sched/fair: Use non-atomic cpumask_{set,clear}_cpu()

The cpumasks updated here are not subject to concurrency and using
atomic bitops for them is pointless and expensive. Use the non-atomic
variants instead.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Link: http://lkml.kernel.org/r/2e2a10f84b9049a81eef94ed6d5989447c21e34a.1549963617.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8abd1c2..8213ff6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6097,7 +6097,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 		bool idle = true;
 
 		for_each_cpu(cpu, cpu_smt_mask(core)) {
-			cpumask_clear_cpu(cpu, cpus);
+			__cpumask_clear_cpu(cpu, cpus);
 			if (!available_idle_cpu(cpu))
 				idle = false;
 		}
@@ -9105,7 +9105,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) {
 
 			/* Prevent to re-select dst_cpu via env's CPUs */
-			cpumask_clear_cpu(env.dst_cpu, env.cpus);
+			__cpumask_clear_cpu(env.dst_cpu, env.cpus);
 
 			env.dst_rq	 = cpu_rq(env.new_dst_cpu);
 			env.dst_cpu	 = env.new_dst_cpu;
@@ -9132,7 +9132,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 
 		/* All tasks on this runqueue were pinned by CPU affinity */
 		if (unlikely(env.flags & LBF_ALL_PINNED)) {
-			cpumask_clear_cpu(cpu_of(busiest), cpus);
+			__cpumask_clear_cpu(cpu_of(busiest), cpus);
 			/*
 			 * Attempting to continue load balancing at the current
 			 * sched_domain level only makes sense if there are