diff options
| author | Liu Bo <bo.li.liu@oracle.com> | 2016-05-17 17:21:48 -0700 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2016-06-07 18:18:55 -0700 |
| commit | 327b1cf89e87607cf1d999a27481245b2610149c (patch) | |
| tree | fab881b7e3da50e7c3b5a2f9b50c9839922f1365 | |
| parent | ac5414fc59a48c5a9fb7b1f0e98251dbd4f2f0f4 (diff) | |
| download | linux-stable-327b1cf89e87607cf1d999a27481245b2610149c.tar.gz linux-stable-327b1cf89e87607cf1d999a27481245b2610149c.tar.bz2 linux-stable-327b1cf89e87607cf1d999a27481245b2610149c.zip | |
Btrfs: fix unexpected return value of fiemap
commit 2d324f59f343967a03eeb2690f0ff178304d0687 upstream.
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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
| -rw-r--r-- | fs/btrfs/extent_io.c | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 392592dc7010..57fccc420697 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4385,8 +4385,12 @@ 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; |