migration: run setup callbacks out of big lock

[qemu.git] / savevm.c

/*
 * QEMU System Emulator
 *
 * Copyright (c) 2003-2008 Fabrice Bellard
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

#include "config-host.h"
#include "qemu-common.h"
#include "hw/hw.h"
#include "hw/qdev.h"
#include "net/net.h"
#include "monitor/monitor.h"
#include "sysemu/sysemu.h"
#include "qemu/timer.h"
#include "audio/audio.h"
#include "migration/migration.h"
#include "qemu/sockets.h"
#include "qemu/queue.h"
#include "sysemu/cpus.h"
#include "exec/memory.h"
#include "qmp-commands.h"
#include "trace.h"
#include "qemu/bitops.h"

#define SELF_ANNOUNCE_ROUNDS 5

#ifndef ETH_P_RARP
#define ETH_P_RARP 0x8035
#endif
#define ARP_HTYPE_ETH 0x0001
#define ARP_PTYPE_IP 0x0800
#define ARP_OP_REQUEST_REV 0x3

static int announce_self_create(uint8_t *buf,
				uint8_t *mac_addr)
{
    /* Ethernet header. */
    memset(buf, 0xff, 6);         /* destination MAC addr */
    memcpy(buf + 6, mac_addr, 6); /* source MAC addr */
    *(uint16_t *)(buf + 12) = htons(ETH_P_RARP); /* ethertype */

    /* RARP header. */
    *(uint16_t *)(buf + 14) = htons(ARP_HTYPE_ETH); /* hardware addr space */
    *(uint16_t *)(buf + 16) = htons(ARP_PTYPE_IP); /* protocol addr space */
    *(buf + 18) = 6; /* hardware addr length (ethernet) */
    *(buf + 19) = 4; /* protocol addr length (IPv4) */
    *(uint16_t *)(buf + 20) = htons(ARP_OP_REQUEST_REV); /* opcode */
    memcpy(buf + 22, mac_addr, 6); /* source hw addr */
    memset(buf + 28, 0x00, 4);     /* source protocol addr */
    memcpy(buf + 32, mac_addr, 6); /* target hw addr */
    memset(buf + 38, 0x00, 4);     /* target protocol addr */

    /* Padding to get up to 60 bytes (ethernet min packet size, minus FCS). */
    memset(buf + 42, 0x00, 18);

    return 60; /* len (FCS will be added by hardware) */
}

static void qemu_announce_self_iter(NICState *nic, void *opaque)
{
    uint8_t buf[60];
    int len;

    len = announce_self_create(buf, nic->conf->macaddr.a);

    qemu_send_packet_raw(qemu_get_queue(nic), buf, len);
}


static void qemu_announce_self_once(void *opaque)
{
    static int count = SELF_ANNOUNCE_ROUNDS;
    QEMUTimer *timer = *(QEMUTimer **)opaque;

    qemu_foreach_nic(qemu_announce_self_iter, NULL);

    if (--count) {
        /* delay 50ms, 150ms, 250ms, ... */
        qemu_mod_timer(timer, qemu_get_clock_ms(rt_clock) +
                       50 + (SELF_ANNOUNCE_ROUNDS - count - 1) * 100);
    } else {
	    qemu_del_timer(timer);
	    qemu_free_timer(timer);
    }
}

void qemu_announce_self(void)
{
	static QEMUTimer *timer;
	timer = qemu_new_timer_ms(rt_clock, qemu_announce_self_once, &timer);
	qemu_announce_self_once(&timer);
}

/***********************************************************/
/* savevm/loadvm support */

#define IO_BUF_SIZE 32768

struct QEMUFile {
    const QEMUFileOps *ops;
    void *opaque;
    int is_write;

    int64_t buf_offset; /* start of buffer when writing, end of buffer
                           when reading */
    int buf_index;
    int buf_size; /* 0 when writing */
    uint8_t buf[IO_BUF_SIZE];

    int last_error;
};

typedef struct QEMUFileStdio
{
    FILE *stdio_file;
    QEMUFile *file;
} QEMUFileStdio;

typedef struct QEMUFileSocket
{
    int fd;
    QEMUFile *file;
} QEMUFileSocket;

typedef struct {
    Coroutine *co;
    int fd;
} FDYieldUntilData;

static void fd_coroutine_enter(void *opaque)
{
    FDYieldUntilData *data = opaque;
    qemu_set_fd_handler(data->fd, NULL, NULL, NULL);
    qemu_coroutine_enter(data->co, NULL);
}

/**
 * Yield until a file descriptor becomes readable
 *
 * Note that this function clobbers the handlers for the file descriptor.
 */
static void coroutine_fn yield_until_fd_readable(int fd)
{
    FDYieldUntilData data;

    assert(qemu_in_coroutine());
    data.co = qemu_coroutine_self();
    data.fd = fd;
    qemu_set_fd_handler(fd, fd_coroutine_enter, NULL, &data);
    qemu_coroutine_yield();
}

static int socket_get_fd(void *opaque)
{
    QEMUFileSocket *s = opaque;

    return s->fd;
}

static int socket_get_buffer(void *opaque, uint8_t *buf, int64_t pos, int size)
{
    QEMUFileSocket *s = opaque;
    ssize_t len;

    for (;;) {
        len = qemu_recv(s->fd, buf, size, 0);
        if (len != -1) {
            break;
        }
        if (socket_error() == EAGAIN) {
            yield_until_fd_readable(s->fd);
        } else if (socket_error() != EINTR) {
            break;
        }
    }

    if (len == -1) {
        len = -socket_error();
    }
    return len;
}

static int socket_close(void *opaque)
{
    QEMUFileSocket *s = opaque;
    closesocket(s->fd);
    g_free(s);
    return 0;
}

static int stdio_get_fd(void *opaque)
{
    QEMUFileStdio *s = opaque;

    return fileno(s->stdio_file);
}

static int stdio_put_buffer(void *opaque, const uint8_t *buf, int64_t pos, int size)
{
    QEMUFileStdio *s = opaque;
    return fwrite(buf, 1, size, s->stdio_file);
}

static int stdio_get_buffer(void *opaque, uint8_t *buf, int64_t pos, int size)
{
    QEMUFileStdio *s = opaque;
    FILE *fp = s->stdio_file;
    int bytes;

    for (;;) {
        clearerr(fp);
        bytes = fread(buf, 1, size, fp);
        if (bytes != 0 || !ferror(fp)) {
            break;
        }
        if (errno == EAGAIN) {
            yield_until_fd_readable(fileno(fp));
        } else if (errno != EINTR) {
            break;
        }
    }
    return bytes;
}

static int stdio_pclose(void *opaque)
{
    QEMUFileStdio *s = opaque;
    int ret;
    ret = pclose(s->stdio_file);
    if (ret == -1) {
        ret = -errno;
    }
    g_free(s);
    return ret;
}

static int stdio_fclose(void *opaque)
{
    QEMUFileStdio *s = opaque;
    int ret = 0;
    if (fclose(s->stdio_file) == EOF) {
        ret = -errno;
    }
    g_free(s);
    return ret;
}

static const QEMUFileOps stdio_pipe_read_ops = {
    .get_fd =     stdio_get_fd,
    .get_buffer = stdio_get_buffer,
    .close =      stdio_pclose
};

static const QEMUFileOps stdio_pipe_write_ops = {
    .get_fd =     stdio_get_fd,
    .put_buffer = stdio_put_buffer,
    .close =      stdio_pclose
};

QEMUFile *qemu_popen(FILE *stdio_file, const char *mode)
{
    QEMUFileStdio *s;

    if (stdio_file == NULL || mode == NULL || (mode[0] != 'r' && mode[0] != 'w') || mode[1] != 0) {
        fprintf(stderr, "qemu_popen: Argument validity check failed\n");
        return NULL;
    }

    s = g_malloc0(sizeof(QEMUFileStdio));

    s->stdio_file = stdio_file;

    if(mode[0] == 'r') {
        s->file = qemu_fopen_ops(s, &stdio_pipe_read_ops);
    } else {
        s->file = qemu_fopen_ops(s, &stdio_pipe_write_ops);
    }
    return s->file;
}

