Re: [PATCH v3] sched/fair: fix unthrottle_cfs_rq for leaf_cfs_rq list

[bsegall]

Vincent Guittot <vincent.guittot@xxxxxxxxxx> writes:

> Although not exactly identical, unthrottle_cfs_rq() and enqueue_task_fair()
> are quite close and follow the same sequence for enqueuing an entity in the
> cfs hierarchy. Modify unthrottle_cfs_rq() to use the same pattern as
> enqueue_task_fair(). This fixes a problem already faced with the latter and
> add an optimization in the last for_each_sched_entity loop.
>
> Reported-by Tao Zhou <zohooouoto@xxxxxxxxxxx>
> Reviewed-by: Phil Auld <pauld@xxxxxxxxxx>

Reveiewed-by: Ben Segall <bsegall@xxxxxxxxxx>

> Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
> ---
>
> v3 changes:
>   - remove the unused enqueue variable
>
>  kernel/sched/fair.c | 42 ++++++++++++++++++++++++++++++------------
>  1 file changed, 30 insertions(+), 12 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 4e12ba882663..9a58874ef104 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -4792,7 +4792,6 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
>  	struct rq *rq = rq_of(cfs_rq);
>  	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
>  	struct sched_entity *se;
> -	int enqueue = 1;
>  	long task_delta, idle_task_delta;
>  
>  	se = cfs_rq->tg->se[cpu_of(rq)];
> @@ -4816,26 +4815,44 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
>  	idle_task_delta = cfs_rq->idle_h_nr_running;
>  	for_each_sched_entity(se) {
>  		if (se->on_rq)
> -			enqueue = 0;
> +			break;
> +		cfs_rq = cfs_rq_of(se);
> +		enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
>  
> +		cfs_rq->h_nr_running += task_delta;
> +		cfs_rq->idle_h_nr_running += idle_task_delta;
> +
> +		/* end evaluation on encountering a throttled cfs_rq */
> +		if (cfs_rq_throttled(cfs_rq))
> +			goto unthrottle_throttle;
> +	}
> +
> +	for_each_sched_entity(se) {
>  		cfs_rq = cfs_rq_of(se);
> -		if (enqueue) {
> -			enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
> -		} else {
> -			update_load_avg(cfs_rq, se, 0);
> -			se_update_runnable(se);
> -		}
> +
> +		update_load_avg(cfs_rq, se, UPDATE_TG);
> +		se_update_runnable(se);
>  
>  		cfs_rq->h_nr_running += task_delta;
>  		cfs_rq->idle_h_nr_running += idle_task_delta;
>  
> +
> +		/* end evaluation on encountering a throttled cfs_rq */
>  		if (cfs_rq_throttled(cfs_rq))
> -			break;
> +			goto unthrottle_throttle;
> +
> +		/*
> +		 * One parent has been throttled and cfs_rq removed from the
> +		 * list. Add it back to not break the leaf list.
> +		 */
> +		if (throttled_hierarchy(cfs_rq))
> +			list_add_leaf_cfs_rq(cfs_rq);
>  	}
>  
> -	if (!se)
> -		add_nr_running(rq, task_delta);
> +	/* At this point se is NULL and we are at root level*/
> +	add_nr_running(rq, task_delta);
>  
> +unthrottle_throttle:
>  	/*
>  	 * The cfs_rq_throttled() breaks in the above iteration can result in
>  	 * incomplete leaf list maintenance, resulting in triggering the
> @@ -4844,7 +4861,8 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
>  	for_each_sched_entity(se) {
>  		cfs_rq = cfs_rq_of(se);
>  
> -		list_add_leaf_cfs_rq(cfs_rq);
> +		if (list_add_leaf_cfs_rq(cfs_rq))
> +			break;
>  	}
>  
>  	assert_list_leaf_cfs_rq(rq);