X-Git-Url: https://repo.jachan.dev/qemu.git/blobdiff_plain/efaa7c4eeb7490c6f37f34fbc77e91f29363eebd..4bc0d39a2fd066e64c5e59947228beb41d3e4ffc:/block/vmdk.c diff --git a/block/vmdk.c b/block/vmdk.c index 80f033835e..a9bd22bf93 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -24,15 +24,16 @@ */ #include "qemu/osdep.h" -#include "qemu-common.h" +#include "qapi/error.h" #include "block/block_int.h" #include "sysemu/block-backend.h" #include "qapi/qmp/qerror.h" #include "qemu/error-report.h" #include "qemu/module.h" +#include "qemu/bswap.h" #include "migration/migration.h" +#include "qemu/cutils.h" #include -#include #define VMDK3_MAGIC (('C' << 24) | ('O' << 16) | ('W' << 8) | 'D') #define VMDK4_MAGIC (('K' << 24) | ('D' << 16) | ('M' << 8) | 'V') @@ -251,7 +252,7 @@ static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent) int ret; desc = g_malloc0(DESC_SIZE); - ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE); if (ret < 0) { g_free(desc); return 0; @@ -285,7 +286,7 @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid) desc = g_malloc0(DESC_SIZE); tmp_desc = g_malloc0(DESC_SIZE); - ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE); if (ret < 0) { goto out; } @@ -305,7 +306,7 @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid) pstrcat(desc, DESC_SIZE, tmp_desc); } - ret = bdrv_pwrite_sync(bs->file->bs, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pwrite_sync(bs->file, s->desc_offset, desc, DESC_SIZE); out: g_free(desc); @@ -349,7 +350,7 @@ static int vmdk_parent_open(BlockDriverState *bs) int ret; desc = g_malloc0(DESC_SIZE + 1); - ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE); if (ret < 0) { goto out; } @@ -453,7 +454,7 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent, return -ENOMEM; } - ret = bdrv_pread(extent->file->bs, + ret = bdrv_pread(extent->file, extent->l1_table_offset, extent->l1_table, l1_size); @@ -473,7 +474,7 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent, ret = -ENOMEM; goto fail_l1; } - ret = bdrv_pread(extent->file->bs, + ret = bdrv_pread(extent->file, extent->l1_backup_table_offset, extent->l1_backup_table, l1_size); @@ -507,7 +508,7 @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs, VMDK3Header header; VmdkExtent *extent; - ret = bdrv_pread(file->bs, sizeof(magic), &header, sizeof(header)); + ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header)); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read header from file '%s'", @@ -537,14 +538,13 @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs, static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf, QDict *options, Error **errp); -static char *vmdk_read_desc(BlockDriverState *file, uint64_t desc_offset, - Error **errp) +static char *vmdk_read_desc(BdrvChild *file, uint64_t desc_offset, Error **errp) { int64_t size; char *buf; int ret; - size = bdrv_getlength(file); + size = bdrv_getlength(file->bs); if (size < 0) { error_setg_errno(errp, -size, "Could not access file"); return NULL; @@ -585,7 +585,7 @@ static int vmdk_open_vmdk4(BlockDriverState *bs, int64_t l1_backup_offset = 0; bool compressed; - ret = bdrv_pread(file->bs, sizeof(magic), &header, sizeof(header)); + ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header)); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read header from file '%s'", @@ -595,7 +595,7 @@ static int vmdk_open_vmdk4(BlockDriverState *bs, if (header.capacity == 0) { uint64_t desc_offset = le64_to_cpu(header.desc_offset); if (desc_offset) { - char *buf = vmdk_read_desc(file->bs, desc_offset << 9, errp); + char *buf = vmdk_read_desc(file, desc_offset << 9, errp); if (!buf) { return -EINVAL; } @@ -635,7 +635,7 @@ static int vmdk_open_vmdk4(BlockDriverState *bs, } QEMU_PACKED