diff options
492 files changed, 12193 insertions, 6972 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index eecbd1603349..23e0537f6e0c 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -517,6 +517,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/mds /sys/devices/system/cpu/vulnerabilities/meltdown /sys/devices/system/cpu/vulnerabilities/mmio_stale_data + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling /sys/devices/system/cpu/vulnerabilities/retbleed /sys/devices/system/cpu/vulnerabilities/spec_store_bypass /sys/devices/system/cpu/vulnerabilities/spectre_v1 diff --git a/Documentation/admin-guide/filesystem-monitoring.rst b/Documentation/admin-guide/filesystem-monitoring.rst new file mode 100644 index 000000000000..5a3c84e60095 --- /dev/null +++ b/Documentation/admin-guide/filesystem-monitoring.rst @@ -0,0 +1,74 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================================== +File system Monitoring with fanotify +==================================== + +File system Error Reporting +=========================== + +Fanotify supports the FAN_FS_ERROR event type for file system-wide error +reporting. It is meant to be used by file system health monitoring +daemons, which listen for these events and take actions (notify +sysadmin, start recovery) when a file system problem is detected. + +By design, a FAN_FS_ERROR notification exposes sufficient information +for a monitoring tool to know a problem in the file system has happened. +It doesn't necessarily provide a user space application with semantics +to verify an IO operation was successfully executed. That is out of +scope for this feature. Instead, it is only meant as a framework for +early file system problem detection and reporting recovery tools. + +When a file system operation fails, it is common for dozens of kernel +errors to cascade after the initial failure, hiding the original failure +log, which is usually the most useful debug data to troubleshoot the +problem. For this reason, FAN_FS_ERROR tries to report only the first +error that occurred for a file system since the last notification, and +it simply counts additional errors. This ensures that the most +important pieces of information are never lost. + +FAN_FS_ERROR requires the fanotify group to be setup with the +FAN_REPORT_FID flag. + +At the time of this writing, the only file system that emits FAN_FS_ERROR +notifications is Ext4. + +A FAN_FS_ERROR Notification has the following format:: + + [ Notification Metadata (Mandatory) ] + [ Generic Error Record (Mandatory) ] + [ FID record (Mandatory) ] + +The order of records is not guaranteed, and new records might be added +in the future. Therefore, applications must not rely on the order and +must be prepared to skip over unknown records. Please refer to +``samples/fanotify/fs-monitor.c`` for an example parser. + +Generic error record +-------------------- + +The generic error record provides enough information for a file system +agnostic tool to learn about a problem in the file system, without +providing any additional details about the problem. This record is +identified by ``struct fanotify_event_info_header.info_type`` being set +to FAN_EVENT_INFO_TYPE_ERROR. + + struct fanotify_event_info_error { + struct fanotify_event_info_header hdr; + __s32 error; + __u32 error_count; + }; + +The `error` field identifies the type of error using errno values. +`error_count` tracks the number of errors that occurred and were +suppressed to preserve the original error information, since the last +notification. + +FID record +---------- + +The FID record can be used to uniquely identify the inode that triggered +the error through the combination of fsid and file handle. A file system +specific application can use that information to attempt a recovery +procedure. Errors that are not related to an inode are reported with an +empty file handle of type FILEID_INVALID. diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 6828102baaa7..3e4a14e38b49 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -21,3 +21,4 @@ are configurable at compile, boot or run time. cross-thread-rsb.rst gather_data_sampling.rst srso + reg-file-data-sampling diff --git a/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst new file mode 100644 index 000000000000..810424b4b7f6 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst @@ -0,0 +1,104 @@ +================================== +Register File Data Sampling (RFDS) +================================== + +Register File Data Sampling (RFDS) is a microarchitectural vulnerability that +only affects Intel Atom parts(also branded as E-cores). RFDS may allow +a malicious actor to infer data values previously used in floating point +registers, vector registers, or integer registers. RFDS does not provide the +ability to choose which data is inferred. CVE-2023-28746 is assigned to RFDS. + +Affected Processors +=================== +Below is the list of affected Intel processors [#f1]_: + + =================== ============ + Common name Family_Model + =================== ============ + ATOM_GOLDMONT 06_5CH + ATOM_GOLDMONT_D 06_5FH + ATOM_GOLDMONT_PLUS 06_7AH + ATOM_TREMONT_D 06_86H + ATOM_TREMONT 06_96H + ALDERLAKE 06_97H + ALDERLAKE_L 06_9AH + ATOM_TREMONT_L 06_9CH + RAPTORLAKE 06_B7H + RAPTORLAKE_P 06_BAH + ALDERLAKE_N 06_BEH + RAPTORLAKE_S 06_BFH + =================== ============ + +As an exception to this table, Intel Xeon E family parts ALDERLAKE(06_97H) and +RAPTORLAKE(06_B7H) codenamed Catlow are not affected. They are reported as +vulnerable in Linux because they share the same family/model with an affected +part. Unlike their affected counterparts, they do not enumerate RFDS_CLEAR or +CPUID.HYBRID. This information could be used to distinguish between the +affected and unaffected parts, but it is deemed not worth adding complexity as +the reporting is fixed automatically when these parts enumerate RFDS_NO. + +Mitigation +========== +Intel released a microcode update that enables software to clear sensitive +information using the VERW instruction. Like MDS, RFDS deploys the same +mitigation strategy to force the CPU to clear the affected buffers before an +attacker can extract the secrets. This is achieved by using the otherwise +unused and obsolete VERW instruction in combination with a microcode update. +The microcode clears the affected CPU buffers when the VERW instruction is +executed. + +Mitigation points +----------------- +VERW is executed by the kernel before returning to user space, and by KVM +before VMentry. None of the affected cores support SMT, so VERW is not required +at C-state transitions. + +New bits in IA32_ARCH_CAPABILITIES +---------------------------------- +Newer processors and microcode update on existing affected processors added new +bits to IA32_ARCH_CAPABILITIES MSR. These bits can be used to enumerate +vulnerability and mitigation capability: + +- Bit 27 - RFDS_NO - When set, processor is not affected by RFDS. +- Bit 28 - RFDS_CLEAR - When set, processor is affected by RFDS, and has the + microcode that clears the affected buffers on VERW execution. + +Mitigation control on the kernel command line +--------------------------------------------- +The kernel command line allows to control RFDS mitigation at boot time with the +parameter "reg_file_data_sampling=". The valid arguments are: + + ========== ================================================================= + on If the CPU is vulnerable, enable mitigation; CPU buffer clearing + on exit to userspace and before entering a VM. + off Disables mitigation. + ========== ================================================================= + +Mitigation default is selected by CONFIG_MITIGATION_RFDS. + +Mitigation status information +----------------------------- +The Linux kernel provides a sysfs interface to enumerate the current +vulnerability status of the system: whether the system is vulnerable, and +which mitigations are active. The relevant sysfs file is: + + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling + +The possible values in this file are: + + .. list-table:: + + * - 'Not affected' + - The processor is not vulnerable + * - 'Vulnerable' + - The processor is vulnerable, but no mitigation enabled + * - 'Vulnerable: No microcode' + - The processor is vulnerable but microcode is not updated. + * - 'Mitigation: Clear Register File' + - The processor is vulnerable and the CPU buffer clearing mitigation is + enabled. + +References +---------- +.. [#f1] Affected Processors + https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 0fba3758d0da..fda00aac0d72 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -138,11 +138,10 @@ associated with the source address of the indirect branch. Specifically, the BHB might be shared across privilege levels even in the presence of Enhanced IBRS. -Currently the only known real-world BHB attack vector is via -unprivileged eBPF. Therefore, it's highly recommended to not enable -unprivileged eBPF, especially when eIBRS is used (without retpolines). -For a full mitigation against BHB attacks, it's recommended to use -retpolines (or eIBRS combined with retpolines). +Previously the only known real-world BHB attack vector was via unprivileged +eBPF. Further research has found attacks that don't require unprivileged eBPF. +For a full mitigation against BHB attacks it is recommended to set BHI_DIS_S or +use the BHB clearing sequence. Attack scenarios ---------------- @@ -430,6 +429,23 @@ The possible values in this file are: 'PBRSB-eIBRS: Not affected' CPU is not affected by PBRSB =========================== ======================================================= + - Branch History Injection (BHI) protection status: + +.. list-table:: + + * - BHI: Not affected + - System is not affected + * - BHI: Retpoline + - System is protected by retpoline + * - BHI: BHI_DIS_S + - System is protected by BHI_DIS_S + * - BHI: SW loop; KVM SW loop + - System is protected by software clearing sequence + * - BHI: Syscall hardening + - Syscalls are hardened against BHI + * - BHI: Syscall hardening; KVM: SW loop + - System is protected from userspace attacks by syscall hardening; KVM is protected by software clearing sequence + Full mitigation might require a microcode update from the CPU vendor. When the necessary microcode is not available, the kernel will report vulnerability. @@ -484,11 +500,18 @@ Spectre variant 2 Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at boot, by setting the IBRS bit, and they're automatically protected against - Spectre v2 variant attacks, including cross-thread branch target injections - on SMT systems (STIBP). In other words, eIBRS enables STIBP too. + some Spectre v2 variant attacks. The BHB can still influence the choice of + indirect branch predictor entry, and although branch predictor entries are + isolated between modes when eIBRS is enabled, the BHB itself is not isolated + between modes. Systems which support BHI_DIS_S will set it to protect against + BHI attacks. - Legacy IBRS systems clear the IBRS bit on exit to userspace and - therefore explicitly enable STIBP for that + On Intel's enhanced IBRS systems, this includes cross-thread branch target + injections on SMT systems (STIBP). In other words, Intel eIBRS enables + STIBP, too. + + AMD Automatic IBRS does not protect userspace, and Legacy IBRS systems clear + the IBRS bit on exit to userspace, therefore both explicitly enable STIBP. The retpoline mitigation is turned on by default on vulnerable CPUs. It can be forced on or off by the administrator @@ -622,9 +645,10 @@ kernel command line. retpoline,generic Retpolines retpoline,lfence LFENCE; indirect branch retpoline,amd alias for retpoline,lfence - eibrs enhanced IBRS - eibrs,retpoline enhanced IBRS + Retpolines - eibrs,lfence enhanced IBRS + LFENCE + eibrs Enhanced/Auto IBRS + eibrs,retpoline Enhanced/Auto IBRS + Retpolines + eibrs,lfence Enhanced/Auto IBRS + LFENCE + ibrs use IBRS to protect kernel Not specifying this option is equivalent to spectre_v2=auto. @@ -684,6 +708,24 @@ For user space mitigation: spectre_v2=off. Spectre variant 1 mitigations cannot be disabled. + spectre_bhi= + + [X86] Control mitigation of Branch History Injection + (BHI) vulnerability. Syscalls are hardened against BHI + regardless of this setting. This setting affects the deployment + of the HW BHI control and the SW BHB clearing sequence. + + on + unconditionally enable. + off + unconditionally disable. + auto + enable if hardware mitigation + control(BHI_DIS_S) is available, otherwise + enable alternate mitigation in KVM. + +For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt + Mitigation selection guide -------------------------- diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst index dc00afcabb95..1bedab498104 100644 --- a/Documentation/admin-guide/index.rst +++ b/Documentation/admin-guide/index.rst @@ -82,6 +82,7 @@ configure specific aspects of kernel behavior to your liking. edid efi-stub ext4 + filesystem-monitoring nfs/index gpio/index highuid diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b085c24117d2..25ec9883c113 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1037,6 +1037,26 @@ The filter can be disabled or changed to another driver later using sysfs. + reg_file_data_sampling= + [X86] Controls mitigation for Register File Data + Sampling (RFDS) vulnerability. RFDS is a CPU + vulnerability which may allow userspace to infer + kernel data values previously stored in floating point + registers, vector registers, or integer registers. + RFDS only affects Intel Atom processors. + + on: Turns ON the mitigation. + off: Turns OFF the mitigation. + + This parameter overrides the compile time default set + by CONFIG_MITIGATION_RFDS. Mitigation cannot be + disabled when other VERW based mitigations (like MDS) + are enabled. In order to disable RFDS mitigation all + VERW based mitigations need to be disabled. + + For details see: + Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst + driver_async_probe= [KNL] List of driver names to be probed asynchronously. Format: <driver_name1>,<driver_name2>... @@ -3070,6 +3090,7 @@ nopti [X86,PPC] nospectre_v1 [X86,PPC] nospectre_v2 [X86,PPC,S390,ARM64] + reg_file_data_sampling=off [X86] retbleed=off [X86] spec_store_bypass_disable=off [X86,PPC] spectre_v2_user=off [X86] @@ -5383,6 +5404,18 @@ sonypi.*= [HW] Sony Programmable I/O Control Device driver See Documentation/admin-guide/laptops/sonypi.rst + spectre_bhi= [X86] Control mitigation of Branch History Injection + (BHI) vulnerability. Syscalls are hardened against BHI + reglardless of this setting. This setting affects the + deployment of the HW BHI control and the SW BHB + clearing sequence. + + on - unconditionally enable. + off - unconditionally disable. + auto - (default) enable hardware mitigation + (BHI_DIS_S) if available, otherwise enable + alternate mitigation in KVM. + spectre_v2= [X86] Control mitigation of Spectre variant 2 (indirect branch speculation) vulnerability. The default operation protects the kernel from @@ -5413,9 +5446,9 @@ retpoline,generic - Retpolines retpoline,lfence - LFENCE; indirect branch retpoline,amd - alias for retpoline,lfence - eibrs - enhanced IBRS - eibrs,retpoline - enhanced IBRS + Retpolines - eibrs,lfence - enhanced IBRS + LFENCE + eibrs - Enhanced/Auto IBRS + eibrs,retpoline - Enhanced/Auto IBRS + Retpolines + eibrs,lfence - Enhanced/Auto IBRS + LFENCE ibrs - use IBRS to protect kernel Not specifying this option is equivalent to diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst index 6d6d0edd2d27..829f20a193ca 100644 --- a/Documentation/core-api/dma-api.rst +++ b/Documentation/core-api/dma-api.rst @@ -206,6 +206,20 @@ others should not be larger than the returned value. :: + size_t + dma_opt_mapping_size(struct device *dev); + +Returns the maximum optimal size of a mapping for the device. + +Mapping larger buffers may take much longer in certain scenarios. In +addition, for high-rate short-lived streaming mappings, the upfront time +spent on the mapping may account for an appreciable part of the total +request lifetime. As such, if splitting larger requests incurs no +significant performance penalty, then device drivers are advised to +limit total DMA streaming mappings length to the returned value. + +:: + bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 5833cea4a16b..dabf4f7c755e 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -442,17 +442,21 @@ prototypes:: void (*lm_break)(struct file_lock *); /* break_lease callback */ int (*lm_change)(struct file_lock **, int); bool (*lm_breaker_owns_lease)(struct file_lock *); + bool (*lm_lock_expirable)(struct file_lock *); + void (*lm_expire_lock)(void); locking rules: ====================== ============= ================= ========= -ops inode->i_lock blocked_lock_lock may block +ops flc_lock blocked_lock_lock may block ====================== ============= ================= ========= -lm_notify: yes yes no +lm_notify: no yes no lm_grant: no no no lm_break: yes no no lm_change yes no no -lm_breaker_owns_lease: no no no +lm_breaker_owns_lease: yes no no +lm_lock_expirable yes no no +lm_expire_lock no no yes ====================== ============= ================= ========= buffer_head diff --git a/Documentation/filesystems/nfs/exporting.rst b/Documentation/filesystems/nfs/exporting.rst index 0e98edd353b5..6a1cbd7de38d 100644 --- a/Documentation/filesystems/nfs/exporting.rst +++ b/Documentation/filesystems/nfs/exporting.rst @@ -215,3 +215,36 @@ following flags are defined: This flag causes nfsd to close any open files for this inode _before_ calling into the vfs to do an unlink or a rename that would replace an existing file. + + EXPORT_OP_REMOTE_FS - Backing storage for this filesystem is remote + PF_LOCAL_THROTTLE exists for loopback NFSD, where a thread needs to + write to one bdi (the final bdi) in order to free up writes queued + to another bdi (the client bdi). Such threads get a private balance + of dirty pages so that dirty pages for the client bdi do not imact + the daemon writing to the final bdi. For filesystems whose durable + storage is not local (such as exported NFS filesystems), this + constraint has negative consequences. EXPORT_OP_REMOTE_FS enables + an export to disable writeback throttling. + + EXPORT_OP_NOATOMIC_ATTR - Filesystem does not update attributes atomically + EXPORT_OP_NOATOMIC_ATTR indicates that the exported filesystem + cannot provide the semantics required by the "atomic" boolean in + NFSv4's change_info4. This boolean indicates to a client whether the + returned before and after change attributes were obtained atomically + with the respect to the requested metadata operation (UNLINK, + OPEN/CREATE, MKDIR, etc). + + EXPORT_OP_FLUSH_ON_CLOSE - Filesystem flushes file data on close(2) + On most filesystems, inodes can remain under writeback after the + file is closed. NFSD relies on client activity or local flusher + threads to handle writeback. Certain filesystems, such as NFS, flush + all of an inode's dirty data on last close. Exports that behave this + way should set EXPORT_OP_FLUSH_ON_CLOSE so that NFSD knows to skip + waiting for writeback when closing such files. + + EXPORT_OP_ASYNC_LOCK - Indicates a capable filesystem to do async lock + requests from lockd. Only set EXPORT_OP_ASYNC_LOCK if the filesystem has + it's own ->lock() functionality as core posix_lock_file() implementation + has no async lock request handling yet. For more information about how to + indicate an async lock request from a ->lock() file_operations struct, see + fs/locks.c and comment for the function vfs_lock_file(). diff --git a/Documentation/x86/mds.rst b/Documentation/x86/mds.rst index 5d4330be200f..e801df0bb3a8 100644 --- a/Documentation/x86/mds.rst +++ b/Documentation/x86/mds.rst @@ -95,6 +95,9 @@ The kernel provides a function to invoke the buffer clearing: mds_clear_cpu_buffers() +Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path. +Other than CFLAGS.ZF, this macro doesn't clobber any registers. + The mitigation is invoked on kernel/userspace, hypervisor/guest and C-state (idle) transitions. @@ -138,17 +141,30 @@ Mitigation points When transitioning from kernel to user space the CPU buffers are flushed on affected CPUs when the mitigation is not disabled on the kernel - command line. The migitation is enabled through the static key - mds_user_clear. - - The mitigation is invoked in prepare_exit_to_usermode() which covers - all but one of the kernel to user space transitions. The exception - is when we return from a Non Maskable Interrupt (NMI), which is - handled directly in do_nmi(). - - (The reason that NMI is special is that prepare_exit_to_usermode() can - enable IRQs. In NMI context, NMIs are blocked, and we don't want to - enable IRQs with NMIs blocked.) + command line. The mitigation is enabled through the feature flag + X86_FEATURE_CLEAR_CPU_BUF. + + The mitigation is invoked just before transitioning to userspace after + user registers are restored. This is done to minimize the window in + which kernel data could be accessed after VERW e.g. via an NMI after + VERW. + + **Corner case not handled** + Interrupts returning to kernel don't clear CPUs buffers since the + exit-to-user path is expected to do that anyways. But, there could be + a case when an NMI is generated in kernel after the exit-to-user path + has cleared the buffers. This case is not handled and NMI returning to + kernel don't clear CPU buffers because: + + 1. It is rare to get an NMI after VERW, but before returning to userspace. + 2. For an unprivileged user, there is no known way to make that NMI + less rare or target it. + 3. It would take a large number of these precisely-timed NMIs to mount + an actual attack. There's presumably not enough bandwidth. + 4. The NMI in question occurs after a VERW, i.e. when user state is + restored and most interesting data is already scrubbed. Whats left + is only the data that NMI touches, and that may or may not be of + any interest. 2. C-State transition diff --git a/MAINTAINERS b/MAINTAINERS index 739e8234756c..307ada232af6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9213,6 +9213,7 @@ F: drivers/infiniband/ F: include/rdma/ F: include/trace/events/ib_mad.h F: include/trace/events/ib_umad.h +F: include/trace/misc/rdma.h F: include/uapi/linux/if_infiniband.h F: include/uapi/rdma/ F: samples/bpf/ibumad_kern.c @@ -10201,6 +10202,12 @@ F: fs/nfs_common/ F: fs/nfsd/ F: include/linux/lockd/ F: include/linux/sunrpc/ +F: include/trace/events/rpcgss.h +F: include/trace/events/rpcrdma.h +F: include/trace/events/sunrpc.h +F: include/trace/misc/fs.h +F: include/trace/misc/nfs.h +F: include/trace/misc/sunrpc.h F: include/uapi/linux/nfsd/ F: include/uapi/linux/sunrpc/ F: net/sunrpc/ @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 15 -SUBLEVEL = 153 +SUBLEVEL = 155 EXTRAVERSION = NAME = Trick or Treat @@ -1000,8 +1000,8 @@ KBUILD_CFLAGS += $(CC_FLAGS_CFI) export CC_FLAGS_CFI endif -ifdef CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B -KBUILD_CFLAGS += -falign-functions=64 +ifneq ($(CONFIG_FUNCTION_ALIGNMENT),0) +KBUILD_CFLAGS += -falign-functions=$(CONFIG_FUNCTION_ALIGNMENT) endif # arch Makefile may override CC so keep this after arch Makefile is included diff --git a/arch/Kconfig b/arch/Kconfig index 2e2dc0975ab4..a541ce263865 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1303,4 +1303,28 @@ source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" +config FUNCTION_ALIGNMENT_4B + bool + +config FUNCTION_ALIGNMENT_8B + bool + +config FUNCTION_ALIGNMENT_16B + bool + +config FUNCTION_ALIGNMENT_32B + bool + +config FUNCTION_ALIGNMENT_64B + bool + +config FUNCTION_ALIGNMENT + int + default 64 if FUNCTION_ALIGNMENT_64B + default 32 if FUNCTION_ALIGNMENT_32B + default 16 if FUNCTION_ALIGNMENT_16B + default 8 if FUNCTION_ALIGNMENT_8B + default 4 if FUNCTION_ALIGNMENT_4B + default 0 + endmenu diff --git a/arch/arm/boot/dts/mmp2-brownstone.dts b/arch/arm/boot/dts/mmp2-brownstone.dts index 04f1ae1382e7..bc64348b8218 100644 --- a/arch/arm/boot/dts/mmp2-brownstone.dts +++ b/arch/arm/boot/dts/mmp2-brownstone.dts @@ -28,7 +28,7 @@ &twsi1 { status = "okay"; pmic: max8925@3c { - compatible = "maxium,max8925"; + compatible = "maxim,max8925"; reg = <0x3c>; interrupts = <1>; interrupt-parent = <&intcmux4>; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index a9d36ac6cb90..a88798b80921 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -911,6 +911,8 @@ ap_spi_fp: &spi10 { vddrf-supply = <&pp1300_l2c>; vddch0-supply = <&pp3300_l10c>; max-speed = <3200000>; + + qcom,local-bd-address-broken; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 3cbe83e6fb9a..26f02cc70dc5 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -728,11 +728,20 @@ status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; + hdmi_in_vop: endpoint { remote-endpoint = <&vop_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 9e33f0e6ed50..e98966899f53 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1801,6 +1801,7 @@ hdmi: hdmi@ff940000 { compatible = "rockchip,rk3399-dw-hdmi"; reg = <0x0 0xff940000 0x0 0x20000>; + reg-io-width = <4>; interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH 0>; clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_SFR>, @@ -1809,13 +1810,16 @@ <&cru PLL_VPLL>; clock-names = "iahb", "isfr", "cec", "grf", "vpll"; power-domains = <&power RK3399_PD_HDCP>; - reg-io-width = <4>; rockchip,grf = <&grf>; #sound-dai-cells = <0>; status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; #address-cells = <1>; #size-cells = <0>; @@ -1828,6 +1832,10 @@ remote-endpoint = <&vopl_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 027783829584..87e782eec925 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -13,6 +13,18 @@ #define KVM_PGTABLE_MAX_LEVELS 4U +/* + * The largest supported block sizes for KVM (no 52-bit PA support): + * - 4K (level 1): 1GB + * - 16K (level 2): 32MB + * - 64K (level 2): 512MB + */ +#ifdef CONFIG_ARM64_4K_PAGES +#define KVM_PGTABLE_MIN_BLOCK_LEVEL 1U +#else +#define KVM_PGTABLE_MIN_BLOCK_LEVEL 2U +#endif + static inline u64 kvm_get_parange(u64 mmfr0) { u64 parange = cpuid_feature_extract_unsigned_field(mmfr0, @@ -58,11 +70,7 @@ static inline u64 kvm_granule_size(u32 level) static inline bool kvm_level_supports_block_mapping(u32 level) { - /* - * Reject invalid block mappings and don't bother with 4TB mappings for - * 52-bit PAs. - */ - return !(level == 0 || (PAGE_SIZE != SZ_4K && level == 1)); + return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL; } /** diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h index fe341a6578c3..c8dca8ae359c 100644 --- a/arch/arm64/include/asm/stage2_pgtable.h +++ b/arch/arm64/include/asm/stage2_pgtable.h @@ -11,13 +11,6 @@ #include <linux/pgtable.h> /* - * PGDIR_SHIFT determines the size a top-level page table entry can map - * and depends on the number of levels in the page table. Compute the - * PGDIR_SHIFT for a given number of levels. - */ -#define pt_levels_pgdir_shift(lvls) ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls)) - -/* * The hardware supports concatenation of up to 16 tables at stage2 entry * level and we use the feature whenever possible, which means we resolve 4 * additional bits of address at the entry level. @@ -30,11 +23,6 @@ #define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4) #define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr) -/* stage2_pgdir_shift() is the size mapped by top-level stage2 entry for the VM */ -#define stage2_pgdir_shift(kvm) pt_levels_pgdir_shift(kvm_stage2_levels(kvm)) -#define stage2_pgdir_size(kvm) (1ULL << stage2_pgdir_shift(kvm)) -#define stage2_pgdir_mask(kvm) ~(stage2_pgdir_size(kvm) - 1) - /* * kvm_mmmu_cache_min_pages() is the number of pages required to install * a stage-2 translation. We pre-allocate the entry level page table at @@ -42,12 +30,4 @@ */ #define kvm_mmu_cache_min_pages(kvm) (kvm_stage2_levels(kvm) - 1) -static inline phys_addr_t -stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) -{ - phys_addr_t boundary = (addr + stage2_pgdir_size(kvm)) & stage2_pgdir_mask(kvm); - - return (boundary - 1 < end - 1) ? boundary : end; -} - #endif /* __ARM64_S2_PGTABLE_H_ */ diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 38a8095744a0..db667b4ad103 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -31,6 +31,13 @@ static phys_addr_t hyp_idmap_vector; static unsigned long io_map_base; +static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL); + phys_addr_t boundary = ALIGN_DOWN(addr + size, size); + + return (boundary - 1 < end - 1) ? boundary : end; +} /* * Release kvm_mmu_lock periodically if the memory region is large. Otherwise, @@ -52,7 +59,7 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr, if (!pgt) return -EINVAL; - next = stage2_pgd_addr_end(kvm, addr, end); + next = stage2_range_addr_end(addr, end); ret = fn(pgt, addr, next - addr); if (ret) break; diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 57465bff1fe4..df7f349c8d4f 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -64,6 +64,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG ELF_DETAILS + .hexagon.attributes 0 : { *(.hexagon.attributes) } DISCARDS } diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 89869aff8ca2..8902d1517894 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -63,6 +63,7 @@ config IA64 select PCI_MSI_ARCH_FALLBACKS if PCI_MSI select SET_FS select ZONE_DMA32 + select FUNCTION_ALIGNMENT_32B default y help The Itanium Processor Family is Intel's 64-bit successor to diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile index 7e548c654a29..43cde968da88 100644 --- a/arch/ia64/Makefile +++ b/arch/ia64/Makefile @@ -23,7 +23,7 @@ KBUILD_AFLAGS_KERNEL := -mconstant-gp EXTRA := cflags-y := -pipe $(EXTRA) -ffixed-r13 -mfixed-range=f12-f15,f32-f127 \ - -falign-functions=32 -frename-registers -fno-optimize-sibling-calls + -frename-registers -fno-optimize-sibling-calls KBUILD_CFLAGS_KERNEL := -mconstant-gp GAS_STATUS = $(shell $(srctree)/arch/ia64/scripts/check-gas "$(CC)" "$(OBJDUMP)") diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index a82b2caaa560..b3edbb33b621 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -74,10 +74,10 @@ void *arch_dma_set_uncached(void *cpu_addr, size_t size) * We need to iterate through the pages, clearing the dcache for * them and setting the cache-inhibit bit. */ - mmap_read_lock(&init_mm); - error = walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops, - NULL); - mmap_read_unlock(&init_mm); + mmap_write_lock(&init_mm); + error = walk_page_range_novma(&init_mm, va, va + size, + &set_nocache_walk_ops, NULL, NULL); + mmap_write_unlock(&init_mm); if (error) return ERR_PTR(error); @@ -88,11 +88,11 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size) { unsigned long va = (unsigned long)cpu_addr; - mmap_read_lock(&init_mm); + mmap_write_lock(&init_mm); /* walk_page_range shouldn't be able to fail here */ - WARN_ON(walk_page_range(&init_mm, va, va + size, - &clear_nocache_walk_ops, NULL)); - mmap_read_unlock(&init_mm); + WARN_ON(walk_page_range_novma(&init_mm, va, va + size, + &clear_nocache_walk_ops, NULL, NULL)); + mmap_write_unlock(&init_mm); } void arch_sync_dma_for_device(phys_addr_t addr, size_t size, diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index fd8c1ebd2747..12b9236effbc 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -79,26 +79,28 @@ * version takes two arguments: a src and destination register. * However, the source and destination registers can not be * the same register. + * + * We use add,l to avoid clobbering the C/B bits in the PSW. */ .macro tophys grvirt, grphys - ldil L%(__PAGE_OFFSET), \grphys - sub \grvirt, \grphys, \grphys + ldil L%(-__PAGE_OFFSET), \grphys + addl \grvirt, \grphys, \grphys .endm - + .macro tovirt grphys, grvirt ldil L%(__PAGE_OFFSET), \grvirt - add \grphys, \grvirt, \grvirt + addl \grphys, \grvirt, \grvirt .endm .macro tophys_r1 gr - ldil L%(__PAGE_OFFSET), %r1 - sub \gr, %r1, \gr + ldil L%(-__PAGE_OFFSET), %r1 + addl \gr, %r1, \gr .endm - + .macro tovirt_r1 gr ldil L%(__PAGE_OFFSET), %r1 - add \gr, %r1, \gr + addl \gr, %r1, \gr .endm .macro delay value diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h index 3c43baca7b39..2aceebcd695c 100644 --- a/arch/parisc/include/asm/checksum.h +++ b/arch/parisc/include/asm/checksum.h @@ -40,7 +40,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) " addc %0, %5, %0\n" " addc %0, %3, %0\n" "1: ldws,ma 4(%1), %3\n" -" addib,< 0, %2, 1b\n" +" addib,> -1, %2, 1b\n" " addc %0, %3, %0\n" "\n" " extru %0, 31, 16, %4\n" @@ -126,6 +126,7 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, ** Try to keep 4 registers with "live" values ahead of the ALU. */ +" depdi 0, 31, 32, %0\n"/* clear upper half of incoming checksum */ " ldd,ma 8(%1), %4\n" /* get 1st saddr word */ " ldd,ma 8(%2), %5\n" /* get 1st daddr word */ " add %4, %0, %0\n" @@ -137,8 +138,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " add,dc %3, %0, %0\n" /* fold in proto+len | carry bit */ " extrd,u %0, 31, 32, %4\n"/* copy upper half down */ " depdi 0, 31, 32, %0\n"/* clear upper half */ -" add %4, %0, %0\n" /* fold into 32-bits */ -" addc 0, %0, %0\n" /* add carry */ +" add,dc %4, %0, %0\n" /* fold into 32-bits, plus carry */ +" addc 0, %0, %0\n" /* add final carry */ #else @@ -163,7 +164,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " ldw,ma 4(%2), %7\n" /* 4th daddr */ " addc %6, %0, %0\n" " addc %7, %0, %0\n" -" addc %3, %0, %0\n" /* fold in proto+len, catch carry */ +" addc %3, %0, %0\n" /* fold in proto+len */ +" addc 0, %0, %0\n" /* add carry */ #endif : "=r" (sum), "=r" (saddr), "=r" (daddr), "=r" (len), diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h index a21f529c43d9..8359c06d92d9 100644 --- a/arch/powerpc/include/asm/reg_fsl_emb.h +++ b/arch/powerpc/include/asm/reg_fsl_emb.h @@ -12,9 +12,16 @@ #ifndef __ASSEMBLY__ /* Performance Monitor Registers */ #define mfpmr(rn) ({unsigned int rval; \ - asm volatile("mfpmr %0," __stringify(rn) \ + asm volatile(".machine push; " \ + ".machine e300; " \ + "mfpmr %0," __stringify(rn) ";" \ + ".machine pop; " \ : "=r" (rval)); rval;}) -#define mtpmr(rn, v) asm volatile("mtpmr " __stringify(rn) ",%0" : : "r" (v)) +#define mtpmr(rn, v) asm volatile(".machine push; " \ + ".machine e300; " \ + "mtpmr " __stringify(rn) ",%0; " \ + ".machine pop; " \ + : : "r" (v)) #endif /* __ASSEMBLY__ */ /* Freescale Book E Performance Monitor APU Registers */ diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 6448de85f738..2a4f3d09a08e 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -67,6 +67,6 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o obj-$(CONFIG_ALTIVEC) += xor_vmx.o xor_vmx_glue.o -CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec) +CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec) obj-$(CONFIG_PPC64) += $(obj64-y) diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index d4d628af21a4..0a38801c52aa 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -467,7 +467,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n) #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \ if (unlikely(__kr_err)) \ @@ -476,7 +476,7 @@ do { \ #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \ if (unlikely(__kr_err)) \ diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index bda3bc294718..1dea5b26f77e 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -24,8 +24,6 @@ #include <asm/switch_to.h> #include <asm/thread_info.h> -register unsigned long gp_in_global __asm__("gp"); - #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include <linux/stackprotector.h> unsigned long __stack_chk_guard __read_mostly; @@ -130,7 +128,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* Kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - childregs->gp = gp_in_global; /* Supervisor/Machine, irqs on: */ childregs->status = SR_PP | SR_PIE; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index d530eb4dc413..74ef903f94e7 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -685,6 +685,7 @@ ENDPROC(stack_overflow) .Lthis_cpu: .short 0 .Lstosm_tmp: .byte 0 .section .rodata, "a" + .balign 8 #define SYSCALL(esame,emu) .quad __s390x_ ## esame .globl sys_call_table sys_call_table: diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 060fff95a305..fbf25e926f67 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -274,7 +274,7 @@ static int __init setup_nmi_watchdog(char *str) if (!strncmp(str, "panic", 5)) panic_on_timeout = 1; - return 0; + return 1; } __setup("nmi_watchdog=", setup_nmi_watchdog); diff --git a/arch/sparc/vdso/vma.c b/arch/sparc/vdso/vma.c index cc19e09b0fa1..b073153c711a 100644 --- a/arch/sparc/vdso/vma.c +++ b/arch/sparc/vdso/vma.c @@ -449,9 +449,8 @@ static __init int vdso_setup(char *s) unsigned long val; err = kstrtoul(s, 10, &val); - if (err) - return err; - vdso_enabled = val; - return 0; + if (!err) + vdso_enabled = val; + return 1; } __setup("vdso=", vdso_setup); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5dfd27ab412c..4cd18523662b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -269,6 +269,8 @@ config X86 select HAVE_ARCH_KCSAN if X86_64 select X86_FEATURE_NAMES if PROC_FS select PROC_PID_ARCH_STATUS if PROC_FS + select FUNCTION_ALIGNMENT_16B if X86_64 || X86_ALIGNMENT_16 + select FUNCTION_ALIGNMENT_4B imply IMA_SECURE_AND_OR_TRUSTED_BOOT if EFI config INSTRUCTION_DECODER @@ -2500,6 +2502,42 @@ config GDS_FORCE_MITIGATION If in doubt, say N. +config MITIGATION_RFDS + bool "RFDS Mitigation" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for Register File Data Sampling (RFDS) by default. + RFDS is a hardware vulnerability which affects Intel Atom CPUs. It + allows unprivileged speculative access to stale data previously + stored in floating point, vector and integer registers. + See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst> + +choice + prompt "Clear branch history" + depends on CPU_SUP_INTEL + default SPECTRE_BHI_ON + help + Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks + where the branch history buffer is poisoned to speculatively steer + indirect branches. + See <file:Documentation/admin-guide/hw-vuln/spectre.rst> + +config SPECTRE_BHI_ON + bool "on" + help + Equivalent to setting spectre_bhi=on command line parameter. +config SPECTRE_BHI_OFF + bool "off" + help + Equivalent to setting spectre_bhi=off command line parameter. +config SPECTRE_BHI_AUTO + bool "auto" + help + Equivalent to setting spectre_bhi=auto command line parameter. + +endchoice + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index c3d427c817c7..e189a16ae40a 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -38,6 +38,14 @@ #include "pgtable.h" /* + * Fix alignment at 16 bytes. Following CONFIG_FUNCTION_ALIGNMENT will result + * in assembly errors due to trying to move .org backward due to the excessive + * alignment. + */ +#undef __ALIGN +#define __ALIGN .balign 16, 0x90 + +/* * Locally defined symbols should be marked hidden: */ .hidden _bss diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 6c2826417b33..e160f502d1dc 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -47,7 +47,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr) if (likely(unr < NR_syscalls)) { unr = array_index_nospec(unr, NR_syscalls); - regs->ax = sys_call_table[unr](regs); + regs->ax = x64_sys_call(regs, unr); return true; } return false; @@ -64,7 +64,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr) if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) { xnr = array_index_nospec(xnr, X32_NR_syscalls); - regs->ax = x32_sys_call_table[xnr](regs); + regs->ax = x32_sys_call(regs, xnr); return true; } return false; @@ -109,7 +109,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) if (likely(unr < IA32_NR_syscalls)) { unr = array_index_nospec(unr, IA32_NR_syscalls); - regs->ax = ia32_sys_call_table[unr](regs); + regs->ax = ia32_sys_call(regs, unr); } else if (nr != -1) { regs->ax = __ia32_sys_ni_syscall(regs); } diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index bfb7bcb362bc..09e99d13fc0b 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -6,6 +6,9 @@ #include <linux/linkage.h> #include <asm/export.h> #include <asm/msr-index.h> +#include <asm/unwind_hints.h> +#include <asm/segment.h> +#include <asm/cache.h> .pushsection .noinstr.text, "ax" @@ -20,3 +23,23 @@ SYM_FUNC_END(entry_ibpb) EXPORT_SYMBOL_GPL(entry_ibpb); .popsection + +/* + * Define the VERW operand that is disguised as entry code so that + * it can be referenced with KPTI enabled. This ensure VERW can be + * used late in exit-to-user path after page tables are switched. + */ +.pushsection .entry.text, "ax" + +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_START_NOALIGN(mds_verw_sel) + UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR + .word __KERNEL_DS +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_END(mds_verw_sel); +/* For KVM */ +EXPORT_SYMBOL_GPL(mds_verw_sel); + +.popsection + diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index e309e7156038..ee5def1060c8 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -912,6 +912,7 @@ SYM_FUNC_START(entry_SYSENTER_32) BUG_IF_WRONG_CR3 no_user_check=1 popfl popl %eax + CLEAR_CPU_BUFFERS /* * Return back to the vDSO, which will pop ecx and edx. @@ -981,6 +982,7 @@ restore_all_switch_stack: /* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code + CLEAR_CPU_BUFFERS .Lirq_return: /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -1173,6 +1175,7 @@ SYM_CODE_START(asm_exc_nmi) /* Not on SYSENTER stack. */ call exc_nmi + CLEAR_CPU_BUFFERS jmp .Lnmi_return .Lnmi_from_sysenter_stack: diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 9f1333a9ee41..10d6888713d8 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -114,6 +114,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) /* clobbers %rax, make sure it is after saving the syscall nr */ IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY call do_syscall_64 /* returns with IRQs disabled */ @@ -219,6 +220,7 @@ syscall_return_via_sysret: popq %rdi popq %rsp swapgs + CLEAR_CPU_BUFFERS sysretq SYM_CODE_END(entry_SYSCALL_64) @@ -637,6 +639,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) /* Restore RDI. */ popq %rdi SWAPGS + CLEAR_CPU_BUFFERS INTERRUPT_RETURN @@ -743,6 +746,8 @@ native_irq_return_ldt: */ popq %rax /* Restore user RAX */ + CLEAR_CPU_BUFFERS + /* * RSP now points to an ordinary IRET frame, except that the page * is read-only and RSP[31:16] are preloaded with the userspace @@ -1466,6 +1471,12 @@ nmi_restore: movq $0, 5*8(%rsp) /* clear "NMI executing" */ /* + * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like + * NMI in kernel after user state is restored. For an unprivileged user + * these conditions are hard to meet. + */ + + /* * iretq reads the "iret" frame and exits the NMI stack in a * single instruction. We are returning to kernel mode, so this * cannot result in a fault. Similarly, we don't need to worry @@ -1482,6 +1493,7 @@ SYM_CODE_END(asm_exc_nmi) SYM_CODE_START(ignore_sysret) UNWIND_HINT_EMPTY mov $-ENOSYS, %eax + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(ignore_sysret) #endif @@ -1499,3 +1511,63 @@ SYM_CODE_START(rewind_stack_and_make_dead) call make_task_dead SYM_CODE_END(rewind_stack_and_make_dead) .popsection + +/* + * This sequence executes branches in order to remove user branch information + * from the branch history tracker in the Branch Predictor, therefore removing + * user influence on subsequent BTB lookups. + * + * It should be used on parts prior to Alder Lake. Newer parts should use the + * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being + * virtualized on newer hardware the VMM should protect against BHI attacks by + * setting BHI_DIS_S for the guests. + * + * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging + * and not clearing the branch history. The call tree looks like: + * + * call 1 + * call 2 + * call 2 + * call 2 + * call 2 + * call 2 + * ret + * ret + * ret + * ret + * ret + * ret + * + * This means that the stack is non-constant and ORC can't unwind it with %rsp + * alone. Therefore we unconditionally set up the frame pointer, which allows + * ORC to unwind properly. + * + * The alignment is for performance and not for safety, and may be safely + * refactored in the future if needed. + */ +SYM_FUNC_START(clear_bhb_loop) + push %rbp + mov %rsp, %rbp + movl $5, %ecx + ANNOTATE_INTRA_FUNCTION_CALL + call 1f + jmp 5f + .align 64, 0xcc + ANNOTATE_INTRA_FUNCTION_CALL +1: call 2f + RET + .align 64, 0xcc +2: movl $5, %eax +3: jmp 4f + nop +4: sub $1, %eax + jnz 3b + sub $1, %ecx + jnz 1b + RET +5: lfence + pop %rbp + RET +SYM_FUNC_END(clear_bhb_loop) +EXPORT_SYMBOL_GPL(clear_bhb_loop) +STACK_FRAME_NON_STANDARD(clear_bhb_loop) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 4d637a965efb..d03f0cfbcb1e 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY /* * SYSENTER doesn't filter flags, so we need to clear NT and AC @@ -259,6 +260,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY movq %rsp, %rdi call do_fast_syscall_32 @@ -319,6 +321,7 @@ sysret32_from_system_call: xorl %r9d, %r9d xorl %r10d, %r10d swapgs + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(entry_SYSCALL_compat) @@ -421,6 +424,7 @@ SYM_CODE_START(entry_INT80_compat) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY movq %rsp, %rdi call do_int80_syscall_32 diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 8cfc9bc73e7f..c2235bae17ef 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -18,8 +18,25 @@ #include <asm/syscalls_32.h> #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ +#ifdef CONFIG_X86_32 #define __SYSCALL(nr, sym) __ia32_##sym, - -__visible const sys_call_ptr_t ia32_sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include <asm/syscalls_32.h> }; +#undef __SYSCALL +#endif + +#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs); + +long ia32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_32.h> + default: return __ia32_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index be120eec1fc9..33b3f09e6f15 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -11,8 +11,23 @@ #include <asm/syscalls_64.h> #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ #define __SYSCALL(nr, sym) __x64_##sym, - -asmlinkage const sys_call_ptr_t sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include <asm/syscalls_64.h> }; +#undef __SYSCALL + +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); + +long x64_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_64.h> + default: return __x64_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c index bdd0e03a1265..03de4a932131 100644 --- a/arch/x86/entry/syscall_x32.c +++ b/arch/x86/entry/syscall_x32.c @@ -11,8 +11,12 @@ #include <asm/syscalls_x32.h> #undef __SYSCALL -#define __SYSCALL(nr, sym) __x64_##sym, +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); -asmlinkage const sys_call_ptr_t x32_sys_call_table[] = { -#include <asm/syscalls_x32.h> +long x32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_x32.h> + default: return __x64_sys_ni_syscall(regs); + } }; diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 8f80de627c60..5cdccea45554 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -12,6 +12,7 @@ #include <asm/special_insns.h> #include <asm/preempt.h> #include <asm/asm.h> +#include <asm/nospec-branch.h> #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 6dd47c9ec788..fbcfec4dc4cc 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -6,11 +6,13 @@ # define __ASM_FORM(x, ...) x,## __VA_ARGS__ # define __ASM_FORM_RAW(x, ...) x,## __VA_ARGS__ # define __ASM_FORM_COMMA(x, ...) x,## __VA_ARGS__, +# define __ASM_REGPFX % #else #include <linux/stringify.h> # define __ASM_FORM(x, ...) " " __stringify(x,##__VA_ARGS__) " " # define __ASM_FORM_RAW(x, ...) __stringify(x,##__VA_ARGS__) # define __ASM_FORM_COMMA(x, ...) " " __stringify(x,##__VA_ARGS__) "," +# define __ASM_REGPFX %% #endif #define _ASM_BYTES(x, ...) __ASM_FORM(.byte x,##__VA_ARGS__ ;) @@ -49,6 +51,9 @@ #define _ASM_SI __ASM_REG(si) #define _ASM_DI __ASM_REG(di) +/* Adds a (%rip) suffix on 64 bits only; for immediate memory references */ +#define _ASM_RIP(x) __ASM_SEL_RAW(x, x (__ASM_REGPFX rip)) + #ifndef __x86_64__ /* 32 bit */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index cc3f62f5d551..955ca6b13e35 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -33,6 +33,8 @@ enum cpuid_leafs CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, + CPUID_LNX_5, + NR_CPUID_WORDS, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -93,8 +95,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -118,8 +121,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index d6089072ee41..18817817ea81 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* @@ -302,7 +302,7 @@ #define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ #define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ #define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ - +#define X86_FEATURE_CLEAR_CPU_BUF (11*32+18) /* "" Clear CPU buffers using VERW */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ @@ -416,11 +416,23 @@ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ #define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ /* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0x80000022, etc and Linux defined features. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ + +/* * BUG word(s) */ #define X86_BUG(x) (NCAPINTS*32 + (x)) @@ -466,4 +478,6 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 99a12012c66e..b05d815ceaaa 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -109,6 +109,7 @@ #define DISABLED_MASK18 0 #define DISABLED_MASK19 0 #define DISABLED_MASK20 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define DISABLED_MASK21 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index a12fdf01dc26..f27d6cecd803 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -91,7 +91,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static __always_inline void arch_exit_to_user_mode(void) { - mds_user_clear_cpu_buffers(); amd_clear_divider(); } #define arch_exit_to_user_mode arch_exit_to_user_mode diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 5000cf59bdf5..04a333c334ae 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -11,12 +11,14 @@ #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0))) #endif /* CONFIG_X86_32 */ -#ifdef __ASSEMBLY__ - -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16) -#define __ALIGN .p2align 4, 0x90 +#define __ALIGN .balign CONFIG_FUNCTION_ALIGNMENT, 0x90; #define __ALIGN_STR __stringify(__ALIGN) -#endif + +#define ASM_FUNC_ALIGN __ALIGN_STR +#define __FUNC_ALIGN __ALIGN +#define SYM_F_ALIGN __FUNC_ALIGN + +#ifdef __ASSEMBLY__ #if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) #define RET jmp __x86_return_thunk diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 5672ccb80eb1..15939a71dca7 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -30,6 +30,7 @@ #define _EFER_SVME 12 /* Enable virtualization */ #define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */ #define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ +#define _EFER_AUTOIBRS 21 /* Enable Automatic IBRS */ #define EFER_SCE (1<<_EFER_SCE) #define EFER_LME (1<<_EFER_LME) @@ -38,6 +39,7 @@ #define EFER_SVME (1<<_EFER_SVME) #define EFER_LMSLE (1<<_EFER_LMSLE) #define EFER_FFXSR (1<<_EFER_FFXSR) +#define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) /* Intel MSRs. Some also available on other CPUs */ @@ -53,10 +55,13 @@ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */ +#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT) /* A mask for bits which the kernel toggles when controlling mitigations */ #define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ - | SPEC_CTRL_RRSBA_DIS_S) + | SPEC_CTRL_RRSBA_DIS_S \ + | SPEC_CTRL_BHI_DIS_S) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -153,6 +158,10 @@ * are restricted to targets in * kernel. */ +#define ARCH_CAP_BHI_NO BIT(20) /* + * CPU is not affected by Branch + * History Injection. + */ #define ARCH_CAP_PBRSB_NO BIT(24) /* * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. @@ -166,6 +175,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f3f6c28e5818..ed582fa98cb2 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -155,11 +155,20 @@ .Lskip_rsb_\@: .endm +/* + * The CALL to srso_alias_untrain_ret() must be patched in directly at + * the spot where untraining must be done, ie., srso_alias_untrain_ret() + * must be the target of a CALL instruction instead of indirectly + * jumping to a wrapper which then calls it. Therefore, this macro is + * called outside of __UNTRAIN_RET below, for the time being, before the + * kernel can support nested alternatives with arbitrary nesting. + */ +.macro CALL_UNTRAIN_RET #ifdef CONFIG_CPU_UNRET_ENTRY -#define CALL_UNTRAIN_RET "call entry_untrain_ret" -#else -#define CALL_UNTRAIN_RET "" + ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ + "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif +.endm /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the @@ -176,12 +185,37 @@ #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ defined(CONFIG_CPU_SRSO) ANNOTATE_UNRET_END - ALTERNATIVE_2 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", X86_FEATURE_ENTRY_IBPB + CALL_UNTRAIN_RET + ALTERNATIVE "", "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif .endm +/* + * Macro to execute VERW instruction that mitigate transient data sampling + * attacks such as MDS. On affected systems a microcode update overloaded VERW + * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. + * + * Note: Only the memory operand variant of VERW clears the CPU buffers. + */ +.macro CLEAR_CPU_BUFFERS + ALTERNATIVE "jmp .Lskip_verw_\@", "", X86_FEATURE_CLEAR_CPU_BUF + verw _ASM_RIP(mds_verw_sel) +.Lskip_verw_\@: +.endm + +#ifdef CONFIG_X86_64 +.macro CLEAR_BRANCH_HISTORY + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP +.endm + +.macro CLEAR_BRANCH_HISTORY_VMEXIT + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT +.endm +#else +#define CLEAR_BRANCH_HISTORY +#define CLEAR_BRANCH_HISTORY_VMEXIT +#endif + #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ @@ -207,6 +241,10 @@ extern void srso_alias_untrain_ret(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); +#ifdef CONFIG_X86_64 +extern void clear_bhb_loop(void); +#endif + extern void (*x86_return_thunk)(void); #ifdef CONFIG_RETPOLINE @@ -357,13 +395,14 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); +extern u16 mds_verw_sel; + #include <asm/segment.h> /** @@ -390,17 +429,6 @@ static __always_inline void mds_clear_cpu_buffers(void) } /** - * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability - * - * Clear CPU buffers if the corresponding static key is enabled - */ -static __always_inline void mds_user_clear_cpu_buffers(void) -{ - if (static_branch_likely(&mds_user_clear)) - mds_clear_cpu_buffers(); -} - -/** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * * Clear CPU buffers if the corresponding static key is enabled diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 9bf60a8b9e9c..1fbe53583e95 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -103,6 +103,7 @@ #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 #define REQUIRED_MASK20 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define REQUIRED_MASK21 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index a800abb1a992..d8416b3bf832 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -12,11 +12,6 @@ /* image of the saved processor state */ struct saved_context { - /* - * On x86_32, all segment registers except gs are saved at kernel - * entry in pt_regs. - */ - u16 gs; unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; struct saved_msrs saved_msrs; @@ -27,6 +22,11 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + /* + * On x86_32, all segment registers except gs are saved at kernel + * entry in pt_regs. + */ + u16 gs; bool misc_enable_saved; } __attribute__((packed)); diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index f7e2d82d24fb..825528bf0daf 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -16,19 +16,17 @@ #include <asm/thread_info.h> /* for TS_COMPAT */ #include <asm/unistd.h> +/* This is used purely for kernel/trace/trace_syscalls.c */ typedef long (*sys_call_ptr_t)(const struct pt_regs *); extern const sys_call_ptr_t sys_call_table[]; -#if defined(CONFIG_X86_32) -#define ia32_sys_call_table sys_call_table -#else /* * These may not exist, but still put the prototypes in so we * can use IS_ENABLED(). */ -extern const sys_call_ptr_t ia32_sys_call_table[]; -extern const sys_call_ptr_t x32_sys_call_table[]; -#endif +extern long ia32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x64_sys_call(const struct pt_regs *, unsigned int nr); /* * Only the low 32 bits of orig_ax are meaningful, so we return int. diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index c6015b407461..7281ce64e99d 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -181,6 +181,37 @@ void int3_emulate_ret(struct pt_regs *regs) unsigned long ip = int3_emulate_pop(regs); int3_emulate_jmp(regs, ip); } + +static __always_inline +void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned long disp) +{ + static const unsigned long jcc_mask[6] = { + [0] = X86_EFLAGS_OF, + [1] = X86_EFLAGS_CF, + [2] = X86_EFLAGS_ZF, + [3] = X86_EFLAGS_CF | X86_EFLAGS_ZF, + [4] = X86_EFLAGS_SF, + [5] = X86_EFLAGS_PF, + }; + + bool invert = cc & 1; + bool match; + + if (cc < 0xc) { + match = regs->flags & jcc_mask[cc >> 1]; + } else { + match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ + ((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); + if (cc >= 0xe) + match = match || (regs->flags & X86_EFLAGS_ZF); + } + + if ((match && !invert) || (!match && invert)) + ip += disp; + + int3_emulate_jmp(regs, ip); +} + #endif /* !CONFIG_UML_X86 */ #endif /* _ASM_X86_TEXT_PATCHING_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index e5536edbae57..5614e6d219b7 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -351,6 +351,12 @@ next: kasan_enable_current(); } +static inline bool is_jcc32(struct insn *insn) +{ + /* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */ + return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80; +} + #if defined(CONFIG_RETPOLINE) && defined(CONFIG_STACK_VALIDATION) /* @@ -1201,6 +1207,11 @@ void text_poke_sync(void) on_each_cpu(do_sync_core, NULL, 1); } +/* + * NOTE: crazy scheme to allow patching Jcc.d32 but not increase the size of + * this thing. When len == 6 everything is prefixed with 0x0f and we map + * opcode to Jcc.d8, using len to distinguish. + */ struct text_poke_loc { /* addr := _stext + rel_addr */ s32 rel_addr; @@ -1322,6 +1333,10 @@ noinstr int poke_int3_handler(struct pt_regs *regs) int3_emulate_jmp(regs, (long)ip + tp->disp); break; + case 0x70 ... 0x7f: /* Jcc */ + int3_emulate_jcc(regs, tp->opcode & 0xf, (long)ip, tp->disp); + break; + default: BUG(); } @@ -1395,16 +1410,26 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries * Second step: update all but the first byte of the patched range. */ for (do_sync = 0, i = 0; i < nr_entries; i++) { - u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, }; + u8 old[POKE_MAX_OPCODE_SIZE+1] = { tp[i].old, }; + u8 _new[POKE_MAX_OPCODE_SIZE+1]; + const u8 *new = tp[i].text; int len = tp[i].len; if (len - INT3_INSN_SIZE > 0) { memcpy(old + INT3_INSN_SIZE, text_poke_addr(&tp[i]) + INT3_INSN_SIZE, len - INT3_INSN_SIZE); + + if (len == 6) { + _new[0] = 0x0f; + memcpy(_new + 1, new, 5); + new = _new; + } + text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE, - (const char *)tp[i].text + INT3_INSN_SIZE, + new + INT3_INSN_SIZE, len - INT3_INSN_SIZE); + do_sync++; } @@ -1432,8 +1457,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries * The old instruction is recorded so that the event can be * processed forwards or backwards. */ - perf_event_text_poke(text_poke_addr(&tp[i]), old, len, - tp[i].text, len); + perf_event_text_poke(text_poke_addr(&tp[i]), old, len, new, len); } if (do_sync) { @@ -1450,10 +1474,15 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries * replacing opcode. */ for (do_sync = 0, i = 0; i < nr_entries; i++) { - if (tp[i].text[0] == INT3_INSN_OPCODE) + u8 byte = tp[i].text[0]; + + if (tp[i].len == 6) + byte = 0x0f; + + if (byte == INT3_INSN_OPCODE) continue; - text_poke(text_poke_addr(&tp[i]), tp[i].text, INT3_INSN_SIZE); + text_poke(text_poke_addr(&tp[i]), &byte, INT3_INSN_SIZE); do_sync++; } @@ -1471,9 +1500,11 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, const void *opcode, size_t len, const void *emulate) { struct insn insn; - int ret, i; + int ret, i = 0; - memcpy((void *)tp->text, opcode, len); + if (len == 6) + i = 1; + memcpy((void *)tp->text, opcode+i, len-i); if (!emulate) emulate = opcode; @@ -1484,6 +1515,13 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, tp->len = len; tp->opcode = insn.opcode.bytes[0]; + if (is_jcc32(&insn)) { + /* + * Map Jcc.d32 onto Jcc.d8 and use len to distinguish. + */ + tp->opcode = insn.opcode.bytes[1] - 0x10; + } + switch (tp->opcode) { case RET_INSN_OPCODE: case JMP32_INSN_OPCODE: @@ -1500,7 +1538,6 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, BUG_ON(len != insn.length); }; - switch (tp->opcode) { case INT3_INSN_OPCODE: case RET_INSN_OPCODE: @@ -1509,6 +1546,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, case CALL_INSN_OPCODE: case JMP32_INSN_OPCODE: case JMP8_INSN_OPCODE: + case 0x70 ... 0x7f: /* Jcc */ tp->disp = insn.immediate.value; break; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index dba7fe7ecea9..9fb890574f36 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1021,11 +1021,11 @@ static bool cpu_has_zenbleed_microcode(void) u32 good_rev = 0; switch (boot_cpu_data.x86_model) { - case 0x30 ... 0x3f: good_rev = 0x0830107a; break; - case 0x60 ... 0x67: good_rev = 0x0860010b; break; - case 0x68 ... 0x6f: good_rev = 0x08608105; break; - case 0x70 ... 0x7f: good_rev = 0x08701032; break; - case 0xa0 ... 0xaf: good_rev = 0x08a00008; break; + case 0x30 ... 0x3f: good_rev = 0x0830107b; break; + case 0x60 ... 0x67: good_rev = 0x0860010c; break; + case 0x68 ... 0x6f: good_rev = 0x08608107; break; + case 0x70 ... 0x7f: good_rev = 0x08701033; break; + case 0xa0 ... 0xaf: good_rev = 0x08a00009; break; default: return false; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d1ba55ea46a7..50fdd6ca3b78 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -110,9 +110,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -/* Control MDS CPU buffer clear before returning to user space */ -DEFINE_STATIC_KEY_FALSE(mds_user_clear); -EXPORT_SYMBOL_GPL(mds_user_clear); /* Control MDS CPU buffer clear before idling (halt, mwait) */ DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); @@ -258,7 +255,7 @@ static void __init mds_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV; - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && (mds_nosmt || cpu_mitigations_auto_nosmt())) @@ -362,7 +359,7 @@ static void __init taa_select_mitigation(void) * For guests that can't determine whether the correct microcode is * present on host, enable the mitigation for UCODE_NEEDED as well. */ - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); @@ -430,7 +427,14 @@ static void __init mmio_select_mitigation(void) */ if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + + /* + * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based + * mitigations, disable KVM-only mitigation in that case. + */ + if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) + static_branch_disable(&mmio_stale_data_clear); else static_branch_enable(&mmio_stale_data_clear); @@ -483,6 +487,57 @@ static int __init mmio_stale_data_parse_cmdline(char *str) early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "Register File Data Sampling: " fmt + +enum rfds_mitigations { + RFDS_MITIGATION_OFF, + RFDS_MITIGATION_VERW, + RFDS_MITIGATION_UCODE_NEEDED, +}; + +/* Default mitigation for Register File Data Sampling */ +static enum rfds_mitigations rfds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF; + +static const char * const rfds_strings[] = { + [RFDS_MITIGATION_OFF] = "Vulnerable", + [RFDS_MITIGATION_VERW] = "Mitigation: Clear Register File", + [RFDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", +}; + +static void __init rfds_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) { + rfds_mitigation = RFDS_MITIGATION_OFF; + return; + } + if (rfds_mitigation == RFDS_MITIGATION_OFF) + return; + + if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR) + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + else + rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; +} + +static __init int rfds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + return 0; + + if (!strcmp(str, "off")) + rfds_mitigation = RFDS_MITIGATION_OFF; + else if (!strcmp(str, "on")) + rfds_mitigation = RFDS_MITIGATION_VERW; + + return 0; +} +early_param("reg_file_data_sampling", rfds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "" fmt static void __init md_clear_update_mitigation(void) @@ -490,12 +545,12 @@ static void __init md_clear_update_mitigation(void) if (cpu_mitigations_off()) return; - if (!static_key_enabled(&mds_user_clear)) + if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) goto out; /* - * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data - * mitigation, if necessary. + * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO + * Stale Data mitigation, if necessary. */ if (mds_mitigation == MDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_MDS)) { @@ -507,11 +562,19 @@ static void __init md_clear_update_mitigation(void) taa_mitigation = TAA_MITIGATION_VERW; taa_select_mitigation(); } - if (mmio_mitigation == MMIO_MITIGATION_OFF && - boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { + /* + * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear + * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state. + */ + if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { mmio_mitigation = MMIO_MITIGATION_VERW; mmio_select_mitigation(); } + if (rfds_mitigation == RFDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_RFDS)) { + rfds_mitigation = RFDS_MITIGATION_VERW; + rfds_select_mitigation(); + } out: if (boot_cpu_has_bug(X86_BUG_MDS)) pr_info("MDS: %s\n", mds_strings[mds_mitigation]); @@ -521,6 +584,8 @@ out: pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) pr_info("MMIO Stale Data: Unknown: No mitigations\n"); + if (boot_cpu_has_bug(X86_BUG_RFDS)) + pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]); } static void __init md_clear_select_mitigation(void) @@ -528,11 +593,12 @@ static void __init md_clear_select_mitigation(void) mds_select_mitigation(); taa_select_mitigation(); mmio_select_mitigation(); + rfds_select_mitigation(); /* - * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update - * and print their mitigation after MDS, TAA and MMIO Stale Data - * mitigation selection is done. + * As these mitigations are inter-related and rely on VERW instruction + * to clear the microarchitural buffers, update and print their status + * after mitigation selection is done for each of these vulnerabilities. */ md_clear_update_mitigation(); } @@ -1288,19 +1354,21 @@ spectre_v2_user_select_mitigation(void) } /* - * If no STIBP, enhanced IBRS is enabled, or SMT impossible, STIBP + * If no STIBP, Intel enhanced IBRS is enabled, or SMT impossible, STIBP * is not required. * - * Enhanced IBRS also protects against cross-thread branch target + * Intel's Enhanced IBRS also protects against cross-thread branch target * injection in user-mode as the IBRS bit remains always set which * implicitly enables cross-thread protections. However, in legacy IBRS * mode, the IBRS bit is set only on kernel entry and cleared on return - * to userspace. This disables the implicit cross-thread protection, - * so allow for STIBP to be selected in that case. + * to userspace. AMD Automatic IBRS also does not protect userspace. + * These modes therefore disable the implicit cross-thread protection, + * so allow for STIBP to be selected in those cases. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS))) return; /* @@ -1330,9 +1398,9 @@ static const char * const spectre_v2_strings[] = { [SPECTRE_V2_NONE] = "Vulnerable", [SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines", [SPECTRE_V2_LFENCE] = "Mitigation: LFENCE", - [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", - [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", - [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", + [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced / Automatic IBRS", + [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced / Automatic IBRS + LFENCE", + [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced / Automatic IBRS + Retpolines", [SPECTRE_V2_IBRS] = "Mitigation: IBRS", }; @@ -1401,7 +1469,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && !boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { - pr_err("%s selected but CPU doesn't have eIBRS. Switching to AUTO select\n", + pr_err("%s selected but CPU doesn't have Enhanced or Automatic IBRS. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -1516,6 +1584,79 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_ dump_stack(); } +/* + * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by + * branch history in userspace. Not needed if BHI_NO is set. + */ +static bool __init spec_ctrl_bhi_dis(void) +{ + if (!boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW); + + return true; +} + +enum bhi_mitigations { + BHI_MITIGATION_OFF, + BHI_MITIGATION_ON, + BHI_MITIGATION_AUTO, +}; + +static enum bhi_mitigations bhi_mitigation __ro_after_init = + IS_ENABLED(CONFIG_SPECTRE_BHI_ON) ? BHI_MITIGATION_ON : + IS_ENABLED(CONFIG_SPECTRE_BHI_OFF) ? BHI_MITIGATION_OFF : + BHI_MITIGATION_AUTO; + +static int __init spectre_bhi_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + bhi_mitigation = BHI_MITIGATION_OFF; + else if (!strcmp(str, "on")) + bhi_mitigation = BHI_MITIGATION_ON; + else if (!strcmp(str, "auto")) + bhi_mitigation = BHI_MITIGATION_AUTO; + else + pr_err("Ignoring unknown spectre_bhi option (%s)", str); + + return 0; +} +early_param("spectre_bhi", spectre_bhi_parse_cmdline); + +static void __init bhi_select_mitigation(void) +{ + if (bhi_mitigation == BHI_MITIGATION_OFF) + return; + + /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */ + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) && + !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA)) + return; + + if (spec_ctrl_bhi_dis()) + return; + + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + /* Mitigate KVM by default */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); + pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n"); + + if (bhi_mitigation == BHI_MITIGATION_AUTO) + return; + + /* Mitigate syscalls when the mitigation is forced =on */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP); + pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n"); +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1586,8 +1727,12 @@ static void __init spectre_v2_select_mitigation(void) pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); if (spectre_v2_in_ibrs_mode(mode)) { - x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - update_spec_ctrl(x86_spec_ctrl_base); + if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) { + msr_set_bit(MSR_EFER, _EFER_AUTOIBRS); + } else { + x86_spec_ctrl_base |= SPEC_CTRL_IBRS; + update_spec_ctrl(x86_spec_ctrl_base); + } } switch (mode) { @@ -1622,6 +1767,9 @@ static void __init spectre_v2_select_mitigation(void) mode == SPECTRE_V2_RETPOLINE) spec_ctrl_disable_kernel_rrsba(); + if (boot_cpu_has(X86_BUG_BHI)) + bhi_select_mitigation(); + spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -1671,8 +1819,8 @@ static void __init spectre_v2_select_mitigation(void) /* * Retpoline protects the kernel, but doesn't protect firmware. IBRS * and Enhanced IBRS protect firmware too, so enable IBRS around - * firmware calls only when IBRS / Enhanced IBRS aren't otherwise - * enabled. + * firmware calls only when IBRS / Enhanced / Automatic IBRS aren't + * otherwise enabled. * * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because * the user might select retpoline on the kernel command line and if @@ -2502,74 +2650,74 @@ static const char * const l1tf_vmx_states[] = { static ssize_t l1tf_show_state(char *buf) { if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) - return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED || (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER && sched_smt_active())) { - return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, - l1tf_vmx_states[l1tf_vmx_mitigation]); + return sysfs_emit(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation]); } - return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, - l1tf_vmx_states[l1tf_vmx_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t itlb_multihit_show_state(char *buf) { if (!boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || !boot_cpu_has(X86_FEATURE_VMX)) - return sprintf(buf, "KVM: Mitigation: VMX unsupported\n"); + return sysfs_emit(buf, "KVM: Mitigation: VMX unsupported\n"); else if (!(cr4_read_shadow() & X86_CR4_VMXE)) - return sprintf(buf, "KVM: Mitigation: VMX disabled\n"); + return sysfs_emit(buf, "KVM: Mitigation: VMX disabled\n"); else if (itlb_multihit_kvm_mitigation) - return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + return sysfs_emit(buf, "KVM: Mitigation: Split huge pages\n"); else - return sprintf(buf, "KVM: Vulnerable\n"); + return sysfs_emit(buf, "KVM: Vulnerable\n"); } #else static ssize_t l1tf_show_state(char *buf) { - return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); } static ssize_t itlb_multihit_show_state(char *buf) { - return sprintf(buf, "Processor vulnerable\n"); + return sysfs_emit(buf, "Processor vulnerable\n"); } #endif static ssize_t mds_show_state(char *buf) { if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - return sprintf(buf, "%s; SMT Host state unknown\n", - mds_strings[mds_mitigation]); + return sysfs_emit(buf, "%s; SMT Host state unknown\n", + mds_strings[mds_mitigation]); } if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) { - return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], - (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : - sched_smt_active() ? "mitigated" : "disabled")); + return sysfs_emit(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : + sched_smt_active() ? "mitigated" : "disabled")); } - return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t tsx_async_abort_show_state(char *buf) { if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || (taa_mitigation == TAA_MITIGATION_OFF)) - return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + return sysfs_emit(buf, "%s\n", taa_strings[taa_mitigation]); if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - return sprintf(buf, "%s; SMT Host state unknown\n", - taa_strings[taa_mitigation]); + return sysfs_emit(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); } - return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t mmio_stale_data_show_state(char *buf) @@ -2589,22 +2737,28 @@ static ssize_t mmio_stale_data_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t rfds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); +} + static char *stibp_state(void) { - if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS)) return ""; switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: - return ", STIBP: disabled"; + return "; STIBP: disabled"; case SPECTRE_V2_USER_STRICT: - return ", STIBP: forced"; + return "; STIBP: forced"; case SPECTRE_V2_USER_STRICT_PREFERRED: - return ", STIBP: always-on"; + return "; STIBP: always-on"; case SPECTRE_V2_USER_PRCTL: case SPECTRE_V2_USER_SECCOMP: if (static_key_enabled(&switch_to_cond_stibp)) - return ", STIBP: conditional"; + return "; STIBP: conditional"; } return ""; } @@ -2613,10 +2767,10 @@ static char *ibpb_state(void) { if (boot_cpu_has(X86_FEATURE_IBPB)) { if (static_key_enabled(&switch_mm_always_ibpb)) - return ", IBPB: always-on"; + return "; IBPB: always-on"; if (static_key_enabled(&switch_mm_cond_ibpb)) - return ", IBPB: conditional"; - return ", IBPB: disabled"; + return "; IBPB: conditional"; + return "; IBPB: disabled"; } return ""; } @@ -2626,58 +2780,76 @@ static char *pbrsb_eibrs_state(void) if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) || boot_cpu_has(X86_FEATURE_RSB_VMEXIT)) - return ", PBRSB-eIBRS: SW sequence"; + return "; PBRSB-eIBRS: SW sequence"; else - return ", PBRSB-eIBRS: Vulnerable"; + return "; PBRSB-eIBRS: Vulnerable"; } else { - return ", PBRSB-eIBRS: Not affected"; + return "; PBRSB-eIBRS: Not affected"; } } +static const char * const spectre_bhi_state(void) +{ + if (!boot_cpu_has_bug(X86_BUG_BHI)) + return "; BHI: Not affected"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW)) + return "; BHI: BHI_DIS_S"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP)) + return "; BHI: SW loop, KVM: SW loop"; + else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA)) + return "; BHI: Retpoline"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT)) + return "; BHI: Syscall hardening, KVM: SW loop"; + + return "; BHI: Vulnerable (Syscall hardening enabled)"; +} + static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) - return sprintf(buf, "Vulnerable: LFENCE\n"); + return sysfs_emit(buf, "Vulnerable: LFENCE\n"); if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) - return sprintf(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); + return sysfs_emit(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); if (sched_smt_active() && unprivileged_ebpf_enabled() && spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) - return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); + return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sprintf(buf, "%s%s%s%s%s%s%s\n", - spectre_v2_strings[spectre_v2_enabled], - ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", - pbrsb_eibrs_state(), - spectre_v2_module_string()); + return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n", + spectre_v2_strings[spectre_v2_enabled], + ibpb_state(), + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "", + stibp_state(), + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "", + pbrsb_eibrs_state(), + spectre_bhi_state(), + /* this should always be at the end */ + spectre_v2_module_string()); } static ssize_t srbds_show_state(char *buf) { - return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); + return sysfs_emit(buf, "%s\n", srbds_strings[srbds_mitigation]); } static ssize_t retbleed_show_state(char *buf) { if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET || retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && - boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) - return sprintf(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return sysfs_emit(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); - return sprintf(buf, "%s; SMT %s\n", - retbleed_strings[retbleed_mitigation], - !sched_smt_active() ? "disabled" : - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? - "enabled with STIBP protection" : "vulnerable"); + return sysfs_emit(buf, "%s; SMT %s\n", retbleed_strings[retbleed_mitigation], + !sched_smt_active() ? "disabled" : + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? + "enabled with STIBP protection" : "vulnerable"); } - return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]); + return sysfs_emit(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } static ssize_t gds_show_state(char *buf) @@ -2699,26 +2871,26 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr char *buf, unsigned int bug) { if (!boot_cpu_has_bug(bug)) - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); switch (bug) { case X86_BUG_CPU_MELTDOWN: if (boot_cpu_has(X86_FEATURE_PTI)) - return sprintf(buf, "Mitigation: PTI\n"); + return sysfs_emit(buf, "Mitigation: PTI\n"); if (hypervisor_is_type(X86_HYPER_XEN_PV)) - return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); + return sysfs_emit(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); break; case X86_BUG_SPECTRE_V1: - return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); + return sysfs_emit(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: return spectre_v2_show_state(buf); case X86_BUG_SPEC_STORE_BYPASS: - return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + return sysfs_emit(buf, "%s\n", ssb_strings[ssb_mode]); case X86_BUG_L1TF: if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) @@ -2750,11 +2922,14 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_SRSO: return srso_show_state(buf); + case X86_BUG_RFDS: + return rfds_show_state(buf); + default: break; } - return sprintf(buf, "Vulnerable\n"); + return sysfs_emit(buf, "Vulnerable\n"); } ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) @@ -2824,4 +2999,9 @@ ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribut { return cpu_show_common(dev, attr, buf, X86_BUG_SRSO); } + +ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 01c4f8f45b83..664562389665 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1036,6 +1036,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SPECTRE_V2 BIT(8) #define NO_MMIO BIT(9) #define NO_EIBRS_PBRSB BIT(10) +#define NO_BHI BIT(11) #define VULNWL(vendor, family, model, whitelist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1096,18 +1097,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), /* Zhaoxin Family 7 */ - VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), - VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), {} }; @@ -1138,6 +1139,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define SRSO BIT(5) /* CPU is affected by GDS */ #define GDS BIT(6) +/* CPU is affected by Register File Data Sampling */ +#define RFDS BIT(7) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1165,9 +1168,18 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_N, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), @@ -1201,6 +1213,24 @@ static bool arch_cap_mmio_immune(u64 ia32_cap) ia32_cap & ARCH_CAP_SBDR_SSDP_NO); } +static bool __init vulnerable_to_rfds(u64 ia32_cap) +{ + /* The "immunity" bit trumps everything else: */ + if (ia32_cap & ARCH_CAP_RFDS_NO) + return false; + + /* + * VMMs set ARCH_CAP_RFDS_CLEAR for processors not in the blacklist to + * indicate that mitigation is needed because guest is running on a + * vulnerable hardware or may migrate to such hardware: + */ + if (ia32_cap & ARCH_CAP_RFDS_CLEAR) + return true; + + /* Only consult the blacklist when there is no enumeration: */ + return cpu_matches(cpu_vuln_blacklist, RFDS); +} + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = x86_read_arch_cap_msr(); @@ -1223,8 +1253,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); - if (ia32_cap & ARCH_CAP_IBRS_ALL) + /* + * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature + * flag and protect from vendor-specific bugs via the whitelist. + */ + if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); + if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && + !(ia32_cap & ARCH_CAP_PBRSB_NO)) + setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); + } if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) { @@ -1286,11 +1324,6 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_RETBLEED); } - if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) && - !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && - !(ia32_cap & ARCH_CAP_PBRSB_NO)) - setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); - if (cpu_matches(cpu_vuln_blacklist, SMT_RSB)) setup_force_cpu_bug(X86_BUG_SMT_RSB); @@ -1309,6 +1342,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SRSO); } + if (vulnerable_to_rfds(ia32_cap)) + setup_force_cpu_bug(X86_BUG_RFDS); + + /* When virtualized, eIBRS could be hidden, assume vulnerable */ + if (!(ia32_cap & ARCH_CAP_BHI_NO) && + !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || + boot_cpu_has(X86_FEATURE_HYPERVISOR))) + setup_force_cpu_bug(X86_BUG_BHI); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index eb48729e220e..30d822c2e5c0 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2382,12 +2382,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return -EINVAL; b = &per_cpu(mce_banks_array, s->id)[bank]; - if (!b->init) return -ENODEV; b->ctl = new; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); return size; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 06bfef1c4175..0f5211087810 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, + { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 }, { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 052ea7425c4d..893f040b97b7 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -463,50 +463,26 @@ static void kprobe_emulate_call(struct kprobe *p, struct pt_regs *regs) } NOKPROBE_SYMBOL(kprobe_emulate_call); -static nokprobe_inline -void __kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs, bool cond) +static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs) { unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size; - if (cond) - ip += p->ainsn.rel32; + ip += p->ainsn.rel32; int3_emulate_jmp(regs, ip); } - -static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs) -{ - __kprobe_emulate_jmp(p, regs, true); -} NOKPROBE_SYMBOL(kprobe_emulate_jmp); -static const unsigned long jcc_mask[6] = { - [0] = X86_EFLAGS_OF, - [1] = X86_EFLAGS_CF, - [2] = X86_EFLAGS_ZF, - [3] = X86_EFLAGS_CF | X86_EFLAGS_ZF, - [4] = X86_EFLAGS_SF, - [5] = X86_EFLAGS_PF, -}; - static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs) { - bool invert = p->ainsn.jcc.type & 1; - bool match; + unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size; - if (p->ainsn.jcc.type < 0xc) { - match = regs->flags & jcc_mask[p->ainsn.jcc.type >> 1]; - } else { - match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ - ((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); - if (p->ainsn.jcc.type >= 0xe) - match = match || (regs->flags & X86_EFLAGS_ZF); - } - __kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert)); + int3_emulate_jcc(regs, p->ainsn.jcc.type, ip, p->ainsn.rel32); } NOKPROBE_SYMBOL(kprobe_emulate_jcc); static void kprobe_emulate_loop(struct kprobe *p, struct pt_regs *regs) { + unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size; bool match; if (p->ainsn.loop.type != 3) { /* LOOP* */ @@ -534,7 +510,9 @@ static void kprobe_emulate_loop(struct kprobe *p, struct pt_regs *regs) else if (p->ainsn.loop.type == 1) /* LOOPE */ match = match && (regs->flags & X86_EFLAGS_ZF); - __kprobe_emulate_jmp(p, regs, match); + if (match) + ip += p->ainsn.rel32; + int3_emulate_jmp(regs, ip); } NOKPROBE_SYMBOL(kprobe_emulate_loop); diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 4bce802d25fb..b892fe7035db 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -519,9 +519,6 @@ nmi_restart: write_cr2(this_cpu_read(nmi_cr2)); if (this_cpu_dec_return(nmi_state)) goto nmi_restart; - - if (user_mode(regs)) - mds_user_clear_cpu_buffers(); } #if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index e25050c7ff1e..0e0221271e72 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -9,6 +9,7 @@ enum insn_type { NOP = 1, /* site cond-call */ JMP = 2, /* tramp / site tail-call */ RET = 3, /* tramp / site cond-tail-call */ + JCC = 4, }; /* @@ -25,12 +26,40 @@ static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; +static u8 __is_Jcc(u8 *insn) /* Jcc.d32 */ +{ + u8 ret = 0; + + if (insn[0] == 0x0f) { + u8 tmp = insn[1]; + if ((tmp & 0xf0) == 0x80) + ret = tmp; + } + + return ret; +} + +extern void __static_call_return(void); + +asm (".global __static_call_return\n\t" + ".type __static_call_return, @function\n\t" + ASM_FUNC_ALIGN "\n\t" + "__static_call_return:\n\t" + ANNOTATE_NOENDBR + ANNOTATE_RETPOLINE_SAFE + "ret; int3\n\t" + ".size __static_call_return, . - __static_call_return \n\t"); + static void __ref __static_call_transform(void *insn, enum insn_type type, void *func, bool modinit) { const void *emulate = NULL; int size = CALL_INSN_SIZE; const void *code; + u8 op, buf[6]; + + if ((type == JMP || type == RET) && (op = __is_Jcc(insn))) + type = JCC; switch (type) { case CALL: @@ -56,6 +85,20 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, else code = &retinsn; break; + + case JCC: + if (!func) { + func = __static_call_return; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + func = x86_return_thunk; + } + + buf[0] = 0x0f; + __text_gen_insn(buf+1, op, insn+1, func, 5); + code = buf; + size = 6; + + break; } if (memcmp(insn, code, size) == 0) @@ -67,13 +110,14 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, text_poke_bp(insn, code, size, emulate); } -static void __static_call_validate(void *insn, bool tail) +static void __static_call_validate(u8 *insn, bool tail) { - u8 opcode = *(u8 *)insn; + u8 opcode = insn[0]; if (tail) { if (opcode == JMP32_INSN_OPCODE || - opcode == RET_INSN_OPCODE) + opcode == RET_INSN_OPCODE || + __is_Jcc(insn)) return; } else { if (opcode == CALL_INSN_OPCODE || diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b939b94d931f..537e826205ce 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -355,9 +355,9 @@ static __always_inline void __kvm_cpu_cap_mask(unsigned int leaf) } static __always_inline -void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask) +void kvm_cpu_cap_init_kvm_defined(enum kvm_only_cpuid_leafs leaf, u32 mask) { - /* Use kvm_cpu_cap_mask for non-scattered leafs. */ + /* Use kvm_cpu_cap_mask for leafs that aren't KVM-only. */ BUILD_BUG_ON(leaf < NCAPINTS); kvm_cpu_caps[leaf] = mask; @@ -367,7 +367,7 @@ void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask) static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) { - /* Use kvm_cpu_cap_init_scattered for scattered leafs. */ + /* Use kvm_cpu_cap_init_kvm_defined for KVM-only leafs. */ BUILD_BUG_ON(leaf >= NCAPINTS); kvm_cpu_caps[leaf] &= mask; @@ -469,11 +469,16 @@ void kvm_set_cpu_caps(void) F(AVX_VNNI) | F(AVX512_BF16) ); + kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, + F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) | + F(BHI_CTRL) | F(MCDT_NO) + ); + kvm_cpu_cap_mask(CPUID_D_1_EAX, F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) ); - kvm_cpu_cap_init_scattered(CPUID_12_EAX, + kvm_cpu_cap_init_kvm_defined(CPUID_12_EAX, SF(SGX1) | SF(SGX2) ); @@ -710,13 +715,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; /* function 7 has additional index. */ case 7: - entry->eax = min(entry->eax, 1u); + max_idx = entry->eax = min(entry->eax, 2u); cpuid_entry_override(entry, CPUID_7_0_EBX); cpuid_entry_override(entry, CPUID_7_ECX); cpuid_entry_override(entry, CPUID_7_EDX); - /* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */ - if (entry->eax == 1) { + /* KVM only supports up to 0x7.2, capped above via min(). */ + if (max_idx >= 1) { entry = do_host_cpuid(array, function, 1); if (!entry) goto out; @@ -726,6 +731,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ecx = 0; entry->edx = 0; } + if (max_idx >= 2) { + entry = do_host_cpuid(array, function, 2); + if (!entry) + goto out; + + cpuid_entry_override(entry, CPUID_7_2_EDX); + entry->ecx = 0; + entry->ebx = 0; + entry->eax = 0; + } break; case 0xa: { /* Architectural Performance Monitoring */ struct x86_pmu_capability cap; diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 7eeade35a425..e43909d6504a 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -7,23 +7,44 @@ #include <asm/cpufeatures.h> /* - * Hardware-defined CPUID leafs that are scattered in the kernel, but need to - * be directly used by KVM. Note, these word values conflict with the kernel's - * "bug" caps, but KVM doesn't use those. + * Hardware-defined CPUID leafs that are either scattered by the kernel or are + * unknown to the kernel, but need to be directly used by KVM. Note, these + * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. */ enum kvm_only_cpuid_leafs { CPUID_12_EAX = NCAPINTS, + CPUID_7_2_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, }; +/* + * Define a KVM-only feature flag. + * + * For features that are scattered by cpufeatures.h, __feature_translate() also + * needs to be updated to translate the kernel-defined feature into the + * KVM-defined feature. + * + * For features that are 100% KVM-only, i.e. not defined by cpufeatures.h, + * forego the intermediate KVM_X86_FEATURE and directly define X86_FEATURE_* so + * that X86_FEATURE_* can be used in KVM. No __feature_translate() handling is + * needed in this case. + */ #define KVM_X86_FEATURE(w, f) ((w)*32 + (f)) /* Intel-defined SGX sub-features, CPUID level 0x12 (EAX). */ #define KVM_X86_FEATURE_SGX1 KVM_X86_FEATURE(CPUID_12_EAX, 0) #define KVM_X86_FEATURE_SGX2 KVM_X86_FEATURE(CPUID_12_EAX, 1) +/* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */ +#define X86_FEATURE_INTEL_PSFD KVM_X86_FEATURE(CPUID_7_2_EDX, 0) +#define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1) +#define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2) +#define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3) +#define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) +#define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) + struct cpuid_reg { u32 function; u32 index; @@ -49,6 +70,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX}, [CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX}, [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, + [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, }; /* @@ -61,10 +83,12 @@ static const struct cpuid_reg reverse_cpuid[] = { */ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) { + BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS); BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_5); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); } @@ -75,12 +99,17 @@ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) */ static __always_inline u32 __feature_translate(int x86_feature) { - if (x86_feature == X86_FEATURE_SGX1) - return KVM_X86_FEATURE_SGX1; - else if (x86_feature == X86_FEATURE_SGX2) - return KVM_X86_FEATURE_SGX2; - - return x86_feature; +#define KVM_X86_TRANSLATE_FEATURE(f) \ + case X86_FEATURE_##f: return KVM_X86_FEATURE_##f + + switch (x86_feature) { + KVM_X86_TRANSLATE_FEATURE(SGX1); + KVM_X86_TRANSLATE_FEATURE(SGX2); + KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); + KVM_X86_TRANSLATE_FEATURE(BHI_CTRL); + default: + return x86_feature; + } } static __always_inline u32 __feature_leaf(int x86_feature) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 93d73b55ae3e..0f3d29f83c58 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1662,20 +1662,22 @@ int svm_register_enc_region(struct kvm *kvm, goto e_free; } - region->uaddr = range->addr; - region->size = range->size; - - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are * flushed to ensure that guest data gets written into memory with - * correct C-bit. + * correct C-bit. Note, this must be done before dropping kvm->lock, + * as region and its array of pages can be freed by a different task + * once kvm->lock is released. */ sev_clflush_pages(region->pages, region->npages); + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + return ret; e_free: diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index edc3f16cc189..6a9bfdfbb6e5 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -2,7 +2,10 @@ #ifndef __KVM_X86_VMX_RUN_FLAGS_H #define __KVM_X86_VMX_RUN_FLAGS_H -#define VMX_RUN_VMRESUME (1 << 0) -#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) +#define VMX_RUN_VMRESUME_SHIFT 0 +#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 + +#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) +#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT) #endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 982138bebb70..ef61bd6d071f 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -77,7 +77,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - testb $VMX_RUN_VMRESUME, %bl + bt $VMX_RUN_VMRESUME_SHIFT, %bx /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -99,8 +99,11 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Check EFLAGS.ZF from 'testb' above */ - jz .Lvmlaunch + /* Clobbers EFLAGS.ZF */ + CLEAR_CPU_BUFFERS + + /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */ + jnc .Lvmlaunch /* * After a successful VMRESUME/VMLAUNCH, control flow "magically" @@ -210,6 +213,8 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) call vmx_spec_ctrl_restore_host + CLEAR_BRANCH_HISTORY_VMEXIT + /* Put return value in AX */ mov %_ASM_BX, %_ASM_AX diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 89744ee06101..bedbd077e50e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -398,7 +398,8 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && + vmx_fb_clear_ctrl_available; /* * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS @@ -6747,11 +6748,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, { kvm_guest_enter_irqoff(); - /* L1D Flush includes CPU buffer clear to mitigate MDS */ + /* + * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW + * mitigation for MDS is done late in VMentry and is still + * executed in spite of L1D Flush. This is because an extra VERW + * should not matter much after the big hammer L1D Flush. + */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) - mds_clear_cpu_buffers(); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers(); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0ece8f83d320..cb6d61b9e005 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1498,7 +1498,8 @@ static unsigned int num_msr_based_features; ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1535,6 +1536,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_SSB_NO; if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + data |= ARCH_CAP_RFDS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* @@ -7105,7 +7108,17 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, } if (r < 0) - goto emul_write; + return X86EMUL_UNHANDLEABLE; + + /* + * Mark the page dirty _before_ checking whether or not the CMPXCHG was + * successful, as the old value is written back on failure. Note, for + * live migration, this is unnecessarily conservative as CMPXCHG writes + * back the original value and the access is atomic, but KVM's ABI is + * that all writes are dirty logged, regardless of the value written. + */ + kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa)); + if (r) return X86EMUL_CMPXCHG_FAILED; diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 6f5321b36dbb..019096b66eff 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -108,6 +108,7 @@ SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ret int3 SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) #endif SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) @@ -249,9 +250,7 @@ SYM_CODE_START(srso_return_thunk) SYM_CODE_END(srso_return_thunk) SYM_FUNC_START(entry_untrain_ret) - ALTERNATIVE_2 "jmp retbleed_untrain_ret", \ - "jmp srso_untrain_ret", X86_FEATURE_SRSO, \ - "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS + ALTERNATIVE "jmp retbleed_untrain_ret", "jmp srso_untrain_ret", X86_FEATURE_SRSO SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index f50cc210a981..968d7005f4a7 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -26,31 +26,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, for (; addr < end; addr = next) { pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; - bool use_gbpage; next = (addr & PUD_MASK) + PUD_SIZE; if (next > end) next = end; - /* if this is already a gbpage, this portion is already mapped */ - if (pud_large(*pud)) - continue; - - /* Is using a gbpage allowed? */ - use_gbpage = info->direct_gbpages; - - /* Don't use gbpage if it maps more than the requested region. */ - /* at the begining: */ - use_gbpage &= ((addr & ~PUD_MASK) == 0); - /* ... or at the end: */ - use_gbpage &= ((next & ~PUD_MASK) == 0); - - /* Never overwrite existing mappings */ - use_gbpage &= !pud_present(*pud); - - if (use_gbpage) { + if (info->direct_gbpages) { pud_t pudval; + if (pud_present(*pud)) + continue; + + addr &= PUD_MASK; pudval = __pud((addr - info->offset) | info->page_flag); set_pud(pud, pudval); continue; diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index d5ef64ddd35e..f6466022954b 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -989,6 +989,38 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, + pgprot_t *pgprot) +{ + unsigned long prot; + + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT)); + + /* + * We need the starting PFN and cachemode used for track_pfn_remap() + * that covered the whole VMA. For most mappings, we can obtain that + * information from the page tables. For COW mappings, we might now + * suddenly have anon folios mapped and follow_phys() will fail. + * + * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to + * detect the PFN. If we need the cachemode as well, we're out of luck + * for now and have to fail fork(). + */ + if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (pgprot) + *pgprot = __pgprot(prot); + return 0; + } + if (is_cow_mapping(vma->vm_flags)) { + if (pgprot) + return -EINVAL; + *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; + return 0; + } + WARN_ON_ONCE(1); + return -EINVAL; +} + /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). @@ -999,20 +1031,13 @@ static void free_pfn_range(u64 paddr, unsigned long size) int track_pfn_copy(struct vm_area_struct *vma) { resource_size_t paddr; - unsigned long prot; unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (vma->vm_flags & VM_PAT) { - /* - * reserve the whole chunk covered by vma. We need the - * starting address and protection from pte. - */ - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, &pgprot)) return -EINVAL; - } - pgprot = __pgprot(prot); + /* reserve the whole chunk covered by vma. */ return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } @@ -1087,7 +1112,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size) { resource_size_t paddr; - unsigned long prot; if (vma && !(vma->vm_flags & VM_PAT)) return; @@ -1095,11 +1119,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, /* free the chunk starting from pfn or the whole chunk */ paddr = (resource_size_t)pfn << PAGE_SHIFT; if (!paddr && !size) { - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, NULL)) return; - } - size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); diff --git a/block/blk-settings.c b/block/blk-settings.c index 959b5c1e6d3b..1b92e6624951 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -647,6 +647,10 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->zone_write_granularity = max(t->zone_write_granularity, b->zone_write_granularity); t->zoned = max(t->zoned, b->zoned); + if (!t->zoned) { + t->zone_write_granularity = 0; + t->max_zone_append_sectors = 0; + } return ret; } EXPORT_SYMBOL(blk_stack_limits); diff --git a/block/blk-stat.c b/block/blk-stat.c index ae3dd1fb8e61..6e602f9b966e 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -28,7 +28,7 @@ void blk_rq_stat_init(struct blk_rq_stat *stat) /* src is a per-cpu stat, mean isn't initialized */ void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src) { - if (!src->nr_samples) + if (dst->nr_samples + src->nr_samples <= dst->nr_samples) return; dst->min = min(dst->min, src->min); diff --git a/crypto/algboss.c b/crypto/algboss.c index 1814d2c5188a..eb5fe84efb83 100644 --- a/crypto/algboss.c +++ b/crypto/algboss.c @@ -67,7 +67,7 @@ out: complete_all(¶m->larval->completion); crypto_alg_put(¶m->larval->alg); kfree(param); - module_put_and_exit(0); + module_put_and_kthread_exit(0); } static int cryptomgr_schedule_probe(struct crypto_larval *larval) @@ -190,7 +190,7 @@ skiptest: crypto_alg_tested(param->driver, err); kfree(param); - module_put_and_exit(0); + module_put_and_kthread_exit(0); } static int cryptomgr_schedule_test(struct crypto_alg *alg) diff --git a/drivers/accessibility/speakup/synth.c b/drivers/accessibility/speakup/synth.c index 2b8699673bac..1e10f3c9567b 100644 --- a/drivers/accessibility/speakup/synth.c +++ b/drivers/accessibility/speakup/synth.c @@ -208,8 +208,10 @@ void spk_do_flush(void) wake_up_process(speakup_task); } -void synth_write(const char *buf, size_t count) +void synth_write(const char *_buf, size_t count) { + const unsigned char *buf = (const unsigned char *) _buf; + while (count--) synth_buffer_add(*buf++); synth_start(); diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c index b91155ea9c34..c9131259f717 100644 --- a/drivers/acpi/acpica/dbnames.c +++ b/drivers/acpi/acpica/dbnames.c @@ -550,8 +550,12 @@ acpi_db_walk_for_fields(acpi_handle obj_handle, ACPI_FREE(buffer.pointer); buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER; - acpi_evaluate_object(obj_handle, NULL, NULL, &buffer); - + status = acpi_evaluate_object(obj_handle, NULL, NULL, &buffer); + if (ACPI_FAILURE(status)) { + acpi_os_printf("Could Not evaluate object %p\n", + obj_handle); + return (AE_OK); + } /* * Since this is a field unit, surround the output in braces */ diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index b277e25b276c..95deb55fb9a8 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -382,18 +382,6 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "20GGA00L00"), }, }, - /* - * ASUS B1400CEAE hangs on resume from suspend (see - * https://bugzilla.kernel.org/show_bug.cgi?id=215742). - */ - { - .callback = init_default_s3, - .ident = "ASUS B1400CEAE", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK B1400CEAE"), - }, - }, {}, }; diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index b0a8aac008ba..7807c7b9f37a 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -666,11 +666,6 @@ MODULE_PARM_DESC(mobile_lpm_policy, "Default LPM policy for mobile chipsets"); static void ahci_pci_save_initial_config(struct pci_dev *pdev, struct ahci_host_priv *hpriv) { - if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == 0x1166) { - dev_info(&pdev->dev, "ASM1166 has only six ports\n"); - hpriv->saved_port_map = 0x3f; - } - if (pdev->vendor == PCI_VENDOR_ID_JMICRON && pdev->device == 0x2361) { dev_info(&pdev->dev, "JMB361 has only one port\n"); hpriv->force_port_map = 1; diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index c53633d47bfb..1c9dde51d456 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -787,37 +787,6 @@ static const struct ata_port_info mv_port_info[] = { }, }; -static const struct pci_device_id mv_pci_tbl[] = { - { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, - { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, - /* RocketRAID 1720/174x have different identifiers */ - { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, - - { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, - { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, - { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, - - { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, - - /* Adaptec 1430SA */ - { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, - - /* Marvell 7042 support */ - { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, - - /* Highpoint RocketRAID PCIe series */ - { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, - { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, - - { } /* terminate list */ -}; - static const struct mv_hw_ops mv5xxx_ops = { .phy_errata = mv5_phy_errata, .enable_leds = mv5_enable_leds, @@ -4311,6 +4280,36 @@ static int mv_pci_init_one(struct pci_dev *pdev, static int mv_pci_device_resume(struct pci_dev *pdev); #endif +static const struct pci_device_id mv_pci_tbl[] = { + { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, + { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, + /* RocketRAID 1720/174x have different identifiers */ + { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, + + { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, + { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, + { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, + + { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, + + /* Adaptec 1430SA */ + { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, + + /* Marvell 7042 support */ + { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, + + /* Highpoint RocketRAID PCIe series */ + { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, + { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, + + { } /* terminate list */ +}; static struct pci_driver mv_pci_driver = { .name = DRV_NAME, @@ -4323,6 +4322,7 @@ static struct pci_driver mv_pci_driver = { #endif }; +MODULE_DEVICE_TABLE(pci, mv_pci_tbl); /** * mv_print_info - Dump key info to kernel log for perusal. @@ -4495,7 +4495,6 @@ static void __exit mv_exit(void) MODULE_AUTHOR("Brett Russ"); MODULE_DESCRIPTION("SCSI low-level driver for Marvell SATA controllers"); MODULE_LICENSE("GPL v2"); -MODULE_DEVICE_TABLE(pci, mv_pci_tbl); MODULE_VERSION(DRV_VERSION); MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index 4c01190a5e37..c95685f693a6 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -1004,8 +1004,7 @@ static void pdc20621_get_from_dimm(struct ata_host *host, void *psource, offset -= (idx * window_size); idx++; - dist = ((long) (window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_fromio(psource, dimm_mmio + offset / 4, dist); psource += dist; @@ -1053,8 +1052,7 @@ static void pdc20621_put_to_dimm(struct ata_host *host, void *psource, readl(mmio + PDC_DIMM_WINDOW_CTLR); offset -= (idx * window_size); idx++; - dist = ((long)(s32)(window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_toio(dimm_mmio + offset / 4, psource, dist); writel(0x01, mmio + PDC_GENERAL_CTLR); readl(mmio + PDC_GENERAL_CTLR); diff --git a/drivers/base/core.c b/drivers/base/core.c index adf003a7e8d6..ca56fd745021 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -53,6 +53,7 @@ static unsigned int defer_sync_state_count = 1; static DEFINE_MUTEX(fwnode_link_lock); static bool fw_devlink_is_permissive(void); static bool fw_devlink_drv_reg_done; +static struct workqueue_struct *device_link_wq; /** * fwnode_link_add - Create a link between two fwnode_handles. @@ -501,12 +502,26 @@ static void devlink_dev_release(struct device *dev) /* * It may take a while to complete this work because of the SRCU * synchronization in device_link_release_fn() and if the consumer or - * supplier devices get deleted when it runs, so put it into the "long" - * workqueue. + * supplier devices get deleted when it runs, so put it into the + * dedicated workqueue. */ - queue_work(system_long_wq, &link->rm_work); + queue_work(device_link_wq, &link->rm_work); } +/** + * device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate + */ +void device_link_wait_removal(void) +{ + /* + * devlink removal jobs are queued in the dedicated work queue. + * To be sure that all removal jobs are terminated, ensure that any + * scheduled work has run to completion. + */ + flush_workqueue(device_link_wq); +} +EXPORT_SYMBOL_GPL(device_link_wait_removal); + static struct class devlink_class = { .name = "devlink", .owner = THIS_MODULE, @@ -3825,9 +3840,14 @@ int __init devices_init(void) sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj); if (!sysfs_dev_char_kobj) goto char_kobj_err; + device_link_wq = alloc_workqueue("device_link_wq", 0, 0); + if (!device_link_wq) + goto wq_err; return 0; + wq_err: + kobject_put(sysfs_dev_char_kobj); char_kobj_err: kobject_put(sysfs_dev_block_kobj); block_kobj_err: diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 46430cf2401e..93222cf39157 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -589,6 +589,12 @@ ssize_t __weak cpu_show_spec_rstack_overflow(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_reg_file_data_sampling(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(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); @@ -602,6 +608,7 @@ static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); +static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -617,6 +624,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_retbleed.attr, &dev_attr_gather_data_sampling.attr, &dev_attr_spec_rstack_overflow.attr, + &dev_attr_reg_file_data_sampling.attr, NULL }; diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index 6f2cdd8643af..ab6eced7f576 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -362,8 +362,10 @@ void dev_pm_enable_wake_irq_complete(struct device *dev) return; if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED && - wirq->status & WAKE_IRQ_DEDICATED_REVERSE) + wirq->status & WAKE_IRQ_DEDICATED_REVERSE) { enable_irq(wirq->irq); + wirq->status |= WAKE_IRQ_DEDICATED_ENABLED; + } } /** diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 2a4cc5d8c2d4..0635df202dfa 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -411,7 +411,7 @@ int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver) return PTR_ERR(skb); } - if (skb->len != sizeof(*ver)) { + if (!skb || skb->len != sizeof(*ver)) { bt_dev_err(hdev, "Intel version event size mismatch"); kfree_skb(skb); return -EILSEQ; diff --git a/drivers/clk/qcom/gcc-ipq6018.c b/drivers/clk/qcom/gcc-ipq6018.c index 4c5c7a8f41d0..b9844e41cf99 100644 --- a/drivers/clk/qcom/gcc-ipq6018.c +++ b/drivers/clk/qcom/gcc-ipq6018.c @@ -1557,6 +1557,7 @@ static struct clk_regmap_div nss_ubi0_div_clk_src = { static const struct freq_tbl ftbl_pcie_aux_clk_src[] = { F(24000000, P_XO, 1, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_core_pi_sleep_clk[] = { @@ -1737,6 +1738,7 @@ static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(160000000, P_GPLL0, 5, 0, 0), F(216000000, P_GPLL6, 5, 0, 0), F(308570000, P_GPLL6, 3.5, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_gpll6_gpll0_div2[] = { diff --git a/drivers/clk/qcom/gcc-ipq8074.c b/drivers/clk/qcom/gcc-ipq8074.c index 0393154fea2f..649e75a41f7a 100644 --- a/drivers/clk/qcom/gcc-ipq8074.c +++ b/drivers/clk/qcom/gcc-ipq8074.c @@ -972,6 +972,7 @@ static struct clk_rcg2 pcie0_axi_clk_src = { static const struct freq_tbl ftbl_pcie_aux_clk_src[] = { F(19200000, P_XO, 1, 0, 0), + { } }; static struct clk_rcg2 pcie0_aux_clk_src = { @@ -1077,6 +1078,7 @@ static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(19200000, P_XO, 1, 0, 0), F(160000000, P_GPLL0, 5, 0, 0), F(308570000, P_GPLL6, 3.5, 0, 0), + { } }; static struct clk_rcg2 sdcc1_ice_core_clk_src = { diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c index 58aa3ec9a7fc..fffdb480073e 100644 --- a/drivers/clk/qcom/gcc-sdm845.c +++ b/drivers/clk/qcom/gcc-sdm845.c @@ -3642,3 +3642,4 @@ module_exit(gcc_sdm845_exit); MODULE_DESCRIPTION("QTI GCC SDM845 Driver"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("platform:gcc-sdm845"); +MODULE_SOFTDEP("pre: rpmhpd"); diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c index fbfcf0006739..c2fd0e8f4bc0 100644 --- a/drivers/clk/qcom/mmcc-apq8084.c +++ b/drivers/clk/qcom/mmcc-apq8084.c @@ -333,6 +333,7 @@ static struct freq_tbl ftbl_mmss_axi_clk[] = { F(333430000, P_MMPLL1, 3.5, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), F(466800000, P_MMPLL1, 2.5, 0, 0), + { } }; static struct clk_rcg2 mmss_axi_clk_src = { @@ -357,6 +358,7 @@ static struct freq_tbl ftbl_ocmemnoc_clk[] = { F(150000000, P_GPLL0, 4, 0, 0), F(228570000, P_MMPLL0, 3.5, 0, 0), F(320000000, P_MMPLL0, 2.5, 0, 0), + { } }; static struct clk_rcg2 ocmemnoc_clk_src = { diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c index a1552b6771bc..26509bcd4f80 100644 --- a/drivers/clk/qcom/mmcc-msm8974.c +++ b/drivers/clk/qcom/mmcc-msm8974.c @@ -267,6 +267,7 @@ static struct freq_tbl ftbl_mmss_axi_clk[] = { F(291750000, P_MMPLL1, 4, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), F(466800000, P_MMPLL1, 2.5, 0, 0), + { } }; static struct clk_rcg2 mmss_axi_clk_src = { @@ -291,6 +292,7 @@ static struct freq_tbl ftbl_ocmemnoc_clk[] = { F(150000000, P_GPLL0, 4, 0, 0), F(291750000, P_MMPLL1, 4, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), + { } }; static struct clk_rcg2 ocmemnoc_clk_src = { diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c index 44a61dc6f932..e1c773bb5535 100644 --- a/drivers/clocksource/arm_global_timer.c +++ b/drivers/clocksource/arm_global_timer.c @@ -32,7 +32,7 @@ #define GT_CONTROL_IRQ_ENABLE BIT(2) /* banked */ #define GT_CONTROL_AUTO_INC BIT(3) /* banked */ #define GT_CONTROL_PRESCALER_SHIFT 8 -#define GT_CONTROL_PRESCALER_MAX 0xF +#define GT_CONTROL_PRESCALER_MAX 0xFF #define GT_CONTROL_PRESCALER_MASK (GT_CONTROL_PRESCALER_MAX << \ GT_CONTROL_PRESCALER_SHIFT) diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 38ec0fedb247..552db816ed22 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -481,10 +481,11 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv) static unsigned int brcm_avs_cpufreq_get(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + struct private_data *priv; + if (!policy) return 0; - struct private_data *priv = policy->driver_data; - + priv = policy->driver_data; cpufreq_cpu_put(policy); return brcm_avs_get_frequency(priv->base); diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 8fcaba541539..1bfdfa7e25c1 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -208,7 +208,7 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu) if (!priv) return -ENOMEM; - if (!alloc_cpumask_var(&priv->cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&priv->cpus, GFP_KERNEL)) return -ENOMEM; cpumask_set_cpu(cpu, priv->cpus); diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index f70aa17e2a8e..c594e28adddf 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -16,6 +16,7 @@ #include <linux/cpumask.h> #include <linux/tick.h> #include <linux/cpu.h> +#include <linux/math64.h> #include "cpuidle.h" @@ -185,7 +186,7 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv) s->target_residency_ns = 0; if (s->exit_latency > 0) - s->exit_latency_ns = s->exit_latency * NSEC_PER_USEC; + s->exit_latency_ns = mul_u32_u32(s->exit_latency, NSEC_PER_USEC); else if (s->exit_latency_ns < 0) s->exit_latency_ns = 0; } diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c index ed3e40bc56eb..040595a6ab75 100644 --- a/drivers/crypto/qat/qat_common/adf_aer.c +++ b/drivers/crypto/qat/qat_common/adf_aer.c @@ -95,18 +95,28 @@ static void adf_device_reset_worker(struct work_struct *work) if (adf_dev_init(accel_dev) || adf_dev_start(accel_dev)) { /* The device hanged and we can't restart it so stop here */ dev_err(&GET_DEV(accel_dev), "Restart device failed\n"); - kfree(reset_data); + if (reset_data->mode == ADF_DEV_RESET_ASYNC || + completion_done(&reset_data->compl)) + kfree(reset_data); WARN(1, "QAT: device restart failed. Device is unusable\n"); return; } adf_dev_restarted_notify(accel_dev); clear_bit(ADF_STATUS_RESTARTING, &accel_dev->status); - /* The dev is back alive. Notify the caller if in sync mode */ - if (reset_data->mode == ADF_DEV_RESET_SYNC) - complete(&reset_data->compl); - else + /* + * The dev is back alive. Notify the caller if in sync mode + * + * If device restart will take a more time than expected, + * the schedule_reset() function can timeout and exit. This can be + * detected by calling the completion_done() function. In this case + * the reset_data structure needs to be freed here. + */ + if (reset_data->mode == ADF_DEV_RESET_ASYNC || + completion_done(&reset_data->compl)) kfree(reset_data); + else + complete(&reset_data->compl); } static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, @@ -139,8 +149,9 @@ static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, dev_err(&GET_DEV(accel_dev), "Reset device timeout expired\n"); ret = -EFAULT; + } else { + kfree(reset_data); } - kfree(reset_data); return ret; } return 0; diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index cae590bd08f2..eaed1ddcc803 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -415,7 +415,7 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), void *data, bool duplicates, struct list_head *head) { const struct efivar_operations *ops; - unsigned long variable_name_size = 1024; + unsigned long variable_name_size = 512; efi_char16_t *variable_name; efi_status_t status; efi_guid_t vendor_guid; @@ -438,12 +438,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), } /* - * Per EFI spec, the maximum storage allocated for both - * the variable name and variable data is 1024 bytes. + * A small set of old UEFI implementations reject sizes + * above a certain threshold, the lowest seen in the wild + * is 512. */ do { - variable_name_size = 1024; + variable_name_size = 512; status = ops->get_next_variable(&variable_name_size, variable_name, @@ -491,9 +492,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), break; case EFI_NOT_FOUND: break; + case EFI_BUFFER_TOO_SMALL: + pr_warn("efivars: Variable name size exceeds maximum (%lu > 512)\n", + variable_name_size); + status = EFI_NOT_FOUND; + break; default: - printk(KERN_WARNING "efivars: get_next_variable: status=%lx\n", - status); + pr_warn("efivars: get_next_variable: status=%lx\n", status); status = EFI_NOT_FOUND; break; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index c777aff164b7..654f99f4107e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -625,7 +625,7 @@ amdgpu_connector_fixup_lcd_native_mode(struct drm_encoder *encoder, if (mode->type & DRM_MODE_TYPE_PREFERRED) { if (mode->hdisplay != native_mode->hdisplay || mode->vdisplay != native_mode->vdisplay) - memcpy(native_mode, mode, sizeof(*mode)); + drm_mode_copy(native_mode, mode); } } @@ -634,7 +634,7 @@ amdgpu_connector_fixup_lcd_native_mode(struct drm_encoder *encoder, list_for_each_entry_safe(mode, t, &connector->probed_modes, head) { if (mode->hdisplay == native_mode->hdisplay && mode->vdisplay == native_mode->vdisplay) { - *native_mode = *mode; + drm_mode_copy(native_mode, mode); drm_mode_set_crtcinfo(native_mode, CRTC_INTERLACE_HALVE_V); DRM_DEBUG_KMS("Determined LVDS native mode details from EDID\n"); break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index b06fb1fa411b..9a1b19e3d437 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -859,6 +859,7 @@ static int amdgpu_ttm_gart_bind(struct amdgpu_device *adev, r = amdgpu_gart_bind(adev, gtt->offset, ttm->num_pages, gtt->ttm.dma_address, flags); } + gtt->bound = true; gart_bind_fail: if (r) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 6688129df240..88f9e1aa51f8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -940,8 +940,8 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, * nodes, but not more than args->num_of_nodes as that is * the amount of memory allocated by user */ - pa = kzalloc((sizeof(struct kfd_process_device_apertures) * - args->num_of_nodes), GFP_KERNEL); + pa = kcalloc(args->num_of_nodes, sizeof(struct kfd_process_device_apertures), + GFP_KERNEL); if (!pa) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 7385efe699f8..b7b8a2d77da6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -6219,7 +6219,7 @@ get_highest_refresh_rate_mode(struct amdgpu_dm_connector *aconnector, } } - aconnector->freesync_vid_base = *m_pref; + drm_mode_copy(&aconnector->freesync_vid_base, m_pref); return m_pref; } @@ -6333,8 +6333,10 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, is_freesync_video_mode(&mode, aconnector); if (recalculate_timing) { freesync_mode = get_highest_refresh_rate_mode(aconnector, false); - saved_mode = mode; - mode = *freesync_mode; + drm_mode_copy(&saved_mode, &mode); + saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio; + drm_mode_copy(&mode, freesync_mode); + mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio; } else { decide_crtc_timing_for_drm_display_mode( &mode, preferred_mode, scale); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index f83457375811..8d8114ee67f6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -673,10 +673,20 @@ void dcn30_set_avmute(struct pipe_ctx *pipe_ctx, bool enable) if (pipe_ctx == NULL) return; - if (dc_is_hdmi_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL) + if (dc_is_hdmi_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL) { pipe_ctx->stream_res.stream_enc->funcs->set_avmute( pipe_ctx->stream_res.stream_enc, enable); + + /* Wait for two frame to make sure AV mute is sent out */ + if (enable) { + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + } + } } void dcn30_update_info_frame(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index be61975f1470..11939be2b46a 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -509,6 +509,9 @@ enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp) hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf; memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory)); + if (!display) + return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND; + hdcp_cmd->in_msg.hdcp2_create_session_v2.display_handle = display->index; if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_0) diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h index 4220fd8fdd60..54cd86060f4d 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h @@ -57,10 +57,10 @@ void mod_stats_update_event(struct mod_stats *mod_stats, unsigned int length); void mod_stats_update_flip(struct mod_stats *mod_stats, - unsigned long timestamp_in_ns); + unsigned long long timestamp_in_ns); void mod_stats_update_vupdate(struct mod_stats *mod_stats, - unsigned long timestamp_in_ns); + unsigned long long timestamp_in_ns); void mod_stats_update_freesync(struct mod_stats *mod_stats, unsigned int v_total_min, diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c index f634371c717a..7fd3de89ed07 100644 --- a/drivers/gpu/drm/drm_panel.c +++ b/drivers/gpu/drm/drm_panel.c @@ -207,19 +207,24 @@ EXPORT_SYMBOL(drm_panel_disable); * The modes probed from the panel are automatically added to the connector * that the panel is attached to. * - * Return: The number of modes available from the panel on success or a - * negative error code on failure. + * Return: The number of modes available from the panel on success, or 0 on + * failure (no modes). */ int drm_panel_get_modes(struct drm_panel *panel, struct drm_connector *connector) { if (!panel) - return -EINVAL; + return 0; - if (panel->funcs && panel->funcs->get_modes) - return panel->funcs->get_modes(panel, connector); + if (panel->funcs && panel->funcs->get_modes) { + int num; - return -EOPNOTSUPP; + num = panel->funcs->get_modes(panel, connector); + if (num > 0) + return num; + } + + return 0; } EXPORT_SYMBOL(drm_panel_get_modes); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 7dcc6392792d..c45e5158fdff 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -488,7 +488,7 @@ static const struct drm_driver etnaviv_drm_driver = { .desc = "etnaviv DRM", .date = "20151214", .major = 1, - .minor = 3, + .minor = 4, }; /* diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c index f2fc645c7956..212e7050c4ba 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c @@ -135,6 +135,9 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { bool etnaviv_fill_identity_from_hwdb(struct etnaviv_gpu *gpu) { struct etnaviv_chip_identity *ident = &gpu->identity; + const u32 product_id = ident->product_id; + const u32 customer_id = ident->customer_id; + const u32 eco_id = ident->eco_id; int i; for (i = 0; i < ARRAY_SIZE(etnaviv_chip_identities); i++) { @@ -148,6 +151,12 @@ bool etnaviv_fill_identity_from_hwdb(struct etnaviv_gpu *gpu) etnaviv_chip_identities[i].eco_id == ~0U)) { memcpy(ident, &etnaviv_chip_identities[i], sizeof(*ident)); + + /* Restore some id values as ~0U aka 'don't care' might been used. */ + ident->product_id = product_id; + ident->customer_id = customer_id; + ident->eco_id = eco_id; + return true; } } diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index e96436e11a36..e1ffe8a28b64 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -315,14 +315,14 @@ static int vidi_get_modes(struct drm_connector *connector) */ if (!ctx->raw_edid) { DRM_DEV_DEBUG_KMS(ctx->dev, "raw_edid is null.\n"); - return -EFAULT; + return 0; } edid_len = (1 + ctx->raw_edid->extensions) * EDID_LENGTH; edid = kmemdup(ctx->raw_edid, edid_len, GFP_KERNEL); if (!edid) { DRM_DEV_DEBUG_KMS(ctx->dev, "failed to allocate edid\n"); - return -ENOMEM; + return 0; } drm_connector_update_edid_property(connector, edid); diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 42b6b001405a..35be9f024518 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -887,11 +887,11 @@ static int hdmi_get_modes(struct drm_connector *connector) int ret; if (!hdata->ddc_adpt) - return -ENODEV; + return 0; edid = drm_get_edid(connector, hdata->ddc_adpt); if (!edid) - return -ENODEV; + return 0; hdata->dvi_mode = !drm_detect_hdmi_monitor(edid); DRM_DEV_DEBUG_KMS(hdata->dev, "%s : width[%d] x height[%d]\n", diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 8ea0fa665e53..1eb2395ea206 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -374,6 +374,9 @@ i915_gem_userptr_release(struct drm_i915_gem_object *obj) { GEM_WARN_ON(obj->userptr.page_ref); + if (!obj->userptr.notifier.mm) + return; + mmu_interval_notifier_remove(&obj->userptr.notifier); obj->userptr.notifier.mm = NULL; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index 73e96ca024df..7ddfc9744cdf 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -240,9 +240,6 @@ static int __engine_park(struct intel_wakeref *wf) intel_engine_park_heartbeat(engine); intel_breadcrumbs_park(engine->breadcrumbs); - /* Must be reset upon idling, or we may miss the busy wakeup. */ - GEM_BUG_ON(engine->sched_engine->queue_priority_hint != INT_MIN); - if (engine->park) engine->park(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index f330457209d5..812fde724426 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3181,6 +3181,9 @@ static void execlists_park(struct intel_engine_cs *engine) { cancel_timer(&engine->execlists.timer); cancel_timer(&engine->execlists.preempt); + + /* Reset upon idling, or we may delay the busy wakeup. */ + WRITE_ONCE(engine->sched_engine->queue_priority_hint, INT_MIN); } static void add_to_engine(struct i915_request *rq) diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 63ba2ad84679..5423ea4c1ef9 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -70,14 +70,14 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) int ret; if (!mode) - return -EINVAL; + return 0; ret = of_get_drm_display_mode(np, &imxpd->mode, &imxpd->bus_flags, OF_USE_NATIVE_MODE); if (ret) { drm_mode_destroy(connector->dev, mode); - return ret; + return 0; } drm_mode_copy(mode, &imxpd->mode); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 7a8353d7ab36..88aa00a1891b 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -222,7 +222,7 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector) edid = drm_get_edid(connector, vc4_hdmi->ddc); cec_s_phys_addr_from_edid(vc4_hdmi->cec_adap, edid); if (!edid) - return -ENODEV; + return 0; vc4_encoder->hdmi_monitor = drm_detect_hdmi_monitor(edid); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index b91f8d17404d..21134c7f1838 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -472,7 +472,7 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv, vmw_res_type(ctx) == vmw_res_dx_context) { for (i = 0; i < cotable_max; ++i) { res = vmw_context_cotable(ctx, i); - if (IS_ERR(res)) + if (IS_ERR_OR_NULL(res)) continue; ret = vmw_execbuf_res_noctx_val_add(sw_context, res, @@ -1277,6 +1277,8 @@ static int vmw_cmd_dx_define_query(struct vmw_private *dev_priv, return -EINVAL; cotable_res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_DXQUERY); + if (IS_ERR_OR_NULL(cotable_res)) + return cotable_res ? PTR_ERR(cotable_res) : -EINVAL; ret = vmw_cotable_notify(cotable_res, cmd->body.queryId); return ret; @@ -2455,6 +2457,8 @@ static int vmw_cmd_dx_view_define(struct vmw_private *dev_priv, return ret; res = vmw_context_cotable(ctx_node->ctx, vmw_view_cotables[view_type]); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->defined_id); if (unlikely(ret != 0)) return ret; @@ -2540,8 +2544,8 @@ static int vmw_cmd_dx_so_define(struct vmw_private *dev_priv, so_type = vmw_so_cmd_to_type(header->id); res = vmw_context_cotable(ctx_node->ctx, vmw_so_cotables[so_type]); - if (IS_ERR(res)) - return PTR_ERR(res); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; cmd = container_of(header, typeof(*cmd), header); ret = vmw_cotable_notify(res, cmd->defined_id); @@ -2660,6 +2664,8 @@ static int vmw_cmd_dx_define_shader(struct vmw_private *dev_priv, return -EINVAL; res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_DXSHADER); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->body.shaderId); if (ret) return ret; @@ -2981,6 +2987,8 @@ static int vmw_cmd_dx_define_streamoutput(struct vmw_private *dev_priv, } res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_STREAMOUTPUT); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->body.soid); if (ret) return ret; diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c index ba0ca652b9da..09da654d2b05 100644 --- a/drivers/hid/uhid.c +++ b/drivers/hid/uhid.c @@ -84,7 +84,7 @@ static void uhid_device_add_worker(struct work_struct *work) * However, we do have to clear the ->running flag and do a * wakeup to make sure userspace knows that the device is gone. */ - uhid->running = false; + WRITE_ONCE(uhid->running, false); wake_up_interruptible(&uhid->report_wait); } } @@ -194,9 +194,9 @@ static int __uhid_report_queue_and_wait(struct uhid_device *uhid, spin_unlock_irqrestore(&uhid->qlock, flags); ret = wait_event_interruptible_timeout(uhid->report_wait, - !uhid->report_running || !uhid->running, + !uhid->report_running || !READ_ONCE(uhid->running), 5 * HZ); - if (!ret || !uhid->running || uhid->report_running) + if (!ret || !READ_ONCE(uhid->running) || uhid->report_running) ret = -EIO; else if (ret < 0) ret = -ERESTARTSYS; @@ -237,7 +237,7 @@ static int uhid_hid_get_report(struct hid_device *hid, unsigned char rnum, struct uhid_event *ev; int ret; - if (!uhid->running) + if (!READ_ONCE(uhid->running)) return -EIO; ev = kzalloc(sizeof(*ev), GFP_KERNEL); @@ -279,7 +279,7 @@ static int uhid_hid_set_report(struct hid_device *hid, unsigned char rnum, struct uhid_event *ev; int ret; - if (!uhid->running || count > UHID_DATA_MAX) + if (!READ_ONCE(uhid->running) || count > UHID_DATA_MAX) return -EIO; ev = kzalloc(sizeof(*ev), GFP_KERNEL); @@ -580,7 +580,7 @@ static int uhid_dev_destroy(struct uhid_device *uhid) if (!uhid->hid) return -EINVAL; - uhid->running = false; + WRITE_ONCE(uhid->running, false); wake_up_interruptible(&uhid->report_wait); cancel_work_sync(&uhid->worker); @@ -594,7 +594,7 @@ static int uhid_dev_destroy(struct uhid_device *uhid) static int uhid_dev_input(struct uhid_device *uhid, struct uhid_event *ev) { - if (!uhid->running) + if (!READ_ONCE(uhid->running)) return -EINVAL; hid_input_report(uhid->hid, HID_INPUT_REPORT, ev->u.input.data, @@ -605,7 +605,7 @@ static int uhid_dev_input(struct uhid_device *uhid, struct uhid_event *ev) static int uhid_dev_input2(struct uhid_device *uhid, struct uhid_event *ev) { - if (!uhid->running) + if (!READ_ONCE(uhid->running)) return -EINVAL; hid_input_report(uhid->hid, HID_INPUT_REPORT, ev->u.input2.data, @@ -617,7 +617,7 @@ static int uhid_dev_input2(struct uhid_device *uhid, struct uhid_event *ev) static int uhid_dev_get_report_reply(struct uhid_device *uhid, struct uhid_event *ev) { - if (!uhid->running) + if (!READ_ONCE(uhid->running)) return -EINVAL; uhid_report_wake_up(uhid, ev->u.get_report_reply.id, ev); @@ -627,7 +627,7 @@ static int uhid_dev_get_report_reply(struct uhid_device *uhid, static int uhid_dev_set_report_reply(struct uhid_device *uhid, struct uhid_event *ev) { - if (!uhid->running) + if (!READ_ONCE(uhid->running)) return -EINVAL; uhid_report_wake_up(uhid, ev->u.set_report_reply.id, ev); diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c index 6b1ce2242c61..60dfdb0f5523 100644 --- a/drivers/hwmon/amc6821.c +++ b/drivers/hwmon/amc6821.c @@ -934,10 +934,21 @@ static const struct i2c_device_id amc6821_id[] = { MODULE_DEVICE_TABLE(i2c, amc6821_id); +static const struct of_device_id __maybe_unused amc6821_of_match[] = { + { + .compatible = "ti,amc6821", + .data = (void *)amc6821, + }, + { } +}; + +MODULE_DEVICE_TABLE(of, amc6821_of_match); + static struct i2c_driver amc6821_driver = { .class = I2C_CLASS_HWMON, .driver = { .name = "amc6821", + .of_match_table = of_match_ptr(amc6821_of_match), }, .probe_new = amc6821_probe, .id_table = amc6821_id, diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 87c2c7c84736..7844fba28190 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1416,7 +1416,6 @@ static int i801_add_mux(struct i801_priv *priv) mux_config->gpios[i], "mux", 0); } gpiod_add_lookup_table(lookup); - priv->lookup = lookup; /* * Register the mux device, we use PLATFORM_DEVID_NONE here @@ -1430,7 +1429,10 @@ static int i801_add_mux(struct i801_priv *priv) sizeof(struct i2c_mux_gpio_platform_data)); if (IS_ERR(priv->mux_pdev)) { gpiod_remove_lookup_table(lookup); + devm_kfree(dev, lookup); dev_err(dev, "Failed to register i2c-mux-gpio device\n"); + } else { + priv->lookup = lookup; } return PTR_ERR_OR_ZERO(priv->mux_pdev); diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 680c3ac8cd4c..504e1adf1997 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -34,6 +34,7 @@ MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("InfiniBand CM"); MODULE_LICENSE("Dual BSD/GPL"); +#define CM_DESTROY_ID_WAIT_TIMEOUT 10000 /* msecs */ static const char * const ibcm_rej_reason_strs[] = { [IB_CM_REJ_NO_QP] = "no QP", [IB_CM_REJ_NO_EEC] = "no EEC", @@ -1032,10 +1033,20 @@ static void cm_reset_to_idle(struct cm_id_private *cm_id_priv) } } +static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id) +{ + struct cm_id_private *cm_id_priv; + + cm_id_priv = container_of(cm_id, struct cm_id_private, id); + pr_err("%s: cm_id=%p timed out. state=%d refcnt=%d\n", __func__, + cm_id, cm_id->state, refcount_read(&cm_id_priv->refcount)); +} + static void cm_destroy_id(struct ib_cm_id *cm_id, int err) { struct cm_id_private *cm_id_priv; struct cm_work *work; + int ret; cm_id_priv = container_of(cm_id, struct cm_id_private, id); spin_lock_irq(&cm_id_priv->lock); @@ -1142,7 +1153,14 @@ retest: xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id)); cm_deref_id(cm_id_priv); - wait_for_completion(&cm_id_priv->comp); + do { + ret = wait_for_completion_timeout(&cm_id_priv->comp, + msecs_to_jiffies( + CM_DESTROY_ID_WAIT_TIMEOUT)); + if (!ret) /* timeout happened */ + cm_destroy_id_wait_timeout(cm_id); + } while (!ret); + while ((work = cm_dequeue_work(cm_id_priv)) != NULL) cm_free_work(work); diff --git a/drivers/infiniband/core/cm_trace.h b/drivers/infiniband/core/cm_trace.h index e9d282679ef1..944d9071245d 100644 --- a/drivers/infiniband/core/cm_trace.h +++ b/drivers/infiniband/core/cm_trace.h @@ -16,7 +16,7 @@ #include <linux/tracepoint.h> #include <rdma/ib_cm.h> -#include <trace/events/rdma.h> +#include <trace/misc/rdma.h> /* * enum ib_cm_state, from include/rdma/ib_cm.h diff --git a/drivers/infiniband/core/cma_trace.h b/drivers/infiniband/core/cma_trace.h index e45264267bcc..47f3c6e4be89 100644 --- a/drivers/infiniband/core/cma_trace.h +++ b/drivers/infiniband/core/cma_trace.h @@ -15,7 +15,7 @@ #define _TRACE_RDMA_CMA_H #include <linux/tracepoint.h> -#include <trace/events/rdma.h> +#include <trace/misc/rdma.h> DECLARE_EVENT_CLASS(cma_fsm_class, diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index 258d5fe3d395..aa32371f04af 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -1196,7 +1196,11 @@ static int rmi_driver_probe(struct device *dev) } rmi_driver_set_input_params(rmi_dev, data->input); data->input->phys = devm_kasprintf(dev, GFP_KERNEL, - "%s/input0", dev_name(dev)); + "%s/input0", dev_name(dev)); + if (!data->input->phys) { + retval = -ENOMEM; + goto err; + } } retval = rmi_init_functions(data); diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 8cd63e6ccd2c..aa47d955de6b 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1291,6 +1291,19 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev) return (1UL << __ffs(domain->pgsize_bitmap)) - 1; } +static size_t iommu_dma_opt_mapping_size(void) +{ + return iova_rcache_range(); +} + +static size_t iommu_dma_max_mapping_size(struct device *dev) +{ + if (dev_is_untrusted(dev)) + return swiotlb_max_mapping_size(dev); + + return SIZE_MAX; +} + static const struct dma_map_ops iommu_dma_ops = { .alloc = iommu_dma_alloc, .free = iommu_dma_free, @@ -1313,6 +1326,8 @@ static const struct dma_map_ops iommu_dma_ops = { .map_resource = iommu_dma_map_resource, .unmap_resource = iommu_dma_unmap_resource, .get_merge_boundary = iommu_dma_get_merge_boundary, + .opt_mapping_size = iommu_dma_opt_mapping_size, + .max_mapping_size = iommu_dma_max_mapping_size, }; /* diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 0835f32e040a..f6dfb9e45e95 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -27,6 +27,11 @@ static void free_iova_rcaches(struct iova_domain *iovad); static void fq_destroy_all_entries(struct iova_domain *iovad); static void fq_flush_timeout(struct timer_list *t); +unsigned long iova_rcache_range(void) +{ + return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1); +} + static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node) { struct iova_domain *iovad; diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index df743650d8a9..ae372bc44fbf 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -4083,7 +4083,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) } else if (sscanf(opt_string, "sectors_per_bit:%llu%c", &llval, &dummy) == 1) { log2_sectors_per_bitmap_bit = !llval ? 