Archipelago » qemu

/*

 * QEMU host block devices

 *

 * Copyright (c) 2003-2008 Fabrice Bellard

 *

 * This work is licensed under the terms of the GNU GPL, version 2 or

 * later.  See the COPYING file in the top-level directory.

 *

 * This file incorporates work covered by the following copyright and

 * permission notice:

 *

 * 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 "sysemu/blockdev.h"

#include "hw/block/block.h"

#include "block/blockjob.h"

#include "monitor/monitor.h"

#include "qapi/qmp/qerror.h"

#include "qemu/option.h"

#include "qemu/config-file.h"

#include "qapi/qmp/types.h"

#include "sysemu/sysemu.h"

#include "block/block_int.h"

#include "qmp-commands.h"

#include "trace.h"

#include "sysemu/arch_init.h"

static QTAILQ_HEAD(drivelist, DriveInfo) drives = QTAILQ_HEAD_INITIALIZER(drives);

extern QemuOptsList qemu_common_drive_opts;

static const char *const if_name[IF_COUNT] = {

    [IF_NONE] = "none",

    [IF_IDE] = "ide",

    [IF_SCSI] = "scsi",

    [IF_FLOPPY] = "floppy",

    [IF_PFLASH] = "pflash",

    [IF_MTD] = "mtd",

    [IF_SD] = "sd",

    [IF_VIRTIO] = "virtio",

    [IF_XEN] = "xen",

};

static const int if_max_devs[IF_COUNT] = {

    /*

     * Do not change these numbers!  They govern how drive option

     * index maps to unit and bus.  That mapping is ABI.

     *

     * All controllers used to imlement if=T drives need to support

     * if_max_devs[T] units, for any T with if_max_devs[T] != 0.

     * Otherwise, some index values map to "impossible" bus, unit

     * values.

     *

     * For instance, if you change [IF_SCSI] to 255, -drive

     * if=scsi,index=12 no longer means bus=1,unit=5, but

     * bus=0,unit=12.  With an lsi53c895a controller (7 units max),

     * the drive can't be set up.  Regression.

     */

    [IF_IDE] = 2,

    [IF_SCSI] = 7,

};

/*

 * We automatically delete the drive when a device using it gets

 * unplugged.  Questionable feature, but we can't just drop it.

 * Device models call blockdev_mark_auto_del() to schedule the

 * automatic deletion, and generic qdev code calls blockdev_auto_del()

 * when deletion is actually safe.

 */

void blockdev_mark_auto_del(BlockDriverState *bs)

{

    DriveInfo *dinfo = drive_get_by_blockdev(bs);

    if (bs->job) {

        block_job_cancel(bs->job);

    }

    if (dinfo) {

        dinfo->auto_del = 1;

    }

}

void blockdev_auto_del(BlockDriverState *bs)

{

    DriveInfo *dinfo = drive_get_by_blockdev(bs);

    if (dinfo && dinfo->auto_del) {

        drive_put_ref(dinfo);

    }

}

static int drive_index_to_bus_id(BlockInterfaceType type, int index)

{

    int max_devs = if_max_devs[type];

    return max_devs ? index / max_devs : 0;

}

static int drive_index_to_unit_id(BlockInterfaceType type, int index)

{

    int max_devs = if_max_devs[type];

    return max_devs ? index % max_devs : index;

}

QemuOpts *drive_def(const char *optstr)

{

    return qemu_opts_parse(qemu_find_opts("drive"), optstr, 0);

}

QemuOpts *drive_add(BlockInterfaceType type, int index, const char *file,

                    const char *optstr)

{

    QemuOpts *opts;

    char buf[32];

    opts = drive_def(optstr);

    if (!opts) {

        return NULL;

    }

    if (type != IF_DEFAULT) {

        qemu_opt_set(opts, "if", if_name[type]);

    }

    if (index >= 0) {

        snprintf(buf, sizeof(buf), "%d", index);

        qemu_opt_set(opts, "index", buf);

    }

    if (file)

        qemu_opt_set(opts, "file", file);

    return opts;

}

DriveInfo *drive_get(BlockInterfaceType type, int bus, int unit)

{

    DriveInfo *dinfo;

    /* seek interface, bus and unit */

    QTAILQ_FOREACH(dinfo, &drives, next) {

        if (dinfo->type == type &&

            dinfo->bus == bus &&

            dinfo->unit == unit)

            return dinfo;

    }

    return NULL;

}

DriveInfo *drive_get_by_index(BlockInterfaceType type, int index)

{

    return drive_get(type,

                     drive_index_to_bus_id(type, index),

                     drive_index_to_unit_id(type, index));

}

int drive_get_max_bus(BlockInterfaceType type)

{

    int max_bus;

    DriveInfo *dinfo;

    max_bus = -1;

    QTAILQ_FOREACH(dinfo, &drives, next) {

        if(dinfo->type == type &&

           dinfo->bus > max_bus)

            max_bus = dinfo->bus;

    }

    return max_bus;

}

/* Get a block device.  This should only be used for single-drive devices

   (e.g. SD/Floppy/MTD).  Multi-disk devices (scsi/ide) should use the

   appropriate bus.  */

DriveInfo *drive_get_next(BlockInterfaceType type)

