}
/*
+ * Reserve space from free_tree.
+ * The algorithm is very simple, find the first cache_extent with enough space
+ * and allocate from its beginning.
+ */
+static int reserve_free_space(struct cache_tree *free_tree, u64 len,
+ u64 *ret_start)
+{
+ struct cache_extent *cache;
+ int found = 0;
+
+ ASSERT(ret_start != NULL);
+ cache = first_cache_extent(free_tree);
+ while (cache) {
+ if (cache->size > len) {
+ found = 1;
+ *ret_start = cache->start;
+
+ cache->size -= len;
+ if (cache->size == 0) {
+ remove_cache_extent(free_tree, cache);
+ free(cache);
+ } else {
+ cache->start += len;
+ }
+ break;
+ }
+ cache = next_cache_extent(cache);
+ }
+ if (!found)
+ return -ENOSPC;
+ return 0;
+}
+
+static inline int write_temp_super(int fd, struct btrfs_super_block *sb,
+ u64 sb_bytenr)
+{
+ u32 crc = ~(u32)0;
+ int ret;
+
+ crc = btrfs_csum_data(NULL, (char *)sb + BTRFS_CSUM_SIZE, crc,
+ BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
+ btrfs_csum_final(crc, &sb->csum[0]);
+ ret = pwrite(fd, sb, BTRFS_SUPER_INFO_SIZE, sb_bytenr);
+ if (ret < BTRFS_SUPER_INFO_SIZE)
+ ret = (ret < 0 ? -errno : -EIO);
+ else
+ ret = 0;
+ return ret;
+}
+
+/*
+ * Setup temporary superblock at cfg->super_bynter
+ * Needed info are extracted from cfg, and root_bytenr, chunk_bytenr
+ *
+ * For now sys chunk array will be empty and dev_item is empty too.
+ * They will be re-initialized at temp chunk tree setup.
+ *
+ * The superblock signature is not valid, denotes a partially created
+ * filesystem, needs to be finalized.
+ */
+static int setup_temp_super(int fd, struct btrfs_mkfs_config *cfg,
+ u64 root_bytenr, u64 chunk_bytenr)
+{
+ unsigned char chunk_uuid[BTRFS_UUID_SIZE];
+ char super_buf[BTRFS_SUPER_INFO_SIZE];
+ struct btrfs_super_block *super = (struct btrfs_super_block *)super_buf;
+ int ret;
+
+ memset(super_buf, 0, BTRFS_SUPER_INFO_SIZE);
+ cfg->num_bytes = round_down(cfg->num_bytes, cfg->sectorsize);
+
+ if (*cfg->fs_uuid) {
+ if (uuid_parse(cfg->fs_uuid, super->fsid) != 0) {
+ error("cound not parse UUID: %s", cfg->fs_uuid);
+ ret = -EINVAL;
+ goto out;
+ }
+ if (!test_uuid_unique(cfg->fs_uuid)) {
+ error("non-unique UUID: %s", cfg->fs_uuid);
+ ret = -EINVAL;
+ goto out;
+ }
+ } else {
+ uuid_generate(super->fsid);
+ uuid_unparse(super->fsid, cfg->fs_uuid);
+ }
+ uuid_generate(chunk_uuid);
+ uuid_unparse(chunk_uuid, cfg->chunk_uuid);
+
+ btrfs_set_super_bytenr(super, cfg->super_bytenr);
+ btrfs_set_super_num_devices(super, 1);
+ btrfs_set_super_magic(super, BTRFS_MAGIC_PARTIAL);
+ btrfs_set_super_generation(super, 1);
+ btrfs_set_super_root(super, root_bytenr);
+ btrfs_set_super_chunk_root(super, chunk_bytenr);
+ btrfs_set_super_total_bytes(super, cfg->num_bytes);
+ /*
+ * Temporary filesystem will only have 6 tree roots:
+ * chunk tree, root tree, extent_tree, device tree, fs tree
+ * and csum tree.
+ */
+ btrfs_set_super_bytes_used(super, 6 * cfg->nodesize);
+ btrfs_set_super_sectorsize(super, cfg->sectorsize);
+ btrfs_set_super_leafsize(super, cfg->nodesize);
+ btrfs_set_super_nodesize(super, cfg->nodesize);
+ btrfs_set_super_stripesize(super, cfg->stripesize);
+ btrfs_set_super_csum_type(super, BTRFS_CSUM_TYPE_CRC32);
+ btrfs_set_super_chunk_root(super, chunk_bytenr);
+ btrfs_set_super_cache_generation(super, -1);
+ btrfs_set_super_incompat_flags(super, cfg->features);
+ if (cfg->label)
+ __strncpy_null(super->label, cfg->label, BTRFS_LABEL_SIZE - 1);
+
+ /* Sys chunk array will be re-initialized at chunk tree init time */
+ super->sys_chunk_array_size = 0;
+
+ ret = write_temp_super(fd, super, cfg->super_bytenr);
+out:
+ return ret;
+}
+
+/*
+ * Setup an extent buffer for tree block.
