From: Jim Mattson <jmattson@xxxxxxxxxx>
In preparation for KVM pass-through of IA32_APERF and IA32_MPERF,
introduce wrappers that read these MSRs. Going forward, all kernel
code that needs host APERF/MPERF values should use these wrappers
instead of rdmsrl().
While these functions currently just read the MSRs directly, future
patches will enhance them to handle cases where the MSRs contain guest
values. Moving all host APERF/MPERF reads to use these functions now
will make it easier to add this functionality later.
No functional change intended.
Signed-off-by: Jim Mattson <jmattson@xxxxxxxxxx>
Reviewed-by: Mingwei Zhang <mizhang@xxxxxxxxxx>
Signed-off-by: Mingwei Zhang <mizhang@xxxxxxxxxx>
---
arch/x86/include/asm/topology.h | 3 +++
arch/x86/kernel/cpu/aperfmperf.c | 22 ++++++++++++++++++----
drivers/cpufreq/amd-pstate.c | 4 ++--
drivers/cpufreq/intel_pstate.c | 5 +++--
4 files changed, 26 insertions(+), 8 deletions(-)
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 92f3664dd933b..2ef9903cf85d7 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -302,6 +302,9 @@ static inline void arch_set_max_freq_ratio(bool turbo_disabled) { }
static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { }
#endif
+extern u64 get_host_aperf(void);
+extern u64 get_host_mperf(void);
+
extern void arch_scale_freq_tick(void);
#define arch_scale_freq_tick arch_scale_freq_tick
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index f642de2ebdac8..3be5070ba3361 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -40,8 +40,8 @@ static void init_counter_refs(void)
{
u64 aperf, mperf;
- rdmsrl(MSR_IA32_APERF, aperf);
- rdmsrl(MSR_IA32_MPERF, mperf);
+ aperf = get_host_aperf();
+ mperf = get_host_mperf();
this_cpu_write(cpu_samples.aperf, aperf);
this_cpu_write(cpu_samples.mperf, mperf);
@@ -94,6 +94,20 @@ void arch_set_max_freq_ratio(bool turbo_disabled)
}
EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio);
+u64 get_host_aperf(void)
+{
+ WARN_ON_ONCE(!irqs_disabled());
+ return native_read_msr(MSR_IA32_APERF);
+}
+EXPORT_SYMBOL_GPL(get_host_aperf);
+
+u64 get_host_mperf(void)
+{
+ WARN_ON_ONCE(!irqs_disabled());
+ return native_read_msr(MSR_IA32_MPERF);
+}
+EXPORT_SYMBOL_GPL(get_host_mperf);
+
static bool __init turbo_disabled(void)
{
u64 misc_en;
@@ -474,8 +488,8 @@ void arch_scale_freq_tick(void)
if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
return;
- rdmsrl(MSR_IA32_APERF, aperf);
- rdmsrl(MSR_IA32_MPERF, mperf);
+ aperf = get_host_aperf();
+ mperf = get_host_mperf();
acnt = aperf - s->aperf;
mcnt = mperf - s->mperf;
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index b63863f77c677..c26092284be56 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -446,8 +446,8 @@ static inline bool amd_pstate_sample(struct amd_cpudata *cpudata)
unsigned long flags;
local_irq_save(flags);
- rdmsrl(MSR_IA32_APERF, aperf);
- rdmsrl(MSR_IA32_MPERF, mperf);
+ aperf = get_host_aperf();
+ mperf = get_host_mperf();
tsc = rdtsc();
if (cpudata->prev.mperf == mperf || cpudata->prev.tsc == tsc) {
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 400337f3b572d..993a66095547f 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -27,6 +27,7 @@
#include <linux/vmalloc.h>
#include <linux/pm_qos.h>
#include <linux/bitfield.h>
+#include <linux/topology.h>
#include <trace/events/power.h>
#include <asm/cpu.h>
@@ -2423,8 +2424,8 @@ static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time)
u64 tsc;
local_irq_save(flags);
- rdmsrl(MSR_IA32_APERF, aperf);
- rdmsrl(MSR_IA32_MPERF, mperf);
+ aperf = get_host_aperf();
+ mperf = get_host_mperf();
tsc = rdtsc();
if (cpu->prev_mperf == mperf || cpu->prev_tsc == tsc) {
local_irq_restore(flags);
--
2.47.0.371.ga323438b13-goog