QEMUFile *qemu_popen_cmd(const char *command, const char *mode)
{
    FILE *popen_file;

    popen_file = popen(command, mode);
    if(popen_file == NULL) {
        return NULL;
    }

    return qemu_popen(popen_file, mode);
}

static const QEMUFileOps stdio_file_read_ops = {
    .get_fd =     stdio_get_fd,
    .get_buffer = stdio_get_buffer,
    .close =      stdio_fclose
};

static const QEMUFileOps stdio_file_write_ops = {
    .get_fd =     stdio_get_fd,
    .put_buffer = stdio_put_buffer,
    .close =      stdio_fclose
};

QEMUFile *qemu_fdopen(int fd, const char *mode)
{
    QEMUFileStdio *s;

    if (mode == NULL ||
	(mode[0] != 'r' && mode[0] != 'w') ||
	mode[1] != 'b' || mode[2] != 0) {
        fprintf(stderr, "qemu_fdopen: Argument validity check failed\n");
        return NULL;
    }

    s = g_malloc0(sizeof(QEMUFileStdio));
    s->stdio_file = fdopen(fd, mode);
    if (!s->stdio_file)
        goto fail;

    if(mode[0] == 'r') {
        s->file = qemu_fopen_ops(s, &stdio_file_read_ops);
    } else {
        s->file = qemu_fopen_ops(s, &stdio_file_write_ops);
    }
    return s->file;

fail:
    g_free(s);
    return NULL;
}

static const QEMUFileOps socket_read_ops = {
    .get_fd =     socket_get_fd,
    .get_buffer = socket_get_buffer,
    .close =      socket_close
};

QEMUFile *qemu_fopen_socket(int fd)
{
    QEMUFileSocket *s = g_malloc0(sizeof(QEMUFileSocket));

    s->fd = fd;
    s->file = qemu_fopen_ops(s, &socket_read_ops);
    return s->file;
}

QEMUFile *qemu_fopen(const char *filename, const char *mode)
{
    QEMUFileStdio *s;

    if (mode == NULL ||
	(mode[0] != 'r' && mode[0] != 'w') ||
	mode[1] != 'b' || mode[2] != 0) {
        fprintf(stderr, "qemu_fopen: Argument validity check failed\n");
        return NULL;
    }

    s = g_malloc0(sizeof(QEMUFileStdio));

    s->stdio_file = fopen(filename, mode);
    if (!s->stdio_file)
        goto fail;
    
    if(mode[0] == 'w') {
        s->file = qemu_fopen_ops(s, &stdio_file_write_ops);
    } else {
        s->file = qemu_fopen_ops(s, &stdio_file_read_ops);
    }
    return s->file;
fail:
    g_free(s);
    return NULL;
}

static int block_put_buffer(void *opaque, const uint8_t *buf,
                           int64_t pos, int size)
{
    bdrv_save_vmstate(opaque, buf, pos, size);
    return size;
}

static int block_get_buffer(void *opaque, uint8_t *buf, int64_t pos, int size)
{
    return bdrv_load_vmstate(opaque, buf, pos, size);
}

static int bdrv_fclose(void *opaque)
{
    return bdrv_flush(opaque);
}

static const QEMUFileOps bdrv_read_ops = {
    .get_buffer = block_get_buffer,
    .close =      bdrv_fclose
};

static const QEMUFileOps bdrv_write_ops = {
    .put_buffer = block_put_buffer,
    .close =      bdrv_fclose
};

static QEMUFile *qemu_fopen_bdrv(BlockDriverState *bs, int is_writable)
{
    if (is_writable)
        return qemu_fopen_ops(bs, &bdrv_write_ops);
    return qemu_fopen_ops(bs, &bdrv_read_ops);
}

QEMUFile *qemu_fopen_ops(void *opaque, const QEMUFileOps *ops)
{
    QEMUFile *f;

    f = g_malloc0(sizeof(QEMUFile));

    f->opaque = opaque;
    f->ops = ops;
    f->is_write = 0;

    return f;
}

int qemu_file_get_error(QEMUFile *f)
{
    return f->last_error;
}

void qemu_file_set_error(QEMUFile *f, int ret)
{
    if (f->last_error == 0) {
        f->last_error = ret;
    }
}

/** Flushes QEMUFile buffer
 *
 */
void qemu_fflush(QEMUFile *f)
{
    int ret = 0;

    if (!f->ops->put_buffer) {
        return;
    }
    if (f->is_write && f->buf_index > 0) {
        ret = f->ops->put_buffer(f->opaque, f->buf, f->buf_offset, f->buf_index);
        if (ret >= 0) {
            f->buf_offset += f->buf_index;
        }
        f->buf_index = 0;
    }
    if (ret < 0) {
        qemu_file_set_error(f, ret);
    }
}

static void qemu_fill_buffer(QEMUFile *f)
{
    int len;
    int pending;

    if (!f->ops->get_buffer)
        return;

    if (f->is_write)
        abort();

    pending = f->buf_size - f->buf_index;
    if (pending > 0) {
        memmove(f->buf, f->buf + f->buf_index, pending);
    }
    f->buf_index = 0;
    f->buf_size = pending;

    len = f->ops->get_buffer(f->opaque, f->buf + pending, f->buf_offset,
                        IO_BUF_SIZE - pending);
    if (len > 0) {
        f->buf_size += len;
        f->buf_offset += len;
    } else if (len == 0) {
        qemu_file_set_error(f, -EIO);
    } else if (len != -EAGAIN)
        qemu_file_set_error(f, len);
}

int qemu_get_fd(QEMUFile *f)
{
    if (f->ops->get_fd) {
        return f->ops->get_fd(f->opaque);
    }
    return -1;
}

/** Closes the file
 *
 * Returns negative error value if any error happened on previous operations or
 * while closing the file. Returns 0 or positive number on success.
 *
 * The meaning of return value on success depends on the specific backend
 * being used.
 */
int qemu_fclose(QEMUFile *f)
{
    int ret;
    qemu_fflush(f);
    ret = qemu_file_get_error(f);

    if (f->ops->close) {
        int ret2 = f->ops->close(f->opaque);
        if (ret >= 0) {
            ret = ret2;
        }
    }
    /* If any error was spotted before closing, we should report it
     * instead of the close() return value.
     */
    if (f->last_error) {
        ret = f->last_error;
    }
    g_free(f);
    return ret;
}

void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, int size)
{
    int l;

    if (f->last_error) {
        return;
    }

    if (f->is_write == 0 && f->buf_index > 0) {
        fprintf(stderr,
                "Attempted to write to buffer while read buffer is not empty\n");
        abort();
    }

    while (size > 0) {
        l = IO_BUF_SIZE - f->buf_index;
        if (l > size)
            l = size;
        memcpy(f->buf + f->buf_index, buf, l);
        f->is_write = 1;
        f->buf_index += l;
        buf += l;
        size -= l;
        if (f->buf_index >= IO_BUF_SIZE) {
            qemu_fflush(f);
            if (qemu_file_get_error(f)) {
                break;
            }
        }
    }
}

void qemu_put_byte(QEMUFile *f, int v)
{
    if (f->last_error) {
        return;
    }

    if (f->is_write == 0 && f->buf_index > 0) {
        fprintf(stderr,
                "Attempted to write to buffer while read buffer is not empty\n");
        abort();
    }

    f->buf[f->buf_index++] = v;
    f->is_write = 1;
    if (f->buf_index >= IO_BUF_SIZE) {
        qemu_fflush(f);
    }
}

static void qemu_file_skip(QEMUFile *f, int size)
{
    if (f->buf_index + size <= f->buf_size) {
        f->buf_index += size;
    }
}

static int qemu_peek_buffer(QEMUFile *f, uint8_t *buf, int size, size_t offset)
{
    int pending;
    int index;

    if (f->is_write) {
        abort();
    }

    index = f->buf_index + offset;
    pending = f->buf_size - index;
    if (pending < size) {
        qemu_fill_buffer(f);
        index = f->buf_index + offset;
        pending = f->buf_size - index;
    }

    if (pending <= 0) {
        return 0;
    }
    if (size > pending) {
        size = pending;
    }

    memcpy(buf, f->buf + index, size);
    return size;
}

int qemu_get_buffer(QEMUFile *f, uint8_t *buf, int size)
{
    int pending = size;
    int done = 0;

    while (pending > 0) {
        int res;

