aboutsummaryrefslogtreecommitdiff
path: root/include/linux
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux')
-rw-r--r--include/linux/backing-file.h42
-rw-r--r--include/linux/blk_types.h8
-rw-r--r--include/linux/blkdev.h31
-rw-r--r--include/linux/cleanup.h52
-rw-r--r--include/linux/cpuhotplug.h16
-rw-r--r--include/linux/device.h2
-rw-r--r--include/linux/edac.h3
-rw-r--r--include/linux/entry-common.h95
-rw-r--r--include/linux/eventfd.h17
-rw-r--r--include/linux/export-internal.h6
-rw-r--r--include/linux/fdtable.h19
-rw-r--r--include/linux/file.h12
-rw-r--r--include/linux/fs.h124
-rw-r--r--include/linux/fsnotify.h50
-rw-r--r--include/linux/hid-sensor-ids.h4
-rw-r--r--include/linux/lockdep_types.h2
-rw-r--r--include/linux/mnt_idmapping.h3
-rw-r--r--include/linux/mount.h5
-rw-r--r--include/linux/mutex.h3
-rw-r--r--include/linux/nubus.h2
-rw-r--r--include/linux/osq_lock.h5
-rw-r--r--include/linux/pci.h2
-rw-r--r--include/linux/pci_ids.h2
-rw-r--r--include/linux/perf/arm_pmu.h28
-rw-r--r--include/linux/perf/arm_pmuv3.h34
-rw-r--r--include/linux/perf_event.h22
-rw-r--r--include/linux/phy.h1
-rw-r--r--include/linux/rwsem.h8
-rw-r--r--include/linux/sched/task.h2
-rw-r--r--include/linux/spinlock.h41
-rw-r--r--include/linux/splice.h51
-rw-r--r--include/linux/syscalls.h8
-rw-r--r--include/linux/uidgid.h13
-rw-r--r--include/linux/uio.h2
-rw-r--r--include/linux/writeback.h1
35 files changed, 544 insertions, 172 deletions
diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h
new file mode 100644
index 000000000000..3f1fe1774f1b
--- /dev/null
+++ b/include/linux/backing-file.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Common helpers for stackable filesystems and backing files.
+ *
+ * Copyright (C) 2023 CTERA Networks.
+ */
+
+#ifndef _LINUX_BACKING_FILE_H
+#define _LINUX_BACKING_FILE_H
+
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/fs.h>
+
+struct backing_file_ctx {
+ const struct cred *cred;
+ struct file *user_file;
+ void (*accessed)(struct file *);
+ void (*end_write)(struct file *);
+};
+
+struct file *backing_file_open(const struct path *user_path, int flags,
+ const struct path *real_path,
+ const struct cred *cred);
+ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,
+ struct kiocb *iocb, int flags,
+ struct backing_file_ctx *ctx);
+ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
+ struct kiocb *iocb, int flags,
+ struct backing_file_ctx *ctx);
+ssize_t backing_file_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags,
+ struct backing_file_ctx *ctx);
+ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
+ struct file *out, loff_t *ppos, size_t len,
+ unsigned int flags,
+ struct backing_file_ctx *ctx);
+int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
+ struct backing_file_ctx *ctx);
+
+#endif /* _LINUX_BACKING_FILE_H */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index b29ebd53417d..7c2316c91cbd 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -57,20 +57,18 @@ struct block_device {
void * bd_holder;
const struct blk_holder_ops *bd_holder_ops;
struct mutex bd_holder_lock;
- /* The counter of freeze processes */
- int bd_fsfreeze_count;
int bd_holders;
struct kobject *bd_holder_dir;
- /* Mutex for freeze */
- struct mutex bd_fsfreeze_mutex;
- struct super_block *bd_fsfreeze_sb;
+ atomic_t bd_fsfreeze_count; /* number of freeze requests */
+ struct mutex bd_fsfreeze_mutex; /* serialize freeze/thaw */
struct partition_meta_info *bd_meta_info;
#ifdef CONFIG_FAIL_MAKE_REQUEST
bool bd_make_it_fail;
#endif
bool bd_ro_warned;
+ int bd_writers;
/*
* keep this out-of-line as it's both big and not needed in the fast
* path
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 51fa7ffdee83..c30a98e08423 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -124,6 +124,8 @@ typedef unsigned int __bitwise blk_mode_t;
#define BLK_OPEN_NDELAY ((__force blk_mode_t)(1 << 3))
/* open for "writes" only for ioctls (specialy hack for floppy.c) */
#define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4))
+/* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */
+#define BLK_OPEN_RESTRICT_WRITES ((__force blk_mode_t)(1 << 5))
struct gendisk {
/*
@@ -538,7 +540,7 @@ struct request_queue {
#define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */
#define QUEUE_FLAG_SYNCHRONOUS 11 /* always completes in submit context */
#define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */
-#define QUEUE_FLAG_HW_WC 18 /* Write back caching supported */
+#define QUEUE_FLAG_HW_WC 13 /* Write back caching supported */
#define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */
#define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */
#define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */
@@ -1468,8 +1470,23 @@ struct blk_holder_ops {
* Sync the file system mounted on the block device.
*/
void (*sync)(struct block_device *bdev);
+
+ /*
+ * Freeze the file system mounted on the block device.
+ */
+ int (*freeze)(struct block_device *bdev);
+
+ /*
+ * Thaw the file system mounted on the block device.
+ */
+ int (*thaw)(struct block_device *bdev);
};
+/*
+ * For filesystems using @fs_holder_ops, the @holder argument passed to
+ * helpers used to open and claim block devices via
+ * bd_prepare_to_claim() must point to a superblock.
+ */
extern const struct blk_holder_ops fs_holder_ops;
/*
@@ -1477,7 +1494,8 @@ extern const struct blk_holder_ops fs_holder_ops;
* as stored in sb->s_flags.
*/
#define sb_open_mode(flags) \
- (BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
+ (BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \
+ (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
struct bdev_handle {
struct block_device *bdev;
@@ -1485,10 +1503,6 @@ struct bdev_handle {
blk_mode_t mode;
};
-struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
- const struct blk_holder_ops *hops);
-struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode,
- void *holder, const struct blk_holder_ops *hops);
struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
const struct blk_holder_ops *hops);
struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
@@ -1496,7 +1510,6 @@ struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
int bd_prepare_to_claim(struct block_device *bdev, void *holder,
const struct blk_holder_ops *hops);
void bd_abort_claiming(struct block_device *bdev, void *holder);
-void blkdev_put(struct block_device *bdev, void *holder);
void bdev_release(struct bdev_handle *handle);
/* just for blk-cgroup, don't use elsewhere */
@@ -1541,8 +1554,8 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev)
}
#endif /* CONFIG_BLOCK */
-int freeze_bdev(struct block_device *bdev);
-int thaw_bdev(struct block_device *bdev);
+int bdev_freeze(struct block_device *bdev);
+int bdev_thaw(struct block_device *bdev);
struct io_comp_batch {
struct request *req_list;
diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index 9f1a9c455b68..c2d09bc4f976 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -125,25 +125,55 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
* trivial wrapper around DEFINE_CLASS() above specifically
* for locks.
