| From 4826eccc2fce84b6b883d5b4710db6e327aa72f4 Mon Sep 17 00:00:00 2001 |
| From: Vincent Guittot <vincent.guittot@linaro.org> |
| Date: Fri, 6 Mar 2020 09:42:08 +0100 |
| Subject: [PATCH] sched/fair: Fix reordering of enqueue/dequeue_task_fair() |
| |
| commit 5ab297bab984310267734dfbcc8104566658ebef upstream. |
| |
| Even when a cgroup is throttled, the group se of a child cgroup can still |
| be enqueued and its gse->on_rq stays true. When a task is enqueued on such |
| child, we still have to update the load_avg and increase |
| h_nr_running of the throttled cfs. Nevertheless, the 1st |
| for_each_sched_entity() loop is skipped because of gse->on_rq == true and the |
| 2nd loop because the cfs is throttled whereas we have to update both |
| load_avg with the old h_nr_running and increase h_nr_running in such case. |
| |
| The same sequence can happen during dequeue when se moves to parent before |
| breaking in the 1st loop. |
| |
| Note that the update of load_avg will effectively happen only once in order |
| to sync up to the throttled time. Next call for updating load_avg will stop |
| early because the clock stays unchanged. |
| |
| Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> |
| Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> |
| Signed-off-by: Ingo Molnar <mingo@kernel.org> |
| Fixes: 6d4d22468dae ("sched/fair: Reorder enqueue/dequeue_task_fair path") |
| Link: https://lkml.kernel.org/r/20200306084208.12583-1-vincent.guittot@linaro.org |
| Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> |
| |
| diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c |
| index 5558256609db..199b83c97283 100644 |
| --- a/kernel/sched/fair.c |
| +++ b/kernel/sched/fair.c |
| @@ -5232,15 +5232,15 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) |
| for_each_sched_entity(se) { |
| cfs_rq = cfs_rq_of(se); |
| |
| - /* end evaluation on encountering a throttled cfs_rq */ |
| - if (cfs_rq_throttled(cfs_rq)) |
| - 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; |
| + |
| + /* end evaluation on encountering a throttled cfs_rq */ |
| + if (cfs_rq_throttled(cfs_rq)) |
| + goto enqueue_throttle; |
| } |
| |
| enqueue_throttle: |
| @@ -5328,15 +5328,16 @@ 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); |
| |
| - /* end evaluation on encountering a throttled cfs_rq */ |
| - if (cfs_rq_throttled(cfs_rq)) |
| - 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; |
| + |
| + /* end evaluation on encountering a throttled cfs_rq */ |
| + if (cfs_rq_throttled(cfs_rq)) |
| + goto dequeue_throttle; |
| + |
| } |
| |
| dequeue_throttle: |
| -- |
| 2.7.4 |
| |