block-vmdk.c.svn-base

我们自己开发的一个OSEK操作系统！不知道可不可以？

            s->is_parent = 0;

        // try to open parent images, if exist
        if (vmdk_parent_open(bs, filename) != 0)
            goto fail;
        // write the CID once after the image creation
        s->parent_cid = vmdk_read_cid(bs,1);
    } else {
        goto fail;
    }

    /* read the L1 table */
    l1_size = s->l1_size * sizeof(uint32_t);
    s->l1_table = qemu_malloc(l1_size);
    if (!s->l1_table)
        goto fail;
    if (bdrv_pread(s->hd, s->l1_table_offset, s->l1_table, l1_size) != l1_size)
        goto fail;
    for(i = 0; i < s->l1_size; i++) {
        le32_to_cpus(&s->l1_table[i]);
    }

    if (s->l1_backup_table_offset) {
        s->l1_backup_table = qemu_malloc(l1_size);
        if (!s->l1_backup_table)
            goto fail;
        if (bdrv_pread(s->hd, s->l1_backup_table_offset, s->l1_backup_table, l1_size) != l1_size)
            goto fail;
        for(i = 0; i < s->l1_size; i++) {
            le32_to_cpus(&s->l1_backup_table[i]);
        }
    }

    s->l2_cache = qemu_malloc(s->l2_size * L2_CACHE_SIZE * sizeof(uint32_t));
    if (!s->l2_cache)
        goto fail;
    return 0;
 fail:
    qemu_free(s->l1_backup_table);
    qemu_free(s->l1_table);
    qemu_free(s->l2_cache);
    bdrv_delete(s->hd);
    return -1;
}

static uint64_t get_cluster_offset(BlockDriverState *bs, VmdkMetaData *m_data,
                                   uint64_t offset, int allocate);

static int get_whole_cluster(BlockDriverState *bs, uint64_t cluster_offset,
                             uint64_t offset, int allocate)
{
    uint64_t parent_cluster_offset;
    BDRVVmdkState *s = bs->opaque;
    uint8_t  whole_grain[s->cluster_sectors*512];        // 128 sectors * 512 bytes each = grain size 64KB

    // we will be here if it's first write on non-exist grain(cluster).
    // try to read from parent image, if exist
    if (s->hd->backing_hd) {
        BDRVVmdkState *ps = s->hd->backing_hd->opaque;

        if (!vmdk_is_cid_valid(bs))
            return -1;

        parent_cluster_offset = get_cluster_offset(s->hd->backing_hd, NULL, offset, allocate);

        if (parent_cluster_offset) {
            BDRVVmdkState *act_s = activeBDRV.hd->opaque;

            if (bdrv_pread(ps->hd, parent_cluster_offset, whole_grain, ps->cluster_sectors*512) != ps->cluster_sectors*512)
                return -1;

            //Write grain only into the active image
            if (bdrv_pwrite(act_s->hd, activeBDRV.cluster_offset << 9, whole_grain, sizeof(whole_grain)) != sizeof(whole_grain))
                return -1;
        }
    }
    return 0;
}

static int vmdk_L2update(BlockDriverState *bs, VmdkMetaData *m_data)
{
    BDRVVmdkState *s = bs->opaque;

    /* update L2 table */
    if (bdrv_pwrite(s->hd, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(m_data->offset)),
                    &(m_data->offset), sizeof(m_data->offset)) != sizeof(m_data->offset))
        return -1;
    /* update backup L2 table */
    if (s->l1_backup_table_offset != 0) {
        m_data->l2_offset = s->l1_backup_table[m_data->l1_index];
        if (bdrv_pwrite(s->hd, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(m_data->offset)),
                        &(m_data->offset), sizeof(m_data->offset)) != sizeof(m_data->offset))
            return -1;
    }

    return 0;
}

static uint64_t get_cluster_offset(BlockDriverState *bs, VmdkMetaData *m_data,
                                   uint64_t offset, int allocate)
{
    BDRVVmdkState *s = bs->opaque;
    unsigned int l1_index, l2_offset, l2_index;
    int min_index, i, j;
    uint32_t min_count, *l2_table, tmp = 0;
    uint64_t cluster_offset;

    if (m_data)
        m_data->valid = 0;

    l1_index = (offset >> 9) / s->l1_entry_sectors;
    if (l1_index >= s->l1_size)
        return 0;
    l2_offset = s->l1_table[l1_index];
    if (!l2_offset)
        return 0;
    for(i = 0; i < L2_CACHE_SIZE; i++) {
        if (l2_offset == s->l2_cache_offsets[i]) {
            /* increment the hit count */
            if (++s->l2_cache_counts[i] == 0xffffffff) {
                for(j = 0; j < L2_CACHE_SIZE; j++) {
                    s->l2_cache_counts[j] >>= 1;
                }
            }
            l2_table = s->l2_cache + (i * s->l2_size);
            goto found;
        }
    }
    /* not found: load a new entry in the least used one */
    min_index = 0;
    min_count = 0xffffffff;
    for(i = 0; i < L2_CACHE_SIZE; i++) {
        if (s->l2_cache_counts[i] < min_count) {
            min_count = s->l2_cache_counts[i];
            min_index = i;
        }
    }
    l2_table = s->l2_cache + (min_index * s->l2_size);
    if (bdrv_pread(s->hd, (int64_t)l2_offset * 512, l2_table, s->l2_size * sizeof(uint32_t)) !=
                                                                        s->l2_size * sizeof(uint32_t))
        return 0;

