The LBR could be enabled on the guest if host perf supports LBR
(checked via x86_perf_get_lbr()) and the vcpu model is compatible
with the host one.
If LBR is disabled on the guest, the bits [0, 5] of the read-only
MSR_IA32_PERF_CAPABILITIES which tells about the record format
stored in the LBR records would be cleared.
Signed-off-by: Like Xu <like.xu@xxxxxxxxxxxxxxx>
Reviewed-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
arch/x86/kvm/vmx/capabilities.h | 1 +
arch/x86/kvm/vmx/pmu_intel.c | 40 +++++++++++++++++++++++++++++++++
arch/x86/kvm/vmx/vmx.h | 12 ++++++++++
3 files changed, 53 insertions(+)
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index a58cf3655351..db1178a66d93 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -19,6 +19,7 @@ extern int __read_mostly pt_mode;
#define PT_MODE_HOST_GUEST 1
#define PMU_CAP_FW_WRITES (1ULL << 13)
+#define PMU_CAP_LBR_FMT 0x3f
struct nested_vmx_msrs {
/*
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index f8083ecf8c7b..91212fe5ec56 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -168,6 +168,39 @@ static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr)
return get_gp_pmc(pmu, msr, MSR_IA32_PMC0);
}
+bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu)
+{
+ struct x86_pmu_lbr *lbr = vcpu_to_lbr_records(vcpu);
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+ if (pmu->version < 2)
+ return false;
+
+ /*
+ * As a first step, a guest could only enable LBR feature if its
+ * cpu model is the same as the host because the LBR registers
+ * would be pass-through to the guest and they're model specific.
+ */
+ if (boot_cpu_data.x86_model != guest_cpuid_model(vcpu))
+ return false;
+
+ return !x86_perf_get_lbr(lbr);
+}
+
+bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu)
+{
+ struct x86_pmu_lbr *lbr = vcpu_to_lbr_records(vcpu);
+ u64 lbr_fmt = vcpu->arch.perf_capabilities & PMU_CAP_LBR_FMT;
+
+ if (lbr->nr && lbr_fmt)
+ return true;
+
+ if (!lbr_fmt || !intel_pmu_lbr_is_compatible(vcpu))
+ return false;
+
+ return true;
+}
+
static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -320,6 +353,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
struct kvm_cpuid_entry2 *entry;
union cpuid10_eax eax;
union cpuid10_edx edx;
+ struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
pmu->nr_arch_gp_counters = 0;
pmu->nr_arch_fixed_counters = 0;
@@ -339,6 +373,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
return;
perf_get_x86_pmu_capability(&x86_pmu);
+ if (!intel_pmu_lbr_is_enabled(vcpu)) {
+ vcpu->arch.perf_capabilities &= ~PMU_CAP_LBR_FMT;
+ lbr_desc->records.nr = 0;
+ }
pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
x86_pmu.num_counters_gp);
@@ -384,6 +422,7 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
{
int i;
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
pmu->gp_counters[i].type = KVM_PMC_GP;
@@ -401,6 +440,7 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
vcpu->arch.perf_capabilities = guest_cpuid_has(vcpu, X86_FEATURE_PDCM) ?
vmx_get_perf_capabilities() : 0;
+ lbr_desc->records.nr = 0;
}
static void intel_pmu_reset(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index adc40d36909c..1b0bbfffa1f0 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -70,6 +70,17 @@ struct pt_desc {
struct pt_ctx guest;
};
+#define vcpu_to_lbr_desc(vcpu) (&to_vmx(vcpu)->lbr_desc)
+#define vcpu_to_lbr_records(vcpu) (&to_vmx(vcpu)->lbr_desc.records)
+
+bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu);
+bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu);
+
+struct lbr_desc {
+ /* Basic info about guest LBR records. */
+ struct x86_pmu_lbr records;
+};
+
/*
* The nested_vmx structure is part of vcpu_vmx, and holds information we need
* for correct emulation of VMX (i.e., nested VMX) on this vcpu.
@@ -279,6 +290,7 @@ struct vcpu_vmx {
u64 ept_pointer;
struct pt_desc pt_desc;
+ struct lbr_desc lbr_desc;
/* Save desired MSR intercept (read: pass-through) state */
#define MAX_POSSIBLE_PASSTHROUGH_MSRS 13
--
2.29.2
