block-qcow.c

qemu虚拟机代码

                if (s->crypt_method && 
                    (n_end - n_start) < s->cluster_sectors) {
                    uint64_t start_sect;
                    start_sect = (offset & ~(s->cluster_size - 1)) >> 9;
                    memset(s->cluster_data + 512, 0xaa, 512);
                    for(i = 0; i < s->cluster_sectors; i++) {
                        if (i < n_start || i >= n_end) {
                            encrypt_sectors(s, start_sect + i, 
                                            s->cluster_data, 
                                            s->cluster_data + 512, 1, 1,
                                            &s->aes_encrypt_key);
                            lseek(s->fd, cluster_offset + i * 512, SEEK_SET);
                            if (write(s->fd, s->cluster_data, 512) != 512)
                                return -1;
                        }
                    }
                }
            } else {
                cluster_offset |= QCOW_OFLAG_COMPRESSED | 
                    (uint64_t)compressed_size << (63 - s->cluster_bits);
            }
        }
        /* update L2 table */
        tmp = cpu_to_be64(cluster_offset);
        l2_table[l2_index] = tmp;
        lseek(s->fd, l2_offset + l2_index * sizeof(tmp), SEEK_SET);
        if (write(s->fd, &tmp, sizeof(tmp)) != sizeof(tmp))
            return 0;
    }
    return cluster_offset;
}

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

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

static int decompress_buffer(uint8_t *out_buf, int out_buf_size,
                             const uint8_t *buf, int buf_size)
{
    z_stream strm1, *strm = &strm1;
    int ret, out_len;

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

    strm->next_in = (uint8_t *)buf;
    strm->avail_in = buf_size;
    strm->next_out = out_buf;
    strm->avail_out = out_buf_size;

    ret = inflateInit2(strm, -12);
    if (ret != Z_OK)
        return -1;
    ret = inflate(strm, Z_FINISH);
    out_len = strm->next_out - out_buf;
    if ((ret != Z_STREAM_END && ret != Z_BUF_ERROR) ||
        out_len != out_buf_size) {
        inflateEnd(strm);
        return -1;
    }
    inflateEnd(strm);
    return 0;
}
                              
static int decompress_cluster(BDRVQcowState *s, uint64_t cluster_offset)
{
    int ret, csize;
    uint64_t coffset;

    coffset = cluster_offset & s->cluster_offset_mask;
    if (s->cluster_cache_offset != coffset) {
        csize = cluster_offset >> (63 - s->cluster_bits);
        csize &= (s->cluster_size - 1);
        lseek(s->fd, coffset, SEEK_SET);
        ret = read(s->fd, s->cluster_data, csize);
        if (ret != csize) 
            return -1;
        if (decompress_buffer(s->cluster_cache, s->cluster_size,
                              s->cluster_data, csize) < 0) {
            return -1;
        }
        s->cluster_cache_offset = coffset;
    }
    return 0;
}

static int qcow_read(BlockDriverState *bs, int64_t sector_num, 
                     uint8_t *buf, int nb_sectors)
{
    BDRVQcowState *s = bs->opaque;
    int ret, index_in_cluster, n;
    uint64_t cluster_offset;
    
    while (nb_sectors > 0) {
        cluster_offset = get_cluster_offset(bs, sector_num << 9, 0, 0, 0, 0);
        index_in_cluster = sector_num & (s->cluster_sectors - 1);
        n = s->cluster_sectors - index_in_cluster;
        if (n > nb_sectors)
            n = nb_sectors;
        if (!cluster_offset) {
            memset(buf, 0, 512 * n);
        } else if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
            if (decompress_cluster(s, cluster_offset) < 0)
                return -1;
            memcpy(buf, s->cluster_cache + index_in_cluster * 512, 512 * n);
        } else {
            lseek(s->fd, cluster_offset + index_in_cluster * 512, SEEK_SET);
            ret = read(s->fd, buf, n * 512);
            if (ret != n * 512) 
                return -1;
            if (s->crypt_method) {
                encrypt_sectors(s, sector_num, buf, buf, n, 0, 
                                &s->aes_decrypt_key);
            }
        }
        nb_sectors -= n;
        sector_num += n;
        buf += n * 512;
    }
    return 0;
}

static int qcow_write(BlockDriverState *bs, int64_t sector_num, 
                     const uint8_t *buf, int nb_sectors)
{
    BDRVQcowState *s = bs->opaque;
    int ret, index_in_cluster, n;
    uint64_t cluster_offset;
    
    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, sector_num << 9, 1, 0, 
                                            index_in_cluster, 
                                            index_in_cluster + n);
        if (!cluster_offset)
            return -1;
        lseek(s->fd, cluster_offset + index_in_cluster * 512, SEEK_SET);
        if (s->crypt_method) {
            encrypt_sectors(s, sector_num, s->cluster_data, buf, n, 1,
                            &s->aes_encrypt_key);
            ret = write(s->fd, s->cluster_data, n * 512);
        } else {
            ret = write(s->fd, buf, n * 512);
        }
        if (ret != n * 512) 
            return -1;
        nb_sectors -= n;
        sector_num += n;
        buf += n * 512;
    }
    s->cluster_cache_offset = -1; /* disable compressed cache */
    return 0;
}

static void qcow_close(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    qemu_free(s->l1_table);
    qemu_free(s->l2_cache);
    qemu_free(s->cluster_cache);
    qemu_free(s->cluster_data);
    close(s->fd);
}

static int qcow_create(const char *filename, int64_t total_size,
                      const char *backing_file, int flags)
{
    int fd, header_size, backing_filename_len, l1_size, i, shift;
    QCowHeader header;
    char backing_filename[1024];
    uint64_t tmp;
    struct stat st;

