Merge tag 'for-5.7/io_uring-2020-03-29' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:
 "Here are the io_uring changes for this merge window. Light on new
  features this time around (just splice + buffer selection), lots of
  cleanups, fixes, and improvements to existing support. In particular,
  this contains:

   - Cleanup fixed file update handling for stack fallback (Hillf)

   - Re-work of how pollable async IO is handled, we no longer require
     thread offload to handle that. Instead we rely using poll to drive
     this, with task_work execution.

   - In conjunction with the above, allow expendable buffer selection,
     so that poll+recv (for example) no longer has to be a split
     operation.

   - Make sure we honor RLIMIT_FSIZE for buffered writes

   - Add support for splice (Pavel)

   - Linked work inheritance fixes and optimizations (Pavel)

   - Async work fixes and cleanups (Pavel)

   - Improve io-wq locking (Pavel)

   - Hashed link write improvements (Pavel)

   - SETUP_IOPOLL|SETUP_SQPOLL improvements (Xiaoguang)"

* tag 'for-5.7/io_uring-2020-03-29' of git://git.kernel.dk/linux-block: (54 commits)
  io_uring: cleanup io_alloc_async_ctx()
  io_uring: fix missing 'return' in comment
  io-wq: handle hashed writes in chains
  io-uring: drop 'free_pfile' in struct io_file_put
  io-uring: drop completion when removing file
  io_uring: Fix ->data corruption on re-enqueue
  io-wq: close cancel gap for hashed linked work
  io_uring: make spdxcheck.py happy
  io_uring: honor original task RLIMIT_FSIZE
  io-wq: hash dependent work
  io-wq: split hashing and enqueueing
  io-wq: don't resched if there is no work
  io-wq: remove duplicated cancel code
  io_uring: fix truncated async read/readv and write/writev retry
  io_uring: dual license io_uring.h uapi header
  io_uring: io_uring_enter(2) don't poll while SETUP_IOPOLL|SETUP_SQPOLL enabled
  io_uring: Fix unused function warnings
  io_uring: add end-of-bits marker and build time verify it
  io_uring: provide means of removing buffers
  io_uring: add IOSQE_BUFFER_SELECT support for IORING_OP_RECVMSG
  ...

fs/io-wq.h

@@ -5,10 +5,8 @@ struct io_wq;
 
 enum {
 	IO_WQ_WORK_CANCEL	= 1,
-	IO_WQ_WORK_HAS_MM	= 2,
 	IO_WQ_WORK_HASHED	= 4,
 	IO_WQ_WORK_UNBOUND	= 32,
-	IO_WQ_WORK_CB		= 128,
 	IO_WQ_WORK_NO_CANCEL	= 256,
 	IO_WQ_WORK_CONCURRENT	= 512,
 
@@ -30,6 +28,18 @@ struct io_wq_work_list {
 	struct io_wq_work_node *last;
 };
 
+static inline void wq_list_add_after(struct io_wq_work_node *node,
+				     struct io_wq_work_node *pos,
+				     struct io_wq_work_list *list)
+{
+	struct io_wq_work_node *next = pos->next;
+
+	pos->next = node;
+	node->next = next;
+	if (!next)
+		list->last = node;
+}
+
 static inline void wq_list_add_tail(struct io_wq_work_node *node,
 				    struct io_wq_work_list *list)
 {
@@ -42,17 +52,26 @@ static inline void wq_list_add_tail(struct io_wq_work_node *node,
 	}
 }
 
-static inline void wq_node_del(struct io_wq_work_list *list,
-			       struct io_wq_work_node *node,
+static inline void wq_list_cut(struct io_wq_work_list *list,
+			       struct io_wq_work_node *last,
 			       struct io_wq_work_node *prev)
 {
-	if (node == list->first)
-		WRITE_ONCE(list->first, node->next);
-	if (node == list->last)
+	/* first in the list, if prev==NULL */
+	if (!prev)
+		WRITE_ONCE(list->first, last->next);
+	else
+		prev->next = last->next;
+
+	if (last == list->last)
 		list->last = prev;
-	if (prev)
-		prev->next = node->next;
-	node->next = NULL;
+	last->next = NULL;
+}
+
+static inline void wq_list_del(struct io_wq_work_list *list,
+			       struct io_wq_work_node *node,
+			       struct io_wq_work_node *prev)
+{
+	wq_list_cut(list, node, prev);
 }
 
