[PATCH 11/12] xfs: don't set IOMAP_DIO_SYNCHRONOUS for unaligned I/O

From: Christoph Hellwig
Date: Tue Jan 14 2020 - 11:13:01 EST


Now that i_rwsem is held until asynchronous writes complete, there
is no need to force them to execute synchronously, as the i_rwsem
protection is exactly the same as for synchronous writes.

Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
fs/xfs/xfs_file.c | 12 +++---------
1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index d0ee7d2932e4..3a734ad4bb10 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -510,9 +510,6 @@ xfs_file_dio_aio_write(
}

if (iocb->ki_flags & IOCB_NOWAIT) {
- /* unaligned dio always waits, bail */
- if (unaligned_io)
- return -EAGAIN;
if (!xfs_ilock_nowait(ip, iolock))
return -EAGAIN;
} else {
@@ -526,14 +523,11 @@ xfs_file_dio_aio_write(

/*
* If we are doing unaligned I/O, we can't allow any other overlapping
- * I/O in-flight at the same time or we risk data corruption. Wait for
- * all other I/O to drain before we submit and execute the I/O
- * synchronously to prevent subsequent overlapping I/O. If the I/O is
- * aligned, demote the iolock if we had to take the exclusive lock in
- * xfs_file_aio_write_checks() for other reasons.
+ * If the I/O is aligned, demote the iolock if we had to take the
+ * exclusive lock in xfs_file_aio_write_checks() for other reasons.
*/
if (unaligned_io) {
- dio_flags = IOMAP_DIO_RWSEM_EXCL | IOMAP_DIO_SYNCHRONOUS;
+ dio_flags = IOMAP_DIO_RWSEM_EXCL;
} else {
if (iolock == XFS_IOLOCK_EXCL) {
xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
--
2.24.1