sched/core: Fix incorrect utilization accounting when switching to fair class

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

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>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 94115453c1c4cdccf65864a6755ba8fdbf8cc795..2b5e150e070b515bd75f9ea9ad382c539b8c4ebb 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1109,10 +1109,10 @@ 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);
 }
 
 /*
@@ -3707,10 +3707,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
        p->prio = prio;
 
-       if (running)
-               p->sched_class->set_curr_task(rq);
        if (queued)
                enqueue_task(rq, p, queue_flag);
+       if (running)
+               p->sched_class->set_curr_task(rq);
 
        check_class_changed(rq, p, prev_class, oldprio);
 out_unlock:
@@ -4263,8 +4263,6 @@ change:
        prev_class = p->sched_class;
        __setscheduler(rq, p, attr, pi);
 
-       if (running)
-               p->sched_class->set_curr_task(rq);
        if (queued) {
                /*
                 * We enqueue to tail when the priority of a task is
@@ -4275,6 +4273,8 @@ change:
 
                enqueue_task(rq, p, queue_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 */
@@ -5439,10 +5439,10 @@ 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, &rf);
 }
 #endif /* CONFIG_NUMA_BALANCING */
@@ -7949,10 +7949,10 @@ 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 | ENQUEUE_MOVE);
+       if (unlikely(running))
+               tsk->sched_class->set_curr_task(rq);
 
        task_rq_unlock(rq, tsk, &rf);
 }