diff --git a/arch/x86/kernel/smp_32.c b/arch/x86/kernel/smp_32.c
index dc0cde9d16fb38088587b664f02b91f878176628..e4a6b669a0b824fbceb82169aba5535f02eab57a 100644
--- a/arch/x86/kernel/smp_32.c
+++ b/arch/x86/kernel/smp_32.c
@@ -583,7 +583,7 @@ native_smp_call_function_mask(cpumask_t mask,
 		atomic_set(&data.finished, 0);
 
 	call_data = &data;
-	mb();
+	wmb();
 
 	/* Send a message to other CPUs */
 	if (cpus_equal(mask, allbutself))
diff --git a/arch/x86/kernel/smp_64.c b/arch/x86/kernel/smp_64.c
index aa2edb7f3a5147de61bf9ca0dad6719d90609908..e4494e829dfadb39f87c8f7f728c76b93358bcf5 100644
--- a/arch/x86/kernel/smp_64.c
+++ b/arch/x86/kernel/smp_64.c
@@ -354,26 +354,30 @@ static void __smp_call_function(void (*func) (void *info), void *info,
 }
 
 
-/*
- * this function sends a 'generic call function' IPI to all other CPU
- * of the system defined in the mask.
- */
-static int __smp_call_function_mask(cpumask_t mask,
-				    void (*func)(void *), void *info,
-				    int wait)
+int native_smp_call_function_mask(cpumask_t mask,
+				  void (*func)(void *), void *info,
+				  int wait)
 {
 	struct call_data_struct data;
 	cpumask_t allbutself;
 	int cpus;
 
+	/* Can deadlock when called with interrupts disabled */
+	WARN_ON(irqs_disabled());
+
+	/* Holding any lock stops cpus from going down. */
+	spin_lock(&call_lock);
+
 	allbutself = cpu_online_map;
 	cpu_clear(smp_processor_id(), allbutself);
 
 	cpus_and(mask, mask, allbutself);
 	cpus = cpus_weight(mask);
 
-	if (!cpus)
+	if (!cpus) {
+		spin_unlock(&call_lock);
 		return 0;
+	}
 
 	data.func = func;
 	data.info = info;
@@ -395,43 +399,14 @@ static int __smp_call_function_mask(cpumask_t mask,
 	while (atomic_read(&data.started) != cpus)
 		cpu_relax();
 
-	if (!wait)
-		return 0;
+	if (wait)
+		 while (atomic_read(&data.finished) != cpus)
+			cpu_relax();
 
-	while (atomic_read(&data.finished) != cpus)
-		cpu_relax();
+	spin_unlock(&call_lock);
 
 	return 0;
 }
-/**
- * smp_call_function_mask(): Run a function on a set of other CPUs.
- * @mask: The set of cpus to run on.  Must not include the current cpu.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
- *
- * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-int native_smp_call_function_mask(cpumask_t mask,
-				  void (*func)(void *), void *info,
-				  int wait)
-{
-	int ret;
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	spin_lock(&call_lock);
-	ret = __smp_call_function_mask(mask, func, info, wait);
-	spin_unlock(&call_lock);
-	return ret;
-}
 
 static void stop_this_cpu(void *dummy)
 {