staticvoid btrfs_free_csum_hash(struct btrfs_fs_info *fs_info)
{ if (fs_info->csum_shash)
crypto_free_shash(fs_info->csum_shash);
}
/* * Compute the csum of a btree block and store the result to provided buffer.
*/ staticvoid csum_tree_block(struct extent_buffer *buf, u8 *result)
{ struct btrfs_fs_info *fs_info = buf->fs_info; int num_pages;
u32 first_page_part;
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); char *kaddr; int i;
/* * Multiple single-page folios case would reach here. * * nodesize <= PAGE_SIZE and large folio all handled by above * crypto_shash_update() already.
*/ for (i = 1; i < num_pages && INLINE_EXTENT_BUFFER_PAGES > 1; i++) {
kaddr = folio_address(buf->folios[i]);
crypto_shash_update(shash, kaddr, PAGE_SIZE);
}
memset(result, 0, BTRFS_CSUM_SIZE);
crypto_shash_final(shash, result);
}
/* * we can't consider a given block up to date unless the transid of the * block matches the transid in the parent node's pointer. This is how we * detect blocks that either didn't get written at all or got written * in the wrong place.
*/ int btrfs_buffer_uptodate(struct extent_buffer *eb, u64 parent_transid, int atomic)
{ if (!extent_buffer_uptodate(eb)) return 0;
if (!parent_transid || btrfs_header_generation(eb) == parent_transid) return 1;
staticbool btrfs_supported_super_csum(u16 csum_type)
{ switch (csum_type) { case BTRFS_CSUM_TYPE_CRC32: case BTRFS_CSUM_TYPE_XXHASH: case BTRFS_CSUM_TYPE_SHA256: case BTRFS_CSUM_TYPE_BLAKE2: returntrue; default: returnfalse;
}
}
/* * Return 0 if the superblock checksum type matches the checksum value of that * algorithm. Pass the raw disk superblock data.
*/ int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, conststruct btrfs_super_block *disk_sb)
{ char result[BTRFS_CSUM_SIZE];
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
shash->tfm = fs_info->csum_shash;
/* * The super_block structure does not span the whole * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space is * filled with zeros and is included in the checksum.
*/
crypto_shash_digest(shash, (const u8 *)disk_sb + BTRFS_CSUM_SIZE,
BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, result);
if (memcmp(disk_sb->csum, result, fs_info->csum_size)) return 1;
return 0;
}
staticint btrfs_repair_eb_io_failure(conststruct extent_buffer *eb, int mirror_num)
{ struct btrfs_fs_info *fs_info = eb->fs_info; int ret = 0;
if (sb_rdonly(fs_info->sb)) return -EROFS;
for (int i = 0; i < num_extent_folios(eb); i++) { struct folio *folio = eb->folios[i];
u64 start = max_t(u64, eb->start, folio_pos(folio));
u64 end = min_t(u64, eb->start + eb->len,
folio_pos(folio) + eb->folio_size);
u32 len = end - start;
phys_addr_t paddr = PFN_PHYS(folio_pfn(folio)) +
offset_in_folio(folio, start);
ret = btrfs_repair_io_failure(fs_info, 0, start, len, start,
paddr, mirror_num); if (ret) break;
}
return ret;
}
/* * helper to read a given tree block, doing retries as required when * the checksums don't match and we have alternate mirrors to try. * * @check: expected tree parentness check, see the comments of the * structure for details.
*/ int btrfs_read_extent_buffer(struct extent_buffer *eb, conststruct btrfs_tree_parent_check *check)
{ struct btrfs_fs_info *fs_info = eb->fs_info; int failed = 0; int ret; int num_copies = 0; int mirror_num = 0; int failed_mirror = 0;
ASSERT(check);
while (1) {
ret = read_extent_buffer_pages(eb, mirror_num, check); if (!ret) break;
num_copies = btrfs_num_copies(fs_info,
eb->start, eb->len); if (num_copies == 1) break;
if (!failed_mirror) {
failed = 1;
failed_mirror = eb->read_mirror;
}
mirror_num++; if (mirror_num == failed_mirror)
mirror_num++;
if (mirror_num > num_copies) break;
}
if (failed && !ret && failed_mirror)
btrfs_repair_eb_io_failure(eb, failed_mirror);
return ret;
}
/* * Checksum a dirty tree block before IO.
*/ int btree_csum_one_bio(struct btrfs_bio *bbio)
{ struct extent_buffer *eb = bbio->private; struct btrfs_fs_info *fs_info = eb->fs_info;
u64 found_start = btrfs_header_bytenr(eb);
u64 last_trans;
u8 result[BTRFS_CSUM_SIZE]; int ret;
/* Btree blocks are always contiguous on disk. */ if (WARN_ON_ONCE(bbio->file_offset != eb->start)) return -EIO; if (WARN_ON_ONCE(bbio->bio.bi_iter.bi_size != eb->len)) return -EIO;
/* * If an extent_buffer is marked as EXTENT_BUFFER_ZONED_ZEROOUT, don't * checksum it but zero-out its content. This is done to preserve * ordering of I/O without unnecessarily writing out data.
*/ if (test_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags)) {
memzero_extent_buffer(eb, 0, eb->len); return 0;
}
if (WARN_ON_ONCE(found_start != eb->start)) return -EIO; if (WARN_ON(!btrfs_meta_folio_test_uptodate(eb->folios[0], eb))) return -EIO;
if (btrfs_header_level(eb))
ret = btrfs_check_node(eb); else
ret = btrfs_check_leaf(eb);
if (ret < 0) goto error;
/* * Also check the generation, the eb reached here must be newer than * last committed. Or something seriously wrong happened.
*/
last_trans = btrfs_get_last_trans_committed(fs_info); if (unlikely(btrfs_header_generation(eb) <= last_trans)) {
ret = -EUCLEAN;
btrfs_err(fs_info, "block=%llu bad generation, have %llu expect > %llu",
eb->start, btrfs_header_generation(eb), last_trans); goto error;
}
write_extent_buffer(eb, result, 0, fs_info->csum_size); return 0;
error:
btrfs_print_tree(eb, 0);
btrfs_err(fs_info, "block=%llu write time tree block corruption detected",
eb->start); /* * Be noisy if this is an extent buffer from a log tree. We don't abort * a transaction in case there's a bad log tree extent buffer, we just * fallback to a transaction commit. Still we want to know when there is * a bad log tree extent buffer, as that may signal a bug somewhere.
*/
WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG) ||
btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID); return ret;
}
/* * alloc_fsid_devices() copies the fsid into fs_devices::metadata_uuid. * This is then overwritten by metadata_uuid if it is present in the * device_list_add(). The same true for a seed device as well. So use of * fs_devices::metadata_uuid is appropriate here.
*/ if (memcmp(fsid, fs_info->fs_devices->metadata_uuid, BTRFS_FSID_SIZE) == 0) returnfalse;
list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list) if (!memcmp(fsid, seed_devs->fsid, BTRFS_FSID_SIZE)) returnfalse;
returntrue;
}
/* Do basic extent buffer checks at read time */ int btrfs_validate_extent_buffer(struct extent_buffer *eb, conststruct btrfs_tree_parent_check *check)
{ struct btrfs_fs_info *fs_info = eb->fs_info;
u64 found_start; const u32 csum_size = fs_info->csum_size;
u8 found_level;
u8 result[BTRFS_CSUM_SIZE]; const u8 *header_csum; int ret = 0; constbool ignore_csum = btrfs_test_opt(fs_info, IGNOREMETACSUMS);
ASSERT(check);
found_start = btrfs_header_bytenr(eb); if (found_start != eb->start) {
btrfs_err_rl(fs_info, "bad tree block start, mirror %u want %llu have %llu",
eb->read_mirror, eb->start, found_start);
ret = -EIO; goto out;
} if (check_tree_block_fsid(eb)) {
btrfs_err_rl(fs_info, "bad fsid on logical %llu mirror %u",
eb->start, eb->read_mirror);
ret = -EIO; goto out;
}
found_level = btrfs_header_level(eb); if (found_level >= BTRFS_MAX_LEVEL) {
btrfs_err(fs_info, "bad tree block level, mirror %u level %d on logical %llu",
eb->read_mirror, btrfs_header_level(eb), eb->start);
ret = -EIO; goto out;
}
if (memcmp(result, header_csum, csum_size) != 0) {
btrfs_warn_rl(fs_info, "checksum verify failed on logical %llu mirror %u wanted " CSUM_FMT " found " CSUM_FMT " level %d%s",
eb->start, eb->read_mirror,
CSUM_FMT_VALUE(csum_size, header_csum),
CSUM_FMT_VALUE(csum_size, result),
btrfs_header_level(eb),
ignore_csum ? ", ignored" : ""); if (!ignore_csum) {
ret = -EUCLEAN; goto out;
}
}
if (found_level != check->level) {
btrfs_err(fs_info, "level verify failed on logical %llu mirror %u wanted %u found %u",
eb->start, eb->read_mirror, check->level, found_level);
ret = -EIO; goto out;
} if (unlikely(check->transid &&
btrfs_header_generation(eb) != check->transid)) {
btrfs_err_rl(eb->fs_info, "parent transid verify failed on logical %llu mirror %u wanted %llu found %llu",
eb->start, eb->read_mirror, check->transid,
btrfs_header_generation(eb));
ret = -EIO; goto out;
} if (check->has_first_key) { conststruct btrfs_key *expect_key = &check->first_key; struct btrfs_key found_key;
if (found_level)
btrfs_node_key_to_cpu(eb, &found_key, 0); else
btrfs_item_key_to_cpu(eb, &found_key, 0); if (unlikely(btrfs_comp_cpu_keys(expect_key, &found_key))) {
btrfs_err(fs_info, "tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)",
eb->start, check->transid,
expect_key->objectid,
expect_key->type, expect_key->offset,
found_key.objectid, found_key.type,
found_key.offset);
ret = -EUCLEAN; goto out;
}
} if (check->owner_root) {
ret = btrfs_check_eb_owner(eb, check->owner_root); if (ret < 0) goto out;
}
/* If this is a leaf block and it is corrupt, just return -EIO. */ if (found_level == 0 && btrfs_check_leaf(eb))
ret = -EIO;
if (found_level > 0 && btrfs_check_node(eb))
ret = -EIO;
if (ret)
btrfs_err(fs_info, "read time tree block corruption detected on logical %llu mirror %u",
eb->start, eb->read_mirror);
out: return ret;
}
#ifdef CONFIG_MIGRATION staticint btree_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode)
{ /* * we can't safely write a btree page from here, * we haven't done the locking hook
*/ if (folio_test_dirty(src)) return -EAGAIN; /* * Buffers may be managed in a filesystem specific way. * We must have no buffers or drop them.