*
+ * DEFINE_GUARD_COND(name, ext, condlock)
+ * wrapper around EXTEND_CLASS above to add conditional lock
+ * variants to a base class, eg. mutex_trylock() or
+ * mutex_lock_interruptible().
+ *
* guard(name):
- * an anonymous instance of the (guard) class
+ * an anonymous instance of the (guard) class, not recommended for
+ * conditional locks.
*
* scoped_guard (name, args...) { }:
* similar to CLASS(name, scope)(args), except the variable (with the
* explicit name 'scope') is declard in a for-loop such that its scope is
* bound to the next (compound) statement.
*
+ * for conditional locks the loop body is skipped when the lock is not
+ * acquired.
+ *
+ * scoped_cond_guard (name, fail, args...) { }:
+ * similar to scoped_guard(), except it does fail when the lock
+ * acquire fails.
+ *
*/
#define DEFINE_GUARD(_name, _type, _lock, _unlock) \
- DEFINE_CLASS(_name, _type, _unlock, ({ _lock; _T; }), _type _T)
+ DEFINE_CLASS(_name, _type, if (_T) { _unlock; }, ({ _lock; _T; }), _type _T); \
+ static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \
+ { return *_T; }
+
+#define DEFINE_GUARD_COND(_name, _ext, _condlock) \
+ EXTEND_CLASS(_name, _ext, \
+ ({ void *_t = _T; if (_T && !(_condlock)) _t = NULL; _t; }), \
+ class_##_name##_t _T) \
+ static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
+ { return class_##_name##_lock_ptr(_T); }
#define guard(_name) \
CLASS(_name, __UNIQUE_ID(guard))
+#define __guard_ptr(_name) class_##_name##_lock_ptr
+
#define scoped_guard(_name, args...) \
for (CLASS(_name, scope)(args), \
- *done = NULL; !done; done = (void *)1)
+ *done = NULL; __guard_ptr(_name)(&scope) && !done; done = (void *)1)
+
+#define scoped_cond_guard(_name, _fail, args...) \
+ for (CLASS(_name, scope)(args), \
+ *done = NULL; !done; done = (void *)1) \
+ if (!__guard_ptr(_name)(&scope)) _fail; \
+ else
/*
* Additional helper macros for generating lock guards with types, either for
@@ -152,6 +182,7 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
*
* DEFINE_LOCK_GUARD_0(name, lock, unlock, ...)
* DEFINE_LOCK_GUARD_1(name, type, lock, unlock, ...)
+ * DEFINE_LOCK_GUARD_1_COND(name, ext, condlock)
*
* will result in the following type:
*
@@ -173,6 +204,11 @@ typedef struct { \
static inline void class_##_name##_destructor(class_##_name##_t *_T) \
{ \
if (_T->lock) { _unlock; } \
+} \
+ \
+static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \
+{ \
+ return _T->lock; \
}
@@ -201,4 +237,14 @@ __DEFINE_LOCK_GUARD_1(_name, _type, _lock)
__DEFINE_UNLOCK_GUARD(_name, void, _unlock, __VA_ARGS__) \
__DEFINE_LOCK_GUARD_0(_name, _lock)
+#define DEFINE_LOCK_GUARD_1_COND(_name, _ext, _condlock) \
+ EXTEND_CLASS(_name, _ext, \
+ ({ class_##_name##_t _t = { .lock = l }, *_T = &_t;\
+ if (_T->lock && !(_condlock)) _T->lock = NULL; \
+ _t; }), \
+ typeof_member(class_##_name##_t, lock) l) \
+ static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
+ { return class_##_name##_lock_ptr(_T); }
+
+
#endif /* __LINUX_GUARDS_H */
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index efc0c0b07efb..8bd454dfe453 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -66,15 +66,12 @@ enum cpuhp_state {
CPUHP_PERF_POWER,
CPUHP_PERF_SUPERH,
CPUHP_X86_HPET_DEAD,
- CPUHP_X86_APB_DEAD,
CPUHP_X86_MCE_DEAD,
CPUHP_VIRT_NET_DEAD,
CPUHP_IBMVNIC_DEAD,
CPUHP_SLUB_DEAD,
CPUHP_DEBUG_OBJ_DEAD,
CPUHP_MM_WRITEBACK_DEAD,
- /* Must be after CPUHP_MM_VMSTAT_DEAD */
- CPUHP_MM_DEMOTION_DEAD,
CPUHP_MM_VMSTAT_DEAD,
CPUHP_SOFTIRQ_DEAD,
CPUHP_NET_MVNETA_DEAD,
@@ -96,7 +93,6 @@ enum cpuhp_state {
CPUHP_NET_DEV_DEAD,
CPUHP_PCI_XGENE_DEAD,
CPUHP_IOMMU_IOVA_DEAD,
- CPUHP_LUSTRE_CFS_DEAD,
CPUHP_AP_ARM_CACHE_B15_RAC_DEAD,
CPUHP_PADATA_DEAD,
CPUHP_AP_DTPM_CPU_DEAD,
@@ -118,7 +114,6 @@ enum cpuhp_state {
CPUHP_XEN_EVTCHN_PREPARE,
CPUHP_ARM_SHMOBILE_SCU_PREPARE,
CPUHP_SH_SH3X_PREPARE,
- CPUHP_NET_FLOW_PREPARE,
CPUHP_TOPOLOGY_PREPARE,
CPUHP_NET_IUCV_PREPARE,
CPUHP_ARM_BL_PREPARE,
@@ -151,18 +146,14 @@ enum cpuhp_state {
CPUHP_AP_IRQ_ARMADA_XP_STARTING,
CPUHP_AP_IRQ_BCM2836_STARTING,
CPUHP_AP_IRQ_MIPS_GIC_STARTING,
- CPUHP_AP_IRQ_RISCV_STARTING,
CPUHP_AP_IRQ_LOONGARCH_STARTING,
CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
CPUHP_AP_ARM_MVEBU_COHERENCY,
- CPUHP_AP_MICROCODE_LOADER,
CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
CPUHP_AP_PERF_X86_STARTING,
CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
- CPUHP_AP_PERF_X86_CQM_STARTING,
CPUHP_AP_PERF_X86_CSTATE_STARTING,
CPUHP_AP_PERF_XTENSA_STARTING,
- CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
CPUHP_AP_ARM_VFP_STARTING,
CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
@@ -179,7 +170,6 @@ enum cpuhp_state {
CPUHP_AP_QCOM_TIMER_STARTING,
CPUHP_AP_TEGRA_TIMER_STARTING,
CPUHP_AP_ARMADA_TIMER_STARTING,
- CPUHP_AP_MARCO_TIMER_STARTING,
CPUHP_AP_MIPS_GIC_TIMER_STARTING,
CPUHP_AP_ARC_TIMER_STARTING,
CPUHP_AP_RISCV_TIMER_STARTING,
@@ -217,9 +207,7 @@ enum cpuhp_state {
CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
CPUHP_AP_PERF_X86_RAPL_ONLINE,
- CPUHP_AP_PERF_X86_CQM_ONLINE,
CPUHP_AP_PERF_X86_CSTATE_ONLINE,
- CPUHP_AP_PERF_X86_IDXD_ONLINE,
CPUHP_AP_PERF_S390_CF_ONLINE,
CPUHP_AP_PERF_S390_SF_ONLINE,
CPUHP_AP_PERF_ARM_CCI_ONLINE,
@@ -251,9 +239,7 @@ enum cpuhp_state {
CPUHP_AP_RCUTREE_ONLINE,
CPUHP_AP_BASE_CACHEINFO_ONLINE,
CPUHP_AP_ONLINE_DYN,
- CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30,
- /* Must be after CPUHP_AP_ONLINE_DYN for node_states[N_CPU] update */
- CPUHP_AP_MM_DEMOTION_ONLINE,
+ CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 40,
CPUHP_AP_X86_HPET_ONLINE,
CPUHP_AP_X86_KVM_CLK_ONLINE,
CPUHP_AP_ACTIVE,
diff --git a/include/linux/device.h b/include/linux/device.h
index d7a72a8749ea..6c83294395ac 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1007,6 +1007,8 @@ static inline void device_unlock(struct device *dev)
mutex_unlock(&dev->mutex);
}
+DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T))
+
static inline void device_lock_assert(struct device *dev)
{
lockdep_assert_held(&dev->mutex);
diff --git a/include/linux/edac.h b/include/linux/edac.h
index fa4bda2a70f6..1174beb94ab6 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -187,6 +187,7 @@ static inline char *mc_event_error_type(const unsigned int err_type)
* @MEM_NVDIMM: Non-volatile RAM
* @MEM_WIO2: Wide I/O 2.
