[PATCH 0/10 v14] merge request: No wait AIO

[PATCH 0/10 v14] merge request: No wait AIO

[Goldwyn Rodrigues]

Jens,

As discussed, here are the patches against the block
tree for merge since the block layer changes had the most conflicts.
My tree is at https://github.com/goldwynr/linux/tree/nowait-block

 Changes since v13:
 + nowait support for dax files in ext4 and xfs

-- 
Goldwyn

[PATCH 01/10] fs: Separate out kiocb flags setup based on RWF_* flags

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Also added RWF_SUPPORTED to encompass all flags.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/read_write.c         | 12 +++---------
 include/linux/fs.h      | 14 ++++++++++++++
 include/uapi/linux/fs.h |  2 ++
 3 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index 47c1d4484df9..53c816c61122 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -678,16 +678,10 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 	struct kiocb kiocb;
 	ssize_t ret;
 
-	if (flags & ~(RWF_HIPRI | RWF_DSYNC | RWF_SYNC))
-		return -EOPNOTSUPP;
-
 	init_sync_kiocb(&kiocb, filp);
-	if (flags & RWF_HIPRI)
-		kiocb.ki_flags |= IOCB_HIPRI;
-	if (flags & RWF_DSYNC)
-		kiocb.ki_flags |= IOCB_DSYNC;
-	if (flags & RWF_SYNC)
-		kiocb.ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
+	ret = kiocb_set_rw_flags(&kiocb, flags);
+	if (ret)
+		return ret;
 	kiocb.ki_pos = *ppos;
 
 	if (type == READ)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 023f0324762b..96a1a1fa54a9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3057,6 +3057,20 @@ static inline int iocb_flags(struct file *file)
 	return res;
 }
 
+static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags)
+{
+	if (unlikely(flags & ~RWF_SUPPORTED))
+		return -EOPNOTSUPP;
+
+	if (flags & RWF_HIPRI)
+		ki->ki_flags |= IOCB_HIPRI;
+	if (flags & RWF_DSYNC)
+		ki->ki_flags |= IOCB_DSYNC;
+	if (flags & RWF_SYNC)
+		ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
+	return 0;
+}
+
 static inline ino_t parent_ino(struct dentry *dentry)
 {
 	ino_t res;
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 24e61a54feaa..937c3e39650a 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -361,4 +361,6 @@ struct fscrypt_key {
 #define RWF_DSYNC			0x00000002 /* per-IO O_DSYNC */
 #define RWF_SYNC			0x00000004 /* per-IO O_SYNC */
 
+#define RWF_SUPPORTED			(RWF_HIPRI | RWF_DSYNC | RWF_SYNC)
+
 #endif /* _UAPI_LINUX_FS_H */
-- 
2.12.0

[PATCH 02/10] fs: Introduce filemap_range_has_page()

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

filemap_range_has_page() return true if the file's mapping has
a page within the range mentioned. This function will be used
to check if a write() call will cause a writeback of previous
writes.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 include/linux/fs.h |  2 ++
 mm/filemap.c       | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96a1a1fa54a9..0d34f5b5a6b0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2518,6 +2518,8 @@ extern int filemap_fdatawait(struct address_space *);
 extern void filemap_fdatawait_keep_errors(struct address_space *);
 extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
 				   loff_t lend);
+extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
+				  loff_t lend);
 extern int filemap_write_and_wait(struct address_space *mapping);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
diff --git a/mm/filemap.c b/mm/filemap.c
index 6f1be573a5e6..9b39a2390b9e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -376,6 +376,38 @@ int filemap_flush(struct address_space *mapping)
 }
 EXPORT_SYMBOL(filemap_flush);
 