*/ if (folio_get_private(src) &&
!filemap_release_folio(src, GFP_KERNEL)) return -EAGAIN; return migrate_folio(mapping, dst, src, mode);
} #else #define btree_migrate_folio NULL #endif
staticint btree_writepages(struct address_space *mapping, struct writeback_control *wbc)
{ int ret;
if (wbc->sync_mode == WB_SYNC_NONE) { struct btrfs_fs_info *fs_info;
if (wbc->for_kupdate) return 0;
fs_info = inode_to_fs_info(mapping->host); /* this is a bit racy, but that's ok */
ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
BTRFS_DIRTY_METADATA_THRESH,
fs_info->dirty_metadata_batch); if (ret < 0) return 0;
} return btree_write_cache_pages(mapping, wbc);
}
tree = &folio_to_inode(folio)->io_tree;
extent_invalidate_folio(tree, folio, offset);
btree_release_folio(folio, GFP_NOFS); if (folio_get_private(folio)) {
btrfs_warn(folio_to_fs_info(folio), "folio private not zero on folio %llu",
(unsignedlonglong)folio_pos(folio));
folio_detach_private(folio);
}
}
/* * Read tree block at logical address @bytenr and do variant basic but critical * verification. * * @check: expected tree parentness check, see comments of the * structure for details.
*/ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, struct btrfs_tree_parent_check *check)
{ struct extent_buffer *buf = NULL; int ret;
ASSERT(check);
buf = btrfs_find_create_tree_block(fs_info, bytenr, check->owner_root,
check->level); if (IS_ERR(buf)) return buf;
ret = btrfs_read_extent_buffer(buf, check); if (ret) {
free_extent_buffer_stale(buf); return ERR_PTR(ret);
} return buf;
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS /* Should only be used by the testing infrastructure */ struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info)
{ struct btrfs_root *root;
if (!fs_info) return ERR_PTR(-EINVAL);
root = btrfs_alloc_root(fs_info, BTRFS_ROOT_TREE_OBJECTID, GFP_KERNEL); if (!root) return ERR_PTR(-ENOMEM);
/* We don't use the stripesize in selftest, set it as sectorsize */
root->alloc_bytenr = 0;
/* * We're holding a transaction handle, so use a NOFS memory allocation * context to avoid deadlock if reclaim happens.
*/
nofs_flag = memalloc_nofs_save();
root = btrfs_alloc_root(fs_info, objectid, GFP_KERNEL);
memalloc_nofs_restore(nofs_flag); if (!root) return ERR_PTR(-ENOMEM);
/* * DON'T set SHAREABLE bit for log trees. * * Log trees are not exposed to user space thus can't be snapshotted, * and they go away before a real commit is actually done. * * They do store pointers to file data extents, and those reference * counts still get updated (along with back refs to the log tree).
*/
/* * Initialize subvolume root in-memory structure. * * @anon_dev: anonymous device to attach to the root, if zero, allocate new * * In case of failure the caller is responsible to call btrfs_free_fs_root()
*/ staticint btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
{ int ret;
/* * Don't assign anonymous block device to roots that are not exposed to * userspace, the id pool is limited to 1M
*/ if (btrfs_is_fstree(btrfs_root_id(root)) &&
btrfs_root_refs(&root->root_item) > 0) { if (!anon_dev) {
ret = get_anon_bdev(&root->anon_dev); if (ret) return ret;
} else {
root->anon_dev = anon_dev;
}
}
mutex_lock(&root->objectid_mutex);
ret = btrfs_init_root_free_objectid(root); if (ret) {
mutex_unlock(&root->objectid_mutex); return ret;
}
/* * Get an in-memory reference of a root structure. * * For essential trees like root/extent tree, we grab it from fs_info directly. * For subvolume trees, we check the cached filesystem roots first. If not * found, then read it from disk and add it to cached fs roots. * * Caller should release the root by calling btrfs_put_root() after the usage. * * NOTE: Reloc and log trees can't be read by this function as they share the * same root objectid. * * @objectid: root id * @anon_dev: preallocated anonymous block device number for new roots, * pass NULL for a new allocation. * @check_ref: whether to check root item references, If true, return -ENOENT * for orphan roots
*/ staticstruct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
u64 objectid, dev_t *anon_dev, bool check_ref)
{ struct btrfs_root *root; struct btrfs_path *path; struct btrfs_key key; int ret;
root = btrfs_get_global_root(fs_info, objectid); if (root) return root;
/* * If we're called for non-subvolume trees, and above function didn't * find one, do not try to read it from disk. * * This is namely for free-space-tree and quota tree, which can change * at runtime and should only be grabbed from fs_info.
*/ if (!btrfs_is_fstree(objectid) && objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) return ERR_PTR(-ENOENT);
again:
root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { /* * Some other caller may have read out the newly inserted * subvolume already (for things like backref walk etc). Not * that common but still possible. In that case, we just need * to free the anon_dev.
*/ if (unlikely(anon_dev && *anon_dev)) {
free_anon_bdev(*anon_dev);
*anon_dev = 0;
}
ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
btrfs_free_path(path); if (ret < 0) goto fail; if (ret == 0)
set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
ret = btrfs_insert_fs_root(fs_info, root); if (ret) { if (ret == -EEXIST) {
btrfs_put_root(root); goto again;
} goto fail;
} return root;
fail: /* * If our caller provided us an anonymous device, then it's his * responsibility to free it in case we fail. So we have to set our * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root() * and once again by our caller.
*/ if (anon_dev && *anon_dev)
root->anon_dev = 0;
btrfs_put_root(root); return ERR_PTR(ret);
}
/* * Get in-memory reference of a root structure * * @objectid: tree objectid * @check_ref: if set, verify that the tree exists and the item has at least * one reference
*/ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
u64 objectid, bool check_ref)
{ return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref);
}
/* * Get in-memory reference of a root structure, created as new, optionally pass * the anonymous block device id * * @objectid: tree objectid * @anon_dev: if NULL, allocate a new anonymous block device or use the * parameter value if not NULL
*/ struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
u64 objectid, dev_t *anon_dev)
{ return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
}
/* * Return a root for the given objectid. * * @fs_info: the fs_info * @objectid: the objectid we need to lookup * * This is exclusively used for backref walking, and exists specifically because * of how qgroups does lookups. Qgroups will do a backref lookup at delayed ref * creation time, which means we may have to read the tree_root in order to look * up a fs root that is not in memory. If the root is not in memory we will * read the tree root commit root and look up the fs root from there. This is a * temporary root, it will not be inserted into the radix tree as it doesn't * have the most uptodate information, it'll simply be discarded once the * backref code is finished using the root.
*/ struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
u64 objectid)
{ struct btrfs_root *root; struct btrfs_key key;
/* * This can return -ENOENT if we ask for a root that doesn't exist, but * since this is called via the backref walking code we won't be looking * up a root that doesn't exist, unless there's corruption. So if root * != NULL just return it.
*/
root = btrfs_get_global_root(fs_info, objectid); if (root) return root;
root = btrfs_lookup_fs_root(fs_info, objectid); if (root) return root;
/* Make the cleaner go to sleep early. */ if (btrfs_need_cleaner_sleep(fs_info)) goto sleep;
/* * Do not do anything if we might cause open_ctree() to block * before we have finished mounting the filesystem.
*/ if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags)) goto sleep;
if (!mutex_trylock(&fs_info->cleaner_mutex)) goto sleep;
/* * Avoid the problem that we change the status of the fs * during the above check and trylock.
*/ if (btrfs_need_cleaner_sleep(fs_info)) {
mutex_unlock(&fs_info->cleaner_mutex); goto sleep;
}
if (test_and_clear_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags))
btrfs_sysfs_feature_update(fs_info);
btrfs_run_delayed_iputs(fs_info);
again = btrfs_clean_one_deleted_snapshot(fs_info);
mutex_unlock(&fs_info->cleaner_mutex);
/* * The defragger has dealt with the R/O remount and umount, * needn't do anything special here.
*/
btrfs_run_defrag_inodes(fs_info);
/* * Acquires fs_info->reclaim_bgs_lock to avoid racing * with relocation (btrfs_relocate_chunk) and relocation * acquires fs_info->cleaner_mutex (btrfs_relocate_block_group) * after acquiring fs_info->reclaim_bgs_lock. So we * can't hold, nor need to, fs_info->cleaner_mutex when deleting * unused block groups.
*/
btrfs_delete_unused_bgs(fs_info);
/* * Reclaim block groups in the reclaim_bgs list after we deleted * all unused block_groups. This possibly gives us some more free * space.
*/
btrfs_reclaim_bgs(fs_info);
sleep:
clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); if (kthread_should_park())
kthread_parkme(); if (kthread_should_stop()) return 0; if (!again) {
set_current_state(TASK_INTERRUPTIBLE);
schedule();
__set_current_state(TASK_RUNNING);
}
}
}
/* If the file system is aborted, this will always fail. */
trans = btrfs_attach_transaction(root); if (IS_ERR(trans)) { if (PTR_ERR(trans) != -ENOENT)
cannot_commit = true; goto sleep;
} if (transid == trans->transid) {
btrfs_commit_transaction(trans);
} else {
btrfs_end_transaction(trans);
}
sleep:
wake_up_process(fs_info->cleaner_kthread);
mutex_unlock(&fs_info->transaction_kthread_mutex);
if (BTRFS_FS_ERROR(fs_info))
btrfs_cleanup_transaction(fs_info); if (!kthread_should_stop() &&
(!btrfs_transaction_blocked(fs_info) ||
cannot_commit))
schedule_timeout_interruptible(delay);
} while (!kthread_should_stop()); return 0;
}
/* * This will find the highest generation in the array of root backups. The * index of the highest array is returned, or -EINVAL if we can't find * anything. * * We check to make sure the array is valid by comparing the * generation of the latest root in the array with the generation * in the super block. If they don't match we pitch it.