* @MEM_HBM2: High bandwidth Memory Gen 2.
+ * @MEM_HBM3: High bandwidth Memory Gen 3.
*/
enum mem_type {
MEM_EMPTY = 0,
@@ -218,6 +219,7 @@ enum mem_type {
MEM_NVDIMM,
MEM_WIO2,
MEM_HBM2,
+ MEM_HBM3,
};
#define MEM_FLAG_EMPTY BIT(MEM_EMPTY)
@@ -248,6 +250,7 @@ enum mem_type {
#define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM)
#define MEM_FLAG_WIO2 BIT(MEM_WIO2)
#define MEM_FLAG_HBM2 BIT(MEM_HBM2)
+#define MEM_FLAG_HBM3 BIT(MEM_HBM3)
/**
* enum edac_type - Error Detection and Correction capabilities and mode
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index d95ab85f96ba..b0fb775a600d 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -7,6 +7,11 @@
#include <linux/syscalls.h>
#include <linux/seccomp.h>
#include <linux/sched.h>
+#include <linux/context_tracking.h>
+#include <linux/livepatch.h>
+#include <linux/resume_user_mode.h>
+#include <linux/tick.h>
+#include <linux/kmsan.h>
#include <asm/entry-common.h>
@@ -98,7 +103,19 @@ static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {}
* done between establishing state and enabling interrupts. The caller must
* enable interrupts before invoking syscall_enter_from_user_mode_work().
*/
-void enter_from_user_mode(struct pt_regs *regs);
+static __always_inline void enter_from_user_mode(struct pt_regs *regs)
+{
+ arch_enter_from_user_mode(regs);
+ lockdep_hardirqs_off(CALLER_ADDR0);
+
+ CT_WARN_ON(__ct_state() != CONTEXT_USER);
+ user_exit_irqoff();
+
+ instrumentation_begin();
+ kmsan_unpoison_entry_regs(regs);
+ trace_hardirqs_off_finish();
+ instrumentation_end();
+}
/**
* syscall_enter_from_user_mode_prepare - Establish state and enable interrupts
@@ -117,6 +134,9 @@ void enter_from_user_mode(struct pt_regs *regs);
*/
void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
+long syscall_trace_enter(struct pt_regs *regs, long syscall,
+ unsigned long work);
+
/**
* syscall_enter_from_user_mode_work - Check and handle work before invoking
* a syscall
@@ -140,7 +160,15 @@ void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
* ptrace_report_syscall_entry(), __secure_computing(), trace_sys_enter()
* 2) Invocation of audit_syscall_entry()
*/
-long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
+static __always_inline long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
+{
+ unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
+
+ if (work & SYSCALL_WORK_ENTER)
+ syscall = syscall_trace_enter(regs, syscall, work);
+
+ return syscall;
+}
/**
* syscall_enter_from_user_mode - Establish state and check and handle work
@@ -159,7 +187,19 @@ long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
* Returns: The original or a modified syscall number. See
* syscall_enter_from_user_mode_work() for further explanation.
*/
-long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall);
+static __always_inline long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+{
+ long ret;
+
+ enter_from_user_mode(regs);
+
+ instrumentation_begin();
+ local_irq_enable();
+ ret = syscall_enter_from_user_mode_work(regs, syscall);
+ instrumentation_end();
+
+ return ret;
+}
/**
* local_irq_enable_exit_to_user - Exit to user variant of local_irq_enable()
@@ -259,6 +299,43 @@ static __always_inline void arch_exit_to_user_mode(void) { }
void arch_do_signal_or_restart(struct pt_regs *regs);
/**
+ * exit_to_user_mode_loop - do any pending work before leaving to user space
+ */
+unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+ unsigned long ti_work);
+
+/**
+ * exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
+ * @regs: Pointer to pt_regs on entry stack
+ *
+ * 1) check that interrupts are disabled
+ * 2) call tick_nohz_user_enter_prepare()
+ * 3) call exit_to_user_mode_loop() if any flags from
+ * EXIT_TO_USER_MODE_WORK are set
+ * 4) check that interrupts are still disabled
+ */
+static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+ unsigned long ti_work;
+
+ lockdep_assert_irqs_disabled();
+
+ /* Flush pending rcuog wakeup before the last need_resched() check */
+ tick_nohz_user_enter_prepare();
+
+ ti_work = read_thread_flags();
+ if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
+ ti_work = exit_to_user_mode_loop(regs, ti_work);
+
+ arch_exit_to_user_mode_prepare(regs, ti_work);
+
+ /* Ensure that kernel state is sane for a return to userspace */
+ kmap_assert_nomap();
+ lockdep_assert_irqs_disabled();
+ lockdep_sys_exit();
+}
+
+/**
* exit_to_user_mode - Fixup state when exiting to user mode
*
* Syscall/interrupt exit enables interrupts, but the kernel state is
@@ -276,7 +353,17 @@ void arch_do_signal_or_restart(struct pt_regs *regs);
* non-instrumentable.
* The caller has to invoke syscall_exit_to_user_mode_work() before this.
