From 53edb549565f55ccd0bdf43be3d66ce4c2d48b28 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 28 Nov 2023 17:25:16 +0800 Subject: 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 Reported-by: Al Viro Signed-off-by: Chao Yu Reviewed-by: Jan Kara Signed-off-by: Jaegeuk Kim --- fs/f2fs/namei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/f2fs') diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index a9360ee02da1..a765db9e26c2 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 -- cgit