!419 Backport CVEs and bugfixes

Merge Pull Request from: @zhangjialin11 
 
Pull new CVEs:
CVE-2023-26545
CVE-2023-0045
CVE-2023-20938
CVE-2023-0240

rcu bugfix from Zheng Yejian
net bugfixes from Zhengchao Shao
block bugfix from Zhong Jinghua
md/raid10 bugfixes from Li Nan
arm/kasan bugfix from Longlong Xia 
 
Link:https://gitee.com/openeuler/kernel/pulls/419 

Reviewed-by: Zheng Zengkai <zhengzengkai@huawei.com> 
Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com> 

Makefile

@@ -1129,7 +1129,7 @@ export MODORDER := $(extmod-prefix)modules.order
 export MODULES_NSDEPS := $(extmod-prefix)modules.nsdeps
 
 ifeq ($(KBUILD_EXTMOD),)
-core-y		+= kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/
+core-y		+= kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/ io_uring/
 
 vmlinux-dirs	:= $(patsubst %/,%,$(filter %/, \
 		     $(core-y) $(core-m) $(drivers-y) $(drivers-m) \

arch/arm/include/asm/thread_info.h

@@ -137,6 +137,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
  * thread information flags:
  *  TIF_USEDFPU		- FPU was used by this task this quantum (SMP)
  *  TIF_POLLING_NRFLAG	- true if poll_idle() is polling TIF_NEED_RESCHED
+ *
+ * Any bit in the range of 0..15 will cause do_work_pending() to be invoked.
  */
 #define TIF_SIGPENDING		0	/* signal pending */
 #define TIF_NEED_RESCHED	1	/* rescheduling necessary */
@@ -147,6 +149,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
 #define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
 #define TIF_SECCOMP		7	/* seccomp syscall filtering active */
 #define TIF_PATCH_PENDING	8	/* pending live patching update */
+#define TIF_NOTIFY_SIGNAL	9	/* signal notifications exist */
 
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
@@ -162,6 +165,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_USING_IWMMXT	(1 << TIF_USING_IWMMXT)
 #define _TIF_PATCH_PENDING	(1 << TIF_PATCH_PENDING)
+#define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
 
 /* Checks for any syscall work in entry-common.S */
 #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
@@ -171,7 +175,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
  * Change these and you break ASM code in entry-common.S
  */
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
+				 _TIF_NOTIFY_SIGNAL)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_THREAD_INFO_H */

arch/arm/kernel/entry-common.S

@@ -54,7 +54,7 @@ __ret_fast_syscall:
 	cmp	r2, r1
 	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	movs	r1, r1, lsl #16
 	bne	fast_work_pending
 
 
@@ -92,7 +92,7 @@ __ret_fast_syscall:
 	cmp     r2, r1
 	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	movs	r1, r1, lsl #16
 	beq	no_work_pending
  UNWIND(.fnend		)
 ENDPROC(ret_fast_syscall)
@@ -134,7 +134,7 @@ ENTRY(ret_to_user_from_irq)
 	cmp	r2, r1
 	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]
-	tst	r1, #_TIF_WORK_MASK
+	movs	r1, r1, lsl #16
 	bne	slow_work_pending
 no_work_pending:
 	asm_trace_hardirqs_on save = 0

arch/arm/kernel/entry-v7m.S

@@ -59,7 +59,7 @@ __irq_entry:
 
 	get_thread_info tsk
 	ldr	r2, [tsk, #TI_FLAGS]
-	tst	r2, #_TIF_WORK_MASK
+	movs	r2, r2, lsl #16
 	beq	2f			@ no work pending
 	mov	r0, #V7M_SCB_ICSR_PENDSVSET
 	str	r0, [r1, V7M_SCB_ICSR]	@ raise PendSV

arch/arm/kernel/signal.c

@@ -655,7 +655,7 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 			if (unlikely(!user_mode(regs)))
 				return 0;
 			local_irq_enable();
-			if (thread_flags & _TIF_SIGPENDING) {
+			if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) {
 				int restart = do_signal(regs, syscall);
 				if (unlikely(restart)) {
 					/*

arch/arm/mm/kasan_init.c

@@ -264,12 +264,17 @@ void __init kasan_init(void)
 
 	/*
 	 * 1. The module global variables are in MODULES_VADDR ~ MODULES_END,
-	 *    so we need to map this area.
+	 *    so we need to map this area if CONFIG_KASAN_VMALLOC=n. With
+	 *    VMALLOC support KASAN will manage this region dynamically,
+	 *    refer to kasan_populate_vmalloc() and ARM's implementation of
+	 *    module_alloc().
 	 * 2. PKMAP_BASE ~ PKMAP_BASE+PMD_SIZE's shadow and MODULES_VADDR
 	 *    ~ MODULES_END's shadow is in the same PMD_SIZE, so we can't
 	 *    use kasan_populate_zero_shadow.
 	 */
-	create_mapping((void *)MODULES_VADDR, (void *)(PKMAP_BASE + PMD_SIZE));
+	if (!IS_ENABLED(CONFIG_KASAN_VMALLOC) && IS_ENABLED(CONFIG_MODULES))
+		create_mapping((void *)MODULES_VADDR, (void *)(MODULES_END));
+	create_mapping((void *)PKMAP_BASE, (void *)(PKMAP_BASE + PMD_SIZE));
 
 	/*
 	 * KAsan may reuse the contents of kasan_early_shadow_pte directly, so

arch/arm64/include/asm/thread_info.h

@@ -69,6 +69,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
 #define TIF_UPROBE		4	/* uprobe breakpoint or singlestep */
 #define TIF_MTE_ASYNC_FAULT	5	/* MTE Asynchronous Tag Check Fault */
+#define TIF_NOTIFY_SIGNAL	6	/* signal notifications exist */
 #define TIF_SYSCALL_TRACE	8	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	9	/* syscall auditing */
 #define TIF_SYSCALL_TRACEPOINT	10	/* syscall tracepoint for ftrace */
@@ -101,13 +102,15 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define _TIF_32BIT		(1 << TIF_32BIT)
 #define _TIF_SVE		(1 << TIF_SVE)
 #define _TIF_MTE_ASYNC_FAULT	(1 << TIF_MTE_ASYNC_FAULT)
+#define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
 #define _TIF_32BIT_AARCH64	(1 << TIF_32BIT_AARCH64)
 #define _TIF_PATCH_PENDING	(1 << TIF_PATCH_PENDING)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
 				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
-				 _TIF_UPROBE | _TIF_MTE_ASYNC_FAULT)
+				 _TIF_UPROBE | _TIF_MTE_ASYNC_FAULT | \
+				 _TIF_NOTIFY_SIGNAL)
 
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \

arch/arm64/kernel/signal.c

@@ -711,7 +711,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 					       (void __user *)NULL, current);
 			}
 
-			if (thread_flags & _TIF_SIGPENDING)
+			if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
 				do_signal(regs);
 
 			if (thread_flags & _TIF_NOTIFY_RESUME) {

arch/powerpc/include/asm/thread_info.h

@@ -99,6 +99,7 @@ void arch_setup_new_exec(void);
 #define TIF_SYSCALL_TRACE	0	/* syscall trace active */
 #define TIF_SIGPENDING		1	/* signal pending */
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
+#define TIF_NOTIFY_SIGNAL	3	/* signal notifications exist */
 #define TIF_SYSCALL_EMU		4	/* syscall emulation active */
 #define TIF_RESTORE_TM		5	/* need to restore TM FP/VEC/VSX */
 #define TIF_PATCH_PENDING	6	/* pending live patching update */
@@ -124,6 +125,7 @@ void arch_setup_new_exec(void);
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
+#define _TIF_NOTIFY_SIGNAL	(1<<TIF_NOTIFY_SIGNAL)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_32BIT		(1<<TIF_32BIT)
 #define _TIF_RESTORE_TM		(1<<TIF_RESTORE_TM)
@@ -145,7 +147,8 @@ void arch_setup_new_exec(void);
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
-				 _TIF_RESTORE_TM | _TIF_PATCH_PENDING)
+				 _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \
+				 _TIF_NOTIFY_SIGNAL)
 #define _TIF_PERSYSCALL_MASK	(_TIF_RESTOREALL|_TIF_NOERROR)
 
 /* Bits in local_flags */

arch/powerpc/kernel/signal.c

@@ -318,7 +318,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 	if (thread_info_flags & _TIF_PATCH_PENDING)
 		klp_update_patch_state(current);
 
-	if (thread_info_flags & _TIF_SIGPENDING) {
+	if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) {
 		BUG_ON(regs != current->thread.regs);
 		do_signal(current);
 	}

arch/riscv/include/asm/thread_info.h

@@ -80,6 +80,7 @@ struct thread_info {
 #define TIF_SYSCALL_TRACEPOINT  6       /* syscall tracepoint instrumentation */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing */
 #define TIF_SECCOMP		8	/* syscall secure computing */
+#define TIF_NOTIFY_SIGNAL	9	/* signal notifications exist */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -88,9 +89,11 @@ struct thread_info {
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
 
 #define _TIF_WORK_MASK \
-	(_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED)
+	(_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \
+	 _TIF_NOTIFY_SIGNAL)
 
