From: Vincent Guittot <vincent.guittot@xxxxxxxxxx> [ Upstream commit 6d4d22468dae3d8757af9f8b81b848a76ef4409d ] The walk through the cgroup hierarchy during the enqueue/dequeue of a task is split in 2 distinct parts for throttled cfs_rq without any added value but making code less readable. Change the code ordering such that everything related to a cfs_rq (throttled or not) will be done in the same loop. In addition, the same steps ordering is used when updating a cfs_rq: - update_load_avg - update_cfs_group - update *h_nr_running This reordering enables the use of h_nr_running in PELT algorithm. No functional and performance changes are expected and have been noticed during tests. Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx> Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx> Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx> Reviewed-by: "Dietmar Eggemann <dietmar.eggemann@xxxxxxx>" Acked-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> Cc: Juri Lelli <juri.lelli@xxxxxxxxxx> Cc: Valentin Schneider <valentin.schneider@xxxxxxx> Cc: Phil Auld <pauld@xxxxxxxxxx> Cc: Hillf Danton <hdanton@xxxxxxxx> Link: https://lore.kernel.org/r/20200224095223.13361-5-mgorman@xxxxxxxxxxxxxxxxxxx Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> --- kernel/sched/fair.c | 42 ++++++++++++++++++++---------------------- 1 file changed, 20 insertions(+), 22 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c76a20648b72..a486bf3d5078 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5276,32 +5276,31 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq = cfs_rq_of(se); enqueue_entity(cfs_rq, se, flags); - /* - * end evaluation on encountering a throttled cfs_rq - * - * note: in the case of encountering a throttled cfs_rq we will - * post the final h_nr_running increment below. - */ - if (cfs_rq_throttled(cfs_rq)) - break; cfs_rq->h_nr_running++; cfs_rq->idle_h_nr_running += idle_h_nr_running; + /* end evaluation on encountering a throttled cfs_rq */ + if (cfs_rq_throttled(cfs_rq)) + goto enqueue_throttle; + flags = ENQUEUE_WAKEUP; } for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - cfs_rq->h_nr_running++; - cfs_rq->idle_h_nr_running += idle_h_nr_running; + /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) - break; + goto enqueue_throttle; update_load_avg(cfs_rq, se, UPDATE_TG); update_cfs_group(se); + + cfs_rq->h_nr_running++; + cfs_rq->idle_h_nr_running += idle_h_nr_running; } +enqueue_throttle: if (!se) { add_nr_running(rq, 1); /* @@ -5362,17 +5361,13 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq = cfs_rq_of(se); dequeue_entity(cfs_rq, se, flags); - /* - * end evaluation on encountering a throttled cfs_rq - * - * note: in the case of encountering a throttled cfs_rq we will - * post the final h_nr_running decrement below. - */ - if (cfs_rq_throttled(cfs_rq)) - break; cfs_rq->h_nr_running--; cfs_rq->idle_h_nr_running -= idle_h_nr_running; + /* end evaluation on encountering a throttled cfs_rq */ + if (cfs_rq_throttled(cfs_rq)) + goto dequeue_throttle; + /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { /* Avoid re-evaluating load for this entity: */ @@ -5390,16 +5385,19 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - cfs_rq->h_nr_running--; - cfs_rq->idle_h_nr_running -= idle_h_nr_running; + /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) - break; + goto dequeue_throttle; update_load_avg(cfs_rq, se, UPDATE_TG); update_cfs_group(se); + + cfs_rq->h_nr_running--; + cfs_rq->idle_h_nr_running -= idle_h_nr_running; } +dequeue_throttle: if (!se) sub_nr_running(rq, 1); -- 2.25.1