*/ staticint find_newest_super_backup(struct btrfs_fs_info *info)
{ const u64 newest_gen = btrfs_super_generation(info->super_copy);
u64 cur; struct btrfs_root_backup *root_backup; int i;
for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
root_backup = info->super_copy->super_roots + i;
cur = btrfs_backup_tree_root_gen(root_backup); if (cur == newest_gen) return i;
}
return -EINVAL;
}
/* * copy all the root pointers into the super backup array. * this will bump the backup pointer by one when it is * done
*/ staticvoid backup_super_roots(struct btrfs_fs_info *info)
{ constint next_backup = info->backup_root_index; struct btrfs_root_backup *root_backup;
/* * make sure all of our padding and empty slots get zero filled * regardless of which ones we use today
*/
memset(root_backup, 0, sizeof(*root_backup));
/* * we might commit during log recovery, which happens before we set * the fs_root. Make sure it is valid before we fill it in.
*/ if (info->fs_root && info->fs_root->node) {
btrfs_set_backup_fs_root(root_backup,
info->fs_root->node->start);
btrfs_set_backup_fs_root_gen(root_backup,
btrfs_header_generation(info->fs_root->node));
btrfs_set_backup_fs_root_level(root_backup,
btrfs_header_level(info->fs_root->node));
}
/* * if we don't copy this out to the super_copy, it won't get remembered * for the next commit
*/
memcpy(&info->super_copy->super_roots,
&info->super_for_commit->super_roots, sizeof(*root_backup) * BTRFS_NUM_BACKUP_ROOTS);
}
/* * Reads a backup root based on the passed priority. Prio 0 is the newest, prio * 1/2/3 are 2nd newest/3rd newest/4th (oldest) backup roots * * @fs_info: filesystem whose backup roots need to be read * @priority: priority of backup root required * * Returns backup root index on success and -EINVAL otherwise.
*/ staticint read_backup_root(struct btrfs_fs_info *fs_info, u8 priority)
{ int backup_index = find_newest_super_backup(fs_info); struct btrfs_super_block *super = fs_info->super_copy; struct btrfs_root_backup *root_backup;
if (priority < BTRFS_NUM_BACKUP_ROOTS && backup_index >= 0) { if (priority == 0) return backup_index;
/* * Fixme: the total bytes and num_devices need to match or we should * need a fsck
*/
btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup));
btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup));
return backup_index;
}
/* helper to cleanup workers */ staticvoid btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
{
btrfs_destroy_workqueue(fs_info->fixup_workers);
btrfs_destroy_workqueue(fs_info->delalloc_workers);
btrfs_destroy_workqueue(fs_info->workers); if (fs_info->endio_workers)
destroy_workqueue(fs_info->endio_workers); if (fs_info->rmw_workers)
destroy_workqueue(fs_info->rmw_workers); if (fs_info->compressed_write_workers)
destroy_workqueue(fs_info->compressed_write_workers);
btrfs_destroy_workqueue(fs_info->endio_write_workers);
btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
btrfs_destroy_workqueue(fs_info->delayed_workers);
btrfs_destroy_workqueue(fs_info->caching_workers);
btrfs_destroy_workqueue(fs_info->flush_workers);
btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers); if (fs_info->discard_ctl.discard_workers)
destroy_workqueue(fs_info->discard_ctl.discard_workers); /* * Now that all other work queues are destroyed, we can safely destroy * the queues used for metadata I/O, since tasks from those other work * queues can do metadata I/O operations.
*/ if (fs_info->endio_meta_workers)
destroy_workqueue(fs_info->endio_meta_workers);
}
void btrfs_put_root(struct btrfs_root *root)
{ if (!root) return;
if (refcount_dec_and_test(&root->refs)) { if (WARN_ON(!xa_empty(&root->inodes)))
xa_destroy(&root->inodes); if (WARN_ON(!xa_empty(&root->delayed_nodes)))
xa_destroy(&root->delayed_nodes);
WARN_ON(test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state)); if (root->anon_dev)
free_anon_bdev(root->anon_dev);
free_root_extent_buffers(root); #ifdef CONFIG_BTRFS_DEBUG
spin_lock(&root->fs_info->fs_roots_radix_lock);
list_del_init(&root->leak_list);
spin_unlock(&root->fs_info->fs_roots_radix_lock); #endif
kfree(root);
}
}
void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
{ int ret; struct btrfs_root *gang[8]; int i;
while (!list_empty(&fs_info->dead_roots)) {
gang[0] = list_first_entry(&fs_info->dead_roots, struct btrfs_root, root_list);
list_del(&gang[0]->root_list);
if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state))
btrfs_drop_and_free_fs_root(fs_info, gang[0]);
btrfs_put_root(gang[0]);
}
while (1) {
ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
(void **)gang, 0,
ARRAY_SIZE(gang)); if (!ret) break; for (i = 0; i < ret; i++)
btrfs_drop_and_free_fs_root(fs_info, gang[i]);
}
}
inode = new_inode(sb); if (!inode) return -ENOMEM;
btrfs_set_inode_number(BTRFS_I(inode), BTRFS_BTREE_INODE_OBJECTID);
set_nlink(inode, 1); /* * we set the i_size on the btree inode to the max possible int. * the real end of the address space is determined by all of * the devices in the system
*/
inode->i_size = OFFSET_MAX;
inode->i_mapping->a_ops = &btree_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
if (IS_ERR(csum_shash)) {
btrfs_err(fs_info, "error allocating %s hash for checksum",
csum_driver); return PTR_ERR(csum_shash);
}
fs_info->csum_shash = csum_shash;
/* Check if the checksum implementation is a fast accelerated one. */ switch (csum_type) { case BTRFS_CSUM_TYPE_CRC32: if (crc32_optimizations() & CRC32C_OPTIMIZATION)
set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); break; case BTRFS_CSUM_TYPE_XXHASH:
set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); break; default: break;
}
if (fs_devices->rw_devices == 0) {
btrfs_warn(fs_info, "log replay required on RO media"); return -EIO;
}
log_tree_root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID,
GFP_KERNEL); if (!log_tree_root) return -ENOMEM;
check.level = level;
check.transid = fs_info->generation + 1;
check.owner_root = BTRFS_TREE_LOG_OBJECTID;
log_tree_root->node = read_tree_block(fs_info, bytenr, &check); if (IS_ERR(log_tree_root->node)) {
btrfs_warn(fs_info, "failed to read log tree");
ret = PTR_ERR(log_tree_root->node);
log_tree_root->node = NULL;
btrfs_put_root(log_tree_root); return ret;
} if (!extent_buffer_uptodate(log_tree_root->node)) {
btrfs_err(fs_info, "failed to read log tree");
btrfs_put_root(log_tree_root); return -EIO;
}
/* returns with log_tree_root freed on success */
ret = btrfs_recover_log_trees(log_tree_root);
btrfs_put_root(log_tree_root); if (ret) {
btrfs_handle_fs_error(fs_info, ret, "Failed to recover log tree"); return ret;
}
if (sb_rdonly(fs_info->sb)) {
ret = btrfs_commit_super(fs_info); if (ret) return ret;
}
/* If we have IGNOREDATACSUMS skip loading these roots. */ if (objectid == BTRFS_CSUM_TREE_OBJECTID &&
btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {
set_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state); return 0;
}
while (1) {
ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0); if (ret < 0) break;
if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
ret = btrfs_next_leaf(tree_root, path); if (ret) { if (ret > 0)
ret = 0; break;
}
}
ret = 0;
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid != objectid) break;
btrfs_release_path(path);
/* * Just worry about this for extent tree, it'll be the same for * everybody.
*/ if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
max_global_id = max(max_global_id, key.offset);
found = true;
root = read_tree_root_path(tree_root, path, &key); if (IS_ERR(root)) {
ret = PTR_ERR(root); break;
}
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
ret = btrfs_global_root_insert(root); if (ret) {
btrfs_put_root(root); break;
}
key.offset++;
}
btrfs_release_path(path);
if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
fs_info->nr_global_roots = max_global_id + 1;
if (!found || ret) { if (objectid == BTRFS_CSUM_TREE_OBJECTID)
set_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state);
if (!btrfs_test_opt(fs_info, IGNOREBADROOTS))
ret = ret ? ret : -ENOENT; else
ret = 0;
btrfs_err(fs_info, "failed to load root %s", name);
} return ret;
}
staticint load_global_roots(struct btrfs_root *tree_root)
{
BTRFS_PATH_AUTO_FREE(path); int ret;
path = btrfs_alloc_path(); if (!path) return -ENOMEM;
ret = load_global_roots_objectid(tree_root, path,
BTRFS_EXTENT_TREE_OBJECTID, "extent"); if (ret) return ret;
ret = load_global_roots_objectid(tree_root, path,
BTRFS_CSUM_TREE_OBJECTID, "csum"); if (ret) return ret; if (!btrfs_fs_compat_ro(tree_root->fs_info, FREE_SPACE_TREE)) return ret;
ret = load_global_roots_objectid(tree_root, path,
BTRFS_FREE_SPACE_TREE_OBJECTID, "free space");
if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE)) {
location.objectid = BTRFS_BLOCK_GROUP_TREE_OBJECTID;
root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
ret = PTR_ERR(root); goto out;
}
} else {
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
fs_info->block_group_root = root;
}
}
location.objectid = BTRFS_DEV_TREE_OBJECTID;
root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
ret = PTR_ERR(root); goto out;
}
} else {
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
fs_info->dev_root = root;
} /* Initialize fs_info for all devices in any case */
ret = btrfs_init_devices_late(fs_info); if (ret) goto out;
/* * This tree can share blocks with some other fs tree during relocation * and we need a proper setup by btrfs_get_fs_root
*/
root = btrfs_get_fs_root(tree_root->fs_info,
BTRFS_DATA_RELOC_TREE_OBJECTID, true); if (IS_ERR(root)) { if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
ret = PTR_ERR(root); goto out;
}
} else {
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
fs_info->data_reloc_root = root;
}
staticint validate_sys_chunk_array(conststruct btrfs_fs_info *fs_info, conststruct btrfs_super_block *sb)
{ unsignedint cur = 0; /* Offset inside the sys chunk array */ /* * At sb read time, fs_info is not fully initialized. Thus we have * to use super block sectorsize, which should have been validated.
