/* * Returns the absolute byte offset of the given sector in the image file. * If the sector is not allocated, -1 is returned instead. * * The parameter write must be 1 if the offset will be used for a write * operation (the block bitmaps is updated then), 0 otherwise. */ static inline int64_t get_sector_offset(BlockDriverState *bs, int64_t sector_num, int write) { BDRVVPCState *s = bs->opaque; uint64_t offset = sector_num * 512; uint64_t bitmap_offset, block_offset; uint32_t pagetable_index, pageentry_index; pagetable_index = offset / s->block_size; pageentry_index = (offset % s->block_size) / 512; if (pagetable_index >= s->max_table_entries || s->pagetable[pagetable_index] == 0xffffffff) return -1; // not allocated bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index]; block_offset = bitmap_offset + s->bitmap_size + (512 * pageentry_index); // We must ensure that we don't write to any sectors which are marked as // unused in the bitmap. We get away with setting all bits in the block // bitmap each time we write to a new block. This might cause Virtual PC to // miss sparse read optimization, but it's not a problem in terms of // correctness. if (write && (s->last_bitmap_offset != bitmap_offset)) { uint8_t bitmap[s->bitmap_size]; s->last_bitmap_offset = bitmap_offset; memset(bitmap, 0xff, s->bitmap_size); bdrv_pwrite_sync(bs->file->bs, bitmap_offset, bitmap, s->bitmap_size); } return block_offset; }
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; }
/* * Allocates a new block. This involves writing a new footer and updating * the Block Allocation Table to use the space at the old end of the image * file (overwriting the old footer) * * Returns the sectors' offset in the image file on success and < 0 on error */ static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num) { BDRVVPCState *s = bs->opaque; int64_t bat_offset; uint32_t index, bat_value; int ret; uint8_t bitmap[s->bitmap_size]; // Check if sector_num is valid if ((sector_num < 0) || (sector_num > bs->total_sectors)) return -1; // Write entry into in-memory BAT index = (sector_num * 512) / s->block_size; if (s->pagetable[index] != 0xFFFFFFFF) return -1; s->pagetable[index] = s->free_data_block_offset / 512; // Initialize the block's bitmap memset(bitmap, 0xff, s->bitmap_size); ret = bdrv_pwrite_sync(bs->file->bs, s->free_data_block_offset, bitmap, s->bitmap_size); if (ret < 0) { return ret; } // Write new footer (the old one will be overwritten) s->free_data_block_offset += s->block_size + s->bitmap_size; ret = rewrite_footer(bs); if (ret < 0) goto fail; // Write BAT entry to disk bat_offset = s->bat_offset + (4 * index); bat_value = cpu_to_be32(s->pagetable[index]); ret = bdrv_pwrite_sync(bs->file->bs, bat_offset, &bat_value, 4); if (ret < 0) goto fail; return get_sector_offset(bs, sector_num, 0); fail: s->free_data_block_offset -= (s->block_size + s->bitmap_size); return -1; }
/* * Writes the footer to the end of the image file. This is needed when the * file grows as it overwrites the old footer * * Returns 0 on success and < 0 on error */ static int rewrite_footer(BlockDriverState* bs) { int ret; BDRVVPCState *s = bs->opaque; int64_t offset = s->free_data_block_offset; ret = bdrv_pwrite_sync(bs->file->bs, offset, s->footer_buf, HEADER_SIZE); if (ret < 0) return ret; return 0; }
/* copy the snapshot 'snapshot_name' into the current disk image */ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id) { BDRVQcowState *s = bs->opaque; QCowSnapshot *sn; int i, snapshot_index; int cur_l1_bytes, sn_l1_bytes; snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id); if (snapshot_index < 0) return -ENOENT; sn = &s->snapshots[snapshot_index]; if (qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, -1) < 0) goto fail; if (qcow2_grow_l1_table(bs, sn->l1_size, true) < 0) goto fail; cur_l1_bytes = s->l1_size * sizeof(uint64_t); sn_l1_bytes = sn->l1_size * sizeof(uint64_t); if (cur_l1_bytes > sn_l1_bytes) { memset(s->l1_table + sn->l1_size, 0, cur_l1_bytes - sn_l1_bytes); } /* copy the snapshot l1 table to the current l1 table */ if (bdrv_pread(bs->file, sn->l1_table_offset, s->l1_table, sn_l1_bytes) < 0) goto fail; if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table, cur_l1_bytes) < 0) goto fail; for(i = 0; i < s->l1_size; i++) { be64_to_cpus(&s->l1_table[i]); } if (qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1) < 0) goto fail; #ifdef DEBUG_ALLOC qcow2_check_refcounts(bs); #endif return 0; fail: return -EIO; }
