sched: Micro-optimize the smart wake-affine logic

Smart wake-affine is using node-size as the factor currently, but the overhead
of the mask operation is high.

Thus, this patch introduce the 'sd_llc_size' percpu variable, which will record
the highest cache-share domain size, and make it to be the new factor, in order
to reduce the overhead and make it more reasonable.
Tested-by: NDavidlohr Bueso <davidlohr.bueso@hp.com>
Tested-by: NMichael Wang <wangyun@linux.vnet.ibm.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Acked-by: NMichael Wang <wangyun@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Link: http://lkml.kernel.org/r/51D5008E.6030102@linux.vnet.ibm.com
[ Tidied up the changelog. ]
Signed-off-by: NIngo Molnar <mingo@kernel.org>

kernel/sched/core.c

@@ -5083,18 +5083,23 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu)
  * two cpus are in the same cache domain, see cpus_share_cache().
  */
 DEFINE_PER_CPU(struct sched_domain *, sd_llc);
+DEFINE_PER_CPU(int, sd_llc_size);
 DEFINE_PER_CPU(int, sd_llc_id);
 
 static void update_top_cache_domain(int cpu)
 {
 	struct sched_domain *sd;
 	int id = cpu;
+	int size = 1;
 
 	sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
-	if (sd)
+	if (sd) {
 		id = cpumask_first(sched_domain_span(sd));
+		size = cpumask_weight(sched_domain_span(sd));
+	}
 
 	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
+	per_cpu(sd_llc_size, cpu) = size;
 	per_cpu(sd_llc_id, cpu) = id;
 }
 

kernel/sched/fair.c

@@ -3175,7 +3175,7 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu,
 
 static int wake_wide(struct task_struct *p)
 {
-	int factor = nr_cpus_node(cpu_to_node(smp_processor_id()));
+	int factor = this_cpu_read(sd_llc_size);
 
 	/*
 	 * Yeah, it's the switching-frequency, could means many wakee or

kernel/sched/sched.h

@@ -594,6 +594,7 @@ static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
 }
 
 DECLARE_PER_CPU(struct sched_domain *, sd_llc);
+DECLARE_PER_CPU(int, sd_llc_size);
 DECLARE_PER_CPU(int, sd_llc_id);
 
 struct sched_group_power {