diff options
Diffstat (limited to 'fs/btrfs/disk-io.c')
| -rw-r--r-- | fs/btrfs/disk-io.c | 3582 |
1 files changed, 2157 insertions, 1425 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c6c9a6a8e6c8..d99bf7c64611 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -7,7 +7,6 @@ #include <linux/blkdev.h> #include <linux/radix-tree.h> #include <linux/writeback.h> -#include <linux/buffer_head.h> #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/slab.h> @@ -30,7 +29,6 @@ #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" @@ -42,6 +40,9 @@ #include "ref-verify.h" #include "block-group.h" #include "discard.h" +#include "space-info.h" +#include "zoned.h" +#include "subpage.h" #define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\ BTRFS_HEADER_FLAG_RELOC |\ @@ -50,8 +51,6 @@ 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); @@ -64,38 +63,10 @@ static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, 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) +static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info) { - kmem_cache_destroy(btrfs_end_io_wq_cache); + if (fs_info->csum_shash) + crypto_free_shash(fs_info->csum_shash); } /* @@ -104,190 +75,41 @@ void __cold btrfs_end_io_wq_exit(void) * just before they are sent down the IO stack. */ struct async_submit_bio { - void *private_data; + struct inode *inode; 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; + + /* Optional parameter for submit_bio_start used by direct io */ + u64 dio_file_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. - * - * Returns error if the extent buffer cannot be mapped. */ -static int csum_tree_block(struct extent_buffer *buf, u8 *result) +static void csum_tree_block(struct extent_buffer *buf, u8 *result) { struct btrfs_fs_info *fs_info = buf->fs_info; + const int num_pages = num_extent_pages(buf); + const int first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize); SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); - unsigned long len; - unsigned long cur_len; - unsigned long offset = BTRFS_CSUM_SIZE; char *kaddr; - unsigned long map_start; - unsigned long map_len; - int err; + int i; shash->tfm = fs_info->csum_shash; crypto_shash_init(shash); + kaddr = page_address(buf->pages[0]) + offset_in_page(buf->start); + crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE, + first_page_part - BTRFS_CSUM_SIZE); - len = buf->len - offset; - - while (len > 0) { - /* - * Note: we don't need to check for the err == 1 case here, as - * with the given combination of 'start = BTRFS_CSUM_SIZE (32)' - * and 'min_len = 32' and the currently implemented mapping - * algorithm we cannot cross a page boundary. - */ - err = map_private_extent_buffer(buf, offset, 32, - &kaddr, &map_start, &map_len); - if (WARN_ON(err)) - return err; - cur_len = min(len, map_len - (offset - map_start)); - crypto_shash_update(shash, kaddr + offset - map_start, cur_len); - len -= cur_len; - offset += cur_len; + for (i = 1; i < num_pages; i++) { + kaddr = page_address(buf->pages[i]); + crypto_shash_update(shash, kaddr, PAGE_SIZE); } memset(result, 0, BTRFS_CSUM_SIZE); - crypto_shash_final(shash, result); - - return 0; } /* @@ -302,7 +124,6 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, { struct extent_state *cached_state = NULL; int ret; - bool need_lock = (current->journal_info == BTRFS_SEND_TRANS_STUB); if (!parent_transid || btrfs_header_generation(eb) == parent_transid) return 0; @@ -310,39 +131,21 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, 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); + lock_extent(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, +"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); + 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); + unlock_extent(io_tree, eb->start, eb->start + eb->len - 1, + &cached_state); return ret; } @@ -363,27 +166,23 @@ 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); shash->tfm = fs_info->csum_shash; - crypto_shash_init(shash); /* * The super_block structure does not span the whole * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space is * filled with zeros and is included in the checksum. */ - crypto_shash_update(shash, raw_disk_sb + BTRFS_CSUM_SIZE, - BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE); - crypto_shash_final(shash, result); + 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; @@ -455,9 +254,9 @@ int btrfs_verify_level_key(struct extent_buffer *eb, int level, * @level: expected level, mandatory check * @first_key: expected key of first slot, skip check if NULL */ -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, + u64 parent_transid, int level, + struct btrfs_key *first_key) { struct btrfs_fs_info *fs_info = eb->fs_info; struct extent_io_tree *io_tree; @@ -506,164 +305,202 @@ static int btree_read_extent_buffer_pages(struct extent_buffer *eb, return ret; } -/* - * 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 - */ - -static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) +static int csum_one_extent_buffer(struct extent_buffer *eb) { - u64 start = page_offset(page); - u64 found_start; + struct btrfs_fs_info *fs_info = eb->fs_info; 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; - - 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 (WARN_ON(found_start != start)) - return -EUCLEAN; - if (WARN_ON(!PageUptodate(page))) - return -EUCLEAN; - ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid, - btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0); - - if (csum_tree_block(eb, result)) - return -EINVAL; + 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); - 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. + */ + if (unlikely(btrfs_header_generation(eb) <= fs_info->last_trans_committed)) { + 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), + fs_info->last_trans_committed); + 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); + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); + return ret; } -static int check_tree_block_fsid(struct extent_buffer *eb) +/* Checksum all dirty extent buffers in one bio_vec */ +static int csum_dirty_subpage_buffers(struct btrfs_fs_info *fs_info, + struct bio_vec *bvec) { - struct btrfs_fs_info *fs_info = eb->fs_info; - struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; - u8 fsid[BTRFS_FSID_SIZE]; - int ret = 1; + struct page *page = bvec->bv_page; + u64 bvec_start = page_offset(page) + bvec->bv_offset; + u64 cur; + int ret = 0; - read_extent_buffer(eb, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE); - while (fs_devices) { - u8 *metadata_uuid; + for (cur = bvec_start; cur < bvec_start + bvec->bv_len; + cur += fs_info->nodesize) { + struct extent_buffer *eb; + bool uptodate; - /* - * 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; + eb = find_extent_buffer(fs_info, cur); + uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur, + fs_info->nodesize); - if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE)) { - ret = 0; - break; + /* A dirty eb shouldn't disappear from buffer_radix */ + if (WARN_ON(!eb)) + return -EUCLEAN; + + if (WARN_ON(cur != btrfs_header_bytenr(eb))) { + free_extent_buffer(eb); + return -EUCLEAN; + } + if (WARN_ON(!uptodate)) { + free_extent_buffer(eb); + return -EUCLEAN; } - fs_devices = fs_devices->seed; + + ret = csum_one_extent_buffer(eb); + free_extent_buffer(eb); + if (ret < 0) + return ret; } return ret; } -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) +/* + * 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. + * For subpage extent buffers we need bvec to also read the offset in the page. + */ +static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec) { + struct page *page = bvec->bv_page; + u64 start = page_offset(page); u64 found_start; - int found_level; struct extent_buffer *eb; - struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; - struct btrfs_fs_info *fs_info = root->fs_info; - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); - int ret = 0; - u8 result[BTRFS_CSUM_SIZE]; - int reads_done; - if (!page->private) - goto out; + if (fs_info->nodesize < PAGE_SIZE) + return csum_dirty_subpage_buffers(fs_info, bvec); eb = (struct extent_buffer *)page->private; + if (page != eb->pages[0]) + return 0; - /* 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 + found_start = btrfs_header_bytenr(eb); + + if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) { + WARN_ON(found_start != 0); + return 0; + } + + /* + * Please do not consolidate these warnings into a single if. + * It is useful to know what went wrong. */ - atomic_inc(&eb->refs); + if (WARN_ON(found_start != start)) + return -EUCLEAN; + if (WARN_ON(!PageUptodate(page))) + return -EUCLEAN; - reads_done = atomic_dec_and_test(&eb->io_pages); - if (!reads_done) - goto err; + return csum_one_extent_buffer(eb); +} - eb->read_mirror = mirror; - if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { - ret = -EIO; - goto err; - } +static int 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, *seed_devs; + u8 fsid[BTRFS_FSID_SIZE]; + u8 *metadata_uuid; + + read_extent_buffer(eb, fsid, offsetof(struct btrfs_header, fsid), + BTRFS_FSID_SIZE); + /* + * 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 (btrfs_fs_incompat(fs_info, METADATA_UUID)) + metadata_uuid = fs_devices->metadata_uuid; + else + metadata_uuid = fs_devices->fsid; + + if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE)) + return 0; + + list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list) + if (!memcmp(fsid, seed_devs->fsid, BTRFS_FSID_SIZE)) + return 0; + + return 1; +} + +/* Do basic extent buffer checks at read time */ +static int validate_extent_buffer(struct extent_buffer *eb) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + u64 found_start; + const u32 csum_size = fs_info->csum_size; + u8 found_level; + u8 result[BTRFS_CSUM_SIZE]; + const u8 *header_csum; + int ret = 0; 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); + 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); + 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); + 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); - - ret = csum_tree_block(eb, result); - if (ret) - goto err; - - if (memcmp_extent_buffer(eb, result, 0, csum_size)) { - u32 val; - u32 found = 0; - - memcpy(&found, result, csum_size); + csum_tree_block(eb, result); + header_csum = page_address(eb->pages[0]) + + get_eb_offset_in_page(eb, offsetof(struct btrfs_header, csum)); - 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)); +"checksum verify failed on logical %llu mirror %u wanted " CSUM_FMT " found " CSUM_FMT " level %d", + eb->start, eb->read_mirror, + CSUM_FMT_VALUE(csum_size, header_csum), + CSUM_FMT_VALUE(csum_size, result), + btrfs_header_level(eb)); ret = -EUCLEAN; - goto err; + goto out; } /* @@ -683,79 +520,106 