[RFC PATCH 1/2] sched: encapsulate priority changes in a sched_set_prio static function

[Julien Desfossez]

Currently, the priority of tasks is modified directly in the scheduling
functions. Encapsulate priority updates to enable instrumentation of
priority changes. This will enable analysis of real-time scheduling
delays per thread priority, which cannot be performed accurately if we
only trace the priority of the currently scheduled processes.

The call sites that modify the priority of a task are mostly system
calls: sched_setscheduler, sched_setattr, sched_process_fork and
set_user_nice. Priority can also be dynamically boosted through
priority inheritance of rt_mutex by rt_mutex_setprio.

Signed-off-by: Julien Desfossez <jdesfossez@xxxxxxxxxxxx>
---
 include/linux/sched.h |  3 ++-
 kernel/sched/core.c   | 19 +++++++++++++------
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 52c4847..48b35c0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1409,7 +1409,8 @@ struct task_struct {
 #endif
 	int on_rq;
 
-	int prio, static_prio, normal_prio;
+	int prio; /* Updated through sched_set_prio() */
+	int static_prio, normal_prio;
 	unsigned int rt_priority;
 	const struct sched_class *sched_class;
 	struct sched_entity se;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d1f7149..6946b8f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2230,6 +2230,11 @@ int sysctl_schedstats(struct ctl_table *table, int write,
 #endif
 #endif
 
+static void sched_set_prio(struct task_struct *p, int prio)
+{
+	p->prio = prio;
+}
+
 /*
  * fork()/clone()-time setup:
  */
@@ -2249,7 +2254,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	/*
 	 * Make sure we do not leak PI boosting priority to the child.
 	 */
-	p->prio = current->normal_prio;
+	sched_set_prio(p, current->normal_prio);
 
 	/*
 	 * Revert to default priority/policy on fork if requested.
@@ -2262,7 +2267,8 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 		} else if (PRIO_TO_NICE(p->static_prio) < 0)
 			p->static_prio = NICE_TO_PRIO(0);
 
-		p->prio = p->normal_prio = __normal_prio(p);
+		p->normal_prio = __normal_prio(p);
+		sched_set_prio(p, p->normal_prio);
 		set_load_weight(p);
 
 		/*
@@ -3477,7 +3483,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		p->sched_class = &fair_sched_class;
 	}
 
-	p->prio = prio;
+	sched_set_prio(p, prio);
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
@@ -3524,7 +3530,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	p->static_prio = NICE_TO_PRIO(nice);
 	set_load_weight(p);
 	old_prio = p->prio;
-	p->prio = effective_prio(p);
+	sched_set_prio(p, effective_prio(p));
 	delta = p->prio - old_prio;
 
 	if (queued) {
@@ -3731,9 +3737,10 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
 	 * sched_setscheduler().
 	 */
 	if (keep_boost)
-		p->prio = rt_mutex_get_effective_prio(p, normal_prio(p));
+		sched_set_prio(p, rt_mutex_get_effective_prio(p,
+					normal_prio(p)));
 	else
-		p->prio = normal_prio(p);
+		sched_set_prio(p, normal_prio(p));
 
 	if (dl_prio(p->prio))
 		p->sched_class = &dl_sched_class;
-- 
1.9.1