diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
-rw-r--r-- | arch/x86/kvm/x86.c | 697 |
1 files changed, 497 insertions, 200 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 34afae8..0e3289b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -44,6 +44,7 @@ #include <linux/perf_event.h> #include <linux/uaccess.h> #include <linux/hash.h> +#include <linux/pci.h> #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS @@ -83,6 +84,7 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); static void update_cr8_intercept(struct kvm_vcpu *vcpu); static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); +static void process_nmi(struct kvm_vcpu *vcpu); struct kvm_x86_ops *kvm_x86_ops; EXPORT_SYMBOL_GPL(kvm_x86_ops); @@ -90,6 +92,9 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops); int ignore_msrs = 0; module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR); +unsigned int min_timer_period_us = 500; +module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); + bool kvm_has_tsc_control; EXPORT_SYMBOL_GPL(kvm_has_tsc_control); u32 kvm_max_guest_tsc_khz; @@ -347,6 +352,7 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) vcpu->arch.cr2 = fault->address; kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code); } +EXPORT_SYMBOL_GPL(kvm_inject_page_fault); void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { @@ -358,8 +364,8 @@ void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) void kvm_inject_nmi(struct kvm_vcpu *vcpu) { - kvm_make_request(KVM_REQ_EVENT, vcpu); - vcpu->arch.nmi_pending = 1; + atomic_inc(&vcpu->arch.nmi_queued); + kvm_make_request(KVM_REQ_NMI, vcpu); } EXPORT_SYMBOL_GPL(kvm_inject_nmi); @@ -574,16 +580,33 @@ static bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; - if (!cpu_has_xsave) + if (!static_cpu_has(X86_FEATURE_XSAVE)) return 0; best = kvm_find_cpuid_entry(vcpu, 1, 0); return best && (best->ecx & bit(X86_FEATURE_XSAVE)); } +static bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_SMEP)); +} + +static bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_FSGSBASE)); +} + static void update_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; + struct kvm_lapic *apic = vcpu->arch.apic; best = kvm_find_cpuid_entry(vcpu, 1, 0); if (!best) @@ -595,19 +618,32 @@ static void update_cpuid(struct kvm_vcpu *vcpu) if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) best->ecx |= bit(X86_FEATURE_OSXSAVE); } + + if (apic) { + if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER)) + apic->lapic_timer.timer_mode_mask = 3 << 17; + else + apic->lapic_timer.timer_mode_mask = 1 << 17; + } } int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE; - + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | + X86_CR4_PAE | X86_CR4_SMEP; if (cr4 & CR4_RESERVED_BITS) return 1; if (!guest_cpuid_has_xsave(vcpu) && (cr4 & X86_CR4_OSXSAVE)) return 1; + if (!guest_cpuid_has_smep(vcpu) && (cr4 & X86_CR4_SMEP)) + return 1; + + if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_RDWRGSFS)) + return 1; + if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; @@ -617,11 +653,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) kvm_read_cr3(vcpu))) return 1; - if (cr4 & X86_CR4_VMXE) + if (kvm_x86_ops->set_cr4(vcpu, cr4)) return 1; - kvm_x86_ops->set_cr4(vcpu, cr4); - if ((cr4 ^ old_cr4) & pdptr_bits) kvm_mmu_reset_context(vcpu); @@ -789,12 +823,12 @@ EXPORT_SYMBOL_GPL(kvm_get_dr); * kvm-specific. Those are put in the beginning of the list. */ -#define KVM_SAVE_MSRS_BEGIN 8 +#define KVM_SAVE_MSRS_BEGIN 9 static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, - HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, + HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -806,6 +840,7 @@ static u32 msrs_to_save[] = { static unsigned num_msrs_to_save; static u32 emulated_msrs[] = { + MSR_IA32_TSCDEADLINE, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, @@ -858,7 +893,6 @@ void kvm_enable_efer_bits(u64 mask) } EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); - /* * Writes msr value into into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -866,8 +900,34 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); */ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) { + switch (msr_index) { + case MSR_FS_BASE: + case MSR_GS_BASE: + case MSR_KERNEL_GS_BASE: + case MSR_CSTAR: + case MSR_LSTAR: + if (is_noncanonical_address(data)) + return 1; + break; + case MSR_IA32_SYSENTER_EIP: + case MSR_IA32_SYSENTER_ESP: + /* + * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if + * non-canonical address is written on Intel but not on + * AMD (which ignores the top 32-bits, because it does + * not implement 64-bit SYSENTER). + * + * 64-bit code should hence be able to write a non-canonical + * value on AMD. Making the address canonical ensures that + * vmentry does not fail on Intel after writing a non-canonical + * value, and that something deterministic happens if the guest + * invokes 64-bit SYSENTER. + */ + data = get_canonical(data); + } return kvm_x86_ops->set_msr(vcpu, msr_index, data); } +EXPORT_SYMBOL_GPL(kvm_set_msr); /* * Adapt set_msr() to msr_io()'s calling convention @@ -981,7 +1041,7 @@ static inline int kvm_tsc_changes_freq(void) return ret; } -static u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu) +u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu) { if (vcpu->arch.virtual_tsc_khz) return vcpu->arch.virtual_tsc_khz; @@ -1078,7 +1138,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); - kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp); + tsc_timestamp = kvm_x86_ops->read_l1_tsc(v); kernel_ns = get_kernel_ns(); this_tsc_khz = vcpu_tsc_khz(v); if (unlikely(this_tsc_khz == 0)) { @@ -1384,7 +1444,7 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) return 1; kvm_x86_ops->patch_hypercall(vcpu, instructions); ((unsigned char *)instructions)[3] = 0xc3; /* ret */ - if (copy_to_user((void __user *)addr, instructions, 4)) + if (__copy_to_user((void __user *)addr, instructions, 4)) return 1; kvm->arch.hv_hypercall = data; break; @@ -1411,7 +1471,7 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT); if (kvm_is_error_hva(addr)) return 1; - if (clear_user((void __user *)addr, PAGE_SIZE)) + if (__clear_user((void __user *)addr, PAGE_SIZE)) return 1; vcpu->arch.hv_vapic = data; break; @@ -1461,6 +1521,35 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu) vcpu->arch.pv_time_enabled = false; } +static void accumulate_steal_time(struct kvm_vcpu *vcpu) +{ + u64 delta; + + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) + return; + + delta = current->sched_info.run_delay - vcpu->arch.st.last_steal; + vcpu->arch.st.last_steal = current->sched_info.run_delay; + vcpu->arch.st.accum_steal = delta; +} + +static void record_steal_time(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) + return; + + if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) + return; + + vcpu->arch.st.steal.steal += vcpu->arch.st.accum_steal; + vcpu->arch.st.steal.version += 2; + vcpu->arch.st.accum_steal = 0; + + kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) { switch (msr) { @@ -1508,6 +1597,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: return kvm_x2apic_msr_write(vcpu, msr, data); + case MSR_IA32_TSCDEADLINE: + kvm_set_lapic_tscdeadline_msr(vcpu, data); + break; case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; @@ -1542,6 +1634,34 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (kvm_pv_enable_async_pf(vcpu, data)) return 1; break; + case MSR_KVM_STEAL_TIME: + + if (unlikely(!sched_info_on())) + return 1; + + if (data & KVM_STEAL_RESERVED_MASK) + return 1; + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, + data & KVM_STEAL_VALID_BITS, + sizeof(struct kvm_steal_time))) + return 1; + + vcpu->arch.st.msr_val = data; + + if (!(data & KVM_MSR_ENABLED)) + break; + + vcpu->arch.st.last_steal = current->sched_info.run_delay; + + preempt_disable(); + accumulate_steal_time(vcpu); + preempt_enable(); + + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + + break; + case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1: @@ -1741,6 +1861,9 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); case HV_X64_MSR_TPR: return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); + case HV_X64_MSR_APIC_ASSIST_PAGE: + data = vcpu->arch.hv_vapic; + break; default: pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; @@ -1755,7 +1878,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) switch (msr) { case MSR_IA32_PLATFORM_ID: - case MSR_IA32_UCODE_REV: case MSR_IA32_EBL_CR_POWERON: case MSR_IA32_DEBUGCTLMSR: case MSR_IA32_LASTBRANCHFROMIP: @@ -1763,6 +1885,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: case MSR_K8_SYSCFG: + case MSR_K8_TSEG_ADDR: + case MSR_K8_TSEG_MASK: case MSR_K7_HWCR: case MSR_VM_HSAVE_PA: case MSR_P6_PERFCTR0: @@ -1776,6 +1900,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_FAM10H_MMIO_CONF_BASE: data = 0; break; + case MSR_IA32_UCODE_REV: + data = 0x100000000ULL; + break; case