Date: Mon, 20 Apr 2020 16:39:07 -0700 From: Eric Joyner <erj@freebsd.org> To: Mark Johnston <markj@freebsd.org> Cc: Hans Petter Selasky <hps@selasky.org>, freebsd-net@freebsd.org, shurd <shurd@freebsd.org>, John Baldwin <jhb@freebsd.org>, Drew Gallatin <gallatin@netflix.com> Subject: Re: Issue with epoch_drain_callbacks and unloading iavf(4) [using iflib] Message-ID: <CA%2Bb0zg9bi8Mc0ewnTqadjapHb5V-Mvc1y4c0AgZi08Q_Xy2dcg@mail.gmail.com> In-Reply-To: <CA%2Bb0zg-swzucfwLZ4kmBKeE-g44L0EqRnft4wR8-_BataDgR%2Bg@mail.gmail.com> References: <CA%2Bb0zg809EGMS1Ngr38BSb1yNpDqxbCnAv9eC%2BcDwbMQ5t%2BqXQ@mail.gmail.com> <20200212222219.GE83892@raichu> <CAKdFRZjdiz_axuweksNUHis7jPKXHqOmhQg%2BQWzpVnsKY%2Bcrmg@mail.gmail.com> <20200328225150.GA82767@raichu> <CAKdFRZgm43LmjJ9dYDBGM8EV0ePRMLPr4YW_tPELANXQGpqpCA@mail.gmail.com> <CA%2Bb0zg_k=8nMhapa=T=yTcSJcUrrnG=AfQB%2Be0gPcCrgkbWtCQ@mail.gmail.com> <20200331192024.GE97238@raichu> <CA%2Bb0zg9z7srroWLtV_poedghXjCr0GvHv95cu4JzFrRdZoaeWw@mail.gmail.com> <20200406212903.GA55712@raichu> <CA%2Bb0zg-JM1rjO_OPh16sgM3Hm2hbzePNaW5bcxiL9aOpJ_vsOA@mail.gmail.com> <20200407232347.GA5605@raichu> <CA%2Bb0zg9DZys8v--Rwtg1qBkz8XbByehq6vr-xmLtjenNGgRKiQ@mail.gmail.com> <CA%2Bb0zg-swzucfwLZ4kmBKeE-g44L0EqRnft4wR8-_BataDgR%2Bg@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Apr 9, 2020 at 2:29 PM Eric Joyner <erj@freebsd.org> wrote:
> On Thu, Apr 9, 2020 at 2:02 PM Eric Joyner <erj@freebsd.org> wrote:
>
>> On Tue, Apr 7, 2020 at 4:24 PM Mark Johnston <markj@freebsd.org> wrote:
>>
>>> I spent some time looking at the core. It looks like we have yet
>>> another problem: the gtaskqueue code won't exit the net epoch if it is
>>> constantly running a net task. Could you please retry with the patches
>>> from before, and this one included?
>>>
>>> diff --git a/sys/kern/subr_gtaskqueue.c b/sys/kern/subr_gtaskqueue.c
>>> index f52f32204644..2b1386a612ee 100644
>>> --- a/sys/kern/subr_gtaskqueue.c
>>> +++ b/sys/kern/subr_gtaskqueue.c
>>> @@ -345,7 +345,7 @@ gtaskqueue_run_locked(struct gtaskqueue *queue)
>>> struct epoch_tracker et;
>>> struct gtaskqueue_busy tb;
>>> struct gtask *gtask;
>>> - bool in_net_epoch;
>>> + bool in net_epoch;
>>>
>>> KASSERT(queue != NULL, ("tq is NULL"));
>>> TQ_ASSERT_LOCKED(queue);
>>> @@ -361,20 +361,19 @@ gtaskqueue_run_locked(struct gtaskqueue *queue)
>>> TQ_UNLOCK(queue);
>>>
>>> KASSERT(gtask->ta_func != NULL, ("task->ta_func is
>>> NULL"));
>>> - if (!in_net_epoch && TASK_IS_NET(gtask)) {
>>> - in_net_epoch = true;
>>> + if (TASK_IS_NET(gtask)) {
>>> NET_EPOCH_ENTER(et);
>>> - } else if (in_net_epoch && !TASK_IS_NET(gtask)) {
>>> + in_net_epoch = true;
>>> + }
>>> + gtask->ta_func(gtask->ta_context);
>>> + if (in_net_epoch) {
>>> NET_EPOCH_EXIT(et);
>>> in_net_epoch = false;
>>> }
>>> - gtask->ta_func(gtask->ta_context);
>>>
>>> TQ_LOCK(queue);
>>> wakeup(gtask);
>>> }
>>> - if (in_net_epoch)
>>> - NET_EPOCH_EXIT(et);
>>> LIST_REMOVE(&tb, tb_link);
>>> }
>>>
>>> _______________________________________________
>>> freebsd-net@freebsd.org mailing list
>>> https://lists.freebsd.org/mailman/listinfo/freebsd-net
>>> To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org"
>>>
>>
>> Yeah, I'll give it a spin and try to get back to you before the end of
>> the week.
>>
>> - Eric
>>
>
> I was able to try it out just now, and it looks this (and all of the other
> patches) finally causes the problem to not appear! I can unload the driver
> while iavf1 is receiving heavy traffic!
>
> - Eric
>
Hi Mark,
Are you planning to commit these patches to HEAD? I see the reviews for
D24214 and D24215 are still up, and I don't know if you created a review
for the patch you put in this email chain.
- Eric
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CA%2Bb0zg9bi8Mc0ewnTqadjapHb5V-Mvc1y4c0AgZi08Q_Xy2dcg>