/*
 * QEMU KVM support
 *
 * Copyright (C) 2006-2008 Qumranet Technologies
 * Copyright IBM, Corp. 2008
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */

#include "qemu/osdep.h"
#include "qapi/qapi-events-run-state.h"
#include "qapi/error.h"
#include <sys/ioctl.h>
#include <sys/utsname.h>
#include <sys/syscall.h>

#include <linux/kvm.h>
#include "standard-headers/asm-x86/kvm_para.h"

#include "cpu.h"
#include "host-cpu.h"
#include "sysemu/sysemu.h"
#include "sysemu/hw_accel.h"
#include "sysemu/kvm_int.h"
#include "sysemu/runstate.h"
#include "kvm_i386.h"
#include "sev.h"
#include "hyperv.h"
#include "hyperv-proto.h"

#include "exec/gdbstub.h"
#include "qemu/host-utils.h"
#include "qemu/main-loop.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "qemu/memalign.h"
#include "hw/i386/x86.h"
#include "hw/i386/apic.h"
#include "hw/i386/apic_internal.h"
#include "hw/i386/apic-msidef.h"
#include "hw/i386/intel_iommu.h"
#include "hw/i386/x86-iommu.h"
#include "hw/i386/e820_memory_layout.h"

#include "hw/pci/pci.h"
#include "hw/pci/msi.h"
#include "hw/pci/msix.h"
#include "migration/blocker.h"
#include "exec/memattrs.h"
#include "trace.h"

//#define DEBUG_KVM

#ifdef DEBUG_KVM
#define DPRINTF(fmt, ...) \
    do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
    do { } while (0)
#endif

/* From arch/x86/kvm/lapic.h */
#define KVM_APIC_BUS_CYCLE_NS       1
#define KVM_APIC_BUS_FREQUENCY      (1000000000ULL / KVM_APIC_BUS_CYCLE_NS)

#define MSR_KVM_WALL_CLOCK  0x11
#define MSR_KVM_SYSTEM_TIME 0x12

/* A 4096-byte buffer can hold the 8-byte kvm_msrs header, plus
 * 255 kvm_msr_entry structs */
#define MSR_BUF_SIZE 4096

static void kvm_init_msrs(X86CPU *cpu);

const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
    KVM_CAP_INFO(SET_TSS_ADDR),
    KVM_CAP_INFO(EXT_CPUID),
    KVM_CAP_INFO(MP_STATE),
    KVM_CAP_LAST_INFO
};

static bool has_msr_star;
static bool has_msr_hsave_pa;
static bool has_msr_tsc_aux;
static bool has_msr_tsc_adjust;
static bool has_msr_tsc_deadline;
static bool has_msr_feature_control;
static bool has_msr_misc_enable;
static bool has_msr_smbase;
static bool has_msr_bndcfgs;
static int lm_capable_kernel;
static bool has_msr_hv_hypercall;
static bool has_msr_hv_crash;
static bool has_msr_hv_reset;
static bool has_msr_hv_vpindex;
static bool hv_vpindex_settable;
static bool has_msr_hv_runtime;
static bool has_msr_hv_synic;
static bool has_msr_hv_stimer;
static bool has_msr_hv_frequencies;
static bool has_msr_hv_reenlightenment;
static bool has_msr_xss;
static bool has_msr_umwait;
static bool has_msr_spec_ctrl;
static bool has_tsc_scale_msr;
static bool has_msr_tsx_ctrl;
static bool has_msr_virt_ssbd;
static bool has_msr_smi_count;
static bool has_msr_arch_capabs;
static bool has_msr_core_capabs;
static bool has_msr_vmx_vmfunc;
static bool has_msr_ucode_rev;
static bool has_msr_vmx_procbased_ctls2;
static bool has_msr_perf_capabs;
static bool has_msr_pkrs;

static uint32_t has_architectural_pmu_version;
static uint32_t num_architectural_pmu_gp_counters;
static uint32_t num_architectural_pmu_fixed_counters;

static int has_xsave;
static int has_xsave2;
static int has_xcrs;
static int has_pit_state2;
static int has_sregs2;
static int has_exception_payload;

static bool has_msr_mcg_ext_ctl;

static struct kvm_cpuid2 *cpuid_cache;
static struct kvm_cpuid2 *hv_cpuid_cache;
static struct kvm_msr_list *kvm_feature_msrs;

#define BUS_LOCK_SLICE_TIME 1000000000ULL /* ns */
static RateLimit bus_lock_ratelimit_ctrl;

int kvm_has_pit_state2(void)
{
    return has_pit_state2;
}

bool kvm_has_smm(void)
{
    return kvm_vm_check_extension(kvm_state, KVM_CAP_X86_SMM);
}

bool kvm_has_adjust_clock_stable(void)
{
    int ret = kvm_check_extension(kvm_state, KVM_CAP_ADJUST_CLOCK);

    return (ret == KVM_CLOCK_TSC_STABLE);
}

bool kvm_has_adjust_clock(void)
{
    return kvm_check_extension(kvm_state, KVM_CAP_ADJUST_CLOCK);
}

bool kvm_has_exception_payload(void)
{
    return has_exception_payload;
}

static bool kvm_x2apic_api_set_flags(uint64_t flags)
{
    KVMState *s = KVM_STATE(current_accel());

    return !kvm_vm_enable_cap(s, KVM_CAP_X2APIC_API, 0, flags);
}

#define MEMORIZE(fn, _result) \
    ({ \
        static bool _memorized; \
        \
        if (_memorized) { \
            return _result; \
        } \
        _memorized = true; \
        _result = fn; \
    })

static bool has_x2apic_api;

bool kvm_has_x2apic_api(void)
{
    return has_x2apic_api;
}

bool kvm_enable_x2apic(void)
{
    return MEMORIZE(
             kvm_x2apic_api_set_flags(KVM_X2APIC_API_USE_32BIT_IDS |
                                      KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK),
             has_x2apic_api);
}

bool kvm_hv_vpindex_settable(void)
{
    return hv_vpindex_settable;
}

static int kvm_get_tsc(CPUState *cs)
{
    X86CPU *cpu = X86_CPU(cs);
    CPUX86State *env = &cpu->env;
    struct {
        struct kvm_msrs info;
        struct kvm_msr_entry entries[1];
    } msr_data = {};
    int ret;

    if (env->tsc_valid) {
        return 0;
    }

    memset(&msr_data, 0, sizeof(msr_data));
    msr_data.info.nmsrs = 1;
    msr_data.entries[0].index = MSR_IA32_TSC;
    env->tsc_valid = !runstate_is_running();

    ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_MSRS, &msr_data);
    if (ret < 0) {
        return ret;
    }

    assert(ret == 1);
    env->tsc = msr_data.entries[0].data;
    return 0;
}

static inline void do_kvm_synchronize_tsc(CPUState *cpu, run_on_cpu_data arg)
{
    kvm_get_tsc(cpu);
}

void kvm_synchronize_all_tsc(void)
{
    CPUState *cpu;

    if (kvm_enabled()) {
        CPU_FOREACH(cpu) {
            run_on_cpu(cpu, do_kvm_synchronize_tsc, RUN_ON_CPU_NULL);
        }
    }
}

static struct kvm_cpuid2 *try_get_cpuid(KVMState *s, int max)
{
    struct kvm_cpuid2 *cpuid;
    int r, size;

    size = sizeof(*cpuid) + max * sizeof(*cpuid->entries);
    cpuid = g_malloc0(size);
    cpuid->nent = max;
    r = kvm_ioctl(s, KVM_GET_SUPPORTED_CPUID, cpuid);
    if (r == 0 && cpuid->nent >= max) {
        r = -E2BIG;
    }
    if (r < 0) {
        if (r == -E2BIG) {
            g_free(cpuid);
            return NULL;
        } else {
            fprintf(stderr, "KVM_GET_SUPPORTED_CPUID failed: %s\n",
                    strerror(-r));
            exit(1);
        }
    }
    return cpuid;
}

/* Run KVM_GET_SUPPORTED_CPUID ioctl(), allocating a buffer large enough
 * for all entries.
 */
static struct kvm_cpuid2 *get_supported_cpuid(KVMState *s)
{
    struct kvm_cpuid2 *cpuid;
    int max = 1;

    if (cpuid_cache != NULL) {
        return cpuid_cache;
    }
    while ((cpuid = try_get_cpuid(s, max)) == NULL) {
        max *= 2;
    }
    cpuid_cache = cpuid;
    return cpuid;
}

static bool host_tsx_broken(void)
{
    int family, model, stepping;\
    char vendor[CPUID_VENDOR_SZ + 1];

    host_cpu_vendor_fms(vendor, &family, &model, &stepping);

    /* Check if we are running on a Haswell host known to have broken TSX */
    return !strcmp(vendor, CPUID_VENDOR_INTEL) &&
           (family == 6) &&
           ((model == 63 && stepping < 4) ||
            model == 60 || model == 69 || model == 70);
}

/* Returns the value for a specific register on the cpuid entry
 */
static uint32_t cpuid_entry_get_reg(struct kvm_cpuid_entry2 *entry, int reg)
{
    uint32_t ret = 0;
    switch (reg) {
    case R_EAX:
        ret = entry->eax;
        break;
    case R_EBX:
        ret = entry->ebx;
        break;
    case R_ECX:
        ret = entry->ecx;
        break;
    case R_EDX:
        ret = entry->edx;
        break;
    }
    return ret;
}

/* Find matching entry for function/index on kvm_cpuid2 struct
 */
static struct kvm_cpuid_entry2 *cpuid_find_entry(struct kvm_cpuid2 *cpuid,
                                                 uint32_t function,
                                                 uint32_t index)
{
    int i;
    for (i = 0; i < cpuid->nent; ++i) {
        if (cpuid->entries[i].function == function &&
            cpuid->entries[i].index == index) {
            return &cpuid->entries[i];
        }
    }
    /* not found: */
    return NULL;
}

uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function,
                                      uint32_t index, int reg)
{
    struct kvm_cpuid2 *cpuid;
    uint32_t ret = 0;
    uint32_t cpuid_1_edx;
    uint64_t bitmask;

    cpuid = get_supported_cpuid(s);

    struct kvm_cpuid_entry2 *entry = cpuid_find_entry(cpuid, function, index);
    if (entry) {
        ret = cpuid_entry_get_reg(entry, reg);
    }

    /* Fixups for the data returned by KVM, below */

    if (function == 1 && reg == R_EDX) {
        /* KVM before 2.6.30 misreports the following features */
        ret |= CPUID_MTRR | CPUID_PAT | CPUID_MCE | CPUID_MCA;
    } else if (function == 1 && reg == R_ECX) {
        /* We can set the hypervisor flag, even if KVM does not return it on
         * GET_SUPPORTED_CPUID
         */
        ret |= CPUID_EXT_HYPERVISOR;
        /* tsc-deadline flag is not returned by GET_SUPPORTED_CPUID, but it
         * can be enabled if the kernel has KVM_CAP_TSC_DEADLINE_TIMER,
         * and the irqchip is in the kernel.
         */
        if (kvm_irqchip_in_kernel() &&
                kvm_check_extension(s, KVM_CAP_TSC_DEADLINE_TIMER)) {
            ret |= CPUID_EXT_TSC_DEADLINE_TIMER;
        }

        /* x2apic is reported by GET_SUPPORTED_CPUID, but it can't be enabled
         * without the in-kernel irqchip
         */
        if (!kvm_irqchip_in_kernel()) {
            ret &= ~CPUID_EXT_X2APIC;
        }

        if (enable_cpu_pm) {
            int disable_exits = kvm_check_extension(s,
                                                    KVM_CAP_X86_DISABLE_EXITS);

            if (disable_exits & KVM_X86_DISABLE_EXITS_MWAIT) {
                ret |= CPUID_EXT_MONITOR;
            }
        }
    } else if (function == 6 && reg == R_EAX) {
        ret |= CPUID_6_EAX_ARAT; /* safe to allow because of emulated APIC */
    } else if (function == 7 && index == 0 && reg == R_EBX) {
        if (host_tsx_broken()) {
            ret &= ~(CPUID_7_0_EBX_RTM | CPUID_7_0_EBX_HLE);
        }
    } else if (function == 7 && index == 0 && reg == R_EDX) {
        /*
         * Linux v4.17-v4.20 incorrectly return ARCH_CAPABILITIES on SVM hosts.
         * We can detect the bug by checking if MSR_IA32_ARCH_CAPABILITIES is
         * returned by KVM_GET_MSR_INDEX_LIST.
         */
        if (!has_msr_arch_capabs) {
            ret &= ~CPUID_7_0_EDX_ARCH_CAPABILITIES;
        }
    } else if (function == 0xd && index == 0 &&
               (reg == R_EAX || reg == R_EDX)) {
        /*
         * The value returned by KVM_GET_SUPPORTED_CPUID does not include
         * features that still have to be enabled with the arch_prctl
         * system call.  QEMU needs the full value, which is retrieved
         * with KVM_GET_DEVICE_ATTR.
         */
        struct kvm_device_attr attr = {
            .group = 0,
            .attr = KVM_X86_XCOMP_GUEST_SUPP,
            .addr = (unsigned long) &bitmask
        };

        bool sys_attr = kvm_check_extension(s, KVM_CAP_SYS_ATTRIBUTES);
        if (!sys_attr) {
            return ret;
        }

        int rc = kvm_ioctl(s, KVM_GET_DEVICE_ATTR, &attr);
        if (rc < 0) {
            if (rc != -ENXIO) {
                warn_report("KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) "
                            "error: %d", rc);
            }
            return ret;
        }
        ret = (reg == R_EAX) ? bitmask : bitmask >> 32;
    } else if (function == 0x80000001 && reg == R_ECX) {
        /*
         * It's safe to enable TOPOEXT even if it's not returned by
         * GET_SUPPORTED_CPUID.  Unconditionally enabling TOPOEXT here allows
         * us to keep CPU models including TOPOEXT runnable on older kernels.
         */
        ret |= CPUID_EXT3_TOPOEXT;
    } else if (function == 0x80000001 && reg == R_EDX) {
        /* On Intel, kvm returns cpuid according to the Intel spec,
         * so add missing bits according to the AMD spec:
         */
        cpuid_1_edx = kvm_arch_get_supported_cpuid(s, 1, 0, R_EDX);
        ret |= cpuid_1_edx & CPUID_EXT2_AMD_ALIASES;
    } else if (function == KVM_CPUID_FEATURES && reg == R_EAX) {
        /* kvm_pv_unhalt is reported by GET_SUPPORTED_CPUID, but it can't
         * be enabled without the in-kernel irqchip
         */
        if (!kvm_irqchip_in_kernel()) {
            ret &= ~(1U << KVM_FEATURE_PV_UNHALT);
        }
        if (kvm_irqchip_is_split()) {
            ret |= 1U << KVM_FEATURE_MSI_EXT_DEST_ID;
        }
    } else if (function == KVM_CPUID_FEATURES && reg == R_EDX) {
        ret |= 1U << KVM_HINTS_REALTIME;
    }

    return ret;
}

uint64_t kvm_arch_get_supported_msr_feature(KVMState *s, uint32_t index)
{
    struct {
        struct kvm_msrs info;
        struct kvm_msr_entry entries[1];
    } msr_data = {};
    uint64_t value;
    uint32_t ret, can_be_one, must_be_one;

    if (kvm_feature_msrs == NULL) { /* Host doesn't support feature MSRs */
        return 0;
    }

