[patch v8 8/9] sched: consider runnable load average in move_tasks

[Alex Shi <alex.shi@intel.com>]

Except using runnable load average in background, move_tasks is also
the key functions in load balance. We need consider the runnable load
average in it in order to the apple to apple load comparison.

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

Signed-off-by: Alex Shi <alex.shi@intel.com>
---
 kernel/sched/fair.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index eadd2e7..3aa1dc0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4178,11 +4178,14 @@ 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;
@@ -4208,12 +4211,9 @@ 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)
-- 
1.7.12