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, 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); - } - free_extent_buffer(eb); + "read time tree block corruption detected on logical %llu mirror %u", + eb->start, eb->read_mirror); out: return ret; } -static void end_workqueue_bio(struct bio *bio) +static int validate_subpage_buffer(struct page *page, u64 start, u64 end, + int mirror) { - 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; - else - wq = fs_info->endio_write_workers; - } else { - if (unlikely(end_io_wq->metadata == BTRFS_WQ_ENDIO_DIO_REPAIR)) - wq = fs_info->endio_repair_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; + struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + struct extent_buffer *eb; + bool reads_done; + int ret = 0; + + /* + * We don't allow bio merge for subpage metadata read, so we should + * only get one eb for each endio hook. + */ + ASSERT(end == start + fs_info->nodesize - 1); + ASSERT(PagePrivate(page)); + + eb = find_extent_buffer(fs_info, start); + /* + * When we are reading one tree block, eb must have been inserted into + * the radix tree. If not, something is wrong. + */ + ASSERT(eb); + + reads_done = atomic_dec_and_test(&eb->io_pages); + /* Subpage read must finish in page read */ + ASSERT(reads_done); + + eb->read_mirror = mirror; + if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { + ret = -EIO; + goto err; } + ret = validate_extent_buffer(eb); + if (ret < 0) + goto err; - btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL); - btrfs_queue_work(wq, &end_io_wq->work); + set_extent_buffer_uptodate(eb); + + free_extent_buffer(eb); + return ret; +err: + /* + * end_bio_extent_readpage decrements io_pages in case of error, + * make sure it has something to decrement. + */ + atomic_inc(&eb->io_pages); + clear_extent_buffer_uptodate(eb); + free_extent_buffer(eb); + return ret; } -blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, - enum btrfs_wq_endio_type metadata) +int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio, + struct page *page, u64 start, u64 end, + int mirror) { - struct btrfs_end_io_wq *end_io_wq; + struct extent_buffer *eb; + int ret = 0; + int reads_done; - end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS); - if (!end_io_wq) - return BLK_STS_RESOURCE; + ASSERT(page->private); - 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; + if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE) + return validate_subpage_buffer(page, start, end, mirror); - bio->bi_private = end_io_wq; - bio->bi_end_io = end_workqueue_bio; - return 0; + eb = (struct extent_buffer *)page->private; + + /* + * 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; + + eb->read_mirror = mirror; + if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { + ret = -EIO; + goto err; + } + ret = validate_extent_buffer(eb); +err: + 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); + } + free_extent_buffer(eb); + + return ret; } static void run_one_async_start(struct btrfs_work *work) @@ -764,8 +628,8 @@ static void run_one_async_start(struct btrfs_work *work) 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); + ret = async->submit_bio_start(async->inode, async->bio, + async->dio_file_offset); if (ret) async->status = ret; } @@ -780,17 +644,14 @@ static void run_one_async_start(struct btrfs_work *work) */ 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; + struct async_submit_bio *async = + container_of(work, struct async_submit_bio, work); + struct inode *inode = async->inode; + struct btrfs_bio *bbio = btrfs_bio(async->bio); /* 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); + btrfs_bio_end_io(bbio, async->status); return; } @@ -800,11 +661,7 @@ static void run_one_async_done(struct btrfs_work *work) * 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_submit_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num); } static void run_one_async_free(struct btrfs_work *work) @@ -815,18 +672,25 @@ static void run_one_async_free(struct btrfs_work *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) +/* + * Submit bio to an async queue. + * + * Retrun: + * - true if the work has been succesfuly submitted + * - false in case of error + */ +bool btrfs_wq_submit_bio(struct inode *inode, struct bio *bio, int mirror_num, + u64 dio_file_offset, + extent_submit_bio_start_t *submit_bio_start) { + struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; struct async_submit_bio *async; async = kmalloc(sizeof(*async), GFP_NOFS); if (!async) - return BLK_STS_RESOURCE; + return false; - async->private_data = private_data; + async->inode = inode; async->bio = bio; async->mirror_num = mirror_num; async->submit_bio_start = submit_bio_start; @@ -834,15 +698,15 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, btrfs_init_work(&async->work, run_one_async_start, run_one_async_done, run_one_async_free); - async->bio_offset = bio_offset; + async->dio_file_offset = dio_file_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; + btrfs_queue_work(fs_info->hipri_workers, &async->work); + else + btrfs_queue_work(fs_info->workers, &async->work); + return true; } static blk_status_t btree_csum_one_bio(struct bio *bio) @@ -855,7 +719,7 @@ static blk_status_t btree_csum_one_bio(struct bio *bio) 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); + ret = csum_dirty_buffer(root->fs_info, bvec); if (ret) break; } @@ -863,91 +727,81 @@ static blk_status_t btree_csum_one_bio(struct bio *bio) return errno_to_blk_status(ret); } -static blk_status_t btree_submit_bio_start(void *private_data, struct bio *bio, - u64 bio_offset) +static blk_status_t btree_submit_bio_start(struct inode *inode, struct bio *bio, + u64 dio_file_offset) { /* * when we're called for a write, we're already in the async - * submission context. Just jump into btrfs_map_bio + * submission context. Just jump into btrfs_submit_bio. */ return btree_csum_one_bio(bio); } -static int check_async_write(struct btrfs_fs_info *fs_info, +static bool should_async_write(struct btrfs_fs_info *fs_info, struct btrfs_inode *bi) { + if (btrfs_is_zoned(fs_info)) + return false; if (atomic_read(&bi->sync_writers)) - return 0; + return false; if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags)) - return 0; - return 1; + return false; + return true; } -static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio, - int mirror_num, - unsigned long bio_flags) +void btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, int mirror_num) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - int async = check_async_write(fs_info, BTRFS_I(inode)); + struct btrfs_bio *bbio = btrfs_bio(bio); blk_status_t ret; - 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); + bio->bi_opf |= REQ_META; + + if (btrfs_op(bio) != BTRFS_MAP_WRITE) { + btrfs_submit_bio(fs_info, bio, mirror_num); + return; } - if (ret) - goto out_w_error; - return 0; + /* + * Kthread helpers are used to submit writes so that checksumming can + * happen in parallel across all CPUs. + */ + if (should_async_write(fs_info, BTRFS_I(inode)) && + btrfs_wq_submit_bio(inode, bio, mirror_num, 0, btree_submit_bio_start)) + return; -out_w_error: - bio->bi_status = ret; - bio_endio(bio); - return ret; + ret = btree_csum_one_bio(bio); + if (ret) { + btrfs_bio_end_io(bbio, ret); + return; + } + + btrfs_submit_bio(fs_info, bio, mirror_num); } #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) { @@ -970,114 +824,126 @@ 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) +static bool btree_release_folio(struct folio *folio, gfp_t gfp_flags) { - struct extent_io_tree *tree; - tree = &BTRFS_I(page->mapping->host)->io_tree; - return extent_read_full_page(tree, page, btree_get_extent, 0); -} - -static int btree_releasepage(struct page *page, 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->page); } -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)); - ClearPagePrivate(page); - set_page_private(page, 0); - put_page(page); + tree = &BTRFS_I(folio->mapping->host)->io_tree; + extent_invalidate_folio(tree, folio, offset); + btree_release_folio(folio, GFP_NOFS); + if (folio_get_private(folio)) { + btrfs_warn(BTRFS_I(folio->mapping->host)->root->fs_info, + "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 = btrfs_sb(mapping->host->i_sb); + 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); + } + subpage = folio_get_private(folio); + + ASSERT(subpage->dirty_bitmap); + while (cur_bit < BTRFS_SUBPAGE_BITMAP_SIZE) { + unsigned long flags; + u64 cur; + u16 tmp = (1 << cur_bit); + + spin_lock_irqsave(&subpage->lock, flags); + if (!(tmp & subpage->dirty_bitmap)) { + spin_unlock_irqrestore(&subpage->lock, flags); + cur_bit++; + 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); + } + 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. * + * @owner_root: the objectid of the root owner for this block. * @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 */ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, - u64 parent_transid, int level, - struct btrfs_key *first_key) + u64 owner_root, u64 parent_transid, + int level, struct btrfs_key *first_key) { struct extent_buffer *buf = NULL; int ret; - buf = btrfs_find_create_tree_block(fs_info, bytenr); + buf = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, 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, parent_transid, level, first_key); if (ret) { free_extent_buffer_stale(buf); return ERR_PTR(ret); } + if (btrfs_check_eb_owner(buf, owner_root)) { + free_extent_buffer_stale(buf); + return ERR_PTR(-EUCLEAN); + } return buf; } @@ -1087,61 +953,40 @@ void btrfs_clean_tree_block(struct extent_buffer *buf) struct btrfs_fs_info *fs_info = buf->fs_info; if (btrfs_header_generation(buf) == fs_info->running_transaction->transid) { - btrfs_assert_tree_locked(buf); + btrfs_assert_tree_write_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); } } } -static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void) -{ - struct btrfs_subvolume_writers *writers; - int ret; - - writers = kmalloc(sizeof(*writers), GFP_NOFS); - if (!writers) - return ERR_PTR(-ENOMEM); - - ret = percpu_counter_init(&writers->counter, 0, GFP_NOFS); - if (ret < 0) { - kfree(writers); - return ERR_PTR(ret); - } - - init_waitqueue_head(&writers->wait); - return writers; -} - -static void -btrfs_free_subvolume_writers(struct btrfs_subvolume_writers *writers) -{ - percpu_counter_destroy(&writers->counter); - kfree(writers); -} - 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); + + 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)); + root->fs_info = fs_info; + root->root_key.objectid = objectid; root->node = NULL; root->commit_root = NULL; root->state = 0; - root->orphan_cleanup_state = 0; + RB_CLEAR_NODE(&root->rb_node); root->last_trans = 0; - root->highest_objectid = 