MSR_MTRRcap: data = 0x500 | KVM_NR_VAR_MTRR; break; @@ -1804,6 +1931,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: return kvm_x2apic_msr_read(vcpu, msr, pdata); break; + case MSR_IA32_TSCDEADLINE: + data = kvm_get_lapic_tscdeadline_msr(vcpu); + break; case MSR_IA32_MISC_ENABLE: data = vcpu->arch.ia32_misc_enable_msr; break; @@ -1827,6 +1957,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_KVM_ASYNC_PF_EN: data = vcpu->arch.apf.msr_val; break; + case MSR_KVM_STEAL_TIME: + data = vcpu->arch.st.msr_val; + break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: case MSR_IA32_MCG_CAP: @@ -1999,6 +2132,9 @@ int kvm_dev_ioctl_check_extension(long ext) r = !kvm_x86_ops->cpu_has_accelerated_tpr(); break; case KVM_CAP_NR_VCPUS: + r = KVM_SOFT_MAX_VCPUS; + break; + case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; break; case KVM_CAP_NR_MEMSLOTS: @@ -2008,7 +2144,7 @@ int kvm_dev_ioctl_check_extension(long ext) r = 0; break; case KVM_CAP_IOMMU: - r = iommu_found(); + r = iommu_present(&pci_bus_type); break; case KVM_CAP_MCE: r = KVM_MAX_MCE_BANKS; @@ -2019,6 +2155,9 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_TSC_CONTROL: r = kvm_has_tsc_control; break; + case KVM_CAP_TSC_DEADLINE_TIMER: + r = boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER); + break; default: r = 0; break; @@ -2123,7 +2262,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) s64 tsc_delta; u64 tsc; - kvm_get_msr(vcpu, MSR_IA32_TSC, &tsc); + tsc = kvm_x86_ops->read_l1_tsc(vcpu); tsc_delta = !vcpu->arch.last_guest_tsc ? 0 : tsc - vcpu->arch.last_guest_tsc; @@ -2138,13 +2277,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_migrate_timers(vcpu); vcpu->cpu = cpu; } + + accumulate_steal_time(vcpu); + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); - kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc); + vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); } static int is_efer_nx(void) @@ -2276,6 +2418,13 @@ static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->flags = 0; } +static bool supported_xcr0_bit(unsigned bit) +{ + u64 mask = ((u64)1 << bit); + + return mask & (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) & host_xcr0; +} + #define F(x) bit(X86_FEATURE_##x) static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, @@ -2321,7 +2470,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, 0 /* Reserved, DCA */ | F(XMM4_1) | F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | - F(F16C); + F(F16C) | F(RDRAND); /* cpuid 0x80000001.ecx */ const u32 kvm_supported_word6_x86_features = F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | @@ -2335,6 +2484,10 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | F(PMM) | F(PMM_EN); + /* cpuid 7.0.ebx */ + const u32 kvm_supported_word9_x86_features = + F(SMEP) | F(FSGSBASE) | F(ERMS); + /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); do_cpuid_1_ent(entry, function, index); @@ -2369,7 +2522,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } break; } - /* function 4 and 0xb have additional index. */ + /* function 4 has additional index. */ case 4: { int i, cache_type; @@ -2386,6 +2539,22 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } break; } + case 7: { + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + /* Mask ebx against host capbability word 9 */ + if (index == 0) { + entry->ebx &= kvm_supported_word9_x86_features; + cpuid_mask(&entry->ebx, 9); + } else + entry->ebx = 0; + entry->eax = 0; + entry->ecx = 0; + entry->edx = 0; + break; + } + case 9: + break; + /* function 0xb has additional index. */ case 0xb: { int i, level_type; @@ -2403,16 +2572,17 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, break; } case 0xd: { - int i; + int idx, i; entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - for (i = 1; *nent < maxnent && i < 64; ++i) { - if (entry[i].eax == 0) + for (idx = 1, i = 1; *nent < maxnent && idx < 64; ++idx) { + do_cpuid_1_ent(&entry[i], function, idx); + if (entry[i].eax == 0 || !supported_xcr0_bit(idx)) continue; - do_cpuid_1_ent(&entry[i], function, i); entry[i].flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; ++*nent; + ++i; } break; } @@ -2431,6 +2601,10 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_CLOCKSOURCE2) | (1 << KVM_FEATURE_ASYNC_PF) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT); + + if (sched_info_on()) + entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); + entry->ebx = 0; entry->ecx = 0; entry->edx = 0; @@ -2444,6 +2618,24 