sched/fair: Make per-cpu cpumasks static

The load_balance_mask and select_rq_mask percpu variables are only used in
kernel/sched/fair.c.

Make them static and move their allocation into init_sched_fair_class().

Replace kzalloc_node() with zalloc_cpumask_var_node() to get rid of the
CONFIG_CPUMASK_OFFSTACK #ifdef and to align with per-cpu cpumask
allocation for RT (local_cpu_mask in init_sched_rt_class()) and DL
class (local_cpu_mask_dl in init_sched_dl_class()).

[ mingo: Tidied up changelog & touched up the code. ]
Signed-off-by: Bing Huang <huangbing@kylinos.cn>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220722213609.3901-1-huangbing775@126.com

kernel/sched/core.c

@@ -9563,9 +9563,6 @@ LIST_HEAD(task_groups);
 static struct kmem_cache *task_group_cache __read_mostly;
 #endif
 
-DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
-DECLARE_PER_CPU(cpumask_var_t, select_rq_mask);
-
 void __init sched_init(void)
 {
 	unsigned long ptr = 0;
@@ -9609,14 +9606,6 @@ void __init sched_init(void)
 
 #endif /* CONFIG_RT_GROUP_SCHED */
 	}
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	for_each_possible_cpu(i) {
-		per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
-			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
-		per_cpu(select_rq_mask, i) = (cpumask_var_t)kzalloc_node(
-			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
-	}
-#endif /* CONFIG_CPUMASK_OFFSTACK */
 
 	init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
 

kernel/sched/fair.c

@@ -5893,8 +5893,8 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 #ifdef CONFIG_SMP
 
 /* Working cpumask for: load_balance, load_balance_newidle. */
-DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
-DEFINE_PER_CPU(cpumask_var_t, select_rq_mask);
+static DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
+static DEFINE_PER_CPU(cpumask_var_t, select_rq_mask);
 
 #ifdef CONFIG_NO_HZ_COMMON
 
@@ -12074,6 +12074,13 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m)
 __init void init_sched_fair_class(void)
 {
 #ifdef CONFIG_SMP
+	int i;
+
+	for_each_possible_cpu(i) {
+		zalloc_cpumask_var_node(&per_cpu(load_balance_mask, i), GFP_KERNEL, cpu_to_node(i));
+		zalloc_cpumask_var_node(&per_cpu(select_rq_mask,    i), GFP_KERNEL, cpu_to_node(i));
+	}
+
 	open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
 
 #ifdef CONFIG_NO_HZ_COMMON