+ */
+static int setup_temp_extent_buffer(struct extent_buffer *buf,
+ struct btrfs_mkfs_config *cfg,
+ u64 bytenr, u64 owner)
+{
+ unsigned char fsid[BTRFS_FSID_SIZE];
+ unsigned char chunk_uuid[BTRFS_UUID_SIZE];
+ int ret;
+
+ ret = uuid_parse(cfg->fs_uuid, fsid);
+ if (ret)
+ return -EINVAL;
+ ret = uuid_parse(cfg->chunk_uuid, chunk_uuid);
+ if (ret)
+ return -EINVAL;
+
+ memset(buf->data, 0, cfg->nodesize);
+ buf->len = cfg->nodesize;
+ btrfs_set_header_bytenr(buf, bytenr);
+ btrfs_set_header_generation(buf, 1);
+ btrfs_set_header_backref_rev(buf, BTRFS_MIXED_BACKREF_REV);
+ btrfs_set_header_owner(buf, owner);
+ btrfs_set_header_flags(buf, BTRFS_HEADER_FLAG_WRITTEN);
+ write_extent_buffer(buf, chunk_uuid, btrfs_header_chunk_tree_uuid(buf),
+ BTRFS_UUID_SIZE);
+ write_extent_buffer(buf, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE);
+ return 0;
+}
+
+static inline int write_temp_extent_buffer(int fd, struct extent_buffer *buf,
+ u64 bytenr)
+{
+ int ret;
+
+ csum_tree_block_size(buf, BTRFS_CRC32_SIZE, 0);
+
+ /* Temporary extent buffer is always mapped 1:1 on disk */
+ ret = pwrite(fd, buf->data, buf->len, bytenr);
+ if (ret < buf->len)
+ ret = (ret < 0 ? ret : -EIO);
+ else
+ ret = 0;
+ return ret;
+}
+
+/*
+ * Insert a root item for temporary tree root
+ *
+ * Only used in make_btrfs_v2().
+ */
+static void insert_temp_root_item(struct extent_buffer *buf,
+ struct btrfs_mkfs_config *cfg,
+ int *slot, u32 *itemoff, u64 objectid,
+ u64 bytenr)
+{
+ struct btrfs_root_item root_item;
+ struct btrfs_inode_item *inode_item;
+ struct btrfs_disk_key disk_key;
+
+ btrfs_set_header_nritems(buf, *slot + 1);
+ (*itemoff) -= sizeof(root_item);
+ memset(&root_item, 0, sizeof(root_item));
+ inode_item = &root_item.inode;
+ btrfs_set_stack_inode_generation(inode_item, 1);
+ btrfs_set_stack_inode_size(inode_item, 3);
+ btrfs_set_stack_inode_nlink(inode_item, 1);
+ btrfs_set_stack_inode_nbytes(inode_item, cfg->nodesize);
+ btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
+ btrfs_set_root_refs(&root_item, 1);
+ btrfs_set_root_used(&root_item, cfg->nodesize);
+ btrfs_set_root_generation(&root_item, 1);
+ btrfs_set_root_bytenr(&root_item, bytenr);
+
+ memset(&disk_key, 0, sizeof(disk_key));
+ btrfs_set_disk_key_type(&disk_key, BTRFS_ROOT_ITEM_KEY);
+ btrfs_set_disk_key_objectid(&disk_key, objectid);
+ btrfs_set_disk_key_offset(&disk_key, 0);
+
+ btrfs_set_item_key(buf, &disk_key, *slot);
+ btrfs_set_item_offset(buf, btrfs_item_nr(*slot), *itemoff);
+ btrfs_set_item_size(buf, btrfs_item_nr(*slot), sizeof(root_item));
+ write_extent_buffer(buf, &root_item,
+ btrfs_item_ptr_offset(buf, *slot),
+ sizeof(root_item));
+ (*slot)++;
+}
+
+static int setup_temp_root_tree(int fd, struct btrfs_mkfs_config *cfg,
+ u64 root_bytenr, u64 extent_bytenr,
+ u64 dev_bytenr, u64 fs_bytenr, u64 csum_bytenr)
+{
+ struct extent_buffer *buf = NULL;
+ u32 itemoff = __BTRFS_LEAF_DATA_SIZE(cfg->nodesize);
+ int slot = 0;
+ int ret;
+
+ /*
+ * Provided bytenr must in ascending order, or tree root will have a
+ * bad key order.
+ */
+ if (!(root_bytenr < extent_bytenr && extent_bytenr < dev_bytenr &&
+ dev_bytenr < fs_bytenr && fs_bytenr < csum_bytenr)) {
+ error("bad tree bytenr order: "
+ "root < extent %llu < %llu, "
+ "extent < dev %llu < %llu, "
+ "dev < fs %llu < %llu, "
+ "fs < csum %llu < %llu",
+ (unsigned long long)root_bytenr,
+ (unsigned long long)extent_bytenr,
+ (unsigned long long)extent_bytenr,
+ (unsigned long long)dev_bytenr,
+ (unsigned long long)dev_bytenr,
+ (unsigned long long)fs_bytenr,
+ (unsigned long long)fs_bytenr,
+ (unsigned long long)csum_bytenr);
+ return -EINVAL;
+ }
+ buf = malloc(sizeof(*buf) + cfg->nodesize);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = setup_temp_extent_buffer(buf, cfg, root_bytenr,
+ BTRFS_ROOT_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+
+ insert_temp_root_item(buf, cfg, &slot, &itemoff,
+ BTRFS_EXTENT_TREE_OBJECTID, extent_bytenr);
+ insert_temp_root_item(buf, cfg, &slot, &itemoff,
+ BTRFS_DEV_TREE_OBJECTID, dev_bytenr);
+ insert_temp_root_item(buf, cfg, &slot, &itemoff,
+ BTRFS_FS_TREE_OBJECTID, fs_bytenr);
+ insert_temp_root_item(buf, cfg, &slot, &itemoff,
+ BTRFS_CSUM_TREE_OBJECTID, csum_bytenr);
