Re: [PATCH v3 3/3] KVM: SEV-ES: Fix LBRV code

[Tom Lendacky <thomas.lendacky@amd.com>]

On 5/23/24 07:18, Ravi Bangoria wrote:
> As documented in APM[1], LBR Virtualization must be enabled for SEV-ES
> guests. Although KVM currently enforces LBRV for SEV-ES guests, there
> are multiple issues with it:
> 
> o MSR_IA32_DEBUGCTLMSR is still intercepted. Since MSR_IA32_DEBUGCTLMSR
>    interception is used to dynamically toggle LBRV for performance reasons,
>    this can be fatal for SEV-ES guests. For ex SEV-ES guest on Zen3:
> 
>    [guest ~]# wrmsr 0x1d9 0x4
>    KVM: entry failed, hardware error 0xffffffff
>    EAX=00000004 EBX=00000000 ECX=000001d9 EDX=00000000
> 
>    Fix this by never intercepting MSR_IA32_DEBUGCTLMSR for SEV-ES guests.
>    No additional save/restore logic is required since MSR_IA32_DEBUGCTLMSR
>    is of swap type A.
> 
> o KVM will disable LBRV if userspace sets MSR_IA32_DEBUGCTLMSR before the
>    VMSA is encrypted. Fix this by moving LBRV enablement code post VMSA
>    encryption.
> 
> [1]: AMD64 Architecture Programmer's Manual Pub. 40332, Rev. 4.07 - June
>       2023, Vol 2, 15.35.2 Enabling SEV-ES.
>       https://bugzilla.kernel.org/attachment.cgi?id=304653
> 
> Co-developed-by: Nikunj A Dadhania <nikunj@amd.com>
> Signed-off-by: Nikunj A Dadhania <nikunj@amd.com>
> Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>

Should this have a Fixes: tag, too?

Thanks,
Tom

> ---
>   arch/x86/kvm/svm/sev.c | 13 ++++++++-----
>   arch/x86/kvm/svm/svm.c |  8 +++++++-
>   arch/x86/kvm/svm/svm.h |  3 ++-
>   3 files changed, 17 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
> index 1a2bde579727..3f0c3dbce0c5 100644
> --- a/arch/x86/kvm/svm/sev.c
> +++ b/arch/x86/kvm/svm/sev.c
> @@ -851,6 +851,14 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
>   	 */
>   	fpstate_set_confidential(&vcpu->arch.guest_fpu);
>   	vcpu->arch.guest_state_protected = true;
> +
> +	/*
> +	 * SEV-ES guest mandates LBR Virtualization to be _always_ ON. Enable it
> +	 * only after setting guest_state_protected because KVM_SET_MSRS allows
> +	 * dynamic toggling of LBRV (for performance reason) on write access to
> +	 * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set.
> +	 */
> +	svm_enable_lbrv(vcpu);
>   	return 0;
>   }
>   
> @@ -4279,7 +4287,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
>   	struct kvm_vcpu *vcpu = &svm->vcpu;
>   
>   	svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE;
> -	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
>   
>   	/*
>   	 * An SEV-ES guest requires a VMSA area that is a separate from the
> @@ -4331,10 +4338,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
>   	/* Clear intercepts on selected MSRs */
>   	set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1);
>   	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1);
> -	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
> -	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
> -	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
> -	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
>   }
>   
>   void sev_init_vmcb(struct vcpu_svm *svm)
> diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> index dcb5eb00a4f5..011e8e6c5c53 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -99,6 +99,7 @@ static const struct svm_direct_access_msrs {
>   	{ .index = MSR_IA32_SPEC_CTRL,			.always = false },
>   	{ .index = MSR_IA32_PRED_CMD,			.always = false },
>   	{ .index = MSR_IA32_FLUSH_CMD,			.always = false },
> +	{ .index = MSR_IA32_DEBUGCTLMSR,		.always = false },
>   	{ .index = MSR_IA32_LASTBRANCHFROMIP,		.always = false },
>   	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
>   	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
> @@ -990,7 +991,7 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
>   	vmcb_mark_dirty(to_vmcb, VMCB_LBR);
>   }
>   
> -static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
> +void svm_enable_lbrv(struct kvm_vcpu *vcpu)
>   {
>   	struct vcpu_svm *svm = to_svm(vcpu);
>   
> @@ -1000,6 +1001,9 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
>   	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
>   	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
>   
> +	if (sev_es_guest(vcpu->kvm))
> +		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1);
> +
>   	/* Move the LBR msrs to the vmcb02 so that the guest can see them. */
>   	if (is_guest_mode(vcpu))
>   		svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr);
> @@ -1009,6 +1013,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
>   {
>   	struct vcpu_svm *svm = to_svm(vcpu);
>   
> +	KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm);
> +
>   	svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
>   	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
>   	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
> diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
> index 2d7fd09c08c9..c483d7149420 100644
> --- a/arch/x86/kvm/svm/svm.h
> +++ b/arch/x86/kvm/svm/svm.h
> @@ -30,7 +30,7 @@
>   #define	IOPM_SIZE PAGE_SIZE * 3
>   #define	MSRPM_SIZE PAGE_SIZE * 2
>   
> -#define MAX_DIRECT_ACCESS_MSRS	47
> +#define MAX_DIRECT_ACCESS_MSRS	48
>   #define MSRPM_OFFSETS	32
>   extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
>   extern bool npt_enabled;
> @@ -582,6 +582,7 @@ u32 *svm_vcpu_alloc_msrpm(void);
>   void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm);
>   void svm_vcpu_free_msrpm(u32 *msrpm);
>   void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
> +void svm_enable_lbrv(struct kvm_vcpu *vcpu);
>   void svm_update_lbrv(struct kvm_vcpu *vcpu);
>   
>   int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer);