diff options
Diffstat (limited to 'arch/x86/kvm/vmx/nested.c')
| -rw-r--r-- | arch/x86/kvm/vmx/nested.c | 2609 |
1 files changed, 1673 insertions, 936 deletions
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1a52134b0c42..40777278eabb 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -1,26 +1,30 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/objtool.h> #include <linux/percpu.h> #include <asm/debugreg.h> #include <asm/mmu_context.h> +#include <asm/msr.h> +#include "x86.h" #include "cpuid.h" #include "hyperv.h" #include "mmu.h" #include "nested.h" #include "pmu.h" +#include "posted_intr.h" #include "sgx.h" #include "trace.h" #include "vmx.h" -#include "x86.h" +#include "smm.h" static bool __read_mostly enable_shadow_vmcs = 1; module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO); -static bool __read_mostly nested_early_check = 0; -module_param(nested_early_check, bool, S_IRUGO); +static bool __ro_after_init warn_on_missed_cc; +module_param(warn_on_missed_cc, bool, 0444); #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK @@ -177,7 +181,7 @@ static int nested_vmx_failValid(struct kvm_vcpu *vcpu, * VM_INSTRUCTION_ERROR is not shadowed. Enlightened VMCS 'shadows' all * fields and thus must be synced. */ - if (to_vmx(vcpu)->nested.hv_evmcs_vmptr != EVMPTR_INVALID) + if (nested_vmx_is_evmptr12_set(to_vmx(vcpu))) to_vmx(vcpu)->nested.need_vmcs12_to_shadow_sync = true; return kvm_skip_emulated_instruction(vcpu); @@ -191,8 +195,8 @@ static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error) * failValid writes the error number to the current VMCS, which * can't be done if there isn't a current VMCS. */ - if (vmx->nested.current_vmptr == -1ull && - !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (vmx->nested.current_vmptr == INVALID_GPA && + !nested_vmx_is_evmptr12_valid(vmx)) return nested_vmx_failInvalid(vcpu); return nested_vmx_failValid(vcpu, vm_instruction_error); @@ -202,7 +206,7 @@ static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator) { /* TODO: not to reset guest simply here. */ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); - pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator); + pr_debug_ratelimited("nested vmx abort, indicator %d\n", indicator); } static inline bool vmx_control_verify(u32 control, u32 low, u32 high) @@ -218,20 +222,53 @@ static inline u64 vmx_control_msr(u32 low, u32 high) static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) { secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS); - vmcs_write64(VMCS_LINK_POINTER, -1ull); + vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); vmx->nested.need_vmcs12_to_shadow_sync = false; } static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_KVM_HYPERV + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { - kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); - vmx->nested.hv_evmcs = NULL; + kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map); + vmx->nested.hv_evmcs = NULL; + vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; + + if (hv_vcpu) { + hv_vcpu->nested.pa_page_gpa = INVALID_GPA; + hv_vcpu->nested.vm_id = 0; + hv_vcpu->nested.vp_id = 0; } +#endif +} - vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; +static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr) +{ +#ifdef CONFIG_KVM_HYPERV + struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * When Enlightened VMEntry is enabled on the calling CPU we treat + * memory area pointer by vmptr as Enlightened VMCS (as there's no good + * way to distinguish it from VMCS12) and we must not corrupt it by + * writing to the non-existent 'launch_state' field. The area doesn't + * have to be the currently active EVMCS on the calling CPU and there's + * nothing KVM has to do to transition it from 'active' to 'non-active' + * state. It is possible that the area will stay mapped as + * vmx->nested.hv_evmcs but this shouldn't be a problem. + */ + if (!guest_cpu_cap_has_evmcs(vcpu) || + !evmptr_is_valid(nested_get_evmptr(vcpu))) + return false; + + if (nested_vmx_evmcs(vmx) && vmptr == vmx->nested.hv_evmcs_vmptr) + nested_release_evmcs(vcpu); + + return true; +#else + return false; +#endif } static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, @@ -239,7 +276,7 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, { struct vmcs_host_state *dest, *src; - if (unlikely(!vmx->guest_state_loaded)) + if (unlikely(!vmx->vt.guest_state_loaded)) return; src = &prev->host_state; @@ -265,11 +302,27 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) cpu = get_cpu(); prev = vmx->loaded_vmcs; vmx->loaded_vmcs = vmcs; - vmx_vcpu_load_vmcs(vcpu, cpu, prev); + vmx_vcpu_load_vmcs(vcpu, cpu); vmx_sync_vmcs_host_state(vmx, prev); put_cpu(); - vmx_register_cache_reset(vcpu); + vcpu->arch.regs_avail = ~VMX_REGS_LAZY_LOAD_SET; + + /* + * All lazily updated registers will be reloaded from VMCS12 on both + * vmentry and vmexit. + */ + vcpu->arch.regs_dirty = 0; +} + +static void nested_put_vmcs12_pages(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map); + kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map); + kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map); + vmx->nested.pi_desc = NULL; } /* @@ -290,9 +343,10 @@ static void free_nested(struct kvm_vcpu *vcpu) vmx->nested.vmxon = false; vmx->nested.smm.vmxon = false; + vmx->nested.vmxon_ptr = INVALID_GPA; free_vpid(vmx->nested.vpid02); vmx->nested.posted_intr_nv = -1; - vmx->nested.current_vmptr = -1ull; + vmx->nested.current_vmptr = INVALID_GPA; if (enable_shadow_vmcs) { vmx_disable_shadow_vmcs(vmx); vmcs_clear(vmx->vmcs01.shadow_vmcs); @@ -303,16 +357,10 @@ static void free_nested(struct kvm_vcpu *vcpu) vmx->nested.cached_vmcs12 = NULL; kfree(vmx->nested.cached_shadow_vmcs12); vmx->nested.cached_shadow_vmcs12 = NULL; - /* Unpin physical memory we referred to in the vmcs02 */ - if (vmx->nested.apic_access_page) { - kvm_release_page_clean(vmx->nested.apic_access_page); - vmx->nested.apic_access_page = NULL; - } - kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true); - kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true); - vmx->nested.pi_desc = NULL; - kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); + nested_put_vmcs12_pages(vcpu); + + kvm_mmu_free_roots(vcpu->kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); nested_release_evmcs(vcpu); @@ -330,22 +378,84 @@ void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu) vcpu_put(vcpu); } +#define EPTP_PA_MASK GENMASK_ULL(51, 12) + +static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) +{ + return VALID_PAGE(root_hpa) && + ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); +} + +static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp, + gpa_t addr) +{ + unsigned long roots = 0; + uint i; + struct kvm_mmu_root_info *cached_root; + + WARN_ON_ONCE(!mmu_is_nested(vcpu)); + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + cached_root = &vcpu->arch.mmu->prev_roots[i]; + + if (nested_ept_root_matches(cached_root->hpa, cached_root->pgd, + eptp)) + roots |= KVM_MMU_ROOT_PREVIOUS(i); + } + if (roots) + kvm_mmu_invalidate_addr(vcpu, vcpu->arch.mmu, addr, roots); +} + static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long exit_qualification; u32 vm_exit_reason; - unsigned long exit_qualification = vcpu->arch.exit_qualification; if (vmx->nested.pml_full) { vm_exit_reason = EXIT_REASON_PML_FULL; vmx->nested.pml_full = false; - exit_qualification &= INTR_INFO_UNBLOCK_NMI; - } else if (fault->error_code & PFERR_RSVD_MASK) - vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; - else - vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + + /* + * It should be impossible to trigger a nested PML Full VM-Exit + * for anything other than an EPT Violation from L2. KVM *can* + * trigger nEPT page fault injection in response to an EPT + * Misconfig, e.g. if the MMIO SPTE was stale and L1's EPT + * tables also changed, but KVM should not treat EPT Misconfig + * VM-Exits as writes. + */ + WARN_ON_ONCE(vmx->vt.exit_reason.basic != EXIT_REASON_EPT_VIOLATION); + + /* + * PML Full and EPT Violation VM-Exits both use bit 12 to report + * "NMI unblocking due to IRET", i.e. the bit can be propagated + * as-is from the original EXIT_QUALIFICATION. + */ + exit_qualification = vmx_get_exit_qual(vcpu) & INTR_INFO_UNBLOCK_NMI; + } else { + if (fault->error_code & PFERR_RSVD_MASK) { + vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; + exit_qualification = 0; + } else { + exit_qualification = fault->exit_qualification; + exit_qualification |= vmx_get_exit_qual(vcpu) & + (EPT_VIOLATION_GVA_IS_VALID | + EPT_VIOLATION_GVA_TRANSLATED); + vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + } + + /* + * Although the caller (kvm_inject_emulated_page_fault) would + * have already synced the faulting address in the shadow EPT + * tables for the current EPTP12, we also need to sync it for + * any other cached EPTP02s based on the same EP4TA, since the + * TLB associates mappings to the EP4TA rather than the full EPTP. + */ + nested_ept_invalidate_addr(vcpu, vmcs12->ept_pointer, + fault->address); + } nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification); vmcs12->guest_physical_address = fault->address; @@ -353,9 +463,11 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, static void nested_ept_new_eptp(struct kvm_vcpu *vcpu) { - kvm_init_shadow_ept_mmu(vcpu, - to_vmx(vcpu)->nested.msrs.ept_caps & - VMX_EPT_EXECUTE_ONLY_BIT, + struct vcpu_vmx *vmx = to_vmx(vcpu); + bool execonly = vmx->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT; + int ept_lpage_level = ept_caps_to_lpage_level(vmx->nested.msrs.ept_caps); + + kvm_init_shadow_ept_mmu(vcpu, execonly, ept_lpage_level, nested_ept_ad_enabled(vcpu), nested_ept_get_eptp(vcpu)); } @@ -391,62 +503,22 @@ static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, return inequality ^ bit; } - -/* - * 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. - */ -static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit_qual) +static bool nested_vmx_is_exception_vmexit(struct kvm_vcpu *vcpu, u8 vector, + u32 error_code) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - unsigned int nr = vcpu->arch.exception.nr; - bool has_payload = vcpu->arch.exception.has_payload; - unsigned long payload = vcpu->arch.exception.payload; - - if (nr == PF_VECTOR) { - if (vcpu->arch.exception.nested_apf) { - *exit_qual = vcpu->arch.apf.nested_apf_token; - return 1; - } - if (nested_vmx_is_page_fault_vmexit(vmcs12, - vcpu->arch.exception.error_code)) { - *exit_qual = has_payload ? payload : vcpu->arch.cr2; - return 1; - } - } else if (vmcs12->exception_bitmap & (1u << nr)) { - if (nr == DB_VECTOR) { - if (!has_payload) { - payload = vcpu->arch.dr6; - payload &= ~DR6_BT; - payload ^= DR6_ACTIVE_LOW; - } - *exit_qual = payload; - } else - *exit_qual = 0; - return 1; - } - return 0; -} - - -static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, - struct x86_exception *fault) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - - WARN_ON(!is_guest_mode(vcpu)); + /* + * Drop bits 31:16 of the error code when performing the #PF mask+match + * check. All VMCS fields involved are 32 bits, but Intel CPUs never + * set bits 31:16 and VMX disallows setting bits 31:16 in the injected + * error code. Including the to-be-dropped bits in the check might + * result in an "impossible" or missed exit from L1's perspective. + */ + if (vector == PF_VECTOR) + return nested_vmx_is_page_fault_vmexit(vmcs12, (u16)error_code); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) && - !to_vmx(vcpu)->nested.nested_run_pending) { - 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); - } + return (vmcs12->exception_bitmap & (1u << vector)); } static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu, @@ -483,71 +555,26 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, if (CC(!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr))) return -EINVAL; - return 0; -} - -/* - * Check if MSR is intercepted for L01 MSR bitmap. - */ -static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) -{ - unsigned long *msr_bitmap; - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) - return true; - - msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; - - if (msr <= 0x1fff) { - return !!test_bit(msr, msr_bitmap + 0x800 / f); - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - return !!test_bit(msr, msr_bitmap + 0xc00 / f); - } + if (CC(!nested_cpu_has_vid(vmcs12) && vmcs12->tpr_threshold >> 4)) + return -EINVAL; - return true; + return 0; } /* - * If a msr is allowed by L0, we should check whether it is allowed by L1. - * The corresponding bit will be cleared unless both of L0 and L1 allow it. + * For x2APIC MSRs, ignore the vmcs01 bitmap. L1 can enable x2APIC without L1 + * itself utilizing x2APIC. All MSRs were previously set to be intercepted, + * only the "disable intercept" case needs to be handled. */ -static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, - unsigned long *msr_bitmap_nested, - u32 msr, int type) +static void nested_vmx_disable_intercept_for_x2apic_msr(unsigned long *msr_bitmap_l1, + unsigned long *msr_bitmap_l0, + u32 msr, int type) { - int f = sizeof(unsigned long); - - /* - * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals - * have the write-low and read-high bitmap offsets the wrong way round. - * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. - */ - if (msr <= 0x1fff) { - if (type & MSR_TYPE_R && - !test_bit(msr, msr_bitmap_l1 + 0x000 / f)) - /* read-low */ - __clear_bit(msr, msr_bitmap_nested + 0x000 / f); + if (type & MSR_TYPE_R && !vmx_test_msr_bitmap_read(msr_bitmap_l1, msr)) + vmx_clear_msr_bitmap_read(msr_bitmap_l0, msr); - if (type & MSR_TYPE_W && - !test_bit(msr, msr_bitmap_l1 + 0x800 / f)) - /* write-low */ - __clear_bit(msr, msr_bitmap_nested + 0x800 / f); - - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - if (type & MSR_TYPE_R && - !test_bit(msr, msr_bitmap_l1 + 0x400 / f)) - /* read-high */ - __clear_bit(msr, msr_bitmap_nested + 0x400 / f); - - if (type & MSR_TYPE_W && - !test_bit(msr, msr_bitmap_l1 + 0xc00 / f)) - /* write-high */ - __clear_bit(msr, msr_bitmap_nested + 0xc00 / f); - - } + if (type & MSR_TYPE_W && !vmx_test_msr_bitmap_write(msr_bitmap_l1, msr)) + vmx_clear_msr_bitmap_write(msr_bitmap_l0, msr); } static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) @@ -562,6 +589,34 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) } } +#define BUILD_NVMX_MSR_INTERCEPT_HELPER(rw) \ +static inline \ +void nested_vmx_set_msr_##rw##_intercept(struct vcpu_vmx *vmx, \ + unsigned long *msr_bitmap_l1, \ + unsigned long *msr_bitmap_l0, u32 msr) \ +{ \ + if (vmx_test_msr_bitmap_##rw(vmx->vmcs01.msr_bitmap, msr) || \ + vmx_test_msr_bitmap_##rw(msr_bitmap_l1, msr)) \ + vmx_set_msr_bitmap_##rw(msr_bitmap_l0, msr); \ + else \ + vmx_clear_msr_bitmap_##rw(msr_bitmap_l0, msr); \ +} +BUILD_NVMX_MSR_INTERCEPT_HELPER(read) +BUILD_NVMX_MSR_INTERCEPT_HELPER(write) + +static inline void nested_vmx_set_intercept_for_msr(struct vcpu_vmx *vmx, + unsigned long *msr_bitmap_l1, + unsigned long *msr_bitmap_l0, + u32 msr, int types) +{ + if (types & MSR_TYPE_R) + nested_vmx_set_msr_read_intercept(vmx, msr_bitmap_l1, + msr_bitmap_l0, msr); + if (types & MSR_TYPE_W) + nested_vmx_set_msr_write_intercept(vmx, msr_bitmap_l1, + msr_bitmap_l0, msr); +} + /* * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. @@ -569,25 +624,42 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { + struct vcpu_vmx *vmx = to_vmx(vcpu); int msr; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; - struct kvm_host_map *map = &to_vmx(vcpu)->nested.msr_bitmap_map; + unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; + struct kvm_host_map map; /* Nothing to do if the MSR bitmap is not in use. */ if (!cpu_has_vmx_msr_bitmap() || !