path: root/fs
diff options
authorBrian Foster <bfoster@redhat.com>2019-03-25 17:01:45 -0700
committerDarrick J. Wong <darrick.wong@oracle.com>2019-03-26 08:37:55 -0700
commit2032a8a27b5cc0f578d37fa16fa2494b80a0d00a (patch)
tree327a39070ba431d137729e35407779e287eb5e11 /fs
parented79dac98c5e9f8471456afe2cc09a3912586b52 (diff)
xfs: serialize unaligned dio writes against all other dio writes
XFS applies more strict serialization constraints to unaligned direct writes to accommodate things like direct I/O layer zeroing, unwritten extent conversion, etc. Unaligned submissions acquire the exclusive iolock and wait for in-flight dio to complete to ensure multiple submissions do not race on the same block and cause data corruption. This generally works in the case of an aligned dio followed by an unaligned dio, but the serialization is lost if I/Os occur in the opposite order. If an unaligned write is submitted first and immediately followed by an overlapping, aligned write, the latter submits without the typical unaligned serialization barriers because there is no indication of an unaligned dio still in-flight. This can lead to unpredictable results. To provide proper unaligned dio serialization, require that such direct writes are always the only dio allowed in-flight at one time for a particular inode. We already acquire the exclusive iolock and drain pending dio before submitting the unaligned dio. Wait once more after the dio submission to hold the iolock across the I/O and prevent further submissions until the unaligned I/O completes. This is heavy handed, but consistent with the current pre-submission serialization for unaligned direct writes. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Allison Henderson <allison.henderson@oracle.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Diffstat (limited to 'fs')
1 files changed, 17 insertions, 10 deletions
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 1f2e2845eb76..a7ceae90110e 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -529,18 +529,17 @@ xfs_file_dio_aio_write(
count = iov_iter_count(from);
- * If we are doing unaligned IO, wait for all other IO to drain,
- * otherwise demote the lock if we had to take the exclusive lock
- * for other reasons in xfs_file_aio_write_checks.
+ * If we are doing unaligned IO, we can't allow any other overlapping IO
+ * in-flight at the same time or we risk data corruption. Wait for all
+ * other IO to drain before we submit. If the IO 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) {
- /* 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);
- }
+ /* unaligned dio always waits, bail */
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ return -EAGAIN;
+ inode_dio_wait(inode);
} else if (iolock == XFS_IOLOCK_EXCL) {
xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
@@ -548,6 +547,14 @@ xfs_file_dio_aio_write(
trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
+ /*
+ * If unaligned, this is the only IO in-flight. If it has not yet
+ * completed, wait on it before we release the iolock to prevent
+ * subsequent overlapping IO.
+ */
+ if (ret == -EIOCBQUEUED && unaligned_io)
+ inode_dio_wait(inode);
xfs_iunlock(ip, iolock);