*/ const u32 sectorsize = btrfs_super_sectorsize(sb);
u32 sys_array_size = btrfs_super_sys_array_size(sb);
if (sys_array_size > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
btrfs_err(fs_info, "system chunk array too big %u > %u",
sys_array_size, BTRFS_SYSTEM_CHUNK_ARRAY_SIZE); return -EUCLEAN;
}
disk_key = (struct btrfs_disk_key *)(sb->sys_chunk_array + cur);
len = sizeof(*disk_key);
if (cur + len > sys_array_size) goto short_read;
cur += len;
btrfs_disk_key_to_cpu(&key, disk_key); if (key.type != BTRFS_CHUNK_ITEM_KEY) {
btrfs_err(fs_info, "unexpected item type %u in sys_array at offset %u",
key.type, cur); return -EUCLEAN;
}
chunk = (struct btrfs_chunk *)(sb->sys_chunk_array + cur);
num_stripes = btrfs_stack_chunk_num_stripes(chunk); if (cur + btrfs_chunk_item_size(num_stripes) > sys_array_size) goto short_read;
type = btrfs_stack_chunk_type(chunk); if (!(type & BTRFS_BLOCK_GROUP_SYSTEM)) {
btrfs_err(fs_info, "invalid chunk type %llu in sys_array at offset %u",
type, cur); return -EUCLEAN;
}
ret = btrfs_check_chunk_valid(fs_info, NULL, chunk, key.offset,
sectorsize); if (ret < 0) return ret;
cur += btrfs_chunk_item_size(num_stripes);
} return 0;
short_read:
btrfs_err(fs_info, "super block sys chunk array short read, cur=%u sys_array_size=%u",
cur, sys_array_size); return -EUCLEAN;
}
/* * Real super block validation * NOTE: super csum type and incompat features will not be checked here. * * @sb: super block to check * @mirror_num: the super block number to check its bytenr: * 0 the primary (1st) sb * 1, 2 2nd and 3rd backup copy * -1 skip bytenr check
*/ int btrfs_validate_super(conststruct btrfs_fs_info *fs_info, conststruct btrfs_super_block *sb, int mirror_num)
{
u64 nodesize = btrfs_super_nodesize(sb);
u64 sectorsize = btrfs_super_sectorsize(sb); int ret = 0; constbool ignore_flags = btrfs_test_opt(fs_info, IGNORESUPERFLAGS);
if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
btrfs_err(fs_info, "no valid FS found");
ret = -EINVAL;
} if ((btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP)) { if (!ignore_flags) {
btrfs_err(fs_info, "unrecognized or unsupported super flag 0x%llx",
btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
ret = -EINVAL;
} else {
btrfs_info(fs_info, "unrecognized or unsupported super flags: 0x%llx, ignored",
btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
}
} if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
btrfs_err(fs_info, "tree_root level too big: %d >= %d",
btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
ret = -EINVAL;
} if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
btrfs_err(fs_info, "chunk_root level too big: %d >= %d",
btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
ret = -EINVAL;
} if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
btrfs_err(fs_info, "log_root level too big: %d >= %d",
btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
ret = -EINVAL;
}
/* * Check sectorsize and nodesize first, other check will need it. * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
*/ if (!is_power_of_2(sectorsize) || sectorsize < BTRFS_MIN_BLOCKSIZE ||
sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize);
ret = -EINVAL;
}
/* * We only support at most 3 sectorsizes: 4K, PAGE_SIZE, MIN_BLOCKSIZE. * * For 4K page sized systems with non-debug builds, all 3 matches (4K). * For 4K page sized systems with debug builds, there are two block sizes * supported. (4K and 2K) * * We can support 16K sectorsize with 64K page size without problem, * but such sectorsize/pagesize combination doesn't make much sense. * 4K will be our future standard, PAGE_SIZE is supported from the very * beginning.
*/ if (sectorsize > PAGE_SIZE || (sectorsize != SZ_4K &&
sectorsize != PAGE_SIZE &&
sectorsize != BTRFS_MIN_BLOCKSIZE)) {
btrfs_err(fs_info, "sectorsize %llu not yet supported for page size %lu",
sectorsize, PAGE_SIZE);
ret = -EINVAL;
}
if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
btrfs_err(fs_info, "invalid nodesize %llu", nodesize);
ret = -EINVAL;
} if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
btrfs_err(fs_info, "invalid leafsize %u, should be %llu",
le32_to_cpu(sb->__unused_leafsize), nodesize);
ret = -EINVAL;
}
/* Root alignment check */ if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
btrfs_warn(fs_info, "tree_root block unaligned: %llu",
btrfs_super_root(sb));
ret = -EINVAL;
} if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
btrfs_warn(fs_info, "chunk_root block unaligned: %llu",
btrfs_super_chunk_root(sb));
ret = -EINVAL;
} if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
btrfs_warn(fs_info, "log_root block unaligned: %llu",
btrfs_super_log_root(sb));
ret = -EINVAL;
}
if (!fs_info->fs_devices->temp_fsid &&
memcmp(fs_info->fs_devices->fsid, sb->fsid, BTRFS_FSID_SIZE) != 0) {
btrfs_err(fs_info, "superblock fsid doesn't match fsid of fs_devices: %pU != %pU",
sb->fsid, fs_info->fs_devices->fsid);
ret = -EINVAL;
}
if (memcmp(fs_info->fs_devices->metadata_uuid, btrfs_sb_fsid_ptr(sb),
BTRFS_FSID_SIZE) != 0) {
btrfs_err(fs_info, "superblock metadata_uuid doesn't match metadata uuid of fs_devices: %pU != %pU",
btrfs_sb_fsid_ptr(sb), fs_info->fs_devices->metadata_uuid);
ret = -EINVAL;
}
if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid,
BTRFS_FSID_SIZE) != 0) {
btrfs_err(fs_info, "dev_item UUID does not match metadata fsid: %pU != %pU",
fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid);
ret = -EINVAL;
}
/* * Artificial requirement for block-group-tree to force newer features * (free-space-tree, no-holes) so the test matrix is smaller.
*/ if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE) &&
(!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID) ||
!btrfs_fs_incompat(fs_info, NO_HOLES))) {
btrfs_err(fs_info, "block-group-tree feature requires free-space-tree and no-holes");
ret = -EINVAL;
}
/* * Hint to catch really bogus numbers, bitflips or so, more exact checks are * done later
*/ if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
btrfs_err(fs_info, "bytes_used is too small %llu",
btrfs_super_bytes_used(sb));
ret = -EINVAL;
} if (!is_power_of_2(btrfs_super_stripesize(sb))) {
btrfs_err(fs_info, "invalid stripesize %u",
btrfs_super_stripesize(sb));
ret = -EINVAL;
} if (btrfs_super_num_devices(sb) > (1UL << 31))
btrfs_warn(fs_info, "suspicious number of devices: %llu",
btrfs_super_num_devices(sb)); if (btrfs_super_num_devices(sb) == 0) {
btrfs_err(fs_info, "number of devices is 0");
ret = -EINVAL;
}
/* * Obvious sys_chunk_array corruptions, it must hold at least one key * and one chunk
*/ if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
btrfs_err(fs_info, "system chunk array too big %u > %u",
btrfs_super_sys_array_size(sb),
BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
ret = -EINVAL;
} if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
+ sizeof(struct btrfs_chunk)) {
btrfs_err(fs_info, "system chunk array too small %u < %zu",
btrfs_super_sys_array_size(sb), sizeof(struct btrfs_disk_key)
+ sizeof(struct btrfs_chunk));
ret = -EINVAL;
}
/* * The generation is a global counter, we'll trust it more than the others * but it's still possible that it's the one that's wrong.
*/ if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
btrfs_warn(fs_info, "suspicious: generation < chunk_root_generation: %llu < %llu",
btrfs_super_generation(sb),
btrfs_super_chunk_root_generation(sb)); if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
&& btrfs_super_cache_generation(sb) != (u64)-1)
btrfs_warn(fs_info, "suspicious: generation < cache_generation: %llu < %llu",
btrfs_super_generation(sb),
btrfs_super_cache_generation(sb));
return ret;
}
/* * Validation of super block at mount time. * Some checks already done early at mount time, like csum type and incompat * flags will be skipped.
*/ staticint btrfs_validate_mount_super(struct btrfs_fs_info *fs_info)
{ return btrfs_validate_super(fs_info, fs_info->super_copy, 0);
}
/* * Validation of super block at write time. * Some checks like bytenr check will be skipped as their values will be * overwritten soon. * Extra checks like csum type and incompat flags will be done here.
*/ staticint btrfs_validate_write_super(struct btrfs_fs_info *fs_info, struct btrfs_super_block *sb)
{ int ret;
ret = btrfs_validate_super(fs_info, sb, -1); if (ret < 0) goto out; if (!btrfs_supported_super_csum(btrfs_super_csum_type(sb))) {
ret = -EUCLEAN;
btrfs_err(fs_info, "invalid csum type, has %u want %u",
btrfs_super_csum_type(sb), BTRFS_CSUM_TYPE_CRC32); goto out;
} if (btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP) {
ret = -EUCLEAN;
btrfs_err(fs_info, "invalid incompat flags, has 0x%llx valid mask 0x%llx",
btrfs_super_incompat_flags(sb),
(unsignedlonglong)BTRFS_FEATURE_INCOMPAT_SUPP); goto out;
}
out: if (ret < 0)
btrfs_err(fs_info, "super block corruption detected before writing it to disk"); return ret;
}
staticint load_super_root(struct btrfs_root *root, u64 bytenr, u64 gen, int level)
{ struct btrfs_tree_parent_check check = {
.level = level,
.transid = gen,
.owner_root = btrfs_root_id(root)
}; int ret = 0;
root->node = read_tree_block(root->fs_info, bytenr, &check); if (IS_ERR(root->node)) {
ret = PTR_ERR(root->node);
root->node = NULL; return ret;
} if (!extent_buffer_uptodate(root->node)) {
free_extent_buffer(root->node);
root->node = NULL; return -EIO;
}
bytenr = btrfs_super_root(sb);
gen = btrfs_super_generation(sb);
level = btrfs_super_root_level(sb);
ret = load_super_root(fs_info->tree_root, bytenr, gen, level); if (ret) {
btrfs_warn(fs_info, "couldn't read tree root"); return ret;
} return 0;
}
staticint __cold init_tree_roots(struct btrfs_fs_info *fs_info)
{ int backup_index = find_newest_super_backup(fs_info); struct btrfs_super_block *sb = fs_info->super_copy; struct btrfs_root *tree_root = fs_info->tree_root; bool handle_error = false; int ret = 0; int i;
for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) { if (handle_error) { if (!IS_ERR(tree_root->node))
free_extent_buffer(tree_root->node);
tree_root->node = NULL;
if (!btrfs_test_opt(fs_info, USEBACKUPROOT)) break;
free_root_pointers(fs_info, 0);
/* * Don't use the log in recovery mode, it won't be * valid
*/
btrfs_set_super_log_root(sb, 0);
btrfs_warn(fs_info, "try to load backup roots slot %d", i);
ret = read_backup_root(fs_info, i);
backup_index = ret; if (ret < 0) return ret;
}
ret = load_important_roots(fs_info); if (ret) {
handle_error = true; continue;
}
/* * No need to hold btrfs_root::objectid_mutex since the fs * hasn't been fully initialised and we are the only user
*/
ret = btrfs_init_root_free_objectid(tree_root); if (ret < 0) {
handle_error = true; continue;
}
/* Always begin writing backup roots after the one being used */ if (backup_index < 0) {
fs_info->backup_root_index = 0;
} else {
fs_info->backup_root_index = backup_index + 1;
fs_info->backup_root_index %= BTRFS_NUM_BACKUP_ROOTS;
} break;
}
return ret;
}
/* * Lockdep gets confused between our buffer_tree which requires IRQ locking because * we modify marks in the IRQ context, and our delayed inode xarray which doesn't * have these requirements. Use a class key so lockdep doesn't get them mixed up.
