diff options
author | Dimitri John Ledkov <xnox@ubuntu.com> | 2017-07-31 14:54:24 +0100 |
---|---|---|
committer | Dimitri John Ledkov <xnox@ubuntu.com> | 2017-07-31 14:54:24 +0100 |
commit | 6a0440391da7a99ffab94ccc66264af9b5f3ce34 (patch) | |
tree | 1c7cf4f07b08c4965ab19819ebce367be16fb980 /convert | |
parent | 5f2e2384443a09e3f1fec71940e9e32b70789102 (diff) |
New upstream release.
Diffstat (limited to 'convert')
-rw-r--r-- | convert/Makefile | 7 | ||||
-rw-r--r-- | convert/common.c | 884 | ||||
-rw-r--r-- | convert/common.h | 56 | ||||
-rw-r--r-- | convert/main.c | 2269 | ||||
-rw-r--r-- | convert/source-ext2.c | 886 | ||||
-rw-r--r-- | convert/source-ext2.h | 113 | ||||
-rw-r--r-- | convert/source-fs.c | 280 | ||||
-rw-r--r-- | convert/source-fs.h | 118 |
8 files changed, 2854 insertions, 1759 deletions
diff --git a/convert/Makefile b/convert/Makefile new file mode 100644 index 00000000..66dd7d0b --- /dev/null +++ b/convert/Makefile @@ -0,0 +1,7 @@ +include ../Makefile.inc + +all: + $(MAKE) -C .. btrfs-convert + +clean: + -$(RM) -f -- *.o *.o.d diff --git a/convert/common.c b/convert/common.c new file mode 100644 index 00000000..3860f3b9 --- /dev/null +++ b/convert/common.c @@ -0,0 +1,884 @@ +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +#include <unistd.h> +#include <uuid/uuid.h> +#include "disk-io.h" +#include "volumes.h" +#include "utils.h" +#include "mkfs/common.h" +#include "convert/common.h" + +#define BTRFS_CONVERT_META_GROUP_SIZE SZ_32M + +/* + * 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((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); + super->__unused_leafsize = cpu_to_le32(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; +} + +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_flag(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 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)++; +} + +/* + * Setup an extent buffer for tree block. + */ +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; +} + +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, BTRFS_STRIPE_LEN); + 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; + u32 array_size; + + cur = (char *)sb->sys_chunk_array + + btrfs_super_sys_array_size(sb); + 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)); + array_size = btrfs_super_sys_array_size(sb); + array_size += btrfs_chunk_item_size(1) + + sizeof(disk_key); + btrfs_set_super_sys_array_size(sb, array_size); + + 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 + */ +int make_convert_btrfs(int fd, struct btrfs_mkfs_config *cfg, + struct btrfs_convert_context *cctx) +{ + struct cache_tree *free_space = &cctx->free_space; + struct cache_tree *used_space = &cctx->used_space; + 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; + + /* Source filesystem must be opened, checked and analyzed in advance */ + ASSERT(!cache_tree_empty(used_space)); + + /* + * 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_space, 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_space, BTRFS_MKFS_SYSTEM_GROUP_SIZE, + &sys_chunk_start); + if (ret < 0) + goto out; + ret = reserve_free_space(free_space, 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; +} + diff --git a/convert/common.h b/convert/common.h new file mode 100644 index 00000000..2f4ea485 --- /dev/null +++ b/convert/common.h @@ -0,0 +1,56 @@ +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +/* + * Defines and function declarations for users of the mkfs API, no internal + * defintions. + */ + +#ifndef __BTRFS_CONVERT_COMMON_H__ +#define __BTRFS_CONVERT_COMMON_H__ + +#include "kerncompat.h" +#include "common-defs.h" +#include "extent-cache.h" + +struct btrfs_mkfs_config; + +struct btrfs_convert_context { + u32 blocksize; + u64 first_data_block; + u64 block_count; + u64 inodes_count; + u64 free_inodes_count; + u64 total_bytes; + char *volume_name; + const struct btrfs_convert_operations *convert_ops; + + /* The accurate used space of old filesystem */ + struct cache_tree used_space; + + /* Batched ranges which must be covered by data chunks */ + struct cache_tree data_chunks; + + /* Free space which is not covered by data_chunks */ + struct cache_tree free_space; + + void *fs_data; +}; + +int make_convert_btrfs(int fd, struct btrfs_mkfs_config *cfg, + struct btrfs_convert_context *cctx); + +#endif diff --git a/convert/main.c b/convert/main.c index 8d9f29fa..0deccd9c 100644 --- a/convert/main.c +++ b/convert/main.c @@ -16,69 +16,116 @@ * Boston, MA 021110-1307, USA. */ +/* + * Btrfs convert design: + * + * The overall design of btrfs convert is like the following: + * + * |<------------------Old fs----------------------------->| + * |<- used ->| |<- used ->| |<- used ->| + * || + * \/ + * |<---------------Btrfs fs------------------------------>| + * |<- Old data chunk ->|< new chunk (D/M/S)>|<- ODC ->| + * |<-Old-FE->| |<-Old-FE->|<- Btrfs extents ->|<-Old-FE->| + * + * ODC = Old data chunk, btrfs chunks containing old fs data + * Mapped 1:1 (logical address == device offset) + * Old-FE = file extents pointing to old fs. + * + * So old fs used space is (mostly) kept as is, while btrfs will insert + * its chunk (Data/Meta/Sys) into large enough free space. + * In this way, we can create different profiles for metadata/data for + * converted fs. + * + * We must reserve and relocate 3 ranges for btrfs: + * * [0, 1M) - area never used for any data except the first + * superblock + * * [btrfs_sb_offset(1), +64K) - 1st superblock backup copy + * * [btrfs_sb_offset(2), +64K) - 2nd, dtto + * + * Most work is spent handling corner cases around these reserved ranges. + * + * Detailed workflow is: + * 1) Scan old fs used space and calculate data chunk layout + * 1.1) Scan old fs + * We can a map used space of old fs + * + * 1.2) Calculate data chunk layout - this is the hard part + * New data chunks must meet 3 conditions using result fomr 1.1 + * a. Large enough to be a chunk + * b. Doesn't intersect reserved ranges + * c. Covers all the remaining old fs used space + * + * NOTE: This can be simplified if we don't need to handle backup supers + * + * 1.3) Calculate usable space for new btrfs chunks + * Btrfs chunk usable space must meet 3 conditions using result from 1.2 + * a. Large enough to be a chunk + * b. Doesn't intersect reserved ranges + * c. Doesn't cover any data chunks in 1.1 + * + * 2) Create basic btrfs filesystem structure + * Initial metadata and sys chunks are inserted in the first availabe + * space found in step 1.3 + * Then insert all data chunks into the basic btrfs + * + * 3) Create convert image + * We need to relocate reserved ranges here. + * After this step, the convert image is done, and we can use the image + * as reflink source to create old files + * + * 4) Iterate old fs to create files + * We just reflink file extents from old fs to newly created files on + * btrfs. + */ + #include "kerncompat.h" -#include <sys/ioctl.h> -#include <sys/mount.h> #include <stdio.h> #include <stdlib.h> #include <sys/types.h> -#include <sys/stat.h> #include <fcntl.h> #include <unistd.h> -#include <uuid/uuid.h> -#include <linux/limits.h> #include <getopt.h> +#include <pthread.h> +#include <stdbool.h> #include "ctree.h" #include "disk-io.h" #include "volumes.h" #include "transaction.h" -#include "crc32c.h" #include "utils.h" #include "task-utils.h" +#include "help.h" +#include "mkfs/common.h" +#include "convert/common.h" +#include "convert/source-fs.h" +#include "fsfeatures.h" -#if BTRFSCONVERT_EXT2 -#include <ext2fs/ext2_fs.h> -#include <ext2fs/ext2fs.h> -#include <ext2fs/ext2_ext_attr.h> - -#define INO_OFFSET (BTRFS_FIRST_FREE_OBJECTID - EXT2_ROOT_INO) - -/* - * Compatibility code for e2fsprogs 1.41 which doesn't support RO compat flag - * BIGALLOC. - * Unlike normal RO compat flag, BIGALLOC affects how e2fsprogs check used - * space, and btrfs-convert heavily relies on it. - */ -#ifdef HAVE_OLD_E2FSPROGS -#define EXT2FS_CLUSTER_RATIO(fs) (1) -#define EXT2_CLUSTERS_PER_GROUP(s) (EXT2_BLOCKS_PER_GROUP(s)) -#define EXT2FS_B2C(fs, blk) (blk) -#endif +const struct btrfs_convert_operations ext2_convert_ops; +static const struct btrfs_convert_operations *convert_operations[] = { +#if BTRFSCONVERT_EXT2 + &ext2_convert_ops, #endif - -#define CONV_IMAGE_SUBVOL_OBJECTID BTRFS_FIRST_FREE_OBJECTID - -struct task_ctx { - uint32_t max_copy_inodes; - uint32_t cur_copy_inodes; - struct task_info *info; }; static void *print_copied_inodes(void *p) { struct task_ctx *priv = p; const char work_indicator[] = { '.', 'o', 'O', 'o' }; - uint32_t count = 0; + u64 count = 0; task_period_start(priv->info, 1000 /* 1s */); while (1) { count++; - printf("copy inodes [%c] [%10d/%10d]\r", - work_indicator[count % 4], priv->cur_copy_inodes, - priv->max_copy_inodes); + pthread_mutex_lock(&priv->mutex); + printf("copy inodes [%c] [%10llu/%10llu]\r", + work_indicator[count % 4], + (unsigned long long)priv->cur_copy_inodes, + (unsigned long long)priv->max_copy_inodes); + pthread_mutex_unlock(&priv->mutex); fflush(stdout); task_period_wait(priv->info); } @@ -94,38 +141,11 @@ static int after_copied_inodes(void *p) return 0; } -struct btrfs_convert_context; -struct btrfs_convert_operations { - const char *name; - int (*open_fs)(struct btrfs_convert_context *cctx, const char *devname); - int (*read_used_space)(struct btrfs_convert_context *cctx); - int (*copy_inodes)(struct btrfs_convert_context *cctx, - struct btrfs_root *root, int datacsum, - int packing, int noxattr, struct task_ctx *p); - void (*close_fs)(struct btrfs_convert_context *cctx); - int (*check_state)(struct btrfs_convert_context *cctx); -}; - -static void init_convert_context(struct btrfs_convert_context *cctx) -{ - cache_tree_init(&cctx->used); - cache_tree_init(&cctx->data_chunks); - cache_tree_init(&cctx->free); -} - -static void clean_convert_context(struct btrfs_convert_context *cctx) -{ - free_extent_cache_tree(&cctx->used); - free_extent_cache_tree(&cctx->data_chunks); - free_extent_cache_tree(&cctx->free); -} - static inline int copy_inodes(struct btrfs_convert_context *cctx, - struct btrfs_root *root, int datacsum, - int packing, int noxattr, struct task_ctx *p) + struct btrfs_root *root, u32 convert_flags, + struct task_ctx *p) { - return cctx->convert_ops->copy_inodes(cctx, root, datacsum, packing, - noxattr, p); + return cctx->convert_ops->copy_inodes(cctx, root, convert_flags, p); } static inline void convert_close_fs(struct btrfs_convert_context *cctx) @@ -138,72 +158,11 @@ static inline int convert_check_state(struct btrfs_convert_context *cctx) return cctx->convert_ops->check_state(cctx); } -static int intersect_with_sb(u64 bytenr, u64 num_bytes) -{ - int i; - u64 offset; - - for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { - offset = btrfs_sb_offset(i); - offset &= ~((u64)BTRFS_STRIPE_LEN - 1); - - if (bytenr < offset + BTRFS_STRIPE_LEN && - bytenr + num_bytes > offset) - return 1; - } - return 0; -} - -static int convert_insert_dirent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - const char *name, size_t name_len, - u64 dir, u64 objectid, - u8 file_type, u64 index_cnt, - struct btrfs_inode_item *inode) -{ - int ret; - u64 inode_size; - struct btrfs_key location = { - .objectid = objectid, - .offset = 0, - .type = BTRFS_INODE_ITEM_KEY, - }; - - ret = btrfs_insert_dir_item(trans, root, name, name_len, - dir, &location, file_type, index_cnt); - if (ret) - return ret; - ret = btrfs_insert_inode_ref(trans, root, name, name_len, - objectid, dir, index_cnt); - if (ret) - return ret; - inode_size = btrfs_stack_inode_size(inode) + name_len * 2; - btrfs_set_stack_inode_size(inode, inode_size); - - return 0; -} - -static int read_disk_extent(struct btrfs_root *root, u64 bytenr, - u32 num_bytes, char *buffer) -{ - int ret; - struct btrfs_fs_devices *fs_devs = root->fs_info->fs_devices; - - ret = pread(fs_devs->latest_bdev, buffer, num_bytes, bytenr); - if (ret != num_bytes) - goto fail; - ret = 0; -fail: - if (ret > 0) - ret = -1; - return ret; -} - static int csum_disk_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 disk_bytenr, u64 num_bytes) { - u32 blocksize = root->sectorsize; + u32 blocksize = root->fs_info->sectorsize; u64 offset; char *buffer; int ret = 0; @@ -228,198 +187,12 @@ static int csum_disk_extent(struct btrfs_trans_handle *trans, return ret; } -struct blk_iterate_data { - struct btrfs_trans_handle *trans; - struct btrfs_root *root; - struct btrfs_root *convert_root; - struct btrfs_inode_item *inode; - u64 convert_ino; - u64 objectid; - u64 first_block; - u64 disk_block; - u64 num_blocks; - u64 boundary; - int checksum; - int errcode; -}; - -static void init_blk_iterate_data(struct blk_iterate_data *data, - struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct btrfs_inode_item *inode, - u64 objectid, int checksum) -{ - struct btrfs_key key; - - data->trans = trans; - data->root = root; - data->inode = inode; - data->objectid = objectid; - data->first_block = 0; - data->disk_block = 0; - data->num_blocks = 0; - data->boundary = (u64)-1; - data->checksum = checksum; - data->errcode = 0; - - key.objectid = CONV_IMAGE_SUBVOL_OBJECTID; - key.type = BTRFS_ROOT_ITEM_KEY; - key.offset = (u64)-1; - data->convert_root = btrfs_read_fs_root(root->fs_info, &key); - /* Impossible as we just opened it before */ - BUG_ON(!data->convert_root || IS_ERR(data->convert_root)); - data->convert_ino = BTRFS_FIRST_FREE_OBJECTID + 1; -} - -/* - * Record a file extent in original filesystem into btrfs one. - * The special point is, old disk_block can point to a reserved range. - * So here, we don't use disk_block directly but search convert_root - * to get the real disk_bytenr. - */ -static int record_file_blocks(struct blk_iterate_data *data, - u64 file_block, u64 disk_block, u64 num_blocks) -{ - int ret = 0; - struct btrfs_root *root = data->root; - struct btrfs_root *convert_root = data->convert_root; - struct btrfs_path path; - u64 file_pos = file_block * root->sectorsize; - u64 old_disk_bytenr = disk_block * root->sectorsize; - u64 num_bytes = num_blocks * root->sectorsize; - u64 cur_off = old_disk_bytenr; - - /* Hole, pass it to record_file_extent directly */ - if (old_disk_bytenr == 0) - return btrfs_record_file_extent(data->trans, root, - data->objectid, data->inode, file_pos, 0, - num_bytes); - - btrfs_init_path(&path); - - /* - * Search real disk bytenr from convert root - */ - while (cur_off < old_disk_bytenr + num_bytes) { - struct btrfs_key key; - struct btrfs_file_extent_item *fi; - struct extent_buffer *node; - int slot; - u64 extent_disk_bytenr; - u64 extent_num_bytes; - u64 real_disk_bytenr; - u64 cur_len; - - key.objectid = data->convert_ino; - key.type = BTRFS_EXTENT_DATA_KEY; - key.offset = cur_off; - - ret = btrfs_search_slot(NULL, convert_root, &key, &path, 0, 0); - if (ret < 0) - break; - if (ret > 0) { - ret = btrfs_previous_item(convert_root, &path, - data->convert_ino, - BTRFS_EXTENT_DATA_KEY); - if (ret < 0) - break; - if (ret > 0) { - ret = -ENOENT; - break; - } - } - node = path.nodes[0]; - slot = path.slots[0]; - btrfs_item_key_to_cpu(node, &key, slot); - BUG_ON(key.type != BTRFS_EXTENT_DATA_KEY || - key.objectid != data->convert_ino || - key.offset > cur_off); - fi = btrfs_item_ptr(node, slot, struct btrfs_file_extent_item); - extent_disk_bytenr = btrfs_file_extent_disk_bytenr(node, fi); - extent_num_bytes = btrfs_file_extent_num_bytes(node, fi); - BUG_ON(cur_off - key.offset >= extent_num_bytes); - btrfs_release_path(&path); - - if (extent_disk_bytenr) - real_disk_bytenr = cur_off - key.offset + - extent_disk_bytenr; - else - real_disk_bytenr = 0; - cur_len = min(key.offset + extent_num_bytes, - old_disk_bytenr + num_bytes) - cur_off; - ret = btrfs_record_file_extent(data->trans, data->root, - data->objectid, data->inode, file_pos, - real_disk_bytenr, cur_len); - if (ret < 0) - break; - cur_off += cur_len; - file_pos += cur_len; - - /* - * No need to care about csum - * As every byte of old fs image is calculated for csum, no - * need to waste CPU cycles now. - */ - } - btrfs_release_path(&path); - return ret; -} - -static int block_iterate_proc(u64 disk_block, u64 file_block, - struct blk_iterate_data *idata) -{ - int ret = 0; - int sb_region; - int do_barrier; - struct btrfs_root *root = idata->root; - struct btrfs_block_group_cache *cache; - u64 bytenr = disk_block * root->sectorsize; - - sb_region = intersect_with_sb(bytenr, root->sectorsize); - do_barrier = sb_region || disk_block >= idata->boundary; - if ((idata->num_blocks > 0 && do_barrier) || - (file_block > idata->first_block + idata->num_blocks) || - (disk_block != idata->disk_block + idata->num_blocks)) { - if (idata->num_blocks > 0) { - ret = record_file_blocks(idata, idata->first_block, - idata->disk_block, - idata->num_blocks); - if (ret) - goto fail; - idata->first_block += idata->num_blocks; - idata->num_blocks = 0; - } - if (file_block > idata->first_block) { - ret = record_file_blocks(idata, idata->first_block, - 0, file_block - idata->first_block); - if (ret) - goto fail; - } - - if (sb_region) { - bytenr += BTRFS_STRIPE_LEN - 1; - bytenr &= ~((u64)BTRFS_STRIPE_LEN - 1); - } else { - cache = btrfs_lookup_block_group(root->fs_info, bytenr); - BUG_ON(!cache); - bytenr = cache->key.objectid + cache->key.offset; - } - - idata->first_block = file_block; - idata->disk_block = disk_block; - idata->boundary = bytenr / root->sectorsize; - } - idata->num_blocks++; -fail: - return ret; -} - static int create_image_file_range(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct cache_tree *used, struct btrfs_inode_item *inode, u64 ino, u64 bytenr, u64 *ret_len, - int datacsum) + u32 convert_flags) { struct cache_extent *cache; struct btrfs_block_group_cache *bg_cache; @@ -427,13 +200,14 @@ static int create_image_file_range(struct btrfs_trans_handle *trans, u64 disk_bytenr; int i; int ret; + u32 datacsum = convert_flags & CONVERT_FLAG_DATACSUM; - if (bytenr != round_down(bytenr, root->sectorsize)) { + if (bytenr != round_down(bytenr, root->fs_info->sectorsize)) { error("bytenr not sectorsize aligned: %llu", (unsigned long long)bytenr); return -EINVAL; } - if (len != round_down(len, root->sectorsize)) { + if (len != round_down(len, root->fs_info->sectorsize)) { error("length not sectorsize aligned: %llu", (unsigned long long)len); return -EINVAL; @@ -441,47 +215,40 @@ static int create_image_file_range(struct btrfs_trans_handle *trans, len = min_t(u64, len, BTRFS_MAX_EXTENT_SIZE); /* - * Skip sb ranges first - * [0, 1M), [sb_offset(1), +64K), [sb_offset(2), +64K]. + * Skip reserved ranges first * * Or we will insert a hole into current image file, and later * migrate block will fail as there is already a file extent. */ - if (bytenr < 1024 * 1024) { - *ret_len = 1024 * 1024 - bytenr; - return 0; - } - for (i = 1; i < BTRFS_SUPER_MIRROR_MAX; i++) { - u64 cur = btrfs_sb_offset(i); + for (i = 0; i < ARRAY_SIZE(btrfs_reserved_ranges); i++) { + const struct simple_range *reserved = &btrfs_reserved_ranges[i]; - if (bytenr >= cur && bytenr < cur + BTRFS_STRIPE_LEN) { - *ret_len = cur + BTRFS_STRIPE_LEN - bytenr; + /* + * |-- reserved --| + * |--range---| + * or + * |---- reserved ----| + * |-- range --| + * Skip to reserved range end + */ + if (bytenr >= reserved->start && bytenr < range_end(reserved)) { + *ret_len = range_end(reserved) - bytenr; return 0; } - } - for (i = 1; i < BTRFS_SUPER_MIRROR_MAX; i++) { - u64 cur = btrfs_sb_offset(i); /* - * |--reserved--| + * |---reserved---| * |----range-------| - * May still need to go through file extent inserts + * Leading part may still create a file extent */ - if (bytenr < cur && bytenr + len >= cur) { - len = min_t(u64, len, cur - bytenr); + if (bytenr < reserved->start && + bytenr + len >= range_end(reserved)) { + len = min_t(u64, len, reserved->start - bytenr); break; } - /* - * |--reserved--| - * |---range---| - * Drop out, no need to insert anything - */ - if (bytenr >= cur && bytenr < cur + BTRFS_STRIPE_LEN) { - *ret_len = cur + BTRFS_STRIPE_LEN - bytenr; - return 0; - } } + /* Check if we are going to insert regular file extent, or hole */ cache = search_cache_extent(used, bytenr); if (cache) { if (cache->start <= bytenr) { @@ -489,6 +256,7 @@ static int create_image_file_range(struct btrfs_trans_handle *trans, * |///////Used///////| * |<--insert--->| * bytenr + * Insert one real file extent */ len = min_t(u64, len, cache->start + cache->size - bytenr); @@ -498,6 +266,7 @@ static int create_image_file_range(struct btrfs_trans_handle *trans, * |//Used//| * |<-insert-->| * bytenr + * Insert one hole */ len = min(len, cache->start - bytenr); disk_bytenr = 0; @@ -508,6 +277,7 @@ static int create_image_file_range(struct btrfs_trans_handle *trans, * |//Used//| |EOF * |<-insert-->| * bytenr + * Insert one hole */ disk_bytenr = 0; datacsum = 0; @@ -526,7 +296,7 @@ static int create_image_file_range(struct btrfs_trans_handle *trans, bg_cache->key.offset - bytenr); } - if (len != round_down(len, root->sectorsize)) { + if (len != round_down(len, root->fs_info->sectorsize)) { error("remaining length not sectorsize aligned: %llu", (unsigned long long)len); return -EINVAL; @@ -553,25 +323,33 @@ static int migrate_one_reserved_range(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct cache_tree *used, struct btrfs_inode_item *inode, int fd, - u64 ino, u64 start, u64 len, int datacsum) + u64 ino, const struct simple_range *range, + u32 convert_flags) { - u64 cur_off = start; - u64 cur_len = len; - u64 hole_start = start; + u64 cur_off = range->start; + u64 cur_len = range->len; + u64 hole_start = range->start; u64 hole_len; struct cache_extent *cache; struct btrfs_key key; struct extent_buffer *eb; int ret = 0; - while (cur_off < start + len) { + /* + * It's possible that there are holes in reserved range: + * |<---------------- Reserved range ---------------------->| + * |<- Old fs data ->| |<- Old fs data ->| + * So here we need to iterate through old fs used space and only + * migrate ranges that covered by old fs data. + */ + while (cur_off < range_end(range)) { cache = lookup_cache_extent(used, cur_off, cur_len); if (!cache) break; cur_off = max(cache->start, cur_off); - cur_len = min(cache->start + cache->size, start + len) - + cur_len = min(cache->start + cache->size, range_end(range)) - cur_off; - BUG_ON(cur_len < root->sectorsize); + BUG_ON(cur_len < root->fs_info->sectorsize); /* reserve extent for the data */ ret = btrfs_reserve_extent(trans, root, cur_len, 0, 0, (u64)-1, @@ -595,7 +373,7 @@ static int migrate_one_reserved_range(struct btrfs_trans_handle *trans, eb->len = key.offset; /* Write the data */ - ret = write_and_map_eb(trans, root, eb); + ret = write_and_map_eb(root->fs_info, eb); free(eb); if (ret < 0) break; @@ -606,7 +384,7 @@ static int migrate_one_reserved_range(struct btrfs_trans_handle *trans, if (ret < 0) break; /* Finally, insert csum items */ - if (datacsum) + if (convert_flags & CONVERT_FLAG_DATACSUM) ret = csum_disk_extent(trans, root, key.objectid, key.offset); @@ -621,56 +399,43 @@ static int migrate_one_reserved_range(struct btrfs_trans_handle *trans, cur_off += key.offset; hole_start = cur_off; - cur_len = start + len - cur_off; + cur_len = range_end(range) - cur_off; } - /* Last hole */ - if (start + len - hole_start > 0) + /* + * Last hole + * |<---- reserved -------->| + * |<- Old fs data ->| | + * | Hole | + */ + if (range_end(range) - hole_start > 0) ret = btrfs_record_file_extent(trans, root, ino, inode, - hole_start, 0, start + len - hole_start); + hole_start, 0, range_end(range) - hole_start); return ret; } /* * Relocate the used ext2 data in reserved ranges - * [0,1M) - * [btrfs_sb_offset(1), +BTRFS_STRIPE_LEN) - * [btrfs_sb_offset(2), +BTRFS_STRIPE_LEN) */ static int migrate_reserved_ranges(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct cache_tree *used, struct btrfs_inode_item *inode, int fd, - u64 ino, u64 total_bytes, int datacsum) + u64 ino, u64 total_bytes, u32 convert_flags) { - u64 cur_off; - u64 cur_len; + int i; int ret = 0; - /* 0 ~ 1M */ - cur_off = 0; - cur_len = 1024 * 1024; - ret = migrate_one_reserved_range(trans, root, used, inode, fd, ino, - cur_off, cur_len, datacsum); - if (ret < 0) - return ret; + for (i = 0; i < ARRAY_SIZE(btrfs_reserved_ranges); i++) { + const struct simple_range *range = &btrfs_reserved_ranges[i]; - /* second sb(fisrt sb is included in 0~1M) */ - cur_off = btrfs_sb_offset(1); - cur_len = min(total_bytes, cur_off + BTRFS_STRIPE_LEN) - cur_off; - if (cur_off > total_bytes) - return ret; - ret = migrate_one_reserved_range(trans, root, used, inode, fd, ino, - cur_off, cur_len, datacsum); - if (ret < 0) - return ret; + if (range->start > total_bytes) + return ret; + ret = migrate_one_reserved_range(trans, root, used, inode, fd, + ino, range, convert_flags); + if (ret < 0) + return ret; + } - /* Last sb */ - cur_off = btrfs_sb_offset(2); - cur_len = min(total_bytes, cur_off + BTRFS_STRIPE_LEN) - cur_off; - if (cur_off > total_bytes) - return ret; - ret = migrate_one_reserved_range(trans, root, used, inode, fd, ino, - cur_off, cur_len, datacsum); return ret; } @@ -843,26 +608,25 @@ static int wipe_one_reserved_range(struct cache_tree *tree, static int wipe_reserved_ranges(struct cache_tree *tree, u64 min_stripe_size, int ensure_size) { + int i; int ret; - ret = wipe_one_reserved_range(tree, 0, 1024 * 1024, min_stripe_size, - ensure_size); - if (ret < 0) - return ret; - ret = wipe_one_reserved_range(tree, btrfs_sb_offset(1), - BTRFS_STRIPE_LEN, min_stripe_size, ensure_size); - if (ret < 0) - return ret; - ret = wipe_one_reserved_range(tree, btrfs_sb_offset(2), - BTRFS_STRIPE_LEN, min_stripe_size, ensure_size); + for (i = 0; i < ARRAY_SIZE(btrfs_reserved_ranges); i++) { + const struct simple_range *range = &btrfs_reserved_ranges[i]; + + ret = wipe_one_reserved_range(tree, range->start, range->len, + min_stripe_size, ensure_size); + if (ret < 0) + return ret; + } return ret; } static int calculate_available_space(struct btrfs_convert_context *cctx) { - struct cache_tree *used = &cctx->used; + struct cache_tree *used = &cctx->used_space; struct cache_tree *data_chunks = &cctx->data_chunks; - struct cache_tree *free = &cctx->free; + struct cache_tree *free = &cctx->free_space; struct cache_extent *cache; u64 cur_off = 0; /* @@ -964,7 +728,7 @@ static int convert_read_used_space(struct btrfs_convert_context *cctx) static int create_image(struct btrfs_root *root, struct btrfs_mkfs_config *cfg, struct btrfs_convert_context *cctx, int fd, - u64 size, char *name, int datacsum) + u64 size, char *name, u32 convert_flags) { struct btrfs_inode_item buf; struct btrfs_trans_handle *trans; @@ -977,7 +741,7 @@ static int create_image(struct btrfs_root *root, u64 flags = BTRFS_INODE_READONLY; int ret; - if (!datacsum) + if (!(convert_flags & CONVERT_FLAG_DATACSUM)) flags |= BTRFS_INODE_NODATASUM; trans = btrfs_start_transaction(root, 1); @@ -1020,7 +784,7 @@ static int create_image(struct btrfs_root *root, * Create a new used space cache, which doesn't contain the reserved * range */ - for (cache = first_cache_extent(&cctx->used); cache; + for (cache = first_cache_extent(&cctx->used_space); cache; cache = next_cache_extent(cache)) { ret = add_cache_extent(&used_tmp, cache->start, cache->size); if (ret < 0) @@ -1039,15 +803,15 @@ static int create_image(struct btrfs_root *root, u64 len = size - cur; ret = create_image_file_range(trans, root, &used_tmp, - &buf, ino, cur, &len, datacsum); + &buf, ino, cur, &len, + convert_flags); if (ret < 0) goto out; cur += len; } /* Handle the reserved ranges */ - ret = migrate_reserved_ranges(trans, root, &cctx->used, &buf, fd, ino, - cfg->num_bytes, datacsum); - + ret = migrate_reserved_ranges(trans, root, &cctx->used_space, &buf, fd, + ino, cfg->num_bytes, convert_flags); key.objectid = ino; key.type = BTRFS_INODE_ITEM_KEY; @@ -1250,7 +1014,8 @@ static int make_convert_data_block_groups(struct btrfs_trans_handle *trans, */ max_chunk_size = cfg->num_bytes / 10; max_chunk_size = min((u64)(1024 * 1024 * 1024), max_chunk_size); - max_chunk_size = round_down(max_chunk_size, extent_root->sectorsize); + max_chunk_size = round_down(max_chunk_size, + extent_root->fs_info->sectorsize); for (cache = first_cache_extent(data_chunks); cache; cache = next_cache_extent(cache)) { @@ -1262,12 +1027,12 @@ static int make_convert_data_block_groups(struct btrfs_trans_handle *trans, len = min(max_chunk_size, cache->start + cache->size - cur); - ret = btrfs_alloc_data_chunk(trans, extent_root, + ret = btrfs_alloc_data_chunk(trans, fs_info, &cur_backup, len, BTRFS_BLOCK_GROUP_DATA, 1); if (ret < 0) break; - ret = btrfs_make_block_group(trans, extent_root, 0, + ret = btrfs_make_block_group(trans, fs_info, 0, BTRFS_BLOCK_GROUP_DATA, BTRFS_FIRST_CHUNK_TREE_OBJECTID, cur, len); @@ -1291,8 +1056,7 @@ static int make_convert_data_block_groups(struct btrfs_trans_handle *trans, * But the convert image subvolume is *NOT* linked to fs tree yet. */ static int init_btrfs(struct btrfs_mkfs_config *cfg, struct btrfs_root *root, - struct btrfs_convert_context *cctx, int datacsum, - int packing, int noxattr) + struct btrfs_convert_context *cctx, u32 convert_flags) { struct btrfs_key location; struct btrfs_trans_handle *trans; @@ -1412,951 +1176,11 @@ fail: return ret; } -static int prepare_system_chunk_sb(struct btrfs_super_block *super) -{ - struct btrfs_chunk *chunk; - struct btrfs_disk_key *key; - u32 sectorsize = btrfs_super_sectorsize(super); - - key = (struct btrfs_disk_key *)(super->sys_chunk_array); - chunk = (struct btrfs_chunk *)(super->sys_chunk_array + - sizeof(struct btrfs_disk_key)); - - btrfs_set_disk_key_objectid(key, BTRFS_FIRST_CHUNK_TREE_OBJECTID); - btrfs_set_disk_key_type(key, BTRFS_CHUNK_ITEM_KEY); - btrfs_set_disk_key_offset(key, 0); - - btrfs_set_stack_chunk_length(chunk, btrfs_super_total_bytes(super)); - btrfs_set_stack_chunk_owner(chunk, BTRFS_EXTENT_TREE_OBJECTID); - btrfs_set_stack_chunk_stripe_len(chunk, BTRFS_STRIPE_LEN); - btrfs_set_stack_chunk_type(chunk, BTRFS_BLOCK_GROUP_SYSTEM); - btrfs_set_stack_chunk_io_align(chunk, sectorsize); - btrfs_set_stack_chunk_io_width(chunk, sectorsize); - btrfs_set_stack_chunk_sector_size(chunk, sectorsize); - btrfs_set_stack_chunk_num_stripes(chunk, 1); - btrfs_set_stack_chunk_sub_stripes(chunk, 0); - chunk->stripe.devid = super->dev_item.devid; - btrfs_set_stack_stripe_offset(&chunk->stripe, 0); - memcpy(chunk->stripe.dev_uuid, super->dev_item.uuid, BTRFS_UUID_SIZE); - btrfs_set_super_sys_array_size(super, sizeof(*key) + sizeof(*chunk)); - return 0; -} - -#if BTRFSCONVERT_EXT2 - -/* - * Open Ext2fs in readonly mode, read block allocation bitmap and - * inode bitmap into memory. - */ -static int ext2_open_fs(struct btrfs_convert_context *cctx, const char *name) -{ - errcode_t ret; - ext2_filsys ext2_fs; - ext2_ino_t ino; - u32 ro_feature; - - ret = ext2fs_open(name, 0, 0, 0, unix_io_manager, &ext2_fs); - if (ret) { - fprintf(stderr, "ext2fs_open: %s\n", error_message(ret)); - return -1; - } - /* - * We need to know exactly the used space, some RO compat flags like - * BIGALLOC will affect how used space is present. - * So we need manuall check any unsupported RO compat flags - */ - ro_feature = ext2_fs->super->s_feature_ro_compat; - if (ro_feature & ~EXT2_LIB_FEATURE_RO_COMPAT_SUPP) { - error( -"unsupported RO features detected: %x, abort convert to avoid possible corruption", - ro_feature & ~EXT2_LIB_FEATURE_COMPAT_SUPP); - goto fail; - } - ret = ext2fs_read_inode_bitmap(ext2_fs); - if (ret) { - fprintf(stderr, "ext2fs_read_inode_bitmap: %s\n", - error_message(ret)); - goto fail; - } - ret = ext2fs_read_block_bitmap(ext2_fs); - if (ret) { - fprintf(stderr, "ext2fs_read_block_bitmap: %s\n", - error_message(ret)); - goto fail; - } - /* - * search each block group for a free inode. this set up - * uninit block/inode bitmaps appropriately. - */ - ino = 1; - while (ino <= ext2_fs->super->s_inodes_count) { - ext2_ino_t foo; - ext2fs_new_inode(ext2_fs, ino, 0, NULL, &foo); - ino += EXT2_INODES_PER_GROUP(ext2_fs->super); - } - - if (!(ext2_fs->super->s_feature_incompat & - EXT2_FEATURE_INCOMPAT_FILETYPE)) { - error("filetype feature is missing"); - goto fail; - } - - cctx->fs_data = ext2_fs; - cctx->blocksize = ext2_fs->blocksize; - cctx->block_count = ext2_fs->super->s_blocks_count; - cctx->total_bytes = ext2_fs->blocksize * ext2_fs->super->s_blocks_count; - cctx->volume_name = strndup(ext2_fs->super->s_volume_name, 16); - cctx->first_data_block = ext2_fs->super->s_first_data_block; - cctx->inodes_count = ext2_fs->super->s_inodes_count; - cctx->free_inodes_count = ext2_fs->super->s_free_inodes_count; - return 0; -fail: - ext2fs_close(ext2_fs); - return -1; -} - -static int __ext2_add_one_block(ext2_filsys fs, char *bitmap, - unsigned long group_nr, struct cache_tree *used) -{ - unsigned long offset; - unsigned i; - int ret = 0; - - offset = fs->super->s_first_data_block; - offset /= EXT2FS_CLUSTER_RATIO(fs); - offset += group_nr * EXT2_CLUSTERS_PER_GROUP(fs->super); - for (i = 0; i < EXT2_CLUSTERS_PER_GROUP(fs->super); i++) { - if ((i + offset) >= ext2fs_blocks_count(fs->super)) - break; - - if (ext2fs_test_bit(i, bitmap)) { - u64 start; - - start = (i + offset) * EXT2FS_CLUSTER_RATIO(fs); - start *= fs->blocksize; - ret = add_merge_cache_extent(used, start, - fs->blocksize); - if (ret < 0) - break; - } - } - return ret; -} - -/* - * Read all used ext2 space into cctx->used cache tree - */ -static int ext2_read_used_space(struct btrfs_convert_context *cctx) -{ - ext2_filsys fs = (ext2_filsys)cctx->fs_data; - blk64_t blk_itr = EXT2FS_B2C(fs, fs->super->s_first_data_block); - struct cache_tree *used_tree = &cctx->used; - char *block_bitmap = NULL; - unsigned long i; - int block_nbytes; - int ret = 0; - - block_nbytes = EXT2_CLUSTERS_PER_GROUP(fs->super) / 8; - /* Shouldn't happen */ - BUG_ON(!fs->block_map); - - block_bitmap = malloc(block_nbytes); - if (!block_bitmap) - return -ENOMEM; - - for (i = 0; i < fs->group_desc_count; i++) { - ret = ext2fs_get_block_bitmap_range(fs->block_map, blk_itr, - block_nbytes * 8, block_bitmap); - if (ret) { - error("fail to get bitmap from ext2, %s", - strerror(-ret)); - break; - } - ret = __ext2_add_one_block(fs, block_bitmap, i, used_tree); - if (ret < 0) { - error("fail to build used space tree, %s", - strerror(-ret)); - break; - } - blk_itr += EXT2_CLUSTERS_PER_GROUP(fs->super); - } - - free(block_bitmap); - return ret; -} - -static void ext2_close_fs(struct btrfs_convert_context *cctx) -{ - if (cctx->volume_name) { - free(cctx->volume_name); - cctx->volume_name = NULL; - } - ext2fs_close(cctx->fs_data); -} - -struct dir_iterate_data { - struct btrfs_trans_handle *trans; - struct btrfs_root *root; - struct btrfs_inode_item *inode; - u64 objectid; - u64 index_cnt; - u64 parent; - int errcode; -}; - -static u8 ext2_filetype_conversion_table[EXT2_FT_MAX] = { - [EXT2_FT_UNKNOWN] = BTRFS_FT_UNKNOWN, - [EXT2_FT_REG_FILE] = BTRFS_FT_REG_FILE, - [EXT2_FT_DIR] = BTRFS_FT_DIR, - [EXT2_FT_CHRDEV] = BTRFS_FT_CHRDEV, - [EXT2_FT_BLKDEV] = BTRFS_FT_BLKDEV, - [EXT2_FT_FIFO] = BTRFS_FT_FIFO, - [EXT2_FT_SOCK] = BTRFS_FT_SOCK, - [EXT2_FT_SYMLINK] = BTRFS_FT_SYMLINK, -}; - -static int ext2_dir_iterate_proc(ext2_ino_t dir, int entry, - struct ext2_dir_entry *dirent, - int offset, int blocksize, - char *buf,void *priv_data) -{ - int ret; - int file_type; - u64 objectid; - char dotdot[] = ".."; - struct dir_iterate_data *idata = (struct dir_iterate_data *)priv_data; - int name_len; - - name_len = dirent->name_len & 0xFF; - - objectid = dirent->inode + INO_OFFSET; - if (!strncmp(dirent->name, dotdot, name_len)) { - if (name_len == 2) { - BUG_ON(idata->parent != 0); - idata->parent = objectid; - } - return 0; - } - if (dirent->inode < EXT2_GOOD_OLD_FIRST_INO) - return 0; - - file_type = dirent->name_len >> 8; - BUG_ON(file_type > EXT2_FT_SYMLINK); - - ret = convert_insert_dirent(idata->trans, idata->root, dirent->name, - name_len, idata->objectid, objectid, - ext2_filetype_conversion_table[file_type], - idata->index_cnt, idata->inode); - if (ret < 0) { - idata->errcode = ret; - return BLOCK_ABORT; - } - - idata->index_cnt++; - return 0; -} - -static int ext2_create_dir_entries(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 objectid, - struct btrfs_inode_item *btrfs_inode, - ext2_filsys ext2_fs, ext2_ino_t ext2_ino) -{ - int ret; - errcode_t err; - struct dir_iterate_data data = { - .trans = trans, - .root = root, - .inode = btrfs_inode, - .objectid = objectid, - .index_cnt = 2, - .parent = 0, - .errcode = 0, - }; - - err = ext2fs_dir_iterate2(ext2_fs, ext2_ino, 0, NULL, - ext2_dir_iterate_proc, &data); - if (err) - goto error; - ret = data.errcode; - if (ret == 0 && data.parent == objectid) { - ret = btrfs_insert_inode_ref(trans, root, "..", 2, - objectid, objectid, 0); - } - return ret; -error: - fprintf(stderr, "ext2fs_dir_iterate2: %s\n", error_message(err)); - return -1; -} - -static int ext2_block_iterate_proc(ext2_filsys fs, blk_t *blocknr, - e2_blkcnt_t blockcnt, blk_t ref_block, - int ref_offset, void *priv_data) -{ - int ret; - struct blk_iterate_data *idata; - idata = (struct blk_iterate_data *)priv_data; - ret = block_iterate_proc(*blocknr, blockcnt, idata); - if (ret) { - idata->errcode = ret; - return BLOCK_ABORT; - } - return 0; -} - -/* - * traverse file's data blocks, record these data blocks as file extents. - */ -static int ext2_create_file_extents(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 objectid, - struct btrfs_inode_item *btrfs_inode, - ext2_filsys ext2_fs, ext2_ino_t ext2_ino, - int datacsum, int packing) -{ - int ret; - char *buffer = NULL; - errcode_t err; - u32 last_block; - u32 sectorsize = root->sectorsize; - u64 inode_size = btrfs_stack_inode_size(btrfs_inode); - struct blk_iterate_data data; - - init_blk_iterate_data(&data, trans, root, btrfs_inode, objectid, - datacsum); - - err = ext2fs_block_iterate2(ext2_fs, ext2_ino, BLOCK_FLAG_DATA_ONLY, - NULL, ext2_block_iterate_proc, &data); - if (err) - goto error; - ret = data.errcode; - if (ret) - goto fail; - if (packing && data.first_block == 0 && data.num_blocks > 0 && - inode_size <= BTRFS_MAX_INLINE_DATA_SIZE(root)) { - u64 num_bytes = data.num_blocks * sectorsize; - u64 disk_bytenr = data.disk_block * sectorsize; - u64 nbytes; - - buffer = malloc(num_bytes); - if (!buffer) - return -ENOMEM; - ret = read_disk_extent(root, disk_bytenr, num_bytes, buffer); - if (ret) - goto fail; - if (num_bytes > inode_size) - num_bytes = inode_size; - ret = btrfs_insert_inline_extent(trans, root, objectid, - 0, buffer, num_bytes); - if (ret) - goto fail; - nbytes = btrfs_stack_inode_nbytes(btrfs_inode) + num_bytes; - btrfs_set_stack_inode_nbytes(btrfs_inode, nbytes); - } else if (data.num_blocks > 0) { - ret = record_file_blocks(&data, data.first_block, - data.disk_block, data.num_blocks); - if (ret) - goto fail; - } - data.first_block += data.num_blocks; - last_block = (inode_size + sectorsize - 1) / sectorsize; - if (last_block > data.first_block) { - ret = record_file_blocks(&data, data.first_block, 0, - last_block - data.first_block); - } -fail: - free(buffer); - return ret; -error: - fprintf(stderr, "ext2fs_block_iterate2: %s\n", error_message(err)); - return -1; -} - -static int ext2_create_symbol_link(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 objectid, - struct btrfs_inode_item *btrfs_inode, - ext2_filsys ext2_fs, ext2_ino_t ext2_ino, - struct ext2_inode *ext2_inode) -{ - int ret; - char *pathname; - u64 inode_size = btrfs_stack_inode_size(btrfs_inode); - if (ext2fs_inode_data_blocks(ext2_fs, ext2_inode)) { - btrfs_set_stack_inode_size(btrfs_inode, inode_size + 1); - ret = ext2_create_file_extents(trans, root, objectid, - btrfs_inode, ext2_fs, ext2_ino, 1, 1); - btrfs_set_stack_inode_size(btrfs_inode, inode_size); - return ret; - } - - pathname = (char *)&(ext2_inode->i_block[0]); - BUG_ON(pathname[inode_size] != 0); - ret = btrfs_insert_inline_extent(trans, root, objectid, 0, - pathname, inode_size + 1); - btrfs_set_stack_inode_nbytes(btrfs_inode, inode_size + 1); - return ret; -} - -/* - * Following xattr/acl related codes are based on codes in - * fs/ext3/xattr.c and fs/ext3/acl.c - */ -#define EXT2_XATTR_BHDR(ptr) ((struct ext2_ext_attr_header *)(ptr)) -#define EXT2_XATTR_BFIRST(ptr) \ - ((struct ext2_ext_attr_entry *)(EXT2_XATTR_BHDR(ptr) + 1)) -#define EXT2_XATTR_IHDR(inode) \ - ((struct ext2_ext_attr_header *) ((void *)(inode) + \ - EXT2_GOOD_OLD_INODE_SIZE + (inode)->i_extra_isize)) -#define EXT2_XATTR_IFIRST(inode) \ - ((struct ext2_ext_attr_entry *) ((void *)EXT2_XATTR_IHDR(inode) + \ - sizeof(EXT2_XATTR_IHDR(inode)->h_magic))) - -static int ext2_xattr_check_names(struct ext2_ext_attr_entry *entry, - const void *end) -{ - struct ext2_ext_attr_entry *next; - - while (!EXT2_EXT_IS_LAST_ENTRY(entry)) { - next = EXT2_EXT_ATTR_NEXT(entry); - if ((void *)next >= end) - return -EIO; - entry = next; - } - return 0; -} - -static int ext2_xattr_check_block(const char *buf, size_t size) -{ - int error; - struct ext2_ext_attr_header *header = EXT2_XATTR_BHDR(buf); - - if (header->h_magic != EXT2_EXT_ATTR_MAGIC || - header->h_blocks != 1) - return -EIO; - error = ext2_xattr_check_names(EXT2_XATTR_BFIRST(buf), buf + size); - return error; -} - -static int ext2_xattr_check_entry(struct ext2_ext_attr_entry *entry, - size_t size) -{ - size_t value_size = entry->e_value_size; - - if (entry->e_value_block != 0 || value_size > size || - entry->e_value_offs + value_size > size) - return -EIO; - return 0; -} - -#define EXT2_ACL_VERSION 0x0001 - -/* 23.2.5 acl_tag_t values */ - -#define ACL_UNDEFINED_TAG (0x00) -#define ACL_USER_OBJ (0x01) -#define ACL_USER (0x02) -#define ACL_GROUP_OBJ (0x04) -#define ACL_GROUP (0x08) -#define ACL_MASK (0x10) -#define ACL_OTHER (0x20) - -/* 23.2.7 ACL qualifier constants */ - -#define ACL_UNDEFINED_ID ((id_t)-1) - -typedef struct { - __le16 e_tag; - __le16 e_perm; - __le32 e_id; -} ext2_acl_entry; - -typedef struct { - __le16 e_tag; - __le16 e_perm; -} ext2_acl_entry_short; - -typedef struct { - __le32 a_version; -} ext2_acl_header; - -static inline int ext2_acl_count(size_t size) -{ - ssize_t s; - size -= sizeof(ext2_acl_header); - s = size - 4 * sizeof(ext2_acl_entry_short); - if (s < 0) { - if (size % sizeof(ext2_acl_entry_short)) - return -1; - return size / sizeof(ext2_acl_entry_short); - } else { - if (s % sizeof(ext2_acl_entry)) - return -1; - return s / sizeof(ext2_acl_entry) + 4; - } -} - -#define ACL_EA_VERSION 0x0002 - -typedef struct { - __le16 e_tag; - __le16 e_perm; - __le32 e_id; -} acl_ea_entry; - -typedef struct { - __le32 a_version; - acl_ea_entry a_entries[0]; -} acl_ea_header; - -static inline size_t acl_ea_size(int count) -{ - return sizeof(acl_ea_header) + count * sizeof(acl_ea_entry); -} - -static int ext2_acl_to_xattr(void *dst, const void *src, - size_t dst_size, size_t src_size) -{ - int i, count; - const void *end = src + src_size; - acl_ea_header *ext_acl = (acl_ea_header *)dst; - acl_ea_entry *dst_entry = ext_acl->a_entries; - ext2_acl_entry *src_entry; - - if (src_size < sizeof(ext2_acl_header)) - goto fail; - if (((ext2_acl_header *)src)->a_version != - cpu_to_le32(EXT2_ACL_VERSION)) - goto fail; - src += sizeof(ext2_acl_header); - count = ext2_acl_count(src_size); - if (count <= 0) - goto fail; - - BUG_ON(dst_size < acl_ea_size(count)); - ext_acl->a_version = cpu_to_le32(ACL_EA_VERSION); - for (i = 0; i < count; i++, dst_entry++) { - src_entry = (ext2_acl_entry *)src; - if (src + sizeof(ext2_acl_entry_short) > end) - goto fail; - dst_entry->e_tag = src_entry->e_tag; - dst_entry->e_perm = src_entry->e_perm; - switch (le16_to_cpu(src_entry->e_tag)) { - case ACL_USER_OBJ: - case ACL_GROUP_OBJ: - case ACL_MASK: - case ACL_OTHER: - src += sizeof(ext2_acl_entry_short); - dst_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); - break; - case ACL_USER: - case ACL_GROUP: - src += sizeof(ext2_acl_entry); - if (src > end) - goto fail; - dst_entry->e_id = src_entry->e_id; - break; - default: - goto fail; - } - } - if (src != end) - goto fail; - return 0; -fail: - return -EINVAL; -} - -static char *xattr_prefix_table[] = { - [1] = "user.", - [2] = "system.posix_acl_access", - [3] = "system.posix_acl_default", - [4] = "trusted.", - [6] = "security.", -}; - -static int ext2_copy_single_xattr(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 objectid, - struct ext2_ext_attr_entry *entry, - const void *data, u32 datalen) -{ - int ret = 0; - int name_len; - int name_index; - void *databuf = NULL; - char namebuf[XATTR_NAME_MAX + 1]; - - name_index = entry->e_name_index; - if (name_index >= ARRAY_SIZE(xattr_prefix_table) || - xattr_prefix_table[name_index] == NULL) - return -EOPNOTSUPP; - name_len = strlen(xattr_prefix_table[name_index]) + - entry->e_name_len; - if (name_len >= sizeof(namebuf)) - return -ERANGE; - - if (name_index == 2 || name_index == 3) { - size_t bufsize = acl_ea_size(ext2_acl_count(datalen)); - databuf = malloc(bufsize); - if (!databuf) - return -ENOMEM; - ret = ext2_acl_to_xattr(databuf, data, bufsize, datalen); - if (ret) - goto out; - data = databuf; - datalen = bufsize; - } - strncpy(namebuf, xattr_prefix_table[name_index], XATTR_NAME_MAX); - strncat(namebuf, EXT2_EXT_ATTR_NAME(entry), entry->e_name_len); - if (name_len + datalen > BTRFS_LEAF_DATA_SIZE(root) - - sizeof(struct btrfs_item) - sizeof(struct btrfs_dir_item)) { - fprintf(stderr, "skip large xattr on inode %Lu name %.