Archipelago » qemu

/*

 * Block driver for the VMDK format

 *

 * Copyright (c) 2004 Fabrice Bellard

 * Copyright (c) 2005 Filip Navara

 *

 * 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 "qemu-common.h"

#include "block/block_int.h"

#include "qemu/module.h"

#include "migration/migration.h"

#include <zlib.h>

#define VMDK3_MAGIC (('C' << 24) | ('O' << 16) | ('W' << 8) | 'D')

#define VMDK4_MAGIC (('K' << 24) | ('D' << 16) | ('M' << 8) | 'V')

#define VMDK4_COMPRESSION_DEFLATE 1

#define VMDK4_FLAG_NL_DETECT (1 << 0)

#define VMDK4_FLAG_RGD (1 << 1)

/* Zeroed-grain enable bit */

#define VMDK4_FLAG_ZERO_GRAIN   (1 << 2)

#define VMDK4_FLAG_COMPRESS (1 << 16)

#define VMDK4_FLAG_MARKER (1 << 17)

#define VMDK4_GD_AT_END 0xffffffffffffffffULL

#define VMDK_GTE_ZEROED 0x1

/* VMDK internal error codes */

#define VMDK_OK      0

#define VMDK_ERROR   (-1)

/* Cluster not allocated */

#define VMDK_UNALLOC (-2)

#define VMDK_ZEROED  (-3)

#define BLOCK_OPT_ZEROED_GRAIN "zeroed_grain"

typedef struct {

    uint32_t version;

    uint32_t flags;

    uint32_t disk_sectors;

    uint32_t granularity;

    uint32_t l1dir_offset;

    uint32_t l1dir_size;

    uint32_t file_sectors;

    uint32_t cylinders;

    uint32_t heads;

    uint32_t sectors_per_track;

} QEMU_PACKED VMDK3Header;

typedef struct {

    uint32_t version;

    uint32_t flags;

    uint64_t capacity;

    uint64_t granularity;

    uint64_t desc_offset;

    uint64_t desc_size;

    /* Number of GrainTableEntries per GrainTable */

    uint32_t num_gtes_per_gt;

    uint64_t rgd_offset;

    uint64_t gd_offset;

    uint64_t grain_offset;

    char filler[1];

    char check_bytes[4];

    uint16_t compressAlgorithm;

} QEMU_PACKED VMDK4Header;

#define L2_CACHE_SIZE 16

typedef struct VmdkExtent {

    BlockDriverState *file;

    bool flat;

    bool compressed;

    bool has_marker;

    bool has_zero_grain;

    int version;

    int64_t sectors;

    int64_t end_sector;

    int64_t flat_start_offset;

    int64_t l1_table_offset;

    int64_t l1_backup_table_offset;

    uint32_t *l1_table;

    uint32_t *l1_backup_table;

    unsigned int l1_size;

    uint32_t l1_entry_sectors;

    unsigned int l2_size;

    uint32_t *l2_cache;

    uint32_t l2_cache_offsets[L2_CACHE_SIZE];

    uint32_t l2_cache_counts[L2_CACHE_SIZE];

    int64_t cluster_sectors;

    char *type;

} VmdkExtent;

typedef struct BDRVVmdkState {

    CoMutex lock;

    uint64_t desc_offset;

    bool cid_updated;

    bool cid_checked;

    uint32_t cid;

    uint32_t parent_cid;

    int num_extents;

    /* Extent array with num_extents entries, ascend ordered by address */

    VmdkExtent *extents;

    Error *migration_blocker;

    char *create_type;

} BDRVVmdkState;

typedef struct VmdkMetaData {

    uint32_t offset;

    unsigned int l1_index;

    unsigned int l2_index;

    unsigned int l2_offset;

    int valid;

    uint32_t *l2_cache_entry;

} VmdkMetaData;

typedef struct VmdkGrainMarker {

    uint64_t lba;

    uint32_t size;

    uint8_t  data[0];

} QEMU_PACKED VmdkGrainMarker;

enum {

    MARKER_END_OF_STREAM    = 0,

    MARKER_GRAIN_TABLE      = 1,

    MARKER_GRAIN_DIRECTORY  = 2,

    MARKER_FOOTER           = 3,

};

static int vmdk_probe(const uint8_t *buf, int buf_size, const char *filename)

{

    uint32_t magic;

    if (buf_size < 4) {

        return 0;

    }

    magic = be32_to_cpu(*(uint32_t *)buf);

    if (magic == VMDK3_MAGIC ||

        magic == VMDK4_MAGIC) {

        return 100;

