[RESEND PATCH v4 04/10] KVM: vmx/pmu: Add MSR_ARCH_LBR_CTL emulation for Arch LBR

[Like Xu <like.xu@linux.intel.com>]

Arch LBRs are enabled by setting MSR_ARCH_LBR_CTL.LBREn to 1. A new guest
state field named "Guest IA32_LBR_CTL" is added to enhance guest LBR usage.
When guest Arch LBR is enabled, a guest LBR event will be created like the
model-specific LBR does.

On processors that support Arch LBR, MSR_IA32_DEBUGCTLMSR[bit 0] has no
meaning. It can be written to 0 or 1, but reads will always return 0.
Like IA32_DEBUGCTL, IA32_ARCH_LBR_CTL msr is also reserved on INIT.

Signed-off-by: Like Xu <like.xu@linux.intel.com>
---
 arch/x86/events/intel/lbr.c      |  2 --
 arch/x86/include/asm/msr-index.h |  1 +
 arch/x86/include/asm/vmx.h       |  2 ++
 arch/x86/kvm/vmx/pmu_intel.c     | 31 ++++++++++++++++++++++++++-----
 arch/x86/kvm/vmx/vmx.c           |  9 +++++++++
 5 files changed, 38 insertions(+), 7 deletions(-)

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index f72276f4a5ce..df965fee5988 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -168,8 +168,6 @@ enum {
 	 ARCH_LBR_RETURN		|\
 	 ARCH_LBR_OTHER_BRANCH)
 
-#define ARCH_LBR_CTL_MASK			0x7f000e
-
 static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
 
 static __always_inline bool is_lbr_call_stack_bit_set(u64 config)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 742d89a00721..5d84e8e21330 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -169,6 +169,7 @@
 #define LBR_INFO_BR_TYPE		(0xfull << LBR_INFO_BR_TYPE_OFFSET)
 
 #define MSR_ARCH_LBR_CTL		0x000014ce
+#define ARCH_LBR_CTL_MASK		0x7f000e
 #define ARCH_LBR_CTL_LBREN		BIT(0)
 #define ARCH_LBR_CTL_CPL_OFFSET		1
 #define ARCH_LBR_CTL_CPL		(0x3ull << ARCH_LBR_CTL_CPL_OFFSET)
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 0ffaa3156a4e..ea3be961cc8e 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -245,6 +245,8 @@ enum vmcs_field {
 	GUEST_BNDCFGS_HIGH              = 0x00002813,
 	GUEST_IA32_RTIT_CTL		= 0x00002814,
 	GUEST_IA32_RTIT_CTL_HIGH	= 0x00002815,
+	GUEST_IA32_LBR_CTL		= 0x00002816,
+	GUEST_IA32_LBR_CTL_HIGH		= 0x00002817,
 	HOST_IA32_PAT			= 0x00002c00,
 	HOST_IA32_PAT_HIGH		= 0x00002c01,
 	HOST_IA32_EFER			= 0x00002c02,
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index d9c9cb6c9a4b..15490d31b828 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -19,6 +19,12 @@
 #include "pmu.h"
 
 #define MSR_PMC_FULL_WIDTH_BIT      (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0)
+/*
+ * Regardless of the Arch LBR or legacy LBR, when the LBREn bit 0 of the
+ * corresponding control MSR is set to 1, LBR recording will be enabled.
+ */
+#define LBR_CTL_EN	BIT(0)
+#define KVM_ARCH_LBR_CTL_MASK	(ARCH_LBR_CTL_MASK | LBR_CTL_EN)
 
 static struct kvm_event_hw_type_mapping intel_arch_events[] = {
 	/* Index must match CPUID 0x0A.EBX bit vector */
@@ -221,6 +227,7 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 		ret = pmu->version > 1;
 		break;
 	case MSR_ARCH_LBR_DEPTH:
+	case MSR_ARCH_LBR_CTL:
 		ret = guest_cpuid_has(vcpu, X86_FEATURE_ARCH_LBR);
 		break;
 	default:
@@ -390,6 +397,9 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_ARCH_LBR_DEPTH:
 		msr_info->data = lbr_desc->records.nr;
 		return 0;
+	case MSR_ARCH_LBR_CTL:
+		msr_info->data = vmcs_read64(GUEST_IA32_LBR_CTL);
+		return 0;
 	default:
 		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
 		    (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
@@ -457,6 +467,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		lbr_desc->records.nr = data;
 		lbr_desc->arch_lbr_reset = true;
 		return 0;
+	case MSR_ARCH_LBR_CTL:
+		if (data & ~KVM_ARCH_LBR_CTL_MASK)
+			break;
+		vmcs_write64(GUEST_IA32_LBR_CTL, data);
+		if (intel_pmu_lbr_is_enabled(vcpu) && !lbr_desc->event &&
+		    (data & ARCH_LBR_CTL_LBREN))
+			intel_pmu_create_guest_lbr_event(vcpu);
+		return 0;
 	default:
 		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
 		    (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
@@ -635,12 +653,15 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
  */
 static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu)
 {
-	u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+	u32 lbr_ctl_field = GUEST_IA32_DEBUGCTL;
 
-	if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) {
-		data &= ~DEBUGCTLMSR_LBR;
-		vmcs_write64(GUEST_IA32_DEBUGCTL, data);
-	}
+	if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI))
+		return;
+
+	if (guest_cpuid_has(vcpu, X86_FEATURE_ARCH_LBR))
+		lbr_ctl_field = GUEST_IA32_LBR_CTL;
+
+	vmcs_write64(lbr_ctl_field, vmcs_read64(lbr_ctl_field) & ~LBR_CTL_EN);
 }
 
 static void intel_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f2fd447eed45..458d84672104 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2087,6 +2087,13 @@ 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;
 
+		/*
+		 * For Arch LBR, IA32_DEBUGCTL[bit 0] has no meaning.
+		 * It can be written to 0 or 1, but reads will always return 0.
+		 */
+		if (guest_cpuid_has(vcpu, X86_FEATURE_ARCH_LBR))
+			data &= ~DEBUGCTLMSR_LBR;
+
 		vmcs_write64(GUEST_IA32_DEBUGCTL, data);
 		if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event &&
 		    (data & DEBUGCTLMSR_LBR))
@@ -4526,6 +4533,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		vmcs_writel(GUEST_SYSENTER_ESP, 0);
 		vmcs_writel(GUEST_SYSENTER_EIP, 0);
 		vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+		if (cpu_has_vmx_arch_lbr())
+			vmcs_write64(GUEST_IA32_LBR_CTL, 0);
 	}
 
 	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
-- 
2.31.1