eos_marker; } QEMU_PACKED footer; - ret = bdrv_pread(file->bs, + ret = bdrv_pread(file, bs->file->bs->total_sectors * 512 - 1536, &footer, sizeof(footer)); if (ret < 0) { @@ -873,7 +873,7 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, 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->bs, 0, errp); + char *buf = vmdk_read_desc(extent_file, 0, errp); if (!buf) { ret = -EINVAL; } else { @@ -941,8 +941,15 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags, int ret; BDRVVmdkState *s = bs->opaque; uint32_t magic; + Error *local_err = NULL; + + bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, + false, errp); + if (!bs->file) { + return -EINVAL; + } - buf = vmdk_read_desc(bs->file->bs, 0, errp); + buf = vmdk_read_desc(bs->file, 0, errp); if (!buf) { return -EINVAL; } @@ -976,7 +983,13 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags, error_setg(&s->migration_blocker, "The vmdk format used by node '%s' " "does not support live migration", bdrv_get_device_or_node_name(bs)); - migrate_add_blocker(s->migration_blocker); + ret = migrate_add_blocker(s->migration_blocker, &local_err); + if (local_err) { + error_propagate(errp, local_err); + error_free(s->migration_blocker); + goto fail; + } + g_free(buf); return 0; @@ -996,9 +1009,9 @@ static void vmdk_refresh_limits(BlockDriverState *bs, Error **errp) for (i = 0; i < s->num_extents; i++) { if (!s->extents[i].flat) { - bs->bl.write_zeroes_alignment = - MAX(bs->bl.write_zeroes_alignment, - s->extents[i].cluster_sectors); + bs->bl.pwrite_zeroes_alignment = + MAX(bs->bl.pwrite_zeroes_alignment, + s->extents[i].cluster_sectors << BDRV_SECTOR_BITS); } } } @@ -1015,27 +1028,26 @@ static void vmdk_refresh_limits(BlockDriverState *bs, Error **errp) */ static int get_whole_cluster(BlockDriverState *bs, VmdkExtent *extent, - uint64_t cluster_sector_num, - uint64_t sector_num, - uint64_t skip_start_sector, - uint64_t skip_end_sector) + uint64_t cluster_offset, + uint64_t offset, + uint64_t skip_start_bytes, + uint64_t skip_end_bytes) { int ret = VMDK_OK; int64_t cluster_bytes; uint8_t *whole_grain; /* For COW, align request sector_num to cluster start */ - sector_num = QEMU_ALIGN_DOWN(sector_num, extent->cluster_sectors); cluster_bytes = extent->cluster_sectors << BDRV_SECTOR_BITS; + offset = QEMU_ALIGN_DOWN(offset, cluster_bytes); whole_grain = qemu_blockalign(bs, cluster_bytes); if (!bs->backing) { - memset(whole_grain, 0, skip_start_sector << BDRV_SECTOR_BITS); - memset(whole_grain + (skip_end_sector << BDRV_SECTOR_BITS), 0, - cluster_bytes - (skip_end_sector << BDRV_SECTOR_BITS)); + memset(whole_grain, 0, skip_start_bytes); + memset(whole_grain + skip_end_bytes, 0, cluster_bytes - skip_end_bytes); } - assert(skip_end_sector <= extent->cluster_sectors); + assert(skip_end_bytes <= cluster_bytes); /* we will be here if it's first write on non-exist grain(cluster). * try to read from parent image, if exist */ if (bs->backing && !vmdk_is_cid_valid(bs)) { @@ -1044,42 +1056,43 @@ static int get_whole_cluster(BlockDriverState *bs, } /* Read backing data before skip range */ - if (skip_start_sector > 0) { + if (skip_start_bytes > 0) { if (bs->backing) { - ret = bdrv_read(bs->backing->bs, sector_num, - whole_grain, skip_start_sector); + ret = bdrv_pread(bs->backing, offset, whole_grain, + skip_start_bytes); if (ret < 0) { ret = VMDK_ERROR; goto exit; } } - ret = bdrv_write(extent->file->bs, cluster_sector_num, whole_grain, - skip_start_sector); + ret = bdrv_pwrite(extent->file, cluster_offset, whole_grain, + skip_start_bytes); if (ret < 0) { ret = VMDK_ERROR; goto exit; } } /* Read backing data after skip range */ - if (skip_end_sector < extent->cluster_sectors) { + if (skip_end_bytes < cluster_bytes) { if (bs->backing) { - ret = bdrv_read(bs->backing->bs, sector_num + skip_end_sector, - whole_grain + (skip_end_sector << BDRV_SECTOR_BITS), - extent->cluster_sectors - skip_end_sector); + ret = bdrv_pread(bs->backing, offset + skip_end_bytes, + whole_grain + skip_end_bytes, + cluster_bytes - skip_end_bytes); if (ret < 0) { ret = VMDK_ERROR; goto exit; } } - ret = bdrv_write(extent->file->bs, cluster_sector_num + skip_end_sector, - whole_grain + (skip_end_sector << BDRV_SECTOR_BITS), - extent->cluster_sectors - skip_end_sector); + ret = bdrv_pwrite(extent->file, cluster_offset + skip_end_bytes, + whole_grain + skip_end_bytes, + cluster_bytes - skip_end_bytes); if (ret < 0) { ret = VMDK_ERROR; goto exit; } } + ret = VMDK_OK; exit: qemu_vfree(whole_grain); return ret; @@ -1090,8 +1103,7 @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, { offset = cpu_to_le32(offset); /* update L2 table */ - if (bdrv_pwrite_sync( - extent->file->bs, + if (bdrv_pwrite_sync(extent->file, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(offset)), &offset, sizeof(offset)) < 0) { @@ -1100,8 +1112,7 @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, /* update backup L2 table */ if (extent->l1_backup_table_offset != 0) { m_data->l2_offset = extent->l1_backup_table[m_data->l1_index]; - if (bdrv_pwrite_sync( - extent->file->bs, + if (bdrv_pwrite_sync(extent->file, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(offset)), &offset, sizeof(offset)) < 0) { @@ -1141,8 +1152,8 @@ static int get_cluster_offset(BlockDriverState *bs, uint64_t offset, bool allocate, uint64_t *cluster_offset, - uint64_t skip_start_sector, - uint64_t skip_end_sector) + uint64_t skip_start_bytes, + uint64_t skip_end_bytes) { unsigned int l1_index, l2_offset, l2_index; int min_index, i, j; @@ -1190,8 +1201,7 @@ static int get_cluster_offset(BlockDriverState *bs, } } l2_table = extent->l2_cache + (min_index * extent->l2_size); - if (bdrv_pread( - extent->file->bs, + if (bdrv_pread(extent->file, (int64_t)l2_offset * 512, l2_table, extent->l2_size * sizeof(uint32_t) @@ -1205,13 +1215,6 @@ static int get_cluster_offset(BlockDriverState *bs, l2_index = ((offset >> 9) / extent->cluster_sectors) % extent->l2_size; cluster_sector = le32_to_cpu(l2_table[l2_index]); - if (m_data) { - m_data->valid = 1; - m_data->l1_index = l1_index; - m_data->l2_index = l2_index; - m_data->l2_offset = l2_offset; - m_data->l2_cache_entry = &l2_table[l2_index]; - } if (extent->has_zero_grain && cluster_sector == VMDK_GTE_ZEROED) { zeroed = true; } @@ -1229,13 +1232,18 @@ static int get_cluster_offset(BlockDriverState *bs, * This problem may occur because of insufficient space on host disk * or inappropriate VM shutdown. */ - ret = get_whole_cluster(bs, extent, - cluster_sector, - offset >> BDRV_SECTOR_BITS, - skip_start_sector, skip_end_sector); + ret = get_whole_cluster(bs, extent, cluster_sector * BDRV_SECTOR_SIZE, + offset, skip_start_bytes, skip_end_bytes); if (ret) { return ret; } + if (m_data) { + m_data->valid = 1; + m_data->l1_index = l1_index; + m_data->l2_index = l2_index; + m_data->l2_offset = l2_offset; + m_data->l2_cache_entry = &l2_table[l2_index]; + } } *cluster_offset = cluster_sector << BDRV_SECTOR_BITS; return VMDK_OK; @@ -1258,15 +1266,24 @@ static VmdkExtent *find_extent(BDRVVmdkState *s, return NULL; } +static inline uint64_t vmdk_find_offset_in_cluster(VmdkExtent *extent, + int64_t offset) +{ + uint64_t extent_begin_offset, extent_relative_offset; + uint64_t cluster_size = extent->cluster_sectors * BDRV_SECTOR_SIZE; + + extent_begin_offset = + (extent->end_sector - extent->sectors) * BDRV_SECTOR_SIZE; + extent_relative_offset = offset - extent_begin_offset; + return extent_relative_offset % cluster_size; +} + static inline uint64_t vmdk_find_index_in_cluster(VmdkExtent *extent, int64_t sector_num) { - uint64_t index_in_cluster, extent_begin_sector, extent_relative_sector_num; - - extent_begin_sector = extent->end_sector - extent->sectors; - extent_relative_sector_num = sector_num - extent_begin_sector; - index_in_cluster = extent_relative_sector_num % extent->cluster_sectors; - return index_in_cluster; + uint64_t offset; + offset = vmdk_find_offset_in_cluster(extent, sector_num * BDRV_SECTOR_SIZE); + return offset / BDRV_SECTOR_SIZE; } static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs, @@ -1318,38 +1335,57 @@ static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs, } static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset, - int64_t offset_in_cluster, const uint8_t *buf, - int nb_sectors, int64_t sector_num) + int64_t offset_in_cluster, QEMUIOVector *qiov, + uint64_t qiov_offset, uint64_t n_bytes, + uint64_t offset) { int ret; VmdkGrainMarker *data = NULL; uLongf buf_len; - const uint8_t *write_buf = buf; - int write_len = nb_sectors * 512; + QEMUIOVector local_qiov; + struct iovec iov; int64_t write_offset; int64_t write_end_sector; if (extent->compressed) { + void *compressed_data; + if (!extent->has_marker) { ret = -EINVAL; goto out; } buf_len = (extent->cluster_sectors << 9) * 2; data = g_malloc(buf_len + sizeof(VmdkGrainMarker)); - if (compress(data->data, &buf_len, buf, nb_sectors << 9) != Z_OK || - buf_len == 0) { + + compressed_data = g_malloc(n_bytes); + qemu_iovec_to_buf(qiov, qiov_offset, compressed_data, n_bytes); + ret = compress(data->data, &buf_len, compressed_data, n_bytes); + g_free(compressed_data); + + if (ret != Z_OK || buf_len == 0) { ret = -EINVAL; goto out; } - data->lba = sector_num; - data->size = buf_len; - write_buf = (uint8_t *)data; - write_len = buf_len + sizeof(VmdkGrainMarker); + + data->lba = cpu_to_le64(offset >> BDRV_SECTOR_BITS); + data->size = cpu_to_le32(buf_len); + + n_bytes = buf_len + sizeof(VmdkGrainMarker); + iov = (struct iovec) { + .iov_base = data, + .iov_len = n_bytes, + }; + qemu_iovec_init_external(&local_qiov, &iov, 1); + } else { + qemu_iovec_init(&local_qiov, qiov->niov); + qemu_iovec_concat(&local_qiov, qiov, qiov_offset, n_bytes); } + write_offset = cluster_offset + offset_in_cluster, - ret = bdrv_pwrite(extent->file->bs, write_offset, write_buf, write_len); + ret = bdrv_co_pwritev(extent->file, write_offset, n_bytes, + &local_qiov, 0); - write_end_sector = DIV_ROUND_UP(write_offset + write_len, BDRV_SECTOR_SIZE); + write_end_sector = DIV_ROUND_UP(write_offset + n_bytes, BDRV_SECTOR_SIZE); if (extent->compressed) { extent->next_cluster_sector = write_end_sector; @@ -1358,19 +1394,21 @@ static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset, write_end_sector); } - if (ret != write_len) { - ret = ret < 0 ? ret : -EIO; + if (ret < 0) { goto out; } ret = 0; out: g_free(data); + if (!extent->compressed) { + qemu_iovec_destroy(&local_qiov); + } return ret; } static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset, - int64_t offset_in_cluster, uint8_t *buf, - int nb_sectors) + int64_t offset_in_cluster, QEMUIOVector *qiov, + int bytes) { int ret; int cluster_bytes, buf_bytes; @@ -1382,21 +1420,20 @@ static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset, if (!extent->compressed) { - ret = bdrv_pread(extent->file->bs, - cluster_offset + offset_in_cluster, - buf, nb_sectors * 512); - if (ret == nb_sectors * 512) { - return 0; - } else { - return -EIO; + ret = bdrv_co_preadv(extent->file, + cluster_offset + offset_in_cluster, bytes, + qiov, 0); + if (ret < 0) { + return ret; } + return 0; } cluster_bytes = extent->cluster_sectors * 512; /* Read two clusters in case GrainMarker + compressed data > one cluster */ buf_bytes = cluster_bytes * 