Archipelago » qemu

/*

 * 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 <sys/types.h>

#include <sys/ioctl.h>

#include <sys/mman.h>

#include <sys/utsname.h>

#include <linux/kvm.h>

#include "qemu-common.h"

#include "sysemu.h"

#include "kvm.h"

#include "cpu.h"

#include "gdbstub.h"

#include "host-utils.h"

#include "hw/pc.h"

#include "hw/apic.h"

#include "ioport.h"

#ifdef CONFIG_KVM_PARA

#include <linux/kvm_para.h>

#endif

//

//#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

#define MSR_KVM_WALL_CLOCK  0x11

#define MSR_KVM_SYSTEM_TIME 0x12

#ifndef BUS_MCEERR_AR

#define BUS_MCEERR_AR 4

#endif

#ifndef BUS_MCEERR_AO

#define BUS_MCEERR_AO 5

#endif

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;

#if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ASYNC_PF)

static bool has_msr_async_pf_en;

#endif

static int lm_capable_kernel;

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 = (struct kvm_cpuid2 *)qemu_mallocz(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) {

            qemu_free(cpuid);

            return NULL;

        } else {

            fprintf(stderr, "KVM_GET_SUPPORTED_CPUID failed: %s\n",

                    strerror(-r));

            exit(1);

        }

    }

    return cpuid;

}

#ifdef CONFIG_KVM_PARA

struct kvm_para_features {

    int cap;

    int feature;

} para_features[] = {

    { KVM_CAP_CLOCKSOURCE, KVM_FEATURE_CLOCKSOURCE },

    { KVM_CAP_NOP_IO_DELAY, KVM_FEATURE_NOP_IO_DELAY },

    { KVM_CAP_PV_MMU, KVM_FEATURE_MMU_OP },

#ifdef KVM_CAP_ASYNC_PF

    { KVM_CAP_ASYNC_PF, KVM_FEATURE_ASYNC_PF },

#endif

    { -1, -1 }

};

static int get_para_features(CPUState *env)

{

    int i, features = 0;

    for (i = 0; i < ARRAY_SIZE(para_features) - 1; i++) {

        if (kvm_check_extension(env->kvm_state, para_features[i].cap)) {

            features |= (1 << para_features[i].feature);

        }

    }

    return features;

}

#endif

uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,

                                      uint32_t index, int reg)

{

    struct kvm_cpuid2 *cpuid;

    int i, max;

    uint32_t ret = 0;

    uint32_t cpuid_1_edx;

#ifdef CONFIG_KVM_PARA

    int has_kvm_features = 0;

#endif

    max = 1;

    while ((cpuid = try_get_cpuid(env->kvm_state, max)) == NULL) {

        max *= 2;

    }

    for (i = 0; i < cpuid->nent; ++i) {

        if (cpuid->entries[i].function == function &&

            cpuid->entries[i].index == index) {

#ifdef CONFIG_KVM_PARA

            if (cpuid->entries[i].function == KVM_CPUID_FEATURES) {

                has_kvm_features = 1;

            }

#endif

            switch (reg) {

            case R_EAX:

                ret = cpuid->entries[i].eax;

                break;

            case R_EBX:

                ret = cpuid->entries[i].ebx;

                break;

            case R_ECX:

                ret = cpuid->entries[i].ecx;

                break;

            case R_EDX:

                ret = cpuid->entries[i].edx;

                switch (function) {

                case 1:

                    /* KVM before 2.6.30 misreports the following features */

                    ret |= CPUID_MTRR | CPUID_PAT | CPUID_MCE | CPUID_MCA;

                    break;

                case 0x80000001:

                    /* 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(env, 1, 0, R_EDX);

                    ret |= cpuid_1_edx & 0x183f7ff;

                    break;

                }

                break;

            }

        }

    }

    qemu_free(cpuid);

#ifdef CONFIG_KVM_PARA

    /* fallback for older kernels */

    if (!has_kvm_features && (function == KVM_CPUID_FEATURES)) {

        ret = get_para_features(env);

