diff --git a/kernel/smp.c b/kernel/smp.c
index 7c6ded5effd9616dfcbaffcd7a46877712a2900f..954548906afbe870e979eb350253e05a4bd04fd8 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -450,7 +450,7 @@ void smp_call_function_many(const struct cpumask *mask,
 {
 	struct call_function_data *data;
 	unsigned long flags;
-	int cpu, next_cpu, this_cpu = smp_processor_id();
+	int refs, cpu, next_cpu, this_cpu = smp_processor_id();
 
 	/*
 	 * Can deadlock when called with interrupts disabled.
@@ -461,7 +461,7 @@ void smp_call_function_many(const struct cpumask *mask,
 	WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
 		     && !oops_in_progress && !early_boot_irqs_disabled);
 
-	/* So, what's a CPU they want? Ignoring this one. */
+	/* Try to fastpath.  So, what's a CPU they want? Ignoring this one. */
 	cpu = cpumask_first_and(mask, cpu_online_mask);
 	if (cpu == this_cpu)
 		cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
@@ -519,6 +519,13 @@ void smp_call_function_many(const struct cpumask *mask,
 	/* We rely on the "and" being processed before the store */
 	cpumask_and(data->cpumask, mask, cpu_online_mask);
 	cpumask_clear_cpu(this_cpu, data->cpumask);
+	refs = cpumask_weight(data->cpumask);
+
+	/* Some callers race with other cpus changing the passed mask */
+	if (unlikely(!refs)) {
+		csd_unlock(&data->csd);
+		return;
+	}
 
 	raw_spin_lock_irqsave(&call_function.lock, flags);
 	/*
@@ -532,7 +539,7 @@ void smp_call_function_many(const struct cpumask *mask,
 	 * to the cpumask before this write to refs, which indicates
 	 * data is on the list and is ready to be processed.
 	 */
-	atomic_set(&data->refs, cpumask_weight(data->cpumask));
+	atomic_set(&data->refs, refs);
 	raw_spin_unlock_irqrestore(&call_function.lock, flags);
 
 	/*