1 files changed, 45 insertions, 6 deletions

diff --git a/kernel/smp.c b/kernel/smp.c
index 4b83cd6815e2..9910744f0856 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -194,23 +194,52 @@ void generic_smp_call_function_interrupt(void)
 	 */
 	list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
 		int refs;
+		void (*func) (void *info);
 
-		if (!cpumask_test_and_clear_cpu(cpu, data->cpumask))
+		/*
+		 * Since we walk the list without any locks, we might
+		 * see an entry that was completed, removed from the
+		 * list and is in the process of being reused.
+		 *
+		 * We must check that the cpu is in the cpumask before
+		 * checking the refs, and both must be set before
+		 * executing the callback on this cpu.
+		 */
+
+		if (!cpumask_test_cpu(cpu, data->cpumask))
 			continue;
 
+		smp_rmb();
+
+		if (atomic_read(&data->refs) == 0)
+			continue;
+
+		func = data->csd.func;			/* for later warn */
 		data->csd.func(data->csd.info);
 
+		/*
+		 * If the cpu mask is not still set then it enabled interrupts,
+		 * we took another smp interrupt, and executed the function
+		 * twice on this cpu.  In theory that copy decremented refs.
+		 */
+		if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) {
+			WARN(1, "%pS enabled interrupts and double executed\n",
+			     func);
+			continue;
+		}
+
 		refs = atomic_dec_return(&data->refs);
 		WARN_ON(refs < 0);
-		if (!refs) {
-			raw_spin_lock(&call_function.lock);
-			list_del_rcu(&data->csd.list);
-			raw_spin_unlock(&call_function.lock);
-		}
 
 		if (refs)
 			continue;
 
+		WARN_ON(!cpumask_empty(data->cpumask));
+
+		raw_spin_lock(&call_function.lock);
+		list_del_rcu(&data->csd.list);
+		raw_spin_unlock(&call_function.lock);
+
 		csd_unlock(&data->csd);
 	}
 
@@ -454,11 +483,21 @@ void smp_call_function_many(const struct cpumask *mask,
 
 	data = &__get_cpu_var(cfd_data);
 	csd_lock(&data->csd);
+	BUG_ON(atomic_read(&data->refs) || !cpumask_empty(data->cpumask));
 
 	data->csd.func = func;
 	data->csd.info = info;
 	cpumask_and(data->cpumask, mask, cpu_online_mask);
 	cpumask_clear_cpu(this_cpu, data->cpumask);
+
+	/*
+	 * To ensure the interrupt handler gets an complete view
+	 * we order the cpumask and refs writes and order the read
+	 * of them in the interrupt handler.  In addition we may
+	 * only clear our own cpu bit from the mask.
+	 */
+	smp_wmb();
+
 	atomic_set(&data->refs, cpumask_weight(data->cpumask));
 
 	raw_spin_lock_irqsave(&call_function.lock, flags);