rcu: Permit rt_mutex_unlock() with irqs disabled

Create a separate lockdep class for the rt_mutex used for RCU priority
boosting and enable use of rt_mutex_lock() with irqs disabled.  This
prevents RCU priority boosting from falling prey to deadlocks when
someone begins an RCU read-side critical section in preemptible state,
but releases it with an irq-disabled lock held.

Unfortunately, the scheduler's runqueue and priority-inheritance locks
still must either completely enclose or be completely enclosed by any
overlapping RCU read-side critical section.

This version removes a redundant local_irq_restore() noted by
Yong Zhang.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcutree_plugin.h

@@ -1149,6 +1149,8 @@ static void rcu_initiate_boost_trace(struct rcu_node *rnp)
 
 #endif /* #else #ifdef CONFIG_RCU_TRACE */
 
+static struct lock_class_key rcu_boost_class;
+
 /*
  * Carry out RCU priority boosting on the task indicated by ->exp_tasks
  * or ->boost_tasks, advancing the pointer to the next task in the
@@ -1211,6 +1213,9 @@ static int rcu_boost(struct rcu_node *rnp)
 	 */
 	t = container_of(tb, struct task_struct, rcu_node_entry);
 	rt_mutex_init_proxy_locked(&mtx, t);
+	/* Avoid lockdep false positives.  This rt_mutex is its own thing. */
+	lockdep_set_class_and_name(&mtx.wait_lock, &rcu_boost_class,
+				   "rcu_boost_mutex");
 	t->rcu_boost_mutex = &mtx;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	rt_mutex_lock(&mtx);  /* Side effect: boosts task t's priority. */

kernel/rtmutex.c

@@ -579,6 +579,7 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		    struct rt_mutex_waiter *waiter)
 {
 	int ret = 0;
+	int was_disabled;
 
 	for (;;) {
 		/* Try to acquire the lock: */
@@ -601,10 +602,17 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 
 		raw_spin_unlock(&lock->wait_lock);
 
+		was_disabled = irqs_disabled();
+		if (was_disabled)
+			local_irq_enable();
+
 		debug_rt_mutex_print_deadlock(waiter);
 
 		schedule_rt_mutex(lock);
 
+		if (was_disabled)
+			local_irq_disable();
+
 		raw_spin_lock(&lock->wait_lock);
 		set_current_state(state);
 	}