[09/10] xfs: nowait aio support

Commit Message

Goldwyn Rodrigues June 20, 2017, 12:05 p.m. UTC

From: Goldwyn Rodrigues <[e-mail]>

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 <[e-mail]>
Reviewed-by: Christoph Hellwig <[e-mail]>
Reviewed-by: Darrick J. Wong <[e-mail]>
---
 fs/xfs/xfs_file.c  | 32 ++++++++++++++++++++++++++------
 fs/xfs/xfs_iomap.c | 22 ++++++++++++++++++++++
 2 files changed, 48 insertions(+), 6 deletions(-)

Patch

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