0 : __ilog2_u64(llval); } else if (sscanf(opt_string, "bitmap_flush_interval:%u%c", &val, &dummy) == 1) { - if (val >= (uint64_t)UINT_MAX * 1000 / HZ) { + if ((uint64_t)val >= (uint64_t)UINT_MAX * 1000 / HZ) { r = -EINVAL; ti->error = "Invalid bitmap_flush_interval argument"; goto bad; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 04769fb20cf7..5d1006142aae 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -4049,7 +4049,9 @@ static void raid_resume(struct dm_target *ti) * Take this opportunity to check whether any failed * devices are reachable again. */ + mddev_lock_nointr(mddev); attempt_restore_of_faulty_devices(rs); + mddev_unlock(mddev); } if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) { diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index dcf34c6b05ad..d3716d5c45c2 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -686,8 +686,10 @@ static void dm_exception_table_exit(struct dm_exception_table *et, for (i = 0; i < size; i++) { slot = et->table + i; - hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) + hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) { kmem_cache_free(mem, ex); + cond_resched(); + } } kvfree(et->table); diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c index 524912f20d9f..74bbdc11abbb 100644 --- a/drivers/media/pci/sta2x11/sta2x11_vip.c +++ b/drivers/media/pci/sta2x11/sta2x11_vip.c @@ -760,7 +760,7 @@ static const struct video_device video_dev_template = { /** * vip_irq - interrupt routine * @irq: Number of interrupt ( not used, correct number is assumed ) - * @vip: local data structure containing all information + * @data: local data structure containing all information * * check for both frame interrupts set ( top and bottom ). * check FIFO overflow, but limit number of log messages after open. @@ -770,8 +770,9 @@ static const struct video_device video_dev_template = { * * IRQ_HANDLED, interrupt done. */ -static irqreturn_t vip_irq(int irq, struct sta2x11_vip *vip) +static irqreturn_t vip_irq(int irq, void *data) { + struct sta2x11_vip *vip = data; unsigned int status; status = reg_read(vip, DVP_ITS); @@ -1053,9 +1054,7 @@ static int sta2x11_vip_init_one(struct pci_dev *pdev, spin_lock_init(&vip->slock); - ret = request_irq(pdev->irq, - (irq_handler_t) vip_irq, - IRQF_SHARED, KBUILD_MODNAME, vip); + ret = request_irq(pdev->irq, vip_irq, IRQF_SHARED, KBUILD_MODNAME, vip); if (ret) { dev_err(&pdev->dev, "request_irq failed\n"); ret = -ENODEV; diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c index ef9af052007c..849df4d1c573 100644 --- a/drivers/media/tuners/xc4000.c +++ b/drivers/media/tuners/xc4000.c @@ -1517,10 +1517,10 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq) { struct xc4000_priv *priv = fe->tuner_priv; + mutex_lock(&priv->lock); *freq = priv->freq_hz + priv->freq_offset; if (debug) { - mutex_lock(&priv->lock); if ((priv->cur_fw.type & (BASE | FM | DTV6 | DTV7 | DTV78 | DTV8)) == BASE) { u16 snr = 0; @@ -1531,8 +1531,8 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq) return 0; } } - mutex_unlock(&priv->lock); } + mutex_unlock(&priv->lock); dprintk(1, "%s()\n", __func__); diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 609519571545..00867bcc2ef7 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -112,6 +112,8 @@ #define MEI_DEV_ID_RPL_S 0x7A68 /* Raptor Lake Point S */ #define MEI_DEV_ID_MTL_M 0x7E70 /* Meteor Lake Point M */ +#define MEI_DEV_ID_ARL_S 0x7F68 /* Arrow Lake Point S */ +#define MEI_DEV_ID_ARL_H 0x7770 /* Arrow Lake Point H */ /* * MEI HW Section diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index f2765d6b8c04..91586d8afcaa 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -118,6 +118,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_S, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_H, MEI_ME_PCH15_CFG)}, /* required last entry */ {0, } diff --git a/drivers/misc/vmw_vmci/vmci_datagram.c b/drivers/misc/vmw_vmci/vmci_datagram.c index f50d22882476..a0ad1f3a69f7 100644 --- a/drivers/misc/vmw_vmci/vmci_datagram.c +++ b/drivers/misc/vmw_vmci/vmci_datagram.c @@ -234,7 +234,8 @@ static int dg_dispatch_as_host(u32 context_id, struct vmci_datagram *dg) dg_info->in_dg_host_queue = true; dg_info->entry = dst_entry; - memcpy(&dg_info->msg, dg, dg_size); + dg_info->msg = *dg; + memcpy(&dg_info->msg_payload, dg + 1, dg->payload_size); INIT_WORK(&dg_info->work, dg_delayed_dispatch); schedule_work(&dg_info->work); @@ -377,7 +378,8 @@ int vmci_datagram_invoke_guest_handler(struct vmci_datagram *dg) dg_info->in_dg_host_queue = false; dg_info->entry = dst_entry; - memcpy(&dg_info->msg, dg, VMCI_DG_SIZE(dg)); + dg_info->msg = *dg; + memcpy(&dg_info->msg_payload, dg + 1, dg->payload_size); INIT_WORK(&dg_info->work, dg_delayed_dispatch); schedule_work(&dg_info->work); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index c3202e2e99e8..68f820cd73b2 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -412,7 +412,7 @@ static struct mmc_blk_ioc_data *mmc_blk_ioctl_copy_from_user( struct mmc_blk_ioc_data *idata; int err; - idata = kmalloc(sizeof(*idata), GFP_KERNEL); + idata = kzalloc(sizeof(*idata), GFP_KERNEL); if (!idata) { err = -ENOMEM; goto out; @@ -485,7 +485,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, if (idata->flags & MMC_BLK_IOC_DROP) return 0; - if (idata->flags & MMC_BLK_IOC_SBC) + if (idata->flags & MMC_BLK_IOC_SBC && i > 0) prev_idata = idatas[i - 1]; /* @@ -862,10 +862,11 @@ static const struct block_device_operations mmc_bdops = { static int mmc_blk_part_switch_pre(struct mmc_card *card, unsigned int part_type) { - const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_MASK; + const unsigned int rpmb = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if ((part_type & mask) == mask) { + if ((part_type & mask) == rpmb) { if (card->ext_csd.cmdq_en) { ret = mmc_cmdq_disable(card); if (ret) @@ -880,10 +881,11 @@ static int mmc_blk_part_switch_pre(struct mmc_card *card, static int mmc_blk_part_switch_post(struct mmc_card *card, unsigned int part_type) { - const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_MASK; + const unsigned int rpmb = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if ((part_type & mask) == mask) { + if ((part_type & mask) == rpmb) { mmc_retune_unpause(card->host); if (card->reenable_cmdq && !card->ext_csd.cmdq_en) ret = mmc_cmdq_enable(card); diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 437048bb8027..5024cae411d3 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -259,6 +259,8 @@ static void tmio_mmc_reset_work(struct work_struct *work) else mrq->cmd->error = -ETIMEDOUT; + /* No new calls yet, but disallow concurrent tmio_mmc_done_work() */ + host->mrq = ERR_PTR(-EBUSY); host->cmd = NULL; host->data = NULL; diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index 9d441965321a..9198d54cb34e 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -59,7 +59,7 @@ #define CMDRWGEN(cmd_dir, ran, bch, short_mode, page_size, pages) \ ( \ (cmd_dir) | \ - ((ran) << 19) | \ + (ran) | \ ((bch) << 14) | \ ((short_mode) << 13) | \ (((page_size) & 0x7f) << 6) | \ diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index 6e95c4b1473e..8081fc760d34 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -86,9 +86,10 @@ size_t ubi_calc_fm_size(struct ubi_device *ubi) sizeof(struct ubi_fm_scan_pool) + sizeof(struct ubi_fm_scan_pool) + (ubi->peb_count * sizeof(struct ubi_fm_ec)) + - (sizeof(struct ubi_fm_eba) + - (ubi->peb_count * sizeof(__be32))) + - sizeof(struct ubi_fm_volhdr) * UBI_MAX_VOLUMES; + ((sizeof(struct ubi_fm_eba) + + sizeof(struct ubi_fm_volhdr)) * + (UBI_MAX_VOLUMES + UBI_INT_VOL_COUNT)) + + (ubi->peb_count * sizeof(__be32)); return roundup(size, ubi->leb_size); } diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c index f700f0e4f2ec..6e5489e233dd 100644 --- a/drivers/mtd/ubi/vtbl.c +++ b/drivers/mtd/ubi/vtbl.c @@ -791,6 +791,12 @@ int ubi_read_volume_table(struct ubi_device *ubi, struct ubi_attach_info *ai) * The number of supported volumes is limited by the eraseblock size * and by the UBI_MAX_VOLUMES constant. */ + + if (ubi->leb_size < UBI_VTBL_RECORD_SIZE) { + ubi_err(ubi, "LEB size too small for a volume record"); + return -EINVAL; + } + ubi->vtbl_slots = ubi->leb_size / UBI_VTBL_RECORD_SIZE; if (ubi->vtbl_slots > UBI_MAX_VOLUMES) ubi->vtbl_slots = UBI_MAX_VOLUMES; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 39875ccbaa0f..972808777f30 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2132,8 +2132,6 @@ static int fec_enet_mii_probe(struct net_device *ndev) fep->link = 0; fep->full_duplex = 0; - phy_dev->mac_managed_pm = 1; - phy_attached_info(phy_dev); return 0; @@ -2145,10 +2143,12 @@ static int fec_enet_mii_init(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); bool suppress_preamble = false; + struct phy_device *phydev; struct device_node *node; int err = -ENXIO; u32 mii_speed, holdtime; u32 bus_freq; + int addr; /* * The i.MX28 dual fec interfaces are not equal. @@ -2258,6 +2258,13 @@ static int fec_enet_mii_init(struct platform_device *pdev) goto err_out_free_mdiobus; of_node_put(node); + /* find all the PHY devices on the bus and set mac_managed_pm to true */ + for (addr = 0; addr < PHY_MAX_ADDR; addr++) { + phydev = mdiobus_get_phy(fep->mii_bus, addr); + if (phydev) + phydev->mac_managed_pm = true; + } + mii_cnt++; /* save fec0 mii_bus */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h index 8510b88d4982..f3cd5a376eca 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h @@ -24,7 +24,7 @@ TRACE_EVENT(hclge_pf_mbx_get, __field(u8, code) __field(u8, subcode) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->vport[0].nic.kinfo.netdev->name) + __string(devname, hdev->vport[0].nic.kinfo.netdev->name) __array(u32, mbx_data, PF_GET_MBX_LEN) ), @@ -33,7 +33,7 @@ TRACE_EVENT(hclge_pf_mbx_get, __entry->code = req->msg.code; __entry->subcode = req->msg.subcode; __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name); + __assign_str(devname, hdev->vport[0].nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_vf_to_pf_cmd)); ), @@ -56,7 +56,7 @@ TRACE_EVENT(hclge_pf_mbx_send, __field(u8, vfid) __field(u16, code) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->vport[0].nic.kinfo.netdev->name) + __string(devname, hdev->vport[0].nic.kinfo.netdev->name) __array(u32, mbx_data, PF_SEND_MBX_LEN) ), @@ -64,7 +64,7 @@ TRACE_EVENT(hclge_pf_mbx_send, __entry->vfid = req->dest_vfid; __entry->code = le16_to_cpu(req->msg.code); __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name); + __assign_str(devname, hdev->vport[0].nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_pf_to_vf_cmd)); ), diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h index 5d4895bb57a1..b259e95dd53c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h @@ -23,7 +23,7 @@ TRACE_EVENT(hclge_vf_mbx_get, __field(u8, vfid) __field(u16, code) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->nic.kinfo.netdev->name) + __string(devname, hdev->nic.kinfo.netdev->name) __array(u32, mbx_data, VF_GET_MBX_LEN) ), @@ -31,7 +31,7 @@ TRACE_EVENT(hclge_vf_mbx_get, __entry->vfid = req->dest_vfid; __entry->code = le16_to_cpu(req->msg.code); __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->nic.kinfo.netdev->name); + __assign_str(devname, hdev->nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_pf_to_vf_cmd)); ), @@ -55,7 +55,7 @@ TRACE_EVENT(hclge_vf_mbx_send, __field(u8, code) __field(u8, subcode) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->nic.kinfo.netdev->name) + __string(devname, hdev->nic.kinfo.netdev->name) __array(u32, mbx_data, VF_SEND_MBX_LEN) ), @@ -64,7 +64,7 @@ TRACE_EVENT(hclge_vf_mbx_send, __entry->code = req->msg.code; __entry->subcode = req->msg.subcode; __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->nic.kinfo.netdev->name); + __assign_str(devname, hdev->nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_vf_to_pf_cmd)); ), diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 453a85410634..a05103e2fb52 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -108,7 +108,7 @@ #define I40E_MAX_BW_INACTIVE_ACCUM 4 /* accumulate 4 credits max */ /* driver state flags */ -enum i40e_state_t { +enum i40e_state { __I40E_TESTING, __I40E_CONFIG_BUSY, __I40E_CONFIG_DONE, @@ -156,7 +156,7 @@ enum i40e_state_t { BIT_ULL(__I40E_PF_RESET_AND_REBUILD_REQUESTED) /* VSI state flags */ -enum i40e_vsi_state_t { +enum i40e_vsi_state { __I40E_VSI_DOWN, __I40E_VSI_NEEDS_RESTART, __I40E_VSI_SYNCING_FILTERS, @@ -973,6 +973,8 @@ struct i40e_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; + bool in_busy_poll; + int irq_num; /* IRQ assigned to this q_vector */ } ____cacheline_internodealigned_in_smp; /* lan device */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 7b522d55f368..676ea7d4192f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1231,8 +1231,11 @@ int i40e_count_filters(struct i40e_vsi *vsi) int bkt; int cnt = 0; - hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) - ++cnt; + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (f->state == I40E_FILTER_NEW || + f->state == I40E_FILTER_ACTIVE) + ++cnt; + } return cnt; } @@ -3868,6 +3871,12 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) q_vector->tx.target_itr >> 1); q_vector->tx.current_itr = q_vector->tx.target_itr; + /* Set ITR for software interrupts triggered after exiting + * busy-loop polling. + */ + wr32(hw, I40E_PFINT_ITRN(I40E_SW_ITR, vector - 1), + I40E_ITR_20K); + wr32(hw, I40E_PFINT_RATEN(vector - 1), i40e_intrl_usec_to_reg(vsi->int_rate_limit)); @@ -4130,6 +4139,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) } /* register for affinity change notifications */ + q_vector->irq_num = irq_num; q_vector->affinity_notify.notify = i40e_irq_affinity_notify; q_vector->affinity_notify.release = i40e_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 09b1d5aed1c9..38942d3f7819 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -35,7 +35,7 @@ enum i40e_ptp_pin { GPIO_4 }; -enum i40e_can_set_pins_t { +enum i40e_can_set_pins { CANT_DO_PINS = -1, CAN_SET_PINS, CAN_DO_PINS @@ -193,7 +193,7 @@ static bool i40e_is_ptp_pin_dev(struct i40e_hw *hw) * return CAN_DO_PINS if pins can be manipulated within a NIC or * return CANT_DO_PINS otherwise. **/ -static enum i40e_can_set_pins_t i40e_can_set_pins(struct i40e_pf *pf) +static enum i40e_can_set_pins i40e_can_set_pins(struct i40e_pf *pf) { if (!i40e_is_ptp_pin_dev(&pf->hw)) { dev_warn(&pf->pdev->dev, @@ -1089,7 +1089,7 @@ static void i40e_ptp_set_pins_hw(struct i40e_pf *pf) static int i40e_ptp_set_pins(struct i40e_pf *pf, struct i40e_ptp_pins_settings *pins) { - enum i40e_can_set_pins_t pin_caps = i40e_can_set_pins(pf); + enum i40e_can_set_pins pin_caps = i40e_can_set_pins(pf); int i = 0; if (pin_caps == CANT_DO_PINS) diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index 7339003aa17c..694cb3e45c1e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -328,8 +328,11 @@ #define I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT 3 #define I40E_PFINT_DYN_CTLN_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) #define I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT 5 +#define I40E_PFINT_DYN_CTLN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT) #define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24 #define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT) +#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25 +#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT) #define I40E_PFINT_ICR0 0x00038780 /* Reset: CORER */ #define I40E_PFINT_ICR0_INTEVENT_SHIFT 0 #define I40E_PFINT_ICR0_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_INTEVENT_SHIFT) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index cf8c3d480a4a..e2737875e379 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2560,7 +2560,22 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) return failure ? budget : (int)total_rx_packets; } -static inline u32 i40e_buildreg_itr(const int type, u16 itr) +/** + * i40e_buildreg_itr - build a value for writing to I40E_PFINT_DYN_CTLN register + * @itr_idx: interrupt throttling index + * @interval: interrupt throttling interval value in usecs + * @force_swint: force software interrupt + * + * The function builds a value for I40E_PFINT_DYN_CTLN register that + * is used to update interrupt throttling interval for specified ITR index + * and optionally enforces a software interrupt. If the @itr_idx is equal + * to I40E_ITR_NONE then no interval change is applied and only @force_swint + * parameter is taken into account. If the interval change and enforced + * software interrupt are not requested then the built value just enables + * appropriate vector interrupt. + **/ +static u32 i40e_buildreg_itr(enum i40e_dyn_idx itr_idx, u16 interval, + bool force_swint) { u32 val; @@ -2574,23 +2589,33 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) * an event in the PBA anyway so we need to rely on the automask * to hold pending events for us until the interrupt is re-enabled * - * The itr value is reported in microseconds, and the register - * value is recorded in 2 microsecond units. For this reason we - * only need to shift by the interval shift - 1 instead of the - * full value. + * We have to shift the given value as it is reported in microseconds + * and the register value is recorded in 2 microsecond units. */ - itr &= I40E_ITR_MASK; + interval >>= 1; + /* 1. Enable vector interrupt + * 2. Update the interval for the specified ITR index + * (I40E_ITR_NONE in the register is used to indicate that + * no interval update is requested) + */ val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | - (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1)); + FIELD_PREP(I40E_PFINT_DYN_CTLN_ITR_INDX_MASK, itr_idx) | + FIELD_PREP(I40E_PFINT_DYN_CTLN_INTERVAL_MASK, interval); + + /* 3. Enforce software interrupt trigger if requested + * (These software interrupts rate is limited by ITR2 that is + * set to 20K interrupts per second) + */ + if (force_swint) + val |= I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK | + I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK | + FIELD_PREP(I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK, + I40E_SW_ITR); return val; } -/* a small macro to shorten up some long lines */ -#define INTREG I40E_PFINT_DYN_CTLN - /* The act of updating the ITR will cause it to immediately trigger. In order * to prevent this from throwing off adaptive update statistics we defer the * update so that it can only happen so often. So after either Tx or Rx are @@ -2609,8 +2634,10 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { + enum i40e_dyn_idx itr_idx = I40E_ITR_NONE; struct i40e_hw *hw = &vsi->back->hw; - u32 intval; + u16 interval = 0; + u32 itr_val; /* If we don't have MSIX, then we only need to re-enable icr0 */ if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) { @@ -2632,8 +2659,8 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, */ if (q_vector->rx.target_itr < q_vector->rx.current_itr) { /* Rx ITR needs to be reduced, this is highest priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, - q_vector->rx.target_itr); + itr_idx = I40E_RX_ITR; + interval = q_vector->rx.target_itr; q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) || @@ -2642,25 +2669,36 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, /* Tx ITR needs to be reduced, this is second priority * Tx ITR needs to be increased more than Rx, fourth priority */ - intval = i40e_buildreg_itr(I40E_TX_ITR, - q_vector->tx.target_itr); + itr_idx = I40E_TX_ITR; + interval = q_vector->tx.target_itr; q_vector->tx.current_itr = q_vector->tx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { /* Rx ITR needs to be increased, third priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, - q_vector->rx.target_itr); + itr_idx = I40E_RX_ITR; + interval = q_vector->rx.target_itr; q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else { /* No ITR update, lowest priority */ - intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); if (q_vector->itr_countdown) q_vector->itr_countdown--; } - if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(q_vector->reg_idx), intval); + /* Do not update interrupt control register if VSI is down */ + if (test_bit(__I40E_VSI_DOWN, vsi->state)) + return; + + /* Update ITR interval if necessary and enforce software interrupt + * if we are exiting busy poll. + */ + if (q_vector->in_busy_poll) { + itr_val = i40e_buildreg_itr(itr_idx, interval, true); + q_vector->in_busy_poll = false; + } else { + itr_val = i40e_buildreg_itr(itr_idx, interval, false); + } + wr32(hw, I40E_PFINT_DYN_CTLN(q_vector->reg_idx), itr_val); } /** @@ -2767,6 +2805,8 @@ tx_only: */ if (likely(napi_complete_done(napi, work_done))) i40e_update_enable_itr(vsi, q_vector); + else + q_vector->in_busy_poll = true; return min(work_done, budget - 1); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index f3b0b8151709..054b7d1632e1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -57,7 +57,7 @@ static inline u16 i40e_intrl_usec_to_reg(int intrl) * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any * register but instead is a special value meaning "don't update" ITR0/1/2. */ -enum i40e_dyn_idx_t { +enum i40e_dyn_idx { I40E_IDX_ITR0 = 0, I40E_IDX_ITR1 = 1, I40E_IDX_ITR2 = 2, @@ -67,6 +67,7 @@ enum i40e_dyn_idx_t { /* these are indexes into ITRN registers */ #define I40E_RX_ITR I40E_IDX_ITR0 #define I40E_TX_ITR I40E_IDX_ITR1 +#define I40E_SW_ITR I40E_IDX_ITR2 /* Supported RSS offloads */ #define I40E_DEFAULT_RSS_HENA ( \ @@ -301,7 +302,7 @@ struct i40e_rx_queue_stats { u64 realloc_count; }; -enum i40e_ring_state_t { +enum i40e_ring_state { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, __I40E_RING_STATE_NBITS /* must be last */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 9ff8bf346b9e..d1635df17e46 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1626,8 +1626,8 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) { struct i40e_hw *hw = &pf->hw; struct i40e_vf *vf; - int i, v; u32 reg; + int i; /* If we don't have any VFs, then there is nothing to reset */ if (!pf->num_alloc_vfs) @@ -1638,11 +1638,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) return false; /* Begin reset on all VFs at once */ - for (v = 0; v < pf->num_alloc_vfs; v++) { - vf = &pf->vf[v]; + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* If VF is being reset no need to trigger reset again */ if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) - i40e_trigger_vf_reset(&pf->vf[v], flr); + i40e_trigger_vf_reset(vf, flr); } /* HW requires some time to make sure it can flush the FIFO for a VF @@ -1651,14 +1650,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) * the VFs using a simple iterator that increments once that VF has * finished resetting. */ - for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { + for (i = 0, vf = &pf->vf[0]; i < 10 && vf < &pf->vf[pf->num_alloc_vfs]; ++i) { usleep_range(10000, 20000); /* Check each VF in sequence, beginning with the VF to fail * the previous check. */ - while (v < pf->num_alloc_vfs) { - vf = &pf->vf[v]; + while (vf < &pf->vf[pf->num_alloc_vfs]) { if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) { reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK)) @@ -1668,7 +1666,7 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* If the current VF has finished resetting, move on * to the next VF in sequence. */ - v++; + ++vf; } } @@ -1678,39 +1676,39 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* Display a warning if at least one VF didn't manage to reset in * time, but continue on with the operation. */ - if (v < pf->num_alloc_vfs) + if (vf < &pf->vf[pf->num_alloc_vfs]) dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n", - pf->vf[v].vf_id); + vf->vf_id); usleep_range(10000, 20000); /* Begin disabling all the rings associated with VFs, but do not wait * between each VF. */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* On initial reset, we don't have any queues to disable */ - if (pf->vf[v].lan_vsi_idx == 0) + if (vf->lan_vsi_idx == 0) continue; /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]); + i40e_vsi_stop_rings_no_wait(pf->vsi[vf->lan_vsi_idx]); } /* Now that we've notified HW to disable all of the VF rings, wait * until they finish. */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* On initial reset, we don't have any queues to disable */ - if (pf->vf[v].lan_vsi_idx == 0) + if (vf->lan_vsi_idx == 0) continue; /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]); + i40e_vsi_wait_queues_disabled(pf->vsi[vf->lan_vsi_idx]); } /* Hw may need up to 50ms to finish disabling the RX queues. We @@ -1719,12 +1717,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) mdelay(50); /* Finish the reset on each VF */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_cleanup_reset_vf(&pf->vf[v]); + i40e_cleanup_reset_vf(vf); } i40e_flush(hw); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index 69d11ff7677d..ac198c00b44f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -909,7 +909,13 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) goto err_out; } - xs = kzalloc(sizeof(*xs), GFP_KERNEL); + algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1); + if (unlikely(!algo)) { + err = -ENOENT; + goto err_out; + } + + xs = kzalloc(sizeof(*xs), GFP_ATOMIC); if (unlikely(!xs)) { err = -ENOMEM; goto err_out; @@ -925,14 +931,8 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) memcpy(&xs->id.daddr.a4, sam->addr, sizeof(xs->id.daddr.a4)); xs->xso.dev = adapter->netdev; - algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1); - if (unlikely(!algo)) { - err = -ENOENT; - goto err_xs; - } - aead_len = sizeof(*xs->aead) + IXGBE_IPSEC_KEY_BITS / 8; - xs->aead = kzalloc(aead_len, GFP_KERNEL); + xs->aead = kzalloc(aead_len, GFP_ATOMIC); if (unlikely(!xs->aead)) { err = -ENOMEM; goto err_xs; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 3ade1a6e2f1e..4dec20115895 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -787,6 +787,11 @@ static int cgx_lmac_enadis_pause_frm(void *cgxd, int lmac_id, if (!is_lmac_valid(cgx, lmac_id)) return -ENODEV; + cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); + cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK; + cfg |= rx_pause ? CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK : 0x0; + cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); cfg &= ~CGX_SMUX_RX_FRM_CTL_CTL_BCK; cfg |= rx_pause ? CGX_SMUX_RX_FRM_CTL_CTL_BCK : 0x0; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 604aaa9b960e..c6b6d709e590 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -1622,7 +1622,7 @@ static int npc_fwdb_detect_load_prfl_img(struct rvu *rvu, uint64_t prfl_sz, struct npc_coalesced_kpu_prfl *img_data = NULL; int i = 0, rc = -EINVAL; void __iomem *kpu_prfl_addr; - u16 offset; + u32 offset; img_data = (struct npc_coalesced_kpu_prfl __force *)rvu->kpu_prfl_addr; if (le64_to_cpu(img_data->signature) == KPU_SIGN && diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 167b926196c8..5f093b34db69 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1795,7 +1795,7 @@ int otx2_open(struct net_device *netdev) * mcam entries are enabled to receive the packets. Hence disable the * packet I/O. */ - if (err == EIO) + if (err == -EIO) goto err_disable_rxtx; else if (err) goto err_tx_stop_queues; diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index 679415a64f25..c644ee78e0b4 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/phy.h> #include <linux/platform_device.h> +#include <linux/rtnetlink.h> #include <linux/skbuff.h> #include "mlxbf_gige.h" @@ -141,13 +142,10 @@ static int mlxbf_gige_open(struct net_device *netdev) control |= MLXBF_GIGE_CONTROL_PORT_EN; writeq(control, priv->base + MLXBF_GIGE_CONTROL); - err = mlxbf_gige_request_irqs(priv); - if (err) - return err; mlxbf_gige_cache_stats(priv); err = mlxbf_gige_clean_port(priv); if (err) - goto free_irqs; + return err; /* Clear driver's valid_polarity to match hardware, * since the above call to clean_port() resets the @@ -159,7 +157,7 @@ static int mlxbf_gige_open(struct net_device *netdev) err = mlxbf_gige_tx_init(priv); if (err) - goto free_irqs; + goto phy_deinit; err = mlxbf_gige_rx_init(priv); if (err) goto tx_deinit; @@ -168,6 +166,10 @@ static int mlxbf_gige_open(struct net_device *netdev) napi_enable(&priv->napi); netif_start_queue(netdev); + err = mlxbf_gige_request_irqs(priv); + if (err) + goto napi_deinit; + /* Set bits in INT_EN that we care about */ int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR | MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS | @@ -184,11 +186,17 @@ static int mlxbf_gige_open(struct net_device *netdev) return 0; +napi_deinit: + netif_stop_queue(netdev); + napi_disable(&priv->napi); + netif_napi_del(&priv->napi); + mlxbf_gige_rx_deinit(priv); + tx_deinit: mlxbf_gige_tx_deinit(priv); -free_irqs: - mlxbf_gige_free_irqs(priv); +phy_deinit: + phy_stop(phydev); return err; } @@ -412,8 +420,13 @@ static void mlxbf_gige_shutdown(struct platform_device *pdev) { struct mlxbf_gige *priv = platform_get_drvdata(pdev); - writeq(0, priv->base + MLXBF_GIGE_INT_EN); - mlxbf_gige_clean_port(priv); + rtnl_lock(); + netif_device_detach(priv->netdev); + + if (netif_running(priv->netdev)) + dev_close(priv->netdev); + + rtnl_unlock(); } static const struct acpi_device_id __maybe_unused mlxbf_gige_acpi_match[] = { diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 63181866809f..1f84ba638e6e 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -3232,9 +3232,12 @@ static int ionic_lif_adminq_init(struct ionic_lif *lif) napi_enable(&qcq->napi); - if (qcq->flags & IONIC_QCQ_F_INTR) + if (qcq->flags & IONIC_QCQ_F_INTR) { + irq_set_affinity_hint(qcq->intr.vector, + &qcq->intr.affinity_mask); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); + } qcq->flags |= IONIC_QCQ_F_INITED; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index b8ac07be6157..623286f22105 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5138,6 +5138,15 @@ static int r8169_mdio_register(struct rtl8169_private *tp) struct mii_bus *new_bus; int ret; + /* On some boards with this chip version the BIOS is buggy and misses + * to reset the PHY page selector. This results in the PHY ID read + * accessing registers on a different page, returning a more or + * less random value. Fix this by resetting the page selector first. + */ + if (tp->mac_version == RTL_GIGA_MAC_VER_25 || + tp->mac_version == RTL_GIGA_MAC_VER_26) + r8169_mdio_write(tp, 0x1f, 0); + new_bus = devm_mdiobus_alloc(&pdev->dev); if (!new_bus) return -ENOMEM; @@ -5168,7 +5177,7 @@ static int r8169_mdio_register(struct rtl8169_private *tp) return -EUNATCH; } - tp->phydev->mac_managed_pm = 1; + tp->phydev->mac_managed_pm = true; phy_support_asym_pause(tp->phydev); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 2bf5d4c208d3..eee446e50048 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -969,12 +969,12 @@ static int ravb_poll(struct napi_struct *napi, int budget) int q = napi - priv->napi; int mask = BIT(q); int quota = budget; + bool unmask; /* Processing RX Descriptor Ring */ /* Clear RX interrupt */ ravb_write(ndev, ~(mask | RIS0_RESERVED), RIS0); - if (ravb_rx(ndev, "a, q)) - goto out; + unmask = !ravb_rx(ndev, "a, q); /* Processing TX Descriptor Ring */ spin_lock_irqsave(&priv->lock, flags); @@ -984,6 +984,9 @@ static int ravb_poll(struct napi_struct *napi, int budget) netif_wake_subqueue(ndev, q); spin_unlock_irqrestore(&priv->lock, flags); + if (!unmask) + goto out; + napi_complete(napi); /* Re-enable RX/TX interrupts */ @@ -2067,6 +2070,7 @@ static const struct of_device_id ravb_match_table[] = { { .compatible = "renesas,etheravb-rcar-gen2", .data = &ravb_gen2_hw_info }, { .compatible = "renesas,etheravb-r8a7795", .data = &ravb_gen3_hw_info }, { .compatible = "renesas,etheravb-rcar-gen3", .data = &ravb_gen3_hw_info }, + { .compatible = "renesas,etheravb-rcar-gen4", .data = &ravb_gen3_hw_info }, { } }; MODULE_DEVICE_TABLE(of, ravb_match_table); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f6d6a6d9c555..026e3645e566 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -88,19 +88,41 @@ static void dwmac4_rx_queue_priority(struct mac_device_info *hw, u32 prio, u32 queue) { void __iomem *ioaddr = hw->pcsr; - u32 base_register; - u32 value; + u32 clear_mask = 0; + u32 ctrl2, ctrl3; + int i; - base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3; - if (queue >= 4) - queue -= 4; + ctrl2 = readl(ioaddr + GMAC_RXQ_CTRL2); + ctrl3 = readl(ioaddr + GMAC_RXQ_CTRL3); - value = readl(ioaddr + base_register); + /* The software must ensure that the same priority + * is not mapped to multiple Rx queues + */ + for (i = 0; i < 4; i++) + clear_mask |= ((prio << GMAC_RXQCTRL_PSRQX_SHIFT(i)) & + GMAC_RXQCTRL_PSRQX_MASK(i)); - value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue); - value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & + ctrl2 &= ~clear_mask; + ctrl3 &= ~clear_mask; + + /* First assign new priorities to a queue, then + * clear them from others queues + */ + if (queue < 4) { + ctrl2 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & GMAC_RXQCTRL_PSRQX_MASK(queue); - writel(value, ioaddr + base_register); + + writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2); + writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3); + } else { + queue -= 4; + + ctrl3 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & + GMAC_RXQCTRL_PSRQX_MASK(queue); + + writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3); + writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2); + } } static void dwmac4_tx_queue_priority(struct mac_device_info *hw, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index ec1616ffbfa7..dd73f38ec08d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -97,17 +97,41 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio, u32 queue) { void __iomem *ioaddr = hw->pcsr; - u32 value, reg; + u32 clear_mask = 0; + u32 ctrl2, ctrl3; + int i; - reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3; - if (queue >= 4) + ctrl2 = readl(ioaddr + XGMAC_RXQ_CTRL2); + ctrl3 = readl(ioaddr + XGMAC_RXQ_CTRL3); + + /* The software must ensure that the same priority + * is not mapped to multiple Rx queues + */ + for (i = 0; i < 4; i++) + clear_mask |= ((prio << XGMAC_PSRQ_SHIFT(i)) & + XGMAC_PSRQ(i)); + + ctrl2 &= ~clear_mask; + ctrl3 &= ~clear_mask; + + /* First assign new priorities to a queue, then + * clear them from others queues + */ + if (queue < 4) { + ctrl2 |= (prio << XGMAC_PSRQ_SHIFT(queue)) & + XGMAC_PSRQ(queue); + + writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2); + writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3); + } else { queue -= 4; - value = readl(ioaddr + reg); - value &= ~XGMAC_PSRQ(queue); - value |= (prio << XGMAC_PSRQ_SHIFT(queue)) & XGMAC_PSRQ(queue); + ctrl3 |= (prio << XGMAC_PSRQ_SHIFT(queue)) & + XGMAC_PSRQ(queue); - writel(value, ioaddr + reg); + writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3); + writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2); + } } static void dwxgmac2_tx_queue_prio(struct mac_device_info *hw, u32 prio, diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index b4db50c9e703..4e45153959c7 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1433,7 +1433,7 @@ static int temac_probe(struct platform_device *pdev) } /* map device registers */ - lp->regs = devm_platform_ioremap_resource_byname(pdev, 0); + lp->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(lp->regs)) { dev_err(&pdev->dev, "could not map TEMAC registers\n"); return -ENOMEM; diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 556ca9884356..ab382496c3a8 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -242,7 +242,7 @@ static int xpcs_soft_reset(struct dw_xpcs *xpcs, dev = MDIO_MMD_VEND2; break; default: - return -1; + return -EINVAL; } ret = xpcs_write(xpcs, dev, MDIO_CTRL1, MDIO_CTRL1_RESET); @@ -808,7 +808,7 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, return ret; break; default: - return -1; + return -EINVAL; } if (compat->pma_config) { diff --git a/drivers/net/usb/asix.h b/drivers/net/usb/asix.h index c126df1c13ee..9da88e132d51 100644 --- a/drivers/net/usb/asix.h +++ b/drivers/net/usb/asix.h @@ -157,6 +157,8 @@ #define AX_EEPROM_MAGIC 0xdeadbeef #define AX_EEPROM_LEN 0x200 +#define AX_EMBD_PHY_ADDR 0x10 + /* This structure cannot exceed sizeof(unsigned long [5]) AKA 20 bytes */ struct asix_data { u8 multi_filter[AX_MCAST_FILTER_SIZE]; @@ -181,6 +183,7 @@ struct asix_common_private { struct asix_rx_fixup_info rx_fixup_info; struct mii_bus *mdio; struct phy_device *phydev; + struct phy_device *phydev_int; u16 phy_addr; char phy_name[20]; bool embd_phy; diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 396505396a2e..5a4137b2531f 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -694,10 +694,26 @@ static int ax88772_init_phy(struct usbnet *dev) } phy_suspend(priv->phydev); - priv->phydev->mac_managed_pm = 1; + priv->phydev->mac_managed_pm = true; phy_attached_info(priv->phydev); + if (priv->embd_phy) + return 0; + + /* In case main PHY is not the embedded PHY and MAC is RMII clock + * provider, we need to suspend embedded PHY by keeping PLL enabled + * (AX_SWRESET_IPPD == 0). + */ + priv->phydev_int = mdiobus_get_phy(priv->mdio, AX_EMBD_PHY_ADDR); + if (!priv->phydev_int) { + netdev_err(dev->net, "Could not find internal PHY\n"); + return -ENODEV; + } + + priv->phydev_int->mac_managed_pm = true; + phy_suspend(priv->phydev_int); + return 0; } @@ -753,7 +769,7 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf) return ret; priv->phy_addr = ret; - priv->embd_phy = ((priv->phy_addr & 0x1f) == 0x10); + priv->embd_phy = ((priv->phy_addr & 0x1f) == AX_EMBD_PHY_ADDR); ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG, 0, 0, 1, &chipcode, 0); if (ret < 0) { diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index f5bc279c9a8c..9dc02fa51ed0 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -164,8 +164,8 @@ get_peer(struct wg_peer *peer, struct sk_buff *skb, struct dump_ctx *ctx) if (!allowedips_node) goto no_allowedips; if (!ctx->allowedips_seq) - ctx->allowedips_seq = peer->device->peer_allowedips.seq; - else if (ctx->allowedips_seq != peer->device->peer_allowedips.seq) + ctx->allowedips_seq = ctx->wg->peer_allowedips.seq; + else if (ctx->allowedips_seq != ctx->wg->peer_allowedips.seq) goto no_allowedips; allowedips_nest = nla_nest_start(skb, WGPEER_A_ALLOWEDIPS); @@ -255,17 +255,17 @@ static int wg_get_device_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!peers_nest) goto out; ret = 0; - /* If the last cursor was removed via list_del_init in peer_remove, then + lockdep_assert_held(&wg->device_update_lock); + /* If the last cursor was removed in peer_remove or peer_remove_all, then * we just treat this the same as there being no more peers left. The * reason is that seq_nr should indicate to userspace that this isn't a * coherent dump anyway, so they'll try again. */ if (list_empty(&wg->peer_list) || - (ctx->next_peer && list_empty(&ctx->next_peer->peer_list))) { + (ctx->next_peer && ctx->next_peer->is_dead)) { nla_nest_cancel(skb, peers_nest); goto out; } - lockdep_assert_held(&wg->device_update_lock); peer = list_prepare_entry(ctx->next_peer, &wg->peer_list, peer_list); list_for_each_entry_continue(peer, &wg->peer_list, peer_list) { if (get_peer(peer, skb, ctx)) { diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c index f2149241fb13..265b85c40a4a 100644 --- a/drivers/net/wireless/ath/ath11k/mhi.c +++ b/drivers/net/wireless/ath/ath11k/mhi.c @@ -97,7 +97,7 @@ static struct mhi_controller_config ath11k_mhi_config_qca6390 = { .max_channels = 128, .timeout_ms = 2000, .use_bounce_buf = false, - .buf_len = 0, + .buf_len = 8192, .num_channels = ARRAY_SIZE(ath11k_mhi_channels_qca6390), .ch_cfg = ath11k_mhi_channels_qca6390, .num_events = ARRAY_SIZE(ath11k_mhi_events_qca6390), diff --git a/drivers/net/wireless/ath/ath9k/antenna.c b/drivers/net/wireless/ath/ath9k/antenna.c index 988222cea9df..acc84e6711b0 100644 --- a/drivers/net/wireless/ath/ath9k/antenna.c +++ b/drivers/net/wireless/ath/ath9k/antenna.c @@ -643,7 +643,7 @@ static void ath_ant_try_scan(struct ath_ant_comb *antcomb, conf->main_lna_conf = ATH_ANT_DIV_COMB_LNA1; conf->alt_lna_conf = ATH_ANT_DIV_COMB_LNA1_PLUS_LNA2; } else if (antcomb->rssi_sub > - antcomb->rssi_lna1) { + antcomb->rssi_lna2) { /* set to A-B */ conf->main_lna_conf = ATH_ANT_DIV_COMB_LNA1; conf->alt_lna_conf = ATH_ANT_DIV_COMB_LNA1_MINUS_LNA2; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index b14c54da56ed..1c95e8f75916 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -790,8 +790,7 @@ s32 brcmf_notify_escan_complete(struct brcmf_cfg80211_info *cfg, scan_request = cfg->scan_request; cfg->scan_request = NULL; - if (timer_pending(&cfg->escan_timeout)) - del_timer_sync(&cfg->escan_timeout); + timer_delete_sync(&cfg->escan_timeout); if (fw_abort) { /* Do a scan abort to stop the driver's scan engine */ @@ -7781,6 +7780,7 @@ void brcmf_cfg80211_detach(struct brcmf_cfg80211_info *cfg) brcmf_btcoex_detach(cfg); wiphy_unregister(cfg->wiphy); wl_deinit_priv(cfg); + cancel_work_sync(&cfg->escan_timeout_work); brcmf_free_wiphy(cfg->wiphy); kfree(cfg); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c index 44344216a1a9..4deb242df7b3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c @@ -104,15 +104,17 @@ struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm) if (ret) return ERR_PTR(ret); - if (WARN_ON_ONCE(iwl_rx_packet_payload_len(cmd.resp_pkt) != resp_size)) + if (WARN_ON_ONCE(iwl_rx_packet_payload_len(cmd.resp_pkt) != + resp_size)) { + iwl_free_resp(&cmd); return ERR_PTR(-EIO); + } + + resp = kmemdup(cmd.resp_pkt->data, resp_size, GFP_KERNEL); + iwl_free_resp(&cmd); - resp = kzalloc(resp_size, GFP_KERNEL); if (!resp) return ERR_PTR(-ENOMEM); - memcpy(resp, cmd.resp_pkt->data, resp_size); - - iwl_free_resp(&cmd); return resp; } diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 6e73d3a00eec..8b4be2e4d1cf 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -287,6 +287,7 @@ static struct sk_buff *xennet_alloc_one_rx_buffer(struct netfront_queue *queue) return NULL; } skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE); + skb_mark_for_recycle(skb); /* Align ip header to a 16 bytes boundary */ skb_reserve(skb, NET_IP_ALIGN); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 8f06e5c1706b..960a31e3307a 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1185,7 +1185,7 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return effects; } -static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, +static void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects, struct nvme_command *cmd, int status) { if (effects & NVME_CMD_EFFECTS_CSE_MASK) { @@ -1201,6 +1201,8 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, nvme_queue_scan(ctrl); flush_work(&ctrl->scan_work); } + if (ns) + return; switch (cmd->common.opcode) { case nvme_admin_set_features: @@ -1235,7 +1237,7 @@ int nvme_execute_passthru_rq(struct request *rq) effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode); ret = nvme_execute_rq(disk, rq, false); if (effects) /* nothing to be done for zero cmd effects */ - nvme_passthru_end(ctrl, effects, cmd, ret); + nvme_passthru_end(ctrl, ns, effects, cmd, ret); return ret; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index fd20f3fdb159..7bb74112fef3 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3339,6 +3339,9 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_BOGUS_NID, }, { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */ + .driver_data = NVME_QUIRK_NO_DEEPEST_PS | + NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */ .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, { PCI_DEVICE(0x1bb1, 0x0100), /* Seagate Nytro Flash Storage */ diff --git a/drivers/nvmem/meson-efuse.c b/drivers/nvmem/meson-efuse.c index d6b533497ce1..ba2714bef8d0 100644 --- a/drivers/nvmem/meson-efuse.c +++ b/drivers/nvmem/meson-efuse.c @@ -47,7 +47,6 @@ static int meson_efuse_probe(struct platform_device *pdev) struct nvmem_config *econfig; struct clk *clk; unsigned int size; - int ret; sm_np = of_parse_phandle(pdev->dev.of_node, "secure-monitor", 0); if (!sm_np) { @@ -60,27 +59,9 @@ static int meson_efuse_probe(struct platform_device *pdev) if (!fw) return -EPROBE_DEFER; - clk = devm_clk_get(dev, NULL); - if (IS_ERR(clk)) { - ret = PTR_ERR(clk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get efuse gate"); - return ret; - } - - ret = clk_prepare_enable(clk); - if (ret) { - dev_err(dev, "failed to enable gate"); - return ret; - } - - ret = devm_add_action_or_reset(dev, - (void(*)(void *))clk_disable_unprepare, - clk); - if (ret) { - dev_err(dev, "failed to add disable callback"); - return ret; - } + clk = devm_clk_get_enabled(dev, NULL); + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), "failed to get efuse gate"); if (meson_sm_call(fw, SM_EFUSE_USER_MAX, &size, 0, 0, 0, 0, 0) < 0) { dev_err(dev, "failed to get max user"); diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index ffb7b0446afd..a6358889fd1d 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) "OF: " fmt +#include <linux/device.h> #include <linux/of.h> #include <linux/spinlock.h> #include <linux/slab.h> @@ -678,6 +679,17 @@ void of_changeset_destroy(struct of_changeset *ocs) { struct of_changeset_entry *ce, *cen; + /* + * When a device is deleted, the device links to/from it are also queued + * for deletion. Until these device links are freed, the devices + * themselves aren't freed. If the device being deleted is due to an + * overlay change, this device might be holding a reference to a device + * node that will be freed. So, wait until all already pending device + * links are deleted before freeing a device node. This ensures we don't + * free any device node that has a non-zero reference count. + */ + device_link_wait_removal(); + list_for_each_entry_safe_reverse(ce, cen, &ocs->entries, node) __of_changeset_entry_destroy(ce); } diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index fcb1fdb22ffb..fc92d30a0ad9 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -658,8 +658,13 @@ int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep) nbars = (reg & PCI_REBAR_CTRL_NBAR_MASK) >> PCI_REBAR_CTRL_NBAR_SHIFT; + /* + * PCIe r6.0, sec 7.8.6.2 require us to support at least one + * size in the range from 1 MB to 512 GB. Advertise support + * for 1 MB BAR size only. + */ for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL) - dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, 0x0); + dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, BIT(4)); } dw_pcie_setup(pci); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index f44c0667a83c..46b82bacaff6 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -459,16 +459,21 @@ static void pci_device_remove(struct device *dev) struct pci_dev *pci_dev = to_pci_dev(dev); struct pci_driver *drv = pci_dev->driver; - if (drv) { - if (drv->remove) { - pm_runtime_get_sync(dev); - drv->remove(pci_dev); - pm_runtime_put_noidle(dev); - } - pcibios_free_irq(pci_dev); - pci_dev->driver = NULL; - pci_iov_remove(pci_dev); + if (drv->remove) { + pm_runtime_get_sync(dev); + /* + * If the driver provides a .runtime_idle() callback and it has + * started to run already, it may continue to run in parallel + * with the code below, so wait until all of the runtime PM + * activity has completed. + */ + pm_runtime_barrier(dev); + drv->remove(pci_dev); + pm_runtime_put_noidle(dev); } + pcibios_free_irq(pci_dev); + pci_dev->driver = NULL; + pci_iov_remove(pci_dev); /* Undo the runtime PM settings in local_pci_probe() */ pm_runtime_put_sync(dev); diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index cf0d4ba2e157..ab83f78f3eb1 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -335,11 +335,16 @@ void pci_dpc_init(struct pci_dev *pdev) return; pdev->dpc_rp_extensions = true; - pdev->dpc_rp_log_size = (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8; - if (pdev->dpc_rp_log_size < 4 || pdev->dpc_rp_log_size > 9) { - pci_err(pdev, "RP PIO log size %u is invalid\n", - pdev->dpc_rp_log_size); - pdev->dpc_rp_log_size = 0; + + /* Quirks may set dpc_rp_log_size if device or firmware is buggy */ + if (!pdev->dpc_rp_log_size) { + pdev->dpc_rp_log_size = + (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8; + if (pdev->dpc_rp_log_size < 4 || pdev->dpc_rp_log_size > 9) { + pci_err(pdev, "RP PIO log size %u is invalid\n", + pdev->dpc_rp_log_size); + pdev->dpc_rp_log_size = 0; + } } } diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index b576aa890c76..410fc44d79ee 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -13,6 +13,7 @@ #define dev_fmt(fmt) "AER: " fmt #include <linux/pci.h> +#include <linux/pm_runtime.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/errno.h> @@ -79,6 +80,18 @@ static int report_error_detected(struct pci_dev *dev, return 0; } +static int pci_pm_runtime_get_sync(struct pci_dev *pdev, void *data) +{ + pm_runtime_get_sync(&pdev->dev); + return 0; +} + +static int pci_pm_runtime_put(struct pci_dev *pdev, void *data) +{ + pm_runtime_put(&pdev->dev); + return 0; +} + static int report_frozen_detected(struct pci_dev *dev, void *data) { return report_error_detected(dev, pci_channel_io_frozen, data); @@ -195,6 +208,8 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, else bridge = pci_upstream_bridge(dev); + pci_walk_bridge(bridge, pci_pm_runtime_get_sync, NULL); + pci_dbg(bridge, "broadcast error_detected message\n"); if (state == pci_channel_io_frozen) { pci_walk_bridge(bridge, report_frozen_detected, &status); @@ -239,10 +254,15 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, pcie_clear_device_status(dev); pci_aer_clear_nonfatal_status(dev); } + + pci_walk_bridge(bridge, pci_pm_runtime_put, NULL); + pci_info(bridge, "device recovery successful\n"); return status; failed: + pci_walk_bridge(bridge, pci_pm_runtime_put, NULL); + pci_uevent_ers(bridge, PCI_ERS_RESULT_DISCONNECT); /* TODO: Should kernel panic here? */ diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 1b6484c90609..4d4267105cd2 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -12,6 +12,7 @@ * file, where their drivers can use them. */ +#include <linux/bitfield.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/export.h> @@ -5893,3 +5894,102 @@ static void nvidia_ion_ahci_fixup(struct pci_dev *pdev) pdev->dev_flags |= PCI_DEV_FLAGS_HAS_MSI_MASKING; } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0ab8, nvidia_ion_ahci_fixup); + +static void rom_bar_overlap_defect(struct pci_dev *dev) +{ + pci_info(dev, "working around ROM BAR overlap defect\n"); + dev->rom_bar_overlap = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1533, rom_bar_overlap_defect); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1536, rom_bar_overlap_defect); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1537, rom_bar_overlap_defect); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1538, rom_bar_overlap_defect); + +#ifdef CONFIG_PCIEASPM +/* + * Several Intel DG2 graphics devices advertise that they can only tolerate + * 1us latency when transitioning from L1 to L0, which may prevent ASPM L1 + * from being enabled. But in fact these devices can tolerate unlimited + * latency. Override their Device Capabilities value to allow ASPM L1 to + * be enabled. + */ +static void aspm_l1_acceptable_latency(struct pci_dev *dev) +{ + u32 l1_lat = FIELD_GET(PCI_EXP_DEVCAP_L1, dev->devcap); + + if (l1_lat < 7) { + dev->devcap |= FIELD_PREP(PCI_EXP_DEVCAP_L1, 7); + pci_info(dev, "ASPM: overriding L1 acceptable latency from %#x to 0x7\n", + l1_lat); + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f80, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f81, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f82, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f83, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f84, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f85, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f86, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f87, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f88, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5690, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5691, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5692, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5693, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5694, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5695, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a0, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a1, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a2, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a3, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a4, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a5, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a6, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56b0, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56b1, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56c0, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56c1, aspm_l1_acceptable_latency); +#endif + +#ifdef CONFIG_PCIE_DPC +/* + * Intel Ice Lake, Tiger Lake and Alder Lake BIOS has a bug that clears + * the DPC RP PIO Log Size of the integrated Thunderbolt PCIe Root + * Ports. + */ +static void dpc_log_size(struct pci_dev *dev) +{ + u16 dpc, val; + + dpc = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_DPC); + if (!dpc) + return; + + pci_read_config_word(dev, dpc + PCI_EXP_DPC_CAP, &val); + if (!(val & PCI_EXP_DPC_CAP_RP_EXT)) + return; + + if (!((val & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8)) { + pci_info(dev, "Overriding RP PIO Log Size to 4\n"); + dev->dpc_rp_log_size = 4; + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x461f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x462f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x463f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x466e, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1d, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a21, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a23, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a23, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a25, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a27, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a29, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2b, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2d, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa73f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa76e, dpc_log_size); +#endif diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 875d50c16f19..b492e67c3d87 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -75,12 +75,16 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno) * as zero when disabled, so don't update ROM BARs unless * they're enabled. See * https://lore.kernel.org/r/43147B3D.1030309@vc.cvut.cz/ + * But we must update ROM BAR for buggy devices where even a + * disabled ROM can conflict with other BARs. */ - if (!(res->flags & IORESOURCE_ROM_ENABLE)) + if (!(res->flags & IORESOURCE_ROM_ENABLE) && + !dev->rom_bar_overlap) return; reg = dev->rom_base_reg; - new |= PCI_ROM_ADDRESS_ENABLE; + if (res->flags & IORESOURCE_ROM_ENABLE) + new |= PCI_ROM_ADDRESS_ENABLE; } else return; diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 119e2c039225..bf7706bf101a 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -1485,6 +1485,19 @@ int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl, } EXPORT_SYMBOL_GPL(tegra_xusb_padctl_get_usb3_companion); +int tegra_xusb_padctl_get_port_number(struct phy *phy) +{ + struct tegra_xusb_lane *lane; + + if (!phy) + return -ENODEV; + + lane = phy_get_drvdata(phy); + + return lane->index; +} +EXPORT_SYMBOL_GPL(tegra_xusb_padctl_get_port_number); + MODULE_AUTHOR("Thierry Reding <treding@nvidia.com>"); MODULE_DESCRIPTION("Tegra XUSB Pad Controller driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/pinctrl/renesas/core.c b/drivers/pinctrl/renesas/core.c index 75fc420b6bdf..8d3b75231f39 100644 --- a/drivers/pinctrl/renesas/core.c +++ b/drivers/pinctrl/renesas/core.c @@ -868,9 +868,11 @@ static void __init sh_pfc_check_cfg_reg(const char *drvname, sh_pfc_err("reg 0x%x: var_field_width declares %u instead of %u bits\n", cfg_reg->reg, rw, cfg_reg->reg_width); - if (n != cfg_reg->nr_enum_ids) + if (n != cfg_reg->nr_enum_ids) { sh_pfc_err("reg 0x%x: enum_ids[] has %u instead of %u values\n", cfg_reg->reg, cfg_reg->nr_enum_ids, n); + n = cfg_reg->nr_enum_ids; + } check_enum_ids: sh_pfc_check_reg_enums(drvname, cfg_reg->reg, cfg_reg->enum_ids, n); diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c index 6fb3e597c57a..4e9d3f25c35d 100644 --- a/drivers/platform/x86/intel/vbtn.c +++ b/drivers/platform/x86/intel/vbtn.c @@ -136,8 +136,6 @@ static int intel_vbtn_input_setup(struct platform_device *device) priv->switches_dev->id.bustype = BUS_HOST; if (priv->has_switches) { - detect_tablet_mode(&device->dev); - ret = input_register_device(priv->switches_dev); if (ret) return ret; @@ -316,6 +314,9 @@ static int intel_vbtn_probe(struct platform_device *device) if (ACPI_FAILURE(status)) dev_err(&device->dev, "Error VBDL failed with ACPI status %d\n", status); } + // Check switches after buttons since VBDL may have side effects. + if (has_switches) + detect_tablet_mode(&device->dev); device_init_wakeup(&device->dev, true); /* diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 08a9b802be71..161bd1944104 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -1154,6 +1154,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* Chuwi Vi8 dual-boot (CWI506) */ + .driver_data = (void *)&chuwi_vi8_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "i86"), + DMI_MATCH(DMI_BIOS_VERSION, "CHUWI2.D86JHBNR02"), + }, + }, + { /* Chuwi Vi8 Plus (CWI519) */ .driver_data = (void *)&chuwi_vi8_plus_data, .matches = { diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 17b3f1ea3a5c..fb80b7593c59 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -575,6 +575,7 @@ static inline struct zcrypt_queue *zcrypt_pick_queue(struct zcrypt_card *zc, { if (!zq || !try_module_get(zq->queue->ap_dev.device.driver->owner)) return NULL; + zcrypt_card_get(zc); zcrypt_queue_get(zq); get_device(&zq->queue->ap_dev.device); atomic_add(weight, &zc->load); @@ -594,6 +595,7 @@ static inline void zcrypt_drop_queue(struct zcrypt_card *zc, atomic_sub(weight, &zq->load); put_device(&zq->queue->ap_dev.device); zcrypt_queue_put(zq); + zcrypt_card_put(zc); module_put(mod); } diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 62e7576bff53..c1346c4e2242 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -1142,6 +1142,20 @@ static int qeth_check_irb_error(struct qeth_card *card, struct ccw_device *cdev, } } +/** + * qeth_irq() - qeth interrupt handler + * @cdev: ccw device + * @intparm: expect pointer to iob + * @irb: Interruption Response Block + * + * In the good path: + * corresponding qeth channel is locked with last used iob as active_cmd. + * But this function is also called for error interrupts. + * + * Caller ensures that: + * Interrupts are disabled; ccw device lock is held; + * + */ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, struct irb *irb) { @@ -1183,11 +1197,10 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, iob = (struct qeth_cmd_buffer *) (addr_t)intparm; } - qeth_unlock_channel(card, channel); - rc = qeth_check_irb_error(card, cdev, irb); if (rc) { /* IO was terminated, free its resources. */ + qeth_unlock_channel(card, channel); if (iob) qeth_cancel_cmd(iob, rc); return; @@ -1231,6 +1244,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, rc = qeth_get_problem(card, cdev, irb); if (rc) { card->read_or_write_problem = 1; + qeth_unlock_channel(card, channel); if (iob) qeth_cancel_cmd(iob, rc); qeth_clear_ipacmd_list(card); @@ -1239,6 +1253,26 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, } } + if (scsw_cmd_is_valid_cc(&irb->scsw) && irb->scsw.cmd.cc == 1 && iob) { + /* channel command hasn't started: retry. + * active_cmd is still set to last iob + */ + QETH_CARD_TEXT(card, 2, "irqcc1"); + rc = ccw_device_start_timeout(cdev, __ccw_from_cmd(iob), + (addr_t)iob, 0, 0, iob->timeout); + if (rc) { + QETH_DBF_MESSAGE(2, + "ccw retry on %x failed, rc = %i\n", + CARD_DEVID(card), rc); + QETH_CARD_TEXT_(card, 2, " err%d", rc); + qeth_unlock_channel(card, channel); + qeth_cancel_cmd(iob, rc); + } + return; + } + + qeth_unlock_channel(card, channel); + if (iob) { /* sanity check: */ if (irb->scsw.cmd.count > iob->length) { diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 1b285ce62f8a..4caee4e32461 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -334,12 +334,13 @@ static void scsi_host_dev_release(struct device *dev) if (shost->shost_state == SHOST_CREATED) { /* - * Free the shost_dev device name here if scsi_host_alloc() - * and scsi_host_put() have been called but neither + * Free the shost_dev device name and remove the proc host dir + * here if scsi_host_{alloc,put}() have been called but neither * scsi_host_add() nor scsi_host_remove() has been called. * This avoids that the memory allocated for the shost_dev - * name is leaked. + * name as well as the proc dir structure are leaked. */ + scsi_proc_hostdir_rm(shost->hostt); kfree(dev_name(&shost->shost_dev)); } diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index 2bd35a7424c2..9b862f1254a4 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -724,8 +724,10 @@ lpfc_rcv_padisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, /* Save the ELS cmd */ elsiocb->drvrTimeout = cmd; - lpfc_sli4_resume_rpi(ndlp, - lpfc_mbx_cmpl_resume_rpi, elsiocb); + if (lpfc_sli4_resume_rpi(ndlp, + lpfc_mbx_cmpl_resume_rpi, + elsiocb)) + kfree(elsiocb); goto out; } } diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index 6e3dd0b9bcfa..c58669c9346c 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -1586,7 +1586,7 @@ lpfc_nvmet_setup_io_context(struct lpfc_hba *phba) wqe = &nvmewqe->wqe; /* Initialize WQE */ - memset(wqe, 0, sizeof(union lpfc_wqe)); + memset(wqe, 0, sizeof(*wqe)); ctx_buf->iocbq->context1 = NULL; spin_lock(&phba->sli4_hba.sgl_list_lock); diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c index 386256369dfc..2a61cb726883 100644 --- a/drivers/scsi/myrb.c +++ b/drivers/scsi/myrb.c @@ -1775,9 +1775,9 @@ static ssize_t raid_state_show(struct device *dev, name = myrb_devstate_name(ldev_info->state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->state); } else { struct myrb_pdev_state *pdev_info = sdev->hostdata; @@ -1796,9 +1796,9 @@ static ssize_t raid_state_show(struct device *dev, else name = myrb_devstate_name(pdev_info->state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", pdev_info->state); } return ret; @@ -1886,11 +1886,11 @@ static ssize_t raid_level_show(struct device *dev, name = myrb_raidlevel_name(ldev_info->raid_level); if (!name) - return snprintf(buf, 32, "Invalid (%02X)\n", + return snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->state); - return snprintf(buf, 32, "%s\n", name); + return snprintf(buf, 64, "%s\n", name); } - return snprintf(buf, 32, "Physical Drive\n"); + return snprintf(buf, 64, "Physical Drive\n"); } static DEVICE_ATTR_RO(raid_level); @@ -1903,15 +1903,15 @@ static ssize_t rebuild_show(struct device *dev, unsigned char status; if (sdev->channel < myrb_logical_channel(sdev->host)) - return snprintf(buf, 32, "physical device - not rebuilding\n"); + return snprintf(buf, 64, "physical device - not rebuilding\n"); status = myrb_get_rbld_progress(cb, &rbld_buf); if (rbld_buf.ldev_num != sdev->id || status != MYRB_STATUS_SUCCESS) - return snprintf(buf, 32, "not rebuilding\n"); + return snprintf(buf, 64, "not rebuilding\n"); - return snprintf(buf, 32, "rebuilding block %u of %u\n", + return snprintf(buf, 64, "rebuilding block %u of %u\n", rbld_buf.ldev_size - rbld_buf.blocks_left, rbld_buf.ldev_size); } diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c index a4d244ee4548..3f05f13fb107 100644 --- a/drivers/scsi/myrs.c +++ b/drivers/scsi/myrs.c @@ -949,9 +949,9 @@ static ssize_t raid_state_show(struct device *dev, name = myrs_devstate_name(ldev_info->dev_state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->dev_state); } else { struct myrs_pdev_info *pdev_info; @@ -960,9 +960,9 @@ static ssize_t raid_state_show(struct device *dev, pdev_info = sdev->hostdata; name = myrs_devstate_name(pdev_info->dev_state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", pdev_info->dev_state); } return ret; @@ -1068,13 +1068,13 @@ static ssize_t raid_level_show(struct device *dev, ldev_info = sdev->hostdata; name = myrs_raid_level_name(ldev_info->raid_level); if (!name) - return snprintf(buf, 32, "Invalid (%02X)\n", + return snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->dev_state); } else name = myrs_raid_level_name(MYRS_RAID_PHYSICAL); - return snprintf(buf, 32, "%s\n", name); + return snprintf(buf, 64, "%s\n", name); } static DEVICE_ATTR_RO(raid_level); @@ -1088,7 +1088,7 @@ static ssize_t rebuild_show(struct device *dev, unsigned char status; if (sdev->channel < cs->ctlr_info->physchan_present) - return snprintf(buf, 32, "physical device - not rebuilding\n"); + return snprintf(buf, 64, "physical device - not rebuilding\n"); ldev_info = sdev->hostdata; ldev_num = ldev_info->ldev_num; @@ -1100,11 +1100,11 @@ static ssize_t rebuild_show(struct device *dev, return -EIO; } if (ldev_info->rbld_active) { - return snprintf(buf, 32, "rebuilding block %zu of %zu\n", + return snprintf(buf, 64, "rebuilding block %zu of %zu\n", (size_t)ldev_info->rbld_lba, (size_t)ldev_info->cfg_devsize); } else - return snprintf(buf, 32, "not rebuilding\n"); + return snprintf(buf, 64, "not rebuilding\n"); } static ssize_t rebuild_store(struct device *dev, @@ -1192,7 +1192,7 @@ static ssize_t consistency_check_show(struct device *dev, unsigned short ldev_num; if (sdev->channel < cs->ctlr_info->physchan_present) - return snprintf(buf, 32, "physical device - not checking\n"); + return snprintf(buf, 64, "physical device - not checking\n"); ldev_info = sdev->hostdata; if (!ldev_info) @@ -1200,11 +1200,11 @@ static ssize_t consistency_check_show(struct device *dev, ldev_num = ldev_info->ldev_num; myrs_get_ldev_info(cs, ldev_num, ldev_info); if (ldev_info->cc_active) - return snprintf(buf, 32, "checking block %zu of %zu\n", + return snprintf(buf, 64, "checking block %zu of %zu\n", (size_t)ldev_info->cc_lba, (size_t)ldev_info->cfg_devsize); else - return snprintf(buf, 32, "not checking\n"); + return snprintf(buf, 64, "not checking\n"); } static ssize_t consistency_check_store(struct device *dev, diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index fe0e8b23a805..6e2b80934154 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2732,7 +2732,13 @@ qla2x00_dev_loss_tmo_callbk(struct fc_rport *rport) return; if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) { - qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16); + /* Will wait for wind down of adapter */ + ql_dbg(ql_dbg_aer, fcport->vha, 0x900c, + "%s pci offline detected (id %06x)\n", __func__, + fcport->d_id.b24); + qla_pci_set_eeh_busy(fcport->vha); + qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24, + 0, WAIT_TARGET); return; } } @@ -2754,7 +2760,11 @@ qla2x00_terminate_rport_io(struct fc_rport *rport) vha = fcport->vha; if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) { - qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16); + /* Will wait for wind down of adapter */ + ql_dbg(ql_dbg_aer, fcport->vha, 0x900b, + "%s pci offline detected (id %06x)\n", __func__, + fcport->d_id.b24); + qla_pci_set_eeh_busy(vha); qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24, 0, WAIT_TARGET); return; diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 3c876967e8b1..87ada9b44717 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -78,7 +78,7 @@ typedef union { #include "qla_nvme.h" #define QLA2XXX_DRIVER_NAME "qla2xxx" #define QLA2XXX_APIDEV "ql2xapidev" -#define QLA2XXX_MANUFACTURER "QLogic Corporation" +#define QLA2XXX_MANUFACTURER "Marvell" /* * We have MAILBOX_REGISTER_COUNT sized arrays in a few places, diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index 3861e41a8d2c..18376b50e349 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -44,7 +44,7 @@ extern int qla2x00_fabric_login(scsi_qla_host_t *, fc_port_t *, uint16_t *); extern int qla2x00_local_device_login(scsi_qla_host_t *, fc_port_t *); extern int qla24xx_els_dcmd_iocb(scsi_qla_host_t *, int, port_id_t); -extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *, bool); +extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *); extern void qla2x00_els_dcmd2_free(scsi_qla_host_t *vha, struct els_plogi *els_plogi); diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index d3742a83d2fd..b0f3bf42c340 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -1615,7 +1615,7 @@ qla2x00_hba_attributes(scsi_qla_host_t *vha, void *entries, eiter->type = cpu_to_be16(FDMI_HBA_MANUFACTURER); alen = scnprintf( eiter->a.manufacturer, sizeof(eiter->a.manufacturer), - "%s", "QLogic Corporation"); + "%s", QLA2XXX_MANUFACTURER); alen += FDMI_ATTR_ALIGNMENT(alen); alen += FDMI_ATTR_TYPELEN(eiter); eiter->len = cpu_to_be16(alen); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index b59d5b560a27..585df40e95bb 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1188,8 +1188,12 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport) return rval; done_free_sp: - /* ref: INIT */ - kref_put(&sp->cmd_kref, qla2x00_sp_release); + /* + * use qla24xx_async_gnl_sp_done to purge all pending gnl request. + * kref_put is call behind the scene. + */ + sp->u.iocb_cmd.u.mbx.in_mb[0] = MBS_COMMAND_ERROR; + qla24xx_async_gnl_sp_done(sp, QLA_COMMAND_ERROR); fcport->flags &= ~(FCF_ASYNC_SENT); done: fcport->flags &= ~(FCF_ASYNC_ACTIVE); @@ -2667,6 +2671,40 @@ exit: return rval; } +static void qla_enable_fce_trace(scsi_qla_host_t *vha) +{ + int rval; + struct qla_hw_data *ha = vha->hw; + + if (ha->fce) { + ha->flags.fce_enabled = 1; + memset(ha->fce, 0, fce_calc_size(ha->fce_bufs)); + rval = qla2x00_enable_fce_trace(vha, + ha->fce_dma, ha->fce_bufs, ha->fce_mb, &ha->fce_bufs); + + if (rval) { + ql_log(ql_log_warn, vha, 0x8033, + "Unable to reinitialize FCE (%d).\n", rval); + ha->flags.fce_enabled = 0; + } + } +} + +static void qla_enable_eft_trace(scsi_qla_host_t *vha) +{ + int rval; + struct qla_hw_data *ha = vha->hw; + + if (ha->eft) { + memset(ha->eft, 0, EFT_SIZE); + rval = qla2x00_enable_eft_trace(vha, ha->eft_dma, EFT_NUM_BUFFERS); + + if (rval) { + ql_log(ql_log_warn, vha, 0x8034, + "Unable to reinitialize EFT (%d).\n", rval); + } + } +} /* * qla2x00_initialize_adapter * Initialize board. @@ -3670,9 +3708,8 @@ qla24xx_chip_diag(scsi_qla_host_t *vha) } static void -qla2x00_init_fce_trace(scsi_qla_host_t *vha) +qla2x00_alloc_fce_trace(scsi_qla_host_t *vha) { - int rval; dma_addr_t tc_dma; void *tc; struct qla_hw_data *ha = vha->hw; @@ -3701,27 +3738,17 @@ qla2x00_init_fce_trace(scsi_qla_host_t *vha) return; } - rval = qla2x00_enable_fce_trace(vha, tc_dma, FCE_NUM_BUFFERS, - ha->fce_mb, &ha->fce_bufs); - if (rval) { - ql_log(ql_log_warn, vha, 0x00bf, - "Unable to initialize FCE (%d).\n", rval); - dma_free_coherent(&ha->pdev->dev, FCE_SIZE, tc, tc_dma); - return; - } - ql_dbg(ql_dbg_init, vha, 0x00c0, "Allocated (%d KB) for FCE...\n", FCE_SIZE / 1024); - ha->flags.fce_enabled = 1; ha->fce_dma = tc_dma; ha->fce = tc; + ha->fce_bufs = FCE_NUM_BUFFERS; } static void -qla2x00_init_eft_trace(scsi_qla_host_t *vha) +qla2x00_alloc_eft_trace(scsi_qla_host_t *vha) { - int rval; dma_addr_t tc_dma; void *tc; struct qla_hw_data *ha = vha->hw; @@ -3746,14 +3773,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *vha) return; } - rval = qla2x00_enable_eft_trace(vha, tc_dma, EFT_NUM_BUFFERS); - if (rval) { - ql_log(ql_log_warn, vha, 0x00c2, - "Unable to initialize EFT (%d).\n", rval); - dma_free_coherent(&ha->pdev->dev, EFT_SIZE, tc, tc_dma); - return; - } - ql_dbg(ql_dbg_init, vha, 0x00c3, "Allocated (%d KB) EFT ...\n", EFT_SIZE / 1024); @@ -3761,13 +3780,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *vha) ha->eft = tc; } -static void -qla2x00_alloc_offload_mem(scsi_qla_host_t *vha) -{ - qla2x00_init_fce_trace(vha); - qla2x00_init_eft_trace(vha); -} - void qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) { @@ -3822,10 +3834,10 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) if (ha->tgt.atio_ring) mq_size += ha->tgt.atio_q_length * sizeof(request_t); - qla2x00_init_fce_trace(vha); + qla2x00_alloc_fce_trace(vha); if (ha->fce) fce_size = sizeof(struct qla2xxx_fce_chain) + FCE_SIZE; - qla2x00_init_eft_trace(vha); + qla2x00_alloc_eft_trace(vha); if (ha->eft) eft_size = EFT_SIZE; } @@ -4255,7 +4267,6 @@ qla2x00_setup_chip(scsi_qla_host_t *vha) struct qla_hw_data *ha = vha->hw; struct device_reg_2xxx __iomem *reg = &ha->iobase->isp; unsigned long flags; - uint16_t fw_major_version; int done_once = 0; if (IS_P3P_TYPE(ha)) { @@ -4322,7 +4333,6 @@ execute_fw_with_lr: goto failed; enable_82xx_npiv: - fw_major_version = ha->fw_major_version; if (IS_P3P_TYPE(ha)) qla82xx_check_md_needed(vha); else @@ -4351,12 +4361,11 @@ enable_82xx_npiv: if (rval != QLA_SUCCESS) goto failed; - if (!fw_major_version && !(IS_P3P_TYPE(ha))) - qla2x00_alloc_offload_mem(vha); - if (ql2xallocfwdump && !(IS_P3P_TYPE(ha))) qla2x00_alloc_fw_dump(vha); + qla_enable_fce_trace(vha); + qla_enable_eft_trace(vha); } else { goto failed; } @@ -7568,12 +7577,12 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha) int qla2x00_abort_isp(scsi_qla_host_t *vha) { - int rval; uint8_t status = 0; struct qla_hw_data *ha = vha->hw; struct scsi_qla_host *vp, *tvp; struct req_que *req = ha->req_q_map[0]; unsigned long flags; + fc_port_t *fcport; if (vha->flags.online) { qla2x00_abort_isp_cleanup(vha); @@ -7639,6 +7648,15 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) "ISP Abort - ISP reg disconnect post nvmram config, exiting.\n"); return status; } + + /* User may have updated [fcp|nvme] prefer in flash */ + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (NVME_PRIORITY(ha, fcport)) + fcport->do_prli_nvme = 1; + else + fcport->do_prli_nvme = 0; + } + if (!qla2x00_restart_isp(vha)) { clear_bit(RESET_MARKER_NEEDED, &vha->dpc_flags); @@ -7659,31 +7677,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) if (IS_QLA81XX(ha) || IS_QLA8031(ha)) qla2x00_get_fw_version(vha); - if (ha->fce) { - ha->flags.fce_enabled = 1; - memset(ha->fce, 0, - fce_calc_size(ha->fce_bufs)); - rval = qla2x00_enable_fce_trace(vha, - ha->fce_dma, ha->fce_bufs, ha->fce_mb, - &ha->fce_bufs); - if (rval) { - ql_log(ql_log_warn, vha, 0x8033, - "Unable to reinitialize FCE " - "(%d).\n", rval); - ha->flags.fce_enabled = 0; - } - } - if (ha->eft) { - memset(ha->eft, 0, EFT_SIZE); - rval = qla2x00_enable_eft_trace(vha, - ha->eft_dma, EFT_NUM_BUFFERS); - if (rval) { - ql_log(ql_log_warn, vha, 0x8034, - "Unable to reinitialize EFT " - "(%d).\n", rval); - } - } } else { /* failed the ISP abort */ vha->flags.online = 1; if (test_bit(ISP_ABORT_RETRY, &vha->dpc_flags)) { @@ -7733,6 +7727,14 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) atomic_inc(&vp->vref_count); spin_unlock_irqrestore(&ha->vport_slock, flags); + /* User may have updated [fcp|nvme] prefer in flash */ + list_for_each_entry(fcport, &vp->vp_fcports, list) { + if (NVME_PRIORITY(ha, fcport)) + fcport->do_prli_nvme = 1; + else + fcport->do_prli_nvme = 0; + } + qla2x00_vp_abort_isp(vp); spin_lock_irqsave(&ha->vport_slock, flags); diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 9e524d52dc86..7bccd525ee19 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2588,6 +2588,33 @@ void qla2x00_sp_release(struct kref *kref) { struct srb *sp = container_of(kref, struct srb, cmd_kref); + struct scsi_qla_host *vha = sp->vha; + + switch (sp->type) { + case SRB_CT_PTHRU_CMD: + /* GPSC & GFPNID use fcport->ct_desc.ct_sns for both req & rsp */ + if (sp->u.iocb_cmd.u.ctarg.req && + (!sp->fcport || + sp->u.iocb_cmd.u.ctarg.req != sp->fcport->ct_desc.ct_sns)) { + dma_free_coherent(&vha->hw->pdev->dev, + sp->u.iocb_cmd.u.ctarg.req_allocated_size, + sp->u.iocb_cmd.u.ctarg.req, + sp->u.iocb_cmd.u.ctarg.req_dma); + sp->u.iocb_cmd.u.ctarg.req = NULL; + } + if (sp->u.iocb_cmd.u.ctarg.rsp && + (!sp->fcport || + sp->u.iocb_cmd.u.ctarg.rsp != sp->fcport->ct_desc.ct_sns)) { + dma_free_coherent(&vha->hw->pdev->dev, + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, + sp->u.iocb_cmd.u.ctarg.rsp, + sp->u.iocb_cmd.u.ctarg.rsp_dma); + sp->u.iocb_cmd.u.ctarg.rsp = NULL; + } + break; + default: + break; + } sp->free(sp); } @@ -2611,7 +2638,8 @@ static void qla2x00_els_dcmd_sp_free(srb_t *sp) { struct srb_iocb *elsio = &sp->u.iocb_cmd; - kfree(sp->fcport); + if (sp->fcport) + qla2x00_free_fcport(sp->fcport); if (elsio->u.els_logo.els_logo_pyld) dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE, @@ -2693,7 +2721,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, */ sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); if (!sp) { - kfree(fcport); + qla2x00_free_fcport(fcport); ql_log(ql_log_info, vha, 0x70e6, "SRB allocation failed\n"); return -ENOMEM; @@ -2724,6 +2752,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, if (!elsio->u.els_logo.els_logo_pyld) { /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); + qla2x00_free_fcport(fcport); return QLA_FUNCTION_FAILED; } @@ -2748,6 +2777,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, if (rval != QLA_SUCCESS) { /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); + qla2x00_free_fcport(fcport); return QLA_FUNCTION_FAILED; } @@ -3013,7 +3043,7 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res) int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, - fc_port_t *fcport, bool wait) + fc_port_t *fcport) { srb_t *sp; struct srb_iocb *elsio = NULL; @@ -3028,8 +3058,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (!sp) { ql_log(ql_log_info, vha, 0x70e6, "SRB allocation failed\n"); - fcport->flags &= ~FCF_ASYNC_ACTIVE; - return -ENOMEM; + goto done; } fcport->flags |= FCF_ASYNC_SENT; @@ -3038,9 +3067,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, ql_dbg(ql_dbg_io, vha, 0x3073, "%s Enter: PLOGI portid=%06x\n", __func__, fcport->d_id.b24); - if (wait) - sp->flags = SRB_WAKEUP_ON_COMP; - sp->type = SRB_ELS_DCMD; sp->name = "ELS_DCMD"; sp->fcport = fcport; @@ -3056,7 +3082,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (!elsio->u.els_plogi.els_plogi_pyld) { rval = QLA_FUNCTION_FAILED; - goto out; + goto done_free_sp; } resp_ptr = elsio->u.els_plogi.els_resp_pyld = @@ -3065,7 +3091,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (!elsio->u.els_plogi.els_resp_pyld) { rval = QLA_FUNCTION_FAILED; - goto out; + goto done_free_sp; } ql_dbg(ql_dbg_io, vha, 0x3073, "PLOGI %p %p\n", ptr, resp_ptr); @@ -3080,7 +3106,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (els_opcode == ELS_DCMD_PLOGI && DBELL_ACTIVE(vha)) { struct fc_els_flogi *p = ptr; - p->fl_csp.sp_features |= cpu_to_be16(FC_SP_FT_SEC); } @@ -3089,10 +3114,11 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, sizeof(*elsio->u.els_plogi.els_plogi_pyld)); - init_completion(&elsio->u.els_plogi.comp); rval = qla2x00_start_sp(sp); if (rval != QLA_SUCCESS) { - rval = QLA_FUNCTION_FAILED; + fcport->flags |= FCF_LOGIN_NEEDED; + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + goto done_free_sp; } else { ql_dbg(ql_dbg_disc, vha, 0x3074, "%s PLOGI sent, hdl=%x, loopid=%x, to port_id %06x from port_id %06x\n", @@ -3100,21 +3126,15 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, fcport->d_id.b24, vha->d_id.b24); } - if (wait) { - wait_for_completion(&elsio->u.els_plogi.comp); - - if (elsio->u.els_plogi.comp_status != CS_COMPLETE) - rval = QLA_FUNCTION_FAILED; - } else { - goto done; - } + return rval; -out: - fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); +done_free_sp: qla2x00_els_dcmd2_free(vha, &elsio->u.els_plogi); /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); done: + fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); + qla2x00_set_fcport_disc_state(fcport, DSC_DELETED); return rval; } @@ -3916,7 +3936,7 @@ qla2x00_start_sp(srb_t *sp) return -EAGAIN; } - pkt = __qla2x00_alloc_iocbs(sp->qpair, sp); + pkt = qla2x00_alloc_iocbs_ready(sp->qpair, sp); if (!pkt) { rval = -EAGAIN; ql_log(ql_log_warn, vha, 0x700c, diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 511f31611aed..d2ff54beb7cd 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -194,7 +194,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) if (ha->flags.purge_mbox || chip_reset != ha->chip_reset || ha->flags.eeh_busy) { ql_log(ql_log_warn, vha, 0xd035, - "Error detected: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n", + "Purge mbox: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n", ha->flags.purge_mbox, ha->flags.eeh_busy, mcp->mb[0]); rval = QLA_ABORTED; goto premature_exit; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index a2d3f8bb63a0..f418d43ee841 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -5530,7 +5530,7 @@ qla2x00_do_work(struct scsi_qla_host *vha) break; case QLA_EVT_ELS_PLOGI: qla24xx_els_dcmd2_iocb(vha, ELS_DCMD_PLOGI, - e->u.fcport.fcport, false); + e->u.fcport.fcport); break; case QLA_EVT_SA_REPLACE: rc = qla24xx_issue_sa_replace_iocb(vha, e); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index ef46dce73978..aac36e730a5a 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1083,6 +1083,16 @@ void qlt_free_session_done(struct work_struct *work) "%s: sess %p logout completed\n", __func__, sess); } + /* check for any straggling io left behind */ + if (!(sess->flags & FCF_FCP2_DEVICE) && + qla2x00_eh_wait_for_pending_commands(sess->vha, sess->d_id.b24, 0, WAIT_TARGET)) { + ql_log(ql_log_warn, vha, 0x3027, + "IO not return. Resetting.\n"); + set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags); + qla2xxx_wake_dpc(vha); + qla2x00_wait_for_chip_reset(vha); + } + if (sess->logo_ack_needed) { sess->logo_ack_needed = 0; qla24xx_async_notify_ack(vha, sess, diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index 78480e332ab8..d1e3de844812 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -436,8 +436,8 @@ static int slim_device_alloc_laddr(struct slim_device *sbdev, if (ret < 0) goto err; } else if (report_present) { - ret = ida_simple_get(&ctrl->laddr_ida, - 0, SLIM_LA_MANAGER - 1, GFP_KERNEL); + ret = ida_alloc_max(&ctrl->laddr_ida, + SLIM_LA_MANAGER - 1, GFP_KERNEL); if (ret < 0) goto err; diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index fde4edd83c14..7e9074519ad2 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -991,7 +991,7 @@ struct qman_portal { /* linked-list of CSCN handlers. */ struct list_head cgr_cbs; /* list lock */ - spinlock_t cgr_lock; + raw_spinlock_t cgr_lock; struct work_struct congestion_work; struct work_struct mr_work; char irqname[MAX_IRQNAME]; @@ -1281,7 +1281,7 @@ static int qman_create_portal(struct qman_portal *portal, /* if the given mask is NULL, assume all CGRs can be seen */ qman_cgrs_fill(&portal->cgrs[0]); INIT_LIST_HEAD(&portal->cgr_cbs); - spin_lock_init(&portal->cgr_lock); + raw_spin_lock_init(&portal->cgr_lock); INIT_WORK(&portal->congestion_work, qm_congestion_task); INIT_WORK(&portal->mr_work, qm_mr_process_task); portal->bits = 0; @@ -1456,11 +1456,14 @@ static void qm_congestion_task(struct work_struct *work) union qm_mc_result *mcr; struct qman_cgr *cgr; - spin_lock(&p->cgr_lock); + /* + * FIXME: QM_MCR_TIMEOUT is 10ms, which is too long for a raw spinlock! + */ + raw_spin_lock_irq(&p->cgr_lock); qm_mc_start(&p->p); qm_mc_commit(&p->p, QM_MCC_VERB_QUERYCONGESTION); if (!qm_mc_result_timeout(&p->p, &mcr)) { - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); dev_crit(p->config->dev, "QUERYCONGESTION timeout\n"); qman_p_irqsource_add(p, QM_PIRQ_CSCI); return; @@ -1476,7 +1479,7 @@ static void qm_congestion_task(struct work_struct *work) list_for_each_entry(cgr, &p->cgr_cbs, node) if (cgr->cb && qman_cgrs_get(&c, cgr->cgrid)) cgr->cb(p, cgr, qman_cgrs_get(&rr, cgr->cgrid)); - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); qman_p_irqsource_add(p, QM_PIRQ_CSCI); } @@ -2440,7 +2443,7 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags, preempt_enable(); cgr->chan = p->config->channel; - spin_lock(&p->cgr_lock); + raw_spin_lock_irq(&p->cgr_lock); if (opts) { struct qm_mcc_initcgr local_opts = *opts; @@ -2477,19 +2480,14 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags, qman_cgrs_get(&p->cgrs[1], cgr->cgrid)) cgr->cb(p, cgr, 1); out: - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); put_affine_portal(); return ret; } EXPORT_SYMBOL(qman_create_cgr); -int qman_delete_cgr(struct qman_cgr *cgr) +static struct qman_portal *qman_cgr_get_affine_portal(struct qman_cgr *cgr) { - unsigned long irqflags; - struct qm_mcr_querycgr cgr_state; - struct qm_mcc_initcgr local_opts; - int ret = 0; - struct qman_cgr *i; struct qman_portal *p = get_affine_portal(); if (cgr->chan != p->config->channel) { @@ -2497,12 +2495,27 @@ int qman_delete_cgr(struct qman_cgr *cgr) dev_err(p->config->dev, "CGR not owned by current portal"); dev_dbg(p->config->dev, " create 0x%x, delete 0x%x\n", cgr->chan, p->config->channel); - - ret = -EINVAL; - goto put_portal; + put_affine_portal(); + return NULL; } + + return p; +} + +int qman_delete_cgr(struct qman_cgr *cgr) +{ + unsigned long irqflags; + struct qm_mcr_querycgr cgr_state; + struct qm_mcc_initcgr local_opts; + int ret = 0; + struct qman_cgr *i; + struct qman_portal *p = qman_cgr_get_affine_portal(cgr); + + if (!p) + return -EINVAL; + memset(&local_opts, 0, sizeof(struct qm_mcc_initcgr)); - spin_lock_irqsave(&p->cgr_lock, irqflags); + raw_spin_lock_irqsave(&p->cgr_lock, irqflags); list_del(&cgr->node); /* * If there are no other CGR objects for this CGRID in the list, @@ -2527,8 +2540,7 @@ int qman_delete_cgr(struct qman_cgr *cgr) /* add back to the list */ list_add(&cgr->node, &p->cgr_cbs); release_lock: - spin_unlock_irqrestore(&p->cgr_lock, irqflags); -put_portal: + raw_spin_unlock_irqrestore(&p->cgr_lock, irqflags); put_affine_portal(); return ret; } @@ -2559,6 +2571,54 @@ void qman_delete_cgr_safe(struct qman_cgr *cgr) } EXPORT_SYMBOL(qman_delete_cgr_safe); +static int qman_update_cgr(struct qman_cgr *cgr, struct qm_mcc_initcgr *opts) +{ + int ret; + unsigned long irqflags; + struct qman_portal *p = qman_cgr_get_affine_portal(cgr); + + if (!p) + return -EINVAL; + + raw_spin_lock_irqsave(&p->cgr_lock, irqflags); + ret = qm_modify_cgr(cgr, 0, opts); + raw_spin_unlock_irqrestore(&p->cgr_lock, irqflags); + put_affine_portal(); + return ret; +} + +struct update_cgr_params { + struct qman_cgr *cgr; + struct qm_mcc_initcgr *opts; + int ret; +}; + +static void qman_update_cgr_smp_call(void *p) +{ + struct update_cgr_params *params = p; + + params->ret = qman_update_cgr(params->cgr, params->opts); +} + +int qman_update_cgr_safe(struct qman_cgr *cgr, struct qm_mcc_initcgr *opts) +{ + struct update_cgr_params params = { + .cgr = cgr, + .opts = opts, + }; + + preempt_disable(); + if (qman_cgr_cpus[cgr->cgrid] != smp_processor_id()) + smp_call_function_single(qman_cgr_cpus[cgr->cgrid], + qman_update_cgr_smp_call, ¶ms, + true); + else + params.ret = qman_update_cgr(cgr, opts); + preempt_enable(); + return params.ret; +} +EXPORT_SYMBOL(qman_update_cgr_safe); + /* Cleanup FQs */ static int _qm_mr_consume_and_match_verb(struct qm_portal *p, int v) diff --git a/drivers/staging/media/ipu3/ipu3-v4l2.c b/drivers/staging/media/ipu3/ipu3-v4l2.c index ed091418f7e7..5110e95923cc 100644 --- a/drivers/staging/media/ipu3/ipu3-v4l2.c +++ b/drivers/staging/media/ipu3/ipu3-v4l2.c @@ -1068,6 +1068,11 @@ static int imgu_v4l2_subdev_register(struct imgu_device *imgu, struct imgu_media_pipe *imgu_pipe = &imgu->imgu_pipe[pipe]; /* Initialize subdev media entity */ + imgu_sd->subdev.entity.ops = &imgu_media_ops; + for (i = 0; i < IMGU_NODE_NUM; i++) { + imgu_sd->subdev_pads[i].flags = imgu_pipe->nodes[i].output ? + MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE; + } r = media_entity_pads_init(&imgu_sd->subdev.entity, IMGU_NODE_NUM, imgu_sd->subdev_pads); if (r) { @@ -1075,11 +1080,6 @@ static int imgu_v4l2_subdev_register(struct imgu_device *imgu, "failed initialize subdev media entity (%d)\n", r); return r; } - imgu_sd->subdev.entity.ops = &imgu_media_ops; - for (i = 0; i < IMGU_NODE_NUM; i++) { - imgu_sd->subdev_pads[i].flags = imgu_pipe->nodes[i].output ? - MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE; - } /* Initialize subdev */ v4l2_subdev_init(&imgu_sd->subdev, &imgu_subdev_ops); @@ -1174,15 +1174,15 @@ static int imgu_v4l2_node_setup(struct imgu_device *imgu, unsigned int pipe, } /* Initialize media entities */ + node->vdev_pad.flags = node->output ? + MEDIA_PAD_FL_SOURCE : MEDIA_PAD_FL_SINK; + vdev->entity.ops = NULL; r = media_entity_pads_init(&vdev->entity, 1, &node->vdev_pad); if (r) { dev_err(dev, "failed initialize media entity (%d)\n", r); mutex_destroy(&node->lock); return r; } - node->vdev_pad.flags = node->output ? - MEDIA_PAD_FL_SOURCE : MEDIA_PAD_FL_SINK; - vdev->entity.ops = NULL; /* Initialize vbq */ vbq->type = node->vdev_fmt.type; diff --git a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c index 76d3f0399964..168ee6a59d5f 100644 --- a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c +++ b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c @@ -940,8 +940,9 @@ static int create_component(struct vchiq_mmal_instance *instance, /* build component create message */ m.h.type = MMAL_MSG_TYPE_COMPONENT_CREATE; m.u.component_create.client_component = component->client_component; - strncpy(m.u.component_create.name, name, - sizeof(m.u.component_create.name)); + strscpy_pad(m.u.component_create.name, name, + sizeof(m.u.component_create.name)); + m.u.component_create.pid = 0; ret = send_synchronous_mmal_msg(instance, &m, sizeof(m.u.component_create), diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c index 8957065ea730..8be1dfcc06bd 100644 --- a/drivers/tee/optee/device.c +++ b/drivers/tee/optee/device.c @@ -90,13 +90,14 @@ static int optee_register_device(const uuid_t *device_uuid, u32 func) if (rc) { pr_err("device registration failed, err: %d\n", rc); put_device(&optee_device->dev); + return rc; } if (func == PTA_CMD_GET_DEVICES_SUPP) device_create_file(&optee_device->dev, &dev_attr_need_supplicant); - return rc; + return 0; } static int __optee_enumerate_devices(u32 func) diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c index d38a80adec73..5be79b5d788e 100644 --- a/drivers/thermal/devfreq_cooling.c +++ b/drivers/thermal/devfreq_cooling.c @@ -199,7 +199,7 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd res = dfc->power_ops->get_real_power(df, power, freq, voltage); if (!res) { - state = dfc->capped_state; + state = dfc->max_state - dfc->capped_state; dfc->res_util = dfc->em_pd->table[state].power; dfc->res_util *= SCALE_ERROR_MITIGATION; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 2337402f95df..4ff3010a82ea 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2827,6 +2827,9 @@ static int gsmld_open(struct tty_struct *tty) { struct gsm_mux *gsm; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (tty->ops->write == NULL) return -EINVAL; diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index cb897a6289ba..45b9ad9c5a52 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1366,9 +1366,6 @@ static void autoconfig_irq(struct uart_8250_port *up) inb_p(ICP); } - if (uart_console(port)) - console_lock(); - /* forget possible initially masked and pending IRQ */ probe_irq_off(probe_irq_on()); save_mcr = serial8250_in_MCR(up); @@ -1399,9 +1396,6 @@ static void autoconfig_irq(struct uart_8250_port *up) if (port->flags & UPF_FOURPORT) outb_p(save_ICP, ICP); - if (uart_console(port)) - console_unlock(); - port->irq = (irq > 0) ? irq : 0; } diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index e0d576b88d7d..9f1be9ce47e0 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2237,9 +2237,12 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios, lpuart32_write(&sport->port, bd, UARTBAUD); lpuart32_serial_setbrg(sport, baud); - lpuart32_write(&sport->port, modem, UARTMODIR); - lpuart32_write(&sport->port, ctrl, UARTCTRL); + /* disable CTS before enabling UARTCTRL_TE to avoid pending idle preamble */ + lpuart32_write(&sport->port, modem & ~UARTMODIR_TXCTSE, UARTMODIR); /* restore control register */ + lpuart32_write(&sport->port, ctrl, UARTCTRL); + /* re-enable the CTS if needed */ + lpuart32_write(&sport->port, modem, UARTMODIR); if (old && sport->lpuart_dma_rx_use) { if (!lpuart_start_rx_dma(sport)) diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 4504b5fcc171..0587beaaea08 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -491,8 +491,7 @@ static void imx_uart_stop_tx(struct uart_port *port) } } -/* called with port.lock taken and irqs off */ -static void imx_uart_stop_rx(struct uart_port *port) +static void imx_uart_stop_rx_with_loopback_ctrl(struct uart_port *port, bool loopback) { struct imx_port *sport = (struct imx_port *)port; u32 ucr1, ucr2, ucr4, uts; @@ -514,7 +513,7 @@ static void imx_uart_stop_rx(struct uart_port *port) /* See SER_RS485_ENABLED/UTS_LOOP comment in imx_uart_probe() */ if (port->rs485.flags & SER_RS485_ENABLED && port->rs485.flags & SER_RS485_RTS_ON_SEND && - sport->have_rtscts && !sport->have_rtsgpio) { + sport->have_rtscts && !sport->have_rtsgpio && loopback) { uts = imx_uart_readl(sport, imx_uart_uts_reg(sport)); uts |= UTS_LOOP; imx_uart_writel(sport, uts, imx_uart_uts_reg(sport)); @@ -527,6 +526,16 @@ static void imx_uart_stop_rx(struct uart_port *port) } /* called with port.lock taken and irqs off */ +static void imx_uart_stop_rx(struct uart_port *port) +{ + /* + * Stop RX and enable loopback in order to make sure RS485 bus + * is not blocked. Se comment in imx_uart_probe(). + */ + imx_uart_stop_rx_with_loopback_ctrl(port, true); +} + +/* called with port.lock taken and irqs off */ static void imx_uart_enable_ms(struct uart_port *port) { struct imx_port *sport = (struct imx_port *)port; @@ -714,8 +723,13 @@ static void imx_uart_start_tx(struct uart_port *port) imx_uart_rts_inactive(sport, &ucr2); imx_uart_writel(sport, ucr2, UCR2); + /* + * Since we are about to transmit we can not stop RX + * with loopback enabled because that will make our + * transmitted data being just looped to RX. + */ if (!(port->rs485.flags & SER_RS485_RX_DURING_TX)) - imx_uart_stop_rx(port); + imx_uart_stop_rx_with_loopback_ctrl(port, false); sport->tx_state = WAIT_AFTER_RTS; start_hrtimer_ms(&sport->trigger_start_tx, diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 8c09c97f9814..0066a0e23516 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -376,9 +376,7 @@ static void sc16is7xx_fifo_read(struct uart_port *port, unsigned int rxlen) const u8 line = sc16is7xx_line(port); u8 addr = (SC16IS7XX_RHR_REG << SC16IS7XX_REG_SHIFT) | line; - regcache_cache_bypass(s->regmap, true); - regmap_raw_read(s->regmap, addr, s->buf, rxlen); - regcache_cache_bypass(s->regmap, false); + regmap_noinc_read(s->regmap, addr, s->buf, rxlen); } static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send) @@ -394,9 +392,7 @@ static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send) if (unlikely(!to_send)) return; - regcache_cache_bypass(s->regmap, true); - regmap_raw_write(s->regmap, addr, s->buf, to_send); - regcache_cache_bypass(s->regmap, false); + regmap_noinc_write(s->regmap, addr, s->buf, to_send); } static void sc16is7xx_port_update(struct uart_port *port, u8 reg, @@ -489,6 +485,11 @@ static bool sc16is7xx_regmap_precious(struct device *dev, unsigned int reg) return false; } +static bool sc16is7xx_regmap_noinc(struct device *dev, unsigned int reg) +{ + return reg == SC16IS7XX_RHR_REG; +} + static int sc16is7xx_set_baud(struct uart_port *port, int baud) { struct sc16is7xx_port *s = dev_get_drvdata(port->dev); @@ -1439,6 +1440,8 @@ static struct regmap_config regcfg = { .cache_type = REGCACHE_RBTREE, .volatile_reg = sc16is7xx_regmap_volatile, .precious_reg = sc16is7xx_regmap_precious, + .writeable_noinc_reg = sc16is7xx_regmap_noinc, + .readable_noinc_reg = sc16is7xx_regmap_noinc, }; #ifdef CONFIG_SERIAL_SC16IS7XX_SPI diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 45b721abaa2f..b638b2fd2d3d 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2410,7 +2410,12 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, port->type = PORT_UNKNOWN; flags |= UART_CONFIG_TYPE; } + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); port->ops->config_port(port, flags); + if (uart_console(port)) + console_unlock(); } if (port->type != PORT_UNKNOWN) { @@ -2418,6 +2423,10 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_report_port(drv, port); + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); + /* Power up port for set_mctrl() */ uart_change_pm(state, UART_PM_STATE_ON); @@ -2434,6 +2443,9 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, port->rs485_config(port, &port->rs485); spin_unlock_irqrestore(&port->lock, flags); + if (uart_console(port)) + console_unlock(); + /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 442579f087c7..3dc2124bd02a 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -398,7 +398,7 @@ static void vc_uniscr_delete(struct vc_data *vc, unsigned int nr) char32_t *ln = uniscr->lines[vc->state.y]; unsigned int x = vc->state.x, cols = vc->vc_cols; - memcpy(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln)); + memmove(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln)); memset32(&ln[cols - nr], ' ', nr); } } diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 0d99ba64ea52..38c2e6089e4c 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -485,6 +485,7 @@ out_free_mem: static int service_outstanding_interrupt(struct wdm_device *desc) { int rv = 0; + int used; /* submit read urb only if the device is waiting for it */ if (!desc->resp_count || !--desc->resp_count) @@ -499,7 +500,10 @@ static int service_outstanding_interrupt(struct wdm_device *desc) goto out; } - set_bit(WDM_RESPONDING, &desc->flags); + used = test_and_set_bit(WDM_RESPONDING, &desc->flags); + if (used) + goto out; + spin_unlock_irq(&desc->iuspin); rv = usb_submit_urb(desc->response, GFP_KERNEL); spin_lock_irq(&desc->iuspin); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 2cd0089660ea..a603e8a54196 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -116,7 +116,6 @@ EXPORT_SYMBOL_GPL(ehci_cf_port_reset_rwsem); #define HUB_DEBOUNCE_STEP 25 #define HUB_DEBOUNCE_STABLE 100 -static void hub_release(struct kref *kref); static int usb_reset_and_verify_device(struct usb_device *udev); static int hub_port_disable(struct usb_hub *hub, int port1, int set_state); static bool hub_port_warm_reset_required(struct usb_hub *hub, int port1, @@ -678,14 +677,14 @@ static void kick_hub_wq(struct usb_hub *hub) */ intf = to_usb_interface(hub->intfdev); usb_autopm_get_interface_no_resume(intf); - kref_get(&hub->kref); + hub_get(hub); if (queue_work(hub_wq, &hub->events)) return; /* the work has already been scheduled */ usb_autopm_put_interface_async(intf); - kref_put(&hub->kref, hub_release); + hub_put(hub); } void usb_kick_hub_wq(struct usb_device *hdev) @@ -1053,7 +1052,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) goto init2; goto init3; } - kref_get(&hub->kref); + hub_get(hub); /* The superspeed hub except for root hub has to use Hub Depth * value as an offset into the route string to locate the bits @@ -1301,7 +1300,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) device_unlock(&hdev->dev); } - kref_put(&hub->kref, hub_release); + hub_put(hub); } /* Implement the continuations for the delays above */ @@ -1717,6 +1716,16 @@ static void hub_release(struct kref *kref) kfree(hub); } +void hub_get(struct usb_hub *hub) +{ + kref_get(&hub->kref); +} + +void hub_put(struct usb_hub *hub) +{ + kref_put(&hub->kref, hub_release); +} + static unsigned highspeed_hubs; static void hub_disconnect(struct usb_interface *intf) @@ -1763,7 +1772,7 @@ static void hub_disconnect(struct usb_interface *intf) if (hub->quirk_disable_autosuspend) usb_autopm_put_interface(intf); - kref_put(&hub->kref, hub_release); + hub_put(hub); } static bool hub_descriptor_is_sane(struct usb_host_interface *desc) @@ -5853,7 +5862,7 @@ out_hdev_lock: /* Balance the stuff in kick_hub_wq() and allow autosuspend */ usb_autopm_put_interface(intf); - kref_put(&hub->kref, hub_release); + hub_put(hub); kcov_remote_stop(); } diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h index db4c7e2c5960..dd049bc85f88 100644 --- a/drivers/usb/core/hub.h +++ b/drivers/usb/core/hub.h @@ -117,6 +117,8 @@ extern void usb_hub_remove_port_device(struct usb_hub *hub, extern int usb_hub_set_port_power(struct usb_device *hdev, struct usb_hub *hub, int port1, bool set); extern struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev); +extern void hub_get(struct usb_hub *hub); +extern void hub_put(struct usb_hub *hub); extern int hub_port_debounce(struct usb_hub *hub, int port1, bool must_be_connected); extern int usb_clear_port_feature(struct usb_device *hdev, diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index dfcca9c876c7..1f2e2a39b70f 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -450,7 +450,7 @@ static int match_location(struct usb_device *peer_hdev, void *p) struct usb_hub *peer_hub = usb_hub_to_struct_hub(peer_hdev); struct usb_device *hdev = to_usb_device(port_dev->dev.parent->parent); - if (!peer_hub) + if (!peer_hub || port_dev->connect_type == USB_PORT_NOT_USED) return 0; hcd = bus_to_hcd(hdev->bus); @@ -461,7 +461,8 @@ static int match_location(struct usb_device *peer_hdev, void *p) for (port1 = 1; port1 <= peer_hdev->maxchild; port1++) { peer = peer_hub->ports[port1 - 1]; - if (peer && peer->location == port_dev->location) { + if (peer && peer->connect_type != USB_PORT_NOT_USED && + peer->location == port_dev->location) { link_peers_report(port_dev, peer); return 1; /* done */ } diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index 60ee0469d86e..c9501907f7eb 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -1169,14 +1169,24 @@ static ssize_t interface_authorized_store(struct device *dev, { struct usb_interface *intf = to_usb_interface(dev); bool val; + struct kernfs_node *kn; if (strtobool(buf, &val) != 0) return -EINVAL; - if (val) + if (val) { usb_authorize_interface(intf); - else - usb_deauthorize_interface(intf); + } else { + /* + * Prevent deadlock if another process is concurrently + * trying to unregister intf. + */ + kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); + if (kn) { + usb_deauthorize_interface(intf); + sysfs_unbreak_active_protection(kn); + } + } return count; } diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h index 71e62b3081db..cbf975b75df7 100644 --- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -755,8 +755,14 @@ struct dwc2_dregs_backup { * struct dwc2_hregs_backup - Holds host registers state before * entering partial power down * @hcfg: Backup of HCFG register + * @hflbaddr: Backup of HFLBADDR register * @haintmsk: Backup of HAINTMSK register + * @hcchar: Backup of HCCHAR register + * @hcsplt: Backup of HCSPLT register * @hcintmsk: Backup of HCINTMSK register + * @hctsiz: Backup of HCTSIZ register + * @hdma: Backup of HCDMA register + * @hcdmab: Backup of HCDMAB register * @hprt0: Backup of HPTR0 register * @hfir: Backup of HFIR register * @hptxfsiz: Backup of HPTXFSIZ register @@ -764,8 +770,14 @@ struct dwc2_dregs_backup { */ struct dwc2_hregs_backup { u32 hcfg; + u32 hflbaddr; u32 haintmsk; + u32 hcchar[MAX_EPS_CHANNELS]; + u32 hcsplt[MAX_EPS_CHANNELS]; u32 hcintmsk[MAX_EPS_CHANNELS]; + u32 hctsiz[MAX_EPS_CHANNELS]; + u32 hcidma[MAX_EPS_CHANNELS]; + u32 hcidmab[MAX_EPS_CHANNELS]; u32 hprt0; u32 hfir; u32 hptxfsiz; @@ -1107,6 +1119,7 @@ struct dwc2_hsotg { bool needs_byte_swap; /* DWC OTG HW Release versions */ +#define DWC2_CORE_REV_4_30a 0x4f54430a #define DWC2_CORE_REV_2_71a 0x4f54271a #define DWC2_CORE_REV_2_72a 0x4f54272a #define DWC2_CORE_REV_2_80a 0x4f54280a @@ -1345,6 +1358,7 @@ int dwc2_backup_global_registers(struct dwc2_hsotg *hsotg); int dwc2_restore_global_registers(struct dwc2_hsotg *hsotg); void dwc2_enable_acg(struct dwc2_hsotg *hsotg); +void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg, bool remotewakeup); /* This function should be called on every hardware interrupt. */ irqreturn_t dwc2_handle_common_intr(int irq, void *dev); diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c index a5c52b237e72..5db14b1a5cb3 100644 --- a/drivers/usb/dwc2/core_intr.c +++ b/drivers/usb/dwc2/core_intr.c @@ -327,7 +327,8 @@ static void dwc2_handle_session_req_intr(struct dwc2_hsotg *hsotg) /* Exit gadget mode clock gating. */ if (hsotg->params.power_down == - DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended) + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) dwc2_gadget_exit_clock_gating(hsotg, 0); } @@ -352,10 +353,11 @@ static void dwc2_handle_session_req_intr(struct dwc2_hsotg *hsotg) * @hsotg: Programming view of DWC_otg controller * */ -static void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg) +void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg, bool remotewakeup) { u32 glpmcfg; - u32 i = 0; + u32 pcgctl; + u32 dctl; if (hsotg->lx_state != DWC2_L1) { dev_err(hsotg->dev, "Core isn't in DWC2_L1 state\n"); @@ -364,37 +366,57 @@ static void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg) glpmcfg = dwc2_readl(hsotg, GLPMCFG); if (dwc2_is_device_mode(hsotg)) { - dev_dbg(hsotg->dev, "Exit from L1 state\n"); + dev_dbg(hsotg->dev, "Exit from L1 state, remotewakeup=%d\n", remotewakeup); glpmcfg &= ~GLPMCFG_ENBLSLPM; - glpmcfg &= ~GLPMCFG_HIRD_THRES_EN; + glpmcfg &= ~GLPMCFG_HIRD_THRES_MASK; dwc2_writel(hsotg, glpmcfg, GLPMCFG); - do { - glpmcfg = dwc2_readl(hsotg, GLPMCFG); + pcgctl = dwc2_readl(hsotg, PCGCTL); + pcgctl &= ~PCGCTL_ENBL_SLEEP_GATING; + dwc2_writel(hsotg, pcgctl, PCGCTL); - if (!(glpmcfg & (GLPMCFG_COREL1RES_MASK | - GLPMCFG_L1RESUMEOK | GLPMCFG_SLPSTS))) - break; + glpmcfg = dwc2_readl(hsotg, GLPMCFG); + if (glpmcfg & GLPMCFG_ENBESL) { + glpmcfg |= GLPMCFG_RSTRSLPSTS; + dwc2_writel(hsotg, glpmcfg, GLPMCFG); + } + + if (remotewakeup) { + if (dwc2_hsotg_wait_bit_set(hsotg, GLPMCFG, GLPMCFG_L1RESUMEOK, 1000)) { + dev_warn(hsotg->dev, "%s: timeout GLPMCFG_L1RESUMEOK\n", __func__); + goto fail; + return; + } + + dctl = dwc2_readl(hsotg, DCTL); + dctl |= DCTL_RMTWKUPSIG; + dwc2_writel(hsotg, dctl, DCTL); - udelay(1); - } while (++i < 200); + if (dwc2_hsotg_wait_bit_set(hsotg, GINTSTS, GINTSTS_WKUPINT, 1000)) { + dev_warn(hsotg->dev, "%s: timeout GINTSTS_WKUPINT\n", __func__); + goto fail; + return; + } + } - if (i == 200) { - dev_err(hsotg->dev, "Failed to exit L1 sleep state in 200us.\n"); + glpmcfg = dwc2_readl(hsotg, GLPMCFG); + if (glpmcfg & GLPMCFG_COREL1RES_MASK || glpmcfg & GLPMCFG_SLPSTS || + glpmcfg & GLPMCFG_L1RESUMEOK) { + goto fail; return; } - dwc2_gadget_init_lpm(hsotg); + + /* Inform gadget to exit from L1 */ + call_gadget(hsotg, resume); + /* Change to L0 state */ + hsotg->lx_state = DWC2_L0; + hsotg->bus_suspended = false; +fail: dwc2_gadget_init_lpm(hsotg); } else { /* TODO */ dev_err(hsotg->dev, "Host side LPM is not supported.\n"); return; } - - /* Change to L0 state */ - hsotg->lx_state = DWC2_L0; - - /* Inform gadget to exit from L1 */ - call_gadget(hsotg, resume); } /* @@ -415,7 +437,7 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg) dev_dbg(hsotg->dev, "%s lxstate = %d\n", __func__, hsotg->lx_state); if (hsotg->lx_state == DWC2_L1) { - dwc2_wakeup_from_lpm_l1(hsotg); + dwc2_wakeup_from_lpm_l1(hsotg, false); return; } @@ -438,7 +460,8 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg) /* Exit gadget mode clock gating. */ if (hsotg->params.power_down == - DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended) + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) dwc2_gadget_exit_clock_gating(hsotg, 0); } else { /* Change to L0 state */ @@ -455,7 +478,8 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg) } if (hsotg->params.power_down == - DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended) + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) dwc2_host_exit_clock_gating(hsotg, 1); /* diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 519bb82b00e8..f6b2a4f2e59d 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -1416,6 +1416,10 @@ static int dwc2_hsotg_ep_queue(struct usb_ep *ep, struct usb_request *req, ep->name, req, req->length, req->buf, req->no_interrupt, req->zero, req->short_not_ok); + if (hs->lx_state == DWC2_L1) { + dwc2_wakeup_from_lpm_l1(hs, true); + } + /* Prevent new request submission when controller is suspended */ if (hs->lx_state != DWC2_L0) { dev_dbg(hs->dev, "%s: submit request only in active state\n", @@ -3728,6 +3732,12 @@ irq_retry: if (hsotg->in_ppd && hsotg->lx_state == DWC2_L2) dwc2_exit_partial_power_down(hsotg, 0, true); + /* Exit gadget mode clock gating. */ + if (hsotg->params.power_down == + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) + dwc2_gadget_exit_clock_gating(hsotg, 0); + hsotg->lx_state = DWC2_L0; } diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index d17a1dd6d0d9..f6195f44e548 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -2734,8 +2734,11 @@ enum dwc2_transaction_type dwc2_hcd_select_transactions( hsotg->available_host_channels--; } qh = list_entry(qh_ptr, struct dwc2_qh, qh_list_entry); - if (dwc2_assign_and_init_hc(hsotg, qh)) + if (dwc2_assign_and_init_hc(hsotg, qh)) { + if (hsotg->params.uframe_sched) + hsotg->available_host_channels++; break; + } /* * Move the QH from the periodic ready schedule to the @@ -2768,8 +2771,11 @@ enum dwc2_transaction_type dwc2_hcd_select_transactions( hsotg->available_host_channels--; } - if (dwc2_assign_and_init_hc(hsotg, qh)) + if (dwc2_assign_and_init_hc(hsotg, qh)) { + if (hsotg->params.uframe_sched) + hsotg->available_host_channels++; break; + } /* * Move the QH from the non-periodic inactive schedule to the @@ -4176,6 +4182,8 @@ void dwc2_host_complete(struct dwc2_hsotg *hsotg, struct dwc2_qtd *qtd, urb->actual_length); if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) { + if (!hsotg->params.dma_desc_enable) + urb->start_frame = qtd->qh->start_active_frame; urb->error_count = dwc2_hcd_urb_get_error_count(qtd->urb); for (i = 0; i < urb->number_of_packets; ++i) { urb->iso_frame_desc[i].actual_length = @@ -4682,7 +4690,7 @@ static int _dwc2_hcd_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, } if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE && - hsotg->bus_suspended) { + hsotg->bus_suspended && !hsotg->params.no_clock_gating) { if (dwc2_is_device_mode(hsotg)) dwc2_gadget_exit_clock_gating(hsotg, 0); else @@ -5437,9 +5445,16 @@ int dwc2_backup_host_registers(struct dwc2_hsotg *hsotg) /* Backup Host regs */ hr = &hsotg->hr_backup; hr->hcfg = dwc2_readl(hsotg, HCFG); + hr->hflbaddr = dwc2_readl(hsotg, HFLBADDR); hr->haintmsk = dwc2_readl(hsotg, HAINTMSK); - for (i = 0; i < hsotg->params.host_channels; ++i) + for (i = 0; i < hsotg->params.host_channels; ++i) { + hr->hcchar[i] = dwc2_readl(hsotg, HCCHAR(i)); + hr->hcsplt[i] = dwc2_readl(hsotg, HCSPLT(i)); hr->hcintmsk[i] = dwc2_readl(hsotg, HCINTMSK(i)); + hr->hctsiz[i] = dwc2_readl(hsotg, HCTSIZ(i)); + hr->hcidma[i] = dwc2_readl(hsotg, HCDMA(i)); + hr->hcidmab[i] = dwc2_readl(hsotg, HCDMAB(i)); + } hr->hprt0 = dwc2_read_hprt0(hsotg); hr->hfir = dwc2_readl(hsotg, HFIR); @@ -5473,10 +5488,17 @@ int dwc2_restore_host_registers(struct dwc2_hsotg *hsotg) hr->valid = false; dwc2_writel(hsotg, hr->hcfg, HCFG); + dwc2_writel(hsotg, hr->hflbaddr, HFLBADDR); dwc2_writel(hsotg, hr->haintmsk, HAINTMSK); - for (i = 0; i < hsotg->params.host_channels; ++i) + for (i = 0; i < hsotg->params.host_channels; ++i) { + dwc2_writel(hsotg, hr->hcchar[i], HCCHAR(i)); + dwc2_writel(hsotg, hr->hcsplt[i], HCSPLT(i)); dwc2_writel(hsotg, hr->hcintmsk[i], HCINTMSK(i)); + dwc2_writel(hsotg, hr->hctsiz[i], HCTSIZ(i)); + dwc2_writel(hsotg, hr->hcidma[i], HCDMA(i)); + dwc2_writel(hsotg, hr->hcidmab[i], HCDMAB(i)); + } dwc2_writel(hsotg, hr->hprt0, HPRT0); dwc2_writel(hsotg, hr->hfir, HFIR); @@ -5641,10 +5663,12 @@ int dwc2_host_exit_hibernation(struct dwc2_hsotg *hsotg, int rem_wakeup, dwc2_writel(hsotg, hr->hcfg, HCFG); /* De-assert Wakeup Logic */ - gpwrdn = dwc2_readl(hsotg, GPWRDN); - gpwrdn &= ~GPWRDN_PMUACTV; - dwc2_writel(hsotg, gpwrdn, GPWRDN); - udelay(10); + if (!(rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) { + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn &= ~GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + } hprt0 = hr->hprt0; hprt0 |= HPRT0_PWR; @@ -5669,6 +5693,13 @@ int dwc2_host_exit_hibernation(struct dwc2_hsotg *hsotg, int rem_wakeup, hprt0 |= HPRT0_RES; dwc2_writel(hsotg, hprt0, HPRT0); + /* De-assert Wakeup Logic */ + if ((rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) { + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn &= ~GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + } /* Wait for Resume time and then program HPRT again */ mdelay(100); hprt0 &= ~HPRT0_RES; diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c index a858b5f9c1d6..6a4aa71da103 100644 --- a/drivers/usb/dwc2/hcd_ddma.c +++ b/drivers/usb/dwc2/hcd_ddma.c @@ -589,7 +589,7 @@ static void dwc2_init_isoc_dma_desc(struct dwc2_hsotg *hsotg, idx = qh->td_last; inc = qh->host_interval; hsotg->frame_number = dwc2_hcd_get_frame_number(hsotg); - cur_idx = dwc2_frame_list_idx(hsotg->frame_number); + cur_idx = idx; next_idx = dwc2_desclist_idx_inc(qh->td_last, inc, qh->dev_speed); /* @@ -896,6 +896,8 @@ static int dwc2_cmpl_host_isoc_dma_desc(struct dwc2_hsotg *hsotg, { struct dwc2_dma_desc *dma_desc; struct dwc2_hcd_iso_packet_desc *frame_desc; + u16 frame_desc_idx; + struct urb *usb_urb = qtd->urb->priv; u16 remain = 0; int rc = 0; @@ -908,8 +910,11 @@ static int dwc2_cmpl_host_isoc_dma_desc(struct dwc2_hsotg *hsotg, DMA_FROM_DEVICE); dma_desc = &qh->desc_list[idx]; + frame_desc_idx = (idx - qtd->isoc_td_first) & (usb_urb->number_of_packets - 1); - frame_desc = &qtd->urb->iso_descs[qtd->isoc_frame_index_last]; + frame_desc = &qtd->urb->iso_descs[frame_desc_idx]; + if (idx == qtd->isoc_td_first) + usb_urb->start_frame = dwc2_hcd_get_frame_number(hsotg); dma_desc->buf = (u32)(qtd->urb->dma + frame_desc->offset); if (chan->ep_is_in) remain = (dma_desc->status & HOST_DMA_ISOC_NBYTES_MASK) >> @@ -930,7 +935,7 @@ static int dwc2_cmpl_host_isoc_dma_desc(struct dwc2_hsotg *hsotg, frame_desc->status = 0; } - if (++qtd->isoc_frame_index == qtd->urb->packet_count) { + if (++qtd->isoc_frame_index == usb_urb->number_of_packets) { /* * urb->status is not used for isoc transfers here. The * individual frame_desc status are used instead. @@ -1035,11 +1040,11 @@ static void dwc2_complete_isoc_xfer_ddma(struct dwc2_hsotg *hsotg, return; idx = dwc2_desclist_idx_inc(idx, qh->host_interval, chan->speed); - if (!rc) + if (rc == 0) continue; - if (rc == DWC2_CMPL_DONE) - break; + if (rc == DWC2_CMPL_DONE || rc == DWC2_CMPL_STOP) + goto stop_scan; /* rc == DWC2_CMPL_STOP */ diff --git a/drivers/usb/dwc2/hw.h b/drivers/usb/dwc2/hw.h index 6b16fbf98bc6..5a076269894c 100644 --- a/drivers/usb/dwc2/hw.h +++ b/drivers/usb/dwc2/hw.h @@ -728,7 +728,7 @@ #define TXSTS_QTOP_TOKEN_MASK (0x3 << 25) #define TXSTS_QTOP_TOKEN_SHIFT 25 #define TXSTS_QTOP_TERMINATE BIT(24) -#define TXSTS_QSPCAVAIL_MASK (0xff << 16) +#define TXSTS_QSPCAVAIL_MASK (0x7f << 16) #define TXSTS_QSPCAVAIL_SHIFT 16 #define TXSTS_FSPCAVAIL_MASK (0xffff << 0) #define TXSTS_FSPCAVAIL_SHIFT 0 diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index 6496bfbd34ed..79094384d8fd 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -344,7 +344,7 @@ static int dwc2_driver_remove(struct platform_device *dev) /* Exit clock gating when driver is removed. */ if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE && - hsotg->bus_suspended) { + hsotg->bus_suspended && !hsotg->params.no_clock_gating) { if (dwc2_is_device_mode(hsotg)) dwc2_gadget_exit_clock_gating(hsotg, 0); else diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 537f7a729f0e..e93b0eb74c08 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1352,7 +1352,7 @@ parse_ntb: if (to_process == 1 && (*(unsigned char *)(ntb_ptr + block_len) == 0x00)) { to_process--; - } else if (to_process > 0) { + } else if ((to_process > 0) && (block_len != 0)) { ntb_ptr = (unsigned char *)(ntb_ptr + block_len); goto parse_ntb; } diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 4f50a8e18d91..808a8d062e6a 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -275,7 +275,9 @@ int usb_ep_queue(struct usb_ep *ep, { int ret = 0; - if (WARN_ON_ONCE(!ep->enabled && ep->address)) { + if (!ep->enabled && ep->address) { + pr_debug("USB gadget: queue request to disabled ep 0x%x (%s)\n", + ep->address, ep->name); ret = -ESHUTDOWN; goto out; } diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index 52996bf2cc70..fdbb9d73aa8e 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -3480,8 +3480,8 @@ static void tegra_xudc_device_params_init(struct tegra_xudc *xudc) static int tegra_xudc_phy_get(struct tegra_xudc *xudc) { - int err = 0, usb3; - unsigned int i; + int err = 0, usb3_companion_port; + unsigned int i, j; xudc->utmi_phy = devm_kcalloc(xudc->dev, xudc->soc->num_phys, sizeof(*xudc->utmi_phy), GFP_KERNEL); @@ -3509,7 +3509,7 @@ static int tegra_xudc_phy_get(struct tegra_xudc *xudc) if (IS_ERR(xudc->utmi_phy[i])) { err = PTR_ERR(xudc->utmi_phy[i]); dev_err_probe(xudc->dev, err, - "failed to get usb2-%d PHY\n", i); + "failed to get PHY for phy-name usb2-%d\n", i); goto clean_up; } else if (xudc->utmi_phy[i]) { /* Get usb-phy, if utmi phy is available */ @@ -3528,19 +3528,30 @@ static int tegra_xudc_phy_get(struct tegra_xudc *xudc) } /* Get USB3 phy */ - usb3 = tegra_xusb_padctl_get_usb3_companion(xudc->padctl, i); - if (usb3 < 0) + usb3_companion_port = tegra_xusb_padctl_get_usb3_companion(xudc->padctl, i); + if (usb3_companion_port < 0) continue; - snprintf(phy_name, sizeof(phy_name), "usb3-%d", usb3); - xudc->usb3_phy[i] = devm_phy_optional_get(xudc->dev, phy_name); - if (IS_ERR(xudc->usb3_phy[i])) { - err = PTR_ERR(xudc->usb3_phy[i]); - dev_err_probe(xudc->dev, err, - "failed to get usb3-%d PHY\n", usb3); - goto clean_up; - } else if (xudc->usb3_phy[i]) - dev_dbg(xudc->dev, "usb3-%d PHY registered", usb3); + for (j = 0; j < xudc->soc->num_phys; j++) { + snprintf(phy_name, sizeof(phy_name), "usb3-%d", j); + xudc->usb3_phy[i] = devm_phy_optional_get(xudc->dev, phy_name); + if (IS_ERR(xudc->usb3_phy[i])) { + err = PTR_ERR(xudc->usb3_phy[i]); + dev_err_probe(xudc->dev, err, + "failed to get PHY for phy-name usb3-%d\n", j); + goto clean_up; + } else if (xudc->usb3_phy[i]) { + int usb2_port = + tegra_xusb_padctl_get_port_number(xudc->utmi_phy[i]); + int usb3_port = + tegra_xusb_padctl_get_port_number(xudc->usb3_phy[i]); + if (usb3_port == usb3_companion_port) { + dev_dbg(xudc->dev, "USB2 port %d is paired with USB3 port %d for device mode port %d\n", + usb2_port, usb3_port, i); + break; + } + } + } } return err; diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c index 825ff6727310..d3de9f47552d 100644 --- a/drivers/usb/host/sl811-hcd.c +++ b/drivers/usb/host/sl811-hcd.c @@ -585,6 +585,7 @@ done(struct sl811 *sl811, struct sl811h_ep *ep, u8 bank) finish_request(sl811, ep, urb, urbstat); } +#ifdef QUIRK2 static inline u8 checkdone(struct sl811 *sl811) { u8 ctl; @@ -616,6 +617,7 @@ static inline u8 checkdone(struct sl811 *sl811) #endif return irqstat; } +#endif static irqreturn_t sl811h_irq(struct usb_hcd *hcd) { diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 5c9d3be136d2..2539d97b90c3 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1324,6 +1324,8 @@ static int xhci_map_temp_buffer(struct usb_hcd *hcd, struct urb *urb) temp = kzalloc_node(buf_len, GFP_ATOMIC, dev_to_node(hcd->self.sysdev)); + if (!temp) + return -ENOMEM; if (usb_urb_dir_out(urb)) sg_pcopy_to_buffer(urb->sg, urb->num_sgs, diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c index 34b9f8140187..661a229c105d 100644 --- a/drivers/usb/phy/phy-generic.c +++ b/drivers/usb/phy/phy-generic.c @@ -268,13 +268,6 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop) return -EPROBE_DEFER; } - nop->vbus_draw = devm_regulator_get_exclusive(dev, "vbus"); - if (PTR_ERR(nop->vbus_draw) == -ENODEV) - nop->vbus_draw = NULL; - if (IS_ERR(nop->vbus_draw)) - return dev_err_probe(dev, PTR_ERR(nop->vbus_draw), - "could not get vbus regulator\n"); - nop->dev = dev; nop->phy.dev = nop->dev; nop->phy.label = "nop-xceiv"; diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index f47c2f392292..4183942a1c19 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -56,6 +56,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x0471, 0x066A) }, /* AKTAKOM ACE-1001 cable */ { USB_DEVICE(0x0489, 0xE000) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */ { USB_DEVICE(0x0489, 0xE003) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */ + { USB_DEVICE(0x04BF, 0x1301) }, /* TDK Corporation NC0110013M - Network Controller */ + { USB_DEVICE(0x04BF, 0x1303) }, /* TDK Corporation MM0110113M - i3 Micro Module */ { USB_DEVICE(0x0745, 0x1000) }, /* CipherLab USB CCD Barcode Scanner 1000 */ { USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */ { USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */ @@ -144,6 +146,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */ { USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */ { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ + { USB_DEVICE(0x10C4, 0x863C) }, /* MGP Instruments PDS100 */ { USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */ { USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */ { USB_DEVICE(0x10C4, 0x87ED) }, /* IMST USB-Stick for Smart Meter */ @@ -177,6 +180,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0xF004) }, /* Elan Digital Systems USBcount50 */ { USB_DEVICE(0x10C5, 0xEA61) }, /* Silicon Labs MobiData GPRS USB Modem */ { USB_DEVICE(0x10CE, 0xEA6A) }, /* Silicon Labs MobiData GPRS USB Modem 100EU */ + { USB_DEVICE(0x11CA, 0x0212) }, /* Verifone USB to Printer (UART, CP2102) */ { USB_DEVICE(0x12B8, 0xEC60) }, /* Link G4 ECU */ { USB_DEVICE(0x12B8, 0xEC62) }, /* Link G4+ ECU */ { USB_DEVICE(0x13AD, 0x9999) }, /* Baltech card reader */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 2345208b7221..1915b92c388f 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1055,6 +1055,8 @@ static const struct usb_device_id id_table_combined[] = { .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 }, + /* GMC devices */ + { USB_DEVICE(GMC_VID, GMC_Z216C_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 9a0f9fc99124..b2aec1106678 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1599,3 +1599,9 @@ #define UBLOX_VID 0x1546 #define UBLOX_C099F9P_ZED_PID 0x0502 #define UBLOX_C099F9P_ODIN_PID 0x0503 + +/* + * GMC devices + */ +#define GMC_VID 0x1cd7 +#define GMC_Z216C_PID 0x0217 /* GMC Z216C Adapter IR-USB */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index c0a0cca65437..1a3e5a9414f0 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -613,6 +613,11 @@ static void option_instat_callback(struct urb *urb); /* Luat Air72*U series based on UNISOC UIS8910 uses UNISOC's vendor ID */ #define LUAT_PRODUCT_AIR720U 0x4e00 +/* MeiG Smart Technology products */ +#define MEIGSMART_VENDOR_ID 0x2dee +/* MeiG Smart SLM320 based on UNISOC UIS8910 */ +#define MEIGSMART_PRODUCT_SLM320 0x4d41 + /* Device flags */ /* Highest interface number which can be used with NCTRL() and RSVD() */ @@ -2282,6 +2287,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/storage/isd200.c b/drivers/usb/storage/isd200.c index 3c76336e43bb..1d22db59f7bd 100644 --- a/drivers/usb/storage/isd200.c +++ b/drivers/usb/storage/isd200.c @@ -1105,7 +1105,7 @@ static void isd200_dump_driveid(struct us_data *us, u16 *id) static int isd200_get_inquiry_data( struct us_data *us ) { struct isd200_info *info = (struct isd200_info *)us->extra; - int retStatus = ISD200_GOOD; + int retStatus; u16 *id = info->id; usb_stor_dbg(us, "Entering isd200_get_inquiry_data\n"); @@ -1137,6 +1137,13 @@ static int isd200_get_inquiry_data( struct us_data *us ) isd200_fix_driveid(id); isd200_dump_driveid(us, id); + /* Prevent division by 0 in isd200_scsi_to_ata() */ + if (id[ATA_ID_HEADS] == 0 || id[ATA_ID_SECTORS] == 0) { + usb_stor_dbg(us, " Invalid ATA Identify data\n"); + retStatus = ISD200_ERROR; + goto Done; + } + memset(&info->InquiryData, 0, sizeof(info->InquiryData)); /* Standard IDE interface only supports disks */ @@ -1202,6 +1209,7 @@ static int isd200_get_inquiry_data( struct us_data *us ) } } + Done: usb_stor_dbg(us, "Leaving isd200_get_inquiry_data %08X\n", retStatus); return(retStatus); @@ -1481,22 +1489,27 @@ static int isd200_init_info(struct us_data *us) static int isd200_Initialization(struct us_data *us) { + int rc = 0; + usb_stor_dbg(us, "ISD200 Initialization...\n"); /* Initialize ISD200 info struct */ - if (isd200_init_info(us) == ISD200_ERROR) { + if (isd200_init_info(us) < 0) { usb_stor_dbg(us, "ERROR Initializing ISD200 Info struct\n"); + rc = -ENOMEM; } else { /* Get device specific data */ - if (isd200_get_inquiry_data(us) != ISD200_GOOD) + if (isd200_get_inquiry_data(us) != ISD200_GOOD) { usb_stor_dbg(us, "ISD200 Initialization Failure\n"); - else + rc = -EINVAL; + } else { usb_stor_dbg(us, "ISD200 Initialization complete\n"); + } } - return 0; + return rc; } diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index b8e1109f0e0d..e104aa651ccc 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -393,7 +393,6 @@ static int queuecommand_lck(struct scsi_cmnd *srb, } /* enqueue the command and wake up the control thread */ - srb->scsi_done = done; us->srb = srb; complete(&us->cmnd_ready); diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index bef89c6bd1d7..11a551a9cd05 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -113,7 +113,7 @@ static void uas_do_work(struct work_struct *work) continue; cmnd = devinfo->cmnd[i]; - cmdinfo = (void *)&cmnd->SCp; + cmdinfo = scsi_cmd_priv(cmnd); if (!(cmdinfo->state & IS_IN_WORK_LIST)) continue; @@ -139,10 +139,9 @@ static void uas_scan_work(struct work_struct *work) dev_dbg(&devinfo->intf->dev, "scan complete\n"); } -static void uas_add_work(struct uas_cmd_info *cmdinfo) +static void uas_add_work(struct scsi_cmnd *cmnd) { - struct scsi_pointer *scp = (void *)cmdinfo; - struct scsi_cmnd *cmnd = container_of(scp, struct scsi_cmnd, SCp); + struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct uas_dev_info *devinfo = cmnd->device->hostdata; lockdep_assert_held(&devinfo->lock); @@ -163,7 +162,7 @@ static void uas_zap_pending(struct uas_dev_info *devinfo, int result) continue; cmnd = devinfo->cmnd[i]; - cmdinfo = (void *)&cmnd->SCp; + cmdinfo = scsi_cmd_priv(cmnd); uas_log_cmd_state(cmnd, __func__, 0); /* Sense urbs were killed, clear COMMAND_INFLIGHT manually */ cmdinfo->state &= ~COMMAND_INFLIGHT; @@ -200,15 +199,14 @@ static void uas_sense(struct urb *urb, struct scsi_cmnd *cmnd) static void uas_log_cmd_state(struct scsi_cmnd *cmnd, const char *prefix, int status) { - struct uas_cmd_info *ci = (void *)&cmnd->SCp; - struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; + struct uas_cmd_info *ci = scsi_cmd_priv(cmnd); if (status == -ENODEV) /* too late */ return; scmd_printk(KERN_INFO, cmnd, "%s %d uas-tag %d inflight:%s%s%s%s%s%s%s%s%s%s%s%s ", - prefix, status, cmdinfo->uas_tag, + prefix, status, ci->uas_tag, (ci->state & SUBMIT_STATUS_URB) ? " s-st" : "", (ci->state & ALLOC_DATA_IN_URB) ? " a-in" : "", (ci->state & SUBMIT_DATA_IN_URB) ? " s-in" : "", @@ -231,7 +229,7 @@ static void uas_free_unsubmitted_urbs(struct scsi_cmnd *cmnd) if (!cmnd) return; - cmdinfo = (void *)&cmnd->SCp; + cmdinfo = scsi_cmd_priv(cmnd); if (cmdinfo->state & SUBMIT_CMD_URB) usb_free_urb(cmdinfo->cmd_urb); @@ -245,7 +243,7 @@ static void uas_free_unsubmitted_urbs(struct scsi_cmnd *cmnd) static int uas_try_complete(struct scsi_cmnd *cmnd, const char *caller) { - struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; + struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct uas_dev_info *devinfo = (void *)cmnd->device->hostdata; lockdep_assert_held(&devinfo->lock); @@ -256,20 +254,20 @@ static int uas_try_complete(struct scsi_cmnd *cmnd, const char *caller) return -EBUSY; devinfo->cmnd[cmdinfo->uas_tag - 1] = NULL; uas_free_unsubmitted_urbs(cmnd); - cmnd->scsi_done(cmnd); + scsi_done(cmnd); return 0; } static void uas_xfer_data(struct urb *urb, struct scsi_cmnd *cmnd, unsigned direction) { - struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; + struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); int err; cmdinfo->state |= direction | SUBMIT_STATUS_URB; err = uas_submit_urbs(cmnd, cmnd->device->hostdata); if (err) { - uas_add_work(cmdinfo); + uas_add_work(cmnd); } } @@ -329,7 +327,7 @@ static void uas_stat_cmplt(struct urb *urb) } cmnd = devinfo->cmnd[idx]; - cmdinfo = (void *)&cmnd->SCp; + cmdinfo = scsi_cmd_priv(cmnd); if (!(cmdinfo->state & COMMAND_INFLIGHT)) { uas_log_cmd_state(cmnd, "unexpected status cmplt", 0); @@ -394,7 +392,7 @@ out: static void uas_data_cmplt(struct urb *urb) { struct scsi_cmnd *cmnd = urb->context; - struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; + struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct uas_dev_info *devinfo = (void *)cmnd->device->hostdata; struct scsi_data_buffer *sdb = &cmnd->sdb; unsigned long flags; @@ -446,7 +444,7 @@ static struct urb *uas_alloc_data_urb(struct uas_dev_info *devinfo, gfp_t gfp, enum dma_data_direction dir) { struct usb_device *udev = devinfo->udev; - struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; + struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct urb *urb = usb_alloc_urb(0, gfp); struct scsi_data_buffer *sdb = &cmnd->sdb; unsigned int pipe = (dir == DMA_FROM_DEVICE) @@ -468,7 +466,7 @@ static struct urb *uas_alloc_sense_urb(struct uas_dev_info *devinfo, gfp_t gfp, struct scsi_cmnd *cmnd) { struct usb_device *udev = devinfo->udev; - struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; + struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct urb *urb = usb_alloc_urb(0, gfp); struct sense_iu *iu; @@ -496,7 +494,7 @@ static struct urb *uas_alloc_cmd_urb(struct uas_dev_info *devinfo, gfp_t gfp, { struct usb_device *udev = devinfo->udev; struct scsi_device *sdev = cmnd->device; - struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; + struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct urb *urb = usb_alloc_urb(0, gfp); struct command_iu *iu; int len; @@ -535,7 +533,7 @@ static struct urb *uas_alloc_cmd_urb(struct uas_dev_info *devinfo, gfp_t gfp, * daft to me. */ -static struct urb *uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp) +static int uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp) { struct uas_dev_info *devinfo = cmnd->device->hostdata; struct urb *urb; @@ -543,30 +541,28 @@ static struct urb *uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp) urb = uas_alloc_sense_urb(devinfo, gfp, cmnd); if (!urb) - return NULL; + return -ENOMEM; usb_anchor_urb(urb, &devinfo->sense_urbs); err = usb_submit_urb(urb, gfp); if (err) { usb_unanchor_urb(urb); uas_log_cmd_state(cmnd, "sense submit err", err); usb_free_urb(urb); - return NULL; } - return urb; + return err; } static int uas_submit_urbs(struct scsi_cmnd *cmnd, struct uas_dev_info *devinfo) { - struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; - struct urb *urb; + struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); int err; lockdep_assert_held(&devinfo->lock); if (cmdinfo->state & SUBMIT_STATUS_URB) { - urb = uas_submit_sense_urb(cmnd, GFP_ATOMIC); - if (!urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + err = uas_submit_sense_urb(cmnd, GFP_ATOMIC); + if (err) + return err; cmdinfo->state &= ~SUBMIT_STATUS_URB; } @@ -574,7 +570,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, cmdinfo->data_in_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC, cmnd, DMA_FROM_DEVICE); if (!cmdinfo->data_in_urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + return -ENOMEM; cmdinfo->state &= ~ALLOC_DATA_IN_URB; } @@ -584,7 +580,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (err) { usb_unanchor_urb(cmdinfo->data_in_urb); uas_log_cmd_state(cmnd, "data in submit err", err); - return SCSI_MLQUEUE_DEVICE_BUSY; + return err; } cmdinfo->state &= ~SUBMIT_DATA_IN_URB; cmdinfo->state |= DATA_IN_URB_INFLIGHT; @@ -594,7 +590,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, cmdinfo->data_out_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC, cmnd, DMA_TO_DEVICE); if (!cmdinfo->data_out_urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + return -ENOMEM; cmdinfo->state &= ~ALLOC_DATA_OUT_URB; } @@ -604,7 +600,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (err) { usb_unanchor_urb(cmdinfo->data_out_urb); uas_log_cmd_state(cmnd, "data out submit err", err); - return SCSI_MLQUEUE_DEVICE_BUSY; + return err; } cmdinfo->state &= ~SUBMIT_DATA_OUT_URB; cmdinfo->state |= DATA_OUT_URB_INFLIGHT; @@ -613,7 +609,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (cmdinfo->state & ALLOC_CMD_URB) { cmdinfo->cmd_urb = uas_alloc_cmd_urb(devinfo, GFP_ATOMIC, cmnd); if (!cmdinfo->cmd_urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + return -ENOMEM; cmdinfo->state &= ~ALLOC_CMD_URB; } @@ -623,7 +619,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (err) { usb_unanchor_urb(cmdinfo->cmd_urb); uas_log_cmd_state(cmnd, "cmd submit err", err); - return SCSI_MLQUEUE_DEVICE_BUSY; + return err; } cmdinfo->cmd_urb = NULL; cmdinfo->state &= ~SUBMIT_CMD_URB; @@ -638,12 +634,10 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd, { struct scsi_device *sdev = cmnd->device; struct uas_dev_info *devinfo = sdev->hostdata; - struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; + struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); unsigned long flags; int idx, err; - BUILD_BUG_ON(sizeof(struct uas_cmd_info) > sizeof(struct scsi_pointer)); - /* Re-check scsi_block_requests now that we've the host-lock */ if (cmnd->device->host->host_self_blocked) return SCSI_MLQUEUE_DEVICE_BUSY; @@ -653,7 +647,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd, memcpy(cmnd->sense_buffer, usb_stor_sense_invalidCDB, sizeof(usb_stor_sense_invalidCDB)); cmnd->result = SAM_STAT_CHECK_CONDITION; - cmnd->scsi_done(cmnd); + scsi_done(cmnd); return 0; } @@ -661,7 +655,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd, if (devinfo->resetting) { set_host_byte(cmnd, DID_ERROR); - cmnd->scsi_done(cmnd); + scsi_done(cmnd); goto zombie; } @@ -675,8 +669,6 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd, return SCSI_MLQUEUE_DEVICE_BUSY; } - cmnd->scsi_done = done; - memset(cmdinfo, 0, sizeof(*cmdinfo)); cmdinfo->uas_tag = idx + 1; /* uas-tag == usb-stream-id, so 1 based */ cmdinfo->state = SUBMIT_STATUS_URB | ALLOC_CMD_URB | SUBMIT_CMD_URB; @@ -705,8 +697,8 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd, * of queueing, no matter how fatal the error */ if (err == -ENODEV) { - set_host_byte(cmnd, DID_ERROR); - cmnd->scsi_done(cmnd); + set_host_byte(cmnd, DID_NO_CONNECT); + scsi_done(cmnd); goto zombie; } if (err) { @@ -715,7 +707,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd, spin_unlock_irqrestore(&devinfo->lock, flags); return SCSI_MLQUEUE_DEVICE_BUSY; } - uas_add_work(cmdinfo); + uas_add_work(cmnd); } devinfo->cmnd[idx] = cmnd; @@ -733,7 +725,7 @@ static DEF_SCSI_QCMD(uas_queuecommand) */ static int uas_eh_abort_handler(struct scsi_cmnd *cmnd) { - struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp; + struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); struct uas_dev_info *devinfo = (void *)cmnd->device->hostdata; struct urb *data_in_urb = NULL; struct urb *data_out_urb = NULL; @@ -913,6 +905,7 @@ static struct scsi_host_template uas_host_template = { .this_id = -1, .skip_settle_delay = 1, .dma_boundary = PAGE_SIZE - 1, + .cmd_size = sizeof(struct uas_cmd_info), }; #define UNUSUAL_DEV(id_vendor, id_product, bcdDeviceMin, bcdDeviceMax, \ diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index 90aa9c12ffac..8b543f2c9857 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -388,7 +388,7 @@ static int usb_stor_control_thread(void * __us) if (srb->result == DID_ABORT << 16) { SkipForAbort: usb_stor_dbg(us, "scsi command aborted\n"); - srb = NULL; /* Don't call srb->scsi_done() */ + srb = NULL; /* Don't call scsi_done() */ } /* @@ -417,7 +417,7 @@ SkipForAbort: if (srb) { usb_stor_dbg(us, "scsi cmd done, result=0x%x\n", srb->result); - srb->scsi_done(srb); + scsi_done(srb); } } /* for (;;) */ diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index a7b0134d382b..e047a15e6734 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -899,6 +899,7 @@ MODULE_DEVICE_TABLE(i2c, tcpci_id); #ifdef CONFIG_OF static const struct of_device_id tcpci_of_match[] = { { .compatible = "nxp,ptn5110", }, + { .compatible = "tcpci", }, {}, }; MODULE_DEVICE_TABLE(of, tcpci_of_match); diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index dca6803a75bd..985e512c0e65 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -138,8 +138,12 @@ static int ucsi_exec_command(struct ucsi *ucsi, u64 cmd) if (!