On 2021-07-15 at 15:36 Greg KH (<greg@xxxxxxxxx>) wrote:
>
> On Sat, Jul 10, 2021 at 09:37:10PM +0300, Davis Mosenkovs wrote:
> > Commit e3d4030498c3 ("mac80211: do not accept/forward invalid EAPOL
> > frames") uses skb_mac_header() before eth_type_trans() is called
> > leading to incorrect pointer, the pointer gets written to. This issue
> > has appeared during backporting to 4.4, 4.9 and 4.14.
>
> So this is also needed in 4.9 and 4.14, right? If so, now queued up
> everywhere. If not, please let me know so I can drop it from the other
> trees.
>
> thanks,
>
> greg k-h
Thank you! Yes - this is needed in 4.4, 4.9 and 4.14.
Only line offsets and commit messages (they contain references to
backport commits introducing the issue) differ between kernel versions
and I see the patches are queued with correct line offsets.
Patches for 4.9
(https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git/tree/queue-4.9/mac80211-fix-memory-corruption-in-eapol-handling.patch)
and 4.14 (https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git/tree/queue-4.14/mac80211-fix-memory-corruption-in-eapol-handling.patch)
still contain 4.4 in the cc line in sign-off section. Also these
patches contain reference to commit e3d4030498c3 that is from 4.4
branch. Is this OK?
Br,
Davis
