[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20231128092516.2882629-1-chao@kernel.org>
Date: Tue, 28 Nov 2023 17:25:16 +0800
From: Chao Yu <chao@...nel.org>
To: jaegeuk@...nel.org
Cc: linux-f2fs-devel@...ts.sourceforge.net,
linux-kernel@...r.kernel.org, Chao Yu <chao@...nel.org>,
Jan Kara <jack@...e.cz>, Al Viro <viro@...iv.linux.org.uk>
Subject: [PATCH] f2fs: fix to avoid dirent corruption
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 <jack@...e.cz>
Reported-by: Al Viro <viro@...iv.linux.org.uk>
Signed-off-by: Chao Yu <chao@...nel.org>
---
fs/f2fs/namei.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 3b1793cfb002..ede6afb81762 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -1105,7 +1105,7 @@ 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
--
2.40.1
Powered by blists - more mailing lists