Re: [PATCH v2] KVM: x86: Prevent KVM SVM from loading on kernels with 5-level paging

[Paolo Bonzini <pbonzini@redhat.com>]

On 05/05/21 22:42, Sean Christopherson wrote:
> Disallow loading KVM SVM if 5-level paging is supported.  In theory, NPT
> for L1 should simply work, but there unknowns with respect to how the
> guest's MAXPHYADDR will be handled by hardware.
> 
> Nested NPT is more problematic, as running an L1 VMM that is using
> 2-level page tables requires stacking single-entry PDP and PML4 tables in
> KVM's NPT for L2, as there are no equivalent entries in L1's NPT to
> shadow.  Barring hardware magic, for 5-level paging, KVM would need stack
> another layer to handle PML5.
> 
> Opportunistically rename the lm_root pointer, which is used for the
> aforementioned stacking when shadowing 2-level L1 NPT, to pml4_root to
> call out that it's specifically for PML4.
> 
> Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
> Signed-off-by: Sean Christopherson <seanjc@google.com>
> ---
>   arch/x86/include/asm/kvm_host.h |  2 +-
>   arch/x86/kvm/mmu/mmu.c          | 20 ++++++++++----------
>   arch/x86/kvm/svm/svm.c          |  5 +++++
>   3 files changed, 16 insertions(+), 11 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 3e5fc80a35c8..bf35f369b49e 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -407,7 +407,7 @@ struct kvm_mmu {
>   	u32 pkru_mask;
>   
>   	u64 *pae_root;
> -	u64 *lm_root;
> +	u64 *pml4_root;
>   
>   	/*
>   	 * check zero bits on shadow page table entries, these
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 930ac8a7e7c9..04c869794ab3 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -3310,12 +3310,12 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
>   	if (mmu->shadow_root_level == PT64_ROOT_4LEVEL) {
>   		pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK;
>   
> -		if (WARN_ON_ONCE(!mmu->lm_root)) {
> +		if (WARN_ON_ONCE(!mmu->pml4_root)) {
>   			r = -EIO;
>   			goto out_unlock;
>   		}
>   
> -		mmu->lm_root[0] = __pa(mmu->pae_root) | pm_mask;
> +		mmu->pml4_root[0] = __pa(mmu->pae_root) | pm_mask;
>   	}
>   
>   	for (i = 0; i < 4; ++i) {
> @@ -3335,7 +3335,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
>   	}
>   
>   	if (mmu->shadow_root_level == PT64_ROOT_4LEVEL)
> -		mmu->root_hpa = __pa(mmu->lm_root);
> +		mmu->root_hpa = __pa(mmu->pml4_root);
>   	else
>   		mmu->root_hpa = __pa(mmu->pae_root);
>   
> @@ -3350,7 +3350,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
>   static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
>   {
>   	struct kvm_mmu *mmu = vcpu->arch.mmu;
> -	u64 *lm_root, *pae_root;
> +	u64 *pml4_root, *pae_root;
>   
>   	/*
>   	 * When shadowing 32-bit or PAE NPT with 64-bit NPT, the PML4 and PDP
> @@ -3369,14 +3369,14 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
>   	if (WARN_ON_ONCE(mmu->shadow_root_level != PT64_ROOT_4LEVEL))
>   		return -EIO;
>   
> -	if (mmu->pae_root && mmu->lm_root)
> +	if (mmu->pae_root && mmu->pml4_root)
>   		return 0;
>   
>   	/*
>   	 * The special roots should always be allocated in concert.  Yell and
>   	 * bail if KVM ends up in a state where only one of the roots is valid.
>   	 */
> -	if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->lm_root))
> +	if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->pml4_root))
>   		return -EIO;
>   
>   	/*
> @@ -3387,14 +3387,14 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
>   	if (!pae_root)
>   		return -ENOMEM;
>   
> -	lm_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
> -	if (!lm_root) {
> +	pml4_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
> +	if (!pml4_root) {
>   		free_page((unsigned long)pae_root);
>   		return -ENOMEM;
>   	}
>   
>   	mmu->pae_root = pae_root;
> -	mmu->lm_root = lm_root;
> +	mmu->pml4_root = pml4_root;
>   
>   	return 0;
>   }
> @@ -5261,7 +5261,7 @@ static void free_mmu_pages(struct kvm_mmu *mmu)
>   	if (!tdp_enabled && mmu->pae_root)
>   		set_memory_encrypted((unsigned long)mmu->pae_root, 1);
>   	free_page((unsigned long)mmu->pae_root);
> -	free_page((unsigned long)mmu->lm_root);
> +	free_page((unsigned long)mmu->pml4_root);
>   }
>   
>   static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
> diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> index 14ff7f0963e9..d29dfe4a6503 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -447,6 +447,11 @@ static int has_svm(void)
>   		return 0;
>   	}
>   
> +	if (pgtable_l5_enabled()) {
> +		pr_info("KVM doesn't yet support 5-level paging on AMD SVM\n");
> +		return 0;
> +	}
> +
>   	return 1;
>   }
>   
> 

Queued, thanks.

Paolo