+/**
+ * filemap_range_has_page - check if a page exists in range.
+ * @mapping:           address space within which to check
+ * @start_byte:        offset in bytes where the range starts
+ * @end_byte:          offset in bytes where the range ends (inclusive)
+ *
+ * Find at least one page in the range supplied, usually used to check if
+ * direct writing in this range will trigger a writeback.
+ */
+bool filemap_range_has_page(struct address_space *mapping,
+			   loff_t start_byte, loff_t end_byte)
+{
+	pgoff_t index = start_byte >> PAGE_SHIFT;
+	pgoff_t end = end_byte >> PAGE_SHIFT;
+	struct pagevec pvec;
+	bool ret;
+
+	if (end_byte < start_byte)
+		return false;
+
+	if (mapping->nrpages == 0)
+		return false;
+
+	pagevec_init(&pvec, 0);
+	if (!pagevec_lookup(&pvec, mapping, index, 1))
+		return false;
+	ret = (pvec.pages[0]->index <= end);
+	pagevec_release(&pvec);
+	return ret;
+}
+EXPORT_SYMBOL(filemap_range_has_page);
+
 static int __filemap_fdatawait_range(struct address_space *mapping,
 				     loff_t start_byte, loff_t end_byte)
 {
-- 
2.12.0

[PATCH 03/10] fs: Use RWF_* flags for AIO operations

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

aio_rw_flags is introduced in struct iocb (using aio_reserved1) which will
carry the RWF_* flags. We cannot use aio_flags because they are not
checked for validity which may break existing applications.

Note, the only place RWF_HIPRI comes in effect is dio_await_one().
All the rest of the locations, aio code return -EIOCBQUEUED before the
checks for RWF_HIPRI.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/aio.c                     | 8 +++++++-
 include/uapi/linux/aio_abi.h | 2 +-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index f52d925ee259..020fa0045e3c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1541,7 +1541,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	ssize_t ret;
 
 	/* enforce forwards compatibility on users */
-	if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2)) {
+	if (unlikely(iocb->aio_reserved2)) {
 		pr_debug("EINVAL: reserve field set\n");
 		return -EINVAL;
 	}
@@ -1586,6 +1586,12 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		req->common.ki_flags |= IOCB_EVENTFD;
 	}
 
+	ret = kiocb_set_rw_flags(&req->common, iocb->aio_rw_flags);
+	if (unlikely(ret)) {
+		pr_debug("EINVAL: aio_rw_flags\n");
+		goto out_put_req;
+	}
+
 	ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
 	if (unlikely(ret)) {
 		pr_debug("EFAULT: aio_key\n");
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index bb2554f7fbd1..a2d4a8ac94ca 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -79,7 +79,7 @@ struct io_event {
 struct iocb {
 	/* these are internal to the kernel/libc. */
 	__u64	aio_data;	/* data to be returned in event's data */
-	__u32	PADDED(aio_key, aio_reserved1);
+	__u32	PADDED(aio_key, aio_rw_flags);
 				/* the kernel sets aio_key to the req # */
 
 	/* common fields */
-- 
2.12.0

[PATCH 04/10] fs: Introduce RWF_NOWAIT and FMODE_AIO_NOWAIT

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

RWF_NOWAIT informs kernel to bail out if an AIO request will block
for reasons such as file allocations, or a writeback triggered,
or would block while allocating requests while performing
direct I/O.

RWF_NOWAIT is translated to IOCB_NOWAIT for iocb->ki_flags.

FMODE_AIO_NOWAIT is a flag which identifies the file opened is capable
of returning -EAGAIN if the AIO call will block. This must be set by
supporting filesystems in the ->open() call.

Filesystems xfs, btrfs and ext4 would be supported in the following patches.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/aio.c                | 6 ++++++
 include/linux/fs.h      | 9 +++++++++
 include/uapi/linux/fs.h | 4 +++-
 3 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/fs/aio.c b/fs/aio.c
index 020fa0045e3c..34027b67e2f4 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1592,6 +1592,12 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		goto out_put_req;
 	}
 
+	if ((req->common.ki_flags & IOCB_NOWAIT) &&
+			!(req->common.ki_flags & IOCB_DIRECT)) {
+		ret = -EOPNOTSUPP;
+		goto out_put_req;
+	}
+
 	ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
 	if (unlikely(ret)) {
 		pr_debug("EFAULT: aio_key\n");
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0d34f5b5a6b0..4574121f4746 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -143,6 +143,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
+/* File is capable of returning -EAGAIN if AIO will block */
+#define FMODE_AIO_NOWAIT	((__force fmode_t)0x8000000)
+
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
  * that indicates that they should check the contents of the iovec are
@@ -269,6 +272,7 @@ struct writeback_control;
 #define IOCB_DSYNC		(1 << 4)
 #define IOCB_SYNC		(1 << 5)
 #define IOCB_WRITE		(1 << 6)
+#define IOCB_NOWAIT		(1 << 7)
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -3064,6 +3068,11 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags)
 	if (unlikely(flags & ~RWF_SUPPORTED))
 		return -EOPNOTSUPP;
 
