diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/cpuid.c | 104 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 19 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 15 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.c | 7 | ||||
-rw-r--r-- | arch/x86/kvm/svm/avic.c | 93 | ||||
-rw-r--r-- | arch/x86/kvm/svm/nested.c | 35 | ||||
-rw-r--r-- | arch/x86/kvm/svm/sev.c | 9 | ||||
-rw-r--r-- | arch/x86/kvm/svm/svm.c | 288 | ||||
-rw-r--r-- | arch/x86/kvm/svm/svm.h | 22 | ||||
-rw-r--r-- | arch/x86/kvm/svm/svm_onhyperv.h | 12 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/capabilities.h | 1 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/evmcs.c | 4 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/evmcs.h | 48 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/nested.c | 93 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmcs12.c | 4 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmcs12.h | 6 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 97 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.h | 5 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 161 | ||||
-rw-r--r-- | arch/x86/kvm/x86.h | 45 | ||||
-rw-r--r-- | arch/x86/kvm/xen.c | 107 |
21 files changed, 749 insertions, 426 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 3902c28fb6cb..b8f8d268d058 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -133,6 +133,7 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 orig = &vcpu->arch.cpuid_entries[i]; if (e2[i].function != orig->function || e2[i].index != orig->index || + e2[i].flags != orig->flags || e2[i].eax != orig->eax || e2[i].ebx != orig->ebx || e2[i].ecx != orig->ecx || e2[i].edx != orig->edx) return -EINVAL; @@ -196,10 +197,26 @@ void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) vcpu->arch.pv_cpuid.features = best->eax; } +/* + * Calculate guest's supported XCR0 taking into account guest CPUID data and + * supported_xcr0 (comprised of host configuration and KVM_SUPPORTED_XCR0). + */ +static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent) +{ + struct kvm_cpuid_entry2 *best; + + best = cpuid_entry2_find(entries, nent, 0xd, 0); + if (!best) + return 0; + + return (best->eax | ((u64)best->edx << 32)) & supported_xcr0; +} + static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries, int nent) { struct kvm_cpuid_entry2 *best; + u64 guest_supported_xcr0 = cpuid_get_supported_xcr0(entries, nent); best = cpuid_entry2_find(entries, nent, 1, 0); if (best) { @@ -238,6 +255,21 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT); } + + /* + * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate + * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's + * requested XCR0 value. The enclave's XFRM must be a subset of XCRO + * at the time of EENTER, thus adjust the allowed XFRM by the guest's + * supported XCR0. Similar to XCR0 handling, FP and SSE are forced to + * '1' even on CPUs that don't support XSAVE. + */ + best = cpuid_entry2_find(entries, nent, 0x12, 0x1); + if (best) { + best->ecx &= guest_supported_xcr0 & 0xffffffff; + best->edx &= guest_supported_xcr0 >> 32; + best->ecx |= XFEATURE_MASK_FPSSE; + } } void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) @@ -250,6 +282,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; + u64 guest_supported_xcr0; best = kvm_find_cpuid_entry(vcpu, 1, 0); if (best && apic) { @@ -261,27 +294,10 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_apic_set_version(vcpu); } - best = kvm_find_cpuid_entry(vcpu, 0xD, 0); - if (!best) - vcpu->arch.guest_supported_xcr0 = 0; - else - vcpu->arch.guest_supported_xcr0 = - (best->eax | ((u64)best->edx << 32)) & supported_xcr0; + guest_supported_xcr0 = + cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); - /* - * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate - * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's - * requested XCR0 value. The enclave's XFRM must be a subset of XCRO - * at the time of EENTER, thus adjust the allowed XFRM by the guest's - * supported XCR0. Similar to XCR0 handling, FP and SSE are forced to - * '1' even on CPUs that don't support XSAVE. - */ - best = kvm_find_cpuid_entry(vcpu, 0x12, 0x1); - if (best) { - best->ecx &= vcpu->arch.guest_supported_xcr0 & 0xffffffff; - best->edx &= vcpu->arch.guest_supported_xcr0 >> 32; - best->ecx |= XFEATURE_MASK_FPSSE; - } + vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0; kvm_update_pv_runtime(vcpu); @@ -346,8 +362,14 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, * KVM_SET_CPUID{,2} again. To support this legacy behavior, check * whether the supplied CPUID data is equal to what's already set. */ - if (vcpu->arch.last_vmentry_cpu != -1) - return kvm_cpuid_check_equal(vcpu, e2, nent); + if (vcpu->arch.last_vmentry_cpu != -1) { + r = kvm_cpuid_check_equal(vcpu, e2, nent); + if (r) + return r; + + kvfree(e2); + return 0; + } r = kvm_check_cpuid(vcpu, e2, nent); if (r) @@ -535,12 +557,13 @@ void kvm_set_cpu_caps(void) ); kvm_cpu_cap_mask(CPUID_7_0_EBX, - F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | - F(BMI2) | F(ERMS) | F(INVPCID) | F(RTM) | 0 /*MPX*/ | F(RDSEED) | - F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) | - F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | - F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/ - ); + F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | + F(FDP_EXCPTN_ONLY) | F(SMEP) | F(BMI2) | F(ERMS) | F(INVPCID) | + F(RTM) | F(ZERO_FCS_FDS) | 0 /*MPX*/ | F(AVX512F) | + F(AVX512DQ) | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512IFMA) | + F(CLFLUSHOPT) | F(CLWB) | 0 /*INTEL_PT*/ | F(AVX512PF) | + F(AVX512ER) | F(AVX512CD) | F(SHA_NI) | F(AVX512BW) | + F(AVX512VL)); kvm_cpu_cap_mask(CPUID_7_ECX, F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) | @@ -887,13 +910,14 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) } break; case 0xd: { - u64 guest_perm = xstate_get_guest_group_perm(); + u64 permitted_xcr0 = supported_xcr0 & xstate_get_guest_group_perm(); + u64 permitted_xss = supported_xss; - entry->eax &= supported_xcr0 & guest_perm; - entry->ebx = xstate_required_size(supported_xcr0, false); + entry->eax &= permitted_xcr0; + entry->ebx = xstate_required_size(permitted_xcr0, false); entry->ecx = entry->ebx; - entry->edx &= (supported_xcr0 & guest_perm) >> 32; - if (!supported_xcr0) + entry->edx &= permitted_xcr0 >> 32; + if (!permitted_xcr0) break; entry = do_host_cpuid(array, function, 1); @@ -902,20 +926,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) cpuid_entry_override(entry, CPUID_D_1_EAX); if (entry->eax & (F(XSAVES)|F(XSAVEC))) - entry->ebx = xstate_required_size(supported_xcr0 | supported_xss, + entry->ebx = xstate_required_size(permitted_xcr0 | permitted_xss, true); else { - WARN_ON_ONCE(supported_xss != 0); + WARN_ON_ONCE(permitted_xss != 0); entry->ebx = 0; } - entry->ecx &= supported_xss; - entry->edx &= supported_xss >> 32; + entry->ecx &= permitted_xss; + entry->edx &= permitted_xss >> 32; for (i = 2; i < 64; ++i) { bool s_state; - if (supported_xcr0 & BIT_ULL(i)) + if (permitted_xcr0 & BIT_ULL(i)) s_state = false; - else if (supported_xss & BIT_ULL(i)) + else if (permitted_xss & BIT_ULL(i)) s_state = true; else continue; @@ -929,7 +953,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * invalid sub-leafs. Only valid sub-leafs should * reach this point, and they should have a non-zero * save state size. Furthermore, check whether the - * processor agrees with supported_xcr0/supported_xss + * processor agrees with permitted_xcr0/permitted_xss * on whether this is an XCR0- or IA32_XSS-managed area. */ if (WARN_ON_ONCE(!entry->eax || (entry->ecx & 0x1) != s_state)) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index baca9fa37a91..9322e6340a74 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1096,14 +1096,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic->regs + APIC_TMR); } - if (static_call(kvm_x86_deliver_posted_interrupt)(vcpu, vector)) { - kvm_lapic_set_irr(vector, apic); - kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_vcpu_kick(vcpu); - } else { - trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, - trig_mode, vector); - } + static_call(kvm_x86_deliver_interrupt)(apic, delivery_mode, + trig_mode, vector); break; case APIC_DM_REMRD: @@ -2312,7 +2306,12 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) apic->irr_pending = true; apic->isr_count = 1; } else { - apic->irr_pending = (apic_search_irr(apic) != -1); + /* + * Don't clear irr_pending, searching the IRR can race