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 wrong 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 which is : -enqueue a task -then set the task as current task.
This wrong ordering is the root cause of wrong 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 --- kernel/sched/core.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3e52d08..7a9c9b9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1105,10 +1105,10 @@ 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); }
/* @@ -3687,10 +3687,10 @@ 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: @@ -4243,8 +4243,6 @@ static int __sched_setscheduler(struct task_struct *p, 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 @@ -4255,6 +4253,8 @@ static int __sched_setscheduler(struct task_struct *p,
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 */ @@ -5417,10 +5417,10 @@ 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 */ @@ -7868,10 +7868,10 @@ 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); }