        res = qemu_peek_buffer(f, buf, pending, 0);
        if (res == 0) {
            return done;
        }
        qemu_file_skip(f, res);
        buf += res;
        pending -= res;
        done += res;
    }
    return done;
}

static int qemu_peek_byte(QEMUFile *f, int offset)
{
    int index = f->buf_index + offset;

    if (f->is_write) {
        abort();
    }

    if (index >= f->buf_size) {
        qemu_fill_buffer(f);
        index = f->buf_index + offset;
        if (index >= f->buf_size) {
            return 0;
        }
    }
    return f->buf[index];
}

int qemu_get_byte(QEMUFile *f)
{
    int result;

    result = qemu_peek_byte(f, 0);
    qemu_file_skip(f, 1);
    return result;
}

int64_t qemu_ftell(QEMUFile *f)
{
    /* buf_offset excludes buffer for writing but includes it for reading */
    if (f->is_write) {
        return f->buf_offset + f->buf_index;
    } else {
        return f->buf_offset - f->buf_size + f->buf_index;
    }
}

int qemu_file_rate_limit(QEMUFile *f)
{
    if (f->ops->rate_limit)
        return f->ops->rate_limit(f->opaque);

    return 0;
}

int64_t qemu_file_get_rate_limit(QEMUFile *f)
{
    if (f->ops->get_rate_limit)
        return f->ops->get_rate_limit(f->opaque);

    return 0;
}

int64_t qemu_file_set_rate_limit(QEMUFile *f, int64_t new_rate)
{
    /* any failed or completed migration keeps its state to allow probing of
     * migration data, but has no associated file anymore */
    if (f && f->ops->set_rate_limit)
        return f->ops->set_rate_limit(f->opaque, new_rate);

    return 0;
}

void qemu_put_be16(QEMUFile *f, unsigned int v)
{
    qemu_put_byte(f, v >> 8);
    qemu_put_byte(f, v);
}

void qemu_put_be32(QEMUFile *f, unsigned int v)
{
    qemu_put_byte(f, v >> 24);
    qemu_put_byte(f, v >> 16);
    qemu_put_byte(f, v >> 8);
    qemu_put_byte(f, v);
}

void qemu_put_be64(QEMUFile *f, uint64_t v)
{
    qemu_put_be32(f, v >> 32);
    qemu_put_be32(f, v);
}

unsigned int qemu_get_be16(QEMUFile *f)
{
    unsigned int v;
    v = qemu_get_byte(f) << 8;
    v |= qemu_get_byte(f);
    return v;
}

unsigned int qemu_get_be32(QEMUFile *f)
{
    unsigned int v;
    v = qemu_get_byte(f) << 24;
    v |= qemu_get_byte(f) << 16;
    v |= qemu_get_byte(f) << 8;
    v |= qemu_get_byte(f);
    return v;
}

uint64_t qemu_get_be64(QEMUFile *f)
{
    uint64_t v;
    v = (uint64_t)qemu_get_be32(f) << 32;
    v |= qemu_get_be32(f);
    return v;
}


/* timer */

void qemu_put_timer(QEMUFile *f, QEMUTimer *ts)
{
    uint64_t expire_time;

    expire_time = qemu_timer_expire_time_ns(ts);
    qemu_put_be64(f, expire_time);
}

void qemu_get_timer(QEMUFile *f, QEMUTimer *ts)
{
    uint64_t expire_time;

    expire_time = qemu_get_be64(f);
    if (expire_time != -1) {
        qemu_mod_timer_ns(ts, expire_time);
    } else {
        qemu_del_timer(ts);
    }
}


/* bool */

static int get_bool(QEMUFile *f, void *pv, size_t size)
{
    bool *v = pv;
    *v = qemu_get_byte(f);
    return 0;
}

static void put_bool(QEMUFile *f, void *pv, size_t size)
{
    bool *v = pv;
    qemu_put_byte(f, *v);
}

const VMStateInfo vmstate_info_bool = {
    .name = "bool",
    .get  = get_bool,
    .put  = put_bool,
};

/* 8 bit int */

static int get_int8(QEMUFile *f, void *pv, size_t size)
{
    int8_t *v = pv;
    qemu_get_s8s(f, v);
    return 0;
}

static void put_int8(QEMUFile *f, void *pv, size_t size)
{
    int8_t *v = pv;
    qemu_put_s8s(f, v);
}

const VMStateInfo vmstate_info_int8 = {
    .name = "int8",
    .get  = get_int8,
    .put  = put_int8,
};

/* 16 bit int */

static int get_int16(QEMUFile *f, void *pv, size_t size)
{
    int16_t *v = pv;
    qemu_get_sbe16s(f, v);
    return 0;
}

static void put_int16(QEMUFile *f, void *pv, size_t size)
{
    int16_t *v = pv;
    qemu_put_sbe16s(f, v);
}

const VMStateInfo vmstate_info_int16 = {
    .name = "int16",
    .get  = get_int16,
    .put  = put_int16,
};

/* 32 bit int */

static int get_int32(QEMUFile *f, void *pv, size_t size)
{
    int32_t *v = pv;
    qemu_get_sbe32s(f, v);
    return 0;
}

static void put_int32(QEMUFile *f, void *pv, size_t size)
{
    int32_t *v = pv;
    qemu_put_sbe32s(f, v);
}

const VMStateInfo vmstate_info_int32 = {
    .name = "int32",
    .get  = get_int32,
    .put  = put_int32,
};

/* 32 bit int. See that the received value is the same than the one
   in the field */

static int get_int32_equal(QEMUFile *f, void *pv, size_t size)
{
    int32_t *v = pv;
    int32_t v2;
    qemu_get_sbe32s(f, &v2);

    if (*v == v2)
        return 0;
    return -EINVAL;
}

const VMStateInfo vmstate_info_int32_equal = {
    .name = "int32 equal",
    .get  = get_int32_equal,
    .put  = put_int32,
};

/* 32 bit int. See that the received value is the less or the same
   than the one in the field */

static int get_int32_le(QEMUFile *f, void *pv, size_t size)
{
    int32_t *old = pv;
    int32_t new;
    qemu_get_sbe32s(f, &new);

    if (*old <= new)
        return 0;
    return -EINVAL;
}

const VMStateInfo vmstate_info_int32_le = {
    .name = "int32 equal",
    .get  = get_int32_le,
    .put  = put_int32,
};

/* 64 bit int */

static int get_int64(QEMUFile *f, void *pv, size_t size)
{
    int64_t *v = pv;
    qemu_get_sbe64s(f, v);
    return 0;
}

static void put_int64(QEMUFile *f, void *pv, size_t size)
{
    int64_t *v = pv;
    qemu_put_sbe64s(f, v);
}

const VMStateInfo vmstate_info_int64 = {
    .name = "int64",
    .get  = get_int64,
    .put  = put_int64,
};

/* 8 bit unsigned int */

static int get_uint8(QEMUFile *f, void *pv, size_t size)
{
    uint8_t *v = pv;
    qemu_get_8s(f, v);
    return 0;
}

static void put_uint8(QEMUFile *f, void *pv, size_t size)
{
    uint8_t *v = pv;
    qemu_put_8s(f, v);
}

const VMStateInfo vmstate_info_uint8 = {
    .name = "uint8",
    .get  = get_uint8,
    .put  = put_uint8,
};

/* 16 bit unsigned int */

static int get_uint16(QEMUFile *f, void *pv, size_t size)
{
    uint16_t *v = pv;
    qemu_get_be16s(f, v);
    return 0;
}

static void put_uint16(QEMUFile *f, void *pv, size_t size)
{
    uint16_t *v = pv;
    qemu_put_be16s(f, v);
}

const VMStateInfo vmstate_info_uint16 = {
    .name = "uint16",
    .get  = get_uint16,
    .put  = put_uint16,
};

/* 32 bit unsigned int */

static int get_uint32(QEMUFile *f, void *pv, size_t size)
{
    uint32_t *v = pv;
    qemu_get_be32s(f, v);
    return 0;
}

static void put_uint32(QEMUFile *f, void *pv, size_t size)
{
    uint32_t *v = pv;
    qemu_put_be32s(f, v);
}

const VMStateInfo vmstate_info_uint32 = {
    .name = "uint32",
    .get  = get_uint32,
    .put  = put_uint32,
};

