Re: [tip:sched/core] sched/core: Add debugging code to catch missing update_rq_clock() calls

[Wanpeng Li]

2017-02-02 23:55 GMT+08:00 Peter Zijlstra <peterz@xxxxxxxxxxxxx>:
> On Tue, Jan 31, 2017 at 10:22:47AM -0700, Ross Zwisler wrote:
>> On Tue, Jan 31, 2017 at 4:48 AM, Mike Galbraith <efault@xxxxxx> wrote:
>> > On Tue, 2017-01-31 at 16:30 +0530, Sachin Sant wrote:
>
>
> Could some of you test this? It seems to cure things in my (very)
> limited testing.
>

Tested-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>

> ---
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 96e4ccc..b773821 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -5609,7 +5609,7 @@ static void migrate_tasks(struct rq *dead_rq)
>  {
>         struct rq *rq = dead_rq;
>         struct task_struct *next, *stop = rq->stop;
> -       struct rq_flags rf, old_rf;
> +       struct rq_flags rf;
>         int dest_cpu;
>
>         /*
> @@ -5628,7 +5628,9 @@ static void migrate_tasks(struct rq *dead_rq)
>          * class method both need to have an up-to-date
>          * value of rq->clock[_task]
>          */
> +       rq_pin_lock(rq, &rf);
>         update_rq_clock(rq);
> +       rq_unpin_lock(rq, &rf);
>
>         for (;;) {
>                 /*
> @@ -5641,7 +5643,7 @@ static void migrate_tasks(struct rq *dead_rq)
>                 /*
>                  * pick_next_task assumes pinned rq->lock.
>                  */
> -               rq_pin_lock(rq, &rf);
> +               rq_repin_lock(rq, &rf);
>                 next = pick_next_task(rq, &fake_task, &rf);
>                 BUG_ON(!next);
>                 next->sched_class->put_prev_task(rq, next);
> @@ -5670,13 +5672,6 @@ static void migrate_tasks(struct rq *dead_rq)
>                         continue;
>                 }
>
> -               /*
> -                * __migrate_task() may return with a different
> -                * rq->lock held and a new cookie in 'rf', but we need
> -                * to preserve rf::clock_update_flags for 'dead_rq'.
> -                */
> -               old_rf = rf;
> -
>                 /* Find suitable destination for @next, with force if needed. */
>                 dest_cpu = select_fallback_rq(dead_rq->cpu, next);
>
> @@ -5685,7 +5680,6 @@ static void migrate_tasks(struct rq *dead_rq)
>                         raw_spin_unlock(&rq->lock);
>                         rq = dead_rq;
>                         raw_spin_lock(&rq->lock);
> -                       rf = old_rf;
>                 }
>                 raw_spin_unlock(&next->pi_lock);
>         }