{

    static int next_block_unit[IF_COUNT];

    return drive_get(type, 0, next_block_unit[type]++);

}

DriveInfo *drive_get_by_blockdev(BlockDriverState *bs)

{

    DriveInfo *dinfo;

    QTAILQ_FOREACH(dinfo, &drives, next) {

        if (dinfo->bdrv == bs) {

            return dinfo;

        }

    }

    return NULL;

}

static void bdrv_format_print(void *opaque, const char *name)

{

    error_printf(" %s", name);

}

static void drive_uninit(DriveInfo *dinfo)

{

    qemu_opts_del(dinfo->opts);

    bdrv_unref(dinfo->bdrv);

    g_free(dinfo->id);

    QTAILQ_REMOVE(&drives, dinfo, next);

    g_free(dinfo->serial);

    g_free(dinfo);

}

void drive_put_ref(DriveInfo *dinfo)

{

    assert(dinfo->refcount);

    if (--dinfo->refcount == 0) {

        drive_uninit(dinfo);

    }

}

void drive_get_ref(DriveInfo *dinfo)

{

    dinfo->refcount++;

}

typedef struct {

    QEMUBH *bh;

    BlockDriverState *bs;

} BDRVPutRefBH;

static void bdrv_put_ref_bh(void *opaque)

{

    BDRVPutRefBH *s = opaque;

    bdrv_unref(s->bs);

    qemu_bh_delete(s->bh);

    g_free(s);

}

/*

 * Release a BDS reference in a BH

 *

 * It is not safe to use bdrv_unref() from a callback function when the callers

 * still need the BlockDriverState.  In such cases we schedule a BH to release

 * the reference.

 */

static void bdrv_put_ref_bh_schedule(BlockDriverState *bs)

{

    BDRVPutRefBH *s;

    s = g_new(BDRVPutRefBH, 1);

    s->bh = qemu_bh_new(bdrv_put_ref_bh, s);

    s->bs = bs;

    qemu_bh_schedule(s->bh);

}

static int parse_block_error_action(const char *buf, bool is_read)

{

    if (!strcmp(buf, "ignore")) {

        return BLOCKDEV_ON_ERROR_IGNORE;

    } else if (!is_read && !strcmp(buf, "enospc")) {

        return BLOCKDEV_ON_ERROR_ENOSPC;

    } else if (!strcmp(buf, "stop")) {

        return BLOCKDEV_ON_ERROR_STOP;

    } else if (!strcmp(buf, "report")) {

        return BLOCKDEV_ON_ERROR_REPORT;

    } else {

        error_report("'%s' invalid %s error action",

                     buf, is_read ? "read" : "write");

        return -1;

    }

}

static bool check_throttle_config(ThrottleConfig *cfg, Error **errp)

{

    if (throttle_conflicting(cfg)) {

        error_setg(errp, "bps/iops/max total values and read/write values"

                         " cannot be used at the same time");

        return false;

    }

    if (!throttle_is_valid(cfg)) {

        error_setg(errp, "bps/iops/maxs values must be 0 or greater");

        return false;

    }

    return true;

}

static DriveInfo *blockdev_init(QemuOpts *all_opts,

                                BlockInterfaceType block_default_type)

{

    const char *buf;

    const char *file = NULL;

    const char *serial;

    const char *mediastr = "";

    BlockInterfaceType type;

    enum { MEDIA_DISK, MEDIA_CDROM } media;

    int bus_id, unit_id;

    int cyls, heads, secs, translation;

    int max_devs;

    int index;

    int ro = 0;

    int bdrv_flags = 0;

    int on_read_error, on_write_error;

    const char *devaddr;

    DriveInfo *dinfo;

    ThrottleConfig cfg;

    int snapshot = 0;

    bool copy_on_read;

    int ret;

    Error *error = NULL;

    QemuOpts *opts;

    QDict *bs_opts;

    const char *id;

    bool has_driver_specific_opts;

    BlockDriver *drv = NULL;

    translation = BIOS_ATA_TRANSLATION_AUTO;

    media = MEDIA_DISK;

    /* Check common options by copying from all_opts to opts, all other options

     * are stored in bs_opts. */

    id = qemu_opts_id(all_opts);

    opts = qemu_opts_create(&qemu_common_drive_opts, id, 1, &error);

    if (error_is_set(&error)) {

        qerror_report_err(error);

        error_free(error);

        return NULL;

    }

    bs_opts = qdict_new();

    qemu_opts_to_qdict(all_opts, bs_opts);

    qemu_opts_absorb_qdict(opts, bs_opts, &error);

    if (error_is_set(&error)) {

        qerror_report_err(error);

        error_free(error);

        return NULL;

    }

    if (id) {

        qdict_del(bs_opts, "id");

    }

    has_driver_specific_opts = !!qdict_size(bs_opts);

