From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 21 Feb 2017 13:36:23 +0000 (+0100)
Subject: sched/core: Make sched_ttwu_pending() atomic in time
X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=77558e4d01ac0c7fa8cb1af4a61c2ab508d79f30;p=GitHub%2FLineageOS%2Fandroid_kernel_motorola_exynos9610.git

sched/core: Make sched_ttwu_pending() atomic in time

Since all tasks on the wake_list are woken under a single rq->lock
avoid calling update_rq_clock() for each task.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 247d0a0c319e..dead90d680fd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1685,7 +1685,7 @@ static void
 ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		 struct rq_flags *rf)
 {
-	int en_flags = ENQUEUE_WAKEUP;
+	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
 
 	lockdep_assert_held(&rq->lock);
 
@@ -1737,6 +1737,7 @@ void sched_ttwu_pending(void)
 		return;
 
 	rq_lock_irqsave(rq, &rf);
+	update_rq_clock(rq);
 
 	while (llist) {
 		int wake_flags = 0;
@@ -1849,6 +1850,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 #endif
 
 	rq_lock(rq, &rf);
+	update_rq_clock(rq);
 	ttwu_do_activate(rq, p, wake_flags, &rf);
 	rq_unlock(rq, &rf);
 }