linux-wireless.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Wen Gong <quic_wgong@quicinc.com>
To: Felix Fietkau <nbd@nbd.name>, <linux-wireless@vger.kernel.org>
Cc: <johannes@sipsolutions.net>, <ath11k@lists.infradead.org>,
	<johannes.berg@intel.com>
Subject: Re: [PATCH 4/5] mac80211: run late dequeue late tx handlers without holding fq->lock
Date: Wed, 7 Dec 2022 14:30:45 +0800	[thread overview]
Message-ID: <a918d3ee-edc7-b6a2-d15a-e0d77f0683e2@quicinc.com> (raw)
In-Reply-To: <9bce39db-1de4-f129-8d2f-77f51a64a5db@quicinc.com>

Hi Johannes,

do you know it?

On 12/5/2022 5:46 PM, Wen Gong wrote:
> On 3/17/2019 1:06 AM, Felix Fietkau wrote:
>> Reduces lock contention on enqueue/dequeue of iTXQ packets
>>
>> Signed-off-by: Felix Fietkau <nbd@nbd.name>
>> ---
>>   net/mac80211/tx.c | 10 ++++++++--
>>   1 file changed, 8 insertions(+), 2 deletions(-)
>>
>> diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
>> index 8127e43e12b1..f85344c9af62 100644
>> --- a/net/mac80211/tx.c
>> +++ b/net/mac80211/tx.c
>> @@ -3544,6 +3544,7 @@ struct sk_buff *ieee80211_tx_dequeue(struct 
>> ieee80211_hw *hw,
>>       ieee80211_tx_result r;
>>       struct ieee80211_vif *vif = txq->vif;
>>   +begin:
>>       spin_lock_bh(&fq->lock);
> Maybe use-after-free will happened?
>
> You can see ieee80211_tx_dequeue() in tx.c as below, after 
> ieee80211_free_txskb(), it will goto begin,
> If goto out happened in below check, then the skb which is freed will 
> be returned, and use-after-free will happen.
>
> https://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git/tree/net/mac80211/tx.c?id=ded4698b58cb23c22b0dcbd829ced19ce4e6ce02#n3538 
>
> begin:
>     spin_lock_bh(&fq->lock);
>
>     if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ||
>         test_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags))
>         goto out;
>
>     if (vif->txqs_stopped[ieee80211_ac_from_tid(txq->tid)]) {
>         set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags);
>         goto out;
>     }
>
>     /* Make sure fragments stay together. */
>     skb = __skb_dequeue(&txqi->frags);
>     if (skb)
>         goto out;
>
>     skb = fq_tin_dequeue(fq, tin, fq_tin_dequeue_func);
>     if (!skb)
>         goto out;
>
>     spin_unlock_bh(&fq->lock);
>
> Maybe "skb = NULL;" should be added after "begin:".
>
> ...
>

  reply	other threads:[~2022-12-07  6:31 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-16 17:06 [PATCH 1/5] mac80211: mesh: drop redundant rcu_read_lock/unlock calls Felix Fietkau
2019-03-16 17:06 ` [PATCH 2/5] mac80211: fix memory accounting with A-MSDU aggregation Felix Fietkau
2019-03-16 18:12   ` Toke Høiland-Jørgensen
2019-03-16 17:06 ` [PATCH 3/5] mac80211: calculate hash for fq without holding fq->lock in itxq enqueue Felix Fietkau
2019-03-16 18:13   ` Toke Høiland-Jørgensen
2019-03-16 17:06 ` [PATCH 4/5] mac80211: run late dequeue late tx handlers without holding fq->lock Felix Fietkau
2019-03-16 18:13   ` Toke Høiland-Jørgensen
2022-12-05  9:46   ` Wen Gong
2022-12-07  6:30     ` Wen Gong [this message]
2022-12-12  8:31       ` Wen Gong
2019-03-16 17:06 ` [PATCH 5/5] mac80211: set NETIF_F_LLTX when using intermediate tx queues Felix Fietkau
2019-03-16 18:14   ` Toke Høiland-Jørgensen
2019-04-14  9:44     ` Arend Van Spriel
2019-04-14 11:19       ` Felix Fietkau
2019-04-14 12:34         ` Arend Van Spriel
2019-04-16  7:34           ` Arend Van Spriel
2019-04-16  7:44       ` Herbert Xu
2019-04-16  8:04         ` Arend Van Spriel
2019-04-16  8:36           ` Herbert Xu
2019-04-16  8:37             ` Johannes Berg
2019-04-16  9:17               ` Arend Van Spriel
2019-04-16  9:29                 ` Herbert Xu
2019-04-16  9:33               ` Toke Høiland-Jørgensen
2019-04-16  9:33                 ` Johannes Berg
2019-04-16  9:37                   ` Herbert Xu
2019-04-16  9:39                     ` Johannes Berg
2019-04-16 10:02                       ` Toke Høiland-Jørgensen
2019-04-17  2:11                         ` Herbert Xu
2019-04-17  8:28                           ` Toke Høiland-Jørgensen
2019-04-16 13:13                       ` Herbert Xu
2019-04-16 13:18                         ` Toke Høiland-Jørgensen
2019-04-17  3:38                           ` Herbert Xu
2019-04-17  9:09                             ` Toke Høiland-Jørgensen
2019-04-17  9:16                               ` Arend Van Spriel
2019-04-17  9:17                             ` Toke Høiland-Jørgensen
2019-04-23 12:41                               ` Johannes Berg
2019-04-25  8:35                                 ` Herbert Xu
2019-04-25  8:39                                   ` Johannes Berg
2019-04-25  8:44                                     ` Herbert Xu
2019-04-25  8:49                                       ` Johannes Berg
2019-04-16 19:13                         ` Johannes Berg
2019-04-17  2:13                           ` Herbert Xu
2019-04-16  9:38                   ` Toke Høiland-Jørgensen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=a918d3ee-edc7-b6a2-d15a-e0d77f0683e2@quicinc.com \
    --to=quic_wgong@quicinc.com \
    --cc=ath11k@lists.infradead.org \
    --cc=johannes.berg@intel.com \
    --cc=johannes@sipsolutions.net \
    --cc=linux-wireless@vger.kernel.org \
    --cc=nbd@nbd.name \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).