[RFC][PATCH 3/4] sched: Change sched_class::set_cpus_allowed calling context

[Peter Zijlstra]

Change the calling context of sched_class::set_cpus_allowed() such
that we can assume the task is inactive.

This allows us to easily make changes that affect accounting done by
enqueue/dequeue. This does in fact completely remove
set_cpus_allowed_rt and greatly reduces set_cpus_allowed_dl.


Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 kernel/sched/core.c     |   23 +++++++++++++++++++++++
 kernel/sched/deadline.c |   39 ++-------------------------------------
 kernel/sched/rt.c       |   45 +--------------------------------------------
 3 files changed, 26 insertions(+), 81 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4803,8 +4803,31 @@ void set_cpus_allowed_common(struct task
 
 void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
+	struct rq *rq = task_rq(p);
+	bool queued, running;
+
 	lockdep_assert_held(&p->pi_lock);
+
+	queued = task_on_rq_queued(p);
+	running = task_current(rq, p);
+
+	if (queued) {
+		/*
+		 * Because __kthread_bind() calls this on blocked tasks without
+		 * holding rq->lock.
+		 */
+		lockdep_assert_held(&rq->lock);
+		dequeue_task(rq, p, 0);
+	}
+	if (running)
+		put_prev_task(rq, p);
+
 	p->sched_class->set_cpus_allowed(p, new_mask);
+
+	if (running)
+		p->sched_class->set_curr_task(rq);
+	if (queued)
+		enqueue_task(rq, p, 0);
 }
 
 /*
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1569,9 +1569,8 @@ static void task_woken_dl(struct rq *rq,
 static void set_cpus_allowed_dl(struct task_struct *p,
 				const struct cpumask *new_mask)
 {
-	struct rq *rq;
 	struct root_domain *src_rd;
-	int weight;
+	struct rq *rq;
 
 	BUG_ON(!dl_task(p));
 
@@ -1597,41 +1596,7 @@ static void set_cpus_allowed_dl(struct t
 		raw_spin_unlock(&src_dl_b->lock);
 	}
 
-	weight = cpumask_weight(new_mask);
-
-	/*
-	 * Only update if the process changes its state from whether it
-	 * can migrate or not.
-	 */
-	if ((p->nr_cpus_allowed > 1) == (weight > 1))
-		goto done;
-
-	/*
-	 * Update only if the task is actually running (i.e.,
-	 * it is on the rq AND it is not throttled).
-	 */
-	if (!on_dl_rq(&p->dl))
-		goto done;
-
-	/*
-	 * The process used to be able to migrate OR it can now migrate
-	 */
-	if (weight <= 1) {
-		if (!task_current(rq, p))
-			dequeue_pushable_dl_task(rq, p);
-		BUG_ON(!rq->dl.dl_nr_migratory);
-		rq->dl.dl_nr_migratory--;
-	} else {
-		if (!task_current(rq, p))
-			enqueue_pushable_dl_task(rq, p);
-		rq->dl.dl_nr_migratory++;
-	}
-
-	update_dl_migration(&rq->dl);
-
-done:
-	cpumask_copy(&p->cpus_allowed, new_mask);
-	p->nr_cpus_allowed = weight;
+	set_cpus_allowed_common(p, new_mask);
 }
 
 /* Assumes rq->lock is held */
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2057,49 +2057,6 @@ static void task_woken_rt(struct rq *rq,
 		push_rt_tasks(rq);
 }
 
-static void set_cpus_allowed_rt(struct task_struct *p,
-				const struct cpumask *new_mask)
-{
-	struct rq *rq;
-	int weight;
-
-	BUG_ON(!rt_task(p));
-
-	weight = cpumask_weight(new_mask);
-
-	/*
-	 * Only update if the process changes its state from whether it
-	 * can migrate or not.
-	 */
-	if ((p->nr_cpus_allowed > 1) == (weight > 1))
-		goto done;
-
-	if (!task_on_rq_queued(p))
-		goto done;
-
-	rq = task_rq(p);
-
-	/*
-	 * The process used to be able to migrate OR it can now migrate
-	 */
-	if (weight <= 1) {
-		if (!task_current(rq, p))
-			dequeue_pushable_task(rq, p);
-		BUG_ON(!rq->rt.rt_nr_migratory);
-		rq->rt.rt_nr_migratory--;
-	} else {
-		if (!task_current(rq, p))
-			enqueue_pushable_task(rq, p);
-		rq->rt.rt_nr_migratory++;
-	}
-
-	update_rt_migration(&rq->rt);
-
-done:
-	cpumask_copy(&p->cpus_allowed, new_mask);
-	p->nr_cpus_allowed = weight;
-}
-
 /* Assumes rq->lock is held */
 static void rq_online_rt(struct rq *rq)
 {
@@ -2313,7 +2270,7 @@ const struct sched_class rt_sched_class
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_rt,
 
-	.set_cpus_allowed       = set_cpus_allowed_rt,
+	.set_cpus_allowed       = set_cpus_allowed_common,
 	.rq_online              = rq_online_rt,
 	.rq_offline             = rq_offline_rt,
 	.post_schedule		= post_schedule_rt,


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/