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return false; - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map)) + /* + * MSR bitmap update can be skipped when: + * - MSR bitmap for L1 hasn't changed. + * - Nested hypervisor (L1) is attempting to launch the same L2 as + * before. + * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature + * and tells KVM (L0) there were no changes in MSR bitmap for L2. + */ + if (!vmx->nested.force_msr_bitmap_recalc) { + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); + + if (evmcs && evmcs->hv_enlightenments_control.msr_bitmap && + evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) + return true; + } + + if (kvm_vcpu_map_readonly(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), &map)) return false; - msr_bitmap_l1 = (unsigned long *)map->hva; + msr_bitmap_l1 = (unsigned long *)map.hva; /* * To keep the control flow simple, pay eight 8-byte writes (sixteen * 4-byte writes on 32-bit systems) up front to enable intercepts for - * the x2APIC MSR range and selectively disable them below. + * the x2APIC MSR range and selectively toggle those relevant to L2. */ enable_x2apic_msr_intercepts(msr_bitmap_l0); @@ -606,61 +678,73 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, } } - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_R | MSR_TYPE_W); if (nested_cpu_has_vid(vmcs12)) { - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); } } - /* KVM unconditionally exposes the FS/GS base MSRs to L1. */ + /* + * Always check vmcs01's bitmap to honor userspace MSR filters and any + * other runtime changes to vmcs01's bitmap, e.g. dynamic pass-through. + */ #ifdef CONFIG_X86_64 - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_FS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_FS_BASE, MSR_TYPE_RW); - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_GS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_GS_BASE, MSR_TYPE_RW); - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_KERNEL_GS_BASE, MSR_TYPE_RW); #endif + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); - /* - * Checking the L0->L1 bitmap is trying to verify two things: - * - * 1. L0 gave a permission to L1 to actually passthrough the MSR. This - * ensures that we do not accidentally generate an L02 MSR bitmap - * from the L12 MSR bitmap that is too permissive. - * 2. That L1 or L2s have actually used the MSR. This avoids - * unnecessarily merging of the bitmap if the MSR is unused. This - * works properly because we only update the L01 MSR bitmap lazily. - * So even if L0 should pass L1 these MSRs, the L01 bitmap is only - * updated to reflect this when L1 (or its L2s) actually write to - * the MSR. - */ - if (!msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL)) - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - MSR_IA32_SPEC_CTRL, - MSR_TYPE_R | MSR_TYPE_W); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, MSR_TYPE_W); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_FLUSH_CMD, MSR_TYPE_W); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_APERF, MSR_TYPE_R); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_MPERF, MSR_TYPE_R); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_U_CET, MSR_TYPE_RW); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_S_CET, MSR_TYPE_RW); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PL0_SSP, MSR_TYPE_RW); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PL1_SSP, MSR_TYPE_RW); - if (!msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD)) - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - MSR_IA32_PRED_CMD, - MSR_TYPE_W); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PL2_SSP, MSR_TYPE_RW); - kvm_vcpu_unmap(vcpu, &to_vmx(vcpu)->nested.msr_bitmap_map, false); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PL3_SSP, MSR_TYPE_RW); + + kvm_vcpu_unmap(vcpu, &map); + + vmx->nested.force_msr_bitmap_recalc = false; return true; } @@ -668,33 +752,39 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - struct kvm_host_map map; - struct vmcs12 *shadow; + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; if (!nested_cpu_has_shadow_vmcs(vmcs12) || - vmcs12->vmcs_link_pointer == -1ull) + vmcs12->vmcs_link_pointer == INVALID_GPA) return; - shadow = get_shadow_vmcs12(vcpu); - - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map)) + if (ghc->gpa != vmcs12->vmcs_link_pointer && + kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, + vmcs12->vmcs_link_pointer, VMCS12_SIZE)) return; - memcpy(shadow, map.hva, VMCS12_SIZE); - kvm_vcpu_unmap(vcpu, &map, false); + kvm_read_guest_cached(vcpu->kvm, ghc, get_shadow_vmcs12(vcpu), + VMCS12_SIZE); } static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; if (!nested_cpu_has_shadow_vmcs(vmcs12) || - vmcs12->vmcs_link_pointer == -1ull) + vmcs12->vmcs_link_pointer == INVALID_GPA) + return; + + if (ghc->gpa != vmcs12->vmcs_link_pointer && + kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, + vmcs12->vmcs_link_pointer, VMCS12_SIZE)) return; - kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer, - get_shadow_vmcs12(vcpu), VMCS12_SIZE); + kvm_write_guest_cached(vcpu->kvm, ghc, get_shadow_vmcs12(vcpu), + VMCS12_SIZE); } /* @@ -762,12 +852,30 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, return 0; } +static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low, + vmx->nested.msrs.misc_high); + + return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER; +} + static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, u32 count, u64 addr) { if (count == 0) return 0; + /* + * Exceeding the limit results in architecturally _undefined_ behavior, + * i.e. KVM is allowed to do literally anything in response to a bad + * limit. Immediately generate a consistency check so that code that + * consumes the count doesn't need to worry about extreme edge cases. + */ + if (count > nested_vmx_max_atomic_switch_msrs(vcpu)) + return -EINVAL; + if (!kvm_vcpu_is_legal_aligned_gpa(vcpu, addr, 16) || !kvm_vcpu_is_legal_gpa(vcpu, (addr + count * sizeof(struct vmx_msr_entry) - 1))) return -EINVAL; @@ -878,15 +986,6 @@ static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu, return 0; } -static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low, - vmx->nested.msrs.misc_high); - - return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER; -} - /* * Load guest's/host's msr at nested entry/exit. * return 0 for success, entry index for failure. @@ -903,7 +1002,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu); for (i = 0; i < count; i++) { - if (unlikely(i >= max_msr_list_size)) + if (WARN_ON_ONCE(i >= max_msr_list_size)) goto fail; if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e), @@ -919,7 +1018,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index, e.reserved); goto fail; } - if (kvm_set_msr(vcpu, e.index, e.value)) { + if (kvm_emulate_msr_write(vcpu, e.index, e.value)) { pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, e.value); @@ -955,7 +1054,7 @@ static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu, } } - if (kvm_get_msr(vcpu, msr_index, data)) { + if (kvm_emulate_msr_read(vcpu, msr_index, data)) { pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__, msr_index); return false; @@ -991,7 +1090,7 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu); for (i = 0; i < count; i++) { - if (unlikely(i >= max_msr_list_size)) + if (WARN_ON_ONCE(i >= max_msr_list_size)) return -EINVAL; if (!read_and_check_msr_entry(vcpu, gpa, i, &e)) @@ -1050,9 +1149,9 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, /* * Emulated VMEntry does not fail here. Instead a less * accurate value will be returned by - * nested_vmx_get_vmexit_msr_value() using kvm_get_msr() - * instead of reading the value from the vmcs02 VMExit - * MSR-store area. + * nested_vmx_get_vmexit_msr_value() by reading KVM's + * internal MSR state instead of reading the value from + * the vmcs02 VMExit MSR-store area. */ pr_warn_ratelimited( "Not enough msr entries in msr_autostore. Can't add msr %x\n", @@ -1077,7 +1176,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, bool reload_pdptrs, enum vm_entry_failure_code *entry_failure_code) { - if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) { + if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -1087,20 +1186,20 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, * must not be dereferenced. */ if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) && - CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { + CC(!load_pdptrs(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_PDPTE; return -EINVAL; } - if (!nested_ept) - kvm_mmu_new_pgd(vcpu, cr3); - vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ kvm_init_mmu(vcpu); + if (!nested_ept) + kvm_mmu_new_pgd(vcpu, cr3); + return 0; } @@ -1131,12 +1230,18 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* Handle pending Hyper-V TLB flush requests */ + kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept); + /* - * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings - * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a - * full TLB flush from the guest's perspective. This is required even - * if VPID is disabled in the host as KVM may need to synchronize the - * MMU in response to the guest TLB flush. + * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the + * same VPID as the host, and so architecturally, linear and combined + * mappings for VPID=0 must be flushed at VM-Enter and VM-Exit. KVM + * emulates L2 sharing L1's VPID=0 by using vpid01 while running L2, + * and so KVM must also emulate TLB flush of VPID=0, i.e. vpid01. This + * is required if VPID is disabled in KVM, as a TLB flush (there are no + * VPIDs) still occurs from L1's perspective, and KVM may need to + * synchronize the MMU in response to the guest TLB flush. * * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use. * EPT is a special snowflake, as guest-physical mappings aren't @@ -1154,29 +1259,26 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, WARN_ON(!enable_vpid); /* - * If VPID is enabled and used by vmc12, but L2 does not have a unique - * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate - * a VPID for L2, flush the current context as the effective ASID is - * common to both L1 and L2. - * - * Defer the flush so that it runs after vmcs02.EPTP has been set by - * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid - * redundant flushes further down the nested pipeline. - * - * If a TLB flush isn't required due to any of the above, and vpid12 is - * changing then the new "virtual" VPID (vpid12) will reuse the same - * "real" VPID (vpid02), and so needs to be flushed. There's no direct - * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for - * all nested vCPUs. Remember, a flush on VM-Enter does not invalidate - * guest-physical mappings, so there is no need to sync the nEPT MMU. + * VPID is enabled and in use by vmcs12. If vpid12 is changing, then + * emulate a guest TLB flush as KVM does not track vpid12 history nor + * is the VPID incorporated into the MMU context. I.e. KVM must assume + * that the new vpid12 has never been used and thus represents a new + * guest ASID that cannot have entries in the TLB. */ - if (!nested_has_guest_tlb_tag(vcpu)) { - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } else if (is_vmenter && - vmcs12->virtual_processor_id != vmx->nested.last_vpid) { + if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) { vmx->nested.last_vpid = vmcs12->virtual_processor_id; - vpid_sync_context(nested_get_vpid02(vcpu)); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + return; } + + /* + * If VPID is enabled, used by vmc12, and vpid12 is not changing but + * does not have a unique TLB tag (ASID), i.e. EPT is disabled and + * KVM was unable to allocate a VPID for L2, flush the current context + * as the effective ASID is common to both L1 and L2. + */ + if (!nested_has_guest_tlb_tag(vcpu)) + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) @@ -1189,21 +1291,33 @@ static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data) { - const u64 feature_and_reserved = - /* feature (except bit 48; see below) */ - BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) | - /* reserved */ - BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56); - u64 vmx_basic = vmx->nested.msrs.basic; + const u64 feature_bits = VMX_BASIC_DUAL_MONITOR_TREATMENT | + VMX_BASIC_INOUT | + VMX_BASIC_TRUE_CTLS | + VMX_BASIC_NO_HW_ERROR_CODE_CC; + + const u64 reserved_bits = GENMASK_ULL(63, 57) | + GENMASK_ULL(47, 45) | + BIT_ULL(31); - if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved)) + u64 vmx_basic = vmcs_config.nested.basic; + + BUILD_BUG_ON(feature_bits & reserved_bits); + + /* + * Except for 32BIT_PHYS_ADDR_ONLY, which is an anti-feature bit (has + * inverted polarity), the incoming value must not set feature bits or + * reserved bits that aren't allowed/supported by KVM. Fields, i.e. + * multi-bit values, are explicitly checked below. + */ + if (!is_bitwise_subset(vmx_basic, data, feature_bits | reserved_bits)) return -EINVAL; /* * KVM does not emulate a version of VMX that constrains physical * addresses of VMX structures (e.g. VMCS) to 32-bits. */ - if (data & BIT_ULL(48)) + if (data & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EINVAL; if (vmx_basic_vmcs_revision_id(vmx_basic) != @@ -1217,36 +1331,42 @@ static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data) return 0; } -static int -vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) +static void vmx_get_control_msr(struct nested_vmx_msrs *msrs, u32 msr_index, + u32 **low, u32 **high) { - u64 supported; - u32 *lowp, *highp; - switch (msr_index) { case MSR_IA32_VMX_TRUE_PINBASED_CTLS: - lowp = &vmx->nested.msrs.pinbased_ctls_low; - highp = &vmx->nested.msrs.pinbased_ctls_high; + *low = &msrs->pinbased_ctls_low; + *high = &msrs->pinbased_ctls_high; break; case MSR_IA32_VMX_TRUE_PROCBASED_CTLS: - lowp = &vmx->nested.msrs.procbased_ctls_low; - highp = &vmx->nested.msrs.procbased_ctls_high; + *low = &msrs->procbased_ctls_low; + *high = &msrs->procbased_ctls_high; break; case MSR_IA32_VMX_TRUE_EXIT_CTLS: - lowp = &vmx->nested.msrs.exit_ctls_low; - highp = &vmx->nested.msrs.exit_ctls_high; + *low = &msrs->exit_ctls_low; + *high = &msrs->exit_ctls_high; break; case MSR_IA32_VMX_TRUE_ENTRY_CTLS: - lowp = &vmx->nested.msrs.entry_ctls_low; - highp = &vmx->nested.msrs.entry_ctls_high; + *low = &msrs->entry_ctls_low; + *high = &msrs->entry_ctls_high; break; case MSR_IA32_VMX_PROCBASED_CTLS2: - lowp = &vmx->nested.msrs.secondary_ctls_low; - highp = &vmx->nested.msrs.secondary_ctls_high; + *low = &msrs->secondary_ctls_low; + *high = &msrs->secondary_ctls_high; break; default: BUG(); } +} + +static int +vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) +{ + u32 *lowp, *highp; + u64 supported; + + vmx_get_control_msr(&vmcs_config.nested, msr_index, &lowp, &highp); supported = vmx_control_msr(*lowp, *highp); @@ -1258,6 +1378,7 @@ vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) if (!is_bitwise_subset(supported, data, GENMASK_ULL(63, 32))) return -EINVAL; + vmx_get_control_msr(&vmx->nested.msrs, msr_index, &lowp, &highp); *lowp = data; *highp = data >> 32; return 0; @@ -1265,18 +1386,29 @@ vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data) { - const u64 feature_and_reserved_bits = - /* feature */ - BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) | - BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) | - /* reserved */ - GENMASK_ULL(13, 9) | BIT_ULL(31); - u64 vmx_misc; + const u64 feature_bits = VMX_MISC_SAVE_EFER_LMA | + VMX_MISC_ACTIVITY_HLT | + VMX_MISC_ACTIVITY_SHUTDOWN | + VMX_MISC_ACTIVITY_WAIT_SIPI | + VMX_MISC_INTEL_PT | + VMX_MISC_RDMSR_IN_SMM | + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | + VMX_MISC_VMXOFF_BLOCK_SMI | + VMX_MISC_ZERO_LEN_INS; + + const u64 reserved_bits = BIT_ULL(31) | GENMASK_ULL(13, 9); - vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low, - vmx->nested.msrs.misc_high); + u64 vmx_misc = vmx_control_msr(vmcs_config.nested.misc_low, + vmcs_config.nested.misc_high); - if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits)) + BUILD_BUG_ON(feature_bits & reserved_bits); + + /* + * The incoming value must not set feature bits or reserved bits that + * aren't allowed/supported by KVM. Fields, i.e. multi-bit values, are + * explicitly checked below. + */ + if (!is_bitwise_subset(vmx_misc, data, feature_bits | reserved_bits)) return -EINVAL; if ((vmx->nested.msrs.pinbased_ctls_high & @@ -1302,10 +1434,8 @@ static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data) static int vmx_restore_vmx_ept_vpid_cap(struct vcpu_vmx *vmx, u64 data) { - u64 vmx_ept_vpid_cap; - - vmx_ept_vpid_cap = vmx_control_msr(vmx->nested.msrs.ept_caps, - vmx->nested.msrs.vpid_caps); + u64 vmx_ept_vpid_cap = vmx_control_msr(vmcs_config.nested.ept_caps, + vmcs_config.nested.vpid_caps); /* Every bit is either reserved or a feature bit. */ if (!is_bitwise_subset(vmx_ept_vpid_cap, data, -1ULL)) @@ -1316,20 +1446,21 @@ static int vmx_restore_vmx_ept_vpid_cap(struct vcpu_vmx *vmx, u64 data) return 0; } -static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) +static u64 *vmx_get_fixed0_msr(struct nested_vmx_msrs *msrs, u32 msr_index) { - u64 *msr; - switch (msr_index) { case MSR_IA32_VMX_CR0_FIXED0: - msr = &vmx->nested.msrs.cr0_fixed0; - break; + return &msrs->cr0_fixed0; case MSR_IA32_VMX_CR4_FIXED0: - msr = &vmx->nested.msrs.cr4_fixed0; - break; + return &msrs->cr4_fixed0; default: BUG(); } +} + +static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) +{ + const u64 *msr = vmx_get_fixed0_msr(&vmcs_config.nested, msr_index); /* * 1 bits (which indicates bits which "must-be-1" during VMX operation) @@ -1338,7 +1469,7 @@ static int vmx_restore_fixed0_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) if (!is_bitwise_subset(data, *msr, -1ULL)) return -EINVAL; - *msr = data; + *vmx_get_fixed0_msr(&vmx->nested.msrs, msr_index) = data; return 0; } @@ -1399,7 +1530,7 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) vmx->nested.msrs.vmcs_enum = data; return 0; case MSR_IA32_VMX_VMFUNC: - if (data & ~vmx->nested.msrs.vmfunc_controls) + if (data & ~vmcs_config.nested.vmfunc_controls) return -EINVAL; vmx->nested.msrs.vmfunc_controls = data; return 0; @@ -1560,19 +1691,32 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields) { +#ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; - struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu); /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */ vmcs12->tpr_threshold = evmcs->tpr_threshold; vmcs12->guest_rip = evmcs->guest_rip; if (unlikely(!(hv_clean_fields & + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL))) { + hv_vcpu->nested.pa_page_gpa = evmcs->partition_assist_page; + hv_vcpu->nested.vm_id = evmcs->hv_vm_id; + hv_vcpu->nested.vp_id = evmcs->hv_vp_id; + } + + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) { vmcs12->guest_rsp = evmcs->guest_rsp; vmcs12->guest_rflags = evmcs->guest_rflags; vmcs12->guest_interruptibility_info = evmcs->guest_interruptibility_info; + /* + * Not present in struct vmcs12: + * vmcs12->guest_ssp = evmcs->guest_ssp; + */ } if (unlikely(!(hv_clean_fields & @@ -1619,6 +1763,13 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields vmcs12->host_fs_selector = evmcs->host_fs_selector; vmcs12->host_gs_selector = evmcs->host_gs_selector; vmcs12->host_tr_selector = evmcs->host_tr_selector; + vmcs12->host_ia32_perf_global_ctrl = evmcs->host_ia32_perf_global_ctrl; + /* + * Not present in struct vmcs12: + * vmcs12->host_ia32_s_cet = evmcs->host_ia32_s_cet; + * vmcs12->host_ssp = evmcs->host_ssp; + * vmcs12->host_ia32_int_ssp_table_addr = evmcs->host_ia32_int_ssp_table_addr; + */ } if (unlikely(!(hv_clean_fields & @@ -1686,6 +1837,8 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields vmcs12->tsc_offset = evmcs->tsc_offset; vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr; vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap; + vmcs12->encls_exiting_bitmap = evmcs->encls_exiting_bitmap; + vmcs12->tsc_multiplier = evmcs->tsc_multiplier; } if (unlikely(!