINK));
+	AuDebugOn(au_plink_maint(inode->i_sb, AuLock_NOPLM));
+
+	found = 0;
+	i = au_plink_hash(inode->i_ino);
+	plink_hlist = &sbinfo->si_plink[i].head;
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(icntnr, plink_hlist, plink)
+		if (&icntnr->vfs_inode == inode) {
+			found = 1;
+			break;
+		}
+	rcu_read_unlock();
+	return found;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * generate a name for plink.
+ * the file will be stored under AUFS_WH_PLINKDIR.
+ */
+/* 20 is max digits length of ulong 64 */
+#define PLINK_NAME_LEN	((20 + 1) * 2)
+
+static int plink_name(char *name, int len, struct inode *inode,
+		      aufs_bindex_t bindex)
+{
+	int rlen;
+	struct inode *h_inode;
+
+	h_inode = au_h_iptr(inode, bindex);
+	rlen = snprintf(name, len, "%lu.%lu", inode->i_ino, h_inode->i_ino);
+	return rlen;
+}
+
+struct au_do_plink_lkup_args {
+	struct dentry **errp;
+	struct qstr *tgtname;
+	struct dentry *h_parent;
+	struct au_branch *br;
+};
+
+static struct dentry *au_do_plink_lkup(struct qstr *tgtname,
+				       struct dentry *h_parent,
+				       struct au_branch *br)
+{
+	struct dentry *h_dentry;
+	struct inode *h_inode;
+
+	h_inode = d_inode(h_parent);
+	vfsub_inode_lock_shared_nested(h_inode, AuLsc_I_CHILD2);
+	h_dentry = vfsub_lkup_one(tgtname, h_parent);
+	inode_unlock_shared(h_inode);
+	return h_dentry;
+}
+
+static void au_call_do_plink_lkup(void *args)
+{
+	struct au_do_plink_lkup_args *a = args;
+	*a->errp = au_do_plink_lkup(a->tgtname, a->h_parent, a->br);
+}
+
+/* lookup the plink-ed @inode under the branch at @bindex */
+struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex)
+{
+	struct dentry *h_dentry, *h_parent;
+	struct au_branch *br;
+	int wkq_err;
+	char a[PLINK_NAME_LEN];
+	struct qstr tgtname = QSTR_INIT(a, 0);
+
+	AuDebugOn(au_plink_maint(inode->i_sb, AuLock_NOPLM));
+
+	br = au_sbr(inode->i_sb, bindex);
+	h_parent = br->br_wbr->wbr_plink;
+	tgtname.len = plink_name(a, sizeof(a), inode, bindex);
+
+	if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) {
+		struct au_do_plink_lkup_args args = {
+			.errp		= &h_dentry,
+			.tgtname	= &tgtname,
+			.h_parent	= h_parent,
+			.br		= br
+		};
+
+		wkq_err = au_wkq_wait(au_call_do_plink_lkup, &args);
+		if (unlikely(wkq_err))
+			h_dentry = ERR_PTR(wkq_err);
+	} else
+		h_dentry = au_do_plink_lkup(&tgtname, h_parent, br);
+
+	return h_dentry;
+}
+
+/* create a pseudo-link */
+static int do_whplink(struct qstr *tgt, struct dentry *h_parent,
+		      struct dentry *h_dentry, struct au_branch *br)
+{
+	int err;
+	struct path h_path = {
+		.mnt = au_br_mnt(br)
+	};
+	struct inode *h_dir, *delegated;
+
+	h_dir = d_inode(h_parent);
+	inode_lock_nested(h_dir, AuLsc_I_CHILD2);
+again:
+	h_path.dentry = vfsub_lkup_one(tgt, h_parent);
+	err = PTR_ERR(h_path.dentry);
+	if (IS_ERR(h_path.dentry))
+		goto out;
+
+	err = 0;
+	/* wh.plink dir is not monitored */
+	/* todo: is it really safe? */
+	if (d_is_positive(h_path.dentry)
+	    && d_inode(h_path.dentry) != d_inode(h_dentry)) {
+		delegated = NULL;
+		err = vfsub_unlink(h_dir, &h_path, &delegated, /*force*/0);
+		if (unlikely(err == -EWOULDBLOCK)) {
+			pr_warn("cannot retry for NFSv4 delegation"
+				" for an internal unlink\n");
+			iput(delegated);
+		}
+		dput(h_path.dentry);
+		h_path.dentry = NULL;
+		if (!err)
+			goto again;
+	}
+	if (!err && d_is_negative(h_path.dentry)) {
+		delegated = NULL;
+		err = vfsub_link(h_dentry, h_dir, &h_path, &delegated);
+		if (unlikely(err == -EWOULDBLOCK)) {
+			pr_warn("cannot retry for NFSv4 delegation"
+				" for an internal link\n");
+			iput(delegated);
+		}
+	}
+	dput(h_path.dentry);
+
+out:
+	inode_unlock(h_dir);
+	return err;
+}
+
+struct do_whplink_args {
+	int *errp;
+	struct qstr *tgt;
+	struct dentry *h_parent;
+	struct dentry *h_dentry;
+	struct au_branch *br;
+};
+
+static void call_do_whplink(void *args)
+{
+	struct do_whplink_args *a = args;
+	*a->errp = do_whplink(a->tgt, a->h_parent, a->h_dentry, a->br);
+}
+
+static int whplink(struct dentry *h_dentry, struct inode *inode,
+		   aufs_bindex_t bindex, struct au_branch *br)
+{
+	int err, wkq_err;
+	struct au_wbr *wbr;
+	struct dentry *h_parent;
+	char a[PLINK_NAME_LEN];
+	struct qstr tgtname = QSTR_INIT(a, 0);
+
+	wbr = au_sbr(inode->i_sb, bindex)->br_wbr;
+	h_parent = wbr->wbr_plink;
+	tgtname.len = plink_name(a, sizeof(a), inode, bindex);
+
+	/* always superio. */
+	if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) {
+		struct do_whplink_args args = {
+			.errp		= &err,
+			.tgt		= &tgtname,
+			.h_parent	= h_parent,
+			.h_dentry	= h_dentry,
+			.br		= br
+		};
+		wkq_err = au_wkq_wait(call_do_whplink, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+	} else
+		err = do_whplink(&tgtname, h_parent, h_dentry, br);
+
+	return err;
+}
+
+/*
+ * create a new pseudo-link for @h_dentry on @bindex.
+ * the linked inode is held in aufs @inode.
+ */
+void au_plink_append(struct inode *inode, aufs_bindex_t bindex,
+		     struct dentry *h_dentry)
+{
+	struct super_block *sb;
+	struct au_sbinfo *sbinfo;
+	struct hlist_head *plink_hlist;
+	struct au_icntnr *icntnr;
+	struct au_sphlhead *sphl;
+	int found, err, cnt, i;
+
+	sb = inode->i_sb;
+	sbinfo = au_sbi(sb);
+	AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK));
+	AuDebugOn(au_plink_maint(sb, AuLock_NOPLM));
+
+	found = au_plink_test(inode);
+	if (found)
+		return;
+
+	i = au_plink_hash(inode->i_ino);
+	sphl = sbinfo->si_plink + i;
+	plink_hlist = &sphl->head;
+	au_igrab(inode);
+
+	spin_lock(&sphl->spin);
+	hlist_for_each_entry(icntnr, plink_hlist, plink) {
+		if (&icntnr->vfs_inode == inode) {
+			found = 1;
+			break;
+		}
+	}
+	if (!found) {
+		icntnr = container_of(inode, struct au_icntnr, vfs_inode);
+		hlist_add_head_rcu(&icntnr->plink, plink_hlist);
+	}
+	spin_unlock(&sphl->spin);
+	if (!found) {
+		cnt = au_sphl_count(sphl);
+#define msg "unexpectedly unblanced or too many pseudo-links"
+		if (cnt > AUFS_PLINK_WARN)
+			AuWarn1(msg ", %d\n", cnt);
+#undef msg
+		err = whplink(h_dentry, inode, bindex, au_sbr(sb, bindex));
+		if (unlikely(err)) {
+			pr_warn("err %d, damaged pseudo link.\n", err);
+			au_sphl_del_rcu(&icntnr->plink, sphl);
+			iput(&icntnr->vfs_inode);
+		}
+	} else
+		iput(&icntnr->vfs_inode);
+}
+
+/* free all plinks */
+void au_plink_put(struct super_block *sb, int verbose)
+{
+	int i, warned;
+	struct au_sbinfo *sbinfo;
+	struct hlist_head *plink_hlist;
+	struct hlist_node *tmp;
+	struct au_icntnr *icntnr;
+
+	SiMustWriteLock(sb);
+
+	sbinfo = au_sbi(sb);
+	AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK));
+	AuDebugOn(au_plink_maint(sb, AuLock_NOPLM));
+
+	/* no spin_lock since sbinfo is write-locked */
+	warned = 0;
+	for (i = 0; i < AuPlink_NHASH; i++) {
+		plink_hlist = &sbinfo->si_plink[i].head;
+		if (!warned && verbose && !hlist_empty(plink_hlist)) {
+			pr_warn("pseudo-link is not flushed");
+			warned = 1;
+		}
+		hlist_for_each_entry_safe(icntnr, tmp, plink_hlist, plink)
+			iput(&icntnr->vfs_inode);
+		INIT_HLIST_HEAD(plink_hlist);
+	}
+}
+
+void au_plink_clean(struct super_block *sb, int verbose)
+{
+	struct dentry *root;
+
+	root = sb->s_root;
+	aufs_write_lock(root);
+	if (au_opt_test(au_mntflags(sb), PLINK))
+		au_plink_put(sb, verbose);
+	aufs_write_unlock(root);
+}
+
+static int au_plink_do_half_refresh(struct inode *inode, aufs_bindex_t br_id)
+{
+	int do_put;
+	aufs_bindex_t btop, bbot, bindex;
+
+	do_put = 0;
+	btop = au_ibtop(inode);
+	bbot = au_ibbot(inode);
+	if (btop >= 0) {
+		for (bindex = btop; bindex <= bbot; bindex++) {
+			if (!au_h_iptr(inode, bindex)
+			    || au_ii_br_id(inode, bindex) != br_id)
+				continue;
+			au_set_h_iptr(inode, bindex, NULL, 0);
+			do_put = 1;
+			break;
+		}
+		if (do_put)
+			for (bindex = btop; bindex <= bbot; bindex++)
+				if (au_h_iptr(inode, bindex)) {
+					do_put = 0;
+					break;
+				}
+	} else
+		do_put = 1;
+
+	return do_put;
+}
+
+/* free the plinks on a branch specified by @br_id */
+void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id)
+{
+	struct au_sbinfo *sbinfo;
+	struct hlist_head *plink_hlist;
+	struct hlist_node *tmp;
+	struct au_icntnr *icntnr;
+	struct inode *inode;
+	int i, do_put;
+
+	SiMustWriteLock(sb);
+
+	sbinfo = au_sbi(sb);
+	AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK));
+	AuDebugOn(au_plink_maint(sb, AuLock_NOPLM));
+
+	/* no spin_lock since sbinfo is write-locked */
+	for (i = 0; i < AuPlink_NHASH; i++) {
+		plink_hlist = &sbinfo->si_plink[i].head;
+		hlist_for_each_entry_safe(icntnr, tmp, plink_hlist, plink) {
+			inode = au_igrab(&icntnr->vfs_inode);
+			ii_write_lock_child(inode);
+			do_put = au_plink_do_half_refresh(inode, br_id);
+			if (do_put) {
+				hlist_del(&icntnr->plink);
+				iput(inode);
+			}
+			ii_write_unlock(inode);
+			iput(inode);
+		}
+	}
+}
diff --git a/fs/aufs/poll.c b/fs/aufs/poll.c
new file mode 100644
index 000000000000..1aea1948fd39
--- /dev/null
+++ b/fs/aufs/poll.c
@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * poll operation
+ * There is only one filesystem which implements ->poll operation, currently.
+ */
+
+#include "aufs.h"
+
+unsigned int aufs_poll(struct file *file, poll_table *wait)
+{
+	unsigned int mask;
+	int err;
+	struct file *h_file;
+	struct super_block *sb;
+
+	/* We should pretend an error happened. */
+	mask = POLLERR /* | POLLIN | POLLOUT */;
+	sb = file->f_path.dentry->d_sb;
+	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
+	h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
+	err = PTR_ERR(h_file);
+	if (IS_ERR(h_file))
+		goto out;
+
+	/* it is not an error if h_file has no operation */
+	mask = DEFAULT_POLLMASK;
+	if (h_file->f_op->poll)
+		mask = h_file->f_op->poll(h_file, wait);
+	fput(h_file); /* instead of au_read_post() */
+
+out:
+	si_read_unlock(sb);
+	AuTraceErr((int)mask);
+	return mask;
+}
diff --git a/fs/aufs/posix_acl.c b/fs/aufs/posix_acl.c
new file mode 100644
index 000000000000..816a47c7df84
--- /dev/null
+++ b/fs/aufs/posix_acl.c
@@ -0,0 +1,102 @@
+/*
+ * Copyright (C) 2014-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * posix acl operations
+ */
+
+#include <linux/fs.h>
+#include "aufs.h"
+
+struct posix_acl *aufs_get_acl(struct inode *inode, int type)
+{
+	struct posix_acl *acl;
+	int err;
+	aufs_bindex_t bindex;
+	struct inode *h_inode;
+	struct super_block *sb;
+
+	acl = NULL;
+	sb = inode->i_sb;
+	si_read_lock(sb, AuLock_FLUSH);
+	ii_read_lock_child(inode);
+	if (!(sb->s_flags & MS_POSIXACL))
+		goto out;
+
+	bindex = au_ibtop(inode);
+	h_inode = au_h_iptr(inode, bindex);
+	if (unlikely(!h_inode
+		     || ((h_inode->i_mode & S_IFMT)
+			 != (inode->i_mode & S_IFMT)))) {
+		err = au_busy_or_stale();
+		acl = ERR_PTR(err);
+		goto out;
+	}
+
+	/* always topmost only */
+	acl = get_acl(h_inode, type);
+	if (!IS_ERR_OR_NULL(acl))
+		set_cached_acl(inode, type, acl);
+
+out:
+	ii_read_unlock(inode);
+	si_read_unlock(sb);
+
+	AuTraceErrPtr(acl);
+	return acl;
+}
+
+int aufs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+	int err;
+	ssize_t ssz;
+	struct dentry *dentry;
+	struct au_sxattr arg = {
+		.type = AU_ACL_SET,
+		.u.acl_set = {
+			.acl	= acl,
+			.type	= type
+		},
+	};
+
+	IMustLock(inode);
+
+	if (inode->i_ino == AUFS_ROOT_INO)
+		dentry = dget(inode->i_sb->s_root);
+	else {
+		dentry = d_find_alias(inode);
+		if (!dentry)
+			dentry = d_find_any_alias(inode);
+		if (!dentry) {
+			pr_warn("cannot handle this inode, "
+				"please report to aufs-users ML\n");
+			err = -ENOENT;
+			goto out;
+		}
+	}
+
+	ssz = au_sxattr(dentry, inode, &arg);
+	dput(dentry);
+	err = ssz;
+	if (ssz >= 0) {
+		err = 0;
+		set_cached_acl(inode, type, acl);
+	}
+
+out:
+	return err;
+}
diff --git a/fs/aufs/procfs.c b/fs/aufs/procfs.c
new file mode 100644
index 000000000000..b94c0038c0e0
--- /dev/null
+++ b/fs/aufs/procfs.c
@@ -0,0 +1,169 @@
+/*
+ * Copyright (C) 2010-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * procfs interfaces
+ */
+
+#include <linux/proc_fs.h>
+#include "aufs.h"
+
+static int au_procfs_plm_release(struct inode *inode, struct file *file)
+{
+	struct au_sbinfo *sbinfo;
+
+	sbinfo = file->private_data;
+	if (sbinfo) {
+		au_plink_maint_leave(sbinfo);
+		kobject_put(&sbinfo->si_kobj);
+	}
+
+	return 0;
+}
+
+static void au_procfs_plm_write_clean(struct file *file)
+{
+	struct au_sbinfo *sbinfo;
+
+	sbinfo = file->private_data;
+	if (sbinfo)
+		au_plink_clean(sbinfo->si_sb, /*verbose*/0);
+}
+
+static int au_procfs_plm_write_si(struct file *file, unsigned long id)
+{
+	int err;
+	struct super_block *sb;
+	struct au_sbinfo *sbinfo;
+
+	err = -EBUSY;
+	if (unlikely(file->private_data))
+		goto out;
+
+	sb = NULL;
+	/* don't use au_sbilist_lock() here */
+	spin_lock(&au_sbilist.spin);
+	hlist_for_each_entry(sbinfo, &au_sbilist.head, si_list)
+		if (id == sysaufs_si_id(sbinfo)) {
+			kobject_get(&sbinfo->si_kobj);
+			sb = sbinfo->si_sb;
+			break;
+		}
+	spin_unlock(&au_sbilist.spin);
+
+	err = -EINVAL;
+	if (unlikely(!sb))
+		goto out;
+
+	err = au_plink_maint_enter(sb);
+	if (!err)
+		/* keep kobject_get() */
+		file->private_data = sbinfo;
+	else
+		kobject_put(&sbinfo->si_kobj);
+out:
+	return err;
+}
+
+/*
+ * Accept a valid "si=xxxx" only.
+ * Once it is accepted successfully, accept "clean" too.
+ */
+static ssize_t au_procfs_plm_write(struct file *file, const char __user *ubuf,
+				   size_t count, loff_t *ppos)
+{
+	ssize_t err;
+	unsigned long id;
+	/* last newline is allowed */
+	char buf[3 + sizeof(unsigned long) * 2 + 1];
+
+	err = -EACCES;
+	if (unlikely(!capable(CAP_SYS_ADMIN)))
+		goto out;
+
+	err = -EINVAL;
+	if (unlikely(count > sizeof(buf)))
+		goto out;
+
+	err = copy_from_user(buf, ubuf, count);
+	if (unlikely(err)) {
+		err = -EFAULT;
+		goto out;
+	}
+	buf[count] = 0;
+
+	err = -EINVAL;
+	if (!strcmp("clean", buf)) {
+		au_procfs_plm_write_clean(file);
+		goto out_success;
+	} else if (unlikely(strncmp("si=", buf, 3)))
+		goto out;
+
+	err = kstrtoul(buf + 3, 16, &id);
+	if (unlikely(err))
+		goto out;
+
+	err = au_procfs_plm_write_si(file, id);
+	if (unlikely(err))
+		goto out;
+
+out_success:
+	err = count; /* success */
+out:
+	return err;
+}
+
+static const struct file_operations au_procfs_plm_fop = {
+	.write		= au_procfs_plm_write,
+	.release	= au_procfs_plm_release,
+	.owner		= THIS_MODULE
+};
+
+/* ---------------------------------------------------------------------- */
+
+static struct proc_dir_entry *au_procfs_dir;
+
+void au_procfs_fin(void)
+{
+	remove_proc_entry(AUFS_PLINK_MAINT_NAME, au_procfs_dir);
+	remove_proc_entry(AUFS_PLINK_MAINT_DIR, NULL);
+}
+
+int __init au_procfs_init(void)
+{
+	int err;
+	struct proc_dir_entry *entry;
+
+	err = -ENOMEM;
+	au_procfs_dir = proc_mkdir(AUFS_PLINK_MAINT_DIR, NULL);
+	if (unlikely(!au_procfs_dir))
+		goto out;
+
+	entry = proc_create(AUFS_PLINK_MAINT_NAME, S_IFREG | S_IWUSR,
+			    au_procfs_dir, &au_procfs_plm_fop);
+	if (unlikely(!entry))
+		goto out_dir;
+
+	err = 0;
+	goto out; /* success */
+
+
+out_dir:
+	remove_proc_entry(AUFS_PLINK_MAINT_DIR, NULL);
+out:
+	return err;
+}
diff --git a/fs/aufs/rdu.c b/fs/aufs/rdu.c
new file mode 100644
index 000000000000..1f0d8c65e1f7
--- /dev/null
+++ b/fs/aufs/rdu.c
@@ -0,0 +1,381 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * readdir in userspace.
+ */
+
+#include <linux/compat.h>
+#include <linux/fs_stack.h>
+#include <linux/security.h>
+#include "aufs.h"
+
+/* bits for struct aufs_rdu.flags */
+#define	AuRdu_CALLED	1
+#define	AuRdu_CONT	(1 << 1)
+#define	AuRdu_FULL	(1 << 2)
+#define au_ftest_rdu(flags, name)	((flags) & AuRdu_##name)
+#define au_fset_rdu(flags, name) \
+	do { (flags) |= AuRdu_##name; } while (0)
+#define au_fclr_rdu(flags, name) \
+	do { (flags) &= ~AuRdu_##name; } while (0)
+
+struct au_rdu_arg {
+	struct dir_context		ctx;
+	struct aufs_rdu			*rdu;
+	union au_rdu_ent_ul		ent;
+	unsigned long			end;
+
+	struct super_block		*sb;
+	int				err;
+};
+
+static int au_rdu_fill(struct dir_context *ctx, const char *name, int nlen,
+		       loff_t offset, u64 h_ino, unsigned int d_type)
+{
+	int err, len;
+	struct au_rdu_arg *arg = container_of(ctx, struct au_rdu_arg, ctx);
+	struct aufs_rdu *rdu = arg->rdu;
+	struct au_rdu_ent ent;
+
+	err = 0;
+	arg->err = 0;
+	au_fset_rdu(rdu->cookie.flags, CALLED);
+	len = au_rdu_len(nlen);
+	if (arg->ent.ul + len  < arg->end) {
+		ent.ino = h_ino;
+		ent.bindex = rdu->cookie.bindex;
+		ent.type = d_type;
+		ent.nlen = nlen;
+		if (unlikely(nlen > AUFS_MAX_NAMELEN))
+			ent.type = DT_UNKNOWN;
+
+		/* unnecessary to support mmap_sem since this is a dir */
+		err = -EFAULT;
+		if (copy_to_user(arg->ent.e, &ent, sizeof(ent)))
+			goto out;
+		if (copy_to_user(arg->ent.e->name, name, nlen))
+			goto out;
+		/* the terminating NULL */
+		if (__put_user(0, arg->ent.e->name + nlen))
+			goto out;
+		err = 0;
+		/* AuDbg("%p, %.*s\n", arg->ent.p, nlen, name); */
+		arg->ent.ul += len;
+		rdu->rent++;
+	} else {
+		err = -EFAULT;
+		au_fset_rdu(rdu->cookie.flags, FULL);
+		rdu->full = 1;
+		rdu->tail = arg->ent;
+	}
+
+out:
+	/* AuTraceErr(err); */
+	return err;
+}
+
+static int au_rdu_do(struct file *h_file, struct au_rdu_arg *arg)
+{
+	int err;
+	loff_t offset;
+	struct au_rdu_cookie *cookie = &arg->rdu->cookie;
+
+	/* we don't have to care (FMODE_32BITHASH | FMODE_64BITHASH) for ext4 */
+	offset = vfsub_llseek(h_file, cookie->h_pos, SEEK_SET);
+	err = offset;
+	if (unlikely(offset != cookie->h_pos))
+		goto out;
+
+	err = 0;
+	do {
+		arg->err = 0;
+		au_fclr_rdu(cookie->flags, CALLED);
+		/* smp_mb(); */
+		err = vfsub_iterate_dir(h_file, &arg->ctx);
+		if (err >= 0)
+			err = arg->err;
+	} while (!err
+		 && au_ftest_rdu(cookie->flags, CALLED)
+		 && !au_ftest_rdu(cookie->flags, FULL));
+	cookie->h_pos = h_file->f_pos;
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+static int au_rdu(struct file *file, struct aufs_rdu *rdu)
+{
+	int err;
+	aufs_bindex_t bbot;
+	struct au_rdu_arg arg = {
+		.ctx = {
+			.actor = au_rdu_fill
+		}
+	};
+	struct dentry *dentry;
+	struct inode *inode;
+	struct file *h_file;
+	struct au_rdu_cookie *cookie = &rdu->cookie;
+
+	err = !access_ok(VERIFY_WRITE, rdu->ent.e, rdu->sz);
+	if (unlikely(err)) {
+		err = -EFAULT;
+		AuTraceErr(err);
+		goto out;
+	}
+	rdu->rent = 0;
+	rdu->tail = rdu->ent;
+	rdu->full = 0;
+	arg.rdu = rdu;
+	arg.ent = rdu->ent;
+	arg.end = arg.ent.ul;
+	arg.end += rdu->sz;
+
+	err = -ENOTDIR;
+	if (unlikely(!file->f_op->iterate && !file->f_op->iterate_shared))
+		goto out;
+
+	err = security_file_permission(file, MAY_READ);
+	AuTraceErr(err);
+	if (unlikely(err))
+		goto out;
+
+	dentry = file->f_path.dentry;
+	inode = d_inode(dentry);
+	inode_lock_shared(inode);
+
+	arg.sb = inode->i_sb;
+	err = si_read_lock(arg.sb, AuLock_FLUSH | AuLock_NOPLM);
+	if (unlikely(err))
+		goto out_mtx;
+	err = au_alive_dir(dentry);
+	if (unlikely(err))
+		goto out_si;
+	/* todo: reval? */
+	fi_read_lock(file);
+
+	err = -EAGAIN;
+	if (unlikely(au_ftest_rdu(cookie->flags, CONT)
+		     && cookie->generation != au_figen(file)))
+		goto out_unlock;
+
+	err = 0;
+	if (!rdu->blk) {
+		rdu->blk = au_sbi(arg.sb)->si_rdblk;
+		if (!rdu->blk)
+			rdu->blk = au_dir_size(file, /*dentry*/NULL);
+	}
+	bbot = au_fbtop(file);
+	if (cookie->bindex < bbot)
+		cookie->bindex = bbot;
+	bbot = au_fbbot_dir(file);
+	/* AuDbg("b%d, b%d\n", cookie->bindex, bbot); */
+	for (; !err && cookie->bindex <= bbot;
+	     cookie->bindex++, cookie->h_pos = 0) {
+		h_file = au_hf_dir(file, cookie->bindex);
+		if (!h_file)
+			continue;
+
+		au_fclr_rdu(cookie->flags, FULL);
+		err = au_rdu_do(h_file, &arg);
+		AuTraceErr(err);
+		if (unlikely(au_ftest_rdu(cookie->flags, FULL) || err))
+			break;
+	}
+	AuDbg("rent %llu\n", rdu->rent);
+
+	if (!err && !au_ftest_rdu(cookie->flags, CONT)) {
+		rdu->shwh = !!au_opt_test(au_sbi(arg.sb)->si_mntflags, SHWH);
+		au_fset_rdu(cookie->flags, CONT);
+		cookie->generation = au_figen(file);
+	}
+
+	ii_read_lock_child(inode);
+	fsstack_copy_attr_atime(inode, au_h_iptr(inode, au_ibtop(inode)));
+	ii_read_unlock(inode);
+
+out_unlock:
+	fi_read_unlock(file);
+out_si:
+	si_read_unlock(arg.sb);
+out_mtx:
+	inode_unlock_shared(inode);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+static int au_rdu_ino(struct file *file, struct aufs_rdu *rdu)
+{
+	int err;
+	ino_t ino;
+	unsigned long long nent;
+	union au_rdu_ent_ul *u;
+	struct au_rdu_ent ent;
+	struct super_block *sb;
+
+	err = 0;
+	nent = rdu->nent;
+	u = &rdu->ent;
+	sb = file->f_path.dentry->d_sb;
+	si_read_lock(sb, AuLock_FLUSH);
+	while (nent-- > 0) {
+		/* unnecessary to support mmap_sem since this is a dir */
+		err = copy_from_user(&ent, u->e, sizeof(ent));
+		if (!err)
+			err = !access_ok(VERIFY_WRITE, &u->e->ino, sizeof(ino));
+		if (unlikely(err)) {
+			err = -EFAULT;
+			AuTraceErr(err);
+			break;
+		}
+
+		/* AuDbg("b%d, i%llu\n", ent.bindex, ent.ino); */
+		if (!ent.wh)
+			err = au_ino(sb, ent.bindex, ent.ino, ent.type, &ino);
+		else
+			err = au_wh_ino(sb, ent.bindex, ent.ino, ent.type,
+					&ino);
+		if (unlikely(err)) {
+			AuTraceErr(err);
+			break;
+		}
+
+		err = __put_user(ino, &u->e->ino);
+		if (unlikely(err)) {
+			err = -EFAULT;
+			AuTraceErr(err);
+			break;
+		}
+		u->ul += au_rdu_len(ent.nlen);
+	}
+	si_read_unlock(sb);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_rdu_verify(struct aufs_rdu *rdu)
+{
+	AuDbg("rdu{%llu, %p, %u | %u | %llu, %u, %u | "
+	      "%llu, b%d, 0x%x, g%u}\n",
+	      rdu->sz, rdu->ent.e, rdu->verify[AufsCtlRduV_SZ],
+	      rdu->blk,
+	      rdu->rent, rdu->shwh, rdu->full,
+	      rdu->cookie.h_pos, rdu->cookie.bindex, rdu->cookie.flags,
+	      rdu->cookie.generation);
+
+	if (rdu->verify[AufsCtlRduV_SZ] == sizeof(*rdu))
+		return 0;
+
+	AuDbg("%u:%u\n",
+	      rdu->verify[AufsCtlRduV_SZ], (unsigned int)sizeof(*rdu));
+	return -EINVAL;
+}
+
+long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	long err, e;
+	struct aufs_rdu rdu;
+	void __user *p = (void __user *)arg;
+
+	err = copy_from_user(&rdu, p, sizeof(rdu));
+	if (unlikely(err)) {
+		err = -EFAULT;
+		AuTraceErr(err);
+		goto out;
+	}
+	err = au_rdu_verify(&rdu);
+	if (unlikely(err))
+		goto out;
+
+	switch (cmd) {
+	case AUFS_CTL_RDU:
+		err = au_rdu(file, &rdu);
+		if (unlikely(err))
+			break;
+
+		e = copy_to_user(p, &rdu, sizeof(rdu));
+		if (unlikely(e)) {
+			err = -EFAULT;
+			AuTraceErr(err);
+		}
+		break;
+	case AUFS_CTL_RDU_INO:
+		err = au_rdu_ino(file, &rdu);
+		break;
+
+	default:
+		/* err = -ENOTTY; */
+		err = -EINVAL;
+	}
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+#ifdef CONFIG_COMPAT
+long au_rdu_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	long err, e;
+	struct aufs_rdu rdu;
+	void __user *p = compat_ptr(arg);
+
+	/* todo: get_user()? */
+	err = copy_from_user(&rdu, p, sizeof(rdu));
+	if (unlikely(err)) {
+		err = -EFAULT;
+		AuTraceErr(err);
+		goto out;
+	}
+	rdu.ent.e = compat_ptr(rdu.ent.ul);
+	err = au_rdu_verify(&rdu);
+	if (unlikely(err))
+		goto out;
+
+	switch (cmd) {
+	case AUFS_CTL_RDU:
+		err = au_rdu(file, &rdu);
+		if (unlikely(err))
+			break;
+
+		rdu.ent.ul = ptr_to_compat(rdu.ent.e);
+		rdu.tail.ul = ptr_to_compat(rdu.tail.e);
+		e = copy_to_user(p, &rdu, sizeof(rdu));
+		if (unlikely(e)) {
+			err = -EFAULT;
+			AuTraceErr(err);
+		}
+		break;
+	case AUFS_CTL_RDU_INO:
+		err = au_rdu_ino(file, &rdu);
+		break;
+
+	default:
+		/* err = -ENOTTY; */
+		err = -EINVAL;
+	}
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+#endif
diff --git a/fs/aufs/rwsem.h b/fs/aufs/rwsem.h
new file mode 100644
index 000000000000..2abe89fb29ff
--- /dev/null
+++ b/fs/aufs/rwsem.h
@@ -0,0 +1,198 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * simple read-write semaphore wrappers
+ */
+
+#ifndef __AUFS_RWSEM_H__
+#define __AUFS_RWSEM_H__
+
+#ifdef __KERNEL__
+
+#include "debug.h"
+
+struct au_rwsem {
+	struct rw_semaphore	rwsem;
+#ifdef CONFIG_AUFS_DEBUG
+	/* just for debugging, not almighty counter */
+	atomic_t		rcnt, wcnt;
+#endif
+};
+
+#ifdef CONFIG_LOCKDEP
+#define au_lockdep_set_name(rw)						\
+	lockdep_set_class_and_name(&(rw)->rwsem,			\
+				   /*original key*/(rw)->rwsem.dep_map.key, \
+				   /*name*/#rw)
+#else
+#define au_lockdep_set_name(rw) do {} while (0)
+#endif
+
+#ifdef CONFIG_AUFS_DEBUG
+#define AuDbgCntInit(rw) do { \
+	atomic_set(&(rw)->rcnt, 0); \
+	atomic_set(&(rw)->wcnt, 0); \
+	smp_mb(); /* atomic set */ \
+} while (0)
+
+#define AuDbgCnt(rw, cnt)	atomic_read(&(rw)->cnt)
+#define AuDbgCntInc(rw, cnt)	atomic_inc(&(rw)->cnt)
+#define AuDbgCntDec(rw, cnt)	WARN_ON(atomic_dec_return(&(rw)->cnt) < 0)
+#define AuDbgRcntInc(rw)	AuDbgCntInc(rw, rcnt)
+#define AuDbgRcntDec(rw)	AuDbgCntDec(rw, rcnt)
+#define AuDbgWcntInc(rw)	AuDbgCntInc(rw, wcnt)
+#define AuDbgWcntDec(rw)	AuDbgCntDec(rw, wcnt)
+#else
+#define AuDbgCnt(rw, cnt)	0
+#define AuDbgCntInit(rw)	do {} while (0)
+#define AuDbgRcntInc(rw)	do {} while (0)
+#define AuDbgRcntDec(rw)	do {} while (0)
+#define AuDbgWcntInc(rw)	do {} while (0)
+#define AuDbgWcntDec(rw)	do {} while (0)
+#endif /* CONFIG_AUFS_DEBUG */
+
+/* to debug easier, do not make them inlined functions */
+#define AuRwMustNoWaiters(rw)	AuDebugOn(rwsem_is_contended(&(rw)->rwsem))
+/* rwsem_is_locked() is unusable */
+#define AuRwMustReadLock(rw)	AuDebugOn(AuDbgCnt(rw, rcnt) <= 0)
+#define AuRwMustWriteLock(rw)	AuDebugOn(AuDbgCnt(rw, wcnt) <= 0)
+#define AuRwMustAnyLock(rw)	AuDebugOn(AuDbgCnt(rw, rcnt) <= 0	\
+					  && AuDbgCnt(rw, wcnt) <= 0)
+#define AuRwDestroy(rw)		AuDebugOn(AuDbgCnt(rw, rcnt)		\
+					  || AuDbgCnt(rw, wcnt))
+
+#define au_rw_init(rw) do {			\
+		AuDbgCntInit(rw);		\
+		init_rwsem(&(rw)->rwsem);	\
+		au_lockdep_set_name(rw);	\
+	} while (0)
+
+#define au_rw_init_wlock(rw) do {		\
+		au_rw_init(rw);			\
+		down_write(&(rw)->rwsem);	\
+		AuDbgWcntInc(rw);		\
+	} while (0)
+
+#define au_rw_init_wlock_nested(rw, lsc) do { \
+		au_rw_init(rw);				\
+		down_write_nested(&(rw)->rwsem, lsc);	\
+		AuDbgWcntInc(rw);			\
+	} while (0)
+
+static inline void au_rw_read_lock(struct au_rwsem *rw)
+{
+	down_read(&rw->rwsem);
+	AuDbgRcntInc(rw);
+}
+
+static inline void au_rw_read_lock_nested(struct au_rwsem *rw, unsigned int lsc)
+{
+	down_read_nested(&rw->rwsem, lsc);
+	AuDbgRcntInc(rw);
+}
+
+static inline void au_rw_read_unlock(struct au_rwsem *rw)
+{
+	AuRwMustReadLock(rw);
+	AuDbgRcntDec(rw);
+	up_read(&rw->rwsem);
+}
+
+static inline void au_rw_dgrade_lock(struct au_rwsem *rw)
+{
+	AuRwMustWriteLock(rw);
+	AuDbgRcntInc(rw);
+	AuDbgWcntDec(rw);
+	downgrade_write(&rw->rwsem);
+}
+
+static inline void au_rw_write_lock(struct au_rwsem *rw)
+{
+	down_write(&rw->rwsem);
+	AuDbgWcntInc(rw);
+}
+
+static inline void au_rw_write_lock_nested(struct au_rwsem *rw,
+					   unsigned int lsc)
+{
+	down_write_nested(&rw->rwsem, lsc);
+	AuDbgWcntInc(rw);
+}
+
+static inline void au_rw_write_unlock(struct au_rwsem *rw)
+{
+	AuRwMustWriteLock(rw);
+	AuDbgWcntDec(rw);
+	up_write(&rw->rwsem);
+}
+
+/* why is not _nested version defined */
+static inline int au_rw_read_trylock(struct au_rwsem *rw)
+{
+	int ret;
+
+	ret = down_read_trylock(&rw->rwsem);
+	if (ret)
+		AuDbgRcntInc(rw);
+	return ret;
+}
+
+static inline int au_rw_write_trylock(struct au_rwsem *rw)
+{
+	int ret;
+
+	ret = down_write_trylock(&rw->rwsem);
+	if (ret)
+		AuDbgWcntInc(rw);
+	return ret;
+}
+
+#undef AuDbgCntDec
+#undef AuDbgRcntInc
+#undef AuDbgRcntDec
+#undef AuDbgWcntDec
+
+#define AuSimpleLockRwsemFuncs(prefix, param, rwsem) \
+static inline void prefix##_read_lock(param) \
+{ au_rw_read_lock(rwsem); } \
+static inline void prefix##_write_lock(param) \
+{ au_rw_write_lock(rwsem); } \
+static inline int prefix##_read_trylock(param) \
+{ return au_rw_read_trylock(rwsem); } \
+static inline int prefix##_write_trylock(param) \
+{ return au_rw_write_trylock(rwsem); }
+/* why is not _nested version defined */
+/* static inline void prefix##_read_trylock_nested(param, lsc)
+{ au_rw_read_trylock_nested(rwsem, lsc)); }
+static inline void prefix##_write_trylock_nestd(param, lsc)
+{ au_rw_write_trylock_nested(rwsem, lsc); } */
+
+#define AuSimpleUnlockRwsemFuncs(prefix, param, rwsem) \
+static inline void prefix##_read_unlock(param) \
+{ au_rw_read_unlock(rwsem); } \
+static inline void prefix##_write_unlock(param) \
+{ au_rw_write_unlock(rwsem); } \
+static inline void prefix##_downgrade_lock(param) \
+{ au_rw_dgrade_lock(rwsem); }
+
+#define AuSimpleRwsemFuncs(prefix, param, rwsem) \
+	AuSimpleLockRwsemFuncs(prefix, param, rwsem) \
+	AuSimpleUnlockRwsemFuncs(prefix, param, rwsem)
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_RWSEM_H__ */
diff --git a/fs/aufs/sbinfo.c b/fs/aufs/sbinfo.c
new file mode 100644
index 000000000000..995514e901b2
--- /dev/null
+++ b/fs/aufs/sbinfo.c
@@ -0,0 +1,304 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * superblock private data
+ */
+
+#include "aufs.h"
+
+/*
+ * they are necessary regardless sysfs is disabled.
+ */
+void au_si_free(struct kobject *kobj)
+{
+	int i;
+	struct au_sbinfo *sbinfo;
+	char *locked __maybe_unused; /* debug only */
+
+	sbinfo = container_of(kobj, struct au_sbinfo, si_kobj);
+	for (i = 0; i < AuPlink_NHASH; i++)
+		AuDebugOn(!hlist_empty(&sbinfo->si_plink[i].head));
+	AuDebugOn(atomic_read(&sbinfo->si_nowait.nw_len));
+
+	AuDebugOn(percpu_counter_sum(&sbinfo->si_ninodes));
+	percpu_counter_destroy(&sbinfo->si_ninodes);
+	AuDebugOn(percpu_counter_sum(&sbinfo->si_nfiles));
+	percpu_counter_destroy(&sbinfo->si_nfiles);
+
+	au_rw_write_lock(&sbinfo->si_rwsem);
+	au_br_free(sbinfo);
+	au_rw_write_unlock(&sbinfo->si_rwsem);
+
+	kfree(sbinfo->si_branch);
+	mutex_destroy(&sbinfo->si_xib_mtx);
+	AuRwDestroy(&sbinfo->si_rwsem);
+
+	kfree(sbinfo);
+}
+
+int au_si_alloc(struct super_block *sb)
+{
+	int err, i;
+	struct au_sbinfo *sbinfo;
+
+	err = -ENOMEM;
+	sbinfo = kzalloc(sizeof(*sbinfo), GFP_NOFS);
+	if (unlikely(!sbinfo))
+		goto out;
+
+	/* will be reallocated separately */
+	sbinfo->si_branch = kzalloc(sizeof(*sbinfo->si_branch), GFP_NOFS);
+	if (unlikely(!sbinfo->si_branch))
+		goto out_sbinfo;
+
+	err = sysaufs_si_init(sbinfo);
+	if (unlikely(err))
+		goto out_br;
+
+	au_nwt_init(&sbinfo->si_nowait);
+	au_rw_init_wlock(&sbinfo->si_rwsem);
+
+	percpu_counter_init(&sbinfo->si_ninodes, 0, GFP_NOFS);
+	percpu_counter_init(&sbinfo->si_nfiles, 0, GFP_NOFS);
+
+	sbinfo->si_bbot = -1;
+	sbinfo->si_last_br_id = AUFS_BRANCH_MAX / 2;
+
+	sbinfo->si_wbr_copyup = AuWbrCopyup_Def;
+	sbinfo->si_wbr_create = AuWbrCreate_Def;
+	sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + sbinfo->si_wbr_copyup;
+	sbinfo->si_wbr_create_ops = au_wbr_create_ops + sbinfo->si_wbr_create;
+
+	au_fhsm_init(sbinfo);
+
+	sbinfo->si_mntflags = au_opts_plink(AuOpt_Def);
+
+	sbinfo->si_xino_jiffy = jiffies;
+	sbinfo->si_xino_expire
+		= msecs_to_jiffies(AUFS_XINO_DEF_SEC * MSEC_PER_SEC);
+	mutex_init(&sbinfo->si_xib_mtx);
+	sbinfo->si_xino_brid = -1;
+	/* leave si_xib_last_pindex and si_xib_next_bit */
+
+	au_sphl_init(&sbinfo->si_aopen);
+
+	sbinfo->si_rdcache = msecs_to_jiffies(AUFS_RDCACHE_DEF * MSEC_PER_SEC);
+	sbinfo->si_rdblk = AUFS_RDBLK_DEF;
+	sbinfo->si_rdhash = AUFS_RDHASH_DEF;
+	sbinfo->si_dirwh = AUFS_DIRWH_DEF;
+
+	for (i = 0; i < AuPlink_NHASH; i++)
+		au_sphl_init(sbinfo->si_plink + i);
+	init_waitqueue_head(&sbinfo->si_plink_wq);
+	spin_lock_init(&sbinfo->si_plink_maint_lock);
+
+	au_sphl_init(&sbinfo->si_files);
+
+	/* with getattr by default */
+	sbinfo->si_iop_array = aufs_iop;
+
+	/* leave other members for sysaufs and si_mnt. */
+	sbinfo->si_sb = sb;
+	sb->s_fs_info = sbinfo;
+	si_pid_set(sb);
+	return 0; /* success */
+
+out_br:
+	kfree(sbinfo->si_branch);
+out_sbinfo:
+	kfree(sbinfo);
+out:
+	return err;
+}
+
+int au_sbr_realloc(struct au_sbinfo *sbinfo, int nbr, int may_shrink)
+{
+	int err, sz;
+	struct au_branch **brp;
+
+	AuRwMustWriteLock(&sbinfo->si_rwsem);
+
+	err = -ENOMEM;
+	sz = sizeof(*brp) * (sbinfo->si_bbot + 1);
+	if (unlikely(!sz))
+		sz = sizeof(*brp);
+	brp = au_kzrealloc(sbinfo->si_branch, sz, sizeof(*brp) * nbr, GFP_NOFS,
+			   may_shrink);
+	if (brp) {
+		sbinfo->si_branch = brp;
+		err = 0;
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+unsigned int au_sigen_inc(struct super_block *sb)
+{
+	unsigned int gen;
+	struct inode *inode;
+
+	SiMustWriteLock(sb);
+
+	gen = ++au_sbi(sb)->si_generation;
+	au_update_digen(sb->s_root);
+	inode = d_inode(sb->s_root);
+	au_update_iigen(inode, /*half*/0);
+	inode->i_version++;
+	return gen;
+}
+
+aufs_bindex_t au_new_br_id(struct super_block *sb)
+{
+	aufs_bindex_t br_id;
+	int i;
+	struct au_sbinfo *sbinfo;
+
+	SiMustWriteLock(sb);
+
+	sbinfo = au_sbi(sb);
+	for (i = 0; i <= AUFS_BRANCH_MAX; i++) {
+		br_id = ++sbinfo->si_last_br_id;
+		AuDebugOn(br_id < 0);
+		if (br_id && au_br_index(sb, br_id) < 0)
+			return br_id;
+	}
+
+	return -1;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* it is ok that new 'nwt' tasks are appended while we are sleeping */
+int si_read_lock(struct super_block *sb, int flags)
+{
+	int err;
+
+	err = 0;
+	if (au_ftest_lock(flags, FLUSH))
+		au_nwt_flush(&au_sbi(sb)->si_nowait);
+
+	si_noflush_read_lock(sb);
+	err = au_plink_maint(sb, flags);
+	if (unlikely(err))
+		si_read_unlock(sb);
+
+	return err;
+}
+
+int si_write_lock(struct super_block *sb, int flags)
+{
+	int err;
+
+	if (au_ftest_lock(flags, FLUSH))
+		au_nwt_flush(&au_sbi(sb)->si_nowait);
+
+	si_noflush_write_lock(sb);
+	err = au_plink_maint(sb, flags);
+	if (unlikely(err))
+		si_write_unlock(sb);
+
+	return err;
+}
+
+/* dentry and super_block lock. call at entry point */
+int aufs_read_lock(struct dentry *dentry, int flags)
+{
+	int err;
+	struct super_block *sb;
+
+	sb = dentry->d_sb;
+	err = si_read_lock(sb, flags);
+	if (unlikely(err))
+		goto out;
+
+	if (au_ftest_lock(flags, DW))
+		di_write_lock_child(dentry);
+	else
+		di_read_lock_child(dentry, flags);
+
+	if (au_ftest_lock(flags, GEN)) {
+		err = au_digen_test(dentry, au_sigen(sb));
+		if (!au_opt_test(au_mntflags(sb), UDBA_NONE))
+			AuDebugOn(!err && au_dbrange_test(dentry));
+		else if (!err)
+			err = au_dbrange_test(dentry);
+		if (unlikely(err))
+			aufs_read_unlock(dentry, flags);
+	}
+
+out:
+	return err;
+}
+
+void aufs_read_unlock(struct dentry *dentry, int flags)
+{
+	if (au_ftest_lock(flags, DW))
+		di_write_unlock(dentry);
+	else
+		di_read_unlock(dentry, flags);
+	si_read_unlock(dentry->d_sb);
+}
+
+void aufs_write_lock(struct dentry *dentry)
+{
+	si_write_lock(dentry->d_sb, AuLock_FLUSH | AuLock_NOPLMW);
+	di_write_lock_child(dentry);
+}
+
+void aufs_write_unlock(struct dentry *dentry)
+{
+	di_write_unlock(dentry);
+	si_write_unlock(dentry->d_sb);
+}
+
+int aufs_read_and_write_lock2(struct dentry *d1, struct dentry *d2, int flags)
+{
+	int err;
+	unsigned int sigen;
+	struct super_block *sb;
+
+	sb = d1->d_sb;
+	err = si_read_lock(sb, flags);
+	if (unlikely(err))
+		goto out;
+
+	di_write_lock2_child(d1, d2, au_ftest_lock(flags, DIRS));
+
+	if (au_ftest_lock(flags, GEN)) {
+		sigen = au_sigen(sb);
+		err = au_digen_test(d1, sigen);
+		AuDebugOn(!err && au_dbrange_test(d1));
+		if (!err) {
+			err = au_digen_test(d2, sigen);
+			AuDebugOn(!err && au_dbrange_test(d2));
+		}
+		if (unlikely(err))
+			aufs_read_and_write_unlock2(d1, d2);
+	}
+
+out:
+	return err;
+}
+
+void aufs_read_and_write_unlock2(struct dentry *d1, struct dentry *d2)
+{
+	di_write_unlock2(d1, d2);
+	si_read_unlock(d1->d_sb);
+}
diff --git a/fs/aufs/spl.h b/fs/aufs/spl.h
new file mode 100644
index 000000000000..2845873ef250
--- /dev/null
+++ b/fs/aufs/spl.h
@@ -0,0 +1,113 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * simple list protected by a spinlock
+ */
+
+#ifndef __AUFS_SPL_H__
+#define __AUFS_SPL_H__
+
+#ifdef __KERNEL__
+
+#if 0
+struct au_splhead {
+	spinlock_t		spin;
+	struct list_head	head;
+};
+
+static inline void au_spl_init(struct au_splhead *spl)
+{
+	spin_lock_init(&spl->spin);
+	INIT_LIST_HEAD(&spl->head);
+}
+
+static inline void au_spl_add(struct list_head *list, struct au_splhead *spl)
+{
+	spin_lock(&spl->spin);
+	list_add(list, &spl->head);
+	spin_unlock(&spl->spin);
+}
+
+static inline void au_spl_del(struct list_head *list, struct au_splhead *spl)
+{
+	spin_lock(&spl->spin);
+	list_del(list);
+	spin_unlock(&spl->spin);
+}
+
+static inline void au_spl_del_rcu(struct list_head *list,
+				  struct au_splhead *spl)
+{
+	spin_lock(&spl->spin);
+	list_del_rcu(list);
+	spin_unlock(&spl->spin);
+}
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+struct au_sphlhead {
+	spinlock_t		spin;
+	struct hlist_head	head;
+};
+
+static inline void au_sphl_init(struct au_sphlhead *sphl)
+{
+	spin_lock_init(&sphl->spin);
+	INIT_HLIST_HEAD(&sphl->head);
+}
+
+static inline void au_sphl_add(struct hlist_node *hlist,
+			       struct au_sphlhead *sphl)
+{
+	spin_lock(&sphl->spin);
+	hlist_add_head(hlist, &sphl->head);
+	spin_unlock(&sphl->spin);
+}
+
+static inline void au_sphl_del(struct hlist_node *hlist,
+			       struct au_sphlhead *sphl)
+{
+	spin_lock(&sphl->spin);
+	hlist_del(hlist);
+	spin_unlock(&sphl->spin);
+}
+
+static inline void au_sphl_del_rcu(struct hlist_node *hlist,
+				   struct au_sphlhead *sphl)
+{
+	spin_lock(&sphl->spin);
+	hlist_del_rcu(hlist);
+	spin_unlock(&sphl->spin);
+}
+
+static inline unsigned long au_sphl_count(struct au_sphlhead *sphl)
+{
+	unsigned long cnt;
+	struct hlist_node *pos;
+
+	cnt = 0;
+	spin_lock(&sphl->spin);
+	hlist_for_each(pos, &sphl->head)
+		cnt++;
+	spin_unlock(&sphl->spin);
+	return cnt;
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_SPL_H__ */
diff --git a/fs/aufs/super.c b/fs/aufs/super.c
new file mode 100644
index 000000000000..d89373028a8f
--- /dev/null
+++ b/fs/aufs/super.c
@@ -0,0 +1,1044 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * mount and super_block operations
+ */
+
+#include <linux/mm.h>
+#include <linux/seq_file.h>
+#include <linux/statfs.h>
+#include <linux/vmalloc.h>
+#include "aufs.h"
+
+/*
+ * super_operations
+ */
+static struct inode *aufs_alloc_inode(struct super_block *sb __maybe_unused)
+{
+	struct au_icntnr *c;
+
+	c = au_cache_alloc_icntnr();
+	if (c) {
+		au_icntnr_init(c);
+		c->vfs_inode.i_version = 1; /* sigen(sb); */
+		c->iinfo.ii_hinode = NULL;
+		return &c->vfs_inode;
+	}
+	return NULL;
+}
+
+static void aufs_destroy_inode_cb(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+
+	au_cache_free_icntnr(container_of(inode, struct au_icntnr, vfs_inode));
+}
+
+static void aufs_destroy_inode(struct inode *inode)
+{
+	if (!au_is_bad_inode(inode))
+		au_iinfo_fin(inode);
+	call_rcu(&inode->i_rcu, aufs_destroy_inode_cb);
+}
+
+struct inode *au_iget_locked(struct super_block *sb, ino_t ino)
+{
+	struct inode *inode;
+	int err;
+
+	inode = iget_locked(sb, ino);
+	if (unlikely(!inode)) {
+		inode = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+	if (!(inode->i_state & I_NEW))
+		goto out;
+
+	err = au_xigen_new(inode);
+	if (!err)
+		err = au_iinfo_init(inode);
+	if (!err)
+		inode->i_version++;
+	else {
+		iget_failed(inode);
+		inode = ERR_PTR(err);
+	}
+
+out:
+	/* never return NULL */
+	AuDebugOn(!inode);
+	AuTraceErrPtr(inode);
+	return inode;
+}
+
+/* lock free root dinfo */
+static int au_show_brs(struct seq_file *seq, struct super_block *sb)
+{
+	int err;
+	aufs_bindex_t bindex, bbot;
+	struct path path;
+	struct au_hdentry *hdp;
+	struct au_branch *br;
+	au_br_perm_str_t perm;
+
+	err = 0;
+	bbot = au_sbbot(sb);
+	bindex = 0;
+	hdp = au_hdentry(au_di(sb->s_root), bindex);
+	for (; !err && bindex <= bbot; bindex++, hdp++) {
+		br = au_sbr(sb, bindex);
+		path.mnt = au_br_mnt(br);
+		path.dentry = hdp->hd_dentry;
+		err = au_seq_path(seq, &path);
+		if (!err) {
+			au_optstr_br_perm(&perm, br->br_perm);
+			seq_printf(seq, "=%s", perm.a);
+			if (bindex != bbot)
+				seq_putc(seq, ':');
+		}
+	}
+	if (unlikely(err || seq_has_overflowed(seq)))
+		err = -E2BIG;
+
+	return err;
+}
+
+static void au_gen_fmt(char *fmt, int len __maybe_unused, const char *pat,
+		       const char *append)
+{
+	char *p;
+
+	p = fmt;
+	while (*pat != ':')
+		*p++ = *pat++;
+	*p++ = *pat++;
+	strcpy(p, append);
+	AuDebugOn(strlen(fmt) >= len);
+}
+
+static void au_show_wbr_create(struct seq_file *m, int v,
+			       struct au_sbinfo *sbinfo)
+{
+	const char *pat;
+	char fmt[32];
+	struct au_wbr_mfs *mfs;
+
+	AuRwMustAnyLock(&sbinfo->si_rwsem);
+
+	seq_puts(m, ",create=");
+	pat = au_optstr_wbr_create(v);
+	mfs = &sbinfo->si_wbr_mfs;
+	switch (v) {
+	case AuWbrCreate_TDP:
+	case AuWbrCreate_RR:
+	case AuWbrCreate_MFS:
+	case AuWbrCreate_PMFS:
+		seq_puts(m, pat);
+		break;
+	case AuWbrCreate_MFSRR:
+	case AuWbrCreate_TDMFS:
+	case AuWbrCreate_PMFSRR:
+		au_gen_fmt(fmt, sizeof(fmt), pat, "%llu");
+		seq_printf(m, fmt, mfs->mfsrr_watermark);
+		break;
+	case AuWbrCreate_MFSV:
+	case AuWbrCreate_PMFSV:
+		au_gen_fmt(fmt, sizeof(fmt), pat, "%lu");
+		seq_printf(m, fmt,
+			   jiffies_to_msecs(mfs->mfs_expire)
+			   / MSEC_PER_SEC);
+		break;
+	case AuWbrCreate_MFSRRV:
+	case AuWbrCreate_TDMFSV:
+	case AuWbrCreate_PMFSRRV:
+		au_gen_fmt(fmt, sizeof(fmt), pat, "%llu:%lu");
+		seq_printf(m, fmt, mfs->mfsrr_watermark,
+			   jiffies_to_msecs(mfs->mfs_expire) / MSEC_PER_SEC);
+		break;
+	default:
+		BUG();
+	}
+}
+
+static int au_show_xino(struct seq_file *seq, struct super_block *sb)
+{
+#ifdef CONFIG_SYSFS
+	return 0;
+#else
+	int err;
+	const int len = sizeof(AUFS_XINO_FNAME) - 1;
+	aufs_bindex_t bindex, brid;
+	struct qstr *name;
+	struct file *f;
+	struct dentry *d, *h_root;
+
+	AuRwMustAnyLock(&sbinfo->si_rwsem);
+
+	err = 0;
+	f = au_sbi(sb)->si_xib;
+	if (!f)
+		goto out;
+
+	/* stop printing the default xino path on the first writable branch */
+	h_root = NULL;
+	brid = au_xino_brid(sb);
+	if (brid >= 0) {
+		bindex = au_br_index(sb, brid);
+		h_root = au_hdentry(au_di(sb->s_root), bindex)->hd_dentry;
+	}
+	d = f->f_path.dentry;
+	name = &d->d_name;
+	/* safe ->d_parent because the file is unlinked */
+	if (d->d_parent == h_root
+	    && name->len == len
+	    && !memcmp(name->name, AUFS_XINO_FNAME, len))
+		goto out;
+
+	seq_puts(seq, ",xino=");
+	err = au_xino_path(seq, f);
+
+out:
+	return err;
+#endif
+}
+
+/* seq_file will re-call me in case of too long string */
+static int aufs_show_options(struct seq_file *m, struct dentry *dentry)
+{
+	int err;
+	unsigned int mnt_flags, v;
+	struct super_block *sb;
+	struct au_sbinfo *sbinfo;
+
+#define AuBool(name, str) do { \
+	v = au_opt_test(mnt_flags, name); \
+	if (v != au_opt_test(AuOpt_Def, name)) \
+		seq_printf(m, ",%s" #str, v ? "" : "no"); \
+} while (0)
+
+#define AuStr(name, str) do { \
+	v = mnt_flags & AuOptMask_##name; \
+	if (v != (AuOpt_Def & AuOptMask_##name)) \
+		seq_printf(m, "," #str "=%s", au_optstr_##str(v)); \
+} while (0)
+
+#define AuUInt(name, str, val) do { \
+	if (val != AUFS_##name##_DEF) \
+		seq_printf(m, "," #str "=%u", val); \
+} while (0)
+
+	sb = dentry->d_sb;
+	if (sb->s_flags & MS_POSIXACL)
+		seq_puts(m, ",acl");
+
+	/* lock free root dinfo */
+	si_noflush_read_lock(sb);
+	sbinfo = au_sbi(sb);
+	seq_printf(m, ",si=%lx", sysaufs_si_id(sbinfo));
+
+	mnt_flags = au_mntflags(sb);
+	if (au_opt_test(mnt_flags, XINO)) {
+		err = au_show_xino(m, sb);
+		if (unlikely(err))
+			goto out;
+	} else
+		seq_puts(m, ",noxino");
+
+	AuBool(TRUNC_XINO, trunc_xino);
+	AuStr(UDBA, udba);
+	AuBool(SHWH, shwh);
+	AuBool(PLINK, plink);
+	AuBool(DIO, dio);
+	AuBool(DIRPERM1, dirperm1);
+
+	v = sbinfo->si_wbr_create;
+	if (v != AuWbrCreate_Def)
+		au_show_wbr_create(m, v, sbinfo);
+
+	v = sbinfo->si_wbr_copyup;
+	if (v != AuWbrCopyup_Def)
+		seq_printf(m, ",cpup=%s", au_optstr_wbr_copyup(v));
+
+	v = au_opt_test(mnt_flags, ALWAYS_DIROPQ);
+	if (v != au_opt_test(AuOpt_Def, ALWAYS_DIROPQ))
+		seq_printf(m, ",diropq=%c", v ? 'a' : 'w');
+
+	AuUInt(DIRWH, dirwh, sbinfo->si_dirwh);
+
+	v = jiffies_to_msecs(sbinfo->si_rdcache) / MSEC_PER_SEC;
+	AuUInt(RDCACHE, rdcache, v);
+
+	AuUInt(RDBLK, rdblk, sbinfo->si_rdblk);
+	AuUInt(RDHASH, rdhash, sbinfo->si_rdhash);
+
+	au_fhsm_show(m, sbinfo);
+
+	AuBool(SUM, sum);
+	/* AuBool(SUM_W, wsum); */
+	AuBool(WARN_PERM, warn_perm);
+	AuBool(VERBOSE, verbose);
+
+out:
+	/* be sure to print "br:" last */
+	if (!sysaufs_brs) {
+		seq_puts(m, ",br:");
+		au_show_brs(m, sb);
+	}
+	si_read_unlock(sb);
+	return 0;
+
+#undef AuBool
+#undef AuStr
+#undef AuUInt
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* sum mode which returns the summation for statfs(2) */
+
+static u64 au_add_till_max(u64 a, u64 b)
+{
+	u64 old;
+
+	old = a;
+	a += b;
+	if (old <= a)
+		return a;
+	return ULLONG_MAX;
+}
+
+static u64 au_mul_till_max(u64 a, long mul)
+{
+	u64 old;
+
+	old = a;
+	a *= mul;
+	if (old <= a)
+		return a;
+	return ULLONG_MAX;
+}
+
+static int au_statfs_sum(struct super_block *sb, struct kstatfs *buf)
+{
+	int err;
+	long bsize, factor;
+	u64 blocks, bfree, bavail, files, ffree;
+	aufs_bindex_t bbot, bindex, i;
+	unsigned char shared;
+	struct path h_path;
+	struct super_block *h_sb;
+
+	err = 0;
+	bsize = LONG_MAX;
+	files = 0;
+	ffree = 0;
+	blocks = 0;
+	bfree = 0;
+	bavail = 0;
+	bbot = au_sbbot(sb);
+	for (bindex = 0; bindex <= bbot; bindex++) {
+		h_path.mnt = au_sbr_mnt(sb, bindex);
+		h_sb = h_path.mnt->mnt_sb;
+		shared = 0;
+		for (i = 0; !shared && i < bindex; i++)
+			shared = (au_sbr_sb(sb, i) == h_sb);
+		if (shared)
+			continue;
+
+		/* sb->s_root for NFS is unreliable */
+		h_path.dentry = h_path.mnt->mnt_root;
+		err = vfs_statfs(&h_path, buf);
+		if (unlikely(err))
+			goto out;
+
+		if (bsize > buf->f_bsize) {
+			/*
+			 * we will reduce bsize, so we have to expand blocks
+			 * etc. to match them again
+			 */
+			factor = (bsize / buf->f_bsize);
+			blocks = au_mul_till_max(blocks, factor);
+			bfree = au_mul_till_max(bfree, factor);
+			bavail = au_mul_till_max(bavail, factor);
+			bsize = buf->f_bsize;
+		}
+
+		factor = (buf->f_bsize / bsize);
+		blocks = au_add_till_max(blocks,
+				au_mul_till_max(buf->f_blocks, factor));
+		bfree = au_add_till_max(bfree,
+				au_mul_till_max(buf->f_bfree, factor));
+		bavail = au_add_till_max(bavail,
+				au_mul_till_max(buf->f_bavail, factor));
+		files = au_add_till_max(files, buf->f_files);
+		ffree = au_add_till_max(ffree, buf->f_ffree);
+	}
+
+	buf->f_bsize = bsize;
+	buf->f_blocks = blocks;
+	buf->f_bfree = bfree;
+	buf->f_bavail = bavail;
+	buf->f_files = files;
+	buf->f_ffree = ffree;
+	buf->f_frsize = 0;
+
+out:
+	return err;
+}
+
+static int aufs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	int err;
+	struct path h_path;
+	struct super_block *sb;
+
+	/* lock free root dinfo */
+	sb = dentry->d_sb;
+	si_noflush_read_lock(sb);
+	if (!au_opt_test(au_mntflags(sb), SUM)) {
+		/* sb->s_root for NFS is unreliable */
+		h_path.mnt = au_sbr_mnt(sb, 0);
+		h_path.dentry = h_path.mnt->mnt_root;
+		err = vfs_statfs(&h_path, buf);
+	} else
+		err = au_statfs_sum(sb, buf);
+	si_read_unlock(sb);
+
+	if (!err) {
+		buf->f_type = AUFS_SUPER_MAGIC;
+		buf->f_namelen = AUFS_MAX_NAMELEN;
+		memset(&buf->f_fsid, 0, sizeof(buf->f_fsid));
+	}
+	/* buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1; */
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int aufs_sync_fs(struct super_block *sb, int wait)
+{
+	int err, e;
+	aufs_bindex_t bbot, bindex;
+	struct au_branch *br;
+	struct super_block *h_sb;
+
+	err = 0;
+	si_noflush_read_lock(sb);
+	bbot = au_sbbot(sb);
+	for (bindex = 0; bindex <= bbot; bindex++) {
+		br = au_sbr(sb, bindex);
+		if (!au_br_writable(br->br_perm))
+			continue;
+
+		h_sb = au_sbr_sb(sb, bindex);
+		e = vfsub_sync_filesystem(h_sb, wait);
+		if (unlikely(e && !err))
+			err = e;
+		/* go on even if an error happens */
+	}
+	si_read_unlock(sb);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* final actions when unmounting a file system */
+static void aufs_put_super(struct super_block *sb)
+{
+	struct au_sbinfo *sbinfo;
+
+	sbinfo = au_sbi(sb);
+	if (!sbinfo)
+		return;
+
+	dbgaufs_si_fin(sbinfo);
+	kobject_put(&sbinfo->si_kobj);
+}
+
+/* ---------------------------------------------------------------------- */
+
+void *au_array_alloc(unsigned long long *hint, au_arraycb_t cb,
+		     struct super_block *sb, void *arg)
+{
+	void *array;
+	unsigned long long n, sz;
+
+	array = NULL;
+	n = 0;
+	if (!*hint)
+		goto out;
+
+	if (*hint > ULLONG_MAX / sizeof(array)) {
+		array = ERR_PTR(-EMFILE);
+		pr_err("hint %llu\n", *hint);
+		goto out;
+	}
+
+	sz = sizeof(array) * *hint;
+	array = kzalloc(sz, GFP_NOFS);
+	if (unlikely(!array))
+		array = vzalloc(sz);
+	if (unlikely(!array)) {
+		array = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	n = cb(sb, array, *hint, arg);
+	AuDebugOn(n > *hint);
+
+out:
+	*hint = n;
+	return array;
+}
+
+static unsigned long long au_iarray_cb(struct super_block *sb, void *a,
+				       unsigned long long max __maybe_unused,
+				       void *arg)
+{
+	unsigned long long n;
+	struct inode **p, *inode;
+	struct list_head *head;
+
+	n = 0;
+	p = a;
+	head = arg;
+	spin_lock(&sb->s_inode_list_lock);
+	list_for_each_entry(inode, head, i_sb_list) {
+		if (!au_is_bad_inode(inode)
+		    && au_ii(inode)->ii_btop >= 0) {
+			spin_lock(&inode->i_lock);
+			if (atomic_read(&inode->i_count)) {
+				au_igrab(inode);
+				*p++ = inode;
+				n++;
+				AuDebugOn(n > max);
+			}
+			spin_unlock(&inode->i_lock);
+		}
+	}
+	spin_unlock(&sb->s_inode_list_lock);
+
+	return n;
+}
+
+struct inode **au_iarray_alloc(struct super_block *sb, unsigned long long *max)
+{
+	*max = au_ninodes(sb);
+	return au_array_alloc(max, au_iarray_cb, sb, &sb->s_inodes);
+}
+
+void au_iarray_free(struct inode **a, unsigned long long max)
+{
+	unsigned long long ull;
+
+	for (ull = 0; ull < max; ull++)
+		iput(a[ull]);
+	kvfree(a);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * refresh dentry and inode at remount time.
+ */
+/* todo: consolidate with simple_reval_dpath() and au_reval_for_attr() */
+static int au_do_refresh(struct dentry *dentry, unsigned int dir_flags,
+		      struct dentry *parent)
+{
+	int err;
+
+	di_write_lock_child(dentry);
+	di_read_lock_parent(parent, AuLock_IR);
+	err = au_refresh_dentry(dentry, parent);
+	if (!err && dir_flags)
+		au_hn_reset(d_inode(dentry), dir_flags);
+	di_read_unlock(parent, AuLock_IR);
+	di_write_unlock(dentry);
+
+	return err;
+}
+
+static int au_do_refresh_d(struct dentry *dentry, unsigned int sigen,
+			   struct au_sbinfo *sbinfo,
+			   const unsigned int dir_flags, unsigned int do_idop)
+{
+	int err;
+	struct dentry *parent;
+
+	err = 0;
+	parent = dget_parent(dentry);
+	if (!au_digen_test(parent, sigen) && au_digen_test(dentry, sigen)) {
+		if (d_really_is_positive(dentry)) {
+			if (!d_is_dir(dentry))
+				err = au_do_refresh(dentry, /*dir_flags*/0,
+						 parent);
+			else {
+				err = au_do_refresh(dentry, dir_flags, parent);
+				if (unlikely(err))
+					au_fset_si(sbinfo, FAILED_REFRESH_DIR);
+			}
+		} else
+			err = au_do_refresh(dentry, /*dir_flags*/0, parent);
+		AuDbgDentry(dentry);
+	}
+	dput(parent);
+
+	if (!err) {
+		if (do_idop)
+			au_refresh_dop(dentry, /*force_reval*/0);
+	} else
+		au_refresh_dop(dentry, /*force_reval*/1);
+
+	AuTraceErr(err);
+	return err;
+}
+
+static int au_refresh_d(struct super_block *sb, unsigned int do_idop)
+{
+	int err, i, j, ndentry, e;
+	unsigned int sigen;
+	struct au_dcsub_pages dpages;
+	struct au_dpage *dpage;
+	struct dentry **dentries, *d;
+	struct au_sbinfo *sbinfo;
+	struct dentry *root = sb->s_root;
+	const unsigned int dir_flags = au_hi_flags(d_inode(root), /*isdir*/1);
+
+	if (do_idop)
+		au_refresh_dop(root, /*force_reval*/0);
+
+	err = au_dpages_init(&dpages, GFP_NOFS);
+	if (unlikely(err))
+		goto out;
+	err = au_dcsub_pages(&dpages, root, NULL, NULL);
+	if (unlikely(err))
+		goto out_dpages;
+
+	sigen = au_sigen(sb);
+	sbinfo = au_sbi(sb);
+	for (i = 0; i < dpages.ndpage; i++) {
+		dpage = dpages.dpages + i;
+		dentries = dpage->dentries;
+		ndentry = dpage->ndentry;
+		for (j = 0; j < ndentry; j++) {
+			d = dentries[j];
+			e = au_do_refresh_d(d, sigen, sbinfo, dir_flags,
+					    do_idop);
+			if (unlikely(e && !err))
+				err = e;
+			/* go on even err */
+		}
+	}
+
+out_dpages:
+	au_dpages_free(&dpages);
+out:
+	return err;
+}
+
+static int au_refresh_i(struct super_block *sb, unsigned int do_idop)
+{
+	int err, e;
+	unsigned int sigen;
+	unsigned long long max, ull;
+	struct inode *inode, **array;
+
+	array = au_iarray_alloc(sb, &max);
+	err = PTR_ERR(array);
+	if (IS_ERR(array))
+		goto out;
+
+	err = 0;
+	sigen = au_sigen(sb);
+	for (ull = 0; ull < max; ull++) {
+		inode = array[ull];
+		if (unlikely(!inode))
+			break;
+
+		e = 0;
+		ii_write_lock_child(inode);
+		if (au_iigen(inode, NULL) != sigen) {
+			e = au_refresh_hinode_self(inode);
+			if (unlikely(e)) {
+				au_refresh_iop(inode, /*force_getattr*/1);
+				pr_err("error %d, i%lu\n", e, inode->i_ino);
+				if (!err)
+					err = e;
+				/* go on even if err */
+			}
+		}
+		if (!e && do_idop)
+			au_refresh_iop(inode, /*force_getattr*/0);
+		ii_write_unlock(inode);
+	}
+
+	au_iarray_free(array, max);
+
+out:
+	return err;
+}
+
+static void au_remount_refresh(struct super_block *sb, unsigned int do_idop)
+{
+	int err, e;
+	unsigned int udba;
+	aufs_bindex_t bindex, bbot;
+	struct dentry *root;
+	struct inode *inode;
+	struct au_branch *br;
+	struct au_sbinfo *sbi;
+
+	au_sigen_inc(sb);
+	sbi = au_sbi(sb);
+	au_fclr_si(sbi, FAILED_REFRESH_DIR);
+
+	root = sb->s_root;
+	DiMustNoWaiters(root);
+	inode = d_inode(root);
+	IiMustNoWaiters(inode);
+
+	udba = au_opt_udba(sb);
+	bbot = au_sbbot(sb);
+	for (bindex = 0; bindex <= bbot; bindex++) {
+		br = au_sbr(sb, bindex);
+		err = au_hnotify_reset_br(udba, br, br->br_perm);
+		if (unlikely(err))
+			AuIOErr("hnotify failed on br %d, %d, ignored\n",
+				bindex, err);
+		/* go on even if err */
+	}
+	au_hn_reset(inode, au_hi_flags(inode, /*isdir*/1));
+
+	if (do_idop) {
+		if (au_ftest_si(sbi, NO_DREVAL)) {
+			AuDebugOn(sb->s_d_op == &aufs_dop_noreval);
+			sb->s_d_op = &aufs_dop_noreval;
+			AuDebugOn(sbi->si_iop_array == aufs_iop_nogetattr);
+			sbi->si_iop_array = aufs_iop_nogetattr;
+		} else {
+			AuDebugOn(sb->s_d_op == &aufs_dop);
+			sb->s_d_op = &aufs_dop;
+			AuDebugOn(sbi->si_iop_array == aufs_iop);
+			sbi->si_iop_array = aufs_iop;
+		}
+		pr_info("reset to %pf and %pf\n",
+			sb->s_d_op, sbi->si_iop_array);
+	}
+
+	di_write_unlock(root);
+	err = au_refresh_d(sb, do_idop);
+	e = au_refresh_i(sb, do_idop);
+	if (unlikely(e && !err))
+		err = e;
+	/* aufs_write_lock() calls ..._child() */
+	di_write_lock_child(root);
+
+	au_cpup_attr_all(inode, /*force*/1);
+
+	if (unlikely(err))
+		AuIOErr("refresh failed, ignored, %d\n", err);
+}
+
+/* stop extra interpretation of errno in mount(8), and strange error messages */
+static int cvt_err(int err)
+{
+	AuTraceErr(err);
+
+	switch (err) {
+	case -ENOENT:
+	case -ENOTDIR:
+	case -EEXIST:
+	case -EIO:
+		err = -EINVAL;
+	}
+	return err;
+}
+
+static int aufs_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	int err, do_dx;
+	unsigned int mntflags;
+	struct au_opts opts = {
+		.opt = NULL
+	};
+	struct dentry *root;
+	struct inode *inode;
+	struct au_sbinfo *sbinfo;
+
+	err = 0;
+	root = sb->s_root;
+	if (!data || !*data) {
+		err = si_write_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
+		if (!err) {
+			di_write_lock_child(root);
+			err = au_opts_verify(sb, *flags, /*pending*/0);
+			aufs_write_unlock(root);
+		}
+		goto out;
+	}
+
+	err = -ENOMEM;
+	opts.opt = (void *)__get_free_page(GFP_NOFS);
+	if (unlikely(!opts.opt))
+		goto out;
+	opts.max_opt = PAGE_SIZE / sizeof(*opts.opt);
+	opts.flags = AuOpts_REMOUNT;
+	opts.sb_flags = *flags;
+
+	/* parse it before aufs lock */
+	err = au_opts_parse(sb, data, &opts);
+	if (unlikely(err))
+		goto out_opts;
+
+	sbinfo = au_sbi(sb);
+	inode = d_inode(root);
+	inode_lock(inode);
+	err = si_write_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
+	if (unlikely(err))
+		goto out_mtx;
+	di_write_lock_child(root);
+
+	/* au_opts_remount() may return an error */
+	err = au_opts_remount(sb, &opts);
+	au_opts_free(&opts);
+
+	if (au_ftest_opts(opts.flags, REFRESH))
+		au_remount_refresh(sb, au_ftest_opts(opts.flags, REFRESH_IDOP));
+
+	if (au_ftest_opts(opts.flags, REFRESH_DYAOP)) {
+		mntflags = au_mntflags(sb);
+		do_dx = !!au_opt_test(mntflags, DIO);
+		au_dy_arefresh(do_dx);
+	}
+
+	au_fhsm_wrote_all(sb, /*force*/1); /* ?? */
+	aufs_write_unlock(root);
+
+out_mtx:
+	inode_unlock(inode);
+out_opts:
+	free_page((unsigned long)opts.opt);
+out:
+	err = cvt_err(err);
+	AuTraceErr(err);
+	return err;
+}
+
+static const struct super_operations aufs_sop = {
+	.alloc_inode	= aufs_alloc_inode,
+	.destroy_inode	= aufs_destroy_inode,
+	/* always deleting, no clearing */
+	.drop_inode	= generic_delete_inode,
+	.show_options	= aufs_show_options,
+	.statfs		= aufs_statfs,
+	.put_super	= aufs_put_super,
+	.sync_fs	= aufs_sync_fs,
+	.remount_fs	= aufs_remount_fs
+};
+
+/* ---------------------------------------------------------------------- */
+
+static int alloc_root(struct super_block *sb)
+{
+	int err;
+	struct inode *inode;
+	struct dentry *root;
+
+	err = -ENOMEM;
+	inode = au_iget_locked(sb, AUFS_ROOT_INO);
+	err = PTR_ERR(inode);
+	if (IS_ERR(inode))
+		goto out;
+
+	inode->i_op = aufs_iop + AuIop_DIR; /* with getattr by default */
+	inode->i_fop = &aufs_dir_fop;
+	inode->i_mode = S_IFDIR;
+	set_nlink(inode, 2);
+	unlock_new_inode(inode);
+
+	root = d_make_root(inode);
+	if (unlikely(!root))
+		goto out;
+	err = PTR_ERR(root);
+	if (IS_ERR(root))
+		goto out;
+
+	err = au_di_init(root);
+	if (!err) {
+		sb->s_root = root;
+		return 0; /* success */
+	}
+	dput(root);
+
+out:
+	return err;
+}
+
+static int aufs_fill_super(struct super_block *sb, void *raw_data,
+			   int silent __maybe_unused)
+{
+	int err;
+	struct au_opts opts = {
+		.opt = NULL
+	};
+	struct au_sbinfo *sbinfo;
+	struct dentry *root;
+	struct inode *inode;
+	char *arg = raw_data;
+
+	if (unlikely(!arg || !*arg)) {
+		err = -EINVAL;
+		pr_err("no arg\n");
+		goto out;
+	}
+
+	err = -ENOMEM;
+	opts.opt = (void *)__get_free_page(GFP_NOFS);
+	if (unlikely(!opts.opt))
+		goto out;
+	opts.max_opt = PAGE_SIZE / sizeof(*opts.opt);
+	opts.sb_flags = sb->s_flags;
+
+	err = au_si_alloc(sb);
+	if (unlikely(err))
+		goto out_opts;
+	sbinfo = au_sbi(sb);
+
+	/* all timestamps always follow the ones on the branch */
+	sb->s_flags |= MS_NOATIME | MS_NODIRATIME;
+	sb->s_op = &aufs_sop;
+	sb->s_d_op = &aufs_dop;
+	sb->s_magic = AUFS_SUPER_MAGIC;
+	sb->s_maxbytes = 0;
+	sb->s_stack_depth = 1;
+	au_export_init(sb);
+	au_xattr_init(sb);
+
+	err = alloc_root(sb);
+	if (unlikely(err)) {
+		si_write_unlock(sb);
+		goto out_info;
+	}
+	root = sb->s_root;
+	inode = d_inode(root);
+
+	/*
+	 * actually we can parse options regardless aufs lock here.
+	 * but at remount time, parsing must be done before aufs lock.
+	 * so we follow the same rule.
+	 */
+	ii_write_lock_parent(inode);
+	aufs_write_unlock(root);
+	err = au_opts_parse(sb, arg, &opts);
+	if (unlikely(err))
+		goto out_root;
+
+	/* lock vfs_inode first, then aufs. */
+	inode_lock(inode);
+	aufs_write_lock(root);
+	err = au_opts_mount(sb, &opts);
+	au_opts_free(&opts);
+	if (!err && au_ftest_si(sbinfo, NO_DREVAL)) {
+		sb->s_d_op = &aufs_dop_noreval;
+		pr_info("%pf\n", sb->s_d_op);
+		au_refresh_dop(root, /*force_reval*/0);
+		sbinfo->si_iop_array = aufs_iop_nogetattr;
+		au_refresh_iop(inode, /*force_getattr*/0);
+	}
+	aufs_write_unlock(root);
+	inode_unlock(inode);
+	if (!err)
+		goto out_opts; /* success */
+
+out_root:
+	dput(root);
+	sb->s_root = NULL;
+out_info:
+	dbgaufs_si_fin(sbinfo);
+	kobject_put(&sbinfo->si_kobj);
+	sb->s_fs_info = NULL;
+out_opts:
+	free_page((unsigned long)opts.opt);
+out:
+	AuTraceErr(err);
+	err = cvt_err(err);
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static struct dentry *aufs_mount(struct file_system_type *fs_type, int flags,
+				 const char *dev_name __maybe_unused,
+				 void *raw_data)
+{
+	struct dentry *root;
+	struct super_block *sb;
+
+	/* all timestamps always follow the ones on the branch */
+	/* mnt->mnt_flags |= MNT_NOATIME | MNT_NODIRATIME; */
+	root = mount_nodev(fs_type, flags, raw_data, aufs_fill_super);
+	if (IS_ERR(root))
+		goto out;
+
+	sb = root->d_sb;
+	si_write_lock(sb, !AuLock_FLUSH);
+	sysaufs_brs_add(sb, 0);
+	si_write_unlock(sb);
+	au_sbilist_add(sb);
+
+out:
+	return root;
+}
+
+static void aufs_kill_sb(struct super_block *sb)
+{
+	struct au_sbinfo *sbinfo;
+
+	sbinfo = au_sbi(sb);
+	if (sbinfo) {
+		au_sbilist_del(sb);
+		aufs_write_lock(sb->s_root);
+		au_fhsm_fin(sb);
+		if (sbinfo->si_wbr_create_ops->fin)
+			sbinfo->si_wbr_create_ops->fin(sb);
+		if (au_opt_test(sbinfo->si_mntflags, UDBA_HNOTIFY)) {
+			au_opt_set_udba(sbinfo->si_mntflags, UDBA_NONE);
+			au_remount_refresh(sb, /*do_idop*/0);
+		}
+		if (au_opt_test(sbinfo->si_mntflags, PLINK))
+			au_plink_put(sb, /*verbose*/1);
+		au_xino_clr(sb);
+		sbinfo->si_sb = NULL;
+		aufs_write_unlock(sb->s_root);
+		au_nwt_flush(&sbinfo->si_nowait);
+	}
+	kill_anon_super(sb);
+}
+
+struct file_system_type aufs_fs_type = {
+	.name		= AUFS_FSTYPE,
+	/* a race between rename and others */
+	.fs_flags	= FS_RENAME_DOES_D_MOVE,
+	.mount		= aufs_mount,
+	.kill_sb	= aufs_kill_sb,
+	/* no need to __module_get() and module_put(). */
+	.owner		= THIS_MODULE,
+};
diff --git a/fs/aufs/super.h b/fs/aufs/super.h
new file mode 100644
index 000000000000..dede05b266d0
--- /dev/null
+++ b/fs/aufs/super.h
@@ -0,0 +1,617 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * super_block operations
+ */
+
+#ifndef __AUFS_SUPER_H__
+#define __AUFS_SUPER_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/kobject.h>
+#include "rwsem.h"
+#include "spl.h"
+#include "wkq.h"
+
+/* policies to select one among multiple writable branches */
+struct au_wbr_copyup_operations {
+	int (*copyup)(struct dentry *dentry);
+};
+
+#define AuWbr_DIR	1		/* target is a dir */
+#define AuWbr_PARENT	(1 << 1)	/* always require a parent */
+
+#define au_ftest_wbr(flags, name)	((flags) & AuWbr_##name)
+#define au_fset_wbr(flags, name)	{ (flags) |= AuWbr_##name; }
+#define au_fclr_wbr(flags, name)	{ (flags) &= ~AuWbr_##name; }
+
+struct au_wbr_create_operations {
+	int (*create)(struct dentry *dentry, unsigned int flags);
+	int (*init)(struct super_block *sb);
+	int (*fin)(struct super_block *sb);
+};
+
+struct au_wbr_mfs {
+	struct mutex	mfs_lock; /* protect this structure */
+	unsigned long	mfs_jiffy;
+	unsigned long	mfs_expire;
+	aufs_bindex_t	mfs_bindex;
+
+	unsigned long long	mfsrr_bytes;
+	unsigned long long	mfsrr_watermark;
+};
+
+#define AuPlink_NHASH 100
+static inline int au_plink_hash(ino_t ino)
+{
+	return ino % AuPlink_NHASH;
+}
+
+/* File-based Hierarchical Storage Management */
+struct au_fhsm {
+#ifdef CONFIG_AUFS_FHSM
+	/* allow only one process who can receive the notification */
+	spinlock_t		fhsm_spin;
+	pid_t			fhsm_pid;
+	wait_queue_head_t	fhsm_wqh;
+	atomic_t		fhsm_readable;
+
+	/* these are protected by si_rwsem */
+	unsigned long		fhsm_expire;
+	aufs_bindex_t		fhsm_bottom;
+#endif
+};
+
+struct au_branch;
+struct au_sbinfo {
+	/* nowait tasks in the system-wide workqueue */
+	struct au_nowait_tasks	si_nowait;
+
+	/*
+	 * tried sb->s_umount, but failed due to the dependecy between i_mutex.
+	 * rwsem for au_sbinfo is necessary.
+	 */
+	struct au_rwsem		si_rwsem;
+
+	/*
+	 * dirty approach to protect sb->sb_inodes and ->s_files (gone) from
+	 * remount.
+	 */
+	struct percpu_counter	si_ninodes, si_nfiles;
+
+	/* branch management */
+	unsigned int		si_generation;
+
+	/* see AuSi_ flags */
+	unsigned char		au_si_status;
+
+	aufs_bindex_t		si_bbot;
+
+	/* dirty trick to keep br_id plus */
+	unsigned int		si_last_br_id :
+				sizeof(aufs_bindex_t) * BITS_PER_BYTE - 1;
+	struct au_branch	**si_branch;
+
+	/* policy to select a writable branch */
+	unsigned char		si_wbr_copyup;
+	unsigned char		si_wbr_create;
+	struct au_wbr_copyup_operations *si_wbr_copyup_ops;
+	struct au_wbr_create_operations *si_wbr_create_ops;
+
+	/* round robin */
+	atomic_t		si_wbr_rr_next;
+
+	/* most free space */
+	struct au_wbr_mfs	si_wbr_mfs;
+
+	/* File-based Hierarchical Storage Management */
+	struct au_fhsm		si_fhsm;
+
+	/* mount flags */
+	/* include/asm-ia64/siginfo.h defines a macro named si_flags */
+	unsigned int		si_mntflags;
+
+	/* external inode number (bitmap and translation table) */
+	vfs_readf_t		si_xread;
+	vfs_writef_t		si_xwrite;
+	struct file		*si_xib;
+	struct mutex		si_xib_mtx; /* protect xib members */
+	unsigned long		*si_xib_buf;
+	unsigned long		si_xib_last_pindex;
+	int			si_xib_next_bit;
+	aufs_bindex_t		si_xino_brid;
+	unsigned long		si_xino_jiffy;
+	unsigned long		si_xino_expire;
+	/* reserved for future use */
+	/* unsigned long long	si_xib_limit; */	/* Max xib file size */
+
+#ifdef CONFIG_AUFS_EXPORT
+	/* i_generation */
+	struct file		*si_xigen;
+	atomic_t		si_xigen_next;
+#endif
+
+	/* dirty trick to suppoer atomic_open */
+	struct au_sphlhead	si_aopen;
+
+	/* vdir parameters */
+	unsigned long		si_rdcache;	/* max cache time in jiffies */
+	unsigned int		si_rdblk;	/* deblk size */
+	unsigned int		si_rdhash;	/* hash size */
+
+	/*
+	 * If the number of whiteouts are larger than si_dirwh, leave all of
+	 * them after au_whtmp_ren to reduce the cost of rmdir(2).
+	 * future fsck.aufs or kernel thread will remove them later.
+	 * Otherwise, remove all whiteouts and the dir in rmdir(2).
+	 */
+	unsigned int		si_dirwh;
+
+	/* pseudo_link list */
+	struct au_sphlhead	si_plink[AuPlink_NHASH];
+	wait_queue_head_t	si_plink_wq;
+	spinlock_t		si_plink_maint_lock;
+	pid_t			si_plink_maint_pid;
+
+	/* file list */
+	struct au_sphlhead	si_files;
+
+	/* with/without getattr, brother of sb->s_d_op */
+	struct inode_operations *si_iop_array;
+
+	/*
+	 * sysfs and lifetime management.
+	 * this is not a small structure and it may be a waste of memory in case
+	 * of sysfs is disabled, particulary when many aufs-es are mounted.
+	 * but using sysfs is majority.
+	 */
+	struct kobject		si_kobj;
+#ifdef CONFIG_DEBUG_FS
+	struct dentry		 *si_dbgaufs;
+	struct dentry		 *si_dbgaufs_plink;
+	struct dentry		 *si_dbgaufs_xib;
+#ifdef CONFIG_AUFS_EXPORT
+	struct dentry		 *si_dbgaufs_xigen;
+#endif
+#endif
+
+#ifdef CONFIG_AUFS_SBILIST
+	struct hlist_node	si_list;
+#endif
+
+	/* dirty, necessary for unmounting, sysfs and sysrq */
+	struct super_block	*si_sb;
+};
+
+/* sbinfo status flags */
+/*
+ * set true when refresh_dirs() failed at remount time.
+ * then try refreshing dirs at access time again.
+ * if it is false, refreshing dirs at access time is unnecesary
+ */
+#define AuSi_FAILED_REFRESH_DIR	1
+#define AuSi_FHSM		(1 << 1)	/* fhsm is active now */
+#define AuSi_NO_DREVAL		(1 << 2)	/* disable all d_revalidate */
+
+#ifndef CONFIG_AUFS_FHSM
+#undef AuSi_FHSM
+#define AuSi_FHSM		0
+#endif
+
+static inline unsigned char au_do_ftest_si(struct au_sbinfo *sbi,
+					   unsigned int flag)
+{
+	AuRwMustAnyLock(&sbi->si_rwsem);
+	return sbi->au_si_status & flag;
+}
+#define au_ftest_si(sbinfo, name)	au_do_ftest_si(sbinfo, AuSi_##name)
+#define au_fset_si(sbinfo, name) do { \
+	AuRwMustWriteLock(&(sbinfo)->si_rwsem); \
+	(sbinfo)->au_si_status |= AuSi_##name; \
+} while (0)
+#define au_fclr_si(sbinfo, name) do { \
+	AuRwMustWriteLock(&(sbinfo)->si_rwsem); \
+	(sbinfo)->au_si_status &= ~AuSi_##name; \
+} while (0)
+
+/* ---------------------------------------------------------------------- */
+
+/* policy to select one among writable branches */
+#define AuWbrCopyup(sbinfo, ...) \
+	((sbinfo)->si_wbr_copyup_ops->copyup(__VA_ARGS__))
+#define AuWbrCreate(sbinfo, ...) \
+	((sbinfo)->si_wbr_create_ops->create(__VA_ARGS__))
+
+/* flags for si_read_lock()/aufs_read_lock()/di_read_lock() */
+#define AuLock_DW		1		/* write-lock dentry */
+#define AuLock_IR		(1 << 1)	/* read-lock inode */
+#define AuLock_IW		(1 << 2)	/* write-lock inode */
+#define AuLock_FLUSH		(1 << 3)	/* wait for 'nowait' tasks */
+#define AuLock_DIRS		(1 << 4)	/* target is a pair of dirs */
+						/* except RENAME_EXCHANGE */
+#define AuLock_NOPLM		(1 << 5)	/* return err in plm mode */
+#define AuLock_NOPLMW		(1 << 6)	/* wait for plm mode ends */
+#define AuLock_GEN		(1 << 7)	/* test digen/iigen */
+#define au_ftest_lock(flags, name)	((flags) & AuLock_##name)
+#define au_fset_lock(flags, name) \
+	do { (flags) |= AuLock_##name; } while (0)
+#define au_fclr_lock(flags, name) \
+	do { (flags) &= ~AuLock_##name; } while (0)
+
+/* ---------------------------------------------------------------------- */
+
+/* super.c */
+extern struct file_system_type aufs_fs_type;
+struct inode *au_iget_locked(struct super_block *sb, ino_t ino);
+typedef unsigned long long (*au_arraycb_t)(struct super_block *sb, void *array,
+					   unsigned long long max, void *arg);
+void *au_array_alloc(unsigned long long *hint, au_arraycb_t cb,
+		     struct super_block *sb, void *arg);
+struct inode **au_iarray_alloc(struct super_block *sb, unsigned long long *max);
+void au_iarray_free(struct inode **a, unsigned long long max);
+
+/* sbinfo.c */
+void au_si_free(struct kobject *kobj);
+int au_si_alloc(struct super_block *sb);
+int au_sbr_realloc(struct au_sbinfo *sbinfo, int nbr, int may_shrink);
+
+unsigned int au_sigen_inc(struct super_block *sb);
+aufs_bindex_t au_new_br_id(struct super_block *sb);
+
+int si_read_lock(struct super_block *sb, int flags);
+int si_write_lock(struct super_block *sb, int flags);
+int aufs_read_lock(struct dentry *dentry, int flags);
+void aufs_read_unlock(struct dentry *dentry, int flags);
+void aufs_write_lock(struct dentry *dentry);
+void aufs_write_unlock(struct dentry *dentry);
+int aufs_read_and_write_lock2(struct dentry *d1, struct dentry *d2, int flags);
+void aufs_read_and_write_unlock2(struct dentry *d1, struct dentry *d2);
+
+/* wbr_policy.c */
+extern struct au_wbr_copyup_operations au_wbr_copyup_ops[];
+extern struct au_wbr_create_operations au_wbr_create_ops[];
+int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst);
+int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex);
+int au_wbr_do_copyup_bu(struct dentry *dentry, aufs_bindex_t btop);
+
+/* mvdown.c */
+int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *arg);
+
+#ifdef CONFIG_AUFS_FHSM
+/* fhsm.c */
+
+static inline pid_t au_fhsm_pid(struct au_fhsm *fhsm)
+{
+	pid_t pid;
+
+	spin_lock(&fhsm->fhsm_spin);
+	pid = fhsm->fhsm_pid;
+	spin_unlock(&fhsm->fhsm_spin);
+
+	return pid;
+}
+
+void au_fhsm_wrote(struct super_block *sb, aufs_bindex_t bindex, int force);
+void au_fhsm_wrote_all(struct super_block *sb, int force);
+int au_fhsm_fd(struct super_block *sb, int oflags);
+int au_fhsm_br_alloc(struct au_branch *br);
+void au_fhsm_set_bottom(struct super_block *sb, aufs_bindex_t bindex);
+void au_fhsm_fin(struct super_block *sb);
+void au_fhsm_init(struct au_sbinfo *sbinfo);
+void au_fhsm_set(struct au_sbinfo *sbinfo, unsigned int sec);
+void au_fhsm_show(struct seq_file *seq, struct au_sbinfo *sbinfo);
+#else
+AuStubVoid(au_fhsm_wrote, struct super_block *sb, aufs_bindex_t bindex,
+	   int force)
+AuStubVoid(au_fhsm_wrote_all, struct super_block *sb, int force)
+AuStub(int, au_fhsm_fd, return -EOPNOTSUPP, struct super_block *sb, int oflags)
+AuStub(pid_t, au_fhsm_pid, return 0, struct au_fhsm *fhsm)
+AuStubInt0(au_fhsm_br_alloc, struct au_branch *br)
+AuStubVoid(au_fhsm_set_bottom, struct super_block *sb, aufs_bindex_t bindex)
+AuStubVoid(au_fhsm_fin, struct super_block *sb)
+AuStubVoid(au_fhsm_init, struct au_sbinfo *sbinfo)
+AuStubVoid(au_fhsm_set, struct au_sbinfo *sbinfo, unsigned int sec)
+AuStubVoid(au_fhsm_show, struct seq_file *seq, struct au_sbinfo *sbinfo)
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+static inline struct au_sbinfo *au_sbi(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+/* ---------------------------------------------------------------------- */
+
+#ifdef CONFIG_AUFS_EXPORT
+int au_test_nfsd(void);
+void au_export_init(struct super_block *sb);
+void au_xigen_inc(struct inode *inode);
+int au_xigen_new(struct inode *inode);
+int au_xigen_set(struct super_block *sb, struct file *base);
+void au_xigen_clr(struct super_block *sb);
+
+static inline int au_busy_or_stale(void)
+{
+	if (!au_test_nfsd())
+		return -EBUSY;
+	return -ESTALE;
+}
+#else
+AuStubInt0(au_test_nfsd, void)
+AuStubVoid(au_export_init, struct super_block *sb)
+AuStubVoid(au_xigen_inc, struct inode *inode)
+AuStubInt0(au_xigen_new, struct inode *inode)
+AuStubInt0(au_xigen_set, struct super_block *sb, struct file *base)
+AuStubVoid(au_xigen_clr, struct super_block *sb)
+AuStub(int, au_busy_or_stale, return -EBUSY, void)
+#endif /* CONFIG_AUFS_EXPORT */
+
+/* ---------------------------------------------------------------------- */
+
+#ifdef CONFIG_AUFS_SBILIST
+/* module.c */
+extern struct au_sphlhead au_sbilist;
+
+static inline void au_sbilist_init(void)
+{
+	au_sphl_init(&au_sbilist);
+}
+
+static inline void au_sbilist_add(struct super_block *sb)
+{
+	au_sphl_add(&au_sbi(sb)->si_list, &au_sbilist);
+}
+
+static inline void au_sbilist_del(struct super_block *sb)
+{
+	au_sphl_del(&au_sbi(sb)->si_list, &au_sbilist);
+}
+
+#ifdef CONFIG_AUFS_MAGIC_SYSRQ
+static inline void au_sbilist_lock(void)
+{
+	spin_lock(&au_sbilist.spin);
+}
+
+static inline void au_sbilist_unlock(void)
+{
+	spin_unlock(&au_sbilist.spin);
+}
+#define AuGFP_SBILIST	GFP_ATOMIC
+#else
+AuStubVoid(au_sbilist_lock, void)
+AuStubVoid(au_sbilist_unlock, void)
+#define AuGFP_SBILIST	GFP_NOFS
+#endif /* CONFIG_AUFS_MAGIC_SYSRQ */
+#else
+AuStubVoid(au_sbilist_init, void)
+AuStubVoid(au_sbilist_add, struct super_block *sb)
+AuStubVoid(au_sbilist_del, struct super_block *sb)
+AuStubVoid(au_sbilist_lock, void)
+AuStubVoid(au_sbilist_unlock, void)
+#define AuGFP_SBILIST	GFP_NOFS
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+static inline void dbgaufs_si_null(struct au_sbinfo *sbinfo)
+{
+	/*
+	 * This function is a dynamic '__init' function actually,
+	 * so the tiny check for si_rwsem is unnecessary.
+	 */
+	/* AuRwMustWriteLock(&sbinfo->si_rwsem); */
+#ifdef CONFIG_DEBUG_FS
+	sbinfo->si_dbgaufs = NULL;
+	sbinfo->si_dbgaufs_plink = NULL;
+	sbinfo->si_dbgaufs_xib = NULL;
+#ifdef CONFIG_AUFS_EXPORT
+	sbinfo->si_dbgaufs_xigen = NULL;
+#endif
+#endif
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* current->atomic_flags */
+/* this value should never corrupt the ones defined in linux/sched.h */
+#define PFA_AUFS	7
+
+TASK_PFA_TEST(AUFS, test_aufs)	/* task_test_aufs */
+TASK_PFA_SET(AUFS, aufs)	/* task_set_aufs */
+TASK_PFA_CLEAR(AUFS, aufs)	/* task_clear_aufs */
+
+static inline int si_pid_test(struct super_block *sb)
+{
+	return !!task_test_aufs(current);
+}
+
+static inline void si_pid_clr(struct super_block *sb)
+{
+	AuDebugOn(!task_test_aufs(current));
+	task_clear_aufs(current);
+}
+
+static inline void si_pid_set(struct super_block *sb)
+{
+	AuDebugOn(task_test_aufs(current));
+	task_set_aufs(current);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* lock superblock. mainly for entry point functions */
+/*
+ * __si_read_lock, __si_write_lock,
+ * __si_read_unlock, __si_write_unlock, __si_downgrade_lock
+ */
+AuSimpleRwsemFuncs(__si, struct super_block *sb, &au_sbi(sb)->si_rwsem);
+
+#define SiMustNoWaiters(sb)	AuRwMustNoWaiters(&au_sbi(sb)->si_rwsem)
+#define SiMustAnyLock(sb)	AuRwMustAnyLock(&au_sbi(sb)->si_rwsem)
+#define SiMustWriteLock(sb)	AuRwMustWriteLock(&au_sbi(sb)->si_rwsem)
+
+static inline void si_noflush_read_lock(struct super_block *sb)
+{
+	__si_read_lock(sb);
+	si_pid_set(sb);
+}
+
+static inline int si_noflush_read_trylock(struct super_block *sb)
+{
+	int locked;
+
+	locked = __si_read_trylock(sb);
+	if (locked)
+		si_pid_set(sb);
+	return locked;
+}
+
+static inline void si_noflush_write_lock(struct super_block *sb)
+{
+	__si_write_lock(sb);
+	si_pid_set(sb);
+}
+
+static inline int si_noflush_write_trylock(struct super_block *sb)
+{
+	int locked;
+
+	locked = __si_write_trylock(sb);
+	if (locked)
+		si_pid_set(sb);
+	return locked;
+}
+
+#if 0 /* reserved */
+static inline int si_read_trylock(struct super_block *sb, int flags)
+{
+	if (au_ftest_lock(flags, FLUSH))
+		au_nwt_flush(&au_sbi(sb)->si_nowait);
+	return si_noflush_read_trylock(sb);
+}
+#endif
+
+static inline void si_read_unlock(struct super_block *sb)
+{
+	si_pid_clr(sb);
+	__si_read_unlock(sb);
+}
+
+#if 0 /* reserved */
+static inline int si_write_trylock(struct super_block *sb, int flags)
+{
+	if (au_ftest_lock(flags, FLUSH))
+		au_nwt_flush(&au_sbi(sb)->si_nowait);
+	return si_noflush_write_trylock(sb);
+}
+#endif
+
+static inline void si_write_unlock(struct super_block *sb)
+{
+	si_pid_clr(sb);
+	__si_write_unlock(sb);
+}
+
+#if 0 /* reserved */
+static inline void si_downgrade_lock(struct super_block *sb)
+{
+	__si_downgrade_lock(sb);
+}
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+static inline aufs_bindex_t au_sbbot(struct super_block *sb)
+{
+	SiMustAnyLock(sb);
+	return au_sbi(sb)->si_bbot;
+}
+
+static inline unsigned int au_mntflags(struct super_block *sb)
+{
+	SiMustAnyLock(sb);
+	return au_sbi(sb)->si_mntflags;
+}
+
+static inline unsigned int au_sigen(struct super_block *sb)
+{
+	SiMustAnyLock(sb);
+	return au_sbi(sb)->si_generation;
+}
+
+static inline unsigned long long au_ninodes(struct super_block *sb)
+{
+	s64 n = percpu_counter_sum(&au_sbi(sb)->si_ninodes);
+
+	BUG_ON(n < 0);
+	return n;
+}
+
+static inline void au_ninodes_inc(struct super_block *sb)
+{
+	percpu_counter_inc(&au_sbi(sb)->si_ninodes);
+}
+
+static inline void au_ninodes_dec(struct super_block *sb)
+{
+	percpu_counter_dec(&au_sbi(sb)->si_ninodes);
+}
+
+static inline unsigned long long au_nfiles(struct super_block *sb)
+{
+	s64 n = percpu_counter_sum(&au_sbi(sb)->si_nfiles);
+
+	BUG_ON(n < 0);
+	return n;
+}
+
+static inline void au_nfiles_inc(struct super_block *sb)
+{
+	percpu_counter_inc(&au_sbi(sb)->si_nfiles);
+}
+
+static inline void au_nfiles_dec(struct super_block *sb)
+{
+	percpu_counter_dec(&au_sbi(sb)->si_nfiles);
+}
+
+static inline struct au_branch *au_sbr(struct super_block *sb,
+				       aufs_bindex_t bindex)
+{
+	SiMustAnyLock(sb);
+	return au_sbi(sb)->si_branch[0 + bindex];
+}
+
+static inline void au_xino_brid_set(struct super_block *sb, aufs_bindex_t brid)
+{
+	SiMustWriteLock(sb);
+	au_sbi(sb)->si_xino_brid = brid;
+}
+
+static inline aufs_bindex_t au_xino_brid(struct super_block *sb)
+{
+	SiMustAnyLock(sb);
+	return au_sbi(sb)->si_xino_brid;
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_SUPER_H__ */
diff --git a/fs/aufs/sysaufs.c b/fs/aufs/sysaufs.c
new file mode 100644
index 000000000000..3f172fd022e4
--- /dev/null
+++ b/fs/aufs/sysaufs.c
@@ -0,0 +1,104 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * sysfs interface and lifetime management
+ * they are necessary regardless sysfs is disabled.
+ */
+
+#include <linux/random.h>
+#include "aufs.h"
+
+unsigned long sysaufs_si_mask;
+struct kset *sysaufs_kset;
+
+#define AuSiAttr(_name) { \
+	.attr   = { .name = __stringify(_name), .mode = 0444 },	\
+	.show   = sysaufs_si_##_name,				\
+}
+
+static struct sysaufs_si_attr sysaufs_si_attr_xi_path = AuSiAttr(xi_path);
+struct attribute *sysaufs_si_attrs[] = {
+	&sysaufs_si_attr_xi_path.attr,
+	NULL,
+};
+
+static const struct sysfs_ops au_sbi_ops = {
+	.show   = sysaufs_si_show
+};
+
+static struct kobj_type au_sbi_ktype = {
+	.release	= au_si_free,
+	.sysfs_ops	= &au_sbi_ops,
+	.default_attrs	= sysaufs_si_attrs
+};
+
+/* ---------------------------------------------------------------------- */
+
+int sysaufs_si_init(struct au_sbinfo *sbinfo)
+{
+	int err;
+
+	sbinfo->si_kobj.kset = sysaufs_kset;
+	/* cf. sysaufs_name() */
+	err = kobject_init_and_add
+		(&sbinfo->si_kobj, &au_sbi_ktype, /*&sysaufs_kset->kobj*/NULL,
+		 SysaufsSiNamePrefix "%lx", sysaufs_si_id(sbinfo));
+
+	dbgaufs_si_null(sbinfo);
+	if (!err) {
+		err = dbgaufs_si_init(sbinfo);
+		if (unlikely(err))
+			kobject_put(&sbinfo->si_kobj);
+	}
+	return err;
+}
+
+void sysaufs_fin(void)
+{
+	dbgaufs_fin();
+	sysfs_remove_group(&sysaufs_kset->kobj, sysaufs_attr_group);
+	kset_unregister(sysaufs_kset);
+}
+
+int __init sysaufs_init(void)
+{
+	int err;
+
+	do {
+		get_random_bytes(&sysaufs_si_mask, sizeof(sysaufs_si_mask));
+	} while (!sysaufs_si_mask);
+
+	err = -EINVAL;
+	sysaufs_kset = kset_create_and_add(AUFS_NAME, NULL, fs_kobj);
+	if (unlikely(!sysaufs_kset))
+		goto out;
+	err = PTR_ERR(sysaufs_kset);
+	if (IS_ERR(sysaufs_kset))
+		goto out;
+	err = sysfs_create_group(&sysaufs_kset->kobj, sysaufs_attr_group);
+	if (unlikely(err)) {
+		kset_unregister(sysaufs_kset);
+		goto out;
+	}
+
+	err = dbgaufs_init();
+	if (unlikely(err))
+		sysaufs_fin();
+out:
+	return err;
+}
diff --git a/fs/aufs/sysaufs.h b/fs/aufs/sysaufs.h
new file mode 100644
index 000000000000..33307336ff75
--- /dev/null
+++ b/fs/aufs/sysaufs.h
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * sysfs interface and mount lifetime management
+ */
+
+#ifndef __SYSAUFS_H__
+#define __SYSAUFS_H__
+
+#ifdef __KERNEL__
+
+#include <linux/sysfs.h>
+#include "module.h"
+
+struct super_block;
+struct au_sbinfo;
+
+struct sysaufs_si_attr {
+	struct attribute attr;
+	int (*show)(struct seq_file *seq, struct super_block *sb);
+};
+
+/* ---------------------------------------------------------------------- */
+
+/* sysaufs.c */
+extern unsigned long sysaufs_si_mask;
+extern struct kset *sysaufs_kset;
+extern struct attribute *sysaufs_si_attrs[];
+int sysaufs_si_init(struct au_sbinfo *sbinfo);
+int __init sysaufs_init(void);
+void sysaufs_fin(void);
+
+/* ---------------------------------------------------------------------- */
+
+/* some people doesn't like to show a pointer in kernel */
+static inline unsigned long sysaufs_si_id(struct au_sbinfo *sbinfo)
+{
+	return sysaufs_si_mask ^ (unsigned long)sbinfo;
+}
+
+#define SysaufsSiNamePrefix	"si_"
+#define SysaufsSiNameLen	(sizeof(SysaufsSiNamePrefix) + 16)
+static inline void sysaufs_name(struct au_sbinfo *sbinfo, char *name)
+{
+	snprintf(name, SysaufsSiNameLen, SysaufsSiNamePrefix "%lx",
+		 sysaufs_si_id(sbinfo));
+}
+
+struct au_branch;
+#ifdef CONFIG_SYSFS
+/* sysfs.c */
+extern struct attribute_group *sysaufs_attr_group;
+
+int sysaufs_si_xi_path(struct seq_file *seq, struct super_block *sb);
+ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr,
+			 char *buf);
+long au_brinfo_ioctl(struct file *file, unsigned long arg);
+#ifdef CONFIG_COMPAT
+long au_brinfo_compat_ioctl(struct file *file, unsigned long arg);
+#endif
+
+void sysaufs_br_init(struct au_branch *br);
+void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex);
+void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex);
+
+#define sysaufs_brs_init()	do {} while (0)
+
+#else
+#define sysaufs_attr_group	NULL
+
+AuStubInt0(sysaufs_si_xi_path, struct seq_file *seq, struct super_block *sb)
+AuStub(ssize_t, sysaufs_si_show, return 0, struct kobject *kobj,
+       struct attribute *attr, char *buf)
+AuStubVoid(sysaufs_br_init, struct au_branch *br)
+AuStubVoid(sysaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex)
+AuStubVoid(sysaufs_brs_del, struct super_block *sb, aufs_bindex_t bindex)
+
+static inline void sysaufs_brs_init(void)
+{
+	sysaufs_brs = 0;
+}
+
+#endif /* CONFIG_SYSFS */
+
+#endif /* __KERNEL__ */
+#endif /* __SYSAUFS_H__ */
diff --git a/fs/aufs/sysfs.c b/fs/aufs/sysfs.c
new file mode 100644
index 000000000000..096bde996740
--- /dev/null
+++ b/fs/aufs/sysfs.c
@@ -0,0 +1,376 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * sysfs interface
+ */
+
+#include <linux/compat.h>
+#include <linux/seq_file.h>
+#include "aufs.h"
+
+#ifdef CONFIG_AUFS_FS_MODULE
+/* this entry violates the "one line per file" policy of sysfs */
+static ssize_t config_show(struct kobject *kobj, struct kobj_attribute *attr,
+			   char *buf)
+{
+	ssize_t err;
+	static char *conf =
+/* this file is generated at compiling */
+#include "conf.str"
+		;
+
+	err = snprintf(buf, PAGE_SIZE, conf);
+	if (unlikely(err >= PAGE_SIZE))
+		err = -EFBIG;
+	return err;
+}
+
+static struct kobj_attribute au_config_attr = __ATTR_RO(config);
+#endif
+
+static struct attribute *au_attr[] = {
+#ifdef CONFIG_AUFS_FS_MODULE
+	&au_config_attr.attr,
+#endif
+	NULL,	/* need to NULL terminate the list of attributes */
+};
+
+static struct attribute_group sysaufs_attr_group_body = {
+	.attrs = au_attr
+};
+
+struct attribute_group *sysaufs_attr_group = &sysaufs_attr_group_body;
+
+/* ---------------------------------------------------------------------- */
+
+int sysaufs_si_xi_path(struct seq_file *seq, struct super_block *sb)
+{
+	int err;
+
+	SiMustAnyLock(sb);
+
+	err = 0;
+	if (au_opt_test(au_mntflags(sb), XINO)) {
+		err = au_xino_path(seq, au_sbi(sb)->si_xib);
+		seq_putc(seq, '\n');
+	}
+	return err;
+}
+
+/*
+ * the lifetime of branch is independent from the entry under sysfs.
+ * sysfs handles the lifetime of the entry, and never call ->show() after it is
+ * unlinked.
+ */
+static int sysaufs_si_br(struct seq_file *seq, struct super_block *sb,
+			 aufs_bindex_t bindex, int idx)
+{
+	int err;
+	struct path path;
+	struct dentry *root;
+	struct au_branch *br;
+	au_br_perm_str_t perm;
+
+	AuDbg("b%d\n", bindex);
+
+	err = 0;
+	root = sb->s_root;
+	di_read_lock_parent(root, !AuLock_IR);
+	br = au_sbr(sb, bindex);
+
+	switch (idx) {
+	case AuBrSysfs_BR:
+		path.mnt = au_br_mnt(br);
+		path.dentry = au_h_dptr(root, bindex);
+		err = au_seq_path(seq, &path);
+		if (!err) {
+			au_optstr_br_perm(&perm, br->br_perm);
+			seq_printf(seq, "=%s\n", perm.a);
+		}
+		break;
+	case AuBrSysfs_BRID:
+		seq_printf(seq, "%d\n", br->br_id);
+		break;
+	}
+	di_read_unlock(root, !AuLock_IR);
+	if (unlikely(err || seq_has_overflowed(seq)))
+		err = -E2BIG;
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static struct seq_file *au_seq(char *p, ssize_t len)
+{
+	struct seq_file *seq;
+
+	seq = kzalloc(sizeof(*seq), GFP_NOFS);
+	if (seq) {
+		/* mutex_init(&seq.lock); */
+		seq->buf = p;
+		seq->size = len;
+		return seq; /* success */
+	}
+
+	seq = ERR_PTR(-ENOMEM);
+	return seq;
+}
+
+#define SysaufsBr_PREFIX	"br"
+#define SysaufsBrid_PREFIX	"brid"
+
+/* todo: file size may exceed PAGE_SIZE */
+ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr,
+			char *buf)
+{
+	ssize_t err;
+	int idx;
+	long l;
+	aufs_bindex_t bbot;
+	struct au_sbinfo *sbinfo;
+	struct super_block *sb;
+	struct seq_file *seq;
+	char *name;
+	struct attribute **cattr;
+
+	sbinfo = container_of(kobj, struct au_sbinfo, si_kobj);
+	sb = sbinfo->si_sb;
+
+	/*
+	 * prevent a race condition between sysfs and aufs.
+	 * for instance, sysfs_file_read() calls sysfs_get_active_two() which
+	 * prohibits maintaining the sysfs entries.
+	 * hew we acquire read lock after sysfs_get_active_two().
+	 * on the other hand, the remount process may maintain the sysfs/aufs
+	 * entries after acquiring write lock.
+	 * it can cause a deadlock.
+	 * simply we gave up processing read here.
+	 */
+	err = -EBUSY;
+	if (unlikely(!si_noflush_read_trylock(sb)))
+		goto out;
+
+	seq = au_seq(buf, PAGE_SIZE);
+	err = PTR_ERR(seq);
+	if (IS_ERR(seq))
+		goto out_unlock;
+
+	name = (void *)attr->name;
+	cattr = sysaufs_si_attrs;
+	while (*cattr) {
+		if (!strcmp(name, (*cattr)->name)) {
+			err = container_of(*cattr, struct sysaufs_si_attr, attr)
+				->show(seq, sb);
+			goto out_seq;
+		}
+		cattr++;
+	}
+
+	if (!strncmp(name, SysaufsBrid_PREFIX,
+		     sizeof(SysaufsBrid_PREFIX) - 1)) {
+		idx = AuBrSysfs_BRID;
+		name += sizeof(SysaufsBrid_PREFIX) - 1;
+	} else if (!strncmp(name, SysaufsBr_PREFIX,
+			    sizeof(SysaufsBr_PREFIX) - 1)) {
+		idx = AuBrSysfs_BR;
+		name += sizeof(SysaufsBr_PREFIX) - 1;
+	} else
+		  BUG();
+
+	err = kstrtol(name, 10, &l);
+	if (!err) {
+		bbot = au_sbbot(sb);
+		if (l <= bbot)
+			err = sysaufs_si_br(seq, sb, (aufs_bindex_t)l, idx);
+		else
+			err = -ENOENT;
+	}
+
+out_seq:
+	if (!err) {
+		err = seq->count;
+		/* sysfs limit */
+		if (unlikely(err == PAGE_SIZE))
+			err = -EFBIG;
+	}
+	kfree(seq);
+out_unlock:
+	si_read_unlock(sb);
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_brinfo(struct super_block *sb, union aufs_brinfo __user *arg)
+{
+	int err;
+	int16_t brid;
+	aufs_bindex_t bindex, bbot;
+	size_t sz;
+	char *buf;
+	struct seq_file *seq;
+	struct au_branch *br;
+
+	si_read_lock(sb, AuLock_FLUSH);
+	bbot = au_sbbot(sb);
+	err = bbot + 1;
+	if (!arg)
+		goto out;
+
+	err = -ENOMEM;
+	buf = (void *)__get_free_page(GFP_NOFS);
+	if (unlikely(!buf))
+		goto out;
+
+	seq = au_seq(buf, PAGE_SIZE);
+	err = PTR_ERR(seq);
+	if (IS_ERR(seq))
+		goto out_buf;
+
+	sz = sizeof(*arg) - offsetof(union aufs_brinfo, path);
+	for (bindex = 0; bindex <= bbot; bindex++, arg++) {
+		err = !access_ok(VERIFY_WRITE, arg, sizeof(*arg));
+		if (unlikely(err))
+			break;
+
+		br = au_sbr(sb, bindex);
+		brid = br->br_id;
+		BUILD_BUG_ON(sizeof(brid) != sizeof(arg->id));
+		err = __put_user(brid, &arg->id);
+		if (unlikely(err))
+			break;
+
+		BUILD_BUG_ON(sizeof(br->br_perm) != sizeof(arg->perm));
+		err = __put_user(br->br_perm, &arg->perm);
+		if (unlikely(err))
+			break;
+
+		err = au_seq_path(seq, &br->br_path);
+		if (unlikely(err))
+			break;
+		seq_putc(seq, '\0');
+		if (!seq_has_overflowed(seq)) {
+			err = copy_to_user(arg->path, seq->buf, seq->count);
+			seq->count = 0;
+			if (unlikely(err))
+				break;
+		} else {
+			err = -E2BIG;
+			goto out_seq;
+		}
+	}
+	if (unlikely(err))
+		err = -EFAULT;
+
+out_seq:
+	kfree(seq);
+out_buf:
+	free_page((unsigned long)buf);
+out:
+	si_read_unlock(sb);
+	return err;
+}
+
+long au_brinfo_ioctl(struct file *file, unsigned long arg)
+{
+	return au_brinfo(file->f_path.dentry->d_sb, (void __user *)arg);
+}
+
+#ifdef CONFIG_COMPAT
+long au_brinfo_compat_ioctl(struct file *file, unsigned long arg)
+{
+	return au_brinfo(file->f_path.dentry->d_sb, compat_ptr(arg));
+}
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+void sysaufs_br_init(struct au_branch *br)
+{
+	int i;
+	struct au_brsysfs *br_sysfs;
+	struct attribute *attr;
+
+	br_sysfs = br->br_sysfs;
+	for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) {
+		attr = &br_sysfs->attr;
+		sysfs_attr_init(attr);
+		attr->name = br_sysfs->name;
+		attr->mode = S_IRUGO;
+		br_sysfs++;
+	}
+}
+
+void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex)
+{
+	struct au_branch *br;
+	struct kobject *kobj;
+	struct au_brsysfs *br_sysfs;
+	int i;
+	aufs_bindex_t bbot;
+
+	dbgaufs_brs_del(sb, bindex);
+
+	if (!sysaufs_brs)
+		return;
+
+	kobj = &au_sbi(sb)->si_kobj;
+	bbot = au_sbbot(sb);
+	for (; bindex <= bbot; bindex++) {
+		br = au_sbr(sb, bindex);
+		br_sysfs = br->br_sysfs;
+		for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) {
+			sysfs_remove_file(kobj, &br_sysfs->attr);
+			br_sysfs++;
+		}
+	}
+}
+
+void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex)
+{
+	int err, i;
+	aufs_bindex_t bbot;
+	struct kobject *kobj;
+	struct au_branch *br;
+	struct au_brsysfs *br_sysfs;
+
+	dbgaufs_brs_add(sb, bindex);
+
+	if (!sysaufs_brs)
+		return;
+
+	kobj = &au_sbi(sb)->si_kobj;
+	bbot = au_sbbot(sb);
+	for (; bindex <= bbot; bindex++) {
+		br = au_sbr(sb, bindex);
+		br_sysfs = br->br_sysfs;
+		snprintf(br_sysfs[AuBrSysfs_BR].name, sizeof(br_sysfs->name),
+			 SysaufsBr_PREFIX "%d", bindex);
+		snprintf(br_sysfs[AuBrSysfs_BRID].name, sizeof(br_sysfs->name),
+			 SysaufsBrid_PREFIX "%d", bindex);
+		for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) {
+			err = sysfs_create_file(kobj, &br_sysfs->attr);
+			if (unlikely(err))
+				pr_warn("failed %s under sysfs(%d)\n",
+					br_sysfs->name, err);
+			br_sysfs++;
+		}
+	}
+}
diff --git a/fs/aufs/sysrq.c b/fs/aufs/sysrq.c
new file mode 100644
index 000000000000..98d5ad2a28aa
--- /dev/null
+++ b/fs/aufs/sysrq.c
@@ -0,0 +1,157 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * magic sysrq hanlder
+ */
+
+/* #include <linux/sysrq.h> */
+#include <linux/writeback.h>
+#include "aufs.h"
+
+/* ---------------------------------------------------------------------- */
+
+static void sysrq_sb(struct super_block *sb)
+{
+	char *plevel;
+	struct au_sbinfo *sbinfo;
+	struct file *file;
+	struct au_sphlhead *files;
+	struct au_finfo *finfo;
+
+	plevel = au_plevel;
+	au_plevel = KERN_WARNING;
+
+	/* since we define pr_fmt, call printk directly */
+#define pr(str) printk(KERN_WARNING AUFS_NAME ": " str)
+
+	sbinfo = au_sbi(sb);
+	printk(KERN_WARNING "si=%lx\n", sysaufs_si_id(sbinfo));
+	pr("superblock\n");
+	au_dpri_sb(sb);
+
+#if 0
+	pr("root dentry\n");
+	au_dpri_dentry(sb->s_root);
+	pr("root inode\n");
+	au_dpri_inode(d_inode(sb->s_root));
+#endif
+
+#if 0
+	do {
+		int err, i, j, ndentry;
+		struct au_dcsub_pages dpages;
+		struct au_dpage *dpage;
+
+		err = au_dpages_init(&dpages, GFP_ATOMIC);
+		if (unlikely(err))
+			break;
+		err = au_dcsub_pages(&dpages, sb->s_root, NULL, NULL);
+		if (!err)
+			for (i = 0; i < dpages.ndpage; i++) {
+				dpage = dpages.dpages + i;
+				ndentry = dpage->ndentry;
+				for (j = 0; j < ndentry; j++)
+					au_dpri_dentry(dpage->dentries[j]);
+			}
+		au_dpages_free(&dpages);
+	} while (0);
+#endif
+
+#if 1
+	{
+		struct inode *i;
+
+		pr("isolated inode\n");
+		spin_lock(&sb->s_inode_list_lock);
+		list_for_each_entry(i, &sb->s_inodes, i_sb_list) {
+			spin_lock(&i->i_lock);
+			if (1 || hlist_empty(&i->i_dentry))
+				au_dpri_inode(i);
+			spin_unlock(&i->i_lock);
+		}
+		spin_unlock(&sb->s_inode_list_lock);
+	}
+#endif
+	pr("files\n");
+	files = &au_sbi(sb)->si_files;
+	spin_lock(&files->spin);
+	hlist_for_each_entry(finfo, &files->head, fi_hlist) {
+		umode_t mode;
+
+		file = finfo->fi_file;
+		mode = file_inode(file)->i_mode;
+		if (!special_file(mode))
+			au_dpri_file(file);
+	}
+	spin_unlock(&files->spin);
+	pr("done\n");
+
+#undef pr
+	au_plevel = plevel;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* module parameter */
+static char *aufs_sysrq_key = "a";
+module_param_named(sysrq, aufs_sysrq_key, charp, S_IRUGO);
+MODULE_PARM_DESC(sysrq, "MagicSysRq key for " AUFS_NAME);
+
+static void au_sysrq(int key __maybe_unused)
+{
+	struct au_sbinfo *sbinfo;
+
+	lockdep_off();
+	au_sbilist_lock();
+	hlist_for_each_entry(sbinfo, &au_sbilist.head, si_list)
+		sysrq_sb(sbinfo->si_sb);
+	au_sbilist_unlock();
+	lockdep_on();
+}
+
+static struct sysrq_key_op au_sysrq_op = {
+	.handler	= au_sysrq,
+	.help_msg	= "Aufs",
+	.action_msg	= "Aufs",
+	.enable_mask	= SYSRQ_ENABLE_DUMP
+};
+
+/* ---------------------------------------------------------------------- */
+
+int __init au_sysrq_init(void)
+{
+	int err;
+	char key;
+
+	err = -1;
+	key = *aufs_sysrq_key;
+	if ('a' <= key && key <= 'z')
+		err = register_sysrq_key(key, &au_sysrq_op);
+	if (unlikely(err))
+		pr_err("err %d, sysrq=%c\n", err, key);
+	return err;
+}
+
+void au_sysrq_fin(void)
+{
+	int err;
+
+	err = unregister_sysrq_key(*aufs_sysrq_key, &au_sysrq_op);
+	if (unlikely(err))
+		pr_err("err %d (ignored)\n", err);
+}
diff --git a/fs/aufs/vdir.c b/fs/aufs/vdir.c
new file mode 100644
index 000000000000..15f0106e43d7
--- /dev/null
+++ b/fs/aufs/vdir.c
@@ -0,0 +1,892 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * virtual or vertical directory
+ */
+
+#include "aufs.h"
+
+static unsigned int calc_size(int nlen)
+{
+	return ALIGN(sizeof(struct au_vdir_de) + nlen, sizeof(ino_t));
+}
+
+static int set_deblk_end(union au_vdir_deblk_p *p,
+			 union au_vdir_deblk_p *deblk_end)
+{
+	if (calc_size(0) <= deblk_end->deblk - p->deblk) {
+		p->de->de_str.len = 0;
+		/* smp_mb(); */
+		return 0;
+	}
+	return -1; /* error */
+}
+
+/* returns true or false */
+static int is_deblk_end(union au_vdir_deblk_p *p,
+			union au_vdir_deblk_p *deblk_end)
+{
+	if (calc_size(0) <= deblk_end->deblk - p->deblk)
+		return !p->de->de_str.len;
+	return 1;
+}
+
+static unsigned char *last_deblk(struct au_vdir *vdir)
+{
+	return vdir->vd_deblk[vdir->vd_nblk - 1];
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* estimate the appropriate size for name hash table */
+unsigned int au_rdhash_est(loff_t sz)
+{
+	unsigned int n;
+
+	n = UINT_MAX;
+	sz >>= 10;
+	if (sz < n)
+		n = sz;
+	if (sz < AUFS_RDHASH_DEF)
+		n = AUFS_RDHASH_DEF;
+	/* pr_info("n %u\n", n); */
+	return n;
+}
+
+/*
+ * the allocated memory has to be freed by
+ * au_nhash_wh_free() or au_nhash_de_free().
+ */
+int au_nhash_alloc(struct au_nhash *nhash, unsigned int num_hash, gfp_t gfp)
+{
+	struct hlist_head *head;
+	unsigned int u;
+	size_t sz;
+
+	sz = sizeof(*nhash->nh_head) * num_hash;
+	head = kmalloc(sz, gfp);
+	if (head) {
+		nhash->nh_num = num_hash;
+		nhash->nh_head = head;
+		for (u = 0; u < num_hash; u++)
+			INIT_HLIST_HEAD(head++);
+		return 0; /* success */
+	}
+
+	return -ENOMEM;
+}
+
+static void nhash_count(struct hlist_head *head)
+{
+#if 0
+	unsigned long n;
+	struct hlist_node *pos;
+
+	n = 0;
+	hlist_for_each(pos, head)
+		n++;
+	pr_info("%lu\n", n);
+#endif
+}
+
+static void au_nhash_wh_do_free(struct hlist_head *head)
+{
+	struct au_vdir_wh *pos;
+	struct hlist_node *node;
+
+	hlist_for_each_entry_safe(pos, node, head, wh_hash)
+		kfree(pos);
+}
+
+static void au_nhash_de_do_free(struct hlist_head *head)
+{
+	struct au_vdir_dehstr *pos;
+	struct hlist_node *node;
+
+	hlist_for_each_entry_safe(pos, node, head, hash)
+		au_cache_free_vdir_dehstr(pos);
+}
+
+static void au_nhash_do_free(struct au_nhash *nhash,
+			     void (*free)(struct hlist_head *head))
+{
+	unsigned int n;
+	struct hlist_head *head;
+
+	n = nhash->nh_num;
+	if (!n)
+		return;
+
+	head = nhash->nh_head;
+	while (n-- > 0) {
+		nhash_count(head);
+		free(head++);
+	}
+	kfree(nhash->nh_head);
+}
+
+void au_nhash_wh_free(struct au_nhash *whlist)
+{
+	au_nhash_do_free(whlist, au_nhash_wh_do_free);
+}
+
+static void au_nhash_de_free(struct au_nhash *delist)
+{
+	au_nhash_do_free(delist, au_nhash_de_do_free);
+}
+
+/* ---------------------------------------------------------------------- */
+
+int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt,
+			    int limit)
+{
+	int num;
+	unsigned int u, n;
+	struct hlist_head *head;
+	struct au_vdir_wh *pos;
+
+	num = 0;
+	n = whlist->nh_num;
+	head = whlist->nh_head;
+	for (u = 0; u < n; u++, head++)
+		hlist_for_each_entry(pos, head, wh_hash)
+			if (pos->wh_bindex == btgt && ++num > limit)
+				return 1;
+	return 0;
+}
+
+static struct hlist_head *au_name_hash(struct au_nhash *nhash,
+				       unsigned char *name,
+				       unsigned int len)
+{
+	unsigned int v;
+	/* const unsigned int magic_bit = 12; */
+
+	AuDebugOn(!nhash->nh_num || !nhash->nh_head);
+
+	v = 0;
+	if (len > 8)
+		len = 8;
+	while (len--)
+		v += *name++;
+	/* v = hash_long(v, magic_bit); */
+	v %= nhash->nh_num;
+	return nhash->nh_head + v;
+}
+
+static int au_nhash_test_name(struct au_vdir_destr *str, const char *name,
+			      int nlen)
+{
+	return str->len == nlen && !memcmp(str->name, name, nlen);
+}
+
+/* returns found or not */
+int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen)
+{
+	struct hlist_head *head;
+	struct au_vdir_wh *pos;
+	struct au_vdir_destr *str;
+
+	head = au_name_hash(whlist, name, nlen);
+	hlist_for_each_entry(pos, head, wh_hash) {
+		str = &pos->wh_str;
+		AuDbg("%.*s\n", str->len, str->name);
+		if (au_nhash_test_name(str, name, nlen))
+			return 1;
+	}
+	return 0;
+}
+
+/* returns found(true) or not */
+static int test_known(struct au_nhash *delist, char *name, int nlen)
+{
+	struct hlist_head *head;
+	struct au_vdir_dehstr *pos;
+	struct au_vdir_destr *str;
+
+	head = au_name_hash(delist, name, nlen);
+	hlist_for_each_entry(pos, head, hash) {
+		str = pos->str;
+		AuDbg("%.*s\n", str->len, str->name);
+		if (au_nhash_test_name(str, name, nlen))
+			return 1;
+	}
+	return 0;
+}
+
+static void au_shwh_init_wh(struct au_vdir_wh *wh, ino_t ino,
+			    unsigned char d_type)
+{
+#ifdef CONFIG_AUFS_SHWH
+	wh->wh_ino = ino;
+	wh->wh_type = d_type;
+#endif
+}
+
+/* ---------------------------------------------------------------------- */
+
+int au_nhash_append_wh(struct au_nhash *whlist, char *name, int nlen, ino_t ino,
+		       unsigned int d_type, aufs_bindex_t bindex,
+		       unsigned char shwh)
+{
+	int err;
+	struct au_vdir_destr *str;
+	struct au_vdir_wh *wh;
+
+	AuDbg("%.*s\n", nlen, name);
+	AuDebugOn(!whlist->nh_num || !whlist->nh_head);
+
+	err = -ENOMEM;
+	wh = kmalloc(sizeof(*wh) + nlen, GFP_NOFS);
+	if (unlikely(!wh))
+		goto out;
+
+	err = 0;
+	wh->wh_bindex = bindex;
+	if (shwh)
+		au_shwh_init_wh(wh, ino, d_type);
+	str = &wh->wh_str;
+	str->len = nlen;
+	memcpy(str->name, name, nlen);
+	hlist_add_head(&wh->wh_hash, au_name_hash(whlist, name, nlen));
+	/* smp_mb(); */
+
+out:
+	return err;
+}
+
+static int append_deblk(struct au_vdir *vdir)
+{
+	int err;
+	unsigned long ul;
+	const unsigned int deblk_sz = vdir->vd_deblk_sz;
+	union au_vdir_deblk_p p, deblk_end;
+	unsigned char **o;
+
+	err = -ENOMEM;
+	o = au_krealloc(vdir->vd_deblk, sizeof(*o) * (vdir->vd_nblk + 1),
+			GFP_NOFS, /*may_shrink*/0);
+	if (unlikely(!o))
+		goto out;
+
+	vdir->vd_deblk = o;
+	p.deblk = kmalloc(deblk_sz, GFP_NOFS);
+	if (p.deblk) {
+		ul = vdir->vd_nblk++;
+		vdir->vd_deblk[ul] = p.deblk;
+		vdir->vd_last.ul = ul;
+		vdir->vd_last.p.deblk = p.deblk;
+		deblk_end.deblk = p.deblk + deblk_sz;
+		err = set_deblk_end(&p, &deblk_end);
+	}
+
+out:
+	return err;
+}
+
+static int append_de(struct au_vdir *vdir, char *name, int nlen, ino_t ino,
+		     unsigned int d_type, struct au_nhash *delist)
+{
+	int err;
+	unsigned int sz;
+	const unsigned int deblk_sz = vdir->vd_deblk_sz;
+	union au_vdir_deblk_p p, *room, deblk_end;
+	struct au_vdir_dehstr *dehstr;
+
+	p.deblk = last_deblk(vdir);
+	deblk_end.deblk = p.deblk + deblk_sz;
+	room = &vdir->vd_last.p;
+	AuDebugOn(room->deblk < p.deblk || deblk_end.deblk <= room->deblk
+		  || !is_deblk_end(room, &deblk_end));
+
+	sz = calc_size(nlen);
+	if (unlikely(sz > deblk_end.deblk - room->deblk)) {
+		err = append_deblk(vdir);
+		if (unlikely(err))
+			goto out;
+
+		p.deblk = last_deblk(vdir);
+		deblk_end.deblk = p.deblk + deblk_sz;
+		/* smp_mb(); */
+		AuDebugOn(room->deblk != p.deblk);
+	}
+
+	err = -ENOMEM;
+	dehstr = au_cache_alloc_vdir_dehstr();
+	if (unlikely(!dehstr))
+		goto out;
+
+	dehstr->str = &room->de->de_str;
+	hlist_add_head(&dehstr->hash, au_name_hash(delist, name, nlen));
+	room->de->de_ino = ino;
+	room->de->de_type = d_type;
+	room->de->de_str.len = nlen;
+	memcpy(room->de->de_str.name, name, nlen);
+
+	err = 0;
+	room->deblk += sz;
+	if (unlikely(set_deblk_end(room, &deblk_end)))
+		err = append_deblk(vdir);
+	/* smp_mb(); */
+
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_vdir_free(struct au_vdir *vdir)
+{
+	unsigned char **deblk;
+
+	deblk = vdir->vd_deblk;
+	while (vdir->vd_nblk--)
+		kfree(*deblk++);
+	kfree(vdir->vd_deblk);
+	au_cache_free_vdir(vdir);
+}
+
+static struct au_vdir *alloc_vdir(struct file *file)
+{
+	struct au_vdir *vdir;
+	struct super_block *sb;
+	int err;
+
+	sb = file->f_path.dentry->d_sb;
+	SiMustAnyLock(sb);
+
+	err = -ENOMEM;
+	vdir = au_cache_alloc_vdir();
+	if (unlikely(!vdir))
+		goto out;
+
+	vdir->vd_deblk = kzalloc(sizeof(*vdir->vd_deblk), GFP_NOFS);
+	if (unlikely(!vdir->vd_deblk))
+		goto out_free;
+
+	vdir->vd_deblk_sz = au_sbi(sb)->si_rdblk;
+	if (!vdir->vd_deblk_sz) {
+		/* estimate the appropriate size for deblk */
+		vdir->vd_deblk_sz = au_dir_size(file, /*dentry*/NULL);
+		/* pr_info("vd_deblk_sz %u\n", vdir->vd_deblk_sz); */
+	}
+	vdir->vd_nblk = 0;
+	vdir->vd_version = 0;
+	vdir->vd_jiffy = 0;
+	err = append_deblk(vdir);
+	if (!err)
+		return vdir; /* success */
+
+	kfree(vdir->vd_deblk);
+
+out_free:
+	au_cache_free_vdir(vdir);
+out:
+	vdir = ERR_PTR(err);
+	return vdir;
+}
+
+static int reinit_vdir(struct au_vdir *vdir)
+{
+	int err;
+	union au_vdir_deblk_p p, deblk_end;
+
+	while (vdir->vd_nblk > 1) {
+		kfree(vdir->vd_deblk[vdir->vd_nblk - 1]);
+		/* vdir->vd_deblk[vdir->vd_nblk - 1] = NULL; */
+		vdir->vd_nblk--;
+	}
+	p.deblk = vdir->vd_deblk[0];
+	deblk_end.deblk = p.deblk + vdir->vd_deblk_sz;
+	err = set_deblk_end(&p, &deblk_end);
+	/* keep vd_dblk_sz */
+	vdir->vd_last.ul = 0;
+	vdir->vd_last.p.deblk = vdir->vd_deblk[0];
+	vdir->vd_version = 0;
+	vdir->vd_jiffy = 0;
+	/* smp_mb(); */
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+#define AuFillVdir_CALLED	1
+#define AuFillVdir_WHABLE	(1 << 1)
+#define AuFillVdir_SHWH		(1 << 2)
+#define au_ftest_fillvdir(flags, name)	((flags) & AuFillVdir_##name)
+#define au_fset_fillvdir(flags, name) \
+	do { (flags) |= AuFillVdir_##name; } while (0)
+#define au_fclr_fillvdir(flags, name) \
+	do { (flags) &= ~AuFillVdir_##name; } while (0)
+
+#ifndef CONFIG_AUFS_SHWH
+#undef AuFillVdir_SHWH
+#define AuFillVdir_SHWH		0
+#endif
+
+struct fillvdir_arg {
+	struct dir_context	ctx;
+	struct file		*file;
+	struct au_vdir		*vdir;
+	struct au_nhash		delist;
+	struct au_nhash		whlist;
+	aufs_bindex_t		bindex;
+	unsigned int		flags;
+	int			err;
+};
+
+static int fillvdir(struct dir_context *ctx, const char *__name, int nlen,
+		    loff_t offset __maybe_unused, u64 h_ino,
+		    unsigned int d_type)
+{
+	struct fillvdir_arg *arg = container_of(ctx, struct fillvdir_arg, ctx);
+	char *name = (void *)__name;
+	struct super_block *sb;
+	ino_t ino;
+	const unsigned char shwh = !!au_ftest_fillvdir(arg->flags, SHWH);
+
+	arg->err = 0;
+	sb = arg->file->f_path.dentry->d_sb;
+	au_fset_fillvdir(arg->flags, CALLED);
+	/* smp_mb(); */
+	if (nlen <= AUFS_WH_PFX_LEN
+	    || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) {
+		if (test_known(&arg->delist, name, nlen)
+		    || au_nhash_test_known_wh(&arg->whlist, name, nlen))
+			goto out; /* already exists or whiteouted */
+
+		arg->err = au_ino(sb, arg->bindex, h_ino, d_type, &ino);
+		if (!arg->err) {
+			if (unlikely(nlen > AUFS_MAX_NAMELEN))
+				d_type = DT_UNKNOWN;
+			arg->err = append_de(arg->vdir, name, nlen, ino,
+					     d_type, &arg->delist);
+		}
+	} else if (au_ftest_fillvdir(arg->flags, WHABLE)) {
+		name += AUFS_WH_PFX_LEN;
+		nlen -= AUFS_WH_PFX_LEN;
+		if (au_nhash_test_known_wh(&arg->whlist, name, nlen))
+			goto out; /* already whiteouted */
+
+		if (shwh)
+			arg->err = au_wh_ino(sb, arg->bindex, h_ino, d_type,
+					     &ino);
+		if (!arg->err) {
+			if (nlen <= AUFS_MAX_NAMELEN + AUFS_WH_PFX_LEN)
+				d_type = DT_UNKNOWN;
+			arg->err = au_nhash_append_wh
+				(&arg->whlist, name, nlen, ino, d_type,
+				 arg->bindex, shwh);
+		}
+	}
+
+out:
+	if (!arg->err)
+		arg->vdir->vd_jiffy = jiffies;
+	/* smp_mb(); */
+	AuTraceErr(arg->err);
+	return arg->err;
+}
+
+static int au_handle_shwh(struct super_block *sb, struct au_vdir *vdir,
+			  struct au_nhash *whlist, struct au_nhash *delist)
+{
+#ifdef CONFIG_AUFS_SHWH
+	int err;
+	unsigned int nh, u;
+	struct hlist_head *head;
+	struct au_vdir_wh *pos;
+	struct hlist_node *n;
+	char *p, *o;
+	struct au_vdir_destr *destr;
+
+	AuDebugOn(!au_opt_test(au_mntflags(sb), SHWH));
+
+	err = -ENOMEM;
+	o = p = (void *)__get_free_page(GFP_NOFS);
+	if (unlikely(!p))
+		goto out;
+
+	err = 0;
+	nh = whlist->nh_num;
+	memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN);
+	p += AUFS_WH_PFX_LEN;
+	for (u = 0; u < nh; u++) {
+		head = whlist->nh_head + u;
+		hlist_for_each_entry_safe(pos, n, head, wh_hash) {
+			destr = &pos->wh_str;
+			memcpy(p, destr->name, destr->len);
+			err = append_de(vdir, o, destr->len + AUFS_WH_PFX_LEN,
+					pos->wh_ino, pos->wh_type, delist);
+			if (unlikely(err))
+				break;
+		}
+	}
+
+	free_page((unsigned long)o);
+
+out:
+	AuTraceErr(err);
+	return err;
+#else
+	return 0;
+#endif
+}
+
+static int au_do_read_vdir(struct fillvdir_arg *arg)
+{
+	int err;
+	unsigned int rdhash;
+	loff_t offset;
+	aufs_bindex_t bbot, bindex, btop;
+	unsigned char shwh;
+	struct file *hf, *file;
+	struct super_block *sb;
+
+	file = arg->file;
+	sb = file->f_path.dentry->d_sb;
+	SiMustAnyLock(sb);
+
+	rdhash = au_sbi(sb)->si_rdhash;
+	if (!rdhash)
+		rdhash = au_rdhash_est(au_dir_size(file, /*dentry*/NULL));
+	err = au_nhash_alloc(&arg->delist, rdhash, GFP_NOFS);
+	if (unlikely(err))
+		goto out;
+	err = au_nhash_alloc(&arg->whlist, rdhash, GFP_NOFS);
+	if (unlikely(err))
+		goto out_delist;
+
+	err = 0;
+	arg->flags = 0;
+	shwh = 0;
+	if (au_opt_test(au_mntflags(sb), SHWH)) {
+		shwh = 1;
+		au_fset_fillvdir(arg->flags, SHWH);
+	}
+	btop = au_fbtop(file);
+	bbot = au_fbbot_dir(file);
+	for (bindex = btop; !err && bindex <= bbot; bindex++) {
+		hf = au_hf_dir(file, bindex);
+		if (!hf)
+			continue;
+
+		offset = vfsub_llseek(hf, 0, SEEK_SET);
+		err = offset;
+		if (unlikely(offset))
+			break;
+
+		arg->bindex = bindex;
+		au_fclr_fillvdir(arg->flags, WHABLE);
+		if (shwh
+		    || (bindex != bbot
+			&& au_br_whable(au_sbr_perm(sb, bindex))))
+			au_fset_fillvdir(arg->flags, WHABLE);
+		do {
+			arg->err = 0;
+			au_fclr_fillvdir(arg->flags, CALLED);
+			/* smp_mb(); */
+			err = vfsub_iterate_dir(hf, &arg->ctx);
+			if (err >= 0)
+				err = arg->err;
+		} while (!err && au_ftest_fillvdir(arg->flags, CALLED));
+
+		/*
+		 * dir_relax() may be good for concurrency, but aufs should not
+		 * use it since it will cause a lockdep problem.
+		 */
+	}
+
+	if (!err && shwh)
+		err = au_handle_shwh(sb, arg->vdir, &arg->whlist, &arg->delist);
+
+	au_nhash_wh_free(&arg->whlist);
+
+out_delist:
+	au_nhash_de_free(&arg->delist);
+out:
+	return err;
+}
+
+static int read_vdir(struct file *file, int may_read)
+{
+	int err;
+	unsigned long expire;
+	unsigned char do_read;
+	struct fillvdir_arg arg = {
+		.ctx = {
+			.actor = fillvdir
+		}
+	};
+	struct inode *inode;
+	struct au_vdir *vdir, *allocated;
+
+	err = 0;
+	inode = file_inode(file);
+	IMustLock(inode);
+	IiMustWriteLock(inode);
+	SiMustAnyLock(inode->i_sb);
+
+	allocated = NULL;
+	do_read = 0;
+	expire = au_sbi(inode->i_sb)->si_rdcache;
+	vdir = au_ivdir(inode);
+	if (!vdir) {
+		do_read = 1;
+		vdir = alloc_vdir(file);
+		err = PTR_ERR(vdir);
+		if (IS_ERR(vdir))
+			goto out;
+		err = 0;
+		allocated = vdir;
+	} else if (may_read
+		   && (inode->i_version != vdir->vd_version
+		       || time_after(jiffies, vdir->vd_jiffy + expire))) {
+		do_read = 1;
+		err = reinit_vdir(vdir);
+		if (unlikely(err))
+			goto out;
+	}
+
+	if (!do_read)
+		return 0; /* success */
+
+	arg.file = file;
+	arg.vdir = vdir;
+	err = au_do_read_vdir(&arg);
+	if (!err) {
+		/* file->f_pos = 0; */ /* todo: ctx->pos? */
+		vdir->vd_version = inode->i_version;
+		vdir->vd_last.ul = 0;
+		vdir->vd_last.p.deblk = vdir->vd_deblk[0];
+		if (allocated)
+			au_set_ivdir(inode, allocated);
+	} else if (allocated)
+		au_vdir_free(allocated);
+
+out:
+	return err;
+}
+
+static int copy_vdir(struct au_vdir *tgt, struct au_vdir *src)
+{
+	int err, rerr;
+	unsigned long ul, n;
+	const unsigned int deblk_sz = src->vd_deblk_sz;
+
+	AuDebugOn(tgt->vd_nblk != 1);
+
+	err = -ENOMEM;
+	if (tgt->vd_nblk < src->vd_nblk) {
+		unsigned char **p;
+
+		p = au_krealloc(tgt->vd_deblk, sizeof(*p) * src->vd_nblk,
+				GFP_NOFS, /*may_shrink*/0);
+		if (unlikely(!p))
+			goto out;
+		tgt->vd_deblk = p;
+	}
+
+	if (tgt->vd_deblk_sz != deblk_sz) {
+		unsigned char *p;
+
+		tgt->vd_deblk_sz = deblk_sz;
+		p = au_krealloc(tgt->vd_deblk[0], deblk_sz, GFP_NOFS,
+				/*may_shrink*/1);
+		if (unlikely(!p))
+			goto out;
+		tgt->vd_deblk[0] = p;
+	}
+	memcpy(tgt->vd_deblk[0], src->vd_deblk[0], deblk_sz);
+	tgt->vd_version = src->vd_version;
+	tgt->vd_jiffy = src->vd_jiffy;
+
+	n = src->vd_nblk;
+	for (ul = 1; ul < n; ul++) {
+		tgt->vd_deblk[ul] = kmemdup(src->vd_deblk[ul], deblk_sz,
+					    GFP_NOFS);
+		if (unlikely(!tgt->vd_deblk[ul]))
+			goto out;
+		tgt->vd_nblk++;
+	}
+	tgt->vd_nblk = n;
+	tgt->vd_last.ul = tgt->vd_last.ul;
+	tgt->vd_last.p.deblk = tgt->vd_deblk[tgt->vd_last.ul];
+	tgt->vd_last.p.deblk += src->vd_last.p.deblk
+		- src->vd_deblk[src->vd_last.ul];
+	/* smp_mb(); */
+	return 0; /* success */
+
+out:
+	rerr = reinit_vdir(tgt);
+	BUG_ON(rerr);
+	return err;
+}
+
+int au_vdir_init(struct file *file)
+{
+	int err;
+	struct inode *inode;
+	struct au_vdir *vdir_cache, *allocated;
+
+	/* test file->f_pos here instead of ctx->pos */
+	err = read_vdir(file, !file->f_pos);
+	if (unlikely(err))
+		goto out;
+
+	allocated = NULL;
+	vdir_cache = au_fvdir_cache(file);
+	if (!vdir_cache) {
+		vdir_cache = alloc_vdir(file);
+		err = PTR_ERR(vdir_cache);
+		if (IS_ERR(vdir_cache))
+			goto out;
+		allocated = vdir_cache;
+	} else if (!file->f_pos && vdir_cache->vd_version != file->f_version) {
+		/* test file->f_pos here instead of ctx->pos */
+		err = reinit_vdir(vdir_cache);
+		if (unlikely(err))
+			goto out;
+	} else
+		return 0; /* success */
+
+	inode = file_inode(file);
+	err = copy_vdir(vdir_cache, au_ivdir(inode));
+	if (!err) {
+		file->f_version = inode->i_version;
+		if (allocated)
+			au_set_fvdir_cache(file, allocated);
+	} else if (allocated)
+		au_vdir_free(allocated);
+
+out:
+	return err;
+}
+
+static loff_t calc_offset(struct au_vdir *vdir)
+{
+	loff_t offset;
+	union au_vdir_deblk_p p;
+
+	p.deblk = vdir->vd_deblk[vdir->vd_last.ul];
+	offset = vdir->vd_last.p.deblk - p.deblk;
+	offset += vdir->vd_deblk_sz * vdir->vd_last.ul;
+	return offset;
+}
+
+/* returns true or false */
+static int seek_vdir(struct file *file, struct dir_context *ctx)
+{
+	int valid;
+	unsigned int deblk_sz;
+	unsigned long ul, n;
+	loff_t offset;
+	union au_vdir_deblk_p p, deblk_end;
+	struct au_vdir *vdir_cache;
+
+	valid = 1;
+	vdir_cache = au_fvdir_cache(file);
+	offset = calc_offset(vdir_cache);
+	AuDbg("offset %lld\n", offset);
+	if (ctx->pos == offset)
+		goto out;
+
+	vdir_cache->vd_last.ul = 0;
+	vdir_cache->vd_last.p.deblk = vdir_cache->vd_deblk[0];
+	if (!ctx->pos)
+		goto out;
+
+	valid = 0;
+	deblk_sz = vdir_cache->vd_deblk_sz;
+	ul = div64_u64(ctx->pos, deblk_sz);
+	AuDbg("ul %lu\n", ul);
+	if (ul >= vdir_cache->vd_nblk)
+		goto out;
+
+	n = vdir_cache->vd_nblk;
+	for (; ul < n; ul++) {
+		p.deblk = vdir_cache->vd_deblk[ul];
+		deblk_end.deblk = p.deblk + deblk_sz;
+		offset = ul;
+		offset *= deblk_sz;
+		while (!is_deblk_end(&p, &deblk_end) && offset < ctx->pos) {
+			unsigned int l;
+
+			l = calc_size(p.de->de_str.len);
+			offset += l;
+			p.deblk += l;
+		}
+		if (!is_deblk_end(&p, &deblk_end)) {
+			valid = 1;
+			vdir_cache->vd_last.ul = ul;
+			vdir_cache->vd_last.p = p;
+			break;
+		}
+	}
+
+out:
+	/* smp_mb(); */
+	AuTraceErr(valid - 1);
+	return valid;
+}
+
+int au_vdir_fill_de(struct file *file, struct dir_context *ctx)
+{
+	unsigned int l, deblk_sz;
+	union au_vdir_deblk_p deblk_end;
+	struct au_vdir *vdir_cache;
+	struct au_vdir_de *de;
+
+	vdir_cache = au_fvdir_cache(file);
+	if (!seek_vdir(file, ctx))
+		return 0;
+
+	deblk_sz = vdir_cache->vd_deblk_sz;
+	while (1) {
+		deblk_end.deblk = vdir_cache->vd_deblk[vdir_cache->vd_last.ul];
+		deblk_end.deblk += deblk_sz;
+		while (!is_deblk_end(&vdir_cache->vd_last.p, &deblk_end)) {
+			de = vdir_cache->vd_last.p.de;
+			AuDbg("%.*s, off%lld, i%lu, dt%d\n",
+			      de->de_str.len, de->de_str.name, ctx->pos,
+			      (unsigned long)de->de_ino, de->de_type);
+			if (unlikely(!dir_emit(ctx, de->de_str.name,
+					       de->de_str.len, de->de_ino,
+					       de->de_type))) {
+				/* todo: ignore the error caused by udba? */
+				/* return err; */
+				return 0;
+			}
+
+			l = calc_size(de->de_str.len);
+			vdir_cache->vd_last.p.deblk += l;
+			ctx->pos += l;
+		}
+		if (vdir_cache->vd_last.ul < vdir_cache->vd_nblk - 1) {
+			vdir_cache->vd_last.ul++;
+			vdir_cache->vd_last.p.deblk
+				= vdir_cache->vd_deblk[vdir_cache->vd_last.ul];
+			ctx->pos = deblk_sz * vdir_cache->vd_last.ul;
+			continue;
+		}
+		break;
+	}
+
+	/* smp_mb(); */
+	return 0;
+}
diff --git a/fs/aufs/vfsub.c b/fs/aufs/vfsub.c
new file mode 100644
index 000000000000..da07be8099fa
--- /dev/null
+++ b/fs/aufs/vfsub.c
@@ -0,0 +1,900 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * sub-routines for VFS
+ */
+
+#include <linux/namei.h>
+#include <linux/nsproxy.h>
+#include <linux/security.h>
+#include <linux/splice.h>
+#ifdef CONFIG_AUFS_BR_FUSE
+#include "../fs/mount.h"
+#endif
+#include "aufs.h"
+
+#ifdef CONFIG_AUFS_BR_FUSE
+int vfsub_test_mntns(struct vfsmount *mnt, struct super_block *h_sb)
+{
+	struct nsproxy *ns;
+
+	if (!au_test_fuse(h_sb) || !au_userns)
+		return 0;
+
+	ns = current->nsproxy;
+	/* no {get,put}_nsproxy(ns) */
+	return real_mount(mnt)->mnt_ns == ns->mnt_ns ? 0 : -EACCES;
+}
+#endif
+
+int vfsub_sync_filesystem(struct super_block *h_sb, int wait)
+{
+	int err;
+
+	lockdep_off();
+	down_read(&h_sb->s_umount);
+	err = __sync_filesystem(h_sb, wait);
+	up_read(&h_sb->s_umount);
+	lockdep_on();
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int vfsub_update_h_iattr(struct path *h_path, int *did)
+{
+	int err;
+	struct kstat st;
+	struct super_block *h_sb;
+
+	/* for remote fs, leave work for its getattr or d_revalidate */
+	/* for bad i_attr fs, handle them in aufs_getattr() */
+	/* still some fs may acquire i_mutex. we need to skip them */
+	err = 0;
+	if (!did)
+		did = &err;
+	h_sb = h_path->dentry->d_sb;
+	*did = (!au_test_fs_remote(h_sb) && au_test_fs_refresh_iattr(h_sb));
+	if (*did)
+		err = vfsub_getattr(h_path, &st);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct file *vfsub_dentry_open(struct path *path, int flags)
+{
+	struct file *file;
+
+	file = dentry_open(path, flags /* | __FMODE_NONOTIFY */,
+			   current_cred());
+	if (!IS_ERR_OR_NULL(file)
+	    && (file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+		i_readcount_inc(d_inode(path->dentry));
+
+	return file;
+}
+
+struct file *vfsub_filp_open(const char *path, int oflags, int mode)
+{
+	struct file *file;
+
+	lockdep_off();
+	file = filp_open(path,
+			 oflags /* | __FMODE_NONOTIFY */,
+			 mode);
+	lockdep_on();
+	if (IS_ERR(file))
+		goto out;
+	vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/
+
+out:
+	return file;
+}
+
+/*
+ * Ideally this function should call VFS:do_last() in order to keep all its
+ * checkings. But it is very hard for aufs to regenerate several VFS internal
+ * structure such as nameidata. This is a second (or third) best approach.
+ * cf. linux/fs/namei.c:do_last(), lookup_open() and atomic_open().
+ */
+int vfsub_atomic_open(struct inode *dir, struct dentry *dentry,
+		      struct vfsub_aopen_args *args, struct au_branch *br)
+{
+	int err;
+	struct file *file = args->file;
+	/* copied from linux/fs/namei.c:atomic_open() */
+	struct dentry *const DENTRY_NOT_SET = (void *)-1UL;
+
+	IMustLock(dir);
+	AuDebugOn(!dir->i_op->atomic_open);
+
+	err = au_br_test_oflag(args->open_flag, br);
+	if (unlikely(err))
+		goto out;
+
+	args->file->f_path.dentry = DENTRY_NOT_SET;
+	args->file->f_path.mnt = au_br_mnt(br);
+	err = dir->i_op->atomic_open(dir, dentry, file, args->open_flag,
+				     args->create_mode, args->opened);
+	if (err >= 0) {
+		/* some filesystems don't set FILE_CREATED while succeeded? */
+		if (*args->opened & FILE_CREATED)
+			fsnotify_create(dir, dentry);
+	} else
+		goto out;
+
+
+	if (!err) {
+		/* todo: call VFS:may_open() here */
+		err = open_check_o_direct(file);
+		/* todo: ima_file_check() too? */
+		if (!err && (args->open_flag & __FMODE_EXEC))
+			err = deny_write_access(file);
+		if (unlikely(err))
+			/* note that the file is created and still opened */
+			goto out;
+	}
+
+	au_br_get(br);
+	fsnotify_open(file);
+
+out:
+	return err;
+}
+
+int vfsub_kern_path(const char *name, unsigned int flags, struct path *path)
+{
+	int err;
+
+	err = kern_path(name, flags, path);
+	if (!err && d_is_positive(path->dentry))
+		vfsub_update_h_iattr(path, /*did*/NULL); /*ignore*/
+	return err;
+}
+
+struct dentry *vfsub_lookup_one_len_unlocked(const char *name,
+					     struct dentry *parent, int len)
+{
+	struct path path = {
+		.mnt = NULL
+	};
+
+	path.dentry = lookup_one_len_unlocked(name, parent, len);
+	if (IS_ERR(path.dentry))
+		goto out;
+	if (d_is_positive(path.dentry))
+		vfsub_update_h_iattr(&path, /*did*/NULL); /*ignore*/
+
+out:
+	AuTraceErrPtr(path.dentry);
+	return path.dentry;
+}
+
+struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent,
+				    int len)
+{
+	struct path path = {
+		.mnt = NULL
+	};
+
+	/* VFS checks it too, but by WARN_ON_ONCE() */
+	IMustLock(d_inode(parent));
+
+	path.dentry = lookup_one_len(name, parent, len);
+	if (IS_ERR(path.dentry))
+		goto out;
+	if (d_is_positive(path.dentry))
+		vfsub_update_h_iattr(&path, /*did*/NULL); /*ignore*/
+
+out:
+	AuTraceErrPtr(path.dentry);
+	return path.dentry;
+}
+
+void vfsub_call_lkup_one(void *args)
+{
+	struct vfsub_lkup_one_args *a = args;
+	*a->errp = vfsub_lkup_one(a->name, a->parent);
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct dentry *vfsub_lock_rename(struct dentry *d1, struct au_hinode *hdir1,
+				 struct dentry *d2, struct au_hinode *hdir2)
+{
+	struct dentry *d;
+
+	lockdep_off();
+	d = lock_rename(d1, d2);
+	lockdep_on();
+	au_hn_suspend(hdir1);
+	if (hdir1 != hdir2)
+		au_hn_suspend(hdir2);
+
+	return d;
+}
+
+void vfsub_unlock_rename(struct dentry *d1, struct au_hinode *hdir1,
+			 struct dentry *d2, struct au_hinode *hdir2)
+{
+	au_hn_resume(hdir1);
+	if (hdir1 != hdir2)
+		au_hn_resume(hdir2);
+	lockdep_off();
+	unlock_rename(d1, d2);
+	lockdep_on();
+}
+
+/* ---------------------------------------------------------------------- */
+
+int vfsub_create(struct inode *dir, struct path *path, int mode, bool want_excl)
+{
+	int err;
+	struct dentry *d;
+
+	IMustLock(dir);
+
+	d = path->dentry;
+	path->dentry = d->d_parent;
+	err = security_path_mknod(path, d, mode, 0);
+	path->dentry = d;
+	if (unlikely(err))
+		goto out;
+
+	lockdep_off();
+	err = vfs_create(dir, path->dentry, mode, want_excl);
+	lockdep_on();
+	if (!err) {
+		struct path tmp = *path;
+		int did;
+
+		vfsub_update_h_iattr(&tmp, &did);
+		if (did) {
+			tmp.dentry = path->dentry->d_parent;
+			vfsub_update_h_iattr(&tmp, /*did*/NULL);
+		}
+		/*ignore*/
+	}
+
+out:
+	return err;
+}
+
+int vfsub_symlink(struct inode *dir, struct path *path, const char *symname)
+{
+	int err;
+	struct dentry *d;
+
+	IMustLock(dir);
+
+	d = path->dentry;
+	path->dentry = d->d_parent;
+	err = security_path_symlink(path, d, symname);
+	path->dentry = d;
+	if (unlikely(err))
+		goto out;
+
+	lockdep_off();
+	err = vfs_symlink(dir, path->dentry, symname);
+	lockdep_on();
+	if (!err) {
+		struct path tmp = *path;
+		int did;
+
+		vfsub_update_h_iattr(&tmp, &did);
+		if (did) {
+			tmp.dentry = path->dentry->d_parent;
+			vfsub_update_h_iattr(&tmp, /*did*/NULL);
+		}
+		/*ignore*/
+	}
+
+out:
+	return err;
+}
+
+int vfsub_mknod(struct inode *dir, struct path *path, int mode, dev_t dev)
+{
+	int err;
+	struct dentry *d;
+
+	IMustLock(dir);
+
+	d = path->dentry;
+	path->dentry = d->d_parent;
+	err = security_path_mknod(path, d, mode, new_encode_dev(dev));
+	path->dentry = d;
+	if (unlikely(err))
+		goto out;
+
+	lockdep_off();
+	err = vfs_mknod(dir, path->dentry, mode, dev);
+	lockdep_on();
+	if (!err) {
+		struct path tmp = *path;
+		int did;
+
+		vfsub_update_h_iattr(&tmp, &did);
+		if (did) {
+			tmp.dentry = path->dentry->d_parent;
+			vfsub_update_h_iattr(&tmp, /*did*/NULL);
+		}
+		/*ignore*/
+	}
+
+out:
+	return err;
+}
+
+static int au_test_nlink(struct inode *inode)
+{
+	const unsigned int link_max = UINT_MAX >> 1; /* rough margin */
+
+	if (!au_test_fs_no_limit_nlink(inode->i_sb)
+	    || inode->i_nlink < link_max)
+		return 0;
+	return -EMLINK;
+}
+
+int vfsub_link(struct dentry *src_dentry, struct inode *dir, struct path *path,
+	       struct inode **delegated_inode)
+{
+	int err;
+	struct dentry *d;
+
+	IMustLock(dir);
+
+	err = au_test_nlink(d_inode(src_dentry));
+	if (unlikely(err))
+		return err;
+
+	/* we don't call may_linkat() */
+	d = path->dentry;
+	path->dentry = d->d_parent;
+	err = security_path_link(src_dentry, path, d);
+	path->dentry = d;
+	if (unlikely(err))
+		goto out;
+
+	lockdep_off();
+	err = vfs_link(src_dentry, dir, path->dentry, delegated_inode);
+	lockdep_on();
+	if (!err) {
+		struct path tmp = *path;
+		int did;
+
+		/* fuse has different memory inode for the same inumber */
+		vfsub_update_h_iattr(&tmp, &did);
+		if (did) {
+			tmp.dentry = path->dentry->d_parent;
+			vfsub_update_h_iattr(&tmp, /*did*/NULL);
+			tmp.dentry = src_dentry;
+			vfsub_update_h_iattr(&tmp, /*did*/NULL);
+		}
+		/*ignore*/
+	}
+
+out:
+	return err;
+}
+
+int vfsub_rename(struct inode *src_dir, struct dentry *src_dentry,
+		 struct inode *dir, struct path *path,
+		 struct inode **delegated_inode, unsigned int flags)
+{
+	int err;
+	struct path tmp = {
+		.mnt	= path->mnt
+	};
+	struct dentry *d;
+
+	IMustLock(dir);
+	IMustLock(src_dir);
+
+	d = path->dentry;
+	path->dentry = d->d_parent;
+	tmp.dentry = src_dentry->d_parent;
+	err = security_path_rename(&tmp, src_dentry, path, d, /*flags*/0);
+	path->dentry = d;
+	if (unlikely(err))
+		goto out;
+
+	lockdep_off();
+	err = vfs_rename(src_dir, src_dentry, dir, path->dentry,
+			 delegated_inode, flags);
+	lockdep_on();
+	if (!err) {
+		int did;
+
+		tmp.dentry = d->d_parent;
+		vfsub_update_h_iattr(&tmp, &did);
+		if (did) {
+			tmp.dentry = src_dentry;
+			vfsub_update_h_iattr(&tmp, /*did*/NULL);
+			tmp.dentry = src_dentry->d_parent;
+			vfsub_update_h_iattr(&tmp, /*did*/NULL);
+		}
+		/*ignore*/
+	}
+
+out:
+	return err;
+}
+
+int vfsub_mkdir(struct inode *dir, struct path *path, int mode)
+{
+	int err;
+	struct dentry *d;
+
+	IMustLock(dir);
+
+	d = path->dentry;
+	path->dentry = d->d_parent;
+	err = security_path_mkdir(path, d, mode);
+	path->dentry = d;
+	if (unlikely(err))
+		goto out;
+
+	lockdep_off();
+	err = vfs_mkdir(dir, path->dentry, mode);
+	lockdep_on();
+	if (!err) {
+		struct path tmp = *path;
+		int did;
+
+		vfsub_update_h_iattr(&tmp, &did);
+		if (did) {
+			tmp.dentry = path->dentry->d_parent;
+			vfsub_update_h_iattr(&tmp, /*did*/NULL);
+		}
+		/*ignore*/
+	}
+
+out:
+	return err;
+}
+
+int vfsub_rmdir(struct inode *dir, struct path *path)
+{
+	int err;
+	struct dentry *d;
+
+	IMustLock(dir);
+
+	d = path->dentry;
+	path->dentry = d->d_parent;
+	err = security_path_rmdir(path, d);
+	path->dentry = d;
+	if (unlikely(err))
+		goto out;
+
+	lockdep_off();
+	err = vfs_rmdir(dir, path->dentry);
+	lockdep_on();
+	if (!err) {
+		struct path tmp = {
+			.dentry	= path->dentry->d_parent,
+			.mnt	= path->mnt
+		};
+
+		vfsub_update_h_iattr(&tmp, /*did*/NULL); /*ignore*/
+	}
+
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* todo: support mmap_sem? */
+ssize_t vfsub_read_u(struct file *file, char __user *ubuf, size_t count,
+		     loff_t *ppos)
+{
+	ssize_t err;
+
+	lockdep_off();
+	err = vfs_read(file, ubuf, count, ppos);
+	lockdep_on();
+	if (err >= 0)
+		vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/
+	return err;
+}
+
+/* todo: kernel_read()? */
+ssize_t vfsub_read_k(struct file *file, void *kbuf, size_t count,
+		     loff_t *ppos)
+{
+	ssize_t err;
+	mm_segment_t oldfs;
+	union {
+		void *k;
+		char __user *u;
+	} buf;
+
+	buf.k = kbuf;
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	err = vfsub_read_u(file, buf.u, count, ppos);
+	set_fs(oldfs);
+	return err;
+}
+
+ssize_t vfsub_write_u(struct file *file, const char __user *ubuf, size_t count,
+		      loff_t *ppos)
+{
+	ssize_t err;
+
+	lockdep_off();
+	err = vfs_write(file, ubuf, count, ppos);
+	lockdep_on();
+	if (err >= 0)
+		vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/
+	return err;
+}
+
+ssize_t vfsub_write_k(struct file *file, void *kbuf, size_t count, loff_t *ppos)
+{
+	ssize_t err;
+	mm_segment_t oldfs;
+	union {
+		void *k;
+		const char __user *u;
+	} buf;
+
+	buf.k = kbuf;
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	err = vfsub_write_u(file, buf.u, count, ppos);
+	set_fs(oldfs);
+	return err;
+}
+
+int vfsub_flush(struct file *file, fl_owner_t id)
+{
+	int err;
+
+	err = 0;
+	if (file->f_op->flush) {
+		if (!au_test_nfs(file->f_path.dentry->d_sb))
+			err = file->f_op->flush(file, id);
+		else {
+			lockdep_off();
+			err = file->f_op->flush(file, id);
+			lockdep_on();
+		}
+		if (!err)
+			vfsub_update_h_iattr(&file->f_path, /*did*/NULL);
+		/*ignore*/
+	}
+	return err;
+}
+
+int vfsub_iterate_dir(struct file *file, struct dir_context *ctx)
+{
+	int err;
+
+	AuDbg("%pD, ctx{%pf, %llu}\n", file, ctx->actor, ctx->pos);
+
+	lockdep_off();
+	err = iterate_dir(file, ctx);
+	lockdep_on();
+	if (err >= 0)
+		vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/
+
+	return err;
+}
+
+long vfsub_splice_to(struct file *in, loff_t *ppos,
+		     struct pipe_inode_info *pipe, size_t len,
+		     unsigned int flags)
+{
+	long err;
+
+	lockdep_off();
+	err = do_splice_to(in, ppos, pipe, len, flags);
+	lockdep_on();
+	file_accessed(in);
+	if (err >= 0)
+		vfsub_update_h_iattr(&in->f_path, /*did*/NULL); /*ignore*/
+	return err;
+}
+
+long vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out,
+		       loff_t *ppos, size_t len, unsigned int flags)
+{
+	long err;
+
+	lockdep_off();
+	err = do_splice_from(pipe, out, ppos, len, flags);
+	lockdep_on();
+	if (err >= 0)
+		vfsub_update_h_iattr(&out->f_path, /*did*/NULL); /*ignore*/
+	return err;
+}
+
+int vfsub_fsync(struct file *file, struct path *path, int datasync)
+{
+	int err;
+
+	/* file can be NULL */
+	lockdep_off();
+	err = vfs_fsync(file, datasync);
+	lockdep_on();
+	if (!err) {
+		if (!path) {
+			AuDebugOn(!file);
+			path = &file->f_path;
+		}
+		vfsub_update_h_iattr(path, /*did*/NULL); /*ignore*/
+	}
+	return err;
+}
+
+/* cf. open.c:do_sys_truncate() and do_sys_ftruncate() */
+int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr,
+		struct file *h_file)
+{
+	int err;
+	struct inode *h_inode;
+	struct super_block *h_sb;
+
+	if (!h_file) {
+		err = vfsub_truncate(h_path, length);
+		goto out;
+	}
+
+	h_inode = d_inode(h_path->dentry);
+	h_sb = h_inode->i_sb;
+	lockdep_off();
+	sb_start_write(h_sb);
+	lockdep_on();
+	err = locks_verify_truncate(h_inode, h_file, length);
+	if (!err)
+		err = security_path_truncate(h_path);
+	if (!err) {
+		lockdep_off();
+		err = do_truncate(h_path->dentry, length, attr, h_file);
+		lockdep_on();
+	}
+	lockdep_off();
+	sb_end_write(h_sb);
+	lockdep_on();
+
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct au_vfsub_mkdir_args {
+	int *errp;
+	struct inode *dir;
+	struct path *path;
+	int mode;
+};
+
+static void au_call_vfsub_mkdir(void *args)
+{
+	struct au_vfsub_mkdir_args *a = args;
+	*a->errp = vfsub_mkdir(a->dir, a->path, a->mode);
+}
+
+int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode)
+{
+	int err, do_sio, wkq_err;
+
+	do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE);
+	if (!do_sio) {
+		lockdep_off();
+		err = vfsub_mkdir(dir, path, mode);
+		lockdep_on();
+	} else {
+		struct au_vfsub_mkdir_args args = {
+			.errp	= &err,
+			.dir	= dir,
+			.path	= path,
+			.mode	= mode
+		};
+		wkq_err = au_wkq_wait(au_call_vfsub_mkdir, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+	}
+
+	return err;
+}
+
+struct au_vfsub_rmdir_args {
+	int *errp;
+	struct inode *dir;
+	struct path *path;
+};
+
+static void au_call_vfsub_rmdir(void *args)
+{
+	struct au_vfsub_rmdir_args *a = args;
+	*a->errp = vfsub_rmdir(a->dir, a->path);
+}
+
+int vfsub_sio_rmdir(struct inode *dir, struct path *path)
+{
+	int err, do_sio, wkq_err;
+
+	do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE);
+	if (!do_sio) {
+		lockdep_off();
+		err = vfsub_rmdir(dir, path);
+		lockdep_on();
+	} else {
+		struct au_vfsub_rmdir_args args = {
+			.errp	= &err,
+			.dir	= dir,
+			.path	= path
+		};
+		wkq_err = au_wkq_wait(au_call_vfsub_rmdir, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct notify_change_args {
+	int *errp;
+	struct path *path;
+	struct iattr *ia;
+	struct inode **delegated_inode;
+};
+
+static void call_notify_change(void *args)
+{
+	struct notify_change_args *a = args;
+	struct inode *h_inode;
+
+	h_inode = d_inode(a->path->dentry);
+	IMustLock(h_inode);
+
+	*a->errp = -EPERM;
+	if (!IS_IMMUTABLE(h_inode) && !IS_APPEND(h_inode)) {
+		lockdep_off();
+		*a->errp = notify_change(a->path->dentry, a->ia,
+					 a->delegated_inode);
+		lockdep_on();
+		if (!*a->errp)
+			vfsub_update_h_iattr(a->path, /*did*/NULL); /*ignore*/
+	}
+	AuTraceErr(*a->errp);
+}
+
+int vfsub_notify_change(struct path *path, struct iattr *ia,
+			struct inode **delegated_inode)
+{
+	int err;
+	struct notify_change_args args = {
+		.errp			= &err,
+		.path			= path,
+		.ia			= ia,
+		.delegated_inode	= delegated_inode
+	};
+
+	call_notify_change(&args);
+
+	return err;
+}
+
+int vfsub_sio_notify_change(struct path *path, struct iattr *ia,
+			    struct inode **delegated_inode)
+{
+	int err, wkq_err;
+	struct notify_change_args args = {
+		.errp			= &err,
+		.path			= path,
+		.ia			= ia,
+		.delegated_inode	= delegated_inode
+	};
+
+	wkq_err = au_wkq_wait(call_notify_change, &args);
+	if (unlikely(wkq_err))
+		err = wkq_err;
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct unlink_args {
+	int *errp;
+	struct inode *dir;
+	struct path *path;
+	struct inode **delegated_inode;
+};
+
+static void call_unlink(void *args)
+{
+	struct unlink_args *a = args;
+	struct dentry *d = a->path->dentry;
+	struct inode *h_inode;
+	const int stop_sillyrename = (au_test_nfs(d->d_sb)
+				      && au_dcount(d) == 1);
+
+	IMustLock(a->dir);
+
+	a->path->dentry = d->d_parent;
+	*a->errp = security_path_unlink(a->path, d);
+	a->path->dentry = d;
+	if (unlikely(*a->errp))
+		return;
+
+	if (!stop_sillyrename)
+		dget(d);
+	h_inode = NULL;
+	if (d_is_positive(d)) {
+		h_inode = d_inode(d);
+		ihold(h_inode);
+	}
+
+	lockdep_off();
+	*a->errp = vfs_unlink(a->dir, d, a->delegated_inode);
+	lockdep_on();
+	if (!*a->errp) {
+		struct path tmp = {
+			.dentry = d->d_parent,
+			.mnt	= a->path->mnt
+		};
+		vfsub_update_h_iattr(&tmp, /*did*/NULL); /*ignore*/
+	}
+
+	if (!stop_sillyrename)
+		dput(d);
+	if (h_inode)
+		iput(h_inode);
+
+	AuTraceErr(*a->errp);
+}
+
+/*
+ * @dir: must be locked.
+ * @dentry: target dentry.
+ */
+int vfsub_unlink(struct inode *dir, struct path *path,
+		 struct inode **delegated_inode, int force)
+{
+	int err;
+	struct unlink_args args = {
+		.errp			= &err,
+		.dir			= dir,
+		.path			= path,
+		.delegated_inode	= delegated_inode
+	};
+
+	if (!force)
+		call_unlink(&args);
+	else {
+		int wkq_err;
+
+		wkq_err = au_wkq_wait(call_unlink, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+	}
+
+	return err;
+}
diff --git a/fs/aufs/vfsub.h b/fs/aufs/vfsub.h
new file mode 100644
index 000000000000..7ccfc83c6017
--- /dev/null
+++ b/fs/aufs/vfsub.h
@@ -0,0 +1,360 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * sub-routines for VFS
+ */
+
+#ifndef __AUFS_VFSUB_H__
+#define __AUFS_VFSUB_H__
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/posix_acl.h>
+#include <linux/xattr.h>
+#include "debug.h"
+
+/* copied from linux/fs/internal.h */
+/* todo: BAD approach!! */
+extern void __mnt_drop_write(struct vfsmount *);
+extern int open_check_o_direct(struct file *f);
+
+/* ---------------------------------------------------------------------- */
+
+/* lock subclass for lower inode */
+/* default MAX_LOCKDEP_SUBCLASSES(8) is not enough */
+/* reduce? gave up. */
+enum {
+	AuLsc_I_Begin = I_MUTEX_PARENT2, /* 5 */
+	AuLsc_I_PARENT,		/* lower inode, parent first */
+	AuLsc_I_PARENT2,	/* copyup dirs */
+	AuLsc_I_PARENT3,	/* copyup wh */
+	AuLsc_I_CHILD,
+	AuLsc_I_CHILD2,
+	AuLsc_I_End
+};
+
+/* to debug easier, do not make them inlined functions */
+#define MtxMustLock(mtx)	AuDebugOn(!mutex_is_locked(mtx))
+#define IMustLock(i)		AuDebugOn(!inode_is_locked(i))
+
+/* why VFS doesn't define it? */
+static inline
+void vfsub_inode_lock_shared_nested(struct inode *inode, unsigned int sc)
+{
+	down_read_nested(&inode->i_rwsem, sc);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static inline void vfsub_drop_nlink(struct inode *inode)
+{
+	AuDebugOn(!inode->i_nlink);
+	drop_nlink(inode);
+}
+
+static inline void vfsub_dead_dir(struct inode *inode)
+{
+	AuDebugOn(!S_ISDIR(inode->i_mode));
+	inode->i_flags |= S_DEAD;
+	clear_nlink(inode);
+}
+
+static inline int vfsub_native_ro(struct inode *inode)
+{
+	return (inode->i_sb->s_flags & MS_RDONLY)
+		|| IS_RDONLY(inode)
+		/* || IS_APPEND(inode) */
+		|| IS_IMMUTABLE(inode);
+}
+
+#ifdef CONFIG_AUFS_BR_FUSE
+int vfsub_test_mntns(struct vfsmount *mnt, struct super_block *h_sb);
+#else
+AuStubInt0(vfsub_test_mntns, struct vfsmount *mnt, struct super_block *h_sb);
+#endif
+
+int vfsub_sync_filesystem(struct super_block *h_sb, int wait);
+
+/* ---------------------------------------------------------------------- */
+
+int vfsub_update_h_iattr(struct path *h_path, int *did);
+struct file *vfsub_dentry_open(struct path *path, int flags);
+struct file *vfsub_filp_open(const char *path, int oflags, int mode);
+struct vfsub_aopen_args {
+	struct file	*file;
+	unsigned int	open_flag;
+	umode_t		create_mode;
+	int		*opened;
+};
+struct au_branch;
+int vfsub_atomic_open(struct inode *dir, struct dentry *dentry,
+		      struct vfsub_aopen_args *args, struct au_branch *br);
+int vfsub_kern_path(const char *name, unsigned int flags, struct path *path);
+
+struct dentry *vfsub_lookup_one_len_unlocked(const char *name,
+					     struct dentry *parent, int len);
+struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent,
+				    int len);
+
+struct vfsub_lkup_one_args {
+	struct dentry **errp;
+	struct qstr *name;
+	struct dentry *parent;
+};
+
+static inline struct dentry *vfsub_lkup_one(struct qstr *name,
+					    struct dentry *parent)
+{
+	return vfsub_lookup_one_len(name->name, parent, name->len);
+}
+
+void vfsub_call_lkup_one(void *args);
+
+/* ---------------------------------------------------------------------- */
+
+static inline int vfsub_mnt_want_write(struct vfsmount *mnt)
+{
+	int err;
+
+	lockdep_off();
+	err = mnt_want_write(mnt);
+	lockdep_on();
+	return err;
+}
+
+static inline void vfsub_mnt_drop_write(struct vfsmount *mnt)
+{
+	lockdep_off();
+	mnt_drop_write(mnt);
+	lockdep_on();
+}
+
+#if 0 /* reserved */
+static inline void vfsub_mnt_drop_write_file(struct file *file)
+{
+	lockdep_off();
+	mnt_drop_write_file(file);
+	lockdep_on();
+}
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+struct au_hinode;
+struct dentry *vfsub_lock_rename(struct dentry *d1, struct au_hinode *hdir1,
+				 struct dentry *d2, struct au_hinode *hdir2);
+void vfsub_unlock_rename(struct dentry *d1, struct au_hinode *hdir1,
+			 struct dentry *d2, struct au_hinode *hdir2);
+
+int vfsub_create(struct inode *dir, struct path *path, int mode,
+		 bool want_excl);
+int vfsub_symlink(struct inode *dir, struct path *path,
+		  const char *symname);
+int vfsub_mknod(struct inode *dir, struct path *path, int mode, dev_t dev);
+int vfsub_link(struct dentry *src_dentry, struct inode *dir,
+	       struct path *path, struct inode **delegated_inode);
+int vfsub_rename(struct inode *src_hdir, struct dentry *src_dentry,
+		 struct inode *hdir, struct path *path,
+		 struct inode **delegated_inode, unsigned int flags);
+int vfsub_mkdir(struct inode *dir, struct path *path, int mode);
+int vfsub_rmdir(struct inode *dir, struct path *path);
+
+/* ---------------------------------------------------------------------- */
+
+ssize_t vfsub_read_u(struct file *file, char __user *ubuf, size_t count,
+		     loff_t *ppos);
+ssize_t vfsub_read_k(struct file *file, void *kbuf, size_t count,
+			loff_t *ppos);
+ssize_t vfsub_write_u(struct file *file, const char __user *ubuf, size_t count,
+		      loff_t *ppos);
+ssize_t vfsub_write_k(struct file *file, void *kbuf, size_t count,
+		      loff_t *ppos);
+int vfsub_flush(struct file *file, fl_owner_t id);
+int vfsub_iterate_dir(struct file *file, struct dir_context *ctx);
+
+static inline loff_t vfsub_f_size_read(struct file *file)
+{
+	return i_size_read(file_inode(file));
+}
+
+static inline unsigned int vfsub_file_flags(struct file *file)
+{
+	unsigned int flags;
+
+	spin_lock(&file->f_lock);
+	flags = file->f_flags;
+	spin_unlock(&file->f_lock);
+
+	return flags;
+}
+
+static inline int vfsub_file_execed(struct file *file)
+{
+	/* todo: direct access f_flags */
+	return !!(vfsub_file_flags(file) & __FMODE_EXEC);
+}
+
+#if 0 /* reserved */
+static inline void vfsub_file_accessed(struct file *h_file)
+{
+	file_accessed(h_file);
+	vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL); /*ignore*/
+}
+#endif
+
+#if 0 /* reserved */
+static inline void vfsub_touch_atime(struct vfsmount *h_mnt,
+				     struct dentry *h_dentry)
+{
+	struct path h_path = {
+		.dentry	= h_dentry,
+		.mnt	= h_mnt
+	};
+	touch_atime(&h_path);
+	vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/
+}
+#endif
+
+static inline int vfsub_update_time(struct inode *h_inode, struct timespec *ts,
+				    int flags)
+{
+	return update_time(h_inode, ts, flags);
+	/* no vfsub_update_h_iattr() since we don't have struct path */
+}
+
+#ifdef CONFIG_FS_POSIX_ACL
+static inline int vfsub_acl_chmod(struct inode *h_inode, umode_t h_mode)
+{
+	int err;
+
+	err = posix_acl_chmod(h_inode, h_mode);
+	if (err == -EOPNOTSUPP)
+		err = 0;
+	return err;
+}
+#else
+AuStubInt0(vfsub_acl_chmod, struct inode *h_inode, umode_t h_mode);
+#endif
+
+long vfsub_splice_to(struct file *in, loff_t *ppos,
+		     struct pipe_inode_info *pipe, size_t len,
+		     unsigned int flags);
+long vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out,
+		       loff_t *ppos, size_t len, unsigned int flags);
+
+static inline long vfsub_truncate(struct path *path, loff_t length)
+{
+	long err;
+
+	lockdep_off();
+	err = vfs_truncate(path, length);
+	lockdep_on();
+	return err;
+}
+
+int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr,
+		struct file *h_file);
+int vfsub_fsync(struct file *file, struct path *path, int datasync);
+
+/*
+ * re-use branch fs's ioctl(FICLONE) while aufs itself doesn't support such
+ * ioctl.
+ */
+static inline int vfsub_clone_file_range(struct file *src, struct file *dst,
+					 u64 len)
+{
+	int err;
+
+	lockdep_off();
+	err = vfs_clone_file_range(src, 0, dst, 0, len);
+	lockdep_on();
+
+	return err;
+}
+
+/* copy_file_range(2) is a systemcall */
+static inline ssize_t vfsub_copy_file_range(struct file *src, loff_t src_pos,
+					    struct file *dst, loff_t dst_pos,
+					    size_t len, unsigned int flags)
+{
+	ssize_t ssz;
+
+	lockdep_off();
+	ssz = vfs_copy_file_range(src, src_pos, dst, dst_pos, len, flags);
+	lockdep_on();
+
+	return ssz;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static inline loff_t vfsub_llseek(struct file *file, loff_t offset, int origin)
+{
+	loff_t err;
+
+	lockdep_off();
+	err = vfs_llseek(file, offset, origin);
+	lockdep_on();
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode);
+int vfsub_sio_rmdir(struct inode *dir, struct path *path);
+int vfsub_sio_notify_change(struct path *path, struct iattr *ia,
+			    struct inode **delegated_inode);
+int vfsub_notify_change(struct path *path, struct iattr *ia,
+			struct inode **delegated_inode);
+int vfsub_unlink(struct inode *dir, struct path *path,
+		 struct inode **delegated_inode, int force);
+
+static inline int vfsub_getattr(const struct path *path, struct kstat *st)
+{
+	return vfs_getattr(path, st, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static inline int vfsub_setxattr(struct dentry *dentry, const char *name,
+				 const void *value, size_t size, int flags)
+{
+	int err;
+
+	lockdep_off();
+	err = vfs_setxattr(dentry, name, value, size, flags);
+	lockdep_on();
+
+	return err;
+}
+
+static inline int vfsub_removexattr(struct dentry *dentry, const char *name)
+{
+	int err;
+
+	lockdep_off();
+	err = vfs_removexattr(dentry, name);
+	lockdep_on();
+
+	return err;
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_VFSUB_H__ */
diff --git a/fs/aufs/wbr_policy.c b/fs/aufs/wbr_policy.c
new file mode 100644
index 000000000000..a28296d9cd31
--- /dev/null
+++ b/fs/aufs/wbr_policy.c
@@ -0,0 +1,830 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * policies for selecting one among multiple writable branches
+ */
+
+#include <linux/statfs.h>
+#include "aufs.h"
+
+/* subset of cpup_attr() */
+static noinline_for_stack
+int au_cpdown_attr(struct path *h_path, struct dentry *h_src)
+{
+	int err, sbits;
+	struct iattr ia;
+	struct inode *h_isrc;
+
+	h_isrc = d_inode(h_src);
+	ia.ia_valid = ATTR_FORCE | ATTR_MODE | ATTR_UID | ATTR_GID;
+	ia.ia_mode = h_isrc->i_mode;
+	ia.ia_uid = h_isrc->i_uid;
+	ia.ia_gid = h_isrc->i_gid;
+	sbits = !!(ia.ia_mode & (S_ISUID | S_ISGID));
+	au_cpup_attr_flags(d_inode(h_path->dentry), h_isrc->i_flags);
+	/* no delegation since it is just created */
+	err = vfsub_sio_notify_change(h_path, &ia, /*delegated*/NULL);
+
+	/* is this nfs only? */
+	if (!err && sbits && au_test_nfs(h_path->dentry->d_sb)) {
+		ia.ia_valid = ATTR_FORCE | ATTR_MODE;
+		ia.ia_mode = h_isrc->i_mode;
+		err = vfsub_sio_notify_change(h_path, &ia, /*delegated*/NULL);
+	}
+
+	return err;
+}
+
+#define AuCpdown_PARENT_OPQ	1
+#define AuCpdown_WHED		(1 << 1)
+#define AuCpdown_MADE_DIR	(1 << 2)
+#define AuCpdown_DIROPQ		(1 << 3)
+#define au_ftest_cpdown(flags, name)	((flags) & AuCpdown_##name)
+#define au_fset_cpdown(flags, name) \
+	do { (flags) |= AuCpdown_##name; } while (0)
+#define au_fclr_cpdown(flags, name) \
+	do { (flags) &= ~AuCpdown_##name; } while (0)
+
+static int au_cpdown_dir_opq(struct dentry *dentry, aufs_bindex_t bdst,
+			     unsigned int *flags)
+{
+	int err;
+	struct dentry *opq_dentry;
+
+	opq_dentry = au_diropq_create(dentry, bdst);
+	err = PTR_ERR(opq_dentry);
+	if (IS_ERR(opq_dentry))
+		goto out;
+	dput(opq_dentry);
+	au_fset_cpdown(*flags, DIROPQ);
+
+out:
+	return err;
+}
+
+static int au_cpdown_dir_wh(struct dentry *dentry, struct dentry *h_parent,
+			    struct inode *dir, aufs_bindex_t bdst)
+{
+	int err;
+	struct path h_path;
+	struct au_branch *br;
+
+	br = au_sbr(dentry->d_sb, bdst);
+	h_path.dentry = au_wh_lkup(h_parent, &dentry->d_name, br);
+	err = PTR_ERR(h_path.dentry);
+	if (IS_ERR(h_path.dentry))
+		goto out;
+
+	err = 0;
+	if (d_is_positive(h_path.dentry)) {
+		h_path.mnt = au_br_mnt(br);
+		err = au_wh_unlink_dentry(au_h_iptr(dir, bdst), &h_path,
+					  dentry);
+	}
+	dput(h_path.dentry);
+
+out:
+	return err;
+}
+
+static int au_cpdown_dir(struct dentry *dentry, aufs_bindex_t bdst,
+			 struct au_pin *pin,
+			 struct dentry *h_parent, void *arg)
+{
+	int err, rerr;
+	aufs_bindex_t bopq, btop;
+	struct path h_path;
+	struct dentry *parent;
+	struct inode *h_dir, *h_inode, *inode, *dir;
+	unsigned int *flags = arg;
+
+	btop = au_dbtop(dentry);
+	/* dentry is di-locked */
+	parent = dget_parent(dentry);
+	dir = d_inode(parent);
+	h_dir = d_inode(h_parent);
+	AuDebugOn(h_dir != au_h_iptr(dir, bdst));
+	IMustLock(h_dir);
+
+	err = au_lkup_neg(dentry, bdst, /*wh*/0);
+	if (unlikely(err < 0))
+		goto out;
+	h_path.dentry = au_h_dptr(dentry, bdst);
+	h_path.mnt = au_sbr_mnt(dentry->d_sb, bdst);
+	err = vfsub_sio_mkdir(au_h_iptr(dir, bdst), &h_path,
+			      S_IRWXU | S_IRUGO | S_IXUGO);
+	if (unlikely(err))
+		goto out_put;
+	au_fset_cpdown(*flags, MADE_DIR);
+
+	bopq = au_dbdiropq(dentry);
+	au_fclr_cpdown(*flags, WHED);
+	au_fclr_cpdown(*flags, DIROPQ);
+	if (au_dbwh(dentry) == bdst)
+		au_fset_cpdown(*flags, WHED);
+	if (!au_ftest_cpdown(*flags, PARENT_OPQ) && bopq <= bdst)
+		au_fset_cpdown(*flags, PARENT_OPQ);
+	h_inode = d_inode(h_path.dentry);
+	inode_lock_nested(h_inode, AuLsc_I_CHILD);
+	if (au_ftest_cpdown(*flags, WHED)) {
+		err = au_cpdown_dir_opq(dentry, bdst, flags);
+		if (unlikely(err)) {
+			inode_unlock(h_inode);
+			goto out_dir;
+		}
+	}
+
+	err = au_cpdown_attr(&h_path, au_h_dptr(dentry, btop));
+	inode_unlock(h_inode);
+	if (unlikely(err))
+		goto out_opq;
+
+	if (au_ftest_cpdown(*flags, WHED)) {
+		err = au_cpdown_dir_wh(dentry, h_parent, dir, bdst);
+		if (unlikely(err))
+			goto out_opq;
+	}
+
+	inode = d_inode(dentry);
+	if (au_ibbot(inode) < bdst)
+		au_set_ibbot(inode, bdst);
+	au_set_h_iptr(inode, bdst, au_igrab(h_inode),
+		      au_hi_flags(inode, /*isdir*/1));
+	au_fhsm_wrote(dentry->d_sb, bdst, /*force*/0);
+	goto out; /* success */
+
+	/* revert */
+out_opq:
+	if (au_ftest_cpdown(*flags, DIROPQ)) {
+		inode_lock_nested(h_inode, AuLsc_I_CHILD);
+		rerr = au_diropq_remove(dentry, bdst);
+		inode_unlock(h_inode);
+		if (unlikely(rerr)) {
+			AuIOErr("failed removing diropq for %pd b%d (%d)\n",
+				dentry, bdst, rerr);
+			err = -EIO;
+			goto out;
+		}
+	}
+out_dir:
+	if (au_ftest_cpdown(*flags, MADE_DIR)) {
+		rerr = vfsub_sio_rmdir(au_h_iptr(dir, bdst), &h_path);
+		if (unlikely(rerr)) {
+			AuIOErr("failed removing %pd b%d (%d)\n",
+				dentry, bdst, rerr);
+			err = -EIO;
+		}
+	}
+out_put:
+	au_set_h_dptr(dentry, bdst, NULL);
+	if (au_dbbot(dentry) == bdst)
+		au_update_dbbot(dentry);
+out:
+	dput(parent);
+	return err;
+}
+
+int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst)
+{
+	int err;
+	unsigned int flags;
+
+	flags = 0;
+	err = au_cp_dirs(dentry, bdst, au_cpdown_dir, &flags);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* policies for create */
+
+int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex)
+{
+	int err, i, j, ndentry;
+	aufs_bindex_t bopq;
+	struct au_dcsub_pages dpages;
+	struct au_dpage *dpage;
+	struct dentry **dentries, *parent, *d;
+
+	err = au_dpages_init(&dpages, GFP_NOFS);
+	if (unlikely(err))
+		goto out;
+	parent = dget_parent(dentry);
+	err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/0);
+	if (unlikely(err))
+		goto out_free;
+
+	err = bindex;
+	for (i = 0; i < dpages.ndpage; i++) {
+		dpage = dpages.dpages + i;
+		dentries = dpage->dentries;
+		ndentry = dpage->ndentry;
+		for (j = 0; j < ndentry; j++) {
+			d = dentries[j];
+			di_read_lock_parent2(d, !AuLock_IR);
+			bopq = au_dbdiropq(d);
+			di_read_unlock(d, !AuLock_IR);
+			if (bopq >= 0 && bopq < err)
+				err = bopq;
+		}
+	}
+
+out_free:
+	dput(parent);
+	au_dpages_free(&dpages);
+out:
+	return err;
+}
+
+static int au_wbr_bu(struct super_block *sb, aufs_bindex_t bindex)
+{
+	for (; bindex >= 0; bindex--)
+		if (!au_br_rdonly(au_sbr(sb, bindex)))
+			return bindex;
+	return -EROFS;
+}
+
+/* top down parent */
+static int au_wbr_create_tdp(struct dentry *dentry,
+			     unsigned int flags __maybe_unused)
+{
+	int err;
+	aufs_bindex_t btop, bindex;
+	struct super_block *sb;
+	struct dentry *parent, *h_parent;
+
+	sb = dentry->d_sb;
+	btop = au_dbtop(dentry);
+	err = btop;
+	if (!au_br_rdonly(au_sbr(sb, btop)))
+		goto out;
+
+	err = -EROFS;
+	parent = dget_parent(dentry);
+	for (bindex = au_dbtop(parent); bindex < btop; bindex++) {
+		h_parent = au_h_dptr(parent, bindex);
+		if (!h_parent || d_is_negative(h_parent))
+			continue;
+
+		if (!au_br_rdonly(au_sbr(sb, bindex))) {
+			err = bindex;
+			break;
+		}
+	}
+	dput(parent);
+
+	/* bottom up here */
+	if (unlikely(err < 0)) {
+		err = au_wbr_bu(sb, btop - 1);
+		if (err >= 0)
+			err = au_wbr_nonopq(dentry, err);
+	}
+
+out:
+	AuDbg("b%d\n", err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* an exception for the policy other than tdp */
+static int au_wbr_create_exp(struct dentry *dentry)
+{
+	int err;
+	aufs_bindex_t bwh, bdiropq;
+	struct dentry *parent;
+
+	err = -1;
+	bwh = au_dbwh(dentry);
+	parent = dget_parent(dentry);
+	bdiropq = au_dbdiropq(parent);
+	if (bwh >= 0) {
+		if (bdiropq >= 0)
+			err = min(bdiropq, bwh);
+		else
+			err = bwh;
+		AuDbg("%d\n", err);
+	} else if (bdiropq >= 0) {
+		err = bdiropq;
+		AuDbg("%d\n", err);
+	}
+	dput(parent);
+
+	if (err >= 0)
+		err = au_wbr_nonopq(dentry, err);
+
+	if (err >= 0 && au_br_rdonly(au_sbr(dentry->d_sb, err)))
+		err = -1;
+
+	AuDbg("%d\n", err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* round robin */
+static int au_wbr_create_init_rr(struct super_block *sb)
+{
+	int err;
+
+	err = au_wbr_bu(sb, au_sbbot(sb));
+	atomic_set(&au_sbi(sb)->si_wbr_rr_next, -err); /* less important */
+	/* smp_mb(); */
+
+	AuDbg("b%d\n", err);
+	return err;
+}
+
+static int au_wbr_create_rr(struct dentry *dentry, unsigned int flags)
+{
+	int err, nbr;
+	unsigned int u;
+	aufs_bindex_t bindex, bbot;
+	struct super_block *sb;
+	atomic_t *next;
+
+	err = au_wbr_create_exp(dentry);
+	if (err >= 0)
+		goto out;
+
+	sb = dentry->d_sb;
+	next = &au_sbi(sb)->si_wbr_rr_next;
+	bbot = au_sbbot(sb);
+	nbr = bbot + 1;
+	for (bindex = 0; bindex <= bbot; bindex++) {
+		if (!au_ftest_wbr(flags, DIR)) {
+			err = atomic_dec_return(next) + 1;
+			/* modulo for 0 is meaningless */
+			if (unlikely(!err))
+				err = atomic_dec_return(next) + 1;
+		} else
+			err = atomic_read(next);
+		AuDbg("%d\n", err);
+		u = err;
+		err = u % nbr;
+		AuDbg("%d\n", err);
+		if (!au_br_rdonly(au_sbr(sb, err)))
+			break;
+		err = -EROFS;
+	}
+
+	if (err >= 0)
+		err = au_wbr_nonopq(dentry, err);
+
+out:
+	AuDbg("%d\n", err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* most free space */
+static void au_mfs(struct dentry *dentry, struct dentry *parent)
+{
+	struct super_block *sb;
+	struct au_branch *br;
+	struct au_wbr_mfs *mfs;
+	struct dentry *h_parent;
+	aufs_bindex_t bindex, bbot;
+	int err;
+	unsigned long long b, bavail;
+	struct path h_path;
+	/* reduce the stack usage */
+	struct kstatfs *st;
+
+	st = kmalloc(sizeof(*st), GFP_NOFS);
+	if (unlikely(!st)) {
+		AuWarn1("failed updating mfs(%d), ignored\n", -ENOMEM);
+		return;
+	}
+
+	bavail = 0;
+	sb = dentry->d_sb;
+	mfs = &au_sbi(sb)->si_wbr_mfs;
+	MtxMustLock(&mfs->mfs_lock);
+	mfs->mfs_bindex = -EROFS;
+	mfs->mfsrr_bytes = 0;
+	if (!parent) {
+		bindex = 0;
+		bbot = au_sbbot(sb);
+	} else {
+		bindex = au_dbtop(parent);
+		bbot = au_dbtaildir(parent);
+	}
+
+	for (; bindex <= bbot; bindex++) {
+		if (parent) {
+			h_parent = au_h_dptr(parent, bindex);
+			if (!h_parent || d_is_negative(h_parent))
+				continue;
+		}
+		br = au_sbr(sb, bindex);
+		if (au_br_rdonly(br))
+			continue;
+
+		/* sb->s_root for NFS is unreliable */
+		h_path.mnt = au_br_mnt(br);
+		h_path.dentry = h_path.mnt->mnt_root;
+		err = vfs_statfs(&h_path, st);
+		if (unlikely(err)) {
+			AuWarn1("failed statfs, b%d, %d\n", bindex, err);
+			continue;
+		}
+
+		/* when the available size is equal, select the lower one */
+		BUILD_BUG_ON(sizeof(b) < sizeof(st->f_bavail)
+			     || sizeof(b) < sizeof(st->f_bsize));
+		b = st->f_bavail * st->f_bsize;
+		br->br_wbr->wbr_bytes = b;
+		if (b >= bavail) {
+			bavail = b;
+			mfs->mfs_bindex = bindex;
+			mfs->mfs_jiffy = jiffies;
+		}
+	}
+
+	mfs->mfsrr_bytes = bavail;
+	AuDbg("b%d\n", mfs->mfs_bindex);
+	kfree(st);
+}
+
+static int au_wbr_create_mfs(struct dentry *dentry, unsigned int flags)
+{
+	int err;
+	struct dentry *parent;
+	struct super_block *sb;
+	struct au_wbr_mfs *mfs;
+
+	err = au_wbr_create_exp(dentry);
+	if (err >= 0)
+		goto out;
+
+	sb = dentry->d_sb;
+	parent = NULL;
+	if (au_ftest_wbr(flags, PARENT))
+		parent = dget_parent(dentry);
+	mfs = &au_sbi(sb)->si_wbr_mfs;
+	mutex_lock(&mfs->mfs_lock);
+	if (time_after(jiffies, mfs->mfs_jiffy + mfs->mfs_expire)
+	    || mfs->mfs_bindex < 0
+	    || au_br_rdonly(au_sbr(sb, mfs->mfs_bindex)))
+		au_mfs(dentry, parent);
+	mutex_unlock(&mfs->mfs_lock);
+	err = mfs->mfs_bindex;
+	dput(parent);
+
+	if (err >= 0)
+		err = au_wbr_nonopq(dentry, err);
+
+out:
+	AuDbg("b%d\n", err);
+	return err;
+}
+
+static int au_wbr_create_init_mfs(struct super_block *sb)
+{
+	struct au_wbr_mfs *mfs;
+
+	mfs = &au_sbi(sb)->si_wbr_mfs;
+	mutex_init(&mfs->mfs_lock);
+	mfs->mfs_jiffy = 0;
+	mfs->mfs_bindex = -EROFS;
+
+	return 0;
+}
+
+static int au_wbr_create_fin_mfs(struct super_block *sb __maybe_unused)
+{
+	mutex_destroy(&au_sbi(sb)->si_wbr_mfs.mfs_lock);
+	return 0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* top down regardless parent, and then mfs */
+static int au_wbr_create_tdmfs(struct dentry *dentry,
+			       unsigned int flags __maybe_unused)
+{
+	int err;
+	aufs_bindex_t bwh, btail, bindex, bfound, bmfs;
+	unsigned long long watermark;
+	struct super_block *sb;
+	struct au_wbr_mfs *mfs;
+	struct au_branch *br;
+	struct dentry *parent;
+
+	sb = dentry->d_sb;
+	mfs = &au_sbi(sb)->si_wbr_mfs;
+	mutex_lock(&mfs->mfs_lock);
+	if (time_after(jiffies, mfs->mfs_jiffy + mfs->mfs_expire)
+	    || mfs->mfs_bindex < 0)
+		au_mfs(dentry, /*parent*/NULL);
+	watermark = mfs->mfsrr_watermark;
+	bmfs = mfs->mfs_bindex;
+	mutex_unlock(&mfs->mfs_lock);
+
+	/* another style of au_wbr_create_exp() */
+	bwh = au_dbwh(dentry);
+	parent = dget_parent(dentry);
+	btail = au_dbtaildir(parent);
+	if (bwh >= 0 && bwh < btail)
+		btail = bwh;
+
+	err = au_wbr_nonopq(dentry, btail);
+	if (unlikely(err < 0))
+		goto out;
+	btail = err;
+	bfound = -1;
+	for (bindex = 0; bindex <= btail; bindex++) {
+		br = au_sbr(sb, bindex);
+		if (au_br_rdonly(br))
+			continue;
+		if (br->br_wbr->wbr_bytes > watermark) {
+			bfound = bindex;
+			break;
+		}
+	}
+	err = bfound;
+	if (err < 0)
+		err = bmfs;
+
+out:
+	dput(parent);
+	AuDbg("b%d\n", err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* most free space and then round robin */
+static int au_wbr_create_mfsrr(struct dentry *dentry, unsigned int flags)
+{
+	int err;
+	struct au_wbr_mfs *mfs;
+
+	err = au_wbr_create_mfs(dentry, flags);
+	if (err >= 0) {
+		mfs = &au_sbi(dentry->d_sb)->si_wbr_mfs;
+		mutex_lock(&mfs->mfs_lock);
+		if (mfs->mfsrr_bytes < mfs->mfsrr_watermark)
+			err = au_wbr_create_rr(dentry, flags);
+		mutex_unlock(&mfs->mfs_lock);
+	}
+
+	AuDbg("b%d\n", err);
+	return err;
+}
+
+static int au_wbr_create_init_mfsrr(struct super_block *sb)
+{
+	int err;
+
+	au_wbr_create_init_mfs(sb); /* ignore */
+	err = au_wbr_create_init_rr(sb);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* top down parent and most free space */
+static int au_wbr_create_pmfs(struct dentry *dentry, unsigned int flags)
+{
+	int err, e2;
+	unsigned long long b;
+	aufs_bindex_t bindex, btop, bbot;
+	struct super_block *sb;
+	struct dentry *parent, *h_parent;
+	struct au_branch *br;
+
+	err = au_wbr_create_tdp(dentry, flags);
+	if (unlikely(err < 0))
+		goto out;
+	parent = dget_parent(dentry);
+	btop = au_dbtop(parent);
+	bbot = au_dbtaildir(parent);
+	if (btop == bbot)
+		goto out_parent; /* success */
+
+	e2 = au_wbr_create_mfs(dentry, flags);
+	if (e2 < 0)
+		goto out_parent; /* success */
+
+	/* when the available size is equal, select upper one */
+	sb = dentry->d_sb;
+	br = au_sbr(sb, err);
+	b = br->br_wbr->wbr_bytes;
+	AuDbg("b%d, %llu\n", err, b);
+
+	for (bindex = btop; bindex <= bbot; bindex++) {
+		h_parent = au_h_dptr(parent, bindex);
+		if (!h_parent || d_is_negative(h_parent))
+			continue;
+
+		br = au_sbr(sb, bindex);
+		if (!au_br_rdonly(br) && br->br_wbr->wbr_bytes > b) {
+			b = br->br_wbr->wbr_bytes;
+			err = bindex;
+			AuDbg("b%d, %llu\n", err, b);
+		}
+	}
+
+	if (err >= 0)
+		err = au_wbr_nonopq(dentry, err);
+
+out_parent:
+	dput(parent);
+out:
+	AuDbg("b%d\n", err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * - top down parent
+ * - most free space with parent
+ * - most free space round-robin regardless parent
+ */
+static int au_wbr_create_pmfsrr(struct dentry *dentry, unsigned int flags)
+{
+	int err;
+	unsigned long long watermark;
+	struct super_block *sb;
+	struct au_branch *br;
+	struct au_wbr_mfs *mfs;
+
+	err = au_wbr_create_pmfs(dentry, flags | AuWbr_PARENT);
+	if (unlikely(err < 0))
+		goto out;
+
+	sb = dentry->d_sb;
+	br = au_sbr(sb, err);
+	mfs = &au_sbi(sb)->si_wbr_mfs;
+	mutex_lock(&mfs->mfs_lock);
+	watermark = mfs->mfsrr_watermark;
+	mutex_unlock(&mfs->mfs_lock);
+	if (br->br_wbr->wbr_bytes < watermark)
+		/* regardless the parent dir */
+		err = au_wbr_create_mfsrr(dentry, flags);
+
+out:
+	AuDbg("b%d\n", err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* policies for copyup */
+
+/* top down parent */
+static int au_wbr_copyup_tdp(struct dentry *dentry)
+{
+	return au_wbr_create_tdp(dentry, /*flags, anything is ok*/0);
+}
+
+/* bottom up parent */
+static int au_wbr_copyup_bup(struct dentry *dentry)
+{
+	int err;
+	aufs_bindex_t bindex, btop;
+	struct dentry *parent, *h_parent;
+	struct super_block *sb;
+
+	err = -EROFS;
+	sb = dentry->d_sb;
+	parent = dget_parent(dentry);
+	btop = au_dbtop(parent);
+	for (bindex = au_dbtop(dentry); bindex >= btop; bindex--) {
+		h_parent = au_h_dptr(parent, bindex);
+		if (!h_parent || d_is_negative(h_parent))
+			continue;
+
+		if (!au_br_rdonly(au_sbr(sb, bindex))) {
+			err = bindex;
+			break;
+		}
+	}
+	dput(parent);
+
+	/* bottom up here */
+	if (unlikely(err < 0))
+		err = au_wbr_bu(sb, btop - 1);
+
+	AuDbg("b%d\n", err);
+	return err;
+}
+
+/* bottom up */
+int au_wbr_do_copyup_bu(struct dentry *dentry, aufs_bindex_t btop)
+{
+	int err;
+
+	err = au_wbr_bu(dentry->d_sb, btop);
+	AuDbg("b%d\n", err);
+	if (err > btop)
+		err = au_wbr_nonopq(dentry, err);
+
+	AuDbg("b%d\n", err);
+	return err;
+}
+
+static int au_wbr_copyup_bu(struct dentry *dentry)
+{
+	int err;
+	aufs_bindex_t btop;
+
+	btop = au_dbtop(dentry);
+	err = au_wbr_do_copyup_bu(dentry, btop);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct au_wbr_copyup_operations au_wbr_copyup_ops[] = {
+	[AuWbrCopyup_TDP] = {
+		.copyup	= au_wbr_copyup_tdp
+	},
+	[AuWbrCopyup_BUP] = {
+		.copyup	= au_wbr_copyup_bup
+	},
+	[AuWbrCopyup_BU] = {
+		.copyup	= au_wbr_copyup_bu
+	}
+};
+
+struct au_wbr_create_operations au_wbr_create_ops[] = {
+	[AuWbrCreate_TDP] = {
+		.create	= au_wbr_create_tdp
+	},
+	[AuWbrCreate_RR] = {
+		.create	= au_wbr_create_rr,
+		.init	= au_wbr_create_init_rr
+	},
+	[AuWbrCreate_MFS] = {
+		.create	= au_wbr_create_mfs,
+		.init	= au_wbr_create_init_mfs,
+		.fin	= au_wbr_create_fin_mfs
+	},
+	[AuWbrCreate_MFSV] = {
+		.create	= au_wbr_create_mfs,
+		.init	= au_wbr_create_init_mfs,
+		.fin	= au_wbr_create_fin_mfs
+	},
+	[AuWbrCreate_MFSRR] = {
+		.create	= au_wbr_create_mfsrr,
+		.init	= au_wbr_create_init_mfsrr,
+		.fin	= au_wbr_create_fin_mfs
+	},
+	[AuWbrCreate_MFSRRV] = {
+		.create	= au_wbr_create_mfsrr,
+		.init	= au_wbr_create_init_mfsrr,
+		.fin	= au_wbr_create_fin_mfs
+	},
+	[AuWbrCreate_TDMFS] = {
+		.create	= au_wbr_create_tdmfs,
+		.init	= au_wbr_create_init_mfs,
+		.fin	= au_wbr_create_fin_mfs
+	},
+	[AuWbrCreate_TDMFSV] = {
+		.create	= au_wbr_create_tdmfs,
+		.init	= au_wbr_create_init_mfs,
+		.fin	= au_wbr_create_fin_mfs
+	},
+	[AuWbrCreate_PMFS] = {
+		.create	= au_wbr_create_pmfs,
+		.init	= au_wbr_create_init_mfs,
+		.fin	= au_wbr_create_fin_mfs
+	},
+	[AuWbrCreate_PMFSV] = {
+		.create	= au_wbr_create_pmfs,
+		.init	= au_wbr_create_init_mfs,
+		.fin	= au_wbr_create_fin_mfs
+	},
+	[AuWbrCreate_PMFSRR] = {
+		.create	= au_wbr_create_pmfsrr,
+		.init	= au_wbr_create_init_mfsrr,
+		.fin	= au_wbr_create_fin_mfs
+	},
+	[AuWbrCreate_PMFSRRV] = {
+		.create	= au_wbr_create_pmfsrr,
+		.init	= au_wbr_create_init_mfsrr,
+		.fin	= au_wbr_create_fin_mfs
+	}
+};
diff --git a/fs/aufs/whout.c b/fs/aufs/whout.c
new file mode 100644
index 000000000000..05c069ebb7c4
--- /dev/null
+++ b/fs/aufs/whout.c
@@ -0,0 +1,1061 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * whiteout for logical deletion and opaque directory
+ */
+
+#include "aufs.h"
+
+#define WH_MASK			S_IRUGO
+
+/*
+ * If a directory contains this file, then it is opaque.  We start with the
+ * .wh. flag so that it is blocked by lookup.
+ */
+static struct qstr diropq_name = QSTR_INIT(AUFS_WH_DIROPQ,
+					   sizeof(AUFS_WH_DIROPQ) - 1);
+
+/*
+ * generate whiteout name, which is NOT terminated by NULL.
+ * @name: original d_name.name
+ * @len: original d_name.len
+ * @wh: whiteout qstr
+ * returns zero when succeeds, otherwise error.
+ * succeeded value as wh->name should be freed by kfree().
+ */
+int au_wh_name_alloc(struct qstr *wh, const struct qstr *name)
+{
+	char *p;
+
+	if (unlikely(name->len > PATH_MAX - AUFS_WH_PFX_LEN))
+		return -ENAMETOOLONG;
+
+	wh->len = name->len + AUFS_WH_PFX_LEN;
+	p = kmalloc(wh->len, GFP_NOFS);
+	wh->name = p;
+	if (p) {
+		memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN);
+		memcpy(p + AUFS_WH_PFX_LEN, name->name, name->len);
+		/* smp_mb(); */
+		return 0;
+	}
+	return -ENOMEM;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * test if the @wh_name exists under @h_parent.
+ * @try_sio specifies the necessary of super-io.
+ */
+int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, int try_sio)
+{
+	int err;
+	struct dentry *wh_dentry;
+
+	if (!try_sio)
+		wh_dentry = vfsub_lkup_one(wh_name, h_parent);
+	else
+		wh_dentry = au_sio_lkup_one(wh_name, h_parent);
+	err = PTR_ERR(wh_dentry);
+	if (IS_ERR(wh_dentry)) {
+		if (err == -ENAMETOOLONG)
+			err = 0;
+		goto out;
+	}
+
+	err = 0;
+	if (d_is_negative(wh_dentry))
+		goto out_wh; /* success */
+
+	err = 1;
+	if (d_is_reg(wh_dentry))
+		goto out_wh; /* success */
+
+	err = -EIO;
+	AuIOErr("%pd Invalid whiteout entry type 0%o.\n",
+		wh_dentry, d_inode(wh_dentry)->i_mode);
+
+out_wh:
+	dput(wh_dentry);
+out:
+	return err;
+}
+
+/*
+ * test if the @h_dentry sets opaque or not.
+ */
+int au_diropq_test(struct dentry *h_dentry)
+{
+	int err;
+	struct inode *h_dir;
+
+	h_dir = d_inode(h_dentry);
+	err = au_wh_test(h_dentry, &diropq_name,
+			 au_test_h_perm_sio(h_dir, MAY_EXEC));
+	return err;
+}
+
+/*
+ * returns a negative dentry whose name is unique and temporary.
+ */
+struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br,
+			     struct qstr *prefix)
+{
+	struct dentry *dentry;
+	int i;
+	char defname[NAME_MAX - AUFS_MAX_NAMELEN + DNAME_INLINE_LEN + 1],
+		*name, *p;
+	/* strict atomic_t is unnecessary here */
+	static unsigned short cnt;
+	struct qstr qs;
+
+	BUILD_BUG_ON(sizeof(cnt) * 2 > AUFS_WH_TMP_LEN);
+
+	name = defname;
+	qs.len = sizeof(defname) - DNAME_INLINE_LEN + prefix->len - 1;
+	if (unlikely(prefix->len > DNAME_INLINE_LEN)) {
+		dentry = ERR_PTR(-ENAMETOOLONG);
+		if (unlikely(qs.len > NAME_MAX))
+			goto out;
+		dentry = ERR_PTR(-ENOMEM);
+		name = kmalloc(qs.len + 1, GFP_NOFS);
+		if (unlikely(!name))
+			goto out;
+	}
+
+	/* doubly whiteout-ed */
+	memcpy(name, AUFS_WH_PFX AUFS_WH_PFX, AUFS_WH_PFX_LEN * 2);
+	p = name + AUFS_WH_PFX_LEN * 2;
+	memcpy(p, prefix->name, prefix->len);
+	p += prefix->len;
+	*p++ = '.';
+	AuDebugOn(name + qs.len + 1 - p <= AUFS_WH_TMP_LEN);
+
+	qs.name = name;
+	for (i = 0; i < 3; i++) {
+		sprintf(p, "%.*x", AUFS_WH_TMP_LEN, cnt++);
+		dentry = au_sio_lkup_one(&qs, h_parent);
+		if (IS_ERR(dentry) || d_is_negative(dentry))
+			goto out_name;
+		dput(dentry);
+	}
+	/* pr_warn("could not get random name\n"); */
+	dentry = ERR_PTR(-EEXIST);
+	AuDbg("%.*s\n", AuLNPair(&qs));
+	BUG();
+
+out_name:
+	if (name != defname)
+		kfree(name);
+out:
+	AuTraceErrPtr(dentry);
+	return dentry;
+}
+
+/*
+ * rename the @h_dentry on @br to the whiteouted temporary name.
+ */
+int au_whtmp_ren(struct dentry *h_dentry, struct au_branch *br)
+{
+	int err;
+	struct path h_path = {
+		.mnt = au_br_mnt(br)
+	};
+	struct inode *h_dir, *delegated;
+	struct dentry *h_parent;
+
+	h_parent = h_dentry->d_parent; /* dir inode is locked */
+	h_dir = d_inode(h_parent);
+	IMustLock(h_dir);
+
+	h_path.dentry = au_whtmp_lkup(h_parent, br, &h_dentry->d_name);
+	err = PTR_ERR(h_path.dentry);
+	if (IS_ERR(h_path.dentry))
+		goto out;
+
+	/* under the same dir, no need to lock_rename() */
+	delegated = NULL;
+	err = vfsub_rename(h_dir, h_dentry, h_dir, &h_path, &delegated,
+			   /*flags*/0);
+	AuTraceErr(err);
+	if (unlikely(err == -EWOULDBLOCK)) {
+		pr_warn("cannot retry for NFSv4 delegation"
+			" for an internal rename\n");
+		iput(delegated);
+	}
+	dput(h_path.dentry);
+
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+/*
+ * functions for removing a whiteout
+ */
+
+static int do_unlink_wh(struct inode *h_dir, struct path *h_path)
+{
+	int err, force;
+	struct inode *delegated;
+
+	/*
+	 * forces superio when the dir has a sticky bit.
+	 * this may be a violation of unix fs semantics.
+	 */
+	force = (h_dir->i_mode & S_ISVTX)
+		&& !uid_eq(current_fsuid(), d_inode(h_path->dentry)->i_uid);
+	delegated = NULL;
+	err = vfsub_unlink(h_dir, h_path, &delegated, force);
+	if (unlikely(err == -EWOULDBLOCK)) {
+		pr_warn("cannot retry for NFSv4 delegation"
+			" for an internal unlink\n");
+		iput(delegated);
+	}
+	return err;
+}
+
+int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path,
+			struct dentry *dentry)
+{
+	int err;
+
+	err = do_unlink_wh(h_dir, h_path);
+	if (!err && dentry)
+		au_set_dbwh(dentry, -1);
+
+	return err;
+}
+
+static int unlink_wh_name(struct dentry *h_parent, struct qstr *wh,
+			  struct au_branch *br)
+{
+	int err;
+	struct path h_path = {
+		.mnt = au_br_mnt(br)
+	};
+
+	err = 0;
+	h_path.dentry = vfsub_lkup_one(wh, h_parent);
+	if (IS_ERR(h_path.dentry))
+		err = PTR_ERR(h_path.dentry);
+	else {
+		if (d_is_reg(h_path.dentry))
+			err = do_unlink_wh(d_inode(h_parent), &h_path);
+		dput(h_path.dentry);
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+/*
+ * initialize/clean whiteout for a branch
+ */
+
+static void au_wh_clean(struct inode *h_dir, struct path *whpath,
+			const int isdir)
+{
+	int err;
+	struct inode *delegated;
+
+	if (d_is_negative(whpath->dentry))
+		return;
+
+	if (isdir)
+		err = vfsub_rmdir(h_dir, whpath);
+	else {
+		delegated = NULL;
+		err = vfsub_unlink(h_dir, whpath, &delegated, /*force*/0);
+		if (unlikely(err == -EWOULDBLOCK)) {
+			pr_warn("cannot retry for NFSv4 delegation"
+				" for an internal unlink\n");
+			iput(delegated);
+		}
+	}
+	if (unlikely(err))
+		pr_warn("failed removing %pd (%d), ignored.\n",
+			whpath->dentry, err);
+}
+
+static int test_linkable(struct dentry *h_root)
+{
+	struct inode *h_dir = d_inode(h_root);
+
+	if (h_dir->i_op->link)
+		return 0;
+
+	pr_err("%pd (%s) doesn't support link(2), use noplink and rw+nolwh\n",
+	       h_root, au_sbtype(h_root->d_sb));
+	return -ENOSYS;
+}
+
+/* todo: should this mkdir be done in /sbin/mount.aufs helper? */
+static int au_whdir(struct inode *h_dir, struct path *path)
+{
+	int err;
+
+	err = -EEXIST;
+	if (d_is_negative(path->dentry)) {
+		int mode = S_IRWXU;
+
+		if (au_test_nfs(path->dentry->d_sb))
+			mode |= S_IXUGO;
+		err = vfsub_mkdir(h_dir, path, mode);
+	} else if (d_is_dir(path->dentry))
+		err = 0;
+	else
+		pr_err("unknown %pd exists\n", path->dentry);
+
+	return err;
+}
+
+struct au_wh_base {
+	const struct qstr *name;
+	struct dentry *dentry;
+};
+
+static void au_wh_init_ro(struct inode *h_dir, struct au_wh_base base[],
+			  struct path *h_path)
+{
+	h_path->dentry = base[AuBrWh_BASE].dentry;
+	au_wh_clean(h_dir, h_path, /*isdir*/0);
+	h_path->dentry = base[AuBrWh_PLINK].dentry;
+	au_wh_clean(h_dir, h_path, /*isdir*/1);
+	h_path->dentry = base[AuBrWh_ORPH].dentry;
+	au_wh_clean(h_dir, h_path, /*isdir*/1);
+}
+
+/*
+ * returns tri-state,
+ * minus: error, caller should print the message
+ * zero: succuess
+ * plus: error, caller should NOT print the message
+ */
+static int au_wh_init_rw_nolink(struct dentry *h_root, struct au_wbr *wbr,
+				int do_plink, struct au_wh_base base[],
+				struct path *h_path)
+{
+	int err;
+	struct inode *h_dir;
+
+	h_dir = d_inode(h_root);
+	h_path->dentry = base[AuBrWh_BASE].dentry;
+	au_wh_clean(h_dir, h_path, /*isdir*/0);
+	h_path->dentry = base[AuBrWh_PLINK].dentry;
+	if (do_plink) {
+		err = test_linkable(h_root);
+		if (unlikely(err)) {
+			err = 1;
+			goto out;
+		}
+
+		err = au_whdir(h_dir, h_path);
+		if (unlikely(err))
+			goto out;
+		wbr->wbr_plink = dget(base[AuBrWh_PLINK].dentry);
+	} else
+		au_wh_clean(h_dir, h_path, /*isdir*/1);
+	h_path->dentry = base[AuBrWh_ORPH].dentry;
+	err = au_whdir(h_dir, h_path);
+	if (unlikely(err))
+		goto out;
+	wbr->wbr_orph = dget(base[AuBrWh_ORPH].dentry);
+
+out:
+	return err;
+}
+
+/*
+ * for the moment, aufs supports the branch filesystem which does not support
+ * link(2). testing on FAT which does not support i_op->setattr() fully either,
+ * copyup failed. finally, such filesystem will not be used as the writable
+ * branch.
+ *
+ * returns tri-state, see above.
+ */
+static int au_wh_init_rw(struct dentry *h_root, struct au_wbr *wbr,
+			 int do_plink, struct au_wh_base base[],
+			 struct path *h_path)
+{
+	int err;
+	struct inode *h_dir;
+
+	WbrWhMustWriteLock(wbr);
+
+	err = test_linkable(h_root);
+	if (unlikely(err)) {
+		err = 1;
+		goto out;
+	}
+
+	/*
+	 * todo: should this create be done in /sbin/mount.aufs helper?
+	 */
+	err = -EEXIST;
+	h_dir = d_inode(h_root);
+	if (d_is_negative(base[AuBrWh_BASE].dentry)) {
+		h_path->dentry = base[AuBrWh_BASE].dentry;
+		err = vfsub_create(h_dir, h_path, WH_MASK, /*want_excl*/true);
+	} else if (d_is_reg(base[AuBrWh_BASE].dentry))
+		err = 0;
+	else
+		pr_err("unknown %pd2 exists\n", base[AuBrWh_BASE].dentry);
+	if (unlikely(err))
+		goto out;
+
+	h_path->dentry = base[AuBrWh_PLINK].dentry;
+	if (do_plink) {
+		err = au_whdir(h_dir, h_path);
+		if (unlikely(err))
+			goto out;
+		wbr->wbr_plink = dget(base[AuBrWh_PLINK].dentry);
+	} else
+		au_wh_clean(h_dir, h_path, /*isdir*/1);
+	wbr->wbr_whbase = dget(base[AuBrWh_BASE].dentry);
+
+	h_path->dentry = base[AuBrWh_ORPH].dentry;
+	err = au_whdir(h_dir, h_path);
+	if (unlikely(err))
+		goto out;
+	wbr->wbr_orph = dget(base[AuBrWh_ORPH].dentry);
+
+out:
+	return err;
+}
+
+/*
+ * initialize the whiteout base file/dir for @br.
+ */
+int au_wh_init(struct au_branch *br, struct super_block *sb)
+{
+	int err, i;
+	const unsigned char do_plink
+		= !!au_opt_test(au_mntflags(sb), PLINK);
+	struct inode *h_dir;
+	struct path path = br->br_path;
+	struct dentry *h_root = path.dentry;
+	struct au_wbr *wbr = br->br_wbr;
+	static const struct qstr base_name[] = {
+		[AuBrWh_BASE] = QSTR_INIT(AUFS_BASE_NAME,
+					  sizeof(AUFS_BASE_NAME) - 1),
+		[AuBrWh_PLINK] = QSTR_INIT(AUFS_PLINKDIR_NAME,
+					   sizeof(AUFS_PLINKDIR_NAME) - 1),
+		[AuBrWh_ORPH] = QSTR_INIT(AUFS_ORPHDIR_NAME,
+					  sizeof(AUFS_ORPHDIR_NAME) - 1)
+	};
+	struct au_wh_base base[] = {
+		[AuBrWh_BASE] = {
+			.name	= base_name + AuBrWh_BASE,
+			.dentry	= NULL
+		},
+		[AuBrWh_PLINK] = {
+			.name	= base_name + AuBrWh_PLINK,
+			.dentry	= NULL
+		},
+		[AuBrWh_ORPH] = {
+			.name	= base_name + AuBrWh_ORPH,
+			.dentry	= NULL
+		}
+	};
+
+	if (wbr)
+		WbrWhMustWriteLock(wbr);
+
+	for (i = 0; i < AuBrWh_Last; i++) {
+		/* doubly whiteouted */
+		struct dentry *d;
+
+		d = au_wh_lkup(h_root, (void *)base[i].name, br);
+		err = PTR_ERR(d);
+		if (IS_ERR(d))
+			goto out;
+
+		base[i].dentry = d;
+		AuDebugOn(wbr
+			  && wbr->wbr_wh[i]
+			  && wbr->wbr_wh[i] != base[i].dentry);
+	}
+
+	if (wbr)
+		for (i = 0; i < AuBrWh_Last; i++) {
+			dput(wbr->wbr_wh[i]);
+			wbr->wbr_wh[i] = NULL;
+		}
+
+	err = 0;
+	if (!au_br_writable(br->br_perm)) {
+		h_dir = d_inode(h_root);
+		au_wh_init_ro(h_dir, base, &path);
+	} else if (!au_br_wh_linkable(br->br_perm)) {
+		err = au_wh_init_rw_nolink(h_root, wbr, do_plink, base, &path);
+		if (err > 0)
+			goto out;
+		else if (err)
+			goto out_err;
+	} else {
+		err = au_wh_init_rw(h_root, wbr, do_plink, base, &path);
+		if (err > 0)
+			goto out;
+		else if (err)
+			goto out_err;
+	}
+	goto out; /* success */
+
+out_err:
+	pr_err("an error(%d) on the writable branch %pd(%s)\n",
+	       err, h_root, au_sbtype(h_root->d_sb));
+out:
+	for (i = 0; i < AuBrWh_Last; i++)
+		dput(base[i].dentry);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+/*
+ * whiteouts are all hard-linked usually.
+ * when its link count reaches a ceiling, we create a new whiteout base
+ * asynchronously.
+ */
+
+struct reinit_br_wh {
+	struct super_block *sb;
+	struct au_branch *br;
+};
+
+static void reinit_br_wh(void *arg)
+{
+	int err;
+	aufs_bindex_t bindex;
+	struct path h_path;
+	struct reinit_br_wh *a = arg;
+	struct au_wbr *wbr;
+	struct inode *dir, *delegated;
+	struct dentry *h_root;
+	struct au_hinode *hdir;
+
+	err = 0;
+	wbr = a->br->br_wbr;
+	/* big aufs lock */
+	si_noflush_write_lock(a->sb);
+	if (!au_br_writable(a->br->br_perm))
+		goto out;
+	bindex = au_br_index(a->sb, a->br->br_id);
+	if (unlikely(bindex < 0))
+		goto out;
+
+	di_read_lock_parent(a->sb->s_root, AuLock_IR);
+	dir = d_inode(a->sb->s_root);
+	hdir = au_hi(dir, bindex);
+	h_root = au_h_dptr(a->sb->s_root, bindex);
+	AuDebugOn(h_root != au_br_dentry(a->br));
+
+	au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT);
+	wbr_wh_write_lock(wbr);
+	err = au_h_verify(wbr->wbr_whbase, au_opt_udba(a->sb), hdir->hi_inode,
+			  h_root, a->br);
+	if (!err) {
+		h_path.dentry = wbr->wbr_whbase;
+		h_path.mnt = au_br_mnt(a->br);
+		delegated = NULL;
+		err = vfsub_unlink(hdir->hi_inode, &h_path, &delegated,
+				   /*force*/0);
+		if (unlikely(err == -EWOULDBLOCK)) {
+			pr_warn("cannot retry for NFSv4 delegation"
+				" for an internal unlink\n");
+			iput(delegated);
+		}
+	} else {
+		pr_warn("%pd is moved, ignored\n", wbr->wbr_whbase);
+		err = 0;
+	}
+	dput(wbr->wbr_whbase);
+	wbr->wbr_whbase = NULL;
+	if (!err)
+		err = au_wh_init(a->br, a->sb);
+	wbr_wh_write_unlock(wbr);
+	au_hn_inode_unlock(hdir);
+	di_read_unlock(a->sb->s_root, AuLock_IR);
+	if (!err)
+		au_fhsm_wrote(a->sb, bindex, /*force*/0);
+
+out:
+	if (wbr)
+		atomic_dec(&wbr->wbr_wh_running);
+	au_br_put(a->br);
+	si_write_unlock(a->sb);
+	au_nwt_done(&au_sbi(a->sb)->si_nowait);
+	kfree(arg);
+	if (unlikely(err))
+		AuIOErr("err %d\n", err);
+}
+
+static void kick_reinit_br_wh(struct super_block *sb, struct au_branch *br)
+{
+	int do_dec, wkq_err;
+	struct reinit_br_wh *arg;
+
+	do_dec = 1;
+	if (atomic_inc_return(&br->br_wbr->wbr_wh_running) != 1)
+		goto out;
+
+	/* ignore ENOMEM */
+	arg = kmalloc(sizeof(*arg), GFP_NOFS);
+	if (arg) {
+		/*
+		 * dec(wh_running), kfree(arg) and dec(br_count)
+		 * in reinit function
+		 */
+		arg->sb = sb;
+		arg->br = br;
+		au_br_get(br);
+		wkq_err = au_wkq_nowait(reinit_br_wh, arg, sb, /*flags*/0);
+		if (unlikely(wkq_err)) {
+			atomic_dec(&br->br_wbr->wbr_wh_running);
+			au_br_put(br);
+			kfree(arg);
+		}
+		do_dec = 0;
+	}
+
+out:
+	if (do_dec)
+		atomic_dec(&br->br_wbr->wbr_wh_running);
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * create the whiteout @wh.
+ */
+static int link_or_create_wh(struct super_block *sb, aufs_bindex_t bindex,
+			     struct dentry *wh)
+{
+	int err;
+	struct path h_path = {
+		.dentry = wh
+	};
+	struct au_branch *br;
+	struct au_wbr *wbr;
+	struct dentry *h_parent;
+	struct inode *h_dir, *delegated;
+
+	h_parent = wh->d_parent; /* dir inode is locked */
+	h_dir = d_inode(h_parent);
+	IMustLock(h_dir);
+
+	br = au_sbr(sb, bindex);
+	h_path.mnt = au_br_mnt(br);
+	wbr = br->br_wbr;
+	wbr_wh_read_lock(wbr);
+	if (wbr->wbr_whbase) {
+		delegated = NULL;
+		err = vfsub_link(wbr->wbr_whbase, h_dir, &h_path, &delegated);
+		if (unlikely(err == -EWOULDBLOCK)) {
+			pr_warn("cannot retry for NFSv4 delegation"
+				" for an internal link\n");
+			iput(delegated);
+		}
+		if (!err || err != -EMLINK)
+			goto out;
+
+		/* link count full. re-initialize br_whbase. */
+		kick_reinit_br_wh(sb, br);
+	}
+
+	/* return this error in this context */
+	err = vfsub_create(h_dir, &h_path, WH_MASK, /*want_excl*/true);
+	if (!err)
+		au_fhsm_wrote(sb, bindex, /*force*/0);
+
+out:
+	wbr_wh_read_unlock(wbr);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * create or remove the diropq.
+ */
+static struct dentry *do_diropq(struct dentry *dentry, aufs_bindex_t bindex,
+				unsigned int flags)
+{
+	struct dentry *opq_dentry, *h_dentry;
+	struct super_block *sb;
+	struct au_branch *br;
+	int err;
+
+	sb = dentry->d_sb;
+	br = au_sbr(sb, bindex);
+	h_dentry = au_h_dptr(dentry, bindex);
+	opq_dentry = vfsub_lkup_one(&diropq_name, h_dentry);
+	if (IS_ERR(opq_dentry))
+		goto out;
+
+	if (au_ftest_diropq(flags, CREATE)) {
+		err = link_or_create_wh(sb, bindex, opq_dentry);
+		if (!err) {
+			au_set_dbdiropq(dentry, bindex);
+			goto out; /* success */
+		}
+	} else {
+		struct path tmp = {
+			.dentry = opq_dentry,
+			.mnt	= au_br_mnt(br)
+		};
+		err = do_unlink_wh(au_h_iptr(d_inode(dentry), bindex), &tmp);
+		if (!err)
+			au_set_dbdiropq(dentry, -1);
+	}
+	dput(opq_dentry);
+	opq_dentry = ERR_PTR(err);
+
+out:
+	return opq_dentry;
+}
+
+struct do_diropq_args {
+	struct dentry **errp;
+	struct dentry *dentry;
+	aufs_bindex_t bindex;
+	unsigned int flags;
+};
+
+static void call_do_diropq(void *args)
+{
+	struct do_diropq_args *a = args;
+	*a->errp = do_diropq(a->dentry, a->bindex, a->flags);
+}
+
+struct dentry *au_diropq_sio(struct dentry *dentry, aufs_bindex_t bindex,
+			     unsigned int flags)
+{
+	struct dentry *diropq, *h_dentry;
+
+	h_dentry = au_h_dptr(dentry, bindex);
+	if (!au_test_h_perm_sio(d_inode(h_dentry), MAY_EXEC | MAY_WRITE))
+		diropq = do_diropq(dentry, bindex, flags);
+	else {
+		int wkq_err;
+		struct do_diropq_args args = {
+			.errp		= &diropq,
+			.dentry		= dentry,
+			.bindex		= bindex,
+			.flags		= flags
+		};
+
+		wkq_err = au_wkq_wait(call_do_diropq, &args);
+		if (unlikely(wkq_err))
+			diropq = ERR_PTR(wkq_err);
+	}
+
+	return diropq;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * lookup whiteout dentry.
+ * @h_parent: lower parent dentry which must exist and be locked
+ * @base_name: name of dentry which will be whiteouted
+ * returns dentry for whiteout.
+ */
+struct dentry *au_wh_lkup(struct dentry *h_parent, struct qstr *base_name,
+			  struct au_branch *br)
+{
+	int err;
+	struct qstr wh_name;
+	struct dentry *wh_dentry;
+
+	err = au_wh_name_alloc(&wh_name, base_name);
+	wh_dentry = ERR_PTR(err);
+	if (!err) {
+		wh_dentry = vfsub_lkup_one(&wh_name, h_parent);
+		kfree(wh_name.name);
+	}
+	return wh_dentry;
+}
+
+/*
+ * link/create a whiteout for @dentry on @bindex.
+ */
+struct dentry *au_wh_create(struct dentry *dentry, aufs_bindex_t bindex,
+			    struct dentry *h_parent)
+{
+	struct dentry *wh_dentry;
+	struct super_block *sb;
+	int err;
+
+	sb = dentry->d_sb;
+	wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, au_sbr(sb, bindex));
+	if (!IS_ERR(wh_dentry) && d_is_negative(wh_dentry)) {
+		err = link_or_create_wh(sb, bindex, wh_dentry);
+		if (!err) {
+			au_set_dbwh(dentry, bindex);
+			au_fhsm_wrote(sb, bindex, /*force*/0);
+		} else {
+			dput(wh_dentry);
+			wh_dentry = ERR_PTR(err);
+		}
+	}
+
+	return wh_dentry;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* Delete all whiteouts in this directory on branch bindex. */
+static int del_wh_children(struct dentry *h_dentry, struct au_nhash *whlist,
+			   aufs_bindex_t bindex, struct au_branch *br)
+{
+	int err;
+	unsigned long ul, n;
+	struct qstr wh_name;
+	char *p;
+	struct hlist_head *head;
+	struct au_vdir_wh *pos;
+	struct au_vdir_destr *str;
+
+	err = -ENOMEM;
+	p = (void *)__get_free_page(GFP_NOFS);
+	wh_name.name = p;
+	if (unlikely(!wh_name.name))
+		goto out;
+
+	err = 0;
+	memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN);
+	p += AUFS_WH_PFX_LEN;
+	n = whlist->nh_num;
+	head = whlist->nh_head;
+	for (ul = 0; !err && ul < n; ul++, head++) {
+		hlist_for_each_entry(pos, head, wh_hash) {
+			if (pos->wh_bindex != bindex)
+				continue;
+
+			str = &pos->wh_str;
+			if (str->len + AUFS_WH_PFX_LEN <= PATH_MAX) {
+				memcpy(p, str->name, str->len);
+				wh_name.len = AUFS_WH_PFX_LEN + str->len;
+				err = unlink_wh_name(h_dentry, &wh_name, br);
+				if (!err)
+					continue;
+				break;
+			}
+			AuIOErr("whiteout name too long %.*s\n",
+				str->len, str->name);
+			err = -EIO;
+			break;
+		}
+	}
+	free_page((unsigned long)wh_name.name);
+
+out:
+	return err;
+}
+
+struct del_wh_children_args {
+	int *errp;
+	struct dentry *h_dentry;
+	struct au_nhash *whlist;
+	aufs_bindex_t bindex;
+	struct au_branch *br;
+};
+
+static void call_del_wh_children(void *args)
+{
+	struct del_wh_children_args *a = args;
+	*a->errp = del_wh_children(a->h_dentry, a->whlist, a->bindex, a->br);
+}
+
+/* ---------------------------------------------------------------------- */
+
+struct au_whtmp_rmdir *au_whtmp_rmdir_alloc(struct super_block *sb, gfp_t gfp)
+{
+	struct au_whtmp_rmdir *whtmp;
+	int err;
+	unsigned int rdhash;
+
+	SiMustAnyLock(sb);
+
+	whtmp = kzalloc(sizeof(*whtmp), gfp);
+	if (unlikely(!whtmp)) {
+		whtmp = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	/* no estimation for dir size */
+	rdhash = au_sbi(sb)->si_rdhash;
+	if (!rdhash)
+		rdhash = AUFS_RDHASH_DEF;
+	err = au_nhash_alloc(&whtmp->whlist, rdhash, gfp);
+	if (unlikely(err)) {
+		kfree(whtmp);
+		whtmp = ERR_PTR(err);
+	}
+
+out:
+	return whtmp;
+}
+
+void au_whtmp_rmdir_free(struct au_whtmp_rmdir *whtmp)
+{
+	if (whtmp->br)
+		au_br_put(whtmp->br);
+	dput(whtmp->wh_dentry);
+	iput(whtmp->dir);
+	au_nhash_wh_free(&whtmp->whlist);
+	kfree(whtmp);
+}
+
+/*
+ * rmdir the whiteouted temporary named dir @h_dentry.
+ * @whlist: whiteouted children.
+ */
+int au_whtmp_rmdir(struct inode *dir, aufs_bindex_t bindex,
+		   struct dentry *wh_dentry, struct au_nhash *whlist)
+{
+	int err;
+	unsigned int h_nlink;
+	struct path h_tmp;
+	struct inode *wh_inode, *h_dir;
+	struct au_branch *br;
+
+	h_dir = d_inode(wh_dentry->d_parent); /* dir inode is locked */
+	IMustLock(h_dir);
+
+	br = au_sbr(dir->i_sb, bindex);
+	wh_inode = d_inode(wh_dentry);
+	inode_lock_nested(wh_inode, AuLsc_I_CHILD);
+
+	/*
+	 * someone else might change some whiteouts while we were sleeping.
+	 * it means this whlist may have an obsoleted entry.
+	 */
+	if (!au_test_h_perm_sio(wh_inode, MAY_EXEC | MAY_WRITE))
+		err = del_wh_children(wh_dentry, whlist, bindex, br);
+	else {
+		int wkq_err;
+		struct del_wh_children_args args = {
+			.errp		= &err,
+			.h_dentry	= wh_dentry,
+			.whlist		= whlist,
+			.bindex		= bindex,
+			.br		= br
+		};
+
+		wkq_err = au_wkq_wait(call_del_wh_children, &args);
+		if (unlikely(wkq_err))
+			err = wkq_err;
+	}
+	inode_unlock(wh_inode);
+
+	if (!err) {
+		h_tmp.dentry = wh_dentry;
+		h_tmp.mnt = au_br_mnt(br);
+		h_nlink = h_dir->i_nlink;
+		err = vfsub_rmdir(h_dir, &h_tmp);
+		/* some fs doesn't change the parent nlink in some cases */
+		h_nlink -= h_dir->i_nlink;
+	}
+
+	if (!err) {
+		if (au_ibtop(dir) == bindex) {
+			/* todo: dir->i_mutex is necessary */
+			au_cpup_attr_timesizes(dir);
+			if (h_nlink)
+				vfsub_drop_nlink(dir);
+		}
+		return 0; /* success */
+	}
+
+	pr_warn("failed removing %pd(%d), ignored\n", wh_dentry, err);
+	return err;
+}
+
+static void call_rmdir_whtmp(void *args)
+{
+	int err;
+	aufs_bindex_t bindex;
+	struct au_whtmp_rmdir *a = args;
+	struct super_block *sb;
+	struct dentry *h_parent;
+	struct inode *h_dir;
+	struct au_hinode *hdir;
+
+	/* rmdir by nfsd may cause deadlock with this i_mutex */
+	/* inode_lock(a->dir); */
+	err = -EROFS;
+	sb = a->dir->i_sb;
+	si_read_lock(sb, !AuLock_FLUSH);
+	if (!au_br_writable(a->br->br_perm))
+		goto out;
+	bindex = au_br_index(sb, a->br->br_id);
+	if (unlikely(bindex < 0))
+		goto out;
+
+	err = -EIO;
+	ii_write_lock_parent(a->dir);
+	h_parent = dget_parent(a->wh_dentry);
+	h_dir = d_inode(h_parent);
+	hdir = au_hi(a->dir, bindex);
+	err = vfsub_mnt_want_write(au_br_mnt(a->br));
+	if (unlikely(err))
+		goto out_mnt;
+	au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT);
+	err = au_h_verify(a->wh_dentry, au_opt_udba(sb), h_dir, h_parent,
+			  a->br);
+	if (!err)
+		err = au_whtmp_rmdir(a->dir, bindex, a->wh_dentry, &a->whlist);
+	au_hn_inode_unlock(hdir);
+	vfsub_mnt_drop_write(au_br_mnt(a->br));
+
+out_mnt:
+	dput(h_parent);
+	ii_write_unlock(a->dir);
+out:
+	/* inode_unlock(a->dir); */
+	au_whtmp_rmdir_free(a);
+	si_read_unlock(sb);
+	au_nwt_done(&au_sbi(sb)->si_nowait);
+	if (unlikely(err))
+		AuIOErr("err %d\n", err);
+}
+
+void au_whtmp_kick_rmdir(struct inode *dir, aufs_bindex_t bindex,
+			 struct dentry *wh_dentry, struct au_whtmp_rmdir *args)
+{
+	int wkq_err;
+	struct super_block *sb;
+
+	IMustLock(dir);
+
+	/* all post-process will be done in do_rmdir_whtmp(). */
+	sb = dir->i_sb;
+	args->dir = au_igrab(dir);
+	args->br = au_sbr(sb, bindex);
+	au_br_get(args->br);
+	args->wh_dentry = dget(wh_dentry);
+	wkq_err = au_wkq_nowait(call_rmdir_whtmp, args, sb, /*flags*/0);
+	if (unlikely(wkq_err)) {
+		pr_warn("rmdir error %pd (%d), ignored\n", wh_dentry, wkq_err);
+		au_whtmp_rmdir_free(args);
+	}
+}
diff --git a/fs/aufs/whout.h b/fs/aufs/whout.h
new file mode 100644
index 000000000000..eb4b1823bd49
--- /dev/null
+++ b/fs/aufs/whout.h
@@ -0,0 +1,85 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * whiteout for logical deletion and opaque directory
+ */
+
+#ifndef __AUFS_WHOUT_H__
+#define __AUFS_WHOUT_H__
+
+#ifdef __KERNEL__
+
+#include "dir.h"
+
+/* whout.c */
+int au_wh_name_alloc(struct qstr *wh, const struct qstr *name);
+int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, int try_sio);
+int au_diropq_test(struct dentry *h_dentry);
+struct au_branch;
+struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br,
+			     struct qstr *prefix);
+int au_whtmp_ren(struct dentry *h_dentry, struct au_branch *br);
+int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path,
+			struct dentry *dentry);
+int au_wh_init(struct au_branch *br, struct super_block *sb);
+
+/* diropq flags */
+#define AuDiropq_CREATE	1
+#define au_ftest_diropq(flags, name)	((flags) & AuDiropq_##name)
+#define au_fset_diropq(flags, name) \
+	do { (flags) |= AuDiropq_##name; } while (0)
+#define au_fclr_diropq(flags, name) \
+	do { (flags) &= ~AuDiropq_##name; } while (0)
+
+struct dentry *au_diropq_sio(struct dentry *dentry, aufs_bindex_t bindex,
+			     unsigned int flags);
+struct dentry *au_wh_lkup(struct dentry *h_parent, struct qstr *base_name,
+			  struct au_branch *br);
+struct dentry *au_wh_create(struct dentry *dentry, aufs_bindex_t bindex,
+			    struct dentry *h_parent);
+
+/* real rmdir for the whiteout-ed dir */
+struct au_whtmp_rmdir {
+	struct inode *dir;
+	struct au_branch *br;
+	struct dentry *wh_dentry;
+	struct au_nhash whlist;
+};
+
+struct au_whtmp_rmdir *au_whtmp_rmdir_alloc(struct super_block *sb, gfp_t gfp);
+void au_whtmp_rmdir_free(struct au_whtmp_rmdir *whtmp);
+int au_whtmp_rmdir(struct inode *dir, aufs_bindex_t bindex,
+		   struct dentry *wh_dentry, struct au_nhash *whlist);
+void au_whtmp_kick_rmdir(struct inode *dir, aufs_bindex_t bindex,
+			 struct dentry *wh_dentry, struct au_whtmp_rmdir *args);
+
+/* ---------------------------------------------------------------------- */
+
+static inline struct dentry *au_diropq_create(struct dentry *dentry,
+					      aufs_bindex_t bindex)
+{
+	return au_diropq_sio(dentry, bindex, AuDiropq_CREATE);
+}
+
+static inline int au_diropq_remove(struct dentry *dentry, aufs_bindex_t bindex)
+{
+	return PTR_ERR(au_diropq_sio(dentry, bindex, !AuDiropq_CREATE));
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_WHOUT_H__ */
diff --git a/fs/aufs/wkq.c b/fs/aufs/wkq.c
new file mode 100644
index 000000000000..7371d91eb911
--- /dev/null
+++ b/fs/aufs/wkq.c
@@ -0,0 +1,213 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * workqueue for asynchronous/super-io operations
+ * todo: try new dredential scheme
+ */
+
+#include <linux/module.h>
+#include "aufs.h"
+
+/* internal workqueue named AUFS_WKQ_NAME */
+
+static struct workqueue_struct *au_wkq;
+
+struct au_wkinfo {
+	struct work_struct wk;
+	struct kobject *kobj;
+
+	unsigned int flags; /* see wkq.h */
+
+	au_wkq_func_t func;
+	void *args;
+
+	struct completion *comp;
+};
+
+/* ---------------------------------------------------------------------- */
+
+static void wkq_func(struct work_struct *wk)
+{
+	struct au_wkinfo *wkinfo = container_of(wk, struct au_wkinfo, wk);
+
+	AuDebugOn(!uid_eq(current_fsuid(), GLOBAL_ROOT_UID));
+	AuDebugOn(rlimit(RLIMIT_FSIZE) != RLIM_INFINITY);
+
+	wkinfo->func(wkinfo->args);
+	if (au_ftest_wkq(wkinfo->flags, WAIT))
+		complete(wkinfo->comp);
+	else {
+		kobject_put(wkinfo->kobj);
+		module_put(THIS_MODULE); /* todo: ?? */
+		kfree(wkinfo);
+	}
+}
+
+/*
+ * Since struct completion is large, try allocating it dynamically.
+ */
+#if 1 /* defined(CONFIG_4KSTACKS) || defined(AuTest4KSTACKS) */
+#define AuWkqCompDeclare(name)	struct completion *comp = NULL
+
+static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp)
+{
+	*comp = kmalloc(sizeof(**comp), GFP_NOFS);
+	if (*comp) {
+		init_completion(*comp);
+		wkinfo->comp = *comp;
+		return 0;
+	}
+	return -ENOMEM;
+}
+
+static void au_wkq_comp_free(struct completion *comp)
+{
+	kfree(comp);
+}
+
+#else
+
+/* no braces */
+#define AuWkqCompDeclare(name) \
+	DECLARE_COMPLETION_ONSTACK(_ ## name); \
+	struct completion *comp = &_ ## name
+
+static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp)
+{
+	wkinfo->comp = *comp;
+	return 0;
+}
+
+static void au_wkq_comp_free(struct completion *comp __maybe_unused)
+{
+	/* empty */
+}
+#endif /* 4KSTACKS */
+
+static void au_wkq_run(struct au_wkinfo *wkinfo)
+{
+	if (au_ftest_wkq(wkinfo->flags, NEST)) {
+		if (au_wkq_test()) {
+			AuWarn1("wkq from wkq, unless silly-rename on NFS,"
+				" due to a dead dir by UDBA?\n");
+			AuDebugOn(au_ftest_wkq(wkinfo->flags, WAIT));
+		}
+	} else
+		au_dbg_verify_kthread();
+
+	if (au_ftest_wkq(wkinfo->flags, WAIT)) {
+		INIT_WORK_ONSTACK(&wkinfo->wk, wkq_func);
+		queue_work(au_wkq, &wkinfo->wk);
+	} else {
+		INIT_WORK(&wkinfo->wk, wkq_func);
+		schedule_work(&wkinfo->wk);
+	}
+}
+
+/*
+ * Be careful. It is easy to make deadlock happen.
+ * processA: lock, wkq and wait
+ * processB: wkq and wait, lock in wkq
+ * --> deadlock
+ */
+int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args)
+{
+	int err;
+	AuWkqCompDeclare(comp);
+	struct au_wkinfo wkinfo = {
+		.flags	= flags,
+		.func	= func,
+		.args	= args
+	};
+
+	err = au_wkq_comp_alloc(&wkinfo, &comp);
+	if (!err) {
+		au_wkq_run(&wkinfo);
+		/* no timeout, no interrupt */
+		wait_for_completion(wkinfo.comp);
+		au_wkq_comp_free(comp);
+		destroy_work_on_stack(&wkinfo.wk);
+	}
+
+	return err;
+
+}
+
+/*
+ * Note: dget/dput() in func for aufs dentries are not supported. It will be a
+ * problem in a concurrent umounting.
+ */
+int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb,
+		  unsigned int flags)
+{
+	int err;
+	struct au_wkinfo *wkinfo;
+
+	atomic_inc(&au_sbi(sb)->si_nowait.nw_len);
+
+	/*
+	 * wkq_func() must free this wkinfo.
+	 * it highly depends upon the implementation of workqueue.
+	 */
+	err = 0;
+	wkinfo = kmalloc(sizeof(*wkinfo), GFP_NOFS);
+	if (wkinfo) {
+		wkinfo->kobj = &au_sbi(sb)->si_kobj;
+		wkinfo->flags = flags & ~AuWkq_WAIT;
+		wkinfo->func = func;
+		wkinfo->args = args;
+		wkinfo->comp = NULL;
+		kobject_get(wkinfo->kobj);
+		__module_get(THIS_MODULE); /* todo: ?? */
+
+		au_wkq_run(wkinfo);
+	} else {
+		err = -ENOMEM;
+		au_nwt_done(&au_sbi(sb)->si_nowait);
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_nwt_init(struct au_nowait_tasks *nwt)
+{
+	atomic_set(&nwt->nw_len, 0);
+	/* smp_mb(); */ /* atomic_set */
+	init_waitqueue_head(&nwt->nw_wq);
+}
+
+void au_wkq_fin(void)
+{
+	destroy_workqueue(au_wkq);
+}
+
+int __init au_wkq_init(void)
+{
+	int err;
+
+	err = 0;
+	au_wkq = alloc_workqueue(AUFS_WKQ_NAME, 0, WQ_DFL_ACTIVE);
+	if (IS_ERR(au_wkq))
+		err = PTR_ERR(au_wkq);
+	else if (!au_wkq)
+		err = -ENOMEM;
+
+	return err;
+}
diff --git a/fs/aufs/wkq.h b/fs/aufs/wkq.h
new file mode 100644
index 000000000000..0f1f42da519a
--- /dev/null
+++ b/fs/aufs/wkq.h
@@ -0,0 +1,93 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * workqueue for asynchronous/super-io operations
+ * todo: try new credentials management scheme
+ */
+
+#ifndef __AUFS_WKQ_H__
+#define __AUFS_WKQ_H__
+
+#ifdef __KERNEL__
+
+#include <linux/percpu_counter.h>
+
+struct super_block;
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * in the next operation, wait for the 'nowait' tasks in system-wide workqueue
+ */
+struct au_nowait_tasks {
+	atomic_t		nw_len;
+	wait_queue_head_t	nw_wq;
+};
+
+/* ---------------------------------------------------------------------- */
+
+typedef void (*au_wkq_func_t)(void *args);
+
+/* wkq flags */
+#define AuWkq_WAIT	1
+#define AuWkq_NEST	(1 << 1)
+#define au_ftest_wkq(flags, name)	((flags) & AuWkq_##name)
+#define au_fset_wkq(flags, name) \
+	do { (flags) |= AuWkq_##name; } while (0)
+#define au_fclr_wkq(flags, name) \
+	do { (flags) &= ~AuWkq_##name; } while (0)
+
+#ifndef CONFIG_AUFS_HNOTIFY
+#undef AuWkq_NEST
+#define AuWkq_NEST	0
+#endif
+
+/* wkq.c */
+int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args);
+int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb,
+		  unsigned int flags);
+void au_nwt_init(struct au_nowait_tasks *nwt);
+int __init au_wkq_init(void);
+void au_wkq_fin(void);
+
+/* ---------------------------------------------------------------------- */
+
+static inline int au_wkq_test(void)
+{
+	return current->flags & PF_WQ_WORKER;
+}
+
+static inline int au_wkq_wait(au_wkq_func_t func, void *args)
+{
+	return au_wkq_do_wait(AuWkq_WAIT, func, args);
+}
+
+static inline void au_nwt_done(struct au_nowait_tasks *nwt)
+{
+	if (atomic_dec_and_test(&nwt->nw_len))
+		wake_up_all(&nwt->nw_wq);
+}
+
+static inline int au_nwt_flush(struct au_nowait_tasks *nwt)
+{
+	wait_event(nwt->nw_wq, !atomic_read(&nwt->nw_len));
+	return 0;
+}
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_WKQ_H__ */
diff --git a/fs/aufs/xattr.c b/fs/aufs/xattr.c
new file mode 100644
index 000000000000..ffff4efbbc22
--- /dev/null
+++ b/fs/aufs/xattr.c
@@ -0,0 +1,355 @@
+/*
+ * Copyright (C) 2014-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * handling xattr functions
+ */
+
+#include <linux/fs.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/xattr.h>
+#include "aufs.h"
+
+static int au_xattr_ignore(int err, char *name, unsigned int ignore_flags)
+{
+	if (!ignore_flags)
+		goto out;
+	switch (err) {
+	case -ENOMEM:
+	case -EDQUOT:
+		goto out;
+	}
+
+	if ((ignore_flags & AuBrAttr_ICEX) == AuBrAttr_ICEX) {
+		err = 0;
+		goto out;
+	}
+
+#define cmp(brattr, prefix) do {					\
+		if (!strncmp(name, XATTR_##prefix##_PREFIX,		\
+			     XATTR_##prefix##_PREFIX_LEN)) {		\
+			if (ignore_flags & AuBrAttr_ICEX_##brattr)	\
+				err = 0;				\
+			goto out;					\
+		}							\
+	} while (0)
+
+	cmp(SEC, SECURITY);
+	cmp(SYS, SYSTEM);
+	cmp(TR, TRUSTED);
+	cmp(USR, USER);
+#undef cmp
+
+	if (ignore_flags & AuBrAttr_ICEX_OTH)
+		err = 0;
+
+out:
+	return err;
+}
+
+static const int au_xattr_out_of_list = AuBrAttr_ICEX_OTH << 1;
+
+static int au_do_cpup_xattr(struct dentry *h_dst, struct dentry *h_src,
+			    char *name, char **buf, unsigned int ignore_flags,
+			    unsigned int verbose)
+{
+	int err;
+	ssize_t ssz;
+	struct inode *h_idst;
+
+	ssz = vfs_getxattr_alloc(h_src, name, buf, 0, GFP_NOFS);
+	err = ssz;
+	if (unlikely(err <= 0)) {
+		if (err == -ENODATA
+		    || (err == -EOPNOTSUPP
+			&& ((ignore_flags & au_xattr_out_of_list)
+			    || (au_test_nfs_noacl(d_inode(h_src))
+				&& (!strcmp(name, XATTR_NAME_POSIX_ACL_ACCESS)
+				    || !strcmp(name,
+					       XATTR_NAME_POSIX_ACL_DEFAULT))))
+			    ))
+			err = 0;
+		if (err && (verbose || au_debug_test()))
+			pr_err("%s, err %d\n", name, err);
+		goto out;
+	}
+
+	/* unlock it temporary */
+	h_idst = d_inode(h_dst);
+	inode_unlock(h_idst);
+	err = vfsub_setxattr(h_dst, name, *buf, ssz, /*flags*/0);
+	inode_lock_nested(h_idst, AuLsc_I_CHILD2);
+	if (unlikely(err)) {
+		if (verbose || au_debug_test())
+			pr_err("%s, err %d\n", name, err);
+		err = au_xattr_ignore(err, name, ignore_flags);
+	}
+
+out:
+	return err;
+}
+
+int au_cpup_xattr(struct dentry *h_dst, struct dentry *h_src, int ignore_flags,
+		  unsigned int verbose)
+{
+	int err, unlocked, acl_access, acl_default;
+	ssize_t ssz;
+	struct inode *h_isrc, *h_idst;
+	char *value, *p, *o, *e;
+
+	/* try stopping to update the source inode while we are referencing */
+	/* there should not be the parent-child relationship between them */
+	h_isrc = d_inode(h_src);
+	h_idst = d_inode(h_dst);
+	inode_unlock(h_idst);
+	vfsub_inode_lock_shared_nested(h_isrc, AuLsc_I_CHILD);
+	inode_lock_nested(h_idst, AuLsc_I_CHILD2);
+	unlocked = 0;
+
+	/* some filesystems don't list POSIX ACL, for example tmpfs */
+	ssz = vfs_listxattr(h_src, NULL, 0);
+	err = ssz;
+	if (unlikely(err < 0)) {
+		AuTraceErr(err);
+		if (err == -ENODATA
+		    || err == -EOPNOTSUPP)
+			err = 0;	/* ignore */
+		goto out;
+	}
+
+	err = 0;
+	p = NULL;
+	o = NULL;
+	if (ssz) {
+		err = -ENOMEM;
+		p = kmalloc(ssz, GFP_NOFS);
+		o = p;
+		if (unlikely(!p))
+			goto out;
+		err = vfs_listxattr(h_src, p, ssz);
+	}
+	inode_unlock_shared(h_isrc);
+	unlocked = 1;
+	AuDbg("err %d, ssz %zd\n", err, ssz);
+	if (unlikely(err < 0))
+		goto out_free;
+
+	err = 0;
+	e = p + ssz;
+	value = NULL;
+	acl_access = 0;
+	acl_default = 0;
+	while (!err && p < e) {
+		acl_access |= !strncmp(p, XATTR_NAME_POSIX_ACL_ACCESS,
+				       sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1);
+		acl_default |= !strncmp(p, XATTR_NAME_POSIX_ACL_DEFAULT,
+					sizeof(XATTR_NAME_POSIX_ACL_DEFAULT)
+					- 1);
+		err = au_do_cpup_xattr(h_dst, h_src, p, &value, ignore_flags,
+				       verbose);
+		p += strlen(p) + 1;
+	}
+	AuTraceErr(err);
+	ignore_flags |= au_xattr_out_of_list;
+	if (!err && !acl_access) {
+		err = au_do_cpup_xattr(h_dst, h_src,
+				       XATTR_NAME_POSIX_ACL_ACCESS, &value,
+				       ignore_flags, verbose);
+		AuTraceErr(err);
+	}
+	if (!err && !acl_default) {
+		err = au_do_cpup_xattr(h_dst, h_src,
+				       XATTR_NAME_POSIX_ACL_DEFAULT, &value,
+				       ignore_flags, verbose);
+		AuTraceErr(err);
+	}
+
+	kfree(value);
+
+out_free:
+	kfree(o);
+out:
+	if (!unlocked)
+		inode_unlock_shared(h_isrc);
+	AuTraceErr(err);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_smack_reentering(struct super_block *sb)
+{
+#if IS_ENABLED(CONFIG_SECURITY_SMACK)
+	/*
+	 * as a part of lookup, smack_d_instantiate() is called, and it calls
+	 * i_op->getxattr(). ouch.
+	 */
+	return si_pid_test(sb);
+#else
+	return 0;
+#endif
+}
+
+enum {
+	AU_XATTR_LIST,
+	AU_XATTR_GET
+};
+
+struct au_lgxattr {
+	int type;
+	union {
+		struct {
+			char	*list;
+			size_t	size;
+		} list;
+		struct {
+			const char	*name;
+			void		*value;
+			size_t		size;
+		} get;
+	} u;
+};
+
+static ssize_t au_lgxattr(struct dentry *dentry, struct au_lgxattr *arg)
+{
+	ssize_t err;
+	int reenter;
+	struct path h_path;
+	struct super_block *sb;
+
+	sb = dentry->d_sb;
+	reenter = au_smack_reentering(sb);
+	if (!reenter) {
+		err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
+		if (unlikely(err))
+			goto out;
+	}
+	err = au_h_path_getattr(dentry, /*force*/1, &h_path, reenter);
+	if (unlikely(err))
+		goto out_si;
+	if (unlikely(!h_path.dentry))
+		/* illegally overlapped or something */
+		goto out_di; /* pretending success */
+
+	/* always topmost entry only */
+	switch (arg->type) {
+	case AU_XATTR_LIST:
+		err = vfs_listxattr(h_path.dentry,
+				    arg->u.list.list, arg->u.list.size);
+		break;
+	case AU_XATTR_GET:
+		AuDebugOn(d_is_negative(h_path.dentry));
+		err = vfs_getxattr(h_path.dentry,
+				   arg->u.get.name, arg->u.get.value,
+				   arg->u.get.size);
+		break;
+	}
+
+out_di:
+	if (!reenter)
+		di_read_unlock(dentry, AuLock_IR);
+out_si:
+	if (!reenter)
+		si_read_unlock(sb);
+out:
+	AuTraceErr(err);
+	return err;
+}
+
+ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size)
+{
+	struct au_lgxattr arg = {
+		.type = AU_XATTR_LIST,
+		.u.list = {
+			.list	= list,
+			.size	= size
+		},
+	};
+
+	return au_lgxattr(dentry, &arg);
+}
+
+static ssize_t au_getxattr(struct dentry *dentry,
+			   struct inode *inode __maybe_unused,
+			   const char *name, void *value, size_t size)
+{
+	struct au_lgxattr arg = {
+		.type = AU_XATTR_GET,
+		.u.get = {
+			.name	= name,
+			.value	= value,
+			.size	= size
+		},
+	};
+
+	return au_lgxattr(dentry, &arg);
+}
+
+static int au_setxattr(struct dentry *dentry, struct inode *inode,
+		       const char *name, const void *value, size_t size,
+		       int flags)
+{
+	struct au_sxattr arg = {
+		.type = AU_XATTR_SET,
+		.u.set = {
+			.name	= name,
+			.value	= value,
+			.size	= size,
+			.flags	= flags
+		},
+	};
+
+	return au_sxattr(dentry, inode, &arg);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_xattr_get(const struct xattr_handler *handler,
+			struct dentry *dentry, struct inode *inode,
+			const char *name, void *buffer, size_t size)
+{
+	return au_getxattr(dentry, inode, name, buffer, size);
+}
+
+static int au_xattr_set(const struct xattr_handler *handler,
+			struct dentry *dentry, struct inode *inode,
+			const char *name, const void *value, size_t size,
+			int flags)
+{
+	return au_setxattr(dentry, inode, name, value, size, flags);
+}
+
+static const struct xattr_handler au_xattr_handler = {
+	.name	= "",
+	.prefix	= "",
+	.get	= au_xattr_get,
+	.set	= au_xattr_set
+};
+
+static const struct xattr_handler *au_xattr_handlers[] = {
+#ifdef CONFIG_FS_POSIX_ACL
+	&posix_acl_access_xattr_handler,
+	&posix_acl_default_xattr_handler,
+#endif
+	&au_xattr_handler, /* must be last */
+	NULL
+};
+
+void au_xattr_init(struct super_block *sb)
+{
+	sb->s_xattr = au_xattr_handlers;
+}
diff --git a/fs/aufs/xino.c b/fs/aufs/xino.c
new file mode 100644
index 000000000000..1d41d5752048
--- /dev/null
+++ b/fs/aufs/xino.c
@@ -0,0 +1,1415 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * external inode number translation table and bitmap
+ */
+
+#include <linux/seq_file.h>
+#include <linux/statfs.h>
+#include "aufs.h"
+
+/* todo: unnecessary to support mmap_sem since kernel-space? */
+ssize_t xino_fread(vfs_readf_t func, struct file *file, void *kbuf, size_t size,
+		   loff_t *pos)
+{
+	ssize_t err;
+	mm_segment_t oldfs;
+	union {
+		void *k;
+		char __user *u;
+	} buf;
+
+	buf.k = kbuf;
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	do {
+		/* todo: signal_pending? */
+		err = func(file, buf.u, size, pos);
+	} while (err == -EAGAIN || err == -EINTR);
+	set_fs(oldfs);
+
+#if 0 /* reserved for future use */
+	if (err > 0)
+		fsnotify_access(file->f_path.dentry);
+#endif
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static ssize_t xino_fwrite_wkq(vfs_writef_t func, struct file *file, void *buf,
+			       size_t size, loff_t *pos);
+
+static ssize_t do_xino_fwrite(vfs_writef_t func, struct file *file, void *kbuf,
+			      size_t size, loff_t *pos)
+{
+	ssize_t err;
+	mm_segment_t oldfs;
+	union {
+		void *k;
+		const char __user *u;
+	} buf;
+	int i;
+	const int prevent_endless = 10;
+
+	i = 0;
+	buf.k = kbuf;
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	do {
+		err = func(file, buf.u, size, pos);
+		if (err == -EINTR
+		    && !au_wkq_test()
+		    && fatal_signal_pending(current)) {
+			set_fs(oldfs);
+			err = xino_fwrite_wkq(func, file, kbuf, size, pos);
+			BUG_ON(err == -EINTR);
+			oldfs = get_fs();
+			set_fs(KERNEL_DS);
+		}
+	} while (i++ < prevent_endless
+		 && (err == -EAGAIN || err == -EINTR));
+	set_fs(oldfs);
+
+#if 0 /* reserved for future use */
+	if (err > 0)
+		fsnotify_modify(file->f_path.dentry);
+#endif
+
+	return err;
+}
+
+struct do_xino_fwrite_args {
+	ssize_t *errp;
+	vfs_writef_t func;
+	struct file *file;
+	void *buf;
+	size_t size;
+	loff_t *pos;
+};
+
+static void call_do_xino_fwrite(void *args)
+{
+	struct do_xino_fwrite_args *a = args;
+	*a->errp = do_xino_fwrite(a->func, a->file, a->buf, a->size, a->pos);
+}
+
+static ssize_t xino_fwrite_wkq(vfs_writef_t func, struct file *file, void *buf,
+			       size_t size, loff_t *pos)
+{
+	ssize_t err;
+	int wkq_err;
+	struct do_xino_fwrite_args args = {
+		.errp	= &err,
+		.func	= func,
+		.file	= file,
+		.buf	= buf,
+		.size	= size,
+		.pos	= pos
+	};
+
+	/*
+	 * it breaks RLIMIT_FSIZE and normal user's limit,
+	 * users should care about quota and real 'filesystem full.'
+	 */
+	wkq_err = au_wkq_wait(call_do_xino_fwrite, &args);
+	if (unlikely(wkq_err))
+		err = wkq_err;
+
+	return err;
+}
+
+ssize_t xino_fwrite(vfs_writef_t func, struct file *file, void *buf,
+		    size_t size, loff_t *pos)
+{
+	ssize_t err;
+
+	if (rlimit(RLIMIT_FSIZE) == RLIM_INFINITY) {
+		lockdep_off();
+		err = do_xino_fwrite(func, file, buf, size, pos);
+		lockdep_on();
+	} else
+		err = xino_fwrite_wkq(func, file, buf, size, pos);
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * create a new xinofile at the same place/path as @base_file.
+ */
+struct file *au_xino_create2(struct file *base_file, struct file *copy_src)
+{
+	struct file *file;
+	struct dentry *base, *parent;
+	struct inode *dir, *delegated;
+	struct qstr *name;
+	struct path path;
+	int err;
+
+	base = base_file->f_path.dentry;
+	parent = base->d_parent; /* dir inode is locked */
+	dir = d_inode(parent);
+	IMustLock(dir);
+
+	file = ERR_PTR(-EINVAL);
+	name = &base->d_name;
+	path.dentry = vfsub_lookup_one_len(name->name, parent, name->len);
+	if (IS_ERR(path.dentry)) {
+		file = (void *)path.dentry;
+		pr_err("%pd lookup err %ld\n",
+		       base, PTR_ERR(path.dentry));
+		goto out;
+	}
+
+	/* no need to mnt_want_write() since we call dentry_open() later */
+	err = vfs_create(dir, path.dentry, S_IRUGO | S_IWUGO, NULL);
+	if (unlikely(err)) {
+		file = ERR_PTR(err);
+		pr_err("%pd create err %d\n", base, err);
+		goto out_dput;
+	}
+
+	path.mnt = base_file->f_path.mnt;
+	file = vfsub_dentry_open(&path,
+				 O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE
+				 /* | __FMODE_NONOTIFY */);
+	if (IS_ERR(file)) {
+		pr_err("%pd open err %ld\n", base, PTR_ERR(file));
+		goto out_dput;
+	}
+
+	delegated = NULL;
+	err = vfsub_unlink(dir, &file->f_path, &delegated, /*force*/0);
+	if (unlikely(err == -EWOULDBLOCK)) {
+		pr_warn("cannot retry for NFSv4 delegation"
+			" for an internal unlink\n");
+		iput(delegated);
+	}
+	if (unlikely(err)) {
+		pr_err("%pd unlink err %d\n", base, err);
+		goto out_fput;
+	}
+
+	if (copy_src) {
+		/* no one can touch copy_src xino */
+		err = au_copy_file(file, copy_src, vfsub_f_size_read(copy_src));
+		if (unlikely(err)) {
+			pr_err("%pd copy err %d\n", base, err);
+			goto out_fput;
+		}
+	}
+	goto out_dput; /* success */
+
+out_fput:
+	fput(file);
+	file = ERR_PTR(err);
+out_dput:
+	dput(path.dentry);
+out:
+	return file;
+}
+
+struct au_xino_lock_dir {
+	struct au_hinode *hdir;
+	struct dentry *parent;
+	struct inode *dir;
+};
+
+static void au_xino_lock_dir(struct super_block *sb, struct file *xino,
+			     struct au_xino_lock_dir *ldir)
+{
+	aufs_bindex_t brid, bindex;
+
+	ldir->hdir = NULL;
+	bindex = -1;
+	brid = au_xino_brid(sb);
+	if (brid >= 0)
+		bindex = au_br_index(sb, brid);
+	if (bindex >= 0) {
+		ldir->hdir = au_hi(d_inode(sb->s_root), bindex);
+		au_hn_inode_lock_nested(ldir->hdir, AuLsc_I_PARENT);
+	} else {
+		ldir->parent = dget_parent(xino->f_path.dentry);
+		ldir->dir = d_inode(ldir->parent);
+		inode_lock_nested(ldir->dir, AuLsc_I_PARENT);
+	}
+}
+
+static void au_xino_unlock_dir(struct au_xino_lock_dir *ldir)
+{
+	if (ldir->hdir)
+		au_hn_inode_unlock(ldir->hdir);
+	else {
+		inode_unlock(ldir->dir);
+		dput(ldir->parent);
+	}
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* trucate xino files asynchronously */
+
+int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex)
+{
+	int err;
+	unsigned long jiffy;
+	blkcnt_t blocks;
+	aufs_bindex_t bi, bbot;
+	struct kstatfs *st;
+	struct au_branch *br;
+	struct file *new_xino, *file;
+	struct super_block *h_sb;
+	struct au_xino_lock_dir ldir;
+
+	err = -ENOMEM;
+	st = kmalloc(sizeof(*st), GFP_NOFS);
+	if (unlikely(!st))
+		goto out;
+
+	err = -EINVAL;
+	bbot = au_sbbot(sb);
+	if (unlikely(bindex < 0 || bbot < bindex))
+		goto out_st;
+	br = au_sbr(sb, bindex);
+	file = br->br_xino.xi_file;
+	if (!file)
+		goto out_st;
+
+	err = vfs_statfs(&file->f_path, st);
+	if (unlikely(err))
+		AuErr1("statfs err %d, ignored\n", err);
+	jiffy = jiffies;
+	blocks = file_inode(file)->i_blocks;
+	pr_info("begin truncating xino(b%d), ib%llu, %llu/%llu free blks\n",
+		bindex, (u64)blocks, st->f_bfree, st->f_blocks);
+
+	au_xino_lock_dir(sb, file, &ldir);
+	/* mnt_want_write() is unnecessary here */
+	new_xino = au_xino_create2(file, file);
+	au_xino_unlock_dir(&ldir);
+	err = PTR_ERR(new_xino);
+	if (IS_ERR(new_xino)) {
+		pr_err("err %d, ignored\n", err);
+		goto out_st;
+	}
+	err = 0;
+	fput(file);
+	br->br_xino.xi_file = new_xino;
+
+	h_sb = au_br_sb(br);
+	for (bi = 0; bi <= bbot; bi++) {
+		if (unlikely(bi == bindex))
+			continue;
+		br = au_sbr(sb, bi);
+		if (au_br_sb(br) != h_sb)
+			continue;
+
+		fput(br->br_xino.xi_file);
+		br->br_xino.xi_file = new_xino;
+		get_file(new_xino);
+	}
+
+	err = vfs_statfs(&new_xino->f_path, st);
+	if (!err) {
+		pr_info("end truncating xino(b%d), ib%llu, %llu/%llu free blks\n",
+			bindex, (u64)file_inode(new_xino)->i_blocks,
+			st->f_bfree, st->f_blocks);
+		if (file_inode(new_xino)->i_blocks < blocks)
+			au_sbi(sb)->si_xino_jiffy = jiffy;
+	} else
+		AuErr1("statfs err %d, ignored\n", err);
+
+out_st:
+	kfree(st);
+out:
+	return err;
+}
+
+struct xino_do_trunc_args {
+	struct super_block *sb;
+	struct au_branch *br;
+};
+
+static void xino_do_trunc(void *_args)
+{
+	struct xino_do_trunc_args *args = _args;
+	struct super_block *sb;
+	struct au_branch *br;
+	struct inode *dir;
+	int err;
+	aufs_bindex_t bindex;
+
+	err = 0;
+	sb = args->sb;
+	dir = d_inode(sb->s_root);
+	br = args->br;
+
+	si_noflush_write_lock(sb);
+	ii_read_lock_parent(dir);
+	bindex = au_br_index(sb, br->br_id);
+	err = au_xino_trunc(sb, bindex);
+	ii_read_unlock(dir);
+	if (unlikely(err))
+		pr_warn("err b%d, (%d)\n", bindex, err);
+	atomic_dec(&br->br_xino_running);
+	au_br_put(br);
+	si_write_unlock(sb);
+	au_nwt_done(&au_sbi(sb)->si_nowait);
+	kfree(args);
+}
+
+static int xino_trunc_test(struct super_block *sb, struct au_branch *br)
+{
+	int err;
+	struct kstatfs st;
+	struct au_sbinfo *sbinfo;
+
+	/* todo: si_xino_expire and the ratio should be customizable */
+	sbinfo = au_sbi(sb);
+	if (time_before(jiffies,
+			sbinfo->si_xino_jiffy + sbinfo->si_xino_expire))
+		return 0;
+
+	/* truncation border */
+	err = vfs_statfs(&br->br_xino.xi_file->f_path, &st);
+	if (unlikely(err)) {
+		AuErr1("statfs err %d, ignored\n", err);
+		return 0;
+	}
+	if (div64_u64(st.f_bfree * 100, st.f_blocks) >= AUFS_XINO_DEF_TRUNC)
+		return 0;
+
+	return 1;
+}
+
+static void xino_try_trunc(struct super_block *sb, struct au_branch *br)
+{
+	struct xino_do_trunc_args *args;
+	int wkq_err;
+
+	if (!xino_trunc_test(sb, br))
+		return;
+
+	if (atomic_inc_return(&br->br_xino_running) > 1)
+		goto out;
+
+	/* lock and kfree() will be called in trunc_xino() */
+	args = kmalloc(sizeof(*args), GFP_NOFS);
+	if (unlikely(!args)) {
+		AuErr1("no memory\n");
+		goto out;
+	}
+
+	au_br_get(br);
+	args->sb = sb;
+	args->br = br;
+	wkq_err = au_wkq_nowait(xino_do_trunc, args, sb, /*flags*/0);
+	if (!wkq_err)
+		return; /* success */
+
+	pr_err("wkq %d\n", wkq_err);
+	au_br_put(br);
+	kfree(args);
+
+out:
+	atomic_dec(&br->br_xino_running);
+}
+
+/* ---------------------------------------------------------------------- */
+
+static int au_xino_do_write(vfs_writef_t write, struct file *file,
+			    ino_t h_ino, ino_t ino)
+{
+	loff_t pos;
+	ssize_t sz;
+
+	pos = h_ino;
+	if (unlikely(au_loff_max / sizeof(ino) - 1 < pos)) {
+		AuIOErr1("too large hi%lu\n", (unsigned long)h_ino);
+		return -EFBIG;
+	}
+	pos *= sizeof(ino);
+	sz = xino_fwrite(write, file, &ino, sizeof(ino), &pos);
+	if (sz == sizeof(ino))
+		return 0; /* success */
+
+	AuIOErr("write failed (%zd)\n", sz);
+	return -EIO;
+}
+
+/*
+ * write @ino to the xinofile for the specified branch{@sb, @bindex}
+ * at the position of @h_ino.
+ * even if @ino is zero, it is written to the xinofile and means no entry.
+ * if the size of the xino file on a specific filesystem exceeds the watermark,
+ * try truncating it.
+ */
+int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+		  ino_t ino)
+{
+	int err;
+	unsigned int mnt_flags;
+	struct au_branch *br;
+
+	BUILD_BUG_ON(sizeof(long long) != sizeof(au_loff_max)
+		     || ((loff_t)-1) > 0);
+	SiMustAnyLock(sb);
+
+	mnt_flags = au_mntflags(sb);
+	if (!au_opt_test(mnt_flags, XINO))
+		return 0;
+
+	br = au_sbr(sb, bindex);
+	err = au_xino_do_write(au_sbi(sb)->si_xwrite, br->br_xino.xi_file,
+			       h_ino, ino);
+	if (!err) {
+		if (au_opt_test(mnt_flags, TRUNC_XINO)
+		    && au_test_fs_trunc_xino(au_br_sb(br)))
+			xino_try_trunc(sb, br);
+		return 0; /* success */
+	}
+
+	AuIOErr("write failed (%d)\n", err);
+	return -EIO;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* aufs inode number bitmap */
+
+static const int page_bits = (int)PAGE_SIZE * BITS_PER_BYTE;
+static ino_t xib_calc_ino(unsigned long pindex, int bit)
+{
+	ino_t ino;
+
+	AuDebugOn(bit < 0 || page_bits <= bit);
+	ino = AUFS_FIRST_INO + pindex * page_bits + bit;
+	return ino;
+}
+
+static void xib_calc_bit(ino_t ino, unsigned long *pindex, int *bit)
+{
+	AuDebugOn(ino < AUFS_FIRST_INO);
+	ino -= AUFS_FIRST_INO;
+	*pindex = ino / page_bits;
+	*bit = ino % page_bits;
+}
+
+static int xib_pindex(struct super_block *sb, unsigned long pindex)
+{
+	int err;
+	loff_t pos;
+	ssize_t sz;
+	struct au_sbinfo *sbinfo;
+	struct file *xib;
+	unsigned long *p;
+
+	sbinfo = au_sbi(sb);
+	MtxMustLock(&sbinfo->si_xib_mtx);
+	AuDebugOn(pindex > ULONG_MAX / PAGE_SIZE
+		  || !au_opt_test(sbinfo->si_mntflags, XINO));
+
+	if (pindex == sbinfo->si_xib_last_pindex)
+		return 0;
+
+	xib = sbinfo->si_xib;
+	p = sbinfo->si_xib_buf;
+	pos = sbinfo->si_xib_last_pindex;
+	pos *= PAGE_SIZE;
+	sz = xino_fwrite(sbinfo->si_xwrite, xib, p, PAGE_SIZE, &pos);
+	if (unlikely(sz != PAGE_SIZE))
+		goto out;
+
+	pos = pindex;
+	pos *= PAGE_SIZE;
+	if (vfsub_f_size_read(xib) >= pos + PAGE_SIZE)
+		sz = xino_fread(sbinfo->si_xread, xib, p, PAGE_SIZE, &pos);
+	else {
+		memset(p, 0, PAGE_SIZE);
+		sz = xino_fwrite(sbinfo->si_xwrite, xib, p, PAGE_SIZE, &pos);
+	}
+	if (sz == PAGE_SIZE) {
+		sbinfo->si_xib_last_pindex = pindex;
+		return 0; /* success */
+	}
+
+out:
+	AuIOErr1("write failed (%zd)\n", sz);
+	err = sz;
+	if (sz >= 0)
+		err = -EIO;
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+static void au_xib_clear_bit(struct inode *inode)
+{
+	int err, bit;
+	unsigned long pindex;
+	struct super_block *sb;
+	struct au_sbinfo *sbinfo;
+
+	AuDebugOn(inode->i_nlink);
+
+	sb = inode->i_sb;
+	xib_calc_bit(inode->i_ino, &pindex, &bit);
+	AuDebugOn(page_bits <= bit);
+	sbinfo = au_sbi(sb);
+	mutex_lock(&sbinfo->si_xib_mtx);
+	err = xib_pindex(sb, pindex);
+	if (!err) {
+		clear_bit(bit, sbinfo->si_xib_buf);
+		sbinfo->si_xib_next_bit = bit;
+	}
+	mutex_unlock(&sbinfo->si_xib_mtx);
+}
+
+/* for s_op->delete_inode() */
+void au_xino_delete_inode(struct inode *inode, const int unlinked)
+{
+	int err;
+	unsigned int mnt_flags;
+	aufs_bindex_t bindex, bbot, bi;
+	unsigned char try_trunc;
+	struct au_iinfo *iinfo;
+	struct super_block *sb;
+	struct au_hinode *hi;
+	struct inode *h_inode;
+	struct au_branch *br;
+	vfs_writef_t xwrite;
+
+	AuDebugOn(au_is_bad_inode(inode));
+
+	sb = inode->i_sb;
+	mnt_flags = au_mntflags(sb);
+	if (!au_opt_test(mnt_flags, XINO)
+	    || inode->i_ino == AUFS_ROOT_INO)
+		return;
+
+	if (unlinked) {
+		au_xigen_inc(inode);
+		au_xib_clear_bit(inode);
+	}
+
+	iinfo = au_ii(inode);
+	bindex = iinfo->ii_btop;
+	if (bindex < 0)
+		return;
+
+	xwrite = au_sbi(sb)->si_xwrite;
+	try_trunc = !!au_opt_test(mnt_flags, TRUNC_XINO);
+	hi = au_hinode(iinfo, bindex);
+	bbot = iinfo->ii_bbot;
+	for (; bindex <= bbot; bindex++, hi++) {
+		h_inode = hi->hi_inode;
+		if (!h_inode
+		    || (!unlinked && h_inode->i_nlink))
+			continue;
+
+		/* inode may not be revalidated */
+		bi = au_br_index(sb, hi->hi_id);
+		if (bi < 0)
+			continue;
+
+		br = au_sbr(sb, bi);
+		err = au_xino_do_write(xwrite, br->br_xino.xi_file,
+				       h_inode->i_ino, /*ino*/0);
+		if (!err && try_trunc
+		    && au_test_fs_trunc_xino(au_br_sb(br)))
+			xino_try_trunc(sb, br);
+	}
+}
+
+/* get an unused inode number from bitmap */
+ino_t au_xino_new_ino(struct super_block *sb)
+{
+	ino_t ino;
+	unsigned long *p, pindex, ul, pend;
+	struct au_sbinfo *sbinfo;
+	struct file *file;
+	int free_bit, err;
+
+	if (!au_opt_test(au_mntflags(sb), XINO))
+		return iunique(sb, AUFS_FIRST_INO);
+
+	sbinfo = au_sbi(sb);
+	mutex_lock(&sbinfo->si_xib_mtx);
+	p = sbinfo->si_xib_buf;
+	free_bit = sbinfo->si_xib_next_bit;
+	if (free_bit < page_bits && !test_bit(free_bit, p))
+		goto out; /* success */
+	free_bit = find_first_zero_bit(p, page_bits);
+	if (free_bit < page_bits)
+		goto out; /* success */
+
+	pindex = sbinfo->si_xib_last_pindex;
+	for (ul = pindex - 1; ul < ULONG_MAX; ul--) {
+		err = xib_pindex(sb, ul);
+		if (unlikely(err))
+			goto out_err;
+		free_bit = find_first_zero_bit(p, page_bits);
+		if (free_bit < page_bits)
+			goto out; /* success */
+	}
+
+	file = sbinfo->si_xib;
+	pend = vfsub_f_size_read(file) / PAGE_SIZE;
+	for (ul = pindex + 1; ul <= pend; ul++) {
+		err = xib_pindex(sb, ul);
+		if (unlikely(err))
+			goto out_err;
+		free_bit = find_first_zero_bit(p, page_bits);
+		if (free_bit < page_bits)
+			goto out; /* success */
+	}
+	BUG();
+
+out:
+	set_bit(free_bit, p);
+	sbinfo->si_xib_next_bit = free_bit + 1;
+	pindex = sbinfo->si_xib_last_pindex;
+	mutex_unlock(&sbinfo->si_xib_mtx);
+	ino = xib_calc_ino(pindex, free_bit);
+	AuDbg("i%lu\n", (unsigned long)ino);
+	return ino;
+out_err:
+	mutex_unlock(&sbinfo->si_xib_mtx);
+	AuDbg("i0\n");
+	return 0;
+}
+
+/*
+ * read @ino from xinofile for the specified branch{@sb, @bindex}
+ * at the position of @h_ino.
+ * if @ino does not exist and @do_new is true, get new one.
+ */
+int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+		 ino_t *ino)
+{
+	int err;
+	ssize_t sz;
+	loff_t pos;
+	struct file *file;
+	struct au_sbinfo *sbinfo;
+
+	*ino = 0;
+	if (!au_opt_test(au_mntflags(sb), XINO))
+		return 0; /* no xino */
+
+	err = 0;
+	sbinfo = au_sbi(sb);
+	pos = h_ino;
+	if (unlikely(au_loff_max / sizeof(*ino) - 1 < pos)) {
+		AuIOErr1("too large hi%lu\n", (unsigned long)h_ino);
+		return -EFBIG;
+	}
+	pos *= sizeof(*ino);
+
+	file = au_sbr(sb, bindex)->br_xino.xi_file;
+	if (vfsub_f_size_read(file) < pos + sizeof(*ino))
+		return 0; /* no ino */
+
+	sz = xino_fread(sbinfo->si_xread, file, ino, sizeof(*ino), &pos);
+	if (sz == sizeof(*ino))
+		return 0; /* success */
+
+	err = sz;
+	if (unlikely(sz >= 0)) {
+		err = -EIO;
+		AuIOErr("xino read error (%zd)\n", sz);
+	}
+
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* create and set a new xino file */
+
+struct file *au_xino_create(struct super_block *sb, char *fname, int silent)
+{
+	struct file *file;
+	struct dentry *h_parent, *d;
+	struct inode *h_dir, *inode;
+	int err;
+
+	/*
+	 * at mount-time, and the xino file is the default path,
+	 * hnotify is disabled so we have no notify events to ignore.
+	 * when a user specified the xino, we cannot get au_hdir to be ignored.
+	 */
+	file = vfsub_filp_open(fname, O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE
+			       /* | __FMODE_NONOTIFY */,
+			       S_IRUGO | S_IWUGO);
+	if (IS_ERR(file)) {
+		if (!silent)
+			pr_err("open %s(%ld)\n", fname, PTR_ERR(file));
+		return file;
+	}
+
+	/* keep file count */
+	err = 0;
+	inode = file_inode(file);
+	h_parent = dget_parent(file->f_path.dentry);
+	h_dir = d_inode(h_parent);
+	inode_lock_nested(h_dir, AuLsc_I_PARENT);
+	/* mnt_want_write() is unnecessary here */
+	/* no delegation since it is just created */
+	if (inode->i_nlink)
+		err = vfsub_unlink(h_dir, &file->f_path, /*delegated*/NULL,
+				   /*force*/0);
+	inode_unlock(h_dir);
+	dput(h_parent);
+	if (unlikely(err)) {
+		if (!silent)
+			pr_err("unlink %s(%d)\n", fname, err);
+		goto out;
+	}
+
+	err = -EINVAL;
+	d = file->f_path.dentry;
+	if (unlikely(sb == d->d_sb)) {
+		if (!silent)
+			pr_err("%s must be outside\n", fname);
+		goto out;
+	}
+	if (unlikely(au_test_fs_bad_xino(d->d_sb))) {
+		if (!silent)
+			pr_err("xino doesn't support %s(%s)\n",
+			       fname, au_sbtype(d->d_sb));
+		goto out;
+	}
+	return file; /* success */
+
+out:
+	fput(file);
+	file = ERR_PTR(err);
+	return file;
+}
+
+/*
+ * find another branch who is on the same filesystem of the specified
+ * branch{@btgt}. search until @bbot.
+ */
+static int is_sb_shared(struct super_block *sb, aufs_bindex_t btgt,
+			aufs_bindex_t bbot)
+{
+	aufs_bindex_t bindex;
+	struct super_block *tgt_sb = au_sbr_sb(sb, btgt);
+
+	for (bindex = 0; bindex < btgt; bindex++)
+		if (unlikely(tgt_sb == au_sbr_sb(sb, bindex)))
+			return bindex;
+	for (bindex++; bindex <= bbot; bindex++)
+		if (unlikely(tgt_sb == au_sbr_sb(sb, bindex)))
+			return bindex;
+	return -1;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * initialize the xinofile for the specified branch @br
+ * at the place/path where @base_file indicates.
+ * test whether another branch is on the same filesystem or not,
+ * if @do_test is true.
+ */
+int au_xino_br(struct super_block *sb, struct au_branch *br, ino_t h_ino,
+	       struct file *base_file, int do_test)
+{
+	int err;
+	ino_t ino;
+	aufs_bindex_t bbot, bindex;
+	struct au_branch *shared_br, *b;
+	struct file *file;
+	struct super_block *tgt_sb;
+
+	shared_br = NULL;
+	bbot = au_sbbot(sb);
+	if (do_test) {
+		tgt_sb = au_br_sb(br);
+		for (bindex = 0; bindex <= bbot; bindex++) {
+			b = au_sbr(sb, bindex);
+			if (tgt_sb == au_br_sb(b)) {
+				shared_br = b;
+				break;
+			}
+		}
+	}
+
+	if (!shared_br || !shared_br->br_xino.xi_file) {
+		struct au_xino_lock_dir ldir;
+
+		au_xino_lock_dir(sb, base_file, &ldir);
+		/* mnt_want_write() is unnecessary here */
+		file = au_xino_create2(base_file, NULL);
+		au_xino_unlock_dir(&ldir);
+		err = PTR_ERR(file);
+		if (IS_ERR(file))
+			goto out;
+		br->br_xino.xi_file = file;
+	} else {
+		br->br_xino.xi_file = shared_br->br_xino.xi_file;
+		get_file(br->br_xino.xi_file);
+	}
+
+	ino = AUFS_ROOT_INO;
+	err = au_xino_do_write(au_sbi(sb)->si_xwrite, br->br_xino.xi_file,
+			       h_ino, ino);
+	if (unlikely(err)) {
+		fput(br->br_xino.xi_file);
+		br->br_xino.xi_file = NULL;
+	}
+
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* trucate a xino bitmap file */
+
+/* todo: slow */
+static int do_xib_restore(struct super_block *sb, struct file *file, void *page)
+{
+	int err, bit;
+	ssize_t sz;
+	unsigned long pindex;
+	loff_t pos, pend;
+	struct au_sbinfo *sbinfo;
+	vfs_readf_t func;
+	ino_t *ino;
+	unsigned long *p;
+
+	err = 0;
+	sbinfo = au_sbi(sb);
+	MtxMustLock(&sbinfo->si_xib_mtx);
+	p = sbinfo->si_xib_buf;
+	func = sbinfo->si_xread;
+	pend = vfsub_f_size_read(file);
+	pos = 0;
+	while (pos < pend) {
+		sz = xino_fread(func, file, page, PAGE_SIZE, &pos);
+		err = sz;
+		if (unlikely(sz <= 0))
+			goto out;
+
+		err = 0;
+		for (ino = page; sz > 0; ino++, sz -= sizeof(ino)) {
+			if (unlikely(*ino < AUFS_FIRST_INO))
+				continue;
+
+			xib_calc_bit(*ino, &pindex, &bit);
+			AuDebugOn(page_bits <= bit);
+			err = xib_pindex(sb, pindex);
+			if (!err)
+				set_bit(bit, p);
+			else
+				goto out;
+		}
+	}
+
+out:
+	return err;
+}
+
+static int xib_restore(struct super_block *sb)
+{
+	int err;
+	aufs_bindex_t bindex, bbot;
+	void *page;
+
+	err = -ENOMEM;
+	page = (void *)__get_free_page(GFP_NOFS);
+	if (unlikely(!page))
+		goto out;
+
+	err = 0;
+	bbot = au_sbbot(sb);
+	for (bindex = 0; !err && bindex <= bbot; bindex++)
+		if (!bindex || is_sb_shared(sb, bindex, bindex - 1) < 0)
+			err = do_xib_restore
+				(sb, au_sbr(sb, bindex)->br_xino.xi_file, page);
+		else
+			AuDbg("b%d\n", bindex);
+	free_page((unsigned long)page);
+
+out:
+	return err;
+}
+
+int au_xib_trunc(struct super_block *sb)
+{
+	int err;
+	ssize_t sz;
+	loff_t pos;
+	struct au_xino_lock_dir ldir;
+	struct au_sbinfo *sbinfo;
+	unsigned long *p;
+	struct file *file;
+
+	SiMustWriteLock(sb);
+
+	err = 0;
+	sbinfo = au_sbi(sb);
+	if (!au_opt_test(sbinfo->si_mntflags, XINO))
+		goto out;
+
+	file = sbinfo->si_xib;
+	if (vfsub_f_size_read(file) <= PAGE_SIZE)
+		goto out;
+
+	au_xino_lock_dir(sb, file, &ldir);
+	/* mnt_want_write() is unnecessary here */
+	file = au_xino_create2(sbinfo->si_xib, NULL);
+	au_xino_unlock_dir(&ldir);
+	err = PTR_ERR(file);
+	if (IS_ERR(file))
+		goto out;
+	fput(sbinfo->si_xib);
+	sbinfo->si_xib = file;
+
+	p = sbinfo->si_xib_buf;
+	memset(p, 0, PAGE_SIZE);
+	pos = 0;
+	sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xib, p, PAGE_SIZE, &pos);
+	if (unlikely(sz != PAGE_SIZE)) {
+		err = sz;
+		AuIOErr("err %d\n", err);
+		if (sz >= 0)
+			err = -EIO;
+		goto out;
+	}
+
+	mutex_lock(&sbinfo->si_xib_mtx);
+	/* mnt_want_write() is unnecessary here */
+	err = xib_restore(sb);
+	mutex_unlock(&sbinfo->si_xib_mtx);
+
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * xino mount option handlers
+ */
+
+/* xino bitmap */
+static void xino_clear_xib(struct super_block *sb)
+{
+	struct au_sbinfo *sbinfo;
+
+	SiMustWriteLock(sb);
+
+	sbinfo = au_sbi(sb);
+	sbinfo->si_xread = NULL;
+	sbinfo->si_xwrite = NULL;
+	if (sbinfo->si_xib)
+		fput(sbinfo->si_xib);
+	sbinfo->si_xib = NULL;
+	if (sbinfo->si_xib_buf)
+		free_page((unsigned long)sbinfo->si_xib_buf);
+	sbinfo->si_xib_buf = NULL;
+}
+
+static int au_xino_set_xib(struct super_block *sb, struct file *base)
+{
+	int err;
+	loff_t pos;
+	struct au_sbinfo *sbinfo;
+	struct file *file;
+
+	SiMustWriteLock(sb);
+
+	sbinfo = au_sbi(sb);
+	file = au_xino_create2(base, sbinfo->si_xib);
+	err = PTR_ERR(file);
+	if (IS_ERR(file))
+		goto out;
+	if (sbinfo->si_xib)
+		fput(sbinfo->si_xib);
+	sbinfo->si_xib = file;
+	sbinfo->si_xread = vfs_readf(file);
+	sbinfo->si_xwrite = vfs_writef(file);
+
+	err = -ENOMEM;
+	if (!sbinfo->si_xib_buf)
+		sbinfo->si_xib_buf = (void *)get_zeroed_page(GFP_NOFS);
+	if (unlikely(!sbinfo->si_xib_buf))
+		goto out_unset;
+
+	sbinfo->si_xib_last_pindex = 0;
+	sbinfo->si_xib_next_bit = 0;
+	if (vfsub_f_size_read(file) < PAGE_SIZE) {
+		pos = 0;
+		err = xino_fwrite(sbinfo->si_xwrite, file, sbinfo->si_xib_buf,
+				  PAGE_SIZE, &pos);
+		if (unlikely(err != PAGE_SIZE))
+			goto out_free;
+	}
+	err = 0;
+	goto out; /* success */
+
+out_free:
+	if (sbinfo->si_xib_buf)
+		free_page((unsigned long)sbinfo->si_xib_buf);
+	sbinfo->si_xib_buf = NULL;
+	if (err >= 0)
+		err = -EIO;
+out_unset:
+	fput(sbinfo->si_xib);
+	sbinfo->si_xib = NULL;
+	sbinfo->si_xread = NULL;
+	sbinfo->si_xwrite = NULL;
+out:
+	return err;
+}
+
+/* xino for each branch */
+static void xino_clear_br(struct super_block *sb)
+{
+	aufs_bindex_t bindex, bbot;
+	struct au_branch *br;
+
+	bbot = au_sbbot(sb);
+	for (bindex = 0; bindex <= bbot; bindex++) {
+		br = au_sbr(sb, bindex);
+		if (!br || !br->br_xino.xi_file)
+			continue;
+
+		fput(br->br_xino.xi_file);
+		br->br_xino.xi_file = NULL;
+	}
+}
+
+static int au_xino_set_br(struct super_block *sb, struct file *base)
+{
+	int err;
+	ino_t ino;
+	aufs_bindex_t bindex, bbot, bshared;
+	struct {
+		struct file *old, *new;
+	} *fpair, *p;
+	struct au_branch *br;
+	struct inode *inode;
+	vfs_writef_t writef;
+
+	SiMustWriteLock(sb);
+
+	err = -ENOMEM;
+	bbot = au_sbbot(sb);
+	fpair = kcalloc(bbot + 1, sizeof(*fpair), GFP_NOFS);
+	if (unlikely(!fpair))
+		goto out;
+
+	inode = d_inode(sb->s_root);
+	ino = AUFS_ROOT_INO;
+	writef = au_sbi(sb)->si_xwrite;
+	for (bindex = 0, p = fpair; bindex <= bbot; bindex++, p++) {
+		bshared = is_sb_shared(sb, bindex, bindex - 1);
+		if (bshared >= 0) {
+			/* shared xino */
+			*p = fpair[bshared];
+			get_file(p->new);
+		}
+
+		if (!p->new) {
+			/* new xino */
+			br = au_sbr(sb, bindex);
+			p->old = br->br_xino.xi_file;
+			p->new = au_xino_create2(base, br->br_xino.xi_file);
+			err = PTR_ERR(p->new);
+			if (IS_ERR(p->new)) {
+				p->new = NULL;
+				goto out_pair;
+			}
+		}
+
+		err = au_xino_do_write(writef, p->new,
+				       au_h_iptr(inode, bindex)->i_ino, ino);
+		if (unlikely(err))
+			goto out_pair;
+	}
+
+	for (bindex = 0, p = fpair; bindex <= bbot; bindex++, p++) {
+		br = au_sbr(sb, bindex);
+		if (br->br_xino.xi_file)
+			fput(br->br_xino.xi_file);
+		get_file(p->new);
+		br->br_xino.xi_file = p->new;
+	}
+
+out_pair:
+	for (bindex = 0, p = fpair; bindex <= bbot; bindex++, p++)
+		if (p->new)
+			fput(p->new);
+		else
+			break;
+	kfree(fpair);
+out:
+	return err;
+}
+
+void au_xino_clr(struct super_block *sb)
+{
+	struct au_sbinfo *sbinfo;
+
+	au_xigen_clr(sb);
+	xino_clear_xib(sb);
+	xino_clear_br(sb);
+	sbinfo = au_sbi(sb);
+	/* lvalue, do not call au_mntflags() */
+	au_opt_clr(sbinfo->si_mntflags, XINO);
+}
+
+int au_xino_set(struct super_block *sb, struct au_opt_xino *xino, int remount)
+{
+	int err, skip;
+	struct dentry *parent, *cur_parent;
+	struct qstr *dname, *cur_name;
+	struct file *cur_xino;
+	struct inode *dir;
+	struct au_sbinfo *sbinfo;
+
+	SiMustWriteLock(sb);
+
+	err = 0;
+	sbinfo = au_sbi(sb);
+	parent = dget_parent(xino->file->f_path.dentry);
+	if (remount) {
+		skip = 0;
+		dname = &xino->file->f_path.dentry->d_name;
+		cur_xino = sbinfo->si_xib;
+		if (cur_xino) {
+			cur_parent = dget_parent(cur_xino->f_path.dentry);
+			cur_name = &cur_xino->f_path.dentry->d_name;
+			skip = (cur_parent == parent
+				&& au_qstreq(dname, cur_name));
+			dput(cur_parent);
+		}
+		if (skip)
+			goto out;
+	}
+
+	au_opt_set(sbinfo->si_mntflags, XINO);
+	dir = d_inode(parent);
+	inode_lock_nested(dir, AuLsc_I_PARENT);
+	/* mnt_want_write() is unnecessary here */
+	err = au_xino_set_xib(sb, xino->file);
+	if (!err)
+		err = au_xigen_set(sb, xino->file);
+	if (!err)
+		err = au_xino_set_br(sb, xino->file);
+	inode_unlock(dir);
+	if (!err)
+		goto out; /* success */
+
+	/* reset all */
+	AuIOErr("failed creating xino(%d).\n", err);
+	au_xigen_clr(sb);
+	xino_clear_xib(sb);
+
+out:
+	dput(parent);
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/*
+ * create a xinofile at the default place/path.
+ */
+struct file *au_xino_def(struct super_block *sb)
+{
+	struct file *file;
+	char *page, *p;
+	struct au_branch *br;
+	struct super_block *h_sb;
+	struct path path;
+	aufs_bindex_t bbot, bindex, bwr;
+
+	br = NULL;
+	bbot = au_sbbot(sb);
+	bwr = -1;
+	for (bindex = 0; bindex <= bbot; bindex++) {
+		br = au_sbr(sb, bindex);
+		if (au_br_writable(br->br_perm)
+		    && !au_test_fs_bad_xino(au_br_sb(br))) {
+			bwr = bindex;
+			break;
+		}
+	}
+
+	if (bwr >= 0) {
+		file = ERR_PTR(-ENOMEM);
+		page = (void *)__get_free_page(GFP_NOFS);
+		if (unlikely(!page))
+			goto out;
+		path.mnt = au_br_mnt(br);
+		path.dentry = au_h_dptr(sb->s_root, bwr);
+		p = d_path(&path, page, PATH_MAX - sizeof(AUFS_XINO_FNAME));
+		file = (void *)p;
+		if (!IS_ERR(p)) {
+			strcat(p, "/" AUFS_XINO_FNAME);
+			AuDbg("%s\n", p);
+			file = au_xino_create(sb, p, /*silent*/0);
+			if (!IS_ERR(file))
+				au_xino_brid_set(sb, br->br_id);
+		}
+		free_page((unsigned long)page);
+	} else {
+		file = au_xino_create(sb, AUFS_XINO_DEFPATH, /*silent*/0);
+		if (IS_ERR(file))
+			goto out;
+		h_sb = file->f_path.dentry->d_sb;
+		if (unlikely(au_test_fs_bad_xino(h_sb))) {
+			pr_err("xino doesn't support %s(%s)\n",
+			       AUFS_XINO_DEFPATH, au_sbtype(h_sb));
+			fput(file);
+			file = ERR_PTR(-EINVAL);
+		}
+		if (!IS_ERR(file))
+			au_xino_brid_set(sb, -1);
+	}
+
+out:
+	return file;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int au_xino_path(struct seq_file *seq, struct file *file)
+{
+	int err;
+
+	err = au_seq_path(seq, &file->f_path);
+	if (unlikely(err))
+		goto out;
+
+#define Deleted "\\040(deleted)"
+	seq->count -= sizeof(Deleted) - 1;
+	AuDebugOn(memcmp(seq->buf + seq->count, Deleted,
+			 sizeof(Deleted) - 1));
+#undef Deleted
+
+out:
+	return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void au_xinondir_leave(struct super_block *sb, aufs_bindex_t bindex,
+		       ino_t h_ino, int idx)
+{
+	struct au_xino_file *xino;
+
+	AuDebugOn(!au_opt_test(au_mntflags(sb), XINO));
+	xino = &au_sbr(sb, bindex)->br_xino;
+	AuDebugOn(idx < 0 || xino->xi_nondir.total <= idx);
+
+	spin_lock(&xino->xi_nondir.spin);
+	AuDebugOn(xino->xi_nondir.array[idx] != h_ino);
+	xino->xi_nondir.array[idx] = 0;
+	spin_unlock(&xino->xi_nondir.spin);
+	wake_up_all(&xino->xi_nondir.wqh);
+}
+
+static int au_xinondir_find(struct au_xino_file *xino, ino_t h_ino)
+{
+	int found, total, i;
+
+	found = -1;
+	total = xino->xi_nondir.total;
+	for (i = 0; i < total; i++) {
+		if (xino->xi_nondir.array[i] != h_ino)
+			continue;
+		found = i;
+		break;
+	}
+
+	return found;
+}
+
+static int au_xinondir_expand(struct au_xino_file *xino)
+{
+	int err, sz;
+	ino_t *p;
+
+	BUILD_BUG_ON(KMALLOC_MAX_SIZE > INT_MAX);
+
+	err = -ENOMEM;
+	sz = xino->xi_nondir.total * sizeof(ino_t);
+	if (unlikely(sz > KMALLOC_MAX_SIZE / 2))
+		goto out;
+	p = au_kzrealloc(xino->xi_nondir.array, sz, sz << 1, GFP_ATOMIC,
+			 /*may_shrink*/0);
+	if (p) {
+		xino->xi_nondir.array = p;
+		xino->xi_nondir.total <<= 1;
+		AuDbg("xi_nondir.total %d\n", xino->xi_nondir.total);
+		err = 0;
+	}
+
+out:
+	return err;
+}
+
+int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
+		      int *idx)
+{
+	int err, found, empty;
+	struct au_xino_file *xino;
+
+	err = 0;
+	*idx = -1;
+	if (!au_opt_test(au_mntflags(sb), XINO))
+		goto out; /* no xino */
+
+	xino = &au_sbr(sb, bindex)->br_xino;
+
+again:
+	spin_lock(&xino->xi_nondir.spin);
+	found = au_xinondir_find(xino, h_ino);
+	if (found == -1) {
+		empty = au_xinondir_find(xino, /*h_ino*/0);
+		if (empty == -1) {
+			empty = xino->xi_nondir.total;
+			err = au_xinondir_expand(xino);
+			if (unlikely(err))
+				goto out_unlock;
+		}
+		xino->xi_nondir.array[empty] = h_ino;
+		*idx = empty;
+	} else {
+		spin_unlock(&xino->xi_nondir.spin);
+		wait_event(xino->xi_nondir.wqh,
+			   xino->xi_nondir.array[found] != h_ino);
+		goto again;
+	}
+
+out_unlock:
+	spin_unlock(&xino->xi_nondir.spin);
+out:
+	return err;
+}
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 166846a40078..2c433c95adb5 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1740,7 +1740,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 		    (!regset->active || regset->active(t->task, regset) > 0)) {
 			int ret;
 			size_t size = regset->n * regset->size;
-			void *data = kmalloc(size, GFP_KERNEL);
+			void *data = kzalloc(size, GFP_KERNEL);
 			if (unlikely(!data))
 				return 0;
 			ret = regset->get(t->task, regset,
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 61949e3446e5..23fb999b49e1 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1439,10 +1439,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	 */
 	if (!for_part) {
 		ret = devcgroup_inode_permission(bdev->bd_inode, perm);
-		if (ret != 0) {
-			bdput(bdev);
+		if (ret != 0)
 			return ret;
-		}
 	}
 