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= kvm_supported_word6_x86_features; cpuid_mask(&entry->ecx, 6); break; + case 0x80000008: { + unsigned g_phys_as = (entry->eax >> 16) & 0xff; + unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); + unsigned phys_as = entry->eax & 0xff; + + if (!g_phys_as) + g_phys_as = phys_as; + entry->eax = g_phys_as | (virt_as << 8); + entry->ebx = entry->edx = 0; + break; + } + case 0x80000019: + entry->ecx = entry->edx = 0; + break; + case 0x8000001a: + break; + case 0x8000001d: + break; /*Add support for Centaur's CPUID instruction*/ case 0xC0000000: /*Just support up to 0xC0000004 now*/ @@ -2453,10 +2645,16 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->edx &= kvm_supported_word5_x86_features; cpuid_mask(&entry->edx, 5); break; + case 3: /* Processor serial number */ + case 5: /* MONITOR/MWAIT */ + case 6: /* Thermal management */ + case 0xA: /* Architectural Performance Monitoring */ + case 0x80000007: /* Advanced power management */ case 0xC0000002: case 0xC0000003: case 0xC0000004: - /*Now nothing to do, reserved for the future*/ + default: + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } @@ -2673,6 +2871,7 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { + process_nmi(vcpu); events->exception.injected = vcpu->arch.exception.pending && !kvm_exception_is_soft(vcpu->arch.exception.nr); @@ -2690,7 +2889,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI); events->nmi.injected = vcpu->arch.nmi_injected; - events->nmi.pending = vcpu->arch.nmi_pending; + events->nmi.pending = vcpu->arch.nmi_pending != 0; events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); events->nmi.pad = 0; @@ -2710,6 +2909,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, | KVM_VCPUEVENT_VALID_SHADOW)) return -EINVAL; + process_nmi(vcpu); vcpu->arch.exception.pending = events->exception.injected; vcpu->arch.exception.nr = events->exception.nr; vcpu->arch.exception.has_error_code = events->exception.has_error_code; @@ -2970,8 +3170,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&va, argp, sizeof va)) goto out; - r = 0; - kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); + r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); break; } case KVM_X86_SETUP_MCE: { @@ -3413,7 +3612,11 @@ long kvm_arch_vm_ioctl(struct file *filp, if (r) { mutex_lock(&kvm->slots_lock); kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev); + &vpic->dev_master); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_slave); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_eclr); mutex_unlock(&kvm->slots_lock); kfree(vpic); goto create_irqchip_unlock; @@ -3813,7 +4016,7 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, exception); } -static int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt, +int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { @@ -3823,6 +4026,7 @@ static int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt, return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } +EXPORT_SYMBOL_GPL(kvm_read_guest_virt); static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, @@ -3832,7 +4036,7 @@ static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt, return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception); } -static int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, +int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) @@ -3864,62 +4068,41 @@ static int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, out: return r; } +EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); -static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, - unsigned long addr, - void *val, - unsigned int bytes, - struct x86_exception *exception) +static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, + gpa_t *gpa, struct x86_exception *exception, + bool write) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - gpa_t gpa; - int handled; + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; - if (vcpu->mmio_read_completed) { - memcpy(val, vcpu->mmio_data, bytes); - trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, - vcpu->mmio_phys_addr, *(u64 *)val); - vcpu->mmio_read_completed = 0; - return X86EMUL_CONTINUE; + if (vcpu_match_mmio_gva(vcpu, gva) && + check_write_user_access(vcpu, write, access, + vcpu->arch.access)) { + *gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT | + (gva & (PAGE_SIZE - 1)); + trace_vcpu_match_mmio(gva, *gpa, write, false); + return 1; } - gpa = kvm_mmu_gva_to_gpa_read(vcpu, addr, exception); + if (write) + access |= PFERR_WRITE_MASK; - if (gpa == UNMAPPED_GVA) - return X86EMUL_PROPAGATE_FAULT; - - /* For APIC access vmexit */ - if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) - goto mmio; - - if (kvm_read_guest_virt(ctxt, addr, val, bytes, exception) - == X86EMUL_CONTINUE) - return X86EMUL_CONTINUE; + *gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); -mmio: - /* - * Is this MMIO handled locally? - */ - handled = vcpu_mmio_read(vcpu, gpa, bytes, val); - - if (handled == bytes) - return X86EMUL_CONTINUE; - - gpa += handled; - bytes -= handled; - val += handled; + if (*gpa == UNMAPPED_GVA) + return -1; - trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); + /* For APIC access vmexit */ + if ((*gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + return 1; - vcpu->mmio_needed = 1; - vcpu->run->exit_reason = KVM_EXIT_MMIO; - vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->run->mmio.len = min(vcpu->mmio_size, 8); - vcpu->run->mmio.is_write = vcpu->mmio_is_write = 0; - vcpu->mmio_index = 0; + if (vcpu_match_mmio_gpa(vcpu, *gpa)) { + trace_vcpu_match_mmio(gva, *gpa, write, true); + return 1; + } - return X86EMUL_IO_NEEDED; + return 0; } int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -3934,33 +4117,109 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, return 1; } -static int emulator_write_emulated_onepage(unsigned long addr, - const void *val, - unsigned int bytes, - struct x86_exception *exception, - struct kvm_vcpu *vcpu) +struct read_write_emulator_ops { + int (*read_write_prepare)(struct kvm_vcpu *vcpu, void *val, + int bytes); + int (*read_write_emulate)(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes); + int (*read_write_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, + int bytes, void *val); + int (*read_write_exit_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes); + bool write; +}; + +static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) +{ + if (vcpu->mmio_read_completed) { + memcpy(val, vcpu->mmio_data, bytes); + trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, + vcpu->mmio_phys_addr, *(u64 *)val); + vcpu->mmio_read_completed = 0; + return 1; + } + + return 0; +} + +static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) { - gpa_t gpa; - int handled; + return !kvm_read_guest(vcpu->kvm, gpa, val, bytes); +} - gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, exception); +static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + return emulator_write_phys(vcpu, gpa, val, bytes); +} - if (gpa == UNMAPPED_GVA) +static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val) +{ + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); + return vcpu_mmio_write(vcpu, gpa, bytes, val); +} + +static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); + return X86EMUL_IO_NEEDED; +} + +static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + memcpy(vcpu->mmio_data, val, bytes); + memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8); + return X86EMUL_CONTINUE; +} + +static struct read_write_emulator_ops read_emultor = { + .read_write_prepare = read_prepare, + .read_write_emulate = read_emulate, + .read_write_mmio = vcpu_mmio_read, + .read_write_exit_mmio = read_exit_mmio, +}; + +static struct read_write_emulator_ops write_emultor = { + .read_write_emulate = write_emulate, + .read_write_mmio = write_mmio, + .read_write_exit_mmio = write_exit_mmio, + .write = true, +}; + +static int emulator_read_write_onepage(unsigned long addr, void *val, + unsigned int bytes, + struct x86_exception *exception, + struct kvm_vcpu *vcpu, + struct read_write_emulator_ops *ops) +{ + gpa_t gpa; + int handled, ret; + bool write = ops->write; + + if (ops->read_write_prepare && + ops->read_write_prepare(vcpu, val, bytes)) + return X86EMUL_CONTINUE; + + ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); + + if (ret < 0) return X86EMUL_PROPAGATE_FAULT; /* For APIC access vmexit */ - if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + if (ret) goto mmio; - if (emulator_write_phys(vcpu, gpa, val, bytes)) + if (ops->read_write_emulate(vcpu, gpa, val, bytes)) return X86EMUL_CONTINUE; mmio: - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); /* * Is this MMIO handled locally? */ - handled = vcpu_mmio_write(vcpu, gpa, bytes, val); + handled = ops->read_write_mmio(vcpu, gpa, bytes, val); if (handled == bytes) return X86EMUL_CONTINUE; @@ -3969,23 +4228,20 @@ mmio: val += handled; vcpu->mmio_needed = 