Date:   Tue, 14 Mar 2023 18:16:07 +0100
From:   Peter Zijlstra <peterz@infradead.org>
To:     Vincent Guittot <vincent.guittot@linaro.org>
Cc:     Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Zhang Qiao <zhangqiao22@huawei.com>,
        linux-kernel@vger.kernel.org, mingo@redhat.com,
        juri.lelli@redhat.com, rostedt@goodmis.org, bsegall@google.com,
        mgorman@suse.de, bristot@redhat.com, vschneid@redhat.com,
        rkagan@amazon.de
Subject: Re: [PATCH v2] sched/fair: sanitize vruntime of entity being migrated
Message-ID: <20230314171607.GN2017917@hirez.programming.kicks-ass.net>
References: <CAKfTPtAf5RrzZRSHtfK+r3QvnFQ-oM3+rJ-z5SB8T4+nUv1aQw@mail.gmail.com>
 <20230309142825.GB273121@hirez.programming.kicks-ass.net>
 <ZAnvCGdlOrWbIC/o@hirez.programming.kicks-ass.net>
 <CAKfTPtADUas2QHZCQyu0ad-JTKRQ=PcsB=o7+PuJNVxHwAzkCQ@mail.gmail.com>
 <ZAs+zV0o9ShO7nLT@vingu-book>
 <02a08042-e7c4-464d-bc20-9ec4ccdab1ff@arm.com>
 <8c093661-7431-00d8-d703-b8f7a7c8e747@arm.com>
 <CAKfTPtBw9SJxVBcN1qff7jRzE81kXSjbc-rXD6goEBFiXEwbyg@mail.gmail.com>
 <20230314120726.GG1845660@hirez.programming.kicks-ass.net>
 <CAKfTPtBHocw4N-YMHeqfMj78Ro=aF8sJPanxVCN=tM70hr6r8g@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CAKfTPtBHocw4N-YMHeqfMj78Ro=aF8sJPanxVCN=tM70hr6r8g@mail.gmail.com>
Precedence: bulk

On Tue, Mar 14, 2023 at 02:24:37PM +0100, Vincent Guittot wrote:

> > @@ -7632,11 +7646,8 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
> >          * min_vruntime -- the latter is done by enqueue_entity() when placing
> >          * the task on the new runqueue.
> >          */
> > -       if (READ_ONCE(p->__state) == TASK_WAKING) {
> > -               struct cfs_rq *cfs_rq = cfs_rq_of(se);
> > -
> > +       if (READ_ONCE(p->__state) == TASK_WAKING || reset_vruntime(cfs_rq, se))
> 
> That's somehow what was proposed in one of the previous proposals but
> we can't call rq_clock_task(rq_of(cfs_rq)) because rq lock might not
> be hold and rq task clock has not been updated before being used

Argh indeed. I spend a lot of time ensuring we didn't take the old rq
lock on wakeup -- and then a lot of time cursing about how we don't :-)

Now, if we could rely on the rq-clock being no more than 1 tick behind
current, this would still be entirely sufficient to catch the long sleep
case.

Except I suppose that NOHZ can bite us here. If the old CPU is idle, the
timestamps can be arbitrarily old. Mooo :/