  restart:
@@ -1515,8 +1513,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				goto out_clear;
 			BUG_ON(for_part);
 			ret = __blkdev_get(whole, mode, 1);
-			if (ret)
+			if (ret) {
+				bdput(whole);
 				goto out_clear;
+			}
 			bdev->bd_contains = whole;
 			bdev->bd_part = disk_get_part(disk, partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
@@ -1570,7 +1570,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	put_disk(disk);
 	module_put(owner);
  out:
-	bdput(bdev);
 
 	return ret;
 }
@@ -1656,6 +1655,9 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 		bdput(whole);
 	}
 
+	if (res)
+		bdput(bdev);
+
 	return res;
 }
 EXPORT_SYMBOL(blkdev_get);
@@ -1775,6 +1777,16 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 	struct gendisk *disk = bdev->bd_disk;
 	struct block_device *victim = NULL;
 
+	/*
+	 * Sync early if it looks like we're the last one.  If someone else
+	 * opens the block device between now and the decrement of bd_openers
+	 * then we did a sync that we didn't need to, but that's not the end
+	 * of the world and we want to avoid long (could be several minute)
+	 * syncs while holding the mutex.
+	 */
+	if (bdev->bd_openers == 1)
+		sync_blockdev(bdev);
+
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
 	if (for_part)
 		bdev->bd_part_count--;
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index e4d5e6eae409..1cf75d1032e1 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1420,6 +1420,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans,
 		if (ret < 0 && ret != -ENOENT) {
 			ulist_free(tmp);
 			ulist_free(*roots);
+			*roots = NULL;
 			return ret;
 		}
 		node = ulist_next(tmp, &uiter);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index f5a8c0d26cf3..cf1e8ba50f6b 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1367,7 +1367,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	btrfs_tree_read_unlock_blocking(eb);
 	free_extent_buffer(eb);
 
-	extent_buffer_get(eb_rewin);
+	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin),
+				       eb_rewin, btrfs_header_level(eb_rewin));
 	btrfs_tree_read_lock(eb_rewin);
 	__tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm);
 	WARN_ON(btrfs_header_nritems(eb_rewin) >
@@ -1438,8 +1439,6 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 
 	if (!eb)
 		return NULL;
-	extent_buffer_get(eb);
-	btrfs_tree_read_lock(eb);
 	if (old_root) {
 		btrfs_set_header_bytenr(eb, eb->start);
 		btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV);
@@ -1447,6 +1446,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 		btrfs_set_header_level(eb, old_root->level);
 		btrfs_set_header_generation(eb, old_generation);
 	}
+	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb,
+				       btrfs_header_level(eb));
+	btrfs_tree_read_lock(eb);
 	if (tm)
 		__tree_mod_log_rewind(fs_info, eb, time_seq, tm);
 	else
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5412b12491cb..19a668e9164b 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1257,6 +1257,7 @@ struct btrfs_root {
 	int send_in_progress;
 	struct btrfs_subvolume_writers *subv_writers;
 	atomic_t will_be_snapshotted;
+	atomic_t snapshot_force_cow;
 
 	/* For qgroup metadata space reserve */
 	atomic64_t qgroup_meta_rsv;
@@ -3262,6 +3263,8 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
 int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 			unsigned long new_flags);
 int btrfs_sync_fs(struct super_block *sb, int wait);
+char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
+					  u64 subvol_objectid);
 
 static inline __printf(2, 3)
 void btrfs_no_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 096c015b22a4..ace58d6a270b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1200,6 +1200,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	refcount_set(&root->refs, 1);
 	atomic_set(&root->will_be_snapshotted, 0);
 	atomic64_set(&root->qgroup_meta_rsv, 0);
+	atomic_set(&root->snapshot_force_cow, 0);
 	root->log_transid = 0;
 	root->log_transid_committed = -1;
 	root->last_log_commit = 0;
@@ -1509,9 +1510,16 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 	spin_lock_init(&root->ino_cache_lock);
 	init_waitqueue_head(&root->ino_cache_wait);
 
-	ret = get_anon_bdev(&root->anon_dev);
-	if (ret)
-		goto fail;
+	/*
+	 * Don't assign anonymous block device to roots that are not exposed to
+	 * userspace, the id pool is limited to 1M
+	 */
+	if (is_fstree(root->root_key.objectid) &&
+	    btrfs_root_refs(&root->root_item) > 0) {
+		ret = get_anon_bdev(&root->anon_dev);
+		if (ret)
+			goto fail;
+	}
 
 	mutex_lock(&root->objectid_mutex);
 	ret = btrfs_find_highest_objectid(root,
@@ -4337,6 +4345,7 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache)
 		cache->io_ctl.inode = NULL;
 		iput(inode);
 	}
+	ASSERT(cache->io_ctl.pages == NULL);
 	btrfs_put_block_group(cache);
 }
 
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 3aeb5770f896..b6ce765aa7f3 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -56,9 +56,9 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len,
 	return type;
 }
 
-static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
-				       u64 root_objectid, u32 generation,
-				       int check_generation)
+struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
+				u64 root_objectid, u32 generation,
+				int check_generation)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
 	struct btrfs_root *root;
@@ -151,7 +151,7 @@ static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh,
 	return btrfs_get_dentry(sb, objectid, root_objectid, generation, 1);
 }
 
-static struct dentry *btrfs_get_parent(struct dentry *child)
+struct dentry *btrfs_get_parent(struct dentry *child)
 {
 	struct inode *dir = d_inode(child);
 	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
diff --git a/fs/btrfs/export.h b/fs/btrfs/export.h
index 91b3908e7c54..15db02462141 100644
--- a/fs/btrfs/export.h
+++ b/fs/btrfs/export.h
@@ -17,4 +17,9 @@ struct btrfs_fid {
 	u64 parent_root_objectid;
 } __attribute__ ((packed));
 
+struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
+				u64 root_objectid, u32 generation,
+				int check_generation);
+struct dentry *btrfs_get_parent(struct dentry *child);
+
 #endif
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 51e26f90f0bb..00481cfe6cfc 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1170,12 +1170,11 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
 			if (type == BTRFS_SHARED_BLOCK_REF_KEY) {
 				ASSERT(eb->fs_info);
 				/*
-				 * Every shared one has parent tree
-				 * block, which must be aligned to
-				 * nodesize.
+				 * Every shared one has parent tree block,
+				 * which must be aligned to sector size.
 				 */
 				if (offset &&
-				    IS_ALIGNED(offset, eb->fs_info->nodesize))
+				    IS_ALIGNED(offset, eb->fs_info->sectorsize))
 					return type;
 			}
 		} else if (is_data == BTRFS_REF_TYPE_DATA) {
@@ -1184,12 +1183,11 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
 			if (type == BTRFS_SHARED_DATA_REF_KEY) {
 				ASSERT(eb->fs_info);
 				/*
-				 * Every shared one has parent tree
-				 * block, which must be aligned to
-				 * nodesize.
+				 * Every shared one has parent tree block,
+				 * which must be aligned to sector size.
 				 */
 				if (offset &&
-				    IS_ALIGNED(offset, eb->fs_info->nodesize))
+				    IS_ALIGNED(offset, eb->fs_info->sectorsize))
 					return type;
 			}
 		} else {
@@ -1199,8 +1197,9 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
 	}
 
 	btrfs_print_leaf((struct extent_buffer *)eb);
-	btrfs_err(eb->fs_info, "eb %llu invalid extent inline ref type %d",
-		  eb->start, type);
+	btrfs_err(eb->fs_info,
+		  "eb %llu iref 0x%lx invalid extent inline ref type %d",
+		  eb->start, (unsigned long)iref, type);
 	WARN_ON(1);
 
 	return BTRFS_REF_TYPE_INVALID;
@@ -9365,8 +9364,6 @@ out:
 	 */
 	if (!for_reloc && root_dropped == false)
 		btrfs_add_dead_root(root);
-	if (err && err != -EAGAIN)
-		btrfs_handle_fs_error(fs_info, err, NULL);
 	return err;
 }
 
@@ -10554,7 +10551,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
-		goto out_put_group;
+		goto out;
 	}
 
 	/*
@@ -10591,7 +10588,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 		if (ret) {
 			btrfs_add_delayed_iput(inode);
-			goto out_put_group;
+			goto out;
 		}
 		clear_nlink(inode);
 		/* One for the block groups ref */
@@ -10614,13 +10611,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
 	if (ret < 0)
-		goto out_put_group;
+		goto out;
 	if (ret > 0)
 		btrfs_release_path(path);
 	if (ret == 0) {
 		ret = btrfs_del_item(trans, tree_root, path);
 		if (ret)
-			goto out_put_group;
+			goto out;
 		btrfs_release_path(path);
 	}
 
@@ -10629,6 +10626,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		 &fs_info->block_group_cache_tree);
 	RB_CLEAR_NODE(&block_group->cache_node);
 
+	/* Once for the block groups rbtree */
+	btrfs_put_block_group(block_group);
+
 	if (fs_info->first_logical_byte == block_group->key.objectid)
 		fs_info->first_logical_byte = (u64)-1;
 	spin_unlock(&fs_info->block_group_cache_lock);
@@ -10778,10 +10778,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	ret = remove_block_group_free_space(trans, fs_info, block_group);
 	if (ret)
-		goto out_put_group;
-
-	/* Once for the block groups rbtree */
-	btrfs_put_block_group(block_group);
+		goto out;
 
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret > 0)
@@ -10791,10 +10788,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_del_item(trans, root, path);
 
-out_put_group:
+out:
 	/* Once for the lookup reference */
 	btrfs_put_block_group(block_group);
-out:
 	btrfs_free_path(path);
 	return ret;
 }
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index a8be9478ca3e..0ba338cffa93 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1721,7 +1721,8 @@ static int __process_pages_contig(struct address_space *mapping,
 				if (!PageDirty(pages[i]) ||
 				    pages[i]->mapping != mapping) {
 					unlock_page(pages[i]);
-					put_page(pages[i]);
+					for (; i < ret; i++)
+						put_page(pages[i]);
 					err = -EAGAIN;
 					goto out;
 				}
@@ -4322,6 +4323,8 @@ int try_release_extent_mapping(struct extent_map_tree *map,
 
 			/* once for us */
 			free_extent_map(em);
+
+			cond_resched(); /* Allow large-extent preemption. */
 		}
 	}
 	return try_release_extent_state(map, tree, page, mask);
@@ -4862,25 +4865,28 @@ struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 static void check_buffer_tree_ref(struct extent_buffer *eb)
 {
 	int refs;
-	/* the ref bit is tricky.  We have to make sure it is set
-	 * if we have the buffer dirty.   Otherwise the
-	 * code to free a buffer can end up dropping a dirty
-	 * page
+	/*
+	 * The TREE_REF bit is first set when the extent_buffer is added
+	 * to the radix tree. It is also reset, if unset, when a new reference
+	 * is created by find_extent_buffer.
 	 *
-	 * Once the ref bit is set, it won't go away while the
-	 * buffer is dirty or in writeback, and it also won't
-	 * go away while we have the reference count on the
-	 * eb bumped.
+	 * It is only cleared in two cases: freeing the last non-tree
+	 * reference to the extent_buffer when its STALE bit is set or
+	 * calling releasepage when the tree reference is the only reference.
 	 *
-	 * We can't just set the ref bit without bumping the
-	 * ref on the eb because free_extent_buffer might
-	 * see the ref bit and try to clear it.  If this happens
-	 * free_extent_buffer might end up dropping our original
-	 * ref by mistake and freeing the page before we are able
-	 * to add one more ref.
+	 * In both cases, care is taken to ensure that the extent_buffer's
+	 * pages are not under io. However, releasepage can be concurrently
+	 * called with creating new references, which is prone to race
+	 * conditions between the calls to check_buffer_tree_ref in those
+	 * codepaths and clearing TREE_REF in try_release_extent_buffer.
 	 *
-	 * So bump the ref count first, then set the bit.  If someone
-	 * beat us to it, drop the ref we added.
+	 * The actual lifetime of the extent_buffer in the radix tree is
+	 * adequately protected by the refcount, but the TREE_REF bit and
+	 * its corresponding reference are not. To protect against this
+	 * class of races, we call check_buffer_tree_ref from the codepaths
+	 * which trigger io after they set eb->io_pages. Note that once io is
+	 * initiated, TREE_REF can no longer be cleared, so that is the
+	 * moment at which any such race is best fixed.
 	 */
 	refs = atomic_read(&eb->refs);
 	if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
@@ -5344,6 +5350,11 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = 0;
 	atomic_set(&eb->io_pages, num_reads);
+	/*
+	 * It is possible for releasepage to clear the TREE_REF bit before we
+	 * set io_pages. See check_buffer_tree_ref for a more detailed comment.
+	 */
+	check_buffer_tree_ref(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 
@@ -5437,9 +5448,9 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
 	}
 }
 
-int read_extent_buffer_to_user(const struct extent_buffer *eb,
-			       void __user *dstv,
-			       unsigned long start, unsigned long len)
+int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
+				       void __user *dstv,
+				       unsigned long start, unsigned long len)
 {
 	size_t cur;
 	size_t offset;
@@ -5460,7 +5471,7 @@ int read_extent_buffer_to_user(const struct extent_buffer *eb,
 
 		cur = min(len, (PAGE_SIZE - offset));
 		kaddr = page_address(page);
-		if (copy_to_user(dst, kaddr + offset, cur)) {
+		if (probe_user_write(dst, kaddr + offset, cur)) {
 			ret = -EFAULT;
 			break;
 		}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index e5535bbe6953..90c5095ae97e 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -455,9 +455,9 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
 void read_extent_buffer(const struct extent_buffer *eb, void *dst,
 			unsigned long start,
 			unsigned long len);
-int read_extent_buffer_to_user(const struct extent_buffer *eb,
-			       void __user *dst, unsigned long start,
-			       unsigned long len);
+int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
+				       void __user *dst, unsigned long start,
+				       unsigned long len);
 void write_extent_buffer_fsid(struct extent_buffer *eb, const void *src);
 void write_extent_buffer_chunk_tree_uuid(struct extent_buffer *eb,
 		const void *src);
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 717d82d51bb1..edd5f152e448 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -795,10 +795,12 @@ again:
 		nritems = btrfs_header_nritems(path->nodes[0]);
 		if (!nritems || (path->slots[0] >= nritems - 1)) {
 			ret = btrfs_next_leaf(root, path);
-			if (ret == 1)
+			if (ret < 0) {
+				goto out;
+			} else if (ret > 0) {
 				found_next = 1;
-			if (ret != 0)
 				goto insert;
+			}
 			slot = path->slots[0];
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index abeb26d48d0a..9bf72a9088ac 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1169,7 +1169,6 @@ static int __btrfs_wait_cache_io(struct btrfs_root *root,
 	ret = update_cache_item(trans, root, inode, path, offset,
 				io_ctl->entries, io_ctl->bitmaps);
 out:
-	io_ctl_free(io_ctl);
 	if (ret) {
 		invalidate_inode_pages2(inode->i_mapping);
 		BTRFS_I(inode)->generation = 0;
@@ -1334,6 +1333,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 	 * them out later
 	 */
 	io_ctl_drop_pages(io_ctl);
+	io_ctl_free(io_ctl);
 
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
 			     i_size_read(inode) - 1, &cached_state, GFP_NOFS);
@@ -2169,7 +2169,7 @@ out:
 static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl,
 			  struct btrfs_free_space *info, bool update_stat)
 {
-	struct btrfs_free_space *left_info;
+	struct btrfs_free_space *left_info = NULL;
 	struct btrfs_free_space *right_info;
 	bool merged = false;
 	u64 offset = info->offset;
@@ -2184,7 +2184,7 @@ static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl,
 	if (right_info && rb_prev(&right_info->offset_index))
 		left_info = rb_entry(rb_prev(&right_info->offset_index),
 				     struct btrfs_free_space, offset_index);
-	else
+	else if (!right_info)
 		left_info = tree_search_offset(ctl, offset - 1, 0, 0);
 
 	if (right_info && !right_info->bitmap) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2a196bb134d9..e985e820724e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -629,7 +629,21 @@ cont:
 				btrfs_free_reserved_data_space_noquota(inode,
 							       start,
 							       end - start + 1);
-			goto free_pages_out;
+
+			/*
+			 * Ensure we only free the compressed pages if we have
+			 * them allocated, as we can still reach here with
+			 * inode_need_compress() == false.
+			 */
+			if (pages) {
+				for (i = 0; i < nr_pages; i++) {
+					WARN_ON(pages[i]->mapping);
+					put_page(pages[i]);
+				}
+				kfree(pages);
+			}
+
+			return;
 		}
 	}
 
@@ -708,13 +722,6 @@ cleanup_and_bail_uncompressed:
 	*num_added += 1;
 
 	return;
-
-free_pages_out:
-	for (i = 0; i < nr_pages; i++) {
-		WARN_ON(pages[i]->mapping);
-		put_page(pages[i]);
-	}
-	kfree(pages);
 }
 
 static void free_async_extent_pages(struct async_extent *async_extent)
@@ -978,8 +985,8 @@ static noinline int cow_file_range(struct inode *inode,
 	u64 alloc_hint = 0;
 	u64 num_bytes;
 	unsigned long ram_size;
-	u64 disk_num_bytes;
 	u64 cur_alloc_size = 0;
+	u64 min_alloc_size;
 	u64 blocksize = fs_info->sectorsize;
 	struct btrfs_key ins;
 	struct extent_map *em;
@@ -996,7 +1003,6 @@ static noinline int cow_file_range(struct inode *inode,
 
 	num_bytes = ALIGN(end - start + 1, blocksize);
 	num_bytes = max(blocksize,  num_bytes);
-	disk_num_bytes = num_bytes;
 
 	inode_should_defrag(BTRFS_I(inode), start, end, num_bytes, SZ_64K);
 
@@ -1023,17 +1029,32 @@ static noinline int cow_file_range(struct inode *inode,
 		}
 	}
 
-	BUG_ON(disk_num_bytes >
-	       btrfs_super_total_bytes(fs_info->super_copy));
+	BUG_ON(num_bytes > btrfs_super_total_bytes(fs_info->super_copy));
 
 	alloc_hint = get_extent_allocation_hint(inode, start, num_bytes);
 	btrfs_drop_extent_cache(BTRFS_I(inode), start,
 			start + num_bytes - 1, 0);
 
-	while (disk_num_bytes > 0) {
-		cur_alloc_size = disk_num_bytes;
+	/*
+	 * Relocation relies on the relocated extents to have exactly the same
+	 * size as the original extents. Normally writeback for relocation data
+	 * extents follows a NOCOW path because relocation preallocates the
+	 * extents. However, due to an operation such as scrub turning a block
+	 * group to RO mode, it may fallback to COW mode, so we must make sure
+	 * an extent allocated during COW has exactly the requested size and can
+	 * not be split into smaller extents, otherwise relocation breaks and
+	 * fails during the stage where it updates the bytenr of file extent
+	 * items.
+	 */
+	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
+		min_alloc_size = num_bytes;
+	else
+		min_alloc_size = fs_info->sectorsize;
+
+	while (num_bytes > 0) {
+		cur_alloc_size = num_bytes;
 		ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
-					   fs_info->sectorsize, 0, alloc_hint,
+					   min_alloc_size, 0, alloc_hint,
 					   &ins, 1, 1);
 		if (ret < 0)
 			goto out_unlock;
@@ -1097,11 +1118,10 @@ static noinline int cow_file_range(struct inode *inode,
 					     delalloc_end, locked_page,
 					     EXTENT_LOCKED | EXTENT_DELALLOC,
 					     page_ops);
-		if (disk_num_bytes < cur_alloc_size)
-			disk_num_bytes = 0;
+		if (num_bytes < cur_alloc_size)
+			num_bytes = 0;
 		else
-			disk_num_bytes -= cur_alloc_size;
-		num_bytes -= cur_alloc_size;
+			num_bytes -= cur_alloc_size;
 		alloc_hint = ins.objectid + ins.offset;
 		start += cur_alloc_size;
 		extent_reserved = false;
@@ -1139,8 +1159,8 @@ out_unlock:
 	 */
 	if (extent_reserved) {
 		extent_clear_unlock_delalloc(inode, start,
-					     start + cur_alloc_size,
-					     start + cur_alloc_size,
+					     start + cur_alloc_size - 1,
+					     start + cur_alloc_size - 1,
 					     locked_page,
 					     clear_bits,
 					     page_ops);
@@ -1315,7 +1335,7 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 	u64 disk_num_bytes;
 	u64 ram_bytes;
 	int extent_type;
-	int ret, err;
+	int ret;
 	int type;
 	int nocow;
 	int check_prev = 1;
@@ -1440,11 +1460,8 @@ next_slot:
 			 * if there are pending snapshots for this root,
 			 * we fall into common COW way.
 			 */
-			if (!nolock) {
-				err = btrfs_start_write_no_snapshotting(root);
-				if (!err)
-					goto out_check;
-			}
+			if (!nolock && atomic_read(&root->snapshot_force_cow))
+				goto out_check;
 			/*
 			 * force cow if csum exists in the range.
 			 * this ensure that csum for a given extent are
@@ -1453,9 +1470,6 @@ next_slot:
 			ret = csum_exist_in_range(fs_info, disk_bytenr,
 						  num_bytes);
 			if (ret) {
-				if (!nolock)
-					btrfs_end_write_no_snapshotting(root);
-
 				/*
 				 * ret could be -EIO if the above fails to read
 				 * metadata.
@@ -1468,11 +1482,8 @@ next_slot:
 				WARN_ON_ONCE(nolock);
 				goto out_check;
 			}
-			if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) {
-				if (!nolock)
-					btrfs_end_write_no_snapshotting(root);
+			if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr))
 				goto out_check;
-			}
 			nocow = 1;
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = found_key.offset +
@@ -1485,8 +1496,6 @@ next_slot:
 out_check:
 		if (extent_end <= start) {
 			path->slots[0]++;
-			if (!nolock && nocow)
-				btrfs_end_write_no_snapshotting(root);
 			if (nocow)
 				btrfs_dec_nocow_writers(fs_info, disk_bytenr);
 			goto next_slot;
@@ -1508,8 +1517,6 @@ out_check:
 					     end, page_started, nr_written, 1,
 					     NULL);
 			if (ret) {
-				if (!nolock && nocow)
-					btrfs_end_write_no_snapshotting(root);
 				if (nocow)
 					btrfs_dec_nocow_writers(fs_info,
 								disk_bytenr);
@@ -1529,8 +1536,6 @@ out_check:
 					  ram_bytes, BTRFS_COMPRESS_NONE,
 					  BTRFS_ORDERED_PREALLOC);
 			if (IS_ERR(em)) {
-				if (!nolock && nocow)
-					btrfs_end_write_no_snapshotting(root);
 				if (nocow)
 					btrfs_dec_nocow_writers(fs_info,
 								disk_bytenr);
@@ -1569,8 +1574,6 @@ out_check:
 					     EXTENT_CLEAR_DATA_RESV,
 					     PAGE_UNLOCK | PAGE_SET_PRIVATE2);
 
-		if (!nolock && nocow)
-			btrfs_end_write_no_snapshotting(root);
 		cur_offset = extent_end;
 
 		/*
@@ -8707,7 +8710,6 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
 
 	/* bio split */
 	ASSERT(map_length <= INT_MAX);
-	atomic_inc(&dip->pending_bios);
 	do {
 		clone_len = min_t(int, submit_len, map_length);
 
@@ -8758,7 +8760,8 @@ submit:
 	if (!status)
 		return 0;
 
-	bio_put(bio);
+	if (bio != orig_bio)
+		bio_put(bio);
 out_err:
 	dip->errors = 1;
 	/*
@@ -8798,7 +8801,7 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
 	bio->bi_private = dip;
 	dip->orig_bio = bio;
 	dip->dio_bio = dio_bio;
-	atomic_set(&dip->pending_bios, 0);
+	atomic_set(&dip->pending_bios, 1);
 	io_bio = btrfs_io_bio(bio);
 	io_bio->logical = file_offset;
 
@@ -8947,9 +8950,6 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 			dio_data.overwrite = 1;
 			inode_unlock(inode);
 			relock = true;
-		} else if (iocb->ki_flags & IOCB_NOWAIT) {
-			ret = -EAGAIN;
-			goto out;
 		}
 		ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
 						   offset, count);
@@ -9187,20 +9187,17 @@ again:
 	/*
 	 * Qgroup reserved space handler
 	 * Page here will be either
-	 * 1) Already written to disk
-	 *    In this case, its reserved space is released from data rsv map
-	 *    and will be freed by delayed_ref handler finally.
-	 *    So even we call qgroup_free_data(), it won't decrease reserved
-	 *    space.
-	 * 2) Not written to disk
-	 *    This means the reserved space should be freed here. However,
-	 *    if a truncate invalidates the page (by clearing PageDirty)
-	 *    and the page is accounted for while allocating extent
-	 *    in btrfs_check_data_free_space() we let delayed_ref to
-	 *    free the entire extent.
+	 * 1) Already written to disk or ordered extent already submitted
+	 *    Then its QGROUP_RESERVED bit in io_tree is already cleaned.
+	 *    Qgroup will be handled by its qgroup_record then.
+	 *    btrfs_qgroup_free_data() call will do nothing here.
+	 *
+	 * 2) Not written to disk yet
+	 *    Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED
+	 *    bit of its io_tree, and free the qgroup reserved data space.
+	 *    Since the IO will never happen for this page.
 	 */
-	if (PageDirty(page))
-		btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
+	btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
 	if (!inode_evicting) {
 		clear_extent_bit(tree, page_start, page_end,
 				 EXTENT_LOCKED | EXTENT_DIRTY |
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index e82b4f3f490c..56123ce3b9f0 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -655,6 +655,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	struct btrfs_pending_snapshot *pending_snapshot;
 	struct btrfs_trans_handle *trans;
 	int ret;
+	bool snapshot_force_cow = false;
 
 	if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 		return -EINVAL;
@@ -671,6 +672,11 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 		goto free_pending;
 	}
 
+	/*
+	 * Force new buffered writes to reserve space even when NOCOW is
+	 * possible. This is to avoid later writeback (running dealloc) to
+	 * fallback to COW mode and unexpectedly fail with ENOSPC.
+	 */
 	atomic_inc(&root->will_be_snapshotted);
 	smp_mb__after_atomic();
 	btrfs_wait_for_no_snapshotting_writes(root);
@@ -679,6 +685,14 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	if (ret)
 		goto dec_and_free;
 
+	/*
+	 * All previous writes have started writeback in NOCOW mode, so now
+	 * we force future writes to fallback to COW mode during snapshot
+	 * creation.
+	 */
+	atomic_inc(&root->snapshot_force_cow);
+	snapshot_force_cow = true;
+
 	btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1);
 
 	btrfs_init_block_rsv(&pending_snapshot->block_rsv,
@@ -744,6 +758,8 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 fail:
 	btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv);
 dec_and_free:
+	if (snapshot_force_cow)
+		atomic_dec(&root->snapshot_force_cow);
 	if (atomic_dec_and_test(&root->will_be_snapshotted))
 		wake_up_atomic_t(&root->will_be_snapshotted);
 free_pending:
@@ -2021,9 +2037,14 @@ static noinline int copy_to_sk(struct btrfs_path *path,
 		sh.len = item_len;
 		sh.transid = found_transid;
 
-		/* copy search result header */
-		if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) {
-			ret = -EFAULT;
+		/*
+		 * Copy search result header. If we fault then loop again so we
+		 * can fault in the pages and -EFAULT there if there's a
+		 * problem. Otherwise we'll fault and then copy the buffer in
+		 * properly this next time through
+		 */
+		if (probe_user_write(ubuf + *sk_offset, &sh, sizeof(sh))) {
+			ret = 0;
 			goto out;
 		}
 
@@ -2031,10 +2052,14 @@ static noinline int copy_to_sk(struct btrfs_path *path,
 
 		if (item_len) {
 			char __user *up = ubuf + *sk_offset;
-			/* copy the item */
-			if (read_extent_buffer_to_user(leaf, up,
-						       item_off, item_len)) {
-				ret = -EFAULT;
+			/*
+			 * Copy the item, same behavior as above, but reset the
+			 * * sk_offset so we copy the full thing again.
+			 */
+			if (read_extent_buffer_to_user_nofault(leaf, up,
+						item_off, item_len)) {
+				ret = 0;
+				*sk_offset -= sizeof(sh);
 				goto out;
 			}
 
@@ -2122,6 +2147,11 @@ static noinline int search_ioctl(struct inode *inode,
 	key.offset = sk->min_offset;
 
 	while (1) {
+		ret = fault_in_pages_writeable(ubuf + sk_offset,
+					       *buf_size - sk_offset);
+		if (ret)
+			break;
+
 		ret = btrfs_search_forward(root, &key, path, sk->min_transid);
 		if (ret != 0) {
 			if (ret > 0)
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 47336d4b19d8..f96eb176166d 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -116,9 +116,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 			 * offset is supposed to be a tree block which
 			 * must be aligned to nodesize.
 			 */
-			if (!IS_ALIGNED(offset, eb->fs_info->nodesize))
-				pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n",
-					offset, (unsigned long long)eb->fs_info->nodesize);
+			if (!IS_ALIGNED(offset, eb->fs_info->sectorsize))
+				pr_info(
+			"\t\t\t(parent %llu not aligned to sectorsize %u)\n",
+					offset, eb->fs_info->sectorsize);
 			break;
 		case BTRFS_EXTENT_DATA_REF_KEY:
 			dref = (struct btrfs_extent_data_ref *)(&iref->offset);
@@ -133,8 +134,9 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 			 * must be aligned to nodesize.
 			 */
 			if (!IS_ALIGNED(offset, eb->fs_info->nodesize))
-				pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n",
-				     offset, (unsigned long long)eb->fs_info->nodesize);
+				pr_info(
+			"\t\t\t(parent %llu not aligned to sectorsize %u)\n",
+				     offset, eb->fs_info->sectorsize);
 			break;
 		default:
 			pr_cont("(extent %llu has INVALID ref type %d)\n",
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index ca15d65a2070..654ab6e57ec3 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -35,6 +35,7 @@
 #include "btrfs_inode.h"
 #include "transaction.h"
 #include "compression.h"
+#include "xattr.h"
 
 /*
  * Maximum number of references an extent can have in order for us to attempt to
@@ -4554,6 +4555,10 @@ static int __process_new_xattr(int num, struct btrfs_key *di_key,
 	struct fs_path *p;
 	struct posix_acl_xattr_header dummy_acl;
 
+	/* Capabilities are emitted by finish_inode_if_needed */
+	if (!strncmp(name, XATTR_NAME_CAPS, name_len))
+		return 0;
+
 	p = fs_path_alloc();
 	if (!p)
 		return -ENOMEM;
@@ -5096,6 +5101,64 @@ static int send_extent_data(struct send_ctx *sctx,
 	return 0;
 }
 
+/*
+ * Search for a capability xattr related to sctx->cur_ino. If the capability is
+ * found, call send_set_xattr function to emit it.
+ *
+ * Return 0 if there isn't a capability, or when the capability was emitted
+ * successfully, or < 0 if an error occurred.
+ */
+static int send_capabilities(struct send_ctx *sctx)
+{
+	struct fs_path *fspath = NULL;
+	struct btrfs_path *path;
+	struct btrfs_dir_item *di;
+	struct extent_buffer *leaf;
+	unsigned long data_ptr;
+	char *buf = NULL;
+	int buf_len;
+	int ret = 0;
+
+	path = alloc_path_for_send();
+	if (!path)
+		return -ENOMEM;
+
+	di = btrfs_lookup_xattr(NULL, sctx->send_root, path, sctx->cur_ino,
+				XATTR_NAME_CAPS, strlen(XATTR_NAME_CAPS), 0);
+	if (!di) {
+		/* There is no xattr for this inode */
+		goto out;
+	} else if (IS_ERR(di)) {
+		ret = PTR_ERR(di);
+		goto out;
+	}
+
+	leaf = path->nodes[0];
+	buf_len = btrfs_dir_data_len(leaf, di);
+
+	fspath = fs_path_alloc();
+	buf = kmalloc(buf_len, GFP_KERNEL);
+	if (!fspath || !buf) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, fspath);
+	if (ret < 0)
+		goto out;
+
+	data_ptr = (unsigned long)(di + 1) + btrfs_dir_name_len(leaf, di);
+	read_extent_buffer(leaf, buf, data_ptr, buf_len);
+
+	ret = send_set_xattr(sctx, fspath, XATTR_NAME_CAPS,
+			strlen(XATTR_NAME_CAPS), buf, buf_len);
+out:
+	kfree(buf);
+	fs_path_free(fspath);
+	btrfs_free_path(path);
+	return ret;
+}
+
 static int clone_range(struct send_ctx *sctx,
 		       struct clone_root *clone_root,
 		       const u64 disk_byte,
@@ -5907,6 +5970,10 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 			goto out;
 	}
 
+	ret = send_capabilities(sctx);
+	if (ret < 0)
+		goto out;
+
 	/*
 	 * If other directory inodes depended on our current directory
 	 * inode's move/rename, now do their move/rename operations.
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 17a8463ef35c..eb64d4b159e0 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -939,8 +939,8 @@ out:
 	return error;
 }
 
-static char *get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
-					   u64 subvol_objectid)
+char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
+					  u64 subvol_objectid)
 {
 	struct btrfs_root *root = fs_info->tree_root;
 	struct btrfs_root *fs_root;
@@ -1221,6 +1221,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 {
 	struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb);
 	char *compress_type;
+	const char *subvol_name;
 
 	if (btrfs_test_opt(info, DEGRADED))
 		seq_puts(seq, ",degraded");
@@ -1307,8 +1308,13 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 #endif
 	seq_printf(seq, ",subvolid=%llu",
 		  BTRFS_I(d_inode(dentry))->root->root_key.objectid);
-	seq_puts(seq, ",subvol=");
-	seq_dentry(seq, dentry, " \t\n\\");
+	subvol_name = btrfs_get_subvol_name_from_objectid(info,
+			BTRFS_I(d_inode(dentry))->root->root_key.objectid);
+	if (!IS_ERR(subvol_name)) {
+		seq_puts(seq, ",subvol=");
+		seq_escape(seq, subvol_name, " \t\n\\");
+		kfree(subvol_name);
+	}
 	return 0;
 }
 
@@ -1427,8 +1433,8 @@ static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid,
 				goto out;
 			}
 		}
-		subvol_name = get_subvol_name_from_objectid(btrfs_sb(mnt->mnt_sb),
-							    subvol_objectid);
+		subvol_name = btrfs_get_subvol_name_from_objectid(
+					btrfs_sb(mnt->mnt_sb), subvol_objectid);
 		if (IS_ERR(subvol_name)) {
 			root = ERR_CAST(subvol_name);
 			subvol_name = NULL;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index f05341bda1d1..383546ff62f0 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -25,6 +25,7 @@
 #include <linux/bug.h>
 #include <linux/genhd.h>
 #include <linux/debugfs.h>
+#include <linux/sched/mm.h>
 
 #include "ctree.h"
 #include "disk-io.h"
@@ -749,7 +750,9 @@ int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
 {
 	int error = 0;
 	struct btrfs_device *dev;
+	unsigned int nofs_flag;
 
+	nofs_flag = memalloc_nofs_save();
 	list_for_each_entry(dev, &fs_devices->devices, dev_list) {
 		struct hd_struct *disk;
 		struct kobject *disk_kobj;
@@ -768,6 +771,7 @@ int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
 		if (error)
 			break;
 	}
+	memalloc_nofs_restore(nofs_flag);
 
 	return error;
 }
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index bcfb7a772c8e..ec8706a6e9c6 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3311,11 +3311,13 @@ fail:
 	btrfs_free_path(path);
 out_unlock:
 	mutex_unlock(&dir->log_mutex);
-	if (ret == -ENOSPC) {
+	if (err == -ENOSPC) {
 		btrfs_set_log_full_commit(root->fs_info, trans);
-		ret = 0;
-	} else if (ret < 0)
-		btrfs_abort_transaction(trans, ret);
+		err = 0;
+	} else if (err < 0 && err != -ENOENT) {
+		/* ENOENT can be returned if the entry hasn't been fsynced yet */
+		btrfs_abort_transaction(trans, err);
+	}
 
 	btrfs_end_log_trans(root);
 
@@ -3854,11 +3856,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 						fs_info->csum_root,
 						ds + cs, ds + cs + cl - 1,
 						&ordered_sums, 0);
-				if (ret) {
-					btrfs_release_path(dst_path);
-					kfree(ins_data);
-					return ret;
-				}
+				if (ret)
+					break;
 			}
 		}
 	}
@@ -3871,7 +3870,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	 * we have to do this after the loop above to avoid changing the
 	 * log tree while trying to change the log tree.
 	 */
-	ret = 0;
 	while (!list_empty(&ordered_sums)) {
 		struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next,
 						   struct btrfs_ordered_sum,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6d34842912e8..f3cb042a28d5 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -16,6 +16,7 @@
  * Boston, MA 021110-1307, USA.
  */
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
 #include <linux/buffer_head.h>
@@ -4174,6 +4175,7 @@ static int btrfs_uuid_scan_kthread(void *data)
 			goto skip;
 		}
 update_tree:
+		btrfs_release_path(path);
 		if (!btrfs_is_empty_uuid(root_item.uuid)) {
 			ret = btrfs_uuid_tree_add(trans, fs_info,
 						  root_item.uuid,
@@ -4199,6 +4201,7 @@ update_tree:
 		}
 
 skip:
+		btrfs_release_path(path);
 		if (trans) {
 			ret = btrfs_end_transaction(trans);
 			trans = NULL;
@@ -4206,7 +4209,6 @@ skip:
 				break;
 		}
 
-		btrfs_release_path(path);
 		if (key.offset < (u64)-1) {
 			key.offset++;
 		} else if (key.type < BTRFS_ROOT_ITEM_KEY) {
@@ -6277,8 +6279,17 @@ static struct btrfs_device *add_missing_dev(struct btrfs_fs_devices *fs_devices,
 					    u64 devid, u8 *dev_uuid)
 {
 	struct btrfs_device *device;
+	unsigned int nofs_flag;
 
+	/*
+	 * We call this under the chunk_mutex, so we want to use NOFS for this
+	 * allocation, however we don't want to change btrfs_alloc_device() to
+	 * always do NOFS because we use it in a lot of other GFP_KERNEL safe
+	 * places.
+	 */
+	nofs_flag = memalloc_nofs_save();
 	device = btrfs_alloc_device(NULL, &devid, dev_uuid);
+	memalloc_nofs_restore(nofs_flag);
 	if (IS_ERR(device))
 		return NULL;
 
@@ -6902,6 +6913,14 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 	mutex_lock(&fs_info->chunk_mutex);
 
 	/*
+	 * It is possible for mount and umount to race in such a way that
+	 * we execute this code path, but open_fs_devices failed to clear
+	 * total_rw_bytes. We certainly want it cleared before reading the
+	 * device items, so clear it here.
+	 */
+	fs_info->fs_devices->total_rw_bytes = 0;
+
+	/*
 	 * Read all device items, and then all the chunk items. All
 	 * device items are found before any chunk item (their object id
 	 * is smaller than the lowest possible object id for a chunk
diff --git a/fs/buffer.c b/fs/buffer.c
index cae7f24a0410..9fbeddb6834a 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3250,6 +3250,15 @@ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags)
 	WARN_ON(atomic_read(&bh->b_count) < 1);
 	lock_buffer(bh);
 	if (test_clear_buffer_dirty(bh)) {
+		/*
+		 * The bh should be mapped, but it might not be if the
+		 * device was hot-removed. Not much we can do but fail the I/O.
+		 */
+		if (!buffer_mapped(bh)) {
+			unlock_buffer(bh);
+			return -EIO;
+		}
+
 		get_bh(bh);
 		bh->b_end_io = end_buffer_write_sync;
 		ret = submit_bh(REQ_OP_WRITE, op_flags, bh);
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 5e9176ec0d3a..c073a0f680fd 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -64,9 +64,9 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
 	object = container_of(op->op.object, struct cachefiles_object, fscache);
 	spin_lock(&object->work_lock);
 	list_add_tail(&monitor->op_link, &op->to_do);
+	fscache_enqueue_retrieval(op);
 	spin_unlock(&object->work_lock);
 
-	fscache_enqueue_retrieval(op);
 	fscache_put_retrieval(op);
 	return 0;
 }
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 589cfe3ed873..ce94d09f6abf 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1906,12 +1906,24 @@ ack:
 			if (mutex_trylock(&session->s_mutex) == 0) {
 				dout("inverting session/ino locks on %p\n",
 				     session);
+				session = ceph_get_mds_session(session);
 				spin_unlock(&ci->i_ceph_lock);
 				if (took_snap_rwsem) {
 					up_read(&mdsc->snap_rwsem);
 					took_snap_rwsem = 0;
 				}
-				mutex_lock(&session->s_mutex);
+				if (session) {
+					mutex_lock(&session->s_mutex);
+					ceph_put_mds_session(session);
+				} else {
+					/*
+					 * Because we take the reference while
+					 * holding the i_ceph_lock, it should
+					 * never be NULL. Throw a warning if it
+					 * ever is.
+					 */
+					WARN_ON_ONCE(true);
+				}
 				goto retry;
 			}
 		}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 6d653235e323..1f873034f469 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1728,6 +1728,7 @@ const struct file_operations ceph_file_fops = {
 	.mmap = ceph_mmap,
 	.fsync = ceph_fsync,
 	.lock = ceph_lock,
+	.setlease = simple_nosetlease,
 	.flock = ceph_flock,
 	.splice_read = generic_file_splice_read,
 	.splice_write = iter_file_splice_write,
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f36ddfea4997..06109314d93c 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3518,6 +3518,9 @@ static void delayed_work(struct work_struct *work)
 	dout("mdsc delayed_work\n");
 	ceph_check_delayed_caps(mdsc);
 
+	if (mdsc->stopping)
+		return;
+
 	mutex_lock(&mdsc->mutex);
 	renew_interval = mdsc->mdsmap->m_session_timeout >> 2;
 	renew_caps = time_after_eq(jiffies, HZ*renew_interval +
@@ -3851,7 +3854,16 @@ void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc)
 static void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
 {
 	dout("stop\n");
-	cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */
+	/*
+	 * Make sure the delayed work stopped before releasing
+	 * the resources.
+	 *
+	 * Because the cancel_delayed_work_sync() will only
+	 * guarantee that the work finishes executing. But the
+	 * delayed work will re-arm itself again after that.
+	 */
+	flush_delayed_work(&mdsc->delayed_work);
+
 	if (mdsc->mdsmap)
 		ceph_mdsmap_destroy(mdsc->mdsmap);
 	kfree(mdsc->sessions);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 600bb838c15b..f166fcb48ac0 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -246,8 +246,9 @@ struct smb_version_operations {
 	int (*check_message)(char *, unsigned int, struct TCP_Server_Info *);
 	bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
 	int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *);
-	void (*downgrade_oplock)(struct TCP_Server_Info *,
-					struct cifsInodeInfo *, bool);
+	void (*downgrade_oplock)(struct TCP_Server_Info *server,
+				 struct cifsInodeInfo *cinode, __u32 oplock,
+				 unsigned int epoch, bool *purge_cache);
 	/* process transaction2 response */
 	bool (*check_trans2)(struct mid_q_entry *, struct TCP_Server_Info *,
 			     char *, int);
@@ -1092,6 +1093,8 @@ struct cifsFileInfo {
 	unsigned int f_flags;
 	bool invalidHandle:1;	/* file closed via session abend */
 	bool oplock_break_cancelled:1;
+	unsigned int oplock_epoch; /* epoch from the lease break */
+	__u32 oplock_level; /* oplock/lease level from the lease break */
 	int count;
 	spinlock_t file_info_lock; /* protects four flag/count fields above */
 	struct mutex fh_mutex; /* prevents reopen race after dead ses*/
@@ -1223,7 +1226,7 @@ struct cifsInodeInfo {
 	unsigned int epoch;		/* used to track lease state changes */
 #define CIFS_INODE_PENDING_OPLOCK_BREAK   (0) /* oplock break in progress */
 #define CIFS_INODE_PENDING_WRITERS	  (1) /* Writes in progress */
-#define CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 (2) /* Downgrade oplock to L2 */
+#define CIFS_INODE_FLAG_UNUSED		  (2) /* Unused flag */
 #define CIFS_INO_DELETE_PENDING		  (3) /* delete pending on server */
 #define CIFS_INO_INVALID_MAPPING	  (4) /* pagecache is invalid */
 #define CIFS_INO_LOCK			  (5) /* lock bit for synchronization */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 58e7288e5151..64e52374ecc2 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -4324,9 +4324,12 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 	vol_info->retry = master_tcon->retry;
 	vol_info->nocase = master_tcon->nocase;
 	vol_info->local_lease = master_tcon->local_lease;
+	vol_info->resilient = master_tcon->use_resilient;
+	vol_info->persistent = master_tcon->use_persistent;
 	vol_info->no_linux_ext = !master_tcon->unix_ext;
 	vol_info->sectype = master_tcon->ses->sectype;
 	vol_info->sign = master_tcon->ses->sign;
+	vol_info->seal = master_tcon->seal;
 
 	rc = cifs_set_vol_auth(vol_info, master_tcon->ses);
 	if (rc) {
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 662977b8d6ae..6c77a96437e6 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3496,7 +3496,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
 			 * than it negotiated since it will refuse the read
 			 * then.
 			 */
-			if ((tcon->ses) && !(tcon->ses->capabilities &
+			if (!(tcon->ses->capabilities &
 				tcon->ses->server->vals->cap_large_files)) {
 				current_read_size = min_t(uint,
 					current_read_size, CIFSMaxBufSize);
@@ -3753,7 +3753,8 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 			break;
 
 		__SetPageLocked(page);
-		if (add_to_page_cache_locked(page, mapping, page->index, gfp)) {
+		rc = add_to_page_cache_locked(page, mapping, page->index, gfp);
+		if (rc) {
 			__ClearPageLocked(page);
 			break;
 		}
@@ -3769,6 +3770,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 	struct list_head *page_list, unsigned num_pages)
 {
 	int rc;
+	int err = 0;
 	struct list_head tmplist;
 	struct cifsFileInfo *open_file = file->private_data;
 	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
@@ -3809,7 +3811,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 	 * the order of declining indexes. When we put the pages in
 	 * the rdata->pages, then we want them in increasing order.
 	 */
-	while (!list_empty(page_list)) {
+	while (!list_empty(page_list) && !err) {
 		unsigned int i, nr_pages, bytes, rsize;
 		loff_t offset;
 		struct page *page, *tpage;
@@ -3832,9 +3834,10 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 			return 0;
 		}
 
-		rc = readpages_get_pages(mapping, page_list, rsize, &tmplist,
+		nr_pages = 0;
+		err = readpages_get_pages(mapping, page_list, rsize, &tmplist,
 					 &nr_pages, &offset, &bytes);
-		if (rc) {
+		if (!nr_pages) {
 			add_credits_and_wake_if(server, credits, 0);
 			break;
 		}
@@ -4135,12 +4138,13 @@ void cifs_oplock_break(struct work_struct *work)
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
 	int rc = 0;
+	bool purge_cache = false;
 
 	wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS,
 			TASK_UNINTERRUPTIBLE);
 
-	server->ops->downgrade_oplock(server, cinode,
-		test_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags));
+	server->ops->downgrade_oplock(server, cinode, cfile->oplock_level,
+				      cfile->oplock_epoch, &purge_cache);
 
 	if (!CIFS_CACHE_WRITE(cinode) && CIFS_CACHE_READ(cinode) &&
 						cifs_has_mand_locks(cinode)) {
@@ -4155,18 +4159,21 @@ void cifs_oplock_break(struct work_struct *work)
 		else
 			break_lease(inode, O_WRONLY);
 		rc = filemap_fdatawrite(inode->i_mapping);
-		if (!CIFS_CACHE_READ(cinode)) {
+		if (!CIFS_CACHE_READ(cinode) || purge_cache) {
 			rc = filemap_fdatawait(inode->i_mapping);
 			mapping_set_error(inode->i_mapping, rc);
 			cifs_zap_mapping(inode);
 		}
 		cifs_dbg(FYI, "Oplock flush inode %p rc %d\n", inode, rc);
+		if (CIFS_CACHE_WRITE(cinode))
+			goto oplock_break_ack;
 	}
 
 	rc = cifs_push_locks(cfile);
 	if (rc)
 		cifs_dbg(VFS, "Push locks rc = %d\n", rc);
 
+oplock_break_ack:
 	/*
 	 * releasing stale oplock after recent reconnect of smb session using
 	 * a now incorrect file handle is not a data integrity issue but do
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index bdce714e9448..b76e73395299 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -2210,6 +2210,15 @@ set_size_out:
 	if (rc == 0) {
 		cifsInode->server_eof = attrs->ia_size;
 		cifs_setsize(inode, attrs->ia_size);
+
+		/*
+		 * The man page of truncate says if the size changed,
+		 * then the st_ctime and st_mtime fields for the file
+		 * are updated.
+		 */
+		attrs->ia_ctime = attrs->ia_mtime = current_time(inode);
+		attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME;
+
 		cifs_truncate_page(inode->i_mapping, inode->i_size);
 	}
 
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 76f1649ab444..d0e024856c0d 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -473,21 +473,10 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
 				set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK,
 					&pCifsInode->flags);
 
-				/*
-				 * Set flag if the server downgrades the oplock
-				 * to L2 else clear.
-				 */
-				if (pSMB->OplockLevel)
-					set_bit(
-					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
-					   &pCifsInode->flags);
-				else
-					clear_bit(
-					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
-					   &pCifsInode->flags);
-
-				cifs_queue_oplock_break(netfile);
+				netfile->oplock_epoch = 0;
+				netfile->oplock_level = pSMB->OplockLevel;
 				netfile->oplock_break_cancelled = false;
+				cifs_queue_oplock_break(netfile);
 
 				spin_unlock(&tcon->open_file_lock);
 				spin_unlock(&cifs_tcp_ses_lock);
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 483458340b10..9b271ae641c1 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -379,12 +379,10 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr)
 
 static void
 cifs_downgrade_oplock(struct TCP_Server_Info *server,
-			struct cifsInodeInfo *cinode, bool set_level2)
+		      struct cifsInodeInfo *cinode, __u32 oplock,
+		      unsigned int epoch, bool *purge_cache)
 {
-	if (set_level2)
-		cifs_set_oplock_level(cinode, OPLOCK_READ);
-	else
-		cifs_set_oplock_level(cinode, 0);
+	cifs_set_oplock_level(cinode, oplock);
 }
 
 static bool
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index ff2ad15f67d6..0c6e5450ff76 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -496,7 +496,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
 
 		cifs_dbg(FYI, "found in the open list\n");
 		cifs_dbg(FYI, "lease key match, lease break 0x%x\n",
-			 le32_to_cpu(rsp->NewLeaseState));
+			 lease_state);
 
 		if (ack_req)
 			cfile->oplock_break_cancelled = false;
@@ -505,17 +505,8 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
 
 		set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags);
 
-		/*
-		 * Set or clear flags depending on the lease state being READ.
-		 * HANDLE caching flag should be added when the client starts
-		 * to defer closing remote file handles with HANDLE leases.
-		 */
-		if (lease_state & SMB2_LEASE_READ_CACHING_HE)
-			set_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
-				&cinode->flags);
-		else
-			clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
-				  &cinode->flags);
+		cfile->oplock_epoch = le16_to_cpu(rsp->Epoch);
+		cfile->oplock_level = lease_state;
 
 		cifs_queue_oplock_break(cfile);
 		kfree(lw);
@@ -538,7 +529,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
 
 		cifs_dbg(FYI, "found in the pending open list\n");
 		cifs_dbg(FYI, "lease key match, lease break 0x%x\n",
-			 le32_to_cpu(rsp->NewLeaseState));
+			 lease_state);
 
 		open->oplock = lease_state;
 	}
@@ -650,18 +641,9 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 				set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK,
 					&cinode->flags);
 
-				/*
-				 * Set flag if the server downgrades the oplock
-				 * to L2 else clear.
-				 */
-				if (rsp->OplockLevel)
-					set_bit(
-					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
-					   &cinode->flags);
-				else
-					clear_bit(
-					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
-					   &cinode->flags);
+				cfile->oplock_epoch = 0;
+				cfile->oplock_level = rsp->OplockLevel;
+
 				spin_unlock(&cfile->file_info_lock);
 
 				cifs_queue_oplock_break(cfile);
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 951c444d83e7..d2cfba90d9f8 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -652,7 +652,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 		return rc;
 	}
 
-	len = sizeof(ea) + ea_name_len + ea_value_len + 1;
+	len = sizeof(*ea) + ea_name_len + ea_value_len + 1;
 	ea = kzalloc(len, GFP_KERNEL);
 	if (ea == NULL) {
 		SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
@@ -1755,6 +1755,12 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	inode = d_inode(cfile->dentry);
 	cifsi = CIFS_I(inode);
 
+	/*
+	 * We zero the range through ioctl, so we need remove the page caches
+	 * first, otherwise the data may be inconsistent with the server.
+	 */
+	truncate_pagecache_range(inode, offset, offset + len - 1);
+
 	/* if file not oplocked can't be sure whether asking to extend size */
 	if (!CIFS_CACHE_READ(cifsi))
 		if (keep_size == false) {
@@ -1824,6 +1830,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 		return rc;
 	}
 
+	/*
+	 * We implement the punch hole through ioctl, so we need remove the page
+	 * caches first, otherwise the data may be inconsistent with the server.
+	 */
+	truncate_pagecache_range(inode, offset, offset + len - 1);
+
 	cifs_dbg(FYI, "offset %lld len %lld", offset, len);
 
 	fsctl_buf.FileOffset = cpu_to_le64(offset);
@@ -1923,22 +1935,38 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode,
 
 static void
 smb2_downgrade_oplock(struct TCP_Server_Info *server,
-			struct cifsInodeInfo *cinode, bool set_level2)
+		      struct cifsInodeInfo *cinode, __u32 oplock,
+		      unsigned int epoch, bool *purge_cache)
 {
-	if (set_level2)
-		server->ops->set_oplock_level(cinode, SMB2_OPLOCK_LEVEL_II,
-						0, NULL);
-	else
-		server->ops->set_oplock_level(cinode, 0, 0, NULL);
+	server->ops->set_oplock_level(cinode, oplock, 0, NULL);
 }
 
 static void
-smb21_downgrade_oplock(struct TCP_Server_Info *server,
-		       struct cifsInodeInfo *cinode, bool set_level2)
+smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
+		       unsigned int epoch, bool *purge_cache);
+
+static void
+smb3_downgrade_oplock(struct TCP_Server_Info *server,
+		       struct cifsInodeInfo *cinode, __u32 oplock,
+		       unsigned int epoch, bool *purge_cache)
 {
-	server->ops->set_oplock_level(cinode,
-				      set_level2 ? SMB2_LEASE_READ_CACHING_HE :
-				      0, 0, NULL);
+	unsigned int old_state = cinode->oplock;
+	unsigned int old_epoch = cinode->epoch;
+	unsigned int new_state;
+
+	if (epoch > old_epoch) {
+		smb21_set_oplock_level(cinode, oplock, 0, NULL);
+		cinode->epoch = epoch;
+	}
+
+	new_state = cinode->oplock;
+	*purge_cache = false;
+
+	if ((old_state & CIFS_CACHE_READ_FLG) != 0 &&
+	    (new_state & CIFS_CACHE_READ_FLG) == 0)
+		*purge_cache = true;
+	else if (old_state == new_state && (epoch - old_epoch > 1))
+		*purge_cache = true;
 }
 
 static void
@@ -2941,7 +2969,7 @@ struct smb_version_operations smb21_operations = {
 	.print_stats = smb2_print_stats,
 	.is_oplock_break = smb2_is_valid_oplock_break,
 	.handle_cancelled_mid = smb2_handle_cancelled_mid,
-	.downgrade_oplock = smb21_downgrade_oplock,
+	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
 	.negotiate_wsize = smb2_negotiate_wsize,
@@ -3036,7 +3064,7 @@ struct smb_version_operations smb30_operations = {
 	.dump_share_caps = smb2_dump_share_caps,
 	.is_oplock_break = smb2_is_valid_oplock_break,
 	.handle_cancelled_mid = smb2_handle_cancelled_mid,
-	.downgrade_oplock = smb21_downgrade_oplock,
+	.downgrade_oplock = smb3_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
 	.negotiate_wsize = smb2_negotiate_wsize,
@@ -3141,7 +3169,7 @@ struct smb_version_operations smb311_operations = {
 	.dump_share_caps = smb2_dump_share_caps,
 	.is_oplock_break = smb2_is_valid_oplock_break,
 	.handle_cancelled_mid = smb2_handle_cancelled_mid,
-	.downgrade_oplock = smb21_downgrade_oplock,
+	.downgrade_oplock = smb3_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
 	.negotiate_wsize = smb2_negotiate_wsize,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 1c87a429ce72..2097b5fd51ba 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -942,6 +942,8 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
 	spnego_key = cifs_get_spnego_key(ses);
 	if (IS_ERR(spnego_key)) {
 		rc = PTR_ERR(spnego_key);
+		if (rc == -ENOKEY)
+			cifs_dbg(VFS, "Verify user has a krb5 ticket and keyutils is installed\n");
 		spnego_key = NULL;
 		goto out;
 	}
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index bad458a2b579..f8baa54c8300 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -1046,7 +1046,7 @@ struct smb2_oplock_break {
 struct smb2_lease_break {
 	struct smb2_hdr hdr;
 	__le16 StructureSize; /* Must be 44 */
-	__le16 Reserved;
+	__le16 Epoch;
 	__le32 Flags;
 	__u8   LeaseKey[16];
 	__le32 CurrentLeaseState;
diff --git a/fs/dcache.c b/fs/dcache.c
index 9ac1290ae44f..c4fe6f8db002 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1217,7 +1217,7 @@ enum d_walk_ret {
  *
  * The @enter() and @finish() callbacks are called with d_lock held.
  */
-static void d_walk(struct dentry *parent, void *data,
+void d_walk(struct dentry *parent, void *data,
 		   enum d_walk_ret (*enter)(void *, struct dentry *),
 		   void (*finish)(void *))
 {
@@ -1325,6 +1325,7 @@ rename_retry:
 	seq = 1;
 	goto again;
 }
+EXPORT_SYMBOL_GPL(d_walk);
 
 struct check_mount {
 	struct vfsmount *mnt;
@@ -2950,6 +2951,7 @@ void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
 
 	write_sequnlock(&rename_lock);
 }
+EXPORT_SYMBOL_GPL(d_exchange);
 
 /**
  * d_ancestor - search for an ancestor
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index 748e8d59e611..cb287df13a7a 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -99,7 +99,6 @@ do { \
                __LINE__, __FILE__, #x, jiffies); \
     {do} \
     printk("\n"); \
-    BUG(); \
     panic("DLM:  Record message above and reboot.\n"); \
   } \
 }
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 9c8c9a09b4a6..7a6b0327ceb0 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -633,6 +633,9 @@ static int new_lockspace(const char *name, const char *cluster,
 	wait_event(ls->ls_recover_lock_wait,
 		   test_bit(LSFL_RECOVER_LOCK, &ls->ls_flags));
 
+	/* let kobject handle freeing of ls if there's an error */
+	do_unreg = 1;
+
 	ls->ls_kobj.kset = dlm_kset;
 	error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL,
 				     "%s", ls->ls_name);
@@ -640,9 +643,6 @@ static int new_lockspace(const char *name, const char *cluster,
 		goto out_recoverd;
 	kobject_uevent(&ls->ls_kobj, KOBJ_ADD);
 
-	/* let kobject handle freeing of ls if there's an error */
-	do_unreg = 1;
-
 	/* This uevent triggers dlm_controld in userspace to add us to the
 	   group of nodes that are members of this lockspace (managed by the
 	   cluster infrastructure.)  Once it's done that, it tells us who the
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index c291bf61afb9..c9feb119aa47 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -223,8 +223,7 @@ struct eventpoll {
 	struct file *file;
 
 	/* used to optimize loop detection check */
-	int visited;
-	struct list_head visited_list_link;
+	u64 gen;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	/* used to track busy poll napi_id */
@@ -273,6 +272,8 @@ static long max_user_watches __read_mostly;
  */
 static DEFINE_MUTEX(epmutex);
 
+static u64 loop_check_gen = 0;
+
 /* Used to check for epoll file descriptor inclusion loops */
 static struct nested_calls poll_loop_ncalls;
 
@@ -288,9 +289,6 @@ static struct kmem_cache *epi_cache __read_mostly;
 /* Slab cache used to allocate "struct eppoll_entry" */
 static struct kmem_cache *pwq_cache __read_mostly;
 
-/* Visited nodes during ep_loop_check(), so we can unset them when we finish */
-static LIST_HEAD(visited_list);
-
 /*
  * List of files with newly added links, where we may need to limit the number
  * of emanating paths. Protected by the epmutex.
@@ -1391,7 +1389,7 @@ static int reverse_path_check(void)
 
 static int ep_create_wakeup_source(struct epitem *epi)
 {
-	const char *name;
+	struct name_snapshot n;
 	struct wakeup_source *ws;
 
 	if (!epi->ep->ws) {
@@ -1400,8 +1398,9 @@ static int ep_create_wakeup_source(struct epitem *epi)
 			return -ENOMEM;
 	}
 
-	name = epi->ffd.file->f_path.dentry->d_name.name;
-	ws = wakeup_source_register(name);
+	take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry);
+	ws = wakeup_source_register(n.name);
+	release_dentry_name_snapshot(&n);
 
 	if (!ws)
 		return -ENOMEM;
@@ -1461,6 +1460,22 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 		RCU_INIT_POINTER(epi->ws, NULL);
 	}
 
+	/* Add the current item to the list of active epoll hook for this file */
+	spin_lock(&tfile->f_lock);
+	list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links);
+	spin_unlock(&tfile->f_lock);
+
+	/*
+	 * Add the current item to the RB tree. All RB tree operations are
+	 * protected by "mtx", and ep_insert() is called with "mtx" held.
+	 */
+	ep_rbtree_insert(ep, epi);
+
+	/* now check if we've created too many backpaths */
+	error = -EINVAL;
+	if (full_check && reverse_path_check())
+		goto error_remove_epi;
+
 	/* Initialize the poll table using the queue callback */
 	epq.epi = epi;
 	init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);
@@ -1483,22 +1498,6 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 	if (epi->nwait < 0)
 		goto error_unregister;
 
-	/* Add the current item to the list of active epoll hook for this file */
-	spin_lock(&tfile->f_lock);
-	list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links);
-	spin_unlock(&tfile->f_lock);
-
-	/*
-	 * Add the current item to the RB tree. All RB tree operations are
-	 * protected by "mtx", and ep_insert() is called with "mtx" held.
-	 */
-	ep_rbtree_insert(ep, epi);
-
-	/* now check if we've created too many backpaths */
-	error = -EINVAL;
-	if (full_check && reverse_path_check())
-		goto error_remove_epi;
-
 	/* We have to drop the new item inside our item list to keep track of it */
 	spin_lock_irqsave(&ep->lock, flags);
 
@@ -1527,6 +1526,8 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 
 	return 0;
 
+error_unregister:
+	ep_unregister_pollwait(ep, epi);
 error_remove_epi:
 	spin_lock(&tfile->f_lock);
 	list_del_rcu(&epi->fllink);
@@ -1534,9 +1535,6 @@ error_remove_epi:
 
 	rb_erase_cached(&epi->rbn, &ep->rbr);
 
-error_unregister:
-	ep_unregister_pollwait(ep, epi);
-
 	/*
 	 * We need to do this because an event could have been arrived on some
 	 * allocated wait queue. Note that we don't care about the ep->ovflist
@@ -1878,13 +1876,12 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
 	struct epitem *epi;
 
 	mutex_lock_nested(&ep->mtx, call_nests + 1);
-	ep->visited = 1;
-	list_add(&ep->visited_list_link, &visited_list);
+	ep->gen = loop_check_gen;
 	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		if (unlikely(is_file_epoll(epi->ffd.file))) {
 			ep_tovisit = epi->ffd.file->private_data;
-			if (ep_tovisit->visited)
+			if (ep_tovisit->gen == loop_check_gen)
 				continue;
 			error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
 					ep_loop_check_proc, epi->ffd.file,
@@ -1900,9 +1897,11 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
 			 * not already there, and calling reverse_path_check()
 			 * during ep_insert().
 			 */
-			if (list_empty(&epi->ffd.file->f_tfile_llink))
-				list_add(&epi->ffd.file->f_tfile_llink,
-					 &tfile_check_list);
+			if (list_empty(&epi->ffd.file->f_tfile_llink)) {
+				if (get_file_rcu(epi->ffd.file))
+					list_add(&epi->ffd.file->f_tfile_llink,
+						 &tfile_check_list);
+			}
 		}
 	}
 	mutex_unlock(&ep->mtx);
@@ -1923,18 +1922,8 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
  */
 static int ep_loop_check(struct eventpoll *ep, struct file *file)
 {
-	int ret;
-	struct eventpoll *ep_cur, *ep_next;
-
-	ret = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+	return ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
 			      ep_loop_check_proc, file, ep, current);
-	/* clear visited list */
-	list_for_each_entry_safe(ep_cur, ep_next, &visited_list,
-							visited_list_link) {
-		ep_cur->visited = 0;
-		list_del(&ep_cur->visited_list_link);
-	}
-	return ret;
 }
 
 static void clear_tfile_check_list(void)
@@ -1946,6 +1935,7 @@ static void clear_tfile_check_list(void)
 		file = list_first_entry(&tfile_check_list, struct file,
 					f_tfile_llink);
 		list_del_init(&file->f_tfile_llink);
+		fput(file);
 	}
 	INIT_LIST_HEAD(&tfile_check_list);
 }
@@ -2090,19 +2080,20 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	mutex_lock_nested(&ep->mtx, 0);
 	if (op == EPOLL_CTL_ADD) {
 		if (!list_empty(&f.file->f_ep_links) ||
+				ep->gen == loop_check_gen ||
 						is_file_epoll(tf.file)) {
 			full_check = 1;
 			mutex_unlock(&ep->mtx);
 			mutex_lock(&epmutex);
 			if (is_file_epoll(tf.file)) {
 				error = -ELOOP;
-				if (ep_loop_check(ep, tf.file) != 0) {
-					clear_tfile_check_list();
+				if (ep_loop_check(ep, tf.file) != 0)
 					goto error_tgt_fput;
-				}
-			} else
+			} else {
+				get_file(tf.file);
 				list_add(&tf.file->f_tfile_llink,
 							&tfile_check_list);
+			}
 			mutex_lock_nested(&ep->mtx, 0);
 			if (is_file_epoll(tf.file)) {
 				tep = tf.file->private_data;
@@ -2126,8 +2117,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 			error = ep_insert(ep, &epds, tf.file, fd, full_check);
 		} else
 			error = -EEXIST;
-		if (full_check)
-			clear_tfile_check_list();
 		break;
 	case EPOLL_CTL_DEL:
 		if (epi)
@@ -2150,8 +2139,11 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	mutex_unlock(&ep->mtx);
 
 error_tgt_fput:
-	if (full_check)
+	if (full_check) {
+		clear_tfile_check_list();
+		loop_check_gen++;
 		mutex_unlock(&epmutex);
+	}
 
 	fdput(tf);
 error_fput:
diff --git a/fs/exec.c b/fs/exec.c
index 92fd21f0b0ff..b38d7277b7de 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -109,6 +109,7 @@ bool path_noexec(const struct path *path)
 	return (path->mnt->mnt_flags & MNT_NOEXEC) ||
 	       (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC);
 }
+EXPORT_SYMBOL_GPL(path_noexec);
 
 #ifdef CONFIG_USELIB
 /*
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index a1fc3dabca41..6d5fce776d8e 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -80,6 +80,7 @@ static void ext2_release_inode(struct super_block *sb, int group, int dir)
 	if (dir)
 		le16_add_cpu(&desc->bg_used_dirs_count, -1);
 	spin_unlock(sb_bgl_lock(EXT2_SB(sb), group));
+	percpu_counter_inc(&EXT2_SB(sb)->s_freeinodes_counter);
 	if (dir)
 		percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter);
 	mark_buffer_dirty(bh);
@@ -531,7 +532,7 @@ got:
 		goto fail;
 	}
 
-	percpu_counter_add(&sbi->s_freeinodes_counter, -1);
+	percpu_counter_dec(&sbi->s_freeinodes_counter);
 	if (S_ISDIR(mode))
 		percpu_counter_inc(&sbi->s_dirs_counter);
 
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index a284fb28944b..63291c265aa0 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -169,10 +169,13 @@ struct ext4_ext_path {
 	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
 #define EXT_LAST_INDEX(__hdr__) \
 	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
-#define EXT_MAX_EXTENT(__hdr__) \
-	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+#define EXT_MAX_EXTENT(__hdr__)	\
+	((le16_to_cpu((__hdr__)->eh_max)) ? \
+	((EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \
+					: 0)
 #define EXT_MAX_INDEX(__hdr__) \
-	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+	((le16_to_cpu((__hdr__)->eh_max)) ? \
+	((EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) : 0)
 
 static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode)
 {
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 4f9eb4b61549..fc6bc261f7ac 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2917,7 +2917,7 @@ again:
 			 * in use to avoid freeing it when removing blocks.
 			 */
 			if (sbi->s_cluster_ratio > 1) {
-				pblk = ext4_ext_pblock(ex) + end - ee_block + 2;
+				pblk = ext4_ext_pblock(ex) + end - ee_block + 1;
 				partial_cluster =
 					-(long long) EXT4_B2C(sbi, pblk);
 			}
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 5508baa11bb6..8a28d47bd502 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -44,30 +44,28 @@
  */
 static int ext4_sync_parent(struct inode *inode)
 {
-	struct dentry *dentry = NULL;
-	struct inode *next;
+	struct dentry *dentry, *next;
 	int ret = 0;
 
 	if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
 		return 0;
-	inode = igrab(inode);
+	dentry = d_find_any_alias(inode);
+	if (!dentry)
+		return 0;
 	while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
 		ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
-		dentry = d_find_any_alias(inode);
-		if (!dentry)
-			break;
-		next = igrab(d_inode(dentry->d_parent));
+
+		next = dget_parent(dentry);
 		dput(dentry);
-		if (!next)
-			break;
-		iput(inode);
-		inode = next;
+		dentry = next;
+		inode = dentry->d_inode;
+
 		/*
 		 * The directory inode may have gone through rmdir by now. But
 		 * the inode itself and its blocks are still allocated (we hold
-		 * a reference to the inode so it didn't go through
-		 * ext4_evict_inode()) and so we are safe to flush metadata
-		 * blocks and the inode.
+		 * a reference to the inode via its dentry), so it didn't go
+		 * through ext4_evict_inode()) and so we are safe to flush
+		 * metadata blocks and the inode.
 		 */
 		ret = sync_mapping_buffers(inode->i_mapping);
 		if (ret)
@@ -76,7 +74,7 @@ static int ext4_sync_parent(struct inode *inode)
 		if (ret)
 			break;
 	}
-	iput(inode);
+	dput(dentry);
 	return ret;
 }
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5f03a4fabeaa..34da8d341c0c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3794,6 +3794,11 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = mapping->host;
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
+	loff_t offset = iocb->ki_pos;
+	loff_t size = i_size_read(inode);
+
+	if (offset >= size)
+		return 0;
 
 	/*
 	 * Shared inode_lock is enough for us - it protects against concurrent
@@ -5174,7 +5179,7 @@ static int ext4_do_update_inode(handle_t *handle,
 		raw_inode->i_file_acl_high =
 			cpu_to_le16(ei->i_file_acl >> 32);
 	raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
-	if (ei->i_disksize != ext4_isize(inode->i_sb, raw_inode)) {
+	if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode)) {
 		ext4_isize_set(raw_inode, ei->i_disksize);
 		need_datasync = 1;
 	}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 161099f39ab9..3f999053457b 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1308,8 +1308,8 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
 		    ext4_match(fname, de)) {
 			/* found a match - just to be sure, do
 			 * a full check */
-			if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data,
-						 bh->b_size, offset))
+			if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf,
+						 buf_size, offset))
 				return -1;
 			*res_dir = de;
 			return 1;
@@ -1741,7 +1741,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 			     blocksize, hinfo, map);
 	map -= count;
 	dx_sort_map(map, count);
-	/* Split the existing block in the middle, size-wise */
+	/* Ensure that neither split block is over half full */
 	size = 0;
 	move = 0;
 	for (i = count-1; i >= 0; i--) {
@@ -1751,8 +1751,18 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 		size += map[i].size;
 		move++;
 	}
-	/* map index at which we will split */
-	split = count - move;
+	/*
+	 * map index at which we will split
+	 *
+	 * If the sum of active entries didn't exceed half the block size, just
+	 * split it in half by count; each resulting block will have at least
+	 * half the space free.
+	 */
+	if (i > 0)
+		split = count - move;
+	else
+		split = count/2;
+
 	hash2 = map[split].hash;
 	continued = hash2 == map[split - 1].hash;
 	dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
@@ -2353,7 +2363,7 @@ int ext4_generic_delete_entry(handle_t *handle,
 	de = (struct ext4_dir_entry_2 *)entry_buf;
 	while (i < buf_size - csum_size) {
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
-					 bh->b_data, bh->b_size, i))
+					 entry_buf, buf_size, i))
 			return -EFSCORRUPTED;
 		if (de == de_del)  {
 			if (pde)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index ffc985d78137..634c822d1dc9 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -63,10 +63,10 @@ static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
 static int ext4_show_options(struct seq_file *seq, struct dentry *root);
 static int ext4_commit_super(struct super_block *sb, int sync);
-static void ext4_mark_recovery_complete(struct super_block *sb,
+static int ext4_mark_recovery_complete(struct super_block *sb,
 					struct ext4_super_block *es);
-static void ext4_clear_journal_err(struct super_block *sb,
-				   struct ext4_super_block *es);
+static int ext4_clear_journal_err(struct super_block *sb,
+				  struct ext4_super_block *es);
 static int ext4_sync_fs(struct super_block *sb, int wait);
 static int ext4_remount(struct super_block *sb, int *flags, char *data);
 static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
@@ -4458,7 +4458,9 @@ no_journal:
 	EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
 	if (needs_recovery) {
 		ext4_msg(sb, KERN_INFO, "recovery complete");
-		ext4_mark_recovery_complete(sb, es);
+		err = ext4_mark_recovery_complete(sb, es);
+		if (err)
+			goto failed_mount8;
 	}
 	if (EXT4_SB(sb)->s_journal) {
 		if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
@@ -4501,10 +4503,8 @@ cantfind_ext4:
 		ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
 	goto failed_mount;
 
-#ifdef CONFIG_QUOTA
 failed_mount8:
 	ext4_unregister_sysfs(sb);
-#endif
 failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
@@ -4640,7 +4640,8 @@ static journal_t *ext4_get_journal(struct super_block *sb,
 	struct inode *journal_inode;
 	journal_t *journal;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return NULL;
 
 	journal_inode = ext4_get_journal_inode(sb, journal_inum);
 	if (!journal_inode)
@@ -4670,7 +4671,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 	struct ext4_super_block *es;
 	struct block_device *bdev;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return NULL;
 
 	bdev = ext4_blkdev_get(j_dev, sb);
 	if (bdev == NULL)
@@ -4762,7 +4764,8 @@ static int ext4_load_journal(struct super_block *sb,
 	int err = 0;
 	int really_read_only;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return -EFSCORRUPTED;
 
 	if (journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
@@ -4831,7 +4834,12 @@ static int ext4_load_journal(struct super_block *sb,
 	}
 
 	EXT4_SB(sb)->s_journal = journal;
-	ext4_clear_journal_err(sb, es);
+	err = ext4_clear_journal_err(sb, es);
+	if (err) {
+		EXT4_SB(sb)->s_journal = NULL;
+		jbd2_journal_destroy(journal);
+		return err;
+	}
 
 	if (!really_read_only && journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
@@ -4854,13 +4862,6 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 		return error;
 
 	/*
-	 * The superblock bh should be mapped, but it might not be if the
-	 * device was hot-removed. Not much we can do but fail the I/O.
-	 */
-	if (!buffer_mapped(sbh))
-		return error;
-
-	/*
 	 * If the file system is mounted read-only, don't update the
 	 * superblock write time.  This avoids updating the superblock
 	 * write time when we are mounting the root file system
@@ -4930,26 +4931,32 @@ static int ext4_commit_super(struct super_block *sb, int sync)
  * remounting) the filesystem readonly, then we will end up with a
  * consistent fs on disk.  Record that fact.
  */
-static void ext4_mark_recovery_complete(struct super_block *sb,
-					struct ext4_super_block *es)
+static int ext4_mark_recovery_complete(struct super_block *sb,
+				       struct ext4_super_block *es)
 {
+	int err;
 	journal_t *journal = EXT4_SB(sb)->s_journal;
 
 	if (!ext4_has_feature_journal(sb)) {
-		BUG_ON(journal != NULL);
-		return;
+		if (journal != NULL) {
+			ext4_error(sb, "Journal got removed while the fs was "
+				   "mounted!");
+			return -EFSCORRUPTED;
+		}
+		return 0;
 	}
 	jbd2_journal_lock_updates(journal);
-	if (jbd2_journal_flush(journal) < 0)
+	err = jbd2_journal_flush(journal);
+	if (err < 0)
 		goto out;
 
 	if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) {
 		ext4_clear_feature_journal_needs_recovery(sb);
 		ext4_commit_super(sb, 1);
 	}
-
 out:
 	jbd2_journal_unlock_updates(journal);
+	return err;
 }
 
 /*
@@ -4957,14 +4964,17 @@ out:
  * has recorded an error from a previous lifetime, move that error to the
  * main filesystem now.
  */
-static void ext4_clear_journal_err(struct super_block *sb,
+static int ext4_clear_journal_err(struct super_block *sb,
 				   struct ext4_super_block *es)
 {
 	journal_t *journal;
 	int j_errno;
 	const char *errstr;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (!ext4_has_feature_journal(sb)) {
+		ext4_error(sb, "Journal got removed while the fs was mounted!");
+		return -EFSCORRUPTED;
+	}
 
 	journal = EXT4_SB(sb)->s_journal;
 
@@ -4989,6 +4999,7 @@ static void ext4_clear_journal_err(struct super_block *sb,
 		jbd2_journal_clear_err(journal);
 		jbd2_journal_update_sb_errno(journal);
 	}
+	return 0;
 }
 
 /*
@@ -5268,8 +5279,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			    (sbi->s_mount_state & EXT4_VALID_FS))
 				es->s_state = cpu_to_le16(sbi->s_mount_state);
 
-			if (sbi->s_journal)
+			if (sbi->s_journal) {
+				/*
+				 * We let remount-ro finish even if marking fs
+				 * as clean failed...
+				 */
 				ext4_mark_recovery_complete(sb, es);
+			}
 			if (sbi->s_mmp_tsk)
 				kthread_stop(sbi->s_mmp_tsk);
 		} else {
@@ -5317,8 +5333,11 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			 * been changed by e2fsck since we originally mounted
 			 * the partition.)
 			 */
-			if (sbi->s_journal)
-				ext4_clear_journal_err(sb, es);
+			if (sbi->s_journal) {
+				err = ext4_clear_journal_err(sb, es);
+				if (err)
+					goto restore_opts;
+			}
 			sbi->s_mount_state = le16_to_cpu(es->s_state);
 			if (!ext4_setup_super(sb, es, 0))
 				sb->s_flags &= ~MS_RDONLY;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index b0873b89dc87..823b01f6b0f0 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1823,8 +1823,11 @@ ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i,
 	if (EXT4_I(inode)->i_file_acl) {
 		/* The inode already has an extended attribute block. */
 		bs->bh = ext4_sb_bread(sb, EXT4_I(inode)->i_file_acl, REQ_PRIO);
-		if (IS_ERR(bs->bh))
-			return PTR_ERR(bs->bh);
+		if (IS_ERR(bs->bh)) {
+			error = PTR_ERR(bs->bh);
+			bs->bh = NULL;
+			return error;
+		}
 		ea_bdebug(bs->bh, "b_count=%d, refcount=%d",
 			atomic_read(&(bs->bh->b_count)),
 			le32_to_cpu(BHDR(bs->bh)->h_refcount));
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 4abefd841b6c..ff519f7a8784 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -817,6 +817,17 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 		de_name.name = d->filename[bit_pos];
 		de_name.len = le16_to_cpu(de->name_len);
 
+		/* check memory boundary before moving forward */
+		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+		if (unlikely(bit_pos > d->max ||
+				le16_to_cpu(de->name_len) > F2FS_NAME_LEN)) {
+			f2fs_msg(F2FS_I_SB(d->inode)->sb, KERN_WARNING,
+				"%s: corrupted namelen=%d, run fsck to fix.",
+				__func__, le16_to_cpu(de->name_len));
+			set_sbi_flag(F2FS_I_SB(d->inode)->sb->s_fs_info, SBI_NEED_FSCK);
+			return -EINVAL;
+		}
+
 		if (f2fs_encrypted_inode(d->inode)) {
 			int save_len = fstr->len;
 			int err;
@@ -835,7 +846,6 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 					le32_to_cpu(de->ino), d_type))
 			return 1;
 
-		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
 		ctx->pos = start_pos + bit_pos;
 	}
 	return 0;
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index e7b8e2b35e22..f8006f62c546 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -2011,6 +2011,9 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 	if (unlikely(nid >= nm_i->max_nid))
 		nid = 0;
 
+	if (unlikely(nid % NAT_ENTRY_PER_BLOCK))
+		nid = NAT_BLOCK_OFFSET(nid) * NAT_ENTRY_PER_BLOCK;
+
 	/* Enough entries */
 	if (nm_i->nid_cnt[FREE_NID_LIST] >= NAT_ENTRY_PER_BLOCK)
 		return;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 2d021a33914a..990339c538b0 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -782,6 +782,9 @@ static void f2fs_put_super(struct super_block *sb)
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	int i;
 
+	/* unregister procfs/sysfs entries in advance to avoid race case */
+	f2fs_unregister_sysfs(sbi);
+
 	f2fs_quota_off_umount(sb);
 
 	/* prevent remaining shrinker jobs */
@@ -834,8 +837,6 @@ static void f2fs_put_super(struct super_block *sb)
 
 	kfree(sbi->ckpt);
 
-	f2fs_unregister_sysfs(sbi);
-
 	sb->s_fs_info = NULL;
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
@@ -918,7 +919,8 @@ static int f2fs_statfs_project(struct super_block *sb,
 		limit >>= sb->s_blocksize_bits;
 
 	if (limit && buf->f_blocks > limit) {
-		curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
+		curblock = (dquot->dq_dqb.dqb_curspace +
+			    dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
 		buf->f_blocks = limit;
 		buf->f_bfree = buf->f_bavail =
 			(buf->f_blocks > curblock) ?
diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig
index 3ff1772f612e..ca5c78bda750 100644
--- a/fs/fat/Kconfig
+++ b/fs/fat/Kconfig
@@ -74,6 +74,27 @@ config VFAT_FS
 	  To compile this as a module, choose M here: the module will be called
 	  vfat.
 