 #define wq_list_for_each(pos, prv, head)			\
@@ -65,10 +84,7 @@ static inline void wq_node_del(struct io_wq_work_list *list,
 } while (0)
 
 struct io_wq_work {
-	union {
 	struct io_wq_work_node list;
-		void *data;
-	};
 	void (*func)(struct io_wq_work **);
 	struct files_struct *files;
 	struct mm_struct *mm;
@@ -83,14 +99,20 @@ struct io_wq_work {
 		*(work) = (struct io_wq_work){ .func = _func };	\
 	} while (0)						\
 
-typedef void (get_work_fn)(struct io_wq_work *);
-typedef void (put_work_fn)(struct io_wq_work *);
+static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
+{
+	if (!work->list.next)
+		return NULL;
+
+	return container_of(work->list.next, struct io_wq_work, list);
+}
+
+typedef void (free_work_fn)(struct io_wq_work *);
 
 struct io_wq_data {
 	struct user_struct *user;
 
-	get_work_fn *get_work;
-	put_work_fn *put_work;
+	free_work_fn *free_work;
 };
 
 struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
@@ -98,7 +120,12 @@ bool io_wq_get(struct io_wq *wq, struct io_wq_data *data);
 void io_wq_destroy(struct io_wq *wq);
 
 void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
-void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val);
+void io_wq_hash_work(struct io_wq_work *work, void *val);
+
+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);
 enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);

fs/splice.c

@@ -1109,7 +1109,7 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
 /*
  * Determine where to splice to/from.
  */
-static long do_splice(struct file *in, loff_t __user *off_in,
+long do_splice(struct file *in, loff_t __user *off_in,
 		struct file *out, loff_t __user *off_out,
 		size_t len, unsigned int flags)
 {

include/linux/socket.h

@@ -391,6 +391,10 @@ extern int recvmsg_copy_msghdr(struct msghdr *msg,
 			       struct user_msghdr __user *umsg, unsigned flags,
 			       struct sockaddr __user **uaddr,
 			       struct iovec **iov);
+extern int __copy_msghdr_from_user(struct msghdr *kmsg,
+				   struct user_msghdr __user *umsg,
+				   struct sockaddr __user **save_addr,
+				   struct iovec __user **uiov, size_t *nsegs);
 
 /* helpers which do the actual work for syscalls */
 extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,

include/linux/splice.h

@@ -78,6 +78,9 @@ extern ssize_t add_to_pipe(struct pipe_inode_info *,
 			      struct pipe_buffer *);
 extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
 				      splice_direct_actor *);
+extern long do_splice(struct file *in, loff_t __user *off_in,
+		      struct file *out, loff_t __user *off_out,
+		      size_t len, unsigned int flags);
 
 /*
  * for dynamic pipe sizing

include/net/compat.h

@@ -38,6 +38,9 @@ struct compat_cmsghdr {
 #define compat_mmsghdr	mmsghdr
 #endif /* defined(CONFIG_COMPAT) */
 
+int __get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg,
+			struct sockaddr __user **save_addr, compat_uptr_t *ptr,
+			compat_size_t *len);
 int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *,
 		      struct sockaddr __user **, struct iovec **);
 struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval);

include/trace/events/io_uring.h

@@ -357,6 +357,109 @@ TRACE_EVENT(io_uring_submit_sqe,
 			  __entry->force_nonblock, __entry->sq_thread)
 );
 