+	if (flags & RWF_NOWAIT) {
+		if (!(ki->ki_filp->f_mode & FMODE_AIO_NOWAIT))
+			return -EOPNOTSUPP;
+		ki->ki_flags |= IOCB_NOWAIT;
+	}
 	if (flags & RWF_HIPRI)
 		ki->ki_flags |= IOCB_HIPRI;
 	if (flags & RWF_DSYNC)
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 937c3e39650a..27d8c36c04af 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -360,7 +360,9 @@ struct fscrypt_key {
 #define RWF_HIPRI			0x00000001 /* high priority request, poll if possible */
 #define RWF_DSYNC			0x00000002 /* per-IO O_DSYNC */
 #define RWF_SYNC			0x00000004 /* per-IO O_SYNC */
+#define RWF_NOWAIT			0x00000008 /* per-IO, return -EAGAIN if operation would block */
 
-#define RWF_SUPPORTED			(RWF_HIPRI | RWF_DSYNC | RWF_SYNC)
+#define RWF_SUPPORTED			(RWF_HIPRI | RWF_DSYNC | RWF_SYNC |\
+					 RWF_NOWAIT)
 
 #endif /* _UAPI_LINUX_FS_H */
-- 
2.12.0

[PATCH 05/10] fs: return if direct I/O will trigger writeback

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Find out if the I/O will trigger a wait due to writeback. If yes,
return -EAGAIN.

Return -EINVAL for buffered AIO: there are multiple causes of
delay such as page locks, dirty throttling logic, page loading
from disk etc. which cannot be taken care of.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 mm/filemap.c | 32 +++++++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 9b39a2390b9e..742034e56100 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2070,10 +2070,17 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 		loff_t size;
 
 		size = i_size_read(inode);
-		retval = filemap_write_and_wait_range(mapping, iocb->ki_pos,
-					iocb->ki_pos + count - 1);
-		if (retval < 0)
-			goto out;
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			if (filemap_range_has_page(mapping, iocb->ki_pos,
+						   iocb->ki_pos + count - 1))
+				return -EAGAIN;
+		} else {
+			retval = filemap_write_and_wait_range(mapping,
+						iocb->ki_pos,
+					        iocb->ki_pos + count - 1);
+			if (retval < 0)
+				goto out;
+		}
 
 		file_accessed(file);
 
@@ -2674,6 +2681,9 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 
 	pos = iocb->ki_pos;
 
+	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+		return -EINVAL;
+
 	if (limit != RLIM_INFINITY) {
 		if (iocb->ki_pos >= limit) {
 			send_sig(SIGXFSZ, current, 0);
@@ -2742,9 +2752,17 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	write_len = iov_iter_count(from);
 	end = (pos + write_len - 1) >> PAGE_SHIFT;
 
-	written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1);
-	if (written)
-		goto out;
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		/* If there are pages to writeback, return */
+		if (filemap_range_has_page(inode->i_mapping, pos,
+					   pos + iov_iter_count(from)))
+			return -EAGAIN;
+	} else {
+		written = filemap_write_and_wait_range(mapping, pos,
+							pos + write_len - 1);
+		if (written)
+			goto out;
+	}
 
 	/*
 	 * After a write we want buffered reads to be sure to go to disk to get
-- 
2.12.0

[PATCH 06/10] fs: Introduce IOMAP_NOWAIT

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

IOCB_NOWAIT translates to IOMAP_NOWAIT for iomaps.
This is used by XFS in the XFS patch.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/iomap.c            | 8 ++++++++
 include/linux/iomap.h | 1 +
 2 files changed, 9 insertions(+)

diff --git a/fs/iomap.c b/fs/iomap.c
index 18f2f2b8ba2c..c71a64b97fba 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -881,6 +881,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		flags |= IOMAP_WRITE;
 	}
 