    }

#endif

    return ret;

}

typedef struct HWPoisonPage {

    ram_addr_t ram_addr;

    QLIST_ENTRY(HWPoisonPage) list;

} HWPoisonPage;

static QLIST_HEAD(, HWPoisonPage) hwpoison_page_list =

    QLIST_HEAD_INITIALIZER(hwpoison_page_list);

static void kvm_unpoison_all(void *param)

{

    HWPoisonPage *page, *next_page;

    QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) {

        QLIST_REMOVE(page, list);

        qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE);

        qemu_free(page);

    }

}

#ifdef KVM_CAP_MCE

static void kvm_hwpoison_page_add(ram_addr_t ram_addr)

{

    HWPoisonPage *page;

    QLIST_FOREACH(page, &hwpoison_page_list, list) {

        if (page->ram_addr == ram_addr) {

            return;

        }

    }

    page = qemu_malloc(sizeof(HWPoisonPage));

    page->ram_addr = ram_addr;

    QLIST_INSERT_HEAD(&hwpoison_page_list, page, list);

}

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(CPUState *env, target_phys_addr_t paddr, int code)

{

    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;

    if (code == BUS_MCEERR_AR) {

        status |= MCI_STATUS_AR | 0x134;

        mcg_status |= MCG_STATUS_EIPV;

    } else {

        status |= 0xc0;

        mcg_status |= MCG_STATUS_RIPV;

    }

    cpu_x86_inject_mce(NULL, env, 9, status, mcg_status, paddr,

                       (MCM_ADDR_PHYS << 6) | 0xc,

                       cpu_x86_support_mca_broadcast(env) ?

                       MCE_INJECT_BROADCAST : 0);

}

#endif /* KVM_CAP_MCE */

static void hardware_memory_error(void)

{

    fprintf(stderr, "Hardware memory error!\n");

    exit(1);

}

int kvm_arch_on_sigbus_vcpu(CPUState *env, int code, void *addr)

{

#ifdef KVM_CAP_MCE

    ram_addr_t ram_addr;

    target_phys_addr_t paddr;

    if ((env->mcg_cap & MCG_SER_P) && addr

        && (code == BUS_MCEERR_AR || code == BUS_MCEERR_AO)) {

        if (qemu_ram_addr_from_host(addr, &ram_addr) ||

            !kvm_physical_memory_addr_from_ram(env->kvm_state, ram_addr,

                                               &paddr)) {

            fprintf(stderr, "Hardware memory error for memory used by "

                    "QEMU itself instead of guest system!\n");

            /* Hope we are lucky for AO MCE */

            if (code == BUS_MCEERR_AO) {

                return 0;

            } else {

                hardware_memory_error();

            }

        }

        kvm_hwpoison_page_add(ram_addr);

        kvm_mce_inject(env, paddr, code);

    } else

#endif /* KVM_CAP_MCE */

    {

        if (code == BUS_MCEERR_AO) {

            return 0;

        } else if (code == BUS_MCEERR_AR) {

            hardware_memory_error();

        } else {

            return 1;

        }

    }

    return 0;

}

int kvm_arch_on_sigbus(int code, void *addr)

{

#ifdef KVM_CAP_MCE

    if ((first_cpu->mcg_cap & MCG_SER_P) && addr && code == BUS_MCEERR_AO) {

        ram_addr_t ram_addr;

        target_phys_addr_t paddr;

        /* Hope we are lucky for AO MCE */

        if (qemu_ram_addr_from_host(addr, &ram_addr) ||

            !kvm_physical_memory_addr_from_ram(first_cpu->kvm_state, ram_addr,

                                               &paddr)) {

            fprintf(stderr, "Hardware memory error for memory used by "

                    "QEMU itself instead of guest system!: %p\n", addr);

            return 0;

        }

        kvm_hwpoison_page_add(ram_addr);

        kvm_mce_inject(first_cpu, paddr, code);

