Merge tag 'for-5.2/io_uring-20190507' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:
 "Set of changes/improvements for io_uring. This contains:

   - Fix of a shadowed variable (Colin)

   - Add support for draining commands (me)

   - Add support for sync_file_range() (me)

   - Add eventfd support (me)

   - cpu_online() fix (Shenghui)

   - Removal of a redundant ->error assignment (Stefan)"

* tag 'for-5.2/io_uring-20190507' of git://git.kernel.dk/linux-block:
  io_uring: use cpu_online() to check p->sq_thread_cpu instead of cpu_possible()
  io_uring: fix shadowed variable ret return code being not checked
  req->error only used for iopoll
  io_uring: add support for eventfd notifications
  io_uring: add support for IORING_OP_SYNC_FILE_RANGE
  fs: add sync_file_range() helper
  io_uring: add support for marking commands as draining

fs/io_uring.c

@@ -222,6 +222,8 @@ struct io_ring_ctx {
 		unsigned		sq_mask;
 		unsigned		sq_thread_idle;
 		struct io_uring_sqe	*sq_sqes;
+
+		struct list_head	defer_list;
 	} ____cacheline_aligned_in_smp;
 
 	/* IO offload */
@@ -239,6 +241,7 @@ struct io_ring_ctx {
 		unsigned		cq_mask;
 		struct wait_queue_head	cq_wait;
 		struct fasync_struct	*cq_fasync;
+		struct eventfd_ctx	*cq_ev_fd;
 	} ____cacheline_aligned_in_smp;
 
 	/*
@@ -327,8 +330,11 @@ struct io_kiocb {
 #define REQ_F_FIXED_FILE	4	/* ctx owns file */
 #define REQ_F_SEQ_PREV		8	/* sequential with previous */
 #define REQ_F_PREPPED		16	/* prep already done */
+#define REQ_F_IO_DRAIN		32	/* drain existing IO first */
+#define REQ_F_IO_DRAINED	64	/* drain done */
 	u64			user_data;
-	u64			error;
+	u32			error;	/* iopoll result from callback */
+	u32			sequence;
 
 	struct work_struct	work;
 };
@@ -356,6 +362,8 @@ struct io_submit_state {
 	unsigned int		ios_left;
 };
 
+static void io_sq_wq_submit_work(struct work_struct *work);
+
 static struct kmem_cache *req_cachep;
 
 static const struct file_operations io_uring_fops;
@@ -407,10 +415,36 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	spin_lock_init(&ctx->completion_lock);
 	INIT_LIST_HEAD(&ctx->poll_list);
 	INIT_LIST_HEAD(&ctx->cancel_list);
+	INIT_LIST_HEAD(&ctx->defer_list);
 	return ctx;
 }
 
-static void io_commit_cqring(struct io_ring_ctx *ctx)
+static inline bool io_sequence_defer(struct io_ring_ctx *ctx,
+				     struct io_kiocb *req)
+{
+	if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN)
+		return false;
+
+	return req->sequence > ctx->cached_cq_tail + ctx->sq_ring->dropped;
+}
+
+static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
+{
+	struct io_kiocb *req;
+
+	if (list_empty(&ctx->defer_list))
+		return NULL;
+
+	req = list_first_entry(&ctx->defer_list, struct io_kiocb, list);
+	if (!io_sequence_defer(ctx, req)) {
+		list_del_init(&req->list);
+		return req;
+	}
+
+	return NULL;
+}
+
+static void __io_commit_cqring(struct io_ring_ctx *ctx)
 {
 	struct io_cq_ring *ring = ctx->cq_ring;
 
@@ -425,6 +459,18 @@ static void io_commit_cqring(struct io_ring_ctx *ctx)
 	}
 }
 
+static void io_commit_cqring(struct io_ring_ctx *ctx)
+{
+	struct io_kiocb *req;
+
+	__io_commit_cqring(ctx);
+
+	while ((req = io_get_deferred_req(ctx)) != NULL) {
+		req->flags |= REQ_F_IO_DRAINED;
+		queue_work(ctx->sqo_wq, &req->work);
+	}
+}
+
 static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
 {
 	struct io_cq_ring *ring = ctx->cq_ring;
@@ -471,6 +517,8 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
 		wake_up(&ctx->wait);
 	if (waitqueue_active(&ctx->sqo_wait))
 		wake_up(&ctx->sqo_wait);
+	if (ctx->cq_ev_fd)
+		eventfd_signal(ctx->cq_ev_fd, 1);
 }
 
 static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data,
@@ -1222,6 +1270,54 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	return 0;
 }
 
