Re: [PATCH 5/5] sched/fair: Unify cfs_rq throttling via account_cfs_rq_runtime()

[Peter Zijlstra]

On Thu, May 28, 2026 at 09:48:30AM +0000, K Prateek Nayak wrote:

> @@ -9893,8 +9882,15 @@ static struct task_struct *pick_task_fair(struct rq *rq, struct rq_flags *rf)
>  		/* Might not have done put_prev_entity() */
>  		if (cfs_rq->curr && cfs_rq->curr->on_rq)
>  			update_curr(cfs_rq);
> -
> -		throttled |= check_cfs_rq_runtime(cfs_rq);
> +		/*
> +		 * For the current hierarchy, update_curr() above would
> +		 * have set the throttle indicators if the cfs_rq has
> +		 * run out of bandwidth. For others, enqueue / last
> +		 * update_curr() for the cfs_rq would have ensured the
> +		 * throttle indicators are set if bandwidth was not
> +		 * available.
> +		 */
> +		throttled |= cfs_rq_throttled(cfs_rq);
>  
>  		se = pick_next_entity(rq, cfs_rq, true);
>  		if (!se)

> @@ -15074,15 +15070,19 @@ static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool firs
>  static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
>  {
>  	struct sched_entity *se = &p->se;
> +	bool throttled = false;
>  
>  	for_each_sched_entity(se) {
>  		struct cfs_rq *cfs_rq = cfs_rq_of(se);
>  
>  		set_next_entity(cfs_rq, se, first);
>  		/* ensure bandwidth has been allocated on our new cfs_rq */
> -		account_cfs_rq_runtime(cfs_rq, 0);
> +		throttled |= account_cfs_rq_runtime(cfs_rq, 0);
>  	}
>  
> +	if (throttled)
> +		task_throttle_setup_work(p);
> +
>  	__set_next_task_fair(rq, p, first);
>  }

(noticed while trying to rebase flat on top)

Why do we have both? Isn't just set_next_task_fair(.first=true)
sufficient?