Merge tag 'v5.10.162' of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux into ti-linux-5.10.y-cicd

This is the 5.10.162 stable release

* tag 'v5.10.162' of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux: (198 commits)
  Linux 5.10.162
  io_uring: pass in EPOLL_URING_WAKE for eventfd signaling and wakeups
  eventfd: provide a eventfd_signal_mask() helper
  eventpoll: add EPOLL_URING_WAKE poll wakeup flag
  Revert "proc: don't allow async path resolution of /proc/self components"
  Revert "proc: don't allow async path resolution of /proc/thread-self components"
  net: remove cmsg restriction from io_uring based send/recvmsg calls
  task_work: unconditionally run task_work from get_signal()
  signal: kill JOBCTL_TASK_WORK
  io_uring: import 5.15-stable io_uring
  task_work: add helper for more targeted task_work canceling
  kernel: don't call do_exit() for PF_IO_WORKER threads
  kernel: stop masking signals in create_io_thread()
  x86/process: setup io_threads more like normal user space threads
  arch: ensure parisc/powerpc handle PF_IO_WORKER in copy_thread()
  arch: setup PF_IO_WORKER threads like PF_KTHREAD
  entry/kvm: Exit to user mode when TIF_NOTIFY_SIGNAL is set
  kernel: allow fork with TIF_NOTIFY_SIGNAL pending
  coredump: Limit what can interrupt coredumps
  kernel: remove checking for TIF_NOTIFY_SIGNAL
  ...

Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>

27 files changed, 302 insertions, 118 deletions

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index a0c4b99d2899..f40c9534f20b 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -205,12 +205,16 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 #define tlb_needs_table_invalidate() (true)
 #endif
 
+void tlb_remove_table_sync_one(void);
+
 #else
 
 #ifdef tlb_needs_table_invalidate
 #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
 #endif
 
+static inline void tlb_remove_table_sync_one(void) { }
+
 #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
 
 
diff --git a/include/linux/can/platform/sja1000.h b/include/linux/can/platform/sja1000.h
index 5755ae5a4712..6a869682c120 100644
--- a/include/linux/can/platform/sja1000.h
+++ b/include/linux/can/platform/sja1000.h
@@ -14,7 +14,7 @@
 #define OCR_MODE_TEST     0x01
 #define OCR_MODE_NORMAL   0x02
 #define OCR_MODE_CLOCK    0x03
-#define OCR_MODE_MASK     0x07
+#define OCR_MODE_MASK     0x03
 #define OCR_TX0_INVERT    0x04
 #define OCR_TX0_PULLDOWN  0x08
 #define OCR_TX0_PULLUP    0x10
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 618838c48313..959b370733f0 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -68,6 +68,7 @@ struct css_task_iter {
 	struct list_head		iters_node;	/* css_set->task_iters */
 };
 
+extern struct file_system_type cgroup_fs_type;
 extern struct cgroup_root cgrp_dfl_root;
 extern struct css_set init_css_set;
 
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 7dff07713a07..46c42479f950 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -69,7 +69,7 @@
 
 #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)
 
 /**
@@ -259,12 +259,13 @@ 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()
diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h
index 0cef17afb41a..9b93f8584ff7 100644
--- a/include/linux/entry-kvm.h
+++ b/include/linux/entry-kvm.h
@@ -11,8 +11,8 @@
 # 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;
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index dc4fd8a6644d..ce1cf42740bf 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -39,6 +39,7 @@ 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, unsigned mask);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
 
@@ -66,6 +67,12 @@ static inline int eventfd_signal(struct eventfd_ctx *ctx, int n)
 	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)
 {
 
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index 921e750843e6..766fcd973beb 100644
--- a/include/linux/fcntl.h
+++ b/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 */
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index a32bf47c593e..f1a99d3e5570 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -123,7 +123,7 @@ 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);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index df54acdd3554..ebfc0b2b4969 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1817,6 +1817,14 @@ struct dir_context {
  */
 #define REMAP_FILE_ADVISORY		(REMAP_FILE_CAN_SHORTEN)
 
+/*
+ * These flags control the behavior of vfs_copy_file_range().
+ * They are not available to the user via syscall.
+ *
+ * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops
+ */
+#define COPY_FILE_SPLICE		(1 << 0)
+
 struct iov_iter;
 
 struct file_operations {
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b9fbb6d4150e..955b19dc28a8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -174,8 +174,8 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
 struct page *follow_huge_pd(struct vm_area_struct *vma,
 			    unsigned long address, hugepd_t hpd,
 			    int flags, int pdshift);
-struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-				pmd_t *pmd, int flags);
+struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address,
+				 int flags);
 struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 				pud_t *pud, int flags);
 struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
@@ -261,8 +261,8 @@ static inline struct page *follow_huge_pd(struct vm_area_struct *vma,
 	return NULL;
 }
 
-static inline struct page *follow_huge_pmd(struct mm_struct *mm,
-				unsigned long address, pmd_t *pmd, int flags)
+static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma,
+				unsigned long address, int flags)
 {
 	return NULL;
 }
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 35b2d845704d..649a4d7c241b 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -5,50 +5,20 @@
 #include <linux/sched.h>
 #include <linux/xarray.h>
 