+
+ ret = write_temp_extent_buffer(fd, buf, root_bytenr);
+out:
+ free(buf);
+ return ret;
+}
+
+static int insert_temp_dev_item(int fd, struct extent_buffer *buf,
+ struct btrfs_mkfs_config *cfg,
+ int *slot, u32 *itemoff)
+{
+ struct btrfs_disk_key disk_key;
+ struct btrfs_dev_item *dev_item;
+ char super_buf[BTRFS_SUPER_INFO_SIZE];
+ unsigned char dev_uuid[BTRFS_UUID_SIZE];
+ unsigned char fsid[BTRFS_FSID_SIZE];
+ struct btrfs_super_block *super = (struct btrfs_super_block *)super_buf;
+ int ret;
+
+ ret = pread(fd, super_buf, BTRFS_SUPER_INFO_SIZE, cfg->super_bytenr);
+ if (ret < BTRFS_SUPER_INFO_SIZE) {
+ ret = (ret < 0 ? -errno : -EIO);
+ goto out;
+ }
+
+ btrfs_set_header_nritems(buf, *slot + 1);
+ (*itemoff) -= sizeof(*dev_item);
+ /* setup device item 1, 0 is for replace case */
+ btrfs_set_disk_key_type(&disk_key, BTRFS_DEV_ITEM_KEY);
+ btrfs_set_disk_key_objectid(&disk_key, BTRFS_DEV_ITEMS_OBJECTID);
+ btrfs_set_disk_key_offset(&disk_key, 1);
+ btrfs_set_item_key(buf, &disk_key, *slot);
+ btrfs_set_item_offset(buf, btrfs_item_nr(*slot), *itemoff);
+ btrfs_set_item_size(buf, btrfs_item_nr(*slot), sizeof(*dev_item));
+
+ dev_item = btrfs_item_ptr(buf, *slot, struct btrfs_dev_item);
+ /* Generate device uuid */
+ uuid_generate(dev_uuid);
+ write_extent_buffer(buf, dev_uuid,
+ (unsigned long)btrfs_device_uuid(dev_item),
+ BTRFS_UUID_SIZE);
+ uuid_parse(cfg->fs_uuid, fsid);
+ write_extent_buffer(buf, fsid,
+ (unsigned long)btrfs_device_fsid(dev_item),
+ BTRFS_FSID_SIZE);
+ btrfs_set_device_id(buf, dev_item, 1);
+ btrfs_set_device_generation(buf, dev_item, 0);
+ btrfs_set_device_total_bytes(buf, dev_item, cfg->num_bytes);
+ /*
+ * The number must match the initial SYSTEM and META chunk size
+ */
+ btrfs_set_device_bytes_used(buf, dev_item,
+ BTRFS_MKFS_SYSTEM_GROUP_SIZE +
+ BTRFS_CONVERT_META_GROUP_SIZE);
+ btrfs_set_device_io_align(buf, dev_item, cfg->sectorsize);
+ btrfs_set_device_io_width(buf, dev_item, cfg->sectorsize);
+ btrfs_set_device_sector_size(buf, dev_item, cfg->sectorsize);
+ btrfs_set_device_type(buf, dev_item, 0);
+
+ /* Super dev_item is not complete, copy the complete one to sb */
+ read_extent_buffer(buf, &super->dev_item, (unsigned long)dev_item,
+ sizeof(*dev_item));
+ ret = write_temp_super(fd, super, cfg->super_bytenr);
+ (*slot)++;
+out:
+ return ret;
+}
+
+static int insert_temp_chunk_item(int fd, struct extent_buffer *buf,
+ struct btrfs_mkfs_config *cfg,
+ int *slot, u32 *itemoff, u64 start, u64 len,
+ u64 type)
+{
+ struct btrfs_chunk *chunk;
+ struct btrfs_disk_key disk_key;
+ char super_buf[BTRFS_SUPER_INFO_SIZE];
+ struct btrfs_super_block *sb = (struct btrfs_super_block *)super_buf;
+ int ret = 0;
+
+ ret = pread(fd, super_buf, BTRFS_SUPER_INFO_SIZE,
+ cfg->super_bytenr);
+ if (ret < BTRFS_SUPER_INFO_SIZE) {
+ ret = (ret < 0 ? ret : -EIO);
+ return ret;
+ }
+
+ btrfs_set_header_nritems(buf, *slot + 1);
+ (*itemoff) -= btrfs_chunk_item_size(1);
+ btrfs_set_disk_key_type(&disk_key, BTRFS_CHUNK_ITEM_KEY);
+ btrfs_set_disk_key_objectid(&disk_key, BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+ btrfs_set_disk_key_offset(&disk_key, start);
+ btrfs_set_item_key(buf, &disk_key, *slot);
+ btrfs_set_item_offset(buf, btrfs_item_nr(*slot), *itemoff);
+ btrfs_set_item_size(buf, btrfs_item_nr(*slot),
+ btrfs_chunk_item_size(1));
+
+ chunk = btrfs_item_ptr(buf, *slot, struct btrfs_chunk);
+ btrfs_set_chunk_length(buf, chunk, len);
+ btrfs_set_chunk_owner(buf, chunk, BTRFS_EXTENT_TREE_OBJECTID);
+ btrfs_set_chunk_stripe_len(buf, chunk, 64 * 1024);
+ btrfs_set_chunk_type(buf, chunk, type);
+ btrfs_set_chunk_io_align(buf, chunk, cfg->sectorsize);
+ btrfs_set_chunk_io_width(buf, chunk, cfg->sectorsize);
+ btrfs_set_chunk_sector_size(buf, chunk, cfg->sectorsize);
+ btrfs_set_chunk_num_stripes(buf, chunk, 1);
+ /* TODO: Support DUP profile for system chunk */
+ btrfs_set_stripe_devid_nr(buf, chunk, 0, 1);
+ /* We are doing 1:1 mapping, so start is its dev offset */
+ btrfs_set_stripe_offset_nr(buf, chunk, 0, start);
+ write_extent_buffer(buf, &sb->dev_item.uuid,
+ (unsigned long)btrfs_stripe_dev_uuid_nr(chunk, 0),
+ BTRFS_UUID_SIZE);
+ (*slot)++;
+
+ /*
+ * If it's system chunk, also copy it to super block.
