diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4b4cc633b..e50a70f45 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -541,6 +541,7 @@ struct sched_entity {
 	struct rb_node			run_node;
 	struct list_head		group_node;
 	unsigned int			on_rq;
+	unsigned int			migrated;

 	u64				exec_start;
 	u64				sum_exec_runtime;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2f461f059..b586c6e84 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1004,6 +1004,7 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	/*
 	 * We are starting a new run period:
 	 */
+	se->migrated = 0;
 	se->exec_start = rq_clock_task(rq_of(cfs_rq));
 }

@@ -4190,17 +4191,18 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
 	u64 vruntime = cfs_rq->min_vruntime;

-	/*
-	 * The 'current' period is already promised to the current tasks,
-	 * however the extra weight of the new task will slow them down a
-	 * little, place the new task so that it fits in the slot that
-	 * stays open at the end.
-	 */
-	if (initial && sched_feat(START_DEBIT))
-		vruntime += sched_vslice(cfs_rq, se);
+	if (unlikely(initial)) { /* task creation is once, wakeup is often */
+		/*
+		 * The 'current' period is already promised to the current
+		 * tasks, however the extra weight of the new task will slow
+		 * them down a little, place the new task so that it fits in
+		 * the slot that stays open at the end.
+		 */
+		if (sched_feat(START_DEBIT))
+			vruntime += sched_vslice(cfs_rq, se);

-	/* sleeps up to a single latency don't count. */
-	if (!initial) {
+	} else {
+		/* sleeps up to a single latency don't count. */
 		unsigned long thresh;

 		if (se_is_idle(se))
@@ -4221,6 +4223,27 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 	/* ensure we never gain time by being placed backwards. */
 	se->vruntime = max_vruntime(se->vruntime, vruntime);
 }
+
+static void place_entity_migrate(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	if (!sched_feat(PLACE_MIGRATE))
+		return;
+
+	if (cfs_rq->nr_running < se->migrated) {
+		/*
+		 * Migrated to a shorter runqueue, go first because
+		 * we were under-served on the old runqueue.
+		 */
+		se->vruntime = cfs_rq->min_vruntime;
+		return;
+	}
+
+	/*
+	 * Migrated to a longer runqueue, go last because
+	 * we got over-served on the old runqueue.
+	 */
+	se->vruntime = cfs_rq->min_vruntime + sched_vslice(cfs_rq, se);
+}

 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);

@@ -4295,6 +4318,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)

 	if (flags & ENQUEUE_WAKEUP)
 		place_entity(cfs_rq, se, 0);
+	else if (se->migrated)
+		place_entity_migrate(cfs_rq, se);

 	check_schedstat_required();
 	update_stats_enqueue_fair(cfs_rq, se, flags);
@@ -6929,6 +6954,7 @@ static void detach_entity_cfs_rq(struct sched_entity *se);
  */
 static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 {
+	struct sched_entity *se = &p->se;
 	/*
 	 * As blocked tasks retain absolute vruntime the migration needs to
 	 * deal with this by subtracting the old and adding the new
@@ -6936,7 +6962,6 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 	 * the task on the new runqueue.
 	 */
 	if (READ_ONCE(p->__state) == TASK_WAKING) {
-		struct sched_entity *se = &p->se;
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 		u64 min_vruntime;

@@ -6961,7 +6986,7 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 		 * rq->lock and can modify state directly.
 		 */
 		lockdep_assert_rq_held(task_rq(p));
-		detach_entity_cfs_rq(&p->se);
+		detach_entity_cfs_rq(se);

 	} else {
 		/*
@@ -6972,14 +6997,15 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 		 * wakee task is less decayed, but giving the wakee more load
 		 * sounds not bad.
 		 */
-		remove_entity_load_avg(&p->se);
+		remove_entity_load_avg(se);
 	}

 	/* Tell new CPU we are migrated */
-	p->se.avg.last_update_time = 0;
+	se->avg.last_update_time = 0;

 	/* We have migrated, no longer consider this task hot */
-	p->se.exec_start = 0;
+	for_each_sched_entity(se)
+		se->migrated = READ_ONCE(cfs_rq_of(se)->nr_running) + !se->on_rq;

 	update_scan_period(p, new_cpu);
 }
@@ -7665,6 +7691,9 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
 	if (sysctl_sched_migration_cost == 0)
 		return 0;

+	if (p->se.migrated)
+		return 0;
+
 	delta = rq_clock_task(env->src_rq) - p->se.exec_start;

 	return delta < (s64)sysctl_sched_migration_cost;
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 1cf435bbc..cfff560e0 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -100,3 +100,5 @@ SCHED_FEAT(LATENCY_WARN, false)

 SCHED_FEAT(ALT_PERIOD, true)
 SCHED_FEAT(BASE_SLICE, true)
+
+SCHED_FEAT(PLACE_MIGRATE, true)
\ No newline at end of file
--
2.30.2