sched: Only queue remote wakeups when crossing cache boundaries

Mike reported a 13% drop in netperf TCP_RR performance due to the
new remote wakeup code. Suresh too noticed some performance issues
with it.

Reducing the IPIs to only cross cache domains solves the observed
performance issues.

Reported-by: Suresh Siddha <suresh.b.siddha@intel.com>
Reported-by: Mike Galbraith <efault@gmx.de>
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
Acked-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Dave Kleikamp <dave.kleikamp@oracle.com>
Link: http://lkml.kernel.org/r/1323338531.17673.7.camel@twins
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 36 insertions, 6 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d8d3613a4055..98c0c2623db8 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -487,6 +487,14 @@ static inline int cpu_of(struct rq *rq)
 
 DECLARE_PER_CPU(struct rq, runqueues);
 
+#define cpu_rq(cpu)             (&per_cpu(runqueues, (cpu)))
+#define this_rq()               (&__get_cpu_var(runqueues))
+#define task_rq(p)              cpu_rq(task_cpu(p))
+#define cpu_curr(cpu)           (cpu_rq(cpu)->curr)
+#define raw_rq()                (&__raw_get_cpu_var(runqueues))
+
+#ifdef CONFIG_SMP
+
 #define rcu_dereference_check_sched_domain(p) \
         rcu_dereference_check((p), \
                               lockdep_is_held(&sched_domains_mutex))
@@ -499,15 +507,37 @@ DECLARE_PER_CPU(struct rq, runqueues);
  * preempt-disabled sections.
  */
 #define for_each_domain(cpu, __sd) \
-        for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)
+        for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \
+                        __sd; __sd = __sd->parent)
 
 #define for_each_lower_domain(sd) for (; sd; sd = sd->child)
 
-#define cpu_rq(cpu)             (&per_cpu(runqueues, (cpu)))
-#define this_rq()               (&__get_cpu_var(runqueues))
-#define task_rq(p)              cpu_rq(task_cpu(p))
-#define cpu_curr(cpu)           (cpu_rq(cpu)->curr)
-#define raw_rq()                (&__raw_get_cpu_var(runqueues))
+/**
+ * highest_flag_domain - Return highest sched_domain containing flag.
+ * @cpu:        The cpu whose highest level of sched domain is to
+ *              be returned.
+ * @flag:       The flag to check for the highest sched_domain
+ *              for the given cpu.
+ *
+ * Returns the highest sched_domain of a cpu which contains the given flag.
+ */
+static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
+{
+        struct sched_domain *sd, *hsd = NULL;
+
+        for_each_domain(cpu, sd) {
+                if (!(sd->flags & flag))
+                        break;
+                hsd = sd;
+        }
+
+        return hsd;
+}
+
+DECLARE_PER_CPU(struct sched_domain *, sd_llc);
+DECLARE_PER_CPU(int, sd_llc_id);
+
+#endif /* CONFIG_SMP */
 
 #include "stats.h"
 #include "auto_group.h"