Re: [PATCH v3 20/21] KVM:x86: Enable kernel IBT support for guest

[Sean Christopherson <seanjc@google.com>]

On Thu, May 11, 2023, Yang Weijiang wrote:
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index a2494156902d..1d0151f9e575 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -711,6 +711,7 @@ static bool is_valid_passthrough_msr(u32 msr)
>  		return true;
>  	case MSR_IA32_U_CET:
>  	case MSR_IA32_PL3_SSP:
> +	case MSR_IA32_S_CET:
>  		return true;
>  	}
>  
> @@ -2097,14 +2098,18 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>  			msr_info->data = vmx->pt_desc.guest.addr_a[index / 2];
>  		break;
>  	case MSR_IA32_U_CET:
> +	case MSR_IA32_S_CET:
>  	case MSR_IA32_PL3_SSP:
>  	case MSR_KVM_GUEST_SSP:
>  		if (!kvm_cet_is_msr_accessible(vcpu, msr_info))
>  			return 1;
> -		if (msr_info->index == MSR_KVM_GUEST_SSP)
> +		if (msr_info->index == MSR_KVM_GUEST_SSP) {

Unnecessary curly braces.

>  			msr_info->data = vmcs_readl(GUEST_SSP);
> -		else
> +		} else if (msr_info->index == MSR_IA32_S_CET) {
> +			msr_info->data = vmcs_readl(GUEST_S_CET);
> +		} else {
>  			kvm_get_xsave_msr(msr_info);
> +		}
>  		break;
>  	case MSR_IA32_DEBUGCTLMSR:
>  		msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL);
> @@ -2419,6 +2424,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>  			vmx->pt_desc.guest.addr_a[index / 2] = data;
>  		break;
>  	case MSR_IA32_U_CET:
> +	case MSR_IA32_S_CET:
>  	case MSR_IA32_PL3_SSP:
>  	case MSR_KVM_GUEST_SSP:
>  		if (!kvm_cet_is_msr_accessible(vcpu, msr_info))
> @@ -2430,10 +2436,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
>  		if ((msr_index == MSR_IA32_PL3_SSP ||
>  		     msr_index == MSR_KVM_GUEST_SSP) && (data & GENMASK(2, 0)))
>  			return 1;
> -		if (msr_index == MSR_KVM_GUEST_SSP)
> +		if (msr_index == MSR_KVM_GUEST_SSP) {
>  			vmcs_writel(GUEST_SSP, data);
> -		else
> +		} else if (msr_index == MSR_IA32_S_CET) {
> +			vmcs_writel(GUEST_S_CET, data);
> +		} else {

Same here.

>  			kvm_set_xsave_msr(msr_info);
> +		}
>  		break;
>  	case MSR_IA32_PERF_CAPABILITIES:
>  		if (data && !vcpu_to_pmu(vcpu)->version)
> @@ -7322,6 +7331,19 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
>  
>  	kvm_wait_lapic_expire(vcpu);
>  
> +	/*
> +	 * Save host MSR_IA32_S_CET so that it can be reloaded at vm_exit.
> +	 * No need to save the other two vmcs fields as supervisor SHSTK
> +	 * are not enabled on Intel platform now.
> +	 */
> +	if (IS_ENABLED(CONFIG_X86_KERNEL_IBT) &&
> +	    (vm_exit_controls_get(vmx) & VM_EXIT_LOAD_CET_STATE)) {
> +		u64 msr;
> +
> +		rdmsrl(MSR_IA32_S_CET, msr);

Reading the MSR on every VM-Enter can't possibly be necessary.  At the absolute
minimum, this could be moved outside of the fastpath; if the kernel modifies S_CET
from NMI context, KVM is hosed.  And *if* S_CET isn't static post-boot, this can
be done in .prepare_switch_to_guest() so long as S_CET isn't modified from IRQ
context.

But unless mine eyes deceive me, S_CET is only truly modified during setup_cet(),
i.e. is static post boot, which means it can be read once at KVM load time, e.g.
just like host_efer.

The kernel does save/restore IBT when making BIOS calls, but if KVM is running a
vCPU across a BIOS call then we've got bigger issues.

> +		vmcs_writel(HOST_S_CET, msr);
> +	}
> +
>  	/* The actual VMENTER/EXIT is in the .noinstr.text section. */
>  	vmx_vcpu_enter_exit(vcpu, __vmx_vcpu_run_flags(vmx));
>  
> @@ -7735,6 +7757,13 @@ static void vmx_update_intercept_for_cet_msr(struct kvm_vcpu *vcpu)
>  
>  	incpt |= !guest_cpuid_has(vcpu, X86_FEATURE_SHSTK);
>  	vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL3_SSP, MSR_TYPE_RW, incpt);
> +
> +	/*
> +	 * If IBT is available to guest, then passthrough S_CET MSR too since
> +	 * kernel IBT is already in mainline kernel tree.
> +	 */
> +	incpt = !guest_cpuid_has(vcpu, X86_FEATURE_IBT);
> +	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)
> @@ -7805,7 +7834,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
>  	/* Refresh #PF interception to account for MAXPHYADDR changes. */
>  	vmx_update_exception_bitmap(vcpu);
>  
> -	if (kvm_cet_user_supported())
> +	if (kvm_cet_user_supported() || kvm_cpu_cap_has(X86_FEATURE_IBT))

Yeah, kvm_cet_user_supported() simply looks wrong.