0; + root->free_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; + + btrfs_init_root_block_rsv(root); INIT_LIST_HEAD(&root->dirty_list); INIT_LIST_HEAD(&root->root_list); @@ -1163,6 +1008,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, 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]); @@ -1173,36 +1019,35 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, atomic_set(&root->log_writers, 0); atomic_set(&root->log_batch, 0); refcount_set(&root->refs, 1); - atomic_set(&root->will_be_snapshotted, 0); 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) + root->anon_dev = 0; + if (!dummy) { extent_io_tree_init(fs_info, &root->dirty_log_pages, IO_TREE_ROOT_DIRTY_LOG_PAGES, 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; + extent_io_tree_init(fs_info, &root->log_csum_range, + IO_TREE_LOG_CSUM_RANGE, NULL); + } spin_lock_init(&root->root_item_lock); btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks); +#ifdef CONFIG_BTRFS_DEBUG + INIT_LIST_HEAD(&root->leak_list); + spin_lock(&fs_info->fs_roots_radix_lock); + 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, - gfp_t flags) + u64 objectid, gfp_t flags) { struct btrfs_root *root = kzalloc(sizeof(*root), flags); if (root) - root->fs_info = fs_info; + __setup_root(root, fs_info, objectid); return root; } @@ -1215,18 +1060,113 @@ struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info) if (!fs_info) return ERR_PTR(-EINVAL); - root = btrfs_alloc_root(fs_info, GFP_KERNEL); + root = btrfs_alloc_root(fs_info, BTRFS_ROOT_TREE_OBJECTID, GFP_KERNEL); if (!root) return ERR_PTR(-ENOMEM); /* We don't use the stripesize in selftest, set it as sectorsize */ - __setup_root(root, fs_info, BTRFS_ROOT_TREE_OBJECTID); root->alloc_bytenr = 0; return root; } #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; + + 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); + ASSERT(!tmp); + + return tmp ? -EEXIST : 0; +} + +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) { @@ -1237,28 +1177,27 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, struct btrfs_key key; unsigned int nofs_flag; int ret = 0; - uuid_le uuid = NULL_UUID_LE; /* * We're holding a transaction handle, so use a NOFS memory allocation * context to avoid deadlock if reclaim happens. */ nofs_flag = memalloc_nofs_save(); - root = btrfs_alloc_root(fs_info, GFP_KERNEL); + root = btrfs_alloc_root(fs_info, objectid, GFP_KERNEL); memalloc_nofs_restore(nofs_flag); if (!root) return ERR_PTR(-ENOMEM); - __setup_root(root, fs_info, objectid); root->root_key.objectid = objectid; 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, + BTRFS_NESTING_NORMAL); if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); leaf = NULL; - goto fail; + goto fail_unlock; } root->node = leaf; @@ -1267,8 +1206,8 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, 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); @@ -1277,9 +1216,12 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, btrfs_set_root_last_snapshot(&root->root_item, 0); btrfs_set_root_dirid(&root->root_item, 0); if (is_fstree(objectid)) - uuid_le_gen(&uuid); - memcpy(root->root_item.uuid, uuid.b, BTRFS_UUID_SIZE); - root->root_item.drop_level = 0; + generate_random_guid(root->root_item.uuid); + else + export_guid(root->root_item.uuid, &guid_null); + btrfs_set_root_drop_level(&root->root_item, 0); + + btrfs_tree_unlock(leaf); key.objectid = objectid; key.type = BTRFS_ROOT_ITEM_KEY; @@ -1288,17 +1230,13 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, if (ret) goto fail; - btrfs_tree_unlock(leaf); - return root; -fail: - if (leaf) { +fail_unlock: + if (leaf) btrfs_tree_unlock(leaf); - free_extent_buffer(root->commit_root); - free_extent_buffer(leaf); - } - kfree(root); +fail: + btrfs_put_root(root); return ERR_PTR(ret); } @@ -1307,39 +1245,44 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { struct btrfs_root *root; - struct extent_buffer *leaf; - root = btrfs_alloc_root(fs_info, GFP_NOFS); + root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, GFP_NOFS); if (!root) return ERR_PTR(-ENOMEM); - __setup_root(root, fs_info, BTRFS_TREE_LOG_OBJECTID); - root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID; 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 REF_COWS for log trees + * DON'T set SHAREABLE bit for log trees. * - * log trees do not get reference counted because they go away - * before a real commit is actually done. They do store pointers - * to file data extents, and those reference counts still get - * updated (along with back refs to the log tree). + * Log trees are not exposed to user space thus can't be snapshotted, + * and they go away before a real commit is actually done. + * + * They do store pointers to file data extents, and those reference + * counts still get updated (along with back refs to the log tree). */ leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID, - NULL, 0, 0, 0); - if (IS_ERR(leaf)) { - kfree(root); - return ERR_CAST(leaf); - } + NULL, 0, 0, 0, BTRFS_NESTING_NORMAL); + if (IS_ERR(leaf)) + return PTR_ERR(leaf); root->node = leaf; btrfs_mark_buffer_dirty(root->node); btrfs_tree_unlock(root->node); - return root; + + return 0; } int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, @@ -1350,6 +1293,16 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, log_root = alloc_log_tree(trans, 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; @@ -1361,11 +1314,18 @@ 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); if (IS_ERR(log_root)) return PTR_ERR(log_root); + ret = btrfs_alloc_log_tree_node(trans, log_root); + if (ret) { + btrfs_put_root(log_root); + return ret; + } + log_root->last_trans = trans->transid; log_root->root_key.offset = root->root_key.objectid; @@ -1387,115 +1347,130 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans, return 0; } -static 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, + struct btrfs_key *key) { struct btrfs_root *root; 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) + root = btrfs_alloc_root(fs_info, key->objectid, GFP_NOFS); + if (!root) return ERR_PTR(-ENOMEM); - root = btrfs_alloc_root(fs_info, GFP_NOFS); - if (!root) { - ret = -ENOMEM; - goto alloc_fail; - } - - __setup_root(root, fs_info, key->objectid); - 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); + key->objectid, generation, level, NULL); if (IS_ERR(root->node)) { ret = PTR_ERR(root->node); - goto find_fail; - } else if (!btrfs_buffer_uptodate(root->node, generation, 0)) { + root->node = NULL; + goto fail; + } + if (!btrfs_buffer_uptodate(root->node, generation, 0)) { ret = -EIO; - free_extent_buffer(root->node); - goto find_fail; + goto fail; + } + + /* + * For real fs, and not log/reloc trees, root owner must + * match its root node owner + */ + if (!test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state) && + root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID && + root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID && + root->root_key.objectid != btrfs_header_owner(root->node)) { + btrfs_crit(fs_info, +"root=%llu block=%llu, tree root owner mismatch, have %llu expect %llu", + root->root_key.objectid, root->node->start, + btrfs_header_owner(root->node), + root->root_key.objectid); + ret = -EUCLEAN; + goto fail; } root->commit_root = btrfs_root_node(root); -out: - btrfs_free_path(path); return root; - -find_fail: - kfree(root); -alloc_fail: - root = ERR_PTR(ret); - goto out; +fail: + btrfs_put_root(root); + return ERR_PTR(ret); } -struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root, - struct btrfs_key *location) +struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, + struct btrfs_key *key) { struct btrfs_root *root; + struct btrfs_path *path; - root = btrfs_read_tree_root(tree_root, location); - if (IS_ERR(root)) - return root; - - if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { - set_bit(BTRFS_ROOT_REF_COWS, &root->state); - btrfs_check_and_init_root_item(&root->root_item); - } + path = btrfs_alloc_path(); + if (!path) + return ERR_PTR(-ENOMEM); + root = read_tree_root_path(tree_root, path, key); + btrfs_free_path(path); return root; } -int btrfs_init_fs_root(struct btrfs_root *root) +/* + * Initialize subvolume root in-memory structure + * + * @anon_dev: anonymous device to attach to the root, if zero, allocate new + */ +static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) { int ret; - struct btrfs_subvolume_writers *writers; + unsigned int nofs_flag; - 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; + /* + * 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; - } - writers = btrfs_alloc_subvolume_writers(); - if (IS_ERR(writers)) { - ret = PTR_ERR(writers); - goto fail; + if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID && + !btrfs_is_data_reloc_root(root)) { + set_bit(BTRFS_ROOT_SHAREABLE, &root->state); + btrfs_check_and_init_root_item(&root->root_item); } - root->subv_writers = writers; - - 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 (is_fstree(root->root_key.objectid) && + btrfs_root_refs(&root->root_item) > 0) { + if (!anon_dev) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto fail; + } 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; } - ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + ASSERT(root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); mutex_unlock(&root->objectid_mutex); @@ -1505,18 +1480,56 @@ fail: return ret; } -struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, - u64 root_id) +static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id) { struct btrfs_root *root; 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); 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, + }; + + if (objectid == BTRFS_ROOT_TREE_OBJECTID) + return btrfs_grab_root(fs_info->tree_root); + if (objectid == BTRFS_EXTENT_TREE_OBJECTID) + return btrfs_grab_root(btrfs_global_root(fs_info, &key)); + 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(btrfs_global_root(fs_info, &key)); + 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_BLOCK_GROUP_TREE_OBJECTID) + return btrfs_grab_root(fs_info->block_group_root) ? + fs_info->block_group_root : ERR_PTR(-ENOENT); + if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) { + struct btrfs_root *root = btrfs_global_root(fs_info, &key); + + return btrfs_grab_root(root) ? root : ERR_PTR(-ENOENT); + } + return NULL; +} + int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) { @@ -1530,51 +1543,123 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, ret = radix_tree_insert(&fs_info->fs_roots_radix, (unsigned long)root->root_key.objectid, root); - if (ret == 0) + if (ret == 0) { + btrfs_grab_root(root); set_bit(BTRFS_ROOT_IN_RADIX, &root->state); + } spin_unlock(&fs_info->fs_roots_radix_lock); radix_tree_preload_end(); return ret; } -struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, - struct btrfs_key *location, - bool