btrfs: abort in rename_exchange if we fail to insert the second ref

Error injection stress uncovered a problem where we'd leave a dangling
inode ref if we failed during a rename_exchange.  This happens because
we insert the inode ref for one side of the rename, and then for the
other side.  If this second inode ref insert fails we'll leave the first
one dangling and leave a corrupt file system behind.  Fix this by
aborting if we did the insert for the first inode ref.

CC: stable@vger.kernel.org # 4.9+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 14af9458e01ad6d4d54965bb3ce68ba3e9c94a83..c70ae0a5df92b419c624a156b65c99ecf48aa2f1 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9094,6 +9094,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
        int ret2;
        bool root_log_pinned = false;
        bool dest_log_pinned = false;
+       bool need_abort = false;
 
        /* we only allow rename subvolume link between subvolumes */
        if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
@@ -9153,6 +9154,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
                                             old_idx);
                if (ret)
                        goto out_fail;
+               need_abort = true;
        }
 
        /* And now for the dest. */
@@ -9168,8 +9170,11 @@ static int btrfs_rename_exchange(struct inode *old_dir,
                                             new_ino,
                                             btrfs_ino(BTRFS_I(old_dir)),
                                             new_idx);
-               if (ret)
+               if (ret) {
+                       if (need_abort)
+                               btrfs_abort_transaction(trans, ret);
                        goto out_fail;
+               }
        }
 
        /* Update inode version and ctime/mtime. */