diff options
Diffstat (limited to 'fs/btrfs/disk-io.c')
| -rw-r--r-- | fs/btrfs/disk-io.c | 3913 |
1 files changed, 2085 insertions, 1828 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 7c6f0bbb54a5..89149fac804c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -17,21 +17,18 @@ #include <linux/error-injection.h> #include <linux/crc32c.h> #include <linux/sched/mm.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/hash.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" #include "btrfs_inode.h" -#include "volumes.h" +#include "bio.h" #include "print-tree.h" #include "locking.h" #include "tree-log.h" #include "free-space-cache.h" #include "free-space-tree.h" -#include "inode-map.h" -#include "check-integrity.h" -#include "rcu-string.h" #include "dev-replace.h" #include "raid56.h" #include "sysfs.h" @@ -42,6 +39,18 @@ #include "block-group.h" #include "discard.h" #include "space-info.h" +#include "zoned.h" +#include "subpage.h" +#include "fs.h" +#include "accessors.h" +#include "extent-tree.h" +#include "root-tree.h" +#include "defrag.h" +#include "uuid-tree.h" +#include "relocation.h" +#include "scrub.h" +#include "super.h" +#include "delayed-inode.h" #define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\ BTRFS_HEADER_FLAG_RELOC |\ @@ -50,54 +59,9 @@ BTRFS_SUPER_FLAG_METADUMP |\ BTRFS_SUPER_FLAG_METADUMP_V2) -static const struct extent_io_ops btree_extent_io_ops; -static void end_workqueue_fn(struct btrfs_work *work); -static void btrfs_destroy_ordered_extents(struct btrfs_root *root); -static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, - struct btrfs_fs_info *fs_info); -static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root); -static int btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info, - struct extent_io_tree *dirty_pages, - int mark); -static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, - struct extent_io_tree *pinned_extents); static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info); static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info); -/* - * btrfs_end_io_wq structs are used to do processing in task context when an IO - * is complete. This is used during reads to verify checksums, and it is used - * by writes to insert metadata for new file extents after IO is complete. - */ -struct btrfs_end_io_wq { - struct bio *bio; - bio_end_io_t *end_io; - void *private; - struct btrfs_fs_info *info; - blk_status_t status; - enum btrfs_wq_endio_type metadata; - struct btrfs_work work; -}; - -static struct kmem_cache *btrfs_end_io_wq_cache; - -int __init btrfs_end_io_wq_init(void) -{ - btrfs_end_io_wq_cache = kmem_cache_create("btrfs_end_io_wq", - sizeof(struct btrfs_end_io_wq), - 0, - SLAB_MEM_SPREAD, - NULL); - if (!btrfs_end_io_wq_cache) - return -ENOMEM; - return 0; -} - -void __cold btrfs_end_io_wq_exit(void) -{ - kmem_cache_destroy(btrfs_end_io_wq_cache); -} - static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info) { if (fs_info->csum_shash) @@ -105,171 +69,42 @@ static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info) } /* - * async submit bios are used to offload expensive checksumming - * onto the worker threads. They checksum file and metadata bios - * just before they are sent down the IO stack. - */ -struct async_submit_bio { - void *private_data; - struct bio *bio; - extent_submit_bio_start_t *submit_bio_start; - int mirror_num; - /* - * bio_offset is optional, can be used if the pages in the bio - * can't tell us where in the file the bio should go - */ - u64 bio_offset; - struct btrfs_work work; - blk_status_t status; -}; - -/* - * Lockdep class keys for extent_buffer->lock's in this root. For a given - * eb, the lockdep key is determined by the btrfs_root it belongs to and - * the level the eb occupies in the tree. - * - * Different roots are used for different purposes and may nest inside each - * other and they require separate keysets. As lockdep keys should be - * static, assign keysets according to the purpose of the root as indicated - * by btrfs_root->root_key.objectid. This ensures that all special purpose - * roots have separate keysets. - * - * Lock-nesting across peer nodes is always done with the immediate parent - * node locked thus preventing deadlock. As lockdep doesn't know this, use - * subclass to avoid triggering lockdep warning in such cases. - * - * The key is set by the readpage_end_io_hook after the buffer has passed - * csum validation but before the pages are unlocked. It is also set by - * btrfs_init_new_buffer on freshly allocated blocks. - * - * We also add a check to make sure the highest level of the tree is the - * same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this code - * needs update as well. - */ -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# if BTRFS_MAX_LEVEL != 8 -# error -# endif - -static struct btrfs_lockdep_keyset { - u64 id; /* root objectid */ - const char *name_stem; /* lock name stem */ - char names[BTRFS_MAX_LEVEL + 1][20]; - struct lock_class_key keys[BTRFS_MAX_LEVEL + 1]; -} btrfs_lockdep_keysets[] = { - { .id = BTRFS_ROOT_TREE_OBJECTID, .name_stem = "root" }, - { .id = BTRFS_EXTENT_TREE_OBJECTID, .name_stem = "extent" }, - { .id = BTRFS_CHUNK_TREE_OBJECTID, .name_stem = "chunk" }, - { .id = BTRFS_DEV_TREE_OBJECTID, .name_stem = "dev" }, - { .id = BTRFS_FS_TREE_OBJECTID, .name_stem = "fs" }, - { .id = BTRFS_CSUM_TREE_OBJECTID, .name_stem = "csum" }, - { .id = BTRFS_QUOTA_TREE_OBJECTID, .name_stem = "quota" }, - { .id = BTRFS_TREE_LOG_OBJECTID, .name_stem = "log" }, - { .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" }, - { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" }, - { .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" }, - { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, .name_stem = "free-space" }, - { .id = 0, .name_stem = "tree" }, -}; - -void __init btrfs_init_lockdep(void) -{ - int i, j; - - /* initialize lockdep class names */ - for (i = 0; i < ARRAY_SIZE(btrfs_lockdep_keysets); i++) { - struct btrfs_lockdep_keyset *ks = &btrfs_lockdep_keysets[i]; - - for (j = 0; j < ARRAY_SIZE(ks->names); j++) - snprintf(ks->names[j], sizeof(ks->names[j]), - "btrfs-%s-%02d", ks->name_stem, j); - } -} - -void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, - int level) -{ - struct btrfs_lockdep_keyset *ks; - - BUG_ON(level >= ARRAY_SIZE(ks->keys)); - - /* find the matching keyset, id 0 is the default entry */ - for (ks = btrfs_lockdep_keysets; ks->id; ks++) - if (ks->id == objectid) - break; - - lockdep_set_class_and_name(&eb->lock, - &ks->keys[level], ks->names[level]); -} - -#endif - -/* - * extents on the btree inode are pretty simple, there's one extent - * that covers the entire device - */ -struct extent_map *btree_get_extent(struct btrfs_inode *inode, - struct page *page, size_t pg_offset, - u64 start, u64 len) -{ - struct extent_map_tree *em_tree = &inode->extent_tree; - struct extent_map *em; - int ret; - - read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, start, len); - if (em) { - read_unlock(&em_tree->lock); - goto out; - } - read_unlock(&em_tree->lock); - - em = alloc_extent_map(); - if (!em) { - em = ERR_PTR(-ENOMEM); - goto out; - } - em->start = 0; - em->len = (u64)-1; - em->block_len = (u64)-1; - em->block_start = 0; - - write_lock(&em_tree->lock); - ret = add_extent_mapping(em_tree, em, 0); - if (ret == -EEXIST) { - free_extent_map(em); - em = lookup_extent_mapping(em_tree, start, len); - if (!em) - em = ERR_PTR(-EIO); - } else if (ret) { - free_extent_map(em); - em = ERR_PTR(ret); - } - write_unlock(&em_tree->lock); - -out: - return em; -} - -/* * Compute the csum of a btree block and store the result to provided buffer. */ static void csum_tree_block(struct extent_buffer *buf, u8 *result) { struct btrfs_fs_info *fs_info = buf->fs_info; - const int num_pages = fs_info->nodesize >> PAGE_SHIFT; + int num_pages; + u32 first_page_part; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); char *kaddr; int i; shash->tfm = fs_info->csum_shash; crypto_shash_init(shash); - kaddr = page_address(buf->pages[0]); + + if (buf->addr) { + /* Pages are contiguous, handle them as a big one. */ + kaddr = buf->addr; + first_page_part = fs_info->nodesize; + num_pages = 1; + } else { + kaddr = folio_address(buf->folios[0]); + first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize); + num_pages = num_extent_pages(buf); + } + crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE, - PAGE_SIZE - BTRFS_CSUM_SIZE); + first_page_part - BTRFS_CSUM_SIZE); - for (i = 1; i < num_pages; i++) { - kaddr = page_address(buf->pages[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); @@ -282,54 +117,27 @@ static void csum_tree_block(struct extent_buffer *buf, u8 *result) * detect blocks that either didn't get written at all or got written * in the wrong place. */ -static int verify_parent_transid(struct extent_io_tree *io_tree, - struct extent_buffer *eb, u64 parent_transid, - int atomic) +int btrfs_buffer_uptodate(struct extent_buffer *eb, u64 parent_transid, bool atomic) { - struct extent_state *cached_state = NULL; - int ret; - bool need_lock = (current->journal_info == BTRFS_SEND_TRANS_STUB); + if (!extent_buffer_uptodate(eb)) + return 0; if (!parent_transid || btrfs_header_generation(eb) == parent_transid) - return 0; + return 1; if (atomic) return -EAGAIN; - if (need_lock) { - btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_read(eb); - } - - lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1, - &cached_state); - if (extent_buffer_uptodate(eb) && - btrfs_header_generation(eb) == parent_transid) { - ret = 0; - goto out; - } - btrfs_err_rl(eb->fs_info, - "parent transid verify failed on %llu wanted %llu found %llu", - eb->start, + if (!extent_buffer_uptodate(eb) || + btrfs_header_generation(eb) != parent_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, parent_transid, btrfs_header_generation(eb)); - ret = 1; - - /* - * Things reading via commit roots that don't have normal protection, - * like send, can have a really old block in cache that may point at a - * block that has been freed and re-allocated. So don't clear uptodate - * if we find an eb that is under IO (dirty/writeback) because we could - * end up reading in the stale data and then writing it back out and - * making everybody very sad. - */ - if (!extent_buffer_under_io(eb)) clear_extent_buffer_uptodate(eb); -out: - unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1, - &cached_state); - if (need_lock) - btrfs_tree_read_unlock_blocking(eb); - return ret; + return 0; + } + return 1; } static bool btrfs_supported_super_csum(u16 csum_type) @@ -349,11 +157,9 @@ static bool btrfs_supported_super_csum(u16 csum_type) * Return 0 if the superblock checksum type matches the checksum value of that * algorithm. Pass the raw disk superblock data. */ -static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, - char *raw_disk_sb) +int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, + const struct btrfs_super_block *disk_sb) { - struct btrfs_super_block *disk_sb = - (struct btrfs_super_block *)raw_disk_sb; char result[BTRFS_CSUM_SIZE]; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); @@ -364,70 +170,46 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, * 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, raw_disk_sb + BTRFS_CSUM_SIZE, + 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, btrfs_super_csum_size(disk_sb))) + if (memcmp(disk_sb->csum, result, fs_info->csum_size)) return 1; return 0; } -int btrfs_verify_level_key(struct extent_buffer *eb, int level, - struct btrfs_key *first_key, u64 parent_transid) +static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, + int mirror_num) { struct btrfs_fs_info *fs_info = eb->fs_info; - int found_level; - struct btrfs_key found_key; - int ret; + const u32 step = min(fs_info->nodesize, PAGE_SIZE); + const u32 nr_steps = eb->len / step; + phys_addr_t paddrs[BTRFS_MAX_BLOCKSIZE / PAGE_SIZE]; + int ret = 0; - found_level = btrfs_header_level(eb); - if (found_level != level) { - WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), - KERN_ERR "BTRFS: tree level check failed\n"); - btrfs_err(fs_info, -"tree level mismatch detected, bytenr=%llu level expected=%u has=%u", - eb->start, level, found_level); - return -EIO; - } + if (sb_rdonly(fs_info->sb)) + return -EROFS; - if (!first_key) - return 0; + for (int i = 0; i < num_extent_pages(eb); i++) { + struct folio *folio = eb->folios[i]; - /* - * For live tree block (new tree blocks in current transaction), - * we need proper lock context to avoid race, which is impossible here. - * So we only checks tree blocks which is read from disk, whose - * generation <= fs_info->last_trans_committed. - */ - if (btrfs_header_generation(eb) > fs_info->last_trans_committed) - return 0; + /* No large folio support yet. */ + ASSERT(folio_order(folio) == 0); + ASSERT(i < nr_steps); - /* We have @first_key, so this @eb must have at least one item */ - if (btrfs_header_nritems(eb) == 0) { - btrfs_err(fs_info, - "invalid tree nritems, bytenr=%llu nritems=0 expect >0", - eb->start); - WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); - return -EUCLEAN; + /* + * For nodesize < page size, there is just one paddr, with some + * offset inside the page. + * + * For nodesize >= page size, it's one or more paddrs, and eb->start + * must be aligned to page boundary. + */ + paddrs[i] = page_to_phys(&folio->page) + offset_in_page(eb->start); } - if (found_level) - btrfs_node_key_to_cpu(eb, &found_key, 0); - else - btrfs_item_key_to_cpu(eb, &found_key, 0); - ret = btrfs_comp_cpu_keys(first_key, &found_key); - - if (ret) { - WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), - KERN_ERR "BTRFS: tree first key check failed\n"); - 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, parent_transid, first_key->objectid, - first_key->type, first_key->offset, - found_key.objectid, found_key.type, - found_key.offset); - } + ret = btrfs_repair_io_failure(fs_info, 0, eb->start, eb->len, eb->start, + paddrs, step, mirror_num); return ret; } @@ -435,36 +217,25 @@ int btrfs_verify_level_key(struct extent_buffer *eb, int level, * helper to read a given tree block, doing retries as required when * the checksums don't match and we have alternate mirrors to try. * - * @parent_transid: expected transid, skip check if 0 - * @level: expected level, mandatory check - * @first_key: expected key of first slot, skip check if NULL + * @check: expected tree parentness check, see the comments of the + * structure for details. */ -static int btree_read_extent_buffer_pages(struct extent_buffer *eb, - u64 parent_transid, int level, - struct btrfs_key *first_key) +int btrfs_read_extent_buffer(struct extent_buffer *eb, + const struct btrfs_tree_parent_check *check) { struct btrfs_fs_info *fs_info = eb->fs_info; - struct extent_io_tree *io_tree; int failed = 0; int ret; int num_copies = 0; int mirror_num = 0; int failed_mirror = 0; - io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree; + ASSERT(check); + while (1) { - clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); - ret = read_extent_buffer_pages(eb, WAIT_COMPLETE, mirror_num); - if (!ret) { - if (verify_parent_transid(io_tree, eb, - parent_transid, 0)) - ret = -EIO; - else if (btrfs_verify_level_key(eb, level, - first_key, parent_transid)) - ret = -EUCLEAN; - else - break; - } + ret = read_extent_buffer_pages(eb, mirror_num, check); + if (!ret) + break; num_copies = btrfs_num_copies(fs_info, eb->start, eb->len); @@ -491,457 +262,254 @@ static int btree_read_extent_buffer_pages(struct extent_buffer *eb, } /* - * checksum a dirty tree block before IO. This has extra checks to make sure - * we only fill in the checksum field in the first page of a multi-page block + * Checksum a dirty tree block before IO. */ - -static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) +int btree_csum_one_bio(struct btrfs_bio *bbio) { - u64 start = page_offset(page); - u64 found_start; + 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]; - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); - struct extent_buffer *eb; int ret; - eb = (struct extent_buffer *)page->private; - if (page != eb->pages[0]) - return 0; + /* 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; - found_start = btrfs_header_bytenr(eb); /* - * Please do not consolidate these warnings into a single if. - * It is useful to know what went wrong. + * 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 (WARN_ON(found_start != start)) - return -EUCLEAN; - if (WARN_ON(!PageUptodate(page))) - return -EUCLEAN; + 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; ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid, offsetof(struct btrfs_header, fsid), BTRFS_FSID_SIZE) == 0); - csum_tree_block(eb, result); if (btrfs_header_level(eb)) ret = btrfs_check_node(eb); else - ret = btrfs_check_leaf_full(eb); + ret = btrfs_check_leaf(eb); - if (ret < 0) { - btrfs_print_tree(eb, 0); + 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 write time tree block corruption detected", - eb->start); - WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); - return ret; + "block=%llu bad generation, have %llu expect > %llu", + eb->start, btrfs_header_generation(eb), last_trans); + goto error; } - write_extent_buffer(eb, result, 0, csum_size); - + 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; } -static int check_tree_block_fsid(struct extent_buffer *eb) +static bool check_tree_block_fsid(struct extent_buffer *eb) { struct btrfs_fs_info *fs_info = eb->fs_info; - struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices, *seed_devs; u8 fsid[BTRFS_FSID_SIZE]; - int ret = 1; read_extent_buffer(eb, fsid, offsetof(struct btrfs_header, fsid), BTRFS_FSID_SIZE); - while (fs_devices) { - u8 *metadata_uuid; - /* - * Checking the incompat flag is only valid for the current - * fs. For seed devices it's forbidden to have their uuid - * changed so reading ->fsid in this case is fine - */ - if (fs_devices == fs_info->fs_devices && - btrfs_fs_incompat(fs_info, METADATA_UUID)) - metadata_uuid = fs_devices->metadata_uuid; - else - metadata_uuid = fs_devices->fsid; + /* + * 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) + return false; - if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE)) { - ret = 0; - break; - } - fs_devices = fs_devices->seed; - } - return ret; + list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list) + if (!memcmp(fsid, seed_devs->fsid, BTRFS_FSID_SIZE)) + return false; + + return true; } -static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, - u64 phy_offset, struct page *page, - u64 start, u64 end, int mirror) +/* Do basic extent buffer checks at read time */ +int btrfs_validate_extent_buffer(struct extent_buffer *eb, + const struct btrfs_tree_parent_check *check) { + struct btrfs_fs_info *fs_info = eb->fs_info; u64 found_start; - int found_level; - struct extent_buffer *eb; - struct btrfs_fs_info *fs_info; - u16 csum_size; - int ret = 0; + const u32 csum_size = fs_info->csum_size; + u8 found_level; u8 result[BTRFS_CSUM_SIZE]; - int reads_done; - - if (!page->private) - goto out; - - eb = (struct extent_buffer *)page->private; - fs_info = eb->fs_info; - csum_size = btrfs_super_csum_size(fs_info->super_copy); - - /* the pending IO might have been the only thing that kept this buffer - * in memory. Make sure we have a ref for all this other checks - */ - atomic_inc(&eb->refs); - - reads_done = atomic_dec_and_test(&eb->io_pages); - if (!reads_done) - goto err; + const u8 *header_csum; + int ret = 0; + const bool ignore_csum = btrfs_test_opt(fs_info, IGNOREMETACSUMS); - eb->read_mirror = mirror; - if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { - ret = -EIO; - goto err; - } + ASSERT(check); found_start = btrfs_header_bytenr(eb); - if (found_start != eb->start) { - btrfs_err_rl(fs_info, "bad tree block start, want %llu have %llu", - eb->start, found_start); + if (unlikely(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 err; + goto out; } - if (check_tree_block_fsid(eb)) { - btrfs_err_rl(fs_info, "bad fsid on block %llu", - eb->start); + if (unlikely(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 err; + goto out; } found_level = btrfs_header_level(eb); - if (found_level >= BTRFS_MAX_LEVEL) { - btrfs_err(fs_info, "bad tree block level %d on %llu", - (int)btrfs_header_level(eb), eb->start); + if (unlikely(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 err; + goto out; } - btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), - eb, found_level); - csum_tree_block(eb, result); + header_csum = folio_address(eb->folios[0]) + + get_eb_offset_in_folio(eb, offsetof(struct btrfs_header, csum)); - if (memcmp_extent_buffer(eb, result, 0, csum_size)) { - u32 val; - u32 found = 0; - - memcpy(&found, result, csum_size); - - read_extent_buffer(eb, &val, 0, csum_size); + if (memcmp(result, header_csum, csum_size) != 0) { btrfs_warn_rl(fs_info, - "%s checksum verify failed on %llu wanted %x found %x level %d", - fs_info->sb->s_id, eb->start, - val, found, btrfs_header_level(eb)); - ret = -EUCLEAN; - goto err; +"checksum verify failed on logical %llu mirror %u wanted " BTRFS_CSUM_FMT " found " BTRFS_CSUM_FMT " level %d%s", + eb->start, eb->read_mirror, + BTRFS_CSUM_FMT_VALUE(csum_size, header_csum), + BTRFS_CSUM_FMT_VALUE(csum_size, result), + btrfs_header_level(eb), + ignore_csum ? ", ignored" : ""); + if (unlikely(!ignore_csum)) { + ret = -EUCLEAN; + goto out; + } } - /* - * If this is a leaf block and it is corrupt, set the corrupt bit so - * that we don't try and read the other copies of this block, just - * return -EIO. - */ - if (found_level == 0 && btrfs_check_leaf_full(eb)) { - set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); + if (unlikely(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 (found_level > 0 && btrfs_check_node(eb)) + 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; - - if (!ret) - set_extent_buffer_uptodate(eb); - else - btrfs_err(fs_info, - "block=%llu read time tree block corruption detected", - eb->start); -err: - if (reads_done && - test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) - btree_readahead_hook(eb, ret); - - if (ret) { - /* - * our io error hook is going to dec the io pages - * again, we have to make sure it has something - * to decrement - */ - atomic_inc(&eb->io_pages); - clear_extent_buffer_uptodate(eb); + goto out; } - free_extent_buffer(eb); -out: - return ret; -} + if (check->has_first_key) { + const struct btrfs_key *expect_key = &check->first_key; + struct btrfs_key found_key; -static void end_workqueue_bio(struct bio *bio) -{ - struct btrfs_end_io_wq *end_io_wq = bio->bi_private; - struct btrfs_fs_info *fs_info; - struct btrfs_workqueue *wq; - - fs_info = end_io_wq->info; - end_io_wq->status = bio->bi_status; - - if (bio_op(bio) == REQ_OP_WRITE) { - if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) - wq = fs_info->endio_meta_write_workers; - else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) - wq = fs_info->endio_freespace_worker; - else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) - wq = fs_info->endio_raid56_workers; + if (found_level) + btrfs_node_key_to_cpu(eb, &found_key, 0); else - wq = fs_info->endio_write_workers; - } else { - if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) - wq = fs_info->endio_raid56_workers; - else if (end_io_wq->metadata) - wq = fs_info->endio_meta_workers; - else - wq = fs_info->endio_workers; - } - - btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL); - btrfs_queue_work(wq, &end_io_wq->work); -} - -blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, - enum btrfs_wq_endio_type metadata) -{ - struct btrfs_end_io_wq *end_io_wq; - - end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS); - if (!end_io_wq) - return BLK_STS_RESOURCE; - - end_io_wq->private = bio->bi_private; - end_io_wq->end_io = bio->bi_end_io; - end_io_wq->info = info; - end_io_wq->status = 0; - end_io_wq->bio = bio; - end_io_wq->metadata = metadata; - - bio->bi_private = end_io_wq; - bio->bi_end_io = end_workqueue_bio; - return 0; -} - -static void run_one_async_start(struct btrfs_work *work) -{ - struct async_submit_bio *async; - blk_status_t ret; - - async = container_of(work, struct async_submit_bio, work); - ret = async->submit_bio_start(async->private_data, async->bio, - async->bio_offset); - if (ret) - async->status = ret; -} - -/* - * In order to insert checksums into the metadata in large chunks, we wait - * until bio submission time. All the pages in the bio are checksummed and - * sums are attached onto the ordered extent record. - * - * At IO completion time the csums attached on the ordered extent record are - * inserted into the tree. - */ -static void run_one_async_done(struct btrfs_work *work) -{ - struct async_submit_bio *async; - struct inode *inode; - blk_status_t ret; - - async = container_of(work, struct async_submit_bio, work); - inode = async->private_data; - - /* If an error occurred we just want to clean up the bio and move on */ - if (async->status) { - async->bio->bi_status = async->status; - bio_endio(async->bio); - return; - } - - /* - * All of the bios that pass through here are from async helpers. - * Use REQ_CGROUP_PUNT to issue them from the owning cgroup's context. - * This changes nothing when cgroups aren't in use. - */ - async->bio->bi_opf |= REQ_CGROUP_PUNT; - ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num); - if (ret) { - async->bio->bi_status = ret; - bio_endio(async->bio); + 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; + } } -} - -static void run_one_async_free(struct btrfs_work *work) -{ - struct async_submit_bio *async; - - async = container_of(work, struct async_submit_bio, work); - kfree(async); -} - -blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset, void *private_data, - extent_submit_bio_start_t *submit_bio_start) -{ - struct async_submit_bio *async; - - async = kmalloc(sizeof(*async), GFP_NOFS); - if (!async) - return BLK_STS_RESOURCE; - - async->private_data = private_data; - async->bio = bio; - async->mirror_num = mirror_num; - async->submit_bio_start = submit_bio_start; - - btrfs_init_work(&async->work, run_one_async_start, run_one_async_done, - run_one_async_free); - - async->bio_offset = bio_offset; - - async->status = 0; - - if (op_is_sync(bio->bi_opf)) - btrfs_set_work_high_priority(&async->work); - - btrfs_queue_work(fs_info->workers, &async->work); - return 0; -} - -static blk_status_t btree_csum_one_bio(struct bio *bio) -{ - struct bio_vec *bvec; - struct btrfs_root *root; - int ret = 0; - struct bvec_iter_all iter_all; - - ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, iter_all) { - root = BTRFS_I(bvec->bv_page->mapping->host)->root; - ret = csum_dirty_buffer(root->fs_info, bvec->bv_page); - if (ret) - break; + if (check->owner_root) { + ret = btrfs_check_eb_owner(eb, check->owner_root); + if (ret < 0) + goto out; } - return errno_to_blk_status(ret); -} - -static blk_status_t btree_submit_bio_start(void *private_data, struct bio *bio, - u64 bio_offset) -{ - /* - * when we're called for a write, we're already in the async - * submission context. Just jump into btrfs_map_bio - */ - return btree_csum_one_bio(bio); -} - -static int check_async_write(struct btrfs_fs_info *fs_info, - struct btrfs_inode *bi) -{ - if (atomic_read(&bi->sync_writers)) - return 0; - if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags)) - return 0; - return 1; -} - -static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio, - int mirror_num, - unsigned long bio_flags) -{ - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - int async = check_async_write(fs_info, BTRFS_I(inode)); - blk_status_t ret; + /* If this is a leaf block and it is corrupt, just return -EIO. */ + if (found_level == 0 && btrfs_check_leaf(eb)) + ret = -EIO; - if (bio_op(bio) != REQ_OP_WRITE) { - /* - * called for a read, do the setup so that checksum validation - * can happen in the async kernel threads - */ - ret = btrfs_bio_wq_end_io(fs_info, bio, - BTRFS_WQ_ENDIO_METADATA); - if (ret) - goto out_w_error; - ret = btrfs_map_bio(fs_info, bio, mirror_num); - } else if (!async) { - ret = btree_csum_one_bio(bio); - if (ret) - goto out_w_error; - ret = btrfs_map_bio(fs_info, bio, mirror_num); - } else { - /* - * kthread helpers are used to submit writes so that - * checksumming can happen in parallel across all CPUs - */ - ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0, - 0, inode, btree_submit_bio_start); - } + if (found_level > 0 && btrfs_check_node(eb)) + ret = -EIO; if (ret) - goto out_w_error; - return 0; - -out_w_error: - bio->bi_status = ret; - bio_endio(bio); + 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 -static int btree_migratepage(struct address_space *mapping, - struct page *newpage, struct page *page, - enum migrate_mode mode) +static int 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 (PageDirty(page)) + 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 (page_has_private(page) && - !try_to_release_page(page, GFP_KERNEL)) + if (folio_get_private(src) && + !filemap_release_folio(src, GFP_KERNEL)) return -EAGAIN; - return migrate_page(mapping, newpage, page, mode); + return migrate_folio(mapping, dst, src, mode); } +#else +#define btree_migrate_folio NULL #endif - static int btree_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct btrfs_fs_info *fs_info; int ret; if (wbc->sync_mode == WB_SYNC_NONE) { + struct btrfs_fs_info *fs_info; if (wbc->for_kupdate) return 0; - fs_info = BTRFS_I(mapping->host)->root->fs_info; + 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, @@ -952,106 +520,121 @@ static int btree_writepages(struct address_space *mapping, return btree_write_cache_pages(mapping, wbc); } -static int btree_readpage(struct file *file, struct page *page) -{ - return extent_read_full_page(page, btree_get_extent, 0); -} - -static int btree_releasepage(struct page *page, gfp_t gfp_flags) +static bool btree_release_folio(struct folio *folio, gfp_t gfp_flags) { - if (PageWriteback(page) || PageDirty(page)) - return 0; + if (folio_test_writeback(folio) || folio_test_dirty(folio)) + return false; - return try_release_extent_buffer(page); + return try_release_extent_buffer(folio); } -static void btree_invalidatepage(struct page *page, unsigned int offset, - unsigned int length) +static void btree_invalidate_folio(struct folio *folio, size_t offset, + size_t length) { struct extent_io_tree *tree; - tree = &BTRFS_I(page->mapping->host)->io_tree; - extent_invalidatepage(tree, page, offset); - btree_releasepage(page, GFP_NOFS); - if (PagePrivate(page)) { - btrfs_warn(BTRFS_I(page->mapping->host)->root->fs_info, - "page private not zero on page %llu", - (unsigned long long)page_offset(page)); - detach_page_private(page); + + 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", + (unsigned long long)folio_pos(folio)); + folio_detach_private(folio); } } -static int btree_set_page_dirty(struct page *page) -{ #ifdef DEBUG +static bool btree_dirty_folio(struct address_space *mapping, + struct folio *folio) +{ + struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); + struct btrfs_subpage_info *spi = fs_info->subpage_info; + struct btrfs_subpage *subpage; struct extent_buffer *eb; + int cur_bit = 0; + u64 page_start = folio_pos(folio); + + if (fs_info->sectorsize == PAGE_SIZE) { + eb = folio_get_private(folio); + BUG_ON(!eb); + BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); + BUG_ON(!atomic_read(&eb->refs)); + btrfs_assert_tree_write_locked(eb); + return filemap_dirty_folio(mapping, folio); + } + + ASSERT(spi); + subpage = folio_get_private(folio); + + for (cur_bit = spi->dirty_offset; + cur_bit < spi->dirty_offset + spi->bitmap_nr_bits; + cur_bit++) { + unsigned long flags; + u64 cur; + + spin_lock_irqsave(&subpage->lock, flags); + if (!test_bit(cur_bit, subpage->bitmaps)) { + spin_unlock_irqrestore(&subpage->lock, flags); + continue; + } + spin_unlock_irqrestore(&subpage->lock, flags); + cur = page_start + cur_bit * fs_info->sectorsize; - BUG_ON(!PagePrivate(page)); - eb = (struct extent_buffer *)page->private; - BUG_ON(!eb); - BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); - BUG_ON(!atomic_read(&eb->refs)); - btrfs_assert_tree_locked(eb); -#endif - return __set_page_dirty_nobuffers(page); + eb = find_extent_buffer(fs_info, cur); + ASSERT(eb); + ASSERT(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); + ASSERT(atomic_read(&eb->refs)); + btrfs_assert_tree_write_locked(eb); + free_extent_buffer(eb); + + cur_bit += (fs_info->nodesize >> fs_info->sectorsize_bits) - 1; + } + return filemap_dirty_folio(mapping, folio); } +#else +#define btree_dirty_folio filemap_dirty_folio +#endif static const struct address_space_operations btree_aops = { - .readpage = btree_readpage, .writepages = btree_writepages, - .releasepage = btree_releasepage, - .invalidatepage = btree_invalidatepage, -#ifdef CONFIG_MIGRATION - .migratepage = btree_migratepage, -#endif - .set_page_dirty = btree_set_page_dirty, + .release_folio = btree_release_folio, + .invalidate_folio = btree_invalidate_folio, + .migrate_folio = btree_migrate_folio, + .dirty_folio = btree_dirty_folio, }; -void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr) -{ - struct extent_buffer *buf = NULL; - int ret; - - buf = btrfs_find_create_tree_block(fs_info, bytenr); - if (IS_ERR(buf)) - return; - - ret = read_extent_buffer_pages(buf, WAIT_NONE, 0); - if (ret < 0) - free_extent_buffer_stale(buf); - else - free_extent_buffer(buf); -} - struct extent_buffer *btrfs_find_create_tree_block( struct btrfs_fs_info *fs_info, - u64 bytenr) + u64 bytenr, u64 owner_root, + int level) { if (btrfs_is_testing(fs_info)) return alloc_test_extent_buffer(fs_info, bytenr); - return alloc_extent_buffer(fs_info, bytenr); + return alloc_extent_buffer(fs_info, bytenr, owner_root, level); } /* * Read tree block at logical address @bytenr and do variant basic but critical * verification. * - * @parent_transid: expected transid of this tree block, skip check if 0 - * @level: expected level, mandatory check - * @first_key: expected key in slot 0, skip check if NULL + * @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, - u64 parent_transid, int level, - struct btrfs_key *first_key) + struct btrfs_tree_parent_check *check) { struct extent_buffer *buf = NULL; int ret; - buf = btrfs_find_create_tree_block(fs_info, bytenr); + ASSERT(check); + + buf = btrfs_find_create_tree_block(fs_info, bytenr, check->owner_root, + check->level); if (IS_ERR(buf)) return buf; - ret = btree_read_extent_buffer_pages(buf, parent_transid, - level, first_key); + ret = btrfs_read_extent_buffer(buf, check); if (ret) { free_extent_buffer_stale(buf); return ERR_PTR(ret); @@ -1060,41 +643,23 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, } -void btrfs_clean_tree_block(struct extent_buffer *buf) +static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info, + u64 objectid, gfp_t flags) { - struct btrfs_fs_info *fs_info = buf->fs_info; - if (btrfs_header_generation(buf) == - fs_info->running_transaction->transid) { - btrfs_assert_tree_locked(buf); - - if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) { - percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, - -buf->len, - fs_info->dirty_metadata_batch); - /* ugh, clear_extent_buffer_dirty needs to lock the page */ - btrfs_set_lock_blocking_write(buf); - clear_extent_buffer_dirty(buf); - } - } -} + struct btrfs_root *root; + + root = kzalloc(sizeof(*root), flags); + if (!root) + return NULL; -static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, - u64 objectid) -{ - bool dummy = test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state); root->fs_info = fs_info; - root->node = NULL; - root->commit_root = NULL; - root->state = 0; - root->orphan_cleanup_state = 0; - - root->last_trans = 0; - root->highest_objectid = 0; - root->nr_delalloc_inodes = 0; - root->nr_ordered_extents = 0; - root->inode_tree = RB_ROOT; - INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC); - root->block_rsv = NULL; + root->root_key.objectid = objectid; + RB_CLEAR_NODE(&root->rb_node); + + xa_init(&root->inodes); + xa_init(&root->delayed_nodes); + + btrfs_init_root_block_rsv(root); INIT_LIST_HEAD(&root->dirty_list); INIT_LIST_HEAD(&root->root_list); @@ -1103,19 +668,15 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, INIT_LIST_HEAD(&root->ordered_extents); INIT_LIST_HEAD(&root->ordered_root); INIT_LIST_HEAD(&root->reloc_dirty_list); - INIT_LIST_HEAD(&root->logged_list[0]); - INIT_LIST_HEAD(&root->logged_list[1]); - spin_lock_init(&root->inode_lock); spin_lock_init(&root->delalloc_lock); spin_lock_init(&root->ordered_extent_lock); spin_lock_init(&root->accounting_lock); - spin_lock_init(&root->log_extents_lock[0]); - spin_lock_init(&root->log_extents_lock[1]); spin_lock_init(&root->qgroup_meta_rsv_lock); mutex_init(&root->objectid_mutex); mutex_init(&root->log_mutex); mutex_init(&root->ordered_extent_mutex); mutex_init(&root->delalloc_mutex); + init_waitqueue_head(&root->qgroup_flush_wait); init_waitqueue_head(&root->log_writer_wait); init_waitqueue_head(&root->log_commit_wait[0]); init_waitqueue_head(&root->log_commit_wait[1]); @@ -1128,25 +689,13 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, refcount_set(&root->refs, 1); atomic_set(&root->snapshot_force_cow, 0); atomic_set(&root->nr_swapfiles, 0); - root->log_transid = 0; root->log_transid_committed = -1; - root->last_log_commit = 0; - if (!dummy) { - extent_io_tree_init(fs_info, &root->dirty_log_pages, - IO_TREE_ROOT_DIRTY_LOG_PAGES, NULL); - extent_io_tree_init(fs_info, &root->log_csum_range, - IO_TREE_LOG_CSUM_RANGE, NULL); - } - - memset(&root->root_key, 0, sizeof(root->root_key)); - memset(&root->root_item, 0, sizeof(root->root_item)); - memset(&root->defrag_progress, 0, sizeof(root->defrag_progress)); - if (!dummy) - root->defrag_trans_start = fs_info->generation; - else - root->defrag_trans_start = 0; - root->root_key.objectid = objectid; - root->anon_dev = 0; + if (!btrfs_is_testing(fs_info)) { + btrfs_extent_io_tree_init(fs_info, &root->dirty_log_pages, + IO_TREE_ROOT_DIRTY_LOG_PAGES); + btrfs_extent_io_tree_init(fs_info, &root->log_csum_range, + IO_TREE_LOG_CSUM_RANGE); + } spin_lock_init(&root->root_item_lock); btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks); @@ -1156,14 +705,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, list_add_tail(&root->leak_list, &fs_info->allocated_roots); spin_unlock(&fs_info->fs_roots_radix_lock); #endif -} -static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info, - u64 objectid, gfp_t flags) -{ - struct btrfs_root *root = kzalloc(sizeof(*root), flags); - if (root) - __setup_root(root, fs_info, objectid); return root; } @@ -1187,6 +729,107 @@ struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info) } #endif +static int global_root_cmp(struct rb_node *a_node, const struct rb_node *b_node) +{ + const struct btrfs_root *a = rb_entry(a_node, struct btrfs_root, rb_node); + const struct btrfs_root *b = rb_entry(b_node, struct btrfs_root, rb_node); + + return btrfs_comp_cpu_keys(&a->root_key, &b->root_key); +} + +static int global_root_key_cmp(const void *k, const struct rb_node *node) +{ + const struct btrfs_key *key = k; + const struct btrfs_root *root = rb_entry(node, struct btrfs_root, rb_node); + + return btrfs_comp_cpu_keys(key, &root->root_key); +} + +int btrfs_global_root_insert(struct btrfs_root *root) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct rb_node *tmp; + int ret = 0; + + write_lock(&fs_info->global_root_lock); + tmp = rb_find_add(&root->rb_node, &fs_info->global_root_tree, global_root_cmp); + write_unlock(&fs_info->global_root_lock); + + if (tmp) { + ret = -EEXIST; + btrfs_warn(fs_info, "global root %llu %llu already exists", + btrfs_root_id(root), root->root_key.offset); + } + return ret; +} + +void btrfs_global_root_delete(struct btrfs_root *root) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + + write_lock(&fs_info->global_root_lock); + rb_erase(&root->rb_node, &fs_info->global_root_tree); + write_unlock(&fs_info->global_root_lock); +} + +struct btrfs_root *btrfs_global_root(struct btrfs_fs_info *fs_info, + struct btrfs_key *key) +{ + struct rb_node *node; + struct btrfs_root *root = NULL; + + read_lock(&fs_info->global_root_lock); + node = rb_find(key, &fs_info->global_root_tree, global_root_key_cmp); + if (node) + root = container_of(node, struct btrfs_root, rb_node); + read_unlock(&fs_info->global_root_lock); + + return root; +} + +static u64 btrfs_global_root_id(struct btrfs_fs_info *fs_info, u64 bytenr) +{ + struct btrfs_block_group *block_group; + u64 ret; + + if (!btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) + return 0; + + if (bytenr) + block_group = btrfs_lookup_block_group(fs_info, bytenr); + else + block_group = btrfs_lookup_first_block_group(fs_info, bytenr); + ASSERT(block_group); + if (!block_group) + return 0; + ret = block_group->global_root_id; + btrfs_put_block_group(block_group); + + return ret; +} + +struct btrfs_root *btrfs_csum_root(struct btrfs_fs_info *fs_info, u64 bytenr) +{ + struct btrfs_key key = { + .objectid = BTRFS_CSUM_TREE_OBJECTID, + .type = BTRFS_ROOT_ITEM_KEY, + .offset = btrfs_global_root_id(fs_info, bytenr), + }; + + return btrfs_global_root(fs_info, &key); +} + +struct btrfs_root *btrfs_extent_root(struct btrfs_fs_info *fs_info, u64 bytenr) +{ + struct btrfs_key key = { + .objectid = BTRFS_EXTENT_TREE_OBJECTID, + .type = BTRFS_ROOT_ITEM_KEY, + .offset = btrfs_global_root_id(fs_info, bytenr), + }; + + return btrfs_global_root(fs_info, &key); +} + struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, u64 objectid) { @@ -1212,7 +855,8 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, root->root_key.type = BTRFS_ROOT_ITEM_KEY; root->root_key.offset = 0; - leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0); + leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0, + 0, BTRFS_NESTING_NORMAL); if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); leaf = NULL; @@ -1220,13 +864,13 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, } root->node = leaf; - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); root->commit_root = btrfs_root_node(root); set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - root->root_item.flags = 0; - root->root_item.byte_limit = 0; + btrfs_set_root_flags(&root->root_item, 0); + btrfs_set_root_limit(&root->root_item, 0); btrfs_set_root_bytenr(&root->root_item, leaf->start); btrfs_set_root_generation(&root->root_item, trans->transid); btrfs_set_root_level(&root->root_item, 0); @@ -1234,11 +878,13 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, btrfs_set_root_used(&root->root_item, leaf->len); btrfs_set_root_last_snapshot(&root->root_item, 0); btrfs_set_root_dirid(&root->root_item, 0); - if (is_fstree(objectid)) + if (btrfs_is_fstree(objectid)) generate_random_guid(root->root_item.uuid); else export_guid(root->root_item.uuid, &guid_null); - root->root_item.drop_level = 0; + btrfs_set_root_drop_level(&root->root_item, 0); + + btrfs_tree_unlock(leaf); key.objectid = objectid; key.type = BTRFS_ROOT_ITEM_KEY; @@ -1247,23 +893,17 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, if (ret) goto fail; - btrfs_tree_unlock(leaf); - return root; fail: - if (leaf) - btrfs_tree_unlock(leaf); btrfs_put_root(root); return ERR_PTR(ret); } -static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) +static struct btrfs_root *alloc_log_tree(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; - struct extent_buffer *leaf; root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, GFP_NOFS); if (!root) @@ -1273,6 +913,14 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, root->root_key.type = BTRFS_ROOT_ITEM_KEY; root->root_key.offset = BTRFS_TREE_LOG_OBJECTID; + return root; +} + +int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_root *root) +{ + struct extent_buffer *leaf; + /* * DON'T set SHAREABLE bit for log trees. * @@ -1284,17 +932,16 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, */ leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID, - NULL, 0, 0, 0); - if (IS_ERR(leaf)) { - btrfs_put_root(root); - return ERR_CAST(leaf); - } + NULL, 0, 0, 0, 0, BTRFS_NESTING_NORMAL); + if (IS_ERR(leaf)) + return PTR_ERR(leaf); root->node = leaf; - btrfs_mark_buffer_dirty(root->node); + btrfs_mark_buffer_dirty(trans, root->node); btrfs_tree_unlock(root->node); - return root; + + return 0; } int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, @@ -1302,9 +949,19 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, { struct btrfs_root *log_root; - log_root = alloc_log_tree(trans, fs_info); + log_root = alloc_log_tree(fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); + + if (!btrfs_is_zoned(fs_info)) { + int ret = btrfs_alloc_log_tree_node(trans, log_root); + + if (ret) { + btrfs_put_root(log_root); + return ret; + } + } + WARN_ON(fs_info->log_root_tree); fs_info->log_root_tree = log_root; return 0; @@ -1316,13 +973,20 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log_root; struct btrfs_inode_item *inode_item; + int ret; - log_root = alloc_log_tree(trans, fs_info); + log_root = alloc_log_tree(fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); - log_root->last_trans = trans->transid; - log_root->root_key.offset = root->root_key.objectid; + ret = btrfs_alloc_log_tree_node(trans, log_root); + if (ret) { + btrfs_put_root(log_root); + return ret; + } + + btrfs_set_root_last_trans(log_root, trans->transid); + log_root->root_key.offset = btrfs_root_id(root); inode_item = &log_root->root_item.inode; btrfs_set_stack_inode_generation(inode_item, 1); @@ -1336,118 +1000,136 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans, WARN_ON(root->log_root); root->log_root = log_root; - root->log_transid = 0; + btrfs_set_root_log_transid(root, 0); root->log_transid_committed = -1; - root->last_log_commit = 0; + btrfs_set_root_last_log_commit(root, 0); return 0; } -struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, - struct btrfs_key *key) +static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root, + struct btrfs_path *path, + const struct btrfs_key *key) { struct btrfs_root *root; + struct btrfs_tree_parent_check check = { 0 }; struct btrfs_fs_info *fs_info = tree_root->fs_info; - struct btrfs_path *path; u64 generation; int ret; int level; - path = btrfs_alloc_path(); - if (!path) - return ERR_PTR(-ENOMEM); - root = btrfs_alloc_root(fs_info, key->objectid, GFP_NOFS); - if (!root) { - ret = -ENOMEM; - goto alloc_fail; - } + if (!root) + return ERR_PTR(-ENOMEM); ret = btrfs_find_root(tree_root, key, path, &root->root_item, &root->root_key); if (ret) { if (ret > 0) ret = -ENOENT; - goto find_fail; + goto fail; } generation = btrfs_root_generation(&root->root_item); level = btrfs_root_level(&root->root_item); - root->node = read_tree_block(fs_info, - btrfs_root_bytenr(&root->root_item), - generation, level, NULL); + check.level = level; + check.transid = generation; + check.owner_root = key->objectid; + root->node = read_tree_block(fs_info, btrfs_root_bytenr(&root->root_item), + &check); if (IS_ERR(root->node)) { ret = PTR_ERR(root->node); root->node = NULL; - goto find_fail; - } else if (!btrfs_buffer_uptodate(root->node, generation, 0)) { + goto fail; + } + if (unlikely(!btrfs_buffer_uptodate(root->node, generation, false))) { ret = -EIO; - goto find_fail; + goto fail; + } + + /* + * For real fs, and not log/reloc trees, root owner must + * match its root node owner + */ + if (unlikely(!btrfs_is_testing(fs_info) && + btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID && + btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID && + btrfs_root_id(root) != btrfs_header_owner(root->node))) { + btrfs_crit(fs_info, +"root=%llu block=%llu, tree root owner mismatch, have %llu expect %llu", + btrfs_root_id(root), root->node->start, + btrfs_header_owner(root->node), + btrfs_root_id(root)); + ret = -EUCLEAN; + goto fail; } root->commit_root = btrfs_root_node(root); -out: - btrfs_free_path(path); return root; - -find_fail: +fail: btrfs_put_root(root); -alloc_fail: - root = ERR_PTR(ret); - goto out; + return ERR_PTR(ret); } -static int btrfs_init_fs_root(struct btrfs_root *root) +struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, + const struct btrfs_key *key) { - int ret; - unsigned int nofs_flag; + struct btrfs_root *root; + BTRFS_PATH_AUTO_FREE(path); - root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS); - root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned), - GFP_NOFS); - if (!root->free_ino_pinned || !root->free_ino_ctl) { - ret = -ENOMEM; - goto fail; - } + path = btrfs_alloc_path(); + if (!path) + return ERR_PTR(-ENOMEM); + root = read_tree_root_path(tree_root, path, key); - /* - * We might be called under a transaction (e.g. indirect backref - * resolution) which could deadlock if it triggers memory reclaim - */ - nofs_flag = memalloc_nofs_save(); - ret = btrfs_drew_lock_init(&root->snapshot_lock); - memalloc_nofs_restore(nofs_flag); - if (ret) - goto fail; + return root; +} + +/* + * 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() + */ +static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) +{ + int ret; - if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID && - root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) { + btrfs_drew_lock_init(&root->snapshot_lock); + + if (btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID && + !btrfs_is_data_reloc_root(root) && + btrfs_is_fstree(btrfs_root_id(root))) { set_bit(BTRFS_ROOT_SHAREABLE, &root->state); btrfs_check_and_init_root_item(&root->root_item); } - btrfs_init_free_ino_ctl(root); - spin_lock_init(&root->ino_cache_lock); - init_waitqueue_head(&root->ino_cache_wait); - - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; + /* + * 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_find_highest_objectid(root, - &root->highest_objectid); + ret = btrfs_init_root_free_objectid(root); if (ret) { mutex_unlock(&root->objectid_mutex); - goto fail; + return ret; } - ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + ASSERT(root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); mutex_unlock(&root->objectid_mutex); return 0; -fail: - /* The caller is responsible to call btrfs_free_fs_root */ - return ret; } static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, @@ -1458,12 +1140,46 @@ static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, spin_lock(&fs_info->fs_roots_radix_lock); root = radix_tree_lookup(&fs_info->fs_roots_radix, (unsigned long)root_id); - if (root) - root = btrfs_grab_root(root); + root = btrfs_grab_root(root); spin_unlock(&fs_info->fs_roots_radix_lock); return root; } +static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info, + u64 objectid) +{ + struct btrfs_key key = { + .objectid = objectid, + .type = BTRFS_ROOT_ITEM_KEY, + .offset = 0, + }; + + switch (objectid) { + case BTRFS_ROOT_TREE_OBJECTID: + return btrfs_grab_root(fs_info->tree_root); + case BTRFS_EXTENT_TREE_OBJECTID: + return btrfs_grab_root(btrfs_global_root(fs_info, &key)); + case BTRFS_CHUNK_TREE_OBJECTID: + return btrfs_grab_root(fs_info->chunk_root); + case BTRFS_DEV_TREE_OBJECTID: + return btrfs_grab_root(fs_info->dev_root); + case BTRFS_CSUM_TREE_OBJECTID: + return btrfs_grab_root(btrfs_global_root(fs_info, &key)); + case BTRFS_QUOTA_TREE_OBJECTID: + return btrfs_grab_root(fs_info->quota_root); + case BTRFS_UUID_TREE_OBJECTID: + return btrfs_grab_root(fs_info->uuid_root); + case BTRFS_BLOCK_GROUP_TREE_OBJECTID: + return btrfs_grab_root(fs_info->block_group_root); + case BTRFS_FREE_SPACE_TREE_OBJECTID: + return btrfs_grab_root(btrfs_global_root(fs_info, &key)); + case BTRFS_RAID_STRIPE_TREE_OBJECTID: + return btrfs_grab_root(fs_info->stripe_root); + default: + return NULL; + } +} + int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) { @@ -1475,7 +1191,7 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, spin_lock(&fs_info->fs_roots_radix_lock); ret = radix_tree_insert(&fs_info->fs_roots_radix, - (unsigned long)root->root_key.objectid, + (unsigned long)btrfs_root_id(root), root); if (ret == 0) { btrfs_grab_root(root); @@ -1487,17 +1203,20 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, return ret; } -void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info) +void btrfs_check_leaked_roots(const struct btrfs_fs_info *fs_info) { #ifdef CONFIG_BTRFS_DEBUG struct btrfs_root *root; while (!list_empty(&fs_info->allocated_roots)) { + char buf[BTRFS_ROOT_NAME_BUF_LEN]; + root = list_first_entry(&fs_info->allocated_roots, struct btrfs_root, leak_list); - btrfs_err(fs_info, "leaked root %llu-%llu refcount %d", - root->root_key.objectid, root->root_key.offset, + btrfs_err(fs_info, "leaked root %s refcount %d", + btrfs_root_name(&root->root_key, buf), refcount_read(&root->refs)); + WARN_ON_ONCE(1); while (refcount_read(&root->refs) > 1) btrfs_put_root(root); btrfs_put_root(root); @@ -1505,27 +1224,48 @@ void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info) #endif } +static void free_global_roots(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *root; + struct rb_node *node; + + while ((node = rb_first_postorder(&fs_info->global_root_tree)) != NULL) { + root = rb_entry(node, struct btrfs_root, rb_node); + rb_erase(&root->rb_node, &fs_info->global_root_tree); + btrfs_put_root(root); + } +} + void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) { + struct percpu_counter *em_counter = &fs_info->evictable_extent_maps; + + if (fs_info->fs_devices) + btrfs_close_devices(fs_info->fs_devices); + btrfs_free_compress_wsm(fs_info); + percpu_counter_destroy(&fs_info->stats_read_blocks); percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); - percpu_counter_destroy(&fs_info->dio_bytes); + percpu_counter_destroy(&fs_info->ordered_bytes); + if (percpu_counter_initialized(em_counter)) + ASSERT(percpu_counter_sum_positive(em_counter) == 0); + percpu_counter_destroy(em_counter); percpu_counter_destroy(&fs_info->dev_replace.bio_counter); btrfs_free_csum_hash(fs_info); btrfs_free_stripe_hash_table(fs_info); btrfs_free_ref_cache(fs_info); kfree(fs_info->balance_ctl); kfree(fs_info->delayed_root); - btrfs_put_root(fs_info->extent_root); + free_global_roots(fs_info); btrfs_put_root(fs_info->tree_root); btrfs_put_root(fs_info->chunk_root); btrfs_put_root(fs_info->dev_root); - btrfs_put_root(fs_info->csum_root); btrfs_put_root(fs_info->quota_root); btrfs_put_root(fs_info->uuid_root); - btrfs_put_root(fs_info->free_space_root); btrfs_put_root(fs_info->fs_root); btrfs_put_root(fs_info->data_reloc_root); + btrfs_put_root(fs_info->block_group_root); + btrfs_put_root(fs_info->stripe_root); btrfs_check_leaked_roots(fs_info); btrfs_extent_buffer_leak_debug_check(fs_info); kfree(fs_info->super_copy); @@ -1534,36 +1274,60 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) } -struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, bool check_ref) +/* + * 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 + */ +static struct 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; - if (objectid == BTRFS_ROOT_TREE_OBJECTID) - return btrfs_grab_root(fs_info->tree_root); - if (objectid == BTRFS_EXTENT_TREE_OBJECTID) - return btrfs_grab_root(fs_info->extent_root); - if (objectid == BTRFS_CHUNK_TREE_OBJECTID) - return btrfs_grab_root(fs_info->chunk_root); - if (objectid == BTRFS_DEV_TREE_OBJECTID) - return btrfs_grab_root(fs_info->dev_root); - if (objectid == BTRFS_CSUM_TREE_OBJECTID) - return btrfs_grab_root(fs_info->csum_root); - if (objectid == BTRFS_QUOTA_TREE_OBJECTID) - return btrfs_grab_root(fs_info->quota_root) ? - fs_info->quota_root : ERR_PTR(-ENOENT); - if (objectid == BTRFS_UUID_TREE_OBJECTID) - return btrfs_grab_root(fs_info->uuid_root) ? - fs_info->uuid_root : ERR_PTR(-ENOENT); - if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) - return btrfs_grab_root(fs_info->free_space_root) ? - fs_info->free_space_root : ERR_PTR(-ENOENT); + 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; + } + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); @@ -1583,7 +1347,7 @@ again: goto fail; } - ret = btrfs_init_fs_root(root); + ret = btrfs_init_fs_root(root, anon_dev ? *anon_dev : 0); if (ret) goto fail; @@ -1605,61 +1369,103 @@ again: ret = btrfs_insert_fs_root(fs_info, root); if (ret) { - btrfs_put_root(root); - if (ret == -EEXIST) + 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); } -static int btrfs_congested_fn(void *congested_data, int bdi_bits) +/* + * 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) { - struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; - int ret = 0; - struct btrfs_device *device; - struct backing_dev_info *bdi; + return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref); +} - rcu_read_lock(); - list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) { - if (!device->bdev) - continue; - bdi = device->bdev->bd_bdi; - if (bdi_congested(bdi, bdi_bits)) { - ret = 1; - break; - } - } - rcu_read_unlock(); - return ret; +/* + * 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); } /* - * called by the kthread helper functions to finally call the bio end_io - * functions. This is where read checksum verification actually happens + * 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. */ -static void end_workqueue_fn(struct btrfs_work *work) +struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, + u64 objectid) { - struct bio *bio; - struct btrfs_end_io_wq *end_io_wq; + struct btrfs_root *root; + struct btrfs_key key; + + ASSERT(path->search_commit_root && path->skip_locking); + + /* + * 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; - end_io_wq = container_of(work, struct btrfs_end_io_wq, work); - bio = end_io_wq->bio; + root = btrfs_lookup_fs_root(fs_info, objectid); + if (root) + return root; - bio->bi_status = end_io_wq->status; - bio->bi_private = end_io_wq->private; - bio->bi_end_io = end_io_wq->end_io; - bio_endio(bio); - kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); + key.objectid = objectid; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + root = read_tree_root_path(fs_info->tree_root, path, &key); + btrfs_release_path(path); + + return root; } static int cleaner_kthread(void *arg) { - struct btrfs_root *root = arg; - struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_fs_info *fs_info = arg; int again; while (1) { @@ -1690,9 +1496,12 @@ static int cleaner_kthread(void *arg) 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(root); + again = btrfs_clean_one_deleted_snapshot(fs_info); mutex_unlock(&fs_info->cleaner_mutex); /* @@ -1702,16 +1511,23 @@ static int cleaner_kthread(void *arg) btrfs_run_defrag_inodes(fs_info); /* - * Acquires fs_info->delete_unused_bgs_mutex to avoid racing + * 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->delete_unused_bgs_mutex. So we + * 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_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); + clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); if (kthread_should_park()) kthread_parkme(); if (kthread_should_stop()) @@ -1731,13 +1547,13 @@ static int transaction_kthread(void *arg) struct btrfs_trans_handle *trans; struct btrfs_transaction *cur; u64 transid; - time64_t now; + time64_t delta; unsigned long delay; bool cannot_commit; do { cannot_commit = false; - delay = HZ * fs_info->commit_interval; + delay = secs_to_jiffies(fs_info->commit_interval); mutex_lock(&fs_info->transaction_kthread_mutex); spin_lock(&fs_info->trans_lock); @@ -1747,13 +1563,14 @@ static int transaction_kthread(void *arg) goto sleep; } - now = ktime_get_seconds(); - if (cur->state < TRANS_STATE_COMMIT_START && - !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) && - (now < cur->start_time || - now - cur->start_time < fs_info->commit_interval)) { + delta = ktime_get_seconds() - cur->start_time; + if (!test_and_clear_bit(BTRFS_FS_COMMIT_TRANS, &fs_info->flags) && + cur->state < TRANS_STATE_COMMIT_PREP && + delta < fs_info->commit_interval) { spin_unlock(&fs_info->trans_lock); - delay = HZ * 5; + delay -= secs_to_jiffies(delta - 1); + delay = min(delay, + secs_to_jiffies(fs_info->commit_interval)); goto sleep; } transid = cur->transid; @@ -1775,8 +1592,7 @@ sleep: wake_up_process(fs_info->cleaner_kthread); mutex_unlock(&fs_info->transaction_kthread_mutex); - if (unlikely(test_bit(BTRFS_FS_STATE_ERROR, - &fs_info->fs_state))) + if (BTRFS_FS_ERROR(fs_info)) btrfs_cleanup_transaction(fs_info); if (!kthread_should_stop() && (!btrfs_transaction_blocked(fs_info) || @@ -1845,11 +1661,23 @@ static void backup_super_roots(struct btrfs_fs_info *info) btrfs_set_backup_chunk_root_level(root_backup, btrfs_header_level(info->chunk_root->node)); - btrfs_set_backup_extent_root(root_backup, info->extent_root->node->start); - btrfs_set_backup_extent_root_gen(root_backup, - btrfs_header_generation(info->extent_root->node)); - btrfs_set_backup_extent_root_level(root_backup, - btrfs_header_level(info->extent_root->node)); + if (!btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE)) { + struct btrfs_root *extent_root = btrfs_extent_root(info, 0); + struct btrfs_root *csum_root = btrfs_csum_root(info, 0); + + btrfs_set_backup_extent_root(root_backup, + extent_root->node->start); + btrfs_set_backup_extent_root_gen(root_backup, + btrfs_header_generation(extent_root->node)); + btrfs_set_backup_extent_root_level(root_backup, + btrfs_header_level(extent_root->node)); + + btrfs_set_backup_csum_root(root_backup, csum_root->node->start); + btrfs_set_backup_csum_root_gen(root_backup, + btrfs_header_generation(csum_root->node)); + btrfs_set_backup_csum_root_level(root_backup, + btrfs_header_level(csum_root->node)); + } /* * we might commit during log recovery, which happens before we set @@ -1870,12 +1698,6 @@ static void backup_super_roots(struct btrfs_fs_info *info) btrfs_set_backup_dev_root_level(root_backup, btrfs_header_level(info->dev_root->node)); - btrfs_set_backup_csum_root(root_backup, info->csum_root->node->start); - btrfs_set_backup_csum_root_gen(root_backup, - btrfs_header_generation(info->csum_root->node)); - btrfs_set_backup_csum_root_level(root_backup, - btrfs_header_level(info->csum_root->node)); - btrfs_set_backup_total_bytes(root_backup, btrfs_super_total_bytes(info->super_copy)); btrfs_set_backup_bytes_used(root_backup, @@ -1893,11 +1715,11 @@ static void backup_super_roots(struct btrfs_fs_info *info) } /* - * read_backup_root - 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 + * 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 + * @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. */ @@ -1942,14 +1764,14 @@ static void 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); - btrfs_destroy_workqueue(fs_info->endio_workers); - btrfs_destroy_workqueue(fs_info->endio_raid56_workers); - btrfs_destroy_workqueue(fs_info->rmw_workers); + if (fs_info->endio_workers) + destroy_workqueue(fs_info->endio_workers); + if (fs_info->rmw_workers) + destroy_workqueue(fs_info->rmw_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->readahead_workers); btrfs_destroy_workqueue(fs_info->flush_workers); btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers); if (fs_info->discard_ctl.discard_workers) @@ -1959,8 +1781,8 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) * the queues used for metadata I/O, since tasks from those other work * queues can do metadata I/O operations. */ - btrfs_destroy_workqueue(fs_info->endio_meta_workers); - btrfs_destroy_workqueue(fs_info->endio_meta_write_workers); + if (fs_info->endio_meta_workers) + destroy_workqueue(fs_info->endio_meta_workers); } static void free_root_extent_buffers(struct btrfs_root *root) @@ -1973,21 +1795,31 @@ static void free_root_extent_buffers(struct btrfs_root *root) } } +static void free_global_root_pointers(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *root, *tmp; + + rbtree_postorder_for_each_entry_safe(root, tmp, + &fs_info->global_root_tree, + rb_node) + free_root_extent_buffers(root); +} + /* helper to cleanup tree roots */ static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root) { free_root_extent_buffers(info->tree_root); + free_global_root_pointers(info); free_root_extent_buffers(info->dev_root); - free_root_extent_buffers(info->extent_root); - free_root_extent_buffers(info->csum_root); free_root_extent_buffers(info->quota_root); free_root_extent_buffers(info->uuid_root); free_root_extent_buffers(info->fs_root); free_root_extent_buffers(info->data_reloc_root); + free_root_extent_buffers(info->block_group_root); + free_root_extent_buffers(info->stripe_root); if (free_chunk_root) free_root_extent_buffers(info->chunk_root); - free_root_extent_buffers(info->free_space_root); } void btrfs_put_root(struct btrfs_root *root) @@ -1996,15 +1828,14 @@ void btrfs_put_root(struct btrfs_root *root) return; if (refcount_dec_and_test(&root->refs)) { - WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree)); + 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); - btrfs_drew_lock_destroy(&root->snapshot_lock); - free_extent_buffer(root->node); - free_extent_buffer(root->commit_root); - kfree(root->free_ino_ctl); - kfree(root->free_ino_pinned); + free_root_extent_buffers(root); #ifdef CONFIG_BTRFS_DEBUG spin_lock(&root->fs_info->fs_roots_radix_lock); list_del_init(&root->leak_list); @@ -2021,8 +1852,8 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info) int i; while (!list_empty(&fs_info->dead_roots)) { - gang[0] = list_entry(fs_info->dead_roots.next, - struct btrfs_root, root_list); + 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)) @@ -2060,13 +1891,21 @@ static void btrfs_init_balance(struct btrfs_fs_info *fs_info) atomic_set(&fs_info->balance_cancel_req, 0); fs_info->balance_ctl = NULL; init_waitqueue_head(&fs_info->balance_wait_q); + atomic_set(&fs_info->reloc_cancel_req, 0); } -static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info) +static int btrfs_init_btree_inode(struct super_block *sb) { - struct inode *inode = fs_info->btree_inode; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + unsigned long hash = btrfs_inode_hash(BTRFS_BTREE_INODE_OBJECTID, + fs_info->tree_root); + struct inode *inode; - inode->i_ino = BTRFS_BTREE_INODE_OBJECTID; + 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. @@ -2075,19 +1914,19 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info) */ inode->i_size = OFFSET_MAX; inode->i_mapping->a_ops = &btree_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); - RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node); - extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree, - IO_TREE_INODE_IO, inode); - BTRFS_I(inode)->io_tree.track_uptodate = false; - extent_map_tree_init(&BTRFS_I(inode)->extent_tree); - - BTRFS_I(inode)->io_tree.ops = &btree_extent_io_ops; + btrfs_extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree, + IO_TREE_BTREE_INODE_IO); + btrfs_extent_map_tree_init(&BTRFS_I(inode)->extent_tree); BTRFS_I(inode)->root = btrfs_grab_root(fs_info->tree_root); - memset(&BTRFS_I(inode)->location, 0, sizeof(struct btrfs_key)); set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags); - btrfs_insert_inode_hash(inode); + __insert_inode_hash(inode, hash); + set_bit(AS_KERNEL_FILE, &inode->i_mapping->flags); + fs_info->btree_inode = inode; + + return 0; } static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info) @@ -2104,20 +1943,19 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) fs_info->qgroup_tree = RB_ROOT; INIT_LIST_HEAD(&fs_info->dirty_qgroups); fs_info->qgroup_seq = 1; - fs_info->qgroup_ulist = NULL; fs_info->qgroup_rescan_running = false; + fs_info->qgroup_drop_subtree_thres = BTRFS_QGROUP_DROP_SUBTREE_THRES_DEFAULT; mutex_init(&fs_info->qgroup_rescan_lock); } -static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, - struct btrfs_fs_devices *fs_devices) +static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info) { u32 max_active = fs_info->thread_pool_size; unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND; + unsigned int ordered_flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_PERCPU; fs_info->workers = - btrfs_alloc_workqueue(fs_info, "worker", - flags | WQ_HIGHPRI, max_active, 16); + btrfs_alloc_workqueue(fs_info, "worker", flags, max_active, 16); fs_info->delalloc_workers = btrfs_alloc_workqueue(fs_info, "delalloc", @@ -2131,25 +1969,13 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0); fs_info->fixup_workers = - btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0); + btrfs_alloc_ordered_workqueue(fs_info, "fixup", ordered_flags); - /* - * endios are largely parallel and should have a very - * low idle thresh - */ fs_info->endio_workers = - btrfs_alloc_workqueue(fs_info, "endio", flags, max_active, 4); + alloc_workqueue("btrfs-endio", flags, max_active); fs_info->endio_meta_workers = - btrfs_alloc_workqueue(fs_info, "endio-meta", flags, - max_active, 4); - fs_info->endio_meta_write_workers = - btrfs_alloc_workqueue(fs_info, "endio-meta-write", flags, - max_active, 2); - fs_info->endio_raid56_workers = - btrfs_alloc_workqueue(fs_info, "endio-raid56", flags, - max_active, 4); - fs_info->rmw_workers = - btrfs_alloc_workqueue(fs_info, "rmw", flags, max_active, 2); + alloc_workqueue("btrfs-endio-meta", flags, max_active); + fs_info->rmw_workers = alloc_workqueue("btrfs-rmw", flags, max_active); fs_info->endio_write_workers = btrfs_alloc_workqueue(fs_info, "endio-write", flags, max_active, 2); @@ -2159,23 +1985,19 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, fs_info->delayed_workers = btrfs_alloc_workqueue(fs_info, "delayed-meta", flags, max_active, 0); - fs_info->readahead_workers = - btrfs_alloc_workqueue(fs_info, "readahead", flags, - max_active, 2); fs_info->qgroup_rescan_workers = - btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0); + btrfs_alloc_ordered_workqueue(fs_info, "qgroup-rescan", + ordered_flags); fs_info->discard_ctl.discard_workers = - alloc_workqueue("btrfs_discard", WQ_UNBOUND | WQ_FREEZABLE, 1); + alloc_ordered_workqueue("btrfs-discard", WQ_FREEZABLE); - if (!(fs_info->workers && fs_info->delalloc_workers && - fs_info->flush_workers && + if (!(fs_info->workers && + fs_info->delalloc_workers && fs_info->flush_workers && fs_info->endio_workers && fs_info->endio_meta_workers && - fs_info->endio_meta_write_workers && - fs_info->endio_write_workers && fs_info->endio_raid56_workers && + fs_info->endio_write_workers && fs_info->endio_freespace_worker && fs_info->rmw_workers && - fs_info->caching_workers && fs_info->readahead_workers && - fs_info->fixup_workers && fs_info->delayed_workers && - fs_info->qgroup_rescan_workers && + fs_info->caching_workers && fs_info->fixup_workers && + fs_info->delayed_workers && fs_info->qgroup_rescan_workers && fs_info->discard_ctl.discard_workers)) { return -ENOMEM; } @@ -2198,6 +2020,22 @@ static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) 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; + } + + btrfs_info(fs_info, "using %s (%s) checksum algorithm", + btrfs_super_csum_name(csum_type), + crypto_shash_driver_name(csum_shash)); return 0; } @@ -2205,12 +2043,13 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, struct btrfs_fs_devices *fs_devices) { int ret; + struct btrfs_tree_parent_check check = { 0 }; struct btrfs_root *log_tree_root; struct btrfs_super_block *disk_super = fs_info->super_copy; u64 bytenr = btrfs_super_log_root(disk_super); int level = btrfs_super_log_root_level(disk_super); - if (fs_devices->rw_devices == 0) { + if (unlikely(fs_devices->rw_devices == 0)) { btrfs_warn(fs_info, "log replay required on RO media"); return -EIO; } @@ -2220,26 +2059,29 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, if (!log_tree_root) return -ENOMEM; - log_tree_root->node = read_tree_block(fs_info, bytenr, - fs_info->generation + 1, - level, NULL); + 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; - } else if (!extent_buffer_uptodate(log_tree_root->node)) { + } + if (unlikely(!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"); - btrfs_put_root(log_tree_root); return ret; } @@ -2252,6 +2094,113 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, return 0; } +static int load_global_roots_objectid(struct btrfs_root *tree_root, + struct btrfs_path *path, u64 objectid, + const char *name) +{ + struct btrfs_fs_info *fs_info = tree_root->fs_info; + struct btrfs_root *root; + u64 max_global_id = 0; + int ret; + struct btrfs_key key = { + .objectid = objectid, + .type = BTRFS_ROOT_ITEM_KEY, + .offset = 0, + }; + bool found = false; + + /* 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; +} + +static int 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"); + + return ret; +} + static int btrfs_read_roots(struct btrfs_fs_info *fs_info) { struct btrfs_root *tree_root = fs_info->tree_root; @@ -2259,38 +2208,44 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) struct btrfs_key location; int ret; - BUG_ON(!fs_info->tree_root); + ASSERT(fs_info->tree_root); + + ret = load_global_roots(tree_root); + if (ret) + return ret; - location.objectid = BTRFS_EXTENT_TREE_OBJECTID; location.type = BTRFS_ROOT_ITEM_KEY; location.offset = 0; - root = btrfs_read_tree_root(tree_root, &location); - if (IS_ERR(root)) { - ret = PTR_ERR(root); - goto out; + 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; + } } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - fs_info->extent_root = root; location.objectid = BTRFS_DEV_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { - ret = PTR_ERR(root); - goto out; + 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; } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - fs_info->dev_root = root; - btrfs_init_devices_late(fs_info); - - location.objectid = BTRFS_CSUM_TREE_OBJECTID; - root = btrfs_read_tree_root(tree_root, &location); - if (IS_ERR(root)) { - ret = PTR_ERR(root); + /* Initialize fs_info for all devices in any case */ + ret = btrfs_init_devices_late(fs_info); + if (ret) goto out; - } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - fs_info->csum_root = root; /* * This tree can share blocks with some other fs tree during relocation @@ -2299,40 +2254,47 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) root = btrfs_get_fs_root(tree_root->fs_info, BTRFS_DATA_RELOC_TREE_OBJECTID, true); if (IS_ERR(root)) { - ret = PTR_ERR(root); - goto out; + 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; } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - fs_info->data_reloc_root = root; location.objectid = BTRFS_QUOTA_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (!IS_ERR(root)) { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); fs_info->quota_root = root; } location.objectid = BTRFS_UUID_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { - ret = PTR_ERR(root); - if (ret != -ENOENT) - goto out; + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + if (ret != -ENOENT) + goto out; + } } else { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); fs_info->uuid_root = root; } - if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { - location.objectid = BTRFS_FREE_SPACE_TREE_OBJECTID; + if (btrfs_fs_incompat(fs_info, RAID_STRIPE_TREE)) { + location.objectid = BTRFS_RAID_STRIPE_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { - ret = PTR_ERR(root); - goto out; + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->stripe_root = root; } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - fs_info->free_space_root = root; } return 0; @@ -2342,6 +2304,71 @@ out: return ret; } +static int validate_sys_chunk_array(const struct btrfs_fs_info *fs_info, + const struct btrfs_super_block *sb) +{ + unsigned int 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 (unlikely(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; + } + + while (cur < sys_array_size) { + struct btrfs_disk_key *disk_key; + struct btrfs_chunk *chunk; + struct btrfs_key key; + u64 type; + u16 num_stripes; + u32 len; + int ret; + + disk_key = (struct btrfs_disk_key *)(sb->sys_chunk_array + cur); + len = sizeof(*disk_key); + + if (unlikely(cur + len > sys_array_size)) + goto short_read; + cur += len; + + btrfs_disk_key_to_cpu(&key, disk_key); + if (unlikely(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 (unlikely(cur + btrfs_chunk_item_size(num_stripes) > sys_array_size)) + goto short_read; + type = btrfs_stack_chunk_type(chunk); + if (unlikely(!(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. @@ -2352,21 +2379,29 @@ out: * 1, 2 2nd and 3rd backup copy * -1 skip bytenr check */ -static int validate_super(struct btrfs_fs_info *fs_info, - struct btrfs_super_block *sb, int mirror_num) +int btrfs_validate_super(const struct btrfs_fs_info *fs_info, + const struct btrfs_super_block *sb, int mirror_num) { u64 nodesize = btrfs_super_nodesize(sb); u64 sectorsize = btrfs_super_sectorsize(sb); int ret = 0; + const bool 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) { - btrfs_err(fs_info, "unrecognized or unsupported super flag: %llu", - btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP); - 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", @@ -2388,18 +2423,19 @@ static int validate_super(struct btrfs_fs_info *fs_info, * 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 < 4096 || + 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; } - /* Only PAGE SIZE is supported yet */ - if (sectorsize != PAGE_SIZE) { + + if (!btrfs_supported_blocksize(sectorsize)) { btrfs_err(fs_info, - "sectorsize %llu not supported yet, only support %lu", + "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); @@ -2428,6 +2464,22 @@ static int validate_super(struct btrfs_fs_info *fs_info, 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, @@ -2437,6 +2489,18 @@ static int validate_super(struct btrfs_fs_info *fs_info, } /* + * 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 */ @@ -2465,6 +2529,11 @@ static int validate_super(struct btrfs_fs_info *fs_info, ret = -EINVAL; } + if (ret) + return ret; + + ret = validate_sys_chunk_array(fs_info, sb); + /* * Obvious sys_chunk_array corruptions, it must hold at least one key * and one chunk @@ -2510,7 +2579,7 @@ static int validate_super(struct btrfs_fs_info *fs_info, */ static int btrfs_validate_mount_super(struct btrfs_fs_info *fs_info) { - return validate_super(fs_info, fs_info->super_copy, 0); + return btrfs_validate_super(fs_info, fs_info->super_copy, 0); } /* @@ -2524,16 +2593,16 @@ static int btrfs_validate_write_super(struct btrfs_fs_info *fs_info, { int ret; - ret = validate_super(fs_info, sb, -1); + ret = btrfs_validate_super(fs_info, sb, -1); if (ret < 0) goto out; - if (!btrfs_supported_super_csum(btrfs_super_csum_type(sb))) { + if (unlikely(!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) { + if (unlikely(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", @@ -2548,6 +2617,50 @@ out: return ret; } +static int 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 (unlikely(!extent_buffer_uptodate(root->node))) { + free_extent_buffer(root->node); + root->node = NULL; + return -EIO; + } + + btrfs_set_root_node(&root->root_item, root->node); + root->commit_root = btrfs_root_node(root); + btrfs_set_root_refs(&root->root_item, 1); + return ret; +} + +static int load_important_roots(struct btrfs_fs_info *fs_info) +{ + struct btrfs_super_block *sb = fs_info->super_copy; + u64 gen, bytenr; + int level, ret; + + 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; +} + static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) { int backup_index = find_newest_super_backup(fs_info); @@ -2558,9 +2671,6 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) int i; for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) { - u64 generation; - int level; - if (handle_error) { if (!IS_ERR(tree_root->node)) free_extent_buffer(tree_root->node); @@ -2577,47 +2687,30 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) */ btrfs_set_super_log_root(sb, 0); - /* We can't trust the free space cache either */ - btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE); - + 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; } - generation = btrfs_super_generation(sb); - level = btrfs_super_root_level(sb); - tree_root->node = read_tree_block(fs_info, btrfs_super_root(sb), - generation, level, NULL); - if (IS_ERR(tree_root->node) || - !extent_buffer_uptodate(tree_root->node)) { - handle_error = true; - - if (IS_ERR(tree_root->node)) - ret = PTR_ERR(tree_root->node); - else if (!extent_buffer_uptodate(tree_root->node)) - ret = -EUCLEAN; - btrfs_warn(fs_info, "failed to read tree root"); + ret = load_important_roots(fs_info); + if (ret) { + handle_error = true; continue; } - btrfs_set_root_node(&tree_root->root_item, tree_root->node); - tree_root->commit_root = btrfs_root_node(tree_root); - btrfs_set_root_refs(&tree_root->root_item, 1); - /* * No need to hold btrfs_root::objectid_mutex since the fs * hasn't been fully initialised and we are the only user */ - ret = btrfs_find_highest_objectid(tree_root, - &tree_root->highest_objectid); + ret = btrfs_init_root_free_objectid(tree_root); if (ret < 0) { handle_error = true; continue; } - ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + ASSERT(tree_root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); ret = btrfs_read_roots(fs_info); if (ret < 0) { @@ -2626,8 +2719,9 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) } /* All successful */ - fs_info->generation = generation; - fs_info->last_trans_committed = generation; + fs_info->generation = btrfs_header_generation(tree_root->node); + btrfs_set_last_trans_committed(fs_info, fs_info->generation); + fs_info->last_reloc_trans = 0; /* Always begin writing backup roots after the one being used */ if (backup_index < 0) { @@ -2642,10 +2736,21 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) 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. + */ +static struct lock_class_key buffer_xa_class; + void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) { INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC); - INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC); + + /* 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); + INIT_LIST_HEAD(&fs_info->trans_list); INIT_LIST_HEAD(&fs_info->dead_roots); INIT_LIST_HEAD(&fs_info->delayed_iputs); @@ -2657,29 +2762,51 