(cci & UCSI_CCI_COMMAND_COMPLETE)) return -EIO; - if (cci & UCSI_CCI_NOT_SUPPORTED) + if (cci & UCSI_CCI_NOT_SUPPORTED) { + if (ucsi_acknowledge_command(ucsi) < 0) + dev_err(ucsi->dev, + "ACK of unsupported command failed\n"); return -EOPNOTSUPP; + } if (cci & UCSI_CCI_ERROR) { if (cmd == UCSI_GET_ERROR_STATUS) @@ -875,13 +879,47 @@ static int ucsi_reset_connector(struct ucsi_connector *con, bool hard) static int ucsi_reset_ppm(struct ucsi *ucsi) { - u64 command = UCSI_PPM_RESET; + u64 command; unsigned long tmo; u32 cci; int ret; mutex_lock(&ucsi->ppm_lock); + ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci)); + if (ret < 0) + goto out; + + /* + * If UCSI_CCI_RESET_COMPLETE is already set we must clear + * the flag before we start another reset. Send a + * UCSI_SET_NOTIFICATION_ENABLE command to achieve this. + * Ignore a timeout and try the reset anyway if this fails. + */ + if (cci & UCSI_CCI_RESET_COMPLETE) { + command = UCSI_SET_NOTIFICATION_ENABLE; + ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command, + sizeof(command)); + if (ret < 0) + goto out; + + tmo = jiffies + msecs_to_jiffies(UCSI_TIMEOUT_MS); + do { + ret = ucsi->ops->read(ucsi, UCSI_CCI, + &cci, sizeof(cci)); + if (ret < 0) + goto out; + if (cci & UCSI_CCI_COMMAND_COMPLETE) + break; + if (time_is_before_jiffies(tmo)) + break; + msleep(20); + } while (1); + + WARN_ON(cci & UCSI_CCI_RESET_COMPLETE); + } + + command = UCSI_PPM_RESET; ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command, sizeof(command)); if (ret < 0) diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index cee666790907..3dc3da8dbbdf 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -220,12 +220,12 @@ struct ucsi_cable_property { #define UCSI_CABLE_PROP_FLAG_VBUS_IN_CABLE BIT(0) #define UCSI_CABLE_PROP_FLAG_ACTIVE_CABLE BIT(1) #define UCSI_CABLE_PROP_FLAG_DIRECTIONALITY BIT(2) -#define UCSI_CABLE_PROP_FLAG_PLUG_TYPE(_f_) ((_f_) & GENMASK(3, 0)) +#define UCSI_CABLE_PROP_FLAG_PLUG_TYPE(_f_) (((_f_) & GENMASK(4, 3)) >> 3) #define UCSI_CABLE_PROPERTY_PLUG_TYPE_A 0 #define UCSI_CABLE_PROPERTY_PLUG_TYPE_B 1 #define UCSI_CABLE_PROPERTY_PLUG_TYPE_C 2 #define UCSI_CABLE_PROPERTY_PLUG_OTHER 3 -#define UCSI_CABLE_PROP_MODE_SUPPORT BIT(5) +#define UCSI_CABLE_PROP_FLAG_MODE_SUPPORT BIT(5) u8 latency; } __packed; diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c index 77e584093a23..50c2f82f2b68 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c @@ -142,13 +142,14 @@ static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev, irq = &vdev->mc_irqs[index]; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_fsl_mc_irq_handler(hwirq, irq); + if (irq->trigger) + eventfd_signal(irq->trigger, 1); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { u8 trigger = *(u8 *)data; - if (trigger) - vfio_fsl_mc_irq_handler(hwirq, irq); + if (trigger && irq->trigger) + eventfd_signal(irq->trigger, 1); } return 0; diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 6069a11fb51a..cb55f96b4f03 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -29,15 +29,22 @@ static void vfio_send_intx_eventfd(void *opaque, void *unused) { struct vfio_pci_core_device *vdev = opaque; - if (likely(is_intx(vdev) && !vdev->virq_disabled)) - eventfd_signal(vdev->ctx[0].trigger, 1); + if (likely(is_intx(vdev) && !vdev->virq_disabled)) { + struct eventfd_ctx *trigger; + + trigger = READ_ONCE(vdev->ctx[0].trigger); + if (likely(trigger)) + eventfd_signal(trigger, 1); + } } -void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) +static void __vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; unsigned long flags; + lockdep_assert_held(&vdev->igate); + spin_lock_irqsave(&vdev->irqlock, flags); /* @@ -65,6 +72,13 @@ void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) spin_unlock_irqrestore(&vdev->irqlock, flags); } +void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) +{ + mutex_lock(&vdev->igate); + __vfio_pci_intx_mask(vdev); + mutex_unlock(&vdev->igate); +} + /* * If this is triggered by an eventfd, we can't call eventfd_signal * or else we'll deadlock on the eventfd wait queue. Return >0 when @@ -107,12 +121,21 @@ static int vfio_pci_intx_unmask_handler(void *opaque, void *unused) return ret; } -void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev) +static void __vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev) { + lockdep_assert_held(&vdev->igate); + if (vfio_pci_intx_unmask_handler(vdev, NULL) > 0) vfio_send_intx_eventfd(vdev, NULL); } +void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev) +{ + mutex_lock(&vdev->igate); + __vfio_pci_intx_unmask(vdev); + mutex_unlock(&vdev->igate); +} + static irqreturn_t vfio_intx_handler(int irq, void *dev_id) { struct vfio_pci_core_device *vdev = dev_id; @@ -139,95 +162,104 @@ static irqreturn_t vfio_intx_handler(int irq, void *dev_id) return ret; } -static int vfio_intx_enable(struct vfio_pci_core_device *vdev) +static int vfio_intx_enable(struct vfio_pci_core_device *vdev, + struct eventfd_ctx *trigger) { + struct pci_dev *pdev = vdev->pdev; + unsigned long irqflags; + char *name; + int ret; + if (!is_irq_none(vdev)) return -EINVAL; - if (!vdev->pdev->irq) + if (!pdev->irq) return -ENODEV; + name = kasprintf(GFP_KERNEL, "vfio-intx(%s)", pci_name(pdev)); + if (!name) + return -ENOMEM; + vdev->ctx = kzalloc(sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL); if (!vdev->ctx) return -ENOMEM; vdev->num_ctx = 1; + vdev->ctx[0].name = name; + vdev->ctx[0].trigger = trigger; + /* - * If the virtual interrupt is masked, restore it. Devices - * supporting DisINTx can be masked at the hardware level - * here, non-PCI-2.3 devices will have to wait until the - * interrupt is enabled. + * Fill the initial masked state based on virq_disabled. After + * enable, changing the DisINTx bit in vconfig directly changes INTx + * masking. igate prevents races during setup, once running masked + * is protected via irqlock. + * + * Devices supporting DisINTx also reflect the current mask state in + * the physical DisINTx bit, which is not affected during IRQ setup. + * + * Devices without DisINTx support require an exclusive interrupt. + * IRQ masking is performed at the IRQ chip. Again, igate protects + * against races during setup and IRQ handlers and irqfds are not + * yet active, therefore masked is stable and can be used to + * conditionally auto-enable the IRQ. + * + * irq_type must be stable while the IRQ handler is registered, + * therefore it must be set before request_irq(). */ vdev->ctx[0].masked = vdev->virq_disabled; - if (vdev->pci_2_3) - pci_intx(vdev->pdev, !vdev->ctx[0].masked); + if (vdev->pci_2_3) { + pci_intx(pdev, !vdev->ctx[0].masked); + irqflags = IRQF_SHARED; + } else { + irqflags = vdev->ctx[0].masked ? IRQF_NO_AUTOEN : 0; + } vdev->irq_type = VFIO_PCI_INTX_IRQ_INDEX; + ret = request_irq(pdev->irq, vfio_intx_handler, + irqflags, vdev->ctx[0].name, vdev); + if (ret) { + vdev->irq_type = VFIO_PCI_NUM_IRQS; + kfree(name); + vdev->num_ctx = 0; + kfree(vdev->ctx); + return ret; + } + return 0; } -static int vfio_intx_set_signal(struct vfio_pci_core_device *vdev, int fd) +static int vfio_intx_set_signal(struct vfio_pci_core_device *vdev, + struct eventfd_ctx *trigger) { struct pci_dev *pdev = vdev->pdev; - unsigned long irqflags = IRQF_SHARED; - struct eventfd_ctx *trigger; - unsigned long flags; - int ret; + struct eventfd_ctx *old; - if (vdev->ctx[0].trigger) { - free_irq(pdev->irq, vdev); - kfree(vdev->ctx[0].name); - eventfd_ctx_put(vdev->ctx[0].trigger); - vdev->ctx[0].trigger = NULL; - } - - if (fd < 0) /* Disable only */ - return 0; - - vdev->ctx[0].name = kasprintf(GFP_KERNEL, "vfio-intx(%s)", - pci_name(pdev)); - if (!vdev->ctx[0].name) - return -ENOMEM; - - trigger = eventfd_ctx_fdget(fd); - if (IS_ERR(trigger)) { - kfree(vdev->ctx[0].name); - return PTR_ERR(trigger); - } - - vdev->ctx[0].trigger = trigger; + old = vdev->ctx[0].trigger; - if (!vdev->pci_2_3) - irqflags = 0; + WRITE_ONCE(vdev->ctx[0].trigger, trigger); - ret = request_irq(pdev->irq, vfio_intx_handler, - irqflags, vdev->ctx[0].name, vdev); - if (ret) { - vdev->ctx[0].trigger = NULL; - kfree(vdev->ctx[0].name); - eventfd_ctx_put(trigger); - return ret; + /* Releasing an old ctx requires synchronizing in-flight users */ + if (old) { + synchronize_irq(pdev->irq); + vfio_virqfd_flush_thread(&vdev->ctx[0].unmask); + eventfd_ctx_put(old); } - /* - * INTx disable will stick across the new irq setup, - * disable_irq won't. - */ - spin_lock_irqsave(&vdev->irqlock, flags); - if (!vdev->pci_2_3 && vdev->ctx[0].masked) - disable_irq_nosync(pdev->irq); - spin_unlock_irqrestore(&vdev->irqlock, flags); - return 0; } static void vfio_intx_disable(struct vfio_pci_core_device *vdev) { + struct pci_dev *pdev = vdev->pdev; + vfio_virqfd_disable(&vdev->ctx[0].unmask); vfio_virqfd_disable(&vdev->ctx[0].mask); - vfio_intx_set_signal(vdev, -1); + free_irq(pdev->irq, vdev); + if (vdev->ctx[0].trigger) + eventfd_ctx_put(vdev->ctx[0].trigger); + kfree(vdev->ctx[0].name); vdev->irq_type = VFIO_PCI_NUM_IRQS; vdev->num_ctx = 0; kfree(vdev->ctx); @@ -425,11 +457,11 @@ static int vfio_pci_set_intx_unmask(struct vfio_pci_core_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_pci_intx_unmask(vdev); + __vfio_pci_intx_unmask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { uint8_t unmask = *(uint8_t *)data; if (unmask) - vfio_pci_intx_unmask(vdev); + __vfio_pci_intx_unmask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { int32_t fd = *(int32_t *)data; if (fd >= 0) @@ -452,11 +484,11 @@ static int vfio_pci_set_intx_mask(struct vfio_pci_core_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_pci_intx_mask(vdev); + __vfio_pci_intx_mask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { uint8_t mask = *(uint8_t *)data; if (mask) - vfio_pci_intx_mask(vdev); + __vfio_pci_intx_mask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { return -ENOTTY; /* XXX implement me */ } @@ -477,19 +509,23 @@ static int vfio_pci_set_intx_trigger(struct vfio_pci_core_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { + struct eventfd_ctx *trigger = NULL; int32_t fd = *(int32_t *)data; int ret; - if (is_intx(vdev)) - return vfio_intx_set_signal(vdev, fd); + if (fd >= 0) { + trigger = eventfd_ctx_fdget(fd); + if (IS_ERR(trigger)) + return PTR_ERR(trigger); + } - ret = vfio_intx_enable(vdev); - if (ret) - return ret; + if (is_intx(vdev)) + ret = vfio_intx_set_signal(vdev, trigger); + else + ret = vfio_intx_enable(vdev, trigger); - ret = vfio_intx_set_signal(vdev, fd); - if (ret) - vfio_intx_disable(vdev); + if (ret && trigger) + eventfd_ctx_put(trigger); return ret; } diff --git a/drivers/vfio/platform/vfio_platform_irq.c b/drivers/vfio/platform/vfio_platform_irq.c index c5b09ec0a3c9..7f4341a8d718 100644 --- a/drivers/vfio/platform/vfio_platform_irq.c +++ b/drivers/vfio/platform/vfio_platform_irq.c @@ -136,6 +136,16 @@ static int vfio_platform_set_irq_unmask(struct vfio_platform_device *vdev, return 0; } +/* + * The trigger eventfd is guaranteed valid in the interrupt path + * and protected by the igate mutex when triggered via ioctl. + */ +static void vfio_send_eventfd(struct vfio_platform_irq *irq_ctx) +{ + if (likely(irq_ctx->trigger)) + eventfd_signal(irq_ctx->trigger, 1); +} + static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id) { struct vfio_platform_irq *irq_ctx = dev_id; @@ -155,7 +165,7 @@ static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id) spin_unlock_irqrestore(&irq_ctx->lock, flags); if (ret == IRQ_HANDLED) - eventfd_signal(irq_ctx->trigger, 1); + vfio_send_eventfd(irq_ctx); return ret; } @@ -164,22 +174,19 @@ static irqreturn_t vfio_irq_handler(int irq, void *dev_id) { struct vfio_platform_irq *irq_ctx = dev_id; - eventfd_signal(irq_ctx->trigger, 1); + vfio_send_eventfd(irq_ctx); return IRQ_HANDLED; } static int vfio_set_trigger(struct vfio_platform_device *vdev, int index, - int fd, irq_handler_t handler) + int fd) { struct vfio_platform_irq *irq = &vdev->irqs[index]; struct eventfd_ctx *trigger; - int ret; if (irq->trigger) { - irq_clear_status_flags(irq->hwirq, IRQ_NOAUTOEN); - free_irq(irq->hwirq, irq); - kfree(irq->name); + disable_irq(irq->hwirq); eventfd_ctx_put(irq->trigger); irq->trigger = NULL; } @@ -187,30 +194,20 @@ static int vfio_set_trigger(struct vfio_platform_device *vdev, int index, if (fd < 0) /* Disable only */ return 0; - irq->name = kasprintf(GFP_KERNEL, "vfio-irq[%d](%s)", - irq->hwirq, vdev->name); - if (!irq->name) - return -ENOMEM; - trigger = eventfd_ctx_fdget(fd); - if (IS_ERR(trigger)) { - kfree(irq->name); + if (IS_ERR(trigger)) return PTR_ERR(trigger); - } irq->trigger = trigger; - irq_set_status_flags(irq->hwirq, IRQ_NOAUTOEN); - ret = request_irq(irq->hwirq, handler, 0, irq->name, irq); - if (ret) { - kfree(irq->name); - eventfd_ctx_put(trigger); - irq->trigger = NULL; - return ret; - } - - if (!irq->masked) - enable_irq(irq->hwirq); + /* + * irq->masked effectively provides nested disables within the overall + * enable relative to trigger. Specifically request_irq() is called + * with NO_AUTOEN, therefore the IRQ is initially disabled. The user + * may only further disable the IRQ with a MASK operations because + * irq->masked is initially false. + */ + enable_irq(irq->hwirq); return 0; } @@ -229,7 +226,7 @@ static int vfio_platform_set_irq_trigger(struct vfio_platform_device *vdev, handler = vfio_irq_handler; if (!count && (flags & VFIO_IRQ_SET_DATA_NONE)) - return vfio_set_trigger(vdev, index, -1, handler); + return vfio_set_trigger(vdev, index, -1); if (start != 0 || count != 1) return -EINVAL; @@ -237,7 +234,7 @@ static int vfio_platform_set_irq_trigger(struct vfio_platform_device *vdev, if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { int32_t fd = *(int32_t *)data; - return vfio_set_trigger(vdev, index, fd, handler); + return vfio_set_trigger(vdev, index, fd); } if (flags & VFIO_IRQ_SET_DATA_NONE) { @@ -261,6 +258,14 @@ int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev, unsigned start, unsigned count, uint32_t flags, void *data) = NULL; + /* + * For compatibility, errors from request_irq() are local to the + * SET_IRQS path and reflected in the name pointer. This allows, + * for example, polling mode fallback for an exclusive IRQ failure. + */ + if (IS_ERR(vdev->irqs[index].name)) + return PTR_ERR(vdev->irqs[index].name); + switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) { case VFIO_IRQ_SET_ACTION_MASK: func = vfio_platform_set_irq_mask; @@ -281,7 +286,7 @@ int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev, int vfio_platform_irq_init(struct vfio_platform_device *vdev) { - int cnt = 0, i; + int cnt = 0, i, ret = 0; while (vdev->get_irq(vdev, cnt) >= 0) cnt++; @@ -292,37 +297,70 @@ int vfio_platform_irq_init(struct vfio_platform_device *vdev) for (i = 0; i < cnt; i++) { int hwirq = vdev->get_irq(vdev, i); + irq_handler_t handler = vfio_irq_handler; - if (hwirq < 0) + if (hwirq < 0) { + ret = -EINVAL; goto err; + } spin_lock_init(&vdev->irqs[i].lock); vdev->irqs[i].flags = VFIO_IRQ_INFO_EVENTFD; - if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK) + if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK) { vdev->irqs[i].flags |= VFIO_IRQ_INFO_MASKABLE | VFIO_IRQ_INFO_AUTOMASKED; + handler = vfio_automasked_irq_handler; + } vdev->irqs[i].count = 1; vdev->irqs[i].hwirq = hwirq; vdev->irqs[i].masked = false; + vdev->irqs[i].name = kasprintf(GFP_KERNEL, + "vfio-irq[%d](%s)", hwirq, + vdev->name); + if (!vdev->irqs[i].name) { + ret = -ENOMEM; + goto err; + } + + ret = request_irq(hwirq, handler, IRQF_NO_AUTOEN, + vdev->irqs[i].name, &vdev->irqs[i]); + if (ret) { + kfree(vdev->irqs[i].name); + vdev->irqs[i].name = ERR_PTR(ret); + } } vdev->num_irqs = cnt; return 0; err: + for (--i; i >= 0; i--) { + if (!IS_ERR(vdev->irqs[i].name)) { + free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]); + kfree(vdev->irqs[i].name); + } + } kfree(vdev->irqs); - return -EINVAL; + return ret; } void vfio_platform_irq_cleanup(struct vfio_platform_device *vdev) { int i; - for (i = 0; i < vdev->num_irqs; i++) - vfio_set_trigger(vdev, i, -1, NULL); + for (i = 0; i < vdev->num_irqs; i++) { + vfio_virqfd_disable(&vdev->irqs[i].mask); + vfio_virqfd_disable(&vdev->irqs[i].unmask); + if (!IS_ERR(vdev->irqs[i].name)) { + free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]); + if (vdev->irqs[i].trigger) + eventfd_ctx_put(vdev->irqs[i].trigger); + kfree(vdev->irqs[i].name); + } + } vdev->num_irqs = 0; kfree(vdev->irqs); diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c index 414e98d82b02..b58ba030e7ae 100644 --- a/drivers/vfio/virqfd.c +++ b/drivers/vfio/virqfd.c @@ -104,6 +104,13 @@ static void virqfd_inject(struct work_struct *work) virqfd->thread(virqfd->opaque, virqfd->data); } +static void virqfd_flush_inject(struct work_struct *work) +{ + struct virqfd *virqfd = container_of(work, struct virqfd, flush_inject); + + flush_work(&virqfd->inject); +} + int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), void (*thread)(void *, void *), @@ -127,6 +134,7 @@ int vfio_virqfd_enable(void *opaque, INIT_WORK(&virqfd->shutdown, virqfd_shutdown); INIT_WORK(&virqfd->inject, virqfd_inject); + INIT_WORK(&virqfd->flush_inject, virqfd_flush_inject); irqfd = fdget(fd); if (!irqfd.file) { @@ -217,6 +225,19 @@ void vfio_virqfd_disable(struct virqfd **pvirqfd) } EXPORT_SYMBOL_GPL(vfio_virqfd_disable); +void vfio_virqfd_flush_thread(struct virqfd **pvirqfd) +{ + unsigned long flags; + + spin_lock_irqsave(&virqfd_lock, flags); + if (*pvirqfd && (*pvirqfd)->thread) + queue_work(vfio_irqfd_cleanup_wq, &(*pvirqfd)->flush_inject); + spin_unlock_irqrestore(&virqfd_lock, flags); + + flush_workqueue(vfio_irqfd_cleanup_wq); +} +EXPORT_SYMBOL_GPL(vfio_virqfd_flush_thread); + module_init(vfio_virqfd_init); module_exit(vfio_virqfd_exit); diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c index b0e690f41025..9ca99da3a56a 100644 --- a/drivers/video/fbdev/core/fbmon.c +++ b/drivers/video/fbdev/core/fbmon.c @@ -1311,7 +1311,7 @@ int fb_get_mode(int flags, u32 val, struct fb_var_screeninfo *var, struct fb_inf int fb_videomode_from_videomode(const struct videomode *vm, struct fb_videomode *fbmode) { - unsigned int htotal, vtotal; + unsigned int htotal, vtotal, total; fbmode->xres = vm->hactive; fbmode->left_margin = vm->hback_porch; @@ -1344,8 +1344,9 @@ int fb_videomode_from_videomode(const struct videomode *vm, vtotal = vm->vactive + vm->vfront_porch + vm->vback_porch + vm->vsync_len; /* prevent division by zero */ - if (htotal && vtotal) { - fbmode->refresh = vm->pixelclock / (htotal * vtotal); + total = htotal * vtotal; + if (total) { + fbmode->refresh = vm->pixelclock / total; /* a mode must have htotal and vtotal != 0 or it is invalid */ } else { fbmode->refresh = 0; diff --git a/drivers/video/fbdev/via/accel.c b/drivers/video/fbdev/via/accel.c index 0a1bc7a4d785..1e04026f0809 100644 --- a/drivers/video/fbdev/via/accel.c +++ b/drivers/video/fbdev/via/accel.c @@ -115,7 +115,7 @@ static int hw_bitblt_1(void __iomem *engine, u8 op, u32 width, u32 height, if (op != VIA_BITBLT_FILL) { tmp = src_mem ? 0 : src_addr; - if (dst_addr & 0xE0000007) { + if (tmp & 0xE0000007) { printk(KERN_WARNING "hw_bitblt_1: Unsupported source " "address %X\n", tmp); return -EINVAL; @@ -260,7 +260,7 @@ static int hw_bitblt_2(void __iomem *engine, u8 op, u32 width, u32 height, writel(tmp, engine + 0x18); tmp = src_mem ? 0 : src_addr; - if (dst_addr & 0xE0000007) { + if (tmp & 0xE0000007) { printk(KERN_WARNING "hw_bitblt_2: Unsupported source " "address %X\n", tmp); return -EINVAL; diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index c2b733ef95b0..2f8f3bd56b00 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -455,13 +455,19 @@ EXPORT_SYMBOL_GPL(unregister_virtio_device); int virtio_device_freeze(struct virtio_device *dev) { struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); + int ret; virtio_config_disable(dev); dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; - if (drv && drv->freeze) - return drv->freeze(dev); + if (drv && drv->freeze) { + ret = drv->freeze(dev); + if (ret) { + virtio_config_enable(dev); + return ret; + } + } return 0; } diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index ee691b20d4a3..04ff194fecf4 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -936,8 +936,8 @@ static void shutdown_pirq(struct irq_data *data) return; do_mask(info, EVT_MASK_REASON_EXPLICIT); - xen_evtchn_close(evtchn); xen_irq_info_cleanup(info); + xen_evtchn_close(evtchn); } static void enable_pirq(struct irq_data *data) @@ -981,8 +981,6 @@ static void __unbind_from_irq(unsigned int irq) unsigned int cpu = cpu_from_irq(irq); struct xenbus_device *dev; - xen_evtchn_close(evtchn); - switch (type_from_irq(irq)) { case IRQT_VIRQ: per_cpu(virq_to_irq, cpu)[virq_from_irq(irq)] = -1; @@ -1000,6 +998,7 @@ static void __unbind_from_irq(unsigned int irq) } xen_irq_info_cleanup(info); + xen_evtchn_close(evtchn); } xen_free_irq(irq); diff --git a/fs/Kconfig b/fs/Kconfig index 418248887aa6..d4d9623a87e1 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -346,7 +346,7 @@ config LOCKD config LOCKD_V4 bool - depends on NFSD_V3 || NFS_V3 + depends on NFSD || NFS_V3 depends on FILE_LOCKING default y @@ -564,8 +564,8 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { - struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw); - struct kioctx *ctx = req->ki_ctx; + struct aio_kiocb *req; + struct kioctx *ctx; unsigned long flags; /* @@ -575,9 +575,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) if (!(iocb->ki_flags & IOCB_AIO_RW)) return; + req = container_of(iocb, struct aio_kiocb, rw); + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; + ctx = req->ki_ctx; + spin_lock_irqsave(&ctx->ctx_lock, flags); list_add_tail(&req->ki_list, &ctx->active_reqs); req->ki_cancel = cancel; diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index fab7eb76e53b..58b0f04d7123 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -161,8 +161,15 @@ struct dentry *btrfs_get_parent(struct dentry *child) ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto fail; + if (ret == 0) { + /* + * Key with offset of -1 found, there would have to exist an + * inode with such number or a root with such id. + */ + ret = -EUCLEAN; + goto fail; + } - BUG_ON(ret == 0); /* Key with offset of -1 found */ if (path->slots[0] == 0) { ret = -ENOENT; goto fail; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 0d1715ebdef9..6ffd34d39e99 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3972,7 +3972,17 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, gen = fs_info->last_trans_committed; for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { - bytenr = btrfs_sb_offset(i); + ret = btrfs_sb_log_location(scrub_dev, i, 0, &bytenr); + if (ret == -ENOENT) + break; + + if (ret) { + spin_lock(&sctx->stat_lock); + sctx->stat.super_errors++; + spin_unlock(&sctx->stat_lock); + continue; + } + if (bytenr + BTRFS_SUPER_INFO_SIZE > scrub_dev->commit_total_bytes) break; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 9900f879fa34..f1ef176a6424 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -976,7 +976,15 @@ static int iterate_inode_ref(struct btrfs_root *root, struct btrfs_path *path, ret = PTR_ERR(start); goto out; } - BUG_ON(start < p->buf); + if (unlikely(start < p->buf)) { + btrfs_err(root->fs_info, + "send: path ref buffer underflow for key (%llu %u %llu)", + found_key->objectid, + found_key->type, + found_key->offset); + ret = -EINVAL; + goto out; + } } p->start = start; } else { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index cc18ba50a61c..36e77956c63f 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1473,7 +1473,7 @@ static bool contains_pending_extent(struct btrfs_device *device, u64 *start, if (in_range(physical_start, *start, len) || in_range(*start, physical_start, - physical_end - physical_start)) { + physical_end + 1 - physical_start)) { *start = physical_end + 1; return true; } @@ -3358,7 +3358,17 @@ again: mutex_unlock(&fs_info->reclaim_bgs_lock); goto error; } - BUG_ON(ret == 0); /* Corruption */ + if (ret == 0) { + /* + * On the first search we would find chunk tree with + * offset -1, which is not possible. On subsequent + * loops this would find an existing item on an invalid + * offset (one less than the previous one, wrong + * alignment and size). + */ + ret = -EUCLEAN; + goto error; + } ret = btrfs_previous_item(chunk_root, path, key.objectid, key.type); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a3e4811b7871..1cbfb74c5380 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1145,7 +1145,7 @@ next_pdu: } memalloc_noreclaim_restore(noreclaim_flag); - module_put_and_exit(0); + module_put_and_kthread_exit(0); } /* diff --git a/fs/exec.c b/fs/exec.c index 972de9df56d1..cba914eb4acc 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -889,6 +889,7 @@ int transfer_args_to_stack(struct linux_binprm *bprm, goto out; } + bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp; out: diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 3ef80d000e13..584bdd912cdd 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -18,7 +18,7 @@ #include <linux/sched.h> #include <linux/cred.h> -#define dprintk(fmt, args...) do{}while(0) +#define dprintk(fmt, args...) pr_debug(fmt, ##args) static int get_name(const struct path *path, char *name, struct dentry *child); @@ -132,8 +132,8 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, inode_unlock(dentry->d_inode); if (IS_ERR(parent)) { - dprintk("%s: get_parent of %ld failed, err %d\n", - __func__, dentry->d_inode->i_ino, PTR_ERR(parent)); + dprintk("get_parent of %lu failed, err %ld\n", + dentry->d_inode->i_ino, PTR_ERR(parent)); return parent; } @@ -147,7 +147,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, dprintk("%s: found name: %s\n", __func__, nbuf); tmp = lookup_one_unlocked(mnt_user_ns(mnt), nbuf, parent, strlen(nbuf)); if (IS_ERR(tmp)) { - dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp)); + dprintk("lookup failed: %ld\n", PTR_ERR(tmp)); err = PTR_ERR(tmp); goto out_err; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a254c2ba0357..8dba416aa6c1 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2950,7 +2950,10 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); - seq_puts(seq, " ]\n"); + seq_puts(seq, " ]"); + if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info)) + seq_puts(seq, " Block bitmap corrupted!"); + seq_puts(seq, "\n"); return 0; } @@ -4696,10 +4699,16 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) .fe_len = ac->ac_g_ex.fe_len, }; loff_t orig_goal_end = extent_logical_end(sbi, &ex); + loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex); - /* we can't allocate as much as normalizer wants. - * so, found space must get proper lstart - * to cover original request */ + /* + * We can't allocate as much as normalizer wants, so we try + * to get proper lstart to cover the original request, except + * when the goal doesn't cover the original request as below: + * + * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048 + * best_ex:0/200(200) -> adjusted: 1848/2048(200) + */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); @@ -4711,7 +4720,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) * 1. Check if best ex can be kept at end of goal and still * cover original start * 2. Else, check if best ex can be kept at start of goal and - * still cover original start + * still cover original end * 3. Else, keep the best ex at start of original request. */ ex.fe_len = ac->ac_b_ex.fe_len; @@ -4721,7 +4730,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) goto adjust_bex; ex.fe_logical = ac->ac_g_ex.fe_logical; - if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex)) + if (o_ex_end <= extent_logical_end(sbi, &ex)) goto adjust_bex; ex.fe_logical = ac->ac_o_ex.fe_logical; @@ -4729,7 +4738,6 @@ adjust_bex: ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); - BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 70d4f6e3aaa7..4687d5972074 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1559,7 +1559,8 @@ exit_journal: int gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); - int meta_bg = ext4_has_feature_meta_bg(sb); + int meta_bg = ext4_has_feature_meta_bg(sb) && + gdb_num >= le32_to_cpu(es->s_first_meta_bg); sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - ext4_group_first_block_no(sb, 0); sector_t old_gdb = 0; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 65716a17059d..b09b7a6b7a15 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -46,6 +46,7 @@ #include <linux/part_stat.h> #include <linux/kthread.h> #include <linux/freezer.h> +#include <linux/fsnotify.h> #include "ext4.h" #include "ext4_extents.h" /* Needed for trace points definition */ @@ -753,6 +754,8 @@ void __ext4_error(struct super_block *sb, const char *function, sb->s_id, function, line, current->comm, &vaf); va_end(args); } + fsnotify_sb_error(sb, NULL, error ? error : EFSCORRUPTED); + ext4_handle_error(sb, force_ro, error, 0, block, function, line); } @@ -783,6 +786,8 @@ void __ext4_error_inode(struct inode *inode, const char *function, current->comm, &vaf); va_end(args); } + fsnotify_sb_error(inode->i_sb, inode, error ? error : EFSCORRUPTED); + ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block, function, line); } @@ -821,6 +826,8 @@ void __ext4_error_file(struct file *file, const char *function, current->comm, path, &vaf); va_end(args); } + fsnotify_sb_error(inode->i_sb, inode, EFSCORRUPTED); + ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block, function, line); } @@ -888,6 +895,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n", sb->s_id, function, line, errstr); } + fsnotify_sb_error(sb, NULL, errno ? errno : EFSCORRUPTED); ext4_handle_error(sb, false, -errno, 0, 0, function, line); } @@ -5843,7 +5851,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) - ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user"); + ext4_abort(sb, ESHUTDOWN, "Abort forced by user"); sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); @@ -6162,6 +6170,10 @@ static int ext4_write_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to commit dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6178,6 +6190,10 @@ static int ext4_acquire_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to acquire dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6197,6 +6213,10 @@ static int ext4_release_dquot(struct dquot *dquot) return PTR_ERR(handle); } ret = dquot_release(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to release dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index af191371c352..bab63eeaf9cb 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -130,6 +130,12 @@ fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp, fid->parent_i_gen = parent->i_generation; type = FILEID_FAT_WITH_PARENT; *lenp = FAT_FID_SIZE_WITH_PARENT; + } else { + /* + * We need to initialize this field because the fh is actually + * 12 bytes long + */ + fid->parent_i_pos_hi = 0; } return type; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 4ea52906ae15..44d1c8cc58a4 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -390,6 +390,10 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name goto out_put_forget; if (fuse_invalid_attr(&outarg->attr)) goto out_put_forget; + if (outarg->nodeid == FUSE_ROOT_ID && outarg->generation != 0) { + pr_warn_once("root generation should be zero\n"); + outarg->generation = 0; + } *inode = fuse_iget(sb, outarg->nodeid, outarg->generation, &outarg->attr, entry_attr_timeout(outarg), diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 4b8f094345e1..55b7ca26fb8a 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -899,7 +899,6 @@ static inline bool fuse_stale_inode(const struct inode *inode, int generation, static inline void fuse_make_bad(struct inode *inode) { - remove_inode_hash(inode); set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state); } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 97dc24557bf2..62b4143ccf26 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -413,8 +413,11 @@ retry: } else if (fuse_stale_inode(inode, generation, attr)) { /* nodeid was reused, any I/O on the old inode should fail */ fuse_make_bad(inode); - iput(inode); - goto retry; + if (inode != d_inode(sb->s_root)) { + remove_inode_hash(inode); + iput(inode); + goto retry; + } } fi = get_fuse_inode(inode); spin_lock(&fi->lock); diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 0c6eacfcbeef..07252d2a7f5f 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -908,8 +908,22 @@ root_found: * we then decide whether to use the Joliet descriptor. */ inode = isofs_iget(s, sbi->s_firstdatazone, 0); - if (IS_ERR(inode)) - goto out_no_root; + + /* + * Fix for broken CDs with a corrupt root inode but a correct Joliet + * root directory. + */ + if (IS_ERR(inode)) { + if (joliet_level && sbi->s_firstdatazone != first_data_zone) { + printk(KERN_NOTICE + "ISOFS: root inode is unusable. " + "Disabling Rock Ridge and switching to Joliet."); + sbi->s_rock = 0; + inode = NULL; + } else { + goto out_no_root; + } + } /* * Fix for broken CDs with Rock Ridge and empty ISO root directory but diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 0613b8d14409..14cd86a14012 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -5759,15 +5759,21 @@ static int set_file_allocation_info(struct ksmbd_work *work, loff_t alloc_blks; struct inode *inode; + struct kstat stat; int rc; if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; + rc = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (rc) + return rc; + alloc_blks = (le64_to_cpu(file_alloc_info->AllocationSize) + 511) >> 9; inode = file_inode(fp->filp); - if (alloc_blks > inode->i_blocks) { + if (alloc_blks > stat.blocks) { smb_break_all_levII_oplock(work, fp, 1); rc = vfs_fallocate(fp->filp, FALLOC_FL_KEEP_SIZE, 0, alloc_blks * 512); @@ -5775,7 +5781,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, pr_err("vfs_fallocate is failed : %d\n", rc); return rc; } - } else if (alloc_blks < inode->i_blocks) { + } else if (alloc_blks < stat.blocks) { loff_t size; /* diff --git a/fs/lockd/host.c b/fs/lockd/host.c index f802223e71ab..cdc8e12cdac4 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -164,7 +164,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni, host->h_addrbuf = nsm->sm_addrbuf; host->net = ni->net; host->h_cred = get_cred(ni->cred); - strlcpy(host->nodename, utsname()->nodename, sizeof(host->nodename)); + strscpy(host->nodename, utsname()->nodename, sizeof(host->nodename)); out: return host; diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index b632be3ad57b..5579e67da17d 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -54,13 +54,9 @@ EXPORT_SYMBOL_GPL(nlmsvc_ops); static DEFINE_MUTEX(nlmsvc_mutex); static unsigned int nlmsvc_users; -static struct task_struct *nlmsvc_task; -static struct svc_rqst *nlmsvc_rqst; +static struct svc_serv *nlmsvc_serv; unsigned long nlmsvc_timeout; -static atomic_t nlm_ntf_refcnt = ATOMIC_INIT(0); -static DECLARE_WAIT_QUEUE_HEAD(nlm_ntf_wq); - unsigned int lockd_net_id; /* @@ -184,6 +180,10 @@ lockd(void *vrqstp) nlm_shutdown_hosts(); cancel_delayed_work_sync(&ln->grace_period_end); locks_end_grace(&ln->lockd_manager); + + dprintk("lockd_down: service stopped\n"); + + svc_exit_thread(rqstp); return 0; } @@ -196,8 +196,8 @@ static int create_lockd_listener(struct svc_serv *serv, const char *name, xprt = svc_find_xprt(serv, name, net, family, 0); if (xprt == NULL) - return svc_create_xprt(serv, name, net, family, port, - SVC_SOCK_DEFAULTS, cred); + return svc_xprt_create(serv, name, net, family, port, + SVC_SOCK_DEFAULTS, cred); svc_xprt_put(xprt); return 0; } @@ -247,7 +247,8 @@ out_err: if (warned++ == 0) printk(KERN_WARNING "lockd_up: makesock failed, error=%d\n", err); - svc_shutdown_net(serv, net); + svc_xprt_destroy_all(serv, net); + svc_rpcb_cleanup(serv, net); return err; } @@ -285,13 +286,12 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net) nlm_shutdown_hosts_net(net); cancel_delayed_work_sync(&ln->grace_period_end); locks_end_grace(&ln->lockd_manager); - svc_shutdown_net(serv, net); - dprintk("%s: per-net data destroyed; net=%x\n", - __func__, net->ns.inum); + svc_xprt_destroy_all(serv, net); + svc_rpcb_cleanup(serv, net); } } else { - pr_err("%s: no users! task=%p, net=%x\n", - __func__, nlmsvc_task, net->ns.inum); + pr_err("%s: no users! net=%x\n", + __func__, net->ns.inum); BUG(); } } @@ -302,20 +302,16 @@ static int lockd_inetaddr_event(struct notifier_block *this, struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; struct sockaddr_in sin; - if ((event != NETDEV_DOWN) || - !atomic_inc_not_zero(&nlm_ntf_refcnt)) + if (event != NETDEV_DOWN) goto out; - if (nlmsvc_rqst) { + if (nlmsvc_serv) { dprintk("lockd_inetaddr_event: removed %pI4\n", &ifa->ifa_local); sin.sin_family = AF_INET; sin.sin_addr.s_addr = ifa->ifa_local; - svc_age_temp_xprts_now(nlmsvc_rqst->rq_server, - (struct sockaddr *)&sin); + svc_age_temp_xprts_now(nlmsvc_serv, (struct sockaddr *)&sin); } - atomic_dec(&nlm_ntf_refcnt); - wake_up(&nlm_ntf_wq); out: return NOTIFY_DONE; @@ -332,21 +328,17 @@ static int lockd_inet6addr_event(struct notifier_block *this, struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; struct sockaddr_in6 sin6; - if ((event != NETDEV_DOWN) || - !atomic_inc_not_zero(&nlm_ntf_refcnt)) + if (event != NETDEV_DOWN) goto out; - if (nlmsvc_rqst) { + if (nlmsvc_serv) { dprintk("lockd_inet6addr_event: removed %pI6\n", &ifa->addr); sin6.sin6_family = AF_INET6; sin6.sin6_addr = ifa->addr; if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL) sin6.sin6_scope_id = ifa->idev->dev->ifindex; - svc_age_temp_xprts_now(nlmsvc_rqst->rq_server, - (struct sockaddr *)&sin6); + svc_age_temp_xprts_now(nlmsvc_serv, (struct sockaddr *)&sin6); } - atomic_dec(&nlm_ntf_refcnt); - wake_up(&nlm_ntf_wq); out: return NOTIFY_DONE; @@ -357,86 +349,14 @@ static struct notifier_block lockd_inet6addr_notifier = { }; #endif -static void lockd_unregister_notifiers(void) -{ - unregister_inetaddr_notifier(&lockd_inetaddr_notifier); -#if IS_ENABLED(CONFIG_IPV6) - unregister_inet6addr_notifier(&lockd_inet6addr_notifier); -#endif - wait_event(nlm_ntf_wq, atomic_read(&nlm_ntf_refcnt) == 0); -} - -static void lockd_svc_exit_thread(void) -{ - atomic_dec(&nlm_ntf_refcnt); - lockd_unregister_notifiers(); - svc_exit_thread(nlmsvc_rqst); -} - -static int lockd_start_svc(struct svc_serv *serv) +static int lockd_get(void) { + struct svc_serv *serv; int error; - if (nlmsvc_rqst) + if (nlmsvc_serv) { + nlmsvc_users++; return 0; - - /* - * Create the kernel thread and wait for it to start. - */ - nlmsvc_rqst = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE); - if (IS_ERR(nlmsvc_rqst)) { - error = PTR_ERR(nlmsvc_rqst); - printk(KERN_WARNING - "lockd_up: svc_rqst allocation failed, error=%d\n", - error); - lockd_unregister_notifiers(); - goto out_rqst; - } - - atomic_inc(&nlm_ntf_refcnt); - svc_sock_update_bufs(serv); - serv->sv_maxconn = nlm_max_connections; - - nlmsvc_task = kthread_create(lockd, nlmsvc_rqst, "%s", serv->sv_name); - if (IS_ERR(nlmsvc_task)) { - error = PTR_ERR(nlmsvc_task); - printk(KERN_WARNING - "lockd_up: kthread_run failed, error=%d\n", error); - goto out_task; - } - nlmsvc_rqst->rq_task = nlmsvc_task; - wake_up_process(nlmsvc_task); - - dprintk("lockd_up: service started\n"); - return 0; - -out_task: - lockd_svc_exit_thread(); - nlmsvc_task = NULL; -out_rqst: - nlmsvc_rqst = NULL; - return error; -} - -static const struct svc_serv_ops lockd_sv_ops = { - .svo_shutdown = svc_rpcb_cleanup, - .svo_enqueue_xprt = svc_xprt_do_enqueue, -}; - -static struct svc_serv *lockd_create_svc(void) -{ - struct svc_serv *serv; - - /* - * Check whether we're already up and running. - */ - if (nlmsvc_rqst) { - /* - * Note: increase service usage, because later in case of error - * svc_destroy() will be called. - */ - svc_get(nlmsvc_rqst->rq_server); - return nlmsvc_rqst->rq_server; } /* @@ -451,17 +371,44 @@ static struct svc_serv *lockd_create_svc(void) nlm_timeout = LOCKD_DFLT_TIMEO; nlmsvc_timeout = nlm_timeout * HZ; - serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, &lockd_sv_ops); + serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, lockd); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); - return ERR_PTR(-ENOMEM); + return -ENOMEM; } + + serv->sv_maxconn = nlm_max_connections; + error = svc_set_num_threads(serv, NULL, 1); + /* The thread now holds the only reference */ + svc_put(serv); + if (error < 0) + return error; + + nlmsvc_serv = serv; register_inetaddr_notifier(&lockd_inetaddr_notifier); #if IS_ENABLED(CONFIG_IPV6) register_inet6addr_notifier(&lockd_inet6addr_notifier); #endif dprintk("lockd_up: service created\n"); - return serv; + nlmsvc_users++; + return 0; +} + +static void lockd_put(void) +{ + if (WARN(nlmsvc_users <= 0, "lockd_down: no users!\n")) + return; + if (--nlmsvc_users) + return; + + unregister_inetaddr_notifier(&lockd_inetaddr_notifier); +#if IS_ENABLED(CONFIG_IPV6) + unregister_inet6addr_notifier(&lockd_inet6addr_notifier); +#endif + + svc_set_num_threads(nlmsvc_serv, NULL, 0); + nlmsvc_serv = NULL; + dprintk("lockd_down: service destroyed\n"); } /* @@ -469,36 +416,21 @@ static struct svc_serv *lockd_create_svc(void) */ int lockd_up(struct net *net, const struct cred *cred) { - struct svc_serv *serv; int error; mutex_lock(&nlmsvc_mutex); - serv = lockd_create_svc(); - if (IS_ERR(serv)) { - error = PTR_ERR(serv); - goto err_create; - } + error = lockd_get(); + if (error) + goto err; - error = lockd_up_net(serv, net, cred); + error = lockd_up_net(nlmsvc_serv, net, cred); if (error < 0) { - lockd_unregister_notifiers(); - goto err_put; + lockd_put(); + goto err; } - error = lockd_start_svc(serv); - if (error < 0) { - lockd_down_net(serv, net); - goto err_put; - } - nlmsvc_users++; - /* - * Note: svc_serv structures have an initial use count of 1, - * so we exit through here on both success and failure. - */ -err_put: - svc_destroy(serv); -err_create: +err: mutex_unlock(&nlmsvc_mutex); return error; } @@ -511,27 +443,8 @@ void lockd_down(struct net *net) { mutex_lock(&nlmsvc_mutex); - lockd_down_net(nlmsvc_rqst->rq_server, net); - if (nlmsvc_users) { - if (--nlmsvc_users) - goto out; - } else { - printk(KERN_ERR "lockd_down: no users! task=%p\n", - nlmsvc_task); - BUG(); - } - - if (!nlmsvc_task) { - printk(KERN_ERR "lockd_down: no lockd running.\n"); - BUG(); - } - kthread_stop(nlmsvc_task); - dprintk("lockd_down: service stopped\n"); - lockd_svc_exit_thread(); - dprintk("lockd_down: service destroyed\n"); - nlmsvc_task = NULL; - nlmsvc_rqst = NULL; -out: + lockd_down_net(nlmsvc_serv, net); + lockd_put(); mutex_unlock(&nlmsvc_mutex); } EXPORT_SYMBOL_GPL(lockd_down); @@ -780,11 +693,9 @@ module_exit(exit_nlm); static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp) { const struct svc_procedure *procp = rqstp->rq_procinfo; - struct kvec *argv = rqstp->rq_arg.head; - struct kvec *resv = rqstp->rq_res.head; svcxdr_init_decode(rqstp); - if (!procp->pc_decode(rqstp, argv->iov_base)) + if (!procp->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; *statp = procp->pc_func(rqstp); @@ -794,7 +705,7 @@ static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp) return 1; svcxdr_init_encode(rqstp); - if (!procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) + if (!procp->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; return 1; diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 1c9214801e69..e318d55e4c0e 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -52,6 +52,7 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, *filp = file; /* Set up the missing parts of the file_lock structure */ + lock->fl.fl_flags = FL_POSIX; lock->fl.fl_file = file->f_file[mode]; lock->fl.fl_pid = current->tgid; lock->fl.fl_start = (loff_t)lock->lock_start; @@ -95,6 +96,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; + struct nlm_lockowner *test_owner; __be32 rc = rpc_success; dprintk("lockd: TEST4 called\n"); @@ -104,6 +106,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file))) return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; + test_owner = argp->lock.fl.fl_owner; /* Now check for conflicting locks */ resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie); if (resp->status == nlm_drop_reply) @@ -111,7 +114,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) else dprintk("lockd: TEST4 status %d\n", ntohl(resp->status)); - nlmsvc_release_lockowner(&argp->lock); + nlmsvc_put_lockowner(test_owner); nlmsvc_release_host(host); nlm_release_file(file); return rc; @@ -521,6 +524,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_void, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_void), + .pc_argzero = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "NULL", @@ -530,6 +534,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_testargs, .pc_encode = nlm4svc_encode_testres, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+2+No+Rg, .pc_name = "TEST", @@ -539,6 +544,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_lockargs, .pc_encode = nlm4svc_encode_res, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, .pc_name = "LOCK", @@ -548,6 +554,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_cancargs, .pc_encode = nlm4svc_encode_res, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, .pc_name = "CANCEL", @@ -557,6 +564,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_unlockargs, .pc_encode = nlm4svc_encode_res, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, .pc_name = "UNLOCK", @@ -566,6 +574,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_testargs, .pc_encode = nlm4svc_encode_res, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, .pc_name = "GRANTED", @@ -575,6 +584,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_testargs, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "TEST_MSG", @@ -584,6 +594,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_lockargs, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "LOCK_MSG", @@ -593,6 +604,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_cancargs, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "CANCEL_MSG", @@ -602,6 +614,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_unlockargs, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "UNLOCK_MSG", @@ -611,6 +624,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_testargs, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "GRANTED_MSG", @@ -620,6 +634,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_void, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_res), + .pc_argzero = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "TEST_RES", @@ -629,6 +644,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_void, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_res), + .pc_argzero = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "LOCK_RES", @@ -638,6 +654,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_void, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_res), + .pc_argzero = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "CANCEL_RES", @@ -647,6 +664,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_void, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_res), + .pc_argzero = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "UNLOCK_RES", @@ -656,6 +674,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_res, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_res), + .pc_argzero = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "GRANTED_RES", @@ -665,6 +684,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_reboot, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_reboot), + .pc_argzero = sizeof(struct nlm_reboot), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "SM_NOTIFY", @@ -674,6 +694,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_void, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_void), + .pc_argzero = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = 0, .pc_name = "UNUSED", @@ -683,6 +704,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_void, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_void), + .pc_argzero = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = 0, .pc_name = "UNUSED", @@ -692,6 +714,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_void, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_void), + .pc_argzero = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = 0, .pc_name = "UNUSED", @@ -701,6 +724,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_shareargs, .pc_encode = nlm4svc_encode_shareres, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+1, .pc_name = "SHARE", @@ -710,6 +734,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_shareargs, .pc_encode = nlm4svc_encode_shareres, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+1, .pc_name = "UNSHARE", @@ -719,6 +744,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_lockargs, .pc_encode = nlm4svc_encode_res, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, .pc_name = "NM_LOCK", @@ -728,6 +754,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_decode = nlm4svc_decode_notify, .pc_encode = nlm4svc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "FREE_ALL", diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index e9b85d8fd5fe..55c0a0331188 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -340,7 +340,7 @@ nlmsvc_get_lockowner(struct nlm_lockowner *lockowner) return lockowner; } -static void nlmsvc_put_lockowner(struct nlm_lockowner *lockowner) +void nlmsvc_put_lockowner(struct nlm_lockowner *lockowner) { if (!refcount_dec_and_lock(&lockowner->count, &lockowner->host->h_lock)) return; @@ -470,8 +470,8 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, struct nlm_host *host, struct nlm_lock *lock, int wait, struct nlm_cookie *cookie, int reclaim) { - struct nlm_block *block = NULL; struct inode *inode = nlmsvc_file_inode(file); + struct nlm_block *block = NULL; int error; int mode; int async_block = 0; @@ -484,7 +484,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, (long long)lock->fl.fl_end, wait); - if (inode->i_sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS) { + if (!exportfs_lock_op_is_async(inode->i_sb->s_export_op)) { async_block = wait; wait = 0; } @@ -588,7 +588,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, int error; int mode; __be32 ret; - struct nlm_lockowner *test_owner; dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n", nlmsvc_file_inode(file)->i_sb->s_id, @@ -602,9 +601,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, goto out; } - /* If there's a conflicting lock, remember to clean up the test lock */ - test_owner = (struct nlm_lockowner *)lock->fl.fl_owner; - mode = lock_to_openmode(&lock->fl); error = vfs_test_lock(file->f_file[mode], &lock->fl); if (error) { @@ -633,10 +629,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, conflock->fl.fl_end = lock->fl.fl_end; locks_release_private(&lock->fl); - /* Clean up the test lock */ - lock->fl.fl_owner = NULL; - nlmsvc_put_lockowner(test_owner); - ret = nlm_lck_denied; out: return ret; @@ -665,11 +657,13 @@ nlmsvc_unlock(struct net *net, struct nlm_file *file, struct nlm_lock *lock) nlmsvc_cancel_blocked(net, file, lock); lock->fl.fl_type = F_UNLCK; - if (file->f_file[O_RDONLY]) - error = vfs_lock_file(file->f_file[O_RDONLY], F_SETLK, + lock->fl.fl_file = file->f_file[O_RDONLY]; + if (lock->fl.fl_file) + error = vfs_lock_file(lock->fl.fl_file, F_SETLK, &lock->fl, NULL); - if (file->f_file[O_WRONLY]) - error = vfs_lock_file(file->f_file[O_WRONLY], F_SETLK, + lock->fl.fl_file = file->f_file[O_WRONLY]; + if (lock->fl.fl_file) + error |= vfs_lock_file(lock->fl.fl_file, F_SETLK, &lock->fl, NULL); return (error < 0)? nlm_lck_denied_nolocks : nlm_granted; @@ -703,9 +697,10 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l block = nlmsvc_lookup_block(file, lock); mutex_unlock(&file->f_mutex); if (block != NULL) { - mode = lock_to_openmode(&lock->fl); - vfs_cancel_lock(block->b_file->f_file[mode], - &block->b_call->a_args.lock.fl); + struct file_lock *fl = &block->b_call->a_args.lock.fl; + + mode = lock_to_openmode(fl); + vfs_cancel_lock(block->b_file->f_file[mode], fl); status = nlmsvc_unlink_block(block); nlmsvc_release_block(block); } diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 99696d3f6dd6..2a615032f5d0 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -77,6 +77,7 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, /* Set up the missing parts of the file_lock structure */ mode = lock_to_openmode(&lock->fl); + lock->fl.fl_flags = FL_POSIX; lock->fl.fl_file = file->f_file[mode]; lock->fl.fl_pid = current->tgid; lock->fl.fl_lmops = &nlmsvc_lock_operations; @@ -116,6 +117,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; + struct nlm_lockowner *test_owner; __be32 rc = rpc_success; dprintk("lockd: TEST called\n"); @@ -125,6 +127,8 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file))) return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; + test_owner = argp->lock.fl.fl_owner; + /* Now check for conflicting locks */ resp->status = cast_status(nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie)); if (resp->status == nlm_drop_reply) @@ -133,7 +137,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) dprintk("lockd: TEST status %d vers %d\n", ntohl(resp->status), rqstp->rq_vers); - nlmsvc_release_lockowner(&argp->lock); + nlmsvc_put_lockowner(test_owner); nlmsvc_release_host(host); nlm_release_file(file); return rc; @@ -554,6 +558,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_void, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_void), + .pc_argzero = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "NULL", @@ -563,6 +568,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_testargs, .pc_encode = nlmsvc_encode_testres, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+2+No+Rg, .pc_name = "TEST", @@ -572,6 +578,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_lockargs, .pc_encode = nlmsvc_encode_res, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, .pc_name = "LOCK", @@ -581,6 +588,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_cancargs, .pc_encode = nlmsvc_encode_res, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, .pc_name = "CANCEL", @@ -590,6 +598,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_unlockargs, .pc_encode = nlmsvc_encode_res, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, .pc_name = "UNLOCK", @@ -599,6 +608,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_testargs, .pc_encode = nlmsvc_encode_res, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, .pc_name = "GRANTED", @@ -608,6 +618,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_testargs, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "TEST_MSG", @@ -617,6 +628,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_lockargs, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "LOCK_MSG", @@ -626,6 +638,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_cancargs, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "CANCEL_MSG", @@ -635,6 +648,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_unlockargs, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "UNLOCK_MSG", @@ -644,6 +658,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_testargs, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "GRANTED_MSG", @@ -653,6 +668,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_void, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_res), + .pc_argzero = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "TEST_RES", @@ -662,6 +678,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_void, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_res), + .pc_argzero = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "LOCK_RES", @@ -671,6 +688,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_void, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_res), + .pc_argzero = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "CANCEL_RES", @@ -680,6 +698,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_void, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_res), + .pc_argzero = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "UNLOCK_RES", @@ -689,6 +708,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_res, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_res), + .pc_argzero = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "GRANTED_RES", @@ -698,6 +718,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_reboot, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_reboot), + .pc_argzero = sizeof(struct nlm_reboot), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "SM_NOTIFY", @@ -707,6 +728,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_void, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_void), + .pc_argzero = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "UNUSED", @@ -716,6 +738,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_void, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_void), + .pc_argzero = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "UNUSED", @@ -725,6 +748,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_void, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_void), + .pc_argzero = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, .pc_name = "UNUSED", @@ -734,6 +758,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_shareargs, .pc_encode = nlmsvc_encode_shareres, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+1, .pc_name = "SHARE", @@ -743,6 +768,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_shareargs, .pc_encode = nlmsvc_encode_shareres, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+1, .pc_name = "UNSHARE", @@ -752,6 +778,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_lockargs, .pc_encode = nlmsvc_encode_res, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, .pc_name = "NM_LOCK", @@ -761,6 +788,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_decode = nlmsvc_decode_notify, .pc_encode = nlmsvc_encode_void, .pc_argsize = sizeof(struct nlm_args), + .pc_argzero = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = 0, .pc_name = "FREE_ALL", diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 3515f17eaf3f..e3b6229e7ae5 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -210,7 +210,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file, { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; - struct file_lock_context *flctx = inode->i_flctx; + struct file_lock_context *flctx = locks_inode_context(inode); struct nlm_host *lockhost; if (!flctx || list_empty_careful(&flctx->flc_posix)) @@ -265,7 +265,7 @@ nlm_file_inuse(struct nlm_file *file) { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; - struct file_lock_context *flctx = inode->i_flctx; + struct file_lock_context *flctx = locks_inode_context(inode); if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares) return 1; diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 9235e60b1769..2fb5748dae0c 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -145,137 +145,131 @@ svcxdr_encode_testrply(struct xdr_stream *xdr, const struct nlm_res *resp) * Decode Call arguments */ -int -nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int -nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + return true; } -int -nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; argp->monitor = 1; /* monitor client by default */ - return 1; + return true; } -int -nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + return true; } -int -nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; argp->lock.fl.fl_type = F_UNLCK; - return 1; + return true; } -int -nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_res *resp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_decode_stats(xdr, &resp->status)) - return 0; + return false; - return 1; + return true; } -int -nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_reboot *argp = rqstp->rq_argp; + __be32 *p; u32 len; if (xdr_stream_decode_u32(xdr, &len) < 0) - return 0; + return false; if (len > SM_MAXSTRLEN) - return 0; + return false; p = xdr_inline_decode(xdr, len); if (!p) - return 0; + return false; argp->len = len; argp->mon = (char *)p; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; p = xdr_inline_decode(xdr, SM_PRIV_SIZE); if (!p) - return 0; + return false; memcpy(&argp->priv.data, p, sizeof(argp->priv.data)); - return 1; + return true; } -int -nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; @@ -284,35 +278,34 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) lock->svid = ~(u32)0; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (!svcxdr_decode_fhandle(xdr, &lock->fh)) - return 0; + return false; if (!svcxdr_decode_owner(xdr, &lock->oh)) - return 0; + return false; /* XXX: Range checks are missing in the original code */ if (xdr_stream_decode_u32(xdr, &argp->fsm_mode) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->fsm_access) < 0) - return 0; + return false; - return 1; + return true; } -int -nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; - return 1; + return true; } @@ -320,45 +313,42 @@ nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p) * Encode Reply results */ -int -nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int -nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && svcxdr_encode_testrply(xdr, resp); } -int -nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && svcxdr_encode_stats(xdr, resp->status); } -int -nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) +bool +nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; if (!svcxdr_encode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_encode_stats(xdr, resp->status)) - return 0; + return false; /* sequence */ if (xdr_stream_encode_u32(xdr, 0) < 0) - return 0; + return false; - return 1; + return true; } diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index b303ecd74f33..5fcbf30cd275 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -140,136 +140,131 @@ svcxdr_encode_testrply(struct xdr_stream *xdr, const struct nlm_res *resp) * Decode Call arguments */ -int -nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int -nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + return true; } -int -nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; argp->monitor = 1; /* monitor client by default */ - return 1; + return true; } -int -nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + + return true; } -int -nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; argp->lock.fl.fl_type = F_UNLCK; - return 1; + return true; } -int -nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_res *resp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_decode_stats(xdr, &resp->status)) - return 0; + return false; - return 1; + return true; } -int -nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_reboot *argp = rqstp->rq_argp; + __be32 *p; u32 len; if (xdr_stream_decode_u32(xdr, &len) < 0) - return 0; + return false; if (len > SM_MAXSTRLEN) - return 0; + return false; p = xdr_inline_decode(xdr, len); if (!p) - return 0; + return false; argp->len = len; argp->mon = (char *)p; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; p = xdr_inline_decode(xdr, SM_PRIV_SIZE); if (!p) - return 0; + return false; memcpy(&argp->priv.data, p, sizeof(argp->priv.data)); - return 1; + return true; } -int -nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; @@ -278,35 +273,34 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) lock->svid = ~(u32)0; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (!svcxdr_decode_fhandle(xdr, &lock->fh)) - return 0; + return false; if (!svcxdr_decode_owner(xdr, &lock->oh)) - return 0; + return false; /* XXX: Range checks are missing in the original code */ if (xdr_stream_decode_u32(xdr, &argp->fsm_mode) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->fsm_access) < 0) - return 0; + return false; - return 1; + return true; } -int -nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; - return 1; + return true; } @@ -314,45 +308,42 @@ nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p) * Encode Reply results */ -int -nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int -nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && svcxdr_encode_testrply(xdr, resp); } -int -nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && svcxdr_encode_stats(xdr, resp->status); } -int -nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) +bool +nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; if (!svcxdr_encode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_encode_stats(xdr, resp->status)) - return 0; + return false; /* sequence */ if (xdr_stream_encode_u32(xdr, 0) < 0) - return 0; + return false; - return 1; + return true; } diff --git a/fs/locks.c b/fs/locks.c index 4899a4666f24..77781b71bcaa 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -251,7 +251,7 @@ locks_get_lock_context(struct inode *inode, int type) struct file_lock_context *ctx; /* paired with cmpxchg() below */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (likely(ctx) || type == F_UNLCK) goto out; @@ -270,7 +270,7 @@ locks_get_lock_context(struct inode *inode, int type) */ if (cmpxchg(&inode->i_flctx, NULL, ctx)) { kmem_cache_free(flctx_cache, ctx); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); } out: trace_locks_get_lock_context(inode, type, ctx); @@ -323,7 +323,7 @@ locks_check_ctx_file_list(struct file *filp, struct list_head *list, void locks_free_lock_context(struct inode *inode) { - struct file_lock_context *ctx = inode->i_flctx; + struct file_lock_context *ctx = locks_inode_context(inode); if (unlikely(ctx)) { locks_check_ctx_lists(inode); @@ -376,6 +376,34 @@ void locks_release_private(struct file_lock *fl) } EXPORT_SYMBOL_GPL(locks_release_private); +/** + * locks_owner_has_blockers - Check for blocking lock requests + * @flctx: file lock context + * @owner: lock owner + * + * Return values: + * %true: @owner has at least one blocker + * %false: @owner has no blockers + */ +bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner) +{ + struct file_lock *fl; + + spin_lock(&flctx->flc_lock); + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { + if (fl->fl_owner != owner) + continue; + if (!list_empty(&fl->fl_blocked_requests)) { + spin_unlock(&flctx->flc_lock); + return true; + } + } + spin_unlock(&flctx->flc_lock); + return false; +} +EXPORT_SYMBOL_GPL(locks_owner_has_blockers); + /* Free a lock which is not in use. */ void locks_free_lock(struct file_lock *fl) { @@ -954,19 +982,32 @@ posix_test_lock(struct file *filp, struct file_lock *fl) struct file_lock *cfl; struct file_lock_context *ctx; struct inode *inode = locks_inode(filp); + void *owner; + void (*func)(void); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->fl_type = F_UNLCK; return; } +retry: spin_lock(&ctx->flc_lock); list_for_each_entry(cfl, &ctx->flc_posix, fl_list) { - if (posix_locks_conflict(fl, cfl)) { - locks_copy_conflock(fl, cfl); - goto out; + if (!posix_locks_conflict(fl, cfl)) + continue; + if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable + && (*cfl->fl_lmops->lm_lock_expirable)(cfl)) { + owner = cfl->fl_lmops->lm_mod_owner; + func = cfl->fl_lmops->lm_expire_lock; + __module_get(owner); + spin_unlock(&ctx->flc_lock); + (*func)(); + module_put(owner); + goto retry; } + locks_copy_conflock(fl, cfl); + goto out; } fl->fl_type = F_UNLCK; out: @@ -1140,6 +1181,8 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, int error; bool added = false; LIST_HEAD(dispose); + void *owner; + void (*func)(void); ctx = locks_get_lock_context(inode, request->fl_type); if (!ctx) @@ -1158,6 +1201,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, new_fl2 = locks_alloc_lock(); } +retry: percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); /* @@ -1169,6 +1213,17 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (!posix_locks_conflict(request, fl)) continue; + if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable + && (*fl->fl_lmops->lm_lock_expirable)(fl)) { + owner = fl->fl_lmops->lm_mod_owner; + func = fl->fl_lmops->lm_expire_lock; + __module_get(owner); + spin_unlock(&ctx->flc_lock); + percpu_up_read(&file_rwsem); + (*func)(); + module_put(owner); + goto retry; + } if (conflock) locks_copy_conflock(conflock, fl); error = -EAGAIN; @@ -1522,7 +1577,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) new_fl->fl_flags = type; /* typically we will check that ctx is non-NULL before calling */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) { WARN_ON_ONCE(1); goto free_lock; @@ -1627,7 +1682,7 @@ void lease_get_mtime(struct inode *inode, struct timespec64 *time) struct file_lock_context *ctx; struct file_lock *fl; - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); fl = list_first_entry_or_null(&ctx->flc_lease, @@ -1673,7 +1728,7 @@ int fcntl_getlease(struct file *filp) int type = F_UNLCK; LIST_HEAD(dispose); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); @@ -1862,7 +1917,7 @@ static int generic_delete_lease(struct file *filp, void *owner) struct file_lock_context *ctx; LIST_HEAD(dispose); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; @@ -2596,7 +2651,7 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx || list_empty(&ctx->flc_posix)) return; @@ -2669,7 +2724,7 @@ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx; - ctx = smp_load_acquire(&locks_inode(filp)->i_flctx); + ctx = locks_inode_context(locks_inode(filp)); if (!ctx) return; @@ -2716,7 +2771,7 @@ bool vfs_inode_has_locks(struct inode *inode) struct file_lock_context *ctx; bool ret; - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) return false; @@ -2907,7 +2962,7 @@ void show_fd_locks(struct seq_file *f, struct file_lock_context *ctx; int id = 0; - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) return; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 86d856de1389..456af7d230cf 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -17,7 +17,6 @@ #include <linux/errno.h> #include <linux/mutex.h> #include <linux/freezer.h> -#include <linux/kthread.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/bc_xprt.h> @@ -45,18 +44,18 @@ static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net) int ret; struct nfs_net *nn = net_generic(net, nfs_net_id); - ret = svc_create_xprt(serv, "tcp", net, PF_INET, - nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, - cred); + ret = svc_xprt_create(serv, "tcp", net, PF_INET, + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, + cred); if (ret <= 0) goto out_err; nn->nfs_callback_tcpport = ret; dprintk("NFS: Callback listener port = %u (af %u, net %x)\n", nn->nfs_callback_tcpport, PF_INET, net->ns.inum); - ret = svc_create_xprt(serv, "tcp", net, PF_INET6, - nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, - cred); + ret = svc_xprt_create(serv, "tcp", net, PF_INET6, + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, + cred); if (ret > 0) { nn->nfs_callback_tcpport6 = ret; dprintk("NFS: Callback listener port = %u (af %u, net %x)\n", @@ -92,8 +91,8 @@ nfs4_callback_svc(void *vrqstp) continue; svc_process(rqstp); } + svc_exit_thread(rqstp); - module_put_and_exit(0); return 0; } @@ -136,8 +135,8 @@ nfs41_callback_svc(void *vrqstp) finish_wait(&serv->sv_cb_waitq, &wq); } } + svc_exit_thread(rqstp); - module_put_and_exit(0); return 0; } @@ -169,12 +168,12 @@ static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt, if (nrservs < NFS4_MIN_NR_CALLBACK_THREADS) nrservs = NFS4_MIN_NR_CALLBACK_THREADS; - if (serv->sv_nrthreads-1 == nrservs) + if (serv->sv_nrthreads == nrservs) return 0; - ret = serv->sv_ops->svo_setup(serv, NULL, nrservs); + ret = svc_set_num_threads(serv, NULL, nrservs); if (ret) { - serv->sv_ops->svo_setup(serv, NULL, 0); + svc_set_num_threads(serv, NULL, 0); return ret; } dprintk("nfs_callback_up: service started\n"); @@ -189,7 +188,7 @@ static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struc return; dprintk("NFS: destroy per-net callback data; net=%x\n", net->ns.inum); - svc_shutdown_net(serv, net); + svc_xprt_destroy_all(serv, net); } static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, @@ -232,59 +231,17 @@ err_bind: return ret; } -static const struct svc_serv_ops nfs40_cb_sv_ops = { - .svo_function = nfs4_callback_svc, - .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads_sync, - .svo_module = THIS_MODULE, -}; -#if defined(CONFIG_NFS_V4_1) -static const struct svc_serv_ops nfs41_cb_sv_ops = { - .svo_function = nfs41_callback_svc, - .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads_sync, - .svo_module = THIS_MODULE, -}; - -static const struct svc_serv_ops *nfs4_cb_sv_ops[] = { - [0] = &nfs40_cb_sv_ops, - [1] = &nfs41_cb_sv_ops, -}; -#else -static const struct svc_serv_ops *nfs4_cb_sv_ops[] = { - [0] = &nfs40_cb_sv_ops, - [1] = NULL, -}; -#endif - static struct svc_serv *nfs_callback_create_svc(int minorversion) { struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion]; - const struct svc_serv_ops *sv_ops; + int (*threadfn)(void *data); struct svc_serv *serv; /* * Check whether we're already up and running. */ - if (cb_info->serv) { - /* - * Note: increase service usage, because later in case of error - * svc_destroy() will be called. - */ - svc_get(cb_info->serv); - return cb_info->serv; - } - - switch (minorversion) { - case 0: - sv_ops = nfs4_cb_sv_ops[0]; - break; - default: - sv_ops = nfs4_cb_sv_ops[1]; - } - - if (sv_ops == NULL) - return ERR_PTR(-ENOTSUPP); + if (cb_info->serv) + return svc_get(cb_info->serv); /* * Sanity check: if there's no task, @@ -294,7 +251,16 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion) printk(KERN_WARNING "nfs_callback_create_svc: no kthread, %d users??\n", cb_info->users); - serv = svc_create_pooled(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, sv_ops); + threadfn = nfs4_callback_svc; +#if defined(CONFIG_NFS_V4_1) + if (minorversion) + threadfn = nfs41_callback_svc; +#else + if (minorversion) + return ERR_PTR(-ENOTSUPP); +#endif + serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, + threadfn); if (!serv) { printk(KERN_ERR "nfs_callback_create_svc: create service failed\n"); return ERR_PTR(-ENOMEM); @@ -335,16 +301,10 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt) goto err_start; cb_info->users++; - /* - * svc_create creates the svc_serv with sv_nrthreads == 1, and then - * svc_prepare_thread increments that. So we need to call svc_destroy - * on both success and failure so that the refcount is 1 when the - * thread exits. - */ err_net: if (!cb_info->users) cb_info->serv = NULL; - svc_destroy(serv); + svc_put(serv); err_create: mutex_unlock(&nfs_callback_mutex); return ret; @@ -369,8 +329,8 @@ void nfs_callback_down(int minorversion, struct net *net) cb_info->users--; if (cb_info->users == 0) { svc_get(serv); - serv->sv_ops->svo_setup(serv, NULL, 0); - svc_destroy(serv); + svc_set_num_threads(serv, NULL, 0); + svc_put(serv); dprintk("nfs_callback_down: service destroyed\n"); cb_info->serv = NULL; } diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index ea17085ef884..d0cccddb7d08 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -67,9 +67,9 @@ static __be32 nfs4_callback_null(struct svc_rqst *rqstp) * svc_process_common() looks for an XDR encoder to know when * not to drop a Reply. */ -static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p) +static bool nfs4_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return xdr_ressize_check(rqstp, p); + return true; } static __be32 decode_string(struct xdr_stream *xdr, unsigned int *len, @@ -1065,6 +1065,7 @@ static const struct svc_procedure nfs4_callback_procedures1[] = { .pc_func = nfs4_callback_compound, .pc_encode = nfs4_encode_void, .pc_argsize = 256, + .pc_argzero = 256, .pc_ressize = 256, .pc_xdrressize = NFS4_CALLBACK_BUFSIZE, .pc_name = "COMPOUND", diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index bbe2a5cc49f6..3185899676ad 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -678,10 +678,17 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) LIST_HEAD(mds_list); nfs_init_cinfo_from_dreq(&cinfo, dreq); + nfs_commit_begin(cinfo.mds); nfs_scan_commit(dreq->inode, &mds_list, &cinfo); res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo); - if (res < 0) /* res == -ENOMEM */ - nfs_direct_write_reschedule(dreq); + if (res < 0) { /* res == -ENOMEM */ + spin_lock(&dreq->lock); + if (dreq->flags == 0) + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + } + if (nfs_commit_end(cinfo.mds)) + nfs_direct_write_complete(dreq); } static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq) diff --git a/fs/nfs/export.c b/fs/nfs/export.c index d772c20bbfd1..eafa9d7b0911 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -178,7 +178,10 @@ const struct export_operations nfs_export_ops = { .fh_to_dentry = nfs_fh_to_dentry, .get_parent = nfs_get_parent, .fetch_iversion = nfs_fetch_iversion, - .flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK| - EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS| - EXPORT_OP_NOATOMIC_ATTR|EXPORT_OP_SYNC_LOCKS, + .flags = EXPORT_OP_NOWCC | + EXPORT_OP_NOSUBTREECHK | + EXPORT_OP_CLOSE_BEFORE_UNLINK | + EXPORT_OP_REMOTE_FS | + EXPORT_OP_NOATOMIC_ATTR | + EXPORT_OP_FLUSH_ON_CLOSE, }; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 258e6b167285..d7868cc52780 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2766,6 +2766,6 @@ again: goto again; nfs_put_client(clp); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index bcd18e96b44f..8565fa654f59 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -9,322 +9,10 @@ #define _TRACE_NFS4_H #include <linux/tracepoint.h> +#include <trace/misc/sunrpc.h> -TRACE_DEFINE_ENUM(EPERM); -TRACE_DEFINE_ENUM(ENOENT); -TRACE_DEFINE_ENUM(EIO); -TRACE_DEFINE_ENUM(ENXIO); -TRACE_DEFINE_ENUM(EACCES); -TRACE_DEFINE_ENUM(EEXIST); -TRACE_DEFINE_ENUM(EXDEV); -TRACE_DEFINE_ENUM(ENOTDIR); -TRACE_DEFINE_ENUM(EISDIR); -TRACE_DEFINE_ENUM(EFBIG); -TRACE_DEFINE_ENUM(ENOSPC); -TRACE_DEFINE_ENUM(EROFS); -TRACE_DEFINE_ENUM(EMLINK); -TRACE_DEFINE_ENUM(ENAMETOOLONG); -TRACE_DEFINE_ENUM(ENOTEMPTY); -TRACE_DEFINE_ENUM(EDQUOT); -TRACE_DEFINE_ENUM(ESTALE); -TRACE_DEFINE_ENUM(EBADHANDLE); -TRACE_DEFINE_ENUM(EBADCOOKIE); -TRACE_DEFINE_ENUM(ENOTSUPP); -TRACE_DEFINE_ENUM(ETOOSMALL); -TRACE_DEFINE_ENUM(EREMOTEIO); -TRACE_DEFINE_ENUM(EBADTYPE); -TRACE_DEFINE_ENUM(EAGAIN); -TRACE_DEFINE_ENUM(ELOOP); -TRACE_DEFINE_ENUM(EOPNOTSUPP); -TRACE_DEFINE_ENUM(EDEADLK); -TRACE_DEFINE_ENUM(ENOMEM); -TRACE_DEFINE_ENUM(EKEYEXPIRED); -TRACE_DEFINE_ENUM(ETIMEDOUT); -TRACE_DEFINE_ENUM(ERESTARTSYS); -TRACE_DEFINE_ENUM(ECONNREFUSED); -TRACE_DEFINE_ENUM(ECONNRESET); -TRACE_DEFINE_ENUM(ENETUNREACH); -TRACE_DEFINE_ENUM(EHOSTUNREACH); -TRACE_DEFINE_ENUM(EHOSTDOWN); -TRACE_DEFINE_ENUM(EPIPE); -TRACE_DEFINE_ENUM(EPFNOSUPPORT); -TRACE_DEFINE_ENUM(EPROTONOSUPPORT); - -TRACE_DEFINE_ENUM(NFS4_OK); -TRACE_DEFINE_ENUM(NFS4ERR_ACCESS); -TRACE_DEFINE_ENUM(NFS4ERR_ATTRNOTSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_ADMIN_REVOKED); -TRACE_DEFINE_ENUM(NFS4ERR_BACK_CHAN_BUSY); -TRACE_DEFINE_ENUM(NFS4ERR_BADCHAR); -TRACE_DEFINE_ENUM(NFS4ERR_BADHANDLE); -TRACE_DEFINE_ENUM(NFS4ERR_BADIOMODE); -TRACE_DEFINE_ENUM(NFS4ERR_BADLAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_BADLABEL); -TRACE_DEFINE_ENUM(NFS4ERR_BADNAME); -TRACE_DEFINE_ENUM(NFS4ERR_BADOWNER); -TRACE_DEFINE_ENUM(NFS4ERR_BADSESSION); -TRACE_DEFINE_ENUM(NFS4ERR_BADSLOT); -TRACE_DEFINE_ENUM(NFS4ERR_BADTYPE); -TRACE_DEFINE_ENUM(NFS4ERR_BADXDR); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_COOKIE); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_HIGH_SLOT); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_RANGE); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_SEQID); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_SESSION_DIGEST); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_CB_PATH_DOWN); -TRACE_DEFINE_ENUM(NFS4ERR_CLID_INUSE); -TRACE_DEFINE_ENUM(NFS4ERR_CLIENTID_BUSY); -TRACE_DEFINE_ENUM(NFS4ERR_COMPLETE_ALREADY); -TRACE_DEFINE_ENUM(NFS4ERR_CONN_NOT_BOUND_TO_SESSION); -TRACE_DEFINE_ENUM(NFS4ERR_DEADLOCK); -TRACE_DEFINE_ENUM(NFS4ERR_DEADSESSION); -TRACE_DEFINE_ENUM(NFS4ERR_DELAY); -TRACE_DEFINE_ENUM(NFS4ERR_DELEG_ALREADY_WANTED); -TRACE_DEFINE_ENUM(NFS4ERR_DELEG_REVOKED); -TRACE_DEFINE_ENUM(NFS4ERR_DENIED); -TRACE_DEFINE_ENUM(NFS4ERR_DIRDELEG_UNAVAIL); -TRACE_DEFINE_ENUM(NFS4ERR_DQUOT); -TRACE_DEFINE_ENUM(NFS4ERR_ENCR_ALG_UNSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_EXIST); -TRACE_DEFINE_ENUM(NFS4ERR_EXPIRED); -TRACE_DEFINE_ENUM(NFS4ERR_FBIG); -TRACE_DEFINE_ENUM(NFS4ERR_FHEXPIRED); -TRACE_DEFINE_ENUM(NFS4ERR_FILE_OPEN); -TRACE_DEFINE_ENUM(NFS4ERR_GRACE); -TRACE_DEFINE_ENUM(NFS4ERR_HASH_ALG_UNSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_INVAL); -TRACE_DEFINE_ENUM(NFS4ERR_IO); -TRACE_DEFINE_ENUM(NFS4ERR_ISDIR); -TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTTRYLATER); -TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTUNAVAILABLE); -TRACE_DEFINE_ENUM(NFS4ERR_LEASE_MOVED); -TRACE_DEFINE_ENUM(NFS4ERR_LOCKED); -TRACE_DEFINE_ENUM(NFS4ERR_LOCKS_HELD); -TRACE_DEFINE_ENUM(NFS4ERR_LOCK_RANGE); -TRACE_DEFINE_ENUM(NFS4ERR_MINOR_VERS_MISMATCH); -TRACE_DEFINE_ENUM(NFS4ERR_MLINK); -TRACE_DEFINE_ENUM(NFS4ERR_MOVED); -TRACE_DEFINE_ENUM(NFS4ERR_NAMETOOLONG); -TRACE_DEFINE_ENUM(NFS4ERR_NOENT); -TRACE_DEFINE_ENUM(NFS4ERR_NOFILEHANDLE); -TRACE_DEFINE_ENUM(NFS4ERR_NOMATCHING_LAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_NOSPC); -TRACE_DEFINE_ENUM(NFS4ERR_NOTDIR); -TRACE_DEFINE_ENUM(NFS4ERR_NOTEMPTY); -TRACE_DEFINE_ENUM(NFS4ERR_NOTSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_NOT_ONLY_OP); -TRACE_DEFINE_ENUM(NFS4ERR_NOT_SAME); -TRACE_DEFINE_ENUM(NFS4ERR_NO_GRACE); -TRACE_DEFINE_ENUM(NFS4ERR_NXIO); -TRACE_DEFINE_ENUM(NFS4ERR_OLD_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_OPENMODE); -TRACE_DEFINE_ENUM(NFS4ERR_OP_ILLEGAL); -TRACE_DEFINE_ENUM(NFS4ERR_OP_NOT_IN_SESSION); -TRACE_DEFINE_ENUM(NFS4ERR_PERM); -TRACE_DEFINE_ENUM(NFS4ERR_PNFS_IO_HOLE); -TRACE_DEFINE_ENUM(NFS4ERR_PNFS_NO_LAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_RECALLCONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_BAD); -TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_CONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_REJECT_DELEG); -TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG); -TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG_TO_CACHE); -TRACE_DEFINE_ENUM(NFS4ERR_REQ_TOO_BIG); -TRACE_DEFINE_ENUM(NFS4ERR_RESOURCE); -TRACE_DEFINE_ENUM(NFS4ERR_RESTOREFH); -TRACE_DEFINE_ENUM(NFS4ERR_RETRY_UNCACHED_REP); -TRACE_DEFINE_ENUM(NFS4ERR_RETURNCONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_ROFS); -TRACE_DEFINE_ENUM(NFS4ERR_SAME); -TRACE_DEFINE_ENUM(NFS4ERR_SHARE_DENIED); -TRACE_DEFINE_ENUM(NFS4ERR_SEQUENCE_POS); -TRACE_DEFINE_ENUM(NFS4ERR_SEQ_FALSE_RETRY); -TRACE_DEFINE_ENUM(NFS4ERR_SEQ_MISORDERED); -TRACE_DEFINE_ENUM(NFS4ERR_SERVERFAULT); -TRACE_DEFINE_ENUM(NFS4ERR_STALE); -TRACE_DEFINE_ENUM(NFS4ERR_STALE_CLIENTID); -TRACE_DEFINE_ENUM(NFS4ERR_STALE_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_SYMLINK); -TRACE_DEFINE_ENUM(NFS4ERR_TOOSMALL); -TRACE_DEFINE_ENUM(NFS4ERR_TOO_MANY_OPS); -TRACE_DEFINE_ENUM(NFS4ERR_UNKNOWN_LAYOUTTYPE); -TRACE_DEFINE_ENUM(NFS4ERR_UNSAFE_COMPOUND); -TRACE_DEFINE_ENUM(NFS4ERR_WRONGSEC); -TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED); -TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE); -TRACE_DEFINE_ENUM(NFS4ERR_XDEV); - -TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_MDS); -TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_PNFS); - -#define show_nfsv4_errors(error) \ - __print_symbolic(error, \ - { NFS4_OK, "OK" }, \ - /* Mapped by nfs4_stat_to_errno() */ \ - { EPERM, "EPERM" }, \ - { ENOENT, "ENOENT" }, \ - { EIO, "EIO" }, \ - { ENXIO, "ENXIO" }, \ - { EACCES, "EACCES" }, \ - { EEXIST, "EEXIST" }, \ - { EXDEV, "EXDEV" }, \ - { ENOTDIR, "ENOTDIR" }, \ - { EISDIR, "EISDIR" }, \ - { EFBIG, "EFBIG" }, \ - { ENOSPC, "ENOSPC" }, \ - { EROFS, "EROFS" }, \ - { EMLINK, "EMLINK" }, \ - { ENAMETOOLONG, "ENAMETOOLONG" }, \ - { ENOTEMPTY, "ENOTEMPTY" }, \ - { EDQUOT, "EDQUOT" }, \ - { ESTALE, "ESTALE" }, \ - { EBADHANDLE, "EBADHANDLE" }, \ - { EBADCOOKIE, "EBADCOOKIE" }, \ - { ENOTSUPP, "ENOTSUPP" }, \ - { ETOOSMALL, "ETOOSMALL" }, \ - { EREMOTEIO, "EREMOTEIO" }, \ - { EBADTYPE, "EBADTYPE" }, \ - { EAGAIN, "EAGAIN" }, \ - { ELOOP, "ELOOP" }, \ - { EOPNOTSUPP, "EOPNOTSUPP" }, \ - { EDEADLK, "EDEADLK" }, \ - /* RPC errors */ \ - { ENOMEM, "ENOMEM" }, \ - { EKEYEXPIRED, "EKEYEXPIRED" }, \ - { ETIMEDOUT, "ETIMEDOUT" }, \ - { ERESTARTSYS, "ERESTARTSYS" }, \ - { ECONNREFUSED, "ECONNREFUSED" }, \ - { ECONNRESET, "ECONNRESET" }, \ - { ENETUNREACH, "ENETUNREACH" }, \ - { EHOSTUNREACH, "EHOSTUNREACH" }, \ - { EHOSTDOWN, "EHOSTDOWN" }, \ - { EPIPE, "EPIPE" }, \ - { EPFNOSUPPORT, "EPFNOSUPPORT" }, \ - { EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ - /* NFSv4 native errors */ \ - { NFS4ERR_ACCESS, "ACCESS" }, \ - { NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ - { NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ - { NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ - { NFS4ERR_BADCHAR, "BADCHAR" }, \ - { NFS4ERR_BADHANDLE, "BADHANDLE" }, \ - { NFS4ERR_BADIOMODE, "BADIOMODE" }, \ - { NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ - { NFS4ERR_BADLABEL, "BADLABEL" }, \ - { NFS4ERR_BADNAME, "BADNAME" }, \ - { NFS4ERR_BADOWNER, "BADOWNER" }, \ - { NFS4ERR_BADSESSION, "BADSESSION" }, \ - { NFS4ERR_BADSLOT, "BADSLOT" }, \ - { NFS4ERR_BADTYPE, "BADTYPE" }, \ - { NFS4ERR_BADXDR, "BADXDR" }, \ - { NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ - { NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ - { NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ - { NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ - { NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ - { NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ - { NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ - { NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ - { NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ - { NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ - { NFS4ERR_CONN_NOT_BOUND_TO_SESSION, \ - "CONN_NOT_BOUND_TO_SESSION" }, \ - { NFS4ERR_DEADLOCK, "DEADLOCK" }, \ - { NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ - { NFS4ERR_DELAY, "DELAY" }, \ - { NFS4ERR_DELEG_ALREADY_WANTED, \ - "DELEG_ALREADY_WANTED" }, \ - { NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ - { NFS4ERR_DENIED, "DENIED" }, \ - { NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ - { NFS4ERR_DQUOT, "DQUOT" }, \ - { NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ - { NFS4ERR_EXIST, "EXIST" }, \ - { NFS4ERR_EXPIRED, "EXPIRED" }, \ - { NFS4ERR_FBIG, "FBIG" }, \ - { NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ - { NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ - { NFS4ERR_GRACE, "GRACE" }, \ - { NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ - { NFS4ERR_INVAL, "INVAL" }, \ - { NFS4ERR_IO, "IO" }, \ - { NFS4ERR_ISDIR, "ISDIR" }, \ - { NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ - { NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ - { NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ - { NFS4ERR_LOCKED, "LOCKED" }, \ - { NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ - { NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ - { NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ - { NFS4ERR_MLINK, "MLINK" }, \ - { NFS4ERR_MOVED, "MOVED" }, \ - { NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ - { NFS4ERR_NOENT, "NOENT" }, \ - { NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ - { NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ - { NFS4ERR_NOSPC, "NOSPC" }, \ - { NFS4ERR_NOTDIR, "NOTDIR" }, \ - { NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ - { NFS4ERR_NOTSUPP, "NOTSUPP" }, \ - { NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ - { NFS4ERR_NOT_SAME, "NOT_SAME" }, \ - { NFS4ERR_NO_GRACE, "NO_GRACE" }, \ - { NFS4ERR_NXIO, "NXIO" }, \ - { NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ - { NFS4ERR_OPENMODE, "OPENMODE" }, \ - { NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ - { NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ - { NFS4ERR_PERM, "PERM" }, \ - { NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ - { NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ - { NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ - { NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ - { NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ - { NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ - { NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ - { NFS4ERR_REP_TOO_BIG_TO_CACHE, \ - "REP_TOO_BIG_TO_CACHE" }, \ - { NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ - { NFS4ERR_RESOURCE, "RESOURCE" }, \ - { NFS4ERR_RESTOREFH, "RESTOREFH" }, \ - { NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ - { NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ - { NFS4ERR_ROFS, "ROFS" }, \ - { NFS4ERR_SAME, "SAME" }, \ - { NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ - { NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ - { NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ - { NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ - { NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ - { NFS4ERR_STALE, "STALE" }, \ - { NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ - { NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ - { NFS4ERR_SYMLINK, "SYMLINK" }, \ - { NFS4ERR_TOOSMALL, "TOOSMALL" }, \ - { NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ - { NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ - { NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ - { NFS4ERR_WRONGSEC, "WRONGSEC" }, \ - { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ - { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ - { NFS4ERR_XDEV, "XDEV" }, \ - /* ***** Internal to Linux NFS client ***** */ \ - { NFS4ERR_RESET_TO_MDS, "RESET_TO_MDS" }, \ - { NFS4ERR_RESET_TO_PNFS, "RESET_TO_PNFS" }) - -#define show_open_flags(flags) \ - __print_flags(flags, "|", \ - { O_CREAT, "O_CREAT" }, \ - { O_EXCL, "O_EXCL" }, \ - { O_TRUNC, "O_TRUNC" }, \ - { O_DIRECT, "O_DIRECT" }) - -#define show_fmode_flags(mode) \ - __print_flags(mode, "|", \ - { ((__force unsigned long)FMODE_READ), "READ" }, \ - { ((__force unsigned long)FMODE_WRITE), "WRITE" }, \ - { ((__force unsigned long)FMODE_EXEC), "EXEC" }) +#include <trace/misc/fs.h> +#include <trace/misc/nfs.h> #define show_nfs_fattr_flags(valid) \ __print_flags((unsigned long)valid, "|", \ @@ -365,7 +53,7 @@ DECLARE_EVENT_CLASS(nfs4_clientid_event, TP_printk( "error=%ld (%s) dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __get_str(dstaddr) ) ); @@ -389,29 +77,6 @@ DEFINE_NFS4_CLIENTID_EVENT(nfs4_bind_conn_to_session); DEFINE_NFS4_CLIENTID_EVENT(nfs4_sequence); DEFINE_NFS4_CLIENTID_EVENT(nfs4_reclaim_complete); -#define show_nfs4_sequence_status_flags(status) \ - __print_flags((unsigned long)status, "|", \ - { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ - { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING, \ - "CB_GSS_CONTEXTS_EXPIRING" }, \ - { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED, \ - "CB_GSS_CONTEXTS_EXPIRED" }, \ - { SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED, \ - "EXPIRED_ALL_STATE_REVOKED" }, \ - { SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED, \ - "EXPIRED_SOME_STATE_REVOKED" }, \ - { SEQ4_STATUS_ADMIN_STATE_REVOKED, \ - "ADMIN_STATE_REVOKED" }, \ - { SEQ4_STATUS_RECALLABLE_STATE_REVOKED, \ - "RECALLABLE_STATE_REVOKED" }, \ - { SEQ4_STATUS_LEASE_MOVED, "LEASE_MOVED" }, \ - { SEQ4_STATUS_RESTART_RECLAIM_NEEDED, \ - "RESTART_RECLAIM_NEEDED" }, \ - { SEQ4_STATUS_CB_PATH_DOWN_SESSION, \ - "CB_PATH_DOWN_SESSION" }, \ - { SEQ4_STATUS_BACKCHANNEL_FAULT, \ - "BACKCHANNEL_FAULT" }) - TRACE_EVENT(nfs4_sequence_done, TP_PROTO( const struct nfs4_session *session, @@ -425,7 +90,7 @@ TRACE_EVENT(nfs4_sequence_done, __field(unsigned int, seq_nr) __field(unsigned int, highest_slotid) __field(unsigned int, target_highest_slotid) - __field(unsigned int, status_flags) + __field(unsigned long, status_flags) __field(unsigned long, error) ), @@ -444,16 +109,16 @@ TRACE_EVENT(nfs4_sequence_done, TP_printk( "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u " "highest_slotid=%u target_highest_slotid=%u " - "status_flags=%u (%s)", + "status_flags=0x%lx (%s)", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->session, __entry->slot_nr, __entry->seq_nr, __entry->highest_slotid, __entry->target_highest_slotid, __entry->status_flags, - show_nfs4_sequence_status_flags(__entry->status_flags) + show_nfs4_seq4_status(__entry->status_flags) ) ); @@ -490,7 +155,7 @@ TRACE_EVENT(nfs4_cb_sequence, "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u " "highest_slotid=%u", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->session, __entry->slot_nr, __entry->seq_nr, @@ -527,7 +192,7 @@ TRACE_EVENT(nfs4_cb_seqid_err, "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u " "highest_slotid=%u", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->session, __entry->slot_nr, __entry->seq_nr, @@ -663,7 +328,7 @@ TRACE_EVENT(nfs4_state_mgr_failed, "hostname=%s clp state=%s error=%ld (%s) section=%s", __get_str(hostname), show_nfs4_clp_state(__entry->state), -__entry->error, - show_nfsv4_errors(__entry->error), __get_str(section) + show_nfs4_status(__entry->error), __get_str(section) ) ) @@ -696,8 +361,8 @@ TRACE_EVENT(nfs4_xdr_bad_operation, __entry->expected = expected; ), - TP_printk( - "task:%u@%d xid=0x%08x operation=%u, expected=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x operation=%u, expected=%u", __entry->task_id, __entry->client_id, __entry->xid, __entry->op, __entry->expected ) @@ -731,10 +396,10 @@ DECLARE_EVENT_CLASS(nfs4_xdr_event, __entry->error = error; ), - TP_printk( - "task:%u@%d xid=0x%08x error=%ld (%s) operation=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x error=%ld (%s) operation=%u", __entry->task_id, __entry->client_id, __entry->xid, - -__entry->error, show_nfsv4_errors(__entry->error), + -__entry->error, show_nfs4_status(__entry->error), __entry->op ) ); @@ -795,8 +460,8 @@ DECLARE_EVENT_CLASS(nfs4_open_event, TP_STRUCT__entry( __field(unsigned long, error) - __field(unsigned int, flags) - __field(unsigned int, fmode) + __field(unsigned long, flags) + __field(unsigned long, fmode) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) @@ -814,7 +479,7 @@ DECLARE_EVENT_CLASS(nfs4_open_event, __entry->error = -error; __entry->flags = flags; - __entry->fmode = (__force unsigned int)ctx->mode; + __entry->fmode = (__force unsigned long)ctx->mode; __entry->dev = ctx->dentry->d_sb->s_dev; if (!IS_ERR_OR_NULL(state)) { inode = state->inode; @@ -844,15 +509,15 @@ DECLARE_EVENT_CLASS(nfs4_open_event, ), TP_printk( - "error=%ld (%s) flags=%d (%s) fmode=%s " + "error=%ld (%s) flags=%lu (%s) fmode=%s " "fileid=%02x:%02x:%llu fhandle=0x%08x " "name=%02x:%02x:%llu/%s stateid=%d:0x%08x " "openstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->flags, - show_open_flags(__entry->flags), - show_fmode_flags(__entry->fmode), + show_fs_fcntl_open_flags(__entry->flags), + show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -906,7 +571,7 @@ TRACE_EVENT(nfs4_cached_open, TP_printk( "fmode=%s fileid=%02x:%02x:%llu " "fhandle=0x%08x stateid=%d:0x%08x", - __entry->fmode ? show_fmode_flags(__entry->fmode) : + __entry->fmode ? show_fs_fmode_flags(__entry->fmode) : "closed", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, @@ -953,8 +618,8 @@ TRACE_EVENT(nfs4_close, "error=%ld (%s) fmode=%s fileid=%02x:%02x:%llu " "fhandle=0x%08x openstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), - __entry->fmode ? show_fmode_flags(__entry->fmode) : + show_nfs4_status(__entry->error), + __entry->fmode ? show_fs_fmode_flags(__entry->fmode) : "closed", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, @@ -963,24 +628,6 @@ TRACE_EVENT(nfs4_close, ) ); -TRACE_DEFINE_ENUM(F_GETLK); -TRACE_DEFINE_ENUM(F_SETLK); -TRACE_DEFINE_ENUM(F_SETLKW); -TRACE_DEFINE_ENUM(F_RDLCK); -TRACE_DEFINE_ENUM(F_WRLCK); -TRACE_DEFINE_ENUM(F_UNLCK); - -#define show_lock_cmd(type) \ - __print_symbolic((int)type, \ - { F_GETLK, "GETLK" }, \ - { F_SETLK, "SETLK" }, \ - { F_SETLKW, "SETLKW" }) -#define show_lock_type(type) \ - __print_symbolic((int)type, \ - { F_RDLCK, "RDLCK" }, \ - { F_WRLCK, "WRLCK" }, \ - { F_UNLCK, "UNLCK" }) - DECLARE_EVENT_CLASS(nfs4_lock_event, TP_PROTO( const struct file_lock *request, @@ -993,8 +640,8 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, TP_STRUCT__entry( __field(unsigned long, error) - __field(int, cmd) - __field(char, type) + __field(unsigned long, cmd) + __field(unsigned long, type) __field(loff_t, start) __field(loff_t, end) __field(dev_t, dev) @@ -1026,9 +673,9 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, "fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), - show_lock_cmd(__entry->cmd), - show_lock_type(__entry->type), + show_nfs4_status(__entry->error), + show_fs_fcntl_cmd(__entry->cmd), + show_fs_fcntl_lock_type(__entry->type), (long long)__entry->start, (long long)__entry->end, MAJOR(__entry->dev), MINOR(__entry->dev), @@ -1063,8 +710,8 @@ TRACE_EVENT(nfs4_set_lock, TP_STRUCT__entry( __field(unsigned long, error) - __field(int, cmd) - __field(char, type) + __field(unsigned long, cmd) + __field(unsigned long, type) __field(loff_t, start) __field(loff_t, end) __field(dev_t, dev) @@ -1102,9 +749,9 @@ TRACE_EVENT(nfs4_set_lock, "fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x lockstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), - show_lock_cmd(__entry->cmd), - show_lock_type(__entry->type), + show_nfs4_status(__entry->error), + show_fs_fcntl_cmd(__entry->cmd), + show_fs_fcntl_lock_type(__entry->type), (long long)__entry->start, (long long)__entry->end, MAJOR(__entry->dev), MINOR(__entry->dev), @@ -1221,7 +868,7 @@ DECLARE_EVENT_CLASS(nfs4_set_delegation_event, TP_printk( "fmode=%s fileid=%02x:%02x:%llu fhandle=0x%08x", - show_fmode_flags(__entry->fmode), + show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle @@ -1268,7 +915,7 @@ TRACE_EVENT(nfs4_delegreturn_exit, "error=%ld (%s) dev=%02x:%02x fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fhandle, __entry->stateid_seq, __entry->stateid_hash @@ -1311,7 +958,7 @@ DECLARE_EVENT_CLASS(nfs4_test_stateid_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1358,7 +1005,7 @@ DECLARE_EVENT_CLASS(nfs4_lookup_event, TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -1405,7 +1052,7 @@ TRACE_EVENT(nfs4_lookupp, TP_printk( "error=%ld (%s) inode=%02x:%02x:%llu", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->ino ) @@ -1444,7 +1091,7 @@ TRACE_EVENT(nfs4_rename, "error=%ld (%s) oldname=%02x:%02x:%llu/%s " "newname=%02x:%02x:%llu/%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->olddir, __get_str(oldname), @@ -1479,7 +1126,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_event, TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle @@ -1537,7 +1184,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1590,7 +1237,7 @@ DECLARE_EVENT_CLASS(nfs4_getattr_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "valid=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1646,7 +1293,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1707,7 +1354,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1756,7 +1403,7 @@ DECLARE_EVENT_CLASS(nfs4_idmap_event, TP_printk( "error=%ld (%s) id=%u name=%s", - -__entry->error, show_nfsv4_errors(__entry->error), + -__entry->error, show_nfs4_status(__entry->error), __entry->id, __get_str(name) ) @@ -1834,7 +1481,7 @@ DECLARE_EVENT_CLASS(nfs4_read_event, "offset=%lld count=%u res=%u stateid=%d:0x%08x " "layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1908,7 +1555,7 @@ DECLARE_EVENT_CLASS(nfs4_write_event, "offset=%lld count=%u res=%u stateid=%d:0x%08x " "layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1972,7 +1619,7 @@ DECLARE_EVENT_CLASS(nfs4_commit_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1992,16 +1639,6 @@ DEFINE_NFS4_COMMIT_EVENT(nfs4_commit); #ifdef CONFIG_NFS_V4_1 DEFINE_NFS4_COMMIT_EVENT(nfs4_pnfs_commit_ds); -TRACE_DEFINE_ENUM(IOMODE_READ); -TRACE_DEFINE_ENUM(IOMODE_RW); -TRACE_DEFINE_ENUM(IOMODE_ANY); - -#define show_pnfs_iomode(iomode) \ - __print_symbolic(iomode, \ - { IOMODE_READ, "READ" }, \ - { IOMODE_RW, "RW" }, \ - { IOMODE_ANY, "ANY" }) - TRACE_EVENT(nfs4_layoutget, TP_PROTO( const struct nfs_open_context *ctx, @@ -2057,11 +1694,11 @@ TRACE_EVENT(nfs4_layoutget, "iomode=%s offset=%llu count=%llu stateid=%d:0x%08x " "layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - show_pnfs_iomode(__entry->iomode), + show_pnfs_layout_iomode(__entry->iomode), (unsigned long long)__entry->offset, (unsigned long long)__entry->count, __entry->stateid_seq, __entry->stateid_hash, @@ -2155,7 +1792,7 @@ TRACE_EVENT(pnfs_update_layout, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - show_pnfs_iomode(__entry->iomode), + show_pnfs_layout_iomode(__entry->iomode), (unsigned long long)__entry->pos, (unsigned long long)__entry->count, __entry->layoutstateid_seq, __entry->layoutstateid_hash, @@ -2209,7 +1846,7 @@ DECLARE_EVENT_CLASS(pnfs_layout_event, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - show_pnfs_iomode(__entry->iomode), + show_pnfs_layout_iomode(__entry->iomode), (unsigned long long)__entry->pos, (unsigned long long)__entry->count, __entry->layoutstateid_seq, __entry->layoutstateid_hash, @@ -2354,7 +1991,7 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -2410,7 +2047,7 @@ TRACE_EVENT(ff_layout_commit_error, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%llu count=%u dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 8a224871be74..6804ca2efbf9 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -11,45 +11,9 @@ #include <linux/tracepoint.h> #include <linux/iversion.h> -TRACE_DEFINE_ENUM(DT_UNKNOWN); -TRACE_DEFINE_ENUM(DT_FIFO); -TRACE_DEFINE_ENUM(DT_CHR); -TRACE_DEFINE_ENUM(DT_DIR); -TRACE_DEFINE_ENUM(DT_BLK); -TRACE_DEFINE_ENUM(DT_REG); -TRACE_DEFINE_ENUM(DT_LNK); -TRACE_DEFINE_ENUM(DT_SOCK); -TRACE_DEFINE_ENUM(DT_WHT); - -#define nfs_show_file_type(ftype) \ - __print_symbolic(ftype, \ - { DT_UNKNOWN, "UNKNOWN" }, \ - { DT_FIFO, "FIFO" }, \ - { DT_CHR, "CHR" }, \ - { DT_DIR, "DIR" }, \ - { DT_BLK, "BLK" }, \ - { DT_REG, "REG" }, \ - { DT_LNK, "LNK" }, \ - { DT_SOCK, "SOCK" }, \ - { DT_WHT, "WHT" }) - -TRACE_DEFINE_ENUM(NFS_INO_INVALID_DATA); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_ATIME); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_ACCESS); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_ACL); -TRACE_DEFINE_ENUM(NFS_INO_REVAL_PAGECACHE); -TRACE_DEFINE_ENUM(NFS_INO_REVAL_FORCED); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_LABEL); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_CHANGE); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_CTIME); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_MTIME); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_SIZE); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_OTHER); -TRACE_DEFINE_ENUM(NFS_INO_DATA_INVAL_DEFER); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_BLOCKS); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_XATTR); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_NLINK); -TRACE_DEFINE_ENUM(NFS_INO_INVALID_MODE); +#include <trace/misc/fs.h> +#include <trace/misc/nfs.h> +#include <trace/misc/sunrpc.h> #define nfs_show_cache_validity(v) \ __print_flags(v, "|", \ @@ -71,17 +35,6 @@ TRACE_DEFINE_ENUM(NFS_INO_INVALID_MODE); { NFS_INO_INVALID_NLINK, "INVALID_NLINK" }, \ { NFS_INO_INVALID_MODE, "INVALID_MODE" }) -TRACE_DEFINE_ENUM(NFS_INO_ADVISE_RDPLUS); -TRACE_DEFINE_ENUM(NFS_INO_STALE); -TRACE_DEFINE_ENUM(NFS_INO_ACL_LRU_SET); -TRACE_DEFINE_ENUM(NFS_INO_INVALIDATING); -TRACE_DEFINE_ENUM(NFS_INO_FSCACHE); -TRACE_DEFINE_ENUM(NFS_INO_FSCACHE_LOCK); -TRACE_DEFINE_ENUM(NFS_INO_LAYOUTCOMMIT); -TRACE_DEFINE_ENUM(NFS_INO_LAYOUTCOMMITTING); -TRACE_DEFINE_ENUM(NFS_INO_LAYOUTSTATS); -TRACE_DEFINE_ENUM(NFS_INO_ODIRECT); - #define nfs_show_nfsi_flags(v) \ __print_flags(v, "|", \ { BIT(NFS_INO_ADVISE_RDPLUS), "ADVISE_RDPLUS" }, \ @@ -163,12 +116,12 @@ DECLARE_EVENT_CLASS(nfs_inode_event_done, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "type=%u (%s) version=%llu size=%lld " "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s)", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->type, - nfs_show_file_type(__entry->type), + show_fs_dirent_type(__entry->type), (unsigned long long)__entry->version, (long long)__entry->size, __entry->cache_validity, @@ -254,12 +207,12 @@ TRACE_EVENT(nfs_access_exit, "type=%u (%s) version=%llu size=%lld " "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s) " "mask=0x%x permitted=0x%x", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->type, - nfs_show_file_type(__entry->type), + show_fs_dirent_type(__entry->type), (unsigned long long)__entry->version, (long long)__entry->size, __entry->cache_validity, @@ -270,34 +223,6 @@ TRACE_EVENT(nfs_access_exit, ) ); -TRACE_DEFINE_ENUM(LOOKUP_FOLLOW); -TRACE_DEFINE_ENUM(LOOKUP_DIRECTORY); -TRACE_DEFINE_ENUM(LOOKUP_AUTOMOUNT); -TRACE_DEFINE_ENUM(LOOKUP_PARENT); -TRACE_DEFINE_ENUM(LOOKUP_REVAL); -TRACE_DEFINE_ENUM(LOOKUP_RCU); -TRACE_DEFINE_ENUM(LOOKUP_OPEN); -TRACE_DEFINE_ENUM(LOOKUP_CREATE); -TRACE_DEFINE_ENUM(LOOKUP_EXCL); -TRACE_DEFINE_ENUM(LOOKUP_RENAME_TARGET); -TRACE_DEFINE_ENUM(LOOKUP_EMPTY); -TRACE_DEFINE_ENUM(LOOKUP_DOWN); - -#define show_lookup_flags(flags) \ - __print_flags(flags, "|", \ - { LOOKUP_FOLLOW, "FOLLOW" }, \ - { LOOKUP_DIRECTORY, "DIRECTORY" }, \ - { LOOKUP_AUTOMOUNT, "AUTOMOUNT" }, \ - { LOOKUP_PARENT, "PARENT" }, \ - { LOOKUP_REVAL, "REVAL" }, \ - { LOOKUP_RCU, "RCU" }, \ - { LOOKUP_OPEN, "OPEN" }, \ - { LOOKUP_CREATE, "CREATE" }, \ - { LOOKUP_EXCL, "EXCL" }, \ - { LOOKUP_RENAME_TARGET, "RENAME_TARGET" }, \ - { LOOKUP_EMPTY, "EMPTY" }, \ - { LOOKUP_DOWN, "DOWN" }) - DECLARE_EVENT_CLASS(nfs_lookup_event, TP_PROTO( const struct inode *dir, @@ -324,7 +249,7 @@ DECLARE_EVENT_CLASS(nfs_lookup_event, TP_printk( "flags=0x%lx (%s) name=%02x:%02x:%llu/%s", __entry->flags, - show_lookup_flags(__entry->flags), + show_fs_lookup_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -368,9 +293,9 @@ DECLARE_EVENT_CLASS(nfs_lookup_event_done, TP_printk( "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), __entry->flags, - show_lookup_flags(__entry->flags), + show_fs_lookup_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -392,46 +317,6 @@ DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_exit); DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_revalidate_enter); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_revalidate_exit); -TRACE_DEFINE_ENUM(O_WRONLY); -TRACE_DEFINE_ENUM(O_RDWR); -TRACE_DEFINE_ENUM(O_CREAT); -TRACE_DEFINE_ENUM(O_EXCL); -TRACE_DEFINE_ENUM(O_NOCTTY); -TRACE_DEFINE_ENUM(O_TRUNC); -TRACE_DEFINE_ENUM(O_APPEND); -TRACE_DEFINE_ENUM(O_NONBLOCK); -TRACE_DEFINE_ENUM(O_DSYNC); -TRACE_DEFINE_ENUM(O_DIRECT); -TRACE_DEFINE_ENUM(O_LARGEFILE); -TRACE_DEFINE_ENUM(O_DIRECTORY); -TRACE_DEFINE_ENUM(O_NOFOLLOW); -TRACE_DEFINE_ENUM(O_NOATIME); -TRACE_DEFINE_ENUM(O_CLOEXEC); - -#define show_open_flags(flags) \ - __print_flags(flags, "|", \ - { O_WRONLY, "O_WRONLY" }, \ - { O_RDWR, "O_RDWR" }, \ - { O_CREAT, "O_CREAT" }, \ - { O_EXCL, "O_EXCL" }, \ - { O_NOCTTY, "O_NOCTTY" }, \ - { O_TRUNC, "O_TRUNC" }, \ - { O_APPEND, "O_APPEND" }, \ - { O_NONBLOCK, "O_NONBLOCK" }, \ - { O_DSYNC, "O_DSYNC" }, \ - { O_DIRECT, "O_DIRECT" }, \ - { O_LARGEFILE, "O_LARGEFILE" }, \ - { O_DIRECTORY, "O_DIRECTORY" }, \ - { O_NOFOLLOW, "O_NOFOLLOW" }, \ - { O_NOATIME, "O_NOATIME" }, \ - { O_CLOEXEC, "O_CLOEXEC" }) - -#define show_fmode_flags(mode) \ - __print_flags(mode, "|", \ - { ((__force unsigned long)FMODE_READ), "READ" }, \ - { ((__force unsigned long)FMODE_WRITE), "WRITE" }, \ - { ((__force unsigned long)FMODE_EXEC), "EXEC" }) - TRACE_EVENT(nfs_atomic_open_enter, TP_PROTO( const struct inode *dir, @@ -443,7 +328,7 @@ TRACE_EVENT(nfs_atomic_open_enter, TP_STRUCT__entry( __field(unsigned long, flags) - __field(unsigned int, fmode) + __field(unsigned long, fmode) __field(dev_t, dev) __field(u64, dir) __string(name, ctx->dentry->d_name.name) @@ -453,15 +338,15 @@ TRACE_EVENT(nfs_atomic_open_enter, __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; - __entry->fmode = (__force unsigned int)ctx->mode; + __entry->fmode = (__force unsigned long)ctx->mode; __assign_str(name, ctx->dentry->d_name.name); ), TP_printk( "flags=0x%lx (%s) fmode=%s name=%02x:%02x:%llu/%s", __entry->flags, - show_open_flags(__entry->flags), - show_fmode_flags(__entry->fmode), + show_fs_fcntl_open_flags(__entry->flags), + show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -481,7 +366,7 @@ TRACE_EVENT(nfs_atomic_open_exit, TP_STRUCT__entry( __field(unsigned long, error) __field(unsigned long, flags) - __field(unsigned int, fmode) + __field(unsigned long, fmode) __field(dev_t, dev) __field(u64, dir) __string(name, ctx->dentry->d_name.name) @@ -492,17 +377,17 @@ TRACE_EVENT(nfs_atomic_open_exit, __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; - __entry->fmode = (__force unsigned int)ctx->mode; + __entry->fmode = (__force unsigned long)ctx->mode; __assign_str(name, ctx->dentry->d_name.name); ), TP_printk( "error=%ld (%s) flags=0x%lx (%s) fmode=%s " "name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), __entry->flags, - show_open_flags(__entry->flags), - show_fmode_flags(__entry->fmode), + show_fs_fcntl_open_flags(__entry->flags), + show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -535,7 +420,7 @@ TRACE_EVENT(nfs_create_enter, TP_printk( "flags=0x%lx (%s) name=%02x:%02x:%llu/%s", __entry->flags, - show_open_flags(__entry->flags), + show_fs_fcntl_open_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -570,9 +455,9 @@ TRACE_EVENT(nfs_create_exit, TP_printk( "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), __entry->flags, - show_open_flags(__entry->flags), + show_fs_fcntl_open_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -640,7 +525,7 @@ DECLARE_EVENT_CLASS(nfs_directory_event_done, TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -730,7 +615,7 @@ TRACE_EVENT(nfs_link_exit, TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fileid, MAJOR(__entry->dev), MINOR(__entry->dev), @@ -817,7 +702,7 @@ DECLARE_EVENT_CLASS(nfs_rename_event_done, TP_printk( "error=%ld (%s) old_name=%02x:%02x:%llu/%s " "new_name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->old_dir, __get_str(old_name), @@ -871,7 +756,7 @@ TRACE_EVENT(nfs_sillyrename_unlink, TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -1054,16 +939,6 @@ TRACE_EVENT(nfs_pgio_error, ) ); -TRACE_DEFINE_ENUM(NFS_UNSTABLE); -TRACE_DEFINE_ENUM(NFS_DATA_SYNC); -TRACE_DEFINE_ENUM(NFS_FILE_SYNC); - -#define nfs_show_stable(stable) \ - __print_symbolic(stable, \ - { NFS_UNSTABLE, "UNSTABLE" }, \ - { NFS_DATA_SYNC, "DATA_SYNC" }, \ - { NFS_FILE_SYNC, "FILE_SYNC" }) - TRACE_EVENT(nfs_initiate_write, TP_PROTO( const struct nfs_pgio_header *hdr @@ -1077,7 +952,7 @@ TRACE_EVENT(nfs_initiate_write, __field(u64, fileid) __field(loff_t, offset) __field(u32, count) - __field(enum nfs3_stable_how, stable) + __field(unsigned long, stable) ), TP_fast_assign( @@ -1101,7 +976,7 @@ TRACE_EVENT(nfs_initiate_write, (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->count, - nfs_show_stable(__entry->stable) + show_nfs_stable_how(__entry->stable) ) ); @@ -1121,7 +996,7 @@ TRACE_EVENT(nfs_writeback_done, __field(u32, arg_count) __field(u32, res_count) __field(int, status) - __field(enum nfs3_stable_how, stable) + __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), @@ -1154,8 +1029,8 @@ TRACE_EVENT(nfs_writeback_done, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, __entry->status, - nfs_show_stable(__entry->stable), - __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE) + show_nfs_stable_how(__entry->stable), + show_nfs4_verifier(__entry->verifier) ) ); @@ -1256,7 +1131,7 @@ TRACE_EVENT(nfs_commit_done, __field(u64, fileid) __field(loff_t, offset) __field(int, status) - __field(enum nfs3_stable_how, stable) + __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), @@ -1285,8 +1160,8 @@ TRACE_EVENT(nfs_commit_done, (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->status, - nfs_show_stable(__entry->stable), - __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE) + show_nfs_stable_how(__entry->stable), + show_nfs4_verifier(__entry->verifier) ) ); @@ -1323,76 +1198,6 @@ TRACE_EVENT(nfs_fh_to_dentry, ) ); -TRACE_DEFINE_ENUM(NFS_OK); -TRACE_DEFINE_ENUM(NFSERR_PERM); -TRACE_DEFINE_ENUM(NFSERR_NOENT); -TRACE_DEFINE_ENUM(NFSERR_IO); -TRACE_DEFINE_ENUM(NFSERR_NXIO); -TRACE_DEFINE_ENUM(ECHILD); -TRACE_DEFINE_ENUM(NFSERR_EAGAIN); -TRACE_DEFINE_ENUM(NFSERR_ACCES); -TRACE_DEFINE_ENUM(NFSERR_EXIST); -TRACE_DEFINE_ENUM(NFSERR_XDEV); -TRACE_DEFINE_ENUM(NFSERR_NODEV); -TRACE_DEFINE_ENUM(NFSERR_NOTDIR); -TRACE_DEFINE_ENUM(NFSERR_ISDIR); -TRACE_DEFINE_ENUM(NFSERR_INVAL); -TRACE_DEFINE_ENUM(NFSERR_FBIG); -TRACE_DEFINE_ENUM(NFSERR_NOSPC); -TRACE_DEFINE_ENUM(NFSERR_ROFS); -TRACE_DEFINE_ENUM(NFSERR_MLINK); -TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP); -TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG); -TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY); -TRACE_DEFINE_ENUM(NFSERR_DQUOT); -TRACE_DEFINE_ENUM(NFSERR_STALE); -TRACE_DEFINE_ENUM(NFSERR_REMOTE); -TRACE_DEFINE_ENUM(NFSERR_WFLUSH); -TRACE_DEFINE_ENUM(NFSERR_BADHANDLE); -TRACE_DEFINE_ENUM(NFSERR_NOT_SYNC); -TRACE_DEFINE_ENUM(NFSERR_BAD_COOKIE); -TRACE_DEFINE_ENUM(NFSERR_NOTSUPP); -TRACE_DEFINE_ENUM(NFSERR_TOOSMALL); -TRACE_DEFINE_ENUM(NFSERR_SERVERFAULT); -TRACE_DEFINE_ENUM(NFSERR_BADTYPE); -TRACE_DEFINE_ENUM(NFSERR_JUKEBOX); - -#define nfs_show_status(x) \ - __print_symbolic(x, \ - { NFS_OK, "OK" }, \ - { NFSERR_PERM, "PERM" }, \ - { NFSERR_NOENT, "NOENT" }, \ - { NFSERR_IO, "IO" }, \ - { NFSERR_NXIO, "NXIO" }, \ - { ECHILD, "CHILD" }, \ - { NFSERR_EAGAIN, "AGAIN" }, \ - { NFSERR_ACCES, "ACCES" }, \ - { NFSERR_EXIST, "EXIST" }, \ - { NFSERR_XDEV, "XDEV" }, \ - { NFSERR_NODEV, "NODEV" }, \ - { NFSERR_NOTDIR, "NOTDIR" }, \ - { NFSERR_ISDIR, "ISDIR" }, \ - { NFSERR_INVAL, "INVAL" }, \ - { NFSERR_FBIG, "FBIG" }, \ - { NFSERR_NOSPC, "NOSPC" }, \ - { NFSERR_ROFS, "ROFS" }, \ - { NFSERR_MLINK, "MLINK" }, \ - { NFSERR_OPNOTSUPP, "OPNOTSUPP" }, \ - { NFSERR_NAMETOOLONG, "NAMETOOLONG" }, \ - { NFSERR_NOTEMPTY, "NOTEMPTY" }, \ - { NFSERR_DQUOT, "DQUOT" }, \ - { NFSERR_STALE, "STALE" }, \ - { NFSERR_REMOTE, "REMOTE" }, \ - { NFSERR_WFLUSH, "WFLUSH" }, \ - { NFSERR_BADHANDLE, "BADHANDLE" }, \ - { NFSERR_NOT_SYNC, "NOTSYNC" }, \ - { NFSERR_BAD_COOKIE, "BADCOOKIE" }, \ - { NFSERR_NOTSUPP, "NOTSUPP" }, \ - { NFSERR_TOOSMALL, "TOOSMALL" }, \ - { NFSERR_SERVERFAULT, "REMOTEIO" }, \ - { NFSERR_BADTYPE, "BADTYPE" }, \ - { NFSERR_JUKEBOX, "JUKEBOX" }) - DECLARE_EVENT_CLASS(nfs_xdr_event, TP_PROTO( const struct xdr_stream *xdr, @@ -1427,12 +1232,12 @@ DECLARE_EVENT_CLASS(nfs_xdr_event, __assign_str(procedure, task->tk_msg.rpc_proc->p_name); ), - TP_printk( - "task:%u@%d xid=0x%08x %sv%d %s error=%ld (%s)", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x %sv%d %s error=%ld (%s)", __entry->task_id, __entry->client_id, __entry->xid, __get_str(program), __entry->version, __get_str(procedure), -__entry->error, - nfs_show_status(__entry->error) + show_nfs_status(__entry->error) ) ); #define DEFINE_NFS_XDR_EVENT(name) \ diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 3307361c7956..f331f067691b 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -82,10 +82,6 @@ enum pnfs_try_status { PNFS_TRY_AGAIN = 2, }; -/* error codes for internal use */ -#define NFS4ERR_RESET_TO_MDS 12001 -#define NFS4ERR_RESET_TO_PNFS 12002 - #ifdef CONFIG_NFS_V4_1 #define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4" diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 4231d51fc1ad..3d06bad2760d 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1644,7 +1644,7 @@ static int wait_on_commit(struct nfs_mds_commit_info *cinfo) !atomic_read(&cinfo->rpcs_out)); } -static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) { atomic_inc(&cinfo->rpcs_out); } diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 6e9ea4ee0f73..7f071519fb2e 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -8,6 +8,7 @@ config NFSD select SUNRPC select EXPORTFS select NFS_ACL_SUPPORT if NFSD_V2_ACL + select NFS_ACL_SUPPORT if NFSD_V3_ACL depends on MULTIUSER help Choose Y here if you want to allow other computers to access @@ -26,28 +27,29 @@ config NFSD Below you can choose which versions of the NFS protocol are available to clients mounting the NFS server on this system. - Support for NFS version 2 (RFC 1094) is always available when + Support for NFS version 3 (RFC 1813) is always available when CONFIG_NFSD is selected. If unsure, say N. -config NFSD_V2_ACL - bool - depends on NFSD - -config NFSD_V3 - bool "NFS server support for NFS version 3" +config NFSD_V2 + bool "NFS server support for NFS version 2 (DEPRECATED)" depends on NFSD + default n help - This option enables support in your system's NFS server for - version 3 of the NFS protocol (RFC 1813). + NFSv2 (RFC 1094) was the first publicly-released version of NFS. + Unless you are hosting ancient (1990's era) NFS clients, you don't + need this. - If unsure, say Y. + If unsure, say N. + +config NFSD_V2_ACL + bool "NFS server support for the NFSv2 ACL protocol extension" + depends on NFSD_V2 config NFSD_V3_ACL bool "NFS server support for the NFSv3 ACL protocol extension" - depends on NFSD_V3 - select NFSD_V2_ACL + depends on NFSD help Solaris NFS servers support an auxiliary NFSv3 ACL protocol that never became an official part of the NFS version 3 protocol. @@ -70,7 +72,6 @@ config NFSD_V3_ACL config NFSD_V4 bool "NFS server support for NFS version 4" depends on NFSD && PROC_FS - select NFSD_V3 select FS_POSIX_ACL select SUNRPC_GSS select CRYPTO diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 3f0983e93a99..6fffc8f03f74 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -10,11 +10,11 @@ obj-$(CONFIG_NFSD) += nfsd.o # this one should be compiled first, as the tracing macros can easily blow up nfsd-y += trace.o -nfsd-y += nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \ - export.o auth.o lockd.o nfscache.o nfsxdr.o \ - stats.o filecache.o +nfsd-y += nfssvc.o nfsctl.o nfsfh.o vfs.o \ + export.o auth.o lockd.o nfscache.o \ + stats.o filecache.o nfs3proc.o nfs3xdr.o +nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o -nfsd-$(CONFIG_NFSD_V3) += nfs3proc.o nfs3xdr.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ nfs4acl.o nfs4callback.o nfs4recover.o diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h index ba14d2f4b64f..4b7324458a94 100644 --- a/fs/nfsd/acl.h +++ b/fs/nfsd/acl.h @@ -38,6 +38,8 @@ struct nfs4_acl; struct svc_fh; struct svc_rqst; +struct nfsd_attrs; +enum nfs_ftype4; int nfs4_acl_bytes(int entries); int nfs4_acl_get_whotype(char *, u32); @@ -45,7 +47,7 @@ __be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who); int nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_acl **acl); -__be32 nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct nfs4_acl *acl); +__be32 nfsd4_acl_to_attr(enum nfs_ftype4 type, struct nfs4_acl *acl, + struct nfsd_attrs *attr); #endif /* LINUX_NFS4_ACL_H */ diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index c99dee99a3c1..0ddd20cb6806 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -16,6 +16,7 @@ #include "blocklayoutxdr.h" #include "pnfs.h" #include "filecache.h" +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PNFS diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 2455dc8be18a..1ed2f691ebb9 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -9,6 +9,7 @@ #include "nfsd.h" #include "blocklayoutxdr.h" +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PNFS diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index 65c331f75e9c..f21259ead64b 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -84,6 +84,6 @@ int nfsd_reply_cache_init(struct nfsd_net *); void nfsd_reply_cache_shutdown(struct nfsd_net *); int nfsd_cache_lookup(struct svc_rqst *); void nfsd_cache_update(struct svc_rqst *, int, __be32 *); -int nfsd_reply_cache_stats_open(struct inode *, struct file *); +int nfsd_reply_cache_stats_show(struct seq_file *m, void *v); #endif /* NFSCACHE_H */ diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index ee0e3aba4a6e..d03f7f6a8642 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -115,7 +115,6 @@ struct svc_export * rqst_find_fsidzero_export(struct svc_rqst *); int exp_rootfh(struct net *, struct auth_domain *, char *path, struct knfsd_fh *, int maxsize); __be32 exp_pseudoroot(struct svc_rqst *, struct svc_fh *); -__be32 nfserrno(int errno); static inline void exp_put(struct svc_export *exp) { diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 1e8c31ed6c7c..615ea8324911 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -1,7 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * Open file cache. + * The NFSD open file cache. * * (c) 2015 - Jeff Layton <jeff.layton@primarydata.com> + * + * An nfsd_file object is a per-file collection of open state that binds + * together: + * - a struct file * + * - a user credential + * - a network namespace + * - a read-ahead context + * - monitoring for writeback errors + * + * nfsd_file objects are reference-counted. Consumers acquire a new + * object via the nfsd_file_acquire API. They manage their interest in + * the acquired object, and hence the object's reference count, via + * nfsd_file_get and nfsd_file_put. There are two varieties of nfsd_file + * object: + * + * * non-garbage-collected: When a consumer wants to precisely control + * the lifetime of a file's open state, it acquires a non-garbage- + * collected nfsd_file. The final nfsd_file_put releases the open + * state immediately. + * + * * garbage-collected: When a consumer does not control the lifetime + * of open state, it acquires a garbage-collected nfsd_file. The + * final nfsd_file_put allows the open state to linger for a period + * during which it may be re-used. */ #include <linux/hash.h> @@ -12,6 +37,7 @@ #include <linux/fsnotify_backend.h> #include <linux/fsnotify.h> #include <linux/seq_file.h> +#include <linux/rhashtable.h> #include "vfs.h" #include "nfsd.h" @@ -20,63 +46,75 @@ #include "filecache.h" #include "trace.h" -#define NFSDDBG_FACILITY NFSDDBG_FH - -/* FIXME: dynamically size this for the machine somehow? */ -#define NFSD_FILE_HASH_BITS 12 -#define NFSD_FILE_HASH_SIZE (1 << NFSD_FILE_HASH_BITS) #define NFSD_LAUNDRETTE_DELAY (2 * HZ) -#define NFSD_FILE_SHUTDOWN (1) -#define NFSD_FILE_LRU_THRESHOLD (4096UL) -#define NFSD_FILE_LRU_LIMIT (NFSD_FILE_LRU_THRESHOLD << 2) +#define NFSD_FILE_CACHE_UP (0) /* We only care about NFSD_MAY_READ/WRITE for this cache */ #define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE) -struct nfsd_fcache_bucket { - struct hlist_head nfb_head; - spinlock_t nfb_lock; - unsigned int nfb_count; - unsigned int nfb_maxcount; -}; - static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits); +static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions); +static DEFINE_PER_CPU(unsigned long, nfsd_file_releases); +static DEFINE_PER_CPU(unsigned long, nfsd_file_total_age); +static DEFINE_PER_CPU(unsigned long, nfsd_file_evictions); struct nfsd_fcache_disposal { - struct list_head list; struct work_struct work; - struct net *net; spinlock_t lock; struct list_head freeme; - struct rcu_head rcu; }; static struct workqueue_struct *nfsd_filecache_wq __read_mostly; static struct kmem_cache *nfsd_file_slab; static struct kmem_cache *nfsd_file_mark_slab; -static struct nfsd_fcache_bucket *nfsd_file_hashtbl; static struct list_lru nfsd_file_lru; -static long nfsd_file_lru_flags; +static unsigned long nfsd_file_flags; static struct fsnotify_group *nfsd_file_fsnotify_group; -static atomic_long_t nfsd_filecache_count; static struct delayed_work nfsd_filecache_laundrette; -static DEFINE_SPINLOCK(laundrette_lock); -static LIST_HEAD(laundrettes); +static struct rhltable nfsd_file_rhltable + ____cacheline_aligned_in_smp; + +static bool +nfsd_match_cred(const struct cred *c1, const struct cred *c2) +{ + int i; + + if (!uid_eq(c1->fsuid, c2->fsuid)) + return false; + if (!gid_eq(c1->fsgid, c2->fsgid)) + return false; + if (c1->group_info == NULL || c2->group_info == NULL) + return c1->group_info == c2->group_info; + if (c1->group_info->ngroups != c2->group_info->ngroups) + return false; + for (i = 0; i < c1->group_info->ngroups; i++) { + if (!gid_eq(c1->group_info->gid[i], c2->group_info->gid[i])) + return false; + } + return true; +} -static void nfsd_file_gc(void); +static const struct rhashtable_params nfsd_file_rhash_params = { + .key_len = sizeof_field(struct nfsd_file, nf_inode), + .key_offset = offsetof(struct nfsd_file, nf_inode), + .head_offset = offsetof(struct nfsd_file, nf_rlist), + + /* + * Start with a single page hash table to reduce resizing churn + * on light workloads. + */ + .min_size = 256, + .automatic_shrinking = true, +}; static void nfsd_file_schedule_laundrette(void) { - long count = atomic_long_read(&nfsd_filecache_count); - - if (count == 0 || test_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags)) - return; - - queue_delayed_work(system_wq, &nfsd_filecache_laundrette, - NFSD_LAUNDRETTE_DELAY); + if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags)) + queue_delayed_work(system_wq, &nfsd_filecache_laundrette, + NFSD_LAUNDRETTE_DELAY); } static void @@ -115,22 +153,21 @@ nfsd_file_mark_put(struct nfsd_file_mark *nfm) } static struct nfsd_file_mark * -nfsd_file_mark_find_or_create(struct nfsd_file *nf) +nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode) { int err; struct fsnotify_mark *mark; struct nfsd_file_mark *nfm = NULL, *new; - struct inode *inode = nf->nf_inode; do { - mutex_lock(&nfsd_file_fsnotify_group->mark_mutex); + fsnotify_group_lock(nfsd_file_fsnotify_group); mark = fsnotify_find_mark(&inode->i_fsnotify_marks, - nfsd_file_fsnotify_group); + nfsd_file_fsnotify_group); if (mark) { nfm = nfsd_file_mark_get(container_of(mark, struct nfsd_file_mark, nfm_mark)); - mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex); + fsnotify_group_unlock(nfsd_file_fsnotify_group); if (nfm) { fsnotify_put_mark(mark); break; @@ -138,8 +175,9 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf) /* Avoid soft lockup race with nfsd_file_mark_put() */ fsnotify_destroy_mark(mark, nfsd_file_fsnotify_group); fsnotify_put_mark(mark); - } else - mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex); + } else { + fsnotify_group_unlock(nfsd_file_fsnotify_group); + } /* allocate a new nfm */ new = kmem_cache_alloc(nfsd_file_mark_slab, GFP_KERNEL); @@ -170,238 +208,233 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf) } static struct nfsd_file * -nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval, - struct net *net) +nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need, + bool want_gc) { struct nfsd_file *nf; nf = kmem_cache_alloc(nfsd_file_slab, GFP_KERNEL); - if (nf) { - INIT_HLIST_NODE(&nf->nf_node); - INIT_LIST_HEAD(&nf->nf_lru); - nf->nf_file = NULL; - nf->nf_cred = get_current_cred(); - nf->nf_net = net; - nf->nf_flags = 0; - nf->nf_inode = inode; - nf->nf_hashval = hashval; - refcount_set(&nf->nf_ref, 1); - nf->nf_may = may & NFSD_FILE_MAY_MASK; - nf->nf_mark = NULL; - trace_nfsd_file_alloc(nf); - } - return nf; -} - -static bool -nfsd_file_free(struct nfsd_file *nf) -{ - bool flush = false; - - trace_nfsd_file_put_final(nf); - if (nf->nf_mark) - nfsd_file_mark_put(nf->nf_mark); - if (nf->nf_file) { - get_file(nf->nf_file); - filp_close(nf->nf_file, NULL); - fput(nf->nf_file); - flush = true; - } - call_rcu(&nf->nf_rcu, nfsd_file_slab_free); - return flush; -} - -static bool -nfsd_file_check_writeback(struct nfsd_file *nf) -{ - struct file *file = nf->nf_file; - struct address_space *mapping; + if (unlikely(!nf)) + return NULL; - if (!file || !(file->f_mode & FMODE_WRITE)) - return false; - mapping = file->f_mapping; - return mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) || - mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); + INIT_LIST_HEAD(&nf->nf_lru); + nf->nf_birthtime = ktime_get(); + nf->nf_file = NULL; + nf->nf_cred = get_current_cred(); + nf->nf_net = net; + nf->nf_flags = want_gc ? + BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING) | BIT(NFSD_FILE_GC) : + BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING); + nf->nf_inode = inode; + refcount_set(&nf->nf_ref, 1); + nf->nf_may = need; + nf->nf_mark = NULL; + return nf; } -static int +/** + * nfsd_file_check_write_error - check for writeback errors on a file + * @nf: nfsd_file to check for writeback errors + * + * Check whether a nfsd_file has an unseen error. Reset the write + * verifier if so. + */ +static void nfsd_file_check_write_error(struct nfsd_file *nf) { struct file *file = nf->nf_file; - if (!file || !(file->f_mode & FMODE_WRITE)) - return 0; - return filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err)); + if ((file->f_mode & FMODE_WRITE) && + filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err))) + nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); } static void -nfsd_file_do_unhash(struct nfsd_file *nf) +nfsd_file_hash_remove(struct nfsd_file *nf) { - lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); - trace_nfsd_file_unhash(nf); - - if (nfsd_file_check_write_error(nf)) - nfsd_reset_boot_verifier(net_generic(nf->nf_net, nfsd_net_id)); - --nfsd_file_hashtbl[nf->nf_hashval].nfb_count; - hlist_del_rcu(&nf->nf_node); - atomic_long_dec(&nfsd_filecache_count); + rhltable_remove(&nfsd_file_rhltable, &nf->nf_rlist, + nfsd_file_rhash_params); } static bool nfsd_file_unhash(struct nfsd_file *nf) { if (test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { - nfsd_file_do_unhash(nf); - if (!list_empty(&nf->nf_lru)) - list_lru_del(&nfsd_file_lru, &nf->nf_lru); + nfsd_file_hash_remove(nf); return true; } return false; } -/* - * Return true if the file was unhashed. - */ -static bool -nfsd_file_unhash_and_release_locked(struct nfsd_file *nf, struct list_head *dispose) +static void +nfsd_file_free(struct nfsd_file *nf) { - lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); + s64 age = ktime_to_ms(ktime_sub(ktime_get(), nf->nf_birthtime)); - trace_nfsd_file_unhash_and_release_locked(nf); - if (!nfsd_file_unhash(nf)) - return false; - /* keep final reference for nfsd_file_lru_dispose */ - if (refcount_dec_not_one(&nf->nf_ref)) - return true; - - list_add(&nf->nf_lru, dispose); - return true; -} + trace_nfsd_file_free(nf); -static void -nfsd_file_put_noref(struct nfsd_file *nf) -{ - trace_nfsd_file_put(nf); + this_cpu_inc(nfsd_file_releases); + this_cpu_add(nfsd_file_total_age, age); - if (refcount_dec_and_test(&nf->nf_ref)) { - WARN_ON(test_bit(NFSD_FILE_HASHED, &nf->nf_flags)); - nfsd_file_free(nf); + nfsd_file_unhash(nf); + if (nf->nf_mark) + nfsd_file_mark_put(nf->nf_mark); + if (nf->nf_file) { + nfsd_file_check_write_error(nf); + filp_close(nf->nf_file, NULL); } -} -void -nfsd_file_put(struct nfsd_file *nf) -{ - bool is_hashed; - - set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); - if (refcount_read(&nf->nf_ref) > 2 || !nf->nf_file) { - nfsd_file_put_noref(nf); + /* + * If this item is still linked via nf_lru, that's a bug. + * WARN and leak it to preserve system stability. + */ + if (WARN_ON_ONCE(!list_empty(&nf->nf_lru))) return; - } - filemap_flush(nf->nf_file->f_mapping); - is_hashed = test_bit(NFSD_FILE_HASHED, &nf->nf_flags) != 0; - nfsd_file_put_noref(nf); - if (is_hashed) - nfsd_file_schedule_laundrette(); - if (atomic_long_read(&nfsd_filecache_count) >= NFSD_FILE_LRU_LIMIT) - nfsd_file_gc(); + call_rcu(&nf->nf_rcu, nfsd_file_slab_free); } -struct nfsd_file * -nfsd_file_get(struct nfsd_file *nf) +static bool +nfsd_file_check_writeback(struct nfsd_file *nf) { - if (likely(refcount_inc_not_zero(&nf->nf_ref))) - return nf; - return NULL; + struct file *file = nf->nf_file; + struct address_space *mapping; + + /* File not open for write? */ + if (!(file->f_mode & FMODE_WRITE)) + return false; + + /* + * Some filesystems (e.g. NFS) flush all dirty data on close. + * On others, there is no need to wait for writeback. + */ + if (!