diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6e371f43fc80..6df80d47a525 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2878,7 +2878,9 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
 static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 {
 	struct sched_avg *sa = &cfs_rq->avg;
+	struct rq *rq = rq_of(cfs_rq);
 	int decayed, removed = 0;
+	int cpu = cpu_of(rq);
 
 	if (atomic_long_read(&cfs_rq->removed_load_avg)) {
 		s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
@@ -2893,7 +2895,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 		sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
 	}
 
-	decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
+	decayed = __update_load_avg(now, cpu, sa,
 		scale_load_down(cfs_rq->load.weight), cfs_rq->curr != NULL, cfs_rq);
 
 #ifndef CONFIG_64BIT
@@ -2901,6 +2903,29 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 	cfs_rq->load_last_update_time_copy = sa->last_update_time;
 #endif
 
+	if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) {
+		unsigned long max = rq->cpu_capacity_orig;
+
+		/*
+		 * There are a few boundary cases this might miss but it should
+		 * get called often enough that that should (hopefully) not be
+		 * a real problem -- added to that it only calls on the local
+		 * CPU, so if we enqueue remotely we'll miss an update, but
+		 * the next tick/schedule should update.
+		 *
+		 * It will not get called when we go idle, because the idle
+		 * thread is a different class (!fair), nor will the utilization
+		 * number include things like RT tasks.
+		 *
+		 * As is, the util number is not freq-invariant (we'd have to
+		 * implement arch_scale_freq_capacity() for that).
+		 *
+		 * See cpu_util().
+		 */
+		cpufreq_update_util(rq_clock(rq),
+				    min(sa->util_avg, max), max);
+	}
+
 	return decayed || removed;
 }
 
@@ -2922,29 +2947,6 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 
 	if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
 		update_tg_load_avg(cfs_rq, 0);
-
-	if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) {
-		unsigned long max = rq->cpu_capacity_orig;
-
-		/*
-		 * There are a few boundary cases this might miss but it should
-		 * get called often enough that that should (hopefully) not be
-		 * a real problem -- added to that it only calls on the local
-		 * CPU, so if we enqueue remotely we'll miss an update, but
-		 * the next tick/schedule should update.
-		 *
-		 * It will not get called when we go idle, because the idle
-		 * thread is a different class (!fair), nor will the utilization
-		 * number include things like RT tasks.
-		 *
-		 * As is, the util number is not freq-invariant (we'd have to
-		 * implement arch_scale_freq_capacity() for that).
-		 *
-		 * See cpu_util().
-		 */
-		cpufreq_update_util(rq_clock(rq),
-				    min(cfs_rq->avg.util_avg, max), max);
-	}
 }
 
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)