[RFC,02/22] x86/aperfmperf: Introduce set_guest_[am]perf()

Commit Message

Mingwei Zhang Nov. 21, 2024, 6:52 p.m. UTC

From: Jim Mattson <[e-mail]>

KVM guests need access to IA32_APERF and IA32_MPERF to observe their
effective CPU frequency, but intercepting reads of these MSRs is too
expensive since Linux guests read them every scheduler tick (250 Hz by
default). Allow the guest to read these MSRs without interception by
loading guest values into the hardware MSRs.

When loading a guest value into IA32_APERF or IA32_MPERF:
1. Query the current host value
2. Record the offset between guest and host values in a per-CPU variable
3. Load the guest value into the MSR

Modify get_host_[am]perf() to add the per-CPU offset to the raw MSR
value, so that host kernel code can still obtain correct host values
even when the MSRs contain guest values.

Signed-off-by: Jim Mattson <[e-mail]>
Reviewed-by: Mingwei Zhang <[e-mail]>
Signed-off-by: Mingwei Zhang <[e-mail]>
---
 arch/x86/include/asm/topology.h  |  5 +++++
 arch/x86/kernel/cpu/aperfmperf.c | 31 +++++++++++++++++++++++++++++--
 2 files changed, 34 insertions(+), 2 deletions(-)

Patch

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 2ef9903cf85d7..fef5846c01976 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -302,8 +302,13 @@  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
 
+DECLARE_PER_CPU(u64, host_aperf_offset);
+DECLARE_PER_CPU(u64, host_mperf_offset);
+
 extern u64 get_host_aperf(void);
 extern u64 get_host_mperf(void);
+extern void set_guest_aperf(u64 aperf);
+extern void set_guest_mperf(u64 mperf);
 
 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 3be5070ba3361..8b66872aa98c1 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -94,20 +94,47 @@  void arch_set_max_freq_ratio(bool turbo_disabled)
 }
 EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio);
 
+DEFINE_PER_CPU(u64, host_aperf_offset);
+DEFINE_PER_CPU(u64, host_mperf_offset);
+
 u64 get_host_aperf(void)
 {
 	WARN_ON_ONCE(!irqs_disabled());
-	return native_read_msr(MSR_IA32_APERF);
+	return native_read_msr(MSR_IA32_APERF) +
+		this_cpu_read(host_aperf_offset);
 }
 EXPORT_SYMBOL_GPL(get_host_aperf);
 
 u64 get_host_mperf(void)
 {
 	WARN_ON_ONCE(!irqs_disabled());
-	return native_read_msr(MSR_IA32_MPERF);
+	return native_read_msr(MSR_IA32_MPERF) +
+		this_cpu_read(host_mperf_offset);
 }
 EXPORT_SYMBOL_GPL(get_host_mperf);
 
+void set_guest_aperf(u64 guest_aperf)
+{
+	u64 host_aperf;
+
+	WARN_ON_ONCE(!irqs_disabled());
+	host_aperf = get_host_aperf();
+	wrmsrl(MSR_IA32_APERF, guest_aperf);
+	this_cpu_write(host_aperf_offset, host_aperf - guest_aperf);
+}
+EXPORT_SYMBOL_GPL(set_guest_aperf);
+
+void set_guest_mperf(u64 guest_mperf)
+{
+	u64 host_mperf;
+
+	WARN_ON_ONCE(!irqs_disabled());
+	host_mperf = get_host_mperf();
+	wrmsrl(MSR_IA32_MPERF, guest_mperf);
+	this_cpu_write(host_mperf_offset, host_mperf - guest_mperf);
+}
+EXPORT_SYMBOL_GPL(set_guest_mperf);
+
 static bool __init turbo_disabled(void)
 {
 	u64 misc_en;