rcu: add rcu_barrier_sched() and rcu_barrier_bh()

Add rcu_barrier_sched() and rcu_barrier_bh().  With these in place,
rcutorture no longer gives the occasional oops when repeatedly starting
and stopping torturing rcu_bh.  Also adds the API needed to flush out
pre-existing call_rcu_sched() callbacks.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 411969c..e8b4039 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -246,6 +246,8 @@
 /* Exported common interfaces */
 extern void synchronize_rcu(void);
 extern void rcu_barrier(void);
+extern void rcu_barrier_bh(void);
+extern void rcu_barrier_sched(void);
 
 /* Internal to kernel */
 extern void rcu_init(void);
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index a4e329d..4a74b8d 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -45,6 +45,12 @@
 #include <linux/mutex.h>
 #include <linux/module.h>
 
+enum rcu_barrier {
+	RCU_BARRIER_STD,
+	RCU_BARRIER_BH,
+	RCU_BARRIER_SCHED,
+};
+
 static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
 static atomic_t rcu_barrier_cpu_count;
 static DEFINE_MUTEX(rcu_barrier_mutex);
@@ -83,19 +89,30 @@
 /*
  * Called with preemption disabled, and from cross-cpu IRQ context.
  */
-static void rcu_barrier_func(void *notused)
+static void rcu_barrier_func(void *type)
 {
 	int cpu = smp_processor_id();
 	struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu);
 
 	atomic_inc(&rcu_barrier_cpu_count);
-	call_rcu(head, rcu_barrier_callback);
+	switch ((enum rcu_barrier)type) {
+	case RCU_BARRIER_STD:
+		call_rcu(head, rcu_barrier_callback);
+		break;
+	case RCU_BARRIER_BH:
+		call_rcu_bh(head, rcu_barrier_callback);
+		break;
+	case RCU_BARRIER_SCHED:
+		call_rcu_sched(head, rcu_barrier_callback);
+		break;
+	}
 }
 
-/**
- * rcu_barrier - Wait until all the in-flight RCUs are complete.
+/*
+ * Orchestrate the specified type of RCU barrier, waiting for all
+ * RCU callbacks of the specified type to complete.
  */
-void rcu_barrier(void)
+static void _rcu_barrier(enum rcu_barrier type)
 {
 	BUG_ON(in_interrupt());
 	/* Take cpucontrol mutex to protect against CPU hotplug */
@@ -111,13 +128,39 @@
 	 * until all the callbacks are queued.
 	 */
 	rcu_read_lock();
-	on_each_cpu(rcu_barrier_func, NULL, 0, 1);
+	on_each_cpu(rcu_barrier_func, (void *)type, 0, 1);
 	rcu_read_unlock();
 	wait_for_completion(&rcu_barrier_completion);
 	mutex_unlock(&rcu_barrier_mutex);
 }
+
+/**
+ * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
+ */
+void rcu_barrier(void)
+{
+	_rcu_barrier(RCU_BARRIER_STD);
+}
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
+/**
+ * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
+ */
+void rcu_barrier_bh(void)
+{
+	_rcu_barrier(RCU_BARRIER_BH);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+
+/**
+ * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
+ */
+void rcu_barrier_sched(void)
+{
+	_rcu_barrier(RCU_BARRIER_SCHED);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_sched);
+
 void __init rcu_init(void)
 {
 	__rcu_init();