sched: redundant reschedule when set_user_nice() boosts a prio of a task from the "expired" array

- Make TASK_PREEMPTS_CURR(task, rq) return "true" only if the task's prio
  is higher than the current's one and the task is in the "active" array.
  This ensures we don't make redundant resched_task() calls when the task
  is in the "expired" array (as may happen now in set_user_prio(),
  rt_mutex_setprio() and pull_task() ) ;

- generalise conditions for a call to resched_task() in set_user_nice(),
  rt_mutex_setprio() and sched_setscheduler()

Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Cc: Con Kolivas <kernel@kolivas.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 16 insertions, 18 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index e60786eb731c..be2706c885a7 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -169,7 +169,7 @@ unsigned long long __attribute__((weak)) sched_clock(void)
 		(MAX_BONUS / 2 + DELTA((p)) + 1) / MAX_BONUS - 1))
 
 #define TASK_PREEMPTS_CURR(p, rq) \
-	((p)->prio < (rq)->curr->prio)
+	(((p)->prio < (rq)->curr->prio) && ((p)->array == (rq)->active))
 
 #define SCALE_PRIO(x, prio) \
 	max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_TIMESLICE)
@@ -4076,13 +4076,13 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	struct prio_array *array;
 	unsigned long flags;
 	struct rq *rq;
-	int oldprio;
+	int delta;
 
 	BUG_ON(prio < 0 || prio > MAX_PRIO);
 
 	rq = task_rq_lock(p, &flags);
 
-	oldprio = p->prio;
+	delta = prio - p->prio;
 	array = p->array;
 	if (array)
 		dequeue_task(p, array);
@@ -4098,13 +4098,11 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		enqueue_task(p, array);
 		/*
 		 * Reschedule if we are currently running on this runqueue and
-		 * our priority decreased, or if we are not currently running on
-		 * this runqueue and our priority is higher than the current's
+		 * our priority decreased, or if our priority became higher
+		 * than the current's.
 		 */
-		if (task_running(rq, p)) {
-			if (p->prio > oldprio)
-				resched_task(rq->curr);
-		} else if (TASK_PREEMPTS_CURR(p, rq))
+		if (TASK_PREEMPTS_CURR(p, rq) ||
+				(delta > 0 && task_running(rq, p)))
 			resched_task(rq->curr);
 	}
 	task_rq_unlock(rq, &flags);
@@ -4152,10 +4150,12 @@ void set_user_nice(struct task_struct *p, long nice)
 		enqueue_task(p, array);
 		inc_raw_weighted_load(rq, p);
 		/*
-		 * If the task increased its priority or is running and
-		 * lowered its priority, then reschedule its CPU:
+		 * Reschedule if we are currently running on this runqueue and
+		 * our priority decreased, or if our priority became higher
+		 * than the current's.
 		 */
-		if (delta < 0 || (delta > 0 && task_running(rq, p)))
+		if (TASK_PREEMPTS_CURR(p, rq) ||
+				(delta > 0 && task_running(rq, p)))
 			resched_task(rq->curr);
 	}
 out_unlock:
@@ -4382,13 +4382,11 @@ recheck:
 		__activate_task(p, rq);
 		/*
 		 * Reschedule if we are currently running on this runqueue and
-		 * our priority decreased, or if we are not currently running on
-		 * this runqueue and our priority is higher than the current's
+		 * our priority decreased, or our priority became higher
+		 * than the current's.
 		 */
-		if (task_running(rq, p)) {
-			if (p->prio > oldprio)
-				resched_task(rq->curr);
-		} else if (TASK_PREEMPTS_CURR(p, rq))
+		if (TASK_PREEMPTS_CURR(p, rq) ||
+				(task_running(rq, p) && p->prio > oldprio))
 			resched_task(rq->curr);
 	}
 	__task_rq_unlock(rq);