(file_inode(file)->i_sb->s_export_op->flags & EXPORT_OP_FLUSH_ON_CLOSE)) + return false; + + mapping = file->f_mapping; + return mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) || + mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); } -static void -nfsd_file_dispose_list(struct list_head *dispose) -{ - struct nfsd_file *nf; - while(!list_empty(dispose)) { - nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - list_del(&nf->nf_lru); - nfsd_file_put_noref(nf); +static bool nfsd_file_lru_add(struct nfsd_file *nf) +{ + set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); + if (list_lru_add(&nfsd_file_lru, &nf->nf_lru)) { + trace_nfsd_file_lru_add(nf); + return true; } + return false; } -static void -nfsd_file_dispose_list_sync(struct list_head *dispose) +static bool nfsd_file_lru_remove(struct nfsd_file *nf) { - bool flush = false; - struct nfsd_file *nf; - - while(!list_empty(dispose)) { - nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - list_del(&nf->nf_lru); - if (!refcount_dec_and_test(&nf->nf_ref)) - continue; - if (nfsd_file_free(nf)) - flush = true; + if (list_lru_del(&nfsd_file_lru, &nf->nf_lru)) { + trace_nfsd_file_lru_del(nf); + return true; } - if (flush) - flush_delayed_fput(); + return false; } -static void -nfsd_file_list_remove_disposal(struct list_head *dst, - struct nfsd_fcache_disposal *l) +struct nfsd_file * +nfsd_file_get(struct nfsd_file *nf) { - spin_lock(&l->lock); - list_splice_init(&l->freeme, dst); - spin_unlock(&l->lock); + if (nf && refcount_inc_not_zero(&nf->nf_ref)) + return nf; + return NULL; } -static void -nfsd_file_list_add_disposal(struct list_head *files, struct net *net) +/** + * nfsd_file_put - put the reference to a nfsd_file + * @nf: nfsd_file of which to put the reference + * + * Put a reference to a nfsd_file. In the non-GC case, we just put the + * reference immediately. In the GC case, if the reference would be + * the last one, the put it on the LRU instead to be cleaned up later. + */ +void +nfsd_file_put(struct nfsd_file *nf) { - struct nfsd_fcache_disposal *l; + might_sleep(); + trace_nfsd_file_put(nf); - rcu_read_lock(); - list_for_each_entry_rcu(l, &laundrettes, list) { - if (l->net == net) { - spin_lock(&l->lock); - list_splice_tail_init(files, &l->freeme); - spin_unlock(&l->lock); - queue_work(nfsd_filecache_wq, &l->work); - break; + if (test_bit(NFSD_FILE_GC, &nf->nf_flags) && + test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { + /* + * If this is the last reference (nf_ref == 1), then try to + * transfer it to the LRU. + */ + if (refcount_dec_not_one(&nf->nf_ref)) + return; + + /* Try to add it to the LRU. If that fails, decrement. */ + if (nfsd_file_lru_add(nf)) { + /* If it's still hashed, we're done */ + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { + nfsd_file_schedule_laundrette(); + return; + } + + /* + * We're racing with unhashing, so try to remove it from + * the LRU. If removal fails, then someone else already + * has our reference. + */ + if (!nfsd_file_lru_remove(nf)) + return; } } - rcu_read_unlock(); + if (refcount_dec_and_test(&nf->nf_ref)) + nfsd_file_free(nf); } static void -nfsd_file_list_add_pernet(struct list_head *dst, struct list_head *src, - struct net *net) +nfsd_file_dispose_list(struct list_head *dispose) { - struct nfsd_file *nf, *tmp; + struct nfsd_file *nf; - list_for_each_entry_safe(nf, tmp, src, nf_lru) { - if (nf->nf_net == net) - list_move_tail(&nf->nf_lru, dst); + while (!list_empty(dispose)) { + nf = list_first_entry(dispose, struct nfsd_file, nf_lru); + list_del_init(&nf->nf_lru); + nfsd_file_free(nf); } } +/** + * nfsd_file_dispose_list_delayed - move list of dead files to net's freeme list + * @dispose: list of nfsd_files to be disposed + * + * Transfers each file to the "freeme" list for its nfsd_net, to eventually + * be disposed of by the per-net garbage collector. + */ static void nfsd_file_dispose_list_delayed(struct list_head *dispose) { - LIST_HEAD(list); - struct nfsd_file *nf; - while(!list_empty(dispose)) { - nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - nfsd_file_list_add_pernet(&list, dispose, nf->nf_net); - nfsd_file_list_add_disposal(&list, nf->nf_net); + struct nfsd_file *nf = list_first_entry(dispose, + struct nfsd_file, nf_lru); + struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id); + struct nfsd_fcache_disposal *l = nn->fcache_disposal; + + spin_lock(&l->lock); + list_move_tail(&nf->nf_lru, &l->freeme); + spin_unlock(&l->lock); + queue_work(nfsd_filecache_wq, &l->work); } } -/* - * Note this can deadlock with nfsd_file_cache_purge. +/** + * nfsd_file_lru_cb - Examine an entry on the LRU list + * @item: LRU entry to examine + * @lru: controlling LRU + * @lock: LRU list lock (unused) + * @arg: dispose list + * + * Return values: + * %LRU_REMOVED: @item was removed from the LRU + * %LRU_ROTATE: @item is to be moved to the LRU tail + * %LRU_SKIP: @item cannot be evicted */ static enum lru_status nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, @@ -412,72 +445,60 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, struct list_head *head = arg; struct nfsd_file *nf = list_entry(item, struct nfsd_file, nf_lru); - /* - * Do a lockless refcount check. The hashtable holds one reference, so - * we look to see if anything else has a reference, or if any have - * been put since the shrinker last ran. Those don't get unhashed and - * released. - * - * Note that in the put path, we set the flag and then decrement the - * counter. Here we check the counter and then test and clear the flag. - * That order is deliberate to ensure that we can do this locklessly. - */ - if (refcount_read(&nf->nf_ref) > 1) - goto out_skip; + /* We should only be dealing with GC entries here */ + WARN_ON_ONCE(!test_bit(NFSD_FILE_GC, &nf->nf_flags)); /* * Don't throw out files that are still undergoing I/O or * that have uncleared errors pending. */ - if (nfsd_file_check_writeback(nf)) - goto out_skip; + if (nfsd_file_check_writeback(nf)) { + trace_nfsd_file_gc_writeback(nf); + return LRU_SKIP; + } - if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags)) - goto out_skip; + /* If it was recently added to the list, skip it */ + if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags)) { + trace_nfsd_file_gc_referenced(nf); + return LRU_ROTATE; + } - if (!test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) - goto out_skip; + /* + * Put the reference held on behalf of the LRU. If it wasn't the last + * one, then just remove it from the LRU and ignore it. + */ + if (!refcount_dec_and_test(&nf->nf_ref)) { + trace_nfsd_file_gc_in_use(nf); + list_lru_isolate(lru, &nf->nf_lru); + return LRU_REMOVED; + } + /* Refcount went to zero. Unhash it and queue it to the dispose list */ + nfsd_file_unhash(nf); list_lru_isolate_move(lru, &nf->nf_lru, head); + this_cpu_inc(nfsd_file_evictions); + trace_nfsd_file_gc_disposed(nf); return LRU_REMOVED; -out_skip: - return LRU_SKIP; -} - -static unsigned long -nfsd_file_lru_walk_list(struct shrink_control *sc) -{ - LIST_HEAD(head); - struct nfsd_file *nf; - unsigned long ret; - - if (sc) - ret = list_lru_shrink_walk(&nfsd_file_lru, sc, - nfsd_file_lru_cb, &head); - else - ret = list_lru_walk(&nfsd_file_lru, - nfsd_file_lru_cb, - &head, LONG_MAX); - list_for_each_entry(nf, &head, nf_lru) { - spin_lock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); - nfsd_file_do_unhash(nf); - spin_unlock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); - } - nfsd_file_dispose_list_delayed(&head); - return ret; } static void nfsd_file_gc(void) { - nfsd_file_lru_walk_list(NULL); + LIST_HEAD(dispose); + unsigned long ret; + + ret = list_lru_walk(&nfsd_file_lru, nfsd_file_lru_cb, + &dispose, list_lru_count(&nfsd_file_lru)); + trace_nfsd_file_gc_removed(ret, list_lru_count(&nfsd_file_lru)); + nfsd_file_dispose_list_delayed(&dispose); } static void nfsd_file_gc_worker(struct work_struct *work) { nfsd_file_gc(); - nfsd_file_schedule_laundrette(); + if (list_lru_count(&nfsd_file_lru)) + nfsd_file_schedule_laundrette(); } static unsigned long @@ -489,7 +510,14 @@ nfsd_file_lru_count(struct shrinker *s, struct shrink_control *sc) static unsigned long nfsd_file_lru_scan(struct shrinker *s, struct shrink_control *sc) { - return nfsd_file_lru_walk_list(sc); + LIST_HEAD(dispose); + unsigned long ret; + + ret = list_lru_shrink_walk(&nfsd_file_lru, sc, + nfsd_file_lru_cb, &dispose); + trace_nfsd_file_shrinker_removed(ret, list_lru_count(&nfsd_file_lru)); + nfsd_file_dispose_list_delayed(&dispose); + return ret; } static struct shrinker nfsd_file_shrinker = { @@ -498,70 +526,123 @@ static struct shrinker nfsd_file_shrinker = { .seeks = 1, }; +/** + * nfsd_file_cond_queue - conditionally unhash and queue a nfsd_file + * @nf: nfsd_file to attempt to queue + * @dispose: private list to queue successfully-put objects + * + * Unhash an nfsd_file, try to get a reference to it, and then put that + * reference. If it's the last reference, queue it to the dispose list. + */ static void -__nfsd_file_close_inode(struct inode *inode, unsigned int hashval, - struct list_head *dispose) +nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) + __must_hold(RCU) { - struct nfsd_file *nf; - struct hlist_node *tmp; + int decrement = 1; - spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock); - hlist_for_each_entry_safe(nf, tmp, &nfsd_file_hashtbl[hashval].nfb_head, nf_node) { - if (inode == nf->nf_inode) - nfsd_file_unhash_and_release_locked(nf, dispose); + /* If we raced with someone else unhashing, ignore it */ + if (!nfsd_file_unhash(nf)) + return; + + /* If we can't get a reference, ignore it */ + if (!nfsd_file_get(nf)) + return; + + /* Extra decrement if we remove from the LRU */ + if (nfsd_file_lru_remove(nf)) + ++decrement; + + /* If refcount goes to 0, then put on the dispose list */ + if (refcount_sub_and_test(decrement, &nf->nf_ref)) { + list_add(&nf->nf_lru, dispose); + trace_nfsd_file_closing(nf); } - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); } /** - * nfsd_file_close_inode_sync - attempt to forcibly close a nfsd_file - * @inode: inode of the file to attempt to remove + * nfsd_file_queue_for_close: try to close out any open nfsd_files for an inode + * @inode: inode on which to close out nfsd_files + * @dispose: list on which to gather nfsd_files to close out + * + * An nfsd_file represents a struct file being held open on behalf of nfsd. + * An open file however can block other activity (such as leases), or cause + * undesirable behavior (e.g. spurious silly-renames when reexporting NFS). + * + * This function is intended to find open nfsd_files when this sort of + * conflicting access occurs and then attempt to close those files out. * - * Walk the whole hash bucket, looking for any files that correspond to "inode". - * If any do, then unhash them and put the hashtable reference to them and - * destroy any that had their last reference put. Also ensure that any of the - * fputs also have their final __fput done as well. + * Populates the dispose list with entries that have already had their + * refcounts go to zero. The actual free of an nfsd_file can be expensive, + * so we leave it up to the caller whether it wants to wait or not. */ -void -nfsd_file_close_inode_sync(struct inode *inode) +static void +nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose) { - unsigned int hashval = (unsigned int)hash_long(inode->i_ino, - NFSD_FILE_HASH_BITS); - LIST_HEAD(dispose); + struct rhlist_head *tmp, *list; + struct nfsd_file *nf; - __nfsd_file_close_inode(inode, hashval, &dispose); - trace_nfsd_file_close_inode_sync(inode, hashval, !list_empty(&dispose)); - nfsd_file_dispose_list_sync(&dispose); + rcu_read_lock(); + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { + if (!test_bit(NFSD_FILE_GC, &nf->nf_flags)) + continue; + nfsd_file_cond_queue(nf, dispose); + } + rcu_read_unlock(); } /** * nfsd_file_close_inode - attempt a delayed close of a nfsd_file * @inode: inode of the file to attempt to remove * - * Walk the whole hash bucket, looking for any files that correspond to "inode". - * If any do, then unhash them and put the hashtable reference to them and - * destroy any that had their last reference put. + * Close out any open nfsd_files that can be reaped for @inode. The + * actual freeing is deferred to the dispose_list_delayed infrastructure. + * + * This is used by the fsnotify callbacks and setlease notifier. */ static void nfsd_file_close_inode(struct inode *inode) { - unsigned int hashval = (unsigned int)hash_long(inode->i_ino, - NFSD_FILE_HASH_BITS); LIST_HEAD(dispose); - __nfsd_file_close_inode(inode, hashval, &dispose); - trace_nfsd_file_close_inode(inode, hashval, !list_empty(&dispose)); + nfsd_file_queue_for_close(inode, &dispose); nfsd_file_dispose_list_delayed(&dispose); } /** + * nfsd_file_close_inode_sync - attempt to forcibly close a nfsd_file + * @inode: inode of the file to attempt to remove + * + * Close out any open nfsd_files that can be reaped for @inode. The + * nfsd_files are closed out synchronously. + * + * This is called from nfsd_rename and nfsd_unlink to avoid silly-renames + * when reexporting NFS. + */ +void +nfsd_file_close_inode_sync(struct inode *inode) +{ + struct nfsd_file *nf; + LIST_HEAD(dispose); + + trace_nfsd_file_close(inode); + + nfsd_file_queue_for_close(inode, &dispose); + while (!list_empty(&dispose)) { + nf = list_first_entry(&dispose, struct nfsd_file, nf_lru); + list_del_init(&nf->nf_lru); + nfsd_file_free(nf); + } + flush_delayed_fput(); +} + +/** * nfsd_file_delayed_close - close unused nfsd_files * @work: dummy * - * Walk the LRU list and close any entries that have not been used since - * the last scan. - * - * Note this can deadlock with nfsd_file_cache_purge. + * Scrape the freeme list for this nfsd_net, and then dispose of them + * all. */ static void nfsd_file_delayed_close(struct work_struct *work) @@ -570,7 +651,10 @@ nfsd_file_delayed_close(struct work_struct *work) struct nfsd_fcache_disposal *l = container_of(work, struct nfsd_fcache_disposal, work); - nfsd_file_list_remove_disposal(&head, l); + spin_lock(&l->lock); + list_splice_init(&l->freeme, &head); + spin_unlock(&l->lock); + nfsd_file_dispose_list(&head); } @@ -582,7 +666,7 @@ nfsd_file_lease_notifier_call(struct notifier_block *nb, unsigned long arg, /* Only close files for F_SETLEASE leases */ if (fl->fl_flags & FL_LEASE) - nfsd_file_close_inode_sync(file_inode(fl->fl_file)); + nfsd_file_close_inode(file_inode(fl->fl_file)); return 0; } @@ -595,6 +679,9 @@ nfsd_file_fsnotify_handle_event(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { + if (WARN_ON_ONCE(!inode)) + return 0; + trace_nfsd_file_fsnotify_handle_event(inode, mask); /* Should be no marks on non-regular files */ @@ -622,25 +709,21 @@ static const struct fsnotify_ops nfsd_file_fsnotify_ops = { int nfsd_file_cache_init(void) { - int ret = -ENOMEM; - unsigned int i; + int ret; - clear_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags); - - if (nfsd_file_hashtbl) + lockdep_assert_held(&nfsd_mutex); + if (test_and_set_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) return 0; + ret = rhltable_init(&nfsd_file_rhltable, &nfsd_file_rhash_params); + if (ret) + return ret; + + ret = -ENOMEM; nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0); if (!nfsd_filecache_wq) goto out; - nfsd_file_hashtbl = kvcalloc(NFSD_FILE_HASH_SIZE, - sizeof(*nfsd_file_hashtbl), GFP_KERNEL); - if (!nfsd_file_hashtbl) { - pr_err("nfsd: unable to allocate nfsd_file_hashtbl\n"); - goto out_err; - } - nfsd_file_slab = kmem_cache_create("nfsd_file", sizeof(struct nfsd_file), 0, 0, NULL); if (!nfsd_file_slab) { @@ -674,7 +757,8 @@ nfsd_file_cache_init(void) goto out_shrinker; } - nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops); + nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops, + FSNOTIFY_GROUP_NOFS); if (IS_ERR(nfsd_file_fsnotify_group)) { pr_err("nfsd: unable to create fsnotify group: %ld\n", PTR_ERR(nfsd_file_fsnotify_group)); @@ -683,11 +767,6 @@ nfsd_file_cache_init(void) goto out_notifier; } - for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) { - INIT_HLIST_HEAD(&nfsd_file_hashtbl[i].nfb_head); - spin_lock_init(&nfsd_file_hashtbl[i].nfb_lock); - } - INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker); out: return ret; @@ -702,50 +781,47 @@ out_err: nfsd_file_slab = NULL; kmem_cache_destroy(nfsd_file_mark_slab); nfsd_file_mark_slab = NULL; - kvfree(nfsd_file_hashtbl); - nfsd_file_hashtbl = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; + rhltable_destroy(&nfsd_file_rhltable); goto out; } -/* - * Note this can deadlock with nfsd_file_lru_cb. +/** + * __nfsd_file_cache_purge: clean out the cache for shutdown + * @net: net-namespace to shut down the cache (may be NULL) + * + * Walk the nfsd_file cache and close out any that match @net. If @net is NULL, + * then close out everything. Called when an nfsd instance is being shut down, + * and when the exports table is flushed. */ -void -nfsd_file_cache_purge(struct net *net) +static void +__nfsd_file_cache_purge(struct net *net) { - unsigned int i; - struct nfsd_file *nf; - struct hlist_node *next; + struct rhashtable_iter iter; + struct nfsd_file *nf; LIST_HEAD(dispose); - bool del; - if (!nfsd_file_hashtbl) - return; + rhltable_walk_enter(&nfsd_file_rhltable, &iter); + do { + rhashtable_walk_start(&iter); - for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) { - struct nfsd_fcache_bucket *nfb = &nfsd_file_hashtbl[i]; + nf = rhashtable_walk_next(&iter); + while (!IS_ERR_OR_NULL(nf)) { + if (!net || nf->nf_net == net) + nfsd_file_cond_queue(nf, &dispose); + nf = rhashtable_walk_next(&iter); + } - spin_lock(&nfb->nfb_lock); - hlist_for_each_entry_safe(nf, next, &nfb->nfb_head, nf_node) { - if (net && nf->nf_net != net) - continue; - del = nfsd_file_unhash_and_release_locked(nf, &dispose); + rhashtable_walk_stop(&iter); + } while (nf == ERR_PTR(-EAGAIN)); + rhashtable_walk_exit(&iter); - /* - * Deadlock detected! Something marked this entry as - * unhased, but hasn't removed it from the hash list. - */ - WARN_ON_ONCE(!del); - } - spin_unlock(&nfb->nfb_lock); - nfsd_file_dispose_list(&dispose); - } + nfsd_file_dispose_list(&dispose); } static struct nfsd_fcache_disposal * -nfsd_alloc_fcache_disposal(struct net *net) +nfsd_alloc_fcache_disposal(void) { struct nfsd_fcache_disposal *l; @@ -753,7 +829,6 @@ nfsd_alloc_fcache_disposal(struct net *net) if (!l) return NULL; INIT_WORK(&l->work, nfsd_file_delayed_close); - l->net = net; spin_lock_init(&l->lock); INIT_LIST_HEAD(&l->freeme); return l; @@ -762,61 +837,40 @@ nfsd_alloc_fcache_disposal(struct net *net) static void nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l) { - rcu_assign_pointer(l->net, NULL); cancel_work_sync(&l->work); nfsd_file_dispose_list(&l->freeme); - kfree_rcu(l, rcu); -} - -static void -nfsd_add_fcache_disposal(struct nfsd_fcache_disposal *l) -{ - spin_lock(&laundrette_lock); - list_add_tail_rcu(&l->list, &laundrettes); - spin_unlock(&laundrette_lock); + kfree(l); } static void -nfsd_del_fcache_disposal(struct nfsd_fcache_disposal *l) -{ - spin_lock(&laundrette_lock); - list_del_rcu(&l->list); - spin_unlock(&laundrette_lock); -} - -static int -nfsd_alloc_fcache_disposal_net(struct net *net) +nfsd_free_fcache_disposal_net(struct net *net) { - struct nfsd_fcache_disposal *l; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct nfsd_fcache_disposal *l = nn->fcache_disposal; - l = nfsd_alloc_fcache_disposal(net); - if (!l) - return -ENOMEM; - nfsd_add_fcache_disposal(l); - return 0; + nfsd_free_fcache_disposal(l); } -static void -nfsd_free_fcache_disposal_net(struct net *net) +int +nfsd_file_cache_start_net(struct net *net) { - struct nfsd_fcache_disposal *l; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); - rcu_read_lock(); - list_for_each_entry_rcu(l, &laundrettes, list) { - if (l->net != net) - continue; - nfsd_del_fcache_disposal(l); - rcu_read_unlock(); - nfsd_free_fcache_disposal(l); - return; - } - rcu_read_unlock(); + nn->fcache_disposal = nfsd_alloc_fcache_disposal(); + return nn->fcache_disposal ? 0 : -ENOMEM; } -int -nfsd_file_cache_start_net(struct net *net) +/** + * nfsd_file_cache_purge - Remove all cache items associated with @net + * @net: target net namespace + * + */ +void +nfsd_file_cache_purge(struct net *net) { - return nfsd_alloc_fcache_disposal_net(net); + lockdep_assert_held(&nfsd_mutex); + if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) + __nfsd_file_cache_purge(net); } void @@ -829,7 +883,11 @@ nfsd_file_cache_shutdown_net(struct net *net) void nfsd_file_cache_shutdown(void) { - set_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags); + int i; + + lockdep_assert_held(&nfsd_mutex); + if (test_and_clear_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0) + return; lease_unregister_notifier(&nfsd_file_lease_notifier); unregister_shrinker(&nfsd_file_shrinker); @@ -838,7 +896,7 @@ nfsd_file_cache_shutdown(void) * calling nfsd_file_cache_purge */ cancel_delayed_work_sync(&nfsd_filecache_laundrette); - nfsd_file_cache_purge(NULL); + __nfsd_file_cache_purge(NULL); list_lru_destroy(&nfsd_file_lru); rcu_barrier(); fsnotify_put_group(nfsd_file_fsnotify_group); @@ -848,226 +906,332 @@ nfsd_file_cache_shutdown(void) fsnotify_wait_marks_destroyed(); kmem_cache_destroy(nfsd_file_mark_slab); nfsd_file_mark_slab = NULL; - kvfree(nfsd_file_hashtbl); - nfsd_file_hashtbl = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; -} - -static bool -nfsd_match_cred(const struct cred *c1, const struct cred *c2) -{ - int i; - - if (!uid_eq(c1->fsuid, c2->fsuid)) - return false; - if (!gid_eq(c1->fsgid, c2->fsgid)) - return false; - if (c1->group_info == NULL || c2->group_info == NULL) - return c1->group_info == c2->group_info; - if (c1->group_info->ngroups != c2->group_info->ngroups) - return false; - for (i = 0; i < c1->group_info->ngroups; i++) { - if (!gid_eq(c1->group_info->gid[i], c2->group_info->gid[i])) - return false; + rhltable_destroy(&nfsd_file_rhltable); + + for_each_possible_cpu(i) { + per_cpu(nfsd_file_cache_hits, i) = 0; + per_cpu(nfsd_file_acquisitions, i) = 0; + per_cpu(nfsd_file_releases, i) = 0; + per_cpu(nfsd_file_total_age, i) = 0; + per_cpu(nfsd_file_evictions, i) = 0; } - return true; } static struct nfsd_file * -nfsd_file_find_locked(struct inode *inode, unsigned int may_flags, - unsigned int hashval, struct net *net) +nfsd_file_lookup_locked(const struct net *net, const struct cred *cred, + struct inode *inode, unsigned char need, + bool want_gc) { + struct rhlist_head *tmp, *list; struct nfsd_file *nf; - unsigned char need = may_flags & NFSD_FILE_MAY_MASK; - hlist_for_each_entry_rcu(nf, &nfsd_file_hashtbl[hashval].nfb_head, - nf_node, lockdep_is_held(&nfsd_file_hashtbl[hashval].nfb_lock)) { + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { if (nf->nf_may != need) continue; - if (nf->nf_inode != inode) - continue; if (nf->nf_net != net) continue; - if (!nfsd_match_cred(nf->nf_cred, current_cred())) + if (!nfsd_match_cred(nf->nf_cred, cred)) continue; - if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) + if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != want_gc) continue; - if (nfsd_file_get(nf) != NULL) - return nf; + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) + continue; + + if (!nfsd_file_get(nf)) + continue; + return nf; } return NULL; } /** - * nfsd_file_is_cached - are there any cached open files for this fh? - * @inode: inode of the file to check + * nfsd_file_is_cached - are there any cached open files for this inode? + * @inode: inode to check + * + * The lookup matches inodes in all net namespaces and is atomic wrt + * nfsd_file_acquire(). * - * Scan the hashtable for open files that match this fh. Returns true if there - * are any, and false if not. + * Return values: + * %true: filecache contains at least one file matching this inode + * %false: filecache contains no files matching this inode */ bool nfsd_file_is_cached(struct inode *inode) { - bool ret = false; - struct nfsd_file *nf; - unsigned int hashval; - - hashval = (unsigned int)hash_long(inode->i_ino, NFSD_FILE_HASH_BITS); + struct rhlist_head *tmp, *list; + struct nfsd_file *nf; + bool ret = false; rcu_read_lock(); - hlist_for_each_entry_rcu(nf, &nfsd_file_hashtbl[hashval].nfb_head, - nf_node) { - if (inode == nf->nf_inode) { + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) + if (test_bit(NFSD_FILE_GC, &nf->nf_flags)) { ret = true; break; } - } rcu_read_unlock(); - trace_nfsd_file_is_cached(inode, hashval, (int)ret); + + trace_nfsd_file_is_cached(inode, (int)ret); return ret; } -__be32 -nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, - unsigned int may_flags, struct nfsd_file **pnf) +static __be32 +nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct file *file, + struct nfsd_file **pnf, bool want_gc) { - __be32 status; + unsigned char need = may_flags & NFSD_FILE_MAY_MASK; struct net *net = SVC_NET(rqstp); - struct nfsd_file *nf, *new; + struct nfsd_file *new, *nf; + const struct cred *cred; + bool open_retry = true; struct inode *inode; - unsigned int hashval; - bool retry = true; + __be32 status; + int ret; - /* FIXME: skip this if fh_dentry is already set? */ status = fh_verify(rqstp, fhp, S_IFREG, may_flags|NFSD_MAY_OWNER_OVERRIDE); if (status != nfs_ok) return status; - inode = d_inode(fhp->fh_dentry); - hashval = (unsigned int)hash_long(inode->i_ino, NFSD_FILE_HASH_BITS); + cred = get_current_cred(); + retry: rcu_read_lock(); - nf = nfsd_file_find_locked(inode, may_flags, hashval, net); + nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc); rcu_read_unlock(); - if (nf) + + if (nf) { + /* + * If the nf is on the LRU then it holds an extra reference + * that must be put if it's removed. It had better not be + * the last one however, since we should hold another. + */ + if (nfsd_file_lru_remove(nf)) + WARN_ON_ONCE(refcount_dec_and_test(&nf->nf_ref)); goto wait_for_construction; + } - new = nfsd_file_alloc(inode, may_flags, hashval, net); + new = nfsd_file_alloc(net, inode, need, want_gc); if (!new) { - trace_nfsd_file_acquire(rqstp, hashval, inode, may_flags, - NULL, nfserr_jukebox); - return nfserr_jukebox; + status = nfserr_jukebox; + goto out; } - spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock); - nf = nfsd_file_find_locked(inode, may_flags, hashval, net); - if (nf == NULL) + rcu_read_lock(); + spin_lock(&inode->i_lock); + nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc); + if (unlikely(nf)) { + spin_unlock(&inode->i_lock); + rcu_read_unlock(); + nfsd_file_slab_free(&new->nf_rcu); + goto wait_for_construction; + } + nf = new; + ret = rhltable_insert(&nfsd_file_rhltable, &nf->nf_rlist, + nfsd_file_rhash_params); + spin_unlock(&inode->i_lock); + rcu_read_unlock(); + if (likely(ret == 0)) goto open_file; - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); - nfsd_file_slab_free(&new->nf_rcu); + + if (ret == -EEXIST) + goto retry; + trace_nfsd_file_insert_err(rqstp, inode, may_flags, ret); + status = nfserr_jukebox; + goto construction_err; wait_for_construction: wait_on_bit(&nf->nf_flags, NFSD_FILE_PENDING, TASK_UNINTERRUPTIBLE); /* Did construction of this file fail? */ if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { - if (!retry) { + trace_nfsd_file_cons_err(rqstp, inode, may_flags, nf); + if (!open_retry) { status = nfserr_jukebox; - goto out; + goto construction_err; } - retry = false; - nfsd_file_put_noref(nf); + open_retry = false; goto retry; } - this_cpu_inc(nfsd_file_cache_hits); status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags)); -out: - if (status == nfs_ok) { - *pnf = nf; - } else { + if (status != nfs_ok) { nfsd_file_put(nf); nf = NULL; } - trace_nfsd_file_acquire(rqstp, hashval, inode, may_flags, nf, status); +out: + if (status == nfs_ok) { + this_cpu_inc(nfsd_file_acquisitions); + nfsd_file_check_write_error(nf); + *pnf = nf; + } + put_cred(cred); + trace_nfsd_file_acquire(rqstp, inode, may_flags, nf, status); return status; + open_file: - nf = new; - /* Take reference for the hashtable */ - refcount_inc(&nf->nf_ref); - __set_bit(NFSD_FILE_HASHED, &nf->nf_flags); - __set_bit(NFSD_FILE_PENDING, &nf->nf_flags); - list_lru_add(&nfsd_file_lru, &nf->nf_lru); - hlist_add_head_rcu(&nf->nf_node, &nfsd_file_hashtbl[hashval].nfb_head); - ++nfsd_file_hashtbl[hashval].nfb_count; - nfsd_file_hashtbl[hashval].nfb_maxcount = max(nfsd_file_hashtbl[hashval].nfb_maxcount, - nfsd_file_hashtbl[hashval].nfb_count); - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); - if (atomic_long_inc_return(&nfsd_filecache_count) >= NFSD_FILE_LRU_THRESHOLD) - nfsd_file_gc(); - - nf->nf_mark = nfsd_file_mark_find_or_create(nf); - if (nf->nf_mark) - status = nfsd_open_verified(rqstp, fhp, S_IFREG, - may_flags, &nf->nf_file); - else + trace_nfsd_file_alloc(nf); + nf->nf_mark = nfsd_file_mark_find_or_create(nf, inode); + if (nf->nf_mark) { + if (file) { + get_file(file); + nf->nf_file = file; + status = nfs_ok; + trace_nfsd_file_opened(nf, status); + } else { + status = nfsd_open_verified(rqstp, fhp, may_flags, + &nf->nf_file); + trace_nfsd_file_open(nf, status); + } + } else status = nfserr_jukebox; /* * If construction failed, or we raced with a call to unlink() * then unhash. */ - if (status != nfs_ok || inode->i_nlink == 0) { - bool do_free; - spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock); - do_free = nfsd_file_unhash(nf); - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); - if (do_free) - nfsd_file_put_noref(nf); - } - clear_bit_unlock(NFSD_FILE_PENDING, &nf->nf_flags); - smp_mb__after_atomic(); - wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING); + if (status != nfs_ok || inode->i_nlink == 0) + nfsd_file_unhash(nf); + clear_and_wake_up_bit(NFSD_FILE_PENDING, &nf->nf_flags); + if (status == nfs_ok) + goto out; + +construction_err: + if (refcount_dec_and_test(&nf->nf_ref)) + nfsd_file_free(nf); + nf = NULL; goto out; } +/** + * nfsd_file_acquire_gc - Get a struct nfsd_file with an open file + * @rqstp: the RPC transaction being executed + * @fhp: the NFS filehandle of the file to be opened + * @may_flags: NFSD_MAY_ settings for the file + * @pnf: OUT: new or found "struct nfsd_file" object + * + * The nfsd_file object returned by this API is reference-counted + * and garbage-collected. The object is retained for a few + * seconds after the final nfsd_file_put() in case the caller + * wants to re-use it. + * + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. + */ +__be32 +nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct nfsd_file **pnf) +{ + return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true); +} + +/** + * nfsd_file_acquire - Get a struct nfsd_file with an open file + * @rqstp: the RPC transaction being executed + * @fhp: the NFS filehandle of the file to be opened + * @may_flags: NFSD_MAY_ settings for the file + * @pnf: OUT: new or found "struct nfsd_file" object + * + * The nfsd_file_object returned by this API is reference-counted + * but not garbage-collected. The object is unhashed after the + * final nfsd_file_put(). + * + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. + */ +__be32 +nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct nfsd_file **pnf) +{ + return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false); +} + +/** + * nfsd_file_acquire_opened - Get a struct nfsd_file using existing open file + * @rqstp: the RPC transaction being executed + * @fhp: the NFS filehandle of the file just created + * @may_flags: NFSD_MAY_ settings for the file + * @file: cached, already-open file (may be NULL) + * @pnf: OUT: new or found "struct nfsd_file" object + * + * Acquire a nfsd_file object that is not GC'ed. If one doesn't already exist, + * and @file is non-NULL, use it to instantiate a new nfsd_file instead of + * opening a new one. + * + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. + */ +__be32 +nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct file *file, + struct nfsd_file **pnf) +{ + return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false); +} + /* * Note that fields may be added, removed or reordered in the future. Programs * scraping this file for info should test the labels to ensure they're * getting the correct field. */ -static int nfsd_file_cache_stats_show(struct seq_file *m, void *v) +int nfsd_file_cache_stats_show(struct seq_file *m, void *v) { - unsigned int i, count = 0, longest = 0; - unsigned long hits = 0; + unsigned long releases = 0, evictions = 0; + unsigned long hits = 0, acquisitions = 0; + unsigned int i, count = 0, buckets = 0; + unsigned long lru = 0, total_age = 0; - /* - * No need for spinlocks here since we're not terribly interested in - * accuracy. We do take the nfsd_mutex simply to ensure that we - * don't end up racing with server shutdown - */ + /* Serialize with server shutdown */ mutex_lock(&nfsd_mutex); - if (nfsd_file_hashtbl) { - for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) { - count += nfsd_file_hashtbl[i].nfb_count; - longest = max(longest, nfsd_file_hashtbl[i].nfb_count); - } + if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) { + struct bucket_table *tbl; + struct rhashtable *ht; + + lru = list_lru_count(&nfsd_file_lru); + + rcu_read_lock(); + ht = &nfsd_file_rhltable.ht; + count = atomic_read(&ht->nelems); + tbl = rht_dereference_rcu(ht->tbl, ht); + buckets = tbl->size; + rcu_read_unlock(); } mutex_unlock(&nfsd_mutex); - for_each_possible_cpu(i) + for_each_possible_cpu(i) { hits += per_cpu(nfsd_file_cache_hits, i); + acquisitions += per_cpu(nfsd_file_acquisitions, i); + releases += per_cpu(nfsd_file_releases, i); + total_age += per_cpu(nfsd_file_total_age, i); + evictions += per_cpu(nfsd_file_evictions, i); + } - seq_printf(m, "total entries: %u\n", count); - seq_printf(m, "longest chain: %u\n", longest); + seq_printf(m, "total inodes: %u\n", count); + seq_printf(m, "hash buckets: %u\n", buckets); + seq_printf(m, "lru entries: %lu\n", lru); seq_printf(m, "cache hits: %lu\n", hits); + seq_printf(m, "acquisitions: %lu\n", acquisitions); + seq_printf(m, "releases: %lu\n", releases); + seq_printf(m, "evictions: %lu\n", evictions); + if (releases) + seq_printf(m, "mean age (ms): %ld\n", total_age / releases); + else + seq_printf(m, "mean age (ms): -\n"); return 0; } - -int nfsd_file_cache_stats_open(struct inode *inode, struct file *file) -{ - return single_open(file, nfsd_file_cache_stats_show, NULL); -} diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index 63104be2865c..e54165a3224f 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -29,21 +29,23 @@ struct nfsd_file_mark { * never be dereferenced, only used for comparison. */ struct nfsd_file { - struct hlist_node nf_node; - struct list_head nf_lru; - struct rcu_head nf_rcu; + struct rhlist_head nf_rlist; + void *nf_inode; struct file *nf_file; const struct cred *nf_cred; struct net *nf_net; #define NFSD_FILE_HASHED (0) #define NFSD_FILE_PENDING (1) #define NFSD_FILE_REFERENCED (2) +#define NFSD_FILE_GC (3) unsigned long nf_flags; - struct inode *nf_inode; - unsigned int nf_hashval; refcount_t nf_ref; unsigned char nf_may; + struct nfsd_file_mark *nf_mark; + struct list_head nf_lru; + struct rcu_head nf_rcu; + ktime_t nf_birthtime; }; int nfsd_file_cache_init(void); @@ -55,7 +57,12 @@ void nfsd_file_put(struct nfsd_file *nf); struct nfsd_file *nfsd_file_get(struct nfsd_file *nf); void nfsd_file_close_inode_sync(struct inode *inode); bool nfsd_file_is_cached(struct inode *inode); +__be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct nfsd_file **nfp); __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **nfp); -int nfsd_file_cache_stats_open(struct inode *, struct file *); +__be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct file *file, + struct nfsd_file **nfp); +int nfsd_file_cache_stats_show(struct seq_file *m, void *v); #endif /* _FS_NFSD_FILECACHE_H */ diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c index db7ef07ae50c..fabc21ed68ce 100644 --- a/fs/nfsd/flexfilelayout.c +++ b/fs/nfsd/flexfilelayout.c @@ -15,6 +15,7 @@ #include "flexfilelayoutxdr.h" #include "pnfs.h" +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PNFS @@ -61,7 +62,7 @@ nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, goto out_error; fl->fh.size = fhp->fh_handle.fh_size; - memcpy(fl->fh.data, &fhp->fh_handle.fh_base, fl->fh.size); + memcpy(fl->fh.data, &fhp->fh_handle.fh_raw, fl->fh.size); /* Give whole file layout segments */ seg->offset = 0; diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 606fa155c28a..46a7f9b813e5 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -35,7 +35,7 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp, /* must initialize before using! but maxsize doesn't matter */ fh_init(&fh,0); fh.fh_handle.fh_size = f->size; - memcpy((char*)&fh.fh_handle.fh_base, f->data, f->size); + memcpy(&fh.fh_handle.fh_raw, f->data, f->size); fh.fh_export = NULL; access = (mode == O_WRONLY) ? NFSD_MAY_WRITE : NFSD_MAY_READ; diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 935c1028c217..51a4b7885cae 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -11,6 +11,7 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/percpu_counter.h> +#include <linux/siphash.h> /* Hash tables for nfs4_clientid state */ #define CLIENT_HASH_BITS 4 @@ -108,9 +109,8 @@ struct nfsd_net { bool nfsd_net_up; bool lockd_up; - /* Time of server startup */ - struct timespec64 nfssvc_boot; - seqlock_t boot_lock; + seqlock_t writeverf_lock; + unsigned char writeverf[8]; /* * Max number of connections this nfsd container will allow. Defaults @@ -123,12 +123,13 @@ struct nfsd_net { u32 clverifier_counter; struct svc_serv *nfsd_serv; - - wait_queue_head_t ntf_wq; - atomic_t ntf_refcnt; - - /* Allow umount to wait for nfsd state cleanup */ - struct completion nfsd_shutdown_complete; + /* When a listening socket is added to nfsd, keep_active is set + * and this justifies a reference on nfsd_serv. This stops + * nfsd_serv from being freed. When the number of threads is + * set, keep_active is cleared and the reference is dropped. So + * when the last thread exits, the service will be destroyed. + */ + int keep_active; /* * clientid and stateid data for construction of net unique COPY @@ -184,6 +185,17 @@ struct nfsd_net { /* utsname taken from the process that starts the server */ char nfsd_name[UNX_MAXNODENAME+1]; + + struct nfsd_fcache_disposal *fcache_disposal; + + siphash_key_t siphash_key; + + atomic_t nfs4_client_count; + int nfs4_max_clients; + + atomic_t nfsd_courtesy_clients; + struct shrinker nfsd_client_shrinker; + struct work_struct nfsd_shrinker_work; }; /* Simple check to find out if a given net was properly initialized */ @@ -193,6 +205,6 @@ extern void nfsd_netns_free_versions(struct nfsd_net *nn); extern unsigned int nfsd_net_id; -void nfsd_copy_boot_verifier(__be32 verf[2], struct nfsd_net *nn); -void nfsd_reset_boot_verifier(struct nfsd_net *nn); +void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn); +void nfsd_reset_write_verifier(struct nfsd_net *nn); #endif /* __NFSD_NETNS_H__ */ diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 30a1782a03f0..65d4511b7af0 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -111,7 +111,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) if (error) goto out_errno; - fh_lock(fh); + inode_lock(inode); error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, argp->acl_access); @@ -122,7 +122,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) if (error) goto out_drop_lock; - fh_unlock(fh); + inode_unlock(inode); fh_drop_write(fh); @@ -136,7 +136,7 @@ out: return rpc_success; out_drop_lock: - fh_unlock(fh); + inode_unlock(inode); fh_drop_write(fh); out_errno: resp->status = nfserrno(error); @@ -188,51 +188,51 @@ out: * XDR decode functions */ -static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) +static bool +nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_getaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &argp->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) - return 0; + return false; - return 1; + return true; } -static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) +static bool +nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_setaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &argp->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) - return 0; + return false; if (argp->mask & ~NFS_ACL_MASK) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ? &argp->acl_access : NULL)) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ? &argp->acl_default : NULL)) - return 0; + return false; - return 1; + return true; } -static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) +static bool +nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_accessargs *args = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->access) < 0) - return 0; + return false; - return 1; + return true; } /* @@ -240,9 +240,9 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) */ /* GETACL */ -static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) +static bool +nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; struct inode *inode; @@ -270,9 +270,9 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) } /* ACCESS */ -static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) +static bool +nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) @@ -321,6 +321,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, @@ -332,6 +333,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_encode = nfsaclsvc_encode_getaclres, .pc_release = nfsaclsvc_release_getacl, .pc_argsize = sizeof(struct nfsd3_getaclargs), + .pc_argzero = sizeof(struct nfsd3_getaclargs), .pc_ressize = sizeof(struct nfsd3_getaclres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+1+2*(1+ACL), @@ -343,6 +345,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_encode = nfssvc_encode_attrstatres, .pc_release = nfssvc_release_attrstat, .pc_argsize = sizeof(struct nfsd3_setaclargs), + .pc_argzero = sizeof(struct nfsd3_setaclargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, @@ -354,6 +357,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_encode = nfssvc_encode_attrstatres, .pc_release = nfssvc_release_attrstat, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, @@ -365,6 +369,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_encode = nfsaclsvc_encode_accessres, .pc_release = nfsaclsvc_release_access, .pc_argsize = sizeof(struct nfsd3_accessargs), + .pc_argzero = sizeof(struct nfsd3_accessargs), .pc_ressize = sizeof(struct nfsd3_accessres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT+1, diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 5dfe7644a517..a34a22e272ad 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -101,7 +101,7 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) if (error) goto out_errno; - fh_lock(fh); + inode_lock(inode); error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, argp->acl_access); @@ -111,7 +111,7 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) argp->acl_default); out_drop_lock: - fh_unlock(fh); + inode_unlock(inode); fh_drop_write(fh); out_errno: resp->status = nfserrno(error); @@ -127,38 +127,38 @@ out: * XDR decode functions */ -static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) +static bool +nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_getaclargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->mask) < 0) - return 0; + return false; - return 1; + return true; } -static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) +static bool +nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_setaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &argp->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) - return 0; + return false; if (argp->mask & ~NFS_ACL_MASK) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ? &argp->acl_access : NULL)) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ? &argp->acl_default : NULL)) - return 0; + return false; - return 1; + return true; } /* @@ -166,61 +166,43 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) */ /* GETACL */ -static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) +static bool +nfs3svc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; - struct kvec *head = rqstp->rq_res.head; struct inode *inode; - unsigned int base; - int n; - int w; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: inode = d_inode(dentry); if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->mask) < 0) - return 0; - - base = (char *)xdr->p - (char *)head->iov_base; - - rqstp->rq_res.page_len = w = nfsacl_size( - (resp->mask & NFS_ACL) ? resp->acl_access : NULL, - (resp->mask & NFS_DFACL) ? resp->acl_default : NULL); - while (w > 0) { - if (!*(rqstp->rq_next_page++)) - return 0; - w -= PAGE_SIZE; - } - - n = nfsacl_encode(&rqstp->rq_res, base, inode, - resp->acl_access, - resp->mask & NFS_ACL, 0); - if (n > 0) - n = nfsacl_encode(&rqstp->rq_res, base + n, inode, - resp->acl_default, - resp->mask & NFS_DFACL, - NFS_ACL_DEFAULT); - if (n <= 0) - return 0; + return false; + + if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access, + resp->mask & NFS_ACL, 0)) + return false; + if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default, + resp->mask & NFS_DFACL, + NFS_ACL_DEFAULT)) + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* SETACL */ -static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p) +static bool +nfs3svc_encode_setaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_attrstat *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && @@ -252,6 +234,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, @@ -263,6 +246,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { .pc_encode = nfs3svc_encode_getaclres, .pc_release = nfs3svc_release_getacl, .pc_argsize = sizeof(struct nfsd3_getaclargs), + .pc_argzero = sizeof(struct nfsd3_getaclargs), .pc_ressize = sizeof(struct nfsd3_getaclres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+1+2*(1+ACL), @@ -274,6 +258,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { .pc_encode = nfs3svc_encode_setaclres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_setaclargs), + .pc_argzero = sizeof(struct nfsd3_setaclargs), .pc_ressize = sizeof(struct nfsd3_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT, diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index eaf785aec070..d01b29aba662 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -8,10 +8,12 @@ #include <linux/fs.h> #include <linux/ext2_fs.h> #include <linux/magic.h> +#include <linux/namei.h> #include "cache.h" #include "xdr3.h" #include "vfs.h" +#include "filecache.h" #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -66,12 +68,15 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp) { struct nfsd3_sattrargs *argp = rqstp->rq_argp; struct nfsd3_attrstat *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; dprintk("nfsd: SETATTR(3) %s\n", SVCFH_fmt(&argp->fh)); fh_copy(&resp->fh, &argp->fh); - resp->status = nfsd_setattr(rqstp, &resp->fh, &argp->attrs, + resp->status = nfsd_setattr(rqstp, &resp->fh, &attrs, argp->check_guard, argp->guardtime); return rpc_success; } @@ -220,17 +225,137 @@ nfsd3_proc_write(struct svc_rqst *rqstp) } /* - * With NFSv3, CREATE processing is a lot easier than with NFSv2. - * At least in theory; we'll see how it fares in practice when the - * first reports about SunOS compatibility problems start to pour in... + * Implement NFSv3's unchecked, guarded, and exclusive CREATE + * semantics for regular files. Except for the created file, + * this operation is stateless on the server. + * + * Upon return, caller must release @fhp and @resfhp. */ static __be32 +nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct svc_fh *resfhp, struct nfsd3_createargs *argp) +{ + struct iattr *iap = &argp->attrs; + struct dentry *parent, *child; + struct nfsd_attrs attrs = { + .na_iattr = iap, + }; + __u32 v_mtime, v_atime; + struct inode *inode; + __be32 status; + int host_err; + + if (isdotent(argp->name, argp->len)) + return nfserr_exist; + if (!(iap->ia_valid & ATTR_MODE)) + iap->ia_mode = 0; + + status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC); + if (status != nfs_ok) + return status; + + parent = fhp->fh_dentry; + inode = d_inode(parent); + + host_err = fh_want_write(fhp); + if (host_err) + return nfserrno(host_err); + + inode_lock_nested(inode, I_MUTEX_PARENT); + + child = lookup_one_len(argp->name, parent, argp->len); + if (IS_ERR(child)) { + status = nfserrno(PTR_ERR(child)); + goto out; + } + + if (d_really_is_negative(child)) { + status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE); + if (status != nfs_ok) + goto out; + } + + status = fh_compose(resfhp, fhp->fh_export, child, fhp); + if (status != nfs_ok) + goto out; + + v_mtime = 0; + v_atime = 0; + if (argp->createmode == NFS3_CREATE_EXCLUSIVE) { + u32 *verifier = (u32 *)argp->verf; + + /* + * Solaris 7 gets confused (bugid 4218508) if these have + * the high bit set, as do xfs filesystems without the + * "bigtime" feature. So just clear the high bits. + */ + v_mtime = verifier[0] & 0x7fffffff; + v_atime = verifier[1] & 0x7fffffff; + } + + if (d_really_is_positive(child)) { + status = nfs_ok; + + switch (argp->createmode) { + case NFS3_CREATE_UNCHECKED: + if (!d_is_reg(child)) + break; + iap->ia_valid &= ATTR_SIZE; + goto set_attr; + case NFS3_CREATE_GUARDED: + status = nfserr_exist; + break; + case NFS3_CREATE_EXCLUSIVE: + if (d_inode(child)->i_mtime.tv_sec == v_mtime && + d_inode(child)->i_atime.tv_sec == v_atime && + d_inode(child)->i_size == 0) { + break; + } + status = nfserr_exist; + } + goto out; + } + + if (!IS_POSIXACL(inode)) + iap->ia_mode &= ~current_umask(); + + fh_fill_pre_attrs(fhp); + host_err = vfs_create(&init_user_ns, inode, child, iap->ia_mode, true); + if (host_err < 0) { + status = nfserrno(host_err); + goto out; + } + fh_fill_post_attrs(fhp); + + /* A newly created file already has a file size of zero. */ + if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0)) + iap->ia_valid &= ~ATTR_SIZE; + if (argp->createmode == NFS3_CREATE_EXCLUSIVE) { + iap->ia_valid = ATTR_MTIME | ATTR_ATIME | + ATTR_MTIME_SET | ATTR_ATIME_SET; + iap->ia_mtime.tv_sec = v_mtime; + iap->ia_atime.tv_sec = v_atime; + iap->ia_mtime.tv_nsec = 0; + iap->ia_atime.tv_nsec = 0; + } + +set_attr: + status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs); + +out: + inode_unlock(inode); + if (child && !IS_ERR(child)) + dput(child); + fh_drop_write(fhp); + return status; +} + +static __be32 nfsd3_proc_create(struct svc_rqst *rqstp) { struct nfsd3_createargs *argp = rqstp->rq_argp; struct nfsd3_diropres *resp = rqstp->rq_resp; - svc_fh *dirfhp, *newfhp = NULL; - struct iattr *attr; + svc_fh *dirfhp, *newfhp; dprintk("nfsd: CREATE(3) %s %.*s\n", SVCFH_fmt(&argp->fh), @@ -239,21 +364,8 @@ nfsd3_proc_create(struct svc_rqst *rqstp) dirfhp = fh_copy(&resp->dirfh, &argp->fh); newfhp = fh_init(&resp->fh, NFS3_FHSIZE); - attr = &argp->attrs; - - /* Unfudge the mode bits */ - attr->ia_mode &= ~S_IFMT; - if (!(attr->ia_valid & ATTR_MODE)) { - attr->ia_valid |= ATTR_MODE; - attr->ia_mode = S_IFREG; - } else { - attr->ia_mode = (attr->ia_mode & ~S_IFMT) | S_IFREG; - } - /* Now create the file and set attributes */ - resp->status = do_nfsd_create(rqstp, dirfhp, argp->name, argp->len, - attr, newfhp, argp->createmode, - (u32 *)argp->verf, NULL, NULL); + resp->status = nfsd3_create_file(rqstp, dirfhp, newfhp, argp); return rpc_success; } @@ -265,6 +377,9 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp) { struct nfsd3_createargs *argp = rqstp->rq_argp; struct nfsd3_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; dprintk("nfsd: MKDIR(3) %s %.*s\n", SVCFH_fmt(&argp->fh), @@ -275,8 +390,7 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp) fh_copy(&resp->dirfh, &argp->fh); fh_init(&resp->fh, NFS3_FHSIZE); resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, - &argp->attrs, S_IFDIR, 0, &resp->fh); - fh_unlock(&resp->dirfh); + &attrs, S_IFDIR, 0, &resp->fh); return rpc_success; } @@ -285,6 +399,9 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp) { struct nfsd3_symlinkargs *argp = rqstp->rq_argp; struct nfsd3_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; if (argp->tlen == 0) { resp->status = nfserr_inval; @@ -311,7 +428,7 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp) fh_copy(&resp->dirfh, &argp->ffh); fh_init(&resp->fh, NFS3_FHSIZE); resp->status = nfsd_symlink(rqstp, &resp->dirfh, argp->fname, - argp->flen, argp->tname, &resp->fh); + argp->flen, argp->tname, &attrs, &resp->fh); kfree(argp->tname); out: return rpc_success; @@ -325,6 +442,9 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) { struct nfsd3_mknodargs *argp = rqstp->rq_argp; struct nfsd3_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; int type; dev_t rdev = 0; @@ -350,8 +470,7 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) type = nfs3_ftypes[argp->ftype]; resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, - &argp->attrs, type, rdev, &resp->fh); - fh_unlock(&resp->dirfh); + &attrs, type, rdev, &resp->fh); out: return rpc_success; } @@ -374,7 +493,6 @@ nfsd3_proc_remove(struct svc_rqst *rqstp) fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_unlink(rqstp, &resp->fh, -S_IFDIR, argp->name, argp->len); - fh_unlock(&resp->fh); return rpc_success; } @@ -395,7 +513,6 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp) fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_unlink(rqstp, &resp->fh, S_IFDIR, argp->name, argp->len); - fh_unlock(&resp->fh); return rpc_success; } @@ -458,15 +575,7 @@ static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp, buf->pages = rqstp->rq_next_page; rqstp->rq_next_page += (buf->buflen + PAGE_SIZE - 1) >> PAGE_SHIFT; - /* This is xdr_init_encode(), but it assumes that - * the head kvec has already been consumed. */ - xdr_set_scratch_buffer(xdr, NULL, 0); - xdr->buf = buf; - xdr->page_ptr = buf->pages; - xdr->iov = NULL; - xdr->p = page_address(*buf->pages); - xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE); - xdr->rqst = NULL; + xdr_init_encode_pages(xdr, buf, buf->pages, NULL); } /* @@ -655,6 +764,7 @@ nfsd3_proc_commit(struct svc_rqst *rqstp) { struct nfsd3_commitargs *argp = rqstp->rq_argp; struct nfsd3_commitres *resp = rqstp->rq_resp; + struct nfsd_file *nf; dprintk("nfsd: COMMIT(3) %s %u@%Lu\n", SVCFH_fmt(&argp->fh), @@ -662,8 +772,14 @@ nfsd3_proc_commit(struct svc_rqst *rqstp) (unsigned long long) argp->offset); fh_copy(&resp->fh, &argp->fh); - resp->status = nfsd_commit(rqstp, &resp->fh, argp->offset, + resp->status = nfsd_file_acquire_gc(rqstp, &resp->fh, NFSD_MAY_WRITE | + NFSD_MAY_NOT_BREAK_LEASE, &nf); + if (resp->status) + goto out; + resp->status = nfsd_commit(rqstp, &resp->fh, nf, argp->offset, argp->count, resp->verf); + nfsd_file_put(nf); +out: return rpc_success; } @@ -693,6 +809,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, @@ -704,6 +821,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_getattrres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd3_attrstatres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, @@ -715,6 +833,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_sattrargs), + .pc_argzero = sizeof(struct nfsd3_sattrargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, @@ -726,6 +845,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_lookupres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_diropargs), + .pc_argzero = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_diropres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+FH+pAT+pAT, @@ -737,6 +857,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_accessres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_accessargs), + .pc_argzero = sizeof(struct nfsd3_accessargs), .pc_ressize = sizeof(struct nfsd3_accessres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+1, @@ -748,6 +869,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_readlinkres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd3_readlinkres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4, @@ -759,6 +881,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_readres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readargs), + .pc_argzero = sizeof(struct nfsd3_readargs), .pc_ressize = sizeof(struct nfsd3_readres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4, @@ -770,6 +893,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_writeres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_writeargs), + .pc_argzero = sizeof(struct nfsd3_writeargs), .pc_ressize = sizeof(struct nfsd3_writeres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC+4, @@ -781,6 +905,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_createargs), + .pc_argzero = sizeof(struct nfsd3_createargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, @@ -792,6 +917,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mkdirargs), + .pc_argzero = sizeof(struct nfsd3_mkdirargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, @@ -803,6 +929,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_symlinkargs), + .pc_argzero = sizeof(struct nfsd3_symlinkargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, @@ -814,6 +941,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mknodargs), + .pc_argzero = sizeof(struct nfsd3_mknodargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, @@ -825,6 +953,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), + .pc_argzero = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, @@ -836,6 +965,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), + .pc_argzero = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, @@ -847,6 +977,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_renameres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_renameargs), + .pc_argzero = sizeof(struct nfsd3_renameargs), .pc_ressize = sizeof(struct nfsd3_renameres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC+WC, @@ -858,6 +989,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_linkres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_linkargs), + .pc_argzero = sizeof(struct nfsd3_linkargs), .pc_ressize = sizeof(struct nfsd3_linkres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+pAT+WC, @@ -869,6 +1001,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirargs), + .pc_argzero = sizeof(struct nfsd3_readdirargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, .pc_name = "READDIR", @@ -879,6 +1012,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirplusargs), + .pc_argzero = sizeof(struct nfsd3_readdirplusargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, .pc_name = "READDIRPLUS", @@ -888,6 +1022,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = nfs3svc_encode_fsstatres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), + .pc_argzero = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsstatres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+2*6+1, @@ -898,6 +1033,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = nfs3svc_encode_fsinfores, .pc_argsize = sizeof(struct nfsd3_fhandleargs), + .pc_argzero = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsinfores), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+12, @@ -908,6 +1044,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = nfs3svc_encode_pathconfres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), + .pc_argzero = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_pathconfres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+6, @@ -919,6 +1056,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_encode = nfs3svc_encode_commitres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_commitargs), + .pc_argzero = sizeof(struct nfsd3_commitargs), .pc_ressize = sizeof(struct nfsd3_commitres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+WC+2, diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 48d4f99b7f90..3308dd671ef0 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -92,7 +92,7 @@ svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp) return false; fh_init(fhp, NFS3_FHSIZE); fhp->fh_handle.fh_size = size; - memcpy(&fhp->fh_handle.fh_base, p, size); + memcpy(&fhp->fh_handle.fh_raw, p, size); return true; } @@ -131,7 +131,7 @@ svcxdr_encode_nfs_fh3(struct xdr_stream *xdr, const struct svc_fh *fhp) *p++ = cpu_to_be32(size); if (size) p[XDR_QUADLEN(size) - 1] = 0; - memcpy(p, &fhp->fh_handle.fh_base, size); + memcpy(p, &fhp->fh_handle.fh_raw, size); return true; } @@ -488,77 +488,20 @@ neither: } /* - * Fill in the pre_op attr for the wcc data - */ -void fill_pre_wcc(struct svc_fh *fhp) -{ - struct inode *inode; - struct kstat stat; - bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); - __be32 err; - - if (fhp->fh_no_wcc || fhp->fh_pre_saved) - return; - inode = d_inode(fhp->fh_dentry); - err = fh_getattr(fhp, &stat); - if (err) { - /* Grab the times from inode anyway */ - stat.mtime = inode->i_mtime; - stat.ctime = inode->i_ctime; - stat.size = inode->i_size; - } - if (v4) - fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); - - fhp->fh_pre_mtime = stat.mtime; - fhp->fh_pre_ctime = stat.ctime; - fhp->fh_pre_size = stat.size; - fhp->fh_pre_saved = true; -} - -/* - * Fill in the post_op attr for the wcc data - */ -void fill_post_wcc(struct svc_fh *fhp) -{ - bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); - struct inode *inode = d_inode(fhp->fh_dentry); - __be32 err; - - if (fhp->fh_no_wcc) - return; - - if (fhp->fh_post_saved) - printk("nfsd: inode locked twice during operation.\n"); - - err = fh_getattr(fhp, &fhp->fh_post_attr); - if (err) { - fhp->fh_post_saved = false; - fhp->fh_post_attr.ctime = inode->i_ctime; - } else - fhp->fh_post_saved = true; - if (v4) - fhp->fh_post_change = - nfsd4_change_attribute(&fhp->fh_post_attr, inode); -} - -/* * XDR decode functions */ -int -nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_fhandle *args = rqstp->rq_argp; return svcxdr_decode_nfs_fh3(xdr, &args->fh); } -int -nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_sattrargs *args = rqstp->rq_argp; return svcxdr_decode_nfs_fh3(xdr, &args->fh) && @@ -566,88 +509,81 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) svcxdr_decode_sattrguard3(xdr, args); } -int -nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_diropargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len); } -int -nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_accessargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->access) < 0) - return 0; + return false; - return 1; + return true; } -int -nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } -int -nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_writeargs *args = rqstp->rq_argp; u32 max_blocksize = svc_max_payload(rqstp); if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->stable) < 0) - return 0; + return false; /* opaque data */ if (xdr_stream_decode_u32(xdr, &args->len) < 0) - return 0; + return false; /* request sanity */ if (args->count != args->len) - return 0; + return false; if (args->count > max_blocksize) { args->count = max_blocksize; args->len = max_blocksize; } - if (!xdr_stream_subsegment(xdr, &args->payload, args->count)) - return 0; - return 1; + return xdr_stream_subsegment(xdr, &args->payload, args->count); } -int -nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_createargs *args = rqstp->rq_argp; if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->createmode) < 0) - return 0; + return false; switch (args->createmode) { case NFS3_CREATE_UNCHECKED: case NFS3_CREATE_GUARDED: @@ -655,18 +591,17 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) case NFS3_CREATE_EXCLUSIVE: args->verf = xdr_inline_decode(xdr, NFS3_CREATEVERFSIZE); if (!args->verf) - return 0; + return false; break; default: - return 0; + return false; } - return 1; + return true; } -int -nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_createargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs3(xdr, &args->fh, @@ -674,44 +609,34 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) svcxdr_decode_sattr3(rqstp, xdr, &args->attrs); } -int -nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_symlinkargs *args = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; - struct kvec *tail = rqstp->rq_arg.tail; - size_t remaining; if (!svcxdr_decode_diropargs3(xdr, &args->ffh, &args->fname, &args->flen)) - return 0; + return false; if (!svcxdr_decode_sattr3(rqstp, xdr, &args->attrs)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->tlen) < 0) - return 0; - - /* request sanity */ - remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len; - remaining -= xdr_stream_pos(xdr); - if (remaining < xdr_align_size(args->tlen)) - return 0; + return false; - args->first.iov_base = xdr->p; + /* symlink_data */ args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); - - return 1; + args->first.iov_base = xdr_inline_decode(xdr, args->tlen); + return args->first.iov_base != NULL; } -int -nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_mknodargs *args = rqstp->rq_argp; if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->ftype) < 0) - return 0; + return false; switch (args->ftype) { case NF3CHR: case NF3BLK: @@ -725,16 +650,15 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) /* Valid XDR but illegal file types */ break; default: - return 0; + return false; } - return 1; + return true; } -int -nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_renameargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs3(xdr, &args->ffh, @@ -743,10 +667,9 @@ nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) &args->tname, &args->tlen); } -int -nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_linkargs *args = rqstp->rq_argp; return svcxdr_decode_nfs_fh3(xdr, &args->ffh) && @@ -754,62 +677,59 @@ nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) &args->tname, &args->tlen); } -int -nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readdirargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->cookie) < 0) - return 0; + return false; args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE); if (!args->verf) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } -int -nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readdirargs *args = rqstp->rq_argp; u32 dircount; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->cookie) < 0) - return 0; + return false; args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE); if (!args->verf) - return 0; + return false; /* dircount is ignored */ if (xdr_stream_decode_u32(xdr, &dircount) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } -int -nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_commitargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } /* @@ -817,30 +737,28 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p) */ /* GETATTR */ -int -nfs3svc_encode_getattrres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_attrstat *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: lease_get_mtime(d_inode(resp->fh.fh_dentry), &resp->stat.mtime); if (!svcxdr_encode_fattr3(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; break; } - return 1; + return true; } /* SETATTR, REMOVE, RMDIR */ -int -nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_attrstat *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && @@ -848,174 +766,168 @@ nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p) } /* LOOKUP */ -int nfs3svc_encode_lookupres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_nfs_fh3(xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh)) - return 0; + return false; } - return 1; + return true; } /* ACCESS */ -int -nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->access) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* READLINK */ -int -nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_readlinkres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->len) < 0) - return 0; + return false; xdr_write_pages(xdr, resp->pages, 0, resp->len); if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* READ */ -int -nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_readres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; if (xdr_stream_encode_bool(xdr, resp->eof) < 0) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base, resp->count); if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* WRITE */ -int -nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_writeres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->committed) < 0) - return 0; + return false; if (!svcxdr_encode_writeverf3(xdr, resp->verf)) - return 0; + return false; break; default: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* CREATE, MKDIR, SYMLINK, MKNOD */ -int -nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_fh3(xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh)) - return 0; + return false; break; default: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh)) - return 0; + return false; } - return 1; + return true; } /* RENAME */ -int -nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_renameres *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && @@ -1024,10 +936,9 @@ nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p) } /* LINK */ -int -nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_linkres *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && @@ -1036,34 +947,33 @@ nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p) } /* READDIR */ -int -nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_readdirres *resp = rqstp->rq_resp; struct xdr_buf *dirlist = &resp->dirlist; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_cookieverf3(xdr, resp->verf)) - return 0; + return false; xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len); /* no more entries */ if (xdr_stream_encode_item_absent(xdr) < 0) - return 0; + return false; if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } static __be32 @@ -1140,7 +1050,7 @@ svcxdr_encode_entry3_common(struct nfsd3_readdirres *resp, const char *name, return false; /* cookie */ resp->cookie_offset = dirlist->len; - if (xdr_stream_encode_u64(xdr, NFS_OFFSET_MAX) < 0) + if (xdr_stream_encode_u64(xdr, OFFSET_MAX) < 0) return false; return true; @@ -1290,27 +1200,26 @@ svcxdr_encode_fsstat3resok(struct xdr_stream *xdr, } /* FSSTAT */ -int -nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_fsstatres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; if (!svcxdr_encode_fsstat3resok(xdr, resp)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; } - return 1; + return true; } static bool @@ -1337,27 +1246,26 @@ svcxdr_encode_fsinfo3resok(struct xdr_stream *xdr, } /* FSINFO */ -int -nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_fsinfores *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; if (!svcxdr_encode_fsinfo3resok(xdr, resp)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; } - return 1; + return true; } static bool @@ -1380,51 +1288,49 @@ svcxdr_encode_pathconf3resok(struct xdr_stream *xdr, } /* PATHCONF */ -int -nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_pathconfres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; if (!svcxdr_encode_pathconf3resok(xdr, resp)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; } - return 1; + return true; } /* COMMIT */ -int -nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_commitres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_writeverf3(xdr, resp->verf)) - return 0; + return false; break; default: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index eaa3a0cf38f1..bb8e2f6d7d03 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -751,58 +751,26 @@ out_estate: return ret; } -__be32 -nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct nfs4_acl *acl) +__be32 nfsd4_acl_to_attr(enum nfs_ftype4 type, struct nfs4_acl *acl, + struct nfsd_attrs *attr) { - __be32 error; int host_error; - struct dentry *dentry; - struct inode *inode; - struct posix_acl *pacl = NULL, *dpacl = NULL; unsigned int flags = 0; - /* Get inode */ - error = fh_verify(rqstp, fhp, 0, NFSD_MAY_SATTR); - if (error) - return error; - - dentry = fhp->fh_dentry; - inode = d_inode(dentry); + if (!acl) + return nfs_ok; - if (S_ISDIR(inode->i_mode)) + if (type == NF4DIR) flags = NFS4_ACL_DIR; - host_error = nfs4_acl_nfsv4_to_posix(acl, &pacl, &dpacl, flags); + host_error = nfs4_acl_nfsv4_to_posix(acl, &attr->na_pacl, + &attr->na_dpacl, flags); if (host_error == -EINVAL) return nfserr_attrnotsupp; - if (host_error < 0) - goto out_nfserr; - - fh_lock(fhp); - - host_error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, pacl); - if (host_error < 0) - goto out_drop_lock; - - if (S_ISDIR(inode->i_mode)) { - host_error = set_posix_acl(&init_user_ns, inode, - ACL_TYPE_DEFAULT, dpacl); - } - -out_drop_lock: - fh_unlock(fhp); - - posix_acl_release(pacl); - posix_acl_release(dpacl); -out_nfserr: - if (host_error == -EOPNOTSUPP) - return nfserr_attrnotsupp; else return nfserrno(host_error); } - static short ace2type(struct nfs4_ace *ace) { diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 97f517e9b418..4eae2c5af2ed 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -76,6 +76,17 @@ static __be32 *xdr_encode_empty_array(__be32 *p) * 1 Protocol" */ +static void encode_uint32(struct xdr_stream *xdr, u32 n) +{ + WARN_ON_ONCE(xdr_stream_encode_u32(xdr, n) < 0); +} + +static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap, + size_t len) +{ + WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0); +} + /* * nfs_cb_opnum4 * @@ -121,7 +132,7 @@ static void encode_nfs_fh4(struct xdr_stream *xdr, const struct knfsd_fh *fh) BUG_ON(length > NFS4_FHSIZE); p = xdr_reserve_space(xdr, 4 + length); - xdr_encode_opaque(p, &fh->fh_base, length); + xdr_encode_opaque(p, &fh->fh_raw, length); } /* @@ -329,6 +340,24 @@ static void encode_cb_recall4args(struct xdr_stream *xdr, } /* + * CB_RECALLANY4args + * + * struct CB_RECALLANY4args { + * uint32_t craa_objects_to_keep; + * bitmap4 craa_type_mask; + * }; + */ +static void +encode_cb_recallany4args(struct xdr_stream *xdr, + struct nfs4_cb_compound_hdr *hdr, struct nfsd4_cb_recall_any *ra) +{ + encode_nfs_cb_opnum4(xdr, OP_CB_RECALL_ANY); + encode_uint32(xdr, ra->ra_keep); + encode_bitmap4(xdr, ra->ra_bmval, ARRAY_SIZE(ra->ra_bmval)); + hdr->nops++; +} + +/* * CB_SEQUENCE4args * * struct CB_SEQUENCE4args { @@ -482,6 +511,26 @@ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr, encode_cb_nops(&hdr); } +/* + * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects + */ +static void +nfs4_xdr_enc_cb_recall_any(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ + const struct nfsd4_callback *cb = data; + struct nfsd4_cb_recall_any *ra; + struct nfs4_cb_compound_hdr hdr = { + .ident = cb->cb_clp->cl_cb_ident, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + ra = container_of(cb, struct nfsd4_cb_recall_any, ra_cb); + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_recallany4args(xdr, &hdr, ra); + encode_cb_nops(&hdr); +} /* * NFSv4.0 and NFSv4.1 XDR decode functions @@ -520,6 +569,28 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, return decode_cb_op_status(xdr, OP_CB_RECALL, &cb->cb_status); } +/* + * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects + */ +static int +nfs4_xdr_dec_cb_recall_any(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + return status; + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + status = decode_cb_op_status(xdr, OP_CB_RECALL_ANY, &cb->cb_status); + return status; +} + #ifdef CONFIG_NFSD_PNFS /* * CB_LAYOUTRECALL4args @@ -679,7 +750,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, * case NFS4_OK: * write_response4 coa_resok4; * default: - * length4 coa_bytes_copied; + * length4 coa_bytes_copied; * }; * struct CB_OFFLOAD4args { * nfs_fh4 coa_fh; @@ -688,21 +759,22 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, * }; */ static void encode_offload_info4(struct xdr_stream *xdr, - __be32 nfserr, - const struct nfsd4_copy *cp) + const struct nfsd4_cb_offload *cbo) { __be32 *p; p = xdr_reserve_space(xdr, 4); - *p++ = nfserr; - if (!nfserr) { + *p = cbo->co_nfserr; + switch (cbo->co_nfserr) { + case nfs_ok: p = xdr_reserve_space(xdr, 4 + 8 + 4 + NFS4_VERIFIER_SIZE); p = xdr_encode_empty_array(p); - p = xdr_encode_hyper(p, cp->cp_res.wr_bytes_written); - *p++ = cpu_to_be32(cp->cp_res.wr_stable_how); - p = xdr_encode_opaque_fixed(p, cp->cp_res.wr_verifier.data, + p = xdr_encode_hyper(p, cbo->co_res.wr_bytes_written); + *p++ = cpu_to_be32(cbo->co_res.wr_stable_how); + p = xdr_encode_opaque_fixed(p, cbo->co_res.wr_verifier.data, NFS4_VERIFIER_SIZE); - } else { + break; + default: p = xdr_reserve_space(xdr, 8); /* We always return success if bytes were written */ p = xdr_encode_hyper(p, 0); @@ -710,18 +782,16 @@ static void encode_offload_info4(struct xdr_stream *xdr, } static void encode_cb_offload4args(struct xdr_stream *xdr, - __be32 nfserr, - const struct knfsd_fh *fh, - const struct nfsd4_copy *cp, + const struct nfsd4_cb_offload *cbo, struct nfs4_cb_compound_hdr *hdr) { __be32 *p; p = xdr_reserve_space(xdr, 4); - *p++ = cpu_to_be32(OP_CB_OFFLOAD); - encode_nfs_fh4(xdr, fh); - encode_stateid4(xdr, &cp->cp_res.cb_stateid); - encode_offload_info4(xdr, nfserr, cp); + *p = cpu_to_be32(OP_CB_OFFLOAD); + encode_nfs_fh4(xdr, &cbo->co_fh); + encode_stateid4(xdr, &cbo->co_res.cb_stateid); + encode_offload_info4(xdr, cbo); hdr->nops++; } @@ -731,8 +801,8 @@ static void nfs4_xdr_enc_cb_offload(struct rpc_rqst *req, const void *data) { const struct nfsd4_callback *cb = data; - const struct nfsd4_copy *cp = - container_of(cb, struct nfsd4_copy, cp_cb); + const struct nfsd4_cb_offload *cbo = + container_of(cb, struct nfsd4_cb_offload, co_cb); struct nfs4_cb_compound_hdr hdr = { .ident = 0, .minorversion = cb->cb_clp->cl_minorversion, @@ -740,7 +810,7 @@ static void nfs4_xdr_enc_cb_offload(struct rpc_rqst *req, encode_cb_compound4args(xdr, &hdr); encode_cb_sequence4args(xdr, cb, &hdr); - encode_cb_offload4args(xdr, cp->nfserr, &cp->fh, cp, &hdr); + encode_cb_offload4args(xdr, cbo, &hdr); encode_cb_nops(&hdr); } @@ -784,6 +854,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = { #endif PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), PROC(CB_OFFLOAD, COMPOUND, cb_offload, cb_offload), + PROC(CB_RECALL_ANY, COMPOUND, cb_recall_any, cb_recall_any), }; static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; @@ -1374,11 +1445,21 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_holds_slot = false; } -void nfsd4_run_cb(struct nfsd4_callback *cb) +/** + * nfsd4_run_cb - queue up a callback job to run + * @cb: callback to queue + * + * Kick off a callback to do its thing. Returns false if it was already + * on a queue, true otherwise. + */ +bool nfsd4_run_cb(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; + bool queued; nfsd41_cb_inflight_begin(clp); - if (!nfsd4_queue_cb(cb)) + queued = nfsd4_queue_cb(cb); + if (!queued) nfsd41_cb_inflight_end(clp); + return queued; } diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index f92161ce1f97..5e9809aff37e 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -41,6 +41,7 @@ #include "idmap.h" #include "nfsd.h" #include "netns.h" +#include "vfs.h" /* * Turn off idmapping when using AUTH_SYS. @@ -82,8 +83,8 @@ ent_init(struct cache_head *cnew, struct cache_head *citm) new->id = itm->id; new->type = itm->type; - strlcpy(new->name, itm->name, sizeof(new->name)); - strlcpy(new->authname, itm->authname, sizeof(new->authname)); + strscpy(new->name, itm->name, sizeof(new->name)); + strscpy(new->authname, itm->authname, sizeof(new->authname)); } static void @@ -548,7 +549,7 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen return nfserr_badowner; memcpy(key.name, name, namelen); key.name[namelen] = '\0'; - strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); + strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); ret = idmap_lookup(rqstp, nametoid_lookup, &key, nn->nametoid_cache, &item); if (ret == -ENOENT) return nfserr_badowner; @@ -584,7 +585,7 @@ static __be32 idmap_id_to_name(struct xdr_stream *xdr, int ret; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); + strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item); if (ret == -ENOENT) return encode_ascii_id(xdr, id); diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 2673019d30ec..e4e23b2a3e65 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -421,7 +421,7 @@ nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls) new = kmem_cache_alloc(nfs4_layout_cache, GFP_KERNEL); if (!new) return nfserr_jukebox; - memcpy(&new->lo_seg, seg, sizeof(lp->lo_seg)); + memcpy(&new->lo_seg, seg, sizeof(new->lo_seg)); new->lo_state = ls; spin_lock(&fp->fi_lock); @@ -657,7 +657,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) ktime_t now, cutoff; const struct nfsd4_layout_ops *ops; - + trace_nfsd_cb_layout_done(&ls->ls_stid.sc_stateid, task); switch (task->tk_status) { case 0: case -NFS4ERR_DELAY: diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f71af990e1e8..c14f5ac1484c 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -37,6 +37,8 @@ #include <linux/falloc.h> #include <linux/slab.h> #include <linux/kthread.h> +#include <linux/namei.h> + #include <linux/sunrpc/addr.h> #include <linux/nfs_ssc.h> @@ -62,36 +64,6 @@ MODULE_PARM_DESC(nfsd4_ssc_umount_timeout, "idle msecs before unmount export from source server"); #endif -#ifdef CONFIG_NFSD_V4_SECURITY_LABEL -#include <linux/security.h> - -static inline void -nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval) -{ - struct inode *inode = d_inode(resfh->fh_dentry); - int status; - - inode_lock(inode); - status = security_inode_setsecctx(resfh->fh_dentry, - label->data, label->len); - inode_unlock(inode); - - if (status) - /* - * XXX: We should really fail the whole open, but we may - * already have created a new file, so it may be too - * late. For now this seems the least of evils: - */ - bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL; - - return; -} -#else -static inline void -nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval) -{ } -#endif - #define NFSDDBG_FACILITY NFSDDBG_PROC static u32 nfsd_attrmask[] = { @@ -156,26 +128,6 @@ is_create_with_attrs(struct nfsd4_open *open) || open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1); } -/* - * if error occurs when setting the acl, just clear the acl bit - * in the returned attr bitmap. - */ -static void -do_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct nfs4_acl *acl, u32 *bmval) -{ - __be32 status; - - status = nfsd4_set_nfs4_acl(rqstp, fhp, acl); - if (status) - /* - * We should probably fail the whole open at this point, - * but we've already created the file, so it's too late; - * So this seems the least of evils: - */ - bmval[0] &= ~FATTR4_WORD0_ACL; -} - static inline void fh_dup2(struct svc_fh *dst, struct svc_fh *src) { @@ -189,7 +141,6 @@ fh_dup2(struct svc_fh *dst, struct svc_fh *src) static __be32 do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open, int accmode) { - __be32 status; if (open->op_truncate && !(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) @@ -204,9 +155,7 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs if (open->op_share_deny & NFS4_SHARE_DENY_READ) accmode |= NFSD_MAY_WRITE; - status = fh_verify(rqstp, current_fh, S_IFREG, accmode); - - return status; + return fh_verify(rqstp, current_fh, S_IFREG, accmode); } static __be32 nfsd_check_obj_isreg(struct svc_fh *fh) @@ -235,6 +184,202 @@ static void nfsd4_set_open_owner_reply_cache(struct nfsd4_compound_state *cstate &resfh->fh_handle); } +static inline bool nfsd4_create_is_exclusive(int createmode) +{ + return createmode == NFS4_CREATE_EXCLUSIVE || + createmode == NFS4_CREATE_EXCLUSIVE4_1; +} + +static __be32 +nfsd4_vfs_create(struct svc_fh *fhp, struct dentry *child, + struct nfsd4_open *open) +{ + struct file *filp; + struct path path; + int oflags; + + oflags = O_CREAT | O_LARGEFILE; + switch (open->op_share_access & NFS4_SHARE_ACCESS_BOTH) { + case NFS4_SHARE_ACCESS_WRITE: + oflags |= O_WRONLY; + break; + case NFS4_SHARE_ACCESS_BOTH: + oflags |= O_RDWR; + break; + default: + oflags |= O_RDONLY; + } + + path.mnt = fhp->fh_export->ex_path.mnt; + path.dentry = child; + filp = dentry_create(&path, oflags, open->op_iattr.ia_mode, + current_cred()); + if (IS_ERR(filp)) + return nfserrno(PTR_ERR(filp)); + + open->op_filp = filp; + return nfs_ok; +} + +/* + * Implement NFSv4's unchecked, guarded, and exclusive create + * semantics for regular files. Open state for this new file is + * subsequently fabricated in nfsd4_process_open2(). + * + * Upon return, caller must release @fhp and @resfhp. + */ +static __be32 +nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct svc_fh *resfhp, struct nfsd4_open *open) +{ + struct iattr *iap = &open->op_iattr; + struct nfsd_attrs attrs = { + .na_iattr = iap, + .na_seclabel = &open->op_label, + }; + struct dentry *parent, *child; + __u32 v_mtime, v_atime; + struct inode *inode; + __be32 status; + int host_err; + + if (isdotent(open->op_fname, open->op_fnamelen)) + return nfserr_exist; + if (!(iap->ia_valid & ATTR_MODE)) + iap->ia_mode = 0; + + status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC); + if (status != nfs_ok) + return status; + parent = fhp->fh_dentry; + inode = d_inode(parent); + + host_err = fh_want_write(fhp); + if (host_err) + return nfserrno(host_err); + + if (is_create_with_attrs(open)) + nfsd4_acl_to_attr(NF4REG, open->op_acl, &attrs); + + inode_lock_nested(inode, I_MUTEX_PARENT); + + child = lookup_one_len(open->op_fname, parent, open->op_fnamelen); + if (IS_ERR(child)) { + status = nfserrno(PTR_ERR(child)); + goto out; + } + + if (d_really_is_negative(child)) { + status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE); + if (status != nfs_ok) + goto out; + } + + status = fh_compose(resfhp, fhp->fh_export, child, fhp); + if (status != nfs_ok) + goto out; + + v_mtime = 0; + v_atime = 0; + if (nfsd4_create_is_exclusive(open->op_createmode)) { + u32 *verifier = (u32 *)open->op_verf.data; + + /* + * Solaris 7 gets confused (bugid 4218508) if these have + * the high bit set, as do xfs filesystems without the + * "bigtime" feature. So just clear the high bits. If this + * is ever changed to use different attrs for storing the + * verifier, then do_open_lookup() will also need to be + * fixed accordingly. + */ + v_mtime = verifier[0] & 0x7fffffff; + v_atime = verifier[1] & 0x7fffffff; + } + + if (d_really_is_positive(child)) { + status = nfs_ok; + + /* NFSv4 protocol requires change attributes even though + * no change happened. + */ + fh_fill_both_attrs(fhp); + + switch (open->op_createmode) { + case NFS4_CREATE_UNCHECKED: + if (!d_is_reg(child)) + break; + + /* + * In NFSv4, we don't want to truncate the file + * now. This would be wrong if the OPEN fails for + * some other reason. Furthermore, if the size is + * nonzero, we should ignore it according to spec! + */ + open->op_truncate = (iap->ia_valid & ATTR_SIZE) && + !iap->ia_size; + break; + case NFS4_CREATE_GUARDED: + status = nfserr_exist; + break; + case NFS4_CREATE_EXCLUSIVE: + if (d_inode(child)->i_mtime.tv_sec == v_mtime && + d_inode(child)->i_atime.tv_sec == v_atime && + d_inode(child)->i_size == 0) { + open->op_created = true; + break; /* subtle */ + } + status = nfserr_exist; + break; + case NFS4_CREATE_EXCLUSIVE4_1: + if (d_inode(child)->i_mtime.tv_sec == v_mtime && + d_inode(child)->i_atime.tv_sec == v_atime && + d_inode(child)->i_size == 0) { + open->op_created = true; + goto set_attr; /* subtle */ + } + status = nfserr_exist; + } + goto out; + } + + if (!IS_POSIXACL(inode)) + iap->ia_mode &= ~current_umask(); + + fh_fill_pre_attrs(fhp); + status = nfsd4_vfs_create(fhp, child, open); + if (status != nfs_ok) + goto out; + open->op_created = true; + fh_fill_post_attrs(fhp); + + /* A newly created file already has a file size of zero. */ + if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0)) + iap->ia_valid &= ~ATTR_SIZE; + if (nfsd4_create_is_exclusive(open->op_createmode)) { + iap->ia_valid = ATTR_MTIME | ATTR_ATIME | + ATTR_MTIME_SET|ATTR_ATIME_SET; + iap->ia_mtime.tv_sec = v_mtime; + iap->ia_atime.tv_sec = v_atime; + iap->ia_mtime.tv_nsec = 0; + iap->ia_atime.tv_nsec = 0; + } + +set_attr: + status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs); + + if (attrs.na_labelerr) + open->op_bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + if (attrs.na_aclerr) + open->op_bmval[0] &= ~FATTR4_WORD0_ACL; +out: + inode_unlock(inode); + nfsd_attrs_free(&attrs); + if (child && !IS_ERR(child)) + dput(child); + fh_drop_write(fhp); + return status; +} + static __be32 do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh **resfh) { @@ -264,47 +409,33 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru * yes | yes | GUARDED4 | GUARDED4 */ - /* - * Note: create modes (UNCHECKED,GUARDED...) are the same - * in NFSv4 as in v3 except EXCLUSIVE4_1. - */ current->fs->umask = open->op_umask; - status = do_nfsd_create(rqstp, current_fh, open->op_fname, - open->op_fnamelen, &open->op_iattr, - *resfh, open->op_createmode, - (u32 *)open->op_verf.data, - &open->op_truncate, &open->op_created); + status = nfsd4_create_file(rqstp, current_fh, *resfh, open); current->fs->umask = 0; - if (!status && open->op_label.len) - nfsd4_security_inode_setsecctx(*resfh, &open->op_label, open->op_bmval); - /* * Following rfc 3530 14.2.16, and rfc 5661 18.16.4 * use the returned bitmask to indicate which attributes * we used to store the verifier: */ - if (nfsd_create_is_exclusive(open->op_createmode) && status == 0) + if (nfsd4_create_is_exclusive(open->op_createmode) && status == 0) open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS | FATTR4_WORD1_TIME_MODIFY); - } else - /* - * Note this may exit with the parent still locked. - * We will hold the lock until nfsd4_open's final - * lookup, to prevent renames or unlinks until we've had - * a chance to an acquire a delegation if appropriate. - */ + } else { status = nfsd_lookup(rqstp, current_fh, open->op_fname, open->op_fnamelen, *resfh); + if (!status) + /* NFSv4 protocol requires change attributes even though + * no change happened. + */ + fh_fill_both_attrs(current_fh); + } if (status) goto out; status = nfsd_check_obj_isreg(*resfh); if (status) goto out; - if (is_create_with_attrs(open) && open->op_acl != NULL) - do_set_nfs4_acl(rqstp, *resfh, open->op_acl, open->op_bmval); - nfsd4_set_open_owner_reply_cache(cstate, open, *resfh); accmode = NFSD_MAY_NOP; if (open->op_created || @@ -320,7 +451,6 @@ static __be32 do_open_fhandle(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open) { struct svc_fh *current_fh = &cstate->current_fh; - __be32 status; int accmode = 0; /* We don't know the target directory, and therefore can not @@ -345,9 +475,7 @@ do_open_fhandle(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, str if (open->op_claim_type == NFS4_OPEN_CLAIM_DELEG_CUR_FH) accmode = NFSD_MAY_OWNER_OVERRIDE; - status = do_open_permission(rqstp, current_fh, open, accmode); - - return status; + return do_open_permission(rqstp, current_fh, open, accmode); } static void @@ -375,6 +503,9 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, (int)open->op_fnamelen, open->op_fname, open->op_openowner); + open->op_filp = NULL; + open->op_rqstp = rqstp; + /* This check required by spec. */ if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL) return nfserr_inval; @@ -427,50 +558,46 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; switch (open->op_claim_type) { - case NFS4_OPEN_CLAIM_DELEGATE_CUR: - case NFS4_OPEN_CLAIM_NULL: - status = do_open_lookup(rqstp, cstate, open, &resfh); - if (status) - goto out; - break; - case NFS4_OPEN_CLAIM_PREVIOUS: - status = nfs4_check_open_reclaim(cstate->clp); - if (status) - goto out; - open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; - reclaim = true; - fallthrough; - case NFS4_OPEN_CLAIM_FH: - case NFS4_OPEN_CLAIM_DELEG_CUR_FH: - status = do_open_fhandle(rqstp, cstate, open); - if (status) - goto out; - resfh = &cstate->current_fh; - break; - case NFS4_OPEN_CLAIM_DELEG_PREV_FH: - case NFS4_OPEN_CLAIM_DELEGATE_PREV: - dprintk("NFSD: unsupported OPEN claim type %d\n", - open->op_claim_type); - status = nfserr_notsupp; + case NFS4_OPEN_CLAIM_DELEGATE_CUR: + case NFS4_OPEN_CLAIM_NULL: + status = do_open_lookup(rqstp, cstate, open, &resfh); + if (status) goto out; - default: - dprintk("NFSD: Invalid OPEN claim type %d\n", - open->op_claim_type); - status = nfserr_inval; + break; + case NFS4_OPEN_CLAIM_PREVIOUS: + status = nfs4_check_open_reclaim(cstate->clp); + if (status) goto out; + open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; + reclaim = true; + fallthrough; + case NFS4_OPEN_CLAIM_FH: + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: + status = do_open_fhandle(rqstp, cstate, open); + if (status) + goto out; + resfh = &cstate->current_fh; + break; + case NFS4_OPEN_CLAIM_DELEG_PREV_FH: + case NFS4_OPEN_CLAIM_DELEGATE_PREV: + status = nfserr_notsupp; + goto out; + default: + status = nfserr_inval; + goto out; } - /* - * nfsd4_process_open2() does the actual opening of the file. If - * successful, it (1) truncates the file if open->op_truncate was - * set, (2) sets open->op_stateid, (3) sets open->op_delegation. - */ + status = nfsd4_process_open2(rqstp, resfh, open); - WARN(status && open->op_created, - "nfsd4_process_open2 failed to open newly-created file! status=%u\n", - be32_to_cpu(status)); + if (status && open->op_created) + pr_warn("nfsd4_process_open2 failed to open newly-created file: status=%u\n", + be32_to_cpu(status)); if (reclaim && !status) nn->somebody_reclaimed = true; out: + if (open->op_filp) { + fput(open->op_filp); + open->op_filp = NULL; + } if (resfh && resfh != &cstate->current_fh) { fh_dup2(&cstate->current_fh, resfh); fh_put(resfh); @@ -519,7 +646,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fh_put(&cstate->current_fh); cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen; - memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval, + memcpy(&cstate->current_fh.fh_handle.fh_raw, putfh->pf_fhval, putfh->pf_fhlen); ret = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS); #ifdef CONFIG_NFSD_V4_2_INTER_SSC @@ -535,11 +662,9 @@ static __be32 nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { - __be32 status; - fh_put(&cstate->current_fh); - status = exp_pseudoroot(rqstp, &cstate->current_fh); - return status; + + return exp_pseudoroot(rqstp, &cstate->current_fh); } static __be32 @@ -598,7 +723,7 @@ static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net) BUILD_BUG_ON(2*sizeof(*verf) != sizeof(verifier->data)); - nfsd_copy_boot_verifier(verf, net_generic(net, nfsd_net_id)); + nfsd_copy_write_verifier(verf, net_generic(net, nfsd_net_id)); } static __be32 @@ -606,10 +731,19 @@ nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_commit *commit = &u->commit; + struct nfsd_file *nf; + __be32 status; + + status = nfsd_file_acquire(rqstp, &cstate->current_fh, NFSD_MAY_WRITE | + NFSD_MAY_NOT_BREAK_LEASE, &nf); + if (status != nfs_ok) + return status; - return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset, + status = nfsd_commit(rqstp, &cstate->current_fh, nf, commit->co_offset, commit->co_count, (__be32 *)commit->co_verf.data); + nfsd_file_put(nf); + return status; } static __be32 @@ -617,6 +751,10 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_create *create = &u->create; + struct nfsd_attrs attrs = { + .na_iattr = &create->cr_iattr, + .na_seclabel = &create->cr_label, + }; struct svc_fh resfh; __be32 status; dev_t rdev; @@ -632,12 +770,13 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) return status; + status = nfsd4_acl_to_attr(create->cr_type, create->cr_acl, &attrs); current->fs->umask = create->cr_umask; switch (create->cr_type) { case NF4LNK: status = nfsd_symlink(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - create->cr_data, &resfh); + create->cr_data, &attrs, &resfh); break; case NF4BLK: @@ -648,7 +787,7 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out_umask; status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFBLK, rdev, &resfh); + &attrs, S_IFBLK, rdev, &resfh); break; case NF4CHR: @@ -659,26 +798,26 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out_umask; status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr,S_IFCHR, rdev, &resfh); + &attrs, S_IFCHR, rdev, &resfh); break; case NF4SOCK: status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFSOCK, 0, &resfh); + &attrs, S_IFSOCK, 0, &resfh); break; case NF4FIFO: status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFIFO, 0, &resfh); + &attrs, S_IFIFO, 0, &resfh); break; case NF4DIR: create->cr_iattr.ia_valid &= ~ATTR_SIZE; status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFDIR, 0, &resfh); + &attrs, S_IFDIR, 0, &resfh); break; default: @@ -688,20 +827,17 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - if (create->cr_label.len) - nfsd4_security_inode_setsecctx(&resfh, &create->cr_label, create->cr_bmval); - - if (create->cr_acl != NULL) - do_set_nfs4_acl(rqstp, &resfh, create->cr_acl, - create->cr_bmval); - - fh_unlock(&cstate->current_fh); + if (attrs.na_labelerr) + create->cr_bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + if (attrs.na_aclerr) + create->cr_bmval[0] &= ~FATTR4_WORD0_ACL; set_change_info(&create->cr_cinfo, &cstate->current_fh); fh_dup2(&cstate->current_fh, &resfh); out: fh_put(&resfh); out_umask: current->fs->umask = 0; + nfsd_attrs_free(&attrs); return status; } @@ -807,12 +943,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &read->rd_stateid, RD_STATE, &read->rd_nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); - goto out; - } - status = nfs_ok; -out: + read->rd_rqstp = rqstp; read->rd_fhp = &cstate->current_fh; return status; @@ -874,10 +1005,8 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_grace; status = nfsd_unlink(rqstp, &cstate->current_fh, 0, remove->rm_name, remove->rm_namelen); - if (!status) { - fh_unlock(&cstate->current_fh); + if (!status) set_change_info(&remove->rm_cinfo, &cstate->current_fh); - } return status; } @@ -917,7 +1046,6 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &exp, &dentry); if (err) return err; - fh_unlock(&cstate->current_fh); if (d_really_is_negative(dentry)) { exp_put(exp); err = nfserr_noent; @@ -972,17 +1100,21 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_setattr *setattr = &u->setattr; + struct nfsd_attrs attrs = { + .na_iattr = &setattr->sa_iattr, + .na_seclabel = &setattr->sa_label, + }; + struct inode *inode; __be32 status = nfs_ok; + bool save_no_wcc; int err; if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &setattr->sa_stateid, WR_STATE, NULL, NULL); - if (status) { - dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); + if (status) return status; - } } err = fh_want_write(&cstate->current_fh); if (err) @@ -994,19 +1126,23 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - if (setattr->sa_acl != NULL) - status = nfsd4_set_nfs4_acl(rqstp, &cstate->current_fh, - setattr->sa_acl); - if (status) - goto out; - if (setattr->sa_label.len) - status = nfsd4_set_nfs4_label(rqstp, &cstate->current_fh, - &setattr->sa_label); + inode = cstate->current_fh.fh_dentry->d_inode; + status = nfsd4_acl_to_attr(S_ISDIR(inode->i_mode) ? NF4DIR : NF4REG, + setattr->sa_acl, &attrs); + if (status) goto out; - status = nfsd_setattr(rqstp, &cstate->current_fh, &setattr->sa_iattr, + save_no_wcc = cstate->current_fh.fh_no_wcc; + cstate->current_fh.fh_no_wcc = true; + status = nfsd_setattr(rqstp, &cstate->current_fh, &attrs, 0, (time64_t)0); + cstate->current_fh.fh_no_wcc = save_no_wcc; + if (!status) + status = nfserrno(attrs.na_labelerr); + if (!status) + status = nfserrno(attrs.na_aclerr); out: + nfsd_attrs_free(&attrs); fh_drop_write(&cstate->current_fh); return status; } @@ -1031,10 +1167,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, write->wr_offset, cnt); status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, stateid, WR_STATE, &nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_write: couldn't process stateid!\n"); + if (status) return status; - } write->wr_how_written = write->wr_stable_how; @@ -1065,17 +1199,13 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh, src_stateid, RD_STATE, src, NULL); - if (status) { - dprintk("NFSD: %s: couldn't process src stateid!\n", __func__); + if (status) goto out; - } status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, dst_stateid, WR_STATE, dst, NULL); - if (status) { - dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__); + if (status) goto out_put_src; - } /* fix up for NFS-specific error code */ if (!S_ISREG(file_inode((*src)->nf_file)->i_mode) || @@ -1108,7 +1238,7 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - status = nfsd4_clone_file_range(src, clone->cl_src_pos, + status = nfsd4_clone_file_range(rqstp, src, clone->cl_src_pos, dst, clone->cl_dst_pos, clone->cl_count, EX_ISSYNC(cstate->current_fh.fh_export)); @@ -1118,30 +1248,17 @@ out: return status; } -void nfs4_put_copy(struct nfsd4_copy *copy) +static void nfs4_put_copy(struct nfsd4_copy *copy) { if (!refcount_dec_and_test(©->refcount)) return; + kfree(copy->cp_src); kfree(copy); } -static bool -check_and_set_stop_copy(struct nfsd4_copy *copy) -{ - bool value; - - spin_lock(©->cp_clp->async_lock); - value = copy->stopped; - if (!copy->stopped) - copy->stopped = true; - spin_unlock(©->cp_clp->async_lock); - return value; -} - static void nfsd4_stop_copy(struct nfsd4_copy *copy) { - /* only 1 thread should stop the copy */ - if (!check_and_set_stop_copy(copy)) + if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, ©->cp_flags)) kthread_stop(copy->copy_task); nfs4_put_copy(copy); } @@ -1182,15 +1299,15 @@ extern void nfs_sb_deactive(struct super_block *sb); * setup a work entry in the ssc delayed unmount list. */ static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr, - struct nfsd4_ssc_umount_item **retwork, struct vfsmount **ss_mnt) + struct nfsd4_ssc_umount_item **nsui) { - struct nfsd4_ssc_umount_item *ni = 0; + struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *work = NULL; struct nfsd4_ssc_umount_item *tmp; DEFINE_WAIT(wait); + __be32 status = 0; - *ss_mnt = NULL; - *retwork = NULL; + *nsui = NULL; work = kzalloc(sizeof(*work), GFP_KERNEL); try_again: spin_lock(&nn->nfsd_ssc_lock); @@ -1214,44 +1331,45 @@ try_again: finish_wait(&nn->nfsd_ssc_waitq, &wait); goto try_again; } - *ss_mnt = ni->nsui_vfsmount; + *nsui = ni; refcount_inc(&ni->nsui_refcnt); spin_unlock(&nn->nfsd_ssc_lock); kfree(work); - /* return vfsmount in ss_mnt */ + /* return vfsmount in (*nsui)->nsui_vfsmount */ return 0; } if (work) { - strncpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr)); + strscpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr) - 1); refcount_set(&work->nsui_refcnt, 2); work->nsui_busy = true; list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list); - *retwork = work; - } + *nsui = work; + } else + status = nfserr_resource; spin_unlock(&nn->nfsd_ssc_lock); - return 0; + return status; } -static void nfsd4_ssc_update_dul_work(struct nfsd_net *nn, - struct nfsd4_ssc_umount_item *work, struct vfsmount *ss_mnt) +static void nfsd4_ssc_update_dul(struct nfsd_net *nn, + struct nfsd4_ssc_umount_item *nsui, + struct vfsmount *ss_mnt) { - /* set nsui_vfsmount, clear busy flag and wakeup waiters */ spin_lock(&nn->nfsd_ssc_lock); - work->nsui_vfsmount = ss_mnt; - work->nsui_busy = false; + nsui->nsui_vfsmount = ss_mnt; + nsui->nsui_busy = false; wake_up_all(&nn->nfsd_ssc_waitq); spin_unlock(&nn->nfsd_ssc_lock); } -static void nfsd4_ssc_cancel_dul_work(struct nfsd_net *nn, - struct nfsd4_ssc_umount_item *work) +static void nfsd4_ssc_cancel_dul(struct nfsd_net *nn, + struct nfsd4_ssc_umount_item *nsui) { spin_lock(&nn->nfsd_ssc_lock); - list_del(&work->nsui_list); + list_del(&nsui->nsui_list); wake_up_all(&nn->nfsd_ssc_waitq); spin_unlock(&nn->nfsd_ssc_lock); - kfree(work); + kfree(nsui); } /* @@ -1259,7 +1377,7 @@ static void nfsd4_ssc_cancel_dul_work(struct nfsd_net *nn, */ static __be32 nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, - struct vfsmount **mount) + struct nfsd4_ssc_umount_item **nsui) { struct file_system_type *type; struct vfsmount *ss_mnt; @@ -1270,7 +1388,6 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, char *ipaddr, *dev_name, *raw_data; int len, raw_len; __be32 status = nfserr_inval; - struct nfsd4_ssc_umount_item *work = NULL; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); naddr = &nss->u.nl4_addr; @@ -1278,6 +1395,7 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, naddr->addr_len, (struct sockaddr *)&tmp_addr, sizeof(tmp_addr)); + *nsui = NULL; if (tmp_addrlen == 0) goto out_err; @@ -1320,10 +1438,10 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, goto out_free_rawdata; snprintf(dev_name, len + 5, "%s%s%s:/", startsep, ipaddr, endsep); - status = nfsd4_ssc_setup_dul(nn, ipaddr, &work, &ss_mnt); + status = nfsd4_ssc_setup_dul(nn, ipaddr, nsui); if (status) goto out_free_devname; - if (ss_mnt) + if ((*nsui)->nsui_vfsmount) goto out_done; /* Use an 'internal' mount: SB_KERNMOUNT -> MNT_INTERNAL */ @@ -1331,15 +1449,12 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, module_put(type->owner); if (IS_ERR(ss_mnt)) { status = nfserr_nodev; - if (work) - nfsd4_ssc_cancel_dul_work(nn, work); + nfsd4_ssc_cancel_dul(nn, *nsui); goto out_free_devname; } - if (work) - nfsd4_ssc_update_dul_work(nn, work, ss_mnt); + nfsd4_ssc_update_dul(nn, *nsui, ss_mnt); out_done: status = 0; - *mount = ss_mnt; out_free_devname: kfree(dev_name); @@ -1363,7 +1478,7 @@ out_err: static __be32 nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_copy *copy, struct vfsmount **mount) + struct nfsd4_copy *copy) { struct svc_fh *s_fh = NULL; stateid_t *s_stid = ©->cp_src_stateid; @@ -1376,14 +1491,14 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, if (status) goto out; - status = nfsd4_interssc_connect(©->cp_src, rqstp, mount); + status = nfsd4_interssc_connect(copy->cp_src, rqstp, ©->ss_nsui); if (status) goto out; s_fh = &cstate->save_fh; copy->c_fh.size = s_fh->fh_handle.fh_size; - memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_base, copy->c_fh.size); + memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_raw, copy->c_fh.size); copy->stateid.seqid = cpu_to_be32(s_stid->si_generation); memcpy(copy->stateid.other, (void *)&s_stid->si_opaque, sizeof(stateid_opaque_t)); @@ -1394,45 +1509,26 @@ out: } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, +nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp, struct nfsd_file *dst) { - bool found = false; - long timeout; - struct nfsd4_ssc_umount_item *tmp; - struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd_net *nn = net_generic(dst->nf_net, nfsd_net_id); + long timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout); - nfs42_ssc_close(src->nf_file); - nfsd_file_put(dst); - fput(src->nf_file); + nfs42_ssc_close(filp); + fput(filp); - if (!nn) { - mntput(ss_mnt); - return; - } spin_lock(&nn->nfsd_ssc_lock); - timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout); - list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { - if (ni->nsui_vfsmount->mnt_sb == ss_mnt->mnt_sb) { - list_del(&ni->nsui_list); - /* - * vfsmount can be shared by multiple exports, - * decrement refcnt. If the count drops to 1 it - * will be unmounted when nsui_expire expires. - */ - refcount_dec(&ni->nsui_refcnt); - ni->nsui_expire = jiffies + timeout; - list_add_tail(&ni->nsui_list, &nn->nfsd_ssc_mount_list); - found = true; - break; - } - } + list_del(&nsui->nsui_list); + /* + * vfsmount can be shared by multiple exports, + * decrement refcnt. If the count drops to 1 it + * will be unmounted when nsui_expire expires. + */ + refcount_dec(&nsui->nsui_refcnt); + nsui->nsui_expire = jiffies + timeout; + list_add_tail(&nsui->nsui_list, &nn->nfsd_ssc_mount_list); spin_unlock(&nn->nfsd_ssc_lock); - if (!found) { - mntput(ss_mnt); - return; - } } #else /* CONFIG_NFSD_V4_2_INTER_SSC */ @@ -1440,15 +1536,13 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, static __be32 nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_copy *copy, - struct vfsmount **mount) + struct nfsd4_copy *copy) { - *mount = NULL; return nfserr_inval; } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, +nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp, struct nfsd_file *dst) { } @@ -1471,23 +1565,21 @@ nfsd4_setup_intra_ssc(struct svc_rqst *rqstp, ©->nf_dst); } -static void -nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst) -{ - nfsd_file_put(src); - nfsd_file_put(dst); -} - static void nfsd4_cb_offload_release(struct nfsd4_callback *cb) { - struct nfsd4_copy *copy = container_of(cb, struct nfsd4_copy, cp_cb); + struct nfsd4_cb_offload *cbo = + container_of(cb, struct nfsd4_cb_offload, co_cb); - nfs4_put_copy(copy); + kfree(cbo); } static int nfsd4_cb_offload_done(struct nfsd4_callback *cb, struct rpc_task *task) { + struct nfsd4_cb_offload *cbo = + container_of(cb, struct nfsd4_cb_offload, co_cb); + + trace_nfsd_cb_offload_done(&cbo->co_res.cb_stateid, task); return 1; } @@ -1499,15 +1591,16 @@ static const struct nfsd4_callback_ops nfsd4_cb_offload_ops = { static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync) { copy->cp_res.wr_stable_how = - copy->committed ? NFS_FILE_SYNC : NFS_UNSTABLE; - copy->cp_synchronous = sync; + test_bit(NFSD4_COPY_F_COMMITTED, ©->cp_flags) ? + NFS_FILE_SYNC : NFS_UNSTABLE; + nfsd4_copy_set_sync(copy, sync); gen_boot_verifier(©->cp_res.wr_verifier, copy->cp_clp->net); } -static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy) +static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, + struct file *dst, + struct file *src) { - struct file *dst = copy->nf_dst->nf_file; - struct file *src = copy->nf_src->nf_file; errseq_t since; ssize_t bytes_copied = 0; u64 bytes_total = copy->cp_count; @@ -1530,26 +1623,29 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy) copy->cp_res.wr_bytes_written += bytes_copied; src_pos += bytes_copied; dst_pos += bytes_copied; - } while (bytes_total > 0 && !copy->cp_synchronous); + } while (bytes_total > 0 && nfsd4_copy_is_async(copy)); /* for a non-zero asynchronous copy do a commit of data */ - if (!copy->cp_synchronous && copy->cp_res.wr_bytes_written > 0) { + if (nfsd4_copy_is_async(copy) && copy->cp_res.wr_bytes_written > 0) { since = READ_ONCE(dst->f_wb_err); end = copy->cp_dst_pos + copy->cp_res.wr_bytes_written - 1; status = vfs_fsync_range(dst, copy->cp_dst_pos, end, 0); if (!status) status = filemap_check_wb_err(dst->f_mapping, since); if (!status) - copy->committed = true; + set_bit(NFSD4_COPY_F_COMMITTED, ©->cp_flags); } return bytes_copied; } -static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync) +static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, + struct file *src, struct file *dst, + bool sync) { __be32 status; ssize_t bytes; - bytes = _nfsd_copy_file_range(copy); + bytes = _nfsd_copy_file_range(copy, dst, src); + /* for async copy, we ignore the error, client can always retry * to get the error */ @@ -1559,13 +1655,6 @@ static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync) nfsd4_init_copy_res(copy, sync); status = nfs_ok; } - - if (!copy->cp_intra) /* Inter server SSC */ - nfsd4_cleanup_inter_ssc(copy->ss_mnt, copy->nf_src, - copy->nf_dst); - else - nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst); - return status; } @@ -1574,73 +1663,100 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst) dst->cp_src_pos = src->cp_src_pos; dst->cp_dst_pos = src->cp_dst_pos; dst->cp_count = src->cp_count; - dst->cp_synchronous = src->cp_synchronous; + dst->cp_flags = src->cp_flags; memcpy(&dst->cp_res, &src->cp_res, sizeof(src->cp_res)); memcpy(&dst->fh, &src->fh, sizeof(src->fh)); dst->cp_clp = src->cp_clp; dst->nf_dst = nfsd_file_get(src->nf_dst); - dst->cp_intra = src->cp_intra; - if (src->cp_intra) /* for inter, file_src doesn't exist yet */ + /* for inter, nf_src doesn't exist yet */ + if (!nfsd4_ssc_is_inter(src)) dst->nf_src = nfsd_file_get(src->nf_src); memcpy(&dst->cp_stateid, &src->cp_stateid, sizeof(src->cp_stateid)); - memcpy(&dst->cp_src, &src->cp_src, sizeof(struct nl4_server)); + memcpy(dst->cp_src, src->cp_src, sizeof(struct nl4_server)); memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid)); memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh)); - dst->ss_mnt = src->ss_mnt; + dst->ss_nsui = src->ss_nsui; +} + +static void release_copy_files(struct nfsd4_copy *copy) +{ + if (copy->nf_src) + nfsd_file_put(copy->nf_src); + if (copy->nf_dst) + nfsd_file_put(copy->nf_dst); } static void cleanup_async_copy(struct nfsd4_copy *copy) { nfs4_free_copy_state(copy); - nfsd_file_put(copy->nf_dst); - if (copy->cp_intra) - nfsd_file_put(copy->nf_src); - spin_lock(©->cp_clp->async_lock); - list_del(©->copies); - spin_unlock(©->cp_clp->async_lock); + release_copy_files(copy); + if (copy->cp_clp) { + spin_lock(©->cp_clp->async_lock); + if (!list_empty(©->copies)) + list_del_init(©->copies); + spin_unlock(©->cp_clp->async_lock); + } nfs4_put_copy(copy); } +static void nfsd4_send_cb_offload(struct nfsd4_copy *copy, __be32 nfserr) +{ + struct nfsd4_cb_offload *cbo; + + cbo = kzalloc(sizeof(*cbo), GFP_KERNEL); + if (!cbo) + return; + + memcpy(&cbo->co_res, ©->cp_res, sizeof(copy->cp_res)); + memcpy(&cbo->co_fh, ©->fh, sizeof(copy->fh)); + cbo->co_nfserr = nfserr; + + nfsd4_init_cb(&cbo->co_cb, copy->cp_clp, &nfsd4_cb_offload_ops, + NFSPROC4_CLNT_CB_OFFLOAD); + trace_nfsd_cb_offload(copy->cp_clp, &cbo->co_res.cb_stateid, + &cbo->co_fh, copy->cp_count, nfserr); + nfsd4_run_cb(&cbo->co_cb); +} + +/** + * nfsd4_do_async_copy - kthread function for background server-side COPY + * @data: arguments for COPY operation + * + * Return values: + * %0: Copy operation is done. + */ static int nfsd4_do_async_copy(void *data) { struct nfsd4_copy *copy = (struct nfsd4_copy *)data; - struct nfsd4_copy *cb_copy; + __be32 nfserr; - if (!copy->cp_intra) { /* Inter server SSC */ - copy->nf_src = kzalloc(sizeof(struct nfsd_file), GFP_KERNEL); - if (!copy->nf_src) { - copy->nfserr = nfserr_serverfault; - /* ss_mnt will be unmounted by the laundromat */ - goto do_callback; - } - copy->nf_src->nf_file = nfs42_ssc_open(copy->ss_mnt, ©->c_fh, - ©->stateid); - if (IS_ERR(copy->nf_src->nf_file)) { - copy->nfserr = nfserr_offload_denied; + if (nfsd4_ssc_is_inter(copy)) { + struct file *filp; + + filp = nfs42_ssc_open(copy->ss_nsui->nsui_vfsmount, + ©->c_fh, ©->stateid); + if (IS_ERR(filp)) { + switch (PTR_ERR(filp)) { + case -EBADF: + nfserr = nfserr_wrong_type; + break; + default: + nfserr = nfserr_offload_denied; + } /* ss_mnt will be unmounted by the laundromat */ goto do_callback; } + nfserr = nfsd4_do_copy(copy, filp, copy->nf_dst->nf_file, + false); + nfsd4_cleanup_inter_ssc(copy->ss_nsui, filp, copy->nf_dst); + } else { + nfserr = nfsd4_do_copy(copy, copy->nf_src->nf_file, + copy->nf_dst->nf_file, false); } - copy->nfserr = nfsd4_do_copy(copy, 0); do_callback: - cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); - if (!cb_copy) - goto out; - refcount_set(&cb_copy->refcount, 1); - memcpy(&cb_copy->cp_res, ©->cp_res, sizeof(copy->cp_res)); - cb_copy->cp_clp = copy->cp_clp; - cb_copy->nfserr = copy->nfserr; - memcpy(&cb_copy->fh, ©->fh, sizeof(copy->fh)); - nfsd4_init_cb(&cb_copy->cp_cb, cb_copy->cp_clp, - &nfsd4_cb_offload_ops, NFSPROC4_CLNT_CB_OFFLOAD); - trace_nfsd_cb_offload(copy->cp_clp, ©->cp_res.cb_stateid, - ©->fh, copy->cp_count, copy->nfserr); - nfsd4_run_cb(&cb_copy->cp_cb); -out: - if (!copy->cp_intra) - kfree(copy->nf_src); + nfsd4_send_cb_offload(copy, nfserr); cleanup_async_copy(copy); return 0; } @@ -1653,13 +1769,12 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd4_copy *async_copy = NULL; - if (!copy->cp_intra) { /* Inter server SSC */ - if (!inter_copy_offload_enable || copy->cp_synchronous) { + if (nfsd4_ssc_is_inter(copy)) { + if (!inter_copy_offload_enable || nfsd4_copy_is_sync(copy)) { status = nfserr_notsupp; goto out; } - status = nfsd4_setup_inter_ssc(rqstp, cstate, copy, - ©->ss_mnt); + status = nfsd4_setup_inter_ssc(rqstp, cstate, copy); if (status) return nfserr_offload_denied; } else { @@ -1671,17 +1786,21 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, copy->cp_clp = cstate->clp; memcpy(©->fh, &cstate->current_fh.fh_handle, sizeof(struct knfsd_fh)); - if (!copy->cp_synchronous) { + if (nfsd4_copy_is_async(copy)) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); status = nfserrno(-ENOMEM); async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!async_copy) goto out_err; + INIT_LIST_HEAD(&async_copy->copies); + refcount_set(&async_copy->refcount, 1); + async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); + if (!async_copy->cp_src) + goto out_err; if (!nfs4_init_copy_state(nn, copy)) goto out_err; - refcount_set(&async_copy->refcount, 1); - memcpy(©->cp_res.cb_stateid, ©->cp_stateid.stid, + memcpy(©->cp_res.cb_stateid, ©->cp_stateid.cs_stid, sizeof(copy->cp_res.cb_stateid)); dup_copy_fields(copy, async_copy); async_copy->copy_task = kthread_create(nfsd4_do_async_copy, @@ -1695,18 +1814,24 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, wake_up_process(async_copy->copy_task); status = nfs_ok; } else { - status = nfsd4_do_copy(copy, 1); + status = nfsd4_do_copy(copy, copy->nf_src->nf_file, + copy->nf_dst->nf_file, true); } out: + release_copy_files(copy); return status; out_err: + if (nfsd4_ssc_is_inter(copy)) { + /* + * Source's vfsmount of inter-copy will be unmounted + * by the laundromat. Use copy instead of async_copy + * since async_copy->ss_nsui might not be set yet. + */ + refcount_dec(©->ss_nsui->nsui_refcnt); + } if (async_copy) cleanup_async_copy(async_copy); status = nfserrno(-ENOMEM); - /* - * source's vfsmount of inter-copy will be unmounted - * by the laundromat - */ goto out; } @@ -1717,7 +1842,7 @@ find_async_copy(struct nfs4_client *clp, stateid_t *stateid) spin_lock(&clp->async_lock); list_for_each_entry(copy, &clp->async_copies, copies) { - if (memcmp(©->cp_stateid.stid, stateid, NFS4_STATEID_SIZE)) + if (memcmp(©->cp_stateid.cs_stid, stateid, NFS4_STATEID_SIZE)) continue; refcount_inc(©->refcount); spin_unlock(&clp->async_lock); @@ -1771,16 +1896,16 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cps = nfs4_alloc_init_cpntf_state(nn, stid); if (!cps) goto out; - memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.stid, sizeof(stateid_t)); + memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.cs_stid, sizeof(stateid_t)); memcpy(&cps->cp_p_stateid, &stid->sc_stateid, sizeof(stateid_t)); memcpy(&cps->cp_p_clid, &clp->cl_clientid, sizeof(clientid_t)); /* For now, only return one server address in cpn_src, the * address used by the client to connect to this server. */ - cn->cpn_src.nl4_type = NL4_NETADDR; + cn->cpn_src->nl4_type = NL4_NETADDR; status = nfsd4_set_netaddr((struct sockaddr *)&rqstp->rq_daddr, - &cn->cpn_src.u.nl4_addr); + &cn->cpn_src->u.nl4_addr); WARN_ON_ONCE(status); if (status) { nfs4_put_cpntf_state(nn, cps); @@ -1801,10 +1926,8 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &fallocate->falloc_stateid, WR_STATE, &nf, NULL); - if (status != nfs_ok) { - dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n"); + if (status != nfs_ok) return status; - } status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, nf->nf_file, fallocate->falloc_offset, @@ -1860,10 +1983,8 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &seek->seek_stateid, RD_STATE, &nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n"); + if (status) return status; - } switch (seek->seek_whence) { case NFS4_CONTENT_DATA: @@ -2434,7 +2555,7 @@ check_if_stalefh_allowed(struct nfsd4_compoundargs *args) return; } putfh = (struct nfsd4_putfh *)&saved_op->u; - if (!copy->cp_intra) + if (nfsd4_ssc_is_inter(copy)) putfh->no_verify = true; } } @@ -2462,11 +2583,11 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) __be32 status; resp->xdr = &rqstp->rq_res_stream; + resp->statusp = resp->xdr->p; /* reserve space for: NFS status code */ xdr_reserve_space(resp->xdr, XDR_UNIT); - resp->tagp = resp->xdr->p; /* reserve space for: taglen, tag, and opcnt */ xdr_reserve_space(resp->xdr, XDR_UNIT * 2 + args->taglen); resp->taglen = args->taglen; @@ -2499,7 +2620,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) rqstp->rq_lease_breaker = (void **)&cstate->clp; - trace_nfsd_compound(rqstp, args->client_opcnt); + trace_nfsd_compound(rqstp, args->tag, args->taglen, args->client_opcnt); while (!status && resp->opcnt < args->opcnt) { op = &args->ops[resp->opcnt++]; @@ -2536,13 +2657,13 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) goto encode_op; } - fh_clear_wcc(current_fh); + fh_clear_pre_post_attrs(current_fh); /* If op is non-idempotent */ if (op->opdesc->op_flags & OP_MODIFIES_SOMETHING) { /* * Don't execute this op if we couldn't encode a - * succesful reply: + * successful reply: */ u32 plen = op->opdesc->op_rsize_bop(rqstp, op); /* @@ -2623,28 +2744,49 @@ out: #define op_encode_channel_attrs_maxsz (6 + 1 + 1) -static inline u32 nfsd4_only_status_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +/* + * The _rsize() helpers are invoked by the NFSv4 COMPOUND decoder, which + * is called before sunrpc sets rq_res.buflen. Thus we have to compute + * the maximum payload size here, based on transport limits and the size + * of the remaining space in the rq_pages array. + */ +static u32 nfsd4_max_payload(const struct svc_rqst *rqstp) +{ + u32 buflen; + + buflen = (rqstp->rq_page_end - rqstp->rq_next_page) * PAGE_SIZE; + buflen -= rqstp->rq_auth_slack; + buflen -= rqstp->rq_res.head[0].iov_len; + return min_t(u32, buflen, svc_max_payload(rqstp)); +} + +static u32 nfsd4_only_status_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size) * sizeof(__be32); } -static inline u32 nfsd4_status_stateid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_status_stateid_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_stateid_maxsz)* sizeof(__be32); } -static inline u32 nfsd4_access_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_access_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { /* ac_supported, ac_resp_access */ return (op_encode_hdr_size + 2)* sizeof(__be32); } -static inline u32 nfsd4_commit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_commit_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_verifier_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_create_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_create_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz + nfs4_fattr_bitmap_maxsz) * sizeof(__be32); @@ -2655,17 +2797,17 @@ static inline u32 nfsd4_create_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op * the op prematurely if the estimate is too large. We may turn off splice * reads unnecessarily. */ -static inline u32 nfsd4_getattr_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_getattr_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 *bmap = op->u.getattr.ga_bmval; + const u32 *bmap = op->u.getattr.ga_bmval; u32 bmap0 = bmap[0], bmap1 = bmap[1], bmap2 = bmap[2]; u32 ret = 0; if (bmap0 & FATTR4_WORD0_ACL) - return svc_max_payload(rqstp); + return nfsd4_max_payload(rqstp); if (bmap0 & FATTR4_WORD0_FS_LOCATIONS) - return svc_max_payload(rqstp); + return nfsd4_max_payload(rqstp); if (bmap1 & FATTR4_WORD1_OWNER) { ret += IDMAP_NAMESZ + 4; @@ -2693,24 +2835,28 @@ static inline u32 nfsd4_getattr_rsize(struct svc_rqst *rqstp, return ret; } -static inline u32 nfsd4_getfh_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_getfh_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1) * sizeof(__be32) + NFS4_FHSIZE; } -static inline u32 nfsd4_link_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_link_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_lock_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_lock_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_lock_denied_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_open_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_open_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_stateid_maxsz + op_encode_change_info_maxsz + 1 @@ -2718,20 +2864,18 @@ static inline u32 nfsd4_open_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) + op_encode_delegation_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_read_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_read_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount = 0, rlen = 0; - - maxcount = svc_max_payload(rqstp); - rlen = min(op->u.read.rd_length, maxcount); + u32 rlen = min(op->u.read.rd_length, nfsd4_max_payload(rqstp)); return (op_encode_hdr_size + 2 + XDR_QUADLEN(rlen)) * sizeof(__be32); } -static inline u32 nfsd4_read_plus_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_read_plus_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount = svc_max_payload(rqstp); - u32 rlen = min(op->u.read.rd_length, maxcount); + u32 rlen = min(op->u.read.rd_length, nfsd4_max_payload(rqstp)); /* * If we detect that the file changed during hole encoding, then we * recover by encoding the remaining reply as data. This means we need @@ -2742,70 +2886,77 @@ static inline u32 nfsd4_read_plus_rsize(struct svc_rqst *rqstp, struct nfsd4_op return (op_encode_hdr_size + 2 + seg_len + XDR_QUADLEN(rlen)) * sizeof(__be32); } -static inline u32 nfsd4_readdir_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_readdir_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount = 0, rlen = 0; - - maxcount = svc_max_payload(rqstp); - rlen = min(op->u.readdir.rd_maxcount, maxcount); + u32 rlen = min(op->u.readdir.rd_maxcount, nfsd4_max_payload(rqstp)); return (op_encode_hdr_size + op_encode_verifier_maxsz + XDR_QUADLEN(rlen)) * sizeof(__be32); } -static inline u32 nfsd4_readlink_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_readlink_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1) * sizeof(__be32) + PAGE_SIZE; } -static inline u32 nfsd4_remove_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_remove_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_rename_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_rename_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz + op_encode_change_info_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_sequence_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_sequence_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) * sizeof(__be32); } -static inline u32 nfsd4_test_stateid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_test_stateid_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1 + op->u.test_stateid.ts_num_ids) * sizeof(__be32); } -static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_setattr_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + nfs4_fattr_bitmap_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_secinfo_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_secinfo_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + RPC_AUTH_MAXFLAVOR * (4 + XDR_QUADLEN(GSS_OID_MAX_LEN))) * sizeof(__be32); } -static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_setclientid_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 2 + XDR_QUADLEN(NFS4_VERIFIER_SIZE)) * sizeof(__be32); } -static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_write_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 2 + op_encode_verifier_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_exchange_id_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 2 + 1 + /* eir_clientid, eir_sequenceid */\ 1 + 1 + /* eir_flags, spr_how */\ @@ -2819,14 +2970,16 @@ static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_o 0 /* ignored eir_server_impl_id contents */) * sizeof(__be32); } -static inline u32 nfsd4_bind_conn_to_session_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_bind_conn_to_session_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + \ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + /* bctsr_sessid */\ 2 /* bctsr_dir, use_conn_in_rdma_mode */) * sizeof(__be32); } -static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_create_session_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + \ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + /* sessionid */\ @@ -2835,7 +2988,8 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd op_encode_channel_attrs_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_copy_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_copy_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1 /* wr_callback */ + @@ -2847,16 +3001,16 @@ static inline u32 nfsd4_copy_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) 1 /* cr_synchronous */) * sizeof(__be32); } -static inline u32 nfsd4_offload_status_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_offload_status_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 2 /* osr_count */ + 1 /* osr_complete<1> optional 0 for now */) * sizeof(__be32); } -static inline u32 nfsd4_copy_notify_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_copy_notify_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 3 /* cnr_lease_time */ + @@ -2871,12 +3025,10 @@ static inline u32 nfsd4_copy_notify_rsize(struct svc_rqst *rqstp, } #ifdef CONFIG_NFSD_PNFS -static inline u32 nfsd4_getdeviceinfo_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_getdeviceinfo_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount = 0, rlen = 0; - - maxcount = svc_max_payload(rqstp); - rlen = min(op->u.getdeviceinfo.gd_maxcount, maxcount); + u32 rlen = min(op->u.getdeviceinfo.gd_maxcount, nfsd4_max_payload(rqstp)); return (op_encode_hdr_size + 1 /* gd_layout_type*/ + @@ -2889,7 +3041,8 @@ static inline u32 nfsd4_getdeviceinfo_rsize(struct svc_rqst *rqstp, struct nfsd4 * so we need to define an arbitrary upper bound here. */ #define MAX_LAYOUT_SIZE 128 -static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_layoutget_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1 /* logr_return_on_close */ + @@ -2898,14 +3051,16 @@ static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op MAX_LAYOUT_SIZE) * sizeof(__be32); } -static inline u32 nfsd4_layoutcommit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_layoutcommit_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1 /* locr_newsize */ + 2 /* ns_size */) * sizeof(__be32); } -static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_layoutreturn_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 1 /* lrs_stateid */ + @@ -2914,41 +3069,36 @@ static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_ #endif /* CONFIG_NFSD_PNFS */ -static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +static u32 nfsd4_seek_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + 3) * sizeof(__be32); } -static inline u32 nfsd4_getxattr_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_getxattr_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount, rlen; - - maxcount = svc_max_payload(rqstp); - rlen = min_t(u32, XATTR_SIZE_MAX, maxcount); + u32 rlen = min_t(u32, XATTR_SIZE_MAX, nfsd4_max_payload(rqstp)); return (op_encode_hdr_size + 1 + XDR_QUADLEN(rlen)) * sizeof(__be32); } -static inline u32 nfsd4_setxattr_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_setxattr_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz) * sizeof(__be32); } -static inline u32 nfsd4_listxattrs_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_listxattrs_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { - u32 maxcount, rlen; - - maxcount = svc_max_payload(rqstp); - rlen = min(op->u.listxattrs.lsxa_maxcount, maxcount); + u32 rlen = min(op->u.listxattrs.lsxa_maxcount, nfsd4_max_payload(rqstp)); return (op_encode_hdr_size + 4 + XDR_QUADLEN(rlen)) * sizeof(__be32); } -static inline u32 nfsd4_removexattr_rsize(struct svc_rqst *rqstp, - struct nfsd4_op *op) +static u32 nfsd4_removexattr_rsize(const struct svc_rqst *rqstp, + const struct nfsd4_op *op) { return (op_encode_hdr_size + op_encode_change_info_maxsz) * sizeof(__be32); @@ -3437,6 +3587,7 @@ static const struct svc_procedure nfsd_procedures4[2] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 1, @@ -3447,6 +3598,7 @@ static const struct svc_procedure nfsd_procedures4[2] = { .pc_decode = nfs4svc_decode_compoundargs, .pc_encode = nfs4svc_encode_compoundres, .pc_argsize = sizeof(struct nfsd4_compoundargs), + .pc_argzero = offsetof(struct nfsd4_compoundargs, iops), .pc_ressize = sizeof(struct nfsd4_compoundres), .pc_release = nfsd4_release_compoundargs, .pc_cachetype = RC_NOCACHE, diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 8f24485e0f04..5d680045fa2c 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -807,17 +807,17 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg, if (get_user(namelen, &ci->cc_name.cn_len)) return -EFAULT; name.data = memdup_user(&ci->cc_name.cn_id, namelen); - if (IS_ERR_OR_NULL(name.data)) - return -EFAULT; + if (IS_ERR(name.data)) + return PTR_ERR(name.data); name.len = namelen; get_user(princhashlen, &ci->cc_princhash.cp_len); if (princhashlen > 0) { princhash.data = memdup_user( &ci->cc_princhash.cp_data, princhashlen); - if (IS_ERR_OR_NULL(princhash.data)) { + if (IS_ERR(princhash.data)) { kfree(name.data); - return -EFAULT; + return PTR_ERR(princhash.data); } princhash.len = princhashlen; } else @@ -829,8 +829,8 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg, if (get_user(namelen, &cnm->cn_len)) return -EFAULT; name.data = memdup_user(&cnm->cn_id, namelen); - if (IS_ERR_OR_NULL(name.data)) - return -EFAULT; + if (IS_ERR(name.data)) + return PTR_ERR(name.data); name.len = namelen; } if (name.len > 5 && memcmp(name.data, "hash:", 5) == 0) { diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 9b660491f393..40b5b226e504 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -44,7 +44,9 @@ #include <linux/jhash.h> #include <linux/string_helpers.h> #include <linux/fsnotify.h> +#include <linux/rhashtable.h> #include <linux/nfs_ssc.h> + #include "xdr4.h" #include "xdr4cb.h" #include "vfs.h" @@ -84,6 +86,7 @@ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) static void nfs4_free_ol_stateid(struct nfs4_stid *stid); void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); +static void nfsd4_file_hash_remove(struct nfs4_file *fi); /* Locking: */ @@ -125,6 +128,23 @@ static void free_session(struct nfsd4_session *); static const struct nfsd4_callback_ops nfsd4_cb_recall_ops; static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops; +static struct workqueue_struct *laundry_wq; + +int nfsd4_create_laundry_wq(void) +{ + int rc = 0; + + laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4"); + if (laundry_wq == NULL) + rc = -ENOMEM; + return rc; +} + +void nfsd4_destroy_laundry_wq(void) +{ + destroy_workqueue(laundry_wq); +} + static bool is_session_dead(struct nfsd4_session *ses) { return ses->se_flags & NFS4_SESSION_DEAD; @@ -143,6 +163,13 @@ static bool is_client_expired(struct nfs4_client *clp) return clp->cl_time == 0; } +static void nfsd4_dec_courtesy_client_count(struct nfsd_net *nn, + struct nfs4_client *clp) +{ + if (clp->cl_state != NFSD4_ACTIVE) + atomic_add_unless(&nn->nfsd_courtesy_clients, -1, 0); +} + static __be32 get_client_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); @@ -152,6 +179,8 @@ static __be32 get_client_locked(struct nfs4_client *clp) if (is_client_expired(clp)) return nfserr_expired; atomic_inc(&clp->cl_rpc_users); + nfsd4_dec_courtesy_client_count(nn, clp); + clp->cl_state = NFSD4_ACTIVE; return nfs_ok; } @@ -172,6 +201,8 @@ renew_client_locked(struct nfs4_client *clp) list_move_tail(&clp->cl_lru, &nn->client_lru); clp->cl_time = ktime_get_boottime_seconds(); + nfsd4_dec_courtesy_client_count(nn, clp); + clp->cl_state = NFSD4_ACTIVE; } static void put_client_renew_locked(struct nfs4_client *clp) @@ -246,6 +277,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh, list_for_each_entry(cur, &lo->lo_blocked, nbl_list) { if (fh_match(fh, &cur->nbl_fh)) { list_del_init(&cur->nbl_list); + WARN_ON(list_empty(&cur->nbl_lru)); list_del_init(&cur->nbl_lru); found = cur; break; @@ -271,6 +303,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, INIT_LIST_HEAD(&nbl->nbl_lru); fh_copy_shallow(&nbl->nbl_fh, fh); locks_init_lock(&nbl->nbl_lock); + kref_init(&nbl->nbl_kref); nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client, &nfsd4_cb_notify_lock_ops, NFSPROC4_CLNT_CB_NOTIFY_LOCK); @@ -280,14 +313,23 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, } static void -free_blocked_lock(struct nfsd4_blocked_lock *nbl) +free_nbl(struct kref *kref) { - locks_delete_block(&nbl->nbl_lock); + struct nfsd4_blocked_lock *nbl; + + nbl = container_of(kref, struct nfsd4_blocked_lock, nbl_kref); locks_release_private(&nbl->nbl_lock); kfree(nbl); } static void +free_blocked_lock(struct nfsd4_blocked_lock *nbl) +{ + locks_delete_block(&nbl->nbl_lock); + kref_put(&nbl->nbl_kref, free_nbl); +} + +static void remove_blocked_locks(struct nfs4_lockowner *lo) { struct nfs4_client *clp = lo->lo_owner.so_client; @@ -302,6 +344,7 @@ remove_blocked_locks(struct nfs4_lockowner *lo) struct nfsd4_blocked_lock, nbl_list); list_del_init(&nbl->nbl_list); + WARN_ON(list_empty(&nbl->nbl_lru)); list_move(&nbl->nbl_lru, &reaplist); } spin_unlock(&nn->blocked_locks_lock); @@ -326,6 +369,8 @@ nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb) static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { + trace_nfsd_cb_notify_lock_done(&zero_stateid, task); + /* * Since this is just an optimization, we don't try very hard if it * turns out not to succeed. We'll requeue it on NFS4ERR_DELAY, and @@ -360,11 +405,13 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { * st_{access,deny}_bmap field of the stateid, in order to track not * only what share bits are currently in force, but also what * combinations of share bits previous opens have used. This allows us - * to enforce the recommendation of rfc 3530 14.2.19 that the server - * return an error if the client attempt to downgrade to a combination - * of share bits not explicable by closing some of its previous opens. + * to enforce the recommendation in + * https://datatracker.ietf.org/doc/html/rfc7530#section-16.19.4 that + * the server return an error if the client attempt to downgrade to a + * combination of share bits not explicable by closing some of its + * previous opens. * - * XXX: This enforcement is actually incomplete, since we don't keep + * This enforcement is arguably incomplete, since we don't keep * track of access/deny bit combinations; so, e.g., we allow: * * OPEN allow read, deny write @@ -372,6 +419,10 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { * DOWNGRADE allow read, deny none * * which we should reject. + * + * But you could also argue that our current code is already overkill, + * since it only exists to return NFS4ERR_INVAL on incorrect client + * behavior. */ static unsigned int bmap_to_share_mode(unsigned long bmap) @@ -540,11 +591,8 @@ static void nfsd4_free_file_rcu(struct rcu_head *rcu) void put_nfs4_file(struct nfs4_file *fi) { - might_lock(&state_lock); - - if (refcount_dec_and_lock(&fi->fi_ref, &state_lock)) { - hlist_del_rcu(&fi->fi_hash); - spin_unlock(&state_lock); + if (refcount_dec_and_test(&fi->fi_ref)) { + nfsd4_file_hash_remove(fi); WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate)); WARN_ON_ONCE(!list_empty(&fi->fi_delegations)); call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu); @@ -554,9 +602,7 @@ put_nfs4_file(struct nfs4_file *fi) static struct nfsd_file * __nfs4_get_fd(struct nfs4_file *f, int oflag) { - if (f->fi_fds[oflag]) - return nfsd_file_get(f->fi_fds[oflag]); - return NULL; + return nfsd_file_get(f->fi_fds[oflag]); } static struct nfsd_file * @@ -669,20 +715,72 @@ static unsigned int ownerstr_hashval(struct xdr_netobj *ownername) return ret & OWNER_HASH_MASK; } -/* hash table for nfs4_file */ -#define FILE_HASH_BITS 8 -#define FILE_HASH_SIZE (1 << FILE_HASH_BITS) +static struct rhltable nfs4_file_rhltable ____cacheline_aligned_in_smp; + +static const struct rhashtable_params nfs4_file_rhash_params = { + .key_len = sizeof_field(struct nfs4_file, fi_inode), + .key_offset = offsetof(struct nfs4_file, fi_inode), + .head_offset = offsetof(struct nfs4_file, fi_rlist), + + /* + * Start with a single page hash table to reduce resizing churn + * on light workloads. + */ + .min_size = 256, + .automatic_shrinking = true, +}; -static unsigned int file_hashval(struct svc_fh *fh) +/* + * Check if courtesy clients have conflicting access and resolve it if possible + * + * access: is op_share_access if share_access is true. + * Check if access mode, op_share_access, would conflict with + * the current deny mode of the file 'fp'. + * access: is op_share_deny if share_access is false. + * Check if the deny mode, op_share_deny, would conflict with + * current access of the file 'fp'. + * stp: skip checking this entry. + * new_stp: normal open, not open upgrade. + * + * Function returns: + * false - access/deny mode conflict with normal client. + * true - no conflict or conflict with courtesy client(s) is resolved. + */ +static bool +nfs4_resolve_deny_conflicts_locked(struct nfs4_file *fp, bool new_stp, + struct nfs4_ol_stateid *stp, u32 access, bool share_access) { - struct inode *inode = d_inode(fh->fh_dentry); + struct nfs4_ol_stateid *st; + bool resolvable = true; + unsigned char bmap; + struct nfsd_net *nn; + struct nfs4_client *clp; - /* XXX: why not (here & in file cache) use inode? */ - return (unsigned int)hash_long(inode->i_ino, FILE_HASH_BITS); + lockdep_assert_held(&fp->fi_lock); + list_for_each_entry(st, &fp->fi_stateids, st_perfile) { + /* ignore lock stateid */ + if (st->st_openstp) + continue; + if (st == stp && new_stp) + continue; + /* check file access against deny mode or vice versa */ + bmap = share_access ? st->st_deny_bmap : st->st_access_bmap; + if (!