(hv_clean_fields & @@ -1733,6 +1886,13 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields vmcs12->guest_bndcfgs = evmcs->guest_bndcfgs; vmcs12->guest_activity_state = evmcs->guest_activity_state; vmcs12->guest_sysenter_cs = evmcs->guest_sysenter_cs; + vmcs12->guest_ia32_perf_global_ctrl = evmcs->guest_ia32_perf_global_ctrl; + /* + * Not present in struct vmcs12: + * vmcs12->guest_ia32_s_cet = evmcs->guest_ia32_s_cet; + * vmcs12->guest_ia32_lbr_ctl = evmcs->guest_ia32_lbr_ctl; + * vmcs12->guest_ia32_int_ssp_table_addr = evmcs->guest_ia32_int_ssp_table_addr; + */ } /* @@ -1772,12 +1932,16 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields */ return; +#else /* CONFIG_KVM_HYPERV */ + KVM_BUG_ON(1, vmx->vcpu.kvm); +#endif /* CONFIG_KVM_HYPERV */ } static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) { +#ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; - struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); /* * Should not be changed by KVM: @@ -1835,12 +1999,23 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) * evmcs->vm_exit_msr_store_count = vmcs12->vm_exit_msr_store_count; * evmcs->vm_exit_msr_load_count = vmcs12->vm_exit_msr_load_count; * evmcs->vm_entry_msr_load_count = vmcs12->vm_entry_msr_load_count; + * evmcs->guest_ia32_perf_global_ctrl = vmcs12->guest_ia32_perf_global_ctrl; + * evmcs->host_ia32_perf_global_ctrl = vmcs12->host_ia32_perf_global_ctrl; + * evmcs->encls_exiting_bitmap = vmcs12->encls_exiting_bitmap; + * evmcs->tsc_multiplier = vmcs12->tsc_multiplier; * * Not present in struct vmcs12: * evmcs->exit_io_instruction_ecx = vmcs12->exit_io_instruction_ecx; * evmcs->exit_io_instruction_esi = vmcs12->exit_io_instruction_esi; * evmcs->exit_io_instruction_edi = vmcs12->exit_io_instruction_edi; * evmcs->exit_io_instruction_eip = vmcs12->exit_io_instruction_eip; + * evmcs->host_ia32_s_cet = vmcs12->host_ia32_s_cet; + * evmcs->host_ssp = vmcs12->host_ssp; + * evmcs->host_ia32_int_ssp_table_addr = vmcs12->host_ia32_int_ssp_table_addr; + * evmcs->guest_ia32_s_cet = vmcs12->guest_ia32_s_cet; + * evmcs->guest_ia32_lbr_ctl = vmcs12->guest_ia32_lbr_ctl; + * evmcs->guest_ia32_int_ssp_table_addr = vmcs12->guest_ia32_int_ssp_table_addr; + * evmcs->guest_ssp = vmcs12->guest_ssp; */ evmcs->guest_es_selector = vmcs12->guest_es_selector; @@ -1935,6 +2110,9 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs; return; +#else /* CONFIG_KVM_HYPERV */ + KVM_BUG_ON(1, vmx->vcpu.kvm); +#endif /* CONFIG_KVM_HYPERV */ } /* @@ -1944,20 +2122,22 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( struct kvm_vcpu *vcpu, bool from_launch) { +#ifdef CONFIG_KVM_HYPERV struct vcpu_vmx *vmx = to_vmx(vcpu); bool evmcs_gpa_changed = false; u64 evmcs_gpa; - if (likely(!vmx->nested.enlightened_vmcs_enabled)) + if (likely(!guest_cpu_cap_has_evmcs(vcpu))) return EVMPTRLD_DISABLED; - if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) { + evmcs_gpa = nested_get_evmptr(vcpu); + if (!evmptr_is_valid(evmcs_gpa)) { nested_release_evmcs(vcpu); return EVMPTRLD_DISABLED; } if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { - vmx->nested.current_vmptr = -1ull; + vmx->nested.current_vmptr = INVALID_GPA; nested_release_evmcs(vcpu); @@ -2016,18 +2196,24 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( * Clean fields data can't be used on VMLAUNCH and when we switch * between different L2 guests as KVM keeps a single VMCS12 per L1. */ - if (from_launch || evmcs_gpa_changed) + if (from_launch || evmcs_gpa_changed) { vmx->nested.hv_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + vmx->nested.force_msr_bitmap_recalc = true; + } + return EVMPTRLD_SUCCEEDED; +#else + return EVMPTRLD_DISABLED; +#endif } void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) copy_vmcs12_to_enlightened(vmx); else copy_vmcs12_to_shadow(vmx); @@ -2101,6 +2287,8 @@ static u64 nested_vmx_calc_efer(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) { + struct kvm *kvm = vmx->vcpu.kvm; + /* * If vmcs02 hasn't been initialized, set the constant vmcs02 state * according to L0's settings (vmcs12 is irrelevant here). Host @@ -2111,14 +2299,8 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) return; vmx->nested.vmcs02_initialized = true; - /* - * We don't care what the EPTP value is we just need to guarantee - * it's valid so we don't get a false positive when doing early - * consistency checks. - */ - if (enable_ept && nested_early_check) - vmcs_write64(EPT_POINTER, - construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL)); + if (vmx->ve_info) + vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info)); /* All VMFUNCs are currently emulated through L0 vmexits. */ if (cpu_has_vmx_vmfunc()) @@ -2141,7 +2323,10 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) } if (cpu_has_vmx_encls_vmexit()) - vmcs_write64(ENCLS_EXITING_BITMAP, -1ull); + vmcs_write64(ENCLS_EXITING_BITMAP, INVALID_GPA); + + if (kvm_notify_vmexit_enabled(kvm)) + vmcs_write32(NOTIFY_WINDOW, kvm->arch.notify_window); /* * Set the MSR load/store lists to match L0's settings. Only the @@ -2160,8 +2345,19 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, { prepare_vmcs02_constant_state(vmx); - vmcs_write64(VMCS_LINK_POINTER, -1ull); + vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); + /* + * If VPID is disabled, then guest TLB accesses use VPID=0, i.e. the + * same VPID as the host. Emulate this behavior by using vpid01 for L2 + * if VPID is disabled in vmcs12. Note, if VPID is disabled, VM-Enter + * and VM-Exit are architecturally required to flush VPID=0, but *only* + * VPID=0. I.e. using vpid02 would be ok (so long as KVM emulates the + * required flushes), but doing so would cause KVM to over-flush. E.g. + * if L1 runs L2 X with VPID12=1, then runs L2 Y with VPID12 disabled, + * and then runs L2 X again, then KVM can and should retain TLB entries + * for VPID12=1. + */ if (enable_vpid) { if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); @@ -2170,26 +2366,28 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, } } -static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) +static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs01, + struct vmcs12 *vmcs12) { u32 exec_control; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); - if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) prepare_vmcs02_early_rare(vmx, vmcs12); /* * PIN CONTROLS */ - exec_control = vmx_pin_based_exec_ctrl(vmx); + exec_control = __pin_controls_get(vmcs01); exec_control |= (vmcs12->pin_based_vm_exec_control & ~PIN_BASED_VMX_PREEMPTION_TIMER); /* Posted interrupts setting is only taken from vmcs12. */ + vmx->nested.pi_pending = false; if (nested_cpu_has_posted_intr(vmcs12)) { vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; - vmx->nested.pi_pending = false; } else { + vmx->nested.posted_intr_nv = -1; exec_control &= ~PIN_BASED_POSTED_INTR; } pin_controls_set(vmx, exec_control); @@ -2197,7 +2395,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) /* * EXEC CONTROLS */ - exec_control = vmx_exec_control(vmx); /* L0's desires */ + exec_control = __exec_controls_get(vmcs01); /* L0's desires */ exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING; exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING; exec_control &= ~CPU_BASED_TPR_SHADOW; @@ -2234,18 +2432,20 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * SECONDARY EXEC CONTROLS */ if (cpu_has_secondary_exec_ctrls()) { - exec_control = vmx->secondary_exec_control; + exec_control = __secondary_exec_controls_get(vmcs01); /* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_ENABLE_RDTSCP | - SECONDARY_EXEC_XSAVES | + SECONDARY_EXEC_ENABLE_XSAVES | SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_TSC_SCALING); + SECONDARY_EXEC_DESC); + if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -2260,8 +2460,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * Preset *DT exiting when emulating UMIP, so that vmx_set_cr4() * will not have to rewrite the controls just for this bit. */ - if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated() && - (vmcs12->guest_cr4 & X86_CR4_UMIP)) + if (vmx_umip_emulated() && (vmcs12->guest_cr4 & X86_CR4_UMIP)) exec_control |= SECONDARY_EXEC_DESC; if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) @@ -2284,13 +2483,19 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate * on the related bits (if supported by the CPU) in the hope that * we can avoid VMWrites during vmx_set_efer(). + * + * Similarly, take vmcs01's PERF_GLOBAL_CTRL in the hope that if KVM is + * loading PERF_GLOBAL_CTRL via the VMCS for L1, then KVM will want to + * do the same for L2. */ - exec_control = (vmcs12->vm_entry_controls | vmx_vmentry_ctrl()) & - ~VM_ENTRY_IA32E_MODE & ~VM_ENTRY_LOAD_IA32_EFER; + exec_control = __vm_entry_controls_get(vmcs01); + exec_control |= (vmcs12->vm_entry_controls & + ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL); + exec_control &= ~(VM_ENTRY_IA32E_MODE | VM_ENTRY_LOAD_IA32_EFER); if (cpu_has_load_ia32_efer()) { if (guest_efer & EFER_LMA) exec_control |= VM_ENTRY_IA32E_MODE; - if (guest_efer != host_efer) + if (guest_efer != kvm_host.efer) exec_control |= VM_ENTRY_LOAD_IA32_EFER; } vm_entry_controls_set(vmx, exec_control); @@ -2302,9 +2507,11 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER * bits may be modified by vmx_set_efer() in prepare_vmcs02(). */ - exec_control = vmx_vmexit_ctrl(); - if (cpu_has_load_ia32_efer() && guest_efer != host_efer) + exec_control = __vm_exit_controls_get(vmcs01); + if (cpu_has_load_ia32_efer() && guest_efer != kvm_host.efer) exec_control |= VM_EXIT_LOAD_IA32_EFER; + else + exec_control &= ~VM_EXIT_LOAD_IA32_EFER; vm_exit_controls_set(vmx, exec_control); /* @@ -2326,12 +2533,39 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) } } +static void vmcs_read_cet_state(struct kvm_vcpu *vcpu, u64 *s_cet, + u64 *ssp, u64 *ssp_tbl) +{ + if (guest_cpu_cap_has(vcpu, X86_FEATURE_IBT) || + guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) + *s_cet = vmcs_readl(GUEST_S_CET); + + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) { + *ssp = vmcs_readl(GUEST_SSP); + *ssp_tbl = vmcs_readl(GUEST_INTR_SSP_TABLE); + } +} + +static void vmcs_write_cet_state(struct kvm_vcpu *vcpu, u64 s_cet, + u64 ssp, u64 ssp_tbl) +{ + if (guest_cpu_cap_has(vcpu, X86_FEATURE_IBT) || + guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) + vmcs_writel(GUEST_S_CET, s_cet); + + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) { + vmcs_writel(GUEST_SSP, ssp); + vmcs_writel(GUEST_INTR_SSP_TABLE, ssp_tbl); + } +} + static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { - struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *hv_evmcs = nested_vmx_evmcs(vmx); if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) { + vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector); @@ -2369,7 +2603,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); - vmx->segment_cache.bitmask = 0; + vmx_segment_cache_clear(vmx); } if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & @@ -2441,6 +2675,10 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE) + vmcs_write_cet_state(&vmx->vcpu, vmcs12->guest_s_cet, + vmcs12->guest_ssp, vmcs12->guest_ssp_tbl); + set_cr4_guest_host_mask(vmx); } @@ -2460,28 +2698,36 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, enum vm_entry_failure_code *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); bool load_guest_pdptrs_vmcs12 = false; - if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) { prepare_vmcs02_rare(vmx, vmcs12); vmx->nested.dirty_vmcs12 = false; - load_guest_pdptrs_vmcs12 = !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) || - !(vmx->nested.hv_evmcs->hv_clean_fields & - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); + load_guest_pdptrs_vmcs12 = !nested_vmx_is_evmptr12_valid(vmx) || + !(evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); } if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl); + vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl & + vmx_get_supported_debugctl(vcpu, false)); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl); + vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl); } + + if (!vmx->nested.nested_run_pending || + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE)) + vmcs_write_cet_state(vcpu, vmx->nested.pre_vmenter_s_cet, + vmx->nested.pre_vmenter_ssp, + vmx->nested.pre_vmenter_ssp_tbl); + if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) - vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs); + vmcs_write64(GUEST_BNDCFGS, vmx->nested.pre_vmenter_bndcfgs); vmx_set_rflags(vcpu, vmcs12->guest_rflags); /* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the @@ -2497,7 +2743,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat); vcpu->arch.pat = vmcs12->guest_ia32_pat; } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { - vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); + vmcs_write64(GUEST_IA32_PAT, vcpu->arch.pat); } vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( @@ -2510,7 +2756,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmx_get_l2_tsc_multiplier(vcpu)); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); - if (kvm_has_tsc_control) + if (kvm_caps.has_tsc_control) vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); nested_vmx_transition_tlb_flush(vcpu, vmcs12, true); @@ -2519,12 +2765,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, nested_ept_init_mmu_context(vcpu); /* - * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those - * bits which we consider mandatory enabled. - * The CR0_READ_SHADOW is what L2 should have expected to read given - * the specifications by L1; It's not enough to take - * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we - * have more bits than L1 expected. + * Override the CR0/CR4 read shadows after setting the effective guest + * CR0/CR4. The common helpers also set the shadows, but they don't + * account for vmcs12's cr0/4_guest_host_mask. */ vmx_set_cr0(vcpu, vmcs12->guest_cr0); vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12)); @@ -2540,8 +2783,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * Guest state is invalid and unrestricted guest is disabled, * which means L1 attempted VMEntry to L2 with invalid state. * Fail the VMEntry. + * + * However when force loading the guest state (SMM exit or + * loading nested state after migration, it is possible to + * have invalid guest state now, which will be later fixed by + * restoring L2 register state */ - if (CC(!vmx_guest_state_valid(vcpu))) { + if (CC(from_vmentry && !vmx_guest_state_valid(vcpu))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -2570,13 +2818,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); } - if (!enable_ept) - vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; - if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && - WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, - vmcs12->guest_ia32_perf_global_ctrl))) + kvm_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu)) && + WARN_ON_ONCE(__kvm_emulate_msr_write(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, + vmcs12->guest_ia32_perf_global_ctrl))) { + *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; + } kvm_rsp_write(vcpu, vmcs12->guest_rsp); kvm_rip_write(vcpu, vmcs12->guest_rip); @@ -2587,9 +2835,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * bits when it changes a field in eVMCS. Mark all fields as clean * here. */ - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) - vmx->nested.hv_evmcs->hv_clean_fields |= - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + if (nested_vmx_is_evmptr12_valid(vmx)) + evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; return 0; } @@ -2640,7 +2887,7 @@ static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp) } /* Reserved bits should not be set */ - if (CC(kvm_vcpu_is_illegal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f))) + if (CC(!kvm_vcpu_is_legal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f))) return false; /* AD, if set, should be supported */ @@ -2708,6 +2955,10 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, } } + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING) && + CC(!vmcs12->tsc_multiplier)) + return -EINVAL; + return 0; } @@ -2752,7 +3003,6 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, u8 vector = intr_info & INTR_INFO_VECTOR_MASK; u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK; bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK; - bool should_have_error_code; bool urg = nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST); bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE; @@ -2769,12 +3019,19 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, CC(intr_type == INTR_TYPE_OTHER_EVENT && vector != 0)) return -EINVAL; - /* VM-entry interruption-info field: deliver error code */ - should_have_error_code = - intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode && - x86_exception_has_error_code(vector); - if (CC(has_error_code != should_have_error_code)) - return -EINVAL; + /* + * Cannot deliver error code in real mode or if the interrupt + * type is not hardware exception. For other cases, do the + * consistency check only if the vCPU doesn't enumerate + * VMX_BASIC_NO_HW_ERROR_CODE_CC. + */ + if (!prot_mode || intr_type != INTR_TYPE_HARD_EXCEPTION) { + if (CC(has_error_code)) + return -EINVAL; + } else if (!nested_cpu_has_no_hw_errcode_cc(vcpu)) { + if (CC(has_error_code != x86_exception_has_error_code(vector))) + return -EINVAL; + } /* VM-entry exception error code */ if (CC(has_error_code && @@ -2790,7 +3047,7 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, case INTR_TYPE_SOFT_EXCEPTION: case INTR_TYPE_SOFT_INTR: case INTR_TYPE_PRIV_SW_EXCEPTION: - if (CC(vmcs12->vm_entry_instruction_len > 15) || + if (CC(vmcs12->vm_entry_instruction_len > X86_MAX_INSTRUCTION_LENGTH) || CC(vmcs12->vm_entry_instruction_len == 0 && CC(!nested_cpu_has_zero_length_injection(vcpu)))) return -EINVAL; @@ -2811,8 +3068,74 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, nested_check_vm_entry_controls(vcpu, vmcs12)) return -EINVAL; - if (to_vmx(vcpu)->nested.enlightened_vmcs_enabled) +#ifdef CONFIG_KVM_HYPERV + if (guest_cpu_cap_has_evmcs(vcpu)) return nested_evmcs_check_controls(vmcs12); +#endif + + return 0; +} + +static int nested_vmx_check_controls_late(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + void *vapic = to_vmx(vcpu)->nested.virtual_apic_map.hva; + u32 vtpr = vapic ? (*(u32 *)(vapic + APIC_TASKPRI)) >> 4 : 0; + + /* + * Don't bother with the consistency checks if KVM isn't configured to + * WARN on missed consistency checks, as KVM needs to rely on hardware + * to fully detect an illegal vTPR vs. TRP Threshold combination due to + * the vTPR being writable by L1 at all times (it's an in-memory value, + * not a VMCS field). I.e. even if the check passes now, it might fail + * at the actual VM-Enter. + * + * Keying off the module param also allows treating an invalid vAPIC + * mapping as a consistency check failure without increasing the risk + * of breaking a "real" VM. + */ + if (!warn_on_missed_cc) + return 0; + + if ((exec_controls_get(to_vmx(vcpu)) & CPU_BASED_TPR_SHADOW) && + nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW) && + !nested_cpu_has_vid(vmcs12) && + !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) && + (CC(!vapic) || + CC((vmcs12->tpr_threshold & GENMASK(3, 0)) > (vtpr & GENMASK(3, 0))))) + return -EINVAL; + + return 0; +} + +static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ +#ifdef CONFIG_X86_64 + if (CC(!!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) != + !!