    } else {

        const char *p = (const char *)buf;

        const char *end = p + buf_size;

        while (p < end) {

            if (*p == '#') {

                /* skip comment line */

                while (p < end && *p != '\n') {

                    p++;

                }

                p++;

                continue;

            }

            if (*p == ' ') {

                while (p < end && *p == ' ') {

                    p++;

                }

                /* skip '\r' if windows line endings used. */

                if (p < end && *p == '\r') {

                    p++;

                }

                /* only accept blank lines before 'version=' line */

                if (p == end || *p != '\n') {

                    return 0;

                }

                p++;

                continue;

            }

            if (end - p >= strlen("version=X\n")) {

                if (strncmp("version=1\n", p, strlen("version=1\n")) == 0 ||

                    strncmp("version=2\n", p, strlen("version=2\n")) == 0) {

                    return 100;

                }

            }

            if (end - p >= strlen("version=X\r\n")) {

                if (strncmp("version=1\r\n", p, strlen("version=1\r\n")) == 0 ||

                    strncmp("version=2\r\n", p, strlen("version=2\r\n")) == 0) {

                    return 100;

                }

            }

            return 0;

        }

        return 0;

    }

}

#define SECTOR_SIZE 512

#define DESC_SIZE (20 * SECTOR_SIZE)    /* 20 sectors of 512 bytes each */

#define BUF_SIZE 4096

#define HEADER_SIZE 512                 /* first sector of 512 bytes */

static void vmdk_free_extents(BlockDriverState *bs)

{

    int i;

    BDRVVmdkState *s = bs->opaque;

    VmdkExtent *e;

    for (i = 0; i < s->num_extents; i++) {

        e = &s->extents[i];

        g_free(e->l1_table);

        g_free(e->l2_cache);

        g_free(e->l1_backup_table);

        g_free(e->type);

        if (e->file != bs->file) {

            bdrv_unref(e->file);

        }

    }

    g_free(s->extents);

}

static void vmdk_free_last_extent(BlockDriverState *bs)

{

    BDRVVmdkState *s = bs->opaque;

    if (s->num_extents == 0) {

        return;

    }

    s->num_extents--;

    s->extents = g_realloc(s->extents, s->num_extents * sizeof(VmdkExtent));

}

static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent)

{

    char desc[DESC_SIZE];

    uint32_t cid = 0xffffffff;

    const char *p_name, *cid_str;

    size_t cid_str_size;

    BDRVVmdkState *s = bs->opaque;

    int ret;

    ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE);

    if (ret < 0) {

        return 0;

    }

    if (parent) {

        cid_str = "parentCID";

        cid_str_size = sizeof("parentCID");

    } else {

        cid_str = "CID";

        cid_str_size = sizeof("CID");

    }

    desc[DESC_SIZE - 1] = '\0';

    p_name = strstr(desc, cid_str);

    if (p_name != NULL) {

        p_name += cid_str_size;

        sscanf(p_name, "%x", &cid);

    }

    return cid;

}

static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid)

{

    char desc[DESC_SIZE], tmp_desc[DESC_SIZE];

    char *p_name, *tmp_str;

    BDRVVmdkState *s = bs->opaque;

    int ret;

    ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE);

    if (ret < 0) {

        return ret;

    }

    desc[DESC_SIZE - 1] = '\0';

    tmp_str = strstr(desc, "parentCID");

    if (tmp_str == NULL) {

        return -EINVAL;

    }

    pstrcpy(tmp_desc, sizeof(tmp_desc), tmp_str);

    p_name = strstr(desc, "CID");

    if (p_name != NULL) {

        p_name += sizeof("CID");

        snprintf(p_name, sizeof(desc) - (p_name - desc), "%x\n", cid);

        pstrcat(desc, sizeof(desc), tmp_desc);

    }

    ret = bdrv_pwrite_sync(bs->file, s->desc_offset, desc, DESC_SIZE);

    if (ret < 0) {

        return ret;

    }

    return 0;

}

static int vmdk_is_cid_valid(BlockDriverState *bs)

{

    BDRVVmdkState *s = bs->opaque;

    BlockDriverState *p_bs = bs->backing_hd;

    uint32_t cur_pcid;

    if (!s->cid_checked && p_bs) {

        cur_pcid = vmdk_read_cid(p_bs, 0);

        if (s->parent_cid != cur_pcid) {

            /* CID not valid */

            return 0;