(access & bmap_to_share_mode(bmap))) + continue; + clp = st->st_stid.sc_client; + if (try_to_expire_client(clp)) + continue; + resolvable = false; + break; + } + if (resolvable) { + clp = stp->st_stid.sc_client; + nn = net_generic(clp->net, nfsd_net_id); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + } + return resolvable; } -static struct hlist_head file_hashtbl[FILE_HASH_SIZE]; - static void __nfs4_file_get_access(struct nfs4_file *fp, u32 access) { @@ -886,23 +984,23 @@ out_free: * Create a unique stateid_t to represent each COPY. */ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, - unsigned char sc_type) + unsigned char cs_type) { int new_id; - stid->stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time; - stid->stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id; - stid->sc_type = sc_type; + stid->cs_stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time; + stid->cs_stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id; idr_preload(GFP_KERNEL); spin_lock(&nn->s2s_cp_lock); new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT); - stid->stid.si_opaque.so_id = new_id; - stid->stid.si_generation = 1; + stid->cs_stid.si_opaque.so_id = new_id; + stid->cs_stid.si_generation = 1; spin_unlock(&nn->s2s_cp_lock); idr_preload_end(); if (new_id < 0) return 0; + stid->cs_type = cs_type; return 1; } @@ -920,7 +1018,7 @@ struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, if (!cps) return NULL; cps->cpntf_time = ktime_get_boottime_seconds(); - refcount_set(&cps->cp_stateid.sc_count, 1); + refcount_set(&cps->cp_stateid.cs_count, 1); if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID)) goto out_free; spin_lock(&nn->s2s_cp_lock); @@ -936,11 +1034,12 @@ void nfs4_free_copy_state(struct nfsd4_copy *copy) { struct nfsd_net *nn; - WARN_ON_ONCE(copy->cp_stateid.sc_type != NFS4_COPY_STID); + if (copy->cp_stateid.cs_type != NFS4_COPY_STID) + return; nn = net_generic(copy->cp_clp->net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); idr_remove(&nn->s2s_cp_stateids, - copy->cp_stateid.stid.si_opaque.so_id); + copy->cp_stateid.cs_stid.si_opaque.so_id); spin_unlock(&nn->s2s_cp_lock); } @@ -972,7 +1071,12 @@ static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) static void nfs4_free_deleg(struct nfs4_stid *stid) { - WARN_ON(!list_empty(&stid->sc_cp_list)); + struct nfs4_delegation *dp = delegstateid(stid); + + WARN_ON_ONCE(!list_empty(&stid->sc_cp_list)); + WARN_ON_ONCE(!list_empty(&dp->dl_perfile)); + WARN_ON_ONCE(!list_empty(&dp->dl_perclnt)); + WARN_ON_ONCE(!list_empty(&dp->dl_recall_lru)); kmem_cache_free(deleg_slab, stid); atomic_long_dec(&num_delegations); } @@ -1022,7 +1126,7 @@ static int delegation_blocked(struct knfsd_fh *fh) } spin_unlock(&blocked_delegations_lock); } - hash = jhash(&fh->fh_base, fh->fh_size, 0); + hash = jhash(&fh->fh_raw, fh->fh_size, 0); if (test_bit(hash&255, bd->set[0]) && test_bit((hash>>8)&255, bd->set[0]) && test_bit((hash>>16)&255, bd->set[0])) @@ -1041,7 +1145,7 @@ static void block_delegations(struct knfsd_fh *fh) u32 hash; struct bloom_pair *bd = &blocked_delegations; - hash = jhash(&fh->fh_base, fh->fh_size, 0); + hash = jhash(&fh->fh_raw, fh->fh_size, 0); spin_lock(&blocked_delegations_lock); __set_bit(hash&255, bd->set[bd->new]); @@ -1055,7 +1159,6 @@ static void block_delegations(struct knfsd_fh *fh) static struct nfs4_delegation * alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, - struct svc_fh *current_fh, struct nfs4_clnt_odstate *odstate) { struct nfs4_delegation *dp; @@ -1065,7 +1168,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, n = atomic_long_inc_return(&num_delegations); if (n < 0 || n > max_delegations) goto out_dec; - if (delegation_blocked(¤t_fh->fh_handle)) + if (delegation_blocked(&fp->fi_fhandle)) goto out_dec; dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg)); if (dp == NULL) @@ -1084,6 +1187,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, get_clnt_odstate(odstate); dp->dl_type = NFS4_OPEN_DELEGATE_READ; dp->dl_retries = 1; + dp->dl_recalled = false; nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client, &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL); get_nfs4_file(fp); @@ -1262,6 +1366,8 @@ static void revoke_delegation(struct nfs4_delegation *dp) WARN_ON(!list_empty(&dp->dl_recall_lru)); + trace_nfsd_stid_revoke(&dp->dl_stid); + if (clp->cl_minorversion) { spin_lock(&clp->cl_lock); dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; @@ -1726,13 +1832,12 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs, int numslots = fattrs->maxreqs; int slotsize = slot_bytes(fattrs); struct nfsd4_session *new; - int mem, i; + int i; - BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot *) - + sizeof(struct nfsd4_session) > PAGE_SIZE); - mem = numslots * sizeof(struct nfsd4_slot *); + BUILD_BUG_ON(struct_size(new, se_slots, NFSD_MAX_SLOTS_PER_SESSION) + > PAGE_SIZE); - new = kzalloc(sizeof(*new) + mem, GFP_KERNEL); + new = kzalloc(struct_size(new, se_slots, numslots), GFP_KERNEL); if (!new) return NULL; /* allocate each struct nfsd4_slot and data cache in one piece */ @@ -1977,11 +2082,16 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) * This type of memory management is somewhat inefficient, but we use it * anyway since SETCLIENTID is not a common operation. */ -static struct nfs4_client *alloc_client(struct xdr_netobj name) +static struct nfs4_client *alloc_client(struct xdr_netobj name, + struct nfsd_net *nn) { struct nfs4_client *clp; int i; + if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) { + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + return NULL; + } clp = kmem_cache_zalloc(client_slab, GFP_KERNEL); if (clp == NULL) return NULL; @@ -1999,6 +2109,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) idr_init(&clp->cl_stateids); atomic_set(&clp->cl_rpc_users, 0); clp->cl_cb_state = NFSD4_CB_UNKNOWN; + clp->cl_state = NFSD4_ACTIVE; + atomic_inc(&nn->nfs4_client_count); + atomic_set(&clp->cl_delegs_in_recall, 0); INIT_LIST_HEAD(&clp->cl_idhash); INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); @@ -2030,6 +2143,7 @@ static void __free_client(struct kref *k) kfree(clp->cl_nii_domain.data); kfree(clp->cl_nii_name.data); idr_destroy(&clp->cl_stateids); + kfree(clp->cl_ra); kmem_cache_free(client_slab, clp); } @@ -2105,6 +2219,7 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp) static void __destroy_client(struct nfs4_client *clp) { + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); int i; struct nfs4_openowner *oo; struct nfs4_delegation *dp; @@ -2148,6 +2263,8 @@ __destroy_client(struct nfs4_client *clp) nfsd4_shutdown_callback(clp); if (clp->cl_cb_conn.cb_xprt) svc_xprt_put(clp->cl_cb_conn.cb_xprt); + atomic_add_unless(&nn->nfs4_client_count, -1, 0); + nfsd4_dec_courtesy_client_count(nn, clp); free_client(clp); wake_up_all(&expiry_wq); } @@ -2393,7 +2510,7 @@ static const char *cb_state2str(int state) static int client_info_show(struct seq_file *m, void *v) { - struct inode *inode = m->private; + struct inode *inode = file_inode(m->file); struct nfs4_client *clp; u64 clid; @@ -2403,10 +2520,17 @@ static int client_info_show(struct seq_file *m, void *v) memcpy(&clid, &clp->cl_clientid, sizeof(clid)); seq_printf(m, "clientid: 0x%llx\n", clid); seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr); - if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags)) + + if (clp->cl_state == NFSD4_COURTESY) + seq_puts(m, "status: courtesy\n"); + else if (clp->cl_state == NFSD4_EXPIRABLE) + seq_puts(m, "status: expirable\n"); + else if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags)) seq_puts(m, "status: confirmed\n"); else seq_puts(m, "status: unconfirmed\n"); + seq_printf(m, "seconds from last renew: %lld\n", + ktime_get_boottime_seconds() - clp->cl_time); seq_printf(m, "name: "); seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len); seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion); @@ -2426,17 +2550,7 @@ static int client_info_show(struct seq_file *m, void *v) return 0; } -static int client_info_open(struct inode *inode, struct file *file) -{ - return single_open(file, client_info_show, inode); -} - -static const struct file_operations client_info_fops = { - .open = client_info_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(client_info); static void *states_start(struct seq_file *s, loff_t *pos) __acquires(&clp->cl_lock) @@ -2479,7 +2593,7 @@ static void nfs4_show_fname(struct seq_file *s, struct nfsd_file *f) static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f) { - struct inode *inode = f->nf_inode; + struct inode *inode = file_inode(f->nf_file); seq_printf(s, "superblock: \"%02x:%02x:%ld\"", MAJOR(inode->i_sb->s_dev), @@ -2757,6 +2871,34 @@ static const struct tree_descr client_files[] = { [3] = {""}, }; +static int +nfsd4_cb_recall_any_done(struct nfsd4_callback *cb, + struct rpc_task *task) +{ + trace_nfsd_cb_recall_any_done(cb, task); + switch (task->tk_status) { + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; + default: + return 1; + } +} + +static void +nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) +{ + struct nfs4_client *clp = cb->cb_clp; + + clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); + drop_client(clp); +} + +static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { + .done = nfsd4_cb_recall_any_done, + .release = nfsd4_cb_recall_any_release, +}; + static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { @@ -2767,7 +2909,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name, struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct dentry *dentries[ARRAY_SIZE(client_files)]; - clp = alloc_client(name); + clp = alloc_client(name, nn); if (clp == NULL) return NULL; @@ -2794,6 +2936,14 @@ static struct nfs4_client *create_client(struct xdr_netobj name, free_client(clp); return NULL; } + clp->cl_ra = kzalloc(sizeof(*clp->cl_ra), GFP_KERNEL); + if (!clp->cl_ra) { + free_client(clp); + return NULL; + } + clp->cl_ra_time = 0; + nfsd4_init_cb(&clp->cl_ra->ra_cb, clp, &nfsd4_cb_recall_any_ops, + NFSPROC4_CLNT_CB_RECALL_ANY); return clp; } @@ -4163,11 +4313,9 @@ static struct nfs4_file *nfsd4_alloc_file(void) } /* OPEN Share state helper functions */ -static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval, - struct nfs4_file *fp) -{ - lockdep_assert_held(&state_lock); +static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp) +{ refcount_set(&fp->fi_ref, 1); spin_lock_init(&fp->fi_lock); INIT_LIST_HEAD(&fp->fi_stateids); @@ -4185,7 +4333,6 @@ static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval, INIT_LIST_HEAD(&fp->fi_lo_states); atomic_set(&fp->fi_lo_recalls, 0); #endif - hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]); } void @@ -4249,6 +4396,54 @@ out: return -ENOMEM; } +static unsigned long +nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) +{ + int count; + struct nfsd_net *nn = container_of(shrink, + struct nfsd_net, nfsd_client_shrinker); + + count = atomic_read(&nn->nfsd_courtesy_clients); + if (!count) + count = atomic_long_read(&num_delegations); + if (count) + queue_work(laundry_wq, &nn->nfsd_shrinker_work); + return (unsigned long)count; +} + +static unsigned long +nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + return SHRINK_STOP; +} + +void +nfsd4_init_leases_net(struct nfsd_net *nn) +{ + struct sysinfo si; + u64 max_clients; + + nn->nfsd4_lease = 90; /* default lease time */ + nn->nfsd4_grace = 90; + nn->somebody_reclaimed = false; + nn->track_reclaim_completes = false; + nn->clverifier_counter = prandom_u32(); + nn->clientid_base = prandom_u32(); + nn->clientid_counter = nn->clientid_base + 1; + nn->s2s_cp_cl_id = nn->clientid_counter++; + + atomic_set(&nn->nfs4_client_count, 0); + si_meminfo(&si); + max_clients = (u64)si.totalram * si.mem_unit / (1024 * 1024 * 1024); + max_clients *= NFS4_CLIENTS_PER_GB; + nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB); + + atomic_set(&nn->nfsd_courtesy_clients, 0); + nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; + nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; + nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; +} + static void init_nfs4_replay(struct nfs4_replay *rp) { rp->rp_status = nfserr_serverfault; @@ -4517,71 +4712,80 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) nfs4_put_stid(&last->st_stid); } -/* search file_hashtbl[] for file */ -static struct nfs4_file * -find_file_locked(struct svc_fh *fh, unsigned int hashval) +static noinline_for_stack struct nfs4_file * +nfsd4_file_hash_lookup(const struct svc_fh *fhp) { - struct nfs4_file *fp; + struct inode *inode = d_inode(fhp->fh_dentry); + struct rhlist_head *tmp, *list; + struct nfs4_file *fi; - hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash, - lockdep_is_held(&state_lock)) { - if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) { - if (refcount_inc_not_zero(&fp->fi_ref)) - return fp; + rcu_read_lock(); + list = rhltable_lookup(&nfs4_file_rhltable, &inode, + nfs4_file_rhash_params); + rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { + if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { + if (refcount_inc_not_zero(&fi->fi_ref)) { + rcu_read_unlock(); + return fi; + } } } + rcu_read_unlock(); return NULL; } -static struct nfs4_file *insert_file(struct nfs4_file *new, struct svc_fh *fh, - unsigned int hashval) +/* + * On hash insertion, identify entries with the same inode but + * distinct filehandles. They will all be on the list returned + * by rhltable_lookup(). + * + * inode->i_lock prevents racing insertions from adding an entry + * for the same inode/fhp pair twice. + */ +static noinline_for_stack struct nfs4_file * +nfsd4_file_hash_insert(struct nfs4_file *new, const struct svc_fh *fhp) { - struct nfs4_file *fp; + struct inode *inode = d_inode(fhp->fh_dentry); + struct rhlist_head *tmp, *list; struct nfs4_file *ret = NULL; bool alias_found = false; + struct nfs4_file *fi; + int err; - spin_lock(&state_lock); - hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash, - lockdep_is_held(&state_lock)) { - if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) { - if (refcount_inc_not_zero(&fp->fi_ref)) - ret = fp; - } else if (d_inode(fh->fh_dentry) == fp->fi_inode) - fp->fi_aliased = alias_found = true; - } - if (likely(ret == NULL)) { - nfsd4_init_file(fh, hashval, new); - new->fi_aliased = alias_found; - ret = new; + rcu_read_lock(); + spin_lock(&inode->i_lock); + + list = rhltable_lookup(&nfs4_file_rhltable, &inode, + nfs4_file_rhash_params); + rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { + if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { + if (refcount_inc_not_zero(&fi->fi_ref)) + ret = fi; + } else + fi->fi_aliased = alias_found = true; } - spin_unlock(&state_lock); - return ret; -} + if (ret) + goto out_unlock; -static struct nfs4_file * find_file(struct svc_fh *fh) -{ - struct nfs4_file *fp; - unsigned int hashval = file_hashval(fh); + nfsd4_file_init(fhp, new); + err = rhltable_insert(&nfs4_file_rhltable, &new->fi_rlist, + nfs4_file_rhash_params); + if (err) + goto out_unlock; - rcu_read_lock(); - fp = find_file_locked(fh, hashval); + new->fi_aliased = alias_found; + ret = new; + +out_unlock: + spin_unlock(&inode->i_lock); rcu_read_unlock(); - return fp; + return ret; } -static struct nfs4_file * -find_or_add_file(struct nfs4_file *new, struct svc_fh *fh) +static noinline_for_stack void nfsd4_file_hash_remove(struct nfs4_file *fi) { - struct nfs4_file *fp; - unsigned int hashval = file_hashval(fh); - - rcu_read_lock(); - fp = find_file_locked(fh, hashval); - rcu_read_unlock(); - if (fp) - return fp; - - return insert_file(new, fh, hashval); + rhltable_remove(&nfs4_file_rhltable, &fi->fi_rlist, + nfs4_file_rhash_params); } /* @@ -4594,9 +4798,10 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) struct nfs4_file *fp; __be32 ret = nfs_ok; - fp = find_file(current_fh); + fp = nfsd4_file_hash_lookup(current_fh); if (!fp) return ret; + /* Check for conflicting share reservations */ spin_lock(&fp->fi_lock); if (fp->fi_share_deny & deny_type) @@ -4606,6 +4811,35 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) return ret; } +static bool nfsd4_deleg_present(const struct inode *inode) +{ + struct file_lock_context *ctx = locks_inode_context(inode); + + return ctx && !list_empty_careful(&ctx->flc_lease); +} + +/** + * nfsd_wait_for_delegreturn - wait for delegations to be returned + * @rqstp: the RPC transaction being executed + * @inode: in-core inode of the file being waited for + * + * The timeout prevents deadlock if all nfsd threads happen to be + * tied up waiting for returning delegations. + * + * Return values: + * %true: delegation was returned + * %false: timed out waiting for delegreturn + */ +bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode) +{ + long __maybe_unused timeo; + + timeo = wait_var_event_timeout(inode, !nfsd4_deleg_present(inode), + NFSD_DELEGRETURN_TIMEOUT); + trace_nfsd_delegret_wakeup(rqstp, inode, timeo); + return timeo > 0; +} + static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb) { struct nfs4_delegation *dp = cb_to_delegation(cb); @@ -4634,6 +4868,8 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, { struct nfs4_delegation *dp = cb_to_delegation(cb); + trace_nfsd_cb_recall_done(&dp->dl_stid.sc_stateid, task); + if (dp->dl_stid.sc_type == NFS4_CLOSED_DELEG_STID || dp->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID) return 1; @@ -4679,23 +4915,31 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp) * We're assuming the state code never drops its reference * without first removing the lease. Since we're in this lease * callback (and since the lease code is serialized by the - * i_lock) we know the server hasn't removed the lease yet, and + * flc_lock) we know the server hasn't removed the lease yet, and * we know it's safe to take a reference. */ refcount_inc(&dp->dl_stid.sc_count); - nfsd4_run_cb(&dp->dl_recall); + WARN_ON_ONCE(!nfsd4_run_cb(&dp->dl_recall)); } -/* Called from break_lease() with i_lock held. */ +/* Called from break_lease() with flc_lock held. */ static bool nfsd_break_deleg_cb(struct file_lock *fl) { - bool ret = false; struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner; struct nfs4_file *fp = dp->dl_stid.sc_file; + struct nfs4_client *clp = dp->dl_stid.sc_client; + struct nfsd_net *nn; trace_nfsd_cb_recall(&dp->dl_stid); + dp->dl_recalled = true; + atomic_inc(&clp->cl_delegs_in_recall); + if (try_to_expire_client(clp)) { + nn = net_generic(clp->net, nfsd_net_id); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + } + /* * We don't want the locks code to timeout the lease for us; * we'll remove it ourself if a delegation isn't returned @@ -4703,11 +4947,9 @@ nfsd_break_deleg_cb(struct file_lock *fl) */ fl->fl_break_time = 0; - spin_lock(&fp->fi_lock); fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); - spin_unlock(&fp->fi_lock); - return ret; + return false; } /** @@ -4738,9 +4980,14 @@ static int nfsd_change_deleg_cb(struct file_lock *onlist, int arg, struct list_head *dispose) { - if (arg & F_UNLCK) + struct nfs4_delegation *dp = (struct nfs4_delegation *)onlist->fl_owner; + struct nfs4_client *clp = dp->dl_stid.sc_client; + + if (arg & F_UNLCK) { + if (dp->dl_recalled) + atomic_dec(&clp->cl_delegs_in_recall); return lease_modify(onlist, arg, dispose); - else + } else return -EAGAIN; } @@ -4937,16 +5184,19 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, .ia_valid = ATTR_SIZE, .ia_size = 0, }; + struct nfsd_attrs attrs = { + .na_iattr = &iattr, + }; if (!open->op_truncate) return 0; if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) return nfserr_inval; - return nfsd_setattr(rqstp, fh, &iattr, 0, (time64_t)0); + return nfsd_setattr(rqstp, fh, &attrs, 0, (time64_t)0); } static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, - struct nfsd4_open *open) + struct nfsd4_open *open, bool new_stp) { struct nfsd_file *nf = NULL; __be32 status; @@ -4962,6 +5212,13 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, */ status = nfs4_file_check_deny(fp, open->op_share_deny); if (status != nfs_ok) { + if (status != nfserr_share_denied) { + spin_unlock(&fp->fi_lock); + goto out; + } + if (nfs4_resolve_deny_conflicts_locked(fp, new_stp, + stp, open->op_share_deny, false)) + status = nfserr_jukebox; spin_unlock(&fp->fi_lock); goto out; } @@ -4969,6 +5226,13 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, /* set access to the file */ status = nfs4_file_get_access(fp, open->op_share_access); if (status != nfs_ok) { + if (status != nfserr_share_denied) { + spin_unlock(&fp->fi_lock); + goto out; + } + if (nfs4_resolve_deny_conflicts_locked(fp, new_stp, + stp, open->op_share_access, true)) + status = nfserr_jukebox; spin_unlock(&fp->fi_lock); goto out; } @@ -4984,9 +5248,12 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, if (!fp->fi_fds[oflag]) { spin_unlock(&fp->fi_lock); - status = nfsd_file_acquire(rqstp, cur_fh, access, &nf); - if (status) + + status = nfsd_file_acquire_opened(rqstp, cur_fh, access, + open->op_filp, &nf); + if (status != nfs_ok) goto out_put_access; + spin_lock(&fp->fi_lock); if (!fp->fi_fds[oflag]) { fp->fi_fds[oflag] = nf; @@ -5015,21 +5282,30 @@ out_put_access: } static __be32 -nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open) +nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, + struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, + struct nfsd4_open *open) { __be32 status; unsigned char old_deny_bmap = stp->st_deny_bmap; if (!test_access(open->op_share_access, stp)) - return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open); + return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open, false); /* test and set deny mode */ spin_lock(&fp->fi_lock); status = nfs4_file_check_deny(fp, open->op_share_deny); - if (status == nfs_ok) { + switch (status) { + case nfs_ok: set_deny(open->op_share_deny, stp); fp->fi_share_deny |= - (open->op_share_deny & NFS4_SHARE_DENY_BOTH); + (open->op_share_deny & NFS4_SHARE_DENY_BOTH); + break; + case nfserr_share_denied: + if (nfs4_resolve_deny_conflicts_locked(fp, false, + stp, open->op_share_deny, false)) + status = nfserr_jukebox; + break; } spin_unlock(&fp->fi_lock); @@ -5132,11 +5408,59 @@ static int nfsd4_check_conflicting_opens(struct nfs4_client *clp, return 0; } +/* + * It's possible that between opening the dentry and setting the delegation, + * that it has been renamed or unlinked. Redo the lookup to verify that this + * hasn't happened. + */ +static int +nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp, + struct svc_fh *parent) +{ + struct svc_export *exp; + struct dentry *child; + __be32 err; + + err = nfsd_lookup_dentry(open->op_rqstp, parent, + open->op_fname, open->op_fnamelen, + &exp, &child); + + if (err) + return -EAGAIN; + + exp_put(exp); + dput(child); + if (child != file_dentry(fp->fi_deleg_file->nf_file)) + return -EAGAIN; + + return 0; +} + +/* + * We avoid breaking delegations held by a client due to its own activity, but + * clearing setuid/setgid bits on a write is an implicit activity and the client + * may not notice and continue using the old mode. Avoid giving out a delegation + * on setuid/setgid files when the client is requesting an open for write. + */ +static int +nfsd4_verify_setuid_write(struct nfsd4_open *open, struct nfsd_file *nf) +{ + struct inode *inode = file_inode(nf->nf_file); + + if ((open->op_share_access & NFS4_SHARE_ACCESS_WRITE) && + (inode->i_mode & (S_ISUID|S_ISGID))) + return -EAGAIN; + return 0; +} + static struct nfs4_delegation * -nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, - struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate) +nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, + struct svc_fh *parent) { int status = 0; + struct nfs4_client *clp = stp->st_stid.sc_client; + struct nfs4_file *fp = stp->st_stid.sc_file; + struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate; struct nfs4_delegation *dp; struct nfsd_file *nf; struct file_lock *fl; @@ -5162,6 +5486,8 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, spin_lock(&fp->fi_lock); if (nfs4_delegation_exists(clp, fp)) status = -EAGAIN; + else if (nfsd4_verify_setuid_write(open, nf)) + status = -EAGAIN; else if (!fp->fi_deleg_file) { fp->fi_deleg_file = nf; /* increment early to prevent fi_deleg_file from being @@ -5178,7 +5504,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, return ERR_PTR(status); status = -ENOMEM; - dp = alloc_init_deleg(clp, fp, fh, odstate); + dp = alloc_init_deleg(clp, fp, odstate); if (!dp) goto out_delegees; @@ -5191,16 +5517,32 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, locks_free_lock(fl); if (status) goto out_clnt_odstate; + + if (parent) { + status = nfsd4_verify_deleg_dentry(open, fp, parent); + if (status) + goto out_unlock; + } + status = nfsd4_check_conflicting_opens(clp, fp); if (status) goto out_unlock; + /* + * Now that the deleg is set, check again to ensure that nothing + * raced in and changed the mode while we weren't lookng. + */ + status = nfsd4_verify_setuid_write(open, fp->fi_deleg_file); + if (status) + goto out_unlock; + + status = -EAGAIN; + if (fp->fi_had_conflict) + goto out_unlock; + spin_lock(&state_lock); spin_lock(&fp->fi_lock); - if (fp->fi_had_conflict) - status = -EAGAIN; - else - status = hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); @@ -5246,12 +5588,13 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) * proper support for them. */ static void -nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, - struct nfs4_ol_stateid *stp) +nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, + struct svc_fh *currentfh) { struct nfs4_delegation *dp; struct nfs4_openowner *oo = openowner(stp->st_stateowner); struct nfs4_client *clp = stp->st_stid.sc_client; + struct svc_fh *parent = NULL; int cb_up; int status = 0; @@ -5265,6 +5608,8 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, goto out_no_deleg; break; case NFS4_OPEN_CLAIM_NULL: + parent = currentfh; + fallthrough; case NFS4_OPEN_CLAIM_FH: /* * Let's not give out any delegations till everyone's @@ -5279,7 +5624,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, default: goto out_no_deleg; } - dp = nfs4_set_delegation(clp, fh, stp->st_stid.sc_file, stp->st_clnt_odstate); + dp = nfs4_set_delegation(open, stp, parent); if (IS_ERR(dp)) goto out_no_deleg; @@ -5321,6 +5666,18 @@ static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open, */ } +/** + * nfsd4_process_open2 - finish open processing + * @rqstp: the RPC transaction being executed + * @current_fh: NFSv4 COMPOUND's current filehandle + * @open: OPEN arguments + * + * If successful, (1) truncate the file if open->op_truncate was + * set, (2) set open->op_stateid, (3) set open->op_delegation. + * + * Returns %nfs_ok on success; otherwise an nfs4stat value in + * network byte order is returned. + */ __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open) { @@ -5337,7 +5694,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf * and check for delegations in the process of being recalled. * If not found, create the nfs4_file struct */ - fp = find_or_add_file(open->op_file, current_fh); + fp = nfsd4_file_hash_insert(open->op_file, current_fh); + if (unlikely(!fp)) + return nfserr_jukebox; if (fp != open->op_file) { status = nfs4_check_deleg(cl, open, &dp); if (status) @@ -5370,7 +5729,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf goto out; } } else { - status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open); + status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open, true); if (status) { stp->st_stid.sc_type = NFS4_CLOSED_STID; release_open_stateid(stp); @@ -5399,7 +5758,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf * Attempt to hand out a delegation. No error return, because the * OPEN succeeds even if we fail. */ - nfs4_open_delegation(current_fh, open, stp); + nfs4_open_delegation(open, stp, &resp->cstate.current_fh); nodeleg: status = nfs_ok; trace_nfsd_open(&stp->st_stid.sc_stateid); @@ -5573,7 +5932,7 @@ static void nfsd4_ssc_shutdown_umount(struct nfsd_net *nn) static void nfsd4_ssc_expire_umount(struct nfsd_net *nn) { bool do_wakeup = false; - struct nfsd4_ssc_umount_item *ni = 0; + struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *tmp; spin_lock(&nn->nfsd_ssc_lock); @@ -5604,10 +5963,131 @@ static void nfsd4_ssc_expire_umount(struct nfsd_net *nn) } #endif +/* Check if any lock belonging to this lockowner has any blockers */ +static bool +nfs4_lockowner_has_blockers(struct nfs4_lockowner *lo) +{ + struct file_lock_context *ctx; + struct nfs4_ol_stateid *stp; + struct nfs4_file *nf; + + list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { + nf = stp->st_stid.sc_file; + ctx = locks_inode_context(nf->fi_inode); + if (!ctx) + continue; + if (locks_owner_has_blockers(ctx, lo)) + return true; + } + return false; +} + +static bool +nfs4_anylock_blockers(struct nfs4_client *clp) +{ + int i; + struct nfs4_stateowner *so; + struct nfs4_lockowner *lo; + + if (atomic_read(&clp->cl_delegs_in_recall)) + return true; + spin_lock(&clp->cl_lock); + for (i = 0; i < OWNER_HASH_SIZE; i++) { + list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[i], + so_strhash) { + if (so->so_is_open_owner) + continue; + lo = lockowner(so); + if (nfs4_lockowner_has_blockers(lo)) { + spin_unlock(&clp->cl_lock); + return true; + } + } + } + spin_unlock(&clp->cl_lock); + return false; +} + +static void +nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist, + struct laundry_time *lt) +{ + unsigned int maxreap, reapcnt = 0; + struct list_head *pos, *next; + struct nfs4_client *clp; + + maxreap = (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) ? + NFSD_CLIENT_MAX_TRIM_PER_RUN : 0; + INIT_LIST_HEAD(reaplist); + spin_lock(&nn->client_lock); + list_for_each_safe(pos, next, &nn->client_lru) { + clp = list_entry(pos, struct nfs4_client, cl_lru); + if (clp->cl_state == NFSD4_EXPIRABLE) + goto exp_client; + if (!state_expired(lt, clp->cl_time)) + break; + if (!atomic_read(&clp->cl_rpc_users)) { + if (clp->cl_state == NFSD4_ACTIVE) + atomic_inc(&nn->nfsd_courtesy_clients); + clp->cl_state = NFSD4_COURTESY; + } + if (!client_has_state(clp)) + goto exp_client; + if (!nfs4_anylock_blockers(clp)) + if (reapcnt >= maxreap) + continue; +exp_client: + if (!mark_client_expired_locked(clp)) { + list_add(&clp->cl_lru, reaplist); + reapcnt++; + } + } + spin_unlock(&nn->client_lock); +} + +static void +nfs4_get_courtesy_client_reaplist(struct nfsd_net *nn, + struct list_head *reaplist) +{ + unsigned int maxreap = 0, reapcnt = 0; + struct list_head *pos, *next; + struct nfs4_client *clp; + + maxreap = NFSD_CLIENT_MAX_TRIM_PER_RUN; + INIT_LIST_HEAD(reaplist); + + spin_lock(&nn->client_lock); + list_for_each_safe(pos, next, &nn->client_lru) { + clp = list_entry(pos, struct nfs4_client, cl_lru); + if (clp->cl_state == NFSD4_ACTIVE) + break; + if (reapcnt >= maxreap) + break; + if (!mark_client_expired_locked(clp)) { + list_add(&clp->cl_lru, reaplist); + reapcnt++; + } + } + spin_unlock(&nn->client_lock); +} + +static void +nfs4_process_client_reaplist(struct list_head *reaplist) +{ + struct list_head *pos, *next; + struct nfs4_client *clp; + + list_for_each_safe(pos, next, reaplist) { + clp = list_entry(pos, struct nfs4_client, cl_lru); + trace_nfsd_clid_purged(&clp->cl_clientid); + list_del_init(&clp->cl_lru); + expire_client(clp); + } +} + static time64_t nfs4_laundromat(struct nfsd_net *nn) { - struct nfs4_client *clp; struct nfs4_openowner *oo; struct nfs4_delegation *dp; struct nfs4_ol_stateid *stp; @@ -5626,33 +6106,18 @@ nfs4_laundromat(struct nfsd_net *nn) goto out; } nfsd4_end_grace(nn); - INIT_LIST_HEAD(&reaplist); spin_lock(&nn->s2s_cp_lock); idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) { cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); - if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID && + if (cps->cp_stateid.cs_type == NFS4_COPYNOTIFY_STID && state_expired(<, cps->cpntf_time)) _free_cpntf_state_locked(nn, cps); } spin_unlock(&nn->s2s_cp_lock); + nfs4_get_client_reaplist(nn, &reaplist, <); + nfs4_process_client_reaplist(&reaplist); - spin_lock(&nn->client_lock); - list_for_each_safe(pos, next, &nn->client_lru) { - clp = list_entry(pos, struct nfs4_client, cl_lru); - if (!state_expired(<, clp->cl_time)) - break; - if (mark_client_expired_locked(clp)) - continue; - list_add(&clp->cl_lru, &reaplist); - } - spin_unlock(&nn->client_lock); - list_for_each_safe(pos, next, &reaplist) { - clp = list_entry(pos, struct nfs4_client, cl_lru); - trace_nfsd_clid_purged(&clp->cl_clientid); - list_del_init(&clp->cl_lru); - expire_client(clp); - } spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); @@ -5721,7 +6186,6 @@ out: return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); } -static struct workqueue_struct *laundry_wq; static void laundromat_main(struct work_struct *); static void @@ -5736,6 +6200,64 @@ laundromat_main(struct work_struct *laundry) queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } +static void +courtesy_client_reaper(struct nfsd_net *nn) +{ + struct list_head reaplist; + + nfs4_get_courtesy_client_reaplist(nn, &reaplist); + nfs4_process_client_reaplist(&reaplist); +} + +static void +deleg_reaper(struct nfsd_net *nn) +{ + struct list_head *pos, *next; + struct nfs4_client *clp; + struct list_head cblist; + + INIT_LIST_HEAD(&cblist); + spin_lock(&nn->client_lock); + list_for_each_safe(pos, next, &nn->client_lru) { + clp = list_entry(pos, struct nfs4_client, cl_lru); + if (clp->cl_state != NFSD4_ACTIVE || + list_empty(&clp->cl_delegations) || + atomic_read(&clp->cl_delegs_in_recall) || + test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags) || + (ktime_get_boottime_seconds() - + clp->cl_ra_time < 5)) { + continue; + } + list_add(&clp->cl_ra_cblist, &cblist); + + /* release in nfsd4_cb_recall_any_release */ + kref_get(&clp->cl_nfsdfs.cl_ref); + set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); + clp->cl_ra_time = ktime_get_boottime_seconds(); + } + spin_unlock(&nn->client_lock); + + while (!list_empty(&cblist)) { + clp = list_first_entry(&cblist, struct nfs4_client, + cl_ra_cblist); + list_del_init(&clp->cl_ra_cblist); + clp->cl_ra->ra_keep = 0; + clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG); + trace_nfsd_cb_recall_any(clp->cl_ra); + nfsd4_run_cb(&clp->cl_ra->ra_cb); + } +} + +static void +nfsd4_state_shrinker_worker(struct work_struct *work) +{ + struct nfsd_net *nn = container_of(work, struct nfsd_net, + nfsd_shrinker_work); + + courtesy_client_reaper(nn); + deleg_reaper(nn); +} + static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) { if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) @@ -5869,6 +6391,7 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, struct nfs4_stid **s, struct nfsd_net *nn) { __be32 status; + struct nfs4_stid *stid; bool return_revoked = false; /* @@ -5891,15 +6414,16 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, } if (status) return status; - *s = find_stateid_by_type(cstate->clp, stateid, typemask); - if (!*s) + stid = find_stateid_by_type(cstate->clp, stateid, typemask); + if (!stid) return nfserr_bad_stateid; - if (((*s)->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) { - nfs4_put_stid(*s); + if ((stid->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) { + nfs4_put_stid(stid); if (cstate->minorversion) return nfserr_deleg_revoked; return nfserr_bad_stateid; } + *s = stid; return nfs_ok; } @@ -5964,12 +6488,12 @@ out: static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) { - WARN_ON_ONCE(cps->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID); - if (!refcount_dec_and_test(&cps->cp_stateid.sc_count)) + WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID); + if (!refcount_dec_and_test(&cps->cp_stateid.cs_count)) return; list_del(&cps->cp_list); idr_remove(&nn->s2s_cp_stateids, - cps->cp_stateid.stid.si_opaque.so_id); + cps->cp_stateid.cs_stid.si_opaque.so_id); kfree(cps); } /* @@ -5991,12 +6515,12 @@ __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st, if (cps_t) { state = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); - if (state->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID) { + if (state->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID) { state = NULL; goto unlock; } if (!clp) - refcount_inc(&state->cp_stateid.sc_count); + refcount_inc(&state->cp_stateid.cs_count); else _free_cpntf_state_locked(nn, state); } @@ -6498,6 +7022,8 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto put_stateid; + trace_nfsd_deleg_return(stateid); + wake_up_var(d_inode(cstate->current_fh.fh_dentry)); destroy_delegation(dp); put_stateid: nfs4_put_stid(&dp->dl_stid); @@ -6534,7 +7060,7 @@ nfs4_transform_lock_offset(struct file_lock *lock) } static fl_owner_t -nfsd4_fl_get_owner(fl_owner_t owner) +nfsd4_lm_get_owner(fl_owner_t owner) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; @@ -6543,7 +7069,7 @@ nfsd4_fl_get_owner(fl_owner_t owner) } static void -nfsd4_fl_put_owner(fl_owner_t owner) +nfsd4_lm_put_owner(fl_owner_t owner) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; @@ -6551,6 +7077,29 @@ nfsd4_fl_put_owner(fl_owner_t owner) nfs4_put_stateowner(&lo->lo_owner); } +/* return pointer to struct nfs4_client if client is expirable */ +static bool +nfsd4_lm_lock_expirable(struct file_lock *cfl) +{ + struct nfs4_lockowner *lo = (struct nfs4_lockowner *)cfl->fl_owner; + struct nfs4_client *clp = lo->lo_owner.so_client; + struct nfsd_net *nn; + + if (try_to_expire_client(clp)) { + nn = net_generic(clp->net, nfsd_net_id); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + return true; + } + return false; +} + +/* schedule laundromat to run immediately and wait for it to complete */ +static void +nfsd4_lm_expire_lock(void) +{ + flush_workqueue(laundry_wq); +} + static void nfsd4_lm_notify(struct file_lock *fl) { @@ -6577,9 +7126,12 @@ nfsd4_lm_notify(struct file_lock *fl) } static const struct lock_manager_operations nfsd_posix_mng_ops = { + .lm_mod_owner = THIS_MODULE, .lm_notify = nfsd4_lm_notify, - .lm_get_owner = nfsd4_fl_get_owner, - .lm_put_owner = nfsd4_fl_put_owner, + .lm_get_owner = nfsd4_lm_get_owner, + .lm_put_owner = nfsd4_lm_put_owner, + .lm_lock_expirable = nfsd4_lm_lock_expirable, + .lm_expire_lock = nfsd4_lm_expire_lock, }; static inline void @@ -6942,8 +7494,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: - if (nfsd4_has_session(cstate) && - !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS)) + if (nfsd4_has_session(cstate) || + exportfs_lock_op_is_async(sb->s_export_op)) fl_flags |= FL_SLEEP; fallthrough; case NFS4_READ_LT: @@ -6955,8 +7507,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fl_type = F_RDLCK; break; case NFS4_WRITEW_LT: - if (nfsd4_has_session(cstate) && - !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS)) + if (nfsd4_has_session(cstate) || + exportfs_lock_op_is_async(sb->s_export_op)) fl_flags |= FL_SLEEP; fallthrough; case NFS4_WRITE_LT: @@ -6977,6 +7529,16 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } + /* + * Most filesystems with their own ->lock operations will block + * the nfsd thread waiting to acquire the lock. That leads to + * deadlocks (we don't want every nfsd thread tied up waiting + * for file locks), so don't attempt blocking lock notifications + * on those filesystems: + */ + if (!exportfs_lock_op_is_async(sb->s_export_op)) + fl_flags &= ~FL_SLEEP; + nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn); if (!nbl) { dprintk("NFSD: %s: unable to allocate block!\n", __func__); @@ -7007,6 +7569,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, spin_lock(&nn->blocked_locks_lock); list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked); list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru); + kref_get(&nbl->nbl_kref); spin_unlock(&nn->blocked_locks_lock); } @@ -7019,6 +7582,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nn->somebody_reclaimed = true; break; case FILE_LOCK_DEFERRED: + kref_put(&nbl->nbl_kref, free_nbl); nbl = NULL; fallthrough; case -EAGAIN: /* conflock holds conflicting lock */ @@ -7039,8 +7603,13 @@ out: /* dequeue it if we queued it before */ if (fl_flags & FL_SLEEP) { spin_lock(&nn->blocked_locks_lock); - list_del_init(&nbl->nbl_list); - list_del_init(&nbl->nbl_lru); + if (!list_empty(&nbl->nbl_list) && + !list_empty(&nbl->nbl_lru)) { + list_del_init(&nbl->nbl_list); + list_del_init(&nbl->nbl_lru); + kref_put(&nbl->nbl_kref, free_nbl); + } + /* nbl can use one of lists to be linked to reaplist */ spin_unlock(&nn->blocked_locks_lock); } free_blocked_lock(nbl); @@ -7081,21 +7650,22 @@ out: static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock) { struct nfsd_file *nf; + struct inode *inode; __be32 err; err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf); if (err) return err; - fh_lock(fhp); /* to block new leases till after test_lock: */ - err = nfserrno(nfsd_open_break_lease(fhp->fh_dentry->d_inode, - NFSD_MAY_READ)); + inode = fhp->fh_dentry->d_inode; + inode_lock(inode); /* to block new leases till after test_lock: */ + err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (err) goto out; lock->fl_file = nf->nf_file; err = nfserrno(vfs_test_lock(nf->nf_file, lock)); lock->fl_file = NULL; out: - fh_unlock(fhp); + inode_unlock(inode); nfsd_file_put(nf); return err; } @@ -7257,18 +7827,20 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { struct file_lock *fl; int status = false; - struct nfsd_file *nf = find_any_file(fp); + struct nfsd_file *nf; struct inode *inode; struct file_lock_context *flctx; + spin_lock(&fp->fi_lock); + nf = find_any_file_locked(fp); if (!nf) { /* Any valid lock stateid should have some sort of access */ WARN_ON_ONCE(1); - return status; + goto out; } inode = locks_inode(nf->nf_file); - flctx = inode->i_flctx; + flctx = locks_inode_context(inode); if (flctx && !list_empty_careful(&flctx->flc_posix)) { spin_lock(&flctx->flc_lock); @@ -7280,26 +7852,39 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) } spin_unlock(&flctx->flc_lock); } - nfsd_file_put(nf); +out: + spin_unlock(&fp->fi_lock); return status; } +/** + * nfsd4_release_lockowner - process NFSv4.0 RELEASE_LOCKOWNER operations + * @rqstp: RPC transaction + * @cstate: NFSv4 COMPOUND state + * @u: RELEASE_LOCKOWNER arguments + * + * Check if theree are any locks still held and if not - free the lockowner + * and any lock state that is owned. + * + * Return values: + * %nfs_ok: lockowner released or not found + * %nfserr_locks_held: lockowner still in use + * %nfserr_stale_clientid: clientid no longer active + * %nfserr_expired: clientid not recognized + */ __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); clientid_t *clid = &rlockowner->rl_clientid; - struct nfs4_stateowner *sop; - struct nfs4_lockowner *lo = NULL; struct nfs4_ol_stateid *stp; - struct xdr_netobj *owner = &rlockowner->rl_owner; - unsigned int hashval = ownerstr_hashval(owner); - __be32 status; - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct nfs4_lockowner *lo; struct nfs4_client *clp; - LIST_HEAD (reaplist); + LIST_HEAD(reaplist); + __be32 status; dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n", clid->cl_boot, clid->cl_id); @@ -7307,30 +7892,22 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, status = set_client(clid, cstate, nn); if (status) return status; - clp = cstate->clp; - /* Find the matching lock stateowner */ - spin_lock(&clp->cl_lock); - list_for_each_entry(sop, &clp->cl_ownerstr_hashtbl[hashval], - so_strhash) { - if (sop->so_is_open_owner || !same_owner_str(sop, owner)) - continue; + spin_lock(&clp->cl_lock); + lo = find_lockowner_str_locked(clp, &rlockowner->rl_owner); + if (!lo) { + spin_unlock(&clp->cl_lock); + return nfs_ok; + } - if (atomic_read(&sop->so_count) != 1) { + list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { + if (check_for_locks(stp->st_stid.sc_file, lo)) { spin_unlock(&clp->cl_lock); + nfs4_put_stateowner(&lo->lo_owner); return nfserr_locks_held; } - - lo = lockowner(sop); - nfs4_get_stateowner(sop); - break; - } - if (!lo) { - spin_unlock(&clp->cl_lock); - return status; } - unhash_lockowner_locked(lo); while (!list_empty(&lo->lo_owner.so_stateids)) { stp = list_first_entry(&lo->lo_owner.so_stateids, @@ -7340,11 +7917,11 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, put_ol_stateid_locked(stp, &reaplist); } spin_unlock(&clp->cl_lock); + free_ol_stateid_reaplist(&reaplist); remove_blocked_locks(lo); nfs4_put_stateowner(&lo->lo_owner); - - return status; + return nfs_ok; } static inline struct nfs4_client_reclaim * @@ -7510,10 +8087,20 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->blocked_locks_lru); INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); + INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net); + nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; + nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; + nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; + + if (register_shrinker(&nn->nfsd_client_shrinker)) + goto err_shrinker; return 0; +err_shrinker: + put_net(net); + kfree(nn->sessionid_hashtbl); err_sessionid: kfree(nn->unconf_id_hashtbl); err_unconf_id: @@ -7585,22 +8172,18 @@ nfs4_state_start(void) { int ret; - laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4"); - if (laundry_wq == NULL) { - ret = -ENOMEM; - goto out; - } - ret = nfsd4_create_callback_queue(); + ret = rhltable_init(&nfs4_file_rhltable, &nfs4_file_rhash_params); if (ret) - goto out_free_laundry; + return ret; + + ret = nfsd4_create_callback_queue(); + if (ret) { + rhltable_destroy(&nfs4_file_rhltable); + return ret; + } set_max_delegations(); return 0; - -out_free_laundry: - destroy_workqueue(laundry_wq); -out: - return ret; } void @@ -7610,6 +8193,8 @@ nfs4_state_shutdown_net(struct net *net) struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + unregister_shrinker(&nn->nfsd_client_shrinker); + cancel_work(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); @@ -7637,8 +8222,8 @@ nfs4_state_shutdown_net(struct net *net) void nfs4_state_shutdown(void) { - destroy_workqueue(laundry_wq); nfsd4_destroy_callback_queue(); + rhltable_destroy(&nfs4_file_rhltable); } static void diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index d28b75909de8..5b95499a1f34 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -42,6 +42,8 @@ #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/addr.h> #include <linux/xattr.h> +#include <linux/vmalloc.h> + #include <uapi/linux/xattr.h> #include "idmap.h" @@ -277,21 +279,10 @@ nfsd4_decode_verifier4(struct nfsd4_compoundargs *argp, nfs4_verifier *verf) static __be32 nfsd4_decode_bitmap4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen) { - u32 i, count; - __be32 *p; - - if (xdr_stream_decode_u32(argp->xdr, &count) < 0) - return nfserr_bad_xdr; - /* request sanity */ - if (count > 1000) - return nfserr_bad_xdr; - p = xdr_inline_decode(argp->xdr, count << 2); - if (!p) - return nfserr_bad_xdr; - for (i = 0; i < bmlen; i++) - bmval[i] = (i < count) ? be32_to_cpup(p++) : 0; + ssize_t status; - return nfs_ok; + status = xdr_stream_decode_uint32_array(argp->xdr, bmval, bmlen); + return status == -EBADMSG ? nfserr_bad_xdr : nfs_ok; } static __be32 @@ -481,6 +472,15 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen, return nfserr_bad_xdr; } } + if (bmval[1] & FATTR4_WORD1_TIME_CREATE) { + struct timespec64 ts; + + /* No Linux filesystem supports setting this attribute. */ + bmval[1] &= ~FATTR4_WORD1_TIME_CREATE; + status = nfsd4_decode_nfstime4(argp, &ts); + if (status) + return status; + } if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) { u32 set_it; @@ -770,16 +770,18 @@ nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_cb_sec *cbs) static __be32 nfsd4_decode_access(struct nfsd4_compoundargs *argp, - struct nfsd4_access *access) + union nfsd4_op_u *u) { + struct nfsd4_access *access = &u->access; if (xdr_stream_decode_u32(argp->xdr, &access->ac_req_access) < 0) return nfserr_bad_xdr; return nfs_ok; } static __be32 -nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close) +nfsd4_decode_close(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_close *close = &u->close; if (xdr_stream_decode_u32(argp->xdr, &close->cl_seqid) < 0) return nfserr_bad_xdr; return nfsd4_decode_stateid4(argp, &close->cl_stateid); @@ -787,20 +789,24 @@ nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close) static __be32 -nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit) +nfsd4_decode_commit(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_commit *commit = &u->commit; if (xdr_stream_decode_u64(argp->xdr, &commit->co_offset) < 0) return nfserr_bad_xdr; if (xdr_stream_decode_u32(argp->xdr, &commit->co_count) < 0) return nfserr_bad_xdr; + memset(&commit->co_verf, 0, sizeof(commit->co_verf)); return nfs_ok; } static __be32 -nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create) +nfsd4_decode_create(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_create *create = &u->create; __be32 *p, status; + memset(create, 0, sizeof(*create)); if (xdr_stream_decode_u32(argp->xdr, &create->cr_type) < 0) return nfserr_bad_xdr; switch (create->cr_type) { @@ -842,21 +848,26 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create } static inline __be32 -nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, struct nfsd4_delegreturn *dr) +nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_delegreturn *dr = &u->delegreturn; return nfsd4_decode_stateid4(argp, &dr->dr_stateid); } static inline __be32 -nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, struct nfsd4_getattr *getattr) +nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_getattr *getattr = &u->getattr; + memset(getattr, 0, sizeof(*getattr)); return nfsd4_decode_bitmap4(argp, getattr->ga_bmval, ARRAY_SIZE(getattr->ga_bmval)); } static __be32 -nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link) +nfsd4_decode_link(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_link *link = &u->link; + memset(link, 0, sizeof(*link)); return nfsd4_decode_component4(argp, &link->li_name, &link->li_namelen); } @@ -903,8 +914,10 @@ nfsd4_decode_locker4(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) } static __be32 -nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) +nfsd4_decode_lock(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lock *lock = &u->lock; + memset(lock, 0, sizeof(*lock)); if (xdr_stream_decode_u32(argp->xdr, &lock->lk_type) < 0) return nfserr_bad_xdr; if ((lock->lk_type < NFS4_READ_LT) || (lock->lk_type > NFS4_WRITEW_LT)) @@ -919,8 +932,10 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) } static __be32 -nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt) +nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lockt *lockt = &u->lockt; + memset(lockt, 0, sizeof(*lockt)); if (xdr_stream_decode_u32(argp->xdr, &lockt->lt_type) < 0) return nfserr_bad_xdr; if ((lockt->lt_type < NFS4_READ_LT) || (lockt->lt_type > NFS4_WRITEW_LT)) @@ -934,8 +949,9 @@ nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt) } static __be32 -nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) +nfsd4_decode_locku(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_locku *locku = &u->locku; __be32 status; if (xdr_stream_decode_u32(argp->xdr, &locku->lu_type) < 0) @@ -956,8 +972,9 @@ nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) } static __be32 -nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup) +nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lookup *lookup = &u->lookup; return nfsd4_decode_component4(argp, &lookup->lo_name, &lookup->lo_len); } @@ -1137,16 +1154,14 @@ nfsd4_decode_open_claim4(struct nfsd4_compoundargs *argp, } static __be32 -nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) +nfsd4_decode_open(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_open *open = &u->open; __be32 status; u32 dummy; - memset(open->op_bmval, 0, sizeof(open->op_bmval)); - open->op_iattr.ia_valid = 0; - open->op_openowner = NULL; + memset(open, 0, sizeof(*open)); - open->op_xdr_error = 0; if (xdr_stream_decode_u32(argp->xdr, &open->op_seqid) < 0) return nfserr_bad_xdr; /* deleg_want is ignored */ @@ -1168,8 +1183,10 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) } static __be32 -nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_confirm *open_conf) +nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_open_confirm *open_conf = &u->open_confirm; __be32 status; if (argp->minorversion >= 1) @@ -1181,14 +1198,19 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con if (xdr_stream_decode_u32(argp->xdr, &open_conf->oc_seqid) < 0) return nfserr_bad_xdr; + memset(&open_conf->oc_resp_stateid, 0, + sizeof(open_conf->oc_resp_stateid)); return nfs_ok; } static __be32 -nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_downgrade *open_down) +nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_open_downgrade *open_down = &u->open_downgrade; __be32 status; + memset(open_down, 0, sizeof(*open_down)); status = nfsd4_decode_stateid4(argp, &open_down->od_stateid); if (status) return status; @@ -1203,8 +1225,9 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d } static __be32 -nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) +nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_putfh *putfh = &u->putfh; __be32 *p; if (xdr_stream_decode_u32(argp->xdr, &putfh->pf_fhlen) < 0) @@ -1218,11 +1241,12 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) if (!putfh->pf_fhval) return nfserr_jukebox; + putfh->no_verify = false; return nfs_ok; } static __be32 -nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { if (argp->minorversion == 0) return nfs_ok; @@ -1230,10 +1254,12 @@ nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, void *p) } static __be32 -nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) +nfsd4_decode_read(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_read *read = &u->read; __be32 status; + memset(read, 0, sizeof(*read)); status = nfsd4_decode_stateid4(argp, &read->rd_stateid); if (status) return status; @@ -1246,10 +1272,12 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) } static __be32 -nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *readdir) +nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_readdir *readdir = &u->readdir; __be32 status; + memset(readdir, 0, sizeof(*readdir)); if (xdr_stream_decode_u64(argp->xdr, &readdir->rd_cookie) < 0) return nfserr_bad_xdr; status = nfsd4_decode_verifier4(argp, &readdir->rd_verf); @@ -1267,16 +1295,20 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read } static __be32 -nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove) +nfsd4_decode_remove(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_remove *remove = &u->remove; + memset(&remove->rm_cinfo, 0, sizeof(remove->rm_cinfo)); return nfsd4_decode_component4(argp, &remove->rm_name, &remove->rm_namelen); } static __be32 -nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename) +nfsd4_decode_rename(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_rename *rename = &u->rename; __be32 status; + memset(rename, 0, sizeof(*rename)); status = nfsd4_decode_component4(argp, &rename->rn_sname, &rename->rn_snamelen); if (status) return status; @@ -1284,23 +1316,28 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename } static __be32 -nfsd4_decode_renew(struct nfsd4_compoundargs *argp, clientid_t *clientid) +nfsd4_decode_renew(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + clientid_t *clientid = &u->renew; return nfsd4_decode_clientid4(argp, clientid); } static __be32 nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp, - struct nfsd4_secinfo *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo *secinfo = &u->secinfo; + secinfo->si_exp = NULL; return nfsd4_decode_component4(argp, &secinfo->si_name, &secinfo->si_namelen); } static __be32 -nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr) +nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_setattr *setattr = &u->setattr; __be32 status; + memset(setattr, 0, sizeof(*setattr)); status = nfsd4_decode_stateid4(argp, &setattr->sa_stateid); if (status) return status; @@ -1311,10 +1348,13 @@ nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *seta } static __be32 -nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclientid *setclientid) +nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_setclientid *setclientid = &u->setclientid; __be32 *p, status; + memset(setclientid, 0, sizeof(*setclientid)); + if (argp->minorversion >= 1) return nfserr_notsupp; @@ -1352,8 +1392,10 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient } static __be32 -nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_setclientid_confirm *scd_c) +nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_setclientid_confirm *scd_c = &u->setclientid_confirm; __be32 status; if (argp->minorversion >= 1) @@ -1367,10 +1409,13 @@ nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_s /* Also used for NVERIFY */ static __be32 -nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify) +nfsd4_decode_verify(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_verify *verify = &u->verify; __be32 *p, status; + memset(verify, 0, sizeof(*verify)); + status = nfsd4_decode_bitmap4(argp, verify->ve_bmval, ARRAY_SIZE(verify->ve_bmval)); if (status) @@ -1392,8 +1437,9 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify } static __be32 -nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) +nfsd4_decode_write(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_write *write = &u->write; __be32 status; status = nfsd4_decode_stateid4(argp, &write->wr_stateid); @@ -1410,12 +1456,17 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) if (!xdr_stream_subsegment(argp->xdr, &write->wr_payload, write->wr_buflen)) return nfserr_bad_xdr; + write->wr_bytes_written = 0; + write->wr_how_written = 0; + memset(&write->wr_verifier, 0, sizeof(write->wr_verifier)); return nfs_ok; } static __be32 -nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_release_lockowner *rlockowner) +nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; __be32 status; if (argp->minorversion >= 1) @@ -1432,18 +1483,24 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel return nfs_ok; } -static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, struct nfsd4_backchannel_ctl *bc) +static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_backchannel_ctl *bc = &u->backchannel_ctl; + memset(bc, 0, sizeof(*bc)); if (xdr_stream_decode_u32(argp->xdr, &bc->bc_cb_program) < 0) return nfserr_bad_xdr; return nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec); } -static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts) +static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; u32 use_conn_in_rdma_mode; __be32 status; + memset(bcts, 0, sizeof(*bcts)); status = nfsd4_decode_sessionid4(argp, &bcts->sessionid); if (status) return status; @@ -1581,10 +1638,12 @@ nfsd4_decode_nfs_impl_id4(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, - struct nfsd4_exchange_id *exid) + union nfsd4_op_u *u) { + struct nfsd4_exchange_id *exid = &u->exchange_id; __be32 status; + memset(exid, 0, sizeof(*exid)); status = nfsd4_decode_verifier4(argp, &exid->verifier); if (status) return status; @@ -1633,10 +1692,12 @@ nfsd4_decode_channel_attrs4(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, - struct nfsd4_create_session *sess) + union nfsd4_op_u *u) { + struct nfsd4_create_session *sess = &u->create_session; __be32 status; + memset(sess, 0, sizeof(*sess)); status = nfsd4_decode_clientid4(argp, &sess->clientid); if (status) return status; @@ -1652,34 +1713,34 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, return status; if (xdr_stream_decode_u32(argp->xdr, &sess->callback_prog) < 0) return nfserr_bad_xdr; - status = nfsd4_decode_cb_sec(argp, &sess->cb_sec); - if (status) - return status; - - return nfs_ok; + return nfsd4_decode_cb_sec(argp, &sess->cb_sec); } static __be32 nfsd4_decode_destroy_session(struct nfsd4_compoundargs *argp, - struct nfsd4_destroy_session *destroy_session) + union nfsd4_op_u *u) { + struct nfsd4_destroy_session *destroy_session = &u->destroy_session; return nfsd4_decode_sessionid4(argp, &destroy_session->sessionid); } static __be32 nfsd4_decode_free_stateid(struct nfsd4_compoundargs *argp, - struct nfsd4_free_stateid *free_stateid) + union nfsd4_op_u *u) { + struct nfsd4_free_stateid *free_stateid = &u->free_stateid; return nfsd4_decode_stateid4(argp, &free_stateid->fr_stateid); } #ifdef CONFIG_NFSD_PNFS static __be32 nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, - struct nfsd4_getdeviceinfo *gdev) + union nfsd4_op_u *u) { + struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; __be32 status; + memset(gdev, 0, sizeof(*gdev)); status = nfsd4_decode_deviceid4(argp, &gdev->gd_devid); if (status) return status; @@ -1696,10 +1757,12 @@ nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutcommit *lcp) + union nfsd4_op_u *u) { + struct nfsd4_layoutcommit *lcp = &u->layoutcommit; __be32 *p, status; + memset(lcp, 0, sizeof(*lcp)); if (xdr_stream_decode_u64(argp->xdr, &lcp->lc_seg.offset) < 0) return nfserr_bad_xdr; if (xdr_stream_decode_u64(argp->xdr, &lcp->lc_seg.length) < 0) @@ -1731,10 +1794,12 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutget *lgp) + union nfsd4_op_u *u) { + struct nfsd4_layoutget *lgp = &u->layoutget; __be32 status; + memset(lgp, 0, sizeof(*lgp)); if (xdr_stream_decode_u32(argp->xdr, &lgp->lg_signal) < 0) return nfserr_bad_xdr; if (xdr_stream_decode_u32(argp->xdr, &lgp->lg_layout_type) < 0) @@ -1758,8 +1823,10 @@ nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutreturn *lrp) + union nfsd4_op_u *u) { + struct nfsd4_layoutreturn *lrp = &u->layoutreturn; + memset(lrp, 0, sizeof(*lrp)); if (xdr_stream_decode_bool(argp->xdr, &lrp->lr_reclaim) < 0) return nfserr_bad_xdr; if (xdr_stream_decode_u32(argp->xdr, &lrp->lr_layout_type) < 0) @@ -1771,17 +1838,21 @@ nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, #endif /* CONFIG_NFSD_PNFS */ static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, - struct nfsd4_secinfo_no_name *sin) + union nfsd4_op_u *u) { + struct nfsd4_secinfo_no_name *sin = &u->secinfo_no_name; if (xdr_stream_decode_u32(argp->xdr, &sin->sin_style) < 0) return nfserr_bad_xdr; + + sin->sin_exp = NULL; return nfs_ok; } static __be32 nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, - struct nfsd4_sequence *seq) + union nfsd4_op_u *u) { + struct nfsd4_sequence *seq = &u->sequence; __be32 *p, status; status = nfsd4_decode_sessionid4(argp, &seq->sessionid); @@ -1795,16 +1866,20 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, seq->maxslots = be32_to_cpup(p++); seq->cachethis = be32_to_cpup(p); + seq->status_flags = 0; return nfs_ok; } static __be32 -nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_stateid *test_stateid) +nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct nfsd4_test_stateid_id *stateid; __be32 status; u32 i; + memset(test_stateid, 0, sizeof(*test_stateid)); if (xdr_stream_decode_u32(argp->xdr, &test_stateid->ts_num_ids) < 0) return nfserr_bad_xdr; @@ -1812,7 +1887,7 @@ nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_sta for (i = 0; i < test_stateid->ts_num_ids; i++) { stateid = svcxdr_tmpalloc(argp, sizeof(*stateid)); if (!stateid) - return nfserrno(-ENOMEM); /* XXX: not jukebox? */ + return nfserr_jukebox; INIT_LIST_HEAD(&stateid->ts_id_list); list_add_tail(&stateid->ts_id_list, &test_stateid->ts_stateid_list); status = nfsd4_decode_stateid4(argp, &stateid->ts_id_stateid); @@ -1824,14 +1899,16 @@ nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_sta } static __be32 nfsd4_decode_destroy_clientid(struct nfsd4_compoundargs *argp, - struct nfsd4_destroy_clientid *dc) + union nfsd4_op_u *u) { + struct nfsd4_destroy_clientid *dc = &u->destroy_clientid; return nfsd4_decode_clientid4(argp, &dc->clientid); } static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, - struct nfsd4_reclaim_complete *rc) + union nfsd4_op_u *u) { + struct nfsd4_reclaim_complete *rc = &u->reclaim_complete; if (xdr_stream_decode_bool(argp->xdr, &rc->rca_one_fs) < 0) return nfserr_bad_xdr; return nfs_ok; @@ -1839,8 +1916,9 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp, - struct nfsd4_fallocate *fallocate) + union nfsd4_op_u *u) { + struct nfsd4_fallocate *fallocate = &u->allocate; __be32 status; status = nfsd4_decode_stateid4(argp, &fallocate->falloc_stateid); @@ -1896,12 +1974,14 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp, } static __be32 -nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) +nfsd4_decode_copy(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_copy *copy = &u->copy; + u32 consecutive, i, count, sync; struct nl4_server *ns_dummy; - u32 consecutive, i, count; __be32 status; + memset(copy, 0, sizeof(*copy)); status = nfsd4_decode_stateid4(argp, ©->cp_src_stateid); if (status) return status; @@ -1917,25 +1997,28 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) /* ca_consecutive: we always do consecutive copies */ if (xdr_stream_decode_u32(argp->xdr, &consecutive) < 0) return nfserr_bad_xdr; - if (xdr_stream_decode_u32(argp->xdr, ©->cp_synchronous) < 0) + if (xdr_stream_decode_bool(argp->xdr, &sync) < 0) return nfserr_bad_xdr; + nfsd4_copy_set_sync(copy, sync); if (xdr_stream_decode_u32(argp->xdr, &count) < 0) return nfserr_bad_xdr; - copy->cp_intra = false; + copy->cp_src = svcxdr_tmpalloc(argp, sizeof(*copy->cp_src)); + if (copy->cp_src == NULL) + return nfserr_jukebox; if (count == 0) { /* intra-server copy */ - copy->cp_intra = true; + __set_bit(NFSD4_COPY_F_INTRA, ©->cp_flags); return nfs_ok; } /* decode all the supplied server addresses but use only the first */ - status = nfsd4_decode_nl4_server(argp, ©->cp_src); + status = nfsd4_decode_nl4_server(argp, copy->cp_src); if (status) return status; ns_dummy = kmalloc(sizeof(struct nl4_server), GFP_KERNEL); if (ns_dummy == NULL) - return nfserrno(-ENOMEM); /* XXX: jukebox? */ + return nfserr_jukebox; for (i = 0; i < count - 1; i++) { status = nfsd4_decode_nl4_server(argp, ns_dummy); if (status) { @@ -1950,26 +2033,39 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) static __be32 nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp, - struct nfsd4_copy_notify *cn) + union nfsd4_op_u *u) { + struct nfsd4_copy_notify *cn = &u->copy_notify; __be32 status; + memset(cn, 0, sizeof(*cn)); + cn->cpn_src = svcxdr_tmpalloc(argp, sizeof(*cn->cpn_src)); + if (cn->cpn_src == NULL) + return nfserr_jukebox; + cn->cpn_dst = svcxdr_tmpalloc(argp, sizeof(*cn->cpn_dst)); + if (cn->cpn_dst == NULL) + return nfserr_jukebox; + status = nfsd4_decode_stateid4(argp, &cn->cpn_src_stateid); if (status) return status; - return nfsd4_decode_nl4_server(argp, &cn->cpn_dst); + return nfsd4_decode_nl4_server(argp, cn->cpn_dst); } static __be32 nfsd4_decode_offload_status(struct nfsd4_compoundargs *argp, - struct nfsd4_offload_status *os) + union nfsd4_op_u *u) { + struct nfsd4_offload_status *os = &u->offload_status; + os->count = 0; + os->status = 0; return nfsd4_decode_stateid4(argp, &os->stateid); } static __be32 -nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) +nfsd4_decode_seek(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_seek *seek = &u->seek; __be32 status; status = nfsd4_decode_stateid4(argp, &seek->seek_stateid); @@ -1980,12 +2076,15 @@ nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) if (xdr_stream_decode_u32(argp->xdr, &seek->seek_whence) < 0) return nfserr_bad_xdr; + seek->seek_eof = 0; + seek->seek_pos = 0; return nfs_ok; } static __be32 -nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone) +nfsd4_decode_clone(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_clone *clone = &u->clone; __be32 status; status = nfsd4_decode_stateid4(argp, &clone->cl_src_stateid); @@ -2110,11 +2209,13 @@ nfsd4_decode_xattr_name(struct nfsd4_compoundargs *argp, char **namep) */ static __be32 nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp, - struct nfsd4_getxattr *getxattr) + union nfsd4_op_u *u) { + struct nfsd4_getxattr *getxattr = &u->getxattr; __be32 status; u32 maxcount; + memset(getxattr, 0, sizeof(*getxattr)); status = nfsd4_decode_xattr_name(argp, &getxattr->getxa_name); if (status) return status; @@ -2123,17 +2224,19 @@ nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp, maxcount = min_t(u32, XATTR_SIZE_MAX, maxcount); getxattr->getxa_len = maxcount; - - return status; + return nfs_ok; } static __be32 nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp, - struct nfsd4_setxattr *setxattr) + union nfsd4_op_u *u) { + struct nfsd4_setxattr *setxattr = &u->setxattr; u32 flags, maxcount, size; __be32 status; + memset(setxattr, 0, sizeof(*setxattr)); + if (xdr_stream_decode_u32(argp->xdr, &flags) < 0) return nfserr_bad_xdr; @@ -2168,10 +2271,13 @@ nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp, - struct nfsd4_listxattrs *listxattrs) + union nfsd4_op_u *u) { + struct nfsd4_listxattrs *listxattrs = &u->listxattrs; u32 maxcount; + memset(listxattrs, 0, sizeof(*listxattrs)); + if (xdr_stream_decode_u64(argp->xdr, &listxattrs->lsxa_cookie) < 0) return nfserr_bad_xdr; @@ -2197,112 +2303,114 @@ nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_removexattr(struct nfsd4_compoundargs *argp, - struct nfsd4_removexattr *removexattr) + union nfsd4_op_u *u) { + struct nfsd4_removexattr *removexattr = &u->removexattr; + memset(removexattr, 0, sizeof(*removexattr)); return nfsd4_decode_xattr_name(argp, &removexattr->rmxa_name); } static __be32 -nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_noop(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { return nfs_ok; } static __be32 -nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { return nfserr_notsupp; } -typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, void *); +typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u); static const nfsd4_dec nfsd4_dec_ops[] = { - [OP_ACCESS] = (nfsd4_dec)nfsd4_decode_access, - [OP_CLOSE] = (nfsd4_dec)nfsd4_decode_close, - [OP_COMMIT] = (nfsd4_dec)nfsd4_decode_commit, - [OP_CREATE] = (nfsd4_dec)nfsd4_decode_create, - [OP_DELEGPURGE] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_DELEGRETURN] = (nfsd4_dec)nfsd4_decode_delegreturn, - [OP_GETATTR] = (nfsd4_dec)nfsd4_decode_getattr, - [OP_GETFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_LINK] = (nfsd4_dec)nfsd4_decode_link, - [OP_LOCK] = (nfsd4_dec)nfsd4_decode_lock, - [OP_LOCKT] = (nfsd4_dec)nfsd4_decode_lockt, - [OP_LOCKU] = (nfsd4_dec)nfsd4_decode_locku, - [OP_LOOKUP] = (nfsd4_dec)nfsd4_decode_lookup, - [OP_LOOKUPP] = (nfsd4_dec)nfsd4_decode_noop, - [OP_NVERIFY] = (nfsd4_dec)nfsd4_decode_verify, - [OP_OPEN] = (nfsd4_dec)nfsd4_decode_open, - [OP_OPENATTR] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_OPEN_CONFIRM] = (nfsd4_dec)nfsd4_decode_open_confirm, - [OP_OPEN_DOWNGRADE] = (nfsd4_dec)nfsd4_decode_open_downgrade, - [OP_PUTFH] = (nfsd4_dec)nfsd4_decode_putfh, - [OP_PUTPUBFH] = (nfsd4_dec)nfsd4_decode_putpubfh, - [OP_PUTROOTFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_READ] = (nfsd4_dec)nfsd4_decode_read, - [OP_READDIR] = (nfsd4_dec)nfsd4_decode_readdir, - [OP_READLINK] = (nfsd4_dec)nfsd4_decode_noop, - [OP_REMOVE] = (nfsd4_dec)nfsd4_decode_remove, - [OP_RENAME] = (nfsd4_dec)nfsd4_decode_rename, - [OP_RENEW] = (nfsd4_dec)nfsd4_decode_renew, - [OP_RESTOREFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_SAVEFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_SECINFO] = (nfsd4_dec)nfsd4_decode_secinfo, - [OP_SETATTR] = (nfsd4_dec)nfsd4_decode_setattr, - [OP_SETCLIENTID] = (nfsd4_dec)nfsd4_decode_setclientid, - [OP_SETCLIENTID_CONFIRM] = (nfsd4_dec)nfsd4_decode_setclientid_confirm, - [OP_VERIFY] = (nfsd4_dec)nfsd4_decode_verify, - [OP_WRITE] = (nfsd4_dec)nfsd4_decode_write, - [OP_RELEASE_LOCKOWNER] = (nfsd4_dec)nfsd4_decode_release_lockowner, + [OP_ACCESS] = nfsd4_decode_access, + [OP_CLOSE] = nfsd4_decode_close, + [OP_COMMIT] = nfsd4_decode_commit, + [OP_CREATE] = nfsd4_decode_create, + [OP_DELEGPURGE] = nfsd4_decode_notsupp, + [OP_DELEGRETURN] = nfsd4_decode_delegreturn, + [OP_GETATTR] = nfsd4_decode_getattr, + [OP_GETFH] = nfsd4_decode_noop, + [OP_LINK] = nfsd4_decode_link, + [OP_LOCK] = nfsd4_decode_lock, + [OP_LOCKT] = nfsd4_decode_lockt, + [OP_LOCKU] = nfsd4_decode_locku, + [OP_LOOKUP] = nfsd4_decode_lookup, + [OP_LOOKUPP] = nfsd4_decode_noop, + [OP_NVERIFY] = nfsd4_decode_verify, + [OP_OPEN] = nfsd4_decode_open, + [OP_OPENATTR] = nfsd4_decode_notsupp, + [OP_OPEN_CONFIRM] = nfsd4_decode_open_confirm, + [OP_OPEN_DOWNGRADE] = nfsd4_decode_open_downgrade, + [OP_PUTFH] = nfsd4_decode_putfh, + [OP_PUTPUBFH] = nfsd4_decode_putpubfh, + [OP_PUTROOTFH] = nfsd4_decode_noop, + [OP_READ] = nfsd4_decode_read, + [OP_READDIR] = nfsd4_decode_readdir, + [OP_READLINK] = nfsd4_decode_noop, + [OP_REMOVE] = nfsd4_decode_remove, + [OP_RENAME] = nfsd4_decode_rename, + [OP_RENEW] = nfsd4_decode_renew, + [OP_RESTOREFH] = nfsd4_decode_noop, + [OP_SAVEFH] = nfsd4_decode_noop, + [OP_SECINFO] = nfsd4_decode_secinfo, + [OP_SETATTR] = nfsd4_decode_setattr, + [OP_SETCLIENTID] = nfsd4_decode_setclientid, + [OP_SETCLIENTID_CONFIRM] = nfsd4_decode_setclientid_confirm, + [OP_VERIFY] = nfsd4_decode_verify, + [OP_WRITE] = nfsd4_decode_write, + [OP_RELEASE_LOCKOWNER] = nfsd4_decode_release_lockowner, /* new operations for NFSv4.1 */ - [OP_BACKCHANNEL_CTL] = (nfsd4_dec)nfsd4_decode_backchannel_ctl, - [OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_bind_conn_to_session, - [OP_EXCHANGE_ID] = (nfsd4_dec)nfsd4_decode_exchange_id, - [OP_CREATE_SESSION] = (nfsd4_dec)nfsd4_decode_create_session, - [OP_DESTROY_SESSION] = (nfsd4_dec)nfsd4_decode_destroy_session, - [OP_FREE_STATEID] = (nfsd4_dec)nfsd4_decode_free_stateid, - [OP_GET_DIR_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_BACKCHANNEL_CTL] = nfsd4_decode_backchannel_ctl, + [OP_BIND_CONN_TO_SESSION] = nfsd4_decode_bind_conn_to_session, + [OP_EXCHANGE_ID] = nfsd4_decode_exchange_id, + [OP_CREATE_SESSION] = nfsd4_decode_create_session, + [OP_DESTROY_SESSION] = nfsd4_decode_destroy_session, + [OP_FREE_STATEID] = nfsd4_decode_free_stateid, + [OP_GET_DIR_DELEGATION] = nfsd4_decode_notsupp, #ifdef CONFIG_NFSD_PNFS - [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_getdeviceinfo, - [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_layoutcommit, - [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_layoutget, - [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_layoutreturn, + [OP_GETDEVICEINFO] = nfsd4_decode_getdeviceinfo, + [OP_GETDEVICELIST] = nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] = nfsd4_decode_layoutcommit, + [OP_LAYOUTGET] = nfsd4_decode_layoutget, + [OP_LAYOUTRETURN] = nfsd4_decode_layoutreturn, #else - [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_GETDEVICEINFO] = nfsd4_decode_notsupp, + [OP_GETDEVICELIST] = nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] = nfsd4_decode_notsupp, + [OP_LAYOUTGET] = nfsd4_decode_notsupp, + [OP_LAYOUTRETURN] = nfsd4_decode_notsupp, #endif - [OP_SECINFO_NO_NAME] = (nfsd4_dec)nfsd4_decode_secinfo_no_name, - [OP_SEQUENCE] = (nfsd4_dec)nfsd4_decode_sequence, - [OP_SET_SSV] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_TEST_STATEID] = (nfsd4_dec)nfsd4_decode_test_stateid, - [OP_WANT_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_DESTROY_CLIENTID] = (nfsd4_dec)nfsd4_decode_destroy_clientid, - [OP_RECLAIM_COMPLETE] = (nfsd4_dec)nfsd4_decode_reclaim_complete, + [OP_SECINFO_NO_NAME] = nfsd4_decode_secinfo_no_name, + [OP_SEQUENCE] = nfsd4_decode_sequence, + [OP_SET_SSV] = nfsd4_decode_notsupp, + [OP_TEST_STATEID] = nfsd4_decode_test_stateid, + [OP_WANT_DELEGATION] = nfsd4_decode_notsupp, + [OP_DESTROY_CLIENTID] = nfsd4_decode_destroy_clientid, + [OP_RECLAIM_COMPLETE] = nfsd4_decode_reclaim_complete, /* new operations for NFSv4.2 */ - [OP_ALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, - [OP_COPY] = (nfsd4_dec)nfsd4_decode_copy, - [OP_COPY_NOTIFY] = (nfsd4_dec)nfsd4_decode_copy_notify, - [OP_DEALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, - [OP_IO_ADVISE] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTERROR] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTSTATS] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_OFFLOAD_CANCEL] = (nfsd4_dec)nfsd4_decode_offload_status, - [OP_OFFLOAD_STATUS] = (nfsd4_dec)nfsd4_decode_offload_status, - [OP_READ_PLUS] = (nfsd4_dec)nfsd4_decode_read, - [OP_SEEK] = (nfsd4_dec)nfsd4_decode_seek, - [OP_WRITE_SAME] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_CLONE] = (nfsd4_dec)nfsd4_decode_clone, + [OP_ALLOCATE] = nfsd4_decode_fallocate, + [OP_COPY] = nfsd4_decode_copy, + [OP_COPY_NOTIFY] = nfsd4_decode_copy_notify, + [OP_DEALLOCATE] = nfsd4_decode_fallocate, + [OP_IO_ADVISE] = nfsd4_decode_notsupp, + [OP_LAYOUTERROR] = nfsd4_decode_notsupp, + [OP_LAYOUTSTATS] = nfsd4_decode_notsupp, + [OP_OFFLOAD_CANCEL] = nfsd4_decode_offload_status, + [OP_OFFLOAD_STATUS] = nfsd4_decode_offload_status, + [OP_READ_PLUS] = nfsd4_decode_read, + [OP_SEEK] = nfsd4_decode_seek, + [OP_WRITE_SAME] = nfsd4_decode_notsupp, + [OP_CLONE] = nfsd4_decode_clone, /* RFC 8276 extended atributes operations */ - [OP_GETXATTR] = (nfsd4_dec)nfsd4_decode_getxattr, - [OP_SETXATTR] = (nfsd4_dec)nfsd4_decode_setxattr, - [OP_LISTXATTRS] = (nfsd4_dec)nfsd4_decode_listxattrs, - [OP_REMOVEXATTR] = (nfsd4_dec)nfsd4_decode_removexattr, + [OP_GETXATTR] = nfsd4_decode_getxattr, + [OP_SETXATTR] = nfsd4_decode_setxattr, + [OP_LISTXATTRS] = nfsd4_decode_listxattrs, + [OP_REMOVEXATTR] = nfsd4_decode_removexattr, }; static inline bool @@ -2319,7 +2427,7 @@ nfsd4_opnum_in_range(struct nfsd4_compoundargs *argp, struct nfsd4_op *op) return true; } -static int +static bool nfsd4_decode_compound(struct nfsd4_compoundargs *argp) { struct nfsd4_op *op; @@ -2332,35 +2440,34 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) int i; if (xdr_stream_decode_u32(argp->xdr, &argp->taglen) < 0) - return 0; + return false; max_reply += XDR_UNIT; argp->tag = NULL; if (unlikely(argp->taglen)) { if (argp->taglen > NFSD4_MAX_TAGLEN) - return 0; + return false; p = xdr_inline_decode(argp->xdr, argp->taglen); if (!p) - return 0; + return false; argp->tag = svcxdr_savemem(argp, p, argp->taglen); if (!argp->tag) - return 0; + return false; max_reply += xdr_align_size(argp->taglen); } if (xdr_stream_decode_u32(argp->xdr, &argp->minorversion) < 0) - return 0; + return false; if (xdr_stream_decode_u32(argp->xdr, &argp->client_opcnt) < 0) - return 0; + return false; argp->opcnt = min_t(u32, argp->client_opcnt, NFSD_MAX_OPS_PER_COMPOUND); if (argp->opcnt > ARRAY_SIZE(argp->iops)) { - argp->ops = kzalloc(argp->opcnt * sizeof(*argp->ops), GFP_KERNEL); + argp->ops = vcalloc(argp->opcnt, sizeof(*argp->ops)); if (!argp->ops) { argp->ops = argp->iops; - dprintk("nfsd: couldn't allocate room for COMPOUND\n"); - return 0; + return false; } } @@ -2373,7 +2480,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->opdesc = NULL; if (xdr_stream_decode_u32(argp->xdr, &op->opnum) < 0) - return 0; + return false; if (nfsd4_opnum_in_range(argp, op)) { op->opdesc = OPDESC(op); op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); @@ -2421,7 +2528,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); - return 1; + return true; } static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, @@ -2435,6 +2542,20 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, return p; } +static __be32 nfsd4_encode_nfstime4(struct xdr_stream *xdr, + struct timespec64 *tv) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, XDR_UNIT * 3); + if (!p) + return nfserr_resource; + + p = xdr_encode_hyper(p, (s64)tv->tv_sec); + *p = cpu_to_be32(tv->tv_nsec); + return nfs_ok; +} + /* * ctime (in NFSv4, time_metadata) is not writeable, and the client * doesn't really care what resolution could theoretically be stored by @@ -2763,9 +2884,10 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *bmval2, u32 } -static int get_parent_attributes(struct svc_export *exp, struct kstat *stat) +static int nfsd4_get_mounted_on_ino(struct svc_export *exp, u64 *pino) { struct path path = exp->ex_path; + struct kstat stat; int err; path_get(&path); @@ -2773,8 +2895,10 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat) if (path.dentry != path.mnt->mnt_root) break; } - err = vfs_getattr(&path, stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); + err = vfs_getattr(&path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT); path_put(&path); + if (!err) + *pino = stat.ino; return err; } @@ -2827,10 +2951,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, struct kstat stat; struct svc_fh *tempfh = NULL; struct kstatfs statfs; - __be32 *p; + __be32 *p, *attrlen_p; int starting_len = xdr->buf->len; int attrlen_offset; - __be32 attrlen; u32 dummy; u64 dummy64; u32 rdattr_err = 0; @@ -2862,6 +2985,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, err = vfs_getattr(&path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); if (err) goto out_nfserr; + if (!(stat.result_mask & STATX_BTIME)) + /* underlying FS does not offer btime so we can't share it */ + bmval1 &= ~FATTR4_WORD1_TIME_CREATE; if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) || (bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | @@ -2915,10 +3041,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, goto out; attrlen_offset = xdr->buf->len; - p = xdr_reserve_space(xdr, 4); - if (!p) + attrlen_p = xdr_reserve_space(xdr, XDR_UNIT); + if (!attrlen_p) goto out_resource; - p++; /* to be backfilled later */ if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { u32 supp[3]; @@ -3104,7 +3229,7 @@ out_acl: p = xdr_reserve_space(xdr, fhp->fh_handle.fh_size + 4); if (!p) goto out_resource; - p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, + p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw, fhp->fh_handle.fh_size); } if (bmval0 & FATTR4_WORD0_FILEID) { @@ -3236,11 +3361,14 @@ out_acl: p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_TIME_ACCESS) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.atime.tv_sec); - *p++ = cpu_to_be32(stat.atime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.atime); + if (status) + goto out; + } + if (bmval1 & FATTR4_WORD1_TIME_CREATE) { + status = nfsd4_encode_nfstime4(xdr, &stat.btime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_TIME_DELTA) { p = xdr_reserve_space(xdr, 12); @@ -3249,36 +3377,31 @@ out_acl: p = encode_time_delta(p, d_inode(dentry)); } if (bmval1 & FATTR4_WORD1_TIME_METADATA) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.ctime.tv_sec); - *p++ = cpu_to_be32(stat.ctime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.ctime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_TIME_MODIFY) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.mtime.tv_sec); - *p++ = cpu_to_be32(stat.mtime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.mtime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) { - struct kstat parent_stat; u64 ino = stat.ino; p = xdr_reserve_space(xdr, 8); if (!p) goto out_resource; /* - * Get parent's attributes if not ignoring crossmount - * and this is the root of a cross-mounted filesystem. + * Get ino of mountpoint in parent filesystem, if not ignoring + * crossmount and this is the root of a cross-mounted + * filesystem. */ if (ignore_crossmnt == 0 && dentry == exp->ex_path.mnt->mnt_root) { - err = get_parent_attributes(exp, &parent_stat); + err = nfsd4_get_mounted_on_ino(exp, &ino); if (err) goto out_nfserr; - ino = parent_stat.ino; } p = xdr_encode_hyper(p, ino); } @@ -3333,8 +3456,7 @@ out_acl: *p++ = cpu_to_be32(err == 0); } - attrlen = htonl(xdr->buf->len - attrlen_offset - 4); - write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4); + *attrlen_p = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT); status = nfs_ok; out: @@ -3503,7 +3625,7 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, p = xdr_reserve_space(xdr, 3*4 + namlen); if (!p) goto fail; - p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */ + p = xdr_encode_hyper(p, OFFSET_MAX); /* offset of next entry */ p = xdr_encode_array(p, name, namlen); /* name length & name */ nfserr = nfsd4_encode_dirent_fattr(xdr, cd, name, namlen); @@ -3587,8 +3709,10 @@ nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid) } static __be32 -nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access) +nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_access *access = &u->access; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3600,8 +3724,10 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ return 0; } -static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts) +static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3617,8 +3743,10 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, } static __be32 -nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close) +nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_close *close = &u->close; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &close->cl_stateid); @@ -3626,8 +3754,10 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c static __be32 -nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit) +nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_commit *commit = &u->commit; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3640,8 +3770,10 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ } static __be32 -nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create) +nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_create *create = &u->create; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3654,8 +3786,10 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ } static __be32 -nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getattr *getattr) +nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_getattr *getattr = &u->getattr; struct svc_fh *fhp = getattr->ga_fhp; struct xdr_stream *xdr = resp->xdr; @@ -3664,8 +3798,10 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 } static __be32 -nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp) +nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct svc_fh **fhpp = &u->getfh; struct xdr_stream *xdr = resp->xdr; struct svc_fh *fhp = *fhpp; unsigned int len; @@ -3675,7 +3811,7 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh p = xdr_reserve_space(xdr, len + 4); if (!p) return nfserr_resource; - p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, len); + p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw, len); return 0; } @@ -3719,8 +3855,10 @@ again: } static __be32 -nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock) +nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_lock *lock = &u->lock; struct xdr_stream *xdr = resp->xdr; if (!nfserr) @@ -3732,8 +3870,10 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo } static __be32 -nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt) +nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_lockt *lockt = &u->lockt; struct xdr_stream *xdr = resp->xdr; if (nfserr == nfserr_denied) @@ -3742,8 +3882,10 @@ nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l } static __be32 -nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku) +nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_locku *locku = &u->locku; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &locku->lu_stateid); @@ -3751,8 +3893,10 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l static __be32 -nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link) +nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_link *link = &u->link; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3765,8 +3909,10 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li static __be32 -nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open) +nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open *open = &u->open; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3859,16 +4005,20 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op } static __be32 -nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc) +nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open_confirm *oc = &u->open_confirm; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid); } static __be32 -nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od) +nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open_downgrade *od = &u->open_downgrade; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &od->od_stateid); @@ -3882,16 +4032,15 @@ static __be32 nfsd4_encode_splice_read( struct xdr_stream *xdr = resp->xdr; struct xdr_buf *buf = xdr->buf; int status, space_left; - u32 eof; __be32 nfserr; - __be32 *p = xdr->p - 2; /* Make sure there will be room for padding if needed */ if (xdr->end - xdr->p < 1) return nfserr_resource; nfserr = nfsd_splice_read(read->rd_rqstp, read->rd_fhp, - file, read->rd_offset, &maxcount, &eof); + file, read->rd_offset, &maxcount, + &read->rd_eof); read->rd_length = maxcount; if (nfserr) goto out_err; @@ -3902,9 +4051,6 @@ static __be32 nfsd4_encode_splice_read( goto out_err; } - *(p++) = htonl(eof); - *(p++) = htonl(maxcount); - buf->page_len = maxcount; buf->len += maxcount; xdr->page_ptr += (buf->page_base + maxcount + PAGE_SIZE - 1) @@ -3946,11 +4092,9 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, struct file *file, unsigned long maxcount) { struct xdr_stream *xdr = resp->xdr; - u32 eof; - int starting_len = xdr->buf->len - 8; + unsigned int starting_len = xdr->buf->len; + __be32 zero = xdr_zero; __be32 nfserr; - __be32 tmp; - int pad; read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, maxcount); if (read->rd_vlen < 0) @@ -3958,31 +4102,25 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset, resp->rqstp->rq_vec, read->rd_vlen, &maxcount, - &eof); + &read->rd_eof); read->rd_length = maxcount; if (nfserr) return nfserr; - if (svc_encode_result_payload(resp->rqstp, starting_len + 8, maxcount)) + if (svc_encode_result_payload(resp->rqstp, starting_len, maxcount)) return nfserr_io; - xdr_truncate_encode(xdr, starting_len + 8 + xdr_align_size(maxcount)); - - tmp = htonl(eof); - write_bytes_to_xdr_buf(xdr->buf, starting_len , &tmp, 4); - tmp = htonl(maxcount); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); - - tmp = xdr_zero; - pad = (maxcount&3) ? 4 - (maxcount&3) : 0; - write_bytes_to_xdr_buf(xdr->buf, starting_len + 8 + maxcount, - &tmp, pad); - return 0; + xdr_truncate_encode(xdr, starting_len + xdr_align_size(maxcount)); + write_bytes_to_xdr_buf(xdr->buf, starting_len + maxcount, &zero, + xdr_pad_size(maxcount)); + return nfs_ok; } static __be32 nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_read *read) + union nfsd4_op_u *u) { + struct nfsd4_read *read = &u->read; + bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); unsigned long maxcount; struct xdr_stream *xdr = resp->xdr; struct file *file; @@ -3995,11 +4133,10 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */ if (!p) { - WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)); + WARN_ON_ONCE(splice_ok); return nfserr_resource; } - if (resp->xdr->buf->page_len && - test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) { + if (resp->xdr->buf->page_len && splice_ok) { WARN_ON_ONCE(1); return nfserr_serverfault; } @@ -4008,31 +4145,32 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, maxcount = min_t(unsigned long, read->rd_length, (xdr->buf->buflen - xdr->buf->len)); - if (file->f_op->splice_read && - test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) + if (file->f_op->splice_read && splice_ok) nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount); else nfserr = nfsd4_encode_readv(resp, read, file, maxcount); - - if (nfserr) + if (nfserr) { xdr_truncate_encode(xdr, starting_len); + return nfserr; + } - return nfserr; + p = xdr_encode_bool(p, read->rd_eof); + *p = cpu_to_be32(read->rd_length); + return nfs_ok; } static __be32 -nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink) +nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { - int maxcount; - __be32 wire_count; - int zero = 0; + struct nfsd4_readlink *readlink = &u->readlink; + __be32 *p, *maxcount_p, zero = xdr_zero; struct xdr_stream *xdr = resp->xdr; int length_offset = xdr->buf->len; - int status; - __be32 *p; + int maxcount, status; - p = xdr_reserve_space(xdr, 4); - if (!p) + maxcount_p = xdr_reserve_space(xdr, XDR_UNIT); + if (!maxcount_p) return nfserr_resource; maxcount = PAGE_SIZE; @@ -4057,14 +4195,11 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd nfserr = nfserrno(status); goto out_err; } - - wire_count = htonl(maxcount); - write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, 4); - xdr_truncate_encode(xdr, length_offset + 4 + ALIGN(maxcount, 4)); - if (maxcount & 3) - write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, - &zero, 4 - (maxcount&3)); - return 0; + *maxcount_p = cpu_to_be32(maxcount); + xdr_truncate_encode(xdr, length_offset + 4 + xdr_align_size(maxcount)); + write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, &zero, + xdr_pad_size(maxcount)); + return nfs_ok; out_err: xdr_truncate_encode(xdr, length_offset); @@ -4072,8 +4207,10 @@ out_err: } static __be32 -nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readdir *readdir) +nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_readdir *readdir = &u->readdir; int maxcount; int bytes_left; loff_t offset; @@ -4163,8 +4300,10 @@ err_no_verf: } static __be32 -nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove) +nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_remove *remove = &u->remove; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4176,8 +4315,10 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ } static __be32 -nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename) +nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_rename *rename = &u->rename; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4259,8 +4400,9 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) static __be32 nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_secinfo *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo *secinfo = &u->secinfo; struct xdr_stream *xdr = resp->xdr; return nfsd4_do_encode_secinfo(xdr, secinfo->si_exp); @@ -4268,8 +4410,9 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_secinfo_no_name *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo_no_name *secinfo = &u->secinfo_no_name; struct xdr_stream *xdr = resp->xdr; return nfsd4_do_encode_secinfo(xdr, secinfo->sin_exp); @@ -4280,8 +4423,10 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, * regardless of the error status. */ static __be32 -nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr) +nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_setattr *setattr = &u->setattr; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4304,8 +4449,10 @@ nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 } static __be32 -nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd) +nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_setclientid *scd = &u->setclientid; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4328,8 +4475,10 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n } static __be32 -nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write) +nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_write *write = &u->write; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4345,8 +4494,9 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w static __be32 nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_exchange_id *exid) + union nfsd4_op_u *u) { + struct nfsd4_exchange_id *exid = &u->exchange_id; struct xdr_stream *xdr = resp->xdr; __be32 *p; char *major_id; @@ -4423,8 +4573,9 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_create_session *sess) + union nfsd4_op_u *u) { + struct nfsd4_create_session *sess = &u->create_session; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4476,8 +4627,9 @@ nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_sequence *seq) + union nfsd4_op_u *u) { + struct nfsd4_sequence *seq = &u->sequence; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4499,8 +4651,9 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_test_stateid *test_stateid) + union nfsd4_op_u *u) { + struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct xdr_stream *xdr = resp->xdr; struct nfsd4_test_stateid_id *stateid, *next; __be32 *p; @@ -4520,8 +4673,9 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, #ifdef CONFIG_NFSD_PNFS static __be32 nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_getdeviceinfo *gdev) + union nfsd4_op_u *u) { + struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; struct xdr_stream *xdr = resp->xdr; const struct nfsd4_layout_ops *ops; u32 starting_len = xdr->buf->len, needed_len; @@ -4573,8 +4727,9 @@ toosmall: static __be32 nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutget *lgp) + union nfsd4_op_u *u) { + struct nfsd4_layoutget *lgp = &u->layoutget; struct xdr_stream *xdr = resp->xdr; const struct nfsd4_layout_ops *ops; __be32 *p; @@ -4600,8 +4755,9 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutcommit *lcp) + union nfsd4_op_u *u) { + struct nfsd4_layoutcommit *lcp = &u->layoutcommit; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4621,8 +4777,9 @@ nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutreturn *lrp) + union nfsd4_op_u *u) { + struct nfsd4_layoutreturn *lrp = &u->layoutreturn; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4707,25 +4864,27 @@ nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns) static __be32 nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_copy *copy) + union nfsd4_op_u *u) { + struct nfsd4_copy *copy = &u->copy; __be32 *p; nfserr = nfsd42_encode_write_res(resp, ©->cp_res, - !!copy->cp_synchronous); + nfsd4_copy_is_sync(copy)); if (nfserr) return nfserr; p = xdr_reserve_space(resp->xdr, 4 + 4); *p++ = xdr_one; /* cr_consecutive */ - *p++ = cpu_to_be32(copy->cp_synchronous); + *p = nfsd4_copy_is_sync(copy) ? xdr_one : xdr_zero; return 0; } static __be32 nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_offload_status *os) + union nfsd4_op_u *u) { + struct nfsd4_offload_status *os = &u->offload_status; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4739,156 +4898,83 @@ nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, - struct nfsd4_read *read, - unsigned long *maxcount, u32 *eof, - loff_t *pos) + struct nfsd4_read *read) { - struct xdr_stream *xdr = resp->xdr; + bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); struct file *file = read->rd_nf->nf_file; - int starting_len = xdr->buf->len; - loff_t hole_pos; - __be32 nfserr; - __be32 *p, tmp; - __be64 tmp64; - - hole_pos = pos ? *pos : vfs_llseek(file, read->rd_offset, SEEK_HOLE); - if (hole_pos > read->rd_offset) - *maxcount = min_t(unsigned long, *maxcount, hole_pos - read->rd_offset); - *maxcount = min_t(unsigned long, *maxcount, (xdr->buf->buflen - xdr->buf->len)); + struct xdr_stream *xdr = resp->xdr; + unsigned long maxcount; + __be32 nfserr, *p; /* Content type, offset, byte count */ p = xdr_reserve_space(xdr, 4 + 8 + 4); if (!p) - return nfserr_resource; + return nfserr_io; + if (resp->xdr->buf->page_len && splice_ok) { + WARN_ON_ONCE(splice_ok); + return nfserr_serverfault; + } - read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, *maxcount); - if (read->rd_vlen < 0) - return nfserr_resource; + maxcount = min_t(unsigned long, read->rd_length, + (xdr->buf->buflen - xdr->buf->len)); - nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset, - resp->rqstp->rq_vec, read->rd_vlen, maxcount, eof); + if (file->f_op->splice_read && splice_ok) + nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount); + else + nfserr = nfsd4_encode_readv(resp, read, file, maxcount); if (nfserr) return nfserr; - xdr_truncate_encode(xdr, starting_len + 16 + xdr_align_size(*maxcount)); - - tmp = htonl(NFS4_CONTENT_DATA); - write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); - tmp64 = cpu_to_be64(read->rd_offset); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp64, 8); - tmp = htonl(*maxcount); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 12, &tmp, 4); - - tmp = xdr_zero; - write_bytes_to_xdr_buf(xdr->buf, starting_len + 16 + *maxcount, &tmp, - xdr_pad_size(*maxcount)); - return nfs_ok; -} - -static __be32 -nfsd4_encode_read_plus_hole(struct nfsd4_compoundres *resp, - struct nfsd4_read *read, - unsigned long *maxcount, u32 *eof) -{ - struct file *file = read->rd_nf->nf_file; - loff_t data_pos = vfs_llseek(file, read->rd_offset, SEEK_DATA); - loff_t f_size = i_size_read(file_inode(file)); - unsigned long count; - __be32 *p; - - if (data_pos == -ENXIO) - data_pos = f_size; - else if (data_pos <= read->rd_offset || (data_pos < f_size && data_pos % PAGE_SIZE)) - return nfsd4_encode_read_plus_data(resp, read, maxcount, eof, &f_size); - count = data_pos - read->rd_offset; - - /* Content type, offset, byte count */ - p = xdr_reserve_space(resp->xdr, 4 + 8 + 8); - if (!p) - return nfserr_resource; - *p++ = htonl(NFS4_CONTENT_HOLE); - p = xdr_encode_hyper(p, read->rd_offset); - p = xdr_encode_hyper(p, count); + *p++ = cpu_to_be32(NFS4_CONTENT_DATA); + p = xdr_encode_hyper(p, read->rd_offset); + *p = cpu_to_be32(read->rd_length); - *eof = (read->rd_offset + count) >= f_size; - *maxcount = min_t(unsigned long, count, *maxcount); return nfs_ok; } static __be32 nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_read *read) + union nfsd4_op_u *u) { - unsigned long maxcount, count; + struct nfsd4_read *read = &u->read; + struct file *file = read->rd_nf->nf_file; struct xdr_stream *xdr = resp->xdr; - struct file *file; int starting_len = xdr->buf->len; - int last_segment = xdr->buf->len; - int segments = 0; - __be32 *p, tmp; - bool is_data; - loff_t pos; - u32 eof; + u32 segments = 0; + __be32 *p; if (nfserr) return nfserr; - file = read->rd_nf->nf_file; /* eof flag, segment count */ p = xdr_reserve_space(xdr, 4 + 4); if (!p) - return nfserr_resource; + return nfserr_io; xdr_commit_encode(xdr); - maxcount = min_t(unsigned long, read->rd_length, - (xdr->buf->buflen - xdr->buf->len)); - count = maxcount; - - eof = read->rd_offset >= i_size_read(file_inode(file)); - if (eof) + read->rd_eof = read->rd_offset >= i_size_read(file_inode(file)); + if (read->rd_eof) goto out; - pos = vfs_llseek(file, read->rd_offset, SEEK_HOLE); - is_data = pos > read->rd_offset; - - while (count > 0 && !eof) { - maxcount = count; - if (is_data) - nfserr = nfsd4_encode_read_plus_data(resp, read, &maxcount, &eof, - segments == 0 ? &pos : NULL); - else - nfserr = nfsd4_encode_read_plus_hole(resp, read, &maxcount, &eof); - if (nfserr) - goto out; - count -= maxcount; - read->rd_offset += maxcount; - is_data = !is_data; - last_segment = xdr->buf->len; - segments++; - } - -out: - if (nfserr && segments == 0) + nfserr = nfsd4_encode_read_plus_data(resp, read); + if (nfserr) { xdr_truncate_encode(xdr, starting_len); - else { - if (nfserr) { - xdr_truncate_encode(xdr, last_segment); - nfserr = nfs_ok; - eof = 0; - } - tmp = htonl(eof); - write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); - tmp = htonl(segments); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); + return nfserr; } + segments++; + +out: + p = xdr_encode_bool(p, read->rd_eof); + *p = cpu_to_be32(segments); return nfserr; } static __be32 nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_copy_notify *cn) + union nfsd4_op_u *u) { + struct nfsd4_copy_notify *cn = &u->copy_notify; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4916,13 +5002,15 @@ nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, *p++ = cpu_to_be32(1); - return nfsd42_encode_nl4_server(resp, &cn->cpn_src); + nfserr = nfsd42_encode_nl4_server(resp, cn->cpn_src); + return nfserr; } static __be32 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_seek *seek) + union nfsd4_op_u *u) { + struct nfsd4_seek *seek = &u->seek; __be32 *p; p = xdr_reserve_space(resp->xdr, 4 + 8); @@ -4933,7 +5021,8 @@ nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, } static __be32 -nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p) +nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *p) { return nfserr; } @@ -4984,8 +5073,9 @@ nfsd4_vbuf_to_stream(struct xdr_stream *xdr, char *buf, u32 buflen) static __be32 nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_getxattr *getxattr) + union nfsd4_op_u *u) { + struct nfsd4_getxattr *getxattr = &u->getxattr; struct xdr_stream *xdr = resp->xdr; __be32 *p, err; @@ -5008,8 +5098,9 @@ nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_setxattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_setxattr *setxattr) + union nfsd4_op_u *u) { + struct nfsd4_setxattr *setxattr = &u->setxattr; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -5049,8 +5140,9 @@ nfsd4_listxattr_validate_cookie(struct nfsd4_listxattrs *listxattrs, static __be32 nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_listxattrs *listxattrs) + union nfsd4_op_u *u) { + struct nfsd4_listxattrs *listxattrs = &u->listxattrs; struct xdr_stream *xdr = resp->xdr; u32 cookie_offset, count_offset, eof; u32 left, xdrleft, slen, count; @@ -5160,8 +5252,9 @@ out: static __be32 nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_removexattr *removexattr) + union nfsd4_op_u *u) { + struct nfsd4_removexattr *removexattr = &u->removexattr; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -5173,7 +5266,7 @@ nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr, return 0; } -typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); +typedef __be32(*nfsd4_enc)(struct nfsd4_compoundres *, __be32, union nfsd4_op_u *u); /* * Note: nfsd4_enc_ops vector is shared for v4.0 and v4.1 @@ -5181,93 +5274,93 @@ typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); * done in the decoding phase. */ static const nfsd4_enc nfsd4_enc_ops[] = { - [OP_ACCESS] = (nfsd4_enc)nfsd4_encode_access, - [OP_CLOSE] = (nfsd4_enc)nfsd4_encode_close, - [OP_COMMIT] = (nfsd4_enc)nfsd4_encode_commit, - [OP_CREATE] = (nfsd4_enc)nfsd4_encode_create, - [OP_DELEGPURGE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_DELEGRETURN] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GETATTR] = (nfsd4_enc)nfsd4_encode_getattr, - [OP_GETFH] = (nfsd4_enc)nfsd4_encode_getfh, - [OP_LINK] = (nfsd4_enc)nfsd4_encode_link, - [OP_LOCK] = (nfsd4_enc)nfsd4_encode_lock, - [OP_LOCKT] = (nfsd4_enc)nfsd4_encode_lockt, - [OP_LOCKU] = (nfsd4_enc)nfsd4_encode_locku, - [OP_LOOKUP] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LOOKUPP] = (nfsd4_enc)nfsd4_encode_noop, - [OP_NVERIFY] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OPEN] = (nfsd4_enc)nfsd4_encode_open, - [OP_OPENATTR] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OPEN_CONFIRM] = (nfsd4_enc)nfsd4_encode_open_confirm, - [OP_OPEN_DOWNGRADE] = (nfsd4_enc)nfsd4_encode_open_downgrade, - [OP_PUTFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_PUTPUBFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_PUTROOTFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_READ] = (nfsd4_enc)nfsd4_encode_read, - [OP_READDIR] = (nfsd4_enc)nfsd4_encode_readdir, - [OP_READLINK] = (nfsd4_enc)nfsd4_encode_readlink, - [OP_REMOVE] = (nfsd4_enc)nfsd4_encode_remove, - [OP_RENAME] = (nfsd4_enc)nfsd4_encode_rename, - [OP_RENEW] = (nfsd4_enc)nfsd4_encode_noop, - [OP_RESTOREFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_SAVEFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_SECINFO] = (nfsd4_enc)nfsd4_encode_secinfo, - [OP_SETATTR] = (nfsd4_enc)nfsd4_encode_setattr, - [OP_SETCLIENTID] = (nfsd4_enc)nfsd4_encode_setclientid, - [OP_SETCLIENTID_CONFIRM] = (nfsd4_enc)nfsd4_encode_noop, - [OP_VERIFY] = (nfsd4_enc)nfsd4_encode_noop, - [OP_WRITE] = (nfsd4_enc)nfsd4_encode_write, - [OP_RELEASE_LOCKOWNER] = (nfsd4_enc)nfsd4_encode_noop, + [OP_ACCESS] = nfsd4_encode_access, + [OP_CLOSE] = nfsd4_encode_close, + [OP_COMMIT] = nfsd4_encode_commit, + [OP_CREATE] = nfsd4_encode_create, + [OP_DELEGPURGE] = nfsd4_encode_noop, + [OP_DELEGRETURN] = nfsd4_encode_noop, + [OP_GETATTR] = nfsd4_encode_getattr, + [OP_GETFH] = nfsd4_encode_getfh, + [OP_LINK] = nfsd4_encode_link, + [OP_LOCK] = nfsd4_encode_lock, + [OP_LOCKT] = nfsd4_encode_lockt, + [OP_LOCKU] = nfsd4_encode_locku, + [OP_LOOKUP] = nfsd4_encode_noop, + [OP_LOOKUPP] = nfsd4_encode_noop, + [OP_NVERIFY] = nfsd4_encode_noop, + [OP_OPEN] = nfsd4_encode_open, + [OP_OPENATTR] = nfsd4_encode_noop, + [OP_OPEN_CONFIRM] = nfsd4_encode_open_confirm, + [OP_OPEN_DOWNGRADE] = nfsd4_encode_open_downgrade, + [OP_PUTFH] = nfsd4_encode_noop, + [OP_PUTPUBFH] = nfsd4_encode_noop, + [OP_PUTROOTFH] = nfsd4_encode_noop, + [OP_READ] = nfsd4_encode_read, + [OP_READDIR] = nfsd4_encode_readdir, + [OP_READLINK] = nfsd4_encode_readlink, + [OP_REMOVE] = nfsd4_encode_remove, + [OP_RENAME] = nfsd4_encode_rename, + [OP_RENEW] = nfsd4_encode_noop, + [OP_RESTOREFH] = nfsd4_encode_noop, + [OP_SAVEFH] = nfsd4_encode_noop, + [OP_SECINFO] = nfsd4_encode_secinfo, + [OP_SETATTR] = nfsd4_encode_setattr, + [OP_SETCLIENTID] = nfsd4_encode_setclientid, + [OP_SETCLIENTID_CONFIRM] = nfsd4_encode_noop, + [OP_VERIFY] = nfsd4_encode_noop, + [OP_WRITE] = nfsd4_encode_write, + [OP_RELEASE_LOCKOWNER] = nfsd4_encode_noop, /* NFSv4.1 operations */ - [OP_BACKCHANNEL_CTL] = (nfsd4_enc)nfsd4_encode_noop, - [OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_bind_conn_to_session, - [OP_EXCHANGE_ID] = (nfsd4_enc)nfsd4_encode_exchange_id, - [OP_CREATE_SESSION] = (nfsd4_enc)nfsd4_encode_create_session, - [OP_DESTROY_SESSION] = (nfsd4_enc)nfsd4_encode_noop, - [OP_FREE_STATEID] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GET_DIR_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, + [OP_BACKCHANNEL_CTL] = nfsd4_encode_noop, + [OP_BIND_CONN_TO_SESSION] = nfsd4_encode_bind_conn_to_session, + [OP_EXCHANGE_ID] = nfsd4_encode_exchange_id, + [OP_CREATE_SESSION] = nfsd4_encode_create_session, + [OP_DESTROY_SESSION] = nfsd4_encode_noop, + [OP_FREE_STATEID] = nfsd4_encode_noop, + [OP_GET_DIR_DELEGATION] = nfsd4_encode_noop, #ifdef CONFIG_NFSD_PNFS - [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_getdeviceinfo, - [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_layoutcommit, - [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_layoutget, - [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_layoutreturn, + [OP_GETDEVICEINFO] = nfsd4_encode_getdeviceinfo, + [OP_GETDEVICELIST] = nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = nfsd4_encode_layoutcommit, + [OP_LAYOUTGET] = nfsd4_encode_layoutget, + [OP_LAYOUTRETURN] = nfsd4_encode_layoutreturn, #else - [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GETDEVICEINFO] = nfsd4_encode_noop, + [OP_GETDEVICELIST] = nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = nfsd4_encode_noop, + [OP_LAYOUTGET] = nfsd4_encode_noop, + [OP_LAYOUTRETURN] = nfsd4_encode_noop, #endif - [OP_SECINFO_NO_NAME] = (nfsd4_enc)nfsd4_encode_secinfo_no_name, - [OP_SEQUENCE] = (nfsd4_enc)nfsd4_encode_sequence, - [OP_SET_SSV] = (nfsd4_enc)nfsd4_encode_noop, - [OP_TEST_STATEID] = (nfsd4_enc)nfsd4_encode_test_stateid, - [OP_WANT_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, - [OP_DESTROY_CLIENTID] = (nfsd4_enc)nfsd4_encode_noop, - [OP_RECLAIM_COMPLETE] = (nfsd4_enc)nfsd4_encode_noop, + [OP_SECINFO_NO_NAME] = nfsd4_encode_secinfo_no_name, + [OP_SEQUENCE] = nfsd4_encode_sequence, + [OP_SET_SSV] = nfsd4_encode_noop, + [OP_TEST_STATEID] = nfsd4_encode_test_stateid, + [OP_WANT_DELEGATION] = nfsd4_encode_noop, + [OP_DESTROY_CLIENTID] = nfsd4_encode_noop, + [OP_RECLAIM_COMPLETE] = nfsd4_encode_noop, /* NFSv4.2 operations */ - [OP_ALLOCATE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_COPY] = (nfsd4_enc)nfsd4_encode_copy, - [OP_COPY_NOTIFY] = (nfsd4_enc)nfsd4_encode_copy_notify, - [OP_DEALLOCATE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_IO_ADVISE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTERROR] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTSTATS] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OFFLOAD_CANCEL] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OFFLOAD_STATUS] = (nfsd4_enc)nfsd4_encode_offload_status, - [OP_READ_PLUS] = (nfsd4_enc)nfsd4_encode_read_plus, - [OP_SEEK] = (nfsd4_enc)nfsd4_encode_seek, - [OP_WRITE_SAME] = (nfsd4_enc)nfsd4_encode_noop, - [OP_CLONE] = (nfsd4_enc)nfsd4_encode_noop, + [OP_ALLOCATE] = nfsd4_encode_noop, + [OP_COPY] = nfsd4_encode_copy, + [OP_COPY_NOTIFY] = nfsd4_encode_copy_notify, + [OP_DEALLOCATE] = nfsd4_encode_noop, + [OP_IO_ADVISE] = nfsd4_encode_noop, + [OP_LAYOUTERROR] = nfsd4_encode_noop, + [OP_LAYOUTSTATS] = nfsd4_encode_noop, + [OP_OFFLOAD_CANCEL] = nfsd4_encode_noop, + [OP_OFFLOAD_STATUS] = nfsd4_encode_offload_status, + [OP_READ_PLUS] = nfsd4_encode_read_plus, + [OP_SEEK] = nfsd4_encode_seek, + [OP_WRITE_SAME] = nfsd4_encode_noop, + [OP_CLONE] = nfsd4_encode_noop, /* RFC 8276 extended atributes operations */ - [OP_GETXATTR] = (nfsd4_enc)nfsd4_encode_getxattr, - [OP_SETXATTR] = (nfsd4_enc)nfsd4_encode_setxattr, - [OP_LISTXATTRS] = (nfsd4_enc)nfsd4_encode_listxattrs, - [OP_REMOVEXATTR] = (nfsd4_enc)nfsd4_encode_removexattr, + [OP_GETXATTR] = nfsd4_encode_getxattr, + [OP_SETXATTR] = nfsd4_encode_setxattr, + [OP_LISTXATTRS] = nfsd4_encode_listxattrs, + [OP_REMOVEXATTR] = nfsd4_encode_removexattr, }; /* @@ -5311,10 +5404,8 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) __be32 *p; p = xdr_reserve_space(xdr, 8); - if (!p) { - WARN_ON_ONCE(1); - return; - } + if (!p) + goto release; *p++ = cpu_to_be32(op->opnum); post_err_offset = xdr->buf->len; @@ -5329,8 +5420,6 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) op->status = encoder(resp, op->status, &op->u); if (op->status) trace_nfsd_compound_encode_err(rqstp, op->opnum, op->status); - if (opdesc && opdesc->op_release) - opdesc->op_release(&op->u); xdr_commit_encode(xdr); /* nfsd4_check_resp_size guarantees enough room for error status */ @@ -5370,8 +5459,10 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) so->so_replay.rp_buf, len); } status: - /* Note that op->status is already in network byte order: */ - write_bytes_to_xdr_buf(xdr->buf, post_err_offset - 4, &op->status, 4); + *p = op->status; +release: + if (opdesc && opdesc->op_release) + opdesc->op_release(&op->u); } /* @@ -5402,7 +5493,7 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp) struct nfsd4_compoundargs *args = rqstp->rq_argp; if (args->ops != args->iops) { - kfree(args->ops); + vfree(args->ops); args->ops = args->iops; } while (args->to_free) { @@ -5412,40 +5503,42 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp) } } -int -nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd4_compoundargs *args = rqstp->rq_argp; /* svcxdr_tmp_alloc */ args->to_free = NULL; - args->xdr = &rqstp->rq_arg_stream; + args->xdr = xdr; args->ops = args->iops; args->rqstp = rqstp; return nfsd4_decode_compound(args); } -int -nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p) +bool +nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd4_compoundres *resp = rqstp->rq_resp; - struct xdr_buf *buf = resp->xdr->buf; + __be32 *p; - WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len + - buf->tail[0].iov_len); + /* + * Send buffer space for the following items is reserved + * at the top of nfsd4_proc_compound(). + */ + p = resp->statusp; - *p = resp->cstate.status; + *p++ = resp->cstate.status; - rqstp->rq_next_page = resp->xdr->page_ptr + 1; + rqstp->rq_next_page = xdr->page_ptr + 1; - p = resp->tagp; *p++ = htonl(resp->taglen); memcpy(p, resp->tag, resp->taglen); p += XDR_QUADLEN(resp->taglen); *p++ = htonl(resp->opcnt); nfsd4_sequence_done(resp); - return 1; + return true; } diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 830bb8493c7f..2b5417e06d80 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -84,12 +84,6 @@ nfsd_hashsize(unsigned int limit) return roundup_pow_of_two(limit / TARGET_BUCKET_SIZE); } -static u32 -nfsd_cache_hash(__be32 xid, struct nfsd_net *nn) -{ - return hash_32(be32_to_cpu(xid), nn->maskbits); -} - static struct svc_cacherep * nfsd_reply_cache_alloc(struct svc_rqst *rqstp, __wsum csum, struct nfsd_net *nn) @@ -241,8 +235,16 @@ lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp) list_move_tail(&rp->c_lru, &b->lru_head); } -static long -prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn) +static noinline struct nfsd_drc_bucket * +nfsd_cache_bucket_find(__be32 xid, struct nfsd_net *nn) +{ + unsigned int hash = hash_32((__force u32)xid, nn->maskbits); + + return &nn->drc_hashtbl[hash]; +} + +static long prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn, + unsigned int max) { struct svc_cacherep *rp, *tmp; long freed = 0; @@ -258,11 +260,17 @@ prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn) time_before(jiffies, rp->c_timestamp + RC_EXPIRE)) break; nfsd_reply_cache_free_locked(b, rp, nn); - freed++; + if (max && freed++ > max) + break; } return freed; } +static long nfsd_prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn) +{ + return prune_bucket(b, nn, 3); +} + /* * Walk the LRU list and prune off entries that are older than RC_EXPIRE. * Also prune the oldest ones when the total exceeds the max number of entries. @@ -279,7 +287,7 @@ prune_cache_entries(struct nfsd_net *nn) if (list_empty(&b->lru_head)) continue; spin_lock(&b->cache_lock); - freed += prune_bucket(b, nn); + freed += prune_bucket(b, nn, 0); spin_unlock(&b->cache_lock); } return freed; @@ -413,12 +421,10 @@ out: */ int nfsd_cache_lookup(struct svc_rqst *rqstp) { - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct nfsd_net *nn; struct svc_cacherep *rp, *found; - __be32 xid = rqstp->rq_xid; __wsum csum; - u32 hash = nfsd_cache_hash(xid, nn); - struct nfsd_drc_bucket *b = &nn->drc_hashtbl[hash]; + struct nfsd_drc_bucket *b; int type = rqstp->rq_cachetype; int rtn = RC_DOIT; @@ -434,17 +440,16 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp) * Since the common case is a cache miss followed by an insert, * preallocate an entry. */ + nn = net_generic(SVC_NET(rqstp), nfsd_net_id); rp = nfsd_reply_cache_alloc(rqstp, csum, nn); if (!rp) goto out; + b = nfsd_cache_bucket_find(rqstp->rq_xid, nn); spin_lock(&b->cache_lock); found = nfsd_cache_insert(b, rp, nn); - if (found != rp) { - nfsd_reply_cache_free_locked(NULL, rp, nn); - rp = found; + if (found != rp) goto found_entry; - } nfsd_stats_rc_misses_inc(); rqstp->rq_cacherep = rp; @@ -453,8 +458,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp) atomic_inc(&nn->num_drc_entries); nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp)); - /* go ahead and prune the cache */ - prune_bucket(b, nn); + nfsd_prune_bucket(b, nn); out_unlock: spin_unlock(&b->cache_lock); @@ -463,8 +467,10 @@ out: found_entry: /* We found a matching entry which is either in progress or done. */ + nfsd_reply_cache_free_locked(NULL, rp, nn); nfsd_stats_rc_hits_inc(); rtn = RC_DROPIT; + rp = found; /* Request being processed */ if (rp->c_state == RC_INPROG) @@ -523,7 +529,6 @@ void nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct svc_cacherep *rp = rqstp->rq_cacherep; struct kvec *resv = &rqstp->rq_res.head[0], *cachv; - u32 hash; struct nfsd_drc_bucket *b; int len; size_t bufsize = 0; @@ -531,8 +536,7 @@ void nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) if (!rp) return; - hash = nfsd_cache_hash(rp->c_key.k_xid, nn); - b = &nn->drc_hashtbl[hash]; + b = nfsd_cache_bucket_find(rp->c_key.k_xid, nn); len = resv->iov_len - ((char*)statp - (char*)resv->iov_base); len >>= 2; @@ -599,9 +603,10 @@ nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data) * scraping this file for info should test the labels to ensure they're * getting the correct field. */ -static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v) +int nfsd_reply_cache_stats_show(struct seq_file *m, void *v) { - struct nfsd_net *nn = m->private; + struct nfsd_net *nn = net_generic(file_inode(m->file)->i_sb->s_fs_info, + nfsd_net_id); seq_printf(m, "max entries: %u\n", nn->max_drc_entries); seq_printf(m, "num entries: %u\n", @@ -621,11 +626,3 @@ static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v) seq_printf(m, "cachesize at longest: %u\n", nn->longest_chain_cachesize); return 0; } - -int nfsd_reply_cache_stats_open(struct inode *inode, struct file *file) -{ - struct nfsd_net *nn = net_generic(file_inode(file)->i_sb->s_fs_info, - nfsd_net_id); - - return single_open(file, nfsd_reply_cache_stats_show, nn); -} diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index cb73c1292562..f77f00c93172 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -25,6 +25,7 @@ #include "state.h" #include "netns.h" #include "pnfs.h" +#include "filecache.h" /* * We have a single directory with several nodes in it. @@ -45,6 +46,7 @@ enum { NFSD_Ports, NFSD_MaxBlkSize, NFSD_MaxConnections, + NFSD_Filecache, NFSD_SupportedEnctypes, /* * The below MUST come last. Otherwise we leave a hole in nfsd_files[] @@ -183,17 +185,7 @@ static int export_features_show(struct seq_file *m, void *v) return 0; } -static int export_features_open(struct inode *inode, struct file *file) -{ - return single_open(file, export_features_show, NULL); -} - -static const struct file_operations export_features_operations = { - .open = export_features_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(export_features); #if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE) static int supported_enctypes_show(struct seq_file *m, void *v) @@ -202,17 +194,7 @@ static int supported_enctypes_show(struct seq_file *m, void *v) return 0; } -static int supported_enctypes_open(struct inode *inode, struct file *file) -{ - return single_open(file, supported_enctypes_show, NULL); -} - -static const struct file_operations supported_enctypes_ops = { - .open = supported_enctypes_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(supported_enctypes); #endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ static const struct file_operations pool_stats_operations = { @@ -222,12 +204,9 @@ static const struct file_operations pool_stats_operations = { .release = nfsd_pool_stats_release, }; -static const struct file_operations reply_cache_stats_operations = { - .open = nfsd_reply_cache_stats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(nfsd_reply_cache_stats); + +DEFINE_SHOW_ATTRIBUTE(nfsd_file_cache_stats); /*----------------------------------------------------------------------------*/ /* @@ -395,12 +374,12 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) auth_domain_put(dom); if (len) return len; - + mesg = buf; len = SIMPLE_TRANSACTION_LIMIT; - qword_addhex(&mesg, &len, (char*)&fh.fh_base, fh.fh_size); + qword_addhex(&mesg, &len, fh.fh_raw, fh.fh_size); mesg[-1] = '\n'; - return mesg - buf; + return mesg - buf; } /* @@ -602,7 +581,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) cmd = sign == '-' ? NFSD_CLEAR : NFSD_SET; switch(num) { +#ifdef CONFIG_NFSD_V2 case 2: +#endif case 3: nfsd_vers(nn, num, cmd); break; @@ -622,7 +603,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) } break; default: - return -EINVAL; + /* Ignore requests to disable non-existent versions */ + if (cmd == NFSD_SET) + return -EINVAL; } vers += len + 1; } while ((len = qword_get(&mesg, vers, size)) > 0); @@ -633,7 +616,6 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) } /* Now write current state into reply buffer */ - len = 0; sep = ""; remaining = SIMPLE_TRANSACTION_LIMIT; for (num=2 ; num <= 4 ; num++) { @@ -727,28 +709,25 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred char *mesg = buf; int fd, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; err = get_int(&mesg, &fd); if (err != 0 || fd < 0) return -EINVAL; - if (svc_alien_sock(net, fd)) { - printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__); - return -EINVAL; - } - err = nfsd_create_serv(net); if (err != 0) return err; - err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); - if (err < 0) { - nfsd_destroy(net); - return err; - } + serv = nn->nfsd_serv; + err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); - /* Decrease the count, but don't shut down the service */ - nn->nfsd_serv->sv_nrthreads--; + if (err < 0 && !serv->sv_nrthreads && !nn->keep_active) + nfsd_last_thread(net); + else if (err >= 0 && !serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + svc_get(serv); + + svc_put(serv); return err; } @@ -762,6 +741,7 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr struct svc_xprt *xprt; int port, err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; if (sscanf(buf, "%15s %5u", transport, &port) != 2) return -EINVAL; @@ -773,30 +753,33 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr if (err != 0) return err; - err = svc_create_xprt(nn->nfsd_serv, transport, net, - PF_INET, port, SVC_SOCK_ANONYMOUS, cred); + serv = nn->nfsd_serv; + err = svc_xprt_create(serv, transport, net, + PF_INET, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0) goto out_err; - err = svc_create_xprt(nn->nfsd_serv, transport, net, - PF_INET6, port, SVC_SOCK_ANONYMOUS, cred); + err = svc_xprt_create(serv, transport, net, + PF_INET6, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; - /* Decrease the count, but don't shut down the service */ - nn->nfsd_serv->sv_nrthreads--; + if (!serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + svc_get(serv); + + svc_put(serv); return 0; out_close: - xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port); + xprt = svc_find_xprt(serv, transport, net, PF_INET, port); if (xprt != NULL) { - svc_close_xprt(xprt); + svc_xprt_close(xprt); svc_xprt_put(xprt); } out_err: - if (!list_empty(&nn->nfsd_serv->sv_permsocks)) - nn->nfsd_serv->sv_nrthreads--; - else - nfsd_destroy(net); + if (!serv->sv_nrthreads && !nn->keep_active) + nfsd_last_thread(net); + + svc_put(serv); return err; } @@ -1359,7 +1342,7 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) /* Per-export io stats use same ops as exports file */ [NFSD_Export_Stats] = {"export_stats", &exports_nfsd_operations, S_IRUGO}, [NFSD_Export_features] = {"export_features", - &export_features_operations, S_IRUGO}, + &export_features_fops, S_IRUGO}, [NFSD_FO_UnlockIP] = {"unlock_ip", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_FO_UnlockFS] = {"unlock_filesystem", @@ -1368,13 +1351,16 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) [NFSD_Threads] = {"threads", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Pool_Threads] = {"pool_threads", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Pool_Stats] = {"pool_stats", &pool_stats_operations, S_IRUGO}, - [NFSD_Reply_Cache_Stats] = {"reply_cache_stats", &reply_cache_stats_operations, S_IRUGO}, + [NFSD_Reply_Cache_Stats] = {"reply_cache_stats", + &nfsd_reply_cache_stats_fops, S_IRUGO}, [NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_MaxConnections] = {"max_connections", &transaction_ops, S_IWUSR|S_IRUGO}, + [NFSD_Filecache] = {"filecache", &nfsd_file_cache_stats_fops, S_IRUGO}, #if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE) - [NFSD_SupportedEnctypes] = {"supported_krb5_enctypes", &supported_enctypes_ops, S_IRUGO}, + [NFSD_SupportedEnctypes] = {"supported_krb5_enctypes", + &supported_enctypes_fops, S_IRUGO}, #endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR}, @@ -1474,25 +1460,16 @@ static __net_init int nfsd_init_net(struct net *net) goto out_idmap_error; nn->nfsd_versions = NULL; nn->nfsd4_minorversions = NULL; + nfsd4_init_leases_net(nn); retval = nfsd_reply_cache_init(nn); if (retval) - goto out_drc_error; - nn->nfsd4_lease = 90; /* default lease time */ - nn->nfsd4_grace = 90; - nn->somebody_reclaimed = false; - nn->track_reclaim_completes = false; - nn->clverifier_counter = prandom_u32(); - nn->clientid_base = prandom_u32(); - nn->clientid_counter = nn->clientid_base + 1; - nn->s2s_cp_cl_id = nn->clientid_counter++; - - atomic_set(&nn->ntf_refcnt, 0); - init_waitqueue_head(&nn->ntf_wq); - seqlock_init(&nn->boot_lock); + goto out_cache_error; + get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key)); + seqlock_init(&nn->writeverf_lock); return 0; -out_drc_error: +out_cache_error: nfsd_idmap_shutdown(net); out_idmap_error: nfsd_export_shutdown(net); @@ -1520,7 +1497,6 @@ static struct pernet_operations nfsd_net_ops = { static int __init init_nfsd(void) { int retval; - printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n"); retval = nfsd4_init_slabs(); if (retval) @@ -1538,20 +1514,25 @@ static int __init init_nfsd(void) retval = create_proc_exports_entry(); if (retval) goto out_free_lockd; - retval = register_filesystem(&nfsd_fs_type); - if (retval) - goto out_free_exports; retval = register_pernet_subsys(&nfsd_net_ops); if (retval < 0) - goto out_free_filesystem; + goto out_free_exports; retval = register_cld_notifier(); if (retval) + goto out_free_subsys; + retval = nfsd4_create_laundry_wq(); + if (retval) + goto out_free_cld; + retval = register_filesystem(&nfsd_fs_type); + if (retval) goto out_free_all; return 0; out_free_all: + nfsd4_destroy_laundry_wq(); +out_free_cld: + unregister_cld_notifier(); +out_free_subsys: unregister_pernet_subsys(&nfsd_net_ops); -out_free_filesystem: - unregister_filesystem(&nfsd_fs_type); out_free_exports: remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); @@ -1569,6 +1550,8 @@ out_free_slabs: static void __exit exit_nfsd(void) { + unregister_filesystem(&nfsd_fs_type); + nfsd4_destroy_laundry_wq(); unregister_cld_notifier(); unregister_pernet_subsys(&nfsd_net_ops); nfsd_drc_slab_free(); @@ -1578,7 +1561,6 @@ static void __exit exit_nfsd(void) nfsd_lockd_shutdown(); nfsd4_free_slabs(); nfsd4_exit_pnfs(); - unregister_filesystem(&nfsd_fs_type); } MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 9664303afdaf..013bfa24ced2 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -64,8 +64,7 @@ struct readdir_cd { extern struct svc_program nfsd_program; -extern const struct svc_version nfsd_version2, nfsd_version3, - nfsd_version4; +extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; extern unsigned long nfsd_drc_max_mem; @@ -78,8 +77,10 @@ extern const struct seq_operations nfs_exports_op; */ struct nfsd_voidargs { }; struct nfsd_voidres { }; -int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p); -int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p); +bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, + struct xdr_stream *xdr); +bool nfssvc_encode_voidres(struct svc_rqst *rqstp, + struct xdr_stream *xdr); /* * Function prototypes. @@ -95,8 +96,6 @@ int nfsd_pool_stats_open(struct inode *, struct file *); int nfsd_pool_stats_release(struct inode *, struct file *); void nfsd_shutdown_threads(struct net *net); -void nfsd_destroy(struct net *net); - bool i_am_nfsd(void); struct nfsdfs_client { @@ -132,6 +131,7 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change); int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change); void nfsd_reset_versions(struct nfsd_net *nn); int nfsd_create_serv(struct net *net); +void nfsd_last_thread(struct net *net); extern int nfsd_max_blksize; @@ -160,6 +160,9 @@ void nfs4_state_shutdown_net(struct net *net); int nfs4_reset_recoverydir(char *recdir); char * nfs4_recoverydir(void); bool nfsd4_spo_must_allow(struct svc_rqst *rqstp); +int nfsd4_create_laundry_wq(void); +void nfsd4_destroy_laundry_wq(void); +bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode); #else static inline int nfsd4_init_slabs(void) { return 0; } static inline void nfsd4_free_slabs(void) { } @@ -173,6 +176,13 @@ static inline bool nfsd4_spo_must_allow(struct svc_rqst *rqstp) { return false; } +static inline int nfsd4_create_laundry_wq(void) { return 0; }; +static inline void nfsd4_destroy_laundry_wq(void) {}; +static inline bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, + struct inode *inode) +{ + return false; +} #endif /* @@ -334,6 +344,10 @@ void nfsd_lockd_shutdown(void); #define COMPOUND_ERR_SLACK_SPACE 16 /* OP_SETATTR */ #define NFSD_LAUNDROMAT_MINTIMEOUT 1 /* seconds */ +#define NFSD_COURTESY_CLIENT_TIMEOUT (24 * 60 * 60) /* seconds */ +#define NFSD_CLIENT_MAX_TRIM_PER_RUN 128 +#define NFS4_CLIENTS_PER_GB 1024 +#define NFSD_DELEGRETURN_TIMEOUT (HZ / 34) /* 30ms */ /* * The following attributes are currently not supported by the NFSv4 server: @@ -362,7 +376,7 @@ void nfsd_lockd_shutdown(void); | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP | FATTR4_WORD1_RAWDEV \ | FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL \ | FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS | FATTR4_WORD1_TIME_ACCESS_SET \ - | FATTR4_WORD1_TIME_DELTA | FATTR4_WORD1_TIME_METADATA \ + | FATTR4_WORD1_TIME_DELTA | FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_CREATE \ | FATTR4_WORD1_TIME_MODIFY | FATTR4_WORD1_TIME_MODIFY_SET | FATTR4_WORD1_MOUNTED_ON_FILEID) #define NFSD4_SUPPORTED_ATTRS_WORD2 0 @@ -458,7 +472,8 @@ static inline bool nfsd_attrs_supported(u32 minorversion, const u32 *bmval) (FATTR4_WORD0_SIZE | FATTR4_WORD0_ACL) #define NFSD_WRITEABLE_ATTRS_WORD1 \ (FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP \ - | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) + | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_CREATE \ + | FATTR4_WORD1_TIME_MODIFY_SET) #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #define MAYBE_FATTR4_WORD2_SECURITY_LABEL \ FATTR4_WORD2_SECURITY_LABEL @@ -488,12 +503,16 @@ extern void unregister_cld_notifier(void); extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn); #endif +extern void nfsd4_init_leases_net(struct nfsd_net *nn); + #else /* CONFIG_NFSD_V4 */ static inline int nfsd4_is_junction(struct dentry *dentry) { return 0; } +static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { }; + #define register_cld_notifier() 0 #define unregister_cld_notifier() do { } while(0) diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index c475d2271f9c..8c52b6c9d31a 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -154,11 +154,12 @@ static inline __be32 check_pseudo_root(struct svc_rqst *rqstp, static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) { struct knfsd_fh *fh = &fhp->fh_handle; - struct fid *fid = NULL, sfid; + struct fid *fid = NULL; struct svc_export *exp; struct dentry *dentry; int fileid_type; int data_left = fh->fh_size/4; + int len; __be32 error; error = nfserr_stale; @@ -167,48 +168,35 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) if (rqstp->rq_vers == 4 && fh->fh_size == 0) return nfserr_nofilehandle; - if (fh->fh_version == 1) { - int len; - - if (--data_left < 0) - return error; - if (fh->fh_auth_type != 0) - return error; - len = key_len(fh->fh_fsid_type) / 4; - if (len == 0) - return error; - if (fh->fh_fsid_type == FSID_MAJOR_MINOR) { - /* deprecated, convert to type 3 */ - len = key_len(FSID_ENCODE_DEV)/4; - fh->fh_fsid_type = FSID_ENCODE_DEV; - /* - * struct knfsd_fh uses host-endian fields, which are - * sometimes used to hold net-endian values. This - * confuses sparse, so we must use __force here to - * keep it from complaining. - */ - fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fh->fh_fsid[0]), - ntohl((__force __be32)fh->fh_fsid[1]))); - fh->fh_fsid[1] = fh->fh_fsid[2]; - } - data_left -= len; - if (data_left < 0) - return error; - exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid); - fid = (struct fid *)(fh->fh_fsid + len); - } else { - __u32 tfh[2]; - dev_t xdev; - ino_t xino; - - if (fh->fh_size != NFS_FHSIZE) - return error; - /* assume old filehandle format */ - xdev = old_decode_dev(fh->ofh_xdev); - xino = u32_to_ino_t(fh->ofh_xino); - mk_fsid(FSID_DEV, tfh, xdev, xino, 0, NULL); - exp = rqst_exp_find(rqstp, FSID_DEV, tfh); + if (fh->fh_version != 1) + return error; + + if (--data_left < 0) + return error; + if (fh->fh_auth_type != 0) + return error; + len = key_len(fh->fh_fsid_type) / 4; + if (len == 0) + return error; + if (fh->fh_fsid_type == FSID_MAJOR_MINOR) { + /* deprecated, convert to type 3 */ + len = key_len(FSID_ENCODE_DEV)/4; + fh->fh_fsid_type = FSID_ENCODE_DEV; + /* + * struct knfsd_fh uses host-endian fields, which are + * sometimes used to hold net-endian values. This + * confuses sparse, so we must use __force here to + * keep it from complaining. + */ + fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fh->fh_fsid[0]), + ntohl((__force __be32)fh->fh_fsid[1]))); + fh->fh_fsid[1] = fh->fh_fsid[2]; } + data_left -= len; + if (data_left < 0) + return error; + exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid); + fid = (struct fid *)(fh->fh_fsid + len); error = nfserr_stale; if (IS_ERR(exp)) { @@ -253,18 +241,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) if (rqstp->rq_vers > 2) error = nfserr_badhandle; - if (fh->fh_version != 1) { - sfid.i32.ino = fh->ofh_ino; - sfid.i32.gen = fh->ofh_generation; - sfid.i32.parent_ino = fh->ofh_dirino; - fid = &sfid; - data_left = 3; - if (fh->ofh_dirino == 0) - fileid_type = FILEID_INO32_GEN; - else - fileid_type = FILEID_INO32_GEN_PARENT; - } else - fileid_type = fh->fh_fileid_type; + fileid_type = fh->fh_fileid_type; if (fileid_type == FILEID_ROOT) dentry = dget(exp->ex_path.dentry); @@ -354,8 +331,6 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) struct dentry *dentry; __be32 error; - dprintk("nfsd: fh_verify(%s)\n", SVCFH_fmt(fhp)); - if (!fhp->fh_dentry) { error = nfsd_set_fh_dentry(rqstp, fhp); if (error) @@ -363,6 +338,9 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) } dentry = fhp->fh_dentry; exp = fhp->fh_export; + + trace_nfsd_fh_verify(rqstp, fhp, type, access); + /* * We still have to do all these permission checks, even when * fh_dentry is already set: @@ -414,14 +392,8 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) skip_pseudoflavor_check: /* Finally, check access permissions. */ error = nfsd_permission(rqstp, exp, dentry, access); - - if (error) { - dprintk("fh_verify: %pd2 permission failure, " - "acc=%x, error=%d\n", - dentry, - access, ntohl(error)); - } out: + trace_nfsd_fh_verify_err(rqstp, fhp, type, access, error); if (error == nfserr_stale) nfsd_stats_fh_stale_inc(exp); return error; @@ -452,20 +424,6 @@ static void _fh_update(struct svc_fh *fhp, struct svc_export *exp, } } -/* - * for composing old style file handles - */ -static inline void _fh_update_old(struct dentry *dentry, - struct svc_export *exp, - struct knfsd_fh *fh) -{ - fh->ofh_ino = ino_t_to_u32(d_inode(dentry)->i_ino); - fh->ofh_generation = d_inode(dentry)->i_generation; - if (d_is_dir(dentry) || - (exp->ex_flags & NFSEXP_NOSUBTREECHECK)) - fh->ofh_dirino = 0; -} - static bool is_root_export(struct svc_export *exp) { return exp->ex_path.dentry == exp->ex_path.dentry->d_sb->s_root; @@ -562,9 +520,6 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, /* ref_fh is a reference file handle. * if it is non-null and for the same filesystem, then we should compose * a filehandle which is of the same version, where possible. - * Currently, that means that if ref_fh->fh_handle.fh_version == 0xca - * Then create a 32byte filehandle using nfs_fhbase_old - * */ struct inode * inode = d_inode(dentry); @@ -588,7 +543,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, if (ref_fh == fhp) fh_put(ref_fh); - if (fhp->fh_locked || fhp->fh_dentry) { + if (fhp->fh_dentry) { printk(KERN_ERR "fh_compose: fh %pd2 not initialized!