sched/tg: Use 'unsigned long' for load variable in task group

Since tg->load_avg is smaller than tg->load_weight, we don't need a
atomic64_t variable for load_avg in 32 bit machine.
The same reason for cfs_rq->tg_load_contrib.

The atomic_long_t/unsigned long variable type are more efficient and
convenience for them.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1371694737-29336-11-git-send-email-alex.shi@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/debug.c

@@ -215,9 +215,9 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->runnable_load_avg);
 	SEQ_printf(m, "  .%-30s: %ld\n", "blocked_load_avg",
 			cfs_rq->blocked_load_avg);
-	SEQ_printf(m, "  .%-30s: %lld\n", "tg_load_avg",
-			(unsigned long long)atomic64_read(&cfs_rq->tg->load_avg));
-	SEQ_printf(m, "  .%-30s: %lld\n", "tg_load_contrib",
+	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_avg",
+			atomic_long_read(&cfs_rq->tg->load_avg));
+	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_contrib",
 			cfs_rq->tg_load_contrib);
 	SEQ_printf(m, "  .%-30s: %d\n", "tg_runnable_contrib",
 			cfs_rq->tg_runnable_contrib);

kernel/sched/fair.c

@@ -1075,7 +1075,7 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
 	 * to gain a more accurate current total weight. See
 	 * update_cfs_rq_load_contribution().
 	 */
-	tg_weight = atomic64_read(&tg->load_avg);
+	tg_weight = atomic_long_read(&tg->load_avg);
 	tg_weight -= cfs_rq->tg_load_contrib;
 	tg_weight += cfs_rq->load.weight;
 
@@ -1356,13 +1356,13 @@ static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
 						 int force_update)
 {
 	struct task_group *tg = cfs_rq->tg;
-	s64 tg_contrib;
+	long tg_contrib;
 
 	tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg;
 	tg_contrib -= cfs_rq->tg_load_contrib;
 
-	if (force_update || abs64(tg_contrib) > cfs_rq->tg_load_contrib / 8) {
-		atomic64_add(tg_contrib, &tg->load_avg);
+	if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) {
+		atomic_long_add(tg_contrib, &tg->load_avg);
 		cfs_rq->tg_load_contrib += tg_contrib;
 	}
 }
@@ -1397,8 +1397,8 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
 	u64 contrib;
 
 	contrib = cfs_rq->tg_load_contrib * tg->shares;
-	se->avg.load_avg_contrib = div64_u64(contrib,
-					     atomic64_read(&tg->load_avg) + 1);
+	se->avg.load_avg_contrib = div_u64(contrib,
+				     atomic_long_read(&tg->load_avg) + 1);
 
 	/*
 	 * For group entities we need to compute a correction term in the case

kernel/sched/sched.h

@@ -150,7 +150,7 @@ struct task_group {
 
 	atomic_t load_weight;
 #ifdef	CONFIG_SMP
-	atomic64_t load_avg;
+	atomic_long_t load_avg;
 	atomic_t runnable_avg;
 #endif
 #endif
@@ -284,7 +284,7 @@ struct cfs_rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* Required to track per-cpu representation of a task_group */
 	u32 tg_runnable_contrib;
-	u64 tg_load_contrib;
+	unsigned long tg_load_contrib;
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 	/*