    /* Check if requested MSR is supported feature MSR */
    int i;
    for (i = 0; i < kvm_feature_msrs->nmsrs; i++)
        if (kvm_feature_msrs->indices[i] == index) {
            break;
        }
    if (i == kvm_feature_msrs->nmsrs) {
        return 0; /* if the feature MSR is not supported, simply return 0 */
    }

    msr_data.info.nmsrs = 1;
    msr_data.entries[0].index = index;

    ret = kvm_ioctl(s, KVM_GET_MSRS, &msr_data);
    if (ret != 1) {
        error_report("KVM get MSR (index=0x%x) feature failed, %s",
            index, strerror(-ret));
        exit(1);
    }

    value = msr_data.entries[0].data;
    switch (index) {
    case MSR_IA32_VMX_PROCBASED_CTLS2:
        if (!has_msr_vmx_procbased_ctls2) {
            /* KVM forgot to add these bits for some time, do this ourselves. */
            if (kvm_arch_get_supported_cpuid(s, 0xD, 1, R_ECX) &
                CPUID_XSAVE_XSAVES) {
                value |= (uint64_t)VMX_SECONDARY_EXEC_XSAVES << 32;
            }
            if (kvm_arch_get_supported_cpuid(s, 1, 0, R_ECX) &
                CPUID_EXT_RDRAND) {
                value |= (uint64_t)VMX_SECONDARY_EXEC_RDRAND_EXITING << 32;
            }
            if (kvm_arch_get_supported_cpuid(s, 7, 0, R_EBX) &
                CPUID_7_0_EBX_INVPCID) {
                value |= (uint64_t)VMX_SECONDARY_EXEC_ENABLE_INVPCID << 32;
            }
            if (kvm_arch_get_supported_cpuid(s, 7, 0, R_EBX) &
                CPUID_7_0_EBX_RDSEED) {
                value |= (uint64_t)VMX_SECONDARY_EXEC_RDSEED_EXITING << 32;
            }
            if (kvm_arch_get_supported_cpuid(s, 0x80000001, 0, R_EDX) &
                CPUID_EXT2_RDTSCP) {
                value |= (uint64_t)VMX_SECONDARY_EXEC_RDTSCP << 32;
            }
        }
        /* fall through */
    case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
    case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
    case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
    case MSR_IA32_VMX_TRUE_EXIT_CTLS:
        /*
         * Return true for bits that can be one, but do not have to be one.
         * The SDM tells us which bits could have a "must be one" setting,
         * so we can do the opposite transformation in make_vmx_msr_value.
         */
        must_be_one = (uint32_t)value;
        can_be_one = (uint32_t)(value >> 32);
        return can_be_one & ~must_be_one;

    default:
        return value;
    }
}

static int kvm_get_mce_cap_supported(KVMState *s, uint64_t *mce_cap,
                                     int *max_banks)
{
    int r;

    r = kvm_check_extension(s, KVM_CAP_MCE);
    if (r > 0) {
        *max_banks = r;
        return kvm_ioctl(s, KVM_X86_GET_MCE_CAP_SUPPORTED, mce_cap);
    }
    return -ENOSYS;
}

static void kvm_mce_inject(X86CPU *cpu, hwaddr paddr, int code)
{
    CPUState *cs = CPU(cpu);
    CPUX86State *env = &cpu->env;
    uint64_t status = MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN |
                      MCI_STATUS_MISCV | MCI_STATUS_ADDRV | MCI_STATUS_S;
    uint64_t mcg_status = MCG_STATUS_MCIP;
    int flags = 0;

    if (code == BUS_MCEERR_AR) {
        status |= MCI_STATUS_AR | 0x134;
        mcg_status |= MCG_STATUS_RIPV | MCG_STATUS_EIPV;
    } else {
        status |= 0xc0;
        mcg_status |= MCG_STATUS_RIPV;
    }

    flags = cpu_x86_support_mca_broadcast(env) ? MCE_INJECT_BROADCAST : 0;
    /* We need to read back the value of MSR_EXT_MCG_CTL that was set by the
     * guest kernel back into env->mcg_ext_ctl.
     */
    cpu_synchronize_state(cs);
    if (env->mcg_ext_ctl & MCG_EXT_CTL_LMCE_EN) {
        mcg_status |= MCG_STATUS_LMCE;
        flags = 0;
    }

    cpu_x86_inject_mce(NULL, cpu, 9, status, mcg_status, paddr,
                       (MCM_ADDR_PHYS << 6) | 0xc, flags);
}

static void emit_hypervisor_memory_failure(MemoryFailureAction action, bool ar)
{
    MemoryFailureFlags mff = {.action_required = ar, .recursive = false};

    qapi_event_send_memory_failure(MEMORY_FAILURE_RECIPIENT_HYPERVISOR, action,
                                   &mff);
}

static void hardware_memory_error(void *host_addr)
{
    emit_hypervisor_memory_failure(MEMORY_FAILURE_ACTION_FATAL, true);
    error_report("QEMU got Hardware memory error at addr %p", host_addr);
    exit(1);
}

void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
{
    X86CPU *cpu = X86_CPU(c);
    CPUX86State *env = &cpu->env;
    ram_addr_t ram_addr;
    hwaddr paddr;

    /* If we get an action required MCE, it has been injected by KVM
     * while the VM was running.  An action optional MCE instead should
     * be coming from the main thread, which qemu_init_sigbus identifies
     * as the "early kill" thread.
     */
    assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO);

    if ((env->mcg_cap & MCG_SER_P) && addr) {
        ram_addr = qemu_ram_addr_from_host(addr);
        if (ram_addr != RAM_ADDR_INVALID &&
            kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) {
            kvm_hwpoison_page_add(ram_addr);
            kvm_mce_inject(cpu, paddr, code);

            /*
             * Use different logging severity based on error type.
             * If there is additional MCE reporting on the hypervisor, QEMU VA
             * could be another source to identify the PA and MCE details.
             */
            if (code == BUS_MCEERR_AR) {
                error_report("Guest MCE Memory Error at QEMU addr %p and "
                    "GUEST addr 0x%" HWADDR_PRIx " of type %s injected",
                    addr, paddr, "BUS_MCEERR_AR");
            } else {
                 warn_report("Guest MCE Memory Error at QEMU addr %p and "
                     "GUEST addr 0x%" HWADDR_PRIx " of type %s injected",
                     addr, paddr, "BUS_MCEERR_AO");
            }

            return;
        }

        if (code == BUS_MCEERR_AO) {
            warn_report("Hardware memory error at addr %p of type %s "
                "for memory used by QEMU itself instead of guest system!",
                 addr, "BUS_MCEERR_AO");
        }
    }

    if (code == BUS_MCEERR_AR) {
        hardware_memory_error(addr);
    }

    /* Hope we are lucky for AO MCE, just notify a event */
    emit_hypervisor_memory_failure(MEMORY_FAILURE_ACTION_IGNORE, false);
}

static void kvm_reset_exception(CPUX86State *env)
{
    env->exception_nr = -1;
    env->exception_pending = 0;
    env->exception_injected = 0;
    env->exception_has_payload = false;
    env->exception_payload = 0;
}

static void kvm_queue_exception(CPUX86State *env,
                                int32_t exception_nr,
                                uint8_t exception_has_payload,
                                uint64_t exception_payload)
{
    assert(env->exception_nr == -1);
    assert(!env->exception_pending);
    assert(!env->exception_injected);
    assert(!env->exception_has_payload);

    env->exception_nr = exception_nr;

    if (has_exception_payload) {
        env->exception_pending = 1;

        env->exception_has_payload = exception_has_payload;
        env->exception_payload = exception_payload;
    } else {
        env->exception_injected = 1;

        if (exception_nr == EXCP01_DB) {
            assert(exception_has_payload);
            env->dr[6] = exception_payload;
        } else if (exception_nr == EXCP0E_PAGE) {
            assert(exception_has_payload);
            env->cr[2] = exception_payload;
        } else {
            assert(!exception_has_payload);
        }
    }
}

static int kvm_inject_mce_oldstyle(X86CPU *cpu)
{
    CPUX86State *env = &cpu->env;

    if (!kvm_has_vcpu_events() && env->exception_nr == EXCP12_MCHK) {
        unsigned int bank, bank_num = env->mcg_cap & 0xff;
        struct kvm_x86_mce mce;

        kvm_reset_exception(env);

        /*
         * There must be at least one bank in use if an MCE is pending.
         * Find it and use its values for the event injection.
         */
        for (bank = 0; bank < bank_num; bank++) {
            if (env->mce_banks[bank * 4 + 1] & MCI_STATUS_VAL) {
                break;
            }
        }
        assert(bank < bank_num);

        mce.bank = bank;
        mce.status = env->mce_banks[bank * 4 + 1];
        mce.mcg_status = env->mcg_status;
        mce.addr = env->mce_banks[bank * 4 + 2];
        mce.misc = env->mce_banks[bank * 4 + 3];

        return kvm_vcpu_ioctl(CPU(cpu), KVM_X86_SET_MCE, &mce);
    }
    return 0;
}

static void cpu_update_state(void *opaque, bool running, RunState state)
{
    CPUX86State *env = opaque;

    if (running) {
        env->tsc_valid = false;
    }
}

unsigned long kvm_arch_vcpu_id(CPUState *cs)
{
    X86CPU *cpu = X86_CPU(cs);
    return cpu->apic_id;
}

#ifndef KVM_CPUID_SIGNATURE_NEXT
#define KVM_CPUID_SIGNATURE_NEXT                0x40000100
#endif

static bool hyperv_enabled(X86CPU *cpu)
{
    return kvm_check_extension(kvm_state, KVM_CAP_HYPERV) > 0 &&
        ((cpu->hyperv_spinlock_attempts != HYPERV_SPINLOCK_NEVER_NOTIFY) ||
         cpu->hyperv_features || cpu->hyperv_passthrough);
}

/*
 * Check whether target_freq is within conservative
 * ntp correctable bounds (250ppm) of freq
 */
static inline bool freq_within_bounds(int freq, int target_freq)
{
        int max_freq = freq + (freq * 250 / 1000000);
        int min_freq = freq - (freq * 250 / 1000000);

        if (target_freq >= min_freq && target_freq <= max_freq) {
                return true;
        }

        return false;
}

static int kvm_arch_set_tsc_khz(CPUState *cs)
{
    X86CPU *cpu = X86_CPU(cs);
    CPUX86State *env = &cpu->env;
    int r, cur_freq;
    bool set_ioctl = false;

    if (!env->tsc_khz) {
        return 0;
    }

    cur_freq = kvm_check_extension(cs->kvm_state, KVM_CAP_GET_TSC_KHZ) ?
               kvm_vcpu_ioctl(cs, KVM_GET_TSC_KHZ) : -ENOTSUP;

    /*
     * If TSC scaling is supported, attempt to set TSC frequency.
     */
    if (kvm_check_extension(cs->kvm_state, KVM_CAP_TSC_CONTROL)) {
        set_ioctl = true;
    }

