1 files changed, 28 insertions, 8 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e28f3d4691af..5f06eb1f4384 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7116,21 +7116,41 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 	if (ret)
 		return ERR_PTR(ret);
 
-	em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
-			      ins.offset, ins.offset, ins.offset, 0);
-	if (IS_ERR(em)) {
-		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
-		return em;
-	}
-
+	/*
+	 * Create the ordered extent before the extent map. This is to avoid
+	 * races with the fast fsync path that would lead to it logging file
+	 * extent items that point to disk extents that were not yet written to.
+	 * The fast fsync path collects ordered extents into a local list and
+	 * then collects all the new extent maps, so we must create the ordered
+	 * extent first and make sure the fast fsync path collects any new
+	 * ordered extents after collecting new extent maps as well.
+	 * The fsync path simply can not rely on inode_dio_wait() because it
+	 * causes deadlock with AIO.
+	 */
 	ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
 					   ins.offset, ins.offset, 0);
 	if (ret) {
 		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
-		free_extent_map(em);
 		return ERR_PTR(ret);
 	}
 
+	em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
+			      ins.offset, ins.offset, ins.offset, 0);
+	if (IS_ERR(em)) {
+		struct btrfs_ordered_extent *oe;
+
+		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
+		oe = btrfs_lookup_ordered_extent(inode, start);
+		ASSERT(oe);
+		if (WARN_ON(!oe))
+			return em;
+		set_bit(BTRFS_ORDERED_IOERR, &oe->flags);
+		set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags);
+		btrfs_remove_ordered_extent(inode, oe);
+		/* Once for our lookup and once for the ordered extents tree. */
+		btrfs_put_ordered_extent(oe);
+		btrfs_put_ordered_extent(oe);
+	}
 	return em;
 }