+ */
+ if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
+ char *cur;
+
+ cur = (char *)sb->sys_chunk_array + sb->sys_chunk_array_size;
+ memcpy(cur, &disk_key, sizeof(disk_key));
+ cur += sizeof(disk_key);
+ read_extent_buffer(buf, cur, (unsigned long int)chunk,
+ btrfs_chunk_item_size(1));
+ sb->sys_chunk_array_size += btrfs_chunk_item_size(1) +
+ sizeof(disk_key);
+
+ ret = write_temp_super(fd, sb, cfg->super_bytenr);
+ }
+ return ret;
+}
+
+static int setup_temp_chunk_tree(int fd, struct btrfs_mkfs_config *cfg,
+ u64 sys_chunk_start, u64 meta_chunk_start,
+ u64 chunk_bytenr)
+{
+ struct extent_buffer *buf = NULL;
+ u32 itemoff = __BTRFS_LEAF_DATA_SIZE(cfg->nodesize);
+ int slot = 0;
+ int ret;
+
+ /* Must ensure SYS chunk starts before META chunk */
+ if (meta_chunk_start < sys_chunk_start) {
+ error("wrong chunk order: meta < system %llu < %llu",
+ (unsigned long long)meta_chunk_start,
+ (unsigned long long)sys_chunk_start);
+ return -EINVAL;
+ }
+ buf = malloc(sizeof(*buf) + cfg->nodesize);
+ if (!buf)
+ return -ENOMEM;
+ ret = setup_temp_extent_buffer(buf, cfg, chunk_bytenr,
+ BTRFS_CHUNK_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+
+ ret = insert_temp_dev_item(fd, buf, cfg, &slot, &itemoff);
+ if (ret < 0)
+ goto out;
+ ret = insert_temp_chunk_item(fd, buf, cfg, &slot, &itemoff,
+ sys_chunk_start,
+ BTRFS_MKFS_SYSTEM_GROUP_SIZE,
+ BTRFS_BLOCK_GROUP_SYSTEM);
+ if (ret < 0)
+ goto out;
+ ret = insert_temp_chunk_item(fd, buf, cfg, &slot, &itemoff,
+ meta_chunk_start,
+ BTRFS_CONVERT_META_GROUP_SIZE,
+ BTRFS_BLOCK_GROUP_METADATA);
+ if (ret < 0)
+ goto out;
+ ret = write_temp_extent_buffer(fd, buf, chunk_bytenr);
+
+out:
+ free(buf);
+ return ret;
+}
+
+static void insert_temp_dev_extent(struct extent_buffer *buf,
+ int *slot, u32 *itemoff, u64 start, u64 len)
+{
+ struct btrfs_dev_extent *dev_extent;
+ struct btrfs_disk_key disk_key;
+
+ btrfs_set_header_nritems(buf, *slot + 1);
+ (*itemoff) -= sizeof(*dev_extent);
+ btrfs_set_disk_key_type(&disk_key, BTRFS_DEV_EXTENT_KEY);
+ btrfs_set_disk_key_objectid(&disk_key, 1);
+ btrfs_set_disk_key_offset(&disk_key, start);
+ btrfs_set_item_key(buf, &disk_key, *slot);
+ btrfs_set_item_offset(buf, btrfs_item_nr(*slot), *itemoff);
+ btrfs_set_item_size(buf, btrfs_item_nr(*slot), sizeof(*dev_extent));
+
+ dev_extent = btrfs_item_ptr(buf, *slot, struct btrfs_dev_extent);
+ btrfs_set_dev_extent_chunk_objectid(buf, dev_extent,
+ BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+ btrfs_set_dev_extent_length(buf, dev_extent, len);
+ btrfs_set_dev_extent_chunk_offset(buf, dev_extent, start);
+ btrfs_set_dev_extent_chunk_tree(buf, dev_extent,
+ BTRFS_CHUNK_TREE_OBJECTID);
+ (*slot)++;
+}
+
+static int setup_temp_dev_tree(int fd, struct btrfs_mkfs_config *cfg,
+ u64 sys_chunk_start, u64 meta_chunk_start,
+ u64 dev_bytenr)
+{
+ struct extent_buffer *buf = NULL;
+ u32 itemoff = __BTRFS_LEAF_DATA_SIZE(cfg->nodesize);
+ int slot = 0;
+ int ret;
+
+ /* Must ensure SYS chunk starts before META chunk */
+ if (meta_chunk_start < sys_chunk_start) {
+ error("wrong chunk order: meta < system %llu < %llu",
+ (unsigned long long)meta_chunk_start,
+ (unsigned long long)sys_chunk_start);
+ return -EINVAL;
+ }
+ buf = malloc(sizeof(*buf) + cfg->nodesize);
+ if (!buf)
+ return -ENOMEM;
+ ret = setup_temp_extent_buffer(buf, cfg, dev_bytenr,
+ BTRFS_DEV_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+ insert_temp_dev_extent(buf, &slot, &itemoff, sys_chunk_start,
+ BTRFS_MKFS_SYSTEM_GROUP_SIZE);
+ insert_temp_dev_extent(buf, &slot, &itemoff, meta_chunk_start,
+ BTRFS_CONVERT_META_GROUP_SIZE);
+ ret = write_temp_extent_buffer(fd, buf, dev_bytenr);
+out:
+ free(buf);
+ return ret;
+}
+
+static int setup_temp_fs_tree(int fd, struct btrfs_mkfs_config *cfg,
+ u64 fs_bytenr)
+{
+ struct extent_buffer *buf = NULL;
+ int ret;
+
+ buf = malloc(sizeof(*buf) + cfg->nodesize);
+ if (!buf)
+ return -ENOMEM;
+ ret = setup_temp_extent_buffer(buf, cfg, fs_bytenr,
+ BTRFS_FS_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+ /*
+ * Temporary fs tree is completely empty.
+ */
+ ret = write_temp_extent_buffer(fd, buf, fs_bytenr);
+out:
+ free(buf);
+ return ret;
+}
+
+static int setup_temp_csum_tree(int fd, struct btrfs_mkfs_config *cfg,
+ u64 csum_bytenr)
+{
+ struct extent_buffer *buf = NULL;
+ int ret;
+
+ buf = malloc(sizeof(*buf) + cfg->nodesize);
+ if (!buf)
+ return -ENOMEM;
+ ret = setup_temp_extent_buffer(buf, cfg, csum_bytenr,
+ BTRFS_CSUM_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+ /*
+ * Temporary csum tree is completely empty.