    /*
     * If desired TSC frequency is within bounds of NTP correction,
     * attempt to set TSC frequency.
     */
    if (cur_freq != -ENOTSUP && freq_within_bounds(cur_freq, env->tsc_khz)) {
        set_ioctl = true;
    }

    r = set_ioctl ?
        kvm_vcpu_ioctl(cs, KVM_SET_TSC_KHZ, env->tsc_khz) :
        -ENOTSUP;

    if (r < 0) {
        /* When KVM_SET_TSC_KHZ fails, it's an error only if the current
         * TSC frequency doesn't match the one we want.
         */
        cur_freq = kvm_check_extension(cs->kvm_state, KVM_CAP_GET_TSC_KHZ) ?
                   kvm_vcpu_ioctl(cs, KVM_GET_TSC_KHZ) :
                   -ENOTSUP;
        if (cur_freq <= 0 || cur_freq != env->tsc_khz) {
            warn_report("TSC frequency mismatch between "
                        "VM (%" PRId64 " kHz) and host (%d kHz), "
                        "and TSC scaling unavailable",
                        env->tsc_khz, cur_freq);
            return r;
        }
    }

    return 0;
}

static bool tsc_is_stable_and_known(CPUX86State *env)
{
    if (!env->tsc_khz) {
        return false;
    }
    return (env->features[FEAT_8000_0007_EDX] & CPUID_APM_INVTSC)
        || env->user_tsc_khz;
}

static struct {
    const char *desc;
    struct {
        uint32_t func;
        int reg;
        uint32_t bits;
    } flags[2];
    uint64_t dependencies;
} kvm_hyperv_properties[] = {
    [HYPERV_FEAT_RELAXED] = {
        .desc = "relaxed timing (hv-relaxed)",
        .flags = {
            {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX,
             .bits = HV_RELAXED_TIMING_RECOMMENDED}
        }
    },
    [HYPERV_FEAT_VAPIC] = {
        .desc = "virtual APIC (hv-vapic)",
        .flags = {
            {.func = HV_CPUID_FEATURES, .reg = R_EAX,
             .bits = HV_APIC_ACCESS_AVAILABLE}
        }
    },
    [HYPERV_FEAT_TIME] = {
        .desc = "clocksources (hv-time)",
        .flags = {
            {.func = HV_CPUID_FEATURES, .reg = R_EAX,
             .bits = HV_TIME_REF_COUNT_AVAILABLE | HV_REFERENCE_TSC_AVAILABLE}
        }
    },
    [HYPERV_FEAT_CRASH] = {
        .desc = "crash MSRs (hv-crash)",
        .flags = {
            {.func = HV_CPUID_FEATURES, .reg = R_EDX,
             .bits = HV_GUEST_CRASH_MSR_AVAILABLE}
        }
    },
    [HYPERV_FEAT_RESET] = {
        .desc = "reset MSR (hv-reset)",
        .flags = {
            {.func = HV_CPUID_FEATURES, .reg = R_EAX,
             .bits = HV_RESET_AVAILABLE}
        }
    },
    [HYPERV_FEAT_VPINDEX] = {
        .desc = "VP_INDEX MSR (hv-vpindex)",
        .flags = {
            {.func = HV_CPUID_FEATURES, .reg = R_EAX,
             .bits = HV_VP_INDEX_AVAILABLE}
        }
    },
    [HYPERV_FEAT_RUNTIME] = {
        .desc = "VP_RUNTIME MSR (hv-runtime)",
        .flags = {
            {.func = HV_CPUID_FEATURES, .reg = R_EAX,
             .bits = HV_VP_RUNTIME_AVAILABLE}
        }
    },
    [HYPERV_FEAT_SYNIC] = {
        .desc = "synthetic interrupt controller (hv-synic)",
        .flags = {
            {.func = HV_CPUID_FEATURES, .reg = R_EAX,
             .bits = HV_SYNIC_AVAILABLE}
        }
    },
    [HYPERV_FEAT_STIMER] = {
        .desc = "synthetic timers (hv-stimer)",
        .flags = {
            {.func = HV_CPUID_FEATURES, .reg = R_EAX,
             .bits = HV_SYNTIMERS_AVAILABLE}
        },
        .dependencies = BIT(HYPERV_FEAT_SYNIC) | BIT(HYPERV_FEAT_TIME)
    },
    [HYPERV_FEAT_FREQUENCIES] = {
        .desc = "frequency MSRs (hv-frequencies)",
        .flags = {
            {.func = HV_CPUID_FEATURES, .reg = R_EAX,
             .bits = HV_ACCESS_FREQUENCY_MSRS},
            {.func = HV_CPUID_FEATURES, .reg = R_EDX,
             .bits = HV_FREQUENCY_MSRS_AVAILABLE}
        }
    },
    [HYPERV_FEAT_REENLIGHTENMENT] = {
        .desc = "reenlightenment MSRs (hv-reenlightenment)",
        .flags = {
            {.func = HV_CPUID_FEATURES, .reg = R_EAX,
             .bits = HV_ACCESS_REENLIGHTENMENTS_CONTROL}
        }
    },
    [HYPERV_FEAT_TLBFLUSH] = {
        .desc = "paravirtualized TLB flush (hv-tlbflush)",
        .flags = {
            {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX,
             .bits = HV_REMOTE_TLB_FLUSH_RECOMMENDED |
             HV_EX_PROCESSOR_MASKS_RECOMMENDED}
        },
        .dependencies = BIT(HYPERV_FEAT_VPINDEX)
    },
    [HYPERV_FEAT_EVMCS] = {
        .desc = "enlightened VMCS (hv-evmcs)",
        .flags = {
            {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX,
             .bits = HV_ENLIGHTENED_VMCS_RECOMMENDED}
        },
        .dependencies = BIT(HYPERV_FEAT_VAPIC)
    },
    [HYPERV_FEAT_IPI] = {
        .desc = "paravirtualized IPI (hv-ipi)",
        .flags = {
            {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX,
             .bits = HV_CLUSTER_IPI_RECOMMENDED |
             HV_EX_PROCESSOR_MASKS_RECOMMENDED}
        },
        .dependencies = BIT(HYPERV_FEAT_VPINDEX)
    },
    [HYPERV_FEAT_STIMER_DIRECT] = {
        .desc = "direct mode synthetic timers (hv-stimer-direct)",
        .flags = {
            {.func = HV_CPUID_FEATURES, .reg = R_EDX,
             .bits = HV_STIMER_DIRECT_MODE_AVAILABLE}
        },
        .dependencies = BIT(HYPERV_FEAT_STIMER)
    },
    [HYPERV_FEAT_AVIC] = {
        .desc = "AVIC/APICv support (hv-avic/hv-apicv)",
        .flags = {
            {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX,
             .bits = HV_DEPRECATING_AEOI_RECOMMENDED}
        }
    },
};

static struct kvm_cpuid2 *try_get_hv_cpuid(CPUState *cs, int max,
                                           bool do_sys_ioctl)
{
    struct kvm_cpuid2 *cpuid;
    int r, size;

    size = sizeof(*cpuid) + max * sizeof(*cpuid->entries);
    cpuid = g_malloc0(size);
    cpuid->nent = max;

    if (do_sys_ioctl) {
        r = kvm_ioctl(kvm_state, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
    } else {
        r = kvm_vcpu_ioctl(cs, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
    }
    if (r == 0 && cpuid->nent >= max) {
        r = -E2BIG;
    }
    if (r < 0) {
        if (r == -E2BIG) {
            g_free(cpuid);
            return NULL;
        } else {
            fprintf(stderr, "KVM_GET_SUPPORTED_HV_CPUID failed: %s\n",
                    strerror(-r));
            exit(1);
        }
    }
    return cpuid;
}

/*

 * Run KVM_GET_SUPPORTED_HV_CPUID ioctl(), allocating a buffer large enough
 * for all entries.
 */
static struct kvm_cpuid2 *get_supported_hv_cpuid(CPUState *cs)
{
    struct kvm_cpuid2 *cpuid;
    /* 0x40000000..0x40000005, 0x4000000A, 0x40000080..0x40000080 leaves */
    int max = 10;
    int i;
    bool do_sys_ioctl;

    do_sys_ioctl =
        kvm_check_extension(kvm_state, KVM_CAP_SYS_HYPERV_CPUID) > 0;

    /*
     * Non-empty KVM context is needed when KVM_CAP_SYS_HYPERV_CPUID is
     * unsupported, kvm_hyperv_expand_features() checks for that.
     */
    assert(do_sys_ioctl || cs->kvm_state);

    /*
     * When the buffer is too small, KVM_GET_SUPPORTED_HV_CPUID fails with
     * -E2BIG, however, it doesn't report back the right size. Keep increasing
     * it and re-trying until we succeed.
     */
    while ((cpuid = try_get_hv_cpuid(cs, max, do_sys_ioctl)) == NULL) {
        max++;
    }

    /*
     * KVM_GET_SUPPORTED_HV_CPUID does not set EVMCS CPUID bit before
     * KVM_CAP_HYPERV_ENLIGHTENED_VMCS is enabled but we want to get the
     * information early, just check for the capability and set the bit
     * manually.
     */
    if (!do_sys_ioctl && kvm_check_extension(cs->kvm_state,
                            KVM_CAP_HYPERV_ENLIGHTENED_VMCS) > 0) {
        for (i = 0; i < cpuid->nent; i++) {
            if (cpuid->entries[i].function == HV_CPUID_ENLIGHTMENT_INFO) {
                cpuid->entries[i].eax |= HV_ENLIGHTENED_VMCS_RECOMMENDED;
            }
        }
    }

    return cpuid;
}

/*
 * When KVM_GET_SUPPORTED_HV_CPUID is not supported we fill CPUID feature
 * leaves from KVM_CAP_HYPERV* and present MSRs data.
 */
static struct kvm_cpuid2 *get_supported_hv_cpuid_legacy(CPUState *cs)
{
    X86CPU *cpu = X86_CPU(cs);
    struct kvm_cpuid2 *cpuid;
    struct kvm_cpuid_entry2 *entry_feat, *entry_recomm;

    /* HV_CPUID_FEATURES, HV_CPUID_ENLIGHTMENT_INFO */
    cpuid = g_malloc0(sizeof(*cpuid) + 2 * sizeof(*cpuid->entries));
    cpuid->nent = 2;

    /* HV_CPUID_VENDOR_AND_MAX_FUNCTIONS */
    entry_feat = &cpuid->entries[0];
    entry_feat->function = HV_CPUID_FEATURES;

    entry_recomm = &cpuid->entries[1];
    entry_recomm->function = HV_CPUID_ENLIGHTMENT_INFO;
    entry_recomm->ebx = cpu->hyperv_spinlock_attempts;

    if (kvm_check_extension(cs->kvm_state, KVM_CAP_HYPERV) > 0) {
        entry_feat->eax |= HV_HYPERCALL_AVAILABLE;
        entry_feat->eax |= HV_APIC_ACCESS_AVAILABLE;
        entry_feat->edx |= HV_CPU_DYNAMIC_PARTITIONING_AVAILABLE;
        entry_recomm->eax |= HV_RELAXED_TIMING_RECOMMENDED;
        entry_recomm->eax |= HV_APIC_ACCESS_RECOMMENDED;
    }

    if (kvm_check_extension(cs->kvm_state, KVM_CAP_HYPERV_TIME) > 0) {
        entry_feat->eax |= HV_TIME_REF_COUNT_AVAILABLE;
        entry_feat->eax |= HV_REFERENCE_TSC_AVAILABLE;
    }

    if (has_msr_hv_frequencies) {
        entry_feat->eax |= HV_ACCESS_FREQUENCY_MSRS;
        entry_feat->edx |= HV_FREQUENCY_MSRS_AVAILABLE;
    }

    if (has_msr_hv_crash) {
        entry_feat->edx |= HV_GUEST_CRASH_MSR_AVAILABLE;
    }

    if (has_msr_hv_reenlightenment) {
        entry_feat->eax |= HV_ACCESS_REENLIGHTENMENTS_CONTROL;
    }

    if (has_msr_hv_reset) {
        entry_feat->eax |= HV_RESET_AVAILABLE;
    }

    if (has_msr_hv_vpindex) {
        entry_feat->eax |= HV_VP_INDEX_AVAILABLE;
    }

    if (has_msr_hv_runtime) {
        entry_feat->eax |= HV_VP_RUNTIME_AVAILABLE;
    }

    if (has_msr_hv_synic) {
        unsigned int cap = cpu->hyperv_synic_kvm_only ?
            KVM_CAP_HYPERV_SYNIC : KVM_CAP_HYPERV_SYNIC2;

        if (kvm_check_extension(cs->kvm_state, cap) > 0) {
            entry_feat->eax |= HV_SYNIC_AVAILABLE;
        }
    }

    if (has_msr_hv_stimer) {
        entry_feat->eax |= HV_SYNTIMERS_AVAILABLE;
    }

    if (kvm_check_extension(cs->kvm_state,
                            KVM_CAP_HYPERV_TLBFLUSH) > 0) {
        entry_recomm->eax |= HV_REMOTE_TLB_FLUSH_RECOMMENDED;
        entry_recomm->eax |= HV_EX_PROCESSOR_MASKS_RECOMMENDED;
    }

    if (kvm_check_extension(cs->kvm_state,
                            KVM_CAP_HYPERV_ENLIGHTENED_VMCS) > 0) {
        entry_recomm->eax |= HV_ENLIGHTENED_VMCS_RECOMMENDED;
    }

    if (kvm_check_extension(cs->kvm_state,
                            KVM_CAP_HYPERV_SEND_IPI) > 0) {
        entry_recomm->eax |= HV_CLUSTER_IPI_RECOMMENDED;
        entry_recomm->eax |= HV_EX_PROCESSOR_MASKS_RECOMMENDED;
    }

    return cpuid;
}

static uint32_t hv_cpuid_get_host(CPUState *cs, uint32_t func, int reg)
{
    struct kvm_cpuid_entry2 *entry;
    struct kvm_cpuid2 *cpuid;

    if (hv_cpuid_cache) {
        cpuid = hv_cpuid_cache;
    } else {
        if (kvm_check_extension(kvm_state, KVM_CAP_HYPERV_CPUID) > 0) {
            cpuid = get_supported_hv_cpuid(cs);
        } else {
            /*
             * 'cs->kvm_state' may be NULL when Hyper-V features are expanded
             * before KVM context is created but this is only done when
             * KVM_CAP_SYS_HYPERV_CPUID is supported and it implies
             * KVM_CAP_HYPERV_CPUID.
             */
            assert(cs->kvm_state);

            cpuid = get_supported_hv_cpuid_legacy(cs);
        }
        hv_cpuid_cache = cpuid;
    }

    if (!cpuid) {
        return 0;
    }

    entry = cpuid_find_entry(cpuid, func, 0);
    if (!entry) {
        return 0;
    }

    return cpuid_entry_get_reg(entry, reg);
}

static bool hyperv_feature_supported(CPUState *cs, int feature)
{
    uint32_t func, bits;
    int i, reg;

