CVE-2023-52444

In the Linux kernel, the following vulnerability has been resolved:

f2fs: fix to avoid dirent corruption

As Al reported in link[1]:

f2fsrename() ... if (olddir != newdir && !whiteout) f2fssetlink(oldinode, olddirentry, olddirpage, newdir); else f2fsputpage(olddir_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 f2fssetlink() to update ".." link to new directory. - mkdir -p dir/foo - renameat2 -w dir/foo bar

[ASSERT] (__chkdotsdentries:1421) --> Bad inode number[0x4] for '..', parent parent ino is [0x3] [FSCK] other corrupted bugs [Fail]