/* 32 bit uint. See that the received value is the same than the one
   in the field */

static int get_uint32_equal(QEMUFile *f, void *pv, size_t size)
{
    uint32_t *v = pv;
    uint32_t v2;
    qemu_get_be32s(f, &v2);

    if (*v == v2) {
        return 0;
    }
    return -EINVAL;
}

const VMStateInfo vmstate_info_uint32_equal = {
    .name = "uint32 equal",
    .get  = get_uint32_equal,
    .put  = put_uint32,
};

/* 64 bit unsigned int */

static int get_uint64(QEMUFile *f, void *pv, size_t size)
{
    uint64_t *v = pv;
    qemu_get_be64s(f, v);
    return 0;
}

static void put_uint64(QEMUFile *f, void *pv, size_t size)
{
    uint64_t *v = pv;
    qemu_put_be64s(f, v);
}

const VMStateInfo vmstate_info_uint64 = {
    .name = "uint64",
    .get  = get_uint64,
    .put  = put_uint64,
};

/* 8 bit int. See that the received value is the same than the one
   in the field */

static int get_uint8_equal(QEMUFile *f, void *pv, size_t size)
{
    uint8_t *v = pv;
    uint8_t v2;
    qemu_get_8s(f, &v2);

    if (*v == v2)
        return 0;
    return -EINVAL;
}

const VMStateInfo vmstate_info_uint8_equal = {
    .name = "uint8 equal",
    .get  = get_uint8_equal,
    .put  = put_uint8,
};

/* 16 bit unsigned int int. See that the received value is the same than the one
   in the field */

static int get_uint16_equal(QEMUFile *f, void *pv, size_t size)
{
    uint16_t *v = pv;
    uint16_t v2;
    qemu_get_be16s(f, &v2);

    if (*v == v2)
        return 0;
    return -EINVAL;
}

const VMStateInfo vmstate_info_uint16_equal = {
    .name = "uint16 equal",
    .get  = get_uint16_equal,
    .put  = put_uint16,
};

/* timers  */

static int get_timer(QEMUFile *f, void *pv, size_t size)
{
    QEMUTimer *v = pv;
    qemu_get_timer(f, v);
    return 0;
}

static void put_timer(QEMUFile *f, void *pv, size_t size)
{
    QEMUTimer *v = pv;
    qemu_put_timer(f, v);
}

const VMStateInfo vmstate_info_timer = {
    .name = "timer",
    .get  = get_timer,
    .put  = put_timer,
};

/* uint8_t buffers */

static int get_buffer(QEMUFile *f, void *pv, size_t size)
{
    uint8_t *v = pv;
    qemu_get_buffer(f, v, size);
    return 0;
}

static void put_buffer(QEMUFile *f, void *pv, size_t size)
{
    uint8_t *v = pv;
    qemu_put_buffer(f, v, size);
}

const VMStateInfo vmstate_info_buffer = {
    .name = "buffer",
    .get  = get_buffer,
    .put  = put_buffer,
};

/* unused buffers: space that was used for some fields that are
   not useful anymore */

static int get_unused_buffer(QEMUFile *f, void *pv, size_t size)
{
    uint8_t buf[1024];
    int block_len;

    while (size > 0) {
        block_len = MIN(sizeof(buf), size);
        size -= block_len;
        qemu_get_buffer(f, buf, block_len);
    }
   return 0;
}

static void put_unused_buffer(QEMUFile *f, void *pv, size_t size)
{
    static const uint8_t buf[1024];
    int block_len;

    while (size > 0) {
        block_len = MIN(sizeof(buf), size);
        size -= block_len;
        qemu_put_buffer(f, buf, block_len);
    }
}

const VMStateInfo vmstate_info_unused_buffer = {
    .name = "unused_buffer",
    .get  = get_unused_buffer,
    .put  = put_unused_buffer,
};

/* bitmaps (as defined by bitmap.h). Note that size here is the size
 * of the bitmap in bits. The on-the-wire format of a bitmap is 64
 * bit words with the bits in big endian order. The in-memory format
 * is an array of 'unsigned long', which may be either 32 or 64 bits.
 */
/* This is the number of 64 bit words sent over the wire */
#define BITS_TO_U64S(nr) DIV_ROUND_UP(nr, 64)
static int get_bitmap(QEMUFile *f, void *pv, size_t size)
{
    unsigned long *bmp = pv;
    int i, idx = 0;
    for (i = 0; i < BITS_TO_U64S(size); i++) {
        uint64_t w = qemu_get_be64(f);
        bmp[idx++] = w;
        if (sizeof(unsigned long) == 4 && idx < BITS_TO_LONGS(size)) {
            bmp[idx++] = w >> 32;
        }
    }
    return 0;
}

static void put_bitmap(QEMUFile *f, void *pv, size_t size)
{
    unsigned long *bmp = pv;
    int i, idx = 0;
    for (i = 0; i < BITS_TO_U64S(size); i++) {
        uint64_t w = bmp[idx++];
        if (sizeof(unsigned long) == 4 && idx < BITS_TO_LONGS(size)) {
            w |= ((uint64_t)bmp[idx++]) << 32;
        }
        qemu_put_be64(f, w);
    }
}

const VMStateInfo vmstate_info_bitmap = {
    .name = "bitmap",
    .get = get_bitmap,
    .put = put_bitmap,
};

typedef struct CompatEntry {
    char idstr[256];
    int instance_id;
} CompatEntry;

typedef struct SaveStateEntry {
    QTAILQ_ENTRY(SaveStateEntry) entry;
    char idstr[256];
    int instance_id;
    int alias_id;
    int version_id;
    int section_id;
    SaveVMHandlers *ops;
    const VMStateDescription *vmsd;
    void *opaque;
    CompatEntry *compat;
    int no_migrate;
    int is_ram;
} SaveStateEntry;


static QTAILQ_HEAD(savevm_handlers, SaveStateEntry) savevm_handlers =
    QTAILQ_HEAD_INITIALIZER(savevm_handlers);
static int global_section_id;

static int calculate_new_instance_id(const char *idstr)
{
    SaveStateEntry *se;
    int instance_id = 0;

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        if (strcmp(idstr, se->idstr) == 0
            && instance_id <= se->instance_id) {
            instance_id = se->instance_id + 1;
        }
    }
    return instance_id;
}

static int calculate_compat_instance_id(const char *idstr)
{
    SaveStateEntry *se;
    int instance_id = 0;

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        if (!se->compat)
            continue;

        if (strcmp(idstr, se->compat->idstr) == 0
            && instance_id <= se->compat->instance_id) {
            instance_id = se->compat->instance_id + 1;
        }
    }
    return instance_id;
}

/* TODO: Individual devices generally have very little idea about the rest
   of the system, so instance_id should be removed/replaced.
   Meanwhile pass -1 as instance_id if you do not already have a clearly
   distinguishing id for all instances of your device class. */
int register_savevm_live(DeviceState *dev,
                         const char *idstr,
                         int instance_id,
                         int version_id,
                         SaveVMHandlers *ops,
                         void *opaque)
{
    SaveStateEntry *se;

    se = g_malloc0(sizeof(SaveStateEntry));
    se->version_id = version_id;
    se->section_id = global_section_id++;
    se->ops = ops;
    se->opaque = opaque;
    se->vmsd = NULL;
    se->no_migrate = 0;
    /* if this is a live_savem then set is_ram */
    if (ops->save_live_setup != NULL) {
        se->is_ram = 1;
    }

    if (dev) {
        char *id = qdev_get_dev_path(dev);
        if (id) {
            pstrcpy(se->idstr, sizeof(se->idstr), id);
            pstrcat(se->idstr, sizeof(se->idstr), "/");
            g_free(id);

            se->compat = g_malloc0(sizeof(CompatEntry));
            pstrcpy(se->compat->idstr, sizeof(se->compat->idstr), idstr);
            se->compat->instance_id = instance_id == -1 ?
                         calculate_compat_instance_id(idstr) : instance_id;
            instance_id = -1;
        }
    }
    pstrcat(se->idstr, sizeof(se->idstr), idstr);

    if (instance_id == -1) {
        se->instance_id = calculate_new_instance_id(se->idstr);
    } else {
        se->instance_id = instance_id;
    }
    assert(!se->compat || se->instance_id == 0);
    /* add at the end of list */
    QTAILQ_INSERT_TAIL(&savevm_handlers, se, entry);
    return 0;
}

int register_savevm(DeviceState *dev,
                    const char *idstr,
                    int instance_id,
                    int version_id,
                    SaveStateHandler *save_state,
                    LoadStateHandler *load_state,
                    void *opaque)
{
    SaveVMHandlers *ops = g_malloc0(sizeof(SaveVMHandlers));
    ops->save_state = save_state;
    ops->load_state = load_state;
    return register_savevm_live(dev, idstr, instance_id, version_id,
                                ops, opaque);
}

void unregister_savevm(DeviceState *dev, const char *idstr, void *opaque)
{
    SaveStateEntry *se, *new_se;
    char id[256] = "";

    if (dev) {
        char *path = qdev_get_dev_path(dev);
        if (path) {
            pstrcpy(id, sizeof(id), path);
            pstrcat(id, sizeof(id), "/");
            g_free(path);
        }
    }
    pstrcat(id, sizeof(id), idstr);

