sched: Guarantee task priority in pick_next_task()

Michael spotted that the idle_balance() push down created a task
priority problem.

Previously, when we called idle_balance() before pick_next_task() it
wasn't a problem when -- because of the rq->lock droppage -- an rt/dl
task slipped in.

Similarly for pre_schedule(), rt pre-schedule could have a dl task
slip in.

But by pulling it into the pick_next_task() loop, we'll not try a
higher task priority again.

Cure this by creating a re-start condition in pick_next_task(); and
triggering this from pick_next_task_{rt,fair}().

It also fixes a live-lock where we get stuck in pick_next_task_fair()
due to idle_balance() seeing !0 nr_running but there not actually
being any fair tasks about.
Reported-by: Michael Wang <wangyun@linux.vnet.ibm.com>
Fixes: 38033c37 ("sched: Push down pre_schedule() and idle_balance()")
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20140224121218.GR15586@twins.programming.kicks-ass.netSigned-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/core.c

@@ -2586,24 +2586,28 @@ static inline void schedule_debug(struct task_struct *prev)
 static inline struct task_struct *
 pick_next_task(struct rq *rq, struct task_struct *prev)
 {
-	const struct sched_class *class;
+	const struct sched_class *class = &fair_sched_class;
 	struct task_struct *p;
 
 	/*
 	 * Optimization: we know that if all tasks are in
 	 * the fair class we can call that function directly:
 	 */
-	if (likely(prev->sched_class == &fair_sched_class &&
+	if (likely(prev->sched_class == class &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
 		p = fair_sched_class.pick_next_task(rq, prev);
-		if (likely(p))
+		if (likely(p && p != RETRY_TASK))
 			return p;
 	}
 
+again:
 	for_each_class(class) {
 		p = class->pick_next_task(rq, prev);
-		if (p)
+		if (p) {
+			if (unlikely(p == RETRY_TASK))
+				goto again;
 			return p;
+		}
 	}
 
 	BUG(); /* the idle class will always have a runnable task */

kernel/sched/fair.c

@@ -4686,6 +4686,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev)
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
 	struct task_struct *p;
+	int new_tasks;
 
 again:
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -4784,7 +4785,17 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev)
 	return p;
 
 idle:
-	if (idle_balance(rq)) /* drops rq->lock */
+	/*
+	 * Because idle_balance() releases (and re-acquires) rq->lock, it is
+	 * possible for any higher priority task to appear. In that case we
+	 * must re-start the pick_next_entity() loop.
+	 */
+	new_tasks = idle_balance(rq);
+
+	if (rq->nr_running != rq->cfs.h_nr_running)
+		return RETRY_TASK;
+
+	if (new_tasks)
 		goto again;
 
 	return NULL;

kernel/sched/rt.c

@@ -1360,8 +1360,16 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev)
 	struct task_struct *p;
 	struct rt_rq *rt_rq = &rq->rt;
 
-	if (need_pull_rt_task(rq, prev))
+	if (need_pull_rt_task(rq, prev)) {
 		pull_rt_task(rq);
+		/*
+		 * pull_rt_task() can drop (and re-acquire) rq->lock; this
+		 * means a dl task can slip in, in which case we need to
+		 * re-start task selection.
+		 */
+		if (unlikely(rq->dl.dl_nr_running))
+			return RETRY_TASK;
+	}
 
 	if (!rt_rq->rt_nr_running)
 		return NULL;

kernel/sched/sched.h

@@ -1091,6 +1091,8 @@ static const u32 prio_to_wmult[40] = {
 
 #define DEQUEUE_SLEEP		1
 
+#define RETRY_TASK		((void *)-1UL)
+
 struct sched_class {
 	const struct sched_class *next;
 
@@ -1105,6 +1107,9 @@ struct sched_class {
 	 * It is the responsibility of the pick_next_task() method that will
 	 * return the next task to call put_prev_task() on the @prev task or
 	 * something equivalent.
+	 *
+	 * May return RETRY_TASK when it finds a higher prio class has runnable
+	 * tasks.
 	 */
 	struct task_struct * (*pick_next_task) (struct rq *rq,
 						struct task_struct *prev);