diff options
| author | Qu Wenruo <wqu@suse.com> | 2018-06-06 15:41:49 +0800 |
|---|---|---|
| committer | David Sterba <dsterba@suse.com> | 2018-08-06 13:12:38 +0200 |
| commit | e41ca5897489b1c18af75ff0cc8f5c80260b3281 (patch) | |
| tree | dc20051c4be3bb6f4b47bb1823364ae345d75809 /include/trace | |
| parent | bc877d285ca3dba24c52406946a4a69847cc7422 (diff) | |
| download | linux-e41ca5897489b1c18af75ff0cc8f5c80260b3281.tar.bz2 | |
btrfs: Get rid of the confusing btrfs_file_extent_inline_len
We used to call btrfs_file_extent_inline_len() to get the uncompressed
data size of an inlined extent.
However this function is hiding evil, for compressed extent, it has no
choice but to directly read out ram_bytes from btrfs_file_extent_item.
While for uncompressed extent, it uses item size to calculate the real
data size, and ignoring ram_bytes completely.
In fact, for corrupted ram_bytes, due to above behavior kernel
btrfs_print_leaf() can't even print correct ram_bytes to expose the bug.
Since we have the tree-checker to verify all EXTENT_DATA, such mismatch
can be detected pretty easily, thus we can trust ram_bytes without the
evil btrfs_file_extent_inline_len().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'include/trace')
| -rw-r--r-- | include/trace/events/btrfs.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 7057cc99d267..b401c4e36394 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -374,7 +374,7 @@ DECLARE_EVENT_CLASS( __entry->extent_type = btrfs_file_extent_type(l, fi); __entry->compression = btrfs_file_extent_compression(l, fi); __entry->extent_start = start; - __entry->extent_end = (start + btrfs_file_extent_inline_len(l, slot, fi)); + __entry->extent_end = (start + btrfs_file_extent_ram_bytes(l, fi)); ), TP_printk_btrfs( |