-struct io_identity {
-	struct files_struct		*files;
-	struct mm_struct		*mm;
-#ifdef CONFIG_BLK_CGROUP
-	struct cgroup_subsys_state	*blkcg_css;
-#endif
-	const struct cred		*creds;
-	struct nsproxy			*nsproxy;
-	struct fs_struct		*fs;
-	unsigned long			fsize;
-#ifdef CONFIG_AUDIT
-	kuid_t				loginuid;
-	unsigned int			sessionid;
-#endif
-	refcount_t			count;
-};
-
-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;
-};
-
 #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 +33,7 @@ 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)
diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h
index 1e0205811394..b0da04fe087b 100644
--- a/include/linux/mc146818rtc.h
+++ b/include/linux/mc146818rtc.h
@@ -125,7 +125,11 @@ struct cmos_rtc_board_info {
 #define RTC_IO_EXTENT_USED      RTC_IO_EXTENT
 #endif /* ARCH_RTC_LOCATION */
 
-unsigned int mc146818_get_time(struct rtc_time *time);
+bool mc146818_does_rtc_work(void);
+int mc146818_get_time(struct rtc_time *time);
 int mc146818_set_time(struct rtc_time *time);
 
+bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
+			void *param);
+
 #endif /* _MC146818RTC_H */
diff --git a/include/linux/namei.h b/include/linux/namei.h
index a4bb992623c4..b9605b2b46e7 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -46,6 +46,7 @@ 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)
 
diff --git a/include/linux/net.h b/include/linux/net.h
index 0dcd51feef02..ae713c851342 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -42,8 +42,6 @@ struct net;
 #define SOCK_PASSCRED		3
 #define SOCK_PASSSEC		4
 
-#define PROTO_CMSG_DATA_ONLY	0x0001
-
 #ifndef ARCH_HAS_SOCKET_TYPES
 /**
  * enum sock_type - Socket types
@@ -138,7 +136,6 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
 
 struct proto_ops {
 	int		family;
-	unsigned int	flags;
 	struct module	*owner;
 	int		(*release)   (struct socket *sock);
 	int		(*bind)	     (struct socket *sock,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b055c217eb0b..5da4b3c89f63 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -885,6 +885,9 @@ struct task_struct {
 	/* CLONE_CHILD_CLEARTID: */
 	int __user			*clear_child_tid;
 
+	/* PF_IO_WORKER */
+	void				*pf_io_worker;
+
 	u64				utime;
 	u64				stime;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index d2b4204ba4d3..fa067de9f1a9 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -19,7 +19,6 @@ struct task_struct;
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
-#define JOBCTL_TASK_WORK_BIT	24	/* set by TWA_SIGNAL */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -29,10 +28,9 @@ struct task_struct;
 #define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
 #define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
-#define JOBCTL_TASK_WORK	(1UL << JOBCTL_TASK_WORK_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
-#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK | JOBCTL_TASK_WORK)
+#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
 
 extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask);
 extern void task_clear_jobctl_trapping(struct task_struct *task);
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 657640015b33..ae60f838ebb9 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -354,11 +354,23 @@ 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));
@@ -366,7 +378,7 @@ 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)
@@ -503,7 +515,7 @@ 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();
 }
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index eeacb4a16fe3..4ce511437a8a 100644
--- a/include/linux/sched/task.h
+++ b/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);
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 9a6dd92e60c0..72794d115364 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -424,6 +424,9 @@ 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);
@@ -439,5 +442,6 @@ 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 */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index aea0ce9f3b74..a058c96cf213 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -341,7 +341,7 @@ asmlinkage long sys_io_uring_setup(u32 entries,
 				struct io_uring_params __user *p);
 asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit,
 				u32 min_complete, u32 flags,
-				const sigset_t __user *sig, size_t sigsz);
+				const void __user *argp, size_t argsz);
 asmlinkage long sys_io_uring_register(unsigned int fd, unsigned int op,
 				void __user *arg, unsigned int nr_args);
 
diff --git a/include/linux/task_work.h b/include/linux/task_work.h
index 0d848a1e9e62..5b8a93f288bb 100644
--- a/include/linux/task_work.h
+++ b/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);
 
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index b480e1a07ed8..ee9ab7dbc8c3 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -198,4 +198,27 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 	blkcg_maybe_throttle_current();
 }
 
+/*
+ * 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> */
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 27ff8eb786dc..cedb68e49e4f 100644
--- a/include/linux/uio.h
+++ b/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);
 
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index 9f0d3b7d56b0..0dd30de00e5b 100644
--- a/include/trace/events/io_uring.h
+++ b/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 */
diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h
index 8a3432d0f0dc..e687658843b1 100644
--- a/include/uapi/linux/eventpoll.h
+++ b/include/uapi/linux/eventpoll.h
@@ -41,6 +41,12 @@
 #define EPOLLMSG	(__force __poll_t)0x00000400
 #define EPOLLRDHUP	(__force __poll_t)0x00002000
 
+/*
+ * Internal flag - wakeup generated by io_uring, used to detect recursion back
+ * into the io_uring poll handler.
+ */
+#define EPOLL_URING_WAKE	((__force __poll_t)(1U << 27))
+
 /* Set exclusive wakeup mode for the target file descriptor */
 #define EPOLLEXCLUSIVE	((__force __poll_t)(1U << 28))
 
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 98d8e06dea22..6481db937002 100644
--- a/include/uapi/linux/io_uring.h
+++ b/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,
@@ -145,8 +150,13 @@ 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
@@ -154,6 +164,21 @@ enum {
 #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)
  */
 struct io_uring_cqe {
@@ -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
diff --git a/include/uapi/linux/openat2.h b/include/uapi/linux/openat2.h
index 58b1eb711360..a5feb7604948 100644
--- a/include/uapi/linux/openat2.h
+++ b/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 */