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>
This commit is contained in:
Liu Bo 2016-05-17 17:21:48 -07:00 committed by David Sterba
parent 1c8b5b6e8b
commit 2d324f59f3
1 changed files with 5 additions and 1 deletions

View File

@ -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;