diff options
Diffstat (limited to 'arch/x86/kvm')
| -rw-r--r-- | arch/x86/kvm/Kconfig | 1 | ||||
| -rw-r--r-- | arch/x86/kvm/cpuid.c | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/kvm_cache_regs.h | 5 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu.c | 41 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu.h | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/svm.c | 54 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx.c | 264 | ||||
| -rw-r--r-- | arch/x86/kvm/x86.c | 51 |
8 files changed, 265 insertions, 155 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 2688c7dc5323..3ea624452f93 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -89,6 +89,5 @@ config KVM_MMU_AUDIT # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. source drivers/vhost/Kconfig -source drivers/lguest/Kconfig endif # VIRTUALIZATION diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 59ca2eea522c..19adbb418443 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -469,7 +469,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; cpuid_mask(&entry->ecx, CPUID_7_ECX); /* PKU is not yet implemented for shadow paging. */ - if (!tdp_enabled) + if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 762cdf2595f9..e1e89ee4af75 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -84,11 +84,6 @@ static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu) | ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32); } -static inline u32 kvm_read_pkru(struct kvm_vcpu *vcpu) -{ - return kvm_x86_ops->get_pkru(vcpu); -} - static inline void enter_guest_mode(struct kvm_vcpu *vcpu) { vcpu->arch.hflags |= HF_GUEST_MASK; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 9b1dd114956a..04d750813c9d 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -108,7 +108,7 @@ module_param(dbg, bool, 0644); (((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1)) -#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) +#define PT64_BASE_ADDR_MASK __sme_clr((((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))) #define PT64_DIR_BASE_ADDR_MASK \ (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1)) #define PT64_LVL_ADDR_MASK(level) \ @@ -126,7 +126,7 @@ module_param(dbg, bool, 0644); * PT32_LEVEL_BITS))) - 1)) #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \ - | shadow_x_mask | shadow_nx_mask) + | shadow_x_mask | shadow_nx_mask | shadow_me_mask) #define ACC_EXEC_MASK 1 #define ACC_WRITE_MASK PT_WRITABLE_MASK @@ -186,6 +186,7 @@ static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_mmio_value; static u64 __read_mostly shadow_present_mask; +static u64 __read_mostly shadow_me_mask; /* * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value. @@ -349,7 +350,7 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) */ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, - u64 acc_track_mask) + u64 acc_track_mask, u64 me_mask) { BUG_ON(!dirty_mask != !accessed_mask); BUG_ON(!accessed_mask && !acc_track_mask); @@ -362,6 +363,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, shadow_x_mask = x_mask; shadow_present_mask = p_mask; shadow_acc_track_mask = acc_track_mask; + shadow_me_mask = me_mask; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); @@ -2433,7 +2435,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK | - shadow_user_mask | shadow_x_mask; + shadow_user_mask | shadow_x_mask | shadow_me_mask; if (sp_ad_disabled(sp)) spte |= shadow_acc_track_value; @@ -2745,6 +2747,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, pte_access &= ~ACC_WRITE_MASK; spte |= (u64)pfn << PAGE_SHIFT; + spte |= shadow_me_mask; if (pte_access & ACC_WRITE_MASK) { @@ -4106,16 +4109,28 @@ void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { bool uses_nx = context->nx || context->base_role.smep_andnot_wp; + struct rsvd_bits_validate *shadow_zero_check; + int i; /* * Passing "true" to the last argument is okay; it adds a check * on bit 8 of the SPTEs which KVM doesn't use anyway. */ - __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + shadow_zero_check = &context->shadow_zero_check; + __reset_rsvds_bits_mask(vcpu, shadow_zero_check, boot_cpu_data.x86_phys_bits, context->shadow_root_level, uses_nx, guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), true); + + if (!shadow_me_mask) + return; + + for (i = context->shadow_root_level; --i >= 0;) { + shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask; + shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask; + } + } EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask); @@ -4133,17 +4148,29 @@ static void reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { + struct rsvd_bits_validate *shadow_zero_check; + int i; + + shadow_zero_check = &context->shadow_zero_check; + if (boot_cpu_is_amd()) - __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + __reset_rsvds_bits_mask(vcpu, shadow_zero_check, boot_cpu_data.x86_phys_bits, context->shadow_root_level, false, boot_cpu_has(X86_FEATURE_GBPAGES), true, true); else - __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, + __reset_rsvds_bits_mask_ept(shadow_zero_check, boot_cpu_data.x86_phys_bits, false); + if (!shadow_me_mask) + return; + + for (i = context->shadow_root_level; --i >= 0;) { + shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask; + shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask; + } } /* diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index d7d248a000dd..4b9a3ae6b725 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -185,7 +185,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, * index of the protection domain, so pte_pkey * 2 is * is the index of the first bit for the domain. */ - pkru_bits = (kvm_read_pkru(vcpu) >> (pte_pkey * 2)) & 3; + pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3; /* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */ offset = (pfec & ~1) + diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 4d8141e533c3..8dbd8dbc83eb 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1100,7 +1100,7 @@ static __init int svm_hardware_setup(void) if (vls) { if (!npt_enabled || - !boot_cpu_has(X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE) || + !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) || !IS_ENABLED(CONFIG_X86_64)) { vls = false; } else { @@ -1167,9 +1167,9 @@ static void avic_init_vmcb(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb; struct kvm_arch *vm_data = &svm->vcpu.kvm->arch; - phys_addr_t bpa = page_to_phys(svm->avic_backing_page); - phys_addr_t lpa = page_to_phys(vm_data->avic_logical_id_table_page); - phys_addr_t ppa = page_to_phys(vm_data->avic_physical_id_table_page); + phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page)); + phys_addr_t lpa = __sme_set(page_to_phys(vm_data->avic_logical_id_table_page)); + phys_addr_t ppa = __sme_set(page_to_phys(vm_data->avic_physical_id_table_page)); vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK; vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; @@ -1232,8 +1232,8 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_MWAIT); } - control->iopm_base_pa = iopm_base; - control->msrpm_base_pa = __pa(svm->msrpm); + control->iopm_base_pa = __sme_set(iopm_base); + control->msrpm_base_pa = __sme_set(__pa(svm->msrpm)); control->int_ctl = V_INTR_MASKING_MASK; init_seg(&save->es); @@ -1377,9 +1377,9 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return -EINVAL; new_entry = READ_ONCE(*entry); - new_entry = (page_to_phys(svm->avic_backing_page) & - AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | - AVIC_PHYSICAL_ID_ENTRY_VALID_MASK; + new_entry = __sme_set((page_to_phys(svm->avic_backing_page) & + AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | + AVIC_PHYSICAL_ID_ENTRY_VALID_MASK); WRITE_ONCE(*entry, new_entry); svm->avic_physical_id_cache = entry; @@ -1647,7 +1647,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->vmcb = page_address(page); clear_page(svm->vmcb); - svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; + svm->vmcb_pa = __sme_set(page_to_pfn(page) << PAGE_SHIFT); svm->asid_generation = 0; init_vmcb(svm); @@ -1675,7 +1675,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT)); + __free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT)); __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); @@ -1777,11 +1777,6 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_svm(vcpu)->vmcb->save.rflags = rflags; } -static u32 svm_get_pkru(struct kvm_vcpu *vcpu) -{ - return 0; -} - static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { switch (reg) { @@ -2335,7 +2330,7 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) u64 pdpte; int ret; - ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte, + ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(__sme_clr(cr3)), &pdpte, offset_in_page(cr3) + index * 8, 8); if (ret) return 0; @@ -2347,7 +2342,7 @@ static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->control.nested_cr3 = root; + svm->vmcb->control.nested_cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_NPT); svm_flush_tlb(vcpu); } @@ -2430,6 +2425,16 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; svm->vmcb->control.exit_code_hi = 0; svm->vmcb->control.exit_info_1 = error_code; + + /* + * FIXME: we should not write CR2 when L1 intercepts an L2 #PF exception. + * The fix is to add the ancillary datum (CR2 or DR6) to structs + * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 can be + * written only when inject_pending_event runs (DR6 would written here + * too). This should be conditional on a new capability---if the + * capability is disabled, kvm_multiple_exception would write the + * ancillary information to CR2 or DR6, for backwards ABI-compatibility. + */ if (svm->vcpu.arch.exception.nested_apf) svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; else @@ -2868,7 +2873,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) svm->nested.msrpm[p] = svm->msrpm[p] | value; } - svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm); + svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm)); return true; } @@ -4501,7 +4506,7 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, pr_debug("SVM: %s: use GA mode for irq %u\n", __func__, irq.vector); *svm = to_svm(vcpu); - vcpu_info->pi_desc_addr = page_to_phys((*svm)->avic_backing_page); + vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page)); vcpu_info->vector = irq.vector; return 0; @@ -4552,7 +4557,8 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, struct amd_iommu_pi_data pi; /* Try to enable guest_mode in IRTE */ - pi.base = page_to_phys(svm->avic_backing_page) & AVIC_HPA_MASK; + pi.base = __sme_set(page_to_phys(svm->avic_backing_page) & + AVIC_HPA_MASK); pi.ga_tag = AVIC_GATAG(kvm->arch.avic_vm_id, svm->vcpu.vcpu_id); pi.is_guest_mode = true; @@ -5001,7 +5007,7 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->save.cr3 = root; + svm->vmcb->save.cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_CR); svm_flush_tlb(vcpu); } @@ -5010,7 +5016,7 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->control.nested_cr3 = root; + svm->vmcb->control.nested_cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_NPT); /* Also sync guest cr3 here in case we live migrate */ @@ -5403,8 +5409,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, - .get_pkru = svm_get_pkru, - .tlb_flush = svm_flush_tlb, .run = svm_vcpu_run, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 39a6222bf968..d40900914a72 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -416,13 +416,10 @@ struct nested_vmx { /* The guest-physical address of the current VMCS L1 keeps for L2 */ gpa_t current_vmptr; - /* The host-usable pointer to the above */ - struct page *current_vmcs12_page; - struct vmcs12 *current_vmcs12; /* * Cache of the guest's VMCS, existing outside of guest memory. * Loaded from guest memory during VMPTRLD. Flushed to guest - * memory during VMXOFF, VMCLEAR, VMPTRLD. + * memory during VMCLEAR and VMPTRLD. */ struct vmcs12 *cached_vmcs12; /* @@ -639,8 +636,6 @@ struct vcpu_vmx { u64 current_tsc_ratio; - bool guest_pkru_valid; - u32 guest_pkru; u32 host_pkru; /* @@ -927,6 +922,10 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var); static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); static int alloc_identity_pagetable(struct kvm *kvm); +static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); +static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); +static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, + u16 error_code); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -2382,11 +2381,6 @@ static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_vmx(vcpu)->emulation_required = emulation_required(vcpu); } -static u32 vmx_get_pkru(struct kvm_vcpu *vcpu) -{ - return to_vmx(vcpu)->guest_pkru; -} - static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) { u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); @@ -2428,6 +2422,30 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) vmx_set_interrupt_shadow(vcpu, 0); } +static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, + unsigned long exit_qual) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned int nr = vcpu->arch.exception.nr; + u32 intr_info = nr | INTR_INFO_VALID_MASK; + + if (vcpu->arch.exception.has_error_code) { + vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code; + intr_info |= INTR_INFO_DELIVER_CODE_MASK; + } + + if (kvm_exception_is_soft(nr)) + intr_info |= INTR_TYPE_SOFT_EXCEPTION; + else + intr_info |= INTR_TYPE_HARD_EXCEPTION; + + if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) && + vmx_get_nmi_mask(vcpu)) + intr_info |= INTR_INFO_UNBLOCK_NMI; + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual); +} + /* * KVM wants to inject page-faults which it got to the guest. This function * checks whether in a nested guest, we need to inject them to L1 or L2. @@ -2437,23 +2455,38 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned int nr = vcpu->arch.exception.nr; - if (!((vmcs12->exception_bitmap & (1u << nr)) || - (nr == PF_VECTOR && vcpu->arch.exception.nested_apf))) - return 0; + if (nr == PF_VECTOR) { + if (vcpu->arch.exception.nested_apf) { + nested_vmx_inject_exception_vmexit(vcpu, + vcpu->arch.apf.nested_apf_token); + return 1; + } + /* + * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception. + * The fix is to add the ancillary datum (CR2 or DR6) to structs + * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 + * can be written only when inject_pending_event runs. This should be + * conditional on a new capability---if the capability is disabled, + * kvm_multiple_exception would write the ancillary information to + * CR2 or DR6, for backwards ABI-compatibility. + */ + if (nested_vmx_is_page_fault_vmexit(vmcs12, + vcpu->arch.exception.error_code)) { + nested_vmx_inject_exception_vmexit(vcpu, vcpu->arch.cr2); + return 1; + } + } else { + unsigned long exit_qual = 0; + if (nr == DB_VECTOR) + exit_qual = vcpu->arch.dr6; - if (vcpu->arch.exception.nested_apf) { - vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code); - nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, - PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | - INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK, - vcpu->arch.apf.nested_apf_token); - return 1; + if (vmcs12->exception_bitmap & (1u << nr)) { + nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + return 1; + } } - nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_readl(EXIT_QUALIFICATION)); - return 1; + return 0; } static void vmx_queue_exception(struct kvm_vcpu *vcpu) @@ -2667,7 +2700,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) * reason is that if one of these bits is necessary, it will appear * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control * fields of vmcs01 and vmcs02, will turn these bits off - and - * nested_vmx_exit_handled() will not pass related exits to L1. + * nested_vmx_exit_reflected() will not pass related exits to L1. * These rules have exceptions below. */ @@ -4955,6 +4988,28 @@ static bool vmx_get_enable_apicv(void) return enable_apicv; } +static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + gfn_t gfn; + + /* + * Don't need to mark the APIC access page dirty; it is never + * written to by the CPU during APIC virtualization. + */ + + if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { + gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } + + if (nested_cpu_has_posted_intr(vmcs12)) { + gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } +} + + static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4962,18 +5017,15 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) void *vapic_page; u16 status; - if (vmx->nested.pi_desc && - vmx->nested.pi_pending) { - vmx->nested.pi_pending = false; - if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return; - - max_irr = find_last_bit( - (unsigned long *)vmx->nested.pi_desc->pir, 256); + if (!vmx->nested.pi_desc || !vmx->nested.pi_pending) + return; - if (max_irr == 256) - return; + vmx->nested.pi_pending = false; + if (!pi_test_and_clear_on(vmx->nested.pi_desc)) + return; + max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); + if (max_irr != 256) { vapic_page = kmap(vmx->nested.virtual_apic_page); __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); kunmap(vmx->nested.virtual_apic_page); @@ -4985,6 +5037,8 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_INTR_STATUS, status); } } + + nested_mark_vmcs12_pages_dirty(vcpu); } static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, @@ -6502,7 +6556,7 @@ void vmx_enable_tdp(void) enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull, 0ull, VMX_EPT_EXECUTABLE_MASK, cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK, - VMX_EPT_RWX_MASK); + VMX_EPT_RWX_MASK, 0ull); ept_set_mmio_spte_mask(); kvm_enable_tdp(); @@ -7134,34 +7188,32 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) return 1; } +static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) +{ + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS); + vmcs_write64(VMCS_LINK_POINTER, -1ull); +} + static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) { if (vmx->nested.current_vmptr == -1ull) return; - /* current_vmptr and current_vmcs12 are always set/reset together */ - if (WARN_ON(vmx->nested.current_vmcs12 == NULL)) - return; - if (enable_shadow_vmcs) { /* copy to memory all shadowed fields in case they were modified */ copy_shadow_to_vmcs12(vmx); vmx->nested.sync_shadow_vmcs = false; - vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_SHADOW_VMCS); - vmcs_write64(VMCS_LINK_POINTER, -1ull); + vmx_disable_shadow_vmcs(vmx); } vmx->nested.posted_intr_nv = -1; /* Flush VMCS12 to guest memory */ - memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12, - VMCS12_SIZE); + kvm_vcpu_write_guest_page(&vmx->vcpu, + vmx->nested.current_vmptr >> PAGE_SHIFT, + vmx->nested.cached_vmcs12, 0, VMCS12_SIZE); - kunmap(vmx->nested.current_vmcs12_page); - nested_release_page(vmx->nested.current_vmcs12_page); vmx->nested.current_vmptr = -1ull; - vmx->nested.current_vmcs12 = NULL; } /* @@ -7175,12 +7227,14 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.vmxon = false; free_vpid(vmx->nested.vpid02); - nested_release_vmcs12(vmx); + vmx->nested.posted_intr_nv = -1; + vmx->nested.current_vmptr = -1ull; if (vmx->nested.msr_bitmap) { free_page((unsigned long)vmx->nested.msr_bitmap); vmx->nested.msr_bitmap = NULL; } if (enable_shadow_vmcs) { + vmx_disable_shadow_vmcs(vmx); vmcs_clear(vmx->vmcs01.shadow_vmcs); free_vmcs(vmx->vmcs01.shadow_vmcs); vmx->vmcs01.shadow_vmcs = NULL; @@ -7579,14 +7633,14 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) } nested_release_vmcs12(vmx); - vmx->nested.current_vmcs12 = new_vmcs12; - vmx->nested.current_vmcs12_page = page; /* * Load VMCS12 from guest memory since it is not already * cached. */ - memcpy(vmx->nested.cached_vmcs12, - vmx->nested.current_vmcs12, VMCS12_SIZE); + memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE); + kunmap(page); + nested_release_page_clean(page); + set_current_vmptr(vmx, vmptr); } @@ -8019,12 +8073,11 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, * should handle it ourselves in L0 (and then continue L2). Only call this * when in is_guest_mode (L2). */ -static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) +static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) { u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO); struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u32 exit_reason = vmx->exit_reason; trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason, vmcs_readl(EXIT_QUALIFICATION), @@ -8033,6 +8086,18 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) vmcs_read32(VM_EXIT_INTR_ERROR_CODE), KVM_ISA_VMX); + /* + * The host physical addresses of some pages of guest memory + * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU + * may write to these pages via their host physical address while + * L2 is running, bypassing any address-translation-based dirty + * tracking (e.g. EPT write protection). + * + * Mark them dirty on every exit from L2 to prevent them from + * getting out of sync with dirty tracking. + */ + nested_mark_vmcs12_pages_dirty(vcpu); + if (vmx->nested.nested_run_pending) return false; @@ -8169,6 +8234,29 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) } } +static int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason) +{ + u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + + /* + * At this point, the exit interruption info in exit_intr_info + * is only valid for EXCEPTION_NMI exits. For EXTERNAL_INTERRUPT + * we need to query the in-kernel LAPIC. + */ + WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT); + if ((exit_intr_info & + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) == + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + vmcs12->vm_exit_intr_error_code = + vmcs_read32(VM_EXIT_INTR_ERROR_CODE); + } + + nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info, + vmcs_readl(EXIT_QUALIFICATION)); + return 1; +} + static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) { *info1 = vmcs_readl(EXIT_QUALIFICATION); @@ -8415,12 +8503,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) if (vmx->emulation_required) return handle_invalid_guest_state(vcpu); - if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) { - nested_vmx_vmexit(vcpu, exit_reason, - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_readl(EXIT_QUALIFICATION)); - return 1; - } + if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason)) + return nested_vmx_reflect_vmexit(vcpu, exit_reason); if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { dump_vmcs(); @@ -8929,8 +9013,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); - if (vmx->guest_pkru_valid) - __write_pkru(vmx->guest_pkru); + if (static_cpu_has(X86_FEATURE_PKU) && + kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && + vcpu->arch.pkru != vmx->host_pkru) + __write_pkru(vcpu->arch.pkru); atomic_switch_perf_msrs(vmx); debugctlmsr = get_debugctlmsr(); @@ -9078,13 +9164,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * back on host, so it is safe to read guest PKRU from current * XSAVE. */ - if (boot_cpu_has(X86_FEATURE_OSPKE)) { - vmx->guest_pkru = __read_pkru(); - if (vmx->guest_pkru != vmx->host_pkru) { - vmx->guest_pkru_valid = true; + if (static_cpu_has(X86_FEATURE_PKU) && + kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) { + vcpu->arch.pkru = __read_pkru(); + if (vcpu->arch.pkru != vmx->host_pkru) __write_pkru(vmx->host_pkru); - } else - vmx->guest_pkru_valid = false; } /* @@ -9223,7 +9307,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; - vmx->nested.current_vmcs12 = NULL; vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; @@ -9509,12 +9592,15 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, WARN_ON(!is_guest_mode(vcpu)); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) - nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason, - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_readl(EXIT_QUALIFICATION)); - else + if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) { + vmcs12->vm_exit_intr_error_code = fault->error_code; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, + PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | + INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK, + fault->address); + } else { kvm_inject_page_fault(vcpu, fault); + } } static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, @@ -10094,12 +10180,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept, * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when * !enable_ept, EB.PF is 1, so the "or" will always be 1. - * - * A problem with this approach (when !enable_ept) is that L1 may be - * injected with more page faults than it asked for. This could have - * caused problems, but in practice existing hypervisors don't care. - * To fix this, we will need to emulate the PFEC checking (on the L1 - * page tables), using walk_addr(), when injecting PFs to L1. */ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, enable_ept ? vmcs12->page_fault_error_code_mask : 0); @@ -10847,13 +10927,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->vm_exit_reason = exit_reason; vmcs12->exit_qualification = exit_qualification; - vmcs12->vm_exit_intr_info = exit_intr_info; - if ((vmcs12->vm_exit_intr_info & - (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) == - (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) - vmcs12->vm_exit_intr_error_code = - vmcs_read32(VM_EXIT_INTR_ERROR_CODE); + vmcs12->idt_vectoring_info_field = 0; vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); @@ -11049,8 +11124,15 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmx_switch_vmcs(vcpu, &vmx->vmcs01); - if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) - && nested_exit_intr_ack_set(vcpu)) { + /* + * TODO: SDM says that with acknowledge interrupt on exit, bit 31 of + * the VM-exit interrupt information (valid interrupt) is always set to + * 1 on EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't need + * kvm_cpu_has_interrupt(). See the commit message for details. + */ + if (nested_exit_intr_ack_set(vcpu) && + exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && + kvm_cpu_has_interrupt(vcpu)) { int irq = kvm_cpu_get_interrupt(vcpu); WARN_ON(irq < 0); vmcs12->vm_exit_intr_info = irq | @@ -11593,8 +11675,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, - .get_pkru = vmx_get_pkru, - .tlb_flush = vmx_flush_tlb, .run = vmx_vcpu_run, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6c97c82814c4..ef5102f80497 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -54,6 +54,7 @@ #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> #include <linux/sched/stat.h> +#include <linux/mem_encrypt.h> #include <trace/events/kvm.h> @@ -3159,15 +3160,18 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, kvm_set_hflags(vcpu, hflags); vcpu->arch.smi_pending = events->smi.pending; - if (events->smi.smm_inside_nmi) - vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; - else - vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; - if (lapic_in_kernel(vcpu)) { - if (events->smi.latched_init) - set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + + if (events->smi.smm) { + if (events->smi.smm_inside_nmi) + vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else - clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; + if (lapic_in_kernel(vcpu)) { + if (events->smi.latched_init) + set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + else + clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + } } } @@ -3242,7 +3246,12 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) u32 size, offset, ecx, edx; cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); - memcpy(dest + offset, src, size); + if (feature == XFEATURE_MASK_PKRU) + memcpy(dest + offset, &vcpu->arch.pkru, + sizeof(vcpu->arch.pkru)); + else + memcpy(dest + offset, src, size); + } valid -= feature; @@ -3280,7 +3289,11 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) u32 size, offset, ecx, edx; cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); - memcpy(dest, src + offset, size); + if (feature == XFEATURE_MASK_PKRU) + memcpy(&vcpu->arch.pkru, src + offset, + sizeof(vcpu->arch.pkru)); + else + memcpy(dest, src + offset, size); } valid -= feature; @@ -6113,7 +6126,7 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0, - PT_PRESENT_MASK, 0); + PT_PRESENT_MASK, 0, sme_me_mask); kvm_timer_init(); perf_register_guest_info_callbacks(&kvm_guest_cbs); @@ -6215,6 +6228,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) lapic_irq.shorthand = 0; lapic_irq.dest_mode = 0; + lapic_irq.level = 0; lapic_irq.dest_id = apicid; lapic_irq.msi_redir_hint = false; @@ -6721,17 +6735,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); -void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address) -{ - /* - * The physical address of apic access page is stored in the VMCS. - * Update it when it becomes invalid. - */ - if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT)) - kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); -} - /* * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the @@ -7629,7 +7632,9 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) */ vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state); + /* PKRU is separately restored in kvm_x86_ops->run. */ + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, + ~XFEATURE_MASK_PKRU); trace_kvm_fpu(1); } |