sched/pelt: Ensure that *_sum is always synced with *_avg

Rounding in PELT calculation happening when entities are attached/detached
of a cfs_rq can result into situations where util/runnable_avg is not null
but util/runnable_sum is. This is normally not possible so we need to
ensure that util/runnable_sum stays synced with util/runnable_avg.

detach_entity_load_avg() is the last place where we don't sync
util/runnable_sum with util/runnbale_avg when moving some sched_entities

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210601085832.12626-1-vincent.guittot@linaro.org

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e7c8277..7b98fb3 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3765,11 +3765,17 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
  */
 static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+       /*
+        * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
+        * See ___update_load_avg() for details.
+        */
+       u32 divider = get_pelt_divider(&cfs_rq->avg);
+
        dequeue_load_avg(cfs_rq, se);
        sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
-       sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+       cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider;
        sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg);
-       sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum);
+       cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider;
 
        add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);