with + * updates from the CPU as APICv is still active from hardware's + * perspective. The flag will be cleared as appropriate when + * KVM injects the interrupt. + */ apic->isr_count = count_vectors(apic->regs + APIC_ISR); } } @@ -2629,7 +2628,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) kvm_apic_set_version(vcpu); apic_update_ppr(apic); - hrtimer_cancel(&apic->lapic_timer.timer); + cancel_apic_timer(apic); apic->lapic_timer.expired_tscdeadline = 0; apic_update_lvtt(apic); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 593093b52395..5628d0ba637e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3565,7 +3565,7 @@ set_root_pgd: out_unlock: write_unlock(&vcpu->kvm->mmu_lock); - return 0; + return r; } static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) @@ -3889,12 +3889,23 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) walk_shadow_page_lockless_end(vcpu); } +static u32 alloc_apf_token(struct kvm_vcpu *vcpu) +{ + /* make sure the token value is not 0 */ + u32 id = vcpu->arch.apf.id; + + if (id << 12 == 0) + vcpu->arch.apf.id = 1; + + return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; +} + static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, gfn_t gfn) { struct kvm_arch_async_pf arch; - arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; + arch.token = alloc_apf_token(vcpu); arch.gfn = gfn; arch.direct_map = vcpu->arch.mmu->direct_map; arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index f614f95acc6b..b1a02993782b 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -95,7 +95,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event, } static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, - unsigned config, bool exclude_user, + u64 config, bool exclude_user, bool exclude_kernel, bool intr, bool in_tx, bool in_tx_cp) { @@ -181,7 +181,8 @@ static int cmp_u64(const void *a, const void *b) void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) { - unsigned config, type = PERF_TYPE_RAW; + u64 config; + u32 type = PERF_TYPE_RAW; struct kvm *kvm = pmc->vcpu->kvm; struct kvm_pmu_event_filter *filter; bool allow_event = true; @@ -220,7 +221,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) } if (type == PERF_TYPE_RAW) - config = eventsel & X86_RAW_EVENT_MASK; + config = eventsel & AMD64_RAW_EVENT_MASK; if (pmc->current_config == eventsel && pmc_resume_counter(pmc)) return; diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 90364d02f22a..fb3e20791338 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -27,20 +27,6 @@ #include "irq.h" #include "svm.h" -#define SVM_AVIC_DOORBELL 0xc001011b - -#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) - -/* - * 0xff is broadcast, so the max index allowed for physical APIC ID - * table is 0xfe. APIC IDs above 0xff are reserved. - */ -#define AVIC_MAX_PHYSICAL_ID_COUNT 255 - -#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 -#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 -#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF - /* AVIC GATAG is encoded using VM and VCPU IDs */ #define AVIC_VCPU_ID_BITS 8 #define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) @@ -73,12 +59,6 @@ struct amd_svm_iommu_ir { void *data; /* Storing pointer to struct amd_ir_data */ }; -enum avic_ipi_failure_cause { - AVIC_IPI_FAILURE_INVALID_INT_TYPE, - AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, - AVIC_IPI_FAILURE_INVALID_TARGET, - AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, -}; /* Note: * This function is called from IOMMU driver to notify @@ -289,6 +269,22 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } +void avic_ring_doorbell(struct kvm_vcpu *vcpu) +{ + /* + * Note, the vCPU could get migrated to a different pCPU at any point, + * which could result in signalling the wrong/previous pCPU. But if + * that happens the vCPU is guaranteed to do a VMRUN (after being + * migrated) and thus will process pending interrupts, i.e. a doorbell + * is not needed (and the spurious one is harmless). + */ + int cpu = READ_ONCE(vcpu->cpu); + + if (cpu != get_cpu()) + wrmsrl(MSR_AMD64_SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); + put_cpu(); +} + static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh) { @@ -304,8 +300,13 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, kvm_for_each_vcpu(i, vcpu, kvm) { if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK, GET_APIC_DEST_FIELD(icrh), - icrl & APIC_DEST_MASK)) - kvm_vcpu_wake_up(vcpu); + icrl & APIC_DEST_MASK)) { + vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); + } } } @@ -345,8 +346,6 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh); break; case AVIC_IPI_FAILURE_INVALID_TARGET: - WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n", - index, vcpu->vcpu_id, icrh, icrl); break; case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); @@ -669,52 +668,6 @@ void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) -{ - if (!vcpu->arch.apicv_active) - return -1; - - kvm_lapic_set_irr(vec, vcpu->arch.apic); - - /* - * Pairs with the smp_mb_*() after setting vcpu->guest_mode in - * vcpu_enter_guest() to ensure the write to the vIRR is ordered before - * the read of guest_mode, which guarantees that either VMRUN will see - * and process the new vIRR entry, or that the below code will signal - * the doorbell if the vCPU is already running in the guest. - */ - smp_mb__after_atomic(); - - /* - * Signal the doorbell to tell hardware to inject the IRQ if the vCPU - * is in the guest. If the vCPU is not in the guest, hardware will - * automatically process AVIC interrupts at VMRUN. - */ - if (vcpu->mode == IN_GUEST_MODE) { - int cpu = READ_ONCE(vcpu->cpu); - - /* - * Note, the vCPU could get migrated to a different pCPU at any - * point, which could result in signalling the wrong/previous - * pCPU. But if that happens the vCPU is guaranteed to do a - * VMRUN (after being migrated) and thus will process pending - * interrupts, i.e. a doorbell is not needed (and the spurious - * one is harmless). - */ - if (cpu != get_cpu()) - wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); - put_cpu(); - } else { - /* - * Wake the vCPU if it was blocking. KVM will then detect the - * pending IRQ when checking if the vCPU has a wake event. - */ - kvm_vcpu_wake_up(vcpu); - } - - return 0; -} - bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) { return false; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index cf206855ebf0..39d280e7e80e 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -983,9 +983,9 @@ void svm_free_nested(struct vcpu_svm *svm) /* * Forcibly leave nested mode in order to be able to reset the VCPU later on. */ -void svm_leave_nested(struct vcpu_svm *svm) +void svm_leave_nested(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu = &svm->vcpu; + struct vcpu_svm *svm = to_svm(vcpu); if (is_guest_mode(vcpu)) { svm->nested.nested_run_pending = 0; @@ -1411,7 +1411,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) { - svm_leave_nested(svm); + svm_leave_nested(vcpu); svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); return 0; } @@ -1457,18 +1457,6 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, !__nested_vmcb_check_save(vcpu, &save_cached)) goto out_free; - /* - * While the nested guest CR3 is already checked and set by - * KVM_SET_SREGS, it was set when nested state was yet loaded, - * thus MMU might not be initialized correctly. - * Set it again to fix this. - */ - - ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, - nested_npt_enabled(svm), false); - if (WARN_ON_ONCE(ret)) - goto out_free; - /* * All checks done, we can enter guest mode. Userspace provides @@ -1478,7 +1466,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, */ if (is_guest_mode(vcpu)) - svm_leave_nested(svm); + svm_leave_nested(vcpu); else svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save; @@ -1494,6 +1482,20 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm_switch_vmcb(svm, &svm->nested.vmcb02); nested_vmcb02_prepare_control(svm); + + /* + * While the nested guest CR3 is already checked and set by + * KVM_SET_SREGS, it was set when nested state was yet loaded, + * thus MMU might not be initialized correctly. + * Set it again to fix this. + */ + + ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, + nested_npt_enabled(svm), false); + if (WARN_ON_ONCE(ret)) + goto out_free; + + kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); ret = 0; out_free: @@ -1532,6 +1534,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) } struct kvm_x86_nested_ops svm_nested_ops = { + .leave_nested = svm_leave_nested, .check_events = svm_check_nested_events, .triple_fault = nested_svm_triple_fault, .get_nested_state_pages = svm_get_nested_state_pages, diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 6a22798eaaee..17b53457d866 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2100,8 +2100,13 @@ void __init sev_hardware_setup(void) if (!sev_enabled || !npt_enabled) goto out; - /* Does the CPU support SEV? */ - if (!boot_cpu_has(X86_FEATURE_SEV)) + /* + * SEV must obviously be supported in hardware. Sanity check that the + * CPU supports decode assists, which is mandatory for SEV guests to + * support instruction emulation. + */ + if (!boot_cpu_has(X86_FEATURE_SEV) || + WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS))) goto out; /* Retrieve SEV CPUID information */ diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2c99b18d76c0..fd3a00c892c7 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -290,7 +290,7 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) if ((old_efer & EFER_SVME) != (efer & EFER_SVME)) { if (!