    s->l2_cache_offsets[min_index] = l2_offset;
    s->l2_cache_counts[min_index] = 1;
 found:
    l2_index = ((offset >> 9) / s->cluster_sectors) % s->l2_size;
    cluster_offset = le32_to_cpu(l2_table[l2_index]);

    if (!cluster_offset) {
        if (!allocate)
            return 0;
        // Avoid the L2 tables update for the images that have snapshots.
        if (!s->is_parent) {
            cluster_offset = bdrv_getlength(s->hd);
            bdrv_truncate(s->hd, cluster_offset + (s->cluster_sectors << 9));

            cluster_offset >>= 9;
            tmp = cpu_to_le32(cluster_offset);
            l2_table[l2_index] = tmp;
            // Save the active image state
            activeBDRV.cluster_offset = cluster_offset;
            activeBDRV.hd = bs;
        }
        /* First of all we write grain itself, to avoid race condition
         * that may to corrupt the image.
         * This problem may occur because of insufficient space on host disk
         * or inappropriate VM shutdown.
         */
        if (get_whole_cluster(bs, cluster_offset, offset, allocate) == -1)
            return 0;

        if (m_data) {
            m_data->offset = tmp;
            m_data->l1_index = l1_index;
            m_data->l2_index = l2_index;
            m_data->l2_offset = l2_offset;
            m_data->valid = 1;
        }
    }
    cluster_offset <<= 9;
    return cluster_offset;
}

static int vmdk_is_allocated(BlockDriverState *bs, int64_t sector_num,
                             int nb_sectors, int *pnum)
{
    BDRVVmdkState *s = bs->opaque;
    int index_in_cluster, n;
    uint64_t cluster_offset;

    cluster_offset = get_cluster_offset(bs, NULL, sector_num << 9, 0);
    index_in_cluster = sector_num % s->cluster_sectors;
    n = s->cluster_sectors - index_in_cluster;
    if (n > nb_sectors)
        n = nb_sectors;
    *pnum = n;
    return (cluster_offset != 0);
}

static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
                    uint8_t *buf, int nb_sectors)
{
    BDRVVmdkState *s = bs->opaque;
    int index_in_cluster, n, ret;
    uint64_t cluster_offset;

    while (nb_sectors > 0) {
        cluster_offset = get_cluster_offset(bs, NULL, sector_num << 9, 0);
        index_in_cluster = sector_num % s->cluster_sectors;
        n = s->cluster_sectors - index_in_cluster;
        if (n > nb_sectors)
            n = nb_sectors;
        if (!cluster_offset) {
            // try to read from parent image, if exist
            if (s->hd->backing_hd) {
                if (!vmdk_is_cid_valid(bs))
                    return -1;
                ret = bdrv_read(s->hd->backing_hd, sector_num, buf, n);
                if (ret < 0)
                    return -1;
            } else {
                memset(buf, 0, 512 * n);
            }
        } else {
            if(bdrv_pread(s->hd, cluster_offset + index_in_cluster * 512, buf, n * 512) != n * 512)
                return -1;
        }
        nb_sectors -= n;
        sector_num += n;
        buf += n * 512;
    }
    return 0;
}

static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
                     const uint8_t *buf, int nb_sectors)
{
    BDRVVmdkState *s = bs->opaque;
    VmdkMetaData m_data;
    int index_in_cluster, n;
    uint64_t cluster_offset;
    static int cid_update = 0;

    if (sector_num > bs->total_sectors) {
        fprintf(stderr,
                "(VMDK) Wrong offset: sector_num=0x%" PRIx64
                " total_sectors=0x%" PRIx64 "\n",
                sector_num, bs->total_sectors);
        return -1;
    }

    while (nb_sectors > 0) {
        index_in_cluster = sector_num & (s->cluster_sectors - 1);
        n = s->cluster_sectors - index_in_cluster;
        if (n > nb_sectors)
            n = nb_sectors;
        cluster_offset = get_cluster_offset(bs, &m_data, sector_num << 9, 1);
        if (!cluster_offset)
            return -1;

        if (bdrv_pwrite(s->hd, cluster_offset + index_in_cluster * 512, buf, n * 512) != n * 512)
            return -1;
        if (m_data.valid) {
            /* update L2 tables */
            if (vmdk_L2update(bs, &m_data) == -1)
                return -1;
        }
        nb_sectors -= n;
        sector_num += n;
        buf += n * 512;