+TRACE_EVENT(io_uring_poll_arm,
+
+	TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask, int events),
+
+	TP_ARGS(ctx, opcode, user_data, mask, events),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx		)
+		__field(  u8,		opcode		)
+		__field(  u64,		user_data	)
+		__field(  int,		mask		)
+		__field(  int,		events		)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__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)
+);
+
+TRACE_EVENT(io_uring_poll_wake,
+
+	TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask),
+
+	TP_ARGS(ctx, opcode, user_data, mask),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx		)
+		__field(  u8,		opcode		)
+		__field(  u64,		user_data	)
+		__field(  int,		mask		)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__entry->opcode		= opcode;
+		__entry->user_data	= user_data;
+		__entry->mask		= mask;
+	),
+
+	TP_printk("ring %p, op %d, data 0x%llx, mask 0x%x",
+			  __entry->ctx, __entry->opcode,
+			  (unsigned long long) __entry->user_data,
+			  __entry->mask)
+);
+
+TRACE_EVENT(io_uring_task_add,
+
+	TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask),
+
+	TP_ARGS(ctx, opcode, user_data, mask),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx		)
+		__field(  u8,		opcode		)
+		__field(  u64,		user_data	)
+		__field(  int,		mask		)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__entry->opcode		= opcode;
+		__entry->user_data	= user_data;
+		__entry->mask		= mask;
+	),
+
+	TP_printk("ring %p, op %d, data 0x%llx, mask %x",
+			  __entry->ctx, __entry->opcode,
+			  (unsigned long long) __entry->user_data,
+			  __entry->mask)
+);
+
+TRACE_EVENT(io_uring_task_run,
+
+	TP_PROTO(void *ctx, u8 opcode, u64 user_data),
+
+	TP_ARGS(ctx, opcode, user_data),
+
+	TP_STRUCT__entry (
+		__field(  void *,	ctx		)
+		__field(  u8,		opcode		)
+		__field(  u64,		user_data	)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__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)
+);
+
 #endif /* _TRACE_IO_URING_H */
 
 /* This part must be outside protection */

include/uapi/linux/io_uring.h

-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
 /*
  * Header file for the io_uring interface.
  *
@@ -23,7 +23,10 @@ struct io_uring_sqe {
 		__u64	off;	/* offset into file */
 		__u64	addr2;
 	};
+	union {
 		__u64	addr;	/* pointer to buffer or iovecs */
+		__u64	splice_off_in;
+	};
 	__u32	len;		/* buffer size or number of iovecs */
 	union {
 		__kernel_rwf_t	rw_flags;
@@ -37,14 +40,21 @@ struct io_uring_sqe {
 		__u32		open_flags;
 		__u32		statx_flags;
 		__u32		fadvise_advice;
+		__u32		splice_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	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];
 	};
@@ -56,6 +66,7 @@ enum {
 	IOSQE_IO_LINK_BIT,
 	IOSQE_IO_HARDLINK_BIT,
 	IOSQE_ASYNC_BIT,
+	IOSQE_BUFFER_SELECT_BIT,
 };
 
 /*
@@ -71,6 +82,8 @@ enum {
 #define IOSQE_IO_HARDLINK	(1U << IOSQE_IO_HARDLINK_BIT)
 /* always go async */
 #define IOSQE_ASYNC		(1U << IOSQE_ASYNC_BIT)
+/* select buffer from sqe->buf_group */
+#define IOSQE_BUFFER_SELECT	(1U << IOSQE_BUFFER_SELECT_BIT)
 
 /*
  * io_uring_setup() flags
@@ -113,6 +126,9 @@ enum {
 	IORING_OP_RECV,
 	IORING_OP_OPENAT2,
 	IORING_OP_EPOLL_CTL,
+	IORING_OP_SPLICE,
+	IORING_OP_PROVIDE_BUFFERS,
+	IORING_OP_REMOVE_BUFFERS,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -128,6 +144,12 @@ enum {
  */
 #define IORING_TIMEOUT_ABS	(1U << 0)
 
+/*
+ * sqe->splice_flags
+ * extends splice(2) flags
+ */
+#define SPLICE_F_FD_IN_FIXED	(1U << 31) /* the last bit of __u32 */
+
 /*
  * IO completion data structure (Completion Queue Entry)
  */
@@ -137,6 +159,17 @@ struct io_uring_cqe {
 	__u32	flags;
 };
 
+/*
+ * cqe->flags
+ *
+ * IORING_CQE_F_BUFFER	If set, the upper 16 bits are the buffer ID
+ */
+#define IORING_CQE_F_BUFFER		(1U << 0)
+
+enum {
+	IORING_CQE_BUFFER_SHIFT		= 16,
+};
+
 /*
  * Magic offsets for the application to mmap the data it needs
  */
@@ -204,6 +237,7 @@ struct io_uring_params {
 #define IORING_FEAT_SUBMIT_STABLE	(1U << 2)
 #define IORING_FEAT_RW_CUR_POS		(1U << 3)
 #define IORING_FEAT_CUR_PERSONALITY	(1U << 4)
+#define IORING_FEAT_FAST_POLL		(1U << 5)
 