(efer & EFER_SVME)) { - svm_leave_nested(svm); + svm_leave_nested(vcpu); svm_set_gif(svm, true); /* #GP intercept is still needed for vmware backdoor */ if (!enable_vmware_backdoor) @@ -312,7 +312,11 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) return ret; } - if (svm_gp_erratum_intercept) + /* + * Never intercept #GP for SEV guests, KVM can't + * decrypt guest memory to workaround the erratum. + */ + if (svm_gp_erratum_intercept && !sev_guest(vcpu->kvm)) set_exception_intercept(svm, GP_VECTOR); } } @@ -1010,9 +1014,10 @@ static void init_vmcb(struct kvm_vcpu *vcpu) * Guest access to VMware backdoor ports could legitimately * trigger #GP because of TSS I/O permission bitmap. * We intercept those #GP and allow access to them anyway - * as VMware does. + * as VMware does. Don't intercept #GP for SEV guests as KVM can't + * decrypt guest memory to decode the faulting instruction. */ - if (enable_vmware_backdoor) + if (enable_vmware_backdoor && !sev_guest(vcpu->kvm)) set_exception_intercept(svm, GP_VECTOR); svm_set_intercept(svm, INTERCEPT_INTR); @@ -1580,6 +1585,7 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_svm *svm = to_svm(vcpu); u64 hcr0 = cr0; + bool old_paging = is_paging(vcpu); #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) { @@ -1596,8 +1602,11 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) #endif vcpu->arch.cr0 = cr0; - if (!npt_enabled) + if (!npt_enabled) { hcr0 |= X86_CR0_PG | X86_CR0_WP; + if (old_paging != is_paging(vcpu)) + svm_set_cr4(vcpu, kvm_read_cr4(vcpu)); + } /* * re-enable caching here because the QEMU bios @@ -1641,8 +1650,12 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) svm_flush_tlb(vcpu); vcpu->arch.cr4 = cr4; - if (!npt_enabled) + if (!npt_enabled) { cr4 |= X86_CR4_PAE; + + if (!is_paging(vcpu)) + cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE); + } cr4 |= host_cr4_mce; to_svm(vcpu)->vmcb->save.cr4 = cr4; vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); @@ -2091,10 +2104,6 @@ static int gp_interception(struct kvm_vcpu *vcpu) if (error_code) goto reinject; - /* All SVM instructions expect page aligned RAX */ - if (svm->vmcb->save.rax & ~PAGE_MASK) - goto reinject; - /* Decode the instruction for usage later */ if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK) goto reinject; @@ -2112,8 +2121,13 @@ static int gp_interception(struct kvm_vcpu *vcpu) if (!is_guest_mode(vcpu)) return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP | EMULTYPE_NO_DECODE); - } else + } else { + /* All SVM instructions expect page aligned RAX */ + if (svm->vmcb->save.rax & ~PAGE_MASK) + goto reinject; + return emulate_svm_instr(vcpu, opcode); + } reinject: kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); @@ -2679,8 +2693,23 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) u64 data = msr->data; switch (ecx) { case MSR_AMD64_TSC_RATIO: - if (!msr->host_initiated && !svm->tsc_scaling_enabled) - return 1; + + if (!svm->tsc_scaling_enabled) { + + if (!msr->host_initiated) + return 1; + /* + * In case TSC scaling is not enabled, always + * leave this MSR at the default value. + * + * Due to bug in qemu 6.2.0, it would try to set + * this msr to 0 if tsc scaling is not enabled. + * Ignore this value as well. + */ + if (data != 0 && data != svm->tsc_ratio_msr) + return 1; + break; + } if (data & TSC_RATIO_RSVD) return 1; @@ -3285,6 +3314,55 @@ static void svm_set_irq(struct kvm_vcpu *vcpu) SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; } +void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vector) +{ + /* + * vcpu->arch.apicv_active must be read after vcpu->mode. + * Pairs with smp_store_release in vcpu_enter_guest. + */ + bool in_guest_mode = (smp_load_acquire(&vcpu->mode) == IN_GUEST_MODE); + + if (!READ_ONCE(vcpu->arch.apicv_active)) { + /* Process the interrupt via inject_pending_event */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + return; + } + + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector); + if (in_guest_mode) { + /* + * Signal the doorbell to tell hardware to inject the IRQ. If + * the vCPU exits the guest before the doorbell chimes, hardware + * will automatically process AVIC interrupts at the next VMRUN. + */ + avic_ring_doorbell(vcpu); + } else { + /* + * Wake the vCPU if it was blocking. KVM will then detect the + * pending IRQ when checking if the vCPU has a wake event. + */ + kvm_vcpu_wake_up(vcpu); + } +} + +static void svm_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) +{ + kvm_lapic_set_irr(vector, apic); + + /* + * Pairs with the smp_mb_*() after setting vcpu->guest_mode in + * vcpu_enter_guest() to ensure the write to the vIRR is ordered before + * the read of guest_mode. This guarantees that either VMRUN will see + * and process the new vIRR entry, or that svm_complete_interrupt_delivery + * will signal the doorbell if the CPU has already entered the guest. + */ + smp_mb__after_atomic(); + svm_complete_interrupt_delivery(apic->vcpu, delivery_mode, trig_mode, vector); +} + static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3332,11 +3410,13 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_nmi_blocked(vcpu)) + return 0; + /* An NMI must not be injected into L2 if it's supposed to VM-Exit. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) return -EBUSY; - - return !svm_nmi_blocked(vcpu); + return 1; } static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) @@ -3388,9 +3468,13 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) { struct vcpu_svm *svm = to_svm(vcpu); + if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_interrupt_blocked(vcpu)) + return 0; + /* * An IRQ must not be injected into L2 if it's supposed to VM-Exit, * e.g. if the IRQ arrived asynchronously after checking nested events. @@ -3398,7 +3482,7 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(svm)) return -EBUSY; - return !svm_interrupt_blocked(vcpu); + return 1; } static void svm_enable_irq_window(struct kvm_vcpu *vcpu) @@ -3609,7 +3693,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); unsigned long vmcb_pa = svm->current_vmcb->pa; - kvm_guest_enter_irqoff(); + guest_state_enter_irqoff(); if (sev_es_guest(vcpu->kvm)) { __svm_sev_es_vcpu_run(vmcb_pa); @@ -3629,7 +3713,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) vmload(__sme_page_pa(sd->save_area)); } - kvm_guest_exit_irqoff(); + guest_state_exit_irqoff(); } static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) @@ -4129,11 +4213,14 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_smi_blocked(vcpu)) + return 0; + /* An SMI must not be injected into L2 if it's supposed to VM-Exit. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_smi(svm)) return -EBUSY; - return !svm_smi_blocked(vcpu); + return 1; } static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) @@ -4227,11 +4314,18 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) * Enter the nested guest now */ + vmcb_mark_all_dirty(svm->vmcb01.ptr); + vmcb12 = map.hva; nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); + if (ret) + goto unmap_save; + + svm->nested.nested_run_pending = 1; + unmap_save: kvm_vcpu_unmap(vcpu, &map_save, true); unmap_map: @@ -4252,79 +4346,140 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) } } -static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len) +static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { bool smep, smap, is_user; unsigned long cr4; + u64 error_code; + + /* Emulation is always possible when KVM has access to all guest state. */ + if (!sev_guest(vcpu->kvm)) + return true; + + /* #UD and #GP should never be intercepted for SEV guests. */ + WARN_ON_ONCE(emul_type & (EMULTYPE_TRAP_UD | + EMULTYPE_TRAP_UD_FORCED | + EMULTYPE_VMWARE_GP)); /* - * When the guest is an SEV-ES guest, emulation is not possible. + * Emulation is impossible for SEV-ES guests as KVM doesn't have access + * to guest register state. */ if (sev_es_guest(vcpu->kvm)) return false; /* + * Emulation is possible if the instruction is already decoded, e.g. + * when completing I/O after returning from userspace. + */ + if (emul_type & EMULTYPE_NO_DECODE) + return true; + + /* + * Emulation is possible for SEV guests if and only if a prefilled + * buffer containing the bytes of the intercepted instruction is + * available. SEV guest memory is encrypted with a guest specific key + * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and + * decode garbage. + * + * Inject #UD if KVM reached this point without an instruction buffer. + * In practice, this path should never be hit by a well-behaved guest, + * e.g. KVM doesn't intercept #UD or #GP for SEV guests, but this path + * is still theoretically reachable, e.g. via unaccelerated fault-like + * AVIC access, and needs to be handled by KVM to avoid putting the + * guest into an infinite loop. Injecting #UD is somewhat arbitrary, + * but its the least awful option given lack of insight into the guest. + */ + if (unlikely(!insn)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return false; + } + + /* + * Emulate for SEV guests if the insn buffer is not empty. The buffer + * will be empty if the DecodeAssist microcode cannot fetch bytes for + * the faulting instruction because the code fetch itself faulted, e.g. + * the guest attempted to fetch from emulated MMIO or a guest page + * table used to translate CS:RIP resides in emulated MMIO. + */ + if (likely(insn_len)) + return true; + + /* * Detect and workaround Errata 1096 Fam_17h_00_0Fh. * * Errata: - * When CPU raise #NPF on guest data access and vCPU CR4.SMAP=1, it is - * possible that CPU microcode implementing DecodeAssist will fail - * to read bytes of instruction which caused #NPF. In this case, - * GuestIntrBytes field of the VMCB on a VMEXIT will incorrectly - * return 0 instead of the correct guest instruction bytes. - * - * This happens because CPU microcode reading instruction bytes - * uses a special opcode which attempts to read data using CPL=0 - * privileges. The microcode reads CS:RIP and if it hits a SMAP - * fault, it gives up and returns no instruction bytes. + * When CPU raises #NPF on guest data access and vCPU CR4.SMAP=1, it is + * possible that CPU microcode implementing DecodeAssist will fail to + * read guest memory at CS:RIP and vmcb.GuestIntrBytes will incorrectly + * be '0'. This happens because microcode reads CS:RIP using a _data_ + * loap uop with CPL=0 privileges. If the load hits a SMAP #PF, ucode + * gives up and does not fill the instruction bytes buffer. * - * Detection: - * We reach here in case CPU supports DecodeAssist, raised #NPF and - * returned 0 in GuestIntrBytes field of the VMCB. - * First, errata can only be triggered in case vCPU CR4.SMAP=1. - * Second, if vCPU CR4.SMEP=1, errata could only be triggered - * in case vCPU CPL==3 (Because otherwise guest would have triggered - * a SMEP fault instead of #NPF). - * Otherwise, vCPU CR4.SMEP=0, errata could be triggered by any vCPU CPL. - * As most guests enable SMAP if they have also enabled SMEP, use above - * logic in order to attempt minimize false-positive of detecting errata - * while still preserving all cases semantic correctness. + * As above, KVM reaches this point iff the VM is an SEV guest, the CPU + * supports DecodeAssist, a #NPF was raised, KVM's page fault handler + * triggered emulation (e.g. for MMIO), and the CPU returned 0 in the + * GuestIntrBytes field of the VMCB. * - * Workaround: - * To determine what instruction the guest was executing, the hypervisor - * will have to decode the instruction at the instruction pointer. + * This does _not_ mean that the erratum has been encountered, as the + * DecodeAssist will also fail if the load for CS:RIP hits a legitimate + * #PF, e.g. if the guest attempt to execute from emulated MMIO and + * encountered a reserved/not-present #PF. * - * In non SEV guest, hypervisor will be able to read the guest - * memory to decode the instruction pointer when insn_len is zero - * so we return true to indicate that decoding is possible. + * To hit the erratum, the following conditions must be true: + * 1. CR4.SMAP=1 (obviously). + * 2. CR4.SMEP=0 || CPL=3. If SMEP=1 and CPL<3, the erratum cannot + * have been hit as the guest would have encountered a SMEP + * violation #PF, not a #NPF. + * 3. The #NPF is not due to a code fetch, in which case failure to + * retrieve the instruction bytes is legitimate (see abvoe). * - * But in the SEV guest, the guest memory is encrypted with the - * guest specific key and hypervisor will not be able to decode the - * instruction pointer so we will not able to workaround it. Lets - * print the error and request to kill the guest. - */ - if (likely(!insn || insn_len)) - return true; - - /* - * If RIP is invalid, go ahead with emulation which will cause an - * internal error exit. + * In addition, don't apply the erratum workaround if the #NPF occurred + * while translating guest page tables (see below). */ - if (!kvm_vcpu_gfn_to_memslot(vcpu, kvm_rip_read(vcpu) >> PAGE_SHIFT)) - return true; + error_code = to_svm(vcpu)->vmcb->control.exit_info_1; + if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK)) + goto resume_guest; cr4 = kvm_read_cr4(vcpu); smep = cr4 & X86_CR4_SMEP; smap = cr4 & X86_CR4_SMAP; is_user = svm_get_cpl(vcpu) == 3; if (smap && (!smep || is_user)) { - if (!sev_guest(vcpu->kvm)) - return true; - pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n"); - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + + /* + * If the fault occurred in userspace, arbitrarily inject #GP + * to avoid killing the guest and to hopefully avoid confusing + * the guest kernel too much, e.g. injecting #PF would not be + * coherent with respect to the guest's page tables. Request + * triple fault if the fault occurred in the kernel as there's + * no fault that KVM can inject without confusing the guest. + * In practice, the triple fault is moot as no sane SEV kernel + * will execute from user memory while also running with SMAP=1. + */ + if (is_user) + kvm_inject_gp(vcpu, 0); + else + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); } +resume_guest: + /* + * If the erratum was not hit, simply resume the guest and let it fault + * again. While awful, e.g. the vCPU may get stuck in an infinite loop + * if the fault is at CPL=0, it's the lesser of all evils. Exiting to + * userspace will kill the guest, and letting the emulator read garbage + * will yield random behavior and potentially corrupt the guest. + * + * Simply resuming the guest is technically not a violation of the SEV + * architecture. AMD's APM states that all code fetches and page table + * accesses for SEV guest are encrypted, regardless of the C-Bit. The + * APM also states that encrypted accesses to MMIO are "ignored", but + * doesn't explicitly define "ignored", i.e. doing nothing and letting + * the guest spin is technically "ignoring" the access. + */ return false; } @@ -4478,7 +4633,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .pmu_ops = &amd_pmu_ops, .nested_ops = &svm_nested_ops, - .deliver_posted_interrupt = svm_deliver_avic_intr, + .deliver_interrupt = svm_deliver_interrupt, .dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt, .update_pi_irte = svm_update_pi_irte, .setup_mce = svm_setup_mce, @@ -4555,6 +4710,7 @@ static __init void svm_set_cpu_caps(void) /* CPUID 0x80000001 and 0x8000000A (SVM features) */ if (nested) { kvm_cpu_cap_set(X86_FEATURE_SVM); + kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN); if (nrips) kvm_cpu_cap_set(X86_FEATURE_NRIPS); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 47ef8f4a9358..fa98d6844728 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -304,11 +304,6 @@ static inline void vmcb_mark_all_clean(struct vmcb *vmcb) & ~VMCB_ALWAYS_DIRTY_MASK; } -static inline bool vmcb_is_clean(struct vmcb *vmcb, int bit) -{ - return (vmcb->control.clean & (1 << bit)); -} - static inline void vmcb_mark_dirty(struct vmcb *vmcb, int bit) { vmcb->control.clean &= ~(1 << bit); @@ -494,6 +489,8 @@ void svm_set_gif(struct vcpu_svm *svm, bool value); int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code); void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, int read, int write); +void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vec); /* nested.c */ @@ -525,7 +522,7 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun); -void svm_leave_nested(struct vcpu_svm *svm); +void svm_leave_nested(struct kvm_vcpu *vcpu); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); int nested_svm_vmrun(struct kvm_vcpu *vcpu); @@ -561,17 +558,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops; /* avic.c */ -#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) -#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 -#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) - -#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) -#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) -#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) -#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) - -#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL - int avic_ga_log_notifier(u32 ga_tag); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); @@ -588,12 +574,12 @@ bool svm_check_apicv_inhibit_reasons(ulong bit); void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); -int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec); bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu); int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void avic_vcpu_blocking(struct kvm_vcpu *vcpu); void avic_vcpu_unblocking(struct kvm_vcpu *vcpu); +void avic_ring_doorbell(struct kvm_vcpu *vcpu); /* sev.c */ diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index c53b8bf8d013..489ca56212c6 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -46,6 +46,9 @@ static inline void svm_hv_init_vmcb(struct vmcb *vmcb) if (npt_enabled && ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) hve->hv_enlightenments_control.enlightened_npt_tlb = 1; + + if (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP) + hve->hv_enlightenments_control.msr_bitmap = 1; } static inline void svm_hv_hardware_setup(void) @@ -83,14 +86,7 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments( struct hv_enlightenments *hve = (struct hv_enlightenments *)vmcb->control.reserved_sw; - /* - * vmcb can be NULL if called during early vcpu init. - * And its okay not to mark vmcb dirty during vcpu init - * as we mark it dirty unconditionally towards end of vcpu - * init phase. - */ - if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) && - hve->hv_enlightenments_control.msr_bitmap) + if (hve->hv_enlightenments_control.msr_bitmap) vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); } diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 959b59d13b5a..3f430e218375 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -54,7 +54,6 @@ struct nested_vmx_msrs { struct vmcs_config { int size; - int order; u32 basic_cap; u32 revision_id; u32 pin_based_exec_ctrl; diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index ba6f99f584ac..87e3dc10edf4 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -12,8 +12,6 @@ DEFINE_STATIC_KEY_FALSE(enable_evmcs); -#if IS_ENABLED(CONFIG_HYPERV) - #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) #define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ {EVMCS1_OFFSET(name), clean_field} @@ -296,6 +294,7 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { }; const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); +#if IS_ENABLED(CONFIG_HYPERV) __init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) { vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL; @@ -362,6 +361,7 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) case MSR_IA32_VMX_PROCBASED_CTLS2: ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC; break; + case MSR_IA32_VMX_TRUE_PINBASED_CTLS: case MSR_IA32_VMX_PINBASED_CTLS: ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; break; diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index 16731d2cf231..8d70f9aea94b 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -59,12 +59,12 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); SECONDARY_EXEC_SHADOW_VMCS | \ SECONDARY_EXEC_TSC_SCALING | \ SECONDARY_EXEC_PAUSE_LOOP_EXITING) -#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) +#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) #define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) #define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING) -#if IS_ENABLED(CONFIG_HYPERV) - struct evmcs_field { u16 offset; u16 clean_field; @@ -73,26 +73,56 @@ struct evmcs_field { extern const struct evmcs_field vmcs_field_to_evmcs_1[]; extern const unsigned int nr_evmcs_1_fields; -static __always_inline int get_evmcs_offset(unsigned long field, - u16 *clean_field) +static __always_inline int evmcs_field_offset(unsigned long field, + u16 *clean_field) { unsigned int index = ROL16(field, 6); const struct evmcs_field *evmcs_field; - if (unlikely(index >= nr_evmcs_1_fields)) { - WARN_ONCE(1, "KVM: accessing unsupported EVMCS field %lx\n", - field); + if (unlikely(index >= nr_evmcs_1_fields)) return -ENOENT; - } evmcs_field = &vmcs_field_to_evmcs_1[index]; + /* + * Use offset=0 to detect holes in eVMCS. This offset belongs to + * 'revision_id' but this field has no encoding and is supposed to + * be accessed directly. + */ + if (unlikely(!evmcs_field->offset)) + return -ENOENT; + if (clean_field) *clean_field = evmcs_field->clean_field; return evmcs_field->offset; } +static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, + unsigned long field, u16 offset) +{ + /* + * vmcs12_read_any() doesn't care whether the supplied structure + * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes + * the exact offset of the required field, use it for convenience + * here. + */ + return vmcs12_read_any((void *)evmcs, field, offset); +} + +#if IS_ENABLED(CONFIG_HYPERV) + +static __always_inline int get_evmcs_offset(unsigned long field, + u16 *clean_field) +{ + int offset = evmcs_field_offset(field, clean_field); + + WARN_ONCE(offset < 0, "KVM: accessing unsupported EVMCS field %lx\n", + field); + + return offset; +} + static __always_inline void evmcs_write64(unsigned long field, u64 value) { u16 clean_field; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f235f77cbc03..dc822a1d403d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -7,6 +7,7 @@ #include <asm/mmu_context.h> #include "cpuid.h" +#include "evmcs.h" #include "hyperv.h" #include "mmu.h" #include "nested.h" @@ -245,8 +246,7 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, src = &prev->host_state; dest = &vmx->loaded_vmcs->host_state; - vmx_set_vmcs_host_state(dest, src->cr3, src->fs_sel, src->gs_sel, - src->fs_base, src->gs_base); + vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base); dest->ldt_sel = src->ldt_sel; #ifdef CONFIG_X86_64 dest->ds_sel = src->ds_sel; @@ -3055,7 +3055,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr4; + unsigned long cr3, cr4; bool vm_fail; if (!nested_early_check) @@ -3078,6 +3078,12 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) */ 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); @@ -4851,18 +4857,20 @@ 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; } @@ -5099,27 +5107,49 @@ 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 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); - /* 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 (!