*/
-void exit_to_user_mode(void);
+static __always_inline void exit_to_user_mode(void)
+{
+ instrumentation_begin();
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare();
+ instrumentation_end();
+
+ user_enter_irqoff();
+ arch_exit_to_user_mode();
+ lockdep_hardirqs_on(CALLER_ADDR0);
+}
/**
* syscall_exit_to_user_mode_work - Handle work before returning to user mode
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index b9d83652c097..e32bee4345fb 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -35,8 +35,7 @@ void eventfd_ctx_put(struct eventfd_ctx *ctx);
struct file *eventfd_fget(int fd);
struct eventfd_ctx *eventfd_ctx_fdget(int fd);
struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
-__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
-__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask);
+void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask);
int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
__u64 *cnt);
void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
@@ -58,15 +57,8 @@ static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd)
return ERR_PTR(-ENOSYS);
}
-static inline int eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
+static inline void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
{
- return -ENOSYS;
-}
-
-static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n,
- unsigned mask)
-{
- return -ENOSYS;
}
static inline void eventfd_ctx_put(struct eventfd_ctx *ctx)
@@ -92,5 +84,10 @@ static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
#endif
+static inline void eventfd_signal(struct eventfd_ctx *ctx)
+{
+ eventfd_signal_mask(ctx, 0);
+}
+
#endif /* _LINUX_EVENTFD_H */
diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h
index 69501e0ec239..d445705ac13c 100644
--- a/include/linux/export-internal.h
+++ b/include/linux/export-internal.h
@@ -16,10 +16,13 @@
* and eliminates the need for absolute relocations that require runtime
* processing on relocatable kernels.
*/
+#define __KSYM_ALIGN ".balign 4"
#define __KSYM_REF(sym) ".long " #sym "- ."
#elif defined(CONFIG_64BIT)
+#define __KSYM_ALIGN ".balign 8"
#define __KSYM_REF(sym) ".quad " #sym
#else
+#define __KSYM_ALIGN ".balign 4"
#define __KSYM_REF(sym) ".long " #sym
#endif
@@ -42,7 +45,7 @@
" .asciz \"" ns "\"" "\n" \
" .previous" "\n" \
" .section \"___ksymtab" sec "+" #name "\", \"a\"" "\n" \
- " .balign 4" "\n" \
+ __KSYM_ALIGN "\n" \
"__ksymtab_" #name ":" "\n" \
__KSYM_REF(sym) "\n" \
__KSYM_REF(__kstrtab_ ##name) "\n" \
@@ -61,6 +64,7 @@
#define SYMBOL_CRC(sym, crc, sec) \
asm(".section \"___kcrctab" sec "+" #sym "\",\"a\"" "\n" \
+ ".balign 4" "\n" \
"__crc_" #sym ":" "\n" \
".long " #crc "\n" \
".previous" "\n")
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index bc4c3287a65e..78c8326d74ae 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -83,12 +83,17 @@ struct dentry;
static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd)
{
struct fdtable *fdt = rcu_dereference_raw(files->fdt);
-
- if (fd < fdt->max_fds) {
- fd = array_index_nospec(fd, fdt->max_fds);
- return rcu_dereference_raw(fdt->fd[fd]);
- }
- return NULL;
+ unsigned long mask = array_index_mask_nospec(fd, fdt->max_fds);
+ struct file *needs_masking;
+
+ /*
+ * 'mask' is zero for an out-of-bounds fd, all ones for ok.
+ * 'fd&mask' is 'fd' for ok, or 0 for out of bounds.
+ *
+ * Accessing fdt->fd[0] is ok, but needs masking of the result.
+ */
+ needs_masking = rcu_dereference_raw(fdt->fd[fd&mask]);
+ return (struct file *)(mask & (unsigned long)needs_masking);
}
static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd)
@@ -114,7 +119,7 @@ int iterate_fd(struct files_struct *, unsigned,
extern int close_fd(unsigned int fd);
extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
-extern struct file *close_fd_get_file(unsigned int fd);
+extern struct file *file_close_fd(unsigned int fd);
extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
struct files_struct **new_fdp);
diff --git a/include/linux/file.h b/include/linux/file.h
index 6e9099d29343..6834a29338c4 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -96,18 +96,8 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T),
extern void fd_install(unsigned int fd, struct file *file);
-extern int __receive_fd(struct file *file, int __user *ufd,
- unsigned int o_flags);
+int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags);
-extern int receive_fd(struct file *file, unsigned int o_flags);
-
-static inline int receive_fd_user(struct file *file, int __user *ufd,
- unsigned int o_flags)
-{
- if (ufd == NULL)
- return -EFAULT;
- return __receive_fd(file, ufd, o_flags);
-}
int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags);
extern void flush_delayed_fput(void);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98b7a7a8c42e..cdbf43a8ea88 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -463,9 +463,9 @@ extern const struct address_space_operations empty_aops;
* @a_ops: Methods.
* @flags: Error bits and flags (AS_*).
* @wb_err: The most recent error which has occurred.
- * @private_lock: For use by the owner of the address_space.
- * @private_list: For use by the owner of the address_space.
- * @private_data: For use by the owner of the address_space.
+ * @i_private_lock: For use by the owner of the address_space.
+ * @i_private_list: For use by the owner of the address_space.
+ * @i_private_data: For use by the owner of the address_space.
*/
struct address_space {
struct inode *host;
@@ -484,9 +484,9 @@ struct address_space {
unsigned long flags;
struct rw_semaphore i_mmap_rwsem;
errseq_t wb_err;
- spinlock_t private_lock;
- struct list_head private_list;
- void *private_data;
+ spinlock_t i_private_lock;
+ struct list_head i_private_list;
+ void * i_private_data;
} __attribute__((aligned(sizeof(long)))) __randomize_layout;
/*
* On most architectures that alignment is already the case; but
@@ -991,8 +991,10 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
*/
struct file {
union {
+ /* fput() uses task work when closing and freeing file (default). */
+ struct callback_head f_task_work;
+ /* fput() must use workqueue (most kernel threads). */
struct llist_node f_llist;
- struct rcu_head f_rcuhead;
unsigned int f_iocb_flags;
};
@@ -1185,7 +1187,8 @@ enum {
struct sb_writers {
unsigned short frozen; /* Is sb frozen? */
- unsigned short freeze_holders; /* Who froze fs? */
+ int freeze_kcount; /* How many kernel freeze requests? */
+ int freeze_ucount; /* How many userspace freeze requests? */
struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS];
};
@@ -1645,9 +1648,70 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
#define __sb_writers_release(sb, lev) \
percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
+/**
+ * __sb_write_started - check if sb freeze level is held
+ * @sb: the super we write to
+ * @level: the freeze level
+ *
+ * * > 0 - sb freeze level is held
+ * * 0 - sb freeze level is not held
+ * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN
+ */
+static inline int __sb_write_started(const struct super_block *sb, int level)
+{
+ return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1);
+}
+
+/**
+ * sb_write_started - check if SB_FREEZE_WRITE is held
+ * @sb: the super we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ */
static inline bool sb_write_started(const struct super_block *sb)
{
- return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1);
+ return __sb_write_started(sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * sb_write_not_started - check if SB_FREEZE_WRITE is not held
+ * @sb: the super we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ */
+static inline bool sb_write_not_started(const struct super_block *sb)
+{
+ return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0;
+}
+
+/**
+ * file_write_started - check if SB_FREEZE_WRITE is held
+ * @file: the file we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ * May be false positive with !S_ISREG, because file_start_write() has
+ * no effect on !S_ISREG.