+static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	int ret = 0;
+
+	if (!req->file)
+		return -EBADF;
+	/* Prep already done (EAGAIN retry) */
+	if (req->flags & REQ_F_PREPPED)
+		return 0;
+
+	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+	if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index))
+		return -EINVAL;
+
+	req->flags |= REQ_F_PREPPED;
+	return ret;
+}
+
+static int io_sync_file_range(struct io_kiocb *req,
+			      const struct io_uring_sqe *sqe,
+			      bool force_nonblock)
+{
+	loff_t sqe_off;
+	loff_t sqe_len;
+	unsigned flags;
+	int ret;
+
+	ret = io_prep_sfr(req, sqe);
+	if (ret)
+		return ret;
+
+	/* sync_file_range always requires a blocking context */
+	if (force_nonblock)
+		return -EAGAIN;
+
+	sqe_off = READ_ONCE(sqe->off);
+	sqe_len = READ_ONCE(sqe->len);
+	flags = READ_ONCE(sqe->sync_range_flags);
+
+	ret = sync_file_range(req->rw.ki_filp, sqe_off, sqe_len, flags);
+
+	io_cqring_add_event(req->ctx, sqe->user_data, ret, 0);
+	io_put_req(req);
+	return 0;
+}
+
 static void io_poll_remove_one(struct io_kiocb *req)
 {
 	struct io_poll_iocb *poll = &req->poll;
@@ -1424,7 +1520,6 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		spin_unlock(&poll->head->lock);
 	}
 	if (mask) { /* no async, we'd stolen it */
-		req->error = mangle_poll(mask);
 		ipt.error = 0;
 		io_poll_complete(ctx, req, mask);
 	}
@@ -1437,6 +1532,34 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return ipt.error;
 }
 
+static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req,
+			const struct io_uring_sqe *sqe)
+{
+	struct io_uring_sqe *sqe_copy;
+
+	if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list))
+		return 0;
+
+	sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL);
+	if (!sqe_copy)
+		return -EAGAIN;
+
+	spin_lock_irq(&ctx->completion_lock);
+	if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list)) {
+		spin_unlock_irq(&ctx->completion_lock);
+		kfree(sqe_copy);
+		return 0;
+	}
+
+	memcpy(sqe_copy, sqe, sizeof(*sqe_copy));
+	req->submit.sqe = sqe_copy;
+
+	INIT_WORK(&req->work, io_sq_wq_submit_work);
+	list_add_tail(&req->list, &ctx->defer_list);
+	spin_unlock_irq(&ctx->completion_lock);
+	return -EIOCBQUEUED;
+}
+
 static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 			   const struct sqe_submit *s, bool force_nonblock)
 {
@@ -1476,6 +1599,9 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	case IORING_OP_POLL_REMOVE:
 		ret = io_poll_remove(req, s->sqe);
 		break;
+	case IORING_OP_SYNC_FILE_RANGE:
+		ret = io_sync_file_range(req, s->sqe, force_nonblock);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -1684,6 +1810,11 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
 	flags = READ_ONCE(s->sqe->flags);
 	fd = READ_ONCE(s->sqe->fd);
 
+	if (flags & IOSQE_IO_DRAIN) {
+		req->flags |= REQ_F_IO_DRAIN;
+		req->sequence = ctx->cached_sq_head - 1;
+	}
+
 	if (!io_op_needs_file(s->sqe)) {
 		req->file = NULL;
 		return 0;
@@ -1713,7 +1844,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
 	int ret;
 
 	/* enforce forwards compatibility on users */
-	if (unlikely(s->sqe->flags & ~IOSQE_FIXED_FILE))
+	if (unlikely(s->sqe->flags & ~(IOSQE_FIXED_FILE | IOSQE_IO_DRAIN)))
 		return -EINVAL;
 
 	req = io_get_req(ctx, state);
@@ -1724,6 +1855,13 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
 	if (unlikely(ret))
 		goto out;
 
+	ret = io_req_defer(ctx, req, s->sqe);
+	if (ret) {
+		if (ret == -EIOCBQUEUED)
+			ret = 0;
+		return ret;
+	}
+
 	ret = __io_submit_sqe(ctx, req, s, true);
 	if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
 		struct io_uring_sqe *sqe_copy;
@@ -2225,7 +2363,6 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx)
 	left = ctx->nr_user_files;
 	while (left) {
 		unsigned this_files = min_t(unsigned, left, SCM_MAX_FD);
-		int ret;
 
 		ret = __io_sqe_files_scm(ctx, this_files, total);
 		if (ret)
@@ -2334,7 +2471,7 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 							nr_cpu_ids);
 
 			ret = -EINVAL;
-			if (!cpu_possible(cpu))
+			if (!cpu_online(cpu))
 				goto err;
 
 			ctx->sqo_thread = kthread_create_on_cpu(io_sq_thread,
@@ -2621,6 +2758,38 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 	return ret;
 }
 