    /* extract parameters */

    bus_id  = qemu_opt_get_number(opts, "bus", 0);

    unit_id = qemu_opt_get_number(opts, "unit", -1);

    index   = qemu_opt_get_number(opts, "index", -1);

    cyls  = qemu_opt_get_number(opts, "cyls", 0);

    heads = qemu_opt_get_number(opts, "heads", 0);

    secs  = qemu_opt_get_number(opts, "secs", 0);

    snapshot = qemu_opt_get_bool(opts, "snapshot", 0);

    ro = qemu_opt_get_bool(opts, "read-only", 0);

    copy_on_read = qemu_opt_get_bool(opts, "copy-on-read", false);

    file = qemu_opt_get(opts, "file");

    serial = qemu_opt_get(opts, "serial");

    if ((buf = qemu_opt_get(opts, "if")) != NULL) {

        for (type = 0; type < IF_COUNT && strcmp(buf, if_name[type]); type++)

            ;

        if (type == IF_COUNT) {

            error_report("unsupported bus type '%s'", buf);

            return NULL;

        }

    } else {

        type = block_default_type;

    }

    max_devs = if_max_devs[type];

    if (cyls || heads || secs) {

        if (cyls < 1) {

            error_report("invalid physical cyls number");

            return NULL;

        }

        if (heads < 1) {

            error_report("invalid physical heads number");

            return NULL;

        }

        if (secs < 1) {

            error_report("invalid physical secs number");

            return NULL;

        }

    }

    if ((buf = qemu_opt_get(opts, "trans")) != NULL) {

        if (!cyls) {

            error_report("'%s' trans must be used with cyls, heads and secs",

                         buf);

            return NULL;

        }

        if (!strcmp(buf, "none"))

            translation = BIOS_ATA_TRANSLATION_NONE;

        else if (!strcmp(buf, "lba"))

            translation = BIOS_ATA_TRANSLATION_LBA;

        else if (!strcmp(buf, "auto"))

            translation = BIOS_ATA_TRANSLATION_AUTO;

        else {

            error_report("'%s' invalid translation type", buf);

            return NULL;

        }

    }

    if ((buf = qemu_opt_get(opts, "media")) != NULL) {

        if (!strcmp(buf, "disk")) {

            media = MEDIA_DISK;

        } else if (!strcmp(buf, "cdrom")) {

            if (cyls || secs || heads) {

                error_report("CHS can't be set with media=%s", buf);

                return NULL;

            }

            media = MEDIA_CDROM;

        } else {

            error_report("'%s' invalid media", buf);

            return NULL;

        }

    }

    if ((buf = qemu_opt_get(opts, "discard")) != NULL) {

        if (bdrv_parse_discard_flags(buf, &bdrv_flags) != 0) {

            error_report("invalid discard option");

            return NULL;

        }

    }

    if (qemu_opt_get_bool(opts, "cache.writeback", true)) {

        bdrv_flags |= BDRV_O_CACHE_WB;

    }

    if (qemu_opt_get_bool(opts, "cache.direct", false)) {

        bdrv_flags |= BDRV_O_NOCACHE;

    }

    if (qemu_opt_get_bool(opts, "cache.no-flush", true)) {

        bdrv_flags |= BDRV_O_NO_FLUSH;

    }

#ifdef CONFIG_LINUX_AIO

    if ((buf = qemu_opt_get(opts, "aio")) != NULL) {

        if (!strcmp(buf, "native")) {

            bdrv_flags |= BDRV_O_NATIVE_AIO;

        } else if (!strcmp(buf, "threads")) {

            /* this is the default */

        } else {

           error_report("invalid aio option");

           return NULL;

        }

    }

#endif

    if ((buf = qemu_opt_get(opts, "format")) != NULL) {

        if (is_help_option(buf)) {

            error_printf("Supported formats:");

            bdrv_iterate_format(bdrv_format_print, NULL);

            error_printf("\n");

            return NULL;

        }

        drv = bdrv_find_whitelisted_format(buf, ro);

        if (!drv) {

            if (!ro && bdrv_find_whitelisted_format(buf, !ro)) {

                error_report("'%s' can be only used as read-only device.", buf);

            } else {

                error_report("'%s' invalid format", buf);

            }

            return NULL;

        }

    }

    /* disk I/O throttling */

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

    cfg.buckets[THROTTLE_BPS_TOTAL].avg =

        qemu_opt_get_number(opts, "throttling.bps-total", 0);

    cfg.buckets[THROTTLE_BPS_READ].avg  =

        qemu_opt_get_number(opts, "throttling.bps-read", 0);

    cfg.buckets[THROTTLE_BPS_WRITE].avg =

        qemu_opt_get_number(opts, "throttling.bps-write", 0);

    cfg.buckets[THROTTLE_OPS_TOTAL].avg =

        qemu_opt_get_number(opts, "throttling.iops-total", 0);

    cfg.buckets[THROTTLE_OPS_READ].avg =

        qemu_opt_get_number(opts, "throttling.iops-read", 0);

    cfg.buckets[THROTTLE_OPS_WRITE].avg =

        qemu_opt_get_number(opts, "throttling.iops-write", 0);

    cfg.buckets[THROTTLE_BPS_TOTAL].max =

        qemu_opt_get_number(opts, "throttling.bps-total-max", 0);

    cfg.buckets[THROTTLE_BPS_READ].max  =

        qemu_opt_get_number(opts, "throttling.bps-read-max", 0);

    cfg.buckets[THROTTLE_BPS_WRITE].max =

        qemu_opt_get_number(opts, "throttling.bps-write-max", 0);

    cfg.buckets[THROTTLE_OPS_TOTAL].max =

        qemu_opt_get_number(opts, "throttling.iops-total-max", 0);

    cfg.buckets[THROTTLE_OPS_READ].max =

        qemu_opt_get_number(opts, "throttling.iops-read-max", 0);

    cfg.buckets[THROTTLE_OPS_WRITE].max =

        qemu_opt_get_number(opts, "throttling.iops-write-max", 0);

    cfg.op_size = qemu_opt_get_number(opts, "throttling.iops-size", 0);

    if (!check_throttle_config(&cfg, &error)) {

        error_report("%s", error_get_pretty(error));

        error_free(error);

        return NULL;

    }

    if (qemu_opt_get(opts, "boot") != NULL) {

        fprintf(stderr, "qemu-kvm: boot=on|off is deprecated and will be "

                "ignored. Future versions will reject this parameter. Please "

                "update your scripts.\n");

    }

    on_write_error = BLOCKDEV_ON_ERROR_ENOSPC;

    if ((buf = qemu_opt_get(opts, "werror")) != NULL) {

        if (type != IF_IDE && type != IF_SCSI && type != IF_VIRTIO && type != IF_NONE) {

            error_report("werror is not supported by this bus type");

            return NULL;

        }

        on_write_error = parse_block_error_action(buf, 0);

        if (on_write_error < 0) {

            return NULL;

        }

    }

    on_read_error = BLOCKDEV_ON_ERROR_REPORT;

    if ((buf = qemu_opt_get(opts, "rerror")) != NULL) {

        if (type != IF_IDE && type != IF_VIRTIO && type != IF_SCSI && type != IF_NONE) {

            error_report("rerror is not supported by this bus type");

            return NULL;

        }

        on_read_error = parse_block_error_action(buf, 1);

        if (on_read_error < 0) {

            return NULL;

        }

    }

    if ((devaddr = qemu_opt_get(opts, "addr")) != NULL) {

        if (type != IF_VIRTIO) {

            error_report("addr is not supported by this bus type");

            return NULL;

        }

    }

    /* compute bus and unit according index */

    if (index != -1) {

        if (bus_id != 0 || unit_id != -1) {

            error_report("index cannot be used with bus and unit");

            return NULL;

        }

        bus_id = drive_index_to_bus_id(type, index);

        unit_id = drive_index_to_unit_id(type, index);

    }

    /* if user doesn't specify a unit_id,

     * try to find the first free

     */

    if (unit_id == -1) {

       unit_id = 0;

       while (drive_get(type, bus_id, unit_id) != NULL) {

           unit_id++;

           if (max_devs && unit_id >= max_devs) {

               unit_id -= max_devs;

               bus_id++;

           }

       }

    }

    /* check unit id */

    if (max_devs && unit_id >= max_devs) {

        error_report("unit %d too big (max is %d)",

                     unit_id, max_devs - 1);

        return NULL;

    }

    /*

     * catch multiple definitions

     */

    if (drive_get(type, bus_id, unit_id) != NULL) {

        error_report("drive with bus=%d, unit=%d (index=%d) exists",

                     bus_id, unit_id, index);

        return NULL;

    }

    /* init */

    dinfo = g_malloc0(sizeof(*dinfo));

    if ((buf = qemu_opts_id(opts)) != NULL) {

        dinfo->id = g_strdup(buf);

    } else {

        /* no id supplied -> create one */

        dinfo->id = g_malloc0(32);

        if (type == IF_IDE || type == IF_SCSI)

            mediastr = (media == MEDIA_CDROM) ? "-cd" : "-hd";

        if (max_devs)

            snprintf(dinfo->id, 32, "%s%i%s%i",

                     if_name[type], bus_id, mediastr, unit_id);

        else

            snprintf(dinfo->id, 32, "%s%s%i",

                     if_name[type], mediastr, unit_id);

    }

    dinfo->bdrv = bdrv_new(dinfo->id);

    dinfo->bdrv->open_flags = snapshot ? BDRV_O_SNAPSHOT : 0;

    dinfo->bdrv->read_only = ro;

    dinfo->devaddr = devaddr;

    dinfo->type = type;

    dinfo->bus = bus_id;

    dinfo->unit = unit_id;

    dinfo->cyls = cyls;

    dinfo->heads = heads;

    dinfo->secs = secs;

    dinfo->trans = translation;

    dinfo->opts = all_opts;

    dinfo->refcount = 1;

    if (serial != NULL) {

        dinfo->serial = g_strdup(serial);

    }

    QTAILQ_INSERT_TAIL(&drives, dinfo, next);

    bdrv_set_on_error(dinfo->bdrv, on_read_error, on_write_error);

    /* disk I/O throttling */

    if (throttle_enabled(&cfg)) {

        bdrv_io_limits_enable(dinfo->bdrv);

        bdrv_set_io_limits(dinfo->bdrv, &cfg);

    }

    switch(type) {

    case IF_IDE:

    case IF_SCSI:

    case IF_XEN:

    case IF_NONE:

        dinfo->media_cd = media == MEDIA_CDROM;

        break;

    case IF_SD:

    case IF_FLOPPY:

    case IF_PFLASH:

    case IF_MTD:

        break;

    case IF_VIRTIO:

