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: Davidlohr Bueso <davidlohr.bueso@hp.com>
Tested-by: Michael Wang <wangyun@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Michael 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: Ingo Molnar <mingo@kernel.org>

1 files changed, 6 insertions, 1 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b7c32cb7bfeb..6df0fbe53767 100644
--- a/kernel/sched/core.c
+++ b/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;
 }