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>
This commit is contained in:
@@ -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(
|
||||
|
Reference in New Issue
Block a user