+config VFAT_FS_NO_DUALNAMES
+	bool "disable VFAT dual names support (patent workaround)"
+	depends on VFAT_FS
+	help
+	  This option disables support for dual filenames on VFAT filesystems.
+	  If this option is enabled then file creation will either put
+	  a short (8.3) name or a long name on the file, but never both.
+	  The field where a shortname would normally go is filled with
+	  invalid characters such that it cannot be considered a valid
+	  short filename.
+
+	  That means that long filenames created with this option
+	  disabled will not be accessible at all to operating systems
+	  that do not understand the FAT long filename extensions.
+
+	  Users considering disabling this option should consider the
+	  implications of any patents that may exist on dual filenames
+	  in VFAT.
+
+	  If unsure, say N
+
 config FAT_DEFAULT_CODEPAGE
 	int "Default codepage for FAT"
 	depends on MSDOS_FS || VFAT_FS
@@ -100,6 +121,17 @@ config FAT_DEFAULT_IOCHARSET
 	  Enable any character sets you need in File Systems/Native Language
 	  Support.
 
+config VFAT_NO_CREATE_WITH_LONGNAMES
+	bool "Disable creating files with long names"
+	depends on VFAT_FS
+	default n
+	help
+	  Set this to disable support for creating files or directories with
+	  names longer than 8.3 (the original DOS maximum file name length)
+	  e.g. naming a file FILE1234.TXT would be allowed but creating or
+	  renaming a file to FILE12345.TXT or FILE1234.TEXT would not
+	  be permitted.  Reading files with long file names is still permitted.
+
 config FAT_DEFAULT_UTF8
 	bool "Enable FAT UTF-8 option by default"
 	depends on VFAT_FS
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 971e369517a7..0bbe89a7ebc3 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -368,7 +368,8 @@ static int fat_parse_short(struct super_block *sb,
 		dotoffset = 1;
 	}
 
-	memcpy(work, de->name, sizeof(work));
+	memcpy(work, de->name, sizeof(de->name));
+
 	/* see namei.c, msdos_format_name */
 	if (work[0] == 0x05)
 		work[0] = 0xE5;
@@ -498,6 +499,13 @@ parse_record:
 				goto end_of_dir;
 		}
 
+		/*
+		 * The FAT_NO_83NAME flag is used to mark files
+		 * created with no 8.3 short name
+		 */
+		if (de->lcase & FAT_NO_83NAME)
+			goto compare_longname;
+
 		/* Never prepend '.' to hidden files here.
 		 * That is done only for msdos mounts (and only when
 		 * 'dotsOK=yes'); if we are executing here, it is in the
@@ -511,6 +519,7 @@ parse_record:
 		if (fat_name_match(sbi, name, name_len, bufname, len))
 			goto found;
 
+compare_longname:
 		if (nr_slots) {
 			void *longname = unicode + FAT_MAX_UNI_CHARS;
 			int size = PATH_MAX - FAT_MAX_UNI_SIZE;
@@ -602,6 +611,8 @@ parse_record:
 		if (de->attr != ATTR_EXT && IS_FREE(de->name))
 			goto record_end;
 	} else {
+		if (de->lcase & FAT_NO_83NAME)
+			goto record_end;
 		if ((de->attr & ATTR_VOLUME) || IS_FREE(de->name))
 			goto record_end;
 	}
@@ -960,6 +971,10 @@ int fat_scan(struct inode *dir, const unsigned char *name,
 	sinfo->bh = NULL;
 	while (fat_get_short_entry(dir, &sinfo->slot_off, &sinfo->bh,
 				   &sinfo->de) >= 0) {
+		/* skip files marked as having no 8.3 short name  */
+		if (sinfo->de->lcase & FAT_NO_83NAME)
+			continue;
+
 		if (!strncmp(sinfo->de->name, name, MSDOS_NAME)) {
 			sinfo->slot_off -= sizeof(*sinfo->de);
 			sinfo->nr_slots = 1;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 1df023c4c2cc..c41393e30a04 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1512,6 +1512,12 @@ static int fat_read_bpb(struct super_block *sb, struct fat_boot_sector *b,
 		goto out;
 	}
 
+	if (bpb->fat_fat_length == 0 && bpb->fat32_length == 0) {
+		if (!silent)
+			fat_msg(sb, KERN_ERR, "bogus number of FAT sectors");
+		goto out;
+	}
+
 	error = 0;
 
 out:
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 02c066663a3a..25da90c05d82 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -20,7 +20,7 @@
 #include <linux/slab.h>
 #include <linux/namei.h>
 #include <linux/kernel.h>
-
+#include <linux/random.h>
 #include "fat.h"
 
 static inline unsigned long vfat_d_version(struct dentry *dentry)
@@ -335,6 +335,17 @@ static int vfat_create_shortname(struct inode *dir, struct nls_table *nls,
 	int sz = 0, extlen, baselen, i, numtail_baselen, numtail2_baselen;
 	int is_shortname;
 	struct shortname_info base_info, ext_info;
+	unsigned opts_shortname = opts->shortname;
+
+#ifdef CONFIG_VFAT_FS_NO_DUALNAMES
+	/*
+	 * When we do not have dualnames, we want to maximise the
+	 * chance that a file will be able to be represented with just
+	 * a 8.3 entry. We can do that by using the WINNT case
+	 * handling extensions to FAT.
+	 */
+	opts_shortname = VFAT_SFN_CREATE_WINNT;
+#endif
 
 	is_shortname = 1;
 	INIT_SHORTNAME_INFO(&base_info);
@@ -443,13 +454,22 @@ static int vfat_create_shortname(struct inode *dir, struct nls_table *nls,
 	memcpy(name_res, base, baselen);
 	memcpy(name_res + 8, ext, extlen);
 	*lcase = 0;
+
+#ifdef CONFIG_VFAT_NO_CREATE_WITH_LONGNAMES
+	if (is_shortname == 0)
+		return -ENAMETOOLONG;
+	if (!base_info.valid || !ext_info.valid)
+		return -EINVAL;
+	opts_shortname = VFAT_SFN_CREATE_WINNT;
+#endif
+
 	if (is_shortname && base_info.valid && ext_info.valid) {
 		if (vfat_find_form(dir, name_res) == 0)
 			return -EEXIST;
 
-		if (opts->shortname & VFAT_SFN_CREATE_WIN95) {
+		if (opts_shortname & VFAT_SFN_CREATE_WIN95) {
 			return (base_info.upper && ext_info.upper);
-		} else if (opts->shortname & VFAT_SFN_CREATE_WINNT) {
+		} else if (opts_shortname & VFAT_SFN_CREATE_WINNT) {
 			if ((base_info.upper || base_info.lower) &&
 			    (ext_info.upper || ext_info.lower)) {
 				if (!base_info.upper && base_info.lower)
@@ -575,6 +595,66 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname,
 	return 0;
 }
 
+#ifdef CONFIG_VFAT_FS_NO_DUALNAMES
+/*
+ * This function creates a dummy 8.3 entry which is as compatible as
+ * possible with existing FAT devices, while not being a valid
+ * filename under windows or Linux
+ */
+static void vfat_build_dummy_83_buffer(struct inode *dir, char *msdos_name,
+				       int is_dir)
+{
+	/*
+	 * These characters are all invalid in 8.3 names, plus have
+	 * been shown to be harmless on all tested devices
+	 */
+	const char invalidchar[] = { 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x0B,
+				     0x0C, 0x0E, 0x0F, 0x10, 0x11, 0x12, 0x13,
+				     0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1A,
+				     0x1B, 0x1C, 0x1D, 0x1E, 0x1F, 0x22, 0x2a,
+				     0x3a, 0x3c, 0x3e, 0x3f, 0x5b, 0x5d, 0x7c };
+	int i, tilde_pos, slash_pos;
+	u32 rand_num = prandom_u32();
+
+	/* We need a '~' in the prefix to make Win98 happy. */
+	tilde_pos = rand_num % 8;
+	rand_num >>= 3;
+
+	/*
+	 * the '/' makes sure that even unpatched Linux systems can't
+	 * get at files by the 8.3 entry. Don't put in a / in
+	 * directories as it can cause problems with some
+	 * photo frames
+	 */
+	if (is_dir)
+		slash_pos = -1;
+	else {
+		slash_pos = (tilde_pos + 1 + rand_num % 7) % 8;
+		rand_num >>= 3;
+	}
+
+	/*
+	 * fill in the first 8 bytes with invalid characters. Note
+	 * that we need to be careful not to run out of randomness. We
+	 * leave the 3 byte extension in place as some cheap MP3
+	 * players need them.
+	 */
+	for (i = 0; i < 8; i++) {
+		if (i == tilde_pos)
+			msdos_name[i] = '~';
+		else if (i == slash_pos)
+			msdos_name[i] = '/';
+		else {
+			msdos_name[i] =
+				invalidchar[rand_num % sizeof(invalidchar)];
+			rand_num /= sizeof(invalidchar);
+			if (rand_num < sizeof(invalidchar))
+				rand_num = prandom_u32();
+		}
+	}
+}
+#endif
+
 static int vfat_build_slots(struct inode *dir, const unsigned char *name,
 			    int len, int is_dir, int cluster,
 			    struct timespec *ts,
@@ -582,15 +662,19 @@ static int vfat_build_slots(struct inode *dir, const unsigned char *name,
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(dir->i_sb);
 	struct fat_mount_options *opts = &sbi->options;
-	struct msdos_dir_slot *ps;
 	struct msdos_dir_entry *de;
-	unsigned char cksum, lcase;
+	unsigned char lcase;
 	unsigned char msdos_name[MSDOS_NAME];
 	wchar_t *uname;
 	__le16 time, date;
 	u8 time_cs;
-	int err, ulen, usize, i;
+	int err, ulen, usize;
+#ifndef CONFIG_VFAT_NO_CREATE_WITH_LONGNAMES
+	int i;
+	struct msdos_dir_slot *ps;
+	unsigned char cksum;
 	loff_t offset;
+#endif
 
 	*nr_slots = 0;
 
@@ -617,6 +701,16 @@ static int vfat_build_slots(struct inode *dir, const unsigned char *name,
 		goto shortname;
 	}
 
+#ifdef CONFIG_VFAT_FS_NO_DUALNAMES
+	printk_once(KERN_INFO
+		    "VFAT: not creating 8.3 short filenames for long names\n");
+	vfat_build_dummy_83_buffer(dir, msdos_name, is_dir);
+	lcase = FAT_NO_83NAME;
+#endif
+
+#ifdef CONFIG_VFAT_NO_CREATE_WITH_LONGNAMES
+	de = (struct msdos_dir_entry *)slots;
+#else
 	/* build the entry of long file name */
 	cksum = fat_checksum(msdos_name);
 
@@ -634,6 +728,7 @@ static int vfat_build_slots(struct inode *dir, const unsigned char *name,
 	}
 	slots[0].id |= 0x40;
 	de = (struct msdos_dir_entry *)ps;
+#endif
 
 shortname:
 	/* build the entry of 8.3 alias name */
@@ -1068,7 +1163,11 @@ static struct dentry *vfat_mount(struct file_system_type *fs_type,
 
 static struct file_system_type vfat_fs_type = {
 	.owner		= THIS_MODULE,
+#ifdef CONFIG_VFAT_NO_CREATE_WITH_LONGNAMES
+	.name		= "lfat",
+#else
 	.name		= "vfat",
+#endif
 	.mount		= vfat_mount,
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
@@ -1088,6 +1187,9 @@ static void __exit exit_vfat_fs(void)
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("VFAT filesystem support");
 MODULE_AUTHOR("Gordon Chaffee");
+#ifdef CONFIG_VFAT_NO_CREATE_WITH_LONGNAMES
+MODULE_ALIAS("lfat");
+#endif
 
 module_init(init_vfat_fs)
 module_exit(exit_vfat_fs)
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 0345a46b8856..e8c9dc38c2e1 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -32,7 +32,7 @@
 
 #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
 
-static int setfl(int fd, struct file * filp, unsigned long arg)
+int setfl(int fd, struct file * filp, unsigned long arg)
 {
 	struct inode * inode = file_inode(filp);
 	int error = 0;
@@ -63,6 +63,8 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 
 	if (filp->f_op->check_flags)
 		error = filp->f_op->check_flags(arg);
+	if (!error && filp->f_op->setfl)
+		error = filp->f_op->setfl(filp, arg);
 	if (error)
 		return error;
 
@@ -83,6 +85,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
  out:
 	return error;
 }
+EXPORT_SYMBOL_GPL(setfl);
 
 static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
                      int force)
diff --git a/fs/file_table.c b/fs/file_table.c
index 61517f57f8ef..c6bab39c1813 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -148,6 +148,7 @@ over:
 	}
 	return ERR_PTR(-ENFILE);
 }
+EXPORT_SYMBOL_GPL(get_empty_filp);
 
 /**
  * alloc_file - allocate and initialize a 'struct file'
@@ -258,6 +259,7 @@ void flush_delayed_fput(void)
 {
 	delayed_fput(NULL);
 }
+EXPORT_SYMBOL_GPL(flush_delayed_fput);
 
 static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
 
@@ -300,6 +302,7 @@ void __fput_sync(struct file *file)
 }
 
 EXPORT_SYMBOL(fput);
+EXPORT_SYMBOL_GPL(__fput_sync);
 
 void put_filp(struct file *file)
 {
@@ -308,6 +311,7 @@ void put_filp(struct file *file)
 		file_free(file);
 	}
 }
+EXPORT_SYMBOL_GPL(put_filp);
 
 void __init files_init(void)
 {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 6398bd8a066e..3dbb875ed790 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -45,7 +45,6 @@ struct wb_completion {
 struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
-	unsigned long *older_than_this;
 	enum writeback_sync_modes sync_mode;
 	unsigned int tagged_writepages:1;
 	unsigned int for_kupdate:1;
@@ -160,7 +159,9 @@ static void inode_io_list_del_locked(struct inode *inode,
 				     struct bdi_writeback *wb)
 {
 	assert_spin_locked(&wb->list_lock);
+	assert_spin_locked(&inode->i_lock);
 
+	inode->i_state &= ~I_SYNC_QUEUED;
 	list_del_init(&inode->i_io_list);
 	wb_io_lists_depopulated(wb);
 }
@@ -269,6 +270,7 @@ void __inode_attach_wb(struct inode *inode, struct page *page)
 	if (unlikely(cmpxchg(&inode->i_wb, NULL, wb)))
 		wb_put(wb);
 }
+EXPORT_SYMBOL_GPL(__inode_attach_wb);
 
 /**
  * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it
@@ -1038,7 +1040,9 @@ void inode_io_list_del(struct inode *inode)
 	struct bdi_writeback *wb;
 
 	wb = inode_to_wb_and_lock_list(inode);
+	spin_lock(&inode->i_lock);
 	inode_io_list_del_locked(inode, wb);
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&wb->list_lock);
 }
 
@@ -1087,8 +1091,10 @@ void sb_clear_inode_writeback(struct inode *inode)
  * the case then the inode must have been redirtied while it was being written
  * out and we don't reset its dirtied_when.
  */
-static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
+static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb)
 {
+	assert_spin_locked(&inode->i_lock);
+
 	if (!list_empty(&wb->b_dirty)) {
 		struct inode *tail;
 
@@ -1097,6 +1103,14 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
 			inode->dirtied_when = jiffies;
 	}
 	inode_io_list_move_locked(inode, wb, &wb->b_dirty);
+	inode->i_state &= ~I_SYNC_QUEUED;
+}
+
+static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
+{
+	spin_lock(&inode->i_lock);
+	redirty_tail_locked(inode, wb);
+	spin_unlock(&inode->i_lock);
 }
 
 /*
@@ -1135,16 +1149,13 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
 #define EXPIRE_DIRTY_ATIME 0x0001
 
 /*
- * Move expired (dirtied before work->older_than_this) dirty inodes from
+ * Move expired (dirtied before dirtied_before) dirty inodes from
  * @delaying_queue to @dispatch_queue.
  */
 static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
-			       int flags,
-			       struct wb_writeback_work *work)
+			       int flags, unsigned long dirtied_before)
 {
-	unsigned long *older_than_this = NULL;
-	unsigned long expire_time;
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;
 	struct super_block *sb = NULL;
@@ -1152,21 +1163,17 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 	int moved = 0;
 
-	if ((flags & EXPIRE_DIRTY_ATIME) == 0)
-		older_than_this = work->older_than_this;
-	else if (!work->for_sync) {
-		expire_time = jiffies - (dirtytime_expire_interval * HZ);
-		older_than_this = &expire_time;
-	}
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (older_than_this &&
-		    inode_dirtied_after(inode, *older_than_this))
+		if (inode_dirtied_after(inode, dirtied_before))
 			break;
 		list_move(&inode->i_io_list, &tmp);
 		moved++;
+		spin_lock(&inode->i_lock);
 		if (flags & EXPIRE_DIRTY_ATIME)
-			set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state);
+			inode->i_state |= I_DIRTY_TIME_EXPIRED;
+		inode->i_state |= I_SYNC_QUEUED;
+		spin_unlock(&inode->i_lock);
 		if (sb_is_blkdev_sb(inode->i_sb))
 			continue;
 		if (sb && sb != inode->i_sb)
@@ -1204,18 +1211,22 @@ out:
  *                                           |
  *                                           +--> dequeue for IO
  */
-static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
+static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work,
+		     unsigned long dirtied_before)
 {
 	int moved;
+	unsigned long time_expire_jif = dirtied_before;
 
 	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
-	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work);
+	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, dirtied_before);
+	if (!work->for_sync)
+		time_expire_jif = jiffies - dirtytime_expire_interval * HZ;
 	moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
-				     EXPIRE_DIRTY_ATIME, work);
+				     EXPIRE_DIRTY_ATIME, time_expire_jif);
 	if (moved)
 		wb_io_lists_populated(wb);
-	trace_writeback_queue_io(wb, work, moved);
+	trace_writeback_queue_io(wb, work, dirtied_before, moved);
 }
 
 static int write_inode(struct inode *inode, struct writeback_control *wbc)
@@ -1309,7 +1320,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		 * writeback is not making progress due to locked
 		 * buffers. Skip this inode for now.
 		 */
-		redirty_tail(inode, wb);
+		redirty_tail_locked(inode, wb);
 		return;
 	}
 
@@ -1329,7 +1340,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 			 * retrying writeback of the dirty page/inode
 			 * that cannot be performed immediately.
 			 */
-			redirty_tail(inode, wb);
+			redirty_tail_locked(inode, wb);
 		}
 	} else if (inode->i_state & I_DIRTY) {
 		/*
@@ -1337,10 +1348,11 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		 * such as delayed allocation during submission or metadata
 		 * updates after data IO completion.
 		 */
-		redirty_tail(inode, wb);
+		redirty_tail_locked(inode, wb);
 	} else if (inode->i_state & I_DIRTY_TIME) {
 		inode->dirtied_when = jiffies;
 		inode_io_list_move_locked(inode, wb, &wb->b_dirty_time);
+		inode->i_state &= ~I_SYNC_QUEUED;
 	} else {
 		/* The inode is clean. Remove from writeback lists. */
 		inode_io_list_del_locked(inode, wb);
@@ -1584,8 +1596,8 @@ static long writeback_sb_inodes(struct super_block *sb,
 		 */
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+			redirty_tail_locked(inode, wb);
 			spin_unlock(&inode->i_lock);
-			redirty_tail(inode, wb);
 			continue;
 		}
 		if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) {
@@ -1726,7 +1738,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 	blk_start_plug(&plug);
 	spin_lock(&wb->list_lock);
 	if (list_empty(&wb->b_io))
-		queue_io(wb, &work);
+		queue_io(wb, &work, jiffies);
 	__writeback_inodes_wb(wb, &work);
 	spin_unlock(&wb->list_lock);
 	blk_finish_plug(&plug);
@@ -1746,7 +1758,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
  * takes longer than a dirty_writeback_interval interval, then leave a
  * one-second gap.
  *
- * older_than_this takes precedence over nr_to_write.  So we'll only write back
+ * dirtied_before takes precedence over nr_to_write.  So we'll only write back
  * all dirty pages if they are all attached to "old" mappings.
  */
 static long wb_writeback(struct bdi_writeback *wb,
@@ -1754,14 +1766,11 @@ static long wb_writeback(struct bdi_writeback *wb,
 {
 	unsigned long wb_start = jiffies;
 	long nr_pages = work->nr_pages;
-	unsigned long oldest_jif;
+	unsigned long dirtied_before = jiffies;
 	struct inode *inode;
 	long progress;
 	struct blk_plug plug;
 
-	oldest_jif = jiffies;
-	work->older_than_this = &oldest_jif;
-
 	blk_start_plug(&plug);
 	spin_lock(&wb->list_lock);
 	for (;;) {
@@ -1795,14 +1804,14 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * safe.
 		 */
 		if (work->for_kupdate) {
-			oldest_jif = jiffies -
+			dirtied_before = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
 		} else if (work->for_background)
-			oldest_jif = jiffies;
+			dirtied_before = jiffies;
 
 		trace_writeback_start(wb, work);
 		if (list_empty(&wb->b_io))
-			queue_io(wb, work);
+			queue_io(wb, work, dirtied_before);
 		if (work->sb)
 			progress = writeback_sb_inodes(work->sb, wb, work);
 		else
@@ -2175,11 +2184,12 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		inode->i_state |= flags;
 
 		/*
-		 * If the inode is being synced, just update its dirty state.
-		 * The unlocker will place the inode on the appropriate
-		 * superblock list, based upon its state.
+		 * If the inode is queued for writeback by flush worker, just
+		 * update its dirty state. Once the flush worker is done with
+		 * the inode it will place it on the appropriate superblock
+		 * list, based upon its state.
 		 */
-		if (inode->i_state & I_SYNC)
+		if (inode->i_state & I_SYNC_QUEUED)
 			goto out_unlock_inode;
 
 		/*
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index f580695b7bb9..1b9c4c19bed2 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -824,7 +824,6 @@ static int fuse_check_page(struct page *page)
 {
 	if (page_mapcount(page) ||
 	    page->mapping != NULL ||
-	    page_count(page) != 1 ||
 	    (page->flags & PAGE_FLAGS_CHECK_AT_PREP &
 	     ~(1 << PG_locked |
 	       1 << PG_referenced |
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 969584c99c54..4238939af2fe 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -17,6 +17,7 @@
 #include <linux/swap.h>
 #include <linux/falloc.h>
 #include <linux/uio.h>
+#include <linux/fs.h>
 
 static const struct file_operations fuse_direct_io_file_operations;
 
@@ -2534,7 +2535,16 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 		struct iovec *iov = iov_page;
 
 		iov->iov_base = (void __user *)arg;
-		iov->iov_len = _IOC_SIZE(cmd);
+
+		switch (cmd) {
+		case FS_IOC_GETFLAGS:
+		case FS_IOC_SETFLAGS:
+			iov->iov_len = sizeof(int);
+			break;
+		default:
+			iov->iov_len = _IOC_SIZE(cmd);
+			break;
+		}
 
 		if (_IOC_DIR(cmd) & _IOC_WRITE) {
 			in_iov = iov;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index cdd1c5f06f45..f1844af4005b 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -89,6 +89,8 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	memset(&tr, 0, sizeof(tr));
 	INIT_LIST_HEAD(&tr.tr_buf);
 	INIT_LIST_HEAD(&tr.tr_databuf);
+	INIT_LIST_HEAD(&tr.tr_ail1_list);
+	INIT_LIST_HEAD(&tr.tr_ail2_list);
 	tr.tr_revokes = atomic_read(&gl->gl_ail_count);
 
 	if (!tr.tr_revokes)
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 6c6401084d3d..e893b1fbde98 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -714,7 +714,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 
 	error = gfs2_trans_begin(sdp, blocks, 0);
 	if (error)
-		goto fail_gunlock2;
+		goto fail_free_inode;
 
 	if (blocks > 1) {
 		ip->i_eattr = ip->i_no_addr + 1;
@@ -725,7 +725,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 
 	error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
 	if (error)
-		goto fail_gunlock2;
+		goto fail_free_inode;
 
 	BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags));
 
@@ -734,7 +734,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		goto fail_gunlock2;
 
 	glock_set_object(ip->i_iopen_gh.gh_gl, ip);
-	gfs2_glock_put(io_gl);
 	gfs2_set_iop(inode);
 	insert_inode_hash(inode);
 
@@ -767,6 +766,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 
 	mark_inode_dirty(inode);
 	d_instantiate(dentry, inode);
+	/* After instantiate, errors should result in evict which will destroy
+	 * both inode and iopen glocks properly. */
 	if (file) {
 		*opened |= FILE_CREATED;
 		error = finish_open(file, dentry, gfs2_open_common, opened);
@@ -774,15 +775,15 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	gfs2_glock_dq_uninit(ghs);
 	gfs2_glock_dq_uninit(ghs + 1);
 	clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
+	gfs2_glock_put(io_gl);
 	return error;
 
 fail_gunlock3:
 	glock_clear_object(io_gl, ip);
 	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
-	gfs2_glock_put(io_gl);
 fail_gunlock2:
-	if (io_gl)
-		clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
+	clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
+	gfs2_glock_put(io_gl);
 fail_free_inode:
 	if (ip->i_gl) {
 		glock_clear_object(ip->i_gl, ip);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index a3208511f35a..b05c0ed36b6f 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -734,8 +734,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
 	tr = sdp->sd_log_tr;
 	if (tr) {
 		sdp->sd_log_tr = NULL;
-		INIT_LIST_HEAD(&tr->tr_ail1_list);
-		INIT_LIST_HEAD(&tr->tr_ail2_list);
 		tr->tr_first = sdp->sd_log_flush_head;
 		if (unlikely (state == SFS_FROZEN))
 			gfs2_assert_withdraw(sdp, !tr->tr_num_buf_new && !tr->tr_num_databuf_new);
@@ -804,8 +802,10 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
  * @new: New transaction to be merged
  */
 
-static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
+static void gfs2_merge_trans(struct gfs2_sbd *sdp, struct gfs2_trans *new)
 {
+	struct gfs2_trans *old = sdp->sd_log_tr;
+
 	WARN_ON_ONCE(!test_bit(TR_ATTACHED, &old->tr_flags));
 
 	old->tr_num_buf_new	+= new->tr_num_buf_new;
@@ -817,6 +817,11 @@ static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
 
 	list_splice_tail_init(&new->tr_databuf, &old->tr_databuf);
 	list_splice_tail_init(&new->tr_buf, &old->tr_buf);
+
+	spin_lock(&sdp->sd_ail_lock);
+	list_splice_tail_init(&new->tr_ail1_list, &old->tr_ail1_list);
+	list_splice_tail_init(&new->tr_ail2_list, &old->tr_ail2_list);
+	spin_unlock(&sdp->sd_ail_lock);
 }
 
 static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
@@ -828,7 +833,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	gfs2_log_lock(sdp);
 
 	if (sdp->sd_log_tr) {
-		gfs2_merge_trans(sdp->sd_log_tr, tr);
+		gfs2_merge_trans(sdp, tr);
 	} else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
 		gfs2_assert_withdraw(sdp, test_bit(TR_ALLOCED, &tr->tr_flags));
 		sdp->sd_log_tr = tr;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 057be88eb1b4..2de67588ac2d 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -922,7 +922,7 @@ fail:
 }
 
 static const match_table_t nolock_tokens = {
-	{ Opt_jid, "jid=%d\n", },
+	{ Opt_jid, "jid=%d", },
 	{ Opt_err, NULL },
 };
 
@@ -1179,7 +1179,17 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent
 		goto fail_per_node;
 	}
 
-	if (!sb_rdonly(sb)) {
+	if (sb_rdonly(sb)) {
+		struct gfs2_holder freeze_gh;
+
+		error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
+					   GL_EXACT, &freeze_gh);
+		if (error) {
+			fs_err(sdp, "can't make FS RO: %d\n", error);
+			goto fail_per_node;
+		}
+		gfs2_glock_dq_uninit(&freeze_gh);
+	} else {
 		error = gfs2_make_fs_rw(sdp);
 		if (error) {
 			fs_err(sdp, "can't make FS RW: %d\n", error);
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index e700fb162664..a833e2e07167 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1039,8 +1039,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 	u32 x;
 	int error = 0;
 
-	if (capable(CAP_SYS_RESOURCE) ||
-	    sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
+	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
 		return 0;
 
 	error = gfs2_quota_hold(ip, uid, gid);
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index 836f29480be6..e3a6e2404d11 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -47,7 +47,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip,
 	int ret;
 
 	ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */
-	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+	if (capable(CAP_SYS_RESOURCE) ||
+	    sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
 		return 0;
 	ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
 	if (ret)
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 69e3402a3cc5..3a9abc3aac82 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -56,6 +56,8 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 						   sizeof(u64));
 	INIT_LIST_HEAD(&tr->tr_databuf);
 	INIT_LIST_HEAD(&tr->tr_buf);
+	INIT_LIST_HEAD(&tr->tr_ail1_list);
+	INIT_LIST_HEAD(&tr->tr_ail2_list);
 
 	sb_start_intwrite(sdp->sd_vfs);
 
diff --git a/fs/inode.c b/fs/inode.c
index 17172b616d22..5f048203a6d4 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1664,7 +1664,7 @@ EXPORT_SYMBOL(generic_update_time);
  * This does the actual work of updating an inodes time or version.  Must have
  * had called mnt_want_write() before calling this.
  */
-static int update_time(struct inode *inode, struct timespec *time, int flags)
+int update_time(struct inode *inode, struct timespec *time, int flags)
 {
 	int (*update_time)(struct inode *, struct timespec *, int);
 
@@ -1673,6 +1673,7 @@ static int update_time(struct inode *inode, struct timespec *time, int flags)
 
 	return update_time(inode, time, flags);
 }
+EXPORT_SYMBOL_GPL(update_time);
 
 /**
  *	touch_atime	-	update the access time
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 6e054b368b5f..93a466cf58ba 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1356,8 +1356,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
 	int ret;
 
 	/* Buffer got discarded which means block device got invalidated */
-	if (!buffer_mapped(bh))
+	if (!buffer_mapped(bh)) {
+		unlock_buffer(bh);
 		return -EIO;
+	}
 
 	trace_jbd2_write_superblock(journal, write_flags);
 	if (!(journal->j_flags & JBD2_BARRIER))
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index a355ca418e78..3311b1e684de 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1914,6 +1914,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
  */
 static void __jbd2_journal_unfile_buffer(struct journal_head *jh)
 {
+	J_ASSERT_JH(jh, jh->b_transaction != NULL);
+	J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
+
 	__jbd2_journal_temp_unlink_buffer(jh);
 	jh->b_transaction = NULL;
 	jbd2_journal_put_journal_head(jh);
@@ -2005,6 +2008,7 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal,
 {
 	struct buffer_head *head;
 	struct buffer_head *bh;
+	bool has_write_io_error = false;
 	int ret = 0;
 
 	J_ASSERT(PageLocked(page));
@@ -2029,11 +2033,26 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal,
 		jbd_unlock_bh_state(bh);
 		if (buffer_jbd(bh))
 			goto busy;
+
+		/*
+		 * If we free a metadata buffer which has been failed to
+		 * write out, the jbd2 checkpoint procedure will not detect
+		 * this failure and may lead to filesystem inconsistency
+		 * after cleanup journal tail.
+		 */
+		if (buffer_write_io_error(bh)) {
+			pr_err("JBD2: Error while async write back metadata bh %llu.",
+			       (unsigned long long)bh->b_blocknr);
+			has_write_io_error = true;
+		}
 	} while ((bh = bh->b_this_page) != head);
 
 	ret = try_to_free_buffers(page);
 
 busy:
+	if (has_write_io_error)
+		jbd2_journal_abort(journal, -EIO);
+
 	return ret;
 }
 
@@ -2461,6 +2480,13 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh)
 
 	was_dirty = test_clear_buffer_jbddirty(bh);
 	__jbd2_journal_temp_unlink_buffer(jh);
+
+	/*
+	 * b_transaction must be set, otherwise the new b_transaction won't
+	 * be holding jh reference
+	 */
+	J_ASSERT_JH(jh, jh->b_transaction != NULL);
+
 	/*
 	 * We set b_transaction here because b_next_transaction will inherit
 	 * our jh reference and thus __jbd2_journal_file_buffer() must not
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index e5a6deb38e1e..f4a5ec92f5dc 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -590,10 +590,14 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry)
 	int ret;
 	uint32_t now = get_seconds();
 
+	mutex_lock(&f->sem);
 	for (fd = f->dents ; fd; fd = fd->next) {
-		if (fd->ino)
+		if (fd->ino) {
+			mutex_unlock(&f->sem);
 			return -ENOTEMPTY;
+		}
 	}
+	mutex_unlock(&f->sem);
 
 	ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name,
 			      dentry->d_name.len, f, now);
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index b6829d679643..d49337b5abfa 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -155,6 +155,23 @@ static int minix_remount (struct super_block * sb, int * flags, char * data)
 	return 0;
 }
 
+static bool minix_check_superblock(struct minix_sb_info *sbi)
+{
+	if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0)
+		return false;
+
+	/*
+	 * s_max_size must not exceed the block mapping limitation.  This check
+	 * is only needed for V1 filesystems, since V2/V3 support an extra level
+	 * of indirect blocks which places the limit well above U32_MAX.
+	 */
+	if (sbi->s_version == MINIX_V1 &&
+	    sbi->s_max_size > (7 + 512 + 512*512) * BLOCK_SIZE)
+		return false;
+
+	return true;
+}
+
 static int minix_fill_super(struct super_block *s, void *data, int silent)
 {
 	struct buffer_head *bh;
@@ -233,11 +250,12 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
 	} else
 		goto out_no_fs;
 
+	if (!minix_check_superblock(sbi))
+		goto out_illegal_sb;
+
 	/*
 	 * Allocate the buffer map to keep the superblock small.
 	 */
-	if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0)
-		goto out_illegal_sb;
 	i = (sbi->s_imap_blocks + sbi->s_zmap_blocks) * sizeof(bh);
 	map = kzalloc(i, GFP_KERNEL);
 	if (!map)
@@ -471,6 +489,13 @@ static struct inode *V1_minix_iget(struct inode *inode)
 		iget_failed(inode);
 		return ERR_PTR(-EIO);
 	}
+	if (raw_inode->i_nlinks == 0) {
+		printk("MINIX-fs: deleted inode referenced: %lu\n",
+		       inode->i_ino);
+		brelse(bh);
+		iget_failed(inode);
+		return ERR_PTR(-ESTALE);
+	}
 	inode->i_mode = raw_inode->i_mode;
 	i_uid_write(inode, raw_inode->i_uid);
 	i_gid_write(inode, raw_inode->i_gid);
@@ -504,6 +529,13 @@ static struct inode *V2_minix_iget(struct inode *inode)
 		iget_failed(inode);
 		return ERR_PTR(-EIO);
 	}
+	if (raw_inode->i_nlinks == 0) {
+		printk("MINIX-fs: deleted inode referenced: %lu\n",
+		       inode->i_ino);
+		brelse(bh);
+		iget_failed(inode);
+		return ERR_PTR(-ESTALE);
+	}
 	inode->i_mode = raw_inode->i_mode;
 	i_uid_write(inode, raw_inode->i_uid);
 	i_gid_write(inode, raw_inode->i_gid);
diff --git a/fs/minix/itree_common.c b/fs/minix/itree_common.c
index 043c3fdbc8e7..446148792f41 100644
--- a/fs/minix/itree_common.c
+++ b/fs/minix/itree_common.c
@@ -75,6 +75,7 @@ static int alloc_branch(struct inode *inode,
 	int n = 0;
 	int i;
 	int parent = minix_new_block(inode);
+	int err = -ENOSPC;
 
 	branch[0].key = cpu_to_block(parent);
 	if (parent) for (n = 1; n < num; n++) {
@@ -85,6 +86,11 @@ static int alloc_branch(struct inode *inode,
 			break;
 		branch[n].key = cpu_to_block(nr);
 		bh = sb_getblk(inode->i_sb, parent);
+		if (!bh) {
+			minix_free_block(inode, nr);
+			err = -ENOMEM;
+			break;
+		}
 		lock_buffer(bh);
 		memset(bh->b_data, 0, bh->b_size);
 		branch[n].bh = bh;
@@ -103,7 +109,7 @@ static int alloc_branch(struct inode *inode,
 		bforget(branch[i].bh);
 	for (i = 0; i < n; i++)
 		minix_free_block(inode, block_to_cpu(branch[i].key));
-	return -ENOSPC;
+	return err;
 }
 
 static inline int splice_branch(struct inode *inode,
diff --git a/fs/namespace.c b/fs/namespace.c
index c8acc60c456d..f264ff8491c8 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -517,6 +517,7 @@ void __mnt_drop_write(struct vfsmount *mnt)
 	mnt_dec_writers(real_mount(mnt));
 	preempt_enable();
 }
+EXPORT_SYMBOL_GPL(__mnt_drop_write);
 
 /**
  * mnt_drop_write - give up write access to a mount
@@ -1918,6 +1919,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(iterate_mounts);
 
 static void cleanup_group_ids(struct mount *mnt, struct mount *end)
 {
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index ac3e06367cb6..7ccc30a757ec 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -39,6 +39,19 @@ config NFS_V2
 
 	  If unsure, say Y.
 
+config NFS_DEF_FILE_IO_SIZE
+	int "Default size for NFS I/O read and write at runtime"
+	depends on NFS_FS
+	default "4096"
+	help
+	  To change the default rsize and wsize supported by the NFS client,
+	  adjust NFS_DEF_FILE_IO_SIZE.  64KB is a typical maximum, but some
+	  servers can support a megabyte or more.  The default is left at 4096
+	  bytes, which is reasonable for NFS over UDP, however, for some
+	  systems, setting a smaller value like 1024 can work around
+	  limitations in the driver or hardware and result in overall
+	  improved performance.
+
 config NFS_V3
 	tristate "NFS client support for NFS version 3"
 	depends on NFS_FS
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 9e7d49fac4e3..ee72691ce94f 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -9,7 +9,6 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/sched.h>
@@ -70,7 +69,7 @@ static const struct rpc_version *nfs_version[5] = {
 	[4] = NULL,
 };
 
-const struct rpc_program nfs_program = {
+struct rpc_program nfs_program = {
 	.name			= "nfs",
 	.number			= NFS_PROGRAM,
 	.nrvers			= ARRAY_SIZE(nfs_version),
@@ -162,6 +161,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 		goto error_dealloc;
 
 	clp->rpc_ops = clp->cl_nfs_mod->rpc_ops;
+	clp->nfs_prog = cl_init->nfs_prog;
 
 	atomic_set(&clp->cl_count, 1);
 	clp->cl_cons_state = NFS_CS_INITING;
@@ -320,6 +320,9 @@ again:
 		/* Match nfsv4 minorversion */
 		if (clp->cl_minorversion != data->minorversion)
 			continue;
+		if (clp->nfs_prog != data->nfs_prog)
+			continue;
+
 		/* Match the full socket address */
 		if (!rpc_cmp_addr_port(sap, clap))
 			/* Match all xprt_switch full socket addresses */
@@ -525,6 +528,10 @@ int nfs_create_rpc_client(struct nfs_client *clp,
 	if (!IS_ERR(clp->cl_rpcclient))
 		return 0;
 
+	if (clp->nfs_prog)
+		nfs_program.number = clp->nfs_prog;
+	else
+		nfs_program.number = NFS_PROGRAM;
 	clnt = rpc_create(&args);
 	if (IS_ERR(clnt)) {
 		dprintk("%s: cannot create RPC client. Error = %ld\n",
@@ -662,6 +669,7 @@ static int nfs_init_server(struct nfs_server *server,
 		.proto = data->nfs_server.protocol,
 		.net = data->net,
 		.timeparms = &timeparms,
+                .nfs_prog = data->nfs_prog,
 	};
 	struct nfs_client *clp;
 	int error;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 673d89bb817e..5c26e90db588 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -560,6 +560,9 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
 	do {
+		if (entry->label)
+			entry->label->len = NFS4_MAXLABELLEN;
+
 		status = xdr_decode(desc, entry, &stream);
 		if (status != 0) {
 			if (status == -EAGAIN)
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 8dbde5ded042..74f15498c9bf 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -921,9 +921,8 @@ retry:
 		goto out_mds;
 
 	/* Use a direct mapping of ds_idx to pgio mirror_idx */
-	if (WARN_ON_ONCE(pgio->pg_mirror_count !=
-	    FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg)))
-		goto out_mds;
+	if (pgio->pg_mirror_count != FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg))
+		goto out_eagain;
 
 	for (i = 0; i < pgio->pg_mirror_count; i++) {
 		ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
@@ -942,11 +941,15 @@ retry:
 	}
 
 	return;
-
+out_eagain:
+	pnfs_generic_pg_cleanup(pgio);
+	pgio->pg_error = -EAGAIN;
+	return;
 out_mds:
 	pnfs_put_lseg(pgio->pg_lseg);
 	pgio->pg_lseg = NULL;
 	nfs_pageio_reset_write_mds(pgio);
+	pgio->pg_error = -EAGAIN;
 }
 
 static unsigned int
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index f9a4a5524bd5..e8ccab17a962 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -83,6 +83,7 @@ struct nfs_client_initdata {
 	u32 minorversion;
 	struct net *net;
 	const struct rpc_timeout *timeparms;
+	int nfs_prog;
 };
 
 /*
@@ -94,6 +95,8 @@ struct nfs_parsed_mount_data {
 	unsigned int		timeo, retrans;
 	unsigned int		acregmin, acregmax,
 				acdirmin, acdirmax;
+	int			nfs_prog;
+	int			mount_prog;
 	unsigned int		namlen;
 	unsigned int		options;
 	unsigned int		bsize;
@@ -150,11 +153,11 @@ struct nfs_mount_info {
 	struct nfs_fh *mntfh;
 };
 
-extern int nfs_mount(struct nfs_mount_request *info);
+extern int nfs_mount(struct nfs_mount_request *info, int prog);
 extern void nfs_umount(const struct nfs_mount_request *info);
 
 /* client.c */
-extern const struct rpc_program nfs_program;
+extern struct rpc_program nfs_program;
 extern void nfs_clients_init(struct net *net);
 extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *);
 int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t);
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index d979ff4fee7e..7035dc1797c2 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -66,7 +66,7 @@ enum {
 	MOUNTPROC3_EXPORT	= 5,
 };
 
-static const struct rpc_program mnt_program;
+static struct rpc_program mnt_program;
 
 /*
  * Defined by OpenGroup XNFS Version 3W, chapter 8
@@ -143,7 +143,7 @@ struct mnt_fhstatus {
  * with the list from the server or a faked-up list if the server didn't
  * provide one.
  */
-int nfs_mount(struct nfs_mount_request *info)
+int nfs_mount(struct nfs_mount_request *info, int m_prog)
 {
 	struct mountres	result = {
 		.fh		= info->fh,
@@ -177,6 +177,7 @@ int nfs_mount(struct nfs_mount_request *info)
 	if (info->noresvport)
 		args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
 
+	mnt_program.number = m_prog;
 	mnt_clnt = rpc_create(&args);
 	if (IS_ERR(mnt_clnt))
 		goto out_clnt_err;
@@ -530,7 +531,7 @@ static const struct rpc_version *mnt_version[] = {
 
 static struct rpc_stat mnt_stats;
 
-static const struct rpc_program mnt_program = {
+static struct rpc_program mnt_program = {
 	.name		= "mount",
 	.number		= NFS_MNT_PROGRAM,
 	.nrvers		= ARRAY_SIZE(mnt_version),
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4d45786738ab..997b731ee19a 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5323,8 +5323,6 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf,
 		return ret;
 	if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL))
 		return -ENOENT;
-	if (buflen < label.len)
-		return -ERANGE;
 	return 0;
 }
 
@@ -6689,7 +6687,12 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state,
 	err = nfs4_set_lock_state(state, fl);
 	if (err != 0)
 		return err;
-	err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
+	do {
+		err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
+		if (err != -NFS4ERR_DELAY)
+			break;
+		ssleep(1);
+	} while (err == -NFS4ERR_DELAY);
 	return nfs4_handle_delegation_recall_error(server, state, stateid, fl, err);
 }
 
@@ -7309,7 +7312,7 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 }
 
 static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
-	.rpc_call_done =  &nfs4_bind_one_conn_to_session_done,
+	.rpc_call_done =  nfs4_bind_one_conn_to_session_done,
 };
 
 /*
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 0b2d051990e9..3cd04c98da6b 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -4258,7 +4258,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap,
 			goto out_overflow;
 		if (len < NFS4_MAXLABELLEN) {
 			if (label) {
-				memcpy(label->label, p, len);
+				if (label->len) {
+					if (label->len < len)
+						return -ERANGE;
+					memcpy(label->label, p, len);
+				}
 				label->len = len;
 				label->pi = pi;
 				label->lfs = lfs;
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 7c01936be7c7..37358dba3b03 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -132,47 +132,70 @@ nfs_async_iocounter_wait(struct rpc_task *task, struct nfs_lock_context *l_ctx)
 EXPORT_SYMBOL_GPL(nfs_async_iocounter_wait);
 
 /*
- * nfs_page_group_lock - lock the head of the page group
- * @req - request in group that is to be locked
+ * nfs_page_set_headlock - set the request PG_HEADLOCK
+ * @req: request that is to be locked
  *
- * this lock must be held when traversing or modifying the page
- * group list
+ * this lock must be held when modifying req->wb_head
  *
  * return 0 on success, < 0 on error
  */
 int
-nfs_page_group_lock(struct nfs_page *req)
+nfs_page_set_headlock(struct nfs_page *req)
 {
-	struct nfs_page *head = req->wb_head;
-
-	WARN_ON_ONCE(head != head->wb_head);
-
-	if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags))
+	if (!test_and_set_bit(PG_HEADLOCK, &req->wb_flags))
 		return 0;
 
-	set_bit(PG_CONTENDED1, &head->wb_flags);
+	set_bit(PG_CONTENDED1, &req->wb_flags);
 	smp_mb__after_atomic();
-	return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
+	return wait_on_bit_lock(&req->wb_flags, PG_HEADLOCK,
 				TASK_UNINTERRUPTIBLE);
 }
 
 /*
- * nfs_page_group_unlock - unlock the head of the page group
- * @req - request in group that is to be unlocked
+ * nfs_page_clear_headlock - clear the request PG_HEADLOCK
+ * @req: request that is to be locked
  */
 void
-nfs_page_group_unlock(struct nfs_page *req)
+nfs_page_clear_headlock(struct nfs_page *req)
 {
-	struct nfs_page *head = req->wb_head;
-
-	WARN_ON_ONCE(head != head->wb_head);
-
 	smp_mb__before_atomic();
-	clear_bit(PG_HEADLOCK, &head->wb_flags);
+	clear_bit(PG_HEADLOCK, &req->wb_flags);
 	smp_mb__after_atomic();
-	if (!test_bit(PG_CONTENDED1, &head->wb_flags))
+	if (!test_bit(PG_CONTENDED1, &req->wb_flags))
 		return;
-	wake_up_bit(&head->wb_flags, PG_HEADLOCK);
+	wake_up_bit(&req->wb_flags, PG_HEADLOCK);
+}
+
+/*
+ * nfs_page_group_lock - lock the head of the page group
+ * @req: request in group that is to be locked
+ *
+ * this lock must be held when traversing or modifying the page
+ * group list
+ *
+ * return 0 on success, < 0 on error
+ */
+int
+nfs_page_group_lock(struct nfs_page *req)
+{
+	int ret;
+
+	ret = nfs_page_set_headlock(req);
+	if (ret || req->wb_head == req)
+		return ret;
+	return nfs_page_set_headlock(req->wb_head);
+}
+
+/*
+ * nfs_page_group_unlock - unlock the head of the page group
+ * @req: request in group that is to be unlocked
+ */
+void
+nfs_page_group_unlock(struct nfs_page *req)
+{
+	if (req != req->wb_head)
+		nfs_page_clear_headlock(req->wb_head);
+	nfs_page_clear_headlock(req);
 }
 
 /*
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 470b761839a5..cea9f124ceb0 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -102,6 +102,8 @@ enum {
 	Opt_mountport,
 	Opt_mountvers,
 	Opt_minorversion,
+	Opt_mountprog,
+	Opt_nfsprog,
 
 	/* Mount options that take string arguments */
 	Opt_nfsvers,
@@ -167,6 +169,8 @@ static const match_table_t nfs_mount_option_tokens = {
 	{ Opt_mountport, "mountport=%s" },
 	{ Opt_mountvers, "mountvers=%s" },
 	{ Opt_minorversion, "minorversion=%s" },
+	{ Opt_mountprog, "mountprog=%s" },
+	{ Opt_nfsprog, "nfsprog=%s" },
 
 	{ Opt_nfsvers, "nfsvers=%s" },
 	{ Opt_nfsvers, "vers=%s" },
@@ -922,6 +926,8 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void)
 		data->acregmax		= NFS_DEF_ACREGMAX;
 		data->acdirmin		= NFS_DEF_ACDIRMIN;
 		data->acdirmax		= NFS_DEF_ACDIRMAX;
+		data->nfs_prog		= NFS_PROGRAM;
+		data->mount_prog	= NFS_MNT_PROGRAM;
 		data->mount_server.port	= NFS_UNSPEC_PORT;
 		data->nfs_server.port	= NFS_UNSPEC_PORT;
 		data->nfs_server.protocol = XPRT_TRANSPORT_TCP;
@@ -1389,6 +1395,26 @@ static int nfs_parse_mount_options(char *raw,
 				goto out_invalid_value;
 			mnt->acdirmax = option;
 			break;
+		case Opt_mountprog:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = kstrtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
+			mnt->mount_prog = option;
+			break;
+		case Opt_nfsprog:
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = kstrtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+			       goto out_invalid_value;
+			mnt->nfs_prog = option;
+			break;
 		case Opt_actimeo:
 			if (nfs_get_option_ul(args, &option))
 				goto out_invalid_value;
@@ -1784,7 +1810,7 @@ static int nfs_request_mount(struct nfs_parsed_mount_data *args,
 	 * Now ask the mount server to map our export path
 	 * to a file handle.
 	 */
-	status = nfs_mount(&request);
+	status = nfs_mount(&request,args->mount_prog);
 	if (status != 0) {
 		dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n",
 				request.hostname, status);
@@ -2095,6 +2121,9 @@ static int nfs23_validate_mount_data(void *options,
 		}
 
 		break;
+	case 7:
+		args->nfs_prog = (data->version >= 7) ? data->nfs_prog : NFS_PROGRAM;
+		break;
 	default:
 		return NFS_TEXT_DATA;
 	}
@@ -2157,6 +2186,7 @@ static int nfs_validate_text_mount_data(void *options,
 	int max_namelen = PAGE_SIZE;
 	int max_pathlen = NFS_MAXPATHLEN;
 	struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
+	args->nfs_prog		= NFS_PROGRAM;
 
 	if (nfs_parse_mount_options((char *)options, args) == 0)
 		return -EINVAL;
@@ -2775,6 +2805,8 @@ static int nfs4_validate_mount_data(void *options,
 
 	args->version = 4;
 
+	args->nfs_prog = NFS_PROGRAM;
+
 	switch (data->version) {
 	case 1:
 		if (data->host_addrlen > sizeof(args->nfs_server.address))
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 7b6bda68aa86..767e46c09074 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -406,22 +406,28 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list,
 		destroy_list = (subreq->wb_this_page == old_head) ?
 				   NULL : subreq->wb_this_page;
 
+		/* Note: lock subreq in order to change subreq->wb_head */
+		nfs_page_set_headlock(subreq);
 		WARN_ON_ONCE(old_head != subreq->wb_head);
 
 		/* make sure old group is not used */
 		subreq->wb_this_page = subreq;
+		subreq->wb_head = subreq;
 
 		clear_bit(PG_REMOVE, &subreq->wb_flags);
 
 		/* Note: races with nfs_page_group_destroy() */
 		if (!kref_read(&subreq->wb_kref)) {
 			/* Check if we raced with nfs_page_group_destroy() */
-			if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags))
+			if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags)) {
+				nfs_page_clear_headlock(subreq);
 				nfs_free_request(subreq);
+			} else
+				nfs_page_clear_headlock(subreq);
 			continue;
 		}
+		nfs_page_clear_headlock(subreq);
 
-		subreq->wb_head = subreq;
 		nfs_release_request(old_head);
 
 		if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) {
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 80aeb19b176b..22b784e7ef50 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1161,6 +1161,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 	err = setup_callback_client(clp, &conn, ses);
 	if (err) {
 		nfsd4_mark_cb_down(clp, err);
+		if (c)
+			svc_xprt_put(c->cn_xprt);
 		return;
 	}
 }
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 06d1f2edf2ec..a64065ad8851 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1202,6 +1202,9 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		iap->ia_mode = 0;
 	iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type;
 
+	if (!IS_POSIXACL(dirp))
+		iap->ia_mode &= ~current_umask();
+
 	err = 0;
 	host_err = 0;
 	switch (type) {
@@ -1413,6 +1416,9 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out;
 	}
 
+	if (!IS_POSIXACL(dirp))
+		iap->ia_mode &= ~current_umask();
+
 	host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
 	if (host_err < 0) {
 		fh_drop_write(fhp);
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 50e12956c737..5d1e5832690e 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -2794,6 +2794,8 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root)
 	if (!nilfs->ns_writer)
 		return -ENOMEM;
 
+	inode_attach_wb(nilfs->ns_bdev->bd_inode, NULL);
+
 	err = nilfs_segctor_start_thread(nilfs->ns_writer);
 	if (err) {
 		kfree(nilfs->ns_writer);
diff --git a/fs/notify/group.c b/fs/notify/group.c
index 32357534de18..14a2d48f3ce2 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -22,6 +22,7 @@
 #include <linux/srcu.h>
 #include <linux/rculist.h>
 #include <linux/wait.h>
+#include <linux/module.h>
 
 #include <linux/fsnotify_backend.h>
 #include "fsnotify.h"
@@ -109,6 +110,7 @@ void fsnotify_get_group(struct fsnotify_group *group)
 {
 	atomic_inc(&group->refcnt);
 }
+EXPORT_SYMBOL_GPL(fsnotify_get_group);
 
 /*
  * Drop a reference to a group.  Free it if it's through.
@@ -118,6 +120,7 @@ void fsnotify_put_group(struct fsnotify_group *group)
 	if (atomic_dec_and_test(&group->refcnt))
 		fsnotify_final_destroy_group(group);
 }
+EXPORT_SYMBOL_GPL(fsnotify_put_group);
 
 /*
  * Create a new fsnotify_group and hold a reference for the group returned.
@@ -147,6 +150,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
 
 	return group;
 }
+EXPORT_SYMBOL_GPL(fsnotify_alloc_group);
 
 int fsnotify_fasync(int fd, struct file *file, int on)
 {
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 258d99087183..c3851219dba5 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -108,6 +108,7 @@ void fsnotify_get_mark(struct fsnotify_mark *mark)
 	WARN_ON_ONCE(!atomic_read(&mark->refcnt));
 	atomic_inc(&mark->refcnt);
 }
+EXPORT_SYMBOL_GPL(fsnotify_put_mark);
 
 static void __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
 {
@@ -392,6 +393,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 	mutex_unlock(&group->mark_mutex);
 	fsnotify_free_mark(mark);
 }
+EXPORT_SYMBOL_GPL(fsnotify_destroy_mark);
 
 /*
  * Sorting function for lists of fsnotify marks.
@@ -604,6 +606,7 @@ err:
 	fsnotify_put_mark(mark);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(fsnotify_add_mark);
 
 int fsnotify_add_mark(struct fsnotify_mark *mark, struct inode *inode,
 		      struct vfsmount *mnt, int allow_dups)
@@ -739,6 +742,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
 	fsnotify_get_group(group);
 	mark->group = group;
 }
+EXPORT_SYMBOL_GPL(fsnotify_init_mark);
 
 /*
  * Destroy all marks in destroy_list, waits for SRCU period to finish before
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 9a50f222ac97..b15537a76516 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -336,8 +336,8 @@ struct ocfs2_super
 	spinlock_t osb_lock;
 	u32 s_next_generation;
 	unsigned long osb_flags;
-	s16 s_inode_steal_slot;
-	s16 s_meta_steal_slot;
+	u16 s_inode_steal_slot;
+	u16 s_meta_steal_slot;
 	atomic_t s_num_inodes_stolen;
 	atomic_t s_num_meta_stolen;
 
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 5bb4a89f9045..0773c774e2bf 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -303,7 +303,7 @@
 #define OCFS2_MAX_SLOTS			255
 
 /* Slot map indicator for an empty slot */
-#define OCFS2_INVALID_SLOT		-1
+#define OCFS2_INVALID_SLOT		((u16)-1)
 
 #define OCFS2_VOL_UUID_LEN		16
 #define OCFS2_MAX_VOL_LABEL_LEN		64
@@ -339,8 +339,8 @@ struct ocfs2_system_inode_info {
 enum {
 	BAD_BLOCK_SYSTEM_INODE = 0,
 	GLOBAL_INODE_ALLOC_SYSTEM_INODE,
+#define OCFS2_FIRST_ONLINE_SYSTEM_INODE GLOBAL_INODE_ALLOC_SYSTEM_INODE
 	SLOT_MAP_SYSTEM_INODE,
-#define OCFS2_FIRST_ONLINE_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE
 	HEARTBEAT_SYSTEM_INODE,
 	GLOBAL_BITMAP_SYSTEM_INODE,
 	USER_QUOTA_SYSTEM_INODE,
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 71f22c8fbffd..8d03630dfd59 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -895,9 +895,9 @@ static void __ocfs2_set_steal_slot(struct ocfs2_super *osb, int slot, int type)
 {
 	spin_lock(&osb->osb_lock);
 	if (type == INODE_ALLOC_SYSTEM_INODE)
-		osb->s_inode_steal_slot = slot;
+		osb->s_inode_steal_slot = (u16)slot;
 	else if (type == EXTENT_ALLOC_SYSTEM_INODE)
-		osb->s_meta_steal_slot = slot;
+		osb->s_meta_steal_slot = (u16)slot;
 	spin_unlock(&osb->osb_lock);
 }
 
@@ -2891,9 +2891,12 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res)
 		goto bail;
 	}
 
-	inode_alloc_inode =
-		ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE,
-					    suballoc_slot);
+	if (suballoc_slot == (u16)OCFS2_INVALID_SLOT)
+		inode_alloc_inode = ocfs2_get_system_file_inode(osb,
+			GLOBAL_INODE_ALLOC_SYSTEM_INODE, suballoc_slot);
+	else
+		inode_alloc_inode = ocfs2_get_system_file_inode(osb,
+			INODE_ALLOC_SYSTEM_INODE, suballoc_slot);
 	if (!inode_alloc_inode) {
 		/* the error code could be inaccurate, but we are not able to
 		 * get the correct one. */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 24ab735d91dd..8216550faf45 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -92,7 +92,7 @@ struct mount_options
 	unsigned long	commit_interval;
 	unsigned long	mount_opt;
 	unsigned int	atime_quantum;
-	signed short	slot;
+	unsigned short	slot;
 	int		localalloc_opt;
 	unsigned int	resv_level;
 	int		dir_resv_level;
@@ -1369,7 +1369,7 @@ static int ocfs2_parse_options(struct super_block *sb,
 				goto bail;
 			}
 			if (option)
-				mopt->slot = (s16)option;
+				mopt->slot = (u16)option;
 			break;
 		case Opt_commit:
 			if (match_int(&args[0], &option)) {
diff --git a/fs/open.c b/fs/open.c
index 49fd070be0ec..ad744d6ac4e0 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -64,6 +64,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
 	inode_unlock(dentry->d_inode);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(do_truncate);
 
 long vfs_truncate(const struct path *path, loff_t length)
 {
@@ -710,6 +711,7 @@ int open_check_o_direct(struct file *f)
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(open_check_o_direct);
 
 static int do_dentry_open(struct file *f,
 			  struct inode *inode,
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 321eae740148..b97fc1df6212 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -59,7 +59,7 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
 {
 	ssize_t list_size, size, value_size = 0;
 	char *buf, *name, *value = NULL;
-	int uninitialized_var(error);
+	int error = 0;
 	size_t slen;
 
 	if (!(old->d_inode->i_opflags & IOP_XATTR) ||
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 64695dcf89f3..eeaad0f45b6e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2031,7 +2031,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path)
 	down_read(&mm->mmap_sem);
 	vma = find_exact_vma(mm, vm_start, vm_end);
 	if (vma && vma->vm_file) {
-		*path = vma->vm_file->f_path;
+		*path = vma_pr_or_file(vma)->f_path;
 		path_get(path);
 		rc = 0;
 	}
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 225f541f7078..d8e1249adb18 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -432,7 +432,7 @@ const struct inode_operations proc_link_inode_operations = {
 
 struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 {
-	struct inode *inode = new_inode_pseudo(sb);
+	struct inode *inode = new_inode(sb);
 
 	if (inode) {
 		inode->i_ino = de->low_ino;
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index 75634379f82e..7c0dc0ff4882 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -45,7 +45,10 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
 	file = region->vm_file;
 
 	if (file) {
-		struct inode *inode = file_inode(region->vm_file);
+		struct inode *inode;
+
+		file = vmr_pr_or_file(region);
+		inode = file_inode(file);
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 	}
diff --git a/fs/proc/self.c b/fs/proc/self.c
index 31326bb23b8b..398cdf9a9f0c 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -41,7 +41,7 @@ int proc_setup_self(struct super_block *s)
 	inode_lock(root_inode);
 	self = d_alloc_name(s->s_root, "self");
 	if (self) {
-		struct inode *inode = new_inode_pseudo(s);
+		struct inode *inode = new_inode(s);
 		if (inode) {
 			inode->i_ino = self_inum;
 			inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 309d24118f9a..c6288e71ecfc 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -310,7 +310,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 	const char *name = NULL;
 
 	if (file) {
-		struct inode *inode = file_inode(vma->vm_file);
+		struct inode *inode;
+
+		file = vma_pr_or_file(vma);
+		inode = file_inode(file);
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 		pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
@@ -1775,7 +1778,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
 	struct vm_area_struct *vma = v;
 	struct numa_maps *md = &numa_priv->md;
-	struct file *file = vma->vm_file;
+	struct file *file = vma_pr_or_file(vma);
 	struct mm_struct *mm = vma->vm_mm;
 	struct mm_walk walk = {
 		.hugetlb_entry = gather_hugetlb_stats,
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 5b62f57bd9bc..dfb4a3bd0fac 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -156,7 +156,10 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
 	file = vma->vm_file;
 
 	if (file) {
-		struct inode *inode = file_inode(vma->vm_file);
+		struct inode *inode;
+
+		file = vma_pr_or_file(vma);
+		inode = file_inode(file);
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 		pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
index b813e3b529f2..c6cd35e5ef5d 100644
--- a/fs/proc/thread_self.c
+++ b/fs/proc/thread_self.c
@@ -42,7 +42,7 @@ int proc_setup_thread_self(struct super_block *s)
 	inode_lock(root_inode);
 	thread_self = d_alloc_name(s->s_root, "thread-self");
 	if (thread_self) {
-		struct inode *inode = new_inode_pseudo(s);
+		struct inode *inode = new_inode(s);
 		if (inode) {
 			inode->i_ino = thread_self_inum;
 			inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
diff --git a/fs/read_write.c b/fs/read_write.c
index e8136a72c13f..b6f5f4469bf7 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -484,6 +484,30 @@ ssize_t __vfs_write(struct file *file, const char __user *p, size_t count,
 		return -EINVAL;
 }
 
+vfs_readf_t vfs_readf(struct file *file)
+{
+	const struct file_operations *fop = file->f_op;
+
+	if (fop->read)
+		return fop->read;
+	if (fop->read_iter)
+		return new_sync_read;
+	return ERR_PTR(-ENOSYS);
+}
+EXPORT_SYMBOL_GPL(vfs_readf);
+
+vfs_writef_t vfs_writef(struct file *file)
+{
+	const struct file_operations *fop = file->f_op;
+
+	if (fop->write)
+		return fop->write;
+	if (fop->write_iter)
+		return new_sync_write;
+	return ERR_PTR(-ENOSYS);
+}
+EXPORT_SYMBOL_GPL(vfs_writef);
+
 ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
 {
 	mm_segment_t old_fs;
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 683496322aa8..4b0fed69e033 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1552,11 +1552,7 @@ void reiserfs_read_locked_inode(struct inode *inode,
 	 * set version 1, version 2 could be used too, because stat data
 	 * key is the same in both versions
 	 */
-	key.version = KEY_FORMAT_3_5;
-	key.on_disk_key.k_dir_id = dirino;
-	key.on_disk_key.k_objectid = inode->i_ino;
-	key.on_disk_key.k_offset = 0;
-	key.on_disk_key.k_type = 0;
+	_make_cpu_key(&key, KEY_FORMAT_3_5, dirino, inode->i_ino, 0, 0, 3);
 
 	/* look for the object's stat data */
 	retval = search_item(inode->i_sb, &key, &path_to_sd);
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 28f6daf371d3..57a7b9a164a2 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -665,6 +665,13 @@ reiserfs_xattr_get(struct inode *inode, const char *name, void *buffer,
 	if (get_inode_sd_version(inode) == STAT_DATA_V1)
 		return -EOPNOTSUPP;
 
+	/*
+	 * priv_root needn't be initialized during mount so allow initial
+	 * lookups to succeed.
+	 */
+	if (!REISERFS_SB(inode->i_sb)->priv_root)
+		return 0;
+
 	dentry = xattr_lookup(inode, name, XATTR_REPLACE);
 	if (IS_ERR(dentry)) {
 		err = PTR_ERR(dentry);
diff --git a/fs/romfs/storage.c b/fs/romfs/storage.c
index f86f51f99ace..1dcadd22b440 100644
--- a/fs/romfs/storage.c
+++ b/fs/romfs/storage.c
@@ -221,10 +221,8 @@ int romfs_dev_read(struct super_block *sb, unsigned long pos,
 	size_t limit;
 
 	limit = romfs_maxsize(sb);
-	if (pos >= limit)
+	if (pos >= limit || buflen > limit - pos)
 		return -EIO;
-	if (buflen > limit - pos)
-		buflen = limit - pos;
 
 #ifdef CONFIG_ROMFS_ON_MTD
 	if (sb->s_mtd)
diff --git a/fs/splice.c b/fs/splice.c
index c84ac7e97e21..3724bd22e8d4 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -837,8 +837,8 @@ EXPORT_SYMBOL(generic_splice_sendpage);
 /*
  * Attempt to initiate a splice from pipe to file.
  */
-static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
-			   loff_t *ppos, size_t len, unsigned int flags)
+long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
+		    loff_t *ppos, size_t len, unsigned int flags)
 {
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *,
 				loff_t *, size_t, unsigned int);
@@ -850,13 +850,14 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 
 	return splice_write(pipe, out, ppos, len, flags);
 }
+EXPORT_SYMBOL_GPL(do_splice_from);
 
 /*
  * Attempt to initiate a splice from a file to a pipe.
  */
-static long do_splice_to(struct file *in, loff_t *ppos,
-			 struct pipe_inode_info *pipe, size_t len,
-			 unsigned int flags)
+long do_splice_to(struct file *in, loff_t *ppos,
+		  struct pipe_inode_info *pipe, size_t len,
+		  unsigned int flags)
 {
 	ssize_t (*splice_read)(struct file *, loff_t *,
 			       struct pipe_inode_info *, size_t, unsigned int);
@@ -879,6 +880,7 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 
 	return splice_read(in, ppos, pipe, len, flags);
 }
+EXPORT_SYMBOL_GPL(do_splice_to);
 
 /**
  * splice_direct_to_actor - splices data directly between two non-pipes
diff --git a/fs/sync.c b/fs/sync.c
index 83ac79a960dd..e3386eabba81 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -28,7 +28,7 @@
  * wait == 1 case since in that case write_inode() functions do
  * sync_dirty_buffer() and thus effectively write one block at a time.
  */
-static int __sync_filesystem(struct super_block *sb, int wait)
+int __sync_filesystem(struct super_block *sb, int wait)
 {
 	if (wait)
 		sync_inodes_sb(sb);
@@ -39,6 +39,7 @@ static int __sync_filesystem(struct super_block *sb, int wait)
 		sb->s_op->sync_fs(sb, wait);
 	return __sync_blockdev(sb->s_bdev, wait);
 }
+EXPORT_SYMBOL_GPL(__sync_filesystem);
 
 /*
  * Write out and wait upon all dirty data associated with this
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index 3be28900bf37..135e95950f51 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -237,7 +237,7 @@ int ubifs_is_mapped(const struct ubifs_info *c, int lnum)
 int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum,
 		     int offs, int quiet, int must_chk_crc)
 {
-	int err = -EINVAL, type, node_len;
+	int err = -EINVAL, type, node_len, dump_node = 1;
 	uint32_t crc, node_crc, magic;
 	const struct ubifs_ch *ch = buf;
 
@@ -290,10 +290,22 @@ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum,
 out_len:
 	if (!quiet)
 		ubifs_err(c, "bad node length %d", node_len);
+	if (type == UBIFS_DATA_NODE && node_len > UBIFS_DATA_NODE_SZ)
+		dump_node = 0;
 out:
 	if (!quiet) {
 		ubifs_err(c, "bad node at LEB %d:%d", lnum, offs);
-		ubifs_dump_node(c, buf);
+		if (dump_node) {
+			ubifs_dump_node(c, buf);
+		} else {
+			int safe_len = min3(node_len, c->leb_size - offs,
+				(int)UBIFS_MAX_DATA_NODE_SZ);
+			pr_err("\tprevent out-of-bounds memory access\n");
+			pr_err("\ttruncated data node length      %d\n", safe_len);
+			pr_err("\tcorrupted data node:\n");
+			print_hex_dump(KERN_ERR, "\t", DUMP_PREFIX_OFFSET, 32, 1,
+					buf, safe_len, 0);
+		}
 		dump_stack();
 	}
 	return err;
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 6440003f8ddc..e3f3a0df6027 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -99,7 +99,7 @@ static struct inode *ufs_nfs_get_inode(struct super_block *sb, u64 ino, u32 gene
 	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
 	struct inode *inode;
 
-	if (ino < UFS_ROOTINO || ino > uspi->s_ncg * uspi->s_ipg)
+	if (ino < UFS_ROOTINO || ino > (u64)uspi->s_ncg * uspi->s_ipg)
 		return ERR_PTR(-ESTALE);
 
 	inode = ufs_iget(sb, ino);
diff --git a/fs/xattr.c b/fs/xattr.c
index 50029811fbe3..2086a96dfa09 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -204,10 +204,22 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
 	return error;
 }
 
-
+/**
+ * __vfs_setxattr_locked: set an extended attribute while holding the inode
+ * lock
+ *
+ *  @dentry - object to perform setxattr on
+ *  @name - xattr name to set
+ *  @value - value to set @name to
+ *  @size - size of @value
+ *  @flags - flags to pass into filesystem operations
+ *  @delegated_inode - on return, will contain an inode pointer that
+ *  a delegation was broken on, NULL if none.
+ */
 int
-vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
-		size_t size, int flags)
+__vfs_setxattr_locked(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags,
+		struct inode **delegated_inode)
 {
 	struct inode *inode = dentry->d_inode;
 	int error;
@@ -216,15 +228,40 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	if (error)
 		return error;
 
-	inode_lock(inode);
 	error = security_inode_setxattr(dentry, name, value, size, flags);
 	if (error)
 		goto out;
 
+	error = try_break_deleg(inode, delegated_inode);
+	if (error)
+		goto out;
+
 	error = __vfs_setxattr_noperm(dentry, name, value, size, flags);
 
 out:
+	return error;
+}
+EXPORT_SYMBOL_GPL(__vfs_setxattr_locked);
+
+int
+vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
+		size_t size, int flags)
+{
+	struct inode *inode = dentry->d_inode;
+	struct inode *delegated_inode = NULL;
+	int error;
+
+retry_deleg:
+	inode_lock(inode);
+	error = __vfs_setxattr_locked(dentry, name, value, size, flags,
+	    &delegated_inode);
 	inode_unlock(inode);
+
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	return error;
 }
 EXPORT_SYMBOL_GPL(vfs_setxattr);
@@ -297,6 +334,7 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value,
 	*xattr_value = value;
 	return error;
 }
+EXPORT_SYMBOL_GPL(vfs_getxattr_alloc);
 
 ssize_t
 __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name,
@@ -380,8 +418,18 @@ __vfs_removexattr(struct dentry *dentry, const char *name)
 }
 EXPORT_SYMBOL(__vfs_removexattr);
 
+/**
+ * __vfs_removexattr_locked: set an extended attribute while holding the inode
+ * lock
+ *
+ *  @dentry - object to perform setxattr on
+ *  @name - name of xattr to remove
+ *  @delegated_inode - on return, will contain an inode pointer that
+ *  a delegation was broken on, NULL if none.
+ */
 int
-vfs_removexattr(struct dentry *dentry, const char *name)
+__vfs_removexattr_locked(struct dentry *dentry, const char *name,
+		struct inode **delegated_inode)
 {
 	struct inode *inode = dentry->d_inode;
 	int error;
@@ -390,11 +438,14 @@ vfs_removexattr(struct dentry *dentry, const char *name)
 	if (error)
 		return error;
 
-	inode_lock(inode);
 	error = security_inode_removexattr(dentry, name);
 	if (error)
 		goto out;
 
+	error = try_break_deleg(inode, delegated_inode);
+	if (error)
+		goto out;
+
 	error = __vfs_removexattr(dentry, name);
 
 	if (!error) {
@@ -403,12 +454,32 @@ vfs_removexattr(struct dentry *dentry, const char *name)
 	}
 
 out:
+	return error;
+}
+EXPORT_SYMBOL_GPL(__vfs_removexattr_locked);
+
+int
+vfs_removexattr(struct dentry *dentry, const char *name)
+{
+	struct inode *inode = dentry->d_inode;
+	struct inode *delegated_inode = NULL;
+	int error;
+
+retry_deleg:
+	inode_lock(inode);
+	error = __vfs_removexattr_locked(dentry, name, &delegated_inode);
 	inode_unlock(inode);
+
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
+
 	return error;
 }
 EXPORT_SYMBOL_GPL(vfs_removexattr);
 
-
 /*
  * Extended attribute SET operations
  */
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 516e0c57cf9c..a10d9a3c181e 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2529,6 +2529,13 @@ xfs_agf_verify(
 	      be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp)))
 		return false;
 
+	if (be32_to_cpu(agf->agf_length) > mp->m_sb.sb_dblocks)
+		return false;
+
+	if (be32_to_cpu(agf->agf_freeblks) < be32_to_cpu(agf->agf_longest) ||
+	    be32_to_cpu(agf->agf_freeblks) > be32_to_cpu(agf->agf_length))
+		return false;
+
 	if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 ||
 	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) < 1 ||
 	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > XFS_BTREE_MAXLEVELS ||
@@ -2540,6 +2547,10 @@ xfs_agf_verify(
 	     be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > XFS_BTREE_MAXLEVELS))
 		return false;
 
+	if (xfs_sb_version_hasrmapbt(&mp->m_sb) &&
+	    be32_to_cpu(agf->agf_rmap_blocks) > be32_to_cpu(agf->agf_length))
+		return false;
+
 	/*
 	 * during growfs operations, the perag is not fully initialised,
 	 * so we can't use it for any useful checking. growfs ensures we can't
@@ -2554,6 +2565,11 @@ xfs_agf_verify(
 		return false;
 
 	if (xfs_sb_version_hasreflink(&mp->m_sb) &&
+	    be32_to_cpu(agf->agf_refcount_blocks) >
+	    be32_to_cpu(agf->agf_length))
+		return false;
+
+	if (xfs_sb_version_hasreflink(&mp->m_sb) &&
 	    (be32_to_cpu(agf->agf_refcount_level) < 1 ||
 	     be32_to_cpu(agf->agf_refcount_level) > XFS_BTREE_MAXLEVELS))
 		return false;
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 73a541755d5b..facb83031ba7 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -520,8 +520,8 @@ xfs_attr_shortform_create(xfs_da_args_t *args)
 		ASSERT(ifp->if_flags & XFS_IFINLINE);
 	}
 	xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
-	hdr = (xfs_attr_sf_hdr_t *)ifp->if_u1.if_data;
-	hdr->count = 0;
+	hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data;
+	memset(hdr, 0, sizeof(*hdr));
 	hdr->totsize = cpu_to_be16(sizeof(*hdr));
 	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA);
 }
@@ -1335,7 +1335,9 @@ xfs_attr3_leaf_add_work(
 	for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
 		if (ichdr->freemap[i].base == tmp) {
 			ichdr->freemap[i].base += sizeof(xfs_attr_leaf_entry_t);
-			ichdr->freemap[i].size -= sizeof(xfs_attr_leaf_entry_t);
+			ichdr->freemap[i].size -=
+				min_t(uint16_t, ichdr->freemap[i].size,
+						sizeof(xfs_attr_leaf_entry_t));
 		}
 	}
 	ichdr->usedbytes += xfs_attr_leaf_entsize(leaf, args->index);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 84245d210182..2b07dadc5916 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -761,12 +761,16 @@ xfs_bmap_extents_to_btree(
 	*logflagsp = 0;
 	if ((error = xfs_alloc_vextent(&args))) {
 		xfs_iroot_realloc(ip, -1, whichfork);
+		ASSERT(ifp->if_broot == NULL);
+		XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
 		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
 		return error;
 	}
 
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
 		xfs_iroot_realloc(ip, -1, whichfork);
+		ASSERT(ifp->if_broot == NULL);
+		XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
 		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
 		return -ENOSPC;
 	}
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 682e2bf370c7..ee4ebc2dd749 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -212,6 +212,7 @@ __xfs_dir3_free_read(
 		xfs_buf_ioerror(*bpp, -EFSCORRUPTED);
 		xfs_verifier_error(*bpp);
 		xfs_trans_brelse(tp, *bpp);
+		*bpp = NULL;
 		return -EFSCORRUPTED;
 	}
 
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 360e32220f93..0c0f70e6c7d9 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -2684,7 +2684,6 @@ xlog_state_do_callback(
 	int		   funcdidcallbacks; /* flag: function did callbacks */
 	int		   repeats;	/* for issuing console warnings if
 					 * looping too many times */
-	int		   wake = 0;
 
 	spin_lock(&log->l_icloglock);
 	first_iclog = iclog = log->l_iclog;
@@ -2886,11 +2885,9 @@ xlog_state_do_callback(
 #endif
 
 	if (log->l_iclog->ic_state & (XLOG_STATE_ACTIVE|XLOG_STATE_IOERROR))
-		wake = 1;
-	spin_unlock(&log->l_icloglock);
-
-	if (wake)
 		wake_up_all(&log->l_flush_wait);
+
+	spin_unlock(&log->l_icloglock);
 }
 
 
@@ -4052,7 +4049,9 @@ xfs_log_force_umount(
 	 * item committed callback functions will do this again under lock to
 	 * avoid races.
 	 */
+	spin_lock(&log->l_cilp->xc_push_lock);
 	wake_up_all(&log->l_cilp->xc_commit_wait);
+	spin_unlock(&log->l_cilp->xc_push_lock);
 	xlog_state_do_callback(log, XFS_LI_ABORTED, NULL);
 
 #ifdef XFSERRORDEBUG
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index db7f9fdd20a3..4d37f1b59436 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1076,6 +1076,7 @@ xfs_reflink_remap_extent(
 	xfs_filblks_t		rlen;
 	xfs_filblks_t		unmap_len;
 	xfs_off_t		newlen;
+	int64_t			qres;
 	int			error;
 
 	unmap_len = irec->br_startoff + irec->br_blockcount - destoff;
@@ -1098,13 +1099,19 @@ xfs_reflink_remap_extent(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	/* If we're not just clearing space, then do we have enough quota? */
-	if (real_extent) {
-		error = xfs_trans_reserve_quota_nblks(tp, ip,
-				irec->br_blockcount, 0, XFS_QMOPT_RES_REGBLKS);
-		if (error)
-			goto out_cancel;
-	}
+	/*
+	 * Reserve quota for this operation.  We don't know if the first unmap
+	 * in the dest file will cause a bmap btree split, so we always reserve
+	 * at least enough blocks for that split.  If the extent being mapped
+	 * in is written, we need to reserve quota for that too.
+	 */
+	qres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
+	if (real_extent)
+		qres += irec->br_blockcount;
+	error = xfs_trans_reserve_quota_nblks(tp, ip, qres, 0,
+			XFS_QMOPT_RES_REGBLKS);
+	if (error)
+		goto out_cancel;
 
 	trace_xfs_reflink_remap(ip, irec->br_startoff,
 				irec->br_blockcount, irec->br_startblock);
diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h
index d04637181ef2..980c9429abec 100644
--- a/fs/xfs/xfs_sysfs.h
+++ b/fs/xfs/xfs_sysfs.h
@@ -44,9 +44,11 @@ xfs_sysfs_init(
 	struct xfs_kobj		*parent_kobj,
 	const char		*name)
 {
+	struct kobject		*parent;
+
+	parent = parent_kobj ? &parent_kobj->kobject : NULL;
 	init_completion(&kobj->complete);
-	return kobject_init_and_add(&kobj->kobject, ktype,
-				    &parent_kobj->kobject, "%s", name);
+	return kobject_init_and_add(&kobj->kobject, ktype, parent, "%s", name);
 }
 