\n", dentry); } @@ -600,35 +555,21 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, fhp->fh_dentry = dget(dentry); /* our internal copy */ fhp->fh_export = exp_get(exp); - if (fhp->fh_handle.fh_version == 0xca) { - /* old style filehandle please */ - memset(&fhp->fh_handle.fh_base, 0, NFS_FHSIZE); - fhp->fh_handle.fh_size = NFS_FHSIZE; - fhp->fh_handle.ofh_dcookie = 0xfeebbaca; - fhp->fh_handle.ofh_dev = old_encode_dev(ex_dev); - fhp->fh_handle.ofh_xdev = fhp->fh_handle.ofh_dev; - fhp->fh_handle.ofh_xino = - ino_t_to_u32(d_inode(exp->ex_path.dentry)->i_ino); - fhp->fh_handle.ofh_dirino = ino_t_to_u32(parent_ino(dentry)); - if (inode) - _fh_update_old(dentry, exp, &fhp->fh_handle); - } else { - fhp->fh_handle.fh_size = - key_len(fhp->fh_handle.fh_fsid_type) + 4; - fhp->fh_handle.fh_auth_type = 0; - - mk_fsid(fhp->fh_handle.fh_fsid_type, - fhp->fh_handle.fh_fsid, - ex_dev, - d_inode(exp->ex_path.dentry)->i_ino, - exp->ex_fsid, exp->ex_uuid); - - if (inode) - _fh_update(fhp, exp, dentry); - if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) { - fh_put(fhp); - return nfserr_opnotsupp; - } + fhp->fh_handle.fh_size = + key_len(fhp->fh_handle.fh_fsid_type) + 4; + fhp->fh_handle.fh_auth_type = 0; + + mk_fsid(fhp->fh_handle.fh_fsid_type, + fhp->fh_handle.fh_fsid, + ex_dev, + d_inode(exp->ex_path.dentry)->i_ino, + exp->ex_fsid, exp->ex_uuid); + + if (inode) + _fh_update(fhp, exp, dentry); + if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) { + fh_put(fhp); + return nfserr_opnotsupp; } return 0; @@ -649,16 +590,12 @@ fh_update(struct svc_fh *fhp) dentry = fhp->fh_dentry; if (d_really_is_negative(dentry)) goto out_negative; - if (fhp->fh_handle.fh_version != 1) { - _fh_update_old(dentry, fhp->fh_export, &fhp->fh_handle); - } else { - if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT) - return 0; + if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT) + return 0; - _fh_update(fhp, fhp->fh_export, dentry); - if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) - return nfserr_opnotsupp; - } + _fh_update(fhp, fhp->fh_export, dentry); + if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) + return nfserr_opnotsupp; return 0; out_bad: printk(KERN_ERR "fh_update: fh not verified!\n"); @@ -669,6 +606,85 @@ out_negative: return nfserr_serverfault; } +/** + * fh_fill_pre_attrs - Fill in pre-op attributes + * @fhp: file handle to be updated + * + */ +void fh_fill_pre_attrs(struct svc_fh *fhp) +{ + bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); + struct inode *inode; + struct kstat stat; + __be32 err; + + if (fhp->fh_no_wcc || fhp->fh_pre_saved) + return; + + inode = d_inode(fhp->fh_dentry); + err = fh_getattr(fhp, &stat); + if (err) { + /* Grab the times from inode anyway */ + stat.mtime = inode->i_mtime; + stat.ctime = inode->i_ctime; + stat.size = inode->i_size; + } + if (v4) + fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); + + fhp->fh_pre_mtime = stat.mtime; + fhp->fh_pre_ctime = stat.ctime; + fhp->fh_pre_size = stat.size; + fhp->fh_pre_saved = true; +} + +/** + * fh_fill_post_attrs - Fill in post-op attributes + * @fhp: file handle to be updated + * + */ +void fh_fill_post_attrs(struct svc_fh *fhp) +{ + bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); + struct inode *inode = d_inode(fhp->fh_dentry); + __be32 err; + + if (fhp->fh_no_wcc) + return; + + if (fhp->fh_post_saved) + printk("nfsd: inode locked twice during operation.\n"); + + err = fh_getattr(fhp, &fhp->fh_post_attr); + if (err) { + fhp->fh_post_saved = false; + fhp->fh_post_attr.ctime = inode->i_ctime; + } else + fhp->fh_post_saved = true; + if (v4) + fhp->fh_post_change = + nfsd4_change_attribute(&fhp->fh_post_attr, inode); +} + +/** + * fh_fill_both_attrs - Fill pre-op and post-op attributes + * @fhp: file handle to be updated + * + * This is used when the directory wasn't changed, but wcc attributes + * are needed anyway. + */ +void fh_fill_both_attrs(struct svc_fh *fhp) +{ + fh_fill_post_attrs(fhp); + if (!fhp->fh_post_saved) + return; + fhp->fh_pre_change = fhp->fh_post_change; + fhp->fh_pre_mtime = fhp->fh_post_attr.mtime; + fhp->fh_pre_ctime = fhp->fh_post_attr.ctime; + fhp->fh_pre_size = fhp->fh_post_attr.size; + fhp->fh_pre_saved = true; +} + /* * Release a file handle. */ @@ -678,10 +694,9 @@ fh_put(struct svc_fh *fhp) struct dentry * dentry = fhp->fh_dentry; struct svc_export * exp = fhp->fh_export; if (dentry) { - fh_unlock(fhp); fhp->fh_dentry = NULL; dput(dentry); - fh_clear_wcc(fhp); + fh_clear_pre_post_attrs(fhp); } fh_drop_write(fhp); if (exp) { @@ -698,16 +713,11 @@ fh_put(struct svc_fh *fhp) char * SVCFH_fmt(struct svc_fh *fhp) { struct knfsd_fh *fh = &fhp->fh_handle; + static char buf[2+1+1+64*3+1]; - static char buf[80]; - sprintf(buf, "%d: %08x %08x %08x %08x %08x %08x", - fh->fh_size, - fh->fh_base.fh_pad[0], - fh->fh_base.fh_pad[1], - fh->fh_base.fh_pad[2], - fh->fh_base.fh_pad[3], - fh->fh_base.fh_pad[4], - fh->fh_base.fh_pad[5]); + if (fh->fh_size < 0 || fh->fh_size> 64) + return "bad-fh"; + sprintf(buf, "%d: %*ph", fh->fh_size, fh->fh_size, fh->fh_raw); return buf; } diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 6106697adc04..513e028b0bbe 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -10,9 +10,56 @@ #include <linux/crc32.h> #include <linux/sunrpc/svc.h> -#include <uapi/linux/nfsd/nfsfh.h> #include <linux/iversion.h> #include <linux/exportfs.h> +#include <linux/nfs4.h> + +/* + * The file handle starts with a sequence of four-byte words. + * The first word contains a version number (1) and three descriptor bytes + * that tell how the remaining 3 variable length fields should be handled. + * These three bytes are auth_type, fsid_type and fileid_type. + * + * All four-byte values are in host-byte-order. + * + * The auth_type field is deprecated and must be set to 0. + * + * The fsid_type identifies how the filesystem (or export point) is + * encoded. + * Current values: + * 0 - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number + * NOTE: we cannot use the kdev_t device id value, because kdev_t.h + * says we mustn't. We must break it up and reassemble. + * 1 - 4 byte user specified identifier + * 2 - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED + * 3 - 4 byte device id, encoded for user-space, 4 byte inode number + * 4 - 4 byte inode number and 4 byte uuid + * 5 - 8 byte uuid + * 6 - 16 byte uuid + * 7 - 8 byte inode number and 16 byte uuid + * + * The fileid_type identifies how the file within the filesystem is encoded. + * The values for this field are filesystem specific, exccept that + * filesystems must not use the values '0' or '0xff'. 'See enum fid_type' + * in include/linux/exportfs.h for currently registered values. + */ + +struct knfsd_fh { + unsigned int fh_size; /* + * Points to the current size while + * building a new file handle. + */ + union { + char fh_raw[NFS4_FHSIZE]; + struct { + u8 fh_version; /* == 1 */ + u8 fh_auth_type; /* deprecated */ + u8 fh_fsid_type; + u8 fh_fileid_type; + u32 fh_fsid[]; /* flexible-array member */ + }; + }; +}; static inline __u32 ino_t_to_u32(ino_t ino) { @@ -34,7 +81,6 @@ typedef struct svc_fh { struct dentry * fh_dentry; /* validated dentry */ struct svc_export * fh_export; /* export pointer */ - bool fh_locked; /* inode locked by us */ bool fh_want_write; /* remount protection taken */ bool fh_no_wcc; /* no wcc data needed */ bool fh_no_atomic_attr; @@ -43,11 +89,10 @@ typedef struct svc_fh { * operation */ int fh_flags; /* FH flags */ -#ifdef CONFIG_NFSD_V3 bool fh_post_saved; /* post-op attrs saved */ bool fh_pre_saved; /* pre-op attrs saved */ - /* Pre-op attributes saved during fh_lock */ + /* Pre-op attributes saved when inode is locked */ __u64 fh_pre_size; /* size before operation */ struct timespec64 fh_pre_mtime; /* mtime before oper */ struct timespec64 fh_pre_ctime; /* ctime before oper */ @@ -57,10 +102,9 @@ typedef struct svc_fh { */ u64 fh_pre_change; - /* Post-op attributes saved in fh_unlock */ + /* Post-op attributes saved in fh_fill_post_attrs() */ struct kstat fh_post_attr; /* full attrs after operation */ u64 fh_post_change; /* nfsv4 change; see above */ -#endif /* CONFIG_NFSD_V3 */ } svc_fh; #define NFSD4_FH_FOREIGN (1<<0) #define SET_FH_FLAG(c, f) ((c)->fh_flags |= (f)) @@ -176,19 +220,19 @@ __be32 fh_update(struct svc_fh *); void fh_put(struct svc_fh *); static __inline__ struct svc_fh * -fh_copy(struct svc_fh *dst, struct svc_fh *src) +fh_copy(struct svc_fh *dst, const struct svc_fh *src) { - WARN_ON(src->fh_dentry || src->fh_locked); - + WARN_ON(src->fh_dentry); + *dst = *src; return dst; } static inline void -fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src) +fh_copy_shallow(struct knfsd_fh *dst, const struct knfsd_fh *src) { dst->fh_size = src->fh_size; - memcpy(&dst->fh_base, &src->fh_base, src->fh_size); + memcpy(&dst->fh_raw, &src->fh_raw, src->fh_size); } static __inline__ struct svc_fh * @@ -199,16 +243,18 @@ fh_init(struct svc_fh *fhp, int maxsize) return fhp; } -static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) +static inline bool fh_match(const struct knfsd_fh *fh1, + const struct knfsd_fh *fh2) { if (fh1->fh_size != fh2->fh_size) return false; - if (memcmp(fh1->fh_base.fh_pad, fh2->fh_base.fh_pad, fh1->fh_size) != 0) + if (memcmp(fh1->fh_raw, fh2->fh_raw, fh1->fh_size) != 0) return false; return true; } -static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) +static inline bool fh_fsid_match(const struct knfsd_fh *fh1, + const struct knfsd_fh *fh2) { if (fh1->fh_fsid_type != fh2->fh_fsid_type) return false; @@ -227,7 +273,7 @@ static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) */ static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) { - return ~crc32_le(0xFFFFFFFF, (unsigned char *)&fh->fh_base, fh->fh_size); + return ~crc32_le(0xFFFFFFFF, fh->fh_raw, fh->fh_size); } #else static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) @@ -236,13 +282,12 @@ static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) } #endif -#ifdef CONFIG_NFSD_V3 -/* - * The wcc data stored in current_fh should be cleared - * between compound ops. +/** + * fh_clear_pre_post_attrs - Reset pre/post attributes + * @fhp: file handle to be updated + * */ -static inline void -fh_clear_wcc(struct svc_fh *fhp) +static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp) { fhp->fh_post_saved = false; fhp->fh_pre_saved = false; @@ -276,59 +321,7 @@ static inline u64 nfsd4_change_attribute(struct kstat *stat, return time_to_chattr(&stat->ctime); } -extern void fill_pre_wcc(struct svc_fh *fhp); -extern void fill_post_wcc(struct svc_fh *fhp); -#else -#define fh_clear_wcc(ignored) -#define fill_pre_wcc(ignored) -#define fill_post_wcc(notused) -#endif /* CONFIG_NFSD_V3 */ - - -/* - * Lock a file handle/inode - * NOTE: both fh_lock and fh_unlock are done "by hand" in - * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once - * so, any changes here should be reflected there. - */ - -static inline void -fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) -{ - struct dentry *dentry = fhp->fh_dentry; - struct inode *inode; - - BUG_ON(!dentry); - - if (fhp->fh_locked) { - printk(KERN_WARNING "fh_lock: %pd2 already locked!\n", - dentry); - return; - } - - inode = d_inode(dentry); - inode_lock_nested(inode, subclass); - fill_pre_wcc(fhp); - fhp->fh_locked = true; -} - -static inline void -fh_lock(struct svc_fh *fhp) -{ - fh_lock_nested(fhp, I_MUTEX_NORMAL); -} - -/* - * Unlock a file handle/inode - */ -static inline void -fh_unlock(struct svc_fh *fhp) -{ - if (fhp->fh_locked) { - fill_post_wcc(fhp); - inode_unlock(d_inode(fhp->fh_dentry)); - fhp->fh_locked = false; - } -} - +extern void fh_fill_pre_attrs(struct svc_fh *fhp); +extern void fh_fill_post_attrs(struct svc_fh *fhp); +extern void fh_fill_both_attrs(struct svc_fh *fhp); #endif /* _LINUX_NFSD_NFSFH_H */ diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index b009da1dcbb5..9744443c3965 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -51,6 +51,9 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) struct nfsd_sattrargs *argp = rqstp->rq_argp; struct nfsd_attrstat *resp = rqstp->rq_resp; struct iattr *iap = &argp->attrs; + struct nfsd_attrs attrs = { + .na_iattr = iap, + }; struct svc_fh *fhp; dprintk("nfsd: SETATTR %s, valid=%x, size=%ld\n", @@ -100,7 +103,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) } } - resp->status = nfsd_setattr(rqstp, fhp, iap, 0, (time64_t)0); + resp->status = nfsd_setattr(rqstp, fhp, &attrs, 0, (time64_t)0); if (resp->status != nfs_ok) goto out; @@ -208,7 +211,7 @@ nfsd_proc_read(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - return rpc_drop_reply; + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } @@ -243,7 +246,7 @@ nfsd_proc_write(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - return rpc_drop_reply; + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } @@ -261,6 +264,9 @@ nfsd_proc_create(struct svc_rqst *rqstp) svc_fh *dirfhp = &argp->fh; svc_fh *newfhp = &resp->fh; struct iattr *attr = &argp->attrs; + struct nfsd_attrs attrs = { + .na_iattr = attr, + }; struct inode *inode; struct dentry *dchild; int type, mode; @@ -286,7 +292,7 @@ nfsd_proc_create(struct svc_rqst *rqstp) goto done; } - fh_lock_nested(dirfhp, I_MUTEX_PARENT); + inode_lock_nested(dirfhp->fh_dentry->d_inode, I_MUTEX_PARENT); dchild = lookup_one_len(argp->name, dirfhp->fh_dentry, argp->len); if (IS_ERR(dchild)) { resp->status = nfserrno(PTR_ERR(dchild)); @@ -385,9 +391,8 @@ nfsd_proc_create(struct svc_rqst *rqstp) resp->status = nfs_ok; if (!inode) { /* File doesn't exist. Create it and set attrs */ - resp->status = nfsd_create_locked(rqstp, dirfhp, argp->name, - argp->len, attr, type, rdev, - newfhp); + resp->status = nfsd_create_locked(rqstp, dirfhp, &attrs, type, + rdev, newfhp); } else if (type == S_IFREG) { dprintk("nfsd: existing %s, valid=%x, size=%ld\n", argp->name, attr->ia_valid, (long) attr->ia_size); @@ -397,13 +402,12 @@ nfsd_proc_create(struct svc_rqst *rqstp) */ attr->ia_valid &= ATTR_SIZE; if (attr->ia_valid) - resp->status = nfsd_setattr(rqstp, newfhp, attr, 0, + resp->status = nfsd_setattr(rqstp, newfhp, &attrs, 0, (time64_t)0); } out_unlock: - /* We don't really need to unlock, as fh_put does it. */ - fh_unlock(dirfhp); + inode_unlock(dirfhp->fh_dentry->d_inode); fh_drop_write(dirfhp); done: fh_put(dirfhp); @@ -473,6 +477,9 @@ nfsd_proc_symlink(struct svc_rqst *rqstp) { struct nfsd_symlinkargs *argp = rqstp->rq_argp; struct nfsd_stat *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; struct svc_fh newfh; if (argp->tlen > NFS_MAXPATHLEN) { @@ -494,7 +501,7 @@ nfsd_proc_symlink(struct svc_rqst *rqstp) fh_init(&newfh, NFS_FHSIZE); resp->status = nfsd_symlink(rqstp, &argp->ffh, argp->fname, argp->flen, - argp->tname, &newfh); + argp->tname, &attrs, &newfh); kfree(argp->tname); fh_put(&argp->ffh); @@ -512,6 +519,9 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp) { struct nfsd_createargs *argp = rqstp->rq_argp; struct nfsd_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; dprintk("nfsd: MKDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name); @@ -523,7 +533,7 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp) argp->attrs.ia_valid &= ~ATTR_SIZE; fh_init(&resp->fh, NFS_FHSIZE); resp->status = nfsd_create(rqstp, &argp->fh, argp->name, argp->len, - &argp->attrs, S_IFDIR, 0, &resp->fh); + &attrs, S_IFDIR, 0, &resp->fh); fh_put(&argp->fh); if (resp->status != nfs_ok) goto out; @@ -565,15 +575,7 @@ static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp, buf->pages = rqstp->rq_next_page; rqstp->rq_next_page++; - /* This is xdr_init_encode(), but it assumes that - * the head kvec has already been consumed. */ - xdr_set_scratch_buffer(xdr, NULL, 0); - xdr->buf = buf; - xdr->page_ptr = buf->pages; - xdr->iov = NULL; - xdr->p = page_address(*buf->pages); - xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE); - xdr->rqst = NULL; + xdr_init_encode_pages(xdr, buf, buf->pages, NULL); } /* @@ -635,6 +637,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 0, @@ -646,6 +649,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_attrstatres, .pc_release = nfssvc_release_attrstat, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, @@ -657,6 +661,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_attrstatres, .pc_release = nfssvc_release_attrstat, .pc_argsize = sizeof(struct nfsd_sattrargs), + .pc_argzero = sizeof(struct nfsd_sattrargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+AT, @@ -667,6 +672,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 0, @@ -678,6 +684,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_diropres, .pc_argsize = sizeof(struct nfsd_diropargs), + .pc_argzero = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+FH+AT, @@ -688,6 +695,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_fhandleargs, .pc_encode = nfssvc_encode_readlinkres, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_readlinkres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+1+NFS_MAXPATHLEN/4, @@ -699,6 +707,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_readres, .pc_release = nfssvc_release_readres, .pc_argsize = sizeof(struct nfsd_readargs), + .pc_argzero = sizeof(struct nfsd_readargs), .pc_ressize = sizeof(struct nfsd_readres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4, @@ -709,6 +718,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_voidarg, .pc_encode = nfssvc_encode_voidres, .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_argzero = sizeof(struct nfsd_voidargs), .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 0, @@ -720,6 +730,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_attrstatres, .pc_release = nfssvc_release_attrstat, .pc_argsize = sizeof(struct nfsd_writeargs), + .pc_argzero = sizeof(struct nfsd_writeargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+AT, @@ -731,6 +742,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_diropres, .pc_argsize = sizeof(struct nfsd_createargs), + .pc_argzero = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+FH+AT, @@ -741,6 +753,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_diropargs, .pc_encode = nfssvc_encode_statres, .pc_argsize = sizeof(struct nfsd_diropargs), + .pc_argzero = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, @@ -751,6 +764,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_renameargs, .pc_encode = nfssvc_encode_statres, .pc_argsize = sizeof(struct nfsd_renameargs), + .pc_argzero = sizeof(struct nfsd_renameargs), .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, @@ -761,6 +775,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_linkargs, .pc_encode = nfssvc_encode_statres, .pc_argsize = sizeof(struct nfsd_linkargs), + .pc_argzero = sizeof(struct nfsd_linkargs), .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, @@ -771,6 +786,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_symlinkargs, .pc_encode = nfssvc_encode_statres, .pc_argsize = sizeof(struct nfsd_symlinkargs), + .pc_argzero = sizeof(struct nfsd_symlinkargs), .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, @@ -782,6 +798,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_diropres, .pc_argsize = sizeof(struct nfsd_createargs), + .pc_argzero = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+FH+AT, @@ -792,6 +809,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_diropargs, .pc_encode = nfssvc_encode_statres, .pc_argsize = sizeof(struct nfsd_diropargs), + .pc_argzero = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, @@ -802,6 +820,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_readdirargs, .pc_encode = nfssvc_encode_readdirres, .pc_argsize = sizeof(struct nfsd_readdirargs), + .pc_argzero = sizeof(struct nfsd_readdirargs), .pc_ressize = sizeof(struct nfsd_readdirres), .pc_cachetype = RC_NOCACHE, .pc_name = "READDIR", @@ -811,6 +830,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_decode = nfssvc_decode_fhandleargs, .pc_encode = nfssvc_encode_statfsres, .pc_argsize = sizeof(struct nfsd_fhandle), + .pc_argzero = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_statfsres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+5, @@ -828,62 +848,3 @@ const struct svc_version nfsd_version2 = { .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS2_SVC_XDRSIZE, }; - -/* - * Map errnos to NFS errnos. - */ -__be32 -nfserrno (int errno) -{ - static struct { - __be32 nfserr; - int syserr; - } nfs_errtbl[] = { - { nfs_ok, 0 }, - { nfserr_perm, -EPERM }, - { nfserr_noent, -ENOENT }, - { nfserr_io, -EIO }, - { nfserr_nxio, -ENXIO }, - { nfserr_fbig, -E2BIG }, - { nfserr_acces, -EACCES }, - { nfserr_exist, -EEXIST }, - { nfserr_xdev, -EXDEV }, - { nfserr_mlink, -EMLINK }, - { nfserr_nodev, -ENODEV }, - { nfserr_notdir, -ENOTDIR }, - { nfserr_isdir, -EISDIR }, - { nfserr_inval, -EINVAL }, - { nfserr_fbig, -EFBIG }, - { nfserr_nospc, -ENOSPC }, - { nfserr_rofs, -EROFS }, - { nfserr_mlink, -EMLINK }, - { nfserr_nametoolong, -ENAMETOOLONG }, - { nfserr_notempty, -ENOTEMPTY }, -#ifdef EDQUOT - { nfserr_dquot, -EDQUOT }, -#endif - { nfserr_stale, -ESTALE }, - { nfserr_jukebox, -ETIMEDOUT }, - { nfserr_jukebox, -ERESTARTSYS }, - { nfserr_jukebox, -EAGAIN }, - { nfserr_jukebox, -EWOULDBLOCK }, - { nfserr_jukebox, -ENOMEM }, - { nfserr_io, -ETXTBSY }, - { nfserr_notsupp, -EOPNOTSUPP }, - { nfserr_toosmall, -ETOOSMALL }, - { nfserr_serverfault, -ESERVERFAULT }, - { nfserr_serverfault, -ENFILE }, - { nfserr_io, -EUCLEAN }, - { nfserr_perm, -ENOKEY }, - { nfserr_no_grace, -ENOGRACE}, - }; - int i; - - for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) { - if (nfs_errtbl[i].syserr == errno) - return nfs_errtbl[i].nfserr; - } - WARN_ONCE(1, "nfsd: non-standard errno: %d\n", errno); - return nfserr_io; -} - diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 373695cc62a7..4c1a0a1623e5 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/fs_struct.h> #include <linux/swap.h> +#include <linux/siphash.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svcsock.h> @@ -55,18 +56,17 @@ static __be32 nfsd_init_request(struct svc_rqst *, struct svc_process_info *); /* - * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and the members - * of the svc_serv struct. In particular, ->sv_nrthreads but also to some - * extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt + * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and some members + * of the svc_serv struct such as ->sv_temp_socks and ->sv_permsocks. * * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a - * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0. That number - * of nfsd threads must exist and each must listed in ->sp_all_threads in each - * entry of ->sv_pools[]. + * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0 (unless + * nn->keep_active is set). That number of nfsd threads must + * exist and each must be listed in ->sp_all_threads in some entry of + * ->sv_pools[]. * - * Transitions of the thread count between zero and non-zero are of particular - * interest since the svc_serv needs to be created and initialized at that - * point, or freed. + * Each active thread holds a counted reference on nn->nfsd_serv, as does + * the nn->keep_active flag and various transient calls to svc_get(). * * Finally, the nfsd_mutex also protects some of the global variables that are * accessed when nfsd starts and that are settable via the write_* routines in @@ -91,8 +91,12 @@ unsigned long nfsd_drc_mem_used; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; static const struct svc_version *nfsd_acl_version[] = { +# if defined(CONFIG_NFSD_V2_ACL) [2] = &nfsd_acl_version2, +# endif +# if defined(CONFIG_NFSD_V3_ACL) [3] = &nfsd_acl_version3, +# endif }; #define NFSD_ACL_MINVERS 2 @@ -116,10 +120,10 @@ static struct svc_stat nfsd_acl_svcstats = { #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ static const struct svc_version *nfsd_version[] = { +#if defined(CONFIG_NFSD_V2) [2] = &nfsd_version2, -#if defined(CONFIG_NFSD_V3) - [3] = &nfsd_version3, #endif + [3] = &nfsd_version3, #if defined(CONFIG_NFSD_V4) [4] = &nfsd_version4, #endif @@ -293,13 +297,13 @@ static int nfsd_init_socks(struct net *net, const struct cred *cred) if (!list_empty(&nn->nfsd_serv->sv_permsocks)) return 0; - error = svc_create_xprt(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT, - SVC_SOCK_DEFAULTS, cred); + error = svc_xprt_create(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT, + SVC_SOCK_DEFAULTS, cred); if (error < 0) return error; - error = svc_create_xprt(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT, - SVC_SOCK_DEFAULTS, cred); + error = svc_xprt_create(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT, + SVC_SOCK_DEFAULTS, cred); if (error < 0) return error; @@ -345,33 +349,57 @@ static bool nfsd_needs_lockd(struct nfsd_net *nn) return nfsd_vers(nn, 2, NFSD_TEST) || nfsd_vers(nn, 3, NFSD_TEST); } -void nfsd_copy_boot_verifier(__be32 verf[2], struct nfsd_net *nn) +/** + * nfsd_copy_write_verifier - Atomically copy a write verifier + * @verf: buffer in which to receive the verifier cookie + * @nn: NFS net namespace + * + * This function provides a wait-free mechanism for copying the + * namespace's write verifier without tearing it. + */ +void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn) { int seq = 0; do { - read_seqbegin_or_lock(&nn->boot_lock, &seq); - /* - * This is opaque to client, so no need to byte-swap. Use - * __force to keep sparse happy. y2038 time_t overflow is - * irrelevant in this usage - */ - verf[0] = (__force __be32)nn->nfssvc_boot.tv_sec; - verf[1] = (__force __be32)nn->nfssvc_boot.tv_nsec; - } while (need_seqretry(&nn->boot_lock, seq)); - done_seqretry(&nn->boot_lock, seq); + read_seqbegin_or_lock(&nn->writeverf_lock, &seq); + memcpy(verf, nn->writeverf, sizeof(nn->writeverf)); + } while (need_seqretry(&nn->writeverf_lock, seq)); + done_seqretry(&nn->writeverf_lock, seq); } -static void nfsd_reset_boot_verifier_locked(struct nfsd_net *nn) +static void nfsd_reset_write_verifier_locked(struct nfsd_net *nn) { - ktime_get_real_ts64(&nn->nfssvc_boot); + struct timespec64 now; + u64 verf; + + /* + * Because the time value is hashed, y2038 time_t overflow + * is irrelevant in this usage. + */ + ktime_get_raw_ts64(&now); + verf = siphash_2u64(now.tv_sec, now.tv_nsec, &nn->siphash_key); + memcpy(nn->writeverf, &verf, sizeof(nn->writeverf)); } -void nfsd_reset_boot_verifier(struct nfsd_net *nn) +/** + * nfsd_reset_write_verifier - Generate a new write verifier + * @nn: NFS net namespace + * + * This function updates the ->writeverf field of @nn. This field + * contains an opaque cookie that, according to Section 18.32.3 of + * RFC 8881, "the client can use to determine whether a server has + * changed instance state (e.g., server restart) between a call to + * WRITE and a subsequent call to either WRITE or COMMIT. This + * cookie MUST be unchanged during a single instance of the NFSv4.1 + * server and MUST be unique between instances of the NFSv4.1 + * server." + */ +void nfsd_reset_write_verifier(struct nfsd_net *nn) { - write_seqlock(&nn->boot_lock); - nfsd_reset_boot_verifier_locked(nn); - write_sequnlock(&nn->boot_lock); + write_seqlock(&nn->writeverf_lock); + nfsd_reset_write_verifier_locked(nn); + write_sequnlock(&nn->writeverf_lock); } static int nfsd_startup_net(struct net *net, const struct cred *cred) @@ -435,6 +463,7 @@ static void nfsd_shutdown_net(struct net *net) nfsd_shutdown_generic(); } +static DEFINE_SPINLOCK(nfsd_notifier_lock); static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -444,18 +473,17 @@ static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event, struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct sockaddr_in sin; - if ((event != NETDEV_DOWN) || - !atomic_inc_not_zero(&nn->ntf_refcnt)) + if (event != NETDEV_DOWN || !nn->nfsd_serv) goto out; + spin_lock(&nfsd_notifier_lock); if (nn->nfsd_serv) { dprintk("nfsd_inetaddr_event: removed %pI4\n", &ifa->ifa_local); sin.sin_family = AF_INET; sin.sin_addr.s_addr = ifa->ifa_local; svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin); } - atomic_dec(&nn->ntf_refcnt); - wake_up(&nn->ntf_wq); + spin_unlock(&nfsd_notifier_lock); out: return NOTIFY_DONE; @@ -475,10 +503,10 @@ static int nfsd_inet6addr_event(struct notifier_block *this, struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct sockaddr_in6 sin6; - if ((event != NETDEV_DOWN) || - !atomic_inc_not_zero(&nn->ntf_refcnt)) + if (event != NETDEV_DOWN || !nn->nfsd_serv) goto out; + spin_lock(&nfsd_notifier_lock); if (nn->nfsd_serv) { dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr); sin6.sin6_family = AF_INET6; @@ -487,8 +515,8 @@ static int nfsd_inet6addr_event(struct notifier_block *this, sin6.sin6_scope_id = ifa->idev->dev->ifindex; svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6); } - atomic_dec(&nn->ntf_refcnt); - wake_up(&nn->ntf_wq); + spin_unlock(&nfsd_notifier_lock); + out: return NOTIFY_DONE; } @@ -501,11 +529,15 @@ static struct notifier_block nfsd_inet6addr_notifier = { /* Only used under nfsd_mutex, so this atomic may be overkill: */ static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0); -static void nfsd_last_thread(struct svc_serv *serv, struct net *net) +void nfsd_last_thread(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv = nn->nfsd_serv; + + spin_lock(&nfsd_notifier_lock); + nn->nfsd_serv = NULL; + spin_unlock(&nfsd_notifier_lock); - atomic_dec(&nn->ntf_refcnt); /* check if the notifier still has clients */ if (atomic_dec_return(&nfsd_notifier_refcount) == 0) { unregister_inetaddr_notifier(&nfsd_inetaddr_notifier); @@ -513,7 +545,8 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) unregister_inet6addr_notifier(&nfsd_inet6addr_notifier); #endif } - wait_event(nn->ntf_wq, atomic_read(&nn->ntf_refcnt) == 0); + + svc_xprt_destroy_all(serv, net); /* * write_ports can create the server without actually starting @@ -590,24 +623,6 @@ static int nfsd_get_default_max_blksize(void) return ret; } -static const struct svc_serv_ops nfsd_thread_sv_ops = { - .svo_shutdown = nfsd_last_thread, - .svo_function = nfsd, - .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads, - .svo_module = THIS_MODULE, -}; - -static void nfsd_complete_shutdown(struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - WARN_ON(!mutex_is_locked(&nfsd_mutex)); - - nn->nfsd_serv = NULL; - complete(&nn->nfsd_shutdown_complete); -} - void nfsd_shutdown_threads(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -622,11 +637,10 @@ void nfsd_shutdown_threads(struct net *net) svc_get(serv); /* Kill outstanding nfsd threads */ - serv->sv_ops->svo_setup(serv, NULL, 0); - nfsd_destroy(net); + svc_set_num_threads(serv, NULL, 0); + nfsd_last_thread(net); + svc_put(serv); mutex_unlock(&nfsd_mutex); - /* Wait for shutdown of nfsd_serv to complete */ - wait_for_completion(&nn->nfsd_shutdown_complete); } bool i_am_nfsd(void) @@ -638,6 +652,7 @@ int nfsd_create_serv(struct net *net) { int error; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; WARN_ON(!mutex_is_locked(&nfsd_mutex)); if (nn->nfsd_serv) { @@ -647,19 +662,19 @@ int nfsd_create_serv(struct net *net) if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); nfsd_reset_versions(nn); - nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, - &nfsd_thread_sv_ops); - if (nn->nfsd_serv == NULL) + serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, nfsd); + if (serv == NULL) return -ENOMEM; - init_completion(&nn->nfsd_shutdown_complete); - nn->nfsd_serv->sv_maxconn = nn->max_connections; - error = svc_bind(nn->nfsd_serv, net); + serv->sv_maxconn = nn->max_connections; + error = svc_bind(serv, net); if (error < 0) { - svc_destroy(nn->nfsd_serv); - nfsd_complete_shutdown(net); + svc_put(serv); return error; } + spin_lock(&nfsd_notifier_lock); + nn->nfsd_serv = serv; + spin_unlock(&nfsd_notifier_lock); set_max_drc(); /* check if the notifier is already set */ @@ -669,8 +684,7 @@ int nfsd_create_serv(struct net *net) register_inet6addr_notifier(&nfsd_inet6addr_notifier); #endif } - atomic_inc(&nn->ntf_refcnt); - nfsd_reset_boot_verifier(nn); + nfsd_reset_write_verifier(nn); return 0; } @@ -697,18 +711,6 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) return 0; } -void nfsd_destroy(struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - int destroy = (nn->nfsd_serv->sv_nrthreads == 1); - - if (destroy) - svc_shutdown_net(nn->nfsd_serv, net); - svc_destroy(nn->nfsd_serv); - if (destroy) - nfsd_complete_shutdown(net); -} - int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) { int i = 0; @@ -733,7 +735,7 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) if (tot > NFSD_MAXSERVS) { /* total too large: scale down requested numbers */ for (i = 0; i < n && tot > 0; i++) { - int new = nthreads[i] * NFSD_MAXSERVS / tot; + int new = nthreads[i] * NFSD_MAXSERVS / tot; tot -= (nthreads[i] - new); nthreads[i] = new; } @@ -753,12 +755,13 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) /* apply the new numbers */ svc_get(nn->nfsd_serv); for (i = 0; i < n; i++) { - err = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv, - &nn->nfsd_serv->sv_pools[i], nthreads[i]); + err = svc_set_num_threads(nn->nfsd_serv, + &nn->nfsd_serv->sv_pools[i], + nthreads[i]); if (err) break; } - nfsd_destroy(net); + svc_put(nn->nfsd_serv); return err; } @@ -773,6 +776,7 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) int error; bool nfsd_up_before; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; mutex_lock(&nfsd_mutex); dprintk("nfsd: creating service\n"); @@ -784,7 +788,7 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) if (nrservs == 0 && nn->nfsd_serv == NULL) goto out; - strlcpy(nn->nfsd_name, utsname()->nodename, + strscpy(nn->nfsd_name, utsname()->nodename, sizeof(nn->nfsd_name)); error = nfsd_create_serv(net); @@ -792,24 +796,25 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) goto out; nfsd_up_before = nn->nfsd_net_up; + serv = nn->nfsd_serv; error = nfsd_startup_net(net, cred); if (error) - goto out_destroy; - error = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv, - NULL, nrservs); + goto out_put; + error = svc_set_num_threads(serv, NULL, nrservs); if (error) goto out_shutdown; - /* We are holding a reference to nn->nfsd_serv which - * we don't want to count in the return value, - * so subtract 1 - */ - error = nn->nfsd_serv->sv_nrthreads - 1; + error = serv->sv_nrthreads; + if (error == 0) + nfsd_last_thread(net); out_shutdown: if (error < 0 && !nfsd_up_before) nfsd_shutdown_net(net); -out_destroy: - nfsd_destroy(net); /* Release server */ +out_put: + /* Threads now hold service active */ + if (xchg(&nn->keep_active, 0)) + svc_put(serv); + svc_put(serv); out: mutex_unlock(&nfsd_mutex); return error; @@ -923,9 +928,6 @@ nfsd(void *vrqstp) struct nfsd_net *nn = net_generic(net, nfsd_net_id); int err; - /* Lock module and set up kernel thread */ - mutex_lock(&nfsd_mutex); - /* At this point, the thread shares current->fs * with the init process. We need to create files with the * umask as defined by the client instead of init's umask. */ @@ -945,8 +947,7 @@ nfsd(void *vrqstp) allow_signal(SIGINT); allow_signal(SIGQUIT); - nfsdstats.th_cnt++; - mutex_unlock(&nfsd_mutex); + atomic_inc(&nfsdstats.th_cnt); set_freezable(); @@ -973,20 +974,11 @@ nfsd(void *vrqstp) /* Clear signals before calling svc_exit_thread() */ flush_signals(current); - mutex_lock(&nfsd_mutex); - nfsdstats.th_cnt --; + atomic_dec(&nfsdstats.th_cnt); out: - rqstp->rq_server = NULL; - /* Release the thread */ svc_exit_thread(rqstp); - - nfsd_destroy(net); - - /* Release module */ - mutex_unlock(&nfsd_mutex); - module_put_and_exit(0); return 0; } @@ -1004,9 +996,6 @@ out: int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { const struct svc_procedure *proc = rqstp->rq_procinfo; - struct kvec *argv = &rqstp->rq_arg.head[0]; - struct kvec *resv = &rqstp->rq_res.head[0]; - __be32 *p; /* * Give the xdr decoder a chance to change this if it wants @@ -1015,7 +1004,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) rqstp->rq_cachetype = proc->pc_cachetype; svcxdr_init_decode(rqstp); - if (!proc->pc_decode(rqstp, argv->iov_base)) + if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; switch (nfsd_cache_lookup(rqstp)) { @@ -1031,14 +1020,13 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) * Need to grab the location to store the status, as * NFSv4 does some encoding while processing */ - p = resv->iov_base + resv->iov_len; svcxdr_init_encode(rqstp); *statp = proc->pc_func(rqstp); - if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags)) + if (test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; - if (!proc->pc_encode(rqstp, p)) + if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1); @@ -1065,29 +1053,29 @@ out_encode_err: /** * nfssvc_decode_voidarg - Decode void arguments * @rqstp: Server RPC transaction context - * @p: buffer containing arguments to decode + * @xdr: XDR stream positioned at arguments to decode * * Return values: - * %0: Arguments were not valid - * %1: Decoding was successful + * %false: Arguments were not valid + * %true: Decoding was successful */ -int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p) +bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } /** * nfssvc_encode_voidres - Encode void results * @rqstp: Server RPC transaction context - * @p: buffer in which to encode results + * @xdr: XDR stream into which to encode results * * Return values: - * %0: Local error while encoding - * %1: Encoding was successful + * %false: Local error while encoding + * %true: Encoding was successful */ -int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) +bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } int nfsd_pool_stats_open(struct inode *inode, struct file *file) @@ -1100,7 +1088,6 @@ int nfsd_pool_stats_open(struct inode *inode, struct file *file) mutex_unlock(&nfsd_mutex); return -ENODEV; } - /* bump up the psudo refcount while traversing */ svc_get(nn->nfsd_serv); ret = svc_pool_stats_open(nn->nfsd_serv, file); mutex_unlock(&nfsd_mutex); @@ -1109,12 +1096,12 @@ int nfsd_pool_stats_open(struct inode *inode, struct file *file) int nfsd_pool_stats_release(struct inode *inode, struct file *file) { + struct seq_file *seq = file->private_data; + struct svc_serv *serv = seq->private; int ret = seq_release(inode, file); - struct net *net = inode->i_sb->s_fs_info; mutex_lock(&nfsd_mutex); - /* this function really, really should have been called svc_put() */ - nfsd_destroy(net); + svc_put(serv); mutex_unlock(&nfsd_mutex); return ret; } diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 26a42f87c240..caf6355b18fa 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -64,7 +64,7 @@ svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp) if (!p) return false; fh_init(fhp, NFS_FHSIZE); - memcpy(&fhp->fh_handle.fh_base, p, NFS_FHSIZE); + memcpy(&fhp->fh_handle.fh_raw, p, NFS_FHSIZE); fhp->fh_handle.fh_size = NFS_FHSIZE; return true; @@ -78,7 +78,7 @@ svcxdr_encode_fhandle(struct xdr_stream *xdr, const struct svc_fh *fhp) p = xdr_reserve_space(xdr, NFS_FHSIZE); if (!p) return false; - memcpy(p, &fhp->fh_handle.fh_base, NFS_FHSIZE); + memcpy(p, &fhp->fh_handle.fh_raw, NFS_FHSIZE); return true; } @@ -272,87 +272,79 @@ svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr, * XDR decode functions */ -int -nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_fhandle *args = rqstp->rq_argp; return svcxdr_decode_fhandle(xdr, &args->fh); } -int -nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_sattrargs *args = rqstp->rq_argp; return svcxdr_decode_fhandle(xdr, &args->fh) && svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } -int -nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_diropargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs(xdr, &args->fh, &args->name, &args->len); } -int -nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_readargs *args = rqstp->rq_argp; u32 totalcount; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; /* totalcount is ignored */ if (xdr_stream_decode_u32(xdr, &totalcount) < 0) - return 0; + return false; - return 1; + return true; } -int -nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_writeargs *args = rqstp->rq_argp; u32 beginoffset, totalcount; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; /* beginoffset is ignored */ if (xdr_stream_decode_u32(xdr, &beginoffset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->offset) < 0) - return 0; + return false; /* totalcount is ignored */ if (xdr_stream_decode_u32(xdr, &totalcount) < 0) - return 0; + return false; /* opaque data */ if (xdr_stream_decode_u32(xdr, &args->len) < 0) - return 0; + return false; if (args->len > NFSSVC_MAXBLKSIZE_V2) - return 0; - if (!xdr_stream_subsegment(xdr, &args->payload, args->len)) - return 0; + return false; - return 1; + return xdr_stream_subsegment(xdr, &args->payload, args->len); } -int -nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_createargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs(xdr, &args->fh, @@ -360,10 +352,9 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } -int -nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_renameargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs(xdr, &args->ffh, @@ -372,10 +363,9 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) &args->tname, &args->tlen); } -int -nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_linkargs *args = rqstp->rq_argp; return svcxdr_decode_fhandle(xdr, &args->ffh) && @@ -383,178 +373,170 @@ nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) &args->tname, &args->tlen); } -int -nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_symlinkargs *args = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; if (!svcxdr_decode_diropargs(xdr, &args->ffh, &args->fname, &args->flen)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->tlen) < 0) - return 0; + return false; if (args->tlen == 0) - return 0; + return false; args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); args->first.iov_base = xdr_inline_decode(xdr, args->tlen); if (!args->first.iov_base) - return 0; + return false; return svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } -int -nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_readdirargs *args = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->cookie) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } /* * XDR encode functions */ -int -nfssvc_encode_statres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_stat *resp = rqstp->rq_resp; return svcxdr_encode_stat(xdr, resp->status); } -int -nfssvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_attrstat *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; break; } - return 1; + return true; } -int -nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fhandle(xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; break; } - return 1; + return true; } -int -nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_readlinkres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (xdr_stream_encode_u32(xdr, resp->len) < 0) - return 0; + return false; xdr_write_pages(xdr, &resp->page, 0, resp->len); if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0) - return 0; + return false; break; } - return 1; + return true; } -int -nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_readres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base, resp->count); if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0) - return 0; + return false; break; } - return 1; + return true; } -int -nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_readdirres *resp = rqstp->rq_resp; struct xdr_buf *dirlist = &resp->dirlist; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len); /* no more entries */ if (xdr_stream_encode_item_absent(xdr) < 0) - return 0; + return false; if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0) - return 0; + return false; break; } - return 1; + return true; } -int -nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p) +bool +nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_statfsres *resp = rqstp->rq_resp; struct kstatfs *stat = &resp->stats; + __be32 *p; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: p = xdr_reserve_space(xdr, XDR_UNIT * 5); if (!p) - return 0; + return false; *p++ = cpu_to_be32(NFSSVC_MAXBLKSIZE_V2); *p++ = cpu_to_be32(stat->f_bsize); *p++ = cpu_to_be32(stat->f_blocks); @@ -563,7 +545,7 @@ nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p) break; } - return 1; + return true; } /** diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index e73bdbb1634a..e94634d30591 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -57,11 +57,11 @@ typedef struct { } stateid_t; typedef struct { - stateid_t stid; + stateid_t cs_stid; #define NFS4_COPY_STID 1 #define NFS4_COPYNOTIFY_STID 2 - unsigned char sc_type; - refcount_t sc_count; + unsigned char cs_type; + refcount_t cs_count; } copy_stateid_t; struct nfsd4_callback { @@ -149,6 +149,7 @@ struct nfs4_delegation { /* For recall: */ int dl_retries; struct nfsd4_callback dl_recall; + bool dl_recalled; }; #define cb_to_delegation(cb) \ @@ -174,7 +175,7 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s) /* Maximum number of slots per session. 160 is useful for long haul TCP */ #define NFSD_MAX_SLOTS_PER_SESSION 160 /* Maximum number of operations per session compound */ -#define NFSD_MAX_OPS_PER_COMPOUND 16 +#define NFSD_MAX_OPS_PER_COMPOUND 50 /* Maximum session per slot cache size */ #define NFSD_SLOT_CACHE_SIZE 2048 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */ @@ -283,6 +284,28 @@ struct nfsd4_sessionid { #define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */ /* + * State Meaning Where set + * -------------------------------------------------------------------------- + * | NFSD4_ACTIVE | Confirmed, active | Default | + * |------------------- ----------------------------------------------------| + * | NFSD4_COURTESY | Courtesy state. | nfs4_get_client_reaplist | + * | | Lease/lock/share | | + * | | reservation conflict | | + * | | can cause Courtesy | | + * | | client to be expired | | + * |------------------------------------------------------------------------| + * | NFSD4_EXPIRABLE | Courtesy client to be| nfs4_laundromat | + * | | expired by Laundromat| try_to_expire_client | + * | | due to conflict | | + * |------------------------------------------------------------------------| + */ +enum { + NFSD4_ACTIVE = 0, + NFSD4_COURTESY, + NFSD4_EXPIRABLE, +}; + +/* * struct nfs4_client - one per client. Clientids live here. * * The initial object created by an NFS client using SETCLIENTID (for NFSv4.0) @@ -345,6 +368,7 @@ struct nfs4_client { #define NFSD4_CLIENT_UPCALL_LOCK (5) /* upcall serialization */ #define NFSD4_CLIENT_CB_FLAG_MASK (1 << NFSD4_CLIENT_CB_UPDATE | \ 1 << NFSD4_CLIENT_CB_KILL) +#define NFSD4_CLIENT_CB_RECALL_ANY (6) unsigned long cl_flags; const struct cred *cl_cb_cred; struct rpc_clnt *cl_cb_client; @@ -385,6 +409,13 @@ struct nfs4_client { struct list_head async_copies; /* list of async copies */ spinlock_t async_lock; /* lock for async copies */ atomic_t cl_cb_inflight; /* Outstanding callbacks */ + + unsigned int cl_state; + atomic_t cl_delegs_in_recall; + + struct nfsd4_cb_recall_any *cl_ra; + time64_t cl_ra_time; + struct list_head cl_ra_cblist; }; /* struct nfs4_client_reset @@ -510,16 +541,13 @@ struct nfs4_clnt_odstate { * inode can have multiple filehandles associated with it, so there is * (potentially) a many to one relationship between this struct and struct * inode. - * - * These are hashed by filehandle in the file_hashtbl, which is protected by - * the global state_lock spinlock. */ struct nfs4_file { refcount_t fi_ref; struct inode * fi_inode; bool fi_aliased; spinlock_t fi_lock; - struct hlist_node fi_hash; /* hash on fi_fhandle */ + struct rhlist_head fi_rlist; struct list_head fi_stateids; union { struct list_head fi_delegations; @@ -568,6 +596,10 @@ struct nfs4_ol_stateid { struct list_head st_locks; struct nfs4_stateowner *st_stateowner; struct nfs4_clnt_odstate *st_clnt_odstate; +/* + * These bitmasks use 3 separate bits for READ, ALLOW, and BOTH; see the + * comment above bmap_to_share_mode() for explanation: + */ unsigned char st_access_bmap; unsigned char st_deny_bmap; struct nfs4_ol_stateid *st_openstp; @@ -609,6 +641,7 @@ enum nfsd4_cb_op { NFSPROC4_CLNT_CB_OFFLOAD, NFSPROC4_CLNT_CB_SEQUENCE, NFSPROC4_CLNT_CB_NOTIFY_LOCK, + NFSPROC4_CLNT_CB_RECALL_ANY, }; /* Returns true iff a is later than b: */ @@ -629,6 +662,7 @@ struct nfsd4_blocked_lock { struct file_lock nbl_lock; struct knfsd_fh nbl_fh; struct nfsd4_callback nbl_cb; + struct kref nbl_kref; }; struct nfsd4_compound_state; @@ -661,18 +695,16 @@ extern void nfsd4_probe_callback_sync(struct nfs4_client *clp); extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *); extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op); -extern void nfsd4_run_cb(struct nfsd4_callback *cb); +extern bool nfsd4_run_cb(struct nfsd4_callback *cb); extern int nfsd4_create_callback_queue(void); extern void nfsd4_destroy_callback_queue(void); extern void nfsd4_shutdown_callback(struct nfs4_client *); extern void nfsd4_shutdown_copy(struct nfs4_client *clp); -extern void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp); extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, struct nfsd_net *nn); extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn); void put_nfs4_file(struct nfs4_file *fi); -extern void nfs4_put_copy(struct nfsd4_copy *copy); extern struct nfsd4_copy * find_async_copy(struct nfs4_client *clp, stateid_t *staetid); extern void nfs4_put_cpntf_state(struct nfsd_net *nn, @@ -697,4 +729,9 @@ extern void nfsd4_client_record_remove(struct nfs4_client *clp); extern int nfsd4_client_record_check(struct nfs4_client *clp); extern void nfsd4_record_grace_done(struct nfsd_net *nn); +static inline bool try_to_expire_client(struct nfs4_client *clp) +{ + cmpxchg(&clp->cl_state, NFSD4_COURTESY, NFSD4_EXPIRABLE); + return clp->cl_state == NFSD4_EXPIRABLE; +} #endif /* NFSD4_STATE_H */ diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 1d3b881e7382..777e24e5da33 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -32,7 +32,7 @@ struct svc_stat nfsd_svcstats = { .program = &nfsd_program, }; -static int nfsd_proc_show(struct seq_file *seq, void *v) +static int nfsd_show(struct seq_file *seq, void *v) { int i; @@ -45,7 +45,7 @@ static int nfsd_proc_show(struct seq_file *seq, void *v) percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_IO_WRITE])); /* thread usage: */ - seq_printf(seq, "th %u 0", nfsdstats.th_cnt); + seq_printf(seq, "th %u 0", atomic_read(&nfsdstats.th_cnt)); /* deprecated thread usage histogram stats */ for (i = 0; i < 10; i++) @@ -72,17 +72,7 @@ static int nfsd_proc_show(struct seq_file *seq, void *v) return 0; } -static int nfsd_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, nfsd_proc_show, NULL); -} - -static const struct proc_ops nfsd_proc_ops = { - .proc_open = nfsd_proc_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = single_release, -}; +DEFINE_PROC_SHOW_ATTRIBUTE(nfsd); int nfsd_percpu_counters_init(struct percpu_counter counters[], int num) { diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h index 51ecda852e23..9b43dc3d9991 100644 --- a/fs/nfsd/stats.h +++ b/fs/nfsd/stats.h @@ -29,11 +29,9 @@ enum { struct nfsd_stats { struct percpu_counter counter[NFSD_STATS_COUNTERS_NUM]; - /* Protected by nfsd_mutex */ - unsigned int th_cnt; /* number of available threads */ + atomic_t th_cnt; /* number of available threads */ }; - extern struct nfsd_stats nfsdstats; extern struct svc_stat nfsd_svcstats; diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 0fc1fa6f28e0..276420ea3b8d 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -9,24 +9,12 @@ #define _NFSD_TRACE_H #include <linux/tracepoint.h> +#include <linux/sunrpc/xprt.h> +#include <trace/misc/nfs.h> + #include "export.h" #include "nfsfh.h" - -#define NFSD_TRACE_PROC_ARG_FIELDS \ - __field(unsigned int, netns_ino) \ - __field(u32, xid) \ - __array(unsigned char, server, sizeof(struct sockaddr_in6)) \ - __array(unsigned char, client, sizeof(struct sockaddr_in6)) - -#define NFSD_TRACE_PROC_ARG_ASSIGNMENTS \ - do { \ - __entry->netns_ino = SVC_NET(rqstp)->ns.inum; \ - __entry->xid = be32_to_cpu(rqstp->rq_xid); \ - memcpy(__entry->server, &rqstp->rq_xprt->xpt_local, \ - rqstp->rq_xprt->xpt_locallen); \ - memcpy(__entry->client, &rqstp->rq_xprt->xpt_remote, \ - rqstp->rq_xprt->xpt_remotelen); \ - } while (0); +#include "xdr4.h" #define NFSD_TRACE_PROC_RES_FIELDS \ __field(unsigned int, netns_ino) \ @@ -46,49 +34,41 @@ rqstp->rq_xprt->xpt_remotelen); \ } while (0); -TRACE_EVENT(nfsd_garbage_args_err, +DECLARE_EVENT_CLASS(nfsd_xdr_err_class, TP_PROTO( const struct svc_rqst *rqstp ), TP_ARGS(rqstp), TP_STRUCT__entry( - NFSD_TRACE_PROC_ARG_FIELDS - + __field(unsigned int, netns_ino) + __field(u32, xid) __field(u32, vers) __field(u32, proc) + __sockaddr(server, rqstp->rq_xprt->xpt_locallen) + __sockaddr(client, rqstp->rq_xprt->xpt_remotelen) ), TP_fast_assign( - NFSD_TRACE_PROC_ARG_ASSIGNMENTS + const struct svc_xprt *xprt = rqstp->rq_xprt; + __entry->netns_ino = xprt->xpt_net->ns.inum; + __entry->xid = be32_to_cpu(rqstp->rq_xid); __entry->vers = rqstp->rq_vers; __entry->proc = rqstp->rq_proc; + __assign_sockaddr(server, &xprt->xpt_local, xprt->xpt_locallen); + __assign_sockaddr(client, &xprt->xpt_remote, xprt->xpt_remotelen); ), TP_printk("xid=0x%08x vers=%u proc=%u", __entry->xid, __entry->vers, __entry->proc ) ); -TRACE_EVENT(nfsd_cant_encode_err, - TP_PROTO( - const struct svc_rqst *rqstp - ), - TP_ARGS(rqstp), - TP_STRUCT__entry( - NFSD_TRACE_PROC_ARG_FIELDS - - __field(u32, vers) - __field(u32, proc) - ), - TP_fast_assign( - NFSD_TRACE_PROC_ARG_ASSIGNMENTS +#define DEFINE_NFSD_XDR_ERR_EVENT(name) \ +DEFINE_EVENT(nfsd_xdr_err_class, nfsd_##name##_err, \ + TP_PROTO(const struct svc_rqst *rqstp), \ + TP_ARGS(rqstp)) - __entry->vers = rqstp->rq_vers; - __entry->proc = rqstp->rq_proc; - ), - TP_printk("xid=0x%08x vers=%u proc=%u", - __entry->xid, __entry->vers, __entry->proc - ) -); +DEFINE_NFSD_XDR_ERR_EVENT(garbage_args); +DEFINE_NFSD_XDR_ERR_EVENT(cant_encode); #define show_nfsd_may_flags(x) \ __print_flags(x, "|", \ @@ -107,19 +87,26 @@ TRACE_EVENT(nfsd_cant_encode_err, { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" }) TRACE_EVENT(nfsd_compound, - TP_PROTO(const struct svc_rqst *rqst, - u32 args_opcnt), - TP_ARGS(rqst, args_opcnt), + TP_PROTO( + const struct svc_rqst *rqst, + const char *tag, + u32 taglen, + u32 opcnt + ), + TP_ARGS(rqst, tag, taglen, opcnt), TP_STRUCT__entry( __field(u32, xid) - __field(u32, args_opcnt) + __field(u32, opcnt) + __string_len(tag, tag, taglen) ), TP_fast_assign( __entry->xid = be32_to_cpu(rqst->rq_xid); - __entry->args_opcnt = args_opcnt; + __entry->opcnt = opcnt; + __assign_str_len(tag, tag, taglen); ), - TP_printk("xid=0x%08x opcnt=%u", - __entry->xid, __entry->args_opcnt) + TP_printk("xid=0x%08x opcnt=%u tag=%s", + __entry->xid, __entry->opcnt, __get_str(tag) + ) ) TRACE_EVENT(nfsd_compound_status, @@ -194,6 +181,97 @@ TRACE_EVENT(nfsd_compound_encode_err, __entry->opnum, __entry->status) ); +#define show_fs_file_type(x) \ + __print_symbolic(x, \ + { S_IFLNK, "LNK" }, \ + { S_IFREG, "REG" }, \ + { S_IFDIR, "DIR" }, \ + { S_IFCHR, "CHR" }, \ + { S_IFBLK, "BLK" }, \ + { S_IFIFO, "FIFO" }, \ + { S_IFSOCK, "SOCK" }) + +TRACE_EVENT(nfsd_fh_verify, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp, + umode_t type, + int access + ), + TP_ARGS(rqstp, fhp, type, access), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) + __sockaddr(client, rqstp->rq_xprt->xpt_remotelen) + __field(u32, xid) + __field(u32, fh_hash) + __field(const void *, inode) + __field(unsigned long, type) + __field(unsigned long, access) + ), + TP_fast_assign( + __entry->netns_ino = SVC_NET(rqstp)->ns.inum; + __assign_sockaddr(server, &rqstp->rq_xprt->xpt_local, + rqstp->rq_xprt->xpt_locallen); + __assign_sockaddr(client, &rqstp->rq_xprt->xpt_remote, + rqstp->rq_xprt->xpt_remotelen); + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + __entry->inode = d_inode(fhp->fh_dentry); + __entry->type = type; + __entry->access = access; + ), + TP_printk("xid=0x%08x fh_hash=0x%08x type=%s access=%s", + __entry->xid, __entry->fh_hash, + show_fs_file_type(__entry->type), + show_nfsd_may_flags(__entry->access) + ) +); + +TRACE_EVENT_CONDITION(nfsd_fh_verify_err, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp, + umode_t type, + int access, + __be32 error + ), + TP_ARGS(rqstp, fhp, type, access, error), + TP_CONDITION(error), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) + __sockaddr(client, rqstp->rq_xprt->xpt_remotelen) + __field(u32, xid) + __field(u32, fh_hash) + __field(const void *, inode) + __field(unsigned long, type) + __field(unsigned long, access) + __field(int, error) + ), + TP_fast_assign( + __entry->netns_ino = SVC_NET(rqstp)->ns.inum; + __assign_sockaddr(server, &rqstp->rq_xprt->xpt_local, + rqstp->rq_xprt->xpt_locallen); + __assign_sockaddr(client, &rqstp->rq_xprt->xpt_remote, + rqstp->rq_xprt->xpt_remotelen); + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + if (fhp->fh_dentry) + __entry->inode = d_inode(fhp->fh_dentry); + else + __entry->inode = NULL; + __entry->type = type; + __entry->access = access; + __entry->error = be32_to_cpu(error); + ), + TP_printk("xid=0x%08x fh_hash=0x%08x type=%s access=%s error=%d", + __entry->xid, __entry->fh_hash, + show_fs_file_type(__entry->type), + show_nfsd_may_flags(__entry->access), + __entry->error + ) +); DECLARE_EVENT_CLASS(nfsd_fh_err_class, TP_PROTO(struct svc_rqst *rqstp, @@ -412,10 +490,83 @@ TRACE_EVENT(nfsd_dirent, ) ) +DECLARE_EVENT_CLASS(nfsd_copy_err_class, + TP_PROTO(struct svc_rqst *rqstp, + struct svc_fh *src_fhp, + loff_t src_offset, + struct svc_fh *dst_fhp, + loff_t dst_offset, + u64 count, + int status), + TP_ARGS(rqstp, src_fhp, src_offset, dst_fhp, dst_offset, count, status), + TP_STRUCT__entry( + __field(u32, xid) + __field(u32, src_fh_hash) + __field(loff_t, src_offset) + __field(u32, dst_fh_hash) + __field(loff_t, dst_offset) + __field(u64, count) + __field(int, status) + ), + TP_fast_assign( + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->src_fh_hash = knfsd_fh_hash(&src_fhp->fh_handle); + __entry->src_offset = src_offset; + __entry->dst_fh_hash = knfsd_fh_hash(&dst_fhp->fh_handle); + __entry->dst_offset = dst_offset; + __entry->count = count; + __entry->status = status; + ), + TP_printk("xid=0x%08x src_fh_hash=0x%08x src_offset=%lld " + "dst_fh_hash=0x%08x dst_offset=%lld " + "count=%llu status=%d", + __entry->xid, __entry->src_fh_hash, __entry->src_offset, + __entry->dst_fh_hash, __entry->dst_offset, + (unsigned long long)__entry->count, + __entry->status) +) + +#define DEFINE_NFSD_COPY_ERR_EVENT(name) \ +DEFINE_EVENT(nfsd_copy_err_class, nfsd_##name, \ + TP_PROTO(struct svc_rqst *rqstp, \ + struct svc_fh *src_fhp, \ + loff_t src_offset, \ + struct svc_fh *dst_fhp, \ + loff_t dst_offset, \ + u64 count, \ + int status), \ + TP_ARGS(rqstp, src_fhp, src_offset, dst_fhp, dst_offset, \ + count, status)) + +DEFINE_NFSD_COPY_ERR_EVENT(clone_file_range_err); + #include "state.h" #include "filecache.h" #include "vfs.h" +TRACE_EVENT(nfsd_delegret_wakeup, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct inode *inode, + long timeo + ), + TP_ARGS(rqstp, inode, timeo), + TP_STRUCT__entry( + __field(u32, xid) + __field(const void *, inode) + __field(long, timeo) + ), + TP_fast_assign( + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->inode = inode; + __entry->timeo = timeo; + ), + TP_printk("xid=0x%08x inode=%p%s", + __entry->xid, __entry->inode, + __entry->timeo == 0 ? " (timed out)" : "" + ) +); + DECLARE_EVENT_CLASS(nfsd_stateid_class, TP_PROTO(stateid_t *stp), TP_ARGS(stp), @@ -456,6 +607,7 @@ DEFINE_STATEID_EVENT(layout_recall_release); DEFINE_STATEID_EVENT(open); DEFINE_STATEID_EVENT(deleg_read); +DEFINE_STATEID_EVENT(deleg_return); DEFINE_STATEID_EVENT(deleg_recall); DECLARE_EVENT_CLASS(nfsd_stateseqid_class, @@ -488,6 +640,61 @@ DEFINE_EVENT(nfsd_stateseqid_class, nfsd_##name, \ DEFINE_STATESEQID_EVENT(preprocess); DEFINE_STATESEQID_EVENT(open_confirm); +TRACE_DEFINE_ENUM(NFS4_OPEN_STID); +TRACE_DEFINE_ENUM(NFS4_LOCK_STID); +TRACE_DEFINE_ENUM(NFS4_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_CLOSED_STID); +TRACE_DEFINE_ENUM(NFS4_REVOKED_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_CLOSED_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_LAYOUT_STID); + +#define show_stid_type(x) \ + __print_flags(x, "|", \ + { NFS4_OPEN_STID, "OPEN" }, \ + { NFS4_LOCK_STID, "LOCK" }, \ + { NFS4_DELEG_STID, "DELEG" }, \ + { NFS4_CLOSED_STID, "CLOSED" }, \ + { NFS4_REVOKED_DELEG_STID, "REVOKED" }, \ + { NFS4_CLOSED_DELEG_STID, "CLOSED_DELEG" }, \ + { NFS4_LAYOUT_STID, "LAYOUT" }) + +DECLARE_EVENT_CLASS(nfsd_stid_class, + TP_PROTO( + const struct nfs4_stid *stid + ), + TP_ARGS(stid), + TP_STRUCT__entry( + __field(unsigned long, sc_type) + __field(int, sc_count) + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, si_id) + __field(u32, si_generation) + ), + TP_fast_assign( + const stateid_t *stp = &stid->sc_stateid; + + __entry->sc_type = stid->sc_type; + __entry->sc_count = refcount_read(&stid->sc_count); + __entry->cl_boot = stp->si_opaque.so_clid.cl_boot; + __entry->cl_id = stp->si_opaque.so_clid.cl_id; + __entry->si_id = stp->si_opaque.so_id; + __entry->si_generation = stp->si_generation; + ), + TP_printk("client %08x:%08x stateid %08x:%08x ref=%d type=%s", + __entry->cl_boot, __entry->cl_id, + __entry->si_id, __entry->si_generation, + __entry->sc_count, show_stid_type(__entry->sc_type) + ) +); + +#define DEFINE_STID_EVENT(name) \ +DEFINE_EVENT(nfsd_stid_class, nfsd_stid_##name, \ + TP_PROTO(const struct nfs4_stid *stid), \ + TP_ARGS(stid)) + +DEFINE_STID_EVENT(revoke); + DECLARE_EVENT_CLASS(nfsd_clientid_class, TP_PROTO(const clientid_t *clid), TP_ARGS(clid), @@ -537,6 +744,34 @@ DEFINE_EVENT(nfsd_net_class, nfsd_##name, \ DEFINE_NET_EVENT(grace_start); DEFINE_NET_EVENT(grace_complete); +TRACE_EVENT(nfsd_writeverf_reset, + TP_PROTO( + const struct nfsd_net *nn, + const struct svc_rqst *rqstp, + int error + ), + TP_ARGS(nn, rqstp, error), + TP_STRUCT__entry( + __field(unsigned long long, boot_time) + __field(u32, xid) + __field(int, error) + __array(unsigned char, verifier, NFS4_VERIFIER_SIZE) + ), + TP_fast_assign( + __entry->boot_time = nn->boot_time; + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->error = error; + + /* avoid seqlock inside TP_fast_assign */ + memcpy(__entry->verifier, nn->writeverf, + NFS4_VERIFIER_SIZE); + ), + TP_printk("boot_time=%16llx xid=0x%08x error=%d new verifier=0x%s", + __entry->boot_time, __entry->xid, __entry->error, + __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE) + ) +); + TRACE_EVENT(nfsd_clid_cred_mismatch, TP_PROTO( const struct nfs4_client *clp, @@ -606,7 +841,7 @@ DECLARE_EVENT_CLASS(nfsd_clid_class, __array(unsigned char, addr, sizeof(struct sockaddr_in6)) __field(unsigned long, flavor) __array(unsigned char, verifier, NFS4_VERIFIER_SIZE) - __string_len(name, name, clp->cl_name.len) + __string_len(name, clp->cl_name.data, clp->cl_name.len) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; @@ -640,13 +875,13 @@ DEFINE_CLID_EVENT(confirmed_r); __print_flags(val, "|", \ { 1 << NFSD_FILE_HASHED, "HASHED" }, \ { 1 << NFSD_FILE_PENDING, "PENDING" }, \ - { 1 << NFSD_FILE_REFERENCED, "REFERENCED"}) + { 1 << NFSD_FILE_REFERENCED, "REFERENCED" }, \ + { 1 << NFSD_FILE_GC, "GC" }) DECLARE_EVENT_CLASS(nfsd_file_class, TP_PROTO(struct nfsd_file *nf), TP_ARGS(nf), TP_STRUCT__entry( - __field(unsigned int, nf_hashval) __field(void *, nf_inode) __field(int, nf_ref) __field(unsigned long, nf_flags) @@ -654,15 +889,13 @@ DECLARE_EVENT_CLASS(nfsd_file_class, __field(struct file *, nf_file) ), TP_fast_assign( - __entry->nf_hashval = nf->nf_hashval; __entry->nf_inode = nf->nf_inode; __entry->nf_ref = refcount_read(&nf->nf_ref); __entry->nf_flags = nf->nf_flags; __entry->nf_may = nf->nf_may; __entry->nf_file = nf->nf_file; ), - TP_printk("hash=0x%x inode=%p ref=%d flags=%s may=%s file=%p", - __entry->nf_hashval, + TP_printk("inode=%p ref=%d flags=%s may=%s nf_file=%p", __entry->nf_inode, __entry->nf_ref, show_nf_flags(__entry->nf_flags), @@ -675,34 +908,60 @@ DEFINE_EVENT(nfsd_file_class, name, \ TP_PROTO(struct nfsd_file *nf), \ TP_ARGS(nf)) -DEFINE_NFSD_FILE_EVENT(nfsd_file_alloc); -DEFINE_NFSD_FILE_EVENT(nfsd_file_put_final); +DEFINE_NFSD_FILE_EVENT(nfsd_file_free); DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash); DEFINE_NFSD_FILE_EVENT(nfsd_file_put); -DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_release_locked); +DEFINE_NFSD_FILE_EVENT(nfsd_file_closing); +DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_queue); + +TRACE_EVENT(nfsd_file_alloc, + TP_PROTO( + const struct nfsd_file *nf + ), + TP_ARGS(nf), + TP_STRUCT__entry( + __field(const void *, nf_inode) + __field(unsigned long, nf_flags) + __field(unsigned long, nf_may) + __field(unsigned int, nf_ref) + ), + TP_fast_assign( + __entry->nf_inode = nf->nf_inode; + __entry->nf_flags = nf->nf_flags; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->nf_may = nf->nf_may; + ), + TP_printk("inode=%p ref=%u flags=%s may=%s", + __entry->nf_inode, __entry->nf_ref, + show_nf_flags(__entry->nf_flags), + show_nfsd_may_flags(__entry->nf_may) + ) +); TRACE_EVENT(nfsd_file_acquire, - TP_PROTO(struct svc_rqst *rqstp, unsigned int hash, - struct inode *inode, unsigned int may_flags, - struct nfsd_file *nf, __be32 status), + TP_PROTO( + const struct svc_rqst *rqstp, + const struct inode *inode, + unsigned int may_flags, + const struct nfsd_file *nf, + __be32 status + ), - TP_ARGS(rqstp, hash, inode, may_flags, nf, status), + TP_ARGS(rqstp, inode, may_flags, nf, status), TP_STRUCT__entry( __field(u32, xid) - __field(unsigned int, hash) - __field(void *, inode) + __field(const void *, inode) __field(unsigned long, may_flags) - __field(int, nf_ref) + __field(unsigned int, nf_ref) __field(unsigned long, nf_flags) __field(unsigned long, nf_may) - __field(struct file *, nf_file) + __field(const void *, nf_file) __field(u32, status) ), TP_fast_assign( __entry->xid = be32_to_cpu(rqstp->rq_xid); - __entry->hash = hash; __entry->inode = inode; __entry->may_flags = may_flags; __entry->nf_ref = nf ? refcount_read(&nf->nf_ref) : 0; @@ -712,39 +971,131 @@ TRACE_EVENT(nfsd_file_acquire, __entry->status = be32_to_cpu(status); ), - TP_printk("xid=0x%x hash=0x%x inode=%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=%p status=%u", - __entry->xid, __entry->hash, __entry->inode, + TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p status=%u", + __entry->xid, __entry->inode, show_nfsd_may_flags(__entry->may_flags), __entry->nf_ref, show_nf_flags(__entry->nf_flags), show_nfsd_may_flags(__entry->nf_may), - __entry->nf_file, __entry->status) + __entry->nf_file, __entry->status + ) ); -DECLARE_EVENT_CLASS(nfsd_file_search_class, - TP_PROTO(struct inode *inode, unsigned int hash, int found), - TP_ARGS(inode, hash, found), +TRACE_EVENT(nfsd_file_insert_err, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct inode *inode, + unsigned int may_flags, + long error + ), + TP_ARGS(rqstp, inode, may_flags, error), TP_STRUCT__entry( - __field(struct inode *, inode) - __field(unsigned int, hash) - __field(int, found) + __field(u32, xid) + __field(const void *, inode) + __field(unsigned long, may_flags) + __field(long, error) ), TP_fast_assign( + __entry->xid = be32_to_cpu(rqstp->rq_xid); __entry->inode = inode; - __entry->hash = hash; - __entry->found = found; + __entry->may_flags = may_flags; + __entry->error = error; ), - TP_printk("hash=0x%x inode=%p found=%d", __entry->hash, - __entry->inode, __entry->found) + TP_printk("xid=0x%x inode=%p may_flags=%s error=%ld", + __entry->xid, __entry->inode, + show_nfsd_may_flags(__entry->may_flags), + __entry->error + ) ); -#define DEFINE_NFSD_FILE_SEARCH_EVENT(name) \ -DEFINE_EVENT(nfsd_file_search_class, name, \ - TP_PROTO(struct inode *inode, unsigned int hash, int found), \ - TP_ARGS(inode, hash, found)) +TRACE_EVENT(nfsd_file_cons_err, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct inode *inode, + unsigned int may_flags, + const struct nfsd_file *nf + ), + TP_ARGS(rqstp, inode, may_flags, nf), + TP_STRUCT__entry( + __field(u32, xid) + __field(const void *, inode) + __field(unsigned long, may_flags) + __field(unsigned int, nf_ref) + __field(unsigned long, nf_flags) + __field(unsigned long, nf_may) + __field(const void *, nf_file) + ), + TP_fast_assign( + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->inode = inode; + __entry->may_flags = may_flags; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->nf_flags = nf->nf_flags; + __entry->nf_may = nf->nf_may; + __entry->nf_file = nf->nf_file; + ), + TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p", + __entry->xid, __entry->inode, + show_nfsd_may_flags(__entry->may_flags), __entry->nf_ref, + show_nf_flags(__entry->nf_flags), + show_nfsd_may_flags(__entry->nf_may), __entry->nf_file + ) +); -DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode_sync); -DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode); -DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_is_cached); +DECLARE_EVENT_CLASS(nfsd_file_open_class, + TP_PROTO(const struct nfsd_file *nf, __be32 status), + TP_ARGS(nf, status), + TP_STRUCT__entry( + __field(void *, nf_inode) /* cannot be dereferenced */ + __field(int, nf_ref) + __field(unsigned long, nf_flags) + __field(unsigned long, nf_may) + __field(void *, nf_file) /* cannot be dereferenced */ + ), + TP_fast_assign( + __entry->nf_inode = nf->nf_inode; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->nf_flags = nf->nf_flags; + __entry->nf_may = nf->nf_may; + __entry->nf_file = nf->nf_file; + ), + TP_printk("inode=%p ref=%d flags=%s may=%s file=%p", + __entry->nf_inode, + __entry->nf_ref, + show_nf_flags(__entry->nf_flags), + show_nfsd_may_flags(__entry->nf_may), + __entry->nf_file) +) + +#define DEFINE_NFSD_FILE_OPEN_EVENT(name) \ +DEFINE_EVENT(nfsd_file_open_class, name, \ + TP_PROTO( \ + const struct nfsd_file *nf, \ + __be32 status \ + ), \ + TP_ARGS(nf, status)) + +DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_open); +DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_opened); + +TRACE_EVENT(nfsd_file_is_cached, + TP_PROTO( + const struct inode *inode, + int found + ), + TP_ARGS(inode, found), + TP_STRUCT__entry( + __field(const struct inode *, inode) + __field(int, found) + ), + TP_fast_assign( + __entry->inode = inode; + __entry->found = found; + ), + TP_printk("inode=%p is %scached", + __entry->inode, + __entry->found ? "" : "not " + ) +); TRACE_EVENT(nfsd_file_fsnotify_handle_event, TP_PROTO(struct inode *inode, u32 mask), @@ -765,6 +1116,91 @@ TRACE_EVENT(nfsd_file_fsnotify_handle_event, __entry->nlink, __entry->mode, __entry->mask) ); +DECLARE_EVENT_CLASS(nfsd_file_gc_class, + TP_PROTO( + const struct nfsd_file *nf + ), + TP_ARGS(nf), + TP_STRUCT__entry( + __field(void *, nf_inode) + __field(void *, nf_file) + __field(int, nf_ref) + __field(unsigned long, nf_flags) + ), + TP_fast_assign( + __entry->nf_inode = nf->nf_inode; + __entry->nf_file = nf->nf_file; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->nf_flags = nf->nf_flags; + ), + TP_printk("inode=%p ref=%d nf_flags=%s nf_file=%p", + __entry->nf_inode, __entry->nf_ref, + show_nf_flags(__entry->nf_flags), + __entry->nf_file + ) +); + +#define DEFINE_NFSD_FILE_GC_EVENT(name) \ +DEFINE_EVENT(nfsd_file_gc_class, name, \ + TP_PROTO( \ + const struct nfsd_file *nf \ + ), \ + TP_ARGS(nf)) + +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_add); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_add_disposed); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_del); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_del_disposed); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_in_use); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_writeback); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_referenced); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_disposed); + +DECLARE_EVENT_CLASS(nfsd_file_lruwalk_class, + TP_PROTO( + unsigned long removed, + unsigned long remaining + ), + TP_ARGS(removed, remaining), + TP_STRUCT__entry( + __field(unsigned long, removed) + __field(unsigned long, remaining) + ), + TP_fast_assign( + __entry->removed = removed; + __entry->remaining = remaining; + ), + TP_printk("%lu entries removed, %lu remaining", + __entry->removed, __entry->remaining) +); + +#define DEFINE_NFSD_FILE_LRUWALK_EVENT(name) \ +DEFINE_EVENT(nfsd_file_lruwalk_class, name, \ + TP_PROTO( \ + unsigned long removed, \ + unsigned long remaining \ + ), \ + TP_ARGS(removed, remaining)) + +DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_gc_removed); +DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_shrinker_removed); + +TRACE_EVENT(nfsd_file_close, + TP_PROTO( + const struct inode *inode + ), + TP_ARGS(inode), + TP_STRUCT__entry( + __field(const void *, inode) + ), + TP_fast_assign( + __entry->inode = inode; + ), + TP_printk("inode=%p", + __entry->inode + ) +); + #include "cache.h" TRACE_DEFINE_ENUM(RC_DROPIT); @@ -1060,6 +1496,92 @@ TRACE_EVENT(nfsd_cb_offload, __entry->fh_hash, __entry->count, __entry->status) ); +TRACE_EVENT(nfsd_cb_recall_any, + TP_PROTO( + const struct nfsd4_cb_recall_any *ra + ), + TP_ARGS(ra), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, keep) + __field(unsigned long, bmval0) + __sockaddr(addr, ra->ra_cb.cb_clp->cl_cb_conn.cb_addrlen) + ), + TP_fast_assign( + __entry->cl_boot = ra->ra_cb.cb_clp->cl_clientid.cl_boot; + __entry->cl_id = ra->ra_cb.cb_clp->cl_clientid.cl_id; + __entry->keep = ra->ra_keep; + __entry->bmval0 = ra->ra_bmval[0]; + __assign_sockaddr(addr, &ra->ra_cb.cb_clp->cl_addr, + ra->ra_cb.cb_clp->cl_cb_conn.cb_addrlen); + ), + TP_printk("addr=%pISpc client %08x:%08x keep=%u bmval0=%s", + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, + __entry->keep, show_rca_mask(__entry->bmval0) + ) +); + +DECLARE_EVENT_CLASS(nfsd_cb_done_class, + TP_PROTO( + const stateid_t *stp, + const struct rpc_task *task + ), + TP_ARGS(stp, task), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, si_id) + __field(u32, si_generation) + __field(int, status) + ), + TP_fast_assign( + __entry->cl_boot = stp->si_opaque.so_clid.cl_boot; + __entry->cl_id = stp->si_opaque.so_clid.cl_id; + __entry->si_id = stp->si_opaque.so_id; + __entry->si_generation = stp->si_generation; + __entry->status = task->tk_status; + ), + TP_printk("client %08x:%08x stateid %08x:%08x status=%d", + __entry->cl_boot, __entry->cl_id, __entry->si_id, + __entry->si_generation, __entry->status + ) +); + +#define DEFINE_NFSD_CB_DONE_EVENT(name) \ +DEFINE_EVENT(nfsd_cb_done_class, name, \ + TP_PROTO( \ + const stateid_t *stp, \ + const struct rpc_task *task \ + ), \ + TP_ARGS(stp, task)) + +DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_recall_done); +DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_notify_lock_done); +DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_layout_done); +DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_offload_done); + +TRACE_EVENT(nfsd_cb_recall_any_done, + TP_PROTO( + const struct nfsd4_callback *cb, + const struct rpc_task *task + ), + TP_ARGS(cb, task), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(int, status) + ), + TP_fast_assign( + __entry->status = task->tk_status; + __entry->cl_boot = cb->cb_clp->cl_clientid.cl_boot; + __entry->cl_id = cb->cb_clp->cl_clientid.cl_id; + ), + TP_printk("client %08x:%08x status=%d", + __entry->cl_boot, __entry->cl_id, __entry->status + ) +); + #endif /* _NFSD_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index c39b8a653804..0f430548bfbb 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -32,14 +32,13 @@ #include <linux/writeback.h> #include <linux/security.h> -#ifdef CONFIG_NFSD_V3 #include "xdr3.h" -#endif /* CONFIG_NFSD_V3 */ #ifdef CONFIG_NFSD_V4 #include "../internal.h" #include "acl.h" #include "idmap.h" +#include "xdr4.h" #endif /* CONFIG_NFSD_V4 */ #include "nfsd.h" @@ -49,6 +48,69 @@ #define NFSDDBG_FACILITY NFSDDBG_FILEOP +/** + * nfserrno - Map Linux errnos to NFS errnos + * @errno: POSIX(-ish) error code to be mapped + * + * Returns the appropriate (net-endian) nfserr_* (or nfs_ok if errno is 0). If + * it's an error we don't expect, log it once and return nfserr_io. + */ +__be32 +nfserrno (int errno) +{ + static struct { + __be32 nfserr; + int syserr; + } nfs_errtbl[] = { + { nfs_ok, 0 }, + { nfserr_perm, -EPERM }, + { nfserr_noent, -ENOENT }, + { nfserr_io, -EIO }, + { nfserr_nxio, -ENXIO }, + { nfserr_fbig, -E2BIG }, + { nfserr_stale, -EBADF }, + { nfserr_acces, -EACCES }, + { nfserr_exist, -EEXIST }, + { nfserr_xdev, -EXDEV }, + { nfserr_mlink, -EMLINK }, + { nfserr_nodev, -ENODEV }, + { nfserr_notdir, -ENOTDIR }, + { nfserr_isdir, -EISDIR }, + { nfserr_inval, -EINVAL }, + { nfserr_fbig, -EFBIG }, + { nfserr_nospc, -ENOSPC }, + { nfserr_rofs, -EROFS }, + { nfserr_mlink, -EMLINK }, + { nfserr_nametoolong, -ENAMETOOLONG }, + { nfserr_notempty, -ENOTEMPTY }, + { nfserr_dquot, -EDQUOT }, + { nfserr_stale, -ESTALE }, + { nfserr_jukebox, -ETIMEDOUT }, + { nfserr_jukebox, -ERESTARTSYS }, + { nfserr_jukebox, -EAGAIN }, + { nfserr_jukebox, -EWOULDBLOCK }, + { nfserr_jukebox, -ENOMEM }, + { nfserr_io, -ETXTBSY }, + { nfserr_notsupp, -EOPNOTSUPP }, + { nfserr_toosmall, -ETOOSMALL }, + { nfserr_serverfault, -ESERVERFAULT }, + { nfserr_serverfault, -ENFILE }, + { nfserr_io, -EREMOTEIO }, + { nfserr_stale, -EOPENSTALE }, + { nfserr_io, -EUCLEAN }, + { nfserr_perm, -ENOKEY }, + { nfserr_no_grace, -ENOGRACE}, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) { + if (nfs_errtbl[i].syserr == errno) + return nfs_errtbl[i].nfserr; + } + WARN_ONCE(1, "nfsd: non-standard errno: %d\n", errno); + return nfserr_io; +} + /* * Called from nfsd_lookup and encode_dirent. Check if we have crossed * a mount point. @@ -199,27 +261,13 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_nfserr; } } else { - /* - * In the nfsd4_open() case, this may be held across - * subsequent open and delegation acquisition which may - * need to take the child's i_mutex: - */ - fh_lock_nested(fhp, I_MUTEX_PARENT); - dentry = lookup_one_len(name, dparent, len); + dentry = lookup_one_len_unlocked(name, dparent, len); host_err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_nfserr; if (nfsd_mountpoint(dentry, exp)) { - /* - * We don't need the i_mutex after all. It's - * still possible we could open this (regular - * files can be mountpoints too), but the - * i_mutex is just there to prevent renames of - * something that we might be about to delegate, - * and a mountpoint won't be renamed: - */ - fh_unlock(fhp); - if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) { + host_err = nfsd_cross_mnt(rqstp, &dentry, &exp); + if (host_err) { dput(dentry); goto out_nfserr; } @@ -234,7 +282,15 @@ out_nfserr: return nfserrno(host_err); } -/* +/** + * nfsd_lookup - look up a single path component for nfsd + * + * @rqstp: the request context + * @fhp: the file handle of the directory + * @name: the component name, or %NULL to look up parent + * @len: length of name to examine + * @resfh: pointer to pre-initialised filehandle to hold result. + * * Look up one component of a pathname. * N.B. After this call _both_ fhp and resfh need an fh_put * @@ -244,10 +300,11 @@ out_nfserr: * returned. Otherwise the covered directory is returned. * NOTE: this mountpoint crossing is not supported properly by all * clients and is explicitly disallowed for NFSv3 + * */ __be32 nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, - unsigned int len, struct svc_fh *resfh) + unsigned int len, struct svc_fh *resfh) { struct svc_export *exp; struct dentry *dentry; @@ -305,6 +362,10 @@ commit_metadata(struct svc_fh *fhp) static void nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) { + /* Ignore mode updates on symlinks */ + if (S_ISLNK(inode->i_mode)) + iap->ia_valid &= ~ATTR_MODE; + /* sanitize the mode change */ if (iap->ia_valid & ATTR_MODE) { iap->ia_mode &= S_IALLUGO; @@ -346,21 +407,77 @@ nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp, return nfserrno(get_write_access(inode)); } -/* - * Set various file attributes. After this call fhp needs an fh_put. +static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) +{ + int host_err; + + if (iap->ia_valid & ATTR_SIZE) { + /* + * RFC5661, Section 18.30.4: + * Changing the size of a file with SETATTR indirectly + * changes the time_modify and change attributes. + * + * (and similar for the older RFCs) + */ + struct iattr size_attr = { + .ia_valid = ATTR_SIZE | ATTR_CTIME | ATTR_MTIME, + .ia_size = iap->ia_size, + }; + + if (iap->ia_size < 0) + return -EFBIG; + + host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL); + if (host_err) + return host_err; + iap->ia_valid &= ~ATTR_SIZE; + + /* + * Avoid the additional setattr call below if the only other + * attribute that the client sends is the mtime, as we update + * it as part of the size change above. + */ + if ((iap->ia_valid & ~ATTR_MTIME) == 0) + return 0; + } + + if (!iap->ia_valid) + return 0; + + iap->ia_valid |= ATTR_CTIME; + return notify_change(&init_user_ns, dentry, iap, NULL); +} + +/** + * nfsd_setattr - Set various file attributes. + * @rqstp: controlling RPC transaction + * @fhp: filehandle of target + * @attr: attributes to set + * @check_guard: set to 1 if guardtime is a valid timestamp + * @guardtime: do not act if ctime.tv_sec does not match this timestamp + * + * This call may adjust the contents of @attr (in particular, this + * call may change the bits in the na_iattr.ia_valid field). + * + * Returns nfs_ok on success, otherwise an NFS status code is + * returned. Caller must release @fhp by calling fh_put in either + * case. */ __be32 -nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, +nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_attrs *attr, int check_guard, time64_t guardtime) { struct dentry *dentry; struct inode *inode; + struct iattr *iap = attr->na_iattr; int accmode = NFSD_MAY_SATTR; umode_t ftype = 0; __be32 err; - int host_err; + int host_err = 0; bool get_write_count; bool size_change = (iap->ia_valid & ATTR_SIZE); + int retries; if (iap->ia_valid & ATTR_SIZE) { accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE; @@ -396,13 +513,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, dentry = fhp->fh_dentry; inode = d_inode(dentry); - /* Ignore any mode updates on symlinks */ - if (S_ISLNK(inode->i_mode)) - iap->ia_valid &= ~ATTR_MODE; - - if (!iap->ia_valid) - return 0; - nfsd_sanitize_attrs(inode, iap); if (check_guard && guardtime != inode->i_ctime.tv_sec) @@ -421,49 +531,43 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, return err; } - fh_lock(fhp); - if (size_change) { - /* - * RFC5661, Section 18.30.4: - * Changing the size of a file with SETATTR indirectly - * changes the time_modify and change attributes. - * - * (and similar for the older RFCs) - */ - struct iattr size_attr = { - .ia_valid = ATTR_SIZE | ATTR_CTIME | ATTR_MTIME, - .ia_size = iap->ia_size, - }; - - host_err = -EFBIG; - if (iap->ia_size < 0) - goto out_unlock; - - host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL); - if (host_err) - goto out_unlock; - iap->ia_valid &= ~ATTR_SIZE; + inode_lock(inode); + fh_fill_pre_attrs(fhp); + for (retries = 1;;) { + struct iattr attrs; /* - * Avoid the additional setattr call below if the only other - * attribute that the client sends is the mtime, as we update - * it as part of the size change above. + * notify_change() can alter its iattr argument, making + * @iap unsuitable for submission multiple times. Make a + * copy for every loop iteration. */ - if ((iap->ia_valid & ~ATTR_MTIME) == 0) - goto out_unlock; + attrs = *iap; + host_err = __nfsd_setattr(dentry, &attrs); + if (host_err != -EAGAIN || !retries--) + break; + if (!nfsd_wait_for_delegreturn(rqstp, inode)) + break; } - - iap->ia_valid |= ATTR_CTIME; - host_err = notify_change(&init_user_ns, dentry, iap, NULL); - -out_unlock: - fh_unlock(fhp); + if (attr->na_seclabel && attr->na_seclabel->len) + attr->na_labelerr = security_inode_setsecctx(dentry, + attr->na_seclabel->data, attr->na_seclabel->len); + if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && attr->na_pacl) + attr->na_aclerr = set_posix_acl(&init_user_ns, + inode, ACL_TYPE_ACCESS, + attr->na_pacl); + if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && + !attr->na_aclerr && attr->na_dpacl && S_ISDIR(inode->i_mode)) + attr->na_aclerr = set_posix_acl(&init_user_ns, + inode, ACL_TYPE_DEFAULT, + attr->na_dpacl); + fh_fill_post_attrs(fhp); + inode_unlock(inode); if (size_change) put_write_access(inode); out: if (!host_err) host_err = commit_metadata(fhp); - return nfserrno(host_err); + return err != 0 ? err : nfserrno(host_err); } #if defined(CONFIG_NFSD_V4) @@ -495,35 +599,16 @@ int nfsd4_is_junction(struct dentry *dentry) return 0; return 1; } -#ifdef CONFIG_NFSD_V4_SECURITY_LABEL -__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct xdr_netobj *label) -{ - __be32 error; - int host_error; - struct dentry *dentry; - error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, NFSD_MAY_SATTR); - if (error) - return error; - - dentry = fhp->fh_dentry; - - inode_lock(d_inode(dentry)); - host_error = security_inode_setsecctx(dentry, label->data, label->len); - inode_unlock(d_inode(dentry)); - return nfserrno(host_error); -} -#else -__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct xdr_netobj *label) +static struct nfsd4_compound_state *nfsd4_get_cstate(struct svc_rqst *rqstp) { - return nfserr_notsupp; + return &((struct nfsd4_compoundres *)rqstp->rq_resp)->cstate; } -#endif -__be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos, - struct nfsd_file *nf_dst, u64 dst_pos, u64 count, bool sync) +__be32 nfsd4_clone_file_range(struct svc_rqst *rqstp, + struct nfsd_file *nf_src, u64 src_pos, + struct nfsd_file *nf_dst, u64 dst_pos, + u64 count, bool sync) { struct file *src = nf_src->nf_file; struct file *dst = nf_dst->nf_file; @@ -550,8 +635,17 @@ __be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos, if (!status) status = commit_inode_metadata(file_inode(src)); if (status < 0) { - nfsd_reset_boot_verifier(net_generic(nf_dst->nf_net, - nfsd_net_id)); + struct nfsd_net *nn = net_generic(nf_dst->nf_net, + nfsd_net_id); + + trace_nfsd_clone_file_range_err(rqstp, + &nfsd4_get_cstate(rqstp)->save_fh, + src_pos, + &nfsd4_get_cstate(rqstp)->current_fh, + dst_pos, + count, status); + nfsd_reset_write_verifier(nn); + trace_nfsd_writeverf_reset(nn, rqstp, status); ret = nfserrno(status); } } @@ -598,7 +692,6 @@ __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp, } #endif /* defined(CONFIG_NFSD_V4) */ -#ifdef CONFIG_NFSD_V3 /* * Check server access rights to a file system object */ @@ -710,7 +803,6 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor out: return error; } -#endif /* CONFIG_NFSD_V3 */ int nfsd_open_break_lease(struct inode *inode, int access) { @@ -743,9 +835,6 @@ __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, path.dentry = fhp->fh_dentry; inode = d_inode(path.dentry); - /* Disallow write access to files with the append-only bit set - * or any access when mandatory locking enabled - */ err = nfserr_perm; if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE)) goto out; @@ -793,6 +882,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp) { __be32 err; + bool retried = false; validate_process_creds(); /* @@ -808,21 +898,37 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, */ if (type == S_IFREG) may_flags |= NFSD_MAY_OWNER_OVERRIDE; +retry: err = fh_verify(rqstp, fhp, type, may_flags); - if (!err) + if (!err) { err = __nfsd_open(rqstp, fhp, type, may_flags, filp); + if (err == nfserr_stale && !retried) { + retried = true; + fh_put(fhp); + goto retry; + } + } validate_process_creds(); return err; } +/** + * nfsd_open_verified - Open a regular file for the filecache + * @rqstp: RPC request + * @fhp: NFS filehandle of the file to open + * @may_flags: internal permission flags + * @filp: OUT: open "struct file *" + * + * Returns an nfsstat value in network byte order. + */ __be32 -nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, - int may_flags, struct file **filp) +nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags, + struct file **filp) { __be32 err; validate_process_creds(); - err = __nfsd_open(rqstp, fhp, type, may_flags, filp); + err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp); validate_process_creds(); return err; } @@ -837,17 +943,23 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { struct svc_rqst *rqstp = sd->u.data; - struct page **pp = rqstp->rq_next_page; - struct page *page = buf->page; + struct page *page = buf->page; // may be a compound one + unsigned offset = buf->offset; + struct page *last_page; - if (rqstp->rq_res.page_len == 0) { - svc_rqst_replace_page(rqstp, page); - rqstp->rq_res.page_base = buf->offset; - } else if (page != pp[-1]) { + last_page = page + (offset + sd->len - 1) / PAGE_SIZE; + for (page += offset / PAGE_SIZE; page <= last_page; page++) { + /* + * Skip page replacement when extending the contents + * of the current page. + */ + if (page == *(rqstp->rq_next_page - 1)) + continue; svc_rqst_replace_page(rqstp, page); } + if (rqstp->rq_res.page_len == 0) // first call + rqstp->rq_res.page_base = offset % PAGE_SIZE; rqstp->rq_res.page_len += sd->len; - return sd->len; } @@ -960,6 +1072,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, unsigned long *cnt, int stable, __be32 *verf) { + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct file *file = nf->nf_file; struct super_block *sb = file_inode(file)->i_sb; struct svc_export *exp; @@ -1003,25 +1116,14 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt); since = READ_ONCE(file->f_wb_err); - if (flags & RWF_SYNC) { - if (verf) - nfsd_copy_boot_verifier(verf, - net_generic(SVC_NET(rqstp), - nfsd_net_id)); - host_err = vfs_iter_write(file, &iter, &pos, flags); - if (host_err < 0) - nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp), - nfsd_net_id)); - } else { - if (verf) - nfsd_copy_boot_verifier(verf, - net_generic(SVC_NET(rqstp), - nfsd_net_id)); - host_err = vfs_iter_write(file, &iter, &pos, flags); - } + if (verf) + nfsd_copy_write_verifier(verf, nn); + file_start_write(file); + host_err = vfs_iter_write(file, &iter, &pos, flags); + file_end_write(file); if (host_err < 0) { - nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp), - nfsd_net_id)); + nfsd_reset_write_verifier(nn); + trace_nfsd_writeverf_reset(nn, rqstp, host_err); goto out_nfserr; } *cnt = host_err; @@ -1033,9 +1135,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, if (stable && use_wgather) { host_err = wait_for_concurrent_writes(file); - if (host_err < 0) - nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp), - nfsd_net_id)); + if (host_err < 0) { + nfsd_reset_write_verifier(nn); + trace_nfsd_writeverf_reset(nn, rqstp, host_err); + } } out_nfserr: @@ -1065,7 +1168,7 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 err; trace_nfsd_read_start(rqstp, fhp, offset, *count); - err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf); + err = nfsd_file_acquire_gc(rqstp, fhp, NFSD_MAY_READ, &nf); if (err) return err; @@ -1097,7 +1200,7 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset, trace_nfsd_write_start(rqstp, fhp, offset, *cnt); - err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_WRITE, &nf); + err = nfsd_file_acquire_gc(rqstp, fhp, NFSD_MAY_WRITE, &nf); if (err) goto out; @@ -1109,11 +1212,11 @@ out: return err; } -#ifdef CONFIG_NFSD_V3 /** * nfsd_commit - Commit pending writes to stable storage * @rqstp: RPC request being processed * @fhp: NFS filehandle + * @nf: target file * @offset: raw offset from beginning of file * @count: raw count of bytes to sync * @verf: filled in with the server's current write verifier @@ -1130,19 +1233,13 @@ out: * An nfsstat value in network byte order. */ __be32 -nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset, - u32 count, __be32 *verf) +nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, + u64 offset, u32 count, __be32 *verf) { + __be32 err = nfs_ok; u64 maxbytes; loff_t start, end; struct nfsd_net *nn; - struct nfsd_file *nf; - __be32 err; - - err = nfsd_file_acquire(rqstp, fhp, - NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &nf); - if (err) - goto out; /* * Convert the client-provided (offset, count) range to a @@ -1167,7 +1264,7 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset, err2 = vfs_fsync_range(nf->nf_file, start, end, 0); switch (err2) { case 0: - nfsd_copy_boot_verifier(verf, nn); + nfsd_copy_write_verifier(verf, nn); err2 = filemap_check_wb_err(nf->nf_file->f_mapping, since); err = nfserrno(err2); @@ -1176,26 +1273,37 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset, err = nfserr_notsupp; break; default: - nfsd_reset_boot_verifier(nn); + nfsd_reset_write_verifier(nn); + trace_nfsd_writeverf_reset(nn, rqstp, err2); err = nfserrno(err2); } } else - nfsd_copy_boot_verifier(verf, nn); + nfsd_copy_write_verifier(verf, nn); - nfsd_file_put(nf); -out: return err; } -#endif /* CONFIG_NFSD_V3 */ -static __be32 -nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp, - struct iattr *iap) +/** + * nfsd_create_setattr - Set a created file's attributes + * @rqstp: RPC transaction being executed + * @fhp: NFS filehandle of parent directory + * @resfhp: NFS filehandle of new object + * @attrs: requested attributes of new object + * + * Returns nfs_ok on success, or an nfsstat in network byte order. + */ +__be32 +nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct svc_fh *resfhp, struct nfsd_attrs *attrs) { + struct iattr *iap = attrs->na_iattr; + __be32 status; + /* - * Mode has already been set earlier in create: + * Mode has already been set by file creation. */ iap->ia_valid &= ~ATTR_MODE; + /* * Setting uid/gid works only for root. Irix appears to * send along the gid on create when it tries to implement @@ -1203,10 +1311,31 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp, */ if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) iap->ia_valid &= ~(ATTR_UID|ATTR_GID); + + /* + * Callers expect new file metadata to be committed even + * if the attributes have not changed. + */ if (iap->ia_valid) - return nfsd_setattr(rqstp, resfhp, iap, 0, (time64_t)0); - /* Callers expect file metadata to be committed here */ - return nfserrno(commit_metadata(resfhp)); + status = nfsd_setattr(rqstp, resfhp, attrs, 0, (time64_t)0); + else + status = nfserrno(commit_metadata(resfhp)); + + /* + * Transactional filesystems had a chance to commit changes + * for both parent and child simultaneously making the + * following commit_metadata a noop in many cases. + */ + if (!status) + status = nfserrno(commit_metadata(fhp)); + + /* + * Update the new filehandle to pick up the new attributes. + */ + if (!status) + status = fh_update(resfhp); + + return status; } /* HPUX client sometimes creates a file in mode 000, and sets size to 0. @@ -1227,26 +1356,19 @@ nfsd_check_ignore_resizing(struct iattr *iap) /* The parent directory should already be locked: */ __be32 nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, - char *fname, int flen, struct iattr *iap, - int type, dev_t rdev, struct svc_fh *resfhp) + struct nfsd_attrs *attrs, + int type, dev_t rdev, struct svc_fh *resfhp) { struct dentry *dentry, *dchild; struct inode *dirp; + struct iattr *iap = attrs->na_iattr; __be32 err; - __be32 err2; int host_err; dentry = fhp->fh_dentry; dirp = d_inode(dentry); dchild = dget(resfhp->fh_dentry); - if (!fhp->fh_locked) { - WARN_ONCE(1, "nfsd_create: parent %pd2 not locked!\n", - dentry); - err = nfserr_io; - goto out; - } - err = nfsd_permission(rqstp, fhp->fh_export, dentry, NFSD_MAY_CREATE); if (err) goto out; @@ -1259,7 +1381,6 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, iap->ia_mode &= ~current_umask(); err = 0; - host_err = 0; switch (type) { case S_IFREG: host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true); @@ -1306,22 +1427,8 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err < 0) goto out_nfserr; - err = nfsd_create_setattr(rqstp, resfhp, iap); + err = nfsd_create_setattr(rqstp, fhp, resfhp, attrs); - /* - * nfsd_create_setattr already committed the child. Transactional - * filesystems had a chance to commit changes for both parent and - * child simultaneously making the following commit_metadata a - * noop. - */ - err2 = nfserrno(commit_metadata(fhp)); - if (err2) - err = err2; - /* - * Update the file handle to get the new inode info. - */ - if (!err) - err = fh_update(resfhp); out: dput(dchild); return err; @@ -1339,8 +1446,8 @@ out_nfserr: */ __be32 nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, - char *fname, int flen, struct iattr *iap, - int type, dev_t rdev, struct svc_fh *resfhp) + char *fname, int flen, struct nfsd_attrs *attrs, + int type, dev_t rdev, struct svc_fh *resfhp) { struct dentry *dentry, *dchild = NULL; __be32 err; @@ -1359,11 +1466,13 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err) return nfserrno(host_err); - fh_lock_nested(fhp, I_MUTEX_PARENT); + inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); dchild = lookup_one_len(fname, dentry, flen); host_err = PTR_ERR(dchild); - if (IS_ERR(dchild)) - return nfserrno(host_err); + if (IS_ERR(dchild)) { + err = nfserrno(host_err); + goto out_unlock; + } err = fh_compose(resfhp, fhp->fh_export, dchild, fhp); /* * We unconditionally drop our ref to dchild as fh_compose will have @@ -1371,178 +1480,14 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, */ dput(dchild); if (err) - return err; - return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type, - rdev, resfhp); -} - -#ifdef CONFIG_NFSD_V3 - -/* - * NFSv3 and NFSv4 version of nfsd_create - */ -__be32 -do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, - char *fname, int flen, struct iattr *iap, - struct svc_fh *resfhp, int createmode, u32 *verifier, - bool *truncp, bool *created) -{ - struct dentry *dentry, *dchild = NULL; - struct inode *dirp; - __be32 err; - int host_err; - __u32 v_mtime=0, v_atime=0; - - err = nfserr_perm; - if (!flen) - goto out; - err = nfserr_exist; - if (isdotent(fname, flen)) - goto out; - if (!(iap->ia_valid & ATTR_MODE)) - iap->ia_mode = 0; - err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC); - if (err) - goto out; - - dentry = fhp->fh_dentry; - dirp = d_inode(dentry); - - host_err = fh_want_write(fhp); - if (host_err) - goto out_nfserr; - - fh_lock_nested(fhp, I_MUTEX_PARENT); - - /* - * Compose the response file handle. - */ - dchild = lookup_one_len(fname, dentry, flen); - host_err = PTR_ERR(dchild); - if (IS_ERR(dchild)) - goto out_nfserr; - - /* If file doesn't exist, check for permissions to create one */ - if (d_really_is_negative(dchild)) { - err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE); - if (err) - goto out; - } - - err = fh_compose(resfhp, fhp->fh_export, dchild, fhp); - if (err) - goto out; - - if (nfsd_create_is_exclusive(createmode)) { - /* solaris7 gets confused (bugid 4218508) if these have - * the high bit set, so just clear the high bits. If this is - * ever changed to use different attrs for storing the - * verifier, then do_open_lookup() will also need to be fixed - * accordingly. - */ - v_mtime = verifier[0]&0x7fffffff; - v_atime = verifier[1]&0x7fffffff; - } - - if (d_really_is_positive(dchild)) { - err = 0; - - switch (createmode) { - case NFS3_CREATE_UNCHECKED: - if (! d_is_reg(dchild)) - goto out; - else if (truncp) { - /* in nfsv4, we need to treat this case a little - * differently. we don't want to truncate the - * file now; this would be wrong if the OPEN - * fails for some other reason. furthermore, - * if the size is nonzero, we should ignore it - * according to spec! - */ - *truncp = (iap->ia_valid & ATTR_SIZE) && !iap->ia_size; - } - else { - iap->ia_valid &= ATTR_SIZE; - goto set_attr; - } - break; - case NFS3_CREATE_EXCLUSIVE: - if ( d_inode(dchild)->i_mtime.tv_sec == v_mtime - && d_inode(dchild)->i_atime.tv_sec == v_atime - && d_inode(dchild)->i_size == 0 ) { - if (created) - *created = true; - break; - } - fallthrough; - case NFS4_CREATE_EXCLUSIVE4_1: - if ( d_inode(dchild)->i_mtime.tv_sec == v_mtime - && d_inode(dchild)->i_atime.tv_sec == v_atime - && d_inode(dchild)->i_size == 0 ) { - if (created) - *created = true; - goto set_attr; - } - fallthrough; - case NFS3_CREATE_GUARDED: - err = nfserr_exist; - } - fh_drop_write(fhp); - goto out; - } - - if (!IS_POSIXACL(dirp)) - iap->ia_mode &= ~current_umask(); - - host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true); - if (host_err < 0) { - fh_drop_write(fhp); - goto out_nfserr; - } - if (created) - *created = true; - - nfsd_check_ignore_resizing(iap); - - if (nfsd_create_is_exclusive(createmode)) { - /* Cram the verifier into atime/mtime */ - iap->ia_valid = ATTR_MTIME|ATTR_ATIME - | ATTR_MTIME_SET|ATTR_ATIME_SET; - /* XXX someone who knows this better please fix it for nsec */ - iap->ia_mtime.tv_sec = v_mtime; - iap->ia_atime.tv_sec = v_atime; - iap->ia_mtime.tv_nsec = 0; - iap->ia_atime.tv_nsec = 0; - } - - set_attr: - err = nfsd_create_setattr(rqstp, resfhp, iap); - - /* - * nfsd_create_setattr already committed the child - * (and possibly also the parent). - */ - if (!err) - err = nfserrno(commit_metadata(fhp)); - - /* - * Update the filehandle to get the new inode info. - */ - if (!err) - err = fh_update(resfhp); - - out: - fh_unlock(fhp); - if (dchild && !IS_ERR(dchild)) - dput(dchild); - fh_drop_write(fhp); - return err; - - out_nfserr: - err = nfserrno(host_err); - goto out; + goto out_unlock; + fh_fill_pre_attrs(fhp); + err = nfsd_create_locked(rqstp, fhp, attrs, type, rdev, resfhp); + fh_fill_post_attrs(fhp); +out_unlock: + inode_unlock(dentry->d_inode); + return err; } -#endif /* CONFIG_NFSD_V3 */ /* * Read a symlink. On entry, *lenp must contain the maximum path length that @@ -1582,15 +1527,25 @@ nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp) return 0; } -/* - * Create a symlink and look up its inode +/** + * nfsd_symlink - Create a symlink and look up its inode + * @rqstp: RPC transaction being executed + * @fhp: NFS filehandle of parent directory + * @fname: filename of the new symlink + * @flen: length of @fname + * @path: content of the new symlink (NUL-terminated) + * @attrs: requested attributes of new object + * @resfhp: NFS filehandle of new object + * * N.B. After this call _both_ fhp and resfhp need an fh_put + * + * Returns nfs_ok on success, or an nfsstat in network byte order. */ __be32 nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, - char *fname, int flen, - char *path, - struct svc_fh *resfhp) + char *fname, int flen, + char *path, struct nfsd_attrs *attrs, + struct svc_fh *resfhp) { struct dentry *dentry, *dnew; __be32 err, cerr; @@ -1608,33 +1563,35 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; host_err = fh_want_write(fhp); - if (host_err) - goto out_nfserr; + if (host_err) { + err = nfserrno(host_err); + goto out; + } - fh_lock(fhp); dentry = fhp->fh_dentry; + inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); dnew = lookup_one_len(fname, dentry, flen); - host_err = PTR_ERR(dnew); - if (IS_ERR(dnew)) - goto out_nfserr; - + if (IS_ERR(dnew)) { + err = nfserrno(PTR_ERR(dnew)); + inode_unlock(dentry->d_inode); + goto out_drop_write; + } + fh_fill_pre_attrs(fhp); host_err = vfs_symlink(&init_user_ns, d_inode(dentry), dnew, path); err = nfserrno(host_err); - fh_unlock(fhp); + cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp); + if (!err) + nfsd_create_setattr(rqstp, fhp, resfhp, attrs); + fh_fill_post_attrs(fhp); + inode_unlock(dentry->d_inode); if (!err) err = nfserrno(commit_metadata(fhp)); - - fh_drop_write(fhp); - - cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp); dput(dnew); if (err==0) err = cerr; +out_drop_write: + fh_drop_write(fhp); out: return err; - -out_nfserr: - err = nfserrno(host_err); - goto out; } /* @@ -1672,22 +1629,25 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, goto out; } - fh_lock_nested(ffhp, I_MUTEX_PARENT); ddir = ffhp->fh_dentry; dirp = d_inode(ddir); + inode_lock_nested(dirp, I_MUTEX_PARENT); dnew = lookup_one_len(name, ddir, len); - host_err = PTR_ERR(dnew); - if (IS_ERR(dnew)) - goto out_nfserr; + if (IS_ERR(dnew)) { + err = nfserrno(PTR_ERR(dnew)); + goto out_unlock; + } dold = tfhp->fh_dentry; err = nfserr_noent; if (d_really_is_negative(dold)) goto out_dput; + fh_fill_pre_attrs(ffhp); host_err = vfs_link(dold, &init_user_ns, dirp, dnew, NULL); - fh_unlock(ffhp); + fh_fill_post_attrs(ffhp); + inode_unlock(dirp); if (!host_err) { err = nfserrno(commit_metadata(ffhp)); if (!err) @@ -1698,17 +1658,17 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, else err = nfserrno(host_err); } -out_dput: dput(dnew); -out_unlock: - fh_unlock(ffhp); +out_drop_write: fh_drop_write(tfhp); out: return err; -out_nfserr: - err = nfserrno(host_err); - goto out_unlock; +out_dput: + dput(dnew); +out_unlock: + inode_unlock(dirp); + goto out_drop_write; } static void @@ -1775,12 +1735,9 @@ retry: goto out; } - /* cannot use fh_lock as we need deadlock protective ordering - * so do it by hand */ trap = lock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = true; - fill_pre_wcc(ffhp); - fill_pre_wcc(tfhp); + fh_fill_pre_attrs(ffhp); + fh_fill_pre_attrs(tfhp); odentry = lookup_one_len(fname, fdentry, flen); host_err = PTR_ERR(odentry); @@ -1815,7 +1772,15 @@ retry: .new_dir = tdir, .new_dentry = ndentry, }; - host_err = vfs_rename(&rd); + int retries; + + for (retries = 1;;) { + host_err = vfs_rename(&rd); + if (host_err != -EAGAIN || !retries--) + break; + if (!nfsd_wait_for_delegreturn(rqstp, d_inode(odentry))) + break; + } if (!host_err) { host_err = commit_metadata(tfhp); if (!host_err) @@ -1828,17 +1793,12 @@ retry: dput(odentry); out_nfserr: err = nfserrno(host_err); - /* - * We cannot rely on fh_unlock on the two filehandles, - * as that would do the wrong thing if the two directories - * were the same, so again we do it by hand. - */ + if (!close_cached) { - fill_post_wcc(ffhp); - fill_post_wcc(tfhp); + fh_fill_post_attrs(ffhp); + fh_fill_post_attrs(tfhp); } unlock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = false; fh_drop_write(ffhp); /* @@ -1882,19 +1842,19 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (host_err) goto out_nfserr; - fh_lock_nested(fhp, I_MUTEX_PARENT); dentry = fhp->fh_dentry; dirp = d_inode(dentry); + inode_lock_nested(dirp, I_MUTEX_PARENT); rdentry = lookup_one_len(fname, dentry, flen); host_err = PTR_ERR(rdentry); if (IS_ERR(rdentry)) - goto out_drop_write; + goto out_unlock; if (d_really_is_negative(rdentry)) { dput(rdentry); host_err = -ENOENT; - goto out_drop_write; + goto out_unlock; } rinode = d_inode(rdentry); ihold(rinode); @@ -1902,15 +1862,26 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (!type) type = d_inode(rdentry)->i_mode & S_IFMT; + fh_fill_pre_attrs(fhp); if (type != S_IFDIR) { + int retries; + if (rdentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) nfsd_close_cached_files(rdentry); - host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL); + + for (retries = 1;;) { + host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL); + if (host_err != -EAGAIN || !retries--) + break; + if (!nfsd_wait_for_delegreturn(rqstp, rinode)) + break; + } } else { host_err = vfs_rmdir(&init_user_ns, dirp, rdentry); } + fh_fill_post_attrs(fhp); - fh_unlock(fhp); + inode_unlock(dirp); if (!host_err) host_err = commit_metadata(fhp); dput(rdentry); @@ -1932,6 +1903,9 @@ out_nfserr: } out: return err; +out_unlock: + inode_unlock(dirp); + goto out_drop_write; } /* @@ -2285,13 +2259,16 @@ out: return err; } -/* - * Removexattr and setxattr need to call fh_lock to both lock the inode - * and set the change attribute. Since the top-level vfs_removexattr - * and vfs_setxattr calls already do their own inode_lock calls, call - * the _locked variant. Pass in a NULL pointer for delegated_inode, - * and let the client deal with NFS4ERR_DELAY (same as with e.g. - * setattr and remove). +/** + * nfsd_removexattr - Remove an extended attribute + * @rqstp: RPC transaction being executed + * @fhp: NFS filehandle of object with xattr to remove + * @name: name of xattr to remove (NUL-terminate) + * + * Pass in a NULL pointer for delegated_inode, and let the client deal + * with NFS4ERR_DELAY (same as with e.g. setattr and remove). + * + * Returns nfs_ok on success, or an nfsstat in network byte order. */ __be32 nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) @@ -2307,12 +2284,14 @@ nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) if (ret) return nfserrno(ret); - fh_lock(fhp); + inode_lock(fhp->fh_dentry->d_inode); + fh_fill_pre_attrs(fhp); ret = __vfs_removexattr_locked(&init_user_ns, fhp->fh_dentry, name, NULL); - fh_unlock(fhp); + fh_fill_post_attrs(fhp); + inode_unlock(fhp->fh_dentry->d_inode); fh_drop_write(fhp); return nfsd_xattr_errno(ret); @@ -2332,12 +2311,13 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, ret = fh_want_write(fhp); if (ret) return nfserrno(ret); - fh_lock(fhp); + inode_lock(fhp->fh_dentry->d_inode); + fh_fill_pre_attrs(fhp); ret = __vfs_setxattr_locked(&init_user_ns, fhp->fh_dentry, name, buf, len, flags, NULL); - - fh_unlock(fhp); + fh_fill_post_attrs(fhp); + inode_unlock(fhp->fh_dentry->d_inode); fh_drop_write(fhp); return nfsd_xattr_errno(ret); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 3cf5a8a13da5..dbdfef7ae85b 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -6,6 +6,8 @@ #ifndef LINUX_NFSD_VFS_H #define LINUX_NFSD_VFS_H +#include <linux/fs.h> +#include <linux/posix_acl.h> #include "nfsfh.h" #include "nfsd.h" @@ -42,6 +44,23 @@ struct nfsd_file; typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned); /* nfsd/vfs.c */ +struct nfsd_attrs { + struct iattr *na_iattr; /* input */ + struct xdr_netobj *na_seclabel; /* input */ + struct posix_acl *na_pacl; /* input */ + struct posix_acl *na_dpacl; /* input */ + + int na_labelerr; /* output */ + int na_aclerr; /* output */ +}; + +static inline void nfsd_attrs_free(struct nfsd_attrs *attrs) +{ + posix_acl_release(attrs->na_pacl); + posix_acl_release(attrs->na_dpacl); +} + +__be32 nfserrno (int errno); int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct svc_export **expp); __be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *, @@ -50,32 +69,28 @@ __be32 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *, const char *, unsigned int, struct svc_export **, struct dentry **); __be32 nfsd_setattr(struct svc_rqst *, struct svc_fh *, - struct iattr *, int, time64_t); + struct nfsd_attrs *, int, time64_t); int nfsd_mountpoint(struct dentry *, struct svc_export *); #ifdef CONFIG_NFSD_V4 -__be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *, - struct xdr_netobj *); __be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *, struct file *, loff_t, loff_t, int); -__be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos, +__be32 nfsd4_clone_file_range(struct svc_rqst *rqstp, + struct nfsd_file *nf_src, u64 src_pos, struct nfsd_file *nf_dst, u64 dst_pos, u64 count, bool sync); #endif /* CONFIG_NFSD_V4 */ __be32 nfsd_create_locked(struct svc_rqst *, struct svc_fh *, - char *name, int len, struct iattr *attrs, - int type, dev_t rdev, struct svc_fh *res); + struct nfsd_attrs *attrs, int type, dev_t rdev, + struct svc_fh *res); __be32 nfsd_create(struct svc_rqst *, struct svc_fh *, - char *name, int len, struct iattr *attrs, + char *name, int len, struct nfsd_attrs *attrs, int type, dev_t rdev, struct svc_fh *res); -#ifdef CONFIG_NFSD_V3 __be32 nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *); -__be32 do_nfsd_create(struct svc_rqst *, struct svc_fh *, - char *name, int len, struct iattr *attrs, - struct svc_fh *res, int createmode, - u32 *verifier, bool *truncp, bool *created); +__be32 nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct svc_fh *resfhp, struct nfsd_attrs *iap); __be32 nfsd_commit(struct svc_rqst *rqst, struct svc_fh *fhp, - u64 offset, u32 count, __be32 *verf); -#endif /* CONFIG_NFSD_V3 */ + struct nfsd_file *nf, u64 offset, u32 count, + __be32 *verf); #ifdef CONFIG_NFSD_V4 __be32 nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, void **bufp, int *lenp); @@ -89,7 +104,7 @@ __be32 nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, int nfsd_open_break_lease(struct inode *, int); __be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t, int, struct file **); -__be32 nfsd_open_verified(struct svc_rqst *, struct svc_fh *, umode_t, +__be32 nfsd_open_verified(struct svc_rqst *, struct svc_fh *, int, struct file **); __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, @@ -113,8 +128,9 @@ __be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, char *, int *); __be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, - char *name, int len, char *path, - struct svc_fh *res); + char *name, int len, char *path, + struct nfsd_attrs *attrs, + struct svc_fh *res); __be32 nfsd_link(struct svc_rqst *, struct svc_fh *, char *, int, struct svc_fh *); ssize_t nfsd_copy_file_range(struct file *, u64, @@ -160,10 +176,4 @@ static inline __be32 fh_getattr(const struct svc_fh *fh, struct kstat *stat) AT_STATX_SYNC_AS_STAT)); } -static inline int nfsd_create_is_exclusive(int createmode) -{ - return createmode == NFS3_CREATE_EXCLUSIVE - || createmode == NFS4_CREATE_EXCLUSIVE4_1; -} - #endif /* LINUX_NFSD_VFS_H */ diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 863a35f24910..852f71580bd0 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -141,23 +141,24 @@ union nfsd_xdrstore { #define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore) -int nfssvc_decode_fhandleargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_readargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_createargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *); -int nfssvc_encode_statres(struct svc_rqst *, __be32 *); -int nfssvc_encode_attrstatres(struct svc_rqst *, __be32 *); -int nfssvc_encode_diropres(struct svc_rqst *, __be32 *); -int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *); -int nfssvc_encode_readres(struct svc_rqst *, __be32 *); -int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *); -int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *); +bool nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); + +bool nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr); void nfssvc_encode_nfscookie(struct nfsd_readdirres *resp, u32 offset); int nfssvc_encode_entry(void *data, const char *name, int namlen, diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 712c117300cb..03fe4e21306c 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -265,36 +265,37 @@ union nfsd3_xdrstore { #define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore) -int nfs3svc_decode_fhandleargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *); -int nfs3svc_encode_getattrres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *); -int nfs3svc_encode_lookupres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_readres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_createres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *); -int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *); +bool nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); + +bool nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr); void nfs3svc_release_fhandle(struct svc_rqst *); void nfs3svc_release_fhandle2(struct svc_rqst *); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 45257666a688..510978e602da 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -273,11 +273,13 @@ struct nfsd4_open { bool op_truncate; /* used during processing */ bool op_created; /* used during processing */ struct nfs4_openowner *op_openowner; /* used during processing */ + struct file *op_filp; /* used during processing */ struct nfs4_file *op_file; /* used during processing */ struct nfs4_ol_stateid *op_stp; /* used during processing */ struct nfs4_clnt_odstate *op_odstate; /* used during processing */ struct nfs4_acl *op_acl; struct xdr_netobj op_label; + struct svc_rqst *op_rqstp; }; struct nfsd4_open_confirm { @@ -301,9 +303,10 @@ struct nfsd4_read { u32 rd_length; /* request */ int rd_vlen; struct nfsd_file *rd_nf; - + struct svc_rqst *rd_rqstp; /* response */ - struct svc_fh *rd_fhp; /* response */ + struct svc_fh *rd_fhp; /* response */ + u32 rd_eof; /* response */ }; struct nfsd4_readdir { @@ -531,6 +534,13 @@ struct nfsd42_write_res { stateid_t cb_stateid; }; +struct nfsd4_cb_offload { + struct nfsd4_callback co_cb; + struct nfsd42_write_res co_res; + __be32 co_nfserr; + struct knfsd_fh co_fh; +}; + struct nfsd4_copy { /* request */ stateid_t cp_src_stateid; @@ -538,18 +548,16 @@ struct nfsd4_copy { u64 cp_src_pos; u64 cp_dst_pos; u64 cp_count; - struct nl4_server cp_src; - bool cp_intra; + struct nl4_server *cp_src; - /* both */ - u32 cp_synchronous; + unsigned long cp_flags; +#define NFSD4_COPY_F_STOPPED (0) +#define NFSD4_COPY_F_INTRA (1) +#define NFSD4_COPY_F_SYNCHRONOUS (2) +#define NFSD4_COPY_F_COMMITTED (3) /* response */ struct nfsd42_write_res cp_res; - - /* for cb_offload */ - struct nfsd4_callback cp_cb; - __be32 nfserr; struct knfsd_fh fh; struct nfs4_client *cp_clp; @@ -562,14 +570,35 @@ struct nfsd4_copy { struct list_head copies; struct task_struct *copy_task; refcount_t refcount; - bool stopped; - struct vfsmount *ss_mnt; + struct nfsd4_ssc_umount_item *ss_nsui; struct nfs_fh c_fh; nfs4_stateid stateid; - bool committed; }; +static inline void nfsd4_copy_set_sync(struct nfsd4_copy *copy, bool sync) +{ + if (sync) + set_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); + else + clear_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); +} + +static inline bool nfsd4_copy_is_sync(const struct nfsd4_copy *copy) +{ + return test_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); +} + +static inline bool nfsd4_copy_is_async(const struct nfsd4_copy *copy) +{ + return !test_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); +} + +static inline bool nfsd4_ssc_is_inter(const struct nfsd4_copy *copy) +{ + return !test_bit(NFSD4_COPY_F_INTRA, ©->cp_flags); +} + struct nfsd4_seek { /* request */ stateid_t seek_stateid; @@ -593,19 +622,20 @@ struct nfsd4_offload_status { struct nfsd4_copy_notify { /* request */ stateid_t cpn_src_stateid; - struct nl4_server cpn_dst; + struct nl4_server *cpn_dst; /* response */ stateid_t cpn_cnr_stateid; u64 cpn_sec; u32 cpn_nsec; - struct nl4_server cpn_src; + struct nl4_server *cpn_src; }; struct nfsd4_op { u32 opnum; - const struct nfsd4_operation * opdesc; __be32 status; + const struct nfsd4_operation *opdesc; + struct nfs4_replay *replay; union nfsd4_op_u { struct nfsd4_access access; struct nfsd4_close close; @@ -669,7 +699,6 @@ struct nfsd4_op { struct nfsd4_listxattrs listxattrs; struct nfsd4_removexattr removexattr; } u; - struct nfs4_replay * replay; }; bool nfsd4_cache_this_op(struct nfsd4_op *); @@ -695,7 +724,6 @@ struct nfsd4_compoundargs { u32 opcnt; struct nfsd4_op *ops; struct nfsd4_op iops[8]; - int cachetype; }; struct nfsd4_compoundres { @@ -703,10 +731,11 @@ struct nfsd4_compoundres { struct xdr_stream *xdr; struct svc_rqst * rqstp; - u32 taglen; + __be32 *statusp; char * tag; + u32 taglen; u32 opcnt; - __be32 * tagp; /* tag, opcount encode location */ + struct nfsd4_compound_state cstate; }; @@ -757,8 +786,8 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); -int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *); -int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *); +bool nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op); @@ -859,12 +888,18 @@ struct nfsd4_operation { u32 op_flags; char *op_name; /* Try to get response size before operation */ - u32 (*op_rsize_bop)(struct svc_rqst *, struct nfsd4_op *); + u32 (*op_rsize_bop)(const struct svc_rqst *rqstp, + const struct nfsd4_op *op); void (*op_get_currentstateid)(struct nfsd4_compound_state *, union nfsd4_op_u *); void (*op_set_currentstateid)(struct nfsd4_compound_state *, union nfsd4_op_u *); }; +struct nfsd4_cb_recall_any { + struct nfsd4_callback ra_cb; + u32 ra_keep; + u32 ra_bmval[1]; +}; #endif diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h index 547cf07cf4e0..0d39af1b00a0 100644 --- a/fs/nfsd/xdr4cb.h +++ b/fs/nfsd/xdr4cb.h @@ -48,3 +48,9 @@ #define NFS4_dec_cb_offload_sz (cb_compound_dec_hdr_sz + \ cb_sequence_dec_sz + \ op_dec_sz) +#define NFS4_enc_cb_recall_any_sz (cb_compound_enc_hdr_sz + \ + cb_sequence_enc_sz + \ + 1 + 1 + 1) +#define NFS4_dec_cb_recall_any_sz (cb_compound_dec_hdr_sz + \ + cb_sequence_dec_sz + \ + op_dec_sz) diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index def9121a466e..385ec71fcdef 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -724,7 +724,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, dat = nilfs_bmap_get_dat(btree); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr = blocknr; } cnt = 1; @@ -743,7 +743,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt || ++cnt == maxblocks) @@ -781,6 +781,11 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, out: nilfs_btree_free_path(path); return ret; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + goto out; } static void nilfs_btree_promote_key(struct nilfs_bmap *btree, diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index f353101955e3..7faf8c285d6c 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -66,7 +66,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, dat = nilfs_bmap_get_dat(direct); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr = blocknr; } @@ -79,7 +79,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt) @@ -87,6 +87,11 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, } *ptrp = ptr; return cnt; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + return ret; } static __u64 diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 324e23236c34..475fd522c7e3 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -112,7 +112,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, "%s (ino=%lu): a race condition while inserting a data block at offset=%llu", __func__, inode->i_ino, (unsigned long long)blkoff); - err = 0; + err = -EAGAIN; } nilfs_transaction_abort(inode->i_sb); goto out; diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index e85e13c50d6d..fa81c59a2ad4 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -150,7 +150,7 @@ void dnotify_flush(struct file *filp, fl_owner_t id) return; dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); - mutex_lock(&dnotify_group->mark_mutex); + fsnotify_group_lock(dnotify_group); spin_lock(&fsn_mark->lock); prev = &dn_mark->dn; @@ -173,7 +173,7 @@ void dnotify_flush(struct file *filp, fl_owner_t id) free = true; } - mutex_unlock(&dnotify_group->mark_mutex); + fsnotify_group_unlock(dnotify_group); if (free) fsnotify_free_mark(fsn_mark); @@ -196,7 +196,7 @@ static __u32 convert_arg(unsigned long arg) if (arg & DN_ATTRIB) new_mask |= FS_ATTRIB; if (arg & DN_RENAME) - new_mask |= FS_DN_RENAME; + new_mask |= FS_RENAME; if (arg & DN_CREATE) new_mask |= (FS_CREATE | FS_MOVED_TO); @@ -306,7 +306,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg) new_dn_mark->dn = NULL; /* this is needed to prevent the fcntl/close race described below */ - mutex_lock(&dnotify_group->mark_mutex); + fsnotify_group_lock(dnotify_group); /* add the new_fsn_mark or find an old one. */ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group); @@ -316,7 +316,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg) } else { error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0); if (error) { - mutex_unlock(&dnotify_group->mark_mutex); + fsnotify_group_unlock(dnotify_group); goto out_err; } spin_lock(&new_fsn_mark->lock); @@ -365,7 +365,7 @@ out: if (destroy) fsnotify_detach_mark(fsn_mark); - mutex_unlock(&dnotify_group->mark_mutex); + fsnotify_group_unlock(dnotify_group); if (destroy) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); @@ -383,7 +383,8 @@ static int __init dnotify_init(void) SLAB_PANIC|SLAB_ACCOUNT); dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); - dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops); + dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, + FSNOTIFY_GROUP_NOFS); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); return 0; diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 057abd2cf887..a2a15bc4df28 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -18,7 +18,7 @@ #include "fanotify.h" -static bool fanotify_path_equal(struct path *p1, struct path *p2) +static bool fanotify_path_equal(const struct path *p1, const struct path *p2) { return p1->mnt == p2->mnt && p1->dentry == p2->dentry; } @@ -76,8 +76,10 @@ static bool fanotify_info_equal(struct fanotify_info *info1, struct fanotify_info *info2) { if (info1->dir_fh_totlen != info2->dir_fh_totlen || + info1->dir2_fh_totlen != info2->dir2_fh_totlen || info1->file_fh_totlen != info2->file_fh_totlen || - info1->name_len != info2->name_len) + info1->name_len != info2->name_len || + info1->name2_len != info2->name2_len) return false; if (info1->dir_fh_totlen && @@ -85,14 +87,24 @@ static bool fanotify_info_equal(struct fanotify_info *info1, fanotify_info_dir_fh(info2))) return false; + if (info1->dir2_fh_totlen && + !fanotify_fh_equal(fanotify_info_dir2_fh(info1), + fanotify_info_dir2_fh(info2))) + return false; + if (info1->file_fh_totlen && !fanotify_fh_equal(fanotify_info_file_fh(info1), fanotify_info_file_fh(info2))) return false; - return !info1->name_len || - !memcmp(fanotify_info_name(info1), fanotify_info_name(info2), - info1->name_len); + if (info1->name_len && + memcmp(fanotify_info_name(info1), fanotify_info_name(info2), + info1->name_len)) + return false; + + return !info1->name2_len || + !memcmp(fanotify_info_name2(info1), fanotify_info_name2(info2), + info1->name2_len); } static bool fanotify_name_event_equal(struct fanotify_name_event *fne1, @@ -111,6 +123,16 @@ static bool fanotify_name_event_equal(struct fanotify_name_event *fne1, return fanotify_info_equal(info1, info2); } +static bool fanotify_error_event_equal(struct fanotify_error_event *fee1, + struct fanotify_error_event *fee2) +{ + /* Error events against the same file system are always merged. */ + if (!fanotify_fsid_equal(&fee1->fsid, &fee2->fsid)) + return false; + + return true; +} + static bool fanotify_should_merge(struct fanotify_event *old, struct fanotify_event *new) { @@ -131,6 +153,13 @@ static bool fanotify_should_merge(struct fanotify_event *old, if ((old->mask & FS_ISDIR) != (new->mask & FS_ISDIR)) return false; + /* + * FAN_RENAME event is reported with special info record types, + * so we cannot merge it with other events. + */ + if ((old->mask & FAN_RENAME) != (new->mask & FAN_RENAME)) + return false; + switch (old->type) { case FANOTIFY_EVENT_TYPE_PATH: return fanotify_path_equal(fanotify_event_path(old), @@ -141,6 +170,9 @@ static bool fanotify_should_merge(struct fanotify_event *old, case FANOTIFY_EVENT_TYPE_FID_NAME: return fanotify_name_event_equal(FANOTIFY_NE(old), FANOTIFY_NE(new)); + case FANOTIFY_EVENT_TYPE_FS_ERROR: + return fanotify_error_event_equal(FANOTIFY_EE(old), + FANOTIFY_EE(new)); default: WARN_ON_ONCE(1); } @@ -176,6 +208,10 @@ static int fanotify_merge(struct fsnotify_group *group, break; if (fanotify_should_merge(old, new)) { old->mask |= new->mask; + + if (fanotify_is_error_event(old->mask)) + FANOTIFY_EE(old)->err_count++; + return 1; } } @@ -255,15 +291,17 @@ out: */ static u32 fanotify_group_event_mask(struct fsnotify_group *group, struct fsnotify_iter_info *iter_info, - u32 event_mask, const void *data, - int data_type, struct inode *dir) + u32 *match_mask, u32 event_mask, + const void *data, int data_type, + struct inode *dir) { - __u32 marks_mask = 0, marks_ignored_mask = 0; + __u32 marks_mask = 0, marks_ignore_mask = 0; __u32 test_mask, user_mask = FANOTIFY_OUTGOING_EVENTS | FANOTIFY_EVENT_FLAGS; const struct path *path = fsnotify_data_path(data, data_type); unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); struct fsnotify_mark *mark; + bool ondir = event_mask & FAN_ONDIR; int type; pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n", @@ -278,37 +316,30 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group, return 0; } else if (!(fid_mode & FAN_REPORT_FID)) { /* Do we have a directory inode to report? */ - if (!dir && !(event_mask & FS_ISDIR)) + if (!dir && !ondir) return 0; } - fsnotify_foreach_obj_type(type) { - if (!fsnotify_iter_should_report_type(iter_info, type)) - continue; - mark = iter_info->marks[type]; - - /* Apply ignore mask regardless of ISDIR and ON_CHILD flags */ - marks_ignored_mask |= mark->ignored_mask; - + fsnotify_foreach_iter_mark_type(iter_info, mark, type) { /* - * If the event is on dir and this mark doesn't care about - * events on dir, don't send it! + * Apply ignore mask depending on event flags in ignore mask. */ - if (event_mask & FS_ISDIR && !(mark->mask & FS_ISDIR)) - continue; + marks_ignore_mask |= + fsnotify_effective_ignore_mask(mark, ondir, type); /* - * If the event is on a child and this mark is on a parent not - * watching children, don't send it! + * Send the event depending on event flags in mark mask. */ - if (type == FSNOTIFY_OBJ_TYPE_PARENT && - !(mark->mask & FS_EVENT_ON_CHILD)) + if (!fsnotify_mask_applicable(mark->mask, ondir, type)) continue; marks_mask |= mark->mask; + + /* Record the mark types of this group that matched the event */ + *match_mask |= 1U << type; } - test_mask = event_mask & marks_mask & ~marks_ignored_mask; + test_mask = event_mask & marks_mask & ~marks_ignore_mask; /* * For dirent modification events (create/delete/move) that do not carry @@ -343,13 +374,23 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group, static int fanotify_encode_fh_len(struct inode *inode) { int dwords = 0; + int fh_len; if (!inode) return 0; exportfs_encode_inode_fh(inode, NULL, &dwords, NULL); + fh_len = dwords << 2; - return dwords << 2; + /* + * struct fanotify_error_event might be preallocated and is + * limited to MAX_HANDLE_SZ. This should never happen, but + * safeguard by forcing an invalid file handle. + */ + if (WARN_ON_ONCE(fh_len > MAX_HANDLE_SZ)) + return 0; + + return fh_len; } /* @@ -370,15 +411,21 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode, fh->type = FILEID_ROOT; fh->len = 0; fh->flags = 0; + + /* + * Invalid FHs are used by FAN_FS_ERROR for errors not + * linked to any inode. The f_handle won't be reported + * back to userspace. + */ if (!inode) - return 0; + goto out; /* * !gpf means preallocated variable size fh, but fh_len could * be zero in that case if encoding fh len failed. */ err = -ENOENT; - if (fh_len < 4 || WARN_ON_ONCE(fh_len % 4)) + if (fh_len < 4 || WARN_ON_ONCE(fh_len % 4) || fh_len > MAX_HANDLE_SZ) goto out_err; /* No external buffer in a variable size allocated fh */ @@ -403,8 +450,13 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode, fh->type = type; fh->len = fh_len; - /* Mix fh into event merge key */ - *hash ^= fanotify_hash_fh(fh); +out: + /* + * Mix fh into event merge key. Hash might be NULL in case of + * unhashed FID events (i.e. FAN_FS_ERROR). + */ + if (hash) + *hash ^= fanotify_hash_fh(fh); return FANOTIFY_FH_HDR_LEN + fh_len; @@ -420,17 +472,41 @@ out_err: } /* - * The inode to use as identifier when reporting fid depends on the event. - * Report the modified directory inode on dirent modification events. - * Report the "victim" inode otherwise. + * FAN_REPORT_FID is ambiguous in that it reports the fid of the child for + * some events and the fid of the parent for create/delete/move events. + * + * With the FAN_REPORT_TARGET_FID flag, the fid of the child is reported + * also in create/delete/move events in addition to the fid of the parent + * and the name of the child. + */ +static inline bool fanotify_report_child_fid(unsigned int fid_mode, u32 mask) +{ + if (mask & ALL_FSNOTIFY_DIRENT_EVENTS) + return (fid_mode & FAN_REPORT_TARGET_FID); + + return (fid_mode & FAN_REPORT_FID) && !(mask & FAN_ONDIR); +} + +/* + * The inode to use as identifier when reporting fid depends on the event + * and the group flags. + * + * With the group flag FAN_REPORT_TARGET_FID, always report the child fid. + * + * Without the group flag FAN_REPORT_TARGET_FID, report the modified directory + * fid on dirent events and the child fid otherwise. + * * For example: - * FS_ATTRIB reports the child inode even if reported on a watched parent. - * FS_CREATE reports the modified dir inode and not the created inode. + * FS_ATTRIB reports the child fid even if reported on a watched parent. + * FS_CREATE reports the modified dir fid without FAN_REPORT_TARGET_FID. + * and reports the created child fid with FAN_REPORT_TARGET_FID. */ static struct inode *fanotify_fid_inode(u32 event_mask, const void *data, - int data_type, struct inode *dir) + int data_type, struct inode *dir, + unsigned int fid_mode) { - if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) + if ((event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) && + !(fid_mode & FAN_REPORT_TARGET_FID)) return dir; return fsnotify_data_inode(data, data_type); @@ -452,7 +528,7 @@ static struct inode *fanotify_dfid_inode(u32 event_mask, const void *data, if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) return dir; - if (S_ISDIR(inode->i_mode)) + if (inode && S_ISDIR(inode->i_mode)) return inode; return dir; @@ -514,25 +590,34 @@ static struct fanotify_event *fanotify_alloc_fid_event(struct inode *id, return &ffe->fae; } -static struct fanotify_event *fanotify_alloc_name_event(struct inode *id, +static struct fanotify_event *fanotify_alloc_name_event(struct inode *dir, __kernel_fsid_t *fsid, const struct qstr *name, struct inode *child, + struct dentry *moved, unsigned int *hash, gfp_t gfp) { struct fanotify_name_event *fne; struct fanotify_info *info; struct fanotify_fh *dfh, *ffh; - unsigned int dir_fh_len = fanotify_encode_fh_len(id); + struct inode *dir2 = moved ? d_inode(moved->d_parent) : NULL; + const struct qstr *name2 = moved ? &moved->d_name : NULL; + unsigned int dir_fh_len = fanotify_encode_fh_len(dir); + unsigned int dir2_fh_len = fanotify_encode_fh_len(dir2); unsigned int child_fh_len = fanotify_encode_fh_len(child); - unsigned int size; - - size = sizeof(*fne) + FANOTIFY_FH_HDR_LEN + dir_fh_len; + unsigned long name_len = name ? name->len : 0; + unsigned long name2_len = name2 ? name2->len : 0; + unsigned int len, size; + + /* Reserve terminating null byte even for empty name */ + size = sizeof(*fne) + name_len + name2_len + 2; + if (dir_fh_len) + size += FANOTIFY_FH_HDR_LEN + dir_fh_len; + if (dir2_fh_len) + size += FANOTIFY_FH_HDR_LEN + dir2_fh_len; if (child_fh_len) size += FANOTIFY_FH_HDR_LEN + child_fh_len; - if (name) - size += name->len + 1; fne = kmalloc(size, gfp); if (!fne) return NULL; @@ -542,40 +627,97 @@ static struct fanotify_event *fanotify_alloc_name_event(struct inode *id, *hash ^= fanotify_hash_fsid(fsid); info = &fne->info; fanotify_info_init(info); - dfh = fanotify_info_dir_fh(info); - info->dir_fh_totlen = fanotify_encode_fh(dfh, id, dir_fh_len, hash, 0); + if (dir_fh_len) { + dfh = fanotify_info_dir_fh(info); + len = fanotify_encode_fh(dfh, dir, dir_fh_len, hash, 0); + fanotify_info_set_dir_fh(info, len); + } + if (dir2_fh_len) { + dfh = fanotify_info_dir2_fh(info); + len = fanotify_encode_fh(dfh, dir2, dir2_fh_len, hash, 0); + fanotify_info_set_dir2_fh(info, len); + } if (child_fh_len) { ffh = fanotify_info_file_fh(info); - info->file_fh_totlen = fanotify_encode_fh(ffh, child, - child_fh_len, hash, 0); + len = fanotify_encode_fh(ffh, child, child_fh_len, hash, 0); + fanotify_info_set_file_fh(info, len); } - if (name) { - long salt = name->len; - + if (name_len) { fanotify_info_copy_name(info, name); - *hash ^= full_name_hash((void *)salt, name->name, name->len); + *hash ^= full_name_hash((void *)name_len, name->name, name_len); + } + if (name2_len) { + fanotify_info_copy_name2(info, name2); + *hash ^= full_name_hash((void *)name2_len, name2->name, + name2_len); } - pr_debug("%s: ino=%lu size=%u dir_fh_len=%u child_fh_len=%u name_len=%u name='%.*s'\n", - __func__, id->i_ino, size, dir_fh_len, child_fh_len, + pr_debug("%s: size=%u dir_fh_len=%u child_fh_len=%u name_len=%u name='%.*s'\n", + __func__, size, dir_fh_len, child_fh_len, info->name_len, info->name_len, fanotify_info_name(info)); + if (dir2_fh_len) { + pr_debug("%s: dir2_fh_len=%u name2_len=%u name2='%.