        }

    }

    s->cid_checked = true;

    /* CID valid */

    return 1;

}

/* Queue extents, if any, for reopen() */

static int vmdk_reopen_prepare(BDRVReopenState *state,

                               BlockReopenQueue *queue, Error **errp)

{

    BDRVVmdkState *s;

    int ret = -1;

    int i;

    VmdkExtent *e;

    assert(state != NULL);

    assert(state->bs != NULL);

    if (queue == NULL) {

        error_setg(errp, "No reopen queue for VMDK extents");

        goto exit;

    }

    s = state->bs->opaque;

    assert(s != NULL);

    for (i = 0; i < s->num_extents; i++) {

        e = &s->extents[i];

        if (e->file != state->bs->file) {

            bdrv_reopen_queue(queue, e->file, state->flags);

        }

    }

    ret = 0;

exit:

    return ret;

}

static int vmdk_parent_open(BlockDriverState *bs)

{

    char *p_name;

    char desc[DESC_SIZE + 1];

    BDRVVmdkState *s = bs->opaque;

    int ret;

    desc[DESC_SIZE] = '\0';

    ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE);

    if (ret < 0) {

        return ret;

    }

    p_name = strstr(desc, "parentFileNameHint");

    if (p_name != NULL) {

        char *end_name;

        p_name += sizeof("parentFileNameHint") + 1;

        end_name = strchr(p_name, '\"');

        if (end_name == NULL) {

            return -EINVAL;

        }

        if ((end_name - p_name) > sizeof(bs->backing_file) - 1) {

            return -EINVAL;

        }

        pstrcpy(bs->backing_file, end_name - p_name + 1, p_name);

    }

    return 0;

}

/* Create and append extent to the extent array. Return the added VmdkExtent

 * address. return NULL if allocation failed. */

static int vmdk_add_extent(BlockDriverState *bs,

                           BlockDriverState *file, bool flat, int64_t sectors,

                           int64_t l1_offset, int64_t l1_backup_offset,

                           uint32_t l1_size,

                           int l2_size, uint64_t cluster_sectors,

                           VmdkExtent **new_extent,

                           Error **errp)

{

    VmdkExtent *extent;

    BDRVVmdkState *s = bs->opaque;

    if (cluster_sectors > 0x200000) {

        /* 0x200000 * 512Bytes = 1GB for one cluster is unrealistic */

        error_setg(errp, "Invalid granularity, image may be corrupt");

        return -EFBIG;

    }

    if (l1_size > 512 * 1024 * 1024) {

        /* Although with big capacity and small l1_entry_sectors, we can get a

         * big l1_size, we don't want unbounded value to allocate the table.

         * Limit it to 512M, which is 16PB for default cluster and L2 table

         * size */

        error_setg(errp, "L1 size too big");

        return -EFBIG;

    }

    s->extents = g_realloc(s->extents,

                              (s->num_extents + 1) * sizeof(VmdkExtent));

    extent = &s->extents[s->num_extents];

    s->num_extents++;

    memset(extent, 0, sizeof(VmdkExtent));

    extent->file = file;

    extent->flat = flat;

    extent->sectors = sectors;

    extent->l1_table_offset = l1_offset;

    extent->l1_backup_table_offset = l1_backup_offset;

    extent->l1_size = l1_size;

    extent->l1_entry_sectors = l2_size * cluster_sectors;

    extent->l2_size = l2_size;

    extent->cluster_sectors = flat ? sectors : cluster_sectors;

    if (s->num_extents > 1) {

        extent->end_sector = (*(extent - 1)).end_sector + extent->sectors;

    } else {

        extent->end_sector = extent->sectors;

    }

    bs->total_sectors = extent->end_sector;

    if (new_extent) {

        *new_extent = extent;

    }

    return 0;

}

static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,

                            Error **errp)

{

    int ret;

    int l1_size, i;

    /* read the L1 table */

    l1_size = extent->l1_size * sizeof(uint32_t);

    extent->l1_table = g_malloc(l1_size);

    ret = bdrv_pread(extent->file,

                     extent->l1_table_offset,

                     extent->l1_table,

                     l1_size);

    if (ret < 0) {

        error_setg_errno(errp, -ret,

                         "Could not read l1 table from extent '%s'",

                         extent->file->filename);

        goto fail_l1;

    }

    for (i = 0; i < extent->l1_size; i++) {

        le32_to_cpus(&extent->l1_table[i]);

    }

    if (extent->l1_backup_table_offset) {

        extent->l1_backup_table = g_malloc(l1_size);

        ret = bdrv_pread(extent->file,

                         extent->l1_backup_table_offset,

                         extent->l1_backup_table,

                         l1_size);

        if (ret < 0) {

            error_setg_errno(errp, -ret,

                             "Could not read l1 backup table from extent '%s'",

                             extent->file->filename);

            goto fail_l1b;

        }

        for (i = 0; i < extent->l1_size; i++) {

            le32_to_cpus(&extent->l1_backup_table[i]);

        }

    }

    extent->l2_cache =

        g_malloc(extent->l2_size * L2_CACHE_SIZE * sizeof(uint32_t));

    return 0;

 fail_l1b:

    g_free(extent->l1_backup_table);

 fail_l1:

    g_free(extent->l1_table);

    return ret;

}

static int vmdk_open_vmfs_sparse(BlockDriverState *bs,

                                 BlockDriverState *file,

                                 int flags, Error **errp)

{

    int ret;

    uint32_t magic;

    VMDK3Header header;

    VmdkExtent *extent;

    ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header));

    if (ret < 0) {

        error_setg_errno(errp, -ret,

                         "Could not read header from file '%s'",

                         file->filename);

        return ret;

    }

    ret = vmdk_add_extent(bs, file, false,

                          le32_to_cpu(header.disk_sectors),

                          le32_to_cpu(header.l1dir_offset) << 9,

                          0,

                          le32_to_cpu(header.l1dir_size),

                          4096,

                          le32_to_cpu(header.granularity),

                          &extent,

                          errp);

    if (ret < 0) {

        return ret;

    }

    ret = vmdk_init_tables(bs, extent, errp);

    if (ret) {

        /* free extent allocated by vmdk_add_extent */

        vmdk_free_last_extent(bs);

    }

    return ret;

}

static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,

                               Error **errp);

static char *vmdk_read_desc(BlockDriverState *file, uint64_t desc_offset,

                            Error **errp)

{

    int64_t size;

    char *buf;

    int ret;

    size = bdrv_getlength(file);

    if (size < 0) {

        error_setg_errno(errp, -size, "Could not access file");

        return NULL;

    }

    size = MIN(size, 1 << 20);  /* avoid unbounded allocation */

    buf = g_malloc0(size + 1);

    ret = bdrv_pread(file, desc_offset, buf, size);

    if (ret < 0) {

        error_setg_errno(errp, -ret, "Could not read from file");

        g_free(buf);

        return NULL;

    }

    return buf;

}

static int vmdk_open_vmdk4(BlockDriverState *bs,

                           BlockDriverState *file,

                           int flags, Error **errp)

{

    int ret;

    uint32_t magic;

    uint32_t l1_size, l1_entry_sectors;

    VMDK4Header header;

    VmdkExtent *extent;

    BDRVVmdkState *s = bs->opaque;

    int64_t l1_backup_offset = 0;

    ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header));

    if (ret < 0) {

        error_setg_errno(errp, -ret,

                         "Could not read header from file '%s'",

                         file->filename);

        return -EINVAL;

    }

    if (header.capacity == 0) {

        uint64_t desc_offset = le64_to_cpu(header.desc_offset);

        if (desc_offset) {

            char *buf = vmdk_read_desc(file, desc_offset << 9, errp);

            if (!buf) {

                return -EINVAL;

            }

            ret = vmdk_open_desc_file(bs, flags, buf, errp);

            g_free(buf);

            return ret;

        }

    }

    if (!s->create_type) {

        s->create_type = g_strdup("monolithicSparse");

    }

    if (le64_to_cpu(header.gd_offset) == VMDK4_GD_AT_END) {

        /*

         * The footer takes precedence over the header, so read it in. The

         * footer starts at offset -1024 from the end: One sector for the

         * footer, and another one for the end-of-stream marker.