check_ref) +void btrfs_check_leaked_roots(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 %s refcount %d", + btrfs_root_name(&root->root_key, buf), + refcount_read(&root->refs)); + while (refcount_read(&root->refs) > 1) + btrfs_put_root(root); + btrfs_put_root(root); + } +#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) +{ + percpu_counter_destroy(&fs_info->dirty_metadata_bytes); + percpu_counter_destroy(&fs_info->delalloc_bytes); + percpu_counter_destroy(&fs_info->ordered_bytes); + 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); + 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->quota_root); + btrfs_put_root(fs_info->uuid_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_check_leaked_roots(fs_info); + btrfs_extent_buffer_leak_debug_check(fs_info); + kfree(fs_info->super_copy); + kfree(fs_info->super_for_commit); + kfree(fs_info->subpage_info); + kvfree(fs_info); +} + + +/* + * 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 0 for 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 (location->objectid == BTRFS_ROOT_TREE_OBJECTID) - return fs_info->tree_root; - if (location->objectid == BTRFS_EXTENT_TREE_OBJECTID) - return fs_info->extent_root; - if (location->objectid == BTRFS_CHUNK_TREE_OBJECTID) - return fs_info->chunk_root; - if (location->objectid == BTRFS_DEV_TREE_OBJECTID) - return fs_info->dev_root; - if (location->objectid == BTRFS_CSUM_TREE_OBJECTID) - return fs_info->csum_root; - if (location->objectid == BTRFS_QUOTA_TREE_OBJECTID) - return fs_info->quota_root ? fs_info->quota_root : - ERR_PTR(-ENOENT); - if (location->objectid == BTRFS_UUID_TREE_OBJECTID) - return fs_info->uuid_root ? fs_info->uuid_root : - ERR_PTR(-ENOENT); - if (location->objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) - return 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; again: - root = btrfs_lookup_fs_root(fs_info, location->objectid); + root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { - if (check_ref && btrfs_root_refs(&root->root_item) == 0) + /* Shouldn't get preallocated anon_dev for cached roots */ + ASSERT(!anon_dev); + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { + btrfs_put_root(root); return ERR_PTR(-ENOENT); + } return root; } - root = btrfs_read_fs_root(fs_info->tree_root, location); + key.objectid = objectid; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + root = btrfs_read_tree_root(fs_info->tree_root, &key); if (IS_ERR(root)) return root; @@ -1583,7 +1668,7 @@ again: goto fail; } - ret = btrfs_init_fs_root(root); + ret = btrfs_init_fs_root(root, anon_dev); if (ret) goto fail; @@ -1594,7 +1679,7 @@ again: } key.objectid = BTRFS_ORPHAN_OBJECTID; key.type = BTRFS_ORPHAN_ITEM_KEY; - key.offset = location->objectid; + key.offset = objectid; ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); btrfs_free_path(path); @@ -1606,61 +1691,101 @@ again: ret = btrfs_insert_fs_root(fs_info, root); if (ret) { if (ret == -EEXIST) { - btrfs_free_fs_root(root); + btrfs_put_root(root); goto again; } goto fail; } return root; fail: - btrfs_free_fs_root(root); + /* + * 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) + 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, 0, 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 zero, allocate a new anonymous block device or use the + * parameter value + */ +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 + * btrfs_get_fs_root_commit_root - 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; + + root = btrfs_lookup_fs_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; + 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); - 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); + 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) { @@ -1693,7 +1818,7 @@ static int cleaner_kthread(void *arg) 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); /* @@ -1703,16 +1828,23 @@ 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()) @@ -1732,13 +1864,13 @@ 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 = msecs_to_jiffies(fs_info->commit_interval * 1000); mutex_lock(&fs_info->transaction_kthread_mutex); spin_lock(&fs_info->trans_lock); @@ -1748,13 +1880,14 @@ 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_START && + delta < fs_info->commit_interval) { spin_unlock(&fs_info->trans_lock); - delay = HZ * 5; + delay -= msecs_to_jiffies((delta - 1) * 1000); + delay = min(delay, + msecs_to_jiffies(fs_info->commit_interval * 1000)); goto sleep; } transid = cur->transid; @@ -1776,8 +1909,7 @@ 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) || @@ -1846,11 +1978,23 @@ 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 @@ -1871,12 +2015,6 @@ 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, @@ -1942,16 +2080,20 @@ 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->hipri_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->endio_repair_workers); - btrfs_destroy_workqueue(fs_info->rmw_workers); + if (fs_info->endio_workers) + destroy_workqueue(fs_info->endio_workers); + if (fs_info->endio_raid56_workers) + destroy_workqueue(fs_info->endio_raid56_workers); + if (fs_info->rmw_workers) + destroy_workqueue(fs_info->rmw_workers); + if (fs_info->compressed_write_workers) + destroy_workqueue(fs_info->compressed_write_workers); btrfs_destroy_workqueue(fs_info->endio_write_workers); btrfs_destroy_workqueue(fs_info->endio_freespace_worker); btrfs_destroy_workqueue(fs_info->delayed_workers); btrfs_destroy_workqueue(fs_info->caching_workers); - btrfs_destroy_workqueue(fs_info->readahead_workers); btrfs_destroy_workqueue(fs_info->flush_workers); btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers); if (fs_info->discard_ctl.discard_workers) @@ -1961,8 +2103,8 @@ 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) @@ -1975,19 +2117,51 @@ 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); 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) +{ + if (!root) + return; + + if (refcount_dec_and_test(&root->refs)) { + WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree)); + 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_root_extent_buffers(root); +#ifdef CONFIG_BTRFS_DEBUG + spin_lock(&root->fs_info->fs_roots_radix_lock); + list_del_init(&root->leak_list); + spin_unlock(&root->fs_info->fs_roots_radix_lock); +#endif + kfree(root); + } } void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info) @@ -2001,13 +2175,9 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info) struct btrfs_root, root_list); list_del(&gang[0]->root_list); - if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state)) { + if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state)) btrfs_drop_and_free_fs_root(fs_info, gang[0]); - } else { - free_extent_buffer(gang[0]->node); - free_extent_buffer(gang[0]->commit_root); - btrfs_put_fs_root(gang[0]); - } + btrfs_put_root(gang[0]); } while (1) { @@ -2019,11 +2189,6 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info) for (i = 0; i < ret; i++) btrfs_drop_and_free_fs_root(fs_info, gang[i]); } - - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { - btrfs_free_log_root_tree(NULL, fs_info); - btrfs_destroy_pinned_extent(fs_info, fs_info->pinned_extents); - } } static void btrfs_init_scrub(struct btrfs_fs_info *fs_info) @@ -2045,11 +2210,14 @@ 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) { struct inode *inode = fs_info->btree_inode; + unsigned long hash = btrfs_inode_hash(BTRFS_BTREE_INODE_OBJECTID, + fs_info->tree_root); inode->i_ino = BTRFS_BTREE_INODE_OBJECTID; set_nlink(inode, 1); @@ -2063,16 +2231,15 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info) 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; + IO_TREE_BTREE_INODE_IO, NULL); extent_map_tree_init(&BTRFS_I(inode)->extent_tree); - BTRFS_I(inode)->io_tree.ops = &btree_extent_io_ops; - - BTRFS_I(inode)->root = fs_info->tree_root; - memset(&BTRFS_I(inode)->location, 0, sizeof(struct btrfs_key)); + BTRFS_I(inode)->root = btrfs_grab_root(fs_info->tree_root); + BTRFS_I(inode)->location.objectid = BTRFS_BTREE_INODE_OBJECTID; + BTRFS_I(inode)->location.type = 0; + BTRFS_I(inode)->location.offset = 0; set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags); - btrfs_insert_inode_hash(inode); + __insert_inode_hash(inode, hash); } static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info) @@ -2091,17 +2258,19 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) fs_info->qgroup_seq = 1; fs_info->qgroup_ulist = NULL; fs_info->qgroup_rescan_running = false; + fs_info->qgroup_drop_subtree_thres = BTRFS_MAX_LEVEL; 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; fs_info->workers = - btrfs_alloc_workqueue(fs_info, "worker", + btrfs_alloc_workqueue(fs_info, "worker", flags, max_active, 16); + fs_info->hipri_workers = + btrfs_alloc_workqueue(fs_info, "worker-high", flags | WQ_HIGHPRI, max_active, 16); fs_info->delalloc_workers = @@ -2118,52 +2287,37 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, fs_info->fixup_workers = btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0); - /* - * 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); + alloc_workqueue("btrfs-endio-meta", flags, max_active); fs_info->endio_raid56_workers = - btrfs_alloc_workqueue(fs_info, "endio-raid56", flags, - max_active, 4); - fs_info->endio_repair_workers = - btrfs_alloc_workqueue(fs_info, "endio-repair", flags, 1, 0); - fs_info->rmw_workers = - btrfs_alloc_workqueue(fs_info, "rmw", flags, max_active, 2); + alloc_workqueue("btrfs-endio-raid56", 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); + fs_info->compressed_write_workers = + alloc_workqueue("btrfs-compressed-write", flags, max_active); fs_info->endio_freespace_worker = btrfs_alloc_workqueue(fs_info, "freespace-write", flags, max_active, 0); 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); fs_info->discard_ctl.discard_workers = alloc_workqueue("btrfs_discard", WQ_UNBOUND | WQ_FREEZABLE, 1); - if (!(fs_info->workers && fs_info->delalloc_workers && - fs_info->flush_workers && + if (!