diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 903c9ee1db4529..6130ab170e9331 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2312,7 +2312,13 @@ static void wake_csd_func(void *info)
 	sched_ttwu_pending();
 }
 
-static void __ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
+/*
+ * Queue a task on the target CPUs wake_list and wake the CPU via IPI if
+ * necessary. The wakee CPU on receipt of the IPI will queue the task
+ * via sched_ttwu_wakeup() for activation so the wakee incurs the cost
+ * of the wakeup instead of the waker.
+ */
+static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 {
 	struct rq *rq = cpu_rq(cpu);
 
@@ -2355,11 +2361,32 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
 
-static bool ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
+static inline bool ttwu_queue_cond(int cpu, int wake_flags)
+{
+	/*
+	 * If the CPU does not share cache, then queue the task on the
+	 * remote rqs wakelist to avoid accessing remote data.
+	 */
+	if (!cpus_share_cache(smp_processor_id(), cpu))
+		return true;
+
+	/*
+	 * If the task is descheduling and the only running task on the
+	 * CPU then use the wakelist to offload the task activation to
+	 * the soon-to-be-idle CPU as the current CPU is likely busy.
+	 * nr_running is checked to avoid unnecessary task stacking.
+	 */
+	if ((wake_flags & WF_ON_RQ) && cpu_rq(cpu)->nr_running <= 1)
+		return true;
+
+	return false;
+}
+
+static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 {
-	if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
+	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
 		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
-		__ttwu_queue_remote(p, cpu, wake_flags);
+		__ttwu_queue_wakelist(p, cpu, wake_flags);
 		return true;
 	}
 
@@ -2373,7 +2400,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 	struct rq_flags rf;
 
 #if defined(CONFIG_SMP)
-	if (ttwu_queue_remote(p, cpu, wake_flags))
+	if (ttwu_queue_wakelist(p, cpu, wake_flags))
 		return;
 #endif
 
@@ -2593,7 +2620,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * let the waker make forward progress. This is safe because IRQs are
 	 * disabled and the IPI will deliver after on_cpu is cleared.
 	 */
-	if (READ_ONCE(p->on_cpu) && ttwu_queue_remote(p, cpu, wake_flags))
+	if (READ_ONCE(p->on_cpu) && ttwu_queue_wakelist(p, cpu, wake_flags | WF_ON_RQ))
 		goto unlock;
 
 	/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f7ab6334e9922b..4b32cff0dcbe9b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1685,7 +1685,8 @@ static inline int task_on_rq_migrating(struct task_struct *p)
  */
 #define WF_SYNC			0x01		/* Waker goes to sleep after wakeup */
 #define WF_FORK			0x02		/* Child wakeup after fork */
-#define WF_MIGRATED		0x4		/* Internal use, task got migrated */
+#define WF_MIGRATED		0x04		/* Internal use, task got migrated */
+#define WF_ON_RQ		0x08		/* Wakee is on_rq */
 
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution