Commit 2d324f59 authored May 17, 2016 by Liu Bo Committed by David Sterba May 25, 2016

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>

parent 1c8b5b6e

fs/btrfs/extent_io.c

+5 −1

Original line number	Original line	Diff line number	Diff line
	@@ -4389,8 +4389,12 @@ int extent_fiemap(struct inode inode, struct fiemap_extent_info fieinfo,
	if (ret < 0) {		if (ret < 0) {
	btrfs_free_path(path);		btrfs_free_path(path);
	return ret;		return ret;
	}		} else {
	WARN_ON(!ret);		WARN_ON(!ret);
			if (ret == 1)
			ret = 0;
			}

	path->slots[0]--;		path->slots[0]--;
	btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);		btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
	found_type = found_key.type;		found_type = found_key.type;