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:
Qu Wenruo
2018-06-06 15:41:49 +08:00
committed by David Sterba
parent bc877d285c
commit e41ca58974
8 changed files with 22 additions and 56 deletions

View File

@@ -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(