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (filemap_range_has_page(mapping, start, end)) {
+			ret = -EAGAIN;
+			goto out_free_dio;
+		}
+		flags |= IOMAP_NOWAIT;
+	}
+
 	ret = filemap_write_and_wait_range(mapping, start, end);
 	if (ret)
 		goto out_free_dio;
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index f753e788da31..69f4e9470084 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -52,6 +52,7 @@ struct iomap {
 #define IOMAP_REPORT		(1 << 2) /* report extent status, e.g. FIEMAP */
 #define IOMAP_FAULT		(1 << 3) /* mapping for page fault */
 #define IOMAP_DIRECT		(1 << 4) /* direct I/O */
+#define IOMAP_NOWAIT		(1 << 5) /* Don't wait for writeback */
 
 struct iomap_ops {
 	/*
-- 
2.12.0

[PATCH 07/10] block: return on congested block device

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

A new bio operation flag REQ_NOWAIT is introduced to identify bio's
orignating from iocb with IOCB_NOWAIT. This flag indicates
to return immediately if a request cannot be made instead
of retrying.

Stacked devices such as md (the ones with make_request_fn hooks)
currently are not supported because it may block for housekeeping.
For example, an md can have a part of the device suspended.
For this reason, only request based devices are supported.
In the future, this feature will be expanded to stacked devices
by teaching them how to handle the REQ_NOWAIT flags.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 block/blk-core.c          | 22 ++++++++++++++++++++--
 block/blk-mq.c            |  4 ++++
 fs/direct-io.c            | 10 ++++++++--
 include/linux/bio.h       |  6 ++++++
 include/linux/blk_types.h |  4 ++++
 5 files changed, 42 insertions(+), 4 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 62cf92550512..279e3c432d7b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -143,6 +143,7 @@ static const struct {
 	[BLK_STS_MEDIUM]	= { -ENODATA,	"critical medium" },
 	[BLK_STS_PROTECTION]	= { -EILSEQ,	"protection" },
 	[BLK_STS_RESOURCE]	= { -ENOMEM,	"kernel resource" },
+	[BLK_STS_AGAIN]		= { -EAGAIN,	"nonblocking retry" },
 
 	/* device mapper special case, should not leak out: */
 	[BLK_STS_DM_REQUEUE]	= { -EREMCHG, "dm internal retry" },
@@ -1314,6 +1315,11 @@ static struct request *get_request(struct request_queue *q, unsigned int op,
 	if (!IS_ERR(rq))
 		return rq;
 
+	if (op & REQ_NOWAIT) {
+		blk_put_rl(rl);
+		return ERR_PTR(-EAGAIN);
+	}
+
 	if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) {
 		blk_put_rl(rl);
 		return rq;
@@ -1961,6 +1967,14 @@ generic_make_request_checks(struct bio *bio)
 		goto end_io;
 	}
 
+	/*
+	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
+	 * if queue is not a request based queue.
+	 */
+
+	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q))
+		goto not_supported;
+
 	part = bio->bi_bdev->bd_part;
 	if (should_fail_request(part, bio->bi_iter.bi_size) ||
 	    should_fail_request(&part_to_disk(part)->part0,
@@ -2118,7 +2132,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
-		if (likely(blk_queue_enter(q, false) == 0)) {
+		if (likely(blk_queue_enter(q, bio->bi_opf & REQ_NOWAIT) == 0)) {
 			struct bio_list lower, same;
 
 			/* Create a fresh bio_list for all subordinate requests */
@@ -2143,7 +2157,11 @@ blk_qc_t generic_make_request(struct bio *bio)
 			bio_list_merge(&bio_list_on_stack[0], &same);
 			bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
 		} else {
-			bio_io_error(bio);
+			if (unlikely(!blk_queue_dying(q) &&
+					(bio->bi_opf & REQ_NOWAIT)))
+				bio_wouldblock_error(bio);
+			else
+				bio_io_error(bio);
 		}
 		bio = bio_list_pop(&bio_list_on_stack[0]);
 	} while (bio);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index dd276a9e138e..ca03cd4b263f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -293,6 +293,8 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 		data->ctx = blk_mq_get_ctx(q);
 	if (likely(!data->hctx))
 		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
+	if (op & REQ_NOWAIT)
+		data->flags |= BLK_MQ_REQ_NOWAIT;
 
 	if (e) {
 		data->flags |= BLK_MQ_REQ_INTERNAL;
@@ -1544,6 +1546,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
 		__wbt_done(q->rq_wb, wb_acct);
+		if (bio->bi_opf & REQ_NOWAIT)
+			bio_wouldblock_error(bio);
 		return BLK_QC_T_NONE;
 	}
 
diff --git a/fs/direct-io.c b/fs/direct-io.c
index e8baaabebf13..c87077d1dc33 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -479,8 +479,12 @@ static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio)
 	unsigned i;
 	blk_status_t err = bio->bi_status;
 