+ */
+ ret = write_temp_extent_buffer(fd, buf, csum_bytenr);
+out:
+ free(buf);
+ return ret;
+}
+
+/*
+ * Insert one temporary extent item.
+ *
+ * NOTE: if skinny_metadata is not enabled, this function must be called
+ * after all other trees are initialized.
+ * Or fs without skinny-metadata will be screwed up.
+ */
+static int insert_temp_extent_item(int fd, struct extent_buffer *buf,
+ struct btrfs_mkfs_config *cfg,
+ int *slot, u32 *itemoff, u64 bytenr,
+ u64 ref_root)
+{
+ struct extent_buffer *tmp;
+ struct btrfs_extent_item *ei;
+ struct btrfs_extent_inline_ref *iref;
+ struct btrfs_disk_key disk_key;
+ struct btrfs_disk_key tree_info_key;
+ struct btrfs_tree_block_info *info;
+ int itemsize;
+ int skinny_metadata = cfg->features &
+ BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA;
+ int ret;
+
+ if (skinny_metadata)
+ itemsize = sizeof(*ei) + sizeof(*iref);
+ else
+ itemsize = sizeof(*ei) + sizeof(*iref) +
+ sizeof(struct btrfs_tree_block_info);
+
+ btrfs_set_header_nritems(buf, *slot + 1);
+ *(itemoff) -= itemsize;
+
+ if (skinny_metadata) {
+ btrfs_set_disk_key_type(&disk_key, BTRFS_METADATA_ITEM_KEY);
+ btrfs_set_disk_key_offset(&disk_key, 0);
+ } else {
+ btrfs_set_disk_key_type(&disk_key, BTRFS_EXTENT_ITEM_KEY);
+ btrfs_set_disk_key_offset(&disk_key, cfg->nodesize);
+ }
+ btrfs_set_disk_key_objectid(&disk_key, bytenr);
+
+ btrfs_set_item_key(buf, &disk_key, *slot);
+ btrfs_set_item_offset(buf, btrfs_item_nr(*slot), *itemoff);
+ btrfs_set_item_size(buf, btrfs_item_nr(*slot), itemsize);
+
+ ei = btrfs_item_ptr(buf, *slot, struct btrfs_extent_item);
+ btrfs_set_extent_refs(buf, ei, 1);
+ btrfs_set_extent_generation(buf, ei, 1);
+ btrfs_set_extent_flags(buf, ei, BTRFS_EXTENT_FLAG_TREE_BLOCK);
+
+ if (skinny_metadata) {
+ iref = (struct btrfs_extent_inline_ref *)(ei + 1);
+ } else {
+ info = (struct btrfs_tree_block_info *)(ei + 1);
+ iref = (struct btrfs_extent_inline_ref *)(info + 1);
+ }
+ btrfs_set_extent_inline_ref_type(buf, iref,
+ BTRFS_TREE_BLOCK_REF_KEY);
+ btrfs_set_extent_inline_ref_offset(buf, iref, ref_root);
+
+ (*slot)++;
+ if (skinny_metadata)
+ return 0;
+
+ /*
+ * Lastly, check the tree block key by read the tree block
+ * Since we do 1:1 mapping for convert case, we can directly
+ * read the bytenr from disk
+ */
+ tmp = malloc(sizeof(*tmp) + cfg->nodesize);
+ if (!tmp)
+ return -ENOMEM;
+ ret = setup_temp_extent_buffer(tmp, cfg, bytenr, ref_root);
+ if (ret < 0)
+ goto out;
+ ret = pread(fd, tmp->data, cfg->nodesize, bytenr);
+ if (ret < cfg->nodesize) {
+ ret = (ret < 0 ? -errno : -EIO);
+ goto out;
+ }
+ if (btrfs_header_nritems(tmp) == 0) {
+ btrfs_set_disk_key_type(&tree_info_key, 0);
+ btrfs_set_disk_key_objectid(&tree_info_key, 0);
+ btrfs_set_disk_key_offset(&tree_info_key, 0);
+ } else {
+ btrfs_item_key(tmp, &tree_info_key, 0);
+ }
+ btrfs_set_tree_block_key(buf, info, &tree_info_key);
+
+out:
+ free(tmp);
+ return ret;
+}
+
+static void insert_temp_block_group(struct extent_buffer *buf,
+ struct btrfs_mkfs_config *cfg,
+ int *slot, u32 *itemoff,
+ u64 bytenr, u64 len, u64 used, u64 flag)
+{
+ struct btrfs_block_group_item bgi;
+ struct btrfs_disk_key disk_key;
+
+ btrfs_set_header_nritems(buf, *slot + 1);
+ (*itemoff) -= sizeof(bgi);
+ btrfs_set_disk_key_type(&disk_key, BTRFS_BLOCK_GROUP_ITEM_KEY);
+ btrfs_set_disk_key_objectid(&disk_key, bytenr);
+ btrfs_set_disk_key_offset(&disk_key, len);
+ btrfs_set_item_key(buf, &disk_key, *slot);
+ btrfs_set_item_offset(buf, btrfs_item_nr(*slot), *itemoff);
+ btrfs_set_item_size(buf, btrfs_item_nr(*slot), sizeof(bgi));
+
+ btrfs_set_block_group_flags(&bgi, flag);
+ btrfs_set_block_group_used(&bgi, used);
+ btrfs_set_block_group_chunk_objectid(&bgi,
+ BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+ write_extent_buffer(buf, &bgi, btrfs_item_ptr_offset(buf, *slot),
+ sizeof(bgi));
+ (*slot)++;
+}
+
+static int setup_temp_extent_tree(int fd, struct btrfs_mkfs_config *cfg,
+ u64 chunk_bytenr, u64 root_bytenr,
+ u64 extent_bytenr, u64 dev_bytenr,
+ u64 fs_bytenr, u64 csum_bytenr)
+{
+ struct extent_buffer *buf = NULL;
+ u32 itemoff = __BTRFS_LEAF_DATA_SIZE(cfg->nodesize);
+ int slot = 0;
+ int ret;
+
+ /*
+ * We must ensure provided bytenr are in ascending order,
+ * or extent tree key order will be broken.