    QTAILQ_FOREACH_SAFE(se, &savevm_handlers, entry, new_se) {
        if (strcmp(se->idstr, id) == 0 && se->opaque == opaque) {
            QTAILQ_REMOVE(&savevm_handlers, se, entry);
            if (se->compat) {
                g_free(se->compat);
            }
            g_free(se->ops);
            g_free(se);
        }
    }
}

int vmstate_register_with_alias_id(DeviceState *dev, int instance_id,
                                   const VMStateDescription *vmsd,
                                   void *opaque, int alias_id,
                                   int required_for_version)
{
    SaveStateEntry *se;

    /* If this triggers, alias support can be dropped for the vmsd. */
    assert(alias_id == -1 || required_for_version >= vmsd->minimum_version_id);

    se = g_malloc0(sizeof(SaveStateEntry));
    se->version_id = vmsd->version_id;
    se->section_id = global_section_id++;
    se->opaque = opaque;
    se->vmsd = vmsd;
    se->alias_id = alias_id;
    se->no_migrate = vmsd->unmigratable;

    if (dev) {
        char *id = qdev_get_dev_path(dev);
        if (id) {
            pstrcpy(se->idstr, sizeof(se->idstr), id);
            pstrcat(se->idstr, sizeof(se->idstr), "/");
            g_free(id);

            se->compat = g_malloc0(sizeof(CompatEntry));
            pstrcpy(se->compat->idstr, sizeof(se->compat->idstr), vmsd->name);
            se->compat->instance_id = instance_id == -1 ?
                         calculate_compat_instance_id(vmsd->name) : instance_id;
            instance_id = -1;
        }
    }
    pstrcat(se->idstr, sizeof(se->idstr), vmsd->name);

    if (instance_id == -1) {
        se->instance_id = calculate_new_instance_id(se->idstr);
    } else {
        se->instance_id = instance_id;
    }
    assert(!se->compat || se->instance_id == 0);
    /* add at the end of list */
    QTAILQ_INSERT_TAIL(&savevm_handlers, se, entry);
    return 0;
}

int vmstate_register(DeviceState *dev, int instance_id,
                     const VMStateDescription *vmsd, void *opaque)
{
    return vmstate_register_with_alias_id(dev, instance_id, vmsd,
                                          opaque, -1, 0);
}

void vmstate_unregister(DeviceState *dev, const VMStateDescription *vmsd,
                        void *opaque)
{
    SaveStateEntry *se, *new_se;

    QTAILQ_FOREACH_SAFE(se, &savevm_handlers, entry, new_se) {
        if (se->vmsd == vmsd && se->opaque == opaque) {
            QTAILQ_REMOVE(&savevm_handlers, se, entry);
            if (se->compat) {
                g_free(se->compat);
            }
            g_free(se);
        }
    }
}

static void vmstate_subsection_save(QEMUFile *f, const VMStateDescription *vmsd,
                                    void *opaque);
static int vmstate_subsection_load(QEMUFile *f, const VMStateDescription *vmsd,
                                   void *opaque);

int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd,
                       void *opaque, int version_id)
{
    VMStateField *field = vmsd->fields;
    int ret;

    if (version_id > vmsd->version_id) {
        return -EINVAL;
    }
    if (version_id < vmsd->minimum_version_id_old) {
        return -EINVAL;
    }
    if  (version_id < vmsd->minimum_version_id) {
        return vmsd->load_state_old(f, opaque, version_id);
    }
    if (vmsd->pre_load) {
        int ret = vmsd->pre_load(opaque);
        if (ret)
            return ret;
    }
    while(field->name) {
        if ((field->field_exists &&
             field->field_exists(opaque, version_id)) ||
            (!field->field_exists &&
             field->version_id <= version_id)) {
            void *base_addr = opaque + field->offset;
            int i, n_elems = 1;
            int size = field->size;

            if (field->flags & VMS_VBUFFER) {
                size = *(int32_t *)(opaque+field->size_offset);
                if (field->flags & VMS_MULTIPLY) {
                    size *= field->size;
                }
            }
            if (field->flags & VMS_ARRAY) {
                n_elems = field->num;
            } else if (field->flags & VMS_VARRAY_INT32) {
                n_elems = *(int32_t *)(opaque+field->num_offset);
            } else if (field->flags & VMS_VARRAY_UINT32) {
                n_elems = *(uint32_t *)(opaque+field->num_offset);
            } else if (field->flags & VMS_VARRAY_UINT16) {
                n_elems = *(uint16_t *)(opaque+field->num_offset);
            } else if (field->flags & VMS_VARRAY_UINT8) {
                n_elems = *(uint8_t *)(opaque+field->num_offset);
            }
            if (field->flags & VMS_POINTER) {
                base_addr = *(void **)base_addr + field->start;
            }
            for (i = 0; i < n_elems; i++) {
                void *addr = base_addr + size * i;

                if (field->flags & VMS_ARRAY_OF_POINTER) {
                    addr = *(void **)addr;
                }
                if (field->flags & VMS_STRUCT) {
                    ret = vmstate_load_state(f, field->vmsd, addr, field->vmsd->version_id);
                } else {
                    ret = field->info->get(f, addr, size);

                }
                if (ret < 0) {
                    return ret;
                }
            }
        }
        field++;
    }
    ret = vmstate_subsection_load(f, vmsd, opaque);
    if (ret != 0) {
        return ret;
    }
    if (vmsd->post_load) {
        return vmsd->post_load(opaque, version_id);
    }
    return 0;
}

void vmstate_save_state(QEMUFile *f, const VMStateDescription *vmsd,
                        void *opaque)
{
    VMStateField *field = vmsd->fields;

    if (vmsd->pre_save) {
        vmsd->pre_save(opaque);
    }
    while(field->name) {
        if (!field->field_exists ||
            field->field_exists(opaque, vmsd->version_id)) {
            void *base_addr = opaque + field->offset;
            int i, n_elems = 1;
            int size = field->size;

            if (field->flags & VMS_VBUFFER) {
                size = *(int32_t *)(opaque+field->size_offset);
                if (field->flags & VMS_MULTIPLY) {
                    size *= field->size;
                }
            }
            if (field->flags & VMS_ARRAY) {
                n_elems = field->num;
            } else if (field->flags & VMS_VARRAY_INT32) {
                n_elems = *(int32_t *)(opaque+field->num_offset);
            } else if (field->flags & VMS_VARRAY_UINT32) {
                n_elems = *(uint32_t *)(opaque+field->num_offset);
            } else if (field->flags & VMS_VARRAY_UINT16) {
                n_elems = *(uint16_t *)(opaque+field->num_offset);
            } else if (field->flags & VMS_VARRAY_UINT8) {
                n_elems = *(uint8_t *)(opaque+field->num_offset);
            }
            if (field->flags & VMS_POINTER) {
                base_addr = *(void **)base_addr + field->start;
            }
            for (i = 0; i < n_elems; i++) {
                void *addr = base_addr + size * i;

                if (field->flags & VMS_ARRAY_OF_POINTER) {
                    addr = *(void **)addr;
                }
                if (field->flags & VMS_STRUCT) {
                    vmstate_save_state(f, field->vmsd, addr);
                } else {
                    field->info->put(f, addr, size);
                }
            }
        }
        field++;
    }
    vmstate_subsection_save(f, vmsd, opaque);
}

static int vmstate_load(QEMUFile *f, SaveStateEntry *se, int version_id)
{
    if (!se->vmsd) {         /* Old style */
        return se->ops->load_state(f, se->opaque, version_id);
    }
    return vmstate_load_state(f, se->vmsd, se->opaque, version_id);
}

static void vmstate_save(QEMUFile *f, SaveStateEntry *se)
{
    if (!se->vmsd) {         /* Old style */
        se->ops->save_state(f, se->opaque);
        return;
    }
    vmstate_save_state(f,se->vmsd, se->opaque);
}