    for (i = 0; i < ARRAY_SIZE(kvm_hyperv_properties[feature].flags); i++) {

        func = kvm_hyperv_properties[feature].flags[i].func;
        reg = kvm_hyperv_properties[feature].flags[i].reg;
        bits = kvm_hyperv_properties[feature].flags[i].bits;

        if (!func) {
            continue;
        }

        if ((hv_cpuid_get_host(cs, func, reg) & bits) != bits) {
            return false;
        }
    }

    return true;
}

/* Checks that all feature dependencies are enabled */
static bool hv_feature_check_deps(X86CPU *cpu, int feature, Error **errp)
{
    uint64_t deps;
    int dep_feat;

    deps = kvm_hyperv_properties[feature].dependencies;
    while (deps) {
        dep_feat = ctz64(deps);
        if (!(hyperv_feat_enabled(cpu, dep_feat))) {
            error_setg(errp, "Hyper-V %s requires Hyper-V %s",
                       kvm_hyperv_properties[feature].desc,
                       kvm_hyperv_properties[dep_feat].desc);
            return false;
        }
        deps &= ~(1ull << dep_feat);
    }

    return true;
}

static uint32_t hv_build_cpuid_leaf(CPUState *cs, uint32_t func, int reg)
{
    X86CPU *cpu = X86_CPU(cs);
    uint32_t r = 0;
    int i, j;

    for (i = 0; i < ARRAY_SIZE(kvm_hyperv_properties); i++) {
        if (!hyperv_feat_enabled(cpu, i)) {
            continue;
        }

        for (j = 0; j < ARRAY_SIZE(kvm_hyperv_properties[i].flags); j++) {
            if (kvm_hyperv_properties[i].flags[j].func != func) {
                continue;
            }
            if (kvm_hyperv_properties[i].flags[j].reg != reg) {
                continue;
            }

            r |= kvm_hyperv_properties[i].flags[j].bits;
        }
    }

    return r;
}

/*
 * Expand Hyper-V CPU features. In partucular, check that all the requested
 * features are supported by the host and the sanity of the configuration
 * (that all the required dependencies are included). Also, this takes care
 * of 'hv_passthrough' mode and fills the environment with all supported
 * Hyper-V features.
 */
bool kvm_hyperv_expand_features(X86CPU *cpu, Error **errp)
{
    CPUState *cs = CPU(cpu);
    Error *local_err = NULL;
    int feat;

    if (!hyperv_enabled(cpu))
        return true;

    /*
     * When kvm_hyperv_expand_features is called at CPU feature expansion
     * time per-CPU kvm_state is not available yet so we can only proceed
     * when KVM_CAP_SYS_HYPERV_CPUID is supported.
     */
    if (!cs->kvm_state &&
        !kvm_check_extension(kvm_state, KVM_CAP_SYS_HYPERV_CPUID))
        return true;

    if (cpu->hyperv_passthrough) {
        cpu->hyperv_vendor_id[0] =
            hv_cpuid_get_host(cs, HV_CPUID_VENDOR_AND_MAX_FUNCTIONS, R_EBX);
        cpu->hyperv_vendor_id[1] =
            hv_cpuid_get_host(cs, HV_CPUID_VENDOR_AND_MAX_FUNCTIONS, R_ECX);
        cpu->hyperv_vendor_id[2] =
            hv_cpuid_get_host(cs, HV_CPUID_VENDOR_AND_MAX_FUNCTIONS, R_EDX);
        cpu->hyperv_vendor = g_realloc(cpu->hyperv_vendor,
                                       sizeof(cpu->hyperv_vendor_id) + 1);
        memcpy(cpu->hyperv_vendor, cpu->hyperv_vendor_id,
               sizeof(cpu->hyperv_vendor_id));
        cpu->hyperv_vendor[sizeof(cpu->hyperv_vendor_id)] = 0;

        cpu->hyperv_interface_id[0] =
            hv_cpuid_get_host(cs, HV_CPUID_INTERFACE, R_EAX);
        cpu->hyperv_interface_id[1] =
            hv_cpuid_get_host(cs, HV_CPUID_INTERFACE, R_EBX);
        cpu->hyperv_interface_id[2] =
            hv_cpuid_get_host(cs, HV_CPUID_INTERFACE, R_ECX);
        cpu->hyperv_interface_id[3] =
            hv_cpuid_get_host(cs, HV_CPUID_INTERFACE, R_EDX);

        cpu->hyperv_ver_id_build =
            hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EAX);
        cpu->hyperv_ver_id_major =
            hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EBX) >> 16;
        cpu->hyperv_ver_id_minor =
            hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EBX) & 0xffff;
        cpu->hyperv_ver_id_sp =
            hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_ECX);
        cpu->hyperv_ver_id_sb =
            hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EDX) >> 24;
        cpu->hyperv_ver_id_sn =
            hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EDX) & 0xffffff;

        cpu->hv_max_vps = hv_cpuid_get_host(cs, HV_CPUID_IMPLEMENT_LIMITS,
                                            R_EAX);
        cpu->hyperv_limits[0] =
            hv_cpuid_get_host(cs, HV_CPUID_IMPLEMENT_LIMITS, R_EBX);
        cpu->hyperv_limits[1] =
            hv_cpuid_get_host(cs, HV_CPUID_IMPLEMENT_LIMITS, R_ECX);
        cpu->hyperv_limits[2] =
            hv_cpuid_get_host(cs, HV_CPUID_IMPLEMENT_LIMITS, R_EDX);

        cpu->hyperv_spinlock_attempts =
            hv_cpuid_get_host(cs, HV_CPUID_ENLIGHTMENT_INFO, R_EBX);

        /*
         * Mark feature as enabled in 'cpu->hyperv_features' as
         * hv_build_cpuid_leaf() uses this info to build guest CPUIDs.
         */
        for (feat = 0; feat < ARRAY_SIZE(kvm_hyperv_properties); feat++) {
            if (hyperv_feature_supported(cs, feat)) {
                cpu->hyperv_features |= BIT(feat);
            }
        }
    } else {
        /* Check features availability and dependencies */
        for (feat = 0; feat < ARRAY_SIZE(kvm_hyperv_properties); feat++) {
            /* If the feature was not requested skip it. */
            if (!hyperv_feat_enabled(cpu, feat)) {
                continue;
            }

            /* Check if the feature is supported by KVM */
            if (!hyperv_feature_supported(cs, feat)) {
                error_setg(errp, "Hyper-V %s is not supported by kernel",
                           kvm_hyperv_properties[feat].desc);
                return false;
            }

            /* Check dependencies */
            if (!hv_feature_check_deps(cpu, feat, &local_err)) {
                error_propagate(errp, local_err);
                return false;
            }
        }
    }

    /* Additional dependencies not covered by kvm_hyperv_properties[] */
    if (hyperv_feat_enabled(cpu, HYPERV_FEAT_SYNIC) &&
        !cpu->hyperv_synic_kvm_only &&
        !hyperv_feat_enabled(cpu, HYPERV_FEAT_VPINDEX)) {
        error_setg(errp, "Hyper-V %s requires Hyper-V %s",
                   kvm_hyperv_properties[HYPERV_FEAT_SYNIC].desc,
                   kvm_hyperv_properties[HYPERV_FEAT_VPINDEX].desc);
        return false;
    }

    return true;
}

/*
 * Fill in Hyper-V CPUIDs. Returns the number of entries filled in cpuid_ent.
 */
static int hyperv_fill_cpuids(CPUState *cs,
                              struct kvm_cpuid_entry2 *cpuid_ent)
{
    X86CPU *cpu = X86_CPU(cs);
    struct kvm_cpuid_entry2 *c;
    uint32_t cpuid_i = 0;

    c = &cpuid_ent[cpuid_i++];
    c->function = HV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
    c->eax = hyperv_feat_enabled(cpu, HYPERV_FEAT_EVMCS) ?
        HV_CPUID_NESTED_FEATURES : HV_CPUID_IMPLEMENT_LIMITS;
    c->ebx = cpu->hyperv_vendor_id[0];
    c->ecx = cpu->hyperv_vendor_id[1];
    c->edx = cpu->hyperv_vendor_id[2];

    c = &cpuid_ent[cpuid_i++];
    c->function = HV_CPUID_INTERFACE;
    c->eax = cpu->hyperv_interface_id[0];
    c->ebx = cpu->hyperv_interface_id[1];
    c->ecx = cpu->hyperv_interface_id[2];
    c->edx = cpu->hyperv_interface_id[3];

    c = &cpuid_ent[cpuid_i++];
    c->function = HV_CPUID_VERSION;
    c->eax = cpu->hyperv_ver_id_build;
    c->ebx = (uint32_t)cpu->hyperv_ver_id_major << 16 |
        cpu->hyperv_ver_id_minor;
    c->ecx = cpu->hyperv_ver_id_sp;
    c->edx = (uint32_t)cpu->hyperv_ver_id_sb << 24 |
        (cpu->hyperv_ver_id_sn & 0xffffff);

    c = &cpuid_ent[cpuid_i++];
    c->function = HV_CPUID_FEATURES;
    c->eax = hv_build_cpuid_leaf(cs, HV_CPUID_FEATURES, R_EAX);
    c->ebx = hv_build_cpuid_leaf(cs, HV_CPUID_FEATURES, R_EBX);
    c->edx = hv_build_cpuid_leaf(cs, HV_CPUID_FEATURES, R_EDX);

    /* Unconditionally required with any Hyper-V enlightenment */
    c->eax |= HV_HYPERCALL_AVAILABLE;

    /* SynIC and Vmbus devices require messages/signals hypercalls */
    if (hyperv_feat_enabled(cpu, HYPERV_FEAT_SYNIC) &&
        !cpu->hyperv_synic_kvm_only) {
        c->ebx |= HV_POST_MESSAGES | HV_SIGNAL_EVENTS;
    }


    /* Not exposed by KVM but needed to make CPU hotplug in Windows work */
    c->edx |= HV_CPU_DYNAMIC_PARTITIONING_AVAILABLE;

    c = &cpuid_ent[cpuid_i++];
    c->function = HV_CPUID_ENLIGHTMENT_INFO;
    c->eax = hv_build_cpuid_leaf(cs, HV_CPUID_ENLIGHTMENT_INFO, R_EAX);
    c->ebx = cpu->hyperv_spinlock_attempts;

    if (hyperv_feat_enabled(cpu, HYPERV_FEAT_VAPIC) &&
        !hyperv_feat_enabled(cpu, HYPERV_FEAT_AVIC)) {
        c->eax |= HV_APIC_ACCESS_RECOMMENDED;
    }

    if (cpu->hyperv_no_nonarch_cs == ON_OFF_AUTO_ON) {
        c->eax |= HV_NO_NONARCH_CORESHARING;
    } else if (cpu->hyperv_no_nonarch_cs == ON_OFF_AUTO_AUTO) {
        c->eax |= hv_cpuid_get_host(cs, HV_CPUID_ENLIGHTMENT_INFO, R_EAX) &
            HV_NO_NONARCH_CORESHARING;
    }

    c = &cpuid_ent[cpuid_i++];
    c->function = HV_CPUID_IMPLEMENT_LIMITS;
    c->eax = cpu->hv_max_vps;
    c->ebx = cpu->hyperv_limits[0];
    c->ecx = cpu->hyperv_limits[1];
    c->edx = cpu->hyperv_limits[2];

    if (hyperv_feat_enabled(cpu, HYPERV_FEAT_EVMCS)) {
        uint32_t function;

        /* Create zeroed 0x40000006..0x40000009 leaves */
        for (function = HV_CPUID_IMPLEMENT_LIMITS + 1;
             function < HV_CPUID_NESTED_FEATURES; function++) {
            c = &cpuid_ent[cpuid_i++];
            c->function = function;
        }

        c = &cpuid_ent[cpuid_i++];
        c->function = HV_CPUID_NESTED_FEATURES;
        c->eax = cpu->hyperv_nested[0];
    }

    return cpuid_i;
}

static Error *hv_passthrough_mig_blocker;
static Error *hv_no_nonarch_cs_mig_blocker;

/* Checks that the exposed eVMCS version range is supported by KVM */
static bool evmcs_version_supported(uint16_t evmcs_version,
                                    uint16_t supported_evmcs_version)
{
    uint8_t min_version = evmcs_version & 0xff;
    uint8_t max_version = evmcs_version >> 8;
    uint8_t min_supported_version = supported_evmcs_version & 0xff;
    uint8_t max_supported_version = supported_evmcs_version >> 8;

    return (min_version >= min_supported_version) &&
        (max_version <= max_supported_version);
}