(fs_info->workers && fs_info->hipri_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_repair_workers && + fs_info->compressed_write_workers && fs_info->endio_write_workers && fs_info->endio_raid56_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; } @@ -2186,14 +2340,12 @@ static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) fs_info->csum_shash = csum_shash; + btrfs_info(fs_info, "using %s (%s) checksum algorithm", + btrfs_super_csum_name(csum_type), + crypto_shash_driver_name(csum_shash)); return 0; } -static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info) -{ - crypto_free_shash(fs_info->csum_shash); -} - static int btrfs_replay_log(struct btrfs_fs_info *fs_info, struct btrfs_fs_devices *fs_devices) { @@ -2208,33 +2360,34 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, return -EIO; } - log_tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL); + log_tree_root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, + GFP_KERNEL); if (!log_tree_root) return -ENOMEM; - __setup_root(log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID); - log_tree_root->node = read_tree_block(fs_info, bytenr, - fs_info->generation + 1, - level, NULL); + BTRFS_TREE_LOG_OBJECTID, + fs_info->generation + 1, level, + NULL); if (IS_ERR(log_tree_root->node)) { btrfs_warn(fs_info, "failed to read log tree"); ret = PTR_ERR(log_tree_root->node); - kfree(log_tree_root); + log_tree_root->node = NULL; + btrfs_put_root(log_tree_root); return ret; - } else if (!extent_buffer_uptodate(log_tree_root->node)) { + } + if (!extent_buffer_uptodate(log_tree_root->node)) { btrfs_err(fs_info, "failed to read log tree"); - free_extent_buffer(log_tree_root->node); - kfree(log_tree_root); + btrfs_put_root(log_tree_root); return -EIO; } + /* returns with log_tree_root freed on success */ ret = btrfs_recover_log_trees(log_tree_root); if (ret) { btrfs_handle_fs_error(fs_info, ret, "Failed to recover log tree"); - free_extent_buffer(log_tree_root->node); - kfree(log_tree_root); + btrfs_put_root(log_tree_root); return ret; } @@ -2247,6 +2400,115 @@ 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_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)) { + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) + 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_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) +{ + struct btrfs_path *path; + int ret = 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + ret = load_global_roots_objectid(tree_root, path, + BTRFS_EXTENT_TREE_OBJECTID, "extent"); + if (ret) + goto out; + ret = load_global_roots_objectid(tree_root, path, + BTRFS_CSUM_TREE_OBJECTID, "csum"); + if (ret) + goto out; + if (!btrfs_fs_compat_ro(tree_root->fs_info, FREE_SPACE_TREE)) + goto out; + ret = load_global_roots_objectid(tree_root, path, + BTRFS_FREE_SPACE_TREE_OBJECTID, + "free space"); +out: + btrfs_free_path(path); + return ret; +} + static int btrfs_read_roots(struct btrfs_fs_info *fs_info) { struct btrfs_root *tree_root = fs_info->tree_root; @@ -2256,36 +2518,58 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) BUG_ON(!fs_info->tree_root); - location.objectid = BTRFS_EXTENT_TREE_OBJECTID; + ret = load_global_roots(tree_root); + if (ret) + return ret; + 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); + /* Initialize fs_info for all devices in any case */ + ret = btrfs_init_devices_late(fs_info); + if (ret) + goto out; - location.objectid = BTRFS_CSUM_TREE_OBJECTID; - root = btrfs_read_tree_root(tree_root, &location); + /* + * This tree can share blocks with some other fs tree during relocation + * and we need a proper setup by btrfs_get_fs_root + */ + root = btrfs_get_fs_root(tree_root->fs_info, + BTRFS_DATA_RELOC_TREE_OBJECTID, true); if (IS_ERR(root)) { - 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->csum_root = root; location.objectid = BTRFS_QUOTA_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); @@ -2298,23 +2582,14 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) 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; - } 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; - 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; + if (ret != -ENOENT) + goto out; } + } else { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - fs_info->free_space_root = root; + fs_info->uuid_root = root; } return 0; @@ -2334,8 +2609,8 @@ 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(struct btrfs_fs_info *fs_info, + struct btrfs_super_block *sb, int mirror_num) { u64 nodesize = btrfs_super_nodesize(sb); u64 sectorsize = btrfs_super_sectorsize(sb); @@ -2375,13 +2650,22 @@ static int validate_super(struct btrfs_fs_info *fs_info, btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize); ret = -EINVAL; } - /* Only PAGE SIZE is supported yet */ - if (sectorsize != PAGE_SIZE) { + + /* + * We only support at most two sectorsizes: 4K and PAGE_SIZE. + * + * We can support 16K sectorsize with 64K page size without problem, + * but such sectorsize/pagesize combination doesn't make much sense. + * 4K will be our future standard, PAGE_SIZE is supported from the very + * beginning. + */ + if (sectorsize > PAGE_SIZE || (sectorsize != SZ_4K && sectorsize != PAGE_SIZE)) { 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); @@ -2410,6 +2694,36 @@ static int validate_super(struct btrfs_fs_info *fs_info, ret = -EINVAL; } + if (memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid, + BTRFS_FSID_SIZE)) { + btrfs_err(fs_info, + "superblock fsid doesn't match fsid of fs_devices: %pU != %pU", + fs_info->super_copy->fsid, fs_info->fs_devices->fsid); + ret = -EINVAL; + } + + if (btrfs_fs_incompat(fs_info, METADATA_UUID) && + memcmp(fs_info->fs_devices->metadata_uuid, + fs_info->super_copy->metadata_uuid, BTRFS_FSID_SIZE)) { + btrfs_err(fs_info, +"superblock metadata_uuid doesn't match metadata uuid of fs_devices: %pU != %pU", + fs_info->super_copy->metadata_uuid, + fs_info->fs_devices->metadata_uuid); + ret = -EINVAL; + } + + /* + * Artificial requirement for block-group-tree to force newer features + * (free-space-tree, no-holes) so the test matrix is smaller. + */ + if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE) && + (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID) || + !btrfs_fs_incompat(fs_info, NO_HOLES))) { + btrfs_err(fs_info, + "block-group-tree feature requires fres-space-tree and no-holes"); + ret = -EINVAL; + } + if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) { btrfs_err(fs_info, @@ -2492,7 +2806,7 @@ 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); } /* @@ -2506,7 +2820,7 @@ 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))) { @@ -2530,6 +2844,46 @@ out: return ret; } +static int load_super_root(struct btrfs_root *root, u64 bytenr, u64 gen, int level) +{ + int ret = 0; + + root->node = read_tree_block(root->fs_info, bytenr, + root->root_key.objectid, gen, level, NULL); + if (IS_ERR(root->node)) { + ret = PTR_ERR(root->node); + root->node = NULL; + return ret; + } + if (!extent_buffer_uptodate(root->node)) { + free_extent_buffer(root->node); + root->node = NULL; + return -EIO; + } + + 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); @@ -2540,9 +2894,6 @@ 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); @@ -2567,39 +2918,24 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) 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) { @@ -2608,8 +2944,9 @@ 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); + fs_info->last_trans_committed = fs_info->generation; + fs_info->last_reloc_trans = 0; /* Always begin writing backup roots after the one being used */ if (backup_index < 0) { @@ -2624,67 +2961,8 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) return ret; } -int __cold open_ctree(struct super_block *sb, - struct btrfs_fs_devices *fs_devices, - char *options) +void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) { - u32 sectorsize; - u32 nodesize; - u32 stripesize; - u64 generation; - u64 features; - u16 csum_type; - struct btrfs_key location; - struct buffer_head *bh; - 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; - - tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL); - chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL); - if (!tree_root || !chunk_root) { - err = -ENOMEM; - goto fail; - } - - ret = init_srcu_struct(&fs_info->subvol_srcu); - if (ret) { - err = ret; - goto fail; - } - - ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL); - if (ret) { - err = ret; - goto fail_srcu; - } - - ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); - if (ret) { - err = ret; - goto fail_dio_bytes; - } - fs_info->dirty_metadata_batch = PAGE_SIZE * - (1 + ilog2(nr_cpu_ids)); - - ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL); - if (ret) { - err = ret; - goto fail_dirty_metadata_bytes; - } - - ret = percpu_counter_init(&fs_info->dev_replace.bio_counter, 0, - GFP_KERNEL); - if (ret) { - err = ret; - goto fail_delalloc_bytes; - } - INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC); INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC); INIT_LIST_HEAD(&fs_info->trans_list); @@ -2700,17 +2978,43 @@ int __cold open_ctree(struct super_block *sb, 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_start, + BTRFS_LOCKDEP_TRANS_COMMIT_START); + 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); btrfs_init_block_rsv(&fs_info->global_block_rsv, BTRFS_BLOCK_RSV_GLOBAL); @@ -2724,10 +3028,9 @@ int __cold open_ctree(struct super_block *sb, 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->sb = sb; + 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; @@ -2735,9 +3038,6 @@ int __cold open_ctree(struct super_block *sb, 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, @@ -2746,43 +3046,18 @@ int __cold open_ctree(struct super_block *sb, INIT_LIST_HEAD(&fs_info->ordered_roots); spin_lock_init(&fs_info->ordered_root_lock); - fs_info->btree_inode = new_inode(sb); - if (!fs_info->btree_inode) { - err = -ENOMEM; - goto fail_bio_counter; - } - mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS); - - fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root), - GFP_KERNEL); - if (!fs_info->delayed_root) { - err = -ENOMEM; - goto fail_iput; - } - btrfs_init_delayed_root(fs_info->delayed_root); - 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); - - sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE; - sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE); - - btrfs_init_btree_inode(fs_info); + btrfs_init_async_reclaim_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->freed_extents[0], - IO_TREE_FS_INFO_FREED_EXTENTS0, NULL); - extent_io_tree_init(fs_info, &fs_info->freed_extents[1], - IO_TREE_FS_INFO_FREED_EXTENTS1, NULL); - fs_info->pinned_extents = &fs_info->freed_extents[0]; - set_bit(BTRFS_FS_BARRIER, &fs_info->flags); + extent_io_tree_init(fs_info, &fs_info->excluded_extents, + IO_TREE_FS_EXCLUDED_EXTENTS, NULL); mutex_init(&fs_info->ordered_operations_mutex); mutex_init(&fs_info->tree_log_mutex); @@ -2811,48 +3086,392 @@ int __cold open_ctree(struct super_block *sb, /* 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; + 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) +{ + int ret; + + fs_info->sb = sb; + sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE; + sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE); + + ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL); + if (ret) + return ret; + + ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); + if (ret) + return ret; + + fs_info->dirty_metadata_batch = PAGE_SIZE * + (1 + ilog2(nr_cpu_ids)); + + ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL); + if (ret) + return ret; + + ret = percpu_counter_init(&fs_info->dev_replace.bio_counter, 0, + GFP_KERNEL); + if (ret) + return ret; + + fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root), + GFP_KERNEL); + if (!fs_info->delayed_root) + return -ENOMEM; + btrfs_init_delayed_root(fs_info->delayed_root); + + if (sb_rdonly(sb)) + set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state); + + return btrfs_alloc_stripe_hash_table(fs_info); +} + +static int btrfs_uuid_rescan_kthread(void *data) +{ + struct btrfs_fs_info *fs_info = data; + int ret; + + /* + * 1st step is to iterate through the existing UUID tree and + * to delete all entries that contain outdated data. + * 2nd step is to add all missing entries to the UUID tree. + */ + ret = btrfs_uuid_tree_iterate(fs_info); + if (ret < 0) { + if (ret != -EINTR) + btrfs_warn(fs_info, "iterating uuid_tree failed %d", + ret); + up(&fs_info->uuid_tree_rescan_sem); + return ret; + } + return btrfs_uuid_scan_kthread(data); +} + +static int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info) +{ + struct task_struct *task; + + down(&fs_info->uuid_tree_rescan_sem); + task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid"); + if (IS_ERR(task)) { + /* fs_info->update_uuid_tree_gen remains 0 in all error case */ + btrfs_warn(fs_info, "failed to start uuid_rescan task"); + up(&fs_info->uuid_tree_rescan_sem); + return PTR_ERR(task); + } + + return 0; +} + +/* + * Some options only have meaning at mount time and shouldn't persist across + * remounts, or be displayed. Clear these at the end of mount and remount + * code paths. + */ +void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info) +{ + btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT); + btrfs_clear_opt(fs_info->mount_opt, CLEAR_CACHE); +} + +/* + * 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 clear_free_space_tree = false; + + if (btrfs_test_opt(fs_info, CLEAR_CACHE) && + btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { + clear_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"); + clear_free_space_tree = true; + } + + 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); + 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. + * + * 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, struct super_block *sb) +{ + 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 && !sb_rdonly(sb)) { + btrfs_err(fs_info, + "cannot mount read-write because of unknown compat_ro features (0x%llx)", + compat_ro); + return -EINVAL; + } + + /* + * We have unsupported RO compat features, although RO mounted, we + * should not cause any metadata writes, including log replay. + * Or we could screw up whatever the new feature requires. + */ + if (compat_ro_unsupp && btrfs_super_log_root(disk_super) && + !btrfs_test_opt(fs_info, NOLOGREPLAY)) { + btrfs_err(fs_info, +"cannot replay dirty log with unsupported compat_ro features (0x%llx), try rescue=nologreplay", + compat_ro); + return -EINVAL; + } + + /* + * Artificial limitations for block group tree, to force + * block-group-tree to rely on no-holes and free-space-tree. + */ + if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE) && + (!btrfs_fs_incompat(fs_info, NO_HOLES) || + !btrfs_test_opt(fs_info, FREE_SPACE_TREE))) { + btrfs_err(fs_info, +"block-group-tree feature requires no-holes and free-space-tree features"); + return -EINVAL; + } + + /* + * Subpage runtime limitation on v1 cache. + * + * V1 space cache still has some hard codeed PAGE_SIZE usage, while + * we're already defaulting to v2 cache, no need to bother v1 as it's + * going to be deprecated anyway. + */ + if (fs_info->sectorsize < PAGE_SIZE && btrfs_test_opt(fs_info, SPACE_CACHE)) { + btrfs_warn(fs_info, + "v1 space cache is not supported for page size %lu with sectorsize %u", + PAGE_SIZE, fs_info->sectorsize); + return -EINVAL; + } + + /* This can be called by remount, we need to protect the super block. */ + spin_lock(&fs_info->super_lock); + btrfs_set_super_incompat_flags(disk_super, incompat); + spin_unlock(&fs_info->super_lock); + + return 0; +} + +int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, + char *options) +{ + 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 level; - ret = btrfs_alloc_stripe_hash_table(fs_info); + ret = init_mount_fs_info(fs_info, sb); if (ret) { err = ret; - goto fail_alloc; + goto fail; + } + + /* These need to be init'ed before we start creating inodes and such. */ + tree_root = btrfs_alloc_root(fs_info, BTRFS_ROOT_TREE_OBJECTID, + GFP_KERNEL); + fs_info->tree_root = tree_root; + chunk_root = btrfs_alloc_root(fs_info, BTRFS_CHUNK_TREE_OBJECTID, + GFP_KERNEL); + fs_info->chunk_root = chunk_root; + if (!tree_root || !chunk_root) { + err = -ENOMEM; + goto fail; } - __setup_root(tree_root, fs_info, BTRFS_ROOT_TREE_OBJECTID); + fs_info->btree_inode = new_inode(sb); + if (!fs_info->btree_inode) { + err = -ENOMEM; + 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 */ - bh = btrfs_read_dev_super(fs_devices->latest_bdev); - if (IS_ERR(bh)) { - err = PTR_ERR(bh); + disk_super = btrfs_read_dev_super(fs_devices->latest_dev->bdev); + if (IS_ERR(disk_super)) { + err = PTR_ERR(disk_super); goto fail_alloc; } /* - * 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((struct btrfs_super_block *)bh->b_data); + 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; - brelse(bh); + 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; } @@ -2860,11 +3479,11 @@ int __cold open_ctree(struct super_block *sb, * 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, bh->b_data)) { + if (btrfs_check_super_csum(fs_info, disk_super)) { btrfs_err(fs_info, "superblock checksum mismatch"); err = -EINVAL; - brelse(bh); - goto fail_csum; + btrfs_release_disk_super(disk_super); + goto fail_alloc; } /* @@ -2872,19 +3491,11 @@ int __cold open_ctree(struct super_block *sb, * following bytes up to INFO_SIZE, the checksum is calculated from * the whole block of INFO_SIZE */ - memcpy(fs_info->super_copy, bh->b_data, sizeof(*fs_info->super_copy)); - brelse(bh); + memcpy(fs_info->super_copy, disk_super, sizeof(*fs_info->super_copy)); + btrfs_release_disk_super(disk_super); 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) { @@ -2901,11 +3512,11 @@ int __cold open_ctree(struct super_block *sb, if (ret) { btrfs_err(fs_info, "superblock contains fatal errors"); err = -EINVAL; - goto fail_csum; + goto fail_alloc; } if (!btrfs_super_root(disk_super)) - goto fail_csum; + goto fail_alloc; /* check FS state, whether FS is broken. */ if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR) @@ -2917,92 +3528,62 @@ int __cold open_ctree(struct super_block *sb, */ fs_info->compress_type = BTRFS_COMPRESS_ZLIB; - ret = btrfs_parse_options(fs_info, options, sb->s_flags); - if (ret) { - err = ret; - goto fail_csum; - } - - 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_csum; - } - - 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; - } + /* 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->sectorsize = sectorsize; + fs_info->sectorsize_bits = ilog2(sectorsize); + fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size; fs_info->stripesize = stripesize; - /* - * mixed block groups end up with duplicate but slightly offset - * extent buffers for the same range. It leads to corruptions - */ - 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); - goto fail_csum; + ret = btrfs_parse_options(fs_info, options, sb->s_flags); + if (ret) { + err = ret; + goto fail_alloc; } - /* - * Needn't use the lock because there is no other task which will - * update the flag. - */ - btrfs_set_super_incompat_flags(disk_super, features); + ret = btrfs_check_features(fs_info, sb); + if (ret < 0) { + err = ret; + goto fail_alloc; + } - 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_csum; + if (sectorsize < PAGE_SIZE) { + struct btrfs_subpage_info *subpage_info; + + /* + * V1 space cache has some hardcoded PAGE_SIZE usage, and is + * going to be deprecated. + * + * Force to use v2 cache for subpage case. + */ + btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE); + btrfs_set_and_info(fs_info, FREE_SPACE_TREE, + "forcing free space tree for sector size %u with page size %lu", + sectorsize, PAGE_SIZE); + + btrfs_warn(fs_info, + "read-write for sector size %u with page size %lu is experimental", + sectorsize, PAGE_SIZE); + subpage_info = kzalloc(sizeof(*subpage_info), GFP_KERNEL); + if (!subpage_info) + goto fail_alloc; + btrfs_init_subpage_info(subpage_info, sectorsize); + fs_info->subpage_info = subpage_info; } - ret = btrfs_init_workqueues(fs_info, fs_devices); + ret = btrfs_init_workqueues(fs_info); if (ret) { err = 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); @@ -3020,25 +3601,16 @@ int __cold open_ctree(struct super_block *sb, generation = btrfs_super_chunk_root_generation(disk_super); level = btrfs_super_chunk_root_level(disk_super); - - __setup_root(chunk_root, fs_info, BTRFS_CHUNK_TREE_OBJECTID); - - 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, - btrfs_header_chunk_tree_uuid(chunk_root->node), BTRFS_UUID_SIZE); + offsetof(struct btrfs_header, chunk_tree_uuid), + BTRFS_UUID_SIZE); ret = btrfs_read_chunk_tree(fs_info); if (ret) { @@ -3047,12 +3619,14 @@ int __cold open_ctree(struct super_block *sb, } /* - * 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 (!fs_devices->latest_dev->bdev) { btrfs_err(fs_info, "failed to read devices"); goto fail_tree_roots; } @@ -3061,6 +3635,31 @@ int __cold open_ctree(struct super_block *sb, if (ret) goto fail_tree_roots; + /* + * Get zone type information of zoned block devices. This will also + * handle emulation of a zoned filesystem if a regular device has the + * zoned incompat feature flag set. + */ + ret = btrfs_get_dev_zone_info_all_devices(fs_info); + if (ret) { + btrfs_err(fs_info, + "zoned: failed to read device zone info: %d", + ret); + goto fail_block_groups; + } + + /* + * If we have a uuid root and we're not being told to rescan we need to + * check the generation here so we can set the + * BTRFS_FS_UPDATE_UUID_TREE_GEN bit. Otherwise we could commit the + * transaction during a balance or the log replay without updating the + * uuid generation, and then if we crash we would rescan the uuid tree, + * even though it was perfectly fine. + */ + if (fs_info->uuid_root && !btrfs_test_opt(fs_info, RESCAN_UUID_TREE) && + fs_info->generation == btrfs_super_uuid_tree_generation(disk_super)) + set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags); + ret = btrfs_verify_dev_extents(fs_info); if (ret) { btrfs_err(fs_info, @@ -3086,7 +3685,12 @@ int __cold open_ctree(struct super_block *sb, 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) { @@ -3113,13 +3717,16 @@ int __cold open_ctree(struct super_block *sb, goto fail_sysfs; } - if (!sb_rdonly(sb) && !btrfs_check_rw_degradable(fs_info, NULL)) { + btrfs_free_zone_cache(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"); 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)) goto fail_sysfs; @@ -3145,8 +3752,7 @@ int __cold open_ctree(struct super_block *sb, 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, + CHECK_INTEGRITY_DATA) ? 