Btrfs: fix unexpected return value of fiemap

btrfs's fiemap is supposed to return 0 on success and return < 0 on
error. however, ret becomes 1 after looking up the last file extent:

  btrfs_lookup_file_extent ->
    btrfs_search_slot(..., ins_len=0, cow=0)

and if the offset is beyond EOF, we'll get 'path' pointed to the place
of potentail insertion, and ret == 1.

This may confuse applications using ioctl(FIEL_IOC_FIEMAP).

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2f83448..f661688 100644 (file)
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4389,8 +4389,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
        if (ret < 0) {
                btrfs_free_path(path);
                return ret;
+       } else {
+               WARN_ON(!ret);
+               if (ret == 1)
+                       ret = 0;
        }
-       WARN_ON(!ret);
+
        path->slots[0]--;
        btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
        found_type = found_key.type;