/* All VHDX structures on disk are little endian */
static void vhdx_header_le_import(VHDXHeader *h)
{
assert(h != NULL);
le32_to_cpus(&h->signature);
le32_to_cpus(&h->checksum);
le64_to_cpus(&h->sequence_number);
leguid_to_cpus(&h->file_write_guid);
leguid_to_cpus(&h->data_write_guid);
leguid_to_cpus(&h->log_guid);
le16_to_cpus(&h->log_version);
le16_to_cpus(&h->version);
le32_to_cpus(&h->log_length);
le64_to_cpus(&h->log_offset);
}
static void mptsas_fix_sgentry_endianness(MPISGEntry *sge)
{
le32_to_cpus(&sge->FlagsLength);
if (sge->FlagsLength & MPI_SGE_FLAGS_64_BIT_ADDRESSING) {
le64_to_cpus(&sge->u.Address64);
} else {
le32_to_cpus(&sge->u.Address32);
}
}
static void vdi_header_to_cpu(VdiHeader *header)
{
le32_to_cpus(&header->signature);
le32_to_cpus(&header->version);
le32_to_cpus(&header->header_size);
le32_to_cpus(&header->image_type);
le32_to_cpus(&header->image_flags);
le32_to_cpus(&header->offset_bmap);
le32_to_cpus(&header->offset_data);
le32_to_cpus(&header->cylinders);
le32_to_cpus(&header->heads);
le32_to_cpus(&header->sectors);
le32_to_cpus(&header->sector_size);
le64_to_cpus(&header->disk_size);
le32_to_cpus(&header->block_size);
le32_to_cpus(&header->block_extra);
le32_to_cpus(&header->blocks_in_image);
le32_to_cpus(&header->blocks_allocated);
uuid_convert(header->uuid_image);
uuid_convert(header->uuid_last_snap);
uuid_convert(header->uuid_link);
uuid_convert(header->uuid_parent);
}
static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVVHDXState *s = bs->opaque;
int ret = 0;
uint32_t i;
uint64_t signature;
uint32_t data_blocks_cnt, bitmap_blocks_cnt;
s->bat = NULL;
qemu_co_mutex_init(&s->lock);
/* validate the file signature */
ret = bdrv_pread(bs->file, 0, &signature, sizeof(uint64_t));
if (ret < 0) {
goto fail;
}
if (memcmp(&signature, "vhdxfile", 8)) {
ret = -EINVAL;
goto fail;
}
ret = vhdx_parse_header(bs, s);
if (ret) {
goto fail;
}
ret = vhdx_parse_log(bs, s);
if (ret) {
goto fail;
}
ret = vhdx_open_region_tables(bs, s);
if (ret) {
goto fail;
}
ret = vhdx_parse_metadata(bs, s);
if (ret) {
goto fail;
}
s->block_size = s->params.block_size;
/* the VHDX spec dictates that virtual_disk_size is always a multiple of
* logical_sector_size */
bs->total_sectors = s->virtual_disk_size >> s->logical_sector_size_bits;
data_blocks_cnt = s->virtual_disk_size >> s->block_size_bits;
if (s->virtual_disk_size - (data_blocks_cnt << s->block_size_bits)) {
data_blocks_cnt++;
}
bitmap_blocks_cnt = data_blocks_cnt >> s->chunk_ratio_bits;
if (data_blocks_cnt - (bitmap_blocks_cnt << s->chunk_ratio_bits)) {
bitmap_blocks_cnt++;
}
if (s->parent_entries) {
s->bat_entries = bitmap_blocks_cnt * (s->chunk_ratio + 1);
} else {
s->bat_entries = data_blocks_cnt +
((data_blocks_cnt - 1) >> s->chunk_ratio_bits);
}
s->bat_offset = s->bat_rt.file_offset;
if (s->bat_entries > s->bat_rt.length / sizeof(VHDXBatEntry)) {
/* BAT allocation is not large enough for all entries */
ret = -EINVAL;
goto fail;
}
s->bat = qemu_blockalign(bs, s->bat_rt.length);
ret = bdrv_pread(bs->file, s->bat_offset, s->bat, s->bat_rt.length);
if (ret < 0) {
goto fail;
}
for (i = 0; i < s->bat_entries; i++) {
le64_to_cpus(&s->bat[i]);
}
if (flags & BDRV_O_RDWR) {
ret = -ENOTSUP;
goto fail;
}
/* TODO: differencing files, write */
/* Disable migration when VHDX images are used */
error_set(&s->migration_blocker,
QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
"vhdx", bs->device_name, "live migration");
migrate_add_blocker(s->migration_blocker);
return 0;
fail:
qemu_vfree(s->headers[0]);
qemu_vfree(s->headers[1]);
qemu_vfree(s->bat);
qemu_vfree(s->parent_entries);
return ret;
}
/* Metadata initial parser
*
* This loads all the metadata entry fields. This may cause additional
* fields to be processed (e.g. parent locator, etc..).