(vcpu->arch.efer & EFER_LMA))) + return -EINVAL; +#endif + return 0; +} + +static bool is_l1_noncanonical_address_on_vmexit(u64 la, struct vmcs12 *vmcs12) +{ + /* + * Check that the given linear address is canonical after a VM exit + * from L2, based on HOST_CR4.LA57 value that will be loaded for L1. + */ + u8 l1_address_bits_on_exit = (vmcs12->host_cr4 & X86_CR4_LA57) ? 57 : 48; + + return !__is_canonical_address(la, l1_address_bits_on_exit); +} + +static int nested_vmx_check_cet_state_common(struct kvm_vcpu *vcpu, u64 s_cet, + u64 ssp, u64 ssp_tbl) +{ + if (CC(!kvm_is_valid_u_s_cet(vcpu, s_cet)) || CC(!IS_ALIGNED(ssp, 4)) || + CC(is_noncanonical_msr_address(ssp_tbl, vcpu))) + return -EINVAL; return 0; } @@ -2820,15 +3143,18 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - bool ia32e; + bool ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE); if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) || CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) || - CC(kvm_vcpu_is_illegal_gpa(vcpu, vmcs12->host_cr3))) + CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3))) return -EINVAL; - if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu))) + if (CC(vmcs12->host_cr4 & X86_CR4_CET && !(vmcs12->host_cr0 & X86_CR0_WP))) + return -EINVAL; + + if (CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || + CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_eip, vcpu))) return -EINVAL; if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) && @@ -2840,19 +3166,11 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, vmcs12->host_ia32_perf_global_ctrl))) return -EINVAL; -#ifdef CONFIG_X86_64 - ia32e = !!(vcpu->arch.efer & EFER_LMA); -#else - ia32e = false; -#endif - if (ia32e) { - if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) || - CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) + if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) return -EINVAL; } else { - if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) || - CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) || + if (CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) || CC(vmcs12->host_cr4 & X86_CR4_PCIDE) || CC((vmcs12->host_rip) >> 32)) return -EINVAL; @@ -2870,12 +3188,12 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, CC(vmcs12->host_ss_selector == 0 && !ia32e)) return -EINVAL; - if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_idtr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_rip, vcpu))) + if (CC(is_noncanonical_base_address(vmcs12->host_fs_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_gs_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_gdtr_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_idtr_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_tr_base, vcpu)) || + CC(is_l1_noncanonical_address_on_vmexit(vmcs12->host_rip, vmcs12))) return -EINVAL; /* @@ -2891,33 +3209,58 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, return -EINVAL; } + if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_CET_STATE) { + if (nested_vmx_check_cet_state_common(vcpu, vmcs12->host_s_cet, + vmcs12->host_ssp, + vmcs12->host_ssp_tbl)) + return -EINVAL; + + /* + * IA32_S_CET and SSP must be canonical if the host will + * enter 64-bit mode after VM-exit; otherwise, higher + * 32-bits must be all 0s. + */ + if (ia32e) { + if (CC(is_noncanonical_msr_address(vmcs12->host_s_cet, vcpu)) || + CC(is_noncanonical_msr_address(vmcs12->host_ssp, vcpu))) + return -EINVAL; + } else { + if (CC(vmcs12->host_s_cet >> 32) || CC(vmcs12->host_ssp >> 32)) + return -EINVAL; + } + } + return 0; } static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - int r = 0; - struct vmcs12 *shadow; - struct kvm_host_map map; + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; + struct vmcs_hdr hdr; - if (vmcs12->vmcs_link_pointer == -1ull) + if (vmcs12->vmcs_link_pointer == INVALID_GPA) return 0; if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer))) return -EINVAL; - if (CC(kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))) - return -EINVAL; + if (ghc->gpa != vmcs12->vmcs_link_pointer && + CC(kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, + vmcs12->vmcs_link_pointer, VMCS12_SIZE))) + return -EINVAL; - shadow = map.hva; + if (CC(kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr, + offsetof(struct vmcs12, hdr), + sizeof(hdr)))) + return -EINVAL; - if (CC(shadow->hdr.revision_id != VMCS12_REVISION) || - CC(shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12))) - r = -EINVAL; + if (CC(hdr.revision_id != VMCS12_REVISION) || + CC(hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12))) + return -EINVAL; - kvm_vcpu_unmap(vcpu, &map, false); - return r; + return 0; } /* @@ -2937,7 +3280,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, enum vm_entry_failure_code *entry_failure_code) { - bool ia32e; + bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE); *entry_failure_code = ENTRY_FAIL_DEFAULT; @@ -2945,8 +3288,12 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4))) return -EINVAL; + if (CC(vmcs12->guest_cr4 & X86_CR4_CET && !(vmcs12->guest_cr0 & X86_CR0_WP))) + return -EINVAL; + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && - CC(!kvm_dr7_valid(vmcs12->guest_dr7))) + (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || + CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false)))) return -EINVAL; if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) && @@ -2963,6 +3310,13 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, vmcs12->guest_ia32_perf_global_ctrl))) return -EINVAL; + if (CC((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG)) + return -EINVAL; + + if (CC(ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) || + CC(ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG))) + return -EINVAL; + /* * If the load IA32_EFER VM-entry control is 1, the following checks * are performed on the field for the IA32_EFER MSR: @@ -2974,7 +3328,6 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, */ if (to_vmx(vcpu)->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) { - ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0; if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) || CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) || CC(((vmcs12->guest_cr0 & X86_CR0_PG) && @@ -2983,94 +3336,34 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) && - (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) || + (CC(is_noncanonical_msr_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) || CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))) return -EINVAL; - if (nested_check_guest_non_reg_state(vmcs12)) - return -EINVAL; - - return 0; -} - -static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; - bool vm_fail; - - if (!nested_early_check) - return 0; - - if (vmx->msr_autoload.host.nr) - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); - if (vmx->msr_autoload.guest.nr) - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); - - preempt_disable(); - - vmx_prepare_switch_to_guest(vcpu); - - /* - * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS, - * which is reserved to '1' by hardware. GUEST_RFLAGS is guaranteed to - * be written (by prepare_vmcs02()) before the "real" VMEnter, i.e. - * there is no need to preserve other bits or save/restore the field. - */ - vmcs_writel(GUEST_RFLAGS, 0); - - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } - - cr4 = cr4_read_shadow(); - if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { - vmcs_writel(HOST_CR4, cr4); - vmx->loaded_vmcs->host_state.cr4 = cr4; - } - - vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, - vmx->loaded_vmcs->launched); - - if (vmx->msr_autoload.host.nr) - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); - if (vmx->msr_autoload.guest.nr) - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); - - if (vm_fail) { - u32 error = vmcs_read32(VM_INSTRUCTION_ERROR); - - preempt_enable(); + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE) { + if (nested_vmx_check_cet_state_common(vcpu, vmcs12->guest_s_cet, + vmcs12->guest_ssp, + vmcs12->guest_ssp_tbl)) + return -EINVAL; - trace_kvm_nested_vmenter_failed( - "early hardware check VM-instruction error: ", error); - WARN_ON_ONCE(error != VMXERR_ENTRY_INVALID_CONTROL_FIELD); - return 1; + /* + * Guest SSP must have 63:N bits identical, rather than + * be canonical (i.e., 63:N-1 bits identical), where N is + * the CPU's maximum linear-address width. Similar to + * is_noncanonical_msr_address(), use the host's + * linear-address width. + */ + if (CC(!__is_canonical_address(vmcs12->guest_ssp, max_host_virt_addr_bits() + 1))) + return -EINVAL; } - /* - * VMExit clears RFLAGS.IF and DR7, even on a consistency check. - */ - if (hw_breakpoint_active()) - set_debugreg(__this_cpu_read(cpu_dr7), 7); - local_irq_enable(); - preempt_enable(); - - /* - * A non-failing VMEntry means we somehow entered guest mode with - * an illegal RIP, and that's just the tip of the iceberg. There - * is no telling what memory has been modified or what state has - * been exposed to unknown code. Hitting this all but guarantees - * a (very critical) hardware issue. - */ - WARN_ON(!(vmcs_read32(VM_EXIT_REASON) & - VMX_EXIT_REASONS_FAILED_VMENTRY)); + if (nested_check_guest_non_reg_state(vmcs12)) + return -EINVAL; return 0; } +#ifdef CONFIG_KVM_HYPERV static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3080,7 +3373,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) * L2 was running), map it here to make sure vmcs12 changes are * properly reflected. */ - if (vmx->nested.enlightened_vmcs_enabled && + if (guest_cpu_cap_has_evmcs(vcpu) && vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) { enum nested_evmptrld_status evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, false); @@ -3098,14 +3391,13 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) return true; } +#endif static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_host_map *map; - struct page *page; - u64 hpa; if (!vcpu->arch.pdptrs_from_userspace && !nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { @@ -3114,29 +3406,18 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) * the guest CR3 might be restored prior to setting the nested * state which can lead to a load of wrong PDPTRs. */ - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) return false; } if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - /* - * Translate L1 physical address to host physical - * address for vmcs02. Keep the page pinned, so this - * physical address remains valid. We keep a reference - * to it so we can release it later. - */ - if (vmx->nested.apic_access_page) { /* shouldn't happen */ - kvm_release_page_clean(vmx->nested.apic_access_page); - vmx->nested.apic_access_page = NULL; - } - page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr); - if (!is_error_page(page)) { - vmx->nested.apic_access_page = page; - hpa = page_to_phys(vmx->nested.apic_access_page); - vmcs_write64(APIC_ACCESS_ADDR, hpa); + map = &vmx->nested.apic_access_page_map; + + if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->apic_access_addr), map)) { + vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(map->pfn)); } else { - pr_debug_ratelimited("%s: no backing 'struct page' for APIC-access address in vmcs12\n", + pr_debug_ratelimited("%s: no backing for APIC-access address in vmcs12\n", __func__); vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = @@ -3168,7 +3449,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR to * force VM-Entry to fail. */ - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull); + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, INVALID_GPA); } } @@ -3202,6 +3483,13 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_KVM_HYPERV + /* + * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy + * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory + * to make nested_evmcs_l2_tlb_flush_enabled() work correctly post + * migration. + */ if (!nested_get_evmcs_page(vcpu)) { pr_debug_ratelimited("%s: enlightened vmptrld failed\n", __func__); @@ -3212,6 +3500,7 @@ static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) return false; } +#endif if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) return false; @@ -3239,7 +3528,7 @@ static int nested_vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) if (!nested_cpu_has_pml(vmcs12)) return 0; - if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) { + if (vmcs12->guest_pml_index >= PML_LOG_NR_ENTRIES) { vmx->nested.pml_full = true; return 1; } @@ -3278,14 +3567,6 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) return 1; } -static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu) -{ - u8 rvi = vmx_get_rvi(); - u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI); - - return ((rvi & 0xf0) > (vppr & 0xf0)); -} - static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12); @@ -3305,49 +3586,56 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); enum vm_entry_failure_code entry_failure_code; - bool evaluate_pending_interrupts; union vmx_exit_reason exit_reason = { .basic = EXIT_REASON_INVALID_STATE, .failed_vmentry = 1, }; u32 failed_index; - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); - - evaluate_pending_interrupts = exec_controls_get(vmx) & - (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); - if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) - evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); - - if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) - vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + trace_kvm_nested_vmenter(kvm_rip_read(vcpu), + vmx->nested.current_vmptr, + vmcs12->guest_rip, + vmcs12->guest_intr_status, + vmcs12->vm_entry_intr_info_field, + vmcs12->secondary_vm_exec_control & SECONDARY_EXEC_ENABLE_EPT, + vmcs12->ept_pointer, + vmcs12->guest_cr3, + KVM_ISA_VMX); + + kvm_service_local_tlb_flush_requests(vcpu); + + if (!vmx->nested.nested_run_pending || + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) + vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read(); if (kvm_mpx_supported() && - !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) - vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); + (!vmx->nested.nested_run_pending || + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) + vmx->nested.pre_vmenter_bndcfgs = vmcs_read64(GUEST_BNDCFGS); + + if (!vmx->nested.nested_run_pending || + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_CET_STATE)) + vmcs_read_cet_state(vcpu, &vmx->nested.pre_vmenter_s_cet, + &vmx->nested.pre_vmenter_ssp, + &vmx->nested.pre_vmenter_ssp_tbl); /* - * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and* - * nested early checks are disabled. In the event of a "late" VM-Fail, - * i.e. a VM-Fail detected by hardware but not KVM, KVM must unwind its - * software model to the pre-VMEntry host state. When EPT is disabled, - * GUEST_CR3 holds KVM's shadow CR3, not L1's "real" CR3, which causes - * nested_vmx_restore_host_state() to corrupt vcpu->arch.cr3. Stuffing - * vmcs01.GUEST_CR3 results in the unwind naturally setting arch.cr3 to - * the correct value. Smashing vmcs01.GUEST_CR3 is safe because nested - * VM-Exits, and the unwind, reset KVM's MMU, i.e. vmcs01.GUEST_CR3 is - * guaranteed to be overwritten with a shadow CR3 prior to re-entering - * L1. Don't stuff vmcs01.GUEST_CR3 when using nested early checks as - * KVM modifies vcpu->arch.cr3 if and only if the early hardware checks - * pass, and early VM-Fails do not reset KVM's MMU, i.e. the VM-Fail - * path would need to manually save/restore vmcs01.GUEST_CR3. + * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled. In the + * event of a "late" VM-Fail, i.e. a VM-Fail detected by hardware but + * not KVM, KVM must unwind its software model to the pre-VM-Entry host + * state. When EPT is disabled, GUEST_CR3 holds KVM's shadow CR3, not + * L1's "real" CR3, which causes nested_vmx_restore_host_state() to + * corrupt vcpu->arch.cr3. Stuffing vmcs01.GUEST_CR3 results in the + * unwind naturally setting arch.cr3 to the correct value. Smashing + * vmcs01.GUEST_CR3 is safe because nested VM-Exits, and the unwind, + * reset KVM's MMU, i.e. vmcs01.GUEST_CR3 is guaranteed to be + * overwritten with a shadow CR3 prior to re-entering L1. */ - if (!enable_ept && !nested_early_check) + if (!enable_ept) vmcs_writel(GUEST_CR3, vcpu->arch.cr3); vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); - prepare_vmcs02_early(vmx, vmcs12); + prepare_vmcs02_early(vmx, &vmx->vmcs01, vmcs12); if (from_vmentry) { if (unlikely(!nested_get_vmcs12_pages(vcpu))) { @@ -3355,7 +3643,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, return NVMX_VMENTRY_KVM_INTERNAL_ERROR; } - if (nested_vmx_check_vmentry_hw(vcpu)) { + if (nested_vmx_check_controls_late(vcpu, vmcs12)) { vmx_switch_vmcs(vcpu, &vmx->vmcs01); return NVMX_VMENTRY_VMFAIL; } @@ -3397,20 +3685,16 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, } /* - * If L1 had a pending IRQ/NMI until it executed - * VMLAUNCH/VMRESUME which wasn't delivered because it was - * disallowed (e.g. interrupts disabled), L0 needs to - * evaluate if this pending event should cause an exit from L2 - * to L1 or delivered directly to L2 (e.g. In case L1 don't - * intercept EXTERNAL_INTERRUPT). - * - * Usually this would be handled by the processor noticing an - * IRQ/NMI window request, or checking RVI during evaluation of - * pending virtual interrupts. However, this setting was done - * on VMCS01 and now VMCS02 is active instead. Thus, we force L0 - * to perform pending event evaluation by requesting a KVM_REQ_EVENT. + * Re-evaluate pending events if L1 had a pending IRQ/NMI/INIT/SIPI + * when it executed VMLAUNCH/VMRESUME, as entering non-root mode can + * effectively unblock various events, e.g. INIT/SIPI cause VM-Exit + * unconditionally. Take care to pull data from vmcs01 as appropriate, + * e.g. when checking for interrupt windows, as vmcs02 is now loaded. */ - if (unlikely(evaluate_pending_interrupts)) + if ((__exec_controls_get(&vmx->vmcs01) & (CPU_BASED_INTR_WINDOW_EXITING | + CPU_BASED_NMI_WINDOW_EXITING)) || + kvm_apic_has_pending_init_or_sipi(vcpu) || + kvm_apic_has_interrupt(vcpu)) kvm_make_request(KVM_REQ_EVENT, vcpu); /* @@ -3450,7 +3734,7 @@ vmentry_fail_vmexit: load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason.full; - if (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx)) vmx->nested.need_vmcs12_to_shadow_sync = true; return NVMX_VMENTRY_VMEXIT; } @@ -3474,12 +3758,15 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (evmptrld_status == EVMPTRLD_ERROR) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; - } else