sched: Fix avg_load computation

The computation of avg_load and avg_load_per_task should only take into
account the number of CFS tasks. The non-CFS tasks are already taken into
account by decreasing the CPU's capacity and they will be tracked in the
CPU's utilization (group_utilization) of the next patches.

Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: riel@redhat.com
Cc: Morten.Rasmussen@arm.com
Cc: efault@gmx.de
Cc: nicolas.pitre@linaro.org
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1409051215-16788-4-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/fair.c

@@ -4095,7 +4095,7 @@ static unsigned long capacity_of(int cpu)
 static unsigned long cpu_avg_load_per_task(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long nr_running = ACCESS_ONCE(rq->nr_running);
+	unsigned long nr_running = ACCESS_ONCE(rq->cfs.h_nr_running);
 	unsigned long load_avg = rq->cfs.runnable_load_avg;
 
 	if (nr_running)
@@ -5985,7 +5985,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			load = source_load(i, load_idx);
 
 		sgs->group_load += load;
-		sgs->sum_nr_running += rq->nr_running;
+		sgs->sum_nr_running += rq->cfs.h_nr_running;
 
 		if (rq->nr_running > 1)
 			*overload = true;