Re: [PATCH v12 07/11] KVM: vmx/pmu: Unmask LBR fields in the MSR_IA32_DEBUGCTLMSR emualtion

[Xiaoyao Li <xiaoyao.li@intel.com>]

On 6/13/2020 4:09 PM, Like Xu wrote:
> When the LBR feature is reported by the vmx_get_perf_capabilities(),
> the LBR fields in the [vmx|vcpu]_supported debugctl should be unmasked.
> 
> The debugctl msr is handled separately in vmx/svm and they're not
> completely identical, hence remove the common msr handling code.
> 
> Signed-off-by: Like Xu <like.xu@linux.intel.com>
> ---
>   arch/x86/kvm/vmx/capabilities.h | 12 ++++++++++++
>   arch/x86/kvm/vmx/pmu_intel.c    | 19 +++++++++++++++++++
>   arch/x86/kvm/x86.c              | 13 -------------
>   3 files changed, 31 insertions(+), 13 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
> index b633a90320ee..f6fcfabb1026 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
> @@ -387,4 +389,14 @@ static inline u64 vmx_get_perf_capabilities(void)
>   	return perf_cap;
>   }
>   
> +static inline u64 vmx_get_supported_debugctl(void)
> +{
> +	u64 val = 0;
> +
> +	if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)
> +		val |= DEBUGCTLMSR_LBR_MASK;
> +
> +	return val;
> +}
> +
>   #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 a953c7d633f6..d92e95b64c74 100644
> --- a/arch/x86/kvm/vmx/pmu_intel.c
> +++ b/arch/x86/kvm/vmx/pmu_intel.c
> @@ -187,6 +187,7 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
>   	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
>   		ret = pmu->version > 1;
>   		break;
> +	case MSR_IA32_DEBUGCTLMSR:
>   	case MSR_IA32_PERF_CAPABILITIES:
>   		ret = 1;
>   		break;
> @@ -237,6 +238,9 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>   			return 1;
>   		msr_info->data = vcpu->arch.perf_capabilities;
>   		return 0;
> +	case MSR_IA32_DEBUGCTLMSR:
> +		msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL);

Can we put the emulation of MSR_IA32_DEBUGCTLMSR in 
vmx_{get/set})_msr(). AFAIK, MSR_IA32_DEBUGCTLMSR is not a pure PMU 
related MSR that there is bit 2 to enable #DB for bus lock.

> +		return 0;
>   	default:
>   		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
>   		    (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
> @@ -282,6 +286,16 @@ static inline bool lbr_is_compatible(struct kvm_vcpu *vcpu)
>   	return true;
>   }
>   
> +static inline u64 vcpu_get_supported_debugctl(struct kvm_vcpu *vcpu)
> +{
> +	u64 debugctlmsr = vmx_get_supported_debugctl();
> +
> +	if (!lbr_is_enabled(vcpu))
> +		debugctlmsr &= ~DEBUGCTLMSR_LBR_MASK;
> +
> +	return debugctlmsr;
> +}
> +
>   static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>   {
>   	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
> @@ -336,6 +350,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>   		}
>   		vcpu->arch.perf_capabilities = data;
>   		return 0;
> +	case MSR_IA32_DEBUGCTLMSR:
> +		if (data & ~vcpu_get_supported_debugctl(vcpu))
> +			return 1;
> +		vmcs_write64(GUEST_IA32_DEBUGCTL, data);
> +		return 0;
>   	default:
>   		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
>   		    (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 00c88c2f34e4..56f275eb4554 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -2840,18 +2840,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>   			return 1;
>   		}
>   		break;
> -	case MSR_IA32_DEBUGCTLMSR:
> -		if (!data) {
> -			/* We support the non-activated case already */
> -			break;
> -		} else if (data & ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF)) {

So after this patch, guest trying to set bit DEBUGCTLMSR_BTF will get a 
#GP instead of being ignored and printing a log in kernel.

These codes were introduced ~12 years ago in commit b5e2fec0ebc3 ("KVM: 
Ignore DEBUGCTL MSRs with no effect"), just to make Netware happy. Maybe 
I'm overthinking for that too old thing.

> -			/* Values other than LBR and BTF are vendor-specific,
> -			   thus reserved and should throw a #GP */
> -			return 1;
> -		}
> -		vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
> -			    __func__, data);
> -		break;
>   	case 0x200 ... 0x2ff:
>   		return kvm_mtrr_set_msr(vcpu, msr, data);
>   	case MSR_IA32_APICBASE:
> @@ -3120,7 +3108,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>   	switch (msr_info->index) {
>   	case MSR_IA32_PLATFORM_ID:
>   	case MSR_IA32_EBL_CR_POWERON:
> -	case MSR_IA32_DEBUGCTLMSR:
>   	case MSR_IA32_LASTBRANCHFROMIP:
>   	case MSR_IA32_LASTBRANCHTOIP:
>   	case MSR_IA32_LASTINTFROMIP:
>