-	if (err)
-		dio->io_error = -EIO;
+	if (err) {
+		if (err == BLK_STS_AGAIN && (bio->bi_opf & REQ_NOWAIT))
+			dio->io_error = -EAGAIN;
+		else
+			dio->io_error = -EIO;
+	}
 
 	if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) {
 		bio_check_pages_dirty(bio);	/* transfers ownership */
@@ -1194,6 +1198,8 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	if (iov_iter_rw(iter) == WRITE) {
 		dio->op = REQ_OP_WRITE;
 		dio->op_flags = REQ_SYNC | REQ_IDLE;
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			dio->op_flags |= REQ_NOWAIT;
 	} else {
 		dio->op = REQ_OP_READ;
 	}
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 40d054185277..36aa641cde28 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -416,6 +416,12 @@ static inline void bio_io_error(struct bio *bio)
 	bio_endio(bio);
 }
 
+static inline void bio_wouldblock_error(struct bio *bio)
+{
+	bio->bi_status = BLK_STS_AGAIN;
+	bio_endio(bio);
+}
+
 struct request_queue;
 extern int bio_phys_segments(struct request_queue *, struct bio *);
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index dcd45b15a3a5..e210da6d14b8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -36,6 +36,8 @@ typedef u8 __bitwise blk_status_t;
 /* hack for device mapper, don't use elsewhere: */
 #define BLK_STS_DM_REQUEUE    ((__force blk_status_t)11)
 
+#define BLK_STS_AGAIN		((__force blk_status_t)12)
+
 struct blk_issue_stat {
 	u64 stat;
 };
@@ -224,6 +226,7 @@ enum req_flag_bits {
 	/* command specific flags for REQ_OP_WRITE_ZEROES: */
 	__REQ_NOUNMAP,		/* do not free blocks when zeroing */
 
+	__REQ_NOWAIT,           /* Don't wait if request will block */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -242,6 +245,7 @@ enum req_flag_bits {
 #define REQ_BACKGROUND		(1ULL << __REQ_BACKGROUND)
 
 #define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
+#define REQ_NOWAIT		(1ULL << __REQ_NOWAIT)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
-- 
2.12.0

[PATCH 08/10] ext4: nowait aio support

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Return EAGAIN if any of the following checks fail for direct I/O:
  + i_rwsem is lockable
  + Writing beyond end of file (will trigger allocation)
  + Blocks are not allocated at the write location

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 fs/ext4/file.c | 35 +++++++++++++++++++++++++++++------
 1 file changed, 29 insertions(+), 6 deletions(-)

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 02ce7e7bbdf5..58e2eeaa0bc4 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -37,7 +37,11 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
-	inode_lock_shared(inode);
+	if (!inode_trylock_shared(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock_shared(inode);
+	}
 	/*
 	 * Recheck under inode lock - at this point we are sure it cannot
 	 * change anymore
@@ -179,7 +183,11 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
-	inode_lock(inode);
+	if (!inode_trylock(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock(inode);
+	}
 	ret = ext4_write_checks(iocb, from);
 	if (ret <= 0)
 		goto out;
@@ -216,7 +224,12 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		return ext4_dax_write_iter(iocb, from);
 #endif
 