2; cluster_buf = g_malloc(buf_bytes); uncomp_buf = g_malloc(cluster_bytes); - ret = bdrv_pread(extent->file->bs, + ret = bdrv_pread(extent->file, cluster_offset, cluster_buf, buf_bytes); if (ret < 0) { @@ -1421,11 +1458,11 @@ static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset, } if (offset_in_cluster < 0 || - offset_in_cluster + nb_sectors * 512 > buf_len) { + offset_in_cluster + bytes > buf_len) { ret = -EINVAL; goto out; } - memcpy(buf, uncomp_buf + offset_in_cluster, nb_sectors * 512); + qemu_iovec_from_buf(qiov, 0, uncomp_buf + offset_in_cluster, bytes); ret = 0; out: @@ -1434,64 +1471,73 @@ static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset, return ret; } -static int vmdk_read(BlockDriverState *bs, int64_t sector_num, - uint8_t *buf, int nb_sectors) +static int coroutine_fn +vmdk_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, int flags) { BDRVVmdkState *s = bs->opaque; int ret; - uint64_t n, index_in_cluster; + uint64_t n_bytes, offset_in_cluster; VmdkExtent *extent = NULL; + QEMUIOVector local_qiov; uint64_t cluster_offset; + uint64_t bytes_done = 0; - while (nb_sectors > 0) { - extent = find_extent(s, sector_num, extent); + qemu_iovec_init(&local_qiov, qiov->niov); + qemu_co_mutex_lock(&s->lock); + + while (bytes > 0) { + extent = find_extent(s, offset >> BDRV_SECTOR_BITS, extent); if (!extent) { - return -EIO; + ret = -EIO; + goto fail; } ret = get_cluster_offset(bs, extent, NULL, - sector_num << 9, false, &cluster_offset, - 0, 0); - index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num); - n = extent->cluster_sectors - index_in_cluster; - if (n > nb_sectors) { - n = nb_sectors; - } + offset, false, &cluster_offset, 0, 0); + offset_in_cluster = vmdk_find_offset_in_cluster(extent, offset); + + n_bytes = MIN(bytes, extent->cluster_sectors * BDRV_SECTOR_SIZE + - offset_in_cluster); + if (ret != VMDK_OK) { /* if not allocated, try to read from parent image, if exist */ if (bs->backing && ret != VMDK_ZEROED) { if (!vmdk_is_cid_valid(bs)) { - return -EINVAL; + ret = -EINVAL; + goto fail; } - ret = bdrv_read(bs->backing->bs, sector_num, buf, n); + + qemu_iovec_reset(&local_qiov); + qemu_iovec_concat(&local_qiov, qiov, bytes_done, n_bytes); + + ret = bdrv_co_preadv(bs->backing, offset, n_bytes, + &local_qiov, 0); if (ret < 0) { - return ret; + goto fail; } } else { - memset(buf, 0, 512 * n); + qemu_iovec_memset(qiov, bytes_done, 0, n_bytes); } } else { - ret = vmdk_read_extent(extent, - cluster_offset, index_in_cluster * 512, - buf, n); + qemu_iovec_reset(&local_qiov); + qemu_iovec_concat(&local_qiov, qiov, bytes_done, n_bytes); + + ret = vmdk_read_extent(extent, cluster_offset, offset_in_cluster, + &local_qiov, n_bytes); if (ret) { - return ret; + goto fail; } } - nb_sectors -= n; - sector_num += n; - buf += n * 512; + bytes -= n_bytes; + offset += n_bytes; + bytes_done += n_bytes; } - return 0; -} -static coroutine_fn int vmdk_co_read(BlockDriverState *bs, int64_t sector_num, - uint8_t *buf, int nb_sectors) -{ - int ret; - BDRVVmdkState *s = bs->opaque; - qemu_co_mutex_lock(&s->lock); - ret = vmdk_read(bs, sector_num, buf, nb_sectors); + ret = 0; +fail: qemu_co_mutex_unlock(&s->lock); + qemu_iovec_destroy(&local_qiov); + return ret; } @@ -1505,38 +1551,38 @@ static coroutine_fn int vmdk_co_read(BlockDriverState *bs, int64_t sector_num, * * Returns: error code with 0 for success. */ -static int vmdk_write(BlockDriverState *bs, int64_t sector_num, - const uint8_t *buf, int nb_sectors, - bool zeroed, bool zero_dry_run) +static int vmdk_pwritev(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, + bool zeroed, bool zero_dry_run) { BDRVVmdkState *s = bs->opaque; VmdkExtent *extent = NULL; int ret; - int64_t index_in_cluster, n; + int64_t