if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) { - return nested_vmx_failInvalid(vcpu); } - if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) && - vmx->nested.current_vmptr == -1ull)) + kvm_pmu_branch_retired(vcpu); + + if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) + return nested_vmx_failInvalid(vcpu); + + if (CC(!nested_vmx_is_evmptr12_valid(vmx) && + vmx->nested.current_vmptr == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); vmcs12 = get_vmcs12(vcpu); @@ -3493,8 +3780,10 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (CC(vmcs12->hdr.shadow_vmcs)) return nested_vmx_failInvalid(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { - copy_enlightened_to_vmcs12(vmx, vmx->nested.hv_evmcs->hv_clean_fields); + if (nested_vmx_is_evmptr12_valid(vmx)) { + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); + + copy_enlightened_to_vmcs12(vmx, evmcs->hv_clean_fields); /* Enlightened VMCS doesn't have launch state */ vmcs12->launch_state = !launch; } else if (enable_shadow_vmcs) { @@ -3522,6 +3811,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (nested_vmx_check_controls(vcpu, vmcs12)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); + if (nested_vmx_check_address_space_size(vcpu, vmcs12)) + return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); + if (nested_vmx_check_host_state(vcpu, vmcs12)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); @@ -3535,16 +3827,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (unlikely(status != NVMX_VMENTRY_SUCCESS)) goto vmentry_failed; - /* Emulate processing of posted interrupts on VM-Enter. */ - if (nested_cpu_has_posted_intr(vmcs12) && - kvm_apic_has_interrupt(vcpu) == vmx->nested.posted_intr_nv) { - vmx->nested.pi_pending = true; - kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_apic_clear_irr(vcpu, vmx->nested.posted_intr_nv); - } - /* Hide L1D cache contents from the nested guest. */ - vmx->vcpu.arch.l1tf_flush_l1d = true; + kvm_request_l1tf_flush_l1d(); /* * Must happen outside of nested_vmx_enter_non_root_mode() as it will @@ -3570,12 +3854,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) && (vmcs12->guest_rflags & X86_EFLAGS_IF))) { vmx->nested.nested_run_pending = 0; - return kvm_vcpu_halt(vcpu); + return kvm_emulate_halt_noskip(vcpu); } break; case GUEST_ACTIVITY_WAIT_SIPI: vmx->nested.nested_run_pending = 0; - vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; + kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED); break; default: break; @@ -3631,13 +3915,35 @@ vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) } static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) + struct vmcs12 *vmcs12, + u32 vm_exit_reason, u32 exit_intr_info) { u32 idt_vectoring; unsigned int nr; - if (vcpu->arch.exception.injected) { - nr = vcpu->arch.exception.nr; + /* + * Per the SDM, VM-Exits due to double and triple faults are never + * considered to occur during event delivery, even if the double/triple + * fault is the result of an escalating vectoring issue. + * + * Note, the SDM qualifies the double fault behavior with "The original + * event results in a double-fault exception". It's unclear why the + * qualification exists since exits due to double fault can occur only + * while vectoring a different exception (injected events are never + * subject to interception), i.e. there's _always_ an original event. + * + * The SDM also uses NMI as a confusing example for the "original event + * causes the VM exit directly" clause. NMI isn't special in any way, + * the same rule applies to all events that cause an exit directly. + * NMI is an odd choice for the example because NMIs can only occur on + * instruction boundaries, i.e. they _can't_ occur during vectoring. + */ + if ((u16)vm_exit_reason == EXIT_REASON_TRIPLE_FAULT || + ((u16)vm_exit_reason == EXIT_REASON_EXCEPTION_NMI && + is_double_fault(exit_intr_info))) { + vmcs12->idt_vectoring_info_field = 0; + } else if (vcpu->arch.exception.injected) { + nr = vcpu->arch.exception.vector; idt_vectoring = nr | VECTORING_INFO_VALID_MASK; if (kvm_exception_is_soft(nr)) { @@ -3669,6 +3975,8 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, idt_vectoring |= INTR_TYPE_EXT_INTR; vmcs12->idt_vectoring_info_field = idt_vectoring; + } else { + vmcs12->idt_vectoring_info_field = 0; } } @@ -3712,8 +4020,8 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) if (!pi_test_and_clear_on(vmx->nested.pi_desc)) return 0; - max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); - if (max_irr != 256) { + max_irr = pi_find_highest_vector(vmx->nested.pi_desc); + if (max_irr > 0) { vapic_page = vmx->nested.virtual_apic_map.hva; if (!vapic_page) goto mmio_needed; @@ -3736,19 +4044,45 @@ mmio_needed: return -ENXIO; } -static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, - unsigned long exit_qual) +static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu) { + struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; + u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - unsigned int nr = vcpu->arch.exception.nr; - u32 intr_info = nr | INTR_INFO_VALID_MASK; + unsigned long exit_qual; + + if (ex->has_payload) { + exit_qual = ex->payload; + } else if (ex->vector == PF_VECTOR) { + exit_qual = vcpu->arch.cr2; + } else if (ex->vector == DB_VECTOR) { + exit_qual = vcpu->arch.dr6; + exit_qual &= ~DR6_BT; + exit_qual ^= DR6_ACTIVE_LOW; + } else { + exit_qual = 0; + } - if (vcpu->arch.exception.has_error_code) { - vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code; + /* + * Unlike AMD's Paged Real Mode, which reports an error code on #PF + * VM-Exits even if the CPU is in Real Mode, Intel VMX never sets the + * "has error code" flags on VM-Exit if the CPU is in Real Mode. + */ + if (ex->has_error_code && is_protmode(vcpu)) { + /* + * Intel CPUs do not generate error codes with bits 31:16 set, + * and more importantly VMX disallows setting bits 31:16 in the + * injected error code for VM-Entry. Drop the bits to mimic + * hardware and avoid inducing failure on nested VM-Entry if L1 + * chooses to inject the exception back to L2. AMD CPUs _do_ + * generate "full" 32-bit error codes, so KVM allows userspace + * to inject exception error codes with bits 31:16 set. + */ + vmcs12->vm_exit_intr_error_code = (u16)ex->error_code; intr_info |= INTR_INFO_DELIVER_CODE_MASK; } - if (kvm_exception_is_soft(nr)) + if (kvm_exception_is_soft(ex->vector)) intr_info |= INTR_TYPE_SOFT_EXCEPTION; else intr_info |= INTR_TYPE_HARD_EXCEPTION; @@ -3761,16 +4095,39 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, } /* - * Returns true if a debug trap is pending delivery. + * Returns true if a debug trap is (likely) pending delivery. Infer the class + * of a #DB (trap-like vs. fault-like) from the exception payload (to-be-DR6). + * Using the payload is flawed because code breakpoints (fault-like) and data + * breakpoints (trap-like) set the same bits in DR6 (breakpoint detected), i.e. + * this will return false positives if a to-be-injected code breakpoint #DB is + * pending (from KVM's perspective, but not "pending" across an instruction + * boundary). ICEBP, a.k.a. INT1, is also not reflected here even though it + * too is trap-like. * - * In KVM, debug traps bear an exception payload. As such, the class of a #DB - * exception may be inferred from the presence of an exception payload. + * KVM "works" despite these flaws as ICEBP isn't currently supported by the + * emulator, Monitor Trap Flag is not marked pending on intercepted #DBs (the + * #DB has already happened), and MTF isn't marked pending on code breakpoints + * from the emulator (because such #DBs are fault-like and thus don't trigger + * actions that fire on instruction retire). */ -static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu) +static unsigned long vmx_get_pending_dbg_trap(struct kvm_queued_exception *ex) { - return vcpu->arch.exception.pending && - vcpu->arch.exception.nr == DB_VECTOR && - vcpu->arch.exception.payload; + if (!ex->pending || ex->vector != DB_VECTOR) + return 0; + + /* General Detect #DBs are always fault-like. */ + return ex->payload & ~DR6_BD; +} + +/* + * Returns true if there's a pending #DB exception that is lower priority than + * a pending Monitor Trap Flag VM-Exit. TSS T-flag #DBs are not emulated by + * KVM, but could theoretically be injected by userspace. Note, this code is + * imperfect, see above. + */ +static bool vmx_is_low_priority_db_trap(struct kvm_queued_exception *ex) +{ + return vmx_get_pending_dbg_trap(ex) & ~DR6_BT; } /* @@ -3782,9 +4139,11 @@ static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu) */ static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu) { - if (vmx_pending_dbg_trap(vcpu)) - vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, - vcpu->arch.exception.payload); + unsigned long pending_dbg; + + pending_dbg = vmx_get_pending_dbg_trap(&vcpu->arch.exception); + if (pending_dbg) + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, pending_dbg); } static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) @@ -3793,21 +4152,161 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) to_vmx(vcpu)->nested.preemption_timer_expired; } -static int vmx_check_nested_events(struct kvm_vcpu *vcpu) +static bool vmx_has_nested_events(struct kvm_vcpu *vcpu, bool for_injection) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long exit_qual; - bool block_nested_events = - vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu); - bool mtf_pending = vmx->nested.mtf_pending; - struct kvm_lapic *apic = vcpu->arch.apic; + void *vapic = vmx->nested.virtual_apic_map.hva; + int max_irr, vppr; + + if (nested_vmx_preemption_timer_pending(vcpu) || + vmx->nested.mtf_pending) + return true; /* - * Clear the MTF state. If a higher priority VM-exit is delivered first, - * this state is discarded. + * Virtual Interrupt Delivery doesn't require manual injection. Either + * the interrupt is already in GUEST_RVI and will be recognized by CPU + * at VM-Entry, or there is a KVM_REQ_EVENT pending and KVM will move + * the interrupt from the PIR to RVI prior to entering the guest. */ - if (!block_nested_events) - vmx->nested.mtf_pending = false; + if (for_injection) + return false; + + if (!nested_cpu_has_vid(get_vmcs12(vcpu)) || + __vmx_interrupt_blocked(vcpu)) + return false; + + if (!vapic) + return false; + + vppr = *((u32 *)(vapic + APIC_PROCPRI)); + + max_irr = vmx_get_rvi(); + if ((max_irr & 0xf0) > (vppr & 0xf0)) + return true; + + if (vmx->nested.pi_pending && vmx->nested.pi_desc && + pi_test_on(vmx->nested.pi_desc)) { + max_irr = pi_find_highest_vector(vmx->nested.pi_desc); + if (max_irr > 0 && (max_irr & 0xf0) > (vppr & 0xf0)) + return true; + } + + return false; +} + +/* + * Per the Intel SDM's table "Priority Among Concurrent Events", with minor + * edits to fill in missing examples, e.g. #DB due to split-lock accesses, + * and less minor edits to splice in the priority of VMX Non-Root specific + * events, e.g. MTF and NMI/INTR-window exiting. + * + * 1 Hardware Reset and Machine Checks + * - RESET + * - Machine Check + * + * 2 Trap on Task Switch + * - T flag in TSS is set (on task switch) + * + * 3 External Hardware Interventions + * - FLUSH + * - STOPCLK + * - SMI + * - INIT + * + * 3.5 Monitor Trap Flag (MTF) VM-exit[1] + * + * 4 Traps on Previous Instruction + * - Breakpoints + * - Trap-class Debug Exceptions (#DB due to TF flag set, data/I-O + * breakpoint, or #DB due to a split-lock access) + * + * 4.3 VMX-preemption timer expired VM-exit + * + * 4.6 NMI-window exiting VM-exit[2] + * + * 5 Nonmaskable Interrupts (NMI) + * + * 5.5 Interrupt-window exiting VM-exit and Virtual-interrupt delivery + * + * 6 Maskable Hardware Interrupts + * + * 7 Code Breakpoint Fault + * + * 8 Faults from Fetching Next Instruction + * - Code-Segment Limit Violation + * - Code Page Fault + * - Control protection exception (missing ENDBRANCH at target of indirect + * call or jump) + * + * 9 Faults from Decoding Next Instruction + * - Instruction length > 15 bytes + * - Invalid Opcode + * - Coprocessor Not Available + * + *10 Faults on Executing Instruction + * - Overflow + * - Bound error + * - Invalid TSS + * - Segment Not Present + * - Stack fault + * - General Protection + * - Data Page Fault + * - Alignment Check + * - x86 FPU Floating-point exception + * - SIMD floating-point exception + * - Virtualization exception + * - Control protection exception + * + * [1] Per the "Monitor Trap Flag" section: System-management interrupts (SMIs), + * INIT signals, and higher priority events take priority over MTF VM exits. + * MTF VM exits take priority over debug-trap exceptions and lower priority + * events. + * + * [2] Debug-trap exceptions and higher priority events take priority over VM exits + * caused by the VMX-preemption timer. VM exits caused by the VMX-preemption + * timer take priority over VM exits caused by the "NMI-window exiting" + * VM-execution control and lower priority events. + * + * [3] Debug-trap exceptions and higher priority events take priority over VM exits + * caused by "NMI-window exiting". VM exits caused by this control take + * priority over non-maskable interrupts (NMIs) and lower priority events. + * + * [4] Virtual-interrupt delivery has the same priority as that of VM exits due to + * the 1-setting of the "interrupt-window exiting" VM-execution control. Thus, + * non-maskable interrupts (NMIs) and higher priority events take priority over + * delivery of a virtual interrupt; delivery of a virtual interrupt takes + * priority over external interrupts and lower priority events. + */ +static int vmx_check_nested_events(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * Only a pending nested run blocks a pending exception. If there is a + * previously injected event, the pending exception occurred while said + * event was being delivered and thus needs to be handled. + */ + bool block_nested_exceptions = vmx->nested.nested_run_pending; + /* + * Events that don't require injection, i.e. that are virtualized by + * hardware, aren't blocked by a pending VM-Enter as KVM doesn't need + * to regain control in order to deliver the event, and hardware will + * handle event ordering, e.g. with respect to injected exceptions. + * + * But, new events (not exceptions) are only recognized at instruction + * boundaries. If an event needs reinjection, then KVM is handling a + * VM-Exit that occurred _during_ instruction execution; new events, + * irrespective of whether or not they're injected, are blocked until + * the instruction completes. + */ + bool block_non_injected_events = kvm_event_needs_reinjection(vcpu); + /* + * Inject events are blocked by nested VM-Enter, as KVM is responsible + * for managing priority between concurrent events, i.e. KVM needs to + * wait until after VM-Enter completes to deliver injected events. + */ + bool block_nested_events = block_nested_exceptions || + block_non_injected_events; if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { @@ -3817,6 +4316,9 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) clear_bit(KVM_APIC_INIT, &apic->pending_events); if (vcpu->arch.mp_state != KVM_MP_STATE_INIT_RECEIVED) nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); + + /* MTF is discarded if the vCPU is in WFS. */ + vmx->nested.mtf_pending = false; return 0; } @@ -3826,31 +4328,41 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) return -EBUSY; clear_bit(KVM_APIC_SIPI, &apic->pending_events); - if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { nested_vmx_vmexit(vcpu, EXIT_REASON_SIPI_SIGNAL, 0, apic->sipi_vector & 0xFFUL); - return 0; + return 0; + } + /* Fallthrough, the SIPI is completely ignored. */ } /* - * Process any exceptions that are not debug traps before MTF. + * Process exceptions that are higher priority than Monitor Trap Flag: + * fault-like exceptions, TSS T flag #DB (not emulated by KVM, but + * could theoretically come in from userspace), and ICEBP (INT1). * - * Note that only a pending nested run can block a pending exception. - * Otherwise an injected NMI/interrupt should either be - * lost or delivered to the nested hypervisor in the IDT_VECTORING_INFO, - * while delivering the pending exception. + * TODO: SMIs have higher priority than MTF and trap-like #DBs (except + * for TSS T flag #DBs). KVM also doesn't save/restore pending MTF + * across SMI/RSM as it should; that needs to be addressed in order to + * prioritize SMI over MTF and trap-like #DBs. */ - - if (vcpu->arch.exception.pending && !vmx_pending_dbg_trap(vcpu)) { - if (vmx->nested.nested_run_pending) + if (vcpu->arch.exception_vmexit.pending && + !vmx_is_low_priority_db_trap(&vcpu->arch.exception_vmexit)) { + if (block_nested_exceptions) return -EBUSY; - if (!nested_vmx_check_exception(vcpu, &exit_qual)) - goto no_vmexit; - nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + + nested_vmx_inject_exception_vmexit(vcpu); return 0; } - if (mtf_pending) { + if (vcpu->arch.exception.pending && + !vmx_is_low_priority_db_trap(&vcpu->arch.exception)) { + if (block_nested_exceptions) + return -EBUSY; + goto no_vmexit; + } + + if (vmx->nested.mtf_pending) { if (block_nested_events) return -EBUSY; nested_vmx_update_pending_dbg(vcpu); @@ -3858,15 +4370,20 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) return 0; } - if (vcpu->arch.exception.pending) { - if (vmx->nested.nested_run_pending) + if (vcpu->arch.exception_vmexit.pending) { + if (block_nested_exceptions) return -EBUSY; - if (!nested_vmx_check_exception(vcpu, &exit_qual)) - goto no_vmexit; - nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + + nested_vmx_inject_exception_vmexit(vcpu); return 0; } + if (vcpu->arch.exception.pending) { + if (block_nested_exceptions) + return -EBUSY; + goto no_vmexit; + } + if (nested_vmx_preemption_timer_pending(vcpu)) { if (block_nested_events) return -EBUSY; @@ -3899,11 +4416,71 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) } if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) { + int irq; + + if (!nested_exit_on_intr(vcpu)) { + if (block_nested_events) + return -EBUSY; + + goto no_vmexit; + } + + if (!nested_exit_intr_ack_set(vcpu)) { + if (block_nested_events) + return -EBUSY; + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); + return 0; + } + + irq = kvm_cpu_get_extint(vcpu); + if (irq != -1) { + if (block_nested_events) + return -EBUSY; + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); + return 0; + } + + irq = kvm_apic_has_interrupt(vcpu); + if (WARN_ON_ONCE(irq < 0)) + goto no_vmexit; + + /* + * If the IRQ is L2's PI notification vector, process posted + * interrupts for L2 instead of injecting VM-Exit, as the + * detection/morphing architecturally occurs when the IRQ is + * delivered to the CPU. Note, only interrupts that are routed + * through the local APIC trigger posted interrupt processing, + * and enabling posted interrupts requires ACK-on-exit. + */ + if (irq == vmx->nested.posted_intr_nv) { + /* + * Nested posted interrupts are delivered via RVI, i.e. + * aren't injected by KVM, and so can be queued even if + * manual event injection is disallowed. + */ + if (block_non_injected_events) + return -EBUSY; + + vmx->nested.pi_pending = true; + kvm_apic_clear_irr(vcpu, irq); + goto no_vmexit; + } + if (block_nested_events) return -EBUSY; - if (!nested_exit_on_intr(vcpu)) - goto no_vmexit; - nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); + + /* + * ACK the interrupt _after_ emulating VM-Exit, as the IRQ must + * be marked as in-service in vmcs01.GUEST_INTERRUPT_STATUS.SVI + * if APICv is active. + */ + kvm_apic_ack_interrupt(vcpu, irq); return 0; } @@ -4013,8 +4590,6 @@ static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, vmcs12->guest_idtr_base = vmcs_readl(GUEST_IDTR_BASE); vmcs12->guest_pending_dbg_exceptions = vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS); - if (kvm_mpx_supported()) - vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); vmx->nested.need_sync_vmcs02_to_vmcs12_rare = false; } @@ -4033,12 +4608,12 @@ static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, cpu = get_cpu(); vmx->loaded_vmcs = &vmx->nested.vmcs02; - vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->vmcs01); + vmx_vcpu_load_vmcs(vcpu, cpu); sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); vmx->loaded_vmcs = &vmx->vmcs01; - vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->nested.vmcs02); + vmx_vcpu_load_vmcs(vcpu, cpu); put_cpu(); } @@ -4052,11 +4627,11 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); vmx->nested.need_sync_vmcs02_to_vmcs12_rare = - !