[PATCH 1/6] KVM: x86/pmu: Cap kvm_pmu_cap.num_counters_gp at KVM's internal max

From: Sean Christopherson
Date: Tue Jan 24 2023 - 18:49:21 EST


Limit kvm_pmu_cap.num_counters_gp during kvm_init_pmu_capability() based
on the vendor PMU capabilities so that consuming num_counters_gp naturally
does the right thing. This fixes a mostly theoretical bug where KVM could
over-report its PMU support in KVM_GET_SUPPORTED_CPUID for leaf 0xA, e.g.
if the number of counters reported by perf is greater than KVM's
hardcoded internal limit. Incorporating input from the AMD PMU also
avoids over-reporting MSRs to save when running on AMD.

Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
---
arch/x86/kvm/pmu.h | 5 ++++-
arch/x86/kvm/svm/pmu.c | 1 +
arch/x86/kvm/vmx/pmu_intel.c | 1 +
arch/x86/kvm/x86.c | 6 +++---
4 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 30bfccc6df60..8c04e9109db0 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -42,6 +42,7 @@ struct kvm_pmu_ops {
void (*cleanup)(struct kvm_vcpu *vcpu);

const u64 EVENTSEL_EVENT;
+ const int MAX_NR_GP_COUNTERS;
};

void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops);
@@ -163,7 +164,7 @@ static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)

extern struct x86_pmu_capability kvm_pmu_cap;

-static inline void kvm_init_pmu_capability(void)
+static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops)
{
bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL;

@@ -182,6 +183,8 @@ static inline void kvm_init_pmu_capability(void)
}

kvm_pmu_cap.version = min(kvm_pmu_cap.version, 2);
+ kvm_pmu_cap.num_counters_gp = min(kvm_pmu_cap.num_counters_gp,
+ pmu_ops->MAX_NR_GP_COUNTERS);
kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed,
KVM_PMC_MAX_FIXED);
}
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 5da8c292e3e3..cc77a0681800 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -232,4 +232,5 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = {
.init = amd_pmu_init,
.reset = amd_pmu_reset,
.EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT,
+ .MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC,
};
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 7980fda3978d..5d525d677967 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -812,4 +812,5 @@ struct kvm_pmu_ops intel_pmu_ops __initdata = {
.deliver_pmi = intel_pmu_deliver_pmi,
.cleanup = intel_pmu_cleanup,
.EVENTSEL_EVENT = ARCH_PERFMON_EVENTSEL_EVENT,
+ .MAX_NR_GP_COUNTERS = KVM_INTEL_PMC_MAX_GENERIC,
};
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index da02a08e21b5..ad95ce92a154 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7061,12 +7061,12 @@ static void kvm_init_msr_list(void)
break;
case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX:
if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
- min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
+ kvm_pmu_cap.num_counters_gp)
continue;
break;
case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX:
if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
- min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
+ kvm_pmu_cap.num_counters_gp)
continue;
break;
case MSR_IA32_XFD:
@@ -9386,7 +9386,7 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
if (boot_cpu_has(X86_FEATURE_XSAVES))
rdmsrl(MSR_IA32_XSS, host_xss);

- kvm_init_pmu_capability();
+ kvm_init_pmu_capability(ops->pmu_ops);

r = ops->hardware_setup();
if (r != 0)
--
2.39.1.456.gfc5497dd1b-goog