sched: Rework CPU hotplug task selection

The CPU hotplug task selection is the only place where we used
put_prev_task() on a task that is not current. While looking at that,
it occured to me that we can simplify all that by by using a custom
pick loop.

Since we don't need to put current, we can do away with the fake task
too.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Aaron Lu <aaron.lwe@gmail.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: mingo@kernel.org
Cc: Phil Auld <pauld@redhat.com>
Cc: Julien Desfossez <jdesfossez@digitalocean.com>
Cc: Nishanth Aravamudan <naravamudan@digitalocean.com>

2 files changed, 15 insertions, 18 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9a821ff68502..364b6d7da2be 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6082,21 +6082,22 @@ static void calc_load_migrate(struct rq *rq)
 		atomic_long_add(delta, &calc_load_tasks);
 }
 
-static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
+static struct task_struct *__pick_migrate_task(struct rq *rq)
 {
-}
+	const struct sched_class *class;
+	struct task_struct *next;
 
-static const struct sched_class fake_sched_class = {
-	.put_prev_task = put_prev_task_fake,
-};
+	for_each_class(class) {
+		next = class->pick_next_task(rq, NULL, NULL);
+		if (next) {
+			next->sched_class->put_prev_task(rq, next);
+			return next;
+		}
+	}
 
-static struct task_struct fake_task = {
-	/*
-	 * Avoid pull_{rt,dl}_task()
-	 */
-	.prio = MAX_PRIO + 1,
-	.sched_class = &fake_sched_class,
-};
+	/* The idle class should always have a runnable task */
+	BUG();
+}
 
 /*
  * Migrate all tasks from the rq, sleeping tasks will be migrated by
@@ -6139,12 +6140,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
 		if (rq->nr_running == 1)
 			break;
 
-		/*
-		 * pick_next_task() assumes pinned rq->lock:
-		 */
-		next = pick_next_task(rq, &fake_task, rf);
-		BUG_ON(!next);
-		put_prev_task(rq, next);
+		next = __pick_migrate_task(rq);
 
 		/*
 		 * Rules for changing task_struct::cpus_mask are holding
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ea48aa5daeee..b3449d0dd7f0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1751,6 +1751,7 @@ struct sched_class {
 
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
+	WARN_ON_ONCE(rq->curr != prev);
 	prev->sched_class->put_prev_task(rq, prev);
 }