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]: 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]

• linux linux kernel (>= 4.2.0 < 4.19.306) • linux linux kernel (>= 4.20 < 5.4.268) • linux linux kernel (>= 5.5.0 < 5.10.209) • linux linux kernel (>= 5.11.0 < 5.15.148) • linux linux kernel (>= 5.16.0 < 6.1.75) • linux linux kernel (>= 6.2.0 < 6.6.14) • linux linux kernel (>= 6.7.0 < 6.7.2)