Re: [PATCH v5 2/4] sched/core: Avoid double calling update_rq_clock() in __balance_push_cpu_stop()

[Peter Zijlstra]

On Tue, Jun 13, 2023 at 04:20:10PM +0800, Hao Jia wrote:
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index a8be5415daba..1eca36299d8b 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -2398,7 +2398,6 @@ static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
>  	if (!is_cpu_allowed(p, dest_cpu))
>  		return rq;
>  
> -	update_rq_clock(rq);
>  	rq = move_queued_task(rq, rf, p, dest_cpu);
>  
>  	return rq;
> @@ -2456,10 +2455,12 @@ static int migration_cpu_stop(void *data)
>  				goto out;
>  		}
>  
> -		if (task_on_rq_queued(p))
> +		if (task_on_rq_queued(p)) {
> +			update_rq_clock(rq);
>  			rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
> -		else
> +		} else {
>  			p->wake_cpu = arg->dest_cpu;
> +		}
>  
>  		/*
>  		 * XXX __migrate_task() can fail, at which point we might end

So now you've got update_rq_clock() in both callers, why not remove it
from __balance_push_cpu_stop() ?

Afaict nothing actually needs it before __migrate_task().

---
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9435,8 +9435,6 @@ static int __balance_push_cpu_stop(void
 	raw_spin_lock_irq(&p->pi_lock);
 	rq_lock(rq, &rf);
 
-	update_rq_clock(rq);
-
 	if (task_rq(p) == rq && task_on_rq_queued(p)) {
 		cpu = select_fallback_rq(rq->cpu, p);
 		rq = __migrate_task(rq, &rf, p, cpu);