*s'\n", + __func__, dir2_fh_len, info->name2_len, + info->name2_len, fanotify_info_name2(info)); + } + return &fne->fae; } -static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, - u32 mask, const void *data, - int data_type, struct inode *dir, - const struct qstr *file_name, - __kernel_fsid_t *fsid) +static struct fanotify_event *fanotify_alloc_error_event( + struct fsnotify_group *group, + __kernel_fsid_t *fsid, + const void *data, int data_type, + unsigned int *hash) +{ + struct fs_error_report *report = + fsnotify_data_error_report(data, data_type); + struct inode *inode; + struct fanotify_error_event *fee; + int fh_len; + + if (WARN_ON_ONCE(!report)) + return NULL; + + fee = mempool_alloc(&group->fanotify_data.error_events_pool, GFP_NOFS); + if (!fee) + return NULL; + + fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR; + fee->error = report->error; + fee->err_count = 1; + fee->fsid = *fsid; + + inode = report->inode; + fh_len = fanotify_encode_fh_len(inode); + + /* Bad fh_len. Fallback to using an invalid fh. Should never happen. */ + if (!fh_len && inode) + inode = NULL; + + fanotify_encode_fh(&fee->object_fh, inode, fh_len, NULL, 0); + + *hash ^= fanotify_hash_fsid(fsid); + + return &fee->fae; +} + +static struct fanotify_event *fanotify_alloc_event( + struct fsnotify_group *group, + u32 mask, const void *data, int data_type, + struct inode *dir, const struct qstr *file_name, + __kernel_fsid_t *fsid, u32 match_mask) { struct fanotify_event *event = NULL; gfp_t gfp = GFP_KERNEL_ACCOUNT; - struct inode *id = fanotify_fid_inode(mask, data, data_type, dir); + unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); + struct inode *id = fanotify_fid_inode(mask, data, data_type, dir, + fid_mode); struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir); const struct path *path = fsnotify_data_path(data, data_type); - unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); struct mem_cgroup *old_memcg; + struct dentry *moved = NULL; struct inode *child = NULL; bool name_event = false; unsigned int hash = 0; @@ -584,11 +726,10 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) { /* - * With both flags FAN_REPORT_DIR_FID and FAN_REPORT_FID, we - * report the child fid for events reported on a non-dir child + * For certain events and group flags, report the child fid * in addition to reporting the parent fid and maybe child name. */ - if ((fid_mode & FAN_REPORT_FID) && id != dirid && !ondir) + if (fanotify_report_child_fid(fid_mode, mask) && id != dirid) child = id; id = dirid; @@ -612,6 +753,38 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, } else if ((mask & ALL_FSNOTIFY_DIRENT_EVENTS) || !ondir) { name_event = true; } + + /* + * In the special case of FAN_RENAME event, use the match_mask + * to determine if we need to report only the old parent+name, + * only the new parent+name or both. + * 'dirid' and 'file_name' are the old parent+name and + * 'moved' has the new parent+name. + */ + if (mask & FAN_RENAME) { + bool report_old, report_new; + + if (WARN_ON_ONCE(!match_mask)) + return NULL; + + /* Report both old and new parent+name if sb watching */ + report_old = report_new = + match_mask & (1U << FSNOTIFY_ITER_TYPE_SB); + report_old |= + match_mask & (1U << FSNOTIFY_ITER_TYPE_INODE); + report_new |= + match_mask & (1U << FSNOTIFY_ITER_TYPE_INODE2); + + if (!report_old) { + /* Do not report old parent+name */ + dirid = NULL; + file_name = NULL; + } + if (report_new) { + /* Report new parent+name */ + moved = fsnotify_data_dentry(data, data_type); + } + } } /* @@ -630,9 +803,12 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, if (fanotify_is_perm_event(mask)) { event = fanotify_alloc_perm_event(path, gfp); - } else if (name_event && (file_name || child)) { - event = fanotify_alloc_name_event(id, fsid, file_name, child, - &hash, gfp); + } else if (fanotify_is_error_event(mask)) { + event = fanotify_alloc_error_event(group, fsid, data, + data_type, &hash); + } else if (name_event && (file_name || moved || child)) { + event = fanotify_alloc_name_event(dirid, fsid, file_name, child, + moved, &hash, gfp); } else if (fid_mode) { event = fanotify_alloc_fid_event(id, fsid, &hash, gfp); } else { @@ -664,16 +840,14 @@ out: */ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info) { + struct fsnotify_mark *mark; int type; __kernel_fsid_t fsid = {}; - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_mark_type(iter_info, mark, type) { struct fsnotify_mark_connector *conn; - if (!fsnotify_iter_should_report_type(iter_info, type)) - continue; - - conn = READ_ONCE(iter_info->marks[type]->connector); + conn = READ_ONCE(mark->connector); /* Mark is just getting destroyed or created? */ if (!conn) continue; @@ -702,6 +876,9 @@ static void fanotify_insert_event(struct fsnotify_group *group, assert_spin_locked(&group->notification_lock); + if (!fanotify_is_hashed_event(event->mask)) + return; + pr_debug("%s: group=%p event=%p bucket=%u\n", __func__, group, event, bucket); @@ -718,6 +895,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, struct fanotify_event *event; struct fsnotify_event *fsn_event; __kernel_fsid_t fsid = {}; + u32 match_mask = 0; BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS); BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY); @@ -738,15 +916,18 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR); BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC); BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); + BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); + BUILD_BUG_ON(FAN_RENAME != FS_RENAME); - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21); - mask = fanotify_group_event_mask(group, iter_info, mask, data, - data_type, dir); + mask = fanotify_group_event_mask(group, iter_info, &match_mask, + mask, data, data_type, dir); if (!mask) return 0; - pr_debug("%s: group=%p mask=%x\n", __func__, group, mask); + pr_debug("%s: group=%p mask=%x report_mask=%x\n", __func__, + group, mask, match_mask); if (fanotify_is_perm_event(mask)) { /* @@ -765,7 +946,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, } event = fanotify_alloc_event(group, mask, data, data_type, dir, - file_name, &fsid); + file_name, &fsid, match_mask); ret = -ENOMEM; if (unlikely(!event)) { /* @@ -778,9 +959,8 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, } fsn_event = &event->fse; - ret = fsnotify_add_event(group, fsn_event, fanotify_merge, - fanotify_is_hashed_event(mask) ? - fanotify_insert_event : NULL); + ret = fsnotify_insert_event(group, fsn_event, fanotify_merge, + fanotify_insert_event); if (ret) { /* Permission events shouldn't be merged */ BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS); @@ -805,6 +985,9 @@ static void fanotify_free_group_priv(struct fsnotify_group *group) if (group->fanotify_data.ucounts) dec_ucount(group->fanotify_data.ucounts, UCOUNT_FANOTIFY_GROUPS); + + if (mempool_initialized(&group->fanotify_data.error_events_pool)) + mempool_exit(&group->fanotify_data.error_events_pool); } static void fanotify_free_path_event(struct fanotify_event *event) @@ -833,7 +1016,16 @@ static void fanotify_free_name_event(struct fanotify_event *event) kfree(FANOTIFY_NE(event)); } -static void fanotify_free_event(struct fsnotify_event *fsn_event) +static void fanotify_free_error_event(struct fsnotify_group *group, + struct fanotify_event *event) +{ + struct fanotify_error_event *fee = FANOTIFY_EE(event); + + mempool_free(fee, &group->fanotify_data.error_events_pool); +} + +static void fanotify_free_event(struct fsnotify_group *group, + struct fsnotify_event *fsn_event) { struct fanotify_event *event; @@ -855,6 +1047,9 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event) case FANOTIFY_EVENT_TYPE_OVERFLOW: kfree(event); break; + case FANOTIFY_EVENT_TYPE_FS_ERROR: + fanotify_free_error_event(group, event); + break; default: WARN_ON_ONCE(1); } diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 4a5e555dc3d2..57f51a9a3015 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -40,15 +40,45 @@ struct fanotify_fh { struct fanotify_info { /* size of dir_fh/file_fh including fanotify_fh hdr size */ u8 dir_fh_totlen; + u8 dir2_fh_totlen; u8 file_fh_totlen; u8 name_len; - u8 pad; + u8 name2_len; + u8 pad[3]; unsigned char buf[]; /* * (struct fanotify_fh) dir_fh starts at buf[0] - * (optional) file_fh starts at buf[dir_fh_totlen] - * name starts at buf[dir_fh_totlen + file_fh_totlen] + * (optional) dir2_fh starts at buf[dir_fh_totlen] + * (optional) file_fh starts at buf[dir_fh_totlen + dir2_fh_totlen] + * name starts at buf[dir_fh_totlen + dir2_fh_totlen + file_fh_totlen] + * ... */ +#define FANOTIFY_DIR_FH_SIZE(info) ((info)->dir_fh_totlen) +#define FANOTIFY_DIR2_FH_SIZE(info) ((info)->dir2_fh_totlen) +#define FANOTIFY_FILE_FH_SIZE(info) ((info)->file_fh_totlen) +#define FANOTIFY_NAME_SIZE(info) ((info)->name_len + 1) +#define FANOTIFY_NAME2_SIZE(info) ((info)->name2_len + 1) + +#define FANOTIFY_DIR_FH_OFFSET(info) 0 +#define FANOTIFY_DIR2_FH_OFFSET(info) \ + (FANOTIFY_DIR_FH_OFFSET(info) + FANOTIFY_DIR_FH_SIZE(info)) +#define FANOTIFY_FILE_FH_OFFSET(info) \ + (FANOTIFY_DIR2_FH_OFFSET(info) + FANOTIFY_DIR2_FH_SIZE(info)) +#define FANOTIFY_NAME_OFFSET(info) \ + (FANOTIFY_FILE_FH_OFFSET(info) + FANOTIFY_FILE_FH_SIZE(info)) +#define FANOTIFY_NAME2_OFFSET(info) \ + (FANOTIFY_NAME_OFFSET(info) + FANOTIFY_NAME_SIZE(info)) + +#define FANOTIFY_DIR_FH_BUF(info) \ + ((info)->buf + FANOTIFY_DIR_FH_OFFSET(info)) +#define FANOTIFY_DIR2_FH_BUF(info) \ + ((info)->buf + FANOTIFY_DIR2_FH_OFFSET(info)) +#define FANOTIFY_FILE_FH_BUF(info) \ + ((info)->buf + FANOTIFY_FILE_FH_OFFSET(info)) +#define FANOTIFY_NAME_BUF(info) \ + ((info)->buf + FANOTIFY_NAME_OFFSET(info)) +#define FANOTIFY_NAME2_BUF(info) \ + ((info)->buf + FANOTIFY_NAME2_OFFSET(info)) } __aligned(4); static inline bool fanotify_fh_has_ext_buf(struct fanotify_fh *fh) @@ -87,7 +117,21 @@ static inline struct fanotify_fh *fanotify_info_dir_fh(struct fanotify_info *inf { BUILD_BUG_ON(offsetof(struct fanotify_info, buf) % 4); - return (struct fanotify_fh *)info->buf; + return (struct fanotify_fh *)FANOTIFY_DIR_FH_BUF(info); +} + +static inline int fanotify_info_dir2_fh_len(struct fanotify_info *info) +{ + if (!info->dir2_fh_totlen || + WARN_ON_ONCE(info->dir2_fh_totlen < FANOTIFY_FH_HDR_LEN)) + return 0; + + return info->dir2_fh_totlen - FANOTIFY_FH_HDR_LEN; +} + +static inline struct fanotify_fh *fanotify_info_dir2_fh(struct fanotify_info *info) +{ + return (struct fanotify_fh *)FANOTIFY_DIR2_FH_BUF(info); } static inline int fanotify_info_file_fh_len(struct fanotify_info *info) @@ -101,32 +145,90 @@ static inline int fanotify_info_file_fh_len(struct fanotify_info *info) static inline struct fanotify_fh *fanotify_info_file_fh(struct fanotify_info *info) { - return (struct fanotify_fh *)(info->buf + info->dir_fh_totlen); + return (struct fanotify_fh *)FANOTIFY_FILE_FH_BUF(info); +} + +static inline char *fanotify_info_name(struct fanotify_info *info) +{ + if (!info->name_len) + return NULL; + + return FANOTIFY_NAME_BUF(info); } -static inline const char *fanotify_info_name(struct fanotify_info *info) +static inline char *fanotify_info_name2(struct fanotify_info *info) { - return info->buf + info->dir_fh_totlen + info->file_fh_totlen; + if (!info->name2_len) + return NULL; + + return FANOTIFY_NAME2_BUF(info); } static inline void fanotify_info_init(struct fanotify_info *info) { + BUILD_BUG_ON(FANOTIFY_FH_HDR_LEN + MAX_HANDLE_SZ > U8_MAX); + BUILD_BUG_ON(NAME_MAX > U8_MAX); + info->dir_fh_totlen = 0; + info->dir2_fh_totlen = 0; info->file_fh_totlen = 0; info->name_len = 0; + info->name2_len = 0; +} + +/* These set/copy helpers MUST be called by order */ +static inline void fanotify_info_set_dir_fh(struct fanotify_info *info, + unsigned int totlen) +{ + if (WARN_ON_ONCE(info->dir2_fh_totlen > 0) || + WARN_ON_ONCE(info->file_fh_totlen > 0) || + WARN_ON_ONCE(info->name_len > 0) || + WARN_ON_ONCE(info->name2_len > 0)) + return; + + info->dir_fh_totlen = totlen; +} + +static inline void fanotify_info_set_dir2_fh(struct fanotify_info *info, + unsigned int totlen) +{ + if (WARN_ON_ONCE(info->file_fh_totlen > 0) || + WARN_ON_ONCE(info->name_len > 0) || + WARN_ON_ONCE(info->name2_len > 0)) + return; + + info->dir2_fh_totlen = totlen; } -static inline unsigned int fanotify_info_len(struct fanotify_info *info) +static inline void fanotify_info_set_file_fh(struct fanotify_info *info, + unsigned int totlen) { - return info->dir_fh_totlen + info->file_fh_totlen + info->name_len; + if (WARN_ON_ONCE(info->name_len > 0) || + WARN_ON_ONCE(info->name2_len > 0)) + return; + + info->file_fh_totlen = totlen; } static inline void fanotify_info_copy_name(struct fanotify_info *info, const struct qstr *name) { + if (WARN_ON_ONCE(name->len > NAME_MAX) || + WARN_ON_ONCE(info->name2_len > 0)) + return; + info->name_len = name->len; - strcpy(info->buf + info->dir_fh_totlen + info->file_fh_totlen, - name->name); + strcpy(fanotify_info_name(info), name->name); +} + +static inline void fanotify_info_copy_name2(struct fanotify_info *info, + const struct qstr *name) +{ + if (WARN_ON_ONCE(name->len > NAME_MAX)) + return; + + info->name2_len = name->len; + strcpy(fanotify_info_name2(info), name->name); } /* @@ -141,6 +243,7 @@ enum fanotify_event_type { FANOTIFY_EVENT_TYPE_PATH, FANOTIFY_EVENT_TYPE_PATH_PERM, FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */ + FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */ __FANOTIFY_EVENT_TYPE_NUM }; @@ -170,12 +273,18 @@ static inline void fanotify_init_event(struct fanotify_event *event, event->pid = NULL; } +#define FANOTIFY_INLINE_FH(name, size) \ +struct { \ + struct fanotify_fh (name); \ + /* Space for object_fh.buf[] - access with fanotify_fh_buf() */ \ + unsigned char _inline_fh_buf[(size)]; \ +} + struct fanotify_fid_event { struct fanotify_event fae; __kernel_fsid_t fsid; - struct fanotify_fh object_fh; - /* Reserve space in object_fh.buf[] - access with fanotify_fh_buf() */ - unsigned char _inline_fh_buf[FANOTIFY_INLINE_FH_LEN]; + + FANOTIFY_INLINE_FH(object_fh, FANOTIFY_INLINE_FH_LEN); }; static inline struct fanotify_fid_event * @@ -196,12 +305,30 @@ FANOTIFY_NE(struct fanotify_event *event) return container_of(event, struct fanotify_name_event, fae); } +struct fanotify_error_event { + struct fanotify_event fae; + s32 error; /* Error reported by the Filesystem. */ + u32 err_count; /* Suppressed errors count */ + + __kernel_fsid_t fsid; /* FSID this error refers to. */ + + FANOTIFY_INLINE_FH(object_fh, MAX_HANDLE_SZ); +}; + +static inline struct fanotify_error_event * +FANOTIFY_EE(struct fanotify_event *event) +{ + return container_of(event, struct fanotify_error_event, fae); +} + static inline __kernel_fsid_t *fanotify_event_fsid(struct fanotify_event *event) { if (event->type == FANOTIFY_EVENT_TYPE_FID) return &FANOTIFY_FE(event)->fsid; else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME) return &FANOTIFY_NE(event)->fsid; + else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR) + return &FANOTIFY_EE(event)->fsid; else return NULL; } @@ -213,6 +340,8 @@ static inline struct fanotify_fh *fanotify_event_object_fh( return &FANOTIFY_FE(event)->object_fh; else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME) return fanotify_info_file_fh(&FANOTIFY_NE(event)->info); + else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR) + return &FANOTIFY_EE(event)->object_fh; else return NULL; } @@ -244,6 +373,37 @@ static inline int fanotify_event_dir_fh_len(struct fanotify_event *event) return info ? fanotify_info_dir_fh_len(info) : 0; } +static inline int fanotify_event_dir2_fh_len(struct fanotify_event *event) +{ + struct fanotify_info *info = fanotify_event_info(event); + + return info ? fanotify_info_dir2_fh_len(info) : 0; +} + +static inline bool fanotify_event_has_object_fh(struct fanotify_event *event) +{ + /* For error events, even zeroed fh are reported. */ + if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR) + return true; + return fanotify_event_object_fh_len(event) > 0; +} + +static inline bool fanotify_event_has_dir_fh(struct fanotify_event *event) +{ + return fanotify_event_dir_fh_len(event) > 0; +} + +static inline bool fanotify_event_has_dir2_fh(struct fanotify_event *event) +{ + return fanotify_event_dir2_fh_len(event) > 0; +} + +static inline bool fanotify_event_has_any_dir_fh(struct fanotify_event *event) +{ + return fanotify_event_has_dir_fh(event) || + fanotify_event_has_dir2_fh(event); +} + struct fanotify_path_event { struct fanotify_event fae; struct path path; @@ -287,13 +447,12 @@ static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse) return container_of(fse, struct fanotify_event, fse); } -static inline bool fanotify_event_has_path(struct fanotify_event *event) +static inline bool fanotify_is_error_event(u32 mask) { - return event->type == FANOTIFY_EVENT_TYPE_PATH || - event->type == FANOTIFY_EVENT_TYPE_PATH_PERM; + return mask & FAN_FS_ERROR; } -static inline struct path *fanotify_event_path(struct fanotify_event *event) +static inline const struct path *fanotify_event_path(struct fanotify_event *event) { if (event->type == FANOTIFY_EVENT_TYPE_PATH) return &FANOTIFY_PE(event)->path; @@ -315,7 +474,8 @@ static inline struct path *fanotify_event_path(struct fanotify_event *event) */ static inline bool fanotify_is_hashed_event(u32 mask) { - return !fanotify_is_perm_event(mask) && !(mask & FS_Q_OVERFLOW); + return !(fanotify_is_perm_event(mask) || + fsnotify_is_overflow_event(mask)); } static inline unsigned int fanotify_event_hash_bucket( @@ -324,3 +484,17 @@ static inline unsigned int fanotify_event_hash_bucket( { return event->hash & FANOTIFY_HTABLE_MASK; } + +static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark) +{ + unsigned int mflags = 0; + + if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY) + mflags |= FAN_MARK_IGNORED_SURV_MODIFY; + if (mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF) + mflags |= FAN_MARK_EVICTABLE; + if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) + mflags |= FAN_MARK_IGNORE; + + return mflags; +} diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 0e2a0eb7cb9e..d93418f21386 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -30,6 +30,7 @@ #define FANOTIFY_DEFAULT_MAX_EVENTS 16384 #define FANOTIFY_OLD_DEFAULT_MAX_MARKS 8192 #define FANOTIFY_DEFAULT_MAX_GROUPS 128 +#define FANOTIFY_DEFAULT_FEE_POOL_SIZE 32 /* * Legacy fanotify marks limits (8192) is per group and we introduced a tunable @@ -114,6 +115,8 @@ struct kmem_cache *fanotify_perm_event_cachep __read_mostly; (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle)) #define FANOTIFY_PIDFD_INFO_HDR_LEN \ sizeof(struct fanotify_event_info_pidfd) +#define FANOTIFY_ERROR_INFO_LEN \ + (sizeof(struct fanotify_event_info_error)) static int fanotify_fid_info_len(int fh_len, int name_len) { @@ -126,17 +129,42 @@ static int fanotify_fid_info_len(int fh_len, int name_len) FANOTIFY_EVENT_ALIGN); } -static int fanotify_event_info_len(unsigned int info_mode, - struct fanotify_event *event) +/* FAN_RENAME may have one or two dir+name info records */ +static int fanotify_dir_name_info_len(struct fanotify_event *event) { struct fanotify_info *info = fanotify_event_info(event); int dir_fh_len = fanotify_event_dir_fh_len(event); - int fh_len = fanotify_event_object_fh_len(event); + int dir2_fh_len = fanotify_event_dir2_fh_len(event); int info_len = 0; + + if (dir_fh_len) + info_len += fanotify_fid_info_len(dir_fh_len, + info->name_len); + if (dir2_fh_len) + info_len += fanotify_fid_info_len(dir2_fh_len, + info->name2_len); + + return info_len; +} + +static size_t fanotify_event_len(unsigned int info_mode, + struct fanotify_event *event) +{ + size_t event_len = FAN_EVENT_METADATA_LEN; + struct fanotify_info *info; + int fh_len; int dot_len = 0; - if (dir_fh_len) { - info_len += fanotify_fid_info_len(dir_fh_len, info->name_len); + if (!info_mode) + return event_len; + + if (fanotify_is_error_event(event->mask)) + event_len += FANOTIFY_ERROR_INFO_LEN; + + info = fanotify_event_info(event); + + if (fanotify_event_has_any_dir_fh(event)) { + event_len += fanotify_dir_name_info_len(event); } else if ((info_mode & FAN_REPORT_NAME) && (event->mask & FAN_ONDIR)) { /* @@ -147,12 +175,14 @@ static int fanotify_event_info_len(unsigned int info_mode, } if (info_mode & FAN_REPORT_PIDFD) - info_len += FANOTIFY_PIDFD_INFO_HDR_LEN; + event_len += FANOTIFY_PIDFD_INFO_HDR_LEN; - if (fh_len) - info_len += fanotify_fid_info_len(fh_len, dot_len); + if (fanotify_event_has_object_fh(event)) { + fh_len = fanotify_event_object_fh_len(event); + event_len += fanotify_fid_info_len(fh_len, dot_len); + } - return info_len; + return event_len; } /* @@ -181,7 +211,7 @@ static void fanotify_unhash_event(struct fsnotify_group *group, static struct fanotify_event *get_one_event(struct fsnotify_group *group, size_t count) { - size_t event_size = FAN_EVENT_METADATA_LEN; + size_t event_size; struct fanotify_event *event = NULL; struct fsnotify_event *fsn_event; unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES); @@ -194,8 +224,7 @@ static struct fanotify_event *get_one_event(struct fsnotify_group *group, goto out; event = FANOTIFY_E(fsn_event); - if (info_mode) - event_size += fanotify_event_info_len(info_mode, event); + event_size = fanotify_event_len(info_mode, event); if (event_size > count) { event = ERR_PTR(-EINVAL); @@ -216,7 +245,7 @@ out: return event; } -static int create_fd(struct fsnotify_group *group, struct path *path, +static int create_fd(struct fsnotify_group *group, const struct path *path, struct file **file) { int client_fd; @@ -231,7 +260,7 @@ static int create_fd(struct fsnotify_group *group, struct path *path, * originally opened O_WRONLY. */ new_file = dentry_open(path, - group->fanotify_data.f_flags | FMODE_NONOTIFY, + group->fanotify_data.f_flags | __FMODE_NONOTIFY, current_cred()); if (IS_ERR(new_file)) { /* @@ -316,6 +345,27 @@ static int process_access_response(struct fsnotify_group *group, return -ENOENT; } +static size_t copy_error_info_to_user(struct fanotify_event *event, + char __user *buf, int count) +{ + struct fanotify_event_info_error info = { }; + struct fanotify_error_event *fee = FANOTIFY_EE(event); + + info.hdr.info_type = FAN_EVENT_INFO_TYPE_ERROR; + info.hdr.len = FANOTIFY_ERROR_INFO_LEN; + + if (WARN_ON(count < info.hdr.len)) + return -EFAULT; + + info.error = fee->error; + info.error_count = fee->err_count; + + if (copy_to_user(buf, &info, sizeof(info))) + return -EFAULT; + + return info.hdr.len; +} + static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, int info_type, const char *name, size_t name_len, @@ -331,9 +381,6 @@ static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, pr_debug("%s: fh_len=%zu name_len=%zu, info_len=%zu, count=%zu\n", __func__, fh_len, name_len, info_len, count); - if (!fh_len) - return 0; - if (WARN_ON_ONCE(len < sizeof(info) || len > count)) return -EFAULT; @@ -348,6 +395,8 @@ static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, return -EFAULT; break; case FAN_EVENT_INFO_TYPE_DFID_NAME: + case FAN_EVENT_INFO_TYPE_OLD_DFID_NAME: + case FAN_EVENT_INFO_TYPE_NEW_DFID_NAME: if (WARN_ON_ONCE(!name || !name_len)) return -EFAULT; break; @@ -368,6 +417,11 @@ static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, handle.handle_type = fh->type; handle.handle_bytes = fh_len; + + /* Mangle handle_type for bad file_handle */ + if (!fh_len) + handle.handle_type = FILEID_INVALID; + if (copy_to_user(buf, &handle, sizeof(handle))) return -EFAULT; @@ -442,11 +496,19 @@ static int copy_info_records_to_user(struct fanotify_event *event, unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD; /* - * Event info records order is as follows: dir fid + name, child fid. + * Event info records order is as follows: + * 1. dir fid + name + * 2. (optional) new dir fid + new name + * 3. (optional) child fid */ - if (fanotify_event_dir_fh_len(event)) { + if (fanotify_event_has_dir_fh(event)) { info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME : FAN_EVENT_INFO_TYPE_DFID; + + /* FAN_RENAME uses special info types */ + if (event->mask & FAN_RENAME) + info_type = FAN_EVENT_INFO_TYPE_OLD_DFID_NAME; + ret = copy_fid_info_to_user(fanotify_event_fsid(event), fanotify_info_dir_fh(info), info_type, @@ -460,7 +522,23 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } - if (fanotify_event_object_fh_len(event)) { + /* New dir fid+name may be reported in addition to old dir fid+name */ + if (fanotify_event_has_dir2_fh(event)) { + info_type = FAN_EVENT_INFO_TYPE_NEW_DFID_NAME; + ret = copy_fid_info_to_user(fanotify_event_fsid(event), + fanotify_info_dir2_fh(info), + info_type, + fanotify_info_name2(info), + info->name2_len, buf, count); + if (ret < 0) + return ret; + + buf += ret; + count -= ret; + total_bytes += ret; + } + + if (fanotify_event_has_object_fh(event)) { const char *dot = NULL; int dot_len = 0; @@ -520,6 +598,15 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } + if (fanotify_is_error_event(event->mask)) { + ret = copy_error_info_to_user(event, buf, count); + if (ret < 0) + return ret; + buf += ret; + count -= ret; + total_bytes += ret; + } + return total_bytes; } @@ -528,7 +615,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, char __user *buf, size_t count) { struct fanotify_event_metadata metadata; - struct path *path = fanotify_event_path(event); + const struct path *path = fanotify_event_path(event); struct fanotify_info *info = fanotify_event_info(event); unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES); unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD; @@ -537,8 +624,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - metadata.event_len = FAN_EVENT_METADATA_LEN + - fanotify_event_info_len(info_mode, event); + metadata.event_len = fanotify_event_len(info_mode, event); metadata.metadata_len = FAN_EVENT_METADATA_LEN; metadata.vers = FANOTIFY_METADATA_VERSION; metadata.reserved = 0; @@ -913,27 +999,28 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark, __u32 mask, unsigned int flags, __u32 umask, int *destroy) { - __u32 oldmask = 0; + __u32 oldmask, newmask; /* umask bits cannot be removed by user */ mask &= ~umask; spin_lock(&fsn_mark->lock); - if (!(flags & FAN_MARK_IGNORED_MASK)) { - oldmask = fsn_mark->mask; + oldmask = fsnotify_calc_mask(fsn_mark); + if (!(flags & FANOTIFY_MARK_IGNORE_BITS)) { fsn_mark->mask &= ~mask; } else { - fsn_mark->ignored_mask &= ~mask; + fsn_mark->ignore_mask &= ~mask; } + newmask = fsnotify_calc_mask(fsn_mark); /* * We need to keep the mark around even if remaining mask cannot * result in any events (e.g. mask == FAN_ONDIR) to support incremenal * changes to the mask. * Destroy mark when only umask bits remain. */ - *destroy = !((fsn_mark->mask | fsn_mark->ignored_mask) & ~umask); + *destroy = !((fsn_mark->mask | fsn_mark->ignore_mask) & ~umask); spin_unlock(&fsn_mark->lock); - return mask & oldmask; + return oldmask & ~newmask; } static int fanotify_remove_mark(struct fsnotify_group *group, @@ -944,10 +1031,10 @@ static int fanotify_remove_mark(struct fsnotify_group *group, __u32 removed; int destroy_mark; - mutex_lock(&group->mark_mutex); + fsnotify_group_lock(group); fsn_mark = fsnotify_find_mark(connp, group); if (!fsn_mark) { - mutex_unlock(&group->mark_mutex); + fsnotify_group_unlock(group); return -ENOENT; } @@ -957,7 +1044,7 @@ static int fanotify_remove_mark(struct fsnotify_group *group, fsnotify_recalc_mask(fsn_mark->connector); if (destroy_mark) fsnotify_detach_mark(fsn_mark); - mutex_unlock(&group->mark_mutex); + fsnotify_group_unlock(group); if (destroy_mark) fsnotify_free_mark(fsn_mark); @@ -990,29 +1077,72 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group, flags, umask); } -static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, - __u32 mask, - unsigned int flags) +static bool fanotify_mark_update_flags(struct fsnotify_mark *fsn_mark, + unsigned int fan_flags) { - __u32 oldmask = -1; + bool want_iref = !(fan_flags & FAN_MARK_EVICTABLE); + unsigned int ignore = fan_flags & FANOTIFY_MARK_IGNORE_BITS; + bool recalc = false; + + /* + * When using FAN_MARK_IGNORE for the first time, mark starts using + * independent event flags in ignore mask. After that, trying to + * update the ignore mask with the old FAN_MARK_IGNORED_MASK API + * will result in EEXIST error. + */ + if (ignore == FAN_MARK_IGNORE) + fsn_mark->flags |= FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS; + + /* + * Setting FAN_MARK_IGNORED_SURV_MODIFY for the first time may lead to + * the removal of the FS_MODIFY bit in calculated mask if it was set + * because of an ignore mask that is now going to survive FS_MODIFY. + */ + if (ignore && (fan_flags & FAN_MARK_IGNORED_SURV_MODIFY) && + !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) { + fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY; + if (!(fsn_mark->mask & FS_MODIFY)) + recalc = true; + } + + if (fsn_mark->connector->type != FSNOTIFY_OBJ_TYPE_INODE || + want_iref == !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) + return recalc; + + /* + * NO_IREF may be removed from a mark, but not added. + * When removed, fsnotify_recalc_mask() will take the inode ref. + */ + WARN_ON_ONCE(!want_iref); + fsn_mark->flags &= ~FSNOTIFY_MARK_FLAG_NO_IREF; + + return true; +} + +static bool fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, + __u32 mask, unsigned int fan_flags) +{ + bool recalc; spin_lock(&fsn_mark->lock); - if (!(flags & FAN_MARK_IGNORED_MASK)) { - oldmask = fsn_mark->mask; + if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS)) fsn_mark->mask |= mask; - } else { - fsn_mark->ignored_mask |= mask; - if (flags & FAN_MARK_IGNORED_SURV_MODIFY) - fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY; - } + else + fsn_mark->ignore_mask |= mask; + + recalc = fsnotify_calc_mask(fsn_mark) & + ~fsnotify_conn_mask(fsn_mark->connector); + + recalc |= fanotify_mark_update_flags(fsn_mark, fan_flags); spin_unlock(&fsn_mark->lock); - return mask & ~oldmask; + return recalc; } static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group, fsnotify_connp_t *connp, - unsigned int type, + unsigned int obj_type, + unsigned int fan_flags, __kernel_fsid_t *fsid) { struct ucounts *ucounts = group->fanotify_data.ucounts; @@ -1035,7 +1165,10 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group, } fsnotify_init_mark(mark, group); - ret = fsnotify_add_mark_locked(mark, connp, type, 0, fsid); + if (fan_flags & FAN_MARK_EVICTABLE) + mark->flags |= FSNOTIFY_MARK_FLAG_NO_IREF; + + ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0, fsid); if (ret) { fsnotify_put_mark(mark); goto out_dec_ucounts; @@ -1049,31 +1182,94 @@ out_dec_ucounts: return ERR_PTR(ret); } +static int fanotify_group_init_error_pool(struct fsnotify_group *group) +{ + if (mempool_initialized(&group->fanotify_data.error_events_pool)) + return 0; + + return mempool_init_kmalloc_pool(&group->fanotify_data.error_events_pool, + FANOTIFY_DEFAULT_FEE_POOL_SIZE, + sizeof(struct fanotify_error_event)); +} + +static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark, + unsigned int fan_flags) +{ + /* + * Non evictable mark cannot be downgraded to evictable mark. + */ + if (fan_flags & FAN_MARK_EVICTABLE && + !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) + return -EEXIST; + + /* + * New ignore mask semantics cannot be downgraded to old semantics. + */ + if (fan_flags & FAN_MARK_IGNORED_MASK && + fsn_mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) + return -EEXIST; + + /* + * An ignore mask that survives modify could never be downgraded to not + * survive modify. With new FAN_MARK_IGNORE semantics we make that rule + * explicit and return an error when trying to update the ignore mask + * without the original FAN_MARK_IGNORED_SURV_MODIFY value. + */ + if (fan_flags & FAN_MARK_IGNORE && + !(fan_flags & FAN_MARK_IGNORED_SURV_MODIFY) && + fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY) + return -EEXIST; + + return 0; +} static int fanotify_add_mark(struct fsnotify_group *group, - fsnotify_connp_t *connp, unsigned int type, - __u32 mask, unsigned int flags, + fsnotify_connp_t *connp, unsigned int obj_type, + __u32 mask, unsigned int fan_flags, __kernel_fsid_t *fsid) { struct fsnotify_mark *fsn_mark; - __u32 added; + bool recalc; + int ret = 0; - mutex_lock(&group->mark_mutex); + fsnotify_group_lock(group); fsn_mark = fsnotify_find_mark(connp, group); if (!fsn_mark) { - fsn_mark = fanotify_add_new_mark(group, connp, type, fsid); + fsn_mark = fanotify_add_new_mark(group, connp, obj_type, + fan_flags, fsid); if (IS_ERR(fsn_mark)) { - mutex_unlock(&group->mark_mutex); + fsnotify_group_unlock(group); return PTR_ERR(fsn_mark); } } - added = fanotify_mark_add_to_mask(fsn_mark, mask, flags); - if (added & ~fsnotify_conn_mask(fsn_mark->connector)) + + /* + * Check if requested mark flags conflict with an existing mark flags. + */ + ret = fanotify_may_update_existing_mark(fsn_mark, fan_flags); + if (ret) + goto out; + + /* + * Error events are pre-allocated per group, only if strictly + * needed (i.e. FAN_FS_ERROR was requested). + */ + if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS) && + (mask & FAN_FS_ERROR)) { + ret = fanotify_group_init_error_pool(group); + if (ret) + goto out; + } + + recalc = fanotify_mark_add_to_mask(fsn_mark, mask, fan_flags); + if (recalc) fsnotify_recalc_mask(fsn_mark->connector); - mutex_unlock(&group->mark_mutex); + +out: + fsnotify_group_unlock(group); fsnotify_put_mark(fsn_mark); - return 0; + return ret; } static int fanotify_add_vfsmount_mark(struct fsnotify_group *group, @@ -1100,10 +1296,10 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group, /* * If some other task has this inode open for write we should not add - * an ignored mark, unless that ignored mark is supposed to survive + * an ignore mask, unless that ignore mask is supposed to survive * modification changes anyway. */ - if ((flags & FAN_MARK_IGNORED_MASK) && + if ((flags & FANOTIFY_MARK_IGNORE_BITS) && !(flags & FAN_MARK_IGNORED_SURV_MODIFY) && inode_is_open_for_write(inode)) return 0; @@ -1207,14 +1403,24 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) if ((fid_mode & FAN_REPORT_NAME) && !(fid_mode & FAN_REPORT_DIR_FID)) return -EINVAL; - f_flags = O_RDWR | FMODE_NONOTIFY; + /* + * FAN_REPORT_TARGET_FID requires FAN_REPORT_NAME and FAN_REPORT_FID + * and is used as an indication to report both dir and child fid on all + * dirent events. + */ + if ((fid_mode & FAN_REPORT_TARGET_FID) && + (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID))) + return -EINVAL; + + f_flags = O_RDWR | __FMODE_NONOTIFY; if (flags & FAN_CLOEXEC) f_flags |= O_CLOEXEC; if (flags & FAN_NONBLOCK) f_flags |= O_NONBLOCK; /* fsnotify_alloc_group takes a ref. Dropped in fanotify_release */ - group = fsnotify_alloc_user_group(&fanotify_fsnotify_ops); + group = fsnotify_alloc_group(&fanotify_fsnotify_ops, + FSNOTIFY_GROUP_USER | FSNOTIFY_GROUP_NOFS); if (IS_ERR(group)) { return PTR_ERR(group); } @@ -1295,16 +1501,15 @@ out_destroy_group: return fd; } -/* Check if filesystem can encode a unique fid */ -static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) +static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid) { __kernel_fsid_t root_fsid; int err; /* - * Make sure path is not in filesystem with zero fsid (e.g. tmpfs). + * Make sure dentry is not of a filesystem with zero fsid (e.g. fuse). */ - err = vfs_get_fsid(path->dentry, fsid); + err = vfs_get_fsid(dentry, fsid); if (err) return err; @@ -1312,10 +1517,10 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) return -ENODEV; /* - * Make sure path is not inside a filesystem subvolume (e.g. btrfs) + * Make sure dentry is not of a filesystem subvolume (e.g. btrfs) * which uses a different fsid than sb root. */ - err = vfs_get_fsid(path->dentry->d_sb->s_root, &root_fsid); + err = vfs_get_fsid(dentry->d_sb->s_root, &root_fsid); if (err) return err; @@ -1323,6 +1528,12 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) root_fsid.val[1] != fsid->val[1]) return -EXDEV; + return 0; +} + +/* Check if filesystem can encode a unique fid */ +static int fanotify_test_fid(struct dentry *dentry) +{ /* * We need to make sure that the file system supports at least * encoding a file handle so user can use name_to_handle_at() to @@ -1330,17 +1541,22 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) * objects. However, name_to_handle_at() requires that the * filesystem also supports decoding file handles. */ - if (!path->dentry->d_sb->s_export_op || - !path->dentry->d_sb->s_export_op->fh_to_dentry) + if (!dentry->d_sb->s_export_op || + !dentry->d_sb->s_export_op->fh_to_dentry) return -EOPNOTSUPP; return 0; } -static int fanotify_events_supported(struct path *path, __u64 mask, +static int fanotify_events_supported(struct fsnotify_group *group, + const struct path *path, __u64 mask, unsigned int flags) { unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; + /* Strict validation of events in non-dir inode mask with v5.17+ APIs */ + bool strict_dir_events = FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID) || + (mask & FAN_RENAME) || + (flags & FAN_MARK_IGNORE); /* * Some filesystems such as 'proc' acquire unusual locks when opening @@ -1368,6 +1584,15 @@ static int fanotify_events_supported(struct path *path, __u64 mask, path->mnt->mnt_sb->s_flags & SB_NOUSER) return -EINVAL; + /* + * We shouldn't have allowed setting dirent events and the directory + * flags FAN_ONDIR and FAN_EVENT_ON_CHILD in mask of non-dir inode, + * but because we always allowed it, error only when using new APIs. + */ + if (strict_dir_events && mark_type == FAN_MARK_INODE && + !d_is_dir(path->dentry) && (mask & FANOTIFY_DIRONLY_EVENT_BITS)) + return -ENOTDIR; + return 0; } @@ -1382,7 +1607,8 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, __kernel_fsid_t __fsid, *fsid = NULL; u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS; unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; - bool ignored = flags & FAN_MARK_IGNORED_MASK; + unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS; + unsigned int ignore = flags & FANOTIFY_MARK_IGNORE_BITS; unsigned int obj_type, fid_mode; u32 umask = 0; int ret; @@ -1411,7 +1637,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, return -EINVAL; } - switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) { + switch (mark_cmd) { case FAN_MARK_ADD: case FAN_MARK_REMOVE: if (!mask) @@ -1431,9 +1657,19 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, if (mask & ~valid_mask) return -EINVAL; - /* Event flags (ONDIR, ON_CHILD) are meaningless in ignored mask */ - if (ignored) + + /* We don't allow FAN_MARK_IGNORE & FAN_MARK_IGNORED_MASK together */ + if (ignore == (FAN_MARK_IGNORE | FAN_MARK_IGNORED_MASK)) + return -EINVAL; + + /* + * Event flags (FAN_ONDIR, FAN_EVENT_ON_CHILD) have no effect with + * FAN_MARK_IGNORED_MASK. + */ + if (ignore == FAN_MARK_IGNORED_MASK) { mask &= ~FANOTIFY_EVENT_FLAGS; + umask = FANOTIFY_EVENT_FLAGS; + } f = fdget(fanotify_fd); if (unlikely(!f.file)) @@ -1465,19 +1701,39 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, group->priority == FS_PRIO_0) goto fput_and_out; + if (mask & FAN_FS_ERROR && + mark_type != FAN_MARK_FILESYSTEM) + goto fput_and_out; + + /* + * Evictable is only relevant for inode marks, because only inode object + * can be evicted on memory pressure. + */ + if (flags & FAN_MARK_EVICTABLE && + mark_type != FAN_MARK_INODE) + goto fput_and_out; + /* - * Events with data type inode do not carry enough information to report - * event->fd, so we do not allow setting a mask for inode events unless - * group supports reporting fid. - * inode events are not supported on a mount mark, because they do not - * carry enough information (i.e. path) to be filtered by mount point. + * Events that do not carry enough information to report + * event->fd require a group that supports reporting fid. Those + * events are not supported on a mount mark, because they do not + * carry enough information (i.e. path) to be filtered by mount + * point. */ fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); - if (mask & FANOTIFY_INODE_EVENTS && + if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) && (!fid_mode || mark_type == FAN_MARK_MOUNT)) goto fput_and_out; - if (flags & FAN_MARK_FLUSH) { + /* + * FAN_RENAME uses special info type records to report the old and + * new parent+name. Reporting only old and new parent id is less + * useful and was not implemented. + */ + if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME)) + goto fput_and_out; + + if (mark_cmd == FAN_MARK_FLUSH) { ret = 0; if (mark_type == FAN_MARK_MOUNT) fsnotify_clear_vfsmount_marks_by_group(group); @@ -1493,14 +1749,18 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, if (ret) goto fput_and_out; - if (flags & FAN_MARK_ADD) { - ret = fanotify_events_supported(&path, mask, flags); + if (mark_cmd == FAN_MARK_ADD) { + ret = fanotify_events_supported(group, &path, mask, flags); if (ret) goto path_put_and_out; } if (fid_mode) { - ret = fanotify_test_fid(&path, &__fsid); + ret = fanotify_test_fsid(path.dentry, &__fsid); + if (ret) + goto path_put_and_out; + + ret = fanotify_test_fid(path.dentry); if (ret) goto path_put_and_out; @@ -1513,6 +1773,13 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, else mnt = path.mnt; + ret = mnt ? -EINVAL : -EISDIR; + /* FAN_MARK_IGNORE requires SURV_MODIFY for sb/mount/dir marks */ + if (mark_cmd == FAN_MARK_ADD && ignore == FAN_MARK_IGNORE && + (mnt || S_ISDIR(inode->i_mode)) && + !(flags & FAN_MARK_IGNORED_SURV_MODIFY)) + goto path_put_and_out; + /* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */ if (mnt || !S_ISDIR(inode->i_mode)) { mask &= ~FAN_EVENT_ON_CHILD; @@ -1522,12 +1789,12 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, * events with parent/name info for non-directory. */ if ((fid_mode & FAN_REPORT_DIR_FID) && - (flags & FAN_MARK_ADD) && !ignored) + (flags & FAN_MARK_ADD) && !ignore) mask |= FAN_EVENT_ON_CHILD; } /* create/update an inode mark */ - switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) { + switch (mark_cmd) { case FAN_MARK_ADD: if (mark_type == FAN_MARK_MOUNT) ret = fanotify_add_vfsmount_mark(group, mnt, mask, @@ -1604,8 +1871,8 @@ static int __init fanotify_user_setup(void) FANOTIFY_DEFAULT_MAX_USER_MARKS); BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS); - BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 11); - BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9); + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12); + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11); fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 3451708fd035..55081ae3a6ec 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -14,6 +14,7 @@ #include <linux/exportfs.h> #include "inotify/inotify.h" +#include "fanotify/fanotify.h" #include "fdinfo.h" #include "fsnotify.h" @@ -28,13 +29,13 @@ static void show_fdinfo(struct seq_file *m, struct file *f, struct fsnotify_group *group = f->private_data; struct fsnotify_mark *mark; - mutex_lock(&group->mark_mutex); + fsnotify_group_lock(group); list_for_each_entry(mark, &group->marks_list, g_list) { show(m, mark); if (seq_has_overflowed(m)) break; } - mutex_unlock(&group->mark_mutex); + fsnotify_group_unlock(group); } #if defined(CONFIG_EXPORTFS) @@ -103,19 +104,16 @@ void inotify_show_fdinfo(struct seq_file *m, struct file *f) static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) { - unsigned int mflags = 0; + unsigned int mflags = fanotify_mark_user_flags(mark); struct inode *inode; - if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY) - mflags |= FAN_MARK_IGNORED_SURV_MODIFY; - if (mark->connector->type == FSNOTIFY_OBJ_TYPE_INODE) { inode = igrab(fsnotify_conn_inode(mark->connector)); if (!inode) return; seq_printf(m, "fanotify ino:%lx sdev:%x mflags:%x mask:%x ignored_mask:%x ", inode->i_ino, inode->i_sb->s_dev, - mflags, mark->mask, mark->ignored_mask); + mflags, mark->mask, mark->ignore_mask); show_mark_fhandle(m, inode); seq_putc(m, '\n'); iput(inode); @@ -123,12 +121,12 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) struct mount *mnt = fsnotify_conn_mount(mark->connector); seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n", - mnt->mnt_id, mflags, mark->mask, mark->ignored_mask); + mnt->mnt_id, mflags, mark->mask, mark->ignore_mask); } else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_SB) { struct super_block *sb = fsnotify_conn_sb(mark->connector); seq_printf(m, "fanotify sdev:%x mflags:%x mask:%x ignored_mask:%x\n", - sb->s_dev, mflags, mark->mask, mark->ignored_mask); + sb->s_dev, mflags, mark->mask, mark->ignore_mask); } } diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 963e6ce75b96..7974e91ffe13 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -70,8 +70,7 @@ static void fsnotify_unmount_inodes(struct super_block *sb) spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); - if (iput_inode) - iput(iput_inode); + iput(iput_inode); /* for each watch, send FS_UNMOUNT and then remove it */ fsnotify_inode(inode, FS_UNMOUNT); @@ -85,8 +84,7 @@ static void fsnotify_unmount_inodes(struct super_block *sb) } spin_unlock(&sb->s_inode_list_lock); - if (iput_inode) - iput(iput_inode); + iput(iput_inode); } void fsnotify_sb_delete(struct super_block *sb) @@ -102,7 +100,7 @@ void fsnotify_sb_delete(struct super_block *sb) * Given an inode, first check if we care what happens to our children. Inotify * and dnotify both tell their parents about events. If we care about any event * on a child we run all of our children and set a dentry flag saying that the - * parent cares. Thus when an event happens on a child it can quickly tell if + * parent cares. Thus when an event happens on a child it can quickly tell * if there is a need to find a parent and send the event to the parent. */ void __fsnotify_update_child_dentry_flags(struct inode *inode) @@ -252,7 +250,10 @@ static int fsnotify_handle_inode_event(struct fsnotify_group *group, if (WARN_ON_ONCE(!ops->handle_inode_event)) return 0; - if ((inode_mark->mask & FS_EXCL_UNLINK) && + if (WARN_ON_ONCE(!inode && !dir)) + return 0; + + if ((inode_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) && path && d_unlinked(path->dentry)) return 0; @@ -276,23 +277,28 @@ static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask, WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info))) return 0; - if (parent_mark) { - /* - * parent_mark indicates that the parent inode is watching - * children and interested in this event, which is an event - * possible on child. But is *this mark* watching children and - * interested in this event? - */ - if (parent_mark->mask & FS_EVENT_ON_CHILD) { - ret = fsnotify_handle_inode_event(group, parent_mark, mask, - data, data_type, dir, name, 0); - if (ret) - return ret; - } - if (!inode_mark) + /* + * For FS_RENAME, 'dir' is old dir and 'data' is new dentry. + * The only ->handle_inode_event() backend that supports FS_RENAME is + * dnotify, where it means file was renamed within same parent. + */ + if (mask & FS_RENAME) { + struct dentry *moved = fsnotify_data_dentry(data, data_type); + + if (dir != moved->d_parent->d_inode) return 0; } + if (parent_mark) { + ret = fsnotify_handle_inode_event(group, parent_mark, mask, + data, data_type, dir, name, 0); + if (ret) + return ret; + } + + if (!inode_mark) + return 0; + if (mask & FS_EVENT_ON_CHILD) { /* * Some events can be sent on both parent dir and child marks @@ -318,42 +324,36 @@ static int send_to_group(__u32 mask, const void *data, int data_type, struct fsnotify_group *group = NULL; __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS); __u32 marks_mask = 0; - __u32 marks_ignored_mask = 0; + __u32 marks_ignore_mask = 0; + bool is_dir = mask & FS_ISDIR; struct fsnotify_mark *mark; int type; - if (WARN_ON(!iter_info->report_mask)) + if (!iter_info->report_mask) return 0; /* clear ignored on inode modification */ if (mask & FS_MODIFY) { - fsnotify_foreach_obj_type(type) { - if (!fsnotify_iter_should_report_type(iter_info, type)) - continue; - mark = iter_info->marks[type]; - if (mark && - !(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) - mark->ignored_mask = 0; + fsnotify_foreach_iter_mark_type(iter_info, mark, type) { + if (!(mark->flags & + FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) + mark->ignore_mask = 0; } } - fsnotify_foreach_obj_type(type) { - if (!fsnotify_iter_should_report_type(iter_info, type)) - continue; - mark = iter_info->marks[type]; - /* does the object mark tell us to do something? */ - if (mark) { - group = mark->group; - marks_mask |= mark->mask; - marks_ignored_mask |= mark->ignored_mask; - } + /* Are any of the group marks interested in this event? */ + fsnotify_foreach_iter_mark_type(iter_info, mark, type) { + group = mark->group; + marks_mask |= mark->mask; + marks_ignore_mask |= + fsnotify_effective_ignore_mask(mark, is_dir, type); } - pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignored_mask=%x data=%p data_type=%d dir=%p cookie=%d\n", - __func__, group, mask, marks_mask, marks_ignored_mask, + pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignore_mask=%x data=%p data_type=%d dir=%p cookie=%d\n", + __func__, group, mask, marks_mask, marks_ignore_mask, data, data_type, dir, cookie); - if (!(test_mask & marks_mask & ~marks_ignored_mask)) + if (!(test_mask & marks_mask & ~marks_ignore_mask)) return 0; if (group->ops->handle_event) { @@ -390,11 +390,11 @@ static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark) /* * iter_info is a multi head priority queue of marks. - * Pick a subset of marks from queue heads, all with the - * same group and set the report_mask for selected subset. - * Returns the report_mask of the selected subset. + * Pick a subset of marks from queue heads, all with the same group + * and set the report_mask to a subset of the selected marks. + * Returns false if there are no more groups to iterate. */ -static unsigned int fsnotify_iter_select_report_types( +static bool fsnotify_iter_select_report_types( struct fsnotify_iter_info *iter_info) { struct fsnotify_group *max_prio_group = NULL; @@ -402,7 +402,7 @@ static unsigned int fsnotify_iter_select_report_types( int type; /* Choose max prio group among groups of all queue heads */ - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && fsnotify_compare_groups(max_prio_group, mark->group) > 0) @@ -410,30 +410,49 @@ static unsigned int fsnotify_iter_select_report_types( } if (!max_prio_group) - return 0; + return false; /* Set the report mask for marks from same group as max prio group */ + iter_info->current_group = max_prio_group; iter_info->report_mask = 0; - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; - if (mark && - fsnotify_compare_groups(max_prio_group, mark->group) == 0) + if (mark && mark->group == iter_info->current_group) { + /* + * FSNOTIFY_ITER_TYPE_PARENT indicates that this inode + * is watching children and interested in this event, + * which is an event possible on child. + * But is *this mark* watching children? + */ + if (type == FSNOTIFY_ITER_TYPE_PARENT && + !(mark->mask & FS_EVENT_ON_CHILD) && + !(fsnotify_ignore_mask(mark) & FS_EVENT_ON_CHILD)) + continue; + fsnotify_iter_set_report_type(iter_info, type); + } } - return iter_info->report_mask; + return true; } /* - * Pop from iter_info multi head queue, the marks that were iterated in the + * Pop from iter_info multi head queue, the marks that belong to the group of * current iteration step. */ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) { + struct fsnotify_mark *mark; int type; - fsnotify_foreach_obj_type(type) { - if (fsnotify_iter_should_report_type(iter_info, type)) + /* + * We cannot use fsnotify_foreach_iter_mark_type() here because we + * may need to advance a mark of type X that belongs to current_group + * but was not selected for reporting. + */ + fsnotify_foreach_iter_type(type) { + mark = iter_info->marks[type]; + if (mark && mark->group == iter_info->current_group) iter_info->marks[type] = fsnotify_next_mark(iter_info->marks[type]); } @@ -455,18 +474,20 @@ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) * @file_name is relative to * @file_name: optional file name associated with event * @inode: optional inode associated with event - - * either @dir or @inode must be non-NULL. - * if both are non-NULL event may be reported to both. + * If @dir and @inode are both non-NULL, event may be + * reported to both. * @cookie: inotify rename cookie */ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, struct inode *inode, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); + struct super_block *sb = fsnotify_data_sb(data, data_type); struct fsnotify_iter_info iter_info = {}; - struct super_block *sb; struct mount *mnt = NULL; - struct inode *parent = NULL; + struct inode *inode2 = NULL; + struct dentry *moved; + int inode2_type; int ret = 0; __u32 test_mask, marks_mask; @@ -476,14 +497,20 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, if (!inode) { /* Dirent event - report on TYPE_INODE to dir */ inode = dir; + /* For FS_RENAME, inode is old_dir and inode2 is new_dir */ + if (mask & FS_RENAME) { + moved = fsnotify_data_dentry(data, data_type); + inode2 = moved->d_parent->d_inode; + inode2_type = FSNOTIFY_ITER_TYPE_INODE2; + } } else if (mask & FS_EVENT_ON_CHILD) { /* * Event on child - report on TYPE_PARENT to dir if it is * watching children and on TYPE_INODE to child. */ - parent = dir; + inode2 = dir; + inode2_type = FSNOTIFY_ITER_TYPE_PARENT; } - sb = inode->i_sb; /* * Optimization: srcu_read_lock() has a memory barrier which can @@ -495,7 +522,7 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, if (!sb->s_fsnotify_marks && (!mnt || !mnt->mnt_fsnotify_marks) && (!inode || !inode->i_fsnotify_marks) && - (!parent || !parent->i_fsnotify_marks)) + (!inode2 || !inode2->i_fsnotify_marks)) return 0; marks_mask = sb->s_fsnotify_mask; @@ -503,33 +530,35 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, marks_mask |= mnt->mnt_fsnotify_mask; if (inode) marks_mask |= inode->i_fsnotify_mask; - if (parent) - marks_mask |= parent->i_fsnotify_mask; + if (inode2) + marks_mask |= inode2->i_fsnotify_mask; /* - * if this is a modify event we may need to clear the ignored masks - * otherwise return if none of the marks care about this type of event. + * If this is a modify event we may need to clear some ignore masks. + * In that case, the object with ignore masks will have the FS_MODIFY + * event in its mask. + * Otherwise, return if none of the marks care about this type of event. */ test_mask = (mask & ALL_FSNOTIFY_EVENTS); - if (!(mask & FS_MODIFY) && !(test_mask & marks_mask)) + if (!(test_mask & marks_mask)) return 0; iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); - iter_info.marks[FSNOTIFY_OBJ_TYPE_SB] = + iter_info.marks[FSNOTIFY_ITER_TYPE_SB] = fsnotify_first_mark(&sb->s_fsnotify_marks); if (mnt) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] = + iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); } if (inode) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = + iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] = fsnotify_first_mark(&inode->i_fsnotify_marks); } - if (parent) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_PARENT] = - fsnotify_first_mark(&parent->i_fsnotify_marks); + if (inode2) { + iter_info.marks[inode2_type] = + fsnotify_first_mark(&inode2->i_fsnotify_marks); } /* @@ -558,7 +587,7 @@ static __init int fsnotify_init(void) { int ret; - BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 25); + BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 23); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h index 87d8a50ee803..fde74eb333cc 100644 --- a/fs/notify/fsnotify.h +++ b/fs/notify/fsnotify.h @@ -76,10 +76,6 @@ static inline void fsnotify_clear_marks_by_sb(struct super_block *sb) */ extern void __fsnotify_update_child_dentry_flags(struct inode *inode); -/* allocate and destroy and event holder to attach events to notification/access queues */ -extern struct fsnotify_event_holder *fsnotify_alloc_event_holder(void); -extern void fsnotify_destroy_event_holder(struct fsnotify_event_holder *holder); - extern struct kmem_cache *fsnotify_mark_connector_cachep; #endif /* __FS_NOTIFY_FSNOTIFY_H_ */ diff --git a/fs/notify/group.c b/fs/notify/group.c index 460ad19c2570..3008eb37a18d 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -58,7 +58,7 @@ void fsnotify_destroy_group(struct fsnotify_group *group) fsnotify_group_stop_queueing(group); /* Clear all marks for this group and queue them for destruction */ - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_ALL_TYPES_MASK); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_ANY); /* * Some marks can still be pinned when waiting for response from @@ -88,7 +88,7 @@ void fsnotify_destroy_group(struct fsnotify_group *group) * that deliberately ignores overflow events. */ if (group->overflow_event) - group->ops->free_event(group->overflow_event); + group->ops->free_event(group, group->overflow_event); fsnotify_put_group(group); } @@ -113,8 +113,10 @@ void fsnotify_put_group(struct fsnotify_group *group) EXPORT_SYMBOL_GPL(fsnotify_put_group); static struct fsnotify_group *__fsnotify_alloc_group( - const struct fsnotify_ops *ops, gfp_t gfp) + const struct fsnotify_ops *ops, + int flags, gfp_t gfp) { + static struct lock_class_key nofs_marks_lock; struct fsnotify_group *group; group = kzalloc(sizeof(struct fsnotify_group), gfp); @@ -134,6 +136,17 @@ static struct fsnotify_group *__fsnotify_alloc_group( INIT_LIST_HEAD(&group->marks_list); group->ops = ops; + group->flags = flags; + /* + * For most backends, eviction of inode with a mark is not expected, + * because marks hold a refcount on the inode against eviction. + * + * Use a different lockdep class for groups that support evictable + * inode marks, because with evictable marks, mark_mutex is NOT + * fs-reclaim safe - the mutex is taken when evicting inodes. + */ + if (flags & FSNOTIFY_GROUP_NOFS) + lockdep_set_class(&group->mark_mutex, &nofs_marks_lock); return group; } @@ -141,20 +154,15 @@ static struct fsnotify_group *__fsnotify_alloc_group( /* * Create a new fsnotify_group and hold a reference for the group returned. */ -struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) +struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops, + int flags) { - return __fsnotify_alloc_group(ops, GFP_KERNEL); -} -EXPORT_SYMBOL_GPL(fsnotify_alloc_group); + gfp_t gfp = (flags & FSNOTIFY_GROUP_USER) ? GFP_KERNEL_ACCOUNT : + GFP_KERNEL; -/* - * Create a new fsnotify_group and hold a reference for the group returned. - */ -struct fsnotify_group *fsnotify_alloc_user_group(const struct fsnotify_ops *ops) -{ - return __fsnotify_alloc_group(ops, GFP_KERNEL_ACCOUNT); + return __fsnotify_alloc_group(ops, flags, gfp); } -EXPORT_SYMBOL_GPL(fsnotify_alloc_user_group); +EXPORT_SYMBOL_GPL(fsnotify_alloc_group); int fsnotify_fasync(int fd, struct file *file, int on) { diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h index 8f00151eb731..7d5df7a21539 100644 --- a/fs/notify/inotify/inotify.h +++ b/fs/notify/inotify/inotify.h @@ -27,11 +27,18 @@ static inline struct inotify_event_info *INOTIFY_E(struct fsnotify_event *fse) * userspace. There is at least one bit (FS_EVENT_ON_CHILD) which is * used only internally to the kernel. */ -#define INOTIFY_USER_MASK (IN_ALL_EVENTS | IN_ONESHOT | IN_EXCL_UNLINK) +#define INOTIFY_USER_MASK (IN_ALL_EVENTS) static inline __u32 inotify_mark_user_mask(struct fsnotify_mark *fsn_mark) { - return fsn_mark->mask & INOTIFY_USER_MASK; + __u32 mask = fsn_mark->mask & INOTIFY_USER_MASK; + + if (fsn_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) + mask |= IN_EXCL_UNLINK; + if (fsn_mark->flags & FSNOTIFY_MARK_FLAG_IN_ONESHOT) + mask |= IN_ONESHOT; + + return mask; } extern void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark, diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index b0530f75b274..993375f0db67 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -123,13 +123,13 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, if (len) strcpy(event->name, name->name); - ret = fsnotify_add_event(group, fsn_event, inotify_merge, NULL); + ret = fsnotify_add_event(group, fsn_event, inotify_merge); if (ret) { /* Our event wasn't used in the end. Free it. */ fsnotify_destroy_event(group, fsn_event); } - if (inode_mark->mask & IN_ONESHOT) + if (inode_mark->flags & FSNOTIFY_MARK_FLAG_IN_ONESHOT) fsnotify_destroy_mark(inode_mark, group); return 0; @@ -184,7 +184,8 @@ static void inotify_free_group_priv(struct fsnotify_group *group) dec_inotify_instances(group->inotify_data.ucounts); } -static void inotify_free_event(struct fsnotify_event *fsn_event) +static void inotify_free_event(struct fsnotify_group *group, + struct fsnotify_event *fsn_event) { kfree(INOTIFY_E(fsn_event)); } diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 9fb7701d2f8a..131938986e54 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -94,10 +94,10 @@ static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg) __u32 mask; /* - * Everything should accept their own ignored and should receive events - * when the inode is unmounted. All directories care about children. + * Everything should receive events when the inode is unmounted. + * All directories care about children. */ - mask = (FS_IN_IGNORED | FS_UNMOUNT); + mask = (FS_UNMOUNT); if (S_ISDIR(inode->i_mode)) mask |= FS_EVENT_ON_CHILD; @@ -107,13 +107,28 @@ static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg) return mask; } +#define INOTIFY_MARK_FLAGS \ + (FSNOTIFY_MARK_FLAG_EXCL_UNLINK | FSNOTIFY_MARK_FLAG_IN_ONESHOT) + +static inline unsigned int inotify_arg_to_flags(u32 arg) +{ + unsigned int flags = 0; + + if (arg & IN_EXCL_UNLINK) + flags |= FSNOTIFY_MARK_FLAG_EXCL_UNLINK; + if (arg & IN_ONESHOT) + flags |= FSNOTIFY_MARK_FLAG_IN_ONESHOT; + + return flags; +} + static inline u32 inotify_mask_to_arg(__u32 mask) { return mask & (IN_ALL_EVENTS | IN_ISDIR | IN_UNMOUNT | IN_IGNORED | IN_Q_OVERFLOW); } -/* intofiy userspace file descriptor functions */ +/* inotify userspace file descriptor functions */ static __poll_t inotify_poll(struct file *file, poll_table *wait) { struct fsnotify_group *group = file->private_data; @@ -518,13 +533,10 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, struct fsnotify_mark *fsn_mark; struct inotify_inode_mark *i_mark; __u32 old_mask, new_mask; - __u32 mask; - int add = (arg & IN_MASK_ADD); + int replace = !(arg & IN_MASK_ADD); int create = (arg & IN_MASK_CREATE); int ret; - mask = inotify_arg_to_mask(inode, arg); - fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group); if (!fsn_mark) return -ENOENT; @@ -537,10 +549,12 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, spin_lock(&fsn_mark->lock); old_mask = fsn_mark->mask; - if (add) - fsn_mark->mask |= mask; - else - fsn_mark->mask = mask; + if (replace) { + fsn_mark->mask = 0; + fsn_mark->flags &= ~INOTIFY_MARK_FLAGS; + } + fsn_mark->mask |= inotify_arg_to_mask(inode, arg); + fsn_mark->flags |= inotify_arg_to_flags(arg); new_mask = fsn_mark->mask; spin_unlock(&fsn_mark->lock); @@ -571,19 +585,17 @@ static int inotify_new_watch(struct fsnotify_group *group, u32 arg) { struct inotify_inode_mark *tmp_i_mark; - __u32 mask; int ret; struct idr *idr = &group->inotify_data.idr; spinlock_t *idr_lock = &group->inotify_data.idr_lock; - mask = inotify_arg_to_mask(inode, arg); - tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL); if (unlikely(!tmp_i_mark)) return -ENOMEM; fsnotify_init_mark(&tmp_i_mark->fsn_mark, group); - tmp_i_mark->fsn_mark.mask = mask; + tmp_i_mark->fsn_mark.mask = inotify_arg_to_mask(inode, arg); + tmp_i_mark->fsn_mark.flags = inotify_arg_to_flags(arg); tmp_i_mark->wd = -1; ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark); @@ -620,13 +632,13 @@ static int inotify_update_watch(struct fsnotify_group *group, struct inode *inod { int ret = 0; - mutex_lock(&group->mark_mutex); + fsnotify_group_lock(group); /* try to update and existing watch with the new arg */ ret = inotify_update_existing_watch(group, inode, arg); /* no mark present, try to add a new one */ if (ret == -ENOENT) ret = inotify_new_watch(group, inode, arg); - mutex_unlock(&group->mark_mutex); + fsnotify_group_unlock(group); return ret; } @@ -636,7 +648,8 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events) struct fsnotify_group *group; struct inotify_event_info *oevent; - group = fsnotify_alloc_user_group(&inotify_fsnotify_ops); + group = fsnotify_alloc_group(&inotify_fsnotify_ops, + FSNOTIFY_GROUP_USER); if (IS_ERR(group)) return group; @@ -837,9 +850,7 @@ static int __init inotify_user_setup(void) BUILD_BUG_ON(IN_UNMOUNT != FS_UNMOUNT); BUILD_BUG_ON(IN_Q_OVERFLOW != FS_Q_OVERFLOW); BUILD_BUG_ON(IN_IGNORED != FS_IN_IGNORED); - BUILD_BUG_ON(IN_EXCL_UNLINK != FS_EXCL_UNLINK); BUILD_BUG_ON(IN_ISDIR != FS_ISDIR); - BUILD_BUG_ON(IN_ONESHOT != FS_IN_ONESHOT); BUILD_BUG_ON(HWEIGHT32(ALL_INOTIFY_BITS) != 22); diff --git a/fs/notify/mark.c b/fs/notify/mark.c index bea106fac090..c74ef947447d 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -116,20 +116,64 @@ __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn) return *fsnotify_conn_mask_p(conn); } -static void __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) +static void fsnotify_get_inode_ref(struct inode *inode) +{ + ihold(inode); + atomic_long_inc(&inode->i_sb->s_fsnotify_connectors); +} + +/* + * Grab or drop inode reference for the connector if needed. + * + * When it's time to drop the reference, we only clear the HAS_IREF flag and + * return the inode object. fsnotify_drop_object() will be resonsible for doing + * iput() outside of spinlocks. This happens when last mark that wanted iref is + * detached. + */ +static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn, + bool want_iref) +{ + bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF; + struct inode *inode = NULL; + + if (conn->type != FSNOTIFY_OBJ_TYPE_INODE || + want_iref == has_iref) + return NULL; + + if (want_iref) { + /* Pin inode if any mark wants inode refcount held */ + fsnotify_get_inode_ref(fsnotify_conn_inode(conn)); + conn->flags |= FSNOTIFY_CONN_FLAG_HAS_IREF; + } else { + /* Unpin inode after detach of last mark that wanted iref */ + inode = fsnotify_conn_inode(conn); + conn->flags &= ~FSNOTIFY_CONN_FLAG_HAS_IREF; + } + + return inode; +} + +static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { u32 new_mask = 0; + bool want_iref = false; struct fsnotify_mark *mark; assert_spin_locked(&conn->lock); /* We can get detached connector here when inode is getting unlinked. */ if (!fsnotify_valid_obj_type(conn->type)) - return; + return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { - if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) - new_mask |= mark->mask; + if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) + continue; + new_mask |= fsnotify_calc_mask(mark); + if (conn->type == FSNOTIFY_OBJ_TYPE_INODE && + !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) + want_iref = true; } *fsnotify_conn_mask_p(conn) = new_mask; + + return fsnotify_update_iref(conn, want_iref); } /* @@ -169,12 +213,6 @@ static void fsnotify_connector_destroy_workfn(struct work_struct *work) } } -static void fsnotify_get_inode_ref(struct inode *inode) -{ - ihold(inode); - atomic_long_inc(&inode->i_sb->s_fsnotify_connectors); -} - static void fsnotify_put_inode_ref(struct inode *inode) { struct super_block *sb = inode->i_sb; @@ -213,6 +251,10 @@ static void *fsnotify_detach_connector_from_object( if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) { inode = fsnotify_conn_inode(conn); inode->i_fsnotify_mask = 0; + + /* Unpin inode when detaching from connector */ + if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF)) + inode = NULL; } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0; } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) { @@ -274,7 +316,8 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) objp = fsnotify_detach_connector_from_object(conn, &type); free_conn = true; } else { - __fsnotify_recalc_mask(conn); + objp = __fsnotify_recalc_mask(conn); + type = conn->type; } WRITE_ONCE(mark->connector, NULL); spin_unlock(&conn->lock); @@ -353,7 +396,7 @@ bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) { int type; - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_type(type) { /* This can fail if mark is being removed */ if (!fsnotify_get_mark_safe(iter_info->marks[type])) { __release(&fsnotify_mark_srcu); @@ -382,7 +425,7 @@ void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) int type; iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); - fsnotify_foreach_obj_type(type) + fsnotify_foreach_iter_type(type) fsnotify_put_mark_wake(iter_info->marks[type]); } @@ -398,9 +441,7 @@ void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) */ void fsnotify_detach_mark(struct fsnotify_mark *mark) { - struct fsnotify_group *group = mark->group; - - WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); + fsnotify_group_assert_locked(mark->group); WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) && refcount_read(&mark->refcnt) < 1 + !!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)); @@ -452,9 +493,9 @@ void fsnotify_free_mark(struct fsnotify_mark *mark) void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { - mutex_lock(&group->mark_mutex); + fsnotify_group_lock(group); fsnotify_detach_mark(mark); - mutex_unlock(&group->mark_mutex); + fsnotify_group_unlock(group); fsnotify_free_mark(mark); } EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); @@ -496,10 +537,9 @@ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) } static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, - unsigned int type, + unsigned int obj_type, __kernel_fsid_t *fsid) { - struct inode *inode = NULL; struct fsnotify_mark_connector *conn; conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL); @@ -507,7 +547,8 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, return -ENOMEM; spin_lock_init(&conn->lock); INIT_HLIST_HEAD(&conn->list); - conn->type = type; + conn->flags = 0; + conn->type = obj_type; conn->obj = connp; /* Cache fsid of filesystem containing the object */ if (fsid) { @@ -517,10 +558,6 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, conn->fsid.val[0] = conn->fsid.val[1] = 0; conn->flags = 0; } - if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) { - inode = fsnotify_conn_inode(conn); - fsnotify_get_inode_ref(inode); - } fsnotify_get_sb_connectors(conn); /* @@ -529,8 +566,6 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, */ if (cmpxchg(connp, NULL, conn)) { /* Someone else created list structure for us */ - if (inode) - fsnotify_put_inode_ref(inode); fsnotify_put_sb_connectors(conn); kmem_cache_free(fsnotify_mark_connector_cachep, conn); } @@ -572,15 +607,16 @@ out: * priority, highest number first, and then by the group's location in memory. */ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, unsigned int type, - int allow_dups, __kernel_fsid_t *fsid) + fsnotify_connp_t *connp, + unsigned int obj_type, + int add_flags, __kernel_fsid_t *fsid) { struct fsnotify_mark *lmark, *last = NULL; struct fsnotify_mark_connector *conn; int cmp; int err = 0; - if (WARN_ON(!fsnotify_valid_obj_type(type))) + if (WARN_ON(!fsnotify_valid_obj_type(obj_type))) return -EINVAL; /* Backend is expected to check for zero fsid (e.g. tmpfs) */ @@ -592,7 +628,8 @@ restart: conn = fsnotify_grab_connector(connp); if (!conn) { spin_unlock(&mark->lock); - err = fsnotify_attach_connector_to_object(connp, type, fsid); + err = fsnotify_attach_connector_to_object(connp, obj_type, + fsid); if (err) return err; goto restart; @@ -631,7 +668,7 @@ restart: if ((lmark->group == mark->group) && (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) && - !allow_dups) { + !(mark->group->flags & FSNOTIFY_GROUP_DUPS)) { err = -EEXIST; goto out_err; } @@ -665,13 +702,13 @@ out_err: * event types should be delivered to which group. */ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, unsigned int type, - int allow_dups, __kernel_fsid_t *fsid) + fsnotify_connp_t *connp, unsigned int obj_type, + int add_flags, __kernel_fsid_t *fsid) { struct fsnotify_group *group = mark->group; int ret = 0; - BUG_ON(!mutex_is_locked(&group->mark_mutex)); + fsnotify_group_assert_locked(group); /* * LOCKING ORDER!!!! @@ -686,12 +723,11 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_get_mark(mark); /* for g_list */ spin_unlock(&mark->lock); - ret = fsnotify_add_mark_list(mark, connp, type, allow_dups, fsid); + ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags, fsid); if (ret) goto err; - if (mark->mask) - fsnotify_recalc_mask(mark->connector); + fsnotify_recalc_mask(mark->connector); return ret; err: @@ -706,14 +742,15 @@ err: } int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, - unsigned int type, int allow_dups, __kernel_fsid_t *fsid) + unsigned int obj_type, int add_flags, + __kernel_fsid_t *fsid) { int ret; struct fsnotify_group *group = mark->group; - mutex_lock(&group->mark_mutex); - ret = fsnotify_add_mark_locked(mark, connp, type, allow_dups, fsid); - mutex_unlock(&group->mark_mutex); + fsnotify_group_lock(group); + ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags, fsid); + fsnotify_group_unlock(group); return ret; } EXPORT_SYMBOL_GPL(fsnotify_add_mark); @@ -747,14 +784,14 @@ EXPORT_SYMBOL_GPL(fsnotify_find_mark); /* Clear any marks in a group with given type mask */ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, - unsigned int type_mask) + unsigned int obj_type) { struct fsnotify_mark *lmark, *mark; LIST_HEAD(to_free); struct list_head *head = &to_free; /* Skip selection step if we want to clear all marks. */ - if (type_mask == FSNOTIFY_OBJ_ALL_TYPES_MASK) { + if (obj_type == FSNOTIFY_OBJ_TYPE_ANY) { head = &group->marks_list; goto clear; } @@ -767,24 +804,24 @@ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, * move marks to free to to_free list in one go and then free marks in * to_free list one by one. */ - mutex_lock(&group->mark_mutex); + fsnotify_group_lock(group); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { - if ((1U << mark->connector->type) & type_mask) + if (mark->connector->type == obj_type) list_move(&mark->g_list, &to_free); } - mutex_unlock(&group->mark_mutex); + fsnotify_group_unlock(group); clear: while (1) { - mutex_lock(&group->mark_mutex); + fsnotify_group_lock(group); if (list_empty(head)) { - mutex_unlock(&group->mark_mutex); + fsnotify_group_unlock(group); break; } mark = list_first_entry(head, struct fsnotify_mark, g_list); fsnotify_get_mark(mark); fsnotify_detach_mark(mark); - mutex_unlock(&group->mark_mutex); + fsnotify_group_unlock(group); fsnotify_free_mark(mark); fsnotify_put_mark(mark); } diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 32f45543b9c6..9022ae650cf8 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -64,7 +64,7 @@ void fsnotify_destroy_event(struct fsnotify_group *group, WARN_ON(!list_empty(&event->list)); spin_unlock(&group->notification_lock); } - group->ops->free_event(event); + group->ops->free_event(group, event); } /* @@ -78,12 +78,12 @@ void fsnotify_destroy_event(struct fsnotify_group *group, * 2 if the event was not queued - either the queue of events has overflown * or the group is shutting down. */ -int fsnotify_add_event(struct fsnotify_group *group, - struct fsnotify_event *event, - int (*merge)(struct fsnotify_group *, - struct fsnotify_event *), - void (*insert)(struct fsnotify_group *, - struct fsnotify_event *)) +int fsnotify_insert_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct fsnotify_group *, + struct fsnotify_event *), + void (*insert)(struct fsnotify_group *, + struct fsnotify_event *)) { int ret = 0; struct list_head *list = &group->notification_list; diff --git a/fs/open.c b/fs/open.c index 761e5993e4ef..cf0558d811bf 100644 --- a/fs/open.c +++ b/fs/open.c @@ -980,6 +980,48 @@ struct file *dentry_open(const struct path *path, int flags, } EXPORT_SYMBOL(dentry_open); +/** + * dentry_create - Create and open a file + * @path: path to create + * @flags: O_ flags + * @mode: mode bits for new file + * @cred: credentials to use + * + * Caller must hold the parent directory's lock, and have prepared + * a negative dentry, placed in @path->dentry, for the new file. + * + * Caller sets @path->mnt to the vfsmount of the filesystem where + * the new file is to be created. The parent directory and the + * negative dentry must reside on the same filesystem instance. + * + * On success, returns a "struct file *". Otherwise a ERR_PTR + * is returned. + */ +struct file *dentry_create(const struct path *path, int flags, umode_t mode, + const struct cred *cred) +{ + struct file *f; + int error; + + validate_creds(cred); + f = alloc_empty_file(flags, cred); + if (IS_ERR(f)) + return f; + + error = vfs_create(mnt_user_ns(path->mnt), + d_inode(path->dentry->d_parent), + path->dentry, mode, true); + if (!error) + error = vfs_open(path, f); + + if (unlikely(error)) { + fput(f); + return ERR_PTR(error); + } + return f; +} +EXPORT_SYMBOL(dentry_create); + struct file *open_with_fake_path(const struct path *path, int flags, struct inode *inode, const struct cred *cred) { diff --git a/fs/pipe.c b/fs/pipe.c index a8b8ef2dae7b..0a8095070b70 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -423,6 +423,18 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) bool was_empty = false; bool wake_next_writer = false; + /* + * Reject writing to watch queue pipes before the point where we lock + * the pipe. + * Otherwise, lockdep would be unhappy if the caller already has another + * pipe locked. + * If we had to support locking a normal pipe and a notification pipe at + * the same time, we could set up lockdep annotations for that, but + * since we don't actually need that, it's simpler to just bail here. + */ + if (pipe_has_watch_queue(pipe)) + return -EXDEV; + /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; @@ -435,11 +447,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } - if (pipe_has_watch_queue(pipe)) { - ret = -EXDEV; - goto out; - } - /* * If it wasn't empty we try to merge new data into * the last buffer. diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c index 5d3f944f6018..295040c249d9 100644 --- a/fs/pstore/zone.c +++ b/fs/pstore/zone.c @@ -973,6 +973,8 @@ static ssize_t psz_kmsg_read(struct pstore_zone *zone, char *buf = kasprintf(GFP_KERNEL, "%s: Total %d times\n", kmsg_dump_reason_str(record->reason), record->count); + if (!buf) + return -ENOMEM; hlen = strlen(buf); record->buf = krealloc(buf, hlen + size, GFP_KERNEL); if (!record->buf) { diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 1e9c520411f8..5800cb065ca5 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -82,9 +82,6 @@ static inline sysv_zone_t *block_end(struct buffer_head *bh) return (sysv_zone_t*)((char*)bh->b_data + bh->b_size); } -/* - * Requires read_lock(&pointers_lock) or write_lock(&pointers_lock) - */ static Indirect *get_branch(struct inode *inode, int depth, int offsets[], @@ -104,15 +101,18 @@ static Indirect *get_branch(struct inode *inode, bh = sb_bread(sb, block); if (!bh) goto failure; + read_lock(&pointers_lock); if (!verify_chain(chain, p)) goto changed; add_chain(++p, bh, (sysv_zone_t*)bh->b_data + *++offsets); + read_unlock(&pointers_lock); if (!p->key) goto no_block; } return NULL; changed: + read_unlock(&pointers_lock); brelse(bh); *err = -EAGAIN; goto no_block; @@ -218,9 +218,7 @@ static int get_block(struct inode *inode, sector_t iblock, struct buffer_head *b goto out; reread: - read_lock(&pointers_lock); partial = get_branch(inode, depth, offsets, chain, &err); - read_unlock(&pointers_lock); /* Simplest case - block found, no allocation needed */ if (!partial) { @@ -290,9 +288,9 @@ static Indirect *find_shared(struct inode *inode, *top = 0; for (k = depth; k > 1 && !offsets[k-1]; k--) ; + partial = get_branch(inode, k, offsets, chain, &err); write_lock(&pointers_lock); - partial = get_branch(inode, k, offsets, chain, &err); if (!partial) partial = chain + k-1; /* diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 7cc2abcb70ae..509144cc41a0 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -262,9 +262,6 @@ static int write_begin_slow(struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } if (PagePrivate(page)) @@ -463,9 +460,6 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } err = allocate_budget(c, page, ui, appending); @@ -475,10 +469,8 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, * If we skipped reading the page because we were going to * write all of it, then it is not up to date. */ - if (skipped_read) { + if (skipped_read) ClearPageChecked(page); - ClearPageUptodate(page); - } /* * Budgeting failed which means it would have to force * write-back but didn't, because we set the @fast flag in the @@ -569,6 +561,9 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, goto out; } + if (len == PAGE_SIZE) + SetPageUptodate(page); + if (!PagePrivate(page)) { attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index 37dd3fe5b1e9..44725007ccc2 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -151,7 +151,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) if (!sbi->nls) { vbg_err("vboxsf: Count not load '%s' nls\n", nls_name); err = -EINVAL; - goto fail_free; + goto fail_destroy_idr; } } @@ -224,6 +224,7 @@ fail_free: ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); if (sbi->nls) unload_nls(sbi->nls); +fail_destroy_idr: idr_destroy(&sbi->ino_idr); kfree(sbi); return err; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 8471717c5085..dd9ea351bc02 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -81,8 +81,8 @@ #define RO_EXCEPTION_TABLE #endif -/* Align . to a 8 byte boundary equals to maximum function alignment. */ -#define ALIGN_FUNCTION() . = ALIGN(8) +/* Align . function alignment. */ +#define ALIGN_FUNCTION() . = ALIGN(CONFIG_FUNCTION_ALIGNMENT) /* * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections, which diff --git a/include/linux/cpu.h b/include/linux/cpu.h index caf3b95017bf..e1e6a045c38b 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -74,6 +74,8 @@ extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/device.h b/include/linux/device.h index e270cb740b9e..3e04bd84f126 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -971,6 +971,7 @@ void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); +void device_link_wait_removal(void); extern __printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index bfffe494356a..2ff55ec902f4 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -69,6 +69,7 @@ struct dma_map_ops { int (*dma_supported)(struct device *dev, u64 mask); u64 (*get_required_mask)(struct device *dev); size_t (*max_mapping_size)(struct device *dev); + size_t (*opt_mapping_size)(void); unsigned long (*get_merge_boundary)(struct device *dev); }; diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index dca2b1355bb1..fe3849434b2a 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -144,6 +144,7 @@ int dma_set_mask(struct device *dev, u64 mask); int dma_set_coherent_mask(struct device *dev, u64 mask); u64 dma_get_required_mask(struct device *dev); size_t dma_max_mapping_size(struct device *dev); +size_t dma_opt_mapping_size(struct device *dev); bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, @@ -266,6 +267,10 @@ static inline size_t dma_max_mapping_size(struct device *dev) { return 0; } +static inline size_t dma_opt_mapping_size(struct device *dev) +{ + return 0; +} static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) { return false; diff --git a/include/linux/dnotify.h b/include/linux/dnotify.h index 0aad774beaec..b87c3b85a166 100644 --- a/include/linux/dnotify.h +++ b/include/linux/dnotify.h @@ -26,7 +26,7 @@ struct dnotify_struct { FS_MODIFY | FS_MODIFY_CHILD |\ FS_ACCESS | FS_ACCESS_CHILD |\ FS_ATTRIB | FS_ATTRIB_CHILD |\ - FS_CREATE | FS_DN_RENAME |\ + FS_CREATE | FS_RENAME |\ FS_MOVED_FROM | FS_MOVED_TO) extern int dir_notify_enable; diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 3260fe714846..6525f4b7eb97 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -221,11 +221,24 @@ struct export_operations { #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ -#define EXPORT_OP_SYNC_LOCKS (0x20) /* Filesystem can't do - asychronous blocking locks */ +#define EXPORT_OP_FLUSH_ON_CLOSE (0x20) /* fs flushes file data on close */ +#define EXPORT_OP_ASYNC_LOCK (0x40) /* fs can do async lock request */ unsigned long flags; }; +/** + * exportfs_lock_op_is_async() - export op supports async lock operation + * @export_ops: the nfs export operations to check + * + * Returns true if the nfs export_operations structure has + * EXPORT_OP_ASYNC_LOCK in their flags set + */ +static inline bool +exportfs_lock_op_is_async(const struct export_operations *export_ops) +{ + return export_ops->flags & EXPORT_OP_ASYNC_LOCK; +} + extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, int *max_len, struct inode *parent); extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index eec3b7c40811..558844c8d259 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -25,7 +25,7 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_CLASS_BITS (FAN_CLASS_NOTIF | FANOTIFY_PERM_CLASSES) -#define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DFID_NAME) +#define FANOTIFY_FID_BITS (FAN_REPORT_DFID_NAME_TARGET) #define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD) @@ -61,14 +61,19 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ FAN_MARK_FILESYSTEM) +#define FANOTIFY_MARK_CMD_BITS (FAN_MARK_ADD | FAN_MARK_REMOVE | \ + FAN_MARK_FLUSH) + +#define FANOTIFY_MARK_IGNORE_BITS (FAN_MARK_IGNORED_MASK | \ + FAN_MARK_IGNORE) + #define FANOTIFY_MARK_FLAGS (FANOTIFY_MARK_TYPE_BITS | \ - FAN_MARK_ADD | \ - FAN_MARK_REMOVE | \ + FANOTIFY_MARK_CMD_BITS | \ + FANOTIFY_MARK_IGNORE_BITS | \ FAN_MARK_DONT_FOLLOW | \ FAN_MARK_ONLYDIR | \ - FAN_MARK_IGNORED_MASK | \ FAN_MARK_IGNORED_SURV_MODIFY | \ - FAN_MARK_FLUSH) + FAN_MARK_EVICTABLE) /* * Events that can be reported with data type FSNOTIFY_EVENT_PATH. @@ -82,15 +87,23 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. */ -#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE) +#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE | \ + FAN_RENAME) + +/* Events that can be reported with event->fd */ +#define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS) /* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */ #define FANOTIFY_INODE_EVENTS (FANOTIFY_DIRENT_EVENTS | \ FAN_ATTRIB | FAN_MOVE_SELF | FAN_DELETE_SELF) +/* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */ +#define FANOTIFY_ERROR_EVENTS (FAN_FS_ERROR) + /* Events that user can request to be notified on */ #define FANOTIFY_EVENTS (FANOTIFY_PATH_EVENTS | \ - FANOTIFY_INODE_EVENTS) + FANOTIFY_INODE_EVENTS | \ + FANOTIFY_ERROR_EVENTS) /* Events that require a permission response from user */ #define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM | \ @@ -104,6 +117,10 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ FANOTIFY_PERM_EVENTS | \ FAN_Q_OVERFLOW | FAN_ONDIR) +/* Events and flags relevant only for directories */ +#define FANOTIFY_DIRONLY_EVENT_BITS (FANOTIFY_DIRENT_EVENTS | \ + FAN_EVENT_ON_CHILD | FAN_ONDIR) + #define ALL_FANOTIFY_EVENT_BITS (FANOTIFY_OUTGOING_EVENTS | \ FANOTIFY_EVENT_FLAGS) diff --git a/include/linux/fs.h b/include/linux/fs.h index c18ac5aab963..32b0269173d9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1066,6 +1066,7 @@ struct file_lock_operations { }; struct lock_manager_operations { + void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ @@ -1074,6 +1075,8 @@ struct lock_manager_operations { int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); bool (*lm_breaker_owns_lease)(struct file_lock *); + bool (*lm_lock_expirable)(struct file_lock *cfl); + void (*lm_expire_lock)(void); }; struct lock_manager { @@ -1212,6 +1215,15 @@ extern void lease_unregister_notifier(struct notifier_block *); struct files_struct; extern void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); +extern bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner); + +static inline struct file_lock_context * +locks_inode_context(const struct inode *inode) +{ + return smp_load_acquire(&inode->i_flctx); +} + #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) @@ -1352,6 +1364,18 @@ static inline int lease_modify(struct file_lock *fl, int arg, struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} +static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner) +{ + return false; +} + +static inline struct file_lock_context * +locks_inode_context(const struct inode *inode) +{ + return NULL; +} + #endif /* !CONFIG_FILE_LOCKING */ static inline struct inode *file_inode(const struct file *f) @@ -2748,6 +2772,8 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt, name, flags, mode); } extern struct file * dentry_open(const struct path *, int, const struct cred *); +extern struct file *dentry_create(const struct path *path, int flags, + umode_t mode, const struct cred *cred); extern struct file * open_with_fake_path(const struct path *, int, struct inode*, const struct cred *); static inline struct file *file_clone_open(struct file *file) diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index a9477c14fad5..bb8467cd11ae 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -26,20 +26,20 @@ * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ -static inline void fsnotify_name(struct inode *dir, __u32 mask, - struct inode *child, - const struct qstr *name, u32 cookie) +static inline int fsnotify_name(__u32 mask, const void *data, int data_type, + struct inode *dir, const struct qstr *name, + u32 cookie) { if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0) - return; + return 0; - fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie); + return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { - fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0); + fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) @@ -86,7 +86,7 @@ notify_child: */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { - fsnotify_parent(dentry, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE); + fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_file(struct file *file, __u32 mask) @@ -144,18 +144,23 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; + __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; - if (old_dir == new_dir) - old_dir_mask |= FS_DN_RENAME; - if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; + rename_mask |= FS_ISDIR; } - fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie); - fsnotify_name(new_dir, new_dir_mask, source, new_name, fs_cookie); + /* Event with information about both old and new parent+name */ + fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, + old_dir, old_name, 0); + + fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, + old_dir, old_name, fs_cookie); + fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, + new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); @@ -190,16 +195,22 @@ static inline void fsnotify_inoderemove(struct inode *inode) /* * fsnotify_create - 'name' was linked in + * + * Caller must make sure that dentry->d_name is stable. + * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate + * ->d_inode later */ -static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) +static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { - audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); + audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_dirent(inode, dentry, FS_CREATE); + fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory + * + * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ @@ -209,7 +220,8 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_name(dir, FS_CREATE, inode, &new_dentry->d_name, 0); + fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, + dir, &new_dentry->d_name, 0); } /* @@ -228,7 +240,8 @@ static inline void fsnotify_delete(struct inode *dir, struct inode *inode, if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; - fsnotify_name(dir, mask, inode, &dentry->d_name, 0); + fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, + 0); } /** @@ -263,12 +276,16 @@ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) /* * fsnotify_mkdir - directory 'name' was created + * + * Caller must make sure that dentry->d_name is stable. + * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate + * ->d_inode later */ -static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) +static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { - audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); + audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_dirent(inode, dentry, FS_CREATE | FS_ISDIR); + fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* @@ -362,4 +379,17 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) fsnotify_dentry(dentry, mask); } +static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, + int error) +{ + struct fs_error_report report = { + .error = error, + .inode = inode, + .sb = sb, + }; + + return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, + NULL, NULL, NULL, 0); +} + #endif /* _LINUX_FS_NOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 1ce66748a2d2..d7d96c806bff 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -19,6 +19,8 @@ #include <linux/atomic.h> #include <linux/user_namespace.h> #include <linux/refcount.h> +#include <linux/mempool.h> +#include <linux/sched/mm.h> /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily @@ -42,13 +44,18 @@ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ +#define FS_ERROR 0x00008000 /* Filesystem Error (fanotify) */ + +/* + * FS_IN_IGNORED overloads FS_ERROR. It is only used internally by inotify + * which does not support FS_ERROR. + */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ -#define FS_EXCL_UNLINK 0x04000000 /* do not send events if object is unlinked */ /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. @@ -56,10 +63,9 @@ */ #define FS_EVENT_ON_CHILD 0x08000000 -#define FS_DN_RENAME 0x10000000 /* file renamed */ +#define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ -#define FS_IN_ONESHOT 0x80000000 /* only send event once */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) @@ -69,7 +75,7 @@ * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ -#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE) +#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) @@ -94,12 +100,12 @@ /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ - FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \ - FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED) + FS_DELETE_SELF | FS_MOVE_SELF | \ + FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ + FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ -#define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ - FS_DN_MULTISHOT | FS_EVENT_ON_CHILD) +#define ALL_FSNOTIFY_FLAGS (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) @@ -136,6 +142,7 @@ struct mem_cgroup; * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. + * Either @inode or @dir must be non-NULL. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * @@ -155,7 +162,7 @@ struct fsnotify_ops { const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); - void (*free_event)(struct fsnotify_event *event); + void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; @@ -204,6 +211,12 @@ struct fsnotify_group { unsigned int priority; bool shutdown; /* group is being shut down, don't queue more events */ +#define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ +#define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ +#define FSNOTIFY_GROUP_NOFS 0x04 /* group lock is not direct reclaim safe */ + int flags; + unsigned int owner_flags; /* stored flags of mark_mutex owner */ + /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t user_waits; /* Number of tasks waiting for user @@ -238,16 +251,50 @@ struct fsnotify_group { int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ struct ucounts *ucounts; + mempool_t error_events_pool; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; }; +/* + * These helpers are used to prevent deadlock when reclaiming inodes with + * evictable marks of the same group that is allocating a new mark. + */ +static inline void fsnotify_group_lock(struct fsnotify_group *group) +{ + mutex_lock(&group->mark_mutex); + if (group->flags & FSNOTIFY_GROUP_NOFS) + group->owner_flags = memalloc_nofs_save(); +} + +static inline void fsnotify_group_unlock(struct fsnotify_group *group) +{ + if (group->flags & FSNOTIFY_GROUP_NOFS) + memalloc_nofs_restore(group->owner_flags); + mutex_unlock(&group->mark_mutex); +} + +static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) +{ + WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); + if (group->flags & FSNOTIFY_GROUP_NOFS) + WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); +} + /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, + FSNOTIFY_EVENT_DENTRY, + FSNOTIFY_EVENT_ERROR, +}; + +struct fs_error_report { + int error; + struct inode *inode; + struct super_block *sb; }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) @@ -255,8 +302,25 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; + case FSNOTIFY_EVENT_DENTRY: + return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); + case FSNOTIFY_EVENT_ERROR: + return ((struct fs_error_report *)data)->inode; + default: + return NULL; + } +} + +static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_DENTRY: + /* Non const is needed for dget() */ + return (struct dentry *)data; + case FSNOTIFY_EVENT_PATH: + return ((const struct path *)data)->dentry; default: return NULL; } @@ -273,58 +337,110 @@ static inline const struct path *fsnotify_data_path(const void *data, } } +static inline struct super_block *fsnotify_data_sb(const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_INODE: + return ((struct inode *)data)->i_sb; + case FSNOTIFY_EVENT_DENTRY: + return ((struct dentry *)data)->d_sb; + case FSNOTIFY_EVENT_PATH: + return ((const struct path *)data)->dentry->d_sb; + case FSNOTIFY_EVENT_ERROR: + return ((struct fs_error_report *) data)->sb; + default: + return NULL; + } +} + +static inline struct fs_error_report *fsnotify_data_error_report( + const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_ERROR: + return (struct fs_error_report *) data; + default: + return NULL; + } +} + +/* + * Index to merged marks iterator array that correlates to a type of watch. + * The type of watched object can be deduced from the iterator type, but not + * the other way around, because an event can match different watched objects + * of the same object type. + * For example, both parent and child are watching an object of type inode. + */ +enum fsnotify_iter_type { + FSNOTIFY_ITER_TYPE_INODE, + FSNOTIFY_ITER_TYPE_VFSMOUNT, + FSNOTIFY_ITER_TYPE_SB, + FSNOTIFY_ITER_TYPE_PARENT, + FSNOTIFY_ITER_TYPE_INODE2, + FSNOTIFY_ITER_TYPE_COUNT +}; + +/* The type of object that a mark is attached to */ enum fsnotify_obj_type { + FSNOTIFY_OBJ_TYPE_ANY = -1, FSNOTIFY_OBJ_TYPE_INODE, - FSNOTIFY_OBJ_TYPE_PARENT, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; -#define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE) -#define FSNOTIFY_OBJ_TYPE_PARENT_FL (1U << FSNOTIFY_OBJ_TYPE_PARENT) -#define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) -#define FSNOTIFY_OBJ_TYPE_SB_FL (1U << FSNOTIFY_OBJ_TYPE_SB) -#define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) - -static inline bool fsnotify_valid_obj_type(unsigned int type) +static inline bool fsnotify_valid_obj_type(unsigned int obj_type) { - return (type < FSNOTIFY_OBJ_TYPE_COUNT); + return (obj_type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { - struct fsnotify_mark *marks[FSNOTIFY_OBJ_TYPE_COUNT]; + struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; + struct fsnotify_group *current_group; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( - struct fsnotify_iter_info *iter_info, int type) + struct fsnotify_iter_info *iter_info, int iter_type) { - return (iter_info->report_mask & (1U << type)); + return (iter_info->report_mask & (1U << iter_type)); } static inline void fsnotify_iter_set_report_type( - struct fsnotify_iter_info *iter_info, int type) + struct fsnotify_iter_info *iter_info, int iter_type) +{ + iter_info->report_mask |= (1U << iter_type); +} + +static inline struct fsnotify_mark *fsnotify_iter_mark( + struct fsnotify_iter_info *iter_info, int iter_type) { - iter_info->report_mask |= (1U << type); + if (fsnotify_iter_should_report_type(iter_info, iter_type)) + return iter_info->marks[iter_type]; + return NULL; } -static inline void fsnotify_iter_set_report_type_mark( - struct fsnotify_iter_info *iter_info, int type, - struct fsnotify_mark *mark) +static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type, + struct fsnotify_mark **markp) { - iter_info->marks[type] = mark; - iter_info->report_mask |= (1U << type); + while (type < FSNOTIFY_ITER_TYPE_COUNT) { + *markp = fsnotify_iter_mark(iter, type); + if (*markp) + break; + type++; + } + return type; } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ - return (iter_info->report_mask & FSNOTIFY_OBJ_TYPE_##NAME##_FL) ? \ - iter_info->marks[FSNOTIFY_OBJ_TYPE_##NAME] : NULL; \ + return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \ } FSNOTIFY_ITER_FUNCS(inode, INODE) @@ -332,8 +448,13 @@ FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) -#define fsnotify_foreach_obj_type(type) \ - for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++) +#define fsnotify_foreach_iter_type(type) \ + for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) +#define fsnotify_foreach_iter_mark_type(iter, mark, type) \ + for (type = 0; \ + type = fsnotify_iter_step(iter, type, &mark), \ + type < FSNOTIFY_ITER_TYPE_COUNT; \ + type++) /* * fsnotify_connp_t is what we embed in objects which connector can be attached @@ -352,6 +473,7 @@ struct fsnotify_mark_connector { spinlock_t lock; unsigned short type; /* Type of object [lock] */ #define FSNOTIFY_CONN_FLAG_HAS_FSID 0x01 +#define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ __kernel_fsid_t fsid; /* fsid of filesystem containing object */ union { @@ -396,11 +518,18 @@ struct fsnotify_mark { struct hlist_node obj_list; /* Head of list of marks for an object [mark ref] */ struct fsnotify_mark_connector *connector; - /* Events types to ignore [mark->lock, group->mark_mutex] */ - __u32 ignored_mask; -#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x01 -#define FSNOTIFY_MARK_FLAG_ALIVE 0x02 -#define FSNOTIFY_MARK_FLAG_ATTACHED 0x04 + /* Events types and flags to ignore [mark->lock, group->mark_mutex] */ + __u32 ignore_mask; + /* General fsnotify mark flags */ +#define FSNOTIFY_MARK_FLAG_ALIVE 0x0001 +#define FSNOTIFY_MARK_FLAG_ATTACHED 0x0002 + /* inotify mark flags */ +#define FSNOTIFY_MARK_FLAG_EXCL_UNLINK 0x0010 +#define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 + /* fanotify mark flags */ +#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 +#define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200 +#define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS 0x0400 unsigned int flags; /* flags [mark->lock] */ }; @@ -466,8 +595,9 @@ static inline void fsnotify_update_flags(struct dentry *dentry) /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ -extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops); -extern struct fsnotify_group *fsnotify_alloc_user_group(const struct fsnotify_ops *ops); +extern struct fsnotify_group *fsnotify_alloc_group( + const struct fsnotify_ops *ops, + int flags); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ @@ -482,16 +612,30 @@ extern int fsnotify_fasync(int fd, struct file *file, int on); extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ -extern int fsnotify_add_event(struct fsnotify_group *group, - struct fsnotify_event *event, - int (*merge)(struct fsnotify_group *, - struct fsnotify_event *), - void (*insert)(struct fsnotify_group *, - struct fsnotify_event *)); +extern int fsnotify_insert_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct fsnotify_group *, + struct fsnotify_event *), + void (*insert)(struct fsnotify_group *, + struct fsnotify_event *)); + +static inline int fsnotify_add_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct fsnotify_group *, + struct fsnotify_event *)) +{ + return fsnotify_insert_event(group, event, merge, NULL); +} + /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { - fsnotify_add_event(group, group->overflow_event, NULL, NULL); + fsnotify_add_event(group, group->overflow_event, NULL); +} + +static inline bool fsnotify_is_overflow_event(u32 mask) +{ + return mask & FS_Q_OVERFLOW; } static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group) @@ -512,6 +656,101 @@ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, /* functions used to manipulate the marks attached to inodes */ +/* + * Canonical "ignore mask" including event flags. + * + * Note the subtle semantic difference from the legacy ->ignored_mask. + * ->ignored_mask traditionally only meant which events should be ignored, + * while ->ignore_mask also includes flags regarding the type of objects on + * which events should be ignored. + */ +static inline __u32 fsnotify_ignore_mask(struct fsnotify_mark *mark) +{ + __u32 ignore_mask = mark->ignore_mask; + + /* The event flags in ignore mask take effect */ + if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) + return ignore_mask; + + /* + * Legacy behavior: + * - Always ignore events on dir + * - Ignore events on child if parent is watching children + */ + ignore_mask |= FS_ISDIR; + ignore_mask &= ~FS_EVENT_ON_CHILD; + ignore_mask |= mark->mask & FS_EVENT_ON_CHILD; + + return ignore_mask; +} + +/* Legacy ignored_mask - only event types to ignore */ +static inline __u32 fsnotify_ignored_events(struct fsnotify_mark *mark) +{ + return mark->ignore_mask & ALL_FSNOTIFY_EVENTS; +} + +/* + * Check if mask (or ignore mask) should be applied depending if victim is a + * directory and whether it is reported to a watching parent. + */ +static inline bool fsnotify_mask_applicable(__u32 mask, bool is_dir, + int iter_type) +{ + /* Should mask be applied to a directory? */ + if (is_dir && !(mask & FS_ISDIR)) + return false; + + /* Should mask be applied to a child? */ + if (iter_type == FSNOTIFY_ITER_TYPE_PARENT && + !(mask & FS_EVENT_ON_CHILD)) + return false; + + return true; +} + +/* + * Effective ignore mask taking into account if event victim is a + * directory and whether it is reported to a watching parent. + */ +static inline __u32 fsnotify_effective_ignore_mask(struct fsnotify_mark *mark, + bool is_dir, int iter_type) +{ + __u32 ignore_mask = fsnotify_ignored_events(mark); + + if (!ignore_mask) + return 0; + + /* For non-dir and non-child, no need to consult the event flags */ + if (!is_dir && iter_type != FSNOTIFY_ITER_TYPE_PARENT) + return ignore_mask; + + ignore_mask = fsnotify_ignore_mask(mark); + if (!fsnotify_mask_applicable(ignore_mask, is_dir, iter_type)) + return 0; + + return ignore_mask & ALL_FSNOTIFY_EVENTS; +} + +/* Get mask for calculating object interest taking ignore mask into account */ +static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark) +{ + __u32 mask = mark->mask; + + if (!fsnotify_ignored_events(mark)) + return mask; + + /* Interest in FS_MODIFY may be needed for clearing ignore mask */ + if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) + mask |= FS_MODIFY; + + /* + * If mark is interested in ignoring events on children, the object must + * show interest in those events for fsnotify_parent() to notice it. + */ + return mask | mark->ignore_mask; +} + /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ @@ -526,27 +765,27 @@ extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn, __kernel_fsid_t *fsid); /* attach the mark to the object */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, unsigned int type, - int allow_dups, __kernel_fsid_t *fsid); + fsnotify_connp_t *connp, unsigned int obj_type, + int add_flags, __kernel_fsid_t *fsid); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, - unsigned int type, int allow_dups, + unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, - int allow_dups) + int add_flags) { return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, allow_dups, NULL); + FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, - int allow_dups) + int add_flags) { return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, allow_dups, + FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } @@ -559,22 +798,23 @@ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); -/* run all the marks in a group, and clear all of the marks attached to given object type */ -extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int type); +/* Clear all of the marks of a group attached to a given object type */ +extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, + unsigned int obj_type); /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE); } /* run all the marks in a group, and clear all of the sn marks */ static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 55b2ec1f965a..d1ca5eb56ff0 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -660,6 +660,15 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); extern void pm_restrict_gfp_mask(void); extern void pm_restore_gfp_mask(void); +/* + * Check if the gfp flags allow compaction - GFP_NOIO is a really + * tricky context because the migration might require IO. + */ +static inline bool gfp_compaction_allowed(gfp_t gfp_mask) +{ + return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); +} + extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_PM_SLEEP diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 8499fc9220e0..edcfddaa5f7a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -164,8 +164,28 @@ struct hv_ring_buffer { u8 buffer[]; } __packed; + +/* + * If the requested ring buffer size is at least 8 times the size of the + * header, steal space from the ring buffer for the header. Otherwise, add + * space for the header so that is doesn't take too much of the ring buffer + * space. + * + * The factor of 8 is somewhat arbitrary. The goal is to prevent adding a + * relatively small header (4 Kbytes on x86) to a large-ish power-of-2 ring + * buffer size (such as 128 Kbytes) and so end up making a nearly twice as + * large allocation that will be almost half wasted. As a contrasting example, + * on ARM64 with 64 Kbyte page size, we don't want to take 64 Kbytes for the + * header from a 128 Kbyte allocation, leaving only 64 Kbytes for the ring. + * In this latter case, we must add 64 Kbytes for the header and not worry + * about what's wasted. + */ +#define VMBUS_HEADER_ADJ(payload_sz) \ + ((payload_sz) >= 8 * sizeof(struct hv_ring_buffer) ? \ + 0 : sizeof(struct hv_ring_buffer)) + /* Calculate the proper size of a ringbuffer, it must be page-aligned */ -#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \ +#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(VMBUS_HEADER_ADJ(payload_sz) + \ (payload_sz)) struct hv_ring_buffer_info { diff --git a/include/linux/iova.h b/include/linux/iova.h index 6b6cc104e300..9aa0acf9820a 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -137,6 +137,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) int iova_cache_get(void); void iova_cache_put(void); +unsigned long iova_rcache_range(void); + void free_iova(struct iova_domain *iovad, unsigned long pfn); void __free_iova(struct iova_domain *iovad, struct iova *iova); struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size, diff --git a/include/linux/kthread.h b/include/linux/kthread.h index db47aae7c481..8e21bd13c36d 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -95,6 +95,7 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); +void kthread_exit(long result) __noreturn; int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/include/linux/linkage.h b/include/linux/linkage.h index dbf8506decca..fc81e51330b2 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -69,8 +69,8 @@ #endif #ifndef __ALIGN -#define __ALIGN .align 4,0x90 -#define __ALIGN_STR ".align 4,0x90" +#define __ALIGN .balign CONFIG_FUNCTION_ALIGNMENT +#define __ALIGN_STR __stringify(__ALIGN) #endif #ifdef __ASSEMBLY__ diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index c4ae6506b8b3..70ce419e2709 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -292,6 +292,7 @@ void nlmsvc_locks_init_private(struct file_lock *, struct nlm_host *, pid_t); __be32 nlm_lookup_file(struct svc_rqst *, struct nlm_file **, struct nlm_lock *); void nlm_release_file(struct nlm_file *); +void nlmsvc_put_lockowner(struct nlm_lockowner *); void nlmsvc_release_lockowner(struct nlm_lock *); void nlmsvc_mark_resources(struct net *); void nlmsvc_free_host_resources(struct nlm_host *); @@ -303,10 +304,15 @@ void nlmsvc_invalidate_all(void); int nlmsvc_unlock_all_by_sb(struct super_block *sb); int nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr); +static inline struct file *nlmsvc_file_file(struct nlm_file *file) +{ + return file->f_file[O_RDONLY] ? + file->f_file[O_RDONLY] : file->f_file[O_WRONLY]; +} + static inline struct inode *nlmsvc_file_inode(struct nlm_file *file) { - return locks_inode(file->f_file[O_RDONLY] ? - file->f_file[O_RDONLY] : file->f_file[O_WRONLY]); + return locks_inode(nlmsvc_file_file(file)); } static inline int __nlm_privileged_request4(const struct sockaddr *sap) diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index bed63156b052..67e4a2c5500b 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -98,18 +98,19 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); -int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *); -int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *); -int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_res(struct svc_rqst *, __be32 *); -int nlmsvc_decode_res(struct svc_rqst *, __be32 *); -int nlmsvc_encode_void(struct svc_rqst *, __be32 *); -int nlmsvc_decode_void(struct svc_rqst *, __be32 *); -int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); -int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); -int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); +bool nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); + +bool nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); #endif /* LOCKD_XDR_H */ diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 025250ade98e..72831e35dca3 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -22,22 +22,21 @@ #define nlm4_fbig cpu_to_be32(NLM_FBIG) #define nlm4_failed cpu_to_be32(NLM_FAILED) - - void nlm4svc_set_file_lock_range(struct file_lock *fl, u64 off, u64 len); -int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); -int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *); -int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *); -int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_res(struct svc_rqst *, __be32 *); -int nlm4svc_decode_res(struct svc_rqst *, __be32 *); -int nlm4svc_encode_void(struct svc_rqst *, __be32 *); -int nlm4svc_decode_void(struct svc_rqst *, __be32 *); -int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); -int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); -int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); +bool nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); + +bool nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); extern const struct rpc_version nlm_version4; diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 5433c08fcc68..1aea34b8f19b 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -52,6 +52,23 @@ #define max(x, y) __careful_cmp(x, y, >) /** + * umin - return minimum of two non-negative values + * Signed types are zero extended to match a larger unsigned type. + * @x: first value + * @y: second value + */ +#define umin(x, y) \ + __careful_cmp((x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull, <) + +/** + * umax - return maximum of two non-negative values + * @x: first value + * @y: second value + */ +#define umax(x, y) \ + __careful_cmp((x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull, >) + +/** * min3 - return minimum of three values * @x: first value * @y: second value diff --git a/include/linux/module.h b/include/linux/module.h index 701c150485b2..fb9762e16f28 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -595,9 +595,9 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); -extern void __noreturn __module_put_and_exit(struct module *mod, +extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); -#define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) +#define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD int module_refcount(struct module *mod); @@ -790,7 +790,7 @@ static inline int unregister_module_notifier(struct notifier_block *nb) return 0; } -#define module_put_and_exit(code) do_exit(code) +#define module_put_and_kthread_exit(code) kthread_exit(code) static inline void print_modules(void) { diff --git a/include/linux/nfs.h b/include/linux/nfs.h index 0dc7ad38a0da..b06375e88e58 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -36,14 +36,6 @@ static inline void nfs_copy_fh(struct nfs_fh *target, const struct nfs_fh *sourc memcpy(target->data, source->data, source->size); } - -/* - * This is really a general kernel constant, but since nothing like - * this is defined in the kernel headers, I have to do it here. - */ -#define NFS_OFFSET_MAX ((__s64)((~(__u64)0) >> 1)) - - enum nfs3_stable_how { NFS_UNSTABLE = 0, NFS_DATA_SYNC = 1, diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 15004c469807..8e2b532919e0 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -292,6 +292,10 @@ enum nfsstat4 { NFS4ERR_XATTR2BIG = 10096, }; +/* error codes for internal client use */ +#define NFS4ERR_RESET_TO_MDS 12001 +#define NFS4ERR_RESET_TO_PNFS 12002 + static inline bool seqid_mutating_err(u32 err) { /* See RFC 7530, section 9.1.7 */ @@ -726,4 +730,17 @@ enum nfs4_setxattr_options { SETXATTR4_CREATE = 1, SETXATTR4_REPLACE = 2, }; + +enum { + RCA4_TYPE_MASK_RDATA_DLG = 0, + RCA4_TYPE_MASK_WDATA_DLG = 1, + RCA4_TYPE_MASK_DIR_DLG = 2, + RCA4_TYPE_MASK_FILE_LAYOUT = 3, + RCA4_TYPE_MASK_BLK_LAYOUT = 4, + RCA4_TYPE_MASK_OBJ_LAYOUT_MIN = 8, + RCA4_TYPE_MASK_OBJ_LAYOUT_MAX = 9, + RCA4_TYPE_MASK_OTHER_LAYOUT_MIN = 12, + RCA4_TYPE_MASK_OTHER_LAYOUT_MAX = 15, +}; + #endif diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 5ddc30405f7f..886bfa99a6af 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -588,6 +588,7 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline int diff --git a/include/linux/nfs_ssc.h b/include/linux/nfs_ssc.h index 222ae8883e85..22265b1ff080 100644 --- a/include/linux/nfs_ssc.h +++ b/include/linux/nfs_ssc.h @@ -53,6 +53,7 @@ static inline void nfs42_ssc_close(struct file *filep) if (nfs_ssc_client_tbl.ssc_nfs4_ops) (*nfs_ssc_client_tbl.ssc_nfs4_ops->sco_close)(filep); } +#endif struct nfsd4_ssc_umount_item { struct list_head nsui_list; @@ -64,9 +65,8 @@ struct nfsd4_ssc_umount_item { refcount_t nsui_refcnt; unsigned long nsui_expire; struct vfsmount *nsui_vfsmount; - char nsui_ipaddr[RPC_MAX_ADDRBUFLEN]; + char nsui_ipaddr[RPC_MAX_ADDRBUFLEN + 1]; }; -#endif /* * NFS_FS diff --git a/include/linux/pci.h b/include/linux/pci.h index 08d26b58f95c..25e2e7756b1d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -455,6 +455,7 @@ struct pci_dev { unsigned int link_active_reporting:1;/* Device capable of reporting link active */ unsigned int no_vf_scan:1; /* Don't scan for VFs after IOV enablement */ unsigned int no_command_memory:1; /* No PCI_COMMAND_MEMORY */ + unsigned int rom_bar_overlap:1; /* ROM BAR disable broken */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ diff --git a/include/linux/phy/tegra/xusb.h b/include/linux/phy/tegra/xusb.h index 3a35e74cdc61..b30343a1f47e 100644 --- a/include/linux/phy/tegra/xusb.h +++ b/include/linux/phy/tegra/xusb.h @@ -24,6 +24,7 @@ int tegra_xusb_padctl_set_vbus_override(struct tegra_xusb_padctl *padctl, int tegra_phy_xusb_utmi_port_reset(struct phy *phy); int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl, unsigned int port); +int tegra_xusb_padctl_get_port_number(struct phy *phy); int tegra_xusb_padctl_enable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy, enum usb_device_speed speed); int tegra_xusb_padctl_disable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy); diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index d373f1bcbf7c..5d52d15faee0 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -58,7 +58,7 @@ DECLARE_PER_CPU(u32, kstack_offset); if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ u32 offset = raw_cpu_read(kstack_offset); \ - offset ^= (rand); \ + offset = ror32(offset, 5) ^ (rand); \ raw_cpu_write(kstack_offset, offset); \ } \ } while (0) diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 3c7d295746f6..3e7bfc0f65ae 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -98,6 +98,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) +typedef bool (*ring_buffer_cond_fn)(void *data); int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full); diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 988528b5da43..48ffe325184c 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -14,10 +14,10 @@ static inline bool page_is_secretmem(struct page *page) * Using page_mapping() is quite slow because of the actual call * instruction and repeated compound_head(page) inside the * page_mapping() function. - * We know that secretmem pages are not compound and LRU so we can + * We know that secretmem pages are not compound, so we can * save a couple of cycles here. */ - if (PageCompound(page) || !PageLRU(page)) + if (PageCompound(page)) return false; mapping = (struct address_space *) diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index ba047a145e09..f5fe330e4f4d 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -199,7 +199,7 @@ struct rpc_wait_queue { unsigned char maxpriority; /* maximum priority (0 if queue is not a priority queue) */ unsigned char priority; /* current priority */ unsigned char nr; /* # tasks remaining for cookie */ - unsigned short qlen; /* total # tasks waiting in queue */ + unsigned int qlen; /* total # tasks waiting in queue */ struct rpc_timer timer_list; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) const char * name; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 664a54e330af..6e48c1c88f1b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -52,25 +52,6 @@ struct svc_pool { unsigned long sp_flags; } ____cacheline_aligned_in_smp; -struct svc_serv; - -struct svc_serv_ops { - /* Callback to use when last thread exits. */ - void (*svo_shutdown)(struct svc_serv *, struct net *); - - /* function for service threads to run */ - int (*svo_function)(void *); - - /* queue up a transport for servicing */ - void (*svo_enqueue_xprt)(struct svc_xprt *); - - /* set up thread (or whatever) execution context */ - int (*svo_setup)(struct svc_serv *, struct svc_pool *, int); - - /* optional module to count when adding threads (pooled svcs only) */ - struct module *svo_module; -}; - /* * RPC service. * @@ -85,6 +66,7 @@ struct svc_serv { struct svc_program * sv_program; /* RPC program */ struct svc_stat * sv_stats; /* RPC statistics */ spinlock_t sv_lock; + struct kref sv_refcnt; unsigned int sv_nrthreads; /* # of server threads */ unsigned int sv_maxconn; /* max connections allowed or * '0' causing max to be based @@ -102,7 +84,8 @@ struct svc_serv { unsigned int sv_nrpools; /* number of thread pools */ struct svc_pool * sv_pools; /* array of thread pools */ - const struct svc_serv_ops *sv_ops; /* server operations */ + int (*sv_threadfn)(void *data); + #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct list_head sv_cb_list; /* queue for callback requests * that arrive over the same @@ -114,15 +97,30 @@ struct svc_serv { #endif /* CONFIG_SUNRPC_BACKCHANNEL */ }; -/* - * We use sv_nrthreads as a reference count. svc_destroy() drops - * this refcount, so we need to bump it up around operations that - * change the number of threads. Horrible, but there it is. - * Should be called with the "service mutex" held. +/** + * svc_get() - increment reference count on a SUNRPC serv + * @serv: the svc_serv to have count incremented + * + * Returns: the svc_serv that was passed in. + */ +static inline struct svc_serv *svc_get(struct svc_serv *serv) +{ + kref_get(&serv->sv_refcnt); + return serv; +} + +void svc_destroy(struct kref *); + +/** + * svc_put - decrement reference count on a SUNRPC serv + * @serv: the svc_serv to have count decremented + * + * When the reference count reaches zero, svc_destroy() + * is called to clean up and free the serv. */ -static inline void svc_get(struct svc_serv *serv) +static inline void svc_put(struct svc_serv *serv) { - serv->sv_nrthreads++; + kref_put(&serv->sv_refcnt, svc_destroy); } /* @@ -456,12 +454,15 @@ struct svc_procedure { /* process the request: */ __be32 (*pc_func)(struct svc_rqst *); /* XDR decode args: */ - int (*pc_decode)(struct svc_rqst *, __be32 *data); + bool (*pc_decode)(struct svc_rqst *rqstp, + struct xdr_stream *xdr); /* XDR encode result: */ - int (*pc_encode)(struct svc_rqst *, __be32 *data); + bool (*pc_encode)(struct svc_rqst *rqstp, + struct xdr_stream *xdr); /* XDR free result: */ void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ + unsigned int pc_argzero; /* how much of argument to clear */ unsigned int pc_ressize; /* result struct size */ unsigned int pc_cachetype; /* cache info (NFS) */ unsigned int pc_xdrressize; /* maximum size of XDR reply */ @@ -469,53 +470,23 @@ struct svc_procedure { }; /* - * Mode for mapping cpus to pools. - */ -enum { - SVC_POOL_AUTO = -1, /* choose one of the others */ - SVC_POOL_GLOBAL, /* no mapping, just a single global pool - * (legacy & UP mode) */ - SVC_POOL_PERCPU, /* one pool per cpu */ - SVC_POOL_PERNODE /* one pool per numa node */ -}; - -struct svc_pool_map { - int count; /* How many svc_servs use us */ - int mode; /* Note: int not enum to avoid - * warnings about "enumeration value - * not handled in switch" */ - unsigned int npools; - unsigned int *pool_to; /* maps pool id to cpu or node */ - unsigned int *to_pool; /* maps cpu or node to pool id */ -}; - -extern struct svc_pool_map svc_pool_map; - -/* * Function prototypes. */ int svc_rpcb_setup(struct svc_serv *serv, struct net *net); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net); int svc_bind(struct svc_serv *serv, struct net *net); struct svc_serv *svc_create(struct svc_program *, unsigned int, - const struct svc_serv_ops *); + int (*threadfn)(void *data)); struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); -struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, - struct svc_pool *pool, int node); void svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); -unsigned int svc_pool_map_get(void); -void svc_pool_map_put(void); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, - const struct svc_serv_ops *); + int (*threadfn)(void *data)); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); -int svc_set_num_threads_sync(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); -void svc_destroy(struct svc_serv *); -void svc_shutdown_net(struct svc_serv *, struct net *); int svc_process(struct svc_rqst *); int bc_svc_process(struct svc_serv *, struct rpc_rqst *, struct svc_rqst *); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 154eee6bc6a0..1f7368f5b4e7 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -127,15 +127,16 @@ int svc_reg_xprt_class(struct svc_xprt_class *); void svc_unreg_xprt_class(struct svc_xprt_class *); void svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *, struct svc_serv *); -int svc_create_xprt(struct svc_serv *, const char *, struct net *, - const int, const unsigned short, int, - const struct cred *); +int svc_xprt_create(struct svc_serv *serv, const char *xprt_name, + struct net *net, const int family, + const unsigned short port, int flags, + const struct cred *cred); +void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net); void svc_xprt_received(struct svc_xprt *xprt); -void svc_xprt_do_enqueue(struct svc_xprt *xprt); void svc_xprt_enqueue(struct svc_xprt *xprt); void svc_xprt_put(struct svc_xprt *xprt); void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt); -void svc_close_xprt(struct svc_xprt *xprt); +void svc_xprt_close(struct svc_xprt *xprt); int svc_port_is_privileged(struct sockaddr *sin); int svc_print_xprts(char *buf, int maxlen); struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index bcc555c7ae9c..13aff355d5a1 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -59,10 +59,9 @@ int svc_recv(struct svc_rqst *, long); int svc_send(struct svc_rqst *); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); -bool svc_alien_sock(struct net *net, int fd); -int svc_addsock(struct svc_serv *serv, const int fd, - char *name_return, const size_t len, - const struct cred *cred); +int svc_addsock(struct svc_serv *serv, struct net *net, + const int fd, char *name_return, const size_t len, + const struct cred *cred); void svc_init_xprt_sock(void); void svc_cleanup_xprt_sock(void); struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot); diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 3a2c714d6b62..98e197376a0d 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -240,6 +240,8 @@ typedef int (*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, struct rpc_rqst *rqst); +extern void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, + struct page **pages, struct rpc_rqst *rqst); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes); diff --git a/include/linux/timer.h b/include/linux/timer.h index fda13c9d1256..e78521bce565 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -183,12 +183,20 @@ extern int timer_reduce(struct timer_list *timer, unsigned long expires); extern void add_timer(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); +extern int timer_delete_sync(struct timer_list *timer); -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) - extern int del_timer_sync(struct timer_list *timer); -#else -# define del_timer_sync(t) del_timer(t) -#endif +/** + * del_timer_sync - Delete a pending timer and wait for a running callback + * @timer: The timer to be deleted + * + * See timer_delete_sync() for detailed explanation. + * + * Do not use in new code. Use timer_delete_sync() instead. + */ +static inline int del_timer_sync(struct timer_list *timer) +{ + return timer_delete_sync(timer); +} #define del_singleshot_timer_sync(t) del_timer_sync(t) diff --git a/include/linux/udp.h b/include/linux/udp.h index 0727276e7538..fdf5afb39316 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -132,6 +132,24 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, } } +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); +#if IS_ENABLED(CONFIG_IPV6) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +#endif + +static inline bool udp_encap_needed(void) +{ + if (static_branch_unlikely(&udp_encap_needed_key)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (static_branch_unlikely(&udpv6_encap_needed_key)) + return true; +#endif + + return false; +} + static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) { if (!skb_is_gso(skb)) @@ -143,6 +161,16 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_sk(sk)->accept_udp_fraglist) return true; + /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still + * land in a tunnel as the socket check in udp_gro_receive cannot be + * foolproof. + */ + if (udp_encap_needed() && + READ_ONCE(udp_sk(sk)->encap_rcv) && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))) + return true; + return false; } diff --git a/include/linux/vfio.h b/include/linux/vfio.h index b53a9557884a..b7275ed44e4c 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -243,6 +243,7 @@ struct virqfd { wait_queue_entry_t wait; poll_table pt; struct work_struct shutdown; + struct work_struct flush_inject; struct virqfd **pvirqfd; }; @@ -251,5 +252,6 @@ extern int vfio_virqfd_enable(void *opaque, void (*thread)(void *, void *), void *data, struct virqfd **pvirqfd, int fd); extern void vfio_virqfd_disable(struct virqfd **pvirqfd); +void vfio_virqfd_flush_thread(struct virqfd **pvirqfd); #endif /* VFIO_H */ diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 6ed07844eb24..5290781abba3 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -257,6 +257,7 @@ struct ieee802154_llsec_key { struct ieee802154_llsec_key_entry { struct list_head list; + struct rcu_head rcu; struct ieee802154_llsec_key_id id; struct ieee802154_llsec_key *key; diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 798aad21694e..b6b7e210f9d7 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -169,6 +169,7 @@ void inet_csk_init_xmit_timers(struct sock *sk, void (*delack_handler)(struct timer_list *), void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); +void inet_csk_clear_xmit_timers_sync(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) { diff --git a/include/net/sock.h b/include/net/sock.h index e19eebaf59f7..44ebec3fdda6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1751,6 +1751,13 @@ static inline void sock_owned_by_me(const struct sock *sk) #endif } +static inline void sock_not_owned_by_me(const struct sock *sk) +{ +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks); +#endif +} + static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h index 59eeba31c192..0d3d6beb7fdb 100644 --- a/include/soc/fsl/qman.h +++ b/include/soc/fsl/qman.h @@ -1172,6 +1172,15 @@ int qman_delete_cgr(struct qman_cgr *cgr); void qman_delete_cgr_safe(struct qman_cgr *cgr); /** + * qman_update_cgr_safe - Modifies a congestion group object from any CPU + * @cgr: the 'cgr' object to modify + * @opts: state of the CGR settings + * + * This will select the proper CPU and modify the CGR settings. + */ +int qman_update_cgr_safe(struct qman_cgr *cgr, struct qm_mcc_initcgr *opts); + +/** * qman_query_cgr_congested - Queries CGR's congestion status * @cgr: the 'cgr' object to query * @result: returns 'cgr's congestion status, 1 (true) if congested diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index b2a2672e6632..b8fd13303ee7 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -13,6 +13,8 @@ #include <linux/tracepoint.h> +#include <trace/misc/sunrpc.h> + /** ** GSS-API related trace events **/ @@ -99,7 +101,7 @@ DECLARE_EVENT_CLASS(rpcgss_gssapi_event, __entry->maj_stat = maj_stat; ), - TP_printk("task:%u@%u maj_stat=%s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " maj_stat=%s", __entry->task_id, __entry->client_id, __entry->maj_stat == 0 ? "GSS_S_COMPLETE" : show_gss_status(__entry->maj_stat)) @@ -332,7 +334,8 @@ TRACE_EVENT(rpcgss_unwrap_failed, __entry->client_id = task->tk_client->cl_clid; ), - TP_printk("task:%u@%u", __entry->task_id, __entry->client_id) + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER, + __entry->task_id, __entry->client_id) ); TRACE_EVENT(rpcgss_bad_seqno, @@ -358,7 +361,8 @@ TRACE_EVENT(rpcgss_bad_seqno, __entry->received = received; ), - TP_printk("task:%u@%u expected seqno %u, received seqno %u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " expected seqno %u, received seqno %u", __entry->task_id, __entry->client_id, __entry->expected, __entry->received) ); @@ -386,7 +390,7 @@ TRACE_EVENT(rpcgss_seqno, __entry->seqno = rqst->rq_seqno; ), - TP_printk("task:%u@%u xid=0x%08x seqno=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x seqno=%u", __entry->task_id, __entry->client_id, __entry->xid, __entry->seqno) ); @@ -418,7 +422,8 @@ TRACE_EVENT(rpcgss_need_reencode, __entry->ret = ret; ), - TP_printk("task:%u@%u xid=0x%08x rq_seqno=%u seq_xmit=%u reencode %sneeded", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x rq_seqno=%u seq_xmit=%u reencode %sneeded", __entry->task_id, __entry->client_id, __entry->xid, __entry->seqno, __entry->seq_xmit, __entry->ret ? "" : "un") @@ -452,7 +457,8 @@ TRACE_EVENT(rpcgss_update_slack, __entry->verfsize = auth->au_verfsize; ), - TP_printk("task:%u@%u xid=0x%08x auth=%p rslack=%u ralign=%u verfsize=%u\n", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x auth=%p rslack=%u ralign=%u verfsize=%u\n", __entry->task_id, __entry->client_id, __entry->xid, __entry->auth, __entry->rslack, __entry->ralign, __entry->verfsize) diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index de4195499592..513c09774e4f 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -14,7 +14,9 @@ #include <linux/sunrpc/rpc_rdma_cid.h> #include <linux/tracepoint.h> #include <rdma/ib_cm.h> -#include <trace/events/rdma.h> + +#include <trace/misc/rdma.h> +#include <trace/misc/sunrpc.h> /** ** Event classes @@ -279,7 +281,8 @@ DECLARE_EVENT_CLASS(xprtrdma_rdch_event, __entry->nsegs = nsegs; ), - TP_printk("task:%u@%u pos=%u %u@0x%016llx:0x%08x (%s)", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " pos=%u %u@0x%016llx:0x%08x (%s)", __entry->task_id, __entry->client_id, __entry->pos, __entry->length, (unsigned long long)__entry->offset, __entry->handle, @@ -326,7 +329,8 @@ DECLARE_EVENT_CLASS(xprtrdma_wrch_event, __entry->nsegs = nsegs; ), - TP_printk("task:%u@%u %u@0x%016llx:0x%08x (%s)", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " %u@0x%016llx:0x%08x (%s)", __entry->task_id, __entry->client_id, __entry->length, (unsigned long long)__entry->offset, __entry->handle, @@ -387,7 +391,8 @@ DECLARE_EVENT_CLASS(xprtrdma_mr_class, __entry->dir = mr->mr_dir; ), - TP_printk("task:%u@%u mr.id=%u nents=%d %u@0x%016llx:0x%08x (%s)", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " mr.id=%u nents=%d %u@0x%016llx:0x%08x (%s)", __entry->task_id, __entry->client_id, __entry->mr_id, __entry->nents, __entry->length, (unsigned long long)__entry->offset, __entry->handle, @@ -630,9 +635,9 @@ TRACE_EVENT(xprtrdma_nomrs_err, __assign_str(port, rpcrdma_portstr(r_xprt)); ), - TP_printk("peer=[%s]:%s task:%u@%u", - __get_str(addr), __get_str(port), - __entry->task_id, __entry->client_id + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " peer=[%s]:%s", + __entry->task_id, __entry->client_id, + __get_str(addr), __get_str(port) ) ); @@ -693,7 +698,8 @@ TRACE_EVENT(xprtrdma_marshal, __entry->wtype = wtype; ), - TP_printk("task:%u@%u xid=0x%08x: hdr=%u xdr=%u/%u/%u %s/%s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x hdr=%u xdr=%u/%u/%u %s/%s", __entry->task_id, __entry->client_id, __entry->xid, __entry->hdrlen, __entry->headlen, __entry->pagelen, __entry->taillen, @@ -723,7 +729,7 @@ TRACE_EVENT(xprtrdma_marshal_failed, __entry->ret = ret; ), - TP_printk("task:%u@%u xid=0x%08x: ret=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x ret=%d", __entry->task_id, __entry->client_id, __entry->xid, __entry->ret ) @@ -750,7 +756,7 @@ TRACE_EVENT(xprtrdma_prepsend_failed, __entry->ret = ret; ), - TP_printk("task:%u@%u xid=0x%08x: ret=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x ret=%d", __entry->task_id, __entry->client_id, __entry->xid, __entry->ret ) @@ -785,7 +791,7 @@ TRACE_EVENT(xprtrdma_post_send, __entry->signaled = req->rl_wr.send_flags & IB_SEND_SIGNALED; ), - TP_printk("task:%u@%u cq.id=%u cid=%d (%d SGE%s) %s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " cq.id=%u cid=%d (%d SGE%s) %s", __entry->task_id, __entry->client_id, __entry->cq_id, __entry->completion_id, __entry->num_sge, (__entry->num_sge == 1 ? "" : "s"), @@ -820,7 +826,7 @@ TRACE_EVENT(xprtrdma_post_send_err, __entry->rc = rc; ), - TP_printk("task:%u@%u cq.id=%u rc=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " cq.id=%u rc=%d", __entry->task_id, __entry->client_id, __entry->cq_id, __entry->rc ) @@ -932,7 +938,7 @@ TRACE_EVENT(xprtrdma_post_linv_err, __entry->status = status; ), - TP_printk("task:%u@%u status=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " status=%d", __entry->task_id, __entry->client_id, __entry->status ) ); @@ -1120,7 +1126,7 @@ TRACE_EVENT(xprtrdma_reply, __entry->credits = credits; ), - TP_printk("task:%u@%u xid=0x%08x credits=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x credits=%u", __entry->task_id, __entry->client_id, __entry->xid, __entry->credits ) @@ -1156,7 +1162,7 @@ TRACE_EVENT(xprtrdma_err_vers, __entry->max = be32_to_cpup(max); ), - TP_printk("task:%u@%u xid=0x%08x versions=[%u, %u]", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x versions=[%u, %u]", __entry->task_id, __entry->client_id, __entry->xid, __entry->min, __entry->max ) @@ -1181,7 +1187,7 @@ TRACE_EVENT(xprtrdma_err_chunk, __entry->xid = be32_to_cpu(rqst->rq_xid); ), - TP_printk("task:%u@%u xid=0x%08x", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x", __entry->task_id, __entry->client_id, __entry->xid ) ); @@ -1207,7 +1213,7 @@ TRACE_EVENT(xprtrdma_err_unrecognized, __entry->procedure = be32_to_cpup(procedure); ), - TP_printk("task:%u@%u xid=0x%08x procedure=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x procedure=%u", __entry->task_id, __entry->client_id, __entry->xid, __entry->procedure ) @@ -1239,7 +1245,7 @@ TRACE_EVENT(xprtrdma_fixup, __entry->taillen = rqst->rq_rcv_buf.tail[0].iov_len; ), - TP_printk("task:%u@%u fixup=%lu