lkml.org 
[lkml]   [2009]   [Sep]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[RFC][PATCH 12/14] x86: sched: provide arch implementations using aperf/mperf
APERF/MPERF support for cpu_power.

APERF/MPERF is arch defined to be a relative scale of work capacity
per logical cpu, this is assumed to include SMT and Turbo mode.

APERF/MPERF are specified to both reset to 0 when either counter
wraps, which is highly inconvenient, since that'll give a blimp when
that happens. The manual specifies writing 0 to the counters after
each read, but that's 1) too expensive, and 2) destroys the
possibility of sharing these counters with other users, so we live
with the blimp - the other existing user does too.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
arch/x86/kernel/cpu/Makefile | 2 -
arch/x86/kernel/cpu/sched.c | 58 +++++++++++++++++++++++++++++++++++++++++++
include/linux/sched.h | 4 ++
3 files changed, 63 insertions(+), 1 deletion(-)

Index: linux-2.6/arch/x86/kernel/cpu/Makefile
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/Makefile
+++ linux-2.6/arch/x86/kernel/cpu/Makefile
@@ -13,7 +13,7 @@ CFLAGS_common.o := $(nostackp)

obj-y := intel_cacheinfo.o addon_cpuid_features.o
obj-y += proc.o capflags.o powerflags.o common.o
-obj-y += vmware.o hypervisor.o
+obj-y += vmware.o hypervisor.o sched.o

obj-$(CONFIG_X86_32) += bugs.o cmpxchg.o
obj-$(CONFIG_X86_64) += bugs_64.o
Index: linux-2.6/arch/x86/kernel/cpu/sched.c
===================================================================
--- /dev/null
+++ linux-2.6/arch/x86/kernel/cpu/sched.c
@@ -0,0 +1,58 @@
+#include <linux/sched.h>
+#include <linux/math64.h>
+#include <linux/percpu.h>
+#include <linux/irqflags.h>
+
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+
+static DEFINE_PER_CPU(struct aperfmperf, old_aperfmperf);
+
+static unsigned long scale_aperfmperf(void)
+{
+ struct aperfmperf cur, val, *old = &__get_cpu_var(old_aperfmperf);
+ unsigned long ratio = SCHED_LOAD_SCALE;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ get_aperfmperf(&val);
+ local_irq_restore(flags);
+
+ cur = val;
+ cur.aperf -= old->aperf;
+ cur.mperf -= old->mperf;
+ *old = val;
+
+ cur.mperf >>= SCHED_LOAD_SHIFT;
+ if (cur.mperf)
+ ratio = div_u64(cur.aperf, cur.mperf);
+
+ return ratio;
+}
+
+unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+ /*
+ * do aperf/mperf on the cpu level because it includes things
+ * like turbo mode, which are relevant to full cores.
+ */
+ if (boot_cpu_has(X86_FEATURE_APERFMPERF))
+ return scale_aperfmperf();
+
+ /*
+ * maybe have something cpufreq here
+ */
+
+ return default_scale_freq_power(sd, cpu);
+}
+
+unsigned long arch_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+ /*
+ * aperf/mperf already includes the smt gain
+ */
+ if (boot_cpu_has(X86_FEATURE_APERFMPERF))
+ return SCHED_LOAD_SCALE;
+
+ return default_scale_smt_power(sd, cpu);
+}
Index: linux-2.6/include/linux/sched.h
===================================================================
--- linux-2.6.orig/include/linux/sched.h
+++ linux-2.6/include/linux/sched.h
@@ -1012,6 +1012,10 @@ partition_sched_domains(int ndoms_new, s
}
#endif /* !CONFIG_SMP */

+
+unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
+unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
+
struct io_context; /* See blkdev.h */


--



\
 
 \ /
  Last update: 2009-09-03 15:27    [W:0.063 / U:0.132 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site