diff options
Diffstat (limited to 'fs/btrfs/disk-io.c')
| -rw-r--r-- | fs/btrfs/disk-io.c | 6370 |
1 files changed, 3607 insertions, 2763 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 6b092a1c4e37..89149fac804c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1,320 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2007 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License v2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> #include <linux/blkdev.h> -#include <linux/scatterlist.h> -#include <linux/swap.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/freezer.h> -#include <linux/crc32c.h> #include <linux/slab.h> #include <linux/migrate.h> #include <linux/ratelimit.h> #include <linux/uuid.h> -#include <asm/unaligned.h> -#include "compat.h" +#include <linux/semaphore.h> +#include <linux/error-injection.h> +#include <linux/crc32c.h> +#include <linux/sched/mm.h> +#include <linux/unaligned.h> +#include <crypto/hash.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" #include "btrfs_inode.h" -#include "volumes.h" +#include "bio.h" #include "print-tree.h" -#include "async-thread.h" #include "locking.h" #include "tree-log.h" #include "free-space-cache.h" -#include "inode-map.h" -#include "check-integrity.h" -#include "rcu-string.h" +#include "free-space-tree.h" #include "dev-replace.h" #include "raid56.h" - -#ifdef CONFIG_X86 -#include <asm/cpufeature.h> -#endif - -static struct extent_io_ops btree_extent_io_ops; -static void end_workqueue_fn(struct btrfs_work *work); -static void free_fs_root(struct btrfs_root *root); -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, - int read_only); -static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t, - struct btrfs_root *root); -static void btrfs_destroy_ordered_extents(struct btrfs_root *root); -static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, - struct btrfs_root *root); -static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t); -static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root); -static int btrfs_destroy_marked_extents(struct btrfs_root *root, - struct extent_io_tree *dirty_pages, - int mark); -static int btrfs_destroy_pinned_extent(struct btrfs_root *root, - struct extent_io_tree *pinned_extents); -static int btrfs_cleanup_transaction(struct btrfs_root *root); -static void btrfs_error_commit_super(struct btrfs_root *root); - -/* - * 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 end_io_wq { - struct bio *bio; - bio_end_io_t *end_io; - void *private; - struct btrfs_fs_info *info; - int error; - int metadata; - struct list_head list; - struct btrfs_work work; -}; - -/* - * async submit bios are used to offload expensive checksumming - * onto the worker threads. They checksum file and metadata bios - * just before they are sent down the IO stack. - */ -struct async_submit_bio { - struct inode *inode; - struct bio *bio; - struct list_head list; - extent_submit_bio_hook_t *submit_bio_start; - extent_submit_bio_hook_t *submit_bio_done; - int rw; - int mirror_num; - unsigned long bio_flags; - /* - * bio_offset is optional, can be used if the pages in the bio - * can't tell us where in the file the bio should go - */ - u64 bio_offset; - struct btrfs_work work; - int error; -}; - -/* - * 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->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 = 0, .name_stem = "tree" }, -}; - -void __init btrfs_init_lockdep(void) +#include "sysfs.h" +#include "qgroup.h" +#include "compression.h" +#include "tree-checker.h" +#include "ref-verify.h" +#include "block-group.h" +#include "discard.h" +#include "space-info.h" +#include "zoned.h" +#include "subpage.h" +#include "fs.h" +#include "accessors.h" +#include "extent-tree.h" +#include "root-tree.h" +#include "defrag.h" +#include "uuid-tree.h" +#include "relocation.h" +#include "scrub.h" +#include "super.h" +#include "delayed-inode.h" + +#define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\ + BTRFS_HEADER_FLAG_RELOC |\ + BTRFS_SUPER_FLAG_ERROR |\ + BTRFS_SUPER_FLAG_SEEDING |\ + BTRFS_SUPER_FLAG_METADUMP |\ + BTRFS_SUPER_FLAG_METADUMP_V2) + +static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info); +static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info); + +static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info) { - 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); - } + if (fs_info->csum_shash) + crypto_free_shash(fs_info->csum_shash); } -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 + * Compute the csum of a btree block and store the result to provided buffer. */ -static struct extent_map *btree_get_extent(struct inode *inode, - struct page *page, size_t pg_offset, u64 start, u64 len, - int create) +static void csum_tree_block(struct extent_buffer *buf, u8 *result) { - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; - struct extent_map *em; - int ret; + struct btrfs_fs_info *fs_info = buf->fs_info; + int num_pages; + u32 first_page_part; + SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); + char *kaddr; + int i; - read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, start, len); - if (em) { - em->bdev = - BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev; - read_unlock(&em_tree->lock); - goto out; - } - read_unlock(&em_tree->lock); + shash->tfm = fs_info->csum_shash; + crypto_shash_init(shash); - em = alloc_extent_map(); - if (!em) { - em = ERR_PTR(-ENOMEM); - goto out; + if (buf->addr) { + /* Pages are contiguous, handle them as a big one. */ + kaddr = buf->addr; + first_page_part = fs_info->nodesize; + num_pages = 1; + } else { + kaddr = folio_address(buf->folios[0]); + first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize); + num_pages = num_extent_pages(buf); } - em->start = 0; - em->len = (u64)-1; - em->block_len = (u64)-1; - em->block_start = 0; - em->bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev; - - 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; -} - -u32 btrfs_csum_data(char *data, u32 seed, size_t len) -{ - return crc32c(seed, data, len); -} -void btrfs_csum_final(u32 crc, char *result) -{ - put_unaligned_le32(~crc, result); -} + crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE, + first_page_part - BTRFS_CSUM_SIZE); -/* - * compute the csum for a btree block, and either verify it or write it - * into the csum field of the block. - */ -static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, - int verify) -{ - u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy); - char *result = NULL; - 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; - u32 crc = ~(u32)0; - unsigned long inline_result; - - len = buf->len - offset; - while (len > 0) { - err = map_private_extent_buffer(buf, offset, 32, - &kaddr, &map_start, &map_len); - if (err) - return 1; - cur_len = min(len, map_len - (offset - map_start)); - crc = btrfs_csum_data(kaddr + offset - map_start, - crc, cur_len); - len -= cur_len; - offset += cur_len; - } - if (csum_size > sizeof(inline_result)) { - result = kzalloc(csum_size * sizeof(char), GFP_NOFS); - if (!result) - return 1; - } else { - result = (char *)&inline_result; - } - - btrfs_csum_final(crc, result); - - if (verify) { - if (memcmp_extent_buffer(buf, result, 0, csum_size)) { - u32 val; - u32 found = 0; - memcpy(&found, result, csum_size); - - read_extent_buffer(buf, &val, 0, csum_size); - printk_ratelimited(KERN_INFO "btrfs: %s checksum verify " - "failed on %llu wanted %X found %X " - "level %d\n", - root->fs_info->sb->s_id, - (unsigned long long)buf->start, val, found, - btrfs_header_level(buf)); - if (result != (char *)&inline_result) - kfree(result); - return 1; - } - } else { - write_extent_buffer(buf, result, 0, csum_size); + /* + * Multiple single-page folios case would reach here. + * + * nodesize <= PAGE_SIZE and large folio all handled by above + * crypto_shash_update() already. + */ + for (i = 1; i < num_pages && INLINE_EXTENT_BUFFER_PAGES > 1; i++) { + kaddr = folio_address(buf->folios[i]); + crypto_shash_update(shash, kaddr, PAGE_SIZE); } - if (result != (char *)&inline_result) - kfree(result); - return 0; + memset(result, 0, BTRFS_CSUM_SIZE); + crypto_shash_final(shash, result); } /* @@ -323,120 +117,127 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, * detect blocks that either didn't get written at all or got written * in the wrong place. */ -static int verify_parent_transid(struct extent_io_tree *io_tree, - struct extent_buffer *eb, u64 parent_transid, - int atomic) +int btrfs_buffer_uptodate(struct extent_buffer *eb, u64 parent_transid, bool atomic) { - struct extent_state *cached_state = NULL; - int ret; + if (!extent_buffer_uptodate(eb)) + return 0; if (!parent_transid || btrfs_header_generation(eb) == parent_transid) - return 0; + return 1; if (atomic) return -EAGAIN; - lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1, - 0, &cached_state); - if (extent_buffer_uptodate(eb) && - btrfs_header_generation(eb) == parent_transid) { - ret = 0; - goto out; + if (!extent_buffer_uptodate(eb) || + btrfs_header_generation(eb) != parent_transid) { + btrfs_err_rl(eb->fs_info, +"parent transid verify failed on logical %llu mirror %u wanted %llu found %llu", + eb->start, eb->read_mirror, + parent_transid, btrfs_header_generation(eb)); + clear_extent_buffer_uptodate(eb); + return 0; + } + return 1; +} + +static bool btrfs_supported_super_csum(u16 csum_type) +{ + switch (csum_type) { + case BTRFS_CSUM_TYPE_CRC32: + case BTRFS_CSUM_TYPE_XXHASH: + case BTRFS_CSUM_TYPE_SHA256: + case BTRFS_CSUM_TYPE_BLAKE2: + return true; + default: + return false; } - printk_ratelimited("parent transid verify failed on %llu wanted %llu " - "found %llu\n", - (unsigned long long)eb->start, - (unsigned long long)parent_transid, - (unsigned long long)btrfs_header_generation(eb)); - ret = 1; - clear_extent_buffer_uptodate(eb); -out: - unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1, - &cached_state, GFP_NOFS); - return ret; } /* * 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(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; - u16 csum_type = btrfs_super_csum_type(disk_sb); - int ret = 0; + char result[BTRFS_CSUM_SIZE]; + SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); - if (csum_type == BTRFS_CSUM_TYPE_CRC32) { - u32 crc = ~(u32)0; - const int csum_size = sizeof(crc); - char result[csum_size]; + shash->tfm = fs_info->csum_shash; - /* - * The super_block structure does not span the whole - * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space - * is filled with zeros and is included in the checkum. - */ - crc = btrfs_csum_data(raw_disk_sb + BTRFS_CSUM_SIZE, - crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE); - btrfs_csum_final(crc, result); + /* + * The super_block structure does not span the whole + * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space is + * filled with zeros and is included in the checksum. + */ + crypto_shash_digest(shash, (const u8 *)disk_sb + BTRFS_CSUM_SIZE, + BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, result); - if (memcmp(raw_disk_sb, result, csum_size)) - ret = 1; + if (memcmp(disk_sb->csum, result, fs_info->csum_size)) + return 1; - if (ret && btrfs_super_generation(disk_sb) < 10) { - printk(KERN_WARNING "btrfs: super block crcs don't match, older mkfs detected\n"); - ret = 0; - } - } + return 0; +} - if (csum_type >= ARRAY_SIZE(btrfs_csum_sizes)) { - printk(KERN_ERR "btrfs: unsupported checksum algorithm %u\n", - csum_type); - ret = 1; +static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, + int mirror_num) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + const u32 step = min(fs_info->nodesize, PAGE_SIZE); + const u32 nr_steps = eb->len / step; + phys_addr_t paddrs[BTRFS_MAX_BLOCKSIZE / PAGE_SIZE]; + int ret = 0; + + if (sb_rdonly(fs_info->sb)) + return -EROFS; + + for (int i = 0; i < num_extent_pages(eb); i++) { + struct folio *folio = eb->folios[i]; + + /* No large folio support