diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 495bc41907d6..0daa14cd0d32 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2450,6 +2450,8 @@ void wake_up_new_task(struct task_struct *p)
 	 */
 	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
+	/* Post initialize new task's util average when its cfs_rq is set */
+	post_init_entity_util_avg(&p->se);
 
 	rq = __task_rq_lock(p);
 	walt_mark_task_starting(p);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e77917b23c79..bb43c742a520 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -701,17 +701,81 @@ void init_entity_runnable_average(struct sched_entity *se)
 	sa->period_contrib = 1023;
 	sa->load_avg = scale_load_down(se->load.weight);
 	sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
-	sa->util_avg =  sched_freq() ?
-		sysctl_sched_initial_task_util :
-		scale_load_down(SCHED_LOAD_SCALE);
-	sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
+	/*
+	 * In previous Android versions, we used to have:
+	 * 	sa->util_avg =  sched_freq() ?
+	 * 		sysctl_sched_initial_task_util :
+	 *		scale_load_down(SCHED_LOAD_SCALE);
+	 * 	sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
+	 * However, that functionality has been moved to enqueue.
+	 * It is unclear if we should restore this in enqueue.
+	 */
+	/*
+	 * At this point, util_avg won't be used in select_task_rq_fair anyway
+	 */
+	sa->util_avg = 0;
+	sa->util_sum = 0;
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
 
+/*
+ * With new tasks being created, their initial util_avgs are extrapolated
+ * based on the cfs_rq's current util_avg:
+ *
+ *   util_avg = cfs_rq->util_avg / (cfs_rq->load_avg + 1) * se.load.weight
+ *
+ * However, in many cases, the above util_avg does not give a desired
+ * value. Moreover, the sum of the util_avgs may be divergent, such
+ * as when the series is a harmonic series.
+ *
+ * To solve this problem, we also cap the util_avg of successive tasks to
+ * only 1/2 of the left utilization budget:
+ *
+ *   util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n
+ *
+ * where n denotes the nth task.
+ *
+ * For example, a simplest series from the beginning would be like:
+ *
+ *  task  util_avg: 512, 256, 128,  64,  32,   16,    8, ...
+ * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ...
+ *
+ * Finally, that extrapolated util_avg is clamped to the cap (util_avg_cap)
+ * if util_avg > util_avg_cap.
+ */
+void post_init_entity_util_avg(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	struct sched_avg *sa = &se->avg;
+	long cap = (long)(scale_load_down(SCHED_LOAD_SCALE) - cfs_rq->avg.util_avg) / 2;
+
+	if (cap > 0) {
+		if (cfs_rq->avg.util_avg != 0) {
+			sa->util_avg  = cfs_rq->avg.util_avg * se->load.weight;
+			sa->util_avg /= (cfs_rq->avg.load_avg + 1);
+
+			if (sa->util_avg > cap)
+				sa->util_avg = cap;
+		} else {
+			sa->util_avg = cap;
+		}
+		/*
+		 * If we wish to restore tuning via setting initial util,
+		 * this is where we should do it.
+		 */
+		sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
+	}
+}
+
+static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
+static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
 #else
 void init_entity_runnable_average(struct sched_entity *se)
 {
 }
+void post_init_entity_util_avg(struct sched_entity *se)
+{
+}
 #endif
 
 /*
@@ -9409,6 +9473,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		init_cfs_rq(cfs_rq);
 		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
 		init_entity_runnable_average(se);
+		post_init_entity_util_avg(se);
 	}
 
 	return 1;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2051fecdb9e5..50b9229d47ab 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1391,6 +1391,7 @@ extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
 unsigned long to_ratio(u64 period, u64 runtime);
 
 extern void init_entity_runnable_average(struct sched_entity *se);
+extern void post_init_entity_util_avg(struct sched_entity *se);
 
 static inline void __add_nr_running(struct rq *rq, unsigned count)
 {