+ */
+ if (!(chunk_bytenr < root_bytenr && root_bytenr < extent_bytenr &&
+ extent_bytenr < dev_bytenr && dev_bytenr < fs_bytenr &&
+ fs_bytenr < csum_bytenr)) {
+ error("bad tree bytenr order: "
+ "chunk < root %llu < %llu, "
+ "root < extent %llu < %llu, "
+ "extent < dev %llu < %llu, "
+ "dev < fs %llu < %llu, "
+ "fs < csum %llu < %llu",
+ (unsigned long long)chunk_bytenr,
+ (unsigned long long)root_bytenr,
+ (unsigned long long)root_bytenr,
+ (unsigned long long)extent_bytenr,
+ (unsigned long long)extent_bytenr,
+ (unsigned long long)dev_bytenr,
+ (unsigned long long)dev_bytenr,
+ (unsigned long long)fs_bytenr,
+ (unsigned long long)fs_bytenr,
+ (unsigned long long)csum_bytenr);
+ return -EINVAL;
+ }
+ buf = malloc(sizeof(*buf) + cfg->nodesize);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = setup_temp_extent_buffer(buf, cfg, extent_bytenr,
+ BTRFS_EXTENT_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+
+ ret = insert_temp_extent_item(fd, buf, cfg, &slot, &itemoff,
+ chunk_bytenr, BTRFS_CHUNK_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+
+ insert_temp_block_group(buf, cfg, &slot, &itemoff, chunk_bytenr,
+ BTRFS_MKFS_SYSTEM_GROUP_SIZE, cfg->nodesize,
+ BTRFS_BLOCK_GROUP_SYSTEM);
+
+ ret = insert_temp_extent_item(fd, buf, cfg, &slot, &itemoff,
+ root_bytenr, BTRFS_ROOT_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+
+ /* 5 tree block used, root, extent, dev, fs and csum*/
+ insert_temp_block_group(buf, cfg, &slot, &itemoff, root_bytenr,
+ BTRFS_CONVERT_META_GROUP_SIZE, cfg->nodesize * 5,
+ BTRFS_BLOCK_GROUP_METADATA);
+
+ ret = insert_temp_extent_item(fd, buf, cfg, &slot, &itemoff,
+ extent_bytenr, BTRFS_EXTENT_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+ ret = insert_temp_extent_item(fd, buf, cfg, &slot, &itemoff,
+ dev_bytenr, BTRFS_DEV_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+ ret = insert_temp_extent_item(fd, buf, cfg, &slot, &itemoff,
+ fs_bytenr, BTRFS_FS_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+ ret = insert_temp_extent_item(fd, buf, cfg, &slot, &itemoff,
+ csum_bytenr, BTRFS_CSUM_TREE_OBJECTID);
+ if (ret < 0)
+ goto out;
+
+ ret = write_temp_extent_buffer(fd, buf, extent_bytenr);
+out:
+ free(buf);
+ return ret;
+}
+
+/*
+ * Improved version of make_btrfs().
+ *
+ * This one will
+ * 1) Do chunk allocation to avoid used data
+ * And after this function, extent type matches chunk type
+ * 2) Better structured code
+ * No super long hand written codes to initialized all tree blocks
+ * Split into small blocks and reuse codes.
+ * TODO: Reuse tree operation facilities by introducing new flags
+ */
+static int make_convert_btrfs(int fd, struct btrfs_mkfs_config *cfg,
+ struct btrfs_convert_context *cctx)
+{
+ struct cache_tree *free = &cctx->free;
+ struct cache_tree *used = &cctx->used;
+ u64 sys_chunk_start;
+ u64 meta_chunk_start;
+ /* chunk tree bytenr, in system chunk */
+ u64 chunk_bytenr;
+ /* metadata trees bytenr, in metadata chunk */
+ u64 root_bytenr;
+ u64 extent_bytenr;
+ u64 dev_bytenr;
+ u64 fs_bytenr;
+ u64 csum_bytenr;
+ int ret;
+
+ /* Shouldn't happen */
+ BUG_ON(cache_tree_empty(used));
+
+ /*
+ * reserve space for temporary superblock first
+ * Here we allocate a little larger space, to keep later
+ * free space will be STRIPE_LEN aligned
+ */
+ ret = reserve_free_space(free, BTRFS_STRIPE_LEN,
+ &cfg->super_bytenr);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * Then reserve system chunk space
+ * TODO: Change system group size depending on cctx->total_bytes.
+ * If using current 4M, it can only handle less than one TB for
+ * worst case and then run out of sys space.
+ */
+ ret = reserve_free_space(free, BTRFS_MKFS_SYSTEM_GROUP_SIZE,
+ &sys_chunk_start);
+ if (ret < 0)
+ goto out;
+ ret = reserve_free_space(free, BTRFS_CONVERT_META_GROUP_SIZE,
+ &meta_chunk_start);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * Allocated meta/sys chunks will be mapped 1:1 with device offset.