#define DEFAULT_EVMCS_VERSION ((1 << 8) | 1)

static int hyperv_init_vcpu(X86CPU *cpu)
{
    CPUState *cs = CPU(cpu);
    Error *local_err = NULL;
    int ret;

    if (cpu->hyperv_passthrough && hv_passthrough_mig_blocker == NULL) {
        error_setg(&hv_passthrough_mig_blocker,
                   "'hv-passthrough' CPU flag prevents migration, use explicit"
                   " set of hv-* flags instead");
        ret = migrate_add_blocker(hv_passthrough_mig_blocker, &local_err);
        if (ret < 0) {
            error_report_err(local_err);
            return ret;
        }
    }

    if (cpu->hyperv_no_nonarch_cs == ON_OFF_AUTO_AUTO &&
        hv_no_nonarch_cs_mig_blocker == NULL) {
        error_setg(&hv_no_nonarch_cs_mig_blocker,
                   "'hv-no-nonarch-coresharing=auto' CPU flag prevents migration"
                   " use explicit 'hv-no-nonarch-coresharing=on' instead (but"
                   " make sure SMT is disabled and/or that vCPUs are properly"
                   " pinned)");
        ret = migrate_add_blocker(hv_no_nonarch_cs_mig_blocker, &local_err);
        if (ret < 0) {
            error_report_err(local_err);
            return ret;
        }
    }

    if (hyperv_feat_enabled(cpu, HYPERV_FEAT_VPINDEX) && !hv_vpindex_settable) {
        /*
         * the kernel doesn't support setting vp_index; assert that its value
         * is in sync
         */
        struct {
            struct kvm_msrs info;
            struct kvm_msr_entry entries[1];
        } msr_data = {
            .info.nmsrs = 1,
            .entries[0].index = HV_X64_MSR_VP_INDEX,
        };

        ret = kvm_vcpu_ioctl(cs, KVM_GET_MSRS, &msr_data);
        if (ret < 0) {
            return ret;
        }
        assert(ret == 1);

        if (msr_data.entries[0].data != hyperv_vp_index(CPU(cpu))) {
            error_report("kernel's vp_index != QEMU's vp_index");
            return -ENXIO;
        }
    }

    if (hyperv_feat_enabled(cpu, HYPERV_FEAT_SYNIC)) {
        uint32_t synic_cap = cpu->hyperv_synic_kvm_only ?
            KVM_CAP_HYPERV_SYNIC : KVM_CAP_HYPERV_SYNIC2;
        ret = kvm_vcpu_enable_cap(cs, synic_cap, 0);
        if (ret < 0) {
            error_report("failed to turn on HyperV SynIC in KVM: %s",
                         strerror(-ret));
            return ret;
        }

        if (!cpu->hyperv_synic_kvm_only) {
            ret = hyperv_x86_synic_add(cpu);
            if (ret < 0) {
                error_report("failed to create HyperV SynIC: %s",
                             strerror(-ret));
                return ret;
            }
        }
    }

    if (hyperv_feat_enabled(cpu, HYPERV_FEAT_EVMCS)) {
        uint16_t evmcs_version = DEFAULT_EVMCS_VERSION;
        uint16_t supported_evmcs_version;

        ret = kvm_vcpu_enable_cap(cs, KVM_CAP_HYPERV_ENLIGHTENED_VMCS, 0,
                                  (uintptr_t)&supported_evmcs_version);

        /*
         * KVM is required to support EVMCS ver.1. as that's what 'hv-evmcs'
         * option sets. Note: we hardcode the maximum supported eVMCS version
         * to '1' as well so 'hv-evmcs' feature is migratable even when (and if)
         * ver.2 is implemented. A new option (e.g. 'hv-evmcs=2') will then have
         * to be added.
         */
        if (ret < 0) {
            error_report("Hyper-V %s is not supported by kernel",
                         kvm_hyperv_properties[HYPERV_FEAT_EVMCS].desc);
            return ret;
        }

        if (!evmcs_version_supported(evmcs_version, supported_evmcs_version)) {
            error_report("eVMCS version range [%d..%d] is not supported by "
                         "kernel (supported: [%d..%d])", evmcs_version & 0xff,
                         evmcs_version >> 8, supported_evmcs_version & 0xff,
                         supported_evmcs_version >> 8);
            return -ENOTSUP;
        }

        cpu->hyperv_nested[0] = evmcs_version;
    }

    if (cpu->hyperv_enforce_cpuid) {
        ret = kvm_vcpu_enable_cap(cs, KVM_CAP_HYPERV_ENFORCE_CPUID, 0, 1);
        if (ret < 0) {
            error_report("failed to enable KVM_CAP_HYPERV_ENFORCE_CPUID: %s",
                         strerror(-ret));
            return ret;
        }
    }

    return 0;
}

static Error *invtsc_mig_blocker;

#define KVM_MAX_CPUID_ENTRIES  100

static void kvm_init_xsave(CPUX86State *env)
{
    if (has_xsave2) {
        env->xsave_buf_len = QEMU_ALIGN_UP(has_xsave2, 4096);
    } else if (has_xsave) {
        env->xsave_buf_len = sizeof(struct kvm_xsave);
    } else {
        return;
    }

    env->xsave_buf = qemu_memalign(4096, env->xsave_buf_len);
    memset(env->xsave_buf, 0, env->xsave_buf_len);
    /*
     * The allocated storage must be large enough for all of the
     * possible XSAVE state components.
     */
    assert(kvm_arch_get_supported_cpuid(kvm_state, 0xd, 0, R_ECX) <=
           env->xsave_buf_len);
}

int kvm_arch_init_vcpu(CPUState *cs)
{
    struct {
        struct kvm_cpuid2 cpuid;
        struct kvm_cpuid_entry2 entries[KVM_MAX_CPUID_ENTRIES];
    } cpuid_data;
    /*
     * The kernel defines these structs with padding fields so there
     * should be no extra padding in our cpuid_data struct.
     */
    QEMU_BUILD_BUG_ON(sizeof(cpuid_data) !=
                      sizeof(struct kvm_cpuid2) +
                      sizeof(struct kvm_cpuid_entry2) * KVM_MAX_CPUID_ENTRIES);

    X86CPU *cpu = X86_CPU(cs);
    CPUX86State *env = &cpu->env;
    uint32_t limit, i, j, cpuid_i;
    uint32_t unused;
    struct kvm_cpuid_entry2 *c;
    uint32_t signature[3];
    int kvm_base = KVM_CPUID_SIGNATURE;
    int max_nested_state_len;
    int r;
    Error *local_err = NULL;

    memset(&cpuid_data, 0, sizeof(cpuid_data));

    cpuid_i = 0;

    has_xsave2 = kvm_check_extension(cs->kvm_state, KVM_CAP_XSAVE2);

    r = kvm_arch_set_tsc_khz(cs);
    if (r < 0) {
        return r;
    }

    /* vcpu's TSC frequency is either specified by user, or following
     * the value used by KVM if the former is not present. In the
     * latter case, we query it from KVM and record in env->tsc_khz,
     * so that vcpu's TSC frequency can be migrated later via this field.
     */
    if (!env->tsc_khz) {
        r = kvm_check_extension(cs->kvm_state, KVM_CAP_GET_TSC_KHZ) ?
            kvm_vcpu_ioctl(cs, KVM_GET_TSC_KHZ) :
            -ENOTSUP;
        if (r > 0) {
            env->tsc_khz = r;
        }
    }

    env->apic_bus_freq = KVM_APIC_BUS_FREQUENCY;

    /*
     * kvm_hyperv_expand_features() is called here for the second time in case
     * KVM_CAP_SYS_HYPERV_CPUID is not supported. While we can't possibly handle
     * 'query-cpu-model-expansion' in this case as we don't have a KVM vCPU to
     * check which Hyper-V enlightenments are supported and which are not, we
     * can still proceed and check/expand Hyper-V enlightenments here so legacy
     * behavior is preserved.
     */
    if (!kvm_hyperv_expand_features(cpu, &local_err)) {
        error_report_err(local_err);
        return -ENOSYS;
    }

    if (hyperv_enabled(cpu)) {
        r = hyperv_init_vcpu(cpu);
        if (r) {
            return r;
        }

        cpuid_i = hyperv_fill_cpuids(cs, cpuid_data.entries);
        kvm_base = KVM_CPUID_SIGNATURE_NEXT;
        has_msr_hv_hypercall = true;
    }

    if (cpu->expose_kvm) {
        memcpy(signature, "KVMKVMKVM\0\0\0", 12);
        c = &cpuid_data.entries[cpuid_i++];
        c->function = KVM_CPUID_SIGNATURE | kvm_base;
        c->eax = KVM_CPUID_FEATURES | kvm_base;
        c->ebx = signature[0];
        c->ecx = signature[1];
        c->edx = signature[2];

        c = &cpuid_data.entries[cpuid_i++];
        c->function = KVM_CPUID_FEATURES | kvm_base;
        c->eax = env->features[FEAT_KVM];
        c->edx = env->features[FEAT_KVM_HINTS];
    }

    cpu_x86_cpuid(env, 0, 0, &limit, &unused, &unused, &unused);

    if (cpu->kvm_pv_enforce_cpuid) {
        r = kvm_vcpu_enable_cap(cs, KVM_CAP_ENFORCE_PV_FEATURE_CPUID, 0, 1);
        if (r < 0) {
            fprintf(stderr,
                    "failed to enable KVM_CAP_ENFORCE_PV_FEATURE_CPUID: %s",
                    strerror(-r));
            abort();
        }
    }

    for (i = 0; i <= limit; i++) {
        if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
            fprintf(stderr, "unsupported level value: 0x%x\n", limit);
            abort();
        }
        c = &cpuid_data.entries[cpuid_i++];

        switch (i) {
        case 2: {
            /* Keep reading function 2 till all the input is received */
            int times;

            c->function = i;
            c->flags = KVM_CPUID_FLAG_STATEFUL_FUNC |
                       KVM_CPUID_FLAG_STATE_READ_NEXT;
            cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
            times = c->eax & 0xff;

            for (j = 1; j < times; ++j) {
                if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
                    fprintf(stderr, "cpuid_data is full, no space for "
                            "cpuid(eax:2):eax & 0xf = 0x%x\n", times);
                    abort();
                }
                c = &cpuid_data.entries[cpuid_i++];
                c->function = i;
                c->flags = KVM_CPUID_FLAG_STATEFUL_FUNC;
                cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
            }
            break;
        }
        case 0x1f:
            if (env->nr_dies < 2) {
                break;
            }
            /* fallthrough */
        case 4:
        case 0xb:
        case 0xd:
            for (j = 0; ; j++) {
                if (i == 0xd && j == 64) {
                    break;
                }

                if (i == 0x1f && j == 64) {
                    break;
                }

                c->function = i;
                c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
                c->index = j;
                cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx);

                if (i == 4 && c->eax == 0) {
                    break;
                }
                if (i == 0xb && !(c->ecx & 0xff00)) {
                    break;
                }
                if (i == 0x1f && !(c->ecx & 0xff00)) {
                    break;
                }
                if (i == 0xd && c->eax == 0) {
                    continue;
                }
                if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
                    fprintf(stderr, "cpuid_data is full, no space for "
                            "cpuid(eax:0x%x,ecx:0x%x)\n", i, j);
                    abort();
                }
                c = &cpuid_data.entries[cpuid_i++];
            }
            break;
        case 0x7:
        case 0x12:
            for (j = 0; ; j++) {
                c->function = i;
                c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
                c->index = j;
                cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx);

                if (j > 1 && (c->eax & 0xf) != 1) {
                    break;
                }

                if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
                    fprintf(stderr, "cpuid_data is full, no space for "
                                "cpuid(eax:0x12,ecx:0x%x)\n", j);
                    abort();
                }
                c = &cpuid_data.entries[cpuid_i++];
            }
            break;
        case 0x14:
        case 0x1d:
        case 0x1e: {
            uint32_t times;

            c->function = i;
            c->index = 0;
            c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
            cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
            times = c->eax;

            for (j = 1; j <= times; ++j) {
                if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
                    fprintf(stderr, "cpuid_data is full, no space for "
                                "cpuid(eax:0x%x,ecx:0x%x)\n", i, j);
                    abort();
                }
                c = &cpuid_data.entries[cpuid_i++];
                c->function = i;
                c->index = j;
                c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
                cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx);
            }
            break;
        }
        default:
            c->function = i;
            c->flags = 0;
            cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
            if (!c->eax && !c->ebx && !c->ecx && !c->edx) {
                /*
                 * KVM already returns all zeroes if a CPUID entry is missing,
                 * so we can omit it and avoid hitting KVM's 80-entry limit.
                 */
                cpuid_i--;
            }
            break;
        }
    }

    if (limit >= 0x0a) {
        uint32_t eax, edx;

        cpu_x86_cpuid(env, 0x0a, 0, &eax, &unused, &unused, &edx);

        has_architectural_pmu_version = eax & 0xff;
        if (has_architectural_pmu_version > 0) {
            num_architectural_pmu_gp_counters = (eax & 0xff00) >> 8;

            /* Shouldn't be more than 32, since that's the number of bits
             * available in EBX to tell us _which_ counters are available.
             * Play it safe.
             */
            if (num_architectural_pmu_gp_counters > MAX_GP_COUNTERS) {
                num_architectural_pmu_gp_counters = MAX_GP_COUNTERS;
            }

            if (has_architectural_pmu_version > 1) {
                num_architectural_pmu_fixed_counters = edx & 0x1f;

                if (num_architectural_pmu_fixed_counters > MAX_FIXED_COUNTERS) {
                    num_architectural_pmu_fixed_counters = MAX_FIXED_COUNTERS;
                }
            }
        }
    }

    cpu_x86_cpuid(env, 0x80000000, 0, &limit, &unused, &unused, &unused);

    for (i = 0x80000000; i <= limit; i++) {
        if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
            fprintf(stderr, "unsupported xlevel value: 0x%x\n", limit);
            abort();
        }
        c = &cpuid_data.entries[cpuid_i++];

        switch (i) {
        case 0x8000001d:
            /* Query for all AMD cache information leaves */
            for (j = 0; ; j++) {
                c->function = i;
                c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
                c->index = j;
                cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx);

                if (c->eax == 0) {
                    break;
                }
                if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
                    fprintf(stderr, "cpuid_data is full, no space for "
                            "cpuid(eax:0x%x,ecx:0x%x)\n", i, j);
                    abort();
                }
                c = &cpuid_data.entries[cpuid_i++];
            }
            break;
        default:
            c->function = i;
            c->flags = 0;
            cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
            if (!c->eax && !c->ebx && !c->ecx && !c->edx) {
                /*
                 * KVM already returns all zeroes if a CPUID entry is missing,
                 * so we can omit it and avoid hitting KVM's 80-entry limit.
                 */
                cpuid_i--;
            }
            break;
        }
    }

