diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bb456f44b7b1..765d87acdf05 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4171,47 +4171,48 @@ static void update_blocked_averages(int cpu)
 }
 
 /*
- * Compute the cpu's hierarchical load factor for each task group.
+ * Compute the hierarchical load factor for cfs_rq and all its ascendants.
  * This needs to be done in a top-down fashion because the load of a child
  * group is a fraction of its parents load.
  */
-static int tg_load_down(struct task_group *tg, void *data)
+static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 {
-	unsigned long load;
-	long cpu = (long)data;
-
-	if (!tg->parent) {
-		load = cpu_rq(cpu)->avg.load_avg_contrib;
-	} else {
-		load = tg->parent->cfs_rq[cpu]->h_load;
-		load = div64_ul(load * tg->se[cpu]->avg.load_avg_contrib,
-				tg->parent->cfs_rq[cpu]->runnable_load_avg + 1);
-	}
-
-	tg->cfs_rq[cpu]->h_load = load;
-
-	return 0;
-}
-
-static void update_h_load(long cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
+	struct rq *rq = rq_of(cfs_rq);
+	struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)];
 	unsigned long now = jiffies;
+	unsigned long load;
 
-	if (rq->h_load_throttle == now)
+	if (cfs_rq->last_h_load_update == now)
 		return;
 
-	rq->h_load_throttle = now;
+	cfs_rq->h_load_next = NULL;
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+		cfs_rq->h_load_next = se;
+		if (cfs_rq->last_h_load_update == now)
+			break;
+	}
 
-	rcu_read_lock();
-	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
-	rcu_read_unlock();
+	if (!se) {
+		cfs_rq->h_load = rq->avg.load_avg_contrib;
+		cfs_rq->last_h_load_update = now;
+	}
+
+	while ((se = cfs_rq->h_load_next) != NULL) {
+		load = cfs_rq->h_load;
+		load = div64_ul(load * se->avg.load_avg_contrib,
+				cfs_rq->runnable_load_avg + 1);
+		cfs_rq = group_cfs_rq(se);
+		cfs_rq->h_load = load;
+		cfs_rq->last_h_load_update = now;
+	}
 }
 
 static unsigned long task_h_load(struct task_struct *p)
 {
 	struct cfs_rq *cfs_rq = task_cfs_rq(p);
 
+	update_cfs_rq_h_load(cfs_rq);
 	return div64_ul(p->se.avg.load_avg_contrib * cfs_rq->h_load,
 			cfs_rq->runnable_load_avg + 1);
 }
@@ -4220,10 +4221,6 @@ static inline void update_blocked_averages(int cpu)
 {
 }
 
-static inline void update_h_load(long cpu)
-{
-}
-
 static unsigned long task_h_load(struct task_struct *p)
 {
 	return p->se.avg.load_avg_contrib;
@@ -5108,7 +5105,6 @@ redo:
 		env.src_rq    = busiest;
 		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
-		update_h_load(env.src_cpu);
 more_balance:
 		local_irq_save(flags);
 		double_rq_lock(env.dst_rq, busiest);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ef0a7b2439dd..5e129efb84ce 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -285,7 +285,6 @@ struct cfs_rq {
 	/* Required to track per-cpu representation of a task_group */
 	u32 tg_runnable_contrib;
 	unsigned long tg_load_contrib;
-#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 	/*
 	 *   h_load = weight * f(tg)
@@ -294,6 +293,9 @@ struct cfs_rq {
 	 * this group.
 	 */
 	unsigned long h_load;
+	u64 last_h_load_update;
+	struct sched_entity *h_load_next;
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -429,9 +431,6 @@ struct rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this cpu: */
 	struct list_head leaf_cfs_rq_list;
-#ifdef CONFIG_SMP
-	unsigned long h_load_throttle;
-#endif /* CONFIG_SMP */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_RT_GROUP_SCHED