yet. */ + ASSERT(folio_order(folio) == 0); + ASSERT(i < nr_steps); + + /* + * For nodesize < page size, there is just one paddr, with some + * offset inside the page. + * + * For nodesize >= page size, it's one or more paddrs, and eb->start + * must be aligned to page boundary. + */ + paddrs[i] = page_to_phys(&folio->page) + offset_in_page(eb->start); } + ret = btrfs_repair_io_failure(fs_info, 0, eb->start, eb->len, eb->start, + paddrs, step, mirror_num); return ret; } /* * helper to read a given tree block, doing retries as required when * the checksums don't match and we have alternate mirrors to try. + * + * @check: expected tree parentness check, see the comments of the + * structure for details. */ -static int btree_read_extent_buffer_pages(struct btrfs_root *root, - struct extent_buffer *eb, - u64 start, u64 parent_transid) +int btrfs_read_extent_buffer(struct extent_buffer *eb, + const struct btrfs_tree_parent_check *check) { - struct extent_io_tree *io_tree; + struct btrfs_fs_info *fs_info = eb->fs_info; int failed = 0; int ret; int num_copies = 0; int mirror_num = 0; int failed_mirror = 0; - clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); - io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree; - while (1) { - ret = read_extent_buffer_pages(io_tree, eb, start, - WAIT_COMPLETE, - btree_get_extent, mirror_num); - if (!ret) { - if (!verify_parent_transid(io_tree, eb, - parent_transid, 0)) - break; - else - ret = -EIO; - } + ASSERT(check); - /* - * This buffer's crc is fine, but its contents are corrupted, so - * there is no reason to read the other copies, they won't be - * any less wrong. - */ - if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags)) + while (1) { + ret = read_extent_buffer_pages(eb, mirror_num, check); + if (!ret) break; - num_copies = btrfs_num_copies(root->fs_info, + num_copies = btrfs_num_copies(fs_info, eb->start, eb->len); if (num_copies == 1) break; @@ -455,750 +256,410 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, } if (failed && !ret && failed_mirror) - repair_eb_io_failure(root, eb, failed_mirror); + btrfs_repair_eb_io_failure(eb, failed_mirror); 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 + * Checksum a dirty tree block before IO. */ - -static int csum_dirty_buffer(struct btrfs_root *root, struct page *page) +int btree_csum_one_bio(struct btrfs_bio *bbio) { - struct extent_io_tree *tree; - u64 start = page_offset(page); - u64 found_start; - struct extent_buffer *eb; + struct extent_buffer *eb = bbio->private; + struct btrfs_fs_info *fs_info = eb->fs_info; + u64 found_start = btrfs_header_bytenr(eb); + u64 last_trans; + u8 result[BTRFS_CSUM_SIZE]; + int ret; - tree = &BTRFS_I(page->mapping->host)->io_tree; + /* Btree blocks are always contiguous on disk. */ + if (WARN_ON_ONCE(bbio->file_offset != eb->start)) + return -EIO; + if (WARN_ON_ONCE(bbio->bio.bi_iter.bi_size != eb->len)) + return -EIO; - eb = (struct extent_buffer *)page->private; - if (page != eb->pages[0]) - return 0; - found_start = btrfs_header_bytenr(eb); - if (found_start != start) { - WARN_ON(1); - return 0; - } - if (!PageUptodate(page)) { - WARN_ON(1); + /* + * If an extent_buffer is marked as EXTENT_BUFFER_ZONED_ZEROOUT, don't + * checksum it but zero-out its content. This is done to preserve + * ordering of I/O without unnecessarily writing out data. + */ + if (test_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags)) { + memzero_extent_buffer(eb, 0, eb->len); return 0; } - csum_tree_block(root, eb, 0); - return 0; -} -static int check_tree_block_fsid(struct btrfs_root *root, - struct extent_buffer *eb) -{ - struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; - u8 fsid[BTRFS_UUID_SIZE]; - int ret = 1; + if (WARN_ON_ONCE(found_start != eb->start)) + return -EIO; + if (WARN_ON(!btrfs_meta_folio_test_uptodate(eb->folios[0], eb))) + return -EIO; - read_extent_buffer(eb, fsid, (unsigned long)btrfs_header_fsid(eb), - BTRFS_FSID_SIZE); - while (fs_devices) { - if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) { - ret = 0; - break; - } - fs_devices = fs_devices->seed; - } - return ret; -} + ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid, + offsetof(struct btrfs_header, fsid), + BTRFS_FSID_SIZE) == 0); + csum_tree_block(eb, result); -#define CORRUPT(reason, eb, root, slot) \ - printk(KERN_CRIT "btrfs: corrupt leaf, %s: block=%llu," \ - "root=%llu, slot=%d\n", reason, \ - (unsigned long long)btrfs_header_bytenr(eb), \ - (unsigned long long)root->objectid, slot) + if (btrfs_header_level(eb)) + ret = btrfs_check_node(eb); + else + ret = btrfs_check_leaf(eb); -static noinline int check_leaf(struct btrfs_root *root, - struct extent_buffer *leaf) -{ - struct btrfs_key key; - struct btrfs_key leaf_key; - u32 nritems = btrfs_header_nritems(leaf); - int slot; - - if (nritems == 0) - return 0; + if (ret < 0) + goto error; - /* Check the 0 item */ - if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) != - BTRFS_LEAF_DATA_SIZE(root)) { - CORRUPT("invalid item offset size pair", leaf, root, 0); - return -EIO; - } + /* + * Also check the generation, the eb reached here must be newer than + * last committed. Or something seriously wrong happened. + */ + last_trans = btrfs_get_last_trans_committed(fs_info); + if (unlikely(btrfs_header_generation(eb) <= last_trans)) { + ret = -EUCLEAN; + btrfs_err(fs_info, + "block=%llu bad generation, have %llu expect > %llu", + eb->start, btrfs_header_generation(eb), last_trans); + goto error; + } + write_extent_buffer(eb, result, 0, fs_info->csum_size); + return 0; +error: + btrfs_print_tree(eb, 0); + btrfs_err(fs_info, "block=%llu write time tree block corruption detected", + eb->start); /* - * Check to make sure each items keys are in the correct order and their - * offsets make sense. We only have to loop through nritems-1 because - * we check the current slot against the next slot, which verifies the - * next slot's offset+size makes sense and that the current's slot - * offset is correct. + * Be noisy if this is an extent buffer from a log tree. We don't abort + * a transaction in case there's a bad log tree extent buffer, we just + * fallback to a transaction commit. Still we want to know when there is + * a bad log tree extent buffer, as that may signal a bug somewhere. */ - for (slot = 0; slot < nritems - 1; slot++) { - btrfs_item_key_to_cpu(leaf, &leaf_key, slot); - btrfs_item_key_to_cpu(leaf, &key, slot + 1); + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG) || + btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID); + return ret; +} - /* Make sure the keys are in the right order */ - if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) { - CORRUPT("bad key order", leaf, root, slot); - return -EIO; - } +static bool check_tree_block_fsid(struct extent_buffer *eb) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices, *seed_devs; + u8 fsid[BTRFS_FSID_SIZE]; - /* - * Make sure the offset and ends are right, remember that the - * item data starts at the end of the leaf and grows towards the - * front. - */ - if (btrfs_item_offset_nr(leaf, slot) != - btrfs_item_end_nr(leaf, slot + 1)) { - CORRUPT("slot offset bad", leaf, root, slot); - return -EIO; - } + read_extent_buffer(eb, fsid, offsetof(struct btrfs_header, fsid), + BTRFS_FSID_SIZE); - /* - * Check to make sure that we don't point outside of the leaf, - * just incase all the items are consistent to eachother, but - * all point outside of the leaf. - */ - if (btrfs_item_end_nr(leaf, slot) > - BTRFS_LEAF_DATA_SIZE(root)) { - CORRUPT("slot end outside of leaf", leaf, root, slot); - return -EIO; - } - } + /* + * alloc_fsid_devices() copies the fsid into fs_devices::metadata_uuid. + * This is then overwritten by metadata_uuid if it is present in the + * device_list_add(). The same true for a seed device as well. So use of + * fs_devices::metadata_uuid is appropriate here. + */ + if (memcmp(fsid, fs_info->fs_devices->metadata_uuid, BTRFS_FSID_SIZE) == 