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + /* + * 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(vmx->nested.hv_evmcs, field, offset); + } /* * Now copy part of this value to register or memory, as requested. @@ -5214,7 +5244,7 @@ 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); @@ -6462,7 +6492,7 @@ 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)); @@ -6771,6 +6801,7 @@ __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, .check_events = vmx_check_nested_events, .hv_timer_pending = nested_vmx_preemption_timer_pending, .triple_fault = nested_vmx_triple_fault, diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c index cab6ba7a5005..2251b60920f8 100644 --- a/arch/x86/kvm/vmx/vmcs12.c +++ b/arch/x86/kvm/vmx/vmcs12.c @@ -8,7 +8,7 @@ FIELD(number, name), \ [ROL16(number##_HIGH, 6)] = VMCS12_OFFSET(name) + sizeof(u32) -const unsigned short vmcs_field_to_offset_table[] = { +const unsigned short vmcs12_field_offsets[] = { FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id), FIELD(POSTED_INTR_NV, posted_intr_nv), FIELD(GUEST_ES_SELECTOR, guest_es_selector), @@ -151,4 +151,4 @@ const unsigned short vmcs_field_to_offset_table[] = { FIELD(HOST_RSP, host_rsp), FIELD(HOST_RIP, host_rip), }; -const unsigned int nr_vmcs12_fields = ARRAY_SIZE(vmcs_field_to_offset_table); +const unsigned int nr_vmcs12_fields = ARRAY_SIZE(vmcs12_field_offsets); diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index 2a45f026ee11..746129ddd5ae 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -361,10 +361,10 @@ static inline void vmx_check_vmcs12_offsets(void) CHECK_OFFSET(guest_pml_index, 996); } -extern const unsigned short vmcs_field_to_offset_table[]; +extern const unsigned short vmcs12_field_offsets[]; extern const unsigned int nr_vmcs12_fields; -static inline short vmcs_field_to_offset(unsigned long field) +static inline short get_vmcs12_field_offset(unsigned long field) { unsigned short offset; unsigned int index; @@ -377,7 +377,7 @@ static inline short vmcs_field_to_offset(unsigned long field) return -ENOENT; index = array_index_nospec(index, nr_vmcs12_fields); - offset = vmcs_field_to_offset_table[index]; + offset = vmcs12_field_offsets[index]; if (offset == 0) return -ENOENT; return offset; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4ac676066d60..b730d799c26e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1080,14 +1080,9 @@ static void pt_guest_exit(struct vcpu_vmx *vmx) wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); } -void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3, - u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base) +void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base) { - if (unlikely(cr3 != host->cr3)) { - vmcs_writel(HOST_CR3, cr3); - host->cr3 = cr3; - } if (unlikely(fs_sel != host->fs_sel)) { if (!(fs_sel & 7)) vmcs_write16(HOST_FS_SELECTOR, fs_sel); @@ -1182,9 +1177,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) gs_base = segment_base(gs_sel); #endif - vmx_set_vmcs_host_state(host_state, __get_current_cr3_fast(), - fs_sel, gs_sel, fs_base, gs_base); - + vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); vmx->guest_state_loaded = true; } @@ -1487,11 +1480,12 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } -static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len) +static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does - * not point tthe failing instruction, and even if it did, the code + * not point at the failing instruction, and even if it did, the code * stream is inaccessible. Inject #UD instead of exiting to userspace * so that guest userspace can't DoS the guest simply by triggering * emulation (enclaves are CPL3 only). @@ -2603,7 +2597,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, return -EIO; vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->order = get_order(vmcs_conf->size); vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; vmcs_conf->revision_id = vmx_msr_low; @@ -2628,7 +2621,7 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) struct page *pages; struct vmcs *vmcs; - pages = __alloc_pages_node(node, flags, vmcs_config.order); + pages = __alloc_pages_node(node, flags, 0); if (!pages) return NULL; vmcs = page_address(pages); @@ -2647,7 +2640,7 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) void free_vmcs(struct vmcs *vmcs) { - free_pages((unsigned long)vmcs, vmcs_config.order); + free_page((unsigned long)vmcs); } /* @@ -4041,6 +4034,21 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) return 0; } +static void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) +{ + struct kvm_vcpu *vcpu = apic->vcpu; + + if (vmx_deliver_posted_interrupt(vcpu, vector)) { + kvm_lapic_set_irr(vector, apic); + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + } else { + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, + trig_mode, vector); + } +} + /* * Set up the vmcs's constant host-state fields, i.e., host-state fields that * will not change in the lifetime of the guest. @@ -4094,10 +4102,14 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) vmcs_write32(HOST_IA32_SYSENTER_CS, low32); /* - * If 32-bit syscall is enabled, vmx_vcpu_load_vcms rewrites - * HOST_IA32_SYSENTER_ESP. + * SYSENTER is used for 32-bit system calls on either 32-bit or + * 64-bit kernels. It is always zero If neither is allowed, otherwise + * vmx_vcpu_load_vmcs loads it with the per-CPU entry stack (and may + * have already done so!). */ - vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); + if (!IS_ENABLED(CONFIG_IA32_EMULATION) && !IS_ENABLED(CONFIG_X86_32)) + vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); + rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl); vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ @@ -4901,8 +4913,33 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) dr6 = vmx_get_exit_qual(vcpu); if (!(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { + /* + * If the #DB was due to ICEBP, a.k.a. INT1, skip the + * instruction. ICEBP generates a trap-like #DB, but + * despite its interception control being tied to #DB, + * is an instruction intercept, i.e. the VM-Exit occurs + * on the ICEBP itself. Note, skipping ICEBP also + * clears STI and MOVSS blocking. + * + * For all other #DBs, set vmcs.PENDING_DBG_EXCEPTIONS.BS + * if single-step is enabled in RFLAGS and STI or MOVSS + * blocking is active, as the CPU doesn't set the bit + * on VM-Exit due to #DB interception. VM-Entry has a + * consistency check that a single-step #DB is pending + * in this scenario as the previous instruction cannot + * have toggled RFLAGS.TF 0=>1 (because STI and POP/MOV + * don't modify RFLAGS), therefore the one instruction + * delay when activating single-step breakpoints must + * have already expired. Note, the CPU sets/clears BS + * as appropriate for all other VM-Exits types. + */ if (is_icebp(intr_info)) WARN_ON(!skip_emulated_instruction(vcpu)); + else if ((vmx_get_rflags(vcpu) & X86_EFLAGS_TF) && + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS))) + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, + vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS) | DR6_BS); kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); return 1; @@ -5397,7 +5434,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { gpa_t gpa; - if (!vmx_can_emulate_instruction(vcpu, NULL, 0)) + if (!vmx_can_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) return 1; /* @@ -6725,7 +6762,7 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - kvm_guest_enter_irqoff(); + guest_state_enter_irqoff(); /* L1D Flush includes CPU buffer clear to mitigate MDS */ if (static_branch_unlikely(&vmx_l1d_should_flush)) @@ -6741,13 +6778,13 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vcpu->arch.cr2 = native_read_cr2(); - kvm_guest_exit_irqoff(); + guest_state_exit_irqoff(); } static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr4; + unsigned long cr3, cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && @@ -6790,6 +6827,19 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); vcpu->arch.regs_dirty = 0; + /* + * Refresh vmcs.HOST_CR3 if necessary. This must be done immediately + * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time + * it switches back to the current->mm, which can occur in KVM context + * when switching to a temporary mm to patch kernel code, e.g. if KVM + * toggles a static key while handling a VM-Exit. + */ + 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); @@ -7615,6 +7665,7 @@ static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) if (ret) return ret; + vmx->nested.nested_run_pending = 1; vmx->nested.smm.guest_mode = false; } return 0; @@ -7739,7 +7790,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .hwapic_isr_update = vmx_hwapic_isr_update, .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_posted_interrupt = vmx_deliver_posted_interrupt, + .deliver_interrupt = vmx_deliver_interrupt, .