| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <62054a31-4708-1696-60d5-b33e4993cddc@huawei.com>
Date: Wed, 12 May 2021 11:34:55 +0800
From: Yunsheng Lin <linyunsheng@...wei.com>
To: Jakub Kicinski <kuba@...nel.org>
CC: <davem@...emloft.net>, <olteanv@...il.com>, <ast@...nel.org>,
<daniel@...earbox.net>, <andriin@...com>, <edumazet@...gle.com>,
<weiwan@...gle.com>, <cong.wang@...edance.com>,
<ap420073@...il.com>, <netdev@...r.kernel.org>,
<linux-kernel@...r.kernel.org>, <linuxarm@...neuler.org>,
<mkl@...gutronix.de>, <linux-can@...r.kernel.org>,
<jhs@...atatu.com>, <xiyou.wangcong@...il.com>, <jiri@...nulli.us>,
<andrii@...nel.org>, <kafai@...com>, <songliubraving@...com>,
<yhs@...com>, <john.fastabend@...il.com>, <kpsingh@...nel.org>,
<bpf@...r.kernel.org>, <jonas.bonn@...rounds.com>,
<pabeni@...hat.com>, <mzhivich@...mai.com>, <johunt@...mai.com>,
<albcamus@...il.com>, <kehuan.feng@...il.com>,
<a.fatoum@...gutronix.de>, <atenart@...nel.org>,
<alexander.duyck@...il.com>, <hdanton@...a.com>, <jgross@...e.com>,
<JKosina@...e.com>, <mkubecek@...e.cz>, <bjorn@...nel.org>,
<alobakin@...me>
Subject: Re: [Linuxarm] Re: [PATCH net v6 3/3] net: sched: fix tx action
reschedule issue with stopped queue
On 2021/5/12 7:30, Jakub Kicinski wrote:
> On Tue, 11 May 2021 20:13:56 +0800 Yunsheng Lin wrote:
>> On 2021/5/11 17:04, Yunsheng Lin wrote:
>>> On 2021/5/11 12:22, Jakub Kicinski wrote:
>>>> The queues are woken asynchronously without holding any locks via
>>>> netif_tx_wake_queue(). Theoretically we can have a situation where:
>>>>
>>>> CPU 0 CPU 1
>>>> . .
>>>> dequeue_skb() .
>>>> netif_xmit_frozen..() # true .
>>>> . [IRQ]
>>>> . netif_tx_wake_queue()
>>>> . <end of IRQ>
>>>> . netif_tx_action()
>>>> . set MISSED
>>>> clear MISSED
>>>> return NULL
>>>> ret from qdisc_restart()
>>>> ret from __qdisc_run()
>>>> qdisc_run_end()
>> [...]
>>>
>>> Yes, the above does seems to have the above data race.
>>>
>>> As my understanding, there is two ways to fix the above data race:
>>> 1. do not clear the STATE_MISSED for netif_xmit_frozen_or_stopped()
>>> case, just check the netif_xmit_frozen_or_stopped() before
>>> calling __netif_schedule() at the end of qdisc_run_end(). This seems
>>> to only work with qdisc with TCQ_F_ONETXQUEUE flag because it seems
>>> we can only check the netif_xmit_frozen_or_stopped() with q->dev_queue,
>>> I am not sure q->dev_queue is pointint to which netdev queue when qdisc
>>> is not set with TCQ_F_ONETXQUEUE flag.
>
> Isn't the case where we have a NOLOCK qdisc without TCQ_F_ONETXQUEUE
> rather unexpected? It'd have to be a single pfifo on multi-queue
> netdev, right? Sounds not worth optimizing for. How about:
>
> static inline void qdisc_run_end(struct Qdisc *qdisc)
> {
> write_seqcount_end(&qdisc->running);
> if (qdisc->flags & TCQ_F_NOLOCK) {
> spin_unlock(&qdisc->seqlock);
>
> if (unlikely(test_bit(__QDISC_STATE_MISSED,
> &qdisc->state))) {
> clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
> if (!(q->flags & TCQ_F_ONETXQUEUE) ||
> !netif_xmit_frozen_or_stopped(q->dev_queue))
> __netif_schedule(qdisc);
> }
> }
> }
>
> For the strange non-ONETXQUEUE case we'd have an occasional unnecessary
> net_tx_action, but no infinite loop possible.
>
>>> 2. clearing the STATE_MISSED for netif_xmit_frozen_or_stopped() case
>>> as this patch does, and protect the __netif_schedule() with q->seqlock
>>> for netif_tx_wake_queue(), which might bring unnecessary overhead for
>>> non-stopped queue case
>>>
>>> Any better idea?
>>
>> 3. Or check the netif_xmit_frozen_or_stopped() again after clearing
>> STATE_MISSED, like below:
>>
>> if (netif_xmit_frozen_or_stopped(txq)) {
>> clear_bit(__QDISC_STATE_MISSED, &q->state);
>>
>> /* Make sure the below netif_xmit_frozen_or_stopped()
>> * checking happens after clearing STATE_MISSED.
>> */
>> smp_mb__after_atomic();
>>
>> /* Checking netif_xmit_frozen_or_stopped() again to
>> * make sure __QDISC_STATE_MISSED is set if the
>> * __QDISC_STATE_MISSED set by netif_tx_wake_queue()'s
>> * rescheduling of net_tx_action() is cleared by the
>> * above clear_bit().
>> */
>> if (!netif_xmit_frozen_or_stopped(txq))
>> set_bit(__QDISC_STATE_MISSED, &q->state);
>> }
>>
>> It is kind of ugly, but it does seem to fix the above data race too.
>> And it seems like a common pattern to deal with the concurrency between
>> xmit and NAPI polling, as below:
>>
>> https://elixir.bootlin.com/linux/v5.12-rc2/source/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c#L1409
>
> This is indeed the idiomatic way of dealing with Tx queue stopping race,
> but it's a bit of code to sprinkle around. My vote would be option 1.
I had done some performance testing to see which is better, tested using
pktgen and dummy netdev with pfifo_fast qdisc attached:
unit: Mpps
threads V6 V6 + option 1 V6 + option 3
1 2.60 2.54 2.60
2 3.86 3.84 3.84
4 5.56 5.50 5.51
8 2.79 2.77 2.77
16 2.23 2.24 2.22
So it seems the netif_xmit_frozen_or_stopped checking overhead for non-stopped queue
is noticable for 1 pktgen thread.
And the performance increase for V6 + option 1 with 16 pktgen threads is because of
"clear_bit(__QDISC_STATE_MISSED, &qdisc->state)" at the end of qdisc_run_end(), which
may avoid the another round of dequeuing in the pfifo_fast_dequeue(). And adding the
"clear_bit(__QDISC_STATE_MISSED, &qdisc->state)" for V6 + option 3, the data for
16 pktgen thread also go up to 2.24Mpps.
So it seems V6 + option 3 with "clear_bit(__QDISC_STATE_MISSED, &qdisc->state)" at
the end of qdisc_run_end() is better?
> _______________________________________________
> Linuxarm mailing list -- linuxarm@...neuler.org
> To unsubscribe send an email to linuxarm-leave@...neuler.org
>
Powered by blists - more mailing lists