static int write_refcount_block(BlockDriverState *bs) { BDRVQcowState *s = bs->opaque; size_t size = s->cluster_size; if (s->refcount_block_cache_offset == 0) { return 0; } BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_UPDATE); if (bdrv_pwrite_sync(bs->file, s->refcount_block_cache_offset, s->refcount_block_cache, size) < 0) { return -EIO; } return 0; }
static int create_fixed_disk(BlockDriverState *bs, uint8_t *buf, int64_t total_size) { int ret; /* Add footer to total size */ total_size += HEADER_SIZE; ret = bdrv_truncate(bs, total_size); if (ret < 0) { return ret; } ret = bdrv_pwrite_sync(bs, total_size - HEADER_SIZE, buf, HEADER_SIZE); if (ret < 0) { return ret; } return ret; }
int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id) { BDRVQcowState *s = bs->opaque; QCowSnapshot *sn; int i, snapshot_index, l1_size2; snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id); if (snapshot_index < 0) return -ENOENT; sn = &s->snapshots[snapshot_index]; if (qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, -1) < 0) goto fail; if (qcow2_grow_l1_table(bs, sn->l1_size) < 0) goto fail; s->l1_size = sn->l1_size; l1_size2 = s->l1_size * sizeof(uint64_t); if (bdrv_pread(bs->file, sn->l1_table_offset, s->l1_table, l1_size2) != l1_size2) goto fail; if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table, l1_size2) < 0) goto fail; for(i = 0;i < s->l1_size; i++) { be64_to_cpus(&s->l1_table[i]); } if (qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1) < 0) goto fail; #ifdef DEBUG_ALLOC qcow2_check_refcounts(bs); #endif return 0; fail: return -EIO; }
/* Flushes the descriptor described by desc to the VHDX image file. * If the descriptor is a data descriptor, than 'data' must be non-NULL, * and >= 4096 bytes (VHDX_LOG_SECTOR_SIZE), containing the data to be * written. * * Verification is performed to make sure the sequence numbers of a data * descriptor match the sequence number in the desc. * * For a zero descriptor, it may describe multiple sectors to fill with zeroes. * In this case, it should be noted that zeroes are written to disk, and the * image file is not extended as a sparse file. */ static int vhdx_log_flush_desc(BlockDriverState *bs, VHDXLogDescriptor *desc, VHDXLogDataSector *data) { int ret = 0; uint64_t seq, file_offset; uint32_t offset = 0; void *buffer = NULL; uint64_t count = 1; int i; buffer = qemu_blockalign(bs, VHDX_LOG_SECTOR_SIZE); if (!memcmp(&desc->signature, "desc", 4)) { /* data sector */ if (data == NULL) { ret = -EFAULT; goto exit; } /* The sequence number of the data sector must match that * in the descriptor */ seq = data->sequence_high; seq <<= 32; seq |= data->sequence_low & 0xffffffff; if (seq != desc->sequence_number) { ret = -EINVAL; goto exit; } /* Each data sector is in total 4096 bytes, however the first * 8 bytes, and last 4 bytes, are located in the descriptor */ memcpy(buffer, &desc->leading_bytes, 8); offset += 8; memcpy(buffer+offset, data->data, 4084); offset += 4084; memcpy(buffer+offset, &desc->trailing_bytes, 4); } else if (!memcmp(&desc->signature, "zero", 4)) { /* write 'count' sectors of sector */ memset(buffer, 0, VHDX_LOG_SECTOR_SIZE); count = desc->zero_length / VHDX_LOG_SECTOR_SIZE; } file_offset = desc->file_offset; /* count is only > 1 if we are writing zeroes */ for (i = 0; i < count; i++) { ret = bdrv_pwrite_sync(bs->file, file_offset, buffer, VHDX_LOG_SECTOR_SIZE); if (ret < 0) { goto exit; } file_offset += VHDX_LOG_SECTOR_SIZE; } exit: qemu_vfree(buffer); return ret; }