         */

        struct {

            struct {

                uint64_t val;

                uint32_t size;

                uint32_t type;

                uint8_t pad[512 - 16];

            } QEMU_PACKED footer_marker;

            uint32_t magic;

            VMDK4Header header;

            uint8_t pad[512 - 4 - sizeof(VMDK4Header)];

            struct {

                uint64_t val;

                uint32_t size;

                uint32_t type;

                uint8_t pad[512 - 16];

            } QEMU_PACKED eos_marker;

        } QEMU_PACKED footer;

        ret = bdrv_pread(file,

            bs->file->total_sectors * 512 - 1536,

            &footer, sizeof(footer));

        if (ret < 0) {

            return ret;

        }

        /* Some sanity checks for the footer */

        if (be32_to_cpu(footer.magic) != VMDK4_MAGIC ||

            le32_to_cpu(footer.footer_marker.size) != 0  ||

            le32_to_cpu(footer.footer_marker.type) != MARKER_FOOTER ||

            le64_to_cpu(footer.eos_marker.val) != 0  ||

            le32_to_cpu(footer.eos_marker.size) != 0  ||

            le32_to_cpu(footer.eos_marker.type) != MARKER_END_OF_STREAM)

        {

            return -EINVAL;

        }

        header = footer.header;

    }

    if (le32_to_cpu(header.version) > 3) {

        char buf[64];

        snprintf(buf, sizeof(buf), "VMDK version %d",

                 le32_to_cpu(header.version));

        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,

                  bs->device_name, "vmdk", buf);

        return -ENOTSUP;

    } else if (le32_to_cpu(header.version) == 3 && (flags & BDRV_O_RDWR)) {

        /* VMware KB 2064959 explains that version 3 added support for

         * persistent changed block tracking (CBT), and backup software can

         * read it as version=1 if it doesn't care about the changed area

         * information. So we are safe to enable read only. */

        error_setg(errp, "VMDK version 3 must be read only");

        return -EINVAL;

    }

    if (le32_to_cpu(header.num_gtes_per_gt) > 512) {

        error_setg(errp, "L2 table size too big");

        return -EINVAL;

    }

    l1_entry_sectors = le32_to_cpu(header.num_gtes_per_gt)

                        * le64_to_cpu(header.granularity);

    if (l1_entry_sectors == 0) {

        return -EINVAL;

    }

    l1_size = (le64_to_cpu(header.capacity) + l1_entry_sectors - 1)

                / l1_entry_sectors;

    if (le32_to_cpu(header.flags) & VMDK4_FLAG_RGD) {

        l1_backup_offset = le64_to_cpu(header.rgd_offset) << 9;

    }

    if (bdrv_getlength(file) <

            le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE) {

        error_setg(errp, "File truncated, expecting at least %lld bytes",

                   le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE);

        return -EINVAL;

    }

    ret = vmdk_add_extent(bs, file, false,

                          le64_to_cpu(header.capacity),

                          le64_to_cpu(header.gd_offset) << 9,

                          l1_backup_offset,

                          l1_size,

                          le32_to_cpu(header.num_gtes_per_gt),

                          le64_to_cpu(header.granularity),

                          &extent,

                          errp);

    if (ret < 0) {

        return ret;

    }

    extent->compressed =

        le16_to_cpu(header.compressAlgorithm) == VMDK4_COMPRESSION_DEFLATE;

    if (extent->compressed) {

        g_free(s->create_type);

        s->create_type = g_strdup("streamOptimized");

    }

    extent->has_marker = le32_to_cpu(header.flags) & VMDK4_FLAG_MARKER;

    extent->version = le32_to_cpu(header.version);

    extent->has_zero_grain = le32_to_cpu(header.flags) & VMDK4_FLAG_ZERO_GRAIN;

    ret = vmdk_init_tables(bs, extent, errp);

    if (ret) {

        /* free extent allocated by vmdk_add_extent */

        vmdk_free_last_extent(bs);

    }

    return ret;

}

/* find an option value out of descriptor file */

static int vmdk_parse_description(const char *desc, const char *opt_name,

        char *buf, int buf_size)

{

    char *opt_pos, *opt_end;

    const char *end = desc + strlen(desc);

    opt_pos = strstr(desc, opt_name);

    if (!opt_pos) {

        return VMDK_ERROR;

    }

    /* Skip "=\"" following opt_name */

    opt_pos += strlen(opt_name) + 2;

    if (opt_pos >= end) {

        return VMDK_ERROR;

    }

    opt_end = opt_pos;

    while (opt_end < end && *opt_end != '"') {

        opt_end++;

    }

    if (opt_end == end || buf_size < opt_end - opt_pos + 1) {

        return VMDK_ERROR;

    }

    pstrcpy(buf, opt_end - opt_pos + 1, opt_pos);

    return VMDK_OK;

}

/* Open an extent file and append to bs array */

static int vmdk_open_sparse(BlockDriverState *bs,

                            BlockDriverState *file, int flags,

                            char *buf, Error **errp)

