On Fri, Nov 19, 2021 at 3:58 PM David Matlack <dmatlack@xxxxxxxxxx> wrote:
>
> Factor out the logic to atomically replace an SPTE with an SPTE that
> points to a new page table. This will be used in a follow-up commit to
> split a large page SPTE into one level lower.
>
> Signed-off-by: David Matlack <dmatlack@xxxxxxxxxx>
> ---
> arch/x86/kvm/mmu/tdp_mmu.c | 53 ++++++++++++++++++++++++++------------
> 1 file changed, 37 insertions(+), 16 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index cc9fe33c9b36..9ee3f4f7fdf5 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -945,6 +945,39 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
> return ret;
> }
>
> +/*
> + * tdp_mmu_install_sp_atomic - Atomically replace the given spte with an
> + * spte pointing to the provided page table.
> + *
> + * @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.
> + *
> + * Returns: True if the new page table was installed. False if spte being
> + * replaced changed, causing the atomic compare-exchange to fail.
> + * If this function returns false the sp will be freed before
> + * returning.
> + */
> +static bool tdp_mmu_install_sp_atomic(struct kvm *kvm,
> + struct tdp_iter *iter,
> + struct kvm_mmu_page *sp,
> + bool account_nx)
> +{
> + u64 spte;
> +
> + spte = make_nonleaf_spte(sp->spt, !shadow_accessed_mask);
> +
> + if (tdp_mmu_set_spte_atomic(kvm, iter, spte)) {
> + tdp_mmu_link_page(kvm, sp, account_nx);
> + return true;
> + } else {
> + tdp_mmu_free_sp(sp);
> + return false;
> + }
> +}
> +
> /*
> * Handle a TDP page fault (NPT/EPT violation/misconfiguration) by installing
> * page tables and SPTEs to translate the faulting guest physical address.
> @@ -954,8 +987,6 @@ 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);
> @@ -983,6 +1014,9 @@ 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
> @@ -992,21 +1026,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> 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);
This refactoring drops this trace point. Is that intentional?
> - } else {
> - tdp_mmu_free_sp(sp);
> + if (!tdp_mmu_install_sp_atomic(vcpu->kvm, &iter, sp, account_nx))
> break;
> - }
> }
> }
>
> --
> 2.34.0.rc2.393.gf8c9666880-goog
>