/* copy the snapshot 'snapshot_name' into the current disk image */ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id) { BDRVQcowState *s = bs->opaque; QCowSnapshot *sn; int i, snapshot_index; int cur_l1_bytes, sn_l1_bytes; int ret; uint64_t *sn_l1_table = NULL; /* Search the snapshot */ snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id); if (snapshot_index < 0) { return -ENOENT; } sn = &s->snapshots[snapshot_index]; if (sn->disk_size != bs->total_sectors * BDRV_SECTOR_SIZE) { error_report("qcow2: Loading snapshots with different disk " "size is not implemented"); ret = -ENOTSUP; goto fail; } /* * Make sure that the current L1 table is big enough to contain the whole * L1 table of the snapshot. If the snapshot L1 table is smaller, the * current one must be padded with zeros. */ ret = qcow2_grow_l1_table(bs, sn->l1_size, true); if (ret < 0) { goto fail; } cur_l1_bytes = s->l1_size * sizeof(uint64_t); sn_l1_bytes = sn->l1_size * sizeof(uint64_t); /* * Copy the snapshot L1 table to the current L1 table. * * Before overwriting the old current L1 table on disk, make sure to * increase all refcounts for the clusters referenced by the new one. * Decrease the refcount referenced by the old one only when the L1 * table is overwritten. */ sn_l1_table = g_malloc0(cur_l1_bytes); ret = bdrv_pread(bs->file, sn->l1_table_offset, sn_l1_table, sn_l1_bytes); if (ret < 0) { goto fail; } ret = qcow2_update_snapshot_refcount(bs, sn->l1_table_offset, sn->l1_size, 1); if (ret < 0) { goto fail; } ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_DEFAULT & ~QCOW2_OL_ACTIVE_L1, s->l1_table_offset, cur_l1_bytes); if (ret < 0) { goto fail; } ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset, sn_l1_table, cur_l1_bytes); if (ret < 0) { goto fail; } /* * Decrease refcount of clusters of current L1 table. * * At this point, the in-memory s->l1_table points to the old L1 table, * whereas on disk we already have the new one. * * qcow2_update_snapshot_refcount special cases the current L1 table to use * the in-memory data instead of really using the offset to load a new one, * which is why this works. */ ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, -1); /* * Now update the in-memory L1 table to be in sync with the on-disk one. We * need to do this even if updating refcounts failed. */ for(i = 0; i < s->l1_size; i++) { s->l1_table[i] = be64_to_cpu(sn_l1_table[i]); } if (ret < 0) { goto fail; } g_free(sn_l1_table); sn_l1_table = NULL; /* * Update QCOW_OFLAG_COPIED in the active L1 table (it may have changed * when we decreased the refcount of the old snapshot. */ ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 0); if (ret < 0) { goto fail; } #ifdef DEBUG_ALLOC { BdrvCheckResult result = {0}; qcow2_check_refcounts(bs, &result, 0); } #endif return 0; fail: g_free(sn_l1_table); return ret; }
/* add at the end of the file a new list of snapshots */ static int qcow2_write_snapshots(BlockDriverState *bs) { BDRVQcowState *s = bs->opaque; QCowSnapshot *sn; QCowSnapshotHeader h; QCowSnapshotExtraData extra; int i, name_size, id_str_size, snapshots_size; struct { uint32_t nb_snapshots; uint64_t snapshots_offset; } QEMU_PACKED header_data; int64_t offset, snapshots_offset; int ret; /* compute the size of the snapshots */ offset = 0; for(i = 0; i < s->nb_snapshots; i++) { sn = s->snapshots + i; offset = align_offset(offset, 8); offset += sizeof(h); offset += sizeof(extra); offset += strlen(sn->id_str); offset += strlen(sn->name); } snapshots_size = offset; /* Allocate space for the new snapshot list */ snapshots_offset = qcow2_alloc_clusters(bs, snapshots_size); offset = snapshots_offset; if (offset < 0) { return offset; } ret = bdrv_flush(bs); if (ret < 0) { return ret; } /* The snapshot list position