    } else

#endif /* KVM_CAP_MCE */

    {

        if (code == BUS_MCEERR_AO) {

            return 0;

        } else if (code == BUS_MCEERR_AR) {

            hardware_memory_error();

        } else {

            return 1;

        }

    }

    return 0;

}

static int kvm_inject_mce_oldstyle(CPUState *env)

{

#ifdef KVM_CAP_MCE

    if (!kvm_has_vcpu_events() && env->exception_injected == EXCP12_MCHK) {

        unsigned int bank, bank_num = env->mcg_cap & 0xff;

        struct kvm_x86_mce mce;

        env->exception_injected = -1;

        /*

         * 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(env, KVM_X86_SET_MCE, &mce);

    }

#endif /* KVM_CAP_MCE */

    return 0;

}

static void cpu_update_state(void *opaque, int running, int reason)

{

    CPUState *env = opaque;

    if (running) {

        env->tsc_valid = false;

    }

}

int kvm_arch_init_vcpu(CPUState *env)

{

    struct {

        struct kvm_cpuid2 cpuid;

        struct kvm_cpuid_entry2 entries[100];

    } __attribute__((packed)) cpuid_data;

    uint32_t limit, i, j, cpuid_i;

    uint32_t unused;

    struct kvm_cpuid_entry2 *c;

#ifdef CONFIG_KVM_PARA

    uint32_t signature[3];

#endif

    env->cpuid_features &= kvm_arch_get_supported_cpuid(env, 1, 0, R_EDX);

    i = env->cpuid_ext_features & CPUID_EXT_HYPERVISOR;

    env->cpuid_ext_features &= kvm_arch_get_supported_cpuid(env, 1, 0, R_ECX);

    env->cpuid_ext_features |= i;

    env->cpuid_ext2_features &= kvm_arch_get_supported_cpuid(env, 0x80000001,

                                                             0, R_EDX);

    env->cpuid_ext3_features &= kvm_arch_get_supported_cpuid(env, 0x80000001,

                                                             0, R_ECX);

    env->cpuid_svm_features  &= kvm_arch_get_supported_cpuid(env, 0x8000000A,

                                                             0, R_EDX);

    cpuid_i = 0;

#ifdef CONFIG_KVM_PARA

    /* Paravirtualization CPUIDs */

    memcpy(signature, "KVMKVMKVM\0\0\0", 12);

    c = &cpuid_data.entries[cpuid_i++];

    memset(c, 0, sizeof(*c));

    c->function = KVM_CPUID_SIGNATURE;

    c->eax = 0;

    c->ebx = signature[0];

    c->ecx = signature[1];

    c->edx = signature[2];

    c = &cpuid_data.entries[cpuid_i++];

    memset(c, 0, sizeof(*c));

    c->function = KVM_CPUID_FEATURES;

    c->eax = env->cpuid_kvm_features & kvm_arch_get_supported_cpuid(env,

                                                KVM_CPUID_FEATURES, 0, R_EAX);

#ifdef KVM_CAP_ASYNC_PF

    has_msr_async_pf_en = c->eax & (1 << KVM_FEATURE_ASYNC_PF);

#endif

#endif

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

    for (i = 0; i <= limit; i++) {

        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) {

                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 4:

        case 0xb:

        case 0xd:

            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 (i == 4 && c->eax == 0) {

                    break;

                }

                if (i == 0xb && !(c->ecx & 0xff00)) {

                    break;

                }

                if (i == 0xd && c->eax == 0) {

                    break;

                }

                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);

            break;

        }

    }

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

    for (i = 0x80000000; i <= limit; i++) {

        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;

#ifdef KVM_CAP_MCE

    if (((env->cpuid_version >> 8)&0xF) >= 6

        && (env->cpuid_features&(CPUID_MCE|CPUID_MCA)) == (CPUID_MCE|CPUID_MCA)