 #define _TIF_SYSCALL_WORK \
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT | \

arch/riscv/kernel/signal.c

@@ -310,7 +310,7 @@ asmlinkage __visible void do_notify_resume(struct pt_regs *regs,
 					   unsigned long thread_info_flags)
 {
 	/* Handle pending signal delivery */
-	if (thread_info_flags & _TIF_SIGPENDING)
+	if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
 		do_signal(regs);
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME)

arch/x86/include/asm/thread_info.h

@@ -99,6 +99,7 @@ struct thread_info {
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
 #define TIF_SLD			18	/* Restore split lock detection on context switch */
+#define TIF_NOTIFY_SIGNAL	19	/* signal notifications exist */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_POLLING_NRFLAG	21	/* idle is polling for TIF_NEED_RESCHED */
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
@@ -127,6 +128,7 @@ struct thread_info {
 #define _TIF_NOCPUID		(1 << TIF_NOCPUID)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
+#define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
 #define _TIF_SLD		(1 << TIF_SLD)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)

arch/x86/kernel/cpu/bugs.c

@@ -1889,6 +1889,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
 			task_set_spec_ib_force_disable(task);
 		task_update_spec_tif(task);
+		if (task == current)
+			indirect_branch_prediction_barrier();
 		break;
 	default:
 		return -ERANGE;

arch/x86/kernel/signal.c

@@ -798,11 +798,11 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
  * mistake.
  */
-void arch_do_signal(struct pt_regs *regs)
+void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal)
 {
 	struct ksignal ksig;
 
-	if (get_signal(&ksig)) {
+	if (has_signal && get_signal(&ksig)) {
 		/* Whee! Actually deliver the signal.  */
 		handle_signal(&ksig, regs);
 		return;

drivers/block/nbd.c

@@ -1771,7 +1771,6 @@ static int nbd_dev_add(int index)
 	struct gendisk *disk;
 	struct request_queue *q;
 	int err = -ENOMEM;
-	int first_minor = index << part_shift;
 
 	nbd = kzalloc(sizeof(struct nbd_device), GFP_KERNEL);
 	if (!nbd)
@@ -1835,7 +1834,7 @@ static int nbd_dev_add(int index)
 	refcount_set(&nbd->refs, 1);
 	INIT_LIST_HEAD(&nbd->list);
 	disk->major = NBD_MAJOR;
-	disk->first_minor = first_minor;
+	disk->first_minor = index << part_shift;
 	disk->fops = &nbd_fops;
 	disk->private_data = nbd;
 	sprintf(disk->disk_name, "nbd%d", index);

drivers/md/md-bitmap.c

@@ -1365,6 +1365,9 @@ __acquires(bitmap->lock)
 	sector_t csize;
 	int err;
 
+	if (page >= bitmap->pages)
+		return NULL;
+
 	err = md_bitmap_checkpage(bitmap, page, create, 0);
 
 	if (bitmap->bp[page].hijacked ||

drivers/md/md.c

@@ -3846,35 +3846,51 @@ static int analyze_sbs(struct mddev *mddev)
  */
 int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale)
 {
-	unsigned long result = 0;
-	long decimals = -1;
-	while (isdigit(*cp) || (*cp == '.' && decimals < 0)) {
-		if (*cp == '.')
-			decimals = 0;
-		else if (decimals < scale) {
-			unsigned int value;
-			value = *cp - '0';
-			result = result * 10 + value;
-			if (decimals >= 0)
-				decimals++;
-		}
-		cp++;
-	}
-	if (*cp == '\n')
-		cp++;
-	if (*cp)
+	unsigned long result = 0, decimals = 0;
+	char *pos, *str;
+	int rv;
+
+	str = kmemdup_nul(cp, strlen(cp), GFP_KERNEL);
+	if (!str)
+		return -ENOMEM;
+	pos = strchr(str, '.');
+	if (pos) {
+		int cnt = scale;
+
+		*pos = '\0';
+		while (isdigit(*(++pos))) {
+			if (cnt) {
+				decimals = decimals * 10 + *pos - '0';
+				cnt--;
+			}
+		}
+		if (*pos == '\n')
+			pos++;
+		if (*pos) {
+			kfree(str);
+			return -EINVAL;
+		}
+		decimals *= int_pow(10, cnt);
+	}
+
+	rv = kstrtoul(str, 10, &result);
+	kfree(str);
+	if (rv)
+		return rv;
+
+	if (result > (ULONG_MAX - decimals) / (unsigned int)int_pow(10, scale))
 		return -EINVAL;
-	if (decimals < 0)
-		decimals = 0;
-	*res = result * int_pow(10, scale - decimals);
-	return 0;
+	*res = result * int_pow(10, scale) + decimals;
+
+	return rv;
 }
 
 static ssize_t
 safe_delay_show(struct mddev *mddev, char *page)
 {
-	int msec = (mddev->safemode_delay*1000)/HZ;
-	return sprintf(page, "%d.%03d\n", msec/1000, msec%1000);
+	unsigned int msec = ((unsigned long)mddev->safemode_delay*1000)/HZ;
+
+	return sprintf(page, "%u.%03u\n", msec/1000, msec%1000);
 }
 static ssize_t
 safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len)
@@ -3888,10 +3904,14 @@ safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len)
 
 	if (strict_strtoul_scaled(cbuf, &msec, 3) < 0)
 		return -EINVAL;
+	if (msec > UINT_MAX)
+		return -EINVAL;
+
 	if (msec == 0)
 		mddev->safemode_delay = 0;
 	else {
 		unsigned long old_delay = mddev->safemode_delay;
+		/* HZ <= 1000, so new_delay < UINT_MAX, too */
 		unsigned long new_delay = (msec*HZ)/1000;
 
 		if (new_delay == 0)
@@ -4543,7 +4563,7 @@ __ATTR_PREALLOC(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_stor
 
 static ssize_t
 max_corrected_read_errors_show(struct mddev *mddev, char *page) {
-	return sprintf(page, "%d\n",
+	return sprintf(page, "%u\n",
 		       atomic_read(&mddev->max_corr_read_errors));
 }
 

drivers/md/raid10.c

@@ -2325,7 +2325,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 	int sect = 0; /* Offset from r10_bio->sector */
 	int sectors = r10_bio->sectors;
 	struct md_rdev *rdev;
-	int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
+	unsigned int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
 	int d = r10_bio->devs[r10_bio->read_slot].devnum;
 
 	/* still own a reference to this rdev, so it cannot
@@ -2344,7 +2344,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 		char b[BDEVNAME_SIZE];
 		bdevname(rdev->bdev, b);
 
-		pr_notice("md/raid10:%s: %s: Raid device exceeded read_error threshold [cur %d:max %d]\n",
+		pr_notice("md/raid10:%s: %s: Raid device exceeded read_error threshold [cur %u:max %u]\n",
 			  mdname(mddev), b,
 			  atomic_read(&rdev->read_errors), max_read_errors);
 		pr_notice("md/raid10:%s: %s: Failing raid device\n",

fs/Makefile

@@ -32,8 +32,6 @@ obj-$(CONFIG_TIMERFD)		+= timerfd.o
 obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_USERFAULTFD)	+= userfaultfd.o
 obj-$(CONFIG_AIO)               += aio.o
-obj-$(CONFIG_IO_URING)		+= io_uring.o
-obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FS_DAX)		+= dax.o
 obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FS_VERITY)		+= verity/

fs/coredump.c

@@ -520,7 +520,7 @@ static bool dump_interrupted(void)
 	 * but then we need to teach dump_write() to restart and clear
 	 * TIF_SIGPENDING.
 	 */
-	return signal_pending(current);
+	return fatal_signal_pending(current) || freezing(current);
 }
 
 static void wait_for_dump_helpers(struct file *file)

fs/file.c

@@ -23,6 +23,8 @@
 #include <linux/close_range.h>
 #include <net/sock.h>
 
+#include "internal.h"
+
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;
 /* our min() is unusable in constant expressions ;-/ */
@@ -829,9 +831,8 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
 }
 
 /*
- * variant of __close_fd that gets a ref on the file for later fput.
- * The caller must ensure that filp_close() called on the file, and then
- * an fput().
+ * See close_fd_get_file() below, this variant assumes current->files->file_lock
+ * is held.
  */
 int __close_fd_get_file(unsigned int fd, struct file **res)
 {
@@ -839,26 +840,39 @@ int __close_fd_get_file(unsigned int fd, struct file **res)
 	struct file *file;
 	struct fdtable *fdt;
 
-	spin_lock(&files->file_lock);
 	fdt = files_fdtable(files);
 	if (fd >= fdt->max_fds)
-		goto out_unlock;
+		goto out_err;
 	file = fdt->fd[fd];
 	if (!file)
-		goto out_unlock;
+		goto out_err;
 	rcu_assign_pointer(fdt->fd[fd], NULL);
 	__put_unused_fd(files, fd);
-	spin_unlock(&files->file_lock);
 	get_file(file);
 	*res = file;
 	return 0;
-
-out_unlock:
-	spin_unlock(&files->file_lock);
+out_err:
 	*res = NULL;
 	return -ENOENT;
 }
 
+/*
+ * variant of close_fd that gets a ref on the file for later fput.
+ * The caller must ensure that filp_close() called on the file, and then
+ * an fput().
+ */
+int close_fd_get_file(unsigned int fd, struct file **res)
+{
+	struct files_struct *files = current->files;
+	int ret;
+
+	spin_lock(&files->file_lock);
+	ret = __close_fd_get_file(fd, res);
+	spin_unlock(&files->file_lock);
+
+	return ret;
+}
+
 void do_close_on_exec(struct files_struct *files)
 {
 	unsigned i;

fs/internal.h

@@ -77,6 +77,8 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 long do_rmdir(int dfd, struct filename *name);
 long do_unlinkat(int dfd, struct filename *name);
 int may_linkat(struct path *link);
+int do_renameat2(int olddfd, struct filename *oldname, int newdfd,
+		 struct filename *newname, unsigned int flags);
 
