Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.34 as permitted sender) client-ip=23.128.96.34;
From:   Chao Yu <chao@kernel.org>
To:     jaegeuk@kernel.org
Cc:     linux-f2fs-devel@lists.sourceforge.net,
        linux-kernel@vger.kernel.org, Chao Yu <chao@kernel.org>,
        Jan Kara <jack@suse.cz>, Al Viro <viro@zeniv.linux.org.uk>
Subject: [PATCH] f2fs: fix to avoid dirent corruption
Date:   Tue, 28 Nov 2023 17:25:16 +0800
Message-Id: <20231128092516.2882629-1-chao@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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@suse.cz>
Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Chao Yu <chao@kernel.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