diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 7e4c31b57a75..64efe8c90c31 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -713,7 +713,7 @@ struct kvm_vcpu_arch { struct kvm_mmu_memory_cache mmu_pte_list_desc_cache; struct kvm_mmu_memory_cache mmu_shadow_page_cache; - struct kvm_mmu_memory_cache mmu_gfn_array_cache; + struct kvm_mmu_memory_cache mmu_shadowed_info_cache; struct kvm_mmu_memory_cache mmu_page_header_cache; /* diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7cca28d89a85..13a059ad5dc7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -656,7 +656,7 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect) if (r) return r; if (maybe_indirect) { - r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_gfn_array_cache, + r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadowed_info_cache, PT64_ROOT_MAX_LEVEL); if (r) return r; @@ -669,7 +669,7 @@ static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) { kvm_mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadow_page_cache); - kvm_mmu_free_memory_cache(&vcpu->arch.mmu_gfn_array_cache); + kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadowed_info_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache); } @@ -678,34 +678,68 @@ static void mmu_free_pte_list_desc(struct pte_list_desc *pte_list_desc) kmem_cache_free(pte_list_desc_cache, pte_list_desc); } +static bool sp_has_gptes(struct kvm_mmu_page *sp); + static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index) { if (sp->role.passthrough) return sp->gfn; if (!sp->role.direct) - return sp->gfns[index]; + return sp->shadowed_translation[index] >> PAGE_SHIFT; return sp->gfn + (index << ((sp->role.level - 1) * SPTE_LEVEL_BITS)); } -static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn) +/* + * For leaf SPTEs, fetch the *guest* access permissions being shadowed. Note + * that the SPTE itself may have a more constrained access permissions that + * what the guest enforces. For example, a guest may create an executable + * huge PTE but KVM may disallow execution to mitigate iTLB multihit. + */ +static u32 kvm_mmu_page_get_access(struct kvm_mmu_page *sp, int index) { - if (sp->role.passthrough) { - WARN_ON_ONCE(gfn != sp->gfn); + if (sp_has_gptes(sp)) + return sp->shadowed_translation[index] & ACC_ALL; + + /* + * For direct MMUs (e.g. TDP or non-paging guests) or passthrough SPs, + * KVM is not shadowing any guest page tables, so the "guest access + * permissions" are just ACC_ALL. + * + * For direct SPs in indirect MMUs (shadow paging), i.e. when KVM + * is shadowing a guest huge page with small pages, the guest access + * permissions being shadowed are the access permissions of the huge + * page. + * + * In both cases, sp->role.access contains the correct access bits. + */ + return sp->role.access; +} + +static void kvm_mmu_page_set_translation(struct kvm_mmu_page *sp, int index, gfn_t gfn, u32 access) +{ + if (sp_has_gptes(sp)) { + sp->shadowed_translation[index] = (gfn << PAGE_SHIFT) | access; return; } - if (!sp->role.direct) { - sp->gfns[index] = gfn; - return; - } + WARN_ONCE(access != kvm_mmu_page_get_access(sp, index), + "access mismatch under %s page %llx (expected %u, got %u)\n", + sp->role.passthrough ? "passthrough" : "direct", + sp->gfn, kvm_mmu_page_get_access(sp, index), access); - if (WARN_ON(gfn != kvm_mmu_page_get_gfn(sp, index))) - pr_err_ratelimited("gfn mismatch under direct page %llx " - "(expected %llx, got %llx)\n", - sp->gfn, - kvm_mmu_page_get_gfn(sp, index), gfn); + WARN_ONCE(gfn != kvm_mmu_page_get_gfn(sp, index), + "gfn mismatch under %s page %llx (expected %llx, got %llx)\n", + sp->role.passthrough ? "passthrough" : "direct", + sp->gfn, kvm_mmu_page_get_gfn(sp, index), gfn); +} + +static void kvm_mmu_page_set_access(struct kvm_mmu_page *sp, int index, u32 access) +{ + gfn_t gfn = kvm_mmu_page_get_gfn(sp, index); + + kvm_mmu_page_set_translation(sp, index, gfn, access); } /* @@ -1554,14 +1588,14 @@ static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, static void __rmap_add(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, const struct kvm_memory_slot *slot, - u64 *spte, gfn_t gfn) + u64 *spte, gfn_t gfn, u32 access) { struct kvm_mmu_page *sp; struct kvm_rmap_head *rmap_head; int rmap_count; sp = sptep_to_sp(spte); - kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); + kvm_mmu_page_set_translation(sp, spte - sp->spt, gfn, access); kvm_update_page_stats(kvm, sp->role.level, 1); rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); @@ -1575,11 +1609,11 @@ static void __rmap_add(struct kvm *kvm, } static void rmap_add(struct kvm_vcpu *vcpu, const struct kvm_memory_slot *slot, - u64 *spte, gfn_t gfn) + u64 *spte, gfn_t gfn, u32 access) { struct kvm_mmu_memory_cache *cache = &vcpu->arch.mmu_pte_list_desc_cache; - __rmap_add(vcpu->kvm, cache, slot, spte, gfn); + __rmap_add(vcpu->kvm, cache, slot, spte, gfn, access); } bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1643,7 +1677,7 @@ static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp) list_del(&sp->link); free_page((unsigned long)sp->spt); if (!sp->role.direct) - free_page((unsigned long)sp->gfns); + free_page((unsigned long)sp->shadowed_translation); kmem_cache_free(mmu_page_header_cache, sp); } @@ -2070,7 +2104,7 @@ out: struct shadow_page_caches { struct kvm_mmu_memory_cache *page_header_cache; struct kvm_mmu_memory_cache *shadow_page_cache; - struct kvm_mmu_memory_cache *gfn_array_cache; + struct kvm_mmu_memory_cache *shadowed_info_cache; }; static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm, @@ -2084,7 +2118,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm, sp = kvm_mmu_memory_cache_alloc(caches->page_header_cache); sp->spt = kvm_mmu_memory_cache_alloc(caches->shadow_page_cache); if (!role.direct) - sp->gfns = kvm_mmu_memory_cache_alloc(caches->gfn_array_cache); + sp->shadowed_translation = kvm_mmu_memory_cache_alloc(caches->shadowed_info_cache); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); @@ -2136,7 +2170,7 @@ static struct kvm_mmu_page *kvm_mmu_get_shadow_page(struct kvm_vcpu *vcpu, struct shadow_page_caches caches = { .page_header_cache = &vcpu->arch.mmu_page_header_cache, .shadow_page_cache = &vcpu->arch.mmu_shadow_page_cache, - .gfn_array_cache = &vcpu->arch.mmu_gfn_array_cache, + .shadowed_info_cache = &vcpu->arch.mmu_shadowed_info_cache, }; return __kvm_mmu_get_shadow_page(vcpu->kvm, vcpu, &caches, gfn, role); @@ -2785,7 +2819,10 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, if (!was_rmapped) { WARN_ON_ONCE(ret == RET_PF_SPURIOUS); - rmap_add(vcpu, slot, sptep, gfn); + rmap_add(vcpu, slot, sptep, gfn, pte_access); + } else { + /* Already rmapped but the pte_access bits may have changed. */ + kvm_mmu_page_set_access(sp, sptep - sp->spt, pte_access); } return ret; diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index bb9d12ac0db3..ae2d660e2dab 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -67,8 +67,21 @@ struct kvm_mmu_page { gfn_t gfn; u64 *spt; - /* hold the gfn of each spte inside spt */ - gfn_t *gfns; + + /* + * Stores the result of the guest translation being shadowed by each + * SPTE. KVM shadows two types of guest translations: nGPA -> GPA + * (shadow EPT/NPT) and GVA -> GPA (traditional shadow paging). In both + * cases the result of the translation is a GPA and a set of access + * constraints. + * + * The GFN is stored in the upper bits (PAGE_SHIFT) and the shadowed + * access permissions are stored in the lower bits. Note, for + * convenience and uniformity across guests, the access permissions are + * stored in KVM format (e.g. ACC_EXEC_MASK) not the raw guest format. + */ + u64 *shadowed_translation; + /* Currently serving as active root */ union { int root_count; diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 6ecdd7a41a82..24f292f3f93f 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -985,7 +985,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } /* - * Using the cached information from sp->gfns is safe because: + * Using the information in sp->shadowed_translation (kvm_mmu_page_get_gfn()) is + * safe because: * - The spte has a reference to the struct page, so the pfn for a given gfn * can't change unless all sptes pointing to it are nuked first. * @@ -1067,12 +1068,16 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) * "present" bit, as all other paging modes will create a * read-only SPTE if pte_access is zero. */ - if ((!pte_access && !shadow_present_mask) || gfn != sp->gfns[i]) { + if ((!pte_access && !shadow_present_mask) || + gfn != kvm_mmu_page_get_gfn(sp, i)) { drop_spte(vcpu->kvm, &sp->spt[i]); flush = true; continue; } + /* Update the shadowed access bits in case they changed. */ + kvm_mmu_page_set_access(sp, i, pte_access); + sptep = &sp->spt[i]; spte = *sptep; host_writable = spte & shadow_host_writable_mask;