sched/fair: Start tracking SCHED_IDLE tasks count in cfs_rq

Track how many tasks are present with SCHED_IDLE policy in each cfs_rq.
This will be used by later commits.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: chris.redpath@arm.com
Cc: quentin.perret@linaro.org
Cc: songliubraving@fb.com
Cc: steven.sistare@oracle.com
Cc: subhra.mazumdar@oracle.com
Cc: tkjos@google.com
Link: https://lkml.kernel.org/r/0d3cdc427fc68808ad5bccc40e86ed0bf9da8bb4.1561523542.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 14 insertions, 3 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9be36ffb5689..9ed5ab53872f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4555,7 +4555,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
-	long task_delta, dequeue = 1;
+	long task_delta, idle_task_delta, dequeue = 1;
 	bool empty;
 
 	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
@@ -4566,6 +4566,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	rcu_read_unlock();
 
 	task_delta = cfs_rq->h_nr_running;
+	idle_task_delta = cfs_rq->idle_h_nr_running;
 	for_each_sched_entity(se) {
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 		/* throttled entity or throttle-on-deactivate */
@@ -4575,6 +4576,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		if (dequeue)
 			dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
 		qcfs_rq->h_nr_running -= task_delta;
+		qcfs_rq->idle_h_nr_running -= idle_task_delta;
 
 		if (qcfs_rq->load.weight)
 			dequeue = 0;
@@ -4614,7 +4616,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	int enqueue = 1;
-	long task_delta;
+	long task_delta, idle_task_delta;
 
 	se = cfs_rq->tg->se[cpu_of(rq)];
 
@@ -4634,6 +4636,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 		return;
 
 	task_delta = cfs_rq->h_nr_running;
+	idle_task_delta = cfs_rq->idle_h_nr_running;
 	for_each_sched_entity(se) {
 		if (se->on_rq)
 			enqueue = 0;
@@ -4642,6 +4645,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 		if (enqueue)
 			enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
 		cfs_rq->h_nr_running += task_delta;
+		cfs_rq->idle_h_nr_running += idle_task_delta;
 
 		if (cfs_rq_throttled(cfs_rq))
 			break;
@@ -5255,6 +5259,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
+	int idle_h_nr_running = task_has_idle_policy(p);
 
 	/*
 	 * The code below (indirectly) updates schedutil which looks at
@@ -5287,6 +5292,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 		cfs_rq->h_nr_running++;
+		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
 		flags = ENQUEUE_WAKEUP;
 	}
@@ -5294,6 +5300,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 		cfs_rq->h_nr_running++;
+		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
 		if (cfs_rq_throttled(cfs_rq))
 			break;
@@ -5355,6 +5362,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 	int task_sleep = flags & DEQUEUE_SLEEP;
+	int idle_h_nr_running = task_has_idle_policy(p);
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
@@ -5369,6 +5377,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 		cfs_rq->h_nr_running--;
+		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
@@ -5388,6 +5397,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 		cfs_rq->h_nr_running--;
+		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
 		if (cfs_rq_throttled(cfs_rq))
 			break;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 802b1f3405f2..aaca0e743776 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -483,7 +483,8 @@ struct cfs_rq {
 	struct load_weight	load;
 	unsigned long		runnable_weight;
 	unsigned int		nr_running;
-	unsigned int		h_nr_running;
+	unsigned int		h_nr_running;      /* SCHED_{NORMAL,BATCH,IDLE} */
+	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
 
 	u64			exec_clock;
 	u64			min_vruntime;