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, .set_tss_addr = vmx_set_tss_addr, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7f2c82e7f38f..9c6bfcd84008 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -374,9 +374,8 @@ int allocate_vpid(void); void free_vpid(int vpid); void vmx_set_constant_host_state(struct vcpu_vmx *vmx); void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); -void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3, - u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base); +void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base); int vmx_get_cpl(struct kvm_vcpu *vcpu); bool vmx_emulation_required(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9e43d756312f..eb4029660bd9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -90,6 +90,8 @@ u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P; EXPORT_SYMBOL_GPL(kvm_mce_cap_supported); +#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) + #define emul_to_vcpu(ctxt) \ ((struct kvm_vcpu *)(ctxt)->vcpu) @@ -982,6 +984,18 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); +static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.guest_fpu.fpstate->user_xfeatures; +} + +#ifdef CONFIG_X86_64 +static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) +{ + return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC; +} +#endif + static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0 = xcr; @@ -1001,7 +1015,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ - valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; + valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; @@ -2349,10 +2363,12 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) return tsc; } +#ifdef CONFIG_X86_64 static inline int gtod_is_based_on_tsc(int mode) { return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; } +#endif static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) { @@ -3535,6 +3551,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~supported_xss) return 1; vcpu->arch.ia32_xss = data; + kvm_update_cpuid_runtime(vcpu); break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) @@ -3703,8 +3720,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; - if (data & ~(XFEATURE_MASK_USER_DYNAMIC & - vcpu->arch.guest_supported_xcr0)) + if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data); @@ -3714,8 +3730,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; - if (data & ~(XFEATURE_MASK_USER_DYNAMIC & - vcpu->arch.guest_supported_xcr0)) + if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; vcpu->arch.guest_fpu.xfd_err = data; @@ -4229,6 +4244,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SREGS2: case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: + case KVM_CAP_SYS_ATTRIBUTES: + case KVM_CAP_ENABLE_CAP: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -4331,7 +4348,49 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; } return r; +} + +static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr) +{ + void __user *uaddr = (void __user*)(unsigned long)attr->addr; + if ((u64)(unsigned long)uaddr != attr->addr) + return ERR_PTR_USR(-EFAULT); + return uaddr; +} + +static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) +{ + u64 __user *uaddr = kvm_get_attr_addr(attr); + + if (attr->group) + return -ENXIO; + + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); + + switch (attr->attr) { + case KVM_X86_XCOMP_GUEST_SUPP: + if (put_user(supported_xcr0, uaddr)) + return -EFAULT; + return 0; + default: + return -ENXIO; + break; + } +} + +static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr) +{ + if (attr->group) + return -ENXIO; + + switch (attr->attr) { + case KVM_X86_XCOMP_GUEST_SUPP: + return 0; + default: + return -ENXIO; + } } long kvm_arch_dev_ioctl(struct file *filp, @@ -4422,6 +4481,22 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; + case KVM_GET_DEVICE_ATTR: { + struct kvm_device_attr attr; + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_x86_dev_get_attr(&attr); + break; + } + case KVM_HAS_DEVICE_ATTR: { + struct kvm_device_attr attr; + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_x86_dev_has_attr(&attr); + break; + } default: r = -EINVAL; break; @@ -4860,8 +4935,10 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { - if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) + if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { + kvm_x86_ops.nested_ops->leave_nested(vcpu); kvm_smm_changed(vcpu, events->smi.smm); + } vcpu->arch.smi_pending = events->smi.pending; @@ -5022,11 +5099,11 @@ static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr; + u64 __user *uaddr = kvm_get_attr_addr(attr); int r; - if ((u64)(unsigned long)uaddr != attr->addr) - return -EFAULT; + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: @@ -5045,12 +5122,12 @@ static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr; + u64 __user *uaddr = kvm_get_attr_addr(attr); struct kvm *kvm = vcpu->kvm; int r; - if ((u64)(unsigned long)uaddr != attr->addr) - return -EFAULT; + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: { @@ -6810,6 +6887,13 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, } EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); +static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) +{ + return static_call(kvm_x86_can_emulate_instruction)(vcpu, emul_type, + insn, insn_len); +} + int handle_ud(struct kvm_vcpu *vcpu) { static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX }; @@ -6817,7 +6901,7 @@ int handle_ud(struct kvm_vcpu *vcpu) char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; - if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, NULL, 0))) + if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0))) return 1; if (force_emulation_prefix && @@ -8193,7 +8277,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool writeback = true; bool write_fault_to_spt; - if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, insn, insn_len))) + if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len))) return 1; vcpu->arch.l1tf_flush_l1d = true; @@ -8871,6 +8955,13 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) return -KVM_EOPNOTSUPP; + /* + * When tsc is in permanent catchup mode guests won't be able to use + * pvclock_read_retry loop to get consistent view of pvclock + */ + if (vcpu->arch.tsc_always_catchup) + return -KVM_EOPNOTSUPP; + if (!kvm_get_walltime_and_clockread(&ts, &cycle)) return -KVM_EOPNOTSUPP; @@ -9089,6 +9180,7 @@ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) likely(!pic_in_kernel(vcpu->kvm)); } +/* Called within kvm->srcu read side. */ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; @@ -9097,16 +9189,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); - /* - * The call to kvm_ready_for_interrupt_injection() may end up in - * kvm_xen_has_interrupt() which may require the srcu lock to be - * held, to protect against changes in the vcpu_info address. - */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; @@ -9706,7 +9791,7 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); } -void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) +static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) return; @@ -9724,6 +9809,7 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); /* + * Called within kvm->srcu read side. * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the * userspace. @@ -9912,7 +9998,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * result in virtual interrupt delivery. */ local_irq_disable(); - vcpu->mode = IN_GUEST_MODE; + + /* Store vcpu->apicv_active before vcpu->mode. */ + smp_store_release(&vcpu->mode, IN_GUEST_MODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -9972,6 +10060,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(0, 7); } + guest_timing_enter_irqoff(); + for (;;) { /* * Assert that vCPU vs. VM APICv state is consistent. An APICv @@ -10056,7 +10146,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * of accounting via context tracking, but the loss of accuracy is * acceptable for all known use cases. */ - vtime_account_guest_exit(); + guest_timing_exit_irqoff(); if (lapic_in_kernel(vcpu)) { s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta; @@ -10098,6 +10188,7 @@ out: return r; } +/* Called within kvm->srcu read side. */ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { bool hv_timer; @@ -10157,12 +10248,12 @@ static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) !vcpu->arch.apf.halted); } +/* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; struct kvm *kvm = vcpu->kvm; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); vcpu->arch.l1tf_flush_l1d = true; for (;;) { @@ -10190,14 +10281,12 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (__xfer_to_guest_mode_work_pending()) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); r = xfer_to_guest_mode_handle_work(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (r) return r; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); } } - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - return r; } @@ -10303,6 +10392,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; + struct kvm *kvm = vcpu->kvm; int r; vcpu_load(vcpu); @@ -10310,6 +10400,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (kvm_run->immediate_exit) { r = -EINTR; @@ -10320,7 +10411,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * use before KVM has ever run the vCPU. */ WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); + + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + if (kvm_apic_accept_events(vcpu) < 0) { r = 0; goto out; @@ -10380,8 +10475,9 @@ out: if (kvm_run->kvm_valid_regs) store_regs(vcpu); post_kvm_run_save(vcpu); - kvm_sigset_deactivate(vcpu); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); return r; } @@ -11209,7 +11305,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.msr_misc_features_enables = 0; - vcpu->arch.xcr0 = XFEATURE_MASK_FP; + __kvm_set_xcr(vcpu, 0, XFEATURE_MASK_FP); + __kvm_set_msr(vcpu, MSR_IA32_XSS, 0, true); } /* All GPRs except RDX (handled below) are zeroed on RESET/INIT. */ @@ -11226,8 +11323,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1, 0); kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600); - vcpu->arch.ia32_xss = 0; - static_call(kvm_x86_vcpu_reset)(vcpu, init_event); kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); @@ -11571,8 +11666,6 @@ void kvm_arch_sync_events(struct kvm *kvm) kvm_free_pit(kvm); } -#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) - /** * __x86_set_memory_region: Setup KVM internal memory slot * diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 635b75f9e145..767ec7f99516 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -10,51 +10,6 @@ void kvm_spurious_fault(void); -static __always_inline void kvm_guest_enter_irqoff(void) -{ - /* - * VMENTER enables interrupts (host state), but the kernel state is - * interrupts disabled when this is invoked. Also tell RCU about - * it. This is the same logic as for exit_to_user_mode(). - * - * This ensures that e.g. latency analysis on the host observes - * guest mode as interrupt enabled. - * - * guest_enter_irqoff() informs context tracking about the - * transition to guest mode and if enabled adjusts RCU state - * accordingly. - */ - instrumentation_begin(); - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); - instrumentation_end(); - - guest_enter_irqoff(); - lockdep_hardirqs_on(CALLER_ADDR0); -} - -static __always_inline void kvm_guest_exit_irqoff(void) -{ - /* - * VMEXIT disables interrupts (host state), but tracing and lockdep - * have them in state 'on' as recorded before entering guest mode. - * Same as enter_from_user_mode(). - * - * context_tracking_guest_exit() restores host context and reinstates - * RCU if enabled and required. - * - * This needs to be done immediately after VM-Exit, before any code - * that might contain tracepoints or call out to the greater world, - * e.g. before x86_spec_ctrl_restore_host(). - */ - lockdep_hardirqs_off(CALLER_ADDR0); - context_tracking_guest_exit(); - - instrumentation_begin(); - trace_hardirqs_off_finish(); - instrumentation_end(); -} - #define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check) \ ({ \ bool failed = (consistency_check); \ diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 0e3f7d6e9fd7..74be1fda58e3 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -133,32 +133,57 @@ static void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) { struct kvm_vcpu_xen *vx = &v->arch.xen; + struct gfn_to_hva_cache *ghc = &vx->runstate_cache; + struct kvm_memslots *slots = kvm_memslots(v->kvm); + bool atomic = (state == RUNSTATE_runnable); uint64_t state_entry_time; - unsigned int offset; + int __user *user_state; + uint64_t __user *user_times; kvm_xen_update_runstate(v, state); if (!vx->runstate_set) return; - BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + if (unlikely(slots->generation != ghc->generation || kvm_is_error_hva(ghc->hva)) && + kvm_gfn_to_hva_cache_init(v->kvm, ghc, ghc->gpa, ghc->len)) + return; + + /* We made sure it fits in a single page */ + BUG_ON(!ghc->memslot); + + if (atomic) + pagefault_disable(); - offset = offsetof(struct compat_vcpu_runstate_info, state_entry_time); -#ifdef CONFIG_X86_64 /* - * The only difference is alignment of uint64_t in 32-bit. - * So the first field 'state' is accessed directly using - * offsetof() (where its offset happens to be zero), while the - * remaining fields which are all uint64_t, start at 'offset' - * which we tweak here by adding 4. + * The only difference between 32-bit and 64-bit versions of the + * runstate struct us the alignment of uint64_t in 32-bit, which + * means that the 64-bit version has an additional 4 bytes of + * padding after the first field 'state'. + * + * So we use 'int __user *user_state' to point to the state field, + * and 'uint64_t __user *user_times' for runstate_entry_time. So + * the actual array of time[] in each state starts at user_times[1]. */ + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != 0); + BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state) != 0); + user_state = (int __user *)ghc->hva; + + BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + + user_times = (uint64_t __user *)(ghc->hva + + offsetof(struct compat_vcpu_runstate_info, + state_entry_time)); +#ifdef CONFIG_X86_64 BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) != offsetof(struct compat_vcpu_runstate_info, state_entry_time) + 4); BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, time) != offsetof(struct compat_vcpu_runstate_info, time) + 4); if (v->kvm->arch.xen.long_mode) - offset = offsetof(struct vcpu_runstate_info, state_entry_time); + user_times = (uint64_t __user *)(ghc->hva + + offsetof(struct vcpu_runstate_info, + state_entry_time)); #endif /* * First write the updated state_entry_time at the appropriate @@ -172,10 +197,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) != sizeof(state_entry_time)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &state_entry_time, offset, - sizeof(state_entry_time))) - return; + if (__put_user(state_entry_time, user_times)) + goto out; smp_wmb(); /* @@ -189,11 +212,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) != sizeof(vx->current_runstate)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &vx->current_runstate, - offsetof(struct vcpu_runstate_info, state), - sizeof(vx->current_runstate))) - return; + if (__put_user(vx->current_runstate, user_state)) + goto out; /* * Write the actual runstate times immediately after the @@ -208,24 +228,23 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) != sizeof(vx->runstate_times)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &vx->runstate_times[0], - offset + sizeof(u64), - sizeof(vx->runstate_times))) - return; - + if (__copy_to_user(user_times + 1, vx->runstate_times, sizeof(vx->runstate_times))) + goto out; smp_wmb(); /* * Finally, clear the XEN_RUNSTATE_UPDATE bit in the guest's * runstate_entry_time field. */ - state_entry_time &= ~XEN_RUNSTATE_UPDATE; - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &state_entry_time, offset, - sizeof(state_entry_time))) - return; + __put_user(state_entry_time, user_times); + smp_wmb(); + + out: + mark_page_dirty_in_slot(v->kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT); + + if (atomic) + pagefault_enable(); } int __kvm_xen_has_interrupt(struct kvm_vcpu *v) @@ -316,10 +335,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) "\tnotq %0\n" "\t" LOCK_PREFIX "andq %0, %2\n" "2:\n" - "\t.section .fixup,\"ax\"\n" - "3:\tjmp\t2b\n" - "\t.previous\n" - _ASM_EXTABLE_UA(1b, 3b) + _ASM_EXTABLE_UA(1b, 2b) : "=r" (evtchn_pending_sel), "+m" (vi->evtchn_pending_sel), "+m" (v->arch.xen.evtchn_pending_sel) @@ -335,10 +351,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) "\tnotl %0\n" "\t" LOCK_PREFIX "andl %0, %2\n" "2:\n" - "\t.section .fixup,\"ax\"\n" - "3:\tjmp\t2b\n" - "\t.previous\n" - _ASM_EXTABLE_UA(1b, 3b) + _ASM_EXTABLE_UA(1b, 2b) : "=r" (evtchn_pending_sel32), "+m" (vi->evtchn_pending_sel), "+m" (v->arch.xen.evtchn_pending_sel) @@ -449,6 +462,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct vcpu_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache, data->u.gpa, @@ -466,6 +485,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct pvclock_vcpu_time_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.vcpu_time_info_cache, data->u.gpa, @@ -487,6 +512,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct vcpu_runstate_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.runstate_cache, data->u.gpa, |