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 <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"

#include "kvm_x86.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

#ifdef KVM_CAP_EXT_CPUID

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;

}

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;

    if (!kvm_check_extension(env->kvm_state, KVM_CAP_EXT_CPUID)) {

        return -1U;

    }

    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) {

            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);

    return ret;

}

#else

uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,

                                      uint32_t index, int reg)

{

    return -1U;

}

#endif

#ifdef CONFIG_KVM_PARA

struct kvm_para_features {

        int cap;

        int feature;

} para_features[] = {

#ifdef KVM_CAP_CLOCKSOURCE

        { KVM_CAP_CLOCKSOURCE, KVM_FEATURE_CLOCKSOURCE },

#endif

#ifdef KVM_CAP_NOP_IO_DELAY

        { KVM_CAP_NOP_IO_DELAY, KVM_FEATURE_NOP_IO_DELAY },

#endif

#ifdef KVM_CAP_PV_MMU

        { KVM_CAP_PV_MMU, KVM_FEATURE_MMU_OP },

#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

#ifdef KVM_CAP_MCE

static int kvm_get_mce_cap_supported(KVMState *s, uint64_t *mce_cap,

                                     int *max_banks)

{

    int r;

    r = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_MCE);

    if (r > 0) {

        *max_banks = r;

        return kvm_ioctl(s, KVM_X86_GET_MCE_CAP_SUPPORTED, mce_cap);

    }

    return -ENOSYS;

}

static int kvm_setup_mce(CPUState *env, uint64_t *mcg_cap)

{

    return kvm_vcpu_ioctl(env, KVM_X86_SETUP_MCE, mcg_cap);

}

static int kvm_set_mce(CPUState *env, struct kvm_x86_mce *m)

{

    return kvm_vcpu_ioctl(env, KVM_X86_SET_MCE, m);

}

struct kvm_x86_mce_data

{

    CPUState *env;

    struct kvm_x86_mce *mce;

};

static void kvm_do_inject_x86_mce(void *_data)

{

    struct kvm_x86_mce_data *data = _data;

    int r;

    r = kvm_set_mce(data->env, data->mce);

    if (r < 0)

        perror("kvm_set_mce FAILED");

}

#endif

void kvm_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,

                        uint64_t mcg_status, uint64_t addr, uint64_t misc)

{

#ifdef KVM_CAP_MCE

    struct kvm_x86_mce mce = {

        .bank = bank,

        .status = status,

        .mcg_status = mcg_status,

        .addr = addr,

        .misc = misc,

    };

    struct kvm_x86_mce_data data = {

            .env = cenv,

            .mce = &mce,

    };

    run_on_cpu(cenv, kvm_do_inject_x86_mce, &data);

#endif

}

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 KVM_CPUID_SIGNATURE

    uint32_t signature[3];

#endif

    env->mp_state = KVM_MP_STATE_RUNNABLE;

    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 & get_para_features(env);

#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;

        if (kvm_get_mce_cap_supported(env->kvm_state, &mcg_cap, &banks))

            perror("kvm_get_mce_cap_supported FAILED");

        else {

            if (banks > MCE_BANKS_DEF)

                banks = MCE_BANKS_DEF;

            mcg_cap &= MCE_CAP_DEF;

            mcg_cap |= banks;

            if (kvm_setup_mce(env, &mcg_cap))

                perror("kvm_setup_mce FAILED");

            else

                env->mcg_cap = mcg_cap;

        }

    }

#endif

    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->nmi_injected = 0;

    env->nmi_pending = 0;

    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_has_msr_star(CPUState *env)

{

    static int has_msr_star;

    int ret;

    /* first time */

    if (has_msr_star == 0) {        

        struct kvm_msr_list msr_list, *kvm_msr_list;

        has_msr_star = -1;

        /* Obtain MSR list from KVM.  These are the MSRs that we must

         * save/restore */

        msr_list.nmsrs = 0;

        ret = kvm_ioctl(env->kvm_state, KVM_GET_MSR_INDEX_LIST, &msr_list);

        if (ret < 0 && ret != -E2BIG) {

            return 0;

        }

        /* 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(env->kvm_state, 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 = 1;

                    break;

                }

            }

        }

        free(kvm_msr_list);

