sched/core: Fix group_entity's share update

The update of the share of a cfs_rq is done when its load_avg is updated
but before the group_entity's load_avg has been updated for the past time
slot. This generates wrong load_avg accounting which can be significant
when small tasks are involved in the scheduling.

Let take the example of a task a that is dequeued of its task group A:
   root
  (cfs_rq)
    \
    (se)
     A
    (cfs_rq)
      \
      (se)
       a

Task "a" was the only task in task group A which becomes idle when a is
dequeued.

We have the sequence:

- dequeue_entity a->se
    - update_load_avg(a->se)
    - dequeue_entity_load_avg(A->cfs_rq, a->se)
    - update_cfs_shares(A->cfs_rq)
	A->cfs_rq->load.weight == 0
        A->se->load.weight is updated with the new share (0 in this case)
- dequeue_entity A->se
    - update_load_avg(A->se) but its weight is now null so the last time
      slot (up to a tick) will be accounted with a weight of 0 instead of
      its real weight during the time slot. The last time slot will be
      accounted as an idle one whereas it was a running one.

If the running time of task a is short enough that no tick happens when it
runs, all running time of group entity A->se will be accounted as idle
time.

Instead, we should update the share of a cfs_rq (in fact the weight of its
group entity) only after having updated the load_avg of the group_entity.

update_cfs_shares() now takes the sched_entity as a parameter instead of the
cfs_rq, and the weight of the group_entity is updated only once its load_avg
has been synced with current time.

Signed-off-by: Vincent Guittot <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: vingu-linaro

kernel/sched/fair.c

@@ -2689,16 +2689,20 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
 
-static void update_cfs_shares(struct cfs_rq *cfs_rq)
+static void update_cfs_shares(struct sched_entity *se)
 {
+	struct cfs_rq *cfs_rq = group_cfs_rq(se);
 	struct task_group *tg;
-	struct sched_entity *se;
 	long shares;
 
-	tg = cfs_rq->tg;
-	se = tg->se[cpu_of(rq_of(cfs_rq))];
-	if (!se || throttled_hierarchy(cfs_rq))
+	if (!cfs_rq)
+		return;
+
+	if (throttled_hierarchy(cfs_rq))
 		return;
+
+	tg = cfs_rq->tg;
+
 #ifndef CONFIG_SMP
 	if (likely(se->load.weight == tg->shares))
 		return;
@@ -2707,8 +2711,9 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq)
 
 	reweight_entity(cfs_rq_of(se), se, shares);
 }
+
 #else /* CONFIG_FAIR_GROUP_SCHED */
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
+static inline void update_cfs_shares(struct sched_entity *se)
 {
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -3582,10 +3587,18 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	if (renorm && !curr)
 		se->vruntime += cfs_rq->min_vruntime;
 
+	/*
+	 * When enqueuing a sched_entity, we must:
+	 *   - Update loads to have both entity and cfs_rq synced with now.
+	 *   - Add its load to cfs_rq->runnable_avg
+	 *   - For group_entity, update its weight to reflect the new share of
+	 *     its group cfs_rq
+	 *   - Add its new weight to cfs_rq->load.weight
+	 */
 	update_load_avg(se, UPDATE_TG);
 	enqueue_entity_load_avg(cfs_rq, se);
+	update_cfs_shares(se);
 	account_entity_enqueue(cfs_rq, se);
-	update_cfs_shares(cfs_rq);
 
 	if (flags & ENQUEUE_WAKEUP)
 		place_entity(cfs_rq, se, 0);
@@ -3657,6 +3670,15 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
+
+	/*
+	 * When dequeuing a sched_entity, we must:
+	 *   - Update loads to have both entity and cfs_rq synced with now.
+	 *   - Substract its load from the cfs_rq->runnable_avg.
+	 *   - Substract its previous weight from cfs_rq->load.weight.
+	 *   - For group entity, update its weight to reflect the new share
+	 *     of its group cfs_rq.
+	 */
 	update_load_avg(se, UPDATE_TG);
 	dequeue_entity_load_avg(cfs_rq, se);
 
@@ -3681,7 +3703,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	/* return excess runtime on last dequeue */
 	return_cfs_rq_runtime(cfs_rq);
 
-	update_cfs_shares(cfs_rq);
+	update_cfs_shares(se);
 
 	/*
 	 * Now advance min_vruntime if @se was the entity holding it back,
@@ -3864,7 +3886,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	 * Ensure that runnable average is periodically updated.
 	 */
 	update_load_avg(curr, UPDATE_TG);
-	update_cfs_shares(cfs_rq);
+	update_cfs_shares(curr);
 
 #ifdef CONFIG_SCHED_HRTICK
 	/*
@@ -4761,7 +4783,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 			break;
 
 		update_load_avg(se, UPDATE_TG);
-		update_cfs_shares(cfs_rq);
+		update_cfs_shares(se);
 	}
 
 	if (!se)
@@ -4820,7 +4842,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 			break;
 
 		update_load_avg(se, UPDATE_TG);
-		update_cfs_shares(cfs_rq);
+		update_cfs_shares(se);
 	}
 
 	if (!se)
@@ -9362,8 +9384,10 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 
 		/* Possible calls to update_curr() need rq clock */
 		update_rq_clock(rq);
-		for_each_sched_entity(se)
-			update_cfs_shares(group_cfs_rq(se));
+		for_each_sched_entity(se) {
+			update_load_avg(se, UPDATE_TG);
+			update_cfs_shares(se);
+		}
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}