sched/cfs_rq: Change atomic64_t removed_load to atomic_long_t

Similar to runnable_load_avg, blocked_load_avg variable, long type is
enough for removed_load in 64 bit or 32 bit machine.

Then we avoid the expensive atomic64 operations on 32 bit machine.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Reviewed-by: Paul Turner <pjt@google.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1371694737-29336-12-git-send-email-alex.shi@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/fair.c

@@ -1517,8 +1517,9 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
 	if (!decays && !force_update)
 		return;
 
-	if (atomic64_read(&cfs_rq->removed_load)) {
-		u64 removed_load = atomic64_xchg(&cfs_rq->removed_load, 0);
+	if (atomic_long_read(&cfs_rq->removed_load)) {
+		unsigned long removed_load;
+		removed_load = atomic_long_xchg(&cfs_rq->removed_load, 0);
 		subtract_blocked_load_contrib(cfs_rq, removed_load);
 	}
 
@@ -3480,7 +3481,8 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu)
 	 */
 	if (se->avg.decay_count) {
 		se->avg.decay_count = -__synchronize_entity_decay(se);
-		atomic64_add(se->avg.load_avg_contrib, &cfs_rq->removed_load);
+		atomic_long_add(se->avg.load_avg_contrib,
+						&cfs_rq->removed_load);
 	}
 }
 #endif /* CONFIG_SMP */
@@ -5942,7 +5944,7 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 #endif
 #ifdef CONFIG_SMP
 	atomic64_set(&cfs_rq->decay_counter, 1);
-	atomic64_set(&cfs_rq->removed_load, 0);
+	atomic_long_set(&cfs_rq->removed_load, 0);
 #endif
 }
 

kernel/sched/sched.h

@@ -278,8 +278,9 @@ struct cfs_rq {
 	 * the FAIR_GROUP_SCHED case).
 	 */
 	unsigned long runnable_load_avg, blocked_load_avg;
-	atomic64_t decay_counter, removed_load;
+	atomic64_t decay_counter;
 	u64 last_decay;
+	atomic_long_t removed_load;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* Required to track per-cpu representation of a task_group */