        && kvm_check_extension(env->kvm_state, KVM_CAP_MCE) > 0) {

        uint64_t mcg_cap;

        int banks;

        int ret;

        ret = kvm_get_mce_cap_supported(env->kvm_state, &mcg_cap, &banks);

        if (ret < 0) {

            fprintf(stderr, "kvm_get_mce_cap_supported: %s", strerror(-ret));

            return ret;

        }

        if (banks > MCE_BANKS_DEF) {

            banks = MCE_BANKS_DEF;

        }

        mcg_cap &= MCE_CAP_DEF;

        mcg_cap |= banks;

        ret = kvm_vcpu_ioctl(env, KVM_X86_SETUP_MCE, &mcg_cap);

        if (ret < 0) {

            fprintf(stderr, "KVM_X86_SETUP_MCE: %s", strerror(-ret));

            return ret;

        }

        env->mcg_cap = mcg_cap;

    }

#endif

    qemu_add_vm_change_state_handler(cpu_update_state, env);

    return kvm_vcpu_ioctl(env, KVM_SET_CPUID2, &cpuid_data);

}

void kvm_arch_reset_vcpu(CPUState *env)

{

    env->exception_injected = -1;

    env->interrupt_injected = -1;

    env->xcr0 = 1;

    if (kvm_irqchip_in_kernel()) {

        env->mp_state = cpu_is_bsp(env) ? KVM_MP_STATE_RUNNABLE :

                                          KVM_MP_STATE_UNINITIALIZED;

    } else {

        env->mp_state = KVM_MP_STATE_RUNNABLE;

    }

}

static int kvm_get_supported_msrs(KVMState *s)

{

    static int kvm_supported_msrs;

    int ret = 0;

    /* first time */

    if (kvm_supported_msrs == 0) {

        struct kvm_msr_list msr_list, *kvm_msr_list;

        kvm_supported_msrs = -1;

        /* 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 = qemu_mallocz(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++) {

                if (kvm_msr_list->indices[i] == MSR_STAR) {

                    has_msr_star = true;

                    continue;

                }

                if (kvm_msr_list->indices[i] == MSR_VM_HSAVE_PA) {

                    has_msr_hsave_pa = true;

                    continue;

                }

            }

        }

        qemu_free(kvm_msr_list);

    }

    return ret;

}

int kvm_arch_init(KVMState *s)

{

    uint64_t identity_base = 0xfffbc000;

    int ret;

    struct utsname utsname;

    ret = kvm_get_supported_msrs(s);

    if (ret < 0) {

        return ret;

    }

    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.

     */

#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR

    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;

        }

    }

#endif

    /* 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;

    }

    qemu_register_reset(kvm_unpoison_all, NULL);

    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 = 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 * 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(CPUState *env, int set)

{

    struct kvm_regs regs;

    int ret = 0;

    if (!set) {

        ret = kvm_vcpu_ioctl(env, 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(env, KVM_SET_REGS, &regs);

    }

    return ret;

}

static int kvm_put_fpu(CPUState *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;

    for (i = 0; i < 8; ++i) {

        fpu.ftwx |= (!env->fptags[i]) << i;

    }

    memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs);

    memcpy(fpu.xmm, env->xmm_regs, sizeof env->xmm_regs);

    fpu.mxcsr = env->mxcsr;

    return kvm_vcpu_ioctl(env, KVM_SET_FPU, &fpu);

}

#ifdef KVM_CAP_XSAVE

#define XSAVE_CWD_RIP     2

#define XSAVE_CWD_RDP     4

#define XSAVE_MXCSR       6

#define XSAVE_ST_SPACE    8

#define XSAVE_XMM_SPACE   40

#define XSAVE_XSTATE_BV   128

#define XSAVE_YMMH_SPACE  144

#endif

static int kvm_put_xsave(CPUState *env)

{

#ifdef KVM_CAP_XSAVE

    int i, r;

    struct kvm_xsave* xsave;

    uint16_t cwd, swd, twd, fop;

    if (!kvm_has_xsave()) {

        return kvm_put_fpu(env);