    /* Call Centaur's CPUID instructions they are supported. */
    if (env->cpuid_xlevel2 > 0) {
        cpu_x86_cpuid(env, 0xC0000000, 0, &limit, &unused, &unused, &unused);

        for (i = 0xC0000000; i <= limit; i++) {
            if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
                fprintf(stderr, "unsupported xlevel2 value: 0x%x\n", limit);
                abort();
            }
            c = &cpuid_data.entries[cpuid_i++];

            c->function = i;
            c->flags = 0;
            cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
        }
    }

    cpuid_data.cpuid.nent = cpuid_i;

    if (((env->cpuid_version >> 8)&0xF) >= 6
        && (env->features[FEAT_1_EDX] & (CPUID_MCE | CPUID_MCA)) ==
           (CPUID_MCE | CPUID_MCA)
        && kvm_check_extension(cs->kvm_state, KVM_CAP_MCE) > 0) {
        uint64_t mcg_cap, unsupported_caps;
        int banks;
        int ret;

        ret = kvm_get_mce_cap_supported(cs->kvm_state, &mcg_cap, &banks);
        if (ret < 0) {
            fprintf(stderr, "kvm_get_mce_cap_supported: %s", strerror(-ret));
            return ret;
        }

        if (banks < (env->mcg_cap & MCG_CAP_BANKS_MASK)) {
            error_report("kvm: Unsupported MCE bank count (QEMU = %d, KVM = %d)",
                         (int)(env->mcg_cap & MCG_CAP_BANKS_MASK), banks);
            return -ENOTSUP;
        }

        unsupported_caps = env->mcg_cap & ~(mcg_cap | MCG_CAP_BANKS_MASK);
        if (unsupported_caps) {
            if (unsupported_caps & MCG_LMCE_P) {
                error_report("kvm: LMCE not supported");
                return -ENOTSUP;
            }
            warn_report("Unsupported MCG_CAP bits: 0x%" PRIx64,
                        unsupported_caps);
        }

        env->mcg_cap &= mcg_cap | MCG_CAP_BANKS_MASK;
        ret = kvm_vcpu_ioctl(cs, KVM_X86_SETUP_MCE, &env->mcg_cap);
        if (ret < 0) {
            fprintf(stderr, "KVM_X86_SETUP_MCE: %s", strerror(-ret));
            return ret;
        }
    }

    cpu->vmsentry = qemu_add_vm_change_state_handler(cpu_update_state, env);

    c = cpuid_find_entry(&cpuid_data.cpuid, 1, 0);
    if (c) {
        has_msr_feature_control = !!(c->ecx & CPUID_EXT_VMX) ||
                                  !!(c->ecx & CPUID_EXT_SMX);
    }

    c = cpuid_find_entry(&cpuid_data.cpuid, 7, 0);
    if (c && (c->ebx & CPUID_7_0_EBX_SGX)) {
        has_msr_feature_control = true;
    }

    if (env->mcg_cap & MCG_LMCE_P) {
        has_msr_mcg_ext_ctl = has_msr_feature_control = true;
    }

    if (!env->user_tsc_khz) {
        if ((env->features[FEAT_8000_0007_EDX] & CPUID_APM_INVTSC) &&
            invtsc_mig_blocker == NULL) {
            error_setg(&invtsc_mig_blocker,
                       "State blocked by non-migratable CPU device"
                       " (invtsc flag)");
            r = migrate_add_blocker(invtsc_mig_blocker, &local_err);
            if (r < 0) {
                error_report_err(local_err);
                return r;
            }
        }
    }

    if (cpu->vmware_cpuid_freq
        /* Guests depend on 0x40000000 to detect this feature, so only expose
         * it if KVM exposes leaf 0x40000000. (Conflicts with Hyper-V) */
        && cpu->expose_kvm
        && kvm_base == KVM_CPUID_SIGNATURE
        /* TSC clock must be stable and known for this feature. */
        && tsc_is_stable_and_known(env)) {

        c = &cpuid_data.entries[cpuid_i++];
        c->function = KVM_CPUID_SIGNATURE | 0x10;
        c->eax = env->tsc_khz;
        c->ebx = env->apic_bus_freq / 1000; /* Hz to KHz */
        c->ecx = c->edx = 0;

        c = cpuid_find_entry(&cpuid_data.cpuid, kvm_base, 0);
        c->eax = MAX(c->eax, KVM_CPUID_SIGNATURE | 0x10);
    }

    cpuid_data.cpuid.nent = cpuid_i;

    cpuid_data.cpuid.padding = 0;
    r = kvm_vcpu_ioctl(cs, KVM_SET_CPUID2, &cpuid_data);
    if (r) {
        goto fail;
    }
    kvm_init_xsave(env);

    max_nested_state_len = kvm_max_nested_state_length();
    if (max_nested_state_len > 0) {
        assert(max_nested_state_len >= offsetof(struct kvm_nested_state, data));

        if (cpu_has_vmx(env) || cpu_has_svm(env)) {
            struct kvm_vmx_nested_state_hdr *vmx_hdr;

            env->nested_state = g_malloc0(max_nested_state_len);
            env->nested_state->size = max_nested_state_len;

            if (cpu_has_vmx(env)) {
                env->nested_state->format = KVM_STATE_NESTED_FORMAT_VMX;
                vmx_hdr = &env->nested_state->hdr.vmx;
                vmx_hdr->vmxon_pa = -1ull;
                vmx_hdr->vmcs12_pa = -1ull;
            } else {
                env->nested_state->format = KVM_STATE_NESTED_FORMAT_SVM;
            }
        }
    }

    cpu->kvm_msr_buf = g_malloc0(MSR_BUF_SIZE);

    if (!(env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_RDTSCP)) {
        has_msr_tsc_aux = false;
    }

    kvm_init_msrs(cpu);

    return 0;

 fail:
    migrate_del_blocker(invtsc_mig_blocker);

    return r;
}

int kvm_arch_destroy_vcpu(CPUState *cs)
{
    X86CPU *cpu = X86_CPU(cs);
    CPUX86State *env = &cpu->env;

    g_free(env->xsave_buf);

    if (cpu->kvm_msr_buf) {
        g_free(cpu->kvm_msr_buf);
        cpu->kvm_msr_buf = NULL;
    }

    if (env->nested_state) {
        g_free(env->nested_state);
        env->nested_state = NULL;
    }

    qemu_del_vm_change_state_handler(cpu->vmsentry);

    return 0;
}

void kvm_arch_reset_vcpu(X86CPU *cpu)
{
    CPUX86State *env = &cpu->env;

    env->xcr0 = 1;
    if (kvm_irqchip_in_kernel()) {
        env->mp_state = cpu_is_bsp(cpu) ? KVM_MP_STATE_RUNNABLE :
                                          KVM_MP_STATE_UNINITIALIZED;
    } else {
        env->mp_state = KVM_MP_STATE_RUNNABLE;
    }

    if (hyperv_feat_enabled(cpu, HYPERV_FEAT_SYNIC)) {
        int i;
        for (i = 0; i < ARRAY_SIZE(env->msr_hv_synic_sint); i++) {
            env->msr_hv_synic_sint[i] = HV_SINT_MASKED;
        }

        hyperv_x86_synic_reset(cpu);
    }
    /* enabled by default */
    env->poll_control_msr = 1;

    sev_es_set_reset_vector(CPU(cpu));
}

void kvm_arch_do_init_vcpu(X86CPU *cpu)
{
    CPUX86State *env = &cpu->env;

    /* APs get directly into wait-for-SIPI state.  */
    if (env->mp_state == KVM_MP_STATE_UNINITIALIZED) {
        env->mp_state = KVM_MP_STATE_INIT_RECEIVED;
    }
}

static int kvm_get_supported_feature_msrs(KVMState *s)
{
    int ret = 0;

    if (kvm_feature_msrs != NULL) {
        return 0;
    }

    if (!kvm_check_extension(s, KVM_CAP_GET_MSR_FEATURES)) {
        return 0;
    }

    struct kvm_msr_list msr_list;

    msr_list.nmsrs = 0;
    ret = kvm_ioctl(s, KVM_GET_MSR_FEATURE_INDEX_LIST, &msr_list);
    if (ret < 0 && ret != -E2BIG) {
        error_report("Fetch KVM feature MSR list failed: %s",
            strerror(-ret));
        return ret;
    }

    assert(msr_list.nmsrs > 0);
    kvm_feature_msrs = (struct kvm_msr_list *) \
        g_malloc0(sizeof(msr_list) +
                 msr_list.nmsrs * sizeof(msr_list.indices[0]));

    kvm_feature_msrs->nmsrs = msr_list.nmsrs;
    ret = kvm_ioctl(s, KVM_GET_MSR_FEATURE_INDEX_LIST, kvm_feature_msrs);

    if (ret < 0) {
        error_report("Fetch KVM feature MSR list failed: %s",
            strerror(-ret));
        g_free(kvm_feature_msrs);
        kvm_feature_msrs = NULL;
        return ret;
    }

    return 0;
}

static int kvm_get_supported_msrs(KVMState *s)
{
    int ret = 0;
    struct kvm_msr_list msr_list, *kvm_msr_list;

    /*
     *  Obtain MSR list from KVM.  These are the MSRs that we must
     *  save/restore.
     */
    msr_list.nmsrs = 0;
    ret = kvm_ioctl(s, KVM_GET_MSR_INDEX_LIST, &msr_list);
    if (ret < 0 && ret != -E2BIG) {
        return ret;
    }
    /*
     * Old kernel modules had a bug and could write beyond the provided
     * memory. Allocate at least a safe amount of 1K.
     */
    kvm_msr_list = g_malloc0(MAX(1024, sizeof(msr_list) +
                                          msr_list.nmsrs *
                                          sizeof(msr_list.indices[0])));

    kvm_msr_list->nmsrs = msr_list.nmsrs;
    ret = kvm_ioctl(s, KVM_GET_MSR_INDEX_LIST, kvm_msr_list);
    if (ret >= 0) {
        int i;

        for (i = 0; i < kvm_msr_list->nmsrs; i++) {
            switch (kvm_msr_list->indices[i]) {
            case MSR_STAR:
                has_msr_star = true;
                break;
            case MSR_VM_HSAVE_PA:
                has_msr_hsave_pa = true;
                break;
            case MSR_TSC_AUX:
                has_msr_tsc_aux = true;
                break;
            case MSR_TSC_ADJUST:
                has_msr_tsc_adjust = true;
                break;
            case MSR_IA32_TSCDEADLINE:
                has_msr_tsc_deadline = true;
                break;
            case MSR_IA32_SMBASE:
                has_msr_smbase = true;
                break;
            case MSR_SMI_COUNT:
                has_msr_smi_count = true;
                break;
            case MSR_IA32_MISC_ENABLE:
                has_msr_misc_enable = true;
                break;
            case MSR_IA32_BNDCFGS:
                has_msr_bndcfgs = true;
                break;
            case MSR_IA32_XSS:
                has_msr_xss = true;
                break;
            case MSR_IA32_UMWAIT_CONTROL:
                has_msr_umwait = true;
                break;
            case HV_X64_MSR_CRASH_CTL:
                has_msr_hv_crash = true;
                break;
            case HV_X64_MSR_RESET:
                has_msr_hv_reset = true;
                break;
            case HV_X64_MSR_VP_INDEX:
                has_msr_hv_vpindex = true;
                break;
            case HV_X64_MSR_VP_RUNTIME:
                has_msr_hv_runtime = true;
                break;
            case HV_X64_MSR_SCONTROL:
                has_msr_hv_synic = true;
                break;
            case HV_X64_MSR_STIMER0_CONFIG:
                has_msr_hv_stimer = true;
                break;
            case HV_X64_MSR_TSC_FREQUENCY:
                has_msr_hv_frequencies = true;
                break;
            case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
                has_msr_hv_reenlightenment = true;
                break;
            case MSR_IA32_SPEC_CTRL:
                has_msr_spec_ctrl = true;
                break;
            case MSR_AMD64_TSC_RATIO:
                has_tsc_scale_msr = true;
                break;
            case MSR_IA32_TSX_CTRL:
                has_msr_tsx_ctrl = true;
                break;
            case MSR_VIRT_SSBD:
                has_msr_virt_ssbd = true;
                break;
            case MSR_IA32_ARCH_CAPABILITIES:
                has_msr_arch_capabs = true;
                break;
            case MSR_IA32_CORE_CAPABILITY:
                has_msr_core_capabs = true;
                break;
            case MSR_IA32_PERF_CAPABILITIES:
                has_msr_perf_capabs = true;
                break;
            case MSR_IA32_VMX_VMFUNC:
                has_msr_vmx_vmfunc = true;
                break;
            case MSR_IA32_UCODE_REV:
                has_msr_ucode_rev = true;
                break;
            case MSR_IA32_VMX_PROCBASED_CTLS2:
                has_msr_vmx_procbased_ctls2 = true;
                break;
            case MSR_IA32_PKRS:
                has_msr_pkrs = true;
                break;
            }
        }
    }

    g_free(kvm_msr_list);

    return ret;
}

static Notifier smram_machine_done;
static KVMMemoryListener smram_listener;
static AddressSpace smram_address_space;
static MemoryRegion smram_as_root;
static MemoryRegion smram_as_mem;

static void register_smram_listener(Notifier *n, void *unused)
{
    MemoryRegion *smram =
        (MemoryRegion *) object_resolve_path("/machine/smram", NULL);

    /* Outer container... */
    memory_region_init(&smram_as_root, OBJECT(kvm_state), "mem-container-smram", ~0ull);
    memory_region_set_enabled(&smram_as_root, true);

    /* ... with two regions inside: normal system memory with low
     * priority, and...
     */
    memory_region_init_alias(&smram_as_mem, OBJECT(kvm_state), "mem-smram",
                             get_system_memory(), 0, ~0ull);
    memory_region_add_subregion_overlap(&smram_as_root, 0, &smram_as_mem, 0);
    memory_region_set_enabled(&smram_as_mem, true);

    if (smram) {
        /* ... SMRAM with higher priority */
        memory_region_add_subregion_overlap(&smram_as_root, 0, smram, 10);
        memory_region_set_enabled(smram, true);
    }

    address_space_init(&smram_address_space, &smram_as_root, "KVM-SMRAM");
    kvm_memory_listener_register(kvm_state, &smram_listener,
                                 &smram_address_space, 1, "kvm-smram");
}

int kvm_arch_init(MachineState *ms, KVMState *s)
{
    uint64_t identity_base = 0xfffbc000;
    uint64_t shadow_mem;
    int ret;
    struct utsname utsname;
    Error *local_err = NULL;

    /*
     * Initialize SEV context, if required
     *
     * If no memory encryption is requested (ms->cgs == NULL) this is
     * a no-op.
     *
     * It's also a no-op if a non-SEV confidential guest support
     * mechanism is selected.  SEV is the only mechanism available to
     * select on x86 at present, so this doesn't arise, but if new
     * mechanisms are supported in future (e.g. TDX), they'll need
     * their own initialization either here or elsewhere.
     */
    ret = sev_kvm_init(ms->cgs, &local_err);
    if (ret < 0) {
        error_report_err(local_err);
        return ret;
    }

    if (!kvm_check_extension(s, KVM_CAP_IRQ_ROUTING)) {
        error_report("kvm: KVM_CAP_IRQ_ROUTING not supported by KVM");
        return -ENOTSUP;
    }

    has_xsave = kvm_check_extension(s, KVM_CAP_XSAVE);
    has_xcrs = kvm_check_extension(s, KVM_CAP_XCRS);
    has_pit_state2 = kvm_check_extension(s, KVM_CAP_PIT_STATE2);
    has_sregs2 = kvm_check_extension(s, KVM_CAP_SREGS2) > 0;

    hv_vpindex_settable = kvm_check_extension(s, KVM_CAP_HYPERV_VP_INDEX);

    has_exception_payload = kvm_check_extension(s, KVM_CAP_EXCEPTION_PAYLOAD);
    if (has_exception_payload) {
        ret = kvm_vm_enable_cap(s, KVM_CAP_EXCEPTION_PAYLOAD, 0, true);
        if (ret < 0) {
            error_report("kvm: Failed to enable exception payload cap: %s",
                         strerror(-ret));
            return ret;
        }
    }

    ret = kvm_get_supported_msrs(s);
    if (ret < 0) {
        return ret;
    }

    kvm_get_supported_feature_msrs(s);

    uname(&utsname);
    lm_capable_kernel = strcmp(utsname.machine, "x86_64") == 0;

    /*
     * On older Intel CPUs, KVM uses vm86 mode to emulate 16-bit code directly.
     * In order to use vm86 mode, an EPT identity map and a TSS  are needed.
     * Since these must be part of guest physical memory, we need to allocate
     * them, both by setting their start addresses in the kernel and by
     * creating a corresponding e820 entry. We need 4 pages before the BIOS.
     *
     * Older KVM versions may not support setting the identity map base. In
     * that case we need to stick with the default, i.e. a 256K maximum BIOS
     * size.
     */
    if (kvm_check_extension(s, KVM_CAP_SET_IDENTITY_MAP_ADDR)) {
        /* Allows up to 16M BIOSes. */
        identity_base = 0xfeffc000;

        ret = kvm_vm_ioctl(s, KVM_SET_IDENTITY_MAP_ADDR, &identity_base);
        if (ret < 0) {
            return ret;
        }
    }

    /* Set TSS base one page after EPT identity map. */
    ret = kvm_vm_ioctl(s, KVM_SET_TSS_ADDR, identity_base + 0x1000);
    if (ret < 0) {
        return ret;
    }

    /* Tell fw_cfg to notify the BIOS to reserve the range. */
    ret = e820_add_entry(identity_base, 0x4000, E820_RESERVED);
    if (ret < 0) {
        fprintf(stderr, "e820_add_entry() table is full\n");
        return ret;
    }

    shadow_mem = object_property_get_int(OBJECT(s), "kvm-shadow-mem", &error_abort);
    if (shadow_mem != -1) {
        shadow_mem /= 4096;
        ret = kvm_vm_ioctl(s, KVM_SET_NR_MMU_PAGES, shadow_mem);
        if (ret < 0) {
            return ret;
        }
    }

    if (kvm_check_extension(s, KVM_CAP_X86_SMM) &&
        object_dynamic_cast(OBJECT(ms), TYPE_X86_MACHINE) &&
        x86_machine_is_smm_enabled(X86_MACHINE(ms))) {
        smram_machine_done.notify = register_smram_listener;
        qemu_add_machine_init_done_notifier(&smram_machine_done);
    }

    if (enable_cpu_pm) {
        int disable_exits = kvm_check_extension(s, KVM_CAP_X86_DISABLE_EXITS);
        int ret;

/* Work around for kernel header with a typo. TODO: fix header and drop. */
#if defined(KVM_X86_DISABLE_EXITS_HTL) && !defined(KVM_X86_DISABLE_EXITS_HLT)
#define KVM_X86_DISABLE_EXITS_HLT KVM_X86_DISABLE_EXITS_HTL
#endif
        if (disable_exits) {
            disable_exits &= (KVM_X86_DISABLE_EXITS_MWAIT |
                              KVM_X86_DISABLE_EXITS_HLT |
                              KVM_X86_DISABLE_EXITS_PAUSE |
                              KVM_X86_DISABLE_EXITS_CSTATE);
        }

        ret = kvm_vm_enable_cap(s, KVM_CAP_X86_DISABLE_EXITS, 0,
                                disable_exits);
        if (ret < 0) {
            error_report("kvm: guest stopping CPU not supported: %s",
                         strerror(-ret));
        }
    }

    if (object_dynamic_cast(OBJECT(ms), TYPE_X86_MACHINE)) {
        X86MachineState *x86ms = X86_MACHINE(ms);

        if (x86ms->bus_lock_ratelimit > 0) {
            ret = kvm_check_extension(s, KVM_CAP_X86_BUS_LOCK_EXIT);
            if (!(ret & KVM_BUS_LOCK_DETECTION_EXIT)) {
                error_report("kvm: bus lock detection unsupported");
                return -ENOTSUP;
            }
            ret = kvm_vm_enable_cap(s, KVM_CAP_X86_BUS_LOCK_EXIT, 0,
                                    KVM_BUS_LOCK_DETECTION_EXIT);
            if (ret < 0) {
                error_report("kvm: Failed to enable bus lock detection cap: %s",
                             strerror(-ret));
                return ret;
            }
            ratelimit_init(&bus_lock_ratelimit_ctrl);
            ratelimit_set_speed(&bus_lock_ratelimit_ctrl,
                                x86ms->bus_lock_ratelimit, BUS_LOCK_SLICE_TIME);
        }
    }

    return 0;
}

static void set_v8086_seg(struct kvm_segment *lhs, const SegmentCache *rhs)
{
    lhs->selector = rhs->selector;
    lhs->base = rhs->base;
    lhs->limit = rhs->limit;
    lhs->type = 3;
    lhs->present = 1;
    lhs->dpl = 3;
    lhs->db = 0;
    lhs->s = 1;
    lhs->l = 0;
    lhs->g = 0;
    lhs->avl = 0;
    lhs->unusable = 0;
}

static void set_seg(struct kvm_segment *lhs, const SegmentCache *rhs)
{
    unsigned flags = rhs->flags;
    lhs->selector = rhs->selector;
    lhs->base = rhs->base;
    lhs->limit = rhs->limit;
    lhs->type = (flags >> DESC_TYPE_SHIFT) & 15;
    lhs->present = (flags & DESC_P_MASK) != 0;
    lhs->dpl = (flags >> DESC_DPL_SHIFT) & 3;
    lhs->db = (flags >> DESC_B_SHIFT) & 1;
    lhs->s = (flags & DESC_S_MASK) != 0;
    lhs->l = (flags >> DESC_L_SHIFT) & 1;
    lhs->g = (flags & DESC_G_MASK) != 0;
    lhs->avl = (flags & DESC_AVL_MASK) != 0;
    lhs->unusable = !lhs->present;
    lhs->padding = 0;
}

static void get_seg(SegmentCache *lhs, const struct kvm_segment *rhs)
{
    lhs->selector = rhs->selector;
    lhs->base = rhs->base;
    lhs->limit = rhs->limit;
    lhs->flags = (rhs->type << DESC_TYPE_SHIFT) |
                 ((rhs->present && !rhs->unusable) * DESC_P_MASK) |
                 (rhs->dpl << DESC_DPL_SHIFT) |
                 (rhs->db << DESC_B_SHIFT) |
                 (rhs->s * DESC_S_MASK) |
                 (rhs->l << DESC_L_SHIFT) |
                 (rhs->g * DESC_G_MASK) |
                 (rhs->avl * DESC_AVL_MASK);
}

static void kvm_getput_reg(__u64 *kvm_reg, target_ulong *qemu_reg, int set)
{
    if (set) {
        *kvm_reg = *qemu_reg;
    } else {
        *qemu_reg = *kvm_reg;
    }
}

static int kvm_getput_regs(X86CPU *cpu, int set)
{
    CPUX86State *env = &cpu->env;
    struct kvm_regs regs;
    int ret = 0;

    if (!set) {
        ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_REGS, &regs);
        if (ret < 0) {
            return ret;
        }
    }

    kvm_getput_reg(&regs.rax, &env->regs[R_EAX], set);
    kvm_getput_reg(&regs.rbx, &env->regs[R_EBX], set);
    kvm_getput_reg(&regs.rcx, &env->regs[R_ECX], set);
    kvm_getput_reg(&regs.rdx, &env->regs[R_EDX], set);
    kvm_getput_reg(&regs.rsi, &env->regs[R_ESI], set);
    kvm_getput_reg(&regs.rdi, &env->regs[R_EDI], set);
    kvm_getput_reg(&regs.rsp, &env->regs[R_ESP], set);
    kvm_getput_reg(&regs.rbp, &env->regs[R_EBP], set);
#ifdef TARGET_X86_64
    kvm_getput_reg(&regs.r8, &env->regs[8], set);
    kvm_getput_reg(&regs.r9, &env->regs[9], set);
    kvm_getput_reg(&regs.r10, &env->regs[10], set);
    kvm_getput_reg(&regs.r11, &env->regs[11], set);
    kvm_getput_reg(&regs.r12, &env->regs[12], set);
    kvm_getput_reg(&regs.r13, &env->regs[13], set);
    kvm_getput_reg(&regs.r14, &env->regs[14], set);
    kvm_getput_reg(&regs.r15, &env->regs[15], set);
#endif

    kvm_getput_reg(&regs.rflags, &env->eflags, set);
    kvm_getput_reg(&regs.rip, &env->eip, set);

    if (set) {
        ret = kvm_vcpu_ioctl(CPU(cpu), KVM_SET_REGS, &regs);
    }

    return ret;
}

static int kvm_put_fpu(X86CPU *cpu)
{
    CPUX86State *env = &cpu->env;
    struct kvm_fpu fpu;
    int i;

    memset(&fpu, 0, sizeof fpu);
    fpu.fsw = env->fpus & ~(7 << 11);
    fpu.fsw |= (env->fpstt & 7) << 11;
    fpu.fcw = env->fpuc;
    fpu.last_opcode = env->fpop;
    fpu.last_ip = env->fpip;
    fpu.last_dp = env->fpdp;
    for (i = 0; i < 8; ++i) {
        fpu.ftwx |= (!env->fptags[i]) << i;
    }
    memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs);
    for (i = 0; i < CPU_NB_REGS; i++) {
        stq_p(&fpu.xmm[i][0], env->xmm_regs[i].ZMM_Q(0));
        stq_p(&fpu.xmm[i][8], env->xmm_regs[i].ZMM_Q(1));
    }
    fpu.mxcsr = env->mxcsr;

    return kvm_vcpu_ioctl(CPU(cpu), KVM_SET_FPU, &fpu);
}

static int kvm_put_xsave(X86CPU *cpu)
{
    CPUX86State *env = &cpu->env;
    void *xsave = env->xsave_buf;

    if (!has_xsave) {
        return kvm_put_fpu(cpu);
    }
    x86_cpu_xsave_all_areas(cpu, xsave, env->xsave_buf_len);

    return kvm_vcpu_ioctl(CPU(cpu), KVM_SET_XSAVE, xsave);
}

static int kvm_put_xcrs(X86CPU *cpu)
{
    CPUX86State *env = &cpu->env;
    struct kvm_xcrs xcrs = {};

    if (!has_xcrs) {
        return 0;
    }

    xcrs.nr_xcrs = 1;
    xcrs.flags = 0;
    xcrs.xcrs[0].xcr = 0;
    xcrs.xcrs[0].value = env->xcr0;
    return kvm_vcpu_ioctl(CPU(cpu), KVM_SET_XCRS, &xcrs);
}

static int kvm_put_sregs(X86CPU *cpu)
{
    CPUX86State *env = &cpu->env;
    struct kvm_sregs sregs;