 static inline void
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index c3d547211d16..9c42e50a5cb7 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -669,7 +669,7 @@ xfs_trans_dqresv(
 			}
 		}
 		if (ninos > 0) {
-			total_count = be64_to_cpu(dqp->q_core.d_icount) + ninos;
+			total_count = dqp->q_res_icount + ninos;
 			timer = be32_to_cpu(dqp->q_core.d_itimer);
 			warns = be16_to_cpu(dqp->q_core.d_iwarns);
 			warnlimit = dqp->q_mount->m_quotainfo->qi_iwarnlimit;
diff --git a/fs/yaffs2/Kconfig b/fs/yaffs2/Kconfig
new file mode 100644
index 000000000000..408570fc7a5e
--- /dev/null
+++ b/fs/yaffs2/Kconfig
@@ -0,0 +1,171 @@
+#
+# yaffs file system configurations
+#
+
+config YAFFS_FS
+	tristate "yaffs2 file system support"
+	default n
+	depends on MTD_BLOCK
+	select YAFFS_YAFFS1
+	select YAFFS_YAFFS2
+	help
+	  yaffs2, or Yet Another Flash File System, is a file system
+	  optimised for NAND Flash chips.
+
+	  To compile the yaffs2 file system support as a module, choose M
+	  here: the module will be called yaffs2.
+
+	  If unsure, say N.
+
+	  Further information on yaffs2 is available at
+	  <http://www.aleph1.co.uk/yaffs/>.
+
+config YAFFS_YAFFS1
+	bool "512 byte / page devices"
+	depends on YAFFS_FS
+	default y
+	help
+	  Enable yaffs1 support -- yaffs for 512 byte / page devices
+
+	  Not needed for 2K-page devices.
+
+	  If unsure, say Y.
+
+config YAFFS_9BYTE_TAGS
+	bool "Use older-style on-NAND data format with pageStatus byte"
+	depends on YAFFS_YAFFS1
+	default n
+	help
+
+	  Older-style on-NAND data format has a "pageStatus" byte to record
+	  chunk/page state.  This byte is zero when the page is discarded.
+	  Choose this option if you have existing on-NAND data using this
+	  format that you need to continue to support.  New data written
+	  also uses the older-style format.  Note: Use of this option
+	  generally requires that MTD's oob layout be adjusted to use the
+	  older-style format.  See notes on tags formats and MTD versions
+	  in yaffs_mtdif1.c.
+
+	  If unsure, say N.
+
+config YAFFS_DOES_ECC
+	bool "Lets yaffs do its own ECC"
+	depends on YAFFS_FS && YAFFS_YAFFS1 && !YAFFS_9BYTE_TAGS
+	default n
+	help
+	  This enables yaffs to use its own ECC functions instead of using
+	  the ones from the generic MTD-NAND driver.
+
+	  If unsure, say N.
+
+config YAFFS_ECC_WRONG_ORDER
+	bool "Use the same ecc byte order as Steven Hill's nand_ecc.c"
+	depends on YAFFS_FS && YAFFS_DOES_ECC && !YAFFS_9BYTE_TAGS
+	default n
+	help
+	  This makes yaffs_ecc.c use the same ecc byte order as Steven
+	  Hill's nand_ecc.c. If not set, then you get the same ecc byte
+	  order as SmartMedia.
+
+	  If unsure, say N.
+
+config YAFFS_YAFFS2
+	bool "2048 byte (or larger) / page devices"
+	depends on YAFFS_FS
+	default y
+	help
+	  Enable yaffs2 support -- yaffs for >= 2K bytes per page devices
+
+	  If unsure, say Y.
+
+config YAFFS_AUTO_YAFFS2
+	bool "Autoselect yaffs2 format"
+	depends on YAFFS_YAFFS2
+	default y
+	help
+	  Without this, you need to explicitely use yaffs2 as the file
+	  system type. With this, you can say "yaffs" and yaffs or yaffs2
+	  will be used depending on the device page size (yaffs on
+	  512-byte page devices, yaffs2 on 2K page devices).
+
+	  If unsure, say Y.
+
+config YAFFS_DISABLE_TAGS_ECC
+	bool "Disable yaffs from doing ECC on tags by default"
+	depends on YAFFS_FS && YAFFS_YAFFS2
+	default n
+	help
+	  This defaults yaffs to using its own ECC calculations on tags instead of
+	  just relying on the MTD.
+	  This behavior can also be overridden with tags_ecc_on and
+	  tags_ecc_off mount options.
+
+	  If unsure, say N.
+
+config YAFFS_ALWAYS_CHECK_CHUNK_ERASED
+	bool "Force chunk erase check"
+	depends on YAFFS_FS
+	default n
+	help
+          Normally yaffs only checks chunks before writing until an erased
+	  chunk is found. This helps to detect any partially written
+	  chunks that might have happened due to power loss.
+
+	  Enabling this forces on the test that chunks are erased in flash
+	  before writing to them. This takes more time but is potentially
+	  a bit more secure.
+
+	  Suggest setting Y during development and ironing out driver
+	  issues etc. Suggest setting to N if you want faster writing.
+
+	  If unsure, say Y.
+
+config YAFFS_EMPTY_LOST_AND_FOUND
+	bool "Empty lost and found on boot"
+	depends on YAFFS_FS
+	default n
+	help
+	  If this is enabled then the contents of lost and found is
+	  automatically dumped at mount.
+
+	  If unsure, say N.
+
+config YAFFS_DISABLE_BLOCK_REFRESHING
+	bool "Disable yaffs2 block refreshing"
+	depends on YAFFS_FS
+	default n
+	help
+	 If this is set, then block refreshing is disabled.
+	 Block refreshing infrequently refreshes the oldest block in
+	 a yaffs2 file system. This mechanism helps to refresh flash to
+	 mitigate against data loss. This is particularly useful for MLC.
+
+	  If unsure, say N.
+
+config YAFFS_DISABLE_BACKGROUND
+	bool "Disable yaffs2 background processing"
+	depends on YAFFS_FS
+	default n
+	help
+	 If this is set, then background processing is disabled.
+	 Background processing makes many foreground activities faster.
+
+	 If unsure, say N.
+
+config YAFFS_DISABLE_BAD_BLOCK_MARKING
+	bool "Disable yaffs2 bad block marking"
+	depends on YAFFS_FS
+	default n
+	help
+	 Useful during early flash bring up to prevent problems causing
+	 lots of bad block marking.
+
+	 If unsure, say N.
+
+config YAFFS_XATTR
+	bool "Enable yaffs2 xattr support"
+	depends on YAFFS_FS
+	default y
+	help
+	 If this is set then yaffs2 will provide xattr support.
+	 If unsure, say Y.
diff --git a/fs/yaffs2/Makefile b/fs/yaffs2/Makefile
new file mode 100644
index 000000000000..f9a9fb1bfdd4
--- /dev/null
+++ b/fs/yaffs2/Makefile
@@ -0,0 +1,18 @@
+#
+# Makefile for the linux YAFFS filesystem routines.
+#
+
+obj-$(CONFIG_YAFFS_FS) += yaffs.o
+
+yaffs-y := yaffs_ecc.o yaffs_vfs.o yaffs_guts.o yaffs_checkptrw.o
+yaffs-y += yaffs_packedtags1.o yaffs_packedtags2.o yaffs_nand.o
+yaffs-y += yaffs_tagscompat.o yaffs_tagsmarshall.o
+yaffs-y += yaffs_mtdif.o
+yaffs-y += yaffs_nameval.o yaffs_attribs.o
+yaffs-y += yaffs_allocator.o
+yaffs-y += yaffs_yaffs1.o
+yaffs-y += yaffs_yaffs2.o
+yaffs-y += yaffs_bitmap.o
+yaffs-y += yaffs_summary.o
+yaffs-y += yaffs_verify.o
+
diff --git a/fs/yaffs2/yaffs_allocator.c b/fs/yaffs2/yaffs_allocator.c
new file mode 100644
index 000000000000..c8f2861c53ee
--- /dev/null
+++ b/fs/yaffs2/yaffs_allocator.c
@@ -0,0 +1,357 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_allocator.h"
+#include "yaffs_guts.h"
+#include "yaffs_trace.h"
+#include "yportenv.h"
+
+/*
+ * Each entry in yaffs_tnode_list and yaffs_obj_list hold blocks
+ * of approx 100 objects that are themn allocated singly.
+ * This is basically a simplified slab allocator.
+ *
+ * We don't use the Linux slab allocator because slab does not allow
+ * us to dump all the objects in one hit when we do a umount and tear
+ * down  all the tnodes and objects. slab requires that we first free
+ * the individual objects.
+ *
+ * Once yaffs has been mainlined I shall try to motivate for a change
+ * to slab to provide the extra features we need here.
+ */
+
+struct yaffs_tnode_list {
+	struct yaffs_tnode_list *next;
+	struct yaffs_tnode *tnodes;
+};
+
+struct yaffs_obj_list {
+	struct yaffs_obj_list *next;
+	struct yaffs_obj *objects;
+};
+
+struct yaffs_allocator {
+	int n_tnodes_created;
+	struct yaffs_tnode *free_tnodes;
+	int n_free_tnodes;
+	struct yaffs_tnode_list *alloc_tnode_list;
+
+	int n_obj_created;
+	struct list_head free_objs;
+	int n_free_objects;
+
+	struct yaffs_obj_list *allocated_obj_list;
+};
+
+static void yaffs_deinit_raw_tnodes(struct yaffs_dev *dev)
+{
+	struct yaffs_allocator *allocator =
+	    (struct yaffs_allocator *)dev->allocator;
+	struct yaffs_tnode_list *tmp;
+
+	if (!allocator) {
+		BUG();
+		return;
+	}
+
+	while (allocator->alloc_tnode_list) {
+		tmp = allocator->alloc_tnode_list->next;
+
+		kfree(allocator->alloc_tnode_list->tnodes);
+		kfree(allocator->alloc_tnode_list);
+		allocator->alloc_tnode_list = tmp;
+	}
+
+	allocator->free_tnodes = NULL;
+	allocator->n_free_tnodes = 0;
+	allocator->n_tnodes_created = 0;
+}
+
+static void yaffs_init_raw_tnodes(struct yaffs_dev *dev)
+{
+	struct yaffs_allocator *allocator = dev->allocator;
+
+	if (!allocator) {
+		BUG();
+		return;
+	}
+
+	allocator->alloc_tnode_list = NULL;
+	allocator->free_tnodes = NULL;
+	allocator->n_free_tnodes = 0;
+	allocator->n_tnodes_created = 0;
+}
+
+static int yaffs_create_tnodes(struct yaffs_dev *dev, int n_tnodes)
+{
+	struct yaffs_allocator *allocator =
+	    (struct yaffs_allocator *)dev->allocator;
+	int i;
+	struct yaffs_tnode *new_tnodes;
+	u8 *mem;
+	struct yaffs_tnode *curr;
+	struct yaffs_tnode *next;
+	struct yaffs_tnode_list *tnl;
+
+	if (!allocator) {
+		BUG();
+		return YAFFS_FAIL;
+	}
+
+	if (n_tnodes < 1)
+		return YAFFS_OK;
+
+	/* make these things */
+	new_tnodes = kmalloc(n_tnodes * dev->tnode_size, GFP_NOFS);
+	mem = (u8 *) new_tnodes;
+
+	if (!new_tnodes) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"yaffs: Could not allocate Tnodes");
+		return YAFFS_FAIL;
+	}
+
+	/* New hookup for wide tnodes */
+	for (i = 0; i < n_tnodes - 1; i++) {
+		curr = (struct yaffs_tnode *)&mem[i * dev->tnode_size];
+		next = (struct yaffs_tnode *)&mem[(i + 1) * dev->tnode_size];
+		curr->internal[0] = next;
+	}
+
+	curr = (struct yaffs_tnode *)&mem[(n_tnodes - 1) * dev->tnode_size];
+	curr->internal[0] = allocator->free_tnodes;
+	allocator->free_tnodes = (struct yaffs_tnode *)mem;
+
+	allocator->n_free_tnodes += n_tnodes;
+	allocator->n_tnodes_created += n_tnodes;
+
+	/* Now add this bunch of tnodes to a list for freeing up.
+	 * NB If we can't add this to the management list it isn't fatal
+	 * but it just means we can't free this bunch of tnodes later.
+	 */
+	tnl = kmalloc(sizeof(struct yaffs_tnode_list), GFP_NOFS);
+	if (!tnl) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"Could not add tnodes to management list");
+		return YAFFS_FAIL;
+	} else {
+		tnl->tnodes = new_tnodes;
+		tnl->next = allocator->alloc_tnode_list;
+		allocator->alloc_tnode_list = tnl;
+	}
+
+	yaffs_trace(YAFFS_TRACE_ALLOCATE, "Tnodes added");
+
+	return YAFFS_OK;
+}
+
+struct yaffs_tnode *yaffs_alloc_raw_tnode(struct yaffs_dev *dev)
+{
+	struct yaffs_allocator *allocator =
+	    (struct yaffs_allocator *)dev->allocator;
+	struct yaffs_tnode *tn = NULL;
+
+	if (!allocator) {
+		BUG();
+		return NULL;
+	}
+
+	/* If there are none left make more */
+	if (!allocator->free_tnodes)
+		yaffs_create_tnodes(dev, YAFFS_ALLOCATION_NTNODES);
+
+	if (allocator->free_tnodes) {
+		tn = allocator->free_tnodes;
+		allocator->free_tnodes = allocator->free_tnodes->internal[0];
+		allocator->n_free_tnodes--;
+	}
+
+	return tn;
+}
+
+/* FreeTnode frees up a tnode and puts it back on the free list */
+void yaffs_free_raw_tnode(struct yaffs_dev *dev, struct yaffs_tnode *tn)
+{
+	struct yaffs_allocator *allocator = dev->allocator;
+
+	if (!allocator) {
+		BUG();
+		return;
+	}
+
+	if (tn) {
+		tn->internal[0] = allocator->free_tnodes;
+		allocator->free_tnodes = tn;
+		allocator->n_free_tnodes++;
+	}
+	dev->checkpoint_blocks_required = 0;	/* force recalculation */
+}
+
+/*--------------- yaffs_obj alloaction ------------------------
+ *
+ * Free yaffs_objs are stored in a list using obj->siblings.
+ * The blocks of allocated objects are stored in a linked list.
+ */
+
+static void yaffs_init_raw_objs(struct yaffs_dev *dev)
+{
+	struct yaffs_allocator *allocator = dev->allocator;
+
+	if (!allocator) {
+		BUG();
+		return;
+	}
+
+	allocator->allocated_obj_list = NULL;
+	INIT_LIST_HEAD(&allocator->free_objs);
+	allocator->n_free_objects = 0;
+}
+
+static void yaffs_deinit_raw_objs(struct yaffs_dev *dev)
+{
+	struct yaffs_allocator *allocator = dev->allocator;
+	struct yaffs_obj_list *tmp;
+
+	if (!allocator) {
+		BUG();
+		return;
+	}
+
+	while (allocator->allocated_obj_list) {
+		tmp = allocator->allocated_obj_list->next;
+		kfree(allocator->allocated_obj_list->objects);
+		kfree(allocator->allocated_obj_list);
+		allocator->allocated_obj_list = tmp;
+	}
+
+	INIT_LIST_HEAD(&allocator->free_objs);
+	allocator->n_free_objects = 0;
+	allocator->n_obj_created = 0;
+}
+
+static int yaffs_create_free_objs(struct yaffs_dev *dev, int n_obj)
+{
+	struct yaffs_allocator *allocator = dev->allocator;
+	int i;
+	struct yaffs_obj *new_objs;
+	struct yaffs_obj_list *list;
+
+	if (!allocator) {
+		BUG();
+		return YAFFS_FAIL;
+	}
+
+	if (n_obj < 1)
+		return YAFFS_OK;
+
+	/* make these things */
+	new_objs = kmalloc(n_obj * sizeof(struct yaffs_obj), GFP_NOFS);
+	list = kmalloc(sizeof(struct yaffs_obj_list), GFP_NOFS);
+
+	if (!new_objs || !list) {
+		kfree(new_objs);
+		new_objs = NULL;
+		kfree(list);
+		list = NULL;
+		yaffs_trace(YAFFS_TRACE_ALLOCATE,
+			"Could not allocate more objects");
+		return YAFFS_FAIL;
+	}
+
+	/* Hook them into the free list */
+	for (i = 0; i < n_obj; i++)
+		list_add(&new_objs[i].siblings, &allocator->free_objs);
+
+	allocator->n_free_objects += n_obj;
+	allocator->n_obj_created += n_obj;
+
+	/* Now add this bunch of Objects to a list for freeing up. */
+
+	list->objects = new_objs;
+	list->next = allocator->allocated_obj_list;
+	allocator->allocated_obj_list = list;
+
+	return YAFFS_OK;
+}
+
+struct yaffs_obj *yaffs_alloc_raw_obj(struct yaffs_dev *dev)
+{
+	struct yaffs_obj *obj = NULL;
+	struct list_head *lh;
+	struct yaffs_allocator *allocator = dev->allocator;
+
+	if (!allocator) {
+		BUG();
+		return obj;
+	}
+
+	/* If there are none left make more */
+	if (list_empty(&allocator->free_objs))
+		yaffs_create_free_objs(dev, YAFFS_ALLOCATION_NOBJECTS);
+
+	if (!list_empty(&allocator->free_objs)) {
+		lh = allocator->free_objs.next;
+		obj = list_entry(lh, struct yaffs_obj, siblings);
+		list_del_init(lh);
+		allocator->n_free_objects--;
+	}
+
+	return obj;
+}
+
+void yaffs_free_raw_obj(struct yaffs_dev *dev, struct yaffs_obj *obj)
+{
+
+	struct yaffs_allocator *allocator = dev->allocator;
+
+	if (!allocator) {
+		BUG();
+		return;
+	}
+
+	/* Link into the free list. */
+	list_add(&obj->siblings, &allocator->free_objs);
+	allocator->n_free_objects++;
+}
+
+void yaffs_deinit_raw_tnodes_and_objs(struct yaffs_dev *dev)
+{
+
+	if (!dev->allocator) {
+		BUG();
+		return;
+	}
+
+	yaffs_deinit_raw_tnodes(dev);
+	yaffs_deinit_raw_objs(dev);
+	kfree(dev->allocator);
+	dev->allocator = NULL;
+}
+
+void yaffs_init_raw_tnodes_and_objs(struct yaffs_dev *dev)
+{
+	struct yaffs_allocator *allocator;
+
+	if (dev->allocator) {
+		BUG();
+		return;
+	}
+
+	allocator = kmalloc(sizeof(struct yaffs_allocator), GFP_NOFS);
+	if (allocator) {
+		dev->allocator = allocator;
+		yaffs_init_raw_tnodes(dev);
+		yaffs_init_raw_objs(dev);
+	}
+}
+
diff --git a/fs/yaffs2/yaffs_allocator.h b/fs/yaffs2/yaffs_allocator.h
new file mode 100644
index 000000000000..a8cc3226421f
--- /dev/null
+++ b/fs/yaffs2/yaffs_allocator.h
@@ -0,0 +1,30 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_ALLOCATOR_H__
+#define __YAFFS_ALLOCATOR_H__
+
+#include "yaffs_guts.h"
+
+void yaffs_init_raw_tnodes_and_objs(struct yaffs_dev *dev);
+void yaffs_deinit_raw_tnodes_and_objs(struct yaffs_dev *dev);
+
+struct yaffs_tnode *yaffs_alloc_raw_tnode(struct yaffs_dev *dev);
+void yaffs_free_raw_tnode(struct yaffs_dev *dev, struct yaffs_tnode *tn);
+
+struct yaffs_obj *yaffs_alloc_raw_obj(struct yaffs_dev *dev);
+void yaffs_free_raw_obj(struct yaffs_dev *dev, struct yaffs_obj *obj);
+
+#endif
diff --git a/fs/yaffs2/yaffs_attribs.c b/fs/yaffs2/yaffs_attribs.c
new file mode 100644
index 000000000000..fdc7f2162ce6
--- /dev/null
+++ b/fs/yaffs2/yaffs_attribs.c
@@ -0,0 +1,124 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_guts.h"
+#include "yaffs_attribs.h"
+
+void yaffs_load_attribs(struct yaffs_obj *obj, struct yaffs_obj_hdr *oh)
+{
+	obj->yst_uid = oh->yst_uid;
+	obj->yst_gid = oh->yst_gid;
+	obj->yst_atime = oh->yst_atime;
+	obj->yst_mtime = oh->yst_mtime;
+	obj->yst_ctime = oh->yst_ctime;
+	obj->yst_rdev = oh->yst_rdev;
+}
+
+void yaffs_load_attribs_oh(struct yaffs_obj_hdr *oh, struct yaffs_obj *obj)
+{
+	oh->yst_uid = obj->yst_uid;
+	oh->yst_gid = obj->yst_gid;
+	oh->yst_atime = obj->yst_atime;
+	oh->yst_mtime = obj->yst_mtime;
+	oh->yst_ctime = obj->yst_ctime;
+	oh->yst_rdev = obj->yst_rdev;
+
+}
+
+void yaffs_load_current_time(struct yaffs_obj *obj, int do_a, int do_c)
+{
+	obj->yst_mtime = Y_CURRENT_TIME;
+	if (do_a)
+		obj->yst_atime = obj->yst_mtime;
+	if (do_c)
+		obj->yst_ctime = obj->yst_mtime;
+}
+
+void yaffs_attribs_init(struct yaffs_obj *obj, u32 gid, u32 uid, u32 rdev)
+{
+	yaffs_load_current_time(obj, 1, 1);
+	obj->yst_rdev = rdev;
+	obj->yst_uid = uid;
+	obj->yst_gid = gid;
+}
+
+static loff_t yaffs_get_file_size(struct yaffs_obj *obj)
+{
+	YCHAR *alias = NULL;
+	obj = yaffs_get_equivalent_obj(obj);
+
+	switch (obj->variant_type) {
+	case YAFFS_OBJECT_TYPE_FILE:
+		return obj->variant.file_variant.file_size;
+	case YAFFS_OBJECT_TYPE_SYMLINK:
+		alias = obj->variant.symlink_variant.alias;
+		if (!alias)
+			return 0;
+		return strnlen(alias, YAFFS_MAX_ALIAS_LENGTH);
+	default:
+		return 0;
+	}
+}
+
+int yaffs_set_attribs(struct yaffs_obj *obj, struct iattr *attr)
+{
+	unsigned int valid = attr->ia_valid;
+
+	if (valid & ATTR_MODE)
+		obj->yst_mode = attr->ia_mode;
+	if (valid & ATTR_UID)
+		obj->yst_uid = ia_uid_read(attr);
+	if (valid & ATTR_GID)
+		obj->yst_gid = ia_gid_read(attr);
+
+	if (valid & ATTR_ATIME)
+		obj->yst_atime = Y_TIME_CONVERT(attr->ia_atime);
+	if (valid & ATTR_CTIME)
+		obj->yst_ctime = Y_TIME_CONVERT(attr->ia_ctime);
+	if (valid & ATTR_MTIME)
+		obj->yst_mtime = Y_TIME_CONVERT(attr->ia_mtime);
+
+	if (valid & ATTR_SIZE)
+		yaffs_resize_file(obj, attr->ia_size);
+
+	yaffs_update_oh(obj, NULL, 1, 0, 0, NULL);
+
+	return YAFFS_OK;
+
+}
+
+int yaffs_get_attribs(struct yaffs_obj *obj, struct iattr *attr)
+{
+	unsigned int valid = 0;
+
+	attr->ia_mode = obj->yst_mode;
+	valid |= ATTR_MODE;
+	ia_uid_write( attr, obj->yst_uid );
+	valid |= ATTR_UID;
+	ia_gid_write( attr, obj->yst_gid );
+	valid |= ATTR_GID;
+
+	Y_TIME_CONVERT(attr->ia_atime) = obj->yst_atime;
+	valid |= ATTR_ATIME;
+	Y_TIME_CONVERT(attr->ia_ctime) = obj->yst_ctime;
+	valid |= ATTR_CTIME;
+	Y_TIME_CONVERT(attr->ia_mtime) = obj->yst_mtime;
+	valid |= ATTR_MTIME;
+
+	attr->ia_size = yaffs_get_file_size(obj);
+	valid |= ATTR_SIZE;
+
+	attr->ia_valid = valid;
+
+	return YAFFS_OK;
+}
diff --git a/fs/yaffs2/yaffs_attribs.h b/fs/yaffs2/yaffs_attribs.h
new file mode 100644
index 000000000000..121d99d38b48
--- /dev/null
+++ b/fs/yaffs2/yaffs_attribs.h
@@ -0,0 +1,71 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_ATTRIBS_H__
+#define __YAFFS_ATTRIBS_H__
+
+#include "yaffs_guts.h"
+
+void yaffs_load_attribs(struct yaffs_obj *obj, struct yaffs_obj_hdr *oh);
+void yaffs_load_attribs_oh(struct yaffs_obj_hdr *oh, struct yaffs_obj *obj);
+void yaffs_attribs_init(struct yaffs_obj *obj, u32 gid, u32 uid, u32 rdev);
+void yaffs_load_current_time(struct yaffs_obj *obj, int do_a, int do_c);
+int yaffs_set_attribs(struct yaffs_obj *obj, struct iattr *attr);
+int yaffs_get_attribs(struct yaffs_obj *obj, struct iattr *attr);
+
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 5, 0))
+static inline uid_t ia_uid_read(const struct iattr *iattr)
+{
+	return from_kuid(&init_user_ns, iattr->ia_uid);
+}
+
+static inline gid_t ia_gid_read(const struct iattr *iattr)
+{
+	return from_kgid(&init_user_ns, iattr->ia_gid);
+}
+
+static inline void ia_uid_write(struct iattr *iattr, uid_t uid)
+{
+	iattr->ia_uid = make_kuid(&init_user_ns, uid);
+}
+
+static inline void ia_gid_write(struct iattr *iattr, gid_t gid)
+{
+	iattr->ia_gid = make_kgid(&init_user_ns, gid);
+}
+#else
+static inline uid_t ia_uid_read(const struct iattr *iattr)
+{
+	return iattr->ia_uid;
+}
+
+static inline gid_t ia_gid_read(const struct iattr *inode)
+{
+	return iattr->ia_gid;
+}
+
+static inline void ia_uid_write(struct iattr *iattr, uid_t uid)
+{
+	iattr->ia_uid = uid;
+}
+
+static inline void ia_gid_write(struct iattr *iattr, gid_t gid)
+{
+	iattr->ia_gid = gid;
+}
+#endif
+
+#endif
diff --git a/fs/yaffs2/yaffs_bitmap.c b/fs/yaffs2/yaffs_bitmap.c
new file mode 100644
index 000000000000..4440e930d6bc
--- /dev/null
+++ b/fs/yaffs2/yaffs_bitmap.c
@@ -0,0 +1,97 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_bitmap.h"
+#include "yaffs_trace.h"
+/*
+ * Chunk bitmap manipulations
+ */
+
+static inline u8 *yaffs_block_bits(struct yaffs_dev *dev, int blk)
+{
+	if (blk < dev->internal_start_block || blk > dev->internal_end_block) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"BlockBits block %d is not valid",
+			blk);
+		BUG();
+	}
+	return dev->chunk_bits +
+	    (dev->chunk_bit_stride * (blk - dev->internal_start_block));
+}
+
+void yaffs_verify_chunk_bit_id(struct yaffs_dev *dev, int blk, int chunk)
+{
+	if (blk < dev->internal_start_block || blk > dev->internal_end_block ||
+	    chunk < 0 || chunk >= dev->param.chunks_per_block) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"Chunk Id (%d:%d) invalid",
+			blk, chunk);
+		BUG();
+	}
+}
+
+void yaffs_clear_chunk_bits(struct yaffs_dev *dev, int blk)
+{
+	u8 *blk_bits = yaffs_block_bits(dev, blk);
+
+	memset(blk_bits, 0, dev->chunk_bit_stride);
+}
+
+void yaffs_clear_chunk_bit(struct yaffs_dev *dev, int blk, int chunk)
+{
+	u8 *blk_bits = yaffs_block_bits(dev, blk);
+
+	yaffs_verify_chunk_bit_id(dev, blk, chunk);
+	blk_bits[chunk / 8] &= ~(1 << (chunk & 7));
+}
+
+void yaffs_set_chunk_bit(struct yaffs_dev *dev, int blk, int chunk)
+{
+	u8 *blk_bits = yaffs_block_bits(dev, blk);
+
+	yaffs_verify_chunk_bit_id(dev, blk, chunk);
+	blk_bits[chunk / 8] |= (1 << (chunk & 7));
+}
+
+int yaffs_check_chunk_bit(struct yaffs_dev *dev, int blk, int chunk)
+{
+	u8 *blk_bits = yaffs_block_bits(dev, blk);
+
+	yaffs_verify_chunk_bit_id(dev, blk, chunk);
+	return (blk_bits[chunk / 8] & (1 << (chunk & 7))) ? 1 : 0;
+}
+
+int yaffs_still_some_chunks(struct yaffs_dev *dev, int blk)
+{
+	u8 *blk_bits = yaffs_block_bits(dev, blk);
+	int i;
+
+	for (i = 0; i < dev->chunk_bit_stride; i++) {
+		if (*blk_bits)
+			return 1;
+		blk_bits++;
+	}
+	return 0;
+}
+
+int yaffs_count_chunk_bits(struct yaffs_dev *dev, int blk)
+{
+	u8 *blk_bits = yaffs_block_bits(dev, blk);
+	int i;
+	int n = 0;
+
+	for (i = 0; i < dev->chunk_bit_stride; i++, blk_bits++)
+		n += hweight8(*blk_bits);
+
+	return n;
+}
diff --git a/fs/yaffs2/yaffs_bitmap.h b/fs/yaffs2/yaffs_bitmap.h
new file mode 100644
index 000000000000..e26b37d89ae4
--- /dev/null
+++ b/fs/yaffs2/yaffs_bitmap.h
@@ -0,0 +1,33 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+/*
+ * Chunk bitmap manipulations
+ */
+
+#ifndef __YAFFS_BITMAP_H__
+#define __YAFFS_BITMAP_H__
+
+#include "yaffs_guts.h"
+
+void yaffs_verify_chunk_bit_id(struct yaffs_dev *dev, int blk, int chunk);
+void yaffs_clear_chunk_bits(struct yaffs_dev *dev, int blk);
+void yaffs_clear_chunk_bit(struct yaffs_dev *dev, int blk, int chunk);
+void yaffs_set_chunk_bit(struct yaffs_dev *dev, int blk, int chunk);
+int yaffs_check_chunk_bit(struct yaffs_dev *dev, int blk, int chunk);
+int yaffs_still_some_chunks(struct yaffs_dev *dev, int blk);
+int yaffs_count_chunk_bits(struct yaffs_dev *dev, int blk);
+
+#endif
diff --git a/fs/yaffs2/yaffs_checkptrw.c b/fs/yaffs2/yaffs_checkptrw.c
new file mode 100644
index 000000000000..e739fb4a104b
--- /dev/null
+++ b/fs/yaffs2/yaffs_checkptrw.c
@@ -0,0 +1,474 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_checkptrw.h"
+#include "yaffs_getblockinfo.h"
+
+struct yaffs_checkpt_chunk_hdr {
+	int version;
+	int seq;
+	u32 sum;
+	u32 xor;
+} ;
+
+
+static int apply_chunk_offset(struct yaffs_dev *dev, int chunk)
+{
+	return chunk - dev->chunk_offset;
+}
+
+static int apply_block_offset(struct yaffs_dev *dev, int block)
+{
+	return block - dev->block_offset;
+}
+
+static void yaffs2_checkpt_init_chunk_hdr(struct yaffs_dev *dev)
+{
+	struct yaffs_checkpt_chunk_hdr hdr;
+
+	hdr.version = YAFFS_CHECKPOINT_VERSION;
+	hdr.seq = dev->checkpt_page_seq;
+	hdr.sum = dev->checkpt_sum;
+	hdr.xor = dev->checkpt_xor;
+
+	dev->checkpt_byte_offs = sizeof(hdr);
+
+	memcpy(dev->checkpt_buffer, &hdr, sizeof(hdr));
+}
+
+static int yaffs2_checkpt_check_chunk_hdr(struct yaffs_dev *dev)
+{
+	struct yaffs_checkpt_chunk_hdr hdr;
+
+	memcpy(&hdr, dev->checkpt_buffer, sizeof(hdr));
+
+	dev->checkpt_byte_offs = sizeof(hdr);
+
+	return hdr.version == YAFFS_CHECKPOINT_VERSION &&
+		hdr.seq == dev->checkpt_page_seq &&
+		hdr.sum == dev->checkpt_sum &&
+		hdr.xor == dev->checkpt_xor;
+}
+
+static int yaffs2_checkpt_space_ok(struct yaffs_dev *dev)
+{
+	int blocks_avail = dev->n_erased_blocks - dev->param.n_reserved_blocks;
+
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+		"checkpt blocks_avail = %d", blocks_avail);
+
+	return (blocks_avail <= 0) ? 0 : 1;
+}
+
+static int yaffs_checkpt_erase(struct yaffs_dev *dev)
+{
+	int i;
+
+	if (!dev->drv.drv_erase_fn)
+		return 0;
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+		"checking blocks %d to %d",
+		dev->internal_start_block, dev->internal_end_block);
+
+	for (i = dev->internal_start_block; i <= dev->internal_end_block; i++) {
+		struct yaffs_block_info *bi = yaffs_get_block_info(dev, i);
+		int offset_i = apply_block_offset(dev, i);
+		int result;
+
+		if (bi->block_state == YAFFS_BLOCK_STATE_CHECKPOINT) {
+			yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"erasing checkpt block %d", i);
+
+			dev->n_erasures++;
+
+			result = dev->drv.drv_erase_fn(dev, offset_i);
+			if(result) {
+				bi->block_state = YAFFS_BLOCK_STATE_EMPTY;
+				dev->n_erased_blocks++;
+				dev->n_free_chunks +=
+				    dev->param.chunks_per_block;
+			} else {
+				dev->drv.drv_mark_bad_fn(dev, offset_i);
+				bi->block_state = YAFFS_BLOCK_STATE_DEAD;
+			}
+		}
+	}
+
+	dev->blocks_in_checkpt = 0;
+
+	return 1;
+}
+
+static void yaffs2_checkpt_find_erased_block(struct yaffs_dev *dev)
+{
+	int i;
+	int blocks_avail = dev->n_erased_blocks - dev->param.n_reserved_blocks;
+
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+		"allocating checkpt block: erased %d reserved %d avail %d next %d ",
+		dev->n_erased_blocks, dev->param.n_reserved_blocks,
+		blocks_avail, dev->checkpt_next_block);
+
+	if (dev->checkpt_next_block >= 0 &&
+	    dev->checkpt_next_block <= dev->internal_end_block &&
+	    blocks_avail > 0) {
+
+		for (i = dev->checkpt_next_block; i <= dev->internal_end_block;
+		     i++) {
+			struct yaffs_block_info *bi;
+
+			bi = yaffs_get_block_info(dev, i);
+			if (bi->block_state == YAFFS_BLOCK_STATE_EMPTY) {
+				dev->checkpt_next_block = i + 1;
+				dev->checkpt_cur_block = i;
+				yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+					"allocating checkpt block %d", i);
+				return;
+			}
+		}
+	}
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT, "out of checkpt blocks");
+
+	dev->checkpt_next_block = -1;
+	dev->checkpt_cur_block = -1;
+}
+
+static void yaffs2_checkpt_find_block(struct yaffs_dev *dev)
+{
+	int i;
+	struct yaffs_ext_tags tags;
+
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+		"find next checkpt block: start:  blocks %d next %d",
+		dev->blocks_in_checkpt, dev->checkpt_next_block);
+
+	if (dev->blocks_in_checkpt < dev->checkpt_max_blocks)
+		for (i = dev->checkpt_next_block; i <= dev->internal_end_block;
+		     i++) {
+			int chunk = i * dev->param.chunks_per_block;
+			enum yaffs_block_state state;
+			u32 seq;
+
+			dev->tagger.read_chunk_tags_fn(dev,
+					apply_chunk_offset(dev, chunk),
+					NULL, &tags);
+			yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+				"find next checkpt block: search: block %d state %d oid %d seq %d eccr %d",
+				i, (int) state,
+				tags.obj_id, tags.seq_number,
+				tags.ecc_result);
+
+			if (tags.seq_number != YAFFS_SEQUENCE_CHECKPOINT_DATA)
+				continue;
+
+			dev->tagger.query_block_fn(dev,
+						apply_block_offset(dev, i),
+						&state, &seq);
+			if (state == YAFFS_BLOCK_STATE_DEAD)
+				continue;
+
+			/* Right kind of block */
+			dev->checkpt_next_block = tags.obj_id;
+			dev->checkpt_cur_block = i;
+			dev->checkpt_block_list[dev->blocks_in_checkpt] = i;
+			dev->blocks_in_checkpt++;
+			yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+				"found checkpt block %d", i);
+			return;
+		}
+
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT, "found no more checkpt blocks");
+
+	dev->checkpt_next_block = -1;
+	dev->checkpt_cur_block = -1;
+}
+
+int yaffs2_checkpt_open(struct yaffs_dev *dev, int writing)
+{
+	int i;
+
+	dev->checkpt_open_write = writing;
+
+	/* Got the functions we need? */
+	if (!dev->tagger.write_chunk_tags_fn ||
+	    !dev->tagger.read_chunk_tags_fn ||
+	    !dev->drv.drv_erase_fn ||
+	    !dev->drv.drv_mark_bad_fn)
+		return 0;
+
+	if (writing && !yaffs2_checkpt_space_ok(dev))
+		return 0;
+
+	if (!dev->checkpt_buffer)
+		dev->checkpt_buffer =
+		    kmalloc(dev->param.total_bytes_per_chunk, GFP_NOFS);
+	if (!dev->checkpt_buffer)
+		return 0;
+
+	dev->checkpt_page_seq = 0;
+	dev->checkpt_byte_count = 0;
+	dev->checkpt_sum = 0;
+	dev->checkpt_xor = 0;
+	dev->checkpt_cur_block = -1;
+	dev->checkpt_cur_chunk = -1;
+	dev->checkpt_next_block = dev->internal_start_block;
+
+	if (writing) {
+		memset(dev->checkpt_buffer, 0, dev->data_bytes_per_chunk);
+		yaffs2_checkpt_init_chunk_hdr(dev);
+		return yaffs_checkpt_erase(dev);
+	}
+
+	/* Opening for a read */
+	/* Set to a value that will kick off a read */
+	dev->checkpt_byte_offs = dev->data_bytes_per_chunk;
+	/* A checkpoint block list of 1 checkpoint block per 16 block is
+	 * (hopefully) going to be way more than we need */
+	dev->blocks_in_checkpt = 0;
+	dev->checkpt_max_blocks =
+	    (dev->internal_end_block - dev->internal_start_block) / 16 + 2;
+	dev->checkpt_block_list =
+	    kmalloc(sizeof(int) * dev->checkpt_max_blocks, GFP_NOFS);
+
+	if (!dev->checkpt_block_list)
+		return 0;
+
+	for (i = 0; i < dev->checkpt_max_blocks; i++)
+		dev->checkpt_block_list[i] = -1;
+
+	return 1;
+}
+
+int yaffs2_get_checkpt_sum(struct yaffs_dev *dev, u32 * sum)
+{
+	u32 composite_sum;
+
+	composite_sum = (dev->checkpt_sum << 8) | (dev->checkpt_xor & 0xff);
+	*sum = composite_sum;
+	return 1;
+}
+
+static int yaffs2_checkpt_flush_buffer(struct yaffs_dev *dev)
+{
+	int chunk;
+	int offset_chunk;
+	struct yaffs_ext_tags tags;
+
+	if (dev->checkpt_cur_block < 0) {
+		yaffs2_checkpt_find_erased_block(dev);
+		dev->checkpt_cur_chunk = 0;
+	}
+
+	if (dev->checkpt_cur_block < 0)
+		return 0;
+
+	tags.is_deleted = 0;
+	tags.obj_id = dev->checkpt_next_block;	/* Hint to next place to look */
+	tags.chunk_id = dev->checkpt_page_seq + 1;
+	tags.seq_number = YAFFS_SEQUENCE_CHECKPOINT_DATA;
+	tags.n_bytes = dev->data_bytes_per_chunk;
+	if (dev->checkpt_cur_chunk == 0) {
+		/* First chunk we write for the block? Set block state to
+		   checkpoint */
+		struct yaffs_block_info *bi =
+		    yaffs_get_block_info(dev, dev->checkpt_cur_block);
+		bi->block_state = YAFFS_BLOCK_STATE_CHECKPOINT;
+		dev->blocks_in_checkpt++;
+	}
+
+	chunk =
+	    dev->checkpt_cur_block * dev->param.chunks_per_block +
+	    dev->checkpt_cur_chunk;
+
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+		"checkpoint wite buffer nand %d(%d:%d) objid %d chId %d",
+		chunk, dev->checkpt_cur_block, dev->checkpt_cur_chunk,
+		tags.obj_id, tags.chunk_id);
+
+	offset_chunk = apply_chunk_offset(dev, chunk);
+
+	dev->n_page_writes++;
+
+	dev->tagger.write_chunk_tags_fn(dev, offset_chunk,
+				       dev->checkpt_buffer, &tags);
+	dev->checkpt_page_seq++;
+	dev->checkpt_cur_chunk++;
+	if (dev->checkpt_cur_chunk >= dev->param.chunks_per_block) {
+		dev->checkpt_cur_chunk = 0;
+		dev->checkpt_cur_block = -1;
+	}
+	memset(dev->checkpt_buffer, 0, dev->data_bytes_per_chunk);
+
+	yaffs2_checkpt_init_chunk_hdr(dev);
+
+
+	return 1;
+}
+
+int yaffs2_checkpt_wr(struct yaffs_dev *dev, const void *data, int n_bytes)
+{
+	int i = 0;
+	int ok = 1;
+	u8 *data_bytes = (u8 *) data;
+
+	if (!dev->checkpt_buffer)
+		return 0;
+
+	if (!dev->checkpt_open_write)
+		return -1;
+
+	while (i < n_bytes && ok) {
+		dev->checkpt_buffer[dev->checkpt_byte_offs] = *data_bytes;
+		dev->checkpt_sum += *data_bytes;
+		dev->checkpt_xor ^= *data_bytes;
+
+		dev->checkpt_byte_offs++;
+		i++;
+		data_bytes++;
+		dev->checkpt_byte_count++;
+
+		if (dev->checkpt_byte_offs < 0 ||
+		    dev->checkpt_byte_offs >= dev->data_bytes_per_chunk)
+			ok = yaffs2_checkpt_flush_buffer(dev);
+	}
+
+	return i;
+}
+
+int yaffs2_checkpt_rd(struct yaffs_dev *dev, void *data, int n_bytes)
+{
+	int i = 0;
+	int ok = 1;
+	struct yaffs_ext_tags tags;
+	int chunk;
+	int offset_chunk;
+	u8 *data_bytes = (u8 *) data;
+
+	if (!dev->checkpt_buffer)
+		return 0;
+
+	if (dev->checkpt_open_write)
+		return -1;
+
+	while (i < n_bytes && ok) {
+
+		if (dev->checkpt_byte_offs < 0 ||
+		    dev->checkpt_byte_offs >= dev->data_bytes_per_chunk) {
+
+			if (dev->checkpt_cur_block < 0) {
+				yaffs2_checkpt_find_block(dev);
+				dev->checkpt_cur_chunk = 0;
+			}
+
+			if (dev->checkpt_cur_block < 0) {
+				ok = 0;
+				break;
+			}
+
+			chunk = dev->checkpt_cur_block *
+			    dev->param.chunks_per_block +
+			    dev->checkpt_cur_chunk;
+
+			offset_chunk = apply_chunk_offset(dev, chunk);
+			dev->n_page_reads++;
+
+			/* read in the next chunk */
+			dev->tagger.read_chunk_tags_fn(dev,
+						offset_chunk,
+						dev->checkpt_buffer,
+						&tags);
+
+			if (tags.chunk_id != (dev->checkpt_page_seq + 1) ||
+			    tags.ecc_result > YAFFS_ECC_RESULT_FIXED ||
+			    tags.seq_number != YAFFS_SEQUENCE_CHECKPOINT_DATA) {
+				ok = 0;
+				break;
+			}
+			if(!yaffs2_checkpt_check_chunk_hdr(dev)) {
+				ok = 0;
+				break;
+			}
+
+			dev->checkpt_page_seq++;
+			dev->checkpt_cur_chunk++;
+
+			if (dev->checkpt_cur_chunk >=
+					dev->param.chunks_per_block)
+				dev->checkpt_cur_block = -1;
+
+		}
+
+		*data_bytes = dev->checkpt_buffer[dev->checkpt_byte_offs];
+		dev->checkpt_sum += *data_bytes;
+		dev->checkpt_xor ^= *data_bytes;
+		dev->checkpt_byte_offs++;
+		i++;
+		data_bytes++;
+		dev->checkpt_byte_count++;
+	}
+
+	return i;
+}
+
+int yaffs_checkpt_close(struct yaffs_dev *dev)
+{
+	int i;
+
+	if (dev->checkpt_open_write) {
+		if (dev->checkpt_byte_offs !=
+			sizeof(sizeof(struct yaffs_checkpt_chunk_hdr)))
+			yaffs2_checkpt_flush_buffer(dev);
+	} else if (dev->checkpt_block_list) {
+		for (i = 0;
+		     i < dev->blocks_in_checkpt &&
+		     dev->checkpt_block_list[i] >= 0; i++) {
+			int blk = dev->checkpt_block_list[i];
+			struct yaffs_block_info *bi = NULL;
+
+			if (dev->internal_start_block <= blk &&
+			    blk <= dev->internal_end_block)
+				bi = yaffs_get_block_info(dev, blk);
+			if (bi && bi->block_state == YAFFS_BLOCK_STATE_EMPTY)
+				bi->block_state = YAFFS_BLOCK_STATE_CHECKPOINT;
+		}
+		kfree(dev->checkpt_block_list);
+		dev->checkpt_block_list = NULL;
+	}
+
+	dev->n_free_chunks -=
+		dev->blocks_in_checkpt * dev->param.chunks_per_block;
+	dev->n_erased_blocks -= dev->blocks_in_checkpt;
+
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT, "checkpoint byte count %d",
+		dev->checkpt_byte_count);
+
+	if (dev->checkpt_buffer) {
+		/* free the buffer */
+		kfree(dev->checkpt_buffer);
+		dev->checkpt_buffer = NULL;
+		return 1;
+	} else {
+		return 0;
+	}
+}
+
+int yaffs2_checkpt_invalidate_stream(struct yaffs_dev *dev)
+{
+	/* Erase the checkpoint data */
+
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+		"checkpoint invalidate of %d blocks",
+		dev->blocks_in_checkpt);
+
+	return yaffs_checkpt_erase(dev);
+}
diff --git a/fs/yaffs2/yaffs_checkptrw.h b/fs/yaffs2/yaffs_checkptrw.h
new file mode 100644
index 000000000000..cdbaba7153ed
--- /dev/null
+++ b/fs/yaffs2/yaffs_checkptrw.h
@@ -0,0 +1,33 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_CHECKPTRW_H__
+#define __YAFFS_CHECKPTRW_H__
+
+#include "yaffs_guts.h"
+
+int yaffs2_checkpt_open(struct yaffs_dev *dev, int writing);
+
+int yaffs2_checkpt_wr(struct yaffs_dev *dev, const void *data, int n_bytes);
+
+int yaffs2_checkpt_rd(struct yaffs_dev *dev, void *data, int n_bytes);
+
+int yaffs2_get_checkpt_sum(struct yaffs_dev *dev, u32 * sum);
+
+int yaffs_checkpt_close(struct yaffs_dev *dev);
+
+int yaffs2_checkpt_invalidate_stream(struct yaffs_dev *dev);
+
+#endif
diff --git a/fs/yaffs2/yaffs_ecc.c b/fs/yaffs2/yaffs_ecc.c
new file mode 100644
index 000000000000..9294107c150d
--- /dev/null
+++ b/fs/yaffs2/yaffs_ecc.c
@@ -0,0 +1,281 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * This code implements the ECC algorithm used in SmartMedia.
+ *
+ * The ECC comprises 22 bits of parity information and is stuffed into 3 bytes.
+ * The two unused bit are set to 1.
+ * The ECC can correct single bit errors in a 256-byte page of data. Thus, two
+ * such ECC blocks are used on a 512-byte NAND page.
+ *
+ */
+
+#include "yportenv.h"
+
+#include "yaffs_ecc.h"
+
+/* Table generated by gen-ecc.c
+ * Using a table means we do not have to calculate p1..p4 and p1'..p4'
+ * for each byte of data. These are instead provided in a table in bits7..2.
+ * Bit 0 of each entry indicates whether the entry has an odd or even parity,
+ * and therefore this bytes influence on the line parity.
+ */
+
+static const unsigned char column_parity_table[] = {
+	0x00, 0x55, 0x59, 0x0c, 0x65, 0x30, 0x3c, 0x69,
+	0x69, 0x3c, 0x30, 0x65, 0x0c, 0x59, 0x55, 0x00,
+	0x95, 0xc0, 0xcc, 0x99, 0xf0, 0xa5, 0xa9, 0xfc,
+	0xfc, 0xa9, 0xa5, 0xf0, 0x99, 0xcc, 0xc0, 0x95,
+	0x99, 0xcc, 0xc0, 0x95, 0xfc, 0xa9, 0xa5, 0xf0,
+	0xf0, 0xa5, 0xa9, 0xfc, 0x95, 0xc0, 0xcc, 0x99,
+	0x0c, 0x59, 0x55, 0x00, 0x69, 0x3c, 0x30, 0x65,
+	0x65, 0x30, 0x3c, 0x69, 0x00, 0x55, 0x59, 0x0c,
+	0xa5, 0xf0, 0xfc, 0xa9, 0xc0, 0x95, 0x99, 0xcc,
+	0xcc, 0x99, 0x95, 0xc0, 0xa9, 0xfc, 0xf0, 0xa5,
+	0x30, 0x65, 0x69, 0x3c, 0x55, 0x00, 0x0c, 0x59,
+	0x59, 0x0c, 0x00, 0x55, 0x3c, 0x69, 0x65, 0x30,
+	0x3c, 0x69, 0x65, 0x30, 0x59, 0x0c, 0x00, 0x55,
+	0x55, 0x00, 0x0c, 0x59, 0x30, 0x65, 0x69, 0x3c,
+	0xa9, 0xfc, 0xf0, 0xa5, 0xcc, 0x99, 0x95, 0xc0,
+	0xc0, 0x95, 0x99, 0xcc, 0xa5, 0xf0, 0xfc, 0xa9,
+	0xa9, 0xfc, 0xf0, 0xa5, 0xcc, 0x99, 0x95, 0xc0,
+	0xc0, 0x95, 0x99, 0xcc, 0xa5, 0xf0, 0xfc, 0xa9,
+	0x3c, 0x69, 0x65, 0x30, 0x59, 0x0c, 0x00, 0x55,
+	0x55, 0x00, 0x0c, 0x59, 0x30, 0x65, 0x69, 0x3c,
+	0x30, 0x65, 0x69, 0x3c, 0x55, 0x00, 0x0c, 0x59,
+	0x59, 0x0c, 0x00, 0x55, 0x3c, 0x69, 0x65, 0x30,
+	0xa5, 0xf0, 0xfc, 0xa9, 0xc0, 0x95, 0x99, 0xcc,
+	0xcc, 0x99, 0x95, 0xc0, 0xa9, 0xfc, 0xf0, 0xa5,
+	0x0c, 0x59, 0x55, 0x00, 0x69, 0x3c, 0x30, 0x65,
+	0x65, 0x30, 0x3c, 0x69, 0x00, 0x55, 0x59, 0x0c,
+	0x99, 0xcc, 0xc0, 0x95, 0xfc, 0xa9, 0xa5, 0xf0,
+	0xf0, 0xa5, 0xa9, 0xfc, 0x95, 0xc0, 0xcc, 0x99,
+	0x95, 0xc0, 0xcc, 0x99, 0xf0, 0xa5, 0xa9, 0xfc,
+	0xfc, 0xa9, 0xa5, 0xf0, 0x99, 0xcc, 0xc0, 0x95,
+	0x00, 0x55, 0x59, 0x0c, 0x65, 0x30, 0x3c, 0x69,
+	0x69, 0x3c, 0x30, 0x65, 0x0c, 0x59, 0x55, 0x00,
+};
+
+
+/* Calculate the ECC for a 256-byte block of data */
+void yaffs_ecc_calc(const unsigned char *data, unsigned char *ecc)
+{
+	unsigned int i;
+	unsigned char col_parity = 0;
+	unsigned char line_parity = 0;
+	unsigned char line_parity_prime = 0;
+	unsigned char t;
+	unsigned char b;
+
+	for (i = 0; i < 256; i++) {
+		b = column_parity_table[*data++];
+		col_parity ^= b;
+
+		if (b & 0x01) {	/* odd number of bits in the byte */
+			line_parity ^= i;
+			line_parity_prime ^= ~i;
+		}
+	}
+
+	ecc[2] = (~col_parity) | 0x03;
+
+	t = 0;
+	if (line_parity & 0x80)
+		t |= 0x80;
+	if (line_parity_prime & 0x80)
+		t |= 0x40;
+	if (line_parity & 0x40)
+		t |= 0x20;
+	if (line_parity_prime & 0x40)
+		t |= 0x10;
+	if (line_parity & 0x20)
+		t |= 0x08;
+	if (line_parity_prime & 0x20)
+		t |= 0x04;
+	if (line_parity & 0x10)
+		t |= 0x02;
+	if (line_parity_prime & 0x10)
+		t |= 0x01;
+	ecc[1] = ~t;
+
+	t = 0;
+	if (line_parity & 0x08)
+		t |= 0x80;
+	if (line_parity_prime & 0x08)
+		t |= 0x40;
+	if (line_parity & 0x04)
+		t |= 0x20;
+	if (line_parity_prime & 0x04)
+		t |= 0x10;
+	if (line_parity & 0x02)
+		t |= 0x08;
+	if (line_parity_prime & 0x02)
+		t |= 0x04;
+	if (line_parity & 0x01)
+		t |= 0x02;
+	if (line_parity_prime & 0x01)
+		t |= 0x01;
+	ecc[0] = ~t;
+
+}
+
+/* Correct the ECC on a 256 byte block of data */
+
+int yaffs_ecc_correct(unsigned char *data, unsigned char *read_ecc,
+		      const unsigned char *test_ecc)
+{
+	unsigned char d0, d1, d2;	/* deltas */
+
+	d0 = read_ecc[0] ^ test_ecc[0];
+	d1 = read_ecc[1] ^ test_ecc[1];
+	d2 = read_ecc[2] ^ test_ecc[2];
+
+	if ((d0 | d1 | d2) == 0)
+		return 0;	/* no error */
+
+	if (((d0 ^ (d0 >> 1)) & 0x55) == 0x55 &&
+	    ((d1 ^ (d1 >> 1)) & 0x55) == 0x55 &&
+	    ((d2 ^ (d2 >> 1)) & 0x54) == 0x54) {
+		/* Single bit (recoverable) error in data */
+
+		unsigned byte;
+		unsigned bit;
+
+		bit = byte = 0;
+
+		if (d1 & 0x80)
+			byte |= 0x80;
+		if (d1 & 0x20)
+			byte |= 0x40;
+		if (d1 & 0x08)
+			byte |= 0x20;
+		if (d1 & 0x02)
+			byte |= 0x10;
+		if (d0 & 0x80)
+			byte |= 0x08;
+		if (d0 & 0x20)
+			byte |= 0x04;
+		if (d0 & 0x08)
+			byte |= 0x02;
+		if (d0 & 0x02)
+			byte |= 0x01;
+
+		if (d2 & 0x80)
+			bit |= 0x04;
+		if (d2 & 0x20)
+			bit |= 0x02;
+		if (d2 & 0x08)
+			bit |= 0x01;
+
+		data[byte] ^= (1 << bit);
+
+		return 1;	/* Corrected the error */
+	}
+
+	if ((hweight8(d0) + hweight8(d1) + hweight8(d2)) == 1) {
+		/* Reccoverable error in ecc */
+
+		read_ecc[0] = test_ecc[0];
+		read_ecc[1] = test_ecc[1];
+		read_ecc[2] = test_ecc[2];
+
+		return 1;	/* Corrected the error */
+	}
+
+	/* Unrecoverable error */
+
+	return -1;
+
+}
+
+/*
+ * ECCxxxOther does ECC calcs on arbitrary n bytes of data
+ */
+void yaffs_ecc_calc_other(const unsigned char *data, unsigned n_bytes,
+			  struct yaffs_ecc_other *ecc_other)
+{
+	unsigned int i;
+	unsigned char col_parity = 0;
+	unsigned line_parity = 0;
+	unsigned line_parity_prime = 0;
+	unsigned char b;
+
+	for (i = 0; i < n_bytes; i++) {
+		b = column_parity_table[*data++];
+		col_parity ^= b;
+
+		if (b & 0x01) {
+			/* odd number of bits in the byte */
+			line_parity ^= i;
+			line_parity_prime ^= ~i;
+		}
+
+	}
+
+	ecc_other->col_parity = (col_parity >> 2) & 0x3f;
+	ecc_other->line_parity = line_parity;
+	ecc_other->line_parity_prime = line_parity_prime;
+}
+
+int yaffs_ecc_correct_other(unsigned char *data, unsigned n_bytes,
+			    struct yaffs_ecc_other *read_ecc,
+			    const struct yaffs_ecc_other *test_ecc)
+{
+	unsigned char delta_col;	/* column parity delta */
+	unsigned delta_line;	/* line parity delta */
+	unsigned delta_line_prime;	/* line parity delta */
+	unsigned bit;
+
+	delta_col = read_ecc->col_parity ^ test_ecc->col_parity;
+	delta_line = read_ecc->line_parity ^ test_ecc->line_parity;
+	delta_line_prime =
+	    read_ecc->line_parity_prime ^ test_ecc->line_parity_prime;
+
+	if ((delta_col | delta_line | delta_line_prime) == 0)
+		return 0;	/* no error */
+
+	if (delta_line == ~delta_line_prime &&
+	    (((delta_col ^ (delta_col >> 1)) & 0x15) == 0x15)) {
+		/* Single bit (recoverable) error in data */
+
+		bit = 0;
+
+		if (delta_col & 0x20)
+			bit |= 0x04;
+		if (delta_col & 0x08)
+			bit |= 0x02;
+		if (delta_col & 0x02)
+			bit |= 0x01;
+
+		if (delta_line >= n_bytes)
+			return -1;
+
+		data[delta_line] ^= (1 << bit);
+
+		return 1;	/* corrected */
+	}
+
+	if ((hweight32(delta_line) +
+	     hweight32(delta_line_prime) +
+	     hweight8(delta_col)) == 1) {
+		/* Reccoverable error in ecc */
+
+		*read_ecc = *test_ecc;
+		return 1;	/* corrected */
+	}
+
+	/* Unrecoverable error */
+
+	return -1;
+}
diff --git a/fs/yaffs2/yaffs_ecc.h b/fs/yaffs2/yaffs_ecc.h
new file mode 100644
index 000000000000..17d47bd80f3e
--- /dev/null
+++ b/fs/yaffs2/yaffs_ecc.h
@@ -0,0 +1,44 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+/*
+ * This code implements the ECC algorithm used in SmartMedia.
+ *
+ * The ECC comprises 22 bits of parity information and is stuffed into 3 bytes.
+ * The two unused bit are set to 1.
+ * The ECC can correct single bit errors in a 256-byte page of data.
+ * Thus, two such ECC blocks are used on a 512-byte NAND page.
+ *
+ */
+
+#ifndef __YAFFS_ECC_H__
+#define __YAFFS_ECC_H__
+
+struct yaffs_ecc_other {
+	unsigned char col_parity;
+	unsigned line_parity;
+	unsigned line_parity_prime;
+};
+
+void yaffs_ecc_calc(const unsigned char *data, unsigned char *ecc);
+int yaffs_ecc_correct(unsigned char *data, unsigned char *read_ecc,
+		      const unsigned char *test_ecc);
+
+void yaffs_ecc_calc_other(const unsigned char *data, unsigned n_bytes,
+			  struct yaffs_ecc_other *ecc);
+int yaffs_ecc_correct_other(unsigned char *data, unsigned n_bytes,
+			    struct yaffs_ecc_other *read_ecc,
+			    const struct yaffs_ecc_other *test_ecc);
+#endif
diff --git a/fs/yaffs2/yaffs_getblockinfo.h b/fs/yaffs2/yaffs_getblockinfo.h
new file mode 100644
index 000000000000..8fd0802bdddb
--- /dev/null
+++ b/fs/yaffs2/yaffs_getblockinfo.h
@@ -0,0 +1,35 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_GETBLOCKINFO_H__
+#define __YAFFS_GETBLOCKINFO_H__
+
+#include "yaffs_guts.h"
+#include "yaffs_trace.h"
+
+/* Function to manipulate block info */
+static inline struct yaffs_block_info *yaffs_get_block_info(struct yaffs_dev
+							      *dev, int blk)
+{
+	if (blk < dev->internal_start_block || blk > dev->internal_end_block) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"**>> yaffs: get_block_info block %d is not valid",
+			blk);
+		BUG();
+	}
+	return &dev->block_info[blk - dev->internal_start_block];
+}
+
+#endif
diff --git a/fs/yaffs2/yaffs_guts.c b/fs/yaffs2/yaffs_guts.c
new file mode 100644
index 000000000000..1fd464d68af7
--- /dev/null
+++ b/fs/yaffs2/yaffs_guts.c
@@ -0,0 +1,5082 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yportenv.h"
+#include "yaffs_trace.h"
+
+#include "yaffs_guts.h"
+#include "yaffs_getblockinfo.h"
+#include "yaffs_tagscompat.h"
+#include "yaffs_tagsmarshall.h"
+#include "yaffs_nand.h"
+#include "yaffs_yaffs1.h"
+#include "yaffs_yaffs2.h"
+#include "yaffs_bitmap.h"
+#include "yaffs_verify.h"
+#include "yaffs_nand.h"
+#include "yaffs_packedtags2.h"
+#include "yaffs_nameval.h"
+#include "yaffs_allocator.h"
+#include "yaffs_attribs.h"
+#include "yaffs_summary.h"
+
+/* Note YAFFS_GC_GOOD_ENOUGH must be <= YAFFS_GC_PASSIVE_THRESHOLD */
+#define YAFFS_GC_GOOD_ENOUGH 2
+#define YAFFS_GC_PASSIVE_THRESHOLD 4
+
+#include "yaffs_ecc.h"
+
+/* Forward declarations */
+
+static int yaffs_wr_data_obj(struct yaffs_obj *in, int inode_chunk,
+			     const u8 *buffer, int n_bytes, int use_reserve);
+
+static void yaffs_fix_null_name(struct yaffs_obj *obj, YCHAR *name,
+				int buffer_size);
+
+/* Function to calculate chunk and offset */
+
+void yaffs_addr_to_chunk(struct yaffs_dev *dev, loff_t addr,
+				int *chunk_out, u32 *offset_out)
+{
+	int chunk;
+	u32 offset;
+
+	chunk = (u32) (addr >> dev->chunk_shift);
+
+	if (dev->chunk_div == 1) {
+		/* easy power of 2 case */
+		offset = (u32) (addr & dev->chunk_mask);
+	} else {
+		/* Non power-of-2 case */
+
+		loff_t chunk_base;
+
+		chunk /= dev->chunk_div;
+
+		chunk_base = ((loff_t) chunk) * dev->data_bytes_per_chunk;
+		offset = (u32) (addr - chunk_base);
+	}
+
+	*chunk_out = chunk;
+	*offset_out = offset;
+}
+
+/* Function to return the number of shifts for a power of 2 greater than or
+ * equal to the given number
+ * Note we don't try to cater for all possible numbers and this does not have to
+ * be hellishly efficient.
+ */
+
+static inline u32 calc_shifts_ceiling(u32 x)
+{
+	int extra_bits;
+	int shifts;
+
+	shifts = extra_bits = 0;
+
+	while (x > 1) {
+		if (x & 1)
+			extra_bits++;
+		x >>= 1;
+		shifts++;
+	}
+
+	if (extra_bits)
+		shifts++;
+
+	return shifts;
+}
+
+/* Function to return the number of shifts to get a 1 in bit 0
+ */
+
+static inline u32 calc_shifts(u32 x)
+{
+	u32 shifts;
+
+	shifts = 0;
+
+	if (!x)
+		return 0;
+
+	while (!(x & 1)) {
+		x >>= 1;
+		shifts++;
+	}
+
+	return shifts;
+}
+
+/*
+ * Temporary buffer manipulations.
+ */
+
+static int yaffs_init_tmp_buffers(struct yaffs_dev *dev)
+{
+	int i;
+	u8 *buf = (u8 *) 1;
+
+	memset(dev->temp_buffer, 0, sizeof(dev->temp_buffer));
+
+	for (i = 0; buf && i < YAFFS_N_TEMP_BUFFERS; i++) {
+		dev->temp_buffer[i].in_use = 0;
+		buf = kmalloc(dev->param.total_bytes_per_chunk, GFP_NOFS);
+		dev->temp_buffer[i].buffer = buf;
+	}
+
+	return buf ? YAFFS_OK : YAFFS_FAIL;
+}
+
+u8 *yaffs_get_temp_buffer(struct yaffs_dev * dev)
+{
+	int i;
+
+	dev->temp_in_use++;
+	if (dev->temp_in_use > dev->max_temp)
+		dev->max_temp = dev->temp_in_use;
+
+	for (i = 0; i < YAFFS_N_TEMP_BUFFERS; i++) {
+		if (dev->temp_buffer[i].in_use == 0) {
+			dev->temp_buffer[i].in_use = 1;
+			return dev->temp_buffer[i].buffer;
+		}
+	}
+
+	yaffs_trace(YAFFS_TRACE_BUFFERS, "Out of temp buffers");
+	/*
+	 * If we got here then we have to allocate an unmanaged one
+	 * This is not good.
+	 */
+
+	dev->unmanaged_buffer_allocs++;
+	return kmalloc(dev->data_bytes_per_chunk, GFP_NOFS);
+
+}
+
+void yaffs_release_temp_buffer(struct yaffs_dev *dev, u8 *buffer)
+{
+	int i;
+
+	dev->temp_in_use--;
+
+	for (i = 0; i < YAFFS_N_TEMP_BUFFERS; i++) {
+		if (dev->temp_buffer[i].buffer == buffer) {
+			dev->temp_buffer[i].in_use = 0;
+			return;
+		}
+	}
+
+	if (buffer) {
+		/* assume it is an unmanaged one. */
+		yaffs_trace(YAFFS_TRACE_BUFFERS,
+			"Releasing unmanaged temp buffer");
+		kfree(buffer);
+		dev->unmanaged_buffer_deallocs++;
+	}
+
+}
+
+/*
+ * Functions for robustisizing TODO
+ *
+ */
+
+static void yaffs_handle_chunk_wr_ok(struct yaffs_dev *dev, int nand_chunk,
+				     const u8 *data,
+				     const struct yaffs_ext_tags *tags)
+{
+	(void) dev;
+	(void) nand_chunk;
+	(void) data;
+	(void) tags;
+}
+
+static void yaffs_handle_chunk_update(struct yaffs_dev *dev, int nand_chunk,
+				      const struct yaffs_ext_tags *tags)
+{
+	(void) dev;
+	(void) nand_chunk;
+	(void) tags;
+}
+
+void yaffs_handle_chunk_error(struct yaffs_dev *dev,
+			      struct yaffs_block_info *bi)
+{
+	if (!bi->gc_prioritise) {
+		bi->gc_prioritise = 1;
+		dev->has_pending_prioritised_gc = 1;
+		bi->chunk_error_strikes++;
+
+		if (bi->chunk_error_strikes > 3) {
+			bi->needs_retiring = 1;	/* Too many stikes, so retire */
+			yaffs_trace(YAFFS_TRACE_ALWAYS,
+				"yaffs: Block struck out");
+
+		}
+	}
+}
+
+static void yaffs_handle_chunk_wr_error(struct yaffs_dev *dev, int nand_chunk,
+					int erased_ok)
+{
+	int flash_block = nand_chunk / dev->param.chunks_per_block;
+	struct yaffs_block_info *bi = yaffs_get_block_info(dev, flash_block);
+
+	yaffs_handle_chunk_error(dev, bi);
+
+	if (erased_ok) {
+		/* Was an actual write failure,
+		 * so mark the block for retirement.*/
+		bi->needs_retiring = 1;
+		yaffs_trace(YAFFS_TRACE_ERROR | YAFFS_TRACE_BAD_BLOCKS,
+		  "**>> Block %d needs retiring", flash_block);
+	}
+
+	/* Delete the chunk */
+	yaffs_chunk_del(dev, nand_chunk, 1, __LINE__);
+	yaffs_skip_rest_of_block(dev);
+}
+
+/*
+ * Verification code
+ */
+
+/*
+ *  Simple hash function. Needs to have a reasonable spread
+ */
+
+static inline int yaffs_hash_fn(int n)
+{
+	if (n < 0)
+		n = -n;
+	return n % YAFFS_NOBJECT_BUCKETS;
+}
+
+/*
+ * Access functions to useful fake objects.
+ * Note that root might have a presence in NAND if permissions are set.
+ */
+
+struct yaffs_obj *yaffs_root(struct yaffs_dev *dev)
+{
+	return dev->root_dir;
+}
+
+struct yaffs_obj *yaffs_lost_n_found(struct yaffs_dev *dev)
+{
+	return dev->lost_n_found;
+}
+
+/*
+ *  Erased NAND checking functions
+ */
+
+int yaffs_check_ff(u8 *buffer, int n_bytes)
+{
+	/* Horrible, slow implementation */
+	while (n_bytes--) {
+		if (*buffer != 0xff)
+			return 0;
+		buffer++;
+	}
+	return 1;
+}
+
+static int yaffs_check_chunk_erased(struct yaffs_dev *dev, int nand_chunk)
+{
+	int retval = YAFFS_OK;
+	u8 *data = yaffs_get_temp_buffer(dev);
+	struct yaffs_ext_tags tags;
+	int result;
+
+	result = yaffs_rd_chunk_tags_nand(dev, nand_chunk, data, &tags);
+
+	if (tags.ecc_result > YAFFS_ECC_RESULT_NO_ERROR)
+		retval = YAFFS_FAIL;
+
+	if (!yaffs_check_ff(data, dev->data_bytes_per_chunk) ||
+		tags.chunk_used) {
+		yaffs_trace(YAFFS_TRACE_NANDACCESS,
+			"Chunk %d not erased", nand_chunk);
+		retval = YAFFS_FAIL;
+	}
+
+	yaffs_release_temp_buffer(dev, data);
+
+	return retval;
+
+}
+
+static int yaffs_verify_chunk_written(struct yaffs_dev *dev,
+				      int nand_chunk,
+				      const u8 *data,
+				      struct yaffs_ext_tags *tags)
+{
+	int retval = YAFFS_OK;
+	struct yaffs_ext_tags temp_tags;
+	u8 *buffer = yaffs_get_temp_buffer(dev);
+	int result;
+
+	result = yaffs_rd_chunk_tags_nand(dev, nand_chunk, buffer, &temp_tags);
+	if (memcmp(buffer, data, dev->data_bytes_per_chunk) ||
+	    temp_tags.obj_id != tags->obj_id ||
+	    temp_tags.chunk_id != tags->chunk_id ||
+	    temp_tags.n_bytes != tags->n_bytes)
+		retval = YAFFS_FAIL;
+
+	yaffs_release_temp_buffer(dev, buffer);
+
+	return retval;
+}
+
+
+int yaffs_check_alloc_available(struct yaffs_dev *dev, int n_chunks)
+{
+	int reserved_chunks;
+	int reserved_blocks = dev->param.n_reserved_blocks;
+	int checkpt_blocks;
+
+	checkpt_blocks = yaffs_calc_checkpt_blocks_required(dev);
+
+	reserved_chunks =
+	    (reserved_blocks + checkpt_blocks) * dev->param.chunks_per_block;
+
+	return (dev->n_free_chunks > (reserved_chunks + n_chunks));
+}
+
+static int yaffs_find_alloc_block(struct yaffs_dev *dev)
+{
+	int i;
+	struct yaffs_block_info *bi;
+
+	if (dev->n_erased_blocks < 1) {
+		/* Hoosterman we've got a problem.
+		 * Can't get space to gc
+		 */
+		yaffs_trace(YAFFS_TRACE_ERROR,
+		  "yaffs tragedy: no more erased blocks");
+
+		return -1;
+	}
+
+	/* Find an empty block. */
+
+	for (i = dev->internal_start_block; i <= dev->internal_end_block; i++) {
+		dev->alloc_block_finder++;
+		if (dev->alloc_block_finder < dev->internal_start_block
+		    || dev->alloc_block_finder > dev->internal_end_block) {
+			dev->alloc_block_finder = dev->internal_start_block;
+		}
+
+		bi = yaffs_get_block_info(dev, dev->alloc_block_finder);
+
+		if (bi->block_state == YAFFS_BLOCK_STATE_EMPTY) {
+			bi->block_state = YAFFS_BLOCK_STATE_ALLOCATING;
+			dev->seq_number++;
+			bi->seq_number = dev->seq_number;
+			dev->n_erased_blocks--;
+			yaffs_trace(YAFFS_TRACE_ALLOCATE,
+			  "Allocated block %d, seq  %d, %d left" ,
+			   dev->alloc_block_finder, dev->seq_number,
+			   dev->n_erased_blocks);
+			return dev->alloc_block_finder;
+		}
+	}
+
+	yaffs_trace(YAFFS_TRACE_ALWAYS,
+		"yaffs tragedy: no more erased blocks, but there should have been %d",
+		dev->n_erased_blocks);
+
+	return -1;
+}
+
+static int yaffs_alloc_chunk(struct yaffs_dev *dev, int use_reserver,
+			     struct yaffs_block_info **block_ptr)
+{
+	int ret_val;
+	struct yaffs_block_info *bi;
+
+	if (dev->alloc_block < 0) {
+		/* Get next block to allocate off */
+		dev->alloc_block = yaffs_find_alloc_block(dev);
+		dev->alloc_page = 0;
+	}
+
+	if (!use_reserver && !yaffs_check_alloc_available(dev, 1)) {
+		/* No space unless we're allowed to use the reserve. */
+		return -1;
+	}
+
+	if (dev->n_erased_blocks < dev->param.n_reserved_blocks
+	    && dev->alloc_page == 0)
+		yaffs_trace(YAFFS_TRACE_ALLOCATE, "Allocating reserve");
+
+	/* Next page please.... */
+	if (dev->alloc_block >= 0) {
+		bi = yaffs_get_block_info(dev, dev->alloc_block);
+
+		ret_val = (dev->alloc_block * dev->param.chunks_per_block) +
+		    dev->alloc_page;
+		bi->pages_in_use++;
+		yaffs_set_chunk_bit(dev, dev->alloc_block, dev->alloc_page);
+
+		dev->alloc_page++;
+
+		dev->n_free_chunks--;
+
+		/* If the block is full set the state to full */
+		if (dev->alloc_page >= dev->param.chunks_per_block) {
+			bi->block_state = YAFFS_BLOCK_STATE_FULL;
+			dev->alloc_block = -1;
+		}
+
+		if (block_ptr)
+			*block_ptr = bi;
+
+		return ret_val;
+	}
+
+	yaffs_trace(YAFFS_TRACE_ERROR,
+		"!!!!!!!!! Allocator out !!!!!!!!!!!!!!!!!");
+
+	return -1;
+}
+
+static int yaffs_get_erased_chunks(struct yaffs_dev *dev)
+{
+	int n;
+
+	n = dev->n_erased_blocks * dev->param.chunks_per_block;
+
+	if (dev->alloc_block > 0)
+		n += (dev->param.chunks_per_block - dev->alloc_page);
+
+	return n;
+
+}
+
+/*
+ * yaffs_skip_rest_of_block() skips over the rest of the allocation block
+ * if we don't want to write to it.
+ */
+void yaffs_skip_rest_of_block(struct yaffs_dev *dev)
+{
+	struct yaffs_block_info *bi;
+
+	if (dev->alloc_block > 0) {
+		bi = yaffs_get_block_info(dev, dev->alloc_block);
+		if (bi->block_state == YAFFS_BLOCK_STATE_ALLOCATING) {
+			bi->block_state = YAFFS_BLOCK_STATE_FULL;
+			dev->alloc_block = -1;
+		}
+	}
+}
+
+static int yaffs_write_new_chunk(struct yaffs_dev *dev,
+				 const u8 *data,
+				 struct yaffs_ext_tags *tags, int use_reserver)
+{
+	int attempts = 0;
+	int write_ok = 0;
+	int chunk;
+
+	yaffs2_checkpt_invalidate(dev);
+
+	do {
+		struct yaffs_block_info *bi = 0;
+		int erased_ok = 0;
+
+		chunk = yaffs_alloc_chunk(dev, use_reserver, &bi);
+		if (chunk < 0) {
+			/* no space */
+			break;
+		}
+
+		/* First check this chunk is erased, if it needs
+		 * checking.  The checking policy (unless forced
+		 * always on) is as follows:
+		 *
+		 * Check the first page we try to write in a block.
+		 * If the check passes then we don't need to check any
+		 * more.        If the check fails, we check again...
+		 * If the block has been erased, we don't need to check.
+		 *
+		 * However, if the block has been prioritised for gc,
+		 * then we think there might be something odd about
+		 * this block and stop using it.
+		 *
+		 * Rationale: We should only ever see chunks that have
+		 * not been erased if there was a partially written
+		 * chunk due to power loss.  This checking policy should
+		 * catch that case with very few checks and thus save a
+		 * lot of checks that are most likely not needed.
+		 *
+		 * Mods to the above
+		 * If an erase check fails or the write fails we skip the
+		 * rest of the block.
+		 */
+
+		/* let's give it a try */
+		attempts++;
+
+		if (dev->param.always_check_erased)
+			bi->skip_erased_check = 0;
+
+		if (!bi->skip_erased_check) {
+			erased_ok = yaffs_check_chunk_erased(dev, chunk);
+			if (erased_ok != YAFFS_OK) {
+				yaffs_trace(YAFFS_TRACE_ERROR,
+				  "**>> yaffs chunk %d was not erased",
+				  chunk);
+
+				/* If not erased, delete this one,
+				 * skip rest of block and
+				 * try another chunk */
+				yaffs_chunk_del(dev, chunk, 1, __LINE__);
+				yaffs_skip_rest_of_block(dev);
+				continue;
+			}
+		}
+
+		write_ok = yaffs_wr_chunk_tags_nand(dev, chunk, data, tags);
+
+		if (!bi->skip_erased_check)
+			write_ok =
+			    yaffs_verify_chunk_written(dev, chunk, data, tags);
+
+		if (write_ok != YAFFS_OK) {
+			/* Clean up aborted write, skip to next block and
+			 * try another chunk */
+			yaffs_handle_chunk_wr_error(dev, chunk, erased_ok);
+			continue;
+		}
+
+		bi->skip_erased_check = 1;
+
+		/* Copy the data into the robustification buffer */
+		yaffs_handle_chunk_wr_ok(dev, chunk, data, tags);
+
+	} while (write_ok != YAFFS_OK &&
+		 (yaffs_wr_attempts <= 0 || attempts <= yaffs_wr_attempts));
+
+	if (!write_ok)
+		chunk = -1;
+
+	if (attempts > 1) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"**>> yaffs write required %d attempts",
+			attempts);
+		dev->n_retried_writes += (attempts - 1);
+	}
+
+	return chunk;
+}
+
+/*
+ * Block retiring for handling a broken block.
+ */
+
+static void yaffs_retire_block(struct yaffs_dev *dev, int flash_block)
+{
+	struct yaffs_block_info *bi = yaffs_get_block_info(dev, flash_block);
+
+	yaffs2_checkpt_invalidate(dev);
+
+	yaffs2_clear_oldest_dirty_seq(dev, bi);
+
+	if (yaffs_mark_bad(dev, flash_block) != YAFFS_OK) {
+		if (yaffs_erase_block(dev, flash_block) != YAFFS_OK) {
+			yaffs_trace(YAFFS_TRACE_ALWAYS,
+				"yaffs: Failed to mark bad and erase block %d",
+				flash_block);
+		} else {
+			struct yaffs_ext_tags tags;
+			int chunk_id =
+			    flash_block * dev->param.chunks_per_block;
+
+			u8 *buffer = yaffs_get_temp_buffer(dev);
+
+			memset(buffer, 0xff, dev->data_bytes_per_chunk);
+			memset(&tags, 0, sizeof(tags));
+			tags.seq_number = YAFFS_SEQUENCE_BAD_BLOCK;
+			if (dev->tagger.write_chunk_tags_fn(dev, chunk_id -
+							dev->chunk_offset,
+							buffer,
+							&tags) != YAFFS_OK)
+				yaffs_trace(YAFFS_TRACE_ALWAYS,
+					"yaffs: Failed to write bad block marker to block %d",
+					flash_block);
+
+			yaffs_release_temp_buffer(dev, buffer);
+		}
+	}
+
+	bi->block_state = YAFFS_BLOCK_STATE_DEAD;
+	bi->gc_prioritise = 0;
+	bi->needs_retiring = 0;
+
+	dev->n_retired_blocks++;
+}
+
+/*---------------- Name handling functions ------------*/
+
+static u16 yaffs_calc_name_sum(const YCHAR *name)
+{
+	u16 sum = 0;
+	u16 i = 1;
+
+	if (!name)
+		return 0;
+
+	while ((*name) && i < (YAFFS_MAX_NAME_LENGTH / 2)) {
+
+		/* 0x1f mask is case insensitive */
+		sum += ((*name) & 0x1f) * i;
+		i++;
+		name++;
+	}
+	return sum;
+}
+
+
+void yaffs_set_obj_name(struct yaffs_obj *obj, const YCHAR * name)
+{
+	memset(obj->short_name, 0, sizeof(obj->short_name));
+
+	if (name && !name[0]) {
+		yaffs_fix_null_name(obj, obj->short_name,
+				YAFFS_SHORT_NAME_LENGTH);
+		name = obj->short_name;
+	} else if (name &&
+		strnlen(name, YAFFS_SHORT_NAME_LENGTH + 1) <=
+		YAFFS_SHORT_NAME_LENGTH)  {
+		strcpy(obj->short_name, name);
+	}
+
+	obj->sum = yaffs_calc_name_sum(name);
+}
+
+void yaffs_set_obj_name_from_oh(struct yaffs_obj *obj,
+				const struct yaffs_obj_hdr *oh)
+{
+#ifdef CONFIG_YAFFS_AUTO_UNICODE
+	YCHAR tmp_name[YAFFS_MAX_NAME_LENGTH + 1];
+	memset(tmp_name, 0, sizeof(tmp_name));
+	yaffs_load_name_from_oh(obj->my_dev, tmp_name, oh->name,
+				YAFFS_MAX_NAME_LENGTH + 1);
+	yaffs_set_obj_name(obj, tmp_name);
+#else
+	yaffs_set_obj_name(obj, oh->name);
+#endif
+}
+
+loff_t yaffs_max_file_size(struct yaffs_dev *dev)
+{
+	if(sizeof(loff_t) < 8)
+		return YAFFS_MAX_FILE_SIZE_32;
+	else
+		return ((loff_t) YAFFS_MAX_CHUNK_ID) * dev->data_bytes_per_chunk;
+}
+
+/*-------------------- TNODES -------------------
+
+ * List of spare tnodes
+ * The list is hooked together using the first pointer
+ * in the tnode.
+ */
+
+struct yaffs_tnode *yaffs_get_tnode(struct yaffs_dev *dev)
+{
+	struct yaffs_tnode *tn = yaffs_alloc_raw_tnode(dev);
+
+	if (tn) {
+		memset(tn, 0, dev->tnode_size);
+		dev->n_tnodes++;
+	}
+
+	dev->checkpoint_blocks_required = 0;	/* force recalculation */
+
+	return tn;
+}
+
+/* FreeTnode frees up a tnode and puts it back on the free list */
+static void yaffs_free_tnode(struct yaffs_dev *dev, struct yaffs_tnode *tn)
+{
+	yaffs_free_raw_tnode(dev, tn);
+	dev->n_tnodes--;
+	dev->checkpoint_blocks_required = 0;	/* force recalculation */
+}
+
+static void yaffs_deinit_tnodes_and_objs(struct yaffs_dev *dev)
+{
+	yaffs_deinit_raw_tnodes_and_objs(dev);
+	dev->n_obj = 0;
+	dev->n_tnodes = 0;
+}
+
+static void yaffs_load_tnode_0(struct yaffs_dev *dev, struct yaffs_tnode *tn,
+			unsigned pos, unsigned val)
+{
+	u32 *map = (u32 *) tn;
+	u32 bit_in_map;
+	u32 bit_in_word;
+	u32 word_in_map;
+	u32 mask;
+
+	pos &= YAFFS_TNODES_LEVEL0_MASK;
+	val >>= dev->chunk_grp_bits;
+
+	bit_in_map = pos * dev->tnode_width;
+	word_in_map = bit_in_map / 32;
+	bit_in_word = bit_in_map & (32 - 1);
+
+	mask = dev->tnode_mask << bit_in_word;
+
+	map[word_in_map] &= ~mask;
+	map[word_in_map] |= (mask & (val << bit_in_word));
+
+	if (dev->tnode_width > (32 - bit_in_word)) {
+		bit_in_word = (32 - bit_in_word);
+		word_in_map++;
+		mask =
+		    dev->tnode_mask >> bit_in_word;
+		map[word_in_map] &= ~mask;
+		map[word_in_map] |= (mask & (val >> bit_in_word));
+	}
+}
+
+u32 yaffs_get_group_base(struct yaffs_dev *dev, struct yaffs_tnode *tn,
+			 unsigned pos)
+{
+	u32 *map = (u32 *) tn;
+	u32 bit_in_map;
+	u32 bit_in_word;
+	u32 word_in_map;
+	u32 val;
+
+	pos &= YAFFS_TNODES_LEVEL0_MASK;
+
+	bit_in_map = pos * dev->tnode_width;
+	word_in_map = bit_in_map / 32;
+	bit_in_word = bit_in_map & (32 - 1);
+
+	val = map[word_in_map] >> bit_in_word;
+
+	if (dev->tnode_width > (32 - bit_in_word)) {
+		bit_in_word = (32 - bit_in_word);
+		word_in_map++;
+		val |= (map[word_in_map] << bit_in_word);
+	}
+
+	val &= dev->tnode_mask;
+	val <<= dev->chunk_grp_bits;
+
+	return val;
+}
+
+/* ------------------- End of individual tnode manipulation -----------------*/
+
+/* ---------Functions to manipulate the look-up tree (made up of tnodes) ------
+ * The look up tree is represented by the top tnode and the number of top_level
+ * in the tree. 0 means only the level 0 tnode is in the tree.
+ */
+
+/* FindLevel0Tnode finds the level 0 tnode, if one exists. */
+struct yaffs_tnode *yaffs_find_tnode_0(struct yaffs_dev *dev,
+				       struct yaffs_file_var *file_struct,
+				       u32 chunk_id)
+{
+	struct yaffs_tnode *tn = file_struct->top;
+	u32 i;
+	int required_depth;
+	int level = file_struct->top_level;
+
+	(void) dev;
+
+	/* Check sane level and chunk Id */
+	if (level < 0 || level > YAFFS_TNODES_MAX_LEVEL)
+		return NULL;
+
+	if (chunk_id > YAFFS_MAX_CHUNK_ID)
+		return NULL;
+
+	/* First check we're tall enough (ie enough top_level) */
+
+	i = chunk_id >> YAFFS_TNODES_LEVEL0_BITS;
+	required_depth = 0;
+	while (i) {
+		i >>= YAFFS_TNODES_INTERNAL_BITS;
+		required_depth++;
+	}
+
+	if (required_depth > file_struct->top_level)
+		return NULL;	/* Not tall enough, so we can't find it */
+
+	/* Traverse down to level 0 */
+	while (level > 0 && tn) {
+		tn = tn->internal[(chunk_id >>
+				   (YAFFS_TNODES_LEVEL0_BITS +
+				    (level - 1) *
+				    YAFFS_TNODES_INTERNAL_BITS)) &
+				  YAFFS_TNODES_INTERNAL_MASK];
+		level--;
+	}
+
+	return tn;
+}
+
+/* add_find_tnode_0 finds the level 0 tnode if it exists,
+ * otherwise first expands the tree.
+ * This happens in two steps:
+ *  1. If the tree isn't tall enough, then make it taller.
+ *  2. Scan down the tree towards the level 0 tnode adding tnodes if required.
+ *
+ * Used when modifying the tree.
+ *
+ *  If the tn argument is NULL, then a fresh tnode will be added otherwise the
+ *  specified tn will be plugged into the ttree.
+ */
+
+struct yaffs_tnode *yaffs_add_find_tnode_0(struct yaffs_dev *dev,
+					   struct yaffs_file_var *file_struct,
+					   u32 chunk_id,
+					   struct yaffs_tnode *passed_tn)
+{
+	int required_depth;
+	int i;
+	int l;
+	struct yaffs_tnode *tn;
+	u32 x;
+
+	/* Check sane level and page Id */
+	if (file_struct->top_level < 0 ||
+	    file_struct->top_level > YAFFS_TNODES_MAX_LEVEL)
+		return NULL;
+
+	if (chunk_id > YAFFS_MAX_CHUNK_ID)
+		return NULL;
+
+	/* First check we're tall enough (ie enough top_level) */
+
+	x = chunk_id >> YAFFS_TNODES_LEVEL0_BITS;
+	required_depth = 0;
+	while (x) {
+		x >>= YAFFS_TNODES_INTERNAL_BITS;
+		required_depth++;
+	}
+
+	if (required_depth > file_struct->top_level) {
+		/* Not tall enough, gotta make the tree taller */
+		for (i = file_struct->top_level; i < required_depth; i++) {
+
+			tn = yaffs_get_tnode(dev);
+
+			if (tn) {
+				tn->internal[0] = file_struct->top;
+				file_struct->top = tn;
+				file_struct->top_level++;
+			} else {
+				yaffs_trace(YAFFS_TRACE_ERROR,
+					"yaffs: no more tnodes");
+				return NULL;
+			}
+		}
+	}
+
+	/* Traverse down to level 0, adding anything we need */
+
+	l = file_struct->top_level;
+	tn = file_struct->top;
+
+	if (l > 0) {
+		while (l > 0 && tn) {
+			x = (chunk_id >>
+			     (YAFFS_TNODES_LEVEL0_BITS +
+			      (l - 1) * YAFFS_TNODES_INTERNAL_BITS)) &
+			    YAFFS_TNODES_INTERNAL_MASK;
+
+			if ((l > 1) && !tn->internal[x]) {
+				/* Add missing non-level-zero tnode */
+				tn->internal[x] = yaffs_get_tnode(dev);
+				if (!tn->internal[x])
+					return NULL;
+			} else if (l == 1) {
+				/* Looking from level 1 at level 0 */
+				if (passed_tn) {
+					/* If we already have one, release it */
+					if (tn->internal[x])
+						yaffs_free_tnode(dev,
+							tn->internal[x]);
+					tn->internal[x] = passed_tn;
+
+				} else if (!tn->internal[x]) {
+					/* Don't have one, none passed in */
+					tn->internal[x] = yaffs_get_tnode(dev);
+					if (!tn->internal[x])
+						return NULL;
+				}
+			}
+
+			tn = tn->internal[x];
+			l--;
+		}
+	} else {
+		/* top is level 0 */
+		if (passed_tn) {
+			memcpy(tn, passed_tn,
+			       (dev->tnode_width * YAFFS_NTNODES_LEVEL0) / 8);
+			yaffs_free_tnode(dev, passed_tn);
+		}
+	}
+
+	return tn;
+}
+
+static int yaffs_tags_match(const struct yaffs_ext_tags *tags, int obj_id,
+			    int chunk_obj)
+{
+	return (tags->chunk_id == chunk_obj &&
+		tags->obj_id == obj_id &&
+		!tags->is_deleted) ? 1 : 0;
+
+}
+
+static int yaffs_find_chunk_in_group(struct yaffs_dev *dev, int the_chunk,
+					struct yaffs_ext_tags *tags, int obj_id,
+					int inode_chunk)
+{
+	int j;
+
+	for (j = 0; the_chunk && j < dev->chunk_grp_size; j++) {
+		if (yaffs_check_chunk_bit
+		    (dev, the_chunk / dev->param.chunks_per_block,
+		     the_chunk % dev->param.chunks_per_block)) {
+
+			if (dev->chunk_grp_size == 1)
+				return the_chunk;
+			else {
+				yaffs_rd_chunk_tags_nand(dev, the_chunk, NULL,
+							 tags);
+				if (yaffs_tags_match(tags,
+							obj_id, inode_chunk)) {
+					/* found it; */
+					return the_chunk;
+				}
+			}
+		}
+		the_chunk++;
+	}
+	return -1;
+}
+
+int yaffs_find_chunk_in_file(struct yaffs_obj *in, int inode_chunk,
+				    struct yaffs_ext_tags *tags)
+{
+	/*Get the Tnode, then get the level 0 offset chunk offset */
+	struct yaffs_tnode *tn;
+	int the_chunk = -1;
+	struct yaffs_ext_tags local_tags;
+	int ret_val = -1;
+	struct yaffs_dev *dev = in->my_dev;
+
+	if (!tags) {
+		/* Passed a NULL, so use our own tags space */
+		tags = &local_tags;
+	}
+
+	tn = yaffs_find_tnode_0(dev, &in->variant.file_variant, inode_chunk);
+
+	if (!tn)
+		return ret_val;
+
+	the_chunk = yaffs_get_group_base(dev, tn, inode_chunk);
+
+	ret_val = yaffs_find_chunk_in_group(dev, the_chunk, tags, in->obj_id,
+					      inode_chunk);
+	return ret_val;
+}
+
+static int yaffs_find_del_file_chunk(struct yaffs_obj *in, int inode_chunk,
+				     struct yaffs_ext_tags *tags)
+{
+	/* Get the Tnode, then get the level 0 offset chunk offset */
+	struct yaffs_tnode *tn;
+	int the_chunk = -1;
+	struct yaffs_ext_tags local_tags;
+	struct yaffs_dev *dev = in->my_dev;
+	int ret_val = -1;
+
+	if (!tags) {
+		/* Passed a NULL, so use our own tags space */
+		tags = &local_tags;
+	}
+
+	tn = yaffs_find_tnode_0(dev, &in->variant.file_variant, inode_chunk);
+
+	if (!tn)
+		return ret_val;
+
+	the_chunk = yaffs_get_group_base(dev, tn, inode_chunk);
+
+	ret_val = yaffs_find_chunk_in_group(dev, the_chunk, tags, in->obj_id,
+					      inode_chunk);
+
+	/* Delete the entry in the filestructure (if found) */
+	if (ret_val != -1)
+		yaffs_load_tnode_0(dev, tn, inode_chunk, 0);
+
+	return ret_val;
+}
+
+int yaffs_put_chunk_in_file(struct yaffs_obj *in, int inode_chunk,
+			    int nand_chunk, int in_scan)
+{
+	/* NB in_scan is zero unless scanning.
+	 * For forward scanning, in_scan is > 0;
+	 * for backward scanning in_scan is < 0
+	 *
+	 * nand_chunk = 0 is a dummy insert to make sure the tnodes are there.
+	 */
+
+	struct yaffs_tnode *tn;
+	struct yaffs_dev *dev = in->my_dev;
+	int existing_cunk;
+	struct yaffs_ext_tags existing_tags;
+	struct yaffs_ext_tags new_tags;
+	unsigned existing_serial, new_serial;
+
+	if (in->variant_type != YAFFS_OBJECT_TYPE_FILE) {
+		/* Just ignore an attempt at putting a chunk into a non-file
+		 * during scanning.
+		 * If it is not during Scanning then something went wrong!
+		 */
+		if (!in_scan) {
+			yaffs_trace(YAFFS_TRACE_ERROR,
+				"yaffs tragedy:attempt to put data chunk into a non-file"
+				);
+			BUG();
+		}
+
+		yaffs_chunk_del(dev, nand_chunk, 1, __LINE__);
+		return YAFFS_OK;
+	}
+
+	tn = yaffs_add_find_tnode_0(dev,
+				    &in->variant.file_variant,
+				    inode_chunk, NULL);
+	if (!tn)
+		return YAFFS_FAIL;
+
+	if (!nand_chunk)
+		/* Dummy insert, bail now */
+		return YAFFS_OK;
+
+	existing_cunk = yaffs_get_group_base(dev, tn, inode_chunk);
+
+	if (in_scan != 0) {
+		/* If we're scanning then we need to test for duplicates
+		 * NB This does not need to be efficient since it should only
+		 * happen when the power fails during a write, then only one
+		 * chunk should ever be affected.
+		 *
+		 * Correction for YAFFS2: This could happen quite a lot and we
+		 * need to think about efficiency! TODO
+		 * Update: For backward scanning we don't need to re-read tags
+		 * so this is quite cheap.
+		 */
+
+		if (existing_cunk > 0) {
+			/* NB Right now existing chunk will not be real
+			 * chunk_id if the chunk group size > 1
+			 * thus we have to do a FindChunkInFile to get the
+			 * real chunk id.
+			 *
+			 * We have a duplicate now we need to decide which
+			 * one to use:
+			 *
+			 * Backwards scanning YAFFS2: The old one is what
+			 * we use, dump the new one.
+			 * YAFFS1: Get both sets of tags and compare serial
+			 * numbers.
+			 */
+
+			if (in_scan > 0) {
+				/* Only do this for forward scanning */
+				yaffs_rd_chunk_tags_nand(dev,
+							 nand_chunk,
+							 NULL, &new_tags);
+
+				/* Do a proper find */
+				existing_cunk =
+				    yaffs_find_chunk_in_file(in, inode_chunk,
+							     &existing_tags);
+			}
+
+			if (existing_cunk <= 0) {
+				/*Hoosterman - how did this happen? */
+
+				yaffs_trace(YAFFS_TRACE_ERROR,
+					"yaffs tragedy: existing chunk < 0 in scan"
+					);
+
+			}
+
+			/* NB The deleted flags should be false, otherwise
+			 * the chunks will not be loaded during a scan
+			 */
+
+			if (in_scan > 0) {
+				new_serial = new_tags.serial_number;
+				existing_serial = existing_tags.serial_number;
+			}
+
+			if ((in_scan > 0) &&
+			    (existing_cunk <= 0 ||
+			     ((existing_serial + 1) & 3) == new_serial)) {
+				/* Forward scanning.
+				 * Use new
+				 * Delete the old one and drop through to
+				 * update the tnode
+				 */
+				yaffs_chunk_del(dev, existing_cunk, 1,
+						__LINE__);
+			} else {
+				/* Backward scanning or we want to use the
+				 * existing one
+				 * Delete the new one and return early so that
+				 * the tnode isn't changed
+				 */
+				yaffs_chunk_del(dev, nand_chunk, 1, __LINE__);
+				return YAFFS_OK;
+			}
+		}
+
+	}
+
+	if (existing_cunk == 0)
+		in->n_data_chunks++;
+
+	yaffs_load_tnode_0(dev, tn, inode_chunk, nand_chunk);
+
+	return YAFFS_OK;
+}
+
+static void yaffs_soft_del_chunk(struct yaffs_dev *dev, int chunk)
+{
+	struct yaffs_block_info *the_block;
+	unsigned block_no;
+
+	yaffs_trace(YAFFS_TRACE_DELETION, "soft delete chunk %d", chunk);
+
+	block_no = chunk / dev->param.chunks_per_block;
+	the_block = yaffs_get_block_info(dev, block_no);
+	if (the_block) {
+		the_block->soft_del_pages++;
+		dev->n_free_chunks++;
+		yaffs2_update_oldest_dirty_seq(dev, block_no, the_block);
+	}
+}
+
+/* SoftDeleteWorker scans backwards through the tnode tree and soft deletes all
+ * the chunks in the file.
+ * All soft deleting does is increment the block's softdelete count and pulls
+ * the chunk out of the tnode.
+ * Thus, essentially this is the same as DeleteWorker except that the chunks
+ * are soft deleted.
+ */
+
+static int yaffs_soft_del_worker(struct yaffs_obj *in, struct yaffs_tnode *tn,
+				 u32 level, int chunk_offset)
+{
+	int i;
+	int the_chunk;
+	int all_done = 1;
+	struct yaffs_dev *dev = in->my_dev;
+
+	if (!tn)
+		return 1;
+
+	if (level > 0) {
+		for (i = YAFFS_NTNODES_INTERNAL - 1;
+			all_done && i >= 0;
+			i--) {
+			if (tn->internal[i]) {
+				all_done =
+				    yaffs_soft_del_worker(in,
+					tn->internal[i],
+					level - 1,
+					(chunk_offset <<
+					YAFFS_TNODES_INTERNAL_BITS)
+					+ i);
+				if (all_done) {
+					yaffs_free_tnode(dev,
+						tn->internal[i]);
+					tn->internal[i] = NULL;
+				} else {
+					/* Can this happen? */
+				}
+			}
+		}
+		return (all_done) ? 1 : 0;
+	}
+
+	/* level 0 */
+	 for (i = YAFFS_NTNODES_LEVEL0 - 1; i >= 0; i--) {
+		the_chunk = yaffs_get_group_base(dev, tn, i);
+		if (the_chunk) {
+			yaffs_soft_del_chunk(dev, the_chunk);
+			yaffs_load_tnode_0(dev, tn, i, 0);
+		}
+	}
+	return 1;
+}
+
+static void yaffs_remove_obj_from_dir(struct yaffs_obj *obj)
+{
+	struct yaffs_dev *dev = obj->my_dev;
+	struct yaffs_obj *parent;
+
+	yaffs_verify_obj_in_dir(obj);
+	parent = obj->parent;
+
+	yaffs_verify_dir(parent);
+
+	if (dev && dev->param.remove_obj_fn)
+		dev->param.remove_obj_fn(obj);
+
+	list_del_init(&obj->siblings);
+	obj->parent = NULL;
+
+	yaffs_verify_dir(parent);
+}
+
+void yaffs_add_obj_to_dir(struct yaffs_obj *directory, struct yaffs_obj *obj)
+{
+	if (!directory) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"tragedy: Trying to add an object to a null pointer directory"
+			);
+		BUG();
+		return;
+	}
+	if (directory->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"tragedy: Trying to add an object to a non-directory"
+			);
+		BUG();
+	}
+
+	if (obj->siblings.prev == NULL) {
+		/* Not initialised */
+		BUG();
+	}
+
+	yaffs_verify_dir(directory);
+
+	yaffs_remove_obj_from_dir(obj);
+
+	/* Now add it */
+	list_add(&obj->siblings, &directory->variant.dir_variant.children);
+	obj->parent = directory;
+
+	if (directory == obj->my_dev->unlinked_dir
+	    || directory == obj->my_dev->del_dir) {
+		obj->unlinked = 1;
+		obj->my_dev->n_unlinked_files++;
+		obj->rename_allowed = 0;
+	}
+
+	yaffs_verify_dir(directory);
+	yaffs_verify_obj_in_dir(obj);
+}
+
+static int yaffs_change_obj_name(struct yaffs_obj *obj,
+				 struct yaffs_obj *new_dir,
+				 const YCHAR *new_name, int force, int shadows)
+{
+	int unlink_op;
+	int del_op;
+	struct yaffs_obj *existing_target;
+
+	if (new_dir == NULL)
+		new_dir = obj->parent;	/* use the old directory */
+
+	if (new_dir->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"tragedy: yaffs_change_obj_name: new_dir is not a directory"
+			);
+		BUG();
+	}
+
+	unlink_op = (new_dir == obj->my_dev->unlinked_dir);
+	del_op = (new_dir == obj->my_dev->del_dir);
+
+	existing_target = yaffs_find_by_name(new_dir, new_name);
+
+	/* If the object is a file going into the unlinked directory,
+	 *   then it is OK to just stuff it in since duplicate names are OK.
+	 *   else only proceed if the new name does not exist and we're putting
+	 *   it into a directory.
+	 */
+	if (!(unlink_op || del_op || force ||
+	      shadows > 0 || !existing_target) ||
+	      new_dir->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY)
+		return YAFFS_FAIL;
+
+	yaffs_set_obj_name(obj, new_name);
+	obj->dirty = 1;
+	yaffs_add_obj_to_dir(new_dir, obj);
+
+	if (unlink_op)
+		obj->unlinked = 1;
+
+	/* If it is a deletion then we mark it as a shrink for gc  */
+	if (yaffs_update_oh(obj, new_name, 0, del_op, shadows, NULL) >= 0)
+		return YAFFS_OK;
+
+	return YAFFS_FAIL;
+}
+
+/*------------------------ Short Operations Cache ------------------------------
+ *   In many situations where there is no high level buffering  a lot of
+ *   reads might be short sequential reads, and a lot of writes may be short
+ *   sequential writes. eg. scanning/writing a jpeg file.
+ *   In these cases, a short read/write cache can provide a huge perfomance
+ *   benefit with dumb-as-a-rock code.
+ *   In Linux, the page cache provides read buffering and the short op cache
+ *   provides write buffering.
+ *
+ *   There are a small number (~10) of cache chunks per device so that we don't
+ *   need a very intelligent search.
+ */
+
+static int yaffs_obj_cache_dirty(struct yaffs_obj *obj)
+{
+	struct yaffs_dev *dev = obj->my_dev;
+	int i;
+	struct yaffs_cache *cache;
+	int n_caches = obj->my_dev->param.n_caches;
+
+	for (i = 0; i < n_caches; i++) {
+		cache = &dev->cache[i];
+		if (cache->object == obj && cache->dirty)
+			return 1;
+	}
+
+	return 0;
+}
+
+static void yaffs_flush_file_cache(struct yaffs_obj *obj)
+{
+	struct yaffs_dev *dev = obj->my_dev;
+	int lowest = -99;	/* Stop compiler whining. */
+	int i;
+	struct yaffs_cache *cache;
+	int chunk_written = 0;
+	int n_caches = obj->my_dev->param.n_caches;
+
+	if (n_caches < 1)
+		return;
+	do {
+		cache = NULL;
+
+		/* Find the lowest dirty chunk for this object */
+		for (i = 0; i < n_caches; i++) {
+			if (dev->cache[i].object == obj &&
+			    dev->cache[i].dirty) {
+				if (!cache ||
+				    dev->cache[i].chunk_id < lowest) {
+					cache = &dev->cache[i];
+					lowest = cache->chunk_id;
+				}
+			}
+		}
+
+		if (cache && !cache->locked) {
+			/* Write it out and free it up */
+			chunk_written =
+			    yaffs_wr_data_obj(cache->object,
+					      cache->chunk_id,
+					      cache->data,
+					      cache->n_bytes, 1);
+			cache->dirty = 0;
+			cache->object = NULL;
+		}
+	} while (cache && chunk_written > 0);
+
+	if (cache)
+		/* Hoosterman, disk full while writing cache out. */
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"yaffs tragedy: no space during cache write");
+}
+
+/*yaffs_flush_whole_cache(dev)
+ *
+ *
+ */
+
+void yaffs_flush_whole_cache(struct yaffs_dev *dev)
+{
+	struct yaffs_obj *obj;
+	int n_caches = dev->param.n_caches;
+	int i;
+
+	/* Find a dirty object in the cache and flush it...
+	 * until there are no further dirty objects.
+	 */
+	do {
+		obj = NULL;
+		for (i = 0; i < n_caches && !obj; i++) {
+			if (dev->cache[i].object && dev->cache[i].dirty)
+				obj = dev->cache[i].object;
+		}
+		if (obj)
+			yaffs_flush_file_cache(obj);
+	} while (obj);
+
+}
+
+/* Grab us a cache chunk for use.
+ * First look for an empty one.
+ * Then look for the least recently used non-dirty one.
+ * Then look for the least recently used dirty one...., flush and look again.
+ */
+static struct yaffs_cache *yaffs_grab_chunk_worker(struct yaffs_dev *dev)
+{
+	int i;
+
+	if (dev->param.n_caches > 0) {
+		for (i = 0; i < dev->param.n_caches; i++) {
+			if (!dev->cache[i].object)
+				return &dev->cache[i];
+		}
+	}
+	return NULL;
+}
+
+static struct yaffs_cache *yaffs_grab_chunk_cache(struct yaffs_dev *dev)
+{
+	struct yaffs_cache *cache;
+	struct yaffs_obj *the_obj;
+	int usage;
+	int i;
+	int pushout;
+
+	if (dev->param.n_caches < 1)
+		return NULL;
+
+	/* Try find a non-dirty one... */
+
+	cache = yaffs_grab_chunk_worker(dev);
+
+	if (!cache) {
+		/* They were all dirty, find the LRU object and flush
+		 * its cache, then  find again.
+		 * NB what's here is not very accurate,
+		 * we actually flush the object with the LRU chunk.
+		 */
+
+		/* With locking we can't assume we can use entry zero,
+		 * Set the_obj to a valid pointer for Coverity. */
+		the_obj = dev->cache[0].object;
+		usage = -1;
+		cache = NULL;
+		pushout = -1;
+
+		for (i = 0; i < dev->param.n_caches; i++) {
+			if (dev->cache[i].object &&
+			    !dev->cache[i].locked &&
+			    (dev->cache[i].last_use < usage ||
+			    !cache)) {
+				usage = dev->cache[i].last_use;
+				the_obj = dev->cache[i].object;
+				cache = &dev->cache[i];
+				pushout = i;
+			}
+		}
+
+		if (!cache || cache->dirty) {
+			/* Flush and try again */
+			yaffs_flush_file_cache(the_obj);
+			cache = yaffs_grab_chunk_worker(dev);
+		}
+	}
+	return cache;
+}
+
+/* Find a cached chunk */
+static struct yaffs_cache *yaffs_find_chunk_cache(const struct yaffs_obj *obj,
+						  int chunk_id)
+{
+	struct yaffs_dev *dev = obj->my_dev;
+	int i;
+
+	if (dev->param.n_caches < 1)
+		return NULL;
+
+	for (i = 0; i < dev->param.n_caches; i++) {
+		if (dev->cache[i].object == obj &&
+		    dev->cache[i].chunk_id == chunk_id) {
+			dev->cache_hits++;
+
+			return &dev->cache[i];
+		}
+	}
+	return NULL;
+}
+
+/* Mark the chunk for the least recently used algorithym */
+static void yaffs_use_cache(struct yaffs_dev *dev, struct yaffs_cache *cache,
+			    int is_write)
+{
+	int i;
+
+	if (dev->param.n_caches < 1)
+		return;
+
+	if (dev->cache_last_use < 0 ||
+		dev->cache_last_use > 100000000) {
+		/* Reset the cache usages */
+		for (i = 1; i < dev->param.n_caches; i++)
+			dev->cache[i].last_use = 0;
+
+		dev->cache_last_use = 0;
+	}
+	dev->cache_last_use++;
+	cache->last_use = dev->cache_last_use;
+
+	if (is_write)
+		cache->dirty = 1;
+}
+
+/* Invalidate a single cache page.
+ * Do this when a whole page gets written,
+ * ie the short cache for this page is no longer valid.
+ */
+static void yaffs_invalidate_chunk_cache(struct yaffs_obj *object, int chunk_id)
+{
+	struct yaffs_cache *cache;
+
+	if (object->my_dev->param.n_caches > 0) {
+		cache = yaffs_find_chunk_cache(object, chunk_id);
+
+		if (cache)
+			cache->object = NULL;
+	}
+}
+
+/* Invalidate all the cache pages associated with this object
+ * Do this whenever ther file is deleted or resized.
+ */
+static void yaffs_invalidate_whole_cache(struct yaffs_obj *in)
+{
+	int i;
+	struct yaffs_dev *dev = in->my_dev;
+
+	if (dev->param.n_caches > 0) {
+		/* Invalidate it. */
+		for (i = 0; i < dev->param.n_caches; i++) {
+			if (dev->cache[i].object == in)
+				dev->cache[i].object = NULL;
+		}
+	}
+}
+
+static void yaffs_unhash_obj(struct yaffs_obj *obj)
+{
+	int bucket;
+	struct yaffs_dev *dev = obj->my_dev;
+
+	/* If it is still linked into the bucket list, free from the list */
+	if (!list_empty(&obj->hash_link)) {
+		list_del_init(&obj->hash_link);
+		bucket = yaffs_hash_fn(obj->obj_id);
+		dev->obj_bucket[bucket].count--;
+	}
+}
+
+/*  FreeObject frees up a Object and puts it back on the free list */
+static void yaffs_free_obj(struct yaffs_obj *obj)
+{
+	struct yaffs_dev *dev;
+
+	if (!obj) {
+		BUG();
+		return;
+	}
+	dev = obj->my_dev;
+	yaffs_trace(YAFFS_TRACE_OS, "FreeObject %p inode %p",
+		obj, obj->my_inode);
+	if (obj->parent)
+		BUG();
+	if (!list_empty(&obj->siblings))
+		BUG();
+
+	if (obj->my_inode) {
+		/* We're still hooked up to a cached inode.
+		 * Don't delete now, but mark for later deletion
+		 */
+		obj->defered_free = 1;
+		return;
+	}
+
+	yaffs_unhash_obj(obj);
+
+	yaffs_free_raw_obj(dev, obj);
+	dev->n_obj--;
+	dev->checkpoint_blocks_required = 0;	/* force recalculation */
+}
+
+void yaffs_handle_defered_free(struct yaffs_obj *obj)
+{
+	if (obj->defered_free)
+		yaffs_free_obj(obj);
+}
+
+static int yaffs_generic_obj_del(struct yaffs_obj *in)
+{
+	/* Iinvalidate the file's data in the cache, without flushing. */
+	yaffs_invalidate_whole_cache(in);
+
+	if (in->my_dev->param.is_yaffs2 && in->parent != in->my_dev->del_dir) {
+		/* Move to unlinked directory so we have a deletion record */
+		yaffs_change_obj_name(in, in->my_dev->del_dir, _Y("deleted"), 0,
+				      0);
+	}
+
+	yaffs_remove_obj_from_dir(in);
+	yaffs_chunk_del(in->my_dev, in->hdr_chunk, 1, __LINE__);
+	in->hdr_chunk = 0;
+
+	yaffs_free_obj(in);
+	return YAFFS_OK;
+
+}
+
+static void yaffs_soft_del_file(struct yaffs_obj *obj)
+{
+	if (!obj->deleted ||
+	    obj->variant_type != YAFFS_OBJECT_TYPE_FILE ||
+	    obj->soft_del)
+		return;
+
+	if (obj->n_data_chunks <= 0) {
+		/* Empty file with no duplicate object headers,
+		 * just delete it immediately */
+		yaffs_free_tnode(obj->my_dev, obj->variant.file_variant.top);
+		obj->variant.file_variant.top = NULL;
+		yaffs_trace(YAFFS_TRACE_TRACING,
+			"yaffs: Deleting empty file %d",
+			obj->obj_id);
+		yaffs_generic_obj_del(obj);
+	} else {
+		yaffs_soft_del_worker(obj,
+				      obj->variant.file_variant.top,
+				      obj->variant.
+				      file_variant.top_level, 0);
+		obj->soft_del = 1;
+	}
+}
+
+/* Pruning removes any part of the file structure tree that is beyond the
+ * bounds of the file (ie that does not point to chunks).
+ *
+ * A file should only get pruned when its size is reduced.
+ *
+ * Before pruning, the chunks must be pulled from the tree and the
+ * level 0 tnode entries must be zeroed out.
+ * Could also use this for file deletion, but that's probably better handled
+ * by a special case.
+ *
+ * This function is recursive. For levels > 0 the function is called again on
+ * any sub-tree. For level == 0 we just check if the sub-tree has data.
+ * If there is no data in a subtree then it is pruned.
+ */
+
+static struct yaffs_tnode *yaffs_prune_worker(struct yaffs_dev *dev,
+					      struct yaffs_tnode *tn, u32 level,
+					      int del0)
+{
+	int i;
+	int has_data;
+
+	if (!tn)
+		return tn;
+
+	has_data = 0;
+
+	if (level > 0) {
+		for (i = 0; i < YAFFS_NTNODES_INTERNAL; i++) {
+			if (tn->internal[i]) {
+				tn->internal[i] =
+				    yaffs_prune_worker(dev,
+						tn->internal[i],
+						level - 1,
+						(i == 0) ? del0 : 1);
+			}
+
+			if (tn->internal[i])
+				has_data++;
+		}
+	} else {
+		int tnode_size_u32 = dev->tnode_size / sizeof(u32);
+		u32 *map = (u32 *) tn;
+
+		for (i = 0; !has_data && i < tnode_size_u32; i++) {
+			if (map[i])
+				has_data++;
+		}
+	}
+
+	if (has_data == 0 && del0) {
+		/* Free and return NULL */
+		yaffs_free_tnode(dev, tn);
+		tn = NULL;
+	}
+	return tn;
+}
+
+static int yaffs_prune_tree(struct yaffs_dev *dev,
+			    struct yaffs_file_var *file_struct)
+{
+	int i;
+	int has_data;
+	int done = 0;
+	struct yaffs_tnode *tn;
+
+	if (file_struct->top_level < 1)
+		return YAFFS_OK;
+
+	file_struct->top =
+	   yaffs_prune_worker(dev, file_struct->top, file_struct->top_level, 0);
+
+	/* Now we have a tree with all the non-zero branches NULL but
+	 * the height is the same as it was.
+	 * Let's see if we can trim internal tnodes to shorten the tree.
+	 * We can do this if only the 0th element in the tnode is in use
+	 * (ie all the non-zero are NULL)
+	 */
+
+	while (file_struct->top_level && !done) {
+		tn = file_struct->top;
+
+		has_data = 0;
+		for (i = 1; i < YAFFS_NTNODES_INTERNAL; i++) {
+			if (tn->internal[i])
+				has_data++;
+		}
+
+		if (!has_data) {
+			file_struct->top = tn->internal[0];
+			file_struct->top_level--;
+			yaffs_free_tnode(dev, tn);
+		} else {
+			done = 1;
+		}
+	}
+
+	return YAFFS_OK;
+}
+
+/*-------------------- End of File Structure functions.-------------------*/
+
+/* alloc_empty_obj gets us a clean Object.*/
+static struct yaffs_obj *yaffs_alloc_empty_obj(struct yaffs_dev *dev)
+{
+	struct yaffs_obj *obj = yaffs_alloc_raw_obj(dev);
+
+	if (!obj)
+		return obj;
+
+	dev->n_obj++;
+
+	/* Now sweeten it up... */
+
+	memset(obj, 0, sizeof(struct yaffs_obj));
+	obj->being_created = 1;
+
+	obj->my_dev = dev;
+	obj->hdr_chunk = 0;
+	obj->variant_type = YAFFS_OBJECT_TYPE_UNKNOWN;
+	INIT_LIST_HEAD(&(obj->hard_links));
+	INIT_LIST_HEAD(&(obj->hash_link));
+	INIT_LIST_HEAD(&obj->siblings);
+
+	/* Now make the directory sane */
+	if (dev->root_dir) {
+		obj->parent = dev->root_dir;
+		list_add(&(obj->siblings),
+			 &dev->root_dir->variant.dir_variant.children);
+	}
+
+	/* Add it to the lost and found directory.
+	 * NB Can't put root or lost-n-found in lost-n-found so
+	 * check if lost-n-found exists first
+	 */
+	if (dev->lost_n_found)
+		yaffs_add_obj_to_dir(dev->lost_n_found, obj);
+
+	obj->being_created = 0;
+
+	dev->checkpoint_blocks_required = 0;	/* force recalculation */
+
+	return obj;
+}
+
+static int yaffs_find_nice_bucket(struct yaffs_dev *dev)
+{
+	int i;
+	int l = 999;
+	int lowest = 999999;
+
+	/* Search for the shortest list or one that
+	 * isn't too long.
+	 */
+
+	for (i = 0; i < 10 && lowest > 4; i++) {
+		dev->bucket_finder++;
+		dev->bucket_finder %= YAFFS_NOBJECT_BUCKETS;
+		if (dev->obj_bucket[dev->bucket_finder].count < lowest) {
+			lowest = dev->obj_bucket[dev->bucket_finder].count;
+			l = dev->bucket_finder;
+		}
+	}
+
+	return l;
+}
+
+static int yaffs_new_obj_id(struct yaffs_dev *dev)
+{
+	int bucket = yaffs_find_nice_bucket(dev);
+	int found = 0;
+	struct list_head *i;
+	u32 n = (u32) bucket;
+
+	/* Now find an object value that has not already been taken
+	 * by scanning the list.
+	 */
+
+	while (!found) {
+		found = 1;
+		n += YAFFS_NOBJECT_BUCKETS;
+		if (1 || dev->obj_bucket[bucket].count > 0) {
+			list_for_each(i, &dev->obj_bucket[bucket].list) {
+				/* If there is already one in the list */
+				if (i && list_entry(i, struct yaffs_obj,
+						    hash_link)->obj_id == n) {
+					found = 0;
+				}
+			}
+		}
+	}
+	return n;
+}
+
+static void yaffs_hash_obj(struct yaffs_obj *in)
+{
+	int bucket = yaffs_hash_fn(in->obj_id);
+	struct yaffs_dev *dev = in->my_dev;
+
+	list_add(&in->hash_link, &dev->obj_bucket[bucket].list);
+	dev->obj_bucket[bucket].count++;
+}
+
+struct yaffs_obj *yaffs_find_by_number(struct yaffs_dev *dev, u32 number)
+{
+	int bucket = yaffs_hash_fn(number);
+	struct list_head *i;
+	struct yaffs_obj *in;
+
+	list_for_each(i, &dev->obj_bucket[bucket].list) {
+		/* Look if it is in the list */
+		in = list_entry(i, struct yaffs_obj, hash_link);
+		if (in->obj_id == number) {
+			/* Don't show if it is defered free */
+			if (in->defered_free)
+				return NULL;
+			return in;
+		}
+	}
+
+	return NULL;
+}
+
+static struct yaffs_obj *yaffs_new_obj(struct yaffs_dev *dev, int number,
+				enum yaffs_obj_type type)
+{
+	struct yaffs_obj *the_obj = NULL;
+	struct yaffs_tnode *tn = NULL;
+
+	if (number < 0)
+		number = yaffs_new_obj_id(dev);
+
+	if (type == YAFFS_OBJECT_TYPE_FILE) {
+		tn = yaffs_get_tnode(dev);
+		if (!tn)
+			return NULL;
+	}
+
+	the_obj = yaffs_alloc_empty_obj(dev);
+	if (!the_obj) {
+		if (tn)
+			yaffs_free_tnode(dev, tn);
+		return NULL;
+	}
+
+	the_obj->fake = 0;
+	the_obj->rename_allowed = 1;
+	the_obj->unlink_allowed = 1;
+	the_obj->obj_id = number;
+	yaffs_hash_obj(the_obj);
+	the_obj->variant_type = type;
+	yaffs_load_current_time(the_obj, 1, 1);
+
+	switch (type) {
+	case YAFFS_OBJECT_TYPE_FILE:
+		the_obj->variant.file_variant.file_size = 0;
+		the_obj->variant.file_variant.scanned_size = 0;
+		the_obj->variant.file_variant.shrink_size =
+						yaffs_max_file_size(dev);
+		the_obj->variant.file_variant.top_level = 0;
+		the_obj->variant.file_variant.top = tn;
+		break;
+	case YAFFS_OBJECT_TYPE_DIRECTORY:
+		INIT_LIST_HEAD(&the_obj->variant.dir_variant.children);
+		INIT_LIST_HEAD(&the_obj->variant.dir_variant.dirty);
+		break;
+	case YAFFS_OBJECT_TYPE_SYMLINK:
+	case YAFFS_OBJECT_TYPE_HARDLINK:
+	case YAFFS_OBJECT_TYPE_SPECIAL:
+		/* No action required */
+		break;
+	case YAFFS_OBJECT_TYPE_UNKNOWN:
+		/* todo this should not happen */
+		break;
+	}
+	return the_obj;
+}
+
+static struct yaffs_obj *yaffs_create_fake_dir(struct yaffs_dev *dev,
+					       int number, u32 mode)
+{
+
+	struct yaffs_obj *obj =
+	    yaffs_new_obj(dev, number, YAFFS_OBJECT_TYPE_DIRECTORY);
+
+	if (!obj)
+		return NULL;
+
+	obj->fake = 1;	/* it is fake so it might not use NAND */
+	obj->rename_allowed = 0;
+	obj->unlink_allowed = 0;
+	obj->deleted = 0;
+	obj->unlinked = 0;
+	obj->yst_mode = mode;
+	obj->my_dev = dev;
+	obj->hdr_chunk = 0;	/* Not a valid chunk. */
+	return obj;
+
+}
+
+
+static void yaffs_init_tnodes_and_objs(struct yaffs_dev *dev)
+{
+	int i;
+
+	dev->n_obj = 0;
+	dev->n_tnodes = 0;
+	yaffs_init_raw_tnodes_and_objs(dev);
+
+	for (i = 0; i < YAFFS_NOBJECT_BUCKETS; i++) {
+		INIT_LIST_HEAD(&dev->obj_bucket[i].list);
+		dev->obj_bucket[i].count = 0;
+	}
+}
+
+struct yaffs_obj *yaffs_find_or_create_by_number(struct yaffs_dev *dev,
+						 int number,
+						 enum yaffs_obj_type type)
+{
+	struct yaffs_obj *the_obj = NULL;
+
+	if (number > 0)
+		the_obj = yaffs_find_by_number(dev, number);
+
+	if (!the_obj)
+		the_obj = yaffs_new_obj(dev, number, type);
+
+	return the_obj;
+
+}
+
+YCHAR *yaffs_clone_str(const YCHAR *str)
+{
+	YCHAR *new_str = NULL;
+	int len;
+
+	if (!str)
+		str = _Y("");
+
+	len = strnlen(str, YAFFS_MAX_ALIAS_LENGTH);
+	new_str = kmalloc((len + 1) * sizeof(YCHAR), GFP_NOFS);
+	if (new_str) {
+		strncpy(new_str, str, len);
+		new_str[len] = 0;
+	}
+	return new_str;
+
+}
+/*
+ *yaffs_update_parent() handles fixing a directories mtime and ctime when a new
+ * link (ie. name) is created or deleted in the directory.
+ *
+ * ie.
+ *   create dir/a : update dir's mtime/ctime
+ *   rm dir/a:   update dir's mtime/ctime
+ *   modify dir/a: don't update dir's mtimme/ctime
+ *
+ * This can be handled immediately or defered. Defering helps reduce the number
+ * of updates when many files in a directory are changed within a brief period.
+ *
+ * If the directory updating is defered then yaffs_update_dirty_dirs must be
+ * called periodically.
+ */
+
+static void yaffs_update_parent(struct yaffs_obj *obj)
+{
+	struct yaffs_dev *dev;
+
+	if (!obj)
+		return;
+	dev = obj->my_dev;
+	obj->dirty = 1;
+	yaffs_load_current_time(obj, 0, 1);
+	if (dev->param.defered_dir_update) {
+		struct list_head *link = &obj->variant.dir_variant.dirty;
+
+		if (list_empty(link)) {
+			list_add(link, &dev->dirty_dirs);
+			yaffs_trace(YAFFS_TRACE_BACKGROUND,
+			  "Added object %d to dirty directories",
+			   obj->obj_id);
+		}
+
+	} else {
+		yaffs_update_oh(obj, NULL, 0, 0, 0, NULL);
+	}
+}
+
+void yaffs_update_dirty_dirs(struct yaffs_dev *dev)
+{
+	struct list_head *link;
+	struct yaffs_obj *obj;
+	struct yaffs_dir_var *d_s;
+	union yaffs_obj_var *o_v;
+
+	yaffs_trace(YAFFS_TRACE_BACKGROUND, "Update dirty directories");
+
+	while (!list_empty(&dev->dirty_dirs)) {
+		link = dev->dirty_dirs.next;
+		list_del_init(link);
+
+		d_s = list_entry(link, struct yaffs_dir_var, dirty);
+		o_v = list_entry(d_s, union yaffs_obj_var, dir_variant);
+		obj = list_entry(o_v, struct yaffs_obj, variant);
+
+		yaffs_trace(YAFFS_TRACE_BACKGROUND, "Update directory %d",
+			obj->obj_id);
+
+		if (obj->dirty)
+			yaffs_update_oh(obj, NULL, 0, 0, 0, NULL);
+	}
+}
+
+/*
+ * Mknod (create) a new object.
+ * equiv_obj only has meaning for a hard link;
+ * alias_str only has meaning for a symlink.
+ * rdev only has meaning for devices (a subset of special objects)
+ */
+
+static struct yaffs_obj *yaffs_create_obj(enum yaffs_obj_type type,
+					  struct yaffs_obj *parent,
+					  const YCHAR *name,
+					  u32 mode,
+					  u32 uid,
+					  u32 gid,
+					  struct yaffs_obj *equiv_obj,
+					  const YCHAR *alias_str, u32 rdev)
+{
+	struct yaffs_obj *in;
+	YCHAR *str = NULL;
+	struct yaffs_dev *dev = parent->my_dev;
+
+	/* Check if the entry exists.
+	 * If it does then fail the call since we don't want a dup. */
+	if (yaffs_find_by_name(parent, name))
+		return NULL;
+
+	if (type == YAFFS_OBJECT_TYPE_SYMLINK) {
+		str = yaffs_clone_str(alias_str);
+		if (!str)
+			return NULL;
+	}
+
+	in = yaffs_new_obj(dev, -1, type);
+
+	if (!in) {
+		kfree(str);
+		return NULL;
+	}
+
+	in->hdr_chunk = 0;
+	in->valid = 1;
+	in->variant_type = type;
+
+	in->yst_mode = mode;
+
+	yaffs_attribs_init(in, gid, uid, rdev);
+
+	in->n_data_chunks = 0;
+
+	yaffs_set_obj_name(in, name);
+	in->dirty = 1;
+
+	yaffs_add_obj_to_dir(parent, in);
+
+	in->my_dev = parent->my_dev;
+
+	switch (type) {
+	case YAFFS_OBJECT_TYPE_SYMLINK:
+		in->variant.symlink_variant.alias = str;
+		break;
+	case YAFFS_OBJECT_TYPE_HARDLINK:
+		in->variant.hardlink_variant.equiv_obj = equiv_obj;
+		in->variant.hardlink_variant.equiv_id = equiv_obj->obj_id;
+		list_add(&in->hard_links, &equiv_obj->hard_links);
+		break;
+	case YAFFS_OBJECT_TYPE_FILE:
+	case YAFFS_OBJECT_TYPE_DIRECTORY:
+	case YAFFS_OBJECT_TYPE_SPECIAL:
+	case YAFFS_OBJECT_TYPE_UNKNOWN:
+		/* do nothing */
+		break;
+	}
+
+	if (yaffs_update_oh(in, name, 0, 0, 0, NULL) < 0) {
+		/* Could not create the object header, fail */
+		yaffs_del_obj(in);
+		in = NULL;
+	}
+
+	if (in)
+		yaffs_update_parent(parent);
+
+	return in;
+}
+
+struct yaffs_obj *yaffs_create_file(struct yaffs_obj *parent,
+				    const YCHAR *name, u32 mode, u32 uid,
+				    u32 gid)
+{
+	return yaffs_create_obj(YAFFS_OBJECT_TYPE_FILE, parent, name, mode,
+				uid, gid, NULL, NULL, 0);
+}
+
+struct yaffs_obj *yaffs_create_dir(struct yaffs_obj *parent, const YCHAR *name,
+				   u32 mode, u32 uid, u32 gid)
+{
+	return yaffs_create_obj(YAFFS_OBJECT_TYPE_DIRECTORY, parent, name,
+				mode, uid, gid, NULL, NULL, 0);
+}
+
+struct yaffs_obj *yaffs_create_special(struct yaffs_obj *parent,
+				       const YCHAR *name, u32 mode, u32 uid,
+				       u32 gid, u32 rdev)
+{
+	return yaffs_create_obj(YAFFS_OBJECT_TYPE_SPECIAL, parent, name, mode,
+				uid, gid, NULL, NULL, rdev);
+}
+
+struct yaffs_obj *yaffs_create_symlink(struct yaffs_obj *parent,
+				       const YCHAR *name, u32 mode, u32 uid,
+				       u32 gid, const YCHAR *alias)
+{
+	return yaffs_create_obj(YAFFS_OBJECT_TYPE_SYMLINK, parent, name, mode,
+				uid, gid, NULL, alias, 0);
+}
+
+/* yaffs_link_obj returns the object id of the equivalent object.*/
+struct yaffs_obj *yaffs_link_obj(struct yaffs_obj *parent, const YCHAR * name,
+				 struct yaffs_obj *equiv_obj)
+{
+	/* Get the real object in case we were fed a hard link obj */
+	equiv_obj = yaffs_get_equivalent_obj(equiv_obj);
+
+	if (yaffs_create_obj(YAFFS_OBJECT_TYPE_HARDLINK,
+			parent, name, 0, 0, 0,
+			equiv_obj, NULL, 0))
+		return equiv_obj;
+
+	return NULL;
+
+}
+
+
+
+/*---------------------- Block Management and Page Allocation -------------*/
+
+static void yaffs_deinit_blocks(struct yaffs_dev *dev)
+{
+	if (dev->block_info_alt && dev->block_info)
+		vfree(dev->block_info);
+	else
+		kfree(dev->block_info);
+
+	dev->block_info_alt = 0;
+
+	dev->block_info = NULL;
+
+	if (dev->chunk_bits_alt && dev->chunk_bits)
+		vfree(dev->chunk_bits);
+	else
+		kfree(dev->chunk_bits);
+	dev->chunk_bits_alt = 0;
+	dev->chunk_bits = NULL;
+}
+
+static int yaffs_init_blocks(struct yaffs_dev *dev)
+{
+	int n_blocks = dev->internal_end_block - dev->internal_start_block + 1;
+
+	dev->block_info = NULL;
+	dev->chunk_bits = NULL;
+	dev->alloc_block = -1;	/* force it to get a new one */
+
+	/* If the first allocation strategy fails, thry the alternate one */
+	dev->block_info =
+		kmalloc(n_blocks * sizeof(struct yaffs_block_info), GFP_NOFS);
+	if (!dev->block_info) {
+		dev->block_info =
+		    vmalloc(n_blocks * sizeof(struct yaffs_block_info));
+		dev->block_info_alt = 1;
+	} else {
+		dev->block_info_alt = 0;
+	}
+
+	if (!dev->block_info)
+		goto alloc_error;
+
+	/* Set up dynamic blockinfo stuff. Round up bytes. */
+	dev->chunk_bit_stride = (dev->param.chunks_per_block + 7) / 8;
+	dev->chunk_bits =
+		kmalloc(dev->chunk_bit_stride * n_blocks, GFP_NOFS);
+	if (!dev->chunk_bits) {
+		dev->chunk_bits =
+		    vmalloc(dev->chunk_bit_stride * n_blocks);
+		dev->chunk_bits_alt = 1;
+	} else {
+		dev->chunk_bits_alt = 0;
+	}
+	if (!dev->chunk_bits)
+		goto alloc_error;
+
+
+	memset(dev->block_info, 0, n_blocks * sizeof(struct yaffs_block_info));
+	memset(dev->chunk_bits, 0, dev->chunk_bit_stride * n_blocks);
+	return YAFFS_OK;
+
+alloc_error:
+	yaffs_deinit_blocks(dev);
+	return YAFFS_FAIL;
+}
+
+
+void yaffs_block_became_dirty(struct yaffs_dev *dev, int block_no)
+{
+	struct yaffs_block_info *bi = yaffs_get_block_info(dev, block_no);
+	int erased_ok = 0;
+	int i;
+
+	/* If the block is still healthy erase it and mark as clean.
+	 * If the block has had a data failure, then retire it.
+	 */
+
+	yaffs_trace(YAFFS_TRACE_GC | YAFFS_TRACE_ERASE,
+		"yaffs_block_became_dirty block %d state %d %s",
+		block_no, bi->block_state,
+		(bi->needs_retiring) ? "needs retiring" : "");
+
+	yaffs2_clear_oldest_dirty_seq(dev, bi);
+
+	bi->block_state = YAFFS_BLOCK_STATE_DIRTY;
+
+	/* If this is the block being garbage collected then stop gc'ing */
+	if (block_no == dev->gc_block)
+		dev->gc_block = 0;
+
+	/* If this block is currently the best candidate for gc
+	 * then drop as a candidate */
+	if (block_no == dev->gc_dirtiest) {
+		dev->gc_dirtiest = 0;
+		dev->gc_pages_in_use = 0;
+	}
+
+	if (!bi->needs_retiring) {
+		yaffs2_checkpt_invalidate(dev);
+		erased_ok = yaffs_erase_block(dev, block_no);
+		if (!erased_ok) {
+			dev->n_erase_failures++;
+			yaffs_trace(YAFFS_TRACE_ERROR | YAFFS_TRACE_BAD_BLOCKS,
+			  "**>> Erasure failed %d", block_no);
+		}
+	}
+
+	/* Verify erasure if needed */
+	if (erased_ok &&
+	    ((yaffs_trace_mask & YAFFS_TRACE_ERASE) ||
+	     !yaffs_skip_verification(dev))) {
+		for (i = 0; i < dev->param.chunks_per_block; i++) {
+			if (!yaffs_check_chunk_erased(dev,
+				block_no * dev->param.chunks_per_block + i)) {
+				yaffs_trace(YAFFS_TRACE_ERROR,
+					">>Block %d erasure supposedly OK, but chunk %d not erased",
+					block_no, i);
+			}
+		}
+	}
+
+	if (!erased_ok) {
+		/* We lost a block of free space */
+		dev->n_free_chunks -= dev->param.chunks_per_block;
+		yaffs_retire_block(dev, block_no);
+		yaffs_trace(YAFFS_TRACE_ERROR | YAFFS_TRACE_BAD_BLOCKS,
+			"**>> Block %d retired", block_no);
+		return;
+	}
+
+	/* Clean it up... */
+	bi->block_state = YAFFS_BLOCK_STATE_EMPTY;
+	bi->seq_number = 0;
+	dev->n_erased_blocks++;
+	bi->pages_in_use = 0;
+	bi->soft_del_pages = 0;
+	bi->has_shrink_hdr = 0;
+	bi->skip_erased_check = 1;	/* Clean, so no need to check */
+	bi->gc_prioritise = 0;
+	bi->has_summary = 0;
+
+	yaffs_clear_chunk_bits(dev, block_no);
+
+	yaffs_trace(YAFFS_TRACE_ERASE, "Erased block %d", block_no);
+}
+
+static inline int yaffs_gc_process_chunk(struct yaffs_dev *dev,
+					struct yaffs_block_info *bi,
+					int old_chunk, u8 *buffer)
+{
+	int new_chunk;
+	int mark_flash = 1;
+	struct yaffs_ext_tags tags;
+	struct yaffs_obj *object;
+	int matching_chunk;
+	int ret_val = YAFFS_OK;
+
+	memset(&tags, 0, sizeof(tags));
+	yaffs_rd_chunk_tags_nand(dev, old_chunk,
+				 buffer, &tags);
+	object = yaffs_find_by_number(dev, tags.obj_id);
+
+	yaffs_trace(YAFFS_TRACE_GC_DETAIL,
+		"Collecting chunk in block %d, %d %d %d ",
+		dev->gc_chunk, tags.obj_id,
+		tags.chunk_id, tags.n_bytes);
+
+	if (object && !yaffs_skip_verification(dev)) {
+		if (tags.chunk_id == 0)
+			matching_chunk =
+			    object->hdr_chunk;
+		else if (object->soft_del)
+			/* Defeat the test */
+			matching_chunk = old_chunk;
+		else
+			matching_chunk =
+			    yaffs_find_chunk_in_file
+			    (object, tags.chunk_id,
+			     NULL);
+
+		if (old_chunk != matching_chunk)
+			yaffs_trace(YAFFS_TRACE_ERROR,
+				"gc: page in gc mismatch: %d %d %d %d",
+				old_chunk,
+				matching_chunk,
+				tags.obj_id,
+				tags.chunk_id);
+	}
+
+	if (!object) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"page %d in gc has no object: %d %d %d ",
+			old_chunk,
+			tags.obj_id, tags.chunk_id,
+			tags.n_bytes);
+	}
+
+	if (object &&
+	    object->deleted &&
+	    object->soft_del && tags.chunk_id != 0) {
+		/* Data chunk in a soft deleted file,
+		 * throw it away.
+		 * It's a soft deleted data chunk,
+		 * No need to copy this, just forget
+		 * about it and fix up the object.
+		 */
+
+		/* Free chunks already includes
+		 * softdeleted chunks, how ever this
+		 * chunk is going to soon be really
+		 * deleted which will increment free
+		 * chunks. We have to decrement free
+		 * chunks so this works out properly.
+		 */
+		dev->n_free_chunks--;
+		bi->soft_del_pages--;
+
+		object->n_data_chunks--;
+		if (object->n_data_chunks <= 0) {
+			/* remeber to clean up obj */
+			dev->gc_cleanup_list[dev->n_clean_ups] = tags.obj_id;
+			dev->n_clean_ups++;
+		}
+		mark_flash = 0;
+	} else if (object) {
+		/* It's either a data chunk in a live
+		 * file or an ObjectHeader, so we're
+		 * interested in it.
+		 * NB Need to keep the ObjectHeaders of
+		 * deleted files until the whole file
+		 * has been deleted off
+		 */
+		tags.serial_number++;
+		dev->n_gc_copies++;
+
+		if (tags.chunk_id == 0) {
+			/* It is an object Id,
+			 * We need to nuke the
+			 * shrinkheader flags since its
+			 * work is done.
+			 * Also need to clean up
+			 * shadowing.
+			 */
+			struct yaffs_obj_hdr *oh;
+			oh = (struct yaffs_obj_hdr *) buffer;
+
+			oh->is_shrink = 0;
+			tags.extra_is_shrink = 0;
+			oh->shadows_obj = 0;
+			oh->inband_shadowed_obj_id = 0;
+			tags.extra_shadows = 0;
+
+			/* Update file size */
+			if (object->variant_type == YAFFS_OBJECT_TYPE_FILE) {
+				yaffs_oh_size_load(oh,
+				    object->variant.file_variant.file_size);
+				tags.extra_file_size =
+				    object->variant.file_variant.file_size;
+			}
+
+			yaffs_verify_oh(object, oh, &tags, 1);
+			new_chunk =
+			    yaffs_write_new_chunk(dev, (u8 *) oh, &tags, 1);
+		} else {
+			new_chunk =
+			    yaffs_write_new_chunk(dev, buffer, &tags, 1);
+		}
+
+		if (new_chunk < 0) {
+			ret_val = YAFFS_FAIL;
+		} else {
+
+			/* Now fix up the Tnodes etc. */
+
+			if (tags.chunk_id == 0) {
+				/* It's a header */
+				object->hdr_chunk = new_chunk;
+				object->serial = tags.serial_number;
+			} else {
+				/* It's a data chunk */
+				yaffs_put_chunk_in_file(object, tags.chunk_id,
+							new_chunk, 0);
+			}
+		}
+	}
+	if (ret_val == YAFFS_OK)
+		yaffs_chunk_del(dev, old_chunk, mark_flash, __LINE__);
+	return ret_val;
+}
+
+static int yaffs_gc_block(struct yaffs_dev *dev, int block, int whole_block)
+{
+	int old_chunk;
+	int ret_val = YAFFS_OK;
+	int i;
+	int is_checkpt_block;
+	int max_copies;
+	int chunks_before = yaffs_get_erased_chunks(dev);
+	int chunks_after;
+	struct yaffs_block_info *bi = yaffs_get_block_info(dev, block);
+
+	is_checkpt_block = (bi->block_state == YAFFS_BLOCK_STATE_CHECKPOINT);
+
+	yaffs_trace(YAFFS_TRACE_TRACING,
+		"Collecting block %d, in use %d, shrink %d, whole_block %d",
+		block, bi->pages_in_use, bi->has_shrink_hdr,
+		whole_block);
+
+	/*yaffs_verify_free_chunks(dev); */
+
+	if (bi->block_state == YAFFS_BLOCK_STATE_FULL)
+		bi->block_state = YAFFS_BLOCK_STATE_COLLECTING;
+
+	bi->has_shrink_hdr = 0;	/* clear the flag so that the block can erase */
+
+	dev->gc_disable = 1;
+
+	yaffs_summary_gc(dev, block);
+
+	if (is_checkpt_block || !yaffs_still_some_chunks(dev, block)) {
+		yaffs_trace(YAFFS_TRACE_TRACING,
+			"Collecting block %d that has no chunks in use",
+			block);
+		yaffs_block_became_dirty(dev, block);
+	} else {
+
+		u8 *buffer = yaffs_get_temp_buffer(dev);
+
+		yaffs_verify_blk(dev, bi, block);
+
+		max_copies = (whole_block) ? dev->param.chunks_per_block : 5;
+		old_chunk = block * dev->param.chunks_per_block + dev->gc_chunk;
+
+		for (/* init already done */ ;
+		     ret_val == YAFFS_OK &&
+		     dev->gc_chunk < dev->param.chunks_per_block &&
+		     (bi->block_state == YAFFS_BLOCK_STATE_COLLECTING) &&
+		     max_copies > 0;
+		     dev->gc_chunk++, old_chunk++) {
+			if (yaffs_check_chunk_bit(dev, block, dev->gc_chunk)) {
+				/* Page is in use and might need to be copied */
+				max_copies--;
+				ret_val = yaffs_gc_process_chunk(dev, bi,
+							old_chunk, buffer);
+			}
+		}
+		yaffs_release_temp_buffer(dev, buffer);
+	}
+
+	yaffs_verify_collected_blk(dev, bi, block);
+
+	if (bi->block_state == YAFFS_BLOCK_STATE_COLLECTING) {
+		/*
+		 * The gc did not complete. Set block state back to FULL
+		 * because checkpointing does not restore gc.
+		 */
+		bi->block_state = YAFFS_BLOCK_STATE_FULL;
+	} else {
+		/* The gc completed. */
+		/* Do any required cleanups */
+		for (i = 0; i < dev->n_clean_ups; i++) {
+			/* Time to delete the file too */
+			struct yaffs_obj *object =
+			    yaffs_find_by_number(dev, dev->gc_cleanup_list[i]);
+			if (object) {
+				yaffs_free_tnode(dev,
+					  object->variant.file_variant.top);
+				object->variant.file_variant.top = NULL;
+				yaffs_trace(YAFFS_TRACE_GC,
+					"yaffs: About to finally delete object %d",
+					object->obj_id);
+				yaffs_generic_obj_del(object);
+				object->my_dev->n_deleted_files--;
+			}
+
+		}
+		chunks_after = yaffs_get_erased_chunks(dev);
+		if (chunks_before >= chunks_after)
+			yaffs_trace(YAFFS_TRACE_GC,
+				"gc did not increase free chunks before %d after %d",
+				chunks_before, chunks_after);
+		dev->gc_block = 0;
+		dev->gc_chunk = 0;
+		dev->n_clean_ups = 0;
+	}
+
+	dev->gc_disable = 0;
+
+	return ret_val;
+}
+
+/*
+ * find_gc_block() selects the dirtiest block (or close enough)
+ * for garbage collection.
+ */
+
+static unsigned yaffs_find_gc_block(struct yaffs_dev *dev,
+				    int aggressive, int background)
+{
+	int i;
+	int iterations;
+	unsigned selected = 0;
+	int prioritised = 0;
+	int prioritised_exist = 0;
+	struct yaffs_block_info *bi;
+	int threshold;
+
+	/* First let's see if we need to grab a prioritised block */
+	if (dev->has_pending_prioritised_gc && !aggressive) {
+		dev->gc_dirtiest = 0;
+		bi = dev->block_info;
+		for (i = dev->internal_start_block;
+		     i <= dev->internal_end_block && !selected; i++) {
+
+			if (bi->gc_prioritise) {
+				prioritised_exist = 1;
+				if (bi->block_state == YAFFS_BLOCK_STATE_FULL &&
+				    yaffs_block_ok_for_gc(dev, bi)) {
+					selected = i;
+					prioritised = 1;
+				}
+			}
+			bi++;
+		}
+
+		/*
+		 * If there is a prioritised block and none was selected then
+		 * this happened because there is at least one old dirty block
+		 * gumming up the works. Let's gc the oldest dirty block.
+		 */
+
+		if (prioritised_exist &&
+		    !selected && dev->oldest_dirty_block > 0)
+			selected = dev->oldest_dirty_block;
+
+		if (!prioritised_exist)	/* None found, so we can clear this */
+			dev->has_pending_prioritised_gc = 0;
+	}
+
+	/* If we're doing aggressive GC then we are happy to take a less-dirty
+	 * block, and search harder.
+	 * else (leasurely gc), then we only bother to do this if the
+	 * block has only a few pages in use.
+	 */
+
+	if (!selected) {
+		int pages_used;
+		int n_blocks =
+		    dev->internal_end_block - dev->internal_start_block + 1;
+		if (aggressive) {
+			threshold = dev->param.chunks_per_block;
+			iterations = n_blocks;
+		} else {
+			int max_threshold;
+
+			if (background)
+				max_threshold = dev->param.chunks_per_block / 2;
+			else
+				max_threshold = dev->param.chunks_per_block / 8;
+
+			if (max_threshold < YAFFS_GC_PASSIVE_THRESHOLD)
+				max_threshold = YAFFS_GC_PASSIVE_THRESHOLD;
+
+			threshold = background ? (dev->gc_not_done + 2) * 2 : 0;
+			if (threshold < YAFFS_GC_PASSIVE_THRESHOLD)
+				threshold = YAFFS_GC_PASSIVE_THRESHOLD;
+			if (threshold > max_threshold)
+				threshold = max_threshold;
+
+			iterations = n_blocks / 16 + 1;
+			if (iterations > 100)
+				iterations = 100;
+		}
+
+		for (i = 0;
+		     i < iterations &&
+		     (dev->gc_dirtiest < 1 ||
+		      dev->gc_pages_in_use > YAFFS_GC_GOOD_ENOUGH);
+		     i++) {
+			dev->gc_block_finder++;
+			if (dev->gc_block_finder < dev->internal_start_block ||
+			    dev->gc_block_finder > dev->internal_end_block)
+				dev->gc_block_finder =
+				    dev->internal_start_block;
+
+			bi = yaffs_get_block_info(dev, dev->gc_block_finder);
+
+			pages_used = bi->pages_in_use - bi->soft_del_pages;
+
+			if (bi->block_state == YAFFS_BLOCK_STATE_FULL &&
+			    pages_used < dev->param.chunks_per_block &&
+			    (dev->gc_dirtiest < 1 ||
+			     pages_used < dev->gc_pages_in_use) &&
+			    yaffs_block_ok_for_gc(dev, bi)) {
+				dev->gc_dirtiest = dev->gc_block_finder;
+				dev->gc_pages_in_use = pages_used;
+			}
+		}
+
+		if (dev->gc_dirtiest > 0 && dev->gc_pages_in_use <= threshold)
+			selected = dev->gc_dirtiest;
+	}
+
+	/*
+	 * If nothing has been selected for a while, try the oldest dirty
+	 * because that's gumming up the works.
+	 */
+
+	if (!selected && dev->param.is_yaffs2 &&
+	    dev->gc_not_done >= (background ? 10 : 20)) {
+		yaffs2_find_oldest_dirty_seq(dev);
+		if (dev->oldest_dirty_block > 0) {
+			selected = dev->oldest_dirty_block;
+			dev->gc_dirtiest = selected;
+			dev->oldest_dirty_gc_count++;
+			bi = yaffs_get_block_info(dev, selected);
+			dev->gc_pages_in_use =
+			    bi->pages_in_use - bi->soft_del_pages;
+		} else {
+			dev->gc_not_done = 0;
+		}
+	}
+
+	if (selected) {
+		yaffs_trace(YAFFS_TRACE_GC,
+			"GC Selected block %d with %d free, prioritised:%d",
+			selected,
+			dev->param.chunks_per_block - dev->gc_pages_in_use,
+			prioritised);
+
+		dev->n_gc_blocks++;
+		if (background)
+			dev->bg_gcs++;
+
+		dev->gc_dirtiest = 0;
+		dev->gc_pages_in_use = 0;
+		dev->gc_not_done = 0;
+		if (dev->refresh_skip > 0)
+			dev->refresh_skip--;
+	} else {
+		dev->gc_not_done++;
+		yaffs_trace(YAFFS_TRACE_GC,
+			"GC none: finder %d skip %d threshold %d dirtiest %d using %d oldest %d%s",
+			dev->gc_block_finder, dev->gc_not_done, threshold,
+			dev->gc_dirtiest, dev->gc_pages_in_use,
+			dev->oldest_dirty_block, background ? " bg" : "");
+	}
+
+	return selected;
+}
+
+/* New garbage collector
+ * If we're very low on erased blocks then we do aggressive garbage collection
+ * otherwise we do "leasurely" garbage collection.
+ * Aggressive gc looks further (whole array) and will accept less dirty blocks.
+ * Passive gc only inspects smaller areas and only accepts more dirty blocks.
+ *
+ * The idea is to help clear out space in a more spread-out manner.
+ * Dunno if it really does anything useful.
+ */
+static int yaffs_check_gc(struct yaffs_dev *dev, int background)
+{
+	int aggressive = 0;
+	int gc_ok = YAFFS_OK;
+	int max_tries = 0;
+	int min_erased;
+	int erased_chunks;
+	int checkpt_block_adjust;
+
+	if (dev->param.gc_control_fn &&
+		(dev->param.gc_control_fn(dev) & 1) == 0)
+		return YAFFS_OK;
+
+	if (dev->gc_disable)
+		/* Bail out so we don't get recursive gc */
+		return YAFFS_OK;
+
+	/* This loop should pass the first time.
+	 * Only loops here if the collection does not increase space.
+	 */
+
+	do {
+		max_tries++;
+
+		checkpt_block_adjust = yaffs_calc_checkpt_blocks_required(dev);
+
+		min_erased =
+		    dev->param.n_reserved_blocks + checkpt_block_adjust + 1;
+		erased_chunks =
+		    dev->n_erased_blocks * dev->param.chunks_per_block;
+
+		/* If we need a block soon then do aggressive gc. */
+		if (dev->n_erased_blocks < min_erased)
+			aggressive = 1;
+		else {
+			if (!background
+			    && erased_chunks > (dev->n_free_chunks / 4))
+				break;
+
+			if (dev->gc_skip > 20)
+				dev->gc_skip = 20;
+			if (erased_chunks < dev->n_free_chunks / 2 ||
+			    dev->gc_skip < 1 || background)
+				aggressive = 0;
+			else {
+				dev->gc_skip--;
+				break;
+			}
+		}
+
+		dev->gc_skip = 5;
+
+		/* If we don't already have a block being gc'd then see if we
+		 * should start another */
+
+		if (dev->gc_block < 1 && !aggressive) {
+			dev->gc_block = yaffs2_find_refresh_block(dev);
+			dev->gc_chunk = 0;
+			dev->n_clean_ups = 0;
+		}
+		if (dev->gc_block < 1) {
+			dev->gc_block =
+			    yaffs_find_gc_block(dev, aggressive, background);
+			dev->gc_chunk = 0;
+			dev->n_clean_ups = 0;
+		}
+
+		if (dev->gc_block > 0) {
+			dev->all_gcs++;
+			if (!aggressive)
+				dev->passive_gc_count++;
+
+			yaffs_trace(YAFFS_TRACE_GC,
+				"yaffs: GC n_erased_blocks %d aggressive %d",
+				dev->n_erased_blocks, aggressive);
+
+			gc_ok = yaffs_gc_block(dev, dev->gc_block, aggressive);
+		}
+
+		if (dev->n_erased_blocks < (dev->param.n_reserved_blocks) &&
+		    dev->gc_block > 0) {
+			yaffs_trace(YAFFS_TRACE_GC,
+				"yaffs: GC !!!no reclaim!!! n_erased_blocks %d after try %d block %d",
+				dev->n_erased_blocks, max_tries,
+				dev->gc_block);
+		}
+	} while ((dev->n_erased_blocks < dev->param.n_reserved_blocks) &&
+		 (dev->gc_block > 0) && (max_tries < 2));
+
+	return aggressive ? gc_ok : YAFFS_OK;
+}
+
+/*
+ * yaffs_bg_gc()
+ * Garbage collects. Intended to be called from a background thread.
+ * Returns non-zero if at least half the free chunks are erased.
+ */
+int yaffs_bg_gc(struct yaffs_dev *dev, unsigned urgency)
+{
+	int erased_chunks = dev->n_erased_blocks * dev->param.chunks_per_block;
+
+	yaffs_trace(YAFFS_TRACE_BACKGROUND, "Background gc %u", urgency);
+
+	yaffs_check_gc(dev, 1);
+	return erased_chunks > dev->n_free_chunks / 2;
+}
+
+/*-------------------- Data file manipulation -----------------*/
+
+static int yaffs_rd_data_obj(struct yaffs_obj *in, int inode_chunk, u8 * buffer)
+{
+	int nand_chunk = yaffs_find_chunk_in_file(in, inode_chunk, NULL);
+
+	if (nand_chunk >= 0)
+		return yaffs_rd_chunk_tags_nand(in->my_dev, nand_chunk,
+						buffer, NULL);
+	else {
+		yaffs_trace(YAFFS_TRACE_NANDACCESS,
+			"Chunk %d not found zero instead",
+			nand_chunk);
+		/* get sane (zero) data if you read a hole */
+		memset(buffer, 0, in->my_dev->data_bytes_per_chunk);
+		return 0;
+	}
+
+}
+
+void yaffs_chunk_del(struct yaffs_dev *dev, int chunk_id, int mark_flash,
+		     int lyn)
+{
+	int block;
+	int page;
+	struct yaffs_ext_tags tags;
+	struct yaffs_block_info *bi;
+
+	if (chunk_id <= 0)
+		return;
+
+	dev->n_deletions++;
+	block = chunk_id / dev->param.chunks_per_block;
+	page = chunk_id % dev->param.chunks_per_block;
+
+	if (!yaffs_check_chunk_bit(dev, block, page))
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Deleting invalid chunk %d", chunk_id);
+
+	bi = yaffs_get_block_info(dev, block);
+
+	yaffs2_update_oldest_dirty_seq(dev, block, bi);
+
+	yaffs_trace(YAFFS_TRACE_DELETION,
+		"line %d delete of chunk %d",
+		lyn, chunk_id);
+
+	if (!dev->param.is_yaffs2 && mark_flash &&
+	    bi->block_state != YAFFS_BLOCK_STATE_COLLECTING) {
+
+		memset(&tags, 0, sizeof(tags));
+		tags.is_deleted = 1;
+		yaffs_wr_chunk_tags_nand(dev, chunk_id, NULL, &tags);
+		yaffs_handle_chunk_update(dev, chunk_id, &tags);
+	} else {
+		dev->n_unmarked_deletions++;
+	}
+
+	/* Pull out of the management area.
+	 * If the whole block became dirty, this will kick off an erasure.
+	 */
+	if (bi->block_state == YAFFS_BLOCK_STATE_ALLOCATING ||
+	    bi->block_state == YAFFS_BLOCK_STATE_FULL ||
+	    bi->block_state == YAFFS_BLOCK_STATE_NEEDS_SCAN ||
+	    bi->block_state == YAFFS_BLOCK_STATE_COLLECTING) {
+		dev->n_free_chunks++;
+		yaffs_clear_chunk_bit(dev, block, page);
+		bi->pages_in_use--;
+
+		if (bi->pages_in_use == 0 &&
+		    !bi->has_shrink_hdr &&
+		    bi->block_state != YAFFS_BLOCK_STATE_ALLOCATING &&
+		    bi->block_state != YAFFS_BLOCK_STATE_NEEDS_SCAN) {
+			yaffs_block_became_dirty(dev, block);
+		}
+	}
+}
+
+static int yaffs_wr_data_obj(struct yaffs_obj *in, int inode_chunk,
+			     const u8 *buffer, int n_bytes, int use_reserve)
+{
+	/* Find old chunk Need to do this to get serial number
+	 * Write new one and patch into tree.
+	 * Invalidate old tags.
+	 */
+
+	int prev_chunk_id;
+	struct yaffs_ext_tags prev_tags;
+	int new_chunk_id;
+	struct yaffs_ext_tags new_tags;
+	struct yaffs_dev *dev = in->my_dev;
+
+	yaffs_check_gc(dev, 0);
+
+	/* Get the previous chunk at this location in the file if it exists.
+	 * If it does not exist then put a zero into the tree. This creates
+	 * the tnode now, rather than later when it is harder to clean up.
+	 */
+	prev_chunk_id = yaffs_find_chunk_in_file(in, inode_chunk, &prev_tags);
+	if (prev_chunk_id < 1 &&
+	    !yaffs_put_chunk_in_file(in, inode_chunk, 0, 0))
+		return 0;
+
+	/* Set up new tags */
+	memset(&new_tags, 0, sizeof(new_tags));
+
+	new_tags.chunk_id = inode_chunk;
+	new_tags.obj_id = in->obj_id;
+	new_tags.serial_number =
+	    (prev_chunk_id > 0) ? prev_tags.serial_number + 1 : 1;
+	new_tags.n_bytes = n_bytes;
+
+	if (n_bytes < 1 || n_bytes > dev->param.total_bytes_per_chunk) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+		  "Writing %d bytes to chunk!!!!!!!!!",
+		   n_bytes);
+		BUG();
+	}
+
+	new_chunk_id =
+	    yaffs_write_new_chunk(dev, buffer, &new_tags, use_reserve);
+
+	if (new_chunk_id > 0) {
+		yaffs_put_chunk_in_file(in, inode_chunk, new_chunk_id, 0);
+
+		if (prev_chunk_id > 0)
+			yaffs_chunk_del(dev, prev_chunk_id, 1, __LINE__);
+
+		yaffs_verify_file_sane(in);
+	}
+	return new_chunk_id;
+
+}
+
+
+
+static int yaffs_do_xattrib_mod(struct yaffs_obj *obj, int set,
+				const YCHAR *name, const void *value, int size,
+				int flags)
+{
+	struct yaffs_xattr_mod xmod;
+	int result;
+
+	xmod.set = set;
+	xmod.name = name;
+	xmod.data = value;
+	xmod.size = size;
+	xmod.flags = flags;
+	xmod.result = -ENOSPC;
+
+	result = yaffs_update_oh(obj, NULL, 0, 0, 0, &xmod);
+
+	if (result > 0)
+		return xmod.result;
+	else
+		return -ENOSPC;
+}
+
+static int yaffs_apply_xattrib_mod(struct yaffs_obj *obj, char *buffer,
+				   struct yaffs_xattr_mod *xmod)
+{
+	int retval = 0;
+	int x_offs = sizeof(struct yaffs_obj_hdr);
+	struct yaffs_dev *dev = obj->my_dev;
+	int x_size = dev->data_bytes_per_chunk - sizeof(struct yaffs_obj_hdr);
+	char *x_buffer = buffer + x_offs;
+
+	if (xmod->set)
+		retval =
+		    nval_set(x_buffer, x_size, xmod->name, xmod->data,
+			     xmod->size, xmod->flags);
+	else
+		retval = nval_del(x_buffer, x_size, xmod->name);
+
+	obj->has_xattr = nval_hasvalues(x_buffer, x_size);
+	obj->xattr_known = 1;
+	xmod->result = retval;
+
+	return retval;
+}
+
+static int yaffs_do_xattrib_fetch(struct yaffs_obj *obj, const YCHAR *name,
+				  void *value, int size)
+{
+	char *buffer = NULL;
+	int result;
+	struct yaffs_ext_tags tags;
+	struct yaffs_dev *dev = obj->my_dev;
+	int x_offs = sizeof(struct yaffs_obj_hdr);
+	int x_size = dev->data_bytes_per_chunk - sizeof(struct yaffs_obj_hdr);
+	char *x_buffer;
+	int retval = 0;
+
+	if (obj->hdr_chunk < 1)
+		return -ENODATA;
+
+	/* If we know that the object has no xattribs then don't do all the
+	 * reading and parsing.
+	 */
+	if (obj->xattr_known && !obj->has_xattr) {
+		if (name)
+			return -ENODATA;
+		else
+			return 0;
+	}
+
+	buffer = (char *)yaffs_get_temp_buffer(dev);
+	if (!buffer)
+		return -ENOMEM;
+
+	result =
+	    yaffs_rd_chunk_tags_nand(dev, obj->hdr_chunk, (u8 *) buffer, &tags);
+
+	if (result != YAFFS_OK)
+		retval = -ENOENT;
+	else {
+		x_buffer = buffer + x_offs;
+
+		if (!obj->xattr_known) {
+			obj->has_xattr = nval_hasvalues(x_buffer, x_size);
+			obj->xattr_known = 1;
+		}
+
+		if (name)
+			retval = nval_get(x_buffer, x_size, name, value, size);
+		else
+			retval = nval_list(x_buffer, x_size, value, size);
+	}
+	yaffs_release_temp_buffer(dev, (u8 *) buffer);
+	return retval;
+}
+
+int yaffs_set_xattrib(struct yaffs_obj *obj, const YCHAR * name,
+		      const void *value, int size, int flags)
+{
+	return yaffs_do_xattrib_mod(obj, 1, name, value, size, flags);
+}
+
+int yaffs_remove_xattrib(struct yaffs_obj *obj, const YCHAR * name)
+{
+	return yaffs_do_xattrib_mod(obj, 0, name, NULL, 0, 0);
+}
+
+int yaffs_get_xattrib(struct yaffs_obj *obj, const YCHAR * name, void *value,
+		      int size)
+{
+	return yaffs_do_xattrib_fetch(obj, name, value, size);
+}
+
+int yaffs_list_xattrib(struct yaffs_obj *obj, char *buffer, int size)
+{
+	return yaffs_do_xattrib_fetch(obj, NULL, buffer, size);
+}
+
+static void yaffs_check_obj_details_loaded(struct yaffs_obj *in)
+{
+	u8 *buf;
+	struct yaffs_obj_hdr *oh;
+	struct yaffs_dev *dev;
+	struct yaffs_ext_tags tags;
+	int result;
+	int alloc_failed = 0;
+
+	if (!in || !in->lazy_loaded || in->hdr_chunk < 1)
+		return;
+
+	dev = in->my_dev;
+	in->lazy_loaded = 0;
+	buf = yaffs_get_temp_buffer(dev);
+
+	result = yaffs_rd_chunk_tags_nand(dev, in->hdr_chunk, buf, &tags);
+	oh = (struct yaffs_obj_hdr *)buf;
+
+	in->yst_mode = oh->yst_mode;
+	yaffs_load_attribs(in, oh);
+	yaffs_set_obj_name_from_oh(in, oh);
+
+	if (in->variant_type == YAFFS_OBJECT_TYPE_SYMLINK) {
+		in->variant.symlink_variant.alias =
+		    yaffs_clone_str(oh->alias);
+		if (!in->variant.symlink_variant.alias)
+			alloc_failed = 1;	/* Not returned */
+	}
+	yaffs_release_temp_buffer(dev, buf);
+}
+
+static void yaffs_load_name_from_oh(struct yaffs_dev *dev, YCHAR *name,
+				    const YCHAR *oh_name, int buff_size)
+{
+#ifdef CONFIG_YAFFS_AUTO_UNICODE
+	if (dev->param.auto_unicode) {
+		if (*oh_name) {
+			/* It is an ASCII name, do an ASCII to
+			 * unicode conversion */
+			const char *ascii_oh_name = (const char *)oh_name;
+			int n = buff_size - 1;
+			while (n > 0 && *ascii_oh_name) {
+				*name = *ascii_oh_name;
+				name++;
+				ascii_oh_name++;
+				n--;
+			}
+		} else {
+			strncpy(name, oh_name + 1, buff_size - 1);
+		}
+	} else {
+#else
+	(void) dev;
+	{
+#endif
+		strncpy(name, oh_name, buff_size - 1);
+	}
+}
+
+static void yaffs_load_oh_from_name(struct yaffs_dev *dev, YCHAR *oh_name,
+				    const YCHAR *name)
+{
+#ifdef CONFIG_YAFFS_AUTO_UNICODE
+
+	int is_ascii;
+	YCHAR *w;
+
+	if (dev->param.auto_unicode) {
+
+		is_ascii = 1;
+		w = name;
+
+		/* Figure out if the name will fit in ascii character set */
+		while (is_ascii && *w) {
+			if ((*w) & 0xff00)
+				is_ascii = 0;
+			w++;
+		}
+
+		if (is_ascii) {
+			/* It is an ASCII name, so convert unicode to ascii */
+			char *ascii_oh_name = (char *)oh_name;
+			int n = YAFFS_MAX_NAME_LENGTH - 1;
+			while (n > 0 && *name) {
+				*ascii_oh_name = *name;
+				name++;
+				ascii_oh_name++;
+				n--;
+			}
+		} else {
+			/* Unicode name, so save starting at the second YCHAR */
+			*oh_name = 0;
+			strncpy(oh_name + 1, name, YAFFS_MAX_NAME_LENGTH - 2);
+		}
+	} else {
+#else
+	dev = dev;
+	{
+#endif
+		strncpy(oh_name, name, YAFFS_MAX_NAME_LENGTH - 1);
+	}
+}
+
+/* UpdateObjectHeader updates the header on NAND for an object.
+ * If name is not NULL, then that new name is used.
+ */
+int yaffs_update_oh(struct yaffs_obj *in, const YCHAR *name, int force,
+		    int is_shrink, int shadows, struct yaffs_xattr_mod *xmod)
+{
+
+	struct yaffs_block_info *bi;
+	struct yaffs_dev *dev = in->my_dev;
+	int prev_chunk_id;
+	int ret_val = 0;
+	int result = 0;
+	int new_chunk_id;
+	struct yaffs_ext_tags new_tags;
+	struct yaffs_ext_tags old_tags;
+	const YCHAR *alias = NULL;
+	u8 *buffer = NULL;
+	YCHAR old_name[YAFFS_MAX_NAME_LENGTH + 1];
+	struct yaffs_obj_hdr *oh = NULL;
+	loff_t file_size = 0;
+
+	strcpy(old_name, _Y("silly old name"));
+
+	if (in->fake && in != dev->root_dir && !force && !xmod)
+		return ret_val;
+
+	yaffs_check_gc(dev, 0);
+	yaffs_check_obj_details_loaded(in);
+
+	buffer = yaffs_get_temp_buffer(in->my_dev);
+	oh = (struct yaffs_obj_hdr *)buffer;
+
+	prev_chunk_id = in->hdr_chunk;
+
+	if (prev_chunk_id > 0) {
+		result = yaffs_rd_chunk_tags_nand(dev, prev_chunk_id,
+						  buffer, &old_tags);
+
+		yaffs_verify_oh(in, oh, &old_tags, 0);
+		memcpy(old_name, oh->name, sizeof(oh->name));
+		memset(buffer, 0xff, sizeof(struct yaffs_obj_hdr));
+	} else {
+		memset(buffer, 0xff, dev->data_bytes_per_chunk);
+	}
+
+	oh->type = in->variant_type;
+	oh->yst_mode = in->yst_mode;
+	oh->shadows_obj = oh->inband_shadowed_obj_id = shadows;
+
+	yaffs_load_attribs_oh(oh, in);
+
+	if (in->parent)
+		oh->parent_obj_id = in->parent->obj_id;
+	else
+		oh->parent_obj_id = 0;
+
+	if (name && *name) {
+		memset(oh->name, 0, sizeof(oh->name));
+		yaffs_load_oh_from_name(dev, oh->name, name);
+	} else if (prev_chunk_id > 0) {
+		memcpy(oh->name, old_name, sizeof(oh->name));
+	} else {
+		memset(oh->name, 0, sizeof(oh->name));
+	}
+
+	oh->is_shrink = is_shrink;
+
+	switch (in->variant_type) {
+	case YAFFS_OBJECT_TYPE_UNKNOWN:
+		/* Should not happen */
+		break;
+	case YAFFS_OBJECT_TYPE_FILE:
+		if (oh->parent_obj_id != YAFFS_OBJECTID_DELETED &&
+		    oh->parent_obj_id != YAFFS_OBJECTID_UNLINKED)
+			file_size = in->variant.file_variant.file_size;
+		yaffs_oh_size_load(oh, file_size);
+		break;
+	case YAFFS_OBJECT_TYPE_HARDLINK:
+		oh->equiv_id = in->variant.hardlink_variant.equiv_id;
+		break;
+	case YAFFS_OBJECT_TYPE_SPECIAL:
+		/* Do nothing */
+		break;
+	case YAFFS_OBJECT_TYPE_DIRECTORY:
+		/* Do nothing */
+		break;
+	case YAFFS_OBJECT_TYPE_SYMLINK:
+		alias = in->variant.symlink_variant.alias;
+		if (!alias)
+			alias = _Y("no alias");
+		strncpy(oh->alias, alias, YAFFS_MAX_ALIAS_LENGTH);
+		oh->alias[YAFFS_MAX_ALIAS_LENGTH] = 0;
+		break;
+	}
+
+	/* process any xattrib modifications */
+	if (xmod)
+		yaffs_apply_xattrib_mod(in, (char *)buffer, xmod);
+
+	/* Tags */
+	memset(&new_tags, 0, sizeof(new_tags));
+	in->serial++;
+	new_tags.chunk_id = 0;
+	new_tags.obj_id = in->obj_id;
+	new_tags.serial_number = in->serial;
+
+	/* Add extra info for file header */
+	new_tags.extra_available = 1;
+	new_tags.extra_parent_id = oh->parent_obj_id;
+	new_tags.extra_file_size = file_size;
+	new_tags.extra_is_shrink = oh->is_shrink;
+	new_tags.extra_equiv_id = oh->equiv_id;
+	new_tags.extra_shadows = (oh->shadows_obj > 0) ? 1 : 0;
+	new_tags.extra_obj_type = in->variant_type;
+	yaffs_verify_oh(in, oh, &new_tags, 1);
+
+	/* Create new chunk in NAND */
+	new_chunk_id =
+	    yaffs_write_new_chunk(dev, buffer, &new_tags,
+				  (prev_chunk_id > 0) ? 1 : 0);
+
+	if (buffer)
+		yaffs_release_temp_buffer(dev, buffer);
+
+	if (new_chunk_id < 0)
+		return new_chunk_id;
+
+	in->hdr_chunk = new_chunk_id;
+
+	if (prev_chunk_id > 0)
+		yaffs_chunk_del(dev, prev_chunk_id, 1, __LINE__);
+
+	if (!yaffs_obj_cache_dirty(in))
+		in->dirty = 0;
+
+	/* If this was a shrink, then mark the block
+	 * that the chunk lives on */
+	if (is_shrink) {
+		bi = yaffs_get_block_info(in->my_dev,
+					  new_chunk_id /
+					  in->my_dev->param.chunks_per_block);
+		bi->has_shrink_hdr = 1;
+	}
+
+
+	return new_chunk_id;
+}
+
+/*--------------------- File read/write ------------------------
+ * Read and write have very similar structures.
+ * In general the read/write has three parts to it
+ * An incomplete chunk to start with (if the read/write is not chunk-aligned)
+ * Some complete chunks
+ * An incomplete chunk to end off with
+ *
+ * Curve-balls: the first chunk might also be the last chunk.
+ */
+
+int yaffs_file_rd(struct yaffs_obj *in, u8 * buffer, loff_t offset, int n_bytes)
+{
+	int chunk;
+	u32 start;
+	int n_copy;
+	int n = n_bytes;
+	int n_done = 0;
+	struct yaffs_cache *cache;
+	struct yaffs_dev *dev;
+
+	dev = in->my_dev;
+
+	while (n > 0) {
+		yaffs_addr_to_chunk(dev, offset, &chunk, &start);
+		chunk++;
+
+		/* OK now check for the curveball where the start and end are in
+		 * the same chunk.
+		 */
+		if ((start + n) < dev->data_bytes_per_chunk)
+			n_copy = n;
+		else
+			n_copy = dev->data_bytes_per_chunk - start;
+
+		cache = yaffs_find_chunk_cache(in, chunk);
+
+		/* If the chunk is already in the cache or it is less than
+		 * a whole chunk or we're using inband tags then use the cache
+		 * (if there is caching) else bypass the cache.
+		 */
+		if (cache || n_copy != dev->data_bytes_per_chunk ||
+		    dev->param.inband_tags) {
+			if (dev->param.n_caches > 0) {
+
+				/* If we can't find the data in the cache,
+				 * then load it up. */
+
+				if (!cache) {
+					cache =
+					    yaffs_grab_chunk_cache(in->my_dev);
+					cache->object = in;
+					cache->chunk_id = chunk;
+					cache->dirty = 0;
+					cache->locked = 0;
+					yaffs_rd_data_obj(in, chunk,
+							  cache->data);
+					cache->n_bytes = 0;
+				}
+
+				yaffs_use_cache(dev, cache, 0);
+
+				cache->locked = 1;
+
+				memcpy(buffer, &cache->data[start], n_copy);
+
+				cache->locked = 0;
+			} else {
+				/* Read into the local buffer then copy.. */
+
+				u8 *local_buffer =
+				    yaffs_get_temp_buffer(dev);
+				yaffs_rd_data_obj(in, chunk, local_buffer);
+
+				memcpy(buffer, &local_buffer[start], n_copy);
+
+				yaffs_release_temp_buffer(dev, local_buffer);
+			}
+		} else {
+			/* A full chunk. Read directly into the buffer. */
+			yaffs_rd_data_obj(in, chunk, buffer);
+		}
+		n -= n_copy;
+		offset += n_copy;
+		buffer += n_copy;
+		n_done += n_copy;
+	}
+	return n_done;
+}
+
+int yaffs_do_file_wr(struct yaffs_obj *in, const u8 *buffer, loff_t offset,
+		     int n_bytes, int write_through)
+{
+
+	int chunk;
+	u32 start;
+	int n_copy;
+	int n = n_bytes;
+	int n_done = 0;
+	int n_writeback;
+	loff_t start_write = offset;
+	int chunk_written = 0;
+	u32 n_bytes_read;
+	loff_t chunk_start;
+	struct yaffs_dev *dev;
+
+	dev = in->my_dev;
+
+	while (n > 0 && chunk_written >= 0) {
+		yaffs_addr_to_chunk(dev, offset, &chunk, &start);
+
+		if (((loff_t)chunk) *
+		    dev->data_bytes_per_chunk + start != offset ||
+		    start >= dev->data_bytes_per_chunk) {
+			yaffs_trace(YAFFS_TRACE_ERROR,
+				"AddrToChunk of offset %lld gives chunk %d start %d",
+				offset, chunk, start);
+		}
+		chunk++;	/* File pos to chunk in file offset */
+
+		/* OK now check for the curveball where the start and end are in
+		 * the same chunk.
+		 */
+
+		if ((start + n) < dev->data_bytes_per_chunk) {
+			n_copy = n;
+
+			/* Now calculate how many bytes to write back....
+			 * If we're overwriting and not writing to then end of
+			 * file then we need to write back as much as was there
+			 * before.
+			 */
+
+			chunk_start = (((loff_t)(chunk - 1)) *
+					dev->data_bytes_per_chunk);
+
+			if (chunk_start > in->variant.file_variant.file_size)
+				n_bytes_read = 0;	/* Past end of file */
+			else
+				n_bytes_read =
+				    in->variant.file_variant.file_size -
+				    chunk_start;
+
+			if (n_bytes_read > dev->data_bytes_per_chunk)
+				n_bytes_read = dev->data_bytes_per_chunk;
+
+			n_writeback =
+			    (n_bytes_read >
+			     (start + n)) ? n_bytes_read : (start + n);
+
+			if (n_writeback < 0 ||
+			    n_writeback > dev->data_bytes_per_chunk)
+				BUG();
+
+		} else {
+			n_copy = dev->data_bytes_per_chunk - start;
+			n_writeback = dev->data_bytes_per_chunk;
+		}
+
+		if (n_copy != dev->data_bytes_per_chunk ||
+		    !dev->param.cache_bypass_aligned ||
+		    dev->param.inband_tags) {
+			/* An incomplete start or end chunk (or maybe both
+			 * start and end chunk), or we're using inband tags,
+			 * or we're forcing writes through the cache,
+			 * so we want to use the cache buffers.
+			 */
+			if (dev->param.n_caches > 0) {
+				struct yaffs_cache *cache;
+
+				/* If we can't find the data in the cache, then
+				 * load the cache */
+				cache = yaffs_find_chunk_cache(in, chunk);
+
+				if (!cache &&
+				    yaffs_check_alloc_available(dev, 1)) {
+					cache = yaffs_grab_chunk_cache(dev);
+					cache->object = in;
+					cache->chunk_id = chunk;
+					cache->dirty = 0;
+					cache->locked = 0;
+					yaffs_rd_data_obj(in, chunk,
+							  cache->data);
+				} else if (cache &&
+					   !cache->dirty &&
+					   !yaffs_check_alloc_available(dev,
+									1)) {
+					/* Drop the cache if it was a read cache
+					 * item and no space check has been made
+					 * for it.
+					 */
+					cache = NULL;
+				}
+
+				if (cache) {
+					yaffs_use_cache(dev, cache, 1);
+					cache->locked = 1;
+
+					memcpy(&cache->data[start], buffer,
+					       n_copy);
+
+					cache->locked = 0;
+					cache->n_bytes = n_writeback;
+
+					if (write_through) {
+						chunk_written =
+						    yaffs_wr_data_obj
+						    (cache->object,
+						     cache->chunk_id,
+						     cache->data,
+						     cache->n_bytes, 1);
+						cache->dirty = 0;
+					}
+				} else {
+					chunk_written = -1;	/* fail write */
+				}
+			} else {
+				/* An incomplete start or end chunk (or maybe
+				 * both start and end chunk). Read into the
+				 * local buffer then copy over and write back.
+				 */
+
+				u8 *local_buffer = yaffs_get_temp_buffer(dev);
+
+				yaffs_rd_data_obj(in, chunk, local_buffer);
+				memcpy(&local_buffer[start], buffer, n_copy);
+
+				chunk_written =
+				    yaffs_wr_data_obj(in, chunk,
+						      local_buffer,
+						      n_writeback, 0);
+
+				yaffs_release_temp_buffer(dev, local_buffer);
+			}
+		} else {
+			/* A full chunk. Write directly from the buffer. */
+
+			chunk_written =
+			    yaffs_wr_data_obj(in, chunk, buffer,
+					      dev->data_bytes_per_chunk, 0);
+
+			/* Since we've overwritten the cached data,
+			 * we better invalidate it. */
+			yaffs_invalidate_chunk_cache(in, chunk);
+		}
+
+		if (chunk_written >= 0) {
+			n -= n_copy;
+			offset += n_copy;
+			buffer += n_copy;
+			n_done += n_copy;
+		}
+	}
+
+	/* Update file object */
+
+	if ((start_write + n_done) > in->variant.file_variant.file_size)
+		in->variant.file_variant.file_size = (start_write + n_done);
+
+	in->dirty = 1;
+	return n_done;
+}
+
+int yaffs_wr_file(struct yaffs_obj *in, const u8 *buffer, loff_t offset,
+		  int n_bytes, int write_through)
+{
+	yaffs2_handle_hole(in, offset);
+	return yaffs_do_file_wr(in, buffer, offset, n_bytes, write_through);
+}
+
+/* ---------------------- File resizing stuff ------------------ */
+
+static void yaffs_prune_chunks(struct yaffs_obj *in, loff_t new_size)
+{
+
+	struct yaffs_dev *dev = in->my_dev;
+	loff_t old_size = in->variant.file_variant.file_size;
+	int i;
+	int chunk_id;
+	u32 dummy;
+	int last_del;
+	int start_del;
+
+	if (old_size > 0)
+		yaffs_addr_to_chunk(dev, old_size - 1, &last_del, &dummy);
+	else
+		last_del = 0;
+
+	yaffs_addr_to_chunk(dev, new_size + dev->data_bytes_per_chunk - 1,
+				&start_del, &dummy);
+	last_del++;
+	start_del++;
+
+	/* Delete backwards so that we don't end up with holes if
+	 * power is lost part-way through the operation.
+	 */
+	for (i = last_del; i >= start_del; i--) {
+		/* NB this could be optimised somewhat,
+		 * eg. could retrieve the tags and write them without
+		 * using yaffs_chunk_del
+		 */
+
+		chunk_id = yaffs_find_del_file_chunk(in, i, NULL);
+
+		if (chunk_id < 1)
+			continue;
+
+		if (chunk_id <
+		    (dev->internal_start_block * dev->param.chunks_per_block) ||
+		    chunk_id >=
+		    ((dev->internal_end_block + 1) *
+		      dev->param.chunks_per_block)) {
+			yaffs_trace(YAFFS_TRACE_ALWAYS,
+				"Found daft chunk_id %d for %d",
+				chunk_id, i);
+		} else {
+			in->n_data_chunks--;
+			yaffs_chunk_del(dev, chunk_id, 1, __LINE__);
+		}
+	}
+}
+
+void yaffs_resize_file_down(struct yaffs_obj *obj, loff_t new_size)
+{
+	int new_full;
+	u32 new_partial;
+	struct yaffs_dev *dev = obj->my_dev;
+
+	yaffs_addr_to_chunk(dev, new_size, &new_full, &new_partial);
+
+	yaffs_prune_chunks(obj, new_size);
+
+	if (new_partial != 0) {
+		int last_chunk = 1 + new_full;
+		u8 *local_buffer = yaffs_get_temp_buffer(dev);
+
+		/* Rewrite the last chunk with its new size and zero pad */
+		yaffs_rd_data_obj(obj, last_chunk, local_buffer);
+		memset(local_buffer + new_partial, 0,
+		       dev->data_bytes_per_chunk - new_partial);
+
+		yaffs_wr_data_obj(obj, last_chunk, local_buffer,
+				  new_partial, 1);
+
+		yaffs_release_temp_buffer(dev, local_buffer);
+	}
+
+	obj->variant.file_variant.file_size = new_size;
+
+	yaffs_prune_tree(dev, &obj->variant.file_variant);
+}
+
+int yaffs_resize_file(struct yaffs_obj *in, loff_t new_size)
+{
+	struct yaffs_dev *dev = in->my_dev;
+	loff_t old_size = in->variant.file_variant.file_size;
+
+	yaffs_flush_file_cache(in);
+	yaffs_invalidate_whole_cache(in);
+
+	yaffs_check_gc(dev, 0);
+
+	if (in->variant_type != YAFFS_OBJECT_TYPE_FILE)
+		return YAFFS_FAIL;
+
+	if (new_size == old_size)
+		return YAFFS_OK;
+
+	if (new_size > old_size) {
+		yaffs2_handle_hole(in, new_size);
+		in->variant.file_variant.file_size = new_size;
+	} else {
+		/* new_size < old_size */
+		yaffs_resize_file_down(in, new_size);
+	}
+
+	/* Write a new object header to reflect the resize.
+	 * show we've shrunk the file, if need be
+	 * Do this only if the file is not in the deleted directories
+	 * and is not shadowed.
+	 */
+	if (in->parent &&
+	    !in->is_shadowed &&
+	    in->parent->obj_id != YAFFS_OBJECTID_UNLINKED &&
+	    in->parent->obj_id != YAFFS_OBJECTID_DELETED)
+		yaffs_update_oh(in, NULL, 0, 0, 0, NULL);
+
+	return YAFFS_OK;
+}
+
+int yaffs_flush_file(struct yaffs_obj *in, int update_time, int data_sync)
+{
+	if (!in->dirty)
+		return YAFFS_OK;
+
+	yaffs_flush_file_cache(in);
+
+	if (data_sync)
+		return YAFFS_OK;
+
+	if (update_time)
+		yaffs_load_current_time(in, 0, 0);
+
+	return (yaffs_update_oh(in, NULL, 0, 0, 0, NULL) >= 0) ?
+				YAFFS_OK : YAFFS_FAIL;
+}
+
+
+/* yaffs_del_file deletes the whole file data
+ * and the inode associated with the file.
+ * It does not delete the links associated with the file.
+ */
+static int yaffs_unlink_file_if_needed(struct yaffs_obj *in)
+{
+	int ret_val;
+	int del_now = 0;
+	struct yaffs_dev *dev = in->my_dev;
+
+	if (!in->my_inode)
+		del_now = 1;
+
+	if (del_now) {
+		ret_val =
+		    yaffs_change_obj_name(in, in->my_dev->del_dir,
+					  _Y("deleted"), 0, 0);
+		yaffs_trace(YAFFS_TRACE_TRACING,
+			"yaffs: immediate deletion of file %d",
+			in->obj_id);
+		in->deleted = 1;
+		in->my_dev->n_deleted_files++;
+		if (dev->param.disable_soft_del || dev->param.is_yaffs2)
+			yaffs_resize_file(in, 0);
+		yaffs_soft_del_file(in);
+	} else {
+		ret_val =
+		    yaffs_change_obj_name(in, in->my_dev->unlinked_dir,
+					  _Y("unlinked"), 0, 0);
+	}
+	return ret_val;
+}
+
+static int yaffs_del_file(struct yaffs_obj *in)
+{
+	int ret_val = YAFFS_OK;
+	int deleted;	/* Need to cache value on stack if in is freed */
+	struct yaffs_dev *dev = in->my_dev;
+
+	if (dev->param.disable_soft_del || dev->param.is_yaffs2)
+		yaffs_resize_file(in, 0);
+
+	if (in->n_data_chunks > 0) {
+		/* Use soft deletion if there is data in the file.
+		 * That won't be the case if it has been resized to zero.
+		 */
+		if (!in->unlinked)
+			ret_val = yaffs_unlink_file_if_needed(in);
+
+		deleted = in->deleted;
+
+		if (ret_val == YAFFS_OK && in->unlinked && !in->deleted) {
+			in->deleted = 1;
+			deleted = 1;
+			in->my_dev->n_deleted_files++;
+			yaffs_soft_del_file(in);
+		}
+		return deleted ? YAFFS_OK : YAFFS_FAIL;
+	} else {
+		/* The file has no data chunks so we toss it immediately */
+		yaffs_free_tnode(in->my_dev, in->variant.file_variant.top);
+		in->variant.file_variant.top = NULL;
+		yaffs_generic_obj_del(in);
+
+		return YAFFS_OK;
+	}
+}
+
+int yaffs_is_non_empty_dir(struct yaffs_obj *obj)
+{
+	return (obj &&
+		obj->variant_type == YAFFS_OBJECT_TYPE_DIRECTORY) &&
+		!(list_empty(&obj->variant.dir_variant.children));
+}
+
+static int yaffs_del_dir(struct yaffs_obj *obj)
+{
+	/* First check that the directory is empty. */
+	if (yaffs_is_non_empty_dir(obj))
+		return YAFFS_FAIL;
+
+	return yaffs_generic_obj_del(obj);
+}
+
+static int yaffs_del_symlink(struct yaffs_obj *in)
+{
+	kfree(in->variant.symlink_variant.alias);
+	in->variant.symlink_variant.alias = NULL;
+
+	return yaffs_generic_obj_del(in);
+}
+
+static int yaffs_del_link(struct yaffs_obj *in)
+{
+	/* remove this hardlink from the list associated with the equivalent
+	 * object
+	 */
+	list_del_init(&in->hard_links);
+	return yaffs_generic_obj_del(in);
+}
+
+int yaffs_del_obj(struct yaffs_obj *obj)
+{
+	int ret_val = -1;
+
+	switch (obj->variant_type) {
+	case YAFFS_OBJECT_TYPE_FILE:
+		ret_val = yaffs_del_file(obj);
+		break;
+	case YAFFS_OBJECT_TYPE_DIRECTORY:
+		if (!list_empty(&obj->variant.dir_variant.dirty)) {
+			yaffs_trace(YAFFS_TRACE_BACKGROUND,
+				"Remove object %d from dirty directories",
+				obj->obj_id);
+			list_del_init(&obj->variant.dir_variant.dirty);
+		}
+		return yaffs_del_dir(obj);
+		break;
+	case YAFFS_OBJECT_TYPE_SYMLINK:
+		ret_val = yaffs_del_symlink(obj);
+		break;
+	case YAFFS_OBJECT_TYPE_HARDLINK:
+		ret_val = yaffs_del_link(obj);
+		break;
+	case YAFFS_OBJECT_TYPE_SPECIAL:
+		ret_val = yaffs_generic_obj_del(obj);
+		break;
+	case YAFFS_OBJECT_TYPE_UNKNOWN:
+		ret_val = 0;
+		break;		/* should not happen. */
+	}
+	return ret_val;
+}
+
+static int yaffs_unlink_worker(struct yaffs_obj *obj)
+{
+	int del_now = 0;
+
+	if (!obj)
+		return YAFFS_FAIL;
+
+	if (!obj->my_inode)
+		del_now = 1;
+
+	yaffs_update_parent(obj->parent);
+
+	if (obj->variant_type == YAFFS_OBJECT_TYPE_HARDLINK) {
+		return yaffs_del_link(obj);
+	} else if (!list_empty(&obj->hard_links)) {
+		/* Curve ball: We're unlinking an object that has a hardlink.
+		 *
+		 * This problem arises because we are not strictly following
+		 * The Linux link/inode model.
+		 *
+		 * We can't really delete the object.
+		 * Instead, we do the following:
+		 * - Select a hardlink.
+		 * - Unhook it from the hard links
+		 * - Move it from its parent directory so that the rename works.
+		 * - Rename the object to the hardlink's name.
+		 * - Delete the hardlink
+		 */
+
+		struct yaffs_obj *hl;
+		struct yaffs_obj *parent;
+		int ret_val;
+		YCHAR name[YAFFS_MAX_NAME_LENGTH + 1];
+
+		hl = list_entry(obj->hard_links.next, struct yaffs_obj,
+				hard_links);
+
+		yaffs_get_obj_name(hl, name, YAFFS_MAX_NAME_LENGTH + 1);
+		parent = hl->parent;
+
+		list_del_init(&hl->hard_links);
+
+		yaffs_add_obj_to_dir(obj->my_dev->unlinked_dir, hl);
+
+		ret_val = yaffs_change_obj_name(obj, parent, name, 0, 0);
+
+		if (ret_val == YAFFS_OK)
+			ret_val = yaffs_generic_obj_del(hl);
+
+		return ret_val;
+
+	} else if (del_now) {
+		switch (obj->variant_type) {
+		case YAFFS_OBJECT_TYPE_FILE:
+			return yaffs_del_file(obj);
+			break;
+		case YAFFS_OBJECT_TYPE_DIRECTORY:
+			list_del_init(&obj->variant.dir_variant.dirty);
+			return yaffs_del_dir(obj);
+			break;
+		case YAFFS_OBJECT_TYPE_SYMLINK:
+			return yaffs_del_symlink(obj);
+			break;
+		case YAFFS_OBJECT_TYPE_SPECIAL:
+			return yaffs_generic_obj_del(obj);
+			break;
+		case YAFFS_OBJECT_TYPE_HARDLINK:
+		case YAFFS_OBJECT_TYPE_UNKNOWN:
+		default:
+			return YAFFS_FAIL;
+		}
+	} else if (yaffs_is_non_empty_dir(obj)) {
+		return YAFFS_FAIL;
+	} else {
+		return yaffs_change_obj_name(obj, obj->my_dev->unlinked_dir,
+						_Y("unlinked"), 0, 0);
+	}
+}
+
+static int yaffs_unlink_obj(struct yaffs_obj *obj)
+{
+	if (obj && obj->unlink_allowed)
+		return yaffs_unlink_worker(obj);
+
+	return YAFFS_FAIL;
+}
+
+int yaffs_unlinker(struct yaffs_obj *dir, const YCHAR *name)
+{
+	struct yaffs_obj *obj;
+
+	obj = yaffs_find_by_name(dir, name);
+	return yaffs_unlink_obj(obj);
+}
+
+/* Note:
+ * If old_name is NULL then we take old_dir as the object to be renamed.
+ */
+int yaffs_rename_obj(struct yaffs_obj *old_dir, const YCHAR *old_name,
+		     struct yaffs_obj *new_dir, const YCHAR *new_name)
+{
+	struct yaffs_obj *obj = NULL;
+	struct yaffs_obj *existing_target = NULL;
+	int force = 0;
+	int result;
+	struct yaffs_dev *dev;
+
+	if (!old_dir || old_dir->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) {
+		BUG();
+		return YAFFS_FAIL;
+	}
+	if (!new_dir || new_dir->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) {
+		BUG();
+		return YAFFS_FAIL;
+	}
+
+	dev = old_dir->my_dev;
+
+#ifdef CONFIG_YAFFS_CASE_INSENSITIVE
+	/* Special case for case insemsitive systems.
+	 * While look-up is case insensitive, the name isn't.
+	 * Therefore we might want to change x.txt to X.txt
+	 */
+	if (old_dir == new_dir &&
+		old_name && new_name &&
+		strcmp(old_name, new_name) == 0)
+		force = 1;
+#endif
+
+	if (strnlen(new_name, YAFFS_MAX_NAME_LENGTH + 1) >
+	    YAFFS_MAX_NAME_LENGTH)
+		/* ENAMETOOLONG */
+		return YAFFS_FAIL;
+
+	if (old_name)
+		obj = yaffs_find_by_name(old_dir, old_name);
+	else{
+		obj = old_dir;
+		old_dir = obj->parent;
+	}
+
+	if (obj && obj->rename_allowed) {
+		/* Now handle an existing target, if there is one */
+		existing_target = yaffs_find_by_name(new_dir, new_name);
+		if (yaffs_is_non_empty_dir(existing_target)) {
+			return YAFFS_FAIL;	/* ENOTEMPTY */
+		} else if (existing_target && existing_target != obj) {
+			/* Nuke the target first, using shadowing,
+			 * but only if it isn't the same object.
+			 *
+			 * Note we must disable gc here otherwise it can mess
+			 * up the shadowing.
+			 *
+			 */
+			dev->gc_disable = 1;
+			yaffs_change_obj_name(obj, new_dir, new_name, force,
+					      existing_target->obj_id);
+			existing_target->is_shadowed = 1;
+			yaffs_unlink_obj(existing_target);
+			dev->gc_disable = 0;
+		}
+
+		result = yaffs_change_obj_name(obj, new_dir, new_name, 1, 0);
+
+		yaffs_update_parent(old_dir);
+		if (new_dir != old_dir)
+			yaffs_update_parent(new_dir);
+
+		return result;
+	}
+	return YAFFS_FAIL;
+}
+
+/*----------------------- Initialisation Scanning ---------------------- */
+
+void yaffs_handle_shadowed_obj(struct yaffs_dev *dev, int obj_id,
+			       int backward_scanning)
+{
+	struct yaffs_obj *obj;
+
+	if (backward_scanning) {
+		/* Handle YAFFS2 case (backward scanning)
+		 * If the shadowed object exists then ignore.
+		 */
+		obj = yaffs_find_by_number(dev, obj_id);
+		if (obj)
+			return;
+	}
+
+	/* Let's create it (if it does not exist) assuming it is a file so that
+	 * it can do shrinking etc.
+	 * We put it in unlinked dir to be cleaned up after the scanning
+	 */
+	obj =
+	    yaffs_find_or_create_by_number(dev, obj_id, YAFFS_OBJECT_TYPE_FILE);
+	if (!obj)
+		return;
+	obj->is_shadowed = 1;
+	yaffs_add_obj_to_dir(dev->unlinked_dir, obj);
+	obj->variant.file_variant.shrink_size = 0;
+	obj->valid = 1;		/* So that we don't read any other info. */
+}
+
+void yaffs_link_fixup(struct yaffs_dev *dev, struct list_head *hard_list)
+{
+	struct list_head *lh;
+	struct list_head *save;
+	struct yaffs_obj *hl;
+	struct yaffs_obj *in;
+
+	list_for_each_safe(lh, save, hard_list) {
+		hl = list_entry(lh, struct yaffs_obj, hard_links);
+		in = yaffs_find_by_number(dev,
+					hl->variant.hardlink_variant.equiv_id);
+
+		if (in) {
+			/* Add the hardlink pointers */
+			hl->variant.hardlink_variant.equiv_obj = in;
+			list_add(&hl->hard_links, &in->hard_links);
+		} else {
+			/* Todo Need to report/handle this better.
+			 * Got a problem... hardlink to a non-existant object
+			 */
+			hl->variant.hardlink_variant.equiv_obj = NULL;
+			INIT_LIST_HEAD(&hl->hard_links);
+		}
+	}
+}
+
+static void yaffs_strip_deleted_objs(struct yaffs_dev *dev)
+{
+	/*
+	 *  Sort out state of unlinked and deleted objects after scanning.
+	 */
+	struct list_head *i;
+	struct list_head *n;
+	struct yaffs_obj *l;
+
+	if (dev->read_only)
+		return;
+
+	/* Soft delete all the unlinked files */
+	list_for_each_safe(i, n,
+			   &dev->unlinked_dir->variant.dir_variant.children) {
+		l = list_entry(i, struct yaffs_obj, siblings);
+		yaffs_del_obj(l);
+	}
+
+	list_for_each_safe(i, n, &dev->del_dir->variant.dir_variant.children) {
+		l = list_entry(i, struct yaffs_obj, siblings);
+		yaffs_del_obj(l);
+	}
+}
+
+/*
+ * This code iterates through all the objects making sure that they are rooted.
+ * Any unrooted objects are re-rooted in lost+found.
+ * An object needs to be in one of:
+ * - Directly under deleted, unlinked
+ * - Directly or indirectly under root.
+ *
+ * Note:
+ *  This code assumes that we don't ever change the current relationships
+ *  between directories:
+ *   root_dir->parent == unlinked_dir->parent == del_dir->parent == NULL
+ *   lost-n-found->parent == root_dir
+ *
+ * This fixes the problem where directories might have inadvertently been
+ * deleted leaving the object "hanging" without being rooted in the
+ * directory tree.
+ */
+
+static int yaffs_has_null_parent(struct yaffs_dev *dev, struct yaffs_obj *obj)
+{
+	return (obj == dev->del_dir ||
+		obj == dev->unlinked_dir || obj == dev->root_dir);
+}
+
+static void yaffs_fix_hanging_objs(struct yaffs_dev *dev)
+{
+	struct yaffs_obj *obj;
+	struct yaffs_obj *parent;
+	int i;
+	struct list_head *lh;
+	struct list_head *n;
+	int depth_limit;
+	int hanging;
+
+	if (dev->read_only)
+		return;
+
+	/* Iterate through the objects in each hash entry,
+	 * looking at each object.
+	 * Make sure it is rooted.
+	 */
+
+	for (i = 0; i < YAFFS_NOBJECT_BUCKETS; i++) {
+		list_for_each_safe(lh, n, &dev->obj_bucket[i].list) {
+			obj = list_entry(lh, struct yaffs_obj, hash_link);
+			parent = obj->parent;
+
+			if (yaffs_has_null_parent(dev, obj)) {
+				/* These directories are not hanging */
+				hanging = 0;
+			} else if (!parent ||
+				   parent->variant_type !=
+				   YAFFS_OBJECT_TYPE_DIRECTORY) {
+				hanging = 1;
+			} else if (yaffs_has_null_parent(dev, parent)) {
+				hanging = 0;
+			} else {
+				/*
+				 * Need to follow the parent chain to
+				 * see if it is hanging.
+				 */
+				hanging = 0;
+				depth_limit = 100;
+
+				while (parent != dev->root_dir &&
+				       parent->parent &&
+				       parent->parent->variant_type ==
+				       YAFFS_OBJECT_TYPE_DIRECTORY &&
+				       depth_limit > 0) {
+					parent = parent->parent;
+					depth_limit--;
+				}
+				if (parent != dev->root_dir)
+					hanging = 1;
+			}
+			if (hanging) {
+				yaffs_trace(YAFFS_TRACE_SCAN,
+					"Hanging object %d moved to lost and found",
+					obj->obj_id);
+				yaffs_add_obj_to_dir(dev->lost_n_found, obj);
+			}
+		}
+	}
+}
+
+/*
+ * Delete directory contents for cleaning up lost and found.
+ */
+static void yaffs_del_dir_contents(struct yaffs_obj *dir)
+{
+	struct yaffs_obj *obj;
+	struct list_head *lh;
+	struct list_head *n;
+
+	if (dir->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY)
+		BUG();
+
+	list_for_each_safe(lh, n, &dir->variant.dir_variant.children) {
+		obj = list_entry(lh, struct yaffs_obj, siblings);
+		if (obj->variant_type == YAFFS_OBJECT_TYPE_DIRECTORY)
+			yaffs_del_dir_contents(obj);
+		yaffs_trace(YAFFS_TRACE_SCAN,
+			"Deleting lost_found object %d",
+			obj->obj_id);
+		yaffs_unlink_obj(obj);
+	}
+}
+
+static void yaffs_empty_l_n_f(struct yaffs_dev *dev)
+{
+	yaffs_del_dir_contents(dev->lost_n_found);
+}
+
+
+struct yaffs_obj *yaffs_find_by_name(struct yaffs_obj *directory,
+				     const YCHAR *name)
+{
+	int sum;
+	struct list_head *i;
+	YCHAR buffer[YAFFS_MAX_NAME_LENGTH + 1];
+	struct yaffs_obj *l;
+
+	if (!name)
+		return NULL;
+
+	if (!directory) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"tragedy: yaffs_find_by_name: null pointer directory"
+			);
+		BUG();
+		return NULL;
+	}
+	if (directory->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"tragedy: yaffs_find_by_name: non-directory"
+			);
+		BUG();
+	}
+
+	sum = yaffs_calc_name_sum(name);
+
+	list_for_each(i, &directory->variant.dir_variant.children) {
+		l = list_entry(i, struct yaffs_obj, siblings);
+
+		if (l->parent != directory)
+			BUG();
+
+		yaffs_check_obj_details_loaded(l);
+
+		/* Special case for lost-n-found */
+		if (l->obj_id == YAFFS_OBJECTID_LOSTNFOUND) {
+			if (!strcmp(name, YAFFS_LOSTNFOUND_NAME))
+				return l;
+		} else if (l->sum == sum || l->hdr_chunk <= 0) {
+			/* LostnFound chunk called Objxxx
+			 * Do a real check
+			 */
+			yaffs_get_obj_name(l, buffer,
+				YAFFS_MAX_NAME_LENGTH + 1);
+			if (!strncmp(name, buffer, YAFFS_MAX_NAME_LENGTH))
+				return l;
+		}
+	}
+	return NULL;
+}
+
+/* GetEquivalentObject dereferences any hard links to get to the
+ * actual object.
+ */
+
+struct yaffs_obj *yaffs_get_equivalent_obj(struct yaffs_obj *obj)
+{
+	if (obj && obj->variant_type == YAFFS_OBJECT_TYPE_HARDLINK) {
+		obj = obj->variant.hardlink_variant.equiv_obj;
+		yaffs_check_obj_details_loaded(obj);
+	}
+	return obj;
+}
+
+/*
+ *  A note or two on object names.
+ *  * If the object name is missing, we then make one up in the form objnnn
+ *
+ *  * ASCII names are stored in the object header's name field from byte zero
+ *  * Unicode names are historically stored starting from byte zero.
+ *
+ * Then there are automatic Unicode names...
+ * The purpose of these is to save names in a way that can be read as
+ * ASCII or Unicode names as appropriate, thus allowing a Unicode and ASCII
+ * system to share files.
+ *
+ * These automatic unicode are stored slightly differently...
+ *  - If the name can fit in the ASCII character space then they are saved as
+ *    ascii names as per above.
+ *  - If the name needs Unicode then the name is saved in Unicode
+ *    starting at oh->name[1].
+
+ */
+static void yaffs_fix_null_name(struct yaffs_obj *obj, YCHAR *name,
+				int buffer_size)
+{
+	/* Create an object name if we could not find one. */
+	if (strnlen(name, YAFFS_MAX_NAME_LENGTH) == 0) {
+		YCHAR local_name[20];
+		YCHAR num_string[20];
+		YCHAR *x = &num_string[19];
+		unsigned v = obj->obj_id;
+		num_string[19] = 0;
+		while (v > 0) {
+			x--;
+			*x = '0' + (v % 10);
+			v /= 10;
+		}
+		/* make up a name */
+		strcpy(local_name, YAFFS_LOSTNFOUND_PREFIX);
+		strcat(local_name, x);
+		strncpy(name, local_name, buffer_size - 1);
+	}
+}
+
+int yaffs_get_obj_name(struct yaffs_obj *obj, YCHAR *name, int buffer_size)
+{
+	memset(name, 0, buffer_size * sizeof(YCHAR));
+	yaffs_check_obj_details_loaded(obj);
+	if (obj->obj_id == YAFFS_OBJECTID_LOSTNFOUND) {
+		strncpy(name, YAFFS_LOSTNFOUND_NAME, buffer_size - 1);
+	} else if (obj->short_name[0]) {
+		strcpy(name, obj->short_name);
+	} else if (obj->hdr_chunk > 0) {
+		int result;
+		u8 *buffer = yaffs_get_temp_buffer(obj->my_dev);
+
+		struct yaffs_obj_hdr *oh = (struct yaffs_obj_hdr *)buffer;
+
+		memset(buffer, 0, obj->my_dev->data_bytes_per_chunk);
+
+		if (obj->hdr_chunk > 0) {
+			result = yaffs_rd_chunk_tags_nand(obj->my_dev,
+							  obj->hdr_chunk,
+							  buffer, NULL);
+		}
+		yaffs_load_name_from_oh(obj->my_dev, name, oh->name,
+					buffer_size);
+
+		yaffs_release_temp_buffer(obj->my_dev, buffer);
+	}
+
+	yaffs_fix_null_name(obj, name, buffer_size);
+
+	return strnlen(name, YAFFS_MAX_NAME_LENGTH);
+}
+
+loff_t yaffs_get_obj_length(struct yaffs_obj *obj)
+{
+	/* Dereference any hard linking */
+	obj = yaffs_get_equivalent_obj(obj);
+
+	if (obj->variant_type == YAFFS_OBJECT_TYPE_FILE)
+		return obj->variant.file_variant.file_size;
+	if (obj->variant_type == YAFFS_OBJECT_TYPE_SYMLINK) {
+		if (!obj->variant.symlink_variant.alias)
+			return 0;
+		return strnlen(obj->variant.symlink_variant.alias,
+				     YAFFS_MAX_ALIAS_LENGTH);
+	} else {
+		/* Only a directory should drop through to here */
+		return obj->my_dev->data_bytes_per_chunk;
+	}
+}
+
+int yaffs_get_obj_link_count(struct yaffs_obj *obj)
+{
+	int count = 0;
+	struct list_head *i;
+
+	if (!obj->unlinked)
+		count++;	/* the object itself */
+
+	list_for_each(i, &obj->hard_links)
+	    count++;		/* add the hard links; */
+
+	return count;
+}
+
+int yaffs_get_obj_inode(struct yaffs_obj *obj)
+{
+	obj = yaffs_get_equivalent_obj(obj);
+
+	return obj->obj_id;
+}
+
+unsigned yaffs_get_obj_type(struct yaffs_obj *obj)
+{
+	obj = yaffs_get_equivalent_obj(obj);
+
+	switch (obj->variant_type) {
+	case YAFFS_OBJECT_TYPE_FILE:
+		return DT_REG;
+		break;
+	case YAFFS_OBJECT_TYPE_DIRECTORY:
+		return DT_DIR;
+		break;
+	case YAFFS_OBJECT_TYPE_SYMLINK:
+		return DT_LNK;
+		break;
+	case YAFFS_OBJECT_TYPE_HARDLINK:
+		return DT_REG;
+		break;
+	case YAFFS_OBJECT_TYPE_SPECIAL:
+		if (S_ISFIFO(obj->yst_mode))
+			return DT_FIFO;
+		if (S_ISCHR(obj->yst_mode))
+			return DT_CHR;
+		if (S_ISBLK(obj->yst_mode))
+			return DT_BLK;
+		if (S_ISSOCK(obj->yst_mode))
+			return DT_SOCK;
+		return DT_REG;
+		break;
+	default:
+		return DT_REG;
+		break;
+	}
+}
+
+YCHAR *yaffs_get_symlink_alias(struct yaffs_obj *obj)
+{
+	obj = yaffs_get_equivalent_obj(obj);
+	if (obj->variant_type == YAFFS_OBJECT_TYPE_SYMLINK)
+		return yaffs_clone_str(obj->variant.symlink_variant.alias);
+	else
+		return yaffs_clone_str(_Y(""));
+}
+
+/*--------------------------- Initialisation code -------------------------- */
+
+static int yaffs_check_dev_fns(struct yaffs_dev *dev)
+{
+	struct yaffs_driver *drv = &dev->drv;
+	struct yaffs_tags_handler *tagger = &dev->tagger;
+
+	/* Common functions, gotta have */
+	if (!drv->drv_read_chunk_fn ||
+	    !drv->drv_write_chunk_fn ||
+	    !drv->drv_erase_fn)
+		return 0;
+
+	if (dev->param.is_yaffs2 &&
+	     (!drv->drv_mark_bad_fn  || !drv->drv_check_bad_fn))
+		return 0;
+
+	/* Install the default tags marshalling functions if needed. */
+	yaffs_tags_compat_install(dev);
+	yaffs_tags_marshall_install(dev);
+
+	/* Check we now have the marshalling functions required. */
+	if (!tagger->write_chunk_tags_fn ||
+	    !tagger->read_chunk_tags_fn ||
+	    !tagger->query_block_fn ||
+	    !tagger->mark_bad_fn)
+		return 0;
+
+	return 1;
+}
+
+static int yaffs_create_initial_dir(struct yaffs_dev *dev)
+{
+	/* Initialise the unlinked, deleted, root and lost+found directories */
+	dev->lost_n_found = dev->root_dir = NULL;
+	dev->unlinked_dir = dev->del_dir = NULL;
+	dev->unlinked_dir =
+	    yaffs_create_fake_dir(dev, YAFFS_OBJECTID_UNLINKED, S_IFDIR);
+	dev->del_dir =
+	    yaffs_create_fake_dir(dev, YAFFS_OBJECTID_DELETED, S_IFDIR);
+	dev->root_dir =
+	    yaffs_create_fake_dir(dev, YAFFS_OBJECTID_ROOT,
+				  YAFFS_ROOT_MODE | S_IFDIR);
+	dev->lost_n_found =
+	    yaffs_create_fake_dir(dev, YAFFS_OBJECTID_LOSTNFOUND,
+				  YAFFS_LOSTNFOUND_MODE | S_IFDIR);
+
+	if (dev->lost_n_found && dev->root_dir && dev->unlinked_dir
+	    && dev->del_dir) {
+		yaffs_add_obj_to_dir(dev->root_dir, dev->lost_n_found);
+		return YAFFS_OK;
+	}
+	return YAFFS_FAIL;
+}
+
+/* Low level init.
+ * Typically only used by yaffs_guts_initialise, but also used by the
+ * Low level yaffs driver tests.
+ */
+
+int yaffs_guts_ll_init(struct yaffs_dev *dev)
+{
+
+
+	yaffs_trace(YAFFS_TRACE_TRACING, "yaffs: yaffs_ll_init()");
+
+	if (!dev) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"yaffs: Need a device"
+			);
+		return YAFFS_FAIL;
+	}
+
+	if (dev->ll_init)
+		return YAFFS_OK;
+
+	dev->internal_start_block = dev->param.start_block;
+	dev->internal_end_block = dev->param.end_block;
+	dev->block_offset = 0;
+	dev->chunk_offset = 0;
+	dev->n_free_chunks = 0;
+
+	dev->gc_block = 0;
+
+	if (dev->param.start_block == 0) {
+		dev->internal_start_block = dev->param.start_block + 1;
+		dev->internal_end_block = dev->param.end_block + 1;
+		dev->block_offset = 1;
+		dev->chunk_offset = dev->param.chunks_per_block;
+	}
+
+	/* Check geometry parameters. */
+
+	if ((!dev->param.inband_tags && dev->param.is_yaffs2 &&
+		dev->param.total_bytes_per_chunk < 1024) ||
+		(!dev->param.is_yaffs2 &&
+			dev->param.total_bytes_per_chunk < 512) ||
+		(dev->param.inband_tags && !dev->param.is_yaffs2) ||
+		 dev->param.chunks_per_block < 2 ||
+		 dev->param.n_reserved_blocks < 2 ||
+		dev->internal_start_block <= 0 ||
+		dev->internal_end_block <= 0 ||
+		dev->internal_end_block <=
+		(dev->internal_start_block + dev->param.n_reserved_blocks + 2)
+		) {
+		/* otherwise it is too small */
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"NAND geometry problems: chunk size %d, type is yaffs%s, inband_tags %d ",
+			dev->param.total_bytes_per_chunk,
+			dev->param.is_yaffs2 ? "2" : "",
+			dev->param.inband_tags);
+		return YAFFS_FAIL;
+	}
+
+	/* Sort out space for inband tags, if required */
+	if (dev->param.inband_tags)
+		dev->data_bytes_per_chunk =
+		    dev->param.total_bytes_per_chunk -
+		    sizeof(struct yaffs_packed_tags2_tags_only);
+	else
+		dev->data_bytes_per_chunk = dev->param.total_bytes_per_chunk;
+
+	/* Got the right mix of functions? */
+	if (!yaffs_check_dev_fns(dev)) {
+		/* Function missing */
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"device function(s) missing or wrong");
+
+		return YAFFS_FAIL;
+	}
+
+	if (yaffs_init_nand(dev) != YAFFS_OK) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS, "InitialiseNAND failed");
+		return YAFFS_FAIL;
+	}
+
+	return YAFFS_OK;
+}
+
+
+int yaffs_format_dev(struct yaffs_dev *dev)
+{
+	int i;
+	enum yaffs_block_state state;
+	u32 dummy;
+
+	if(yaffs_guts_ll_init(dev) != YAFFS_OK)
+		return YAFFS_FAIL;
+
+	if(dev->is_mounted)
+		return YAFFS_FAIL;
+
+	for (i = dev->internal_start_block; i <= dev->internal_end_block; i++) {
+		yaffs_query_init_block_state(dev, i, &state, &dummy);
+		if (state != YAFFS_BLOCK_STATE_DEAD)
+			yaffs_erase_block(dev, i);
+	}
+
+	return YAFFS_OK;
+}
+
+
+int yaffs_guts_initialise(struct yaffs_dev *dev)
+{
+	int init_failed = 0;
+	unsigned x;
+	int bits;
+
+	if(yaffs_guts_ll_init(dev) != YAFFS_OK)
+		return YAFFS_FAIL;
+
+	if (dev->is_mounted) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS, "device already mounted");
+		return YAFFS_FAIL;
+	}
+
+	dev->is_mounted = 1;
+
+	/* OK now calculate a few things for the device */
+
+	/*
+	 *  Calculate all the chunk size manipulation numbers:
+	 */
+	x = dev->data_bytes_per_chunk;
+	/* We always use dev->chunk_shift and dev->chunk_div */
+	dev->chunk_shift = calc_shifts(x);
+	x >>= dev->chunk_shift;
+	dev->chunk_div = x;
+	/* We only use chunk mask if chunk_div is 1 */
+	dev->chunk_mask = (1 << dev->chunk_shift) - 1;
+
+	/*
+	 * Calculate chunk_grp_bits.
+	 * We need to find the next power of 2 > than internal_end_block
+	 */
+
+	x = dev->param.chunks_per_block * (dev->internal_end_block + 1);
+
+	bits = calc_shifts_ceiling(x);
+
+	/* Set up tnode width if wide tnodes are enabled. */
+	if (!dev->param.wide_tnodes_disabled) {
+		/* bits must be even so that we end up with 32-bit words */
+		if (bits & 1)
+			bits++;
+		if (bits < 16)
+			dev->tnode_width = 16;
+		else
+			dev->tnode_width = bits;
+	} else {
+		dev->tnode_width = 16;
+	}
+
+	dev->tnode_mask = (1 << dev->tnode_width) - 1;
+
+	/* Level0 Tnodes are 16 bits or wider (if wide tnodes are enabled),
+	 * so if the bitwidth of the
+	 * chunk range we're using is greater than 16 we need
+	 * to figure out chunk shift and chunk_grp_size
+	 */
+
+	if (bits <= dev->tnode_width)
+		dev->chunk_grp_bits = 0;
+	else
+		dev->chunk_grp_bits = bits - dev->tnode_width;
+
+	dev->tnode_size = (dev->tnode_width * YAFFS_NTNODES_LEVEL0) / 8;
+	if (dev->tnode_size < sizeof(struct yaffs_tnode))
+		dev->tnode_size = sizeof(struct yaffs_tnode);
+
+	dev->chunk_grp_size = 1 << dev->chunk_grp_bits;
+
+	if (dev->param.chunks_per_block < dev->chunk_grp_size) {
+		/* We have a problem because the soft delete won't work if
+		 * the chunk group size > chunks per block.
+		 * This can be remedied by using larger "virtual blocks".
+		 */
+		yaffs_trace(YAFFS_TRACE_ALWAYS, "chunk group too large");
+
+		return YAFFS_FAIL;
+	}
+
+	/* Finished verifying the device, continue with initialisation */
+
+	/* More device initialisation */
+	dev->all_gcs = 0;
+	dev->passive_gc_count = 0;
+	dev->oldest_dirty_gc_count = 0;
+	dev->bg_gcs = 0;
+	dev->gc_block_finder = 0;
+	dev->buffered_block = -1;
+	dev->doing_buffered_block_rewrite = 0;
+	dev->n_deleted_files = 0;
+	dev->n_bg_deletions = 0;
+	dev->n_unlinked_files = 0;
+	dev->n_ecc_fixed = 0;
+	dev->n_ecc_unfixed = 0;
+	dev->n_tags_ecc_fixed = 0;
+	dev->n_tags_ecc_unfixed = 0;
+	dev->n_erase_failures = 0;
+	dev->n_erased_blocks = 0;
+	dev->gc_disable = 0;
+	dev->has_pending_prioritised_gc = 1;
+		/* Assume the worst for now, will get fixed on first GC */
+	INIT_LIST_HEAD(&dev->dirty_dirs);
+	dev->oldest_dirty_seq = 0;
+	dev->oldest_dirty_block = 0;
+
+	/* Initialise temporary buffers and caches. */
+	if (!yaffs_init_tmp_buffers(dev))
+		init_failed = 1;
+
+	dev->cache = NULL;
+	dev->gc_cleanup_list = NULL;
+
+	if (!init_failed && dev->param.n_caches > 0) {
+		int i;
+		void *buf;
+		int cache_bytes =
+		    dev->param.n_caches * sizeof(struct yaffs_cache);
+
+		if (dev->param.n_caches > YAFFS_MAX_SHORT_OP_CACHES)
+			dev->param.n_caches = YAFFS_MAX_SHORT_OP_CACHES;
+
+		dev->cache = kmalloc(cache_bytes, GFP_NOFS);
+
+		buf = (u8 *) dev->cache;
+
+		if (dev->cache)
+			memset(dev->cache, 0, cache_bytes);
+
+		for (i = 0; i < dev->param.n_caches && buf; i++) {
+			dev->cache[i].object = NULL;
+			dev->cache[i].last_use = 0;
+			dev->cache[i].dirty = 0;
+			dev->cache[i].data = buf =
+			    kmalloc(dev->param.total_bytes_per_chunk, GFP_NOFS);
+		}
+		if (!buf)
+			init_failed = 1;
+
+		dev->cache_last_use = 0;
+	}
+
+	dev->cache_hits = 0;
+
+	if (!init_failed) {
+		dev->gc_cleanup_list =
+		    kmalloc(dev->param.chunks_per_block * sizeof(u32),
+					GFP_NOFS);
+		if (!dev->gc_cleanup_list)
+			init_failed = 1;
+	}
+
+	if (dev->param.is_yaffs2)
+		dev->param.use_header_file_size = 1;
+
+	if (!init_failed && !yaffs_init_blocks(dev))
+		init_failed = 1;
+
+	yaffs_init_tnodes_and_objs(dev);
+
+	if (!init_failed && !yaffs_create_initial_dir(dev))
+		init_failed = 1;
+
+	if (!init_failed && dev->param.is_yaffs2 &&
+		!dev->param.disable_summary &&
+		!yaffs_summary_init(dev))
+		init_failed = 1;
+
+	if (!init_failed) {
+		/* Now scan the flash. */
+		if (dev->param.is_yaffs2) {
+			if (yaffs2_checkpt_restore(dev)) {
+				yaffs_check_obj_details_loaded(dev->root_dir);
+				yaffs_trace(YAFFS_TRACE_CHECKPOINT |
+					YAFFS_TRACE_MOUNT,
+					"yaffs: restored from checkpoint"
+					);
+			} else {
+
+				/* Clean up the mess caused by an aborted
+				 * checkpoint load then scan backwards.
+				 */
+				yaffs_deinit_blocks(dev);
+
+				yaffs_deinit_tnodes_and_objs(dev);
+
+				dev->n_erased_blocks = 0;
+				dev->n_free_chunks = 0;
+				dev->alloc_block = -1;
+				dev->alloc_page = -1;
+				dev->n_deleted_files = 0;
+				dev->n_unlinked_files = 0;
+				dev->n_bg_deletions = 0;
+
+				if (!init_failed && !yaffs_init_blocks(dev))
+					init_failed = 1;
+
+				yaffs_init_tnodes_and_objs(dev);
+
+				if (!init_failed
+				    && !yaffs_create_initial_dir(dev))
+					init_failed = 1;
+
+				if (!init_failed && !yaffs2_scan_backwards(dev))
+					init_failed = 1;
+			}
+		} else if (!yaffs1_scan(dev)) {
+			init_failed = 1;
+		}
+
+		yaffs_strip_deleted_objs(dev);
+		yaffs_fix_hanging_objs(dev);
+		if (dev->param.empty_lost_n_found)
+			yaffs_empty_l_n_f(dev);
+	}
+
+	if (init_failed) {
+		/* Clean up the mess */
+		yaffs_trace(YAFFS_TRACE_TRACING,
+		  "yaffs: yaffs_guts_initialise() aborted.");
+
+		yaffs_deinitialise(dev);
+		return YAFFS_FAIL;
+	}
+
+	/* Zero out stats */
+	dev->n_page_reads = 0;
+	dev->n_page_writes = 0;
+	dev->n_erasures = 0;
+	dev->n_gc_copies = 0;
+	dev->n_retried_writes = 0;
+
+	dev->n_retired_blocks = 0;
+
+	yaffs_verify_free_chunks(dev);
+	yaffs_verify_blocks(dev);
+
+	/* Clean up any aborted checkpoint data */
+	if (!dev->is_checkpointed && dev->blocks_in_checkpt > 0)
+		yaffs2_checkpt_invalidate(dev);
+
+	yaffs_trace(YAFFS_TRACE_TRACING,
+	  "yaffs: yaffs_guts_initialise() done.");
+	return YAFFS_OK;
+}
+
+void yaffs_deinitialise(struct yaffs_dev *dev)
+{
+	if (dev->is_mounted) {
+		int i;
+
+		yaffs_deinit_blocks(dev);
+		yaffs_deinit_tnodes_and_objs(dev);
+		yaffs_summary_deinit(dev);
+
+		if (dev->param.n_caches > 0 && dev->cache) {
+
+			for (i = 0; i < dev->param.n_caches; i++) {
+				kfree(dev->cache[i].data);
+				dev->cache[i].data = NULL;
+			}
+
+			kfree(dev->cache);
+			dev->cache = NULL;
+		}
+
+		kfree(dev->gc_cleanup_list);
+
+		for (i = 0; i < YAFFS_N_TEMP_BUFFERS; i++)
+			kfree(dev->temp_buffer[i].buffer);
+
+		dev->is_mounted = 0;
+
+		yaffs_deinit_nand(dev);
+	}
+}
+
+int yaffs_count_free_chunks(struct yaffs_dev *dev)
+{
+	int n_free = 0;
+	int b;
+	struct yaffs_block_info *blk;
+
+	blk = dev->block_info;
+	for (b = dev->internal_start_block; b <= dev->internal_end_block; b++) {
+		switch (blk->block_state) {
+		case YAFFS_BLOCK_STATE_EMPTY:
+		case YAFFS_BLOCK_STATE_ALLOCATING:
+		case YAFFS_BLOCK_STATE_COLLECTING:
+		case YAFFS_BLOCK_STATE_FULL:
+			n_free +=
+			    (dev->param.chunks_per_block - blk->pages_in_use +
+			     blk->soft_del_pages);
+			break;
+		default:
+			break;
+		}
+		blk++;
+	}
+	return n_free;
+}
+
+int yaffs_get_n_free_chunks(struct yaffs_dev *dev)
+{
+	/* This is what we report to the outside world */
+	int n_free;
+	int n_dirty_caches;
+	int blocks_for_checkpt;
+	int i;
+
+	n_free = dev->n_free_chunks;
+	n_free += dev->n_deleted_files;
+
+	/* Now count and subtract the number of dirty chunks in the cache. */
+
+	for (n_dirty_caches = 0, i = 0; i < dev->param.n_caches; i++) {
+		if (dev->cache[i].dirty)
+			n_dirty_caches++;
+	}
+
+	n_free -= n_dirty_caches;
+
+	n_free -=
+	    ((dev->param.n_reserved_blocks + 1) * dev->param.chunks_per_block);
+
+	/* Now figure checkpoint space and report that... */
+	blocks_for_checkpt = yaffs_calc_checkpt_blocks_required(dev);
+
+	n_free -= (blocks_for_checkpt * dev->param.chunks_per_block);
+
+	if (n_free < 0)
+		n_free = 0;
+
+	return n_free;
+}
+
+
+
+/*
+ * Marshalling functions to get loff_t file sizes into and out of
+ * object headers.
+ */
+void yaffs_oh_size_load(struct yaffs_obj_hdr *oh, loff_t fsize)
+{
+	oh->file_size_low = (fsize & 0xFFFFFFFF);
+	oh->file_size_high = ((fsize >> 32) & 0xFFFFFFFF);
+}
+
+loff_t yaffs_oh_to_size(struct yaffs_obj_hdr *oh)
+{
+	loff_t retval;
+
+	if (sizeof(loff_t) >= 8 && ~(oh->file_size_high))
+		retval = (((loff_t) oh->file_size_high) << 32) |
+			(((loff_t) oh->file_size_low) & 0xFFFFFFFF);
+	else
+		retval = (loff_t) oh->file_size_low;
+
+	return retval;
+}
+
+
+void yaffs_count_blocks_by_state(struct yaffs_dev *dev, int bs[10])
+{
+	int i;
+	struct yaffs_block_info *bi;
+	int s;
+
+	for(i = 0; i < 10; i++)
+		bs[i] = 0;
+
+	for(i = dev->internal_start_block; i <= dev->internal_end_block; i++) {
+		bi = yaffs_get_block_info(dev, i);
+		s = bi->block_state;
+		if(s > YAFFS_BLOCK_STATE_DEAD || s < YAFFS_BLOCK_STATE_UNKNOWN)
+			bs[0]++;
+		else
+			bs[s]++;
+	}
+}
diff --git a/fs/yaffs2/yaffs_guts.h b/fs/yaffs2/yaffs_guts.h
new file mode 100644
index 000000000000..05785367cb2e
--- /dev/null
+++ b/fs/yaffs2/yaffs_guts.h
@@ -0,0 +1,1003 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_GUTS_H__
+#define __YAFFS_GUTS_H__
+
+#include "yportenv.h"
+
+#define YAFFS_OK	1
+#define YAFFS_FAIL  0
+
+/* Give us a  Y=0x59,
+ * Give us an A=0x41,
+ * Give us an FF=0xff
+ * Give us an S=0x53
+ * And what have we got...
+ */
+#define YAFFS_MAGIC			0x5941ff53
+
+/*
+ * Tnodes form a tree with the tnodes in "levels"
+ * Levels greater than 0 hold 8 slots which point to other tnodes.
+ * Those at level 0 hold 16 slots which point to chunks in NAND.
+ *
+ * A maximum level of 8 thust supports files of size up to:
+ *
+ * 2^(3*MAX_LEVEL+4)
+ *
+ * Thus a max level of 8 supports files with up to 2^^28 chunks which gives
+ * a maximum file size of around 512Gbytees with 2k chunks.
+ */
+#define YAFFS_NTNODES_LEVEL0		16
+#define YAFFS_TNODES_LEVEL0_BITS	4
+#define YAFFS_TNODES_LEVEL0_MASK	0xf
+
+#define YAFFS_NTNODES_INTERNAL		(YAFFS_NTNODES_LEVEL0 / 2)
+#define YAFFS_TNODES_INTERNAL_BITS	(YAFFS_TNODES_LEVEL0_BITS - 1)
+#define YAFFS_TNODES_INTERNAL_MASK	0x7
+#define YAFFS_TNODES_MAX_LEVEL		8
+#define YAFFS_TNODES_MAX_BITS		(YAFFS_TNODES_LEVEL0_BITS + \
+					YAFFS_TNODES_INTERNAL_BITS * \
+					YAFFS_TNODES_MAX_LEVEL)
+#define YAFFS_MAX_CHUNK_ID		((1 << YAFFS_TNODES_MAX_BITS) - 1)
+
+#define YAFFS_MAX_FILE_SIZE_32		0x7fffffff
+
+/* Constants for YAFFS1 mode */
+#define YAFFS_BYTES_PER_SPARE		16
+#define YAFFS_BYTES_PER_CHUNK		512
+#define YAFFS_CHUNK_SIZE_SHIFT		9
+#define YAFFS_CHUNKS_PER_BLOCK		32
+#define YAFFS_BYTES_PER_BLOCK	(YAFFS_CHUNKS_PER_BLOCK*YAFFS_BYTES_PER_CHUNK)
+
+#define YAFFS_MIN_YAFFS2_CHUNK_SIZE	1024
+#define YAFFS_MIN_YAFFS2_SPARE_SIZE	32
+
+
+
+#define YAFFS_ALLOCATION_NOBJECTS	100
+#define YAFFS_ALLOCATION_NTNODES	100
+#define YAFFS_ALLOCATION_NLINKS		100
+
+#define YAFFS_NOBJECT_BUCKETS		256
+
+#define YAFFS_OBJECT_SPACE		0x40000
+#define YAFFS_MAX_OBJECT_ID		(YAFFS_OBJECT_SPACE - 1)
+
+/* Binary data version stamps */
+#define YAFFS_SUMMARY_VERSION		1
+#define YAFFS_CHECKPOINT_VERSION	7
+
+#ifdef CONFIG_YAFFS_UNICODE
+#define YAFFS_MAX_NAME_LENGTH		127
+#define YAFFS_MAX_ALIAS_LENGTH		79
+#else
+#define YAFFS_MAX_NAME_LENGTH		255
+#define YAFFS_MAX_ALIAS_LENGTH		159
+#endif
+
+#define YAFFS_SHORT_NAME_LENGTH		15
+
+/* Some special object ids for pseudo objects */
+#define YAFFS_OBJECTID_ROOT		1
+#define YAFFS_OBJECTID_LOSTNFOUND	2
+#define YAFFS_OBJECTID_UNLINKED		3
+#define YAFFS_OBJECTID_DELETED		4
+
+/* Fake object Id for summary data */
+#define YAFFS_OBJECTID_SUMMARY		0x10
+
+/* Pseudo object ids for checkpointing */
+#define YAFFS_OBJECTID_CHECKPOINT_DATA	0x20
+#define YAFFS_SEQUENCE_CHECKPOINT_DATA	0x21
+
+#define YAFFS_MAX_SHORT_OP_CACHES	20
+
+#define YAFFS_N_TEMP_BUFFERS		6
+
+/* We limit the number attempts at sucessfully saving a chunk of data.
+ * Small-page devices have 32 pages per block; large-page devices have 64.
+ * Default to something in the order of 5 to 10 blocks worth of chunks.
+ */
+#define YAFFS_WR_ATTEMPTS		(5*64)
+
+/* Sequence numbers are used in YAFFS2 to determine block allocation order.
+ * The range is limited slightly to help distinguish bad numbers from good.
+ * This also allows us to perhaps in the future use special numbers for
+ * special purposes.
+ * EFFFFF00 allows the allocation of 8 blocks/second (~1Mbytes) for 15 years,
+ * and is a larger number than the lifetime of a 2GB device.
+ */
+#define YAFFS_LOWEST_SEQUENCE_NUMBER	0x00001000
+#define YAFFS_HIGHEST_SEQUENCE_NUMBER	0xefffff00
+
+/* Special sequence number for bad block that failed to be marked bad */
+#define YAFFS_SEQUENCE_BAD_BLOCK	0xffff0000
+
+/* ChunkCache is used for short read/write operations.*/
+struct yaffs_cache {
+	struct yaffs_obj *object;
+	int chunk_id;
+	int last_use;
+	int dirty;
+	int n_bytes;		/* Only valid if the cache is dirty */
+	int locked;		/* Can't push out or flush while locked. */
+	u8 *data;
+};
+
+/* yaffs1 tags structures in RAM
+ * NB This uses bitfield. Bitfields should not straddle a u32 boundary
+ * otherwise the structure size will get blown out.
+ */
+
+struct yaffs_tags {
+	unsigned chunk_id:20;
+	unsigned serial_number:2;
+	unsigned n_bytes_lsb:10;
+	unsigned obj_id:18;
+	unsigned ecc:12;
+	unsigned n_bytes_msb:2;
+};
+
+union yaffs_tags_union {
+	struct yaffs_tags as_tags;
+	u8 as_bytes[8];
+};
+
+
+/* Stuff used for extended tags in YAFFS2 */
+
+enum yaffs_ecc_result {
+	YAFFS_ECC_RESULT_UNKNOWN,
+	YAFFS_ECC_RESULT_NO_ERROR,
+	YAFFS_ECC_RESULT_FIXED,
+	YAFFS_ECC_RESULT_UNFIXED
+};
+
+enum yaffs_obj_type {
+	YAFFS_OBJECT_TYPE_UNKNOWN,
+	YAFFS_OBJECT_TYPE_FILE,
+	YAFFS_OBJECT_TYPE_SYMLINK,
+	YAFFS_OBJECT_TYPE_DIRECTORY,
+	YAFFS_OBJECT_TYPE_HARDLINK,
+	YAFFS_OBJECT_TYPE_SPECIAL
+};
+
+#define YAFFS_OBJECT_TYPE_MAX YAFFS_OBJECT_TYPE_SPECIAL
+
+struct yaffs_ext_tags {
+	unsigned chunk_used;	/*  Status of the chunk: used or unused */
+	unsigned obj_id;	/* If 0 this is not used */
+	unsigned chunk_id;	/* If 0 this is a header, else a data chunk */
+	unsigned n_bytes;	/* Only valid for data chunks */
+
+	/* The following stuff only has meaning when we read */
+	enum yaffs_ecc_result ecc_result;
+	unsigned block_bad;
+
+	/* YAFFS 1 stuff */
+	unsigned is_deleted;	/* The chunk is marked deleted */
+	unsigned serial_number;	/* Yaffs1 2-bit serial number */
+
+	/* YAFFS2 stuff */
+	unsigned seq_number;	/* The sequence number of this block */
+
+	/* Extra info if this is an object header (YAFFS2 only) */
+
+	unsigned extra_available;	/* Extra info available if not zero */
+	unsigned extra_parent_id;	/* The parent object */
+	unsigned extra_is_shrink;	/* Is it a shrink header? */
+	unsigned extra_shadows;	/* Does this shadow another object? */
+
+	enum yaffs_obj_type extra_obj_type;	/* What object type? */
+
+	loff_t extra_file_size;		/* Length if it is a file */
+	unsigned extra_equiv_id;	/* Equivalent object for a hard link */
+};
+
+/* Spare structure for YAFFS1 */
+struct yaffs_spare {
+	u8 tb0;
+	u8 tb1;
+	u8 tb2;
+	u8 tb3;
+	u8 page_status;		/* set to 0 to delete the chunk */
+	u8 block_status;
+	u8 tb4;
+	u8 tb5;
+	u8 ecc1[3];
+	u8 tb6;
+	u8 tb7;
+	u8 ecc2[3];
+};
+
+/*Special structure for passing through to mtd */
+struct yaffs_nand_spare {
+	struct yaffs_spare spare;
+	int eccres1;
+	int eccres2;
+};
+
+/* Block data in RAM */
+
+enum yaffs_block_state {
+	YAFFS_BLOCK_STATE_UNKNOWN = 0,
+
+	YAFFS_BLOCK_STATE_SCANNING,
+	/* Being scanned */
+
+	YAFFS_BLOCK_STATE_NEEDS_SCAN,
+	/* The block might have something on it (ie it is allocating or full,
+	 * perhaps empty) but it needs to be scanned to determine its true
+	 * state.
+	 * This state is only valid during scanning.
+	 * NB We tolerate empty because the pre-scanner might be incapable of
+	 * deciding
+	 * However, if this state is returned on a YAFFS2 device,
+	 * then we expect a sequence number
+	 */
+
+	YAFFS_BLOCK_STATE_EMPTY,
+	/* This block is empty */
+
+	YAFFS_BLOCK_STATE_ALLOCATING,
+	/* This block is partially allocated.
+	 * At least one page holds valid data.
+	 * This is the one currently being used for page
+	 * allocation. Should never be more than one of these.
+	 * If a block is only partially allocated at mount it is treated as
+	 * full.
+	 */
+
+	YAFFS_BLOCK_STATE_FULL,
+	/* All the pages in this block have been allocated.
+	 * If a block was only partially allocated when mounted we treat
+	 * it as fully allocated.
+	 */
+
+	YAFFS_BLOCK_STATE_DIRTY,
+	/* The block was full and now all chunks have been deleted.
+	 * Erase me, reuse me.
+	 */
+
+	YAFFS_BLOCK_STATE_CHECKPOINT,
+	/* This block is assigned to holding checkpoint data. */
+
+	YAFFS_BLOCK_STATE_COLLECTING,
+	/* This block is being garbage collected */
+
+	YAFFS_BLOCK_STATE_DEAD
+	    /* This block has failed and is not in use */
+};
+
+#define	YAFFS_NUMBER_OF_BLOCK_STATES (YAFFS_BLOCK_STATE_DEAD + 1)
+
+struct yaffs_block_info {
+
+	int soft_del_pages:10;	/* number of soft deleted pages */
+	int pages_in_use:10;	/* number of pages in use */
+	unsigned block_state:4;	/* One of the above block states. */
+				/* NB use unsigned because enum is sometimes
+				 * an int */
+	u32 needs_retiring:1;	/* Data has failed on this block, */
+				/*need to get valid data off and retire*/
+	u32 skip_erased_check:1;/* Skip the erased check on this block */
+	u32 gc_prioritise:1;	/* An ECC check or blank check has failed.
+				   Block should be prioritised for GC */
+	u32 chunk_error_strikes:3;	/* How many times we've had ecc etc
+				failures on this block and tried to reuse it */
+	u32 has_summary:1;	/* The block has a summary */
+
+	u32 has_shrink_hdr:1;	/* This block has at least one shrink header */
+	u32 seq_number;		/* block sequence number for yaffs2 */
+
+};
+
+/* -------------------------- Object structure -------------------------------*/
+/* This is the object structure as stored on NAND */
+
+struct yaffs_obj_hdr {
+	enum yaffs_obj_type type;
+
+	/* Apply to everything  */
+	int parent_obj_id;
+	u16 sum_no_longer_used;	/* checksum of name. No longer used */
+	YCHAR name[YAFFS_MAX_NAME_LENGTH + 1];
+
+	/* The following apply to all object types except for hard links */
+	u32 yst_mode;		/* protection */
+
+	u32 yst_uid;
+	u32 yst_gid;
+	u32 yst_atime;
+	u32 yst_mtime;
+	u32 yst_ctime;
+
+	/* File size  applies to files only */
+	u32 file_size_low;
+
+	/* Equivalent object id applies to hard links only. */
+	int equiv_id;
+
+	/* Alias is for symlinks only. */
+	YCHAR alias[YAFFS_MAX_ALIAS_LENGTH + 1];
+
+	u32 yst_rdev;	/* stuff for block and char devices (major/min) */
+
+	u32 win_ctime[2];
+	u32 win_atime[2];
+	u32 win_mtime[2];
+
+	u32 inband_shadowed_obj_id;
+	u32 inband_is_shrink;
+
+	u32 file_size_high;
+	u32 reserved[1];
+	int shadows_obj;	/* This object header shadows the
+				specified object if > 0 */
+
+	/* is_shrink applies to object headers written when wemake a hole. */
+	u32 is_shrink;
+
+};
+
+/*--------------------------- Tnode -------------------------- */
+
+struct yaffs_tnode {
+	struct yaffs_tnode *internal[YAFFS_NTNODES_INTERNAL];
+};
+
+/*------------------------  Object -----------------------------*/
+/* An object can be one of:
+ * - a directory (no data, has children links
+ * - a regular file (data.... not prunes :->).
+ * - a symlink [symbolic link] (the alias).
+ * - a hard link
+ */
+
+struct yaffs_file_var {
+	loff_t file_size;
+	loff_t scanned_size;
+	loff_t shrink_size;
+	int top_level;
+	struct yaffs_tnode *top;
+};
+
+struct yaffs_dir_var {
+	struct list_head children;	/* list of child links */
+	struct list_head dirty;	/* Entry for list of dirty directories */
+};
+
+struct yaffs_symlink_var {
+	YCHAR *alias;
+};
+
+struct yaffs_hardlink_var {
+	struct yaffs_obj *equiv_obj;
+	u32 equiv_id;
+};
+
+union yaffs_obj_var {
+	struct yaffs_file_var file_variant;
+	struct yaffs_dir_var dir_variant;
+	struct yaffs_symlink_var symlink_variant;
+	struct yaffs_hardlink_var hardlink_variant;
+};
+
+struct yaffs_obj {
+	u8 deleted:1;		/* This should only apply to unlinked files. */
+	u8 soft_del:1;		/* it has also been soft deleted */
+	u8 unlinked:1;		/* An unlinked file.*/
+	u8 fake:1;		/* A fake object has no presence on NAND. */
+	u8 rename_allowed:1;	/* Some objects cannot be renamed. */
+	u8 unlink_allowed:1;
+	u8 dirty:1;		/* the object needs to be written to flash */
+	u8 valid:1;		/* When the file system is being loaded up, this
+				 * object might be created before the data
+				 * is available
+				 * ie. file data chunks encountered before
+				* the header.
+				 */
+	u8 lazy_loaded:1;	/* This object has been lazy loaded and
+				 * is missing some detail */
+
+	u8 defered_free:1;	/* Object is removed from NAND, but is
+				 * still in the inode cache.
+				 * Free of object is defered.
+				 * until the inode is released.
+				 */
+	u8 being_created:1;	/* This object is still being created
+				 * so skip some verification checks. */
+	u8 is_shadowed:1;	/* This object is shadowed on the way
+				 * to being renamed. */
+
+	u8 xattr_known:1;	/* We know if this has object has xattribs
+				 * or not. */
+	u8 has_xattr:1;		/* This object has xattribs.
+				 * Only valid if xattr_known. */
+
+	u8 serial;		/* serial number of chunk in NAND.*/
+	u16 sum;		/* sum of the name to speed searching */
+
+	struct yaffs_dev *my_dev;	/* The device I'm on */
+
+	struct list_head hash_link;	/* list of objects in hash bucket */
+
+	struct list_head hard_links;	/* hard linked object chain*/
+
+	/* directory structure stuff */
+	/* also used for linking up the free list */
+	struct yaffs_obj *parent;
+	struct list_head siblings;
+
+	/* Where's my object header in NAND? */
+	int hdr_chunk;
+
+	int n_data_chunks;	/* Number of data chunks for this file. */
+
+	u32 obj_id;		/* the object id value */
+
+	u32 yst_mode;
+
+	YCHAR short_name[YAFFS_SHORT_NAME_LENGTH + 1];
+
+#ifdef CONFIG_YAFFS_WINCE
+	u32 win_ctime[2];
+	u32 win_mtime[2];
+	u32 win_atime[2];
+#else
+	u32 yst_uid;
+	u32 yst_gid;
+	u32 yst_atime;
+	u32 yst_mtime;
+	u32 yst_ctime;
+#endif
+
+	u32 yst_rdev;
+
+	void *my_inode;
+
+	enum yaffs_obj_type variant_type;
+
+	union yaffs_obj_var variant;
+
+};
+
+struct yaffs_obj_bucket {
+	struct list_head list;
+	int count;
+};
+
+/* yaffs_checkpt_obj holds the definition of an object as dumped
+ * by checkpointing.
+ */
+
+struct yaffs_checkpt_obj {
+	int struct_type;
+	u32 obj_id;
+	u32 parent_id;
+	int hdr_chunk;
+	enum yaffs_obj_type variant_type:3;
+	u8 deleted:1;
+	u8 soft_del:1;
+	u8 unlinked:1;
+	u8 fake:1;
+	u8 rename_allowed:1;
+	u8 unlink_allowed:1;
+	u8 serial;
+	int n_data_chunks;
+	loff_t size_or_equiv_obj;
+};
+
+/*--------------------- Temporary buffers ----------------
+ *
+ * These are chunk-sized working buffers. Each device has a few.
+ */
+
+struct yaffs_buffer {
+	u8 *buffer;
+	int in_use;
+};
+
+/*----------------- Device ---------------------------------*/
+
+struct yaffs_param {
+	const YCHAR *name;
+
+	/*
+	 * Entry parameters set up way early. Yaffs sets up the rest.
+	 * The structure should be zeroed out before use so that unused
+	 * and default values are zero.
+	 */
+
+	int inband_tags;	/* Use unband tags */
+	u32 total_bytes_per_chunk;	/* Should be >= 512, does not need to
+					 be a power of 2 */
+	int chunks_per_block;	/* does not need to be a power of 2 */
+	int spare_bytes_per_chunk;	/* spare area size */
+	int start_block;	/* Start block we're allowed to use */
+	int end_block;		/* End block we're allowed to use */
+	int n_reserved_blocks;	/* Tuneable so that we can reduce
+				 * reserved blocks on NOR and RAM. */
+
+	int n_caches;		/* If <= 0, then short op caching is disabled,
+				 * else the number of short op caches.
+				 */
+	int cache_bypass_aligned; /* If non-zero then bypass the cache for
+				   * aligned writes.
+				   */
+
+	int use_nand_ecc;	/* Flag to decide whether or not to use
+				 * NAND driver ECC on data (yaffs1) */
+	int tags_9bytes;	/* Use 9 byte tags */
+	int no_tags_ecc;	/* Flag to decide whether or not to do ECC
+				 * on packed tags (yaffs2) */
+
+	int is_yaffs2;		/* Use yaffs2 mode on this device */
+
+	int empty_lost_n_found;	/* Auto-empty lost+found directory on mount */
+
+	int refresh_period;	/* How often to check for a block refresh */
+
+	/* Checkpoint control. Can be set before or after initialisation */
+	u8 skip_checkpt_rd;
+	u8 skip_checkpt_wr;
+
+	int enable_xattr;	/* Enable xattribs */
+
+	int max_objects;	/*
+				 * Set to limit the number of objects created.
+				 * 0 = no limit.
+				*/
+
+	/* The remove_obj_fn function must be supplied by OS flavours that
+	 * need it.
+	 * yaffs direct uses it to implement the faster readdir.
+	 * Linux uses it to protect the directory during unlocking.
+	 */
+	void (*remove_obj_fn) (struct yaffs_obj *obj);
+
+	/* Callback to mark the superblock dirty */
+	void (*sb_dirty_fn) (struct yaffs_dev *dev);
+
+	/*  Callback to control garbage collection. */
+	unsigned (*gc_control_fn) (struct yaffs_dev *dev);
+
+	/* Debug control flags. Don't use unless you know what you're doing */
+	int use_header_file_size;	/* Flag to determine if we should use
+					 * file sizes from the header */
+	int disable_lazy_load;	/* Disable lazy loading on this device */
+	int wide_tnodes_disabled;	/* Set to disable wide tnodes */
+	int disable_soft_del;	/* yaffs 1 only: Set to disable the use of
+				 * softdeletion. */
+
+	int defered_dir_update;	/* Set to defer directory updates */
+
+#ifdef CONFIG_YAFFS_AUTO_UNICODE
+	int auto_unicode;
+#endif
+	int always_check_erased;	/* Force chunk erased check always on */
+
+	int disable_summary;
+	int disable_bad_block_marking;
+
+};
+
+struct yaffs_driver {
+	int (*drv_write_chunk_fn) (struct yaffs_dev *dev, int nand_chunk,
+				   const u8 *data, int data_len,
+				   const u8 *oob, int oob_len);
+	int (*drv_read_chunk_fn) (struct yaffs_dev *dev, int nand_chunk,
+				   u8 *data, int data_len,
+				   u8 *oob, int oob_len,
+				   enum yaffs_ecc_result *ecc_result);
+	int (*drv_erase_fn) (struct yaffs_dev *dev, int block_no);
+	int (*drv_mark_bad_fn) (struct yaffs_dev *dev, int block_no);
+	int (*drv_check_bad_fn) (struct yaffs_dev *dev, int block_no);
+	int (*drv_initialise_fn) (struct yaffs_dev *dev);
+	int (*drv_deinitialise_fn) (struct yaffs_dev *dev);
+};
+
+struct yaffs_tags_handler {
+	int (*write_chunk_tags_fn) (struct yaffs_dev *dev,
+				    int nand_chunk, const u8 *data,
+				    const struct yaffs_ext_tags *tags);
+	int (*read_chunk_tags_fn) (struct yaffs_dev *dev,
+				   int nand_chunk, u8 *data,
+				   struct yaffs_ext_tags *tags);
+
+	int (*query_block_fn) (struct yaffs_dev *dev, int block_no,
+			       enum yaffs_block_state *state,
+			       u32 *seq_number);
+	int (*mark_bad_fn) (struct yaffs_dev *dev, int block_no);
+};
+
+struct yaffs_dev {
+	struct yaffs_param param;
+	struct yaffs_driver drv;
+	struct yaffs_tags_handler tagger;
+
+	/* Context storage. Holds extra OS specific data for this device */
+
+	void *os_context;
+	void *driver_context;
+
+	struct list_head dev_list;
+
+	int ll_init;
+	/* Runtime parameters. Set up by YAFFS. */
+	int data_bytes_per_chunk;
+
+	/* Non-wide tnode stuff */
+	u16 chunk_grp_bits;	/* Number of bits that need to be resolved if
+				 * the tnodes are not wide enough.
+				 */
+	u16 chunk_grp_size;	/* == 2^^chunk_grp_bits */
+
+	/* Stuff to support wide tnodes */
+	u32 tnode_width;
+	u32 tnode_mask;
+	u32 tnode_size;
+
+	/* Stuff for figuring out file offset to chunk conversions */
+	u32 chunk_shift;	/* Shift value */
+	u32 chunk_div;		/* Divisor after shifting: 1 for 2^n sizes */
+	u32 chunk_mask;		/* Mask to use for power-of-2 case */
+
+	int is_mounted;
+	int read_only;
+	int is_checkpointed;
+
+	/* Stuff to support block offsetting to support start block zero */
+	int internal_start_block;
+	int internal_end_block;
+	int block_offset;
+	int chunk_offset;
+
+	/* Runtime checkpointing stuff */
+	int checkpt_page_seq;	/* running sequence number of checkpt pages */
+	int checkpt_byte_count;
+	int checkpt_byte_offs;
+	u8 *checkpt_buffer;
+	int checkpt_open_write;
+	int blocks_in_checkpt;
+	int checkpt_cur_chunk;
+	int checkpt_cur_block;
+	int checkpt_next_block;
+	int *checkpt_block_list;
+	int checkpt_max_blocks;
+	u32 checkpt_sum;
+	u32 checkpt_xor;
+
+	int checkpoint_blocks_required;	/* Number of blocks needed to store
+					 * current checkpoint set */
+
+	/* Block Info */
+	struct yaffs_block_info *block_info;
+	u8 *chunk_bits;		/* bitmap of chunks in use */
+	unsigned block_info_alt:1;	/* allocated using alternative alloc */
+	unsigned chunk_bits_alt:1;	/* allocated using alternative alloc */
+	int chunk_bit_stride;	/* Number of bytes of chunk_bits per block.
+				 * Must be consistent with chunks_per_block.
+				 */
+
+	int n_erased_blocks;
+	int alloc_block;	/* Current block being allocated off */
+	u32 alloc_page;
+	int alloc_block_finder;	/* Used to search for next allocation block */
+
+	/* Object and Tnode memory management */
+	void *allocator;
+	int n_obj;
+	int n_tnodes;
+
+	int n_hardlinks;
+
+	struct yaffs_obj_bucket obj_bucket[YAFFS_NOBJECT_BUCKETS];
+	u32 bucket_finder;
+
+	int n_free_chunks;
+
+	/* Garbage collection control */
+	u32 *gc_cleanup_list;	/* objects to delete at the end of a GC. */
+	u32 n_clean_ups;
+
+	unsigned has_pending_prioritised_gc;	/* We think this device might
+						have pending prioritised gcs */
+	unsigned gc_disable;
+	unsigned gc_block_finder;
+	unsigned gc_dirtiest;
+	unsigned gc_pages_in_use;
+	unsigned gc_not_done;
+	unsigned gc_block;
+	unsigned gc_chunk;
+	unsigned gc_skip;
+	struct yaffs_summary_tags *gc_sum_tags;
+
+	/* Special directories */
+	struct yaffs_obj *root_dir;
+	struct yaffs_obj *lost_n_found;
+
+	int buffered_block;	/* Which block is buffered here? */
+	int doing_buffered_block_rewrite;
+
+	struct yaffs_cache *cache;
+	int cache_last_use;
+
+	/* Stuff for background deletion and unlinked files. */
+	struct yaffs_obj *unlinked_dir;	/* Directory where unlinked and deleted
+					 files live. */
+	struct yaffs_obj *del_dir;	/* Directory where deleted objects are
+					sent to disappear. */
+	struct yaffs_obj *unlinked_deletion;	/* Current file being
+							background deleted. */
+	int n_deleted_files;	/* Count of files awaiting deletion; */
+	int n_unlinked_files;	/* Count of unlinked files. */
+	int n_bg_deletions;	/* Count of background deletions. */
+
+	/* Temporary buffer management */
+	struct yaffs_buffer temp_buffer[YAFFS_N_TEMP_BUFFERS];
+	int max_temp;
+	int temp_in_use;
+	int unmanaged_buffer_allocs;
+	int unmanaged_buffer_deallocs;
+
+	/* yaffs2 runtime stuff */
+	unsigned seq_number;	/* Sequence number of currently
+					allocating block */
+	unsigned oldest_dirty_seq;
+	unsigned oldest_dirty_block;
+
+	/* Block refreshing */
+	int refresh_skip;	/* A skip down counter.
+				 * Refresh happens when this gets to zero. */
+
+	/* Dirty directory handling */
+	struct list_head dirty_dirs;	/* List of dirty directories */
+
+	/* Summary */
+	int chunks_per_summary;
+	struct yaffs_summary_tags *sum_tags;
+
+	/* Statistics */
+	u32 n_page_writes;
+	u32 n_page_reads;
+	u32 n_erasures;
+	u32 n_bad_markings;
+	u32 n_erase_failures;
+	u32 n_gc_copies;
+	u32 all_gcs;
+	u32 passive_gc_count;
+	u32 oldest_dirty_gc_count;
+	u32 n_gc_blocks;
+	u32 bg_gcs;
+	u32 n_retried_writes;
+	u32 n_retired_blocks;
+	u32 n_ecc_fixed;
+	u32 n_ecc_unfixed;
+	u32 n_tags_ecc_fixed;
+	u32 n_tags_ecc_unfixed;
+	u32 n_deletions;
+	u32 n_unmarked_deletions;
+	u32 refresh_count;
+	u32 cache_hits;
+	u32 tags_used;
+	u32 summary_used;
+
+};
+
+/* The CheckpointDevice structure holds the device information that changes
+ *at runtime and must be preserved over unmount/mount cycles.
+ */
+struct yaffs_checkpt_dev {
+	int struct_type;
+	int n_erased_blocks;
+	int alloc_block;	/* Current block being allocated off */
+	u32 alloc_page;
+	int n_free_chunks;
+
+	int n_deleted_files;	/* Count of files awaiting deletion; */
+	int n_unlinked_files;	/* Count of unlinked files. */
+	int n_bg_deletions;	/* Count of background deletions. */
+
+	/* yaffs2 runtime stuff */
+	unsigned seq_number;	/* Sequence number of currently
+				 * allocating block */
+
+};
+
+struct yaffs_checkpt_validity {
+	int struct_type;
+	u32 magic;
+	u32 version;
+	u32 head;
+};
+
+struct yaffs_shadow_fixer {
+	int obj_id;
+	int shadowed_id;
+	struct yaffs_shadow_fixer *next;
+};
+
+/* Structure for doing xattr modifications */
+struct yaffs_xattr_mod {
+	int set;		/* If 0 then this is a deletion */
+	const YCHAR *name;
+	const void *data;
+	int size;
+	int flags;
+	int result;
+};
+
+/*----------------------- YAFFS Functions -----------------------*/
+
+int yaffs_guts_initialise(struct yaffs_dev *dev);
+void yaffs_deinitialise(struct yaffs_dev *dev);
+
+int yaffs_get_n_free_chunks(struct yaffs_dev *dev);
+
+int yaffs_rename_obj(struct yaffs_obj *old_dir, const YCHAR * old_name,
+		     struct yaffs_obj *new_dir, const YCHAR * new_name);
+
+int yaffs_unlinker(struct yaffs_obj *dir, const YCHAR * name);
+int yaffs_del_obj(struct yaffs_obj *obj);
+
+int yaffs_get_obj_name(struct yaffs_obj *obj, YCHAR * name, int buffer_size);
+loff_t yaffs_get_obj_length(struct yaffs_obj *obj);
+int yaffs_get_obj_inode(struct yaffs_obj *obj);
+unsigned yaffs_get_obj_type(struct yaffs_obj *obj);
+int yaffs_get_obj_link_count(struct yaffs_obj *obj);
+
+/* File operations */
+int yaffs_file_rd(struct yaffs_obj *obj, u8 * buffer, loff_t offset,
+		  int n_bytes);
+int yaffs_wr_file(struct yaffs_obj *obj, const u8 * buffer, loff_t offset,
+		  int n_bytes, int write_trhrough);
+int yaffs_resize_file(struct yaffs_obj *obj, loff_t new_size);
+
+struct yaffs_obj *yaffs_create_file(struct yaffs_obj *parent,
+				    const YCHAR *name, u32 mode, u32 uid,
+				    u32 gid);
+
+int yaffs_flush_file(struct yaffs_obj *obj, int update_time, int data_sync);
+
+/* Flushing and checkpointing */
+void yaffs_flush_whole_cache(struct yaffs_dev *dev);
+
+int yaffs_checkpoint_save(struct yaffs_dev *dev);
+int yaffs_checkpoint_restore(struct yaffs_dev *dev);
+
+/* Directory operations */
+struct yaffs_obj *yaffs_create_dir(struct yaffs_obj *parent, const YCHAR *name,
+				   u32 mode, u32 uid, u32 gid);
+struct yaffs_obj *yaffs_find_by_name(struct yaffs_obj *the_dir,
+				     const YCHAR *name);
+struct yaffs_obj *yaffs_find_by_number(struct yaffs_dev *dev, u32 number);
+
+/* Link operations */
+struct yaffs_obj *yaffs_link_obj(struct yaffs_obj *parent, const YCHAR *name,
+				 struct yaffs_obj *equiv_obj);
+
+struct yaffs_obj *yaffs_get_equivalent_obj(struct yaffs_obj *obj);
+
+/* Symlink operations */
+struct yaffs_obj *yaffs_create_symlink(struct yaffs_obj *parent,
+				       const YCHAR *name, u32 mode, u32 uid,
+				       u32 gid, const YCHAR *alias);
+YCHAR *yaffs_get_symlink_alias(struct yaffs_obj *obj);
+
+/* Special inodes (fifos, sockets and devices) */
+struct yaffs_obj *yaffs_create_special(struct yaffs_obj *parent,
+				       const YCHAR *name, u32 mode, u32 uid,
+				       u32 gid, u32 rdev);
+
+int yaffs_set_xattrib(struct yaffs_obj *obj, const YCHAR *name,
+		      const void *value, int size, int flags);
+int yaffs_get_xattrib(struct yaffs_obj *obj, const YCHAR *name, void *value,
+		      int size);
+int yaffs_list_xattrib(struct yaffs_obj *obj, char *buffer, int size);
+int yaffs_remove_xattrib(struct yaffs_obj *obj, const YCHAR *name);
+
+/* Special directories */
+struct yaffs_obj *yaffs_root(struct yaffs_dev *dev);
+struct yaffs_obj *yaffs_lost_n_found(struct yaffs_dev *dev);
+
+void yaffs_handle_defered_free(struct yaffs_obj *obj);
+
+void yaffs_update_dirty_dirs(struct yaffs_dev *dev);
+
+int yaffs_bg_gc(struct yaffs_dev *dev, unsigned urgency);
+
+/* Debug dump  */
+int yaffs_dump_obj(struct yaffs_obj *obj);
+
+void yaffs_guts_test(struct yaffs_dev *dev);
+int yaffs_guts_ll_init(struct yaffs_dev *dev);
+
+
+/* A few useful functions to be used within the core files*/
+void yaffs_chunk_del(struct yaffs_dev *dev, int chunk_id, int mark_flash,
+		     int lyn);
+int yaffs_check_ff(u8 *buffer, int n_bytes);
+void yaffs_handle_chunk_error(struct yaffs_dev *dev,
+			      struct yaffs_block_info *bi);
+
+u8 *yaffs_get_temp_buffer(struct yaffs_dev *dev);
+void yaffs_release_temp_buffer(struct yaffs_dev *dev, u8 *buffer);
+
+struct yaffs_obj *yaffs_find_or_create_by_number(struct yaffs_dev *dev,
+						 int number,
+						 enum yaffs_obj_type type);
+int yaffs_put_chunk_in_file(struct yaffs_obj *in, int inode_chunk,
+			    int nand_chunk, int in_scan);
+void yaffs_set_obj_name(struct yaffs_obj *obj, const YCHAR *name);
+void yaffs_set_obj_name_from_oh(struct yaffs_obj *obj,
+				const struct yaffs_obj_hdr *oh);
+void yaffs_add_obj_to_dir(struct yaffs_obj *directory, struct yaffs_obj *obj);
+YCHAR *yaffs_clone_str(const YCHAR *str);
+void yaffs_link_fixup(struct yaffs_dev *dev, struct list_head *hard_list);
+void yaffs_block_became_dirty(struct yaffs_dev *dev, int block_no);
+int yaffs_update_oh(struct yaffs_obj *in, const YCHAR *name,
+		    int force, int is_shrink, int shadows,
+		    struct yaffs_xattr_mod *xop);
+void yaffs_handle_shadowed_obj(struct yaffs_dev *dev, int obj_id,
+			       int backward_scanning);
+int yaffs_check_alloc_available(struct yaffs_dev *dev, int n_chunks);
+struct yaffs_tnode *yaffs_get_tnode(struct yaffs_dev *dev);
+struct yaffs_tnode *yaffs_add_find_tnode_0(struct yaffs_dev *dev,
+					   struct yaffs_file_var *file_struct,
+					   u32 chunk_id,
+					   struct yaffs_tnode *passed_tn);
+
+int yaffs_do_file_wr(struct yaffs_obj *in, const u8 *buffer, loff_t offset,
+		     int n_bytes, int write_trhrough);
+void yaffs_resize_file_down(struct yaffs_obj *obj, loff_t new_size);
+void yaffs_skip_rest_of_block(struct yaffs_dev *dev);
+
+int yaffs_count_free_chunks(struct yaffs_dev *dev);
+
+struct yaffs_tnode *yaffs_find_tnode_0(struct yaffs_dev *dev,
+				       struct yaffs_file_var *file_struct,
+				       u32 chunk_id);
+
+u32 yaffs_get_group_base(struct yaffs_dev *dev, struct yaffs_tnode *tn,
+			 unsigned pos);
+
+int yaffs_is_non_empty_dir(struct yaffs_obj *obj);
+
+int yaffs_format_dev(struct yaffs_dev *dev);
+
+void yaffs_addr_to_chunk(struct yaffs_dev *dev, loff_t addr,
+				int *chunk_out, u32 *offset_out);
+/*
+ * Marshalling functions to get loff_t file sizes into aand out of
+ * object headers.
+ */
+void yaffs_oh_size_load(struct yaffs_obj_hdr *oh, loff_t fsize);
+loff_t yaffs_oh_to_size(struct yaffs_obj_hdr *oh);
+loff_t yaffs_max_file_size(struct yaffs_dev *dev);
+
+/*
+ * Debug function to count number of blocks in each state
+ * NB Needs to be called with correct number of integers
+ */
+
+void yaffs_count_blocks_by_state(struct yaffs_dev *dev, int bs[10]);
+
+int yaffs_find_chunk_in_file(struct yaffs_obj *in, int inode_chunk,
+				    struct yaffs_ext_tags *tags);
+
+#endif
diff --git a/fs/yaffs2/yaffs_linux.h b/fs/yaffs2/yaffs_linux.h
new file mode 100644
index 000000000000..c20ab14b7fa2
--- /dev/null
+++ b/fs/yaffs2/yaffs_linux.h
@@ -0,0 +1,48 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_LINUX_H__
+#define __YAFFS_LINUX_H__
+
+#include "yportenv.h"
+
+struct yaffs_linux_context {
+	struct list_head context_list;	/* List of these we have mounted */
+	struct yaffs_dev *dev;
+	struct super_block *super;
+	struct task_struct *bg_thread;	/* Background thread for this device */
+	int bg_running;
+	struct mutex gross_lock;	/* Gross locking mutex*/
+	u8 *spare_buffer;	/* For mtdif2 use. Don't know the buffer size
+				 * at compile time so we have to allocate it.
+				 */
+	struct list_head search_contexts;
+	struct task_struct *readdir_process;
+	unsigned mount_id;
+	int dirty;
+};
+
+#define yaffs_dev_to_lc(dev) ((struct yaffs_linux_context *)((dev)->os_context))
+#define yaffs_dev_to_mtd(dev) ((struct mtd_info *)((dev)->driver_context))
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17))
+#define WRITE_SIZE_STR "writesize"
+#define WRITE_SIZE(mtd) ((mtd)->writesize)
+#else
+#define WRITE_SIZE_STR "oobblock"
+#define WRITE_SIZE(mtd) ((mtd)->oobblock)
+#endif
+
+#endif
diff --git a/fs/yaffs2/yaffs_mtdif.c b/fs/yaffs2/yaffs_mtdif.c
new file mode 100644
index 000000000000..03a3d9c24e4c
--- /dev/null
+++ b/fs/yaffs2/yaffs_mtdif.c
@@ -0,0 +1,310 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yportenv.h"
+
+#include "yaffs_mtdif.h"
+
+#include "linux/mtd/mtd.h"
+#include "linux/types.h"
+#include "linux/time.h"
+#include "linux/mtd/rawnand.h"
+#include "linux/kernel.h"
+#include "linux/version.h"
+#include "linux/types.h"
+
+#include "uapi/linux/major.h"
+
+#include "yaffs_trace.h"
+#include "yaffs_guts.h"
+#include "yaffs_linux.h"
+
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 2, 0))
+#define MTD_OPS_AUTO_OOB MTD_OOB_AUTO
+#endif
+
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0))
+#define mtd_erase(m, ei) (m)->erase(m, ei)
+#define mtd_write_oob(m, addr, pops) (m)->write_oob(m, addr, pops)
+#define mtd_read_oob(m, addr, pops) (m)->read_oob(m, addr, pops)
+#define mtd_block_isbad(m, offs) (m)->block_isbad(m, offs)
+#define mtd_block_markbad(m, offs) (m)->block_markbad(m, offs)
+#endif
+
+
+
+int nandmtd_erase_block(struct yaffs_dev *dev, int block_no)
+{
+	struct mtd_info *mtd = yaffs_dev_to_mtd(dev);
+	u32 addr =
+	    ((loff_t) block_no) * dev->param.total_bytes_per_chunk *
+	    dev->param.chunks_per_block;
+	struct erase_info ei;
+	int retval = 0;
+
+	ei.mtd = mtd;
+	ei.addr = addr;
+	ei.len = dev->param.total_bytes_per_chunk * dev->param.chunks_per_block;
+	ei.time = 1000;
+	ei.retries = 2;
+	ei.callback = NULL;
+	ei.priv = (u_long) dev;
+
+	retval = mtd_erase(mtd, &ei);
+
+	if (retval == 0)
+		return YAFFS_OK;
+
+	return YAFFS_FAIL;
+}
+
+
+static 	int yaffs_mtd_write(struct yaffs_dev *dev, int nand_chunk,
+				   const u8 *data, int data_len,
+				   const u8 *oob, int oob_len)
+{
+	struct mtd_info *mtd = yaffs_dev_to_mtd(dev);
+	loff_t addr;
+	struct mtd_oob_ops ops;
+	int retval;
+
+	yaffs_trace(YAFFS_TRACE_MTD,
+			"yaffs_mtd_write(%p, %d, %p, %d, %p, %d)\n",
+			dev, nand_chunk, data, data_len, oob, oob_len);
+
+	if (!data || !data_len) {
+		data = NULL;
+		data_len = 0;
+	}
+
+	if (!oob || !oob_len) {
+		oob = NULL;
+		oob_len = 0;
+	}
+
+	addr = ((loff_t) nand_chunk) * dev->param.total_bytes_per_chunk;
+	memset(&ops, 0, sizeof(ops));
+	ops.mode = MTD_OPS_AUTO_OOB;
+	ops.len = (data) ? data_len : 0;
+	ops.ooblen = oob_len;
+	ops.datbuf = (u8 *)data;
+	ops.oobbuf = (u8 *)oob;
+
+	retval = mtd_write_oob(mtd, addr, &ops);
+	if (retval) {
+		yaffs_trace(YAFFS_TRACE_MTD,
+			"write_oob failed, chunk %d, mtd error %d",
+			nand_chunk, retval);
+	}
+	return retval ? YAFFS_FAIL : YAFFS_OK;
+}
+
+static int yaffs_mtd_read(struct yaffs_dev *dev, int nand_chunk,
+				   u8 *data, int data_len,
+				   u8 *oob, int oob_len,
+				   enum yaffs_ecc_result *ecc_result)
+{
+	struct mtd_info *mtd = yaffs_dev_to_mtd(dev);
+	loff_t addr;
+	struct mtd_oob_ops ops;
+	int retval;
+
+	addr = ((loff_t) nand_chunk) * dev->param.total_bytes_per_chunk;
+	memset(&ops, 0, sizeof(ops));
+	ops.mode = MTD_OPS_AUTO_OOB;
+	ops.len = (data) ? data_len : 0;
+	ops.ooblen = oob_len;
+	ops.datbuf = data;
+	ops.oobbuf = oob;
+
+#if (MTD_VERSION_CODE < MTD_VERSION(2, 6, 20))
+	/* In MTD 2.6.18 to 2.6.19 nand_base.c:nand_do_read_oob() has a bug;
+	 * help it out with ops.len = ops.ooblen when ops.datbuf == NULL.
+	 */
+	ops.len = (ops.datbuf) ? ops.len : ops.ooblen;
+#endif
+	/* Read page and oob using MTD.
+	 * Check status and determine ECC result.
+	 */
+	retval = mtd_read_oob(mtd, addr, &ops);
+	if (retval)
+		yaffs_trace(YAFFS_TRACE_MTD,
+			"read_oob failed, chunk %d, mtd error %d",
+			nand_chunk, retval);
+
+	switch (retval) {
+	case 0:
+		/* no error */
+		if(ecc_result)
+			*ecc_result = YAFFS_ECC_RESULT_NO_ERROR;
+		break;
+
+	case -EUCLEAN:
+		/* MTD's ECC fixed the data */
+		if(ecc_result)
+			*ecc_result = YAFFS_ECC_RESULT_FIXED;
+		dev->n_ecc_fixed++;
+		break;
+
+	case -EBADMSG:
+	default:
+		/* MTD's ECC could not fix the data */
+		dev->n_ecc_unfixed++;
+		if(ecc_result)
+			*ecc_result = YAFFS_ECC_RESULT_UNFIXED;
+		return YAFFS_FAIL;
+	}
+
+	return YAFFS_OK;
+}
+
+static 	int yaffs_mtd_erase(struct yaffs_dev *dev, int block_no)
+{
+	struct mtd_info *mtd = yaffs_dev_to_mtd(dev);
+
+	loff_t addr;
+	struct erase_info ei;
+	int retval = 0;
+	u32 block_size;
+
+	block_size = dev->param.total_bytes_per_chunk *
+		     dev->param.chunks_per_block;
+	addr = ((loff_t) block_no) * block_size;
+
+	ei.mtd = mtd;
+	ei.addr = addr;
+	ei.len = block_size;
+	ei.time = 1000;
+	ei.retries = 2;
+	ei.callback = NULL;
+	ei.priv = (u_long) dev;
+
+	retval = mtd_erase(mtd, &ei);
+
+	if (retval == 0)
+		return YAFFS_OK;
+
+	return YAFFS_FAIL;
+}
+
+static int yaffs_mtd_mark_bad(struct yaffs_dev *dev, int block_no)
+{
+	struct mtd_info *mtd = yaffs_dev_to_mtd(dev);
+	int blocksize = dev->param.chunks_per_block * dev->param.total_bytes_per_chunk;
+	int retval;
+
+	yaffs_trace(YAFFS_TRACE_BAD_BLOCKS, "marking block %d bad", block_no);
+
+	retval = mtd_block_markbad(mtd, (loff_t) blocksize * block_no);
+	return (retval) ? YAFFS_FAIL : YAFFS_OK;
+}
+
+static int yaffs_mtd_check_bad(struct yaffs_dev *dev, int block_no)
+{
+	struct mtd_info *mtd = yaffs_dev_to_mtd(dev);
+	int blocksize = dev->param.chunks_per_block * dev->param.total_bytes_per_chunk;
+	int retval;
+
+	yaffs_trace(YAFFS_TRACE_MTD, "checking block %d bad", block_no);
+
+	retval = mtd_block_isbad(mtd, (loff_t) blocksize * block_no);
+	return (retval) ? YAFFS_FAIL : YAFFS_OK;
+}
+