    {

        /* add virtio block device */

        QemuOpts *devopts;

        devopts = qemu_opts_create_nofail(qemu_find_opts("device"));

        if (arch_type == QEMU_ARCH_S390X) {

            qemu_opt_set(devopts, "driver", "virtio-blk-s390");

        } else {

            qemu_opt_set(devopts, "driver", "virtio-blk-pci");

        }

        qemu_opt_set(devopts, "drive", dinfo->id);

        if (devaddr)

            qemu_opt_set(devopts, "addr", devaddr);

        break;

    }

    default:

        abort();

    }

    if (!file || !*file) {

        if (has_driver_specific_opts) {

            file = NULL;

        } else {

            return dinfo;

        }

    }

    if (snapshot) {

        /* always use cache=unsafe with snapshot */

        bdrv_flags &= ~BDRV_O_CACHE_MASK;

        bdrv_flags |= (BDRV_O_SNAPSHOT|BDRV_O_CACHE_WB|BDRV_O_NO_FLUSH);

    }

    if (copy_on_read) {

        bdrv_flags |= BDRV_O_COPY_ON_READ;

    }

    if (runstate_check(RUN_STATE_INMIGRATE)) {

        bdrv_flags |= BDRV_O_INCOMING;

    }

    if (media == MEDIA_CDROM) {

        /* CDROM is fine for any interface, don't check.  */

        ro = 1;

    } else if (ro == 1) {

        if (type != IF_SCSI && type != IF_VIRTIO && type != IF_FLOPPY &&

            type != IF_NONE && type != IF_PFLASH) {

            error_report("read-only not supported by this bus type");

            goto err;

        }

    }

    bdrv_flags |= ro ? 0 : BDRV_O_RDWR;

    if (ro && copy_on_read) {

        error_report("warning: disabling copy_on_read on read-only drive");

    }

    QINCREF(bs_opts);

    ret = bdrv_open(dinfo->bdrv, file, bs_opts, bdrv_flags, drv, &error);

    if (ret < 0) {

        error_report("could not open disk image %s: %s",

                     file ?: dinfo->id, error_get_pretty(error));

        goto err;

    }

    if (bdrv_key_required(dinfo->bdrv))

        autostart = 0;

    QDECREF(bs_opts);

    qemu_opts_del(opts);

    return dinfo;

err:

    qemu_opts_del(opts);

    QDECREF(bs_opts);

    bdrv_unref(dinfo->bdrv);

    g_free(dinfo->id);

    QTAILQ_REMOVE(&drives, dinfo, next);

    g_free(dinfo);

    return NULL;

}

static void qemu_opt_rename(QemuOpts *opts, const char *from, const char *to)

{

    const char *value;

    value = qemu_opt_get(opts, from);

    if (value) {

        qemu_opt_set(opts, to, value);

        qemu_opt_unset(opts, from);

    }

}

DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)

{

    const char *value;

    /* Change legacy command line options into QMP ones */

    qemu_opt_rename(all_opts, "iops", "throttling.iops-total");

    qemu_opt_rename(all_opts, "iops_rd", "throttling.iops-read");

    qemu_opt_rename(all_opts, "iops_wr", "throttling.iops-write");

    qemu_opt_rename(all_opts, "bps", "throttling.bps-total");

    qemu_opt_rename(all_opts, "bps_rd", "throttling.bps-read");

    qemu_opt_rename(all_opts, "bps_wr", "throttling.bps-write");

    qemu_opt_rename(all_opts, "iops_max", "throttling.iops-total-max");

    qemu_opt_rename(all_opts, "iops_rd_max", "throttling.iops-read-max");

    qemu_opt_rename(all_opts, "iops_wr_max", "throttling.iops-write-max");

    qemu_opt_rename(all_opts, "bps_max", "throttling.bps-total-max");

    qemu_opt_rename(all_opts, "bps_rd_max", "throttling.bps-read-max");

    qemu_opt_rename(all_opts, "bps_wr_max", "throttling.bps-write-max");

    qemu_opt_rename(all_opts,

                    "iops_size", "throttling.iops-size");

    qemu_opt_rename(all_opts, "readonly", "read-only");

    value = qemu_opt_get(all_opts, "cache");

    if (value) {

        int flags = 0;

        if (bdrv_parse_cache_flags(value, &flags) != 0) {

            error_report("invalid cache option");

            return NULL;

        }

        /* Specific options take precedence */

        if (!qemu_opt_get(all_opts, "cache.writeback")) {

            qemu_opt_set_bool(all_opts, "cache.writeback",

                              !!(flags & BDRV_O_CACHE_WB));

        }

        if (!qemu_opt_get(all_opts, "cache.direct")) {

            qemu_opt_set_bool(all_opts, "cache.direct",

                              !!(flags & BDRV_O_NOCACHE));

        }

        if (!qemu_opt_get(all_opts, "cache.no-flush")) {

            qemu_opt_set_bool(all_opts, "cache.no-flush",

                              !!(flags & BDRV_O_NO_FLUSH));

        }

        qemu_opt_unset(all_opts, "cache");

    }

    return blockdev_init(all_opts, block_default_type);