*
* There are 5 Metadata items that are always required:
* - File Parameters (block size, has a parent)
* - Virtual Disk Size (size, in bytes, of the virtual drive)
* - Page 83 Data (scsi page 83 guid)
* - Logical Sector Size (logical sector size in bytes, either 512 or
* 4096. We only support 512 currently)
* - Physical Sector Size (512 or 4096)
*
* Also, if the File Parameters indicate this is a differencing file,
* we must also look for the Parent Locator metadata item.
*/
static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
{
int ret = 0;
uint8_t *buffer;
int offset = 0;
uint32_t i = 0;
VHDXMetadataTableEntry md_entry;
buffer = qemu_blockalign(bs, VHDX_METADATA_TABLE_MAX_SIZE);
ret = bdrv_pread(bs->file, s->metadata_rt.file_offset, buffer,
VHDX_METADATA_TABLE_MAX_SIZE);
if (ret < 0) {
goto exit;
}
memcpy(&s->metadata_hdr, buffer, sizeof(s->metadata_hdr));
offset += sizeof(s->metadata_hdr);
le64_to_cpus(&s->metadata_hdr.signature);
le16_to_cpus(&s->metadata_hdr.reserved);
le16_to_cpus(&s->metadata_hdr.entry_count);
if (memcmp(&s->metadata_hdr.signature, "metadata", 8)) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.present = 0;
if ((s->metadata_hdr.entry_count * sizeof(md_entry)) >
(VHDX_METADATA_TABLE_MAX_SIZE - offset)) {
ret = -EINVAL;
goto exit;
}
for (i = 0; i < s->metadata_hdr.entry_count; i++) {
memcpy(&md_entry, buffer + offset, sizeof(md_entry));
offset += sizeof(md_entry);
leguid_to_cpus(&md_entry.item_id);
le32_to_cpus(&md_entry.offset);
le32_to_cpus(&md_entry.length);
le32_to_cpus(&md_entry.data_bits);
le32_to_cpus(&md_entry.reserved2);
if (guid_eq(md_entry.item_id, file_param_guid)) {
if (s->metadata_entries.present & META_FILE_PARAMETER_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.file_parameters_entry = md_entry;
s->metadata_entries.present |= META_FILE_PARAMETER_PRESENT;
continue;
}
if (guid_eq(md_entry.item_id, virtual_size_guid)) {
if (s->metadata_entries.present & META_VIRTUAL_DISK_SIZE_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.virtual_disk_size_entry = md_entry;
s->metadata_entries.present |= META_VIRTUAL_DISK_SIZE_PRESENT;
continue;
}
if (guid_eq(md_entry.item_id, page83_guid)) {
if (s->metadata_entries.present & META_PAGE_83_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.page83_data_entry = md_entry;
s->metadata_entries.present |= META_PAGE_83_PRESENT;
continue;
}
if (guid_eq(md_entry.item_id, logical_sector_guid)) {
if (s->metadata_entries.present &
META_LOGICAL_SECTOR_SIZE_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.logical_sector_size_entry = md_entry;
s->metadata_entries.present |= META_LOGICAL_SECTOR_SIZE_PRESENT;
continue;
}
if (guid_eq(md_entry.item_id, phys_sector_guid)) {
if (s->metadata_entries.present & META_PHYS_SECTOR_SIZE_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.phys_sector_size_entry = md_entry;
s->metadata_entries.present |= META_PHYS_SECTOR_SIZE_PRESENT;
continue;
}
if (guid_eq(md_entry.item_id, parent_locator_guid)) {
if (s->metadata_entries.present & META_PARENT_LOCATOR_PRESENT) {
ret = -EINVAL;
goto exit;
}
s->metadata_entries.parent_locator_entry = md_entry;
s->metadata_entries.present |= META_PARENT_LOCATOR_PRESENT;
continue;
}
if (md_entry.data_bits & VHDX_META_FLAGS_IS_REQUIRED) {
/* cannot read vhdx file - required region table entry that
* we do not understand. per spec, we must fail to open */
ret = -ENOTSUP;
goto exit;
}
}
if (s->metadata_entries.present != META_ALL_PRESENT) {
ret = -ENOTSUP;
goto exit;
}
ret = bdrv_pread(bs->file,
s->metadata_entries.file_parameters_entry.offset
+ s->metadata_rt.file_offset,
&s->params,
sizeof(s->params));
if (ret < 0) {
goto exit;
}
le32_to_cpus(&s->params.block_size);
le32_to_cpus(&s->params.data_bits);
/* We now have the file parameters, so we can tell if this is a
* differencing file (i.e.. has_parent), is dynamic or fixed
* sized (leave_blocks_allocated), and the block size */
/* The parent locator required iff the file parameters has_parent set */
if (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) {
if (s->metadata_entries.present & META_PARENT_LOCATOR_PRESENT) {
