f2fs: fix to avoid dirent corruption
Linux
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
Linux
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
≥ 7e01e7ad746bc8198a8b46163ddc73a1c7d22339 · < d3c0b49aaa12a61d560528f5d605029ab57f0728| No fix yet |
| Linux Linux |
|
|
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]
From the CVE record · Linux
The Linux kernel’s f2fs filesystem can fail to update a directory’s “..” entry during a cross-directory rename that leaves a whiteout. A local user who can perform that rename can cause directory entry corruption; the input does not specify authentication requirements beyond the ability to perform the operation.
Teams running Linux kernels that use f2fs should check whether their kernel includes the fix; affected versions are not specified.