#define QEMU_VM_FILE_MAGIC           0x5145564d
#define QEMU_VM_FILE_VERSION_COMPAT  0x00000002
#define QEMU_VM_FILE_VERSION         0x00000003

#define QEMU_VM_EOF                  0x00
#define QEMU_VM_SECTION_START        0x01
#define QEMU_VM_SECTION_PART         0x02
#define QEMU_VM_SECTION_END          0x03
#define QEMU_VM_SECTION_FULL         0x04
#define QEMU_VM_SUBSECTION           0x05

bool qemu_savevm_state_blocked(Error **errp)
{
    SaveStateEntry *se;

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        if (se->no_migrate) {
            error_set(errp, QERR_MIGRATION_NOT_SUPPORTED, se->idstr);
            return true;
        }
    }
    return false;
}

void qemu_savevm_state_begin(QEMUFile *f,
                             const MigrationParams *params)
{
    SaveStateEntry *se;
    int ret;

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        if (!se->ops || !se->ops->set_params) {
            continue;
        }
        se->ops->set_params(params, se->opaque);
    }
    
    qemu_put_be32(f, QEMU_VM_FILE_MAGIC);
    qemu_put_be32(f, QEMU_VM_FILE_VERSION);

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        int len;

        if (!se->ops || !se->ops->save_live_setup) {
            continue;
        }
        if (se->ops && se->ops->is_active) {
            if (!se->ops->is_active(se->opaque)) {
                continue;
            }
        }
        /* Section type */
        qemu_put_byte(f, QEMU_VM_SECTION_START);
        qemu_put_be32(f, se->section_id);

        /* ID string */
        len = strlen(se->idstr);
        qemu_put_byte(f, len);
        qemu_put_buffer(f, (uint8_t *)se->idstr, len);

        qemu_put_be32(f, se->instance_id);
        qemu_put_be32(f, se->version_id);

        ret = se->ops->save_live_setup(f, se->opaque);
        if (ret < 0) {
            qemu_file_set_error(f, ret);
            break;
        }
    }
}

/*
 * this function has three return values:
 *   negative: there was one error, and we have -errno.
 *   0 : We haven't finished, caller have to go again
 *   1 : We have finished, we can go to complete phase
 */
int qemu_savevm_state_iterate(QEMUFile *f)
{
    SaveStateEntry *se;
    int ret = 1;

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        if (!se->ops || !se->ops->save_live_iterate) {
            continue;
        }
        if (se->ops && se->ops->is_active) {
            if (!se->ops->is_active(se->opaque)) {
                continue;
            }
        }
        if (qemu_file_rate_limit(f)) {
            return 0;
        }
        trace_savevm_section_start();
        /* Section type */
        qemu_put_byte(f, QEMU_VM_SECTION_PART);
        qemu_put_be32(f, se->section_id);

        ret = se->ops->save_live_iterate(f, se->opaque);
        trace_savevm_section_end(se->section_id);

        if (ret < 0) {
            qemu_file_set_error(f, ret);
        }
        if (ret <= 0) {
            /* Do not proceed to the next vmstate before this one reported
               completion of the current stage. This serializes the migration
               and reduces the probability that a faster changing state is
               synchronized over and over again. */
            break;
        }
    }
    return ret;
}

void qemu_savevm_state_complete(QEMUFile *f)
{
    SaveStateEntry *se;
    int ret;

    cpu_synchronize_all_states();

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        if (!se->ops || !se->ops->save_live_complete) {
            continue;
        }
        if (se->ops && se->ops->is_active) {
            if (!se->ops->is_active(se->opaque)) {
                continue;
            }
        }
        trace_savevm_section_start();
        /* Section type */
        qemu_put_byte(f, QEMU_VM_SECTION_END);
        qemu_put_be32(f, se->section_id);

        ret = se->ops->save_live_complete(f, se->opaque);
        trace_savevm_section_end(se->section_id);
        if (ret < 0) {
            qemu_file_set_error(f, ret);
            return;
        }
    }

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        int len;

        if ((!se->ops || !se->ops->save_state) && !se->vmsd) {
	    continue;
        }
        trace_savevm_section_start();
        /* Section type */
        qemu_put_byte(f, QEMU_VM_SECTION_FULL);
        qemu_put_be32(f, se->section_id);

        /* ID string */
        len = strlen(se->idstr);
        qemu_put_byte(f, len);
        qemu_put_buffer(f, (uint8_t *)se->idstr, len);

        qemu_put_be32(f, se->instance_id);
        qemu_put_be32(f, se->version_id);

        vmstate_save(f, se);
        trace_savevm_section_end(se->section_id);
    }

    qemu_put_byte(f, QEMU_VM_EOF);
}

uint64_t qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size)
{
    SaveStateEntry *se;
    uint64_t ret = 0;

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        if (!se->ops || !se->ops->save_live_pending) {
            continue;
        }
        if (se->ops && se->ops->is_active) {
            if (!se->ops->is_active(se->opaque)) {
                continue;
            }
        }
        ret += se->ops->save_live_pending(f, se->opaque, max_size);
    }
    return ret;
}

void qemu_savevm_state_cancel(void)
{
    SaveStateEntry *se;

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        if (se->ops && se->ops->cancel) {
            se->ops->cancel(se->opaque);
        }
    }
}

static int qemu_savevm_state(QEMUFile *f)
{
    int ret;
    MigrationParams params = {
        .blk = 0,
        .shared = 0
    };

    if (qemu_savevm_state_blocked(NULL)) {
        return -EINVAL;
    }

    qemu_mutex_unlock_iothread();
    qemu_savevm_state_begin(f, &params);
    qemu_mutex_lock_iothread();

    while (qemu_file_get_error(f) == 0) {
        if (qemu_savevm_state_iterate(f) > 0) {
            break;
        }
    }

    ret = qemu_file_get_error(f);
    if (ret == 0) {
        qemu_savevm_state_complete(f);
        ret = qemu_file_get_error(f);
    }
    if (ret != 0) {
        qemu_savevm_state_cancel();
    }
    return ret;
}

static int qemu_save_device_state(QEMUFile *f)
{
    SaveStateEntry *se;

    qemu_put_be32(f, QEMU_VM_FILE_MAGIC);
    qemu_put_be32(f, QEMU_VM_FILE_VERSION);

    cpu_synchronize_all_states();

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        int len;

        if (se->is_ram) {
            continue;
        }
        if ((!se->ops || !se->ops->save_state) && !se->vmsd) {
            continue;
        }

        /* Section type */
        qemu_put_byte(f, QEMU_VM_SECTION_FULL);
        qemu_put_be32(f, se->section_id);

        /* ID string */
        len = strlen(se->idstr);
        qemu_put_byte(f, len);
        qemu_put_buffer(f, (uint8_t *)se->idstr, len);

        qemu_put_be32(f, se->instance_id);
        qemu_put_be32(f, se->version_id);

        vmstate_save(f, se);
    }

    qemu_put_byte(f, QEMU_VM_EOF);

    return qemu_file_get_error(f);
}

static SaveStateEntry *find_se(const char *idstr, int instance_id)
{
    SaveStateEntry *se;