+ *
+ * Inside the allocated metadata chunk, the layout will be:
+ * | offset | contents |
+ * -------------------------------------
+ * | +0 | tree root |
+ * | +nodesize | extent root |
+ * | +nodesize * 2 | device root |
+ * | +nodesize * 3 | fs tree |
+ * | +nodesize * 4 | csum tree |
+ * -------------------------------------
+ * Inside the allocated system chunk, the layout will be:
+ * | offset | contents |
+ * -------------------------------------
+ * | +0 | chunk root |
+ * -------------------------------------
+ */
+ chunk_bytenr = sys_chunk_start;
+ root_bytenr = meta_chunk_start;
+ extent_bytenr = meta_chunk_start + cfg->nodesize;
+ dev_bytenr = meta_chunk_start + cfg->nodesize * 2;
+ fs_bytenr = meta_chunk_start + cfg->nodesize * 3;
+ csum_bytenr = meta_chunk_start + cfg->nodesize * 4;
+
+ ret = setup_temp_super(fd, cfg, root_bytenr, chunk_bytenr);
+ if (ret < 0)
+ goto out;
+
+ ret = setup_temp_root_tree(fd, cfg, root_bytenr, extent_bytenr,
+ dev_bytenr, fs_bytenr, csum_bytenr);
+ if (ret < 0)
+ goto out;
+ ret = setup_temp_chunk_tree(fd, cfg, sys_chunk_start, meta_chunk_start,
+ chunk_bytenr);
+ if (ret < 0)
+ goto out;
+ ret = setup_temp_dev_tree(fd, cfg, sys_chunk_start, meta_chunk_start,
+ dev_bytenr);
+ if (ret < 0)
+ goto out;
+ ret = setup_temp_fs_tree(fd, cfg, fs_bytenr);
+ if (ret < 0)
+ goto out;
+ ret = setup_temp_csum_tree(fd, cfg, csum_bytenr);
+ if (ret < 0)
+ goto out;
+ /*
+ * Setup extent tree last, since it may need to read tree block key
+ * for non-skinny metadata case.
+ */
+ ret = setup_temp_extent_tree(fd, cfg, chunk_bytenr, root_bytenr,
+ extent_bytenr, dev_bytenr, fs_bytenr,
+ csum_bytenr);
+out:
+ return ret;
+}
+
+/*
* @fs_uuid - if NULL, generates a UUID, returns back the new filesystem UUID
+ *
+ * The superblock signature is not valid, denotes a partially created
+ * filesystem, needs to be finalized.
*/
-int make_btrfs(int fd, struct btrfs_mkfs_config *cfg)
+int make_btrfs(int fd, struct btrfs_mkfs_config *cfg,
+ struct btrfs_convert_context *cctx)
{
struct btrfs_super_block super;
struct extent_buffer *buf;
BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA);
u64 num_bytes;
+ if (cctx)
+ return make_convert_btrfs(fd, cfg, cctx);
buf = malloc(sizeof(*buf) + max(cfg->sectorsize, cfg->nodesize));
if (!buf)
return -ENOMEM;
memset(&super, 0, sizeof(super));
num_bytes = (cfg->num_bytes / cfg->sectorsize) * cfg->sectorsize;
- if (cfg->fs_uuid && *cfg->fs_uuid) {
+ if (*cfg->fs_uuid) {
if (uuid_parse(cfg->fs_uuid, super.fsid) != 0) {
error("cannot not parse UUID: %s", cfg->fs_uuid);
ret = -EINVAL;
btrfs_set_super_bytenr(&super, cfg->blocks[0]);
btrfs_set_super_num_devices(&super, 1);
- btrfs_set_super_magic(&super, BTRFS_MAGIC);
+ btrfs_set_super_magic(&super, BTRFS_MAGIC_PARTIAL);
btrfs_set_super_generation(&super, 1);
btrfs_set_super_root(&super, cfg->blocks[1]);
btrfs_set_super_chunk_root(&super, cfg->blocks[3]);
if (!skinny_metadata)
item_size += sizeof(struct btrfs_tree_block_info);
- BUG_ON(cfg->blocks[i] < first_free);
- BUG_ON(cfg->blocks[i] < cfg->blocks[i - 1]);
+ if (cfg->blocks[i] < first_free) {
+ error("block[%d] below first free: %llu < %llu",
+ i, (unsigned long long)cfg->blocks[i],
+ (unsigned long long)first_free);
+ ret = -EINVAL;
+ goto out;
+ }
+ if (cfg->blocks[i] < cfg->blocks[i - 1]) {
+ error("blocks %d and %d in reverse order: %llu < %llu",
+ i, i - 1,
+ (unsigned long long)cfg->blocks[i],
+ (unsigned long long)cfg->blocks[i - 1]);
+ ret = -EINVAL;
+ goto out;
+ }
/* create extent item */
itemoff -= item_size;
}
/* and write out the super block */
- BUG_ON(sizeof(super) > cfg->sectorsize);
memset(buf->data, 0, BTRFS_SUPER_INFO_SIZE);
memcpy(buf->data, &super, sizeof(super));
buf->len = BTRFS_SUPER_INFO_SIZE;
}
int btrfs_add_to_fsid(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, int fd, char *path,
+ struct btrfs_root *root, int fd, const char *path,
u64 device_total_bytes, u32 io_width, u32 io_align,
u32 sectorsize)
{
device_total_bytes = (device_total_bytes / sectorsize) * sectorsize;
- device = kzalloc(sizeof(*device), GFP_NOFS);
- if (!device)
- goto err_nomem;
- buf = kzalloc(sectorsize, GFP_NOFS);
- if (!buf)
- goto err_nomem;
- BUG_ON(sizeof(*disk_super) > sectorsize);
+ device = calloc(1, sizeof(*device));
+ if (!device) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ buf = calloc(1, sectorsize);
+ if (!buf) {
+ ret = -ENOMEM;
+ goto out;
+ }
disk_super = (struct btrfs_super_block *)buf;
dev_item = &disk_super->dev_item;
device->total_ios = 0;
device->dev_root = root->fs_info->dev_root;
device->name = strdup(path);
- if (!device->name)
- goto err_nomem;
+ if (!device->name) {
+ ret = -ENOMEM;
+ goto out;
+ }
INIT_LIST_HEAD(&device->dev_list);
ret = btrfs_add_device(trans, root, device);
- BUG_ON(ret);
+ if (ret)
+ goto out;
fs_total_bytes = btrfs_super_total_bytes(super) + device_total_bytes;
btrfs_set_super_total_bytes(super, fs_total_bytes);
ret = pwrite(fd, buf, sectorsize, BTRFS_SUPER_INFO_OFFSET);
BUG_ON(ret != sectorsize);
- kfree(buf);
+ free(buf);
list_add(&device->dev_list, &root->fs_info->fs_devices->devices);
device->fs_devices = root->fs_info->fs_devices;
return 0;
-err_nomem:
- kfree(device);
- kfree(buf);
- return -ENOMEM;
+out:
+ free(device);
+ free(buf);
+ return ret;
}
static int btrfs_wipe_existing_sb(int fd)
return ret;
}
-int btrfs_prepare_device(int fd, const char *file, int zero_end,
- u64 *block_count_ret, u64 max_block_count, int discard)
+int btrfs_prepare_device(int fd, const char *file, u64 *block_count_ret,
+ u64 max_block_count, unsigned opflags)
{
u64 block_count;
struct stat st;
if (max_block_count)
block_count = min(block_count, max_block_count);
- if (discard) {
+ if (opflags & PREP_DEVICE_DISCARD) {
/*
* We intentionally ignore errors from the discard ioctl. It
* is not necessary for the mkfs functionality but just an
* optimization.
