Merge branch 'for-linus-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/mason...

[linux-2.6-block.git] / fs / btrfs / inode.c

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 1b79dc9b12e4fb78fcc4005511ab73be05a4294e..5f06eb1f43843055c0373daeb9ad98648865150f 100644 (file)
--- 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;
 }
 
@@ -8447,7 +8467,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
                 * not unlock the i_mutex at this case.
                 */
                if (offset + count <= inode->i_size) {
-                       mutex_unlock(&inode->i_mutex);
+                       inode_unlock(inode);
                        relock = true;
                }
                ret = btrfs_delalloc_reserve_space(inode, offset, count);
@@ -8504,7 +8524,7 @@ out:
        if (wakeup)
                inode_dio_end(inode);
        if (relock)
-               mutex_lock(&inode->i_mutex);
+               inode_lock(inode);
 
        return ret;
 }