diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/cpuid.c | 9 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.h | 1 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 127 | ||||
-rw-r--r-- | arch/x86/kvm/hyperv.c | 13 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 15 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 10 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.c | 8 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.h | 3 | ||||
-rw-r--r-- | arch/x86/kvm/pmu_amd.c | 36 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 15 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/nested.c | 205 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/pmu_intel.c | 9 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/run_flags.h | 8 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmenter.S | 160 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 259 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.h | 8 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 48 |
17 files changed, 593 insertions, 341 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 6a8db8eb0e94..db3838667466 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -592,6 +592,11 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, union cpuid10_eax eax; union cpuid10_edx edx; + if (!static_cpu_has(X86_FEATURE_ARCH_PERFMON)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + perf_get_x86_pmu_capability(&cap); /* @@ -754,6 +759,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); + entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); @@ -786,6 +792,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx = entry->edx = 0; break; case 0x8000001a: + entry->eax &= GENMASK(2, 0); + entry->ebx = entry->ecx = entry->edx = 0; + break; case 0x8000001e: break; /*Add support for Centaur's CPUID instruction*/ diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 7dec43b2c420..defae8082789 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -53,6 +53,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_7_ECX] = { 7, 0, CPUID_ECX}, [CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX}, [CPUID_7_EDX] = { 7, 0, CPUID_EDX}, + [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, }; static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ea48a2fb1677..1a9fa2903852 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -776,8 +776,7 @@ static int linearize(struct x86_emulate_ctxt *ctxt, ctxt->mode, linear); } -static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, - enum x86emul_mode mode) +static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) { ulong linear; int rc; @@ -787,41 +786,71 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); - rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear); + rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; } +static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt) +{ + u64 efer; + struct desc_struct cs; + u16 selector; + u32 base3; + + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + + if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) { + /* Real mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_REAL; + return X86EMUL_CONTINUE; + } + + if (ctxt->eflags & X86_EFLAGS_VM) { + /* Protected/VM86 mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_VM86; + return X86EMUL_CONTINUE; + } + + if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS)) + return X86EMUL_UNHANDLEABLE; + + if (efer & EFER_LMA) { + if (cs.l) { + /* Proper long mode */ + ctxt->mode = X86EMUL_MODE_PROT64; + } else if (cs.d) { + /* 32 bit compatibility mode*/ + ctxt->mode = X86EMUL_MODE_PROT32; + } else { + ctxt->mode = X86EMUL_MODE_PROT16; + } + } else { + /* Legacy 32 bit / 16 bit mode */ + ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + } + + return X86EMUL_CONTINUE; +} + static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) { - return assign_eip(ctxt, dst, ctxt->mode); + return assign_eip(ctxt, dst); } -static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, - const struct desc_struct *cs_desc) +static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst) { - enum x86emul_mode mode = ctxt->mode; - int rc; + int rc = emulator_recalc_and_set_mode(ctxt); -#ifdef CONFIG_X86_64 - if (ctxt->mode >= X86EMUL_MODE_PROT16) { - if (cs_desc->l) { - u64 efer = 0; + if (rc != X86EMUL_CONTINUE) + return rc; - ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); - if (efer & EFER_LMA) - mode = X86EMUL_MODE_PROT64; - } else - mode = X86EMUL_MODE_PROT32; /* temporary value */ - } -#endif - if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32) - mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - rc = assign_eip(ctxt, dst, mode); - if (rc == X86EMUL_CONTINUE) - ctxt->mode = mode; - return rc; + return assign_eip(ctxt, dst); } static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -1753,16 +1782,6 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, case VCPU_SREG_TR: if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9)) goto exception; - if (!seg_desc.p) { - err_vec = NP_VECTOR; - goto exception; - } - old_desc = seg_desc; - seg_desc.type |= 2; /* busy */ - ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc, - sizeof(seg_desc), &ctxt->exception); - if (ret != X86EMUL_CONTINUE) - return ret; break; case VCPU_SREG_LDTR: if (seg_desc.s || seg_desc.type != 2) @@ -1800,8 +1819,17 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, if (ret != X86EMUL_CONTINUE) return ret; if (emul_is_noncanonical_address(get_desc_base(&seg_desc) | - ((u64)base3 << 32), ctxt)) - return emulate_gp(ctxt, 0); + ((u64)base3 << 32), ctxt)) + return emulate_gp(ctxt, err_code); + } + + if (seg == VCPU_SREG_TR) { + old_desc = seg_desc; + seg_desc.type |= 2; /* busy */ + ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc, + sizeof(seg_desc), &ctxt->exception); + if (ret != X86EMUL_CONTINUE) + return ret; } load: ctxt->ops->set_segment(ctxt, selector, &seg_desc, base3, seg); @@ -2021,7 +2049,7 @@ static int em_pop_sreg(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - if (ctxt->modrm_reg == VCPU_SREG_SS) + if (seg == VCPU_SREG_SS) ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS; if (ctxt->op_bytes > 2) rsp_increment(ctxt, ctxt->op_bytes - 2); @@ -2238,7 +2266,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2319,7 +2347,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) &new_desc); if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, eip, &new_desc); + rc = assign_eip_far(ctxt, eip); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2954,6 +2982,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ctxt->_eip = rdx; + ctxt->mode = usermode; *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; @@ -3550,7 +3579,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); if (rc != X86EMUL_CONTINUE) goto fail; @@ -3697,11 +3726,25 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt) static int em_cr_write(struct x86_emulate_ctxt *ctxt) { - if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) + int cr_num = ctxt->modrm_reg; + int r; + + if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val)) return emulate_gp(ctxt, 0); /* Disable writeback. */ ctxt->dst.type = OP_NONE; + + if (cr_num == 0) { + /* + * CR0 write might have updated CR0.PE and/or CR0.PG + * which can affect the cpu's execution mode. + */ + r = emulator_recalc_and_set_mode(ctxt); + if (r != X86EMUL_CONTINUE) + return r; + } + return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index ca66459a2e89..8922f63f5566 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -309,6 +309,9 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) struct kvm_lapic_irq irq; int ret, vector; + if (KVM_BUG_ON(!lapic_in_kernel(vcpu), vcpu->kvm)) + return -EINVAL; + if (sint >= ARRAY_SIZE(synic->sint)) return -EINVAL; @@ -552,10 +555,12 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, stimer_cleanup(stimer); stimer->count = count; - if (stimer->count == 0) - stimer->config.enable = 0; - else if (stimer->config.auto_enable) - stimer->config.enable = 1; + if (!host) { + if (stimer->count == 0) + stimer->config.enable = 0; + else if (stimer->config.auto_enable) + stimer->config.enable = 1; + } if (stimer->config.enable) stimer_mark_pending(stimer, false); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index afe3b8e61514..319ed873a111 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -118,7 +118,8 @@ static inline u32 kvm_x2apic_id(struct kvm_lapic *apic) bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu) { - return pi_inject_timer && kvm_vcpu_apicv_active(vcpu); + return pi_inject_timer && kvm_vcpu_apicv_active(vcpu) && + (kvm_mwait_in_guest(vcpu->kvm) || kvm_hlt_in_guest(vcpu->kvm)); } EXPORT_SYMBOL_GPL(kvm_can_post_timer_interrupt); @@ -954,6 +955,10 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, *r = -1; if (irq->shorthand == APIC_DEST_SELF) { + if (KVM_BUG_ON(!src, kvm)) { + *r = 0; + return true; + } *r = kvm_apic_set_irq(src->vcpu, irq, dest_map); return true; } @@ -2239,13 +2244,17 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) { u32 reg = kvm_lapic_get_reg(apic, lvt_type); int vector, mode, trig_mode; + int r; if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) { vector = reg & APIC_VECTOR_MASK; mode = reg & APIC_MODE_MASK; trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; - return __apic_accept_irq(apic, mode, vector, 1, trig_mode, - NULL); + + r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); + if (r && lvt_type == APIC_LVTPC) + kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); + return r; } return 0; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d3877dd713ae..015da62e4ad7 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -5821,6 +5821,7 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; int nr_zapped, batch = 0; + bool unstable; restart: list_for_each_entry_safe_reverse(sp, node, @@ -5853,11 +5854,12 @@ restart: goto restart; } - if (__kvm_mmu_prepare_zap_page(kvm, sp, - &kvm->arch.zapped_obsolete_pages, &nr_zapped)) { - batch += nr_zapped; + unstable = __kvm_mmu_prepare_zap_page(kvm, sp, + &kvm->arch.zapped_obsolete_pages, &nr_zapped); + batch += nr_zapped; + + if (unstable) goto restart; - } } /* diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index e0e3776059af..32561431acde 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -143,7 +143,6 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) { unsigned config, type = PERF_TYPE_RAW; - u8 event_select, unit_mask; struct kvm *kvm = pmc->vcpu->kvm; struct kvm_pmu_event_filter *filter; int i; @@ -175,17 +174,12 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) if (!allow_event) return; - event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT; - unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; - if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE | ARCH_PERFMON_EVENTSEL_INV | ARCH_PERFMON_EVENTSEL_CMASK | HSW_IN_TX | HSW_IN_TX_CHECKPOINTED))) { - config = kvm_x86_ops->pmu_ops->find_arch_event(pmc_to_pmu(pmc), - event_select, - unit_mask); + config = kvm_x86_ops->pmu_ops->pmc_perf_hw_id(pmc); if (config != PERF_COUNT_HW_MAX) type = PERF_TYPE_HARDWARE; } diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 3fc98afd72a8..b63859e340e4 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -22,8 +22,7 @@ struct kvm_event_hw_type_mapping { }; struct kvm_pmu_ops { - unsigned (*find_arch_event)(struct kvm_pmu *pmu, u8 event_select, - u8 unit_mask); + unsigned int (*pmc_perf_hw_id)(struct kvm_pmc *pmc); unsigned (*find_fixed_event)(int idx); bool (*pmc_is_enabled)(struct kvm_pmc *pmc); struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx); diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c index 6bc656abbe66..799b9a3144e3 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/pmu_amd.c @@ -44,6 +44,22 @@ static struct kvm_event_hw_type_mapping amd_event_mapping[] = { [7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, }; +/* duplicated from amd_f17h_perfmon_event_map. */ +static struct kvm_event_hw_type_mapping amd_f17h_event_mapping[] = { + [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x60, 0xff, PERF_COUNT_HW_CACHE_REFERENCES }, + [3] = { 0x64, 0x09, PERF_COUNT_HW_CACHE_MISSES }, + [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [6] = { 0x87, 0x02, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + [7] = { 0x87, 0x01, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + +/* amd_pmc_perf_hw_id depends on these being the same size */ +static_assert(ARRAY_SIZE(amd_event_mapping) == + ARRAY_SIZE(amd_f17h_event_mapping)); + static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type) { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); @@ -126,21 +142,27 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, return &pmu->gp_counters[msr_to_index(msr)]; } -static unsigned amd_find_arch_event(struct kvm_pmu *pmu, - u8 event_select, - u8 unit_mask) +static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) { + struct kvm_event_hw_type_mapping *event_mapping; + u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; + u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; int i; + if (guest_cpuid_family(pmc->vcpu) >= 0x17) + event_mapping = amd_f17h_event_mapping; + else + event_mapping = amd_event_mapping; + for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++) - if (amd_event_mapping[i].eventsel == event_select - && amd_event_mapping[i].unit_mask == unit_mask) + if (event_mapping[i].eventsel == event_select + && event_mapping[i].unit_mask == unit_mask) break; if (i == ARRAY_SIZE(amd_event_mapping)) return PERF_COUNT_HW_MAX; - return amd_event_mapping[i].event_type; + return event_mapping[i].event_type; } /* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */ @@ -300,7 +322,7 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu) } struct kvm_pmu_ops amd_pmu_ops = { - .find_arch_event = amd_find_arch_event, + .pmc_perf_hw_id = amd_pmc_perf_hw_id, .find_fixed_event = amd_find_fixed_event, .pmc_is_enabled = amd_pmc_is_enabled, .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 131271699e71..e9444e202c33 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -4180,9 +4180,9 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr) msr->data = 0; switch (msr->index) { - case MSR_F10H_DECFG: - if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) - msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE; + case MSR_AMD64_DE_CFG: + if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) + msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; break; default: return 1; @@ -4284,7 +4284,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x1E; } break; - case MSR_F10H_DECFG: + case MSR_AMD64_DE_CFG: msr_info->data = svm->msr_decfg; break; default: @@ -4451,7 +4451,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; - case MSR_F10H_DECFG: { + case MSR_AMD64_DE_CFG: { struct kvm_msr_entry msr_entry; msr_entry.index = msr->index; @@ -5138,8 +5138,6 @@ static void svm_set_irq(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - BUG_ON(!(gif_set(svm))); - trace_kvm_inj_virq(vcpu->arch.interrupt.nr); ++vcpu->stat.irq_injections; @@ -6248,7 +6246,8 @@ out: static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) { - + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR) + vcpu->arch.at_instruction_boundary = true; } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 3041015b05f7..cd96c31fe2bb 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -11,6 +11,7 @@ #include "mmu.h" #include "nested.h" #include "trace.h" +#include "vmx.h" #include "x86.h" static bool __read_mostly enable_shadow_vmcs = 1; @@ -1060,7 +1061,7 @@ static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data) 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; + u64 vmx_basic = vmcs_config.nested.basic; if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved)) return -EINVAL; @@ -1083,36 +1084,42 @@ 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); @@ -1124,6 +1131,7 @@ 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; @@ -1137,10 +1145,8 @@ static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data) BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) | /* reserved */ GENMASK_ULL(13, 9) | BIT_ULL(31); - u64 vmx_misc; - - 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)) return -EINVAL; @@ -1168,10 +1174,8 @@ 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)) @@ -1182,20 +1186,21 @@ 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) @@ -1204,7 +1209,7 @@ 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; } @@ -1265,7 +1270,7 @@ 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; @@ -2068,8 +2073,8 @@ 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 &= ~CPU_BASED_VIRTUAL_INTR_PENDING; - exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING; + exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING; + exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING; exec_control &= ~CPU_BASED_TPR_SHADOW; exec_control |= vmcs12->cpu_based_vm_exec_control; @@ -2454,7 +2459,7 @@ static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12) return -EINVAL; if (CC(!nested_cpu_has_virtual_nmis(vmcs12) && - nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING))) + nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING))) return -EINVAL; return 0; @@ -2774,7 +2779,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, u32 *exit_qual) { - bool ia32e; + bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE); *exit_qual = ENTRY_FAIL_DEFAULT; @@ -2791,6 +2796,13 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, 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: @@ -2802,7 +2814,6 @@ 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) && @@ -2859,35 +2870,8 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->host_state.cr4 = cr4; } - asm( - "sub $%c[wordsize], %%" _ASM_SP "\n\t" /* temporarily adjust RSP for CALL */ - "cmp %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t" - "je 1f \n\t" - __ex("vmwrite %%" _ASM_SP ", %[HOST_RSP]") "\n\t" - "mov %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t" - "1: \n\t" - "add $%c[wordsize], %%" _ASM_SP "\n\t" /* un-adjust RSP */ - - /* Check if vmlaunch or vmresume is needed */ - "cmpb $0, %c[launched](%[loaded_vmcs])\n\t" - - /* - * VMLAUNCH and VMRESUME clear RFLAGS.