diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 9fbc54a2585d..83af1f8d8b74 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -454,7 +454,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * Makes rcu_dereference_check() do the dirty work.
  */
 #define rcu_dereference_bh(p) \
-		rcu_dereference_check(p, rcu_read_lock_bh_held())
+		rcu_dereference_check(p, rcu_read_lock_bh_held() || irqs_disabled())
 
 /**
  * rcu_dereference_sched - fetch RCU-protected pointer, checking for RCU-sched
diff --git a/kernel/smp.c b/kernel/smp.c
index 75c970c715d3..ed6aacfcb7ef 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -365,9 +365,10 @@ int smp_call_function_any(const struct cpumask *mask,
 EXPORT_SYMBOL_GPL(smp_call_function_any);
 
 /**
- * __smp_call_function_single(): Run a function on another CPU
+ * __smp_call_function_single(): Run a function on a specific CPU
  * @cpu: The CPU to run on.
  * @data: Pre-allocated and setup data structure
+ * @wait: If true, wait until function has completed on specified CPU.
  *
  * Like smp_call_function_single(), but allow caller to pass in a
  * pre-allocated data structure. Useful for embedding @data inside
@@ -376,8 +377,10 @@ EXPORT_SYMBOL_GPL(smp_call_function_any);
 void __smp_call_function_single(int cpu, struct call_single_data *data,
 				int wait)
 {
-	csd_lock(data);
+	unsigned int this_cpu;
+	unsigned long flags;
 
+	this_cpu = get_cpu();
 	/*
 	 * Can deadlock when called with interrupts disabled.
 	 * We allow cpu's that are not yet online though, as no one else can
@@ -387,7 +390,15 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
 	WARN_ON_ONCE(cpu_online(smp_processor_id()) && wait && irqs_disabled()
 		     && !oops_in_progress);
 
-	generic_exec_single(cpu, data, wait);
+	if (cpu == this_cpu) {
+		local_irq_save(flags);
+		data->func(data->info);
+		local_irq_restore(flags);
+	} else {
+		csd_lock(data);
+		generic_exec_single(cpu, data, wait);
+	}
+	put_cpu();
 }
 
 /**