Re: [PATCH v2 3/6] KVM: x86/mmu: Set disallowed_nx_huge_page in TDP MMU before setting SPTE

From: David Matlack
Date: Mon Jul 25 2022 - 19:16:17 EST


On Sat, Jul 23, 2022 at 01:23:22AM +0000, Sean Christopherson wrote:
> Set nx_huge_page_disallowed in TDP MMU shadow pages before making the SP
> visible to other readers, i.e. before setting its SPTE. This will allow
> KVM to query the flag when determining if a shadow page can be replaced
> by a NX huge page without violating the rules of the mitigation.

It took me a minute to figure out why the same change isn't needed in
the shadow MMU (it always holds the write-lock so it's impossible for
another CPU to see an SP without a correct nx_huge_page_disallowed.
If you send a v2 can you add a short blurb to that effect here?

Otherwise,

Reviewed-by: David Matlack <dmatlack@xxxxxxxxxx>

>
> Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
> ---
> arch/x86/kvm/mmu/mmu.c | 12 +++++-------
> arch/x86/kvm/mmu/mmu_internal.h | 5 ++---
> arch/x86/kvm/mmu/tdp_mmu.c | 30 +++++++++++++++++-------------
> 3 files changed, 24 insertions(+), 23 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 493cdf1c29ff..e9252e7cd5a2 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -802,8 +802,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
> kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
> }
>
> -static void untrack_possible_nx_huge_page(struct kvm *kvm,
> - struct kvm_mmu_page *sp)
> +void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
> {
> if (list_empty(&sp->possible_nx_huge_page_link))
> return;
> @@ -812,15 +811,14 @@ static void untrack_possible_nx_huge_page(struct kvm *kvm,
> list_del_init(&sp->possible_nx_huge_page_link);
> }
>
> -void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
> +static void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
> {
> sp->nx_huge_page_disallowed = false;
>
> untrack_possible_nx_huge_page(kvm, sp);
> }
>
> -static void track_possible_nx_huge_page(struct kvm *kvm,
> - struct kvm_mmu_page *sp)
> +void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
> {
> if (!list_empty(&sp->possible_nx_huge_page_link))
> return;
> @@ -830,8 +828,8 @@ static void track_possible_nx_huge_page(struct kvm *kvm,
> &kvm->arch.possible_nx_huge_pages);
> }
>
> -void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
> - bool nx_huge_page_possible)
> +static void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
> + bool nx_huge_page_possible)
> {
> sp->nx_huge_page_disallowed = true;
>
> diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
> index 83644a0167ab..2a887d08b722 100644
> --- a/arch/x86/kvm/mmu/mmu_internal.h
> +++ b/arch/x86/kvm/mmu/mmu_internal.h
> @@ -336,8 +336,7 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
>
> void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
>
> -void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
> - bool nx_huge_page_possible);
> -void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp);
> +void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp);
> +void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp);
>
> #endif /* __KVM_X86_MMU_INTERNAL_H */
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index a30983947fee..626c40ec2af9 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -392,8 +392,10 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp,
> lockdep_assert_held_write(&kvm->mmu_lock);
>
> list_del(&sp->link);
> - if (sp->nx_huge_page_disallowed)
> - unaccount_nx_huge_page(kvm, sp);
> + if (sp->nx_huge_page_disallowed) {
> + sp->nx_huge_page_disallowed = false;
> + untrack_possible_nx_huge_page(kvm, sp);
> + }
>
> if (shared)
> spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
> @@ -1111,16 +1113,13 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
> * @kvm: kvm instance
> * @iter: a tdp_iter instance currently on the SPTE that should be set
> * @sp: The new TDP page table to install.
> - * @account_nx: True if this page table is being installed to split a
> - * non-executable huge page.
> * @shared: This operation is running under the MMU lock in read mode.
> *
> * Returns: 0 if the new page table was installed. Non-0 if the page table
> * could not be installed (e.g. the atomic compare-exchange failed).
> */
> static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
> - struct kvm_mmu_page *sp, bool account_nx,
> - bool shared)
> + struct kvm_mmu_page *sp, bool shared)
> {
> u64 spte = make_nonleaf_spte(sp->spt, !kvm_ad_enabled());
> int ret = 0;
> @@ -1135,8 +1134,6 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
>
> spin_lock(&kvm->arch.tdp_mmu_pages_lock);
> list_add(&sp->link, &kvm->arch.tdp_mmu_pages);
> - if (account_nx)
> - account_nx_huge_page(kvm, sp, true);
> spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
>
> return 0;
> @@ -1149,6 +1146,7 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
> int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> {
> struct kvm_mmu *mmu = vcpu->arch.mmu;
> + struct kvm *kvm = vcpu->kvm;
> struct tdp_iter iter;
> struct kvm_mmu_page *sp;
> int ret;
> @@ -1185,9 +1183,6 @@ 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 = fault->huge_page_disallowed &&
> - fault->req_level >= iter.level;
> -
> /*
> * If SPTE has been frozen by another thread, just
> * give up and retry, avoiding unnecessary page table
> @@ -1199,10 +1194,19 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> sp = tdp_mmu_alloc_sp(vcpu);
> tdp_mmu_init_child_sp(sp, &iter);
>
> - if (tdp_mmu_link_sp(vcpu->kvm, &iter, sp, account_nx, true)) {
> + sp->nx_huge_page_disallowed = fault->huge_page_disallowed;
> +
> + if (tdp_mmu_link_sp(kvm, &iter, sp, true)) {
> tdp_mmu_free_sp(sp);
> break;
> }
> +
> + if (fault->huge_page_disallowed &&
> + fault->req_level >= iter.level) {
> + spin_lock(&kvm->arch.tdp_mmu_pages_lock);
> + track_possible_nx_huge_page(kvm, sp);
> + spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
> + }
> }
> }
>
> @@ -1490,7 +1494,7 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
> * correctness standpoint since the translation will be the same either
> * way.
> */
> - ret = tdp_mmu_link_sp(kvm, iter, sp, false, shared);
> + ret = tdp_mmu_link_sp(kvm, iter, sp, shared);
> if (ret)
> goto out;
>
> --
> 2.37.1.359.gd136c6c3e2-goog
>