-	inode_lock(inode);
+	if (!inode_trylock(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock(inode);
+	}
+
 	ret = ext4_write_checks(iocb, from);
 	if (ret <= 0)
 		goto out;
@@ -235,9 +248,15 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	iocb->private = &overwrite;
 	/* Check whether we do a DIO overwrite or not */
-	if (o_direct && ext4_should_dioread_nolock(inode) && !unaligned_aio &&
-	    ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from)))
-		overwrite = 1;
+	if (o_direct && !unaligned_aio) {
+		if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
+			if (ext4_should_dioread_nolock(inode))
+				overwrite = 1;
+		} else if (iocb->ki_flags & IOCB_NOWAIT) {
+			ret = -EAGAIN;
+			goto out;
+		}
+	}
 
 	ret = __generic_file_write_iter(iocb, from);
 	inode_unlock(inode);
@@ -435,6 +454,10 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		if (ret < 0)
 			return ret;
 	}
+
+	/* Set the flags to support nowait AIO */
+	filp->f_mode |= FMODE_AIO_NOWAIT;
+
 	return dquot_file_open(inode, filp);
 }
 
-- 
2.12.0

[PATCH 09/10] xfs: nowait aio support

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

If IOCB_NOWAIT is set, bail if the i_rwsem is not lockable
immediately.

IF IOMAP_NOWAIT is set, return EAGAIN in xfs_file_iomap_begin
if it needs allocation either due to file extension, writing to a hole,
or COW or waiting for other DIOs to finish.

Return -EAGAIN if we don't have extent list in memory.

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_file.c  | 32 ++++++++++++++++++++++++++------
 fs/xfs/xfs_iomap.c | 22 ++++++++++++++++++++++
 2 files changed, 48 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5fb5a0958a14..17f27a2fb5e2 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -237,7 +237,11 @@ xfs_file_dax_read(
 	if (!count)
 		return 0; /* skip atime */
 
-	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	}
 	ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops);
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
@@ -541,7 +545,11 @@ xfs_file_dio_aio_write(
 		iolock = XFS_IOLOCK_SHARED;
 	}
 
-	xfs_ilock(ip, iolock);
+	if (!xfs_ilock_nowait(ip, iolock)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		xfs_ilock(ip, iolock);
+	}
 
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
@@ -553,9 +561,15 @@ xfs_file_dio_aio_write(
 	 * otherwise demote the lock if we had to take the exclusive lock
 	 * for other reasons in xfs_file_aio_write_checks.
 	 */
-	if (unaligned_io)
-		inode_dio_wait(inode);
-	else if (iolock == XFS_IOLOCK_EXCL) {
+	if (unaligned_io) {
+		/* If we are going to wait for other DIO to finish, bail */
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			if (atomic_read(&inode->i_dio_count))
+				return -EAGAIN;
+		} else {
+			inode_dio_wait(inode);
+		}
+	} else if (iolock == XFS_IOLOCK_EXCL) {
 		xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
 		iolock = XFS_IOLOCK_SHARED;
 	}
@@ -585,7 +599,12 @@ xfs_file_dax_write(
 	size_t			count;
 	loff_t			pos;
 
-	xfs_ilock(ip, iolock);
+	if (!xfs_ilock_nowait(ip, iolock)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		xfs_ilock(ip, iolock);
+	}
+
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
 		goto out;
@@ -892,6 +911,7 @@ xfs_file_open(
 		return -EFBIG;
 	if (XFS_FORCED_SHUTDOWN(XFS_M(inode->i_sb)))
 		return -EIO;
+	file->f_mode |= FMODE_AIO_NOWAIT;
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 94e5bdf7304c..05dc87e8c1f5 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -995,6 +995,11 @@ xfs_file_iomap_begin(
 		lockmode = xfs_ilock_data_map_shared(ip);
 	}
 
+	if ((flags & IOMAP_NOWAIT) && !(ip->i_df.if_flags & XFS_IFEXTENTS)) {
+		error = -EAGAIN;
+		goto out_unlock;
+	}
+
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 	if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
 		length = mp->m_super->s_maxbytes - offset;
@@ -1016,6 +1021,15 @@ xfs_file_iomap_begin(
 
 	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
 		if (flags & IOMAP_DIRECT) {
+			/*
+			 * A reflinked inode will result in CoW alloc.
+			 * FIXME: It could still overwrite on unshared extents
+			 * and not need allocation.
+			 */
+			if (flags & IOMAP_NOWAIT) {
+				error = -EAGAIN;
+				goto out_unlock;
+			}
 			/* may drop and re-acquire the ilock */
 			error = xfs_reflink_allocate_cow(ip, &imap, &shared,
 					&lockmode);
@@ -1033,6 +1047,14 @@ xfs_file_iomap_begin(
 
 	if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
 		/*
+		 * If nowait is set bail since we are going to make
+		 * allocations.
+		 */
+		if (flags & IOMAP_NOWAIT) {
+			error = -EAGAIN;
+			goto out_unlock;
+		}
+		/*
 		 * We cap the maximum length we map here to MAX_WRITEBACK_PAGES
 		 * pages to keep the chunks of work done where somewhat symmetric
 		 * with the work writeback does. This is a completely arbitrary
-- 
2.12.0

[PATCH 10/10] btrfs: nowait aio support

[Goldwyn Rodrigues]

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Return EAGAIN if any of the following checks fail
 + i_rwsem is not lockable
 + NODATACOW or PREALLOC is not set
 + Cannot nocow at the desired location
 + Writing beyond end of file which is not allocated

Acked-by: David Sterba <dsterba@suse.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/btrfs/file.c  | 33 +++++++++++++++++++++++++++------
 fs/btrfs/inode.c |  3 +++
 2 files changed, 30 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index da1096eb1a40..59e2dccdf75b 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1875,12 +1875,29 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	ssize_t num_written = 0;
 	bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host);
 	ssize_t err;
-	loff_t pos;
-	size_t count;
+	loff_t pos = iocb->ki_pos;
+	size_t count = iov_iter_count(from);
 	loff_t oldsize;
 	int clean_page = 0;
 
-	inode_lock(inode);
+	if ((iocb->ki_flags & IOCB_NOWAIT) &&
+			(iocb->ki_flags & IOCB_DIRECT)) {
+		/* Don't sleep on inode rwsem */
+		if (!inode_trylock(inode))
+			return -EAGAIN;
+		/*
+		 * We will allocate space in case nodatacow is not set,
+		 * so bail
+		 */
+		if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+					      BTRFS_INODE_PREALLOC)) ||
+		    check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) {
+			inode_unlock(inode);
+			return -EAGAIN;
+		}
+	} else
+		inode_lock(inode);
+
 	err = generic_write_checks(iocb, from);
 	if (err <= 0) {
 		inode_unlock(inode);
@@ -1914,8 +1931,6 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	 */
 	update_time_for_write(inode);
 
-	pos = iocb->ki_pos;
-	count = iov_iter_count(from);
 	start_pos = round_down(pos, fs_info->sectorsize);
 	oldsize = i_size_read(inode);
 	if (start_pos > oldsize) {
@@ -3071,13 +3086,19 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
 	return offset;
 }
 
+static int btrfs_file_open(struct inode *inode, struct file *filp)
+{
+	filp->f_mode |= FMODE_AIO_NOWAIT;
+	return generic_file_open(inode, filp);
+}
+
 const struct file_operations btrfs_file_operations = {
 	.llseek		= btrfs_file_llseek,
 	.read_iter      = generic_file_read_iter,
 	.splice_read	= generic_file_splice_read,
 	.write_iter	= btrfs_file_write_iter,
 	.mmap		= btrfs_file_mmap,
-	.open		= generic_file_open,
+	.open		= btrfs_file_open,
 	.release	= btrfs_release_file,
 	.fsync		= btrfs_sync_file,
 	.fallocate	= btrfs_fallocate,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f942293dd7e7..556c93060606 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8754,6 +8754,9 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 			dio_data.overwrite = 1;
 			inode_unlock(inode);
 			relock = true;
+		} else if (iocb->ki_flags & IOCB_NOWAIT) {
+			ret = -EAGAIN;
+			goto out;
 		}
 		ret = btrfs_delalloc_reserve_space(inode, offset, count);
 		if (ret)
-- 
2.12.0

Re: [PATCH 0/10 v14] merge request: No wait AIO

[Jens Axboe]

On 06/20/2017 06:05 AM, Goldwyn Rodrigues wrote:
> Jens,
> 
> As discussed, here are the patches against the block
> tree for merge since the block layer changes had the most conflicts.
> My tree is at https://github.com/goldwynr/linux/tree/nowait-block
> 
>  Changes since v13:
>  + nowait support for dax files in ext4 and xfs

Added for 4.13, thanks.

-- 
Jens Axboe