From: Quentin Perret <qperret@google.com>
To: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
mingo@redhat.com, vincent.guittot@linaro.org,
qais.yousef@arm.com, rickyiu@google.com, wvw@google.com,
patrick.bellasi@matbug.net, xuewen.yan94@gmail.com,
linux-kernel@vger.kernel.org, kernel-team@android.com
Subject: Re: [PATCH v2 1/3] sched: Fix UCLAMP_FLAG_IDLE setting
Date: Mon, 21 Jun 2021 10:57:18 +0000 [thread overview]
Message-ID: <YNBwjnRbQrWiG57/@google.com> (raw)
In-Reply-To: <23e44dd5-5229-ac16-5801-3b74f013b7f3@arm.com>
Hi Dietmar,
On Thursday 17 Jun 2021 at 17:27:56 (+0200), Dietmar Eggemann wrote:
> On 11/06/2021 09:25, Quentin Perret wrote:
> > On Thursday 10 Jun 2021 at 21:05:12 (+0200), Peter Zijlstra wrote:
> >> On Thu, Jun 10, 2021 at 03:13:04PM +0000, Quentin Perret wrote:
> >>> The UCLAMP_FLAG_IDLE flag is set on a runqueue when dequeueing the last
> >>> active task to maintain the last uclamp.max and prevent blocked util
> >>> from suddenly becoming visible.
> >>>
> >>> However, there is an asymmetry in how the flag is set and cleared which
> >>> can lead to having the flag set whilst there are active tasks on the rq.
> >>> Specifically, the flag is cleared in the uclamp_rq_inc() path, which is
> >>> called at enqueue time, but set in uclamp_rq_dec_id() which is called
> >>> both when dequeueing a task _and_ in the update_uclamp_active() path. As
> >>> a result, when both uclamp_rq_{dec,ind}_id() are called from
> >>> update_uclamp_active(), the flag ends up being set but not cleared,
> >>> hence leaving the runqueue in a broken state.
> >>>
> >>> Fix this by setting the flag in the uclamp_rq_inc_id() path to ensure
> >>> things remain symmetrical.
> >>
> >> The code you moved is neither in uclamp_rq_inc_id(), although
> >> uclamp_idle_reset() is called from there
> >
> > Yep, that is what I was trying to say.
> >
> >> nor does it _set_ the flag.
> >
> > Ahem. That I don't have a good excuse for ...
>
> (A) dequeue -> set
>
> (1) dequeue_task() -> uclamp_rq_dec() ->
>
> (2) cpu_util_update_eff() -> ... -> uclamp_update_active() ->
>
> uclamp_rq_dec_id()
>
> uclamp_rq_max_value()
>
> /* No tasks -- default clamp values */
> uclamp_idle_value() {
>
> if (clamp_id == UCLAMP_MAX)
> rq->uclamp_flags |= UCLAMP_FLAG_IDLE; <-- set
> }
>
> ---
>
> (B) enqueue -> clear
>
> (1) enqueue_task() ->
>
> uclamp_rq_inc() {
>
> (2) cpu_util_update_eff() -> ... -> uclamp_update_active() ->
>
> uclamp_rq_inc_id() {
>
> uclamp_idle_reset() {
> <-- new clear
> } ^
> } |
> |
> if (rq->uclamp_flags & UCLAMP_FLAG_IDLE) |
> rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE; <-- old clear
> }
>
> ---
>
> uclamp_update_active()
>
> if (p->uclamp[clamp_id].active) {
> uclamp_rq_dec_id() <-- (A2)
> uclamp_rq_inc_id() <-- (B2)
> }
>
> Is this existing asymmetry in setting the flag but not clearing it in
> uclamp_update_active() the only issue this patch fixes?
I think this is the root of the problem, but it can have odd symptoms.
In a bad case that can lead to hitting the WARN in uclamp_rq_dec_id
(which is how we've found the bug in the first place).
I'll try and repost this with a correct commit message soon -- still
fighting with my inbox right now.
Thanks,
Quentin
next prev parent reply other threads:[~2021-06-21 10:57 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-10 15:13 [PATCH v2 0/3] A few uclamp fixes Quentin Perret
2021-06-10 15:13 ` [PATCH v2 1/3] sched: Fix UCLAMP_FLAG_IDLE setting Quentin Perret
2021-06-10 19:05 ` Peter Zijlstra
2021-06-11 7:25 ` Quentin Perret
2021-06-17 15:27 ` Dietmar Eggemann
2021-06-21 10:57 ` Quentin Perret [this message]
2021-06-10 15:13 ` [PATCH v2 2/3] sched: Skip priority checks with SCHED_FLAG_KEEP_PARAMS Quentin Perret
2021-06-10 19:15 ` Peter Zijlstra
2021-06-11 8:59 ` Quentin Perret
2021-06-11 9:07 ` Quentin Perret
2021-06-11 9:20 ` Peter Zijlstra
2021-06-10 15:13 ` [PATCH v2 3/3] sched: Make uclamp changes depend on CAP_SYS_NICE Quentin Perret
2021-06-11 12:48 ` Qais Yousef
2021-06-11 13:08 ` Quentin Perret
2021-06-11 13:26 ` Qais Yousef
2021-06-11 13:49 ` Quentin Perret
2021-06-11 14:17 ` Qais Yousef
2021-06-11 14:43 ` Quentin Perret
2021-06-14 15:03 ` Qais Yousef
2021-06-21 10:52 ` Quentin Perret
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=YNBwjnRbQrWiG57/@google.com \
--to=qperret@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=kernel-team@android.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=patrick.bellasi@matbug.net \
--cc=peterz@infradead.org \
--cc=qais.yousef@arm.com \
--cc=rickyiu@google.com \
--cc=vincent.guittot@linaro.org \
--cc=wvw@google.com \
--cc=xuewen.yan94@gmail.com \
/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).