On Thu, 2025-04-24 at 11:06 +0800, Yan Zhao wrote:
> From: "Edgecombe, Rick P" <rick.p.edgecombe@xxxxxxxxx>
>
> Disallow page merging (huge page adjustment) for mirror root by leveraging
> the disallowed_hugepage_adjust().
>
> [Yan: Passing is_mirror to disallowed_hugepage_adjust()]
>
> Signed-off-by: Edgecombe, Rick P <rick.p.edgecombe@xxxxxxxxx>
> Signed-off-by: Yan Zhao <yan.y.zhao@xxxxxxxxx>
> ---
> arch/x86/kvm/mmu/mmu.c | 6 +++---
> arch/x86/kvm/mmu/mmu_internal.h | 2 +-
> arch/x86/kvm/mmu/paging_tmpl.h | 2 +-
> arch/x86/kvm/mmu/tdp_mmu.c | 7 ++++---
> 4 files changed, 9 insertions(+), 8 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index a284dce227a0..b923deeeb62e 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -3326,13 +3326,13 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
> fault->pfn &= ~mask;
> }
>
> -void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level)
> +void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level, bool is_mirror)
> {
> if (cur_level > PG_LEVEL_4K &&
> cur_level == fault->goal_level &&
> is_shadow_present_pte(spte) &&
> !is_large_pte(spte) &&
> - spte_to_child_sp(spte)->nx_huge_page_disallowed) {
> + (spte_to_child_sp(spte)->nx_huge_page_disallowed || is_mirror)) {
> /*
> * A small SPTE exists for this pfn, but FNAME(fetch),
> * direct_map(), or kvm_tdp_mmu_map() would like to create a
> @@ -3363,7 +3363,7 @@ static int direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> * large page, as the leaf could be executable.
> */
> if (fault->nx_huge_page_workaround_enabled)
> - disallowed_hugepage_adjust(fault, *it.sptep, it.level);
> + disallowed_hugepage_adjust(fault, *it.sptep, it.level, false);
>
> base_gfn = gfn_round_for_level(fault->gfn, it.level);
> if (it.level == fault->goal_level)
> diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
> index db8f33e4de62..1c1764f46e66 100644
> --- a/arch/x86/kvm/mmu/mmu_internal.h
> +++ b/arch/x86/kvm/mmu/mmu_internal.h
> @@ -411,7 +411,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
> int kvm_mmu_max_mapping_level(struct kvm *kvm,
> const struct kvm_memory_slot *slot, gfn_t gfn);
> void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
> -void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level);
> +void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level, bool is_mirror);
>
> 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);
> diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
> index 68e323568e95..1559182038e3 100644
> --- a/arch/x86/kvm/mmu/paging_tmpl.h
> +++ b/arch/x86/kvm/mmu/paging_tmpl.h
> @@ -717,7 +717,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
> * large page, as the leaf could be executable.
> */
> if (fault->nx_huge_page_workaround_enabled)
> - disallowed_hugepage_adjust(fault, *it.sptep, it.level);
> + disallowed_hugepage_adjust(fault, *it.sptep, it.level, false);
>
> base_gfn = gfn_round_for_level(fault->gfn, it.level);
> if (it.level == fault->goal_level)
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index 405874f4d088..8ee01277cc07 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -1244,6 +1244,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> struct tdp_iter iter;
> struct kvm_mmu_page *sp;
> int ret = RET_PF_RETRY;
> + bool is_mirror = is_mirror_sp(root);
>
> kvm_mmu_hugepage_adjust(vcpu, fault);
>
> @@ -1254,8 +1255,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> for_each_tdp_pte(iter, kvm, root, fault->gfn, fault->gfn + 1) {
> int r;
>
> - if (fault->nx_huge_page_workaround_enabled)
> - disallowed_hugepage_adjust(fault, iter.old_spte, iter.level);
> + if (fault->nx_huge_page_workaround_enabled || is_mirror)
Maybe we should rename nx_huge_page_workaround_enabled to something more generic
and do the is_mirror logic in kvm_mmu_do_page_fault() when setting it. It should
shrink the diff and centralize the logic.
> + disallowed_hugepage_adjust(fault, iter.old_spte, iter.level, is_mirror);
>
> /*
> * If SPTE has been frozen by another thread, just give up and
> @@ -1278,7 +1279,7 @@ 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 (is_mirror_sp(sp))
> + if (is_mirror)
> kvm_mmu_alloc_external_spt(vcpu, sp);
>
> sp->nx_huge_page_disallowed = fault->huge_page_disallowed;
