1 files changed, 52 insertions, 10 deletions

diff --git a/kernel/smp.c b/kernel/smp.c
index 4ec30e0..9910744 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);
 	}
 
@@ -430,7 +459,7 @@ void smp_call_function_many(const struct cpumask *mask,
 	 * can't happen.
 	 */
 	WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
-		     && !oops_in_progress);
+		     && !oops_in_progress && !early_boot_irqs_disabled);
 
 	/* So, what's a CPU they want? Ignoring this one. */
 	cpu = cpumask_first_and(mask, cpu_online_mask);
@@ -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);
@@ -533,17 +572,20 @@ void ipi_call_unlock_irq(void)
 #endif /* USE_GENERIC_SMP_HELPERS */
 
 /*
- * Call a function on all processors
+ * Call a function on all processors.  May be used during early boot while
+ * early_boot_irqs_disabled is set.  Use local_irq_save/restore() instead
+ * of local_irq_disable/enable().
  */
 int on_each_cpu(void (*func) (void *info), void *info, int wait)
 {
+	unsigned long flags;
 	int ret = 0;
 
 	preempt_disable();
 	ret = smp_call_function(func, info, wait);
-	local_irq_disable();
+	local_irq_save(flags);
 	func(info);
-	local_irq_enable();
+	local_irq_restore(flags);
 	preempt_enable();
 	return ret;
 }