Merge tag 'for-5.15/io_uring-2021-08-30' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:

 - cancellation cleanups (Hao, Pavel)

 - io-wq accounting cleanup (Hao)

 - io_uring submit locking fix (Hao)

 - io_uring link handling fixes (Hao)

 - fixed file improvements (wangyangbo, Pavel)

 - allow updates of linked timeouts like regular timeouts (Pavel)

 - IOPOLL fix (Pavel)

 - remove batched file get optimization (Pavel)

 - improve reference handling (Pavel)

 - IRQ task_work batching (Pavel)

 - allow pure fixed file, and add support for open/accept (Pavel)

 - GFP_ATOMIC RT kernel fix

 - multiple CQ ring waiter improvement

 - funnel IRQ completions through task_work

 - add support for limiting async workers explicitly

 - add different clocksource support for timeouts

 - io-wq wakeup race fix

 - lots of cleanups and improvement (Pavel et al)

* tag 'for-5.15/io_uring-2021-08-30' of git://git.kernel.dk/linux-block: (87 commits)
  io-wq: fix wakeup race when adding new work
  io-wq: wqe and worker locks no longer need to be IRQ safe
  io-wq: check max_worker limits if a worker transitions bound state
  io_uring: allow updating linked timeouts
  io_uring: keep ltimeouts in a list
  io_uring: support CLOCK_BOOTTIME/REALTIME for timeouts
  io-wq: provide a way to limit max number of workers
  io_uring: add build check for buf_index overflows
  io_uring: clarify io_req_task_cancel() locking
  io_uring: add task-refs-get helper
  io_uring: fix failed linkchain code logic
  io_uring: remove redundant req_set_fail()
  io_uring: don't free request to slab
  io_uring: accept directly into fixed file table
  io_uring: hand code io_accept() fd installing
  io_uring: openat directly into fixed fd table
  net: add accept helper not installing fd
  io_uring: fix io_try_cancel_userdata race for iowq
  io_uring: IRQ rw completion batching
  io_uring: batch task work locking
  ...

fs/io-wq.h

@@ -44,6 +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);
@@ -51,7 +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,
@@ -128,6 +128,7 @@ 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)
 {

include/linux/io_uring.h

@@ -7,17 +7,18 @@
 
 #if defined(CONFIG_IO_URING)
 struct sock *io_uring_get_socket(struct file *file);
-void __io_uring_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_files_cancel(struct files_struct *files)
+static inline void io_uring_files_cancel(void)
 {
 	if (current->io_uring)
-		__io_uring_cancel(files);
+		__io_uring_cancel(false);
 }
 static inline void io_uring_task_cancel(void)
 {
-	return io_uring_files_cancel(NULL);
+	if (current->io_uring)
+		__io_uring_cancel(true);
 }
 static inline void io_uring_free(struct task_struct *tsk)
 {
@@ -32,7 +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)

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);

include/uapi/linux/io_uring.h

@@ -55,7 +55,10 @@ struct io_uring_sqe {
 	} __attribute__((packed));
 	/* personality to use, if used */
 	__u16	personality;
+	union {
 		__s32	splice_fd_in;
+		__u32	file_index;
+	};
 	__u64	__pad2[2];
 };
 
@@ -148,7 +151,11 @@ enum {
  */
 #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
@@ -306,6 +313,9 @@ enum {
 	IORING_REGISTER_IOWQ_AFF		= 17,
 	IORING_UNREGISTER_IOWQ_AFF		= 18,
 
+	/* set/get max number of workers */
+	IORING_REGISTER_IOWQ_MAX_WORKERS	= 19,
+
 	/* this goes last */
 	IORING_REGISTER_LAST
 };

kernel/exit.c

@@ -777,7 +777,7 @@ 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 */

net/socket.c

@@ -1722,32 +1722,22 @@ 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);
-	if (!sock) {
-		err = -ENOTSOCK;
-		goto out;
-	}
+	if (!sock)
+		return ERR_PTR(-ENOTSOCK);
 
-	err = -ENFILE;
 	newsock = sock_alloc();
 	if (!newsock)
-		goto out;
+		return ERR_PTR(-ENFILE);
 
 	newsock->type = sock->type;
 	newsock->ops = sock->ops;
@@ -1758,18 +1748,9 @@ 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)
@@ -1794,16 +1775,38 @@ 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;
 }
 
 /*