0) + return false; - return 0; + list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list) + if (!memcmp(fsid, seed_devs->fsid, BTRFS_FSID_SIZE)) + return false; + + return true; } -static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end, - struct extent_state *state, int mirror) +/* Do basic extent buffer checks at read time */ +int btrfs_validate_extent_buffer(struct extent_buffer *eb, + const struct btrfs_tree_parent_check *check) { - struct extent_io_tree *tree; + struct btrfs_fs_info *fs_info = eb->fs_info; u64 found_start; - int found_level; - struct extent_buffer *eb; - struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; + const u32 csum_size = fs_info->csum_size; + u8 found_level; + u8 result[BTRFS_CSUM_SIZE]; + const u8 *header_csum; int ret = 0; - int reads_done; + const bool ignore_csum = btrfs_test_opt(fs_info, IGNOREMETACSUMS); - if (!page->private) - goto out; - - tree = &BTRFS_I(page->mapping->host)->io_tree; - 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 - */ - extent_buffer_get(eb); - - reads_done = atomic_dec_and_test(&eb->io_pages); - if (!reads_done) - goto err; - - eb->read_mirror = mirror; - if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) { - ret = -EIO; - goto err; - } + ASSERT(check); found_start = btrfs_header_bytenr(eb); - if (found_start != eb->start) { - printk_ratelimited(KERN_INFO "btrfs bad tree block start " - "%llu %llu\n", - (unsigned long long)found_start, - (unsigned long long)eb->start); + if (unlikely(found_start != eb->start)) { + btrfs_err_rl(fs_info, + "bad tree block start, mirror %u want %llu have %llu", + eb->read_mirror, eb->start, found_start); ret = -EIO; - goto err; + goto out; } - if (check_tree_block_fsid(root, eb)) { - printk_ratelimited(KERN_INFO "btrfs bad fsid on block %llu\n", - (unsigned long long)eb->start); + if (unlikely(check_tree_block_fsid(eb))) { + btrfs_err_rl(fs_info, "bad fsid on logical %llu mirror %u", + eb->start, eb->read_mirror); ret = -EIO; - goto err; + goto out; } found_level = btrfs_header_level(eb); - if (found_level >= BTRFS_MAX_LEVEL) { - btrfs_info(root->fs_info, "bad tree block level %d\n", - (int)btrfs_header_level(eb)); + if (unlikely(found_level >= BTRFS_MAX_LEVEL)) { + btrfs_err(fs_info, + "bad tree block level, mirror %u level %d on logical %llu", + eb->read_mirror, btrfs_header_level(eb), eb->start); ret = -EIO; - goto err; + goto out; } - btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), - eb, found_level); - - ret = csum_tree_block(root, eb, 1); - if (ret) { - ret = -EIO; - goto err; + csum_tree_block(eb, result); + header_csum = folio_address(eb->folios[0]) + + get_eb_offset_in_folio(eb, offsetof(struct btrfs_header, csum)); + + if (memcmp(result, header_csum, csum_size) != 0) { + btrfs_warn_rl(fs_info, +"checksum verify failed on logical %llu mirror %u wanted " BTRFS_CSUM_FMT " found " BTRFS_CSUM_FMT " level %d%s", + eb->start, eb->read_mirror, + BTRFS_CSUM_FMT_VALUE(csum_size, header_csum), + BTRFS_CSUM_FMT_VALUE(csum_size, result), + btrfs_header_level(eb), + ignore_csum ? ", ignored" : ""); + if (unlikely(!ignore_csum)) { + ret = -EUCLEAN; + goto out; + } } - /* - * If this is a leaf block and it is corrupt, set the corrupt bit so - * that we don't try and read the other copies of this block, just - * return -EIO. - */ - if (found_level == 0 && check_leaf(root, eb)) { - set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); + if (unlikely(found_level != check->level)) { + btrfs_err(fs_info, + "level verify failed on logical %llu mirror %u wanted %u found %u", + eb->start, eb->read_mirror, check->level, found_level); ret = -EIO; + goto out; } - - if (!ret) - set_extent_buffer_uptodate(eb); -err: - if (reads_done && - test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) - btree_readahead_hook(root, eb, eb->start, 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); + if (unlikely(check->transid && + btrfs_header_generation(eb) != check->transid)) { + btrfs_err_rl(eb->fs_info, +"parent