On Wed, Mar 03, 2021, Like Xu wrote:
> diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
> index 25d620685ae7..d14a14eb712d 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 0x7f000f
It would nice to build this up with the individual bits instead of tossing in a
magic number.
> static struct kvm_event_hw_type_mapping intel_arch_events[] = {
> /* Index must match CPUID 0x0A.EBX bit vector */
> @@ -221,6 +222,7 @@ 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 +392,9 @@ 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 +462,15 @@ 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)) {
Maybe invert this to reduce indentation?
if (data & ...)
break; (or "return 1;")
> + vmcs_write64(GUEST_IA32_LBR_CTL, data);
> + if (intel_pmu_lbr_is_enabled(vcpu) && !lbr_desc->event &&
> + (data & ARCH_LBR_CTL_LBREN))
Alignment.
> + intel_pmu_create_guest_lbr_event(vcpu);
> + return 0;
> + }
> + break;
> default:
> if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
> (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
> @@ -635,12 +649,15 @@ 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) & ~BIT(0));
Use ARCH_LBR_CTL_LBREN?
> }
>
> 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 6d7e760fdfa0..a0660b9934c6 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -2036,6 +2036,13 @@ 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))
> @@ -4463,6 +4470,8 @@ 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);
Not that any guest is likely to care, but is the MSR cleared on INIT? The SDM
has specific language for warm reset, but I can't find anything for INIT.
On a warm reset, all LBR MSRs, including IA32_LBR_DEPTH, have their values
preserved. However, IA32_LBR_CTL.LBREn is cleared to 0, disabling LBRs. If a
warm reset is triggered while the processor is in C6, also known as warm init,
all LBR MSRs will be reset to their initial values.
> }
>
> kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
> --
> 2.29.2
>
