sched: Consider runnable load average in move_tasks()

Aside from using runnable load average in background, move_tasks is
also the key function in load balance. We need consider the runnable
load average in it in order to make it an apple to apple load
comparison.

Morten had caught a div u64 bug on ARM, thanks!

Thanks-to: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Alex Shi <alex.shi@intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1371694737-29336-8-git-send-email-alex.shi@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/fair.c

@@ -4179,11 +4179,14 @@ static int tg_load_down(struct task_group *tg, void *data)
 	long cpu = (long)data;
 
 	if (!tg->parent) {
-		load = cpu_rq(cpu)->load.weight;
+		load = cpu_rq(cpu)->avg.load_avg_contrib;
 	} else {
+		unsigned long tmp_rla;
+		tmp_rla = tg->parent->cfs_rq[cpu]->runnable_load_avg + 1;
+
 		load = tg->parent->cfs_rq[cpu]->h_load;
-		load *= tg->se[cpu]->load.weight;
-		load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
+		load *= tg->se[cpu]->avg.load_avg_contrib;
+		load /= tmp_rla;
 	}
 
 	tg->cfs_rq[cpu]->h_load = load;
@@ -4209,12 +4212,9 @@ static void update_h_load(long cpu)
 static unsigned long task_h_load(struct task_struct *p)
 {
 	struct cfs_rq *cfs_rq = task_cfs_rq(p);
-	unsigned long load;
-
-	load = p->se.load.weight;
-	load = div_u64(load * cfs_rq->h_load, cfs_rq->load.weight + 1);
 
-	return load;
+	return div64_ul(p->se.avg.load_avg_contrib * cfs_rq->h_load,
+			cfs_rq->runnable_load_avg + 1);
 }
 #else
 static inline void update_blocked_averages(int cpu)
@@ -4227,7 +4227,7 @@ static inline void update_h_load(long cpu)
 
 static unsigned long task_h_load(struct task_struct *p)
 {
-	return p->se.load.weight;
+	return p->se.avg.load_avg_contrib;
 }
 #endif