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.
Fixes: e3d4030498c3 ("mac80211: do not accept/forward invalid EAPOL frames") Link: https://lore.kernel.org/r/CAHQn7pKcyC_jYmGyTcPCdk9xxATwW5QPNph=bsZV8d-HPwNsy... Cc: stable@vger.kernel.org # 4.4.x Signed-off-by: Davis Mosenkovs davis@mosenkovs.lv --- net/mac80211/rx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bde924968cd2..b5848bcc09eb 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2234,7 +2234,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) #endif
if (skb) { - struct ethhdr *ehdr = (void *)skb_mac_header(skb); + struct ethhdr *ehdr = (struct ethhdr *)skb->data;
/* deliver to local stack */ skb->protocol = eth_type_trans(skb, dev);
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
On 2021-07-15 at 15:36 Greg KH (greg@kroah.com) 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...) and 4.14 (https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git/tree...) 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
On Fri, Jul 16, 2021 at 01:02:06AM +0300, Davis wrote:
On 2021-07-15 at 15:36 Greg KH (greg@kroah.com) 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...) and 4.14 (https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git/tree...) 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?
It's fine :)
linux-stable-mirror@lists.linaro.org
-
Davis -
Davis Mosenkovs
-
Greg KH