{

    uint32_t magic;

    magic = ldl_be_p(buf);

    switch (magic) {

        case VMDK3_MAGIC:

            return vmdk_open_vmfs_sparse(bs, file, flags, errp);

            break;

        case VMDK4_MAGIC:

            return vmdk_open_vmdk4(bs, file, flags, errp);

            break;

        default:

            error_setg(errp, "Image not in VMDK format");

            return -EINVAL;

            break;

    }

}

static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,

                              const char *desc_file_path, Error **errp)

{

    int ret;

    char access[11];

    char type[11];

    char fname[512];

    const char *p = desc;

    int64_t sectors = 0;

    int64_t flat_offset;

    char extent_path[PATH_MAX];

    BlockDriverState *extent_file;

    BDRVVmdkState *s = bs->opaque;

    VmdkExtent *extent;

    while (*p) {

        /* parse extent line:

         * RW [size in sectors] FLAT "file-name.vmdk" OFFSET

         * or

         * RW [size in sectors] SPARSE "file-name.vmdk"

         */

        flat_offset = -1;

        ret = sscanf(p, "%10s %" SCNd64 " %10s \"%511[^\n\r\"]\" %" SCNd64,

                access, &sectors, type, fname, &flat_offset);

        if (ret < 4 || strcmp(access, "RW")) {

            goto next_line;

        } else if (!strcmp(type, "FLAT")) {

            if (ret != 5 || flat_offset < 0) {

                error_setg(errp, "Invalid extent lines: \n%s", p);

                return -EINVAL;

            }

        } else if (!strcmp(type, "VMFS")) {

            if (ret == 4) {

                flat_offset = 0;

            } else {

                error_setg(errp, "Invalid extent lines:\n%s", p);

                return -EINVAL;

            }

        } else if (ret != 4) {

            error_setg(errp, "Invalid extent lines:\n%s", p);

            return -EINVAL;

        }

        if (sectors <= 0 ||

            (strcmp(type, "FLAT") && strcmp(type, "SPARSE") &&

             strcmp(type, "VMFS") && strcmp(type, "VMFSSPARSE")) ||

            (strcmp(access, "RW"))) {

            goto next_line;

        }

        path_combine(extent_path, sizeof(extent_path),

                desc_file_path, fname);

        extent_file = NULL;

        ret = bdrv_open(&extent_file, extent_path, NULL, NULL,

                        bs->open_flags | BDRV_O_PROTOCOL, NULL, errp);

        if (ret) {

            return ret;

        }

        /* save to extents array */

        if (!strcmp(type, "FLAT") || !strcmp(type, "VMFS")) {

            /* FLAT extent */

            ret = vmdk_add_extent(bs, extent_file, true, sectors,

                            0, 0, 0, 0, 0, &extent, errp);

            if (ret < 0) {

                return ret;

            }

            extent->flat_start_offset = flat_offset << 9;

        } else if (!strcmp(type, "SPARSE") || !strcmp(type, "VMFSSPARSE")) {

            /* SPARSE extent and VMFSSPARSE extent are both "COWD" sparse file*/

            char *buf = vmdk_read_desc(extent_file, 0, errp);

            if (!buf) {

                ret = -EINVAL;

            } else {

                ret = vmdk_open_sparse(bs, extent_file, bs->open_flags, buf, errp);

            }

            if (ret) {

                g_free(buf);

                bdrv_unref(extent_file);

                return ret;

            }

            extent = &s->extents[s->num_extents - 1];

        } else {

            error_setg(errp, "Unsupported extent type '%s'", type);

            return -ENOTSUP;

        }

        extent->type = g_strdup(type);

next_line:

        /* move to next line */

        while (*p) {

            if (*p == '\n') {

                p++;

                break;

            }

            p++;

        }

    }

    return 0;

}

static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,

                               Error **errp)

{

    int ret;

    char ct[128];

    BDRVVmdkState *s = bs->opaque;

    if (vmdk_parse_description(buf, "createType", ct, sizeof(ct))) {

        error_setg(errp, "invalid VMDK image descriptor");

        ret = -EINVAL;

        goto exit;

    }

    if (strcmp(ct, "monolithicFlat") &&

        strcmp(ct, "vmfs") &&

        strcmp(ct, "vmfsSparse") &&

        strcmp(ct, "twoGbMaxExtentSparse") &&

        strcmp(ct, "twoGbMaxExtentFlat")) {

        error_setg(errp, "Unsupported image type '%s'", ct);

        ret = -ENOTSUP;

        goto exit;