KVM: vmx/pmu: Emulate legacy freezing LBRs on virtual PMI

The current vPMU only supports Architecture Version 2. According to
Intel SDM "17.4.7 Freezing LBR and Performance Counters on PMI", if
IA32_DEBUGCTL.Freeze_LBR_On_PMI = 1, the LBR is frozen on the virtual
PMI and the KVM would emulate to clear the LBR bit (bit 0) in
IA32_DEBUGCTL. Also, guest needs to re-enable IA32_DEBUGCTL.LBR
to resume recording branches.

Signed-off-by: Like Xu <like.xu@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Message-Id: <20210201051039.255478-9-like.xu@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

5 files changed, 39 insertions, 3 deletions

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 67741d2a030851..405890c723a1bf 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -383,8 +383,11 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 
 void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
 {
-	if (lapic_in_kernel(vcpu))
+	if (lapic_in_kernel(vcpu)) {
+		if (kvm_x86_ops.pmu_ops->deliver_pmi)
+			kvm_x86_ops.pmu_ops->deliver_pmi(vcpu);
 		kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC);
+	}
 }
 
 bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 067fef51760c47..742a4e98df8c72 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -39,6 +39,7 @@ struct kvm_pmu_ops {
 	void (*refresh)(struct kvm_vcpu *vcpu);
 	void (*init)(struct kvm_vcpu *vcpu);
 	void (*reset)(struct kvm_vcpu *vcpu);
+	void (*deliver_pmi)(struct kvm_vcpu *vcpu);
 };
 
 static inline u64 pmc_bitmask(struct kvm_pmc *pmc)
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 787edd8c1fc784..8e6179586e2714 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -21,6 +21,8 @@ extern int __read_mostly pt_mode;
 #define PMU_CAP_FW_WRITES	(1ULL << 13)
 #define PMU_CAP_LBR_FMT		0x3f
 
+#define DEBUGCTLMSR_LBR_MASK		(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI)
+
 struct nested_vmx_msrs {
 	/*
 	 * We only store the "true" versions of the VMX capability MSRs. We
@@ -390,7 +392,7 @@ static inline u64 vmx_supported_debugctl(void)
 	u64 debugctl = 0;
 
 	if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)
-		debugctl |= DEBUGCTLMSR_LBR;
+		debugctl |= DEBUGCTLMSR_LBR_MASK;
 
 	return debugctl;
 }
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 254d9fc09863d4..7928d6dee0a26d 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -586,6 +586,35 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
 	intel_pmu_release_guest_lbr_event(vcpu);
 }
 
+/*
+ * Emulate LBR_On_PMI behavior for 1 < pmu.version < 4.
+ *
+ * If Freeze_LBR_On_PMI = 1, the LBR is frozen on PMI and
+ * the KVM emulates to clear the LBR bit (bit 0) in IA32_DEBUGCTL.
+ *
+ * Guest needs to re-enable LBR to resume branches recording.
+ */
+static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu)
+{
+	u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+
+	if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) {
+		data &= ~DEBUGCTLMSR_LBR;
+		vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+	}
+}
+
+static void intel_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
+{
+	u8 version = vcpu_to_pmu(vcpu)->version;
+
+	if (!intel_pmu_lbr_is_enabled(vcpu))
+		return;
+
+	if (version > 1 && version < 4)
+		intel_pmu_legacy_freezing_lbrs_on_pmi(vcpu);
+}
+
 static void vmx_update_intercept_for_lbr_msrs(struct kvm_vcpu *vcpu, bool set)
 {
 	struct x86_pmu_lbr *lbr = vcpu_to_lbr_records(vcpu);
@@ -672,4 +701,5 @@ struct kvm_pmu_ops intel_pmu_ops = {
 	.refresh = intel_pmu_refresh,
 	.init = intel_pmu_init,
 	.reset = intel_pmu_reset,
+	.deliver_pmi = intel_pmu_deliver_pmi,
 };
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e2f8c3c68f02b0..9169c700874e66 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1963,7 +1963,7 @@ static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu)
 	u64 debugctl = vmx_supported_debugctl();
 
 	if (!intel_pmu_lbr_is_enabled(vcpu))
-		debugctl &= ~DEBUGCTLMSR_LBR;
+		debugctl &= ~DEBUGCTLMSR_LBR_MASK;
 
 	return debugctl;
 }