cpumask: reduce stack usage in find_lowest_rq

Impact: reduce stack usage, cleanup

Use a cpumask_var_t in find_lowest_rq() and clean up other old
cpumask_t calls.
Signed-off-by: Mike Travis <travis@sgi.com>

kernel/sched_rt.c

@@ -960,16 +960,17 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 
-static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
+static inline int pick_optimal_cpu(int this_cpu,
+				   const struct cpumask *mask)
 {
 	int first;
 
 	/* "this_cpu" is cheaper to preempt than a remote processor */
-	if ((this_cpu != -1) && cpu_isset(this_cpu, *mask))
+	if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask))
 		return this_cpu;
 
-	first = first_cpu(*mask);
-	if (first != NR_CPUS)
+	first = cpumask_first(mask);
+	if (first < nr_cpu_ids)
 		return first;
 
 	return -1;
@@ -981,6 +982,7 @@ static int find_lowest_rq(struct task_struct *task)
 	struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
+	cpumask_var_t domain_mask;
 
 	if (task->rt.nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
@@ -1013,20 +1015,26 @@ static int find_lowest_rq(struct task_struct *task)
 	if (this_cpu == cpu)
 		this_cpu = -1; /* Skip this_cpu opt if the same */
 
+	if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) {
 		for_each_domain(cpu, sd) {
 			if (sd->flags & SD_WAKE_AFFINE) {
-			cpumask_t domain_mask;
 				int best_cpu;
 
-			cpumask_and(&domain_mask, sched_domain_span(sd),
+				cpumask_and(domain_mask,
+					    sched_domain_span(sd),
 					    lowest_mask);
 
 				best_cpu = pick_optimal_cpu(this_cpu,
-						    &domain_mask);
-			if (best_cpu != -1)
+							    domain_mask);
+
+				if (best_cpu != -1) {
+					free_cpumask_var(domain_mask);
 					return best_cpu;
 				}
 			}
+		}
+		free_cpumask_var(domain_mask);
+	}
 
 	/*
 	 * And finally, if there were no matches within the domains