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr); + !nested_vmx_is_evmptr12_valid(vmx); vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); @@ -4111,11 +4686,21 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | (vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE); + /* + * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02. + * Writes to DEBUGCTL that aren't intercepted by L1 are immediately + * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into + * vmcs02 doesn't strictly track vmcs12. + */ if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) - kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7); + vmcs12->guest_dr7 = vcpu->arch.dr7; if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER) vmcs12->guest_ia32_efer = vcpu->arch.efer; + + vmcs_read_cet_state(&vmx->vcpu, &vmcs12->guest_s_cet, + &vmcs12->guest_ssp, + &vmcs12->guest_ssp_tbl); } /* @@ -4131,19 +4716,19 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) */ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, u32 vm_exit_reason, u32 exit_intr_info, - unsigned long exit_qualification) + unsigned long exit_qualification, u32 exit_insn_len) { /* update exit information fields: */ vmcs12->vm_exit_reason = vm_exit_reason; - if (to_vmx(vcpu)->exit_reason.enclave_mode) + if (vmx_get_exit_reason(vcpu).enclave_mode) vmcs12->vm_exit_reason |= VMX_EXIT_REASONS_SGX_ENCLAVE_MODE; vmcs12->exit_qualification = exit_qualification; - vmcs12->vm_exit_intr_info = exit_intr_info; - - 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); + /* + * On VM-Exit due to a failed VM-Entry, the VMCS isn't marked launched + * and only EXIT_REASON and EXIT_QUALIFICATION are updated, all other + * exit info fields are unmodified. + */ if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) { vmcs12->launch_state = 1; @@ -4155,7 +4740,12 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * Transfer the event that L0 or L1 may wanted to inject into * L2 to IDT_VECTORING_INFO_FIELD. */ - vmcs12_save_pending_event(vcpu, vmcs12); + vmcs12_save_pending_event(vcpu, vmcs12, + vm_exit_reason, exit_intr_info); + + vmcs12->vm_exit_intr_info = exit_intr_info; + vmcs12->vm_exit_instruction_len = exit_insn_len; + vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); /* * According to spec, there's no need to store the guest's @@ -4169,14 +4759,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL); } - - /* - * Drop what we picked up for L2 via vmx_complete_interrupts. It is - * preserved above and would only end up incorrectly in L1. - */ - vcpu->arch.nmi_injected = false; - kvm_clear_exception_queue(vcpu); - kvm_clear_interrupt_queue(vcpu); } /* @@ -4214,7 +4796,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * CR0_GUEST_HOST_MASK is already set in the original vmcs01 * (KVM doesn't change it); */ - vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs12->host_cr0); /* Same as above - no reason to call set_cr4_guest_host_mask(). */ @@ -4244,13 +4826,26 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, if (vmcs12->vm_exit_controls & VM_EXIT_CLEAR_BNDCFGS) vmcs_write64(GUEST_BNDCFGS, 0); + /* + * Load CET state from host state if VM_EXIT_LOAD_CET_STATE is set. + * otherwise CET state should be retained across VM-exit, i.e., + * guest values should be propagated from vmcs12 to vmcs01. + */ + if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_CET_STATE) + vmcs_write_cet_state(vcpu, vmcs12->host_s_cet, vmcs12->host_ssp, + vmcs12->host_ssp_tbl); + else + vmcs_write_cet_state(vcpu, vmcs12->guest_s_cet, vmcs12->guest_ssp, + vmcs12->guest_ssp_tbl); + if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) { vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat); vcpu->arch.pat = vmcs12->host_ia32_pat; } - if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) - WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, - vmcs12->host_ia32_perf_global_ctrl)); + if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) && + kvm_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu))) + WARN_ON_ONCE(__kvm_emulate_msr_write(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, + vmcs12->host_ia32_perf_global_ctrl)); /* Set L1 segment info according to Intel SDM 27.5.2 Loading Host Segment and Descriptor-Table Registers */ @@ -4267,7 +4862,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, seg.l = 1; else seg.db = 1; - vmx_set_segment(vcpu, &seg, VCPU_SREG_CS); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_CS); seg = (struct kvm_segment) { .base = 0, .limit = 0xFFFFFFFF, @@ -4278,17 +4873,17 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, .g = 1 }; seg.selector = vmcs12->host_ds_selector; - vmx_set_segment(vcpu, &seg, VCPU_SREG_DS); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_DS); seg.selector = vmcs12->host_es_selector; - vmx_set_segment(vcpu, &seg, VCPU_SREG_ES); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_ES); seg.selector = vmcs12->host_ss_selector; - vmx_set_segment(vcpu, &seg, VCPU_SREG_SS); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_SS); seg.selector = vmcs12->host_fs_selector; seg.base = vmcs12->host_fs_base; - vmx_set_segment(vcpu, &seg, VCPU_SREG_FS); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_FS); seg.selector = vmcs12->host_gs_selector; seg.base = vmcs12->host_gs_base; - vmx_set_segment(vcpu, &seg, VCPU_SREG_GS); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_GS); seg = (struct kvm_segment) { .base = vmcs12->host_tr_base, .limit = 0x67, @@ -4296,17 +4891,20 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, .type = 11, .present = 1 }; - vmx_set_segment(vcpu, &seg, VCPU_SREG_TR); + __vmx_set_segment(vcpu, &seg, VCPU_SREG_TR); - kvm_set_dr(vcpu, 7, 0x400); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + memset(&seg, 0, sizeof(seg)); + seg.unusable = 1; + __vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR); - if (cpu_has_vmx_msr_bitmap()) - vmx_update_msr_bitmap(vcpu); + kvm_set_dr(vcpu, 7, 0x400); + vmx_guest_debugctl_write(vcpu, 0); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); + + to_vt(vcpu)->emulation_required = vmx_emulation_required(vcpu); } static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) @@ -4318,7 +4916,7 @@ static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) return vmcs_read64(GUEST_IA32_EFER); if (cpu_has_load_ia32_efer()) - return host_efer; + return kvm_host.efer; for (i = 0; i < vmx->msr_autoload.guest.nr; ++i) { if (vmx->msr_autoload.guest.val[i].index == MSR_EFER) @@ -4329,7 +4927,7 @@ static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) if (efer_msr) return efer_msr->data; - return host_efer; + return kvm_host.efer; } static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) @@ -4355,13 +4953,16 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7))); } + /* Reload DEBUGCTL to ensure vmcs01 has a fresh FREEZE_IN_SMM value. */ + vmx_reload_guest_debugctl(vcpu); + /* * Note that calling vmx_set_{efer,cr0,cr4} is important as they * handle a variety of side effects to KVM's software model. */ vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx)); - vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW)); vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); @@ -4382,9 +4983,6 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); - if (cpu_has_vmx_msr_bitmap()) - vmx_update_msr_bitmap(vcpu); - /* * This nasty bit of open coding is a compromise between blindly * loading L1's MSRs using the exit load lists (incorrect emulation @@ -4425,7 +5023,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) goto vmabort; } - if (kvm_set_msr(vcpu, h.index, h.value)) { + if (kvm_emulate_msr_write(vcpu, h.index, h.value)) { pr_debug_ratelimited( "%s WRMSR failed (%u, 0x%x, 0x%llx)\n", __func__, j, h.index, h.value); @@ -4445,18 +5043,20 @@ vmabort: * and modify vmcs12 to make it see what it would expect to see there if * L2 was its real guest. Must only be called when in L2 (is_guest_mode()) */ -void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, - u32 exit_intr_info, unsigned long exit_qualification) +void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, + u32 exit_intr_info, unsigned long exit_qualification, + u32 exit_insn_len) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + /* Pending MTF traps are discarded on VM-Exit. */ + vmx->nested.mtf_pending = false; + /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); - /* Similarly, triple faults in L2 should never escape. */ - WARN_ON_ONCE(kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)); - +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { /* * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map @@ -4466,10 +5066,10 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, */ (void)nested_get_evmcs_page(vcpu); } +#endif - /* Service the TLB flush request for L2 before switching to L1. */ - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); + /* Service pending TLB flush requests for L2 before switching to L1. */ + kvm_service_local_tlb_flush_requests(vcpu); /* * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between @@ -4495,7 +5095,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, if (vm_exit_reason != -1) prepare_vmcs12(vcpu, vmcs12, vm_exit_reason, - exit_intr_info, exit_qualification); + exit_intr_info, exit_qualification, + exit_insn_len); /* * Must happen outside of sync_vmcs02_to_vmcs12() as it will @@ -4511,21 +5112,35 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* * The only expected VM-instruction error is "VM entry with * invalid control field(s)." Anything else indicates a - * problem with L0. And we should never get here with a - * VMFail of any type if early consistency checks are enabled. + * problem with L0. */ WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) != VMXERR_ENTRY_INVALID_CONTROL_FIELD); - WARN_ON_ONCE(nested_early_check); + + /* VM-Fail at VM-Entry means KVM missed a consistency check. */ + WARN_ON_ONCE(warn_on_missed_cc); } + /* + * Drop events/exceptions that were queued for re-injection to L2 + * (picked up via vmx_complete_interrupts()), as well as exceptions + * that were pending for L2. Note, this must NOT be hoisted above + * prepare_vmcs12(), events/exceptions queued for re-injection need to + * be captured in vmcs12 (see vmcs12_save_pending_event()). + */ + vcpu->arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); + vmx_switch_vmcs(vcpu, &vmx->vmcs01); + kvm_nested_vmexit_handle_ibrs(vcpu); + /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); - if (kvm_has_tsc_control) + if (kvm_caps.has_tsc_control) vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); if (vmx->nested.l1_tpr_threshold != -1) @@ -4541,36 +5156,31 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmx_update_cpu_dirty_logging(vcpu); } - /* Unpin physical memory we referred to in vmcs02 */ - if (vmx->nested.apic_access_page) { - kvm_release_page_clean(vmx->nested.apic_access_page); - vmx->nested.apic_access_page = NULL; - } - kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true); - kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true); - vmx->nested.pi_desc = NULL; + nested_put_vmcs12_pages(vcpu); if (vmx->nested.reload_vmcs01_apic_access_page) { vmx->nested.reload_vmcs01_apic_access_page = false; kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); } + if (vmx->nested.update_vmcs01_apicv_status) { + vmx->nested.update_vmcs01_apicv_status = false; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } + + if (vmx->nested.update_vmcs01_hwapic_isr) { + vmx->nested.update_vmcs01_hwapic_isr = false; + kvm_apic_update_hwapic_isr(vcpu); + } + if ((vm_exit_reason != -1) && - (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))) + (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))) vmx->nested.need_vmcs12_to_shadow_sync = true; /* in case we halted in L2 */ - vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); if (likely(!vmx->fail)) { - if ((u16)vm_exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && - nested_exit_intr_ack_set(vcpu)) { - int irq = kvm_cpu_get_interrupt(vcpu); - WARN_ON(irq < 0); - vmcs12->vm_exit_intr_info = irq | - INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR; - } - if (vm_exit_reason != -1) trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, vmcs12->exit_qualification, @@ -4581,6 +5191,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, load_vmcs12_host_state(vcpu, vmcs12); + /* + * Process events if an injectable IRQ or NMI is pending, even + * if the event is blocked (RFLAGS.IF is cleared on VM-Exit). + * If an event became pending while L2 was active, KVM needs to + * either inject the event or request an IRQ/NMI window. SMIs + * don't need to be processed as SMM is mutually exclusive with + * non-root mode. INIT/SIPI don't need to be checked as INIT + * is blocked post-VMXON, and SIPIs are ignored. + */ + if (kvm_cpu_has_injectable_intr(vcpu) || vcpu->arch.nmi_pending) + kvm_make_request(KVM_REQ_EVENT, vcpu); return; } @@ -4606,6 +5227,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu) { + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); } @@ -4681,11 +5303,12 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, else *ret = off; + *ret = vmx_get_untagged_addr(vcpu, *ret, 0); /* Long mode: #GP(0)/#SS(0) if the memory address is in a * non-canonical form. This is the only check on the memory * destination for long mode! */ - exn = is_noncanonical_address(*ret, vcpu); + exn = is_noncanonical_address(*ret, vcpu, 0); } else { /* * When not in long mode, the virtual/linear address is @@ -4739,27 +5362,6 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, return 0; } -void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx; - - if (!nested_vmx_allowed(vcpu)) - return; - - vmx = to_vmx(vcpu); - if (kvm_x86_ops.pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) { - vmx->nested.msrs.entry_ctls_high |= - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; - vmx->nested.msrs.exit_ctls_high |= - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; - } else { - vmx->nested.msrs.entry_ctls_high &= - ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; - vmx->nested.msrs.exit_ctls_high &= - ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; - } -} - static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer, int *ret) { @@ -4794,18 +5396,20 @@ static struct vmcs *alloc_shadow_vmcs(struct kvm_vcpu *vcpu) struct loaded_vmcs *loaded_vmcs = vmx->loaded_vmcs; /* - * We should allocate a shadow vmcs for vmcs01 only when L1 - * executes VMXON and free it when L1 executes VMXOFF. - * As it is invalid to execute VMXON twice, we shouldn't reach - * here when vmcs01 already have an allocated shadow vmcs. + * KVM allocates a shadow VMCS only when L1 executes VMXON and frees it + * when L1 executes VMXOFF or the vCPU is forced out of nested + * operation. VMXON faults if the CPU is already post-VMXON, so it + * should be impossible to already have an allocated shadow VMCS. KVM + * doesn't support virtualization of VMCS shadowing, so vmcs01 should + * always be the loaded VMCS. */ - WARN_ON(loaded_vmcs == &vmx->vmcs01 && loaded_vmcs->shadow_vmcs); + if (WARN_ON(loaded_vmcs != &vmx->vmcs01 || loaded_vmcs->shadow_vmcs)) + return loaded_vmcs->shadow_vmcs; + + loaded_vmcs->shadow_vmcs = alloc_vmcs(true); + if (loaded_vmcs->shadow_vmcs) + vmcs_clear(loaded_vmcs->shadow_vmcs); - if (!loaded_vmcs->shadow_vmcs) { - loaded_vmcs->shadow_vmcs = alloc_vmcs(true); - if (loaded_vmcs->shadow_vmcs) - vmcs_clear(loaded_vmcs->shadow_vmcs); - } return loaded_vmcs->shadow_vmcs; } @@ -4822,6 +5426,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) if (!vmx->nested.cached_vmcs12) goto out_cached_vmcs12; + vmx->nested.shadow_vmcs12_cache.gpa = INVALID_GPA; vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT); if (!vmx->nested.cached_shadow_vmcs12) goto out_cached_shadow_vmcs12; @@ -4829,9 +5434,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) if (enable_shadow_vmcs && !alloc_shadow_vmcs(vcpu)) goto out_shadow_vmcs; - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS_PINNED); - vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; + hrtimer_setup(&vmx->nested.preemption_timer, vmx_preemption_timer_fn, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED); vmx->nested.vpid02 = allocate_vpid(); @@ -4858,15 +5462,8 @@ out_vmcs02: return -ENOMEM; } -/* - * Emulate the VMXON instruction. - * Currently, we just remember that VMX is active, and do not save or even - * inspect the argument to VMXON (the so-called "VMXON pointer") because we - * do not currently need to store anything in that guest-allocated memory - * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their - * argument is different from the VMXON pointer (which the spec says they do). - */ -static int handle_vmon(struct kvm_vcpu *vcpu) +/* Emulate the VMXON instruction. */ +static int handle_vmxon(struct kvm_vcpu *vcpu) { int ret; gpa_t vmptr; @@ -4876,20 +5473,36 @@ static int handle_vmon(struct kvm_vcpu *vcpu) | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; /* - * The Intel VMX Instruction Reference lists a bunch of bits that are - * prerequisite to running VMXON, most notably cr4.VMXE must be set to - * 1 (see vmx_is_valid_cr4() for when we allow the guest to set this). - * Otherwise, we should fail with #UD. But most faulting conditions - * have already been checked by hardware, prior to the VM-exit for - * VMXON. We do test guest cr4.VMXE because processor CR4 always has - * that bit set to 1 in non-root mode. + * Manually check CR4.VMXE checks, KVM must force CR4.VMXE=1 to enter + * the guest and so cannot rely on hardware to perform the check, + * which has higher priority than VM-Exit (see Intel SDM's pseudocode + * for VMXON). + * + * Rely on hardware for the other pre-VM-Exit checks, CR0.PE=1, !VM86 + * and !COMPATIBILITY modes. For an unrestricted guest, KVM doesn't + * force any of the relevant guest state. For a restricted guest, KVM + * does force CR0.PE=1, but only to also force VM86 in order to emulate + * Real Mode, and so there's no need to check CR0.PE manually. */ - if (!kvm_read_cr4_bits(vcpu, X86_CR4_VMXE)) { + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_VMXE)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } - /* CPL=0 must be checked manually. */ + /* + * The CPL is checked for "not in VMX operation" and for "in VMX root", + * and has higher priority than the VM-Fail due to being post-VMXON, + * i.e. VMXON #GPs outside of VMX non-root if CPL!