/* TODO: parse parent locator fields */
ret = -ENOTSUP; /* temp, until differencing files are supported */
goto exit;
} else {
/* if has_parent is set, but there is not parent locator present,
* then that is an invalid combination */
ret = -EINVAL;
goto exit;
}
}
/* determine virtual disk size, logical sector size,
* and phys sector size */
ret = bdrv_pread(bs->file,
s->metadata_entries.virtual_disk_size_entry.offset
+ s->metadata_rt.file_offset,
&s->virtual_disk_size,
sizeof(uint64_t));
if (ret < 0) {
goto exit;
}
ret = bdrv_pread(bs->file,
s->metadata_entries.logical_sector_size_entry.offset
+ s->metadata_rt.file_offset,
&s->logical_sector_size,
sizeof(uint32_t));
if (ret < 0) {
goto exit;
}
ret = bdrv_pread(bs->file,
s->metadata_entries.phys_sector_size_entry.offset
+ s->metadata_rt.file_offset,
&s->physical_sector_size,
sizeof(uint32_t));
if (ret < 0) {
goto exit;
}
le64_to_cpus(&s->virtual_disk_size);
le32_to_cpus(&s->logical_sector_size);
le32_to_cpus(&s->physical_sector_size);
if (s->logical_sector_size == 0 || s->params.block_size == 0) {
ret = -EINVAL;
goto exit;
}
/* both block_size and sector_size are guaranteed powers of 2 */
s->sectors_per_block = s->params.block_size / s->logical_sector_size;
s->chunk_ratio = (VHDX_MAX_SECTORS_PER_BLOCK) *
(uint64_t)s->logical_sector_size /
(uint64_t)s->params.block_size;
/* These values are ones we will want to use for division / multiplication
* later on, and they are all guaranteed (per the spec) to be powers of 2,
* so we can take advantage of that for shift operations during
* reads/writes */
if (s->logical_sector_size & (s->logical_sector_size - 1)) {
ret = -EINVAL;
goto exit;
}
if (s->sectors_per_block & (s->sectors_per_block - 1)) {
ret = -EINVAL;
goto exit;
}
if (s->chunk_ratio & (s->chunk_ratio - 1)) {
ret = -EINVAL;
goto exit;
}
s->block_size = s->params.block_size;
if (s->block_size & (s->block_size - 1)) {
ret = -EINVAL;
goto exit;
}
s->logical_sector_size_bits = 31 - clz32(s->logical_sector_size);
s->sectors_per_block_bits = 31 - clz32(s->sectors_per_block);
s->chunk_ratio_bits = 63 - clz64(s->chunk_ratio);
s->block_size_bits = 31 - clz32(s->block_size);
ret = 0;
exit:
qemu_vfree(buffer);
return ret;
}
static int vhdx_open_region_tables(BlockDriverState *bs, BDRVVHDXState *s)
{
int ret = 0;
uint8_t *buffer;
int offset = 0;
VHDXRegionTableEntry rt_entry;
uint32_t i;
bool bat_rt_found = false;
bool metadata_rt_found = false;
/* We have to read the whole 64KB block, because the crc32 is over the
* whole block */
buffer = qemu_blockalign(bs, VHDX_HEADER_BLOCK_SIZE);
ret = bdrv_pread(bs->file, VHDX_REGION_TABLE_OFFSET, buffer,
VHDX_HEADER_BLOCK_SIZE);
if (ret < 0) {
goto fail;
}
memcpy(&s->rt, buffer, sizeof(s->rt));
le32_to_cpus(&s->rt.signature);
le32_to_cpus(&s->rt.checksum);
le32_to_cpus(&s->rt.entry_count);
le32_to_cpus(&s->rt.reserved);
offset += sizeof(s->rt);
if (!vhdx_checksum_is_valid(buffer, VHDX_HEADER_BLOCK_SIZE, 4) ||
memcmp(&s->rt.signature, "regi", 4)) {
ret = -EINVAL;
goto fail;
}
/* Per spec, maximum region table entry count is 2047 */
if (s->rt.entry_count > 2047) {
ret = -EINVAL;
goto fail;
}
for (i = 0; i < s->rt.entry_count; i++) {
memcpy(&rt_entry, buffer + offset, sizeof(rt_entry));
offset += sizeof(rt_entry);
leguid_to_cpus(&rt_entry.guid);
le64_to_cpus(&rt_entry.file_offset);
le32_to_cpus(&rt_entry.length);
le32_to_cpus(&rt_entry.data_bits);
/* see if we recognize the entry */
if (guid_eq(rt_entry.guid, bat_guid)) {
/* must be unique; if we have already found it this is invalid */
if (bat_rt_found) {
ret = -EINVAL;
goto fail;
}
bat_rt_found = true;
s->bat_rt = rt_entry;
continue;
}
if (guid_eq(rt_entry.guid, metadata_guid)) {
/* must be unique; if we have already found it this is invalid */
if (metadata_rt_found) {
ret = -EINVAL;
goto fail;
}
metadata_rt_found = true;
s->metadata_rt = rt_entry;
continue;
}
if (rt_entry.data_bits & VHDX_REGION_ENTRY_REQUIRED) {
/* cannot read vhdx file - required region table entry that
* we do not understand. per spec, we must fail to open */
ret = -ENOTSUP;
goto fail;
}
}
ret = 0;
fail:
qemu_vfree(buffer);
return ret;
}
