Skip to contentSkip to conversation

x86: sched: Provide arch implementations using aperf/mperf

tip:sched/core tip-bot for Peter Zijlstra 1 participant 1 message Sep 16, 2009

Subsystems (2)
lore
Share & tools
lore
#0 lore raw
Commit-ID:  47fe38fcff0517e67d395c039d2e26d2de688a60
Gitweb:     http://git.kernel.org/tip/47fe38fcff0517e67d395c039d2e26d2de688a60
Author:     Peter Zijlstra <[email protected]>
AuthorDate: Wed, 2 Sep 2009 13:49:18 +0200
Committer:  Ingo Molnar <[email protected]>
CommitDate: Tue, 15 Sep 2009 16:51:27 +0200

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.

LKML-Reference: <new-submission>

---
 arch/x86/kernel/cpu/Makefile |    2 +-
 arch/x86/kernel/cpu/sched.c  |   55 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/sched.h        |    4 +++
 3 files changed, 60 insertions(+), 1 deletions(-)
arch/x86/kernel/cpu/Makefile +1 -1
index c1f253d..8dd3063 100644
@@ -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
arch/x86/kernel/cpu/sched.c new file +55 -0

55 lines not on this page · raw message

include/linux/sched.h +4 -0
index c30bf3d..fc4c0f9 100644
@@ -992,6 +992,9 @@ static inline int test_sd_parent(struct sched_domain *sd, int flag)
 	return 0;
 }
 
+unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
+unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
+
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
@@ -1003,6 +1006,7 @@ partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
 }
 #endif	/* !CONFIG_SMP */
 
+
 struct io_context;			/* See blkdev.h */