transid verify failed on logical %llu mirror %u wanted %llu found %llu", + eb->start, eb->read_mirror, check->transid, + btrfs_header_generation(eb)); + ret = -EIO; + goto out; } - free_extent_buffer(eb); -out: - return ret; -} + if (check->has_first_key) { + const struct btrfs_key *expect_key = &check->first_key; + struct btrfs_key found_key; -static int btree_io_failed_hook(struct page *page, int failed_mirror) -{ - struct extent_buffer *eb; - struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; - - eb = (struct extent_buffer *)page->private; - set_bit(EXTENT_BUFFER_IOERR, &eb->bflags); - eb->read_mirror = failed_mirror; - atomic_dec(&eb->io_pages); - if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) - btree_readahead_hook(root, eb, eb->start, -EIO); - return -EIO; /* we fixed nothing */ -} - -static void end_workqueue_bio(struct bio *bio, int err) -{ - struct end_io_wq *end_io_wq = bio->bi_private; - struct btrfs_fs_info *fs_info; - - fs_info = end_io_wq->info; - end_io_wq->error = err; - end_io_wq->work.func = end_workqueue_fn; - end_io_wq->work.flags = 0; - - if (bio->bi_rw & REQ_WRITE) { - if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) - btrfs_queue_worker(&fs_info->endio_meta_write_workers, - &end_io_wq->work); - else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) - btrfs_queue_worker(&fs_info->endio_freespace_worker, - &end_io_wq->work); - else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) - btrfs_queue_worker(&fs_info->endio_raid56_workers, - &end_io_wq->work); + if (found_level) + btrfs_node_key_to_cpu(eb, &found_key, 0); else - btrfs_queue_worker(&fs_info->endio_write_workers, - &end_io_wq->work); - } else { - if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) - btrfs_queue_worker(&fs_info->endio_raid56_workers, - &end_io_wq->work); - else if (end_io_wq->metadata) - btrfs_queue_worker(&fs_info->endio_meta_workers, - &end_io_wq->work); - else - btrfs_queue_worker(&fs_info->endio_workers, - &end_io_wq->work); - } -} - -/* - * For the metadata arg you want - * - * 0 - if data - * 1 - if normal metadta - * 2 - if writing to the free space cache area - * 3 - raid parity work - */ -int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, - int metadata) -{ - struct end_io_wq *end_io_wq; - end_io_wq = kmalloc(sizeof(*end_io_wq), GFP_NOFS); - if (!end_io_wq) - return -ENOMEM; - - end_io_wq->private = bio->bi_private; - end_io_wq->end_io = bio->bi_end_io; - end_io_wq->info = info; - end_io_wq->error = 0; - end_io_wq->bio = bio; - end_io_wq->metadata = metadata; - - bio->bi_private = end_io_wq; - bio->bi_end_io = end_workqueue_bio; - return 0; -} - -unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info) -{ - unsigned long limit = min_t(unsigned long, - info->workers.max_workers, - info->fs_devices->open_devices); - return 256 * limit; -} - -static void run_one_async_start(struct btrfs_work *work) -{ - struct async_submit_bio *async; - int ret; - - async = container_of(work, struct async_submit_bio, work); - ret = async->submit_bio_start(async->inode, async->rw, async->bio, - async->mirror_num, async->bio_flags, - async->bio_offset); - if (ret) - async->error = ret; -} - -static void run_one_async_done(struct btrfs_work *work) -{ - struct btrfs_fs_info *fs_info; - struct async_submit_bio *async; - int limit; - - async = container_of(work, struct async_submit_bio, work); - fs_info = BTRFS_I(async->inode)->root->fs_info; - - limit = btrfs_async_submit_limit(fs_info); - limit = limit * 2 / 3; - - if (atomic_dec_return(&fs_info->nr_async_submits) < limit && - waitqueue_active(&fs_info->async_submit_wait)) - wake_up(&fs_info->async_submit_wait); - - /* If an error occured we just want to clean up the bio and move on */ - if (async->error) { - bio_endio(async->bio, async->error); - return; - } - - async->submit_bio_done(async->inode, async->rw, async->bio, - async->mirror_num, async->bio_flags, - async->bio_offset); -} - -static void