    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE, 
              0644);
    if (fd < 0)
        return -1;
    memset(&header, 0, sizeof(header));
    header.magic = cpu_to_be32(QCOW_MAGIC);
    header.version = cpu_to_be32(QCOW_VERSION);
    header.size = cpu_to_be64(total_size * 512);
    header_size = sizeof(header);
    backing_filename_len = 0;
    if (backing_file) {
	if (strcmp(backing_file, "fat:")) {
	    const char *p;
	    /* XXX: this is a hack: we do not attempt to check for URL
	       like syntax */
	    p = strchr(backing_file, ':');
	    if (p && (p - backing_file) >= 2) {
		/* URL like but exclude "c:" like filenames */
		pstrcpy(backing_filename, sizeof(backing_filename),
			backing_file);
	    } else {
		realpath(backing_file, backing_filename);
		if (stat(backing_filename, &st) != 0) {
		    return -1;
		}
	    }
	    header.backing_file_offset = cpu_to_be64(header_size);
	    backing_filename_len = strlen(backing_filename);
	    header.backing_file_size = cpu_to_be32(backing_filename_len);
	    header_size += backing_filename_len;
	} else
	    backing_file = NULL;
        header.mtime = cpu_to_be32(st.st_mtime);
        header.cluster_bits = 9; /* 512 byte cluster to avoid copying
                                    unmodifyed sectors */
        header.l2_bits = 12; /* 32 KB L2 tables */
    } else {
        header.cluster_bits = 12; /* 4 KB clusters */
        header.l2_bits = 9; /* 4 KB L2 tables */
    }
    header_size = (header_size + 7) & ~7;
    shift = header.cluster_bits + header.l2_bits;
    l1_size = ((total_size * 512) + (1LL << shift) - 1) >> shift;

    header.l1_table_offset = cpu_to_be64(header_size);
    if (flags) {
        header.crypt_method = cpu_to_be32(QCOW_CRYPT_AES);
    } else {
        header.crypt_method = cpu_to_be32(QCOW_CRYPT_NONE);
    }
    
    /* write all the data */
    write(fd, &header, sizeof(header));
    if (backing_file) {
        write(fd, backing_filename, backing_filename_len);
    }
    lseek(fd, header_size, SEEK_SET);
    tmp = 0;
    for(i = 0;i < l1_size; i++) {
        write(fd, &tmp, sizeof(tmp));
    }
    close(fd);
    return 0;
}

int qcow_make_empty(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    uint32_t l1_length = s->l1_size * sizeof(uint64_t);

    memset(s->l1_table, 0, l1_length);
    lseek(s->fd, s->l1_table_offset, SEEK_SET);
    if (write(s->fd, s->l1_table, l1_length) < 0)
	return -1;
    ftruncate(s->fd, s->l1_table_offset + l1_length);

    memset(s->l2_cache, 0, s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
    memset(s->l2_cache_offsets, 0, L2_CACHE_SIZE * sizeof(uint64_t));
    memset(s->l2_cache_counts, 0, L2_CACHE_SIZE * sizeof(uint32_t));

    return 0;
}

int qcow_get_cluster_size(BlockDriverState *bs)
{
    BDRVQcowState *s = bs->opaque;
    if (bs->drv != &bdrv_qcow)
        return -1;
    return s->cluster_size;
}

/* XXX: put compressed sectors first, then all the cluster aligned
   tables to avoid losing bytes in alignment */
int qcow_compress_cluster(BlockDriverState *bs, int64_t sector_num, 
                          const uint8_t *buf)
{
    BDRVQcowState *s = bs->opaque;
    z_stream strm;
    int ret, out_len;
    uint8_t *out_buf;
    uint64_t cluster_offset;

    if (bs->drv != &bdrv_qcow)
        return -1;

    out_buf = qemu_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);
    if (!out_buf)
        return -1;

    /* best compression, small window, no zlib header */
    memset(&strm, 0, sizeof(strm));
    ret = deflateInit2(&strm, Z_DEFAULT_COMPRESSION,
                       Z_DEFLATED, -12, 
                       9, Z_DEFAULT_STRATEGY);
    if (ret != 0) {
        qemu_free(out_buf);
        return -1;
    }

    strm.avail_in = s->cluster_size;
    strm.next_in = (uint8_t *)buf;
    strm.avail_out = s->cluster_size;
    strm.next_out = out_buf;

    ret = deflate(&strm, Z_FINISH);
    if (ret != Z_STREAM_END && ret != Z_OK) {
        qemu_free(out_buf);
        deflateEnd(&strm);
        return -1;
    }
    out_len = strm.next_out - out_buf;

    deflateEnd(&strm);

    if (ret != Z_STREAM_END || out_len >= s->cluster_size) {
        /* could not compress: write normal cluster */
        qcow_write(bs, sector_num, buf, s->cluster_sectors);
    } else {
        cluster_offset = get_cluster_offset(bs, sector_num << 9, 2, 
                                            out_len, 0, 0);
        cluster_offset &= s->cluster_offset_mask;
        lseek(s->fd, cluster_offset, SEEK_SET);
        if (write(s->fd, out_buf, out_len) != out_len) {
            qemu_free(out_buf);
            return -1;
        }
    }
    
    qemu_free(out_buf);
    return 0;
}

BlockDriver bdrv_qcow = {
    "qcow",
    sizeof(BDRVQcowState),
    qcow_probe,
    qcow_open,
    qcow_read,
    qcow_write,
    qcow_close,
    qcow_create,
    qcow_is_allocated,
    qcow_set_key,
    qcow_make_empty
};