=0. In VMX non-root, + * VMXON causes VM-Exit and KVM unconditionally forwards VMXON VM-Exits + * from L2 to L1, i.e. there's no need to check for the vCPU being in + * VMX non-root. + * + * Forwarding the VM-Exit unconditionally, i.e. without performing the + * #UD checks (see above), is functionally ok because KVM doesn't allow + * L1 to run L2 without CR4.VMXE=0, and because KVM never modifies L2's + * CR0 or CR4, i.e. it's L2's responsibility to emulate #UDs that are + * missed by hardware due to shadowing CR0 and/or CR4. + */ if (vmx_get_cpl(vcpu)) { kvm_inject_gp(vcpu, 0); return 1; @@ -4898,6 +5511,17 @@ static int handle_vmon(struct kvm_vcpu *vcpu) if (vmx->nested.vmxon) return nested_vmx_fail(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); + /* + * Invalid CR0/CR4 generates #GP. These checks are performed if and + * only if the vCPU isn't already in VMX operation, i.e. effectively + * have lower priority than the VM-Fail above. + */ + if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) || + !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) { + kvm_inject_gp(vcpu, 0); + return 1; + } + if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES) != VMXON_NEEDED_FEATURES) { kvm_inject_gp(vcpu, 0); @@ -4934,7 +5558,7 @@ static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vmx->nested.current_vmptr == -1ull) + if (vmx->nested.current_vmptr == INVALID_GPA) return; copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); @@ -4952,21 +5576,21 @@ static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu) vmx->nested.current_vmptr >> PAGE_SHIFT, vmx->nested.cached_vmcs12, 0, VMCS12_SIZE); - kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); + kvm_mmu_free_roots(vcpu->kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); - vmx->nested.current_vmptr = -1ull; + vmx->nested.current_vmptr = INVALID_GPA; } /* Emulate the VMXOFF instruction */ -static int handle_vmoff(struct kvm_vcpu *vcpu) +static int handle_vmxoff(struct kvm_vcpu *vcpu) { if (!nested_vmx_check_permission(vcpu)) return 1; free_nested(vcpu); - /* Process a latched INIT during time CPU was in VMX operation */ - kvm_make_request(KVM_REQ_EVENT, vcpu); + if (kvm_apic_has_pending_init_or_sipi(vcpu)) + kvm_make_request(KVM_REQ_EVENT, vcpu); return nested_vmx_succeed(vcpu); } @@ -4977,7 +5601,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); u32 zero = 0; gpa_t vmptr; - u64 evmcs_gpa; int r; if (!nested_vmx_check_permission(vcpu)) @@ -4992,27 +5615,23 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (vmptr == vmx->nested.vmxon_ptr) return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_VMXON_POINTER); - /* - * When Enlightened VMEntry is enabled on the calling CPU we treat - * memory area pointer by vmptr as Enlightened VMCS (as there's no good - * way to distinguish it from VMCS12) and we must not corrupt it by - * writing to the non-existent 'launch_state' field. The area doesn't - * have to be the currently active EVMCS on the calling CPU and there's - * nothing KVM has to do to transition it from 'active' to 'non-active' - * state. It is possible that the area will stay mapped as - * vmx->nested.hv_evmcs but this shouldn't be a problem. - */ - if (likely(!vmx->nested.enlightened_vmcs_enabled || - !nested_enlightened_vmentry(vcpu, &evmcs_gpa))) { + if (likely(!nested_evmcs_handle_vmclear(vcpu, vmptr))) { if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); - kvm_vcpu_write_guest(vcpu, - vmptr + offsetof(struct vmcs12, - launch_state), - &zero, sizeof(zero)); - } else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) { - nested_release_evmcs(vcpu); + /* + * Silently ignore memory errors on VMCLEAR, Intel's pseudocode + * for VMCLEAR includes a "ensure that data for VMCS referenced + * by the operand is in memory" clause that guards writes to + * memory, i.e. doing nothing for I/O is architecturally valid. + * + * FIXME: Suppress failures if and only if no memslot is found, + * i.e. exit to userspace if __copy_to_user() fails. + */ + (void)kvm_vcpu_write_guest(vcpu, + vmptr + offsetof(struct vmcs12, + launch_state), + &zero, sizeof(zero)); } return nested_vmx_succeed(vcpu); @@ -5048,27 +5667,49 @@ static int handle_vmread(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - /* - * In VMX non-root operation, when the VMCS-link pointer is -1ull, - * any VMREAD sets the ALU flags for VMfailInvalid. - */ - if (vmx->nested.current_vmptr == -1ull || - (is_guest_mode(vcpu) && - get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) - return nested_vmx_failInvalid(vcpu); - /* Decode instruction info and find the field to read */ field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf)); - offset = vmcs_field_to_offset(field); - if (offset < 0) - return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); + if (!nested_vmx_is_evmptr12_valid(vmx)) { + /* + * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, + * any VMREAD sets the ALU flags for VMfailInvalid. + */ + if (vmx->nested.current_vmptr == INVALID_GPA || + (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA)) + return nested_vmx_failInvalid(vcpu); - if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field)) - copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); + offset = get_vmcs12_field_offset(field); + if (offset < 0) + return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); + + if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field)) + copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - /* Read the field, zero-extended to a u64 value */ - value = vmcs12_read_any(vmcs12, field, offset); + /* Read the field, zero-extended to a u64 value */ + value = vmcs12_read_any(vmcs12, field, offset); + } else { + /* + * Hyper-V TLFS (as of 6.0b) explicitly states, that while an + * enlightened VMCS is active VMREAD/VMWRITE instructions are + * unsupported. Unfortunately, certain versions of Windows 11 + * don't comply with this requirement which is not enforced in + * genuine Hyper-V. Allow VMREAD from an enlightened VMCS as a + * workaround, as misbehaving guests will panic on VM-Fail. + * Note, enlightened VMCS is incompatible with shadow VMCS so + * all VMREADs from L2 should go to L1. + */ + if (WARN_ON_ONCE(is_guest_mode(vcpu))) + return nested_vmx_failInvalid(vcpu); + + offset = evmcs_field_offset(field, NULL); + if (offset < 0) + return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); + + /* Read the field, zero-extended to a u64 value */ + value = evmcs_read_any(nested_vmx_evmcs(vmx), field, offset); + } /* * Now copy part of this value to register or memory, as requested. @@ -5141,12 +5782,12 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return 1; /* - * In VMX non-root operation, when the VMCS-link pointer is -1ull, + * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, * any VMWRITE sets the ALU flags for VMfailInvalid. */ - if (vmx->nested.current_vmptr == -1ull || + if (vmx->nested.current_vmptr == INVALID_GPA || (is_guest_mode(vcpu) && - get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) + get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); if (instr_info & BIT(10)) @@ -5163,7 +5804,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf)); - offset = vmcs_field_to_offset(field); + offset = get_vmcs12_field_offset(field); if (offset < 0) return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); @@ -5232,6 +5873,7 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) vmx->nested.need_vmcs12_to_shadow_sync = true; } vmx->nested.dirty_vmcs12 = true; + vmx->nested.force_msr_bitmap_recalc = true; } /* Emulate the VMPTRLD instruction */ @@ -5254,14 +5896,14 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_VMXON_POINTER); /* Forbid normal VMPTRLD if Enlightened version was used */ - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) return 1; if (vmx->nested.current_vmptr != vmptr) { - struct kvm_host_map map; - struct vmcs12 *new_vmcs12; + struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache; + struct vmcs_hdr hdr; - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmptr), &map)) { + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) { /* * Reads from an unbacked page return all 1s, * which means that the 32 bits located at the @@ -5272,12 +5914,16 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); } - new_vmcs12 = map.hva; + if (kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr, + offsetof(struct vmcs12, hdr), + sizeof(hdr))) { + return nested_vmx_fail(vcpu, + VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); + } - if (new_vmcs12->hdr.revision_id != VMCS12_REVISION || - (new_vmcs12->hdr.shadow_vmcs && + if (hdr.revision_id != VMCS12_REVISION || + (hdr.shadow_vmcs && !nested_cpu_has_vmx_shadow_vmcs(vcpu))) { - kvm_vcpu_unmap(vcpu, &map, false); return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); } @@ -5288,8 +5934,11 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) * Load VMCS12 from guest memory since it is not already * cached. */ - memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE); - kvm_vcpu_unmap(vcpu, &map, false); + if (kvm_read_guest_cached(vcpu->kvm, ghc, vmx->nested.cached_vmcs12, + VMCS12_SIZE)) { + return nested_vmx_fail(vcpu, + VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); + } set_current_vmptr(vmx, vmptr); } @@ -5310,7 +5959,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (unlikely(evmptr_is_valid(to_vmx(vcpu)->nested.hv_evmcs_vmptr))) + if (unlikely(nested_vmx_is_evmptr12_valid(to_vmx(vcpu)))) return 1; if (get_vmx_mem_address(vcpu, exit_qual, instr_info, @@ -5325,14 +5974,6 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) return nested_vmx_succeed(vcpu); } -#define EPTP_PA_MASK GENMASK_ULL(51, 12) - -static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) -{ - return VALID_PAGE(root_hpa) && - ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); -} - /* Emulate the INVEPT instruction */ static int handle_invept(struct kvm_vcpu *vcpu) { @@ -5345,7 +5986,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) struct { u64 eptp, gpa; } operand; - int i, r; + int i, r, gpr_index; if (!(vmx->nested.msrs.secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) || @@ -5358,7 +5999,8 @@ static int handle_invept(struct kvm_vcpu *vcpu) return 1; vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); + gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); + type = kvm_register_read(vcpu, gpr_index); types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6; @@ -5388,7 +6030,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); roots_to_free = 0; - if (nested_ept_root_matches(mmu->root_hpa, mmu->root_pgd, + if (nested_ept_root_matches(mmu->root.hpa, mmu->root.pgd, operand.eptp)) roots_to_free |= KVM_MMU_ROOT_CURRENT; @@ -5408,7 +6050,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) } if (roots_to_free) - kvm_mmu_free_roots(vcpu, mmu, roots_to_free); + kvm_mmu_free_roots(vcpu->kvm, mmu, roots_to_free); return nested_vmx_succeed(vcpu); } @@ -5425,7 +6067,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) u64 gla; } operand; u16 vpid02; - int r; + int r, gpr_index; if (!(vmx->nested.msrs.secondary_ctls_high & SECONDARY_EXEC_ENABLE_VPID) || @@ -5438,7 +6080,8 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) return 1; vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); + gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); + type = kvm_register_read(vcpu, gpr_index); types = (vmx->nested.msrs.vpid_caps & VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8; @@ -5461,11 +6104,21 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + /* + * Always flush the effective vpid02, i.e. never flush the current VPID + * and never explicitly flush vpid01. INVVPID targets a VPID, not a + * VMCS, and so whether or not the current vmcs12 has VPID enabled is + * irrelevant (and there may not be a loaded vmcs12). + */ vpid02 = nested_get_vpid02(vcpu); switch (type) { case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: + /* + * LAM doesn't apply to addresses that are inputs to TLB + * invalidation. + */ if (!operand.vpid || - is_noncanonical_address(operand.gla, vcpu)) + is_noncanonical_invlpg_address(operand.gla, vcpu)) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); vpid_sync_vcpu_addr(vpid02, operand.gla); @@ -5496,7 +6149,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) * TODO: sync only the affected SPTEs for INVDIVIDUAL_ADDR. */ if (!enable_ept) - kvm_mmu_free_guest_mode_roots(vcpu, &vcpu->arch.root_mmu); + kvm_mmu_free_guest_mode_roots(vcpu->kvm, &vcpu->arch.root_mmu); return nested_vmx_succeed(vcpu); } @@ -5541,11 +6194,10 @@ static int handle_vmfunc(struct kvm_vcpu *vcpu) u32 function = kvm_rax_read(vcpu); /* - * VMFUNC is only supported for nested guests, but we always enable the - * secondary control for simplicity; for non-nested mode, fake that we - * didn't by injecting #UD. + * VMFUNC should never execute cleanly while L1 is active; KVM supports + * VMFUNC for nested VMs, but not for L1. */ - if (!is_guest_mode(vcpu)) { + if (WARN_ON_ONCE(!is_guest_mode(vcpu))) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -5580,7 +6232,7 @@ fail: * nested VM-Exit. Pass the original exit reason, i.e. don't hardcode * EXIT_REASON_VMFUNC as the exit reason. */ - nested_vmx_vmexit(vcpu, vmx->exit_reason.full, + nested_vmx_vmexit(vcpu, vmx->vt.exit_reason.full, vmx_get_intr_info(vcpu), vmx_get_exit_qual(vcpu)); return 1; @@ -5597,7 +6249,7 @@ bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, gpa_t bitmap, last_bitmap; u8 b; - last_bitmap = (gpa_t)-1; + last_bitmap = INVALID_GPA; b = -1; while (size > 0) { @@ -5651,19 +6303,26 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, union vmx_exit_reason exit_reason) { - u32 msr_index = kvm_rcx_read(vcpu); + u32 msr_index; gpa_t bitmap; if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return true; + if (exit_reason.basic == EXIT_REASON_MSR_READ_IMM || + exit_reason.basic == EXIT_REASON_MSR_WRITE_IMM) + msr_index = vmx_get_exit_qual(vcpu); + else + msr_index = kvm_rcx_read(vcpu); + /* * The MSR_BITMAP page is divided into four 1024-byte bitmaps, * for the four combinations of read/write and low/high MSR numbers. * First we need to figure out which of the four to use: */ bitmap = vmcs12->msr_bitmap; - if (exit_reason.basic == EXIT_REASON_MSR_WRITE) + if (exit_reason.basic == EXIT_REASON_MSR_WRITE || + exit_reason.basic == EXIT_REASON_MSR_WRITE_IMM) bitmap += 2048; if (msr_index >= 0xc0000000) { msr_index -= 0xc0000000; @@ -5760,7 +6419,7 @@ static bool nested_vmx_exit_handled_encls(struct kvm_vcpu *vcpu, { u32 encls_leaf; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SGX) || + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) || !nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENCLS_EXITING)) return false; @@ -5826,7 +6485,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, if (is_nmi(intr_info)) return true; else if (is_page_fault(intr_info)) - return vcpu->arch.apf.host_apf_flags || !enable_ept; + return vcpu->arch.apf.host_apf_flags || + vmx_need_pf_intercept(vcpu); else if (is_debug(intr_info) && vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) @@ -5837,6 +6497,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, else if (is_alignment_check(intr_info) && !vmx_guest_inject_ac(vcpu)) return true; + else if (is_ve_fault(intr_info)) + return true; return false; case EXIT_REASON_EXTERNAL_INTERRUPT: return true; @@ -5869,6 +6531,19 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, case EXIT_REASON_VMFUNC: /* VM functions are emulated through L2->L0 vmexits. */ return true; + case EXIT_REASON_BUS_LOCK: + /* + * At present, bus lock VM exit is never exposed to L1. + * Handle L2's bus locks in L0 directly. + */ + return true; +#ifdef CONFIG_KVM_HYPERV + case EXIT_REASON_VMCALL: + /* Hyper-V L2 TLB flush hypercall is handled by L0 */ + return guest_hv_cpuid_has_l2_tlb_flush(vcpu) && + nested_evmcs_l2_tlb_flush_enabled(vcpu) && + kvm_hv_is_tlb_flush_hcall(vcpu); +#endif default: break; } @@ -5946,6 +6621,8 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, return nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC); case EXIT_REASON_MSR_READ: case EXIT_REASON_MSR_WRITE: + case EXIT_REASON_MSR_READ_IMM: + case EXIT_REASON_MSR_WRITE_IMM: return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason); case EXIT_REASON_INVALID_STATE: return true; @@ -5980,20 +6657,34 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING); case EXIT_REASON_XSETBV: return true; - case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS: + case EXIT_REASON_XSAVES: + case EXIT_REASON_XRSTORS: /* - * This should never happen, since it is not possible to - * set XSS to a non-zero value---neither in L1 nor in L2. - * If if it were, XSS would have to be checked against - * the XSS exit bitmap in vmcs12. + * Always forward XSAVES/XRSTORS to L1 as KVM doesn't utilize + * XSS-bitmap, and always loads vmcs02 with vmcs12's XSS-bitmap + * verbatim, i.e. any exit is due to L1's bitmap. WARN if + * XSAVES isn't enabled, as the CPU is supposed to inject #UD + * in that case, before consulting the XSS-bitmap. */ - return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); + WARN_ON_ONCE(!