    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
        if (!strcmp(se->idstr, idstr) &&
            (instance_id == se->instance_id ||
             instance_id == se->alias_id))
            return se;
        /* Migrating from an older version? */
        if (strstr(se->idstr, idstr) && se->compat) {
            if (!strcmp(se->compat->idstr, idstr) &&
                (instance_id == se->compat->instance_id ||
                 instance_id == se->alias_id))
                return se;
        }
    }
    return NULL;
}

static const VMStateDescription *vmstate_get_subsection(const VMStateSubsection *sub, char *idstr)
{
    while(sub && sub->needed) {
        if (strcmp(idstr, sub->vmsd->name) == 0) {
            return sub->vmsd;
        }
        sub++;
    }
    return NULL;
}

static int vmstate_subsection_load(QEMUFile *f, const VMStateDescription *vmsd,
                                   void *opaque)
{
    while (qemu_peek_byte(f, 0) == QEMU_VM_SUBSECTION) {
        char idstr[256];
        int ret;
        uint8_t version_id, len, size;
        const VMStateDescription *sub_vmsd;

        len = qemu_peek_byte(f, 1);
        if (len < strlen(vmsd->name) + 1) {
            /* subsection name has be be "section_name/a" */
            return 0;
        }
        size = qemu_peek_buffer(f, (uint8_t *)idstr, len, 2);
        if (size != len) {
            return 0;
        }
        idstr[size] = 0;

        if (strncmp(vmsd->name, idstr, strlen(vmsd->name)) != 0) {
            /* it don't have a valid subsection name */
            return 0;
        }
        sub_vmsd = vmstate_get_subsection(vmsd->subsections, idstr);
        if (sub_vmsd == NULL) {
            return -ENOENT;
        }
        qemu_file_skip(f, 1); /* subsection */
        qemu_file_skip(f, 1); /* len */
        qemu_file_skip(f, len); /* idstr */
        version_id = qemu_get_be32(f);

        ret = vmstate_load_state(f, sub_vmsd, opaque, version_id);
        if (ret) {
            return ret;
        }
    }
    return 0;
}

static void vmstate_subsection_save(QEMUFile *f, const VMStateDescription *vmsd,
                                    void *opaque)
{
    const VMStateSubsection *sub = vmsd->subsections;

    while (sub && sub->needed) {
        if (sub->needed(opaque)) {
            const VMStateDescription *vmsd = sub->vmsd;
            uint8_t len;

            qemu_put_byte(f, QEMU_VM_SUBSECTION);
            len = strlen(vmsd->name);
            qemu_put_byte(f, len);
            qemu_put_buffer(f, (uint8_t *)vmsd->name, len);
            qemu_put_be32(f, vmsd->version_id);
            vmstate_save_state(f, vmsd, opaque);
        }
        sub++;
    }
}

typedef struct LoadStateEntry {
    QLIST_ENTRY(LoadStateEntry) entry;
    SaveStateEntry *se;
    int section_id;
    int version_id;
} LoadStateEntry;

int qemu_loadvm_state(QEMUFile *f)
{
    QLIST_HEAD(, LoadStateEntry) loadvm_handlers =
        QLIST_HEAD_INITIALIZER(loadvm_handlers);
    LoadStateEntry *le, *new_le;
    uint8_t section_type;
    unsigned int v;
    int ret;

    if (qemu_savevm_state_blocked(NULL)) {
        return -EINVAL;
    }

    v = qemu_get_be32(f);
    if (v != QEMU_VM_FILE_MAGIC)
        return -EINVAL;

    v = qemu_get_be32(f);
    if (v == QEMU_VM_FILE_VERSION_COMPAT) {
        fprintf(stderr, "SaveVM v2 format is obsolete and don't work anymore\n");
        return -ENOTSUP;
    }
    if (v != QEMU_VM_FILE_VERSION)
        return -ENOTSUP;

    while ((section_type = qemu_get_byte(f)) != QEMU_VM_EOF) {
        uint32_t instance_id, version_id, section_id;
        SaveStateEntry *se;
        char idstr[257];
        int len;

        switch (section_type) {
        case QEMU_VM_SECTION_START:
        case QEMU_VM_SECTION_FULL:
            /* Read section start */
            section_id = qemu_get_be32(f);
            len = qemu_get_byte(f);
            qemu_get_buffer(f, (uint8_t *)idstr, len);
            idstr[len] = 0;
            instance_id = qemu_get_be32(f);
            version_id = qemu_get_be32(f);

            /* Find savevm section */
            se = find_se(idstr, instance_id);
            if (se == NULL) {
                fprintf(stderr, "Unknown savevm section or instance '%s' %d\n", idstr, instance_id);
                ret = -EINVAL;
                goto out;
            }

            /* Validate version */
            if (version_id > se->version_id) {
                fprintf(stderr, "savevm: unsupported version %d for '%s' v%d\n",
                        version_id, idstr, se->version_id);
                ret = -EINVAL;
                goto out;
            }

            /* Add entry */
            le = g_malloc0(sizeof(*le));

            le->se = se;
            le->section_id = section_id;
            le->version_id = version_id;
            QLIST_INSERT_HEAD(&loadvm_handlers, le, entry);

            ret = vmstate_load(f, le->se, le->version_id);
            if (ret < 0) {
                fprintf(stderr, "qemu: warning: error while loading state for instance 0x%x of device '%s'\n",
                        instance_id, idstr);
                goto out;
            }
            break;
        case QEMU_VM_SECTION_PART:
        case QEMU_VM_SECTION_END:
            section_id = qemu_get_be32(f);

            QLIST_FOREACH(le, &loadvm_handlers, entry) {
                if (le->section_id == section_id) {
                    break;
                }
            }
            if (le == NULL) {
                fprintf(stderr, "Unknown savevm section %d\n", section_id);
                ret = -EINVAL;
                goto out;
            }

            ret = vmstate_load(f, le->se, le->version_id);
            if (ret < 0) {
                fprintf(stderr, "qemu: warning: error while loading state section id %d\n",
                        section_id);
                goto out;
            }
            break;
        default:
            fprintf(stderr, "Unknown savevm section type %d\n", section_type);
            ret = -EINVAL;
            goto out;
        }
    }

    cpu_synchronize_all_post_init();

    ret = 0;

out:
    QLIST_FOREACH_SAFE(le, &loadvm_handlers, entry, new_le) {
        QLIST_REMOVE(le, entry);
        g_free(le);
    }

    if (ret == 0) {
        ret = qemu_file_get_error(f);
    }

    return ret;
}

static int bdrv_snapshot_find(BlockDriverState *bs, QEMUSnapshotInfo *sn_info,
                              const char *name)
{
    QEMUSnapshotInfo *sn_tab, *sn;
    int nb_sns, i, ret;

    ret = -ENOENT;
    nb_sns = bdrv_snapshot_list(bs, &sn_tab);
    if (nb_sns < 0)
        return ret;
    for(i = 0; i < nb_sns; i++) {
        sn = &sn_tab[i];
        if (!strcmp(sn->id_str, name) || !strcmp(sn->name, name)) {
            *sn_info = *sn;
            ret = 0;
            break;
        }
    }
    g_free(sn_tab);
    return ret;
}

/*
 * Deletes snapshots of a given name in all opened images.
 */
static int del_existing_snapshots(Monitor *mon, const char *name)
{
    BlockDriverState *bs;
    QEMUSnapshotInfo sn1, *snapshot = &sn1;
    int ret;

    bs = NULL;
    while ((bs = bdrv_next(bs))) {
        if (bdrv_can_snapshot(bs) &&
            bdrv_snapshot_find(bs, snapshot, name) >= 0)
        {
            ret = bdrv_snapshot_delete(bs, name);
            if (ret < 0) {
                monitor_printf(mon,
                               "Error while deleting snapshot on '%s'\n",
                               bdrv_get_device_name(bs));
                return -1;
            }
        }
    }

    return 0;
}

void do_savevm(Monitor *mon, const QDict *qdict)
{
    BlockDriverState *bs, *bs1;
    QEMUSnapshotInfo sn1, *sn = &sn1, old_sn1, *old_sn = &old_sn1;
    int ret;
    QEMUFile *f;
    int saved_vm_running;
    uint64_t vm_state_size;
    qemu_timeval tv;
    struct tm tm;
    const char *name = qdict_get_try_str(qdict, "name");

    /* Verify if there is a device that doesn't support snapshots and is writable */
    bs = NULL;
    while ((bs = bdrv_next(bs))) {

        if (!bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) {
            continue;
        }

        if (!bdrv_can_snapshot(bs)) {
            monitor_printf(mon, "Device '%s' is writable but does not support snapshots.\n",
                               bdrv_get_device_name(bs));
            return;
        }
    }

    bs = bdrv_snapshots();
    if (!bs) {
        monitor_printf(mon, "No block device can accept snapshots\n");
        return;
    }

    saved_vm_running = runstate_is_running();
    vm_stop(RUN_STATE_SAVE_VM);