*/ staticstruct lock_class_key buffer_xa_class;
/* Use the same flags as mapping->i_pages. */
xa_init_flags(&fs_info->buffer_tree, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT);
lockdep_set_class(&fs_info->buffer_tree.xa_lock, &buffer_xa_class);
/* Usable values until the real ones are cached from the superblock */
fs_info->nodesize = 4096;
fs_info->sectorsize = 4096;
fs_info->sectorsize_bits = ilog2(4096);
fs_info->stripesize = 4096;
/* Default compress algorithm when user does -o compress */
fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL); if (ret) return ret;
ret = percpu_counter_init(&fs_info->dev_replace.bio_counter, 0,
GFP_KERNEL); if (ret) return ret;
fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
GFP_KERNEL); if (!fs_info->delayed_root) return -ENOMEM;
btrfs_init_delayed_root(fs_info->delayed_root);
if (sb_rdonly(sb))
set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state); if (btrfs_test_opt(fs_info, IGNOREMETACSUMS))
set_bit(BTRFS_FS_STATE_SKIP_META_CSUMS, &fs_info->fs_state);
/* * 1st step is to iterate through the existing UUID tree and * to delete all entries that contain outdated data. * 2nd step is to add all missing entries to the UUID tree.
*/
ret = btrfs_uuid_tree_iterate(fs_info); if (ret < 0) { if (ret != -EINTR)
btrfs_warn(fs_info, "iterating uuid_tree failed %d",
ret);
up(&fs_info->uuid_tree_rescan_sem); return ret;
} return btrfs_uuid_scan_kthread(data);
}
for (int i = 0; i < found; i++) { /* Avoid to grab roots in dead_roots. */ if (btrfs_root_refs(&gang[i]->root_item) == 0) {
gang[i] = NULL; continue;
} /* Grab all the search result for later use. */
gang[i] = btrfs_grab_root(gang[i]);
}
spin_unlock(&fs_info->fs_roots_radix_lock);
for (int i = 0; i < found; i++) { if (!gang[i]) continue;
root_objectid = btrfs_root_id(gang[i]); /* * Continue to release the remaining roots after the first * error without cleanup and preserve the first error * for the return.
*/ if (!ret)
ret = btrfs_orphan_cleanup(gang[i]);
btrfs_put_root(gang[i]);
} if (ret) break;
root_objectid++;
} return ret;
}
/* * Mounting logic specific to read-write file systems. Shared by open_ctree * and btrfs_remount when remounting from read-only to read-write.
*/ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
{ int ret; constbool cache_opt = btrfs_test_opt(fs_info, SPACE_CACHE); bool rebuild_free_space_tree = false;
if (btrfs_test_opt(fs_info, CLEAR_CACHE) &&
btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))
btrfs_warn(fs_info, "'clear_cache' option is ignored with extent tree v2"); else
rebuild_free_space_tree = true;
} elseif (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) {
btrfs_warn(fs_info, "free space tree is invalid");
rebuild_free_space_tree = true;
}
if (rebuild_free_space_tree) {
btrfs_info(fs_info, "rebuilding free space tree");
ret = btrfs_rebuild_free_space_tree(fs_info); if (ret) {
btrfs_warn(fs_info, "failed to rebuild free space tree: %d", ret); goto out;
}
}
if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
!btrfs_test_opt(fs_info, FREE_SPACE_TREE)) {
btrfs_info(fs_info, "disabling free space tree");
ret = btrfs_delete_free_space_tree(fs_info); if (ret) {
btrfs_warn(fs_info, "failed to disable free space tree: %d", ret); goto out;
}
}
/* * btrfs_find_orphan_roots() is responsible for finding all the dead * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load * them into the fs_info->fs_roots_radix tree. This must be done before * calling btrfs_orphan_cleanup() on the tree root. If we don't do it * first, then btrfs_orphan_cleanup() will delete a dead root's orphan * item before the root's tree is deleted - this means that if we unmount * or crash before the deletion completes, on the next mount we will not * delete what remains of the tree because the orphan item does not * exists anymore, which is what tells us we have a pending deletion.
*/
ret = btrfs_find_orphan_roots(fs_info); if (ret) goto out;
ret = btrfs_cleanup_fs_roots(fs_info); if (ret) goto out;
mutex_lock(&fs_info->cleaner_mutex);
ret = btrfs_recover_relocation(fs_info);
mutex_unlock(&fs_info->cleaner_mutex); if (ret < 0) {
btrfs_warn(fs_info, "failed to recover relocation: %d", ret); goto out;
}
if (btrfs_test_opt(fs_info, FREE_SPACE_TREE) &&
!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
btrfs_info(fs_info, "creating free space tree");
ret = btrfs_create_free_space_tree(fs_info); if (ret) {
btrfs_warn(fs_info, "failed to create free space tree: %d", ret); goto out;
}
}
if (cache_opt != btrfs_free_space_cache_v1_active(fs_info)) {
ret = btrfs_set_free_space_cache_v1_active(fs_info, cache_opt); if (ret) goto out;
}
ret = btrfs_resume_balance_async(fs_info); if (ret) goto out;
ret = btrfs_resume_dev_replace_async(fs_info); if (ret) {
btrfs_warn(fs_info, "failed to resume dev_replace"); goto out;
}
btrfs_qgroup_rescan_resume(fs_info);
if (!fs_info->uuid_root) {
btrfs_info(fs_info, "creating UUID tree");
ret = btrfs_create_uuid_tree(fs_info); if (ret) {
btrfs_warn(fs_info, "failed to create the UUID tree %d", ret); goto out;
}
}
out: return ret;
}
/* * Do various sanity and dependency checks of different features. * * @is_rw_mount: If the mount is read-write. * * This is the place for less strict checks (like for subpage or artificial * feature dependencies). * * For strict checks or possible corruption detection, see * btrfs_validate_super(). * * This should be called after btrfs_parse_options(), as some mount options * (space cache related) can modify on-disk format like free space tree and * screw up certain feature dependencies.
*/ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
{ struct btrfs_super_block *disk_super = fs_info->super_copy;
u64 incompat = btrfs_super_incompat_flags(disk_super); const u64 compat_ro = btrfs_super_compat_ro_flags(disk_super); const u64 compat_ro_unsupp = (compat_ro & ~BTRFS_FEATURE_COMPAT_RO_SUPP);
if (incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP) {
btrfs_err(fs_info, "cannot mount because of unknown incompat features (0x%llx)",
incompat); return -EINVAL;
}
/* Runtime limitation for mixed block groups. */ if ((incompat & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
(fs_info->sectorsize != fs_info->nodesize)) {
btrfs_err(fs_info, "unequal nodesize/sectorsize (%u != %u) are not allowed for mixed block groups",
fs_info->nodesize, fs_info->sectorsize); return -EINVAL;
}
/* Mixed backref is an always-enabled feature. */
incompat |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
/* Set compression related flags just in case. */ if (fs_info->compress_type == BTRFS_COMPRESS_LZO)
incompat |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; elseif (fs_info->compress_type == BTRFS_COMPRESS_ZSTD)
incompat |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD;
/* * An ancient flag, which should really be marked deprecated. * Such runtime limitation doesn't really need a incompat flag.
*/ if (btrfs_super_nodesize(disk_super) > PAGE_SIZE)
incompat |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
if (compat_ro_unsupp && is_rw_mount) {
btrfs_err(fs_info, "cannot mount read-write because of unknown compat_ro features (0x%llx)",
compat_ro); return -EINVAL;
}
/* * We have unsupported RO compat features, although RO mounted, we * should not cause any metadata writes, including log replay. * Or we could screw up whatever the new feature requires.
*/ if (compat_ro_unsupp && btrfs_super_log_root(disk_super) &&
!btrfs_test_opt(fs_info, NOLOGREPLAY)) {
btrfs_err(fs_info, "cannot replay dirty log with unsupported compat_ro features (0x%llx), try rescue=nologreplay",
compat_ro); return -EINVAL;
}
/* * Artificial limitations for block group tree, to force * block-group-tree to rely on no-holes and free-space-tree.
*/ if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE) &&
(!btrfs_fs_incompat(fs_info, NO_HOLES) ||
!btrfs_test_opt(fs_info, FREE_SPACE_TREE))) {
btrfs_err(fs_info, "block-group-tree feature requires no-holes and free-space-tree features"); return -EINVAL;
}
/* * Subpage runtime limitation on v1 cache. * * V1 space cache still has some hard codeed PAGE_SIZE usage, while * we're already defaulting to v2 cache, no need to bother v1 as it's * going to be deprecated anyway.
