diff --git a/kernel/cpu.c b/kernel/cpu.c
index 1972b161c61e98fbe3e3ce003744cf1d2e8c5b1c..d46b4dae0ca097130f78ffa39a5aada6931e5a95 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -408,8 +408,10 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	 *
 	 * Wait for the stop thread to go away.
 	 */
-	while (!idle_cpu(cpu))
+	while (!per_cpu(cpu_dead_idle, cpu))
 		cpu_relax();
+	smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */
+	per_cpu(cpu_dead_idle, cpu) = false;
 
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 94b2d7b88a272856bf0f49ac0f0bdce430a5255d..e99e361ade2078b67ac144375025ad9ed7a92cca 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -198,6 +198,8 @@ static void cpuidle_idle_call(void)
 	start_critical_timings();
 }
 
+DEFINE_PER_CPU(bool, cpu_dead_idle);
+
 /*
  * Generic idle loop implementation
  *
@@ -222,8 +224,11 @@ static void cpu_idle_loop(void)
 			check_pgt_cache();
 			rmb();
 
-			if (cpu_is_offline(smp_processor_id()))
+			if (cpu_is_offline(smp_processor_id())) {
+				smp_mb(); /* all activity before dead. */
+				this_cpu_write(cpu_dead_idle, true);
 				arch_cpu_idle_dead();
+			}
 
 			local_irq_disable();
 			arch_cpu_idle_enter();