*/
if (discard_range(fd, 0, 0) == 0) {
- printf("Performing full device TRIM (%s) ...\n",
- pretty_size(block_count));
+ if (opflags & PREP_DEVICE_VERBOSE)
+ printf("Performing full device TRIM (%s) ...\n",
+ pretty_size(block_count));
discard_blocks(fd, 0, block_count);
}
}
for (i = 0 ; !ret && i < BTRFS_SUPER_MIRROR_MAX; i++)
ret = zero_dev_clamped(fd, btrfs_sb_offset(i),
BTRFS_SUPER_INFO_SIZE, block_count);
- if (!ret && zero_end)
+ if (!ret && (opflags & PREP_DEVICE_ZERO_END))
ret = zero_dev_clamped(fd, block_count - ZERO_DEV_BYTES,
ZERO_DEV_BYTES, block_count);
/* scan the initial device */
ret = btrfs_scan_one_device(fd, file, &fs_devices_mnt,
- &total_devs, BTRFS_SUPER_INFO_OFFSET, 0);
+ &total_devs, BTRFS_SUPER_INFO_OFFSET, SBREAD_DEFAULT);
is_btrfs = (ret >= 0);
/* scan other devices */
ret = 0;
disk_super = (struct btrfs_super_block *)buf;
- if (btrfs_super_magic(disk_super) != BTRFS_MAGIC)
+ /*
+ * Accept devices from the same filesystem, allow partially created
+ * structures.
+ */
+ if (btrfs_super_magic(disk_super) != BTRFS_MAGIC &&
+ btrfs_super_magic(disk_super) != BTRFS_MAGIC_PARTIAL)
goto brelse;
if (!memcmp(disk_super->fsid, root->fs_info->super_copy->fsid,
if (fd < 0)
goto err;
ret = lookup_ino_rootid(fd, &id);
+ if (ret)
+ error("failed to lookup root id: %s", strerror(-ret));
close(fd);
if (ret < 0)
goto err;
*
* Returns 0 on success, or a negative errno.
*/
-int get_fs_info(char *path, struct btrfs_ioctl_fs_info_args *fi_args,
+int get_fs_info(const char *path, struct btrfs_ioctl_fs_info_args *fi_args,
struct btrfs_ioctl_dev_info_args **di_ret)
{
int fd = -1;
u64 dev_cnt, int mixed, int ssd)
{
u64 allowed = 0;
+ u64 profile = metadata_profile | data_profile;
switch (dev_cnt) {
default:
allowed |= BTRFS_BLOCK_GROUP_DUP;
}
- if (dev_cnt > 1 &&
- ((metadata_profile | data_profile) & BTRFS_BLOCK_GROUP_DUP)) {
+ if (dev_cnt > 1 && profile & BTRFS_BLOCK_GROUP_DUP) {
warning("DUP is not recommended on filesystem with multiple devices");
}
if (metadata_profile & ~allowed) {
return 1;
}
+ if (dev_cnt == 3 && profile & BTRFS_BLOCK_GROUP_RAID6) {
+ warning("RAID6 is not recommended on filesystem with 3 devices only");
+ }
+ if (dev_cnt == 2 && profile & BTRFS_BLOCK_GROUP_RAID5) {
+ warning("RAID5 is not recommended on filesystem with 2 devices only");
+ }
warning_on(!mixed && (data_profile & BTRFS_BLOCK_GROUP_DUP) && ssd,
"DUP may not actually lead to 2 copies on the device, see manual page");
continue;
}
ret = btrfs_scan_one_device(fd, path, &tmp_devices,
- &num_devices, BTRFS_SUPER_INFO_OFFSET, 0);
+ &num_devices, BTRFS_SUPER_INFO_OFFSET,
+ SBREAD_DEFAULT);
if (ret) {
error("cannot scan %s: %s", path, strerror(-ret));
close (fd);
args.objectid = BTRFS_FIRST_FREE_OBJECTID;
ret = ioctl(fd, BTRFS_IOC_INO_LOOKUP, &args);
- if (ret < 0) {
- error("failed to lookup root id: %s", strerror(errno));
- return ret;
- }
+ if (ret < 0)
+ return -errno;
*rootid = args.treeid;
}
}
+/*
+ * Same as clean_args_no_options but pass through arguments that could look
+ * like short options. Eg. reisze which takes a negative resize argument like
+ * '-123M' .
+ *
+ * This accepts only two forms:
+ * - "-- option1 option2 ..."
+ * - "option1 option2 ..."
+ */
+void clean_args_no_options_relaxed(int argc, char *argv[], const char * const *usagestr)
+{
+ if (argc <= 1)
+ return;
+
+ if (strcmp(argv[1], "--") == 0)
+ optind = 2;
+}
+
/* Subvolume helper functions */
/*
* test if name is a correct subvolume name
projects / platform / upstream / btrfs-progs.git / blobdiff