*s\n", - objectid - INO_OFFSET, name_len, namebuf); - goto out; - } - ret = btrfs_insert_xattr_item(trans, root, namebuf, name_len, - data, datalen, objectid); -out: - free(databuf); - return ret; -} - -static int ext2_copy_extended_attrs(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 objectid, - struct btrfs_inode_item *btrfs_inode, - ext2_filsys ext2_fs, ext2_ino_t ext2_ino) -{ - int ret = 0; - int inline_ea = 0; - errcode_t err; - u32 datalen; - u32 block_size = ext2_fs->blocksize; - u32 inode_size = EXT2_INODE_SIZE(ext2_fs->super); - struct ext2_inode_large *ext2_inode; - struct ext2_ext_attr_entry *entry; - void *data; - char *buffer = NULL; - char inode_buf[EXT2_GOOD_OLD_INODE_SIZE]; - - if (inode_size <= EXT2_GOOD_OLD_INODE_SIZE) { - ext2_inode = (struct ext2_inode_large *)inode_buf; - } else { - ext2_inode = (struct ext2_inode_large *)malloc(inode_size); - if (!ext2_inode) - return -ENOMEM; - } - err = ext2fs_read_inode_full(ext2_fs, ext2_ino, (void *)ext2_inode, - inode_size); - if (err) { - fprintf(stderr, "ext2fs_read_inode_full: %s\n", - error_message(err)); - ret = -1; - goto out; - } - - if (ext2_ino > ext2_fs->super->s_first_ino && - inode_size > EXT2_GOOD_OLD_INODE_SIZE) { - if (EXT2_GOOD_OLD_INODE_SIZE + - ext2_inode->i_extra_isize > inode_size) { - ret = -EIO; - goto out; - } - if (ext2_inode->i_extra_isize != 0 && - EXT2_XATTR_IHDR(ext2_inode)->h_magic == - EXT2_EXT_ATTR_MAGIC) { - inline_ea = 1; - } - } - if (inline_ea) { - int total; - void *end = (void *)ext2_inode + inode_size; - entry = EXT2_XATTR_IFIRST(ext2_inode); - total = end - (void *)entry; - ret = ext2_xattr_check_names(entry, end); - if (ret) - goto out; - while (!EXT2_EXT_IS_LAST_ENTRY(entry)) { - ret = ext2_xattr_check_entry(entry, total); - if (ret) - goto out; - data = (void *)EXT2_XATTR_IFIRST(ext2_inode) + - entry->e_value_offs; - datalen = entry->e_value_size; - ret = ext2_copy_single_xattr(trans, root, objectid, - entry, data, datalen); - if (ret) - goto out; - entry = EXT2_EXT_ATTR_NEXT(entry); - } - } - - if (ext2_inode->i_file_acl == 0) - goto out; - - buffer = malloc(block_size); - if (!buffer) { - ret = -ENOMEM; - goto out; - } - err = ext2fs_read_ext_attr(ext2_fs, ext2_inode->i_file_acl, buffer); - if (err) { - fprintf(stderr, "ext2fs_read_ext_attr: %s\n", - error_message(err)); - ret = -1; - goto out; - } - ret = ext2_xattr_check_block(buffer, block_size); - if (ret) - goto out; - - entry = EXT2_XATTR_BFIRST(buffer); - while (!EXT2_EXT_IS_LAST_ENTRY(entry)) { - ret = ext2_xattr_check_entry(entry, block_size); - if (ret) - goto out; - data = buffer + entry->e_value_offs; - datalen = entry->e_value_size; - ret = ext2_copy_single_xattr(trans, root, objectid, - entry, data, datalen); - if (ret) - goto out; - entry = EXT2_EXT_ATTR_NEXT(entry); - } -out: - free(buffer); - if ((void *)ext2_inode != inode_buf) - free(ext2_inode); - return ret; -} -#define MINORBITS 20 -#define MKDEV(ma, mi) (((ma) << MINORBITS) | (mi)) - -static inline dev_t old_decode_dev(u16 val) -{ - return MKDEV((val >> 8) & 255, val & 255); -} - -static inline dev_t new_decode_dev(u32 dev) -{ - unsigned major = (dev & 0xfff00) >> 8; - unsigned minor = (dev & 0xff) | ((dev >> 12) & 0xfff00); - return MKDEV(major, minor); -} - -static void ext2_copy_inode_item(struct btrfs_inode_item *dst, - struct ext2_inode *src, u32 blocksize) -{ - btrfs_set_stack_inode_generation(dst, 1); - btrfs_set_stack_inode_sequence(dst, 0); - btrfs_set_stack_inode_transid(dst, 1); - btrfs_set_stack_inode_size(dst, src->i_size); - btrfs_set_stack_inode_nbytes(dst, 0); - btrfs_set_stack_inode_block_group(dst, 0); - btrfs_set_stack_inode_nlink(dst, src->i_links_count); - btrfs_set_stack_inode_uid(dst, src->i_uid | (src->i_uid_high << 16)); - btrfs_set_stack_inode_gid(dst, src->i_gid | (src->i_gid_high << 16)); - btrfs_set_stack_inode_mode(dst, src->i_mode); - btrfs_set_stack_inode_rdev(dst, 0); - btrfs_set_stack_inode_flags(dst, 0); - btrfs_set_stack_timespec_sec(&dst->atime, src->i_atime); - btrfs_set_stack_timespec_nsec(&dst->atime, 0); - btrfs_set_stack_timespec_sec(&dst->ctime, src->i_ctime); - btrfs_set_stack_timespec_nsec(&dst->ctime, 0); - btrfs_set_stack_timespec_sec(&dst->mtime, src->i_mtime); - btrfs_set_stack_timespec_nsec(&dst->mtime, 0); - btrfs_set_stack_timespec_sec(&dst->otime, 0); - btrfs_set_stack_timespec_nsec(&dst->otime, 0); - - if (S_ISDIR(src->i_mode)) { - btrfs_set_stack_inode_size(dst, 0); - btrfs_set_stack_inode_nlink(dst, 1); - } - if (S_ISREG(src->i_mode)) { - btrfs_set_stack_inode_size(dst, (u64)src->i_size_high << 32 | - (u64)src->i_size); - } - if (!S_ISREG(src->i_mode) && !S_ISDIR(src->i_mode) && - !S_ISLNK(src->i_mode)) { - if (src->i_block[0]) { - btrfs_set_stack_inode_rdev(dst, - old_decode_dev(src->i_block[0])); - } else { - btrfs_set_stack_inode_rdev(dst, - new_decode_dev(src->i_block[1])); - } - } - memset(&dst->reserved, 0, sizeof(dst->reserved)); -} -static int ext2_check_state(struct btrfs_convert_context *cctx) -{ - ext2_filsys fs = cctx->fs_data; - - if (!(fs->super->s_state & EXT2_VALID_FS)) - return 1; - else if (fs->super->s_state & EXT2_ERROR_FS) - return 1; - else - return 0; -} - -/* EXT2_*_FL to BTRFS_INODE_FLAG_* stringification helper */ -#define COPY_ONE_EXT2_FLAG(flags, ext2_inode, name) ({ \ - if (ext2_inode->i_flags & EXT2_##name##_FL) \ - flags |= BTRFS_INODE_##name; \ -}) - -/* - * Convert EXT2_*_FL to corresponding BTRFS_INODE_* flags - * - * Only a subset of EXT_*_FL is supported in btrfs. - */ -static void ext2_convert_inode_flags(struct btrfs_inode_item *dst, - struct ext2_inode *src) -{ - u64 flags = 0; - - COPY_ONE_EXT2_FLAG(flags, src, APPEND); - COPY_ONE_EXT2_FLAG(flags, src, SYNC); - COPY_ONE_EXT2_FLAG(flags, src, IMMUTABLE); - COPY_ONE_EXT2_FLAG(flags, src, NODUMP); - COPY_ONE_EXT2_FLAG(flags, src, NOATIME); - COPY_ONE_EXT2_FLAG(flags, src, DIRSYNC); - btrfs_set_stack_inode_flags(dst, flags); -} - -/* - * copy a single inode. do all the required works, such as cloning - * inode item, creating file extents and creating directory entries. - */ -static int ext2_copy_single_inode(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 objectid, - ext2_filsys ext2_fs, ext2_ino_t ext2_ino, - struct ext2_inode *ext2_inode, - int datacsum, int packing, int noxattr) -{ - int ret; - struct btrfs_inode_item btrfs_inode; - - if (ext2_inode->i_links_count == 0) - return 0; - - ext2_copy_inode_item(&btrfs_inode, ext2_inode, ext2_fs->blocksize); - if (!datacsum && S_ISREG(ext2_inode->i_mode)) { - u32 flags = btrfs_stack_inode_flags(&btrfs_inode) | - BTRFS_INODE_NODATASUM; - btrfs_set_stack_inode_flags(&btrfs_inode, flags); - } - ext2_convert_inode_flags(&btrfs_inode, ext2_inode); - - switch (ext2_inode->i_mode & S_IFMT) { - case S_IFREG: - ret = ext2_create_file_extents(trans, root, objectid, - &btrfs_inode, ext2_fs, ext2_ino, datacsum, packing); - break; - case S_IFDIR: - ret = ext2_create_dir_entries(trans, root, objectid, - &btrfs_inode, ext2_fs, ext2_ino); - break; - case S_IFLNK: - ret = ext2_create_symbol_link(trans, root, objectid, - &btrfs_inode, ext2_fs, ext2_ino, ext2_inode); - break; - default: - ret = 0; - break; - } - if (ret) - return ret; - - if (!noxattr) { - ret = ext2_copy_extended_attrs(trans, root, objectid, - &btrfs_inode, ext2_fs, ext2_ino); - if (ret) - return ret; - } - return btrfs_insert_inode(trans, root, objectid, &btrfs_inode); -} - -/* - * scan ext2's inode bitmap and copy all used inodes. - */ -static int ext2_copy_inodes(struct btrfs_convert_context *cctx, - struct btrfs_root *root, - int datacsum, int packing, int noxattr, struct task_ctx *p) -{ - ext2_filsys ext2_fs = cctx->fs_data; - int ret; - errcode_t err; - ext2_inode_scan ext2_scan; - struct ext2_inode ext2_inode; - ext2_ino_t ext2_ino; - u64 objectid; - struct btrfs_trans_handle *trans; - - trans = btrfs_start_transaction(root, 1); - if (!trans) - return -ENOMEM; - err = ext2fs_open_inode_scan(ext2_fs, 0, &ext2_scan); - if (err) { - fprintf(stderr, "ext2fs_open_inode_scan: %s\n", error_message(err)); - return -1; - } - while (!(err = ext2fs_get_next_inode(ext2_scan, &ext2_ino, - &ext2_inode))) { - /* no more inodes */ - if (ext2_ino == 0) - break; - /* skip special inode in ext2fs */ - if (ext2_ino < EXT2_GOOD_OLD_FIRST_INO && - ext2_ino != EXT2_ROOT_INO) - continue; - objectid = ext2_ino + INO_OFFSET; - ret = ext2_copy_single_inode(trans, root, - objectid, ext2_fs, ext2_ino, - &ext2_inode, datacsum, packing, - noxattr); - p->cur_copy_inodes++; - if (ret) - return ret; - if (trans->blocks_used >= 4096) { - ret = btrfs_commit_transaction(trans, root); - BUG_ON(ret); - trans = btrfs_start_transaction(root, 1); - BUG_ON(!trans); - } - } - if (err) { - fprintf(stderr, "ext2fs_get_next_inode: %s\n", error_message(err)); - return -1; - } - ret = btrfs_commit_transaction(trans, root); - BUG_ON(ret); - ext2fs_close_inode_scan(ext2_scan); - - return ret; -} - -static const struct btrfs_convert_operations ext2_convert_ops = { - .name = "ext2", - .open_fs = ext2_open_fs, - .read_used_space = ext2_read_used_space, - .copy_inodes = ext2_copy_inodes, - .close_fs = ext2_close_fs, - .check_state = ext2_check_state, -}; - -#endif - -static const struct btrfs_convert_operations *convert_operations[] = { -#if BTRFSCONVERT_EXT2 - &ext2_convert_ops, -#endif -}; - static int convert_open_fs(const char *devname, struct btrfs_convert_context *cctx) { int i; - memset(cctx, 0, sizeof(*cctx)); - for (i = 0; i < ARRAY_SIZE(convert_operations); i++) { int ret = convert_operations[i]->open_fs(cctx, devname); @@ -2370,9 +1194,8 @@ static int convert_open_fs(const char *devname, return -1; } -static int do_convert(const char *devname, int datacsum, int packing, - int noxattr, u32 nodesize, int copylabel, const char *fslabel, - int progress, u64 features) +static int do_convert(const char *devname, u32 convert_flags, u32 nodesize, + const char *fslabel, int progress, u64 features) { int ret; int fd = -1; @@ -2382,7 +1205,7 @@ static int do_convert(const char *devname, int datacsum, int packing, struct btrfs_root *image_root; struct btrfs_convert_context cctx; struct btrfs_key key; - char *subvol_name = NULL; + char subvol_name[SOURCE_FS_NAME_LEN + 8]; struct task_ctx ctx; char features_buf[64]; struct btrfs_mkfs_config mkfs_cfg; @@ -2421,15 +1244,13 @@ static int do_convert(const char *devname, int datacsum, int packing, printf("\tnodesize: %u\n", nodesize); printf("\tfeatures: %s\n", features_buf); + memset(&mkfs_cfg, 0, sizeof(mkfs_cfg)); mkfs_cfg.label = cctx.volume_name; mkfs_cfg.num_bytes = total_bytes; mkfs_cfg.nodesize = nodesize; mkfs_cfg.sectorsize = blocksize; mkfs_cfg.stripesize = blocksize; mkfs_cfg.features = features; - /* New convert need these space */ - memset(mkfs_cfg.chunk_uuid, 0, BTRFS_UUID_UNPARSED_SIZE); - memset(mkfs_cfg.fs_uuid, 0, BTRFS_UUID_UNPARSED_SIZE); ret = make_convert_btrfs(fd, &mkfs_cfg, &cctx); if (ret) { @@ -2443,19 +1264,15 @@ static int do_convert(const char *devname, int datacsum, int packing, error("unable to open ctree"); goto fail; } - ret = init_btrfs(&mkfs_cfg, root, &cctx, datacsum, packing, noxattr); + ret = init_btrfs(&mkfs_cfg, root, &cctx, convert_flags); if (ret) { error("unable to setup the root tree: %d", ret); goto fail; } printf("creating %s image file\n", cctx.convert_ops->name); - ret = asprintf(&subvol_name, "%s_saved", cctx.convert_ops->name); - if (ret < 0) { - error("memory allocation failure for subvolume name: %s_saved", + snprintf(subvol_name, sizeof(subvol_name), "%s_saved", cctx.convert_ops->name); - goto fail; - } key.objectid = CONV_IMAGE_SUBVOL_OBJECTID; key.offset = (u64)-1; key.type = BTRFS_ROOT_ITEM_KEY; @@ -2465,13 +1282,19 @@ static int do_convert(const char *devname, int datacsum, int packing, goto fail; } ret = create_image(image_root, &mkfs_cfg, &cctx, fd, - mkfs_cfg.num_bytes, "image", datacsum); + mkfs_cfg.num_bytes, "image", + convert_flags); if (ret) { error("failed to create %s/image: %d", subvol_name, ret); goto fail; } printf("creating btrfs metadata"); + ret = pthread_mutex_init(&ctx.mutex, NULL); + if (ret) { + error("failed to initialize mutex: %d", ret); + goto fail; + } ctx.max_copy_inodes = (cctx.inodes_count - cctx.free_inodes_count); ctx.cur_copy_inodes = 0; @@ -2480,7 +1303,7 @@ static int do_convert(const char *devname, int datacsum, int packing, &ctx); task_start(ctx.info); } - ret = copy_inodes(&cctx, root, datacsum, packing, noxattr, &ctx); + ret = copy_inodes(&cctx, root, convert_flags, &ctx); if (ret) { error("error during copy_inodes %d", ret); goto fail; @@ -2496,14 +1319,12 @@ static int do_convert(const char *devname, int datacsum, int packing, goto fail; } - free(subvol_name); - memset(root->fs_info->super_copy->label, 0, BTRFS_LABEL_SIZE); - if (copylabel == 1) { + if (convert_flags & CONVERT_FLAG_COPY_LABEL) { __strncpy_null(root->fs_info->super_copy->label, cctx.volume_name, BTRFS_LABEL_SIZE - 1); printf("copy label '%s'\n", root->fs_info->super_copy->label); - } else if (copylabel == -1) { + } else if (convert_flags & CONVERT_FLAG_SET_LABEL) { strcpy(root->fs_info->super_copy->label, fslabel); printf("set label to '%s'\n", fslabel); } @@ -2548,479 +1369,404 @@ fail: } /* - * Check if a non 1:1 mapped chunk can be rolled back. - * For new convert, it's OK while for old convert it's not. + * Read out data of convert image which is in btrfs reserved ranges so we can + * use them to overwrite