        // update CID on the first write every time the virtual disk is opened
        if (!cid_update) {
            vmdk_write_cid(bs, time(NULL));
            cid_update++;
        }
    }
    return 0;
}

static int vmdk_create(const char *filename, int64_t total_size,
                       const char *backing_file, int flags)
{
    int fd, i;
    VMDK4Header header;
    uint32_t tmp, magic, grains, gd_size, gt_size, gt_count;
    char *desc_template =
        "# Disk DescriptorFile\n"
        "version=1\n"
        "CID=%x\n"
        "parentCID=ffffffff\n"
        "createType=\"monolithicSparse\"\n"
        "\n"
        "# Extent description\n"
        "RW %lu SPARSE \"%s\"\n"
        "\n"
        "# The Disk Data Base \n"
        "#DDB\n"
        "\n"
        "ddb.virtualHWVersion = \"%d\"\n"
        "ddb.geometry.cylinders = \"%lu\"\n"
        "ddb.geometry.heads = \"16\"\n"
        "ddb.geometry.sectors = \"63\"\n"
        "ddb.adapterType = \"ide\"\n";
    char desc[1024];
    const char *real_filename, *temp_str;

    /* XXX: add support for backing file */
    if (backing_file) {
        return vmdk_snapshot_create(filename, backing_file);
    }

    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
              0644);
    if (fd < 0)
        return -1;
    magic = cpu_to_be32(VMDK4_MAGIC);
    memset(&header, 0, sizeof(header));
    header.version = cpu_to_le32(1);
    header.flags = cpu_to_le32(3); /* ?? */
    header.capacity = cpu_to_le64(total_size);
    header.granularity = cpu_to_le64(128);
    header.num_gtes_per_gte = cpu_to_le32(512);

    grains = (total_size + header.granularity - 1) / header.granularity;
    gt_size = ((header.num_gtes_per_gte * sizeof(uint32_t)) + 511) >> 9;
    gt_count = (grains + header.num_gtes_per_gte - 1) / header.num_gtes_per_gte;
    gd_size = (gt_count * sizeof(uint32_t) + 511) >> 9;

    header.desc_offset = 1;
    header.desc_size = 20;
    header.rgd_offset = header.desc_offset + header.desc_size;
    header.gd_offset = header.rgd_offset + gd_size + (gt_size * gt_count);
    header.grain_offset =
       ((header.gd_offset + gd_size + (gt_size * gt_count) +
         header.granularity - 1) / header.granularity) *
        header.granularity;

    header.desc_offset = cpu_to_le64(header.desc_offset);
    header.desc_size = cpu_to_le64(header.desc_size);
    header.rgd_offset = cpu_to_le64(header.rgd_offset);
    header.gd_offset = cpu_to_le64(header.gd_offset);
    header.grain_offset = cpu_to_le64(header.grain_offset);

    header.check_bytes[0] = 0xa;
    header.check_bytes[1] = 0x20;
    header.check_bytes[2] = 0xd;
    header.check_bytes[3] = 0xa;

    /* write all the data */
    write(fd, &magic, sizeof(magic));
    write(fd, &header, sizeof(header));

    ftruncate(fd, header.grain_offset << 9);

    /* write grain directory */
    lseek(fd, le64_to_cpu(header.rgd_offset) << 9, SEEK_SET);
    for (i = 0, tmp = header.rgd_offset + gd_size;
         i < gt_count; i++, tmp += gt_size)
        write(fd, &tmp, sizeof(tmp));

    /* write backup grain directory */
    lseek(fd, le64_to_cpu(header.gd_offset) << 9, SEEK_SET);
    for (i = 0, tmp = header.gd_offset + gd_size;
         i < gt_count; i++, tmp += gt_size)
        write(fd, &tmp, sizeof(tmp));

    /* compose the descriptor */
    real_filename = filename;
    if ((temp_str = strrchr(real_filename, '\\')) != NULL)
        real_filename = temp_str + 1;
    if ((temp_str = strrchr(real_filename, '/')) != NULL)
        real_filename = temp_str + 1;
    if ((temp_str = strrchr(real_filename, ':')) != NULL)
        real_filename = temp_str + 1;
    sprintf(desc, desc_template, time(NULL), (unsigned long)total_size,
            real_filename, (flags & BLOCK_FLAG_COMPAT6 ? 6 : 4), total_size / (63 * 16));

    /* write the descriptor */
    lseek(fd, le64_to_cpu(header.desc_offset) << 9, SEEK_SET);
    write(fd, desc, strlen(desc));

    close(fd);
    return 0;
}

static void vmdk_close(BlockDriverState *bs)
{
    BDRVVmdkState *s = bs->opaque;

    qemu_free(s->l1_table);
    qemu_free(s->l2_cache);
    bdrv_delete(s->hd);
    // try to close parent image, if exist
    vmdk_parent_close(s->hd);
}

static void vmdk_flush(BlockDriverState *bs)
{
    BDRVVmdkState *s = bs->opaque;
    bdrv_flush(s->hd);
}

BlockDriver bdrv_vmdk = {
    "vmdk",
    sizeof(BDRVVmdkState),
    vmdk_probe,
    vmdk_open,
    vmdk_read,
    vmdk_write,
    vmdk_close,
    vmdk_create,
    vmdk_flush,
    vmdk_is_allocated,
};