 /*
  * namespace.c
@@ -132,6 +134,7 @@ extern struct file *do_file_open_root(const struct path *,
 		const char *, const struct open_flags *);
 extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);
+extern int __close_fd_get_file(unsigned int fd, struct file **res);
 
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 int chmod_common(const struct path *path, umode_t mode);

fs/namei.c

@@ -533,6 +533,8 @@ static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
 	p->stack = p->internal;
 	p->dfd = dfd;
 	p->name = name;
+	p->path.mnt = NULL;
+	p->path.dentry = NULL;
 	p->total_link_count = old ? old->total_link_count : 0;
 	p->saved = old;
 	p->state = 0;
@@ -607,6 +609,8 @@ static void terminate_walk(struct nameidata *nd)
 		rcu_read_unlock();
 	}
 	nd->depth = 0;
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
 }
 
 /* path_put is needed afterwards regardless of success or failure */
@@ -635,6 +639,11 @@ static inline bool legitimize_path(struct nameidata *nd,
 static bool legitimize_links(struct nameidata *nd)
 {
 	int i;
+	if (unlikely(nd->flags & LOOKUP_CACHED)) {
+		drop_links(nd);
+		nd->depth = 0;
+		return false;
+	}
 	for (i = 0; i < nd->depth; i++) {
 		struct saved *last = nd->stack + i;
 		if (unlikely(!legitimize_path(nd, &last->link, last->seq))) {
@@ -798,6 +807,7 @@ static int complete_walk(struct nameidata *nd)
 		if (!(nd->state & ND_ROOT_PRESET))
 			if (!(nd->flags & LOOKUP_IS_SCOPED))
 				nd->root.mnt = NULL;
+		nd->flags &= ~LOOKUP_CACHED;
 		if (!try_to_unlazy(nd))
 			return -ECHILD;
 	}
@@ -2210,6 +2220,10 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	int error;
 	const char *s = nd->name->name;
 
+	/* LOOKUP_CACHED requires RCU, ask caller to retry */
+	if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED)
+		return ERR_PTR(-EAGAIN);
+
 	if (!*s)
 		flags &= ~LOOKUP_RCU;
 	if (flags & LOOKUP_RCU)
@@ -2240,8 +2254,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	}
 
 	nd->root.mnt = NULL;
-	nd->path.mnt = NULL;
-	nd->path.dentry = NULL;
 
 	/* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */
 	if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) {
@@ -4353,8 +4365,8 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 }
 EXPORT_SYMBOL(vfs_rename);
 
-static int do_renameat2(int olddfd, const char __user *oldname, int newdfd,
-			const char __user *newname, unsigned int flags)
+int do_renameat2(int olddfd, struct filename *from, int newdfd,
+		 struct filename *to, unsigned int flags)
 {
 	struct dentry *old_dentry, *new_dentry;
 	struct dentry *trap;
@@ -4362,32 +4374,30 @@ static int do_renameat2(int olddfd, const char __user *oldname, int newdfd,
 	struct qstr old_last, new_last;
 	int old_type, new_type;
 	struct inode *delegated_inode = NULL;
-	struct filename *from;
-	struct filename *to;
 	unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET;
 	bool should_retry = false;
-	int error;
+	int error = -EINVAL;
 
 	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
-		return -EINVAL;
+		goto put_both;
 
 	if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) &&
 	    (flags & RENAME_EXCHANGE))
-		return -EINVAL;
+		goto put_both;
 
 	if (flags & RENAME_EXCHANGE)
 		target_flags = 0;
 
 retry:
-	from = filename_parentat(olddfd, getname(oldname), lookup_flags,
-				&old_path, &old_last, &old_type);
+	from = filename_parentat(olddfd, from, lookup_flags, &old_path,
+					&old_last, &old_type);
 	if (IS_ERR(from)) {
 		error = PTR_ERR(from);
-		goto exit;
+		goto put_new;
 	}
 
-	to = filename_parentat(newdfd, getname(newname), lookup_flags,
-				&new_path, &new_last, &new_type);
+	to = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last,
+				&new_type);
 	if (IS_ERR(to)) {
 		error = PTR_ERR(to);
 		goto exit1;
@@ -4480,34 +4490,40 @@ static int do_renameat2(int olddfd, const char __user *oldname, int newdfd,
 	if (retry_estale(error, lookup_flags))
 		should_retry = true;
 	path_put(&new_path);
-	putname(to);
 exit1:
 	path_put(&old_path);
-	putname(from);
 	if (should_retry) {
 		should_retry = false;
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
 	}
-exit:
+put_both:
+	if (!IS_ERR(from))
+		putname(from);
+put_new:
+	if (!IS_ERR(to))
+		putname(to);
 	return error;
 }
 
 SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
 		int, newdfd, const char __user *, newname, unsigned int, flags)
 {
-	return do_renameat2(olddfd, oldname, newdfd, newname, flags);
+	return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname),
+				flags);
 }
 
 SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 		int, newdfd, const char __user *, newname)
 {
-	return do_renameat2(olddfd, oldname, newdfd, newname, 0);
+	return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname),
+				0);
 }
 
 SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname)
 {
-	return do_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
+	return do_renameat2(AT_FDCWD, getname(oldname), AT_FDCWD,
+				getname(newname), 0);
 }
 
 int readlink_copy(char __user *buffer, int buflen, const char *link)

fs/open.c

@@ -1099,6 +1099,12 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op)
 		lookup_flags |= LOOKUP_BENEATH;
 	if (how->resolve & RESOLVE_IN_ROOT)
 		lookup_flags |= LOOKUP_IN_ROOT;
+	if (how->resolve & RESOLVE_CACHED) {
+		/* Don't bother even trying for create/truncate/tmpfile open */
+		if (flags & (O_TRUNC | O_CREAT | O_TMPFILE))
+			return -EAGAIN;
+		lookup_flags |= LOOKUP_CACHED;
+	}
 
 	op->lookup_flags = lookup_flags;
 	return 0;

include/linux/entry-common.h

@@ -70,7 +70,7 @@
 
 #define EXIT_TO_USER_MODE_WORK						\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
-	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING |			\
+	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |	\
 	 ARCH_EXIT_TO_USER_MODE_WORK)
 
 /**
@@ -260,12 +260,13 @@ static __always_inline void arch_exit_to_user_mode(void) { }
 #endif
 
 /**
- * arch_do_signal -  Architecture specific signal delivery function
+ * arch_do_signal_or_restart -  Architecture specific signal delivery function
  * @regs:	Pointer to currents pt_regs
+ * @has_signal:	actual signal to handle
  *
  * Invoked from exit_to_user_mode_loop().
  */
-void arch_do_signal(struct pt_regs *regs);
+void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal);
 
 /**
  * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit()

include/linux/entry-kvm.h

@@ -15,8 +15,8 @@
 # define ARCH_XFER_TO_GUEST_MODE_WORK	(0)
 #endif
 
-#define XFER_TO_GUEST_MODE_WORK					\
-	(_TIF_NEED_RESCHED | _TIF_SIGPENDING |			\
+#define XFER_TO_GUEST_MODE_WORK						\
+	(_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL |	\
 	 _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK)
 
 struct kvm_vcpu;

include/linux/fcntl.h

@@ -19,7 +19,7 @@
 /* List of all valid flags for the how->resolve argument: */
 #define VALID_RESOLVE_FLAGS \
 	(RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \
-	 RESOLVE_BENEATH | RESOLVE_IN_ROOT)
+	 RESOLVE_BENEATH | RESOLVE_IN_ROOT | RESOLVE_CACHED)
 
 /* List of all open_how "versions". */
 #define OPEN_HOW_SIZE_VER0	24 /* sizeof first published struct */

include/linux/fdtable.h

@@ -124,7 +124,7 @@ extern void __fd_install(struct files_struct *files,
 extern int __close_fd(struct files_struct *files,
 		      unsigned int fd);
 extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
-extern int __close_fd_get_file(unsigned int fd, struct file **res);
+extern int close_fd_get_file(unsigned int fd, struct file **res);
 extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
 		      struct files_struct **new_fdp);
 

include/linux/io_uring.h

@@ -22,33 +22,34 @@ struct io_identity {
 	refcount_t			count;
 };
 
+#ifdef __GENKSYMS__
 struct io_uring_task {
 	/* submission side */
-	struct xarray		xa;
-	struct wait_queue_head	wait;
-	struct file		*last;
-	struct percpu_counter	inflight;
-	struct io_identity	__identity;
-	struct io_identity	*identity;
-	atomic_t		in_idle;
-	bool			sqpoll;
+	struct xarray			xa;
+	struct wait_queue_head		wait;
+	struct file			*last;
+	struct percpu_counter		inflight;
+	struct io_identity		 __identity;
+	struct io_identity		*identity;
+	atomic_t			in_idle;
+	bool				sqpoll;
 };
+#endif
 
 #if defined(CONFIG_IO_URING)
 struct sock *io_uring_get_socket(struct file *file);
-void __io_uring_task_cancel(void);
-void __io_uring_files_cancel(struct files_struct *files);
+void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
 