*/ if (fs_info->sectorsize < PAGE_SIZE && btrfs_test_opt(fs_info, SPACE_CACHE)) {
btrfs_warn(fs_info, "v1 space cache is not supported for page size %lu with sectorsize %u",
PAGE_SIZE, fs_info->sectorsize); return -EINVAL;
}
/* This can be called by remount, we need to protect the super block. */
spin_lock(&fs_info->super_lock);
btrfs_set_super_incompat_flags(disk_super, incompat);
spin_unlock(&fs_info->super_lock);
ret = init_mount_fs_info(fs_info, sb); if (ret) goto fail;
/* These need to be init'ed before we start creating inodes and such. */
tree_root = btrfs_alloc_root(fs_info, BTRFS_ROOT_TREE_OBJECTID,
GFP_KERNEL);
fs_info->tree_root = tree_root;
chunk_root = btrfs_alloc_root(fs_info, BTRFS_CHUNK_TREE_OBJECTID,
GFP_KERNEL);
fs_info->chunk_root = chunk_root; if (!tree_root || !chunk_root) {
ret = -ENOMEM; goto fail;
}
ret = btrfs_init_btree_inode(sb); if (ret) goto fail;
invalidate_bdev(fs_devices->latest_dev->bdev);
/* * Read super block and check the signature bytes only
*/
disk_super = btrfs_read_disk_super(fs_devices->latest_dev->bdev, 0, false); if (IS_ERR(disk_super)) {
ret = PTR_ERR(disk_super); goto fail_alloc;
}
btrfs_info(fs_info, "first mount of filesystem %pU", disk_super->fsid); /* * Verify the type first, if that or the checksum value are * corrupted, we'll find out
*/
csum_type = btrfs_super_csum_type(disk_super); if (!btrfs_supported_super_csum(csum_type)) {
btrfs_err(fs_info, "unsupported checksum algorithm: %u",
csum_type);
ret = -EINVAL;
btrfs_release_disk_super(disk_super); goto fail_alloc;
}
ret = btrfs_init_csum_hash(fs_info, csum_type); if (ret) {
btrfs_release_disk_super(disk_super); goto fail_alloc;
}
/* * We want to check superblock checksum, the type is stored inside. * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k).
*/ if (btrfs_check_super_csum(fs_info, disk_super)) {
btrfs_err(fs_info, "superblock checksum mismatch");
ret = -EINVAL;
btrfs_release_disk_super(disk_super); goto fail_alloc;
}
/* * super_copy is zeroed at allocation time and we never touch the * following bytes up to INFO_SIZE, the checksum is calculated from * the whole block of INFO_SIZE
*/
memcpy(fs_info->super_copy, disk_super, sizeof(*fs_info->super_copy));
btrfs_release_disk_super(disk_super);
/* * Handle the space caching options appropriately now that we have the * super block loaded and validated.
*/
btrfs_set_free_space_cache_settings(fs_info);
if (!btrfs_check_options(fs_info, &fs_info->mount_opt, sb->s_flags)) {
ret = -EINVAL; goto fail_alloc;
}
ret = btrfs_check_features(fs_info, !sb_rdonly(sb)); if (ret < 0) goto fail_alloc;
/* * At this point our mount options are validated, if we set ->max_inline * to something non-standard make sure we truncate it to sectorsize.
*/
fs_info->max_inline = min_t(u64, fs_info->max_inline, fs_info->sectorsize);
ret = btrfs_init_workqueues(fs_info); if (ret) goto fail_sb_buffer;
/* Update the values for the current filesystem. */
sb->s_blocksize = sectorsize;
sb->s_blocksize_bits = blksize_bits(sectorsize);
memcpy(&sb->s_uuid, fs_info->fs_devices->fsid, BTRFS_FSID_SIZE);
mutex_lock(&fs_info->chunk_mutex);
ret = btrfs_read_sys_array(fs_info);
mutex_unlock(&fs_info->chunk_mutex); if (ret) {
btrfs_err(fs_info, "failed to read the system array: %d", ret); goto fail_sb_buffer;
}
generation = btrfs_super_chunk_root_generation(disk_super);
level = btrfs_super_chunk_root_level(disk_super);
ret = load_super_root(chunk_root, btrfs_super_chunk_root(disk_super),
generation, level); if (ret) {
btrfs_err(fs_info, "failed to read chunk root"); goto fail_tree_roots;
}
ret = btrfs_read_chunk_tree(fs_info); if (ret) {
btrfs_err(fs_info, "failed to read chunk tree: %d", ret); goto fail_tree_roots;
}
/* * At this point we know all the devices that make this filesystem, * including the seed devices but we don't know yet if the replace * target is required. So free devices that are not part of this * filesystem but skip the replace target device which is checked * below in btrfs_init_dev_replace().
*/
btrfs_free_extra_devids(fs_devices); if (!fs_devices->latest_dev->bdev) {
btrfs_err(fs_info, "failed to read devices");
ret = -EIO; goto fail_tree_roots;
}
ret = init_tree_roots(fs_info); if (ret) goto fail_tree_roots;
/* * Get zone type information of zoned block devices. This will also * handle emulation of a zoned filesystem if a regular device has the * zoned incompat feature flag set.
*/
ret = btrfs_get_dev_zone_info_all_devices(fs_info); if (ret) {
btrfs_err(fs_info, "zoned: failed to read device zone info: %d", ret); goto fail_block_groups;
}
/* * If we have a uuid root and we're not being told to rescan we need to * check the generation here so we can set the * BTRFS_FS_UPDATE_UUID_TREE_GEN bit. Otherwise we could commit the * transaction during a balance or the log replay without updating the * uuid generation, and then if we crash we would rescan the uuid tree, * even though it was perfectly fine.
*/ if (fs_info->uuid_root && !btrfs_test_opt(fs_info, RESCAN_UUID_TREE) &&
fs_info->generation == btrfs_super_uuid_tree_generation(disk_super))
set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags);
ret = btrfs_verify_dev_extents(fs_info); if (ret) {
btrfs_err(fs_info, "failed to verify dev extents against chunks: %d",
ret); goto fail_block_groups;
}
ret = btrfs_recover_balance(fs_info); if (ret) {
btrfs_err(fs_info, "failed to recover balance: %d", ret); goto fail_block_groups;
}
ret = btrfs_init_dev_stats(fs_info); if (ret) {
btrfs_err(fs_info, "failed to init dev_stats: %d", ret); goto fail_block_groups;
}
ret = btrfs_init_dev_replace(fs_info); if (ret) {
btrfs_err(fs_info, "failed to init dev_replace: %d", ret); goto fail_block_groups;
}
ret = btrfs_check_zoned_mode(fs_info); if (ret) {
btrfs_err(fs_info, "failed to initialize zoned mode: %d",
ret); goto fail_block_groups;
}
ret = btrfs_sysfs_add_fsid(fs_devices); if (ret) {
btrfs_err(fs_info, "failed to init sysfs fsid interface: %d",
ret); goto fail_block_groups;
}
ret = btrfs_sysfs_add_mounted(fs_info); if (ret) {
btrfs_err(fs_info, "failed to init sysfs interface: %d", ret); goto fail_fsdev_sysfs;
}
ret = btrfs_init_space_info(fs_info); if (ret) {
btrfs_err(fs_info, "failed to initialize space info: %d", ret); goto fail_sysfs;
}
ret = btrfs_read_block_groups(fs_info); if (ret) {
btrfs_err(fs_info, "failed to read block groups: %d", ret); goto fail_sysfs;
}
if (!sb_rdonly(sb) && fs_info->fs_devices->missing_devices &&
!btrfs_check_rw_degradable(fs_info, NULL)) {
btrfs_warn(fs_info, "writable mount is not allowed due to too many missing devices");
ret = -EINVAL; goto fail_sysfs;
}
fs_info->cleaner_kthread = kthread_run(cleaner_kthread, fs_info, "btrfs-cleaner"); if (IS_ERR(fs_info->cleaner_kthread)) {
ret = PTR_ERR(fs_info->cleaner_kthread); goto fail_sysfs;
}
fs_info->transaction_kthread = kthread_run(transaction_kthread,
tree_root, "btrfs-transaction"); if (IS_ERR(fs_info->transaction_kthread)) {
ret = PTR_ERR(fs_info->transaction_kthread); goto fail_cleaner;
}
ret = btrfs_read_qgroup_config(fs_info); if (ret) goto fail_trans_kthread;
if (btrfs_build_ref_tree(fs_info))
btrfs_err(fs_info, "couldn't build ref tree");
/* do not make disk changes in broken FS or nologreplay is given */ if (btrfs_super_log_root(disk_super) != 0 &&
!btrfs_test_opt(fs_info, NOLOGREPLAY)) {
btrfs_info(fs_info, "start tree-log replay");
ret = btrfs_replay_log(fs_info, fs_devices); if (ret) goto fail_qgroup;
}
fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true); if (IS_ERR(fs_info->fs_root)) {
ret = PTR_ERR(fs_info->fs_root);
btrfs_warn(fs_info, "failed to read fs tree: %d", ret);
fs_info->fs_root = NULL; goto fail_qgroup;
}
if (sb_rdonly(sb)) return 0;
ret = btrfs_start_pre_rw_mount(fs_info); if (ret) {
close_ctree(fs_info); return ret;
}
btrfs_discard_resume(fs_info);
if (fs_info->uuid_root &&
(btrfs_test_opt(fs_info, RESCAN_UUID_TREE) ||
fs_info->generation != btrfs_super_uuid_tree_generation(disk_super))) {
btrfs_info(fs_info, "checking UUID tree");
ret = btrfs_check_uuid_tree(fs_info); if (ret) {
btrfs_warn(fs_info, "failed to check the UUID tree: %d", ret);
close_ctree(fs_info); return ret;
}
}
set_bit(BTRFS_FS_OPEN, &fs_info->flags);
/* Kick the cleaner thread so it'll start deleting snapshots. */ if (test_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags))
wake_up_process(fs_info->cleaner_kthread);
bio_for_each_folio_all(fi, bio) { if (bio->bi_status) {
btrfs_warn_rl(device->fs_info, "lost super block write due to IO error on %s (%d)",
btrfs_dev_name(device),
blk_status_to_errno(bio->bi_status));
btrfs_dev_stat_inc_and_print(device,
BTRFS_DEV_STAT_WRITE_ERRS); /* Ensure failure if the primary sb fails. */ if (bio->bi_opf & REQ_FUA)
atomic_add(BTRFS_SUPER_PRIMARY_WRITE_ERROR,
&device->sb_write_errors); else
atomic_inc(&device->sb_write_errors);
}
folio_unlock(fi.folio);
folio_put(fi.folio);
}
bio_put(bio);
}
/* * Write superblock @sb to the @device. Do not wait for completion, all the * folios we use for writing are locked. * * Write @max_mirrors copies of the superblock, where 0 means default that fit * the expected device size at commit time. Note that max_mirrors must be * same for write and wait phases. * * Return number of errors when folio is not found or submission fails.
