Re: [PATCH v6 19/25] KVM: VMX: Emulate read and write to CET MSRs

[Maxim Levitsky <mlevitsk@redhat.com>]

On Thu, 2023-09-14 at 02:33 -0400, Yang Weijiang wrote:
> Add emulation interface for CET MSR access. The emulation code is split
> into common part and vendor specific part. The former does common check
> for MSRs and reads/writes directly from/to XSAVE-managed MSRs via the
> helpers while the latter accesses the MSRs linked to VMCS fields.
> 
> Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
> ---
>  arch/x86/kvm/vmx/vmx.c | 18 +++++++++++
>  arch/x86/kvm/x86.c     | 71 ++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 89 insertions(+)
> 
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index fd5893b3a2c8..9f4b56337251 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -2111,6 +2111,15 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>  		else
>  			msr_info->data = vmx->pt_desc.guest.addr_a[index / 2];
>  		break;
> +	case MSR_IA32_S_CET:
> +		msr_info->data = vmcs_readl(GUEST_S_CET);
> +		break;
> +	case MSR_KVM_SSP:
> +		msr_info->data = vmcs_readl(GUEST_SSP);
> +		break;
> +	case MSR_IA32_INT_SSP_TAB:
> +		msr_info->data = vmcs_readl(GUEST_INTR_SSP_TABLE);
> +		break;
>  	case MSR_IA32_DEBUGCTLMSR:
>  		msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL);
>  		break;
> @@ -2420,6 +2429,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>  		else
>  			vmx->pt_desc.guest.addr_a[index / 2] = data;
>  		break;
> +	case MSR_IA32_S_CET:
> +		vmcs_writel(GUEST_S_CET, data);
> +		break;
> +	case MSR_KVM_SSP:
> +		vmcs_writel(GUEST_SSP, data);
> +		break;
> +	case MSR_IA32_INT_SSP_TAB:
> +		vmcs_writel(GUEST_INTR_SSP_TABLE, data);
> +		break;
>  	case MSR_IA32_PERF_CAPABILITIES:
>  		if (data && !vcpu_to_pmu(vcpu)->version)
>  			return 1;
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 73b45351c0fc..c85ee42ab4f1 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -1847,6 +1847,11 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type)
>  }
>  EXPORT_SYMBOL_GPL(kvm_msr_allowed);
>  
> +#define CET_US_RESERVED_BITS		GENMASK(9, 6)
> +#define CET_US_SHSTK_MASK_BITS		GENMASK(1, 0)
> +#define CET_US_IBT_MASK_BITS		(GENMASK_ULL(5, 2) | GENMASK_ULL(63, 10))
> +#define CET_US_LEGACY_BITMAP_BASE(data)	((data) >> 12)
> +
>  /*
>   * Write @data into the MSR specified by @index.  Select MSR specific fault
>   * checks are bypassed if @host_initiated is %true.
> @@ -1856,6 +1861,7 @@ EXPORT_SYMBOL_GPL(kvm_msr_allowed);
>  static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
>  			 bool host_initiated)
>  {
> +	bool host_msr_reset = host_initiated && data == 0;

I really don't like this boolean. While 0 is usually the reset value, it doesn't have to
be (like SVM tsc ratio reset value is 1 for example).
Also its name is confusing.

I suggest to just open code this instead.