}

void do_commit(Monitor *mon, const QDict *qdict)

{

    const char *device = qdict_get_str(qdict, "device");

    BlockDriverState *bs;

    int ret;

    if (!strcmp(device, "all")) {

        ret = bdrv_commit_all();

    } else {

        bs = bdrv_find(device);

        if (!bs) {

            monitor_printf(mon, "Device '%s' not found\n", device);

            return;

        }

        ret = bdrv_commit(bs);

    }

    if (ret < 0) {

        monitor_printf(mon, "'commit' error for '%s': %s\n", device,

                       strerror(-ret));

    }

}

static void blockdev_do_action(int kind, void *data, Error **errp)

{

    TransactionAction action;

    TransactionActionList list;

    action.kind = kind;

    action.data = data;

    list.value = &action;

    list.next = NULL;

    qmp_transaction(&list, errp);

}

void qmp_blockdev_snapshot_sync(const char *device, const char *snapshot_file,

                                bool has_format, const char *format,

                                bool has_mode, enum NewImageMode mode,

                                Error **errp)

{

    BlockdevSnapshot snapshot = {

        .device = (char *) device,

        .snapshot_file = (char *) snapshot_file,

        .has_format = has_format,

        .format = (char *) format,

        .has_mode = has_mode,

        .mode = mode,

    };

    blockdev_do_action(TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC,

                       &snapshot, errp);

}

void qmp_blockdev_snapshot_internal_sync(const char *device,

                                         const char *name,

                                         Error **errp)

{

    BlockdevSnapshotInternal snapshot = {

        .device = (char *) device,

        .name = (char *) name

    };

    blockdev_do_action(TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_INTERNAL_SYNC,

                       &snapshot, errp);

}

SnapshotInfo *qmp_blockdev_snapshot_delete_internal_sync(const char *device,

                                                         bool has_id,

                                                         const char *id,

                                                         bool has_name,

                                                         const char *name,

                                                         Error **errp)

{

    BlockDriverState *bs = bdrv_find(device);

    QEMUSnapshotInfo sn;

    Error *local_err = NULL;

    SnapshotInfo *info = NULL;

    int ret;

    if (!bs) {

        error_set(errp, QERR_DEVICE_NOT_FOUND, device);

        return NULL;

    }

    if (!has_id) {

        id = NULL;

    }

    if (!has_name) {

        name = NULL;

    }

    if (!id && !name) {

        error_setg(errp, "Name or id must be provided");

        return NULL;

    }

    ret = bdrv_snapshot_find_by_id_and_name(bs, id, name, &sn, &local_err);

    if (error_is_set(&local_err)) {

        error_propagate(errp, local_err);

        return NULL;

    }

    if (!ret) {

        error_setg(errp,

                   "Snapshot with id '%s' and name '%s' does not exist on "

                   "device '%s'",

                   STR_OR_NULL(id), STR_OR_NULL(name), device);

        return NULL;

    }

    bdrv_snapshot_delete(bs, id, name, &local_err);

    if (error_is_set(&local_err)) {

        error_propagate(errp, local_err);

        return NULL;

    }

    info = g_malloc0(sizeof(SnapshotInfo));

    info->id = g_strdup(sn.id_str);

    info->name = g_strdup(sn.name);

    info->date_nsec = sn.date_nsec;

    info->date_sec = sn.date_sec;

    info->vm_state_size = sn.vm_state_size;

    info->vm_clock_nsec = sn.vm_clock_nsec % 1000000000;

    info->vm_clock_sec = sn.vm_clock_nsec / 1000000000;

    return info;

}

/* New and old BlockDriverState structs for group snapshots */

typedef struct BlkTransactionState BlkTransactionState;

/* Only prepare() may fail. In a single transaction, only one of commit() or

   abort() will be called, clean() will always be called if it present. */

typedef struct BdrvActionOps {

    /* Size of state struct, in bytes. */

    size_t instance_size;

    /* Prepare the work, must NOT be NULL. */

    void (*prepare)(BlkTransactionState *common, Error **errp);

    /* Commit the changes, can be NULL. */

    void (*commit)(BlkTransactionState *common);

    /* Abort the changes on fail, can be NULL. */

    void (*abort)(BlkTransactionState *common);

    /* Clean up resource in the end, can be NULL. */

    void (*clean)(BlkTransactionState *common);

} BdrvActionOps;

/*

 * This structure must be arranged as first member in child type, assuming

 * that compiler will also arrange it to the same address with parent instance.

 * Later it will be used in free().