{CF,ZF} on VM-Exit, set - * RFLAGS.CF on VM-Fail Invalid and set RFLAGS.ZF on VM-Fail - * Valid. vmx_vmenter() directly "returns" RFLAGS, and so the - * results of VM-Enter is captured via CC_{SET,OUT} to vm_fail. - */ - "call vmx_vmenter\n\t" - - CC_SET(be) - : ASM_CALL_CONSTRAINT, CC_OUT(be) (vm_fail) - : [HOST_RSP]"r"((unsigned long)HOST_RSP), - [loaded_vmcs]"r"(vmx->loaded_vmcs), - [launched]"i"(offsetof(struct loaded_vmcs, launched)), - [host_state_rsp]"i"(offsetof(struct loaded_vmcs, host_state.rsp)), - [wordsize]"i"(sizeof(ulong)) - : "memory" - ); + vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, + __vmx_vcpu_run_flags(vmx)); if (vmx->msr_autoload.host.nr) vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); @@ -3061,14 +3045,16 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, u32 exit_qual; evaluate_pending_interrupts = exec_controls_get(vmx) & - (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING); + (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)) + if (!vmx->nested.nested_run_pending || + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); if (kvm_mpx_supported() && - !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) + (!vmx->nested.nested_run_pending || + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); /* @@ -3110,7 +3096,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, } enter_guest_mode(vcpu); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset += vmcs12->tsc_offset; if (prepare_vmcs02(vcpu, vmcs12, &exit_qual)) @@ -3174,7 +3160,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, * 26.7 "VM-entry failures during or after loading guest state". */ vmentry_fail_vmexit_guest_mode: - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset -= vmcs12->tsc_offset; leave_guest_mode(vcpu); @@ -3287,8 +3273,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) */ if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) && !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) && - !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_NMI_PENDING) && - !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_INTR_PENDING) && + !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_NMI_WINDOW_EXITING) && + !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_INTR_WINDOW_EXITING) && (vmcs12->guest_rflags & X86_EFLAGS_IF))) { vmx->nested.nested_run_pending = 0; return kvm_vcpu_halt(vcpu); @@ -3447,7 +3433,16 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, u32 intr_info = nr | INTR_INFO_VALID_MASK; if (vcpu->arch.exception.has_error_code) { - vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code; + /* + * 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)vcpu->arch.exception.error_code; intr_info |= INTR_INFO_DELIVER_CODE_MASK; } @@ -3746,12 +3741,12 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, /* update exit information fields: */ vmcs12->vm_exit_reason = exit_reason; 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; @@ -3763,8 +3758,13 @@ 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->idt_vectoring_info_field = 0; vmcs12_save_pending_event(vcpu, vmcs12); + vmcs12->vm_exit_intr_info = exit_intr_info; + vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); + vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + /* * According to spec, there's no need to store the guest's * MSRs if the exit is due to a VM-entry failure that occurs @@ -3777,14 +3777,6 @@ 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); } /* @@ -4087,7 +4079,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, if (nested_cpu_has_preemption_timer(vmcs12)) hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset -= vmcs12->tsc_offset; if (likely(!vmx->fail)) { @@ -4119,8 +4111,30 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, WARN_ON_ONCE(nested_early_check); } + /* + * 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); + /* + * If IBRS is advertised to the vCPU, KVM must flush the indirect + * branch predictors when transitioning from L2 to L1, as L1 expects + * hardware (KVM in this case) to provide separate predictor modes. + * Bare metal isolates VMX root (host) from VMX non-root (guest), but + * doesn't isolate different VMCSs, i.e. in this case, doesn't provide + * separate modes for L2 vs L1. + */ + if (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + indirect_branch_prediction_barrier(); + /* 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); @@ -5379,10 +5393,10 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) return false; case EXIT_REASON_TRIPLE_FAULT: return true; - case EXIT_REASON_PENDING_INTERRUPT: - return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING); + case EXIT_REASON_INTERRUPT_WINDOW: + return nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING); case EXIT_REASON_NMI_WINDOW: - return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING); + return nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING); case EXIT_REASON_TASK_SWITCH: return true; case EXIT_REASON_CPUID: @@ -5872,8 +5886,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) msrs->procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; msrs->procbased_ctls_high &= - CPU_BASED_VIRTUAL_INTR_PENDING | - CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_INTR_WINDOW_EXITING | + CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING | CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING | CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | @@ -5919,7 +5933,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) SECONDARY_EXEC_RDRAND_EXITING | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_RDSEED_EXITING | - SECONDARY_EXEC_XSAVES; + SECONDARY_EXEC_XSAVES | + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; /* * We can emulate "VMCS shadowing," even if the hardware diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 181e352d38de..395566018ba9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -64,10 +64,11 @@ static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) reprogram_counter(pmu, bit); } -static unsigned intel_find_arch_event(struct kvm_pmu *pmu, - u8 event_select, - u8 unit_mask) +static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc) { + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; + u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; int i; for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++) @@ -374,7 +375,7 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) } struct kvm_pmu_ops intel_pmu_ops = { - .find_arch_event = intel_find_arch_event, + .pmc_perf_hw_id = intel_pmc_perf_hw_id, .find_fixed_event = intel_find_fixed_event, .pmc_is_enabled = intel_pmc_is_enabled, .pmc_idx_to_pmc = intel_pmc_idx_to_pmc, diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h new file mode 100644 index 000000000000..edc3f16cc189 --- /dev/null +++ b/arch/x86/kvm/vmx/run_flags.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_VMX_RUN_FLAGS_H +#define __KVM_X86_VMX_RUN_FLAGS_H + +#define VMX_RUN_VMRESUME (1 << 0) +#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) + +#endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index ca4252f81bf8..2850670c38bb 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -4,6 +4,7 @@ #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> +#include "run_flags.h" #define WORD_SIZE (BITS_PER_LONG / 8) @@ -30,76 +31,11 @@ .text /** - * vmx_vmenter - VM-Enter the current loaded VMCS - * - * %RFLAGS.ZF: !VMCS.LAUNCHED, i.e. controls VMLAUNCH vs. VMRESUME - * - * Returns: - * %RFLAGS.CF is set on VM-Fail Invalid - * %RFLAGS.ZF is set on VM-Fail Valid - * %RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit - * - * Note that VMRESUME/VMLAUNCH fall-through and return directly if - * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump - * to vmx_vmexit. - */ -ENTRY(vmx_vmenter) - /* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */ - je 2f - -1: vmresume - ret - -2: vmlaunch - ret - -3: cmpb $0, kvm_rebooting - je 4f - ret -4: ud2 - - .pushsection .fixup, "ax" -5: jmp 3b - .popsection - - _ASM_EXTABLE(1b, 5b) - _ASM_EXTABLE(2b, 5b) - -ENDPROC(vmx_vmenter) - -/** - * vmx_vmexit - Handle a VMX VM-Exit - * - * Returns: - * %RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit - * - * This is vmx_vmenter's partner in crime. On a VM-Exit, control will jump - * here after hardware loads the host's state, i.e. this is the destination - * referred to by VMCS.HOST_RIP. - */ -ENTRY(vmx_vmexit) -#ifdef CONFIG_RETPOLINE - ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE - /* Preserve guest's RAX, it's used to stuff the RSB. */ - push %_ASM_AX - - /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE - - /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ - or $1, %_ASM_AX - - pop %_ASM_AX -.Lvmexit_skip_rsb: -#endif - ret -ENDPROC(vmx_vmexit) - -/** * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode - * @vmx: struct vcpu_vmx * (forwarded to vmx_update_host_rsp) + * @vmx: struct vcpu_vmx * * @regs: unsigned long * (to guest registers) - * @launched: %true if the VMCS has been launched + * @flags: VMX_RUN_VMRESUME: use VMRESUME instead of VMLAUNCH + * VMX_RUN_SAVE_SPEC_CTRL: save guest SPEC_CTRL into vmx->spec_ctrl * * Returns: * 0 on VM-Exit, 1 on VM-Fail @@ -118,24 +54,29 @@ ENTRY(__vmx_vcpu_run) #endif push %_ASM_BX + /* Save @vmx for SPEC_CTRL handling */ + push %_ASM_ARG1 + + /* Save @flags for SPEC_CTRL handling */ + push %_ASM_ARG3 + /* * Save @regs, _ASM_ARG2 may be modified by vmx_update_host_rsp() and * @regs is needed after VM-Exit to save the guest's register values. */ push %_ASM_ARG2 - /* Copy @launched to BL, _ASM_ARG3 is volatile. */ + /* Copy @flags to BL, _ASM_ARG3 is volatile. */ mov %_ASM_ARG3B, %bl - /* Adjust RSP to account for the CALL to vmx_vmenter(). */ - lea -WORD_SIZE(%_ASM_SP), %_ASM_ARG2 + lea (%_ASM_SP), %_ASM_ARG2 call vmx_update_host_rsp /* Load @regs to RAX. */ mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - cmpb $0, %bl + testb $VMX_RUN_VMRESUME, %bl /* Load guest registers. Don't clobber flags. */ mov VCPU_RBX(%_ASM_AX), %_ASM_BX @@ -157,11 +98,25 @@ ENTRY(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Enter guest mode */ - call vmx_vmenter + /* Check EFLAGS.ZF from 'testb' above */ + jz .Lvmlaunch - /* Jump on VM-Fail. */ - jbe 2f +/* + * If VMRESUME/VMLAUNCH and corresponding vmexit succeed, execution resumes at + * the 'vmx_vmexit' label below. + */ +.Lvmresume: + vmresume + jmp .Lvmfail + +.Lvmlaunch: + vmlaunch + jmp .Lvmfail + + _ASM_EXTABLE(.Lvmresume, .Lfixup) + _ASM_EXTABLE(.Lvmlaunch, .Lfixup) + +SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) /* Temporarily save guest's RAX. */ push %_ASM_AX @@ -188,19 +143,21 @@ ENTRY(__vmx_vcpu_run) mov %r15, VCPU_R15(%_ASM_AX) #endif - /* Clear RAX to indicate VM-Exit (as opposed to VM-Fail). */ - xor %eax, %eax + /* Clear return value to indicate VM-Exit (as opposed to VM-Fail). */ + xor %ebx, %ebx +.Lclear_regs: /* - * Clear all general purpose registers except RSP and RAX to prevent + * Clear all general purpose registers except RSP and RBX to prevent * speculative use of the guest's values, even those that are reloaded * via the stack. In theory, an L1 cache miss when restoring registers * could lead to speculative execution with the guest's values. * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially * free. RSP and RAX are exempt as RSP is restored by hardware during - * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail. + * VM-Exit and RBX is explicitly loaded with 0 or 1 to hold the return + * value. */ -1: xor %ebx, %ebx + xor %eax, %eax xor %ecx, %ecx xor %edx, %edx xor %esi, %esi @@ -219,8 +176,32 @@ ENTRY(__vmx_vcpu_run) /* "POP" @regs. */ add $WORD_SIZE, %_ASM_SP - pop %_ASM_BX + /* + * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before + * the first unbalanced RET after vmexit! + * + * For retpoline or IBRS, RSB filling is needed to prevent poisoned RSB + * entries and (in some cases) RSB underflow. + * + * eIBRS has its own protection against poisoned RSB, so it doesn't + * need the RSB filling sequence. But it does need to be enabled, and a + * single call to retire, before the first unbalanced RET. + */ + + FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\ + X86_FEATURE_RSB_VMEXIT_LITE + + + pop %_ASM_ARG2 /* @flags */ + pop %_ASM_ARG1 /* @vmx */ + + call vmx_spec_ctrl_restore_host + + /* Put return value in AX */ + mov %_ASM_BX, %_ASM_AX + + pop %_ASM_BX #ifdef CONFIG_X86_64 pop %r12 pop %r13 @@ -233,11 +214,20 @@ ENTRY(__vmx_vcpu_run) pop %_ASM_BP ret - /* VM-Fail. Out-of-line to avoid a taken Jcc after VM-Exit. */ -2: mov $1, %eax - jmp 1b +.Lfixup: + cmpb $0, kvm_rebooting + jne .Lvmfail + ud2 +.Lvmfail: + /* VM-Fail: set return value to 1 */ + mov $1, %_ASM_BX + jmp .Lclear_regs + ENDPROC(__vmx_vcpu_run) + +.section .text, "ax" + /** * vmread_error_trampoline - Trampoline from inline asm to vmread_error() * @field: VMCS field encoding that failed diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c407dcb09bf4..c93070829790 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -205,6 +205,9 @@ static const struct { #define L1D_CACHE_ORDER 4 static void *vmx_l1d_flush_pages; +/* Control for disabling CPU Fill buffer clear */ +static bool __read_mostly vmx_fb_clear_ctrl_available; + static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) { struct page *page; @@ -336,6 +339,60 @@ static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); } +static void vmx_setup_fb_clear_ctrl(void) +{ + u64 msr; + + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) && + !boot_cpu_has_bug(X86_BUG_MDS) && + !boot_cpu_has_bug(X86_BUG_TAA)) { + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); + if (msr & ARCH_CAP_FB_CLEAR_CTRL) + vmx_fb_clear_ctrl_available = true; + } +} + +static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) +{ + u64 msr; + + if (!vmx->disable_fb_clear) + return; + + msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL); + msr |= FB_CLEAR_DIS; + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + /* Cache the MSR value to avoid reading it later */ + vmx->msr_ia32_mcu_opt_ctrl = msr; +} + +static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) +{ + if (!vmx->disable_fb_clear) + return; + + vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); +} + +static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) +{ + vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + + /* + * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS + * at VMEntry. Skip the MSR read/write when a guest has no use case to + * execute VERW. + */ + if ((vcpu->arch.arch_capabilities & ARCH_CAP_FB_CLEAR) || + ((vcpu->arch.arch_capabilities & ARCH_CAP_MDS_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_TAA_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_PSDP_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_FBSDP_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_SBDR_SSDP_NO))) + vmx->disable_fb_clear = false; +} + static const struct kernel_param_ops vmentry_l1d_flush_ops = { .set = vmentry_l1d_flush_set, .get = vmentry_l1d_flush_get, @@ -806,6 +863,24 @@ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) return true; } +unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) +{ + unsigned int flags = 0; + + if (vmx->loaded_vmcs->launched) + flags |= VMX_RUN_VMRESUME; + + /* + * If writes to the SPEC_CTRL MSR aren't intercepted, the guest is free + * to change it directly without causing a vmexit. In that case read + * it after vmexit and store it in vmx->spec_ctrl. + */ + if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) + flags |= VMX_RUN_SAVE_SPEC_CTRL; + + return flags; +} + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { @@ -1322,8 +1397,10 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, /* * No indirect branch prediction barrier needed when switching - * the active VMCS within a guest, e.g. on nested VM-Enter. - * The L1 VMM can protect itself with retpolines, IBPB or IBRS. + * the active VMCS within a vCPU, unless IBRS is advertised to + * the vCPU. To minimize the number of IBPBs executed, KVM + * performs IBPB on nested VM-Exit (a single nested transition + * may switch the active VMCS multiple times). */ if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)) indirect_branch_prediction_barrier(); @@ -1601,7 +1678,17 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) kvm_deliver_exception_payload(vcpu); if (has_error_code) { - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); + /* + * Despite the error code being architecturally defined as 32 + * bits, and the VMCS field being 32 bits, Intel CPUs and thus + * VMX don't actually supporting setting bits 31:16. Hardware + * will (should) never provide a bogus error code, but AMD CPUs + * do generate error codes with bits 31:16 set, and so KVM's + * ABI lets userspace shove in arbitrary 32-bit values. Drop + * the upper bits to avoid VM-Fail, losing information that + * does't really exist is preferable to killing the VM. + */ + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)error_code); intr_info |= INTR_INFO_DELIVER_CODE_MASK; } @@ -1695,7 +1782,7 @@ static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)) + (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) return vcpu->arch.tsc_offset - vmcs12->tsc_offset; return vcpu->arch.tsc_offset; @@ -1713,7 +1800,7 @@ static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) * to the newly set TSC to get L2's TSC. */ if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)) + (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) g_tsc_offset = vmcs12->tsc_offset; trace_kvm_write_tsc_offset(vcpu->vcpu_id, @@ -2168,9 +2255,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; } - ret = kvm_set_msr_common(vcpu, msr_info); + ret = kvm_set_msr_common(vcpu, msr_info); } + /* FB_CLEAR may have changed, also update the FB_CLEAR_DIS behavior */ + if (msr_index == MSR_IA32_ARCH_CAPABILITIES) + vmx_update_fb_clear_dis(vcpu, vmx); + return ret; } @@ -2336,7 +2427,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, CPU_BASED_CR3_STORE_EXITING | CPU_BASED_UNCOND_IO_EXITING | CPU_BASED_MOV_DR_EXITING | - CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_USE_TSC_OFFSETTING | CPU_BASED_MWAIT_EXITING | CPU_BASED_MONITOR_EXITING | CPU_BASED_INVLPG_EXITING | @@ -3152,18 +3243,15 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; - if (var->unusable || !var->present) - ar = 1 << 16; - else { - ar = var->type & 15; - ar |= (var->s & 1) << 4; - ar |= (var->dpl & 3) << 5; - ar |= (var->present & 1) << 7; - ar |= (var->avl & 1) << 12; - ar |= (var->l & 1) << 13; - ar |= (var->db & 1) << 14; - ar |= (var->g & 1) << 15; - } + ar = var->type & 15; + ar |= (var->s & 1) << 4; + ar |= (var->dpl & 3) << 5; + ar |= (var->present & 1) << 7; + ar |= (var->avl & 1) << 12; + ar |= (var->l & 1) << 13; + ar |= (var->db & 1) << 14; + ar |= (var->g & 1) << 15; + ar |= (var->unusable || !var->present) << 16; return ar; } @@ -4363,11 +4451,13 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vpid_sync_context(vmx->vpid); if (init_event) vmx_clear_hlt(vcpu); + + vmx_update_fb_clear_dis(vcpu, vmx); } static void enable_irq_window(struct kvm_vcpu *vcpu) { - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING); + exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } static void enable_nmi_window(struct kvm_vcpu *vcpu) @@ -4378,7 +4468,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) return; } - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING); + exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } static void vmx_inject_irq(struct kvm_vcpu *vcpu) @@ -4711,7 +4801,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) return 0; } -static int handle_external_interrupt(struct kvm_vcpu *vcpu) +static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; return 1; @@ -4983,21 +5073,6 @@ static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) vmcs_writel(GUEST_DR7, val); } -static int handle_cpuid(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_cpuid(vcpu); -} - -static int handle_rdmsr(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_rdmsr(vcpu); -} - -static int handle_wrmsr(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_wrmsr(vcpu); -} - static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { kvm_apic_update_ppr(vcpu); @@ -5006,7 +5081,7 @@ static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) static int handle_interrupt_window(struct kvm_vcpu *vcpu) { - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING); + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -5014,11 +5089,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) return 1; } -static int handle_halt(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_halt(vcpu); -} - static int handle_vmcall(struct kvm_vcpu *vcpu) { return kvm_emulate_hypercall(vcpu); @@ -5224,7 +5294,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) static int handle_nmi_window(struct kvm_vcpu *vcpu) { WARN_ON_ONCE(!enable_vnmi); - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING); + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); ++vcpu->stat.nmi_window_exits; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -5245,7 +5315,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending); intr_window_requested = exec_controls_get(vmx) & - CPU_BASED_VIRTUAL_INTR_PENDING; + CPU_BASED_INTR_WINDOW_EXITING; while (vmx->emulation_required && count-- != 0) { if (intr_window_requested && vmx_interrupt_allowed(vcpu)) @@ -5566,11 +5636,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_IO_INSTRUCTION] = handle_io, [EXIT_REASON_CR_ACCESS] = handle_cr, [EXIT_REASON_DR_ACCESS] = handle_dr, - [EXIT_REASON_CPUID] = handle_cpuid, - [EXIT_REASON_MSR_READ] = handle_rdmsr, - [EXIT_REASON_MSR_WRITE] = handle_wrmsr, - [EXIT_REASON_PENDING_INTERRUPT] = handle_interrupt_window, - [EXIT_REASON_HLT] = handle_halt, + [EXIT_REASON_CPUID] = kvm_emulate_cpuid, + [EXIT_REASON_MSR_READ] = kvm_emulate_rdmsr, + [EXIT_REASON_MSR_WRITE] = kvm_emulate_wrmsr, + [EXIT_REASON_INTERRUPT_WINDOW] = handle_interrupt_window, + [EXIT_REASON_HLT] = kvm_emulate_halt, [EXIT_REASON_INVD] = handle_invd, [EXIT_REASON_INVLPG] = handle_invlpg, [EXIT_REASON_RDPMC] = handle_rdpmc, @@ -5944,9 +6014,23 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) } if (exit_reason < kvm_vmx_max_exit_handlers - && kvm_vmx_exit_handlers[exit_reason]) + && kvm_vmx_exit_handlers[exit_reason]) { +#ifdef CONFIG_RETPOLINE + if (exit_reason == EXIT_REASON_MSR_WRITE) + return kvm_emulate_wrmsr(vcpu); + else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER) + return handle_preemption_timer(vcpu); + else if (exit_reason == EXIT_REASON_INTERRUPT_WINDOW) + return handle_interrupt_window(vcpu); + else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + return handle_external_interrupt(vcpu); + else if (exit_reason == EXIT_REASON_HLT) + return kvm_emulate_halt(vcpu); + else if (exit_reason == EXIT_REASON_EPT_MISCONFIG) + return handle_ept_misconfig(vcpu); +#endif return kvm_vmx_exit_handlers[exit_reason](vcpu); - else { + } else { vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", exit_reason); dump_vmcs(); @@ -6274,6 +6358,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) ); kvm_after_interrupt(vcpu); + vcpu->arch.at_instruction_boundary = true; } STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff); @@ -6477,7 +6562,30 @@ void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) } } -bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); +void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, + unsigned int flags) +{ + u64 hostval = this_cpu_read(x86_spec_ctrl_current); + + if (!cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) + return; + + if (flags & VMX_RUN_SAVE_SPEC_CTRL) + vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL); + + /* + * If the guest/host SPEC_CTRL values differ, restore the host value. + * + * For legacy IBRS, the IBRS bit always needs to be written after + * transitioning from a less privileged predictor mode, regardless of + * whether the guest/host values differ. + */ + if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) || + vmx->spec_ctrl != hostval) + native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval); + + barrier_nospec(); +} static void vmx_vcpu_run(struct kvm_vcpu *vcpu) { @@ -6556,34 +6664,21 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_l1d_flush(vcpu); else if (static_branch_unlikely(&mds_user_clear)) mds_clear_cpu_buffers(); + else if (static_branch_unlikely(&mmio_stale_data_clear) && + kvm_arch_has_assigned_device(vcpu->kvm)) + mds_clear_cpu_buffers(); + + vmx_disable_fb_clear(vmx); if (vcpu->arch.cr2 != read_cr2()) write_cr2(vcpu->arch.cr2); vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, - vmx->loaded_vmcs->launched); + __vmx_vcpu_run_flags(vmx)); vcpu->arch.cr2 = read_cr2(); - /* - * We do not use IBRS in the kernel. If this vCPU has used the - * SPEC_CTRL MSR it may have left it on; save the value and - * turn it off. This is much more efficient than blindly adding - * it to the atomic save/restore list. Especially as the former - * (Saving guest MSRs on vmexit) doesn't even exist in KVM. - * - * For non-nested case: - * If the L01 MSR bitmap does not intercept the MSR, then we need to - * save it. - * - * For nested case: - * If the L02 MSR bitmap does not intercept the MSR, then we need to - * save it. - */ - if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) - vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - - x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); + vmx_enable_fb_clear(vmx); /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) @@ -7172,6 +7267,21 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ break; + case x86_intercept_pause: + /* + * PAUSE is a single-byte NOP with a REPE prefix, i.e. collides + * with vanilla NOPs in the emulator. Apply the interception + * check only to actual PAUSE instructions. Don't check + * PAUSE-loop-exiting, software can't expect a given PAUSE to + * exit, i.e. KVM is within its rights to allow L2 to execute + * the PAUSE. + */ + if ((info->rep_prefix != REPE_PREFIX) || + !nested_cpu_has2(vmcs12, CPU_BASED_PAUSE_EXITING)) + return X86EMUL_CONTINUE; + + break; + /* TODO: check more intercepts... */ default: break; @@ -8039,8 +8149,11 @@ static int __init vmx_init(void) return r; } + vmx_setup_fb_clear_ctrl(); + for_each_possible_cpu(cpu) { INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); + INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 55731dd0096f..4d5be4610af8 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -10,6 +10,7 @@ #include "capabilities.h" #include "ops.h" #include "vmcs.h" +#include "run_flags.h" extern const u32 vmx_msr_index[]; extern u64 host_efer; @@ -280,8 +281,11 @@ struct vcpu_vmx { u64 msr_ia32_feature_control; u64 msr_ia32_feature_control_valid_bits; u64 ept_pointer; + u64 msr_ia32_mcu_opt_ctrl; + bool disable_fb_clear; struct pt_desc pt_desc; + }; enum ept_pointers_status { @@ -333,6 +337,10 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr); void pt_update_intercept_for_msr(struct vcpu_vmx *vmx); void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); +void vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, unsigned int flags); +unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx); +bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, + unsigned int flags); #define POSTED_INTR_ON 0 #define POSTED_INTR_SN 1 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1f7dfa5aa42d..07154cae7a15 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -68,6 +68,7 @@ #include <asm/mshyperv.h> #include <asm/hypervisor.h> #include <asm/intel_pt.h> +#include <asm/emulate_prefix.h> #include <clocksource/hyperv_timer.h> #define CREATE_TRACE_POINTS @@ -206,6 +207,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "nmi_injections", VCPU_STAT(nmi_injections) }, { "req_event", VCPU_STAT(req_event) }, { "l1d_flush", VCPU_STAT(l1d_flush) }, + { "preemption_reported", VCPU_STAT(preemption_reported) }, + { "preemption_other", VCPU_STAT(preemption_other) }, { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, { "mmu_pte_write", VM_STAT(mmu_pte_write) }, { "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) }, @@ -1336,7 +1339,7 @@ static const u32 msr_based_features_all[] = { MSR_IA32_VMX_EPT_VPID_CAP, MSR_IA32_VMX_VMFUNC, - MSR_F10H_DECFG, + MSR_AMD64_DE_CFG, MSR_IA32_UCODE_REV, MSR_IA32_ARCH_CAPABILITIES, }; @@ -1402,6 +1405,13 @@ static u64 kvm_get_arch_capabilities(void) /* KVM does not emulate MSR_IA32_TSX_CTRL. */ data &= ~ARCH_CAP_TSX_CTRL_MSR; + + /* Guests don't need to know "Fill buffer clear control" exists */ + data &= ~ARCH_CAP_FB_CLEAR_CTRL; + + if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated()) + data |= ARCH_CAP_GDS_NO; + return data; } @@ -2710,6 +2720,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: break; @@ -3019,6 +3030,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: msr_info->data = 0; break; @@ -3557,6 +3569,19 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) struct kvm_host_map map; struct kvm_steal_time *st; + /* + * The vCPU can be marked preempted if and only if the VM-Exit was on + * an instruction boundary and will not trigger guest emulation of any + * kind (see vcpu_run). Vendor specific code controls (conservatively) + * when this is true, for example allowing the vCPU to be marked + * preempted if and only if the VM-Exit was due to a host interrupt. + */ + if (!vcpu->arch.at_instruction_boundary) { + vcpu->stat.preemption_other++; + return; + } + + vcpu->stat.preemption_reported++; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -3943,12 +3968,11 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, { unsigned long val; + memset(dbgregs, 0, sizeof(*dbgregs)); memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); kvm_get_dr(vcpu, 6, &val); dbgregs->dr6 = val; dbgregs->dr7 = vcpu->arch.dr7; - dbgregs->flags = 0; - memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved)); } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, @@ -5583,6 +5607,7 @@ EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); int handle_ud(struct kvm_vcpu *vcpu) { + static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX }; int emul_type = EMULTYPE_TRAP_UD; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; @@ -5590,7 +5615,7 @@ int handle_ud(struct kvm_vcpu *vcpu) if (force_emulation_prefix && kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu), sig, sizeof(sig), &e) == 0 && - memcmp(sig, "\xf\xbkvm", sizeof(sig)) == 0) { + memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) { kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig)); emul_type = EMULTYPE_TRAP_UD_FORCED; } @@ -6782,7 +6807,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, write_fault_to_spt, emulation_type)) return 1; - if (ctxt->have_exception) { + + if (ctxt->have_exception && + !(emulation_type & EMULTYPE_SKIP)) { /* * #UD should result in just EMULATION_FAILED, and trap-like * exception should not be encountered during decode. @@ -8439,6 +8466,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.l1tf_flush_l1d = true; for (;;) { + /* + * If another guest vCPU requests a PV TLB flush in the middle + * of instruction emulation, the rest of the emulation could + * use a stale page translation. Assume that any code after + * this point can start executing an instruction. + */ + vcpu->arch.at_instruction_boundary = false; if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { @@ -10323,9 +10357,9 @@ void kvm_arch_end_assignment(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); -bool kvm_arch_has_assigned_device(struct kvm *kvm) +bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) { - return atomic_read(&kvm->arch.assigned_device_count); + return arch_atomic_read(&kvm->arch.assigned_device_count); } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); |