the ranges during rollback. */ -static int may_rollback_chunk(struct btrfs_fs_info *fs_info, u64 bytenr) +static int read_reserved_ranges(struct btrfs_root *root, u64 ino, + u64 total_bytes, char *reserved_ranges[]) { - struct btrfs_block_group_cache *bg; - struct btrfs_key key; - struct btrfs_path path; - struct btrfs_root *extent_root = fs_info->extent_root; - u64 bg_start; - u64 bg_end; - int ret; - - bg = btrfs_lookup_first_block_group(fs_info, bytenr); - if (!bg) - return -ENOENT; - bg_start = bg->key.objectid; - bg_end = bg->key.objectid + bg->key.offset; - - key.objectid = bg_end; - key.type = BTRFS_METADATA_ITEM_KEY; - key.offset = 0; - btrfs_init_path(&path); - - ret = btrfs_search_slot(NULL, extent_root, &key, &path, 0, 0); - if (ret < 0) - return ret; + int i; + int ret = 0; - while (1) { - struct btrfs_extent_item *ei; + for (i = 0; i < ARRAY_SIZE(btrfs_reserved_ranges); i++) { + const struct simple_range *range = &btrfs_reserved_ranges[i]; - ret = btrfs_previous_extent_item(extent_root, &path, bg_start); - if (ret > 0) { - ret = 0; + if (range->start + range->len >= total_bytes) break; - } - if (ret < 0) + ret = btrfs_read_file(root, ino, range->start, range->len, + reserved_ranges[i]); + if (ret < range->len) { + error( + "failed to read data of convert image, offset=%llu len=%llu ret=%d", + range->start, range->len, ret); + if (ret >= 0) + ret = -EIO; break; + } + ret = 0; + } + return ret; +} - btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); - if (key.type == BTRFS_METADATA_ITEM_KEY) - continue; - /* Now it's EXTENT_ITEM_KEY only */ - ei = btrfs_item_ptr(path.nodes[0], path.slots[0], - struct btrfs_extent_item); - /* - * Found data extent, means this is old convert must follow 1:1 - * mapping. - */ - if (btrfs_extent_flags(path.nodes[0], ei) - & BTRFS_EXTENT_FLAG_DATA) { - ret = -EINVAL; +static bool is_subset_of_reserved_ranges(u64 start, u64 len) +{ + int i; + bool ret = false; + + for (i = 0; i < ARRAY_SIZE(btrfs_reserved_ranges); i++) { + const struct simple_range *range = &btrfs_reserved_ranges[i]; + + if (start >= range->start && start + len <= range_end(range)) { + ret = true; break; } } - btrfs_release_path(&path); return ret; } -static int may_rollback(struct btrfs_root *root) +static bool is_chunk_direct_mapped(struct btrfs_fs_info *fs_info, u64 start) { - struct btrfs_fs_info *info = root->fs_info; - struct btrfs_multi_bio *multi = NULL; - u64 bytenr; - u64 length; - u64 physical; - u64 total_bytes; - int num_stripes; + struct cache_extent *ce; + struct map_lookup *map; + bool ret = false; + + ce = search_cache_extent(&fs_info->mapping_tree.cache_tree, start); + if (!ce) + goto out; + if (ce->start > start || ce->start + ce->size < start) + goto out; + + map = container_of(ce, struct map_lookup, ce); + + /* Not SINGLE chunk */ + if (map->num_stripes != 1) + goto out; + + /* Chunk's logical doesn't match with phisical, not 1:1 mapped */ + if (map->ce.start != map->stripes[0].physical) + goto out; + ret = true; +out: + return ret; +} + +/* + * Iterate all file extents of the convert image. + * + * All file extents except ones in btrfs_reserved_ranges must be mapped 1:1 + * on disk. (Means thier file_offset must match their on disk bytenr) + * + * File extents in reserved ranges can be relocated to other place, and in + * that case we will read them out for later use. + */ +static int check_convert_image(struct btrfs_root *image_root, u64 ino, + u64 total_size, char *reserved_ranges[]) +{ + struct btrfs_key key; + struct btrfs_path path; + struct btrfs_fs_info *fs_info = image_root->fs_info; + u64 checked_bytes = 0; int ret; - if (btrfs_super_num_devices(info->super_copy) != 1) - goto fail; + key.objectid = ino; + key.offset = 0; + key.type = BTRFS_EXTENT_DATA_KEY; - bytenr = BTRFS_SUPER_INFO_OFFSET; - total_bytes = btrfs_super_total_bytes(root->fs_info->super_copy); + btrfs_init_path(&path); + ret = btrfs_search_slot(NULL, image_root, &key, &path, 0, 0); + /* + * It's possible that some fs doesn't store any (including sb) + * data into 0~1M range, and NO_HOLES is enabled. + * + * So we only need to check if ret < 0 + */ + if (ret < 0) { + error("failed to iterate file extents at offset 0: %s", + strerror(-ret)); + btrfs_release_path(&path); + return ret; + } + /* Loop from the first file extents */ while (1) { - ret = btrfs_map_block(&info->mapping_tree, WRITE, bytenr, - &length, &multi, 0, NULL); - if (ret) { - if (ret == -ENOENT) { - /* removed block group at the tail */ - if (length == (u64)-1) - break; + struct btrfs_file_extent_item *fi; + struct extent_buffer *leaf = path.nodes[0]; + u64 disk_bytenr; + u64 file_offset; + u64 ram_bytes; + int slot = path.slots[0]; - /* removed block group in the middle */ - goto next; - } - goto fail; + if (slot >= btrfs_header_nritems(leaf)) + goto next; + btrfs_item_key_to_cpu(leaf, &key, slot); + + /* + * Iteration is done, exit normally, we have extra check out of + * the loop + */ + if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) { + ret = 0; + break; + } + file_offset = key.offset; + fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); + if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG) { + ret = -EINVAL; + error( + "ino %llu offset %llu doesn't have a regular file extent", + ino, file_offset); + break; + } + if (btrfs_file_extent_compression(leaf, fi) || + btrfs_file_extent_encryption(leaf, fi) || + btrfs_file_extent_other_encoding(leaf, fi)) { + ret = -EINVAL; + error( + "ino %llu offset %llu doesn't have a plain file extent", + ino, file_offset); + break; } - num_stripes = multi->num_stripes; - physical = multi->stripes[0].physical; - free(multi); + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi); + ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi); - if (num_stripes != 1) { - error("num stripes for bytenr %llu is not 1", bytenr); - goto fail; - } + checked_bytes += ram_bytes; + /* Skip hole */ + if (disk_bytenr == 0) + goto next; /* - * Extra check for new convert, as metadata chunk from new - * convert is much more free than old convert, it doesn't need - * to do 1:1 mapping. + * Most file extents must be 1:1 mapped, which means 2 things: + * 1) File extent file offset == disk_bytenr + * 2) That data chunk's logical == chunk's physical + * + * So file extent's file offset == physical position on disk. + * + * And after rolling back btrfs reserved range, other part + * remains what old fs used to be. */ - if (physical != bytenr) { + if (file_offset != disk_bytenr || + !is_chunk_direct_mapped(fs_info, disk_bytenr)) { /* - * Check if it's a metadata chunk and has only metadata - * extent. + * Only file extent in btrfs reserved ranges are + * allowed to be non-1:1 mapped */ - ret = may_rollback_chunk(info, bytenr); - if (ret < 0) - goto fail; + if (!is_subset_of_reserved_ranges(file_offset, + ram_bytes)) { + ret = -EINVAL; + error( + "ino %llu offset %llu file extent should not be relocated", + ino, file_offset); + break; + } } next: - bytenr += length; - if (bytenr >= total_bytes) + ret = btrfs_next_item(image_root, &path); + if (ret) { + if (ret > 0) + ret = 0; break; + } } - return 0; -fail: - return -1; + btrfs_release_path(&path); + /* + * For HOLES mode (without NO_HOLES), we must ensure file extents + * cover the whole range of the image + */ + if (!ret && !btrfs_fs_incompat(fs_info, NO_HOLES)) { + if (checked_bytes != total_size) { + ret = -EINVAL; + error("inode %llu has some file extents not checked", + ino); + return ret; + } + } + + /* So far so good, read old data located in btrfs reserved ranges */ + ret = read_reserved_ranges(image_root, ino, total_size, + reserved_ranges); + return ret; } +/* + * btrfs rollback is just reverted convert: + * |<---------------Btrfs fs------------------------------>| + * |<- Old data chunk ->|< new chunk (D/M/S)>|<- ODC ->| + * |<-Old-FE->| |<-Old-FE->|<- Btrfs extents ->|<-Old-FE->| + * || + * \/ + * |<------------------Old fs----------------------------->| + * |<- used ->| |<- used ->| |<- used ->| + * + * However things are much easier than convert, we don't really need to + * do the complex space calculation, but only to handle btrfs reserved space + * + * |<---------------------------Btrfs fs----------------------------->| + * | RSV 1 | | Old | | RSV 2 | | Old | | RSV 3 | + * | 0~1M | | Fs | | SB2 + 64K | | Fs | | SB3 + 64K | + * + * On the other hande, the converted fs image in btrfs is a completely + * valid old fs. + * + * |<-----------------Converted fs image in btrfs-------------------->| + * | RSV 1 | | Old | | RSV 2 | | Old | | RSV 3 | + * | Relocated | | Fs | | Relocated | | Fs | | Relocated | + * + * Used space in fs image should be at the same physical position on disk. + * We only need to recover the data in reserved ranges, so the whole + * old fs is back. + * + * The idea to rollback is also straightforward, we just "read" out the data + * of reserved ranges, and write them back to there they should be. + * Then the old fs is back. + */ static int do_rollback(const char *devname) { - int fd = -1; - int ret; - int i; struct btrfs_root *root; struct btrfs_root *image_root; - struct btrfs_root *chunk_root; - struct btrfs_dir_item *dir; - struct btrfs_inode_item *inode; - struct btrfs_file_extent_item *fi; - struct btrfs_trans_handle *trans; - struct extent_buffer *leaf; - struct btrfs_block_group_cache *cache1; - struct btrfs_block_group_cache *cache2; + struct btrfs_fs_info *fs_info; struct btrfs_key key; struct btrfs_path path; - struct extent_io_tree io_tree; - char *buf = NULL; - char *name; - u64 bytenr; - u64 num_bytes; - u64 root_dir; - u64 objectid; - u64 offset; - u64 start; - u64 end; - u64 sb_bytenr; - u64 first_free; + struct btrfs_dir_item *dir; + struct btrfs_inode_item *inode_item; + char *image_name = "image"; + char *reserved_ranges[ARRAY_SIZE(btrfs_reserved_ranges)] = { NULL }; u64 total_bytes; - u32 sectorsize; + u64 fsize; + u64 root_dir; + u64 ino; + int fd = -1; + int ret; + int i; - extent_io_tree_init(&io_tree); + for (i = 0; i < ARRAY_SIZE(btrfs_reserved_ranges); i++) { + const struct simple_range *range = &btrfs_reserved_ranges[i]; + reserved_ranges[i] = calloc(1, range->len); + if (!reserved_ranges[i]) { + ret = -ENOMEM; + goto free_mem; + } + } fd = open(devname, O_RDWR); if (fd < 0) { error("unable to open %s: %s", devname, strerror(errno)); - goto fail; + ret = -EIO; + goto free_mem; } + fsize = lseek(fd, 0, SEEK_END); root = open_ctree_fd(fd, devname, 0, OPEN_CTREE_WRITES); if (!root) { error("unable to open ctree"); - goto fail; + ret = -EIO; + goto free_mem; } - ret = may_rollback(root); - if (ret < 0) { - error("unable to do rollback: %d", ret); - goto fail; - } - - sectorsize = root->sectorsize; - buf = malloc(sectorsize); - if (!buf) { - error("unable to allocate memory"); - goto fail; - } - - btrfs_init_path(&path); + fs_info = root->fs_info; + /* + * Search root backref first, or after subvolume deletion (orphan), + * we can still rollback the image. + */ key.objectid = CONV_IMAGE_SUBVOL_OBJECTID; key.type = BTRFS_ROOT_BACKREF_KEY; key.offset = BTRFS_FS_TREE_OBJECTID; - ret = btrfs_search_slot(NULL, root->fs_info->tree_root, &key, &path, 0, - 0); + btrfs_init_path(&path); + ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, &path, 0, 0); btrfs_release_path(&path); if (ret > 0) { - error("unable to convert ext2 image subvolume, is it deleted?"); - goto fail; + error("unable to find ext2 image subvolume, is it deleted?"); + ret = -ENOENT; + goto close_fs; } else if (ret < 0) { - error("unable to open ext2_saved, id %llu: %s", - (unsigned long long)key.objectid, strerror(-ret)); - goto fail; + error("failed to find ext2 image subvolume: %s", + strerror(-ret)); + goto close_fs; } + /* Search convert subvolume */ key.objectid = CONV_IMAGE_SUBVOL_OBJECTID; key.type = BTRFS_ROOT_ITEM_KEY; key.offset = (u64)-1; - image_root = btrfs_read_fs_root(root->fs_info, &key); - if (!image_root || IS_ERR(image_root)) { - error("unable to open subvolume %llu: %ld", - (unsigned long long)key.objectid, PTR_ERR(image_root)); - goto fail; + image_root = btrfs_read_fs_root(fs_info, &key); + if (IS_ERR(image_root)) { + ret = PTR_ERR(image_root); + error("failed to open convert image subvolume: %s", + strerror(-ret)); + goto close_fs; } - name = "image"; - root_dir = btrfs_root_dirid(&root->root_item); - dir = btrfs_lookup_dir_item(NULL, image_root, &path, - root_dir, name, strlen(name), 0); + /* Search the image file */ + root_dir = btrfs_root_dirid(&image_root->root_item); + dir = btrfs_lookup_dir_item(NULL, image_root, &path, root_dir, + image_name, strlen(image_name), 0); + if (!dir || IS_ERR(dir)) { - error("unable to find file %s: %ld", name, PTR_ERR(dir)); - goto fail; + btrfs_release_path(&path); + if (dir) + ret = PTR_ERR(dir); + else + ret = -ENOENT; + error("failed to locate file %s: %s", image_name, + strerror(-ret)); + goto close_fs; } - leaf = path.nodes[0]; - btrfs_dir_item_key_to_cpu(leaf, dir, &key); + btrfs_dir_item_key_to_cpu(path.nodes[0], dir, &key); btrfs_release_path(&path); - objectid = key.objectid; + /* Get total size of the original image */ + ino = key.objectid; ret = btrfs_lookup_inode(NULL, image_root, &path, &key, 0); - if (ret) { - error("unable to find inode item: %d", ret); - goto fail; - } - leaf = path.nodes[0]; - inode = btrfs_item_ptr(leaf, path.slots[0], struct btrfs_inode_item); - total_bytes = btrfs_inode_size(leaf, inode); - btrfs_release_path(&path); - key.objectid = objectid; - key.offset = 0; - key.type = BTRFS_EXTENT_DATA_KEY; - ret = btrfs_search_slot(NULL, image_root, &key, &path, 0, 0); - if (ret != 0) { - error("unable to find first file extent: %d", ret); + if (ret < 0) { btrfs_release_path(&path); - goto fail; - } - - /* build mapping tree for the relocated blocks */ - for (offset = 0; offset < total_bytes; ) { - leaf = path.nodes[0]; - if (path.slots[0] >= btrfs_header_nritems(leaf)) { - ret = btrfs_next_leaf(root, &path); - if (ret != 0) - break; - continue; - } - - btrfs_item_key_to_cpu(leaf, &key, path.slots[0]); - if (key.objectid != objectid || key.offset != offset || - key.type != BTRFS_EXTENT_DATA_KEY) - break; - - fi = btrfs_item_ptr(leaf, path.slots[0], - struct btrfs_file_extent_item); - if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG) - break; - if (btrfs_file_extent_compression(leaf, fi) || - btrfs_file_extent_encryption(leaf, fi) || - btrfs_file_extent_other_encoding(leaf, fi)) - break; - - bytenr = btrfs_file_extent_disk_bytenr(leaf, fi); - /* skip holes and direct mapped extents */ - if (bytenr == 0 || bytenr == offset) - goto next_extent; - - bytenr += btrfs_file_extent_offset(leaf, fi); - num_bytes = btrfs_file_extent_num_bytes(leaf, fi); - - cache1 = btrfs_lookup_block_group(root->fs_info, offset); - cache2 = btrfs_lookup_block_group(root->fs_info, - offset + num_bytes - 1); - /* - * Here we must take consideration of old and new convert - * behavior. - * For old convert case, sign, there is no consist chunk type - * that will cover the extent. META/DATA/SYS are all possible. - * Just ensure relocate one is in SYS chunk. - * For new convert case, they are all covered by DATA chunk. - * - * So, there is not valid chunk type check for it now. - */ - if (cache1 != cache2) - break; - - set_extent_bits(&io_tree, offset, offset + num_bytes - 1, - EXTENT_LOCKED, GFP_NOFS); - set_state_private(&io_tree, offset, bytenr); -next_extent: - offset += btrfs_file_extent_num_bytes(leaf, fi); - path.slots[0]++; + error("unable to find inode %llu: %s", ino, strerror(-ret)); + goto close_fs; } + inode_item = btrfs_item_ptr(path.nodes[0], path.slots[0], + struct btrfs_inode_item); + total_bytes = btrfs_inode_size(path.nodes[0], inode_item); btrfs_release_path(&path); - if (offset < total_bytes) { - error("unable to build extent mapping (offset %llu, total_bytes %llu)", - (unsigned long long)offset, - (unsigned long long)total_bytes); - error("converted filesystem after balance is unable to rollback"); - goto fail; + /* Check if we can rollback the image */ + ret = check_convert_image(image_root, ino, total_bytes, reserved_ranges); + if (ret < 0) { + error("old fs image can't be rolled back"); + goto close_fs; } +close_fs: + btrfs_release_path(&path); + close_ctree_fs_info(fs_info); + if (ret) + goto free_mem; - first_free = BTRFS_SUPER_INFO_OFFSET + 2 * sectorsize - 1; - first_free &= ~((u64)sectorsize - 1); - /* backup for extent #0 should exist */ - if(!test_range_bit(&io_tree, 0, first_free - 1, EXTENT_LOCKED, 1)) { - error("no backup for the first extent"); - goto fail; - } - /* force no allocation from system block group */ - root->fs_info->system_allocs = -1; - trans = btrfs_start_transaction(root, 1); - if (!trans) { - error("unable to start transaction"); - goto fail; - } /* - * recow the whole chunk tree, this will remove all chunk tree blocks - * from system block group + * Everything is OK, just write back old fs data into btrfs reserved + * ranges + * + * Here, we starts from the backup blocks first, so if something goes + * wrong, the fs is still mountable */ - chunk_root = root->fs_info->chunk_root; - memset(&key, 0, sizeof(key)); - while (1) { - ret = btrfs_search_slot(trans, chunk_root, &key, &path, 0, 1); - if (ret < 0) - break; - ret = btrfs_next_leaf(chunk_root, &path); - if (ret) - break; + for (i = ARRAY_SIZE(btrfs_reserved_ranges) - 1; i >= 0; i--) { + u64 real_size; + const struct simple_range *range = &btrfs_reserved_ranges[i]; - btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); - btrfs_release_path(&path); - } - btrfs_release_path(&path); - - offset = 0; - num_bytes = 0; - while(1) { - cache1 = btrfs_lookup_block_group(root->fs_info, offset); - if (!cache1) - break; - - if (cache1->flags & BTRFS_BLOCK_GROUP_SYSTEM) - num_bytes += btrfs_block_group_used(&cache1->item); - - offset = cache1->key.objectid + cache1->key.offset; - } - /* only extent #0 left in system block group? */ - if (num_bytes > first_free) { - error( - "unable to empty system block group (num_bytes %llu, first_free %llu", - (unsigned long long)num_bytes, - (unsigned long long)first_free); - goto fail; - } - /* create a system chunk that maps the whole device */ - ret = prepare_system_chunk_sb(root->fs_info->super_copy); - if (ret) { - error("unable to update system chunk: %d", ret); - goto fail; - } - - ret = btrfs_commit_transaction(trans, root); - if (ret) { - error("transaction commit failed: %d", ret); - goto fail; - } - - ret = close_ctree(root); - if (ret) { - error("close_ctree failed: %d", ret); - goto fail; - } - - /* zero btrfs super block mirrors */ - memset(buf, 0, sectorsize); - for (i = 1 ; i < BTRFS_SUPER_MIRROR_MAX; i++) { - bytenr = btrfs_sb_offset(i); - if (bytenr >= total_bytes) - break; - ret = pwrite(fd, buf, sectorsize, bytenr); - if (ret != sectorsize) { - error("zeroing superblock mirror %d failed: %d", - i, ret); - goto fail; - } - } - - sb_bytenr = (u64)-1; - /* copy all relocated blocks back */ - while(1) { - ret = find_first_extent_bit(&io_tree, 0, &start, &end, - EXTENT_LOCKED); - if (ret) - break; - - ret = get_state_private(&io_tree, start, &bytenr); - BUG_ON(ret); - - clear_extent_bits(&io_tree, start, end, EXTENT_LOCKED, - GFP_NOFS); + if (range_end(range) >= fsize) + continue; - while (start <= end) { - if (start == BTRFS_SUPER_INFO_OFFSET) { - sb_bytenr = bytenr; - goto next_sector; - } - ret = pread(fd, buf, sectorsize, bytenr); - if (ret < 0) { - error("reading superblock at %llu failed: %d", - (unsigned long long)bytenr, ret); - goto fail; - } - BUG_ON(ret != sectorsize); - ret = pwrite(fd, buf, sectorsize, start); - if (ret < 0) { - error("writing superblock at %llu failed: %d", - (unsigned long long)start, ret); - goto fail; - } - BUG_ON(ret != sectorsize); -next_sector: - start += sectorsize; - bytenr += sectorsize; + real_size = min(range_end(range), fsize) - range->start; + ret = pwrite(fd, reserved_ranges[i], real_size, range->start); + if (ret < real_size) { + if (ret < 0) + ret = -errno; + else + ret = -EIO; + error("failed to recover range [%llu, %llu): %s", + range->start, real_size, strerror(-ret)); + goto free_mem; } + ret = 0; } - ret = fsync(fd); - if (ret < 0) { - error("fsync failed: %s", strerror(errno)); - goto fail; - } - /* - * finally, overwrite btrfs super block. - */ - ret = pread(fd, buf, sectorsize, sb_bytenr); - if (ret < 0) { - error("reading primary superblock failed: %s", - strerror(errno)); - goto fail; - } - BUG_ON(ret != sectorsize); - ret = pwrite(fd, buf, sectorsize, BTRFS_SUPER_INFO_OFFSET); - if (ret < 0) { - error("writing primary superblock failed: %s", - strerror(errno)); - goto fail; - } - BUG_ON(ret != sectorsize); - ret = fsync(fd); - if (ret < 0) { - error("fsync failed: %s", strerror(errno)); - goto fail; - } - - close(fd); - free(buf); - extent_io_tree_cleanup(&io_tree); - printf("rollback complete\n"); - return 0; - -fail: - if (fd != -1) - close(fd); - free(buf); - error("rollback aborted"); - return -1; +free_mem: + for (i = 0; i < ARRAY_SIZE(btrfs_reserved_ranges); i++) + free(reserved_ranges[i]); + if (ret) + error("rollback failed"); + else + printf("rollback succeeded\n"); + return ret; } static void print_usage(void) @@ -3096,7 +1842,7 @@ int main(int argc, char *argv[]) rollback = 1; break; case 'l': - copylabel = -1; + copylabel = CONVERT_FLAG_SET_LABEL; if (strlen(optarg) >= BTRFS_LABEL_SIZE) { warning( "label too long, trimmed to %d bytes", @@ -3105,7 +1851,7 @@ int main(int argc, char *argv[]) __strncpy_null(fslabel, optarg, BTRFS_LABEL_SIZE - 1); break; case 'L': - copylabel = 1; + copylabel = CONVERT_FLAG_COPY_LABEL; break; case 'p': progress = 1; @@ -3178,8 +1924,13 @@ int main(int argc, char *argv[]) if (rollback) { ret = do_rollback(file); } else { - ret = do_convert(file, datacsum, packing, noxattr, nodesize, - copylabel, fslabel, progress, features); + u32 cf = 0; + + cf |= datacsum ? CONVERT_FLAG_DATACSUM : 0; + cf |= packing ? CONVERT_FLAG_INLINE_DATA : 0; + cf |= noxattr ? 0 : CONVERT_FLAG_XATTR; + cf |= copylabel; + ret = do_convert(file, cf, nodesize, fslabel, progress, features); } if (ret) return 1; diff --git a/convert/source-ext2.c b/convert/source-ext2.c new file mode 100644 index 00000000..24744e22 --- /dev/null +++ b/convert/source-ext2.c @@ -0,0 +1,886 @@ +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +#if BTRFSCONVERT_EXT2 + +#include "kerncompat.h" +#include <linux/limits.h> +#include <pthread.h> +#include "disk-io.h" +#include "transaction.h" +#include "utils.h" +#include "convert/common.h" +#include "convert/source-ext2.h" + +/* + * Open Ext2fs in readonly mode, read block allocation bitmap and + * inode bitmap into memory. + */ +static int ext2_open_fs(struct btrfs_convert_context *cctx, const char *name) +{ + errcode_t ret; + ext2_filsys ext2_fs; + ext2_ino_t ino; + u32 ro_feature; + int open_flag = EXT2_FLAG_SOFTSUPP_FEATURES | EXT2_FLAG_64BITS; + + ret = ext2fs_open(name, open_flag, 0, 0, unix_io_manager, &ext2_fs); + if (ret) { + fprintf(stderr, "ext2fs_open: %s\n", error_message(ret)); + return -1; + } + /* + * We need to know exactly the used space, some RO compat flags like + * BIGALLOC will affect how used space is present. + * So we need manuall check any unsupported RO compat flags + */ + ro_feature = ext2_fs->super->s_feature_ro_compat; + if (ro_feature & ~EXT2_LIB_FEATURE_RO_COMPAT_SUPP) { + error( +"unsupported RO features detected: %x, abort convert to avoid possible corruption", + ro_feature & ~EXT2_LIB_FEATURE_COMPAT_SUPP); + goto fail; + } + ret = ext2fs_read_inode_bitmap(ext2_fs); + if (ret) { + fprintf(stderr, "ext2fs_read_inode_bitmap: %s\n", + error_message(ret)); + goto fail; + } + ret = ext2fs_read_block_bitmap(ext2_fs); + if (ret) { + fprintf(stderr, "ext2fs_read_block_bitmap: %s\n", + error_message(ret)); + goto fail; + } + /* + * search each block group for a free inode. this set up + * uninit block/inode bitmaps appropriately. + */ + ino = 1; + while (ino <= ext2_fs->super->s_inodes_count) { + ext2_ino_t foo; + ext2fs_new_inode(ext2_fs, ino, 0, NULL, &foo); + ino += EXT2_INODES_PER_GROUP(ext2_fs->super); + } + + if (!(ext2_fs->super->s_feature_incompat & + EXT2_FEATURE_INCOMPAT_FILETYPE)) { + error("filetype feature is missing"); + goto fail; + } + + cctx->fs_data = ext2_fs; + cctx->blocksize = ext2_fs->blocksize; + cctx->block_count = ext2_fs->super->s_blocks_count; + cctx->total_bytes = ext2_fs->blocksize * ext2_fs->super->s_blocks_count; + cctx->volume_name = strndup(ext2_fs->super->s_volume_name, 16); + cctx->first_data_block = ext2_fs->super->s_first_data_block; + cctx->inodes_count = ext2_fs->super->s_inodes_count; + cctx->free_inodes_count = ext2_fs->super->s_free_inodes_count; + return 0; +fail: + ext2fs_close(ext2_fs); + return -1; +} + +static int __ext2_add_one_block(ext2_filsys fs, char *bitmap, + unsigned long group_nr, struct cache_tree *used) +{ + unsigned long offset; + unsigned i; + int ret = 0; + + offset = fs->super->s_first_data_block; + offset /= EXT2FS_CLUSTER_RATIO(fs); + offset += group_nr * EXT2_CLUSTERS_PER_GROUP(fs->super); + for (i = 0; i < EXT2_CLUSTERS_PER_GROUP(fs->super); i++) { + if ((i + offset) >= ext2fs_blocks_count(fs->super)) + break; + + if (ext2fs_test_bit(i, bitmap)) { + u64 start; + + start = (i + offset) * EXT2FS_CLUSTER_RATIO(fs); + start *= fs->blocksize; + ret = add_merge_cache_extent(used, start, + fs->blocksize); + if (ret < 0) + break; + } + } + return ret; +} + +/* + * Read all used ext2 space into cctx->used cache tree + */ +static int ext2_read_used_space(struct btrfs_convert_context *cctx) +{ + ext2_filsys fs = (ext2_filsys)cctx->fs_data; + blk64_t blk_itr = EXT2FS_B2C(fs, fs->super->s_first_data_block); + struct cache_tree *used_tree = &cctx->used_space; + char *block_bitmap = NULL; + unsigned long i; + int block_nbytes; + int ret = 0; + + block_nbytes = EXT2_CLUSTERS_PER_GROUP(fs->super) / 8; + if (!block_nbytes) { + error("EXT2_CLUSTERS_PER_GROUP too small: %llu", + (unsigned long long)(EXT2_CLUSTERS_PER_GROUP(fs->super))); + return -EINVAL; + } + + block_bitmap = malloc(block_nbytes); + if (!block_bitmap) + return -ENOMEM; + + for (i = 0; i < fs->group_desc_count; i++) { + ret = ext2fs_get_block_bitmap_range2(fs->block_map, blk_itr, + block_nbytes * 8, block_bitmap); + if (ret) { + error("fail to get bitmap from ext2, %s", + strerror(-ret)); + break; + } + ret = __ext2_add_one_block(fs, block_bitmap, i, used_tree); + if (ret < 0) { + error("fail to build used space tree, %s", + strerror(-ret)); + break; + } + blk_itr += EXT2_CLUSTERS_PER_GROUP(fs->super); + } + + free(block_bitmap); + return ret; +} + +static void ext2_close_fs(struct btrfs_convert_context *cctx) +{ + if (cctx->volume_name) { + free(cctx->volume_name); + cctx->volume_name = NULL; + } + ext2fs_close(cctx->fs_data); +} + +static u8 ext2_filetype_conversion_table[EXT2_FT_MAX] = { + [EXT2_FT_UNKNOWN] = BTRFS_FT_UNKNOWN, + [EXT2_FT_REG_FILE] = BTRFS_FT_REG_FILE, + [EXT2_FT_DIR] = BTRFS_FT_DIR, + [EXT2_FT_CHRDEV] = BTRFS_FT_CHRDEV, + [EXT2_FT_BLKDEV] = BTRFS_FT_BLKDEV, + [EXT2_FT_FIFO] = BTRFS_FT_FIFO, + [EXT2_FT_SOCK] = BTRFS_FT_SOCK, + [EXT2_FT_SYMLINK] = BTRFS_FT_SYMLINK, +}; + +static int ext2_dir_iterate_proc(ext2_ino_t dir, int entry, + struct ext2_dir_entry *dirent, + int offset, int blocksize, + char *buf,void *priv_data) +{ + int ret; + int file_type; + u64 objectid; + char dotdot[] = ".."; + struct dir_iterate_data *idata = (struct dir_iterate_data *)priv_data; + int name_len; + + name_len = dirent->name_len & 0xFF; + + objectid = dirent->inode + INO_OFFSET; + if (!strncmp(dirent->name, dotdot, name_len)) { + if (name_len == 2) { + BUG_ON(idata->parent != 0); + idata->parent = objectid; + } + return 0; + } + if (dirent->inode < EXT2_GOOD_OLD_FIRST_INO) + return 0; + + file_type = dirent->name_len >> 8; + BUG_ON(file_type > EXT2_FT_SYMLINK); + + ret = convert_insert_dirent(idata->trans, idata->root, dirent->name, + name_len, idata->objectid, objectid, + ext2_filetype_conversion_table[file_type], + idata->index_cnt, idata->inode); + if (ret < 0) { + idata->errcode = ret; + return BLOCK_ABORT; + } + + idata->index_cnt++; + return 0; +} + +static int ext2_create_dir_entries(struct btrfs_trans_handle *trans, + struct btrfs_root *root, u64 objectid, + struct btrfs_inode_item *btrfs_inode, + ext2_filsys ext2_fs, ext2_ino_t ext2_ino) +{ + int ret; + errcode_t err; + struct dir_iterate_data data = { + .trans = trans, + .root = root, + .inode = btrfs_inode, + .objectid = objectid, + .index_cnt = 2, + .parent = 0, + .errcode = 0, + }; + + err = ext2fs_dir_iterate2(ext2_fs, ext2_ino, 0, NULL, + ext2_dir_iterate_proc, &data); + if (err) + goto error; + ret = data.errcode; + if (ret == 0 && data.parent == objectid) { + ret = btrfs_insert_inode_ref(trans, root, "..", 2, + objectid, objectid, 0); + } + return ret; +error: + fprintf(stderr, "ext2fs_dir_iterate2: %s\n", error_message(err)); + return -1; +} + +static int ext2_block_iterate_proc(ext2_filsys fs, blk_t *blocknr, + e2_blkcnt_t blockcnt, blk_t ref_block, + int ref_offset, void *priv_data) +{ + int ret; + struct blk_iterate_data *idata; + idata = (struct blk_iterate_data *)priv_data; + ret = block_iterate_proc(*blocknr, blockcnt, idata); + if (ret) { + idata->errcode = ret; + return BLOCK_ABORT; + } + return 0; +} + +/* + * traverse file's data blocks, record these data blocks as file extents. + */ +static int ext2_create_file_extents(struct btrfs_trans_handle *trans, + struct btrfs_root *root, u64 objectid, + struct btrfs_inode_item *btrfs_inode, + ext2_filsys ext2_fs, ext2_ino_t ext2_ino, + u32 convert_flags) +{ + int ret; + char *buffer = NULL; + errcode_t err; + u32 last_block; + u32 sectorsize = root->fs_info->sectorsize; + u64 inode_size = btrfs_stack_inode_size(btrfs_inode); + struct blk_iterate_data data; + + init_blk_iterate_data(&data, trans, root, btrfs_inode, objectid, + convert_flags & CONVERT_FLAG_DATACSUM); + + err = ext2fs_block_iterate2(ext2_fs, ext2_ino, BLOCK_FLAG_DATA_ONLY, + NULL, ext2_block_iterate_proc, &data); + if (err) + goto error; + ret = data.errcode; + if (ret) + goto fail; + if ((convert_flags & CONVERT_FLAG_INLINE_DATA) && data.first_block == 0 + && data.num_blocks > 0 + && inode_size <= BTRFS_MAX_INLINE_DATA_SIZE(root)) { + u64 num_bytes = data.num_blocks * sectorsize; + u64 disk_bytenr = data.disk_block * sectorsize; + u64 nbytes; + + buffer = malloc(num_bytes); + if (!buffer) + return -ENOMEM; + ret = read_disk_extent(root, disk_bytenr, num_bytes, buffer); + if (ret) + goto fail; + if (num_bytes > inode_size) + num_bytes = inode_size; + ret = btrfs_insert_inline_extent(trans, root, objectid, + 0, buffer, num_bytes); + if (ret) + goto fail; + nbytes = btrfs_stack_inode_nbytes(btrfs_inode) + num_bytes; + btrfs_set_stack_inode_nbytes(btrfs_inode, nbytes); + } else if (data.num_blocks > 0) { + ret = record_file_blocks(&data, data.first_block, + data.disk_block, data.num_blocks); + if (ret) + goto fail; + } + data.first_block += data.num_blocks; + last_block = (inode_size + sectorsize - 1) / sectorsize; + if (last_block > data.first_block) { + ret = record_file_blocks(&data, data.first_block, 0, + last_block - data.first_block); + } +fail: + free(buffer); + return ret; +error: + fprintf(stderr, "ext2fs_block_iterate2: %s\n", error_message(err)); + return -1; +} + +static int ext2_create_symlink(struct btrfs_trans_handle *trans, + struct btrfs_root *root, u64 objectid, + struct btrfs_inode_item *btrfs_inode, + ext2_filsys ext2_fs, ext2_ino_t ext2_ino, + struct ext2_inode *ext2_inode) +{ + int ret; + char *pathname; + u64 inode_size = btrfs_stack_inode_size(btrfs_inode); + if (ext2fs_inode_data_blocks2(ext2_fs, ext2_inode)) { + btrfs_set_stack_inode_size(btrfs_inode, inode_size + 1); + ret = ext2_create_file_extents(trans, root, objectid, + btrfs_inode, ext2_fs, ext2_ino, + CONVERT_FLAG_DATACSUM | + CONVERT_FLAG_INLINE_DATA); + btrfs_set_stack_inode_size(btrfs_inode, inode_size); + return ret; + } + + pathname = (char *)&(ext2_inode->i_block[0]); + BUG_ON(pathname[inode_size] != 0); + ret = btrfs_insert_inline_extent(trans, root, objectid, 0, + pathname, inode_size + 1); + btrfs_set_stack_inode_nbytes(btrfs_inode, inode_size + 1); + return ret; +} + +/* + * Following xattr/acl related codes are based on codes in + * fs/ext3/xattr.c and fs/ext3/acl.c + */ +#define EXT2_XATTR_BHDR(ptr) ((struct ext2_ext_attr_header *)(ptr)) +#define EXT2_XATTR_BFIRST(ptr) \ + ((struct ext2_ext_attr_entry *)(EXT2_XATTR_BHDR(ptr) + 1)) +#define EXT2_XATTR_IHDR(inode) \ + ((struct ext2_ext_attr_header *) ((void *)(inode) + \ + EXT2_GOOD_OLD_INODE_SIZE + (inode)->i_extra_isize)) +#define EXT2_XATTR_IFIRST(inode) \ + ((struct ext2_ext_attr_entry *) ((void *)EXT2_XATTR_IHDR(inode) + \ + sizeof(EXT2_XATTR_IHDR(inode)->h_magic))) + +static int ext2_xattr_check_names(struct ext2_ext_attr_entry *entry, + const void *end) +{ + struct ext2_ext_attr_entry *next; + + while (!EXT2_EXT_IS_LAST_ENTRY(entry)) { + next = EXT2_EXT_ATTR_NEXT(entry); + if ((void *)next >= end) + return -EIO; + entry = next; + } + return 0; +} + +static int ext2_xattr_check_block(const char *buf, size_t size) +{ + int error; + struct ext2_ext_attr_header *header = EXT2_XATTR_BHDR(buf); + + if (header->h_magic != EXT2_EXT_ATTR_MAGIC || + header->h_blocks != 1) + return -EIO; + error = ext2_xattr_check_names(EXT2_XATTR_BFIRST(buf), buf + size); + return error; +} + +static int ext2_xattr_check_entry(struct ext2_ext_attr_entry *entry, + size_t size) +{ + size_t value_size = entry->e_value_size; + + if (entry->e_value_block != 0 || value_size > size || + entry->e_value_offs + value_size > size) + return -EIO; + return 0; +} + +static inline int ext2_acl_count(size_t size) +{ + ssize_t s; + size -= sizeof(ext2_acl_header); + s = size - 4 * sizeof(ext2_acl_entry_short); + if (s < 0) { + if (size % sizeof(ext2_acl_entry_short)) + return -1; + return size / sizeof(ext2_acl_entry_short); + } else { + if (s % sizeof(ext2_acl_entry)) + return -1; + return s / sizeof(ext2_acl_entry) + 4; + } +} + +static inline size_t acl_ea_size(int count) +{ + return sizeof(acl_ea_header) + count * sizeof(acl_ea_entry); +} + +static int ext2_acl_to_xattr(void *dst, const void *src, + size_t dst_size, size_t src_size) +{ + int i, count; + const void *end = src + src_size; + acl_ea_header *ext_acl = (acl_ea_header *)dst; + acl_ea_entry *dst_entry = ext_acl->a_entries; + ext2_acl_entry *src_entry; + + if (src_size < sizeof(ext2_acl_header)) + goto fail; + if (((ext2_acl_header *)src)->a_version != + cpu_to_le32(EXT2_ACL_VERSION)) + goto fail; + src += sizeof(ext2_acl_header); + count = ext2_acl_count(src_size); + if (count <= 0) + goto fail; + + BUG_ON(dst_size < acl_ea_size(count)); + ext_acl->a_version = cpu_to_le32(ACL_EA_VERSION); + for (i = 0; i < count; i++, dst_entry++) { + src_entry = (ext2_acl_entry *)src; + if (src + sizeof(ext2_acl_entry_short) > end) + goto fail; + dst_entry->e_tag = src_entry->e_tag; + dst_entry->e_perm = src_entry->e_perm; + switch (le16_to_cpu(src_entry->e_tag)) { + case ACL_USER_OBJ: + case ACL_GROUP_OBJ: + case ACL_MASK: + case ACL_OTHER: + src += sizeof(ext2_acl_entry_short); + dst_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); + break; + case ACL_USER: + case ACL_GROUP: + src += sizeof(ext2_acl_entry); + if (src > end) + goto fail; + dst_entry->e_id = src_entry->e_id; + break; + default: + goto fail; + } + } + if (src != end) + goto fail; + return 0; +fail: + return -EINVAL; +} + +static char *xattr_prefix_table[] = { + [1] = "user.", + [2] = "system.posix_acl_access", + [3] = "system.posix_acl_default", + [4] = "trusted.", + [6] = "security.", +}; + +static int ext2_copy_single_xattr(struct btrfs_trans_handle *trans, + struct btrfs_root *root, u64 objectid, + struct ext2_ext_attr_entry *entry, + const void *data, u32 datalen) +{ + int ret = 0; + int name_len; + int name_index; + void *databuf = NULL; + char namebuf[XATTR_NAME_MAX + 1]; + + name_index = entry->e_name_index; + if (name_index >= ARRAY_SIZE(xattr_prefix_table) || + xattr_prefix_table[name_index] == NULL) + return -EOPNOTSUPP; + name_len = strlen(xattr_prefix_table[name_index]) + + entry->e_name_len; + if (name_len >= sizeof(namebuf)) + return -ERANGE; + + if (name_index == 2 || name_index == 3) { + size_t bufsize = acl_ea_size(ext2_acl_count(datalen)); + databuf = malloc(bufsize); + if (!databuf) + return -ENOMEM; + ret = ext2_acl_to_xattr(databuf, data, bufsize, datalen); + if (ret) + goto out; + data = databuf; + datalen = bufsize; + } + strncpy(namebuf, xattr_prefix_table[name_index], XATTR_NAME_MAX); + strncat(namebuf, EXT2_EXT_ATTR_NAME(entry), entry->e_name_len); + if (name_len + datalen > BTRFS_LEAF_DATA_SIZE(root) - + sizeof(struct btrfs_item) - sizeof(struct btrfs_dir_item)) { + fprintf(stderr, "skip large xattr on inode %Lu name %.*s\n", + objectid - INO_OFFSET, name_len, namebuf); + goto out; + } + ret = btrfs_insert_xattr_item(trans, root, namebuf, name_len, + data, datalen, objectid); +out: + free(databuf); + return ret; +} + +static int ext2_copy_extended_attrs(struct btrfs_trans_handle *trans, + struct btrfs_root *root, u64 objectid, + struct btrfs_inode_item *btrfs_inode, + ext2_filsys ext2_fs, ext2_ino_t ext2_ino) +{ + int ret = 0; + int inline_ea = 0; + errcode_t err; + u32 datalen; + u32 block_size = ext2_fs->blocksize; + u32 inode_size = EXT2_INODE_SIZE(ext2_fs->super); + struct ext2_inode_large *ext2_inode; + struct ext2_ext_attr_entry *entry; + void *data; + char *buffer = NULL; + char inode_buf[EXT2_GOOD_OLD_INODE_SIZE]; + + if (inode_size <= EXT2_GOOD_OLD_INODE_SIZE) { + ext2_inode = (struct ext2_inode_large *)inode_buf; + } else { + ext2_inode = (struct ext2_inode_large *)malloc(inode_size); + if (!ext2_inode) + return -ENOMEM; + } + err = ext2fs_read_inode_full(ext2_fs, ext2_ino, (void *)ext2_inode, + inode_size); + if (err) { + fprintf(stderr, "ext2fs_read_inode_full: %s\n", + error_message(err)); + ret = -1; + goto out; + } + + if (ext2_ino > ext2_fs->super->s_first_ino && + inode_size > EXT2_GOOD_OLD_INODE_SIZE) { + if (EXT2_GOOD_OLD_INODE_SIZE + + ext2_inode->i_extra_isize > inode_size) { + ret = -EIO; + goto out; + } + if (ext2_inode->i_extra_isize != 0 && + EXT2_XATTR_IHDR(ext2_inode)->h_magic == + EXT2_EXT_ATTR_MAGIC) { + inline_ea = 1; + } + } + if (inline_ea) { + int total; + void *end = (void *)ext2_inode + inode_size; + entry = EXT2_XATTR_IFIRST(ext2_inode); + total = end - (void *)entry; + ret = ext2_xattr_check_names(entry, end); + if (ret) + goto out; + while (!EXT2_EXT_IS_LAST_ENTRY(entry)) { + ret = ext2_xattr_check_entry(entry, total); + if (ret) + goto out; + data = (void *)EXT2_XATTR_IFIRST(ext2_inode) + + entry->e_value_offs; + datalen = entry->e_value_size; + ret = ext2_copy_single_xattr(trans, root, objectid, + entry, data, datalen); + if (ret) + goto out; + entry = EXT2_EXT_ATTR_NEXT(entry); + } + } + + if (ext2_inode->i_file_acl == 0) + goto out; + + buffer = malloc(block_size); + if (!buffer) { + ret = -ENOMEM; + goto out; + } + err = ext2fs_read_ext_attr2(ext2_fs, ext2_inode->i_file_acl, buffer); + if (err) { + fprintf(stderr, "ext2fs_read_ext_attr2: %s\n", + error_message(err)); + ret = -1; + goto out; + } + ret = ext2_xattr_check_block(buffer, block_size); + if (ret) + goto out; + + entry = EXT2_XATTR_BFIRST(buffer); + while (!EXT2_EXT_IS_LAST_ENTRY(entry)) { + ret = ext2_xattr_check_entry(entry, block_size); + if (ret) + goto out; + data = buffer + entry->e_value_offs; + datalen = entry->e_value_size; + ret = ext2_copy_single_xattr(trans, root, objectid, + entry, data, datalen); + if (ret) + goto out; + entry = EXT2_EXT_ATTR_NEXT(entry); + } +out: + free(buffer); + if ((void *)ext2_inode != inode_buf) + free(ext2_inode); + return ret; +} +#define MINORBITS 20 +#define MKDEV(ma, mi) (((ma) << MINORBITS) | (mi)) + +static inline dev_t old_decode_dev(u16 val) +{ + return MKDEV((val >> 8) & 255, val & 255); +} + +static inline dev_t new_decode_dev(u32 dev) +{ + unsigned major = (dev & 0xfff00) >> 8; + unsigned minor = (dev & 0xff) | ((dev >> 12) & 0xfff00); + return MKDEV(major, minor); +} + +static void ext2_copy_inode_item(struct btrfs_inode_item *dst, + struct ext2_inode *src, u32 blocksize) +{ + btrfs_set_stack_inode_generation(dst, 1); + btrfs_set_stack_inode_sequence(dst, 0); + btrfs_set_stack_inode_transid(dst, 1); + btrfs_set_stack_inode_size(dst, src->i_size); + btrfs_set_stack_inode_nbytes(dst, 0); + btrfs_set_stack_inode_block_group(dst, 0); + btrfs_set_stack_inode_nlink(dst, src->i_links_count); + btrfs_set_stack_inode_uid(dst, src->i_uid | (src->i_uid_high << 16)); + btrfs_set_stack_inode_gid(dst, src->i_gid | (src->i_gid_high << 16)); + btrfs_set_stack_inode_mode(dst, src->i_mode); + btrfs_set_stack_inode_rdev(dst, 0); + btrfs_set_stack_inode_flags(dst, 0); + btrfs_set_stack_timespec_sec(&dst->atime, src->i_atime); + btrfs_set_stack_timespec_nsec(&dst->atime, 0); + btrfs_set_stack_timespec_sec(&dst->ctime, src->i_ctime); + btrfs_set_stack_timespec_nsec(&dst->ctime, 0); + btrfs_set_stack_timespec_sec(&dst->mtime, src->i_mtime); + btrfs_set_stack_timespec_nsec(&dst->mtime, 0); + btrfs_set_stack_timespec_sec(&dst->otime, 0); + btrfs_set_stack_timespec_nsec(&dst->otime, 0); + + if (S_ISDIR(src->i_mode)) { + btrfs_set_stack_inode_size(dst, 0); + btrfs_set_stack_inode_nlink(dst, 1); + } + if (S_ISREG(src->i_mode)) { + btrfs_set_stack_inode_size(dst, (u64)src->i_size_high << 32 | + (u64)src->i_size); + } + if (!S_ISREG(src->i_mode) && !S_ISDIR(src->i_mode) && + !S_ISLNK(src->i_mode)) { + if (src->i_block[0]) { + btrfs_set_stack_inode_rdev(dst, + old_decode_dev(src->i_block[0])); + } else { + btrfs_set_stack_inode_rdev(dst, + new_decode_dev(src->i_block[1])); + } + } + memset(&dst->reserved, 0, sizeof(dst->reserved)); +} +static int ext2_check_state(struct btrfs_convert_context *cctx) +{ + ext2_filsys fs = cctx->fs_data; + + if (!(fs->super->s_state & EXT2_VALID_FS)) + return 1; + else if (fs->super->s_state & EXT2_ERROR_FS) + return 1; + else + return 0; +} + +/* EXT2_*_FL to BTRFS_INODE_FLAG_* stringification helper */ +#define COPY_ONE_EXT2_FLAG(flags, ext2_inode, name) ({ \ + if (ext2_inode->i_flags & EXT2_##name##_FL) \ + flags |= BTRFS_INODE_##name; \ +}) + +/* + * Convert EXT2_*_FL to corresponding BTRFS_INODE_* flags + * + * Only a subset of EXT_*_FL is supported in btrfs. + */ +static void ext2_convert_inode_flags(struct btrfs_inode_item *dst, + struct ext2_inode *src) +{ + u64 flags = btrfs_stack_inode_flags(dst); + + COPY_ONE_EXT2_FLAG(flags, src, APPEND); + COPY_ONE_EXT2_FLAG(flags, src, SYNC); + COPY_ONE_EXT2_FLAG(flags, src, IMMUTABLE); + COPY_ONE_EXT2_FLAG(flags, src, NODUMP); + COPY_ONE_EXT2_FLAG(flags, src, NOATIME); + COPY_ONE_EXT2_FLAG(flags, src, DIRSYNC); + btrfs_set_stack_inode_flags(dst, flags); +} + +/* + * copy a single inode. do all the required works, such as cloning + * inode item, creating file extents and creating directory entries. + */ +static int ext2_copy_single_inode(struct btrfs_trans_handle *trans, + struct btrfs_root *root, u64 objectid, + ext2_filsys ext2_fs, ext2_ino_t ext2_ino, + struct ext2_inode *ext2_inode, + u32 convert_flags) +{ + int ret; + struct btrfs_inode_item btrfs_inode; + + if (ext2_inode->i_links_count == 0) + return 0; + + ext2_copy_inode_item(&btrfs_inode, ext2_inode, ext2_fs->blocksize); + if (!(convert_flags & CONVERT_FLAG_DATACSUM) + && S_ISREG(ext2_inode->i_mode)) { + u32 flags = btrfs_stack_inode_flags(&btrfs_inode) | + BTRFS_INODE_NODATASUM; + btrfs_set_stack_inode_flags(&btrfs_inode, flags); + } + ext2_convert_inode_flags(&btrfs_inode, ext2_inode); + + switch (ext2_inode->i_mode & S_IFMT) { + case S_IFREG: + ret = ext2_create_file_extents(trans, root, objectid, + &btrfs_inode, ext2_fs, ext2_ino, convert_flags); + break; + case S_IFDIR: + ret = ext2_create_dir_entries(trans, root, objectid, + &btrfs_inode, ext2_fs, ext2_ino); + break; + case S_IFLNK: + ret = ext2_create_symlink(trans, root, objectid, + &btrfs_inode, ext2_fs, ext2_ino, ext2_inode); + break; + default: + ret = 0; + break; + } + if (ret) + return ret; + + if (convert_flags & CONVERT_FLAG_XATTR) { + ret = ext2_copy_extended_attrs(trans, root, objectid, + &btrfs_inode, ext2_fs, ext2_ino); + if (ret) + return ret; + } + return btrfs_insert_inode(trans, root, objectid, &btrfs_inode); +} + +static int ext2_is_special_inode(ext2_ino_t ino) +{ + if (ino < EXT2_GOOD_OLD_FIRST_INO && ino != EXT2_ROOT_INO) + return 1; + return 0; +} + +/* + * scan ext2's inode bitmap and copy all used inodes. + */ +static int ext2_copy_inodes(struct btrfs_convert_context *cctx, + struct btrfs_root *root, + u32 convert_flags, struct task_ctx *p) +{ + ext2_filsys ext2_fs = cctx->fs_data; + int ret; + errcode_t err; + ext2_inode_scan ext2_scan; + struct ext2_inode ext2_inode; + ext2_ino_t ext2_ino; + u64 objectid; + struct btrfs_trans_handle *trans; + + trans = btrfs_start_transaction(root, 1); + if (!trans) + return -ENOMEM; + err = ext2fs_open_inode_scan(ext2_fs, 0, &ext2_scan); + if (err) { + fprintf(stderr, "ext2fs_open_inode_scan: %s\n", error_message(err)); + return -1; + } + while (!(err = ext2fs_get_next_inode(ext2_scan, &ext2_ino, + &ext2_inode))) { + /* no more inodes */ + if (ext2_ino == 0) + break; + if (ext2_is_special_inode(ext2_ino)) + continue; + objectid = ext2_ino + INO_OFFSET; + ret = ext2_copy_single_inode(trans, root, + objectid, ext2_fs, ext2_ino, + &ext2_inode, convert_flags); + pthread_mutex_lock(&p->mutex); + p->cur_copy_inodes++; + pthread_mutex_unlock(&p->mutex); + if (ret) + return ret; + if (trans->blocks_used >= 4096) { + ret = btrfs_commit_transaction(trans, root); + BUG_ON(ret); + trans = btrfs_start_transaction(root, 1); + BUG_ON(!trans); + } + } + if (err) { + fprintf(stderr, "ext2fs_get_next_inode: %s\n", error_message(err)); + return -1; + } + ret = btrfs_commit_transaction(trans, root); + BUG_ON(ret); + ext2fs_close_inode_scan(ext2_scan); + + return ret; +} + +const struct btrfs_convert_operations ext2_convert_ops = { + .name = "ext2", + .open_fs = ext2_open_fs, + .read_used_space = ext2_read_used_space, + .copy_inodes = ext2_copy_inodes, + .close_fs = ext2_close_fs, + .check_state = ext2_check_state, +}; + +#endif /* BTRFSCONVERT_EXT2 */ diff --git a/convert/source-ext2.h b/convert/source-ext2.h new file mode 100644 index 00000000..20a278ed --- /dev/null +++ b/convert/source-ext2.h @@ -0,0 +1,113 @@ +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +#ifndef __BTRFS_CONVERT_SOURCE_EXT2_H__ +#define __BTRFS_CONVERT_SOURCE_EXT2_H__ + +#if BTRFSCONVERT_EXT2 + +#include "kerncompat.h" + +#include <ext2fs/ext2_fs.h> +#include <ext2fs/ext2fs.h> +#include <ext2fs/ext2_ext_attr.h> +#include "convert/source-fs.h" + +#define INO_OFFSET (BTRFS_FIRST_FREE_OBJECTID - EXT2_ROOT_INO) + +/* + * Compatibility code for e2fsprogs 1.41 which doesn't support RO compat flag + * BIGALLOC. + * Unlike normal RO compat flag, BIGALLOC affects how e2fsprogs check used + * space, and btrfs-convert heavily relies on it. + */ +#ifdef HAVE_OLD_E2FSPROGS +#define EXT2FS_CLUSTER_RATIO(fs) (1) +#define EXT2_CLUSTERS_PER_GROUP(s) (EXT2_BLOCKS_PER_GROUP(s)) +#define EXT2FS_B2C(fs, blk) (blk) +#endif + +/* + * Following xattr/acl related codes are based on codes in + * fs/ext3/xattr.c and fs/ext3/acl.c + */ +#define EXT2_XATTR_BHDR(ptr) ((struct ext2_ext_attr_header *)(ptr)) +#define EXT2_XATTR_BFIRST(ptr) \ + ((struct ext2_ext_attr_entry *)(EXT2_XATTR_BHDR(ptr) + 1)) +#define EXT2_XATTR_IHDR(inode) \ + ((struct ext2_ext_attr_header *) ((void *)(inode) + \ + EXT2_GOOD_OLD_INODE_SIZE + (inode)->i_extra_isize)) +#define EXT2_XATTR_IFIRST(inode) \ + ((struct ext2_ext_attr_entry *) ((void *)EXT2_XATTR_IHDR(inode) + \ + sizeof(EXT2_XATTR_IHDR(inode)->h_magic))) + +struct dir_iterate_data { + struct btrfs_trans_handle *trans; + struct btrfs_root *root; + struct btrfs_inode_item *inode; + u64 objectid; + u64 index_cnt; + u64 parent; + int errcode; +}; + +#define EXT2_ACL_VERSION 0x0001 + +/* 23.2.5 acl_tag_t values */ + +#define ACL_UNDEFINED_TAG (0x00) +#define ACL_USER_OBJ (0x01) +#define ACL_USER (0x02) +#define ACL_GROUP_OBJ (0x04) +#define ACL_GROUP (0x08) +#define ACL_MASK (0x10) +#define ACL_OTHER (0x20) + +/* 23.2.7 ACL qualifier constants */ + +#define ACL_UNDEFINED_ID ((id_t)-1) + +typedef struct { + __le16 e_tag; + __le16 e_perm; + __le32 e_id; +} ext2_acl_entry; + +typedef struct { + __le16 e_tag; + __le16 e_perm; +} ext2_acl_entry_short; + +typedef struct { + __le32 a_version; +} ext2_acl_header; + +#define ACL_EA_VERSION 0x0002 + +typedef struct { + __le16 e_tag; + __le16 e_perm; + __le32 e_id; +} acl_ea_entry; + +typedef struct { + __le32 a_version; + acl_ea_entry a_entries[0]; +} acl_ea_header; + +#endif /* BTRFSCONVERT_EXT2 */ + +#endif diff --git a/convert/source-fs.c b/convert/source-fs.c new file mode 100644 index 00000000..59e36095 --- /dev/null +++ b/convert/source-fs.c @@ -0,0 +1,280 @@ +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +#include "kerncompat.h" +#include <unistd.h> +#include "internal.h" +#include "disk-io.h" +#include "volumes.h" +#include "convert/common.h" +#include "convert/source-fs.h" + +const struct simple_range btrfs_reserved_ranges[3] = { + { 0, SZ_1M }, + { BTRFS_SB_MIRROR_OFFSET(1), SZ_64K }, + { BTRFS_SB_MIRROR_OFFSET(2), SZ_64K } +}; + +static int intersect_with_sb(u64 bytenr, u64 num_bytes) +{ + int i; + u64 offset; + + for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { + offset = btrfs_sb_offset(i); + offset &= ~((u64)BTRFS_STRIPE_LEN - 1); + + if (bytenr < offset + BTRFS_STRIPE_LEN && + bytenr + num_bytes > offset) + return 1; + } + return 0; +} + +void init_convert_context(struct btrfs_convert_context *cctx) +{ + memset(cctx, 0, sizeof(*cctx)); + + cache_tree_init(&cctx->used_space); + cache_tree_init(&cctx->data_chunks); + cache_tree_init(&cctx->free_space); +} + +void clean_convert_context(struct btrfs_convert_context *cctx) +{ + free_extent_cache_tree(&cctx->used_space); + free_extent_cache_tree(&cctx->data_chunks); + free_extent_cache_tree(&cctx->free_space); +} + +int block_iterate_proc(u64 disk_block, u64 file_block, + struct blk_iterate_data *idata) +{ + int ret = 0; + int sb_region; + int do_barrier; + struct btrfs_root *root = idata->root; + struct btrfs_block_group_cache *cache; + u32 sectorsize = root->fs_info->sectorsize; + u64 bytenr = disk_block * sectorsize; + + sb_region = intersect_with_sb(bytenr, sectorsize); + do_barrier = sb_region || disk_block >= idata->boundary; + if ((idata->num_blocks > 0 && do_barrier) || + (file_block > idata->first_block + idata->num_blocks) || + (disk_block != idata->disk_block + idata->num_blocks)) { + if (idata->num_blocks > 0) { + ret = record_file_blocks(idata, idata->first_block, + idata->disk_block, + idata->num_blocks); + if (ret) + goto fail; + idata->first_block += idata->num_blocks; + idata->num_blocks = 0; + } + if (file_block > idata->first_block) { + ret = record_file_blocks(idata, idata->first_block, + 0, file_block - idata->first_block); + if (ret) + goto fail; + } + + if (sb_region) { + bytenr += BTRFS_STRIPE_LEN - 1; + bytenr &= ~((u64)BTRFS_STRIPE_LEN - 1); + } else { + cache = btrfs_lookup_block_group(root->fs_info, bytenr); + BUG_ON(!cache); + bytenr = cache->key.objectid + cache->key.offset; + } + + idata->first_block = file_block; + idata->disk_block = disk_block; + idata->boundary = bytenr / sectorsize; + } + idata->num_blocks++; +fail: + return ret; +} + +void init_blk_iterate_data(struct blk_iterate_data *data, + struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct btrfs_inode_item *inode, + u64 objectid, int checksum) +{ + struct btrfs_key key; + + data->trans = trans; + data->root = root; + data->inode = inode; + data->objectid = objectid; + data->first_block = 0; + data->disk_block = 0; + data->num_blocks = 0; + data->boundary = (u64)-1; + data->checksum = checksum; + data->errcode = 0; + + key.objectid = CONV_IMAGE_SUBVOL_OBJECTID; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + data->convert_root = btrfs_read_fs_root(root->fs_info, &key); + /* Impossible as we just opened it before */ + BUG_ON(!data->convert_root || IS_ERR(data->convert_root)); + data->convert_ino = BTRFS_FIRST_FREE_OBJECTID + 1; +} + +int convert_insert_dirent(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + const char *name, size_t name_len, + u64 dir, u64 objectid, + u8 file_type, u64 index_cnt, + struct btrfs_inode_item *inode) +{ + int ret; + u64 inode_size; + struct btrfs_key location = { + .objectid = objectid, + .offset = 0, + .type = BTRFS_INODE_ITEM_KEY, + }; + + ret = btrfs_insert_dir_item(trans, root, name, name_len, + dir, &location, file_type, index_cnt); + if (ret) + return ret; + ret = btrfs_insert_inode_ref(trans, root, name, name_len, + objectid, dir, index_cnt); + if (ret) + return ret; + inode_size = btrfs_stack_inode_size(inode) + name_len * 2; + btrfs_set_stack_inode_size(inode, inode_size); + + return 0; +} + +int read_disk_extent(struct btrfs_root *root, u64 bytenr, + u32 num_bytes, char *buffer) +{ + int ret; + struct btrfs_fs_devices *fs_devs = root->fs_info->fs_devices; + + ret = pread(fs_devs->latest_bdev, buffer, num_bytes, bytenr); + if (ret != num_bytes) + goto fail; + ret = 0; +fail: + if (ret > 0) + ret = -1; + return ret; +} + +/* + * Record a file extent in original filesystem into btrfs one. + * The special point is, old disk_block can point to a reserved range. + * So here, we don't use disk_block directly but search convert_root + * to get the real disk_bytenr. + */ +int record_file_blocks(struct blk_iterate_data *data, + u64 file_block, u64 disk_block, u64 num_blocks) +{ + int ret = 0; + struct btrfs_root *root = data->root; + struct btrfs_root *convert_root = data->convert_root; + struct btrfs_path path; + u32 sectorsize = root->fs_info->sectorsize; + u64 file_pos = file_block * sectorsize; + u64 old_disk_bytenr = disk_block * sectorsize; + u64 num_bytes = num_blocks * sectorsize; + u64 cur_off = old_disk_bytenr; + + /* Hole, pass it to record_file_extent directly */ + if (old_disk_bytenr == 0) + return btrfs_record_file_extent(data->trans, root, + data->objectid, data->inode, file_pos, 0, + num_bytes); + + btrfs_init_path(&path); + + /* + * Search real disk bytenr from convert root + */ + while (cur_off < old_disk_bytenr + num_bytes) { + struct btrfs_key key; + struct btrfs_file_extent_item *fi; + struct extent_buffer *node; + int slot; + u64 extent_disk_bytenr; + u64 extent_num_bytes; + u64 real_disk_bytenr; + u64 cur_len; + + key.objectid = data->convert_ino; + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = cur_off; + + ret = btrfs_search_slot(NULL, convert_root, &key, &path, 0, 0); + if (ret < 0) + break; + if (ret > 0) { + ret = btrfs_previous_item(convert_root, &path, + data->convert_ino, + BTRFS_EXTENT_DATA_KEY); + if (ret < 0) + break; + if (ret > 0) { + ret = -ENOENT; + break; + } + } + node = path.nodes[0]; + slot = path.slots[0]; + btrfs_item_key_to_cpu(node, &key, slot); + BUG_ON(key.type != BTRFS_EXTENT_DATA_KEY || + key.objectid != data->convert_ino || + key.offset > cur_off); + fi = btrfs_item_ptr(node, slot, struct btrfs_file_extent_item); + extent_disk_bytenr = btrfs_file_extent_disk_bytenr(node, fi); + extent_num_bytes = btrfs_file_extent_num_bytes(node, fi); + BUG_ON(cur_off - key.offset >= extent_num_bytes); + btrfs_release_path(&path); + + if (extent_disk_bytenr) + real_disk_bytenr = cur_off - key.offset + + extent_disk_bytenr; + else + real_disk_bytenr = 0; + cur_len = min(key.offset + extent_num_bytes, + old_disk_bytenr + num_bytes) - cur_off; + ret = btrfs_record_file_extent(data->trans, data->root, + data->objectid, data->inode, file_pos, + real_disk_bytenr, cur_len); + if (ret < 0) + break; + cur_off += cur_len; + file_pos += cur_len; + + /* + * No need to care about csum + * As every byte of old fs image is calculated for csum, no + * need to waste CPU cycles now. + */ + } + btrfs_release_path(&path); + return ret; +} + diff --git a/convert/source-fs.h b/convert/source-fs.h new file mode 100644 index 00000000..3a6fa46c --- /dev/null +++ b/convert/source-fs.h @@ -0,0 +1,118 @@ +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +#ifndef __BTRFS_CONVERT_SOURCE_FS_H__ +#define __BTRFS_CONVERT_SOURCE_FS_H__ + +#include "kerncompat.h" +#include <pthread.h> + + +#define CONV_IMAGE_SUBVOL_OBJECTID BTRFS_FIRST_FREE_OBJECTID + +/* + * Reresents a simple contiguous range. + * + * For multiple or non-contiguous ranges, use extent_cache_tree from + * extent-cache.c + */ +struct simple_range { + u64 start; + u64 len; +}; + +extern const struct simple_range btrfs_reserved_ranges[3]; + +struct task_info; + +struct task_ctx { + pthread_mutex_t mutex; + u64 max_copy_inodes; + u64 cur_copy_inodes; + struct task_info *info; +}; + +struct btrfs_convert_context; + +#define SOURCE_FS_NAME_LEN (16) + +#define CONVERT_FLAG_DATACSUM (1U << 0) +#define CONVERT_FLAG_INLINE_DATA (1U << 1) +#define CONVERT_FLAG_XATTR (1U << 2) +#define CONVERT_FLAG_COPY_LABEL (1U << 3) +#define CONVERT_FLAG_SET_LABEL (1U << 4) + +struct btrfs_convert_operations { + const char name[SOURCE_FS_NAME_LEN]; + int (*open_fs)(struct btrfs_convert_context *cctx, const char *devname); + int (*read_used_space)(struct btrfs_convert_context *cctx); + int (*copy_inodes)(struct btrfs_convert_context *cctx, + struct btrfs_root *root, u32 covert_flags, + struct task_ctx *p); + void (*close_fs)(struct btrfs_convert_context *cctx); + int (*check_state)(struct btrfs_convert_context *cctx); +}; + +struct btrfs_trans_handle; +struct btrfs_root; +struct btrfs_inode_item; + +struct blk_iterate_data { + struct btrfs_trans_handle *trans; + struct btrfs_root *root; + struct btrfs_root *convert_root; + struct btrfs_inode_item *inode; + u64 convert_ino; + u64 objectid; + u64 first_block; + u64 disk_block; + u64 num_blocks; + u64 boundary; + int checksum; + int errcode; +}; + +void init_convert_context(struct btrfs_convert_context *cctx); +void clean_convert_context(struct btrfs_convert_context *cctx); +int block_iterate_proc(u64 disk_block, u64 file_block, + struct blk_iterate_data *idata); +void init_blk_iterate_data(struct blk_iterate_data *data, + struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct btrfs_inode_item *inode, + u64 objectid, int checksum); +int convert_insert_dirent(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + const char *name, size_t name_len, + u64 dir, u64 objectid, + u8 file_type, u64 index_cnt, + struct btrfs_inode_item *inode); +int read_disk_extent(struct btrfs_root *root, u64 bytenr, + u32 num_bytes, char *buffer); +int record_file_blocks(struct blk_iterate_data *data, + u64 file_block, u64 disk_block, u64 num_blocks); + +/* + * Simple range functions + * + * Get range end (exclusive) + */ +static inline u64 range_end(const struct simple_range *range) +{ + return (range->start + range->len); +} + +#endif |