[PATCH 05/36] sched: Add sched_class->switching_to() and expose check_class_changing/changed()

[Tejun Heo]

When a task switches to a new sched_class, the prev and new classes are
notified through ->switched_from() and ->switched_to(), respectively, after
the switching is done.

A new BPF extensible sched_class will have callbacks that allow the BPF
scheduler to keep track of relevant task states (like priority and cpumask).
Those callbacks aren't called while a task is on a different sched_class.
When a task comes back, we wanna tell the BPF progs the up-to-date state
before the task gets enqueued, so we need a hook which is called before the
switching is committed.

This patch adds ->switching_to() which is called during sched_class switch
through check_class_changing() before the task is restored. Also, this patch
exposes check_class_changing/changed() in kernel/sched/sched.h. They will be
used by the new BPF extensible sched_class to implement implicit sched_class
switching which is used e.g. when falling back to CFS when the BPF scheduler
fails or unloads.

This is a prep patch and doesn't cause any behavior changes. The new
operation and exposed functions aren't used yet.

v2: Improve patch description w/ details on planned use.

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Reviewed-by: David Vernet <dvernet@xxxxxxxx>
Acked-by: Josh Don <joshdon@xxxxxxxxxx>
Acked-by: Hao Luo <haoluo@xxxxxxxxxx>
Acked-by: Barret Rhoden <brho@xxxxxxxxxx>
---
 kernel/sched/core.c  | 19 ++++++++++++++++---
 kernel/sched/sched.h |  7 +++++++
 2 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 09e6ce45e65a..26ad5dc65ede 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2191,6 +2191,17 @@ inline int task_curr(const struct task_struct *p)
 	return cpu_curr(task_cpu(p)) == p;
 }
 
+/*
+ * ->switching_to() is called with the pi_lock and rq_lock held and must not
+ * mess with locking.
+ */
+void check_class_changing(struct rq *rq, struct task_struct *p,
+			  const struct sched_class *prev_class)
+{
+	if (prev_class != p->sched_class && p->sched_class->switching_to)
+		p->sched_class->switching_to(rq, p);
+}
+
 /*
  * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
  * use the balance_callback list if you want balancing.
@@ -2198,9 +2209,9 @@ inline int task_curr(const struct task_struct *p)
  * this means any call to check_class_changed() must be followed by a call to
  * balance_callback().
  */
-static inline void check_class_changed(struct rq *rq, struct task_struct *p,
-				       const struct sched_class *prev_class,
-				       int oldprio)
+void check_class_changed(struct rq *rq, struct task_struct *p,
+			 const struct sched_class *prev_class,
+			 int oldprio)
 {
 	if (prev_class != p->sched_class) {
 		if (prev_class->switched_from)
@@ -7193,6 +7204,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	}
 
 	__setscheduler_prio(p, prio);
+	check_class_changing(rq, p, prev_class);
 
 	if (queued)
 		enqueue_task(rq, p, queue_flag);
@@ -7852,6 +7864,7 @@ static int __sched_setscheduler(struct task_struct *p,
 		__setscheduler_prio(p, newprio);
 	}
 	__setscheduler_uclamp(p, attr);
+	check_class_changing(rq, p, prev_class);
 
 	if (queued) {
 		/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index a66b48bc45ba..bfe7303559f1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2257,6 +2257,7 @@ struct sched_class {
 	 * cannot assume the switched_from/switched_to pair is serialized by
 	 * rq->lock. They are however serialized by p->pi_lock.
 	 */
+	void (*switching_to) (struct rq *this_rq, struct task_struct *task);
 	void (*switched_from)(struct rq *this_rq, struct task_struct *task);
 	void (*switched_to)  (struct rq *this_rq, struct task_struct *task);
 	void (*reweight_task)(struct rq *this_rq, struct task_struct *task,
@@ -2497,6 +2498,12 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)
 extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
 extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
+extern void check_class_changing(struct rq *rq, struct task_struct *p,
+				 const struct sched_class *prev_class);
+extern void check_class_changed(struct rq *rq, struct task_struct *p,
+				const struct sched_class *prev_class,
+				int oldprio);
+
 extern void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags);
 
 #ifdef CONFIG_PREEMPT_RT
-- 
2.42.0