1 files changed, 71 insertions, 31 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 20aa234ffe04..23663318fb81 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3298,6 +3298,52 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
 
 #ifdef CONFIG_SMP
 #ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * Because list_add_leaf_cfs_rq always places a child cfs_rq on the list
+ * immediately before a parent cfs_rq, and cfs_rqs are removed from the list
+ * bottom-up, we only have to test whether the cfs_rq before us on the list
+ * is our child.
+ * If cfs_rq is not on the list, test whether a child needs its to be added to
+ * connect a branch to the tree  * (see list_add_leaf_cfs_rq() for details).
+ */
+static inline bool child_cfs_rq_on_list(struct cfs_rq *cfs_rq)
+{
+	struct cfs_rq *prev_cfs_rq;
+	struct list_head *prev;
+
+	if (cfs_rq->on_list) {
+		prev = cfs_rq->leaf_cfs_rq_list.prev;
+	} else {
+		struct rq *rq = rq_of(cfs_rq);
+
+		prev = rq->tmp_alone_branch;
+	}
+
+	prev_cfs_rq = container_of(prev, struct cfs_rq, leaf_cfs_rq_list);
+
+	return (prev_cfs_rq->tg->parent == cfs_rq->tg);
+}
+
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+	if (cfs_rq->load.weight)
+		return false;
+
+	if (cfs_rq->avg.load_sum)
+		return false;
+
+	if (cfs_rq->avg.util_sum)
+		return false;
+
+	if (cfs_rq->avg.runnable_sum)
+		return false;
+
+	if (child_cfs_rq_on_list(cfs_rq))
+		return false;
+
+	return true;
+}
+
 /**
  * update_tg_load_avg - update the tg's load avg
  * @cfs_rq: the cfs_rq whose avg changed
@@ -3499,10 +3545,9 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf
 static inline void
 update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
 {
-	long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
+	long delta, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
 	unsigned long load_avg;
 	u64 load_sum = 0;
-	s64 delta_sum;
 	u32 divider;
 
 	if (!runnable_sum)
@@ -3549,13 +3594,13 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
 	load_sum = (s64)se_weight(se) * runnable_sum;
 	load_avg = div_s64(load_sum, divider);
 
-	delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum;
-	delta_avg = load_avg - se->avg.load_avg;
+	delta = load_avg - se->avg.load_avg;
 
 	se->avg.load_sum = runnable_sum;
 	se->avg.load_avg = load_avg;
-	add_positive(&cfs_rq->avg.load_avg, delta_avg);
-	add_positive(&cfs_rq->avg.load_sum, delta_sum);
+
+	add_positive(&cfs_rq->avg.load_avg, delta);
+	cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider;
 }
 
 static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum)
@@ -3766,11 +3811,17 @@ 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);
 
@@ -3902,7 +3953,7 @@ static inline unsigned long _task_util_est(struct task_struct *p)
 {
 	struct util_est ue = READ_ONCE(p->se.avg.util_est);
 
-	return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED);
+	return max(ue.ewma, (ue.enqueued & ~UTIL_AVG_UNCHANGED));
 }
 
 static inline unsigned long task_util_est(struct task_struct *p)
@@ -4002,7 +4053,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	 * Reset EWMA on utilization increases, the moving average is used only
 	 * to smooth utilization decreases.
 	 */
-	ue.enqueued = (task_util(p) | UTIL_AVG_UNCHANGED);
+	ue.enqueued = task_util(p);
 	if (sched_feat(UTIL_EST_FASTUP)) {
 		if (ue.ewma < ue.enqueued) {
 			ue.ewma = ue.enqueued;
@@ -4051,6 +4102,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	ue.ewma  += last_ewma_diff;
 	ue.ewma >>= UTIL_EST_WEIGHT_SHIFT;
 done:
+	ue.enqueued |= UTIL_AVG_UNCHANGED;
 	WRITE_ONCE(p->se.avg.util_est, ue);
 
 	trace_sched_util_est_se_tp(&p->se);
@@ -4085,6 +4137,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 
 #else /* CONFIG_SMP */
 
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+	return true;
+}
+
 #define UPDATE_TG	0x0
 #define SKIP_AGE_LOAD	0x0
 #define DO_ATTACH	0x0
@@ -4743,8 +4800,8 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 		cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
 					     cfs_rq->throttled_clock_task;
 
-		/* Add cfs_rq with already running entity in the list */
-		if (cfs_rq->nr_running >= 1)
+		/* Add cfs_rq with load or one or more already running entities to the list */
+		if (!cfs_rq_is_decayed(cfs_rq) || cfs_rq->nr_running)
 			list_add_leaf_cfs_rq(cfs_rq);
 	}
 
@@ -6217,7 +6274,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 	}
 
 	if (has_idle_core)
-		set_idle_cores(this, false);
+		set_idle_cores(target, false);
 
 	if (sched_feat(SIS_PROP) && !has_idle_core) {
 		time = cpu_clock(this) - time;
@@ -7990,23 +8047,6 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
-{
-	if (cfs_rq->load.weight)
-		return false;
-
-	if (cfs_rq->avg.load_sum)
-		return false;
-
-	if (cfs_rq->avg.util_sum)
-		return false;
-
-	if (cfs_rq->avg.runnable_sum)
-		return false;
-
-	return true;
-}
-
 static bool __update_blocked_fair(struct rq *rq, bool *done)
 {
 	struct cfs_rq *cfs_rq, *pos;
@@ -8030,7 +8070,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done)
 		/* Propagate pending load changes to the parent, if any: */
 		se = cfs_rq->tg->se[cpu];
 		if (se && !skip_blocked_update(se))
-			update_load_avg(cfs_rq_of(se), se, 0);
+			update_load_avg(cfs_rq_of(se), se, UPDATE_TG);
 
 		/*
 		 * There can be a lot of idle CPU cgroups.  Don't let fully