diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 929739a653d1..3d17bc7f06e6 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -248,6 +248,25 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 	unsigned long flags;
 	int cpu;
 
+#ifdef CONFIG_SMP
+	/*
+	 * If this cpu is not yet active, we are in the cpu online path. There
+	 * can be no stop_machine() in parallel, as stop machine ensures this
+	 * by using get_online_cpus(). We can skip taking the stop_cpus_mutex,
+	 * as we don't need it and also we can't afford to block while waiting
+	 * for the mutex.
+	 *
+	 * If this cpu is active, we need to prevent stop_machine() happening
+	 * in parallel by taking the stop cpus mutex.
+	 *
+	 * Also, this is called in the context of cpu online path or in the
+	 * context where cpu hotplug is prevented. So checking the active status
+	 * of the raw_smp_processor_id() is safe.
+	 */
+	if (cpu_active(raw_smp_processor_id()))
+		mutex_lock(&stop_cpus_mutex);
+#endif
+
 	preempt_disable();
 
 	data.smp_reg = reg;
@@ -330,6 +349,10 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 
 	local_irq_restore(flags);
 	preempt_enable();
+#ifdef CONFIG_SMP
+	if (cpu_active(raw_smp_processor_id()))
+		mutex_unlock(&stop_cpus_mutex);
+#endif
 }
 
 /**
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 092dc9b1ce7d..14d3524d1274 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -27,6 +27,8 @@ struct cpu_stop_work {
 	struct cpu_stop_done	*done;
 };
 
+extern struct mutex stop_cpus_mutex;
+
 int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
 void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			 struct cpu_stop_work *work_buf);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index e3516b29076c..0cae1cc323dc 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -132,8 +132,8 @@ void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 	cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), work_buf);
 }
 
+DEFINE_MUTEX(stop_cpus_mutex);
 /* static data for stop_cpus */
-static DEFINE_MUTEX(stop_cpus_mutex);
 static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work);
 
 int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)