Re: [PATCH v11 07/16] KVM: vmx/pmu: Emulate MSR_ARCH_LBR_CTL for guest Arch LBR

["Liang, Kan" <kan.liang@xxxxxxxxxxxxxxx>]

On 5/5/2022 11:32 PM, Yang Weijiang wrote:
> From: Like Xu <like.xu@xxxxxxxxxxxxxxx>
>
> Arch LBR is 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. Clear guest LBR enable bit on host PMI handling so
> guest can see expected config.
>
> 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 preserved on INIT.
>
> Regardless of the Arch LBR or legacy LBR, when the LBR_EN bit 0 of the
> corresponding control MSR is set to 1, LBR recording will be enabled.
>
> Signed-off-by: Like Xu <like.xu@xxxxxxxxxxxxxxx>
> Co-developed-by: Yang Weijiang <weijiang.yang@xxxxxxxxx>
> Signed-off-by: Yang Weijiang <weijiang.yang@xxxxxxxxx>

Reviewed-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>

> ---
>   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     | 57 ++++++++++++++++++++++++++++----
>   arch/x86/kvm/vmx/vmx.c           | 12 +++++++
>   5 files changed, 66 insertions(+), 8 deletions(-)
>
> diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
> index 4529ce448b2e..4fe6c3b50fc3 100644
> --- a/arch/x86/events/intel/lbr.c
> +++ b/arch/x86/events/intel/lbr.c
> @@ -160,8 +160,6 @@ 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 ee15311b6be1..fdf0e3097e0b 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 e2b5fc1f4f1a..aa36d2072b91 100644
> --- a/arch/x86/kvm/vmx/pmu_intel.c
> +++ b/arch/x86/kvm/vmx/pmu_intel.c
> @@ -19,6 +19,7 @@
>   #include "pmu.h"
>   
>   #define MSR_PMC_FULL_WIDTH_BIT      (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0)
> +#define KVM_ARCH_LBR_CTL_MASK  (ARCH_LBR_CTL_MASK | ARCH_LBR_CTL_LBREN)
>   
>   static struct kvm_event_hw_type_mapping intel_arch_events[] = {
>   	[0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES },
> @@ -192,7 +193,7 @@ static bool intel_pmu_is_valid_lbr_msr(struct kvm_vcpu *vcpu, u32 index)
>   	if (!intel_pmu_lbr_is_enabled(vcpu))
>   		return ret;
>   
> -	if (index == MSR_ARCH_LBR_DEPTH) {
> +	if (index == MSR_ARCH_LBR_DEPTH || index == MSR_ARCH_LBR_CTL) {
>   		if (kvm_cpu_cap_has(X86_FEATURE_ARCH_LBR))
>   			ret = guest_cpuid_has(vcpu, X86_FEATURE_ARCH_LBR);
>   		return ret;
> @@ -363,6 +364,33 @@ static bool arch_lbr_depth_is_valid(struct kvm_vcpu *vcpu, u64 depth)
>   	return (depth == pmu->kvm_arch_lbr_depth);
>   }
>   
> +static bool arch_lbr_ctl_is_valid(struct kvm_vcpu *vcpu, u64 ctl)
> +{
> +	struct kvm_cpuid_entry2 *entry;
> +
> +	if (!kvm_cpu_cap_has(X86_FEATURE_ARCH_LBR))
> +		return false;
> +
> +	if (ctl & ~KVM_ARCH_LBR_CTL_MASK)
> +		goto warn;
> +
> +	entry = kvm_find_cpuid_entry(vcpu, 0x1c, 0);
> +	if (!entry)
> +		return false;
> +
> +	if (!(entry->ebx & BIT(0)) && (ctl & ARCH_LBR_CTL_CPL))
> +		return false;
> +	if (!(entry->ebx & BIT(2)) && (ctl & ARCH_LBR_CTL_STACK))
> +		return false;
> +	if (!(entry->ebx & BIT(1)) && (ctl & ARCH_LBR_CTL_FILTER))
> +		return false;
> +	return true;
> +warn:
> +	pr_warn_ratelimited("kvm: vcpu-%d: invalid arch lbr ctl.\n",
> +			    vcpu->vcpu_id);
> +	return false;
> +}
> +
>   static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>   {
>   	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
> @@ -386,6 +414,9 @@ 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 +488,16 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>   		 */
>   		wrmsrl(MSR_ARCH_LBR_DEPTH, lbr_desc->records.nr);
>   		return 0;
> +	case MSR_ARCH_LBR_CTL:
> +		if (!arch_lbr_ctl_is_valid(vcpu, data))
> +			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))) {
> @@ -666,12 +707,16 @@ 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 (kvm_cpu_cap_has(X86_FEATURE_ARCH_LBR) &&
> +	    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) & ~0x1ULL);
>   }
>   
>   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 d58b763df855..b6bc7d97e4b4 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -2022,6 +2022,13 @@ 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))
> @@ -4553,6 +4560,11 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
>   	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
>   
>   	vpid_sync_context(vmx->vpid);
> +
> +	if (!init_event) {
> +		if (static_cpu_has(X86_FEATURE_ARCH_LBR))
> +			vmcs_write64(GUEST_IA32_LBR_CTL, 0);
> +	}
>   }
>   
>   static void vmx_enable_irq_window(struct kvm_vcpu *vcpu)