 */

struct BlkTransactionState {

    TransactionAction *action;

    const BdrvActionOps *ops;

    QSIMPLEQ_ENTRY(BlkTransactionState) entry;

};

/* internal snapshot private data */

typedef struct InternalSnapshotState {

    BlkTransactionState common;

    BlockDriverState *bs;

    QEMUSnapshotInfo sn;

} InternalSnapshotState;

static void internal_snapshot_prepare(BlkTransactionState *common,

                                      Error **errp)

{

    const char *device;

    const char *name;

    BlockDriverState *bs;

    QEMUSnapshotInfo old_sn, *sn;

    bool ret;

    qemu_timeval tv;

    BlockdevSnapshotInternal *internal;

    InternalSnapshotState *state;

    int ret1;

    g_assert(common->action->kind ==

             TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_INTERNAL_SYNC);

    internal = common->action->blockdev_snapshot_internal_sync;

    state = DO_UPCAST(InternalSnapshotState, common, common);

    /* 1. parse input */

    device = internal->device;

    name = internal->name;

    /* 2. check for validation */

    bs = bdrv_find(device);

    if (!bs) {

        error_set(errp, QERR_DEVICE_NOT_FOUND, device);

        return;

    }

    if (!bdrv_is_inserted(bs)) {

        error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);

        return;

    }

    if (bdrv_is_read_only(bs)) {

        error_set(errp, QERR_DEVICE_IS_READ_ONLY, device);

        return;

    }

    if (!bdrv_can_snapshot(bs)) {

        error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,

                  bs->drv->format_name, device, "internal snapshot");

        return;

    }

    if (!strlen(name)) {

        error_setg(errp, "Name is empty");

        return;

    }

    /* check whether a snapshot with name exist */

    ret = bdrv_snapshot_find_by_id_and_name(bs, NULL, name, &old_sn, errp);

    if (error_is_set(errp)) {

        return;

    } else if (ret) {

        error_setg(errp,

                   "Snapshot with name '%s' already exists on device '%s'",

                   name, device);

        return;

    }

    /* 3. take the snapshot */

    sn = &state->sn;

    pstrcpy(sn->name, sizeof(sn->name), name);

    qemu_gettimeofday(&tv);

    sn->date_sec = tv.tv_sec;

    sn->date_nsec = tv.tv_usec * 1000;

    sn->vm_clock_nsec = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);

    ret1 = bdrv_snapshot_create(bs, sn);

    if (ret1 < 0) {

        error_setg_errno(errp, -ret1,

                         "Failed to create snapshot '%s' on device '%s'",

                         name, device);

        return;

    }

    /* 4. succeed, mark a snapshot is created */

    state->bs = bs;

}

static void internal_snapshot_abort(BlkTransactionState *common)

{

    InternalSnapshotState *state =

                             DO_UPCAST(InternalSnapshotState, common, common);

    BlockDriverState *bs = state->bs;

    QEMUSnapshotInfo *sn = &state->sn;

    Error *local_error = NULL;

    if (!bs) {

        return;

    }

    if (bdrv_snapshot_delete(bs, sn->id_str, sn->name, &local_error) < 0) {

        error_report("Failed to delete snapshot with id '%s' and name '%s' on "

                     "device '%s' in abort: %s",

                     sn->id_str,

                     sn->name,

                     bdrv_get_device_name(bs),

                     error_get_pretty(local_error));

        error_free(local_error);

    }

}

/* external snapshot private data */

typedef struct ExternalSnapshotState {

    BlkTransactionState common;

    BlockDriverState *old_bs;

    BlockDriverState *new_bs;

} ExternalSnapshotState;

static void external_snapshot_prepare(BlkTransactionState *common,

                                      Error **errp)

{

    BlockDriver *drv;

    int flags, ret;

    Error *local_err = NULL;

    const char *device;

    const char *new_image_file;

    const char *format = "qcow2";

    enum NewImageMode mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS;

    ExternalSnapshotState *state =

                             DO_UPCAST(ExternalSnapshotState, common, common);

    TransactionAction *action = common->action;

    /* get parameters */

    g_assert(action->kind == TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC);

    device = action->blockdev_snapshot_sync->device;

    new_image_file = action->blockdev_snapshot_sync->snapshot_file;

    if (action->blockdev_snapshot_sync->has_format) {

        format = action->blockdev_snapshot_sync->format;

    }

    if (action->blockdev_snapshot_sync->has_mode) {

        mode = action->blockdev_snapshot_sync->mode;

    }

    /* start processing */

    drv = bdrv_find_format(format);

    if (!drv) {

        error_set(errp, QERR_INVALID_BLOCK_FORMAT, format);

        return;

    }

    state->old_bs = bdrv_find(device);

    if (!state->old_bs) {

        error_set(errp, QERR_DEVICE_NOT_FOUND, device);

        return;

    }

    if (!bdrv_is_inserted(state->old_bs)) {

        error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);

        return;

    }

    if (bdrv_in_use(state->old_bs)) {

        error_set(errp, QERR_DEVICE_IN_USE, device);

        return;

    }

    if (!bdrv_is_read_only(state->old_bs)) {

        if (bdrv_flush(state->old_bs)) {

            error_set(errp, QERR_IO_ERROR);

            return;

        }

    }

    flags = state->old_bs->open_flags;

    /* create new image w/backing file */

    if (mode != NEW_IMAGE_MODE_EXISTING) {

        bdrv_img_create(new_image_file, format,

                        state->old_bs->filename,

                        state->old_bs->drv->format_name,

                        NULL, -1, flags, &local_err, false);

        if (error_is_set(&local_err)) {

            error_propagate(errp, local_err);

            return;

        }

    }

    /* We will manually add the backing_hd field to the bs later */

    state->new_bs = bdrv_new("");