1; - memcpy(vcpu->mmio_data, val, bytes); vcpu->run->exit_reason = KVM_EXIT_MMIO; vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa; vcpu->mmio_size = bytes; vcpu->run->mmio.len = min(vcpu->mmio_size, 8); - vcpu->run->mmio.is_write = vcpu->mmio_is_write = 1; - memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8); + vcpu->run->mmio.is_write = vcpu->mmio_is_write = write; vcpu->mmio_index = 0; - return X86EMUL_CONTINUE; + return ops->read_write_exit_mmio(vcpu, gpa, val, bytes); } -int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, - unsigned long addr, - const void *val, - unsigned int bytes, - struct x86_exception *exception) +int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, + void *val, unsigned int bytes, + struct x86_exception *exception, + struct read_write_emulator_ops *ops) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); @@ -3994,16 +4250,38 @@ int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, int rc, now; now = -addr & ~PAGE_MASK; - rc = emulator_write_emulated_onepage(addr, val, now, exception, - vcpu); + rc = emulator_read_write_onepage(addr, val, now, exception, + vcpu, ops); + if (rc != X86EMUL_CONTINUE) return rc; addr += now; val += now; bytes -= now; } - return emulator_write_emulated_onepage(addr, val, bytes, exception, - vcpu); + + return emulator_read_write_onepage(addr, val, bytes, exception, + vcpu, ops); +} + +static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, + void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + return emulator_read_write(ctxt, addr, val, bytes, + exception, &read_emultor); +} + +int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, + const void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + return emulator_read_write(ctxt, addr, (void *)val, bytes, + exception, &write_emultor); } #define CMPXCHG_TYPE(t, ptr, old, new) \ @@ -4492,9 +4770,24 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu) kvm_queue_exception(vcpu, ctxt->exception.vector); } +static void init_decode_cache(struct x86_emulate_ctxt *ctxt, + const unsigned long *regs) +{ + memset(&ctxt->twobyte, 0, + (void *)&ctxt->regs - (void *)&ctxt->twobyte); + memcpy(ctxt->regs, regs, sizeof(ctxt->regs)); + + ctxt->fetch.start = 0; + ctxt->fetch.end = 0; + ctxt->io_read.pos = 0; + ctxt->io_read.end = 0; + ctxt->mem_read.pos = 0; + ctxt->mem_read.end = 0; +} + static void init_emulate_ctxt(struct kvm_vcpu *vcpu) { - struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; int cs_db, cs_l; /* @@ -4507,43 +4800,41 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu); - vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu); - vcpu->arch.emulate_ctxt.mode = - (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : - (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) - ? X86EMUL_MODE_VM86 : cs_l - ? X86EMUL_MODE_PROT64 : cs_db - ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - vcpu->arch.emulate_ctxt.guest_mode = is_guest_mode(vcpu); - memset(c, 0, sizeof(struct decode_cache)); - memcpy(c->regs, vcpu->arch.regs, sizeof c->regs); + ctxt->eflags = kvm_get_rflags(vcpu); + ctxt->eip = kvm_rip_read(vcpu); + ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : + (ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : + cs_l ? X86EMUL_MODE_PROT64 : + cs_db ? X86EMUL_MODE_PROT32 : + X86EMUL_MODE_PROT16; + ctxt->guest_mode = is_guest_mode(vcpu); + + init_decode_cache(ctxt, vcpu->arch.regs); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) { - struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); - vcpu->arch.emulate_ctxt.decode.op_bytes = 2; - vcpu->arch.emulate_ctxt.decode.ad_bytes = 2; - vcpu->arch.emulate_ctxt.decode.eip = vcpu->arch.emulate_ctxt.eip + - inc_eip; - ret = emulate_int_real(&vcpu->arch.emulate_ctxt, &emulate_ops, irq); + ctxt->op_bytes = 2; + ctxt->ad_bytes = 2; + ctxt->_eip = ctxt->eip + inc_eip; + ret = emulate_int_real(ctxt, irq); if (ret != X86EMUL_CONTINUE) return EMULATE_FAIL; - vcpu->arch.emulate_ctxt.eip = c->eip; - memcpy(vcpu->arch.regs, c->regs, sizeof c->regs); - kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip); - kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + ctxt->eip = ctxt->_eip; + memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs); + kvm_rip_write(vcpu, ctxt->eip); + kvm_set_rflags(vcpu, ctxt->eflags); if (irq == NMI_VECTOR) - vcpu->arch.nmi_pending = false; + vcpu->arch.nmi_pending = 0; else vcpu->arch.interrupt.pending = false; @@ -4557,7 +4848,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu) ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); - if (!is_guest_mode(vcpu)) { + if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; @@ -4601,25 +4892,25 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, int insn_len) { int r; - struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; bool writeback = true; kvm_clear_exception_queue(vcpu); if (!(emulation_type & EMULTYPE_NO_DECODE)) { init_emulate_ctxt(vcpu); - vcpu->arch.emulate_ctxt.interruptibility = 0; - vcpu->arch.emulate_ctxt.have_exception = false; - vcpu->arch.emulate_ctxt.perm_ok = false; + ctxt->interruptibility = 0; + ctxt->have_exception = false; + ctxt->perm_ok = false; - vcpu->arch.emulate_ctxt.only_vendor_specific_insn + ctxt->only_vendor_specific_insn = emulation_type & EMULTYPE_TRAP_UD; - r = x86_decode_insn(&vcpu->arch.emulate_ctxt, insn, insn_len); + r = x86_decode_insn(ctxt, insn, insn_len); trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; - if (r) { + if (r != EMULATION_OK) { if (emulation_type & EMULTYPE_TRAP_UD) return EMULATE_FAIL; if (reexecute_instruction(vcpu, cr2)) @@ -4631,7 +4922,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, } if (emulation_type & EMULTYPE_SKIP) { - kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.decode.eip); + kvm_rip_write(vcpu, ctxt->_eip); return EMULATE_DONE; } @@ -4639,11 +4930,11 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, changes registers values during IO operation */ if (vcpu->arch.emulate_regs_need_sync_from_vcpu) { vcpu->arch.emulate_regs_need_sync_from_vcpu = false; - memcpy(c->regs, vcpu->arch.regs, sizeof c->regs); + memcpy(ctxt->regs, vcpu->arch.regs, sizeof ctxt->regs); } restart: - r = x86_emulate_insn(&vcpu->arch.emulate_ctxt); + r = x86_emulate_insn(ctxt); if (r == EMULATION_INTERCEPTED) return EMULATE_DONE; @@ -4655,7 +4946,7 @@ restart: return handle_emulation_failure(vcpu); } - if (vcpu->arch.emulate_ctxt.have_exception) { + if (ctxt->have_exception) { inject_emulated_exception(vcpu); r = EMULATE_DONE; } else if (vcpu->arch.pio.count) { @@ -4674,13 +4965,12 @@ restart: r = EMULATE_DONE; if (writeback) { - toggle_interruptibility(vcpu, - vcpu->arch.emulate_ctxt.interruptibility); - kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + toggle_interruptibility(vcpu, ctxt->interruptibility); + kvm_set_rflags(vcpu, ctxt->eflags); kvm_make_request(KVM_REQ_EVENT, vcpu); - memcpy(vcpu->arch.regs, c->regs, sizeof c->regs); + memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; - kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip); + kvm_rip_write(vcpu, ctxt->eip); } else vcpu->arch.emulate_regs_need_sync_to_vcpu = true; @@ -4897,6 +5187,30 @@ void kvm_after_handle_nmi(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_after_handle_nmi); +static void kvm_set_mmio_spte_mask(void) +{ + u64 mask; + int maxphyaddr = boot_cpu_data.x86_phys_bits; + + /* + * Set the reserved bits and the present bit of an paging-structure + * entry to generate page fault with PFER.RSV = 1. + */ + mask = ((1ull << (62 - maxphyaddr + 1)) - 1) << maxphyaddr; + mask |= 1ull; + +#ifdef CONFIG_X86_64 + /* + * If reserved bit is not supported, clear the present bit to disable + * mmio page fault. + */ + if (maxphyaddr == 52) + mask &= ~1ull; +#endif + + kvm_mmu_set_mmio_spte_mask(mask); +} + int kvm_arch_init(void *opaque) { int r; @@ -4923,10 +5237,10 @@ int kvm_arch_init(void *opaque) if (r) goto out; + kvm_set_mmio_spte_mask(); kvm_init_msr_list(); kvm_x86_ops = ops; - kvm_mmu_set_nonpresent_ptes(0ull, 0ull); kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0); @@ -5101,8 +5415,7 @@ int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) kvm_x86_ops->patch_hypercall(vcpu, instruction); - return emulator_write_emulated(&vcpu->arch.emulate_ctxt, - rip, instruction, 3, NULL); + return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); } static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) @@ -5253,33 +5566,6 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) !kvm_event_needs_reinjection(vcpu); } -static void vapic_enter(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = vcpu->arch.apic; - struct page *page; - - if (!apic || !apic->vapic_addr) - return; - - page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); - - vcpu->arch.apic->vapic_page = page; -} - -static void vapic_exit(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = vcpu->arch.apic; - int idx; - - if (!apic || !apic->vapic_addr) - return; - - idx = srcu_read_lock(&vcpu->kvm->srcu); - kvm_release_page_dirty(apic->vapic_page); - mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); - srcu_read_unlock(&vcpu->kvm->srcu, idx); -} - static void update_cr8_intercept(struct kvm_vcpu *vcpu) { int max_irr, tpr; @@ -5330,7 +5616,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu) /* try to inject new event if pending */ if (vcpu->arch.nmi_pending) { if (kvm_x86_ops->nmi_allowed(vcpu)) { - vcpu->arch.nmi_pending = false; + --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; kvm_x86_ops->set_nmi(vcpu); } @@ -5362,10 +5648,26 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) } } +static void process_nmi(struct kvm_vcpu *vcpu) +{ + unsigned limit = 2; + + /* + * x86 is limited to one NMI running, and one NMI pending after it. + * If an NMI is already in progress, limit further NMIs to just one. + * Otherwise, allow two (and we'll inject the first one immediately). + */ + if (kvm_x86_ops->get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) + limit = 1; + + vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); + kvm_make_request(KVM_REQ_EVENT, vcpu); +} + static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; - bool nmi_pending; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && vcpu->run->request_interrupt_window; @@ -5403,25 +5705,22 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 1; goto out; } + if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) + record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_NMI, vcpu)) + process_nmi(vcpu); + } r = kvm_mmu_reload(vcpu); if (unlikely(r)) goto out; - /* - * An NMI can be injected between local nmi_pending read and - * vcpu->arch.nmi_pending read inside inject_pending_event(). - * But in that case, KVM_REQ_EVENT will be set, which makes - * the race described above benign. - */ - nmi_pending = ACCESS_ONCE(vcpu->arch.nmi_pending); - if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { inject_pending_event(vcpu); /* enable NMI/IRQ window open exits if needed */ - if (nmi_pending) + if (vcpu->arch.nmi_pending) kvm_x86_ops->enable_nmi_window(vcpu); else if (kvm_cpu_has_interrupt(vcpu) || req_int_win) kvm_x86_ops->enable_irq_window(vcpu); @@ -5484,7 +5783,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (hw_breakpoint_active()) hw_breakpoint_restore(); - kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc); + vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); @@ -5539,7 +5838,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) } vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - vapic_enter(vcpu); r = 1; while (r > 0) { @@ -5596,8 +5894,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - vapic_exit(vcpu); - return r; } @@ -5690,8 +5986,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) * that usually, but some bad designed PV devices (vmware * backdoor interface) need this to work */ - struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; - memcpy(vcpu->arch.regs, c->regs, sizeof c->regs); + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; } regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX); @@ -5820,21 +6116,20 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, bool has_error_code, u32 error_code) { - struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); - ret = emulator_task_switch(&vcpu->arch.emulate_ctxt, - tss_selector, reason, has_error_code, - error_code); + ret = emulator_task_switch(ctxt, tss_selector, reason, + has_error_code, error_code); if (ret) return EMULATE_FAIL; - memcpy(vcpu->arch.regs, c->regs, sizeof c->regs); - kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip); - kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs); + kvm_rip_write(vcpu, ctxt->eip); + kvm_set_rflags(vcpu, ctxt->eflags); kvm_make_request(KVM_REQ_EVENT, vcpu); return EMULATE_DONE; } @@ -6133,7 +6428,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) { - vcpu->arch.nmi_pending = false; + atomic_set(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; vcpu->arch.switch_db_regs = 0; @@ -6143,6 +6439,7 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); vcpu->arch.apf.msr_val = 0; + vcpu->arch.st.msr_val = 0; kvmclock_reset(vcpu); @@ -6413,7 +6710,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) !vcpu->arch.apf.halted) || !list_empty_careful(&vcpu->async_pf.done) || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED - || vcpu->arch.nmi_pending || + || atomic_read(&vcpu->arch.nmi_queued) || (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)); } |