*/ staticint write_dev_supers(struct btrfs_device *device, struct btrfs_super_block *sb, int max_mirrors)
{ struct btrfs_fs_info *fs_info = device->fs_info; struct address_space *mapping = device->bdev->bd_mapping;
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); int i; int ret;
u64 bytenr, bytenr_orig;
atomic_set(&device->sb_write_errors, 0);
if (max_mirrors == 0)
max_mirrors = BTRFS_SUPER_MIRROR_MAX;
shash->tfm = fs_info->csum_shash;
for (i = 0; i < max_mirrors; i++) { struct folio *folio; struct bio *bio; struct btrfs_super_block *disk_super;
size_t offset;
bytenr_orig = btrfs_sb_offset(i);
ret = btrfs_sb_log_location(device, i, WRITE, &bytenr); if (ret == -ENOENT) { continue;
} elseif (ret < 0) {
btrfs_err(device->fs_info, "couldn't get super block location for mirror %d error %d",
i, ret);
atomic_inc(&device->sb_write_errors); continue;
} if (bytenr + BTRFS_SUPER_INFO_SIZE >=
device->commit_total_bytes) break;
/* * Directly use bios here instead of relying on the page cache * to do I/O, so we don't lose the ability to do integrity * checking.
*/
bio = bio_alloc(device->bdev, 1,
REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO,
GFP_NOFS);
bio->bi_iter.bi_sector = bytenr >> SECTOR_SHIFT;
bio->bi_private = device;
bio->bi_end_io = btrfs_end_super_write;
bio_add_folio_nofail(bio, folio, BTRFS_SUPER_INFO_SIZE, offset);
/* * We FUA only the first super block. The others we allow to * go down lazy and there's a short window where the on-disk * copies might still contain the older version.
*/ if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER))
bio->bi_opf |= REQ_FUA;
submit_bio(bio);
if (btrfs_advance_sb_log(device, i))
atomic_inc(&device->sb_write_errors);
} return atomic_read(&device->sb_write_errors) < i ? 0 : -1;
}
/* * Wait for write completion of superblocks done by write_dev_supers, * @max_mirrors same for write and wait phases. * * Return -1 if primary super block write failed or when there were no super block * copies written. Otherwise 0.
*/ staticint wait_dev_supers(struct btrfs_device *device, int max_mirrors)
{ int i; int errors = 0; bool primary_failed = false; int ret;
u64 bytenr;
if (max_mirrors == 0)
max_mirrors = BTRFS_SUPER_MIRROR_MAX;
for (i = 0; i < max_mirrors; i++) { struct folio *folio;
ret = btrfs_sb_log_location(device, i, READ, &bytenr); if (ret == -ENOENT) { break;
} elseif (ret < 0) {
errors++; if (i == 0)
primary_failed = true; continue;
} if (bytenr + BTRFS_SUPER_INFO_SIZE >=
device->commit_total_bytes) break;
folio = filemap_get_folio(device->bdev->bd_mapping,
bytenr >> PAGE_SHIFT); /* If the folio has been removed, then we know it completed. */ if (IS_ERR(folio)) continue;
/* Folio will be unlocked once the write completes. */
folio_wait_locked(folio);
folio_put(folio);
}
errors += atomic_read(&device->sb_write_errors); if (errors >= BTRFS_SUPER_PRIMARY_WRITE_ERROR)
primary_failed = true; if (primary_failed) {
btrfs_err(device->fs_info, "error writing primary super block to device %llu",
device->devid); return -1;
}
return errors < i ? 0 : -1;
}
/* * endio for the write_dev_flush, this will wake anyone waiting * for the barrier when it is done
*/ staticvoid btrfs_end_empty_barrier(struct bio *bio)
{
bio_uninit(bio);
complete(bio->bi_private);
}
/* * Submit a flush request to the device if it supports it. Error handling is * done in the waiting counterpart.
*/ staticvoid write_dev_flush(struct btrfs_device *device)
{ struct bio *bio = &device->flush_bio;
/* * If the flush bio has been submitted by write_dev_flush, wait for it. * Return true for any error, and false otherwise.
*/ staticbool wait_dev_flush(struct btrfs_device *device)
{ struct bio *bio = &device->flush_bio;
if (!test_and_clear_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state)) returnfalse;
wait_for_completion_io(&device->flush_wait);
if (bio->bi_status) {
device->last_flush_error = bio->bi_status;
btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_FLUSH_ERRS); returntrue;
}
returnfalse;
}
/* * send an empty flush down to each device in parallel, * then wait for them
*/ staticint barrier_all_devices(struct btrfs_fs_info *info)
{ struct list_head *head; struct btrfs_device *dev; int errors_wait = 0;
lockdep_assert_held(&info->fs_devices->device_list_mutex); /* send down all the barriers */
head = &info->fs_devices->devices;
list_for_each_entry(dev, head, dev_list) { if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) continue; if (!dev->bdev) continue; if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) ||
!test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue;
write_dev_flush(dev);
}
/* wait for all the barriers */
list_for_each_entry(dev, head, dev_list) { if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) continue; if (!dev->bdev) {
errors_wait++; continue;
} if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) ||
!test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue;
if (wait_dev_flush(dev))
errors_wait++;
}
/* * Checks last_flush_error of disks in order to determine the device * state.
*/ if (errors_wait && !btrfs_check_rw_degradable(info, NULL)) return -EIO;
return 0;
}
int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags)
{ int raid_type; int min_tolerated = INT_MAX;
/* * max_mirrors == 0 indicates we're from commit_transaction, * not from fsync where the tree roots in fs_info have not * been consistent on disk.
*/ if (max_mirrors == 0)
backup_super_roots(fs_info);
ret = btrfs_validate_write_super(fs_info, sb); if (ret < 0) {
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
btrfs_handle_fs_error(fs_info, -EUCLEAN, "unexpected superblock corruption detected"); return -EUCLEAN;
}
ret = write_dev_supers(dev, sb, max_mirrors); if (ret)
total_errors++;
} if (total_errors > max_errors) {
btrfs_err(fs_info, "%d errors while writing supers",
total_errors);
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
/* FUA is masked off if unsupported and can't be the reason */
btrfs_handle_fs_error(fs_info, -EIO, "%d errors while writing supers",
total_errors); return -EIO;
}
total_errors = 0;
list_for_each_entry(dev, head, dev_list) { if (!dev->bdev) continue; if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) ||
!test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue;
ret = wait_dev_supers(dev, max_mirrors); if (ret)
total_errors++;
}
mutex_unlock(&fs_info->fs_devices->device_list_mutex); if (total_errors > max_errors) {
btrfs_handle_fs_error(fs_info, -EIO, "%d errors while writing supers",
total_errors); return -EIO;
} return 0;
}
/* Drop a fs root from the radix tree and free it. */ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
{ bool drop_ref = false;
spin_lock(&fs_info->fs_roots_radix_lock);
radix_tree_delete(&fs_info->fs_roots_radix,
(unsignedlong)btrfs_root_id(root)); if (test_and_clear_bit(BTRFS_ROOT_IN_RADIX, &root->state))
drop_ref = true;
spin_unlock(&fs_info->fs_roots_radix_lock);
if (BTRFS_FS_ERROR(fs_info)) {
ASSERT(root->log_root == NULL); if (root->reloc_root) {
btrfs_put_root(root->reloc_root);
root->reloc_root = NULL;
}
}
if (drop_ref)
btrfs_put_root(root);
}
int btrfs_commit_super(struct btrfs_fs_info *fs_info)
{
mutex_lock(&fs_info->cleaner_mutex);
btrfs_run_delayed_iputs(fs_info);
mutex_unlock(&fs_info->cleaner_mutex);
wake_up_process(fs_info->cleaner_kthread);
/* wait until ongoing cleanup work done */
down_write(&fs_info->cleanup_work_sem);
up_write(&fs_info->cleanup_work_sem);
/* * This function is only called at the very end of close_ctree(), * thus no other running transaction, no need to take trans_lock.
*/
ASSERT(test_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags));
list_for_each_entry_safe(trans, tmp, &fs_info->trans_list, list) { struct extent_state *cached = NULL;
u64 dirty_bytes = 0;
u64 cur = 0;
u64 found_start;
u64 found_end;
found = true; while (btrfs_find_first_extent_bit(&trans->dirty_pages, cur,
&found_start, &found_end,
EXTENT_DIRTY, &cached)) {
dirty_bytes += found_end + 1 - found_start;
cur = found_end + 1;
}
btrfs_warn(fs_info, "transaction %llu (with %llu dirty metadata bytes) is not committed",
trans->transid, dirty_bytes);
btrfs_cleanup_one_transaction(trans);
if (trans == fs_info->running_transaction)
fs_info->running_transaction = NULL;
list_del_init(&trans->list);
void __cold close_ctree(struct btrfs_fs_info *fs_info)
{ int ret;
set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags);
/* * If we had UNFINISHED_DROPS we could still be processing them, so * clear that bit and wake up relocation so it can stop. * We must do this before stopping the block group reclaim task, because * at btrfs_relocate_block_group() we wait for this bit, and after the * wait we stop with -EINTR if btrfs_fs_closing() returns non-zero - we * have just set BTRFS_FS_CLOSING_START, so btrfs_fs_closing() will * return 1.
*/
btrfs_wake_unfinished_drop(fs_info);
/* * We may have the reclaim task running and relocating a data block group, * in which case it may create delayed iputs. So stop it before we park * the cleaner kthread otherwise we can get new delayed iputs after * parking the cleaner, and that can make the async reclaim task to hang * if it's waiting for delayed iputs to complete, since the cleaner is * parked and can not run delayed iputs - this will make us hang when * trying to stop the async reclaim task.
*/
cancel_work_sync(&fs_info->reclaim_bgs_work); /* * We don't want the cleaner to start new transactions, add more delayed * iputs, etc. while we're closing. We can't use kthread_stop() yet * because that frees the task_struct, and the transaction kthread might * still try to wake up the cleaner.
*/
kthread_park(fs_info->cleaner_kthread);
/* wait for the qgroup rescan worker to stop */
btrfs_qgroup_wait_for_completion(fs_info, false);
/* wait for the uuid_scan task to finish */
down(&fs_info->uuid_tree_rescan_sem); /* avoid complains from lockdep et al., set sem back to initial state */
up(&fs_info->uuid_tree_rescan_sem);
/* pause restriper - we want to resume on mount */
btrfs_pause_balance(fs_info);
btrfs_dev_replace_suspend_for_unmount(fs_info);
btrfs_scrub_cancel(fs_info);
/* wait for any defraggers to finish */
wait_event(fs_info->transaction_wait,
(atomic_read(&fs_info->defrag_running) == 0));
/* clear out the rbtree of defraggable inodes */
btrfs_cleanup_defrag_inodes(fs_info);
/* * Handle the error fs first, as it will flush and wait for all ordered * extents. This will generate delayed iputs, thus we want to handle * it first.