>  	struct msr_data msr;
>  
>  	switch (index) {
> @@ -1906,6 +1912,46 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
>  
>  		data = (u32)data;
>  		break;
> +	case MSR_IA32_U_CET:
> +	case MSR_IA32_S_CET:
> +		if (host_msr_reset && (kvm_cpu_cap_has(X86_FEATURE_SHSTK) ||
> +				       kvm_cpu_cap_has(X86_FEATURE_IBT)))
> +			break;
> +		if (!guest_can_use(vcpu, X86_FEATURE_SHSTK) &&
> +		    !guest_can_use(vcpu, X86_FEATURE_IBT))
> +			return 1;
> +		if (data & CET_US_RESERVED_BITS)
> +			return 1;
> +		if (!guest_can_use(vcpu, X86_FEATURE_SHSTK) &&
> +		    (data & CET_US_SHSTK_MASK_BITS))
> +			return 1;
> +		if (!guest_can_use(vcpu, X86_FEATURE_IBT) &&
> +		    (data & CET_US_IBT_MASK_BITS))
> +			return 1;
> +		if (!IS_ALIGNED(CET_US_LEGACY_BITMAP_BASE(data), 4))
> +			return 1;
> +
> +		/* IBT can be suppressed iff the TRACKER isn't WAIT_ENDBR. */
> +		if ((data & CET_SUPPRESS) && (data & CET_WAIT_ENDBR))
> +			return 1;
> +		break;
> +	case MSR_IA32_INT_SSP_TAB:
> +		if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
> +			return 1;
> +		fallthrough;
> +	case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP:
> +	case MSR_KVM_SSP:
> +		if (host_msr_reset && kvm_cpu_cap_has(X86_FEATURE_SHSTK))
> +			break;
> +		if (!guest_can_use(vcpu, X86_FEATURE_SHSTK))
> +			return 1;
> +		if (index == MSR_KVM_SSP && !host_initiated)
> +			return 1;
> +		if (is_noncanonical_address(data, vcpu))
> +			return 1;
> +		if (index != MSR_IA32_INT_SSP_TAB && !IS_ALIGNED(data, 4))
> +			return 1;
> +		break;
Once again I'll prefer to have an ioctl for setting/getting SSP, this will make the above
code simpler (e.g there will be no need to check that write comes from the host/etc).

>  	}
>  
>  	msr.data = data;
> @@ -1949,6 +1995,23 @@ static int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
>  		    !guest_cpuid_has(vcpu, X86_FEATURE_RDPID))
>  			return 1;
>  		break;
> +	case MSR_IA32_U_CET:
> +	case MSR_IA32_S_CET:
> +		if (!guest_can_use(vcpu, X86_FEATURE_IBT) &&
> +		    !guest_can_use(vcpu, X86_FEATURE_SHSTK))
> +			return 1;
> +		break;
> +	case MSR_IA32_INT_SSP_TAB:
> +		if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
> +			return 1;
> +		fallthrough;
> +	case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP:
> +	case MSR_KVM_SSP:
> +		if (!guest_can_use(vcpu, X86_FEATURE_SHSTK))
> +			return 1;
> +		if (index == MSR_KVM_SSP && !host_initiated)
> +			return 1;
> +		break;
>  	}
>  
>  	msr.index = index;
> @@ -4009,6 +4072,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>  		vcpu->arch.guest_fpu.xfd_err = data;
>  		break;
>  #endif
> +	case MSR_IA32_U_CET:
> +	case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP:
> +		kvm_set_xstate_msr(vcpu, msr_info);

Ah, so here these functions (kvm_set_xstate_msr/kvm_get_xstate_msr) are used. 
I think that this patch should introduce them.

Also I will appreciate a comment to kvm_set_xstate_msr/kvm_get_xstate_msr saying something like:

"This function updates a guest MSR which value is saved in the guest FPU state. 
Wrap the write with load/save of the guest FPU state to keep the state consistent with the new MSR value"

Or something similar, although I will not argue over this.

> +		break;
>  	default:
>  		if (kvm_pmu_is_valid_msr(vcpu, msr))
>  			return kvm_pmu_set_msr(vcpu, msr_info);
> @@ -4365,6 +4432,10 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>  		msr_info->data = vcpu->arch.guest_fpu.xfd_err;
>  		break;
>  #endif
> +	case MSR_IA32_U_CET:
> +	case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP:
> +		kvm_get_xstate_msr(vcpu, msr_info);
> +		break;
>  	default:
>  		if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
>  			return kvm_pmu_get_msr(vcpu, msr_info);


Best regards,
	Maxim Levitsky