diff options
| author | Chao Yu <[email protected]> | 2023-11-28 17:25:16 +0800 |
|---|---|---|
| committer | Greg Kroah-Hartman <[email protected]> | 2024-01-25 15:35:32 -0800 |
| commit | d3c0b49aaa12a61d560528f5d605029ab57f0728 (patch) | |
| tree | bee62183f6521a31695f8e1b1e19fef1c48a25e9 | |
| parent | c111350d673a517c3995849c724e444205f7e51c (diff) | |
| download | linux-d3c0b49aaa12a61d560528f5d605029ab57f0728.tar.gz | |
f2fs: fix to avoid dirent corruption
[ Upstream commit 53edb549565f55ccd0bdf43be3d66ce4c2d48b28 ]
As Al reported in link[1]:
f2fs_rename()
...
if (old_dir != new_dir && !whiteout)
f2fs_set_link(old_inode, old_dir_entry,
old_dir_page, new_dir);
else
f2fs_put_page(old_dir_page, 0);
You want correct inumber in the ".." link. And cross-directory
rename does move the source to new parent, even if you'd been asked
to leave a whiteout in the old place.
[1] https://lore.kernel.org/all/20231017055040.GN800259@ZenIV/
With below testcase, it may cause dirent corruption, due to it missed
to call f2fs_set_link() to update ".." link to new directory.
- mkdir -p dir/foo
- renameat2 -w dir/foo bar
[ASSERT] (__chk_dots_dentries:1421) --> Bad inode number[0x4] for '..', parent parent ino is [0x3]
[FSCK] other corrupted bugs [Fail]
Fixes: 7e01e7ad746b ("f2fs: support RENAME_WHITEOUT")
Cc: Jan Kara <[email protected]>
Reported-by: Al Viro <[email protected]>
Signed-off-by: Chao Yu <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Signed-off-by: Jaegeuk Kim <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
| -rw-r--r-- | fs/f2fs/namei.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 193b22a2d6bfb2..02d9c47797be68 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -1106,7 +1106,7 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, } if (old_dir_entry) { - if (old_dir != new_dir && !whiteout) + if (old_dir != new_dir) f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir); else |