*/ if (unlikely(BTRFS_FS_ERROR(fs_info)))
btrfs_error_commit_super(fs_info);
/* * Wait for any fixup workers to complete. * If we don't wait for them here and they are still running by the time * we call kthread_stop() against the cleaner kthread further below, we * get an use-after-free on the cleaner because the fixup worker adds an * inode to the list of delayed iputs and then attempts to wakeup the * cleaner kthread, which was already stopped and destroyed. We parked * already the cleaner, but below we run all pending delayed iputs.
*/
btrfs_flush_workqueue(fs_info->fixup_workers); /* * Similar case here, we have to wait for delalloc workers before we * proceed below and stop the cleaner kthread, otherwise we trigger a * use-after-tree on the cleaner kthread task_struct when a delalloc * worker running submit_compressed_extents() adds a delayed iput, which * does a wake up on the cleaner kthread, which was already freed below * when we call kthread_stop().
*/
btrfs_flush_workqueue(fs_info->delalloc_workers);
/* * We can have ordered extents getting their last reference dropped from * the fs_info->workers queue because for async writes for data bios we * queue a work for that queue, at btrfs_wq_submit_bio(), that runs * run_one_async_done() which calls btrfs_bio_end_io() in case the bio * has an error, and that later function can do the final * btrfs_put_ordered_extent() on the ordered extent attached to the bio, * which adds a delayed iput for the inode. So we must flush the queue * so that we don't have delayed iputs after committing the current * transaction below and stopping the cleaner and transaction kthreads.
*/
btrfs_flush_workqueue(fs_info->workers);
/* * When finishing a compressed write bio we schedule a work queue item * to finish an ordered extent - btrfs_finish_compressed_write_work() * calls btrfs_finish_ordered_extent() which in turns does a call to * btrfs_queue_ordered_fn(), and that queues the ordered extent * completion either in the endio_write_workers work queue or in the * fs_info->endio_freespace_worker work queue. We flush those queues * below, so before we flush them we must flush this queue for the * workers of compressed writes.
*/
flush_workqueue(fs_info->compressed_write_workers);
/* * After we parked the cleaner kthread, ordered extents may have * completed and created new delayed iputs. If one of the async reclaim * tasks is running and in the RUN_DELAYED_IPUTS flush state, then we * can hang forever trying to stop it, because if a delayed iput is * added after it ran btrfs_run_delayed_iputs() and before it called * btrfs_wait_on_delayed_iputs(), it will hang forever since there is * no one else to run iputs. * * So wait for all ongoing ordered extents to complete and then run * delayed iputs. This works because once we reach this point no one * can create new ordered extents, but delayed iputs can still be added * by a reclaim worker (see comments further below). * * Also note that btrfs_wait_ordered_roots() is not safe here, because * it waits for BTRFS_ORDERED_COMPLETE to be set on an ordered extent, * but the delayed iput for the respective inode is made only when doing * the final btrfs_put_ordered_extent() (which must happen at * btrfs_finish_ordered_io() when we are unmounting).
*/
btrfs_flush_workqueue(fs_info->endio_write_workers); /* Ordered extents for free space inodes. */
btrfs_flush_workqueue(fs_info->endio_freespace_worker); /* * Run delayed iputs in case an async reclaim worker is waiting for them * to be run as mentioned above.
*/
btrfs_run_delayed_iputs(fs_info);
/* * Run delayed iputs again because an async reclaim worker may have * added new ones if it was flushing delalloc: * * shrink_delalloc() -> btrfs_start_delalloc_roots() -> * start_delalloc_inodes() -> btrfs_add_delayed_iput()
*/
btrfs_run_delayed_iputs(fs_info);
/* There should be no more workload to generate new delayed iputs. */
set_bit(BTRFS_FS_STATE_NO_DELAYED_IPUT, &fs_info->fs_state);
/* Cancel or finish ongoing discard work */
btrfs_discard_cleanup(fs_info);
if (!sb_rdonly(fs_info->sb)) { /* * The cleaner kthread is stopped, so do one final pass over * unused block groups.
*/
btrfs_delete_unused_bgs(fs_info);
/* * There might be existing delayed inode workers still running * and holding an empty delayed inode item. We must wait for * them to complete first because they can create a transaction. * This happens when someone calls btrfs_balance_delayed_items() * and then a transaction commit runs the same delayed nodes * before any delayed worker has done something with the nodes. * We must wait for any worker here and not at transaction * commit time since that could cause a deadlock. * This is a very rare case.
*/
btrfs_flush_workqueue(fs_info->delayed_workers);
ret = btrfs_commit_super(fs_info); if (ret)
btrfs_err(fs_info, "commit super ret %d", ret);
}
/* * we must make sure there is not any read request to * submit after we stopping all workers.
*/
invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
btrfs_stop_all_workers(fs_info);
/* We shouldn't have any transaction open at this point */
warn_about_uncommitted_trans(fs_info);
/* * We must free the block groups after dropping the fs_roots as we could * have had an IO error and have left over tree log blocks that aren't * cleaned up until the fs roots are freed. This makes the block group * accounting appear to be wrong because there's pending reserved bytes, * so make sure we do the block group cleanup afterwards.
*/
btrfs_free_block_groups(fs_info);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS /* * This is a fast path so only do this check if we have sanity tests * enabled. Normal people shouldn't be using unmapped buffers as dirty * outside of the sanity tests.
*/ if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &buf->bflags))) return; #endif /* This is an active transaction (its state < TRANS_STATE_UNBLOCKED). */
ASSERT(trans->transid == fs_info->generation);
btrfs_assert_tree_write_locked(buf); if (unlikely(transid != fs_info->generation)) {
btrfs_abort_transaction(trans, -EUCLEAN);
btrfs_crit(fs_info, "dirty buffer transid mismatch, logical %llu found transid %llu running transid %llu",
buf->start, transid, fs_info->generation);
}
set_extent_buffer_dirty(buf);
}
staticvoid __btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info, int flush_delayed)
{ /* * looks as though older kernels can get into trouble with * this code, they end up stuck in balance_dirty_pages forever
*/ int ret;
if (current->flags & PF_MEMALLOC) return;
if (flush_delayed)
btrfs_balance_delayed_items(fs_info);
ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
BTRFS_DIRTY_METADATA_THRESH,
fs_info->dirty_metadata_batch); if (ret > 0) {
balance_dirty_pages_ratelimited(fs_info->btree_inode->i_mapping);
}
}
spin_lock(&root->ordered_extent_lock); /* * This will just short circuit the ordered completion stuff which will * make sure the ordered extent gets properly cleaned up.
*/
list_for_each_entry(ordered, &root->ordered_extents,
root_extent_list)
set_bit(BTRFS_ORDERED_IOERR, &ordered->flags);
spin_unlock(&root->ordered_extent_lock);
}
/* * We need this here because if we've been flipped read-only we won't * get sync() from the umount, so we need to make sure any ordered * extents that haven't had their dirty pages IO start writeout yet * actually get run and error out properly.
*/
btrfs_wait_ordered_roots(fs_info, U64_MAX, NULL);
}
/* * Make sure we get a live inode and that it'll not disappear * meanwhile.
*/
inode = igrab(&btrfs_inode->vfs_inode); if (inode) { unsignedint nofs_flag;
while (1) { struct extent_state *cached_state = NULL;
/* * The btrfs_finish_extent_commit() may get the same range as * ours between find_first_extent_bit and clear_extent_dirty. * Hence, hold the unused_bg_unpin_mutex to avoid double unpin * the same extent range.
*/
mutex_lock(&fs_info->unused_bg_unpin_mutex); if (!btrfs_find_first_extent_bit(unpin, 0, &start, &end,
EXTENT_DIRTY, &cached_state)) {
mutex_unlock(&fs_info->unused_bg_unpin_mutex); break;
}
/* * Refer to the definition of io_bgs member for details why it's safe * to use it without any locking
*/ while (!list_empty(&cur_trans->io_bgs)) {
cache = list_first_entry(&cur_trans->io_bgs, struct btrfs_block_group,
io_list);
spin_lock(&fs_info->trans_lock); while (!list_empty(&fs_info->trans_list)) {
t = list_first_entry(&fs_info->trans_list, struct btrfs_transaction, list); if (t->state >= TRANS_STATE_COMMIT_PREP) {
refcount_inc(&t->use_count);
spin_unlock(&fs_info->trans_lock);
btrfs_wait_for_commit(fs_info, t->transid);
btrfs_put_transaction(t);
spin_lock(&fs_info->trans_lock); continue;
} if (t == fs_info->running_transaction) {
t->state = TRANS_STATE_COMMIT_DOING;
spin_unlock(&fs_info->trans_lock); /* * We wait for 0 num_writers since we don't hold a trans * handle open currently for this transaction.
*/
wait_event(t->writer_wait,
atomic_read(&t->num_writers) == 0);
} else {
spin_unlock(&fs_info->trans_lock);
}
btrfs_cleanup_one_transaction(t);
spin_lock(&fs_info->trans_lock); if (t == fs_info->running_transaction)
fs_info->running_transaction = NULL;
list_del_init(&t->list);
spin_unlock(&fs_info->trans_lock);
int btrfs_init_root_free_objectid(struct btrfs_root *root)
{
BTRFS_PATH_AUTO_FREE(path); int ret; struct extent_buffer *l; struct btrfs_key search_key; struct btrfs_key found_key; int slot;
path = btrfs_alloc_path(); if (!path) return -ENOMEM;
search_key.objectid = BTRFS_LAST_FREE_OBJECTID;
search_key.type = -1;
search_key.offset = (u64)-1;
ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret < 0) return ret; if (ret == 0) { /* * Key with offset -1 found, there would have to exist a root * with such id, but this is out of valid range.
*/ return -EUCLEAN;
} if (path->slots[0] > 0) {
slot = path->slots[0] - 1;
l = path->nodes[0];
btrfs_item_key_to_cpu(l, &found_key, slot);
root->free_objectid = max_t(u64, found_key.objectid + 1,
BTRFS_FIRST_FREE_OBJECTID);
} else {
root->free_objectid = BTRFS_FIRST_FREE_OBJECTID;
}
return 0;
}
int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid)
{ int ret;
mutex_lock(&root->objectid_mutex);
if (unlikely(root->free_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
btrfs_warn(root->fs_info, "the objectid of root %llu reaches its highest value",
btrfs_root_id(root));
ret = -ENOSPC; goto out;
}
¤ Diese beiden folgenden Angebotsgruppen bietet das Unternehmen0.74Angebot
(Wie Sie bei der Firma Beratungs- und Dienstleistungen beauftragen können 2026-04-26)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.