-static inline void io_uring_task_cancel(void)
+static inline void io_uring_files_cancel(void)
 {
-	if (current->io_uring && !xa_empty(&current->io_uring->xa))
-		__io_uring_task_cancel();
+	if (current->io_uring)
+		__io_uring_cancel(false);
 }
-static inline void io_uring_files_cancel(struct files_struct *files)
+static inline void io_uring_task_cancel(void)
 {
-	if (current->io_uring && !xa_empty(&current->io_uring->xa))
-		__io_uring_files_cancel(files);
+	if (current->io_uring)
+		__io_uring_cancel(true);
 }
 static inline void io_uring_free(struct task_struct *tsk)
 {
@@ -63,7 +64,7 @@ static inline struct sock *io_uring_get_socket(struct file *file)
 static inline void io_uring_task_cancel(void)
 {
 }
-static inline void io_uring_files_cancel(struct files_struct *files)
+static inline void io_uring_files_cancel(void)
 {
 }
 static inline void io_uring_free(struct task_struct *tsk)

include/linux/namei.h

@@ -43,6 +43,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT};
 #define LOOKUP_NO_XDEV		0x040000 /* No mountpoint crossing. */
 #define LOOKUP_BENEATH		0x080000 /* No escaping from starting point. */
 #define LOOKUP_IN_ROOT		0x100000 /* Treat dirfd as fs root. */
+#define LOOKUP_CACHED		0x200000 /* Only do cached lookup */
 /* LOOKUP_* flags which do scope-related checks based on the dirfd. */
 #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT)
 

include/linux/sched.h

@@ -1399,7 +1399,7 @@ struct task_struct {
 	 */
 	randomized_struct_fields_end
 
-	KABI_RESERVE(1)
+	KABI_USE(1, void *pf_io_worker)
 	KABI_RESERVE(2)
 	KABI_RESERVE(3)
 	KABI_RESERVE(4)

include/linux/sched/signal.h

@@ -360,11 +360,23 @@ static inline int restart_syscall(void)
 	return -ERESTARTNOINTR;
 }
 
-static inline int signal_pending(struct task_struct *p)
+static inline int task_sigpending(struct task_struct *p)
 {
 	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
 }
 
+static inline int signal_pending(struct task_struct *p)
+{
+	/*
+	 * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same
+	 * behavior in terms of ensuring that we break out of wait loops
+	 * so that notify signal callbacks can be processed.
+	 */
+	if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL)))
+		return 1;
+	return task_sigpending(p);
+}
+
 static inline int __fatal_signal_pending(struct task_struct *p)
 {
 	return unlikely(sigismember(&p->pending.signal, SIGKILL));
@@ -372,7 +384,7 @@ static inline int __fatal_signal_pending(struct task_struct *p)
 
 static inline int fatal_signal_pending(struct task_struct *p)
 {
-	return signal_pending(p) && __fatal_signal_pending(p);
+	return task_sigpending(p) && __fatal_signal_pending(p);
 }
 
 static inline int signal_pending_state(long state, struct task_struct *p)
@@ -509,7 +521,7 @@ extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize);
 static inline void restore_saved_sigmask_unless(bool interrupted)
 {
 	if (interrupted)
-		WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+		WARN_ON(!signal_pending(current));
 	else
 		restore_saved_sigmask();
 }

include/linux/sched/task.h

@@ -31,6 +31,7 @@ struct kernel_clone_args {
 	/* Number of elements in *set_tid */
 	size_t set_tid_size;
 	int cgroup;
+	int io_thread;
 	struct cgroup *cgrp;
 	struct css_set *cset;
 };
@@ -85,6 +86,7 @@ extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct task_struct *);
 
 extern pid_t kernel_clone(struct kernel_clone_args *kargs);
+struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);

include/linux/socket.h

@@ -421,6 +421,9 @@ extern int __sys_accept4_file(struct file *file, unsigned file_flags,
 			struct sockaddr __user *upeer_sockaddr,
 			 int __user *upeer_addrlen, int flags,
 			 unsigned long nofile);
+extern struct file *do_accept(struct file *file, unsigned file_flags,
+			      struct sockaddr __user *upeer_sockaddr,
+			      int __user *upeer_addrlen, int flags);
 extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 			 int __user *upeer_addrlen, int flags);
 extern int __sys_socket(int family, int type, int protocol);
@@ -436,5 +439,6 @@ extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
 			     int __user *usockaddr_len);
 extern int __sys_socketpair(int family, int type, int protocol,
 			    int __user *usockvec);
+extern int __sys_shutdown_sock(struct socket *sock, int how);
 extern int __sys_shutdown(int fd, int how);
 #endif /* _LINUX_SOCKET_H */

include/linux/task_work.h

@@ -22,6 +22,8 @@ enum task_work_notify_mode {
 int task_work_add(struct task_struct *task, struct callback_head *twork,
 			enum task_work_notify_mode mode);
 
+struct callback_head *task_work_cancel_match(struct task_struct *task,
+	bool (*match)(struct callback_head *, void *data), void *data);
 struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t);
 void task_work_run(void);
 

include/linux/tracehook.h

@@ -202,4 +202,27 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 
 }
 
+/*
+ * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This
+ * is currently used by TWA_SIGNAL based task_work, which requires breaking
+ * wait loops to ensure that task_work is noticed and run.
+ */
+static inline void tracehook_notify_signal(void)
+{
+	clear_thread_flag(TIF_NOTIFY_SIGNAL);
+	smp_mb__after_atomic();
+	if (current->task_works)
+		task_work_run();
+}
+
+/*
+ * Called when we have work to process from exit_to_user_mode_loop()
+ */
+static inline void set_notify_signal(struct task_struct *task)
+{
+	if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) &&
+	    !wake_up_state(task, TASK_INTERRUPTIBLE))
+		kick_process(task);
+}
+
 #endif	/* <linux/tracehook.h> */

include/linux/uio.h

@@ -26,6 +26,12 @@ enum iter_type {
 	ITER_DISCARD = 64,
 };
 
+struct iov_iter_state {
+	size_t iov_offset;
+	size_t count;
+	unsigned long nr_segs;
+};
+
 struct iov_iter {
 	/*
 	 * Bit 0 is the read/write bit, set if we're writing.
@@ -55,6 +61,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i)
 	return i->type & ~(READ | WRITE);
 }
 
+static inline void iov_iter_save_state(struct iov_iter *iter,
+				       struct iov_iter_state *state)
+{
+	state->iov_offset = iter->iov_offset;
+	state->count = iter->count;
+	state->nr_segs = iter->nr_segs;
+}
+
 static inline bool iter_is_iovec(const struct iov_iter *i)
 {
 	return iov_iter_type(i) == ITER_IOVEC;
@@ -226,6 +240,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
 ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
 			size_t maxsize, size_t *start);
 int iov_iter_npages(const struct iov_iter *i, int maxpages);
+void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state);
 
 const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags);
 

include/net/sch_generic.h

@@ -1334,4 +1334,11 @@ static inline int skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res)
 	return res->ingress ? netif_receive_skb(skb) : dev_queue_xmit(skb);
 }
 
+/* Make sure qdisc is no longer in SCHED state. */
+static inline void qdisc_synchronize(const struct Qdisc *q)
+{
+	while (test_bit(__QDISC_STATE_SCHED, &q->state))
+		msleep(1);
+}
+
 #endif

include/trace/events/io_uring.h

@@ -12,11 +12,11 @@ struct io_wq_work;
 /**
  * io_uring_create - called after a new io_uring context was prepared
  *
- * @fd:			corresponding file descriptor
- * @ctx:		pointer to a ring context structure
+ * @fd:		corresponding file descriptor
+ * @ctx:	pointer to a ring context structure
  * @sq_entries:	actual SQ size
  * @cq_entries:	actual CQ size
- * @flags:		SQ ring flags, provided to io_uring_setup(2)
+ * @flags:	SQ ring flags, provided to io_uring_setup(2)
  *
  * Allows to trace io_uring creation and provide pointer to a context, that can
  * be used later to find correlated events.
@@ -49,15 +49,15 @@ TRACE_EVENT(io_uring_create,
 );
 
 /**
- * io_uring_register - called after a buffer/file/eventfd was succesfully
+ * io_uring_register - called after a buffer/file/eventfd was successfully
  * 					   registered for a ring
  *
- * @ctx:			pointer to a ring context structure
- * @opcode:			describes which operation to perform
+ * @ctx:		pointer to a ring context structure
+ * @opcode:		describes which operation to perform
  * @nr_user_files:	number of registered files
  * @nr_user_bufs:	number of registered buffers
  * @cq_ev_fd:		whether eventfs registered or not
- * @ret:			return code
+ * @ret:		return code
  *
  * Allows to trace fixed files/buffers/eventfds, that could be registered to
  * avoid an overhead of getting references to them for every operation. This
@@ -142,16 +142,16 @@ TRACE_EVENT(io_uring_queue_async_work,
 	TP_ARGS(ctx, rw, req, work, flags),
 
 	TP_STRUCT__entry (
-		__field(  void *,				ctx		)
-		__field(  int,					rw		)
-		__field(  void *,				req		)
+		__field(  void *,			ctx	)
+		__field(  int,				rw	)
+		__field(  void *,			req	)
 		__field(  struct io_wq_work *,		work	)
 		__field(  unsigned int,			flags	)
 	),
 