    /* TODO Inherit bs->options or only take explicit options with an

     * extended QMP command? */

    ret = bdrv_open(state->new_bs, new_image_file, NULL,

                    flags | BDRV_O_NO_BACKING, drv, &local_err);

    if (ret != 0) {

        error_propagate(errp, local_err);

    }

}

static void external_snapshot_commit(BlkTransactionState *common)

{

    ExternalSnapshotState *state =

                             DO_UPCAST(ExternalSnapshotState, common, common);

    /* This removes our old bs and adds the new bs */

    bdrv_append(state->new_bs, state->old_bs);

    /* We don't need (or want) to use the transactional

     * bdrv_reopen_multiple() across all the entries at once, because we

     * don't want to abort all of them if one of them fails the reopen */

    bdrv_reopen(state->new_bs, state->new_bs->open_flags & ~BDRV_O_RDWR,

                NULL);

}

static void external_snapshot_abort(BlkTransactionState *common)

{

    ExternalSnapshotState *state =

                             DO_UPCAST(ExternalSnapshotState, common, common);

    if (state->new_bs) {

        bdrv_unref(state->new_bs);

    }

}

typedef struct DriveBackupState {

    BlkTransactionState common;

    BlockDriverState *bs;

    BlockJob *job;

} DriveBackupState;

static void drive_backup_prepare(BlkTransactionState *common, Error **errp)

{

    DriveBackupState *state = DO_UPCAST(DriveBackupState, common, common);

    DriveBackup *backup;

    Error *local_err = NULL;

    assert(common->action->kind == TRANSACTION_ACTION_KIND_DRIVE_BACKUP);

    backup = common->action->drive_backup;

    qmp_drive_backup(backup->device, backup->target,

                     backup->has_format, backup->format,

                     backup->sync,

                     backup->has_mode, backup->mode,

                     backup->has_speed, backup->speed,

                     backup->has_on_source_error, backup->on_source_error,

                     backup->has_on_target_error, backup->on_target_error,

                     &local_err);

    if (error_is_set(&local_err)) {

        error_propagate(errp, local_err);

        state->bs = NULL;

        state->job = NULL;

        return;

    }

    state->bs = bdrv_find(backup->device);

    state->job = state->bs->job;

}

static void drive_backup_abort(BlkTransactionState *common)

{

    DriveBackupState *state = DO_UPCAST(DriveBackupState, common, common);

    BlockDriverState *bs = state->bs;

    /* Only cancel if it's the job we started */

    if (bs && bs->job && bs->job == state->job) {

        block_job_cancel_sync(bs->job);

    }

}

static void abort_prepare(BlkTransactionState *common, Error **errp)

{

    error_setg(errp, "Transaction aborted using Abort action");

}

static void abort_commit(BlkTransactionState *common)

{

    g_assert_not_reached(); /* this action never succeeds */

}

static const BdrvActionOps actions[] = {

    [TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC] = {

        .instance_size = sizeof(ExternalSnapshotState),

        .prepare  = external_snapshot_prepare,

        .commit   = external_snapshot_commit,

        .abort = external_snapshot_abort,

    },

    [TRANSACTION_ACTION_KIND_DRIVE_BACKUP] = {

        .instance_size = sizeof(DriveBackupState),

        .prepare = drive_backup_prepare,

        .abort = drive_backup_abort,

    },

    [TRANSACTION_ACTION_KIND_ABORT] = {

        .instance_size = sizeof(BlkTransactionState),

        .prepare = abort_prepare,

        .commit = abort_commit,

    },

    [TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_INTERNAL_SYNC] = {

        .instance_size = sizeof(InternalSnapshotState),

        .prepare  = internal_snapshot_prepare,

        .abort = internal_snapshot_abort,

    },

};

/*

 * 'Atomic' group snapshots.  The snapshots are taken as a set, and if any fail

 *  then we do not pivot any of the devices in the group, and abandon the

 *  snapshots

 */

void qmp_transaction(TransactionActionList *dev_list, Error **errp)

{

    TransactionActionList *dev_entry = dev_list;

    BlkTransactionState *state, *next;

    Error *local_err = NULL;

    QSIMPLEQ_HEAD(snap_bdrv_states, BlkTransactionState) snap_bdrv_states;

    QSIMPLEQ_INIT(&snap_bdrv_states);

    /* drain all i/o before any snapshots */

    bdrv_drain_all();

    /* We don't do anything in this loop that commits us to the snapshot */

    while (NULL != dev_entry) {

        TransactionAction *dev_info = NULL;

        const BdrvActionOps *ops;

        dev_info = dev_entry->value;

        dev_entry = dev_entry->next;

        assert(dev_info->kind < ARRAY_SIZE(actions));

        ops = &actions[dev_info->kind];

        state = g_malloc0(ops->instance_size);

        state->ops = ops;

        state->action = dev_info;

        QSIMPLEQ_INSERT_TAIL(&snap_bdrv_states, state, entry);

        state->ops->prepare(state, &local_err);

        if (error_is_set(&local_err)) {

            error_propagate(errp, local_err);

            goto delete_and_fail;

        }

    }

    QSIMPLEQ_FOREACH(state, &snap_bdrv_states, entry) {

        if (state->ops->commit) {

            state->ops->commit(state);

        }

    }

    /* success */

    goto exit;

delete_and_fail: