sched/core: Fix incorrect utilization accounting when switching to fair classsched-fix-util-accounting-switch-to-fair

[ Upstream commit a399d233078edbba7cf7902a6d080100cdf75636 ]

When a task switches to fair scheduling class, the period between now
and the last update of its utilization is accounted as running time
whatever happened during this period. This incorrect accounting applies
to the task and also to the task group branch.

When changing the property of a running task like its list of allowed
CPUs or its scheduling class, we follow the sequence:

 - dequeue task
 - put task
 - change the property
 - set task as current task
 - enqueue task

The end of the sequence doesn't follow the normal sequence (as per
__schedule()) which is:

 - enqueue a task
 - then set the task as current task.

This incorrectordering is the root cause of incorrect utilization accounting.
Update the sequence to follow the right one:

 - dequeue task
 - put task
 - change the property
 - enqueue task
 - set task as current task

Change-Id: I91975778f6775061c53a039cfae8723ba02dbc0e
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Cc: dietmar.eggemann@arm.com
Cc: linaro-kernel@lists.linaro.org
Cc: pjt@google.com
Cc: yuyang.du@intel.com
Link: http://lkml.kernel.org/r/1473666472-13749-8-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 10 insertions, 10 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9a0c1841993f..8e8134312ecc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1212,10 +1212,10 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 
 	p->sched_class->set_cpus_allowed(p, new_mask);
 
-	if (running)
-		p->sched_class->set_curr_task(rq);
 	if (queued)
 		enqueue_task(rq, p, ENQUEUE_RESTORE);
+	if (running)
+		p->sched_class->set_curr_task(rq);
 }
 
 /*
@@ -3585,10 +3585,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	p->prio = prio;
 
+	if (queued)
+		enqueue_task(rq, p, queue_flag);
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (queued)
-		enqueue_task(rq, p, enqueue_flag);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 out_unlock:
@@ -4147,8 +4147,6 @@ change:
 	prev_class = p->sched_class;
 	__setscheduler(rq, p, attr, pi);
 
-	if (running)
-		p->sched_class->set_curr_task(rq);
 	if (queued) {
 		int enqueue_flags = ENQUEUE_RESTORE;
 		/*
@@ -4160,6 +4158,8 @@ change:
 
 		enqueue_task(rq, p, enqueue_flags);
 	}
+	if (running)
+		p->sched_class->set_curr_task(rq);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 	preempt_disable(); /* avoid rq from going away on us */
@@ -5317,10 +5317,10 @@ void sched_setnuma(struct task_struct *p, int nid)
 
 	p->numa_preferred_nid = nid;
 
-	if (running)
-		p->sched_class->set_curr_task(rq);
 	if (queued)
 		enqueue_task(rq, p, ENQUEUE_RESTORE);
+	if (running)
+		p->sched_class->set_curr_task(rq);
 	task_rq_unlock(rq, p, &flags);
 }
 #endif /* CONFIG_NUMA_BALANCING */
@@ -8207,10 +8207,10 @@ void sched_move_task(struct task_struct *tsk)
 
 	sched_change_group(tsk, TASK_MOVE_GROUP);
 
-	if (unlikely(running))
-		tsk->sched_class->set_curr_task(rq);
 	if (queued)
 		enqueue_task(rq, tsk, ENQUEUE_RESTORE);
+	if (unlikely(running))
+		tsk->sched_class->set_curr_task(rq);
 
 	task_rq_unlock(rq, tsk, &flags);
 }