Merge branch 'xfs-dax-updates' into for-next

1 files changed, 20 insertions, 1 deletions

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index c3cb5a552c4e..f4f5b43cf647 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -132,6 +132,7 @@ xfs_iomap_write_direct(
 	int		committed;
 	int		error;
 	int		lockmode;
+	int		bmapi_flags = XFS_BMAPI_PREALLOC;
 
 	rt = XFS_IS_REALTIME_INODE(ip);
 	extsz = xfs_get_extsz_hint(ip);
@@ -195,6 +196,23 @@ xfs_iomap_write_direct(
 	 * Allocate and setup the transaction
 	 */
 	tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
+
+	/*
+	 * For DAX, we do not allocate unwritten extents, but instead we zero
+	 * the block before we commit the transaction.  Ideally we'd like to do
+	 * this outside the transaction context, but if we commit and then crash
+	 * we may not have zeroed the blocks and this will be exposed on
+	 * recovery of the allocation. Hence we must zero before commit.
+	 * Further, if we are mapping unwritten extents here, we need to zero
+	 * and convert them to written so that we don't need an unwritten extent
+	 * callback for DAX. This also means that we need to be able to dip into
+	 * the reserve block pool if there is no space left but we need to do
+	 * unwritten extent conversion.
+	 */
+	if (IS_DAX(VFS_I(ip))) {
+		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
+		tp->t_flags |= XFS_TRANS_RESERVE;
+	}
 	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
 				  resblks, resrtextents);
 	/*
@@ -221,7 +239,7 @@ xfs_iomap_write_direct(
 	xfs_bmap_init(&free_list, &firstfsb);
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-				XFS_BMAPI_PREALLOC, &firstfsb, resblks, imap,
+				bmapi_flags, &firstfsb, resblks, imap,
 				&nimaps, &free_list);
 	if (error)
 		goto out_bmap_cancel;
@@ -232,6 +250,7 @@ xfs_iomap_write_direct(
 	error = xfs_bmap_finish(&tp, &free_list, &committed);
 	if (error)
 		goto out_bmap_cancel;
+
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_unlock;