has not yet been updated, so these clusters * must indeed be completely free */ ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_DEFAULT, offset, s->snapshots_size); if (ret < 0) { return ret; } /* Write all snapshots to the new list */ for(i = 0; i < s->nb_snapshots; i++) { sn = s->snapshots + i; memset(&h, 0, sizeof(h)); h.l1_table_offset = cpu_to_be64(sn->l1_table_offset); h.l1_size = cpu_to_be32(sn->l1_size); /* If it doesn't fit in 32 bit, older implementations should treat it * as a disk-only snapshot rather than truncate the VM state */ if (sn->vm_state_size <= 0xffffffff) { h.vm_state_size = cpu_to_be32(sn->vm_state_size); } h.date_sec = cpu_to_be32(sn->date_sec); h.date_nsec = cpu_to_be32(sn->date_nsec); h.vm_clock_nsec = cpu_to_be64(sn->vm_clock_nsec); h.extra_data_size = cpu_to_be32(sizeof(extra)); memset(&extra, 0, sizeof(extra)); extra.vm_state_size_large = cpu_to_be64(sn->vm_state_size); extra.disk_size = cpu_to_be64(sn->disk_size); id_str_size = strlen(sn->id_str); name_size = strlen(sn->name); h.id_str_size = cpu_to_be16(id_str_size); h.name_size = cpu_to_be16(name_size); offset = align_offset(offset, 8); ret = bdrv_pwrite(bs->file, offset, &h, sizeof(h)); if (ret < 0) { goto fail; } offset += sizeof(h); ret = bdrv_pwrite(bs->file, offset, &extra, sizeof(extra)); if (ret < 0) { goto fail; } offset += sizeof(extra); ret = bdrv_pwrite(bs->file, offset, sn->id_str, id_str_size); if (ret < 0) { goto fail; } offset += id_str_size; ret = bdrv_pwrite(bs->file, offset, sn->name, name_size); if (ret < 0) { goto fail; } offset += name_size; } /* * Update the header to point to the new snapshot table. This requires the * new table and its refcounts to be stable on disk. */ ret = bdrv_flush(bs); if (ret < 0) { goto fail; } QEMU_BUILD_BUG_ON(offsetof(QCowHeader, snapshots_offset) != offsetof(QCowHeader, nb_snapshots) + sizeof(header_data.nb_snapshots)); header_data.nb_snapshots = cpu_to_be32(s->nb_snapshots); header_data.snapshots_offset = cpu_to_be64(snapshots_offset); ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots), &header_data, sizeof(header_data)); if (ret < 0) { goto fail; } /* free the old snapshot table */ qcow2_free_clusters(bs, s->snapshots_offset, s->snapshots_size, QCOW2_DISCARD_SNAPSHOT); s->snapshots_offset = snapshots_offset; s->snapshots_size = snapshots_size; return 0; fail: return ret; }
/* if no id is provided, a new one is constructed */ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info) { BDRVQcowState *s = bs->opaque; QCowSnapshot *snapshots1, sn1, *sn = &sn1; int i, ret; uint64_t *l1_table = NULL; int64_t l1_table_offset; memset(sn, 0, sizeof(*sn)); if (sn_info->id_str[0] == '\0') { /* compute a new id */ find_new_snapshot_id(bs, sn_info->id_str, sizeof(sn_info->id_str)); } /* check that the ID is unique */ if (find_snapshot_by_id(bs, sn_info->id_str) >= 0) return -ENOENT; sn->id_str = g_strdup(sn_info->id_str); if (!sn->id_str) goto fail; sn->name = g_strdup(sn_info->name); if (!sn->name) goto fail; sn->vm_state_size = sn_info->vm_state_size; sn->date_sec = sn_info->date_sec; sn->date_nsec = sn_info->date_nsec; sn->vm_clock_nsec = sn_info->vm_clock_nsec; ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1); if (ret < 0) goto fail; /* create the L1 table of the snapshot */ l1_table_offset = qcow2_alloc_clusters(bs, s->l1_size * sizeof(uint64_t)); if (l1_table_offset < 0) { goto fail; } bdrv_flush(bs->file); sn->l1_table_offset = l1_table_offset; sn->l1_size = s->l1_size; if (s->l1_size != 0) { l1_table = g_malloc(s->l1_size * sizeof(uint64_t)); } else { l1_table = NULL; } for(i = 0; i < s->l1_size; i++) { l1_table[i] = cpu_to_be64(s->l1_table[i]); } if (bdrv_pwrite_sync(bs->file, sn->l1_table_offset, l1_table, s->l1_size * sizeof(uint64_t)) < 0) goto fail; g_free(l1_table); l1_table = NULL; snapshots1 = g_malloc((s->nb_snapshots + 1) * sizeof(QCowSnapshot)); if (s->snapshots) { memcpy(snapshots1, s->snapshots, s->nb_snapshots * sizeof(QCowSnapshot)); g_free(s->snapshots); } s->snapshots = snapshots1; s->snapshots[s->nb_snapshots++] = *sn; if (qcow2_write_snapshots(bs) < 0) goto fail; #ifdef DEBUG_ALLOC qcow2_check_refcounts(bs); #endif return 0; fail: g_free(sn->name); g_free(l1_table); return -1; }