    /*
     * The interrupt_bitmap is ignored because KVM_SET_SREGS is
     * always followed by KVM_SET_VCPU_EVENTS.
     */
    memset(sregs.interrupt_bitmap, 0, sizeof(sregs.interrupt_bitmap));

    if ((env->eflags & VM_MASK)) {
        set_v8086_seg(&sregs.cs, &env->segs[R_CS]);
        set_v8086_seg(&sregs.ds, &env->segs[R_DS]);
        set_v8086_seg(&sregs.es, &env->segs[R_ES]);
        set_v8086_seg(&sregs.fs, &env->segs[R_FS]);
        set_v8086_seg(&sregs.gs, &env->segs[R_GS]);
        set_v8086_seg(&sregs.ss, &env->segs[R_SS]);
    } else {
        set_seg(&sregs.cs, &env->segs[R_CS]);
        set_seg(&sregs.ds, &env->segs[R_DS]);
        set_seg(&sregs.es, &env->segs[R_ES]);
        set_seg(&sregs.fs, &env->segs[R_FS]);
        set_seg(&sregs.gs, &env->segs[R_GS]);
        set_seg(&sregs.ss, &env->segs[R_SS]);
    }

    set_seg(&sregs.tr, &env->tr);
    set_seg(&sregs.ldt, &env->ldt);

    sregs.idt.limit = env->idt.limit;
    sregs.idt.base = env->idt.base;
    memset(sregs.idt.padding, 0, sizeof sregs.idt.padding);
    sregs.gdt.limit = env->gdt.limit;
    sregs.gdt.base = env->gdt.base;
    memset(sregs.gdt.padding, 0, sizeof sregs.gdt.padding);

    sregs.cr0 = env->cr[0];
    sregs.cr2 = env->cr[2];
    sregs.cr3 = env->cr[3];
    sregs.cr4 = env->cr[4];

    sregs.cr8 = cpu_get_apic_tpr(cpu->apic_state);
    sregs.apic_base = cpu_get_apic_base(cpu->apic_state);

    sregs.efer = env->efer;

    return kvm_vcpu_ioctl(CPU(cpu), KVM_SET_SREGS, &sregs);
}

static int kvm_put_sregs2(X86CPU *cpu)
{
    CPUX86State *env = &cpu->env;
    struct kvm_sregs2 sregs;
    int i;

    sregs.flags = 0;

    if ((env->eflags & VM_MASK)) {
        set_v8086_seg(&sregs.cs, &env->segs[R_CS]);
        set_v8086_seg(&sregs.ds, &env->segs[R_DS]);
        set_v8086_seg(&sregs.es, &env->segs[R_ES]);
        set_v8086_seg(&sregs.fs, &env->segs[R_FS]);
        set_v8086_seg(&sregs.gs, &env->segs[R_GS]);
        set_v8086_seg(&sregs.ss, &env->segs[R_SS]);
    } else {
        set_seg(&sregs.cs, &env->segs[R_CS]);
        set_seg(&sregs.ds, &env->segs[R_DS]);
        set_seg(&sregs.es, &env->segs[R_ES]);
        set_seg(&sregs.fs, &env->segs[R_FS]);
        set_seg(&sregs.gs, &env->segs[R_GS]);
        set_seg(&sregs.ss, &env->segs[R_SS]);
    }

    set_seg(&sregs.tr, &env->tr);
    set_seg(&sregs.ldt, &env->ldt);

    sregs.idt.limit = env->idt.limit;
    sregs.idt.base = env->idt.base;
    memset(sregs.idt.padding, 0, sizeof sregs.idt.padding);
    sregs.gdt.limit = env->gdt.limit;
    sregs.gdt.base = env->gdt.base;
    memset(sregs.gdt.padding, 0, sizeof sregs.gdt.padding);

    sregs.cr0 = env->cr[0];
    sregs.cr2 = env->cr[2];
    sregs.cr3 = env->cr[3];
    sregs.cr4 = env->cr[4];

    sregs.cr8 = cpu_get_apic_tpr(cpu->apic_state);
    sregs.apic_base = cpu_get_apic_base(cpu->apic_state);

    sregs.efer = env->efer;

    if (env->pdptrs_valid) {
        for (i = 0; i < 4; i++) {
            sregs.pdptrs[i] = env->pdptrs[i];
        }
        sregs.flags |= KVM_SREGS2_FLAGS_PDPTRS_VALID;
    }

    return kvm_vcpu_ioctl(CPU(cpu), KVM_SET_SREGS2, &sregs);
}


static void kvm_msr_buf_reset(X86CPU *cpu)
{
    memset(cpu->kvm_msr_buf, 0, MSR_BUF_SIZE);
}

static void kvm_msr_entry_add(X86CPU *cpu, uint32_t index, uint64_t value)
{
    struct kvm_msrs *msrs = cpu->kvm_msr_buf;
    void *limit = ((void *)msrs) + MSR_BUF_SIZE;
    struct kvm_msr_entry *entry = &msrs->entries[msrs->nmsrs];

    assert((void *)(entry + 1) <= limit);

    entry->index = index;
    entry->reserved = 0;
    entry->data = value;
    msrs->nmsrs++;
}

static int kvm_put_one_msr(X86CPU *cpu, int index, uint64_t value)
{
    kvm_msr_buf_reset(cpu);
    kvm_msr_entry_add(cpu, index, value);

    return kvm_vcpu_ioctl(CPU(cpu), KVM_SET_MSRS, cpu->kvm_msr_buf);
}

void kvm_put_apicbase(X86CPU *cpu, uint64_t value)
{
    int ret;

    ret = kvm_put_one_msr(cpu, MSR_IA32_APICBASE, value);
    assert(ret == 1);
}

static int kvm_put_tscdeadline_msr(X86CPU *cpu)
{
    CPUX86State *env = &cpu->env;
    int ret;

    if (!has_msr_tsc_deadline) {
        return 0;
    }

    ret = kvm_put_one_msr(cpu, MSR_IA32_TSCDEADLINE, env->tsc_deadline);
    if (ret < 0) {
        return ret;
    }

    assert(ret == 1);
    return 0;
}

/*
 * Provide a separate write service for the feature control MSR in order to
 * kick the VCPU out of VMXON or even guest mode on reset. This has to be done
 * before writing any other state because forcibly leaving nested mode
 * invalidates the VCPU state.
 */
static int kvm_put_msr_feature_control(X86CPU *cpu)
{
    int ret;

    if (!has_msr_feature_control) {
        return 0;
    }

    ret = kvm_put_one_msr(cpu, MSR_IA32_FEATURE_CONTROL,
                          cpu->env.msr_ia32_feature_control);
    if (ret < 0) {
        return ret;
    }

    assert(ret == 1);
    return 0;
}

static uint64_t make_vmx_msr_value(uint32_t index, uint32_t features)
{
    uint32_t default1, can_be_one, can_be_zero;
    uint32_t must_be_one;

    switch (index) {
    case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
        default1 = 0x00000016;
        break;
    case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
        default1 = 0x0401e172;
        break;
    case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
        default1 = 0x000011ff;
        break;
    case MSR_IA32_VMX_TRUE_EXIT_CTLS:
        default1 = 0x00036dff;
        break;
    case MSR_IA32_VMX_PROCBASED_CTLS2:
        default1 = 0;
        break;
    default:
        abort();
    }

    /* If a feature bit is set, the control can be either set or clear.
     * Otherwise the value is limited to either 0 or 1 by default1.
     */
    can_be_one = features | default1;
    can_be_zero = features | ~default1;
    must_be_one = ~can_be_zero;

    /*
     * Bit 0:31 -> 0 if the control bit can be zero (i.e. 1 if it must be one).
     * Bit 32:63 -> 1 if the control bit can be one.
     */
    return must_be_one | (((uint64_t)can_be_one) << 32);
}

static void kvm_msr_entry_add_vmx(X86CPU *cpu, FeatureWordArray f)
{
    uint64_t kvm_vmx_basic =
        kvm_arch_get_supported_msr_feature(kvm_state,
                                           MSR_IA32_VMX_BASIC);

    if (!kvm_vmx_basic) {
        /* If the kernel doesn't support VMX feature (kvm_intel.nested=0),
         * then kvm_vmx_basic will be 0 and KVM_SET_MSR will fail.
         */
        return;
    }

    uint64_t kvm_vmx_misc =
        kvm_arch_get_supported_msr_feature(kvm_state,
                                           MSR_IA32_VMX_MISC);
    uint64_t kvm_vmx_ept_vpid =
        kvm_arch_get_supported_msr_feature(kvm_state,
                                           MSR_IA32_VMX_EPT_VPID_CAP);

    /*
     * If the guest is 64-bit, a value of 1 is allowed for the host address
     * space size vmexit control.
     */
    uint64_t fixed_vmx_exit = f[FEAT_8000_0001_EDX] & CPUID_EXT2_LM
        ? (uint64_t)VMX_VM_EXIT_HOST_ADDR_SPACE_SIZE << 32 : 0;

    /*
     * Bits 0-30, 32-44 and 50-53 come from the host.  KVM should
     * not change them for backwards compatibility.
     */
    uint64_t fixed_vmx_basic = kvm_vmx_basic &
        (MSR_VMX_BASIC_VMCS_REVISION_MASK |
         MSR_VMX_BASIC_VMXON_REGION_SIZE_MASK |
         MSR_VMX_BASIC_VMCS_MEM_TYPE_MASK);

    /*
     * Same for bits 0-4 and 25-27.  Bits 16-24 (CR3 target count) can
     * change in the future but are always zero for now, clear them to be
     * future proof.  Bits 32-63 in theory could change, though KVM does
     * not support dual-monitor treatment and probably never will; mask
     * them out as well.
     */
    uint64_t fixed_vmx_misc = kvm_vmx_misc &
        (MSR_VMX_MISC_PREEMPTION_TIMER_SHIFT_MASK |
         MSR_VMX_MISC_MAX_MSR_LIST_SIZE_MASK);

    /*
     * EPT memory types should not change either, so we do not bother
     * adding features for them.
     */
    uint64_t fixed_vmx_ept_mask =
            (f[FEAT_VMX_SECONDARY_CTLS] & VMX_SECONDARY_EXEC_ENABLE_EPT ?
             MSR_VMX_EPT_UC | MSR_VMX_EPT_WB : 0);
    uint64_t fixed_vmx_ept_vpid = kvm_vmx_ept_vpid & fixed_vmx_ept_mask;

    kvm_msr_entry_add(cpu, MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
                      make_vmx_msr_value(MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
                                         f[FEAT_VMX_PROCBASED_CTLS]));
    kvm_msr_entry_add(cpu, MSR_IA32_VMX_TRUE_PINBASED_CTLS,
                      make_vmx_msr_value(MSR_IA32_VMX_TRUE_PINBASED_CTLS,
                                         f[FEAT_VMX_PINBASED_CTLS]));
    kvm_msr_entry_add(cpu, MSR_IA32_VMX_TRUE_EXIT_CTLS,
                      make_vmx_msr_value(MSR_IA32_VMX_TRUE_EXIT_CTLS,
                                         f[FEAT_VMX_EXIT_CTLS]) | fixed_vmx_exit);
    kvm_msr_entry_add(cpu, MSR_IA32_VMX_TRUE_ENTRY_CTLS,
                      make_vmx_msr_value(MSR_IA32_VMX_TRUE_ENTRY_CTLS,
                                         f[FEAT_VMX_ENTRY_CTLS]));
    kvm_msr_entry_add(cpu, MSR_IA32_VMX_PROCBASED_CTLS2,
                      make_vmx_msr_value(MSR_IA32_VMX_PROCBASED_CTLS2,
                                         f[FEAT_VMX_SECONDARY_CTLS]));
    kvm_msr_entry_add(cpu, MSR_IA32_VMX_EPT_VPID_CAP,
                      f[FEAT_VMX_EPT_VPID_CAPS] | fixed_vmx_ept_vpid);
    kvm_msr_entry_add(cpu, MSR_IA32_VMX_BASIC,
                      f[FEAT_VMX_BASIC] | fixed_vmx_basic);
    kvm_msr_entry_add(cpu, MSR_IA32_VMX_MISC,
                      f[FEAT_VMX_MISC] | fixed_vmx_misc);
    if (has_msr_vmx_vmfunc) {
        kvm_msr_entry_add(cpu, MSR_IA32_VMX_VMFUNC, f[FEAT_VMX_VMFUNC]);
    }

    /*
     * Just to be safe, write these with constant values.  The CRn_FIXED1
     * MSRs are generated by KVM based on the vCPU's CPUID.
     */
    kvm_msr_entry_add(cpu, MSR_IA32_VMX_CR0_FIXED0,
                      CR0_PE_MASK | CR0_PG_MASK | CR0_NE_MASK);
    kvm_msr_entry_add(cpu, MSR_IA32_VMX_CR4_FIXED0,
                      CR4_VMXE_MASK);

    if (f[FEAT_VMX_SECONDARY_CTLS] & VMX_SECONDARY_EXEC_TSC_SCALING) {
        /* TSC multiplier (0x2032).  */
        kvm_msr_entry_add(cpu, MSR_IA32_VMX_VMCS_ENUM, 0x32);
    } else {
        /* Preemption timer (0x482E).  */
        kvm_msr_entry_add(cpu, MSR_IA32_VMX_VMCS_ENUM, 0x2E);
    }
}

static void kvm_msr_entry_add_perf(X86CPU *cpu, FeatureWordArray f)
{
    uint64_t kvm_perf_cap =
        kvm_arch_get_supported_msr_feature(kvm_state,
                                           MSR_IA32_PERF_CAPABILITIES);

    if (kvm_perf_cap) {
        kvm_msr_entry_add(cpu, MSR_IA32_PERF_CAPABILITIES,
                        kvm_perf_cap & f[FEAT_PERF_CAPABILITIES]);
    }
}

static int kvm_buf_set_msrs(X86CPU *cpu)
{
    int ret = kvm_vcpu_ioctl(CPU(cpu), KVM_SET_MSRS, cpu->kvm_msr_buf);
    if (ret < 0) {
        return ret;
    }

    if (ret < cpu->kvm_msr_buf->nmsrs) {
        struct kvm_msr_entry *e = &cpu->kvm_msr_buf->entries[ret];
        error_report("error: failed to set MSR 0x%" PRIx32 " to 0x%" PRIx64,
                     (uint32_t)e->index, (uint64_t)e->data);
    }

    assert(ret == cpu->kvm_msr_buf->nmsrs);
    return 0;
}

static void kvm_init_msrs(X86CPU *cpu)