+static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg)
+{
+	__s32 __user *fds = arg;
+	int fd;
+
+	if (ctx->cq_ev_fd)
+		return -EBUSY;
+
+	if (copy_from_user(&fd, fds, sizeof(*fds)))
+		return -EFAULT;
+
+	ctx->cq_ev_fd = eventfd_ctx_fdget(fd);
+	if (IS_ERR(ctx->cq_ev_fd)) {
+		int ret = PTR_ERR(ctx->cq_ev_fd);
+		ctx->cq_ev_fd = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int io_eventfd_unregister(struct io_ring_ctx *ctx)
+{
+	if (ctx->cq_ev_fd) {
+		eventfd_ctx_put(ctx->cq_ev_fd);
+		ctx->cq_ev_fd = NULL;
+		return 0;
+	}
+
+	return -ENXIO;
+}
+
 static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 {
 	io_finish_async(ctx);
@@ -2630,6 +2799,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	io_iopoll_reap_events(ctx);
 	io_sqe_buffer_unregister(ctx);
 	io_sqe_files_unregister(ctx);
+	io_eventfd_unregister(ctx);
 
 #if defined(CONFIG_UNIX)
 	if (ctx->ring_sock)
@@ -3043,6 +3213,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_sqe_files_unregister(ctx);
 		break;
+	case IORING_REGISTER_EVENTFD:
+		ret = -EINVAL;
+		if (nr_args != 1)
+			break;
+		ret = io_eventfd_register(ctx, arg);
+		break;
+	case IORING_UNREGISTER_EVENTFD:
+		ret = -EINVAL;
+		if (arg || nr_args)
+			break;
+		ret = io_eventfd_unregister(ctx);
+		break;
 	default:
 		ret = -EINVAL;
 		break;

fs/sync.c

@@ -234,58 +234,10 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
 	return do_fsync(fd, 1);
 }
 
-/*
- * sys_sync_file_range() permits finely controlled syncing over a segment of
- * a file in the range offset .. (offset+nbytes-1) inclusive.  If nbytes is
- * zero then sys_sync_file_range() will operate from offset out to EOF.
- *
- * The flag bits are:
- *
- * SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range
- * before performing the write.
- *
- * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the
- * range which are not presently under writeback. Note that this may block for
- * significant periods due to exhaustion of disk request structures.
- *
- * SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range
- * after performing the write.
- *
- * Useful combinations of the flag bits are:
- *
- * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages
- * in the range which were dirty on entry to sys_sync_file_range() are placed
- * under writeout.  This is a start-write-for-data-integrity operation.
- *
- * SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which
- * are not presently under writeout.  This is an asynchronous flush-to-disk
- * operation.  Not suitable for data integrity operations.
- *
- * SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for
- * completion of writeout of all pages in the range.  This will be used after an
- * earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait
- * for that operation to complete and to return the result.
- *
- * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER:
- * a traditional sync() operation.  This is a write-for-data-integrity operation
- * which will ensure that all pages in the range which were dirty on entry to
- * sys_sync_file_range() are committed to disk.
- *
- *
- * SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any
- * I/O errors or ENOSPC conditions and will return those to the caller, after
- * clearing the EIO and ENOSPC flags in the address_space.
- *
- * It should be noted that none of these operations write out the file's
- * metadata.  So unless the application is strictly performing overwrites of
- * already-instantiated disk blocks, there are no guarantees here that the data
- * will be available after a crash.
- */
-int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
-			 unsigned int flags)
+int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
+		    unsigned int flags)
 {
 	int ret;
-	struct fd f;
 	struct address_space *mapping;
 	loff_t endbyte;			/* inclusive */
 	umode_t i_mode;
@@ -325,41 +277,96 @@ int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
 	else
 		endbyte--;		/* inclusive */
 
-	ret = -EBADF;
-	f = fdget(fd);
-	if (!f.file)
-		goto out;
-
-	i_mode = file_inode(f.file)->i_mode;
+	i_mode = file_inode(file)->i_mode;
 	ret = -ESPIPE;
 	if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
 			!S_ISLNK(i_mode))
-		goto out_put;
+		goto out;
 