xdr=%zu/%u/%zu", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " fixup=%lu xdr=%zu/%u/%zu", __entry->task_id, __entry->client_id, __entry->fixup, __entry->headlen, __entry->pagelen, __entry->taillen ) @@ -1289,7 +1295,7 @@ TRACE_EVENT(xprtrdma_mrs_zap, __entry->client_id = task->tk_client->cl_clid; ), - TP_printk("task:%u@%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER, __entry->task_id, __entry->client_id ) ); diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index f09bbb6c918e..e8eb83315f4f 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -14,6 +14,8 @@ #include <linux/net.h> #include <linux/tracepoint.h> +#include <trace/misc/sunrpc.h> + TRACE_DEFINE_ENUM(SOCK_STREAM); TRACE_DEFINE_ENUM(SOCK_DGRAM); TRACE_DEFINE_ENUM(SOCK_RAW); @@ -78,7 +80,8 @@ DECLARE_EVENT_CLASS(rpc_xdr_buf_class, __entry->msg_len = xdr->len; ), - TP_printk("task:%u@%u head=[%p,%zu] page=%u tail=[%p,%zu] len=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " head=[%p,%zu] page=%u tail=[%p,%zu] len=%u", __entry->task_id, __entry->client_id, __entry->head_base, __entry->head_len, __entry->page_len, __entry->tail_base, __entry->tail_len, __entry->msg_len @@ -114,7 +117,7 @@ DECLARE_EVENT_CLASS(rpc_clnt_class, __entry->client_id = clnt->cl_clid; ), - TP_printk("clid=%u", __entry->client_id) + TP_printk("client=" SUNRPC_TRACE_CLID_SPECIFIER, __entry->client_id) ); #define DEFINE_RPC_CLNT_EVENT(name) \ @@ -158,7 +161,8 @@ TRACE_EVENT(rpc_clnt_new, __assign_str(server, server); ), - TP_printk("client=%u peer=[%s]:%s program=%s server=%s", + TP_printk("client=" SUNRPC_TRACE_CLID_SPECIFIER + " peer=[%s]:%s program=%s server=%s", __entry->client_id, __get_str(addr), __get_str(port), __get_str(program), __get_str(server)) ); @@ -206,7 +210,8 @@ TRACE_EVENT(rpc_clnt_clone_err, __entry->error = error; ), - TP_printk("client=%u error=%d", __entry->client_id, __entry->error) + TP_printk("client=" SUNRPC_TRACE_CLID_SPECIFIER " error=%d", + __entry->client_id, __entry->error) ); @@ -248,7 +253,7 @@ DECLARE_EVENT_CLASS(rpc_task_status, __entry->status = task->tk_status; ), - TP_printk("task:%u@%u status=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " status=%d", __entry->task_id, __entry->client_id, __entry->status) ); @@ -288,7 +293,7 @@ TRACE_EVENT(rpc_request, __assign_str(procname, rpc_proc_name(task)); ), - TP_printk("task:%u@%u %sv%d %s (%ssync)", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " %sv%d %s (%ssync)", __entry->task_id, __entry->client_id, __get_str(progname), __entry->version, __get_str(procname), __entry->async ? "a": "" @@ -348,7 +353,8 @@ DECLARE_EVENT_CLASS(rpc_task_running, __entry->flags = task->tk_flags; ), - TP_printk("task:%u@%d flags=%s runstate=%s status=%d action=%ps", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " flags=%s runstate=%s status=%d action=%ps", __entry->task_id, __entry->client_id, rpc_show_task_flags(__entry->flags), rpc_show_runstate(__entry->runstate), @@ -400,7 +406,8 @@ DECLARE_EVENT_CLASS(rpc_task_queued, __assign_str(q_name, rpc_qname(q)); ), - TP_printk("task:%u@%d flags=%s runstate=%s status=%d timeout=%lu queue=%s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " flags=%s runstate=%s status=%d timeout=%lu queue=%s", __entry->task_id, __entry->client_id, rpc_show_task_flags(__entry->flags), rpc_show_runstate(__entry->runstate), @@ -436,7 +443,7 @@ DECLARE_EVENT_CLASS(rpc_failure, __entry->client_id = task->tk_client->cl_clid; ), - TP_printk("task:%u@%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER, __entry->task_id, __entry->client_id) ); @@ -478,7 +485,8 @@ DECLARE_EVENT_CLASS(rpc_reply_event, __assign_str(servername, task->tk_xprt->servername); ), - TP_printk("task:%u@%d server=%s xid=0x%08x %sv%d %s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " server=%s xid=0x%08x %sv%d %s", __entry->task_id, __entry->client_id, __get_str(servername), __entry->xid, __get_str(progname), __entry->version, __get_str(procname)) @@ -538,7 +546,8 @@ TRACE_EVENT(rpc_buf_alloc, __entry->status = status; ), - TP_printk("task:%u@%u callsize=%zu recvsize=%zu status=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " callsize=%zu recvsize=%zu status=%d", __entry->task_id, __entry->client_id, __entry->callsize, __entry->recvsize, __entry->status ) @@ -567,7 +576,8 @@ TRACE_EVENT(rpc_call_rpcerror, __entry->rpc_status = rpc_status; ), - TP_printk("task:%u@%u tk_status=%d rpc_status=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " tk_status=%d rpc_status=%d", __entry->task_id, __entry->client_id, __entry->tk_status, __entry->rpc_status) ); @@ -607,7 +617,8 @@ TRACE_EVENT(rpc_stats_latency, __entry->execute = ktime_to_us(execute); ), - TP_printk("task:%u@%d xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu", __entry->task_id, __entry->client_id, __entry->xid, __get_str(progname), __entry->version, __get_str(procname), __entry->backlog, __entry->rtt, __entry->execute) @@ -651,8 +662,8 @@ TRACE_EVENT(rpc_xdr_overflow, __entry->version = task->tk_client->cl_vers; __assign_str(procedure, task->tk_msg.rpc_proc->p_name); } else { - __entry->task_id = 0; - __entry->client_id = 0; + __entry->task_id = -1; + __entry->client_id = -1; __assign_str(progname, "unknown"); __entry->version = 0; __assign_str(procedure, "unknown"); @@ -668,8 +679,8 @@ TRACE_EVENT(rpc_xdr_overflow, __entry->len = xdr->buf->len; ), - TP_printk( - "task:%u@%u %sv%d %s requested=%zu p=%p end=%p xdr=[%p,%zu]/%u/[%p,%zu]/%u\n", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " %sv%d %s requested=%zu p=%p end=%p xdr=[%p,%zu]/%u/[%p,%zu]/%u\n", __entry->task_id, __entry->client_id, __get_str(progname), __entry->version, __get_str(procedure), __entry->requested, __entry->p, __entry->end, @@ -727,8 +738,8 @@ TRACE_EVENT(rpc_xdr_alignment, __entry->len = xdr->buf->len; ), - TP_printk( - "task:%u@%u %sv%d %s offset=%zu copied=%u xdr=[%p,%zu]/%u/[%p,%zu]/%u\n", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " %sv%d %s offset=%zu copied=%u xdr=[%p,%zu]/%u/[%p,%zu]/%u\n", __entry->task_id, __entry->client_id, __get_str(progname), __entry->version, __get_str(procedure), __entry->offset, __entry->copied, @@ -917,7 +928,8 @@ TRACE_EVENT(rpc_socket_nospace, __entry->remaining = rqst->rq_slen - transport->xmit.offset; ), - TP_printk("task:%u@%u total=%u remaining=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " total=%u remaining=%u", __entry->task_id, __entry->client_id, __entry->total, __entry->remaining ) @@ -1042,8 +1054,8 @@ TRACE_EVENT(xprt_transmit, __entry->status = status; ), - TP_printk( - "task:%u@%u xid=0x%08x seqno=%u status=%d", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x seqno=%u status=%d", __entry->task_id, __entry->client_id, __entry->xid, __entry->seqno, __entry->status) ); @@ -1082,8 +1094,8 @@ TRACE_EVENT(xprt_retransmit, __assign_str(procname, rpc_proc_name(task)); ), - TP_printk( - "task:%u@%u xid=0x%08x %sv%d %s ntrans=%d timeout=%lu", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " xid=0x%08x %sv%d %s ntrans=%d timeout=%lu", __entry->task_id, __entry->client_id, __entry->xid, __get_str(progname), __entry->version, __get_str(procname), __entry->ntrans, __entry->timeout @@ -1140,7 +1152,8 @@ DECLARE_EVENT_CLASS(xprt_writelock_event, __entry->snd_task_id = -1; ), - TP_printk("task:%u@%u snd_task:%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " snd_task:" SUNRPC_TRACE_PID_SPECIFIER, __entry->task_id, __entry->client_id, __entry->snd_task_id) ); @@ -1192,7 +1205,9 @@ DECLARE_EVENT_CLASS(xprt_cong_event, __entry->wait = test_bit(XPRT_CWND_WAIT, &xprt->state); ), - TP_printk("task:%u@%u snd_task:%u cong=%lu cwnd=%lu%s", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " snd_task:" SUNRPC_TRACE_PID_SPECIFIER + " cong=%lu cwnd=%lu%s", __entry->task_id, __entry->client_id, __entry->snd_task_id, __entry->cong, __entry->cwnd, __entry->wait ? " (wait)" : "") @@ -1230,7 +1245,7 @@ TRACE_EVENT(xprt_reserve, __entry->xid = be32_to_cpu(rqst->rq_xid); ), - TP_printk("task:%u@%u xid=0x%08x", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x", __entry->task_id, __entry->client_id, __entry->xid ) ); @@ -1319,7 +1334,8 @@ TRACE_EVENT(rpcb_getport, __assign_str(servername, task->tk_xprt->servername); ), - TP_printk("task:%u@%u server=%s program=%u version=%u protocol=%d bind_version=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER + " server=%s program=%u version=%u protocol=%d bind_version=%u", __entry->task_id, __entry->client_id, __get_str(servername), __entry->program, __entry->version, __entry->protocol, __entry->bind_version @@ -1349,7 +1365,7 @@ TRACE_EVENT(rpcb_setport, __entry->port = port; ), - TP_printk("task:%u@%u status=%d port=%u", + TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " status=%d port=%u", __entry->task_id, __entry->client_id, __entry->status, __entry->port ) diff --git a/include/trace/misc/fs.h b/include/trace/misc/fs.h new file mode 100644 index 000000000000..738b97f22f36 --- /dev/null +++ b/include/trace/misc/fs.h @@ -0,0 +1,122 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Display helpers for generic filesystem items + * + * Author: Chuck Lever <chuck.lever@oracle.com> + * + * Copyright (c) 2020, Oracle and/or its affiliates. + */ + +#include <linux/fs.h> + +#define show_fs_dirent_type(x) \ + __print_symbolic(x, \ + { DT_UNKNOWN, "UNKNOWN" }, \ + { DT_FIFO, "FIFO" }, \ + { DT_CHR, "CHR" }, \ + { DT_DIR, "DIR" }, \ + { DT_BLK, "BLK" }, \ + { DT_REG, "REG" }, \ + { DT_LNK, "LNK" }, \ + { DT_SOCK, "SOCK" }, \ + { DT_WHT, "WHT" }) + +#define show_fs_fcntl_open_flags(x) \ + __print_flags(x, "|", \ + { O_WRONLY, "O_WRONLY" }, \ + { O_RDWR, "O_RDWR" }, \ + { O_CREAT, "O_CREAT" }, \ + { O_EXCL, "O_EXCL" }, \ + { O_NOCTTY, "O_NOCTTY" }, \ + { O_TRUNC, "O_TRUNC" }, \ + { O_APPEND, "O_APPEND" }, \ + { O_NONBLOCK, "O_NONBLOCK" }, \ + { O_DSYNC, "O_DSYNC" }, \ + { O_DIRECT, "O_DIRECT" }, \ + { O_LARGEFILE, "O_LARGEFILE" }, \ + { O_DIRECTORY, "O_DIRECTORY" }, \ + { O_NOFOLLOW, "O_NOFOLLOW" }, \ + { O_NOATIME, "O_NOATIME" }, \ + { O_CLOEXEC, "O_CLOEXEC" }) + +#define __fmode_flag(x) { (__force unsigned long)FMODE_##x, #x } +#define show_fs_fmode_flags(x) \ + __print_flags(x, "|", \ + __fmode_flag(READ), \ + __fmode_flag(WRITE), \ + __fmode_flag(EXEC)) + +#ifdef CONFIG_64BIT +#define show_fs_fcntl_cmd(x) \ + __print_symbolic(x, \ + { F_DUPFD, "DUPFD" }, \ + { F_GETFD, "GETFD" }, \ + { F_SETFD, "SETFD" }, \ + { F_GETFL, "GETFL" }, \ + { F_SETFL, "SETFL" }, \ + { F_GETLK, "GETLK" }, \ + { F_SETLK, "SETLK" }, \ + { F_SETLKW, "SETLKW" }, \ + { F_SETOWN, "SETOWN" }, \ + { F_GETOWN, "GETOWN" }, \ + { F_SETSIG, "SETSIG" }, \ + { F_GETSIG, "GETSIG" }, \ + { F_SETOWN_EX, "SETOWN_EX" }, \ + { F_GETOWN_EX, "GETOWN_EX" }, \ + { F_GETOWNER_UIDS, "GETOWNER_UIDS" }, \ + { F_OFD_GETLK, "OFD_GETLK" }, \ + { F_OFD_SETLK, "OFD_SETLK" }, \ + { F_OFD_SETLKW, "OFD_SETLKW" }) +#else /* CONFIG_64BIT */ +#define show_fs_fcntl_cmd(x) \ + __print_symbolic(x, \ + { F_DUPFD, "DUPFD" }, \ + { F_GETFD, "GETFD" }, \ + { F_SETFD, "SETFD" }, \ + { F_GETFL, "GETFL" }, \ + { F_SETFL, "SETFL" }, \ + { F_GETLK, "GETLK" }, \ + { F_SETLK, "SETLK" }, \ + { F_SETLKW, "SETLKW" }, \ + { F_SETOWN, "SETOWN" }, \ + { F_GETOWN, "GETOWN" }, \ + { F_SETSIG, "SETSIG" }, \ + { F_GETSIG, "GETSIG" }, \ + { F_GETLK64, "GETLK64" }, \ + { F_SETLK64, "SETLK64" }, \ + { F_SETLKW64, "SETLKW64" }, \ + { F_SETOWN_EX, "SETOWN_EX" }, \ + { F_GETOWN_EX, "GETOWN_EX" }, \ + { F_GETOWNER_UIDS, "GETOWNER_UIDS" }, \ + { F_OFD_GETLK, "OFD_GETLK" }, \ + { F_OFD_SETLK, "OFD_SETLK" }, \ + { F_OFD_SETLKW, "OFD_SETLKW" }) +#endif /* CONFIG_64BIT */ + +#define show_fs_fcntl_lock_type(x) \ + __print_symbolic(x, \ + { F_RDLCK, "RDLCK" }, \ + { F_WRLCK, "WRLCK" }, \ + { F_UNLCK, "UNLCK" }) + +#define show_fs_lookup_flags(flags) \ + __print_flags(flags, "|", \ + { LOOKUP_FOLLOW, "FOLLOW" }, \ + { LOOKUP_DIRECTORY, "DIRECTORY" }, \ + { LOOKUP_AUTOMOUNT, "AUTOMOUNT" }, \ + { LOOKUP_EMPTY, "EMPTY" }, \ + { LOOKUP_DOWN, "DOWN" }, \ + { LOOKUP_MOUNTPOINT, "MOUNTPOINT" }, \ + { LOOKUP_REVAL, "REVAL" }, \ + { LOOKUP_RCU, "RCU" }, \ + { LOOKUP_OPEN, "OPEN" }, \ + { LOOKUP_CREATE, "CREATE" }, \ + { LOOKUP_EXCL, "EXCL" }, \ + { LOOKUP_RENAME_TARGET, "RENAME_TARGET" }, \ + { LOOKUP_PARENT, "PARENT" }, \ + { LOOKUP_NO_SYMLINKS, "NO_SYMLINKS" }, \ + { LOOKUP_NO_MAGICLINKS, "NO_MAGICLINKS" }, \ + { LOOKUP_NO_XDEV, "NO_XDEV" }, \ + { LOOKUP_BENEATH, "BENEATH" }, \ + { LOOKUP_IN_ROOT, "IN_ROOT" }, \ + { LOOKUP_CACHED, "CACHED" }) diff --git a/include/trace/misc/nfs.h b/include/trace/misc/nfs.h new file mode 100644 index 000000000000..0d9d48dca38a --- /dev/null +++ b/include/trace/misc/nfs.h @@ -0,0 +1,387 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Display helpers for NFS protocol elements + * + * Author: Chuck Lever <chuck.lever@oracle.com> + * + * Copyright (c) 2020, Oracle and/or its affiliates. + */ + +#include <linux/nfs.h> +#include <linux/nfs4.h> +#include <uapi/linux/nfs.h> + +TRACE_DEFINE_ENUM(NFS_OK); +TRACE_DEFINE_ENUM(NFSERR_PERM); +TRACE_DEFINE_ENUM(NFSERR_NOENT); +TRACE_DEFINE_ENUM(NFSERR_IO); +TRACE_DEFINE_ENUM(NFSERR_NXIO); +TRACE_DEFINE_ENUM(NFSERR_EAGAIN); +TRACE_DEFINE_ENUM(NFSERR_ACCES); +TRACE_DEFINE_ENUM(NFSERR_EXIST); +TRACE_DEFINE_ENUM(NFSERR_XDEV); +TRACE_DEFINE_ENUM(NFSERR_NODEV); +TRACE_DEFINE_ENUM(NFSERR_NOTDIR); +TRACE_DEFINE_ENUM(NFSERR_ISDIR); +TRACE_DEFINE_ENUM(NFSERR_INVAL); +TRACE_DEFINE_ENUM(NFSERR_FBIG); +TRACE_DEFINE_ENUM(NFSERR_NOSPC); +TRACE_DEFINE_ENUM(NFSERR_ROFS); +TRACE_DEFINE_ENUM(NFSERR_MLINK); +TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP); +TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG); +TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY); +TRACE_DEFINE_ENUM(NFSERR_DQUOT); +TRACE_DEFINE_ENUM(NFSERR_STALE); +TRACE_DEFINE_ENUM(NFSERR_REMOTE); +TRACE_DEFINE_ENUM(NFSERR_WFLUSH); +TRACE_DEFINE_ENUM(NFSERR_BADHANDLE); +TRACE_DEFINE_ENUM(NFSERR_NOT_SYNC); +TRACE_DEFINE_ENUM(NFSERR_BAD_COOKIE); +TRACE_DEFINE_ENUM(NFSERR_NOTSUPP); +TRACE_DEFINE_ENUM(NFSERR_TOOSMALL); +TRACE_DEFINE_ENUM(NFSERR_SERVERFAULT); +TRACE_DEFINE_ENUM(NFSERR_BADTYPE); +TRACE_DEFINE_ENUM(NFSERR_JUKEBOX); + +#define show_nfs_status(x) \ + __print_symbolic(x, \ + { NFS_OK, "OK" }, \ + { NFSERR_PERM, "PERM" }, \ + { NFSERR_NOENT, "NOENT" }, \ + { NFSERR_IO, "IO" }, \ + { NFSERR_NXIO, "NXIO" }, \ + { ECHILD, "CHILD" }, \ + { NFSERR_EAGAIN, "AGAIN" }, \ + { NFSERR_ACCES, "ACCES" }, \ + { NFSERR_EXIST, "EXIST" }, \ + { NFSERR_XDEV, "XDEV" }, \ + { NFSERR_NODEV, "NODEV" }, \ + { NFSERR_NOTDIR, "NOTDIR" }, \ + { NFSERR_ISDIR, "ISDIR" }, \ + { NFSERR_INVAL, "INVAL" }, \ + { NFSERR_FBIG, "FBIG" }, \ + { NFSERR_NOSPC, "NOSPC" }, \ + { NFSERR_ROFS, "ROFS" }, \ + { NFSERR_MLINK, "MLINK" }, \ + { NFSERR_OPNOTSUPP, "OPNOTSUPP" }, \ + { NFSERR_NAMETOOLONG, "NAMETOOLONG" }, \ + { NFSERR_NOTEMPTY, "NOTEMPTY" }, \ + { NFSERR_DQUOT, "DQUOT" }, \ + { NFSERR_STALE, "STALE" }, \ + { NFSERR_REMOTE, "REMOTE" }, \ + { NFSERR_WFLUSH, "WFLUSH" }, \ + { NFSERR_BADHANDLE, "BADHANDLE" }, \ + { NFSERR_NOT_SYNC, "NOTSYNC" }, \ + { NFSERR_BAD_COOKIE, "BADCOOKIE" }, \ + { NFSERR_NOTSUPP, "NOTSUPP" }, \ + { NFSERR_TOOSMALL, "TOOSMALL" }, \ + { NFSERR_SERVERFAULT, "REMOTEIO" }, \ + { NFSERR_BADTYPE, "BADTYPE" }, \ + { NFSERR_JUKEBOX, "JUKEBOX" }) + +TRACE_DEFINE_ENUM(NFS_UNSTABLE); +TRACE_DEFINE_ENUM(NFS_DATA_SYNC); +TRACE_DEFINE_ENUM(NFS_FILE_SYNC); + +#define show_nfs_stable_how(x) \ + __print_symbolic(x, \ + { NFS_UNSTABLE, "UNSTABLE" }, \ + { NFS_DATA_SYNC, "DATA_SYNC" }, \ + { NFS_FILE_SYNC, "FILE_SYNC" }) + +TRACE_DEFINE_ENUM(NFS4_OK); +TRACE_DEFINE_ENUM(NFS4ERR_ACCESS); +TRACE_DEFINE_ENUM(NFS4ERR_ATTRNOTSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_ADMIN_REVOKED); +TRACE_DEFINE_ENUM(NFS4ERR_BACK_CHAN_BUSY); +TRACE_DEFINE_ENUM(NFS4ERR_BADCHAR); +TRACE_DEFINE_ENUM(NFS4ERR_BADHANDLE); +TRACE_DEFINE_ENUM(NFS4ERR_BADIOMODE); +TRACE_DEFINE_ENUM(NFS4ERR_BADLAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_BADLABEL); +TRACE_DEFINE_ENUM(NFS4ERR_BADNAME); +TRACE_DEFINE_ENUM(NFS4ERR_BADOWNER); +TRACE_DEFINE_ENUM(NFS4ERR_BADSESSION); +TRACE_DEFINE_ENUM(NFS4ERR_BADSLOT); +TRACE_DEFINE_ENUM(NFS4ERR_BADTYPE); +TRACE_DEFINE_ENUM(NFS4ERR_BADXDR); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_COOKIE); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_HIGH_SLOT); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_RANGE); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_SEQID); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_SESSION_DIGEST); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_CB_PATH_DOWN); +TRACE_DEFINE_ENUM(NFS4ERR_CLID_INUSE); +TRACE_DEFINE_ENUM(NFS4ERR_CLIENTID_BUSY); +TRACE_DEFINE_ENUM(NFS4ERR_COMPLETE_ALREADY); +TRACE_DEFINE_ENUM(NFS4ERR_CONN_NOT_BOUND_TO_SESSION); +TRACE_DEFINE_ENUM(NFS4ERR_DEADLOCK); +TRACE_DEFINE_ENUM(NFS4ERR_DEADSESSION); +TRACE_DEFINE_ENUM(NFS4ERR_DELAY); +TRACE_DEFINE_ENUM(NFS4ERR_DELEG_ALREADY_WANTED); +TRACE_DEFINE_ENUM(NFS4ERR_DELEG_REVOKED); +TRACE_DEFINE_ENUM(NFS4ERR_DENIED); +TRACE_DEFINE_ENUM(NFS4ERR_DIRDELEG_UNAVAIL); +TRACE_DEFINE_ENUM(NFS4ERR_DQUOT); +TRACE_DEFINE_ENUM(NFS4ERR_ENCR_ALG_UNSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_EXIST); +TRACE_DEFINE_ENUM(NFS4ERR_EXPIRED); +TRACE_DEFINE_ENUM(NFS4ERR_FBIG); +TRACE_DEFINE_ENUM(NFS4ERR_FHEXPIRED); +TRACE_DEFINE_ENUM(NFS4ERR_FILE_OPEN); +TRACE_DEFINE_ENUM(NFS4ERR_GRACE); +TRACE_DEFINE_ENUM(NFS4ERR_HASH_ALG_UNSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_INVAL); +TRACE_DEFINE_ENUM(NFS4ERR_IO); +TRACE_DEFINE_ENUM(NFS4ERR_ISDIR); +TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTTRYLATER); +TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTUNAVAILABLE); +TRACE_DEFINE_ENUM(NFS4ERR_LEASE_MOVED); +TRACE_DEFINE_ENUM(NFS4ERR_LOCKED); +TRACE_DEFINE_ENUM(NFS4ERR_LOCKS_HELD); +TRACE_DEFINE_ENUM(NFS4ERR_LOCK_RANGE); +TRACE_DEFINE_ENUM(NFS4ERR_MINOR_VERS_MISMATCH); +TRACE_DEFINE_ENUM(NFS4ERR_MLINK); +TRACE_DEFINE_ENUM(NFS4ERR_MOVED); +TRACE_DEFINE_ENUM(NFS4ERR_NAMETOOLONG); +TRACE_DEFINE_ENUM(NFS4ERR_NOENT); +TRACE_DEFINE_ENUM(NFS4ERR_NOFILEHANDLE); +TRACE_DEFINE_ENUM(NFS4ERR_NOMATCHING_LAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_NOSPC); +TRACE_DEFINE_ENUM(NFS4ERR_NOTDIR); +TRACE_DEFINE_ENUM(NFS4ERR_NOTEMPTY); +TRACE_DEFINE_ENUM(NFS4ERR_NOTSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_NOT_ONLY_OP); +TRACE_DEFINE_ENUM(NFS4ERR_NOT_SAME); +TRACE_DEFINE_ENUM(NFS4ERR_NO_GRACE); +TRACE_DEFINE_ENUM(NFS4ERR_NXIO); +TRACE_DEFINE_ENUM(NFS4ERR_OLD_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_OPENMODE); +TRACE_DEFINE_ENUM(NFS4ERR_OP_ILLEGAL); +TRACE_DEFINE_ENUM(NFS4ERR_OP_NOT_IN_SESSION); +TRACE_DEFINE_ENUM(NFS4ERR_PERM); +TRACE_DEFINE_ENUM(NFS4ERR_PNFS_IO_HOLE); +TRACE_DEFINE_ENUM(NFS4ERR_PNFS_NO_LAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_RECALLCONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_BAD); +TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_CONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_REJECT_DELEG); +TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG); +TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG_TO_CACHE); +TRACE_DEFINE_ENUM(NFS4ERR_REQ_TOO_BIG); +TRACE_DEFINE_ENUM(NFS4ERR_RESOURCE); +TRACE_DEFINE_ENUM(NFS4ERR_RESTOREFH); +TRACE_DEFINE_ENUM(NFS4ERR_RETRY_UNCACHED_REP); +TRACE_DEFINE_ENUM(NFS4ERR_RETURNCONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_ROFS); +TRACE_DEFINE_ENUM(NFS4ERR_SAME); +TRACE_DEFINE_ENUM(NFS4ERR_SHARE_DENIED); +TRACE_DEFINE_ENUM(NFS4ERR_SEQUENCE_POS); +TRACE_DEFINE_ENUM(NFS4ERR_SEQ_FALSE_RETRY); +TRACE_DEFINE_ENUM(NFS4ERR_SEQ_MISORDERED); +TRACE_DEFINE_ENUM(NFS4ERR_SERVERFAULT); +TRACE_DEFINE_ENUM(NFS4ERR_STALE); +TRACE_DEFINE_ENUM(NFS4ERR_STALE_CLIENTID); +TRACE_DEFINE_ENUM(NFS4ERR_STALE_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_SYMLINK); +TRACE_DEFINE_ENUM(NFS4ERR_TOOSMALL); +TRACE_DEFINE_ENUM(NFS4ERR_TOO_MANY_OPS); +TRACE_DEFINE_ENUM(NFS4ERR_UNKNOWN_LAYOUTTYPE); +TRACE_DEFINE_ENUM(NFS4ERR_UNSAFE_COMPOUND); +TRACE_DEFINE_ENUM(NFS4ERR_WRONGSEC); +TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED); +TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE); +TRACE_DEFINE_ENUM(NFS4ERR_XDEV); + +TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_MDS); +TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_PNFS); + +#define show_nfs4_status(x) \ + __print_symbolic(x, \ + { NFS4_OK, "OK" }, \ + { EPERM, "EPERM" }, \ + { ENOENT, "ENOENT" }, \ + { EIO, "EIO" }, \ + { ENXIO, "ENXIO" }, \ + { EACCES, "EACCES" }, \ + { EEXIST, "EEXIST" }, \ + { EXDEV, "EXDEV" }, \ + { ENOTDIR, "ENOTDIR" }, \ + { EISDIR, "EISDIR" }, \ + { EFBIG, "EFBIG" }, \ + { ENOSPC, "ENOSPC" }, \ + { EROFS, "EROFS" }, \ + { EMLINK, "EMLINK" }, \ + { ENAMETOOLONG, "ENAMETOOLONG" }, \ + { ENOTEMPTY, "ENOTEMPTY" }, \ + { EDQUOT, "EDQUOT" }, \ + { ESTALE, "ESTALE" }, \ + { EBADHANDLE, "EBADHANDLE" }, \ + { EBADCOOKIE, "EBADCOOKIE" }, \ + { ENOTSUPP, "ENOTSUPP" }, \ + { ETOOSMALL, "ETOOSMALL" }, \ + { EREMOTEIO, "EREMOTEIO" }, \ + { EBADTYPE, "EBADTYPE" }, \ + { EAGAIN, "EAGAIN" }, \ + { ELOOP, "ELOOP" }, \ + { EOPNOTSUPP, "EOPNOTSUPP" }, \ + { EDEADLK, "EDEADLK" }, \ + { ENOMEM, "ENOMEM" }, \ + { EKEYEXPIRED, "EKEYEXPIRED" }, \ + { ETIMEDOUT, "ETIMEDOUT" }, \ + { ERESTARTSYS, "ERESTARTSYS" }, \ + { ECONNREFUSED, "ECONNREFUSED" }, \ + { ECONNRESET, "ECONNRESET" }, \ + { ENETUNREACH, "ENETUNREACH" }, \ + { EHOSTUNREACH, "EHOSTUNREACH" }, \ + { EHOSTDOWN, "EHOSTDOWN" }, \ + { EPIPE, "EPIPE" }, \ + { EPFNOSUPPORT, "EPFNOSUPPORT" }, \ + { EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ + { NFS4ERR_ACCESS, "ACCESS" }, \ + { NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ + { NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ + { NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ + { NFS4ERR_BADCHAR, "BADCHAR" }, \ + { NFS4ERR_BADHANDLE, "BADHANDLE" }, \ + { NFS4ERR_BADIOMODE, "BADIOMODE" }, \ + { NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ + { NFS4ERR_BADLABEL, "BADLABEL" }, \ + { NFS4ERR_BADNAME, "BADNAME" }, \ + { NFS4ERR_BADOWNER, "BADOWNER" }, \ + { NFS4ERR_BADSESSION, "BADSESSION" }, \ + { NFS4ERR_BADSLOT, "BADSLOT" }, \ + { NFS4ERR_BADTYPE, "BADTYPE" }, \ + { NFS4ERR_BADXDR, "BADXDR" }, \ + { NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ + { NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ + { NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ + { NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ + { NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ + { NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ + { NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ + { NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ + { NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ + { NFS4ERR_CONN_NOT_BOUND_TO_SESSION, "CONN_NOT_BOUND_TO_SESSION" }, \ + { NFS4ERR_DEADLOCK, "DEADLOCK" }, \ + { NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ + { NFS4ERR_DELAY, "DELAY" }, \ + { NFS4ERR_DELEG_ALREADY_WANTED, "DELEG_ALREADY_WANTED" }, \ + { NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ + { NFS4ERR_DENIED, "DENIED" }, \ + { NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ + { NFS4ERR_DQUOT, "DQUOT" }, \ + { NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ + { NFS4ERR_EXIST, "EXIST" }, \ + { NFS4ERR_EXPIRED, "EXPIRED" }, \ + { NFS4ERR_FBIG, "FBIG" }, \ + { NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ + { NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ + { NFS4ERR_GRACE, "GRACE" }, \ + { NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ + { NFS4ERR_INVAL, "INVAL" }, \ + { NFS4ERR_IO, "IO" }, \ + { NFS4ERR_ISDIR, "ISDIR" }, \ + { NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ + { NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ + { NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ + { NFS4ERR_LOCKED, "LOCKED" }, \ + { NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ + { NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ + { NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ + { NFS4ERR_MLINK, "MLINK" }, \ + { NFS4ERR_MOVED, "MOVED" }, \ + { NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ + { NFS4ERR_NOENT, "NOENT" }, \ + { NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ + { NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ + { NFS4ERR_NOSPC, "NOSPC" }, \ + { NFS4ERR_NOTDIR, "NOTDIR" }, \ + { NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ + { NFS4ERR_NOTSUPP, "NOTSUPP" }, \ + { NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ + { NFS4ERR_NOT_SAME, "NOT_SAME" }, \ + { NFS4ERR_NO_GRACE, "NO_GRACE" }, \ + { NFS4ERR_NXIO, "NXIO" }, \ + { NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ + { NFS4ERR_OPENMODE, "OPENMODE" }, \ + { NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ + { NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ + { NFS4ERR_PERM, "PERM" }, \ + { NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ + { NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ + { NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ + { NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ + { NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ + { NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ + { NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ + { NFS4ERR_REP_TOO_BIG_TO_CACHE, "REP_TOO_BIG_TO_CACHE" }, \ + { NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ + { NFS4ERR_RESOURCE, "RESOURCE" }, \ + { NFS4ERR_RESTOREFH, "RESTOREFH" }, \ + { NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ + { NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ + { NFS4ERR_ROFS, "ROFS" }, \ + { NFS4ERR_SAME, "SAME" }, \ + { NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ + { NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ + { NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ + { NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ + { NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ + { NFS4ERR_STALE, "STALE" }, \ + { NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ + { NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ + { NFS4ERR_SYMLINK, "SYMLINK" }, \ + { NFS4ERR_TOOSMALL, "TOOSMALL" }, \ + { NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ + { NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ + { NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ + { NFS4ERR_WRONGSEC, "WRONGSEC" }, \ + { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ + { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ + { NFS4ERR_XDEV, "XDEV" }, \ + /* ***** Internal to Linux NFS client ***** */ \ + { NFS4ERR_RESET_TO_MDS, "RESET_TO_MDS" }, \ + { NFS4ERR_RESET_TO_PNFS, "RESET_TO_PNFS" }) + +#define show_nfs4_verifier(x) \ + __print_hex_str(x, NFS4_VERIFIER_SIZE) + +TRACE_DEFINE_ENUM(IOMODE_READ); +TRACE_DEFINE_ENUM(IOMODE_RW); +TRACE_DEFINE_ENUM(IOMODE_ANY); + +#define show_pnfs_layout_iomode(x) \ + __print_symbolic(x, \ + { IOMODE_READ, "READ" }, \ + { IOMODE_RW, "RW" }, \ + { IOMODE_ANY, "ANY" }) + +#define show_rca_mask(x) \ + __print_flags(x, "|", \ + { BIT(RCA4_TYPE_MASK_RDATA_DLG), "RDATA_DLG" }, \ + { BIT(RCA4_TYPE_MASK_WDATA_DLG), "WDATA_DLG" }, \ + { BIT(RCA4_TYPE_MASK_DIR_DLG), "DIR_DLG" }, \ + { BIT(RCA4_TYPE_MASK_FILE_LAYOUT), "FILE_LAYOUT" }, \ + { BIT(RCA4_TYPE_MASK_BLK_LAYOUT), "BLK_LAYOUT" }, \ + { BIT(RCA4_TYPE_MASK_OBJ_LAYOUT_MIN), "OBJ_LAYOUT_MIN" }, \ + { BIT(RCA4_TYPE_MASK_OBJ_LAYOUT_MAX), "OBJ_LAYOUT_MAX" }, \ + { BIT(RCA4_TYPE_MASK_OTHER_LAYOUT_MIN), "OTHER_LAYOUT_MIN" }, \ + { BIT(RCA4_TYPE_MASK_OTHER_LAYOUT_MAX), "OTHER_LAYOUT_MAX" }) + +#define show_nfs4_seq4_status(x) \ + __print_flags(x, "|", \ + { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING, "CB_GSS_CONTEXTS_EXPIRING" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED, "CB_GSS_CONTEXTS_EXPIRED" }, \ + { SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED, "EXPIRED_ALL_STATE_REVOKED" }, \ + { SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED, "EXPIRED_SOME_STATE_REVOKED" }, \ + { SEQ4_STATUS_ADMIN_STATE_REVOKED, "ADMIN_STATE_REVOKED" }, \ + { SEQ4_STATUS_RECALLABLE_STATE_REVOKED, "RECALLABLE_STATE_REVOKED" }, \ + { SEQ4_STATUS_LEASE_MOVED, "LEASE_MOVED" }, \ + { SEQ4_STATUS_RESTART_RECLAIM_NEEDED, "RESTART_RECLAIM_NEEDED" }, \ + { SEQ4_STATUS_CB_PATH_DOWN_SESSION, "CB_PATH_DOWN_SESSION" }, \ + { SEQ4_STATUS_BACKCHANNEL_FAULT, "BACKCHANNEL_FAULT" }) diff --git a/include/trace/events/rdma.h b/include/trace/misc/rdma.h index 81bb454fc288..81bb454fc288 100644 --- a/include/trace/events/rdma.h +++ b/include/trace/misc/rdma.h diff --git a/include/trace/misc/sunrpc.h b/include/trace/misc/sunrpc.h new file mode 100644 index 000000000000..588557d07ea8 --- /dev/null +++ b/include/trace/misc/sunrpc.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 Oracle and/or its affiliates. + * + * Common types and format specifiers for sunrpc. + */ + +#if !defined(_TRACE_SUNRPC_BASE_H) +#define _TRACE_SUNRPC_BASE_H + +#include <linux/tracepoint.h> + +#define SUNRPC_TRACE_PID_SPECIFIER "%08x" +#define SUNRPC_TRACE_CLID_SPECIFIER "%08x" +#define SUNRPC_TRACE_TASK_SPECIFIER \ + "task:" SUNRPC_TRACE_PID_SPECIFIER "@" SUNRPC_TRACE_CLID_SPECIFIER + +#endif /* _TRACE_SUNRPC_BASE_H */ diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 64553df9d735..d8536d77fea1 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -20,6 +20,7 @@ #define FAN_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FAN_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ +#define FAN_FS_ERROR 0x00008000 /* Filesystem error */ #define FAN_OPEN_PERM 0x00010000 /* File open in perm check */ #define FAN_ACCESS_PERM 0x00020000 /* File accessed in perm check */ @@ -27,6 +28,8 @@ #define FAN_EVENT_ON_CHILD 0x08000000 /* Interested in child events */ +#define FAN_RENAME 0x10000000 /* File was renamed */ + #define FAN_ONDIR 0x40000000 /* Event occurred against dir */ /* helper events */ @@ -56,9 +59,13 @@ #define FAN_REPORT_FID 0x00000200 /* Report unique file id */ #define FAN_REPORT_DIR_FID 0x00000400 /* Report unique directory id */ #define FAN_REPORT_NAME 0x00000800 /* Report events with name */ +#define FAN_REPORT_TARGET_FID 0x00001000 /* Report dirent target id */ /* Convenience macro - FAN_REPORT_NAME requires FAN_REPORT_DIR_FID */ #define FAN_REPORT_DFID_NAME (FAN_REPORT_DIR_FID | FAN_REPORT_NAME) +/* Convenience macro - FAN_REPORT_TARGET_FID requires all other FID flags */ +#define FAN_REPORT_DFID_NAME_TARGET (FAN_REPORT_DFID_NAME | \ + FAN_REPORT_FID | FAN_REPORT_TARGET_FID) /* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK | \ @@ -75,12 +82,21 @@ #define FAN_MARK_IGNORED_SURV_MODIFY 0x00000040 #define FAN_MARK_FLUSH 0x00000080 /* FAN_MARK_FILESYSTEM is 0x00000100 */ +#define FAN_MARK_EVICTABLE 0x00000200 +/* This bit is mutually exclusive with FAN_MARK_IGNORED_MASK bit */ +#define FAN_MARK_IGNORE 0x00000400 /* These are NOT bitwise flags. Both bits can be used togther. */ #define FAN_MARK_INODE 0x00000000 #define FAN_MARK_MOUNT 0x00000010 #define FAN_MARK_FILESYSTEM 0x00000100 +/* + * Convenience macro - FAN_MARK_IGNORE requires FAN_MARK_IGNORED_SURV_MODIFY + * for non-inode mark types. + */ +#define FAN_MARK_IGNORE_SURV (FAN_MARK_IGNORE | FAN_MARK_IGNORED_SURV_MODIFY) + /* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_MARK_FLAGS (FAN_MARK_ADD |\ FAN_MARK_REMOVE |\ @@ -125,6 +141,13 @@ struct fanotify_event_metadata { #define FAN_EVENT_INFO_TYPE_DFID_NAME 2 #define FAN_EVENT_INFO_TYPE_DFID 3 #define FAN_EVENT_INFO_TYPE_PIDFD 4 +#define FAN_EVENT_INFO_TYPE_ERROR 5 + +/* Special info types for FAN_RENAME */ +#define FAN_EVENT_INFO_TYPE_OLD_DFID_NAME 10 +/* Reserved for FAN_EVENT_INFO_TYPE_OLD_DFID 11 */ +#define FAN_EVENT_INFO_TYPE_NEW_DFID_NAME 12 +/* Reserved for FAN_EVENT_INFO_TYPE_NEW_DFID 13 */ /* Variable length info record following event metadata */ struct fanotify_event_info_header { @@ -159,6 +182,12 @@ struct fanotify_event_info_pidfd { __s32 pidfd; }; +struct fanotify_event_info_error { + struct fanotify_event_info_header hdr; + __s32 error; + __u32 error_count; +}; + struct fanotify_response { __s32 fd; __u32 response; diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 7989d9483ea7..bed20a89c14c 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -602,6 +602,7 @@ #define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */ #define KEY_ROTATE_LOCK_TOGGLE 0x231 /* Display rotation lock */ +#define KEY_REFRESH_RATE_TOGGLE 0x232 /* Display refresh rate toggle */ #define KEY_BUTTONCONFIG 0x240 /* AL Button Configuration */ #define KEY_TASKMANAGER 0x241 /* AL Task/Project Manager */ diff --git a/include/uapi/linux/nfsd/nfsfh.h b/include/uapi/linux/nfsd/nfsfh.h deleted file mode 100644 index e29e8accc4f4..000000000000 --- a/include/uapi/linux/nfsd/nfsfh.h +++ /dev/null @@ -1,115 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * This file describes the layout of the file handles as passed - * over the wire. - * - * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> - */ - -#ifndef _UAPI_LINUX_NFSD_FH_H -#define _UAPI_LINUX_NFSD_FH_H - -#include <linux/types.h> -#include <linux/nfs.h> -#include <linux/nfs2.h> -#include <linux/nfs3.h> -#include <linux/nfs4.h> - -/* - * This is the old "dentry style" Linux NFSv2 file handle. - * - * The xino and xdev fields are currently used to transport the - * ino/dev of the exported inode. - */ -struct nfs_fhbase_old { - __u32 fb_dcookie; /* dentry cookie - always 0xfeebbaca */ - __u32 fb_ino; /* our inode number */ - __u32 fb_dirino; /* dir inode number, 0 for directories */ - __u32 fb_dev; /* our device */ - __u32 fb_xdev; - __u32 fb_xino; - __u32 fb_generation; -}; - -/* - * This is the new flexible, extensible style NFSv2/v3/v4 file handle. - * - * The file handle starts with a sequence of four-byte words. - * The first word contains a version number (1) and three descriptor bytes - * that tell how the remaining 3 variable length fields should be handled. - * These three bytes are auth_type, fsid_type and fileid_type. - * - * All four-byte values are in host-byte-order. - * - * The auth_type field is deprecated and must be set to 0. - * - * The fsid_type identifies how the filesystem (or export point) is - * encoded. - * Current values: - * 0 - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number - * NOTE: we cannot use the kdev_t device id value, because kdev_t.h - * says we mustn't. We must break it up and reassemble. - * 1 - 4 byte user specified identifier - * 2 - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED - * 3 - 4 byte device id, encoded for user-space, 4 byte inode number - * 4 - 4 byte inode number and 4 byte uuid - * 5 - 8 byte uuid - * 6 - 16 byte uuid - * 7 - 8 byte inode number and 16 byte uuid - * - * The fileid_type identified how the file within the filesystem is encoded. - * The values for this field are filesystem specific, exccept that - * filesystems must not use the values '0' or '0xff'. 'See enum fid_type' - * in include/linux/exportfs.h for currently registered values. - */ -struct nfs_fhbase_new { - union { - struct { - __u8 fb_version_aux; /* == 1, even => nfs_fhbase_old */ - __u8 fb_auth_type_aux; - __u8 fb_fsid_type_aux; - __u8 fb_fileid_type_aux; - __u32 fb_auth[1]; - /* __u32 fb_fsid[0]; floating */ - /* __u32 fb_fileid[0]; floating */ - }; - struct { - __u8 fb_version; /* == 1, even => nfs_fhbase_old */ - __u8 fb_auth_type; - __u8 fb_fsid_type; - __u8 fb_fileid_type; - __u32 fb_auth_flex[]; /* flexible-array member */ - }; - }; -}; - -struct knfsd_fh { - unsigned int fh_size; /* significant for NFSv3. - * Points to the current size while building - * a new file handle - */ - union { - struct nfs_fhbase_old fh_old; - __u32 fh_pad[NFS4_FHSIZE/4]; - struct nfs_fhbase_new fh_new; - } fh_base; -}; - -#define ofh_dcookie fh_base.fh_old.fb_dcookie -#define ofh_ino fh_base.fh_old.fb_ino -#define ofh_dirino fh_base.fh_old.fb_dirino -#define ofh_dev fh_base.fh_old.fb_dev -#define ofh_xdev fh_base.fh_old.fb_xdev -#define ofh_xino fh_base.fh_old.fb_xino -#define ofh_generation fh_base.fh_old.fb_generation - -#define fh_version fh_base.fh_new.fb_version -#define fh_fsid_type fh_base.fh_new.fb_fsid_type -#define fh_auth_type fh_base.fh_new.fb_auth_type -#define fh_fileid_type fh_base.fh_new.fb_fileid_type -#define fh_fsid fh_base.fh_new.fb_auth_flex - -/* Do not use, provided for userspace compatiblity. */ -#define fh_auth fh_base.fh_new.fb_auth - -#endif /* _UAPI_LINUX_NFSD_FH_H */ diff --git a/init/initramfs.c b/init/initramfs.c index a842c0544745..f153fb505781 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -655,7 +655,7 @@ static void __init populate_initrd_image(char *err) printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n", err); - file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700); + file = filp_open("/initrd.image", O_WRONLY|O_CREAT|O_LARGEFILE, 0700); if (IS_ERR(file)) return; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index a51429c0342e..ff6c36aec27c 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -8422,7 +8422,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, } io_rsrc_node_switch(ctx, NULL); - return ret; + return 0; out_fput: for (i = 0; i < ctx->nr_user_files; i++) { file = io_file_from_index(ctx, i); diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index c428312938e9..c565fbf66ac8 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -100,7 +100,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa audit_update_mark(audit_mark, dentry->d_inode); audit_mark->rule = krule; - ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, true); + ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, 0); if (ret < 0) { audit_mark->path = NULL; fsnotify_put_mark(&audit_mark->mark); @@ -161,8 +161,7 @@ static int audit_mark_handle_event(struct fsnotify_mark *inode_mark, u32 mask, audit_mark = container_of(inode_mark, struct audit_fsnotify_mark, mark); - if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group) || - WARN_ON_ONCE(!inode)) + if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group)) return 0; if (mask & (FS_CREATE|FS_MOVED_TO|FS_DELETE|FS_MOVED_FROM)) { @@ -183,7 +182,8 @@ static const struct fsnotify_ops audit_mark_fsnotify_ops = { static int __init audit_fsnotify_init(void) { - audit_fsnotify_group = fsnotify_alloc_group(&audit_mark_fsnotify_ops); + audit_fsnotify_group = fsnotify_alloc_group(&audit_mark_fsnotify_ops, + FSNOTIFY_GROUP_DUPS); if (IS_ERR(audit_fsnotify_group)) { audit_fsnotify_group = NULL; audit_panic("cannot create audit fsnotify group"); diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 2cd7b5694422..18ab4575ae00 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -1073,7 +1073,7 @@ static int __init audit_tree_init(void) audit_tree_mark_cachep = KMEM_CACHE(audit_tree_mark, SLAB_PANIC); - audit_tree_group = fsnotify_alloc_group(&audit_tree_ops); + audit_tree_group = fsnotify_alloc_group(&audit_tree_ops, 0); if (IS_ERR(audit_tree_group)) audit_panic("cannot initialize fsnotify group for rectree watches"); diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index edbeffee64b8..5cf22fe30149 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -472,8 +472,7 @@ static int audit_watch_handle_event(struct fsnotify_mark *inode_mark, u32 mask, parent = container_of(inode_mark, struct audit_parent, mark); - if (WARN_ON_ONCE(inode_mark->group != audit_watch_group) || - WARN_ON_ONCE(!inode)) + if (WARN_ON_ONCE(inode_mark->group != audit_watch_group)) return 0; if (mask & (FS_CREATE|FS_MOVED_TO) && inode) @@ -493,7 +492,7 @@ static const struct fsnotify_ops audit_watch_fsnotify_ops = { static int __init audit_watch_init(void) { - audit_watch_group = fsnotify_alloc_group(&audit_watch_fsnotify_ops); + audit_watch_group = fsnotify_alloc_group(&audit_watch_fsnotify_ops, 0); if (IS_ERR(audit_watch_group)) { audit_watch_group = NULL; audit_panic("cannot create audit fsnotify group"); diff --git a/kernel/bounds.c b/kernel/bounds.c index 9795d75b09b2..a94e3769347e 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -19,7 +19,7 @@ int main(void) DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS); DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES); #ifdef CONFIG_SMP - DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS)); + DEFINE(NR_CPUS_BITS, bits_per(CONFIG_NR_CPUS)); #endif DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); /* End of constants */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f099c5481b66..008ddb694c8a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4320,6 +4320,11 @@ static int check_stack_access_within_bounds( err = check_stack_slot_within_bounds(min_off, state, type); if (!err && max_off > 0) err = -EINVAL; /* out of stack access into non-negative offsets */ + if (!err && access_size < 0) + /* access_size should not be negative (or overflow an int); others checks + * along the way should have prevented such an access. + */ + err = -EFAULT; /* invalid negative access size; integer overflow? */ if (err) { if (tnum_is_const(reg->var_off)) { diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 9478eccd1c8e..c9dbc8f5812b 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -777,6 +777,18 @@ size_t dma_max_mapping_size(struct device *dev) } EXPORT_SYMBOL_GPL(dma_max_mapping_size); +size_t dma_opt_mapping_size(struct device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + size_t size = SIZE_MAX; + + if (ops && ops->opt_mapping_size) + size = ops->opt_mapping_size(); + + return min(dma_max_mapping_size(dev), size); +} +EXPORT_SYMBOL_GPL(dma_opt_mapping_size); + bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) { const struct dma_map_ops *ops = get_dma_ops(dev); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index a9849670bdb5..5c7ed5d51942 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -469,8 +469,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(dev, mem->start) & boundary_mask; unsigned long max_slots = get_max_slots(boundary_mask); - unsigned int iotlb_align_mask = - dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1); + unsigned int iotlb_align_mask = dma_get_min_align_mask(dev); unsigned int nslots = nr_slots(alloc_size), stride; unsigned int index, wrap, count = 0, i; unsigned int offset = swiotlb_align_offset(dev, orig_addr); @@ -479,6 +478,14 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, BUG_ON(!nslots); /* + * Ensure that the allocation is at least slot-aligned and update + * 'iotlb_align_mask' to ignore bits that will be preserved when + * offsetting into the allocation. + */ + alloc_align_mask |= (IO_TLB_SIZE - 1); + iotlb_align_mask &= ~alloc_align_mask; + + /* * For mappings with an alignment requirement don't bother looping to * unaligned slots once we found an aligned one. For allocations of * PAGE_SIZE or larger only look for page aligned allocations. diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 51ddfdacfc1f..9327f590cd86 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -73,8 +73,14 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall, /* Either of the above might have changed the syscall number */ syscall = syscall_get_nr(current, regs); - if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) + if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) { trace_sys_enter(regs, syscall); + /* + * Probes or BPF hooks in the tracepoint may have changed the + * system call number as well. + */ + syscall = syscall_get_nr(current, regs); + } syscall_enter_audit(regs, syscall); diff --git a/kernel/events/core.c b/kernel/events/core.c index 4e5a73c7db12..e79cd0fd1d2b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7119,9 +7119,16 @@ static void perf_output_read_group(struct perf_output_handle *handle, { struct perf_event *leader = event->group_leader, *sub; u64 read_format = event->attr.read_format; + unsigned long flags; u64 values[6]; int n = 0; + /* + * Disabling interrupts avoids all counter scheduling + * (context switches, timer based rotation and IPIs). + */ + local_irq_save(flags); + values[n++] = 1 + leader->nr_siblings; if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) @@ -7157,6 +7164,8 @@ static void perf_output_read_group(struct perf_output_handle *handle, __output_copy(handle, values, n * sizeof(u64)); } + + local_irq_restore(flags); } #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\ diff --git a/kernel/kthread.c b/kernel/kthread.c index c3870b2a150d..c30c68816f88 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -268,6 +268,21 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); +/** + * kthread_exit - Cause the current kthread return @result to kthread_stop(). + * @result: The integer value to return to kthread_stop(). + * + * While kthread_exit can be called directly, it exists so that + * functions which do some additional work in non-modular code such as + * module_put_and_kthread_exit can be implemented. + * + * Does not return. + */ +void __noreturn kthread_exit(long result) +{ + do_exit(result); +} + static int kthread(void *_create) { static const struct sched_param param = { .sched_priority = 0 }; @@ -286,13 +301,13 @@ static int kthread(void *_create) done = xchg(&create->done, NULL); if (!done) { kfree(create); - do_exit(-EINTR); + kthread_exit(-EINTR); } if (!self) { create->result = ERR_PTR(-ENOMEM); complete(done); - do_exit(-ENOMEM); + kthread_exit(-ENOMEM); } self->threadfn = threadfn; @@ -326,7 +341,7 @@ static int kthread(void *_create) __kthread_parkme(self); ret = threadfn(data); } - do_exit(ret); + kthread_exit(ret); } /* called from kernel_clone() to get node information for about to be created task */ @@ -628,7 +643,7 @@ EXPORT_SYMBOL_GPL(kthread_park); * instead of calling wake_up_process(): the thread will exit without * calling threadfn(). * - * If threadfn() may call do_exit() itself, the caller must ensure + * If threadfn() may call kthread_exit() itself, the caller must ensure * task_struct can't go away. * * Returns the result of threadfn(), or %-EINTR if wake_up_process() diff --git a/kernel/module.c b/kernel/module.c index 4d49c32af570..2226b591b52e 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -335,14 +335,14 @@ static inline void add_taint_module(struct module *mod, unsigned flag, /* * A thread that wants to hold a reference to a module only while it - * is running can call this to safely exit. nfsd and lockd use this. + * is running can call this to safely exit. */ -void __noreturn __module_put_and_exit(struct module *mod, long code) +void __noreturn __module_put_and_kthread_exit(struct module *mod, long code) { module_put(mod); - do_exit(code); + kthread_exit(code); } -EXPORT_SYMBOL(__module_put_and_exit); +EXPORT_SYMBOL(__module_put_and_kthread_exit); /* Find a module section: 0 means not found. */ static unsigned int find_sec(const struct load_info *info, const char *name) diff --git a/kernel/panic.c b/kernel/panic.c index 8bf64a4e8f9e..0f3de362f338 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -429,6 +429,14 @@ void panic(const char *fmt, ...) /* Do not scroll important messages printed above */ suppress_printk = 1; + + /* + * The final messages may not have been printed if in a context that + * defers printing (such as NMI) and irq_work is not available. + * Explicitly flush the kernel log buffer one last time. + */ + console_flush_on_panic(CONSOLE_FLUSH_PENDING); + local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 13d905dd3267..5d617639e81e 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -187,6 +187,7 @@ static int __init mem_sleep_default_setup(char *str) if (mem_sleep_labels[state] && !strcmp(str, mem_sleep_labels[state])) { mem_sleep_default = state; + mem_sleep_current = state; break; } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 8bf976d88c8c..4e34d2f8ed2c 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2780,6 +2780,21 @@ static int __init keep_bootcon_setup(char *str) early_param("keep_bootcon", keep_bootcon_setup); +static int console_call_setup(struct console *newcon, char *options) +{ + int err; + + if (!newcon->setup) + return 0; + + /* Synchronize with possible boot console. */ + console_lock(); + err = newcon->setup(newcon, options); + console_unlock(); + + return err; +} + /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected @@ -2789,7 +2804,8 @@ early_param("keep_bootcon", keep_bootcon_setup); * Care need to be taken with consoles that are statically * enabled such as netconsole */ -static int try_enable_new_console(struct console *newcon, bool user_specified) +static int try_enable_preferred_console(struct console *newcon, + bool user_specified) { struct console_cmdline *c; int i, err; @@ -2814,8 +2830,8 @@ static int try_enable_new_console(struct console *newcon, bool user_specified) if (_braille_register_console(newcon, c)) return 0; - if (newcon->setup && - (err = newcon->setup(newcon, c->options)) != 0) + err = console_call_setup(newcon, c->options); + if (err) return err; } newcon->flags |= CON_ENABLED; @@ -2837,6 +2853,23 @@ static int try_enable_new_console(struct console *newcon, bool user_specified) return -ENOENT; } +/* Try to enable the console unconditionally */ +static void try_enable_default_console(struct console *newcon) +{ + if (newcon->index < 0) + newcon->index = 0; + + if (console_call_setup(newcon, NULL) != 0) + return; + + newcon->flags |= CON_ENABLED; + + if (newcon->device) { + newcon->flags |= CON_CONSDEV; + has_preferred_console = true; + } +} + /* * The console driver calls this routine during kernel initialization * to register the console printing procedure with printk() and to @@ -2895,25 +2928,15 @@ void register_console(struct console *newcon) * didn't select a console we take the first one * that registers here. */ - if (!has_preferred_console) { - if (newcon->index < 0) - newcon->index = 0; - if (newcon->setup == NULL || - newcon->setup(newcon, NULL) == 0) { - newcon->flags |= CON_ENABLED; - if (newcon->device) { - newcon->flags |= CON_CONSDEV; - has_preferred_console = true; - } - } - } + if (!has_preferred_console) + try_enable_default_console(newcon); /* See if this console matches one we selected on the command line */ - err = try_enable_new_console(newcon, true); + err = try_enable_preferred_console(newcon, true); /* If not, try to match against the platform default(s) */ if (err == -ENOENT) - err = try_enable_new_console(newcon, false); + err = try_enable_preferred_console(newcon, false); /* printk() messages are not printed to the Braille console. */ if (err || newcon->flags & CON_BRL) diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 9dd2a39cb3b0..d4ce3ebe2c8c 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1030,7 +1030,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option /* * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, - * otherwise del_timer_sync() can't detect that the timer's + * otherwise timer_delete_sync() can't detect that the timer's * handler yet has not finished. This also guarantees that the * timer is serialized wrt itself. */ @@ -1068,14 +1068,16 @@ out_unlock: } /** - * mod_timer_pending - modify a pending timer's timeout - * @timer: the pending timer to be modified - * @expires: new timeout in jiffies + * mod_timer_pending - Modify a pending timer's timeout + * @timer: The pending timer to be modified + * @expires: New absolute timeout in jiffies * - * mod_timer_pending() is the same for pending timers as mod_timer(), - * but will not re-activate and modify already deleted timers. + * mod_timer_pending() is the same for pending timers as mod_timer(), but + * will not activate inactive timers. * - * It is useful for unserialized use of timers. + * Return: + * * %0 - The timer was inactive and not modified + * * %1 - The timer was active and requeued to expire at @expires */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { @@ -1084,24 +1086,27 @@ int mod_timer_pending(struct timer_list *timer, unsigned long expires) EXPORT_SYMBOL(mod_timer_pending); /** - * mod_timer - modify a timer's timeout - * @timer: the timer to be modified - * @expires: new timeout in jiffies - * - * mod_timer() is a more efficient way to update the expire field of an - * active timer (if the timer is inactive it will be activated) + * mod_timer - Modify a timer's timeout + * @timer: The timer to be modified + * @expires: New absolute timeout in jiffies * * mod_timer(timer, expires) is equivalent to: * * del_timer(timer); timer->expires = expires; add_timer(timer); * + * mod_timer() is more efficient than the above open coded sequence. In + * case that the timer is inactive, the del_timer() part is a NOP. The + * timer is in any case activated with the new expiry time @expires. + * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_timer() is the only safe way to modify the timeout, * since add_timer() cannot modify an already running timer. * - * The function returns whether it has modified a pending timer or not. - * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an - * active timer returns 1.) + * Return: + * * %0 - The timer was inactive and started + * * %1 - The timer was active and requeued to expire at @expires or + * the timer was active and not modified because @expires did + * not change the effective expiry time */ int mod_timer(struct timer_list *timer, unsigned long expires) { @@ -1112,11 +1117,18 @@ EXPORT_SYMBOL(mod_timer); /** * timer_reduce - Modify a timer's timeout if it would reduce the timeout * @timer: The timer to be modified - * @expires: New timeout in jiffies + * @expires: New absolute timeout in jiffies * * timer_reduce() is very similar to mod_timer(), except that it will only - * modify a running timer if that would reduce the expiration time (it will - * start a timer that isn't running). + * modify an enqueued timer if that would reduce the expiration time. If + * @timer is not enqueued it starts the timer. + * + * Return: + * * %0 - The timer was inactive and started + * * %1 - The timer was active and requeued to expire at @expires or + * the timer was active and not modified because @expires + * did not change the effective expiry time such that the + * timer would expire earlier than already scheduled */ int timer_reduce(struct timer_list *timer, unsigned long expires) { @@ -1125,18 +1137,21 @@ int timer_reduce(struct timer_list *timer, unsigned long expires) EXPORT_SYMBOL(timer_reduce); /** - * add_timer - start a timer - * @timer: the timer to be added + * add_timer - Start a timer + * @timer: The timer to be started * - * The kernel will do a ->function(@timer) callback from the - * timer interrupt at the ->expires point in the future. The - * current time is 'jiffies'. + * Start @timer to expire at @timer->expires in the future. @timer->expires + * is the absolute expiry time measured in 'jiffies'. When the timer expires + * timer->function(timer) will be invoked from soft interrupt context. * - * The timer's ->expires, ->function fields must be set prior calling this - * function. + * The @timer->expires and @timer->function fields must be set prior + * to calling this function. * - * Timers with an ->expires field in the past will be executed in the next - * timer tick. + * If @timer->expires is already in the past @timer will be queued to + * expire at the next timer tick. + * + * This can only operate on an inactive timer. Attempts to invoke this on + * an active timer are rejected with a warning. */ void add_timer(struct timer_list *timer) { @@ -1146,11 +1161,13 @@ void add_timer(struct timer_list *timer) EXPORT_SYMBOL(add_timer); /** - * add_timer_on - start a timer on a particular CPU - * @timer: the timer to be added - * @cpu: the CPU to start it on + * add_timer_on - Start a timer on a particular CPU + * @timer: The timer to be started + * @cpu: The CPU to start it on + * + * Same as add_timer() except that it starts the timer on the given CPU. * - * This is not very scalable on SMP. Double adds are not possible. + * See add_timer() for further details. */ void add_timer_on(struct timer_list *timer, int cpu) { @@ -1185,15 +1202,18 @@ void add_timer_on(struct timer_list *timer, int cpu) EXPORT_SYMBOL_GPL(add_timer_on); /** - * del_timer - deactivate a timer. - * @timer: the timer to be deactivated - * - * del_timer() deactivates a timer - this works on both active and inactive - * timers. - * - * The function returns whether it has deactivated a pending timer or not. - * (ie. del_timer() of an inactive timer returns 0, del_timer() of an - * active timer returns 1.) + * del_timer - Deactivate a timer. + * @timer: The timer to be deactivated + * + * The function only deactivates a pending timer, but contrary to + * timer_delete_sync() it does not take into account whether the timer's + * callback function is concurrently executed on a different CPU or not. + * It neither prevents rearming of the timer. If @timer can be rearmed + * concurrently then the return value of this function is meaningless. + * + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ int del_timer(struct timer_list *timer) { @@ -1215,10 +1235,19 @@ EXPORT_SYMBOL(del_timer); /** * try_to_del_timer_sync - Try to deactivate a timer - * @timer: timer to delete + * @timer: Timer to deactivate + * + * This function tries to deactivate a timer. On success the timer is not + * queued and the timer callback function is not running on any CPU. + * + * This function does not guarantee that the timer cannot be rearmed right + * after dropping the base lock. That needs to be prevented by the calling + * code if necessary. * - * This function tries to deactivate a timer. Upon successful (ret >= 0) - * exit the timer is not queued and the handler is not running on any CPU. + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated + * * %-1 - The timer callback function is running on a different CPU */ int try_to_del_timer_sync(struct timer_list *timer) { @@ -1312,25 +1341,20 @@ static inline void timer_sync_wait_running(struct timer_base *base) { } static inline void del_timer_wait_running(struct timer_list *timer) { } #endif -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) /** - * del_timer_sync - deactivate a timer and wait for the handler to finish. - * @timer: the timer to be deactivated - * - * This function only differs from del_timer() on SMP: besides deactivating - * the timer it also makes sure the handler has finished executing on other - * CPUs. + * timer_delete_sync - Deactivate a timer and wait for the handler to finish. + * @timer: The timer to be deactivated * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts unless the timer is an irqsafe one. The caller must - * not hold locks which would prevent completion of the timer's - * handler. The timer's handler must not call add_timer_on(). Upon exit the - * timer is not queued and the handler is not running on any CPU. + * not hold locks which would prevent completion of the timer's callback + * function. The timer's handler must not call add_timer_on(). Upon exit + * the timer is not queued and the handler is not running on any CPU. * - * Note: For !irqsafe timers, you must not hold locks that are held in - * interrupt context while calling this function. Even if the lock has - * nothing to do with the timer in question. Here's why:: + * For !irqsafe timers, the caller must not hold locks that are held in + * interrupt context. Even if the lock has nothing to do with the timer in + * question. Here's why:: * * CPU0 CPU1 * ---- ---- @@ -1340,16 +1364,23 @@ static inline void del_timer_wait_running(struct timer_list *timer) { } * spin_lock_irq(somelock); * <IRQ> * spin_lock(somelock); - * del_timer_sync(mytimer); + * timer_delete_sync(mytimer); * while (base->running_timer == mytimer); * - * Now del_timer_sync() will never return and never release somelock. - * The interrupt on the other CPU is waiting to grab somelock but - * it has interrupted the softirq that CPU0 is waiting to finish. + * Now timer_delete_sync() will never return and never release somelock. + * The interrupt on the other CPU is waiting to grab somelock but it has + * interrupted the softirq that CPU0 is waiting to finish. + * + * This function cannot guarantee that the timer is not rearmed again by + * some concurrent or preempting code, right after it dropped the base + * lock. If there is the possibility of a concurrent rearm then the return + * value of the function is meaningless. * - * The function returns whether it has deactivated a pending timer or not. + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ -int del_timer_sync(struct timer_list *timer) +int timer_delete_sync(struct timer_list *timer) { int ret; @@ -1389,8 +1420,7 @@ int del_timer_sync(struct timer_list *timer) return ret; } -EXPORT_SYMBOL(del_timer_sync); -#endif +EXPORT_SYMBOL(timer_delete_sync); static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *), @@ -1412,8 +1442,8 @@ static void call_timer_fn(struct timer_list *timer, #endif /* * Couple the lock chain with the lock chain at - * del_timer_sync() by acquiring the lock_map around the fn() - * call here and in del_timer_sync(). + * timer_delete_sync() by acquiring the lock_map around the fn() + * call here and in timer_delete_sync(). */ lock_map_acquire(&lockdep_map); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index d9bed77f96c1..c6bcb80785d8 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -406,7 +406,6 @@ struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; - long wait_index; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; @@ -874,8 +873,19 @@ static void rb_wake_up_waiters(struct irq_work *work) wake_up_all(&rbwork->waiters); if (rbwork->full_waiters_pending || rbwork->wakeup_full) { + /* Only cpu_buffer sets the above flags */ + struct ring_buffer_per_cpu *cpu_buffer = + container_of(rbwork, struct ring_buffer_per_cpu, irq_work); + + /* Called from interrupt context */ + raw_spin_lock(&cpu_buffer->reader_lock); rbwork->wakeup_full = false; rbwork->full_waiters_pending = false; + + /* Waking up all waiters, they will reset the shortest full */ + cpu_buffer->shortest_full = 0; + raw_spin_unlock(&cpu_buffer->reader_lock); + wake_up_all(&rbwork->full_waiters); } } @@ -915,14 +925,95 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) rbwork = &cpu_buffer->irq_work; } - rbwork->wait_index++; - /* make sure the waiters see the new index */ - smp_wmb(); - /* This can be called in any context */ irq_work_queue(&rbwork->work); } +static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full) +{ + struct ring_buffer_per_cpu *cpu_buffer; + bool ret = false; + + /* Reads of all CPUs always waits for any data */ + if (cpu == RING_BUFFER_ALL_CPUS) + return !ring_buffer_empty(buffer); + + cpu_buffer = buffer->buffers[cpu]; + + if (!ring_buffer_empty_cpu(buffer, cpu)) { + unsigned long flags; + bool pagebusy; + + if (!full) + return true; + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; + ret = !pagebusy && full_hit(buffer, cpu, full); + + if (!ret && (!cpu_buffer->shortest_full || + cpu_buffer->shortest_full > full)) { + cpu_buffer->shortest_full = full; + } + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + } + return ret; +} + +static inline bool +rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer, + int cpu, int full, ring_buffer_cond_fn cond, void *data) +{ + if (rb_watermark_hit(buffer, cpu, full)) + return true; + + if (cond(data)) + return true; + + /* + * The events can happen in critical sections where + * checking a work queue can cause deadlocks. + * After adding a task to the queue, this flag is set + * only to notify events to try to wake up the queue + * using irq_work. + * + * We don't clear it even if the buffer is no longer + * empty. The flag only causes the next event to run + * irq_work to do the work queue wake up. The worse + * that can happen if we race with !trace_empty() is that + * an event will cause an irq_work to try to wake up + * an empty queue. + * + * There's no reason to protect this flag either, as + * the work queue and irq_work logic will do the necessary + * synchronization for the wake ups. The only thing + * that is necessary is that the wake up happens after + * a task has been queued. It's OK for spurious wake ups. + */ + if (full) + rbwork->full_waiters_pending = true; + else + rbwork->waiters_pending = true; + + return false; +} + +/* + * The default wait condition for ring_buffer_wait() is to just to exit the + * wait loop the first time it is woken up. + */ +static bool rb_wait_once(void *data) +{ + long *once = data; + + /* wait_event() actually calls this twice before scheduling*/ + if (*once > 1) + return true; + + (*once)++; + return false; +} + /** * ring_buffer_wait - wait for input to the ring buffer * @buffer: buffer to wait on @@ -936,101 +1027,39 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) { struct ring_buffer_per_cpu *cpu_buffer; - DEFINE_WAIT(wait); - struct rb_irq_work *work; - long wait_index; + struct wait_queue_head *waitq; + ring_buffer_cond_fn cond; + struct rb_irq_work *rbwork; + void *data; + long once = 0; int ret = 0; + cond = rb_wait_once; + data = &once; + /* * Depending on what the caller is waiting for, either any * data in any cpu buffer, or a specific buffer, put the * caller on the appropriate wait queue. */ if (cpu == RING_BUFFER_ALL_CPUS) { - work = &buffer->irq_work; + rbwork = &buffer->irq_work; /* Full only makes sense on per cpu reads */ full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return -ENODEV; cpu_buffer = buffer->buffers[cpu]; - work = &cpu_buffer->irq_work; - } - - wait_index = READ_ONCE(work->wait_index); - - while (true) { - if (full) - prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); - else - prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); - - /* - * The events can happen in critical sections where - * checking a work queue can cause deadlocks. - * After adding a task to the queue, this flag is set - * only to notify events to try to wake up the queue - * using irq_work. - * - * We don't clear it even if the buffer is no longer - * empty. The flag only causes the next event to run - * irq_work to do the work queue wake up. The worse - * that can happen if we race with !trace_empty() is that - * an event will cause an irq_work to try to wake up - * an empty queue. - * - * There's no reason to protect this flag either, as - * the work queue and irq_work logic will do the necessary - * synchronization for the wake ups. The only thing - * that is necessary is that the wake up happens after - * a task has been queued. It's OK for spurious wake ups. - */ - if (full) - work->full_waiters_pending = true; - else - work->waiters_pending = true; - - if (signal_pending(current)) { - ret = -EINTR; - break; - } - - if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) - break; - - if (cpu != RING_BUFFER_ALL_CPUS && - !ring_buffer_empty_cpu(buffer, cpu)) { - unsigned long flags; - bool pagebusy; - bool done; - - if (!full) - break; - - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; - done = !pagebusy && full_hit(buffer, cpu, full); - - if (!cpu_buffer->shortest_full || - cpu_buffer->shortest_full > full) - cpu_buffer->shortest_full = full; - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - if (done) - break; - } - - schedule(); - - /* Make sure to see the new wait index */ - smp_rmb(); - if (wait_index != work->wait_index) - break; + rbwork = &cpu_buffer->irq_work; } if (full) - finish_wait(&work->full_waiters, &wait); + waitq = &rbwork->full_waiters; else - finish_wait(&work->waiters, &wait); + waitq = &rbwork->waiters; + + ret = wait_event_interruptible((*waitq), + rb_wait_cond(rbwork, buffer, cpu, full, cond, data)); return ret; } @@ -1054,30 +1083,51 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full) { struct ring_buffer_per_cpu *cpu_buffer; - struct rb_irq_work *work; + struct rb_irq_work *rbwork; if (cpu == RING_BUFFER_ALL_CPUS) { - work = &buffer->irq_work; + rbwork = &buffer->irq_work; full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return EPOLLERR; cpu_buffer = buffer->buffers[cpu]; - work = &cpu_buffer->irq_work; + rbwork = &cpu_buffer->irq_work; } if (full) { - poll_wait(filp, &work->full_waiters, poll_table); - work->full_waiters_pending = true; + unsigned long flags; + + poll_wait(filp, &rbwork->full_waiters, poll_table); + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); if (!cpu_buffer->shortest_full || cpu_buffer->shortest_full > full) cpu_buffer->shortest_full = full; - } else { - poll_wait(filp, &work->waiters, poll_table); - work->waiters_pending = true; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + if (full_hit(buffer, cpu, full)) + return EPOLLIN | EPOLLRDNORM; + /* + * Only allow full_waiters_pending update to be seen after + * the shortest_full is set. If the writer sees the + * full_waiters_pending flag set, it will compare the + * amount in the ring buffer to shortest_full. If the amount + * in the ring buffer is greater than the shortest_full + * percent, it will call the irq_work handler to wake up + * this list. The irq_handler will reset shortest_full + * back to zero. That's done under the reader_lock, but + * the below smp_mb() makes sure that the update to + * full_waiters_pending doesn't leak up into the above. + */ + smp_mb(); + rbwork->full_waiters_pending = true; + return 0; } + poll_wait(filp, &rbwork->waiters, poll_table); + rbwork->waiters_pending = true; + /* * There's a tight race between setting the waiters_pending and * checking if the ring buffer is empty. Once the waiters_pending bit @@ -1093,9 +1143,6 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, */ smp_mb(); - if (full) - return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0; - if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) return EPOLLIN | EPOLLRDNORM; @@ -4343,7 +4390,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) cpu_buffer = iter->cpu_buffer; reader = cpu_buffer->reader_page; head_page = cpu_buffer->head_page; - commit_page = cpu_buffer->commit_page; + commit_page = READ_ONCE(cpu_buffer->commit_page); commit_ts = commit_page->page->time_stamp; /* diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4cfed9c09ccb..d4bd82f8977b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8238,6 +8238,20 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, return size; } +static int tracing_buffers_flush(struct file *file, fl_owner_t id) +{ + struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; + + iter->wait_index++; + /* Make sure the waiters see the new wait_index */ + smp_wmb(); + + ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); + + return 0; +} + static int tracing_buffers_release(struct inode *inode, struct file *file) { struct ftrace_buffer_info *info = file->private_data; @@ -8249,12 +8263,6 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) __trace_array_put(iter->tr); - iter->wait_index++; - /* Make sure the waiters see the new wait_index */ - smp_wmb(); - - ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); - if (info->spare) ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); @@ -8468,6 +8476,7 @@ static const struct file_operations tracing_buffers_fops = { .read = tracing_buffers_read, .poll = tracing_buffers_poll, .release = tracing_buffers_release, + .flush = tracing_buffers_flush, .splice_read = tracing_buffers_splice_read, .unlocked_ioctl = tracing_buffers_ioctl, .llseek = no_llseek, diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 64d6292cf686..28faea9b5da6 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -424,6 +424,7 @@ config SECTION_MISMATCH_WARN_ONLY config DEBUG_FORCE_FUNCTION_ALIGN_64B bool "Force all function address 64B aligned" depends on EXPERT && (X86_64 || ARM64 || PPC32 || PPC64 || ARC) + select FUNCTION_ALIGNMENT_64B help There are cases that a commit from one domain changes the function address alignment of other domains, and cause magic performance diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c index ce39ce9f3526..2829ddb0e316 100644 --- a/lib/pci_iomap.c +++ b/lib/pci_iomap.c @@ -170,8 +170,8 @@ void pci_iounmap(struct pci_dev *dev, void __iomem *p) if (addr >= start && addr < start + IO_SPACE_LIMIT) return; - iounmap(p); #endif + iounmap(p); } EXPORT_SYMBOL(pci_iounmap); diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 46d11796491a..8ea18c923139 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -403,7 +403,8 @@ static void kmalloc_oob_16(struct kunit *test) /* This test is specifically crafted for the generic mode. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); - ptr1 = kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL); + /* RELOC_HIDE to prevent gcc from warning about short alloc */ + ptr1 = RELOC_HIDE(kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL), 0); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1); ptr2 = kmalloc(sizeof(*ptr2), GFP_KERNEL); @@ -543,6 +544,21 @@ static void kmalloc_memmove_invalid_size(struct kunit *test) kfree(ptr); } +static void kmalloc_memmove_invalid_size(struct kunit *test) +{ + char *ptr; + size_t size = 64; + volatile size_t invalid_size = size; + + ptr = kmalloc(size, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + + memset((char *)ptr, 0, 64); + KUNIT_EXPECT_KASAN_FAIL(test, + memmove((char *)ptr, (char *)ptr + 4, invalid_size)); + kfree(ptr); +} + static void kmalloc_uaf(struct kunit *test) { char *ptr; diff --git a/mm/compaction.c b/mm/compaction.c index 89517ad5d6a0..3ec4a2e399cd 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2582,16 +2582,11 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, struct page **capture) { - int may_perform_io = gfp_mask & __GFP_IO; struct zoneref *z; struct zone *zone; enum compact_result rc = COMPACT_SKIPPED; - /* - * Check if the GFP flags allow compaction - GFP_NOIO is really - * tricky context because the migration might require IO - */ - if (!may_perform_io) + if (!gfp_compaction_allowed(gfp_mask)) return COMPACT_SKIPPED; trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio); diff --git a/mm/memory.c b/mm/memory.c index 5ca31af6e22e..b1e866503978 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5086,6 +5086,10 @@ int follow_phys(struct vm_area_struct *vma, goto out; pte = *ptep; + /* Never return PFNs of anon folios in COW mappings. */ + if (vm_normal_page(vma, address, pte)) + goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; diff --git a/mm/memtest.c b/mm/memtest.c index f53ace709ccd..d407373f225b 100644 --- a/mm/memtest.c +++ b/mm/memtest.c @@ -46,10 +46,10 @@ static void __init memtest(u64 pattern, phys_addr_t start_phys, phys_addr_t size last_bad = 0; for (p = start; p < end; p++) - *p = pattern; + WRITE_ONCE(*p, pattern); for (p = start; p < end; p++, start_phys_aligned += incr) { - if (*p == pattern) + if (READ_ONCE(*p) == pattern) continue; if (start_phys_aligned == last_bad + incr) { last_bad += incr; diff --git a/mm/migrate.c b/mm/migrate.c index c7d5566623ad..c37af50f312d 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -424,8 +424,12 @@ int migrate_page_move_mapping(struct address_space *mapping, if (PageSwapBacked(page)) { __SetPageSwapBacked(newpage); if (PageSwapCache(page)) { + int i; + SetPageSwapCache(newpage); - set_page_private(newpage, page_private(page)); + for (i = 0; i < (1 << compound_order(page)); i++) + set_page_private(newpage + i, + page_private(page + i)); } } else { VM_BUG_ON_PAGE(PageSwapCache(page), page); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 189f097253e2..a0ffa809629a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4903,6 +4903,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct alloc_context *ac) { bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; + bool can_compact = gfp_compaction_allowed(gfp_mask); const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER; struct page *page = NULL; unsigned int alloc_flags; @@ -4968,7 +4969,7 @@ restart: * Don't try this for allocations that are allowed to ignore * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen. */ - if (can_direct_reclaim && + if (can_direct_reclaim && can_compact && (costly_order || (order > 0 && ac->migratetype != MIGRATE_MOVABLE)) && !gfp_pfmemalloc_allowed(gfp_mask)) { @@ -5065,9 +5066,10 @@ retry: /* * Do not retry costly high order allocations unless they are - * __GFP_RETRY_MAYFAIL + * __GFP_RETRY_MAYFAIL and we can compact */ - if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL)) + if (costly_order && (!can_compact || + !(gfp_mask & __GFP_RETRY_MAYFAIL))) goto nopage; if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags, @@ -5080,7 +5082,7 @@ retry: * implementation of the compaction depends on the sufficient amount * of free memory (see __compaction_suitable) */ - if (did_some_progress > 0 && + if (did_some_progress > 0 && can_compact && should_compact_retry(ac, order, alloc_flags, compact_result, &compact_priority, &compaction_retries)) diff --git a/mm/swapfile.c b/mm/swapfile.c index b7e1620adee6..fec3e736a194 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1236,6 +1236,18 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, } /* + * When we get a swap entry, if there aren't some other ways to + * prevent swapoff, such as the folio in swap cache is locked, page + * table lock is held, etc., the swap entry may become invalid because + * of swapoff. Then, we need to enclose all swap related functions + * with get_swap_device() and put_swap_device(), unless the swap + * functions call get/put_swap_device() by themselves. + * + * Note that when only holding the PTL, swapoff might succeed immediately + * after freeing a swap entry. Therefore, immediately after + * __swap_entry_free(), the swap info might become stale and should not + * be touched without a prior get_swap_device(). + * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until @@ -1244,9 +1256,8 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way - * to prevent swapoff, such as page lock, page table lock, etc. The - * caller must be prepared for that. For example, the following - * situation is possible. + * to prevent swapoff. The caller must be prepared for that. For + * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() @@ -1762,13 +1773,19 @@ int free_swap_and_cache(swp_entry_t entry) if (non_swap_entry(entry)) return 1; - p = _swap_info_get(entry); + p = get_swap_device(entry); if (p) { + if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) { + put_swap_device(p); + return 0; + } + count = __swap_entry_free(p, entry); if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL); + put_swap_device(p); } return p != NULL; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 201acea81804..342a78a8658f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2834,7 +2834,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { - if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && + if (gfp_compaction_allowed(sc->gfp_mask) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; @@ -3167,6 +3167,9 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) unsigned long watermark; enum compact_result suitable; + if (!gfp_compaction_allowed(sc->gfp_mask)) + return false; + suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx); if (suitable == COMPACT_SUCCESS) /* Allocation should succeed already. Don't reclaim. */ diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 72f47b372705..a796d72c7dba 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -535,7 +535,7 @@ static int bnep_session(void *arg) up_write(&bnep_session_sem); free_netdev(dev); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 83eb84e8e688..90d130588a3e 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -323,7 +323,7 @@ static int cmtp_session(void *arg) up_write(&cmtp_session_sem); kfree(session); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index d112b2bc3798..2f9b2165ec95 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -216,10 +216,12 @@ static int conn_info_min_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val > hdev->conn_info_max_age) + hci_dev_lock(hdev); + if (val == 0 || val > hdev->conn_info_max_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_min_age = val; hci_dev_unlock(hdev); @@ -244,10 +246,12 @@ static int conn_info_max_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val < hdev->conn_info_min_age) + hci_dev_lock(hdev); + if (val == 0 || val < hdev->conn_info_min_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_max_age = val; hci_dev_unlock(hdev); @@ -565,10 +569,12 @@ static int sniff_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val > hdev->sniff_max_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val > hdev->sniff_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_min_interval = val; hci_dev_unlock(hdev); @@ -593,10 +599,12 @@ static int sniff_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val < hdev->sniff_min_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val < hdev->sniff_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_max_interval = val; hci_dev_unlock(hdev); @@ -848,10 +856,12 @@ static int conn_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_min_interval = val; hci_dev_unlock(hdev); @@ -876,10 +886,12 @@ static int conn_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_max_interval = val; hci_dev_unlock(hdev); @@ -988,10 +1000,12 @@ static int adv_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_min_interval = val; hci_dev_unlock(hdev); @@ -1016,10 +1030,12 @@ static int adv_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_max_interval = val; hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 0be37a5c1c0c..13d397493e9c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2729,6 +2729,31 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (test_bit(HCI_ENCRYPT, &hdev->flags)) set_bit(HCI_CONN_ENCRYPT, &conn->flags); + /* "Link key request" completed ahead of "connect request" completes */ + if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) && + ev->link_type == ACL_LINK) { + struct link_key *key; + struct hci_cp_read_enc_key_size cp; + + key = hci_find_link_key(hdev, &ev->bdaddr); + if (key) { + set_bit(HCI_CONN_ENCRYPT, &conn->flags); + + if (!(hdev->commands[20] & 0x10)) { + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } else { + cp.handle = cpu_to_le16(conn->handle); + if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, + sizeof(cp), &cp)) { + bt_dev_err(hdev, "sending read key size failed"); + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } + } + + hci_encrypt_cfm(conn, ev->status); + } + } + /* Get remote features */ if (conn->type == ACL_LINK) { struct hci_cp_read_remote_features cp; diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 021ab957a5c4..8ff45fb6f700 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -1305,7 +1305,7 @@ static int hidp_session_thread(void *arg) l2cap_unregister_user(session->conn, &session->user); hidp_session_put(session); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index c0389199c0dc..2f3ea11785ad 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1111,6 +1111,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) struct ebt_table_info *newinfo; struct ebt_replace tmp; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1422,6 +1424,8 @@ static int update_counters(struct net *net, sockptr_t arg, unsigned int len) { struct ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; @@ -2351,6 +2355,8 @@ static int compat_update_counters(struct net *net, sockptr_t arg, { struct compat_ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3dbefce8d14b..a42431860af9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3976,8 +3976,9 @@ int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) NAPI_GRO_CB(p)->count++; p->data_len += skb->len; - /* sk owenrship - if any - completely transferred to the aggregated packet */ + /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; + skb->sk = NULL; p->truesize += skb->truesize; p->len += skb->len; @@ -4425,8 +4426,9 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) } merge: - /* sk owenrship - if any - completely transferred to the aggregated packet */ + /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; + skb->sk = NULL; delta_truesize = skb->truesize; if (offset > headlen) { unsigned int eat = offset - headlen; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index ba6d5b38fb23..4e42bc679bac 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -413,6 +413,9 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock *sk; int err = 0; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + raw_spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) @@ -931,6 +934,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_elem *elem; int ret = -ENOENT; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 34763f575c30..9751bee3fb2f 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -1634,7 +1634,6 @@ EXPORT_SYMBOL_GPL(dsa_unregister_switch); void dsa_switch_shutdown(struct dsa_switch *ds) { struct net_device *master, *slave_dev; - LIST_HEAD(unregister_list); struct dsa_port *dp; mutex_lock(&dsa2_mutex); @@ -1655,25 +1654,13 @@ void dsa_switch_shutdown(struct dsa_switch *ds) slave_dev = dp->slave; netdev_upper_dev_unlink(master, slave_dev); - /* Just unlinking ourselves as uppers of the master is not - * sufficient. When the master net device unregisters, that will - * also call dev_close, which we will catch as NETDEV_GOING_DOWN - * and trigger a dev_close on our own devices (dsa_slave_close). - * In turn, that will call dev_mc_unsync on the master's net - * device. If the master is also a DSA switch port, this will - * trigger dsa_slave_set_rx_mode which will call dev_mc_sync on - * its own master. Lockdep will complain about the fact that - * all cascaded masters have the same dsa_master_addr_list_lock_key, - * which it normally would not do if the cascaded masters would - * be in a proper upper/lower relationship, which we've just - * destroyed. - * To suppress the lockdep warnings, let's actually unregister - * the DSA slave interfaces too, to avoid the nonsensical - * multicast address list synchronization on shutdown. - */ - unregister_netdevice_queue(slave_dev, &unregister_list); } - unregister_netdevice_many(&unregister_list); + + /* Disconnect from further netdevice notifiers on the master, + * since netdev_uses_dsa() will now return false. + */ + dsa_switch_for_each_cpu_port(dp, ds) + dp->master->dsa_ptr = NULL; rtnl_unlock(); out: diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index da43957a5843..27975a44d1f9 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -589,6 +589,20 @@ void inet_csk_clear_xmit_timers(struct sock *sk) } EXPORT_SYMBOL(inet_csk_clear_xmit_timers); +void inet_csk_clear_xmit_timers_sync(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + /* ongoing timer handlers need to acquire socket lock. */ + sock_not_owned_by_me(sk); + + icsk->icsk_pending = icsk->icsk_ack.pending = 0; + + sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer_sync(sk, &icsk->icsk_delack_timer); + sk_stop_timer_sync(sk, &sk->sk_timer); +} + void inet_csk_delete_keepalive_timer(struct sock *sk) { sk_stop_timer(sk, &sk->sk_timer); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5d17e5f5d090..cd967493bf37 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -280,8 +280,13 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, tpi->flags | TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); } else { + if (unlikely(!pskb_may_pull(skb, + gre_hdr_len + sizeof(*ershdr)))) + return PACKET_REJECT; + ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; + iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, iph->saddr, iph->daddr, tpi->key); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 71bf3aeed73c..07ecb16231cd 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -955,6 +955,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1253,6 +1255,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index a748a1e75460..1e1e7488d6bf 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1109,6 +1109,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1493,6 +1495,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 521c15962c71..16fd3da68e9f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2916,6 +2916,8 @@ void tcp_close(struct sock *sk, long timeout) lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); + if (!sk->sk_net_refcnt) + inet_csk_clear_xmit_timers_sync(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 2caf54c24103..c02f6329c106 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -601,6 +601,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); +EXPORT_SYMBOL(udp_encap_needed_key); + +#if IS_ENABLED(CONFIG_IPV6) +DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +EXPORT_SYMBOL(udpv6_encap_needed_key); +#endif + void udp_encap_enable(void) { static_branch_inc(&udp_encap_needed_key); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 86d32a1e62ac..7c6ac47b0bb1 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -515,11 +515,19 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; - /* we can do L4 aggregation only if the packet can't land in a tunnel - * otherwise we could corrupt the inner stream + /* We can do L4 aggregation only if the packet can't land in a tunnel + * otherwise we could corrupt the inner stream. Detecting such packets + * cannot be foolproof and the aggregation might still happen in some + * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { + /* If the packet was locally encapsulated in a UDP tunnel that + * wasn't detected above, do not GRO. + */ + if (skb->encapsulation) + goto out; + if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled : 1; @@ -683,13 +691,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 7e0a30380be0..bbb9ed6d1ae6 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -645,19 +645,19 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (!w) { /* New dump: * - * 1. hook callback destructor. - */ - cb->args[3] = (long)cb->done; - cb->done = fib6_dump_done; - - /* - * 2. allocate and initialize walker. + * 1. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) return -ENOMEM; w->func = fib6_dump_node; cb->args[2] = (long)w; + + /* 2. hook callback destructor. + */ + cb->args[3] = (long)cb->done; + cb->done = fib6_dump_done; + } arg.skb = skb; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 0efd5b4346b0..501630e3f1b6 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -533,6 +533,9 @@ static int ip6erspan_rcv(struct sk_buff *skb, struct ip6_tnl *tunnel; u8 ver; + if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr)))) + return PACKET_REJECT; + ipv6h = ipv6_hdr(skb); ershdr = (struct erspan_base_hdr *)skb->data; ver = ershdr->ver; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 277a5ee887eb..b17990d514ee 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1127,6 +1127,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1503,6 +1505,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d5d254ca2dfe..5a2abd179e08 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -473,7 +473,7 @@ csum_copy_err: goto try_again; } -DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_inc(&udpv6_encap_needed_key); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index b3d9ed96e5ea..28f63c01a595 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -170,13 +170,7 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 02bd90a53705..f277ce839ddb 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1845,15 +1845,14 @@ static int ieee80211_change_station(struct wiphy *wiphy, } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && - sta->sdata->u.vlan.sta) { - ieee80211_clear_fast_rx(sta); + sta->sdata->u.vlan.sta) RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL); - } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_dec_num_mcast(sta->sdata); sta->sdata = vlansdata; + ieee80211_check_fast_rx(sta); ieee80211_check_fast_xmit(sta); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 55550ead2ced..a4cc9d077c59 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -265,19 +265,27 @@ fail: return -ENOMEM; } +static void mac802154_llsec_key_del_rcu(struct rcu_head *rcu) +{ + struct ieee802154_llsec_key_entry *pos; + struct mac802154_llsec_key *mkey; + + pos = container_of(rcu, struct ieee802154_llsec_key_entry, rcu); + mkey = container_of(pos->key, struct mac802154_llsec_key, key); + + llsec_key_put(mkey); + kfree_sensitive(pos); +} + int mac802154_llsec_key_del(struct mac802154_llsec *sec, const struct ieee802154_llsec_key_id *key) { struct ieee802154_llsec_key_entry *pos; list_for_each_entry(pos, &sec->table.keys, list) { - struct mac802154_llsec_key *mkey; - - mkey = container_of(pos->key, struct mac802154_llsec_key, key); - if (llsec_key_id_equal(&pos->id, key)) { list_del_rcu(&pos->list); - llsec_key_put(mkey); + call_rcu(&pos->rcu, mac802154_llsec_key_del_rcu); return 0; } } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5db1c0142abb..cde62dafda49 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3018,9 +3018,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, sock_hold(new_mptcp_sock); newsk = new_mptcp_sock; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK); - } else { - MPTCP_INC_STATS(sock_net(sk), - MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); } out: diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 80230787554e..ff7239fe3d2c 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -725,6 +725,9 @@ create_child: goto dispose_child; } + if (fallback) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); + subflow_drop_ctx(child); goto out; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 42bf83a20cb5..113c1ebe4a5b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1139,6 +1139,24 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table) #define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \ __NFT_TABLE_F_WAS_AWAKEN) +static bool nft_table_pending_update(const struct nft_ctx *ctx) +{ + struct nftables_pernet *nft_net = nft_pernet(ctx->net); + struct nft_trans *trans; + + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return true; + + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->ctx.table == ctx->table && + trans->msg_type == NFT_MSG_DELCHAIN && + nft_is_base_chain(trans->ctx.chain)) + return true; + } + + return false; +} + static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; @@ -1162,7 +1180,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return -EOPNOTSUPP; /* No dormant off/on/off/on games in single transaction */ - if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + if (nft_table_pending_update(ctx)) return -EINVAL; trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, @@ -2303,6 +2321,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook; + if (table->flags & __NFT_TABLE_F_UPDATE) + return -EINVAL; + if (flags & NFT_CHAIN_BINDING) return -EOPNOTSUPP; @@ -4641,6 +4662,12 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) == (NFT_SET_EVAL | NFT_SET_OBJECT)) return -EOPNOTSUPP; + if ((flags & (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT | NFT_SET_EVAL)) == + (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; + if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) == + (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; } desc.dtype = 0; @@ -5062,6 +5089,7 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + set->dead = 1; if (event) nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_KERNEL); @@ -7683,11 +7711,12 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, return err; } +/* call under rcu_read_lock */ static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family) { const struct nf_flowtable_type *type; - list_for_each_entry(type, &nf_tables_flowtables, list) { + list_for_each_entry_rcu(type, &nf_tables_flowtables, list) { if (family == type->family) return type; } @@ -7699,9 +7728,13 @@ nft_flowtable_type_get(struct net *net, u8 family) { const struct nf_flowtable_type *type; + rcu_read_lock(); type = __nft_flowtable_type_get(family); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -9690,10 +9723,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) struct nft_trans *trans, *next; LIST_HEAD(set_update_list); struct nft_trans_elem *te; + int err = 0; if (action == NFNL_ABORT_VALIDATE && nf_tables_validate(net) < 0) - return -EAGAIN; + err = -EAGAIN; list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { @@ -9864,12 +9898,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nf_tables_abort_release(trans); } - if (action == NFNL_ABORT_AUTOLOAD) - nf_tables_module_autoload(net); - else - nf_tables_module_autoload_cleanup(net); - - return 0; + return err; } static int nf_tables_abort(struct net *net, struct sk_buff *skb, @@ -9883,6 +9912,16 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb, ret = __nf_tables_abort(net, action); nft_gc_seq_end(nft_net, gc_seq); + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + /* module autoload needs to happen after GC sequence update because it + * temporarily releases and grabs mutex again. + */ + if (action == NFNL_ABORT_AUTOLOAD) + nf_tables_module_autoload(net); + else + nf_tables_module_autoload_cleanup(net); + mutex_unlock(&nft_net->commit_mutex); return ret; @@ -10680,9 +10719,10 @@ static void __net_exit nf_tables_exit_net(struct net *net) gc_seq = nft_gc_seq_begin(nft_net); - if (!list_empty(&nft_net->commit_list) || - !list_empty(&nft_net->module_list)) - __nf_tables_abort(net, NFNL_ABORT_NONE); + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + if (!list_empty(&nft_net->module_list)) + nf_tables_module_autoload_cleanup(net); __nft_release_tables(net); @@ -10774,6 +10814,7 @@ static void __exit nf_tables_module_exit(void) unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); nft_chain_route_fini(); + nf_tables_trans_destroy_flush_work(); unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 419a1d0ba4c9..2a821f2b2ffe 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1516,6 +1516,11 @@ static void nci_rx_work(struct work_struct *work) nfc_send_to_raw_sock(ndev->nfc_dev, skb, RAW_PAYLOAD_NCI, NFC_DIRECTION_RX); + if (!nci_plen(skb->data)) { + kfree_skb(skb); + break; + } + /* Process frame */ switch (nci_mt(skb->data)) { case NCI_MT_RSP_PKT: diff --git a/net/rds/rdma.c b/net/rds/rdma.c index c29c7a59f205..3df0affff6b0 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -302,7 +302,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, } ret = PTR_ERR(trans_private); /* Trigger connection so that its ready for the next retry */ - if (ret == -ENODEV) + if (ret == -ENODEV && cp) rds_conn_connect_if_down(cp->cp_conn); goto out; } diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 2083612d8780..308ba1410072 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -240,13 +240,13 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_skbmod *d = to_skbmod(a); unsigned char *b = skb_tail_pointer(skb); struct tcf_skbmod_params *p; - struct tc_skbmod opt = { - .index = d->tcf_index, - .refcnt = refcount_read(&d->tcf_refcnt) - ref, - .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, - }; + struct tc_skbmod opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + opt.index = d->tcf_index; + opt.refcnt = refcount_read(&d->tcf_refcnt) - ref, + opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind; spin_lock_bh(&d->tcf_lock); opt.action = d->tcf_action; p = rcu_dereference_protected(d->skbmod_p, diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 79ee0618d919..c9e4b37e6577 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -796,6 +796,16 @@ static void smc_pnet_create_pnetids_list(struct net *net) u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; + /* Newly created netns do not have devices. + * Do not even acquire rtnl. + */ + if (list_empty(&net->dev_base_head)) + return; + + /* Note: This might not be needed, because smc_pnet_netdev_event() + * is also calling smc_pnet_add_base_pnetid() when handling + * NETDEV_UP event. + */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 36a3ad9336d6..9177b243a949 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -37,18 +37,37 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net); -#define svc_serv_is_pooled(serv) ((serv)->sv_ops->svo_function) - #define SVC_POOL_DEFAULT SVC_POOL_GLOBAL /* + * Mode for mapping cpus to pools. + */ +enum { + SVC_POOL_AUTO = -1, /* choose one of the others */ + SVC_POOL_GLOBAL, /* no mapping, just a single global pool + * (legacy & UP mode) */ + SVC_POOL_PERCPU, /* one pool per cpu */ + SVC_POOL_PERNODE /* one pool per numa node */ +}; + +/* * Structure for mapping cpus to pools and vice versa. * Setup once during sunrpc initialisation. */ -struct svc_pool_map svc_pool_map = { + +struct svc_pool_map { + int count; /* How many svc_servs use us */ + int mode; /* Note: int not enum to avoid + * warnings about "enumeration value + * not handled in switch" */ + unsigned int npools; + unsigned int *pool_to; /* maps pool id to cpu or node */ + unsigned int *to_pool; /* maps cpu or node to pool id */ +}; + +static struct svc_pool_map svc_pool_map = { .mode = SVC_POOL_DEFAULT }; -EXPORT_SYMBOL_GPL(svc_pool_map); static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */ @@ -219,10 +238,12 @@ svc_pool_map_init_pernode(struct svc_pool_map *m) /* * Add a reference to the global map of cpus to pools (and - * vice versa). Initialise the map if we're the first user. - * Returns the number of pools. + * vice versa) if pools are in use. + * Initialise the map if we're the first user. + * Returns the number of pools. If this is '1', no reference + * was taken. */ -unsigned int +static unsigned int svc_pool_map_get(void) { struct svc_pool_map *m = &svc_pool_map; @@ -232,6 +253,7 @@ svc_pool_map_get(void) if (m->count++) { mutex_unlock(&svc_pool_map_mutex); + WARN_ON_ONCE(m->npools <= 1); return m->npools; } @@ -247,30 +269,36 @@ svc_pool_map_get(void) break; } - if (npools < 0) { + if (npools <= 0) { /* default, or memory allocation failure */ npools = 1; m->mode = SVC_POOL_GLOBAL; } m->npools = npools; + if (npools == 1) + /* service is unpooled, so doesn't hold a reference */ + m->count--; + mutex_unlock(&svc_pool_map_mutex); - return m->npools; + return npools; } -EXPORT_SYMBOL_GPL(svc_pool_map_get); /* - * Drop a reference to the global map of cpus to pools. + * Drop a reference to the global map of cpus to pools, if + * pools were in use, i.e. if npools > 1. * When the last reference is dropped, the map data is * freed; this allows the sysadmin to change the pool * mode using the pool_mode module option without * rebooting or re-loading sunrpc.ko. */ -void -svc_pool_map_put(void) +static void +svc_pool_map_put(int npools) { struct svc_pool_map *m = &svc_pool_map; + if (npools <= 1) + return; mutex_lock(&svc_pool_map_mutex); if (!--m->count) { @@ -283,7 +311,6 @@ svc_pool_map_put(void) mutex_unlock(&svc_pool_map_mutex); } -EXPORT_SYMBOL_GPL(svc_pool_map_put); static int svc_pool_map_get_node(unsigned int pidx) { @@ -340,21 +367,18 @@ svc_pool_for_cpu(struct svc_serv *serv, int cpu) struct svc_pool_map *m = &svc_pool_map; unsigned int pidx = 0; - /* - * An uninitialised map happens in a pure client when - * lockd is brought up, so silently treat it the - * same as SVC_POOL_GLOBAL. - */ - if (svc_serv_is_pooled(serv)) { - switch (m->mode) { - case SVC_POOL_PERCPU: - pidx = m->to_pool[cpu]; - break; - case SVC_POOL_PERNODE: - pidx = m->to_pool[cpu_to_node(cpu)]; - break; - } + if (serv->sv_nrpools <= 1) + return serv->sv_pools; + + switch (m->mode) { + case SVC_POOL_PERCPU: + pidx = m->to_pool[cpu]; + break; + case SVC_POOL_PERNODE: + pidx = m->to_pool[cpu_to_node(cpu)]; + break; } + return &serv->sv_pools[pidx % serv->sv_nrpools]; } @@ -424,7 +448,7 @@ __svc_init_bc(struct svc_serv *serv) */ static struct svc_serv * __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, - const struct svc_serv_ops *ops) + int (*threadfn)(void *data)) { struct svc_serv *serv; unsigned int vers; @@ -435,13 +459,13 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, return NULL; serv->sv_name = prog->pg_name; serv->sv_program = prog; - serv->sv_nrthreads = 1; + kref_init(&serv->sv_refcnt); serv->sv_stats = prog->pg_stats; if (bufsize > RPCSVC_MAXPAYLOAD) bufsize = RPCSVC_MAXPAYLOAD; serv->sv_max_payload = bufsize? bufsize : 4096; serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE); - serv->sv_ops = ops; + serv->sv_threadfn = threadfn; xdrsize = 0; while (prog) { prog->pg_lovers = prog->pg_nvers-1; @@ -487,59 +511,56 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, return serv; } -struct svc_serv * -svc_create(struct svc_program *prog, unsigned int bufsize, - const struct svc_serv_ops *ops) +/** + * svc_create - Create an RPC service + * @prog: the RPC program the new service will handle + * @bufsize: maximum message size for @prog + * @threadfn: a function to service RPC requests for @prog + * + * Returns an instantiated struct svc_serv object or NULL. + */ +struct svc_serv *svc_create(struct svc_program *prog, unsigned int bufsize, + int (*threadfn)(void *data)) { - return __svc_create(prog, bufsize, /*npools*/1, ops); + return __svc_create(prog, bufsize, 1, threadfn); } EXPORT_SYMBOL_GPL(svc_create); -struct svc_serv * -svc_create_pooled(struct svc_program *prog, unsigned int bufsize, - const struct svc_serv_ops *ops) +/** + * svc_create_pooled - Create an RPC service with pooled threads + * @prog: the RPC program the new service will handle + * @bufsize: maximum message size for @prog + * @threadfn: a function to service RPC requests for @prog + * + * Returns an instantiated struct svc_serv object or NULL. + */ +struct svc_serv *svc_create_pooled(struct svc_program *prog, + unsigned int bufsize, + int (*threadfn)(void *data)) { struct svc_serv *serv; unsigned int npools = svc_pool_map_get(); - serv = __svc_create(prog, bufsize, npools, ops); + serv = __svc_create(prog, bufsize, npools, threadfn); if (!serv) goto out_err; return serv; out_err: - svc_pool_map_put(); + svc_pool_map_put(npools); return NULL; } EXPORT_SYMBOL_GPL(svc_create_pooled); -void svc_shutdown_net(struct svc_serv *serv, struct net *net) -{ - svc_close_net(serv, net); - - if (serv->sv_ops->svo_shutdown) - serv->sv_ops->svo_shutdown(serv, net); -} -EXPORT_SYMBOL_GPL(svc_shutdown_net); - /* * Destroy an RPC service. Should be called with appropriate locking to - * protect the sv_nrthreads, sv_permsocks and sv_tempsocks. + * protect sv_permsocks and sv_tempsocks. */ void -svc_destroy(struct svc_serv *serv) +svc_destroy(struct kref *ref) { - dprintk("svc: svc_destroy(%s, %d)\n", - serv->sv_program->pg_name, - serv->sv_nrthreads); - - if (serv->sv_nrthreads) { - if (--(serv->sv_nrthreads) != 0) { - svc_sock_update_bufs(serv); - return; - } - } else - printk("svc_destroy: no threads for serv=%p!\n", serv); + struct svc_serv *serv = container_of(ref, struct svc_serv, sv_refcnt); + dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name); del_timer_sync(&serv->sv_temptimer); /* @@ -551,8 +572,7 @@ svc_destroy(struct svc_serv *serv) cache_clean_deferred(serv); - if (svc_serv_is_pooled(serv)) - svc_pool_map_put(); + svc_pool_map_put(serv->sv_nrpools); kfree(serv->sv_pools); kfree(serv); @@ -638,7 +658,7 @@ out_enomem: } EXPORT_SYMBOL_GPL(svc_rqst_alloc); -struct svc_rqst * +static struct svc_rqst * svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) { struct svc_rqst *rqstp; @@ -647,14 +667,17 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) if (!rqstp) return ERR_PTR(-ENOMEM); - serv->sv_nrthreads++; + svc_get(serv); + spin_lock_bh(&serv->sv_lock); + serv->sv_nrthreads += 1; + spin_unlock_bh(&serv->sv_lock); + spin_lock_bh(&pool->sp_lock); pool->sp_nrthreads++; list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads); spin_unlock_bh(&pool->sp_lock); return rqstp; } -EXPORT_SYMBOL_GPL(svc_prepare_thread); /* * Choose a pool in which to create a new thread, for svc_set_num_threads @@ -728,11 +751,9 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) if (IS_ERR(rqstp)) return PTR_ERR(rqstp); - __module_get(serv->sv_ops->svo_module); - task = kthread_create_on_node(serv->sv_ops->svo_function, rqstp, + task = kthread_create_on_node(serv->sv_threadfn, rqstp, node, "%s", serv->sv_name); if (IS_ERR(task)) { - module_put(serv->sv_ops->svo_module); svc_exit_thread(rqstp); return PTR_ERR(task); } @@ -748,59 +769,13 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) return 0; } - -/* destroy old threads */ -static int -svc_signal_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) -{ - struct task_struct *task; - unsigned int state = serv->sv_nrthreads-1; - - /* destroy old threads */ - do { - task = choose_victim(serv, pool, &state); - if (task == NULL) - break; - send_sig(SIGINT, task, 1); - nrservs++; - } while (nrservs < 0); - - return 0; -} - /* * Create or destroy enough new threads to make the number * of threads the given number. If `pool' is non-NULL, applies * only to threads in that pool, otherwise round-robins between * all pools. Caller must ensure that mutual exclusion between this and * server startup or shutdown. - * - * Destroying threads relies on the service threads filling in - * rqstp->rq_task, which only the nfs ones do. Assumes the serv - * has been created using svc_create_pooled(). - * - * Based on code that used to be in nfsd_svc() but tweaked - * to be pool-aware. */ -int -svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) -{ - if (pool == NULL) { - /* The -1 assumes caller has done a svc_get() */ - nrservs -= (serv->sv_nrthreads-1); - } else { - spin_lock_bh(&pool->sp_lock); - nrservs -= pool->sp_nrthreads; - spin_unlock_bh(&pool->sp_lock); - } - - if (nrservs > 0) - return svc_start_kthreads(serv, pool, nrservs); - if (nrservs < 0) - return svc_signal_kthreads(serv, pool, nrservs); - return 0; -} -EXPORT_SYMBOL_GPL(svc_set_num_threads); /* destroy old threads */ static int @@ -825,11 +800,10 @@ svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) } int -svc_set_num_threads_sync(struct svc_serv *serv, struct svc_pool *pool, int nrservs) +svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { if (pool == NULL) { - /* The -1 assumes caller has done a svc_get() */ - nrservs -= (serv->sv_nrthreads-1); + nrservs -= serv->sv_nrthreads; } else { spin_lock_bh(&pool->sp_lock); nrservs -= pool->sp_nrthreads; @@ -842,7 +816,7 @@ svc_set_num_threads_sync(struct svc_serv *serv, struct svc_pool *pool, int nrser return svc_stop_kthreads(serv, pool, nrservs); return 0; } -EXPORT_SYMBOL_GPL(svc_set_num_threads_sync); +EXPORT_SYMBOL_GPL(svc_set_num_threads); /** * svc_rqst_replace_page - Replace one page in rq_pages[] @@ -894,11 +868,14 @@ svc_exit_thread(struct svc_rqst *rqstp) list_del_rcu(&rqstp->rq_all); spin_unlock_bh(&pool->sp_lock); + spin_lock_bh(&serv->sv_lock); + serv->sv_nrthreads -= 1; + spin_unlock_bh(&serv->sv_lock); + svc_sock_update_bufs(serv); + svc_rqst_free(rqstp); - /* Release the server */ - if (serv) - svc_destroy(serv); + svc_put(serv); } EXPORT_SYMBOL_GPL(svc_exit_thread); @@ -1265,7 +1242,7 @@ svc_generic_init_request(struct svc_rqst *rqstp, goto err_bad_proc; /* Initialize storage for argp and resp */ - memset(rqstp->rq_argp, 0, procp->pc_argsize); + memset(rqstp->rq_argp, 0, procp->pc_argzero); memset(rqstp->rq_resp, 0, procp->pc_ressize); /* Bump per-procedure stats counter */ @@ -1438,7 +1415,7 @@ release_dropit: svc_authorise(rqstp); close_xprt: if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags)) - svc_close_xprt(rqstp->rq_xprt); + svc_xprt_close(rqstp->rq_xprt); dprintk("svc: svc_process close\n"); return 0; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 2ea5c3f18fd4..d3ea5b4c854f 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -267,12 +267,12 @@ void svc_xprt_received(struct svc_xprt *xprt) trace_svc_xprt_received(xprt); /* As soon as we clear busy, the xprt could be closed and - * 'put', so we need a reference to call svc_enqueue_xprt with: + * 'put', so we need a reference to call svc_xprt_enqueue with: */ svc_xprt_get(xprt); smp_mb__before_atomic(); clear_bit(XPT_BUSY, &xprt->xpt_flags); - xprt->xpt_server->sv_ops->svo_enqueue_xprt(xprt); + svc_xprt_enqueue(xprt); svc_xprt_put(xprt); } EXPORT_SYMBOL_GPL(svc_xprt_received); @@ -286,7 +286,7 @@ void svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *new) svc_xprt_received(new); } -static int _svc_create_xprt(struct svc_serv *serv, const char *xprt_name, +static int _svc_xprt_create(struct svc_serv *serv, const char *xprt_name, struct net *net, const int family, const unsigned short port, int flags, const struct cred *cred) @@ -322,21 +322,35 @@ static int _svc_create_xprt(struct svc_serv *serv, const char *xprt_name, return -EPROTONOSUPPORT; } -int svc_create_xprt(struct svc_serv *serv, const char *xprt_name, +/** + * svc_xprt_create - Add a new listener to @serv + * @serv: target RPC service + * @xprt_name: transport class name + * @net: network namespace + * @family: network address family + * @port: listener port + * @flags: SVC_SOCK flags + * @cred: credential to bind to this transport + * + * Return values: + * %0: New listener added successfully + * %-EPROTONOSUPPORT: Requested transport type not supported + */ +int svc_xprt_create(struct svc_serv *serv, const char *xprt_name, struct net *net, const int family, const unsigned short port, int flags, const struct cred *cred) { int err; - err = _svc_create_xprt(serv, xprt_name, net, family, port, flags, cred); + err = _svc_xprt_create(serv, xprt_name, net, family, port, flags, cred); if (err == -EPROTONOSUPPORT) { request_module("svc%s", xprt_name); - err = _svc_create_xprt(serv, xprt_name, net, family, port, flags, cred); + err = _svc_xprt_create(serv, xprt_name, net, family, port, flags, cred); } return err; } -EXPORT_SYMBOL_GPL(svc_create_xprt); +EXPORT_SYMBOL_GPL(svc_xprt_create); /* * Copy the local and remote xprt addresses to the rqstp structure @@ -412,6 +426,8 @@ static bool svc_xprt_ready(struct svc_xprt *xprt) smp_rmb(); xpt_flags = READ_ONCE(xprt->xpt_flags); + if (xpt_flags & BIT(XPT_BUSY)) + return false; if (xpt_flags & (BIT(XPT_CONN) | BIT(XPT_CLOSE))) return true; if (xpt_flags & (BIT(XPT_DATA) | BIT(XPT_DEFERRED))) { @@ -424,7 +440,12 @@ static bool svc_xprt_ready(struct svc_xprt *xprt) return false; } -void svc_xprt_do_enqueue(struct svc_xprt *xprt) +/** + * svc_xprt_enqueue - Queue a transport on an idle nfsd thread + * @xprt: transport with data pending + * + */ +void svc_xprt_enqueue(struct svc_xprt *xprt) { struct svc_pool *pool; struct svc_rqst *rqstp = NULL; @@ -468,19 +489,6 @@ out_unlock: put_cpu_light(); trace_svc_xprt_do_enqueue(xprt, rqstp); } -EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue); - -/* - * Queue up a transport with data pending. If there are idle nfsd - * processes, wake 'em up. - * - */ -void svc_xprt_enqueue(struct svc_xprt *xprt) -{ - if (test_bit(XPT_BUSY, &xprt->xpt_flags)) - return; - xprt->xpt_server->sv_ops->svo_enqueue_xprt(xprt); -} EXPORT_SYMBOL_GPL(svc_xprt_enqueue); /* @@ -1070,7 +1078,12 @@ static void svc_delete_xprt(struct svc_xprt *xprt) svc_xprt_put(xprt); } -void svc_close_xprt(struct svc_xprt *xprt) +/** + * svc_xprt_close - Close a client connection + * @xprt: transport to disconnect + * + */ +void svc_xprt_close(struct svc_xprt *xprt) { trace_svc_xprt_close(xprt); set_bit(XPT_CLOSE, &xprt->xpt_flags); @@ -1085,7 +1098,7 @@ void svc_close_xprt(struct svc_xprt *xprt) */ svc_delete_xprt(xprt); } -EXPORT_SYMBOL_GPL(svc_close_xprt); +EXPORT_SYMBOL_GPL(svc_xprt_close); static int svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, struct net *net) { @@ -1137,7 +1150,11 @@ static void svc_clean_up_xprts(struct svc_serv *serv, struct net *net) } } -/* +/** + * svc_xprt_destroy_all - Destroy transports associated with @serv + * @serv: RPC service to be shut down + * @net: target network namespace + * * Server threads may still be running (especially in the case where the * service is still running in other network namespaces). * @@ -1149,7 +1166,7 @@ static void svc_clean_up_xprts(struct svc_serv *serv, struct net *net) * threads, we may need to wait a little while and then check again to * see if they're done. */ -void svc_close_net(struct svc_serv *serv, struct net *net) +void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net) { int delay = 0; @@ -1160,6 +1177,7 @@ void svc_close_net(struct svc_serv *serv, struct net *net) msleep(delay++); } } +EXPORT_SYMBOL_GPL(svc_xprt_destroy_all); /* * Handle defer and revisit of requests diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index be7081284a09..112236dd7290 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1334,25 +1334,10 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, return svsk; } -bool svc_alien_sock(struct net *net, int fd) -{ - int err; - struct socket *sock = sockfd_lookup(fd, &err); - bool ret = false; - - if (!sock) - goto out; - if (sock_net(sock->sk) != net) - ret = true; - sockfd_put(sock); -out: - return ret; -} -EXPORT_SYMBOL_GPL(svc_alien_sock); - /** * svc_addsock - add a listener socket to an RPC service * @serv: pointer to RPC service to which to add a new listener + * @net: caller's network namespace * @fd: file descriptor of the new listener * @name_return: pointer to buffer to fill in with name of listener * @len: size of the buffer @@ -1362,8 +1347,8 @@ EXPORT_SYMBOL_GPL(svc_alien_sock); * Name is terminated with '\n'. On error, returns a negative errno * value. */ -int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, - const size_t len, const struct cred *cred) +int svc_addsock(struct svc_serv *serv, struct net *net, const int fd, + char *name_return, const size_t len, const struct cred *cred) { int err = 0; struct socket *so = sockfd_lookup(fd, &err); @@ -1374,6 +1359,9 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, if (!so) return err; + err = -EINVAL; + if (sock_net(so->sk) != net) + goto out; err = -EAFNOSUPPORT; if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6)) goto out; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index f0a0a4ad6d52..b227d0c8471f 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -919,6 +919,28 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, EXPORT_SYMBOL_GPL(xdr_init_encode); /** + * xdr_init_encode_pages - Initialize an xdr_stream for encoding into pages + * @xdr: pointer to xdr_stream struct + * @buf: pointer to XDR buffer into which to encode data + * @pages: list of pages to decode into + * @rqst: pointer to controlling rpc_rqst, for debugging + * + */ +void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, + struct page **pages, struct rpc_rqst *rqst) +{ + xdr_reset_scratch_buffer(xdr); + + xdr->buf = buf; + xdr->page_ptr = pages; + xdr->iov = NULL; + xdr->p = page_address(*pages); + xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE); + xdr->rqst = rqst; +} +EXPORT_SYMBOL_GPL(xdr_init_encode_pages); + +/** * xdr_commit_encode - Ensure all data is written to buffer * @xdr: pointer to xdr_stream * diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index 16897fcb659c..85c8cdda98b1 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -198,7 +198,7 @@ static int xprt_rdma_bc_send_request(struct rpc_rqst *rqst) ret = rpcrdma_bc_send_request(rdma, rqst); if (ret == -ENOTCONN) - svc_close_xprt(sxprt); + svc_xprt_close(sxprt); return ret; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ff56b6a0162e..d65f781f7a36 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1850,6 +1850,9 @@ static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb) if (xp->xfrm_nr == 0) return 0; + if (xp->xfrm_nr > XFRM_MAX_DEPTH) + return -ENOBUFS; + for (i = 0; i < xp->xfrm_nr; i++) { struct xfrm_user_tmpl *up = &vec[i]; struct xfrm_tmpl *kp = &xp->xfrm_vec[i]; diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index f182700e0ac1..6881a0c96bc1 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -53,6 +53,8 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast) KBUILD_CFLAGS += -Wno-tautological-constant-out-of-range-compare KBUILD_CFLAGS += $(call cc-disable-warning, unaligned-access) KBUILD_CFLAGS += $(call cc-disable-warning, cast-function-type-strict) +KBUILD_CFLAGS += -Wno-enum-compare-conditional +KBUILD_CFLAGS += -Wno-enum-enum-conversion endif endif diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c index b04aa8e91a41..e5c63f806ef2 100644 --- a/scripts/gcc-plugins/stackleak_plugin.c +++ b/scripts/gcc-plugins/stackleak_plugin.c @@ -463,6 +463,12 @@ static bool stackleak_gate(void) return false; if (STRING_EQUAL(section, ".meminit.text")) return false; + if (STRING_EQUAL(section, ".noinstr.text")) + return false; + if (STRING_EQUAL(section, ".entry.text")) + return false; + if (STRING_EQUAL(section, ".head.text")) + return false; } return track_frame_size >= 0; diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index 507d43827afe..229a6918b52f 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -32,6 +32,18 @@ #include "ruleset.h" #include "setup.h" +static bool is_initialized(void) +{ + if (likely(landlock_initialized)) + return true; + + pr_warn_once( + "Disabled but requested by user space. " + "You should enable Landlock at boot time: " + "https://docs.kernel.org/userspace-api/landlock.html#boot-time-configuration\n"); + return false; +} + /** * copy_min_struct_from_user - Safe future-proof argument copying * @@ -165,7 +177,7 @@ SYSCALL_DEFINE3(landlock_create_ruleset, /* Build-time checks. */ build_check_abi(); - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; if (flags) { @@ -311,7 +323,7 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, struct landlock_ruleset *ruleset; int res, err; - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; /* No flag for now. */ @@ -402,7 +414,7 @@ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, struct landlock_cred_security *new_llcred; int err; - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; /* diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 894d170c2f9a..292b50bdfc9f 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1266,7 +1266,8 @@ static int smack_inode_setxattr(struct user_namespace *mnt_userns, check_star = 1; } else if (strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0) { check_priv = 1; - if (size != TRANS_TRUE_SIZE || + if (!S_ISDIR(d_backing_inode(dentry)->i_mode) || + size != TRANS_TRUE_SIZE || strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0) rc = -EINVAL; } else @@ -2722,6 +2723,15 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name, if (value == NULL || size > SMK_LONGLABEL || size == 0) return -EINVAL; + if (strcmp(name, XATTR_SMACK_TRANSMUTE) == 0) { + if (!S_ISDIR(inode->i_mode) || size != TRANS_TRUE_SIZE || + strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0) + return -EINVAL; + + nsp->smk_flags |= SMK_INODE_TRANSMUTE; + return 0; + } + skp = smk_import_entry(value, size); if (IS_ERR(skp)) return PTR_ERR(skp); diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index f8b644cb9157..875312568369 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -771,10 +771,14 @@ static int check_cip_header(struct amdtp_stream *s, const __be32 *buf, } else { unsigned int dbc_interval; - if (*data_blocks > 0 && s->ctx_data.tx.dbc_interval > 0) - dbc_interval = s->ctx_data.tx.dbc_interval; - else - dbc_interval = *data_blocks; + if (!(s->flags & CIP_DBC_IS_PAYLOAD_QUADLETS)) { + if (*data_blocks > 0 && s->ctx_data.tx.dbc_interval > 0) + dbc_interval = s->ctx_data.tx.dbc_interval; + else + dbc_interval = *data_blocks; + } else { + dbc_interval = payload_length / sizeof(__be32); + } lost = dbc != ((*data_block_counter + dbc_interval) & 0xff); } diff --git a/sound/firewire/amdtp-stream.h b/sound/firewire/amdtp-stream.h index 1f957c946c95..cf9ab347277f 100644 --- a/sound/firewire/amdtp-stream.h +++ b/sound/firewire/amdtp-stream.h @@ -37,6 +37,9 @@ * the value of current SYT_INTERVAL; e.g. initial value is not zero. * @CIP_UNAWARE_SYT: For outgoing packet, the value in SYT field of CIP is 0xffff. * For incoming packet, the value in SYT field of CIP is not handled. + * @CIP_DBC_IS_PAYLOAD_QUADLETS: Available for incoming packet, and only effective with + * CIP_DBC_IS_END_EVENT flag. The value of dbc field is the number of accumulated quadlets + * in CIP payload, instead of the number of accumulated data blocks. */ enum cip_flags { CIP_NONBLOCKING = 0x00, @@ -51,6 +54,7 @@ enum cip_flags { CIP_NO_HEADER = 0x100, CIP_UNALIGHED_DBC = 0x200, CIP_UNAWARE_SYT = 0x400, + CIP_DBC_IS_PAYLOAD_QUADLETS = 0x800, }; /** diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 200d0b953d3b..94859fdd1da0 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9270,7 +9270,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x124c, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), - SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), + SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP), @@ -10783,8 +10783,7 @@ static void alc897_hp_automute_hook(struct hda_codec *codec, snd_hda_gen_hp_automute(codec, jack); vref = spec->gen.hp_jack_present ? (PIN_HP | AC_PINCTL_VREF_100) : PIN_HP; - snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, - vref); + snd_hda_set_pin_ctl(codec, 0x1b, vref); } static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec, @@ -10793,6 +10792,10 @@ static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec, struct alc_spec *spec = codec->spec; if (action == HDA_FIXUP_ACT_PRE_PROBE) { spec->gen.hp_automute_hook = alc897_hp_automute_hook; + spec->no_shutup_pins = 1; + } + if (action == HDA_FIXUP_ACT_PROBE) { + snd_hda_set_pin_ctl_cache(codec, 0x1a, PIN_IN | AC_PINCTL_VREF_100); } } diff --git a/sound/sh/aica.c b/sound/sh/aica.c index 6e9d6bd67369..8b47bfcd9031 100644 --- a/sound/sh/aica.c +++ b/sound/sh/aica.c @@ -278,7 +278,8 @@ static void run_spu_dma(struct work_struct *work) dreamcastcard->clicks++; if (unlikely(dreamcastcard->clicks >= AICA_PERIOD_NUMBER)) dreamcastcard->clicks %= AICA_PERIOD_NUMBER; - mod_timer(&dreamcastcard->timer, jiffies + 1); + if (snd_pcm_running(dreamcastcard->substream)) + mod_timer(&dreamcastcard->timer, jiffies + 1); } } @@ -290,6 +291,8 @@ static void aica_period_elapsed(struct timer_list *t) /*timer function - so cannot sleep */ int play_period; struct snd_pcm_runtime *runtime; + if (!snd_pcm_running(substream)) + return; runtime = substream->runtime; dreamcastcard = substream->pcm->private_data; /* Have we played out an additional period? */ @@ -350,12 +353,19 @@ static int snd_aicapcm_pcm_open(struct snd_pcm_substream return 0; } +static int snd_aicapcm_pcm_sync_stop(struct snd_pcm_substream *substream) +{ + struct snd_card_aica *dreamcastcard = substream->pcm->private_data; + + del_timer_sync(&dreamcastcard->timer); + cancel_work_sync(&dreamcastcard->spu_dma_work); + return 0; +} + static int snd_aicapcm_pcm_close(struct snd_pcm_substream *substream) { struct snd_card_aica *dreamcastcard = substream->pcm->private_data; - flush_work(&(dreamcastcard->spu_dma_work)); - del_timer(&dreamcastcard->timer); dreamcastcard->substream = NULL; kfree(dreamcastcard->channel); spu_disable(); @@ -401,6 +411,7 @@ static const struct snd_pcm_ops snd_aicapcm_playback_ops = { .prepare = snd_aicapcm_pcm_prepare, .trigger = snd_aicapcm_pcm_trigger, .pointer = snd_aicapcm_pcm_pointer, + .sync_stop = snd_aicapcm_pcm_sync_stop, }; /* TO DO: set up to handle more than one pcm instance */ diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c index 9fdd9afe00da..f452245b210f 100644 --- a/sound/soc/codecs/rt5682-sdw.c +++ b/sound/soc/codecs/rt5682-sdw.c @@ -787,12 +787,12 @@ static int __maybe_unused rt5682_dev_resume(struct device *dev) return 0; if (!slave->unattach_request) { + mutex_lock(&rt5682->disable_irq_lock); if (rt5682->disable_irq == true) { - mutex_lock(&rt5682->disable_irq_lock); sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF); rt5682->disable_irq = false; - mutex_unlock(&rt5682->disable_irq_lock); } + mutex_unlock(&rt5682->disable_irq_lock); goto regmap_sync; } diff --git a/sound/soc/codecs/rt711-sdca-sdw.c b/sound/soc/codecs/rt711-sdca-sdw.c index 4faf6b8544dd..25e8b9906f31 100644 --- a/sound/soc/codecs/rt711-sdca-sdw.c +++ b/sound/soc/codecs/rt711-sdca-sdw.c @@ -443,13 +443,13 @@ static int __maybe_unused rt711_sdca_dev_resume(struct device *dev) return 0; if (!slave->unattach_request) { + mutex_lock(&rt711->disable_irq_lock); if (rt711->disable_irq == true) { - mutex_lock(&rt711->disable_irq_lock); sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_0); sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8); rt711->disable_irq = false; - mutex_unlock(&rt711->disable_irq_lock); } + mutex_unlock(&rt711->disable_irq_lock); goto regmap_sync; } diff --git a/sound/soc/codecs/rt711-sdw.c b/sound/soc/codecs/rt711-sdw.c index 9545b8a7eb19..af7a0ab5669f 100644 --- a/sound/soc/codecs/rt711-sdw.c +++ b/sound/soc/codecs/rt711-sdw.c @@ -542,12 +542,12 @@ static int __maybe_unused rt711_dev_resume(struct device *dev) return 0; if (!slave->unattach_request) { + mutex_lock(&rt711->disable_irq_lock); if (rt711->disable_irq == true) { - mutex_lock(&rt711->disable_irq_lock); sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF); rt711->disable_irq = false; - mutex_unlock(&rt711->disable_irq_lock); } + mutex_unlock(&rt711->disable_irq_lock); goto regmap_sync; } diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index a5b3ee69fb88..1c4d8b96f77b 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1042,6 +1042,9 @@ int snd_soc_add_pcm_runtime(struct snd_soc_card *card, if (!snd_soc_is_matching_component(platform, component)) continue; + if (snd_soc_component_is_dummy(component) && component->num_dai) + continue; + snd_soc_rtd_add_component(rtd, component); } } diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index c56379fac927..57caa91a4376 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -246,7 +246,7 @@ int snd_soc_get_volsw(struct snd_kcontrol *kcontrol, int max = mc->max; int min = mc->min; int sign_bit = mc->sign_bit; - unsigned int mask = (1 << fls(max)) - 1; + unsigned int mask = (1ULL << fls(max)) - 1; unsigned int invert = mc->invert; int val; int ret; diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c index 6a00a6eecaef..c5c5082cb24e 100644 --- a/tools/iio/iio_utils.c +++ b/tools/iio/iio_utils.c @@ -376,7 +376,7 @@ int build_channel_array(const char *device_dir, int buffer_idx, goto error_close_dir; } - seekdir(dp, 0); + rewinddir(dp); while (ent = readdir(dp), ent) { if (strcmp(ent->d_name + strlen(ent->d_name) - strlen("_en"), "_en") == 0) { diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 5146ff0fa078..6aa1c35273a1 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -224,10 +224,10 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist) static void perf_evlist__id_hash(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id) + int cpu_map_idx, int thread, u64 id) { int hash; - struct perf_sample_id *sid = SID(evsel, cpu, thread); + struct perf_sample_id *sid = SID(evsel, cpu_map_idx, thread); sid->id = id; sid->evsel = evsel; @@ -245,21 +245,27 @@ void perf_evlist__reset_id_hash(struct perf_evlist *evlist) void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id) + int cpu_map_idx, int thread, u64 id) { - perf_evlist__id_hash(evlist, evsel, cpu, thread, id); + if (!SID(evsel, cpu_map_idx, thread)) + return; + + perf_evlist__id_hash(evlist, evsel, cpu_map_idx, thread, id); evsel->id[evsel->ids++] = id; } int perf_evlist__id_add_fd(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, int fd) + int cpu_map_idx, int thread, int fd) { u64 read_data[4] = { 0, }; int id_idx = 1; /* The first entry is the counter value */ u64 id; int ret; + if (!SID(evsel, cpu_map_idx, thread)) + return -1; + ret = ioctl(fd, PERF_EVENT_IOC_ID, &id); if (!ret) goto add; @@ -288,7 +294,7 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist, id = read_data[id_idx]; add: - perf_evlist__id_add(evlist, evsel, cpu, thread, id); + perf_evlist__id_add(evlist, evsel, cpu_map_idx, thread, id); return 0; } diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index f366dbad6a88..49b17b2b3923 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -119,11 +119,11 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist); void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id); + int cpu_map_idx, int thread, u64 id); int perf_evlist__id_add_fd(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, int fd); + int cpu_map_idx, int thread, int fd); void perf_evlist__reset_id_hash(struct perf_evlist *evlist); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index c3bb96e5bfa6..fd6714de2260 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -169,8 +169,9 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "panic", "do_exit", "do_task_dead", + "kthread_exit", "make_task_dead", - "__module_put_and_exit", + "__module_put_and_kthread_exit", "complete_and_exit", "__reiserfs_panic", "lbug_with_loc", diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index 5fd9e594079c..ebda9c366b2b 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -1241,6 +1241,7 @@ unsigned int get_pkg_num(int cpu) retval = fscanf(fp, "%d\n", &pkg); if (retval != 1) errx(1, "%s: failed to parse", pathname); + fclose(fp); return pkg; } diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index e6c381498e63..449e45bd6966 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -836,6 +836,7 @@ sub set_value { if ($lvalue =~ /^(TEST|BISECT|CONFIG_BISECT)_TYPE(\[.*\])?$/ && $prvalue !~ /^(config_|)bisect$/ && $prvalue !~ /^build$/ && + $prvalue !~ /^make_warnings_file$/ && $buildonly) { # Note if a test is something other than build, then we diff --git a/tools/testing/selftests/mqueue/setting b/tools/testing/selftests/mqueue/setting new file mode 100644 index 000000000000..a953c96aa16e --- /dev/null +++ b/tools/testing/selftests/mqueue/setting @@ -0,0 +1 @@ +timeout=180 diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 57a681107f73..a8178a9c1e10 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -53,7 +53,7 @@ __chk_nr() printf "%-50s" "$msg" if [ $nr != $expected ]; then echo "[ fail ] expected $expected found $nr" - ret=$test_cnt + ret=${KSFT_FAIL} else echo "[ ok ]" fi @@ -88,10 +88,10 @@ wait_msk_nr() printf "%-50s" "$msg" if [ $i -ge $timeout ]; then echo "[ fail ] timeout while expecting $expected max $max last $nr" - ret=$test_cnt + ret=${KSFT_FAIL} elif [ $nr != $expected ]; then echo "[ fail ] expected $expected found $nr" - ret=$test_cnt + ret=${KSFT_FAIL} else echo "[ ok ]" fi diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 8efff3f9c52a..5a1277d17286 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -451,6 +451,7 @@ do_transfer() local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") local stat_csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") local stat_csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local stat_tcpfb_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -516,6 +517,7 @@ do_transfer() local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue") + local stat_tcpfb_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -560,6 +562,11 @@ do_transfer() fi fi + if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then + printf "[ FAIL ]\nunexpected fallback to TCP" + rets=1 + fi + if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then printf "[ OK ]" fi diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c index 7c5b12664b03..bfb07dc49518 100644 --- a/tools/testing/selftests/net/reuseaddr_conflict.c +++ b/tools/testing/selftests/net/reuseaddr_conflict.c @@ -109,6 +109,6 @@ int main(void) fd1 = open_port(0, 1); if (fd1 >= 0) error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6"); - fprintf(stderr, "Success"); + fprintf(stderr, "Success\n"); return 0; } diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index fa5aa588e53f..ade308fb1ac7 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -238,7 +238,7 @@ for family in 4 6; do create_vxlan_pair ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on - run_test "GRO frag list over UDP tunnel" $OL_NET$DST 1 1 + run_test "GRO frag list over UDP tunnel" $OL_NET$DST 10 10 cleanup # use NAT to circumvent GRO FWD check @@ -251,13 +251,7 @@ for family in 4 6; do # load arp cache before running the test to reduce the amount of # stray traffic on top of the UDP tunnel ip netns exec $NS_SRC $PING -q -c 1 $OL_NET$DST_NAT >/dev/null - run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST - cleanup - - create_vxlan_pair - run_bench "UDP tunnel fwd perf" $OL_NET$DST - ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on - run_bench "UDP tunnel GRO fwd perf" $OL_NET$DST + run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 10 10 $OL_NET$DST cleanup done diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index dd777688d14a..952afb1bc83b 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -88,7 +88,27 @@ static void async_pf_execute(struct work_struct *work) rcuwait_wake_up(&vcpu->wait); mmput(mm); - kvm_put_kvm(vcpu->kvm); +} + +static void kvm_flush_and_free_async_pf_work(struct kvm_async_pf *work) +{ + /* + * The async #PF is "done", but KVM must wait for the work item itself, + * i.e. async_pf_execute(), to run to completion. If KVM is a module, + * KVM must ensure *no* code owned by the KVM (the module) can be run + * after the last call to module_put(). Note, flushing the work item + * is always required when the item is taken off the completion queue. + * E.g. even if the vCPU handles the item in the "normal" path, the VM + * could be terminated before async_pf_execute() completes. + * + * Wake all events skip the queue and go straight done, i.e. don't + * need to be flushed (but sanity check that the work wasn't queued). + */ + if (work->wakeup_all) + WARN_ON_ONCE(work->work.func); + else + flush_work(&work->work); + kmem_cache_free(async_pf_cache, work); } void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) @@ -115,7 +135,6 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) #else if (cancel_work_sync(&work->work)) { mmput(work->mm); - kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */ kmem_cache_free(async_pf_cache, work); } #endif @@ -127,7 +146,10 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) list_first_entry(&vcpu->async_pf.done, typeof(*work), link); list_del(&work->link); - kmem_cache_free(async_pf_cache, work); + + spin_unlock(&vcpu->async_pf.lock); + kvm_flush_and_free_async_pf_work(work); + spin_lock(&vcpu->async_pf.lock); } spin_unlock(&vcpu->async_pf.lock); @@ -152,7 +174,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) list_del(&work->queue); vcpu->async_pf.queued--; - kmem_cache_free(async_pf_cache, work); + kvm_flush_and_free_async_pf_work(work); } } @@ -187,7 +209,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, work->arch = *arch; work->mm = current->mm; mmget(work->mm); - kvm_get_kvm(work->vcpu->kvm); INIT_WORK(&work->work, async_pf_execute); |