diff --git a/include/linux/sched.h b/include/linux/sched.h
index 25c50317ddc1151f9cde194dcbb9897f9534f174..e09dafa6e1493e20a62cf425fae6fb912dfbe30c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1203,6 +1203,7 @@ struct task_struct {
 	int lock_depth;		/* BKL lock depth */
 
 #ifdef CONFIG_SMP
+	struct task_struct *wake_entry;
 	int on_cpu;
 #endif
 	int on_rq;
@@ -2192,7 +2193,7 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
-static inline void scheduler_ipi(void) { }
+void scheduler_ipi(void);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
 static inline void scheduler_ipi(void) { }
diff --git a/init/Kconfig b/init/Kconfig
index 56240e724d9a31dc4ef43647afcf354b8a70f108..32745bfe059e535fdcee3dd8c3fb83ebcdc71637 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -827,6 +827,11 @@ config SCHED_AUTOGROUP
 	  desktop applications.  Task group autogeneration is currently based
 	  upon task session.
 
+config SCHED_TTWU_QUEUE
+	bool
+	depends on !SPARC32
+	default y
+
 config MM_OWNER
 	bool
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 7d8b85fcdf06d69c3a4ab82a84d06ae6b46f1e5b..9e3ede120e81f609da5cc2f94b7cb90e4cb0123f 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -556,6 +556,10 @@ struct rq {
 	unsigned int ttwu_count;
 	unsigned int ttwu_local;
 #endif
+
+#ifdef CONFIG_SMP
+	struct task_struct *wake_list;
+#endif
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -2516,10 +2520,61 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 	return ret;
 }
 
+#ifdef CONFIG_SMP
+static void sched_ttwu_pending(void)
+{
+	struct rq *rq = this_rq();
+	struct task_struct *list = xchg(&rq->wake_list, NULL);
+
+	if (!list)
+		return;
+
+	raw_spin_lock(&rq->lock);
+
+	while (list) {
+		struct task_struct *p = list;
+		list = list->wake_entry;
+		ttwu_do_activate(rq, p, 0);
+	}
+
+	raw_spin_unlock(&rq->lock);
+}
+
+void scheduler_ipi(void)
+{
+	sched_ttwu_pending();
+}
+
+static void ttwu_queue_remote(struct task_struct *p, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	struct task_struct *next = rq->wake_list;
+
+	for (;;) {
+		struct task_struct *old = next;
+
+		p->wake_entry = next;
+		next = cmpxchg(&rq->wake_list, old, p);
+		if (next == old)
+			break;
+	}
+
+	if (!next)
+		smp_send_reschedule(cpu);
+}
+#endif
+
 static void ttwu_queue(struct task_struct *p, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 
+#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_TTWU_QUEUE)
+	if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) {
+		ttwu_queue_remote(p, cpu);
+		return;
+	}
+#endif
+
 	raw_spin_lock(&rq->lock);
 	ttwu_do_activate(rq, p, 0);
 	raw_spin_unlock(&rq->lock);
@@ -6331,6 +6386,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_DYING:
+		sched_ttwu_pending();
 		/* Update our root-domain */
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 68e69acc29b9570b10ecf8a5892ea62c48700c5c..be40f7371ee1ac2e2d91c6679bafbf798606e08e 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -64,3 +64,9 @@ SCHED_FEAT(OWNER_SPIN, 1)
  * Decrement CPU power based on irq activity
  */
 SCHED_FEAT(NONIRQ_POWER, 1)
+
+/*
+ * Queue remote wakeups on the target CPU and process them
+ * using the scheduler IPI. Reduces rq->lock contention/bounces.
+ */
+SCHED_FEAT(TTWU_QUEUE, 1)