 	TP_fast_assign(
 		__entry->ctx	= ctx;
-		__entry->rw		= rw;
+		__entry->rw	= rw;
 		__entry->req	= req;
 		__entry->work	= work;
 		__entry->flags	= flags;
@@ -196,10 +196,10 @@ TRACE_EVENT(io_uring_defer,
 
 /**
  * io_uring_link - called before the io_uring request added into link_list of
- * 				   another request
+ * 		   another request
  *
- * @ctx:			pointer to a ring context structure
- * @req:			pointer to a linked request
+ * @ctx:		pointer to a ring context structure
+ * @req:		pointer to a linked request
  * @target_req:		pointer to a previous request, that would contain @req
  *
  * Allows to track linked requests, to understand dependencies between requests
@@ -212,8 +212,8 @@ TRACE_EVENT(io_uring_link,
 	TP_ARGS(ctx, req, target_req),
 
 	TP_STRUCT__entry (
-		__field(  void *,	ctx			)
-		__field(  void *,	req			)
+		__field(  void *,	ctx		)
+		__field(  void *,	req		)
 		__field(  void *,	target_req	)
 	),
 
@@ -244,7 +244,7 @@ TRACE_EVENT(io_uring_cqring_wait,
 	TP_ARGS(ctx, min_events),
 
 	TP_STRUCT__entry (
-		__field(  void *,	ctx			)
+		__field(  void *,	ctx		)
 		__field(  int,		min_events	)
 	),
 
@@ -272,7 +272,7 @@ TRACE_EVENT(io_uring_fail_link,
 	TP_ARGS(req, link),
 
 	TP_STRUCT__entry (
-		__field(  void *,	req		)
+		__field(  void *,	req	)
 		__field(  void *,	link	)
 	),
 
@@ -290,38 +290,42 @@ TRACE_EVENT(io_uring_fail_link,
  * @ctx:		pointer to a ring context structure
  * @user_data:		user data associated with the request
  * @res:		result of the request
+ * @cflags:		completion flags
  *
  */
 TRACE_EVENT(io_uring_complete,
 
-	TP_PROTO(void *ctx, u64 user_data, long res),
+	TP_PROTO(void *ctx, u64 user_data, int res, unsigned cflags),
 
-	TP_ARGS(ctx, user_data, res),
+	TP_ARGS(ctx, user_data, res, cflags),
 
 	TP_STRUCT__entry (
 		__field(  void *,	ctx		)
 		__field(  u64,		user_data	)
-		__field(  long,		res		)
+		__field(  int,		res		)
+		__field(  unsigned,	cflags		)
 	),
 
 	TP_fast_assign(
 		__entry->ctx		= ctx;
 		__entry->user_data	= user_data;
 		__entry->res		= res;
+		__entry->cflags		= cflags;
 	),
 
-	TP_printk("ring %p, user_data 0x%llx, result %ld",
+	TP_printk("ring %p, user_data 0x%llx, result %d, cflags %x",
 			  __entry->ctx, (unsigned long long)__entry->user_data,
-			  __entry->res)
+			  __entry->res, __entry->cflags)
 );
 
-
 /**
  * io_uring_submit_sqe - called before submitting one SQE
  *
  * @ctx:		pointer to a ring context structure
+ * @req:		pointer to a submitted request
  * @opcode:		opcode of request
  * @user_data:		user data associated with the request
+ * @flags		request flags
  * @force_nonblock:	whether a context blocking or not
  * @sq_thread:		true if sq_thread has submitted this SQE
  *
@@ -330,41 +334,60 @@ TRACE_EVENT(io_uring_complete,
  */
 TRACE_EVENT(io_uring_submit_sqe,
 
-	TP_PROTO(void *ctx, u8 opcode, u64 user_data, bool force_nonblock,
-		 bool sq_thread),
+	TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data, u32 flags,
+		 bool force_nonblock, bool sq_thread),
 
-	TP_ARGS(ctx, opcode, user_data, force_nonblock, sq_thread),
+	TP_ARGS(ctx, req, opcode, user_data, flags, force_nonblock, sq_thread),
 
 	TP_STRUCT__entry (
 		__field(  void *,	ctx		)
+		__field(  void *,	req		)
 		__field(  u8,		opcode		)
 		__field(  u64,		user_data	)
+		__field(  u32,		flags		)
 		__field(  bool,		force_nonblock	)
 		__field(  bool,		sq_thread	)
 	),
 
 	TP_fast_assign(
 		__entry->ctx		= ctx;
+		__entry->req		= req;
 		__entry->opcode		= opcode;
 		__entry->user_data	= user_data;
+		__entry->flags		= flags;
 		__entry->force_nonblock	= force_nonblock;
 		__entry->sq_thread	= sq_thread;
 	),
 
-	TP_printk("ring %p, op %d, data 0x%llx, non block %d, sq_thread %d",
-			  __entry->ctx, __entry->opcode,
-			  (unsigned long long) __entry->user_data,
-			  __entry->force_nonblock, __entry->sq_thread)
+	TP_printk("ring %p, req %p, op %d, data 0x%llx, flags %u, "
+		  "non block %d, sq_thread %d", __entry->ctx, __entry->req,
+		  __entry->opcode, (unsigned long long)__entry->user_data,
+		  __entry->flags, __entry->force_nonblock, __entry->sq_thread)
 );
 
+/*
+ * io_uring_poll_arm - called after arming a poll wait if successful
+ *
+ * @ctx:		pointer to a ring context structure
+ * @req:		pointer to the armed request
+ * @opcode:		opcode of request
+ * @user_data:		user data associated with the request
+ * @mask:		request poll events mask
+ * @events:		registered events of interest
+ *
+ * Allows to track which fds are waiting for and what are the events of
+ * interest.
+ */
 TRACE_EVENT(io_uring_poll_arm,
 
-	TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask, int events),
+	TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data,
+		 int mask, int events),
 
-	TP_ARGS(ctx, opcode, user_data, mask, events),
+	TP_ARGS(ctx, req, opcode, user_data, mask, events),
 
 	TP_STRUCT__entry (
 		__field(  void *,	ctx		)
+		__field(  void *,	req		)
 		__field(  u8,		opcode		)
 		__field(  u64,		user_data	)
 		__field(  int,		mask		)
@@ -373,16 +396,17 @@ TRACE_EVENT(io_uring_poll_arm,
 
 	TP_fast_assign(
 		__entry->ctx		= ctx;
+		__entry->req		= req;
 		__entry->opcode		= opcode;
 		__entry->user_data	= user_data;
 		__entry->mask		= mask;
 		__entry->events		= events;
 	),
 
-	TP_printk("ring %p, op %d, data 0x%llx, mask 0x%x, events 0x%x",
-			  __entry->ctx, __entry->opcode,
-			  (unsigned long long) __entry->user_data,
-			  __entry->mask, __entry->events)
+	TP_printk("ring %p, req %p, op %d, data 0x%llx, mask 0x%x, events 0x%x",
+		  __entry->ctx, __entry->req, __entry->opcode,
+		  (unsigned long long) __entry->user_data,
+		  __entry->mask, __entry->events)
 );
 
 TRACE_EVENT(io_uring_poll_wake,
@@ -437,27 +461,40 @@ TRACE_EVENT(io_uring_task_add,
 			  __entry->mask)
 );
 
+/*
+ * io_uring_task_run - called when task_work_run() executes the poll events
+ *                     notification callbacks
+ *
+ * @ctx:		pointer to a ring context structure
+ * @req:		pointer to the armed request
+ * @opcode:		opcode of request
+ * @user_data:		user data associated with the request
+ *
+ * Allows to track when notified poll events are processed
+ */
 TRACE_EVENT(io_uring_task_run,
 
-	TP_PROTO(void *ctx, u8 opcode, u64 user_data),
+	TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data),
 
-	TP_ARGS(ctx, opcode, user_data),
+	TP_ARGS(ctx, req, opcode, user_data),
 
 	TP_STRUCT__entry (
 		__field(  void *,	ctx		)
+		__field(  void *,	req		)
 		__field(  u8,		opcode		)
 		__field(  u64,		user_data	)
 	),
 
 	TP_fast_assign(
 		__entry->ctx		= ctx;
+		__entry->req		= req;
 		__entry->opcode		= opcode;
 		__entry->user_data	= user_data;
 	),
 
-	TP_printk("ring %p, op %d, data 0x%llx",
-			  __entry->ctx, __entry->opcode,
-			  (unsigned long long) __entry->user_data)
+	TP_printk("ring %p, req %p, op %d, data 0x%llx",
+		  __entry->ctx, __entry->req, __entry->opcode,
+		  (unsigned long long) __entry->user_data)
 );
 
 #endif /* _TRACE_IO_URING_H */

include/uapi/linux/io_uring.h

@@ -42,23 +42,25 @@ struct io_uring_sqe {
 		__u32		statx_flags;
 		__u32		fadvise_advice;
 		__u32		splice_flags;
+		__u32		rename_flags;
+		__u32		unlink_flags;
+		__u32		hardlink_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
+	/* pack this to avoid bogus arm OABI complaints */
 	union {
-		struct {
-			/* pack this to avoid bogus arm OABI complaints */
-			union {
-				/* index into fixed buffers, if used */
-				__u16	buf_index;
-				/* for grouped buffer selection */
-				__u16	buf_group;
-			} __attribute__((packed));
-			/* personality to use, if used */
-			__u16	personality;
-			__s32	splice_fd_in;
-		};
-		__u64	__pad2[3];
+		/* index into fixed buffers, if used */
+		__u16	buf_index;
+		/* for grouped buffer selection */
+		__u16	buf_group;
+	} __attribute__((packed));
+	/* personality to use, if used */
+	__u16	personality;
+	union {
+		__s32	splice_fd_in;
+		__u32	file_index;
 	};
+	__u64	__pad2[2];
 };
 
 enum {
@@ -132,6 +134,9 @@ enum {
 	IORING_OP_PROVIDE_BUFFERS,
 	IORING_OP_REMOVE_BUFFERS,
 	IORING_OP_TEE,
+	IORING_OP_SHUTDOWN,
+	IORING_OP_RENAMEAT,
+	IORING_OP_UNLINKAT,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -145,14 +150,34 @@ enum {
 /*
  * sqe->timeout_flags
  */
-#define IORING_TIMEOUT_ABS	(1U << 0)
-
+#define IORING_TIMEOUT_ABS		(1U << 0)
+#define IORING_TIMEOUT_UPDATE		(1U << 1)
+#define IORING_TIMEOUT_BOOTTIME		(1U << 2)
+#define IORING_TIMEOUT_REALTIME		(1U << 3)
+#define IORING_LINK_TIMEOUT_UPDATE	(1U << 4)
+#define IORING_TIMEOUT_CLOCK_MASK	(IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME)
+#define IORING_TIMEOUT_UPDATE_MASK	(IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE)
 /*
  * sqe->splice_flags
  * extends splice(2) flags
  */
 #define SPLICE_F_FD_IN_FIXED	(1U << 31) /* the last bit of __u32 */
 
+/*
+ * POLL_ADD flags. Note that since sqe->poll_events is the flag space, the
+ * command flags for POLL_ADD are stored in sqe->len.
+ *
+ * IORING_POLL_ADD_MULTI	Multishot poll. Sets IORING_CQE_F_MORE if
+ *				the poll handler will continue to report
+ *				CQEs on behalf of the same SQE.
+ *
+ * IORING_POLL_UPDATE		Update existing poll request, matching
+ *				sqe->addr as the old user_data field.
+ */
+#define IORING_POLL_ADD_MULTI	(1U << 0)
+#define IORING_POLL_UPDATE_EVENTS	(1U << 1)
+#define IORING_POLL_UPDATE_USER_DATA	(1U << 2)
+
 /*
  * IO completion data structure (Completion Queue Entry)
  */
@@ -166,8 +191,10 @@ struct io_uring_cqe {
  * cqe->flags
  *
  * IORING_CQE_F_BUFFER	If set, the upper 16 bits are the buffer ID
+ * IORING_CQE_F_MORE	If set, parent SQE will generate more CQE entries
  */
 #define IORING_CQE_F_BUFFER		(1U << 0)
+#define IORING_CQE_F_MORE		(1U << 1)
 
 enum {
 	IORING_CQE_BUFFER_SHIFT		= 16,
@@ -226,6 +253,7 @@ struct io_cqring_offsets {
 #define IORING_ENTER_GETEVENTS	(1U << 0)
 #define IORING_ENTER_SQ_WAKEUP	(1U << 1)
 #define IORING_ENTER_SQ_WAIT	(1U << 2)
+#define IORING_ENTER_EXT_ARG	(1U << 3)
 
 /*
  * Passed in for io_uring_setup(2). Copied back with updated info on success
@@ -253,6 +281,10 @@ struct io_uring_params {
 #define IORING_FEAT_CUR_PERSONALITY	(1U << 4)
 #define IORING_FEAT_FAST_POLL		(1U << 5)
 #define IORING_FEAT_POLL_32BITS 	(1U << 6)
+#define IORING_FEAT_SQPOLL_NONFIXED	(1U << 7)
+#define IORING_FEAT_EXT_ARG		(1U << 8)
+#define IORING_FEAT_NATIVE_WORKERS	(1U << 9)
+#define IORING_FEAT_RSRC_TAGS		(1U << 10)
 
 /*
  * io_uring_register(2) opcodes and arguments
@@ -272,16 +304,62 @@ enum {
 	IORING_REGISTER_RESTRICTIONS		= 11,
 	IORING_REGISTER_ENABLE_RINGS		= 12,
 
+	/* extended with tagging */
+	IORING_REGISTER_FILES2			= 13,
+	IORING_REGISTER_FILES_UPDATE2		= 14,
+	IORING_REGISTER_BUFFERS2		= 15,
+	IORING_REGISTER_BUFFERS_UPDATE		= 16,
+
+	/* set/clear io-wq thread affinities */
+	IORING_REGISTER_IOWQ_AFF		= 17,
+	IORING_UNREGISTER_IOWQ_AFF		= 18,
+
+	/* set/get max number of io-wq workers */
+	IORING_REGISTER_IOWQ_MAX_WORKERS	= 19,
+
 	/* this goes last */
 	IORING_REGISTER_LAST
 };
 
+/* io-wq worker categories */
+enum {
+	IO_WQ_BOUND,
+	IO_WQ_UNBOUND,
+};
+
+/* deprecated, see struct io_uring_rsrc_update */
 struct io_uring_files_update {
 	__u32 offset;
 	__u32 resv;
 	__aligned_u64 /* __s32 * */ fds;
 };
 
+struct io_uring_rsrc_register {
+	__u32 nr;
+	__u32 resv;
+	__u64 resv2;
+	__aligned_u64 data;
+	__aligned_u64 tags;
+};
+
+struct io_uring_rsrc_update {
+	__u32 offset;
+	__u32 resv;
+	__aligned_u64 data;
+};
+
+struct io_uring_rsrc_update2 {
+	__u32 offset;
+	__u32 resv;
+	__aligned_u64 data;
+	__aligned_u64 tags;
+	__u32 nr;
+	__u32 resv2;
+};
+
+/* Skip updating fd indexes set to this value in the fd table */
+#define IORING_REGISTER_FILES_SKIP	(-2)
+
 #define IO_URING_OP_SUPPORTED	(1U << 0)
 
 struct io_uring_probe_op {
@@ -329,4 +407,11 @@ enum {
 	IORING_RESTRICTION_LAST
 };
 
+struct io_uring_getevents_arg {
+	__u64	sigmask;
+	__u32	sigmask_sz;
+	__u32	pad;
+	__u64	ts;
+};
+
 #endif

include/uapi/linux/openat2.h

@@ -35,5 +35,9 @@ struct open_how {
 #define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
 					be scoped inside the dirfd
 					(similar to chroot(2)). */
+#define RESOLVE_CACHED		0x20 /* Only complete if resolution can be
+					completed through cached lookup. May
+					return -EAGAIN if that's not
+					possible. */
 
 #endif /* _UAPI_LINUX_OPENAT2_H */

io_uring/Makefile

+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for io_uring
+
+obj-$(CONFIG_IO_URING)		+= io_uring.o
+obj-$(CONFIG_IO_WQ)		+= io-wq.o

fs/io-wq.h → io_uring/io-wq.h

 #ifndef INTERNAL_IO_WQ_H
 #define INTERNAL_IO_WQ_H
 
+#include <linux/refcount.h>
 #include <linux/io_uring.h>
-
 struct io_wq;
 
 enum {
 	IO_WQ_WORK_CANCEL	= 1,
 	IO_WQ_WORK_HASHED	= 2,
 	IO_WQ_WORK_UNBOUND	= 4,
-	IO_WQ_WORK_NO_CANCEL	= 8,
 	IO_WQ_WORK_CONCURRENT	= 16,
 
-	IO_WQ_WORK_FILES	= 32,
-	IO_WQ_WORK_FS		= 64,
-	IO_WQ_WORK_MM		= 128,
-	IO_WQ_WORK_CREDS	= 256,
-	IO_WQ_WORK_BLKCG	= 512,
-	IO_WQ_WORK_FSIZE	= 1024,
-
 	IO_WQ_HASH_SHIFT	= 24,	/* upper 8 bits are used for hash key */
 };
 
@@ -52,6 +44,7 @@ static inline void wq_list_add_after(struct io_wq_work_node *node,
 static inline void wq_list_add_tail(struct io_wq_work_node *node,
 				    struct io_wq_work_list *list)
 {
+	node->next = NULL;
 	if (!list->first) {
 		list->last = node;
 		WRITE_ONCE(list->first, node);
@@ -59,7 +52,6 @@ static inline void wq_list_add_tail(struct io_wq_work_node *node,
 		list->last->next = node;
 		list->last = node;
 	}
-	node->next = NULL;
 }
 
 static inline void wq_list_cut(struct io_wq_work_list *list,
@@ -95,7 +87,6 @@ static inline void wq_list_del(struct io_wq_work_list *list,
 
 struct io_wq_work {
 	struct io_wq_work_node list;
-	struct io_identity *identity;
 	unsigned flags;
 };
 
@@ -107,37 +98,48 @@ static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
 	return container_of(work->list.next, struct io_wq_work, list);
 }
 
-typedef void (free_work_fn)(struct io_wq_work *);
-typedef struct io_wq_work *(io_wq_work_fn)(struct io_wq_work *);
+typedef struct io_wq_work *(free_work_fn)(struct io_wq_work *);
+typedef void (io_wq_work_fn)(struct io_wq_work *);
 
