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_rt.c b/kernel/sched_rt.c
index 060e87b..d73386c 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -231,7 +231,7 @@
 		return 1;
 
 	span = sched_rt_period_mask();
-	for_each_cpu_mask(i, span) {
+	for_each_cpu_mask_nr(i, span) {
 		int enqueue = 0;
 		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
 		struct rq *rq = rq_of_rt_rq(rt_rq);
@@ -272,7 +272,7 @@
 
 	spin_lock(&rt_b->rt_runtime_lock);
 	rt_period = ktime_to_ns(rt_b->rt_period);
-	for_each_cpu_mask(i, rd->span) {
+	for_each_cpu_mask_nr(i, rd->span) {
 		struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
 		s64 diff;
 
@@ -1000,7 +1000,7 @@
 
 	next = pick_next_task_rt(this_rq);
 
-	for_each_cpu_mask(cpu, this_rq->rd->rto_mask) {
+	for_each_cpu_mask_nr(cpu, this_rq->rd->rto_mask) {
 		if (this_cpu == cpu)
 			continue;