Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <1598272219-43040-1-git-send-email-xlpang@linux.alibaba.com>
 <CAPJCdBnTm0=Nazi2w9a6mBcKNv=_66UwvMfTNg6vLNKqW6qfwQ@mail.gmail.com> <495238bd-ea0d-56c6-4a9c-7b18deafcc8f@linux.alibaba.com>
In-Reply-To: <495238bd-ea0d-56c6-4a9c-7b18deafcc8f@linux.alibaba.com>
From:   Jiang Biao <benbjiang@gmail.com>
Date:   Tue, 25 Aug 2020 20:46:24 +0800
Message-ID: <CAPJCdBm4thJ7NT9uGRPLn7Be4tNA8c33fXCvdWiGfbRJcdKf+w@mail.gmail.com>
Subject: Re: [PATCH] sched/fair: Fix wrong cpu selecting from isolated domain
To:     Xunlei Pang <xlpang@linux.alibaba.com>
Cc:     Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Juri Lelli <juri.lelli@redhat.com>,
        Wetp Zhang <wetp.zy@linux.alibaba.com>,
        linux-kernel <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, 25 Aug 2020 at 17:28, xunlei <xlpang@linux.alibaba.com> wrote:
>
> On 2020/8/25 =E4=B8=8B=E5=8D=882:37, Jiang Biao wrote:
> > On Mon, 24 Aug 2020 at 20:31, Xunlei Pang <xlpang@linux.alibaba.com> wr=
ote:
> >>
> >> We've met problems that occasionally tasks with full cpumask
> >> (e.g. by putting it into a cpuset or setting to full affinity)
> >> were migrated to our isolated cpus in production environment.
> >>
> >> After some analysis, we found that it is due to the current
> >> select_idle_smt() not considering the sched_domain mask.
> >>
> >> Fix it by checking the valid domain mask in select_idle_smt().
> >>
> >> Fixes: 10e2f1acd010 ("sched/core: Rewrite and improve select_idle_sibl=
ings())
> >> Reported-by: Wetp Zhang <wetp.zy@linux.alibaba.com>
> >> Signed-off-by: Xunlei Pang <xlpang@linux.alibaba.com>
> >> ---
> >>  kernel/sched/fair.c | 9 +++++----
> >>  1 file changed, 5 insertions(+), 4 deletions(-)
> >>
> >> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> >> index 1a68a05..fa942c4 100644
> >> --- a/kernel/sched/fair.c
> >> +++ b/kernel/sched/fair.c
> >> @@ -6075,7 +6075,7 @@ static int select_idle_core(struct task_struct *=
p, struct sched_domain *sd, int
> >>  /*
> >>   * Scan the local SMT mask for idle CPUs.
> >>   */
> >> -static int select_idle_smt(struct task_struct *p, int target)
> >> +static int select_idle_smt(struct task_struct *p, struct sched_domain=
 *sd, int target)
> >>  {
> >>         int cpu;
> >>
> >> @@ -6083,7 +6083,8 @@ static int select_idle_smt(struct task_struct *p=
, int target)
> >>                 return -1;
> >>
> >>         for_each_cpu(cpu, cpu_smt_mask(target)) {
> >> -               if (!cpumask_test_cpu(cpu, p->cpus_ptr))
> >> +               if (!cpumask_test_cpu(cpu, p->cpus_ptr) ||
> >> +                   !cpumask_test_cpu(cpu, sched_domain_span(sd)))
> > Maybe the following change could be better, :)
> > for_each_cpu_and(cpu, cpu_smt_mask(target), sched_domain_span(sd))
> > keep a similar style with select_idle_core/cpu, and could reduce loops.
> >
>
> I thought that, but given that smt mask is usually small, the original
> code may run a bit faster?
Not sure. :)
It's OK for me.

Regards,
Jiang