-struct io_wq_data {
-	struct user_struct *user;
+struct io_wq_hash {
+	refcount_t refs;
+	unsigned long map;
+	struct wait_queue_head wait;
+};
 
+static inline void io_wq_put_hash(struct io_wq_hash *hash)
+{
+	if (refcount_dec_and_test(&hash->refs))
+		kfree(hash);
+}
+
+struct io_wq_data {
+	struct io_wq_hash *hash;
+	struct task_struct *task;
 	io_wq_work_fn *do_work;
 	free_work_fn *free_work;
 };
 
 struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
-bool io_wq_get(struct io_wq *wq, struct io_wq_data *data);
-void io_wq_destroy(struct io_wq *wq);
+void io_wq_exit_start(struct io_wq *wq);
+void io_wq_put_and_exit(struct io_wq *wq);
 
 void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
 void io_wq_hash_work(struct io_wq_work *work, void *val);
 
+int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask);
+int io_wq_max_workers(struct io_wq *wq, int *new_count);
+
 static inline bool io_wq_is_hashed(struct io_wq_work *work)
 {
 	return work->flags & IO_WQ_WORK_HASHED;
 }
 
-void io_wq_cancel_all(struct io_wq *wq);
-
 typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
 
 enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
 					void *data, bool cancel_all);
 
-struct task_struct *io_wq_get_task(struct io_wq *wq);
-
 #if defined(CONFIG_IO_WQ)
 extern void io_wq_worker_sleeping(struct task_struct *);
 extern void io_wq_worker_running(struct task_struct *);
@@ -152,6 +154,7 @@ static inline void io_wq_worker_running(struct task_struct *tsk)
 
 static inline bool io_wq_current_is_worker(void)
 {
-	return in_task() && (current->flags & PF_IO_WORKER);
+	return in_task() && (current->flags & PF_IO_WORKER) &&
+		current->pf_io_worker;
 }
 #endif

kernel/entry/common.c

@@ -135,7 +135,15 @@ static __always_inline void exit_to_user_mode(void)
 }
 
 /* Workaround to allow gradual conversion of architecture code */
-void __weak arch_do_signal(struct pt_regs *regs) { }
+void __weak arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { }
+
+static void handle_signal_work(struct pt_regs *regs, unsigned long ti_work)
+{
+	if (ti_work & _TIF_NOTIFY_SIGNAL)
+		tracehook_notify_signal();
+
+	arch_do_signal_or_restart(regs, ti_work & _TIF_SIGPENDING);
+}
 
 static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 					    unsigned long ti_work)
@@ -157,8 +165,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		if (ti_work & _TIF_PATCH_PENDING)
 			klp_update_patch_state(current);
 
-		if (ti_work & _TIF_SIGPENDING)
-			arch_do_signal(regs);
+		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
+			handle_signal_work(regs, ti_work);
 
 		if (ti_work & _TIF_NOTIFY_RESUME) {
 			tracehook_notify_resume(regs);

kernel/entry/kvm.c

@@ -8,6 +8,9 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
 	do {
 		int ret;
 
+		if (ti_work & _TIF_NOTIFY_SIGNAL)
+			tracehook_notify_signal();
+
 		if (ti_work & _TIF_SIGPENDING) {
 			kvm_handle_signal_exit(vcpu);
 			return -EINTR;

kernel/events/uprobes.c

@@ -1973,7 +1973,7 @@ bool uprobe_deny_signal(void)
 
 	WARN_ON_ONCE(utask->state != UTASK_SSTEP);
 
-	if (signal_pending(t)) {
+	if (task_sigpending(t)) {
 		spin_lock_irq(&t->sighand->siglock);
 		clear_tsk_thread_flag(t, TIF_SIGPENDING);
 		spin_unlock_irq(&t->sighand->siglock);

kernel/exit.c

@@ -763,7 +763,7 @@ void __noreturn do_exit(long code)
 		schedule();
 	}
 
-	io_uring_files_cancel(tsk->files);
+	io_uring_files_cancel();
 	exit_signals(tsk);  /* sets PF_EXITING */
 
 	/* sync mm's RSS info before statistics gathering */

kernel/fork.c

@@ -948,6 +948,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->splice_pipe = NULL;
 	tsk->task_frag.page = NULL;
 	tsk->wake_q.next = NULL;
+	tsk->pf_io_worker = NULL;
 
 	account_kernel_stack(tsk, 1);
 
@@ -1994,6 +1995,8 @@ static __latent_entropy struct task_struct *copy_process(
 	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
+	if (args->io_thread)
+		p->flags |= PF_IO_WORKER;
 
 	/*
 	 * This _must_ happen before we call free_task(), i.e. before we jump
@@ -2474,6 +2477,34 @@ struct mm_struct *copy_init_mm(void)
 	return dup_mm(NULL, &init_mm);
 }
 
+/*
+ * This is like kernel_clone(), but shaved down and tailored to just
+ * creating io_uring workers. It returns a created task, or an error pointer.
+ * The returned task is inactive, and the caller must fire it up through
+ * wake_up_new_task(p). All signals are blocked in the created task.
+ */
+struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
+{
+	unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD|
+				CLONE_IO;
+	struct kernel_clone_args args = {
+		.flags		= ((lower_32_bits(flags) | CLONE_VM |
+				    CLONE_UNTRACED) & ~CSIGNAL),
+		.exit_signal	= (lower_32_bits(flags) & CSIGNAL),
+		.stack		= (unsigned long)fn,
+		.stack_size	= (unsigned long)arg,
+		.io_thread	= 1,
+	};
+	struct task_struct *tsk;
+
+	tsk = copy_process(NULL, 0, node, &args);
+	if (!IS_ERR(tsk)) {
+		sigfillset(&tsk->blocked);
+		sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
+	}
+	return tsk;
+}
+
 /*
  *  Ok, this is the main fork-routine.
  *

kernel/rcu/tree.c

@@ -986,6 +986,7 @@ void __rcu_irq_enter_check_tick(void)
 	}
 	raw_spin_unlock_rcu_node(rdp->mynode);
 }
+NOKPROBE_SYMBOL(__rcu_irq_enter_check_tick);
 #endif /* CONFIG_NO_HZ_FULL */
 
 /**

kernel/sched/core.c

@@ -21,7 +21,7 @@
 #include <asm/tlb.h>
 
 #include "../workqueue_internal.h"
-#include "../../fs/io-wq.h"
+#include "../../io_uring/io-wq.h"
 #include "../smpboot.h"
 
 #include "pelt.h"

kernel/signal.c

@@ -986,7 +986,7 @@ static inline bool wants_signal(int sig, struct task_struct *p)
 	if (task_is_stopped_or_traced(p))
 		return false;
 
-	return task_curr(p) || !signal_pending(p);
+	return task_curr(p) || !task_sigpending(p);
 }
 
 static void complete_signal(int sig, struct task_struct *p, enum pid_type type)
@@ -2526,6 +2526,18 @@ bool get_signal(struct ksignal *ksig)
 	struct signal_struct *signal = current->signal;
 	int signr;
 
+	/*
+	 * For non-generic architectures, check for TIF_NOTIFY_SIGNAL so
+	 * that the arch handlers don't all have to do it. If we get here
+	 * without TIF_SIGPENDING, just exit after running signal work.
+	 */
+	if (!IS_ENABLED(CONFIG_GENERIC_ENTRY)) {
+		if (test_thread_flag(TIF_NOTIFY_SIGNAL))
+			tracehook_notify_signal();
+		if (!task_sigpending(current))
+			return false;
+	}
+
 	if (unlikely(uprobe_deny_signal()))
 		return false;
 
@@ -2819,7 +2831,7 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which)
 		/* Remove the signals this thread can handle. */
 		sigandsets(&retarget, &retarget, &t->blocked);
 
-		if (!signal_pending(t))
+		if (!task_sigpending(t))
 			signal_wake_up(t, 0);
 
 		if (sigisemptyset(&retarget))
@@ -2853,7 +2865,7 @@ void exit_signals(struct task_struct *tsk)
 
 	cgroup_threadgroup_change_end(tsk);
 
-	if (!signal_pending(tsk))
+	if (!task_sigpending(tsk))
 		goto out;
 
 	unblocked = tsk->blocked;
@@ -2897,7 +2909,7 @@ long do_no_restart_syscall(struct restart_block *param)
 
 static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset)
 {
-	if (signal_pending(tsk) && !thread_group_empty(tsk)) {
+	if (task_sigpending(tsk) && !thread_group_empty(tsk)) {
 		sigset_t newblocked;
 		/* A set of now blocked but previously unblocked signals. */
 		sigandnsets(&newblocked, newset, &current->blocked);

kernel/task_work.c

@@ -70,18 +70,17 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 }
 
 /**
- * task_work_cancel - cancel a pending work added by task_work_add()
+ * task_work_cancel_match - cancel a pending work added by task_work_add()
  * @task: the task which should execute the work
- * @func: identifies the work to remove
- *
- * Find the last queued pending work with ->func == @func and remove
- * it from queue.
+ * @match: match function to call
  *
  * RETURNS:
  * The found work or NULL if not found.
  */
 struct callback_head *
-task_work_cancel(struct task_struct *task, task_work_func_t func)
+task_work_cancel_match(struct task_struct *task,
+		       bool (*match)(struct callback_head *, void *data),
+		       void *data)
 {
 	struct callback_head **pprev = &task->task_works;
 	struct callback_head *work;
@@ -97,7 +96,7 @@ task_work_cancel(struct task_struct *task, task_work_func_t func)
 	 */
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 	while ((work = READ_ONCE(*pprev))) {
-		if (work->func != func)
+		if (!match(work, data))
 			pprev = &work->next;
 		else if (cmpxchg(pprev, work, work->next) == work)
 			break;
@@ -107,6 +106,28 @@ task_work_cancel(struct task_struct *task, task_work_func_t func)
 	return work;
 }
 