+ */
+static inline bool file_write_started(const struct file *file)
+{
+ if (!S_ISREG(file_inode(file)->i_mode))
+ return true;
+ return sb_write_started(file_inode(file)->i_sb);
+}
+
+/**
+ * file_write_not_started - check if SB_FREEZE_WRITE is not held
+ * @file: the file we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ * May be false positive with !S_ISREG, because file_start_write() has
+ * no effect on !S_ISREG.
+ */
+static inline bool file_write_not_started(const struct file *file)
+{
+ if (!S_ISREG(file_inode(file)->i_mode))
+ return true;
+ return sb_write_not_started(file_inode(file)->i_sb);
}
/**
@@ -2029,9 +2093,6 @@ extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
loff_t, size_t, unsigned int);
-extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out,
- size_t len, unsigned int flags);
int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *len, unsigned int remap_flags,
@@ -2051,9 +2112,24 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
struct file *dst_file, loff_t dst_pos,
loff_t len, unsigned int remap_flags);
+/**
+ * enum freeze_holder - holder of the freeze
+ * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem
+ * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem
+ * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed
+ *
+ * Indicate who the owner of the freeze or thaw request is and whether
+ * the freeze needs to be exclusive or can nest.
+ * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the
+ * same holder aren't allowed. It is however allowed to hold a single
+ * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at
+ * the same time. This is relied upon by some filesystems during online
+ * repair or similar.
+ */
enum freeze_holder {
FREEZE_HOLDER_KERNEL = (1U << 0),
FREEZE_HOLDER_USERSPACE = (1U << 1),
+ FREEZE_MAY_NEST = (1U << 2),
};
struct super_operations {
@@ -2517,26 +2593,31 @@ struct file *dentry_open(const struct path *path, int flags,
const struct cred *creds);
struct file *dentry_create(const struct path *path, int flags, umode_t mode,
const struct cred *cred);
-struct file *backing_file_open(const struct path *user_path, int flags,
- const struct path *real_path,
- const struct cred *cred);
struct path *backing_file_user_path(struct file *f);
/*
- * file_user_path - get the path to display for memory mapped file
- *
* When mmapping a file on a stackable filesystem (e.g., overlayfs), the file
* stored in ->vm_file is a backing file whose f_inode is on the underlying
- * filesystem. When the mapped file path is displayed to user (e.g. via
- * /proc/<pid>/maps), this helper should be used to get the path to display
- * to the user, which is the path of the fd that user has requested to map.
+ * filesystem. When the mapped file path and inode number are displayed to
+ * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the
+ * path and inode number to display to the user, which is the path of the fd
+ * that user has requested to map and the inode number that would be returned
+ * by fstat() on that same fd.
*/
+/* Get the path to display in /proc/<pid>/maps */
static inline const struct path *file_user_path(struct file *f)
{
if (unlikely(f->f_mode & FMODE_BACKING))
return backing_file_user_path(f);
return &f->f_path;
}
+/* Get the inode whose inode number to display in /proc/<pid>/maps */
+static inline const struct inode *file_user_inode(struct file *f)
+{
+ if (unlikely(f->f_mode & FMODE_BACKING))
+ return d_inode(backing_file_user_path(f)->dentry);
+ return file_inode(f);
+}
static inline struct file *file_clone_open(struct file *file)
{
@@ -2991,8 +3072,6 @@ ssize_t copy_splice_read(struct file *in, loff_t *ppos,
size_t len, unsigned int flags);
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
-extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
- loff_t *opos, size_t len, unsigned int flags);
extern void
@@ -3121,7 +3200,6 @@ extern int vfs_readlink(struct dentry *, char __user *, int);
extern struct file_system_type *get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
extern struct file_system_type *get_fs_type(const char *name);
-extern struct super_block *get_active_super(struct block_device *bdev);
extern void drop_super(struct super_block *sb);
extern void drop_super_exclusive(struct super_block *sb);
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index bcb6609b54b3..11e6434b8e71 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -100,29 +100,49 @@ static inline int fsnotify_file(struct file *file, __u32 mask)
return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
}
-/* Simple call site for access decisions */
-static inline int fsnotify_perm(struct file *file, int mask)
+/*
+ * fsnotify_file_area_perm - permission hook before access to file range
+ */
+static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
+ const loff_t *ppos, size_t count)
{
- int ret;
- __u32 fsnotify_mask = 0;
+ __u32 fsnotify_mask = FS_ACCESS_PERM;
+
+ /*
+ * filesystem may be modified in the context of permission events
+ * (e.g. by HSM filling a file on access), so sb freeze protection
+ * must not be held.
+ */
+ lockdep_assert_once(file_write_not_started(file));
- if (!(mask & (MAY_READ | MAY_OPEN)))
+ if (!(perm_mask & MAY_READ))
return 0;
- if (mask & MAY_OPEN) {
- fsnotify_mask = FS_OPEN_PERM;
+ return fsnotify_file(file, fsnotify_mask);
+}
+
+/*
+ * fsnotify_file_perm - permission hook before file access
+ */
+static inline int fsnotify_file_perm(struct file *file, int perm_mask)
+{
+ return fsnotify_file_area_perm(file, perm_mask, NULL, 0);
+}
- if (file->f_flags & __FMODE_EXEC) {
- ret = fsnotify_file(file, FS_OPEN_EXEC_PERM);
+/*
+ * fsnotify_open_perm - permission hook before file open
+ */
+static inline int fsnotify_open_perm(struct file *file)
+{
+ int ret;
- if (ret)
- return ret;
- }
- } else if (mask & MAY_READ) {
- fsnotify_mask = FS_ACCESS_PERM;
+ if (file->f_flags & __FMODE_EXEC) {
+ ret = fsnotify_file(file, FS_OPEN_EXEC_PERM);
+ if (ret)
+ return ret;
}
- return fsnotify_file(file, fsnotify_mask);
+ return fsnotify_file(file, FS_OPEN_PERM);
}
/*
diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h
index 6730ee900ee1..13b1e65fbdcc 100644
--- a/include/linux/hid-sensor-ids.h
+++ b/include/linux/hid-sensor-ids.h
@@ -21,10 +21,6 @@
#define HID_USAGE_SENSOR_ALS 0x200041
#define HID_USAGE_SENSOR_DATA_LIGHT 0x2004d0
#define HID_USAGE_SENSOR_LIGHT_ILLUM 0x2004d1
-#define HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE 0x2004d2
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY 0x2004d3
