core: use performance variant for_each_cpu_mask_nr

Change references from for_each_cpu_mask to for_each_cpu_mask_nr
where appropriate

Reviewed-by: Paul Jackson <pj@sgi.com>
Reviewed-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index e24ecd3..e398318 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1022,7 +1022,7 @@
 		    || ((sd->flags & SD_WAKE_IDLE_FAR)
 			&& !task_hot(p, task_rq(p)->clock, sd))) {
 			cpus_and(tmp, sd->span, p->cpus_allowed);
-			for_each_cpu_mask(i, tmp) {
+			for_each_cpu_mask_nr(i, tmp) {
 				if (idle_cpu(i)) {
 					if (i != task_cpu(p)) {
 						schedstat_inc(p,