+static bool task_work_func_match(struct callback_head *cb, void *data)
+{
+	return cb->func == data;
+}
+
+/**
+ * task_work_cancel - cancel a pending work added by task_work_add()
+ * @task: the task which should execute the work
+ * @func: identifies the work to remove
+ *
+ * Find the last queued pending work with ->func == @func and remove
+ * it from queue.
+ *
+ * RETURNS:
+ * The found work or NULL if not found.
+ */
+struct callback_head *
+task_work_cancel(struct task_struct *task, task_work_func_t func)
+{
+	return task_work_cancel_match(task, task_work_func_match, func);
+}
+
 /**
  * task_work_run - execute the works added by task_work_add()
  *

lib/iov_iter.c

@@ -1836,24 +1836,38 @@ int import_single_range(int rw, void __user *buf, size_t len,
 }
 EXPORT_SYMBOL(import_single_range);
 
-int iov_iter_for_each_range(struct iov_iter *i, size_t bytes,
-			    int (*f)(struct kvec *vec, void *context),
-			    void *context)
+/**
+ * iov_iter_restore() - Restore a &struct iov_iter to the same state as when
+ *     iov_iter_save_state() was called.
+ *
+ * @i: &struct iov_iter to restore
+ * @state: state to restore from
+ *
+ * Used after iov_iter_save_state() to bring restore @i, if operations may
+ * have advanced it.
+ *
+ * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC
+ */
+void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state)
 {
-	struct kvec w;
-	int err = -EINVAL;
-	if (!bytes)
-		return 0;
-
-	iterate_all_kinds(i, bytes, v, -EINVAL, ({
-		w.iov_base = kmap(v.bv_page) + v.bv_offset;
-		w.iov_len = v.bv_len;
-		err = f(&w, context);
-		kunmap(v.bv_page);
-		err;}), ({
-		w = v;
-		err = f(&w, context);})
-	)
-	return err;
+	if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) &&
+			 !iov_iter_is_kvec(i))
+		return;
+	i->iov_offset = state->iov_offset;
+	i->count = state->count;
+	/*
+	 * For the *vec iters, nr_segs + iov is constant - if we increment
+	 * the vec, then we also decrement the nr_segs count. Hence we don't
+	 * need to track both of these, just one is enough and we can deduct
+	 * the other from that. ITER_KVEC and ITER_IOVEC are the same struct
+	 * size, so we can just increment the iov pointer as they are unionzed.
+	 * ITER_BVEC _may_ be the same size on some archs, but on others it is
+	 * not. Be safe and handle it separately.
+	 */
+	BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec));
+	if (iov_iter_is_bvec(i))
+		i->bvec -= state->nr_segs - i->nr_segs;
+	else
+		i->iov -= state->nr_segs - i->nr_segs;
+	i->nr_segs = state->nr_segs;
 }
-EXPORT_SYMBOL(iov_iter_for_each_range);

net/mpls/af_mpls.c

@@ -1427,6 +1427,7 @@ static int mpls_dev_sysctl_register(struct net_device *dev,
 free:
 	kfree(table);
 out:
+	mdev->sysctl = NULL;
 	return -ENOBUFS;
 }
 
@@ -1436,6 +1437,9 @@ static void mpls_dev_sysctl_unregister(struct net_device *dev,
 	struct net *net = dev_net(dev);
 	struct ctl_table *table;
 
+	if (!mdev->sysctl)
+		return;
+
 	table = mdev->sysctl->ctl_table_arg;
 	unregister_net_sysctl_table(mdev->sysctl);
 	kfree(table);

net/sched/sch_taprio.c

@@ -1619,6 +1619,7 @@ static void taprio_reset(struct Qdisc *sch)
 	int i;
 
 	hrtimer_cancel(&q->advance_timer);
+
 	if (q->qdiscs) {
 		for (i = 0; i < dev->num_tx_queues; i++)
 			if (q->qdiscs[i])
@@ -1642,6 +1643,7 @@ static void taprio_destroy(struct Qdisc *sch)
 	 * happens in qdisc_create(), after taprio_init() has been called.
 	 */
 	hrtimer_cancel(&q->advance_timer);
+	qdisc_synchronize(sch);
 
 	taprio_disable_offload(dev, q, NULL);
 

net/socket.c

@@ -1688,30 +1688,22 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog)
 	return __sys_listen(fd, backlog);
 }
 
-int __sys_accept4_file(struct file *file, unsigned file_flags,
+struct file *do_accept(struct file *file, unsigned file_flags,
 		       struct sockaddr __user *upeer_sockaddr,
-		       int __user *upeer_addrlen, int flags,
-		       unsigned long nofile)
+		       int __user *upeer_addrlen, int flags)
 {
 	struct socket *sock, *newsock;
 	struct file *newfile;
-	int err, len, newfd;
+	int err, len;
 	struct sockaddr_storage address;
 
-	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
-		return -EINVAL;
-
-	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
-		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
-
 	sock = sock_from_file(file, &err);
 	if (!sock)
-		goto out;
+		return ERR_PTR(err);
 
-	err = -ENFILE;
 	newsock = sock_alloc();
 	if (!newsock)
-		goto out;
+		return ERR_PTR(-ENFILE);
 
 	newsock->type = sock->type;
 	newsock->ops = sock->ops;
@@ -1722,18 +1714,9 @@ int __sys_accept4_file(struct file *file, unsigned file_flags,
 	 */
 	__module_get(newsock->ops->owner);
 
-	newfd = __get_unused_fd_flags(flags, nofile);
-	if (unlikely(newfd < 0)) {
-		err = newfd;
-		sock_release(newsock);
-		goto out;
-	}
 	newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name);
-	if (IS_ERR(newfile)) {
-		err = PTR_ERR(newfile);
-		put_unused_fd(newfd);
-		goto out;
-	}
+	if (IS_ERR(newfile))
+		return newfile;
 
 	err = security_socket_accept(sock, newsock);
 	if (err)
@@ -1758,16 +1741,38 @@ int __sys_accept4_file(struct file *file, unsigned file_flags,
 	}
 
 	/* File flags are not inherited via accept() unlike another OSes. */
-
-	fd_install(newfd, newfile);
-	err = newfd;
-out:
-	return err;
+	return newfile;
 out_fd:
 	fput(newfile);
-	put_unused_fd(newfd);
-	goto out;
+	return ERR_PTR(err);
+}
 
+int __sys_accept4_file(struct file *file, unsigned file_flags,
+		       struct sockaddr __user *upeer_sockaddr,
+		       int __user *upeer_addrlen, int flags,
+		       unsigned long nofile)
+{
+	struct file *newfile;
+	int newfd;
+
+	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
+		return -EINVAL;
+
+	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
+		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
+
+	newfd = __get_unused_fd_flags(flags, nofile);
+	if (unlikely(newfd < 0))
+		return newfd;
+
+	newfile = do_accept(file, file_flags, upeer_sockaddr, upeer_addrlen,
+			    flags);
+	if (IS_ERR(newfile)) {
+		put_unused_fd(newfd);
+		return PTR_ERR(newfile);
+	}
+	fd_install(newfd, newfile);
+	return newfd;
 }
 
 /*
@@ -2181,6 +2186,17 @@ SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
  *	Shutdown a socket.
  */
 
+int __sys_shutdown_sock(struct socket *sock, int how)
+{
+	int err;
+
+	err = security_socket_shutdown(sock, how);
+	if (!err)
+		err = sock->ops->shutdown(sock, how);
+
+	return err;
+}
+
 int __sys_shutdown(int fd, int how)
 {
 	int err, fput_needed;
@@ -2188,9 +2204,7 @@ int __sys_shutdown(int fd, int how)
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (sock != NULL) {
-		err = security_socket_shutdown(sock, how);
-		if (!err)
-			err = sock->ops->shutdown(sock, how);
+		err = __sys_shutdown_sock(sock, how);
 		fput_light(sock->file, fput_needed);
 	}
 	return err;

tools/perf/trace/beauty/include/linux/socket.h

@@ -421,6 +421,9 @@ extern int __sys_accept4_file(struct file *file, unsigned file_flags,
 			struct sockaddr __user *upeer_sockaddr,
 			 int __user *upeer_addrlen, int flags,
 			 unsigned long nofile);
+extern struct file *do_accept(struct file *file, unsigned file_flags,
+			      struct sockaddr __user *upeer_sockaddr,
+			      int __user *upeer_addrlen, int flags);
 extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 			 int __user *upeer_addrlen, int flags);
 extern int __sys_socket(int family, int type, int protocol);
@@ -436,5 +439,6 @@ extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
 			     int __user *usockaddr_len);
 extern int __sys_socketpair(int family, int type, int protocol,
 			    int __user *usockvec);
+extern int __sys_shutdown_sock(struct socket *sock, int how);
 extern int __sys_shutdown(int fd, int how);
 #endif /* _LINUX_SOCKET_H */