Re: [RFC PATCH v5 046/104] KVM: x86/tdp_mmu: refactor kvm_tdp_mmu_map()

[Paolo Bonzini]

On 3/4/22 20:49, isaku.yamahata@xxxxxxxxx wrote:
> From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
>
> Factor out non-leaf SPTE population logic from kvm_tdp_mmu_map().  MapGPA
> hypercall needs to populate non-leaf SPTE to record which GPA, private or
> shared, is allowed in the leaf EPT entry.
>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>

Reviewed-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>

and feel free to rebase/resubmit this one, with subject "KVM: 
x86/tdp_mmu: extract tdp_mmu_populate_nonleaf()".

Paolo

> ---
>   arch/x86/kvm/mmu/tdp_mmu.c | 48 ++++++++++++++++++++++++--------------
>   1 file changed, 30 insertions(+), 18 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index b6ec2f112c26..8db262440d5c 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -955,6 +955,31 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
>   	return ret;
>   }
>   
> +static bool tdp_mmu_populate_nonleaf(
> +	struct kvm_vcpu *vcpu, struct tdp_iter *iter, bool account_nx)
> +{
> +	struct kvm_mmu_page *sp;
> +	u64 *child_pt;
> +	u64 new_spte;
> +
> +	WARN_ON(is_shadow_present_pte(iter->old_spte));
> +	WARN_ON(is_removed_spte(iter->old_spte));
> +
> +	sp = alloc_tdp_mmu_page(vcpu, iter->gfn, iter->level - 1);
> +	child_pt = sp->spt;
> +
> +	new_spte = make_nonleaf_spte(child_pt, !shadow_accessed_mask);
> +
> +	if (!tdp_mmu_set_spte_atomic(vcpu->kvm, iter, new_spte)) {
> +		tdp_mmu_free_sp(sp);
> +		return false;
> +	}
> +
> +	tdp_mmu_link_page(vcpu->kvm, sp, account_nx);
> +	trace_kvm_mmu_get_page(sp, true);
> +	return true;
> +}
> +
>   /*
>    * Handle a TDP page fault (NPT/EPT violation/misconfiguration) by installing
>    * page tables and SPTEs to translate the faulting guest physical address.
> @@ -963,9 +988,6 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
>   {
>   	struct kvm_mmu *mmu = vcpu->arch.mmu;
>   	struct tdp_iter iter;
> -	struct kvm_mmu_page *sp;
> -	u64 *child_pt;
> -	u64 new_spte;
>   	int ret;
>   
>   	kvm_mmu_hugepage_adjust(vcpu, fault);
> @@ -1000,6 +1022,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
>   		}
>   
>   		if (!is_shadow_present_pte(iter.old_spte)) {
> +			bool account_nx;
> +
>   			/*
>   			 * If SPTE has been frozen by another thread, just
>   			 * give up and retry, avoiding unnecessary page table
> @@ -1008,22 +1032,10 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
>   			if (is_removed_spte(iter.old_spte))
>   				break;
>   
> -			sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level - 1);
> -			child_pt = sp->spt;
> -
> -			new_spte = make_nonleaf_spte(child_pt,
> -						     !shadow_accessed_mask);
> -
> -			if (tdp_mmu_set_spte_atomic(vcpu->kvm, &iter, new_spte)) {
> -				tdp_mmu_link_page(vcpu->kvm, sp,
> -						  fault->huge_page_disallowed &&
> -						  fault->req_level >= iter.level);
> -
> -				trace_kvm_mmu_get_page(sp, true);
> -			} else {
> -				tdp_mmu_free_sp(sp);
> +			account_nx = fault->huge_page_disallowed &&
> +				fault->req_level >= iter.level;
> +			if (!tdp_mmu_populate_nonleaf(vcpu, &iter, account_nx))
>   				break;
> -			}
>   		}
>   	}
>