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); spin_lock_init(&fs_info->super_lock); - spin_lock_init(&fs_info->buffer_lock); spin_lock_init(&fs_info->unused_bgs_lock); + spin_lock_init(&fs_info->treelog_bg_lock); + spin_lock_init(&fs_info->zone_active_bgs_lock); + spin_lock_init(&fs_info->relocation_bg_lock); rwlock_init(&fs_info->tree_mod_log_lock); + rwlock_init(&fs_info->global_root_lock); mutex_init(&fs_info->unused_bg_unpin_mutex); - mutex_init(&fs_info->delete_unused_bgs_mutex); + mutex_init(&fs_info->reclaim_bgs_lock); mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); + mutex_init(&fs_info->zoned_meta_io_lock); + mutex_init(&fs_info->zoned_data_reloc_io_lock); seqlock_init(&fs_info->profiles_lock); + btrfs_lockdep_init_map(fs_info, btrfs_trans_num_writers); + btrfs_lockdep_init_map(fs_info, btrfs_trans_num_extwriters); + btrfs_lockdep_init_map(fs_info, btrfs_trans_pending_ordered); + btrfs_lockdep_init_map(fs_info, btrfs_ordered_extent); + btrfs_state_lockdep_init_map(fs_info, btrfs_trans_commit_prep, + BTRFS_LOCKDEP_TRANS_COMMIT_PREP); + btrfs_state_lockdep_init_map(fs_info, btrfs_trans_unblocked, + BTRFS_LOCKDEP_TRANS_UNBLOCKED); + btrfs_state_lockdep_init_map(fs_info, btrfs_trans_super_committed, + BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED); + btrfs_state_lockdep_init_map(fs_info, btrfs_trans_completed, + BTRFS_LOCKDEP_TRANS_COMPLETED); + INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); INIT_LIST_HEAD(&fs_info->space_info); INIT_LIST_HEAD(&fs_info->tree_mod_seq_list); INIT_LIST_HEAD(&fs_info->unused_bgs); + INIT_LIST_HEAD(&fs_info->reclaim_bgs); + INIT_LIST_HEAD(&fs_info->zone_active_bgs); #ifdef CONFIG_BTRFS_DEBUG INIT_LIST_HEAD(&fs_info->allocated_roots); INIT_LIST_HEAD(&fs_info->allocated_ebs); spin_lock_init(&fs_info->eb_leak_lock); #endif - extent_map_tree_init(&fs_info->mapping_tree); + fs_info->mapping_tree = RB_ROOT_CACHED; + rwlock_init(&fs_info->mapping_tree_lock); btrfs_init_block_rsv(&fs_info->global_block_rsv, BTRFS_BLOCK_RSV_GLOBAL); btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS); btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK); + btrfs_init_block_rsv(&fs_info->treelog_rsv, BTRFS_BLOCK_RSV_TREELOG); btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY); btrfs_init_block_rsv(&fs_info->delayed_block_rsv, BTRFS_BLOCK_RSV_DELOPS); @@ -2688,19 +2815,15 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) atomic_set(&fs_info->async_delalloc_pages, 0); atomic_set(&fs_info->defrag_running, 0); - atomic_set(&fs_info->reada_works_cnt, 0); atomic_set(&fs_info->nr_delayed_iputs, 0); atomic64_set(&fs_info->tree_mod_seq, 0); + fs_info->global_root_tree = RB_ROOT; fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE; fs_info->metadata_ratio = 0; fs_info->defrag_inodes = RB_ROOT; atomic64_set(&fs_info->free_chunk_space, 0); fs_info->tree_mod_log = RB_ROOT; fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; - fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */ - /* readahead state */ - INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); - spin_lock_init(&fs_info->reada_lock); btrfs_init_ref_verify(fs_info); fs_info->thread_pool_size = min_t(unsigned long, @@ -2710,19 +2833,15 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) spin_lock_init(&fs_info->ordered_root_lock); btrfs_init_scrub(fs_info); -#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY - fs_info->check_integrity_print_mask = 0; -#endif btrfs_init_balance(fs_info); - btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work); + btrfs_init_async_reclaim_work(fs_info); + btrfs_init_extent_map_shrinker_work(fs_info); - spin_lock_init(&fs_info->block_group_cache_lock); - fs_info->block_group_cache_tree = RB_ROOT; - fs_info->first_logical_byte = (u64)-1; + rwlock_init(&fs_info->block_group_cache_lock); + fs_info->block_group_cache_tree = RB_ROOT_CACHED; - extent_io_tree_init(fs_info, &fs_info->excluded_extents, - IO_TREE_FS_EXCLUDED_EXTENTS, NULL); - set_bit(BTRFS_FS_BARRIER, &fs_info->flags); + btrfs_extent_io_tree_init(fs_info, &fs_info->excluded_extents, + IO_TREE_FS_EXCLUDED_EXTENTS); mutex_init(&fs_info->ordered_operations_mutex); mutex_init(&fs_info->tree_log_mutex); @@ -2751,12 +2870,19 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) /* 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; + + fs_info->max_extent_size = BTRFS_MAX_EXTENT_SIZE; + spin_lock_init(&fs_info->swapfile_pins_lock); fs_info->swapfile_pins = RB_ROOT; - fs_info->send_in_progress = 0; + fs_info->bg_reclaim_threshold = BTRFS_DEFAULT_RECLAIM_THRESH; + INIT_WORK(&fs_info->reclaim_bgs_work, btrfs_reclaim_bgs_work); } static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block *sb) @@ -2764,10 +2890,15 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block int ret; fs_info->sb = sb; + /* Temporary fixed values for block size until we read the superblock. */ sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE; sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE); - ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL); + ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL); + if (ret) + return ret; + + ret = percpu_counter_init(&fs_info->evictable_extent_maps, 0, GFP_KERNEL); if (ret) return ret; @@ -2775,6 +2906,10 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block if (ret) return ret; + ret = percpu_counter_init(&fs_info->stats_read_blocks, 0, GFP_KERNEL); + if (ret) + return ret; + fs_info->dirty_metadata_batch = PAGE_SIZE * (1 + ilog2(nr_cpu_ids)); @@ -2793,12 +2928,17 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block 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); + return btrfs_alloc_stripe_hash_table(fs_info); } static int btrfs_uuid_rescan_kthread(void *data) { - struct btrfs_fs_info *fs_info = (struct btrfs_fs_info *)data; + struct btrfs_fs_info *fs_info = data; int ret; /* @@ -2833,29 +2973,304 @@ static int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info) return 0; } -int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, - char *options) +static int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) +{ + u64 root_objectid = 0; + struct btrfs_root *gang[8]; + int ret = 0; + + while (1) { + unsigned int found; + + spin_lock(&fs_info->fs_roots_radix_lock); + found = radix_tree_gang_lookup(&fs_info->fs_roots_radix, + (void **)gang, root_objectid, + ARRAY_SIZE(gang)); + if (!found) { + spin_unlock(&fs_info->fs_roots_radix_lock); + break; + } + root_objectid = btrfs_root_id(gang[found - 1]) + 1; + + 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; + const bool 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; + } else if (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; + + down_read(&fs_info->cleanup_work_sem); + if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) || + (ret = btrfs_orphan_cleanup(fs_info->tree_root))) { + up_read(&fs_info->cleanup_work_sem); + goto out; + } + up_read(&fs_info->cleanup_work_sem); + + 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; + else if (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/bs > ps runtime limitation on v1 cache. + * + * V1 space cache still has some hard coded 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); + + return 0; +} + +int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices) { u32 sectorsize; u32 nodesize; u32 stripesize; u64 generation; - u64 features; u16 csum_type; struct btrfs_super_block *disk_super; struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *tree_root; struct btrfs_root *chunk_root; int ret; - int err = -EINVAL; - int clear_free_space_tree = 0; int level; ret = init_mount_fs_info(fs_info, sb); - if (ret) { - err = ret; + 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, @@ -2865,45 +3280,43 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device GFP_KERNEL); fs_info->chunk_root = chunk_root; if (!tree_root || !chunk_root) { - err = -ENOMEM; + ret = -ENOMEM; goto fail; } - fs_info->btree_inode = new_inode(sb); - if (!fs_info->btree_inode) { - err = -ENOMEM; + ret = btrfs_init_btree_inode(sb); + if (ret) goto fail; - } - mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS); - btrfs_init_btree_inode(fs_info); - invalidate_bdev(fs_devices->latest_bdev); + invalidate_bdev(fs_devices->latest_dev->bdev); /* * Read super block and check the signature bytes only */ - disk_super = btrfs_read_dev_super(fs_devices->latest_bdev); + disk_super = btrfs_read_disk_super(fs_devices->latest_dev->bdev, 0, false); if (IS_ERR(disk_super)) { - err = PTR_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 the checksum value are + * 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); - err = -EINVAL; + ret = -EINVAL; btrfs_release_disk_super(disk_super); goto fail_alloc; } + fs_info->csum_size = btrfs_super_csum_size(disk_super); + ret = btrfs_init_csum_hash(fs_info, csum_type); if (ret) { - err = ret; btrfs_release_disk_super(disk_super); goto fail_alloc; } @@ -2912,9 +3325,9 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device * 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, (u8 *)disk_super)) { + if (btrfs_check_super_csum(fs_info, disk_super)) { btrfs_err(fs_info, "superblock checksum mismatch"); - err = -EINVAL; + ret = -EINVAL; btrfs_release_disk_super(disk_super); goto fail_alloc; } @@ -2929,135 +3342,79 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device disk_super = fs_info->super_copy; - ASSERT(!memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid, - BTRFS_FSID_SIZE)); - - if (btrfs_fs_incompat(fs_info, METADATA_UUID)) { - ASSERT(!memcmp(fs_info->fs_devices->metadata_uuid, - fs_info->super_copy->metadata_uuid, - BTRFS_FSID_SIZE)); - } - - features = btrfs_super_flags(disk_super); - if (features & BTRFS_SUPER_FLAG_CHANGING_FSID_V2) { - features &= ~BTRFS_SUPER_FLAG_CHANGING_FSID_V2; - btrfs_set_super_flags(disk_super, features); - btrfs_info(fs_info, - "found metadata UUID change in progress flag, clearing"); - } - memcpy(fs_info->super_for_commit, fs_info->super_copy, sizeof(*fs_info->super_for_commit)); ret = btrfs_validate_mount_super(fs_info); if (ret) { btrfs_err(fs_info, "superblock contains fatal errors"); - err = -EINVAL; + ret = -EINVAL; goto fail_alloc; } - if (!btrfs_super_root(disk_super)) + if (!btrfs_super_root(disk_super)) { + btrfs_err(fs_info, "invalid superblock tree root bytenr"); + ret = -EINVAL; goto fail_alloc; + } /* check FS state, whether FS is broken. */ if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR) - set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state); - - /* - * In the long term, we'll store the compression type in the super - * block, and it'll be used for per file compression control. - */ - fs_info->compress_type = BTRFS_COMPRESS_ZLIB; - - ret = btrfs_parse_options(fs_info, options, sb->s_flags); - if (ret) { - err = ret; - goto fail_alloc; - } - - features = btrfs_super_incompat_flags(disk_super) & - ~BTRFS_FEATURE_INCOMPAT_SUPP; - if (features) { - btrfs_err(fs_info, - "cannot mount because of unsupported optional features (%llx)", - features); - err = -EINVAL; - goto fail_alloc; - } - - features = btrfs_super_incompat_flags(disk_super); - features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; - if (fs_info->compress_type == BTRFS_COMPRESS_LZO) - features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; - else if (fs_info->compress_type == BTRFS_COMPRESS_ZSTD) - features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD; - - if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) - btrfs_info(fs_info, "has skinny extents"); - - /* - * flag our filesystem as having big metadata blocks if - * they are bigger than the page size - */ - if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) { - if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA)) - btrfs_info(fs_info, - "flagging fs with big metadata feature"); - features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA; - } + WRITE_ONCE(fs_info->fs_error, -EUCLEAN); + /* Set up fs_info before parsing mount options */ nodesize = btrfs_super_nodesize(disk_super); sectorsize = btrfs_super_sectorsize(disk_super); stripesize = sectorsize; fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids)); fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids)); - /* Cache block sizes */ fs_info->nodesize = nodesize; + fs_info->nodesize_bits = ilog2(nodesize); fs_info->sectorsize = sectorsize; + fs_info->sectorsize_bits = ilog2(sectorsize); + fs_info->block_min_order = ilog2(round_up(sectorsize, PAGE_SIZE) >> PAGE_SHIFT); + fs_info->block_max_order = ilog2((BITS_PER_LONG << fs_info->sectorsize_bits) >> PAGE_SHIFT); + fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size; fs_info->stripesize = stripesize; + fs_info->fs_devices->fs_info = fs_info; + if (fs_info->sectorsize > PAGE_SIZE) + btrfs_warn(fs_info, + "support for block size %u with page size %lu is experimental, some features may be missing", + fs_info->sectorsize, PAGE_SIZE); /* - * mixed block groups end up with duplicate but slightly offset - * extent buffers for the same range. It leads to corruptions + * Handle the space caching options appropriately now that we have the + * super block loaded and validated. */ - if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) && - (sectorsize != nodesize)) { - btrfs_err(fs_info, -"unequal nodesize/sectorsize (%u != %u) are not allowed for mixed block groups", - nodesize, sectorsize); + 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; + /* - * Needn't use the lock because there is no other task which will - * update the flag. + * At this point our mount options are validated, if we set ->max_inline + * to something non-standard make sure we truncate it to sectorsize. */ - btrfs_set_super_incompat_flags(disk_super, features); - - features = btrfs_super_compat_ro_flags(disk_super) & - ~BTRFS_FEATURE_COMPAT_RO_SUPP; - if (!sb_rdonly(sb) && features) { - btrfs_err(fs_info, - "cannot mount read-write because of unsupported optional features (%llx)", - features); - err = -EINVAL; - goto fail_alloc; - } + fs_info->max_inline = min_t(u64, fs_info->max_inline, fs_info->sectorsize); - ret = btrfs_init_workqueues(fs_info, fs_devices); - if (ret) { - err = ret; + ret = btrfs_alloc_compress_wsm(fs_info); + if (ret) + goto fail_sb_buffer; + ret = btrfs_init_workqueues(fs_info); + if (ret) goto fail_sb_buffer; - } - sb->s_bdi->congested_fn = btrfs_congested_fn; - sb->s_bdi->congested_data = fs_info; - sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK; - sb->s_bdi->ra_pages = VM_READAHEAD_PAGES; sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super); sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE); + /* 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); @@ -3072,20 +3429,12 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device generation = btrfs_super_chunk_root_generation(disk_super); level = btrfs_super_chunk_root_level(disk_super); - - chunk_root->node = read_tree_block(fs_info, - btrfs_super_chunk_root(disk_super), - generation, level, NULL); - if (IS_ERR(chunk_root->node) || - !extent_buffer_uptodate(chunk_root->node)) { + 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"); - if (!IS_ERR(chunk_root->node)) - free_extent_buffer(chunk_root->node); - chunk_root->node = NULL; goto fail_tree_roots; } - btrfs_set_root_node(&chunk_root->root_item, chunk_root->node); - chunk_root->commit_root = btrfs_root_node(chunk_root); read_extent_buffer(chunk_root->node, fs_info->chunk_tree_uuid, offsetof(struct btrfs_header, chunk_tree_uuid), @@ -3098,13 +3447,16 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device } /* - * Keep the devid that is marked to be the target device for the - * device replace procedure + * 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, 0); - - if (!fs_devices->latest_bdev) { + btrfs_free_extra_devids(fs_devices); + if (unlikely(!fs_devices->latest_dev->bdev)) { btrfs_err(fs_info, "failed to read devices"); + ret = -EIO; goto fail_tree_roots; } @@ -3113,6 +3465,18 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device 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 @@ -3149,7 +3513,12 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_block_groups; } - btrfs_free_extra_devids(fs_devices, 1); + 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) { @@ -3176,47 +3545,34 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_sysfs; } - if (!sb_rdonly(sb) && !btrfs_check_rw_degradable(fs_info, NULL)) { + btrfs_zoned_reserve_data_reloc_bg(fs_info); + btrfs_free_zone_cache(fs_info); + + btrfs_check_active_zone_reservation(fs_info); + + 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, tree_root, + fs_info->cleaner_kthread = kthread_run(cleaner_kthread, fs_info, "btrfs-cleaner"); - if (IS_ERR(fs_info->cleaner_kthread)) + 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)) + if (IS_ERR(fs_info->transaction_kthread)) { + ret = PTR_ERR(fs_info->transaction_kthread); goto fail_cleaner; - - if (!btrfs_test_opt(fs_info, NOSSD) && - !fs_info->fs_devices->rotating) { - btrfs_set_and_info(fs_info, SSD, "enabling ssd optimizations"); } - /* - * Mount does not set all options immediately, we can do it now and do - * not have to wait for transaction commit - */ - btrfs_apply_pending_changes(fs_info); - -#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY - if (btrfs_test_opt(fs_info, CHECK_INTEGRITY)) { - ret = btrfsic_mount(fs_info, fs_devices, - btrfs_test_opt(fs_info, - CHECK_INTEGRITY_INCLUDING_EXTENT_DATA) ? - 1 : 0, - fs_info->check_integrity_print_mask); - if (ret) - btrfs_warn(fs_info, - "failed to initialize integrity check module: %d", - ret); - } -#endif ret = btrfs_read_qgroup_config(fs_info); if (ret) goto fail_trans_kthread; @@ -3229,36 +3585,14 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device !btrfs_test_opt(fs_info, NOLOGREPLAY)) { btrfs_info(fs_info, "start tree-log replay"); ret = btrfs_replay_log(fs_info, fs_devices); - if (ret) { - err = ret; - goto fail_qgroup; - } - } - - ret = btrfs_find_orphan_roots(fs_info); - if (ret) - goto fail_qgroup; - - if (!sb_rdonly(sb)) { - ret = btrfs_cleanup_fs_roots(fs_info); if (ret) goto fail_qgroup; - - mutex_lock(&fs_info->cleaner_mutex); - ret = btrfs_recover_relocation(tree_root); - mutex_unlock(&fs_info->cleaner_mutex); - if (ret < 0) { - btrfs_warn(fs_info, "failed to recover relocation: %d", - ret); - err = -EINVAL; - 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)) { - err = PTR_ERR(fs_info->fs_root); - btrfs_warn(fs_info, "failed to read fs tree: %d", err); + 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; } @@ -3266,76 +3600,16 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (sb_rdonly(sb)) return 0; - if (btrfs_test_opt(fs_info, CLEAR_CACHE) && - btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { - clear_free_space_tree = 1; - } else if (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"); - clear_free_space_tree = 1; - } - - if (clear_free_space_tree) { - btrfs_info(fs_info, "clearing free space tree"); - ret = btrfs_clear_free_space_tree(fs_info); - if (ret) { - btrfs_warn(fs_info, - "failed to clear free space tree: %d", ret); - close_ctree(fs_info); - return ret; - } - } - - 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); - close_ctree(fs_info); - return ret; - } - } - - down_read(&fs_info->cleanup_work_sem); - if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) || - (ret = btrfs_orphan_cleanup(fs_info->tree_root))) { - up_read(&fs_info->cleanup_work_sem); - close_ctree(fs_info); - return ret; - } - up_read(&fs_info->cleanup_work_sem); - - ret = btrfs_resume_balance_async(fs_info); + ret = btrfs_start_pre_rw_mount(fs_info); if (ret) { - btrfs_warn(fs_info, "failed to resume balance: %d", ret); close_ctree(fs_info); return ret; } - - ret = btrfs_resume_dev_replace_async(fs_info); - if (ret) { - btrfs_warn(fs_info, "failed to resume device replace: %d", ret); - close_ctree(fs_info); - return ret; - } - - btrfs_qgroup_rescan_resume(fs_info); btrfs_discard_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); - close_ctree(fs_info); - return ret; - } - } else if (btrfs_test_opt(fs_info, RESCAN_UUID_TREE) || - fs_info->generation != - btrfs_super_uuid_tree_generation(disk_super)) { + 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) { @@ -3345,13 +3619,12 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device return ret; } } + set_bit(BTRFS_FS_OPEN, &fs_info->flags); - /* - * backuproot only affect mount behavior, and if open_ctree succeeded, - * no need to keep the flag - */ - btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT); + /* 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); return 0; @@ -3380,6 +3653,8 @@ fail_block_groups: btrfs_put_block_group_cache(fs_info); fail_tree_roots: + if (fs_info->data_reloc_root) + btrfs_drop_and_free_fs_root(fs_info, fs_info->data_reloc_root); free_root_pointers(fs_info, true); invalidate_inode_pages2(fs_info->btree_inode->i_mapping); @@ -3387,119 +3662,63 @@ fail_sb_buffer: btrfs_stop_all_workers(fs_info); btrfs_free_block_groups(fs_info); fail_alloc: - btrfs_mapping_tree_free(&fs_info->mapping_tree); + btrfs_mapping_tree_free(fs_info); iput(fs_info->btree_inode); fail: - btrfs_close_devices(fs_info->fs_devices); - return err; + ASSERT(ret < 0); + return ret; } ALLOW_ERROR_INJECTION(open_ctree, ERRNO); static void btrfs_end_super_write(struct bio *bio) { struct btrfs_device *device = bio->bi_private; - struct bio_vec *bvec; - struct bvec_iter_all iter_all; - struct page *page; - - bio_for_each_segment_all(bvec, bio, iter_all) { - page = bvec->bv_page; + struct folio_iter fi; + bio_for_each_folio_all(fi, bio) { if (bio->bi_status) { - btrfs_warn_rl_in_rcu(device->fs_info, - "lost page write due to IO error on %s (%d)", - rcu_str_deref(device->name), + 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)); - ClearPageUptodate(page); - SetPageError(page); btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_WRITE_ERRS); - } else { - SetPageUptodate(page); + /* 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); } - - put_page(page); - unlock_page(page); + folio_unlock(fi.folio); + folio_put(fi.folio); } bio_put(bio); } -struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev, - int copy_num) -{ - struct btrfs_super_block *super; - struct page *page; - u64 bytenr; - struct address_space *mapping = bdev->bd_inode->i_mapping; - - bytenr = btrfs_sb_offset(copy_num); - if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode)) - return ERR_PTR(-EINVAL); - - page = read_cache_page_gfp(mapping, bytenr >> PAGE_SHIFT, GFP_NOFS); - if (IS_ERR(page)) - return ERR_CAST(page); - - super = page_address(page); - if (btrfs_super_bytenr(super) != bytenr || - btrfs_super_magic(super) != BTRFS_MAGIC) { - btrfs_release_disk_super(super); - return ERR_PTR(-EINVAL); - } - - return super; -} - - -struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev) -{ - struct btrfs_super_block *super, *latest = NULL; - int i; - u64 transid = 0; - - /* we would like to check all the supers, but that would make - * a btrfs mount succeed after a mkfs from a different FS. - * So, we need to add a special mount option to scan for - * later supers, using BTRFS_SUPER_MIRROR_MAX instead - */ - for (i = 0; i < 1; i++) { - super = btrfs_read_dev_one_super(bdev, i); - if (IS_ERR(super)) - continue; - - if (!latest || btrfs_super_generation(super) > transid) { - if (latest) - btrfs_release_disk_super(super); - - latest = super; - transid = btrfs_super_generation(super); - } - } - - return super; -} - /* * Write superblock @sb to the @device. Do not wait for completion, all the - * pages we use for writing are locked. + * 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 page is not found or submission fails. + * Return number of errors when folio is not found or submission fails. */ static int 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_inode->i_mapping; + struct address_space *mapping = device->bdev->bd_mapping; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); int i; - int errors = 0; - u64 bytenr; + int ret; + u64 bytenr, bytenr_orig; + + atomic_set(&device->sb_write_errors, 0); if (max_mirrors == 0) max_mirrors = BTRFS_SUPER_MIRROR_MAX; @@ -3507,35 +3726,45 @@ static int write_dev_supers(struct btrfs_device *device, shash->tfm = fs_info->csum_shash; for (i = 0; i < max_mirrors; i++) { - struct page *page; + struct folio *folio; struct bio *bio; struct btrfs_super_block *disk_super; + size_t offset; - bytenr = btrfs_sb_offset(i); + bytenr_orig = btrfs_sb_offset(i); + ret = btrfs_sb_log_location(device, i, WRITE, &bytenr); + if (ret == -ENOENT) { + continue; + } else if (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; - btrfs_set_super_bytenr(sb, bytenr); + btrfs_set_super_bytenr(sb, bytenr_orig); crypto_shash_digest(shash, (const char *)sb + BTRFS_CSUM_SIZE, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, sb->csum); - page = find_or_create_page(mapping, bytenr >> PAGE_SHIFT, - GFP_NOFS); - if (!page) { + folio = __filemap_get_folio(mapping, bytenr >> PAGE_SHIFT, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + GFP_NOFS); + if (IS_ERR(folio)) { btrfs_err(device->fs_info, - "couldn't get super block page for bytenr %llu", - bytenr); - errors++; + "couldn't get super block page for bytenr %llu error %ld", + bytenr, PTR_ERR(folio)); + atomic_inc(&device->sb_write_errors); continue; } - /* Bump the refcount for wait_dev_supers() */ - get_page(page); - - disk_super = page_address(page); + offset = offset_in_folio(folio, bytenr); + disk_super = folio_address(folio) + offset; memcpy(disk_super, sb, BTRFS_SUPER_INFO_SIZE); /* @@ -3543,77 +3772,77 @@ static int write_dev_supers(struct btrfs_device *device, * to do I/O, so we don't lose the ability to do integrity * checking. */ - bio = bio_alloc(GFP_NOFS, 1); - bio_set_dev(bio, device->bdev); + 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_page(bio, page, BTRFS_SUPER_INFO_SIZE, - offset_in_page(bytenr)); + 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. */ - bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO; if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER)) bio->bi_opf |= REQ_FUA; + submit_bio(bio); - btrfsic_submit_bio(bio); + if (btrfs_advance_sb_log(device, i)) + atomic_inc(&device->sb_write_errors); } - return errors < i ? 0 : -1; + 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 number of errors when page is not found or not marked up to - * date. + * Return -1 if primary super block write failed or when there were no super block + * copies written. Otherwise 0. */ static int 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 page *page; + struct folio *folio; - bytenr = btrfs_sb_offset(i); - if (bytenr + BTRFS_SUPER_INFO_SIZE >= - device->commit_total_bytes) + ret = btrfs_sb_log_location(device, i, READ, &bytenr); + if (ret == -ENOENT) { break; - - page = find_get_page(device->bdev->bd_inode->i_mapping, - bytenr >> PAGE_SHIFT); - if (!page) { + } else if (ret < 0) { errors++; if (i == 0) primary_failed = true; continue; } - /* Page is submitted locked and unlocked once the IO completes */ - wait_on_page_locked(page); - if (PageError(page)) { - errors++; - if (i == 0) - primary_failed = true; - } + if (bytenr + BTRFS_SUPER_INFO_SIZE >= + device->commit_total_bytes) + break; - /* Drop our reference */ - put_page(page); + 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; - /* Drop the reference from the writing run */ - put_page(page); + /* Folio will be unlocked once the write completes. */ + folio_wait_locked(folio); + folio_put(folio); } - /* log error, force error return */ + 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); @@ -3629,6 +3858,7 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors) */ static void btrfs_end_empty_barrier(struct bio *bio) { + bio_uninit(bio); complete(bio->bi_private); } @@ -3638,44 +3868,39 @@ static void btrfs_end_empty_barrier(struct bio *bio) */ static void write_dev_flush(struct btrfs_device *device) { - struct request_queue *q = bdev_get_queue(device->bdev); - struct bio *bio = device->flush_bio; + struct bio *bio = &device->flush_bio; - if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) - return; + device->last_flush_error = BLK_STS_OK; - bio_reset(bio); + bio_init(bio, device->bdev, NULL, 0, + REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH); bio->bi_end_io = btrfs_end_empty_barrier; - bio_set_dev(bio, device->bdev); - bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; init_completion(&device->flush_wait); bio->bi_private = &device->flush_wait; - - btrfsic_submit_bio(bio); + submit_bio(bio); set_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state); } /* * If the flush bio has been submitted by write_dev_flush, wait for it. + * Return true for any error, and false otherwise. */ -static blk_status_t wait_dev_flush(struct btrfs_device *device) +static bool wait_dev_flush(struct btrfs_device *device) { - struct bio *bio = device->flush_bio; + struct bio *bio = &device->flush_bio; - if (!test_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state)) - return BLK_STS_OK; + if (!test_and_clear_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state)) + return false; - clear_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state); wait_for_completion_io(&device->flush_wait); - return bio->bi_status; -} + if (bio->bi_status) { + device->last_flush_error = bio->bi_status; + btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_FLUSH_ERRS); + return true; + } -static int check_barrier_error(struct btrfs_fs_info *fs_info) -{ - if (!btrfs_check_rw_degradable(fs_info, NULL)) - return -EIO; - return 0; + return false; } /* @@ -3687,7 +3912,6 @@ static int barrier_all_devices(struct btrfs_fs_info *info) struct list_head *head; struct btrfs_device *dev; int errors_wait = 0; - blk_status_t ret; lockdep_assert_held(&info->fs_devices->device_list_mutex); /* send down all the barriers */ @@ -3702,7 +3926,6 @@ static int barrier_all_devices(struct btrfs_fs_info *info) continue; write_dev_flush(dev); - dev->last_flush_error = BLK_STS_OK; } /* wait for all the barriers */ @@ -3717,23 +3940,17 @@ static int barrier_all_devices(struct btrfs_fs_info *info) !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue; - ret = wait_dev_flush(dev); - if (ret) { - dev->last_flush_error = ret; - btrfs_dev_stat_inc_and_print(dev, - BTRFS_DEV_STAT_FLUSH_ERRS); + if (wait_dev_flush(dev)) errors_wait++; - } } - if (errors_wait) { - /* - * At some point we need the status of all disks - * to arrive at the volume status. So error checking - * is being pushed to a separate loop. - */ - return check_barrier_error(info); - } + /* + * Checks last_flush_error of disks in order to determine the device + * state. + */ + if (unlikely(errors_wait && !btrfs_check_rw_degradable(info, NULL))) + return -EIO; + return 0; } @@ -3759,7 +3976,7 @@ int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags) } if (min_tolerated == INT_MAX) { - pr_warn("BTRFS: unknown raid flag: %llu", flags); + btrfs_warn(NULL, "unknown raid flag: %llu", flags); min_tolerated = 0; } @@ -3833,7 +4050,7 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN); ret = btrfs_validate_write_super(fs_info, sb); - if (ret < 0) { + if (unlikely(ret < 0)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); btrfs_handle_fs_error(fs_info, -EUCLEAN, "unexpected superblock corruption detected"); @@ -3844,7 +4061,7 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) if (ret) total_errors++; } - if (total_errors > max_errors) { + if (unlikely(total_errors > max_errors)) { btrfs_err(fs_info, "%d errors while writing supers", total_errors); mutex_unlock(&fs_info->fs_devices->device_list_mutex); @@ -3869,7 +4086,7 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) total_errors++; } mutex_unlock(&fs_info->fs_devices->device_list_mutex); - if (total_errors > max_errors) { + if (unlikely(total_errors > max_errors)) { btrfs_handle_fs_error(fs_info, -EIO, "%d errors while writing supers", total_errors); @@ -3886,12 +4103,12 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, spin_lock(&fs_info->fs_roots_radix_lock); radix_tree_delete(&fs_info->fs_roots_radix, - (unsigned long)root->root_key.objectid); + (unsigned long)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 (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { + if (BTRFS_FS_ERROR(fs_info)) { ASSERT(root->log_root == NULL); if (root->reloc_root) { btrfs_put_root(root->reloc_root); @@ -3899,73 +4116,12 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, } } - if (root->free_ino_pinned) - __btrfs_remove_free_space_cache(root->free_ino_pinned); - if (root->free_ino_ctl) - __btrfs_remove_free_space_cache(root->free_ino_ctl); - if (root->ino_cache_inode) { - iput(root->ino_cache_inode); - root->ino_cache_inode = NULL; - } if (drop_ref) btrfs_put_root(root); } -int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) -{ - u64 root_objectid = 0; - struct btrfs_root *gang[8]; - int i = 0; - int err = 0; - unsigned int ret = 0; - - while (1) { - spin_lock(&fs_info->fs_roots_radix_lock); - ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, - (void **)gang, root_objectid, - ARRAY_SIZE(gang)); - if (!ret) { - spin_unlock(&fs_info->fs_roots_radix_lock); - break; - } - root_objectid = gang[ret - 1]->root_key.objectid + 1; - - for (i = 0; i < ret; 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 (i = 0; i < ret; i++) { - if (!gang[i]) - continue; - root_objectid = gang[i]->root_key.objectid; - err = btrfs_orphan_cleanup(gang[i]); - if (err) - break; - btrfs_put_root(gang[i]); - } - root_objectid++; - } - - /* release the uncleaned roots due to error */ - for (; i < ret; i++) { - if (gang[i]) - btrfs_put_root(gang[i]); - } - return err; -} - int btrfs_commit_super(struct btrfs_fs_info *fs_info) { - struct btrfs_root *root = fs_info->tree_root; - struct btrfs_trans_handle *trans; - mutex_lock(&fs_info->cleaner_mutex); btrfs_run_delayed_iputs(fs_info); mutex_unlock(&fs_info->cleaner_mutex); @@ -3975,10 +4131,47 @@ int btrfs_commit_super(struct btrfs_fs_info *fs_info) down_write(&fs_info->cleanup_work_sem); up_write(&fs_info->cleanup_work_sem); - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) - return PTR_ERR(trans); - return btrfs_commit_transaction(trans); + return btrfs_commit_current_transaction(fs_info->tree_root); +} + +static void warn_about_uncommitted_trans(struct btrfs_fs_info *fs_info) +{ + struct btrfs_transaction *trans; + struct btrfs_transaction *tmp; + bool found = false; + + /* + * 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); + + btrfs_put_transaction(trans); + trace_btrfs_transaction_commit(fs_info); + } + ASSERT(!found); } void __cold close_ctree(struct btrfs_fs_info *fs_info) @@ -3986,6 +4179,28 @@ 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 @@ -4016,7 +4231,104 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) /* 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 - end_bbio_compressed_write() + * 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->endio_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); + cancel_work_sync(&fs_info->async_reclaim_work); + cancel_work_sync(&fs_info->async_data_reclaim_work); + cancel_work_sync(&fs_info->preempt_reclaim_work); + cancel_work_sync(&fs_info->em_shrinker_work); + + /* + * 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); @@ -4046,16 +4358,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) btrfs_err(fs_info, "commit super ret %d", ret); } - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state) || - test_bit(BTRFS_FS_STATE_TRANS_ABORTED, &fs_info->fs_state)) - btrfs_error_commit_super(fs_info); - kthread_stop(fs_info->transaction_kthread); kthread_stop(fs_info->cleaner_kthread); ASSERT(list_empty(&fs_info->delayed_iputs)); set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags); + if (btrfs_check_quota_leak(fs_info)) { + DEBUG_WARN("qgroup reserved space leaked"); + btrfs_err(fs_info, "qgroup reserved space leaked"); + } + btrfs_free_qgroup_config(fs_info); ASSERT(list_empty(&fs_info->delalloc_roots)); @@ -4064,9 +4377,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_sum(&fs_info->delalloc_bytes)); } - if (percpu_counter_sum(&fs_info->dio_bytes)) + if (percpu_counter_sum(&fs_info->ordered_bytes)) btrfs_info(fs_info, "at unmount dio bytes count %lld", - percpu_counter_sum(&fs_info->dio_bytes)); + percpu_counter_sum(&fs_info->ordered_bytes)); btrfs_sysfs_remove_mounted(fs_info); btrfs_sysfs_remove_fsid(fs_info->fs_devices); @@ -4080,6 +4393,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) 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); + clear_bit(BTRFS_FS_OPEN, &fs_info->flags); free_root_pointers(fs_info, true); btrfs_free_fs_roots(fs_info); @@ -4095,38 +4411,14 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) iput(fs_info->btree_inode); -#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY - if (btrfs_test_opt(fs_info, CHECK_INTEGRITY)) - btrfsic_unmount(fs_info->fs_devices); -#endif - - btrfs_mapping_tree_free(&fs_info->mapping_tree); - btrfs_close_devices(fs_info->fs_devices); + btrfs_mapping_tree_free(fs_info); } -int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, - int atomic) +void btrfs_mark_buffer_dirty(struct btrfs_trans_handle *trans, + struct extent_buffer *buf) { - int ret; - struct inode *btree_inode = buf->pages[0]->mapping->host; - - ret = extent_buffer_uptodate(buf); - if (!ret) - return ret; - - ret = verify_parent_transid(&BTRFS_I(btree_inode)->io_tree, buf, - parent_transid, atomic); - if (ret == -EAGAIN) - return ret; - return !ret; -} - -void btrfs_mark_buffer_dirty(struct extent_buffer *buf) -{ - struct btrfs_fs_info *fs_info; - struct btrfs_root *root; + struct btrfs_fs_info *fs_info = buf->fs_info; u64 transid = btrfs_header_generation(buf); - int was_dirty; #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS /* @@ -4137,29 +4429,16 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &buf->bflags))) return; #endif - root = BTRFS_I(buf->pages[0]->mapping->host)->root; - fs_info = root->fs_info; - btrfs_assert_tree_locked(buf); - if (transid != fs_info->generation) - WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, found %llu running %llu\n", - buf->start, transid, fs_info->generation); - was_dirty = set_extent_buffer_dirty(buf); - if (!was_dirty) - percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, - buf->len, - fs_info->dirty_metadata_batch); -#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY - /* - * Since btrfs_mark_buffer_dirty() can be called with item pointer set - * but item data not updated. - * So here we should only check item pointers, not item data. - */ - if (btrfs_header_level(buf) == 0 && - btrfs_check_leaf_relaxed(buf)) { - btrfs_print_leaf(buf); - ASSERT(0); - } -#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); } static void __btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info, @@ -4195,22 +4474,11 @@ void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info) __btrfs_btree_balance_dirty(fs_info, 0); } -int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level, - struct btrfs_key *first_key) -{ - return btree_read_extent_buffer_pages(buf, parent_transid, - level, first_key); -} - static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info) { /* cleanup FS via transaction */ btrfs_cleanup_transaction(fs_info); - mutex_lock(&fs_info->cleaner_mutex); - btrfs_run_delayed_iputs(fs_info); - mutex_unlock(&fs_info->cleaner_mutex); - down_write(&fs_info->cleanup_work_sem); up_write(&fs_info->cleanup_work_sem); } @@ -4234,7 +4502,7 @@ static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info) for (i = 0; i < ret; i++) { if (!gang[i]) continue; - root_objectid = gang[i]->root_key.objectid; + root_objectid = btrfs_root_id(gang[i]); btrfs_free_log(NULL, gang[i]); btrfs_put_root(gang[i]); } @@ -4263,9 +4531,7 @@ static void btrfs_destroy_ordered_extents(struct btrfs_root *root) static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; - struct list_head splice; - - INIT_LIST_HEAD(&splice); + LIST_HEAD(splice); spin_lock(&fs_info->ordered_root_lock); list_splice_init(&fs_info->ordered_roots, &splice); @@ -4289,98 +4555,13 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) * 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, 0, (u64)-1); -} - -static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, - struct btrfs_fs_info *fs_info) -{ - struct rb_node *node; - struct btrfs_delayed_ref_root *delayed_refs; - struct btrfs_delayed_ref_node *ref; - int ret = 0; - - delayed_refs = &trans->delayed_refs; - - spin_lock(&delayed_refs->lock); - if (atomic_read(&delayed_refs->num_entries) == 0) { - spin_unlock(&delayed_refs->lock); - btrfs_debug(fs_info, "delayed_refs has NO entry"); - return ret; - } - - while ((node = rb_first_cached(&delayed_refs->href_root)) != NULL) { - struct btrfs_delayed_ref_head *head; - struct rb_node *n; - bool pin_bytes = false; - - head = rb_entry(node, struct btrfs_delayed_ref_head, - href_node); - if (btrfs_delayed_ref_lock(delayed_refs, head)) - continue; - - spin_lock(&head->lock); - while ((n = rb_first_cached(&head->ref_tree)) != NULL) { - ref = rb_entry(n, struct btrfs_delayed_ref_node, - ref_node); - ref->in_tree = 0; - rb_erase_cached(&ref->ref_node, &head->ref_tree); - RB_CLEAR_NODE(&ref->ref_node); - if (!list_empty(&ref->add_list)) - list_del(&ref->add_list); - atomic_dec(&delayed_refs->num_entries); - btrfs_put_delayed_ref(ref); - } - if (head->must_insert_reserved) - pin_bytes = true; - btrfs_free_delayed_extent_op(head->extent_op); - btrfs_delete_ref_head(delayed_refs, head); - spin_unlock(&head->lock); - spin_unlock(&delayed_refs->lock); - mutex_unlock(&head->mutex); - - if (pin_bytes) { - struct btrfs_block_group *cache; - - cache = btrfs_lookup_block_group(fs_info, head->bytenr); - BUG_ON(!cache); - - spin_lock(&cache->space_info->lock); - spin_lock(&cache->lock); - cache->pinned += head->num_bytes; - btrfs_space_info_update_bytes_pinned(fs_info, - cache->space_info, head->num_bytes); - cache->reserved -= head->num_bytes; - cache->space_info->bytes_reserved -= head->num_bytes; - spin_unlock(&cache->lock); - spin_unlock(&cache->space_info->lock); - percpu_counter_add_batch( - &cache->space_info->total_bytes_pinned, - head->num_bytes, BTRFS_TOTAL_BYTES_PINNED_BATCH); - - btrfs_put_block_group(cache); - - btrfs_error_unpin_extent_range(fs_info, head->bytenr, - head->bytenr + head->num_bytes - 1); - } - btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); - btrfs_put_delayed_ref_head(head); - cond_resched(); - spin_lock(&delayed_refs->lock); - } - btrfs_qgroup_destroy_extent_records(trans); - - spin_unlock(&delayed_refs->lock); - - return ret; + btrfs_wait_ordered_roots(fs_info, U64_MAX, NULL); } static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) { struct btrfs_inode *btrfs_inode; - struct list_head splice; - - INIT_LIST_HEAD(&splice); + LIST_HEAD(splice); spin_lock(&root->delalloc_lock); list_splice_init(&root->delalloc_inodes, &splice); @@ -4389,7 +4570,7 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) struct inode *inode = NULL; btrfs_inode = list_first_entry(&splice, struct btrfs_inode, delalloc_inodes); - __btrfs_del_delalloc_inode(root, btrfs_inode); + btrfs_del_delalloc_inode(btrfs_inode); spin_unlock(&root->delalloc_lock); /* @@ -4398,7 +4579,11 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) */ inode = igrab(&btrfs_inode->vfs_inode); if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); iput(inode); } spin_lock(&root->delalloc_lock); @@ -4409,9 +4594,7 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; - struct list_head splice; - - INIT_LIST_HEAD(&splice); + LIST_HEAD(splice); spin_lock(&fs_info->delalloc_root_lock); list_splice_init(&fs_info->delalloc_roots, &splice); @@ -4430,45 +4613,38 @@ static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info) spin_unlock(&fs_info->delalloc_root_lock); } -static int btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info, - struct extent_io_tree *dirty_pages, - int mark) +static void btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info, + struct extent_io_tree *dirty_pages, + int mark) { - int ret; struct extent_buffer *eb; u64 start = 0; u64 end; - while (1) { - ret = find_first_extent_bit(dirty_pages, start, &start, &end, - mark, NULL); - if (ret) - break; - - clear_extent_bits(dirty_pages, start, end, mark); + while (btrfs_find_first_extent_bit(dirty_pages, start, &start, &end, + mark, NULL)) { + btrfs_clear_extent_bit(dirty_pages, start, end, mark, NULL); while (start <= end) { eb = find_extent_buffer(fs_info, start); start += fs_info->nodesize; if (!eb) continue; + + btrfs_tree_lock(eb); wait_on_extent_buffer_writeback(eb); + btrfs_clear_buffer_dirty(NULL, eb); + btrfs_tree_unlock(eb); - if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, - &eb->bflags)) - clear_extent_buffer_dirty(eb); free_extent_buffer_stale(eb); } } - - return ret; } -static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, - struct extent_io_tree *unpin) +static void btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, + struct extent_io_tree *unpin) { u64 start; u64 end; - int ret; while (1) { struct extent_state *cached_state = NULL; @@ -4480,21 +4656,18 @@ static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, * the same extent range. */ mutex_lock(&fs_info->unused_bg_unpin_mutex); - ret = find_first_extent_bit(unpin, 0, &start, &end, - EXTENT_DIRTY, &cached_state); - if (ret) { + if (!btrfs_find_first_extent_bit(unpin, 0, &start, &end, + EXTENT_DIRTY, &cached_state)) { mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; } - clear_extent_dirty(unpin, start, end, &cached_state); - free_extent_state(cached_state); + btrfs_clear_extent_dirty(unpin, start, end, &cached_state); + btrfs_free_extent_state(cached_state); btrfs_error_unpin_extent_range(fs_info, start, end); mutex_unlock(&fs_info->unused_bg_unpin_mutex); cond_resched(); } - - return 0; } static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) @@ -4503,11 +4676,17 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) inode = cache->io_ctl.inode; if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); + BTRFS_I(inode)->generation = 0; cache->io_ctl.inode = NULL; iput(inode); } + ASSERT(cache->io_ctl.pages == NULL); btrfs_put_block_group(cache); } @@ -4536,7 +4715,7 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, spin_unlock(&cur_trans->dirty_bgs_lock); btrfs_put_block_group(cache); - btrfs_delayed_refs_rsv_release(fs_info, 1); + btrfs_dec_delayed_refs_rsv_bg_updates(fs_info); spin_lock(&cur_trans->dirty_bgs_lock); } spin_unlock(&cur_trans->dirty_bgs_lock); @@ -4558,9 +4737,35 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, } } -void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, - struct btrfs_fs_info *fs_info) +static void btrfs_free_all_qgroup_pertrans(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *gang[8]; + int i; + int ret; + + spin_lock(&fs_info->fs_roots_radix_lock); + while (1) { + ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix, + (void **)gang, 0, + ARRAY_SIZE(gang), + BTRFS_ROOT_TRANS_TAG); + if (ret == 0) + break; + for (i = 0; i < ret; i++) { + struct btrfs_root *root = gang[i]; + + btrfs_qgroup_free_meta_all_pertrans(root); + radix_tree_tag_clear(&fs_info->fs_roots_radix, + (unsigned long)btrfs_root_id(root), + BTRFS_ROOT_TRANS_TAG); + } + } + spin_unlock(&fs_info->fs_roots_radix_lock); +} + +void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans) { + struct btrfs_fs_info *fs_info = cur_trans->fs_info; struct btrfs_device *dev, *tmp; btrfs_cleanup_dirty_bgs(cur_trans, fs_info); @@ -4572,7 +4777,7 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, list_del_init(&dev->post_commit_list); } - btrfs_destroy_delayed_refs(cur_trans, fs_info); + btrfs_destroy_delayed_refs(cur_trans); cur_trans->state = TRANS_STATE_COMMIT_START; wake_up(&fs_info->transaction_blocked_wait); @@ -4580,8 +4785,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, cur_trans->state = TRANS_STATE_UNBLOCKED; wake_up(&fs_info->transaction_wait); - btrfs_destroy_delayed_inodes(fs_info); - btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages, EXTENT_DIRTY); btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents); @@ -4600,7 +4803,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) 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_START) { + 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); @@ -4620,7 +4823,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) } else { spin_unlock(&fs_info->trans_lock); } - btrfs_cleanup_one_transaction(t, fs_info); + btrfs_cleanup_one_transaction(t); spin_lock(&fs_info->trans_lock); if (t == fs_info->running_transaction) @@ -4629,7 +4832,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) spin_unlock(&fs_info->trans_lock); btrfs_put_transaction(t); - trace_btrfs_transaction_commit(fs_info->tree_root); + trace_btrfs_transaction_commit(fs_info); spin_lock(&fs_info->trans_lock); } spin_unlock(&fs_info->trans_lock); @@ -4638,13 +4841,67 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) btrfs_assert_delayed_root_empty(fs_info); btrfs_destroy_all_delalloc_inodes(fs_info); btrfs_drop_all_logs(fs_info); + btrfs_free_all_qgroup_pertrans(fs_info); mutex_unlock(&fs_info->transaction_kthread_mutex); return 0; } -static const struct extent_io_ops btree_extent_io_ops = { - /* mandatory callbacks */ - .submit_bio_hook = btree_submit_bio_hook, - .readpage_end_io_hook = btree_readpage_end_io_hook, -}; +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 (unlikely(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; + } + + *objectid = root->free_objectid++; + ret = 0; +out: + mutex_unlock(&root->objectid_mutex); + return ret; +} |