/* add at the end of the file a new list of snapshots */ static int qcow2_write_snapshots(BlockDriverState *bs) { BDRVQcowState *s = bs->opaque; QCowSnapshot *sn; QCowSnapshotHeader h; int i, name_size, id_str_size, snapshots_size; uint64_t data64; uint32_t data32; int64_t offset, snapshots_offset; /* compute the size of the snapshots */ offset = 0; for(i = 0; i < s->nb_snapshots; i++) { sn = s->snapshots + i; offset = align_offset(offset, 8); offset += sizeof(h); offset += strlen(sn->id_str); offset += strlen(sn->name); } snapshots_size = offset; snapshots_offset = qcow2_alloc_clusters(bs, snapshots_size); bdrv_flush(bs->file); offset = snapshots_offset; if (offset < 0) { return offset; } for(i = 0; i < s->nb_snapshots; i++) { sn = s->snapshots + i; memset(&h, 0, sizeof(h)); h.l1_table_offset = cpu_to_be64(sn->l1_table_offset); h.l1_size = cpu_to_be32(sn->l1_size); h.vm_state_size = cpu_to_be32(sn->vm_state_size); h.date_sec = cpu_to_be32(sn->date_sec); h.date_nsec = cpu_to_be32(sn->date_nsec); h.vm_clock_nsec = cpu_to_be64(sn->vm_clock_nsec); id_str_size = strlen(sn->id_str); name_size = strlen(sn->name); h.id_str_size = cpu_to_be16(id_str_size); h.name_size = cpu_to_be16(name_size); offset = align_offset(offset, 8); if (bdrv_pwrite_sync(bs->file, offset, &h, sizeof(h)) < 0) goto fail; offset += sizeof(h); if (bdrv_pwrite_sync(bs->file, offset, sn->id_str, id_str_size) < 0) goto fail; offset += id_str_size; if (bdrv_pwrite_sync(bs->file, offset, sn->name, name_size) < 0) goto fail; offset += name_size; } /* update the various header fields */ data64 = cpu_to_be64(snapshots_offset); if (bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, snapshots_offset), &data64, sizeof(data64)) < 0) goto fail; data32 = cpu_to_be32(s->nb_snapshots); if (bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots), &data32, sizeof(data32)) < 0) goto fail; /* free the old snapshot table */ qcow2_free_clusters(bs, s->snapshots_offset, s->snapshots_size); s->snapshots_offset = snapshots_offset; s->snapshots_size = snapshots_size; return 0; fail: return -1; }
static int create_dynamic_disk(BlockDriverState *bs, uint8_t *buf, int64_t total_sectors) { VHDDynDiskHeader *dyndisk_header = (VHDDynDiskHeader *) buf; size_t block_size, num_bat_entries; int i; int ret; int64_t offset = 0; // Write the footer (twice: at the beginning and at the end) block_size = 0x200000; num_bat_entries = (total_sectors + block_size / 512) / (block_size / 512); ret = bdrv_pwrite_sync(bs, offset, buf, HEADER_SIZE); if (ret) { goto fail; } offset = 1536 + ((num_bat_entries * 4 + 511) & ~511); ret = bdrv_pwrite_sync(bs, offset, buf, HEADER_SIZE); if (ret < 0) { goto fail; } // Write the initial BAT offset = 3 * 512; memset(buf, 0xFF, 512); for (i = 0; i < (num_bat_entries * 4 + 511) / 512; i++) { ret = bdrv_pwrite_sync(bs, offset, buf, 512); if (ret < 0) { goto fail; } offset += 512; } // Prepare the Dynamic Disk Header memset(buf, 0, 1024); memcpy(dyndisk_header->magic, "cxsparse", 8); /* * Note: The spec is actually wrong here for data_offset, it says * 0xFFFFFFFF, but MS tools expect all 64 bits to be set. */ dyndisk_header->data_offset = cpu_to_be64(0xFFFFFFFFFFFFFFFFULL); dyndisk_header->table_offset = cpu_to_be64(3 * 512); dyndisk_header->version = cpu_to_be32(0x00010000); dyndisk_header->block_size = cpu_to_be32(block_size); dyndisk_header->max_table_entries = cpu_to_be32(num_bat_entries); dyndisk_header->checksum = cpu_to_be32(vpc_checksum(buf, 1024)); // Write the header offset = 512; ret = bdrv_pwrite_sync(bs, offset, buf, 1024); if (ret < 0) { goto fail; } fail: return ret; }