sched: wake-balance fixes

We have logic to detect whether the system has migratable tasks, but we are
not using it when deciding whether to push tasks away.  So we add support
for considering this new information.

Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/sched.c

@@ -346,6 +346,7 @@ struct rt_rq {
 	unsigned long rt_nr_migratory;
 	/* highest queued rt task prio */
 	int highest_prio;
+	int overloaded;
 };
 
 /*
@@ -6770,6 +6771,7 @@ void __init sched_init(void)
 		rq->migration_thread = NULL;
 		INIT_LIST_HEAD(&rq->migration_queue);
 		rq->rt.highest_prio = MAX_RT_PRIO;
+		rq->rt.overloaded = 0;
 #endif
 		atomic_set(&rq->nr_iowait, 0);
 

kernel/sched_rt.c

@@ -16,6 +16,7 @@ static inline cpumask_t *rt_overload(void)
 }
 static inline void rt_set_overload(struct rq *rq)
 {
+	rq->rt.overloaded = 1;
 	cpu_set(rq->cpu, rt_overload_mask);
 	/*
 	 * Make sure the mask is visible before we set
@@ -32,6 +33,7 @@ static inline void rt_clear_overload(struct rq *rq)
 	/* the order here really doesn't matter */
 	atomic_dec(&rto_count);
 	cpu_clear(rq->cpu, rt_overload_mask);
+	rq->rt.overloaded = 0;
 }
 
 static void update_rt_migration(struct rq *rq)
@@ -448,6 +450,9 @@ static int push_rt_task(struct rq *rq)
 
 	assert_spin_locked(&rq->lock);
 
+	if (!rq->rt.overloaded)
+		return 0;
+
 	next_task = pick_next_highest_task_rt(rq, -1);
 	if (!next_task)
 		return 0;
@@ -675,7 +680,7 @@ static void schedule_tail_balance_rt(struct rq *rq)
 	 * the lock was owned by prev, we need to release it
 	 * first via finish_lock_switch and then reaquire it here.
 	 */
-	if (unlikely(rq->rt.rt_nr_running > 1)) {
+	if (unlikely(rq->rt.overloaded)) {
 		spin_lock_irq(&rq->lock);
 		push_rt_tasks(rq);
 		spin_unlock_irq(&rq->lock);
@@ -687,7 +692,8 @@ static void wakeup_balance_rt(struct rq *rq, struct task_struct *p)
 {
 	if (unlikely(rt_task(p)) &&
 	    !task_running(rq, p) &&
-	    (p->prio >= rq->curr->prio))
+	    (p->prio >= rq->rt.highest_prio) &&
+	    rq->rt.overloaded)
 		push_rt_tasks(rq);
 }