1 : 0, fs_info->check_integrity_print_mask); if (ret) btrfs_warn(fs_info, @@ -3172,31 +3778,7 @@ int __cold open_ctree(struct super_block *sb, } } - 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; - } - } - - location.objectid = BTRFS_FS_TREE_OBJECTID; - location.type = BTRFS_ROOT_ITEM_KEY; - location.offset = 0; - - fs_info->fs_root = btrfs_read_fs_root_no_name(fs_info, &location); + 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); @@ -3205,78 +3787,18 @@ int __cold open_ctree(struct super_block *sb, } 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; - } + goto clear_oneshot; - 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) { @@ -3285,17 +3807,16 @@ int __cold open_ctree(struct super_block *sb, close_ctree(fs_info); return ret; } - } else { - set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags); } + 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); +clear_oneshot: + btrfs_clear_oneshot_options(fs_info); return 0; fail_qgroup: @@ -3323,96 +3844,110 @@ 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); fail_sb_buffer: btrfs_stop_all_workers(fs_info); btrfs_free_block_groups(fs_info); -fail_csum: - btrfs_free_csum_hash(fs_info); fail_alloc: -fail_iput: btrfs_mapping_tree_free(&fs_info->mapping_tree); iput(fs_info->btree_inode); -fail_bio_counter: - percpu_counter_destroy(&fs_info->dev_replace.bio_counter); -fail_delalloc_bytes: - percpu_counter_destroy(&fs_info->delalloc_bytes); -fail_dirty_metadata_bytes: - percpu_counter_destroy(&fs_info->dirty_metadata_bytes); -fail_dio_bytes: - percpu_counter_destroy(&fs_info->dio_bytes); -fail_srcu: - cleanup_srcu_struct(&fs_info->subvol_srcu); fail: - btrfs_free_stripe_hash_table(fs_info); btrfs_close_devices(fs_info->fs_devices); return err; } ALLOW_ERROR_INJECTION(open_ctree, ERRNO); -static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) +static void btrfs_end_super_write(struct bio *bio) { - if (uptodate) { - set_buffer_uptodate(bh); - } else { - struct btrfs_device *device = (struct btrfs_device *) - bh->b_private; - - btrfs_warn_rl_in_rcu(device->fs_info, - "lost page write due to IO error on %s", - rcu_str_deref(device->name)); - /* note, we don't set_buffer_write_io_error because we have - * our own ways of dealing with the IO errors - */ - clear_buffer_uptodate(bh); - btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_WRITE_ERRS); + 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; + + 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), + 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); + } + + put_page(page); + unlock_page(page); } - unlock_buffer(bh); - put_bh(bh); + + bio_put(bio); } -int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num, - struct buffer_head **bh_ret) +struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev, + int copy_num, bool drop_cache) { - struct buffer_head *bh; struct btrfs_super_block *super; - u64 bytenr; + struct page *page; + u64 bytenr, bytenr_orig; + struct address_space *mapping = bdev->bd_inode->i_mapping; + int ret; - bytenr = btrfs_sb_offset(copy_num); - if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode)) - return -EINVAL; + bytenr_orig = btrfs_sb_offset(copy_num); + ret = btrfs_sb_log_location_bdev(bdev, copy_num, READ, &bytenr); + if (ret == -ENOENT) + return ERR_PTR(-EINVAL); + else if (ret) + return ERR_PTR(ret); - bh = __bread(bdev, bytenr / BTRFS_BDEV_BLOCKSIZE, BTRFS_SUPER_INFO_SIZE); - /* - * If we fail to read from the underlying devices, as of now - * the best option we have is to mark it EIO. - */ - if (!bh) - return -EIO; + if (bytenr + BTRFS_SUPER_INFO_SIZE >= bdev_nr_bytes(bdev)) + return ERR_PTR(-EINVAL); - super = (struct btrfs_super_block *)bh->b_data; - if (btrfs_super_bytenr(super) != bytenr || - btrfs_super_magic(super) != BTRFS_MAGIC) { - brelse(bh); - return -EINVAL; + if (drop_cache) { + /* This should only be called with the primary sb. */ + ASSERT(copy_num == 0); + + /* + * Drop the page of the primary superblock, so later read will + * always read from the device. + */ + invalidate_inode_pages2_range(mapping, + bytenr >> PAGE_SHIFT, + (bytenr + BTRFS_SUPER_INFO_SIZE) >> PAGE_SHIFT); } - *bh_ret = bh; - return 0; + 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_magic(super) != BTRFS_MAGIC) { + btrfs_release_disk_super(super); + return ERR_PTR(-ENODATA); + } + + if (btrfs_super_bytenr(super) != bytenr_orig) { + btrfs_release_disk_super(super); + return ERR_PTR(-EINVAL); + } + + return super; } -struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) +struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev) { - struct buffer_head *bh; - struct buffer_head *latest = NULL; - struct btrfs_super_block *super; + struct btrfs_super_block *super, *latest = NULL; int i; u64 transid = 0; - int ret = -EINVAL; /* we would like to check all the supers, but that would make * a btrfs mount succeed after a mkfs from a different FS. @@ -3420,48 +3955,42 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) * later supers, using BTRFS_SUPER_MIRROR_MAX instead */ for (i = 0; i < 1; i++) { - ret = btrfs_read_dev_one_super(bdev, i, &bh); - if (ret) + super = btrfs_read_dev_one_super(bdev, i, false); + if (IS_ERR(super)) continue; - super = (struct btrfs_super_block *)bh->b_data; - if (!latest || btrfs_super_generation(super) > transid) { - brelse(latest); - latest = bh; + if (latest) + btrfs_release_disk_super(super); + + latest = super; transid = btrfs_super_generation(super); - } else { - brelse(bh); } } - if (!latest) - return ERR_PTR(ret); - - return latest; + return super; } /* * Write superblock @sb to the @device. Do not wait for completion, all the - * buffer heads we write are pinned. + * pages 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 buffer head is not found or submission fails. + * Return number of errors when page 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; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); - struct buffer_head *bh; int i; - int ret; int errors = 0; - u64 bytenr; - int op_flags; + int ret; + u64 bytenr, bytenr_orig; if (max_mirrors == 0) max_mirrors = BTRFS_SUPER_MIRROR_MAX; @@ -3469,48 +3998,73 @@ static int write_dev_supers(struct btrfs_device *device, shash->tfm = fs_info->csum_shash; for (i = 0; i < max_mirrors; i++) { - bytenr = btrfs_sb_offset(i); + struct page *page; + struct bio *bio; + struct btrfs_super_block *disk_super; + + 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", + i); + 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_init(shash); - crypto_shash_update(shash, (const char *)sb + BTRFS_CSUM_SIZE, - BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE); - crypto_shash_final(shash, sb->csum); + crypto_shash_digest(shash, (const char *)sb + BTRFS_CSUM_SIZE, + BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, + sb->csum); - /* One reference for us, and we leave it for the caller */ - bh = __getblk(device->bdev, bytenr / BTRFS_BDEV_BLOCKSIZE, - BTRFS_SUPER_INFO_SIZE); - if (!bh) { + page = find_or_create_page(mapping, bytenr >> PAGE_SHIFT, + GFP_NOFS); + if (!page) { btrfs_err(device->fs_info, - "couldn't get super buffer head for bytenr %llu", + "couldn't get super block page for bytenr %llu", bytenr); errors++; continue; } - memcpy(bh->b_data, sb, BTRFS_SUPER_INFO_SIZE); + /* Bump the refcount for wait_dev_supers() */ + get_page(page); - /* one reference for submit_bh */ - get_bh(bh); + disk_super = page_address(page); + memcpy(disk_super, sb, BTRFS_SUPER_INFO_SIZE); - set_buffer_uptodate(bh); - lock_buffer(bh); - bh->b_end_io = btrfs_end_buffer_write_sync; - bh->b_private = device; + /* + * Directly use bios here instead of relying on the page cache + * to do I/O, so we don't lose the ability to do integrity + * checking. + */ + bio = bio_alloc(device->bdev, 1, + REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, + GFP_NOFS); + bio->bi_iter.bi_sector = bytenr >> SECTOR_SHIFT; + bio->bi_private = device; + bio->bi_end_io = btrfs_end_super_write; + __bio_add_page(bio, page, BTRFS_SUPER_INFO_SIZE, + offset_in_page(bytenr)); /* - * we fua the first super. The others we allow - * to go down lazy. + * 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. */ - op_flags = REQ_SYNC | REQ_META | REQ_PRIO; if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER)) - op_flags |= REQ_FUA; - ret = btrfsic_submit_bh(REQ_OP_WRITE, op_flags, bh); - if (ret) + bio->bi_opf |= REQ_FUA; + + btrfsic_check_bio(bio); + submit_bio(bio); + + if (btrfs_advance_sb_log(device, i)) errors++; } return errors < i ? 0 : -1; @@ -3520,47 +4074,57 @@ static int write_dev_supers(struct btrfs_device *device, * Wait for write completion of superblocks done by write_dev_supers, * @max_mirrors same for write and wait phases. * - * Return number of errors when buffer head is not found or not marked up to + * Return number of errors when page is not found or not marked up to * date. */ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors) { - struct buffer_head *bh; 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++) { - bytenr = btrfs_sb_offset(i); + struct page *page; + + ret = btrfs_sb_log_location(device, i, READ, &bytenr); + if (ret == -ENOENT) { + break; + } else if (ret < 0) { + errors++; + if (i == 0) + primary_failed = true; + continue; + } if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->commit_total_bytes) break; - bh = __find_get_block(device->bdev, - bytenr / BTRFS_BDEV_BLOCKSIZE, - BTRFS_SUPER_INFO_SIZE); - if (!bh) { + page = find_get_page(device->bdev->bd_inode->i_mapping, + bytenr >> PAGE_SHIFT); + if (!page) { errors++; if (i == 0) primary_failed = true; continue; } - wait_on_buffer(bh); - if (!buffer_uptodate(bh)) { + /* 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; } - /* drop our reference */ - brelse(bh); + /* Drop our reference */ + put_page(page); - /* drop the reference from the writing run */ - brelse(bh); + /* Drop the reference from the writing run */ + put_page(page); } /* log error, force error return */ @@ -3579,6 +4143,7 @@ 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); } @@ -3588,20 +4153,31 @@ 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)) +#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY + /* + * When a disk has write caching disabled, we skip submission of a bio + * with flush and sync requests before writing the superblock, since + * it's not needed. However when the integrity checker is enabled, this + * results in reports that there are metadata blocks referred by a + * superblock that were not properly flushed. So don't skip the bio + * submission only when the integrity checker is enabled for the sake + * of simplicity, since this is a debug tool and not meant for use in + * non-debug builds. + */ + if (!bdev_write_cache(device->bdev)) return; +#endif - 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); + btrfsic_check_bio(bio); + submit_bio(bio); set_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state); } @@ -3610,7 +4186,7 @@ static void write_dev_flush(struct btrfs_device *device) */ static blk_status_t 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; @@ -3832,44 +4408,25 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) { + bool drop_ref = false; + spin_lock(&fs_info->fs_roots_radix_lock); radix_tree_delete(&fs_info->fs_roots_radix, (unsigned long)root->root_key.objectid); + if (test_and_clear_bit(BTRFS_ROOT_IN_RADIX, &root->state)) + drop_ref = true; spin_unlock(&fs_info->fs_roots_radix_lock); - if (btrfs_root_refs(&root->root_item) == 0) - synchronize_srcu(&fs_info->subvol_srcu); - - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { - btrfs_free_log(NULL, root); + if (BTRFS_FS_ERROR(fs_info)) { + ASSERT(root->log_root == NULL); if (root->reloc_root) { - free_extent_buffer(root->reloc_root->node); - free_extent_buffer(root->reloc_root->commit_root); - btrfs_put_fs_root(root->reloc_root); + btrfs_put_root(root->reloc_root); root->reloc_root = NULL; } } - 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); - btrfs_free_fs_root(root); -} - -void btrfs_free_fs_root(struct btrfs_root *root) -{ - iput(root->ino_cache_inode); - WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree)); - if (root->anon_dev) - free_anon_bdev(root->anon_dev); - if (root->subv_writers) - btrfs_free_subvolume_writers(root->subv_writers); - free_extent_buffer(root->node); - free_extent_buffer(root->commit_root); - kfree(root->free_ino_ctl); - kfree(root->free_ino_pinned); - btrfs_put_fs_root(root); + if (drop_ref) + btrfs_put_root(root); } int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) @@ -3879,15 +4436,14 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) int i = 0; int err = 0; unsigned int ret = 0; - int index; while (1) { - index = srcu_read_lock(&fs_info->subvol_srcu); + 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) { - srcu_read_unlock(&fs_info->subvol_srcu, index); + spin_unlock(&fs_info->fs_roots_radix_lock); break; } root_objectid = gang[ret - 1]->root_key.objectid + 1; @@ -3899,9 +4455,9 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) continue; } /* grab all the search result for later use */ - gang[i] = btrfs_grab_fs_root(gang[i]); + gang[i] = btrfs_grab_root(gang[i]); } - srcu_read_unlock(&fs_info->subvol_srcu, index); + spin_unlock(&fs_info->fs_roots_radix_lock); for (i = 0; i < ret; i++) { if (!gang[i]) @@ -3910,7 +4466,7 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) err = btrfs_orphan_cleanup(gang[i]); if (err) break; - btrfs_put_fs_root(gang[i]); + btrfs_put_root(gang[i]); } root_objectid++; } @@ -3918,7 +4474,7 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) /* release the uncleaned roots due to error */ for (; i < ret; i++) { if (gang[i]) - btrfs_put_fs_root(gang[i]); + btrfs_put_root(gang[i]); } return err; } @@ -3943,11 +4499,75 @@ int btrfs_commit_super(struct btrfs_fs_info *fs_info) return btrfs_commit_transaction(trans); } +static void warn_about_uncommitted_trans(struct btrfs_fs_info *fs_info) +{ + struct btrfs_transaction *trans; + struct btrfs_transaction *tmp; + bool found = false; + + if (list_empty(&fs_info->trans_list)) + return; + + /* + * 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 (!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, fs_info); + + 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) { 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 @@ -3978,7 +4598,34 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) /* clear out the rbtree of defraggable inodes */ btrfs_cleanup_defrag_inodes(fs_info); + /* + * 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 either create new ordered extents nor create delayed iputs + * through some other means. + * + * 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); + 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 or finish ongoing discard work */ btrfs_discard_cleanup(fs_info); @@ -3990,13 +4637,25 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) */ btrfs_delete_unused_bgs(fs_info); + /* + * There might be existing delayed inode workers still running + * and holding an empty delayed inode item. We must wait for + * them to complete first because they can create a transaction. + * This happens when someone calls btrfs_balance_delayed_items() + * and then a transaction commit runs the same delayed nodes + * before any delayed worker has done something with the nodes. + * We must wait for any worker here and not at transaction + * commit time since that could cause a deadlock. + * This is a very rare case. + */ + btrfs_flush_workqueue(fs_info->delayed_workers); + ret = btrfs_commit_super(fs_info); if (ret) btrfs_err(fs_info, "commit super ret %d", ret); } - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state) || - test_bit(BTRFS_FS_STATE_TRANS_ABORTED, &fs_info->fs_state)) + if (BTRFS_FS_ERROR(fs_info)) btrfs_error_commit_super(fs_info); kthread_stop(fs_info->transaction_kthread); @@ -4005,6 +4664,11 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) ASSERT(list_empty(&fs_info->delayed_iputs)); set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags); + if (btrfs_check_quota_leak(fs_info)) { + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); + btrfs_err(fs_info, "qgroup reserved space leaked"); + } + btrfs_free_qgroup_config(fs_info); ASSERT(list_empty(&fs_info->delalloc_roots)); @@ -4013,15 +4677,13 @@ 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); - btrfs_free_fs_roots(fs_info); - btrfs_put_block_group_cache(fs_info); /* @@ -4031,8 +4693,12 @@ 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); /* * We must free the block groups after dropping the fs_roots as we could @@ -4052,16 +4718,6 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) btrfs_mapping_tree_free(&fs_info->mapping_tree); btrfs_close_devices(fs_info->fs_devices); - - 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->dev_replace.bio_counter); - cleanup_srcu_struct(&fs_info->subvol_srcu); - - btrfs_free_csum_hash(fs_info); - btrfs_free_stripe_hash_table(fs_info); - btrfs_free_ref_cache(fs_info); } int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, @@ -4083,8 +4739,7 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, 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; @@ -4097,9 +4752,7 @@ 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); + btrfs_assert_tree_write_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); @@ -4155,13 +4808,6 @@ 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 */ @@ -4175,6 +4821,36 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info) up_write(&fs_info->cleanup_work_sem); } +static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *gang[8]; + u64 root_objectid = 0; + int ret; + + spin_lock(&fs_info->fs_roots_radix_lock); + while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, + (void **)gang, root_objectid, + ARRAY_SIZE(gang))) != 0) { + int i; + + for (i = 0; i < ret; i++) + 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; + btrfs_free_log(NULL, gang[i]); + btrfs_put_root(gang[i]); + } + root_objectid++; + spin_lock(&fs_info->fs_roots_radix_lock); + } + spin_unlock(&fs_info->fs_roots_radix_lock); + btrfs_free_log_root_tree(NULL, fs_info); +} + static void btrfs_destroy_ordered_extents(struct btrfs_root *root) { struct btrfs_ordered_extent *ordered; @@ -4235,7 +4911,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, spin_lock(&delayed_refs->lock); if (atomic_read(&delayed_refs->num_entries) == 0) { spin_unlock(&delayed_refs->lock); - btrfs_info(fs_info, "delayed_refs has NO entry"); + btrfs_debug(fs_info, "delayed_refs has NO entry"); return ret; } @@ -4269,9 +4945,27 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, spin_unlock(&delayed_refs->lock); mutex_unlock(&head->mutex); - if (pin_bytes) - btrfs_pin_extent(fs_info, head->bytenr, - head->num_bytes, 1); + 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); + + 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(); @@ -4327,12 +5021,12 @@ static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info) while (!list_empty(&splice)) { root = list_first_entry(&splice, struct btrfs_root, delalloc_root); - root = btrfs_grab_fs_root(root); + root = btrfs_grab_root(root); BUG_ON(!root); spin_unlock(&fs_info->delalloc_root_lock); btrfs_destroy_delalloc_inodes(root); - btrfs_put_fs_root(root); + btrfs_put_root(root); spin_lock(&fs_info->delalloc_root_lock); } @@ -4373,16 +5067,12 @@ static int btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info, } static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, - struct extent_io_tree *pinned_extents) + struct extent_io_tree *unpin) { - struct extent_io_tree *unpin; u64 start; u64 end; int ret; - bool loop = true; - unpin = pinned_extents; -again: while (1) { struct extent_state *cached_state = NULL; @@ -4407,15 +5097,6 @@ again: cond_resched(); } - if (loop) { - if (unpin == &fs_info->freed_extents[0]) - unpin = &fs_info->freed_extents[1]; - else - unpin = &fs_info->freed_extents[0]; - loop = false; - goto again; - } - return 0; } @@ -4430,6 +5111,7 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) cache->io_ctl.inode = NULL; iput(inode); } + ASSERT(cache->io_ctl.pages == NULL); btrfs_put_block_group(cache); } @@ -4506,8 +5188,9 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages, EXTENT_DIRTY); - btrfs_destroy_pinned_extent(fs_info, - fs_info->pinned_extents); + btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents); + + btrfs_free_redirty_list(cur_trans); cur_trans->state =TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); @@ -4552,22 +5235,71 @@ 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); btrfs_destroy_all_ordered_extents(fs_info); btrfs_destroy_delayed_inodes(fs_info); btrfs_assert_delayed_root_empty(fs_info); - btrfs_destroy_pinned_extent(fs_info, fs_info->pinned_extents); btrfs_destroy_all_delalloc_inodes(fs_info); + btrfs_drop_all_logs(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) +{ + struct btrfs_path *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) + goto error; + BUG_ON(ret == 0); /* Corruption */ + 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; + } + ret = 0; +error: + btrfs_free_path(path); + return ret; +} + +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", + root->root_key.objectid); + ret = -ENOSPC; + goto out; + } + + *objectid = root->free_objectid++; + ret = 0; +out: + mutex_unlock(&root->objectid_mutex); + return ret; +} |