sched: Implement hierarchical task accounting for SCHED_OTHER

Introduce hierarchical task accounting for the group scheduling case in CFS, as
well as promoting the responsibility for maintaining rq->nr_running to the
scheduling classes.

The primary motivation for this is that with scheduling classes supporting
bandwidth throttling it is possible for entities participating in throttled
sub-trees to not have root visible changes in rq->nr_running across activate
and de-activate operations.  This in turn leads to incorrect idle and
weight-per-task load balance decisions.

This also allows us to make a small fixlet to the fastpath in pick_next_task()
under group scheduling.

Note: this issue also exists with the existing sched_rt throttling mechanism.
This patch does not address that.
Signed-off-by: Paul Turner <pjt@google.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110721184756.878333391@google.comSigned-off-by: Ingo Molnar <mingo@elte.hu>

kernel/sched.c

@@ -311,7 +311,7 @@ struct task_group root_task_group;
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
 	struct load_weight load;
-	unsigned long nr_running;
+	unsigned long nr_running, h_nr_running;
 
 	u64 exec_clock;
 	u64 min_vruntime;
@@ -1802,7 +1802,6 @@ static void activate_task(struct rq *rq, struct task_struct *p, int flags)
 		rq->nr_uninterruptible--;
 
 	enqueue_task(rq, p, flags);
-	inc_nr_running(rq);
 }
 
 /*
@@ -1814,7 +1813,6 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 		rq->nr_uninterruptible++;
 
 	dequeue_task(rq, p, flags);
-	dec_nr_running(rq);
 }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -4258,7 +4256,7 @@ pick_next_task(struct rq *rq)
 	 * Optimization: we know that if all tasks are in
 	 * the fair class we can call that function directly:
 	 */
-	if (likely(rq->nr_running == rq->cfs.nr_running)) {
+	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
 		p = fair_sched_class.pick_next_task(rq);
 		if (likely(p))
 			return p;

kernel/sched_fair.c

@@ -1310,16 +1310,19 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 			break;
 		cfs_rq = cfs_rq_of(se);
 		enqueue_entity(cfs_rq, se, flags);
+		cfs_rq->h_nr_running++;
 		flags = ENQUEUE_WAKEUP;
 	}
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
+		cfs_rq->h_nr_running++;
 
 		update_cfs_load(cfs_rq, 0);
 		update_cfs_shares(cfs_rq);
 	}
 
+	inc_nr_running(rq);
 	hrtick_update(rq);
 }
 
@@ -1339,6 +1342,7 @@ 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);
 		dequeue_entity(cfs_rq, se, flags);
+		cfs_rq->h_nr_running--;
 
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
@@ -1358,11 +1362,13 @@ 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--;
 
 		update_cfs_load(cfs_rq, 0);
 		update_cfs_shares(cfs_rq);
 	}
 
+	dec_nr_running(rq);
 	hrtick_update(rq);
 }
 

kernel/sched_rt.c

@@ -936,6 +936,8 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
+
+	inc_nr_running(rq);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
@@ -946,6 +948,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_rt_entity(rt_se);
 
 	dequeue_pushable_task(rq, p);
+
+	dec_nr_running(rq);
 }
 
 /*
@@ -1841,4 +1845,3 @@ static void print_rt_stats(struct seq_file *m, int cpu)
 	rcu_read_unlock();
 }
 #endif /* CONFIG_SCHED_DEBUG */
-

kernel/sched_stoptask.c

@@ -34,11 +34,13 @@ static struct task_struct *pick_next_task_stop(struct rq *rq)
 static void
 enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
 {
+	inc_nr_running(rq);
 }
 
 static void
 dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
 {
+	dec_nr_running(rq);
 }
 
 static void yield_task_stop(struct rq *rq)