 /*
  * io_uring_register(2) opcodes and arguments

kernel/task_work.c

@@ -97,16 +97,26 @@ void task_work_run(void)
 		 * work->func() can do task_work_add(), do not set
 		 * work_exited unless the list is empty.
 		 */
-		raw_spin_lock_irq(&task->pi_lock);
 		do {
+			head = NULL;
 			work = READ_ONCE(task->task_works);
-			head = !work && (task->flags & PF_EXITING) ?
-				&work_exited : NULL;
+			if (!work) {
+				if (task->flags & PF_EXITING)
+					head = &work_exited;
+				else
+					break;
+			}
 		} while (cmpxchg(&task->task_works, work, head) != work);
-		raw_spin_unlock_irq(&task->pi_lock);
 
 		if (!work)
 			break;
+		/*
+		 * Synchronize with task_work_cancel(). It can not remove
+		 * the first entry == work, cmpxchg(task_works) must fail.
+		 * But it can remove another entry from the ->next list.
+		 */
+		raw_spin_lock_irq(&task->pi_lock);
+		raw_spin_unlock_irq(&task->pi_lock);
 
 		do {
 			next = work->next;

net/compat.c

@@ -33,10 +33,10 @@
 #include <linux/uaccess.h>
 #include <net/compat.h>
 
-int get_compat_msghdr(struct msghdr *kmsg,
+int __get_compat_msghdr(struct msghdr *kmsg,
 			struct compat_msghdr __user *umsg,
 			struct sockaddr __user **save_addr,
-		      struct iovec **iov)
+			compat_uptr_t *ptr, compat_size_t *len)
 {
 	struct compat_msghdr msg;
 	ssize_t err;
@@ -79,10 +79,26 @@ int get_compat_msghdr(struct msghdr *kmsg,
 		return -EMSGSIZE;
 
 	kmsg->msg_iocb = NULL;
+	*ptr = msg.msg_iov;
+	*len = msg.msg_iovlen;
+	return 0;
+}
+
+int get_compat_msghdr(struct msghdr *kmsg,
+		      struct compat_msghdr __user *umsg,
+		      struct sockaddr __user **save_addr,
+		      struct iovec **iov)
+{
+	compat_uptr_t ptr;
+	compat_size_t len;
+	ssize_t err;
+
+	err = __get_compat_msghdr(kmsg, umsg, save_addr, &ptr, &len);
+	if (err)
+		return err;
 
-	err = compat_import_iovec(save_addr ? READ : WRITE,
-				   compat_ptr(msg.msg_iov), msg.msg_iovlen,
-				   UIO_FASTIOV, iov, &kmsg->msg_iter);
+	err = compat_import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr),
+				   len, UIO_FASTIOV, iov, &kmsg->msg_iter);
 	return err < 0 ? err : 0;
 }
 

net/socket.c

@@ -2228,10 +2228,10 @@ struct used_address {
 	unsigned int name_len;
 };
 
-static int copy_msghdr_from_user(struct msghdr *kmsg,
+int __copy_msghdr_from_user(struct msghdr *kmsg,
 			    struct user_msghdr __user *umsg,
 			    struct sockaddr __user **save_addr,
-				 struct iovec **iov)
+			    struct iovec __user **uiov, size_t *nsegs)
 {
 	struct user_msghdr msg;
 	ssize_t err;
@@ -2273,6 +2273,23 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 		return -EMSGSIZE;
 
 	kmsg->msg_iocb = NULL;
+	*uiov = msg.msg_iov;
+	*nsegs = msg.msg_iovlen;
+	return 0;
+}
+
+static int copy_msghdr_from_user(struct msghdr *kmsg,
+				 struct user_msghdr __user *umsg,
+				 struct sockaddr __user **save_addr,
+				 struct iovec **iov)
+{
+	struct user_msghdr msg;
+	ssize_t err;
+
+	err = __copy_msghdr_from_user(kmsg, umsg, save_addr, &msg.msg_iov,
+					&msg.msg_iovlen);
+	if (err)
+		return err;
 
 	err = import_iovec(save_addr ? READ : WRITE,
 			    msg.msg_iov, msg.msg_iovlen,