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X 0x2004d4
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y 0x2004d5
/* PROX (200011) */
#define HID_USAGE_SENSOR_PROX 0x200011
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 2ebc323d345a..857d785e89e6 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -127,12 +127,12 @@ struct lock_class {
unsigned long usage_mask;
const struct lock_trace *usage_traces[LOCK_TRACE_STATES];
+ const char *name;
/*
* Generation counter, when doing certain classes of graph walking,
* to ensure that we check one node only once:
*/
int name_version;
- const char *name;
u8 wait_type_inner;
u8 wait_type_outer;
diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h
index b8da2db4ecd2..cd4d5c8781f5 100644
--- a/include/linux/mnt_idmapping.h
+++ b/include/linux/mnt_idmapping.h
@@ -244,7 +244,4 @@ static inline kgid_t mapped_fsgid(struct mnt_idmap *idmap,
return from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(current_fsgid()));
}
-bool check_fsmapping(const struct mnt_idmap *idmap,
- const struct super_block *sb);
-
#endif /* _LINUX_MNT_IDMAPPING_H */
diff --git a/include/linux/mount.h b/include/linux/mount.h
index ac3dd2876197..c34c18b4e8f3 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -50,8 +50,7 @@ struct path;
#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
#define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
- MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | \
- MNT_CURSOR)
+ MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | MNT_ONRB)
#define MNT_INTERNAL 0x4000
@@ -65,7 +64,7 @@ struct path;
#define MNT_SYNC_UMOUNT 0x2000000
#define MNT_MARKED 0x4000000
#define MNT_UMOUNT 0x8000000
-#define MNT_CURSOR 0x10000000
+#define MNT_ONRB 0x10000000
struct vfsmount {
struct dentry *mnt_root; /* root of the mounted tree */
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index a33aa9eb9fc3..95d11308f995 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -221,6 +221,7 @@ extern void mutex_unlock(struct mutex *lock);
extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
DEFINE_GUARD(mutex, struct mutex *, mutex_lock(_T), mutex_unlock(_T))
-DEFINE_FREE(mutex, struct mutex *, if (_T) mutex_unlock(_T))
+DEFINE_GUARD_COND(mutex, _try, mutex_trylock(_T))
+DEFINE_GUARD_COND(mutex, _intr, mutex_lock_interruptible(_T) == 0)
#endif /* __LINUX_MUTEX_H */
diff --git a/include/linux/nubus.h b/include/linux/nubus.h
index bdcd85e622d8..4d103ac8f5c7 100644
--- a/include/linux/nubus.h
+++ b/include/linux/nubus.h
@@ -89,8 +89,6 @@ struct nubus_driver {
void (*remove)(struct nubus_board *board);
};
-extern struct bus_type nubus_bus_type;
-
/* Generic NuBus interface functions, modelled after the PCI interface */
#ifdef CONFIG_PROC_FS
extern bool nubus_populate_procfs;
diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
index 5581dbd3bd34..ea8fb31379e3 100644
--- a/include/linux/osq_lock.h
+++ b/include/linux/osq_lock.h
@@ -6,11 +6,6 @@
* An MCS like lock especially tailored for optimistic spinning for sleeping
* lock implementations (mutex, rwsem, etc).
*/
-struct optimistic_spin_node {
- struct optimistic_spin_node *next, *prev;
- int locked; /* 1 if lock acquired */
- int cpu; /* encoded CPU # + 1 value */
-};
struct optimistic_spin_queue {
/*
diff --git a/include/linux/pci.h b/include/linux/pci.h
index dea043bc1e38..58a4c976c39b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1239,6 +1239,8 @@ int pci_read_config_dword(const struct pci_dev *dev, int where, u32 *val);
int pci_write_config_byte(const struct pci_dev *dev, int where, u8 val);
int pci_write_config_word(const struct pci_dev *dev, int where, u16 val);
int pci_write_config_dword(const struct pci_dev *dev, int where, u32 val);
+void pci_clear_and_set_config_dword(const struct pci_dev *dev, int pos,
+ u32 clear, u32 set);
int pcie_capability_read_word(struct pci_dev *dev, int pos, u16 *val);
int pcie_capability_read_dword(struct pci_dev *dev, int pos, u32 *val);
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 275799b5f535..844ffdac8d7d 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2605,6 +2605,8 @@
#define PCI_VENDOR_ID_TEKRAM 0x1de1
#define PCI_DEVICE_ID_TEKRAM_DC290 0xdc29
+#define PCI_VENDOR_ID_ALIBABA 0x1ded
+
#define PCI_VENDOR_ID_TEHUTI 0x1fc9
#define PCI_DEVICE_ID_TEHUTI_3009 0x3009
#define PCI_DEVICE_ID_TEHUTI_3010 0x3010
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 143fbc10ecfe..b3b34f6670cf 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -60,12 +60,6 @@ struct pmu_hw_events {
DECLARE_BITMAP(used_mask, ARMPMU_MAX_HWEVENTS);
/*
- * Hardware lock to serialize accesses to PMU registers. Needed for the
- * read/modify/write sequences.
- */
- raw_spinlock_t pmu_lock;
-
- /*
* When using percpu IRQs, we need a percpu dev_id. Place it here as we
* already have to allocate this struct per cpu.
*/
@@ -189,4 +183,26 @@ void armpmu_free_irq(int irq, int cpu);
#define ARMV8_SPE_PDEV_NAME "arm,spe-v1"
#define ARMV8_TRBE_PDEV_NAME "arm,trbe"
+/* Why does everything I do descend into this? */
+#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi) \
+ (lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi
+
+#define _GEN_PMU_FORMAT_ATTR(cfg, lo, hi) \
+ __GEN_PMU_FORMAT_ATTR(cfg, lo, hi)
+
+#define GEN_PMU_FORMAT_ATTR(name) \
+ PMU_FORMAT_ATTR(name, \
+ _GEN_PMU_FORMAT_ATTR(ATTR_CFG_FLD_##name##_CFG, \
+ ATTR_CFG_FLD_##name##_LO, \
+ ATTR_CFG_FLD_##name##_HI))
+
+#define _ATTR_CFG_GET_FLD(attr, cfg, lo, hi) \
+ ((((attr)->cfg) >> lo) & GENMASK_ULL(hi - lo, 0))
+
+#define ATTR_CFG_GET_FLD(attr, name) \
+ _ATTR_CFG_GET_FLD(attr, \
+ ATTR_CFG_FLD_##name##_CFG, \
+ ATTR_CFG_FLD_##name##_LO, \
+ ATTR_CFG_FLD_##name##_HI)
+
#endif /* __ARM_PMU_H__ */
diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h
index 9c226adf938a..46377e134d67 100644
--- a/include/linux/perf/arm_pmuv3.h
+++ b/include/linux/perf/arm_pmuv3.h
@@ -215,21 +215,27 @@
#define ARMV8_PMU_PMCR_DP (1 << 5) /* Disable CCNT if non-invasive debug*/
#define ARMV8_PMU_PMCR_LC (1 << 6) /* Overflow on 64 bit cycle counter */
#define ARMV8_PMU_PMCR_LP (1 << 7) /* Long event counter enable */
-#define ARMV8_PMU_PMCR_N_SHIFT 11 /* Number of counters supported */
-#define ARMV8_PMU_PMCR_N_MASK 0x1f
-#define ARMV8_PMU_PMCR_MASK 0xff /* Mask for writable bits */
+#define ARMV8_PMU_PMCR_N GENMASK(15, 11) /* Number of counters supported */
+/* Mask for writable bits */
+#define ARMV8_PMU_PMCR_MASK (ARMV8_PMU_PMCR_E | ARMV8_PMU_PMCR_P | \
+ ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_D | \
