diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 64adb6117e19..3318bde206a5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -287,6 +287,13 @@ struct kvm_mmu { union kvm_mmu_page_role base_role; bool direct_map; + /* + * Bitmap; bit set = permission fault + * Byte index: page fault error code [4:1] + * Bit index: pte permissions in ACC_* format + */ + u8 permissions[16]; + u64 *pae_root; u64 *lm_root; u64 rsvd_bits_mask[2][4]; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f297a2ccf4f6..9c6188931f87 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3516,6 +3516,38 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, } } +static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) +{ + unsigned bit, byte, pfec; + u8 map; + bool fault, x, w, u, wf, uf, ff, smep; + + smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); + for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) { + pfec = byte << 1; + map = 0; + wf = pfec & PFERR_WRITE_MASK; + uf = pfec & PFERR_USER_MASK; + ff = pfec & PFERR_FETCH_MASK; + for (bit = 0; bit < 8; ++bit) { + x = bit & ACC_EXEC_MASK; + w = bit & ACC_WRITE_MASK; + u = bit & ACC_USER_MASK; + + /* Not really needed: !nx will cause pte.nx to fault */ + x |= !mmu->nx; + /* Allow supervisor writes if !cr0.wp */ + w |= !is_write_protection(vcpu) && !uf; + /* Disallow supervisor fetches of user code if cr4.smep */ + x &= !(smep && u && !uf); + + fault = (ff && !x) || (uf && !u) || (wf && !w); + map |= fault << bit; + } + mmu->permissions[byte] = map; + } +} + static int paging64_init_context_common(struct kvm_vcpu *vcpu, struct kvm_mmu *context, int level) @@ -3524,6 +3556,7 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, context->root_level = level; reset_rsvds_bits_mask(vcpu, context); + update_permission_bitmask(vcpu, context); ASSERT(is_pae(vcpu)); context->new_cr3 = paging_new_cr3; @@ -3552,6 +3585,7 @@ static int paging32_init_context(struct kvm_vcpu *vcpu, context->root_level = PT32_ROOT_LEVEL; reset_rsvds_bits_mask(vcpu, context); + update_permission_bitmask(vcpu, context); context->new_cr3 = paging_new_cr3; context->page_fault = paging32_page_fault; @@ -3612,6 +3646,8 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->gva_to_gpa = paging32_gva_to_gpa; } + update_permission_bitmask(vcpu, context); + return 0; } @@ -3687,6 +3723,8 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) g_context->gva_to_gpa = paging32_gva_to_gpa_nested; } + update_permission_bitmask(vcpu, g_context); + return 0; } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 2832081e9b2e..584660775d08 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -89,17 +89,14 @@ static inline bool is_write_protection(struct kvm_vcpu *vcpu) return kvm_read_cr0_bits(vcpu, X86_CR0_WP); } -static inline bool check_write_user_access(struct kvm_vcpu *vcpu, - bool write_fault, bool user_fault, - unsigned long pte) +/* + * Will a fault with a given page-fault error code (pfec) cause a permission + * fault with the given access (in ACC_* format)? + */ +static inline bool permission_fault(struct kvm_mmu *mmu, unsigned pte_access, + unsigned pfec) { - if (unlikely(write_fault && !is_writable_pte(pte) - && (user_fault || is_write_protection(vcpu)))) - return false; - - if (unlikely(user_fault && !(pte & PT_USER_MASK))) - return false; - - return true; + return (mmu->permissions[pfec >> 1] >> pte_access) & 1; } + #endif diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 35a05dd2f69c..8f6c59fadbbe 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -169,7 +169,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, pt_element_t pte; pt_element_t __user *uninitialized_var(ptep_user); gfn_t table_gfn; - unsigned index, pt_access, uninitialized_var(pte_access); + unsigned index, pt_access, pte_access; gpa_t pte_gpa; bool eperm, last_gpte; int offset; @@ -237,24 +237,9 @@ retry_walk: goto error; } - if (!check_write_user_access(vcpu, write_fault, user_fault, - pte)) - eperm = true; - -#if PTTYPE == 64 - if (unlikely(fetch_fault && (pte & PT64_NX_MASK))) - eperm = true; -#endif + pte_access = pt_access & gpte_access(vcpu, pte); last_gpte = FNAME(is_last_gpte)(walker, vcpu, mmu, pte); - if (last_gpte) { - pte_access = pt_access & gpte_access(vcpu, pte); - /* check if the kernel is fetching from user page */ - if (unlikely(pte_access & PT_USER_MASK) && - kvm_read_cr4_bits(vcpu, X86_CR4_SMEP)) - if (fetch_fault && !user_fault) - eperm = true; - } walker->ptes[walker->level - 1] = pte; @@ -284,10 +269,11 @@ retry_walk: break; } - pt_access &= gpte_access(vcpu, pte); + pt_access &= pte_access; --walker->level; } + eperm |= permission_fault(mmu, pte_access, access); if (unlikely(eperm)) { errcode |= PFERR_PRESENT_MASK; goto error; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 19047eafa38d..497226e49d4b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3672,20 +3672,17 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = ((kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0) + | (write ? PFERR_WRITE_MASK : 0); - if (vcpu_match_mmio_gva(vcpu, gva) && - check_write_user_access(vcpu, write, access, - vcpu->arch.access)) { + if (vcpu_match_mmio_gva(vcpu, gva) + && !permission_fault(vcpu->arch.walk_mmu, vcpu->arch.access, access)) { *gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT | (gva & (PAGE_SIZE - 1)); trace_vcpu_match_mmio(gva, *gpa, write, false); return 1; } - if (write) - access |= PFERR_WRITE_MASK; - *gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); if (*gpa == UNMAPPED_GVA)