-	mapping = f.file->f_mapping;
+	mapping = file->f_mapping;
 	ret = 0;
 	if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
-		ret = file_fdatawait_range(f.file, offset, endbyte);
+		ret = file_fdatawait_range(file, offset, endbyte);
 		if (ret < 0)
-			goto out_put;
+			goto out;
 	}
 
 	if (flags & SYNC_FILE_RANGE_WRITE) {
 		ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
 						 WB_SYNC_NONE);
 		if (ret < 0)
-			goto out_put;
+			goto out;
 	}
 
 	if (flags & SYNC_FILE_RANGE_WAIT_AFTER)
-		ret = file_fdatawait_range(f.file, offset, endbyte);
+		ret = file_fdatawait_range(file, offset, endbyte);
 
-out_put:
-	fdput(f);
 out:
 	return ret;
 }
 
+/*
+ * sys_sync_file_range() permits finely controlled syncing over a segment of
+ * a file in the range offset .. (offset+nbytes-1) inclusive.  If nbytes is
+ * zero then sys_sync_file_range() will operate from offset out to EOF.
+ *
+ * The flag bits are:
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range
+ * before performing the write.
+ *
+ * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the
+ * range which are not presently under writeback. Note that this may block for
+ * significant periods due to exhaustion of disk request structures.
+ *
+ * SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range
+ * after performing the write.
+ *
+ * Useful combinations of the flag bits are:
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages
+ * in the range which were dirty on entry to sys_sync_file_range() are placed
+ * under writeout.  This is a start-write-for-data-integrity operation.
+ *
+ * SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which
+ * are not presently under writeout.  This is an asynchronous flush-to-disk
+ * operation.  Not suitable for data integrity operations.
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for
+ * completion of writeout of all pages in the range.  This will be used after an
+ * earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait
+ * for that operation to complete and to return the result.
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER:
+ * a traditional sync() operation.  This is a write-for-data-integrity operation
+ * which will ensure that all pages in the range which were dirty on entry to
+ * sys_sync_file_range() are committed to disk.
+ *
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any
+ * I/O errors or ENOSPC conditions and will return those to the caller, after
+ * clearing the EIO and ENOSPC flags in the address_space.
+ *
+ * It should be noted that none of these operations write out the file's
+ * metadata.  So unless the application is strictly performing overwrites of
+ * already-instantiated disk blocks, there are no guarantees here that the data
+ * will be available after a crash.
+ */
+int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
+			 unsigned int flags)
+{
+	int ret;
+	struct fd f;
+
+	ret = -EBADF;
+	f = fdget(fd);
+	if (f.file)
+		ret = sync_file_range(f.file, offset, nbytes, flags);
+
+	fdput(f);
+	return ret;
+}
+
 SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes,
 				unsigned int, flags)
 {

include/linux/fs.h

@@ -2789,6 +2789,9 @@ extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
 			   int datasync);
 extern int vfs_fsync(struct file *file, int datasync);
 
+extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
+				unsigned int flags);
+
 /*
  * Sync the bytes written if this was a synchronous write.  Expect ki_pos
  * to already be updated for the write, and will return either the amount

include/uapi/linux/io_uring.h

@@ -26,6 +26,7 @@ struct io_uring_sqe {
 		__kernel_rwf_t	rw_flags;
 		__u32		fsync_flags;
 		__u16		poll_events;
+		__u32		sync_range_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	union {
@@ -38,6 +39,7 @@ struct io_uring_sqe {
  * sqe->flags
  */
 #define IOSQE_FIXED_FILE	(1U << 0)	/* use fixed fileset */
+#define IOSQE_IO_DRAIN		(1U << 1)	/* issue after inflight IO */
 
 /*
  * io_uring_setup() flags
@@ -54,6 +56,7 @@ struct io_uring_sqe {
 #define IORING_OP_WRITE_FIXED	5
 #define IORING_OP_POLL_ADD	6
 #define IORING_OP_POLL_REMOVE	7
+#define IORING_OP_SYNC_FILE_RANGE	8
 
 /*
  * sqe->fsync_flags
@@ -133,5 +136,7 @@ struct io_uring_params {
 #define IORING_UNREGISTER_BUFFERS	1
 #define IORING_REGISTER_FILES		2
 #define IORING_UNREGISTER_FILES		3
+#define IORING_REGISTER_EVENTFD		4
+#define IORING_UNREGISTER_EVENTFD	5
 
 #endif