[PATCH 2/2] powerpc: implement arch_scale_smt_power for Power7

[Joel Schopp]

On Power7 processors running in SMT4 mode with 2, 3, or 4 idle threads 
there is performance benefit to idling the higher numbered threads in
the core.  

This patch implements arch_scale_smt_power to dynamically update smt
thread power in these idle cases in order to prefer threads 0,1 over
threads 2,3 within a core.

Signed-off-by: Joel Schopp <jschopp at austin.ibm.com>
---
Index: linux-2.6.git/arch/powerpc/kernel/smp.c
===================================================================
--- linux-2.6.git.orig/arch/powerpc/kernel/smp.c
+++ linux-2.6.git/arch/powerpc/kernel/smp.c
@@ -617,3 +617,44 @@ void __cpu_die(unsigned int cpu)
 		smp_ops->cpu_die(cpu);
 }
 #endif
+
+static inline int thread_in_smt4core(int x)
+{
+  return x % 4;
+}
+unsigned long arch_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+  int cpu2;
+  int idle_count = 0;
+
+  struct cpumask *cpu_map = sched_domain_span(sd);
+
+	unsigned long weight = cpumask_weight(cpu_map);
+	unsigned long smt_gain = sd->smt_gain;
+
+	if (cpu_has_feature(CPU_FTRS_POWER7) && weight == 4) {
+		for_each_cpu(cpu2, cpu_map) {
+			if (idle_cpu(cpu2))
+				idle_count++;
+		}
+
+		/* the following section attempts to tweak cpu power based
+		 * on current idleness of the threads dynamically at runtime
+		 */
+		if (idle_count == 2 || idle_count == 3 || idle_count == 4) {
+			if (thread_in_smt4core(cpu) == 0 ||
+			    thread_in_smt4core(cpu) == 1) {
+				/* add 75 % to thread power */
+				smt_gain += (smt_gain >> 1) + (smt_gain >> 2);
+			} else {
+				 /* subtract 75 % to thread power */
+				smt_gain = smt_gain >> 2;
+			}
+		}
+	}
+	/* default smt gain is 1178, weight is # of SMT threads */
+	smt_gain /= weight;
+
+	return smt_gain;
+
+}
Index: linux-2.6.git/kernel/sched_features.h
===================================================================
--- linux-2.6.git.orig/kernel/sched_features.h
+++ linux-2.6.git/kernel/sched_features.h
@@ -107,7 +107,7 @@ SCHED_FEAT(CACHE_HOT_BUDDY, 1)
 /*
  * Use arch dependent cpu power functions
  */
-SCHED_FEAT(ARCH_POWER, 0)
+SCHED_FEAT(ARCH_POWER, 1)
 
 SCHED_FEAT(HRTICK, 0)
 SCHED_FEAT(DOUBLE_TICK, 0)