diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c5f020c601b2..ff4e3c066dc2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1063,8 +1063,12 @@ static int migration_cpu_stop(void *data)
 	 * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
 	 * we're holding p->pi_lock.
 	 */
-	if (task_rq(p) == rq && task_on_rq_queued(p))
-		rq = __migrate_task(rq, p, arg->dest_cpu);
+	if (task_rq(p) == rq) {
+		if (task_on_rq_queued(p))
+			rq = __migrate_task(rq, p, arg->dest_cpu);
+		else
+			p->wake_cpu = arg->dest_cpu;
+	}
 	raw_spin_unlock(&rq->lock);
 	raw_spin_unlock(&p->pi_lock);
 
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 4a1ca5f6da7e..082e71f17a58 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -126,6 +126,11 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
 	cpu_stop_init_done(&done, 1);
 	if (!cpu_stop_queue_work(cpu, &work))
 		return -ENOENT;
+	/*
+	 * In case @cpu == smp_proccessor_id() we can avoid a sleep+wakeup
+	 * cycle by doing a preemption:
+	 */
+	cond_resched();
 	wait_for_completion(&done.completion);
 	return done.ret;
 }