    }

    if (has_msr_star == 1)

        return 1;

    return 0;

}

static int kvm_init_identity_map_page(KVMState *s)

{

#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR

    int ret;

    uint64_t addr = 0xfffbc000;

    if (!kvm_check_extension(s, KVM_CAP_SET_IDENTITY_MAP_ADDR)) {

        return 0;

    }

    ret = kvm_vm_ioctl(s, KVM_SET_IDENTITY_MAP_ADDR, &addr);

    if (ret < 0) {

        fprintf(stderr, "kvm_set_identity_map_addr: %s\n", strerror(ret));

        return ret;

    }

#endif

    return 0;

}

int kvm_arch_init(KVMState *s, int smp_cpus)

{

    int ret;

    /* create vm86 tss.  KVM uses vm86 mode to emulate 16-bit code

     * directly.  In order to use vm86 mode, a TSS is needed.  Since this

     * must be part of guest physical memory, we need to allocate it.  Older

     * versions of KVM just assumed that it would be at the end of physical

     * memory but that doesn't work with more than 4GB of memory.  We simply

     * refuse to work with those older versions of KVM. */

    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_SET_TSS_ADDR);

    if (ret <= 0) {

        fprintf(stderr, "kvm does not support KVM_CAP_SET_TSS_ADDR\n");

        return ret;

    }

    /* this address is 3 pages before the bios, and the bios should present

     * as unavaible memory.  FIXME, need to ensure the e820 map deals with

     * this?

     */

    /*

     * Tell fw_cfg to notify the BIOS to reserve the range.

     */

    if (e820_add_entry(0xfffbc000, 0x4000, E820_RESERVED) < 0) {

        perror("e820_add_entry() table is full");

        exit(1);

    }

    ret = kvm_vm_ioctl(s, KVM_SET_TSS_ADDR, 0xfffbd000);

    if (ret < 0) {

        return ret;

    }

    return kvm_init_identity_map_page(s);

}

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 = rhs->selector & 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;

    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);

    return kvm_vcpu_ioctl(env, KVM_SET_XSAVE, xsave);

#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]);

            if (env->cr[0] & CR0_PE_MASK) {

                /* force ss cpl to cs cpl */

                sregs.ss.selector = (sregs.ss.selector & ~3) |

                        (sregs.cs.selector & 3);

                sregs.ss.dpl = sregs.ss.selector & 3;

            }

    }

    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);

    if (kvm_has_msr_star(env))

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

#ifdef TARGET_X86_64

    /* FIXME if lm capable */

    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_msr_entry_set(&msrs[n++], MSR_IA32_TSC, env->tsc);

        kvm_msr_entry_set(&msrs[n++], MSR_KVM_SYSTEM_TIME,

                          env->system_time_msr);

        kvm_msr_entry_set(&msrs[n++], MSR_KVM_WALL_CLOCK, env->wall_clock_msr);

    }

    msr_data.info.nmsrs = n;

    return kvm_vcpu_ioctl(env, KVM_SET_MSRS, &msr_data);

}

static int kvm_get_fpu(CPUState *env)

{

    struct kvm_fpu fpu;

    int i, ret;

    ret = kvm_vcpu_ioctl(env, KVM_GET_FPU, &fpu);

    if (ret < 0)

        return ret;

    env->fpstt = (fpu.fsw >> 11) & 7;

    env->fpus = fpu.fsw;

    env->fpuc = fpu.fcw;

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

        env->fptags[i] = !((fpu.ftwx >> i) & 1);

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

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

    env->mxcsr = fpu.mxcsr;

    return 0;

}

static int kvm_get_xsave(CPUState *env)

{

#ifdef KVM_CAP_XSAVE

    struct kvm_xsave* xsave;

    int ret, i;

    uint16_t cwd, swd, twd, fop;

    if (!kvm_has_xsave())

        return kvm_get_fpu(env);

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

    ret = kvm_vcpu_ioctl(env, KVM_GET_XSAVE, xsave);

    if (ret < 0)

        return ret;

    cwd = (uint16_t)xsave->region[0];

    swd = (uint16_t)(xsave->region[0] >> 16);

    twd = (uint16_t)xsave->region[1];

    fop = (uint16_t)(xsave->region[1] >> 16);