+static int yaffs_mtd_initialise(struct yaffs_dev *dev)
+{
+	return YAFFS_OK;
+}
+
+static int yaffs_mtd_deinitialise(struct yaffs_dev *dev)
+{
+	return YAFFS_OK;
+}
+
+
+void yaffs_mtd_drv_install(struct yaffs_dev *dev)
+{
+	struct yaffs_driver *drv = &dev->drv;
+
+	drv->drv_write_chunk_fn = yaffs_mtd_write;
+	drv->drv_read_chunk_fn = yaffs_mtd_read;
+	drv->drv_erase_fn = yaffs_mtd_erase;
+	drv->drv_mark_bad_fn = yaffs_mtd_mark_bad;
+	drv->drv_check_bad_fn = yaffs_mtd_check_bad;
+	drv->drv_initialise_fn = yaffs_mtd_initialise;
+	drv->drv_deinitialise_fn = yaffs_mtd_deinitialise;
+}
+
+
+struct mtd_info * yaffs_get_mtd_device(dev_t sdev)
+{
+	struct mtd_info *mtd;
+
+	mtd = yaffs_get_mtd_device(sdev);
+
+	/* Check it's an mtd device..... */
+	if (MAJOR(sdev) != MTD_BLOCK_MAJOR)
+		return NULL;	/* This isn't an mtd device */
+
+	/* Check it's NAND */
+	if (mtd->type != MTD_NANDFLASH) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"yaffs: MTD device is not NAND it's type %d",
+			mtd->type);
+		return NULL;
+	}
+
+	yaffs_trace(YAFFS_TRACE_OS, " %s %d", WRITE_SIZE_STR, WRITE_SIZE(mtd));
+	yaffs_trace(YAFFS_TRACE_OS, " oobsize %d", mtd->oobsize);
+	yaffs_trace(YAFFS_TRACE_OS, " erasesize %d", mtd->erasesize);
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 29)
+	yaffs_trace(YAFFS_TRACE_OS, " size %u", mtd->size);
+#else
+	yaffs_trace(YAFFS_TRACE_OS, " size %lld", mtd->size);
+#endif
+
+	return mtd;
+}
+
+int yaffs_verify_mtd(struct mtd_info *mtd, int yaffs_version, int inband_tags)
+{
+	if (yaffs_version == 2) {
+		if ((WRITE_SIZE(mtd) < YAFFS_MIN_YAFFS2_CHUNK_SIZE ||
+		     mtd->oobsize < YAFFS_MIN_YAFFS2_SPARE_SIZE) &&
+		    !inband_tags) {
+			yaffs_trace(YAFFS_TRACE_ALWAYS,
+				"MTD device does not have the right page sizes"
+			);
+			return -1;
+		}
+	} else {
+		if (WRITE_SIZE(mtd) < YAFFS_BYTES_PER_CHUNK ||
+		    mtd->oobsize != YAFFS_BYTES_PER_SPARE) {
+			yaffs_trace(YAFFS_TRACE_ALWAYS,
+				"MTD device does not support have the right page sizes"
+			);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+
+void yaffs_put_mtd_device(struct mtd_info *mtd)
+{
+	if(mtd)
+		put_mtd_device(mtd);
+}
diff --git a/fs/yaffs2/yaffs_mtdif.h b/fs/yaffs2/yaffs_mtdif.h
new file mode 100644
index 000000000000..9cff224c6dec
--- /dev/null
+++ b/fs/yaffs2/yaffs_mtdif.h
@@ -0,0 +1,25 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_MTDIF_H__
+#define __YAFFS_MTDIF_H__
+
+#include "yaffs_guts.h"
+
+void yaffs_mtd_drv_install(struct yaffs_dev *dev);
+struct mtd_info * yaffs_get_mtd_device(dev_t sdev);
+void yaffs_put_mtd_device(struct mtd_info *mtd);
+int yaffs_verify_mtd(struct mtd_info *mtd, int yaffs_version, int inband_tags);
+#endif
diff --git a/fs/yaffs2/yaffs_nameval.c b/fs/yaffs2/yaffs_nameval.c
new file mode 100644
index 000000000000..4bdf4ed743a7
--- /dev/null
+++ b/fs/yaffs2/yaffs_nameval.c
@@ -0,0 +1,208 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * This simple implementation of a name-value store assumes a small number of
+* values and fits into a small finite buffer.
+ *
+ * Each attribute is stored as a record:
+ *  sizeof(int) bytes   record size.
+ *  strnlen+1 bytes name null terminated.
+ *  nbytes    value.
+ *  ----------
+ *  total size  stored in record size
+ *
+ * This code has not been tested with unicode yet.
+ */
+
+#include "yaffs_nameval.h"
+
+#include "yportenv.h"
+
+static int nval_find(const char *xb, int xb_size, const YCHAR *name,
+		     int *exist_size)
+{
+	int pos = 0;
+	int size;
+
+	memcpy(&size, xb, sizeof(int));
+	while (size > 0 && (size < xb_size) && (pos + size < xb_size)) {
+		if (!strncmp((YCHAR *) (xb + pos + sizeof(int)),
+				name, size)) {
+			if (exist_size)
+				*exist_size = size;
+			return pos;
+		}
+		pos += size;
+		if (pos < xb_size - sizeof(int))
+			memcpy(&size, xb + pos, sizeof(int));
+		else
+			size = 0;
+	}
+	if (exist_size)
+		*exist_size = 0;
+	return -ENODATA;
+}
+
+static int nval_used(const char *xb, int xb_size)
+{
+	int pos = 0;
+	int size;
+
+	memcpy(&size, xb + pos, sizeof(int));
+	while (size > 0 && (size < xb_size) && (pos + size < xb_size)) {
+		pos += size;
+		if (pos < xb_size - sizeof(int))
+			memcpy(&size, xb + pos, sizeof(int));
+		else
+			size = 0;
+	}
+	return pos;
+}
+
+int nval_del(char *xb, int xb_size, const YCHAR *name)
+{
+	int pos = nval_find(xb, xb_size, name, NULL);
+	int size;
+
+	if (pos < 0 || pos >= xb_size)
+		return -ENODATA;
+
+	/* Find size, shift rest over this record,
+	 * then zero out the rest of buffer */
+	memcpy(&size, xb + pos, sizeof(int));
+	memcpy(xb + pos, xb + pos + size, xb_size - (pos + size));
+	memset(xb + (xb_size - size), 0, size);
+	return 0;
+}
+
+int nval_set(char *xb, int xb_size, const YCHAR *name, const char *buf,
+		int bsize, int flags)
+{
+	int pos;
+	int namelen = strnlen(name, xb_size);
+	int reclen;
+	int size_exist = 0;
+	int space;
+	int start;
+
+	pos = nval_find(xb, xb_size, name, &size_exist);
+
+	if (flags & XATTR_CREATE && pos >= 0)
+		return -EEXIST;
+	if (flags & XATTR_REPLACE && pos < 0)
+		return -ENODATA;
+
+	start = nval_used(xb, xb_size);
+	space = xb_size - start + size_exist;
+
+	reclen = (sizeof(int) + namelen + 1 + bsize);
+
+	if (reclen > space)
+		return -ENOSPC;
+
+	if (pos >= 0) {
+		nval_del(xb, xb_size, name);
+		start = nval_used(xb, xb_size);
+	}
+
+	pos = start;
+
+	memcpy(xb + pos, &reclen, sizeof(int));
+	pos += sizeof(int);
+	strncpy((YCHAR *) (xb + pos), name, reclen);
+	pos += (namelen + 1);
+	memcpy(xb + pos, buf, bsize);
+	return 0;
+}
+
+int nval_get(const char *xb, int xb_size, const YCHAR * name, char *buf,
+	     int bsize)
+{
+	int pos = nval_find(xb, xb_size, name, NULL);
+	int size;
+
+	if (pos >= 0 && pos < xb_size) {
+
+		memcpy(&size, xb + pos, sizeof(int));
+		pos += sizeof(int);	/* advance past record length */
+		size -= sizeof(int);
+
+		/* Advance over name string */
+		while (xb[pos] && size > 0 && pos < xb_size) {
+			pos++;
+			size--;
+		}
+		/*Advance over NUL */
+		pos++;
+		size--;
+
+		/* If bsize is zero then this is a size query.
+		 * Return the size, but don't copy.
+		 */
+		if (!bsize)
+			return size;
+
+		if (size <= bsize) {
+			memcpy(buf, xb + pos, size);
+			return size;
+		}
+	}
+	if (pos >= 0)
+		return -ERANGE;
+
+	return -ENODATA;
+}
+
+int nval_list(const char *xb, int xb_size, char *buf, int bsize)
+{
+	int pos = 0;
+	int size;
+	int name_len;
+	int ncopied = 0;
+	int filled = 0;
+
+	memcpy(&size, xb + pos, sizeof(int));
+	while (size > sizeof(int) &&
+		size <= xb_size &&
+		(pos + size) < xb_size &&
+		!filled) {
+		pos += sizeof(int);
+		size -= sizeof(int);
+		name_len = strnlen((YCHAR *) (xb + pos), size);
+		if (ncopied + name_len + 1 < bsize) {
+			memcpy(buf, xb + pos, name_len * sizeof(YCHAR));
+			buf += name_len;
+			*buf = '\0';
+			buf++;
+			if (sizeof(YCHAR) > 1) {
+				*buf = '\0';
+				buf++;
+			}
+			ncopied += (name_len + 1);
+		} else {
+			filled = 1;
+		}
+		pos += size;
+		if (pos < xb_size - sizeof(int))
+			memcpy(&size, xb + pos, sizeof(int));
+		else
+			size = 0;
+	}
+	return ncopied;
+}
+
+int nval_hasvalues(const char *xb, int xb_size)
+{
+	return nval_used(xb, xb_size) > 0;
+}
diff --git a/fs/yaffs2/yaffs_nameval.h b/fs/yaffs2/yaffs_nameval.h
new file mode 100644
index 000000000000..951e64f872b6
--- /dev/null
+++ b/fs/yaffs2/yaffs_nameval.h
@@ -0,0 +1,28 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __NAMEVAL_H__
+#define __NAMEVAL_H__
+
+#include "yportenv.h"
+
+int nval_del(char *xb, int xb_size, const YCHAR * name);
+int nval_set(char *xb, int xb_size, const YCHAR * name, const char *buf,
+	     int bsize, int flags);
+int nval_get(const char *xb, int xb_size, const YCHAR * name, char *buf,
+	     int bsize);
+int nval_list(const char *xb, int xb_size, char *buf, int bsize);
+int nval_hasvalues(const char *xb, int xb_size);
+#endif
diff --git a/fs/yaffs2/yaffs_nand.c b/fs/yaffs2/yaffs_nand.c
new file mode 100644
index 000000000000..0d8499bdc630
--- /dev/null
+++ b/fs/yaffs2/yaffs_nand.c
@@ -0,0 +1,122 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_nand.h"
+#include "yaffs_tagscompat.h"
+
+#include "yaffs_getblockinfo.h"
+#include "yaffs_summary.h"
+
+static int apply_chunk_offset(struct yaffs_dev *dev, int chunk)
+{
+	return chunk - dev->chunk_offset;
+}
+
+int yaffs_rd_chunk_tags_nand(struct yaffs_dev *dev, int nand_chunk,
+			     u8 *buffer, struct yaffs_ext_tags *tags)
+{
+	int result;
+	struct yaffs_ext_tags local_tags;
+	int flash_chunk = apply_chunk_offset(dev, nand_chunk);
+
+	dev->n_page_reads++;
+
+	/* If there are no tags provided use local tags. */
+	if (!tags)
+		tags = &local_tags;
+
+	result = dev->tagger.read_chunk_tags_fn(dev, flash_chunk, buffer, tags);
+	if (tags && tags->ecc_result > YAFFS_ECC_RESULT_NO_ERROR) {
+
+		struct yaffs_block_info *bi;
+		bi = yaffs_get_block_info(dev,
+					  nand_chunk /
+					  dev->param.chunks_per_block);
+		yaffs_handle_chunk_error(dev, bi);
+	}
+	return result;
+}
+
+int yaffs_wr_chunk_tags_nand(struct yaffs_dev *dev,
+				int nand_chunk,
+				const u8 *buffer, struct yaffs_ext_tags *tags)
+{
+	int result;
+	int flash_chunk = apply_chunk_offset(dev, nand_chunk);
+
+	dev->n_page_writes++;
+
+	if (!tags) {
+		yaffs_trace(YAFFS_TRACE_ERROR, "Writing with no tags");
+		BUG();
+		return YAFFS_FAIL;
+	}
+
+	tags->seq_number = dev->seq_number;
+	tags->chunk_used = 1;
+	yaffs_trace(YAFFS_TRACE_WRITE,
+		"Writing chunk %d tags %d %d",
+		nand_chunk, tags->obj_id, tags->chunk_id);
+
+	result = dev->tagger.write_chunk_tags_fn(dev, flash_chunk,
+							buffer, tags);
+
+	yaffs_summary_add(dev, tags, nand_chunk);
+
+	return result;
+}
+
+int yaffs_mark_bad(struct yaffs_dev *dev, int block_no)
+{
+	block_no -= dev->block_offset;
+	dev->n_bad_markings++;
+
+	if (dev->param.disable_bad_block_marking)
+		return YAFFS_OK;
+
+	return dev->tagger.mark_bad_fn(dev, block_no);
+}
+
+
+int yaffs_query_init_block_state(struct yaffs_dev *dev,
+				 int block_no,
+				 enum yaffs_block_state *state,
+				 u32 *seq_number)
+{
+	block_no -= dev->block_offset;
+	return dev->tagger.query_block_fn(dev, block_no, state, seq_number);
+}
+
+int yaffs_erase_block(struct yaffs_dev *dev, int block_no)
+{
+	int result;
+
+	block_no -= dev->block_offset;
+	dev->n_erasures++;
+	result = dev->drv.drv_erase_fn(dev, block_no);
+	return result;
+}
+
+int yaffs_init_nand(struct yaffs_dev *dev)
+{
+	if (dev->drv.drv_initialise_fn)
+		return dev->drv.drv_initialise_fn(dev);
+	return YAFFS_OK;
+}
+
+int yaffs_deinit_nand(struct yaffs_dev *dev)
+{
+	if (dev->drv.drv_deinitialise_fn)
+		return dev->drv.drv_deinitialise_fn(dev);
+	return YAFFS_OK;
+}
diff --git a/fs/yaffs2/yaffs_nand.h b/fs/yaffs2/yaffs_nand.h
new file mode 100644
index 000000000000..804e97ad66d0
--- /dev/null
+++ b/fs/yaffs2/yaffs_nand.h
@@ -0,0 +1,39 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_NAND_H__
+#define __YAFFS_NAND_H__
+#include "yaffs_guts.h"
+
+int yaffs_rd_chunk_tags_nand(struct yaffs_dev *dev, int nand_chunk,
+			     u8 *buffer, struct yaffs_ext_tags *tags);
+
+int yaffs_wr_chunk_tags_nand(struct yaffs_dev *dev,
+			     int nand_chunk,
+			     const u8 *buffer, struct yaffs_ext_tags *tags);
+
+int yaffs_mark_bad(struct yaffs_dev *dev, int block_no);
+
+int yaffs_query_init_block_state(struct yaffs_dev *dev,
+				 int block_no,
+				 enum yaffs_block_state *state,
+				 unsigned *seq_number);
+
+int yaffs_erase_block(struct yaffs_dev *dev, int flash_block);
+
+int yaffs_init_nand(struct yaffs_dev *dev);
+int yaffs_deinit_nand(struct yaffs_dev *dev);
+
+#endif
diff --git a/fs/yaffs2/yaffs_packedtags1.c b/fs/yaffs2/yaffs_packedtags1.c
new file mode 100644
index 000000000000..dd9a331d8fc4
--- /dev/null
+++ b/fs/yaffs2/yaffs_packedtags1.c
@@ -0,0 +1,56 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_packedtags1.h"
+#include "yportenv.h"
+
+static const u8 all_ff[20] = {
+	0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff,
+	0xff, 0xff, 0xff, 0xff
+};
+
+void yaffs_pack_tags1(struct yaffs_packed_tags1 *pt,
+		      const struct yaffs_ext_tags *t)
+{
+	pt->chunk_id = t->chunk_id;
+	pt->serial_number = t->serial_number;
+	pt->n_bytes = t->n_bytes;
+	pt->obj_id = t->obj_id;
+	pt->ecc = 0;
+	pt->deleted = (t->is_deleted) ? 0 : 1;
+	pt->unused_stuff = 0;
+	pt->should_be_ff = 0xffffffff;
+}
+
+void yaffs_unpack_tags1(struct yaffs_ext_tags *t,
+			const struct yaffs_packed_tags1 *pt)
+{
+
+	if (memcmp(all_ff, pt, sizeof(struct yaffs_packed_tags1))) {
+		t->block_bad = 0;
+		if (pt->should_be_ff != 0xffffffff)
+			t->block_bad = 1;
+		t->chunk_used = 1;
+		t->obj_id = pt->obj_id;
+		t->chunk_id = pt->chunk_id;
+		t->n_bytes = pt->n_bytes;
+		t->ecc_result = YAFFS_ECC_RESULT_NO_ERROR;
+		t->is_deleted = (pt->deleted) ? 0 : 1;
+		t->serial_number = pt->serial_number;
+	} else {
+		memset(t, 0, sizeof(struct yaffs_ext_tags));
+	}
+}
diff --git a/fs/yaffs2/yaffs_packedtags1.h b/fs/yaffs2/yaffs_packedtags1.h
new file mode 100644
index 000000000000..b80f0a5b1574
--- /dev/null
+++ b/fs/yaffs2/yaffs_packedtags1.h
@@ -0,0 +1,39 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+/* This is used to pack YAFFS1 tags, not YAFFS2 tags. */
+
+#ifndef __YAFFS_PACKEDTAGS1_H__
+#define __YAFFS_PACKEDTAGS1_H__
+
+#include "yaffs_guts.h"
+
+struct yaffs_packed_tags1 {
+	unsigned chunk_id:20;
+	unsigned serial_number:2;
+	unsigned n_bytes:10;
+	unsigned obj_id:18;
+	unsigned ecc:12;
+	unsigned deleted:1;
+	unsigned unused_stuff:1;
+	unsigned should_be_ff;
+
+};
+
+void yaffs_pack_tags1(struct yaffs_packed_tags1 *pt,
+		      const struct yaffs_ext_tags *t);
+void yaffs_unpack_tags1(struct yaffs_ext_tags *t,
+			const struct yaffs_packed_tags1 *pt);
+#endif
diff --git a/fs/yaffs2/yaffs_packedtags2.c b/fs/yaffs2/yaffs_packedtags2.c
new file mode 100644
index 000000000000..e1d18cc33c68
--- /dev/null
+++ b/fs/yaffs2/yaffs_packedtags2.c
@@ -0,0 +1,197 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_packedtags2.h"
+#include "yportenv.h"
+#include "yaffs_trace.h"
+
+/* This code packs a set of extended tags into a binary structure for
+ * NAND storage
+ */
+
+/* Some of the information is "extra" struff which can be packed in to
+ * speed scanning
+ * This is defined by having the EXTRA_HEADER_INFO_FLAG set.
+ */
+
+/* Extra flags applied to chunk_id */
+
+#define EXTRA_HEADER_INFO_FLAG	0x80000000
+#define EXTRA_SHRINK_FLAG	0x40000000
+#define EXTRA_SHADOWS_FLAG	0x20000000
+#define EXTRA_SPARE_FLAGS	0x10000000
+
+#define ALL_EXTRA_FLAGS		0xf0000000
+
+/* Also, the top 4 bits of the object Id are set to the object type. */
+#define EXTRA_OBJECT_TYPE_SHIFT (28)
+#define EXTRA_OBJECT_TYPE_MASK  ((0x0f) << EXTRA_OBJECT_TYPE_SHIFT)
+
+static void yaffs_dump_packed_tags2_tags_only(
+				const struct yaffs_packed_tags2_tags_only *ptt)
+{
+	yaffs_trace(YAFFS_TRACE_MTD,
+		"packed tags obj %d chunk %d byte %d seq %d",
+		ptt->obj_id, ptt->chunk_id, ptt->n_bytes, ptt->seq_number);
+}
+
+static void yaffs_dump_packed_tags2(const struct yaffs_packed_tags2 *pt)
+{
+	yaffs_dump_packed_tags2_tags_only(&pt->t);
+}
+
+static void yaffs_dump_tags2(const struct yaffs_ext_tags *t)
+{
+	yaffs_trace(YAFFS_TRACE_MTD,
+		"ext.tags eccres %d blkbad %d chused %d obj %d chunk%d byte %d del %d ser %d seq %d",
+		t->ecc_result, t->block_bad, t->chunk_used, t->obj_id,
+		t->chunk_id, t->n_bytes, t->is_deleted, t->serial_number,
+		t->seq_number);
+
+}
+
+static int yaffs_check_tags_extra_packable(const struct yaffs_ext_tags *t)
+{
+	if (t->chunk_id != 0 || !t->extra_available)
+		return 0;
+
+	/* Check if the file size is too long to store */
+	if (t->extra_obj_type == YAFFS_OBJECT_TYPE_FILE &&
+	    (t->extra_file_size >> 31) != 0)
+		return 0;
+	return 1;
+}
+
+void yaffs_pack_tags2_tags_only(struct yaffs_packed_tags2_tags_only *ptt,
+				const struct yaffs_ext_tags *t)
+{
+	ptt->chunk_id = t->chunk_id;
+	ptt->seq_number = t->seq_number;
+	ptt->n_bytes = t->n_bytes;
+	ptt->obj_id = t->obj_id;
+
+	/* Only store extra tags for object headers.
+	 * If it is a file then only store  if the file size is short\
+	 * enough to fit.
+	 */
+	if (yaffs_check_tags_extra_packable(t)) {
+		/* Store the extra header info instead */
+		/* We save the parent object in the chunk_id */
+		ptt->chunk_id = EXTRA_HEADER_INFO_FLAG | t->extra_parent_id;
+		if (t->extra_is_shrink)
+			ptt->chunk_id |= EXTRA_SHRINK_FLAG;
+		if (t->extra_shadows)
+			ptt->chunk_id |= EXTRA_SHADOWS_FLAG;
+
+		ptt->obj_id &= ~EXTRA_OBJECT_TYPE_MASK;
+		ptt->obj_id |= (t->extra_obj_type << EXTRA_OBJECT_TYPE_SHIFT);
+
+		if (t->extra_obj_type == YAFFS_OBJECT_TYPE_HARDLINK)
+			ptt->n_bytes = t->extra_equiv_id;
+		else if (t->extra_obj_type == YAFFS_OBJECT_TYPE_FILE)
+			ptt->n_bytes = (unsigned) t->extra_file_size;
+		else
+			ptt->n_bytes = 0;
+	}
+
+	yaffs_dump_packed_tags2_tags_only(ptt);
+	yaffs_dump_tags2(t);
+}
+
+void yaffs_pack_tags2(struct yaffs_packed_tags2 *pt,
+		      const struct yaffs_ext_tags *t, int tags_ecc)
+{
+	yaffs_pack_tags2_tags_only(&pt->t, t);
+
+	if (tags_ecc)
+		yaffs_ecc_calc_other((unsigned char *)&pt->t,
+				    sizeof(struct yaffs_packed_tags2_tags_only),
+				    &pt->ecc);
+}
+
+void yaffs_unpack_tags2_tags_only(struct yaffs_ext_tags *t,
+				  struct yaffs_packed_tags2_tags_only *ptt)
+{
+	memset(t, 0, sizeof(struct yaffs_ext_tags));
+
+	if (ptt->seq_number == 0xffffffff)
+		return;
+
+	t->block_bad = 0;
+	t->chunk_used = 1;
+	t->obj_id = ptt->obj_id;
+	t->chunk_id = ptt->chunk_id;
+	t->n_bytes = ptt->n_bytes;
+	t->is_deleted = 0;
+	t->serial_number = 0;
+	t->seq_number = ptt->seq_number;
+
+	/* Do extra header info stuff */
+	if (ptt->chunk_id & EXTRA_HEADER_INFO_FLAG) {
+		t->chunk_id = 0;
+		t->n_bytes = 0;
+
+		t->extra_available = 1;
+		t->extra_parent_id = ptt->chunk_id & (~(ALL_EXTRA_FLAGS));
+		t->extra_is_shrink = ptt->chunk_id & EXTRA_SHRINK_FLAG ? 1 : 0;
+		t->extra_shadows = ptt->chunk_id & EXTRA_SHADOWS_FLAG ? 1 : 0;
+		t->extra_obj_type = ptt->obj_id >> EXTRA_OBJECT_TYPE_SHIFT;
+		t->obj_id &= ~EXTRA_OBJECT_TYPE_MASK;
+
+		if (t->extra_obj_type == YAFFS_OBJECT_TYPE_HARDLINK)
+			t->extra_equiv_id = ptt->n_bytes;
+		else
+			t->extra_file_size = ptt->n_bytes;
+	}
+	yaffs_dump_packed_tags2_tags_only(ptt);
+	yaffs_dump_tags2(t);
+}
+
+void yaffs_unpack_tags2(struct yaffs_ext_tags *t, struct yaffs_packed_tags2 *pt,
+			int tags_ecc)
+{
+	enum yaffs_ecc_result ecc_result = YAFFS_ECC_RESULT_NO_ERROR;
+
+	if (pt->t.seq_number != 0xffffffff && tags_ecc) {
+		/* Chunk is in use and we need to do ECC */
+
+		struct yaffs_ecc_other ecc;
+		int result;
+		yaffs_ecc_calc_other((unsigned char *)&pt->t,
+				sizeof(struct yaffs_packed_tags2_tags_only),
+				&ecc);
+		result =
+		    yaffs_ecc_correct_other((unsigned char *)&pt->t,
+				sizeof(struct yaffs_packed_tags2_tags_only),
+				&pt->ecc, &ecc);
+		switch (result) {
+		case 0:
+			ecc_result = YAFFS_ECC_RESULT_NO_ERROR;
+			break;
+		case 1:
+			ecc_result = YAFFS_ECC_RESULT_FIXED;
+			break;
+		case -1:
+			ecc_result = YAFFS_ECC_RESULT_UNFIXED;
+			break;
+		default:
+			ecc_result = YAFFS_ECC_RESULT_UNKNOWN;
+		}
+	}
+	yaffs_unpack_tags2_tags_only(t, &pt->t);
+
+	t->ecc_result = ecc_result;
+
+	yaffs_dump_packed_tags2(pt);
+	yaffs_dump_tags2(t);
+}
diff --git a/fs/yaffs2/yaffs_packedtags2.h b/fs/yaffs2/yaffs_packedtags2.h
new file mode 100644
index 000000000000..675e719460a8
--- /dev/null
+++ b/fs/yaffs2/yaffs_packedtags2.h
@@ -0,0 +1,47 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+/* This is used to pack YAFFS2 tags, not YAFFS1tags. */
+
+#ifndef __YAFFS_PACKEDTAGS2_H__
+#define __YAFFS_PACKEDTAGS2_H__
+
+#include "yaffs_guts.h"
+#include "yaffs_ecc.h"
+
+struct yaffs_packed_tags2_tags_only {
+	unsigned seq_number;
+	unsigned obj_id;
+	unsigned chunk_id;
+	unsigned n_bytes;
+};
+
+struct yaffs_packed_tags2 {
+	struct yaffs_packed_tags2_tags_only t;
+	struct yaffs_ecc_other ecc;
+};
+
+/* Full packed tags with ECC, used for oob tags */
+void yaffs_pack_tags2(struct yaffs_packed_tags2 *pt,
+		      const struct yaffs_ext_tags *t, int tags_ecc);
+void yaffs_unpack_tags2(struct yaffs_ext_tags *t, struct yaffs_packed_tags2 *pt,
+			int tags_ecc);
+
+/* Only the tags part (no ECC for use with inband tags */
+void yaffs_pack_tags2_tags_only(struct yaffs_packed_tags2_tags_only *pt,
+				const struct yaffs_ext_tags *t);
+void yaffs_unpack_tags2_tags_only(struct yaffs_ext_tags *t,
+				  struct yaffs_packed_tags2_tags_only *pt);
+#endif
diff --git a/fs/yaffs2/yaffs_summary.c b/fs/yaffs2/yaffs_summary.c
new file mode 100644
index 000000000000..6f3c7839fa6f
--- /dev/null
+++ b/fs/yaffs2/yaffs_summary.c
@@ -0,0 +1,313 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Summaries write the useful part of the tags for the chunks in a block into an
+ * an array which is written to the last n chunks of the block.
+ * Reading the summaries gives all the tags for the block in one read. Much
+ * faster.
+ *
+ * Chunks holding summaries are marked with tags making it look like
+ * they are part of a fake file.
+ *
+ * The summary could also be used during gc.
+ *
+ */
+
+#include "yaffs_summary.h"
+#include "yaffs_packedtags2.h"
+#include "yaffs_nand.h"
+#include "yaffs_getblockinfo.h"
+#include "yaffs_bitmap.h"
+
+/*
+ * The summary is built up in an array of summary tags.
+ * This gets written to the last one or two (maybe more) chunks in a block.
+ * A summary header is written as the first part of each chunk of summary data.
+ * The summary header must match or the summary is rejected.
+ */
+
+/* Summary tags don't need the sequence number because that is redundant. */
+struct yaffs_summary_tags {
+	unsigned obj_id;
+	unsigned chunk_id;
+	unsigned n_bytes;
+};
+
+/* Summary header */
+struct yaffs_summary_header {
+	unsigned version;	/* Must match current version */
+	unsigned block;		/* Must be this block */
+	unsigned seq;		/* Must be this sequence number */
+	unsigned sum;		/* Just add up all the bytes in the tags */
+};
+
+
+static void yaffs_summary_clear(struct yaffs_dev *dev)
+{
+	if (!dev->sum_tags)
+		return;
+	memset(dev->sum_tags, 0, dev->chunks_per_summary *
+		sizeof(struct yaffs_summary_tags));
+}
+
+
+void yaffs_summary_deinit(struct yaffs_dev *dev)
+{
+	kfree(dev->sum_tags);
+	dev->sum_tags = NULL;
+	kfree(dev->gc_sum_tags);
+	dev->gc_sum_tags = NULL;
+	dev->chunks_per_summary = 0;
+}
+
+int yaffs_summary_init(struct yaffs_dev *dev)
+{
+	int sum_bytes;
+	int chunks_used; /* Number of chunks used by summary */
+	int sum_tags_bytes;
+
+	sum_bytes = dev->param.chunks_per_block *
+			sizeof(struct yaffs_summary_tags);
+
+	chunks_used = (sum_bytes + dev->data_bytes_per_chunk - 1)/
+			(dev->data_bytes_per_chunk -
+				sizeof(struct yaffs_summary_header));
+
+	dev->chunks_per_summary = dev->param.chunks_per_block - chunks_used;
+	sum_tags_bytes = sizeof(struct yaffs_summary_tags) *
+				dev->chunks_per_summary;
+	dev->sum_tags = kmalloc(sum_tags_bytes, GFP_NOFS);
+	dev->gc_sum_tags = kmalloc(sum_tags_bytes, GFP_NOFS);
+	if (!dev->sum_tags || !dev->gc_sum_tags) {
+		yaffs_summary_deinit(dev);
+		return YAFFS_FAIL;
+	}
+
+	yaffs_summary_clear(dev);
+
+	return YAFFS_OK;
+}
+
+static unsigned yaffs_summary_sum(struct yaffs_dev *dev)
+{
+	u8 *sum_buffer = (u8 *)dev->sum_tags;
+	int i;
+	unsigned sum = 0;
+
+	i = sizeof(struct yaffs_summary_tags) *
+				dev->chunks_per_summary;
+	while (i > 0) {
+		sum += *sum_buffer;
+		sum_buffer++;
+		i--;
+	}
+
+	return sum;
+}
+
+static int yaffs_summary_write(struct yaffs_dev *dev, int blk)
+{
+	struct yaffs_ext_tags tags;
+	u8 *buffer;
+	u8 *sum_buffer = (u8 *)dev->sum_tags;
+	int n_bytes;
+	int chunk_in_nand;
+	int chunk_in_block;
+	int result;
+	int this_tx;
+	struct yaffs_summary_header hdr;
+	int sum_bytes_per_chunk = dev->data_bytes_per_chunk - sizeof(hdr);
+	struct yaffs_block_info *bi = yaffs_get_block_info(dev, blk);
+
+	buffer = yaffs_get_temp_buffer(dev);
+	n_bytes = sizeof(struct yaffs_summary_tags) *
+				dev->chunks_per_summary;
+	memset(&tags, 0, sizeof(struct yaffs_ext_tags));
+	tags.obj_id = YAFFS_OBJECTID_SUMMARY;
+	tags.chunk_id = 1;
+	chunk_in_block = dev->chunks_per_summary;
+	chunk_in_nand = dev->alloc_block * dev->param.chunks_per_block +
+						dev->chunks_per_summary;
+	hdr.version = YAFFS_SUMMARY_VERSION;
+	hdr.block = blk;
+	hdr.seq = bi->seq_number;
+	hdr.sum = yaffs_summary_sum(dev);
+
+	do {
+		this_tx = n_bytes;
+		if (this_tx > sum_bytes_per_chunk)
+			this_tx = sum_bytes_per_chunk;
+		memcpy(buffer, &hdr, sizeof(hdr));
+		memcpy(buffer + sizeof(hdr), sum_buffer, this_tx);
+		tags.n_bytes = this_tx + sizeof(hdr);
+		result = yaffs_wr_chunk_tags_nand(dev, chunk_in_nand,
+						buffer, &tags);
+
+		if (result != YAFFS_OK)
+			break;
+		yaffs_set_chunk_bit(dev, blk, chunk_in_block);
+		bi->pages_in_use++;
+		dev->n_free_chunks--;
+
+		n_bytes -= this_tx;
+		sum_buffer += this_tx;
+		chunk_in_nand++;
+		chunk_in_block++;
+		tags.chunk_id++;
+	} while (result == YAFFS_OK && n_bytes > 0);
+	yaffs_release_temp_buffer(dev, buffer);
+
+
+	if (result == YAFFS_OK)
+		bi->has_summary = 1;
+
+
+	return result;
+}
+
+int yaffs_summary_read(struct yaffs_dev *dev,
+			struct yaffs_summary_tags *st,
+			int blk)
+{
+	struct yaffs_ext_tags tags;
+	u8 *buffer;
+	u8 *sum_buffer = (u8 *)st;
+	int n_bytes;
+	int chunk_id;
+	int chunk_in_nand;
+	int chunk_in_block;
+	int result;
+	int this_tx;
+	struct yaffs_summary_header hdr;
+	struct yaffs_block_info *bi = yaffs_get_block_info(dev, blk);
+	int sum_bytes_per_chunk = dev->data_bytes_per_chunk - sizeof(hdr);
+	int sum_tags_bytes;
+
+	sum_tags_bytes = sizeof(struct yaffs_summary_tags) *
+				dev->chunks_per_summary;
+	buffer = yaffs_get_temp_buffer(dev);
+	n_bytes = sizeof(struct yaffs_summary_tags) * dev->chunks_per_summary;
+	chunk_in_block = dev->chunks_per_summary;
+	chunk_in_nand = blk * dev->param.chunks_per_block +
+							dev->chunks_per_summary;
+	chunk_id = 1;
+	do {
+		this_tx = n_bytes;
+		if (this_tx > sum_bytes_per_chunk)
+			this_tx = sum_bytes_per_chunk;
+		result = yaffs_rd_chunk_tags_nand(dev, chunk_in_nand,
+						buffer, &tags);
+
+		if (tags.chunk_id != chunk_id ||
+			tags.obj_id != YAFFS_OBJECTID_SUMMARY ||
+			tags.chunk_used == 0 ||
+			tags.ecc_result > YAFFS_ECC_RESULT_FIXED ||
+			tags.n_bytes != (this_tx + sizeof(hdr)))
+				result = YAFFS_FAIL;
+		if (result != YAFFS_OK)
+			break;
+
+		if (st == dev->sum_tags) {
+			/* If we're scanning then update the block info */
+			yaffs_set_chunk_bit(dev, blk, chunk_in_block);
+			bi->pages_in_use++;
+		}
+		memcpy(&hdr, buffer, sizeof(hdr));
+		memcpy(sum_buffer, buffer + sizeof(hdr), this_tx);
+		n_bytes -= this_tx;
+		sum_buffer += this_tx;
+		chunk_in_nand++;
+		chunk_in_block++;
+		chunk_id++;
+	} while (result == YAFFS_OK && n_bytes > 0);
+	yaffs_release_temp_buffer(dev, buffer);
+
+	if (result == YAFFS_OK) {
+		/* Verify header */
+		if (hdr.version != YAFFS_SUMMARY_VERSION ||
+		    hdr.block != blk ||
+		    hdr.seq != bi->seq_number ||
+		    hdr.sum != yaffs_summary_sum(dev))
+			result = YAFFS_FAIL;
+	}
+
+	if (st == dev->sum_tags && result == YAFFS_OK)
+		bi->has_summary = 1;
+
+	return result;
+}
+
+int yaffs_summary_add(struct yaffs_dev *dev,
+			struct yaffs_ext_tags *tags,
+			int chunk_in_nand)
+{
+	struct yaffs_packed_tags2_tags_only tags_only;
+	struct yaffs_summary_tags *sum_tags;
+	int block_in_nand = chunk_in_nand / dev->param.chunks_per_block;
+	int chunk_in_block = chunk_in_nand % dev->param.chunks_per_block;
+
+	if (!dev->sum_tags)
+		return YAFFS_OK;
+
+	if (chunk_in_block >= 0 && chunk_in_block < dev->chunks_per_summary) {
+		yaffs_pack_tags2_tags_only(&tags_only, tags);
+		sum_tags = &dev->sum_tags[chunk_in_block];
+		sum_tags->chunk_id = tags_only.chunk_id;
+		sum_tags->n_bytes = tags_only.n_bytes;
+		sum_tags->obj_id = tags_only.obj_id;
+
+		if (chunk_in_block == dev->chunks_per_summary - 1) {
+			/* Time to write out the summary */
+			yaffs_summary_write(dev, block_in_nand);
+			yaffs_summary_clear(dev);
+			yaffs_skip_rest_of_block(dev);
+		}
+	}
+	return YAFFS_OK;
+}
+
+int yaffs_summary_fetch(struct yaffs_dev *dev,
+			struct yaffs_ext_tags *tags,
+			int chunk_in_block)
+{
+	struct yaffs_packed_tags2_tags_only tags_only;
+	struct yaffs_summary_tags *sum_tags;
+	if (chunk_in_block >= 0 && chunk_in_block < dev->chunks_per_summary) {
+		sum_tags = &dev->sum_tags[chunk_in_block];
+		tags_only.chunk_id = sum_tags->chunk_id;
+		tags_only.n_bytes = sum_tags->n_bytes;
+		tags_only.obj_id = sum_tags->obj_id;
+		yaffs_unpack_tags2_tags_only(tags, &tags_only);
+		return YAFFS_OK;
+	}
+	return YAFFS_FAIL;
+}
+
+void yaffs_summary_gc(struct yaffs_dev *dev, int blk)
+{
+	struct yaffs_block_info *bi = yaffs_get_block_info(dev, blk);
+	int i;
+
+	if (!bi->has_summary)
+		return;
+
+	for (i = dev->chunks_per_summary;
+	     i < dev->param.chunks_per_block;
+	     i++) {
+		if (yaffs_check_chunk_bit(dev, blk, i)) {
+			yaffs_clear_chunk_bit(dev, blk, i);
+			bi->pages_in_use--;
+			dev->n_free_chunks++;
+		}
+	}
+}
diff --git a/fs/yaffs2/yaffs_summary.h b/fs/yaffs2/yaffs_summary.h
new file mode 100644
index 000000000000..be141d073369
--- /dev/null
+++ b/fs/yaffs2/yaffs_summary.h
@@ -0,0 +1,37 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_SUMMARY_H__
+#define __YAFFS_SUMMARY_H__
+
+#include "yaffs_packedtags2.h"
+
+
+int yaffs_summary_init(struct yaffs_dev *dev);
+void yaffs_summary_deinit(struct yaffs_dev *dev);
+
+int yaffs_summary_add(struct yaffs_dev *dev,
+			struct yaffs_ext_tags *tags,
+			int chunk_in_block);
+int yaffs_summary_fetch(struct yaffs_dev *dev,
+			struct yaffs_ext_tags *tags,
+			int chunk_in_block);
+int yaffs_summary_read(struct yaffs_dev *dev,
+			struct yaffs_summary_tags *st,
+			int blk);
+void yaffs_summary_gc(struct yaffs_dev *dev, int blk);
+
+
+#endif
diff --git a/fs/yaffs2/yaffs_tagscompat.c b/fs/yaffs2/yaffs_tagscompat.c
new file mode 100644
index 000000000000..092430beccb7
--- /dev/null
+++ b/fs/yaffs2/yaffs_tagscompat.c
@@ -0,0 +1,381 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_guts.h"
+#include "yaffs_tagscompat.h"
+#include "yaffs_ecc.h"
+#include "yaffs_getblockinfo.h"
+#include "yaffs_trace.h"
+
+static void yaffs_handle_rd_data_error(struct yaffs_dev *dev, int nand_chunk);
+
+
+/********** Tags ECC calculations  *********/
+
+
+void yaffs_calc_tags_ecc(struct yaffs_tags *tags)
+{
+	/* Calculate an ecc */
+	unsigned char *b = ((union yaffs_tags_union *)tags)->as_bytes;
+	unsigned i, j;
+	unsigned ecc = 0;
+	unsigned bit = 0;
+
+	tags->ecc = 0;
+
+	for (i = 0; i < 8; i++) {
+		for (j = 1; j & 0xff; j <<= 1) {
+			bit++;
+			if (b[i] & j)
+				ecc ^= bit;
+		}
+	}
+	tags->ecc = ecc;
+}
+
+int yaffs_check_tags_ecc(struct yaffs_tags *tags)
+{
+	unsigned ecc = tags->ecc;
+
+	yaffs_calc_tags_ecc(tags);
+
+	ecc ^= tags->ecc;
+
+	if (ecc && ecc <= 64) {
+		/* TODO: Handle the failure better. Retire? */
+		unsigned char *b = ((union yaffs_tags_union *)tags)->as_bytes;
+
+		ecc--;
+
+		b[ecc / 8] ^= (1 << (ecc & 7));
+
+		/* Now recvalc the ecc */
+		yaffs_calc_tags_ecc(tags);
+
+		return 1;	/* recovered error */
+	} else if (ecc) {
+		/* Wierd ecc failure value */
+		/* TODO Need to do somethiong here */
+		return -1;	/* unrecovered error */
+	}
+	return 0;
+}
+
+/********** Tags **********/
+
+static void yaffs_load_tags_to_spare(struct yaffs_spare *spare_ptr,
+				     struct yaffs_tags *tags_ptr)
+{
+	union yaffs_tags_union *tu = (union yaffs_tags_union *)tags_ptr;
+
+	yaffs_calc_tags_ecc(tags_ptr);
+
+	spare_ptr->tb0 = tu->as_bytes[0];
+	spare_ptr->tb1 = tu->as_bytes[1];
+	spare_ptr->tb2 = tu->as_bytes[2];
+	spare_ptr->tb3 = tu->as_bytes[3];
+	spare_ptr->tb4 = tu->as_bytes[4];
+	spare_ptr->tb5 = tu->as_bytes[5];
+	spare_ptr->tb6 = tu->as_bytes[6];
+	spare_ptr->tb7 = tu->as_bytes[7];
+}
+
+static void yaffs_get_tags_from_spare(struct yaffs_dev *dev,
+				      struct yaffs_spare *spare_ptr,
+				      struct yaffs_tags *tags_ptr)
+{
+	union yaffs_tags_union *tu = (union yaffs_tags_union *)tags_ptr;
+	int result;
+
+	tu->as_bytes[0] = spare_ptr->tb0;
+	tu->as_bytes[1] = spare_ptr->tb1;
+	tu->as_bytes[2] = spare_ptr->tb2;
+	tu->as_bytes[3] = spare_ptr->tb3;
+	tu->as_bytes[4] = spare_ptr->tb4;
+	tu->as_bytes[5] = spare_ptr->tb5;
+	tu->as_bytes[6] = spare_ptr->tb6;
+	tu->as_bytes[7] = spare_ptr->tb7;
+
+	result = yaffs_check_tags_ecc(tags_ptr);
+	if (result > 0)
+		dev->n_tags_ecc_fixed++;
+	else if (result < 0)
+		dev->n_tags_ecc_unfixed++;
+}
+
+static void yaffs_spare_init(struct yaffs_spare *spare)
+{
+	memset(spare, 0xff, sizeof(struct yaffs_spare));
+}
+
+static int yaffs_wr_nand(struct yaffs_dev *dev,
+			 int nand_chunk, const u8 *data,
+			 struct yaffs_spare *spare)
+{
+	int data_size = dev->data_bytes_per_chunk;
+
+	return dev->drv.drv_write_chunk_fn(dev, nand_chunk,
+				data, data_size,
+				(u8 *) spare, sizeof(*spare));
+}
+
+static int yaffs_rd_chunk_nand(struct yaffs_dev *dev,
+			       int nand_chunk,
+			       u8 *data,
+			       struct yaffs_spare *spare,
+			       enum yaffs_ecc_result *ecc_result,
+			       int correct_errors)
+{
+	int ret_val;
+	struct yaffs_spare local_spare;
+	int data_size;
+	int spare_size;
+	int ecc_result1, ecc_result2;
+	u8 calc_ecc[3];
+
+	if (!spare) {
+		/* If we don't have a real spare, then we use a local one. */
+		/* Need this for the calculation of the ecc */
+		spare = &local_spare;
+	}
+	data_size = dev->data_bytes_per_chunk;
+	spare_size = sizeof(struct yaffs_spare);
+
+	if (dev->param.use_nand_ecc)
+		return dev->drv.drv_read_chunk_fn(dev, nand_chunk,
+						data, data_size,
+						(u8 *) spare, spare_size,
+						ecc_result);
+
+
+	/* Handle the ECC at this level. */
+
+	ret_val = dev->drv.drv_read_chunk_fn(dev, nand_chunk,
+						 data, data_size,
+						 (u8 *)spare, spare_size,
+						NULL);
+	if (!data || !correct_errors)
+		return ret_val;
+
+	/* Do ECC correction if needed. */
+	yaffs_ecc_calc(data, calc_ecc);
+	ecc_result1 = yaffs_ecc_correct(data, spare->ecc1, calc_ecc);
+	yaffs_ecc_calc(&data[256], calc_ecc);
+	ecc_result2 = yaffs_ecc_correct(&data[256], spare->ecc2, calc_ecc);
+
+	if (ecc_result1 > 0) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"**>>yaffs ecc error fix performed on chunk %d:0",
+			nand_chunk);
+		dev->n_ecc_fixed++;
+	} else if (ecc_result1 < 0) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"**>>yaffs ecc error unfixed on chunk %d:0",
+			nand_chunk);
+		dev->n_ecc_unfixed++;
+	}
+
+	if (ecc_result2 > 0) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"**>>yaffs ecc error fix performed on chunk %d:1",
+			nand_chunk);
+		dev->n_ecc_fixed++;
+	} else if (ecc_result2 < 0) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"**>>yaffs ecc error unfixed on chunk %d:1",
+			nand_chunk);
+		dev->n_ecc_unfixed++;
+	}
+
+	if (ecc_result1 || ecc_result2) {
+		/* We had a data problem on this page */
+		yaffs_handle_rd_data_error(dev, nand_chunk);
+	}
+
+	if (ecc_result1 < 0 || ecc_result2 < 0)
+		*ecc_result = YAFFS_ECC_RESULT_UNFIXED;
+	else if (ecc_result1 > 0 || ecc_result2 > 0)
+		*ecc_result = YAFFS_ECC_RESULT_FIXED;
+	else
+		*ecc_result = YAFFS_ECC_RESULT_NO_ERROR;
+
+	return ret_val;
+}
+
+/*
+ * Functions for robustisizing
+ */
+
+static void yaffs_handle_rd_data_error(struct yaffs_dev *dev, int nand_chunk)
+{
+	int flash_block = nand_chunk / dev->param.chunks_per_block;
+
+	/* Mark the block for retirement */
+	yaffs_get_block_info(dev, flash_block + dev->block_offset)->
+		needs_retiring = 1;
+	yaffs_trace(YAFFS_TRACE_ERROR | YAFFS_TRACE_BAD_BLOCKS,
+		"**>>Block %d marked for retirement",
+		flash_block);
+
+	/* TODO:
+	 * Just do a garbage collection on the affected block
+	 * then retire the block
+	 * NB recursion
+	 */
+}
+
+static int yaffs_tags_compat_wr(struct yaffs_dev *dev,
+			 int nand_chunk,
+			 const u8 *data, const struct yaffs_ext_tags *ext_tags)
+{
+	struct yaffs_spare spare;
+	struct yaffs_tags tags;
+
+	yaffs_spare_init(&spare);
+
+	if (ext_tags->is_deleted)
+		spare.page_status = 0;
+	else {
+		tags.obj_id = ext_tags->obj_id;
+		tags.chunk_id = ext_tags->chunk_id;
+
+		tags.n_bytes_lsb = ext_tags->n_bytes & (1024 - 1);
+
+		if (dev->data_bytes_per_chunk >= 1024)
+			tags.n_bytes_msb = (ext_tags->n_bytes >> 10) & 3;
+		else
+			tags.n_bytes_msb = 3;
+
+		tags.serial_number = ext_tags->serial_number;
+
+		if (!dev->param.use_nand_ecc && data) {
+			yaffs_ecc_calc(data, spare.ecc1);
+			yaffs_ecc_calc(&data[256], spare.ecc2);
+		}
+
+		yaffs_load_tags_to_spare(&spare, &tags);
+	}
+	return yaffs_wr_nand(dev, nand_chunk, data, &spare);
+}
+
+static int yaffs_tags_compat_rd(struct yaffs_dev *dev,
+			 int nand_chunk,
+			 u8 *data, struct yaffs_ext_tags *ext_tags)
+{
+	struct yaffs_spare spare;
+	struct yaffs_tags tags;
+	enum yaffs_ecc_result ecc_result = YAFFS_ECC_RESULT_UNKNOWN;
+	static struct yaffs_spare spare_ff;
+	static int init;
+	int deleted;
+
+	if (!init) {
+		memset(&spare_ff, 0xff, sizeof(spare_ff));
+		init = 1;
+	}
+
+	if (!yaffs_rd_chunk_nand(dev, nand_chunk,
+					data, &spare, &ecc_result, 1))
+		return YAFFS_FAIL;
+
+	/* ext_tags may be NULL */
+	if (!ext_tags)
+		return YAFFS_OK;
+
+	deleted = (hweight8(spare.page_status) < 7) ? 1 : 0;
+
+	ext_tags->is_deleted = deleted;
+	ext_tags->ecc_result = ecc_result;
+	ext_tags->block_bad = 0;	/* We're reading it */
+	/* therefore it is not a bad block */
+	ext_tags->chunk_used =
+		memcmp(&spare_ff, &spare, sizeof(spare_ff)) ? 1 : 0;
+
+	if (ext_tags->chunk_used) {
+		yaffs_get_tags_from_spare(dev, &spare, &tags);
+		ext_tags->obj_id = tags.obj_id;
+		ext_tags->chunk_id = tags.chunk_id;
+		ext_tags->n_bytes = tags.n_bytes_lsb;
+
+		if (dev->data_bytes_per_chunk >= 1024)
+			ext_tags->n_bytes |=
+				(((unsigned)tags.n_bytes_msb) << 10);
+
+		ext_tags->serial_number = tags.serial_number;
+	}
+
+	return YAFFS_OK;
+}
+
+static int yaffs_tags_compat_mark_bad(struct yaffs_dev *dev, int flash_block)
+{
+	struct yaffs_spare spare;
+
+	memset(&spare, 0xff, sizeof(struct yaffs_spare));
+
+	spare.block_status = 'Y';
+
+	yaffs_wr_nand(dev, flash_block * dev->param.chunks_per_block, NULL,
+		      &spare);
+	yaffs_wr_nand(dev, flash_block * dev->param.chunks_per_block + 1,
+		      NULL, &spare);
+
+	return YAFFS_OK;
+}
+
+static int yaffs_tags_compat_query_block(struct yaffs_dev *dev,
+				  int block_no,
+				  enum yaffs_block_state *state,
+				  u32 *seq_number)
+{
+	struct yaffs_spare spare0, spare1;
+	static struct yaffs_spare spare_ff;
+	static int init;
+	enum yaffs_ecc_result dummy;
+
+	if (!init) {
+		memset(&spare_ff, 0xff, sizeof(spare_ff));
+		init = 1;
+	}
+
+	*seq_number = 0;
+
+	/* Look for bad block markers in the first two chunks */
+	yaffs_rd_chunk_nand(dev, block_no * dev->param.chunks_per_block,
+			    NULL, &spare0, &dummy, 0);
+	yaffs_rd_chunk_nand(dev, block_no * dev->param.chunks_per_block + 1,
+			    NULL, &spare1, &dummy, 0);
+
+	if (hweight8(spare0.block_status & spare1.block_status) < 7)
+		*state = YAFFS_BLOCK_STATE_DEAD;
+	else if (memcmp(&spare_ff, &spare0, sizeof(spare_ff)) == 0)
+		*state = YAFFS_BLOCK_STATE_EMPTY;
+	else
+		*state = YAFFS_BLOCK_STATE_NEEDS_SCAN;
+
+	return YAFFS_OK;
+}
+
+void yaffs_tags_compat_install(struct yaffs_dev *dev)
+{
+	if(dev->param.is_yaffs2)
+		return;
+	if(!dev->tagger.write_chunk_tags_fn)
+		dev->tagger.write_chunk_tags_fn = yaffs_tags_compat_wr;
+	if(!dev->tagger.read_chunk_tags_fn)
+		dev->tagger.read_chunk_tags_fn = yaffs_tags_compat_rd;
+	if(!dev->tagger.query_block_fn)
+		dev->tagger.query_block_fn = yaffs_tags_compat_query_block;
+	if(!dev->tagger.mark_bad_fn)
+		dev->tagger.mark_bad_fn = yaffs_tags_compat_mark_bad;
+}
diff --git a/fs/yaffs2/yaffs_tagscompat.h b/fs/yaffs2/yaffs_tagscompat.h
new file mode 100644
index 000000000000..92d298a6f582
--- /dev/null
+++ b/fs/yaffs2/yaffs_tagscompat.h
@@ -0,0 +1,44 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_TAGSCOMPAT_H__
+#define __YAFFS_TAGSCOMPAT_H__
+
+
+#include "yaffs_guts.h"
+
+#if 0
+
+
+int yaffs_tags_compat_wr(struct yaffs_dev *dev,
+			 int nand_chunk,
+			 const u8 *data, const struct yaffs_ext_tags *tags);
+int yaffs_tags_compat_rd(struct yaffs_dev *dev,
+			 int nand_chunk,
+			 u8 *data, struct yaffs_ext_tags *tags);
+int yaffs_tags_compat_mark_bad(struct yaffs_dev *dev, int block_no);
+int yaffs_tags_compat_query_block(struct yaffs_dev *dev,
+				  int block_no,
+				  enum yaffs_block_state *state,
+				  u32 *seq_number);
+
+#endif
+
+
+void yaffs_tags_compat_install(struct yaffs_dev *dev);
+void yaffs_calc_tags_ecc(struct yaffs_tags *tags);
+int yaffs_check_tags_ecc(struct yaffs_tags *tags);
+
+#endif
diff --git a/fs/yaffs2/yaffs_tagsmarshall.c b/fs/yaffs2/yaffs_tagsmarshall.c
new file mode 100644
index 000000000000..44a83b12ca4d
--- /dev/null
+++ b/fs/yaffs2/yaffs_tagsmarshall.c
@@ -0,0 +1,199 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_guts.h"
+#include "yaffs_trace.h"
+#include "yaffs_packedtags2.h"
+
+static int yaffs_tags_marshall_write(struct yaffs_dev *dev,
+				    int nand_chunk, const u8 *data,
+				    const struct yaffs_ext_tags *tags)
+{
+	struct yaffs_packed_tags2 pt;
+	int retval;
+
+	int packed_tags_size =
+	    dev->param.no_tags_ecc ? sizeof(pt.t) : sizeof(pt);
+	void *packed_tags_ptr =
+	    dev->param.no_tags_ecc ? (void *)&pt.t : (void *)&pt;
+
+	yaffs_trace(YAFFS_TRACE_MTD,
+		"yaffs_tags_marshall_write chunk %d data %p tags %p",
+		nand_chunk, data, tags);
+
+	/* For yaffs2 writing there must be both data and tags.
+	 * If we're using inband tags, then the tags are stuffed into
+	 * the end of the data buffer.
+	 */
+	if (!data || !tags)
+		BUG();
+	else if (dev->param.inband_tags) {
+		struct yaffs_packed_tags2_tags_only *pt2tp;
+		pt2tp =
+		    (struct yaffs_packed_tags2_tags_only *)(data +
+							dev->
+							data_bytes_per_chunk);
+		yaffs_pack_tags2_tags_only(pt2tp, tags);
+	} else {
+		yaffs_pack_tags2(&pt, tags, !dev->param.no_tags_ecc);
+	}
+
+	retval = dev->drv.drv_write_chunk_fn(dev, nand_chunk,
+			data, dev->param.total_bytes_per_chunk,
+			(dev->param.inband_tags) ? NULL : packed_tags_ptr,
+			(dev->param.inband_tags) ? 0 : packed_tags_size);
+
+	return retval;
+}
+
+static int yaffs_tags_marshall_read(struct yaffs_dev *dev,
+				   int nand_chunk, u8 *data,
+				   struct yaffs_ext_tags *tags)
+{
+	int retval = 0;
+	int local_data = 0;
+	u8 spare_buffer[100];
+	enum yaffs_ecc_result ecc_result;
+
+	struct yaffs_packed_tags2 pt;
+
+	int packed_tags_size =
+	    dev->param.no_tags_ecc ? sizeof(pt.t) : sizeof(pt);
+	void *packed_tags_ptr =
+	    dev->param.no_tags_ecc ? (void *)&pt.t : (void *)&pt;
+
+	yaffs_trace(YAFFS_TRACE_MTD,
+		"yaffs_tags_marshall_read chunk %d data %p tags %p",
+		nand_chunk, data, tags);
+
+	if (dev->param.inband_tags) {
+		if (!data) {
+			local_data = 1;
+			data = yaffs_get_temp_buffer(dev);
+		}
+	}
+
+	if (dev->param.inband_tags || (data && !tags))
+		retval = dev->drv.drv_read_chunk_fn(dev, nand_chunk,
+					data, dev->param.total_bytes_per_chunk,
+					NULL, 0,
+					&ecc_result);
+	else if (tags)
+		retval = dev->drv.drv_read_chunk_fn(dev, nand_chunk,
+					data, dev->param.total_bytes_per_chunk,
+					spare_buffer, packed_tags_size,
+					&ecc_result);
+	else
+		BUG();
+
+
+	if (dev->param.inband_tags) {
+		if (tags) {
+			struct yaffs_packed_tags2_tags_only *pt2tp;
+			pt2tp =
+				(struct yaffs_packed_tags2_tags_only *)
+				&data[dev->data_bytes_per_chunk];
+			yaffs_unpack_tags2_tags_only(tags, pt2tp);
+		}
+	} else if (tags) {
+		memcpy(packed_tags_ptr, spare_buffer, packed_tags_size);
+		yaffs_unpack_tags2(tags, &pt, !dev->param.no_tags_ecc);
+	}
+
+	if (local_data)
+		yaffs_release_temp_buffer(dev, data);
+
+	if (tags && ecc_result == YAFFS_ECC_RESULT_UNFIXED) {
+		tags->ecc_result = YAFFS_ECC_RESULT_UNFIXED;
+		dev->n_ecc_unfixed++;
+	}
+
+	if (tags && ecc_result == -YAFFS_ECC_RESULT_FIXED) {
+		if (tags->ecc_result <= YAFFS_ECC_RESULT_NO_ERROR)
+			tags->ecc_result = YAFFS_ECC_RESULT_FIXED;
+		dev->n_ecc_fixed++;
+	}
+
+	if (ecc_result < YAFFS_ECC_RESULT_UNFIXED)
+		return YAFFS_OK;
+	else
+		return YAFFS_FAIL;
+}
+
+static int yaffs_tags_marshall_query_block(struct yaffs_dev *dev, int block_no,
+			       enum yaffs_block_state *state,
+			       u32 *seq_number)
+{
+	int retval;
+
+	yaffs_trace(YAFFS_TRACE_MTD, "yaffs_tags_marshall_query_block %d",
+			block_no);
+
+	retval = dev->drv.drv_check_bad_fn(dev, block_no);
+
+	if (retval== YAFFS_FAIL) {
+		yaffs_trace(YAFFS_TRACE_MTD, "block is bad");
+
+		*state = YAFFS_BLOCK_STATE_DEAD;
+		*seq_number = 0;
+	} else {
+		struct yaffs_ext_tags t;
+
+		yaffs_tags_marshall_read(dev,
+				    block_no * dev->param.chunks_per_block,
+				    NULL, &t);
+
+		if (t.chunk_used) {
+			*seq_number = t.seq_number;
+			*state = YAFFS_BLOCK_STATE_NEEDS_SCAN;
+		} else {
+			*seq_number = 0;
+			*state = YAFFS_BLOCK_STATE_EMPTY;
+		}
+	}
+
+	yaffs_trace(YAFFS_TRACE_MTD,
+		"block query returns  seq %d state %d",
+		*seq_number, *state);
+
+	if (retval == 0)
+		return YAFFS_OK;
+	else
+		return YAFFS_FAIL;
+}
+
+static int yaffs_tags_marshall_mark_bad(struct yaffs_dev *dev, int block_no)
+{
+	return dev->drv.drv_mark_bad_fn(dev, block_no);
+
+}
+
+
+void yaffs_tags_marshall_install(struct yaffs_dev *dev)
+{
+	if (!dev->param.is_yaffs2)
+		return;
+
+	if (!dev->tagger.write_chunk_tags_fn)
+		dev->tagger.write_chunk_tags_fn = yaffs_tags_marshall_write;
+
+	if (!dev->tagger.read_chunk_tags_fn)
+		dev->tagger.read_chunk_tags_fn = yaffs_tags_marshall_read;
+
+	if (!dev->tagger.query_block_fn)
+		dev->tagger.query_block_fn = yaffs_tags_marshall_query_block;
+
+	if (!dev->tagger.mark_bad_fn)
+		dev->tagger.mark_bad_fn = yaffs_tags_marshall_mark_bad;
+
+}
diff --git a/fs/yaffs2/yaffs_tagsmarshall.h b/fs/yaffs2/yaffs_tagsmarshall.h
new file mode 100644
index 000000000000..bf3e68a1a5be
--- /dev/null
+++ b/fs/yaffs2/yaffs_tagsmarshall.h
@@ -0,0 +1,22 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_TAGSMARSHALL_H__
+#define __YAFFS_TAGSMARSHALL_H__
+
+#include "yaffs_guts.h"
+void yaffs_tags_marshall_install(struct yaffs_dev *dev);
+
+#endif
diff --git a/fs/yaffs2/yaffs_trace.h b/fs/yaffs2/yaffs_trace.h
new file mode 100644
index 000000000000..fd26054d3912
--- /dev/null
+++ b/fs/yaffs2/yaffs_trace.h
@@ -0,0 +1,57 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YTRACE_H__
+#define __YTRACE_H__
+
+extern unsigned int yaffs_trace_mask;
+extern unsigned int yaffs_wr_attempts;
+
+/*
+ * Tracing flags.
+ * The flags masked in YAFFS_TRACE_ALWAYS are always traced.
+ */
+
+#define YAFFS_TRACE_OS			0x00000002
+#define YAFFS_TRACE_ALLOCATE		0x00000004
+#define YAFFS_TRACE_SCAN		0x00000008
+#define YAFFS_TRACE_BAD_BLOCKS		0x00000010
+#define YAFFS_TRACE_ERASE		0x00000020
+#define YAFFS_TRACE_GC			0x00000040
+#define YAFFS_TRACE_WRITE		0x00000080
+#define YAFFS_TRACE_TRACING		0x00000100
+#define YAFFS_TRACE_DELETION		0x00000200
+#define YAFFS_TRACE_BUFFERS		0x00000400
+#define YAFFS_TRACE_NANDACCESS		0x00000800
+#define YAFFS_TRACE_GC_DETAIL		0x00001000
+#define YAFFS_TRACE_SCAN_DEBUG		0x00002000
+#define YAFFS_TRACE_MTD			0x00004000
+#define YAFFS_TRACE_CHECKPOINT		0x00008000
+
+#define YAFFS_TRACE_VERIFY		0x00010000
+#define YAFFS_TRACE_VERIFY_NAND		0x00020000
+#define YAFFS_TRACE_VERIFY_FULL		0x00040000
+#define YAFFS_TRACE_VERIFY_ALL		0x000f0000
+
+#define YAFFS_TRACE_SYNC		0x00100000
+#define YAFFS_TRACE_BACKGROUND		0x00200000
+#define YAFFS_TRACE_LOCK		0x00400000
+#define YAFFS_TRACE_MOUNT		0x00800000
+
+#define YAFFS_TRACE_ERROR		0x40000000
+#define YAFFS_TRACE_BUG			0x80000000
+#define YAFFS_TRACE_ALWAYS		0xf0000000
+
+#endif
diff --git a/fs/yaffs2/yaffs_verify.c b/fs/yaffs2/yaffs_verify.c
new file mode 100644
index 000000000000..e8f2f0a6c2be
--- /dev/null
+++ b/fs/yaffs2/yaffs_verify.c
@@ -0,0 +1,529 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_verify.h"
+#include "yaffs_trace.h"
+#include "yaffs_bitmap.h"
+#include "yaffs_getblockinfo.h"
+#include "yaffs_nand.h"
+
+int yaffs_skip_verification(struct yaffs_dev *dev)
+{
+	(void) dev;
+	return !(yaffs_trace_mask &
+		 (YAFFS_TRACE_VERIFY | YAFFS_TRACE_VERIFY_FULL));
+}
+
+static int yaffs_skip_full_verification(struct yaffs_dev *dev)
+{
+	(void) dev;
+	return !(yaffs_trace_mask & (YAFFS_TRACE_VERIFY_FULL));
+}
+
+static int yaffs_skip_nand_verification(struct yaffs_dev *dev)
+{
+	(void) dev;
+	return !(yaffs_trace_mask & (YAFFS_TRACE_VERIFY_NAND));
+}
+
+static const char * const block_state_name[] = {
+	"Unknown",
+	"Needs scan",
+	"Scanning",
+	"Empty",
+	"Allocating",
+	"Full",
+	"Dirty",
+	"Checkpoint",
+	"Collecting",
+	"Dead"
+};
+
+void yaffs_verify_blk(struct yaffs_dev *dev, struct yaffs_block_info *bi, int n)
+{
+	int actually_used;
+	int in_use;
+
+	if (yaffs_skip_verification(dev))
+		return;
+
+	/* Report illegal runtime states */
+	if (bi->block_state >= YAFFS_NUMBER_OF_BLOCK_STATES)
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Block %d has undefined state %d",
+			n, bi->block_state);
+
+	switch (bi->block_state) {
+	case YAFFS_BLOCK_STATE_UNKNOWN:
+	case YAFFS_BLOCK_STATE_SCANNING:
+	case YAFFS_BLOCK_STATE_NEEDS_SCAN:
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Block %d has bad run-state %s",
+			n, block_state_name[bi->block_state]);
+	}
+
+	/* Check pages in use and soft deletions are legal */
+
+	actually_used = bi->pages_in_use - bi->soft_del_pages;
+
+	if (bi->pages_in_use < 0 ||
+	    bi->pages_in_use > dev->param.chunks_per_block ||
+	    bi->soft_del_pages < 0 ||
+	    bi->soft_del_pages > dev->param.chunks_per_block ||
+	    actually_used < 0 || actually_used > dev->param.chunks_per_block)
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Block %d has illegal values pages_in_used %d soft_del_pages %d",
+			n, bi->pages_in_use, bi->soft_del_pages);
+
+	/* Check chunk bitmap legal */
+	in_use = yaffs_count_chunk_bits(dev, n);
+	if (in_use != bi->pages_in_use)
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Block %d has inconsistent values pages_in_use %d counted chunk bits %d",
+			n, bi->pages_in_use, in_use);
+}
+
+void yaffs_verify_collected_blk(struct yaffs_dev *dev,
+				struct yaffs_block_info *bi, int n)
+{
+	yaffs_verify_blk(dev, bi, n);
+
+	/* After collection the block should be in the erased state */
+
+	if (bi->block_state != YAFFS_BLOCK_STATE_COLLECTING &&
+	    bi->block_state != YAFFS_BLOCK_STATE_EMPTY) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"Block %d is in state %d after gc, should be erased",
+			n, bi->block_state);
+	}
+}
+
+void yaffs_verify_blocks(struct yaffs_dev *dev)
+{
+	int i;
+	int state_count[YAFFS_NUMBER_OF_BLOCK_STATES];
+	int illegal_states = 0;
+
+	if (yaffs_skip_verification(dev))
+		return;
+
+	memset(state_count, 0, sizeof(state_count));
+
+	for (i = dev->internal_start_block; i <= dev->internal_end_block; i++) {
+		struct yaffs_block_info *bi = yaffs_get_block_info(dev, i);
+		yaffs_verify_blk(dev, bi, i);
+
+		if (bi->block_state < YAFFS_NUMBER_OF_BLOCK_STATES)
+			state_count[bi->block_state]++;
+		else
+			illegal_states++;
+	}
+
+	yaffs_trace(YAFFS_TRACE_VERIFY,	"Block summary");
+
+	yaffs_trace(YAFFS_TRACE_VERIFY,
+		"%d blocks have illegal states",
+		illegal_states);
+	if (state_count[YAFFS_BLOCK_STATE_ALLOCATING] > 1)
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Too many allocating blocks");
+
+	for (i = 0; i < YAFFS_NUMBER_OF_BLOCK_STATES; i++)
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"%s %d blocks",
+			block_state_name[i], state_count[i]);
+
+	if (dev->blocks_in_checkpt != state_count[YAFFS_BLOCK_STATE_CHECKPOINT])
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Checkpoint block count wrong dev %d count %d",
+			dev->blocks_in_checkpt,
+			state_count[YAFFS_BLOCK_STATE_CHECKPOINT]);
+
+	if (dev->n_erased_blocks != state_count[YAFFS_BLOCK_STATE_EMPTY])
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Erased block count wrong dev %d count %d",
+			dev->n_erased_blocks,
+			state_count[YAFFS_BLOCK_STATE_EMPTY]);
+
+	if (state_count[YAFFS_BLOCK_STATE_COLLECTING] > 1)
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Too many collecting blocks %d (max is 1)",
+			state_count[YAFFS_BLOCK_STATE_COLLECTING]);
+}
+
+/*
+ * Verify the object header. oh must be valid, but obj and tags may be NULL in
+ * which case those tests will not be performed.
+ */
+void yaffs_verify_oh(struct yaffs_obj *obj, struct yaffs_obj_hdr *oh,
+		     struct yaffs_ext_tags *tags, int parent_check)
+{
+	if (obj && yaffs_skip_verification(obj->my_dev))
+		return;
+
+	if (!(tags && obj && oh)) {
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Verifying object header tags %p obj %p oh %p",
+			tags, obj, oh);
+		return;
+	}
+
+	if (oh->type <= YAFFS_OBJECT_TYPE_UNKNOWN ||
+	    oh->type > YAFFS_OBJECT_TYPE_MAX)
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Obj %d header type is illegal value 0x%x",
+			tags->obj_id, oh->type);
+
+	if (tags->obj_id != obj->obj_id)
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Obj %d header mismatch obj_id %d",
+			tags->obj_id, obj->obj_id);
+
+	/*
+	 * Check that the object's parent ids match if parent_check requested.
+	 *
+	 * Tests do not apply to the root object.
+	 */
+
+	if (parent_check && tags->obj_id > 1 && !obj->parent)
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Obj %d header mismatch parent_id %d obj->parent is NULL",
+			tags->obj_id, oh->parent_obj_id);
+
+	if (parent_check && obj->parent &&
+	    oh->parent_obj_id != obj->parent->obj_id &&
+	    (oh->parent_obj_id != YAFFS_OBJECTID_UNLINKED ||
+	     obj->parent->obj_id != YAFFS_OBJECTID_DELETED))
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Obj %d header mismatch parent_id %d parent_obj_id %d",
+			tags->obj_id, oh->parent_obj_id,
+			obj->parent->obj_id);
+
+	if (tags->obj_id > 1 && oh->name[0] == 0)	/* Null name */
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Obj %d header name is NULL",
+			obj->obj_id);
+
+	if (tags->obj_id > 1 && ((u8) (oh->name[0])) == 0xff)	/* Junk name */
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Obj %d header name is 0xff",
+			obj->obj_id);
+}
+
+void yaffs_verify_file(struct yaffs_obj *obj)
+{
+	u32 x;
+	int required_depth;
+	int actual_depth;
+	int last_chunk;
+	u32 offset_in_chunk;
+	u32 the_chunk;
+
+	u32 i;
+	struct yaffs_dev *dev;
+	struct yaffs_ext_tags tags;
+	struct yaffs_tnode *tn;
+	u32 obj_id;
+
+	if (!obj)
+		return;
+
+	if (yaffs_skip_verification(obj->my_dev))
+		return;
+
+	dev = obj->my_dev;
+	obj_id = obj->obj_id;
+
+
+	/* Check file size is consistent with tnode depth */
+	yaffs_addr_to_chunk(dev, obj->variant.file_variant.file_size,
+				&last_chunk, &offset_in_chunk);
+	last_chunk++;
+	x = last_chunk >> YAFFS_TNODES_LEVEL0_BITS;
+	required_depth = 0;
+	while (x > 0) {
+		x >>= YAFFS_TNODES_INTERNAL_BITS;
+		required_depth++;
+	}
+
+	actual_depth = obj->variant.file_variant.top_level;
+
+	/* Check that the chunks in the tnode tree are all correct.
+	 * We do this by scanning through the tnode tree and
+	 * checking the tags for every chunk match.
+	 */
+
+	if (yaffs_skip_nand_verification(dev))
+		return;
+
+	for (i = 1; i <= last_chunk; i++) {
+		tn = yaffs_find_tnode_0(dev, &obj->variant.file_variant, i);
+
+		if (!tn)
+			continue;
+
+		the_chunk = yaffs_get_group_base(dev, tn, i);
+		if (the_chunk > 0) {
+			yaffs_rd_chunk_tags_nand(dev, the_chunk, NULL,
+						 &tags);
+			if (tags.obj_id != obj_id || tags.chunk_id != i)
+				yaffs_trace(YAFFS_TRACE_VERIFY,
+					"Object %d chunk_id %d NAND mismatch chunk %d tags (%d:%d)",
+					obj_id, i, the_chunk,
+					tags.obj_id, tags.chunk_id);
+		}
+	}
+}
+
+void yaffs_verify_link(struct yaffs_obj *obj)
+{
+	if (obj && yaffs_skip_verification(obj->my_dev))
+		return;
+
+	/* Verify sane equivalent object */
+}
+
+void yaffs_verify_symlink(struct yaffs_obj *obj)
+{
+	if (obj && yaffs_skip_verification(obj->my_dev))
+		return;
+
+	/* Verify symlink string */
+}
+
+void yaffs_verify_special(struct yaffs_obj *obj)
+{
+	if (obj && yaffs_skip_verification(obj->my_dev))
+		return;
+}
+
+void yaffs_verify_obj(struct yaffs_obj *obj)
+{
+	struct yaffs_dev *dev;
+	u32 chunk_min;
+	u32 chunk_max;
+	u32 chunk_id_ok;
+	u32 chunk_in_range;
+	u32 chunk_wrongly_deleted;
+	u32 chunk_valid;
+
+	if (!obj)
+		return;
+
+	if (obj->being_created)
+		return;
+
+	dev = obj->my_dev;
+
+	if (yaffs_skip_verification(dev))
+		return;
+
+	/* Check sane object header chunk */
+
+	chunk_min = dev->internal_start_block * dev->param.chunks_per_block;
+	chunk_max =
+	    (dev->internal_end_block + 1) * dev->param.chunks_per_block - 1;
+
+	chunk_in_range = (((unsigned)(obj->hdr_chunk)) >= chunk_min &&
+			  ((unsigned)(obj->hdr_chunk)) <= chunk_max);
+	chunk_id_ok = chunk_in_range || (obj->hdr_chunk == 0);
+	chunk_valid = chunk_in_range &&
+	    yaffs_check_chunk_bit(dev,
+				  obj->hdr_chunk / dev->param.chunks_per_block,
+				  obj->hdr_chunk % dev->param.chunks_per_block);
+	chunk_wrongly_deleted = chunk_in_range && !chunk_valid;
+
+	if (!obj->fake && (!chunk_id_ok || chunk_wrongly_deleted))
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Obj %d has chunk_id %d %s %s",
+			obj->obj_id, obj->hdr_chunk,
+			chunk_id_ok ? "" : ",out of range",
+			chunk_wrongly_deleted ? ",marked as deleted" : "");
+
+	if (chunk_valid && !yaffs_skip_nand_verification(dev)) {
+		struct yaffs_ext_tags tags;
+		struct yaffs_obj_hdr *oh;
+		u8 *buffer = yaffs_get_temp_buffer(dev);
+
+		oh = (struct yaffs_obj_hdr *)buffer;
+
+		yaffs_rd_chunk_tags_nand(dev, obj->hdr_chunk, buffer, &tags);
+
+		yaffs_verify_oh(obj, oh, &tags, 1);
+
+		yaffs_release_temp_buffer(dev, buffer);
+	}
+
+	/* Verify it has a parent */
+	if (obj && !obj->fake && (!obj->parent || obj->parent->my_dev != dev)) {
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Obj %d has parent pointer %p which does not look like an object",
+			obj->obj_id, obj->parent);
+	}
+
+	/* Verify parent is a directory */
+	if (obj->parent &&
+	    obj->parent->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) {
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Obj %d's parent is not a directory (type %d)",
+			obj->obj_id, obj->parent->variant_type);
+	}
+
+	switch (obj->variant_type) {
+	case YAFFS_OBJECT_TYPE_FILE:
+		yaffs_verify_file(obj);
+		break;
+	case YAFFS_OBJECT_TYPE_SYMLINK:
+		yaffs_verify_symlink(obj);
+		break;
+	case YAFFS_OBJECT_TYPE_DIRECTORY:
+		yaffs_verify_dir(obj);
+		break;
+	case YAFFS_OBJECT_TYPE_HARDLINK:
+		yaffs_verify_link(obj);
+		break;
+	case YAFFS_OBJECT_TYPE_SPECIAL:
+		yaffs_verify_special(obj);
+		break;
+	case YAFFS_OBJECT_TYPE_UNKNOWN:
+	default:
+		yaffs_trace(YAFFS_TRACE_VERIFY,
+			"Obj %d has illegaltype %d",
+		   obj->obj_id, obj->variant_type);
+		break;
+	}
+}
+
+void yaffs_verify_objects(struct yaffs_dev *dev)
+{
+	struct yaffs_obj *obj;
+	int i;
+	struct list_head *lh;
+
+	if (yaffs_skip_verification(dev))
+		return;
+
+	/* Iterate through the objects in each hash entry */
+
+	for (i = 0; i < YAFFS_NOBJECT_BUCKETS; i++) {
+		list_for_each(lh, &dev->obj_bucket[i].list) {
+			obj = list_entry(lh, struct yaffs_obj, hash_link);
+			yaffs_verify_obj(obj);
+		}
+	}
+}
+
+void yaffs_verify_obj_in_dir(struct yaffs_obj *obj)
+{
+	struct list_head *lh;
+	struct yaffs_obj *list_obj;
+	int count = 0;
+
+	if (!obj) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS, "No object to verify");
+		BUG();
+		return;
+	}
+
+	if (yaffs_skip_verification(obj->my_dev))
+		return;
+
+	if (!obj->parent) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS, "Object does not have parent");
+		BUG();
+		return;
+	}
+
+	if (obj->parent->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS, "Parent is not directory");
+		BUG();
+	}
+
+	/* Iterate through the objects in each hash entry */
+
+	list_for_each(lh, &obj->parent->variant.dir_variant.children) {
+		list_obj = list_entry(lh, struct yaffs_obj, siblings);
+		yaffs_verify_obj(list_obj);
+		if (obj == list_obj)
+			count++;
+	}
+
+	if (count != 1) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"Object in directory %d times",
+			count);
+		BUG();
+	}
+}
+
+void yaffs_verify_dir(struct yaffs_obj *directory)
+{
+	struct list_head *lh;
+	struct yaffs_obj *list_obj;
+
+	if (!directory) {
+		BUG();
+		return;
+	}
+
+	if (yaffs_skip_full_verification(directory->my_dev))
+		return;
+
+	if (directory->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"Directory has wrong type: %d",
+			directory->variant_type);
+		BUG();
+	}
+
+	/* Iterate through the objects in each hash entry */
+
+	list_for_each(lh, &directory->variant.dir_variant.children) {
+		list_obj = list_entry(lh, struct yaffs_obj, siblings);
+		if (list_obj->parent != directory) {
+			yaffs_trace(YAFFS_TRACE_ALWAYS,
+				"Object in directory list has wrong parent %p",
+				list_obj->parent);
+			BUG();
+		}
+		yaffs_verify_obj_in_dir(list_obj);
+	}
+}
+
+static int yaffs_free_verification_failures;
+
+void yaffs_verify_free_chunks(struct yaffs_dev *dev)
+{
+	int counted;
+	int difference;
+
+	if (yaffs_skip_verification(dev))
+		return;
+
+	counted = yaffs_count_free_chunks(dev);
+
+	difference = dev->n_free_chunks - counted;
+
+	if (difference) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"Freechunks verification failure %d %d %d",
+			dev->n_free_chunks, counted, difference);
+		yaffs_free_verification_failures++;
+	}
+}
+
+int yaffs_verify_file_sane(struct yaffs_obj *in)
+{
+	(void) in;
+	return YAFFS_OK;
+}
diff --git a/fs/yaffs2/yaffs_verify.h b/fs/yaffs2/yaffs_verify.h
new file mode 100644
index 000000000000..4f4af8d29aa4
--- /dev/null
+++ b/fs/yaffs2/yaffs_verify.h
@@ -0,0 +1,43 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_VERIFY_H__
+#define __YAFFS_VERIFY_H__
+
+#include "yaffs_guts.h"
+
+void yaffs_verify_blk(struct yaffs_dev *dev, struct yaffs_block_info *bi,
+		      int n);
+void yaffs_verify_collected_blk(struct yaffs_dev *dev,
+				struct yaffs_block_info *bi, int n);
+void yaffs_verify_blocks(struct yaffs_dev *dev);
+
+void yaffs_verify_oh(struct yaffs_obj *obj, struct yaffs_obj_hdr *oh,
+		     struct yaffs_ext_tags *tags, int parent_check);
+void yaffs_verify_file(struct yaffs_obj *obj);
+void yaffs_verify_link(struct yaffs_obj *obj);
+void yaffs_verify_symlink(struct yaffs_obj *obj);
+void yaffs_verify_special(struct yaffs_obj *obj);
+void yaffs_verify_obj(struct yaffs_obj *obj);
+void yaffs_verify_objects(struct yaffs_dev *dev);
+void yaffs_verify_obj_in_dir(struct yaffs_obj *obj);
+void yaffs_verify_dir(struct yaffs_obj *directory);
+void yaffs_verify_free_chunks(struct yaffs_dev *dev);
+
+int yaffs_verify_file_sane(struct yaffs_obj *obj);
+
+int yaffs_skip_verification(struct yaffs_dev *dev);
+
+#endif
diff --git a/fs/yaffs2/yaffs_vfs.c b/fs/yaffs2/yaffs_vfs.c
new file mode 100644
index 000000000000..c7be4cddd1de
--- /dev/null
+++ b/fs/yaffs2/yaffs_vfs.c
@@ -0,0 +1,3666 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ * Acknowledgements:
+ * Luc van OostenRyck for numerous patches.
+ * Nick Bane for numerous patches.
+ * Nick Bane for 2.5/2.6 integration.
+ * Andras Toth for mknod rdev issue.
+ * Michael Fischer for finding the problem with inode inconsistency.
+ * Some code bodily lifted from JFFS
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ *
+ * This is the file system front-end to YAFFS that hooks it up to
+ * the VFS.
+ *
+ * Special notes:
+ * >> 2.4: sb->u.generic_sbp points to the struct yaffs_dev associated with
+ *         this superblock
+ * >> 2.6: sb->s_fs_info  points to the struct yaffs_dev associated with this
+ *         superblock
+ * >> inode->u.generic_ip points to the associated struct yaffs_obj.
+ */
+
+/*
+ * There are two variants of the VFS glue code. This variant should compile
+ * for any version of Linux.
+ */
+#include <linux/version.h>
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 10))
+#define YAFFS_COMPILE_BACKGROUND
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 23))
+#define YAFFS_COMPILE_FREEZER
+#endif
+#endif
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 28))
+#define YAFFS_COMPILE_EXPORTFS
+#endif
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 35))
+#define YAFFS_USE_SETATTR_COPY
+#define YAFFS_USE_TRUNCATE_SETSIZE
+#endif
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 35))
+#define YAFFS_HAS_EVICT_INODE
+#endif
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 13))
+#define YAFFS_NEW_FOLLOW_LINK 1
+#else
+#define YAFFS_NEW_FOLLOW_LINK 0
+#endif
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 6, 0))
+#define YAFFS_HAS_WRITE_SUPER
+#endif
+
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 19))
+#include <linux/config.h>
+#endif
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/proc_fs.h>
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39))
+#include <linux/smp_lock.h>
+#endif
+#include <linux/pagemap.h>
+#include <linux/mtd/mtd.h>
+#include <linux/interrupt.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+
+#if (YAFFS_NEW_FOLLOW_LINK == 1)
+#include <linux/namei.h>
+#endif
+
+#ifdef YAFFS_COMPILE_EXPORTFS
+#include <linux/exportfs.h>
+#endif
+
+#ifdef YAFFS_COMPILE_BACKGROUND
+#include <linux/kthread.h>
+#include <linux/delay.h>
+#endif
+#ifdef YAFFS_COMPILE_FREEZER
+#include <linux/freezer.h>
+#endif
+
+#include <asm/div64.h>
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+
+#include <linux/statfs.h>
+
+#define UnlockPage(p) unlock_page(p)
+#define Page_Uptodate(page)	test_bit(PG_uptodate, &(page)->flags)
+
+/* FIXME: use sb->s_id instead ? */
+#define yaffs_devname(sb, buf)	bdevname(sb->s_bdev, buf)
+
+#else
+
+#include <linux/locks.h>
+#define	BDEVNAME_SIZE		0
+#define	yaffs_devname(sb, buf)	kdevname(sb->s_dev)
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 5, 0))
+/* added NCB 26/5/2006 for 2.4.25-vrs2-tcl1 kernel */
+#define __user
+#endif
+
+#endif
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 26))
+#define YPROC_ROOT  (&proc_root)
+#else
+#define YPROC_ROOT  NULL
+#endif
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 26))
+#define Y_INIT_TIMER(a)	init_timer(a)
+#else
+#define Y_INIT_TIMER(a)	init_timer_on_stack(a)
+#endif
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 27))
+#define YAFFS_USE_WRITE_BEGIN_END 1
+#else
+#define YAFFS_USE_WRITE_BEGIN_END 0
+#endif
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 6, 0))
+#define YAFFS_SUPER_HAS_DIRTY
+#endif
+
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 2, 0))
+#define set_nlink(inode, count)  do { (inode)->i_nlink = (count); } while(0)
+#endif
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 28))
+static uint32_t YCALCBLOCKS(uint64_t partition_size, uint32_t block_size)
+{
+	uint64_t result = partition_size;
+	do_div(result, block_size);
+	return (uint32_t) result;
+}
+#else
+#define YCALCBLOCKS(s, b) ((s)/(b))
+#endif
+
+#include <linux/uaccess.h>
+#include <linux/mtd/mtd.h>
+#include <linux/cred.h>
+
+#include "yportenv.h"
+#include "yaffs_trace.h"
+#include "yaffs_guts.h"
+#include "yaffs_attribs.h"
+
+#include "yaffs_linux.h"
+
+#include "yaffs_mtdif.h"
+#include "yaffs_packedtags2.h"
+#include "yaffs_getblockinfo.h"
+
+unsigned int yaffs_trace_mask =
+		YAFFS_TRACE_BAD_BLOCKS |
+		YAFFS_TRACE_ALWAYS |
+		0;
+
+unsigned int yaffs_wr_attempts = YAFFS_WR_ATTEMPTS;
+unsigned int yaffs_auto_checkpoint = 1;
+unsigned int yaffs_gc_control = 1;
+unsigned int yaffs_bg_enable = 1;
+unsigned int yaffs_auto_select = 1;
+/* Module Parameters */
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+module_param(yaffs_trace_mask, uint, 0644);
+module_param(yaffs_wr_attempts, uint, 0644);
+module_param(yaffs_auto_checkpoint, uint, 0644);
+module_param(yaffs_gc_control, uint, 0644);
+module_param(yaffs_bg_enable, uint, 0644);
+#else
+MODULE_PARM(yaffs_trace_mask, "i");
+MODULE_PARM(yaffs_wr_attempts, "i");
+MODULE_PARM(yaffs_auto_checkpoint, "i");
+MODULE_PARM(yaffs_gc_control, "i");
+#endif
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 25))
+/* use iget and read_inode */
+#define Y_IGET(sb, inum) iget((sb), (inum))
+
+#else
+/* Call local equivalent */
+#define YAFFS_USE_OWN_IGET
+#define Y_IGET(sb, inum) yaffs_iget((sb), (inum))
+
+#endif
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 18))
+#define yaffs_inode_to_obj_lv(iptr) ((iptr)->i_private)
+#else
+#define yaffs_inode_to_obj_lv(iptr) ((iptr)->u.generic_ip)
+#endif
+
+#define yaffs_inode_to_obj(iptr) \
+	((struct yaffs_obj *)(yaffs_inode_to_obj_lv(iptr)))
+#define yaffs_dentry_to_obj(dptr) yaffs_inode_to_obj((dptr)->d_inode)
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+#define yaffs_super_to_dev(sb)	((struct yaffs_dev *)sb->s_fs_info)
+#else
+#define yaffs_super_to_dev(sb)	((struct yaffs_dev *)sb->u.generic_sbp)
+#endif
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 5, 0))
+#define Y_CLEAR_INODE(i) clear_inode(i)
+#else
+#define Y_CLEAR_INODE(i) end_writeback(i)
+#endif
+
+
+#define update_dir_time(dir) do {\
+			(dir)->i_ctime = (dir)->i_mtime = current_time(dir); \
+		} while (0)
+
+static void yaffs_fill_inode_from_obj(struct inode *inode,
+				      struct yaffs_obj *obj);
+
+
+static void yaffs_gross_lock(struct yaffs_dev *dev)
+{
+	yaffs_trace(YAFFS_TRACE_LOCK, "yaffs locking %p", current);
+	mutex_lock(&(yaffs_dev_to_lc(dev)->gross_lock));
+	yaffs_trace(YAFFS_TRACE_LOCK, "yaffs locked %p", current);
+}
+
+static void yaffs_gross_unlock(struct yaffs_dev *dev)
+{
+	yaffs_trace(YAFFS_TRACE_LOCK, "yaffs unlocking %p", current);
+	mutex_unlock(&(yaffs_dev_to_lc(dev)->gross_lock));
+}
+
+
+static int yaffs_readpage_nolock(struct file *f, struct page *pg)
+{
+	/* Lifted from jffs2 */
+
+	struct yaffs_obj *obj;
+	unsigned char *pg_buf;
+	int ret;
+	loff_t pos = ((loff_t) pg->index) << PAGE_SHIFT;
+	struct yaffs_dev *dev;
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_readpage_nolock at %lld, size %08x",
+		(long long)pos,
+		(unsigned)PAGE_SIZE);
+
+	obj = yaffs_dentry_to_obj(f->f_path.dentry);
+
+	dev = obj->my_dev;
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+	BUG_ON(!PageLocked(pg));
+#else
+	if (!PageLocked(pg))
+		PAGE_BUG(pg);
+#endif
+
+	pg_buf = kmap(pg);
+	/* FIXME: Can kmap fail? */
+
+	yaffs_gross_lock(dev);
+
+	ret = yaffs_file_rd(obj, pg_buf, pos, PAGE_SIZE);
+
+	yaffs_gross_unlock(dev);
+
+	if (ret >= 0)
+		ret = 0;
+
+	if (ret) {
+		ClearPageUptodate(pg);
+		SetPageError(pg);
+	} else {
+		SetPageUptodate(pg);
+		ClearPageError(pg);
+	}
+
+	flush_dcache_page(pg);
+	kunmap(pg);
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_readpage_nolock done");
+	return ret;
+}
+
+static int yaffs_readpage_unlock(struct file *f, struct page *pg)
+{
+	int ret = yaffs_readpage_nolock(f, pg);
+	UnlockPage(pg);
+	return ret;
+}
+
+static int yaffs_readpage(struct file *f, struct page *pg)
+{
+	int ret;
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_readpage");
+	ret = yaffs_readpage_unlock(f, pg);
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_readpage done");
+	return ret;
+}
+
+
+static void yaffs_set_super_dirty_val(struct yaffs_dev *dev, int val)
+{
+	struct yaffs_linux_context *lc = yaffs_dev_to_lc(dev);
+
+	if (lc)
+		lc->dirty = val;
+
+# ifdef YAFFS_SUPER_HAS_DIRTY
+	{
+		struct super_block *sb = lc->super;
+
+		if (sb)
+			sb->s_dirt = val;
+	}
+#endif
+
+}
+
+static void yaffs_set_super_dirty(struct yaffs_dev *dev)
+{
+	yaffs_set_super_dirty_val(dev, 1);
+}
+
+static void yaffs_clear_super_dirty(struct yaffs_dev *dev)
+{
+	yaffs_set_super_dirty_val(dev, 0);
+}
+
+static int yaffs_check_super_dirty(struct yaffs_dev *dev)
+{
+	struct yaffs_linux_context *lc = yaffs_dev_to_lc(dev);
+
+	if (lc && lc->dirty)
+		return 1;
+
+# ifdef YAFFS_SUPER_HAS_DIRTY
+	{
+		struct super_block *sb = lc->super;
+
+		if (sb && sb->s_dirt)
+			return 1;
+	}
+#endif
+	return 0;
+
+}
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+static int yaffs_writepage(struct page *page, struct writeback_control *wbc)
+#else
+static int yaffs_writepage(struct page *page)
+#endif
+{
+	struct yaffs_dev *dev;
+	struct address_space *mapping = page->mapping;
+	struct inode *inode;
+	unsigned long end_index;
+	char *buffer;
+	struct yaffs_obj *obj;
+	int n_written = 0;
+	unsigned n_bytes;
+	loff_t i_size;
+
+	if (!mapping)
+		BUG();
+	inode = mapping->host;
+	if (!inode)
+		BUG();
+	i_size = i_size_read(inode);
+
+	end_index = i_size >> PAGE_SHIFT;
+
+	if (page->index < end_index)
+		n_bytes = PAGE_SIZE;
+	else {
+		n_bytes = i_size & (PAGE_SIZE - 1);
+
+		if (page->index > end_index || !n_bytes) {
+			yaffs_trace(YAFFS_TRACE_OS,
+				"yaffs_writepage at %lld, inode size = %lld!!",
+				((loff_t)page->index) << PAGE_SHIFT,
+				inode->i_size);
+			yaffs_trace(YAFFS_TRACE_OS,
+				"                -> don't care!!");
+
+			zero_user_segment(page, 0, PAGE_SIZE);
+			set_page_writeback(page);
+			unlock_page(page);
+			end_page_writeback(page);
+			return 0;
+		}
+	}
+
+	if (n_bytes != PAGE_SIZE)
+		zero_user_segment(page, n_bytes, PAGE_SIZE);
+
+	get_page(page);
+
+	buffer = kmap(page);
+
+	obj = yaffs_inode_to_obj(inode);
+	dev = obj->my_dev;
+	yaffs_gross_lock(dev);
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_writepage at %lld, size %08x",
+		((loff_t)page->index) << PAGE_SHIFT, n_bytes);
+	yaffs_trace(YAFFS_TRACE_OS,
+		"writepag0: obj = %lld, ino = %lld",
+		obj->variant.file_variant.file_size, inode->i_size);
+
+	n_written = yaffs_wr_file(obj, buffer,
+				  ((loff_t)page->index) << PAGE_SHIFT, n_bytes, 0);
+
+	yaffs_set_super_dirty(dev);
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"writepag1: obj = %lld, ino = %lld",
+		obj->variant.file_variant.file_size, inode->i_size);
+
+	yaffs_gross_unlock(dev);
+
+	kunmap(page);
+	set_page_writeback(page);
+	unlock_page(page);
+	end_page_writeback(page);
+	put_page(page);
+
+	return (n_written == n_bytes) ? 0 : -ENOSPC;
+}
+
+/* Space holding and freeing is done to ensure we have space available for write_begin/end */
+/* For now we just assume few parallel writes and check against a small number. */
+/* Todo: need to do this with a counter to handle parallel reads better */
+
+static ssize_t yaffs_hold_space(struct file *f)
+{
+	struct yaffs_obj *obj;
+	struct yaffs_dev *dev;
+
+	int n_free_chunks;
+
+	obj = yaffs_dentry_to_obj(f->f_path.dentry);
+
+	dev = obj->my_dev;
+
+	yaffs_gross_lock(dev);
+
+	n_free_chunks = yaffs_get_n_free_chunks(dev);
+
+	yaffs_gross_unlock(dev);
+
+	return (n_free_chunks > 20) ? 1 : 0;
+}
+
+static void yaffs_release_space(struct file *f)
+{
+	struct yaffs_obj *obj;
+	struct yaffs_dev *dev;
+
+	obj = yaffs_dentry_to_obj(f->f_path.dentry);
+
+	dev = obj->my_dev;
+
+	yaffs_gross_lock(dev);
+
+	yaffs_gross_unlock(dev);
+}
+
+#if (YAFFS_USE_WRITE_BEGIN_END > 0)
+static int yaffs_write_begin(struct file *filp, struct address_space *mapping,
+			     loff_t pos, unsigned len, unsigned flags,
+			     struct page **pagep, void **fsdata)
+{
+	struct page *pg = NULL;
+	pgoff_t index = pos >> PAGE_SHIFT;
+
+	int ret = 0;
+	int space_held = 0;
+
+	/* Get a page */
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 28)
+	pg = grab_cache_page_write_begin(mapping, index, flags);
+#else
+	pg = __grab_cache_page(mapping, index);
+#endif
+
+	*pagep = pg;
+	if (!pg) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	yaffs_trace(YAFFS_TRACE_OS,
+		"start yaffs_write_begin index %d(%x) uptodate %d",
+		(int)index, (int)index, Page_Uptodate(pg) ? 1 : 0);
+
+	/* Get fs space */
+	space_held = yaffs_hold_space(filp);
+
+	if (!space_held) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	/* Update page if required */
+
+	if (!Page_Uptodate(pg))
+		ret = yaffs_readpage_nolock(filp, pg);
+
+	if (ret)
+		goto out;
+
+	/* Happy path return */
+	yaffs_trace(YAFFS_TRACE_OS, "end yaffs_write_begin - ok");
+
+	return 0;
+
+out:
+	yaffs_trace(YAFFS_TRACE_OS,
+		"end yaffs_write_begin fail returning %d", ret);
+	if (space_held)
+		yaffs_release_space(filp);
+	if (pg) {
+		unlock_page(pg);
+		put_page(pg);
+	}
+	return ret;
+}
+
+#else
+
+static int yaffs_prepare_write(struct file *f, struct page *pg,
+			       unsigned offset, unsigned to)
+{
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_prepair_write");
+
+	if (!Page_Uptodate(pg))
+		return yaffs_readpage_nolock(f, pg);
+	return 0;
+}
+#endif
+
+
+static ssize_t yaffs_file_write(struct file *f, const char *buf, size_t n,
+				loff_t * pos)
+{
+	struct yaffs_obj *obj;
+	int n_written;
+	loff_t ipos;
+	struct inode *inode;
+	struct yaffs_dev *dev;
+
+	obj = yaffs_dentry_to_obj(f->f_path.dentry);
+
+	if (!obj) {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_file_write: hey obj is null!");
+                return -EINVAL;
+        }
+
+	dev = obj->my_dev;
+
+	yaffs_gross_lock(dev);
+
+	inode = f->f_path.dentry->d_inode;
+
+	if (!S_ISBLK(inode->i_mode) && f->f_flags & O_APPEND)
+		ipos = inode->i_size;
+	else
+		ipos = *pos;
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_file_write about to write writing %u(%x) bytes to object %d at %lld",
+		(unsigned)n, (unsigned)n, obj->obj_id, ipos);
+
+	n_written = yaffs_wr_file(obj, buf, ipos, n, 0);
+
+	yaffs_set_super_dirty(dev);
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_file_write: %d(%x) bytes written",
+		(unsigned)n, (unsigned)n);
+
+	if (n_written > 0) {
+		ipos += n_written;
+		*pos = ipos;
+		if (ipos > inode->i_size) {
+			inode->i_size = ipos;
+			inode->i_blocks = (ipos + 511) >> 9;
+
+			yaffs_trace(YAFFS_TRACE_OS,
+				"yaffs_file_write size updated to %lld bytes, %d blocks",
+				ipos, (int)(inode->i_blocks));
+		}
+
+	}
+	yaffs_gross_unlock(dev);
+	return (n_written == 0) && (n > 0) ? -ENOSPC : n_written;
+}
+
+
+#if (YAFFS_USE_WRITE_BEGIN_END > 0)
+static int yaffs_write_end(struct file *filp, struct address_space *mapping,
+			   loff_t pos, unsigned len, unsigned copied,
+			   struct page *pg, void *fsdadata)
+{
+	int ret = 0;
+	void *addr, *kva;
+	uint32_t offset_into_page = pos & (PAGE_SIZE - 1);
+
+	kva = kmap(pg);
+	addr = kva + offset_into_page;
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_write_end addr %p pos %lld n_bytes %d",
+		addr, pos, copied);
+
+	ret = yaffs_file_write(filp, addr, copied, &pos);
+
+	if (ret != copied) {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_write_end not same size ret %d  copied %d",
+			ret, copied);
+		SetPageError(pg);
+	}
+
+	kunmap(pg);
+
+	yaffs_release_space(filp);
+	unlock_page(pg);
+	put_page(pg);
+	return ret;
+}
+#else
+
+static int yaffs_commit_write(struct file *f, struct page *pg, unsigned offset,
+			      unsigned to)
+{
+	void *addr, *kva;
+
+	loff_t pos = (((loff_t) pg->index) << PAGE_SHIFT) + offset;
+	int n_bytes = to - offset;
+	int n_written;
+
+	kva = kmap(pg);
+	addr = kva + offset;
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_commit_write addr %p pos %lld n_bytes %d",
+		addr, pos, n_bytes);
+
+	n_written = yaffs_file_write(f, addr, n_bytes, &pos);
+
+	if (n_written != n_bytes) {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_commit_write not same size n_written %d  n_bytes %d",
+			n_written, n_bytes);
+		SetPageError(pg);
+	}
+	kunmap(pg);
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_commit_write returning %d",
+		n_written == n_bytes ? 0 : n_written);
+
+	return n_written == n_bytes ? 0 : n_written;
+}
+#endif
+
+static struct address_space_operations yaffs_file_address_operations = {
+	.readpage = yaffs_readpage,
+	.writepage = yaffs_writepage,
+#if (YAFFS_USE_WRITE_BEGIN_END > 0)
+	.write_begin = yaffs_write_begin,
+	.write_end = yaffs_write_end,
+#else
+	.prepare_write = yaffs_prepare_write,
+	.commit_write = yaffs_commit_write,
+#endif
+};
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 5, 0))
+#define YCRED_FSUID()	from_kuid(&init_user_ns, current_fsuid())
+#define YCRED_FSGID()	from_kgid(&init_user_ns, current_fsgid())
+#else
+#define YCRED_FSUID()	YCRED(current)->fsuid
+#define YCRED_FSGID()	YCRED(current)->fsgid
+
+static inline uid_t i_uid_read(const struct inode *inode)
+{
+	return inode->i_uid;
+}
+
+static inline gid_t i_gid_read(const struct inode *inode)
+{
+	return inode->i_gid;
+}
+
+static inline void i_uid_write(struct inode *inode, uid_t uid)
+{
+	inode->i_uid = uid;
+}
+
+static inline void i_gid_write(struct inode *inode, gid_t gid)
+{
+	inode->i_gid = gid;
+}
+#endif
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17))
+static int yaffs_file_flush(struct file *file, fl_owner_t id)
+#else
+static int yaffs_file_flush(struct file *file)
+#endif
+{
+	struct yaffs_obj *obj = yaffs_dentry_to_obj(file->f_path.dentry);
+
+	struct yaffs_dev *dev = obj->my_dev;
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_file_flush object %d (%s)",
+		obj->obj_id,
+		obj->dirty ? "dirty" : "clean");
+
+	yaffs_gross_lock(dev);
+
+	yaffs_flush_file(obj, 1, 0);
+
+	yaffs_gross_unlock(dev);
+
+	return 0;
+}
+
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39))
+static int yaffs_sync_object(struct file *file, loff_t start, loff_t end, int datasync)
+#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 34))
+static int yaffs_sync_object(struct file *file, int datasync)
+#else
+static int yaffs_sync_object(struct file *file, struct dentry *dentry,
+			     int datasync)
+#endif
+{
+	struct yaffs_obj *obj;
+	struct yaffs_dev *dev;
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 34))
+	struct dentry *dentry = file->f_path.dentry;
+#endif
+
+	obj = yaffs_dentry_to_obj(dentry);
+
+	dev = obj->my_dev;
+
+	yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_SYNC,
+		"yaffs_sync_object");
+	yaffs_gross_lock(dev);
+	yaffs_flush_file(obj, 1, datasync);
+	yaffs_gross_unlock(dev);
+	return 0;
+}
+
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 22))
+static const struct file_operations yaffs_file_operations = {
+	.read_iter = generic_file_read_iter,
+	.write_iter = generic_file_write_iter,
+	.mmap = generic_file_mmap,
+	.flush = yaffs_file_flush,
+	.fsync = yaffs_sync_object,
+	.splice_read = generic_file_splice_read,
+	.splice_write = iter_file_splice_write,
+	.llseek = generic_file_llseek,
+};
+
+#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 18))
+
+static const struct file_operations yaffs_file_operations = {
+	.read = do_sync_read,
+	.write = do_sync_write,
+	.aio_read = generic_file_aio_read,
+	.aio_write = generic_file_aio_write,
+	.mmap = generic_file_mmap,
+	.flush = yaffs_file_flush,
+	.fsync = yaffs_sync_object,
+	.sendfile = generic_file_sendfile,
+};
+
+#else
+
+static const struct file_operations yaffs_file_operations = {
+	.read = generic_file_read,
+	.write = generic_file_write,
+	.mmap = generic_file_mmap,
+	.flush = yaffs_file_flush,
+	.fsync = yaffs_sync_object,
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+	.sendfile = generic_file_sendfile,
+#endif
+};
+#endif
+
+
+
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 25))
+static void zero_user_segment(struct page *page, unsigned start, unsigned end)
+{
+	void *kaddr = kmap_atomic(page, KM_USER0);
+	memset(kaddr + start, 0, end - start);
+	kunmap_atomic(kaddr, KM_USER0);
+	flush_dcache_page(page);
+}
+#endif
+
+
+static int yaffs_vfs_setsize(struct inode *inode, loff_t newsize)
+{
+#ifdef YAFFS_USE_TRUNCATE_SETSIZE
+	truncate_setsize(inode, newsize);
+	return 0;
+#else
+	truncate_inode_pages(&inode->i_data, newsize);
+	return 0;
+#endif
+
+}
+
+
+static int yaffs_vfs_setattr(struct inode *inode, struct iattr *attr)
+{
+#ifdef YAFFS_USE_SETATTR_COPY
+	setattr_copy(inode, attr);
+	return 0;
+#else
+	return inode_setattr(inode, attr);
+#endif
+
+}
+
+static int yaffs_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	struct inode *inode = dentry->d_inode;
+	int error = 0;
+	struct yaffs_dev *dev;
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_setattr of object %d",
+		yaffs_inode_to_obj(inode)->obj_id);
+#if 0
+	/* Fail if a requested resize >= 2GB */
+	if (attr->ia_valid & ATTR_SIZE && (attr->ia_size >> 31))
+		error = -EINVAL;
+#endif
+
+	if (error == 0)
+		error = setattr_prepare(dentry, attr);
+	if (error == 0) {
+		int result;
+		if (!error) {
+			error = yaffs_vfs_setattr(inode, attr);
+			yaffs_trace(YAFFS_TRACE_OS, "inode_setattr called");
+			if (attr->ia_valid & ATTR_SIZE) {
+				yaffs_vfs_setsize(inode, attr->ia_size);
+				inode->i_blocks = (inode->i_size + 511) >> 9;
+			}
+		}
+		dev = yaffs_inode_to_obj(inode)->my_dev;
+		if (attr->ia_valid & ATTR_SIZE) {
+			yaffs_trace(YAFFS_TRACE_OS,
+				"resize to %d(%x)",
+				(int)(attr->ia_size),
+				(int)(attr->ia_size));
+		}
+		yaffs_gross_lock(dev);
+		result = yaffs_set_attribs(yaffs_inode_to_obj(inode), attr);
+		if (result == YAFFS_OK) {
+			error = 0;
+		} else {
+			error = -EPERM;
+		}
+		yaffs_gross_unlock(dev);
+
+	}
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_setattr done returning %d", error);
+
+	return error;
+}
+
+static int yaffs_setxattr(struct dentry *dentry, struct inode *inode,
+			  const char *name, const void *value, size_t size,
+			  int flags)
+{
+	int error = 0;
+	struct yaffs_dev *dev;
+	struct yaffs_obj *obj = yaffs_inode_to_obj(inode);
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_setxattr of object %d", obj->obj_id);
+
+	/* Currently we don't support posix ACL so never accept any settings
+	 * start with "system.posix_acl_".
+	 */
+	if (strncmp(name, "system.posix_acl_", 17))
+		error = -EOPNOTSUPP;
+
+	if (error == 0) {
+		int result;
+		dev = obj->my_dev;
+		yaffs_gross_lock(dev);
+		result = yaffs_set_xattrib(obj, name, value, size, flags);
+		if (result == YAFFS_OK)
+			error = 0;
+		else if (result < 0)
+			error = result;
+		yaffs_gross_unlock(dev);
+
+	}
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_setxattr done returning %d", error);
+
+	return error;
+}
+
+static ssize_t yaffs_getxattr(struct dentry * dentry, struct inode *inode,
+			      const char *name, void *buff, size_t size)
+{
+	int error = 0;
+	struct yaffs_dev *dev;
+	struct yaffs_obj *obj = yaffs_inode_to_obj(inode);
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_getxattr \"%s\" from object %d",
+		name, obj->obj_id);
+
+	if (error == 0) {
+		dev = obj->my_dev;
+		yaffs_gross_lock(dev);
+		error = yaffs_get_xattrib(obj, name, buff, size);
+		yaffs_gross_unlock(dev);
+
+	}
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_getxattr done returning %d", error);
+
+	return error;
+}
+
+static int yaffs_removexattr(struct dentry *dentry, const char *name)
+{
+	struct inode *inode = dentry->d_inode;
+	int error = 0;
+	struct yaffs_dev *dev;
+	struct yaffs_obj *obj = yaffs_inode_to_obj(inode);
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_removexattr of object %d", obj->obj_id);
+
+	if (error == 0) {
+		int result;
+		dev = obj->my_dev;
+		yaffs_gross_lock(dev);
+		result = yaffs_remove_xattrib(obj, name);
+		if (result == YAFFS_OK)
+			error = 0;
+		else if (result < 0)
+			error = result;
+		yaffs_gross_unlock(dev);
+
+	}
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_removexattr done returning %d", error);
+
+	return error;
+}
+
+static ssize_t yaffs_listxattr(struct dentry * dentry, char *buff, size_t size)
+{
+	struct inode *inode = dentry->d_inode;
+	int error = 0;
+	struct yaffs_dev *dev;
+	struct yaffs_obj *obj = yaffs_inode_to_obj(inode);
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_listxattr of object %d", obj->obj_id);
+
+	if (error == 0) {
+		dev = obj->my_dev;
+		yaffs_gross_lock(dev);
+		error = yaffs_list_xattrib(obj, buff, size);
+		yaffs_gross_unlock(dev);
+
+	}
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_listxattr done returning %d", error);
+
+	return error;
+}
+
+
+static const struct inode_operations yaffs_file_inode_operations = {
+	.setattr = yaffs_setattr,
+	.listxattr = yaffs_listxattr,
+};
+
+
+static int yaffs_readlink(struct dentry *dentry, char __user * buffer,
+			  int buflen)
+{
+	unsigned char *alias;
+	int ret;
+
+	struct yaffs_dev *dev = yaffs_dentry_to_obj(dentry)->my_dev;
+
+	yaffs_gross_lock(dev);
+
+	alias = yaffs_get_symlink_alias(yaffs_dentry_to_obj(dentry));
+
+	yaffs_gross_unlock(dev);
+
+	if (!alias)
+		return -ENOMEM;
+
+	ret = readlink_copy(buffer, buflen, alias);
+	kfree(alias);
+	return ret;
+}
+
+#if (YAFFS_NEW_FOLLOW_LINK == 1)
+static const char *yaffs_get_link(struct dentry *dentry, struct inode *inode,
+				  struct delayed_call *done)
+{
+	void *ret;
+#else
+static int yaffs_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	int ret
+#endif
+	unsigned char *alias;
+	int ret_int = 0;
+	struct yaffs_dev *dev;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	dev = yaffs_dentry_to_obj(dentry)->my_dev;
+	yaffs_gross_lock(dev);
+
+	alias = yaffs_get_symlink_alias(yaffs_dentry_to_obj(dentry));
+	yaffs_gross_unlock(dev);
+
+	if (!alias) {
+		ret_int = -ENOMEM;
+		goto out;
+	}
+#if (YAFFS_NEW_FOLLOW_LINK == 1)
+	set_delayed_call(done, kfree_link, alias);
+	ret = alias;
+out:
+	if (ret_int)
+		ret = ERR_PTR(ret_int);
+	return ret;
+#else
+	ret = vfs_follow_link(nd, alias);
+	kfree(alias);
+out:
+	if (ret_int)
+		ret = ret_int;
+	return ret;
+#endif
+}
+
+
+#ifdef YAFFS_HAS_PUT_INODE
+
+/* For now put inode is just for debugging
+ * Put inode is called when the inode **structure** is put.
+ */
+static void yaffs_put_inode(struct inode *inode)
+{
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_put_inode: ino %d, count %d"),
+		(int)inode->i_ino, atomic_read(&inode->i_count);
+
+}
+#endif
+
+static const struct inode_operations yaffs_symlink_inode_operations = {
+	.readlink = yaffs_readlink,
+#if (YAFFS_NEW_FOLLOW_LINK == 1)
+	.get_link = yaffs_get_link,
+#else
+	.follow_link = yaffs_follow_link,
+#endif
+	.setattr = yaffs_setattr,
+	.listxattr = yaffs_listxattr,
+};
+
+#ifdef YAFFS_USE_OWN_IGET
+
+static struct inode *yaffs_iget(struct super_block *sb, unsigned long ino)
+{
+	struct inode *inode;
+	struct yaffs_obj *obj;
+	struct yaffs_dev *dev = yaffs_super_to_dev(sb);
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_iget for %lu", ino);
+
+	inode = iget_locked(sb, ino);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	if (!(inode->i_state & I_NEW))
+		return inode;
+
+	/* NB This is called as a side effect of other functions, but
+	 * we had to release the lock to prevent deadlocks, so
+	 * need to lock again.
+	 */
+
+	yaffs_gross_lock(dev);
+
+	obj = yaffs_find_by_number(dev, inode->i_ino);
+
+	yaffs_fill_inode_from_obj(inode, obj);
+
+	yaffs_gross_unlock(dev);
+
+	unlock_new_inode(inode);
+	return inode;
+}
+
+#else
+
+static void yaffs_read_inode(struct inode *inode)
+{
+	/* NB This is called as a side effect of other functions, but
+	 * we had to release the lock to prevent deadlocks, so
+	 * need to lock again.
+	 */
+
+	struct yaffs_obj *obj;
+	struct yaffs_dev *dev = yaffs_super_to_dev(inode->i_sb);
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_read_inode for %d", (int)inode->i_ino);
+
+	if (current != yaffs_dev_to_lc(dev)->readdir_process)
+		yaffs_gross_lock(dev);
+
+	obj = yaffs_find_by_number(dev, inode->i_ino);
+
+	yaffs_fill_inode_from_obj(inode, obj);
+
+	if (current != yaffs_dev_to_lc(dev)->readdir_process)
+		yaffs_gross_unlock(dev);
+}
+
+#endif
+
+
+
+struct inode *yaffs_get_inode(struct super_block *sb, int mode, int dev,
+			      struct yaffs_obj *obj)
+{
+	struct inode *inode;
+
+	if (!sb) {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_get_inode for NULL super_block!!");
+		return NULL;
+
+	}
+
+	if (!obj) {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_get_inode for NULL object!!");
+		return NULL;
+
+	}
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_get_inode for object %d", obj->obj_id);
+
+	inode = Y_IGET(sb, obj->obj_id);
+	if (IS_ERR(inode))
+		return NULL;
+
+	/* NB Side effect: iget calls back to yaffs_read_inode(). */
+	/* iget also increments the inode's i_count */
+	/* NB You can't be holding gross_lock or deadlock will happen! */
+
+	return inode;
+}
+
+
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 29)
+#define YCRED(x) x
+#else
+#define YCRED(x) (x->cred)
+#endif
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0))
+static int yaffs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
+		       dev_t rdev)
+#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+static int yaffs_mknod(struct inode *dir, struct dentry *dentry, int mode,
+		       dev_t rdev)
+#else
+static int yaffs_mknod(struct inode *dir, struct dentry *dentry, int mode,
+		       int rdev)
+#endif
+{
+	struct inode *inode;
+
+	struct yaffs_obj *obj = NULL;
+	struct yaffs_dev *dev;
+
+	struct yaffs_obj *parent = yaffs_inode_to_obj(dir);
+
+	int error = -ENOSPC;
+
+	uid_t uid = YCRED_FSUID();
+	gid_t gid = (dir->i_mode & S_ISGID) ? i_gid_read(dir) : YCRED_FSGID();
+
+	if ((dir->i_mode & S_ISGID) && S_ISDIR(mode))
+		mode |= S_ISGID;
+
+	if (parent) {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_mknod: parent object %d type %d",
+			parent->obj_id, parent->variant_type);
+	} else {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_mknod: could not get parent object");
+		return -EPERM;
+	}
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_mknod: making oject for %s, mode %x dev %x",
+		dentry->d_name.name, mode, rdev);
+
+	dev = parent->my_dev;
+
+	yaffs_gross_lock(dev);
+
+	switch (mode & S_IFMT) {
+	default:
+		/* Special (socket, fifo, device...) */
+		yaffs_trace(YAFFS_TRACE_OS, "yaffs_mknod: making special");
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+		obj =
+		    yaffs_create_special(parent, dentry->d_name.name, mode, uid,
+					 gid, old_encode_dev(rdev));
+#else
+		obj =
+		    yaffs_create_special(parent, dentry->d_name.name, mode, uid,
+					 gid, rdev);
+#endif
+		break;
+	case S_IFREG:		/* file          */
+		yaffs_trace(YAFFS_TRACE_OS, "yaffs_mknod: making file");
+		obj = yaffs_create_file(parent, dentry->d_name.name, mode, uid,
+					gid);
+		break;
+	case S_IFDIR:		/* directory */
+		yaffs_trace(YAFFS_TRACE_OS, "yaffs_mknod: making directory");
+		obj = yaffs_create_dir(parent, dentry->d_name.name, mode,
+				       uid, gid);
+		break;
+	case S_IFLNK:		/* symlink */
+		yaffs_trace(YAFFS_TRACE_OS, "yaffs_mknod: making symlink");
+		obj = NULL;	/* Do we ever get here? */
+		break;
+	}
+
+	/* Can not call yaffs_get_inode() with gross lock held */
+	yaffs_gross_unlock(dev);
+
+	if (obj) {
+		inode = yaffs_get_inode(dir->i_sb, mode, rdev, obj);
+		d_instantiate(dentry, inode);
+		update_dir_time(dir);
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_mknod created object %d count = %d",
+			obj->obj_id, atomic_read(&inode->i_count));
+		error = 0;
+		yaffs_fill_inode_from_obj(dir, parent);
+	} else {
+		yaffs_trace(YAFFS_TRACE_OS, "yaffs_mknod failed making object");
+		error = -ENOMEM;
+	}
+
+	return error;
+}
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0))
+static int yaffs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+#else
+static int yaffs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+#endif
+{
+	int ret_val;
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_mkdir");
+	ret_val = yaffs_mknod(dir, dentry, mode | S_IFDIR, 0);
+	return ret_val;
+}
+
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 6, 0))
+static int yaffs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+			bool dummy)
+#elif (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0))
+static int yaffs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+			struct nameidata *n)
+#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+static int yaffs_create(struct inode *dir, struct dentry *dentry, int mode,
+			struct nameidata *n)
+#else
+static int yaffs_create(struct inode *dir, struct dentry *dentry, int mode)
+#endif
+{
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_create");
+	return yaffs_mknod(dir, dentry, mode | S_IFREG, 0);
+}
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 6, 0))
+static struct dentry *yaffs_lookup(struct inode *dir, struct dentry *dentry,
+				   unsigned int dummy)
+#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+static struct dentry *yaffs_lookup(struct inode *dir, struct dentry *dentry,
+				   struct nameidata *n)
+#else
+static struct dentry *yaffs_lookup(struct inode *dir, struct dentry *dentry)
+#endif
+{
+	struct yaffs_obj *obj;
+	struct inode *inode = NULL;	/* NCB 2.5/2.6 needs NULL here */
+
+	struct yaffs_dev *dev = yaffs_inode_to_obj(dir)->my_dev;
+
+	if (current != yaffs_dev_to_lc(dev)->readdir_process)
+		yaffs_gross_lock(dev);
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_lookup for %d:%s",
+		yaffs_inode_to_obj(dir)->obj_id, dentry->d_name.name);
+
+	obj = yaffs_find_by_name(yaffs_inode_to_obj(dir), dentry->d_name.name);
+
+	obj = yaffs_get_equivalent_obj(obj);	/* in case it was a hardlink */
+
+	/* Can't hold gross lock when calling yaffs_get_inode() */
+	if (current != yaffs_dev_to_lc(dev)->readdir_process)
+		yaffs_gross_unlock(dev);
+
+	if (obj) {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_lookup found %d", obj->obj_id);
+
+		inode = yaffs_get_inode(dir->i_sb, obj->yst_mode, 0, obj);
+	} else {
+		yaffs_trace(YAFFS_TRACE_OS, "yaffs_lookup not found");
+
+	}
+
+/* added NCB for 2.5/6 compatability - forces add even if inode is
+ * NULL which creates dentry hash */
+	d_add(dentry, inode);
+
+	return NULL;
+}
+
+/*
+ * Create a link...
+ */
+static int yaffs_link(struct dentry *old_dentry, struct inode *dir,
+		      struct dentry *dentry)
+{
+	struct inode *inode = old_dentry->d_inode;
+	struct yaffs_obj *obj = NULL;
+	struct yaffs_obj *link = NULL;
+	struct yaffs_dev *dev;
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_link");
+
+	obj = yaffs_inode_to_obj(inode);
+	dev = obj->my_dev;
+
+	yaffs_gross_lock(dev);
+
+	if (!S_ISDIR(inode->i_mode))	/* Don't link directories */
+		link =
+		    yaffs_link_obj(yaffs_inode_to_obj(dir), dentry->d_name.name,
+				   obj);
+
+	if (link) {
+		set_nlink(old_dentry->d_inode, yaffs_get_obj_link_count(obj));
+		d_instantiate(dentry, old_dentry->d_inode);
+		atomic_inc(&old_dentry->d_inode->i_count);
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_link link count %d i_count %d",
+			old_dentry->d_inode->i_nlink,
+			atomic_read(&old_dentry->d_inode->i_count));
+	}
+
+	yaffs_gross_unlock(dev);
+
+	if (link) {
+		update_dir_time(dir);
+		return 0;
+	}
+
+	return -EPERM;
+}
+
+static int yaffs_symlink(struct inode *dir, struct dentry *dentry,
+			 const char *symname)
+{
+	struct yaffs_obj *obj;
+	struct yaffs_dev *dev;
+	uid_t uid = YCRED_FSUID();
+	gid_t gid = (dir->i_mode & S_ISGID) ? i_gid_read(dir) : YCRED_FSGID();
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_symlink");
+
+	if (strnlen(dentry->d_name.name, YAFFS_MAX_NAME_LENGTH + 1) >
+				YAFFS_MAX_NAME_LENGTH)
+		return -ENAMETOOLONG;
+
+	if (strnlen(symname, YAFFS_MAX_ALIAS_LENGTH + 1) >
+				YAFFS_MAX_ALIAS_LENGTH)
+		return -ENAMETOOLONG;
+
+	dev = yaffs_inode_to_obj(dir)->my_dev;
+	yaffs_gross_lock(dev);
+	obj = yaffs_create_symlink(yaffs_inode_to_obj(dir), dentry->d_name.name,
+				   S_IFLNK | S_IRWXUGO, uid, gid, symname);
+	yaffs_gross_unlock(dev);
+
+	if (obj) {
+		struct inode *inode;
+
+		inode = yaffs_get_inode(dir->i_sb, obj->yst_mode, 0, obj);
+		d_instantiate(dentry, inode);
+		update_dir_time(dir);
+		yaffs_trace(YAFFS_TRACE_OS, "symlink created OK");
+		return 0;
+	} else {
+		yaffs_trace(YAFFS_TRACE_OS, "symlink not created");
+	}
+
+	return -ENOMEM;
+}
+
+/*
+ * The VFS layer already does all the dentry stuff for rename.
+ *
+ * NB: POSIX says you can rename an object over an old object of the same name
+ */
+static int yaffs_rename(struct inode *old_dir, struct dentry *old_dentry,
+			struct inode *new_dir, struct dentry *new_dentry,
+			unsigned int flags)
+{
+	struct yaffs_dev *dev;
+	int ret_val = YAFFS_FAIL;
+	struct yaffs_obj *target;
+
+	if (flags)
+		return -EINVAL;
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_rename");
+	dev = yaffs_inode_to_obj(old_dir)->my_dev;
+
+	yaffs_gross_lock(dev);
+
+	/* Check if the target is an existing directory that is not empty. */
+	target = yaffs_find_by_name(yaffs_inode_to_obj(new_dir),
+				    new_dentry->d_name.name);
+
+	if (target && target->variant_type == YAFFS_OBJECT_TYPE_DIRECTORY &&
+	    !list_empty(&target->variant.dir_variant.children)) {
+
+		yaffs_trace(YAFFS_TRACE_OS, "target is non-empty dir");
+
+		ret_val = YAFFS_FAIL;
+	} else {
+		/* Now does unlinking internally using shadowing mechanism */
+		yaffs_trace(YAFFS_TRACE_OS, "calling yaffs_rename_obj");
+
+		ret_val = yaffs_rename_obj(yaffs_inode_to_obj(old_dir),
+					   old_dentry->d_name.name,
+					   yaffs_inode_to_obj(new_dir),
+					   new_dentry->d_name.name);
+	}
+	yaffs_gross_unlock(dev);
+
+	if (ret_val == YAFFS_OK) {
+		if (target)
+			inode_dec_link_count(new_dentry->d_inode);
+
+		update_dir_time(old_dir);
+		if (old_dir != new_dir)
+			update_dir_time(new_dir);
+		return 0;
+	} else {
+		return -ENOTEMPTY;
+	}
+}
+
+
+
+
+static int yaffs_unlink(struct inode *dir, struct dentry *dentry)
+{
+	int ret_val;
+
+	struct yaffs_dev *dev;
+	struct yaffs_obj *obj;
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_unlink %d:%s",
+		(int)(dir->i_ino), dentry->d_name.name);
+	obj = yaffs_inode_to_obj(dir);
+	dev = obj->my_dev;
+
+	yaffs_gross_lock(dev);
+
+	ret_val = yaffs_unlinker(obj, dentry->d_name.name);
+
+	if (ret_val == YAFFS_OK) {
+		inode_dec_link_count(dentry->d_inode);
+		dir->i_version++;
+		yaffs_gross_unlock(dev);
+		update_dir_time(dir);
+		return 0;
+	}
+	yaffs_gross_unlock(dev);
+	return -ENOTEMPTY;
+}
+
+
+
+static const struct inode_operations yaffs_dir_inode_operations = {
+	.create = yaffs_create,
+	.lookup = yaffs_lookup,
+	.link = yaffs_link,
+	.unlink = yaffs_unlink,
+	.symlink = yaffs_symlink,
+	.mkdir = yaffs_mkdir,
+	.rmdir = yaffs_unlink,
+	.mknod = yaffs_mknod,
+	.rename = yaffs_rename,
+	.setattr = yaffs_setattr,
+	.listxattr = yaffs_listxattr,
+};
+
+/*-----------------------------------------------------------------*/
+/* Directory search context allows us to unlock access to yaffs during
+ * filldir without causing problems with the directory being modified.
+ * This is similar to the tried and tested mechanism used in yaffs direct.
+ *
+ * A search context iterates along a doubly linked list of siblings in the
+ * directory. If the iterating object is deleted then this would corrupt
+ * the list iteration, likely causing a crash. The search context avoids
+ * this by using the remove_obj_fn to move the search context to the
+ * next object before the object is deleted.
+ *
+ * Many readdirs (and thus seach conexts) may be alive simulateously so
+ * each struct yaffs_dev has a list of these.
+ *
+ * A seach context lives for the duration of a readdir.
+ *
+ * All these functions must be called while yaffs is locked.
+ */
+
+struct yaffs_search_context {
+	struct yaffs_dev *dev;
+	struct yaffs_obj *dir_obj;
+	struct yaffs_obj *next_return;
+	struct list_head others;
+};
+
+/*
+ * yaffs_new_search() creates a new search context, initialises it and
+ * adds it to the device's search context list.
+ *
+ * Called at start of readdir.
+ */
+static struct yaffs_search_context *yaffs_new_search(struct yaffs_obj *dir)
+{
+	struct yaffs_dev *dev = dir->my_dev;
+	struct yaffs_search_context *sc =
+	    kmalloc(sizeof(struct yaffs_search_context), GFP_NOFS);
+	if (sc) {
+		sc->dir_obj = dir;
+		sc->dev = dev;
+		if (list_empty(&sc->dir_obj->variant.dir_variant.children))
+			sc->next_return = NULL;
+		else
+			sc->next_return =
+			    list_entry(dir->variant.dir_variant.children.next,
+				       struct yaffs_obj, siblings);
+		INIT_LIST_HEAD(&sc->others);
+		list_add(&sc->others, &(yaffs_dev_to_lc(dev)->search_contexts));
+	}
+	return sc;
+}
+
+/*
+ * yaffs_search_end() disposes of a search context and cleans up.
+ */
+static void yaffs_search_end(struct yaffs_search_context *sc)
+{
+	if (sc) {
+		list_del(&sc->others);
+		kfree(sc);
+	}
+}
+
+/*
+ * yaffs_search_advance() moves a search context to the next object.
+ * Called when the search iterates or when an object removal causes
+ * the search context to be moved to the next object.
+ */
+static void yaffs_search_advance(struct yaffs_search_context *sc)
+{
+	if (!sc)
+		return;
+
+	if (sc->next_return == NULL ||
+	    list_empty(&sc->dir_obj->variant.dir_variant.children))
+		sc->next_return = NULL;
+	else {
+		struct list_head *next = sc->next_return->siblings.next;
+
+		if (next == &sc->dir_obj->variant.dir_variant.children)
+			sc->next_return = NULL;	/* end of list */
+		else
+			sc->next_return =
+			    list_entry(next, struct yaffs_obj, siblings);
+	}
+}
+
+/*
+ * yaffs_remove_obj_callback() is called when an object is unlinked.
+ * We check open search contexts and advance any which are currently
+ * on the object being iterated.
+ */
+static void yaffs_remove_obj_callback(struct yaffs_obj *obj)
+{
+
+	struct list_head *i;
+	struct yaffs_search_context *sc;
+	struct list_head *search_contexts =
+	    &(yaffs_dev_to_lc(obj->my_dev)->search_contexts);
+
+	/* Iterate through the directory search contexts.
+	 * If any are currently on the object being removed, then advance
+	 * the search context to the next object to prevent a hanging pointer.
+	 */
+	list_for_each(i, search_contexts) {
+		sc = list_entry(i, struct yaffs_search_context, others);
+		if (sc->next_return == obj)
+			yaffs_search_advance(sc);
+	}
+
+}
+
+
+/*-----------------------------------------------------------------*/
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 12, 0))
+static int yaffs_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct yaffs_obj *obj;
+	struct yaffs_dev *dev;
+	struct yaffs_search_context *sc;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	unsigned long offset, curoffs;
+	struct yaffs_obj *l;
+	int ret_val = 0;
+
+	char name[YAFFS_MAX_NAME_LENGTH + 1];
+
+	obj = yaffs_dentry_to_obj(file->f_path.dentry);
+	dev = obj->my_dev;
+
+	yaffs_gross_lock(dev);
+
+	yaffs_dev_to_lc(dev)->readdir_process = current;
+
+	offset = ctx->pos;
+
+	sc = yaffs_new_search(obj);
+	if (!sc) {
+		ret_val = -ENOMEM;
+		goto out;
+	}
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_readdir: starting at %d", (int)offset);
+
+	if (offset == 0) {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_readdir: entry . ino %d",
+			(int)inode->i_ino);
+		yaffs_gross_unlock(dev);
+		if (!dir_emit_dot(file, ctx)) {
+			yaffs_gross_lock(dev);
+			goto out;
+		}
+		yaffs_gross_lock(dev);
+		offset++;
+		ctx->pos++;
+	}
+	if (offset == 1) {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_readdir: entry .. ino %d",
+			(int)file->f_path.dentry->d_parent->d_inode->i_ino);
+		yaffs_gross_unlock(dev);
+		if (!dir_emit_dotdot(file, ctx)) {
+			yaffs_gross_lock(dev);
+			goto out;
+		}
+		yaffs_gross_lock(dev);
+		offset++;
+		ctx->pos++;
+	}
+
+	curoffs = 1;
+
+	/* If the directory has changed since the open or last call to
+	   readdir, rewind to after the 2 canned entries. */
+	if (file->f_version != inode->i_version) {
+		offset = 2;
+		ctx->pos = offset;
+		file->f_version = inode->i_version;
+	}
+
+	while (sc->next_return) {
+		curoffs++;
+		l = sc->next_return;
+		if (curoffs >= offset) {
+			int this_inode = yaffs_get_obj_inode(l);
+			int this_type = yaffs_get_obj_type(l);
+
+			yaffs_get_obj_name(l, name, YAFFS_MAX_NAME_LENGTH + 1);
+			yaffs_trace(YAFFS_TRACE_OS,
+				"yaffs_readdir: %s inode %d",
+				name, yaffs_get_obj_inode(l));
+
+			yaffs_gross_unlock(dev);
+
+			if (!dir_emit(ctx, name, strlen(name),
+				      this_inode, this_type)) {
+				yaffs_gross_lock(dev);
+				goto out;
+			}
+
+			yaffs_gross_lock(dev);
+
+			offset++;
+			ctx->pos++;
+		}
+		yaffs_search_advance(sc);
+	}
+
+out:
+	yaffs_search_end(sc);
+	yaffs_dev_to_lc(dev)->readdir_process = NULL;
+	yaffs_gross_unlock(dev);
+
+	return ret_val;
+}
+#else
+static int yaffs_readdir(struct file *f, void *dirent, filldir_t filldir)
+{
+	struct yaffs_obj *obj;
+	struct yaffs_dev *dev;
+	struct yaffs_search_context *sc;
+	struct inode *inode = f->f_path.dentry->d_inode;
+	unsigned long offset, curoffs;
+	struct yaffs_obj *l;
+	int ret_val = 0;
+
+	char name[YAFFS_MAX_NAME_LENGTH + 1];
+
+	obj = yaffs_dentry_to_obj(f->f_path.dentry);
+	dev = obj->my_dev;
+
+	yaffs_gross_lock(dev);
+
+	yaffs_dev_to_lc(dev)->readdir_process = current;
+
+	offset = f->f_pos;
+
+	sc = yaffs_new_search(obj);
+	if (!sc) {
+		ret_val = -ENOMEM;
+		goto out;
+	}
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_readdir: starting at %d", (int)offset);
+
+	if (offset == 0) {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_readdir: entry . ino %d",
+			(int)inode->i_ino);
+		yaffs_gross_unlock(dev);
+		if (filldir(dirent, ".", 1, offset, inode->i_ino, DT_DIR) < 0) {
+			yaffs_gross_lock(dev);
+			goto out;
+		}
+		yaffs_gross_lock(dev);
+		offset++;
+		f->f_pos++;
+	}
+	if (offset == 1) {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_readdir: entry .. ino %d",
+			(int)f->f_path.dentry->d_parent->d_inode->i_ino);
+		yaffs_gross_unlock(dev);
+		if (filldir(dirent, "..", 2, offset,
+			    f->f_path.dentry->d_parent->d_inode->i_ino,
+			    DT_DIR) < 0) {
+			yaffs_gross_lock(dev);
+			goto out;
+		}
+		yaffs_gross_lock(dev);
+		offset++;
+		f->f_pos++;
+	}
+
+	curoffs = 1;
+
+	/* If the directory has changed since the open or last call to
+	   readdir, rewind to after the 2 canned entries. */
+	if (f->f_version != inode->i_version) {
+		offset = 2;
+		f->f_pos = offset;
+		f->f_version = inode->i_version;
+	}
+
+	while (sc->next_return) {
+		curoffs++;
+		l = sc->next_return;
+		if (curoffs >= offset) {
+			int this_inode = yaffs_get_obj_inode(l);
+			int this_type = yaffs_get_obj_type(l);
+
+			yaffs_get_obj_name(l, name, YAFFS_MAX_NAME_LENGTH + 1);
+			yaffs_trace(YAFFS_TRACE_OS,
+				"yaffs_readdir: %s inode %d",
+				name, yaffs_get_obj_inode(l));
+
+			yaffs_gross_unlock(dev);
+
+			if (filldir(dirent,
+				    name,
+				    strlen(name),
+				    offset, this_inode, this_type) < 0) {
+				yaffs_gross_lock(dev);
+				goto out;
+			}
+
+			yaffs_gross_lock(dev);
+
+			offset++;
+			f->f_pos++;
+		}
+		yaffs_search_advance(sc);
+	}
+
+out:
+	yaffs_search_end(sc);
+	yaffs_dev_to_lc(dev)->readdir_process = NULL;
+	yaffs_gross_unlock(dev);
+
+	return ret_val;
+}
+#endif
+
+static const struct file_operations yaffs_dir_operations = {
+	.read = generic_read_dir,
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 12, 0))
+	.iterate = yaffs_readdir,
+#else
+	.readdir = yaffs_readdir,
+#endif
+	.fsync = yaffs_sync_object,
+	.llseek = generic_file_llseek,
+};
+
+static void yaffs_fill_inode_from_obj(struct inode *inode,
+				      struct yaffs_obj *obj)
+{
+	if (inode && obj) {
+
+		/* Check mode against the variant type and attempt to repair if broken. */
+		u32 mode = obj->yst_mode;
+		switch (obj->variant_type) {
+		case YAFFS_OBJECT_TYPE_FILE:
+			if (!S_ISREG(mode)) {
+				obj->yst_mode &= ~S_IFMT;
+				obj->yst_mode |= S_IFREG;
+			}
+
+			break;
+		case YAFFS_OBJECT_TYPE_SYMLINK:
+			if (!S_ISLNK(mode)) {
+				obj->yst_mode &= ~S_IFMT;
+				obj->yst_mode |= S_IFLNK;
+			}
+
+			break;
+		case YAFFS_OBJECT_TYPE_DIRECTORY:
+			if (!S_ISDIR(mode)) {
+				obj->yst_mode &= ~S_IFMT;
+				obj->yst_mode |= S_IFDIR;
+			}
+
+			break;
+		case YAFFS_OBJECT_TYPE_UNKNOWN:
+		case YAFFS_OBJECT_TYPE_HARDLINK:
+		case YAFFS_OBJECT_TYPE_SPECIAL:
+		default:
+			/* TODO? */
+			break;
+		}
+
+		inode->i_flags |= S_NOATIME;
+
+		inode->i_ino = obj->obj_id;
+		inode->i_mode = obj->yst_mode;
+		i_uid_write(inode, obj->yst_uid);
+		i_gid_write(inode, obj->yst_gid);
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 19))
+		inode->i_blksize = inode->i_sb->s_blocksize;
+#endif
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+
+		inode->i_rdev = old_decode_dev(obj->yst_rdev);
+		inode->i_atime.tv_sec = (time_t) (obj->yst_atime);
+		inode->i_atime.tv_nsec = 0;
+		inode->i_mtime.tv_sec = (time_t) obj->yst_mtime;
+		inode->i_mtime.tv_nsec = 0;
+		inode->i_ctime.tv_sec = (time_t) obj->yst_ctime;
+		inode->i_ctime.tv_nsec = 0;
+#else
+		inode->i_rdev = obj->yst_rdev;
+		inode->i_atime = obj->yst_atime;
+		inode->i_mtime = obj->yst_mtime;
+		inode->i_ctime = obj->yst_ctime;
+#endif
+		inode->i_size = yaffs_get_obj_length(obj);
+		inode->i_blocks = (inode->i_size + 511) >> 9;
+
+		set_nlink(inode, yaffs_get_obj_link_count(obj));
+
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_fill_inode mode %x uid %d gid %d size %lld count %d",
+			inode->i_mode, i_uid_read(inode), i_gid_read(inode),
+			inode->i_size, atomic_read(&inode->i_count));
+
+		switch (obj->yst_mode & S_IFMT) {
+		default:	/* fifo, device or socket */
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+			init_special_inode(inode, obj->yst_mode,
+					   old_decode_dev(obj->yst_rdev));
+#else
+			init_special_inode(inode, obj->yst_mode,
+					   (dev_t) (obj->yst_rdev));
+#endif
+			break;
+		case S_IFREG:	/* file */
+			inode->i_op = &yaffs_file_inode_operations;
+			inode->i_fop = &yaffs_file_operations;
+			inode->i_mapping->a_ops =
+			    &yaffs_file_address_operations;
+			break;
+		case S_IFDIR:	/* directory */
+			inode->i_op = &yaffs_dir_inode_operations;
+			inode->i_fop = &yaffs_dir_operations;
+			break;
+		case S_IFLNK:	/* symlink */
+			inode->i_op = &yaffs_symlink_inode_operations;
+			break;
+		}
+
+		yaffs_inode_to_obj_lv(inode) = obj;
+
+		obj->my_inode = inode;
+
+	} else {
+		yaffs_trace(YAFFS_TRACE_OS,
+			"yaffs_fill_inode invalid parameters");
+	}
+
+}
+
+
+
+/*
+ * yaffs background thread functions .
+ * yaffs_bg_thread_fn() the thread function
+ * yaffs_bg_start() launches the background thread.
+ * yaffs_bg_stop() cleans up the background thread.
+ *
+ * NB:
+ * The thread should only run after the yaffs is initialised
+ * The thread should be stopped before yaffs is unmounted.
+ * The thread should not do any writing while the fs is in read only.
+ */
+
+static unsigned yaffs_bg_gc_urgency(struct yaffs_dev *dev)
+{
+	unsigned erased_chunks =
+	    dev->n_erased_blocks * dev->param.chunks_per_block;
+	struct yaffs_linux_context *context = yaffs_dev_to_lc(dev);
+	unsigned scattered = 0;	/* Free chunks not in an erased block */
+
+	if (erased_chunks < dev->n_free_chunks)
+		scattered = (dev->n_free_chunks - erased_chunks);
+
+	if (!context->bg_running)
+		return 0;
+	else if (scattered < (dev->param.chunks_per_block * 2))
+		return 0;
+	else if (erased_chunks > dev->n_free_chunks / 2)
+		return 0;
+	else if (erased_chunks > dev->n_free_chunks / 4)
+		return 1;
+	else
+		return 2;
+}
+
+#ifdef YAFFS_COMPILE_BACKGROUND
+
+void yaffs_background_waker(unsigned long data)
+{
+	wake_up_process((struct task_struct *)data);
+}
+
+static int yaffs_bg_thread_fn(void *data)
+{
+	struct yaffs_dev *dev = (struct yaffs_dev *)data;
+	struct yaffs_linux_context *context = yaffs_dev_to_lc(dev);
+	unsigned long now = jiffies;
+	unsigned long next_dir_update = now;
+	unsigned long next_gc = now;
+	unsigned long expires;
+	unsigned int urgency;
+
+	int gc_result;
+	struct timer_list timer;
+
+	yaffs_trace(YAFFS_TRACE_BACKGROUND,
+		"yaffs_background starting for dev %p", (void *)dev);
+
+#ifdef YAFFS_COMPILE_FREEZER
+	set_freezable();
+#endif
+	while (context->bg_running) {
+		yaffs_trace(YAFFS_TRACE_BACKGROUND, "yaffs_background");
+
+		if (kthread_should_stop())
+			break;
+
+#ifdef YAFFS_COMPILE_FREEZER
+		if (try_to_freeze())
+			continue;
+#endif
+		yaffs_gross_lock(dev);
+
+		now = jiffies;
+
+		if (time_after(now, next_dir_update) && yaffs_bg_enable) {
+			yaffs_update_dirty_dirs(dev);
+			next_dir_update = now + HZ;
+		}
+
+		if (time_after(now, next_gc) && yaffs_bg_enable) {
+			if (!dev->is_checkpointed) {
+				urgency = yaffs_bg_gc_urgency(dev);
+				gc_result = yaffs_bg_gc(dev, urgency);
+				if (urgency > 1)
+					next_gc = now + HZ / 20 + 1;
+				else if (urgency > 0)
+					next_gc = now + HZ / 10 + 1;
+				else
+					next_gc = now + HZ * 2;
+			} else	{
+			        /*
+				 * gc not running so set to next_dir_update
+				 * to cut down on wake ups
+				 */
+				next_gc = next_dir_update;
+                        }
+		}
+		yaffs_gross_unlock(dev);
+#if 1
+		expires = next_dir_update;
+		if (time_before(next_gc, expires))
+			expires = next_gc;
+		if (time_before(expires, now))
+			expires = now + HZ;
+
+		Y_INIT_TIMER(&timer);
+		timer.expires = expires + 1;
+		timer.data = (unsigned long)current;
+		timer.function = yaffs_background_waker;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		add_timer(&timer);
+		schedule();
+		del_timer_sync(&timer);
+#else
+		msleep(10);
+#endif
+	}
+
+	return 0;
+}
+
+static int yaffs_bg_start(struct yaffs_dev *dev)
+{
+	int retval = 0;
+	struct yaffs_linux_context *context = yaffs_dev_to_lc(dev);
+
+	if (dev->read_only)
+		return -1;
+
+	context->bg_running = 1;
+
+	context->bg_thread = kthread_run(yaffs_bg_thread_fn,
+					 (void *)dev, "yaffs-bg-%d",
+					 context->mount_id);
+
+	if (IS_ERR(context->bg_thread)) {
+		retval = PTR_ERR(context->bg_thread);
+		context->bg_thread = NULL;
+		context->bg_running = 0;
+	}
+	return retval;
+}
+
+static void yaffs_bg_stop(struct yaffs_dev *dev)
+{
+	struct yaffs_linux_context *ctxt = yaffs_dev_to_lc(dev);
+
+	ctxt->bg_running = 0;
+
+	if (ctxt->bg_thread) {
+		kthread_stop(ctxt->bg_thread);
+		ctxt->bg_thread = NULL;
+	}
+}
+#else
+static int yaffs_bg_thread_fn(void *data)
+{
+	return 0;
+}
+
+static int yaffs_bg_start(struct yaffs_dev *dev)
+{
+	return 0;
+}
+
+static void yaffs_bg_stop(struct yaffs_dev *dev)
+{
+}
+#endif
+
+
+static void yaffs_flush_inodes(struct super_block *sb)
+{
+	struct inode *iptr;
+	struct yaffs_obj *obj;
+
+	list_for_each_entry(iptr, &sb->s_inodes, i_sb_list) {
+		obj = yaffs_inode_to_obj(iptr);
+		if (obj) {
+			yaffs_trace(YAFFS_TRACE_OS,
+				"flushing obj %d",
+				obj->obj_id);
+			yaffs_flush_file(obj, 1, 0);
+		}
+	}
+}
+
+static void yaffs_flush_super(struct super_block *sb, int do_checkpoint)
+{
+	struct yaffs_dev *dev = yaffs_super_to_dev(sb);
+	if (!dev)
+		return;
+
+	yaffs_flush_inodes(sb);
+	yaffs_update_dirty_dirs(dev);
+	yaffs_flush_whole_cache(dev);
+	if (do_checkpoint)
+		yaffs_checkpoint_save(dev);
+}
+
+static LIST_HEAD(yaffs_context_list);
+struct mutex yaffs_context_lock;
+
+static void yaffs_put_super(struct super_block *sb)
+{
+	struct yaffs_dev *dev = yaffs_super_to_dev(sb);
+	struct mtd_info *mtd = yaffs_dev_to_mtd(dev);
+
+	yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_ALWAYS,
+			"yaffs_put_super");
+
+	yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_BACKGROUND,
+		"Shutting down yaffs background thread");
+	yaffs_bg_stop(dev);
+	yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_BACKGROUND,
+		"yaffs background thread shut down");
+
+	yaffs_gross_lock(dev);
+
+	yaffs_flush_super(sb, 1);
+
+	yaffs_deinitialise(dev);
+
+	yaffs_gross_unlock(dev);
+
+	mutex_lock(&yaffs_context_lock);
+	list_del_init(&(yaffs_dev_to_lc(dev)->context_list));
+	mutex_unlock(&yaffs_context_lock);
+
+	if (yaffs_dev_to_lc(dev)->spare_buffer) {
+		kfree(yaffs_dev_to_lc(dev)->spare_buffer);
+		yaffs_dev_to_lc(dev)->spare_buffer = NULL;
+	}
+
+	if (dev->os_context)
+		kfree(dev->os_context);
+
+	kfree(dev);
+
+	yaffs_put_mtd_device(mtd);
+
+	yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_ALWAYS,
+			"yaffs_put_super done");
+}
+
+
+static unsigned yaffs_gc_control_callback(struct yaffs_dev *dev)
+{
+	return yaffs_gc_control;
+}
+
+
+#ifdef YAFFS_COMPILE_EXPORTFS
+
+static struct inode *yaffs2_nfs_get_inode(struct super_block *sb, uint64_t ino,
+					  uint32_t generation)
+{
+	return Y_IGET(sb, ino);
+}
+
+static struct dentry *yaffs2_fh_to_dentry(struct super_block *sb,
+					  struct fid *fid, int fh_len,
+					  int fh_type)
+{
+	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
+				    yaffs2_nfs_get_inode);
+}
+
+static struct dentry *yaffs2_fh_to_parent(struct super_block *sb,
+					  struct fid *fid, int fh_len,
+					  int fh_type)
+{
+	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
+				    yaffs2_nfs_get_inode);
+}
+
+struct dentry *yaffs2_get_parent(struct dentry *dentry)
+{
+
+	struct super_block *sb = dentry->d_inode->i_sb;
+	struct dentry *parent = ERR_PTR(-ENOENT);
+	struct inode *inode;
+	unsigned long parent_ino;
+	struct yaffs_obj *d_obj;
+	struct yaffs_obj *parent_obj;
+
+	d_obj = yaffs_inode_to_obj(dentry->d_inode);
+
+	if (d_obj) {
+		parent_obj = d_obj->parent;
+		if (parent_obj) {
+			parent_ino = yaffs_get_obj_inode(parent_obj);
+			inode = Y_IGET(sb, parent_ino);
+
+			if (IS_ERR(inode)) {
+				parent = ERR_CAST(inode);
+			} else {
+				parent = d_obtain_alias(inode);
+				if (!IS_ERR(parent)) {
+					parent = ERR_PTR(-ENOMEM);
+					iput(inode);
+				}
+			}
+		}
+	}
+
+	return parent;
+}
+
+/* Just declare a zero structure as a NULL value implies
+ * using the default functions of exportfs.
+ */
+
+static struct export_operations yaffs_export_ops = {
+	.fh_to_dentry = yaffs2_fh_to_dentry,
+	.fh_to_parent = yaffs2_fh_to_parent,
+	.get_parent = yaffs2_get_parent,
+};
+
+#endif
+
+static void yaffs_unstitch_obj(struct inode *inode, struct yaffs_obj *obj)
+{
+	/* Clear the association between the inode and
+	 * the struct yaffs_obj.
+	 */
+	obj->my_inode = NULL;
+	yaffs_inode_to_obj_lv(inode) = NULL;
+
+	/* If the object freeing was deferred, then the real
+	 * free happens now.
+	 * This should fix the inode inconsistency problem.
+	 */
+	yaffs_handle_defered_free(obj);
+}
+
+#ifdef YAFFS_HAS_EVICT_INODE
+/* yaffs_evict_inode combines into one operation what was previously done in
+ * yaffs_clear_inode() and yaffs_delete_inode()
+ *
+ */
+static void yaffs_evict_inode(struct inode *inode)
+{
+	struct yaffs_obj *obj;
+	struct yaffs_dev *dev;
+	int deleteme = 0;
+
+	obj = yaffs_inode_to_obj(inode);
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_evict_inode: ino %d, count %d %s",
+		(int)inode->i_ino, atomic_read(&inode->i_count),
+		obj ? "object exists" : "null object");
+
+	if (!inode->i_nlink && !is_bad_inode(inode))
+		deleteme = 1;
+	truncate_inode_pages(&inode->i_data, 0);
+	Y_CLEAR_INODE(inode);
+
+	if (deleteme && obj) {
+		dev = obj->my_dev;
+		yaffs_gross_lock(dev);
+		yaffs_del_obj(obj);
+		yaffs_gross_unlock(dev);
+	}
+	if (obj) {
+		dev = obj->my_dev;
+		yaffs_gross_lock(dev);
+		yaffs_unstitch_obj(inode, obj);
+		yaffs_gross_unlock(dev);
+	}
+}
+#else
+
+/* clear is called to tell the fs to release any per-inode data it holds.
+ * The object might still exist on disk and is just being thrown out of the cache
+ * or else the object has actually been deleted and we're being called via
+ * the chain
+ *   yaffs_delete_inode() -> clear_inode()->yaffs_clear_inode()
+ */
+
+static void yaffs_clear_inode(struct inode *inode)
+{
+	struct yaffs_obj *obj;
+	struct yaffs_dev *dev;
+
+	obj = yaffs_inode_to_obj(inode);
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_clear_inode: ino %d, count %d %s",
+		(int)inode->i_ino, atomic_read(&inode->i_count),
+		obj ? "object exists" : "null object");
+
+	if (obj) {
+		dev = obj->my_dev;
+		yaffs_gross_lock(dev);
+		yaffs_unstitch_obj(inode, obj);
+		yaffs_gross_unlock(dev);
+	}
+
+}
+
+/* delete is called when the link count is zero and the inode
+ * is put (ie. nobody wants to know about it anymore, time to
+ * delete the file).
+ * NB Must call clear_inode()
+ */
+static void yaffs_delete_inode(struct inode *inode)
+{
+	struct yaffs_obj *obj = yaffs_inode_to_obj(inode);
+	struct yaffs_dev *dev;
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_delete_inode: ino %d, count %d %s",
+		(int)inode->i_ino, atomic_read(&inode->i_count),
+		obj ? "object exists" : "null object");
+
+	if (obj) {
+		dev = obj->my_dev;
+		yaffs_gross_lock(dev);
+		yaffs_del_obj(obj);
+		yaffs_gross_unlock(dev);
+	}
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 13))
+	truncate_inode_pages(&inode->i_data, 0);
+#endif
+	clear_inode(inode);
+}
+#endif
+
+
+
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17))
+static int yaffs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct yaffs_dev *dev = yaffs_dentry_to_obj(dentry)->my_dev;
+	struct super_block *sb = dentry->d_sb;
+#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+static int yaffs_statfs(struct super_block *sb, struct kstatfs *buf)
+{
+	struct yaffs_dev *dev = yaffs_super_to_dev(sb);
+#else
+static int yaffs_statfs(struct super_block *sb, struct statfs *buf)
+{
+	struct yaffs_dev *dev = yaffs_super_to_dev(sb);
+#endif
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_statfs");
+
+	yaffs_gross_lock(dev);
+
+	buf->f_type = YAFFS_MAGIC;
+	buf->f_bsize = sb->s_blocksize;
+	buf->f_namelen = 255;
+
+	if (dev->data_bytes_per_chunk & (dev->data_bytes_per_chunk - 1)) {
+		/* Do this if chunk size is not a power of 2 */
+
+		uint64_t bytes_in_dev;
+		uint64_t bytes_free;
+
+		bytes_in_dev =
+		    ((uint64_t)
+		     ((dev->param.end_block - dev->param.start_block +
+		       1))) * ((uint64_t) (dev->param.chunks_per_block *
+					   dev->data_bytes_per_chunk));
+
+		do_div(bytes_in_dev, sb->s_blocksize);	/* bytes_in_dev becomes the number of blocks */
+		buf->f_blocks = bytes_in_dev;
+
+		bytes_free = ((uint64_t) (yaffs_get_n_free_chunks(dev))) *
+		    ((uint64_t) (dev->data_bytes_per_chunk));
+
+		do_div(bytes_free, sb->s_blocksize);
+
+		buf->f_bfree = bytes_free;
+
+	} else if (sb->s_blocksize > dev->data_bytes_per_chunk) {
+
+		buf->f_blocks =
+		    (dev->param.end_block - dev->param.start_block + 1) *
+		    dev->param.chunks_per_block /
+		    (sb->s_blocksize / dev->data_bytes_per_chunk);
+		buf->f_bfree =
+		    yaffs_get_n_free_chunks(dev) /
+		    (sb->s_blocksize / dev->data_bytes_per_chunk);
+	} else {
+		buf->f_blocks =
+		    (dev->param.end_block - dev->param.start_block + 1) *
+		    dev->param.chunks_per_block *
+		    (dev->data_bytes_per_chunk / sb->s_blocksize);
+
+		buf->f_bfree =
+		    yaffs_get_n_free_chunks(dev) *
+		    (dev->data_bytes_per_chunk / sb->s_blocksize);
+	}
+
+	buf->f_files = 0;
+	buf->f_ffree = 0;
+	buf->f_bavail = buf->f_bfree;
+
+	yaffs_gross_unlock(dev);
+	return 0;
+}
+
+
+
+static int yaffs_do_sync_fs(struct super_block *sb, int request_checkpoint)
+{
+
+	struct yaffs_dev *dev = yaffs_super_to_dev(sb);
+	unsigned int oneshot_checkpoint = (yaffs_auto_checkpoint & 4);
+	unsigned gc_urgent = yaffs_bg_gc_urgency(dev);
+	int do_checkpoint;
+	int dirty = yaffs_check_super_dirty(dev);
+
+	yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_SYNC | YAFFS_TRACE_BACKGROUND,
+		"yaffs_do_sync_fs: gc-urgency %d %s %s%s",
+		gc_urgent,
+		dirty ? "dirty" : "clean",
+		request_checkpoint ? "checkpoint requested" : "no checkpoint",
+		oneshot_checkpoint ? " one-shot" : "");
+
+	yaffs_gross_lock(dev);
+	do_checkpoint = ((request_checkpoint && !gc_urgent) ||
+			 oneshot_checkpoint) && !dev->is_checkpointed;
+
+	if (dirty || do_checkpoint) {
+		yaffs_flush_super(sb, !dev->is_checkpointed && do_checkpoint);
+		yaffs_clear_super_dirty(dev);
+		if (oneshot_checkpoint)
+			yaffs_auto_checkpoint &= ~4;
+	}
+	yaffs_gross_unlock(dev);
+
+	return 0;
+}
+
+
+#ifdef YAFFS_HAS_WRITE_SUPER
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17))
+static void yaffs_write_super(struct super_block *sb)
+#else
+static int yaffs_write_super(struct super_block *sb)
+#endif
+{
+	unsigned request_checkpoint = (yaffs_auto_checkpoint >= 2);
+
+	yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_SYNC | YAFFS_TRACE_BACKGROUND,
+		"yaffs_write_super %s",
+		request_checkpoint ? " checkpt" : "");
+
+	yaffs_do_sync_fs(sb, request_checkpoint);
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 18))
+	return 0;
+#endif
+}
+#endif
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17))
+static int yaffs_sync_fs(struct super_block *sb, int wait)
+#else
+static int yaffs_sync_fs(struct super_block *sb)
+#endif
+{
+	unsigned request_checkpoint = (yaffs_auto_checkpoint >= 1);
+
+	yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_SYNC,
+		"yaffs_sync_fs%s", request_checkpoint ? " checkpt" : "");
+
+	yaffs_do_sync_fs(sb, request_checkpoint);
+
+	return 0;
+}
+
+/* the function only is used to change dev->read_only when this file system
+ * is remounted.
+ */
+static int yaffs_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	int read_only = 0;
+	struct mtd_info *mtd;
+	struct yaffs_dev *dev = 0;
+
+	/* Get the device */
+	mtd = get_mtd_device(NULL, MINOR(sb->s_dev));
+	if (!mtd) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"MTD device #%u doesn't appear to exist",
+			MINOR(sb->s_dev));
+		return 1;
+	}
+
+	/* Check it's NAND */
+	if (mtd->type != MTD_NANDFLASH) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"MTD device is not NAND it's type %d",
+			mtd->type);
+		return 1;
+	}
+
+	read_only = ((*flags & MS_RDONLY) != 0);
+	if (!read_only && !(mtd->flags & MTD_WRITEABLE)) {
+		read_only = 1;
+		printk(KERN_INFO
+		       "yaffs: mtd is read only, setting superblock read only");
+		*flags |= MS_RDONLY;
+	}
+
+	dev = sb->s_fs_info;
+	dev->read_only = read_only;
+
+	return 0;
+}
+
+static const struct super_operations yaffs_super_ops = {
+	.statfs = yaffs_statfs,
+
+#ifndef YAFFS_USE_OWN_IGET
+	.read_inode = yaffs_read_inode,
+#endif
+#ifdef YAFFS_HAS_PUT_INODE
+	.put_inode = yaffs_put_inode,
+#endif
+	.put_super = yaffs_put_super,
+#ifdef YAFFS_HAS_EVICT_INODE
+	.evict_inode = yaffs_evict_inode,
+#else
+	.delete_inode = yaffs_delete_inode,
+	.clear_inode = yaffs_clear_inode,
+#endif
+	.sync_fs = yaffs_sync_fs,
+#ifdef YAFFS_HAS_WRITE_SUPER
+	.write_super = yaffs_write_super,
+#endif
+	.remount_fs = yaffs_remount_fs,
+};
+
+struct yaffs_options {
+	int inband_tags;
+	int skip_checkpoint_read;
+	int skip_checkpoint_write;
+	int no_cache;
+	int tags_ecc_on;
+	int tags_ecc_overridden;
+	int lazy_loading_enabled;
+	int lazy_loading_overridden;
+	int empty_lost_and_found;
+	int empty_lost_and_found_overridden;
+	int disable_summary;
+};
+
+#define MAX_OPT_LEN 30
+static int yaffs_parse_options(struct yaffs_options *options,
+			       const char *options_str)
+{
+	char cur_opt[MAX_OPT_LEN + 1];
+	int p;
+	int error = 0;
+
+	/* Parse through the options which is a comma seperated list */
+
+	while (options_str && *options_str && !error) {
+		memset(cur_opt, 0, MAX_OPT_LEN + 1);
+		p = 0;
+
+		while (*options_str == ',')
+			options_str++;
+
+		while (*options_str && *options_str != ',') {
+			if (p < MAX_OPT_LEN) {
+				cur_opt[p] = *options_str;
+				p++;
+			}
+			options_str++;
+		}
+
+		if (!strcmp(cur_opt, "inband-tags")) {
+			options->inband_tags = 1;
+		} else if (!strcmp(cur_opt, "tags-ecc-off")) {
+			options->tags_ecc_on = 0;
+			options->tags_ecc_overridden = 1;
+		} else if (!strcmp(cur_opt, "tags-ecc-on")) {
+			options->tags_ecc_on = 1;
+			options->tags_ecc_overridden = 1;
+		} else if (!strcmp(cur_opt, "lazy-loading-off")) {
+			options->lazy_loading_enabled = 0;
+			options->lazy_loading_overridden = 1;
+		} else if (!strcmp(cur_opt, "lazy-loading-on")) {
+			options->lazy_loading_enabled = 1;
+			options->lazy_loading_overridden = 1;
+		} else if (!strcmp(cur_opt, "disable-summary")) {
+			options->disable_summary = 1;
+		} else if (!strcmp(cur_opt, "empty-lost-and-found-off")) {
+			options->empty_lost_and_found = 0;
+			options->empty_lost_and_found_overridden = 1;
+		} else if (!strcmp(cur_opt, "empty-lost-and-found-on")) {
+			options->empty_lost_and_found = 1;
+			options->empty_lost_and_found_overridden = 1;
+		} else if (!strcmp(cur_opt, "no-cache")) {
+			options->no_cache = 1;
+		} else if (!strcmp(cur_opt, "no-checkpoint-read")) {
+			options->skip_checkpoint_read = 1;
+		} else if (!strcmp(cur_opt, "no-checkpoint-write")) {
+			options->skip_checkpoint_write = 1;
+		} else if (!strcmp(cur_opt, "no-checkpoint")) {
+			options->skip_checkpoint_read = 1;
+			options->skip_checkpoint_write = 1;
+		} else {
+			printk(KERN_INFO "yaffs: Bad mount option \"%s\"\n",
+			       cur_opt);
+			error = 1;
+		}
+	}
+
+	return error;
+}
+
+
+static struct dentry *yaffs_make_root(struct inode *inode)
+{
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0))
+	struct dentry *root = d_alloc_root(inode);
+
+	if (!root)
+		iput(inode);
+
+        return root;
+#else
+        return d_make_root(inode);
+#endif
+}
+
+
+static int yaffs_xattr_get(const struct xattr_handler *handler,
+			    struct dentry *dentry, struct inode *inode,
+			    const char *name, void *buff, size_t size)
+{
+	return yaffs_getxattr(dentry, inode, name, buff, size);
+}
+
+static int yaffs_xattr_set(const struct xattr_handler *handler,
+			   struct dentry *dentry, struct inode *inode,
+			   const char *name, const void *value, size_t size,
+			   int flags)
+{
+	if (value)
+		return yaffs_setxattr(dentry, inode, name, value, size, flags);
+	else
+		return yaffs_removexattr(dentry, name);
+}
+
+static const struct xattr_handler yaffs_xattr_handler = {
+	.prefix = "", /* match anything */
+	.get = yaffs_xattr_get,
+	.set = yaffs_xattr_set,
+};
+
+static const struct xattr_handler *yaffs_xattr_handlers[] = {
+	&yaffs_xattr_handler,
+	NULL
+};
+
+static struct super_block *yaffs_internal_read_super(int yaffs_version,
+						     struct super_block *sb,
+						     void *data, int silent)
+{
+	int n_blocks;
+	struct inode *inode = NULL;
+	struct dentry *root;
+	struct yaffs_dev *dev = 0;
+	char devname_buf[BDEVNAME_SIZE + 1];
+	struct mtd_info *mtd;
+	int err;
+	char *data_str = (char *)data;
+	struct yaffs_linux_context *context = NULL;
+	struct yaffs_param *param;
+
+	int read_only = 0;
+	int inband_tags = 0;
+
+	struct yaffs_options options;
+
+	unsigned mount_id;
+	int found;
+	struct yaffs_linux_context *context_iterator;
+	struct list_head *l;
+
+	if (!sb) {
+		printk(KERN_INFO "yaffs: sb is NULL\n");
+		return NULL;
+        }
+
+	sb->s_magic = YAFFS_MAGIC;
+	sb->s_op = &yaffs_super_ops;
+	sb->s_xattr = yaffs_xattr_handlers;
+	sb->s_flags |= MS_NOATIME;
+
+	read_only = ((sb->s_flags & MS_RDONLY) != 0);
+
+#ifdef YAFFS_COMPILE_EXPORTFS
+	sb->s_export_op = &yaffs_export_ops;
+#endif
+
+	if (!sb->s_dev)
+		printk(KERN_INFO "yaffs: sb->s_dev is NULL\n");
+	else if (!yaffs_devname(sb, devname_buf))
+		printk(KERN_INFO "yaffs: devname is NULL\n");
+	else
+		printk(KERN_INFO "yaffs: dev is %d name is \"%s\" %s\n",
+		       sb->s_dev,
+		       yaffs_devname(sb, devname_buf), read_only ? "ro" : "rw");
+
+	if (!data_str)
+		data_str = "";
+
+	printk(KERN_INFO "yaffs: passed flags \"%s\"\n", data_str);
+
+	memset(&options, 0, sizeof(options));
+
+	if (yaffs_parse_options(&options, data_str)) {
+		/* Option parsing failed */
+		return NULL;
+	}
+
+	sb->s_blocksize = PAGE_SIZE;
+	sb->s_blocksize_bits = PAGE_SHIFT;
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_read_super: Using yaffs%d", yaffs_version);
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_read_super: block size %d", (int)(sb->s_blocksize));
+
+	yaffs_trace(YAFFS_TRACE_ALWAYS,
+		"yaffs: Attempting MTD mount of %u.%u,\"%s\"",
+		MAJOR(sb->s_dev), MINOR(sb->s_dev),
+		yaffs_devname(sb, devname_buf));
+
+	/* Get the device */
+	mtd = get_mtd_device(NULL, MINOR(sb->s_dev));
+	if (!mtd) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"yaffs: MTD device %u either not valid or unavailable",
+			MINOR(sb->s_dev));
+		return NULL;
+	}
+
+	if (yaffs_auto_select && yaffs_version == 1 && WRITE_SIZE(mtd) >= 2048) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS, "auto selecting yaffs2");
+		yaffs_version = 2;
+	}
+
+	if (mtd->oobavail < sizeof(struct yaffs_packed_tags2) ||
+	    options.inband_tags)
+		inband_tags = 1;
+
+	/* Added NCB 26/5/2006 for completeness */
+	if (yaffs_version == 2 && !inband_tags
+	    && WRITE_SIZE(mtd) == 512) {
+		yaffs_trace(YAFFS_TRACE_ALWAYS, "auto selecting yaffs1");
+		yaffs_version = 1;
+	}
+
+	if(yaffs_verify_mtd(mtd, yaffs_version, inband_tags) < 0)
+		return NULL;
+
+	/* OK, so if we got here, we have an MTD that's NAND and looks
+	 * like it has the right capabilities
+	 * Set the struct yaffs_dev up for mtd
+	 */
+
+	if (!read_only && !(mtd->flags & MTD_WRITEABLE)) {
+		read_only = 1;
+		printk(KERN_INFO
+		       "yaffs: mtd is read only, setting superblock read only\n"
+		);
+		sb->s_flags |= MS_RDONLY;
+	}
+
+	dev = kmalloc(sizeof(struct yaffs_dev), GFP_KERNEL);
+	context = kmalloc(sizeof(struct yaffs_linux_context), GFP_KERNEL);
+
+	if (!dev || !context) {
+		if (dev)
+			kfree(dev);
+		if (context)
+			kfree(context);
+		dev = NULL;
+		context = NULL;
+	}
+
+	if (!dev) {
+		/* Deep shit could not allocate device structure */
+		yaffs_trace(YAFFS_TRACE_ALWAYS,
+			"yaffs_read_super: Failed trying to allocate struct yaffs_dev."
+		);
+		return NULL;
+	}
+	memset(dev, 0, sizeof(struct yaffs_dev));
+	param = &(dev->param);
+
+	memset(context, 0, sizeof(struct yaffs_linux_context));
+	dev->os_context = context;
+	INIT_LIST_HEAD(&(context->context_list));
+	context->dev = dev;
+	context->super = sb;
+
+	dev->read_only = read_only;
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+	sb->s_fs_info = dev;
+#else
+	sb->u.generic_sbp = dev;
+#endif
+
+
+	dev->driver_context = mtd;
+	param->name = mtd->name;
+
+	/* Set up the memory size parameters.... */
+
+
+	param->n_reserved_blocks = 5;
+	param->n_caches = (options.no_cache) ? 0 : 10;
+	param->inband_tags = inband_tags;
+
+	param->enable_xattr = 1;
+	if (options.lazy_loading_overridden)
+		param->disable_lazy_load = !options.lazy_loading_enabled;
+
+	param->defered_dir_update = 1;
+
+	if (options.tags_ecc_overridden)
+		param->no_tags_ecc = !options.tags_ecc_on;
+
+	param->empty_lost_n_found = 1;
+	param->refresh_period = 500;
+	param->disable_summary = options.disable_summary;
+
+
+#ifdef CONFIG_YAFFS_DISABLE_BAD_BLOCK_MARKING
+	param->disable_bad_block_marking  = 1;
+#endif
+	if (options.empty_lost_and_found_overridden)
+		param->empty_lost_n_found = options.empty_lost_and_found;
+
+	/* ... and the functions. */
+	if (yaffs_version == 2) {
+		param->is_yaffs2 = 1;
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17))
+		param->total_bytes_per_chunk = mtd->writesize;
+		param->chunks_per_block = mtd->erasesize / mtd->writesize;
+#else
+		param->total_bytes_per_chunk = mtd->oobblock;
+		param->chunks_per_block = mtd->erasesize / mtd->oobblock;
+#endif
+		n_blocks = YCALCBLOCKS(mtd->size, mtd->erasesize);
+
+		param->start_block = 0;
+		param->end_block = n_blocks - 1;
+	} else {
+		param->is_yaffs2 = 0;
+		n_blocks = YCALCBLOCKS(mtd->size,
+			     YAFFS_CHUNKS_PER_BLOCK * YAFFS_BYTES_PER_CHUNK);
+
+		param->chunks_per_block = YAFFS_CHUNKS_PER_BLOCK;
+		param->total_bytes_per_chunk = YAFFS_BYTES_PER_CHUNK;
+	}
+
+	param->start_block = 0;
+	param->end_block = n_blocks - 1;
+
+	yaffs_mtd_drv_install(dev);
+
+	param->sb_dirty_fn = yaffs_set_super_dirty;
+	param->gc_control_fn = yaffs_gc_control_callback;
+
+	yaffs_dev_to_lc(dev)->super = sb;
+
+	param->use_nand_ecc = 1;
+
+	param->skip_checkpt_rd = options.skip_checkpoint_read;
+	param->skip_checkpt_wr = options.skip_checkpoint_write;
+
+	mutex_lock(&yaffs_context_lock);
+	/* Get a mount id */
+	found = 0;
+	for (mount_id = 0; !found; mount_id++) {
+		found = 1;
+		list_for_each(l, &yaffs_context_list) {
+			context_iterator =
+			    list_entry(l, struct yaffs_linux_context,
+				       context_list);
+			if (context_iterator->mount_id == mount_id)
+				found = 0;
+		}
+	}
+	context->mount_id = mount_id;
+
+	list_add_tail(&(yaffs_dev_to_lc(dev)->context_list),
+		      &yaffs_context_list);
+	mutex_unlock(&yaffs_context_lock);
+
+	/* Directory search handling... */
+	INIT_LIST_HEAD(&(yaffs_dev_to_lc(dev)->search_contexts));
+	param->remove_obj_fn = yaffs_remove_obj_callback;
+
+	mutex_init(&(yaffs_dev_to_lc(dev)->gross_lock));
+
+	yaffs_gross_lock(dev);
+
+	err = yaffs_guts_initialise(dev);
+
+	yaffs_trace(YAFFS_TRACE_OS,
+		"yaffs_read_super: guts initialised %s",
+		(err == YAFFS_OK) ? "OK" : "FAILED");
+
+	if (err == YAFFS_OK)
+		yaffs_bg_start(dev);
+
+	if (!context->bg_thread)
+		param->defered_dir_update = 0;
+
+	sb->s_maxbytes = yaffs_max_file_size(dev);
+
+	/* Release lock before yaffs_get_inode() */
+	yaffs_gross_unlock(dev);
+
+	/* Create root inode */
+	if (err == YAFFS_OK)
+		inode = yaffs_get_inode(sb, S_IFDIR | 0755, 0, yaffs_root(dev));
+
+	if (!inode)
+		return NULL;
+
+	inode->i_op = &yaffs_dir_inode_operations;
+	inode->i_fop = &yaffs_dir_operations;
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_read_super: got root inode");
+
+	root = yaffs_make_root(inode);
+
+	if (!root)
+		return NULL;
+
+	sb->s_root = root;
+	if(!dev->is_checkpointed)
+		yaffs_set_super_dirty(dev);
+
+	yaffs_trace(YAFFS_TRACE_ALWAYS,
+		"yaffs_read_super: is_checkpointed %d",
+		dev->is_checkpointed);
+
+	yaffs_trace(YAFFS_TRACE_OS, "yaffs_read_super: done");
+	return sb;
+}
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+static int yaffs_internal_read_super_mtd(struct super_block *sb, void *data,
+					 int silent)
+{
+	return yaffs_internal_read_super(1, sb, data, silent) ? 0 : -EINVAL;
+}
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39))
+static struct dentry *yaffs_mount(struct file_system_type *fs_type, int flags,
+        const char *dev_name, void *data)
+{
+    return mount_bdev(fs_type, flags, dev_name, data, yaffs_internal_read_super_mtd);
+}
+#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17))
+static int yaffs_read_super(struct file_system_type *fs,
+			    int flags, const char *dev_name,
+			    void *data, struct vfsmount *mnt)
+{
+
+	return get_sb_bdev(fs, flags, dev_name, data,
+			   yaffs_internal_read_super_mtd, mnt);
+}
+#else
+static struct super_block *yaffs_read_super(struct file_system_type *fs,
+					    int flags, const char *dev_name,
+					    void *data)
+{
+
+	return get_sb_bdev(fs, flags, dev_name, data,
+			   yaffs_internal_read_super_mtd);
+}
+#endif
+
+static struct file_system_type yaffs_fs_type = {
+	.owner = THIS_MODULE,
+	.name = "yaffs",
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39))
+        .mount = yaffs_mount,
+#else
+        .get_sb = yaffs_read_super,
+#endif
+     	.kill_sb = kill_block_super,
+	.fs_flags = FS_REQUIRES_DEV,
+};
+#else
+static struct super_block *yaffs_read_super(struct super_block *sb, void *data,
+					    int silent)
+{
+	return yaffs_internal_read_super(1, sb, data, silent);
+}
+
+static DECLARE_FSTYPE(yaffs_fs_type, "yaffs", yaffs_read_super,
+		      FS_REQUIRES_DEV);
+#endif
+
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+static int yaffs2_internal_read_super_mtd(struct super_block *sb, void *data,
+					  int silent)
+{
+	return yaffs_internal_read_super(2, sb, data, silent) ? 0 : -EINVAL;
+}
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39))
+static struct dentry *yaffs2_mount(struct file_system_type *fs_type, int flags,
+        const char *dev_name, void *data)
+{
+        return mount_bdev(fs_type, flags, dev_name, data, yaffs2_internal_read_super_mtd);
+}
+#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17))
+static int yaffs2_read_super(struct file_system_type *fs,
+			     int flags, const char *dev_name, void *data,
+			     struct vfsmount *mnt)
+{
+	return get_sb_bdev(fs, flags, dev_name, data,
+			   yaffs2_internal_read_super_mtd, mnt);
+}
+#else
+static struct super_block *yaffs2_read_super(struct file_system_type *fs,
+					     int flags, const char *dev_name,
+					     void *data)
+{
+
+	return get_sb_bdev(fs, flags, dev_name, data,
+			   yaffs2_internal_read_super_mtd);
+}
+#endif
+
+static struct file_system_type yaffs2_fs_type = {
+	.owner = THIS_MODULE,
+	.name = "yaffs2",
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39))
+        .mount = yaffs2_mount,
+#else
+        .get_sb = yaffs2_read_super,
+#endif
+     	.kill_sb = kill_block_super,
+	.fs_flags = FS_REQUIRES_DEV,
+};
+#else
+static struct super_block *yaffs2_read_super(struct super_block *sb,
+					     void *data, int silent)
+{
+	return yaffs_internal_read_super(2, sb, data, silent);
+}
+
+static DECLARE_FSTYPE(yaffs2_fs_type, "yaffs2", yaffs2_read_super,
+		      FS_REQUIRES_DEV);
+#endif
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 9, 0))
+static struct proc_dir_entry *my_proc_entry;
+
+static char *yaffs_dump_dev_part0(char *buf, struct yaffs_dev *dev)
+{
+	struct yaffs_param *param = &dev->param;
+	int bs[10];
+
+	yaffs_count_blocks_by_state(dev,bs);
+
+	buf += sprintf(buf, "start_block.......... %d\n", param->start_block);
+	buf += sprintf(buf, "end_block............ %d\n", param->end_block);
+	buf += sprintf(buf, "total_bytes_per_chunk %d\n",
+				param->total_bytes_per_chunk);
+	buf += sprintf(buf, "use_nand_ecc......... %d\n", param->use_nand_ecc);
+	buf += sprintf(buf, "no_tags_ecc.......... %d\n", param->no_tags_ecc);
+	buf += sprintf(buf, "is_yaffs2............ %d\n", param->is_yaffs2);
+	buf += sprintf(buf, "inband_tags.......... %d\n", param->inband_tags);
+	buf += sprintf(buf, "empty_lost_n_found... %d\n",
+				param->empty_lost_n_found);
+	buf += sprintf(buf, "disable_lazy_load.... %d\n",
+				param->disable_lazy_load);
+	buf += sprintf(buf, "disable_bad_block_mrk %d\n",
+				param->disable_bad_block_marking);
+	buf += sprintf(buf, "refresh_period....... %d\n",
+				param->refresh_period);
+	buf += sprintf(buf, "n_caches............. %d\n", param->n_caches);
+	buf += sprintf(buf, "n_reserved_blocks.... %d\n",
+				param->n_reserved_blocks);
+	buf += sprintf(buf, "always_check_erased.. %d\n",
+				param->always_check_erased);
+	buf += sprintf(buf, "\n");
+	buf += sprintf(buf, "block count by state\n");
+	buf += sprintf(buf, "0:%d 1:%d 2:%d 3:%d 4:%d\n",
+				bs[0], bs[1], bs[2], bs[3], bs[4]);
+	buf += sprintf(buf, "5:%d 6:%d 7:%d 8:%d 9:%d\n",
+				bs[5], bs[6], bs[7], bs[8], bs[9]);
+
+	return buf;
+}
+
+static char *yaffs_dump_dev_part1(char *buf, struct yaffs_dev *dev)
+{
+	buf += sprintf(buf, "max file size....... %lld\n",
+				(long long) yaffs_max_file_size(dev));
+	buf += sprintf(buf, "data_bytes_per_chunk. %d\n",
+				dev->data_bytes_per_chunk);
+	buf += sprintf(buf, "chunk_grp_bits....... %d\n", dev->chunk_grp_bits);
+	buf += sprintf(buf, "chunk_grp_size....... %d\n", dev->chunk_grp_size);
+	buf += sprintf(buf, "n_erased_blocks...... %d\n", dev->n_erased_blocks);
+	buf += sprintf(buf, "blocks_in_checkpt.... %d\n",
+				dev->blocks_in_checkpt);
+	buf += sprintf(buf, "\n");
+	buf += sprintf(buf, "n_tnodes............. %d\n", dev->n_tnodes);
+	buf += sprintf(buf, "n_obj................ %d\n", dev->n_obj);
+	buf += sprintf(buf, "n_free_chunks........ %d\n", dev->n_free_chunks);
+	buf += sprintf(buf, "\n");
+	buf += sprintf(buf, "n_page_writes........ %u\n", dev->n_page_writes);
+	buf += sprintf(buf, "n_page_reads......... %u\n", dev->n_page_reads);
+	buf += sprintf(buf, "n_erasures........... %u\n", dev->n_erasures);
+	buf += sprintf(buf, "n_gc_copies.......... %u\n", dev->n_gc_copies);
+	buf += sprintf(buf, "all_gcs.............. %u\n", dev->all_gcs);
+	buf += sprintf(buf, "passive_gc_count..... %u\n",
+				dev->passive_gc_count);
+	buf += sprintf(buf, "oldest_dirty_gc_count %u\n",
+				dev->oldest_dirty_gc_count);
+	buf += sprintf(buf, "n_gc_blocks.......... %u\n", dev->n_gc_blocks);
+	buf += sprintf(buf, "bg_gcs............... %u\n", dev->bg_gcs);
+	buf += sprintf(buf, "n_retried_writes..... %u\n",
+				dev->n_retried_writes);
+	buf += sprintf(buf, "n_retired_blocks..... %u\n",
+				dev->n_retired_blocks);
+	buf += sprintf(buf, "n_ecc_fixed.......... %u\n", dev->n_ecc_fixed);
+	buf += sprintf(buf, "n_ecc_unfixed........ %u\n", dev->n_ecc_unfixed);
+	buf += sprintf(buf, "n_tags_ecc_fixed..... %u\n",
+				dev->n_tags_ecc_fixed);
+	buf += sprintf(buf, "n_tags_ecc_unfixed... %u\n",
+				dev->n_tags_ecc_unfixed);
+	buf += sprintf(buf, "cache_hits........... %u\n", dev->cache_hits);
+	buf += sprintf(buf, "n_deleted_files...... %u\n", dev->n_deleted_files);
+	buf += sprintf(buf, "n_unlinked_files..... %u\n",
+				dev->n_unlinked_files);
+	buf += sprintf(buf, "refresh_count........ %u\n", dev->refresh_count);
+	buf += sprintf(buf, "n_bg_deletions....... %u\n", dev->n_bg_deletions);
+	buf += sprintf(buf, "tags_used............ %u\n", dev->tags_used);
+	buf += sprintf(buf, "summary_used......... %u\n", dev->summary_used);
+
+	return buf;
+}
+
+static int yaffs_proc_read(char *page,
+			   char **start,
+			   off_t offset, int count, int *eof, void *data)
+{
+	struct list_head *item;
+	char *buf = page;
+	int step = offset;
+	int n = 0;
+
+	/* Get proc_file_read() to step 'offset' by one on each sucessive call.
+	 * We use 'offset' (*ppos) to indicate where we are in dev_list.
+	 * This also assumes the user has posted a read buffer large
+	 * enough to hold the complete output; but that's life in /proc.
+	 */
+
+	*(int *)start = 1;
+
+	/* Print header first */
+	if (step == 0)
+		buf +=
+		    sprintf(buf, "Multi-version YAFFS\n");
+	else if (step == 1)
+		buf += sprintf(buf, "\n");
+	else {
+		step -= 2;
+
+		mutex_lock(&yaffs_context_lock);
+
+		/* Locate and print the Nth entry.  Order N-squared but N is small. */
+		list_for_each(item, &yaffs_context_list) {
+			struct yaffs_linux_context *dc =
+			    list_entry(item, struct yaffs_linux_context,
+				       context_list);
+			struct yaffs_dev *dev = dc->dev;
+
+			if (n < (step & ~1)) {
+				n += 2;
+				continue;
+			}
+			if ((step & 1) == 0) {
+				buf +=
+				    sprintf(buf, "\nDevice %d \"%s\"\n", n,
+					    dev->param.name);
+				buf = yaffs_dump_dev_part0(buf, dev);
+			} else {
+				buf = yaffs_dump_dev_part1(buf, dev);
+                        }
+
+			break;
+		}
+		mutex_unlock(&yaffs_context_lock);
+	}
+
+	return buf - page < count ? buf - page : count;
+}
+
+/**
+ * Set the verbosity of the warnings and error messages.
+ *
+ * Note that the names can only be a..z or _ with the current code.
+ */
+
+static struct {
+	char *mask_name;
+	unsigned mask_bitfield;
+} mask_flags[] = {
+	{"allocate", YAFFS_TRACE_ALLOCATE},
+	{"always", YAFFS_TRACE_ALWAYS},
+	{"background", YAFFS_TRACE_BACKGROUND},
+	{"bad_blocks", YAFFS_TRACE_BAD_BLOCKS},
+	{"buffers", YAFFS_TRACE_BUFFERS},
+	{"bug", YAFFS_TRACE_BUG},
+	{"checkpt", YAFFS_TRACE_CHECKPOINT},
+	{"deletion", YAFFS_TRACE_DELETION},
+	{"erase", YAFFS_TRACE_ERASE},
+	{"error", YAFFS_TRACE_ERROR},
+	{"gc_detail", YAFFS_TRACE_GC_DETAIL},
+	{"gc", YAFFS_TRACE_GC},
+	{"lock", YAFFS_TRACE_LOCK},
+	{"mtd", YAFFS_TRACE_MTD},
+	{"nandaccess", YAFFS_TRACE_NANDACCESS},
+	{"os", YAFFS_TRACE_OS},
+	{"scan_debug", YAFFS_TRACE_SCAN_DEBUG},
+	{"scan", YAFFS_TRACE_SCAN},
+	{"mount", YAFFS_TRACE_MOUNT},
+	{"tracing", YAFFS_TRACE_TRACING},
+	{"sync", YAFFS_TRACE_SYNC},
+	{"write", YAFFS_TRACE_WRITE},
+	{"verify", YAFFS_TRACE_VERIFY},
+	{"verify_nand", YAFFS_TRACE_VERIFY_NAND},
+	{"verify_full", YAFFS_TRACE_VERIFY_FULL},
+	{"verify_all", YAFFS_TRACE_VERIFY_ALL},
+	{"all", 0xffffffff},
+	{"none", 0},
+	{NULL, 0},
+};
+
+#define MAX_MASK_NAME_LENGTH 40
+static int yaffs_proc_write_trace_options(struct file *file, const char *buf,
+					  unsigned long count, void *data)
+{
+	unsigned rg = 0, mask_bitfield;
+	char *end;
+	char *mask_name;
+	const char *x;
+	char substring[MAX_MASK_NAME_LENGTH + 1];
+	int i;
+	int done = 0;
+	int add, len = 0;
+	int pos = 0;
+
+	rg = yaffs_trace_mask;
+
+	while (!done && (pos < count)) {
+		done = 1;
+		while ((pos < count) && isspace(buf[pos]))
+			pos++;
+
+		switch (buf[pos]) {
+		case '+':
+		case '-':
+		case '=':
+			add = buf[pos];
+			pos++;
+			break;
+
+		default:
+			add = ' ';
+			break;
+		}
+		mask_name = NULL;
+
+		mask_bitfield = simple_strtoul(buf + pos, &end, 0);
+
+		if (end > buf + pos) {
+			mask_name = "numeral";
+			len = end - (buf + pos);
+			pos += len;
+			done = 0;
+		} else {
+			for (x = buf + pos, i = 0;
+			     (*x == '_' || (*x >= 'a' && *x <= 'z')) &&
+			     i < MAX_MASK_NAME_LENGTH; x++, i++, pos++)
+				substring[i] = *x;
+			substring[i] = '\0';
+
+			for (i = 0; mask_flags[i].mask_name != NULL; i++) {
+				if (strcmp(substring, mask_flags[i].mask_name)
+				    == 0) {
+					mask_name = mask_flags[i].mask_name;
+					mask_bitfield =
+					    mask_flags[i].mask_bitfield;
+					done = 0;
+					break;
+				}
+			}
+		}
+
+		if (mask_name != NULL) {
+			done = 0;
+			switch (add) {
+			case '-':
+				rg &= ~mask_bitfield;
+				break;
+			case '+':
+				rg |= mask_bitfield;
+				break;
+			case '=':
+				rg = mask_bitfield;
+				break;
+			default:
+				rg |= mask_bitfield;
+				break;
+			}
+		}
+	}
+
+	yaffs_trace_mask = rg | YAFFS_TRACE_ALWAYS;
+
+	printk(KERN_DEBUG "new trace = 0x%08X\n", yaffs_trace_mask);
+
+	if (rg & YAFFS_TRACE_ALWAYS) {
+		for (i = 0; mask_flags[i].mask_name != NULL; i++) {
+			char flag;
+			flag = ((rg & mask_flags[i].mask_bitfield) ==
+				mask_flags[i].mask_bitfield) ? '+' : '-';
+			printk(KERN_DEBUG "%c%s\n", flag,
+			       mask_flags[i].mask_name);
+		}
+	}
+
+	return count;
+}
+
+/* Debug strings are of the form:
+ * .bnnn         print info on block n
+ * .cobjn,chunkn print nand chunk id for objn:chunkn
+ */
+
+static int yaffs_proc_debug_write(struct file *file, const char *buf,
+					  unsigned long count, void *data)
+{
+
+	char str[100];
+	char *p0;
+	char *p1;
+	long p1_val;
+	long p0_val;
+	char cmd;
+	struct list_head *item;
+
+	memset(str, 0, sizeof(str));
+	memcpy(str, buf, min(count, sizeof(str) -1));
+
+	cmd = str[1];
+
+	p0 = str + 2;
+
+	p1 = p0;
+
+	while (*p1 && *p1 != ',') {
+		p1++;
+	}
+	*p1 = '\0';
+	p1++;
+
+	p0_val = simple_strtol(p0, NULL, 0);
+	p1_val = simple_strtol(p1, NULL, 0);
+
+
+	mutex_lock(&yaffs_context_lock);
+
+	/* Locate and print the Nth entry.  Order N-squared but N is small. */
+	list_for_each(item, &yaffs_context_list) {
+		struct yaffs_linux_context *dc =
+		    list_entry(item, struct yaffs_linux_context,
+			       context_list);
+		struct yaffs_dev *dev = dc->dev;
+
+		if (cmd == 'b') {
+			struct yaffs_block_info *bi;
+
+			bi = yaffs_get_block_info(dev,p0_val);
+
+			if(bi) {
+				printk("Block %d: state %d, retire %d, use %d, seq %d\n",
+					(int)p0_val, bi->block_state,
+					bi->needs_retiring, bi->pages_in_use,
+					bi->seq_number);
+			}
+		} else if (cmd == 'c') {
+			struct yaffs_obj *obj;
+			int nand_chunk;
+
+			obj = yaffs_find_by_number(dev, p0_val);
+			if (!obj)
+				printk("No obj %d\n", (int)p0_val);
+			else {
+				if(p1_val == 0)
+					nand_chunk = obj->hdr_chunk;
+				else
+					nand_chunk =
+						yaffs_find_chunk_in_file(obj,
+							p1_val, NULL);
+				printk("Nand chunk for %d:%d is %d\n",
+					(int)p0_val, (int)p1_val, nand_chunk);
+			}
+		}
+	}
+
+	mutex_unlock(&yaffs_context_lock);
+
+	return count;
+}
+
+static int yaffs_proc_write(struct file *file, const char *buf,
+			    unsigned long count, void *data)
+{
+	if (buf[0] == '.')
+		return yaffs_proc_debug_write(file, buf, count, data);
+	return yaffs_proc_write_trace_options(file, buf, count, data);
+}
+#endif
+
+/* Stuff to handle installation of file systems */
+struct file_system_to_install {
+	struct file_system_type *fst;
+	int installed;
+};
+
+static struct file_system_to_install fs_to_install[] = {
+	{&yaffs_fs_type, 0},
+	{&yaffs2_fs_type, 0},
+	{NULL, 0}
+};
+
+static int __init init_yaffs_fs(void)
+{
+	int error = 0;
+	struct file_system_to_install *fsinst;
+
+	yaffs_trace(YAFFS_TRACE_ALWAYS, "yaffs Installing.");
+
+	mutex_init(&yaffs_context_lock);
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 9, 0))
+	/* Install the proc_fs entries */
+	my_proc_entry = create_proc_entry("yaffs",
+					  S_IRUGO | S_IFREG, YPROC_ROOT);
+
+	if (my_proc_entry) {
+		my_proc_entry->write_proc = yaffs_proc_write;
+		my_proc_entry->read_proc = yaffs_proc_read;
+		my_proc_entry->data = NULL;
+	} else {
+		return -ENOMEM;
+        }
+#endif
+
+	/* Now add the file system entries */
+
+	fsinst = fs_to_install;
+
+	while (fsinst->fst && !error) {
+		error = register_filesystem(fsinst->fst);
+		if (!error)
+			fsinst->installed = 1;
+		fsinst++;
+	}
+
+	/* Any errors? uninstall  */
+	if (error) {
+		fsinst = fs_to_install;
+
+		while (fsinst->fst) {
+			if (fsinst->installed) {
+				unregister_filesystem(fsinst->fst);
+				fsinst->installed = 0;
+			}
+			fsinst++;
+		}
+	}
+
+	return error;
+}
+
+static void __exit exit_yaffs_fs(void)
+{
+
+	struct file_system_to_install *fsinst;
+
+	yaffs_trace(YAFFS_TRACE_ALWAYS, "yaffs removing.");
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 9, 0))
+	remove_proc_entry("yaffs", YPROC_ROOT);
+#endif
+
+	fsinst = fs_to_install;
+
+	while (fsinst->fst) {
+		if (fsinst->installed) {
+			unregister_filesystem(fsinst->fst);
+			fsinst->installed = 0;
+		}
+		fsinst++;
+	}
+}
+
+module_init(init_yaffs_fs)
+    module_exit(exit_yaffs_fs)
+
+    MODULE_DESCRIPTION("YAFFS2 - a NAND specific flash file system");
+MODULE_AUTHOR("Charles Manning, Aleph One Ltd., 2002-2011");
+MODULE_LICENSE("GPL");
diff --git a/fs/yaffs2/yaffs_yaffs1.c b/fs/yaffs2/yaffs_yaffs1.c
new file mode 100644
index 000000000000..d277e20e2a55
--- /dev/null
+++ b/fs/yaffs2/yaffs_yaffs1.c
@@ -0,0 +1,422 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_yaffs1.h"
+#include "yportenv.h"
+#include "yaffs_trace.h"
+#include "yaffs_bitmap.h"
+#include "yaffs_getblockinfo.h"
+#include "yaffs_nand.h"
+#include "yaffs_attribs.h"
+
+int yaffs1_scan(struct yaffs_dev *dev)
+{
+	struct yaffs_ext_tags tags;
+	int blk;
+	int result;
+	int chunk;
+	int c;
+	int deleted;
+	enum yaffs_block_state state;
+	LIST_HEAD(hard_list);
+	struct yaffs_block_info *bi;
+	u32 seq_number;
+	struct yaffs_obj_hdr *oh;
+	struct yaffs_obj *in;
+	struct yaffs_obj *parent;
+	int alloc_failed = 0;
+	struct yaffs_shadow_fixer *shadow_fixers = NULL;
+	u8 *chunk_data;
+
+	yaffs_trace(YAFFS_TRACE_SCAN,
+		"yaffs1_scan starts  intstartblk %d intendblk %d...",
+		dev->internal_start_block, dev->internal_end_block);
+
+	chunk_data = yaffs_get_temp_buffer(dev);
+
+	dev->seq_number = YAFFS_LOWEST_SEQUENCE_NUMBER;
+
+	/* Scan all the blocks to determine their state */
+	bi = dev->block_info;
+	for (blk = dev->internal_start_block; blk <= dev->internal_end_block;
+	     blk++) {
+		yaffs_clear_chunk_bits(dev, blk);
+		bi->pages_in_use = 0;
+		bi->soft_del_pages = 0;
+
+		yaffs_query_init_block_state(dev, blk, &state, &seq_number);
+
+		bi->block_state = state;
+		bi->seq_number = seq_number;
+
+		if (bi->seq_number == YAFFS_SEQUENCE_BAD_BLOCK)
+			bi->block_state = state = YAFFS_BLOCK_STATE_DEAD;
+
+		yaffs_trace(YAFFS_TRACE_SCAN_DEBUG,
+			"Block scanning block %d state %d seq %d",
+			blk, state, seq_number);
+
+		if (state == YAFFS_BLOCK_STATE_DEAD) {
+			yaffs_trace(YAFFS_TRACE_BAD_BLOCKS,
+				"block %d is bad", blk);
+		} else if (state == YAFFS_BLOCK_STATE_EMPTY) {
+			yaffs_trace(YAFFS_TRACE_SCAN_DEBUG, "Block empty ");
+			dev->n_erased_blocks++;
+			dev->n_free_chunks += dev->param.chunks_per_block;
+		}
+		bi++;
+	}
+
+	/* For each block.... */
+	for (blk = dev->internal_start_block;
+	     !alloc_failed && blk <= dev->internal_end_block; blk++) {
+
+		cond_resched();
+
+		bi = yaffs_get_block_info(dev, blk);
+		state = bi->block_state;
+
+		deleted = 0;
+
+		/* For each chunk in each block that needs scanning.... */
+		for (c = 0;
+			!alloc_failed && c < dev->param.chunks_per_block &&
+			state == YAFFS_BLOCK_STATE_NEEDS_SCAN; c++) {
+			/* Read the tags and decide what to do */
+			chunk = blk * dev->param.chunks_per_block + c;
+
+			result = yaffs_rd_chunk_tags_nand(dev, chunk, NULL,
+							  &tags);
+
+			/* Let's have a good look at this chunk... */
+
+			if (tags.ecc_result == YAFFS_ECC_RESULT_UNFIXED ||
+			    tags.is_deleted) {
+				/* YAFFS1 only...
+				 * A deleted chunk
+				 */
+				deleted++;
+				dev->n_free_chunks++;
+			} else if (!tags.chunk_used) {
+				/* An unassigned chunk in the block
+				 * This means that either the block is empty or
+				 * this is the one being allocated from
+				 */
+
+				if (c == 0) {
+					/* We're looking at the first chunk in
+					 *the block so the block is unused */
+					state = YAFFS_BLOCK_STATE_EMPTY;
+					dev->n_erased_blocks++;
+				} else {
+					/* this is the block being allocated */
+					yaffs_trace(YAFFS_TRACE_SCAN,
+						" Allocating from %d %d",
+						blk, c);
+					state = YAFFS_BLOCK_STATE_ALLOCATING;
+					dev->alloc_block = blk;
+					dev->alloc_page = c;
+					dev->alloc_block_finder = blk;
+
+				}
+
+				dev->n_free_chunks +=
+				    (dev->param.chunks_per_block - c);
+			} else if (tags.chunk_id > 0) {
+				/* chunk_id > 0 so it is a data chunk... */
+				unsigned int endpos;
+
+				yaffs_set_chunk_bit(dev, blk, c);
+				bi->pages_in_use++;
+
+				in = yaffs_find_or_create_by_number(dev,
+							tags.obj_id,
+							YAFFS_OBJECT_TYPE_FILE);
+				/* PutChunkIntoFile checks for a clash
+				 * (two data chunks with the same chunk_id).
+				 */
+
+				if (!in)
+					alloc_failed = 1;
+
+				if (in) {
+					if (!yaffs_put_chunk_in_file
+					    (in, tags.chunk_id, chunk, 1))
+						alloc_failed = 1;
+				}
+
+				endpos =
+				    (tags.chunk_id - 1) *
+				    dev->data_bytes_per_chunk +
+				    tags.n_bytes;
+				if (in &&
+				    in->variant_type ==
+				     YAFFS_OBJECT_TYPE_FILE &&
+				    in->variant.file_variant.scanned_size <
+				      endpos) {
+					in->variant.file_variant.scanned_size =
+					    endpos;
+					if (!dev->param.use_header_file_size) {
+						in->variant.
+						    file_variant.file_size =
+						    in->variant.
+						    file_variant.scanned_size;
+					}
+
+				}
+			} else {
+				/* chunk_id == 0, so it is an ObjectHeader.
+				 * Make the object
+				 */
+				yaffs_set_chunk_bit(dev, blk, c);
+				bi->pages_in_use++;
+
+				result = yaffs_rd_chunk_tags_nand(dev, chunk,
+								  chunk_data,
+								  NULL);
+
+				oh = (struct yaffs_obj_hdr *)chunk_data;
+
+				in = yaffs_find_by_number(dev, tags.obj_id);
+				if (in && in->variant_type != oh->type) {
+					/* This should not happen, but somehow
+					 * Wev'e ended up with an obj_id that
+					 * has been reused but not yet deleted,
+					 * and worse still it has changed type.
+					 * Delete the old object.
+					 */
+
+					yaffs_del_obj(in);
+					in = NULL;
+				}
+
+				in = yaffs_find_or_create_by_number(dev,
+								tags.obj_id,
+								oh->type);
+
+				if (!in)
+					alloc_failed = 1;
+
+				if (in && oh->shadows_obj > 0) {
+
+					struct yaffs_shadow_fixer *fixer;
+					fixer =
+						kmalloc(sizeof
+						(struct yaffs_shadow_fixer),
+						GFP_NOFS);
+					if (fixer) {
+						fixer->next = shadow_fixers;
+						shadow_fixers = fixer;
+						fixer->obj_id = tags.obj_id;
+						fixer->shadowed_id =
+						    oh->shadows_obj;
+						yaffs_trace(YAFFS_TRACE_SCAN,
+							" Shadow fixer: %d shadows %d",
+							fixer->obj_id,
+							fixer->shadowed_id);
+
+					}
+
+				}
+
+				if (in && in->valid) {
+					/* We have already filled this one.
+					 * We have a duplicate and need to
+					 * resolve it. */
+
+					unsigned existing_serial = in->serial;
+					unsigned new_serial =
+					    tags.serial_number;
+
+					if (((existing_serial + 1) & 3) ==
+					    new_serial) {
+						/* Use new one - destroy the
+						 * exisiting one */
+						yaffs_chunk_del(dev,
+								in->hdr_chunk,
+								1, __LINE__);
+						in->valid = 0;
+					} else {
+						/* Use existing - destroy
+						 * this one. */
+						yaffs_chunk_del(dev, chunk, 1,
+								__LINE__);
+					}
+				}
+
+				if (in && !in->valid &&
+				    (tags.obj_id == YAFFS_OBJECTID_ROOT ||
+				     tags.obj_id ==
+				     YAFFS_OBJECTID_LOSTNFOUND)) {
+					/* We only load some info, don't fiddle
+					 * with directory structure */
+					in->valid = 1;
+					in->variant_type = oh->type;
+
+					in->yst_mode = oh->yst_mode;
+					yaffs_load_attribs(in, oh);
+					in->hdr_chunk = chunk;
+					in->serial = tags.serial_number;
+
+				} else if (in && !in->valid) {
+					/* we need to load this info */
+
+					in->valid = 1;
+					in->variant_type = oh->type;
+
+					in->yst_mode = oh->yst_mode;
+					yaffs_load_attribs(in, oh);
+					in->hdr_chunk = chunk;
+					in->serial = tags.serial_number;
+
+					yaffs_set_obj_name_from_oh(in, oh);
+					in->dirty = 0;
+
+					/* directory stuff...
+					 * hook up to parent
+					 */
+
+					parent =
+					    yaffs_find_or_create_by_number
+					    (dev, oh->parent_obj_id,
+					     YAFFS_OBJECT_TYPE_DIRECTORY);
+					if (!parent)
+						alloc_failed = 1;
+					if (parent && parent->variant_type ==
+					    YAFFS_OBJECT_TYPE_UNKNOWN) {
+						/* Set up as a directory */
+						parent->variant_type =
+						    YAFFS_OBJECT_TYPE_DIRECTORY;
+						INIT_LIST_HEAD(&parent->
+							variant.dir_variant.
+							children);
+					} else if (!parent ||
+						parent->variant_type !=
+						YAFFS_OBJECT_TYPE_DIRECTORY) {
+						/* Hoosterman, a problem....
+						 * We're trying to use a
+						 * non-directory as a directory
+						 */
+
+						yaffs_trace(YAFFS_TRACE_ERROR,
+							"yaffs tragedy: attempting to use non-directory as a directory in scan. Put in lost+found."
+							);
+						parent = dev->lost_n_found;
+					}
+
+					yaffs_add_obj_to_dir(parent, in);
+
+					switch (in->variant_type) {
+					case YAFFS_OBJECT_TYPE_UNKNOWN:
+						/* Todo got a problem */
+						break;
+					case YAFFS_OBJECT_TYPE_FILE:
+						if (dev->param.
+						    use_header_file_size)
+							in->variant.
+							file_variant.file_size
+							= yaffs_oh_to_size(oh);
+						break;
+					case YAFFS_OBJECT_TYPE_HARDLINK:
+						in->variant.
+						    hardlink_variant.equiv_id =
+						    oh->equiv_id;
+						list_add(&in->hard_links,
+								&hard_list);
+						break;
+					case YAFFS_OBJECT_TYPE_DIRECTORY:
+						/* Do nothing */
+						break;
+					case YAFFS_OBJECT_TYPE_SPECIAL:
+						/* Do nothing */
+						break;
+					case YAFFS_OBJECT_TYPE_SYMLINK:
+						in->variant.symlink_variant.
+						    alias =
+						    yaffs_clone_str(oh->alias);
+						if (!in->variant.
+						    symlink_variant.alias)
+							alloc_failed = 1;
+						break;
+					}
+				}
+			}
+		}
+
+		if (state == YAFFS_BLOCK_STATE_NEEDS_SCAN) {
+			/* If we got this far while scanning,
+			 * then the block is fully allocated. */
+			state = YAFFS_BLOCK_STATE_FULL;
+		}
+
+		if (state == YAFFS_BLOCK_STATE_ALLOCATING) {
+			/* If the block was partially allocated then
+			 * treat it as fully allocated. */
+			state = YAFFS_BLOCK_STATE_FULL;
+			dev->alloc_block = -1;
+		}
+
+		bi->block_state = state;
+
+		/* Now let's see if it was dirty */
+		if (bi->pages_in_use == 0 &&
+		    !bi->has_shrink_hdr &&
+		    bi->block_state == YAFFS_BLOCK_STATE_FULL)
+			yaffs_block_became_dirty(dev, blk);
+	}
+
+	/* Ok, we've done all the scanning.
+	 * Fix up the hard link chains.
+	 * We should now have scanned all the objects, now it's time to add
+	 * these hardlinks.
+	 */
+
+	yaffs_link_fixup(dev, &hard_list);
+
+	/*
+	 * Fix up any shadowed objects.
+	 * There should not be more than one of these.
+	 */
+	{
+		struct yaffs_shadow_fixer *fixer;
+		struct yaffs_obj *obj;
+
+		while (shadow_fixers) {
+			fixer = shadow_fixers;
+			shadow_fixers = fixer->next;
+			/* Complete the rename transaction by deleting the
+			 * shadowed object then setting the object header
+			 to unshadowed.
+			 */
+			obj = yaffs_find_by_number(dev, fixer->shadowed_id);
+			if (obj)
+				yaffs_del_obj(obj);
+
+			obj = yaffs_find_by_number(dev, fixer->obj_id);
+
+			if (obj)
+				yaffs_update_oh(obj, NULL, 1, 0, 0, NULL);
+
+			kfree(fixer);
+		}
+	}
+
+	yaffs_release_temp_buffer(dev, chunk_data);
+
+	if (alloc_failed)
+		return YAFFS_FAIL;
+
+	yaffs_trace(YAFFS_TRACE_SCAN, "yaffs1_scan ends");
+
+	return YAFFS_OK;
+}
diff --git a/fs/yaffs2/yaffs_yaffs1.h b/fs/yaffs2/yaffs_yaffs1.h
new file mode 100644
index 000000000000..97e2fdd08a5d
--- /dev/null
+++ b/fs/yaffs2/yaffs_yaffs1.h
@@ -0,0 +1,22 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_YAFFS1_H__
+#define __YAFFS_YAFFS1_H__
+
+#include "yaffs_guts.h"
+int yaffs1_scan(struct yaffs_dev *dev);
+
+#endif
diff --git a/fs/yaffs2/yaffs_yaffs2.c b/fs/yaffs2/yaffs_yaffs2.c
new file mode 100644
index 000000000000..f1dc972276f7
--- /dev/null
+++ b/fs/yaffs2/yaffs_yaffs2.c
@@ -0,0 +1,1532 @@
+/*
+ * YAFFS: Yet Another Flash File System. A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "yaffs_guts.h"
+#include "yaffs_trace.h"
+#include "yaffs_yaffs2.h"
+#include "yaffs_checkptrw.h"
+#include "yaffs_bitmap.h"
+#include "yaffs_nand.h"
+#include "yaffs_getblockinfo.h"
+#include "yaffs_verify.h"
+#include "yaffs_attribs.h"
+#include "yaffs_summary.h"
+
+/*
+ * Checkpoints are really no benefit on very small partitions.
+ *
+ * To save space on small partitions don't bother with checkpoints unless
+ * the partition is at least this big.
+ */
+#define YAFFS_CHECKPOINT_MIN_BLOCKS 60
+#define YAFFS_SMALL_HOLE_THRESHOLD 4
+
+/*
+ * Oldest Dirty Sequence Number handling.
+ */
+
+/* yaffs_calc_oldest_dirty_seq()
+ * yaffs2_find_oldest_dirty_seq()
+ * Calculate the oldest dirty sequence number if we don't know it.
+ */
+void yaffs_calc_oldest_dirty_seq(struct yaffs_dev *dev)
+{
+	int i;
+	unsigned seq;
+	unsigned block_no = 0;
+	struct yaffs_block_info *b;
+
+	if (!dev->param.is_yaffs2)
+		return;
+
+	/* Find the oldest dirty sequence number. */
+	seq = dev->seq_number + 1;
+	b = dev->block_info;
+	for (i = dev->internal_start_block; i <= dev->internal_end_block; i++) {
+		if (b->block_state == YAFFS_BLOCK_STATE_FULL &&
+		    (b->pages_in_use - b->soft_del_pages) <
+		    dev->param.chunks_per_block &&
+		    b->seq_number < seq) {
+			seq = b->seq_number;
+			block_no = i;
+		}
+		b++;
+	}
+
+	if (block_no) {
+		dev->oldest_dirty_seq = seq;
+		dev->oldest_dirty_block = block_no;
+	}
+}
+
+void yaffs2_find_oldest_dirty_seq(struct yaffs_dev *dev)
+{
+	if (!dev->param.is_yaffs2)
+		return;
+
+	if (!dev->oldest_dirty_seq)
+		yaffs_calc_oldest_dirty_seq(dev);
+}
+
+/*
+ * yaffs_clear_oldest_dirty_seq()
+ * Called when a block is erased or marked bad. (ie. when its seq_number
+ * becomes invalid). If the value matches the oldest then we clear
+ * dev->oldest_dirty_seq to force its recomputation.
+ */
+void yaffs2_clear_oldest_dirty_seq(struct yaffs_dev *dev,
+				   struct yaffs_block_info *bi)
+{
+
+	if (!dev->param.is_yaffs2)
+		return;
+
+	if (!bi || bi->seq_number == dev->oldest_dirty_seq) {
+		dev->oldest_dirty_seq = 0;
+		dev->oldest_dirty_block = 0;
+	}
+}
+
+/*
+ * yaffs2_update_oldest_dirty_seq()
+ * Update the oldest dirty sequence number whenever we dirty a block.
+ * Only do this if the oldest_dirty_seq is actually being tracked.
+ */
+void yaffs2_update_oldest_dirty_seq(struct yaffs_dev *dev, unsigned block_no,
+				    struct yaffs_block_info *bi)
+{
+	if (!dev->param.is_yaffs2)
+		return;
+
+	if (dev->oldest_dirty_seq) {
+		if (dev->oldest_dirty_seq > bi->seq_number) {
+			dev->oldest_dirty_seq = bi->seq_number;
+			dev->oldest_dirty_block = block_no;
+		}
+	}
+}
+
+int yaffs_block_ok_for_gc(struct yaffs_dev *dev, struct yaffs_block_info *bi)
+{
+
+	if (!dev->param.is_yaffs2)
+		return 1;	/* disqualification only applies to yaffs2. */
+
+	if (!bi->has_shrink_hdr)
+		return 1;	/* can gc */
+
+	yaffs2_find_oldest_dirty_seq(dev);
+
+	/* Can't do gc of this block if there are any blocks older than this
+	 * one that have discarded pages.
+	 */
+	return (bi->seq_number <= dev->oldest_dirty_seq);
+}
+
+/*
+ * yaffs2_find_refresh_block()
+ * periodically finds the oldest full block by sequence number for refreshing.
+ * Only for yaffs2.
+ */
+u32 yaffs2_find_refresh_block(struct yaffs_dev *dev)
+{
+	u32 b;
+	u32 oldest = 0;
+	u32 oldest_seq = 0;
+	struct yaffs_block_info *bi;
+
+	if (!dev->param.is_yaffs2)
+		return oldest;
+
+	/*
+	 * If refresh period < 10 then refreshing is disabled.
+	 */
+	if (dev->param.refresh_period < 10)
+		return oldest;
+
+	/*
+	 * Fix broken values.
+	 */
+	if (dev->refresh_skip > dev->param.refresh_period)
+		dev->refresh_skip = dev->param.refresh_period;
+
+	if (dev->refresh_skip > 0)
+		return oldest;
+
+	/*
+	 * Refresh skip is now zero.
+	 * We'll do a refresh this time around....
+	 * Update the refresh skip and find the oldest block.
+	 */
+	dev->refresh_skip = dev->param.refresh_period;
+	dev->refresh_count++;
+	bi = dev->block_info;
+	for (b = dev->internal_start_block; b <= dev->internal_end_block; b++) {
+
+		if (bi->block_state == YAFFS_BLOCK_STATE_FULL) {
+
+			if (oldest < 1 || bi->seq_number < oldest_seq) {
+				oldest = b;
+				oldest_seq = bi->seq_number;
+			}
+		}
+		bi++;
+	}
+
+	if (oldest > 0) {
+		yaffs_trace(YAFFS_TRACE_GC,
+			"GC refresh count %d selected block %d with seq_number %d",
+			dev->refresh_count, oldest, oldest_seq);
+	}
+
+	return oldest;
+}
+
+int yaffs2_checkpt_required(struct yaffs_dev *dev)
+{
+	int nblocks;
+
+	if (!dev->param.is_yaffs2)
+		return 0;
+
+	nblocks = dev->internal_end_block - dev->internal_start_block + 1;
+
+	return !dev->param.skip_checkpt_wr &&
+	    !dev->read_only && (nblocks >= YAFFS_CHECKPOINT_MIN_BLOCKS);
+}
+
+int yaffs_calc_checkpt_blocks_required(struct yaffs_dev *dev)
+{
+	int retval;
+	int n_bytes = 0;
+	int n_blocks;
+	int dev_blocks;
+
+	if (!dev->param.is_yaffs2)
+		return 0;
+
+	if (!dev->checkpoint_blocks_required && yaffs2_checkpt_required(dev)) {
+		/* Not a valid value so recalculate */
+		dev_blocks = dev->param.end_block - dev->param.start_block + 1;
+		n_bytes += sizeof(struct yaffs_checkpt_validity);
+		n_bytes += sizeof(struct yaffs_checkpt_dev);
+		n_bytes += dev_blocks * sizeof(struct yaffs_block_info);
+		n_bytes += dev_blocks * dev->chunk_bit_stride;
+		n_bytes +=
+		    (sizeof(struct yaffs_checkpt_obj) + sizeof(u32)) *
+		    dev->n_obj;
+		n_bytes += (dev->tnode_size + sizeof(u32)) * dev->n_tnodes;
+		n_bytes += sizeof(struct yaffs_checkpt_validity);
+		n_bytes += sizeof(u32);	/* checksum */
+
+		/* Round up and add 2 blocks to allow for some bad blocks,
+		 * so add 3 */
+
+		n_blocks =
+		    (n_bytes /
+		     (dev->data_bytes_per_chunk *
+		      dev->param.chunks_per_block)) + 3;
+
+		dev->checkpoint_blocks_required = n_blocks;
+	}
+
+	retval = dev->checkpoint_blocks_required - dev->blocks_in_checkpt;
+	if (retval < 0)
+		retval = 0;
+	return retval;
+}
+
+/*--------------------- Checkpointing --------------------*/
+
+static int yaffs2_wr_checkpt_validity_marker(struct yaffs_dev *dev, int head)
+{
+	struct yaffs_checkpt_validity cp;
+
+	memset(&cp, 0, sizeof(cp));
+
+	cp.struct_type = sizeof(cp);
+	cp.magic = YAFFS_MAGIC;
+	cp.version = YAFFS_CHECKPOINT_VERSION;
+	cp.head = (head) ? 1 : 0;
+
+	return (yaffs2_checkpt_wr(dev, &cp, sizeof(cp)) == sizeof(cp)) ? 1 : 0;
+}
+
+static int yaffs2_rd_checkpt_validity_marker(struct yaffs_dev *dev, int head)
+{
+	struct yaffs_checkpt_validity cp;
+	int ok;
+
+	ok = (yaffs2_checkpt_rd(dev, &cp, sizeof(cp)) == sizeof(cp));
+
+	if (ok)
+		ok = (cp.struct_type == sizeof(cp)) &&
+		    (cp.magic == YAFFS_MAGIC) &&
+		    (cp.version == YAFFS_CHECKPOINT_VERSION) &&
+		    (cp.head == ((head) ? 1 : 0));
+	return ok ? 1 : 0;
+}
+
+static void yaffs2_dev_to_checkpt_dev(struct yaffs_checkpt_dev *cp,
+				      struct yaffs_dev *dev)
+{
+	cp->n_erased_blocks = dev->n_erased_blocks;
+	cp->alloc_block = dev->alloc_block;
+	cp->alloc_page = dev->alloc_page;
+	cp->n_free_chunks = dev->n_free_chunks;
+
+	cp->n_deleted_files = dev->n_deleted_files;
+	cp->n_unlinked_files = dev->n_unlinked_files;
+	cp->n_bg_deletions = dev->n_bg_deletions;
+	cp->seq_number = dev->seq_number;
+
+}
+
+static void yaffs_checkpt_dev_to_dev(struct yaffs_dev *dev,
+				     struct yaffs_checkpt_dev *cp)
+{
+	dev->n_erased_blocks = cp->n_erased_blocks;
+	dev->alloc_block = cp->alloc_block;
+	dev->alloc_page = cp->alloc_page;
+	dev->n_free_chunks = cp->n_free_chunks;
+
+	dev->n_deleted_files = cp->n_deleted_files;
+	dev->n_unlinked_files = cp->n_unlinked_files;
+	dev->n_bg_deletions = cp->n_bg_deletions;
+	dev->seq_number = cp->seq_number;
+}
+
+static int yaffs2_wr_checkpt_dev(struct yaffs_dev *dev)
+{
+	struct yaffs_checkpt_dev cp;
+	u32 n_bytes;
+	u32 n_blocks = dev->internal_end_block - dev->internal_start_block + 1;
+	int ok;
+
+	/* Write device runtime values */
+	yaffs2_dev_to_checkpt_dev(&cp, dev);
+	cp.struct_type = sizeof(cp);
+
+	ok = (yaffs2_checkpt_wr(dev, &cp, sizeof(cp)) == sizeof(cp));
+	if (!ok)
+		return 0;
+
+	/* Write block info */
+	n_bytes = n_blocks * sizeof(struct yaffs_block_info);
+	ok = (yaffs2_checkpt_wr(dev, dev->block_info, n_bytes) == n_bytes);
+	if (!ok)
+		return 0;
+
+	/* Write chunk bits */
+	n_bytes = n_blocks * dev->chunk_bit_stride;
+	ok = (yaffs2_checkpt_wr(dev, dev->chunk_bits, n_bytes) == n_bytes);
+
+	return ok ? 1 : 0;
+}
+
+static int yaffs2_rd_checkpt_dev(struct yaffs_dev *dev)
+{
+	struct yaffs_checkpt_dev cp;
+	u32 n_bytes;
+	u32 n_blocks =
+	    (dev->internal_end_block - dev->internal_start_block + 1);
+	int ok;
+
+	ok = (yaffs2_checkpt_rd(dev, &cp, sizeof(cp)) == sizeof(cp));
+	if (!ok)
+		return 0;
+
+	if (cp.struct_type != sizeof(cp))
+		return 0;
+
+	yaffs_checkpt_dev_to_dev(dev, &cp);
+
+	n_bytes = n_blocks * sizeof(struct yaffs_block_info);
+
+	ok = (yaffs2_checkpt_rd(dev, dev->block_info, n_bytes) == n_bytes);
+
+	if (!ok)
+		return 0;
+
+	n_bytes = n_blocks * dev->chunk_bit_stride;
+
+	ok = (yaffs2_checkpt_rd(dev, dev->chunk_bits, n_bytes) == n_bytes);
+
+	return ok ? 1 : 0;
+}
+
+static void yaffs2_obj_checkpt_obj(struct yaffs_checkpt_obj *cp,
+				   struct yaffs_obj *obj)
+{
+	cp->obj_id = obj->obj_id;
+	cp->parent_id = (obj->parent) ? obj->parent->obj_id : 0;
+	cp->hdr_chunk = obj->hdr_chunk;
+	cp->variant_type = obj->variant_type;
+	cp->deleted = obj->deleted;
+	cp->soft_del = obj->soft_del;
+	cp->unlinked = obj->unlinked;
+	cp->fake = obj->fake;
+	cp->rename_allowed = obj->rename_allowed;
+	cp->unlink_allowed = obj->unlink_allowed;
+	cp->serial = obj->serial;
+	cp->n_data_chunks = obj->n_data_chunks;
+
+	if (obj->variant_type == YAFFS_OBJECT_TYPE_FILE)
+		cp->size_or_equiv_obj = obj->variant.file_variant.file_size;
+	else if (obj->variant_type == YAFFS_OBJECT_TYPE_HARDLINK)
+		cp->size_or_equiv_obj = obj->variant.hardlink_variant.equiv_id;
+}
+
+static int yaffs2_checkpt_obj_to_obj(struct yaffs_obj *obj,
+				     struct yaffs_checkpt_obj *cp)
+{
+	struct yaffs_obj *parent;
+
+	if (obj->variant_type != cp->variant_type) {
+		yaffs_trace(YAFFS_TRACE_ERROR,
+			"Checkpoint read object %d type %d chunk %d does not match existing object type %d",
+			cp->obj_id, cp->variant_type, cp->hdr_chunk,
+			obj->variant_type);
+		return 0;
+	}
+
+	obj->obj_id = cp->obj_id;
+
+	if (cp->parent_id)
+		parent = yaffs_find_or_create_by_number(obj->my_dev,
+						cp->parent_id,
+						YAFFS_OBJECT_TYPE_DIRECTORY);
+	else
+		parent = NULL;
+
+	if (parent) {
+		if (parent->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) {
+			yaffs_trace(YAFFS_TRACE_ALWAYS,
+				"Checkpoint read object %d parent %d type %d chunk %d Parent type, %d, not directory",
+				cp->obj_id, cp->parent_id,
+				cp->variant_type, cp->hdr_chunk,
+				parent->variant_type);
+			return 0;
+		}
+		yaffs_add_obj_to_dir(parent, obj);
+	}
+
+	obj->hdr_chunk = cp->hdr_chunk;
+	obj->variant_type = cp->variant_type;
+	obj->deleted = cp->deleted;
+	obj->soft_del = cp->soft_del;
+	obj->unlinked = cp->unlinked;
+	obj->fake = cp->fake;
+	obj->rename_allowed = cp->rename_allowed;
+	obj->unlink_allowed = cp->unlink_allowed;
+	obj->serial = cp->serial;
+	obj->n_data_chunks = cp->n_data_chunks;
+
+	if (obj->variant_type == YAFFS_OBJECT_TYPE_FILE)
+		obj->variant.file_variant.file_size = cp->size_or_equiv_obj;
+	else if (obj->variant_type == YAFFS_OBJECT_TYPE_HARDLINK)
+		obj->variant.hardlink_variant.equiv_id = cp->size_or_equiv_obj;
+
+	if (obj->hdr_chunk > 0)
+		obj->lazy_loaded = 1;
+	return 1;
+}
+
+static int yaffs2_checkpt_tnode_worker(struct yaffs_obj *in,
+				       struct yaffs_tnode *tn, u32 level,
+				       int chunk_offset)
+{
+	int i;
+	struct yaffs_dev *dev = in->my_dev;
+	int ok = 1;
+	u32 base_offset;
+
+	if (!tn)
+		return 1;
+
+	if (level > 0) {
+		for (i = 0; i < YAFFS_NTNODES_INTERNAL && ok; i++) {
+			if (!tn->internal[i])
+				continue;
+			ok = yaffs2_checkpt_tnode_worker(in,
+				 tn->internal[i],
+				 level - 1,
+				 (chunk_offset <<
+				  YAFFS_TNODES_INTERNAL_BITS) + i);
+		}
+		return ok;
+	}
+
+	/* Level 0 tnode */
+	base_offset = chunk_offset << YAFFS_TNODES_LEVEL0_BITS;
+	ok = (yaffs2_checkpt_wr(dev, &base_offset, sizeof(base_offset)) ==
+			sizeof(base_offset));
+	if (ok)
+		ok = (yaffs2_checkpt_wr(dev, tn, dev->tnode_size) ==
+			dev->tnode_size);
+
+	return ok;
+}
+
+static int yaffs2_wr_checkpt_tnodes(struct yaffs_obj *obj)
+{
+	u32 end_marker = ~0;
+	int ok = 1;
+
+	if (obj->variant_type != YAFFS_OBJECT_TYPE_FILE)
+		return ok;
+
+	ok = yaffs2_checkpt_tnode_worker(obj,
+					 obj->variant.file_variant.top,
+					 obj->variant.file_variant.
+					 top_level, 0);
+	if (ok)
+		ok = (yaffs2_checkpt_wr(obj->my_dev, &end_marker,
+				sizeof(end_marker)) == sizeof(end_marker));
+
+	return ok ? 1 : 0;
+}
+
+static int yaffs2_rd_checkpt_tnodes(struct yaffs_obj *obj)
+{
+	u32 base_chunk;
+	int ok = 1;
+	struct yaffs_dev *dev = obj->my_dev;
+	struct yaffs_file_var *file_stuct_ptr = &obj->variant.file_variant;
+	struct yaffs_tnode *tn;
+	int nread = 0;
+
+	ok = (yaffs2_checkpt_rd(dev, &base_chunk, sizeof(base_chunk)) ==
+	      sizeof(base_chunk));
+
+	while (ok && (~base_chunk)) {
+		nread++;
+		/* Read level 0 tnode */
+
+		tn = yaffs_get_tnode(dev);
+		if (tn)
+			ok = (yaffs2_checkpt_rd(dev, tn, dev->tnode_size) ==
+				dev->tnode_size);
+		else
+			ok = 0;
+
+		if (tn && ok)
+			ok = yaffs_add_find_tnode_0(dev,
+						    file_stuct_ptr,
+						    base_chunk, tn) ? 1 : 0;
+
+		if (ok)
+			ok = (yaffs2_checkpt_rd
+			      (dev, &base_chunk,
+			       sizeof(base_chunk)) == sizeof(base_chunk));
+	}
+
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+		"Checkpoint read tnodes %d records, last %d. ok %d",
+		nread, base_chunk, ok);
+
+	return ok ? 1 : 0;
+}
+
+static int yaffs2_wr_checkpt_objs(struct yaffs_dev *dev)
+{
+	struct yaffs_obj *obj;
+	struct yaffs_checkpt_obj cp;
+	int i;
+	int ok = 1;
+	struct list_head *lh;
+
+	/* Iterate through the objects in each hash entry,
+	 * dumping them to the checkpointing stream.
+	 */
+
+	for (i = 0; ok && i < YAFFS_NOBJECT_BUCKETS; i++) {
+		list_for_each(lh, &dev->obj_bucket[i].list) {
+			obj = list_entry(lh, struct yaffs_obj, hash_link);
+			if (!obj->defered_free) {
+				yaffs2_obj_checkpt_obj(&cp, obj);
+				cp.struct_type = sizeof(cp);
+
+				yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+					"Checkpoint write object %d parent %d type %d chunk %d obj addr %p",
+					cp.obj_id, cp.parent_id,
+					cp.variant_type, cp.hdr_chunk, obj);
+
+				ok = (yaffs2_checkpt_wr(dev, &cp,
+						sizeof(cp)) == sizeof(cp));
+
+				if (ok &&
+					obj->variant_type ==
+					YAFFS_OBJECT_TYPE_FILE)
+					ok = yaffs2_wr_checkpt_tnodes(obj);
+			}
+		}
+	}
+
+	/* Dump end of list */
+	memset(&cp, 0xff, sizeof(struct yaffs_checkpt_obj));
+	cp.struct_type = sizeof(cp);
+
+	if (ok)
+		ok = (yaffs2_checkpt_wr(dev, &cp, sizeof(cp)) == sizeof(cp));
+
+	return ok ? 1 : 0;
+}
+
+static int yaffs2_rd_checkpt_objs(struct yaffs_dev *dev)
+{
+	struct yaffs_obj *obj;
+	struct yaffs_checkpt_obj cp;
+	int ok = 1;
+	int done = 0;
+	LIST_HEAD(hard_list);
+
+
+	while (ok && !done) {
+		ok = (yaffs2_checkpt_rd(dev, &cp, sizeof(cp)) == sizeof(cp));
+		if (cp.struct_type != sizeof(cp)) {
+			yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+				"struct size %d instead of %d ok %d",
+				cp.struct_type, (int)sizeof(cp), ok);
+			ok = 0;
+		}
+
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"Checkpoint read object %d parent %d type %d chunk %d ",
+			cp.obj_id, cp.parent_id, cp.variant_type,
+			cp.hdr_chunk);
+
+		if (ok && cp.obj_id == ~0) {
+			done = 1;
+		} else if (ok) {
+			obj =
+			    yaffs_find_or_create_by_number(dev, cp.obj_id,
+							   cp.variant_type);
+			if (obj) {
+				ok = yaffs2_checkpt_obj_to_obj(obj, &cp);
+				if (!ok)
+					break;
+				if (obj->variant_type ==
+					YAFFS_OBJECT_TYPE_FILE) {
+					ok = yaffs2_rd_checkpt_tnodes(obj);
+				} else if (obj->variant_type ==
+					YAFFS_OBJECT_TYPE_HARDLINK) {
+					list_add(&obj->hard_links, &hard_list);
+				}
+			} else {
+				ok = 0;
+			}
+		}
+	}
+
+	if (ok)
+		yaffs_link_fixup(dev, &hard_list);
+
+	return ok ? 1 : 0;
+}
+
+static int yaffs2_wr_checkpt_sum(struct yaffs_dev *dev)
+{
+	u32 checkpt_sum;
+	int ok;
+
+	yaffs2_get_checkpt_sum(dev, &checkpt_sum);
+
+	ok = (yaffs2_checkpt_wr(dev, &checkpt_sum, sizeof(checkpt_sum)) ==
+		sizeof(checkpt_sum));
+
+	if (!ok)
+		return 0;
+
+	return 1;
+}
+
+static int yaffs2_rd_checkpt_sum(struct yaffs_dev *dev)
+{
+	u32 checkpt_sum0;
+	u32 checkpt_sum1;
+	int ok;
+
+	yaffs2_get_checkpt_sum(dev, &checkpt_sum0);
+
+	ok = (yaffs2_checkpt_rd(dev, &checkpt_sum1, sizeof(checkpt_sum1)) ==
+		sizeof(checkpt_sum1));
+
+	if (!ok)
+		return 0;
+
+	if (checkpt_sum0 != checkpt_sum1)
+		return 0;
+
+	return 1;
+}
+
+static int yaffs2_wr_checkpt_data(struct yaffs_dev *dev)
+{
+	int ok = 1;
+
+	if (!yaffs2_checkpt_required(dev)) {
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"skipping checkpoint write");
+		ok = 0;
+	}
+
+	if (ok)
+		ok = yaffs2_checkpt_open(dev, 1);
+
+	if (ok) {
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"write checkpoint validity");
+		ok = yaffs2_wr_checkpt_validity_marker(dev, 1);
+	}
+	if (ok) {
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"write checkpoint device");
+		ok = yaffs2_wr_checkpt_dev(dev);
+	}
+	if (ok) {
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"write checkpoint objects");
+		ok = yaffs2_wr_checkpt_objs(dev);
+	}
+	if (ok) {
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"write checkpoint validity");
+		ok = yaffs2_wr_checkpt_validity_marker(dev, 0);
+	}
+
+	if (ok)
+		ok = yaffs2_wr_checkpt_sum(dev);
+
+	if (!yaffs_checkpt_close(dev))
+		ok = 0;
+
+	if (ok)
+		dev->is_checkpointed = 1;
+	else
+		dev->is_checkpointed = 0;
+
+	return dev->is_checkpointed;
+}
+
+static int yaffs2_rd_checkpt_data(struct yaffs_dev *dev)
+{
+	int ok = 1;
+
+	if (!dev->param.is_yaffs2)
+		ok = 0;
+
+	if (ok && dev->param.skip_checkpt_rd) {
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"skipping checkpoint read");
+		ok = 0;
+	}
+
+	if (ok)
+		ok = yaffs2_checkpt_open(dev, 0); /* open for read */
+
+	if (ok) {
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"read checkpoint validity");
+		ok = yaffs2_rd_checkpt_validity_marker(dev, 1);
+	}
+	if (ok) {
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"read checkpoint device");
+		ok = yaffs2_rd_checkpt_dev(dev);
+	}
+	if (ok) {
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"read checkpoint objects");
+		ok = yaffs2_rd_checkpt_objs(dev);
+	}
+	if (ok) {
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"read checkpoint validity");
+		ok = yaffs2_rd_checkpt_validity_marker(dev, 0);
+	}
+
+	if (ok) {
+		ok = yaffs2_rd_checkpt_sum(dev);
+		yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+			"read checkpoint checksum %d", ok);
+	}
+
+	if (!yaffs_checkpt_close(dev))
+		ok = 0;
+
+	if (ok)
+		dev->is_checkpointed = 1;
+	else
+		dev->is_checkpointed = 0;
+
+	return ok ? 1 : 0;
+}
+
+void yaffs2_checkpt_invalidate(struct yaffs_dev *dev)
+{
+	if (dev->is_checkpointed || dev->blocks_in_checkpt > 0) {
+		dev->is_checkpointed = 0;
+		yaffs2_checkpt_invalidate_stream(dev);
+	}
+	if (dev->param.sb_dirty_fn)
+		dev->param.sb_dirty_fn(dev);
+}
+
+int yaffs_checkpoint_save(struct yaffs_dev *dev)
+{
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+		"save entry: is_checkpointed %d",
+		dev->is_checkpointed);
+
+	yaffs_verify_objects(dev);
+	yaffs_verify_blocks(dev);
+	yaffs_verify_free_chunks(dev);
+
+	if (!dev->is_checkpointed) {
+		yaffs2_checkpt_invalidate(dev);
+		yaffs2_wr_checkpt_data(dev);
+	}
+
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT | YAFFS_TRACE_MOUNT,
+		"save exit: is_checkpointed %d",
+		dev->is_checkpointed);
+
+	return dev->is_checkpointed;
+}
+
+int yaffs2_checkpt_restore(struct yaffs_dev *dev)
+{
+	int retval;
+
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+		"restore entry: is_checkpointed %d",
+		dev->is_checkpointed);
+
+	retval = yaffs2_rd_checkpt_data(dev);
+
+	if (dev->is_checkpointed) {
+		yaffs_verify_objects(dev);
+		yaffs_verify_blocks(dev);
+		yaffs_verify_free_chunks(dev);
+	}
+
+	yaffs_trace(YAFFS_TRACE_CHECKPOINT,
+		"restore exit: is_checkpointed %d",
+		dev->is_checkpointed);
+
+	return retval;
+}
+
+int yaffs2_handle_hole(struct yaffs_obj *obj, loff_t new_size)
+{
+	/* if new_size > old_file_size.
+	 * We're going to be writing a hole.
+	 * If the hole is small then write zeros otherwise write a start
+	 * of hole marker.
+	 */
+	loff_t old_file_size;
+	loff_t increase;
+	int small_hole;
+	int result = YAFFS_OK;
+	struct yaffs_dev *dev = NULL;
+	u8 *local_buffer = NULL;
+	int small_increase_ok = 0;
+
+	if (!obj)
+		return YAFFS_FAIL;
+
+	if (obj->variant_type != YAFFS_OBJECT_TYPE_FILE)
+		return YAFFS_FAIL;
+
+	dev = obj->my_dev;
+
+	/* Bail out if not yaffs2 mode */
+	if (!dev->param.is_yaffs2)
+		return YAFFS_OK;
+
+	old_file_size = obj->variant.file_variant.file_size;
+
+	if (new_size <= old_file_size)
+		return YAFFS_OK;
+
+	increase = new_size - old_file_size;
+
+	if (increase < YAFFS_SMALL_HOLE_THRESHOLD * dev->data_bytes_per_chunk &&
+	    yaffs_check_alloc_available(dev, YAFFS_SMALL_HOLE_THRESHOLD + 1))
+		small_hole = 1;
+	else
+		small_hole = 0;
+
+	if (small_hole)
+		local_buffer = yaffs_get_temp_buffer(dev);
+
+	if (local_buffer) {
+		/* fill hole with zero bytes */
+		loff_t pos = old_file_size;
+		int this_write;
+		int written;
+		memset(local_buffer, 0, dev->data_bytes_per_chunk);
+		small_increase_ok = 1;
+
+		while (increase > 0 && small_increase_ok) {
+			this_write = increase;
+			if (this_write > dev->data_bytes_per_chunk)
+				this_write = dev->data_bytes_per_chunk;
+			written =
+			    yaffs_do_file_wr(obj, local_buffer, pos, this_write,
+					     0);
+			if (written == this_write) {
+				pos += this_write;
+				increase -= this_write;
+			} else {
+				small_increase_ok = 0;
+			}
+		}
+
+		yaffs_release_temp_buffer(dev, local_buffer);
+
+		/* If out of space then reverse any chunks we've added */
+		if (!small_increase_ok)
+			yaffs_resize_file_down(obj, old_file_size);
+	}
+
+	if (!small_increase_ok &&
+	    obj->parent &&
+	    obj->parent->obj_id != YAFFS_OBJECTID_UNLINKED &&
+	    obj->parent->obj_id != YAFFS_OBJECTID_DELETED) {
+		/* Write a hole start header with the old file size */
+		yaffs_update_oh(obj, NULL, 0, 1, 0, NULL);
+	}
+
+	return result;
+}
+
+struct yaffs_block_index {
+	int seq;
+	int block;
+};
+
+static int yaffs2_ybicmp(const void *a, const void *b)
+{
+	int aseq = ((struct yaffs_block_index *)a)->seq;
+	int bseq = ((struct yaffs_block_index *)b)->seq;
+	int ablock = ((struct yaffs_block_index *)a)->block;
+	int bblock = ((struct yaffs_block_index *)b)->block;
+
+	if (aseq == bseq)
+		return ablock - bblock;
+
+	return aseq - bseq;
+}
+
+static inline int yaffs2_scan_chunk(struct yaffs_dev *dev,
+		struct yaffs_block_info *bi,
+		int blk, int chunk_in_block,
+		int *found_chunks,
+		u8 *chunk_data,
+		struct list_head *hard_list,
+		int summary_available)
+{
+	struct yaffs_obj_hdr *oh;
+	struct yaffs_obj *in;
+	struct yaffs_obj *parent;
+	int equiv_id;
+	loff_t file_size;
+	int is_shrink;
+	int is_unlinked;
+	struct yaffs_ext_tags tags;
+	int result;
+	int alloc_failed = 0;
+	int chunk = blk * dev->param.chunks_per_block + chunk_in_block;
+	struct yaffs_file_var *file_var;
+	struct yaffs_hardlink_var *hl_var;
+	struct yaffs_symlink_var *sl_var;
+
+	if (summary_available) {
+		result = yaffs_summary_fetch(dev, &tags, chunk_in_block);
+		tags.seq_number = bi->seq_number;
+	}
+
+	if (!summary_available || tags.obj_id == 0) {
+		result = yaffs_rd_chunk_tags_nand(dev, chunk, NULL, &tags);
+		dev->tags_used++;
+	} else {
+		dev->summary_used++;
+	}
+
+	/* Let's have a good look at this chunk... */
+
+	if (!tags.chunk_used) {
+		/* An unassigned chunk in the block.
+		 * If there are used chunks after this one, then
+		 * it is a chunk that was skipped due to failing
+		 * the erased check. Just skip it so that it can
+		 * be deleted.
+		 * But, more typically, We get here when this is
+		 * an unallocated chunk and his means that
+		 * either the block is empty or this is the one
+		 * being allocated from
+		 */
+
+		if (*found_chunks) {
+			/* This is a chunk that was skipped due
+			 * to failing the erased check */
+		} else if (chunk_in_block == 0) {
+			/* We're looking at the first chunk in
+			 * the block so the block is unused */
+			bi->block_state = YAFFS_BLOCK_STATE_EMPTY;
+			dev->n_erased_blocks++;
+		} else {
+			if (bi->block_state == YAFFS_BLOCK_STATE_NEEDS_SCAN ||
+			    bi->block_state == YAFFS_BLOCK_STATE_ALLOCATING) {
+				if (dev->seq_number == bi->seq_number) {
+					/* Allocating from this block*/
+					yaffs_trace(YAFFS_TRACE_SCAN,
+					    " Allocating from %d %d",
+					    blk, chunk_in_block);
+
+					bi->block_state =
+						YAFFS_BLOCK_STATE_ALLOCATING;
+					dev->alloc_block = blk;
+					dev->alloc_page = chunk_in_block;
+					dev->alloc_block_finder = blk;
+				} else {
+					/* This is a partially written block
+					 * that is not the current
+					 * allocation block.
+					 */
+					yaffs_trace(YAFFS_TRACE_SCAN,
+						"Partially written block %d detected. gc will fix this.",
+						blk);
+				}
+			}
+		}
+
+		dev->n_free_chunks++;
+
+	} else if (tags.ecc_result ==
+		YAFFS_ECC_RESULT_UNFIXED) {
+		yaffs_trace(YAFFS_TRACE_SCAN,
+			" Unfixed ECC in chunk(%d:%d), chunk ignored",
+			blk, chunk_in_block);
+			dev->n_free_chunks++;
+	} else if (tags.obj_id > YAFFS_MAX_OBJECT_ID ||
+		   tags.chunk_id > YAFFS_MAX_CHUNK_ID ||
+		   tags.obj_id == YAFFS_OBJECTID_SUMMARY ||
+		   (tags.chunk_id > 0 &&
+		     tags.n_bytes > dev->data_bytes_per_chunk) ||
+		   tags.seq_number != bi->seq_number) {
+		yaffs_trace(YAFFS_TRACE_SCAN,
+			"Chunk (%d:%d) with bad tags:obj = %d, chunk_id = %d, n_bytes = %d, ignored",
+			blk, chunk_in_block, tags.obj_id,
+			tags.chunk_id, tags.n_bytes);
+		dev->n_free_chunks++;
+	} else if (tags.chunk_id > 0) {
+		/* chunk_id > 0 so it is a data chunk... */
+		loff_t endpos;
+		loff_t chunk_base = (tags.chunk_id - 1) *
+					dev->data_bytes_per_chunk;
+
+		*found_chunks = 1;
+
+		yaffs_set_chunk_bit(dev, blk, chunk_in_block);
+		bi->pages_in_use++;
+
+		in = yaffs_find_or_create_by_number(dev,
+					tags.obj_id,
+					YAFFS_OBJECT_TYPE_FILE);
+		if (!in)
+			/* Out of memory */
+			alloc_failed = 1;
+
+		if (in &&
+		    in->variant_type == YAFFS_OBJECT_TYPE_FILE &&
+		    chunk_base < in->variant.file_variant.shrink_size) {
+			/* This has not been invalidated by
+			 * a resize */
+			if (!yaffs_put_chunk_in_file(in, tags.chunk_id,
+								chunk, -1))
+				alloc_failed = 1;
+
+			/* File size is calculated by looking at
+			 * the data chunks if we have not
+			 * seen an object header yet.
+			 * Stop this practice once we find an
+			 * object header.
+			 */
+			endpos = chunk_base + tags.n_bytes;
+
+			if (!in->valid &&
+			    in->variant.file_variant.scanned_size < endpos) {
+				in->variant.file_variant.
+				    scanned_size = endpos;
+				in->variant.file_variant.
+				    file_size = endpos;
+			}
+		} else if (in) {
+			/* This chunk has been invalidated by a
+			 * resize, or a past file deletion
+			 * so delete the chunk*/
+			yaffs_chunk_del(dev, chunk, 1, __LINE__);
+		}
+	} else {
+		/* chunk_id == 0, so it is an ObjectHeader.
+		 * Thus, we read in the object header and make
+		 * the object
+		 */
+		*found_chunks = 1;
+
+		yaffs_set_chunk_bit(dev, blk, chunk_in_block);
+		bi->pages_in_use++;
+
+		oh = NULL;
+		in = NULL;
+
+		if (tags.extra_available) {
+			in = yaffs_find_or_create_by_number(dev,
+					tags.obj_id,
+					tags.extra_obj_type);
+			if (!in)
+				alloc_failed = 1;
+		}
+
+		if (!in ||
+		    (!in->valid && dev->param.disable_lazy_load) ||
+		    tags.extra_shadows ||
+		    (!in->valid && (tags.obj_id == YAFFS_OBJECTID_ROOT ||
+				 tags.obj_id == YAFFS_OBJECTID_LOSTNFOUND))) {
+
+			/* If we don't have  valid info then we
+			 * need to read the chunk
+			 * TODO In future we can probably defer
+			 * reading the chunk and living with
+			 * invalid data until needed.
+			 */
+
+			result = yaffs_rd_chunk_tags_nand(dev,
+						  chunk,
+						  chunk_data,
+						  NULL);
+
+			oh = (struct yaffs_obj_hdr *)chunk_data;
+
+			if (dev->param.inband_tags) {
+				/* Fix up the header if they got
+				 * corrupted by inband tags */
+				oh->shadows_obj =
+				    oh->inband_shadowed_obj_id;
+				oh->is_shrink =
+				    oh->inband_is_shrink;
+			}
+
+			if (!in) {
+				in = yaffs_find_or_create_by_number(dev,
+							tags.obj_id, oh->type);
+				if (!in)
+					alloc_failed = 1;
+			}
+		}
+
+		if (!in) {
+			/* TODO Hoosterman we have a problem! */
+			yaffs_trace(YAFFS_TRACE_ERROR,
+				"yaffs tragedy: Could not make object for object  %d at chunk %d during scan",
+				tags.obj_id, chunk);
+			return YAFFS_FAIL;
+		}
+
+		if (in->valid) {
+			/* We have already filled this one.
+			 * We have a duplicate that will be
+			 * discarded, but we first have to suck
+			 * out resize info if it is a file.
+			 */
+			if ((in->variant_type == YAFFS_OBJECT_TYPE_FILE) &&
+				((oh && oh->type == YAFFS_OBJECT_TYPE_FILE) ||
+				 (tags.extra_available &&
+				  tags.extra_obj_type == YAFFS_OBJECT_TYPE_FILE)
+				)) {
+				loff_t this_size = (oh) ?
+					yaffs_oh_to_size(oh) :
+					tags.extra_file_size;
+				u32 parent_obj_id = (oh) ?
+					oh->parent_obj_id :
+					tags.extra_parent_id;
+
+				is_shrink = (oh) ?
+					oh->is_shrink :
+					tags.extra_is_shrink;
+
+				/* If it is deleted (unlinked
+				 * at start also means deleted)
+				 * we treat the file size as
+				 * being zeroed at this point.
+				 */
+				if (parent_obj_id == YAFFS_OBJECTID_DELETED ||
+				    parent_obj_id == YAFFS_OBJECTID_UNLINKED) {
+					this_size = 0;
+					is_shrink = 1;
+				}
+
+				if (is_shrink &&
+				    in->variant.file_variant.shrink_size >
+				    this_size)
+					in->variant.file_variant.shrink_size =
+					this_size;
+
+				if (is_shrink)
+					bi->has_shrink_hdr = 1;
+			}
+			/* Use existing - destroy this one. */
+			yaffs_chunk_del(dev, chunk, 1, __LINE__);
+		}
+
+		if (!in->valid && in->variant_type !=
+		    (oh ? oh->type : tags.extra_obj_type))
+			yaffs_trace(YAFFS_TRACE_ERROR,
+				"yaffs tragedy: Bad object type, %d != %d, for object %d at chunk %d during scan",
+				oh ? oh->type : tags.extra_obj_type,
+				in->variant_type, tags.obj_id,
+				chunk);
+
+		if (!in->valid &&
+		    (tags.obj_id == YAFFS_OBJECTID_ROOT ||
+		     tags.obj_id == YAFFS_OBJECTID_LOSTNFOUND)) {
+			/* We only load some info, don't fiddle
+			 * with directory structure */
+			in->valid = 1;
+
+			if (oh) {
+				in->yst_mode = oh->yst_mode;
+				yaffs_load_attribs(in, oh);
+				in->lazy_loaded = 0;
+			} else {
+				in->lazy_loaded = 1;
+			}
+			in->hdr_chunk = chunk;
+
+		} else if (!in->valid) {
+			/* we need to load this info */
+			in->valid = 1;
+			in->hdr_chunk = chunk;
+			if (oh) {
+				in->variant_type = oh->type;
+				in->yst_mode = oh->yst_mode;
+				yaffs_load_attribs(in, oh);
+
+				if (oh->shadows_obj > 0)
+					yaffs_handle_shadowed_obj(dev,
+					     oh->shadows_obj, 1);
+
+				yaffs_set_obj_name_from_oh(in, oh);
+				parent = yaffs_find_or_create_by_number(dev,
+						oh->parent_obj_id,
+						YAFFS_OBJECT_TYPE_DIRECTORY);
+				file_size = yaffs_oh_to_size(oh);
+				is_shrink = oh->is_shrink;
+				equiv_id = oh->equiv_id;
+			} else {
+				in->variant_type = tags.extra_obj_type;
+				parent = yaffs_find_or_create_by_number(dev,
+						tags.extra_parent_id,
+						YAFFS_OBJECT_TYPE_DIRECTORY);
+				file_size = tags.extra_file_size;
+				is_shrink = tags.extra_is_shrink;
+				equiv_id = tags.extra_equiv_id;
+				in->lazy_loaded = 1;
+			}
+			in->dirty = 0;
+
+			if (!parent)
+				alloc_failed = 1;
+
+			/* directory stuff...
+			 * hook up to parent
+			 */
+
+			if (parent &&
+			    parent->variant_type == YAFFS_OBJECT_TYPE_UNKNOWN) {
+				/* Set up as a directory */
+				parent->variant_type =
+					YAFFS_OBJECT_TYPE_DIRECTORY;
+				INIT_LIST_HEAD(&parent->
+						variant.dir_variant.children);
+			} else if (!parent ||
+				   parent->variant_type !=
+					YAFFS_OBJECT_TYPE_DIRECTORY) {
+				/* Hoosterman, another problem....
+				 * Trying to use a non-directory as a directory
+				 */
+
+				yaffs_trace(YAFFS_TRACE_ERROR,
+					"yaffs tragedy: attempting to use non-directory as a directory in scan. Put in lost+found."
+					);
+				parent = dev->lost_n_found;
+			}
+			yaffs_add_obj_to_dir(parent, in);
+
+			is_unlinked = (parent == dev->del_dir) ||
+					(parent == dev->unlinked_dir);
+
+			if (is_shrink)
+				/* Mark the block */
+				bi->has_shrink_hdr = 1;
+
+			/* Note re hardlinks.
+			 * Since we might scan a hardlink before its equivalent
+			 * object is scanned we put them all in a list.
+			 * After scanning is complete, we should have all the
+			 * objects, so we run through this list and fix up all
+			 * the chains.
+			 */
+
+			switch (in->variant_type) {
+			case YAFFS_OBJECT_TYPE_UNKNOWN:
+				/* Todo got a problem */
+				break;
+			case YAFFS_OBJECT_TYPE_FILE:
+				file_var = &in->variant.file_variant;
+				if (file_var->scanned_size < file_size) {
+					/* This covers the case where the file
+					 * size is greater than the data held.
+					 * This will happen if the file is
+					 * resized to be larger than its
+					 * current data extents.
+					 */
+					file_var->file_size = file_size;
+					file_var->scanned_size = file_size;
+				}
+
+				if (file_var->shrink_size > file_size)
+					file_var->shrink_size = file_size;
+
+				break;
+			case YAFFS_OBJECT_TYPE_HARDLINK:
+				hl_var = &in->variant.hardlink_variant;
+				if (!is_unlinked) {
+					hl_var->equiv_id = equiv_id;
+					list_add(&in->hard_links, hard_list);
+				}
+				break;
+			case YAFFS_OBJECT_TYPE_DIRECTORY:
+				/* Do nothing */
+				break;
+			case YAFFS_OBJECT_TYPE_SPECIAL:
+				/* Do nothing */
+				break;
+			case YAFFS_OBJECT_TYPE_SYMLINK:
+				sl_var = &in->variant.symlink_variant;
+				if (oh) {
+					sl_var->alias =
+					    yaffs_clone_str(oh->alias);
+					if (!sl_var->alias)
+						alloc_failed = 1;
+				}
+				break;
+			}
+		}
+	}
+	return alloc_failed ? YAFFS_FAIL : YAFFS_OK;
+}
+
+int yaffs2_scan_backwards(struct yaffs_dev *dev)
+{
+	int blk;
+	int block_iter;
+	int start_iter;
+	int end_iter;
+	int n_to_scan = 0;
+	enum yaffs_block_state state;
+	int c;
+	int deleted;
+	LIST_HEAD(hard_list);
+	struct yaffs_block_info *bi;
+	u32 seq_number;
+	int n_blocks = dev->internal_end_block - dev->internal_start_block + 1;
+	u8 *chunk_data;
+	int found_chunks;
+	int alloc_failed = 0;
+	struct yaffs_block_index *block_index = NULL;
+	int alt_block_index = 0;
+	int summary_available;
+
+	yaffs_trace(YAFFS_TRACE_SCAN,
+		"yaffs2_scan_backwards starts  intstartblk %d intendblk %d...",
+		dev->internal_start_block, dev->internal_end_block);
+
+	dev->seq_number = YAFFS_LOWEST_SEQUENCE_NUMBER;
+
+	block_index =
+		kmalloc(n_blocks * sizeof(struct yaffs_block_index), GFP_NOFS);
+
+	if (!block_index) {
+		block_index =
+		    vmalloc(n_blocks * sizeof(struct yaffs_block_index));
+		alt_block_index = 1;
+	}
+
+	if (!block_index) {
+		yaffs_trace(YAFFS_TRACE_SCAN,
+			"yaffs2_scan_backwards() could not allocate block index!"
+			);
+		return YAFFS_FAIL;
+	}
+
+	dev->blocks_in_checkpt = 0;
+
+	chunk_data = yaffs_get_temp_buffer(dev);
+
+	/* Scan all the blocks to determine their state */
+	bi = dev->block_info;
+	for (blk = dev->internal_start_block; blk <= dev->internal_end_block;
+	     blk++) {
+		yaffs_clear_chunk_bits(dev, blk);
+		bi->pages_in_use = 0;
+		bi->soft_del_pages = 0;
+
+		yaffs_query_init_block_state(dev, blk, &state, &seq_number);
+
+		bi->block_state = state;
+		bi->seq_number = seq_number;
+
+		if (bi->seq_number == YAFFS_SEQUENCE_CHECKPOINT_DATA)
+			bi->block_state = YAFFS_BLOCK_STATE_CHECKPOINT;
+		if (bi->seq_number == YAFFS_SEQUENCE_BAD_BLOCK)
+			bi->block_state = YAFFS_BLOCK_STATE_DEAD;
+
+		yaffs_trace(YAFFS_TRACE_SCAN_DEBUG,
+			"Block scanning block %d state %d seq %d",
+			blk, bi->block_state, seq_number);
+
+		if (bi->block_state == YAFFS_BLOCK_STATE_CHECKPOINT) {
+			dev->blocks_in_checkpt++;
+
+		} else if (bi->block_state == YAFFS_BLOCK_STATE_DEAD) {
+			yaffs_trace(YAFFS_TRACE_BAD_BLOCKS,
+				"block %d is bad", blk);
+		} else if (bi->block_state == YAFFS_BLOCK_STATE_EMPTY) {
+			yaffs_trace(YAFFS_TRACE_SCAN_DEBUG, "Block empty ");
+			dev->n_erased_blocks++;
+			dev->n_free_chunks += dev->param.chunks_per_block;
+		} else if (bi->block_state ==
+				YAFFS_BLOCK_STATE_NEEDS_SCAN) {
+			/* Determine the highest sequence number */
+			if (seq_number >= YAFFS_LOWEST_SEQUENCE_NUMBER &&
+			    seq_number < YAFFS_HIGHEST_SEQUENCE_NUMBER) {
+				block_index[n_to_scan].seq = seq_number;
+				block_index[n_to_scan].block = blk;
+				n_to_scan++;
+				if (seq_number >= dev->seq_number)
+					dev->seq_number = seq_number;
+			} else {
+				/* TODO: Nasty sequence number! */
+				yaffs_trace(YAFFS_TRACE_SCAN,
+					"Block scanning block %d has bad sequence number %d",
+					blk, seq_number);
+			}
+		}
+		bi++;
+	}
+
+	yaffs_trace(YAFFS_TRACE_SCAN, "%d blocks to be sorted...", n_to_scan);
+
+	cond_resched();
+
+	/* Sort the blocks by sequence number */
+	sort(block_index, n_to_scan, sizeof(struct yaffs_block_index),
+		   yaffs2_ybicmp, NULL);
+
+	cond_resched();
+
+	yaffs_trace(YAFFS_TRACE_SCAN, "...done");
+
+	/* Now scan the blocks looking at the data. */
+	start_iter = 0;
+	end_iter = n_to_scan - 1;
+	yaffs_trace(YAFFS_TRACE_SCAN_DEBUG, "%d blocks to scan", n_to_scan);
+
+	/* For each block.... backwards */
+	for (block_iter = end_iter;
+	     !alloc_failed && block_iter >= start_iter;
+	     block_iter--) {
+		/* Cooperative multitasking! This loop can run for so
+		   long that watchdog timers expire. */
+		cond_resched();
+
+		/* get the block to scan in the correct order */
+		blk = block_index[block_iter].block;
+		bi = yaffs_get_block_info(dev, blk);
+		deleted = 0;
+
+		summary_available = yaffs_summary_read(dev, dev->sum_tags, blk);
+
+		/* For each chunk in each block that needs scanning.... */
+		found_chunks = 0;
+		if (summary_available)
+			c = dev->chunks_per_summary - 1;
+		else
+			c = dev->param.chunks_per_block - 1;
+
+		for (/* c is already initialised */;
+		     !alloc_failed && c >= 0 &&
+		     (bi->block_state == YAFFS_BLOCK_STATE_NEEDS_SCAN ||
+		      bi->block_state == YAFFS_BLOCK_STATE_ALLOCATING);
+		      c--) {
+			/* Scan backwards...
+			 * Read the tags and decide what to do
+			 */
+			if (yaffs2_scan_chunk(dev, bi, blk, c,
+					&found_chunks, chunk_data,
+					&hard_list, summary_available) ==
+					YAFFS_FAIL)
+				alloc_failed = 1;
+		}
+
+		if (bi->block_state == YAFFS_BLOCK_STATE_NEEDS_SCAN) {
+			/* If we got this far while scanning, then the block
+			 * is fully allocated. */
+			bi->block_state = YAFFS_BLOCK_STATE_FULL;
+		}
+
+		/* Now let's see if it was dirty */
+		if (bi->pages_in_use == 0 &&
+		    !bi->has_shrink_hdr &&
+		    bi->block_state == YAFFS_BLOCK_STATE_FULL) {
+			yaffs_block_became_dirty(dev, blk);
+		}
+	}
+
+	yaffs_skip_rest_of_block(dev);
+
+	if (alt_block_index)
+		vfree(block_index);
+	else
+		kfree(block_index);
+
+	/* Ok, we've done all the scanning.
+	 * Fix up the hard link chains.
+	 * We have scanned all the objects, now it's time to add these
+	 * hardlinks.
+	 */
+	yaffs_link_fixup(dev, &hard_list);
+
+	yaffs_release_temp_buffer(dev, chunk_data);
+
+	if (alloc_failed)
+		return YAFFS_FAIL;
+
+	yaffs_trace(YAFFS_TRACE_SCAN, "yaffs2_scan_backwards ends");
+
+	return YAFFS_OK;
+}
diff --git a/fs/yaffs2/yaffs_yaffs2.h b/fs/yaffs2/yaffs_yaffs2.h
new file mode 100644
index 000000000000..2363bfd8bcab
--- /dev/null
+++ b/fs/yaffs2/yaffs_yaffs2.h
@@ -0,0 +1,39 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YAFFS_YAFFS2_H__
+#define __YAFFS_YAFFS2_H__
+
+#include "yaffs_guts.h"
+
+void yaffs_calc_oldest_dirty_seq(struct yaffs_dev *dev);
+void yaffs2_find_oldest_dirty_seq(struct yaffs_dev *dev);
+void yaffs2_clear_oldest_dirty_seq(struct yaffs_dev *dev,
+				   struct yaffs_block_info *bi);
+void yaffs2_update_oldest_dirty_seq(struct yaffs_dev *dev, unsigned block_no,
+				    struct yaffs_block_info *bi);
+int yaffs_block_ok_for_gc(struct yaffs_dev *dev, struct yaffs_block_info *bi);
+u32 yaffs2_find_refresh_block(struct yaffs_dev *dev);
+int yaffs2_checkpt_required(struct yaffs_dev *dev);
+int yaffs_calc_checkpt_blocks_required(struct yaffs_dev *dev);
+
+void yaffs2_checkpt_invalidate(struct yaffs_dev *dev);
+int yaffs2_checkpt_save(struct yaffs_dev *dev);
+int yaffs2_checkpt_restore(struct yaffs_dev *dev);
+
+int yaffs2_handle_hole(struct yaffs_obj *obj, loff_t new_size);
+int yaffs2_scan_backwards(struct yaffs_dev *dev);
+
+#endif
diff --git a/fs/yaffs2/yportenv.h b/fs/yaffs2/yportenv.h
new file mode 100644
index 000000000000..0e4e64e45f47
--- /dev/null
+++ b/fs/yaffs2/yportenv.h
@@ -0,0 +1,85 @@
+/*
+ * YAFFS: Yet another Flash File System . A NAND-flash specific file system.
+ *
+ * Copyright (C) 2002-2011 Aleph One Ltd.
+ *   for Toby Churchill Ltd and Brightstar Engineering
+ *
+ * Created by Charles Manning <charles@aleph1.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 2.1 as
+ * published by the Free Software Foundation.
+ *
+ * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL.
+ */
+
+#ifndef __YPORTENV_H__
+#define __YPORTENV_H__
+
+/*
+ * Define the MTD version in terms of Linux Kernel versions
+ * This allows yaffs to be used independantly of the kernel
+ * as well as with it.
+ */
+
+#define MTD_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + (c))
+
+#ifdef YAFFS_OUT_OF_TREE
+#include "moduleconfig.h"
+#endif
+
+#include <linux/version.h>
+#define MTD_VERSION_CODE LINUX_VERSION_CODE
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 19))
+#include <linux/config.h>
+#endif
+#include <linux/version.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/xattr.h>
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/stat.h>
+#include <linux/sort.h>
+#include <linux/bitops.h>
+
+/*  These type wrappings are used to support Unicode names in WinCE. */
+#define YCHAR char
+#define YUCHAR unsigned char
+#define _Y(x)     x
+
+#define YAFFS_LOSTNFOUND_NAME		"lost+found"
+#define YAFFS_LOSTNFOUND_PREFIX		"obj"
+
+
+#define YAFFS_ROOT_MODE			0755
+#define YAFFS_LOSTNFOUND_MODE		0700
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0))
+#define Y_CURRENT_TIME ktime_get_real_seconds()
+#define Y_TIME_CONVERT(x) (x).tv_sec
+#else
+#define Y_CURRENT_TIME CURRENT_TIME
+#define Y_TIME_CONVERT(x) (x)
+#endif
+
+#define compile_time_assertion(assertion) \
+	({ int x = __builtin_choose_expr(assertion, 0, (void)0); (void) x; })
+
+
+#define yaffs_printf(msk, fmt, ...) \
+	printk(KERN_DEBUG "yaffs: " fmt "\n", ##__VA_ARGS__)
+
+#define yaffs_trace(msk, fmt, ...) do { \
+	if (yaffs_trace_mask & (msk)) \
+		printk(KERN_DEBUG "yaffs: " fmt "\n", ##__VA_ARGS__); \
+} while (0)
+
+
+#endif
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 5d2add1a6c96..864fcfa1df41 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -51,7 +51,7 @@
   #ifdef CONFIG_NEED_MULTIPLE_NODES
     #define cpumask_of_node(node)	((node) == 0 ? cpu_online_mask : cpu_none_mask)
   #else
-    #define cpumask_of_node(node)	((void)node, cpu_online_mask)
+    #define cpumask_of_node(node)	((void)(node), cpu_online_mask)
   #endif
 #endif
 #ifndef pcibus_to_node
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index c229ffbed6d4..48e618b20d34 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -251,7 +251,8 @@
 
 #define PAGE_ALIGNED_DATA(page_align)					\
 	. = ALIGN(page_align);						\
-	*(.data..page_aligned)
+	*(.data..page_aligned)						\
+	. = ALIGN(page_align);
 
 #define READ_MOSTLY_DATA(align)						\
 	. = ALIGN(align);						\
@@ -619,7 +620,9 @@
 	. = ALIGN(bss_align);						\
 	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {				\
 		BSS_FIRST_SECTIONS					\
+		. = ALIGN(PAGE_SIZE);					\
 		*(.bss..page_aligned)					\
+		. = ALIGN(PAGE_SIZE);					\
 		*(.dynbss)						\
 		*(BSS_MAIN)						\
 		*(COMMON)						\
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index ac0eae8372ab..2ea6a95ca825 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -34,8 +34,8 @@ struct alg_sock {
 
 	struct sock *parent;
 
-	unsigned int refcnt;
-	unsigned int nokey_refcnt;
+	atomic_t refcnt;
+	atomic_t nokey_refcnt;
 
 	const struct af_alg_type *type;
 	void *private;
diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index f2deb71958b2..a0675db325e0 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -71,7 +71,7 @@
  */
 #define FIELD_FIT(_mask, _val)						\
 	({								\
-		__BF_FIELD_CHECK(_mask, 0ULL, _val, "FIELD_FIT: ");	\
+		__BF_FIELD_CHECK(_mask, 0ULL, 0ULL, "FIELD_FIT: ");	\
 		!((((typeof(_mask))_val) << __bf_shf(_mask)) & ~(_mask)); \
 	})
 
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index c51574fab0b0..00dcb1bad76b 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -50,7 +50,7 @@ static inline int get_bitmask_order(unsigned int count)
 
 static __always_inline unsigned long hweight_long(unsigned long w)
 {
-	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
+	return sizeof(w) == 4 ? hweight32(w) : hweight64((__u64)w);
 }
 
 /**
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5999d8031675..1c3d774d3c83 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1016,6 +1016,19 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 }
 
 /*
+ * The basic unit of block I/O is a sector. It is used in a number of contexts
+ * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9
+ * bytes. Variables of type sector_t represent an offset or size that is a
+ * multiple of 512 bytes. Hence these two constants.
+ */
+#ifndef SECTOR_SHIFT
+#define SECTOR_SHIFT 9
+#endif
+#ifndef SECTOR_SIZE
+#define SECTOR_SIZE (1 << SECTOR_SHIFT)
+#endif
+
+/*
  * blk_rq_pos()			: the current sector
  * blk_rq_bytes()		: bytes left in the entire request
  * blk_rq_cur_bytes()		: bytes left in the current segment
@@ -1042,12 +1055,12 @@ extern unsigned int blk_rq_err_bytes(const struct request *rq);
 
 static inline unsigned int blk_rq_sectors(const struct request *rq)
 {
-	return blk_rq_bytes(rq) >> 9;
+	return blk_rq_bytes(rq) >> SECTOR_SHIFT;
 }
 
 static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 {
-	return blk_rq_cur_bytes(rq) >> 9;
+	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
 }
 
 /*
@@ -1067,7 +1080,8 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 						     int op)
 {
 	if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
-		return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+		return min(q->limits.max_discard_sectors,
+			   UINT_MAX >> SECTOR_SHIFT);
 
 	if (unlikely(op == REQ_OP_WRITE_SAME))
 		return q->limits.max_write_same_sectors;
@@ -1376,16 +1390,21 @@ extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 static inline int sb_issue_discard(struct super_block *sb, sector_t block,
 		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
 {
-	return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9),
-				    nr_blocks << (sb->s_blocksize_bits - 9),
+	return blkdev_issue_discard(sb->s_bdev,
+				    block << (sb->s_blocksize_bits -
+					      SECTOR_SHIFT),
+				    nr_blocks << (sb->s_blocksize_bits -
+						  SECTOR_SHIFT),
 				    gfp_mask, flags);
 }
 static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 		sector_t nr_blocks, gfp_t gfp_mask)
 {
 	return blkdev_issue_zeroout(sb->s_bdev,
-				    block << (sb->s_blocksize_bits - 9),
-				    nr_blocks << (sb->s_blocksize_bits - 9),
+				    block << (sb->s_blocksize_bits -
+					      SECTOR_SHIFT),
+				    nr_blocks << (sb->s_blocksize_bits -
+						  SECTOR_SHIFT),
 				    gfp_mask, 0);
 }
 
@@ -1492,7 +1511,8 @@ static inline int queue_alignment_offset(struct request_queue *q)
 static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
 {
 	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
-	unsigned int alignment = sector_div(sector, granularity >> 9) << 9;
+	unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT)
+		<< SECTOR_SHIFT;
 
 	return (granularity + lim->alignment_offset - alignment) % granularity;
 }
@@ -1526,8 +1546,8 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
 		return 0;
 
 	/* Why are these in bytes, not sectors? */
-	alignment = lim->discard_alignment >> 9;
-	granularity = lim->discard_granularity >> 9;
+	alignment = lim->discard_alignment >> SECTOR_SHIFT;
+	granularity = lim->discard_granularity >> SECTOR_SHIFT;
 	if (!granularity)
 		return 0;
 
@@ -1538,7 +1558,7 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
 	offset = (granularity + alignment - offset) % granularity;
 
 	/* Turn it back into bytes, gaah */
-	return offset << 9;
+	return offset << SECTOR_SHIFT;
 }
 
 static inline int bdev_discard_alignment(struct block_device *bdev)
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index ec8a4d7af6bd..f7dc68cd0a39 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -119,10 +119,17 @@ static inline bool bvec_iter_rewind(const struct bio_vec *bv,
 	return true;
 }
 
+static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter)
+{
+	iter->bi_bvec_done = 0;
+	iter->bi_idx++;
+}
+
 #define for_each_bvec(bvl, bio_vec, iter, start)			\
 	for (iter = (start);						\
 	     (iter).bi_size &&						\
 		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
-	     bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
+	     (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter),	\
+		     (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter)))
 
 #endif /* __LINUX_BVEC_ITER_H */
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 8d4b92185a09..9e1ff02d6c4e 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -681,7 +681,9 @@ struct sock_cgroup_data {
 	union {
 #ifdef __LITTLE_ENDIAN
 		struct {
-			u8	is_data;
+			u8	is_data : 1;
+			u8	no_refcnt : 1;
+			u8	unused : 6;
 			u8	padding;
 			u16	prioidx;
 			u32	classid;
@@ -691,7 +693,9 @@ struct sock_cgroup_data {
 			u32	classid;
 			u16	prioidx;
 			u8	padding;
-			u8	is_data;
+			u8	unused : 6;
+			u8	no_refcnt : 1;
+			u8	is_data : 1;
 		} __packed;
 #endif
 		u64		val;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 61ab21c34866..3be0c9e7e150 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -714,6 +714,7 @@ extern spinlock_t cgroup_sk_update_lock;
 
 void cgroup_sk_alloc_disable(void);
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
+void cgroup_sk_clone(struct sock_cgroup_data *skcd);
 void cgroup_sk_free(struct sock_cgroup_data *skcd);
 
 static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
@@ -727,7 +728,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 	 */
 	v = READ_ONCE(skcd->val);
 
-	if (v & 1)
+	if (v & 3)
 		return &cgrp_dfl_root.cgrp;
 
 	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
@@ -739,6 +740,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 #else	/* CONFIG_CGROUP_DATA */
 
 static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
+static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {}
 static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
 
 #endif	/* CONFIG_CGROUP_DATA */
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index b93efc8feecd..755033acd2b0 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -77,6 +77,8 @@ static const struct file_operations __fops = {				\
 	.llseek  = no_llseek,						\
 }
 
+typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *);
+
 #if defined(CONFIG_DEBUG_FS)
 
 struct dentry *debugfs_lookup(const char *name, struct dentry *parent);
@@ -98,7 +100,6 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent);
 struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 				      const char *dest);
 
-typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *);
 struct dentry *debugfs_create_automount(const char *name,
 					struct dentry *parent,
 					debugfs_automount_t f,
@@ -227,7 +228,7 @@ static inline struct dentry *debugfs_create_symlink(const char *name,
 
 static inline struct dentry *debugfs_create_automount(const char *name,
 					struct dentry *parent,
-					struct vfsmount *(*f)(void *),
+					debugfs_automount_t f,
 					void *data)
 {
 	return ERR_PTR(-ENODEV);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 91a063a1f3b3..5d067136fc27 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -577,8 +577,6 @@ do {									\
 #define DMEMIT(x...) sz += ((sz >= maxlen) ? \
 			  0 : scnprintf(result + sz, maxlen - sz, x))
 
-#define SECTOR_SHIFT 9
-
 /*
  * Definitions of return values from target end_io function.
  */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 2dab158b74c4..598ee6ba5b18 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -948,7 +948,11 @@ extern void *efi_get_pal_addr (void);
 extern void efi_map_pal_code (void);
 extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg);
 extern void efi_gettimeofday (struct timespec64 *ts);
+#ifdef CONFIG_EFI
 extern void efi_enter_virtual_mode (void);	/* switch EFI to virtual mode, if possible */
+#else
+static inline void efi_enter_virtual_mode (void) {}
+#endif
 #ifdef CONFIG_X86
 extern void efi_late_init(void);
 extern void efi_free_boot_services(void);
diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h
index f236f5b931b2..7fdd7f355b52 100644
--- a/include/linux/elfnote.h
+++ b/include/linux/elfnote.h
@@ -54,7 +54,7 @@
 .popsection				;
 
 #define ELFNOTE(name, type, desc)		\
-	ELFNOTE_START(name, type, "")		\
+	ELFNOTE_START(name, type, "a")		\
 		desc			;	\
 	ELFNOTE_END
 
diff --git a/include/linux/file.h b/include/linux/file.h
index 279720db984a..76e38eade225 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -20,6 +20,7 @@ struct dentry;
 struct path;
 extern struct file *alloc_file(const struct path *, fmode_t mode,
 	const struct file_operations *fop);
+extern struct file *get_empty_filp(void);
 
 static inline void fput_light(struct file *file, int fput_needed)
 {
diff --git a/include/linux/font.h b/include/linux/font.h
index d6821769dd1e..f85e70bd4793 100644
--- a/include/linux/font.h
+++ b/include/linux/font.h
@@ -57,4 +57,17 @@ extern const struct font_desc *get_default_font(int xres, int yres,
 /* Max. length for the name of a predefined font */
 #define MAX_FONT_NAME	32
 
+/* Extra word getters */
+#define REFCOUNT(fd)	(((int *)(fd))[-1])
+#define FNTSIZE(fd)	(((int *)(fd))[-2])
+#define FNTCHARCNT(fd)	(((int *)(fd))[-3])
+#define FNTSUM(fd)	(((int *)(fd))[-4])
+
+#define FONT_EXTRA_WORDS 4
+
+struct font_data {
+	unsigned int extra[FONT_EXTRA_WORDS];
+	const unsigned char data[];
+} __packed;
+
 #endif /* _VIDEO_FONT_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 92b9cf88a95e..eac4366da0d2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1271,6 +1271,7 @@ extern void fasync_free(struct fasync_struct *);
 /* can be called from interrupts */
 extern void kill_fasync(struct fasync_struct **, int, int);
 
+extern int setfl(int fd, struct file * filp, unsigned long arg);
 extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
 extern int f_setown(struct file *filp, unsigned long arg, int force);
 extern void f_delown(struct file *filp);
@@ -1718,6 +1719,7 @@ struct file_operations {
 	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
 	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
 	int (*check_flags)(int);
+	int (*setfl)(struct file *, unsigned long);
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
@@ -1788,6 +1790,12 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      struct iovec *fast_pointer,
 			      struct iovec **ret_pointer);
 
+typedef ssize_t (*vfs_readf_t)(struct file *, char __user *, size_t, loff_t *);
+typedef ssize_t (*vfs_writef_t)(struct file *, const char __user *, size_t,
+				loff_t *);
+vfs_readf_t vfs_readf(struct file *file);
+vfs_writef_t vfs_writef(struct file *file);
+
 extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
@@ -1989,6 +1997,10 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
  * I_OVL_INUSE		Used by overlayfs to get exclusive ownership on upper
  *			and work dirs among overlayfs mounts.
  *
+ * I_SYNC_QUEUED	Inode is queued in b_io or b_more_io writeback lists.
+ *			Used to detect that mark_inode_dirty() should not move
+ * 			inode between dirty lists.
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC		(1 << 0)
@@ -2006,10 +2018,10 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 #define I_DIO_WAKEUP		(1 << __I_DIO_WAKEUP)
 #define I_LINKABLE		(1 << 10)
 #define I_DIRTY_TIME		(1 << 11)
-#define __I_DIRTY_TIME_EXPIRED	12
-#define I_DIRTY_TIME_EXPIRED	(1 << __I_DIRTY_TIME_EXPIRED)
+#define I_DIRTY_TIME_EXPIRED	(1 << 12)
 #define I_WB_SWITCH		(1 << 13)
 #define I_OVL_INUSE			(1 << 14)
+#define I_SYNC_QUEUED		(1 << 17)
 
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
 #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
@@ -2192,6 +2204,7 @@ extern int current_umask(void);
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
 extern int generic_update_time(struct inode *, struct timespec *, int);
+extern int update_time(struct inode *, struct timespec *, int);
 
 /* /sys/fs */
 extern struct kobject *fs_kobj;
@@ -2472,6 +2485,7 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb)
 	return false;
 }
 #endif
+extern int __sync_filesystem(struct super_block *, int);
 extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 550fa358893a..37f30d62f3a2 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -693,9 +693,11 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part)
 static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP)
+	preempt_disable();
 	write_seqcount_begin(&part->nr_sects_seq);
 	part->nr_sects = size;
 	write_seqcount_end(&part->nr_sects_seq);
+	preempt_enable();
 #elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT)
 	preempt_disable();
 	part->nr_sects = size;
diff --git a/include/linux/hid.h b/include/linux/hid.h
index ba1f67559831..40409453ef3e 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -919,34 +919,49 @@ static inline void hid_device_io_stop(struct hid_device *hid) {
  * @max: maximal valid usage->code to consider later (out parameter)
  * @type: input event type (EV_KEY, EV_REL, ...)
  * @c: code which corresponds to this usage and type
+ *
+ * The value pointed to by @bit will be set to NULL if either @type is
+ * an unhandled event type, or if @c is out of range for @type. This
+ * can be used as an error condition.
  */
 static inline void hid_map_usage(struct hid_input *hidinput,
 		struct hid_usage *usage, unsigned long **bit, int *max,
-		__u8 type, __u16 c)
+		__u8 type, unsigned int c)
 {
 	struct input_dev *input = hidinput->input;
-
-	usage->type = type;
-	usage->code = c;
+	unsigned long *bmap = NULL;
+	unsigned int limit = 0;
 
 	switch (type) {
 	case EV_ABS:
-		*bit = input->absbit;
-		*max = ABS_MAX;
+		bmap = input->absbit;
+		limit = ABS_MAX;
 		break;
 	case EV_REL:
-		*bit = input->relbit;
-		*max = REL_MAX;
+		bmap = input->relbit;
+		limit = REL_MAX;
 		break;
 	case EV_KEY:
-		*bit = input->keybit;
-		*max = KEY_MAX;
+		bmap = input->keybit;
+		limit = KEY_MAX;
 		break;
 	case EV_LED:
-		*bit = input->ledbit;
-		*max = LED_MAX;
+		bmap = input->ledbit;
+		limit = LED_MAX;
 		break;
 	}
+
+	if (unlikely(c > limit || !bmap)) {
+		pr_warn_ratelimited("%s: Invalid code %d type %d\n",
+				    input->name, c, type);
+		*bit = NULL;
+		return;
+	}
+
+	usage->type = type;
+	usage->code = c;
+	*max = limit;
+	*bit = bmap;
 }
 
 /**
@@ -960,7 +975,8 @@ static inline void hid_map_usage_clear(struct hid_input *hidinput,
 		__u8 type, __u16 c)
 {
 	hid_map_usage(hidinput, usage, bit, max, type, c);
-	clear_bit(c, *bit);
+	if (*bit)
+		clear_bit(usage->code, *bit);
 }
 
 /**
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 8d3ca6da3342..63cd81e5610d 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -422,6 +422,8 @@ enum vmbus_channel_message_type {
 	CHANNELMSG_19				= 19,
 	CHANNELMSG_20				= 20,
 	CHANNELMSG_TL_CONNECT_REQUEST		= 21,
+	CHANNELMSG_22				= 22,
+	CHANNELMSG_TL_CONNECT_RESULT		= 23,
 	CHANNELMSG_COUNT
 };
 
diff --git a/include/linux/i2c-algo-pca.h b/include/linux/i2c-algo-pca.h
index d03071732db4..7c522fdd9ea7 100644
--- a/include/linux/i2c-algo-pca.h
+++ b/include/linux/i2c-algo-pca.h
@@ -53,6 +53,20 @@
 #define I2C_PCA_CON_SI		0x08 /* Serial Interrupt */
 #define I2C_PCA_CON_CR		0x07 /* Clock Rate (MASK) */
 
+/**
+ * struct pca_i2c_bus_settings - The configured PCA i2c bus settings
+ * @mode: Configured i2c bus mode
+ * @tlow: Configured SCL LOW period
+ * @thi: Configured SCL HIGH period
+ * @clock_freq: The configured clock frequency
+ */
+struct pca_i2c_bus_settings {
+	int mode;
+	int tlow;
+	int thi;
+	int clock_freq;
+};
+
 struct i2c_algo_pca_data {
 	void 				*data;	/* private low level data */
 	void (*write_byte)		(void *data, int reg, int val);
@@ -64,6 +78,7 @@ struct i2c_algo_pca_data {
 	 * For PCA9665, use the frequency you want here. */
 	unsigned int			i2c_clock;
 	unsigned int			chip;
+	struct pca_i2c_bus_settings		bus_settings;
 };
 
 int i2c_pca_add_bus(struct i2c_adapter *);
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 70db3af04541..9885080c21c5 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -165,7 +165,6 @@ struct ide_io_ports {
  */
 #define PARTN_BITS	6	/* number of minor dev bits for partitions */
 #define MAX_DRIVES	2	/* per interface; 2 assumed by lots of code */
-#define SECTOR_SIZE	512
 
 /*
  * Timeouts for various operations:
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 4def15c32a01..d2364ba99f6c 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -304,8 +304,8 @@ enum {
 
 #define QI_DEV_EIOTLB_ADDR(a)	((u64)(a) & VTD_PAGE_MASK)
 #define QI_DEV_EIOTLB_SIZE	(((u64)1) << 11)
-#define QI_DEV_EIOTLB_GLOB(g)	((u64)g)
-#define QI_DEV_EIOTLB_PASID(p)	(((u64)p) << 32)
+#define QI_DEV_EIOTLB_GLOB(g)	((u64)(g) & 0x1)
+#define QI_DEV_EIOTLB_PASID(p)	((u64)((p) & 0xfffff) << 32)
 #define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 16)
 #define QI_DEV_EIOTLB_QDEP(qd)	((u64)((qd) & 0x1f) << 4)
 #define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 58df02bd93c9..fa46183b163b 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -120,9 +120,12 @@ io_mapping_init_wc(struct io_mapping *iomap,
 		   resource_size_t base,
 		   unsigned long size)
 {
+	iomap->iomem = ioremap_wc(base, size);
+	if (!iomap->iomem)
+		return NULL;
+
 	iomap->base = base;
 	iomap->size = size;
-	iomap->iomem = ioremap_wc(base, size);
 #if defined(pgprot_noncached_wc) /* archs can't agree on a name ... */
 	iomap->prot = pgprot_noncached_wc(PAGE_KERNEL);
 #elif defined(pgprot_writecombine)
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 0d53626405bf..c08758a63d26 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -212,6 +212,8 @@ struct irq_data {
  *				  mask. Applies only to affinity managed irqs.
  * IRQD_SINGLE_TARGET		- IRQ allows only a single affinity target
  * IRQD_DEFAULT_TRIGGER_SET	- Expected trigger already been set
+ * IRQD_AFFINITY_ON_ACTIVATE	- Affinity is set on activation. Don't call
+ *				  irq_chip::irq_set_affinity() when deactivated.
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
@@ -233,6 +235,7 @@ enum {
 	IRQD_MANAGED_SHUTDOWN		= (1 << 23),
 	IRQD_SINGLE_TARGET		= (1 << 24),
 	IRQD_DEFAULT_TRIGGER_SET	= (1 << 25),
+	IRQD_AFFINITY_ON_ACTIVATE	= (1 << 29),
 };
 
 #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
@@ -377,6 +380,15 @@ static inline bool irqd_is_managed_and_shutdown(struct irq_data *d)
 	return __irqd_to_state(d) & IRQD_MANAGED_SHUTDOWN;
 }
 
+static inline void irqd_set_affinity_on_activate(struct irq_data *d)
+{
+	__irqd_to_state(d) |= IRQD_AFFINITY_ON_ACTIVATE;
+}
+
+static inline bool irqd_affinity_on_activate(struct irq_data *d)
+{
+	return __irqd_to_state(d) & IRQD_AFFINITY_ON_ACTIVATE;
+}
 #undef __irqd_to_state
 
 static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index e465bb15912d..6be5545d3584 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -317,7 +317,7 @@ extern void gdbstub_exit(int status);
 extern int			kgdb_single_step;
 extern atomic_t			kgdb_active;
 #define in_dbg_master() \
-	(raw_smp_processor_id() == atomic_read(&kgdb_active))
+	(irqs_disabled() && (smp_processor_id() == atomic_read(&kgdb_active)))
 extern bool dbg_is_early;
 extern void __init dbg_late_init(void);
 #else /* ! CONFIG_KGDB */
diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index 082d1d2a5216..dc9a2eecc8b8 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -15,6 +15,7 @@ extern int __khugepaged_enter(struct mm_struct *mm);
 extern void __khugepaged_exit(struct mm_struct *mm);
 extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 				      unsigned long vm_flags);
+extern void khugepaged_min_free_kbytes_update(void);
 
 #define khugepaged_enabled()					       \
 	(transparent_hugepage_flags &				       \
@@ -73,6 +74,10 @@ static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 {
 	return 0;
 }
+
+static inline void khugepaged_min_free_kbytes_update(void)
+{
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_KHUGEPAGED_H */
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 520702b82134..be7a49f437ea 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -385,6 +385,10 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
 	return this_cpu_ptr(&kprobe_ctlblk);
 }
 
+extern struct kprobe kprobe_busy;
+void kprobe_busy_begin(void);
+void kprobe_busy_end(void);
+
 kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset);
 int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 93838d98e3f3..c5c34fd78c5a 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -38,6 +38,7 @@
 #include <linux/acpi.h>
 #include <linux/cdrom.h>
 #include <linux/sched.h>
+#include <linux/async.h>
 
 /*
  * Define if arch has non-standard setup.  This is a _PCI_ standard
@@ -439,6 +440,7 @@ enum {
 	ATA_HORKAGE_NO_DMA_LOG	= (1 << 23),	/* don't use DMA for log read */
 	ATA_HORKAGE_NOTRIM	= (1 << 24),	/* don't use TRIM */
 	ATA_HORKAGE_MAX_SEC_1024 = (1 << 25),	/* Limit max sects to 1024 */
+	ATA_HORKAGE_MAX_TRIM_128M = (1 << 26),	/* Limit max trim size to 128M */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */
@@ -502,6 +504,7 @@ enum hsm_task_states {
 };
 
 enum ata_completion_errors {
+	AC_ERR_OK		= 0,	    /* no error */
 	AC_ERR_DEV		= (1 << 0), /* device reported error */
 	AC_ERR_HSM		= (1 << 1), /* host state machine violation */
 	AC_ERR_TIMEOUT		= (1 << 2), /* timeout */
@@ -884,6 +887,8 @@ struct ata_port {
 	struct timer_list	fastdrain_timer;
 	unsigned long		fastdrain_cnt;
 
+	async_cookie_t		cookie;
+
 	int			em_message_type;
 	void			*private_data;
 
@@ -905,9 +910,9 @@ struct ata_port_operations {
 	/*
 	 * Command execution
 	 */
-	int  (*qc_defer)(struct ata_queued_cmd *qc);
-	int  (*check_atapi_dma)(struct ata_queued_cmd *qc);
-	void (*qc_prep)(struct ata_queued_cmd *qc);
+	int (*qc_defer)(struct ata_queued_cmd *qc);
+	int (*check_atapi_dma)(struct ata_queued_cmd *qc);
+	enum ata_completion_errors (*qc_prep)(struct ata_queued_cmd *qc);
 	unsigned int (*qc_issue)(struct ata_queued_cmd *qc);
 	bool (*qc_fill_rtf)(struct ata_queued_cmd *qc);
 
@@ -1171,7 +1176,7 @@ extern int ata_xfer_mode2shift(unsigned long xfer_mode);
 extern const char *ata_mode_string(unsigned long xfer_mask);
 extern unsigned long ata_id_xfermask(const u16 *id);
 extern int ata_std_qc_defer(struct ata_queued_cmd *qc);
-extern void ata_noop_qc_prep(struct ata_queued_cmd *qc);
+extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc);
 extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg,
 		 unsigned int n_elem);
 extern unsigned int ata_dev_classify(const struct ata_taskfile *tf);
@@ -1885,9 +1890,9 @@ extern const struct ata_port_operations ata_bmdma_port_ops;
 	.sg_tablesize		= LIBATA_MAX_PRD,		\
 	.dma_boundary		= ATA_DMA_BOUNDARY
 
-extern void ata_bmdma_qc_prep(struct ata_queued_cmd *qc);
+extern enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc);
 extern unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc);
-extern void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc);
+extern enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc);
 extern unsigned int ata_bmdma_port_intr(struct ata_port *ap,
 				      struct ata_queued_cmd *qc);
 extern irqreturn_t ata_bmdma_interrupt(int irq, void *dev_instance);
diff --git a/include/linux/log2.h b/include/linux/log2.h
index c373295f359f..cca606609e1b 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -159,7 +159,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define roundup_pow_of_two(n)			\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n == 1) ? 1 :			\
+		((n) == 1) ? 1 :		\
 		(1UL << (ilog2((n) - 1) + 1))	\
 				   ) :		\
 	__roundup_pow_of_two(n)			\
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 32d445315128..983cd796cbb3 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -841,6 +841,7 @@ struct mlx5_cmd_work_ent {
 	struct delayed_work	cb_timeout_work;
 	void		       *context;
 	int			idx;
+	struct completion	handling;
 	struct completion	done;
 	struct mlx5_cmd        *cmd;
 	struct work_struct	work;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 858ce84ac7c5..79e47c30d57e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -548,7 +548,13 @@ static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags)
 }
 
 extern void kvfree(const void *addr);
+extern void kvfree_sensitive(const void *addr, size_t len);
 
+/*
+ * Mapcount of compound page as a whole, does not include mapped sub-pages.
+ *
+ * Must be called only for compound pages or any their tail sub-pages.
+ */
 static inline int compound_mapcount(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
@@ -568,10 +574,16 @@ static inline void page_mapcount_reset(struct page *page)
 
 int __page_mapcount(struct page *page);
 
+/*
+ * Mapcount of 0-order page; when compound sub-page, includes
+ * compound_mapcount().
+ *
+ * Result is undefined for pages which cannot be mapped into userspace.
+ * For example SLAB or special types of pages. See function page_has_type().
+ * They use this place in struct page differently.
+ */
 static inline int page_mapcount(struct page *page)
 {
-	VM_BUG_ON_PAGE(PageSlab(page), page);
-
 	if (unlikely(PageCompound(page)))
 		return __page_mapcount(page);
 	return atomic_read(&page->_mapcount) + 1;
@@ -1358,6 +1370,28 @@ static inline int fixup_user_fault(struct task_struct *tsk,
 }
 #endif
 
+extern void vma_do_file_update_time(struct vm_area_struct *, const char[], int);
+extern struct file *vma_do_pr_or_file(struct vm_area_struct *, const char[],
+				      int);
+extern void vma_do_get_file(struct vm_area_struct *, const char[], int);
+extern void vma_do_fput(struct vm_area_struct *, const char[], int);
+
+#define vma_file_update_time(vma)	vma_do_file_update_time(vma, __func__, \
+								__LINE__)
+#define vma_pr_or_file(vma)		vma_do_pr_or_file(vma, __func__, \
+							  __LINE__)
+#define vma_get_file(vma)		vma_do_get_file(vma, __func__, __LINE__)
+#define vma_fput(vma)			vma_do_fput(vma, __func__, __LINE__)
+
+#ifndef CONFIG_MMU
+extern struct file *vmr_do_pr_or_file(struct vm_region *, const char[], int);
+extern void vmr_do_fput(struct vm_region *, const char[], int);
+
+#define vmr_pr_or_file(region)		vmr_do_pr_or_file(region, __func__, \
+							  __LINE__)
+#define vmr_fput(region)		vmr_do_fput(region, __func__, __LINE__)
+#endif /* !CONFIG_MMU */
+
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len,
 		unsigned int gup_flags);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index be5d445bac98..dca97e71716a 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -258,6 +258,7 @@ struct vm_region {
 	unsigned long	vm_top;		/* region allocated to here */
 	unsigned long	vm_pgoff;	/* the offset in vm_file corresponding to vm_start */
 	struct file	*vm_file;	/* the backing file or NULL */
+	struct file	*vm_prfile;	/* the virtual backing file or NULL */
 
 	int		vm_usage;	/* region usage count (access under nommu_region_sem) */
 	bool		vm_icache_flushed : 1; /* true if the icache has been flushed for
@@ -332,6 +333,7 @@ struct vm_area_struct {
 	unsigned long vm_pgoff;		/* Offset (within vm_file) in PAGE_SIZE
 					   units */
 	struct file * vm_file;		/* File we map to (can be NULL). */
+	struct file *vm_prfile;		/* shadow of vm_file */
 	void * vm_private_data;		/* was vm_pte (shared mem) */
 
 	atomic_long_t swap_readahead_info;
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 279b39008a33..de81ed857ea3 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -226,7 +226,7 @@ struct mmc_queue_req;
  * MMC Physical partitions
  */
 struct mmc_part {
-	unsigned int	size;	/* partition size (in bytes) */
+	u64		size;	/* partition size (in bytes) */
 	unsigned int	part_cfg;	/* partition type */
 	char	name[MAX_MMC_PART_NAME_LEN];
 	bool	force_ro;	/* to make boot parts RO by default */
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 6db347b58644..6f8eb1238235 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -293,7 +293,7 @@ struct pcmcia_device_id {
 #define INPUT_DEVICE_ID_LED_MAX		0x0f
 #define INPUT_DEVICE_ID_SND_MAX		0x07
 #define INPUT_DEVICE_ID_FF_MAX		0x7f
-#define INPUT_DEVICE_ID_SW_MAX		0x0f
+#define INPUT_DEVICE_ID_SW_MAX		0x10
 #define INPUT_DEVICE_ID_PROP_MAX	0x1f
 
 #define INPUT_DEVICE_ID_MATCH_BUS	1
@@ -589,6 +589,10 @@ struct mips_cdmm_device_id {
 /*
  * MODULE_DEVICE_TABLE expects this struct to be called x86cpu_device_id.
  * Although gcc seems to ignore this error, clang fails without this define.
+ *
+ * Note: The ordering of the struct is different from upstream because the
+ * static initializers in kernels < 5.7 still use C89 style while upstream
+ * has been converted to proper C99 initializers.
  */
 #define x86cpu_device_id x86_cpu_id
 struct x86_cpu_id {
@@ -597,6 +601,7 @@ struct x86_cpu_id {
 	__u16 model;
 	__u16 feature;	/* bit index */
 	kernel_ulong_t driver_data;
+	__u16 steppings;
 };
 
 #define X86_FEATURE_MATCH(x) \
@@ -605,6 +610,7 @@ struct x86_cpu_id {
 #define X86_VENDOR_ANY 0xffff
 #define X86_FAMILY_ANY 0
 #define X86_MODEL_ANY  0
+#define X86_STEPPING_ANY 0
 #define X86_FEATURE_ANY 0	/* Same as FPU, you can't test for that */
 
 /*
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 2b05f4273bab..e9a791f46eb6 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -22,6 +22,7 @@
 #include <linux/mtd/flashchip.h>
 #include <linux/mtd/bbm.h>
 
+struct nand_chip;
 struct mtd_info;
 struct nand_flash_dev;
 struct device_node;
@@ -37,7 +38,7 @@ int nand_scan_ident(struct mtd_info *mtd, int max_chips,
 int nand_scan_tail(struct mtd_info *mtd);
 
 /* Unregister the MTD device and free resources held by the NAND device */
-void nand_release(struct mtd_info *mtd);
+void nand_release(struct nand_chip *chip);
 
 /* Internal helper for board drivers which need to override command function */
 void nand_wait_ready(struct mtd_info *mtd);
@@ -227,9 +228,6 @@ enum nand_ecc_algo {
 #define NAND_CI_CELLTYPE_MSK	0x0C
 #define NAND_CI_CELLTYPE_SHIFT	2
 
-/* Keep gcc happy */
-struct nand_chip;
-
 /* ONFI features */
 #define ONFI_FEATURE_16_BIT_BUS		(1 << 0)
 #define ONFI_FEATURE_EXT_PARAM_PAGE	(1 << 7)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 31fc54757bf2..3512c337a4a6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2449,7 +2449,7 @@ void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
 DECLARE_PER_CPU(int, xmit_recursion);
-#define XMIT_RECURSION_LIMIT	10
+#define XMIT_RECURSION_LIMIT	8
 
 static inline int dev_recursion_level(void)
 {
diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h
index 833a5b2255ea..ade993809ebc 100644
--- a/include/linux/netfilter/nf_conntrack_pptp.h
+++ b/include/linux/netfilter/nf_conntrack_pptp.h
@@ -5,7 +5,7 @@
 
 #include <linux/netfilter/nf_conntrack_common.h>
 
-extern const char *const pptp_msg_name[];
+const char *pptp_msg_name(u_int16_t msg);
 
 /* state of the control session */
 enum pptp_ctrlsess_state {
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 286b71c418b4..a67741083a00 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -58,6 +58,7 @@ struct nfs_client {
 
 	u32			cl_minorversion;/* NFSv4 minorversion */
 	struct rpc_cred		*cl_machine_cred;
+	int			nfs_prog;
 
 #if IS_ENABLED(CONFIG_NFS_V4)
 	struct list_head	cl_ds_clients; /* auth flavor data servers */
@@ -80,6 +81,7 @@ struct nfs_client {
 	const char *		cl_owner_id;
 
 	u32			cl_cb_ident;	/* v4.0 callback identifier */
+
 	const struct nfs4_minor_version_ops *cl_mvops;
 	unsigned long		cl_mig_gen;
 
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index ad69430fd0eb..5162fc1533c2 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -142,6 +142,8 @@ extern	void nfs_unlock_and_release_request(struct nfs_page *);
 extern int nfs_page_group_lock(struct nfs_page *);
 extern void nfs_page_group_unlock(struct nfs_page *);
 extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int);
+extern	int nfs_page_set_headlock(struct nfs_page *req);
+extern void nfs_page_clear_headlock(struct nfs_page *req);
 extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *);
 
 /*
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 373fb26b5fed..1c508b0ed3c2 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -12,7 +12,7 @@
  * reasonable for NFS over UDP.
  */
 #define NFS_MAX_FILE_IO_SIZE	(1048576U)
-#define NFS_DEF_FILE_IO_SIZE	(4096U)
+#define NFS_DEF_FILE_IO_SIZE	CONFIG_NFS_DEF_FILE_IO_SIZE
 #define NFS_MIN_FILE_IO_SIZE	(1024U)
 
 struct nfs4_string {
diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index d309788f4cd2..40b48e2133cb 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -233,4 +233,77 @@
 		(*_d >> _to_shift) != _a);				\
 })
 
+/**
+ * array_size() - Calculate size of 2-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ *
+ * Calculates size of 2-dimensional array: @a * @b.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array_size(size_t a, size_t b)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(a, b, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+/**
+ * array3_size() - Calculate size of 3-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ * @c: dimension three
+ *
+ * Calculates size of 3-dimensional array: @a * @b * @c.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array3_size(size_t a, size_t b, size_t c)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(a, b, &bytes))
+		return SIZE_MAX;
+	if (check_mul_overflow(bytes, c, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(n, size, &bytes))
+		return SIZE_MAX;
+	if (check_add_overflow(bytes, c, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+/**
+ * struct_size() - Calculate size of structure with trailing array.
+ * @p: Pointer to the structure.
+ * @member: Name of the array member.
+ * @n: Number of elements in the array.
+ *
+ * Calculates size of memory needed for structure @p followed by an
+ * array of @n @member elements.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define struct_size(p, member, n)					\
+	__ab_c_size(n,							\
+		    sizeof(*(p)->member) + __must_be_array((p)->member),\
+		    sizeof(*(p)))
+
 #endif /* __LINUX_OVERFLOW_H */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 7fa3f1498b34..2d036930a3cd 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -45,6 +45,7 @@
 #define PCI_CLASS_MULTIMEDIA_VIDEO	0x0400
 #define PCI_CLASS_MULTIMEDIA_AUDIO	0x0401
 #define PCI_CLASS_MULTIMEDIA_PHONE	0x0402
+#define PCI_CLASS_MULTIMEDIA_HD_AUDIO	0x0403
 #define PCI_CLASS_MULTIMEDIA_OTHER	0x0480
 
 #define PCI_BASE_CLASS_MEMORY		0x05
@@ -1331,6 +1332,7 @@
 #define PCI_DEVICE_ID_IMS_TT3D		0x9135
 
 #define PCI_VENDOR_ID_AMCC		0x10e8
+#define PCI_VENDOR_ID_AMPERE		0x1def
 
 #define PCI_VENDOR_ID_INTERG		0x10ea
 #define PCI_DEVICE_ID_INTERG_1682	0x1682
diff --git a/include/linux/prandom.h b/include/linux/prandom.h
new file mode 100644
index 000000000000..aa16e6468f91
--- /dev/null
+++ b/include/linux/prandom.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * include/linux/prandom.h
+ *
+ * Include file for the fast pseudo-random 32-bit
+ * generation.
+ */
+#ifndef _LINUX_PRANDOM_H
+#define _LINUX_PRANDOM_H
+
+#include <linux/types.h>
+#include <linux/percpu.h>
+
+u32 prandom_u32(void);
+void prandom_bytes(void *buf, size_t nbytes);
+void prandom_seed(u32 seed);
+void prandom_reseed_late(void);
+
+struct rnd_state {
+	__u32 s1, s2, s3, s4;
+};
+
+DECLARE_PER_CPU(struct rnd_state, net_rand_state);
+
+u32 prandom_u32_state(struct rnd_state *state);
+void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
+void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
+
+#define prandom_init_once(pcpu_state)			\
+	DO_ONCE(prandom_seed_full_state, (pcpu_state))
+
+/**
+ * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro)
+ * @ep_ro: right open interval endpoint
+ *
+ * Returns a pseudo-random number that is in interval [0, ep_ro). Note
+ * that the result depends on PRNG being well distributed in [0, ~0U]
+ * u32 space. Here we use maximally equidistributed combined Tausworthe
+ * generator, that is, prandom_u32(). This is useful when requesting a
+ * random index of an array containing ep_ro elements, for example.
+ *
+ * Returns: pseudo-random number in interval [0, ep_ro)
+ */
+static inline u32 prandom_u32_max(u32 ep_ro)
+{
+	return (u32)(((u64) prandom_u32() * ep_ro) >> 32);
+}
+
+/*
+ * Handle minimum values for seeds
+ */
+static inline u32 __seed(u32 x, u32 m)
+{
+	return (x < m) ? x + m : x;
+}
+
+/**
+ * prandom_seed_state - set seed for prandom_u32_state().
+ * @state: pointer to state structure to receive the seed.
+ * @seed: arbitrary 64-bit value to use as a seed.
+ */
+static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
+{
+	u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
+
+	state->s1 = __seed(i,   2U);
+	state->s2 = __seed(i,   8U);
+	state->s3 = __seed(i,  16U);
+	state->s4 = __seed(i, 128U);
+}
+
+/* Pseudo random number generator from numerical recipes. */
+static inline u32 next_pseudo_random32(u32 seed)
+{
+	return seed * 1664525 + 1013904223;
+}
+
+#endif
diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index 733fad7dfbed..6d15040c642c 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -207,28 +207,34 @@ static inline u32 qed_chain_get_cons_idx_u32(struct qed_chain *p_chain)
 
 static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain)
 {
+	u16 elem_per_page = p_chain->elem_per_page;
+	u32 prod = p_chain->u.chain16.prod_idx;
+	u32 cons = p_chain->u.chain16.cons_idx;
 	u16 used;
 
-	used = (u16) (((u32)0x10000 +
-		       (u32)p_chain->u.chain16.prod_idx) -
-		      (u32)p_chain->u.chain16.cons_idx);
+	if (prod < cons)
+		prod += (u32)U16_MAX + 1;
+
+	used = (u16)(prod - cons);
 	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
-		used -= p_chain->u.chain16.prod_idx / p_chain->elem_per_page -
-		    p_chain->u.chain16.cons_idx / p_chain->elem_per_page;
+		used -= prod / elem_per_page - cons / elem_per_page;
 
 	return (u16)(p_chain->capacity - used);
 }
 
 static inline u32 qed_chain_get_elem_left_u32(struct qed_chain *p_chain)
 {
+	u16 elem_per_page = p_chain->elem_per_page;
+	u64 prod = p_chain->u.chain32.prod_idx;
+	u64 cons = p_chain->u.chain32.cons_idx;
 	u32 used;
 
-	used = (u32) (((u64)0x100000000ULL +
-		       (u64)p_chain->u.chain32.prod_idx) -
-		      (u64)p_chain->u.chain32.cons_idx);
+	if (prod < cons)
+		prod += (u64)U32_MAX + 1;
+
+	used = (u32)(prod - cons);
 	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
-		used -= p_chain->u.chain32.prod_idx / p_chain->elem_per_page -
-		    p_chain->u.chain32.cons_idx / p_chain->elem_per_page;
+		used -= (u32)(prod / elem_per_page - cons / elem_per_page);
 
 	return p_chain->capacity - used;
 }
diff --git a/include/linux/random.h b/include/linux/random.h
index 4024f7d9c77d..8eda8c0cbba7 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -107,61 +107,12 @@ declare_get_random_var_wait(long)
 
 unsigned long randomize_page(unsigned long start, unsigned long range);
 
-u32 prandom_u32(void);
-void prandom_bytes(void *buf, size_t nbytes);
-void prandom_seed(u32 seed);
-void prandom_reseed_late(void);
-
-struct rnd_state {
-	__u32 s1, s2, s3, s4;
-};
-
-u32 prandom_u32_state(struct rnd_state *state);
-void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
-void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
-
-#define prandom_init_once(pcpu_state)			\
-	DO_ONCE(prandom_seed_full_state, (pcpu_state))
-
-/**
- * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro)
- * @ep_ro: right open interval endpoint
- *
- * Returns a pseudo-random number that is in interval [0, ep_ro). Note
- * that the result depends on PRNG being well distributed in [0, ~0U]
- * u32 space. Here we use maximally equidistributed combined Tausworthe
- * generator, that is, prandom_u32(). This is useful when requesting a
- * random index of an array containing ep_ro elements, for example.
- *
- * Returns: pseudo-random number in interval [0, ep_ro)
- */
-static inline u32 prandom_u32_max(u32 ep_ro)
-{
-	return (u32)(((u64) prandom_u32() * ep_ro) >> 32);
-}
-
 /*
- * Handle minimum values for seeds
+ * This is designed to be standalone for just prandom
+ * users, but for now we include it from <linux/random.h>
+ * for legacy reasons.
  */
-static inline u32 __seed(u32 x, u32 m)
-{
-	return (x < m) ? x + m : x;
-}
-
-/**
- * prandom_seed_state - set seed for prandom_u32_state().
- * @state: pointer to state structure to receive the seed.
- * @seed: arbitrary 64-bit value to use as a seed.
- */
-static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
-{
-	u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
-
-	state->s1 = __seed(i,   2U);
-	state->s2 = __seed(i,   8U);
-	state->s3 = __seed(i,  16U);
-	state->s4 = __seed(i, 128U);
-}
+#include <linux/prandom.h>
 
 #ifdef CONFIG_ARCH_RANDOM
 # include <asm/archrandom.h>
@@ -192,10 +143,4 @@ static inline bool arch_has_random_seed(void)
 }
 #endif
 
-/* Pseudo random number generator from numerical recipes. */
-static inline u32 next_pseudo_random32(u32 seed)
-{
-	return seed * 1664525 + 1013904223;
-}
-
 #endif /* _LINUX_RANDOM_H */
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index f189a8a3bbb8..7b3b5d05ab0d 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -243,6 +243,13 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
  * usual consistency guarantee. It is one wmb cheaper, because we can
  * collapse the two back-to-back wmb()s.
  *
+ * Note that, writes surrounding the barrier should be declared atomic (e.g.
+ * via WRITE_ONCE): a) to ensure the writes become visible to other threads
+ * atomically, avoiding compiler optimizations; b) to document which writes are
+ * meant to propagate to the reader critical section. This is necessary because
+ * neither writes before and after the barrier are enclosed in a seq-writer
+ * critical section that would ensure readers are aware of ongoing writes.
+ *
  *      seqcount_t seq;
  *      bool X = true, Y = false;
  *
@@ -262,11 +269,11 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
  *
  *      void write(void)
  *      {
- *              Y = true;
+ *              WRITE_ONCE(Y, true);
  *
  *              raw_write_seqcount_barrier(seq);
  *
- *              X = false;
+ *              WRITE_ONCE(X, false);
  *      }
  */
 static inline void raw_write_seqcount_barrier(seqcount_t *s)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a9a764a17c28..3690985e24a8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1675,6 +1675,18 @@ static inline __u32 skb_queue_len(const struct sk_buff_head *list_)
 }
 
 /**
+ *	skb_queue_len_lockless	- get queue length
+ *	@list_: list to measure
+ *
+ *	Return the length of an &sk_buff queue.
+ *	This variant can be used in lockless contexts.
+ */
+static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_)
+{
+	return READ_ONCE(list_->qlen);
+}
+
+/**
  *	__skb_queue_head_init - initialize non-spinlock portions of sk_buff_head
  *	@list: queue to initialize
  *
@@ -1881,7 +1893,7 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
 {
 	struct sk_buff *next, *prev;
 
-	list->qlen--;
+	WRITE_ONCE(list->qlen, list->qlen - 1);
 	next	   = skb->next;
 	prev	   = skb->prev;
 	skb->next  = skb->prev = NULL;
@@ -2999,8 +3011,9 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len)
  *	is untouched. Otherwise it is extended. Returns zero on
  *	success. The skb is freed on error if @free_on_error is true.
  */
-static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len,
-				  bool free_on_error)
+static inline int __must_check __skb_put_padto(struct sk_buff *skb,
+					       unsigned int len,
+					       bool free_on_error)
 {
 	unsigned int size = skb->len;
 
@@ -3023,7 +3036,7 @@ static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len,
  *	is untouched. Otherwise it is extended. Returns zero on
  *	success. The skb is freed on error.
  */
-static inline int skb_put_padto(struct sk_buff *skb, unsigned int len)
+static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len)
 {
 	return __skb_put_padto(skb, len, true);
 }
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 74b4911ac16d..19789fbea567 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -87,4 +87,10 @@ extern void splice_shrink_spd(struct splice_pipe_desc *);
 
 extern const struct pipe_buf_operations page_cache_pipe_buf_ops;
 extern const struct pipe_buf_operations default_pipe_buf_ops;
+
+extern long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
+			   loff_t *ppos, size_t len, unsigned int flags);
+extern long do_splice_to(struct file *in, loff_t *ppos,
+			 struct pipe_inode_info *pipe, size_t len,
+			 unsigned int flags);
 #endif
diff --git a/include/linux/string.h b/include/linux/string.h
index 3d43329c20be..315fef3aff4e 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -238,6 +238,31 @@ void __read_overflow3(void) __compiletime_error("detected read beyond size of ob
 void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter");
 
 #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE)
+
+#ifdef CONFIG_KASAN
+extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr);
+extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp);
+extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy);
+extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove);
+extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset);
+extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat);
+extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy);
+extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen);
+extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat);
+extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy);
+#else
+#define __underlying_memchr	__builtin_memchr
+#define __underlying_memcmp	__builtin_memcmp
+#define __underlying_memcpy	__builtin_memcpy
+#define __underlying_memmove	__builtin_memmove
+#define __underlying_memset	__builtin_memset
+#define __underlying_strcat	__builtin_strcat
+#define __underlying_strcpy	__builtin_strcpy
+#define __underlying_strlen	__builtin_strlen
+#define __underlying_strncat	__builtin_strncat
+#define __underlying_strncpy	__builtin_strncpy
+#endif
+
 __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size)
 {
 	size_t p_size = __builtin_object_size(p, 0);
@@ -245,14 +270,14 @@ __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size)
 		__write_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
-	return __builtin_strncpy(p, q, size);
+	return __underlying_strncpy(p, q, size);
 }
 
 __FORTIFY_INLINE char *strcat(char *p, const char *q)
 {
 	size_t p_size = __builtin_object_size(p, 0);
 	if (p_size == (size_t)-1)
-		return __builtin_strcat(p, q);
+		return __underlying_strcat(p, q);
 	if (strlcat(p, q, p_size) >= p_size)
 		fortify_panic(__func__);
 	return p;
@@ -266,7 +291,7 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p)
 	/* Work around gcc excess stack consumption issue */
 	if (p_size == (size_t)-1 ||
 	    (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0'))
-		return __builtin_strlen(p);
+		return __underlying_strlen(p);
 	ret = strnlen(p, p_size);
 	if (p_size <= ret)
 		fortify_panic(__func__);
@@ -299,7 +324,7 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size)
 			__write_overflow();
 		if (len >= p_size)
 			fortify_panic(__func__);
-		__builtin_memcpy(p, q, len);
+		__underlying_memcpy(p, q, len);
 		p[len] = '\0';
 	}
 	return ret;
@@ -312,12 +337,12 @@ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count)
 	size_t p_size = __builtin_object_size(p, 0);
 	size_t q_size = __builtin_object_size(q, 0);
 	if (p_size == (size_t)-1 && q_size == (size_t)-1)
-		return __builtin_strncat(p, q, count);
+		return __underlying_strncat(p, q, count);
 	p_len = strlen(p);
 	copy_len = strnlen(q, count);
 	if (p_size < p_len + copy_len + 1)
 		fortify_panic(__func__);
-	__builtin_memcpy(p + p_len, q, copy_len);
+	__underlying_memcpy(p + p_len, q, copy_len);
 	p[p_len + copy_len] = '\0';
 	return p;
 }
@@ -329,7 +354,7 @@ __FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size)
 		__write_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
-	return __builtin_memset(p, c, size);
+	return __underlying_memset(p, c, size);
 }
 
 __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size)
@@ -344,7 +369,7 @@ __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size)
 	}
 	if (p_size < size || q_size < size)
 		fortify_panic(__func__);
-	return __builtin_memcpy(p, q, size);
+	return __underlying_memcpy(p, q, size);
 }
 
 __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size)
@@ -359,7 +384,7 @@ __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size)
 	}
 	if (p_size < size || q_size < size)
 		fortify_panic(__func__);
-	return __builtin_memmove(p, q, size);
+	return __underlying_memmove(p, q, size);
 }
 
 extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan);
@@ -385,7 +410,7 @@ __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size)
 	}
 	if (p_size < size || q_size < size)
 		fortify_panic(__func__);
-	return __builtin_memcmp(p, q, size);
+	return __underlying_memcmp(p, q, size);
 }
 
 __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size)
@@ -395,7 +420,7 @@ __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size)
 		__read_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
-	return __builtin_memchr(p, c, size);
+	return __underlying_memchr(p, c, size);
 }
 
 void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv);
@@ -426,11 +451,22 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q)
 	size_t p_size = __builtin_object_size(p, 0);
 	size_t q_size = __builtin_object_size(q, 0);
 	if (p_size == (size_t)-1 && q_size == (size_t)-1)
-		return __builtin_strcpy(p, q);
+		return __underlying_strcpy(p, q);
 	memcpy(p, q, strlen(q) + 1);
 	return p;
 }
 
+/* Don't use these outside the FORITFY_SOURCE implementation */
+#undef __underlying_memchr
+#undef __underlying_memcmp
+#undef __underlying_memcpy
+#undef __underlying_memmove
+#undef __underlying_memset
+#undef __underlying_strcat
+#undef __underlying_strcpy
+#undef __underlying_strlen
+#undef __underlying_strncat
+#undef __underlying_strncpy
 #endif
 
 /**
diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h
index 5ac5db4d295f..566d5f547567 100644
--- a/include/linux/sunrpc/gss_api.h
+++ b/include/linux/sunrpc/gss_api.h
@@ -83,6 +83,7 @@ struct pf_desc {
 	u32	service;
 	char	*name;
 	char	*auth_domain_name;
+	struct auth_domain *domain;
 	bool	datatouch;
 };
 
diff --git a/include/linux/sunrpc/svcauth_gss.h b/include/linux/sunrpc/svcauth_gss.h
index a4528b26c8aa..d229d27ab19e 100644
--- a/include/linux/sunrpc/svcauth_gss.h
+++ b/include/linux/sunrpc/svcauth_gss.h
@@ -21,7 +21,8 @@ int gss_svc_init(void);
 void gss_svc_shutdown(void);
 int gss_svc_init_net(struct net *net);
 void gss_svc_shutdown_net(struct net *net);
-int svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name);
+struct auth_domain *svcauth_gss_register_pseudoflavor(u32 pseudoflavor,
+						      char *name);
 u32 svcauth_gss_flavor(struct auth_domain *dom);
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 60aea230dc6a..61eb40fef759 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -209,6 +209,8 @@ struct tcp_sock {
 		u8 reord;    /* reordering detected */
 	} rack;
 	u16	advmss;		/* Advertised MSS			*/
+	u8	tlp_retrans:1,	/* TLP is a retransmission */
+		unused_1:7;
 	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
 	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
 	u8	chrono_type:2,	/* current chronograph type */
@@ -229,7 +231,7 @@ struct tcp_sock {
 		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
 		save_syn:1,	/* Save headers of SYN packet */
 		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
-	u32	tlp_high_seq;	/* snd_nxt at the time of TLP retransmit. */
+	u32	tlp_high_seq;	/* snd_nxt at the time of TLP */
 
 /* RTT measurement */
 	u64	tcp_mstamp;	/* most recent packet received/sent */
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index a26ffbe09e71..06cb9184a42a 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -318,7 +318,7 @@ extern void syscall_unregfunc(void);
 		static const char *___tp_str __tracepoint_string = str; \
 		___tp_str;						\
 	})
-#define __tracepoint_string	__attribute__((section("__tracepoint_str")))
+#define __tracepoint_string	__attribute__((section("__tracepoint_str"), used))
 #else
 /*
  * tracepoint_string() is used to save the string address for userspace
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 251e655d407f..d49f193a44a2 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -243,6 +243,17 @@ extern long probe_kernel_read(void *dst, const void *src, size_t size);
 extern long __probe_kernel_read(void *dst, const void *src, size_t size);
 
 /*
+ * probe_user_read(): safely attempt to read from a location in user space
+ * @dst: pointer to the buffer that shall take the data
+ * @src: address to read from
+ * @size: size of the data chunk
+ *
+ * Safely read from address @src to the buffer at @dst.  If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+extern long probe_user_read(void *dst, const void __user *src, size_t size);
+
+/*
  * probe_kernel_write(): safely attempt to write to a location
  * @dst: address to write to
  * @src: pointer to the data that shall be written
@@ -254,7 +265,22 @@ extern long __probe_kernel_read(void *dst, const void *src, size_t size);
 extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
 extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
 
+/*
+ * probe_user_write(): safely attempt to write to a location in user space
+ * @dst: address to write to
+ * @src: pointer to the data that shall be written
+ * @size: size of the data chunk
+ *
+ * Safely write to address @dst from the buffer at @src.  If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+extern long notrace probe_user_write(void __user *dst, const void *src, size_t size);
+extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size);
+
 extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
+extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
+				     long count);
+extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count);
 
 /**
  * probe_kernel_address(): safely attempt to read from a location
@@ -267,7 +293,7 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
 	probe_kernel_read(&retval, addr, sizeof(retval))
 
 #ifndef user_access_begin
-#define user_access_begin() do { } while (0)
+#define user_access_begin(type, ptr, len) access_ok(type, ptr, len)
 #define user_access_end() do { } while (0)
 #define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0)
 #define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0)
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index 590d313b5f39..a865698361c1 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -248,6 +248,9 @@ int usb_function_activate(struct usb_function *);
 
 int usb_interface_id(struct usb_configuration *, struct usb_function *);
 
+int config_ep_by_speed_and_alt(struct usb_gadget *g, struct usb_function *f,
+				struct usb_ep *_ep, u8 alt);
+
 int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f,
 			struct usb_ep *_ep);
 
diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h
index 960bedbdec87..77f0f0af3a71 100644
--- a/include/linux/vga_switcheroo.h
+++ b/include/linux/vga_switcheroo.h
@@ -168,11 +168,8 @@ int vga_switcheroo_process_delayed_switch(void);
 bool vga_switcheroo_client_probe_defer(struct pci_dev *pdev);
 enum vga_switcheroo_state vga_switcheroo_get_client_state(struct pci_dev *dev);
 
-void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic);
-
 int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain);
 void vga_switcheroo_fini_domain_pm_ops(struct device *dev);
-int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain);
 #else
 
 static inline void vga_switcheroo_unregister_client(struct pci_dev *dev) {}
@@ -192,11 +189,8 @@ static inline int vga_switcheroo_process_delayed_switch(void) { return 0; }
 static inline bool vga_switcheroo_client_probe_defer(struct pci_dev *pdev) { return false; }
 static inline enum vga_switcheroo_state vga_switcheroo_get_client_state(struct pci_dev *dev) { return VGA_SWITCHEROO_ON; }
 
-static inline void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic) {}
-
 static inline int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; }
 static inline void vga_switcheroo_fini_domain_pm_ops(struct device *dev) {}
-static inline int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; }
 
 #endif
 #endif /* _LINUX_VGA_SWITCHEROO_H_ */
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 44e20c4b5141..d19bfdcf7749 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -31,6 +31,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 {
 	unsigned int gso_type = 0;
 	unsigned int thlen = 0;
+	unsigned int p_off = 0;
 	unsigned int ip_proto;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
@@ -68,7 +69,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
 
-		if (skb_transport_offset(skb) + thlen > skb_headlen(skb))
+		p_off = skb_transport_offset(skb) + thlen;
+		if (p_off > skb_headlen(skb))
 			return -EINVAL;
 	} else {
 		/* gso packets without NEEDS_CSUM do not set transport_offset.
@@ -90,23 +92,32 @@ retry:
 				return -EINVAL;
 			}
 
-			if (keys.control.thoff + thlen > skb_headlen(skb) ||
+			p_off = keys.control.thoff + thlen;
+			if (p_off > skb_headlen(skb) ||
 			    keys.basic.ip_proto != ip_proto)
 				return -EINVAL;
 
 			skb_set_transport_header(skb, keys.control.thoff);
+		} else if (gso_type) {
+			p_off = thlen;
+			if (p_off > skb_headlen(skb))
+				return -EINVAL;
 		}
 	}
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
+		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
-		skb_shinfo(skb)->gso_size = gso_size;
-		skb_shinfo(skb)->gso_type = gso_type;
+		/* Too small packets are not really GSO ones. */
+		if (skb->len - p_off > gso_size) {
+			shinfo->gso_size = gso_size;
+			shinfo->gso_type = gso_type;
 
-		/* Header must be checked, and gso_segs computed. */
-		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
-		skb_shinfo(skb)->gso_segs = 0;
+			/* Header must be checked, and gso_segs computed. */
+			shinfo->gso_type |= SKB_GSO_DODGY;
+			shinfo->gso_segs = 0;
+		}
 	}
 
 	return 0;
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index e223e2632edd..8b8d13f01cae 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -149,7 +149,8 @@ virtio_transport_dgram_enqueue(struct vsock_sock *vsk,
 
 void virtio_transport_destruct(struct vsock_sock *vsk);
 
-void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt);
+void virtio_transport_recv_pkt(struct virtio_transport *t,
+			       struct virtio_vsock_pkt *pkt);
 void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt);
 void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt);
 u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted);
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index d70f77a4b62a..b0945fb7242f 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -52,8 +52,10 @@ ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t);
 ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size);
 int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int);
 int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int);
+int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **);
 int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int);
 int __vfs_removexattr(struct dentry *, const char *);
+int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **);
 int vfs_removexattr(struct dentry *, const char *);
 
 ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size);
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 775387d6ca95..ff268bb0c60f 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -69,7 +69,8 @@ static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm)
 {
 	dtm->install = jiffies_to_clock_t(jiffies - stm->install);
 	dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse);
-	dtm->firstuse = jiffies_to_clock_t(jiffies - stm->firstuse);
+	dtm->firstuse = stm->firstuse ?
+		jiffies_to_clock_t(jiffies - stm->firstuse) : 0;
 	dtm->expires = jiffies_to_clock_t(stm->expires);
 }
 
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index f30ee99a1d72..a4cda4768210 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -270,6 +270,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
 int ipv6_sock_ac_drop(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
+void __ipv6_sock_ac_close(struct sock *sk);
 void ipv6_sock_ac_close(struct sock *sk);
 
 int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr);
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 6cd4d5b48239..f80356a98081 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1252,16 +1252,34 @@ static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status)
 		conn->security_cfm_cb(conn, status);
 }
 
-static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status,
-								__u8 encrypt)
+static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status)
 {
 	struct hci_cb *cb;
+	__u8 encrypt;
+
+	if (conn->state == BT_CONFIG) {
+		if (!status)
+			conn->state = BT_CONNECTED;
 
-	if (conn->sec_level == BT_SECURITY_SDP)
-		conn->sec_level = BT_SECURITY_LOW;
+		hci_connect_cfm(conn, status);
+		hci_conn_drop(conn);
+		return;
+	}
 
-	if (conn->pending_sec_level > conn->sec_level)
-		conn->sec_level = conn->pending_sec_level;
+	if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags))
+		encrypt = 0x00;
+	else if (test_bit(HCI_CONN_AES_CCM, &conn->flags))
+		encrypt = 0x02;
+	else
+		encrypt = 0x01;
+
+	if (!status) {
+		if (conn->sec_level == BT_SECURITY_SDP)
+			conn->sec_level = BT_SECURITY_LOW;
+
+		if (conn->pending_sec_level > conn->sec_level)
+			conn->sec_level = conn->pending_sec_level;
+	}
 
 	mutex_lock(&hci_cb_list_lock);
 	list_for_each_entry(cb, &hci_cb_list, list) {
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 0697fd413087..21dbd38f724d 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -619,6 +619,8 @@ struct l2cap_ops {
 	struct sk_buff		*(*alloc_skb) (struct l2cap_chan *chan,
 					       unsigned long hdr_len,
 					       unsigned long len, int nb);
+	int			(*filter) (struct l2cap_chan * chan,
+					   struct sk_buff *skb);
 };
 
 struct l2cap_conn {
diff --git a/include/net/dst.h b/include/net/dst.h
index 5ebc7356a381..90bad764bc98 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -427,7 +427,15 @@ static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, co
 static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst,
 						     struct sk_buff *skb)
 {
-	struct neighbour *n =  dst->ops->neigh_lookup(dst, skb, NULL);
+	struct neighbour *n = NULL;
+
+	/* The packets from tunnel devices (eg bareudp) may have only
+	 * metadata in the dst pointer of skb. Hence a pointer check of
+	 * neigh_lookup is needed.
+	 */
+	if (dst->ops->neigh_lookup)
+		n = dst->ops->neigh_lookup(dst, skb, NULL);
+
 	return IS_ERR(n) ? NULL : n;
 }
 
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 5ac169a735f4..c25b2e75732b 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -34,12 +34,6 @@ struct genl_info;
  *	do additional, common, filtering and return an error
  * @post_doit: called after an operation's doit callback, it may
  *	undo operations done by pre_doit, for example release locks
- * @mcast_bind: a socket bound to the given multicast group (which
- *	is given as the offset into the groups array)
- * @mcast_unbind: a socket was unbound from the given multicast group.
- *	Note that unbind() will not be called symmetrically if the
- *	generic netlink family is removed while there are still open
- *	sockets.
  * @attrbuf: buffer to store parsed attributes (private)
  * @mcgrps: multicast groups used by this family
  * @n_mcgrps: number of multicast groups
@@ -62,8 +56,6 @@ struct genl_family {
 	void			(*post_doit)(const struct genl_ops *ops,
 					     struct sk_buff *skb,
 					     struct genl_info *info);
-	int			(*mcast_bind)(struct net *net, int group);
-	void			(*mcast_unbind)(struct net *net, int group);
 	struct nlattr **	attrbuf;	/* private */
 	const struct genl_ops *	ops;
 	const struct genl_multicast_group *mcgrps;
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 13e4c89a8231..ceab3a5dd530 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -321,5 +321,9 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
 int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
 			       char __user *optval, unsigned int optlen);
 
+/* update the fast reuse flag when adding a socket */
+void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
+			       struct sock *sk);
+
 struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
 #endif /* _INET_CONNECTION_SOCK_H */
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index f4e5ac8aa366..1fb79c78e200 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1607,18 +1607,16 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 }
 #endif /* CONFIG_IP_VS_NFCT */
 
-/* Really using conntrack? */
-static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp,
-					     struct sk_buff *skb)
+/* Using old conntrack that can not be redirected to another real server? */
+static inline bool ip_vs_conn_uses_old_conntrack(struct ip_vs_conn *cp,
+						 struct sk_buff *skb)
 {
 #ifdef CONFIG_IP_VS_NFCT
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct;
 
-	if (!(cp->flags & IP_VS_CONN_F_NFCT))
-		return false;
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct)
+	if (ct && nf_ct_is_confirmed(ct))
 		return true;
 #endif
 	return false;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index a9704c57430d..3107895115c2 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -136,6 +136,8 @@ static inline u8 nft_reg_load8(u32 *sreg)
 static inline void nft_data_copy(u32 *dst, const struct nft_data *src,
 				 unsigned int len)
 {
+	if (len % NFT_REG32_SIZE)
+		dst[len / NFT_REG32_SIZE] = 0;
 	memcpy(dst, src, len);
 }
 
diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index deaafa9b09cb..d4da07048aa3 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -361,11 +361,13 @@ enum {
 	 ipv4_is_anycast_6to4(a))
 
 /* Flags used for the bind address copy functions.  */
-#define SCTP_ADDR6_ALLOWED	0x00000001	/* IPv6 address is allowed by
+#define SCTP_ADDR4_ALLOWED	0x00000001	/* IPv4 address is allowed by
 						   local sock family */
-#define SCTP_ADDR4_PEERSUPP	0x00000002	/* IPv4 address is supported by
+#define SCTP_ADDR6_ALLOWED	0x00000002	/* IPv6 address is allowed by
+						   local sock family */
+#define SCTP_ADDR4_PEERSUPP	0x00000004	/* IPv4 address is supported by
 						   peer */
-#define SCTP_ADDR6_PEERSUPP	0x00000004	/* IPv6 address is supported by
+#define SCTP_ADDR6_PEERSUPP	0x00000008	/* IPv6 address is supported by
 						   peer */
 
 /* Reasons to retransmit. */
diff --git a/include/net/sock.h b/include/net/sock.h
index c6a003bc4737..55d16db84ea4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -816,6 +816,8 @@ static inline int sk_memalloc_socks(void)
 {
 	return static_key_false(&memalloc_socks);
 }
+
+void __receive_sock(struct file *file);
 #else
 
 static inline int sk_memalloc_socks(void)
@@ -823,6 +825,8 @@ static inline int sk_memalloc_socks(void)
 	return 0;
 }
 
+static inline void __receive_sock(struct file *file)
+{ }
 #endif
 
 static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask)
@@ -1687,7 +1691,6 @@ static inline int sk_tx_queue_get(const struct sock *sk)
 
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
-	sk_tx_queue_clear(sk);
 	sk->sk_socket = sock;
 }
 
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 57b8b11cf7d4..86ff11157449 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1808,21 +1808,17 @@ static inline int xfrm_replay_state_esn_len(struct xfrm_replay_state_esn *replay
 static inline int xfrm_replay_clone(struct xfrm_state *x,
 				     struct xfrm_state *orig)
 {
-	x->replay_esn = kzalloc(xfrm_replay_state_esn_len(orig->replay_esn),
+
+	x->replay_esn = kmemdup(orig->replay_esn,
+				xfrm_replay_state_esn_len(orig->replay_esn),
 				GFP_KERNEL);
 	if (!x->replay_esn)
 		return -ENOMEM;
-
-	x->replay_esn->bmp_len = orig->replay_esn->bmp_len;
-	x->replay_esn->replay_window = orig->replay_esn->replay_window;
-
-	x->preplay_esn = kmemdup(x->replay_esn,
-				 xfrm_replay_state_esn_len(x->replay_esn),
+	x->preplay_esn = kmemdup(orig->preplay_esn,
+				 xfrm_replay_state_esn_len(orig->preplay_esn),
 				 GFP_KERNEL);
-	if (!x->preplay_esn) {
-		kfree(x->replay_esn);
+	if (!x->preplay_esn)
 		return -ENOMEM;
-	}
 
 	return 0;
 }
diff --git a/include/soc/nps/common.h b/include/soc/nps/common.h
index 9b1d43d671a3..8c18dc6d3fde 100644
--- a/include/soc/nps/common.h
+++ b/include/soc/nps/common.h
@@ -45,6 +45,12 @@
 #define CTOP_INST_MOV2B_FLIP_R3_B1_B2_INST	0x5B60
 #define CTOP_INST_MOV2B_FLIP_R3_B1_B2_LIMM	0x00010422
 
+#ifndef AUX_IENABLE
+#define AUX_IENABLE				0x40c
+#endif
+
+#define CTOP_AUX_IACK				(0xFFFFF800 + 0x088)
+
 #ifndef __ASSEMBLY__
 
 /* In order to increase compilation test coverage */
diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index 33a07c3badf0..f58b8edf0371 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -72,6 +72,7 @@ struct snd_compr_runtime {
  * @direction: stream direction, playback/recording
  * @metadata_set: metadata set flag, true when set
  * @next_track: has userspace signal next track transition, true when set
+ * @partial_drain: undergoing partial_drain for stream, true when set
  * @private_data: pointer to DSP private data
  */
 struct snd_compr_stream {
@@ -83,6 +84,7 @@ struct snd_compr_stream {
 	enum snd_compr_direction direction;
 	bool metadata_set;
 	bool next_track;
+	bool partial_drain;
 	void *private_data;
 };
 
@@ -186,7 +188,13 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream)
 	if (snd_BUG_ON(!stream))
 		return;
 
-	stream->runtime->state = SNDRV_PCM_STATE_SETUP;
+	/* for partial_drain case we are back to running state on success */
+	if (stream->partial_drain) {
+		stream->runtime->state = SNDRV_PCM_STATE_RUNNING;
+		stream->partial_drain = false; /* clear this flag as well */
+	} else {
+		stream->runtime->state = SNDRV_PCM_STATE_SETUP;
+	}
 
 	wake_up(&stream->runtime->sleep);
 }
diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index 926ea701cdc4..5d0bf1688eba 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -228,9 +228,6 @@ struct hdac_io_ops {
 #define HDA_UNSOL_QUEUE_SIZE	64
 #define HDA_MAX_CODECS		8	/* limit by controller side */
 
-/* HD Audio class code */
-#define PCI_CLASS_MULTIMEDIA_HD_AUDIO	0x0403
-
 /*
  * CORB/RIRB
  *
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index a58caf5807ff..de3a1effbcbd 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -333,7 +333,7 @@ enum rxrpc_congest_change {
 	EM(rxrpc_cong_begin_retransmission,	" Retrans") \
 	EM(rxrpc_cong_cleared_nacks,		" Cleared") \
 	EM(rxrpc_cong_new_low_nack,		" NewLowN") \
-	EM(rxrpc_cong_no_change,		"") \
+	EM(rxrpc_cong_no_change,		" -") \
 	EM(rxrpc_cong_progress,			" Progres") \
 	EM(rxrpc_cong_retransmit_again,		" ReTxAgn") \
 	EM(rxrpc_cong_rtt_window_end,		" RttWinE") \
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 2e1fa7910306..3a76ca2eecd0 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -361,8 +361,9 @@ DEFINE_WBC_EVENT(wbc_writepage);
 TRACE_EVENT(writeback_queue_io,
 	TP_PROTO(struct bdi_writeback *wb,
 		 struct wb_writeback_work *work,
+		 unsigned long dirtied_before,
 		 int moved),
-	TP_ARGS(wb, work, moved),
+	TP_ARGS(wb, work, dirtied_before, moved),
 	TP_STRUCT__entry(
 		__array(char,		name, 32)
 		__field(unsigned long,	older)
@@ -372,19 +373,17 @@ TRACE_EVENT(writeback_queue_io,
 		__field(unsigned int,	cgroup_ino)
 	),
 	TP_fast_assign(
-		unsigned long *older_than_this = work->older_than_this;
 		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
-		__entry->older	= older_than_this ?  *older_than_this : 0;
-		__entry->age	= older_than_this ?
-				  (jiffies - *older_than_this) * 1000 / HZ : -1;
+		__entry->older	= dirtied_before;
+		__entry->age	= (jiffies - dirtied_before) * 1000 / HZ;
 		__entry->moved	= moved;
 		__entry->reason	= work->reason;
 		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
 	),
 	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%u",
 		__entry->name,
-		__entry->older,	/* older_than_this in jiffies */
-		__entry->age,	/* older_than_this in relative milliseconds */
+		__entry->older,	/* dirtied_before in jiffies */
+		__entry->age,	/* dirtied_before in relative milliseconds */
 		__entry->moved,
 		__print_symbolic(__entry->reason, WB_WORK_REASON),
 		__entry->cgroup_ino
diff --git a/include/uapi/linux/aufs_type.h b/include/uapi/linux/aufs_type.h
new file mode 100644
index 000000000000..4f22ff62de52
--- /dev/null
+++ b/include/uapi/linux/aufs_type.h
@@ -0,0 +1,419 @@
+/*
+ * Copyright (C) 2005-2017 Junjiro R. Okajima
+ *
+ * This program, aufs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __AUFS_TYPE_H__
+#define __AUFS_TYPE_H__
+
+#define AUFS_NAME	"aufs"
+
+#ifdef __KERNEL__
+/*
+ * define it before including all other headers.
+ * sched.h may use pr_* macros before defining "current", so define the
+ * no-current version first, and re-define later.
+ */
+#define pr_fmt(fmt)	AUFS_NAME " %s:%d: " fmt, __func__, __LINE__
+#include <linux/sched.h>
+#undef pr_fmt
+#define pr_fmt(fmt) \
+		AUFS_NAME " %s:%d:%.*s[%d]: " fmt, __func__, __LINE__, \
+		(int)sizeof(current->comm), current->comm, current->pid
+#else
+#include <stdint.h>
+#include <sys/types.h>
+#endif /* __KERNEL__ */
+
+#include <linux/limits.h>
+
+#define AUFS_VERSION	"4.12-20170911"
+
+/* todo? move this to linux-2.6.19/include/magic.h */
+#define AUFS_SUPER_MAGIC	('a' << 24 | 'u' << 16 | 'f' << 8 | 's')
+
+/* ---------------------------------------------------------------------- */
+
+#ifdef CONFIG_AUFS_BRANCH_MAX_127
+typedef int8_t aufs_bindex_t;
+#define AUFS_BRANCH_MAX 127
+#else
+typedef int16_t aufs_bindex_t;
+#ifdef CONFIG_AUFS_BRANCH_MAX_511
+#define AUFS_BRANCH_MAX 511
+#elif defined(CONFIG_AUFS_BRANCH_MAX_1023)
+#define AUFS_BRANCH_MAX 1023
+#elif defined(CONFIG_AUFS_BRANCH_MAX_32767)
+#define AUFS_BRANCH_MAX 32767
+#endif
+#endif
+
+#ifdef __KERNEL__
+#ifndef AUFS_BRANCH_MAX
+#error unknown CONFIG_AUFS_BRANCH_MAX value
+#endif
+#endif /* __KERNEL__ */
+
+/* ---------------------------------------------------------------------- */
+
+#define AUFS_FSTYPE		AUFS_NAME
+
+#define AUFS_ROOT_INO		2
+#define AUFS_FIRST_INO		11
+
+#define AUFS_WH_PFX		".wh."
+#define AUFS_WH_PFX_LEN		((int)sizeof(AUFS_WH_PFX) - 1)
+#define AUFS_WH_TMP_LEN		4
+/* a limit for rmdir/rename a dir and copyup */
+#define AUFS_MAX_NAMELEN	(NAME_MAX \
+				- AUFS_WH_PFX_LEN * 2	/* doubly whiteouted */\
+				- 1			/* dot */\
+				- AUFS_WH_TMP_LEN)	/* hex */
+#define AUFS_XINO_FNAME		"." AUFS_NAME ".xino"
+#define AUFS_XINO_DEFPATH	"/tmp/" AUFS_XINO_FNAME
+#define AUFS_XINO_DEF_SEC	30 /* seconds */
+#define AUFS_XINO_DEF_TRUNC	45 /* percentage */
+#define AUFS_DIRWH_DEF		3
+#define AUFS_RDCACHE_DEF	10 /* seconds */
+#define AUFS_RDCACHE_MAX	3600 /* seconds */
+#define AUFS_RDBLK_DEF		512 /* bytes */
+#define AUFS_RDHASH_DEF		32
+#define AUFS_WKQ_NAME		AUFS_NAME "d"
+#define AUFS_MFS_DEF_SEC	30 /* seconds */
+#define AUFS_MFS_MAX_SEC	3600 /* seconds */
+#define AUFS_FHSM_CACHE_DEF_SEC	30 /* seconds */
+#define AUFS_PLINK_WARN		50 /* number of plinks in a single bucket */
+
+/* pseudo-link maintenace under /proc */
+#define AUFS_PLINK_MAINT_NAME	"plink_maint"
+#define AUFS_PLINK_MAINT_DIR	"fs/" AUFS_NAME
+#define AUFS_PLINK_MAINT_PATH	AUFS_PLINK_MAINT_DIR "/" AUFS_PLINK_MAINT_NAME
+
+#define AUFS_DIROPQ_NAME	AUFS_WH_PFX ".opq" /* whiteouted doubly */
+#define AUFS_WH_DIROPQ		AUFS_WH_PFX AUFS_DIROPQ_NAME
+
+#define AUFS_BASE_NAME		AUFS_WH_PFX AUFS_NAME
+#define AUFS_PLINKDIR_NAME	AUFS_WH_PFX "plnk"
+#define AUFS_ORPHDIR_NAME	AUFS_WH_PFX "orph"
+
+/* doubly whiteouted */
+#define AUFS_WH_BASE		AUFS_WH_PFX AUFS_BASE_NAME
+#define AUFS_WH_PLINKDIR	AUFS_WH_PFX AUFS_PLINKDIR_NAME
+#define AUFS_WH_ORPHDIR		AUFS_WH_PFX AUFS_ORPHDIR_NAME
+
+/* branch permissions and attributes */
+#define AUFS_BRPERM_RW		"rw"
+#define AUFS_BRPERM_RO		"ro"
+#define AUFS_BRPERM_RR		"rr"
+#define AUFS_BRATTR_COO_REG	"coo_reg"
+#define AUFS_BRATTR_COO_ALL	"coo_all"
+#define AUFS_BRATTR_FHSM	"fhsm"
+#define AUFS_BRATTR_UNPIN	"unpin"
+#define AUFS_BRATTR_ICEX	"icex"
+#define AUFS_BRATTR_ICEX_SEC	"icexsec"
+#define AUFS_BRATTR_ICEX_SYS	"icexsys"
+#define AUFS_BRATTR_ICEX_TR	"icextr"
+#define AUFS_BRATTR_ICEX_USR	"icexusr"
+#define AUFS_BRATTR_ICEX_OTH	"icexoth"
+#define AUFS_BRRATTR_WH		"wh"
+#define AUFS_BRWATTR_NLWH	"nolwh"
+#define AUFS_BRWATTR_MOO	"moo"
+
+#define AuBrPerm_RW		1		/* writable, hardlinkable wh */
+#define AuBrPerm_RO		(1 << 1)	/* readonly */
+#define AuBrPerm_RR		(1 << 2)	/* natively readonly */
+#define AuBrPerm_Mask		(AuBrPerm_RW | AuBrPerm_RO | AuBrPerm_RR)
+
+#define AuBrAttr_COO_REG	(1 << 3)	/* copy-up on open */
+#define AuBrAttr_COO_ALL	(1 << 4)
+#define AuBrAttr_COO_Mask	(AuBrAttr_COO_REG | AuBrAttr_COO_ALL)
+
+#define AuBrAttr_FHSM		(1 << 5)	/* file-based hsm */
+#define AuBrAttr_UNPIN		(1 << 6)	/* rename-able top dir of
+						   branch. meaningless since
+						   linux-3.18-rc1 */
+
+/* ignore error in copying XATTR */
+#define AuBrAttr_ICEX_SEC	(1 << 7)
+#define AuBrAttr_ICEX_SYS	(1 << 8)
+#define AuBrAttr_ICEX_TR	(1 << 9)
+#define AuBrAttr_ICEX_USR	(1 << 10)
+#define AuBrAttr_ICEX_OTH	(1 << 11)
+#define AuBrAttr_ICEX		(AuBrAttr_ICEX_SEC	\
+				 | AuBrAttr_ICEX_SYS	\
+				 | AuBrAttr_ICEX_TR	\
+				 | AuBrAttr_ICEX_USR	\
+				 | AuBrAttr_ICEX_OTH)
+
+#define AuBrRAttr_WH		(1 << 12)	/* whiteout-able */
+#define AuBrRAttr_Mask		AuBrRAttr_WH
+
+#define AuBrWAttr_NoLinkWH	(1 << 13)	/* un-hardlinkable whiteouts */
+#define AuBrWAttr_MOO		(1 << 14)	/* move-up on open */
+#define AuBrWAttr_Mask		(AuBrWAttr_NoLinkWH | AuBrWAttr_MOO)
+
+#define AuBrAttr_CMOO_Mask	(AuBrAttr_COO_Mask | AuBrWAttr_MOO)
+
+/* #warning test userspace */
+#ifdef __KERNEL__
+#ifndef CONFIG_AUFS_FHSM
+#undef AuBrAttr_FHSM
+#define AuBrAttr_FHSM		0
+#endif
+#ifndef CONFIG_AUFS_XATTR
+#undef	AuBrAttr_ICEX
+#define AuBrAttr_ICEX		0
+#undef	AuBrAttr_ICEX_SEC
+#define AuBrAttr_ICEX_SEC	0
+#undef	AuBrAttr_ICEX_SYS
+#define AuBrAttr_ICEX_SYS	0
+#undef	AuBrAttr_ICEX_TR
+#define AuBrAttr_ICEX_TR	0
+#undef	AuBrAttr_ICEX_USR
+#define AuBrAttr_ICEX_USR	0
+#undef	AuBrAttr_ICEX_OTH
+#define AuBrAttr_ICEX_OTH	0
+#endif
+#endif
+
+/* the longest combination */
+/* AUFS_BRATTR_ICEX and AUFS_BRATTR_ICEX_TR don't affect here */
+#define AuBrPermStrSz	sizeof(AUFS_BRPERM_RW			\
+			       "+" AUFS_BRATTR_COO_REG		\
+			       "+" AUFS_BRATTR_FHSM		\
+			       "+" AUFS_BRATTR_UNPIN		\
+			       "+" AUFS_BRATTR_ICEX_SEC		\
+			       "+" AUFS_BRATTR_ICEX_SYS		\
+			       "+" AUFS_BRATTR_ICEX_USR		\
+			       "+" AUFS_BRATTR_ICEX_OTH		\
+			       "+" AUFS_BRWATTR_NLWH)
+
+typedef struct {
+	char a[AuBrPermStrSz];
+} au_br_perm_str_t;
+
+static inline int au_br_writable(int brperm)
+{
+	return brperm & AuBrPerm_RW;
+}
+
+static inline int au_br_whable(int brperm)
+{
+	return brperm & (AuBrPerm_RW | AuBrRAttr_WH);
+}
+
+static inline int au_br_wh_linkable(int brperm)
+{
+	return !(brperm & AuBrWAttr_NoLinkWH);
+}
+
+static inline int au_br_cmoo(int brperm)
+{
+	return brperm & AuBrAttr_CMOO_Mask;
+}
+
+static inline int au_br_fhsm(int brperm)
+{
+	return brperm & AuBrAttr_FHSM;
+}
+
+/* ---------------------------------------------------------------------- */
+
+/* ioctl */
+enum {
+	/* readdir in userspace */
+	AuCtl_RDU,
+	AuCtl_RDU_INO,
+
+	AuCtl_WBR_FD,	/* pathconf wrapper */
+	AuCtl_IBUSY,	/* busy inode */
+	AuCtl_MVDOWN,	/* move-down */
+	AuCtl_BR,	/* info about branches */
+	AuCtl_FHSM_FD	/* connection for fhsm */
+};
+
+/* borrowed from linux/include/linux/kernel.h */
+#ifndef ALIGN
+#define ALIGN(x, a)		__ALIGN_MASK(x, (typeof(x))(a)-1)
+#define __ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
+#endif
+
+/* borrowed from linux/include/linux/compiler-gcc3.h */
+#ifndef __aligned
+#define __aligned(x)			__attribute__((aligned(x)))
+#endif
+
+#ifdef __KERNEL__
+#ifndef __packed
+#define __packed			__attribute__((packed))
+#endif
+#endif
+
+struct au_rdu_cookie {
+	uint64_t	h_pos;
+	int16_t		bindex;
+	uint8_t		flags;
+	uint8_t		pad;
+	uint32_t	generation;
+} __aligned(8);
+
+struct au_rdu_ent {
+	uint64_t	ino;
+	int16_t		bindex;
+	uint8_t		type;
+	uint8_t		nlen;
+	uint8_t		wh;
+	char		name[0];
+} __aligned(8);
+
+static inline int au_rdu_len(int nlen)
+{
+	/* include the terminating NULL */
+	return ALIGN(sizeof(struct au_rdu_ent) + nlen + 1,
+		     sizeof(uint64_t));
+}
+
+union au_rdu_ent_ul {
+	struct au_rdu_ent __user	*e;
+	uint64_t			ul;
+};
+
+enum {
+	AufsCtlRduV_SZ,
+	AufsCtlRduV_End
+};
+
+struct aufs_rdu {
+	/* input */
+	union {
+		uint64_t	sz;	/* AuCtl_RDU */
+		uint64_t	nent;	/* AuCtl_RDU_INO */
+	};
+	union au_rdu_ent_ul	ent;
+	uint16_t		verify[AufsCtlRduV_End];
+
+	/* input/output */
+	uint32_t		blk;
+
+	/* output */
+	union au_rdu_ent_ul	tail;
+	/* number of entries which were added in a single call */
+	uint64_t		rent;
+	uint8_t			full;
+	uint8_t			shwh;
+
+	struct au_rdu_cookie	cookie;
+} __aligned(8);
+
+/* ---------------------------------------------------------------------- */
+
+struct aufs_wbr_fd {
+	uint32_t	oflags;
+	int16_t		brid;
+} __aligned(8);
+
+/* ---------------------------------------------------------------------- */
+
+struct aufs_ibusy {
+	uint64_t	ino, h_ino;
+	int16_t		bindex;
+} __aligned(8);
+
+/* ---------------------------------------------------------------------- */
+
+/* error code for move-down */
+/* the actual message strings are implemented in aufs-util.git */
+enum {
+	EAU_MVDOWN_OPAQUE = 1,
+	EAU_MVDOWN_WHITEOUT,
+	EAU_MVDOWN_UPPER,
+	EAU_MVDOWN_BOTTOM,
+	EAU_MVDOWN_NOUPPER,
+	EAU_MVDOWN_NOLOWERBR,
+	EAU_Last
+};
+
+/* flags for move-down */
+#define AUFS_MVDOWN_DMSG	1
+#define AUFS_MVDOWN_OWLOWER	(1 << 1)	/* overwrite lower */
+#define AUFS_MVDOWN_KUPPER	(1 << 2)	/* keep upper */
+#define AUFS_MVDOWN_ROLOWER	(1 << 3)	/* do even if lower is RO */
+#define AUFS_MVDOWN_ROLOWER_R	(1 << 4)	/* did on lower RO */
+#define AUFS_MVDOWN_ROUPPER	(1 << 5)	/* do even if upper is RO */
+#define AUFS_MVDOWN_ROUPPER_R	(1 << 6)	/* did on upper RO */
+#define AUFS_MVDOWN_BRID_UPPER	(1 << 7)	/* upper brid */
+#define AUFS_MVDOWN_BRID_LOWER	(1 << 8)	/* lower brid */
+#define AUFS_MVDOWN_FHSM_LOWER	(1 << 9)	/* find fhsm attr for lower */
+#define AUFS_MVDOWN_STFS	(1 << 10)	/* req. stfs */
+#define AUFS_MVDOWN_STFS_FAILED	(1 << 11)	/* output: stfs is unusable */
+#define AUFS_MVDOWN_BOTTOM	(1 << 12)	/* output: no more lowers */
+
+/* index for move-down */
+enum {
+	AUFS_MVDOWN_UPPER,
+	AUFS_MVDOWN_LOWER,
+	AUFS_MVDOWN_NARRAY
+};
+
+/*
+ * additional info of move-down
+ * number of free blocks and inodes.
+ * subset of struct kstatfs, but smaller and always 64bit.
+ */
+struct aufs_stfs {
+	uint64_t	f_blocks;
+	uint64_t	f_bavail;
+	uint64_t	f_files;
+	uint64_t	f_ffree;
+};
+
+struct aufs_stbr {
+	int16_t			brid;	/* optional input */
+	int16_t			bindex;	/* output */
+	struct aufs_stfs	stfs;	/* output when AUFS_MVDOWN_STFS set */
+} __aligned(8);
+
+struct aufs_mvdown {
+	uint32_t		flags;			/* input/output */
+	struct aufs_stbr	stbr[AUFS_MVDOWN_NARRAY]; /* input/output */
+	int8_t			au_errno;		/* output */
+} __aligned(8);
+
+/* ---------------------------------------------------------------------- */
+
+union aufs_brinfo {
+	/* PATH_MAX may differ between kernel-space and user-space */
+	char	_spacer[4096];
+	struct {
+		int16_t	id;
+		int	perm;
+		char	path[0];
+	};
+} __aligned(8);
+
+/* ---------------------------------------------------------------------- */
+
+#define AuCtlType		'A'
+#define AUFS_CTL_RDU		_IOWR(AuCtlType, AuCtl_RDU, struct aufs_rdu)
+#define AUFS_CTL_RDU_INO	_IOWR(AuCtlType, AuCtl_RDU_INO, struct aufs_rdu)
+#define AUFS_CTL_WBR_FD		_IOW(AuCtlType, AuCtl_WBR_FD, \
+				     struct aufs_wbr_fd)
+#define AUFS_CTL_IBUSY		_IOWR(AuCtlType, AuCtl_IBUSY, struct aufs_ibusy)
+#define AUFS_CTL_MVDOWN		_IOWR(AuCtlType, AuCtl_MVDOWN, \
+				      struct aufs_mvdown)
+#define AUFS_CTL_BRINFO		_IOW(AuCtlType, AuCtl_BR, union aufs_brinfo)
+#define AUFS_CTL_FHSM_FD	_IOW(AuCtlType, AuCtl_FHSM_FD, int)
+
+#endif /* __AUFS_TYPE_H__ */
diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index 61769d4b7dba..bce76e55a3c8 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -793,7 +793,8 @@
 #define SW_LINEIN_INSERT	0x0d  /* set = inserted */
 #define SW_MUTE_DEVICE		0x0e  /* set = device disabled */
 #define SW_PEN_INSERTED		0x0f  /* set = pen inserted */
-#define SW_MAX			0x0f
+#define SW_MACHINE_COVER	0x10  /* set = cover closed */
+#define SW_MAX			0x10
 #define SW_CNT			(SW_MAX+1)
 
 /*
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 27c62abb6c9e..62f5e47aed16 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -189,9 +189,11 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_HYPERV_SYNIC          1
 #define KVM_EXIT_HYPERV_HCALL          2
 	__u32 type;
+	__u32 pad1;
 	union {
 		struct {
 			__u32 msr;
+			__u32 pad2;
 			__u64 control;
 			__u64 evt_page;
 			__u64 msg_page;
@@ -733,9 +735,10 @@ struct kvm_ppc_resize_hpt {
 #define KVM_VM_PPC_HV 1
 #define KVM_VM_PPC_PR 2
 
-/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
-#define KVM_VM_MIPS_TE		0
+/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */
+#define KVM_VM_MIPS_AUTO	0
 #define KVM_VM_MIPS_VZ		1
+#define KVM_VM_MIPS_TE		2
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h
index 45f369dc0a42..83a8c10fd104 100644
--- a/include/uapi/linux/mmc/ioctl.h
+++ b/include/uapi/linux/mmc/ioctl.h
@@ -3,6 +3,7 @@
 #define LINUX_MMC_IOCTL_H
 
 #include <linux/types.h>
+#include <linux/major.h>
 
 struct mmc_ioc_cmd {
 	/* Implies direction of data.  true = write, false = read */
diff --git a/include/uapi/linux/msdos_fs.h b/include/uapi/linux/msdos_fs.h
index a45d0754102e..844700c7abe7 100644
--- a/include/uapi/linux/msdos_fs.h
+++ b/include/uapi/linux/msdos_fs.h
@@ -10,7 +10,9 @@
  * The MS-DOS filesystem constants/structures
  */
 
+#ifndef SECTOR_SIZE
 #define SECTOR_SIZE	512		/* sector size (bytes) */
+#endif
 #define SECTOR_BITS	9		/* log2(SECTOR_SIZE) */
 #define MSDOS_DPB	(MSDOS_DPS)	/* dir entries per block */
 #define MSDOS_DPB_BITS	4		/* log2(MSDOS_DPB) */
@@ -46,6 +48,7 @@
 
 #define CASE_LOWER_BASE	8	/* base is lower case */
 #define CASE_LOWER_EXT	16	/* extension is lower case */
+#define FAT_NO_83NAME	32	/* no 8.3 short filename for this file */
 
 #define DELETED_FLAG	0xe5	/* marks file as deleted when in name[0] */
 #define IS_FREE(n)	(!*(n) || *(n) == DELETED_FLAG)
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index a3ee277b17a1..49b6997c3255 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -125,7 +125,7 @@ enum nf_tables_msg_types {
  * @NFTA_LIST_ELEM: list element (NLA_NESTED)
  */
 enum nft_list_attributes {
-	NFTA_LIST_UNPEC,
+	NFTA_LIST_UNSPEC,
 	NFTA_LIST_ELEM,
 	__NFTA_LIST_MAX
 };
diff --git a/include/uapi/linux/nfs_mount.h b/include/uapi/linux/nfs_mount.h
index e44e00616ab5..af94a8b7ad5c 100644
--- a/include/uapi/linux/nfs_mount.h
+++ b/include/uapi/linux/nfs_mount.h
@@ -21,7 +21,7 @@
  * mount-to-kernel version compatibility.  Some of these aren't used yet
  * but here they are anyway.
  */
-#define NFS_MOUNT_VERSION	6
+#define NFS_MOUNT_VERSION	7
 #define NFS_MAX_CONTEXT_LEN	256
 
 struct nfs_mount_data {
@@ -44,6 +44,8 @@ struct nfs_mount_data {
 	struct nfs3_fh	root;			/* 4 */
 	int		pseudoflavor;		/* 5 */
 	char		context[NFS_MAX_CONTEXT_LEN + 1];	/* 6 */
+	int		nfs_prog; /* 7 */
+	int		mount_prog; /* 7 */
 };
 
 /* bits in the flags field visible to user space */
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index b0d15c73f6d7..1f2d8c81f0e0 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -329,6 +329,7 @@ struct mdp_superblock_1 {
 #define	MD_FEATURE_JOURNAL		512 /* support write cache */
 #define	MD_FEATURE_PPL			1024 /* support PPL */
 #define	MD_FEATURE_MULTIPLE_PPLS	2048 /* support for multiple PPLs */
+#define	MD_FEATURE_RAID0_LAYOUT		4096 /* layout is meaningful for RAID0 */
 #define	MD_FEATURE_ALL			(MD_FEATURE_BITMAP_OFFSET	\
 					|MD_FEATURE_RECOVERY_OFFSET	\
 					|MD_FEATURE_RESHAPE_ACTIVE	\
@@ -341,6 +342,7 @@ struct mdp_superblock_1 {
 					|MD_FEATURE_JOURNAL		\
 					|MD_FEATURE_PPL			\
 					|MD_FEATURE_MULTIPLE_PPLS	\
+					|MD_FEATURE_RAID0_LAYOUT	\
 					)
 
 struct r5l_payload_header {
diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h
index 86eca3208b6b..a2c006a364e0 100644
--- a/include/uapi/linux/wireless.h
+++ b/include/uapi/linux/wireless.h
@@ -74,6 +74,8 @@
 #include <linux/socket.h>		/* for "struct sockaddr" et al	*/
 #include <linux/if.h>			/* for IFNAMSIZ and co... */
 
+#include <stddef.h>                     /* for offsetof */
+
 /***************************** VERSION *****************************/
 /*
  * This constant is used to know the availability of the wireless
@@ -1090,8 +1092,7 @@ struct iw_event {
 /* iw_point events are special. First, the payload (extra data) come at
  * the end of the event, so they are bigger than IW_EV_POINT_LEN. Second,
  * we omit the pointer, so start at an offset. */
-#define IW_EV_POINT_OFF (((char *) &(((struct iw_point *) NULL)->length)) - \
-			  (char *) NULL)
+#define IW_EV_POINT_OFF offsetof(struct iw_point, length)
 #define IW_EV_POINT_LEN	(IW_EV_LCP_LEN + sizeof(struct iw_point) - \
 			 IW_EV_POINT_OFF)
 
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index e3af2859188b..0b636432cdf3 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -304,7 +304,7 @@ enum xfrm_attr_type_t {
 	XFRMA_PROTO,		/* __u8 */
 	XFRMA_ADDRESS_FILTER,	/* struct xfrm_address_filter */
 	XFRMA_PAD,
-	XFRMA_OFFLOAD_DEV,	/* struct xfrm_state_offload */
+	XFRMA_OFFLOAD_DEV,	/* struct xfrm_user_offload */
 	XFRMA_OUTPUT_MARK,	/* __u32 */
 	__XFRMA_MAX
 
diff --git a/include/video/uvesafb.h b/include/video/uvesafb.h
index 8d2a3bfc8dac..f6cbd0d3c8ed 100644
--- a/include/video/uvesafb.h
+++ b/include/video/uvesafb.h
@@ -89,7 +89,9 @@ struct vbe_mode_ib {
 
 #define UVESAFB_DEFAULT_MODE "640x480-16"
 
-/* How long to wait for a reply from userspace [ms] */
+/* How long to wait for a reply from userspace [ms]
+ * This is the default value of module param task_timeout
+ */
 #define UVESAFB_TIMEOUT 5000
 
 /* Max number of concurrent tasks */
diff --git a/init/Kconfig b/init/Kconfig
index 46075327c165..f3f7e41c32fd 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1098,6 +1098,31 @@ menuconfig EXPERT
           environments which can tolerate a "non-standard" kernel.
           Only use this if you really know what you are doing.
 