    }

    xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));

    memset(xsave, 0, sizeof(struct kvm_xsave));

    cwd = swd = twd = fop = 0;

    swd = env->fpus & ~(7 << 11);

    swd |= (env->fpstt & 7) << 11;

    cwd = env->fpuc;

    for (i = 0; i < 8; ++i) {

        twd |= (!env->fptags[i]) << i;

    }

    xsave->region[0] = (uint32_t)(swd << 16) + cwd;

    xsave->region[1] = (uint32_t)(fop << 16) + twd;

    memcpy(&xsave->region[XSAVE_ST_SPACE], env->fpregs,

            sizeof env->fpregs);

    memcpy(&xsave->region[XSAVE_XMM_SPACE], env->xmm_regs,

            sizeof env->xmm_regs);

    xsave->region[XSAVE_MXCSR] = env->mxcsr;

    *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV] = env->xstate_bv;

    memcpy(&xsave->region[XSAVE_YMMH_SPACE], env->ymmh_regs,

            sizeof env->ymmh_regs);

    r = kvm_vcpu_ioctl(env, KVM_SET_XSAVE, xsave);

    qemu_free(xsave);

    return r;

#else

    return kvm_put_fpu(env);

#endif

}

static int kvm_put_xcrs(CPUState *env)

{

#ifdef KVM_CAP_XCRS

    struct kvm_xcrs xcrs;

    if (!kvm_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(env, KVM_SET_XCRS, &xcrs);

#else

    return 0;

#endif

}

static int kvm_put_sregs(CPUState *env)

{

    struct kvm_sregs sregs;

    memset(sregs.interrupt_bitmap, 0, sizeof(sregs.interrupt_bitmap));

    if (env->interrupt_injected >= 0) {

        sregs.interrupt_bitmap[env->interrupt_injected / 64] |=

                (uint64_t)1 << (env->interrupt_injected % 64);

    }

    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;

    sregs.gdt.limit = env->gdt.limit;

    sregs.gdt.base = env->gdt.base;

    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(env->apic_state);

    sregs.apic_base = cpu_get_apic_base(env->apic_state);

    sregs.efer = env->efer;

    return kvm_vcpu_ioctl(env, KVM_SET_SREGS, &sregs);

}

static void kvm_msr_entry_set(struct kvm_msr_entry *entry,

                              uint32_t index, uint64_t value)

{

    entry->index = index;

    entry->data = value;

}

static int kvm_put_msrs(CPUState *env, int level)

{

    struct {

        struct kvm_msrs info;

        struct kvm_msr_entry entries[100];

    } msr_data;

    struct kvm_msr_entry *msrs = msr_data.entries;

    int n = 0;

    kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_CS, env->sysenter_cs);

    kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_ESP, env->sysenter_esp);

    kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_EIP, env->sysenter_eip);

    kvm_msr_entry_set(&msrs[n++], MSR_PAT, env->pat);

    if (has_msr_star) {

        kvm_msr_entry_set(&msrs[n++], MSR_STAR, env->star);

    }

    if (has_msr_hsave_pa) {

        kvm_msr_entry_set(&msrs[n++], MSR_VM_HSAVE_PA, env->vm_hsave);

    }

#ifdef TARGET_X86_64

    if (lm_capable_kernel) {

        kvm_msr_entry_set(&msrs[n++], MSR_CSTAR, env->cstar);

        kvm_msr_entry_set(&msrs[n++], MSR_KERNELGSBASE, env->kernelgsbase);

        kvm_msr_entry_set(&msrs[n++], MSR_FMASK, env->fmask);

        kvm_msr_entry_set(&msrs[n++], MSR_LSTAR, env->lstar);

    }

#endif

    if (level == KVM_PUT_FULL_STATE) {

        /*

         * KVM is yet unable to synchronize TSC values of multiple VCPUs on

         * writeback. Until this is fixed, we only write the offset to SMP

         * guests after migration, desynchronizing the VCPUs, but avoiding