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

    env->fpus = swd;

    env->fpuc = cwd;

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

        env->fptags[i] = !((twd >> i) & 1);

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

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

            sizeof env->fpregs);

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

            sizeof env->xmm_regs);

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

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

            sizeof env->ymmh_regs);

    return 0;

#else

    return kvm_get_fpu(env);

#endif

}

static int kvm_get_xcrs(CPUState *env)

{

#ifdef KVM_CAP_XCRS

    int i, ret;

    struct kvm_xcrs xcrs;

    if (!kvm_has_xcrs())

        return 0;

    ret = kvm_vcpu_ioctl(env, KVM_GET_XCRS, &xcrs);

    if (ret < 0)

        return ret;

    for (i = 0; i < xcrs.nr_xcrs; i++)

        /* Only support xcr0 now */

        if (xcrs.xcrs[0].xcr == 0) {

            env->xcr0 = xcrs.xcrs[0].value;

            break;

        }

    return 0;

#else

    return 0;

#endif

}

static int kvm_get_sregs(CPUState *env)

{

    struct kvm_sregs sregs;

    uint32_t hflags;

    int bit, i, ret;

    ret = kvm_vcpu_ioctl(env, KVM_GET_SREGS, &sregs);

    if (ret < 0)

        return ret;

    /* There can only be one pending IRQ set in the bitmap at a time, so try

       to find it and save its number instead (-1 for none). */

    env->interrupt_injected = -1;

    for (i = 0; i < ARRAY_SIZE(sregs.interrupt_bitmap); i++) {

        if (sregs.interrupt_bitmap[i]) {

            bit = ctz64(sregs.interrupt_bitmap[i]);

            env->interrupt_injected = i * 64 + bit;

            break;

        }

    }

    get_seg(&env->segs[R_CS], &sregs.cs);

    get_seg(&env->segs[R_DS], &sregs.ds);

    get_seg(&env->segs[R_ES], &sregs.es);

    get_seg(&env->segs[R_FS], &sregs.fs);

    get_seg(&env->segs[R_GS], &sregs.gs);

    get_seg(&env->segs[R_SS], &sregs.ss);

    get_seg(&env->tr, &sregs.tr);

    get_seg(&env->ldt, &sregs.ldt);

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

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

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

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

    env->cr[0] = sregs.cr0;

    env->cr[2] = sregs.cr2;

    env->cr[3] = sregs.cr3;

    env->cr[4] = sregs.cr4;

    cpu_set_apic_base(env->apic_state, sregs.apic_base);

    env->efer = sregs.efer;

    //cpu_set_apic_tpr(env->apic_state, sregs.cr8);

#define HFLAG_COPY_MASK ~( \

                        HF_CPL_MASK | HF_PE_MASK | HF_MP_MASK | HF_EM_MASK | \

                        HF_TS_MASK | HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK | \

                        HF_OSFXSR_MASK | HF_LMA_MASK | HF_CS32_MASK | \

                        HF_SS32_MASK | HF_CS64_MASK | HF_ADDSEG_MASK)

    hflags = (env->segs[R_CS].flags >> DESC_DPL_SHIFT) & HF_CPL_MASK;

    hflags |= (env->cr[0] & CR0_PE_MASK) << (HF_PE_SHIFT - CR0_PE_SHIFT);

    hflags |= (env->cr[0] << (HF_MP_SHIFT - CR0_MP_SHIFT)) &

            (HF_MP_MASK | HF_EM_MASK | HF_TS_MASK);

    hflags |= (env->eflags & (HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK));

    hflags |= (env->cr[4] & CR4_OSFXSR_MASK) <<

            (HF_OSFXSR_SHIFT - CR4_OSFXSR_SHIFT);

    if (env->efer & MSR_EFER_LMA) {

        hflags |= HF_LMA_MASK;

    }

    if ((hflags & HF_LMA_MASK) && (env->segs[R_CS].flags & DESC_L_MASK)) {

        hflags |= HF_CS32_MASK | HF_SS32_MASK | HF_CS64_MASK;

    } else {

        hflags |= (env->segs[R_CS].flags & DESC_B_MASK) >>

                (DESC_B_SHIFT - HF_CS32_SHIFT);