+ ARMV8_PMU_PMCR_X | ARMV8_PMU_PMCR_DP | \
+ ARMV8_PMU_PMCR_LC | ARMV8_PMU_PMCR_LP)
/*
* PMOVSR: counters overflow flag status reg
*/
-#define ARMV8_PMU_OVSR_MASK 0xffffffff /* Mask for writable bits */
-#define ARMV8_PMU_OVERFLOWED_MASK ARMV8_PMU_OVSR_MASK
+#define ARMV8_PMU_OVSR_P GENMASK(30, 0)
+#define ARMV8_PMU_OVSR_C BIT(31)
+/* Mask for writable bits is both P and C fields */
+#define ARMV8_PMU_OVERFLOWED_MASK (ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C)
/*
* PMXEVTYPER: Event selection reg
*/
-#define ARMV8_PMU_EVTYPE_MASK 0xc800ffff /* Mask for writable bits */
-#define ARMV8_PMU_EVTYPE_EVENT 0xffff /* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_EVENT GENMASK(15, 0) /* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_TH GENMASK_ULL(43, 32) /* arm64 only */
+#define ARMV8_PMU_EVTYPE_TC GENMASK_ULL(63, 61) /* arm64 only */
/*
* Event filters for PMUv3
@@ -244,19 +250,19 @@
/*
* PMUSERENR: user enable reg
*/
-#define ARMV8_PMU_USERENR_MASK 0xf /* Mask for writable bits */
#define ARMV8_PMU_USERENR_EN (1 << 0) /* PMU regs can be accessed at EL0 */
#define ARMV8_PMU_USERENR_SW (1 << 1) /* PMSWINC can be written at EL0 */
#define ARMV8_PMU_USERENR_CR (1 << 2) /* Cycle counter can be read at EL0 */
#define ARMV8_PMU_USERENR_ER (1 << 3) /* Event counter can be read at EL0 */
+/* Mask for writable bits */
+#define ARMV8_PMU_USERENR_MASK (ARMV8_PMU_USERENR_EN | ARMV8_PMU_USERENR_SW | \
+ ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_ER)
/* PMMIR_EL1.SLOTS mask */
-#define ARMV8_PMU_SLOTS_MASK 0xff
-
-#define ARMV8_PMU_BUS_SLOTS_SHIFT 8
-#define ARMV8_PMU_BUS_SLOTS_MASK 0xff
-#define ARMV8_PMU_BUS_WIDTH_SHIFT 16
-#define ARMV8_PMU_BUS_WIDTH_MASK 0xf
+#define ARMV8_PMU_SLOTS GENMASK(7, 0)
+#define ARMV8_PMU_BUS_SLOTS GENMASK(15, 8)
+#define ARMV8_PMU_BUS_WIDTH GENMASK(19, 16)
+#define ARMV8_PMU_THWIDTH GENMASK(23, 20)
/*
* This code is really good
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5547ba68e6e4..d2a15c0c6f8a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1143,6 +1143,15 @@ static inline bool branch_sample_priv(const struct perf_event *event)
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE;
}
+static inline bool branch_sample_counters(const struct perf_event *event)
+{
+ return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS;
+}
+
+static inline bool branch_sample_call_stack(const struct perf_event *event)
+{
+ return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
+}
struct perf_sample_data {
/*
@@ -1177,6 +1186,7 @@ struct perf_sample_data {
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
+ u64 *br_stack_cntr;
union perf_sample_weight weight;
union perf_mem_data_src data_src;
u64 txn;
@@ -1254,7 +1264,8 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
static inline void perf_sample_save_brstack(struct perf_sample_data *data,
struct perf_event *event,
- struct perf_branch_stack *brs)
+ struct perf_branch_stack *brs,
+ u64 *brs_cntr)
{
int size = sizeof(u64); /* nr */
@@ -1262,7 +1273,16 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
size += sizeof(u64);
size += brs->nr * sizeof(struct perf_branch_entry);
+ /*
+ * The extension space for counters is appended after the
+ * struct perf_branch_stack. It is used to store the occurrences
+ * of events of each branch.
+ */
+ if (brs_cntr)
+ size += brs->nr * sizeof(u64);
+
data->br_stack = brs;
+ data->br_stack_cntr = brs_cntr;
data->dyn_size += size;
data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
}
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3cc52826f18e..bd285950972c 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -568,7 +568,6 @@ struct macsec_ops;
* - Bits [31:24] are reserved for defining generic
* PHY driver behavior.
* @irq: IRQ number of the PHY's interrupt (-1 if none)
- * @phy_timer: The timer for handling the state machine
* @phylink: Pointer to phylink instance for this PHY
* @sfp_bus_attached: Flag indicating whether the SFP bus has been attached
* @sfp_bus: SFP bus attached to this PHY's fiber port
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 1dd530ce8b45..9c29689ff505 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -203,11 +203,11 @@ extern void up_read(struct rw_semaphore *sem);
extern void up_write(struct rw_semaphore *sem);
DEFINE_GUARD(rwsem_read, struct rw_semaphore *, down_read(_T), up_read(_T))
-DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T))
-
-DEFINE_FREE(up_read, struct rw_semaphore *, if (_T) up_read(_T))
-DEFINE_FREE(up_write, struct rw_semaphore *, if (_T) up_write(_T))
+DEFINE_GUARD_COND(rwsem_read, _try, down_read_trylock(_T))
+DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T) == 0)
+DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T))
+DEFINE_GUARD_COND(rwsem_write, _try, down_write_trylock(_T))
/*
* downgrade write lock to read lock
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a23af225c898..4f3dca353556 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -226,4 +226,6 @@ static inline void task_unlock(struct task_struct *p)
spin_unlock(&p->alloc_lock);
}
+DEFINE_GUARD(task_lock, struct task_struct *, task_lock(_T), task_unlock(_T))
+
#endif /* _LINUX_SCHED_TASK_H */
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 31d3d747a9db..90bc853cafb6 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -507,6 +507,8 @@ DEFINE_LOCK_GUARD_1(raw_spinlock, raw_spinlock_t,
raw_spin_lock(_T->lock),
raw_spin_unlock(_T->lock))
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock, _try, raw_spin_trylock(_T->lock))
+
DEFINE_LOCK_GUARD_1(raw_spinlock_nested, raw_spinlock_t,
raw_spin_lock_nested(_T->lock, SINGLE_DEPTH_NESTING),
raw_spin_unlock(_T->lock))
@@ -515,23 +517,62 @@ DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t,
raw_spin_lock_irq(_T->lock),
raw_spin_unlock_irq(_T->lock))
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq(_T->lock))
+
DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t,
raw_spin_lock_irqsave(_T->lock, _T->flags),
raw_spin_unlock_irqrestore(_T->lock, _T->flags),
unsigned long flags)
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irqsave, _try,
+ raw_spin_trylock_irqsave(_T->lock, _T->flags))
+
DEFINE_LOCK_GUARD_1(spinlock, spinlock_t,
spin_lock(_T->lock),
spin_unlock(_T->lock))
+DEFINE_LOCK_GUARD_1_COND(spinlock, _try, spin_trylock(_T->lock))
+
DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t,
spin_lock_irq(_T->lock),
spin_unlock_irq(_T->lock))
+DEFINE_LOCK_GUARD_1_COND(spinlock_irq, _try,
+ spin_trylock_irq(_T->lock))
+
DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t,
spin_lock_irqsave(_T->lock, _T->flags),
spin_unlock_irqrestore(_T->lock, _T->flags),
unsigned long flags)
+DEFINE_LOCK_GUARD_1_COND(spinlock_irqsave, _try,
+ spin_trylock_irqsave(_T->lock, _T->flags))
+
+DEFINE_LOCK_GUARD_1(read_lock, rwlock_t,
+ read_lock(_T->lock),
+ read_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(read_lock_irq, rwlock_t,
+ read_lock_irq(_T->lock),
+ read_unlock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1(read_lock_irqsave, rwlock_t,
+ read_lock_irqsave(_T->lock, _T->flags),
+ read_unlock_irqrestore(_T->lock, _T->flags),
+ unsigned long flags)
+
+DEFINE_LOCK_GUARD_1(write_lock, rwlock_t,
+ write_lock(_T->lock),
+ write_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(write_lock_irq, rwlock_t,
+ write_lock_irq(_T->lock),
+ write_unlock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1(write_lock_irqsave, rwlock_t,
+ write_lock_irqsave(_T->lock, _T->flags),
+ write_unlock_irqrestore(_T->lock, _T->flags),
+ unsigned long flags)
+
#undef __LINUX_INSIDE_SPINLOCK_H
#endif /* __LINUX_SPINLOCK_H */
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 6c461573434d..9dec4861d09f 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -68,28 +68,37 @@ typedef int (splice_actor)(struct pipe_inode_info *, struct pipe_buffer *,
typedef int (splice_direct_actor)(struct pipe_inode_info *,
struct splice_desc *);
-extern ssize_t splice_from_pipe(struct pipe_inode_info *, struct file *,
- loff_t *, size_t, unsigned int,
- splice_actor *);
-extern ssize_t __splice_from_pipe(struct pipe_inode_info *,
- struct splice_desc *, splice_actor *);
-extern ssize_t splice_to_pipe(struct pipe_inode_info *,
- struct splice_pipe_desc *);
-extern ssize_t add_to_pipe(struct pipe_inode_info *,
- struct pipe_buffer *);
-long vfs_splice_read(struct file *in, loff_t *ppos,
- struct pipe_inode_info *pipe, size_t len,
- unsigned int flags);
-extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
- splice_direct_actor *);
-extern long do_splice(struct file *in, loff_t *off_in,
- struct file *out, loff_t *off_out,
- size_t len, unsigned int flags);
+ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
+ loff_t *ppos, size_t len, unsigned int flags,
+ splice_actor *actor);
+ssize_t __splice_from_pipe(struct pipe_inode_info *pipe,
+ struct splice_desc *sd, splice_actor *actor);
+ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
+ struct splice_pipe_desc *spd);
+ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf);
+ssize_t vfs_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags);
+ssize_t splice_direct_to_actor(struct file *file, struct splice_desc *sd,
+ splice_direct_actor *actor);
+ssize_t do_splice(struct file *in, loff_t *off_in, struct file *out,
+ loff_t *off_out, size_t len, unsigned int flags);
+ssize_t do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
+ loff_t *opos, size_t len, unsigned int flags);
+ssize_t splice_file_range(struct file *in, loff_t *ppos, struct file *out,
+ loff_t *opos, size_t len);
-extern long do_tee(struct file *in, struct file *out, size_t len,
- unsigned int flags);
-extern ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out,
- loff_t *ppos, size_t len, unsigned int flags);
+static inline long splice_copy_file_range(struct file *in, loff_t pos_in,
+ struct file *out, loff_t pos_out,
+ size_t len)
+{
+ return splice_file_range(in, &pos_in, out, &pos_out, len);
+}
+
+ssize_t do_tee(struct file *in, struct file *out, size_t len,
+ unsigned int flags);
+ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out,
+ loff_t *ppos, size_t len, unsigned int flags);
/*
* for dynamic pipe sizing
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index fd9d12de7e92..2d6d3e76e3f7 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -74,6 +74,8 @@ struct landlock_ruleset_attr;
enum landlock_rule_type;
struct cachestat_range;
struct cachestat;
+struct statmount;
+struct mnt_id_req;
#include <linux/types.h>
#include <linux/aio_abi.h>
@@ -407,6 +409,12 @@ asmlinkage long sys_statfs64(const char __user *path, size_t sz,
asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf);
asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz,
struct statfs64 __user *buf);
+asmlinkage long sys_statmount(const struct mnt_id_req __user *req,
+ struct statmount __user *buf, size_t bufsize,
+ unsigned int flags);
+asmlinkage long sys_listmount(const struct mnt_id_req __user *req,
+ u64 __user *buf, size_t bufsize,
+ unsigned int flags);
asmlinkage long sys_truncate(const char __user *path, long length);
asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length);
#if BITS_PER_LONG == 32
diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h
index b0542cd11aeb..415a7ca2b882 100644
--- a/include/linux/uidgid.h
+++ b/include/linux/uidgid.h
@@ -17,6 +17,7 @@
struct user_namespace;
extern struct user_namespace init_user_ns;
+struct uid_gid_map;
typedef struct {
uid_t val;
@@ -138,6 +139,9 @@ static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid)
return from_kgid(ns, gid) != (gid_t) -1;
}
+u32 map_id_down(struct uid_gid_map *map, u32 id);
+u32 map_id_up(struct uid_gid_map *map, u32 id);
+
#else
static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid)
@@ -186,6 +190,15 @@ static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid)
return gid_valid(gid);
}
+static inline u32 map_id_down(struct uid_gid_map *map, u32 id)
+{
+ return id;
+}
+
+static inline u32 map_id_up(struct uid_gid_map *map, u32 id)
+{
+ return id;
+}
#endif /* CONFIG_USER_NS */
#endif /* _LINUX_UIDGID_H */
diff --git a/include/linux/uio.h b/include/linux/uio.h
index b6214cbf2a43..bea9c89922d9 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -347,8 +347,6 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec,
ssize_t __import_iovec(int type, const struct iovec __user *uvec,
unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
struct iov_iter *i, bool compat);
-int import_single_range(int type, void __user *buf, size_t len,
- struct iovec *iov, struct iov_iter *i);
int import_ubuf(int type, void __user *buf, size_t len, struct iov_iter *i);
static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 083387c00f0c..6d0a14f7019d 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -193,7 +193,6 @@ void inode_io_list_del(struct inode *inode);
/* writeback.h requires fs.h; it, too, is not included from here. */
static inline void wait_on_inode(struct inode *inode)
{
- might_sleep();
wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE);
}