[PATCH v14 04/11] KVM: vmx/pmu: Expose DEBUGCTLMSR_LBR in the MSR_IA32_DEBUGCTLMSR

[Like Xu <like.xu@xxxxxxxxxxxxxxx>]

When the DEBUGCTLMSR_LBR bit 0 is set, the processor records a running
trace of the most recent branches, interrupts, and/or exceptions taken
by the processor (prior to a debug exception being generated) in the
last branch record (LBR) stack.

Adding vcpu_supported_debugctl() to throw #GP for DEBUGCTLMSR_LBR
based on per-guest LBR setting.

Signed-off-by: Like Xu <like.xu@xxxxxxxxxxxxxxx>
---
 arch/x86/kvm/vmx/capabilities.h |  7 ++++++-
 arch/x86/kvm/vmx/pmu_intel.c    |  7 +++++++
 arch/x86/kvm/vmx/vmx.c          | 28 +++++++++++++++++-----------
 arch/x86/kvm/vmx/vmx.h          |  1 +
 4 files changed, 31 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index db1178a66d93..62aa7a701ebb 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -381,7 +381,12 @@ static inline u64 vmx_get_perf_capabilities(void)
 
 static inline u64 vmx_supported_debugctl(void)
 {
-	return DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF;
+	u64 debugctl = DEBUGCTLMSR_BTF;
+
+	if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)
+		debugctl |= DEBUGCTLMSR_LBR;
+
+	return debugctl;
 }
 
 #endif /* __KVM_X86_VMX_CAPS_H */
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 01b2cd8eca47..e75a957b2068 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -183,6 +183,13 @@ bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu)
 	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);
+
+	return lbr->nr && (vcpu->arch.perf_capabilities & PMU_CAP_LBR_FMT);
+}
+
 static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index af9c7632ecfa..3c008dec407c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1925,7 +1925,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		goto find_uret_msr;
 	case MSR_IA32_DEBUGCTLMSR:
-		msr_info->data = 0;
+		msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL);
 		break;
 	default:
 	find_uret_msr:
@@ -1950,6 +1950,16 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
 	return (unsigned long)data;
 }
 
+static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu)
+{
+	u64 debugctl = vmx_supported_debugctl();
+
+	if (!intel_pmu_lbr_is_enabled(vcpu))
+		debugctl &= ~DEBUGCTLMSR_LBR;
+
+	return debugctl;
+}
+
 /*
  * Writes msr value into the appropriate "register".
  * Returns 0 on success, non-0 otherwise.
@@ -2005,18 +2015,14 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 						VM_EXIT_SAVE_DEBUG_CONTROLS)
 			get_vmcs12(vcpu)->guest_ia32_debugctl = data;
 
-		if (!data) {
-			/* We support the non-activated case already */
-			return 0;
-		} else if (data & ~vmx_supported_debugctl()) {
-			/*
-			 * Values other than LBR and BTF are vendor-specific,
-			 * thus reserved and should throw a #GP.
-			 */
+		if (data & ~vcpu_supported_debugctl(vcpu))
 			return 1;
+		if (data & DEBUGCTLMSR_BTF) {
+			vcpu_unimpl(vcpu, "%s: BTF in MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
+			__func__, data);
+			data &= ~DEBUGCTLMSR_BTF;
 		}
-		vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
-			    __func__, data);
+		vmcs_write64(GUEST_IA32_DEBUGCTL, data);
 		return 0;
 	case MSR_IA32_BNDCFGS:
 		if (!kvm_mpx_supported() ||
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 095e357e5316..1b0bbfffa1f0 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -74,6 +74,7 @@ struct pt_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. */
-- 
2.29.2