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_XSAVES)); + return true; case EXIT_REASON_UMWAIT: case EXIT_REASON_TPAUSE: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE); case EXIT_REASON_ENCLS: return nested_vmx_exit_handled_encls(vcpu, vmcs12); + case EXIT_REASON_NOTIFY: + /* Notify VM exit is not exposed to L1 */ + return false; + case EXIT_REASON_SEAMCALL: + case EXIT_REASON_TDCALL: + /* + * SEAMCALL and TDCALL unconditionally VM-Exit, but aren't + * virtualized by KVM for L1 hypervisors, i.e. L1 should + * never want or expect such an exit. + */ + return false; default: return true; } @@ -6006,7 +6697,7 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - union vmx_exit_reason exit_reason = vmx->exit_reason; + union vmx_exit_reason exit_reason = vmx->vt.exit_reason; unsigned long exit_qual; u32 exit_intr_info; @@ -6025,7 +6716,7 @@ bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) goto reflect_vmexit; } - trace_kvm_nested_vmexit(exit_reason.full, vcpu, KVM_ISA_VMX); + trace_kvm_nested_vmexit(vcpu, KVM_ISA_VMX); /* If L0 (KVM) wants the exit, it trumps L1's desires. */ if (nested_vmx_l0_wants_exit(vcpu, exit_reason)) @@ -6066,8 +6757,8 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, .format = KVM_STATE_NESTED_FORMAT_VMX, .size = sizeof(kvm_state), .hdr.vmx.flags = 0, - .hdr.vmx.vmxon_pa = -1ull, - .hdr.vmx.vmcs12_pa = -1ull, + .hdr.vmx.vmxon_pa = INVALID_GPA, + .hdr.vmx.vmcs12_pa = INVALID_GPA, .hdr.vmx.preemption_timer_deadline = 0, }; struct kvm_vmx_nested_state_data __user *user_vmx_nested_state = @@ -6079,7 +6770,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, vmx = to_vmx(vcpu); vmcs12 = get_vmcs12(vcpu); - if (nested_vmx_allowed(vcpu) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) && (vmx->nested.vmxon || vmx->nested.smm.vmxon)) { kvm_state.hdr.vmx.vmxon_pa = vmx->nested.vmxon_ptr; kvm_state.hdr.vmx.vmcs12_pa = vmx->nested.current_vmptr; @@ -6088,12 +6779,12 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, kvm_state.size += sizeof(user_vmx_nested_state->vmcs12); /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ - if (vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID) + if (nested_vmx_is_evmptr12_set(vmx)) kvm_state.flags |= KVM_STATE_NESTED_EVMCS; if (is_guest_mode(vcpu) && nested_cpu_has_shadow_vmcs(vmcs12) && - vmcs12->vmcs_link_pointer != -1ull) + vmcs12->vmcs_link_pointer != INVALID_GPA) kvm_state.size += sizeof(user_vmx_nested_state->shadow_vmcs12); } @@ -6144,7 +6835,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, } else { copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); if (!vmx->nested.need_vmcs12_to_shadow_sync) { - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) /* * L1 hypervisor is not obliged to keep eVMCS * clean fields data always up-to-date while @@ -6169,7 +6860,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, return -EFAULT; if (nested_cpu_has_shadow_vmcs(vmcs12) && - vmcs12->vmcs_link_pointer != -1ull) { + vmcs12->vmcs_link_pointer != INVALID_GPA) { if (copy_to_user(user_vmx_nested_state->shadow_vmcs12, get_shadow_vmcs12(vcpu), VMCS12_SIZE)) return -EFAULT; @@ -6178,9 +6869,6 @@ out: return kvm_state.size; } -/* - * Forcibly leave nested mode in order to be able to reset the VCPU later on. - */ void vmx_leave_nested(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { @@ -6204,11 +6892,11 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, if (kvm_state->format != KVM_STATE_NESTED_FORMAT_VMX) return -EINVAL; - if (kvm_state->hdr.vmx.vmxon_pa == -1ull) { + if (kvm_state->hdr.vmx.vmxon_pa == INVALID_GPA) { if (kvm_state->hdr.vmx.smm.flags) return -EINVAL; - if (kvm_state->hdr.vmx.vmcs12_pa != -1ull) + if (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA) return -EINVAL; /* @@ -6217,13 +6905,13 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, * code was changed such that flag signals vmcs12 should * be copied into eVMCS in guest memory. * - * To preserve backwards compatability, allow user + * To preserve backwards compatibility, allow user * to set this flag even when there is no VMXON region. */ if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS) return -EINVAL; } else { - if (!nested_vmx_allowed(vcpu)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return -EINVAL; if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa)) @@ -6257,12 +6945,13 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) && - (!nested_vmx_allowed(vcpu) || !vmx->nested.enlightened_vmcs_enabled)) + (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) || + !vmx->nested.enlightened_vmcs_enabled)) return -EINVAL; vmx_leave_nested(vcpu); - if (kvm_state->hdr.vmx.vmxon_pa == -1ull) + if (kvm_state->hdr.vmx.vmxon_pa == INVALID_GPA) return 0; vmx->nested.vmxon_ptr = kvm_state->hdr.vmx.vmxon_pa; @@ -6275,18 +6964,19 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, /* See vmx_has_valid_vmcs12. */ if ((kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE) || (kvm_state->flags & KVM_STATE_NESTED_EVMCS) || - (kvm_state->hdr.vmx.vmcs12_pa != -1ull)) + (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA)) return -EINVAL; else return 0; } - if (kvm_state->hdr.vmx.vmcs12_pa != -1ull) { + if (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA) { if (kvm_state->hdr.vmx.vmcs12_pa == kvm_state->hdr.vmx.vmxon_pa || !page_address_valid(vcpu, kvm_state->hdr.vmx.vmcs12_pa)) return -EINVAL; set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa); +#ifdef CONFIG_KVM_HYPERV } else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) { /* * nested_vmx_handle_enlightened_vmptrld() cannot be called @@ -6296,6 +6986,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, */ vmx->nested.hv_evmcs_vmptr = EVMPTR_MAP_PENDING; kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); +#endif } else { return -EINVAL; } @@ -6326,7 +7017,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, ret = -EINVAL; if (nested_cpu_has_shadow_vmcs(vmcs12) && - vmcs12->vmcs_link_pointer != -1ull) { + vmcs12->vmcs_link_pointer != INVALID_GPA) { struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); if (kvm_state->size < @@ -6359,10 +7050,14 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, goto error_guest_mode; vmx->nested.dirty_vmcs12 = true; + vmx->nested.force_msr_bitmap_recalc = true; ret = nested_vmx_enter_non_root_mode(vcpu, false); if (ret) goto error_guest_mode; + if (vmx->nested.mtf_pending) + kvm_make_request(KVM_REQ_EVENT, vcpu); + return 0; error_guest_mode: @@ -6401,7 +7096,7 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void) max_idx = 0; for (i = 0; i < nr_vmcs12_fields; i++) { /* The vmcs12 table is very, very sparsely populated. */ - if (!vmcs_field_to_offset_table[i]) + if (!vmcs12_field_offsets[i]) continue; idx = vmcs_field_index(VMCS12_IDX_TO_ENC(i)); @@ -6412,39 +7107,13 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void) return (u64)max_idx << VMCS_FIELD_INDEX_SHIFT; } -/* - * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be - * returned for the various VMX controls MSRs when nested VMX is enabled. - * The same values should also be used to verify that vmcs12 control fields are - * valid during nested entry from L1 to L2. - * Each of these control msrs has a low and high 32-bit half: A low bit is on - * if the corresponding bit in the (32-bit) control field *must* be on, and a - * bit in the high half is on if the corresponding bit in the control field - * may be on. See also vmx_control_verify(). - */ -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) +static void nested_vmx_setup_pinbased_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) { - /* - * Note that as a general rule, the high half of the MSRs (bits in - * the control fields which may be 1) should be initialized by the - * intersection of the underlying hardware's MSR (i.e., features which - * can be supported) and the list of features we want to expose - - * because they are known to be properly supported in our code. - * Also, usually, the low half of the MSRs (bits which must be 1) can - * be set to 0, meaning that L1 may turn off any of these bits. The - * 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_l1_wants_exit() will not pass related exits to L1. - * These rules have exceptions below. - */ - - /* pin-based controls */ - rdmsr(MSR_IA32_VMX_PINBASED_CTLS, - msrs->pinbased_ctls_low, - msrs->pinbased_ctls_high); - msrs->pinbased_ctls_low |= + msrs->pinbased_ctls_low = PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; + + msrs->pinbased_ctls_high = vmcs_conf->pin_based_exec_ctrl; msrs->pinbased_ctls_high &= PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | @@ -6453,52 +7122,67 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) msrs->pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; +} - /* exit controls */ - rdmsr(MSR_IA32_VMX_EXIT_CTLS, - msrs->exit_ctls_low, - msrs->exit_ctls_high); +static void nested_vmx_setup_exit_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; + msrs->exit_ctls_high = vmcs_conf->vmexit_ctrl; msrs->exit_ctls_high &= #ifdef CONFIG_X86_64 VM_EXIT_HOST_ADDR_SPACE_SIZE | #endif VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT | - VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_CET_STATE; msrs->exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | - VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT; + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT | + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && + !kvm_cpu_cap_has(X86_FEATURE_IBT)) + msrs->exit_ctls_high &= ~VM_EXIT_LOAD_CET_STATE; /* We support free control of debug control saving. */ msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS; +} - /* entry controls */ - rdmsr(MSR_IA32_VMX_ENTRY_CTLS, - msrs->entry_ctls_low, - msrs->entry_ctls_high); +static void nested_vmx_setup_entry_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; + + msrs->entry_ctls_high = vmcs_conf->vmentry_ctrl; msrs->entry_ctls_high &= #ifdef CONFIG_X86_64 VM_ENTRY_IA32E_MODE | #endif VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS | - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + VM_ENTRY_LOAD_CET_STATE; msrs->entry_ctls_high |= - (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER); + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER | + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL); + + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && + !kvm_cpu_cap_has(X86_FEATURE_IBT)) + msrs->entry_ctls_high &= ~VM_ENTRY_LOAD_CET_STATE; /* We support free control of debug control loading. */ msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS; +} - /* cpu-based controls */ - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, - msrs->procbased_ctls_low, - msrs->procbased_ctls_high); +static void nested_vmx_setup_cpubased_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; + + msrs->procbased_ctls_high = vmcs_conf->cpu_based_exec_ctrl; msrs->procbased_ctls_high &= CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING | @@ -6526,18 +7210,15 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) /* We support free control of CR3 access interception. */ msrs->procbased_ctls_low &= ~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING); +} - /* - * secondary cpu-based controls. Do not include those that - * depend on CPUID bits, they are added later by - * vmx_vcpu_after_set_cpuid. - */ - if (msrs->procbased_ctls_high & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, - msrs->secondary_ctls_low, - msrs->secondary_ctls_high); - +static void nested_vmx_setup_secondary_ctls(u32 ept_caps, + struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->secondary_ctls_low = 0; + + msrs->secondary_ctls_high = vmcs_conf->cpu_based_2nd_exec_ctrl; msrs->secondary_ctls_high &= SECONDARY_EXEC_DESC | SECONDARY_EXEC_ENABLE_RDTSCP | @@ -6547,9 +7228,11 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_RDRAND_EXITING | SECONDARY_EXEC_ENABLE_INVPCID | + SECONDARY_EXEC_ENABLE_VMFUNC | SECONDARY_EXEC_RDSEED_EXITING | - SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_TSC_SCALING; + SECONDARY_EXEC_ENABLE_XSAVES | + SECONDARY_EXEC_TSC_SCALING | + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; /* * We can emulate "VMCS shadowing," even if the hardware @@ -6578,18 +7261,13 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) SECONDARY_EXEC_ENABLE_PML; msrs->ept_caps |= VMX_EPT_AD_BIT; } - } - if (cpu_has_vmx_vmfunc()) { - msrs->secondary_ctls_high |= - SECONDARY_EXEC_ENABLE_VMFUNC; /* - * Advertise EPTP switching unconditionally - * since we emulate it + * Advertise EPTP switching irrespective of hardware support, + * KVM emulates it in software so long as VMFUNC is supported. */ - if (enable_ept) - msrs->vmfunc_controls = - VMX_VMFUNC_EPTP_SWITCHING; + if (cpu_has_vmx_vmfunc()) + msrs->vmfunc_controls = VMX_VMFUNC_EPTP_SWITCHING; } /* @@ -6615,34 +7293,40 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) if (enable_sgx) msrs->secondary_ctls_high |= SECONDARY_EXEC_ENCLS_EXITING; +} - /* miscellaneous data */ - rdmsr(MSR_IA32_VMX_MISC, - msrs->misc_low, - msrs->misc_high); - msrs->misc_low &= VMX_MISC_SAVE_EFER_LMA; +static void nested_vmx_setup_misc_data(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ + msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA; msrs->misc_low |= - MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE | VMX_MISC_ACTIVITY_HLT | VMX_MISC_ACTIVITY_WAIT_SIPI; msrs->misc_high = 0; +} +static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs) +{ /* * This MSR reports some information about VMX support. We * should return information about the VMX we emulate for the * guest, and the VMCS structure we give it - not about the * VMX support of the underlying hardware. */ - msrs->basic = - VMCS12_REVISION | - VMX_BASIC_TRUE_CTLS | - ((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) | - (VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT); + msrs->basic = vmx_basic_encode_vmcs_info(VMCS12_REVISION, VMCS12_SIZE, + X86_MEMTYPE_WB); + msrs->basic |= VMX_BASIC_TRUE_CTLS; if (cpu_has_vmx_basic_inout()) msrs->basic |= VMX_BASIC_INOUT; + if (cpu_has_vmx_basic_no_hw_errcode_cc()) + msrs->basic |= VMX_BASIC_NO_HW_ERROR_CODE_CC; +} +static void nested_vmx_setup_cr_fixed(struct nested_vmx_msrs *msrs) +{ /* * These MSRs specify bits which the guest must keep fixed on * while L1 is in VMXON mode (in L1's root mode, or running an L2). @@ -6654,8 +7338,56 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) msrs->cr4_fixed0 = VMXON_CR4_ALWAYSON; /* These MSRs specify bits which the guest must keep fixed off. */ - rdmsrl(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1); - rdmsrl(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1); + rdmsrq(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1); + rdmsrq(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1); + + if (vmx_umip_emulated()) + msrs->cr4_fixed1 |= X86_CR4_UMIP; +} + +/* + * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be + * returned for the various VMX controls MSRs when nested VMX is enabled. + * The same values should also be used to verify that vmcs12 control fields are + * valid during nested entry from L1 to L2. + * Each of these control msrs has a low and high 32-bit half: A low bit is on + * if the corresponding bit in the (32-bit) control field *must* be on, and a + * bit in the high half is on if the corresponding bit in the control field + * may be on. See also vmx_control_verify(). + */ +void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) +{ + struct nested_vmx_msrs *msrs = &vmcs_conf->nested; + + /* + * Note that as a general rule, the high half of the MSRs (bits in + * the control fields which may be 1) should be initialized by the + * intersection of the underlying hardware's MSR (i.e., features which + * can be supported) and the list of features we want to expose - + * because they are known to be properly supported in our code. + * Also, usually, the low half of the MSRs (bits which must be 1) can + * be set to 0, meaning that L1 may turn off any of these bits. The + * 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_l1_wants_exit() will not pass related exits to L1. + * These rules have exceptions below. + */ + nested_vmx_setup_pinbased_ctls(vmcs_conf, msrs); + + nested_vmx_setup_exit_ctls(vmcs_conf, msrs); + + nested_vmx_setup_entry_ctls(vmcs_conf, msrs); + + nested_vmx_setup_cpubased_ctls(vmcs_conf, msrs); + + nested_vmx_setup_secondary_ctls(ept_caps, vmcs_conf, msrs); + + nested_vmx_setup_misc_data(vmcs_conf, msrs); + + nested_vmx_setup_basic(msrs); + + nested_vmx_setup_cr_fixed(msrs); msrs->vmcs_enum = nested_vmx_calc_vmcs_enum_msr(); } @@ -6700,8 +7432,8 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) exit_handlers[EXIT_REASON_VMREAD] = handle_vmread; exit_handlers[EXIT_REASON_VMRESUME] = handle_vmresume; exit_handlers[EXIT_REASON_VMWRITE] = handle_vmwrite; - exit_handlers[EXIT_REASON_VMOFF] = handle_vmoff; - exit_handlers[EXIT_REASON_VMON] = handle_vmon; + exit_handlers[EXIT_REASON_VMOFF] = handle_vmxoff; + exit_handlers[EXIT_REASON_VMON] = handle_vmxon; exit_handlers[EXIT_REASON_INVEPT] = handle_invept; exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid; exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc; @@ -6710,13 +7442,18 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) } struct kvm_x86_nested_ops vmx_nested_ops = { + .leave_nested = vmx_leave_nested, + .is_exception_vmexit = nested_vmx_is_exception_vmexit, .check_events = vmx_check_nested_events, - .hv_timer_pending = nested_vmx_preemption_timer_pending, + .has_events = vmx_has_nested_events, .triple_fault = nested_vmx_triple_fault, .get_state = vmx_get_nested_state, .set_state = vmx_set_nested_state, .get_nested_state_pages = vmx_get_nested_state_pages, .write_log_dirty = nested_vmx_write_pml_buffer, +#ifdef CONFIG_KVM_HYPERV .enable_evmcs = nested_enable_evmcs, .get_evmcs_version = nested_get_evmcs_version, + .hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush, +#endif }; |