offset_in_cluster, n_bytes; uint64_t cluster_offset; + uint64_t bytes_done = 0; VmdkMetaData m_data; - if (sector_num > bs->total_sectors) { - error_report("Wrong offset: sector_num=0x%" PRIx64 + if (DIV_ROUND_UP(offset, BDRV_SECTOR_SIZE) > bs->total_sectors) { + error_report("Wrong offset: offset=0x%" PRIx64 " total_sectors=0x%" PRIx64, - sector_num, bs->total_sectors); + offset, bs->total_sectors); return -EIO; } - while (nb_sectors > 0) { - extent = find_extent(s, sector_num, extent); + while (bytes > 0) { + extent = find_extent(s, offset >> BDRV_SECTOR_BITS, extent); if (!extent) { return -EIO; } - index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num); - n = extent->cluster_sectors - index_in_cluster; - if (n > nb_sectors) { - n = nb_sectors; - } - ret = get_cluster_offset(bs, extent, &m_data, sector_num << 9, + offset_in_cluster = vmdk_find_offset_in_cluster(extent, offset); + n_bytes = MIN(bytes, extent->cluster_sectors * BDRV_SECTOR_SIZE + - offset_in_cluster); + + ret = get_cluster_offset(bs, extent, &m_data, offset, !(extent->compressed || zeroed), - &cluster_offset, - index_in_cluster, index_in_cluster + n); + &cluster_offset, offset_in_cluster, + offset_in_cluster + n_bytes); if (extent->compressed) { if (ret == VMDK_OK) { /* Refuse write to allocated cluster for streamOptimized */ @@ -1545,7 +1591,7 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num, return -EIO; } else { /* allocate */ - ret = get_cluster_offset(bs, extent, &m_data, sector_num << 9, + ret = get_cluster_offset(bs, extent, &m_data, offset, true, &cluster_offset, 0, 0); } } @@ -1555,9 +1601,9 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num, if (zeroed) { /* Do zeroed write, buf is ignored */ if (extent->has_zero_grain && - index_in_cluster == 0 && - n >= extent->cluster_sectors) { - n = extent->cluster_sectors; + offset_in_cluster == 0 && + n_bytes >= extent->cluster_sectors * BDRV_SECTOR_SIZE) { + n_bytes = extent->cluster_sectors * BDRV_SECTOR_SIZE; if (!zero_dry_run) { /* update L2 tables */ if (vmdk_L2update(extent, &m_data, VMDK_GTE_ZEROED) @@ -1569,9 +1615,8 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num, return -ENOTSUP; } } else { - ret = vmdk_write_extent(extent, - cluster_offset, index_in_cluster * 512, - buf, n, sector_num); + ret = vmdk_write_extent(extent, cluster_offset, offset_in_cluster, + qiov, bytes_done, n_bytes, offset); if (ret) { return ret; } @@ -1584,9 +1629,9 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num, } } } - nb_sectors -= n; - sector_num += n; - buf += n * 512; + bytes -= n_bytes; + offset += n_bytes; + bytes_done += n_bytes; /* update CID on the first write every time the virtual disk is * opened */ @@ -1601,43 +1646,39 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num, return 0; } -static coroutine_fn int vmdk_co_write(BlockDriverState *bs, int64_t sector_num, - const uint8_t *buf, int nb_sectors) +static int coroutine_fn +vmdk_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, int flags) { int ret; BDRVVmdkState *s = bs->opaque; qemu_co_mutex_lock(&s->lock); - ret = vmdk_write(bs, sector_num, buf, nb_sectors, false, false); + ret = vmdk_pwritev(bs, offset, bytes, qiov, false, false); qemu_co_mutex_unlock(&s->lock); return ret; } -static int vmdk_write_compressed(BlockDriverState *bs, - int64_t sector_num, - const uint8_t *buf, - int nb_sectors) +static int coroutine_fn +vmdk_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov) { - BDRVVmdkState *s = bs->opaque; - if (s->num_extents == 1 && s->extents[0].compressed) { - return vmdk_write(bs, sector_num, buf, nb_sectors, false, false); - } else { - return -ENOTSUP; - } + return vmdk_co_pwritev(bs, offset, bytes, qiov, 0); } -static int coroutine_fn