+config UPTIME_LIMITED_KERNEL
+	bool "Create a kernel with uptime limitations"
+	default n
+	help
+	  Limit the amount of time a kernel can run. The associated UPTIME_LIMIT*
+	  kernel config options should be used to tune the behaviour.
+
+config UPTIME_LIMIT_DURATION
+	int "Kernel uptime limit in minutes"
+	depends on UPTIME_LIMITED_KERNEL
+	range 0 14400
+	default 0
+	help
+	  Define the uptime limitation on a kernel in minutes. Once
+	  the defined time expires the kernel will emit a warning, cease
+	  to be usable and eventually restart. The valid range is 0 (disable)
+	  to 14400 (10 days)
+
+config UPTIME_LIMIT_KERNEL_REBOOT
+	bool "Reboot a time limited kernel at expiration"
+	depends on UPTIME_LIMITED_KERNEL
+	default y
+	help
+	  Reboot an uptime limited kernel at expiration.
+
 config UID16
 	bool "Enable 16-bit UID system calls" if EXPERT
 	depends on HAVE_UID16 && MULTIUSER
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 7cf4f6dafd5f..6072a224f4be 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -417,7 +417,9 @@ retry:
 		printk("DEBUG_BLOCK_EXT_DEVT is enabled, you need to specify "
 		       "explicit textual name for \"root=\" boot option.\n");
 #endif
-		panic("VFS: Unable to mount root fs on %s", b);
+		printk(KERN_EMERG "VFS: Unable to mount root fs on %s\n", b);
+		printk(KERN_EMERG "User configuration error - no valid root filesystem found\n");
+		panic("Invalid configuration from end user prevents continuing");
 	}
 	if (!(flags & SB_RDONLY)) {
 		flags |= SB_RDONLY;
@@ -433,7 +435,9 @@ retry:
 #ifdef CONFIG_BLOCK
 	__bdevname(ROOT_DEV, b);
 #endif
-	panic("VFS: Unable to mount root fs on %s", b);
+	printk(KERN_EMERG "VFS: Unable to mount root fs on %s\n", b);
+	printk(KERN_EMERG "User configuration error - no valid root filesystem found\n");
+	panic("Invalid configuration from end user prevents continuing");
 out:
 	put_page(page);
 }
diff --git a/init/main.c b/init/main.c
index 603b1ad88cb6..ae6225c0c187 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1041,6 +1041,7 @@ static int __ref kernel_init(void *unused)
 
 static noinline void __init kernel_init_freeable(void)
 {
+	struct stat console_stat;
 	/*
 	 * Wait until kthreadd is all set-up.
 	 */
@@ -1074,6 +1075,12 @@ static noinline void __init kernel_init_freeable(void)
 
 	do_basic_setup();
 
+	/* Use /dev/console to infer if the rootfs is setup properly */
+	if (sys_newlstat((char __user *) "/dev/console", (struct stat __user *) &console_stat)
+			|| !S_ISCHR(console_stat.st_mode)) {
+		panic("/dev/console is missing or not a character device!\nPlease ensure your rootfs is properly configured\n");
+	}
+
 	/* Open the /dev/console on the rootfs, this should never fail */
 	if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
 		pr_err("Warning: unable to open an initial console.\n");
diff --git a/kernel/Makefile b/kernel/Makefile
index 43e92e3691ec..583ff349e37e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_FREEZER) += freezer.o
 obj-$(CONFIG_PROFILING) += profile.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 obj-y += time/
+obj-$(CONFIG_UPTIME_LIMITED_KERNEL) += uptime_limit.o
 obj-$(CONFIG_FUTEX) += futex.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
 obj-$(CONFIG_SMP) += smp.o
diff --git a/kernel/audit.c b/kernel/audit.c
index aa6d5e39526b..6faaa908544a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -853,7 +853,7 @@ main_queue:
 	return 0;
 }
 
-int audit_send_list(void *_dest)
+int audit_send_list_thread(void *_dest)
 {
 	struct audit_netlink_list *dest = _dest;
 	struct sk_buff *skb;
@@ -897,19 +897,30 @@ out_kfree_skb:
 	return NULL;
 }
 
+static void audit_free_reply(struct audit_reply *reply)
+{
+	if (!reply)
+		return;
+
+	if (reply->skb)
+		kfree_skb(reply->skb);
+	if (reply->net)
+		put_net(reply->net);
+	kfree(reply);
+}
+
 static int audit_send_reply_thread(void *arg)
 {
 	struct audit_reply *reply = (struct audit_reply *)arg;
-	struct sock *sk = audit_get_sk(reply->net);
 
 	mutex_lock(&audit_cmd_mutex);
 	mutex_unlock(&audit_cmd_mutex);
 
 	/* Ignore failure. It'll only happen if the sender goes away,
 	   because our timeout is set to infinite. */
-	netlink_unicast(sk, reply->skb, reply->portid, 0);
-	put_net(reply->net);
-	kfree(reply);
+	netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, 0);
+	reply->skb = NULL;
+	audit_free_reply(reply);
 	return 0;
 }
 
@@ -923,35 +934,32 @@ static int audit_send_reply_thread(void *arg)
  * @payload: payload data
  * @size: payload size
  *
- * Allocates an skb, builds the netlink message, and sends it to the port id.
- * No failure notifications.
+ * Allocates a skb, builds the netlink message, and sends it to the port id.
  */
 static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done,
 			     int multi, const void *payload, int size)
 {
-	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
-	struct sk_buff *skb;
 	struct task_struct *tsk;
-	struct audit_reply *reply = kmalloc(sizeof(struct audit_reply),
-					    GFP_KERNEL);
+	struct audit_reply *reply;
 
+	reply = kzalloc(sizeof(*reply), GFP_KERNEL);
 	if (!reply)
 		return;
 
-	skb = audit_make_reply(seq, type, done, multi, payload, size);
-	if (!skb)
-		goto out;
-
-	reply->net = get_net(net);
+	reply->skb = audit_make_reply(seq, type, done, multi, payload, size);
+	if (!reply->skb)
+		goto err;
+	reply->net = get_net(sock_net(NETLINK_CB(request_skb).sk));
 	reply->portid = NETLINK_CB(request_skb).portid;
-	reply->skb = skb;
 
 	tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
-	if (!IS_ERR(tsk))
-		return;
-	kfree_skb(skb);
-out:
-	kfree(reply);
+	if (IS_ERR(tsk))
+		goto err;
+
+	return;
+
+err:
+	audit_free_reply(reply);
 }
 
 /*
diff --git a/kernel/audit.h b/kernel/audit.h
index 9b110ae17ee3..1007773b0b81 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -248,7 +248,7 @@ struct audit_netlink_list {
 	struct sk_buff_head q;
 };
 
-int audit_send_list(void *_dest);
+int audit_send_list_thread(void *_dest);
 
 extern int selinux_audit_rule_update(void);
 
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 35f1d706bd5b..ac87820cc082 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -316,8 +316,6 @@ static void audit_update_watch(struct audit_parent *parent,
 			if (oentry->rule.exe)
 				audit_remove_mark(oentry->rule.exe);
 
-			audit_watch_log_rule_change(r, owatch, "updated_rules");
-
 			call_rcu(&oentry->rcu, audit_free_rule_rcu);
 		}
 
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 16cf396ea738..f26f4cb5d08d 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1137,11 +1137,8 @@ int audit_rule_change(int type, int seq, void *data, size_t datasz)
  */
 int audit_list_rules_send(struct sk_buff *request_skb, int seq)
 {
-	u32 portid = NETLINK_CB(request_skb).portid;
-	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
 	struct task_struct *tsk;
 	struct audit_netlink_list *dest;
-	int err = 0;
 
 	/* We can't just spew out the rules here because we might fill
 	 * the available socket buffer space and deadlock waiting for
@@ -1149,25 +1146,26 @@ int audit_list_rules_send(struct sk_buff *request_skb, int seq)
 	 * happen if we're actually running in the context of auditctl
 	 * trying to _send_ the stuff */
 
-	dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL);
+	dest = kmalloc(sizeof(*dest), GFP_KERNEL);
 	if (!dest)
 		return -ENOMEM;
-	dest->net = get_net(net);
-	dest->portid = portid;
+	dest->net = get_net(sock_net(NETLINK_CB(request_skb).sk));
+	dest->portid = NETLINK_CB(request_skb).portid;
 	skb_queue_head_init(&dest->q);
 
 	mutex_lock(&audit_filter_mutex);
 	audit_list_rules(seq, &dest->q);
 	mutex_unlock(&audit_filter_mutex);
 
-	tsk = kthread_run(audit_send_list, dest, "audit_send_list");
+	tsk = kthread_run(audit_send_list_thread, dest, "audit_send_list");
 	if (IS_ERR(tsk)) {
 		skb_queue_purge(&dest->q);
+		put_net(dest->net);
 		kfree(dest);
-		err = PTR_ERR(tsk);
+		return PTR_ERR(tsk);
 	}
 
-	return err;
+	return 0;
 }
 
 int audit_comparator(u32 left, u32 op, u32 right)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 505e69854eb8..ecc58137525b 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -645,26 +645,23 @@ static void htab_elem_free_rcu(struct rcu_head *head)
 	struct htab_elem *l = container_of(head, struct htab_elem, rcu);
 	struct bpf_htab *htab = l->htab;
 
-	/* must increment bpf_prog_active to avoid kprobe+bpf triggering while
-	 * we're calling kfree, otherwise deadlock is possible if kprobes
-	 * are placed somewhere inside of slub
-	 */
-	preempt_disable();
-	__this_cpu_inc(bpf_prog_active);
 	htab_elem_free(htab, l);
-	__this_cpu_dec(bpf_prog_active);
-	preempt_enable();
 }
 
-static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
 {
 	struct bpf_map *map = &htab->map;
+	void *ptr;
 
 	if (map->ops->map_fd_put_ptr) {
-		void *ptr = fd_htab_map_get_ptr(map, l);
-
+		ptr = fd_htab_map_get_ptr(map, l);
 		map->ops->map_fd_put_ptr(ptr);
 	}
+}
+
+static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+{
+	htab_put_fd_value(htab, l);
 
 	if (htab_is_prealloc(htab)) {
 		__pcpu_freelist_push(&htab->freelist, &l->fnode);
@@ -725,6 +722,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			 */
 			pl_new = this_cpu_ptr(htab->extra_elems);
 			l_new = *pl_new;
+			htab_put_fd_value(htab, old_elem);
 			*pl_new = old_elem;
 		} else {
 			struct pcpu_freelist_node *l;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 2b3f2ea6a8a3..ada060e628ce 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5798,17 +5798,8 @@ void cgroup_sk_alloc_disable(void)
 
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 {
-	if (cgroup_sk_alloc_disabled)
-		return;
-
-	/* Socket clone path */
-	if (skcd->val) {
-		/*
-		 * We might be cloning a socket which is left in an empty
-		 * cgroup and the cgroup might have already been rmdir'd.
-		 * Don't use cgroup_get_live().
-		 */
-		cgroup_get(sock_cgroup_ptr(skcd));
+	if (cgroup_sk_alloc_disabled) {
+		skcd->no_refcnt = 1;
 		return;
 	}
 
@@ -5832,8 +5823,26 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 	rcu_read_unlock();
 }
 
+void cgroup_sk_clone(struct sock_cgroup_data *skcd)
+{
+	/* Socket clone path */
+	if (skcd->val) {
+		if (skcd->no_refcnt)
+			return;
+		/*
+		 * We might be cloning a socket which is left in an empty
+		 * cgroup and the cgroup might have already been rmdir'd.
+		 * Don't use cgroup_get_live().
+		 */
+		cgroup_get(sock_cgroup_ptr(skcd));
+	}
+}
+
 void cgroup_sk_free(struct sock_cgroup_data *skcd)
 {
+	if (skcd->no_refcnt)
+		return;
+
 	cgroup_put(sock_cgroup_ptr(skcd));
 }
 
diff --git a/kernel/compat.c b/kernel/compat.c
index 7e83733d4c95..45ae3ace49c2 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -437,10 +437,9 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask,
 	bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG);
 	nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size);
 
-	if (!access_ok(VERIFY_READ, umask, bitmap_size / 8))
+	if (!user_access_begin(VERIFY_READ, umask, bitmap_size / 8))
 		return -EFAULT;
 
-	user_access_begin();
 	while (nr_compat_longs > 1) {
 		compat_ulong_t l1, l2;
 		unsafe_get_user(l1, umask++, Efault);
@@ -467,10 +466,9 @@ long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask,
 	bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG);
 	nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size);
 
-	if (!access_ok(VERIFY_WRITE, umask, bitmap_size / 8))
+	if (!user_access_begin(VERIFY_WRITE, umask, bitmap_size / 8))
 		return -EFAULT;
 
-	user_access_begin();
 	while (nr_compat_longs > 1) {
 		unsigned long m = *mask++;
 		unsafe_put_user((compat_ulong_t)m, umask++, Efault);
diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
index 67b02e138a47..2ed6351e2a7e 100644
--- a/kernel/cpu_pm.c
+++ b/kernel/cpu_pm.c
@@ -89,7 +89,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
  */
 int cpu_pm_enter(void)
 {
-	int nr_calls;
+	int nr_calls = 0;
 	int ret = 0;
 
 	ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls);
@@ -140,7 +140,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_exit);
  */
 int cpu_cluster_pm_enter(void)
 {
-	int nr_calls;
+	int nr_calls = 0;
 	int ret = 0;
 
 	ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls);
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 94aa9ae0007a..694fcd049282 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -444,6 +444,7 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
 
 	if (exception_level > 1) {
 		dump_stack();
+		kgdb_io_module_registered = false;
 		panic("Recursive entry to debugger");
 	}
 
@@ -488,6 +489,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
 		arch_kgdb_ops.disable_hw_break(regs);
 
 acquirelock:
+	rcu_read_lock();
 	/*
 	 * Interrupts will be restored by the 'trap return' code, except when
 	 * single stepping.
@@ -544,6 +546,7 @@ return_normal:
 			atomic_dec(&slaves_in_kgdb);
 			dbg_touch_watchdogs();
 			local_irq_restore(flags);
+			rcu_read_unlock();
 			return 0;
 		}
 		cpu_relax();
@@ -562,6 +565,7 @@ return_normal:
 		raw_spin_unlock(&dbg_master_lock);
 		dbg_touch_watchdogs();
 		local_irq_restore(flags);
+		rcu_read_unlock();
 
 		goto acquirelock;
 	}
@@ -681,6 +685,7 @@ kgdb_restore:
 	raw_spin_unlock(&dbg_master_lock);
 	dbg_touch_watchdogs();
 	local_irq_restore(flags);
+	rcu_read_unlock();
 
 	return kgdb_info[cpu].ret_state;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5636c9c48545..5807fad2c405 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -94,11 +94,11 @@ static void remote_function(void *data)
  * @info:	the function call argument
  *
  * Calls the function @func when the task is currently running. This might
- * be on the current CPU, which just calls the function directly
+ * be on the current CPU, which just calls the function directly.  This will
+ * retry due to any failures in smp_call_function_single(), such as if the
+ * task_cpu() goes offline concurrently.
  *
- * returns: @func return value, or
- *	    -ESRCH  - when the process isn't running
- *	    -EAGAIN - when the process moved away
+ * returns @func return value or -ESRCH or -ENXIO when the process isn't running
  */
 static int
 task_function_call(struct task_struct *p, remote_function_f func, void *info)
@@ -111,11 +111,17 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info)
 	};
 	int ret;
 
-	do {
-		ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+	for (;;) {
+		ret = smp_call_function_single(task_cpu(p), remote_function,
+					       &data, 1);
 		if (!ret)
 			ret = data.ret;
-	} while (ret == -EAGAIN);
+
+		if (ret != -EAGAIN)
+			break;
+
+		cond_resched();
+	}
 
 	return ret;
 }
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index c74fc9826250..f08ba79ee5d1 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -612,10 +612,6 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 	if (ret)
 		goto out;
 
-	/* uprobe_write_opcode() assumes we don't cross page boundary */
-	BUG_ON((uprobe->offset & ~PAGE_MASK) +
-			UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
-
 	smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */
 	set_bit(UPROBE_COPY_INSN, &uprobe->flags);
 
@@ -894,6 +890,13 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 	if (offset > i_size_read(inode))
 		return -EINVAL;
 
+	/*
+	 * This ensures that copy_from_page() and copy_to_page()
+	 * can't cross page boundary.
+	 */
+	if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE))
+		return -EINVAL;
+
  retry:
 	uprobe = alloc_uprobe(inode, offset);
 	if (!uprobe)
@@ -1704,6 +1707,9 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	uprobe_opcode_t opcode;
 	int result;
 
+	if (WARN_ON_ONCE(!IS_ALIGNED(vaddr, UPROBE_SWBP_INSN_SIZE)))
+		return -EINVAL;
+
 	pagefault_disable();
 	result = __get_user(opcode, (uprobe_opcode_t __user *)vaddr);
 	pagefault_enable();
@@ -1887,7 +1893,7 @@ static void handle_swbp(struct pt_regs *regs)
 	if (!uprobe) {
 		if (is_swbp > 0) {
 			/* No matching uprobe; signal SIGTRAP. */
-			send_sig(SIGTRAP, current, 0);
+			force_sig(SIGTRAP, current);
 		} else {
 			/*
 			 * Either we raced with uprobe_unregister() or we can't
diff --git a/kernel/exit.c b/kernel/exit.c
index d1baf9c96c3e..7a7984d7a4d8 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -770,8 +770,12 @@ void __noreturn do_exit(long code)
 	struct task_struct *tsk = current;
 	int group_dead;
 
-	profile_task_exit(tsk);
-	kcov_task_exit(tsk);
+	/*
+	 * We can get here from a kernel oops, sometimes with preemption off.
+	 * Start by checking for critical errors.
+	 * Then fix up important state like USER_DS and preemption.
+	 * Then do everything else.
+	 */
 
 	WARN_ON(blk_needs_flush_plug(tsk));
 
@@ -789,6 +793,16 @@ void __noreturn do_exit(long code)
 	 */
 	set_fs(USER_DS);
 
+	if (unlikely(in_atomic())) {
+		pr_info("note: %s[%d] exited with preempt_count %d\n",
+			current->comm, task_pid_nr(current),
+			preempt_count());
+		preempt_count_set(PREEMPT_ENABLED);
+	}
+
+	profile_task_exit(tsk);
+	kcov_task_exit(tsk);
+
 	ptrace_event(PTRACE_EVENT_EXIT, code);
 
 	validate_creds_for_do_exit(tsk);
@@ -806,13 +820,6 @@ void __noreturn do_exit(long code)
 
 	exit_signals(tsk);  /* sets PF_EXITING */
 
-	if (unlikely(in_atomic())) {
-		pr_info("note: %s[%d] exited with preempt_count %d\n",
-			current->comm, task_pid_nr(current),
-			preempt_count());
-		preempt_count_set(PREEMPT_ENABLED);
-	}
-
 	/* sync mm's RSS info before statistics gathering */
 	if (tsk->mm)
 		sync_mm_rss(tsk->mm);
@@ -1597,10 +1604,9 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 	if (!infop)
 		return err;
 
-	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+	if (!user_access_begin(VERIFY_WRITE, infop, sizeof(*infop)))
 		return -EFAULT;
 
-	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
 	unsafe_put_user(info.cause, &infop->si_code, Efault);
@@ -1725,10 +1731,9 @@ COMPAT_SYSCALL_DEFINE5(waitid,
 	if (!infop)
 		return err;
 
-	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+	if (!user_access_begin(VERIFY_WRITE, infop, sizeof(*infop)))
 		return -EFAULT;
 
-	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
 	unsafe_put_user(info.cause, &infop->si_code, Efault);
diff --git a/kernel/fork.c b/kernel/fork.c
index 0a328cf0cb13..dc9ce1b3060b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -670,7 +670,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 			struct inode *inode = file_inode(file);
 			struct address_space *mapping = file->f_mapping;
 
-			get_file(file);
+			vma_get_file(tmp);
 			if (tmp->vm_flags & VM_DENYWRITE)
 				atomic_dec(&inode->i_writecount);
 			i_mmap_lock_write(mapping);
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index ca5e5c0ef853..5b9e76117ded 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -19,7 +19,9 @@
 #include <linux/vmalloc.h>
 #include "gcov.h"
 
-#if (__GNUC__ >= 7)
+#if (__GNUC__ >= 10)
+#define GCOV_COUNTERS			8
+#elif (__GNUC__ >= 7)
 #define GCOV_COUNTERS			9
 #elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
 #define GCOV_COUNTERS			10
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 5277949e82e0..3193be58805c 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -168,9 +168,9 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 			set_bit(IRQTF_AFFINITY, &action->thread_flags);
 }
 
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
 static void irq_validate_effective_affinity(struct irq_data *data)
 {
-#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
 	const struct cpumask *m = irq_data_get_effective_affinity_mask(data);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 
@@ -178,9 +178,19 @@ static void irq_validate_effective_affinity(struct irq_data *data)
 		return;
 	pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n",
 		     chip->name, data->irq);
-#endif
 }
 
+static inline void irq_init_effective_affinity(struct irq_data *data,
+					       const struct cpumask *mask)
+{
+	cpumask_copy(irq_data_get_effective_affinity_mask(data), mask);
+}
+#else
+static inline void irq_validate_effective_affinity(struct irq_data *data) { }
+static inline void irq_init_effective_affinity(struct irq_data *data,
+					       const struct cpumask *mask) { }
+#endif
+
 int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 			bool force)
 {
@@ -205,6 +215,30 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	return ret;
 }
 
+static bool irq_set_affinity_deactivated(struct irq_data *data,
+					 const struct cpumask *mask, bool force)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+
+	/*
+	 * Handle irq chips which can handle affinity only in activated
+	 * state correctly
+	 *
+	 * If the interrupt is not yet activated, just store the affinity
+	 * mask and do not call the chip driver at all. On activation the
+	 * driver has to make sure anyway that the interrupt is in a
+	 * useable state so startup works.
+	 */
+	if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) ||
+	    irqd_is_activated(data) || !irqd_affinity_on_activate(data))
+		return false;
+
+	cpumask_copy(desc->irq_common_data.affinity, mask);
+	irq_init_effective_affinity(data, mask);
+	irqd_set(data, IRQD_AFFINITY_SET);
+	return true;
+}
+
 int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 			    bool force)
 {
@@ -215,6 +249,9 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 	if (!chip || !chip->irq_set_affinity)
 		return -EINVAL;
 
+	if (irq_set_affinity_deactivated(data, mask, force))
+		return 0;
+
 	if (irq_can_move_pcntxt(data)) {
 		ret = irq_do_set_affinity(data, mask, force);
 	} else {
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 86ae0eb80b53..8b8cecd18cce 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -38,17 +38,18 @@ bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear)
 void irq_move_masked_irq(struct irq_data *idata)
 {
 	struct irq_desc *desc = irq_data_to_desc(idata);
-	struct irq_chip *chip = desc->irq_data.chip;
+	struct irq_data *data = &desc->irq_data;
+	struct irq_chip *chip = data->chip;
 
-	if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
+	if (likely(!irqd_is_setaffinity_pending(data)))
 		return;
 
-	irqd_clr_move_pending(&desc->irq_data);
+	irqd_clr_move_pending(data);
 
 	/*
 	 * Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
 	 */
-	if (irqd_is_per_cpu(&desc->irq_data)) {
+	if (irqd_is_per_cpu(data)) {
 		WARN_ON(1);
 		return;
 	}
@@ -73,9 +74,20 @@ void irq_move_masked_irq(struct irq_data *idata)
 	 * For correct operation this depends on the caller
 	 * masking the irqs.
 	 */
-	if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
-		irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
-
+	if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) {
+		int ret;
+
+		ret = irq_do_set_affinity(data, desc->pending_mask, false);
+		/*
+		 * If the there is a cleanup pending in the underlying
+		 * vector management, reschedule the move for the next
+		 * interrupt. Leave desc->pending_mask intact.
+		 */
+		if (ret == -EBUSY) {
+			irqd_set_move_pending(data);
+			return;
+		}
+	}
 	cpumask_clear(desc->pending_mask);
 }
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 66f1818d4762..fdf6656cce29 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -599,11 +599,12 @@ static void kprobe_optimizer(struct work_struct *work)
 	mutex_unlock(&module_mutex);
 	mutex_unlock(&text_mutex);
 	cpus_read_unlock();
-	mutex_unlock(&kprobe_mutex);
 
 	/* Step 5: Kick optimizer again if needed */
 	if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list))
 		kick_kprobe_optimizer();
+
+	mutex_unlock(&kprobe_mutex);
 }
 
 /* Wait for completing optimization and unoptimization */
@@ -1217,6 +1218,26 @@ __releases(hlist_lock)
 }
 NOKPROBE_SYMBOL(kretprobe_table_unlock);
 
+struct kprobe kprobe_busy = {
+	.addr = (void *) get_kprobe,
+};
+
+void kprobe_busy_begin(void)
+{
+	struct kprobe_ctlblk *kcb;
+
+	preempt_disable();
+	__this_cpu_write(current_kprobe, &kprobe_busy);
+	kcb = get_kprobe_ctlblk();
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+}
+
+void kprobe_busy_end(void)
+{
+	__this_cpu_write(current_kprobe, NULL);
+	preempt_enable();
+}
+
 /*
  * This function is called from finish_task_switch when task tk becomes dead,
  * so that we can recycle any function-return probe instances associated
@@ -1234,6 +1255,8 @@ void kprobe_flush_task(struct task_struct *tk)
 		/* Early boot.  kretprobe_table_locks not yet initialized. */
 		return;
 
+	kprobe_busy_begin();
+
 	INIT_HLIST_HEAD(&empty_rp);
 	hash = hash_ptr(tk, KPROBE_HASH_BITS);
 	head = &kretprobe_inst_table[hash];
@@ -1247,6 +1270,8 @@ void kprobe_flush_task(struct task_struct *tk)
 		hlist_del(&ri->hlist);
 		kfree(ri);
 	}
+
+	kprobe_busy_end();
 }
 NOKPROBE_SYMBOL(kprobe_flush_task);
 
@@ -2092,6 +2117,9 @@ static void kill_kprobe(struct kprobe *p)
 {
 	struct kprobe *kp;
 
+	if (WARN_ON_ONCE(kprobe_gone(p)))
+		return;
+
 	p->flags |= KPROBE_FLAG_GONE;
 	if (kprobe_aggrprobe(p)) {
 		/*
@@ -2109,6 +2137,14 @@ static void kill_kprobe(struct kprobe *p)
 	 * the original probed function (which will be freed soon) any more.
 	 */
 	arch_remove_kprobe(p);
+
+	/*
+	 * The module is going away. We should disarm the kprobe which
+	 * is using ftrace, because ftrace framework is still available at
+	 * MODULE_STATE_GOING notification.
+	 */
+	if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed)
+		disarm_kprobe_ftrace(p);
 }
 
 /* Disable one kprobe */
@@ -2227,7 +2263,10 @@ static int kprobes_module_callback(struct notifier_block *nb,
 	mutex_lock(&kprobe_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
-		hlist_for_each_entry_rcu(p, head, hlist)
+		hlist_for_each_entry_rcu(p, head, hlist) {
+			if (kprobe_gone(p))
+				continue;
+
 			if (within_module_init((unsigned long)p->addr, mod) ||
 			    (checkcore &&
 			     within_module_core((unsigned long)p->addr, mod))) {
@@ -2244,6 +2283,7 @@ static int kprobes_module_callback(struct notifier_block *nb,
 				 */
 				kill_kprobe(p);
 			}
+		}
 	}
 	mutex_unlock(&kprobe_mutex);
 	return NOTIFY_DONE;
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 8b2ef15e3552..06c02cd0ff57 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -430,7 +430,7 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt)
 	seq_time(m, lt->min);
 	seq_time(m, lt->max);
 	seq_time(m, lt->total);
-	seq_time(m, lt->nr ? div_s64(lt->total, lt->nr) : 0);
+	seq_time(m, lt->nr ? div64_u64(lt->total, lt->nr) : 0);
 }
 
 static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 4e50beb162c0..f96b22db5fe7 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2092,6 +2092,9 @@ static int __init console_setup(char *str)
 	char *s, *options, *brl_options = NULL;
 	int idx;
 
+	if (str[0] == 0)
+		return 1;
+
 	if (_braille_console_setup(&str, &brl_options))
 		return 1;
 
diff --git a/kernel/relay.c b/kernel/relay.c
index 61d37e6da22d..53c2a1a4b057 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -196,6 +196,7 @@ free_buf:
 static void relay_destroy_channel(struct kref *kref)
 {
 	struct rchan *chan = container_of(kref, struct rchan, kref);
+	free_percpu(chan->buf);
 	kfree(chan);
 }
 
@@ -580,6 +581,11 @@ struct rchan *relay_open(const char *base_filename,
 		return NULL;
 
 	chan->buf = alloc_percpu(struct rchan_buf *);
+	if (!chan->buf) {
+		kfree(chan);
+		return NULL;
+	}
+
 	chan->version = RELAYFS_CHANNEL_VERSION;
 	chan->n_subbufs = n_subbufs;
 	chan->subbuf_size = subbuf_size;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 97a27726ea21..c5599174e745 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3731,7 +3731,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	 */
 	if (dl_prio(prio)) {
 		if (!dl_prio(p->normal_prio) ||
-		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
+		    (pi_task && dl_prio(pi_task->prio) &&
+		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
 			queue_flag |= ENQUEUE_REPLENISH;
 		} else
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0b4e997fea1a..81096dd0ca0c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2643,7 +2643,7 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
 	/*
 	 * We don't care about NUMA placement if we don't have memory.
 	 */
-	if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
+	if ((curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work)
 		return;
 
 	/*
@@ -6871,7 +6871,15 @@ static int detach_tasks(struct lb_env *env)
 		if (!can_migrate_task(p, env))
 			goto next;
 
-		load = task_h_load(p);
+		/*
+		 * Depending of the number of CPUs and tasks and the
+		 * cgroup hierarchy, task_h_load() can return a null
+		 * value. Make sure that env->imbalance decreases
+		 * otherwise detach_tasks() will stop only after
+		 * detaching up to loop_max tasks.
+		 */
+		load = max_t(unsigned long, task_h_load(p), 1);
+
 
 		if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
 			goto next;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 867d173dab48..152ffe0c2433 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1117,7 +1117,7 @@ sd_init(struct sched_domain_topology_level *tl,
 		sd_flags = (*tl->sd_flags)();
 	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
 			"wrong sd_flags in topology description\n"))
-		sd_flags &= ~TOPOLOGY_SD_FLAGS;
+		sd_flags &= TOPOLOGY_SD_FLAGS;
 
 	*sd = (struct sched_domain){
 		.min_interval		= sd_weight,
diff --git a/kernel/sys.c b/kernel/sys.c
index ab96b9882347..2e4f017f7c5a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1217,11 +1217,13 @@ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name)
 
 SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name)
 {
-	struct oldold_utsname tmp = {};
+	struct oldold_utsname tmp;
 
 	if (!name)
 		return -EFAULT;
 
+	memset(&tmp, 0, sizeof(tmp));
+
 	down_read(&uts_sem);
 	memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN);
 	memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN);
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 0fef395662a6..83fb1ecfc33d 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -116,3 +116,4 @@ void task_work_run(void)
 		} while (work);
 	}
 }
+EXPORT_SYMBOL_GPL(task_work_run);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 1ce7c404d0b0..5b6f815a74ee 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -988,9 +988,8 @@ static int scale64_check_overflow(u64 mult, u64 div, u64 *base)
 	    ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem)))
 		return -EOVERFLOW;
 	tmp *= mult;
-	rem *= mult;
 
-	do_div(rem, div);
+	rem = div64_u64(rem * mult, div);
 	*base = tmp + rem;
 	return 0;
 }
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 9f8e8892e5b0..d4bc272e03ee 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -44,6 +44,7 @@
 #include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/random.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -502,8 +503,8 @@ static int calc_wheel_index(unsigned long expires, unsigned long clk)
 		 * Force expire obscene large timeouts to expire at the
 		 * capacity limit of the wheel.
 		 */
-		if (expires >= WHEEL_TIMEOUT_CUTOFF)
-			expires = WHEEL_TIMEOUT_MAX;
+		if (delta >= WHEEL_TIMEOUT_CUTOFF)
+			expires = clk + WHEEL_TIMEOUT_MAX;
 
 		idx = calc_index(expires, LVL_DEPTH - 1);
 	}
@@ -1595,6 +1596,13 @@ void update_process_times(int user_tick)
 	scheduler_tick();
 	if (IS_ENABLED(CONFIG_POSIX_TIMERS))
 		run_posix_cpu_timers(p);
+
+	/* The current CPU might make use of net randoms without receiving IRQs
+	 * to renew them often enough. Let's update the net_rand_state from a
+	 * non-constant value that's not affine to the number of calls to make
+	 * sure it's updated when there's some activity (we don't care in idle).
+	 */
+	this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick);
 }
 
 /**
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index a60c09e0bda8..987daf9cc6e5 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -15,6 +15,9 @@
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  *
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
 #include <linux/blktrace_api.h>
@@ -504,6 +507,16 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 */
 	strreplace(buts->name, '/', '_');
 
+	/*
+	 * bdev can be NULL, as with scsi-generic, this is a helpful as
+	 * we can be.
+	 */
+	if (q->blk_trace) {
+		pr_warn("Concurrent blktraces are not allowed on %s\n",
+			buts->name);
+		return -EBUSY;
+	}
+
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
 	if (!bt)
 		return -ENOMEM;
@@ -528,6 +541,18 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!dir)
 		goto err;
 
+	/*
+	 * As blktrace relies on debugfs for its interface the debugfs directory
+	 * is required, contrary to the usual mantra of not checking for debugfs
+	 * files or directories.
+	 */
+	if (IS_ERR_OR_NULL(dir)) {
+		pr_warn("debugfs_dir not present for %s so skipping\n",
+			buts->name);
+		ret = -ENOENT;
+		goto err;
+	}
+
 	bt->dev = dev;
 	atomic_set(&bt->dropped, 0);
 	INIT_LIST_HEAD(&bt->running_list);
@@ -1022,8 +1047,10 @@ static void blk_add_trace_split(void *ignore,
 
 		__blk_add_trace(bt, bio->bi_iter.bi_sector,
 				bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf,
-				BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu),
-				&rpdu, blk_trace_bio_get_cgid(q, bio));
+				BLK_TA_SPLIT,
+				blk_status_to_errno(bio->bi_status),
+				sizeof(rpdu), &rpdu,
+				blk_trace_bio_get_cgid(q, bio));
 	}
 	rcu_read_unlock();
 }
@@ -1060,7 +1087,8 @@ static void blk_add_trace_bio_remap(void *ignore,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status,
+			bio_op(bio), bio->bi_opf, BLK_TA_REMAP,
+			blk_status_to_errno(bio->bi_status),
 			sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
 	rcu_read_unlock();
 }
@@ -1282,21 +1310,10 @@ static inline __u16 t_error(const struct trace_entry *ent)
 
 static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg)
 {
-	const __u64 *val = pdu_start(ent, has_cg);
+	const __be64 *val = pdu_start(ent, has_cg);
 	return be64_to_cpu(*val);
 }
 
-static void get_pdu_remap(const struct trace_entry *ent,
-			  struct blk_io_trace_remap *r, bool has_cg)
-{
-	const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
-	__u64 sector_from = __r->sector_from;
-
-	r->device_from = be32_to_cpu(__r->device_from);
-	r->device_to   = be32_to_cpu(__r->device_to);
-	r->sector_from = be64_to_cpu(sector_from);
-}
-
 typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act,
 	bool has_cg);
 
@@ -1422,13 +1439,13 @@ static void blk_log_with_error(struct trace_seq *s,
 
 static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
 {
-	struct blk_io_trace_remap r = { .device_from = 0, };
+	const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
 
-	get_pdu_remap(ent, &r, has_cg);
 	trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
 			 t_sector(ent), t_sec(ent),
-			 MAJOR(r.device_from), MINOR(r.device_from),
-			 (unsigned long long)r.sector_from);
+			 MAJOR(be32_to_cpu(__r->device_from)),
+			 MINOR(be32_to_cpu(__r->device_from)),
+			 be64_to_cpu(__r->sector_from));
 }
 
 static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8a8d92a8045b..bb242da3724b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5721,8 +5721,11 @@ static int referenced_filters(struct dyn_ftrace *rec)
 	int cnt = 0;
 
 	for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
-		if (ops_references_rec(ops, rec))
-		    cnt++;
+		if (ops_references_rec(ops, rec)) {
+			cnt++;
+			if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+				rec->flags |= FTRACE_FL_REGS;
+		}
 	}
 
 	return cnt;
@@ -5871,8 +5874,8 @@ void ftrace_module_enable(struct module *mod)
 		if (ftrace_start_up)
 			cnt += referenced_filters(rec);
 
-		/* This clears FTRACE_FL_DISABLED */
-		rec->flags = cnt;
+		rec->flags &= ~FTRACE_FL_DISABLED;
+		rec->flags += cnt;
 
 		if (ftrace_start_up && cnt) {
 			int failed = __ftrace_replace_code(rec, 1);
@@ -6156,17 +6159,15 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 {
 	int bit;
 
-	if ((op->flags & FTRACE_OPS_FL_RCU) && !rcu_is_watching())
-		return;
-
 	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
 	if (bit < 0)
 		return;
 
 	preempt_disable_notrace();
 
-	if (!(op->flags & FTRACE_OPS_FL_PER_CPU) ||
-	    !ftrace_function_local_disabled(op)) {
+	if ((!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching()) &&
+	    (!(op->flags & FTRACE_OPS_FL_PER_CPU) ||
+	     !ftrace_function_local_disabled(op))) {
 		op->func(ip, parent_ip, op, regs);
 	}
 
@@ -6239,12 +6240,12 @@ void ftrace_pid_follow_fork(struct trace_array *tr, bool enable)
 	if (enable) {
 		register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						  tr);
-		register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		register_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						  tr);
 	} else {
 		unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						    tr);
-		unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		unregister_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						    tr);
 	}
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 95ede1f7ffdf..19526297a5b1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3035,6 +3035,9 @@ int trace_array_printk(struct trace_array *tr,
 	if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
+	if (!tr)
+		return -ENOENT;
+
 	va_start(ap, fmt);
 	ret = trace_array_vprintk(tr, ip, fmt, ap);
 	va_end(ap);
@@ -8343,7 +8346,7 @@ __init static int tracer_alloc_buffers(void)
 		goto out_free_buffer_mask;
 
 	/* Only allocate trace_printk buffers if a trace_printk exists */
-	if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt)
+	if (&__stop___trace_bprintk_fmt != &__start___trace_bprintk_fmt)
 		/* Must be called before global_trace.buffer is allocated */
 		trace_printk_init_buffers();
 
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index e3a658bac10f..ff91acff7294 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -179,7 +179,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
 
 	F_STRUCT(
 		__field(	int,		size	)
-		__dynamic_array(unsigned long,	caller	)
+		__array(	unsigned long,	caller,	FTRACE_STACK_ENTRIES	)
 	),
 
 	F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 421166a39253..d69c79ac9798 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -533,12 +533,12 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
 	if (enable) {
 		register_trace_prio_sched_process_fork(event_filter_pid_sched_process_fork,
 						       tr, INT_MIN);
-		register_trace_prio_sched_process_exit(event_filter_pid_sched_process_exit,
+		register_trace_prio_sched_process_free(event_filter_pid_sched_process_exit,
 						       tr, INT_MAX);
 	} else {
 		unregister_trace_sched_process_fork(event_filter_pid_sched_process_fork,
 						    tr);
-		unregister_trace_sched_process_exit(event_filter_pid_sched_process_exit,
+		unregister_trace_sched_process_free(event_filter_pid_sched_process_exit,
 						    tr);
 	}
 }
@@ -799,6 +799,8 @@ static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
 	char *event = NULL, *sub = NULL, *match;
 	int ret;
 
+	if (!tr)
+		return -ENOENT;
 	/*
 	 * The buf format can be <subsystem>:<event-name>
 	 *  *:<event-name> means any event by that name.
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 6fb5eb7b57dc..13f501337308 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -223,11 +223,17 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)
 
 static int trigger_process_regex(struct trace_event_file *file, char *buff)
 {
-	char *command, *next = buff;
+	char *command, *next;
 	struct event_command *p;
 	int ret = -EINVAL;
 
+	next = buff = skip_spaces(buff);
 	command = strsep(&next, ": \t");
+	if (next) {
+		next = skip_spaces(next);
+		if (!*next)
+			next = NULL;
+	}
 	command = (command[0] != '!') ? command : command + 1;
 
 	mutex_lock(&trigger_cmd_mutex);
@@ -630,8 +636,14 @@ event_trigger_callback(struct event_command *cmd_ops,
 	int ret;
 
 	/* separate the trigger from the filter (t:n [if filter]) */
-	if (param && isdigit(param[0]))
+	if (param && isdigit(param[0])) {
 		trigger = strsep(&param, " \t");
+		if (param) {
+			param = skip_spaces(param);
+			if (!*param)
+				param = NULL;
+		}
+	}
 
 	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
 
@@ -1342,6 +1354,11 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 	trigger = strsep(&param, " \t");
 	if (!trigger)
 		return -EINVAL;
+	if (param) {
+		param = skip_spaces(param);
+		if (!*param)
+			param = NULL;
+	}
 
 	system = strsep(&trigger, ":");
 	if (!trigger)
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index bff6c033d70e..64a98a5bb641 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -272,6 +272,7 @@ static bool disable_migrate;
 static void move_to_next_cpu(void)
 {
 	struct cpumask *current_mask = &save_cpumask;
+	struct trace_array *tr = hwlat_trace;
 	int next_cpu;
 
 	if (disable_migrate)
@@ -285,7 +286,7 @@ static void move_to_next_cpu(void)
 		goto disable;
 
 	get_online_cpus();
-	cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 	next_cpu = cpumask_next(smp_processor_id(), current_mask);
 	put_online_cpus();
 
@@ -359,7 +360,7 @@ static int start_kthread(struct trace_array *tr)
 	/* Just pick the first CPU on first iteration */
 	current_mask = &save_cpumask;
 	get_online_cpus();
-	cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 	put_online_cpus();
 	next_cpu = cpumask_first(current_mask);
 
diff --git a/kernel/umh.c b/kernel/umh.c
index a5daa8534d0e..9c41f05f969b 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -13,6 +13,7 @@
 #include <linux/cred.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
+#include <linux/fs_struct.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
 #include <linux/mount.h>
@@ -71,6 +72,14 @@ static int call_usermodehelper_exec_async(void *data)
 	spin_unlock_irq(&current->sighand->siglock);
 
 	/*
+	 * Initial kernel threads share ther FS with init, in order to
+	 * get the init root directory. But we've now created a new
+	 * thread that is going to execve a user process and has its own
+	 * 'struct fs_struct'. Reset umask to the default.
+	 */
+	current->fs->umask = 0022;
+
+	/*
 	 * Our parent (unbound workqueue) runs with elevated scheduling
 	 * priority. Avoid propagating that into the userspace child.
 	 */
diff --git a/kernel/uptime_limit.c b/kernel/uptime_limit.c
new file mode 100644
index 000000000000..b6a1a5e4f9d9
--- /dev/null
+++ b/kernel/uptime_limit.c
@@ -0,0 +1,166 @@
+/*
+ * uptime_limit.c
+ *
+ * This file contains the functions which can limit kernel uptime
+ *
+ * Copyright (C) 2011 Bruce Ashfield (bruce.ashfield@windriver.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ *
+ * This functionality is somewhat close to the softdog watchdog
+ * implementation, but it cannot be used directly for several reasons:
+ *
+ *   - The soft watchdog should be available while this functionality is active
+ *   - The duration range is different between this and the softdog. The
+ *     timeout available here is potentially quite a bit longer.
+ *   - At expiration, there are different expiration requirements and actions.
+ *   - This functionality is specific to a particular use case and should
+ *     not impact mainline functionality
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <linux/timer.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+
+#define UPTIME_LIMIT_IN_SECONDS (CONFIG_UPTIME_LIMIT_DURATION * 60)
+#define MIN(X, Y) ((X) <= (Y) ? (X) : (Y))
+#define TEN_MINUTES_IN_SECONDS 600
+
+enum uptime_expiration_type {
+	uptime_no_action,
+	uptime_reboot
+};
+
+static enum uptime_expiration_type uptime_expiration_action = uptime_no_action;
+static struct timer_list timelimit_timer;
+static struct task_struct *uptime_worker_task;
+
+static void timelimit_expire(unsigned long timeout_seconds)
+{
+	char msg[128];
+	int msglen = 127;
+
+	if (timeout_seconds) {
+		if (timeout_seconds >= 60)
+			snprintf(msg, msglen,
+				 "Uptime: kernel validity duration has %d %s remaining\n",
+				 (int) timeout_seconds / 60, "minute(s)");
+		else
+			snprintf(msg, msglen,
+				 "Uptime: kernel validity duration has %d %s remaining\n",
+				 (int) timeout_seconds, "seconds");
+
+		printk(KERN_CRIT "%s", msg);
+
+		timelimit_timer.expires = jiffies + timeout_seconds * HZ;
+		timelimit_timer.data = 0;
+		add_timer_on(&timelimit_timer, cpumask_first(cpu_online_mask));
+	} else {
+		printk(KERN_CRIT "Uptime: Kernel validity timeout has expired\n");
+#ifdef CONFIG_UPTIME_LIMIT_KERNEL_REBOOT
+		uptime_expiration_action = uptime_reboot;
+		wake_up_process(uptime_worker_task);
+	}
+#endif
+}
+
+/*
+ * This thread starts and then immediately goes to sleep. When it is woken
+ * up, it carries out the instructions left in uptime_expiration_action. If
+ * no action was specified it simply goes back to sleep.
+ */
+static int uptime_worker(void *unused)
+{
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	while (!kthread_should_stop()) {
+		schedule();
+
+		if (kthread_should_stop())
+			break;
+
+		if (uptime_expiration_action == uptime_reboot) {
+			printk(KERN_CRIT "Uptime: restarting machine\n");
+			kernel_restart(NULL);
+		}
+
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__set_current_state(TASK_RUNNING);
+
+	return 0;
+}
+
+static int timeout_enable(int cpu)
+{
+	int err = 0;
+	int warning_limit;
+
+	/*
+	 * Create an uptime worker thread. This thread is required since the
+	 * safe version of kernel restart cannot be called from a
+	 * non-interruptible context. Which means we cannot call it directly
+	 * from a timer callback.  So we arrange for the timer expiration to
+	 * wakeup a thread, which performs the action.
+	 */
+	uptime_worker_task = kthread_create(uptime_worker,
+					    (void *)(unsigned long)cpu,
+					    "uptime_worker/%d", cpu);
+	if (IS_ERR(uptime_worker_task)) {
+		printk(KERN_ERR "Uptime: task for cpu %i failed\n", cpu);
+		err = PTR_ERR(uptime_worker_task);
+		goto out;
+	}
+	/* bind to cpu0 to avoid migration and hot plug nastiness */
+	kthread_bind(uptime_worker_task, cpu);
+	wake_up_process(uptime_worker_task);
+
+	/* Create the timer that will wake the uptime thread at expiration */
+	init_timer(&timelimit_timer);
+	timelimit_timer.function = timelimit_expire;
+	/*
+	 * Fire two timers. One warning timeout and the final timer
+	 * which will carry out the expiration action. The warning timer will
+	 * expire at the minimum of half the original time or ten minutes.
+	 */
+	warning_limit = MIN(UPTIME_LIMIT_IN_SECONDS/2, TEN_MINUTES_IN_SECONDS);
+	timelimit_timer.expires = jiffies + warning_limit * HZ;
+	timelimit_timer.data = UPTIME_LIMIT_IN_SECONDS - warning_limit;
+
+	add_timer_on(&timelimit_timer, cpumask_first(cpu_online_mask));
+out:
+	return err;
+}
+
+static int __init timelimit_init(void)
+{
+	int err = 0;
+
+	printk(KERN_INFO "Uptime: system uptime restrictions enabled\n");
+
+	/*
+	 * Enable the timeout thread for cpu 0 only, assuming that the
+	 * uptime limit is non-zero, to protect against any cpu
+	 * migration issues.
+	 */
+	if (UPTIME_LIMIT_IN_SECONDS)
+		err = timeout_enable(0);
+
+	return err;
+}
+device_initcall(timelimit_init);
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index c7c96bc7654a..91c451e0f474 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -85,22 +85,22 @@ static struct { unsigned flag:8; char opt_char; } opt_array[] = {
 	{ _DPRINTK_FLAGS_NONE, '_' },
 };
 
+struct flagsbuf { char buf[ARRAY_SIZE(opt_array)+1]; };
+
 /* format a string into buf[] which describes the _ddebug's flags */
-static char *ddebug_describe_flags(struct _ddebug *dp, char *buf,
-				    size_t maxlen)
+static char *ddebug_describe_flags(unsigned int flags, struct flagsbuf *fb)
 {
-	char *p = buf;
+	char *p = fb->buf;
 	int i;
 
-	BUG_ON(maxlen < 6);
 	for (i = 0; i < ARRAY_SIZE(opt_array); ++i)
-		if (dp->flags & opt_array[i].flag)
+		if (flags & opt_array[i].flag)
 			*p++ = opt_array[i].opt_char;
-	if (p == buf)
+	if (p == fb->buf)
 		*p++ = '_';
 	*p = '\0';
 
-	return buf;
+	return fb->buf;
 }
 
 #define vpr_info(fmt, ...)					\
@@ -142,7 +142,7 @@ static int ddebug_change(const struct ddebug_query *query,
 	struct ddebug_table *dt;
 	unsigned int newflags;
 	unsigned int nfound = 0;
-	char flagbuf[10];
+	struct flagsbuf fbuf;
 
 	/* search for matching ddebugs */
 	mutex_lock(&ddebug_lock);
@@ -199,8 +199,7 @@ static int ddebug_change(const struct ddebug_query *query,
 			vpr_info("changed %s:%d [%s]%s =%s\n",
 				 trim_prefix(dp->filename), dp->lineno,
 				 dt->mod_name, dp->function,
-				 ddebug_describe_flags(dp, flagbuf,
-						       sizeof(flagbuf)));
+				 ddebug_describe_flags(dp->flags, &fbuf));
 		}
 	}
 	mutex_unlock(&ddebug_lock);
@@ -779,7 +778,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 {
 	struct ddebug_iter *iter = m->private;
 	struct _ddebug *dp = p;
-	char flagsbuf[10];
+	struct flagsbuf flags;
 
 	vpr_info("called m=%p p=%p\n", m, p);
 
@@ -792,7 +791,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 	seq_printf(m, "%s:%u [%s]%s =%s \"",
 		   trim_prefix(dp->filename), dp->lineno,
 		   iter->table->mod_name, dp->function,
-		   ddebug_describe_flags(dp, flagsbuf, sizeof(flagsbuf)));
+		   ddebug_describe_flags(dp->flags, &flags));
 	seq_escape(m, dp->format, "\t\r\n\"");
 	seq_puts(m, "\"\n");
 
diff --git a/lib/fonts/font_10x18.c b/lib/fonts/font_10x18.c
index 532f0ff89a96..0e2deac97da0 100644
--- a/lib/fonts/font_10x18.c
+++ b/lib/fonts/font_10x18.c
@@ -8,8 +8,8 @@
 
 #define FONTDATAMAX 9216
 
-static const unsigned char fontdata_10x18[FONTDATAMAX] = {
-
+static struct font_data fontdata_10x18 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, 0x00, /* 0000000000 */
 	0x00, 0x00, /* 0000000000 */
@@ -5129,8 +5129,7 @@ static const unsigned char fontdata_10x18[FONTDATAMAX] = {
 	0x00, 0x00, /* 0000000000 */
 	0x00, 0x00, /* 0000000000 */
 	0x00, 0x00, /* 0000000000 */
-
-};
+} };
 
 
 const struct font_desc font_10x18 = {
@@ -5138,7 +5137,7 @@ const struct font_desc font_10x18 = {
 	.name	= "10x18",
 	.width	= 10,
 	.height	= 18,
-	.data	= fontdata_10x18,
+	.data	= fontdata_10x18.data,
 #ifdef __sparc__
 	.pref	= 5,
 #else
diff --git a/lib/fonts/font_6x10.c b/lib/fonts/font_6x10.c
index 09b2cc03435b..87da8acd07db 100644
--- a/lib/fonts/font_6x10.c
+++ b/lib/fonts/font_6x10.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/font.h>
 
-static const unsigned char fontdata_6x10[] = {
+#define FONTDATAMAX 2560
 
+static struct font_data fontdata_6x10 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
@@ -3074,14 +3076,13 @@ static const unsigned char fontdata_6x10[] = {
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
-
-};
+} };
 
 const struct font_desc font_6x10 = {
 	.idx	= FONT6x10_IDX,
 	.name	= "6x10",
 	.width	= 6,
 	.height	= 10,
-	.data	= fontdata_6x10,
+	.data	= fontdata_6x10.data,
 	.pref	= 0,
 };
diff --git a/lib/fonts/font_6x11.c b/lib/fonts/font_6x11.c
index d7136c33f1f0..5e975dfa10a5 100644
--- a/lib/fonts/font_6x11.c
+++ b/lib/fonts/font_6x11.c
@@ -9,8 +9,8 @@
 
 #define FONTDATAMAX (11*256)
 
-static const unsigned char fontdata_6x11[FONTDATAMAX] = {
-
+static struct font_data fontdata_6x11 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
@@ -3338,8 +3338,7 @@ static const unsigned char fontdata_6x11[FONTDATAMAX] = {
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
-
-};
+} };
 
 
 const struct font_desc font_vga_6x11 = {
@@ -3347,7 +3346,7 @@ const struct font_desc font_vga_6x11 = {
 	.name	= "ProFont6x11",
 	.width	= 6,
 	.height	= 11,
-	.data	= fontdata_6x11,
+	.data	= fontdata_6x11.data,
 	/* Try avoiding this font if possible unless on MAC */
 	.pref	= -2000,
 };
diff --git a/lib/fonts/font_7x14.c b/lib/fonts/font_7x14.c
index 9ae5b62c8a0d..6d74aa602610 100644
--- a/lib/fonts/font_7x14.c
+++ b/lib/fonts/font_7x14.c
@@ -8,8 +8,8 @@
 
 #define FONTDATAMAX 3584
 
-static const unsigned char fontdata_7x14[FONTDATAMAX] = {
-
+static struct font_data fontdata_7x14 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 0000000 */
 	0x00, /* 0000000 */
@@ -4105,8 +4105,7 @@ static const unsigned char fontdata_7x14[FONTDATAMAX] = {
 	0x00, /* 0000000 */
 	0x00, /* 0000000 */
 	0x00, /* 0000000 */
-
-};
+} };
 
 
 const struct font_desc font_7x14 = {
@@ -4114,6 +4113,6 @@ const struct font_desc font_7x14 = {
 	.name	= "7x14",
 	.width	= 7,
 	.height	= 14,
-	.data	= fontdata_7x14,
+	.data	= fontdata_7x14.data,
 	.pref	= 0,
 };
diff --git a/lib/fonts/font_8x16.c b/lib/fonts/font_8x16.c
index 34292cdfaa23..b7ae913e5b79 100644
--- a/lib/fonts/font_8x16.c
+++ b/lib/fonts/font_8x16.c
@@ -10,8 +10,8 @@
 
 #define FONTDATAMAX 4096
 
-static const unsigned char fontdata_8x16[FONTDATAMAX] = {
-
+static struct font_data fontdata_8x16 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
@@ -4619,8 +4619,7 @@ static const unsigned char fontdata_8x16[FONTDATAMAX] = {
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
-
-};
+} };
 
 
 const struct font_desc font_vga_8x16 = {
@@ -4628,7 +4627,7 @@ const struct font_desc font_vga_8x16 = {
 	.name	= "VGA8x16",
 	.width	= 8,
 	.height	= 16,
-	.data	= fontdata_8x16,
+	.data	= fontdata_8x16.data,
 	.pref	= 0,
 };
 EXPORT_SYMBOL(font_vga_8x16);
diff --git a/lib/fonts/font_8x8.c b/lib/fonts/font_8x8.c
index 751becf3c521..51a736e167b5 100644
--- a/lib/fonts/font_8x8.c
+++ b/lib/fonts/font_8x8.c
@@ -9,8 +9,8 @@
 
 #define FONTDATAMAX 2048
 
-static const unsigned char fontdata_8x8[FONTDATAMAX] = {
-
+static struct font_data fontdata_8x8 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
@@ -2570,8 +2570,7 @@ static const unsigned char fontdata_8x8[FONTDATAMAX] = {
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
-
-};
+} };
 
 
 const struct font_desc font_vga_8x8 = {
@@ -2579,6 +2578,6 @@ const struct font_desc font_vga_8x8 = {
 	.name	= "VGA8x8",
 	.width	= 8,
 	.height	= 8,
-	.data	= fontdata_8x8,
+	.data	= fontdata_8x8.data,
 	.pref	= 0,
 };
diff --git a/lib/fonts/font_acorn_8x8.c b/lib/fonts/font_acorn_8x8.c
index 0ff0e85d4481..069b3e80c434 100644
--- a/lib/fonts/font_acorn_8x8.c
+++ b/lib/fonts/font_acorn_8x8.c
@@ -3,7 +3,10 @@
 
 #include <linux/font.h>
 
-static const unsigned char acorndata_8x8[] = {
+#define FONTDATAMAX 2048
+
+static struct font_data acorndata_8x8 = {
+{ 0, 0, FONTDATAMAX, 0 }, {
 /* 00 */  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* ^@ */
 /* 01 */  0x7e, 0x81, 0xa5, 0x81, 0xbd, 0x99, 0x81, 0x7e, /* ^A */
 /* 02 */  0x7e, 0xff, 0xbd, 0xff, 0xc3, 0xe7, 0xff, 0x7e, /* ^B */
@@ -260,14 +263,14 @@ static const unsigned char acorndata_8x8[] = {
 /* FD */  0x38, 0x04, 0x18, 0x20, 0x3c, 0x00, 0x00, 0x00,
 /* FE */  0x00, 0x00, 0x3c, 0x3c, 0x3c, 0x3c, 0x00, 0x00,
 /* FF */  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
-};
+} };
 
 const struct font_desc font_acorn_8x8 = {
 	.idx	= ACORN8x8_IDX,
 	.name	= "Acorn8x8",
 	.width	= 8,
 	.height	= 8,
-	.data	= acorndata_8x8,
+	.data	= acorndata_8x8.data,
 #ifdef CONFIG_ARCH_ACORN
 	.pref	= 20,
 #else
diff --git a/lib/fonts/font_mini_4x6.c b/lib/fonts/font_mini_4x6.c
index 838caa1cfef7..1449876c6a27 100644
--- a/lib/fonts/font_mini_4x6.c
+++ b/lib/fonts/font_mini_4x6.c
@@ -43,8 +43,8 @@ __END__;
 
 #define FONTDATAMAX 1536
 
-static const unsigned char fontdata_mini_4x6[FONTDATAMAX] = {
-
+static struct font_data fontdata_mini_4x6 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/*{*/
 	  	/*   Char 0: ' '  */
 	0xee,	/*=  [*** ]       */
@@ -2145,14 +2145,14 @@ static const unsigned char fontdata_mini_4x6[FONTDATAMAX] = {
 	0xee,	/*=   [*** ]        */
 	0x00,	/*=   [    ]        */
 	/*}*/
-};
+} };
 
 const struct font_desc font_mini_4x6 = {
 	.idx	= MINI4x6_IDX,
 	.name	= "MINI4x6",
 	.width	= 4,
 	.height	= 6,
-	.data	= fontdata_mini_4x6,
+	.data	= fontdata_mini_4x6.data,
 	.pref	= 3,
 };
 
diff --git a/lib/fonts/font_pearl_8x8.c b/lib/fonts/font_pearl_8x8.c
index b0514c0a7445..dc2cdfe218af 100644
--- a/lib/fonts/font_pearl_8x8.c
+++ b/lib/fonts/font_pearl_8x8.c
@@ -14,8 +14,8 @@
 
 #define FONTDATAMAX 2048
 
-static const unsigned char fontdata_pearl8x8[FONTDATAMAX] = {
-
+static struct font_data fontdata_pearl8x8 = {
+   { 0, 0, FONTDATAMAX, 0 }, {
    /* 0 0x00 '^@' */
    0x00, /* 00000000 */
    0x00, /* 00000000 */
@@ -2575,14 +2575,13 @@ static const unsigned char fontdata_pearl8x8[FONTDATAMAX] = {
    0x00, /* 00000000 */
    0x00, /* 00000000 */
    0x00, /* 00000000 */
-
-};
+} };
 
 const struct font_desc font_pearl_8x8 = {
 	.idx	= PEARL8x8_IDX,
 	.name	= "PEARL8x8",
 	.width	= 8,
 	.height	= 8,
-	.data	= fontdata_pearl8x8,
+	.data	= fontdata_pearl8x8.data,
 	.pref	= 2,
 };
diff --git a/lib/fonts/font_sun12x22.c b/lib/fonts/font_sun12x22.c
index 955d6eee3959..641a6b4dca42 100644
--- a/lib/fonts/font_sun12x22.c
+++ b/lib/fonts/font_sun12x22.c
@@ -3,8 +3,8 @@
 
 #define FONTDATAMAX 11264
 
-static const unsigned char fontdata_sun12x22[FONTDATAMAX] = {
-
+static struct font_data fontdata_sun12x22 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, 0x00, /* 000000000000 */
 	0x00, 0x00, /* 000000000000 */
@@ -6148,8 +6148,7 @@ static const unsigned char fontdata_sun12x22[FONTDATAMAX] = {
 	0x00, 0x00, /* 000000000000 */
 	0x00, 0x00, /* 000000000000 */
 	0x00, 0x00, /* 000000000000 */
-
-};
+} };
 
 
 const struct font_desc font_sun_12x22 = {
@@ -6157,7 +6156,7 @@ const struct font_desc font_sun_12x22 = {
 	.name	= "SUN12x22",
 	.width	= 12,
 	.height	= 22,
-	.data	= fontdata_sun12x22,
+	.data	= fontdata_sun12x22.data,
 #ifdef __sparc__
 	.pref	= 5,
 #else
diff --git a/lib/fonts/font_sun8x16.c b/lib/fonts/font_sun8x16.c
index 03d71e53954a..193fe6d988e0 100644
--- a/lib/fonts/font_sun8x16.c
+++ b/lib/fonts/font_sun8x16.c
@@ -3,7 +3,8 @@
 
 #define FONTDATAMAX 4096
 
-static const unsigned char fontdata_sun8x16[FONTDATAMAX] = {
+static struct font_data fontdata_sun8x16 = {
+{ 0, 0, FONTDATAMAX, 0 }, {
 /* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 /* */ 0x00,0x00,0x7e,0x81,0xa5,0x81,0x81,0xbd,0x99,0x81,0x81,0x7e,0x00,0x00,0x00,0x00,
 /* */ 0x00,0x00,0x7e,0xff,0xdb,0xff,0xff,0xc3,0xe7,0xff,0xff,0x7e,0x00,0x00,0x00,0x00,
@@ -260,14 +261,14 @@ static const unsigned char fontdata_sun8x16[FONTDATAMAX] = {
 /* */ 0x00,0x70,0xd8,0x30,0x60,0xc8,0xf8,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 /* */ 0x00,0x00,0x00,0x00,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x00,0x00,0x00,0x00,0x00,
 /* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-};
+} };
 
 const struct font_desc font_sun_8x16 = {
 	.idx	= SUN8x16_IDX,
 	.name	= "SUN8x16",
 	.width	= 8,
 	.height	= 16,
-	.data	= fontdata_sun8x16,
+	.data	= fontdata_sun8x16.data,
 #ifdef __sparc__
 	.pref	= 10,
 #else
diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h
index e01b705556aa..6c5229f98c9e 100644
--- a/lib/mpi/longlong.h
+++ b/lib/mpi/longlong.h
@@ -671,7 +671,7 @@ do {						\
 	**************  MIPS/64  **************
 	***************************************/
 #if (defined(__mips) && __mips >= 3) && W_TYPE_SIZE == 64
-#if defined(__mips_isa_rev) && __mips_isa_rev >= 6
+#if defined(__mips_isa_rev) && __mips_isa_rev >= 6 && defined(CONFIG_CC_IS_GCC)
 /*
  * GCC ends up emitting a __multi3 intrinsic call for MIPS64r6 with the plain C
  * code below, so we special case MIPS64r6 until the compiler can do better.
diff --git a/lib/random32.c b/lib/random32.c
index 0a90cb0e0fb6..eb54663e9e94 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -48,7 +48,7 @@ static inline void prandom_state_selftest(void)
 }
 #endif
 
-static DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;
+DEFINE_PER_CPU(struct rnd_state, net_rand_state)  __latent_entropy;
 
 /**
  *	prandom_u32_state - seeded pseudo-random number generator.
diff --git a/lib/string.c b/lib/string.c
index 33befc6ba3fa..db9abc18b216 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -236,6 +236,30 @@ ssize_t strscpy(char *dest, const char *src, size_t count)
 EXPORT_SYMBOL(strscpy);
 #endif
 
+/**
+ * stpcpy - copy a string from src to dest returning a pointer to the new end
+ *          of dest, including src's %NUL-terminator. May overrun dest.
+ * @dest: pointer to end of string being copied into. Must be large enough
+ *        to receive copy.
+ * @src: pointer to the beginning of string being copied from. Must not overlap
+ *       dest.
+ *
+ * stpcpy differs from strcpy in a key way: the return value is a pointer
+ * to the new %NUL-terminating character in @dest. (For strcpy, the return
+ * value is a pointer to the start of @dest). This interface is considered
+ * unsafe as it doesn't perform bounds checking of the inputs. As such it's
+ * not recommended for usage. Instead, its definition is provided in case
+ * the compiler lowers other libcalls to stpcpy.
+ */
+char *stpcpy(char *__restrict__ dest, const char *__restrict__ src);
+char *stpcpy(char *__restrict__ dest, const char *__restrict__ src)
+{
+	while ((*dest++ = *src++) != '\0')
+		/* nothing */;
+	return --dest;
+}
+EXPORT_SYMBOL(stpcpy);
+
 #ifndef __HAVE_ARCH_STRCAT
 /**
  * strcat - Append one %NUL-terminated string to another
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
index e304b54c9c7d..fc5b1e2d997d 100644
--- a/lib/strncpy_from_user.c
+++ b/lib/strncpy_from_user.c
@@ -29,13 +29,6 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src,
 	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
 	unsigned long res = 0;
 
-	/*
-	 * Truncate 'max' to the user-specified limit, so that
-	 * we only have one limit we need to check in the loop
-	 */
-	if (max > count)
-		max = count;
-
 	if (IS_UNALIGNED(src, dst))
 		goto byte_at_a_time;
 
@@ -113,12 +106,20 @@ long strncpy_from_user(char *dst, const char __user *src, long count)
 		unsigned long max = max_addr - src_addr;
 		long retval;
 
+		/*
+		 * Truncate 'max' to the user-specified limit, so that
+		 * we only have one limit we need to check in the loop
+		 */
+		if (max > count)
+			max = count;
+
 		kasan_check_write(dst, count);
 		check_object_size(dst, count, false);
-		user_access_begin();
-		retval = do_strncpy_from_user(dst, src, count, max);
-		user_access_end();
-		return retval;
+		if (user_access_begin(VERIFY_READ, src, max)) {
+			retval = do_strncpy_from_user(dst, src, count, max);
+			user_access_end();
+			return retval;
+		}
 	}
 	return -EFAULT;
 }
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index 184f80f7bacf..0bf7c06ebdad 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -32,13 +32,6 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count,
 	unsigned long c;
 
 	/*
-	 * Truncate 'max' to the user-specified limit, so that
-	 * we only have one limit we need to check in the loop
-	 */
-	if (max > count)
-		max = count;
-
-	/*
 	 * Do everything aligned. But that means that we
 	 * need to also expand the maximum..
 	 */
@@ -114,10 +107,18 @@ long strnlen_user(const char __user *str, long count)
 		unsigned long max = max_addr - src_addr;
 		long retval;
 
-		user_access_begin();
-		retval = do_strnlen_user(str, count, max);
-		user_access_end();
-		return retval;
+		/*
+		 * Truncate 'max' to the user-specified limit, so that
+		 * we only have one limit we need to check in the loop
+		 */
+		if (max > count)
+			max = count;
+
+		if (user_access_begin(VERIFY_READ, str, max)) {
+			retval = do_strnlen_user(str, count, max);
+			user_access_end();
+			return retval;
+		}
 	}
 	return 0;
 }
diff --git a/lib/test_kmod.c b/lib/test_kmod.c
index cf619795a182..c0ce0156d54b 100644
--- a/lib/test_kmod.c
+++ b/lib/test_kmod.c
@@ -747,7 +747,7 @@ static int trigger_config_run_type(struct kmod_test_device *test_dev,
 		break;
 	case TEST_KMOD_FS_TYPE:
 		kfree_const(config->test_fs);
-		config->test_driver = NULL;
+		config->test_fs = NULL;
 		copied = config_copy_test_fs(config, test_str,
 					     strlen(test_str));
 		break;
diff --git a/lib/zlib_inflate/inffast.c b/lib/zlib_inflate/inffast.c
index 2c13ecc5bb2c..ed1f3df27260 100644
--- a/lib/zlib_inflate/inffast.c
+++ b/lib/zlib_inflate/inffast.c
@@ -10,17 +10,6 @@
 
 #ifndef ASMINF
 
-/* Allow machine dependent optimization for post-increment or pre-increment.
-   Based on testing to date,
-   Pre-increment preferred for:
-   - PowerPC G3 (Adler)
-   - MIPS R5000 (Randers-Pehrson)
-   Post-increment preferred for:
-   - none
-   No measurable difference:
-   - Pentium III (Anderson)
-   - M68060 (Nikl)
- */
 union uu {
 	unsigned short us;
 	unsigned char b[2];
@@ -38,16 +27,6 @@ get_unaligned16(const unsigned short *p)
 	return mm.us;
 }
 
-#ifdef POSTINC
-#  define OFF 0
-#  define PUP(a) *(a)++
-#  define UP_UNALIGNED(a) get_unaligned16((a)++)
-#else
-#  define OFF 1
-#  define PUP(a) *++(a)
-#  define UP_UNALIGNED(a) get_unaligned16(++(a))
-#endif
-
 /*
    Decode literal, length, and distance codes and write out the resulting
    literal and match bytes until either not enough input or output is
@@ -115,9 +94,9 @@ void inflate_fast(z_streamp strm, unsigned start)
 
     /* copy state to local variables */
     state = (struct inflate_state *)strm->state;
-    in = strm->next_in - OFF;
+    in = strm->next_in;
     last = in + (strm->avail_in - 5);
-    out = strm->next_out - OFF;
+    out = strm->next_out;
     beg = out - (start - strm->avail_out);
     end = out + (strm->avail_out - 257);
 #ifdef INFLATE_STRICT
@@ -138,9 +117,9 @@ void inflate_fast(z_streamp strm, unsigned start)
        input data or output space */
     do {
         if (bits < 15) {
-            hold += (unsigned long)(PUP(in)) << bits;
+            hold += (unsigned long)(*in++) << bits;
             bits += 8;
-            hold += (unsigned long)(PUP(in)) << bits;
+            hold += (unsigned long)(*in++) << bits;
             bits += 8;
         }
         this = lcode[hold & lmask];
@@ -150,14 +129,14 @@ void inflate_fast(z_streamp strm, unsigned start)
         bits -= op;
         op = (unsigned)(this.op);
         if (op == 0) {                          /* literal */
-            PUP(out) = (unsigned char)(this.val);
+            *out++ = (unsigned char)(this.val);
         }
         else if (op & 16) {                     /* length base */
             len = (unsigned)(this.val);
             op &= 15;                           /* number of extra bits */
             if (op) {
                 if (bits < op) {
-                    hold += (unsigned long)(PUP(in)) << bits;
+                    hold += (unsigned long)(*in++) << bits;
                     bits += 8;
                 }
                 len += (unsigned)hold & ((1U << op) - 1);
@@ -165,9 +144,9 @@ void inflate_fast(z_streamp strm, unsigned start)
                 bits -= op;
             }
             if (bits < 15) {
-                hold += (unsigned long)(PUP(in)) << bits;
+                hold += (unsigned long)(*in++) << bits;
                 bits += 8;
-                hold += (unsigned long)(PUP(in)) << bits;
+                hold += (unsigned long)(*in++) << bits;
                 bits += 8;
             }
             this = dcode[hold & dmask];
@@ -180,10 +159,10 @@ void inflate_fast(z_streamp strm, unsigned start)
                 dist = (unsigned)(this.val);
                 op &= 15;                       /* number of extra bits */
                 if (bits < op) {
-                    hold += (unsigned long)(PUP(in)) << bits;
+                    hold += (unsigned long)(*in++) << bits;
                     bits += 8;
                     if (bits < op) {
-                        hold += (unsigned long)(PUP(in)) << bits;
+                        hold += (unsigned long)(*in++) << bits;
                         bits += 8;
                     }
                 }
@@ -205,13 +184,13 @@ void inflate_fast(z_streamp strm, unsigned start)
                         state->mode = BAD;
                         break;
                     }
-                    from = window - OFF;
+                    from = window;
                     if (write == 0) {           /* very common case */
                         from += wsize - op;
                         if (op < len) {         /* some from window */
                             len -= op;
                             do {
-                                PUP(out) = PUP(from);
+                                *out++ = *from++;
                             } while (--op);
                             from = out - dist;  /* rest from output */
                         }
@@ -222,14 +201,14 @@ void inflate_fast(z_streamp strm, unsigned start)
                         if (op < len) {         /* some from end of window */
                             len -= op;
                             do {
-                                PUP(out) = PUP(from);
+                                *out++ = *from++;
                             } while (--op);
-                            from = window - OFF;
+                            from = window;
                             if (write < len) {  /* some from start of window */
                                 op = write;
                                 len -= op;
                                 do {
-                                    PUP(out) = PUP(from);
+                                    *out++ = *from++;
                                 } while (--op);
                                 from = out - dist;      /* rest from output */
                             }
@@ -240,21 +219,21 @@ void inflate_fast(z_streamp strm, unsigned start)
                         if (op < len) {         /* some from window */
                             len -= op;
                             do {
-                                PUP(out) = PUP(from);
+                                *out++ = *from++;
                             } while (--op);
                             from = out - dist;  /* rest from output */
                         }
                     }
                     while (len > 2) {
-                        PUP(out) = PUP(from);
-                        PUP(out) = PUP(from);
-                        PUP(out) = PUP(from);
+                        *out++ = *from++;
+                        *out++ = *from++;
+                        *out++ = *from++;
                         len -= 3;
                     }
                     if (len) {
-                        PUP(out) = PUP(from);
+                        *out++ = *from++;
                         if (len > 1)
-                            PUP(out) = PUP(from);
+                            *out++ = *from++;
                     }
                 }
                 else {
@@ -264,29 +243,29 @@ void inflate_fast(z_streamp strm, unsigned start)
                     from = out - dist;          /* copy direct from output */
 		    /* minimum length is three */
 		    /* Align out addr */
-		    if (!((long)(out - 1 + OFF) & 1)) {
-			PUP(out) = PUP(from);
+		    if (!((long)(out - 1) & 1)) {
+			*out++ = *from++;
 			len--;
 		    }
-		    sout = (unsigned short *)(out - OFF);
+		    sout = (unsigned short *)(out);
 		    if (dist > 2) {
 			unsigned short *sfrom;
 
-			sfrom = (unsigned short *)(from - OFF);
+			sfrom = (unsigned short *)(from);
 			loops = len >> 1;
 			do
 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-			    PUP(sout) = PUP(sfrom);
+			    *sout++ = *sfrom++;
 #else
-			    PUP(sout) = UP_UNALIGNED(sfrom);
+			    *sout++ = get_unaligned16(sfrom++);
 #endif
 			while (--loops);
-			out = (unsigned char *)sout + OFF;
-			from = (unsigned char *)sfrom + OFF;
+			out = (unsigned char *)sout;
+			from = (unsigned char *)sfrom;
 		    } else { /* dist == 1 or dist == 2 */
 			unsigned short pat16;
 
-			pat16 = *(sout-1+OFF);
+			pat16 = *(sout-1);
 			if (dist == 1) {
 				union uu mm;
 				/* copy one char pattern to both bytes */
@@ -296,12 +275,12 @@ void inflate_fast(z_streamp strm, unsigned start)
 			}
 			loops = len >> 1;
 			do
-			    PUP(sout) = pat16;
+			    *sout++ = pat16;
 			while (--loops);
-			out = (unsigned char *)sout + OFF;
+			out = (unsigned char *)sout;
 		    }
 		    if (len & 1)
-			PUP(out) = PUP(from);
+			*out++ = *from++;
                 }
             }
             else if ((op & 64) == 0) {          /* 2nd level distance code */
@@ -336,8 +315,8 @@ void inflate_fast(z_streamp strm, unsigned start)
     hold &= (1U << bits) - 1;
 
     /* update state and return */
-    strm->next_in = in + OFF;
-    strm->next_out = out + OFF;
+    strm->next_in = in;
+    strm->next_out = out;
     strm->avail_in = (unsigned)(in < last ? 5 + (last - in) : 5 - (in - last));
     strm->avail_out = (unsigned)(out < end ?
                                  257 + (end - out) : 257 - (out - end));
diff --git a/mm/Makefile b/mm/Makefile
index e7ebd176fb93..d6bcfb01b528 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -39,7 +39,7 @@ obj-y			:= filemap.o mempool.o oom_kill.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
 			   compaction.o vmacache.o swap_slots.o \
 			   interval_tree.o list_lru.o workingset.o \
-			   debug.o $(mmu-y)
+			   prfile.o debug.o $(mmu-y)
 
 obj-y += init-mm.o
 
diff --git a/mm/filemap.c b/mm/filemap.c
index a30dbf93de99..56fbacfb34b8 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2612,7 +2612,7 @@ int filemap_page_mkwrite(struct vm_fault *vmf)
 	int ret = VM_FAULT_LOCKED;
 
 	sb_start_pagefault(inode->i_sb);
-	file_update_time(vmf->vma->vm_file);
+	vma_file_update_time(vmf->vma);
 	lock_page(page);
 	if (page->mapping != inode->i_mapping) {
 		unlock_page(page);
@@ -2774,6 +2774,14 @@ filler:
 		unlock_page(page);
 		goto out;
 	}
+
+	/*
+	 * A previous I/O error may have been due to temporary
+	 * failures.
+	 * Clear page error before actual read, PG_error will be
+	 * set again if read page fails.
+	 */
+	ClearPageError(page);
 	goto filler;
 
 out:
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 283963032eff..51068ef1dff5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2078,7 +2078,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		put_page(page);
 		add_mm_counter(mm, MM_FILEPAGES, -HPAGE_PMD_NR);
 		return;
-	} else if (is_huge_zero_pmd(*pmd)) {
+	} else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
 		return __split_huge_zero_page_pmd(vma, haddr, pmd);
 	}
 
@@ -2131,27 +2131,33 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		pte = pte_offset_map(&_pmd, addr);
 		BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, addr, pte, entry);
-		atomic_inc(&page[i]._mapcount);
-		pte_unmap(pte);
-	}
-
-	/*
-	 * Set PG_double_map before dropping compound_mapcount to avoid
-	 * false-negative page_mapped().
-	 */
-	if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) {
-		for (i = 0; i < HPAGE_PMD_NR; i++)
+		if (!pmd_migration)
 			atomic_inc(&page[i]._mapcount);
+		pte_unmap(pte);
 	}
 
-	if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
-		/* Last compound_mapcount is gone. */
-		__dec_node_page_state(page, NR_ANON_THPS);
-		if (TestClearPageDoubleMap(page)) {
-			/* No need in mapcount reference anymore */
+	if (!pmd_migration) {
+		/*
+		 * Set PG_double_map before dropping compound_mapcount to avoid
+		 * false-negative page_mapped().
+		 */
+		if (compound_mapcount(page) > 1 &&
+		    !TestSetPageDoubleMap(page)) {
 			for (i = 0; i < HPAGE_PMD_NR; i++)
-				atomic_dec(&page[i]._mapcount);
+				atomic_inc(&page[i]._mapcount);
+		}
+
+		lock_page_memcg(page);
+		if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
+			/* Last compound_mapcount is gone. */
+			__dec_lruvec_page_state(page, NR_ANON_THPS);
+			if (TestClearPageDoubleMap(page)) {
+				/* No need in mapcount reference anymore */
+				for (i = 0; i < HPAGE_PMD_NR; i++)
+					atomic_dec(&page[i]._mapcount);
+			}
 		}
+		unlock_page_memcg(page);
 	}
 
 	smp_wmb(); /* make pte visible before pmd */
@@ -2193,6 +2199,8 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	spinlock_t *ptl;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long haddr = address & HPAGE_PMD_MASK;
+	bool was_locked = false;
+	pmd_t _pmd;
 
 	mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE);
 	ptl = pmd_lock(mm, pmd);
@@ -2202,11 +2210,32 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	 * pmd against. Otherwise we can end up replacing wrong page.
 	 */
 	VM_BUG_ON(freeze && !page);
-	if (page && page != pmd_page(*pmd))
-	        goto out;
+	if (page) {
+		VM_WARN_ON_ONCE(!PageLocked(page));
+		was_locked = true;
+		if (page != pmd_page(*pmd))
+			goto out;
+	}
 
+repeat:
 	if (pmd_trans_huge(*pmd)) {
-		page = pmd_page(*pmd);
+		if (!page) {
+			page = pmd_page(*pmd);
+			if (unlikely(!trylock_page(page))) {
+				get_page(page);
+				_pmd = *pmd;
+				spin_unlock(ptl);
+				lock_page(page);
+				spin_lock(ptl);
+				if (unlikely(!pmd_same(*pmd, _pmd))) {
+					unlock_page(page);
+					put_page(page);
+					page = NULL;
+					goto repeat;
+				}
+				put_page(page);
+			}
+		}
 		if (PageMlocked(page))
 			clear_page_mlock(page);
 	} else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)))
@@ -2214,6 +2243,8 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	__split_huge_pmd_locked(vma, pmd, haddr, freeze);
 out:
 	spin_unlock(ptl);
+	if (!was_locked && page)
+		unlock_page(page);
 	mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE);
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d6464045d3b9..3d919635004e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2911,6 +2911,22 @@ static unsigned int cpuset_mems_nr(unsigned int *array)
 }
 
 #ifdef CONFIG_SYSCTL
+static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write,
+					  void *buffer, size_t *length,
+					  loff_t *ppos, unsigned long *out)
+{
+	struct ctl_table dup_table;
+
+	/*
+	 * In order to avoid races with __do_proc_doulongvec_minmax(), we
+	 * can duplicate the @table and alter the duplicate of it.
+	 */
+	dup_table = *table;
+	dup_table.data = out;
+
+	return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
+}
+
 static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 			 struct ctl_table *table, int write,
 			 void __user *buffer, size_t *length, loff_t *ppos)
@@ -2922,9 +2938,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	if (!hugepages_supported())
 		return -EOPNOTSUPP;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -2968,9 +2983,8 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	if (write && hstate_is_gigantic(h))
 		return -EINVAL;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -4575,25 +4589,21 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end)
 {
-	unsigned long check_addr = *start;
+	unsigned long a_start, a_end;
 
 	if (!(vma->vm_flags & VM_MAYSHARE))
 		return;
 
-	for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) {
-		unsigned long a_start = check_addr & PUD_MASK;
-		unsigned long a_end = a_start + PUD_SIZE;
+	/* Extend the range to be PUD aligned for a worst case scenario */
+	a_start = ALIGN_DOWN(*start, PUD_SIZE);
+	a_end = ALIGN(*end, PUD_SIZE);
 
-		/*
-		 * If sharing is possible, adjust start/end if necessary.
-		 */
-		if (range_in_vma(vma, a_start, a_end)) {
-			if (a_start < *start)
-				*start = a_start;
-			if (a_end > *end)
-				*end = a_end;
-		}
-	}
+	/*
+	 * Intersect the range with the vma range, since pmd sharing won't be
+	 * across vma after all
+	 */
+	*start = max(vma->vm_start, a_start);
+	*end = min(vma->vm_end, a_end);
 }
 
 /*
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index acf66c5dc9bd..349b4782d9f4 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -53,6 +53,9 @@ enum scan_result {
 #define CREATE_TRACE_POINTS
 #include <trace/events/huge_memory.h>
 
+static struct task_struct *khugepaged_thread __read_mostly;
+static DEFINE_MUTEX(khugepaged_mutex);
+
 /* default scan 8*512 pte (or vmas) every 30 second */
 static unsigned int khugepaged_pages_to_scan __read_mostly;
 static unsigned int khugepaged_pages_collapsed;
@@ -394,7 +397,7 @@ static void insert_to_mm_slots_hash(struct mm_struct *mm,
 
 static inline int khugepaged_test_exit(struct mm_struct *mm)
 {
-	return atomic_read(&mm->mm_users) == 0;
+	return atomic_read(&mm->mm_users) == 0 || !mmget_still_valid(mm);
 }
 
 int __khugepaged_enter(struct mm_struct *mm)
@@ -407,7 +410,7 @@ int __khugepaged_enter(struct mm_struct *mm)
 		return -ENOMEM;
 
 	/* __khugepaged_exit() must not run from under us */
-	VM_BUG_ON_MM(khugepaged_test_exit(mm), mm);
+	VM_BUG_ON_MM(atomic_read(&mm->mm_users) == 0, mm);
 	if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) {
 		free_mm_slot(mm_slot);
 		return 0;
@@ -801,6 +804,18 @@ static struct page *khugepaged_alloc_hugepage(bool *wait)
 
 static bool khugepaged_prealloc_page(struct page **hpage, bool *wait)
 {
+	/*
+	 * If the hpage allocated earlier was briefly exposed in page cache
+	 * before collapse_file() failed, it is possible that racing lookups
+	 * have not yet completed, and would then be unpleasantly surprised by
+	 * finding the hpage reused for the same mapping at a different offset.
+	 * Just release the previous allocation if there is any danger of that.
+	 */
+	if (*hpage && page_count(*hpage) > 1) {
+		put_page(*hpage);
+		*hpage = NULL;
+	}
+
 	if (!*hpage)
 		*hpage = khugepaged_alloc_hugepage(wait);
 
@@ -1006,9 +1021,6 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * handled by the anon_vma lock + PG_lock.
 	 */
 	down_write(&mm->mmap_sem);
-	result = SCAN_ANY_PROCESS;
-	if (!mmget_still_valid(mm))
-		goto out;
 	result = hugepage_vma_revalidate(mm, address, &vma);
 	if (result)
 		goto out;
@@ -1252,6 +1264,7 @@ static void collect_mm_slot(struct mm_slot *mm_slot)
 static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 {
 	struct vm_area_struct *vma;
+	struct mm_struct *mm;
 	unsigned long addr;
 	pmd_t *pmd, _pmd;
 
@@ -1265,7 +1278,8 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 			continue;
 		if (vma->vm_end < addr + HPAGE_PMD_SIZE)
 			continue;
-		pmd = mm_find_pmd(vma->vm_mm, addr);
+		mm = vma->vm_mm;
+		pmd = mm_find_pmd(mm, addr);
 		if (!pmd)
 			continue;
 		/*
@@ -1274,14 +1288,16 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		 * re-fault. Not ideal, but it's more important to not disturb
 		 * the system too much.
 		 */
-		if (down_write_trylock(&vma->vm_mm->mmap_sem)) {
-			spinlock_t *ptl = pmd_lock(vma->vm_mm, pmd);
-			/* assume page table is clear */
-			_pmd = pmdp_collapse_flush(vma, addr, pmd);
-			spin_unlock(ptl);
-			up_write(&vma->vm_mm->mmap_sem);
-			atomic_long_dec(&vma->vm_mm->nr_ptes);
-			pte_free(vma->vm_mm, pmd_pgtable(_pmd));
+		if (down_write_trylock(&mm->mmap_sem)) {
+			if (!khugepaged_test_exit(mm)) {
+				spinlock_t *ptl = pmd_lock(mm, pmd);
+				/* assume page table is clear */
+				_pmd = pmdp_collapse_flush(vma, addr, pmd);
+				spin_unlock(ptl);
+				atomic_long_dec(&mm->nr_ptes);
+				pte_free(mm, pmd_pgtable(_pmd));
+			}
+			up_write(&mm->mmap_sem);
 		}
 	}
 	i_mmap_unlock_write(mapping);
@@ -1936,8 +1952,6 @@ static void set_recommended_min_free_kbytes(void)
 
 int start_stop_khugepaged(void)
 {
-	static struct task_struct *khugepaged_thread __read_mostly;
-	static DEFINE_MUTEX(khugepaged_mutex);
 	int err = 0;
 
 	mutex_lock(&khugepaged_mutex);
@@ -1964,3 +1978,11 @@ fail:
 	mutex_unlock(&khugepaged_mutex);
 	return err;
 }
+
+void khugepaged_min_free_kbytes_update(void)
+{
+	mutex_lock(&khugepaged_mutex);
+	if (khugepaged_enabled() && khugepaged_thread)
+		set_recommended_min_free_kbytes();
+	mutex_unlock(&khugepaged_mutex);
+}
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index d779181bed4d..706f705c2e0a 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -2030,7 +2030,7 @@ void __init kmemleak_init(void)
 	create_object((unsigned long)__bss_start, __bss_stop - __bss_start,
 		      KMEMLEAK_GREY, GFP_ATOMIC);
 	/* only register .data..ro_after_init if not within .data */
-	if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata)
+	if (&__start_ro_after_init < &_sdata || &__end_ro_after_init > &_edata)
 		create_object((unsigned long)__start_ro_after_init,
 			      __end_ro_after_init - __start_ro_after_init,
 			      KMEMLEAK_GREY, GFP_ATOMIC);
diff --git a/mm/maccess.c b/mm/maccess.c
index 78f9274dd49d..03ea550f5a74 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -5,8 +5,32 @@
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 
+static __always_inline long
+probe_read_common(void *dst, const void __user *src, size_t size)
+{
+	long ret;
+
+	pagefault_disable();
+	ret = __copy_from_user_inatomic(dst, src, size);
+	pagefault_enable();
+
+	return ret ? -EFAULT : 0;
+}
+
+static __always_inline long
+probe_write_common(void __user *dst, const void *src, size_t size)
+{
+	long ret;
+
+	pagefault_disable();
+	ret = __copy_to_user_inatomic(dst, src, size);
+	pagefault_enable();
+
+	return ret ? -EFAULT : 0;
+}
+
 /**
- * probe_kernel_read(): safely attempt to read from a location
+ * probe_kernel_read(): safely attempt to read from a kernel-space location
  * @dst: pointer to the buffer that shall take the data
  * @src: address to read from
  * @size: size of the data chunk
@@ -29,17 +53,41 @@ long __probe_kernel_read(void *dst, const void *src, size_t size)
 	mm_segment_t old_fs = get_fs();
 
 	set_fs(KERNEL_DS);
-	pagefault_disable();
-	ret = __copy_from_user_inatomic(dst,
-			(__force const void __user *)src, size);
-	pagefault_enable();
+	ret = probe_read_common(dst, (__force const void __user *)src, size);
 	set_fs(old_fs);
 
-	return ret ? -EFAULT : 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(probe_kernel_read);
 
 /**
+ * probe_user_read(): safely attempt to read from a user-space location
+ * @dst: pointer to the buffer that shall take the data
+ * @src: address to read from. This must be a user address.
+ * @size: size of the data chunk
+ *
+ * Safely read from user address @src to the buffer at @dst. If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+
+long __weak probe_user_read(void *dst, const void __user *src, size_t size)
+    __attribute__((alias("__probe_user_read")));
+
+long __probe_user_read(void *dst, const void __user *src, size_t size)
+{
+	long ret = -EFAULT;
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(USER_DS);
+	if (access_ok(VERIFY_READ, src, size))
+		ret = probe_read_common(dst, src, size);
+	set_fs(old_fs);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(probe_user_read);
+
+/**
  * probe_kernel_write(): safely attempt to write to a location
  * @dst: address to write to
  * @src: pointer to the data that shall be written
@@ -48,6 +96,7 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
+
 long __weak probe_kernel_write(void *dst, const void *src, size_t size)
     __attribute__((alias("__probe_kernel_write")));
 
@@ -57,16 +106,41 @@ long __probe_kernel_write(void *dst, const void *src, size_t size)
 	mm_segment_t old_fs = get_fs();
 
 	set_fs(KERNEL_DS);
-	pagefault_disable();
-	ret = __copy_to_user_inatomic((__force void __user *)dst, src, size);
-	pagefault_enable();
+	ret = probe_write_common((__force void __user *)dst, src, size);
 	set_fs(old_fs);
 
-	return ret ? -EFAULT : 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(probe_kernel_write);
 
 /**
+ * probe_user_write(): safely attempt to write to a user-space location
+ * @dst: address to write to
+ * @src: pointer to the data that shall be written
+ * @size: size of the data chunk
+ *
+ * Safely write to address @dst from the buffer at @src.  If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+
+long __weak probe_user_write(void __user *dst, const void *src, size_t size)
+    __attribute__((alias("__probe_user_write")));
+
+long __probe_user_write(void __user *dst, const void *src, size_t size)
+{
+	long ret = -EFAULT;
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(USER_DS);
+	if (access_ok(VERIFY_WRITE, dst, size))
+		ret = probe_write_common(dst, src, size);
+	set_fs(old_fs);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(probe_user_write);
+
+/**
  * strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address.
  * @dst:   Destination address, in kernel space.  This buffer must be at
  *         least @count bytes long.
@@ -105,3 +179,76 @@ long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
 
 	return ret ? -EFAULT : src - unsafe_addr;
 }
+
+/**
+ * strncpy_from_unsafe_user: - Copy a NUL terminated string from unsafe user
+ *				address.
+ * @dst:   Destination address, in kernel space.  This buffer must be at
+ *         least @count bytes long.
+ * @unsafe_addr: Unsafe user address.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Copies a NUL-terminated string from unsafe user address to kernel buffer.
+ *
+ * On success, returns the length of the string INCLUDING the trailing NUL.
+ *
+ * If access fails, returns -EFAULT (some data may have been copied
+ * and the trailing NUL added).
+ *
+ * If @count is smaller than the length of the string, copies @count-1 bytes,
+ * sets the last byte of @dst buffer to NUL and returns @count.
+ */
+long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
+			      long count)
+{
+	mm_segment_t old_fs = get_fs();
+	long ret;
+
+	if (unlikely(count <= 0))
+		return 0;
+
+	set_fs(USER_DS);
+	pagefault_disable();
+	ret = strncpy_from_user(dst, unsafe_addr, count);
+	pagefault_enable();
+	set_fs(old_fs);
+
+	if (ret >= count) {
+		ret = count;
+		dst[ret - 1] = '\0';
+	} else if (ret > 0) {
+		ret++;
+	}
+
+	return ret;
+}
+
+/**
+ * strnlen_unsafe_user: - Get the size of a user string INCLUDING final NUL.
+ * @unsafe_addr: The string to measure.
+ * @count: Maximum count (including NUL)
+ *
+ * Get the size of a NUL-terminated string in user space without pagefault.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ *
+ * If the string is too long, returns a number larger than @count. User
+ * has to check the return value against "> count".
+ * On exception (or invalid count), returns 0.
+ *
+ * Unlike strnlen_user, this can be used from IRQ handler etc. because
+ * it disables pagefaults.
+ */
+long strnlen_unsafe_user(const void __user *unsafe_addr, long count)
+{
+	mm_segment_t old_fs = get_fs();
+	int ret;
+
+	set_fs(USER_DS);
+	pagefault_disable();
+	ret = strnlen_user(unsafe_addr, count);
+	pagefault_enable();
+	set_fs(old_fs);
+
+	return ret;
+}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d8df500e0eea..5cbcd4b81bf8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4883,7 +4883,6 @@ static void __mem_cgroup_clear_mc(void)
 		if (!mem_cgroup_is_root(mc.to))
 			page_counter_uncharge(&mc.to->memory, mc.moved_swap);
 
-		mem_cgroup_id_get_many(mc.to, mc.moved_swap);
 		css_put_many(&mc.to->css, mc.moved_swap);
 
 		mc.moved_swap = 0;
@@ -5074,7 +5073,8 @@ put:			/* get_mctgt_type() gets the page */
 			ent = target.ent;
 			if (!mem_cgroup_move_swap_account(ent, mc.from, mc.to)) {
 				mc.precharge--;
-				/* we fixup refcnts and charges later. */
+				mem_cgroup_id_get_many(mc.to, 1);
+				/* we fixup other refcnts and charges later. */
 				mc.moved_swap++;
 			}
 			break;
diff --git a/mm/memory.c b/mm/memory.c
index e9bce27bc18c..caefa5526b20 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -117,6 +117,18 @@ int randomize_va_space __read_mostly =
 					2;
 #endif
 
+#ifndef arch_faults_on_old_pte
+static inline bool arch_faults_on_old_pte(void)
+{
+	/*
+	 * Those arches which don't have hw access flag feature need to
+	 * implement their own helper. By default, "true" means pagefault
+	 * will be hit on old pte.
+	 */
+	return true;
+}
+#endif
+
 static int __init disable_randmaps(char *s)
 {
 	randomize_va_space = 0;
@@ -2324,32 +2336,101 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
 	return same;
 }
 
-static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
+static inline bool cow_user_page(struct page *dst, struct page *src,
+				 struct vm_fault *vmf)
 {
+	bool ret;
+	void *kaddr;
+	void __user *uaddr;
+	bool locked = false;
+	struct vm_area_struct *vma = vmf->vma;
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long addr = vmf->address;
+
 	debug_dma_assert_idle(src);
 
+	if (likely(src)) {
+		copy_user_highpage(dst, src, addr, vma);
+		return true;
+	}
+
 	/*
 	 * If the source page was a PFN mapping, we don't have
 	 * a "struct page" for it. We do a best-effort copy by
 	 * just copying from the original user address. If that
 	 * fails, we just zero-fill it. Live with it.
 	 */
-	if (unlikely(!src)) {
-		void *kaddr = kmap_atomic(dst);
-		void __user *uaddr = (void __user *)(va & PAGE_MASK);
+	kaddr = kmap_atomic(dst);
+	uaddr = (void __user *)(addr & PAGE_MASK);
+
+	/*
+	 * On architectures with software "accessed" bits, we would
+	 * take a double page fault, so mark it accessed here.
+	 */
+	if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) {
+		pte_t entry;
+
+		vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+		locked = true;
+		if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
+			/*
+			 * Other thread has already handled the fault
+			 * and we don't need to do anything. If it's
+			 * not the case, the fault will be triggered
+			 * again on the same address.
+			 */
+			ret = false;
+			goto pte_unlock;
+		}
+
+		entry = pte_mkyoung(vmf->orig_pte);
+		if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0))
+			update_mmu_cache(vma, addr, vmf->pte);
+	}
+
+	/*
+	 * This really shouldn't fail, because the page is there
+	 * in the page tables. But it might just be unreadable,
+	 * in which case we just give up and fill the result with
+	 * zeroes.
+	 */
+	if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
+		if (locked)
+			goto warn;
+
+		/* Re-validate under PTL if the page is still mapped */
+		vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+		locked = true;
+		if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
+			/* The PTE changed under us. Retry page fault. */
+			ret = false;
+			goto pte_unlock;
+		}
 
 		/*
-		 * This really shouldn't fail, because the page is there
-		 * in the page tables. But it might just be unreadable,
-		 * in which case we just give up and fill the result with
-		 * zeroes.
+		 * The same page can be mapped back since last copy attampt.
+		 * Try to copy again under PTL.
 		 */
-		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
+		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
+			/*
+			 * Give a warn in case there can be some obscure
+			 * use-case
+			 */
+warn:
+			WARN_ON_ONCE(1);
 			clear_page(kaddr);
-		kunmap_atomic(kaddr);
-		flush_dcache_page(dst);
-	} else
-		copy_user_highpage(dst, src, va, vma);
+		}
+	}
+
+	ret = true;
+
+pte_unlock:
+	if (locked)
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+	kunmap_atomic(kaddr);
+	flush_dcache_page(dst);
+
+	return ret;
 }
 
 static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
@@ -2503,7 +2584,19 @@ static int wp_page_copy(struct vm_fault *vmf)
 				vmf->address);
 		if (!new_page)
 			goto oom;
-		cow_user_page(new_page, old_page, vmf->address, vma);
+
+		if (!cow_user_page(new_page, old_page, vmf)) {
+			/*
+			 * COW failed, if the fault was solved by other,
+			 * it's fine. If not, userspace would re-fault on
+			 * the same address and we will handle the fault
+			 * from the second attempt.
+			 */
+			put_page(new_page);
+			if (old_page)
+				put_page(old_page);
+			return 0;
+		}
 	}
 
 	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false))
diff --git a/mm/mmap.c b/mm/mmap.c
index 8c6ed06983f9..8a8961552d3f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -166,7 +166,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	if (vma->vm_ops && vma->vm_ops->close)
 		vma->vm_ops->close(vma);
 	if (vma->vm_file)
-		fput(vma->vm_file);
+		vma_fput(vma);
 	mpol_put(vma_policy(vma));
 	kmem_cache_free(vm_area_cachep, vma);
 	return next;
@@ -891,7 +891,7 @@ again:
 	if (remove_next) {
 		if (file) {
 			uprobe_munmap(next, next->vm_start, next->vm_end);
-			fput(file);
+			vma_fput(vma);
 		}
 		if (next->anon_vma)
 			anon_vma_merge(vma, next);
@@ -1773,8 +1773,8 @@ out:
 	return addr;
 
 unmap_and_free_vma:
+	vma_fput(vma);
 	vma->vm_file = NULL;
-	fput(file);
 
 	/* Undo any partial mapping done by a device driver. */
 	unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
@@ -2034,6 +2034,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.low_limit = mm->mmap_base;
 	info.high_limit = TASK_SIZE;
 	info.align_mask = 0;
+	info.align_offset = 0;
 	return vm_unmapped_area(&info);
 }
 #endif
@@ -2075,6 +2076,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
 	info.high_limit = mm->mmap_base;
 	info.align_mask = 0;
+	info.align_offset = 0;
 	addr = vm_unmapped_area(&info);
 
 	/*
@@ -2601,7 +2603,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_free_mpol;
 
 	if (new->vm_file)
-		get_file(new->vm_file);
+		vma_get_file(new);
 
 	if (new->vm_ops && new->vm_ops->open)
 		new->vm_ops->open(new);
@@ -2620,7 +2622,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (new->vm_ops && new->vm_ops->close)
 		new->vm_ops->close(new);
 	if (new->vm_file)
-		fput(new->vm_file);
+		vma_fput(new);
 	unlink_anon_vmas(new);
  out_free_mpol:
 	mpol_put(vma_policy(new));
@@ -2782,7 +2784,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	struct vm_area_struct *vma;
 	unsigned long populate = 0;
 	unsigned long ret = -EINVAL;
-	struct file *file;
+	struct file *file, *prfile;
 
 	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.txt.\n",
 		     current->comm, current->pid);
@@ -2857,10 +2859,27 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 		}
 	}
 
-	file = get_file(vma->vm_file);
+	vma_get_file(vma);
+	file = vma->vm_file;
+	prfile = vma->vm_prfile;
 	ret = do_mmap_pgoff(vma->vm_file, start, size,
 			prot, flags, pgoff, &populate, NULL);
+	if (!IS_ERR_VALUE(ret) && file && prfile) {
+		struct vm_area_struct *new_vma;
+
+		new_vma = find_vma(mm, ret);
+		if (!new_vma->vm_prfile)
+			new_vma->vm_prfile = prfile;
+		if (new_vma != vma)
+			get_file(prfile);
+	}
+	/*
+	 * two fput()s instead of vma_fput(vma),
+	 * coz vma may not be available anymore.
+	 */
 	fput(file);
+	if (prfile)
+		fput(prfile);
 out:
 	up_write(&mm->mmap_sem);
 	if (populate)
@@ -3065,6 +3084,7 @@ void exit_mmap(struct mm_struct *mm)
 		if (vma->vm_flags & VM_ACCOUNT)
 			nr_accounted += vma_pages(vma);
 		vma = remove_vma(vma);
+		cond_resched();
 	}
 	vm_unacct_memory(nr_accounted);
 }
@@ -3171,7 +3191,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		if (anon_vma_clone(new_vma, vma))
 			goto out_free_mempol;
 		if (new_vma->vm_file)
-			get_file(new_vma->vm_file);
+			vma_get_file(new_vma);
 		if (new_vma->vm_ops && new_vma->vm_ops->open)
 			new_vma->vm_ops->open(new_vma);
 		vma_link(mm, new_vma, prev, rb_link, rb_parent);
diff --git a/mm/mremap.c b/mm/mremap.c
index 88ceeb4ef817..3c7fcd5d5794 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -223,7 +223,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 		new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
 		if (!new_pmd)
 			break;
-		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd)) {
+		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd) || pmd_devmap(*old_pmd)) {
 			if (extent == HPAGE_PMD_SIZE) {
 				bool moved;
 				/* See comment in move_ptes() */
diff --git a/mm/nommu.c b/mm/nommu.c
index 13fc62d97544..945971f288a9 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -645,7 +645,7 @@ static void __put_nommu_region(struct vm_region *region)
 		up_write(&nommu_region_sem);
 
 		if (region->vm_file)
-			fput(region->vm_file);
+			vmr_fput(region);
 
 		/* IO memory and memory shared directly out of the pagecache
 		 * from ramfs/tmpfs mustn't be released here */
@@ -803,7 +803,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
 	if (vma->vm_ops && vma->vm_ops->close)
 		vma->vm_ops->close(vma);
 	if (vma->vm_file)
-		fput(vma->vm_file);
+		vma_fput(vma);
 	put_nommu_region(vma->vm_region);
 	kmem_cache_free(vm_area_cachep, vma);
 }
@@ -1325,7 +1325,7 @@ unsigned long do_mmap(struct file *file,
 					goto error_just_free;
 				}
 			}
-			fput(region->vm_file);
+			vmr_fput(region);
 			kmem_cache_free(vm_region_jar, region);
 			region = pregion;
 			result = start;
@@ -1400,10 +1400,10 @@ error_just_free:
 	up_write(&nommu_region_sem);
 error:
 	if (region->vm_file)
-		fput(region->vm_file);
+		vmr_fput(region);
 	kmem_cache_free(vm_region_jar, region);
 	if (vma->vm_file)
-		fput(vma->vm_file);
+		vma_fput(vma);
 	kmem_cache_free(vm_area_cachep, vma);
 	return ret;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e992afe3a58e..7183807d494f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -67,6 +67,7 @@
 #include <linux/ftrace.h>
 #include <linux/lockdep.h>
 #include <linux/nmi.h>
+#include <linux/khugepaged.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -1114,6 +1115,11 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 	spin_lock(&zone->lock);
 	isolated_pageblocks = has_isolate_pageblock(zone);
 
+	/*
+	 * Ensure proper count is passed which otherwise would stuck in the
+	 * below while (list_empty(list)) loop.
+	 */
+	count = min(pcp->count, count);
 	while (count) {
 		struct page *page;
 		struct list_head *list;
@@ -7016,9 +7022,11 @@ int __meminit init_per_zone_wmark_min(void)
 	setup_min_slab_ratio();
 #endif
 
+	khugepaged_min_free_kbytes_update();
+
 	return 0;
 }
-core_initcall(init_per_zone_wmark_min)
+postcore_initcall(init_per_zone_wmark_min)
 
 /*
  * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 6ac05a6ff2d1..4753b317ef7b 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -617,7 +617,6 @@ static void init_early_allocated_pages(void)
 {
 	pg_data_t *pgdat;
 
-	drain_all_pages(NULL);
 	for_each_online_pgdat(pgdat)
 		init_zones_in_node(pgdat);
 }
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 23a3e415ac2c..84bdb2bac3dc 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -15,9 +15,9 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
 		if (err)
 		       break;
-		addr += PAGE_SIZE;
-		if (addr == end)
+		if (addr >= end - PAGE_SIZE)
 			break;
+		addr += PAGE_SIZE;
 		pte++;
 	}
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 9beb84800d8d..b24d6fe6bd5e 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1099,7 +1099,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 
 	/* allocate chunk */
 	chunk = memblock_virt_alloc(sizeof(struct pcpu_chunk) +
-				    BITS_TO_LONGS(region_size >> PAGE_SHIFT),
+				    BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long),
 				    0);
 
 	INIT_LIST_HEAD(&chunk->list);
diff --git a/mm/prfile.c b/mm/prfile.c
new file mode 100644
index 000000000000..1ef053bf4f49
--- /dev/null
+++ b/mm/prfile.c
@@ -0,0 +1,85 @@
+/*
+ * Mainly for aufs which mmap(2) different file and wants to print different
+ * path in /proc/PID/maps.
+ * Call these functions via macros defined in linux/mm.h.
+ *
+ * See Documentation/filesystems/aufs/design/06mmap.txt
+ *
+ * Copyright (c) 2014-2017 Junjro R. Okajima
+ * Copyright (c) 2014 Ian Campbell
+ */
+
+#include <linux/mm.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+
+/* #define PRFILE_TRACE */
+static inline void prfile_trace(struct file *f, struct file *pr,
+			      const char func[], int line, const char func2[])
+{
+#ifdef PRFILE_TRACE
+	if (pr)
+		pr_info("%s:%d: %s, %pD2\n", func, line, func2, f);
+#endif
+}
+
+void vma_do_file_update_time(struct vm_area_struct *vma, const char func[],
+			     int line)
+{
+	struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	file_update_time(f);
+	if (f && pr)
+		file_update_time(pr);
+}
+
+struct file *vma_do_pr_or_file(struct vm_area_struct *vma, const char func[],
+			       int line)
+{
+	struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	return (f && pr) ? pr : f;
+}
+
+void vma_do_get_file(struct vm_area_struct *vma, const char func[], int line)
+{
+	struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	get_file(f);
+	if (f && pr)
+		get_file(pr);
+}
+
+void vma_do_fput(struct vm_area_struct *vma, const char func[], int line)
+{
+	struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	fput(f);
+	if (f && pr)
+		fput(pr);
+}
+
+#ifndef CONFIG_MMU
+struct file *vmr_do_pr_or_file(struct vm_region *region, const char func[],
+			       int line)
+{
+	struct file *f = region->vm_file, *pr = region->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	return (f && pr) ? pr : f;
+}
+
+void vmr_do_fput(struct vm_region *region, const char func[], int line)
+{
+	struct file *f = region->vm_file, *pr = region->vm_prfile;
+
+	prfile_trace(f, pr, func, line, __func__);
+	fput(f);
+	if (f && pr)
+		fput(pr);
+}
+#endif /* !CONFIG_MMU */
diff --git a/mm/slab_common.c b/mm/slab_common.c
index f6764cf162b8..caba3efce3f4 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1449,7 +1449,7 @@ void kzfree(const void *p)
 	if (unlikely(ZERO_OR_NULL_PTR(mem)))
 		return;
 	ks = ksize(mem);
-	memset(mem, 0, ks);
+	memzero_explicit(mem, ks);
 	kfree(mem);
 }
 EXPORT_SYMBOL(kzfree);
diff --git a/mm/slub.c b/mm/slub.c
index 481518c3f61a..db2639832037 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -658,6 +658,20 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...)
 	va_end(args);
 }
 
+static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
+			       void **freelist, void *nextfree)
+{
+	if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
+	    !check_valid_pointer(s, page, nextfree) && freelist) {
+		object_err(s, page, *freelist, "Freechain corrupt");
+		*freelist = NULL;
+		slab_fix(s, "Isolate corrupted freechain");
+		return true;
+	}
+
+	return false;
+}
+
 static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 {
 	unsigned int off;	/* Offset of last byte */
@@ -1339,6 +1353,11 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node,
 static inline void dec_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 
+static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
+			       void **freelist, void *nextfree)
+{
+	return false;
+}
 #endif /* CONFIG_SLUB_DEBUG */
 
 /*
@@ -2029,6 +2048,14 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 		void *prior;
 		unsigned long counters;
 
+		/*
+		 * If 'nextfree' is invalid, it is possible that the object at
+		 * 'freelist' is already corrupted.  So isolate all objects
+		 * starting at 'freelist'.
+		 */
+		if (freelist_corrupted(s, page, &freelist, nextfree))
+			break;
+
 		do {
 			prior = page->freelist;
 			counters = page->counters;
@@ -5574,7 +5601,8 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 		 */
 		if (buffer)
 			buf = buffer;
-		else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf))
+		else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf) &&
+			 !IS_ENABLED(CONFIG_SLUB_STATS))
 			buf = mbuf;
 		else {
 			buffer = (char *) get_zeroed_page(GFP_KERNEL);
@@ -5727,8 +5755,10 @@ static int sysfs_slab_add(struct kmem_cache *s)
 
 	s->kobj.kset = kset;
 	err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
-	if (err)
+	if (err) {
+		kobject_put(&s->kobj);
 		goto out;
+	}
 
 	err = sysfs_create_group(&s->kobj, &slab_attr_group);
 	if (err)
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 326439428daf..3ceea86818bd 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -23,6 +23,7 @@
 #include <linux/huge_mm.h>
 
 #include <asm/pgtable.h>
+#include "internal.h"
 
 /*
  * swapper_space is a fiction, retained to simplify the path through
@@ -403,7 +404,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		/*
 		 * call radix_tree_preload() while we can wait.
 		 */
-		err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL);
+		err = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
 		if (err)
 			break;
 
@@ -523,10 +524,11 @@ static unsigned long swapin_nr_pages(unsigned long offset)
 		return 1;
 
 	hits = atomic_xchg(&swapin_readahead_hits, 0);
-	pages = __swapin_nr_pages(prev_offset, offset, hits, max_pages,
+	pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits,
+				  max_pages,
 				  atomic_read(&last_readahead_pages));
 	if (!hits)
-		prev_offset = offset;
+		WRITE_ONCE(prev_offset, offset);
 	atomic_set(&last_readahead_pages, pages);
 
 	return pages;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4f9e522643a2..f79f0d938274 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -973,7 +973,7 @@ start_over:
 			goto nextsi;
 		}
 		if (cluster) {
-			if (!(si->flags & SWP_FILE))
+			if (si->flags & SWP_BLKDEV)
 				n_ret = swap_alloc_cluster(si, swp_entries);
 		} else
 			n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
diff --git a/mm/util.c b/mm/util.c
index 842ba5fb662e..f0d773c719a1 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -417,6 +417,24 @@ void kvfree(const void *addr)
 }
 EXPORT_SYMBOL(kvfree);
 
+/**
+ * kvfree_sensitive - Free a data object containing sensitive information.
+ * @addr: address of the data object to be freed.
+ * @len: length of the data object.
+ *
+ * Use the special memzero_explicit() function to clear the content of a
+ * kvmalloc'ed object containing sensitive data to make sure that the
+ * compiler won't optimize out the data clearing.
+ */
+void kvfree_sensitive(const void *addr, size_t len)
+{
+	if (likely(!ZERO_OR_NULL_PTR(addr))) {
+		memzero_explicit((void *)addr, len);
+		kvfree(addr);
+	}
+}
+EXPORT_SYMBOL(kvfree_sensitive);
+
 static inline void *__page_rmapping(struct page *page)
 {
 	unsigned long mapping;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 63bf3f207e16..e8c64dddfecd 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1524,7 +1524,7 @@ static void __vunmap(const void *addr, int deallocate_pages)
 			addr))
 		return;
 
-	area = find_vmap_area((unsigned long)addr)->vm;
+	area = find_vm_area(addr);
 	if (unlikely(!area)) {
 		WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
 				addr);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c6962aa5ddb4..5ee6fbdec8a8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2950,8 +2950,9 @@ static bool allow_direct_reclaim(pg_data_t *pgdat)
 
 	/* kswapd must be awake if processes are being throttled */
 	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
-		pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
-						(enum zone_type)ZONE_NORMAL);
+		if (READ_ONCE(pgdat->kswapd_classzone_idx) > ZONE_NORMAL)
+			WRITE_ONCE(pgdat->kswapd_classzone_idx, ZONE_NORMAL);
+
 		wake_up_interruptible(&pgdat->kswapd_wait);
 	}
 
@@ -3451,9 +3452,9 @@ out:
 static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
 					   enum zone_type prev_classzone_idx)
 {
-	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		return prev_classzone_idx;
-	return pgdat->kswapd_classzone_idx;
+	enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+
+	return curr_idx == MAX_NR_ZONES ? prev_classzone_idx : curr_idx;
 }
 
 static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
@@ -3497,8 +3498,11 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o
 		 * the previous request that slept prematurely.
 		 */
 		if (remaining) {
-			pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
-			pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order);
+			WRITE_ONCE(pgdat->kswapd_classzone_idx,
+				   kswapd_classzone_idx(pgdat, classzone_idx));
+
+			if (READ_ONCE(pgdat->kswapd_order) < reclaim_order)
+				WRITE_ONCE(pgdat->kswapd_order, reclaim_order);
 		}
 
 		finish_wait(&pgdat->kswapd_wait, &wait);
@@ -3580,12 +3584,12 @@ static int kswapd(void *p)
 	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 	set_freezable();
 
-	pgdat->kswapd_order = 0;
-	pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
+	WRITE_ONCE(pgdat->kswapd_order, 0);
+	WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
 	for ( ; ; ) {
 		bool ret;
 
-		alloc_order = reclaim_order = pgdat->kswapd_order;
+		alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
 		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
 
 kswapd_try_sleep:
@@ -3593,10 +3597,10 @@ kswapd_try_sleep:
 					classzone_idx);
 
 		/* Read the new order and classzone_idx */
-		alloc_order = reclaim_order = pgdat->kswapd_order;
+		alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
 		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
-		pgdat->kswapd_order = 0;
-		pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
+		WRITE_ONCE(pgdat->kswapd_order, 0);
+		WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
 
 		ret = try_to_freeze();
 		if (kthread_should_stop())
@@ -3638,20 +3642,23 @@ kswapd_try_sleep:
 void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
+	enum zone_type curr_idx;
 
 	if (!managed_zone(zone))
 		return;
 
 	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
 		return;
+
 	pgdat = zone->zone_pgdat;
+	curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+
+	if (curr_idx == MAX_NR_ZONES || curr_idx < classzone_idx)
+		WRITE_ONCE(pgdat->kswapd_classzone_idx, classzone_idx);
+
+	if (READ_ONCE(pgdat->kswapd_order) < order)
+		WRITE_ONCE(pgdat->kswapd_order, order);
 
-	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		pgdat->kswapd_classzone_idx = classzone_idx;
-	else
-		pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx,
-						  classzone_idx);
-	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
 
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index a9c65f13b7f5..9f020559c192 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -301,7 +301,6 @@ static void p9_read_work(struct work_struct *work)
 {
 	int n, err;
 	struct p9_conn *m;
-	int status = REQ_STATUS_ERROR;
 
 	m = container_of(work, struct p9_conn, rq);
 
@@ -381,11 +380,21 @@ static void p9_read_work(struct work_struct *work)
 	if ((m->req) && (m->rc.offset == m->rc.capacity)) {
 		p9_debug(P9_DEBUG_TRANS, "got new packet\n");
 		spin_lock(&m->client->lock);
-		if (m->req->status != REQ_STATUS_ERROR)
-			status = REQ_STATUS_RCVD;
-		list_del(&m->req->req_list);
-		/* update req->status while holding client->lock  */
-		p9_client_cb(m->client, m->req, status);
+		if (m->req->status == REQ_STATUS_SENT) {
+			list_del(&m->req->req_list);
+			p9_client_cb(m->client, m->req, REQ_STATUS_RCVD);
+		} else if (m->req->status == REQ_STATUS_FLSHD) {
+			/* Ignore replies associated with a cancelled request. */
+			p9_debug(P9_DEBUG_TRANS,
+				 "Ignore replies associated with a cancelled request\n");
+		} else {
+			spin_unlock(&m->client->lock);
+			p9_debug(P9_DEBUG_ERROR,
+				 "Request tag %d errored out while we were reading the reply\n",
+				 m->rc.tag);
+			err = -EIO;
+			goto error;
+		}
 		spin_unlock(&m->client->lock);
 		m->rc.sdata = NULL;
 		m->rc.offset = 0;
@@ -712,11 +721,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
 {
 	p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
 
+	spin_lock(&client->lock);
+	/* Ignore cancelled request if message has been received
+	 * before lock.
+	 */
+	if (req->status == REQ_STATUS_RCVD) {
+		spin_unlock(&client->lock);
+		return 0;
+	}
+
 	/* we haven't received a response for oldreq,
 	 * remove it from the list.
 	 */
-	spin_lock(&client->lock);
 	list_del(&req->req_list);
+	req->status = REQ_STATUS_FLSHD;
 	spin_unlock(&client->lock);
 
 	return 0;
@@ -811,20 +829,28 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd)
 		return -ENOMEM;
 
 	ts->rd = fget(rfd);
+	if (!ts->rd)
+		goto out_free_ts;
+	if (!(ts->rd->f_mode & FMODE_READ))
+		goto out_put_rd;
 	ts->wr = fget(wfd);
-	if (!ts->rd || !ts->wr) {
-		if (ts->rd)
-			fput(ts->rd);
-		if (ts->wr)
-			fput(ts->wr);
-		kfree(ts);
-		return -EIO;
-	}
+	if (!ts->wr)
+		goto out_put_rd;
+	if (!(ts->wr->f_mode & FMODE_WRITE))
+		goto out_put_wr;
 
 	client->trans = ts;
 	client->status = Connected;
 
 	return 0;
+
+out_put_wr:
+	fput(ts->wr);
+out_put_rd:
+	fput(ts->rd);
+out_free_ts:
+	kfree(ts);
+	return -EIO;
 }
 
 static int p9_socket_open(struct p9_client *client, struct socket *csocket)
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 85ce89c8a35c..0b0794b6a814 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -1282,6 +1282,12 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry)
 		entry->vcc = NULL;
 	}
 	if (entry->recv_vcc) {
+		struct atm_vcc *vcc = entry->recv_vcc;
+		struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc);
+
+		kfree(vpriv);
+		vcc->user_back = NULL;
+
 		entry->recv_vcc->push = entry->old_recv_push;
 		vcc_release_async(entry->recv_vcc, -EPIPE);
 		entry->recv_vcc = NULL;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 63fa6ea2341e..6915eebc7a4a 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -639,8 +639,10 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_BINDTODEVICE:
-		if (optlen > IFNAMSIZ)
-			optlen = IFNAMSIZ;
+		if (optlen > IFNAMSIZ - 1)
+			optlen = IFNAMSIZ - 1;
+
+		memset(devname, 0, sizeof(devname));
 
 		if (copy_from_user(devname, optval, optlen)) {
 			res = -EFAULT;
@@ -1189,7 +1191,10 @@ static int __must_check ax25_connect(struct socket *sock,
 	if (addr_len > sizeof(struct sockaddr_ax25) &&
 	    fsa->fsa_ax25.sax25_ndigis != 0) {
 		/* Valid number of digipeaters ? */
-		if (fsa->fsa_ax25.sax25_ndigis < 1 || fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS) {
+		if (fsa->fsa_ax25.sax25_ndigis < 1 ||
+		    fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS ||
+		    addr_len < sizeof(struct sockaddr_ax25) +
+		    sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) {
 			err = -EINVAL;
 			goto out_release;
 		}
@@ -1509,7 +1514,10 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 			struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax;
 
 			/* Valid number of digipeaters ? */
-			if (usax->sax25_ndigis < 1 || usax->sax25_ndigis > AX25_MAX_DIGIS) {
+			if (usax->sax25_ndigis < 1 ||
+			    usax->sax25_ndigis > AX25_MAX_DIGIS ||
+			    addr_len < sizeof(struct sockaddr_ax25) +
+			    sizeof(ax25_address) * usax->sax25_ndigis) {
 				err = -EINVAL;
 				goto out;
 			}
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index f0abbbdafe07..c49c48866a3f 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -715,6 +715,12 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset,
 		   ntohl(ogm_packet->seqno), ogm_throughput, ogm_packet->ttl,
 		   ogm_packet->version, ntohs(ogm_packet->tvlv_len));
 
+	if (batadv_is_my_mac(bat_priv, ogm_packet->orig)) {
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "Drop packet: originator packet from ourself\n");
+		return;
+	}
+
 	/* If the throughput metric is 0, immediately drop the packet. No need
 	 * to create orig_node / neigh_node for an unusable route.
 	 */
@@ -842,11 +848,6 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb,
 	if (batadv_is_my_mac(bat_priv, ethhdr->h_source))
 		goto free_skb;
 
-	ogm_packet = (struct batadv_ogm2_packet *)skb->data;
-
-	if (batadv_is_my_mac(bat_priv, ogm_packet->orig))
-		goto free_skb;
-
 	batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_RX);
 	batadv_add_counter(bat_priv, BATADV_CNT_MGMT_RX_BYTES,
 			   skb->len + ETH_HLEN);
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index c761c0c233e4..ae1147b8710f 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -36,6 +36,7 @@
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
+#include <linux/preempt.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
 #include <linux/seq_file.h>
@@ -95,11 +96,12 @@ static inline u32 batadv_choose_claim(const void *data, u32 size)
  */
 static inline u32 batadv_choose_backbone_gw(const void *data, u32 size)
 {
-	const struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data;
+	const struct batadv_bla_backbone_gw *gw;
 	u32 hash = 0;
 
-	hash = jhash(&claim->addr, sizeof(claim->addr), hash);
-	hash = jhash(&claim->vid, sizeof(claim->vid), hash);
+	gw = (struct batadv_bla_backbone_gw *)data;
+	hash = jhash(&gw->orig, sizeof(gw->orig), hash);
+	hash = jhash(&gw->vid, sizeof(gw->vid), hash);
 
 	return hash % size;
 }
@@ -450,7 +452,10 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
 	batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES,
 			   skb->len + ETH_HLEN);
 
-	netif_rx(skb);
+	if (in_interrupt())
+		netif_rx(skb);
+	else
+		netif_rx_ni(skb);
 out:
 	if (primary_if)
 		batadv_hardif_put(primary_if);
@@ -1822,7 +1827,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb,
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: the frame to be checked
  * @vid: the VLAN ID of the frame
- * @is_bcast: the packet came in a broadcast packet type.
+ * @packet_type: the batman packet type this frame came in
  *
  * batadv_bla_rx avoidance checks if:
  *  * we have to race for a claim
@@ -1834,7 +1839,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb,
  * further process the skb.
  */
 bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
-		   unsigned short vid, bool is_bcast)
+		   unsigned short vid, int packet_type)
 {
 	struct batadv_bla_backbone_gw *backbone_gw;
 	struct ethhdr *ethhdr;
@@ -1856,9 +1861,24 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		goto handled;
 
 	if (unlikely(atomic_read(&bat_priv->bla.num_requests)))
-		/* don't allow broadcasts while requests are in flight */
-		if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast)
-			goto handled;
+		/* don't allow multicast packets while requests are in flight */
+		if (is_multicast_ether_addr(ethhdr->h_dest))
+			/* Both broadcast flooding or multicast-via-unicasts
+			 * delivery might send to multiple backbone gateways
+			 * sharing the same LAN and therefore need to coordinate
+			 * which backbone gateway forwards into the LAN,
+			 * by claiming the payload source address.
+			 *
+			 * Broadcast flooding and multicast-via-unicasts
+			 * delivery use the following two batman packet types.
+			 * Note: explicitly exclude BATADV_UNICAST_4ADDR,
+			 * as the DHCP gateway feature will send explicitly
+			 * to only one BLA gateway, so the claiming process
+			 * should be avoided there.
+			 */
+			if (packet_type == BATADV_BCAST ||
+			    packet_type == BATADV_UNICAST)
+				goto handled;
 
 	ether_addr_copy(search_claim.addr, ethhdr->h_source);
 	search_claim.vid = vid;
@@ -1893,13 +1913,14 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		goto allow;
 	}
 
-	/* if it is a broadcast ... */
-	if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) {
+	/* if it is a multicast ... */
+	if (is_multicast_ether_addr(ethhdr->h_dest) &&
+	    (packet_type == BATADV_BCAST || packet_type == BATADV_UNICAST)) {
 		/* ... drop it. the responsible gateway is in charge.
 		 *
-		 * We need to check is_bcast because with the gateway
+		 * We need to check packet type because with the gateway
 		 * feature, broadcasts (like DHCP requests) may be sent
-		 * using a unicast packet type.
+		 * using a unicast 4 address packet type. See comment above.
 		 */
 		goto handled;
 	} else {
diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h
index 234775748b8e..e05809abf79c 100644
--- a/net/batman-adv/bridge_loop_avoidance.h
+++ b/net/batman-adv/bridge_loop_avoidance.h
@@ -47,7 +47,7 @@ static inline bool batadv_bla_is_loopdetect_mac(const uint8_t *mac)
 
 #ifdef CONFIG_BATMAN_ADV_BLA
 bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
-		   unsigned short vid, bool is_bcast);
+		   unsigned short vid, int packet_type);
 bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		   unsigned short vid);
 bool batadv_bla_is_backbone_gw(struct sk_buff *skb,
@@ -78,7 +78,7 @@ bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr,
 
 static inline bool batadv_bla_rx(struct batadv_priv *bat_priv,
 				 struct sk_buff *skb, unsigned short vid,
-				 bool is_bcast)
+				 int packet_type)
 {
 	return false;
 }
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index c6a7341f0527..056af2eec4a2 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -674,8 +674,10 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len,
 
 	chaddr_offset = *header_len + BATADV_DHCP_CHADDR_OFFSET;
 	/* store the client address if the message is going to a client */
-	if (ret == BATADV_DHCP_TO_CLIENT &&
-	    pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) {
+	if (ret == BATADV_DHCP_TO_CLIENT) {
+		if (!pskb_may_pull(skb, chaddr_offset + ETH_ALEN))
+			return BATADV_DHCP_NO;
+
 		/* check if the DHCP packet carries an Ethernet DHCP */
 		p = skb->data + *header_len + BATADV_DHCP_HTYPE_OFFSET;
 		if (*p != BATADV_DHCP_HTYPE_ETHERNET)
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index f59aac06733e..83f73f840ff9 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -822,6 +822,10 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv,
 	vid = batadv_get_vid(skb, hdr_len);
 	ethhdr = (struct ethhdr *)(skb->data + hdr_len);
 
+	/* do not reroute multicast frames in a unicast header */
+	if (is_multicast_ether_addr(ethhdr->h_dest))
+		return true;
+
 	/* check if the destination client was served by this node and it is now
 	 * roaming. In this case, it means that the node has got a ROAM_ADV
 	 * message and that it knows the new destination in the mesh to re-route
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 7c883420485b..ba9dce04343a 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -418,10 +418,10 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	struct vlan_ethhdr *vhdr;
 	struct ethhdr *ethhdr;
 	unsigned short vid;
-	bool is_bcast;
+	int packet_type;
 
 	batadv_bcast_packet = (struct batadv_bcast_packet *)skb->data;
-	is_bcast = (batadv_bcast_packet->packet_type == BATADV_BCAST);
+	packet_type = batadv_bcast_packet->packet_type;
 
 	skb_pull_rcsum(skb, hdr_size);
 	skb_reset_mac_header(skb);
@@ -464,7 +464,7 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	/* Let the bridge loop avoidance check the packet. If will
 	 * not handle it, we can safely push it up.
 	 */
-	if (batadv_bla_rx(bat_priv, skb, vid, is_bcast))
+	if (batadv_bla_rx(bat_priv, skb, vid, packet_type))
 		goto out;
 
 	if (orig_node)
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 357475cceec6..9a75f9b00b51 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -57,6 +57,7 @@ static bool enable_6lowpan;
 /* We are listening incoming connections via this channel
  */
 static struct l2cap_chan *listen_chan;
+static DEFINE_MUTEX(set_lock);
 
 struct lowpan_peer {
 	struct list_head list;
@@ -1082,12 +1083,14 @@ static void do_enable_set(struct work_struct *work)
 
 	enable_6lowpan = set_enable->flag;
 
+	mutex_lock(&set_lock);
 	if (listen_chan) {
 		l2cap_chan_close(listen_chan, 0);
 		l2cap_chan_put(listen_chan);
 	}
 
 	listen_chan = bt_6lowpan_listen();
+	mutex_unlock(&set_lock);
 
 	kfree(set_enable);
 }
@@ -1139,11 +1142,13 @@ static ssize_t lowpan_control_write(struct file *fp,
 		if (ret == -EINVAL)
 			return ret;
 
+		mutex_lock(&set_lock);
 		if (listen_chan) {
 			l2cap_chan_close(listen_chan, 0);
 			l2cap_chan_put(listen_chan);
 			listen_chan = NULL;
 		}
+		mutex_unlock(&set_lock);
 
 		if (conn) {
 			struct lowpan_peer *peer;
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index aad994edd3bb..cd20c35daa6c 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -233,6 +233,9 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 			struct a2mp_info_req req;
 
 			found = true;
+
+			memset(&req, 0, sizeof(req));
+
 			req.id = cl->id;
 			a2mp_send(mgr, A2MP_GETINFO_REQ, __next_ident(mgr),
 				  sizeof(req), &req);
@@ -312,6 +315,8 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb,
 	if (!hdev || hdev->dev_type != HCI_AMP) {
 		struct a2mp_info_rsp rsp;
 
+		memset(&rsp, 0, sizeof(rsp));
+
 		rsp.id = req->id;
 		rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
 
@@ -355,6 +360,8 @@ static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 	if (!ctrl)
 		return -ENOMEM;
 
+	memset(&req, 0, sizeof(req));
+
 	req.id = rsp->id;
 	a2mp_send(mgr, A2MP_GETAMPASSOC_REQ, __next_ident(mgr), sizeof(req),
 		  &req);
@@ -383,6 +390,8 @@ static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb,
 		struct a2mp_amp_assoc_rsp rsp;
 		rsp.id = req->id;
 
+		memset(&rsp, 0, sizeof(rsp));
+
 		if (tmp) {
 			rsp.status = A2MP_STATUS_COLLISION_OCCURED;
 			amp_mgr_put(tmp);
@@ -471,7 +480,6 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 				   struct a2mp_cmd *hdr)
 {
 	struct a2mp_physlink_req *req = (void *) skb->data;
-
 	struct a2mp_physlink_rsp rsp;
 	struct hci_dev *hdev;
 	struct hci_conn *hcon;
@@ -482,6 +490,8 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	BT_DBG("local_id %d, remote_id %d", req->local_id, req->remote_id);
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	rsp.local_id = req->remote_id;
 	rsp.remote_id = req->local_id;
 
@@ -560,6 +570,8 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	BT_DBG("local_id %d remote_id %d", req->local_id, req->remote_id);
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	rsp.local_id = req->remote_id;
 	rsp.remote_id = req->local_id;
 	rsp.status = A2MP_STATUS_SUCCESS;
@@ -682,6 +694,8 @@ static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb)
 	if (err) {
 		struct a2mp_cmd_rej rej;
 
+		memset(&rej, 0, sizeof(rej));
+
 		rej.reason = cpu_to_le16(0);
 		hdr = (void *) skb->data;
 
@@ -905,6 +919,8 @@ void a2mp_send_getinfo_rsp(struct hci_dev *hdev)
 
 	BT_DBG("%s mgr %p", hdev->name, mgr);
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	rsp.id = hdev->id;
 	rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
 
@@ -1002,6 +1018,8 @@ void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status)
 	if (!mgr)
 		return;
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	hs_hcon = hci_conn_hash_lookup_state(hdev, AMP_LINK, BT_CONNECT);
 	if (!hs_hcon) {
 		rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION;
@@ -1034,6 +1052,8 @@ void a2mp_discover_amp(struct l2cap_chan *chan)
 
 	mgr->bredr_chan = chan;
 
+	memset(&req, 0, sizeof(req));
+
 	req.mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU);
 	req.ext_feat = 0;
 	a2mp_send(mgr, A2MP_DISCOVER_REQ, 1, sizeof(req), &req);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 1d085eed72d0..e3cd81ce2a7b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1163,6 +1163,23 @@ int hci_conn_check_link_mode(struct hci_conn *conn)
 			return 0;
 	}
 
+	 /* AES encryption is required for Level 4:
+	  *
+	  * BLUETOOTH CORE SPECIFICATION Version 5.2 | Vol 3, Part C
+	  * page 1319:
+	  *
+	  * 128-bit equivalent strength for link and encryption keys
+	  * required using FIPS approved algorithms (E0 not allowed,
+	  * SAFER+ not allowed, and P-192 not allowed; encryption key
+	  * not shortened)
+	  */
+	if (conn->sec_level == BT_SECURITY_FIPS &&
+	    !test_bit(HCI_CONN_AES_CCM, &conn->flags)) {
+		bt_dev_err(conn->hdev,
+			   "Invalid security: Missing AES-CCM usage");
+		return 0;
+	}
+
 	if (hci_conn_ssp_enabled(conn) &&
 	    !test_bit(HCI_CONN_ENCRYPT, &conn->flags))
 		return 0;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 363dc85bbc5c..ba12bf8de826 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -41,12 +41,27 @@
 
 /* Handle HCI Event packets */
 
-static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb)
+static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb,
+				  u8 *new_status)
 {
 	__u8 status = *((__u8 *) skb->data);
 
 	BT_DBG("%s status 0x%2.2x", hdev->name, status);
 
+	/* It is possible that we receive Inquiry Complete event right
+	 * before we receive Inquiry Cancel Command Complete event, in
+	 * which case the latter event should have status of Command
+	 * Disallowed (0x0c). This should not be treated as error, since
+	 * we actually achieve what Inquiry Cancel wants to achieve,
+	 * which is to end the last Inquiry session.
+	 */
+	if (status == 0x0c && !test_bit(HCI_INQUIRY, &hdev->flags)) {
+		bt_dev_warn(hdev, "Ignoring error of Inquiry Cancel command");
+		status = 0x00;
+	}
+
+	*new_status = status;
+
 	if (status)
 		return;
 
@@ -1118,6 +1133,9 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr,
 {
 	struct discovery_state *d = &hdev->discovery;
 
+	if (len > HCI_MAX_AD_LENGTH)
+		return;
+
 	bacpy(&d->last_adv_addr, bdaddr);
 	d->last_adv_addr_type = bdaddr_type;
 	d->last_adv_rssi = rssi;
@@ -2094,7 +2112,7 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	BT_DBG("%s num_rsp %d", hdev->name, num_rsp);
 
-	if (!num_rsp)
+	if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1)
 		return;
 
 	if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ))
@@ -2475,7 +2493,7 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 				     &cp);
 		} else {
 			clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
-			hci_encrypt_cfm(conn, ev->status, 0x00);
+			hci_encrypt_cfm(conn, ev->status);
 		}
 	}
 
@@ -2561,22 +2579,7 @@ static void read_enc_key_size_complete(struct hci_dev *hdev, u8 status,
 		conn->enc_key_size = rp->key_size;
 	}
 
-	if (conn->state == BT_CONFIG) {
-		conn->state = BT_CONNECTED;
-		hci_connect_cfm(conn, 0);
-		hci_conn_drop(conn);
-	} else {
-		u8 encrypt;
-
-		if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags))
-			encrypt = 0x00;
-		else if (test_bit(HCI_CONN_AES_CCM, &conn->flags))
-			encrypt = 0x02;
-		else
-			encrypt = 0x01;
-
-		hci_encrypt_cfm(conn, 0, encrypt);
-	}
+	hci_encrypt_cfm(conn, 0);
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -2623,27 +2626,23 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
 
+	/* Check link security requirements are met */
+	if (!hci_conn_check_link_mode(conn))
+		ev->status = HCI_ERROR_AUTH_FAILURE;
+
 	if (ev->status && conn->state == BT_CONNECTED) {
 		if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING)
 			set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags);
 
+		/* Notify upper layers so they can cleanup before
+		 * disconnecting.
+		 */
+		hci_encrypt_cfm(conn, ev->status);
 		hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE);
 		hci_conn_drop(conn);
 		goto unlock;
 	}
 
-	/* In Secure Connections Only mode, do not allow any connections
-	 * that are not encrypted with AES-CCM using a P-256 authenticated
-	 * combination key.
-	 */
-	if (hci_dev_test_flag(hdev, HCI_SC_ONLY) &&
-	    (!test_bit(HCI_CONN_AES_CCM, &conn->flags) ||
-	     conn->key_type != HCI_LK_AUTH_COMBINATION_P256)) {
-		hci_connect_cfm(conn, HCI_ERROR_AUTH_FAILURE);
-		hci_conn_drop(conn);
-		goto unlock;
-	}
-
 	/* Try reading the encryption key size for encrypted ACL links */
 	if (!ev->status && ev->encrypt && conn->type == ACL_LINK) {
 		struct hci_cp_read_enc_key_size cp;
@@ -2673,14 +2672,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	}
 
 notify:
-	if (conn->state == BT_CONFIG) {
-		if (!ev->status)
-			conn->state = BT_CONNECTED;
-
-		hci_connect_cfm(conn, ev->status);
-		hci_conn_drop(conn);
-	} else
-		hci_encrypt_cfm(conn, ev->status, ev->encrypt);
+	hci_encrypt_cfm(conn, ev->status);
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -2772,7 +2764,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
 
 	switch (*opcode) {
 	case HCI_OP_INQUIRY_CANCEL:
-		hci_cc_inquiry_cancel(hdev, skb);
+		hci_cc_inquiry_cancel(hdev, skb, status);
 		break;
 
 	case HCI_OP_PERIODIC_INQ:
@@ -3623,6 +3615,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev,
 		struct inquiry_info_with_rssi_and_pscan_mode *info;
 		info = (void *) (skb->data + 1);
 
+		if (skb->len < num_rsp * sizeof(*info) + 1)
+			goto unlock;
+
 		for (; num_rsp; num_rsp--, info++) {
 			u32 flags;
 
@@ -3644,6 +3639,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev,
 	} else {
 		struct inquiry_info_with_rssi *info = (void *) (skb->data + 1);
 
+		if (skb->len < num_rsp * sizeof(*info) + 1)
+			goto unlock;
+
 		for (; num_rsp; num_rsp--, info++) {
 			u32 flags;
 
@@ -3664,6 +3662,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev,
 		}
 	}
 
+unlock:
 	hci_dev_unlock(hdev);
 }
 
@@ -3775,6 +3774,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev,
 	case 0x11:	/* Unsupported Feature or Parameter Value */
 	case 0x1c:	/* SCO interval rejected */
 	case 0x1a:	/* Unsupported Remote Feature */
+	case 0x1e:	/* Invalid LMP Parameters */
 	case 0x1f:	/* Unspecified error */
 	case 0x20:	/* Unsupported LMP Parameter value */
 		if (conn->out) {
@@ -3825,7 +3825,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev,
 
 	BT_DBG("%s num_rsp %d", hdev->name, num_rsp);
 
-	if (!num_rsp)
+	if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1)
 		return;
 
 	if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ))
@@ -4756,6 +4756,11 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 		return;
 	}
 
+	if (len > HCI_MAX_AD_LENGTH) {
+		pr_err_ratelimited("legacy adv larger than 31 bytes");
+		return;
+	}
+
 	/* Find the end of the data in case the report contains padded zero
 	 * bytes at the end causing an invalid length value.
 	 *
@@ -4816,7 +4821,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 	 */
 	conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type,
 								direct_addr);
-	if (conn && type == LE_ADV_IND) {
+	if (conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) {
 		/* Store report for later inclusion by
 		 * mgmt_device_connected
 		 */
@@ -4941,10 +4946,14 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		struct hci_ev_le_advertising_info *ev = ptr;
 		s8 rssi;
 
-		rssi = ev->data[ev->length];
-		process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
-				   ev->bdaddr_type, NULL, 0, rssi,
-				   ev->data, ev->length);
+		if (ev->length <= HCI_MAX_AD_LENGTH) {
+			rssi = ev->data[ev->length];
+			process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
+					   ev->bdaddr_type, NULL, 0, rssi,
+					   ev->data, ev->length);
+		} else {
+			bt_dev_err(hdev, "Dropping invalid advertising data");
+		}
 
 		ptr += sizeof(*ev) + ev->length + 1;
 	}
@@ -5249,6 +5258,11 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 	u8 status = 0, event = hdr->evt, req_evt = 0;
 	u16 opcode = HCI_OP_NOP;
 
+	if (!event) {
+		bt_dev_warn(hdev, "Received unexpected HCI Event 00000000");
+		goto done;
+	}
+
 	if (hdev->sent_cmd && bt_cb(hdev->sent_cmd)->hci.req_event == event) {
 		struct hci_command_hdr *cmd_hdr = (void *) hdev->sent_cmd->data;
 		opcode = __le16_to_cpu(cmd_hdr->opcode);
@@ -5460,6 +5474,7 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		req_complete_skb(hdev, status, opcode, orig_skb);
 	}
 
+done:
 	kfree_skb(orig_skb);
 	kfree_skb(skb);
 	hdev->stat.evt_rx++;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ebdf1b0e576a..df8cc639c46d 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -414,6 +414,9 @@ static void l2cap_chan_timeout(struct work_struct *work)
 	BT_DBG("chan %p state %s", chan, state_to_string(chan->state));
 
 	mutex_lock(&conn->chan_lock);
+	/* __set_chan_timer() calls l2cap_chan_hold(chan) while scheduling
+	 * this work. No need to call l2cap_chan_hold(chan) here again.
+	 */
 	l2cap_chan_lock(chan);
 
 	if (chan->state == BT_CONNECTED || chan->state == BT_CONFIG)
@@ -426,12 +429,12 @@ static void l2cap_chan_timeout(struct work_struct *work)
 
 	l2cap_chan_close(chan, reason);
 
-	l2cap_chan_unlock(chan);
-
 	chan->ops->close(chan);
-	mutex_unlock(&conn->chan_lock);
 
+	l2cap_chan_unlock(chan);
 	l2cap_chan_put(chan);
+
+	mutex_unlock(&conn->chan_lock);
 }
 
 struct l2cap_chan *l2cap_chan_create(void)
@@ -1725,9 +1728,9 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 
 		l2cap_chan_del(chan, err);
 
-		l2cap_chan_unlock(chan);
-
 		chan->ops->close(chan);
+
+		l2cap_chan_unlock(chan);
 		l2cap_chan_put(chan);
 	}
 
@@ -4114,7 +4117,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,
 		return 0;
 	}
 
-	if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2) {
+	if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2 &&
+	    chan->state != BT_CONNECTED) {
 		cmd_reject_invalid_cid(conn, cmd->ident, chan->scid,
 				       chan->dcid);
 		goto unlock;
@@ -4337,6 +4341,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn,
 		return 0;
 	}
 
+	l2cap_chan_hold(chan);
 	l2cap_chan_lock(chan);
 
 	rsp.dcid = cpu_to_le16(chan->scid);
@@ -4345,12 +4350,11 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn,
 
 	chan->ops->set_shutdown(chan);
 
-	l2cap_chan_hold(chan);
 	l2cap_chan_del(chan, ECONNRESET);
 
-	l2cap_chan_unlock(chan);
-
 	chan->ops->close(chan);
+
+	l2cap_chan_unlock(chan);
 	l2cap_chan_put(chan);
 
 	mutex_unlock(&conn->chan_lock);
@@ -4382,20 +4386,21 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn,
 		return 0;
 	}
 
+	l2cap_chan_hold(chan);
 	l2cap_chan_lock(chan);
 
 	if (chan->state != BT_DISCONN) {
 		l2cap_chan_unlock(chan);
+		l2cap_chan_put(chan);
 		mutex_unlock(&conn->chan_lock);
 		return 0;
 	}
 
-	l2cap_chan_hold(chan);
 	l2cap_chan_del(chan, 0);
 
-	l2cap_chan_unlock(chan);
-
 	chan->ops->close(chan);
+
+	l2cap_chan_unlock(chan);
 	l2cap_chan_put(chan);
 
 	mutex_unlock(&conn->chan_lock);
@@ -6678,9 +6683,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb)
 		goto drop;
 	}
 
-	if ((chan->mode == L2CAP_MODE_ERTM ||
-	     chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb))
-		goto drop;
+	if (chan->ops->filter) {
+		if (chan->ops->filter(chan, skb))
+			goto drop;
+	}
 
 	if (!control->sframe) {
 		int err;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 8c329c549ea6..7ff82f97e42c 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1040,7 +1040,7 @@ done:
 }
 
 /* Kill socket (only if zapped and orphan)
- * Must be called on unlocked socket.
+ * Must be called on unlocked socket, with l2cap channel lock.
  */
 static void l2cap_sock_kill(struct sock *sk)
 {
@@ -1191,6 +1191,7 @@ static int l2cap_sock_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	int err;
+	struct l2cap_chan *chan;
 
 	BT_DBG("sock %p, sk %p", sock, sk);
 
@@ -1200,9 +1201,17 @@ static int l2cap_sock_release(struct socket *sock)
 	bt_sock_unlink(&l2cap_sk_list, sk);
 
 	err = l2cap_sock_shutdown(sock, 2);
+	chan = l2cap_pi(sk)->chan;
+
+	l2cap_chan_hold(chan);
+	l2cap_chan_lock(chan);
 
 	sock_orphan(sk);
 	l2cap_sock_kill(sk);
+
+	l2cap_chan_unlock(chan);
+	l2cap_chan_put(chan);
+
 	return err;
 }
 
@@ -1220,12 +1229,15 @@ static void l2cap_sock_cleanup_listen(struct sock *parent)
 		BT_DBG("child chan %p state %s", chan,
 		       state_to_string(chan->state));
 
+		l2cap_chan_hold(chan);
 		l2cap_chan_lock(chan);
+
 		__clear_chan_timer(chan);
 		l2cap_chan_close(chan, ECONNRESET);
-		l2cap_chan_unlock(chan);
-
 		l2cap_sock_kill(sk);
+
+		l2cap_chan_unlock(chan);
+		l2cap_chan_put(chan);
 	}
 }
 
@@ -1465,6 +1477,19 @@ static void l2cap_sock_suspend_cb(struct l2cap_chan *chan)
 	sk->sk_state_change(sk);
 }
 
+static int l2cap_sock_filter(struct l2cap_chan *chan, struct sk_buff *skb)
+{
+	struct sock *sk = chan->data;
+
+	switch (chan->mode) {
+	case L2CAP_MODE_ERTM:
+	case L2CAP_MODE_STREAMING:
+		return sk_filter(sk, skb);
+	}
+
+	return 0;
+}
+
 static const struct l2cap_ops l2cap_chan_ops = {
 	.name			= "L2CAP Socket Interface",
 	.new_connection		= l2cap_sock_new_connection_cb,
@@ -1479,6 +1504,7 @@ static const struct l2cap_ops l2cap_chan_ops = {
 	.set_shutdown		= l2cap_sock_set_shutdown_cb,
 	.get_sndtimeo		= l2cap_sock_get_sndtimeo_cb,
 	.alloc_skb		= l2cap_sock_alloc_skb_cb,
+	.filter			= l2cap_sock_filter,
 };
 
 static void l2cap_sock_destruct(struct sock *sk)
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ba24f613c0fc..bca1408f815f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -635,7 +635,8 @@ static u32 get_supported_settings(struct hci_dev *hdev)
 
 		if (lmp_ssp_capable(hdev)) {
 			settings |= MGMT_SETTING_SSP;
-			settings |= MGMT_SETTING_HS;
+			if (IS_ENABLED(CONFIG_BT_HS))
+				settings |= MGMT_SETTING_HS;
 		}
 
 		if (lmp_sc_capable(hdev))
@@ -1645,6 +1646,10 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	BT_DBG("request for %s", hdev->name);
 
+	if (!IS_ENABLED(CONFIG_BT_HS))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
+				       MGMT_STATUS_NOT_SUPPORTED);
+
 	status = mgmt_bredr_support(hdev);
 	if (status)
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e870cfc85b14..14ff034e561c 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -190,8 +190,8 @@ struct net_bridge_port_group {
 	struct rcu_head			rcu;
 	struct timer_list		timer;
 	struct br_ip			addr;
+	unsigned char			eth_addr[ETH_ALEN] __aligned(2);
 	unsigned char			flags;
-	unsigned char			eth_addr[ETH_ALEN];
 };
 
 struct net_bridge_mdb_entry
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index b09ec869c913..0ab7688bb724 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -34,6 +34,12 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb,
 	ether_addr_copy(eth->h_dest, eth_hdr(oldskb)->h_source);
 	eth->h_proto = eth_hdr(oldskb)->h_proto;
 	skb_pull(nskb, ETH_HLEN);
+
+	if (skb_vlan_tag_present(oldskb)) {
+		u16 vid = skb_vlan_tag_get(oldskb);
+
+		__vlan_hwaccel_put_tag(nskb, oldskb->vlan_proto, vid);
+	}
 }
 
 static int nft_bridge_iphdr_validate(struct sk_buff *skb)
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 92b2641ab93b..b026128a89d7 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -384,6 +384,7 @@ static void target_copy(struct ceph_osd_request_target *dest,
 	dest->size = src->size;
 	dest->min_size = src->min_size;
 	dest->sort_bitwise = src->sort_bitwise;
+	dest->recovery_deletes = src->recovery_deletes;
 
 	dest->flags = src->flags;
 	dest->paused = src->paused;
@@ -3444,7 +3445,9 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
 		 * supported.
 		 */
 		req->r_t.target_oloc.pool = m.redirect.oloc.pool;
-		req->r_flags |= CEPH_OSD_FLAG_REDIRECTED;
+		req->r_flags |= CEPH_OSD_FLAG_REDIRECTED |
+				CEPH_OSD_FLAG_IGNORE_OVERLAY |
+				CEPH_OSD_FLAG_IGNORE_CACHE;
 		req->r_tid = 0;
 		__submit_request(req, false);
 		goto out_unlock_osdc;
diff --git a/net/compat.c b/net/compat.c
index 790851e70dab..45349658ed01 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -289,6 +289,7 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
 			break;
 		}
 		/* Bump the usage count and install the file. */
+		__receive_sock(fp[i]);
 		fd_install(new_fd, get_file(fp[i]));
 	}
 
diff --git a/net/core/dev.c b/net/core/dev.c
index ed552ad3f783..d101f95a47fb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -83,6 +83,7 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/socket.h>
@@ -194,7 +195,7 @@ static DEFINE_SPINLOCK(napi_hash_lock);
 static unsigned int napi_gen_id = NR_CPUS;
 static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8);
 
-static seqcount_t devnet_rename_seq;
+static DECLARE_RWSEM(devnet_rename_sem);
 
 static inline void dev_base_seq_inc(struct net *net)
 {
@@ -898,33 +899,28 @@ EXPORT_SYMBOL(dev_get_by_napi_id);
  *	@net: network namespace
  *	@name: a pointer to the buffer where the name will be stored.
  *	@ifindex: the ifindex of the interface to get the name from.
- *
- *	The use of raw_seqcount_begin() and cond_resched() before
- *	retrying is required as we want to give the writers a chance
- *	to complete when CONFIG_PREEMPT is not set.
  */
 int netdev_get_name(struct net *net, char *name, int ifindex)
 {
 	struct net_device *dev;
-	unsigned int seq;
+	int ret;
 
-retry:
-	seq = raw_seqcount_begin(&devnet_rename_seq);
+	down_read(&devnet_rename_sem);
 	rcu_read_lock();
+
 	dev = dev_get_by_index_rcu(net, ifindex);
 	if (!dev) {
-		rcu_read_unlock();
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out;
 	}
 
 	strcpy(name, dev->name);
-	rcu_read_unlock();
-	if (read_seqcount_retry(&devnet_rename_seq, seq)) {
-		cond_resched();
-		goto retry;
-	}
 
-	return 0;
+	ret = 0;
+out:
+	rcu_read_unlock();
+	up_read(&devnet_rename_sem);
+	return ret;
 }
 
 /**
@@ -1189,10 +1185,10 @@ int dev_change_name(struct net_device *dev, const char *newname)
 	if (dev->flags & IFF_UP)
 		return -EBUSY;
 
-	write_seqcount_begin(&devnet_rename_seq);
+	down_write(&devnet_rename_sem);
 
 	if (strncmp(newname, dev->name, IFNAMSIZ) == 0) {
-		write_seqcount_end(&devnet_rename_seq);
+		up_write(&devnet_rename_sem);
 		return 0;
 	}
 
@@ -1200,7 +1196,7 @@ int dev_change_name(struct net_device *dev, const char *newname)
 
 	err = dev_get_valid_name(net, dev, newname);
 	if (err < 0) {
-		write_seqcount_end(&devnet_rename_seq);
+		up_write(&devnet_rename_sem);
 		return err;
 	}
 
@@ -1215,11 +1211,11 @@ rollback:
 	if (ret) {
 		memcpy(dev->name, oldname, IFNAMSIZ);
 		dev->name_assign_type = old_assign_type;
-		write_seqcount_end(&devnet_rename_seq);
+		up_write(&devnet_rename_sem);
 		return ret;
 	}
 
-	write_seqcount_end(&devnet_rename_seq);
+	up_write(&devnet_rename_sem);
 
 	netdev_adjacent_rename_links(dev, oldname);
 
@@ -1240,7 +1236,7 @@ rollback:
 		/* err >= 0 after dev_alloc_name() or stores the first errno */
 		if (err >= 0) {
 			err = ret;
-			write_seqcount_begin(&devnet_rename_seq);
+			down_write(&devnet_rename_sem);
 			memcpy(dev->name, oldname, IFNAMSIZ);
 			memcpy(oldname, newname, IFNAMSIZ);
 			dev->name_assign_type = old_assign_type;
@@ -4630,7 +4626,7 @@ static void flush_backlog(struct work_struct *work)
 	skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
 		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->input_pkt_queue);
-			kfree_skb(skb);
+			dev_kfree_skb_irq(skb);
 			input_queue_head_incr(sd);
 		}
 	}
@@ -5536,12 +5532,13 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		pr_err_once("netif_napi_add() called with weight %d on device %s\n",
 			    weight, dev->name);
 	napi->weight = weight;
-	list_add(&napi->dev_list, &dev->napi_list);
 	napi->dev = dev;
 #ifdef CONFIG_NETPOLL
 	napi->poll_owner = -1;
 #endif
 	set_bit(NAPI_STATE_SCHED, &napi->state);
+	set_bit(NAPI_STATE_NPSVC, &napi->state);
+	list_add_rcu(&napi->dev_list, &dev->napi_list);
 	napi_hash_add(napi);
 }
 EXPORT_SYMBOL(netif_napi_add);
@@ -7698,6 +7695,13 @@ int register_netdevice(struct net_device *dev)
 		rcu_barrier();
 
 		dev->reg_state = NETREG_UNREGISTERED;
+		/* We should put the kobject that hold in
+		 * netdev_unregister_kobject(), otherwise
+		 * the net device cannot be freed when
+		 * driver calls free_netdev(), because the
+		 * kobject is being hold.
+		 */
+		kobject_put(&dev->dev.kobj);
 	}
 	/*
 	 *	Prevent userspace races by waiting until the network
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 567e431813e5..20f6c634ad68 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2836,6 +2836,7 @@ static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		*pos = cpu+1;
 		return per_cpu_ptr(tbl->stats, cpu);
 	}
+	(*pos)++;
 	return NULL;
 }
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index baf771d2d088..9d012255cedc 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1028,7 +1028,7 @@ static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf)
 	trans_timeout = queue->trans_timeout;
 	spin_unlock_irq(&queue->_xmit_lock);
 
-	return sprintf(buf, "%lu", trans_timeout);
+	return sprintf(buf, fmt_ulong, trans_timeout);
 }
 
 static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index abab3753a9e0..0b247f7cd583 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -179,7 +179,7 @@ static void poll_napi(struct net_device *dev)
 	struct napi_struct *napi;
 	int cpu = smp_processor_id();
 
-	list_for_each_entry(napi, &dev->napi_list, dev_list) {
+	list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) {
 		if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) {
 			poll_one_napi(napi);
 			smp_store_release(&napi->poll_owner, -1);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index cb15338cfda4..0168c700a201 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2733,7 +2733,8 @@ replay:
 			 */
 			if (err < 0) {
 				/* If device is not registered at all, free it now */
-				if (dev->reg_state == NETREG_UNINITIALIZED)
+				if (dev->reg_state == NETREG_UNINITIALIZED ||
+				    dev->reg_state == NETREG_UNREGISTERED)
 					free_netdev(dev);
 				goto out;
 			}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b1933e1f3aef..807edf1dbaf8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5053,8 +5053,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
 	skb = skb_share_check(skb, GFP_ATOMIC);
 	if (unlikely(!skb))
 		goto err_free;
-
-	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
+	/* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */
+	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short))))
 		goto err_free;
 
 	vhdr = (struct vlan_hdr *)skb->data;
@@ -5447,9 +5447,13 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off,
 	if (skb_has_frag_list(skb))
 		skb_clone_fraglist(skb);
 
-	if (k == 0) {
-		/* split line is in frag list */
-		pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask);
+	/* split line is in frag list */
+	if (k == 0 && pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask)) {
+		/* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */
+		if (skb_has_frag_list(skb))
+			kfree_skb_list(skb_shinfo(skb)->frag_list);
+		kfree(data);
+		return -ENOMEM;
 	}
 	skb_release_data(skb);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index d2cb2051d045..3b65fedf77ca 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1538,6 +1538,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		cgroup_sk_alloc(&sk->sk_cgrp_data);
 		sock_update_classid(&sk->sk_cgrp_data);
 		sock_update_netprioidx(&sk->sk_cgrp_data);
+		sk_tx_queue_clear(sk);
 	}
 
 	return sk;
@@ -1688,7 +1689,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		/* sk->sk_memcg will be populated at accept() time */
 		newsk->sk_memcg = NULL;
 
-		cgroup_sk_alloc(&newsk->sk_cgrp_data);
+		cgroup_sk_clone(&newsk->sk_cgrp_data);
 
 		rcu_read_lock();
 		filter = rcu_dereference(sk->sk_filter);
@@ -1740,6 +1741,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		sk_refcnt_debug_inc(newsk);
 		sk_set_socket(newsk, NULL);
+		sk_tx_queue_clear(newsk);
 		newsk->sk_wq = NULL;
 
 		if (newsk->sk_prot->sockets_allocated)
@@ -2561,6 +2563,27 @@ int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *
 }
 EXPORT_SYMBOL(sock_no_mmap);
 
+/*
+ * When a file is received (via SCM_RIGHTS, etc), we must bump the
+ * various sock-based usage counts.
+ */
+void __receive_sock(struct file *file)
+{
+	struct socket *sock;
+	int error;
+
+	/*
+	 * The resulting value of "error" is ignored here since we only
+	 * need to take action when the file is a socket and testing
+	 * "sock" for NULL is sufficient.
+	 */
+	sock = sock_from_file(file, &error);
+	if (sock) {
+		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
+		sock_update_classid(&sock->sk->sk_cgrp_data);
+	}
+}
+
 ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
 {
 	ssize_t res;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 7d9cf26f4bb1..8279f463c69d 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -899,7 +899,14 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
 		   agents are active. Taking the first reply prevents
 		   arp trashing and chooses the fastest router.
 		 */
-		override = time_after(jiffies,
+		/*
+		 * If n->updated is after jiffies, then the clock has wrapped and
+		 * we are *well* past the locktime, so set the override flag
+		 */
+		if (time_after(n->updated, jiffies))
+			override = 1;
+		else
+			override = time_after(jiffies,
 				      n->updated +
 				      NEIGH_VAR(n->parms, LOCKTIME)) ||
 			   is_garp;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 096a28f9720d..d4d53aea2c60 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -262,6 +262,7 @@ static struct in_device *inetdev_init(struct net_device *dev)
 	err = devinet_sysctl_register(in_dev);
 	if (err) {
 		in_dev->dead = 1;
+		neigh_parms_release(&arp_tbl, in_dev->arp_parms);
 		in_dev_put(in_dev);
 		in_dev = NULL;
 		goto out;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index eff703cb13b6..bc233fdfae0f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -839,7 +839,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
 			if (fl4.flowi4_scope < RT_SCOPE_LINK)
 				fl4.flowi4_scope = RT_SCOPE_LINK;
 
-			if (cfg->fc_table)
+			if (cfg->fc_table && cfg->fc_table != RT_TABLE_MAIN)
 				tbl = fib_get_table(net, cfg->fc_table);
 
 			if (tbl)
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 3f9509679f0e..0c8fcc050ad2 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1729,7 +1729,7 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb)
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
 		struct key_vector *local_l = NULL, *local_tp;
 
-		hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+		hlist_for_each_entry(fa, &l->leaf, fa_list) {
 			struct fib_alias *new_fa;
 
 			if (local_tb->tb_id != fa->tb_id)
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 6a7d980105f6..095c30863745 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -19,12 +19,12 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {
 	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
+	bool need_csum, need_recompute_csum, gso_partial;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	u16 mac_offset = skb->mac_header;
 	__be16 protocol = skb->protocol;
 	u16 mac_len = skb->mac_len;
 	int gre_offset, outer_hlen;
-	bool need_csum, gso_partial;
 
 	if (!skb->encapsulation)
 		goto out;
@@ -45,6 +45,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	skb->protocol = skb->inner_protocol;
 
 	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM);
+	need_recompute_csum = skb->csum_not_inet;
 	skb->encap_hdr_csum = need_csum;
 
 	features &= skb->dev->hw_enc_features;
@@ -102,7 +103,15 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		}
 
 		*(pcsum + 1) = 0;
-		*pcsum = gso_make_checksum(skb, 0);
+		if (need_recompute_csum && !skb_is_gso(skb)) {
+			__wsum csum;
+
+			csum = skb_checksum(skb, gre_offset,
+					    skb->len - gre_offset, 0);
+			*pcsum = csum_fold(csum);
+		} else {
+			*pcsum = gso_make_checksum(skb, 0);
+		}
 	} while ((skb = skb->next));
 out:
 	return segs;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 7826fba34b14..08ba0f91f2ab 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -276,51 +276,12 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
 				    ipv6_only_sock(sk), true);
 }
 
-/* Obtain a reference to a local port for the given sock,
- * if snum is zero it means select any available local port.
- * We try to allocate an odd port (and leave even ports for connect())
- */
-int inet_csk_get_port(struct sock *sk, unsigned short snum)
+void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
+			       struct sock *sk)
 {
-	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
-	struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
-	int ret = 1, port = snum;
-	struct inet_bind_hashbucket *head;
-	struct net *net = sock_net(sk);
-	struct inet_bind_bucket *tb = NULL;
 	kuid_t uid = sock_i_uid(sk);
+	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
 
-	if (!port) {
-		head = inet_csk_find_open_port(sk, &tb, &port);
-		if (!head)
-			return ret;
-		if (!tb)
-			goto tb_not_found;
-		goto success;
-	}
-	head = &hinfo->bhash[inet_bhashfn(net, port,
-					  hinfo->bhash_size)];
-	spin_lock_bh(&head->lock);
-	inet_bind_bucket_for_each(tb, &head->chain)
-		if (net_eq(ib_net(tb), net) && tb->port == port)
-			goto tb_found;
-tb_not_found:
-	tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
-				     net, head, port);
-	if (!tb)
-		goto fail_unlock;
-tb_found:
-	if (!hlist_empty(&tb->owners)) {
-		if (sk->sk_reuse == SK_FORCE_REUSE)
-			goto success;
-
-		if ((tb->fastreuse > 0 && reuse) ||
-		    sk_reuseport_match(tb, sk))
-			goto success;
-		if (inet_csk_bind_conflict(sk, tb, true, true))
-			goto fail_unlock;
-	}
-success:
 	if (hlist_empty(&tb->owners)) {
 		tb->fastreuse = reuse;
 		if (sk->sk_reuseport) {
@@ -364,6 +325,54 @@ success:
 			tb->fastreuseport = 0;
 		}
 	}
+}
+
+/* Obtain a reference to a local port for the given sock,
+ * if snum is zero it means select any available local port.
+ * We try to allocate an odd port (and leave even ports for connect())
+ */
+int inet_csk_get_port(struct sock *sk, unsigned short snum)
+{
+	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
+	struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
+	int ret = 1, port = snum;
+	struct inet_bind_hashbucket *head;
+	struct net *net = sock_net(sk);
+	struct inet_bind_bucket *tb = NULL;
+
+	if (!port) {
+		head = inet_csk_find_open_port(sk, &tb, &port);
+		if (!head)
+			return ret;
+		if (!tb)
+			goto tb_not_found;
+		goto success;
+	}
+	head = &hinfo->bhash[inet_bhashfn(net, port,
+					  hinfo->bhash_size)];
+	spin_lock_bh(&head->lock);
+	inet_bind_bucket_for_each(tb, &head->chain)
+		if (net_eq(ib_net(tb), net) && tb->port == port)
+			goto tb_found;
+tb_not_found:
+	tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
+				     net, head, port);
+	if (!tb)
+		goto fail_unlock;
+tb_found:
+	if (!hlist_empty(&tb->owners)) {
+		if (sk->sk_reuse == SK_FORCE_REUSE)
+			goto success;
+
+		if ((tb->fastreuse > 0 && reuse) ||
+		    sk_reuseport_match(tb, sk))
+			goto success;
+		if (inet_csk_bind_conflict(sk, tb, true, true))
+			goto fail_unlock;
+	}
+success:
+	inet_csk_update_fastreuse(tb, sk);
+
 	if (!inet_csk(sk)->icsk_bind_hash)
 		inet_bind_hash(sk, tb, port);
 	WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 0af13f5bdc9a..8a54babf5c90 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -160,6 +160,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
 				return -ENOMEM;
 			}
 		}
+		inet_csk_update_fastreuse(tb, child);
 	}
 	inet_bind_hash(child, tb, port);
 	spin_unlock(&head->lock);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 73cd64c7692f..819d51101cbd 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -73,6 +73,7 @@
 #include <net/icmp.h>
 #include <net/checksum.h>
 #include <net/inetpeer.h>
+#include <net/inet_ecn.h>
 #include <net/lwtunnel.h>
 #include <linux/bpf-cgroup.h>
 #include <linux/igmp.h>
@@ -1562,7 +1563,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	if (IS_ERR(rt))
 		return;
 
-	inet_sk(sk)->tos = arg->tos;
+	inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK;
 
 	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index f6793017a20d..44cc17c43a6b 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -98,9 +98,10 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 				   __be32 remote, __be32 local,
 				   __be32 key)
 {
-	unsigned int hash;
 	struct ip_tunnel *t, *cand = NULL;
 	struct hlist_head *head;
+	struct net_device *ndev;
+	unsigned int hash;
 
 	hash = ip_tunnel_hash(key, remote);
 	head = &itn->tunnels[hash];
@@ -175,8 +176,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 	if (t && t->dev->flags & IFF_UP)
 		return t;
 
-	if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)
-		return netdev_priv(itn->fb_tunnel_dev);
+	ndev = READ_ONCE(itn->fb_tunnel_dev);
+	if (ndev && ndev->flags & IFF_UP)
+		return netdev_priv(ndev);
 
 	return NULL;
 }
@@ -1211,9 +1213,9 @@ void ip_tunnel_uninit(struct net_device *dev)
 	struct ip_tunnel_net *itn;
 
 	itn = net_generic(net, tunnel->ip_tnl_net_id);
-	/* fb_tunnel_dev will be unregisted in net-exit call. */
-	if (itn->fb_tunnel_dev != dev)
-		ip_tunnel_del(itn, netdev_priv(dev));
+	ip_tunnel_del(itn, netdev_priv(dev));
+	if (itn->fb_tunnel_dev == dev)
+		WRITE_ONCE(itn->fb_tunnel_dev, NULL);
 
 	dst_cache_reset(&tunnel->dst_cache);
 }
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index c1693d75e196..33a85269a9f2 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -50,7 +50,7 @@ static unsigned int vti_net_id __read_mostly;
 static int vti_tunnel_init(struct net_device *dev);
 
 static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
-		     int encap_type)
+		     int encap_type, bool update_skb_dev)
 {
 	struct ip_tunnel *tunnel;
 	const struct iphdr *iph = ip_hdr(skb);
@@ -65,6 +65,9 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
 
 		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
 
+		if (update_skb_dev)
+			skb->dev = tunnel->dev;
+
 		return xfrm_input(skb, nexthdr, spi, encap_type);
 	}
 
@@ -74,25 +77,43 @@ drop:
 	return 0;
 }
 
-static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi,
-		     int encap_type)
+static int vti_input_proto(struct sk_buff *skb, int nexthdr, __be32 spi,
+			   int encap_type)
 {
-	struct ip_tunnel *tunnel;
+	return vti_input(skb, nexthdr, spi, encap_type, false);
+}
+
+static int vti_rcv(struct sk_buff *skb, __be32 spi, bool update_skb_dev)
+{
+	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+	return vti_input(skb, ip_hdr(skb)->protocol, spi, 0, update_skb_dev);
+}
+
+static int vti_rcv_proto(struct sk_buff *skb)
+{
+	return vti_rcv(skb, 0, false);
+}
+
+static int vti_rcv_tunnel(struct sk_buff *skb)
+{
+	struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id);
 	const struct iphdr *iph = ip_hdr(skb);
-	struct net *net = dev_net(skb->dev);
-	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+	struct ip_tunnel *tunnel;
 
 	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 				  iph->saddr, iph->daddr, 0);
 	if (tunnel) {
+		struct tnl_ptk_info tpi = {
+			.proto = htons(ETH_P_IP),
+		};
+
 		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 			goto drop;
-
-		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
-
-		skb->dev = tunnel->dev;
-
-		return xfrm_input(skb, nexthdr, spi, encap_type);
+		if (iptunnel_pull_header(skb, 0, tpi.proto, false))
+			goto drop;
+		return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false);
 	}
 
 	return -EINVAL;
@@ -101,22 +122,6 @@ drop:
 	return 0;
 }
 
-static int vti_rcv(struct sk_buff *skb)
-{
-	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
-	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
-
-	return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
-}
-
-static int vti_rcv_ipip(struct sk_buff *skb)
-{
-	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
-	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
-
-	return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0);
-}
-
 static int vti_rcv_cb(struct sk_buff *skb, int err)
 {
 	unsigned short family;
@@ -482,31 +487,31 @@ static void __net_init vti_fb_tunnel_init(struct net_device *dev)
 }
 
 static struct xfrm4_protocol vti_esp4_protocol __read_mostly = {
-	.handler	=	vti_rcv,
-	.input_handler	=	vti_input,
+	.handler	=	vti_rcv_proto,
+	.input_handler	=	vti_input_proto,
 	.cb_handler	=	vti_rcv_cb,
 	.err_handler	=	vti4_err,
 	.priority	=	100,
 };
 
 static struct xfrm4_protocol vti_ah4_protocol __read_mostly = {
-	.handler	=	vti_rcv,
-	.input_handler	=	vti_input,
+	.handler	=	vti_rcv_proto,
+	.input_handler	=	vti_input_proto,
 	.cb_handler	=	vti_rcv_cb,
 	.err_handler	=	vti4_err,
 	.priority	=	100,
 };
 
 static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
-	.handler	=	vti_rcv,
-	.input_handler	=	vti_input,
+	.handler	=	vti_rcv_proto,
+	.input_handler	=	vti_input_proto,
 	.cb_handler	=	vti_rcv_cb,
 	.err_handler	=	vti4_err,
 	.priority	=	100,
 };
 
 static struct xfrm_tunnel ipip_handler __read_mostly = {
-	.handler	=	vti_rcv_ipip,
+	.handler	=	vti_rcv_tunnel,
 	.err_handler	=	vti4_err,
 	.priority	=	0,
 };
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index cdd627355ed1..df610245d21a 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -702,7 +702,7 @@ out:
 
 rtnl_link_failed:
 #if IS_ENABLED(CONFIG_MPLS)
-	xfrm4_tunnel_deregister(&mplsip_handler, AF_INET);
+	xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
 xfrm_tunnel_mplsip_failed:
 
 #endif
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 8a69363b4884..c66103de86bd 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -165,8 +165,7 @@ pptp_outbound_pkt(struct sk_buff *skb,
 		break;
 	default:
 		pr_debug("unknown outbound packet 0x%04x:%s\n", msg,
-			 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
-					       pptp_msg_name[0]);
+			 pptp_msg_name(msg));
 		/* fall through */
 	case PPTP_SET_LINK_INFO:
 		/* only need to NAT in case PAC is behind NAT box */
@@ -267,9 +266,7 @@ pptp_inbound_pkt(struct sk_buff *skb,
 		pcid_off = offsetof(union pptp_ctrl_union, setlink.peersCallID);
 		break;
 	default:
-		pr_debug("unknown inbound packet %s\n",
-			 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
-					       pptp_msg_name[0]);
+		pr_debug("unknown inbound packet %s\n", pptp_msg_name(msg));
 		/* fall through */
 	case PPTP_START_SESSION_REQUEST:
 	case PPTP_START_SESSION_REPLY:
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 16226d49263d..186fdf0922d2 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -801,6 +801,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
 			   sk->sk_uid);
 
+	fl4.fl4_icmp_type = user_icmph.type;
+	fl4.fl4_icmp_code = user_icmph.code;
+
 	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 967acf2844ef..6fcb12e083d9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -276,6 +276,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		*pos = cpu+1;
 		return &per_cpu(rt_cache_stat, cpu);
 	}
+	(*pos)++;
 	return NULL;
 
 }
@@ -499,18 +500,16 @@ u32 ip_idents_reserve(u32 hash, int segs)
 	atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
 	u32 old = ACCESS_ONCE(*p_tstamp);
 	u32 now = (u32)jiffies;
-	u32 new, delta = 0;
+	u32 delta = 0;
 
 	if (old != now && cmpxchg(p_tstamp, old, now) == old)
 		delta = prandom_u32_max(now - old);
 
-	/* Do not use atomic_add_return() as it makes UBSAN unhappy */
-	do {
-		old = (u32)atomic_read(p_id);
-		new = old + delta + segs;
-	} while (atomic_cmpxchg(p_id, old, new) != old);
-
-	return new - segs;
+	/* If UBSAN reports an error there, please make sure your compiler
+	 * supports -fno-strict-overflow before reporting it that was a bug
+	 * in UBSAN, and it has been fixed in GCC-8.
+	 */
+	return atomic_add_return(segs + delta, p_id) - segs;
 }
 EXPORT_SYMBOL(ip_idents_reserve);
 
@@ -796,6 +795,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			if (fib_lookup(net, fl4, &res, 0) == 0) {
 				struct fib_nh *nh = &FIB_RES_NH(res);
 
+				fib_select_path(net, &res, fl4, skb);
+				nh = &FIB_RES_NH(res);
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
 						0, false,
 						jiffies + ip_rt_gc_timeout);
@@ -1012,6 +1013,7 @@ out:	kfree_skb(skb);
 static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 {
 	struct dst_entry *dst = &rt->dst;
+	struct net *net = dev_net(dst->dev);
 	u32 old_mtu = ipv4_mtu(dst);
 	struct fib_result res;
 	bool lock = false;
@@ -1032,9 +1034,11 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 		return;
 
 	rcu_read_lock();
-	if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
-		struct fib_nh *nh = &FIB_RES_NH(res);
+	if (fib_lookup(net, fl4, &res, 0) == 0) {
+		struct fib_nh *nh;
 
+		fib_select_path(net, &res, fl4, NULL);
+		nh = &FIB_RES_NH(res);
 		update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock,
 				      jiffies + ip_rt_mtu_expires);
 	}
@@ -2507,8 +2511,6 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
 	fib_select_path(net, res, fl4, skb);
 
 	dev_out = FIB_RES_DEV(*res);
-	fl4->flowi4_oif = dev_out->ifindex;
-
 
 make_route:
 	rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6fbfdd5e96de..c9f6f28e54f3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2366,6 +2366,9 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
 	tp->delivered = 0;
+	if (icsk->icsk_ca_ops->release)
+		icsk->icsk_ca_ops->release(sk);
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
@@ -2759,10 +2762,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 #ifdef CONFIG_TCP_MD5SIG
 	case TCP_MD5SIG:
 	case TCP_MD5SIG_EXT:
-		if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
-			err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
-		else
-			err = -EINVAL;
+		err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
 		break;
 #endif
 	case TCP_USER_TIMEOUT:
@@ -3394,10 +3394,13 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data);
 
 int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
 {
+	u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */
 	struct scatterlist sg;
 
-	sg_init_one(&sg, key->key, key->keylen);
-	ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen);
+	sg_init_one(&sg, key->key, keylen);
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
+
+	/* tcp_md5_do_add() might change key->key under us */
 	return crypto_ahash_update(hp->md5_req);
 }
 EXPORT_SYMBOL(tcp_md5_hash_key);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 494e3c3a21a1..755151e95f49 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -199,7 +199,7 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	icsk->icsk_ca_setsockopt = 1;
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	if (sk->sk_state != TCP_CLOSE)
+	if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		tcp_init_congestion_control(sk);
 }
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 78bfadfcf342..8b5ba0a5cd38 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -403,6 +403,8 @@ static void hystart_update(struct sock *sk, u32 delay)
 
 	if (hystart_detect & HYSTART_DELAY) {
 		/* obtain the minimum delay of more than sampling packets */
+		if (ca->curr_rtt > delay)
+			ca->curr_rtt = delay;
 		if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
 			if (ca->curr_rtt == 0 || ca->curr_rtt > delay)
 				ca->curr_rtt = delay;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 29f3df4ddd1f..83d03340417a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3516,10 +3516,8 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
 	}
 }
 
-/* This routine deals with acks during a TLP episode.
- * We mark the end of a TLP episode on receiving TLP dupack or when
- * ack is after tlp_high_seq.
- * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
+/* This routine deals with acks during a TLP episode and ends an episode by
+ * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack
  */
 static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 {
@@ -3528,7 +3526,10 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 	if (before(ack, tp->tlp_high_seq))
 		return;
 
-	if (flag & FLAG_DSACKING_ACK) {
+	if (!tp->tlp_retrans) {
+		/* TLP of new data has been acknowledged */
+		tp->tlp_high_seq = 0;
+	} else if (flag & FLAG_DSACKING_ACK) {
 		/* This DSACK means original and TLP probe arrived; no loss */
 		tp->tlp_high_seq = 0;
 	} else if (after(ack, tp->tlp_high_seq)) {
@@ -4507,7 +4508,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
 				 skb, &fragstolen)) {
 coalesce_done:
-		tcp_grow_window(sk, skb);
+		/* For non sack flows, do not grow window to force DUPACK
+		 * and trigger fast retransmit.
+		 */
+		if (tcp_is_sack(tp))
+			tcp_grow_window(sk, skb);
 		kfree_skb_partial(skb, fragstolen);
 		skb = NULL;
 		goto add_sack;
@@ -4591,7 +4596,11 @@ add_sack:
 		tcp_sack_new_ofo_skb(sk, seq, end_seq);
 end:
 	if (skb) {
-		tcp_grow_window(sk, skb);
+		/* For non sack flows, do not grow window to force DUPACK
+		 * and trigger fast retransmit.
+		 */
+		if (tcp_is_sack(tp))
+			tcp_grow_window(sk, skb);
 		skb_condense(skb);
 		skb_set_owner_r(skb, sk);
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b4f0fc34b0ed..d01c34e95016 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -995,9 +995,18 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 
 	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen);
 	if (key) {
-		/* Pre-existing entry - just update that one. */
+		/* Pre-existing entry - just update that one.
+		 * Note that the key might be used concurrently.
+		 */
 		memcpy(key->key, newkey, newkeylen);
-		key->keylen = newkeylen;
+
+		/* Pairs with READ_ONCE() in tcp_md5_hash_key().
+		 * Also note that a reader could catch new key->keylen value
+		 * but old key->key[], this is the reason we use __GFP_ZERO
+		 * at sock_kmalloc() time below these lines.
+		 */
+		WRITE_ONCE(key->keylen, newkeylen);
+
 		return 0;
 	}
 
@@ -1013,7 +1022,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 		rcu_assign_pointer(tp->md5sig_info, md5sig);
 	}
 
-	key = sock_kmalloc(sk, sizeof(*key), gfp);
+	key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO);
 	if (!key)
 		return -ENOMEM;
 	if (!tcp_alloc_md5sig_pool()) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e1eb56e21dd5..355ebae883c1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -616,7 +616,8 @@ static unsigned int tcp_synack_options(struct request_sock *req,
 				       unsigned int mss, struct sk_buff *skb,
 				       struct tcp_out_options *opts,
 				       const struct tcp_md5sig_key *md5,
-				       struct tcp_fastopen_cookie *foc)
+				       struct tcp_fastopen_cookie *foc,
+				       enum tcp_synack_type synack_type)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -631,7 +632,8 @@ static unsigned int tcp_synack_options(struct request_sock *req,
 		 * rather than TS in order to fit in better with old,
 		 * buggy kernels, but that was deemed to be unnecessary.
 		 */
-		ireq->tstamp_ok &= !ireq->sack_ok;
+		if (synack_type != TCP_SYNACK_COOKIE)
+			ireq->tstamp_ok &= !ireq->sack_ok;
 	}
 #endif
 
@@ -2498,6 +2500,11 @@ void tcp_send_loss_probe(struct sock *sk)
 	int pcount;
 	int mss = tcp_current_mss(sk);
 
+	/* At most one outstanding TLP */
+	if (tp->tlp_high_seq)
+		goto rearm_timer;
+
+	tp->tlp_retrans = 0;
 	skb = tcp_send_head(sk);
 	if (skb) {
 		if (tcp_snd_wnd_test(tp, skb, mss)) {
@@ -2520,10 +2527,6 @@ void tcp_send_loss_probe(struct sock *sk)
 		return;
 	}
 
-	/* At most one outstanding TLP retransmission. */
-	if (tp->tlp_high_seq)
-		goto rearm_timer;
-
 	if (skb_still_in_host_queue(sk, skb))
 		goto rearm_timer;
 
@@ -2544,10 +2547,12 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (__tcp_retransmit_skb(sk, skb, 1))
 		goto rearm_timer;
 
+	tp->tlp_retrans = 1;
+
+probe_sent:
 	/* Record snd_nxt for loss detection. */
 	tp->tlp_high_seq = tp->snd_nxt;
 
-probe_sent:
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
 	/* Reset s.t. tcp_rearm_rto will restart timer from now */
 	inet_csk(sk)->icsk_pending = 0;
@@ -3252,8 +3257,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
 #endif
 	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
-	tcp_header_size = tcp_synack_options(req, mss, skb, &opts, md5, foc) +
-			  sizeof(*th);
+	tcp_header_size = tcp_synack_options(req, mss, skb, &opts, md5,
+					     foc, synack_type) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e33258d69246..f335dd4c84e2 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1894,7 +1894,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	/*
 	 * 	UDP-Lite specific tests, ignored on UDP sockets
 	 */
-	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
+	if ((up->pcflag & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
 
 		/*
 		 * MIB statistics other than incrementing the error count are
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 2d36fd097299..a941f09a3fce 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -321,6 +321,7 @@ config IPV6_SEG6_LWTUNNEL
 config IPV6_SEG6_HMAC
 	bool "IPv6: Segment Routing HMAC support"
 	depends on IPV6
+	select CRYPTO
 	select CRYPTO_HMAC
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 0bbab8a4b5d8..4d8b3d1d530b 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -170,7 +170,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	return 0;
 }
 
-void ipv6_sock_ac_close(struct sock *sk)
+void __ipv6_sock_ac_close(struct sock *sk)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net_device *dev = NULL;
@@ -178,10 +178,7 @@ void ipv6_sock_ac_close(struct sock *sk)
 	struct net *net = sock_net(sk);
 	int	prev_index;
 
-	if (!np->ipv6_ac_list)
-		return;
-
-	rtnl_lock();
+	ASSERT_RTNL();
 	pac = np->ipv6_ac_list;
 	np->ipv6_ac_list = NULL;
 
@@ -198,6 +195,16 @@ void ipv6_sock_ac_close(struct sock *sk)
 		sock_kfree_s(sk, pac, sizeof(*pac));
 		pac = next;
 	}
+}
+
+void ipv6_sock_ac_close(struct sock *sk)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	if (!np->ipv6_ac_list)
+		return;
+	rtnl_lock();
+	__ipv6_sock_ac_close(sk);
 	rtnl_unlock();
 }
 
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index f52c314d4c97..a50d1943dd62 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -121,9 +121,16 @@ static void esp6_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
 	struct ip_esp_hdr *esph;
 	struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct xfrm_offload *xo = xfrm_offload(skb);
-	int proto = iph->nexthdr;
+	u8 proto = iph->nexthdr;
 
 	skb_push(skb, -skb_network_offset(skb));
+
+	if (x->outer_mode->encap == XFRM_MODE_TRANSPORT) {
+		__be16 frag;
+
+		ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &proto, &frag);
+	}
+
 	esph = ip_esp_hdr(skb);
 	*skb_mac_header(skb) = IPPROTO_ESP;
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 726ba41133a3..802457c0a121 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -124,6 +124,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 	int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
 		       ARPHRD_ETHER : ARPHRD_IP6GRE;
 	int score, cand_score = 4;
+	struct net_device *ndev;
 
 	for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) {
 		if (!ipv6_addr_equal(local, &t->parms.laddr) ||
@@ -226,9 +227,9 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 	if (cand)
 		return cand;
 
-	dev = ign->fb_tunnel_dev;
-	if (dev->flags & IFF_UP)
-		return netdev_priv(dev);
+	ndev = READ_ONCE(ign->fb_tunnel_dev);
+	if (ndev && ndev->flags & IFF_UP)
+		return netdev_priv(ndev);
 
 	return NULL;
 }
@@ -364,6 +365,8 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 
 	ip6gre_tunnel_unlink(ign, t);
+	if (ign->fb_tunnel_dev == dev)
+		WRITE_ONCE(ign->fb_tunnel_dev, NULL);
 	dst_cache_reset(&t->dst_cache);
 	dev_put(dev);
 }
@@ -1166,15 +1169,16 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
 static int __net_init ip6gre_init_net(struct net *net)
 {
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	struct net_device *ndev;
 	int err;
 
-	ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0",
-					  NET_NAME_UNKNOWN,
-					  ip6gre_tunnel_setup);
-	if (!ign->fb_tunnel_dev) {
+	ndev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0",
+			    NET_NAME_UNKNOWN, ip6gre_tunnel_setup);
+	if (!ndev) {
 		err = -ENOMEM;
 		goto err_alloc_dev;
 	}
+	ign->fb_tunnel_dev = ndev;
 	dev_net_set(ign->fb_tunnel_dev, net);
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
@@ -1194,7 +1198,7 @@ static int __net_init ip6gre_init_net(struct net *net)
 	return 0;
 
 err_reg_dev:
-	free_netdev(ign->fb_tunnel_dev);
+	free_netdev(ndev);
 err_alloc_dev:
 	return err;
 }
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index c2644405bab1..2ffb4b8eca04 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -872,7 +872,15 @@ int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb,
 		struct metadata_dst *tun_dst,
 		bool log_ecn_err)
 {
-	return __ip6_tnl_rcv(t, skb, tpi, NULL, ip6ip6_dscp_ecn_decapsulate,
+	int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t,
+				    const struct ipv6hdr *ipv6h,
+				    struct sk_buff *skb);
+
+	dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate;
+	if (tpi->proto == htons(ETH_P_IP))
+		dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate;
+
+	return __ip6_tnl_rcv(t, skb, tpi, NULL, dscp_ecn_decapsulate,
 			     log_ecn_err);
 }
 EXPORT_SYMBOL(ip6_tnl_rcv);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 337b43d4c3eb..3f44316db51b 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -185,14 +185,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 					retv = -EBUSY;
 					break;
 				}
-			}
-			if (sk->sk_protocol == IPPROTO_TCP &&
-			    sk->sk_prot != &tcpv6_prot) {
-				retv = -EBUSY;
+			} else if (sk->sk_protocol == IPPROTO_TCP) {
+				if (sk->sk_prot != &tcpv6_prot) {
+					retv = -EBUSY;
+					break;
+				}
+			} else {
 				break;
 			}
-			if (sk->sk_protocol != IPPROTO_TCP)
-				break;
+
 			if (sk->sk_state != TCP_ESTABLISHED) {
 				retv = -ENOTCONN;
 				break;
@@ -206,6 +207,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 
 			fl6_free_socklist(sk);
 			__ipv6_sock_mc_close(sk);
+			__ipv6_sock_ac_close(sk);
 
 			/*
 			 * Sock is moving from IPv6 to IPv4 (sk_prot), so
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 611dc5d55fa0..959057515fc9 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2599,6 +2599,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev)
 		idev->mc_list = i->next;
 
 		write_unlock_bh(&idev->lock);
+		ip6_mc_clear_src(i);
 		ma_put(i);
 		write_lock_bh(&idev->lock);
 	}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index a2ba7356fa65..38ad3fac8c37 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -629,7 +629,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	/*
 	 * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c).
 	 */
-	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
+	if ((up->pcflag & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
 
 		if (up->pcrlen == 0) {          /* full coverage was set  */
 			net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n",
diff --git a/net/key/af_key.c b/net/key/af_key.c
index f8f7065f7b62..0747747fffe5 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1855,6 +1855,13 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms
 	if (ext_hdrs[SADB_X_EXT_FILTER - 1]) {
 		struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1];
 
+		if ((xfilter->sadb_x_filter_splen >=
+			(sizeof(xfrm_address_t) << 3)) ||
+		    (xfilter->sadb_x_filter_dplen >=
+			(sizeof(xfrm_address_t) << 3))) {
+			mutex_unlock(&pfk->dump_lock);
+			return -EINVAL;
+		}
 		filter = kmalloc(sizeof(*filter), GFP_KERNEL);
 		if (filter == NULL) {
 			mutex_unlock(&pfk->dump_lock);
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index c3f8bac32584..36512fbea130 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1141,6 +1141,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
 
 	/* Queue the packet to IP for output */
 	skb->ignore_df = 1;
+	skb_dst_drop(skb);
 #if IS_ENABLED(CONFIG_IPV6)
 	if (l2tp_sk_is_v6(tunnel->sock))
 		error = inet6_csk_xmit(tunnel->sock, skb, NULL);
@@ -1214,10 +1215,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 		goto out_unlock;
 	}
 
-	/* Get routing info from the tunnel socket */
-	skb_dst_drop(skb);
-	skb_dst_set(skb, sk_dst_check(sk, 0));
-
 	inet = inet_sk(sk);
 	fl = &inet->cork.fl;
 	switch (tunnel->encap) {
@@ -1589,6 +1586,8 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 			 tunnel_id, fd);
 		goto err;
 	}
+	if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6)
+		goto err;
 	switch (encap) {
 	case L2TP_ENCAPTYPE_UDP:
 		if (sk->sk_protocol != IPPROTO_UDP) {
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index f7880becc165..37a9f2a25263 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -24,7 +24,6 @@
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/inet_common.h>
-#include <net/inet_hashtables.h>
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
@@ -215,15 +214,31 @@ discard:
 	return 0;
 }
 
-static int l2tp_ip_open(struct sock *sk)
+static int l2tp_ip_hash(struct sock *sk)
 {
-	/* Prevent autobind. We don't have ports. */
-	inet_sk(sk)->inet_num = IPPROTO_L2TP;
+	if (sk_unhashed(sk)) {
+		write_lock_bh(&l2tp_ip_lock);
+		sk_add_node(sk, &l2tp_ip_table);
+		write_unlock_bh(&l2tp_ip_lock);
+	}
+	return 0;
+}
 
+static void l2tp_ip_unhash(struct sock *sk)
+{
+	if (sk_unhashed(sk))
+		return;
 	write_lock_bh(&l2tp_ip_lock);
-	sk_add_node(sk, &l2tp_ip_table);
+	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip_lock);
+}
+
+static int l2tp_ip_open(struct sock *sk)
+{
+	/* Prevent autobind. We don't have ports. */
+	inet_sk(sk)->inet_num = IPPROTO_L2TP;
 
+	l2tp_ip_hash(sk);
 	return 0;
 }
 
@@ -605,8 +620,8 @@ static struct proto l2tp_ip_prot = {
 	.sendmsg	   = l2tp_ip_sendmsg,
 	.recvmsg	   = l2tp_ip_recvmsg,
 	.backlog_rcv	   = l2tp_ip_backlog_recv,
-	.hash		   = inet_hash,
-	.unhash		   = inet_unhash,
+	.hash		   = l2tp_ip_hash,
+	.unhash		   = l2tp_ip_unhash,
 	.obj_size	   = sizeof(struct l2tp_ip_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ip_setsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 6efdfc9b5c43..9c4670fb29d7 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -24,8 +24,6 @@
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/inet_common.h>
-#include <net/inet_hashtables.h>
-#include <net/inet6_hashtables.h>
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
@@ -229,15 +227,31 @@ discard:
 	return 0;
 }
 
-static int l2tp_ip6_open(struct sock *sk)
+static int l2tp_ip6_hash(struct sock *sk)
 {
-	/* Prevent autobind. We don't have ports. */
-	inet_sk(sk)->inet_num = IPPROTO_L2TP;
+	if (sk_unhashed(sk)) {
+		write_lock_bh(&l2tp_ip6_lock);
+		sk_add_node(sk, &l2tp_ip6_table);
+		write_unlock_bh(&l2tp_ip6_lock);
+	}
+	return 0;
+}
 
+static void l2tp_ip6_unhash(struct sock *sk)
+{
+	if (sk_unhashed(sk))
+		return;
 	write_lock_bh(&l2tp_ip6_lock);
-	sk_add_node(sk, &l2tp_ip6_table);
+	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip6_lock);
+}
+
+static int l2tp_ip6_open(struct sock *sk)
+{
+	/* Prevent autobind. We don't have ports. */
+	inet_sk(sk)->inet_num = IPPROTO_L2TP;
 
+	l2tp_ip6_hash(sk);
 	return 0;
 }
 
@@ -742,8 +756,8 @@ static struct proto l2tp_ip6_prot = {
 	.sendmsg	   = l2tp_ip6_sendmsg,
 	.recvmsg	   = l2tp_ip6_recvmsg,
 	.backlog_rcv	   = l2tp_ip6_backlog_recv,
-	.hash		   = inet6_hash,
-	.unhash		   = inet_unhash,
+	.hash		   = l2tp_ip6_hash,
+	.unhash		   = l2tp_ip6_unhash,
 	.obj_size	   = sizeof(struct l2tp_ip6_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index d552e8819713..d301ac51bbe1 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -273,6 +273,10 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
 
 	if (!sock_flag(sk, SOCK_ZAPPED))
 		goto out;
+	if (!addr->sllc_arphrd)
+		addr->sllc_arphrd = ARPHRD_ETHER;
+	if (addr->sllc_arphrd != ARPHRD_ETHER)
+		goto out;
 	rc = -ENODEV;
 	if (sk->sk_bound_dev_if) {
 		llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
@@ -330,15 +334,15 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 	if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr)))
 		goto out;
 	rc = -EAFNOSUPPORT;
-	if (unlikely(addr->sllc_family != AF_LLC))
+	if (!addr->sllc_arphrd)
+		addr->sllc_arphrd = ARPHRD_ETHER;
+	if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER))
 		goto out;
 	rc = -ENODEV;
 	rcu_read_lock();
 	if (sk->sk_bound_dev_if) {
 		llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if);
 		if (llc->dev) {
-			if (!addr->sllc_arphrd)
-				addr->sllc_arphrd = llc->dev->type;
 			if (is_zero_ether_addr(addr->sllc_mac))
 				memcpy(addr->sllc_mac, llc->dev->dev_addr,
 				       IFHWADDRLEN);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index b1484b8316e8..c883cb67b731 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1997,6 +1997,7 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev)
 	ieee80211_stop_mesh(sdata);
 	mutex_lock(&sdata->local->mtx);
 	ieee80211_vif_release_channel(sdata);
+	kfree(sdata->u.mesh.ie);
 	mutex_unlock(&sdata->local->mtx);
 
 	return 0;
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index 986e9b6b961d..fe65701fe95c 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -1088,7 +1088,14 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata)
 	mesh_path_sel_frame_tx(MPATH_PREQ, 0, sdata->vif.addr, ifmsh->sn,
 			       target_flags, mpath->dst, mpath->sn, da, 0,
 			       ttl, lifetime, 0, ifmsh->preq_id++, sdata);
+
+	spin_lock_bh(&mpath->state_lock);
+	if (mpath->flags & MESH_PATH_DELETED) {
+		spin_unlock_bh(&mpath->state_lock);
+		goto enddiscovery;
+	}
 	mod_timer(&mpath->timer, jiffies + mpath->discovery_timeout);
+	spin_unlock_bh(&mpath->state_lock);
 
 enddiscovery:
 	rcu_read_unlock();
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index 130022091205..933f26e2ff8b 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -554,6 +554,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl,
 	del_timer_sync(&mpath->timer);
 	atomic_dec(&sdata->u.mesh.mpaths);
 	atomic_dec(&tbl->entries);
+	mesh_path_flush_pending(mpath);
 	kfree_rcu(mpath, rcu);
 }
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 56d7a3dfa543..04ae9de55d74 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2120,6 +2120,7 @@ static int ieee80211_802_1x_port_control(struct ieee80211_rx_data *rx)
 
 static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc)
 {
+	struct ieee80211_hdr *hdr = (void *)rx->skb->data;
 	struct sk_buff *skb = rx->skb;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 
@@ -2130,6 +2131,31 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc)
 	if (status->flag & RX_FLAG_DECRYPTED)
 		return 0;
 
+	/* check mesh EAPOL frames first */
+	if (unlikely(rx->sta && ieee80211_vif_is_mesh(&rx->sdata->vif) &&
+		     ieee80211_is_data(fc))) {
+		struct ieee80211s_hdr *mesh_hdr;
+		u16 hdr_len = ieee80211_hdrlen(fc);
+		u16 ethertype_offset;
+		__be16 ethertype;
+
+		if (!ether_addr_equal(hdr->addr1, rx->sdata->vif.addr))
+			goto drop_check;
+
+		/* make sure fixed part of mesh header is there, also checks skb len */
+		if (!pskb_may_pull(rx->skb, hdr_len + 6))
+			goto drop_check;
+
+		mesh_hdr = (struct ieee80211s_hdr *)(skb->data + hdr_len);
+		ethertype_offset = hdr_len + ieee80211_get_mesh_hdrlen(mesh_hdr) +
+				   sizeof(rfc1042_header);
+
+		if (skb_copy_bits(rx->skb, ethertype_offset, &ethertype, 2) == 0 &&
+		    ethertype == rx->sdata->control_port_protocol)
+			return 0;
+	}
+
+drop_check:
 	/* Drop unencrypted frames if key is set. */
 	if (unlikely(!ieee80211_has_protected(fc) &&
 		     !ieee80211_is_any_nullfunc(fc) &&
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 77ab9cc1a230..6af5fda6461c 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -952,7 +952,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
 	might_sleep();
 	lockdep_assert_held(&local->sta_mtx);
 
-	while (sta->sta_state == IEEE80211_STA_AUTHORIZED) {
+	if (sta->sta_state == IEEE80211_STA_AUTHORIZED) {
 		ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
 		WARN_ON_ONCE(ret);
 	}
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index 19ec2189d3ac..502b3fbb3b0f 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -170,10 +170,7 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 	/* take some capabilities as-is */
 	cap_info = le32_to_cpu(vht_cap_ie->vht_cap_info);
 	vht_cap->cap = cap_info;
-	vht_cap->cap &= IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 |
-			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 |
-			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 |
-			IEEE80211_VHT_CAP_RXLDPC |
+	vht_cap->cap &= IEEE80211_VHT_CAP_RXLDPC |
 			IEEE80211_VHT_CAP_VHT_TXOP_PS |
 			IEEE80211_VHT_CAP_HTC_VHT |
 			IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK |
@@ -182,6 +179,9 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 			IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN |
 			IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN;
 
+	vht_cap->cap |= min_t(u32, cap_info & IEEE80211_VHT_CAP_MAX_MPDU_MASK,
+			      own_cap.cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK);
+
 	/* and some based on our own capabilities */
 	switch (own_cap.cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) {
 	case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ:
diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
index bcd1a5e6ebf4..2f873a0dc583 100644
--- a/net/mac802154/tx.c
+++ b/net/mac802154/tx.c
@@ -42,11 +42,11 @@ void ieee802154_xmit_worker(struct work_struct *work)
 	if (res)
 		goto err_tx;
 
-	ieee802154_xmit_complete(&local->hw, skb, false);
-
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
 
+	ieee802154_xmit_complete(&local->hw, skb, false);
+
 	return;
 
 err_tx:
@@ -86,6 +86,8 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb)
 
 	/* async is priority, otherwise sync is fallback */
 	if (local->ops->xmit_async) {
+		unsigned int len = skb->len;
+
 		ret = drv_xmit_async(local, skb);
 		if (ret) {
 			ieee802154_wake_queue(&local->hw);
@@ -93,7 +95,7 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb)
 		}
 
 		dev->stats.tx_packets++;
-		dev->stats.tx_bytes += skb->len;
+		dev->stats.tx_bytes += len;
 	} else {
 		local->tx_skb = skb;
 		queue_work(local->workqueue, &local->tx_work);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index c2b21c9c1229..5c59bbad8d19 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -381,6 +381,8 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len,
 	for (id = 0; id < IPSET_EXT_ID_MAX; id++) {
 		if (!add_extension(id, cadt_flags, tb))
 			continue;
+		if (align < ip_set_extensions[id].align)
+			align = ip_set_extensions[id].align;
 		len = ALIGN(len, ip_set_extensions[id].align);
 		set->offset[id] = len;
 		set->extensions |= ip_set_extensions[id].type;
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index e563921e6af5..6ebd63a5d8ba 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -61,7 +61,7 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
 	/* Don't lookup sub-counters at all */
 	opt->cmdflags &= ~IPSET_FLAG_MATCH_COUNTERS;
 	if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE)
-		opt->cmdflags &= ~IPSET_FLAG_SKIP_COUNTER_UPDATE;
+		opt->cmdflags |= IPSET_FLAG_SKIP_COUNTER_UPDATE;
 	list_for_each_entry_rcu(e, &map->members, list) {
 		if (SET_WITH_TIMEOUT(set) &&
 		    ip_set_timeout_expired(ext_timeout(e, set)))
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 2156571455db..a95fe5fe9f04 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1916,14 +1916,14 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 
 	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
 	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
-		bool uses_ct = false, resched = false;
+		bool old_ct = false, resched = false;
 
 		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
 		    unlikely(!atomic_read(&cp->dest->weight))) {
 			resched = true;
-			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
 		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
-			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
 			if (!atomic_read(&cp->n_control)) {
 				resched = true;
 			} else {
@@ -1931,15 +1931,17 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 				 * that uses conntrack while it is still
 				 * referenced by controlled connection(s).
 				 */
-				resched = !uses_ct;
+				resched = !old_ct;
 			}
 		}
 
 		if (resched) {
+			if (!old_ct)
+				cp->flags &= ~IP_VS_CONN_F_NFCT;
 			if (!atomic_read(&cp->n_control))
 				ip_vs_conn_expire_now(cp);
 			__ip_vs_conn_put(cp);
-			if (uses_ct)
+			if (old_ct)
 				return NF_DROP;
 			cp = NULL;
 		}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index b373e053ff9a..90261055062e 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1726,6 +1726,8 @@ static int sync_thread_backup(void *data)
 {
 	struct ip_vs_sync_thread_data *tinfo = data;
 	struct netns_ipvs *ipvs = tinfo->ipvs;
+	struct sock *sk = tinfo->sock->sk;
+	struct udp_sock *up = udp_sk(sk);
 	int len;
 
 	pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, "
@@ -1733,12 +1735,14 @@ static int sync_thread_backup(void *data)
 		ipvs->bcfg.mcast_ifn, ipvs->bcfg.syncid, tinfo->id);
 
 	while (!kthread_should_stop()) {
-		wait_event_interruptible(*sk_sleep(tinfo->sock->sk),
-			 !skb_queue_empty(&tinfo->sock->sk->sk_receive_queue)
-			 || kthread_should_stop());
+		wait_event_interruptible(*sk_sleep(sk),
+					 !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
+					 !skb_queue_empty_lockless(&up->reader_queue) ||
+					 kthread_should_stop());
 
 		/* do we have data now? */
-		while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) {
+		while (!skb_queue_empty_lockless(&sk->sk_receive_queue) ||
+		       !skb_queue_empty_lockless(&up->reader_queue)) {
 			len = ip_vs_receive(tinfo->sock, tinfo->buf,
 					ipvs->bcfg.sync_maxlen);
 			if (len <= 0) {
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 39a32edaa92c..a83147f701da 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1043,6 +1043,8 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[],
 	if (!tb[CTA_TUPLE_IP])
 		return -EINVAL;
 
+	if (l3num != NFPROTO_IPV4 && l3num != NFPROTO_IPV6)
+		return -EOPNOTSUPP;
 	tuple->src.l3num = l3num;
 
 	err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple);
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index 11562f2a08bb..203107ce2455 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -71,24 +71,32 @@ EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_expectfn);
 
 #if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
 /* PptpControlMessageType names */
-const char *const pptp_msg_name[] = {
-	"UNKNOWN_MESSAGE",
-	"START_SESSION_REQUEST",
-	"START_SESSION_REPLY",
-	"STOP_SESSION_REQUEST",
-	"STOP_SESSION_REPLY",
-	"ECHO_REQUEST",
-	"ECHO_REPLY",
-	"OUT_CALL_REQUEST",
-	"OUT_CALL_REPLY",
-	"IN_CALL_REQUEST",
-	"IN_CALL_REPLY",
-	"IN_CALL_CONNECT",
-	"CALL_CLEAR_REQUEST",
-	"CALL_DISCONNECT_NOTIFY",
-	"WAN_ERROR_NOTIFY",
-	"SET_LINK_INFO"
+static const char *const pptp_msg_name_array[PPTP_MSG_MAX + 1] = {
+	[0]				= "UNKNOWN_MESSAGE",
+	[PPTP_START_SESSION_REQUEST]	= "START_SESSION_REQUEST",
+	[PPTP_START_SESSION_REPLY]	= "START_SESSION_REPLY",
+	[PPTP_STOP_SESSION_REQUEST]	= "STOP_SESSION_REQUEST",
+	[PPTP_STOP_SESSION_REPLY]	= "STOP_SESSION_REPLY",
+	[PPTP_ECHO_REQUEST]		= "ECHO_REQUEST",
+	[PPTP_ECHO_REPLY]		= "ECHO_REPLY",
+	[PPTP_OUT_CALL_REQUEST]		= "OUT_CALL_REQUEST",
+	[PPTP_OUT_CALL_REPLY]		= "OUT_CALL_REPLY",
+	[PPTP_IN_CALL_REQUEST]		= "IN_CALL_REQUEST",
+	[PPTP_IN_CALL_REPLY]		= "IN_CALL_REPLY",
+	[PPTP_IN_CALL_CONNECT]		= "IN_CALL_CONNECT",
+	[PPTP_CALL_CLEAR_REQUEST]	= "CALL_CLEAR_REQUEST",
+	[PPTP_CALL_DISCONNECT_NOTIFY]	= "CALL_DISCONNECT_NOTIFY",
+	[PPTP_WAN_ERROR_NOTIFY]		= "WAN_ERROR_NOTIFY",
+	[PPTP_SET_LINK_INFO]		= "SET_LINK_INFO"
 };
+
+const char *pptp_msg_name(u_int16_t msg)
+{
+	if (msg > PPTP_MSG_MAX)
+		return pptp_msg_name_array[0];
+
+	return pptp_msg_name_array[msg];
+}
 EXPORT_SYMBOL(pptp_msg_name);
 #endif
 
@@ -275,7 +283,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 	typeof(nf_nat_pptp_hook_inbound) nf_nat_pptp_inbound;
 
 	msg = ntohs(ctlh->messageType);
-	pr_debug("inbound control message %s\n", pptp_msg_name[msg]);
+	pr_debug("inbound control message %s\n", pptp_msg_name(msg));
 
 	switch (msg) {
 	case PPTP_START_SESSION_REPLY:
@@ -310,7 +318,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		pcid = pptpReq->ocack.peersCallID;
 		if (info->pns_call_id != pcid)
 			goto invalid;
-		pr_debug("%s, CID=%X, PCID=%X\n", pptp_msg_name[msg],
+		pr_debug("%s, CID=%X, PCID=%X\n", pptp_msg_name(msg),
 			 ntohs(cid), ntohs(pcid));
 
 		if (pptpReq->ocack.resultCode == PPTP_OUTCALL_CONNECT) {
@@ -327,7 +335,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 			goto invalid;
 
 		cid = pptpReq->icreq.callID;
-		pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid));
+		pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid));
 		info->cstate = PPTP_CALL_IN_REQ;
 		info->pac_call_id = cid;
 		break;
@@ -346,7 +354,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		if (info->pns_call_id != pcid)
 			goto invalid;
 