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

    /* fill auxiliary fields */
    qemu_gettimeofday(&tv);
    sn->date_sec = tv.tv_sec;
    sn->date_nsec = tv.tv_usec * 1000;
    sn->vm_clock_nsec = qemu_get_clock_ns(vm_clock);

    if (name) {
        ret = bdrv_snapshot_find(bs, old_sn, name);
        if (ret >= 0) {
            pstrcpy(sn->name, sizeof(sn->name), old_sn->name);
            pstrcpy(sn->id_str, sizeof(sn->id_str), old_sn->id_str);
        } else {
            pstrcpy(sn->name, sizeof(sn->name), name);
        }
    } else {
        /* cast below needed for OpenBSD where tv_sec is still 'long' */
        localtime_r((const time_t *)&tv.tv_sec, &tm);
        strftime(sn->name, sizeof(sn->name), "vm-%Y%m%d%H%M%S", &tm);
    }

    /* Delete old snapshots of the same name */
    if (name && del_existing_snapshots(mon, name) < 0) {
        goto the_end;
    }

    /* save the VM state */
    f = qemu_fopen_bdrv(bs, 1);
    if (!f) {
        monitor_printf(mon, "Could not open VM state file\n");
        goto the_end;
    }
    ret = qemu_savevm_state(f);
    vm_state_size = qemu_ftell(f);
    qemu_fclose(f);
    if (ret < 0) {
        monitor_printf(mon, "Error %d while writing VM\n", ret);
        goto the_end;
    }

    /* create the snapshots */

    bs1 = NULL;
    while ((bs1 = bdrv_next(bs1))) {
        if (bdrv_can_snapshot(bs1)) {
            /* Write VM state size only to the image that contains the state */
            sn->vm_state_size = (bs == bs1 ? vm_state_size : 0);
            ret = bdrv_snapshot_create(bs1, sn);
            if (ret < 0) {
                monitor_printf(mon, "Error while creating snapshot on '%s'\n",
                               bdrv_get_device_name(bs1));
            }
        }
    }

 the_end:
    if (saved_vm_running)
        vm_start();
}

void qmp_xen_save_devices_state(const char *filename, Error **errp)
{
    QEMUFile *f;
    int saved_vm_running;
    int ret;

    saved_vm_running = runstate_is_running();
    vm_stop(RUN_STATE_SAVE_VM);

    f = qemu_fopen(filename, "wb");
    if (!f) {
        error_set(errp, QERR_OPEN_FILE_FAILED, filename);
        goto the_end;
    }
    ret = qemu_save_device_state(f);
    qemu_fclose(f);
    if (ret < 0) {
        error_set(errp, QERR_IO_ERROR);
    }

 the_end:
    if (saved_vm_running)
        vm_start();
}

int load_vmstate(const char *name)
{
    BlockDriverState *bs, *bs_vm_state;
    QEMUSnapshotInfo sn;
    QEMUFile *f;
    int ret;

    bs_vm_state = bdrv_snapshots();
    if (!bs_vm_state) {
        error_report("No block device supports snapshots");
        return -ENOTSUP;
    }

    /* Don't even try to load empty VM states */
    ret = bdrv_snapshot_find(bs_vm_state, &sn, name);
    if (ret < 0) {
        return ret;
    } else if (sn.vm_state_size == 0) {
        error_report("This is a disk-only snapshot. Revert to it offline "
            "using qemu-img.");
        return -EINVAL;
    }

    /* Verify if there is any device that doesn't support snapshots and is
    writable and check if the requested snapshot is available too. */
    bs = NULL;
    while ((bs = bdrv_next(bs))) {

        if (!bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) {
            continue;
        }

        if (!bdrv_can_snapshot(bs)) {
            error_report("Device '%s' is writable but does not support snapshots.",
                               bdrv_get_device_name(bs));
            return -ENOTSUP;
        }

        ret = bdrv_snapshot_find(bs, &sn, name);
        if (ret < 0) {
            error_report("Device '%s' does not have the requested snapshot '%s'",
                           bdrv_get_device_name(bs), name);
            return ret;
        }
    }

    /* Flush all IO requests so they don't interfere with the new state.  */
    bdrv_drain_all();

    bs = NULL;
    while ((bs = bdrv_next(bs))) {
        if (bdrv_can_snapshot(bs)) {
            ret = bdrv_snapshot_goto(bs, name);
            if (ret < 0) {
                error_report("Error %d while activating snapshot '%s' on '%s'",
                             ret, name, bdrv_get_device_name(bs));
                return ret;
            }
        }
    }

    /* restore the VM state */
    f = qemu_fopen_bdrv(bs_vm_state, 0);
    if (!f) {
        error_report("Could not open VM state file");
        return -EINVAL;
    }

    qemu_system_reset(VMRESET_SILENT);
    ret = qemu_loadvm_state(f);

    qemu_fclose(f);
    if (ret < 0) {
        error_report("Error %d while loading VM state", ret);
        return ret;
    }

    return 0;
}

void do_delvm(Monitor *mon, const QDict *qdict)
{
    BlockDriverState *bs, *bs1;
    int ret;
    const char *name = qdict_get_str(qdict, "name");

    bs = bdrv_snapshots();
    if (!bs) {
        monitor_printf(mon, "No block device supports snapshots\n");
        return;
    }

    bs1 = NULL;
    while ((bs1 = bdrv_next(bs1))) {
        if (bdrv_can_snapshot(bs1)) {
            ret = bdrv_snapshot_delete(bs1, name);
            if (ret < 0) {
                if (ret == -ENOTSUP)
                    monitor_printf(mon,
                                   "Snapshots not supported on device '%s'\n",
                                   bdrv_get_device_name(bs1));
                else
                    monitor_printf(mon, "Error %d while deleting snapshot on "
                                   "'%s'\n", ret, bdrv_get_device_name(bs1));
            }
        }
    }
}

void do_info_snapshots(Monitor *mon, const QDict *qdict)
{
    BlockDriverState *bs, *bs1;
    QEMUSnapshotInfo *sn_tab, *sn, s, *sn_info = &s;
    int nb_sns, i, ret, available;
    int total;
    int *available_snapshots;
    char buf[256];

    bs = bdrv_snapshots();
    if (!bs) {
        monitor_printf(mon, "No available block device supports snapshots\n");
        return;
    }

    nb_sns = bdrv_snapshot_list(bs, &sn_tab);
    if (nb_sns < 0) {
        monitor_printf(mon, "bdrv_snapshot_list: error %d\n", nb_sns);
        return;
    }

    if (nb_sns == 0) {
        monitor_printf(mon, "There is no snapshot available.\n");
        return;
    }

    available_snapshots = g_malloc0(sizeof(int) * nb_sns);
    total = 0;
    for (i = 0; i < nb_sns; i++) {
        sn = &sn_tab[i];
        available = 1;
        bs1 = NULL;

        while ((bs1 = bdrv_next(bs1))) {
            if (bdrv_can_snapshot(bs1) && bs1 != bs) {
                ret = bdrv_snapshot_find(bs1, sn_info, sn->id_str);
                if (ret < 0) {
                    available = 0;
                    break;
                }
            }
        }

        if (available) {
            available_snapshots[total] = i;
            total++;
        }
    }

    if (total > 0) {
        monitor_printf(mon, "%s\n", bdrv_snapshot_dump(buf, sizeof(buf), NULL));
        for (i = 0; i < total; i++) {
            sn = &sn_tab[available_snapshots[i]];
            monitor_printf(mon, "%s\n", bdrv_snapshot_dump(buf, sizeof(buf), sn));
        }
    } else {
        monitor_printf(mon, "There is no suitable snapshot available\n");
    }

    g_free(sn_tab);
    g_free(available_snapshots);

}

void vmstate_register_ram(MemoryRegion *mr, DeviceState *dev)
{
    qemu_ram_set_idstr(memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK,
                       memory_region_name(mr), dev);
}

void vmstate_unregister_ram(MemoryRegion *mr, DeviceState *dev)
{
    /* Nothing do to while the implementation is in RAMBlock */
}

void vmstate_register_ram_global(MemoryRegion *mr)
{
    vmstate_register_ram(mr, NULL);
}