vmdk_co_write_zeroes(BlockDriverState *bs, - int64_t sector_num, - int nb_sectors, - BdrvRequestFlags flags) +static int coroutine_fn vmdk_co_pwrite_zeroes(BlockDriverState *bs, + int64_t offset, + int bytes, + BdrvRequestFlags flags) { int ret; BDRVVmdkState *s = bs->opaque; + qemu_co_mutex_lock(&s->lock); /* write zeroes could fail if sectors not aligned to cluster, test it with * dry_run == true before really updating image */ - ret = vmdk_write(bs, sector_num, NULL, nb_sectors, true, true); + ret = vmdk_pwritev(bs, offset, bytes, NULL, true, true); if (!ret) { - ret = vmdk_write(bs, sector_num, NULL, nb_sectors, true, false); + ret = vmdk_pwritev(bs, offset, bytes, NULL, true, false); } qemu_co_mutex_unlock(&s->lock); return ret; @@ -1662,7 +1703,7 @@ static int vmdk_create_extent(const char *filename, int64_t filesize, } blk = blk_new_open(filename, NULL, NULL, - BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL, + BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, &local_err); if (blk == NULL) { error_propagate(errp, local_err); @@ -1728,12 +1769,12 @@ static int vmdk_create_extent(const char *filename, int64_t filesize, header.check_bytes[3] = 0xa; /* write all the data */ - ret = blk_pwrite(blk, 0, &magic, sizeof(magic)); + ret = blk_pwrite(blk, 0, &magic, sizeof(magic), 0); if (ret < 0) { error_setg(errp, QERR_IO_ERROR); goto exit; } - ret = blk_pwrite(blk, sizeof(magic), &header, sizeof(header)); + ret = blk_pwrite(blk, sizeof(magic), &header, sizeof(header), 0); if (ret < 0) { error_setg(errp, QERR_IO_ERROR); goto exit; @@ -1753,7 +1794,7 @@ static int vmdk_create_extent(const char *filename, int64_t filesize, gd_buf[i] = cpu_to_le32(tmp); } ret = blk_pwrite(blk, le64_to_cpu(header.rgd_offset) * BDRV_SECTOR_SIZE, - gd_buf, gd_buf_size); + gd_buf, gd_buf_size, 0); if (ret < 0) { error_setg(errp, QERR_IO_ERROR); goto exit; @@ -1765,7 +1806,7 @@ static int vmdk_create_extent(const char *filename, int64_t filesize, gd_buf[i] = cpu_to_le32(tmp); } ret = blk_pwrite(blk, le64_to_cpu(header.gd_offset) * BDRV_SECTOR_SIZE, - gd_buf, gd_buf_size); + gd_buf, gd_buf_size, 0); if (ret < 0) { error_setg(errp, QERR_IO_ERROR); goto exit; @@ -1829,8 +1870,8 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp) int64_t total_size = 0, filesize; char *adapter_type = NULL; char *backing_file = NULL; + char *hw_version = NULL; char *fmt = NULL; - int flags = 0; int ret = 0; bool flat, split, compress; GString *ext_desc_lines; @@ -1861,7 +1902,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp) "# The Disk Data Base\n" "#DDB\n" "\n" - "ddb.virtualHWVersion = \"%d\"\n" + "ddb.virtualHWVersion = \"%s\"\n" "ddb.geometry.cylinders = \"%" PRId64 "\"\n" "ddb.geometry.heads = \"%" PRIu32 "\"\n" "ddb.geometry.sectors = \"63\"\n" @@ -1878,8 +1919,20 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp) BDRV_SECTOR_SIZE); adapter_type = qemu_opt_get_del(opts, BLOCK_OPT_ADAPTER_TYPE); backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE); + hw_version = qemu_opt_get_del(opts, BLOCK_OPT_HWVERSION); if (qemu_opt_get_bool_del(opts, BLOCK_OPT_COMPAT6, false)) { - flags |= BLOCK_FLAG_COMPAT6; + if (strcmp(hw_version, "undefined")) { + error_setg(errp, + "compat6 cannot be enabled with hwversion set"); + ret = -EINVAL; + goto exit; + } + g_free(hw_version); + hw_version = g_strdup("6"); + } + if (strcmp(hw_version, "undefined") == 0) { + g_free(hw_version); + hw_version = g_strdup("4"); } fmt = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT); if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ZEROED_GRAIN, false)) { @@ -1947,7 +2000,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp) } blk = blk_new_open(full_backing, NULL, NULL, - BDRV_O_NO_BACKING | BDRV_O_CACHE_WB, errp); + BDRV_O_NO_BACKING, errp); g_free(full_backing); if (blk == NULL) { ret = -EIO; @@ -2001,7 +2054,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp) fmt, parent_desc_line, ext_desc_lines->str, - (flags & BLOCK_FLAG_COMPAT6 ? 6 : 4), + hw_version, total_size / (int64_t)(63 * number_heads * BDRV_SECTOR_SIZE), number_heads, @@ -2019,7 +2072,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp) } new_blk = blk_new_open(filename, NULL, NULL, - BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL, + BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, &local_err); if (new_blk == NULL) { error_propagate(errp, local_err); @@ -2029,7 +2082,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp) blk_set_allow_write_beyond_eof(new_blk, true); - ret = blk_pwrite(new_blk, desc_offset, desc, desc_len); + ret = blk_pwrite(new_blk, desc_offset, desc, desc_len, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not write description"); goto exit; @@ -2048,6 +2101,7 @@ exit: } g_free(adapter_type); g_free(backing_file); + g_free(hw_version); g_free(fmt); g_free(desc); g_free(path); @@ -2203,18 +2257,18 @@ static ImageInfoSpecific *vmdk_get_specific_info(BlockDriverState *bs) *spec_info = (ImageInfoSpecific){ .type = IMAGE_INFO_SPECIFIC_KIND_VMDK, - { - .vmdk = g_new0(ImageInfoSpecificVmdk, 1), + .u = { + .vmdk.data = g_new0(ImageInfoSpecificVmdk, 1), }, }; - *spec_info->u.vmdk = (ImageInfoSpecificVmdk) { + *spec_info->u.vmdk.data = (ImageInfoSpecificVmdk) { .create_type = g_strdup(s->create_type), .cid = s->cid, .parent_cid = s->parent_cid, }; - next = &spec_info->u.vmdk->extents; + next = &spec_info->u.vmdk.data->extents; for (i = 0; i < s->num_extents; i++) { *next = g_new0(ImageInfoList, 1); (*next)->value = vmdk_get_extent_info(&s->extents[i]); @@ -2251,27 +2305,6 @@ static int vmdk_get_info(BlockDriverState *bs, BlockDriverInfo *bdi) return 0; } -static void vmdk_detach_aio_context(BlockDriverState *bs) -{ - BDRVVmdkState *s = bs->opaque; - int i; - - for (i = 0; i < s->num_extents; i++) { - bdrv_detach_aio_context(s->extents[i].file->bs); - } -} - -static void vmdk_attach_aio_context(BlockDriverState *bs, - AioContext *new_context) -{ - BDRVVmdkState *s = bs->opaque; - int i; - - for (i = 0; i < s->num_extents; i++) { - bdrv_attach_aio_context(s->extents[i].file->bs, new_context); - } -} - static QemuOptsList vmdk_create_opts = { .name = "vmdk-create-opts", .head = QTAILQ_HEAD_INITIALIZER(vmdk_create_opts.head), @@ -2298,6 +2331,12 @@ static QemuOptsList vmdk_create_opts = { .help = "VMDK version 6 image", .def_value_str = "off" }, + { + .name = BLOCK_OPT_HWVERSION, + .type = QEMU_OPT_STRING, + .help = "VMDK hardware version", + .def_value_str = "undefined" + }, { .name = BLOCK_OPT_SUBFMT, .type = QEMU_OPT_STRING, @@ -2322,10 +2361,11 @@ static BlockDriver bdrv_vmdk = { .bdrv_open = vmdk_open, .bdrv_check = vmdk_check, .bdrv_reopen_prepare = vmdk_reopen_prepare, - .bdrv_read = vmdk_co_read, - .bdrv_write = vmdk_co_write, - .bdrv_write_compressed = vmdk_write_compressed, - .bdrv_co_write_zeroes = vmdk_co_write_zeroes, + .bdrv_child_perm = bdrv_format_default_perms, + .bdrv_co_preadv = vmdk_co_preadv, + .bdrv_co_pwritev = vmdk_co_pwritev, + .bdrv_co_pwritev_compressed = vmdk_co_pwritev_compressed, + .bdrv_co_pwrite_zeroes = vmdk_co_pwrite_zeroes, .bdrv_close = vmdk_close, .bdrv_create = vmdk_create, .bdrv_co_flush_to_disk = vmdk_co_flush, @@ -2335,8 +2375,6 @@ static BlockDriver bdrv_vmdk = { .bdrv_get_specific_info = vmdk_get_specific_info, .bdrv_refresh_limits = vmdk_refresh_limits, .bdrv_get_info = vmdk_get_info, - .bdrv_detach_aio_context = vmdk_detach_aio_context, - .bdrv_attach_aio_context = vmdk_attach_aio_context, .supports_backing = true, .create_opts = &vmdk_create_opts,