-		pr_debug("%s, PCID=%X\n", pptp_msg_name[msg], ntohs(pcid));
+		pr_debug("%s, PCID=%X\n", pptp_msg_name(msg), ntohs(pcid));
 		info->cstate = PPTP_CALL_IN_CONF;
 
 		/* we expect a GRE connection from PAC to PNS */
@@ -356,7 +364,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 	case PPTP_CALL_DISCONNECT_NOTIFY:
 		/* server confirms disconnect */
 		cid = pptpReq->disc.callID;
-		pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid));
+		pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid));
 		info->cstate = PPTP_CALL_NONE;
 
 		/* untrack this call id, unexpect GRE packets */
@@ -383,7 +391,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 invalid:
 	pr_debug("invalid %s: type=%d cid=%u pcid=%u "
 		 "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n",
-		 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0],
+		 pptp_msg_name(msg),
 		 msg, ntohs(cid), ntohs(pcid),  info->cstate, info->sstate,
 		 ntohs(info->pns_call_id), ntohs(info->pac_call_id));
 	return NF_ACCEPT;
@@ -403,7 +411,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 	typeof(nf_nat_pptp_hook_outbound) nf_nat_pptp_outbound;
 
 	msg = ntohs(ctlh->messageType);
-	pr_debug("outbound control message %s\n", pptp_msg_name[msg]);
+	pr_debug("outbound control message %s\n", pptp_msg_name(msg));
 
 	switch (msg) {
 	case PPTP_START_SESSION_REQUEST:
@@ -425,7 +433,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		info->cstate = PPTP_CALL_OUT_REQ;
 		/* track PNS call id */
 		cid = pptpReq->ocreq.callID;
-		pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid));
+		pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid));
 		info->pns_call_id = cid;
 		break;
 
@@ -439,7 +447,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		pcid = pptpReq->icack.peersCallID;
 		if (info->pac_call_id != pcid)
 			goto invalid;
-		pr_debug("%s, CID=%X PCID=%X\n", pptp_msg_name[msg],
+		pr_debug("%s, CID=%X PCID=%X\n", pptp_msg_name(msg),
 			 ntohs(cid), ntohs(pcid));
 
 		if (pptpReq->icack.resultCode == PPTP_INCALL_ACCEPT) {
@@ -479,7 +487,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 invalid:
 	pr_debug("invalid %s: type=%d cid=%u pcid=%u "
 		 "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n",
-		 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0],
+		 pptp_msg_name(msg),
 		 msg, ntohs(cid), ntohs(pcid),  info->cstate, info->sstate,
 		 ntohs(info->pns_call_id), ntohs(info->pac_call_id));
 	return NF_ACCEPT;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 5b8d5bfeb7ac..7c95314f0b7d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2882,7 +2882,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 			goto nla_put_failure;
 	}
 
-	if (nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata))
+	if (set->udata &&
+	    nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata))
 		goto nla_put_failure;
 
 	desc = nla_nest_start(skb, NFTA_SET_DESC);
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index dd1030f5dd5e..dfe4e6787219 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -106,7 +106,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 	if (help->helper->data_len == 0)
 		return -EINVAL;
 
-	nla_memcpy(help->data, nla_data(attr), sizeof(help->data));
+	nla_memcpy(help->data, attr, sizeof(help->data));
 	return 0;
 }
 
@@ -240,6 +240,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
 		ret = -ENOMEM;
 		goto err2;
 	}
+	helper->data_len = size;
 
 	helper->flags |= NF_CT_HELPER_F_USERSPACE;
 	memcpy(&helper->tuple, tuple, sizeof(struct nf_conntrack_tuple));
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index ed548d06b6dd..a18cceecef88 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -135,7 +135,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		priv->type = NF_NAT_MANIP_DST;
 		break;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	if (tb[NFTA_NAT_FAMILY] == NULL)
@@ -202,7 +202,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	if (tb[NFTA_NAT_FLAGS]) {
 		priv->flags = ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS]));
 		if (priv->flags & ~NF_NAT_RANGE_MASK)
-			return -EINVAL;
+			return -EOPNOTSUPP;
 	}
 
 	return nf_ct_netns_get(ctx->net, family);
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 19446a89a2a8..b1a9f330a51f 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -79,7 +79,9 @@ static void nft_payload_eval(const struct nft_expr *expr,
 	u32 *dest = &regs->data[priv->dreg];
 	int offset;
 
-	dest[priv->len / NFT_REG32_SIZE] = 0;
+	if (priv->len % NFT_REG32_SIZE)
+		dest[priv->len / NFT_REG32_SIZE] = 0;
+
 	switch (priv->base) {
 	case NFT_PAYLOAD_LL_HEADER:
 		if (!skb_mac_header_was_set(skb))
diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c
index 41d0e95d171e..b1a1718495f3 100644
--- a/net/netlabel/netlabel_domainhash.c
+++ b/net/netlabel/netlabel_domainhash.c
@@ -99,6 +99,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry)
 			kfree(netlbl_domhsh_addr6_entry(iter6));
 		}
 #endif /* IPv6 */
+		kfree(ptr->def.addrsel);
 	}
 	kfree(ptr->domain);
 	kfree(ptr);
@@ -550,6 +551,8 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry,
 				goto add_return;
 		}
 #endif /* IPv6 */
+		/* cleanup the new entry since we've moved everything over */
+		netlbl_domhsh_free_entry(&entry->rcu);
 	} else
 		ret_val = -EINVAL;
 
@@ -593,6 +596,12 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry,
 {
 	int ret_val = 0;
 	struct audit_buffer *audit_buf;
+	struct netlbl_af4list *iter4;
+	struct netlbl_domaddr4_map *map4;
+#if IS_ENABLED(CONFIG_IPV6)
+	struct netlbl_af6list *iter6;
+	struct netlbl_domaddr6_map *map6;
+#endif /* IPv6 */
 
 	if (entry == NULL)
 		return -ENOENT;
@@ -610,6 +619,9 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry,
 		ret_val = -ENOENT;
 	spin_unlock(&netlbl_domhsh_lock);
 
+	if (ret_val)
+		return ret_val;
+
 	audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_DEL, audit_info);
 	if (audit_buf != NULL) {
 		audit_log_format(audit_buf,
@@ -619,40 +631,29 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry,
 		audit_log_end(audit_buf);
 	}
 
-	if (ret_val == 0) {
-		struct netlbl_af4list *iter4;
-		struct netlbl_domaddr4_map *map4;
-#if IS_ENABLED(CONFIG_IPV6)
-		struct netlbl_af6list *iter6;
-		struct netlbl_domaddr6_map *map6;
-#endif /* IPv6 */
-
-		switch (entry->def.type) {
-		case NETLBL_NLTYPE_ADDRSELECT:
-			netlbl_af4list_foreach_rcu(iter4,
-					     &entry->def.addrsel->list4) {
-				map4 = netlbl_domhsh_addr4_entry(iter4);
-				cipso_v4_doi_putdef(map4->def.cipso);
-			}
+	switch (entry->def.type) {
+	case NETLBL_NLTYPE_ADDRSELECT:
+		netlbl_af4list_foreach_rcu(iter4, &entry->def.addrsel->list4) {
+			map4 = netlbl_domhsh_addr4_entry(iter4);
+			cipso_v4_doi_putdef(map4->def.cipso);
+		}
 #if IS_ENABLED(CONFIG_IPV6)
-			netlbl_af6list_foreach_rcu(iter6,
-					     &entry->def.addrsel->list6) {
-				map6 = netlbl_domhsh_addr6_entry(iter6);
-				calipso_doi_putdef(map6->def.calipso);
-			}
+		netlbl_af6list_foreach_rcu(iter6, &entry->def.addrsel->list6) {
+			map6 = netlbl_domhsh_addr6_entry(iter6);
+			calipso_doi_putdef(map6->def.calipso);
+		}
 #endif /* IPv6 */
-			break;
-		case NETLBL_NLTYPE_CIPSOV4:
-			cipso_v4_doi_putdef(entry->def.cipso);
-			break;
+		break;
+	case NETLBL_NLTYPE_CIPSOV4:
+		cipso_v4_doi_putdef(entry->def.cipso);
+		break;
 #if IS_ENABLED(CONFIG_IPV6)
-		case NETLBL_NLTYPE_CALIPSO:
-			calipso_doi_putdef(entry->def.calipso);
-			break;
+	case NETLBL_NLTYPE_CALIPSO:
+		calipso_doi_putdef(entry->def.calipso);
+		break;
 #endif /* IPv6 */
-		}
-		call_rcu(&entry->rcu, netlbl_domhsh_free_entry);
 	}
+	call_rcu(&entry->rcu, netlbl_domhsh_free_entry);
 
 	return ret_val;
 }
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index e9b8b0b0ac43..7bc631bfb101 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -959,60 +959,11 @@ static struct genl_family genl_ctrl __ro_after_init = {
 	.netnsok = true,
 };
 
-static int genl_bind(struct net *net, int group)
-{
-	struct genl_family *f;
-	int err = -ENOENT;
-	unsigned int id;
-
-	down_read(&cb_lock);
-
-	idr_for_each_entry(&genl_fam_idr, f, id) {
-		if (group >= f->mcgrp_offset &&
-		    group < f->mcgrp_offset + f->n_mcgrps) {
-			int fam_grp = group - f->mcgrp_offset;
-
-			if (!f->netnsok && net != &init_net)
-				err = -ENOENT;
-			else if (f->mcast_bind)
-				err = f->mcast_bind(net, fam_grp);
-			else
-				err = 0;
-			break;
-		}
-	}
-	up_read(&cb_lock);
-
-	return err;
-}
-
-static void genl_unbind(struct net *net, int group)
-{
-	struct genl_family *f;
-	unsigned int id;
-
-	down_read(&cb_lock);
-
-	idr_for_each_entry(&genl_fam_idr, f, id) {
-		if (group >= f->mcgrp_offset &&
-		    group < f->mcgrp_offset + f->n_mcgrps) {
-			int fam_grp = group - f->mcgrp_offset;
-
-			if (f->mcast_unbind)
-				f->mcast_unbind(net, fam_grp);
-			break;
-		}
-	}
-	up_read(&cb_lock);
-}
-
 static int __net_init genl_pernet_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
-		.bind		= genl_bind,
-		.unbind		= genl_unbind,
 	};
 
 	/* we'll bump the group number right afterwards */
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index e2188deb08dc..b927730d9ab0 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -344,10 +344,13 @@ static int rawsock_create(struct net *net, struct socket *sock,
 	if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW))
 		return -ESOCKTNOSUPPORT;
 
-	if (sock->type == SOCK_RAW)
+	if (sock->type == SOCK_RAW) {
+		if (!capable(CAP_NET_RAW))
+			return -EPERM;
 		sock->ops = &rawsock_raw_ops;
-	else
+	} else {
 		sock->ops = &rawsock_ops;
+	}
 
 	sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto, kern);
 	if (!sk)
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 737e37b28d93..3d74e33bf829 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -255,10 +255,6 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
 	ovs_ct_update_key(skb, NULL, key, false, false);
 }
 
-#define IN6_ADDR_INITIALIZER(ADDR) \
-	{ (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \
-	  (ADDR).s6_addr32[2], (ADDR).s6_addr32[3] }
-
 int ovs_ct_put_key(const struct sw_flow_key *swkey,
 		   const struct sw_flow_key *output, struct sk_buff *skb)
 {
@@ -280,24 +276,30 @@ int ovs_ct_put_key(const struct sw_flow_key *swkey,
 
 	if (swkey->ct_orig_proto) {
 		if (swkey->eth.type == htons(ETH_P_IP)) {
-			struct ovs_key_ct_tuple_ipv4 orig = {
-				output->ipv4.ct_orig.src,
-				output->ipv4.ct_orig.dst,
-				output->ct.orig_tp.src,
-				output->ct.orig_tp.dst,
-				output->ct_orig_proto,
-			};
+			struct ovs_key_ct_tuple_ipv4 orig;
+
+			memset(&orig, 0, sizeof(orig));
+			orig.ipv4_src = output->ipv4.ct_orig.src;
+			orig.ipv4_dst = output->ipv4.ct_orig.dst;
+			orig.src_port = output->ct.orig_tp.src;
+			orig.dst_port = output->ct.orig_tp.dst;
+			orig.ipv4_proto = output->ct_orig_proto;
+
 			if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,
 				    sizeof(orig), &orig))
 				return -EMSGSIZE;
 		} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
-			struct ovs_key_ct_tuple_ipv6 orig = {
-				IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src),
-				IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst),
-				output->ct.orig_tp.src,
-				output->ct.orig_tp.dst,
-				output->ct_orig_proto,
-			};
+			struct ovs_key_ct_tuple_ipv6 orig;
+
+			memset(&orig, 0, sizeof(orig));
+			memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32,
+			       sizeof(orig.ipv6_src));
+			memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32,
+			       sizeof(orig.ipv6_dst));
+			orig.src_port = output->ct.orig_tp.src;
+			orig.dst_port = output->ct.orig_tp.dst;
+			orig.ipv6_proto = output->ct_orig_proto;
+
 			if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,
 				    sizeof(orig), &orig))
 				return -EMSGSIZE;
@@ -879,15 +881,19 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 	}
 	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);
 
-	if (err == NF_ACCEPT &&
-	    ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) {
-		if (maniptype == NF_NAT_MANIP_SRC)
-			maniptype = NF_NAT_MANIP_DST;
-		else
-			maniptype = NF_NAT_MANIP_SRC;
-
-		err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
-					 maniptype);
+	if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
+		if (ct->status & IPS_SRC_NAT) {
+			if (maniptype == NF_NAT_MANIP_SRC)
+				maniptype = NF_NAT_MANIP_DST;
+			else
+				maniptype = NF_NAT_MANIP_SRC;
+
+			err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
+						 maniptype);
+		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
+			err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL,
+						 NF_NAT_MANIP_SRC);
+		}
 	}
 
 	/* Mark NAT done if successful and update the flow key. */
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 102750bd751c..b62ec43ed54f 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -989,6 +989,7 @@ static int prb_queue_frozen(struct tpacket_kbdq_core *pkc)
 }
 
 static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb)
+	__releases(&pkc->blk_fill_in_prog_lock)
 {
 	struct tpacket_kbdq_core *pkc  = GET_PBDQC_FROM_RB(rb);
 	atomic_dec(&pkc->blk_fill_in_prog);
@@ -1036,6 +1037,7 @@ static void prb_fill_curr_block(char *curr,
 				struct tpacket_kbdq_core *pkc,
 				struct tpacket_block_desc *pbd,
 				unsigned int len)
+	__acquires(&pkc->blk_fill_in_prog_lock)
 {
 	struct tpacket3_hdr *ppd;
 
@@ -2199,7 +2201,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	int skb_len = skb->len;
 	unsigned int snaplen, res;
 	unsigned long status = TP_STATUS_USER;
-	unsigned short macoff, netoff, hdrlen;
+	unsigned short macoff, hdrlen;
+	unsigned int netoff;
 	struct sk_buff *copy_skb = NULL;
 	struct timespec ts;
 	__u32 ts_status;
@@ -2262,6 +2265,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		}
 		macoff = netoff - maclen;
 	}
+	if (netoff > USHRT_MAX) {
+		spin_lock(&sk->sk_receive_queue.lock);
+		po->stats.stats1.tp_drops++;
+		spin_unlock(&sk->sk_receive_queue.lock);
+		goto drop_n_restore;
+	}
 	if (po->tp_version <= TPACKET_V2) {
 		if (macoff + snaplen > po->rx_ring.frame_size) {
 			if (po->copy_thresh &&
@@ -2311,8 +2320,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (do_vnet &&
 	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
 				    sizeof(struct virtio_net_hdr),
-				    vio_le(), true, 0))
+				    vio_le(), true, 0)) {
+		if (po->tp_version == TPACKET_V3)
+			prb_clear_blk_fill_status(&po->rx_ring);
 		goto drop_n_account;
+	}
 
 	if (po->tp_version <= TPACKET_V2) {
 		packet_increment_rx_head(po, &po->rx_ring);
@@ -2418,7 +2430,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		__clear_bit(slot_id, po->rx_ring.rx_owner_map);
 		spin_unlock(&sk->sk_receive_queue.lock);
 		sk->sk_data_ready(sk);
-	} else {
+	} else if (po->tp_version == TPACKET_V3) {
 		prb_clear_blk_fill_status(&po->rx_ring);
 	}
 
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 944ce686bfe5..b9b6235a4cf2 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -660,7 +660,7 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb)
 	}
 	mutex_unlock(&qrtr_node_lock);
 
-	qrtr_local_enqueue(node, skb);
+	qrtr_local_enqueue(NULL, skb);
 
 	return 0;
 }
diff --git a/net/rds/recv.c b/net/rds/recv.c
index c27cceae52e1..ef022d24f87a 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -453,12 +453,13 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
 int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msghdr)
 {
 	struct rds_notifier *notifier;
-	struct rds_rdma_notify cmsg = { 0 }; /* fill holes with zero */
+	struct rds_rdma_notify cmsg;
 	unsigned int count = 0, max_messages = ~0U;
 	unsigned long flags;
 	LIST_HEAD(copy);
 	int err = 0;
 
+	memset(&cmsg, 0, sizeof(cmsg));	/* fill holes with zero */
 
 	/* put_cmsg copies to user space and thus may sleep. We can't do this
 	 * with rs_lock held, so first grab as many notifications as we can stuff
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 2dd13f5c47c8..61425179780c 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -26,6 +26,11 @@
 #include <net/ip.h>
 #include "ar-internal.h"
 
+static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call,
+			       unsigned long user_call_ID)
+{
+}
+
 /*
  * Preallocate a single service call, connection and peer and, if possible,
  * give them a user ID and attach the user's side of the ID to them.
@@ -227,6 +232,8 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
 		if (rx->discard_new_call) {
 			_debug("discard %lx", call->user_call_ID);
 			rx->discard_new_call(call, call->user_call_ID);
+			if (call->notify_rx)
+				call->notify_rx = rxrpc_dummy_notify;
 			rxrpc_put_call(call, rxrpc_call_put_kernel);
 		}
 		rxrpc_call_completed(call);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 7021725fa38a..1c98a026b41a 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -275,7 +275,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	 */
 	ret = rxrpc_connect_call(call, cp, srx, gfp);
 	if (ret < 0)
-		goto error;
+		goto error_attached_to_socket;
 
 	trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage),
 			 here, NULL);
@@ -295,18 +295,29 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 error_dup_user_ID:
 	write_unlock(&rx->call_lock);
 	release_sock(&rx->sk);
-	ret = -EEXIST;
-
-error:
 	__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
-				    RX_CALL_DEAD, ret);
+				    RX_CALL_DEAD, -EEXIST);
 	trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage),
-			 here, ERR_PTR(ret));
+			 here, ERR_PTR(-EEXIST));
 	rxrpc_release_call(rx, call);
 	mutex_unlock(&call->user_mutex);
 	rxrpc_put_call(call, rxrpc_call_put);
-	_leave(" = %d", ret);
-	return ERR_PTR(ret);
+	_leave(" = -EEXIST");
+	return ERR_PTR(-EEXIST);
+
+	/* We got an error, but the call is attached to the socket and is in
+	 * need of release.  However, we might now race with recvmsg() when
+	 * completing the call queues it.  Return 0 from sys_sendmsg() and
+	 * leave the error to recvmsg() to deal with.
+	 */
+error_attached_to_socket:
+	trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage),
+			 here, ERR_PTR(ret));
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+	__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
+				    RX_CALL_DEAD, ret);
+	_leave(" = c=%08x [err]", call->debug_id);
+	return call;
 }
 
 /*
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 75ec1ad595b7..2432c118397f 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -316,18 +316,18 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 			return ret;
 
 		spin_lock(&conn->channel_lock);
-		spin_lock(&conn->state_lock);
+		spin_lock_bh(&conn->state_lock);
 
 		if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
 			conn->state = RXRPC_CONN_SERVICE;
-			spin_unlock(&conn->state_lock);
+			spin_unlock_bh(&conn->state_lock);
 			for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
 				rxrpc_call_is_secure(
 					rcu_dereference_protected(
 						conn->channels[loop].call,
 						lockdep_is_held(&conn->channel_lock)));
 		} else {
-			spin_unlock(&conn->state_lock);
+			spin_unlock_bh(&conn->state_lock);
 		}
 
 		spin_unlock(&conn->channel_lock);
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index af0232820597..0e5087b9e07c 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -196,9 +196,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 
 	call->peer->cong_cwnd = call->cong_cwnd;
 
-	spin_lock_bh(&conn->params.peer->lock);
-	hlist_del_init(&call->error_link);
-	spin_unlock_bh(&conn->params.peer->lock);
+	if (!hlist_unhashed(&call->error_link)) {
+		spin_lock_bh(&conn->params.peer->lock);
+		hlist_del_init(&call->error_link);
+		spin_unlock_bh(&conn->params.peer->lock);
+	}
 
 	if (rxrpc_is_client_call(call))
 		return rxrpc_disconnect_client_call(call);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 18ce6f97462b..98285b117a7c 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -664,13 +664,12 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
 	       ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU),
 	       rwind, ntohl(ackinfo->jumbo_max));
 
+	if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
+		rwind = RXRPC_RXTX_BUFF_SIZE - 1;
 	if (call->tx_winsize != rwind) {
-		if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
-			rwind = RXRPC_RXTX_BUFF_SIZE - 1;
 		if (rwind > call->tx_winsize)
 			wake = true;
-		trace_rxrpc_rx_rwind_change(call, sp->hdr.serial,
-					    ntohl(ackinfo->rwind), wake);
+		trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, rwind, wake);
 		call->tx_winsize = rwind;
 	}
 
diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index ad9d1b21cb0b..2fe2add62a8e 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -905,7 +905,7 @@ int rxrpc_request_key(struct rxrpc_sock *rx, char __user *optval, int optlen)
 
 	_enter("");
 
-	if (optlen <= 0 || optlen > PAGE_SIZE - 1)
+	if (optlen <= 0 || optlen > PAGE_SIZE - 1 || rx->securities)
 		return -EINVAL;
 
 	description = memdup_user_nul(optval, optlen);
@@ -1075,7 +1075,7 @@ static long rxrpc_read(const struct key *key,
 
 		switch (token->security_index) {
 		case RXRPC_SECURITY_RXKAD:
-			toksize += 9 * 4;	/* viceid, kvno, key*2 + len, begin,
+			toksize += 8 * 4;	/* viceid, kvno, key*2, begin,
 						 * end, primary, tktlen */
 			toksize += RND(token->kad->ticket_len);
 			break;
@@ -1110,7 +1110,8 @@ static long rxrpc_read(const struct key *key,
 			break;
 
 		default: /* we have a ticket we can't encode */
-			BUG();
+			pr_err("Unsupported key token type (%u)\n",
+			       token->security_index);
 			continue;
 		}
 
@@ -1141,6 +1142,14 @@ static long rxrpc_read(const struct key *key,
 			memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3));	\
 		xdr += (_l + 3) >> 2;					\
 	} while(0)
+#define ENCODE_BYTES(l, s)						\
+	do {								\
+		u32 _l = (l);						\
+		memcpy(xdr, (s), _l);					\
+		if (_l & 3)						\
+			memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3));	\
+		xdr += (_l + 3) >> 2;					\
+	} while(0)
 #define ENCODE64(x)					\
 	do {						\
 		__be64 y = cpu_to_be64(x);		\
@@ -1168,7 +1177,7 @@ static long rxrpc_read(const struct key *key,
 		case RXRPC_SECURITY_RXKAD:
 			ENCODE(token->kad->vice_id);
 			ENCODE(token->kad->kvno);
-			ENCODE_DATA(8, token->kad->session_key);
+			ENCODE_BYTES(8, token->kad->session_key);
 			ENCODE(token->kad->start);
 			ENCODE(token->kad->expiry);
 			ENCODE(token->kad->primary_flag);
@@ -1218,7 +1227,6 @@ static long rxrpc_read(const struct key *key,
 			break;
 
 		default:
-			BUG();
 			break;
 		}
 
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 2af42c7d5b82..383292adcac6 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -134,10 +134,10 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 	}
 
 	switch (local->srx.transport.family) {
-	case AF_INET:
-		/* we want to receive ICMP errors */
+	case AF_INET6:
+		/* we want to receive ICMPv6 errors */
 		opt = 1;
-		ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
+		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
 					(char *) &opt, sizeof(opt));
 		if (ret < 0) {
 			_debug("setsockopt failed");
@@ -145,19 +145,22 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 		}
 
 		/* we want to set the don't fragment bit */
-		opt = IP_PMTUDISC_DO;
-		ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
+		opt = IPV6_PMTUDISC_DO;
+		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
 					(char *) &opt, sizeof(opt));
 		if (ret < 0) {
 			_debug("setsockopt failed");
 			goto error;
 		}
-		break;
 
-	case AF_INET6:
+		/* Fall through and set IPv4 options too otherwise we don't get
+		 * errors from IPv4 packets sent through the IPv6 socket.
+		 */
+
+	case AF_INET:
 		/* we want to receive ICMP errors */
 		opt = 1;
-		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
+		ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
 					(char *) &opt, sizeof(opt));
 		if (ret < 0) {
 			_debug("setsockopt failed");
@@ -165,8 +168,8 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 		}
 
 		/* we want to set the don't fragment bit */
-		opt = IPV6_PMTUDISC_DO;
-		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
+		opt = IP_PMTUDISC_DO;
+		ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
 					(char *) &opt, sizeof(opt));
 		if (ret < 0) {
 			_debug("setsockopt failed");
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index b74cde2fd214..1cdd8b380d47 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -445,7 +445,7 @@ try_again:
 	    list_empty(&rx->recvmsg_q) &&
 	    rx->sk.sk_state != RXRPC_SERVER_LISTENING) {
 		release_sock(&rx->sk);
-		return -ENODATA;
+		return -EAGAIN;
 	}
 
 	if (list_empty(&rx->recvmsg_q)) {
@@ -522,7 +522,7 @@ try_again:
 			goto error_unlock_call;
 	}
 
-	if (msg->msg_name) {
+	if (msg->msg_name && call->peer) {
 		struct sockaddr_rxrpc *srx = msg->msg_name;
 		size_t len = sizeof(call->peer->srx);
 
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index a980b49d7a4f..8f9a2a7eeb7c 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -222,7 +222,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 	/* this should be in poll */
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
-	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
+	if (sk->sk_shutdown & SEND_SHUTDOWN)
 		return -EPIPE;
 
 	more = msg->msg_flags & MSG_MORE;
@@ -579,6 +579,9 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		if (IS_ERR(call))
 			return PTR_ERR(call);
 		/* ... and we have the call lock. */
+		ret = 0;
+		if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE)
+			goto out_put_unlock;
 	} else {
 		switch (READ_ONCE(call->state)) {
 		case RXRPC_CALL_UNINITIALISED:
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index c5fcdf1a58a0..9198c9983b83 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -545,15 +545,15 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt)
 	if (!p->link.q)
 		p->link.q = &noop_qdisc;
 	pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q);
+	p->link.vcc = NULL;
+	p->link.sock = NULL;
+	p->link.common.classid = sch->handle;
+	p->link.ref = 1;
 
 	err = tcf_block_get(&p->link.block, &p->link.filter_list);
 	if (err)
 		return err;
 
-	p->link.vcc = NULL;
-	p->link.sock = NULL;
-	p->link.common.classid = sch->handle;
-	p->link.ref = 1;
 	tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch);
 	return 0;
 }
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 21b981abbacb..091a9746627f 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -341,6 +341,7 @@ void __netdev_watchdog_up(struct net_device *dev)
 			dev_hold(dev);
 	}
 }
+EXPORT_SYMBOL_GPL(__netdev_watchdog_up);
 
 static void dev_watchdog_up(struct net_device *dev)
 {
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index dd1a3bd80be5..0a5764016721 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1598,12 +1598,15 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
 int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc,
 				     enum sctp_scope scope, gfp_t gfp)
 {
+	struct sock *sk = asoc->base.sk;
 	int flags;
 
 	/* Use scoping rules to determine the subset of addresses from
 	 * the endpoint.
 	 */
-	flags = (PF_INET6 == asoc->base.sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0;
+	flags = (PF_INET6 == sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0;
+	if (!inet_v6_ipv6only(sk))
+		flags |= SCTP_ADDR4_ALLOWED;
 	if (asoc->peer.ipv4_address)
 		flags |= SCTP_ADDR4_PEERSUPP;
 	if (asoc->peer.ipv6_address)
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 00667c50efa7..9d7e72960919 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -493,6 +493,7 @@ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp)
 out_err:
 	/* Clean up any successful allocations */
 	sctp_auth_destroy_hmacs(ep->auth_hmacs);
+	ep->auth_hmacs = NULL;
 	return -ENOMEM;
 }
 
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index 7df3704982f5..38d01cfb313e 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -453,6 +453,7 @@ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest,
 		 * well as the remote peer.
 		 */
 		if ((((AF_INET == addr->sa.sa_family) &&
+		      (flags & SCTP_ADDR4_ALLOWED) &&
 		      (flags & SCTP_ADDR4_PEERSUPP))) ||
 		    (((AF_INET6 == addr->sa.sa_family) &&
 		      (flags & SCTP_ADDR6_ALLOWED) &&
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 785456df7505..8fe9c0646205 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -213,7 +213,8 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
 		 * sock as well as the remote peer.
 		 */
 		if (addr->a.sa.sa_family == AF_INET &&
-		    !(copy_flags & SCTP_ADDR4_PEERSUPP))
+		    (!(copy_flags & SCTP_ADDR4_ALLOWED) ||
+		     !(copy_flags & SCTP_ADDR4_PEERSUPP)))
 			continue;
 		if (addr->a.sa.sa_family == AF_INET6 &&
 		    (!(copy_flags & SCTP_ADDR6_ALLOWED) ||
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index ba29d782af30..80b9f7f097fa 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1829,12 +1829,13 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
 	/* Update the content of current association. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
 	sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
-	if (sctp_state(asoc, SHUTDOWN_PENDING) &&
+	if ((sctp_state(asoc, SHUTDOWN_PENDING) ||
+	     sctp_state(asoc, SHUTDOWN_SENT)) &&
 	    (sctp_sstate(asoc->base.sk, CLOSING) ||
 	     sock_flag(asoc->base.sk, SOCK_DEAD))) {
-		/* if were currently in SHUTDOWN_PENDING, but the socket
-		 * has been closed by user, don't transition to ESTABLISHED.
-		 * Instead trigger SHUTDOWN bundled with COOKIE_ACK.
+		/* If the socket has been closed by user, don't
+		 * transition to ESTABLISHED. Instead trigger SHUTDOWN
+		 * bundled with COOKIE_ACK.
 		 */
 		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
 		return sctp_sf_do_9_2_start_shutdown(net, ep, asoc,
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 442780515760..1f154276a681 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7086,8 +7086,6 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 
 	pr_debug("%s: begins, snum:%d\n", __func__, snum);
 
-	local_bh_disable();
-
 	if (snum == 0) {
 		/* Search for an available port. */
 		int low, high, remaining, index;
@@ -7106,20 +7104,21 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 				continue;
 			index = sctp_phashfn(sock_net(sk), rover);
 			head = &sctp_port_hashtable[index];
-			spin_lock(&head->lock);
+			spin_lock_bh(&head->lock);
 			sctp_for_each_hentry(pp, &head->chain)
 				if ((pp->port == rover) &&
 				    net_eq(sock_net(sk), pp->net))
 					goto next;
 			break;
 		next:
-			spin_unlock(&head->lock);
+			spin_unlock_bh(&head->lock);
+			cond_resched();
 		} while (--remaining > 0);
 
 		/* Exhausted local port range during search? */
 		ret = 1;
 		if (remaining <= 0)
-			goto fail;
+			return ret;
 
 		/* OK, here is the one we will use.  HEAD (the port
 		 * hash table list entry) is non-NULL and we hold it's
@@ -7134,7 +7133,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 		 * port iterator, pp being NULL.
 		 */
 		head = &sctp_port_hashtable[sctp_phashfn(sock_net(sk), snum)];
-		spin_lock(&head->lock);
+		spin_lock_bh(&head->lock);
 		sctp_for_each_hentry(pp, &head->chain) {
 			if ((pp->port == snum) && net_eq(pp->net, sock_net(sk)))
 				goto pp_found;
@@ -7218,10 +7217,7 @@ success:
 	ret = 0;
 
 fail_unlock:
-	spin_unlock(&head->lock);
-
-fail:
-	local_bh_enable();
+	spin_unlock_bh(&head->lock);
 	return ret;
 }
 
diff --git a/net/socket.c b/net/socket.c
index 6a5ec658fcd8..c74cfe1ee169 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -496,7 +496,7 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
 	if (f.file) {
 		sock = sock_from_file(f.file, err);
 		if (likely(sock)) {
-			*fput_needed = f.flags;
+			*fput_needed = f.flags & FDPUT_FPUT;
 			return sock;
 		}
 		fdput(f);
diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c
index 2e0a6f92e563..8391c2785550 100644
--- a/net/sunrpc/addr.c
+++ b/net/sunrpc/addr.c
@@ -81,11 +81,11 @@ static size_t rpc_ntop6(const struct sockaddr *sap,
 
 	rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u",
 			IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id);
-	if (unlikely((size_t)rc > sizeof(scopebuf)))
+	if (unlikely((size_t)rc >= sizeof(scopebuf)))
 		return 0;
 
 	len += rc;
-	if (unlikely(len > buflen))
+	if (unlikely(len >= buflen))
 		return 0;
 
 	strcat(buf, scopebuf);
diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index 5fec3abbe19b..c7d88f979c56 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -61,6 +61,8 @@ gss_mech_free(struct gss_api_mech *gm)
 
 	for (i = 0; i < gm->gm_pf_num; i++) {
 		pf = &gm->gm_pfs[i];
+		if (pf->domain)
+			auth_domain_put(pf->domain);
 		kfree(pf->auth_domain_name);
 		pf->auth_domain_name = NULL;
 	}
@@ -83,6 +85,7 @@ make_auth_domain_name(char *name)
 static int
 gss_mech_svc_setup(struct gss_api_mech *gm)
 {
+	struct auth_domain *dom;
 	struct pf_desc *pf;
 	int i, status;
 
@@ -92,10 +95,13 @@ gss_mech_svc_setup(struct gss_api_mech *gm)
 		status = -ENOMEM;
 		if (pf->auth_domain_name == NULL)
 			goto out;
-		status = svcauth_gss_register_pseudoflavor(pf->pseudoflavor,
-							pf->auth_domain_name);
-		if (status)
+		dom = svcauth_gss_register_pseudoflavor(
+			pf->pseudoflavor, pf->auth_domain_name);
+		if (IS_ERR(dom)) {
+			status = PTR_ERR(dom);
 			goto out;
+		}
+		pf->domain = dom;
 	}
 	return 0;
 out:
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index a457e7afb768..03043d5221e9 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -779,7 +779,7 @@ u32 svcauth_gss_flavor(struct auth_domain *dom)
 
 EXPORT_SYMBOL_GPL(svcauth_gss_flavor);
 
-int
+struct auth_domain *
 svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name)
 {
 	struct gss_domain	*new;
@@ -796,21 +796,23 @@ svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name)
 	new->h.flavour = &svcauthops_gss;
 	new->pseudoflavor = pseudoflavor;
 
-	stat = 0;
 	test = auth_domain_lookup(name, &new->h);
-	if (test != &new->h) { /* Duplicate registration */
+	if (test != &new->h) {
+		pr_warn("svc: duplicate registration of gss pseudo flavour %s.\n",
+			name);
+		stat = -EADDRINUSE;
 		auth_domain_put(test);
-		kfree(new->h.name);
-		goto out_free_dom;
+		goto out_free_name;
 	}
-	return 0;
+	return test;
 
+out_free_name:
+	kfree(new->h.name);
 out_free_dom:
 	kfree(new);
 out:
-	return stat;
+	return ERR_PTR(stat);
 }
-
 EXPORT_SYMBOL_GPL(svcauth_gss_register_pseudoflavor);
 
 static inline int
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 34f94052c519..137f92bfafac 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1347,6 +1347,7 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data)
 	q.len = strlen(gssd_dummy_clnt_dir[0].name);
 	clnt_dentry = d_hash_and_lookup(gssd_dentry, &q);
 	if (!clnt_dentry) {
+		__rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1);
 		pipe_dentry = ERR_PTR(-ENOENT);
 		goto out;
 	}
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index da21efac80f4..7c0b1feb3629 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -981,8 +981,8 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr,
 	p = xdr_inline_decode(xdr, len);
 	if (unlikely(p == NULL))
 		goto out_fail;
-	dprintk("RPC: %5u RPCB_%s reply: %s\n", req->rq_task->tk_pid,
-			req->rq_task->tk_msg.rpc_proc->p_name, (char *)p);
+	dprintk("RPC: %5u RPCB_%s reply: %*pE\n", req->rq_task->tk_pid,
+			req->rq_task->tk_msg.rpc_proc->p_name, len, (char *)p);
 
 	if (rpc_uaddr2sockaddr(req->rq_xprt->xprt_net, (char *)p, len,
 				sap, sizeof(address)) == 0)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 7e5f849b44cd..b293827b2a58 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -103,8 +103,17 @@ void svc_unreg_xprt_class(struct svc_xprt_class *xcl)
 }
 EXPORT_SYMBOL_GPL(svc_unreg_xprt_class);
 
-/*
- * Format the transport list for printing
+/**
+ * svc_print_xprts - Format the transport list for printing
+ * @buf: target buffer for formatted address
+ * @maxlen: length of target buffer
+ *
+ * Fills in @buf with a string containing a list of transport names, each name
+ * terminated with '\n'. If the buffer is too small, some entries may be
+ * missing, but it is guaranteed that all lines in the output buffer are
+ * complete.
+ *
+ * Returns positive length of the filled-in string.
  */
 int svc_print_xprts(char *buf, int maxlen)
 {
@@ -117,9 +126,9 @@ int svc_print_xprts(char *buf, int maxlen)
 	list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
 		int slen;
 
-		sprintf(tmpstr, "%s %d\n", xcl->xcl_name, xcl->xcl_max_payload);
-		slen = strlen(tmpstr);
-		if (len + slen > maxlen)
+		slen = snprintf(tmpstr, sizeof(tmpstr), "%s %d\n",
+				xcl->xcl_name, xcl->xcl_max_payload);
+		if (slen >= sizeof(tmpstr) || len + slen >= maxlen)
 			break;
 		len += slen;
 		strcat(buf, tmpstr);
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 4f382805eb9c..87cf0b933f99 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -1036,6 +1036,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 		base = 0;
 	} else {
 		base -= buf->head[0].iov_len;
+		subbuf->head[0].iov_base = buf->head[0].iov_base;
 		subbuf->head[0].iov_len = 0;
 	}
 
@@ -1048,6 +1049,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 		base = 0;
 	} else {
 		base -= buf->page_len;
+		subbuf->pages = buf->pages;
+		subbuf->page_base = 0;
 		subbuf->page_len = 0;
 	}
 
@@ -1059,6 +1062,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 		base = 0;
 	} else {
 		base -= buf->tail[0].iov_len;
+		subbuf->tail[0].iov_base = buf->tail[0].iov_base;
 		subbuf->tail[0].iov_len = 0;
 	}
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index af7893501e40..4b9aaf487327 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -270,6 +270,7 @@ xprt_rdma_bc_put(struct rpc_xprt *xprt)
 {
 	dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);
 
+	xprt_rdma_free_addresses(xprt);
 	xprt_free(xprt);
 	module_put(THIS_MODULE);
 }
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index e38396025874..d048ec6dab12 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -140,7 +140,8 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 	if (fragid == FIRST_FRAGMENT) {
 		if (unlikely(head))
 			goto err;
-		if (unlikely(skb_unclone(frag, GFP_ATOMIC)))
+		frag = skb_unshare(frag, GFP_ATOMIC);
+		if (unlikely(!frag))
 			goto err;
 		head = *headbuf = frag;
 		*buf = NULL;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index fa0522cd683e..99c69489bb44 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -250,8 +250,9 @@ err_out:
 static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 				 struct tipc_nl_compat_msg *msg)
 {
-	int err;
+	struct nlmsghdr *nlh;
 	struct sk_buff *arg;
+	int err;
 
 	if (msg->req_type && (!msg->req_size ||
 			      !TLV_CHECK_TYPE(msg->req, msg->req_type)))
@@ -280,6 +281,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 		return -ENOMEM;
 	}
 
+	nlh = nlmsg_put(arg, 0, 0, tipc_genl_family.id, 0, NLM_F_MULTI);
+	if (!nlh) {
+		kfree_skb(arg);
+		kfree_skb(msg->rep);
+		msg->rep = NULL;
+		return -EMSGSIZE;
+	}
+	nlmsg_end(arg, nlh);
+
 	err = __tipc_nl_compat_dumpit(cmd, msg, arg);
 	if (err) {
 		kfree_skb(msg->rep);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index d9ec6335c7dc..44ede9ab7898 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2126,18 +2126,18 @@ static int tipc_shutdown(struct socket *sock, int how)
 	lock_sock(sk);
 
 	__tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
-	sk->sk_shutdown = SEND_SHUTDOWN;
+	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	if (sk->sk_state == TIPC_DISCONNECTING) {
 		/* Discard any unreceived messages */
 		__skb_queue_purge(&sk->sk_receive_queue);
 
-		/* Wake up anyone sleeping in poll */
-		sk->sk_state_change(sk);
 		res = 0;
 	} else {
 		res = -ENOTCONN;
 	}
+	/* Wake up anyone sleeping in poll. */
+	sk->sk_state_change(sk);
 
 	release_sock(sk);
 	return res;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 091e93798eac..44ff3f5c22df 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -192,11 +192,17 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk)
 	return unix_peer(osk) == NULL || unix_our_peer(sk, osk);
 }
 
-static inline int unix_recvq_full(struct sock const *sk)
+static inline int unix_recvq_full(const struct sock *sk)
 {
 	return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog;
 }
 
+static inline int unix_recvq_full_lockless(const struct sock *sk)
+{
+	return skb_queue_len_lockless(&sk->sk_receive_queue) >
+		READ_ONCE(sk->sk_max_ack_backlog);
+}
+
 struct sock *unix_peer_get(struct sock *s)
 {
 	struct sock *peer;
@@ -1792,7 +1798,8 @@ restart_locked:
 	 * - unix_peer(sk) == sk by time of get but disconnected before lock
 	 */
 	if (other != sk &&
-	    unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+	    unlikely(unix_peer(other) != sk &&
+	    unix_recvq_full_lockless(other))) {
 		if (timeo) {
 			timeo = unix_wait_for_peer(other, timeo);
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 73eac97e19fb..f297a427b421 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1290,7 +1290,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
 	/* Wait for children sockets to appear; these are the new sockets
 	 * created upon connection establishment.
 	 */
-	timeout = sock_sndtimeo(listener, flags & O_NONBLOCK);
+	timeout = sock_rcvtimeo(listener, flags & O_NONBLOCK);
 	prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE);
 
 	while ((connected = vsock_dequeue_accept(listener)) == NULL &&
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 96ab344f17bb..cc70d651d13e 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -39,6 +39,7 @@ struct virtio_vsock {
 	 * must be accessed with tx_lock held.
 	 */
 	struct mutex tx_lock;
+	bool tx_run;
 
 	struct work_struct send_pkt_work;
 	spinlock_t send_pkt_list_lock;
@@ -54,6 +55,7 @@ struct virtio_vsock {
 	 * must be accessed with rx_lock held.
 	 */
 	struct mutex rx_lock;
+	bool rx_run;
 	int rx_buf_nr;
 	int rx_buf_max_nr;
 
@@ -61,46 +63,28 @@ struct virtio_vsock {
 	 * vqs[VSOCK_VQ_EVENT] must be accessed with event_lock held.
 	 */
 	struct mutex event_lock;
+	bool event_run;
 	struct virtio_vsock_event event_list[8];
 
 	u32 guest_cid;
 };
 
-static struct virtio_vsock *virtio_vsock_get(void)
-{
-	return the_virtio_vsock;
-}
-
 static u32 virtio_transport_get_local_cid(void)
 {
-	struct virtio_vsock *vsock = virtio_vsock_get();
-
-	if (!vsock)
-		return VMADDR_CID_ANY;
-
-	return vsock->guest_cid;
-}
-
-static void virtio_transport_loopback_work(struct work_struct *work)
-{
-	struct virtio_vsock *vsock =
-		container_of(work, struct virtio_vsock, loopback_work);
-	LIST_HEAD(pkts);
-
-	spin_lock_bh(&vsock->loopback_list_lock);
-	list_splice_init(&vsock->loopback_list, &pkts);
-	spin_unlock_bh(&vsock->loopback_list_lock);
-
-	mutex_lock(&vsock->rx_lock);
-	while (!list_empty(&pkts)) {
-		struct virtio_vsock_pkt *pkt;
-
-		pkt = list_first_entry(&pkts, struct virtio_vsock_pkt, list);
-		list_del_init(&pkt->list);
+	struct virtio_vsock *vsock;
+	u32 ret;
 
-		virtio_transport_recv_pkt(pkt);
+	rcu_read_lock();
+	vsock = rcu_dereference(the_virtio_vsock);
+	if (!vsock) {
+		ret = VMADDR_CID_ANY;
+		goto out_rcu;
 	}
-	mutex_unlock(&vsock->rx_lock);
+
+	ret = vsock->guest_cid;
+out_rcu:
+	rcu_read_unlock();
+	return ret;
 }
 
 static int virtio_transport_send_pkt_loopback(struct virtio_vsock *vsock,
@@ -128,6 +112,9 @@ virtio_transport_send_pkt_work(struct work_struct *work)
 
 	mutex_lock(&vsock->tx_lock);
 
+	if (!vsock->tx_run)
+		goto out;
+
 	vq = vsock->vqs[VSOCK_VQ_TX];
 
 	for (;;) {
@@ -186,6 +173,7 @@ virtio_transport_send_pkt_work(struct work_struct *work)
 	if (added)
 		virtqueue_kick(vq);
 
+out:
 	mutex_unlock(&vsock->tx_lock);
 
 	if (restart_rx)
@@ -198,14 +186,18 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
 	struct virtio_vsock *vsock;
 	int len = pkt->len;
 
-	vsock = virtio_vsock_get();
+	rcu_read_lock();
+	vsock = rcu_dereference(the_virtio_vsock);
 	if (!vsock) {
 		virtio_transport_free_pkt(pkt);
-		return -ENODEV;
+		len = -ENODEV;
+		goto out_rcu;
 	}
 
-	if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
-		return virtio_transport_send_pkt_loopback(vsock, pkt);
+	if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid) {
+		len = virtio_transport_send_pkt_loopback(vsock, pkt);
+		goto out_rcu;
+	}
 
 	if (pkt->reply)
 		atomic_inc(&vsock->queued_replies);
@@ -215,6 +207,9 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
 	spin_unlock_bh(&vsock->send_pkt_list_lock);
 
 	queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work);
+
+out_rcu:
+	rcu_read_unlock();
 	return len;
 }
 
@@ -223,12 +218,14 @@ virtio_transport_cancel_pkt(struct vsock_sock *vsk)
 {
 	struct virtio_vsock *vsock;
 	struct virtio_vsock_pkt *pkt, *n;
-	int cnt = 0;
+	int cnt = 0, ret;
 	LIST_HEAD(freeme);
 
-	vsock = virtio_vsock_get();
+	rcu_read_lock();
+	vsock = rcu_dereference(the_virtio_vsock);
 	if (!vsock) {
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_rcu;
 	}
 
 	spin_lock_bh(&vsock->send_pkt_list_lock);
@@ -256,7 +253,11 @@ virtio_transport_cancel_pkt(struct vsock_sock *vsk)
 			queue_work(virtio_vsock_workqueue, &vsock->rx_work);
 	}
 
-	return 0;
+	ret = 0;
+
+out_rcu:
+	rcu_read_unlock();
+	return ret;
 }
 
 static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
@@ -308,6 +309,10 @@ static void virtio_transport_tx_work(struct work_struct *work)
 
 	vq = vsock->vqs[VSOCK_VQ_TX];
 	mutex_lock(&vsock->tx_lock);
+
+	if (!vsock->tx_run)
+		goto out;
+
 	do {
 		struct virtio_vsock_pkt *pkt;
 		unsigned int len;
@@ -318,6 +323,8 @@ static void virtio_transport_tx_work(struct work_struct *work)
 			added = true;
 		}
 	} while (!virtqueue_enable_cb(vq));
+
+out:
 	mutex_unlock(&vsock->tx_lock);
 
 	if (added)
@@ -336,56 +343,6 @@ static bool virtio_transport_more_replies(struct virtio_vsock *vsock)
 	return val < virtqueue_get_vring_size(vq);
 }
 
-static void virtio_transport_rx_work(struct work_struct *work)
-{
-	struct virtio_vsock *vsock =
-		container_of(work, struct virtio_vsock, rx_work);
-	struct virtqueue *vq;
-
-	vq = vsock->vqs[VSOCK_VQ_RX];
-
-	mutex_lock(&vsock->rx_lock);
-
-	do {
-		virtqueue_disable_cb(vq);
-		for (;;) {
-			struct virtio_vsock_pkt *pkt;
-			unsigned int len;
-
-			if (!virtio_transport_more_replies(vsock)) {
-				/* Stop rx until the device processes already
-				 * pending replies.  Leave rx virtqueue
-				 * callbacks disabled.
-				 */
-				goto out;
-			}
-
-			pkt = virtqueue_get_buf(vq, &len);
-			if (!pkt) {
-				break;
-			}
-
-			vsock->rx_buf_nr--;
-
-			/* Drop short/long packets */
-			if (unlikely(len < sizeof(pkt->hdr) ||
-				     len > sizeof(pkt->hdr) + pkt->len)) {
-				virtio_transport_free_pkt(pkt);
-				continue;
-			}
-
-			pkt->len = len - sizeof(pkt->hdr);
-			virtio_transport_deliver_tap_pkt(pkt);
-			virtio_transport_recv_pkt(pkt);
-		}
-	} while (!virtqueue_enable_cb(vq));
-
-out:
-	if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2)
-		virtio_vsock_rx_fill(vsock);
-	mutex_unlock(&vsock->rx_lock);
-}
-
 /* event_lock must be held */
 static int virtio_vsock_event_fill_one(struct virtio_vsock *vsock,
 				       struct virtio_vsock_event *event)
@@ -455,6 +412,9 @@ static void virtio_transport_event_work(struct work_struct *work)
 
 	mutex_lock(&vsock->event_lock);
 
+	if (!vsock->event_run)
+		goto out;
+
 	do {
 		struct virtio_vsock_event *event;
 		unsigned int len;
@@ -469,7 +429,7 @@ static void virtio_transport_event_work(struct work_struct *work)
 	} while (!virtqueue_enable_cb(vq));
 
 	virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]);
-
+out:
 	mutex_unlock(&vsock->event_lock);
 }
 
@@ -546,6 +506,86 @@ static struct virtio_transport virtio_transport = {
 	.send_pkt = virtio_transport_send_pkt,
 };
 
+static void virtio_transport_loopback_work(struct work_struct *work)
+{
+	struct virtio_vsock *vsock =
+		container_of(work, struct virtio_vsock, loopback_work);
+	LIST_HEAD(pkts);
+
+	spin_lock_bh(&vsock->loopback_list_lock);
+	list_splice_init(&vsock->loopback_list, &pkts);
+	spin_unlock_bh(&vsock->loopback_list_lock);
+
+	mutex_lock(&vsock->rx_lock);
+
+	if (!vsock->rx_run)
+		goto out;
+
+	while (!list_empty(&pkts)) {
+		struct virtio_vsock_pkt *pkt;
+
+		pkt = list_first_entry(&pkts, struct virtio_vsock_pkt, list);
+		list_del_init(&pkt->list);
+
+		virtio_transport_recv_pkt(&virtio_transport, pkt);
+	}
+out:
+	mutex_unlock(&vsock->rx_lock);
+}
+
+static void virtio_transport_rx_work(struct work_struct *work)
+{
+	struct virtio_vsock *vsock =
+		container_of(work, struct virtio_vsock, rx_work);
+	struct virtqueue *vq;
+
+	vq = vsock->vqs[VSOCK_VQ_RX];
+
+	mutex_lock(&vsock->rx_lock);
+
+	if (!vsock->rx_run)
+		goto out;
+
+	do {
+		virtqueue_disable_cb(vq);
+		for (;;) {
+			struct virtio_vsock_pkt *pkt;
+			unsigned int len;
+
+			if (!virtio_transport_more_replies(vsock)) {
+				/* Stop rx until the device processes already
+				 * pending replies.  Leave rx virtqueue
+				 * callbacks disabled.
+				 */
+				goto out;
+			}
+
+			pkt = virtqueue_get_buf(vq, &len);
+			if (!pkt) {
+				break;
+			}
+
+			vsock->rx_buf_nr--;
+
+			/* Drop short/long packets */
+			if (unlikely(len < sizeof(pkt->hdr) ||
+				     len > sizeof(pkt->hdr) + pkt->len)) {
+				virtio_transport_free_pkt(pkt);
+				continue;
+			}
+
+			pkt->len = len - sizeof(pkt->hdr);
+			virtio_transport_deliver_tap_pkt(pkt);
+			virtio_transport_recv_pkt(&virtio_transport, pkt);
+		}
+	} while (!virtqueue_enable_cb(vq));
+
+out:
+	if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2)
+		virtio_vsock_rx_fill(vsock);
+	mutex_unlock(&vsock->rx_lock);
+}
+
 static int virtio_vsock_probe(struct virtio_device *vdev)
 {
 	vq_callback_t *callbacks[] = {
@@ -566,7 +606,8 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
 		return ret;
 
 	/* Only one virtio-vsock device per guest is supported */
-	if (the_virtio_vsock) {
+	if (rcu_dereference_protected(the_virtio_vsock,
+				lockdep_is_held(&the_virtio_vsock_mutex))) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -591,8 +632,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
 	vsock->rx_buf_max_nr = 0;
 	atomic_set(&vsock->queued_replies, 0);
 
-	vdev->priv = vsock;
-	the_virtio_vsock = vsock;
 	mutex_init(&vsock->tx_lock);
 	mutex_init(&vsock->rx_lock);
 	mutex_init(&vsock->event_lock);
@@ -606,14 +645,23 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
 	INIT_WORK(&vsock->send_pkt_work, virtio_transport_send_pkt_work);
 	INIT_WORK(&vsock->loopback_work, virtio_transport_loopback_work);
 
+	mutex_lock(&vsock->tx_lock);
+	vsock->tx_run = true;
+	mutex_unlock(&vsock->tx_lock);
+
 	mutex_lock(&vsock->rx_lock);
 	virtio_vsock_rx_fill(vsock);
+	vsock->rx_run = true;
 	mutex_unlock(&vsock->rx_lock);
 
 	mutex_lock(&vsock->event_lock);
 	virtio_vsock_event_fill(vsock);
+	vsock->event_run = true;
 	mutex_unlock(&vsock->event_lock);
 
+	vdev->priv = vsock;
+	rcu_assign_pointer(the_virtio_vsock, vsock);
+
 	mutex_unlock(&the_virtio_vsock_mutex);
 	return 0;
 
@@ -628,6 +676,12 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
 	struct virtio_vsock *vsock = vdev->priv;
 	struct virtio_vsock_pkt *pkt;
 
+	mutex_lock(&the_virtio_vsock_mutex);
+
+	vdev->priv = NULL;
+	rcu_assign_pointer(the_virtio_vsock, NULL);
+	synchronize_rcu();
+
 	flush_work(&vsock->loopback_work);
 	flush_work(&vsock->rx_work);
 	flush_work(&vsock->tx_work);
@@ -637,6 +691,24 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
 	/* Reset all connected sockets when the device disappear */
 	vsock_for_each_connected_socket(virtio_vsock_reset_sock);
 
+	/* Stop all work handlers to make sure no one is accessing the device,
+	 * so we can safely call vdev->config->reset().
+	 */
+	mutex_lock(&vsock->rx_lock);
+	vsock->rx_run = false;
+	mutex_unlock(&vsock->rx_lock);
+
+	mutex_lock(&vsock->tx_lock);
+	vsock->tx_run = false;
+	mutex_unlock(&vsock->tx_lock);
+
+	mutex_lock(&vsock->event_lock);
+	vsock->event_run = false;
+	mutex_unlock(&vsock->event_lock);
+
+	/* Flush all device writes and interrupts, device will not use any
+	 * more buffers.
+	 */
 	vdev->config->reset(vdev);
 
 	mutex_lock(&vsock->rx_lock);
@@ -667,12 +739,11 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
 	}
 	spin_unlock_bh(&vsock->loopback_list_lock);
 
-	mutex_lock(&the_virtio_vsock_mutex);
-	the_virtio_vsock = NULL;
-	mutex_unlock(&the_virtio_vsock_mutex);
-
+	/* Delete virtqueues and flush outstanding callbacks if any */
 	vdev->config->del_vqs(vdev);
 
+	mutex_unlock(&the_virtio_vsock_mutex);
+
 	kfree(vsock);
 }
 
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index d20f43057323..8e4c13cc61ba 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -669,9 +669,9 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
 /* Normally packets are associated with a socket.  There may be no socket if an
  * attempt was made to connect to a socket that does not exist.
  */
-static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt)
+static int virtio_transport_reset_no_sock(const struct virtio_transport *t,
+					  struct virtio_vsock_pkt *pkt)
 {
-	const struct virtio_transport *t;
 	struct virtio_vsock_pkt *reply;
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_RST,
@@ -691,7 +691,6 @@ static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt)
 	if (!reply)
 		return -ENOMEM;
 
-	t = virtio_transport_get_ops();
 	if (!t) {
 		virtio_transport_free_pkt(reply);
 		return -ENOTCONN;
@@ -989,7 +988,8 @@ static bool virtio_transport_space_update(struct sock *sk,
 /* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex
  * lock.
  */
-void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt)
+void virtio_transport_recv_pkt(struct virtio_transport *t,
+			       struct virtio_vsock_pkt *pkt)
 {
 	struct sockaddr_vm src, dst;
 	struct vsock_sock *vsk;
@@ -1011,7 +1011,7 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt)
 					le32_to_cpu(pkt->hdr.fwd_cnt));
 
 	if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) {
-		(void)virtio_transport_reset_no_sock(pkt);
+		(void)virtio_transport_reset_no_sock(t, pkt);
 		goto free_pkt;
 	}
 
@@ -1022,7 +1022,7 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt)
 	if (!sk) {
 		sk = vsock_find_bound_socket(&dst);
 		if (!sk) {
-			(void)virtio_transport_reset_no_sock(pkt);
+			(void)virtio_transport_reset_no_sock(t, pkt);
 			goto free_pkt;
 		}
 	}
@@ -1056,6 +1056,7 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt)
 		virtio_transport_free_pkt(pkt);
 		break;
 	default:
+		(void)virtio_transport_reset_no_sock(t, pkt);
 		virtio_transport_free_pkt(pkt);
 		break;
 	}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d0b75781e6f7..bf3caa376f9f 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3343,6 +3343,9 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		return err;
 
+	if (key.idx < 0)
+		return -EINVAL;
+
 	if (info->attrs[NL80211_ATTR_MAC])
 		mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]);
 
@@ -11859,13 +11862,13 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info)
 				if (!wdev_running(wdev))
 					return -ENETDOWN;
 			}
-
-			if (!vcmd->doit)
-				return -EOPNOTSUPP;
 		} else {
 			wdev = NULL;
 		}
 
+		if (!vcmd->doit)
+			return -EOPNOTSUPP;
+
 		if (info->attrs[NL80211_ATTR_VENDOR_DATA]) {
 			data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]);
 			len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]);
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index b95d1c2bdef7..9eb9d34cef7b 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2408,6 +2408,9 @@ int regulatory_hint_user(const char *alpha2,
 	if (WARN_ON(!alpha2))
 		return -EINVAL;
 
+	if (!is_world_regdom(alpha2) && !is_an_alpha2(alpha2))
+		return -EINVAL;
+
 	request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
 	if (!request)
 		return -ENOMEM;
diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c
index db0b1315d577..a946c1cfb5a2 100644
--- a/net/x25/x25_subr.c
+++ b/net/x25/x25_subr.c
@@ -363,6 +363,12 @@ void x25_disconnect(struct sock *sk, int reason, unsigned char cause,
 		sk->sk_state_change(sk);
 		sock_set_flag(sk, SOCK_DEAD);
 	}
+	if (x25->neighbour) {
+		read_lock_bh(&x25_list_lock);
+		x25_neigh_put(x25->neighbour);
+		x25->neighbour = NULL;
+		read_unlock_bh(&x25_list_lock);
+	}
 }
 
 /*
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 311597401b82..874735742152 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -402,7 +402,7 @@ resume:
 		dev_put(skb->dev);
 
 		spin_lock(&x->lock);
-		if (nexthdr <= 0) {
+		if (nexthdr < 0) {
 			if (nexthdr == -EBADMSG) {
 				xfrm_audit_state_icvfail(x, skb,
 							 x->type->proto);
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index b226b230e8bf..80760a753d72 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -236,18 +236,20 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 		xfrm_state_hold(x);
 
 		if (skb_is_gso(skb)) {
-			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+			if (skb->inner_protocol)
+				return xfrm_output_gso(net, sk, skb);
 
-			return xfrm_output2(net, sk, skb);
+			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+			goto out;
 		}
 
 		if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)
 			goto out;
+	} else {
+		if (skb_is_gso(skb))
+			return xfrm_output_gso(net, sk, skb);
 	}
 
-	if (skb_is_gso(skb))
-		return xfrm_output_gso(net, sk, skb);
-
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		err = skb_checksum_help(skb);
 		if (err) {
@@ -284,7 +286,8 @@ void xfrm_local_error(struct sk_buff *skb, int mtu)
 
 	if (skb->protocol == htons(ETH_P_IP))
 		proto = AF_INET;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+	else if (skb->protocol == htons(ETH_P_IPV6) &&
+		 skb->sk->sk_family == AF_INET6)
 		proto = AF_INET6;
 	else
 		return;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f76bb5237df3..f8fd0aebf771 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -722,12 +722,7 @@ static void xfrm_policy_requeue(struct xfrm_policy *old,
 static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
 				   struct xfrm_policy *pol)
 {
-	u32 mark = policy->mark.v & policy->mark.m;
-
-	if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m)
-		return true;
-
-	if ((mark & pol->mark.m) == pol->mark.v &&
+	if (policy->mark.v == pol->mark.v &&
 	    policy->priority == pol->priority)
 		return true;
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 190ca59d5ba3..05c275a712f1 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -909,7 +909,8 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
 	 */
 	if (x->km.state == XFRM_STATE_VALID) {
 		if ((x->sel.family &&
-		     !xfrm_selector_match(&x->sel, fl, x->sel.family)) ||
+		     (x->sel.family != family ||
+		      !xfrm_selector_match(&x->sel, fl, family))) ||
 		    !security_xfrm_state_pol_flow_match(x, pol, fl))
 			return;
 
@@ -922,7 +923,9 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
 		*acq_in_progress = 1;
 	} else if (x->km.state == XFRM_STATE_ERROR ||
 		   x->km.state == XFRM_STATE_EXPIRED) {
-		if (xfrm_selector_match(&x->sel, fl, x->sel.family) &&
+		if ((!x->sel.family ||
+		     (x->sel.family == family &&
+		      xfrm_selector_match(&x->sel, fl, family))) &&
 		    security_xfrm_state_pol_flow_match(x, pol, fl))
 			*error = -ESRCH;
 	}
@@ -961,7 +964,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		    tmpl->mode == x->props.mode &&
 		    tmpl->id.proto == x->id.proto &&
 		    (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
-			xfrm_state_look_at(pol, x, fl, encap_family,
+			xfrm_state_look_at(pol, x, fl, family,
 					   &best, &acquire_in_progress, &error);
 	}
 	if (best || acquire_in_progress)
@@ -977,7 +980,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		    tmpl->mode == x->props.mode &&
 		    tmpl->id.proto == x->id.proto &&
 		    (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
-			xfrm_state_look_at(pol, x, fl, encap_family,
+			xfrm_state_look_at(pol, x, fl, family,
 					   &best, &acquire_in_progress, &error);
 	}
 
@@ -1320,6 +1323,30 @@ out:
 EXPORT_SYMBOL(xfrm_state_add);
 
 #ifdef CONFIG_XFRM_MIGRATE
+static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security)
+{
+	struct xfrm_user_sec_ctx *uctx;
+	int size = sizeof(*uctx) + security->ctx_len;
+	int err;
+
+	uctx = kmalloc(size, GFP_KERNEL);
+	if (!uctx)
+		return -ENOMEM;
+
+	uctx->exttype = XFRMA_SEC_CTX;
+	uctx->len = size;
+	uctx->ctx_doi = security->ctx_doi;
+	uctx->ctx_alg = security->ctx_alg;
+	uctx->ctx_len = security->ctx_len;
+	memcpy(uctx + 1, security->ctx_str, security->ctx_len);
+	err = security_xfrm_state_alloc(x, uctx);
+	kfree(uctx);
+	if (err)
+		return err;
+
+	return 0;
+}
+
 static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 					   struct xfrm_encap_tmpl *encap)
 {
@@ -1376,6 +1403,10 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 			goto error;
 	}
 
+	if (orig->security)
+		if (clone_security(x, orig->security))
+			goto error;
+
 	if (orig->coaddr) {
 		x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr),
 				    GFP_KERNEL);
@@ -1399,7 +1430,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 	x->tfcpad = orig->tfcpad;
 	x->replay_maxdiff = orig->replay_maxdiff;
 	x->replay_maxage = orig->replay_maxage;
-	x->curlft.add_time = orig->curlft.add_time;
+	memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft));
 	x->km.state = orig->km.state;
 	x->km.seq = orig->km.seq;
 	x->replay = orig->replay;
diff --git a/samples/bpf/lwt_len_hist_user.c b/samples/bpf/lwt_len_hist_user.c
index 7fcb94c09112..965108527a4f 100644
--- a/samples/bpf/lwt_len_hist_user.c
+++ b/samples/bpf/lwt_len_hist_user.c
@@ -15,8 +15,6 @@
 #define MAX_INDEX 64
 #define MAX_STARS 38
 
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
-
 static void stars(char *str, long val, long max, int width)
 {
 	int i;
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index a33fa1a91873..28bfb4378dbd 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -82,20 +82,21 @@ cc-cross-prefix =  \
 		fi)))
 
 # output directory for tests below
-TMPOUT := $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/)
+TMPOUT = $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/).tmp_$$$$
 
 # try-run
 # Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise)
 # Exit code chooses option. "$$TMP" serves as a temporary file and is
 # automatically cleaned up.
 try-run = $(shell set -e;		\
-	TMP="$(TMPOUT).$$$$.tmp";	\
-	TMPO="$(TMPOUT).$$$$.o";	\
+	TMP=$(TMPOUT)/tmp;		\
+	TMPO=$(TMPOUT)/tmp.o;		\
+	mkdir -p $(TMPOUT);		\
+	trap "rm -rf $(TMPOUT)" EXIT;	\
 	if ($(1)) >/dev/null 2>&1;	\
 	then echo "$(2)";		\
 	else echo "$(3)";		\
-	fi;				\
-	rm -f "$$TMP" "$$TMPO")
+	fi)
 
 # as-option
 # Usage: cflags-y += $(call as-option,-Wa$(comma)-isa=foo,)
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 8b80bac055e4..d702bdf19eb1 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2428,8 +2428,8 @@ sub process {
 
 # Check if the commit log has what seems like a diff which can confuse patch
 		if ($in_commit_log && !$commit_log_has_diff &&
-		    (($line =~ m@^\s+diff\b.*a/[\w/]+@ &&
-		      $line =~ m@^\s+diff\b.*a/([\w/]+)\s+b/$1\b@) ||
+		    (($line =~ m@^\s+diff\b.*a/([\w/]+)@ &&
+		      $line =~ m@^\s+diff\b.*a/[\w/]+\s+b/$1\b@) ||
 		     $line =~ m@^\s*(?:\-\-\-\s+a/|\+\+\+\s+b/)@ ||
 		     $line =~ m/^\s*\@\@ \-\d+,\d+ \+\d+,\d+ \@\@/)) {
 			ERROR("DIFF_IN_COMMIT_MSG",
diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh
index 5aa75a0a1ced..946735bd5a25 100755
--- a/scripts/decode_stacktrace.sh
+++ b/scripts/decode_stacktrace.sh
@@ -77,8 +77,8 @@ parse_symbol() {
 		return
 	fi
 
-	# Strip out the base of the path
-	code=${code#$basepath/}
+	# Strip out the base of the path on each line
+	code=$(while read -r line; do echo "${line#$basepath/}"; done <<< "$code")
 
 	# In the case of inlines, move everything to same line
 	code=${code//$'\n'/' '}
diff --git a/scripts/kconfig/lxdialog/check-lxdialog.sh b/scripts/kconfig/lxdialog/check-lxdialog.sh
index a10bd9d6fafd..1520dc04d399 100755..100644
--- a/scripts/kconfig/lxdialog/check-lxdialog.sh
+++ b/scripts/kconfig/lxdialog/check-lxdialog.sh
@@ -5,6 +5,10 @@
 # What library to link
 ldflags()
 {
+	if [ "$CROSS_CURSES_LIB" != "" ]; then
+		echo "$CROSS_CURSES_LIB"
+		exit
+	fi
 	pkg-config --libs ncursesw 2>/dev/null && exit
 	pkg-config --libs ncurses 2>/dev/null && exit
 	for ext in so a dll.a dylib ; do
@@ -22,6 +26,10 @@ ldflags()
 # Where is ncurses.h?
 ccflags()
 {
+	if [ x"$CROSS_CURSES_INC" != x ]; then
+		echo "$CROSS_CURSES_INC"
+		exit
+	fi
 	if pkg-config --cflags ncursesw 2>/dev/null; then
 		echo '-DCURSES_LOC="<ncurses.h>" -DNCURSES_WIDECHAR=1'
 	elif pkg-config --cflags ncurses 2>/dev/null; then
diff --git a/scripts/mksysmap b/scripts/mksysmap
index a35acc0d0b82..9aa23d15862a 100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -41,4 +41,4 @@
 # so we just ignore them to let readprofile continue to work.
 # (At least sparc64 has __crc_ in the middle).
 
-$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)\|\( .L\)' > $2
+$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)\|\( \.L\)' > $2
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index b6eb929899c5..d17a48851634 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -385,9 +385,10 @@ failed:
   * spaces in the beginning of the line is trimmed away.
   * Return a pointer to a static buffer.
   **/
+#define MODPOST_MAX_LINE 32768
 char *get_next_line(unsigned long *pos, void *file, unsigned long size)
 {
-	static char line[4096];
+	static char line[MODPOST_MAX_LINE];
 	int skip = 1;
 	size_t len = 0;
 	signed char *p = (signed char *)file + *pos;
@@ -402,8 +403,11 @@ char *get_next_line(unsigned long *pos, void *file, unsigned long size)
 		if (*p != '\n' && (*pos < size)) {
 			len++;
 			*s++ = *p++;
-			if (len > 4095)
+			if (len > (sizeof(line)-1)) {
+				warn(" %s: line exceeds buffer size %zu bytes\n"
+				     , __func__, sizeof(line));
 				break; /* Too long, stop */
+			}
 		} else {
 			/* End of string */
 			*s = '\0';
@@ -1961,7 +1965,7 @@ static void read_symbols(char *modname)
 	char *version;
 	char *license;
 	struct module *mod;
-	struct elf_info info = { };
+	struct elf_info info = { .hdr = NULL };
 	Elf_Sym *sym;
 
 	if (!parse_elf(&info, modname))
@@ -2408,7 +2412,7 @@ static int dump_sym(struct symbol *sym)
 
 static void write_dump(const char *fname)
 {
-	struct buffer buf = { };
+	struct buffer buf = { NULL, 0, 0 };
 	struct symbol *symbol;
 	int n;
 
@@ -2435,7 +2439,7 @@ struct ext_sym_list {
 int main(int argc, char **argv)
 {
 	struct module *mod;
-	struct buffer buf = { };
+	struct buffer buf = { NULL, 0, 0 };
 	char *kernel_read = NULL, *module_read = NULL;
 	char *dump_write = NULL, *files_source = NULL;
 	int opt;
diff --git a/security/apparmor/label.c b/security/apparmor/label.c
index ea63710442ae..212a0f39ddae 100644
--- a/security/apparmor/label.c
+++ b/security/apparmor/label.c
@@ -1536,13 +1536,13 @@ static const char *label_modename(struct aa_ns *ns, struct aa_label *label,
 
 	label_for_each(i, label, profile) {
 		if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS)) {
-			if (profile->mode == APPARMOR_UNCONFINED)
+			count++;
+			if (profile == profile->ns->unconfined)
 				/* special case unconfined so stacks with
 				 * unconfined don't report as mixed. ie.
 				 * profile_foo//&:ns1:unconfined (mixed)
 				 */
 				continue;
-			count++;
 			if (mode == -1)
 				mode = profile->mode;
 			else if (mode != profile->mode)
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 4f08023101f3..1c6b389ad8f9 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -123,11 +123,11 @@ static int apparmor_ptrace_traceme(struct task_struct *parent)
 	struct aa_label *tracer, *tracee;
 	int error;
 
-	tracee = begin_current_label_crit_section();
+	tracee = __begin_current_label_crit_section();
 	tracer = aa_get_task_label(parent);
 	error = aa_may_ptrace(tracer, tracee, AA_PTRACE_TRACE);
 	aa_put_label(tracer);
-	end_current_label_crit_section(tracee);
+	__end_current_label_crit_section(tracee);
 
 	return error;
 }
diff --git a/security/commoncap.c b/security/commoncap.c
index ae26ef006988..887321acc01f 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -711,6 +711,7 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 	int ret;
 	kuid_t root_uid;
 
+	new->cap_ambient = old->cap_ambient;
 	if (WARN_ON(!cap_ambient_invariant_ok(old)))
 		return -EPERM;
 
@@ -1269,12 +1270,14 @@ int cap_mmap_addr(unsigned long addr)
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(cap_mmap_addr);
 
 int cap_mmap_file(struct file *file, unsigned long reqprot,
 		  unsigned long prot, unsigned long flags)
 {
 	return 0;
 }
+EXPORT_SYMBOL_GPL(cap_mmap_file);
 
 #ifdef CONFIG_SECURITY
 
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index ea014df89428..e434a0618fcd 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -8,6 +8,7 @@
 #include <linux/device_cgroup.h>
 #include <linux/cgroup.h>
 #include <linux/ctype.h>
+#include <linux/export.h>
 #include <linux/list.h>
 #include <linux/uaccess.h>
 #include <linux/seq_file.h>
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index 73791d22ae07..d5843cfa83e7 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -240,7 +240,7 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry,
 
 	/* Portable EVM signatures must include an IMA hash */
 	if (type == EVM_XATTR_PORTABLE_DIGSIG && !ima_present)
-		return -EPERM;
+		error = -EPERM;
 out:
 	kfree(xattr_value);
 	kfree(desc);
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index d52b487ad259..186a3158edef 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -40,7 +40,7 @@ enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
 #define IMA_DIGEST_SIZE		SHA1_DIGEST_SIZE
 #define IMA_EVENT_NAME_LEN_MAX	255
 
-#define IMA_HASH_BITS 9
+#define IMA_HASH_BITS 10
 #define IMA_MEASURE_HTABLE_SIZE (1 << IMA_HASH_BITS)
 
 #define IMA_TEMPLATE_FIELD_ID_MAX_LEN	16
@@ -167,9 +167,10 @@ struct ima_h_table {
 };
 extern struct ima_h_table ima_htable;
 
-static inline unsigned long ima_hash_key(u8 *digest)
+static inline unsigned int ima_hash_key(u8 *digest)
 {
-	return hash_long(*digest, IMA_HASH_BITS);
+	/* there is no point in taking a hash of part of a digest */
+	return (digest[0] | digest[1] << 8) % IMA_MEASURE_HTABLE_SIZE;
 }
 
 #define __ima_hooks(hook)		\
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 4c160bee67f7..46b0bd6b3d62 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -170,7 +170,7 @@ static struct ima_rule_entry secure_boot_rules[] __ro_after_init = {
 static LIST_HEAD(ima_default_rules);
 static LIST_HEAD(ima_policy_rules);
 static LIST_HEAD(ima_temp_rules);
-static struct list_head *ima_rules;
+static struct list_head *ima_rules = &ima_default_rules;
 
 static int ima_policy __initdata;
 
@@ -468,7 +468,6 @@ void __init ima_init_policy(void)
 			temp_ima_appraise |= IMA_APPRAISE_POLICY;
 	}
 
-	ima_rules = &ima_default_rules;
 	ima_update_policy_flag();
 }
 
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 124273e500cf..d479ca71137e 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -306,15 +306,4 @@ static inline void key_check(const struct key *key)
 #define key_check(key) do {} while(0)
 
 #endif
-
-/*
- * Helper function to clear and free a kvmalloc'ed memory object.
- */
-static inline void __kvzfree(const void *addr, size_t len)
-{
-	if (addr) {
-		memset((void *)addr, 0, len);
-		kvfree(addr);
-	}
-}
 #endif /* _INTERNAL_H */
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index c07c2e2b2478..9394d72a77e8 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -133,10 +133,7 @@ SYSCALL_DEFINE5(add_key, const char __user *, _type,
 
 	key_ref_put(keyring_ref);
  error3:
-	if (payload) {
-		memzero_explicit(payload, plen);
-		kvfree(payload);
-	}
+	kvfree_sensitive(payload, plen);
  error2:
 	kfree(description);
  error:
@@ -351,7 +348,7 @@ long keyctl_update_key(key_serial_t id,
 
 	key_ref_put(key_ref);
 error2:
-	__kvzfree(payload, plen);
+	kvfree_sensitive(payload, plen);
 error:
 	return ret;
 }
@@ -859,7 +856,7 @@ can_read_key:
 		 */
 		if (ret > key_data_len) {
 			if (unlikely(key_data))
-				__kvzfree(key_data, key_data_len);
+				kvfree_sensitive(key_data, key_data_len);
 			key_data_len = ret;
 			continue;	/* Allocate buffer */
 		}
@@ -868,7 +865,7 @@ can_read_key:
 			ret = -EFAULT;
 		break;
 	}
-	__kvzfree(key_data, key_data_len);
+	kvfree_sensitive(key_data, key_data_len);
 
 key_put_out:
 	key_put(key);
@@ -1170,10 +1167,7 @@ long keyctl_instantiate_key_common(key_serial_t id,
 		keyctl_change_reqkey_auth(NULL);
 
 error2:
-	if (payload) {
-		memzero_explicit(payload, plen);
-		kvfree(payload);
-	}
+	kvfree_sensitive(payload, plen);
 error:
 	return ret;
 }
diff --git a/security/security.c b/security/security.c
index 4fbe4e495c02..e9393a37444a 100644
--- a/security/security.c
+++ b/security/security.c
@@ -532,6 +532,7 @@ int security_path_rmdir(const struct path *dir, struct dentry *dentry)
 		return 0;
 	return call_int_hook(path_rmdir, 0, dir, dentry);
 }
+EXPORT_SYMBOL_GPL(security_path_rmdir);
 
 int security_path_unlink(const struct path *dir, struct dentry *dentry)
 {
@@ -548,6 +549,7 @@ int security_path_symlink(const struct path *dir, struct dentry *dentry,
 		return 0;
 	return call_int_hook(path_symlink, 0, dir, dentry, old_name);
 }
+EXPORT_SYMBOL_GPL(security_path_symlink);
 
 int security_path_link(struct dentry *old_dentry, const struct path *new_dir,
 		       struct dentry *new_dentry)
@@ -556,6 +558,7 @@ int security_path_link(struct dentry *old_dentry, const struct path *new_dir,
 		return 0;
 	return call_int_hook(path_link, 0, old_dentry, new_dir, new_dentry);
 }
+EXPORT_SYMBOL_GPL(security_path_link);
 
 int security_path_rename(const struct path *old_dir, struct dentry *old_dentry,
 			 const struct path *new_dir, struct dentry *new_dentry,
@@ -583,6 +586,7 @@ int security_path_truncate(const struct path *path)
 		return 0;
 	return call_int_hook(path_truncate, 0, path);
 }
+EXPORT_SYMBOL_GPL(security_path_truncate);
 
 int security_path_chmod(const struct path *path, umode_t mode)
 {
@@ -590,6 +594,7 @@ int security_path_chmod(const struct path *path, umode_t mode)
 		return 0;
 	return call_int_hook(path_chmod, 0, path, mode);
 }
+EXPORT_SYMBOL_GPL(security_path_chmod);
 
 int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid)
 {
@@ -597,6 +602,7 @@ int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid)
 		return 0;
 	return call_int_hook(path_chown, 0, path, uid, gid);
 }
+EXPORT_SYMBOL_GPL(security_path_chown);
 
 int security_path_chroot(const struct path *path)
 {
@@ -682,6 +688,7 @@ int security_inode_readlink(struct dentry *dentry)
 		return 0;
 	return call_int_hook(inode_readlink, 0, dentry);
 }
+EXPORT_SYMBOL_GPL(security_inode_readlink);
 
 int security_inode_follow_link(struct dentry *dentry, struct inode *inode,
 			       bool rcu)
@@ -697,6 +704,7 @@ int security_inode_permission(struct inode *inode, int mask)
 		return 0;
 	return call_int_hook(inode_permission, 0, inode, mask);
 }
+EXPORT_SYMBOL_GPL(security_inode_permission);
 
 int security_inode_setattr(struct dentry *dentry, struct iattr *attr)
 {
@@ -868,6 +876,7 @@ int security_file_permission(struct file *file, int mask)
 
 	return fsnotify_perm(file, mask);
 }
+EXPORT_SYMBOL_GPL(security_file_permission);
 
 int security_file_alloc(struct file *file)
 {
@@ -927,6 +936,7 @@ int security_mmap_file(struct file *file, unsigned long prot,
 		return ret;
 	return ima_file_mmap(file, prot);
 }
+EXPORT_SYMBOL_GPL(security_mmap_file);
 
 int security_mmap_addr(unsigned long addr)
 {
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 00eed842c491..bf50fead9f8c 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -1425,6 +1425,7 @@ static struct avc_cache_stats *sel_avc_get_stat_idx(loff_t *idx)
 		*idx = cpu + 1;
 		return &per_cpu(avc_cache_stats, cpu);
 	}
+	(*idx)++;
 	return NULL;
 }
 
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index b275743e23cc..0158cde957ee 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -2736,8 +2736,12 @@ err:
 	if (*names) {
 		for (i = 0; i < *len; i++)
 			kfree((*names)[i]);
+		kfree(*names);
 	}
 	kfree(*values);
+	*len = 0;
+	*names = NULL;
+	*values = NULL;
 	goto out;
 }
 
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index f6482e53d55a..accd3846f1e3 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -906,11 +906,21 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf,
 	else
 		rule += strlen(skp->smk_known) + 1;
 
+	if (rule > data + count) {
+		rc = -EOVERFLOW;
+		goto out;
+	}
+
 	ret = sscanf(rule, "%d", &maplevel);
-	if (ret != 1 || maplevel > SMACK_CIPSO_MAXLEVEL)
+	if (ret != 1 || maplevel < 0 || maplevel > SMACK_CIPSO_MAXLEVEL)
 		goto out;
 
 	rule += SMK_DIGITLEN;
+	if (rule > data + count) {
+		rc = -EOVERFLOW;
+		goto out;
+	}
+
 	ret = sscanf(rule, "%d", &catlen);
 	if (ret != 1 || catlen > SMACK_CIPSO_MAXCATNUM)
 		goto out;
@@ -923,6 +933,10 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf,
 
 	for (i = 0; i < catlen; i++) {
 		rule += SMK_DIGITLEN;
+		if (rule > data + count) {
+			rc = -EOVERFLOW;
+			goto out;
+		}
 		ret = sscanf(rule, "%u", &cat);
 		if (ret != 1 || cat > SMACK_CIPSO_MAXCATNUM)
 			goto out;
@@ -2736,7 +2750,6 @@ static int smk_open_relabel_self(struct inode *inode, struct file *file)
 static ssize_t smk_write_relabel_self(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
-	struct task_smack *tsp = current_security();
 	char *data;
 	int rc;
 	LIST_HEAD(list_tmp);
@@ -2761,11 +2774,21 @@ static ssize_t smk_write_relabel_self(struct file *file, const char __user *buf,
 	kfree(data);
 
 	if (!rc || (rc == -EINVAL && list_empty(&list_tmp))) {
+		struct cred *new;
+		struct task_smack *tsp;
+
+		new = prepare_creds();
+		if (!new) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		tsp = new->security;
 		smk_destroy_label_list(&tsp->smk_relabel);
 		list_splice(&list_tmp, &tsp->smk_relabel);
+		commit_creds(new);
 		return count;
 	}
-
+out:
 	smk_destroy_label_list(&list_tmp);
 	return rc;
 }
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 7ae8e24dc1e6..81624f6e3f33 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -723,6 +723,9 @@ static int snd_compr_stop(struct snd_compr_stream *stream)
 
 	retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP);
 	if (!retval) {
+		/* clear flags and stop any drain wait */
+		stream->partial_drain = false;
+		stream->metadata_set = false;
 		snd_compr_drain_notify(stream);
 		stream->runtime->total_bytes_available = 0;
 		stream->runtime->total_bytes_transferred = 0;
@@ -880,6 +883,7 @@ static int snd_compr_partial_drain(struct snd_compr_stream *stream)
 	if (stream->next_track == false)
 		return -EPERM;
 
+	stream->partial_drain = true;
 	retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_PARTIAL_DRAIN);
 	if (retval) {
 		pr_debug("Partial drain returned failure\n");
diff --git a/sound/core/hwdep.c b/sound/core/hwdep.c
index a73baa1242be..727219f40201 100644
--- a/sound/core/hwdep.c
+++ b/sound/core/hwdep.c
@@ -229,14 +229,14 @@ static int snd_hwdep_dsp_load(struct snd_hwdep *hw,
 	if (copy_from_user(&info, _info, sizeof(info)))
 		return -EFAULT;
 	/* check whether the dsp was already loaded */
-	if (hw->dsp_loaded & (1 << info.index))
+	if (hw->dsp_loaded & (1u << info.index))
 		return -EBUSY;
 	if (!access_ok(VERIFY_READ, info.image, info.length))
 		return -EFAULT;
 	err = hw->ops.dsp_load(hw, &info);
 	if (err < 0)
 		return err;
-	hw->dsp_loaded |= (1 << info.index);
+	hw->dsp_loaded |= (1u << info.index);
 	return 0;
 }
 
diff --git a/sound/core/info.c b/sound/core/info.c
index 5fb00437507b..f15569cd124d 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -634,7 +634,9 @@ int snd_info_get_line(struct snd_info_buffer *buffer, char *line, int len)
 {
 	int c = -1;
 
-	if (snd_BUG_ON(!buffer || !buffer->buffer))
+	if (snd_BUG_ON(!buffer))
+		return 1;
+	if (!buffer->buffer)
 		return 1;
 	if (len <= 0 || buffer->stop || buffer->error)
 		return 1;
diff --git a/sound/core/oss/mulaw.c b/sound/core/oss/mulaw.c
index 3788906421a7..fe27034f2846 100644
--- a/sound/core/oss/mulaw.c
+++ b/sound/core/oss/mulaw.c
@@ -329,8 +329,8 @@ int snd_pcm_plugin_build_mulaw(struct snd_pcm_substream *plug,
 		snd_BUG();
 		return -EINVAL;
 	}
-	if (snd_BUG_ON(!snd_pcm_format_linear(format->format)))
-		return -ENXIO;
+	if (!snd_pcm_format_linear(format->format))
+		return -EINVAL;
 
 	err = snd_pcm_plugin_build(plug, "Mu-Law<->linear conversion",
 				   src_format, dst_format,
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 14b1ee29509d..071e09c3d855 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -1950,6 +1950,11 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd)
 	}
 	pcm_file = f.file->private_data;
 	substream1 = pcm_file->substream;
+	if (substream == substream1) {
+		res = -EINVAL;
+		goto _badf;
+	}
+
 	group = kmalloc(sizeof(*group), GFP_KERNEL);
 	if (!group) {
 		res = -ENOMEM;
diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c
index 8cdf489df80e..4b7897959913 100644
--- a/sound/core/seq/oss/seq_oss.c
+++ b/sound/core/seq/oss/seq_oss.c
@@ -181,10 +181,16 @@ static long
 odev_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct seq_oss_devinfo *dp;
+	long rc;
+
 	dp = file->private_data;
 	if (snd_BUG_ON(!dp))
 		return -ENXIO;
-	return snd_seq_oss_ioctl(dp, cmd, arg);
+
+	mutex_lock(&register_mutex);
+	rc = snd_seq_oss_ioctl(dp, cmd, arg);
+	mutex_unlock(&register_mutex);
+	return rc;
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/sound/drivers/opl3/opl3_synth.c b/sound/drivers/opl3/opl3_synth.c
index 42920a243328..3f94746d587a 100644
--- a/sound/drivers/opl3/opl3_synth.c
+++ b/sound/drivers/opl3/opl3_synth.c
@@ -104,6 +104,8 @@ int snd_opl3_ioctl(struct snd_hwdep * hw, struct file *file,
 		{
 			struct snd_dm_fm_info info;
 
+			memset(&info, 0, sizeof(info));
+
 			info.fm_mode = opl3->fm_mode;
 			info.rhythm = opl3->rhythm;
 			if (copy_to_user(argp, &info, sizeof(struct snd_dm_fm_info)))
diff --git a/sound/firewire/digi00x/digi00x.c b/sound/firewire/digi00x/digi00x.c
index ef689997d6a5..bf53e342788e 100644
--- a/sound/firewire/digi00x/digi00x.c
+++ b/sound/firewire/digi00x/digi00x.c
@@ -15,6 +15,7 @@ MODULE_LICENSE("GPL v2");
 #define VENDOR_DIGIDESIGN	0x00a07e
 #define MODEL_CONSOLE		0x000001
 #define MODEL_RACK		0x000002
+#define SPEC_VERSION		0x000001
 
 static int name_card(struct snd_dg00x *dg00x)
 {
@@ -185,14 +186,18 @@ static const struct ieee1394_device_id snd_dg00x_id_table[] = {
 	/* Both of 002/003 use the same ID. */
 	{
 		.match_flags = IEEE1394_MATCH_VENDOR_ID |
+			       IEEE1394_MATCH_VERSION |
 			       IEEE1394_MATCH_MODEL_ID,
 		.vendor_id = VENDOR_DIGIDESIGN,
+		.version = SPEC_VERSION,
 		.model_id = MODEL_CONSOLE,
 	},
 	{
 		.match_flags = IEEE1394_MATCH_VENDOR_ID |
+			       IEEE1394_MATCH_VERSION |
 			       IEEE1394_MATCH_MODEL_ID,
 		.vendor_id = VENDOR_DIGIDESIGN,
+		.version = SPEC_VERSION,
 		.model_id = MODEL_RACK,
 	},
 	{}
diff --git a/sound/firewire/tascam/tascam.c b/sound/firewire/tascam/tascam.c
index d3fdc463a884..1e61cdce2895 100644
--- a/sound/firewire/tascam/tascam.c
+++ b/sound/firewire/tascam/tascam.c
@@ -225,11 +225,39 @@ static void snd_tscm_remove(struct fw_unit *unit)
 }
 
 static const struct ieee1394_device_id snd_tscm_id_table[] = {
+	// Tascam, FW-1884.
 	{
 		.match_flags = IEEE1394_MATCH_VENDOR_ID |
-			       IEEE1394_MATCH_SPECIFIER_ID,
+			       IEEE1394_MATCH_SPECIFIER_ID |
+			       IEEE1394_MATCH_VERSION,
 		.vendor_id = 0x00022e,
 		.specifier_id = 0x00022e,
+		.version = 0x800000,
+	},
+	// Tascam, FE-8 (.version = 0x800001)
+	// This kernel module doesn't support FE-8 because the most of features
+	// can be implemented in userspace without any specific support of this
+	// module.
+	//
+	// .version = 0x800002 is unknown.
+	//
+	// Tascam, FW-1082.
+	{
+		.match_flags = IEEE1394_MATCH_VENDOR_ID |
+			       IEEE1394_MATCH_SPECIFIER_ID |
+			       IEEE1394_MATCH_VERSION,
+		.vendor_id = 0x00022e,
+		.specifier_id = 0x00022e,
+		.version = 0x800003,
+	},
+	// Tascam, FW-1804.
+	{
+		.match_flags = IEEE1394_MATCH_VENDOR_ID |
+			       IEEE1394_MATCH_SPECIFIER_ID |
+			       IEEE1394_MATCH_VERSION,
+		.vendor_id = 0x00022e,
+		.specifier_id = 0x00022e,
+		.version = 0x800004,
 	},
 	/* FE-08 requires reverse-engineering because it just has faders. */
 	{}
diff --git a/sound/hda/hdac_bus.c b/sound/hda/hdac_bus.c
index 714a51721a31..ab9236e4c157 100644
--- a/sound/hda/hdac_bus.c
+++ b/sound/hda/hdac_bus.c
@@ -155,6 +155,7 @@ static void process_unsol_events(struct work_struct *work)
 	struct hdac_driver *drv;
 	unsigned int rp, caddr, res;
 
+	spin_lock_irq(&bus->reg_lock);
 	while (bus->unsol_rp != bus->unsol_wp) {
 		rp = (bus->unsol_rp + 1) % HDA_UNSOL_QUEUE_SIZE;
 		bus->unsol_rp = rp;
@@ -166,10 +167,13 @@ static void process_unsol_events(struct work_struct *work)
 		codec = bus->caddr_tbl[caddr & 0x0f];
 		if (!codec || !codec->dev.driver)
 			continue;
+		spin_unlock_irq(&bus->reg_lock);
 		drv = drv_to_hdac_driver(codec->dev.driver);
 		if (drv->unsol_event)
 			drv->unsol_event(codec, res);
+		spin_lock_irq(&bus->reg_lock);
 	}
+	spin_unlock_irq(&bus->reg_lock);
 }
 
 /**
diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c
index 19deb306facb..4a843eb7cc94 100644
--- a/sound/hda/hdac_device.c
+++ b/sound/hda/hdac_device.c
@@ -123,6 +123,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_device_init);
 void snd_hdac_device_exit(struct hdac_device *codec)
 {
 	pm_runtime_put_noidle(&codec->dev);
+	/* keep balance of runtime PM child_count in parent device */
+	pm_runtime_set_suspended(&codec->dev);
 	snd_hdac_bus_remove_device(codec->bus, codec);
 	kfree(codec->vendor_name);
 	kfree(codec->chip_name);
diff --git a/sound/isa/es1688/es1688.c b/sound/isa/es1688/es1688.c
index a826c138e7f5..8a58ed168756 100644
--- a/sound/isa/es1688/es1688.c
+++ b/sound/isa/es1688/es1688.c
@@ -284,8 +284,10 @@ static int snd_es968_pnp_detect(struct pnp_card_link *pcard,
 		return error;
 	}
 	error = snd_es1688_probe(card, dev);
-	if (error < 0)
+	if (error < 0) {
+		snd_card_free(card);
 		return error;
+	}
 	pnp_set_card_drvdata(pcard, card);
 	snd_es968_pnp_is_probed = 1;
 	return 0;
diff --git a/sound/isa/wavefront/wavefront_synth.c b/sound/isa/wavefront/wavefront_synth.c
index 0b1e4b34b299..13c8e6542a2f 100644
--- a/sound/isa/wavefront/wavefront_synth.c
+++ b/sound/isa/wavefront/wavefront_synth.c
@@ -1175,7 +1175,10 @@ wavefront_send_alias (snd_wavefront_t *dev, wavefront_patch_info *header)
 				      "alias for %d\n",
 				      header->number,
 				      header->hdr.a.OriginalSample);
-    
+
+	if (header->number >= WF_MAX_SAMPLE)
+		return -EINVAL;
+
 	munge_int32 (header->number, &alias_hdr[0], 2);
 	munge_int32 (header->hdr.a.OriginalSample, &alias_hdr[2], 2);
 	munge_int32 (*((unsigned int *)&header->hdr.a.sampleStartOffset),
@@ -1206,6 +1209,9 @@ wavefront_send_multisample (snd_wavefront_t *dev, wavefront_patch_info *header)
 	int num_samples;
 	unsigned char *msample_hdr;
 
+	if (header->number >= WF_MAX_SAMPLE)
+		return -EINVAL;
+
 	msample_hdr = kmalloc(WF_MSAMPLE_BYTES, GFP_KERNEL);
 	if (! msample_hdr)
 		return -ENOMEM;
diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c
index b1a2a7ea4172..b4ccd9f92400 100644
--- a/sound/pci/asihpi/hpioctl.c
+++ b/sound/pci/asihpi/hpioctl.c
@@ -350,7 +350,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev,
 	struct hpi_message hm;
 	struct hpi_response hr;
 	struct hpi_adapter adapter;
-	struct hpi_pci pci;
+	struct hpi_pci pci = { 0 };
 
 	memset(&adapter, 0, sizeof(adapter));
 
@@ -506,7 +506,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev,
 	return 0;
 
 err:
-	for (idx = 0; idx < HPI_MAX_ADAPTER_MEM_SPACES; idx++) {
+	while (--idx >= 0) {
 		if (pci.ap_mem_base[idx]) {
 			iounmap(pci.ap_mem_base[idx]);
 			pci.ap_mem_base[idx] = NULL;
diff --git a/sound/pci/ca0106/ca0106_main.c b/sound/pci/ca0106/ca0106_main.c
index cd27b5536654..675b812e96d6 100644
--- a/sound/pci/ca0106/ca0106_main.c
+++ b/sound/pci/ca0106/ca0106_main.c
@@ -551,7 +551,8 @@ static int snd_ca0106_pcm_power_dac(struct snd_ca0106 *chip, int channel_id,
 		else
 			/* Power down */
 			chip->spi_dac_reg[reg] |= bit;
-		return snd_ca0106_spi_write(chip, chip->spi_dac_reg[reg]);
+		if (snd_ca0106_spi_write(chip, chip->spi_dac_reg[reg]) != 0)
+			return -ENXIO;
 	}
 	return 0;
 }
diff --git a/sound/pci/cs46xx/cs46xx_lib.c b/sound/pci/cs46xx/cs46xx_lib.c
index 0020fd0efc46..09c547f4cc18 100644
--- a/sound/pci/cs46xx/cs46xx_lib.c
+++ b/sound/pci/cs46xx/cs46xx_lib.c
@@ -780,7 +780,7 @@ static void snd_cs46xx_set_capture_sample_rate(struct snd_cs46xx *chip, unsigned
 		rate = 48000 / 9;
 
 	/*
-	 *  We can not capture at at rate greater than the Input Rate (48000).
+	 *  We can not capture at a rate greater than the Input Rate (48000).
 	 *  Return an error if an attempt is made to stray outside that limit.
 	 */
 	if (rate > 48000)
diff --git a/sound/pci/cs46xx/dsp_spos_scb_lib.c b/sound/pci/cs46xx/dsp_spos_scb_lib.c
index 7488e1b7a770..4e726d39b05d 100644
--- a/sound/pci/cs46xx/dsp_spos_scb_lib.c
+++ b/sound/pci/cs46xx/dsp_spos_scb_lib.c
@@ -1742,7 +1742,7 @@ int cs46xx_iec958_pre_open (struct snd_cs46xx *chip)
 	struct dsp_spos_instance * ins = chip->dsp_spos_instance;
 
 	if ( ins->spdif_status_out & DSP_SPDIF_STATUS_OUTPUT_ENABLED ) {
-		/* remove AsynchFGTxSCB and and PCMSerialInput_II */
+		/* remove AsynchFGTxSCB and PCMSerialInput_II */
 		cs46xx_dsp_disable_spdif_out (chip);
 
 		/* save state */
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index e1f0bcd45c37..b58a098a7270 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -2215,7 +2215,6 @@ static int snd_echo_resume(struct device *dev)
 	if (err < 0) {
 		kfree(commpage_bak);
 		dev_err(dev, "resume init_hw err=%d\n", err);
-		snd_echo_free(chip);
 		return err;
 	}
 
@@ -2242,7 +2241,6 @@ static int snd_echo_resume(struct device *dev)
 	if (request_irq(pci->irq, snd_echo_interrupt, IRQF_SHARED,
 			KBUILD_MODNAME, chip)) {
 		dev_err(chip->card->dev, "cannot grab irq\n");
-		snd_echo_free(chip);
 		return -EBUSY;
 	}
 	chip->irq = pci->irq;
diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c
index 8b1cf237b96e..c5dc8587d2ac 100644
--- a/sound/pci/hda/hda_auto_parser.c
+++ b/sound/pci/hda/hda_auto_parser.c
@@ -76,6 +76,12 @@ static int compare_input_type(const void *ap, const void *bp)
 	if (a->type != b->type)
 		return (int)(a->type - b->type);
 
+	/* If has both hs_mic and hp_mic, pick the hs_mic ahead of hp_mic. */
+	if (a->is_headset_mic && b->is_headphone_mic)
+		return -1; /* don't swap */
+	else if (a->is_headphone_mic && b->is_headset_mic)
+		return 1; /* swap */
+
 	/* In case one has boost and the other one has not,
 	   pick the one with boost first. */
 	return (int)(b->has_boost_on_pin - a->has_boost_on_pin);
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 7d65fe31c825..a56f018d586f 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -3394,7 +3394,7 @@ EXPORT_SYMBOL_GPL(snd_hda_set_power_save);
  * @nid: NID to check / update
  *
  * Check whether the given NID is in the amp list.  If it's in the list,
- * check the current AMP status, and update the the power-status according
+ * check the current AMP status, and update the power-status according
  * to the mute status.
  *
  * This function is supposed to be set or called from the check_power_status
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index fa261b27d858..8198d2e53b7d 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -1169,16 +1169,23 @@ irqreturn_t azx_interrupt(int irq, void *dev_id)
 		if (snd_hdac_bus_handle_stream_irq(bus, status, stream_update))
 			active = true;
 
-		/* clear rirb int */
 		status = azx_readb(chip, RIRBSTS);
 		if (status & RIRB_INT_MASK) {
+			/*
+			 * Clearing the interrupt status here ensures that no
+			 * interrupt gets masked after the RIRB wp is read in
+			 * snd_hdac_bus_update_rirb. This avoids a possible
+			 * race condition where codec response in RIRB may
+			 * remain unserviced by IRQ, eventually falling back
+			 * to polling mode in azx_rirb_get_response.
+			 */
+			azx_writeb(chip, RIRBSTS, RIRB_INT_MASK);
 			active = true;
 			if (status & RIRB_INT_RESPONSE) {
 				if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND)
 					udelay(80);
 				snd_hdac_bus_update_rirb(bus);
 			}
-			azx_writeb(chip, RIRBSTS, RIRB_INT_MASK);
 		}
 	} while (active && ++repeat < 10);
 
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 28ef409a9e6a..9dee657ce9e2 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -823,7 +823,7 @@ static void activate_amp_in(struct hda_codec *codec, struct nid_path *path,
 	}
 }
 
-/* sync power of each widget in the the given path */
+/* sync power of each widget in the given path */
 static hda_nid_t path_power_update(struct hda_codec *codec,
 				   struct nid_path *path,
 				   bool allow_powerdown)
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 7779f5460715..e399c5718ee6 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1282,6 +1282,7 @@ static void azx_vs_set_state(struct pci_dev *pci,
 	struct snd_card *card = pci_get_drvdata(pci);
 	struct azx *chip = card->private_data;
 	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
+	struct hda_codec *codec;
 	bool disabled;
 
 	wait_for_completion(&hda->probe_wait);
@@ -1306,8 +1307,12 @@ static void azx_vs_set_state(struct pci_dev *pci,
 		dev_info(chip->card->dev, "%s via vga_switcheroo\n",
 			 disabled ? "Disabling" : "Enabling");
 		if (disabled) {
-			pm_runtime_put_sync_suspend(card->dev);
-			azx_suspend(card->dev);
+			list_for_each_codec(codec, &chip->bus) {
+				pm_runtime_suspend(hda_codec_dev(codec));
+				pm_runtime_disable(hda_codec_dev(codec));
+			}
+			pm_runtime_suspend(card->dev);
+			pm_runtime_disable(card->dev);
 			/* when we get suspended by vga_switcheroo we end up in D3cold,
 			 * however we have no ACPI handle, so pci/acpi can't put us there,
 			 * put ourselves there */
@@ -1318,9 +1323,12 @@ static void azx_vs_set_state(struct pci_dev *pci,
 					 "Cannot lock devices!\n");
 		} else {
 			snd_hda_unlock_devices(&chip->bus);
-			pm_runtime_get_noresume(card->dev);
 			chip->disabled = false;
-			azx_resume(card->dev);
+			pm_runtime_enable(card->dev);
+			list_for_each_codec(codec, &chip->bus) {
+				pm_runtime_enable(hda_codec_dev(codec));
+				pm_runtime_resume(hda_codec_dev(codec));
+			}
 		}
 	}
 }
@@ -1350,6 +1358,7 @@ static void init_vga_switcheroo(struct azx *chip)
 		dev_info(chip->card->dev,
 			 "Handle vga_switcheroo audio client\n");
 		hda->use_vga_switcheroo = 1;
+		chip->driver_caps |= AZX_DCAPS_PM_RUNTIME;
 		pci_dev_put(p);
 	}
 }
@@ -1375,9 +1384,6 @@ static int register_vga_switcheroo(struct azx *chip)
 		return err;
 	hda->vga_switcheroo_registered = 1;
 
-	/* register as an optimus hdmi audio power domain */
-	vga_switcheroo_init_domain_pm_optimus_hdmi_audio(chip->card->dev,
-							 &hda->hdmi_pm_domain);
 	return 0;
 }
 #else
@@ -1406,10 +1412,8 @@ static int azx_free(struct azx *chip)
 	if (use_vga_switcheroo(hda)) {
 		if (chip->disabled && hda->probe_continued)
 			snd_hda_unlock_devices(&chip->bus);
-		if (hda->vga_switcheroo_registered) {
+		if (hda->vga_switcheroo_registered)
 			vga_switcheroo_unregister_client(chip->pci);
-			vga_switcheroo_fini_domain_pm_ops(chip->card->dev);
-		}
 	}
 
 	if (bus->chip_init) {
@@ -2301,6 +2305,7 @@ static int azx_probe_continue(struct azx *chip)
 	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
 	struct hdac_bus *bus = azx_bus(chip);
 	struct pci_dev *pci = chip->pci;
+	struct hda_codec *codec;
 	int dev = chip->dev_index;
 	int val;
 	int err;
@@ -2385,6 +2390,14 @@ static int azx_probe_continue(struct azx *chip)
 	chip->running = 1;
 	azx_add_card_list(chip);
 
+	/*
+	 * The discrete GPU cannot power down unless the HDA controller runtime
+	 * suspends, so activate runtime PM on codecs even if power_save == 0.
+	 */
+	if (use_vga_switcheroo(hda))
+		list_for_each_codec(codec, &chip->bus)
+			codec->auto_runtime_pm = 1;
+
 	val = power_save;
 #ifdef CONFIG_PM
 	if (pm_blacklist) {
@@ -2399,7 +2412,7 @@ static int azx_probe_continue(struct azx *chip)
 	}
 #endif /* CONFIG_PM */
 	snd_hda_set_power_save(&chip->bus, val * 1000);
-	if (azx_has_pm_runtime(chip) || hda->use_vga_switcheroo)
+	if (azx_has_pm_runtime(chip))
 		pm_runtime_put_autosuspend(&pci->dev);
 
 out_free:
diff --git a/sound/pci/hda/hda_intel.h b/sound/pci/hda/hda_intel.h
index ff0c4d617bc1..e3a3d318d2e5 100644
--- a/sound/pci/hda/hda_intel.h
+++ b/sound/pci/hda/hda_intel.h
@@ -40,9 +40,6 @@ struct hda_intel {
 	unsigned int vga_switcheroo_registered:1;
 	unsigned int init_failed:1; /* delayed init failed */
 
-	/* secondary power domain for hdmi audio under vga device */
-	struct dev_pm_domain hdmi_pm_domain;
-
 	bool need_i915_power:1; /* the hda controller needs i915 power */
 };
 
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 6b4ebaefd8f8..75bdcede04e6 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2546,6 +2546,7 @@ static void i915_pin_cvt_fixup(struct hda_codec *codec,
 			       hda_nid_t cvt_nid)
 {
 	if (per_pin) {
+		haswell_verify_D0(codec, per_pin->cvt_nid, per_pin->pin_nid);
 		snd_hda_set_dev_select(codec, per_pin->pin_nid,
 			       per_pin->dev_id);
 		intel_verify_pin_cvt_connect(codec, per_pin);
@@ -3398,6 +3399,7 @@ static int tegra_hdmi_build_pcms(struct hda_codec *codec)
 
 static int patch_tegra_hdmi(struct hda_codec *codec)
 {
+	struct hdmi_spec *spec;
 	int err;
 
 	err = patch_generic_hdmi(codec);
@@ -3405,6 +3407,10 @@ static int patch_tegra_hdmi(struct hda_codec *codec)
 		return err;
 
 	codec->patch_ops.build_pcms = tegra_hdmi_build_pcms;
+	spec = codec->spec;
+	spec->chmap.ops.chmap_cea_alloc_validate_get_type =
+		nvhdmi_chmap_cea_alloc_validate_get_type;
+	spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate;
 
 	return 0;
 }
@@ -3861,6 +3867,11 @@ HDA_CODEC_ENTRY(0x10de0095, "GPU 95 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0097, "GPU 97 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0098, "GPU 98 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0099, "GPU 99 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009a, "GPU 9a HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI",	patch_nvhdmi_2ch),
 HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI",	patch_nvhdmi_2ch),
 HDA_CODEC_ENTRY(0x11069f80, "VX900 HDMI/DP",	patch_via_hdmi),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c4e97b3ba1dd..c27623052264 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -341,6 +341,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0282:
 	case 0x10ec0283:
 	case 0x10ec0286:
+	case 0x10ec0287:
 	case 0x10ec0288:
 	case 0x10ec0285:
 	case 0x10ec0298:
@@ -3153,7 +3154,11 @@ static void alc256_shutup(struct hda_codec *codec)
 
 	/* 3k pull low control for Headset jack. */
 	/* NOTE: call this before clearing the pin, otherwise codec stalls */
-	alc_update_coef_idx(codec, 0x46, 0, 3 << 12);
+	/* If disable 3k pulldown control for alc257, the Mic detection will not work correctly
+	 * when booting with headset plugged. So skip setting it for the codec alc257
+	 */
+	if (codec->core.vendor_id != 0x10ec0257)
+		alc_update_coef_idx(codec, 0x46, 0, 3 << 12);
 
 	snd_hda_codec_write(codec, hp_pin, 0,
 			    AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
@@ -7130,6 +7135,12 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		ALC225_STANDARD_PINS,
 		{0x12, 0xb7a60130},
 		{0x17, 0x90170110}),
+	SND_HDA_PIN_QUIRK(0x10ec0623, 0x17aa, "Lenovo", ALC283_FIXUP_HEADSET_MIC,
+		{0x14, 0x01014010},
+		{0x17, 0x90170120},
+		{0x18, 0x02a11030},
+		{0x19, 0x02a1103f},
+		{0x21, 0x0221101f}),
 	{}
 };
 
@@ -7290,6 +7301,7 @@ static int patch_alc269(struct hda_codec *codec)
 	case 0x10ec0215:
 	case 0x10ec0245:
 	case 0x10ec0285:
+	case 0x10ec0287:
 	case 0x10ec0289:
 		spec->codec_variant = ALC269_TYPE_ALC215;
 		spec->gen.mixer_nid = 0;
@@ -8389,6 +8401,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0284, "ALC284", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0285, "ALC285", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0286, "ALC286", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0287, "ALC287", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0288, "ALC288", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0289, "ALC289", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0290, "ALC290", patch_alc269),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 7cd147411b22..f7896a9ae3d6 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -863,7 +863,7 @@ static int stac_auto_create_beep_ctls(struct hda_codec *codec,
 	static struct snd_kcontrol_new beep_vol_ctl =
 		HDA_CODEC_VOLUME(NULL, 0, 0, 0);
 
-	/* check for mute support for the the amp */
+	/* check for mute support for the amp */
 	if ((caps & AC_AMPCAP_MUTE) >> AC_AMPCAP_MUTE_SHIFT) {
 		const struct snd_kcontrol_new *temp;
 		if (spec->anabeep_nid == nid)
diff --git a/sound/pci/ice1712/prodigy192.c b/sound/pci/ice1712/prodigy192.c
index 3919aed39ca0..5e52086d7b98 100644
--- a/sound/pci/ice1712/prodigy192.c
+++ b/sound/pci/ice1712/prodigy192.c
@@ -31,7 +31,7 @@
  *		  Experimentally I found out that only a combination of
  *		  OCKS0=1, OCKS1=1 (128fs, 64fs output) and ice1724 -
  *		  VT1724_MT_I2S_MCLK_128X=0 (256fs input) yields correct
- *		  sampling rate. That means the the FPGA doubles the
+ *		  sampling rate. That means that the FPGA doubles the
  *		  MCK01 rate.
  *
  *	Copyright (c) 2003 Takashi Iwai <tiwai@suse.de>
diff --git a/sound/pci/oxygen/xonar_dg.c b/sound/pci/oxygen/xonar_dg.c
index 4cf3200e988b..df44135e1b0c 100644
--- a/sound/pci/oxygen/xonar_dg.c
+++ b/sound/pci/oxygen/xonar_dg.c
@@ -39,7 +39,7 @@
  *   GPIO 4 <- headphone detect
  *   GPIO 5 -> enable ADC analog circuit for the left channel
  *   GPIO 6 -> enable ADC analog circuit for the right channel
- *   GPIO 7 -> switch green rear output jack between CS4245 and and the first
+ *   GPIO 7 -> switch green rear output jack between CS4245 and the first
  *             channel of CS4361 (mechanical relay)
  *   GPIO 8 -> enable output to speakers
  *
diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c
index 3633eb30dd13..4f949ad50d6a 100644
--- a/sound/soc/codecs/msm8916-wcd-analog.c
+++ b/sound/soc/codecs/msm8916-wcd-analog.c
@@ -16,8 +16,8 @@
 
 #define CDC_D_REVISION1			(0xf000)
 #define CDC_D_PERPH_SUBTYPE		(0xf005)
-#define CDC_D_INT_EN_SET		(0x015)
-#define CDC_D_INT_EN_CLR		(0x016)
+#define CDC_D_INT_EN_SET		(0xf015)
+#define CDC_D_INT_EN_CLR		(0xf016)
 #define MBHC_SWITCH_INT			BIT(7)
 #define MBHC_MIC_ELECTRICAL_INS_REM_DET	BIT(6)
 #define MBHC_BUTTON_PRESS_DET		BIT(5)
diff --git a/sound/soc/codecs/rt5670.h b/sound/soc/codecs/rt5670.h
index 5ba485cae4e6..06d7c0aaeb61 100644
--- a/sound/soc/codecs/rt5670.h
+++ b/sound/soc/codecs/rt5670.h
@@ -760,7 +760,7 @@
 #define RT5670_PWR_VREF2_BIT			4
 #define RT5670_PWR_FV2				(0x1 << 3)
 #define RT5670_PWR_FV2_BIT			3
-#define RT5670_LDO_SEL_MASK			(0x3)
+#define RT5670_LDO_SEL_MASK			(0x7)
 #define RT5670_LDO_SEL_SFT			0
 
 /* Power Management for Analog 2 (0x64) */
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index e10e03800cce..6991718d7c8a 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -1747,8 +1747,10 @@ static int davinci_mcasp_get_dma_type(struct davinci_mcasp *mcasp)
 				PTR_ERR(chan));
 		return PTR_ERR(chan);
 	}
-	if (WARN_ON(!chan->device || !chan->device->dev))
+	if (WARN_ON(!chan->device || !chan->device->dev)) {
+		dma_release_channel(chan);
 		return -EINVAL;
+	}
 
 	if (chan->device->dev->of_node)
 		ret = of_property_read_string(chan->device->dev->of_node,
diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c
index e1b97e59275a..15d7e6da0555 100644
--- a/sound/soc/fsl/fsl_asrc_dma.c
+++ b/sound/soc/fsl/fsl_asrc_dma.c
@@ -243,6 +243,7 @@ static int fsl_asrc_dma_hw_params(struct snd_pcm_substream *substream,
 	ret = dmaengine_slave_config(pair->dma_chan[dir], &config_be);
 	if (ret) {
 		dev_err(dev, "failed to config DMA channel for Back-End\n");
+		dma_release_channel(pair->dma_chan[dir]);
 		return ret;
 	}
 
diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
index 4558c8b93036..3a645fc425cd 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
@@ -339,7 +339,7 @@ static int sst_media_open(struct snd_pcm_substream *substream,
 
 	ret_val = power_up_sst(stream);
 	if (ret_val < 0)
-		return ret_val;
+		goto out_power_up;
 
 	/* Make sure, that the period size is always even */
 	snd_pcm_hw_constraint_step(substream->runtime, 0,
@@ -348,8 +348,9 @@ static int sst_media_open(struct snd_pcm_substream *substream,
 	return snd_pcm_hw_constraint_integer(runtime,
 			 SNDRV_PCM_HW_PARAM_PERIODS);
 out_ops:
-	kfree(stream);
 	mutex_unlock(&sst_lock);
+out_power_up:
+	kfree(stream);
 	return ret_val;
 }
 
diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c
index 7843104fadcb..1b01bc318fd2 100644
--- a/sound/soc/intel/boards/bxt_rt298.c
+++ b/sound/soc/intel/boards/bxt_rt298.c
@@ -529,6 +529,7 @@ static int bxt_card_late_probe(struct snd_soc_card *card)
 /* broxton audio machine driver for SPT + RT298S */
 static struct snd_soc_card broxton_rt298 = {
 	.name = "broxton-rt298",
+	.owner = THIS_MODULE,
 	.dai_link = broxton_rt298_dais,
 	.num_links = ARRAY_SIZE(broxton_rt298_dais),
 	.controls = broxton_controls,
@@ -544,6 +545,7 @@ static struct snd_soc_card broxton_rt298 = {
 
 static struct snd_soc_card geminilake_rt298 = {
 	.name = "geminilake-rt298",
+	.owner = THIS_MODULE,
 	.dai_link = broxton_rt298_dais,
 	.num_links = ARRAY_SIZE(broxton_rt298_dais),
 	.controls = broxton_controls,
diff --git a/sound/soc/kirkwood/kirkwood-dma.c b/sound/soc/kirkwood/kirkwood-dma.c
index cf23af159acf..35ca8e8bb5e5 100644
--- a/sound/soc/kirkwood/kirkwood-dma.c
+++ b/sound/soc/kirkwood/kirkwood-dma.c
@@ -136,7 +136,7 @@ static int kirkwood_dma_open(struct snd_pcm_substream *substream)
 		err = request_irq(priv->irq, kirkwood_dma_irq, IRQF_SHARED,
 				  "kirkwood-i2s", priv);
 		if (err)
-			return -EBUSY;
+			return err;
 
 		/*
 		 * Enable Error interrupts. We're only ack'ing them but
diff --git a/sound/soc/rockchip/rockchip_pdm.c b/sound/soc/rockchip/rockchip_pdm.c
index 8a2e3bbce3a1..ad16c8310dd3 100644
--- a/sound/soc/rockchip/rockchip_pdm.c
+++ b/sound/soc/rockchip/rockchip_pdm.c
@@ -478,8 +478,10 @@ static int rockchip_pdm_resume(struct device *dev)
 	int ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put(dev);
 		return ret;
+	}
 
 	ret = regcache_sync(pdm->regmap);
 
diff --git a/sound/soc/tegra/tegra30_ahub.c b/sound/soc/tegra/tegra30_ahub.c
index 43679aeeb12b..88e838ac937d 100644
--- a/sound/soc/tegra/tegra30_ahub.c
+++ b/sound/soc/tegra/tegra30_ahub.c
@@ -655,8 +655,10 @@ static int tegra30_ahub_resume(struct device *dev)
 	int ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put(dev);
 		return ret;
+	}
 	ret = regcache_sync(ahub->regmap_ahub);
 	ret |= regcache_sync(ahub->regmap_apbif);
 	pm_runtime_put(dev);
diff --git a/sound/soc/tegra/tegra30_i2s.c b/sound/soc/tegra/tegra30_i2s.c
index 0b176ea24914..bf155c5092f0 100644
--- a/sound/soc/tegra/tegra30_i2s.c
+++ b/sound/soc/tegra/tegra30_i2s.c
@@ -551,8 +551,10 @@ static int tegra30_i2s_resume(struct device *dev)
 	int ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put(dev);
 		return ret;
+	}
 	ret = regcache_sync(i2s->regmap);
 	pm_runtime_put(dev);
 
diff --git a/sound/usb/card.c b/sound/usb/card.c
index 4169c71f8a32..721f91f5766d 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -768,9 +768,6 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message)
 	if (chip == (void *)-1L)
 		return 0;
 
-	chip->autosuspended = !!PMSG_IS_AUTO(message);
-	if (!chip->autosuspended)
-		snd_power_change_state(chip->card, SNDRV_CTL_POWER_D3hot);
 	if (!chip->num_suspended_intf++) {
 		list_for_each_entry(as, &chip->pcm_list, list) {
 			snd_pcm_suspend_all(as->pcm);
@@ -783,6 +780,11 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message)
 			snd_usb_mixer_suspend(mixer);
 	}
 
+	if (!PMSG_IS_AUTO(message) && !chip->system_suspend) {
+		snd_power_change_state(chip->card, SNDRV_CTL_POWER_D3hot);
+		chip->system_suspend = chip->num_suspended_intf;
+	}
+
 	return 0;
 }
 
@@ -795,10 +797,11 @@ static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume)
 
 	if (chip == (void *)-1L)
 		return 0;
-	if (--chip->num_suspended_intf)
-		return 0;
 
 	atomic_inc(&chip->active); /* avoid autopm */
+	if (chip->num_suspended_intf > 1)
+		goto out;
+
 	/*
 	 * ALSA leaves material resumption to user space
 	 * we just notify and restart the mixers
@@ -813,9 +816,12 @@ static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume)
 		snd_usbmidi_resume(p);
 	}
 
-	if (!chip->autosuspended)
+ out:
+	if (chip->num_suspended_intf == chip->system_suspend) {
 		snd_power_change_state(chip->card, SNDRV_CTL_POWER_D0);
-	chip->autosuspended = 0;
+		chip->system_suspend = 0;
+	}
+	chip->num_suspended_intf--;
 
 err_out:
 	atomic_dec(&chip->active); /* allow autopm after this point */
diff --git a/sound/usb/card.h b/sound/usb/card.h
index ed87cc83eb47..0cde519bfa42 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -126,6 +126,7 @@ struct snd_usb_substream {
 	unsigned int tx_length_quirk:1;	/* add length specifier to transfers */
 	unsigned int fmt_type;		/* USB audio format type (1-3) */
 	unsigned int pkt_offset_adj;	/* Bytes to drop from beginning of packets (for non-compliant devices) */
+	unsigned int stream_offset_adj;	/* Bytes to drop from beginning of stream (for non-compliant devices) */
 
 	unsigned int running: 1;	/* running status */
 
diff --git a/sound/usb/line6/capture.c b/sound/usb/line6/capture.c
index 7c812565f90d..a65a82d5791d 100644
--- a/sound/usb/line6/capture.c
+++ b/sound/usb/line6/capture.c
@@ -291,6 +291,8 @@ int line6_create_audio_in_urbs(struct snd_line6_pcm *line6pcm)
 		urb->interval = LINE6_ISO_INTERVAL;
 		urb->error_count = 0;
 		urb->complete = audio_in_callback;
+		if (usb_urb_ep_type_check(urb))
+			return -EINVAL;
 	}
 
 	return 0;
diff --git a/sound/usb/line6/playback.c b/sound/usb/line6/playback.c
index 812d18191e01..1736eb3ee98e 100644
--- a/sound/usb/line6/playback.c
+++ b/sound/usb/line6/playback.c
@@ -436,6 +436,8 @@ int line6_create_audio_out_urbs(struct snd_line6_pcm *line6pcm)
 		urb->interval = LINE6_ISO_INTERVAL;
 		urb->error_count = 0;
 		urb->complete = audio_out_callback;
+		if (usb_urb_ep_type_check(urb))
+			return -EINVAL;
 	}
 
 	return 0;
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index a92e2b2a91ec..a3d1c0c1b4a6 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1477,6 +1477,8 @@ void snd_usbmidi_disconnect(struct list_head *p)
 	spin_unlock_irq(&umidi->disc_lock);
 	up_write(&umidi->disc_rwsem);
 
+	del_timer_sync(&umidi->error_timer);
+
 	for (i = 0; i < MIDI_MAX_ENDPOINTS; ++i) {
 		struct snd_usb_midi_endpoint *ep = &umidi->endpoints[i];
 		if (ep->out)
@@ -1503,7 +1505,6 @@ void snd_usbmidi_disconnect(struct list_head *p)
 			ep->in = NULL;
 		}
 	}
-	del_timer_sync(&umidi->error_timer);
 }
 EXPORT_SYMBOL(snd_usbmidi_disconnect);
 
@@ -1804,6 +1805,28 @@ static int snd_usbmidi_create_endpoints(struct snd_usb_midi *umidi,
 	return 0;
 }
 
+static struct usb_ms_endpoint_descriptor *find_usb_ms_endpoint_descriptor(
+					struct usb_host_endpoint *hostep)
+{
+	unsigned char *extra = hostep->extra;
+	int extralen = hostep->extralen;
+
+	while (extralen > 3) {
+		struct usb_ms_endpoint_descriptor *ms_ep =
+				(struct usb_ms_endpoint_descriptor *)extra;
+
+		if (ms_ep->bLength > 3 &&
+		    ms_ep->bDescriptorType == USB_DT_CS_ENDPOINT &&
+		    ms_ep->bDescriptorSubtype == UAC_MS_GENERAL)
+			return ms_ep;
+		if (!extra[0])
+			break;
+		extralen -= extra[0];
+		extra += extra[0];
+	}
+	return NULL;
+}
+
 /*
  * Returns MIDIStreaming device capabilities.
  */
@@ -1841,11 +1864,8 @@ static int snd_usbmidi_get_ms_info(struct snd_usb_midi *umidi,
 		ep = get_ep_desc(hostep);
 		if (!usb_endpoint_xfer_bulk(ep) && !usb_endpoint_xfer_int(ep))
 			continue;
-		ms_ep = (struct usb_ms_endpoint_descriptor *)hostep->extra;
-		if (hostep->extralen < 4 ||
-		    ms_ep->bLength < 4 ||
-		    ms_ep->bDescriptorType != USB_DT_CS_ENDPOINT ||
-		    ms_ep->bDescriptorSubtype != UAC_MS_GENERAL)
+		ms_ep = find_usb_ms_endpoint_descriptor(hostep);
+		if (!ms_ep)
 			continue;
 		if (usb_endpoint_dir_out(ep)) {
 			if (endpoints[epidx].out_ep) {
@@ -2260,16 +2280,22 @@ void snd_usbmidi_input_stop(struct list_head *p)
 }
 EXPORT_SYMBOL(snd_usbmidi_input_stop);
 
-static void snd_usbmidi_input_start_ep(struct snd_usb_midi_in_endpoint *ep)
+static void snd_usbmidi_input_start_ep(struct snd_usb_midi *umidi,
+				       struct snd_usb_midi_in_endpoint *ep)
 {
 	unsigned int i;
+	unsigned long flags;
 
 	if (!ep)
 		return;
 	for (i = 0; i < INPUT_URBS; ++i) {
 		struct urb *urb = ep->urbs[i];
-		urb->dev = ep->umidi->dev;
-		snd_usbmidi_submit_urb(urb, GFP_KERNEL);
+		spin_lock_irqsave(&umidi->disc_lock, flags);
+		if (!atomic_read(&urb->use_count)) {
+			urb->dev = ep->umidi->dev;
+			snd_usbmidi_submit_urb(urb, GFP_ATOMIC);
+		}
+		spin_unlock_irqrestore(&umidi->disc_lock, flags);
 	}
 }
 
@@ -2285,7 +2311,7 @@ void snd_usbmidi_input_start(struct list_head *p)
 	if (umidi->input_running || !umidi->opened[1])
 		return;
 	for (i = 0; i < MIDI_MAX_ENDPOINTS; ++i)
-		snd_usbmidi_input_start_ep(umidi->endpoints[i].in);
+		snd_usbmidi_input_start_ep(umidi, umidi->endpoints[i].in);
 	umidi->input_running = 1;
 }
 EXPORT_SYMBOL(snd_usbmidi_input_start);
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 7b75208d5cea..b29a3546ab6a 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -591,8 +591,9 @@ static int check_matrix_bitmap(unsigned char *bmap,
  * if failed, give up and free the control instance.
  */
 
-int snd_usb_mixer_add_control(struct usb_mixer_elem_list *list,
-			      struct snd_kcontrol *kctl)
+int snd_usb_mixer_add_list(struct usb_mixer_elem_list *list,
+			   struct snd_kcontrol *kctl,
+			   bool is_std_info)
 {
 	struct usb_mixer_interface *mixer = list->mixer;
 	int err;
@@ -605,6 +606,7 @@ int snd_usb_mixer_add_control(struct usb_mixer_elem_list *list,
 		return err;
 	}
 	list->kctl = kctl;
+	list->is_std_info = is_std_info;
 	list->next_id_elem = mixer->id_elems[list->id];
 	mixer->id_elems[list->id] = list;
 	return 0;
@@ -986,6 +988,14 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval,
 			cval->res = 384;
 		}
 		break;
+	case USB_ID(0x0495, 0x3042): /* ESS Technology Asus USB DAC */
+		if ((strstr(kctl->id.name, "Playback Volume") != NULL) ||
+			strstr(kctl->id.name, "Capture Volume") != NULL) {
+			cval->min >>= 8;
+			cval->max = 0;
+			cval->res = 1;
+		}
+		break;
 	}
 }
 
@@ -2395,15 +2405,23 @@ void snd_usb_mixer_notify_id(struct usb_mixer_interface *mixer, int unitid)
 {
 	struct usb_mixer_elem_list *list;
 
-	for (list = mixer->id_elems[unitid]; list; list = list->next_id_elem)
+	for_each_mixer_elem(list, mixer, unitid) {
+		struct usb_mixer_elem_info *info;
+
+		if (!list->is_std_info)
+			continue;
+		info = mixer_elem_list_to_info(list);
+		/* invalidate cache, so the value is read from the device */
+		info->cached = 0;
 		snd_ctl_notify(mixer->chip->card, SNDRV_CTL_EVENT_MASK_VALUE,
 			       &list->kctl->id);
+	}
 }
 
 static void snd_usb_mixer_dump_cval(struct snd_info_buffer *buffer,
 				    struct usb_mixer_elem_list *list)
 {
-	struct usb_mixer_elem_info *cval = (struct usb_mixer_elem_info *)list;
+	struct usb_mixer_elem_info *cval = mixer_elem_list_to_info(list);
 	static char *val_types[] = {"BOOLEAN", "INV_BOOLEAN",
 				    "S8", "U8", "S16", "U16"};
 	snd_iprintf(buffer, "    Info: id=%i, control=%i, cmask=0x%x, "
@@ -2429,8 +2447,7 @@ static void snd_usb_mixer_proc_read(struct snd_info_entry *entry,
 				mixer->ignore_ctl_error);
 		snd_iprintf(buffer, "Card: %s\n", chip->card->longname);
 		for (unitid = 0; unitid < MAX_ID_ELEMS; unitid++) {
-			for (list = mixer->id_elems[unitid]; list;
-			     list = list->next_id_elem) {
+			for_each_mixer_elem(list, mixer, unitid) {
 				snd_iprintf(buffer, "  Unit: %i\n", list->id);
 				if (list->kctl)
 					snd_iprintf(buffer,
@@ -2460,19 +2477,21 @@ static void snd_usb_mixer_interrupt_v2(struct usb_mixer_interface *mixer,
 		return;
 	}
 
-	for (list = mixer->id_elems[unitid]; list; list = list->next_id_elem)
+	for_each_mixer_elem(list, mixer, unitid)
 		count++;
 
 	if (count == 0)
 		return;
 
-	for (list = mixer->id_elems[unitid]; list; list = list->next_id_elem) {
+	for_each_mixer_elem(list, mixer, unitid) {
 		struct usb_mixer_elem_info *info;
 
 		if (!list->kctl)
 			continue;
+		if (!list->is_std_info)
+			continue;
 
-		info = (struct usb_mixer_elem_info *)list;
+		info = mixer_elem_list_to_info(list);
 		if (count > 1 && info->control != control)
 			continue;
 
@@ -2692,7 +2711,7 @@ int snd_usb_mixer_suspend(struct usb_mixer_interface *mixer)
 
 static int restore_mixer_value(struct usb_mixer_elem_list *list)
 {
-	struct usb_mixer_elem_info *cval = (struct usb_mixer_elem_info *)list;
+	struct usb_mixer_elem_info *cval = mixer_elem_list_to_info(list);
 	int c, err, idx;
 
 	if (cval->cmask) {
@@ -2728,8 +2747,7 @@ int snd_usb_mixer_resume(struct usb_mixer_interface *mixer, bool reset_resume)
 	if (reset_resume) {
 		/* restore cached mixer values */
 		for (id = 0; id < MAX_ID_ELEMS; id++) {
-			for (list = mixer->id_elems[id]; list;
-			     list = list->next_id_elem) {
+			for_each_mixer_elem(list, mixer, id) {
 				if (list->resume) {
 					err = list->resume(list);
 					if (err < 0)
diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h
index ba27f7ade670..7c824a44589b 100644
--- a/sound/usb/mixer.h
+++ b/sound/usb/mixer.h
@@ -49,10 +49,17 @@ struct usb_mixer_elem_list {
 	struct usb_mixer_elem_list *next_id_elem; /* list of controls with same id */
 	struct snd_kcontrol *kctl;
 	unsigned int id;
+	bool is_std_info;
 	usb_mixer_elem_dump_func_t dump;
 	usb_mixer_elem_resume_func_t resume;
 };
 
+/* iterate over mixer element list of the given unit id */
+#define for_each_mixer_elem(list, mixer, id)	\
+	for ((list) = (mixer)->id_elems[id]; (list); (list) = (list)->next_id_elem)
+#define mixer_elem_list_to_info(list) \
+	container_of(list, struct usb_mixer_elem_info, head)
+
 struct usb_mixer_elem_info {
 	struct usb_mixer_elem_list head;
 	unsigned int control;	/* CS or ICN (high byte) */
@@ -80,8 +87,12 @@ void snd_usb_mixer_notify_id(struct usb_mixer_interface *mixer, int unitid);
 int snd_usb_mixer_set_ctl_value(struct usb_mixer_elem_info *cval,
 				int request, int validx, int value_set);
 
-int snd_usb_mixer_add_control(struct usb_mixer_elem_list *list,
-			      struct snd_kcontrol *kctl);
+int snd_usb_mixer_add_list(struct usb_mixer_elem_list *list,
+			   struct snd_kcontrol *kctl,
+			   bool is_std_info);
+
+#define snd_usb_mixer_add_control(list, kctl) \
+	snd_usb_mixer_add_list(list, kctl, true)
 
 void snd_usb_mixer_elem_init_std(struct usb_mixer_elem_list *list,
 				 struct usb_mixer_interface *mixer,
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index b9ea4a42aee4..d7878ed5ecc0 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -169,7 +169,8 @@ static int add_single_ctl_with_resume(struct usb_mixer_interface *mixer,
 		return -ENOMEM;
 	}
 	kctl->private_free = snd_usb_mixer_elem_free;
-	return snd_usb_mixer_add_control(list, kctl);
+	/* don't use snd_usb_mixer_add_control() here, this is a special list element */
+	return snd_usb_mixer_add_list(list, kctl, false);
 }
 
 /*
@@ -195,6 +196,7 @@ static const struct rc_config {
 	{ USB_ID(0x041e, 0x3042), 0, 1, 1, 1,  1,  0x000d }, /* Usb X-Fi S51 */
 	{ USB_ID(0x041e, 0x30df), 0, 1, 1, 1,  1,  0x000d }, /* Usb X-Fi S51 Pro */
 	{ USB_ID(0x041e, 0x3237), 0, 1, 1, 1,  1,  0x000d }, /* Usb X-Fi S51 Pro */
+	{ USB_ID(0x041e, 0x3263), 0, 1, 1, 1,  1,  0x000d }, /* Usb X-Fi S51 Pro */
 	{ USB_ID(0x041e, 0x3048), 2, 2, 6, 6,  2,  0x6e91 }, /* Toshiba SB0500 */
 };
 
@@ -1171,7 +1173,7 @@ void snd_emuusb_set_samplerate(struct snd_usb_audio *chip,
 	int unitid = 12; /* SamleRate ExtensionUnit ID */
 
 	list_for_each_entry(mixer, &chip->mixer_list, list) {
-		cval = (struct usb_mixer_elem_info *)mixer->id_elems[unitid];
+		cval = mixer_elem_list_to_info(mixer->id_elems[unitid]);
 		if (cval) {
 			snd_usb_mixer_set_ctl_value(cval, UAC_SET_CUR,
 						    cval->control << 8,
diff --git a/sound/usb/mixer_scarlett.c b/sound/usb/mixer_scarlett.c
index c33e2378089d..4aeb9488a0c9 100644
--- a/sound/usb/mixer_scarlett.c
+++ b/sound/usb/mixer_scarlett.c
@@ -287,8 +287,7 @@ static int scarlett_ctl_switch_put(struct snd_kcontrol *kctl,
 
 static int scarlett_ctl_resume(struct usb_mixer_elem_list *list)
 {
-	struct usb_mixer_elem_info *elem =
-		container_of(list, struct usb_mixer_elem_info, head);
+	struct usb_mixer_elem_info *elem = mixer_elem_list_to_info(list);
 	int i;
 
 	for (i = 0; i < elem->channels; i++)
@@ -447,8 +446,7 @@ static int scarlett_ctl_enum_put(struct snd_kcontrol *kctl,
 
 static int scarlett_ctl_enum_resume(struct usb_mixer_elem_list *list)
 {
-	struct usb_mixer_elem_info *elem =
-		container_of(list, struct usb_mixer_elem_info, head);
+	struct usb_mixer_elem_info *elem = mixer_elem_list_to_info(list);
 
 	if (elem->cached)
 		snd_usb_set_cur_mix_value(elem, 0, 0, *elem->cache_val);
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index ff38fca1781b..f27213b846e6 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -1313,6 +1313,12 @@ static void retire_capture_urb(struct snd_usb_substream *subs,
 			// continue;
 		}
 		bytes = urb->iso_frame_desc[i].actual_length;
+		if (subs->stream_offset_adj > 0) {
+			unsigned int adj = min(subs->stream_offset_adj, bytes);
+			cp += adj;
+			bytes -= adj;
+			subs->stream_offset_adj -= adj;
+		}
 		frames = bytes / stride;
 		if (!subs->txfr_quirk)
 			bytes = frames * stride;
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index c892b4d1e733..a917b7e02d31 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -3323,4 +3323,118 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 	}
 },
 
+/*
+ * MacroSilicon MS2109 based HDMI capture cards
+ *
+ * These claim 96kHz 1ch in the descriptors, but are actually 48kHz 2ch.
+ * They also need QUIRK_AUDIO_ALIGN_TRANSFER, which makes one wonder if
+ * they pretend to be 96kHz mono as a workaround for stereo being broken
+ * by that...
+ *
+ * They also have an issue with initial stream alignment that causes the
+ * channels to be swapped and out of phase, which is dealt with in quirks.c.
+ */
+{
+	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
+		       USB_DEVICE_ID_MATCH_INT_CLASS |
+		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
+	.idVendor = 0x534d,
+	.idProduct = 0x2109,
+	.bInterfaceClass = USB_CLASS_AUDIO,
+	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.vendor_name = "MacroSilicon",
+		.product_name = "MS2109",
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = &(const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_ALIGN_TRANSFER,
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_STANDARD_MIXER,
+			},
+			{
+				.ifnum = 3,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S16_LE,
+					.channels = 2,
+					.iface = 3,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.attributes = 0,
+					.endpoint = 0x82,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC |
+						USB_ENDPOINT_SYNC_ASYNC,
+					.rates = SNDRV_PCM_RATE_CONTINUOUS,
+					.rate_min = 48000,
+					.rate_max = 48000,
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
+	/*
+	 * PIONEER DJ DDJ-RB
+	 * PCM is 4 channels out, 2 dummy channels in @ 44.1 fixed
+	 * The feedback for the output is the dummy input.
+	 */
+	USB_DEVICE_VENDOR_SPEC(0x2b73, 0x000e),
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S24_3LE,
+					.channels = 4,
+					.iface = 0,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x01,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC|
+						   USB_ENDPOINT_SYNC_ASYNC,
+					.rates = SNDRV_PCM_RATE_44100,
+					.rate_min = 44100,
+					.rate_max = 44100,
+					.nr_rates = 1,
+					.rate_table = (unsigned int[]) { 44100 }
+				}
+			},
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S24_3LE,
+					.channels = 2,
+					.iface = 0,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x82,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC|
+						 USB_ENDPOINT_SYNC_ASYNC|
+						 USB_ENDPOINT_USAGE_IMPLICIT_FB,
+					.rates = SNDRV_PCM_RATE_44100,
+					.rate_min = 44100,
+					.rate_max = 44100,
+					.nr_rates = 1,
+					.rate_table = (unsigned int[]) { 44100 }
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+
 #undef USB_DEVICE_VENDOR_SPEC
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index f29a8ed4f856..224e0a760428 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1120,6 +1120,9 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs,
 	case USB_ID(0x041e, 0x3f19): /* E-Mu 0204 USB */
 		set_format_emu_quirk(subs, fmt);
 		break;
+	case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */
+		subs->stream_offset_adj = 2;
+		break;
 	}
 }
 
@@ -1164,6 +1167,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
 static bool is_itf_usb_dsd_2alts_dac(unsigned int id)
 {
 	switch (id) {
+	case USB_ID(0x154e, 0x1002): /* Denon DCD-1500RE */
 	case USB_ID(0x154e, 0x1003): /* Denon DA-300USB */
 	case USB_ID(0x154e, 0x3005): /* Marantz HD-DAC1 */
 	case USB_ID(0x154e, 0x3006): /* Marantz SA-14S1 */
@@ -1318,12 +1322,13 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	    && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
 		mdelay(20);
 
-	/* Zoom R16/24, Logitech H650e, Jabra 550a, Kingston HyperX needs a tiny
-	 * delay here, otherwise requests like get/set frequency return as
-	 * failed despite actually succeeding.
+	/* Zoom R16/24, Logitech H650e/H570e, Jabra 550a, Kingston HyperX
+	 *  needs a tiny delay here, otherwise requests like get/set
+	 *  frequency return as failed despite actually succeeding.
 	 */
 	if ((chip->usb_id == USB_ID(0x1686, 0x00dd) ||
 	     chip->usb_id == USB_ID(0x046d, 0x0a46) ||
+	     chip->usb_id == USB_ID(0x046d, 0x0a56) ||
 	     chip->usb_id == USB_ID(0x0b0e, 0x0349) ||
 	     chip->usb_id == USB_ID(0x0951, 0x16ad)) &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index d1776e5517ff..452646959586 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -95,6 +95,7 @@ static void snd_usb_init_substream(struct snd_usb_stream *as,
 	subs->tx_length_quirk = as->chip->tx_length_quirk;
 	subs->speed = snd_usb_get_speed(subs->dev);
 	subs->pkt_offset_adj = 0;
+	subs->stream_offset_adj = 0;
 
 	snd_usb_set_pcm_ops(as->pcm, stream);
 
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index 4d5c89a7ba2b..f4ee83c8e0b2 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -37,7 +37,7 @@ struct snd_usb_audio {
 	struct usb_interface *pm_intf;
 	u32 usb_id;
 	struct mutex mutex;
-	unsigned int autosuspended:1;	
+	unsigned int system_suspend;
 	atomic_t active;
 	atomic_t shutdown;
 	atomic_t usage_count;
diff --git a/tools/build/Build.include b/tools/build/Build.include
index d9048f145f97..63bb9752612a 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -74,7 +74,8 @@ dep-cmd = $(if $(wildcard $(fixdep)),
 #                   dependencies in the cmd file
 if_changed_dep = $(if $(strip $(any-prereq) $(arg-check)),         \
                   @set -e;                                         \
-                  $(echo-cmd) $(cmd_$(1)) && $(dep-cmd))
+                  $(echo-cmd) $(cmd_$(1));                         \
+                  $(dep-cmd))
 
 # if_changed      - execute command if any prerequisite is newer than
 #                   target, or command line has changed
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index c71a05b9c984..79427b09590c 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -7,7 +7,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CC="$(CC)" CXX="$(CXX)" CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 96982640fbf8..26316749e594 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -55,8 +55,6 @@ FILES=                                          \
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
-CC ?= $(CROSS_COMPILE)gcc
-CXX ?= $(CROSS_COMPILE)g++
 PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config
 LLVM_CONFIG ?= llvm-config
 
diff --git a/tools/gpio/gpio-hammer.c b/tools/gpio/gpio-hammer.c
index 4bcb234c0fca..3da5462a0c7d 100644
--- a/tools/gpio/gpio-hammer.c
+++ b/tools/gpio/gpio-hammer.c
@@ -138,7 +138,14 @@ int main(int argc, char **argv)
 			device_name = optarg;
 			break;
 		case 'o':
-			lines[i] = strtoul(optarg, NULL, 10);
+			/*
+			 * Avoid overflow. Do not immediately error, we want to
+			 * be able to accurately report on the amount of times
+			 * '-o' was given to give an accurate error message
+			 */
+			if (i < GPIOHANDLES_MAX)
+				lines[i] = strtoul(optarg, NULL, 10);
+
 			i++;
 			break;
 		case '?':
@@ -146,6 +153,14 @@ int main(int argc, char **argv)
 			return -1;
 		}
 	}
+
+	if (i >= GPIOHANDLES_MAX) {
+		fprintf(stderr,
+			"Only %d occurences of '-o' are allowed, %d were found\n",
+			GPIOHANDLES_MAX, i + 1);
+		return -1;
+	}
+
 	nlines = i;
 
 	if (!device_name || !nlines) {
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 07fd03c74a77..4c6e89f8d17c 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -38,6 +38,7 @@
 #define __always_inline	inline
 #endif
 
+#undef __user
 #define __user
 #define __rcu
 #define __read_mostly
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 362493a2f950..3b733511bb2b 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1033,7 +1033,7 @@ union perf_mem_data_src {
 
 #define PERF_MEM_SNOOPX_FWD	0x01 /* forward */
 /* 1 free */
-#define PERF_MEM_SNOOPX_SHIFT	37
+#define PERF_MEM_SNOOPX_SHIFT	38
 
 /* locked instruction */
 #define PERF_MEM_LOCK_NA	0x01 /* not available */
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 45b50b89009a..c61841051a90 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -90,6 +90,7 @@ struct fs {
 	const char * const	*mounts;
 	char			 path[PATH_MAX];
 	bool			 found;
+	bool			 checked;
 	long			 magic;
 };
 
@@ -111,31 +112,37 @@ static struct fs fs__entries[] = {
 		.name	= "sysfs",
 		.mounts	= sysfs__fs_known_mountpoints,
 		.magic	= SYSFS_MAGIC,
+		.checked = false,
 	},
 	[FS__PROCFS] = {
 		.name	= "proc",
 		.mounts	= procfs__known_mountpoints,
 		.magic	= PROC_SUPER_MAGIC,
+		.checked = false,
 	},
 	[FS__DEBUGFS] = {
 		.name	= "debugfs",
 		.mounts	= debugfs__known_mountpoints,
 		.magic	= DEBUGFS_MAGIC,
+		.checked = false,
 	},
 	[FS__TRACEFS] = {
 		.name	= "tracefs",
 		.mounts	= tracefs__known_mountpoints,
 		.magic	= TRACEFS_MAGIC,
+		.checked = false,
 	},
 	[FS__HUGETLBFS] = {
 		.name	= "hugetlbfs",
 		.mounts = hugetlbfs__known_mountpoints,
 		.magic	= HUGETLBFS_MAGIC,
+		.checked = false,
 	},
 	[FS__BPF_FS] = {
 		.name	= "bpf",
 		.mounts = bpf_fs__known_mountpoints,
 		.magic	= BPF_FS_MAGIC,
+		.checked = false,
 	},
 };
 
@@ -158,6 +165,7 @@ static bool fs__read_mounts(struct fs *fs)
 	}
 
 	fclose(fp);
+	fs->checked = true;
 	return fs->found = found;
 }
 
@@ -220,6 +228,7 @@ static bool fs__env_override(struct fs *fs)
 		return false;
 
 	fs->found = true;
+	fs->checked = true;
 	strncpy(fs->path, override_path, sizeof(fs->path) - 1);
 	fs->path[sizeof(fs->path) - 1] = '\0';
 	return true;
@@ -246,6 +255,14 @@ static const char *fs__mountpoint(int idx)
 	if (fs->found)
 		return (const char *)fs->path;
 
+	/* the mount point was already checked for the mount point
+	 * but and did not exist, so return NULL to avoid scanning again.
+	 * This makes the found and not found paths cost equivalent
+	 * in case of multiple calls.
+	 */
+	if (fs->checked)
+		return NULL;
+
 	return fs__get_mountpoint(fs);
 }
 
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index dda49deefb52..57a3dc160b08 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -18,6 +18,18 @@
 	const char *name##__mount(void);	\
 	bool name##__configured(void);		\
 
+/*
+ * The xxxx__mountpoint() entry points find the first match mount point for each
+ * filesystems listed below, where xxxx is the filesystem type.
+ *
+ * The interface is as follows:
+ *
+ * - If a mount point is found on first call, it is cached and used for all
+ *   subsequent calls.
+ *
+ * - If a mount point is not found, NULL is returned on first call and all
+ *   subsequent calls.
+ */
 FS(sysfs)
 FS(procfs)
 FS(debugfs)
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 8211e8010e09..d260ca680f07 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2780,6 +2780,7 @@ process_dynamic_array_len(struct event_format *event, struct print_arg *arg,
 	if (read_expected(EVENT_DELIM, ")") < 0)
 		goto out_err;
 
+	free_token(token);
 	type = read_token(&token);
 	*tok = token;
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5685fe2c7a7d..2c8e2dae1701 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -502,7 +502,7 @@ static int add_jump_destinations(struct objtool_file *file)
 		    insn->type != INSN_JUMP_UNCONDITIONAL)
 			continue;
 
-		if (insn->ignore || insn->offset == FAKE_JUMP_OFFSET)
+		if (insn->offset == FAKE_JUMP_OFFSET)
 			continue;
 
 		rela = find_rela_by_dest_range(insn->sec, insn->offset,
@@ -778,6 +778,12 @@ static int add_special_section_alts(struct objtool_file *file)
 		}
 
 		if (special_alt->group) {
+			if (!special_alt->orig_len) {
+				WARN_FUNC("empty alternative entry",
+					  orig_insn->sec, orig_insn->offset);
+				continue;
+			}
+
 			ret = handle_group_alt(file, special_alt, orig_insn,
 					       &new_insn);
 			if (ret)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 63526f4416ea..7b36bc6e32bb 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -33,6 +33,10 @@ OPTIONS
         - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
 	  hexadecimal event descriptor.
 
+        - a symbolic or raw PMU event followed by an optional colon
+	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
+	  linkperf:perf-list[1] man page for details on event modifiers.
+
 	- a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where
 	  'param1', 'param2', etc are defined as formats for the PMU in
 	  /sys/bus/event_source/devices/<pmu>/format/*.
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index c37d61682dfb..670aff81518b 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -39,6 +39,10 @@ report::
 	- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
 	  hexadecimal event descriptor.
 
+        - a symbolic or raw PMU event followed by an optional colon
+	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
+	  linkperf:perf-list[1] man page for details on event modifiers.
+
 	- a symbolically formed event like 'pmu/param1=0x3,param2/' where
 	  param1 and param2 are defined as formats for the PMU in
 	  /sys/bus/event_source/devices/<pmu>/format/*
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 8baaf9797101..166712ca4cd3 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -189,10 +189,10 @@ else
 endif
 
 ifdef PYTHON_CONFIG
-  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) $(PYTHON_CONFIG_LDFLAGS) 2>/dev/null)
+  PYTHON_EMBED_LDOPTS := $(shell pkg-config --libs python 2>/dev/null)
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
-  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+  PYTHON_EMBED_CCOPTS := $(shell pkg-config --cflags python 2>/dev/null)
   ifeq ($(CC_NO_CLANG), 1)
     PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
   endif
@@ -557,8 +557,9 @@ ifndef NO_SLANG
     msg := $(warning slang not found, disables TUI support. Please install slang-devel, libslang-dev or libslang2-dev);
     NO_SLANG := 1
   else
-    # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
-    CFLAGS += -I/usr/include/slang
+    # Some releases like Fedora have /usr/include/slang/slang.h instead of /usr/include/slang.h
+    SLANG_INC ?= -idirafter =/usr/include/slang
+    CFLAGS += $(SLANG_INC)
     CFLAGS += -DHAVE_SLANG_SUPPORT
     EXTLIBS += -lslang
     $(call detected,CONFIG_SLANG)
@@ -592,6 +593,7 @@ else
   FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
   ifneq ($(feature-libperl), 1)
+    msg := $(warning libperl not found, disables Perl scripting support. Please install libperl-dev or perl-devel);
     CFLAGS += -DNO_LIBPERL
     NO_LIBPERL := 1
     msg := $(warning Missing perl devel files. Disabling perl scripting support, please install perl-ExtUtils-Embed/libperl-dev);
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 349ea5133d83..8c310cb736aa 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -781,7 +781,7 @@ install-bin: install-tools install-tests install-traceevent-plugins
 install: install-bin try-install-man
 
 install-python_ext:
-	$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
+	$(PYTHON_WORD) util/setup.py --quiet install --prefix='$(DESTDIR_SQ)/usr'
 
 # 'make install-doc' should call 'make -C Documentation install'
 $(INSTALL_DOC_TARGETS):
diff --git a/tools/perf/arch/x86/tests/gen-insn-x86-dat.awk b/tools/perf/arch/x86/tests/gen-insn-x86-dat.awk
index a21454835cd4..2f5e8c99f372 100644
--- a/tools/perf/arch/x86/tests/gen-insn-x86-dat.awk
+++ b/tools/perf/arch/x86/tests/gen-insn-x86-dat.awk
@@ -1,4 +1,4 @@
-#!/bin/awk -f
+#!/usr/bin/awk -f
 # gen-insn-x86-dat.awk: script to convert data for the insn-x86 test
 # Copyright (c) 2015, Intel Corporation.
 #
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 0251dd348124..4864fc67d01b 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -222,12 +222,8 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
 	return 0;
 }
 
-static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst)
+static void memcpy_prefault(memcpy_t fn, size_t size, void *src, void *dst)
 {
-	u64 cycle_start = 0ULL, cycle_end = 0ULL;
-	memcpy_t fn = r->fn.memcpy;
-	int i;
-
 	/* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */
 	memset(src, 0, size);
 
@@ -236,6 +232,15 @@ static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, vo
 	 * to not measure page fault overhead:
 	 */
 	fn(dst, src, size);
+}
+
+static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst)
+{
+	u64 cycle_start = 0ULL, cycle_end = 0ULL;
+	memcpy_t fn = r->fn.memcpy;
+	int i;
+
+	memcpy_prefault(fn, size, src, dst);
 
 	cycle_start = get_cycles();
 	for (i = 0; i < nr_loops; ++i)
@@ -251,11 +256,7 @@ static double do_memcpy_gettimeofday(const struct function *r, size_t size, void
 	memcpy_t fn = r->fn.memcpy;
 	int i;
 
-	/*
-	 * We prefault the freshly allocated memory range here,
-	 * to not measure page fault overhead:
-	 */
-	fn(dst, src, size);
+	memcpy_prefault(fn, size, src, dst);
 
 	BUG_ON(gettimeofday(&tv_start, NULL));
 	for (i = 0; i < nr_loops; ++i)
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 275f1c3c73b6..065fcdb915d7 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -27,6 +27,7 @@
 #include <string.h>
 #include <unistd.h>
 #include <sys/mman.h>
+#include <inttypes.h>
 #include <sys/time.h>
 #include <sys/resource.h>
 #include <sys/wait.h>
@@ -1194,7 +1195,7 @@ static void *worker_thread(void *__tdata)
 		/* Check whether our max runtime timed out: */
 		if (g->p.nr_secs) {
 			timersub(&stop, &start0, &diff);
-			if ((u32)diff.tv_sec >= g->p.nr_secs) {
+			if ((u32)diff.tv_sec >= (long int)g->p.nr_secs) {
 				g->stop_work = true;
 				break;
 			}
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index e1ac51aaedcf..48d40b12d581 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -377,6 +377,9 @@ static int perf_add_probe_events(struct perf_probe_event *pevs, int npevs)
 
 		for (k = 0; k < pev->ntevs; k++) {
 			struct probe_trace_event *tev = &pev->tevs[k];
+			/* Skipped events have no event name */
+			if (!tev->event)
+				continue;
 
 			/* We use tev's name for showing new events */
 			show_perf_probe_event(tev->group, tev->event, pev,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 429c3e140dc3..35a10b598544 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -401,8 +401,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 	if (evname != NULL)
 		ret += fprintf(fp, " of event '%s'", evname);
 
-	if (symbol_conf.show_ref_callgraph &&
-	    strstr(evname, "call-graph=no")) {
+	if (symbol_conf.show_ref_callgraph && evname && strstr(evname, "call-graph=no")) {
 		ret += fprintf(fp, ", show reference callgraph");
 	}
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 133eb7949321..d5bdcbb4d436 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -652,7 +652,9 @@ repeat:
 	delay_msecs = top->delay_secs * MSEC_PER_SEC;
 	set_term_quiet_input(&save);
 	/* trash return*/
-	getc(stdin);
+	clearerr(stdin);
+	if (poll(&stdin_poll, 1, 0) > 0)
+		getc(stdin);
 
 	while (!done) {
 		perf_top__print_sym_table(top);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index d4ebd0956114..8deb1a6e17c1 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -13,6 +13,8 @@ void test_attr__init(void);
 void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
 		     int fd, int group_fd, unsigned long flags);
 
+#include <stdbool.h>
+
 #define HAVE_ATTR_TEST
 #include "perf-sys.h"
 
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
index fcd1dd667906..43cf40a42bad 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
@@ -19,6 +19,10 @@
  *
  */
 
+#ifdef __mips__
+#include <sgidefs.h>
+#endif
+
 #include <Python.h>
 #include "../../../perf.h"
 #include "../../../util/trace-event.h"
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 60fea0a376fc..278f6afdbc53 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -73,7 +73,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
 		return 0;
 
 	snprintf(path, PATH_MAX, "%s/event-%d-%llu-%d", dir,
-		 attr->type, attr->config, fd);
+		 attr->type, (unsigned long long)attr->config, fd);
 
 	file = fopen(path, "w+");
 	if (!file) {
@@ -82,7 +82,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
 	}
 
 	if (fprintf(file, "[event-%d-%llu-%d]\n",
-		    attr->type, attr->config, fd) < 0) {
+		    attr->type, (unsigned long long)attr->config, fd) < 0) {
 		perror("test attr - failed to write event file");
 		fclose(file);
 		return -1;
@@ -98,10 +98,10 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
 	/* struct perf_event_attr */
 	WRITE_ASS(type,   PRIu32);
 	WRITE_ASS(size,   PRIu32);
-	WRITE_ASS(config,  "llu");
-	WRITE_ASS(sample_period, "llu");
-	WRITE_ASS(sample_type,   "llu");
-	WRITE_ASS(read_format,   "llu");
+	__WRITE_ASS(config,        "llu", (unsigned long long)attr->config);
+	__WRITE_ASS(sample_period, "llu", (unsigned long long)attr->sample_period);
+	__WRITE_ASS(sample_type,   "llu", (unsigned long long)attr->sample_type);
+	__WRITE_ASS(read_format,   "llu", (unsigned long long)attr->read_format);
 	WRITE_ASS(disabled,       "d");
 	WRITE_ASS(inherit,        "d");
 	WRITE_ASS(pinned,         "d");
@@ -126,10 +126,10 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
 	WRITE_ASS(exclude_callchain_user, "d");
 	WRITE_ASS(wakeup_events, PRIu32);
 	WRITE_ASS(bp_type, PRIu32);
-	WRITE_ASS(config1, "llu");
-	WRITE_ASS(config2, "llu");
-	WRITE_ASS(branch_sample_type, "llu");
-	WRITE_ASS(sample_regs_user,   "llu");
+	__WRITE_ASS(config1,            "llu", (unsigned long long)attr->config1);
+	__WRITE_ASS(config2,            "llu", (unsigned long long)attr->config2);
+	__WRITE_ASS(branch_sample_type, "llu", (unsigned long long)attr->branch_sample_type);
+	__WRITE_ASS(sample_regs_user,   "llu", (unsigned long long)attr->sample_regs_user);
 	WRITE_ASS(sample_stack_user,  PRIu32);
 
 	fclose(file);
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index 335b695f4970..44cad1e8c9e0 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -128,7 +128,7 @@ static int __event(bool is_x, void *addr, int sig)
 	fd = sys_perf_event_open(&pe, 0, -1, -1,
 				 perf_event_open_cloexec_flag());
 	if (fd < 0) {
-		pr_debug("failed opening event %llx\n", pe.config);
+		pr_debug("failed opening event %llx\n", (unsigned long long)pe.config);
 		return TEST_FAIL;
 	}
 
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index ca962559e845..35e1de86b295 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -95,7 +95,7 @@ int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __may
 	fd = sys_perf_event_open(&pe, 0, -1, -1,
 				 perf_event_open_cloexec_flag());
 	if (fd < 0) {
-		pr_debug("failed opening event %llx\n", pe.config);
+		pr_debug("failed opening event %llx\n", (unsigned long long)pe.config);
 		return TEST_FAIL;
 	}
 
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 7bedf8608fdd..3e183eef6f85 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -172,6 +172,7 @@ int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused)
 		ret = 0;
 	} while (0);
 
+	perf_pmu__del_formats(&formats);
 	test_format_dir_put(format);
 	return ret;
 }
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
index 068d463e5cbf..4b0922a20970 100644
--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -14,7 +14,7 @@ add_probe_vfs_getname() {
 	if [ $had_vfs_getname -eq 1 ] ; then
 		line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
 		perf probe -q       "vfs_getname=getname_flags:${line} pathname=result->name:string" || \
-		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string"
+		perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring"
 	fi
 }
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 2a8d2a6723f6..e6150f01c885 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1497,7 +1497,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map,
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
+		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|sed 's/\t/        /g'",
 		 objdump_path ? objdump_path : "objdump",
 		 disassembler_style ? "-M " : "",
 		 disassembler_style ? disassembler_style : "",
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index f93846edc1e0..827d844f4efb 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -462,7 +462,7 @@ static void set_max_cpu_num(void)
 
 	/* get the highest possible cpu number for a sparse allocation */
 	ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt);
-	if (ret == PATH_MAX) {
+	if (ret >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		goto out;
 	}
@@ -473,7 +473,7 @@ static void set_max_cpu_num(void)
 
 	/* get the highest present cpu number for a sparse allocation */
 	ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt);
-	if (ret == PATH_MAX) {
+	if (ret >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		goto out;
 	}
@@ -501,7 +501,7 @@ static void set_max_node_num(void)
 
 	/* get the highest possible cpu number for a sparse allocation */
 	ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt);
-	if (ret == PATH_MAX) {
+	if (ret >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		goto out;
 	}
@@ -586,7 +586,7 @@ int cpu__setup_cpunode_map(void)
 		return 0;
 
 	n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt);
-	if (n == PATH_MAX) {
+	if (n >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		return -1;
 	}
@@ -601,7 +601,7 @@ int cpu__setup_cpunode_map(void)
 			continue;
 
 		n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name);
-		if (n == PATH_MAX) {
+		if (n >= PATH_MAX) {
 			pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 			continue;
 		}
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 505c13bf7e30..40b5f656ebc3 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -36,6 +36,7 @@ char dso__symtab_origin(const struct dso *dso)
 		[DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO]	= 'D',
 		[DSO_BINARY_TYPE__FEDORA_DEBUGINFO]		= 'f',
 		[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]		= 'u',
+		[DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO]	= 'x',
 		[DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO]	= 'o',
 		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]		= 'b',
 		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]		= 'd',
@@ -118,6 +119,21 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		snprintf(filename + len, size - len, "%s", dso->long_name);
 		break;
 
+	case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO:
+		/*
+		 * Ubuntu can mixup /usr/lib with /lib, putting debuginfo in
+		 * /usr/lib/debug/lib when it is expected to be in
+		 * /usr/lib/debug/usr/lib
+		 */
+		if (strlen(dso->long_name) < 9 ||
+		    strncmp(dso->long_name, "/usr/lib/", 9)) {
+			ret = -1;
+			break;
+		}
+		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+		snprintf(filename + len, size - len, "%s", dso->long_name + 4);
+		break;
+
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
 	{
 		const char *last_slash;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 926ff2e7f668..ea198d19dadd 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -25,6 +25,7 @@ enum dso_binary_type {
 	DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO,
 	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
 	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
 	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
 	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
 	DSO_BINARY_TYPE__GUEST_KMODULE,
diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
index ddd5c4c21129..d236058fc4e2 100644
--- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
+++ b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
@@ -1,4 +1,4 @@
-#!/bin/awk -f
+#!/usr/bin/awk -f
 # SPDX-License-Identifier: GPL-2.0
 # gen-insn-attr-x86.awk: Instruction attribute table generator
 # Written by Masami Hiramatsu <mhiramat@redhat.com>
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 4357141c7c92..6522b6513895 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1129,6 +1129,7 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
 			return 0;
 		if (err == -EAGAIN ||
 		    intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) {
+			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			if (intel_pt_fup_event(decoder))
 				return 0;
 			return -EAGAIN;
@@ -1780,17 +1781,13 @@ next:
 			}
 			if (decoder->set_fup_mwait)
 				no_tip = true;
+			if (no_tip)
+				decoder->pkt_state = INTEL_PT_STATE_FUP_NO_TIP;
+			else
+				decoder->pkt_state = INTEL_PT_STATE_FUP;
 			err = intel_pt_walk_fup(decoder);
-			if (err != -EAGAIN) {
-				if (err)
-					return err;
-				if (no_tip)
-					decoder->pkt_state =
-						INTEL_PT_STATE_FUP_NO_TIP;
-				else
-					decoder->pkt_state = INTEL_PT_STATE_FUP;
-				return 0;
-			}
+			if (err != -EAGAIN)
+				return err;
 			if (no_tip) {
 				no_tip = false;
 				break;
@@ -2375,15 +2372,11 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 			err = intel_pt_walk_tip(decoder);
 			break;
 		case INTEL_PT_STATE_FUP:
-			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			err = intel_pt_walk_fup(decoder);
 			if (err == -EAGAIN)
 				err = intel_pt_walk_fup_tip(decoder);
-			else if (!err)
-				decoder->pkt_state = INTEL_PT_STATE_FUP;
 			break;
 		case INTEL_PT_STATE_FUP_NO_TIP:
-			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			err = intel_pt_walk_fup(decoder);
 			if (err == -EAGAIN)
 				err = intel_pt_walk_trace(decoder);
diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c
index c5e568188e19..d493f96b806d 100644
--- a/tools/perf/util/libunwind/x86_32.c
+++ b/tools/perf/util/libunwind/x86_32.c
@@ -21,6 +21,7 @@
 #define LIBUNWIND__ARCH_REG_IP PERF_REG_X86_IP
 #define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP
 
+#include <errno.h>
 #include "unwind.h"
 #include "debug.h"
 #include "libunwind-x86.h"
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 2deffc234932..ca00b4104bc0 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1100,6 +1100,17 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to)
 		set_bit(b, bits);
 }
 
+void perf_pmu__del_formats(struct list_head *formats)
+{
+	struct perf_pmu_format *fmt, *tmp;
+
+	list_for_each_entry_safe(fmt, tmp, formats, list) {
+		list_del(&fmt->list);
+		free(fmt->name);
+		free(fmt);
+	}
+}
+
 static int sub_non_neg(int a, int b)
 {
 	if (b > a)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index eca99435f4a0..59ad5de6601a 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -79,6 +79,7 @@ int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits);
 void perf_pmu__set_format(unsigned long *bits, long from, long to);
 int perf_pmu__format_parse(char *dir, struct list_head *head);
+void perf_pmu__del_formats(struct list_head *formats);
 
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 6670e12a2bb3..7c286756c34b 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -122,7 +122,7 @@ static struct symbol *__find_kernel_function(u64 addr, struct map **mapp)
 	return machine__find_kernel_function(host_machine, addr, mapp);
 }
 
-static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
+static struct ref_reloc_sym *kernel_get_ref_reloc_sym(struct map **pmap)
 {
 	/* kmap->ref_reloc_sym should be set if host_machine is initialized */
 	struct kmap *kmap;
@@ -134,6 +134,10 @@ static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
 	kmap = map__kmap(map);
 	if (!kmap)
 		return NULL;
+
+	if (pmap)
+		*pmap = map;
+
 	return kmap->ref_reloc_sym;
 }
 
@@ -145,7 +149,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
 	struct map *map;
 
 	/* ref_reloc_sym is just a label. Need a special fix*/
-	reloc_sym = kernel_get_ref_reloc_sym();
+	reloc_sym = kernel_get_ref_reloc_sym(NULL);
 	if (reloc_sym && strcmp(name, reloc_sym->name) == 0)
 		*addr = (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
 	else {
@@ -764,6 +768,7 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 				       int ntevs)
 {
 	struct ref_reloc_sym *reloc_sym;
+	struct map *map;
 	char *tmp;
 	int i, skipped = 0;
 
@@ -772,7 +777,7 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 		return post_process_offline_probe_trace_events(tevs, ntevs,
 						symbol_conf.vmlinux_name);
 
-	reloc_sym = kernel_get_ref_reloc_sym();
+	reloc_sym = kernel_get_ref_reloc_sym(&map);
 	if (!reloc_sym) {
 		pr_warning("Relocated base symbol is not found!\n");
 		return -EINVAL;
@@ -783,9 +788,13 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 			continue;
 		if (tevs[i].point.retprobe && !kretprobe_offset_is_supported())
 			continue;
-		/* If we found a wrong one, mark it by NULL symbol */
+		/*
+		 * If we found a wrong one, mark it by NULL symbol.
+		 * Since addresses in debuginfo is same as objdump, we need
+		 * to convert it to addresses on memory.
+		 */
 		if (kprobe_warn_out_range(tevs[i].point.symbol,
-					  tevs[i].point.address)) {
+			map__objdump_2mem(map, tevs[i].point.address))) {
 			tmp = NULL;
 			skipped++;
 		} else {
@@ -1762,8 +1771,7 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev)
 	fmt1_str = strtok_r(argv0_str, ":", &fmt);
 	fmt2_str = strtok_r(NULL, "/", &fmt);
 	fmt3_str = strtok_r(NULL, " \t", &fmt);
-	if (fmt1_str == NULL || strlen(fmt1_str) != 1 || fmt2_str == NULL
-	    || fmt3_str == NULL) {
+	if (fmt1_str == NULL || fmt2_str == NULL || fmt3_str == NULL) {
 		semantic_error("Failed to parse event name: %s\n", argv[0]);
 		ret = -EINVAL;
 		goto out;
@@ -2888,7 +2896,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	/* Note that the symbols in the kmodule are not relocated */
 	if (!pev->uprobes && !pev->target &&
 			(!pp->retprobe || kretprobe_offset_is_supported())) {
-		reloc_sym = kernel_get_ref_reloc_sym();
+		reloc_sym = kernel_get_ref_reloc_sym(NULL);
 		if (!reloc_sym) {
 			pr_warning("Relocated base symbol is not found!\n");
 			ret = -EINVAL;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index ae0feea4e8b5..bfa6d9d21556 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -114,6 +114,7 @@ enum dso_binary_type distro_dwarf_types[] = {
 	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
 	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
@@ -1353,7 +1354,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 	tf.ntevs = 0;
 
 	ret = debuginfo__find_probes(dbg, &tf.pf);
-	if (ret < 0) {
+	if (ret < 0 || tf.ntevs == 0) {
 		for (i = 0; i < tf.ntevs; i++)
 			clear_probe_trace_event(&tf.tevs[i]);
 		zfree(tevs);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index f03fa7a835a1..d3bce67a34f7 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -19,6 +19,10 @@
  *
  */
 
+#ifdef __mips__
+#include <sgidefs.h>
+#endif
+
 #include <Python.h>
 
 #include <inttypes.h>
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 84a33f1e9ec9..cd870129131e 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2667,7 +2667,7 @@ static char *prefix_if_not_in(const char *pre, char *str)
 		return str;
 
 	if (asprintf(&n, "%s,%s", pre, str) < 0)
-		return NULL;
+		n = NULL;
 
 	free(str);
 	return n;
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index d028c2786802..821e5790eb0e 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -350,8 +350,10 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	 * interval mode, otherwise overall avg running
 	 * averages will be shown for each interval.
 	 */
-	if (config->interval)
-		init_stats(ps->res_stats);
+	if (config->interval) {
+		for (i = 0; i < 3; i++)
+			init_stats(&ps->res_stats[i]);
+	}
 
 	if (counter->per_pkg)
 		zero_per_pkg(counter);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 3d39332b3a06..a0a4afa7e678 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1420,6 +1420,7 @@ struct kcore_copy_info {
 	u64 first_symbol;
 	u64 last_symbol;
 	u64 first_module;
+	u64 first_module_symbol;
 	u64 last_module_symbol;
 	struct phdr_data kernel_map;
 	struct phdr_data modules_map;
@@ -1434,6 +1435,8 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 		return 0;
 
 	if (strchr(name, '[')) {
+		if (!kci->first_module_symbol || start < kci->first_module_symbol)
+			kci->first_module_symbol = start;
 		if (start > kci->last_module_symbol)
 			kci->last_module_symbol = start;
 		return 0;
@@ -1558,6 +1561,10 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
 		kci->etext += page_size;
 	}
 
+	if (kci->first_module_symbol &&
+	    (!kci->first_module || kci->first_module_symbol < kci->first_module))
+		kci->first_module = kci->first_module_symbol;
+
 	kci->first_module = round_down(kci->first_module, page_size);
 
 	if (kci->last_module_symbol) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 27bffcb213eb..dea6f15af485 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -64,6 +64,7 @@ static enum dso_binary_type binary_type_symtab[] = {
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
@@ -1412,6 +1413,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
 	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
 	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
+	case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO:
 	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
 		return !kmod && dso->kernel == DSO_TYPE_USER;
diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
index 0b24dd9d01ff..98c9f2df8aa7 100755
--- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
+++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
@@ -10,11 +10,11 @@ then this utility enables and collects trace data for a user specified interval
 and generates performance plots.
 
 Prerequisites:
-    Python version 2.7.x
+    Python version 2.7.x or higher
     gnuplot 5.0 or higher
-    gnuplot-py 1.8
+    gnuplot-py 1.8 or higher
     (Most of the distributions have these required packages. They may be called
-     gnuplot-py, phython-gnuplot. )
+     gnuplot-py, phython-gnuplot or phython3-gnuplot, gnuplot-nox, ... )
 
     HWP (Hardware P-States are disabled)
     Kernel config for Linux trace is enabled
@@ -178,7 +178,7 @@ def plot_pstate_cpu_with_sample():
         g_plot('set xlabel "Samples"')
         g_plot('set ylabel "P-State"')
         g_plot('set title "{} : cpu pstate vs. sample : {:%F %H:%M}"'.format(testname, datetime.now()))
-        title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+        title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
         plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_SAMPLE, C_TO)
         g_plot('title_list = "{}"'.format(title_list))
         g_plot(plot_str)
@@ -195,7 +195,7 @@ def plot_pstate_cpu():
 #    the following command is really cool, but doesn't work with the CPU masking option because it aborts on the first missing file.
 #    plot_str = 'plot for [i=0:*] file=sprintf("cpu%03d.csv",i) title_s=sprintf("cpu%03d",i) file using 16:7 pt 7 ps 1 title title_s'
 #
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_TO)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -209,7 +209,7 @@ def plot_load_cpu():
     g_plot('set ylabel "CPU load (percent)"')
     g_plot('set title "{} : cpu loads : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_LOAD)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -223,7 +223,7 @@ def plot_frequency_cpu():
     g_plot('set ylabel "CPU Frequency (GHz)"')
     g_plot('set title "{} : cpu frequencies : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_FREQ)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -238,7 +238,7 @@ def plot_duration_cpu():
     g_plot('set ylabel "Timer Duration (MilliSeconds)"')
     g_plot('set title "{} : cpu durations : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_DURATION)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -252,7 +252,7 @@ def plot_scaled_cpu():
     g_plot('set ylabel "Scaled Busy (Unitless)"')
     g_plot('set title "{} : cpu scaled busy : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_SCALED)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -266,7 +266,7 @@ def plot_boost_cpu():
     g_plot('set ylabel "CPU IO Boost (percent)"')
     g_plot('set title "{} : cpu io boost : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_BOOST)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -280,7 +280,7 @@ def plot_ghz_cpu():
     g_plot('set ylabel "TSC Frequency (GHz)"')
     g_plot('set title "{} : cpu TSC Frequencies (Sanity check calculation) : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_GHZ)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
index 27a54a17da65..f4e92afab14b 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
@@ -30,7 +30,7 @@ ftrace_filter_check '*schedule*' '^.*schedule.*$'
 ftrace_filter_check 'schedule*' '^schedule.*$'
 
 # filter by *mid*end
-ftrace_filter_check '*aw*lock' '.*aw.*lock$'
+ftrace_filter_check '*pin*lock' '.*pin.*lock$'
 
 # filter by start*mid*
 ftrace_filter_check 'mutex*try*' '^mutex.*try.*'
diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
index e11fe84de0fd..6184d2a4c4a6 100644
--- a/tools/testing/selftests/net/msg_zerocopy.c
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -121,9 +121,8 @@ static int do_setcpu(int cpu)
 	CPU_ZERO(&mask);
 	CPU_SET(cpu, &mask);
 	if (sched_setaffinity(0, sizeof(mask), &mask))
-		error(1, 0, "setaffinity %d", cpu);
-
-	if (cfg_verbose)
+		fprintf(stderr, "cpu: unable to pin, may increase variance.\n");
+	else if (cfg_verbose)
 		fprintf(stderr, "cpu: %u\n", cpu);
 
 	return 0;
diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
index dd4162fc0419..c6428f1ac22f 100644
--- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
@@ -114,6 +114,7 @@ static struct option long_options[] = {
 	{ "tcp", no_argument, 0, 't' },
 	{ "udp", no_argument, 0, 'u' },
 	{ "ip", no_argument, 0, 'i' },
+	{ NULL, 0, NULL, 0 },
 };
 
 static int next_port = 19999;
@@ -327,8 +328,7 @@ int main(int argc, char **argv)
 	bool all_tests = true;
 	int arg_index = 0;
 	int failures = 0;
-	int s, t;
-	char opt;
+	int s, t, opt;
 
 	while ((opt = getopt_long(argc, argv, "", long_options,
 				  &arg_index)) != -1) {
diff --git a/tools/testing/selftests/networking/timestamping/timestamping.c b/tools/testing/selftests/networking/timestamping/timestamping.c
index 5cdfd743447b..900ed4b47899 100644
--- a/tools/testing/selftests/networking/timestamping/timestamping.c
+++ b/tools/testing/selftests/networking/timestamping/timestamping.c
@@ -332,10 +332,16 @@ int main(int argc, char **argv)
 	int val;
 	socklen_t len;
 	struct timeval next;
+	size_t if_len;
 
 	if (argc < 2)
 		usage(0);
 	interface = argv[1];
+	if_len = strlen(interface);
+	if (if_len >= IFNAMSIZ) {
+		printf("interface name exceeds IFNAMSIZ\n");
+		exit(1);
+	}
 
 	for (i = 2; i < argc; i++) {
 		if (!strcasecmp(argv[i], "SO_TIMESTAMP"))
@@ -369,12 +375,12 @@ int main(int argc, char **argv)
 		bail("socket");
 
 	memset(&device, 0, sizeof(device));
-	strncpy(device.ifr_name, interface, sizeof(device.ifr_name));
+	memcpy(device.ifr_name, interface, if_len + 1);
 	if (ioctl(sock, SIOCGIFADDR, &device) < 0)
 		bail("getting interface IP address");
 
 	memset(&hwtstamp, 0, sizeof(hwtstamp));
-	strncpy(hwtstamp.ifr_name, interface, sizeof(hwtstamp.ifr_name));
+	memcpy(hwtstamp.ifr_name, interface, if_len + 1);
 	hwtstamp.ifr_data = (void *)&hwconfig;
 	memset(&hwconfig, 0, sizeof(hwconfig));
 	hwconfig.tx_type =
diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
index f4241339edd2..7136eae2170b 100644
--- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c
+++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
@@ -22,6 +22,7 @@
 #include <limits.h>
 #include <sys/time.h>
 #include <sys/syscall.h>
+#include <sys/sysinfo.h>
 #include <sys/types.h>
 #include <sys/shm.h>
 #include <linux/futex.h>
@@ -97,8 +98,9 @@ static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 
 static void start_process_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 {
-	int pid;
-	cpu_set_t cpuset;
+	int pid, ncpus;
+	cpu_set_t *cpuset;
+	size_t size;
 
 	pid = fork();
 	if (pid == -1) {
@@ -109,14 +111,23 @@ static void start_process_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 	if (pid)
 		return;
 
-	CPU_ZERO(&cpuset);
-	CPU_SET(cpu, &cpuset);
+	ncpus = get_nprocs();
+	size = CPU_ALLOC_SIZE(ncpus);
+	cpuset = CPU_ALLOC(ncpus);
+	if (!cpuset) {
+		perror("malloc");
+		exit(1);
+	}
+	CPU_ZERO_S(size, cpuset);
+	CPU_SET_S(cpu, size, cpuset);
 
-	if (sched_setaffinity(0, sizeof(cpuset), &cpuset)) {
+	if (sched_setaffinity(0, size, cpuset)) {
 		perror("sched_setaffinity");
+		CPU_FREE(cpuset);
 		exit(1);
 	}
 
+	CPU_FREE(cpuset);
 	fn(arg);
 
 	exit(0);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
index 94110b1dcd3d..031baa43646f 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -91,8 +91,6 @@ int back_to_back_ebbs(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
index 7c57a8d79535..361e0be9df9a 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -42,8 +42,6 @@ int cycles(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
index ecf5ee3283a3..fe7d0dc2a1a2 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -99,8 +99,6 @@ int cycles_with_freeze(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	printf("EBBs while frozen %d\n", ebbs_while_frozen);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
index c0faba520b35..b9b30f974b5e 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -71,8 +71,6 @@ int cycles_with_mmcr2(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index 46681fec549b..2694ae161a84 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -396,8 +396,6 @@ int ebb_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
index a991d2ea8d0a..174e4f4dae6c 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -38,8 +38,6 @@ static int victim_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	FAIL_IF(ebb_state.stats.ebb_count == 0);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
index eb8acb78bc6c..531083accfca 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -75,7 +75,6 @@ static int test_body(void)
 	ebb_freeze_pmcs();
 	ebb_global_disable();
 
-	count_pmc(4, sample_period);
 	mtspr(SPRN_PMC4, 0xdead);
 
 	dump_summary_ebb_state();
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
index 6ff8c8ff27d6..035c02273cd4 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -70,13 +70,6 @@ int multi_counter(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-	count_pmc(2, sample_period);
-	count_pmc(3, sample_period);
-	count_pmc(4, sample_period);
-	count_pmc(5, sample_period);
-	count_pmc(6, sample_period);
-
 	dump_ebb_state();
 
 	for (i = 0; i < 6; i++)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
index 037cb6154f36..3e9d4ac965c8 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -61,8 +61,6 @@ static int cycles_child(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_summary_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
index c5fa64790c22..d90891fe96a3 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -82,8 +82,6 @@ static int test_body(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	if (mmcr0_mismatch)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index 30e1ac62e8cb..8ca92b9ee5b0 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -76,8 +76,6 @@ int pmc56_overflow(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(2, sample_period);
-
 	dump_ebb_state();
 
 	printf("PMC5/6 overflow %d\n", pmc56_overflowed);
diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c
index d46916867a6f..77db4f6ecf2f 100644
--- a/tools/testing/selftests/powerpc/utils.c
+++ b/tools/testing/selftests/powerpc/utils.c
@@ -12,6 +12,7 @@
 #include <sched.h>
 #include <stdio.h>
 #include <sys/stat.h>
+#include <sys/sysinfo.h>
 #include <sys/types.h>
 #include <unistd.h>
 
@@ -81,26 +82,38 @@ void *get_auxv_entry(int type)
 
 int pick_online_cpu(void)
 {
-	cpu_set_t mask;
-	int cpu;
+	int ncpus, cpu = -1;
+	cpu_set_t *mask;
+	size_t size;
+
+	ncpus = get_nprocs_conf();
+	size = CPU_ALLOC_SIZE(ncpus);
+	mask = CPU_ALLOC(ncpus);
+	if (!mask) {
+		perror("malloc");
+		return -1;
+	}
 
-	CPU_ZERO(&mask);
+	CPU_ZERO_S(size, mask);
 
-	if (sched_getaffinity(0, sizeof(mask), &mask)) {
+	if (sched_getaffinity(0, size, mask)) {
 		perror("sched_getaffinity");
-		return -1;
+		goto done;
 	}
 
 	/* We prefer a primary thread, but skip 0 */
-	for (cpu = 8; cpu < CPU_SETSIZE; cpu += 8)
-		if (CPU_ISSET(cpu, &mask))
-			return cpu;
+	for (cpu = 8; cpu < ncpus; cpu += 8)
+		if (CPU_ISSET_S(cpu, size, mask))
+			goto done;
 
 	/* Search for anything, but in reverse */
-	for (cpu = CPU_SETSIZE - 1; cpu >= 0; cpu--)
-		if (CPU_ISSET(cpu, &mask))
-			return cpu;
+	for (cpu = ncpus - 1; cpu >= 0; cpu--)
+		if (CPU_ISSET_S(cpu, size, mask))
+			goto done;
 
 	printf("No cpus in affinity mask?!\n");
-	return -1;
+
+done:
+	CPU_FREE(mask);
+	return cpu;
 }
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk
index e05182d3e47d..6798ab45032d 100755..100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk
@@ -1,4 +1,4 @@
-#!/usr/bin/awk -f
+#!/usr/usr/bin/awk -f
 # SPDX-License-Identifier: GPL-2.0
 
 # Modify SRCU for formal verification. The first argument should be srcu.h and
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index 5d546dcdbc80..b8778960da10 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -24,6 +24,7 @@
 #define _GNU_SOURCE
 #include <errno.h>
 #include <linux/futex.h>
+#include <time.h>
 #include <sys/time.h>
 #include <sys/syscall.h>
 #include <string.h>
@@ -612,10 +613,10 @@ int alloc_random_pkey(void)
 	int nr_alloced = 0;
 	int random_index;
 	memset(alloced_pkeys, 0, sizeof(alloced_pkeys));
+	srand((unsigned int)time(NULL));
 
 	/* allocate every possible key and make a note of which ones we got */
 	max_nr_pkey_allocs = NR_PKEYS;
-	max_nr_pkey_allocs = 1;
 	for (i = 0; i < max_nr_pkey_allocs; i++) {
 		int new_pkey = alloc_pkey();
 		if (new_pkey < 0)
diff --git a/tools/testing/selftests/x86/syscall_nt.c b/tools/testing/selftests/x86/syscall_nt.c
index 43fcab367fb0..74e6b3fc2d09 100644
--- a/tools/testing/selftests/x86/syscall_nt.c
+++ b/tools/testing/selftests/x86/syscall_nt.c
@@ -67,6 +67,7 @@ static void do_it(unsigned long extraflags)
 	set_eflags(get_eflags() | extraflags);
 	syscall(SYS_getpid);
 	flags = get_eflags();
+	set_eflags(X86_EFLAGS_IF | X86_EFLAGS_FIXED);
 	if ((flags & extraflags) == extraflags) {
 		printf("[OK]\tThe syscall worked and flags are still set\n");
 	} else {
diff --git a/usr/Makefile b/usr/Makefile
index 5f1bc5b23b14..414e841d8c44 100644
--- a/usr/Makefile
+++ b/usr/Makefile
@@ -27,7 +27,7 @@ $(obj)/initramfs_data.o: $(obj)/$(datafile_y) FORCE
 # Generate the initramfs cpio archive
 
 hostprogs-y := gen_init_cpio
-initramfs   := $(CONFIG_SHELL) $(srctree)/scripts/gen_initramfs_list.sh
+initramfs   := $(INITRAMFS_WRAPPER) $(CONFIG_SHELL) $(srctree)/scripts/gen_initramfs_list.sh
 ramfs-input := $(if $(filter-out "",$(CONFIG_INITRAMFS_SOURCE)), \
 			$(shell echo $(CONFIG_INITRAMFS_SOURCE)),-d)
 ramfs-args  := \
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 3814cdad643a..7fe673248e98 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -307,12 +307,6 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 		next = stage2_pgd_addr_end(addr, end);
 		if (!stage2_pgd_none(*pgd))
 			unmap_stage2_puds(kvm, pgd, addr, next);
-		/*
-		 * If the range is too large, release the kvm->mmu_lock
-		 * to prevent starvation and lockup detector warnings.
-		 */
-		if (next != end)
-			cond_resched_lock(&kvm->mmu_lock);
 	} while (pgd++, addr = next, addr != end);
 }
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 71f77ae6c2a6..c1ca4d40157b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -165,6 +165,7 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
 	 */
 	if (pfn_valid(pfn))
 		return PageReserved(pfn_to_page(pfn)) &&
+		       !is_zero_pfn(pfn) &&
 		       !kvm_is_zone_device_pfn(pfn);
 
 	return true;
@@ -3688,7 +3689,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			       struct kvm_io_device *dev)
 {
-	int i;
+	int i, j;
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm_get_bus(kvm, bus_idx);
@@ -3705,17 +3706,20 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 
 	new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) *
 			  sizeof(struct kvm_io_range)), GFP_KERNEL);
-	if (!new_bus)  {
+	if (new_bus) {
+		memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
+		new_bus->dev_count--;
+		memcpy(new_bus->range + i, bus->range + i + 1,
+		       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
+	} else {
 		pr_err("kvm: failed to shrink bus, removing it completely\n");
-		goto broken;
+		for (j = 0; j < bus->dev_count; j++) {
+			if (j == i)
+				continue;
+			kvm_iodevice_destructor(bus->range[j].dev);
+		}
 	}
 
-	memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
-	new_bus->dev_count--;
-	memcpy(new_bus->range + i, bus->range + i + 1,
-	       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
-
-broken:
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);