Re: [PATCH v8 22/26] KVM: VMX: Set up interception for CET MSRs

["Yang, Weijiang" <weijiang.yang@intel.com>]

On 1/15/2024 5:58 PM, Yuan Yao wrote:
> On Thu, Dec 21, 2023 at 09:02:35AM -0500, Yang Weijiang wrote:
>> Enable/disable CET MSRs interception per associated feature configuration.
>> Shadow Stack feature requires all CET MSRs passed through to guest to make
>> it supported in user and supervisor mode while IBT feature only depends on
>> MSR_IA32_{U,S}_CETS_CET to enable user and supervisor IBT.
>>
>> Note, this MSR design introduced an architectural limitation of SHSTK and
>> IBT control for guest, i.e., when SHSTK is exposed, IBT is also available
>> to guest from architectual perspective since IBT relies on subset of SHSTK
>> relevant MSRs.
>>
>> Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
>> ---
>>   arch/x86/kvm/vmx/vmx.c | 42 ++++++++++++++++++++++++++++++++++++++++++
>>   1 file changed, 42 insertions(+)
>>
>> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
>> index 064a5fe87948..08058b182893 100644
>> --- a/arch/x86/kvm/vmx/vmx.c
>> +++ b/arch/x86/kvm/vmx/vmx.c
>> @@ -692,6 +692,10 @@ static bool is_valid_passthrough_msr(u32 msr)
>>   	case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8:
>>   		/* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */
>>   		return true;
>> +	case MSR_IA32_U_CET:
>> +	case MSR_IA32_S_CET:
>> +	case MSR_IA32_PL0_SSP ... MSR_IA32_INT_SSP_TAB:
>> +		return true;
>>   	}
>>
>>   	r = possible_passthrough_msr_slot(msr) != -ENOENT;
>> @@ -7767,6 +7771,42 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
>>   		vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4));
>>   }
>>
>> +static void vmx_update_intercept_for_cet_msr(struct kvm_vcpu *vcpu)
>> +{
>> +	bool incpt;
>> +
>> +	if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) {
>> +		incpt = !guest_cpuid_has(vcpu, X86_FEATURE_SHSTK);
>> +
>> +		vmx_set_intercept_for_msr(vcpu, MSR_IA32_U_CET,
>> +					  MSR_TYPE_RW, incpt);
>> +		vmx_set_intercept_for_msr(vcpu, MSR_IA32_S_CET,
>> +					  MSR_TYPE_RW, incpt);
>> +		vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL0_SSP,
>> +					  MSR_TYPE_RW, incpt);
>> +		vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL1_SSP,
>> +					  MSR_TYPE_RW, incpt);
>> +		vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL2_SSP,
>> +					  MSR_TYPE_RW, incpt);
>> +		vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL3_SSP,
>> +					  MSR_TYPE_RW, incpt);
>> +		if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
> Looks this leading to MSR_IA32_INT_SSP_TAB not intercepted
> after below steps:
>
> Step 1. User space set cpuid w/  X86_FEATURE_LM, w/  SHSTK.
> Step 2. User space set cpuid w/o X86_FEATURE_LM, w/o SHSTK.
>
> Then MSR_IA32_INT_SSP_TAB won't be intercepted even w/o SHSTK
> on guest cpuid, will this lead to inconsistency when do
> rdmsr(MSR_IA32_INT_SSP_TAB) from guest in this scenario ?

Yes, theoretically it's possible, how about changing it as below?

vmx_set_intercept_for_msr(vcpu, MSR_IA32_INT_SSP_TAB,
			  MSR_TYPE_RW,
			  incpt | !guest_cpuid_has(vcpu, X86_FEATURE_LM));

>
>> +			vmx_set_intercept_for_msr(vcpu, MSR_IA32_INT_SSP_TAB,
>> +						  MSR_TYPE_RW, incpt);
>> +		if (!incpt)
>> +			return;
>> +	}
>> +
>> +	if (kvm_cpu_cap_has(X86_FEATURE_IBT)) {
>> +		incpt = !guest_cpuid_has(vcpu, X86_FEATURE_IBT);
>> +
>> +		vmx_set_intercept_for_msr(vcpu, MSR_IA32_U_CET,
>> +					  MSR_TYPE_RW, incpt);
>> +		vmx_set_intercept_for_msr(vcpu, MSR_IA32_S_CET,
>> +					  MSR_TYPE_RW, incpt);
>> +	}
>> +}
>> +
>>   static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
>>   {
>>   	struct vcpu_vmx *vmx = to_vmx(vcpu);
>> @@ -7845,6 +7885,8 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
>>
>>   	/* Refresh #PF interception to account for MAXPHYADDR changes. */
>>   	vmx_update_exception_bitmap(vcpu);
>> +
>> +	vmx_update_intercept_for_cet_msr(vcpu);
>>   }
>>
>>   static u64 vmx_get_perf_capabilities(void)
>> --
>> 2.39.3
>>
>>