run_one_async_free(struct btrfs_work *work) -{ - struct async_submit_bio *async; - - async = container_of(work, struct async_submit_bio, work); - kfree(async); -} - -int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, - int rw, struct bio *bio, int mirror_num, - unsigned long bio_flags, - u64 bio_offset, - extent_submit_bio_hook_t *submit_bio_start, - extent_submit_bio_hook_t *submit_bio_done) -{ - struct async_submit_bio *async; - - async = kmalloc(sizeof(*async), GFP_NOFS); - if (!async) - return -ENOMEM; - - async->inode = inode; - async->rw = rw; - async->bio = bio; - async->mirror_num = mirror_num; - async->submit_bio_start = submit_bio_start; - async->submit_bio_done = submit_bio_done; - - async->work.func = run_one_async_start; - async->work.ordered_func = run_one_async_done; - async->work.ordered_free = run_one_async_free; - - async->work.flags = 0; - async->bio_flags = bio_flags; - async->bio_offset = bio_offset; - - async->error = 0; - - atomic_inc(&fs_info->nr_async_submits); - - if (rw & REQ_SYNC) - btrfs_set_work_high_prio(&async->work); - - btrfs_queue_worker(&fs_info->workers, &async->work); - - while (atomic_read(&fs_info->async_submit_draining) && - atomic_read(&fs_info->nr_async_submits)) { - wait_event(fs_info->async_submit_wait, - (atomic_read(&fs_info->nr_async_submits) == 0)); + btrfs_item_key_to_cpu(eb, &found_key, 0); + if (unlikely(btrfs_comp_cpu_keys(expect_key, &found_key))) { + btrfs_err(fs_info, +"tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)", + eb->start, check->transid, + expect_key->objectid, + expect_key->type, expect_key->offset, + found_key.objectid, found_key.type, + found_key.offset); + ret = -EUCLEAN; + goto out; + } } - - return 0; -} - -static int btree_csum_one_bio(struct bio *bio) -{ - struct bio_vec *bvec = bio->bi_io_vec; - int bio_index = 0; - struct btrfs_root *root; - int ret = 0; - - WARN_ON(bio->bi_vcnt <= 0); - while (bio_index < bio->bi_vcnt) { - root = BTRFS_I(bvec->bv_page->mapping->host)->root; - ret = csum_dirty_buffer(root, bvec->bv_page); - if (ret) - break; - bio_index++; - bvec++; + if (check->owner_root) { + ret = btrfs_check_eb_owner(eb, check->owner_root); + if (ret < 0) + goto out; } - return ret; -} -static int __btree_submit_bio_start(struct inode *inode, int rw, - struct bio *bio, int mirror_num, - unsigned long bio_flags, - u64 bio_offset) -{ - /* - * when we're called for a write, we're already in the async - * submission context. Just jump into btrfs_map_bio - */ - return btree_csum_one_bio(bio); -} + /* If this is a leaf block and it is corrupt, just return -EIO. */ + if (found_level == 0 && btrfs_check_leaf(eb)) + ret = -EIO; -static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) -{ - int ret; + if (found_level > 0 && btrfs_check_node(eb)) + ret = -EIO; - /* - * when we're called for a write, we're already in the async - * submission context. Just jump into btrfs_map_bio - */ - ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1); if (ret) - bio_endio(bio, ret); - return ret; -} - -static int check_async_write(struct inode *inode, unsigned long bio_flags) -{ - if (bio_flags & EXTENT_BIO_TREE_LOG) - return 0; -#ifdef CONFIG_X86 - if (cpu_has_xmm4_2) - return 0; -#endif - return 1; -} - -static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) -{ - int async = check_async_write(inode, bio_flags); - int ret; - - if (!(rw & REQ_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(BTRFS_I(inode)->root->fs_info, - bio, 1); - if (ret) - goto out_w_error; - ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, - mirror_num, 0); - } else if (!async) { - ret = btree_csum_one_bio(bio); - if (ret) - goto out_w_error; - ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, - mirror_num, 0); - } else { - /* - * kthread helpers are used to submit writes so that - * checksumming can happen in parallel across all CPUs - */ - ret = btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info, - inode, rw, bio, mirror_num, 0, - bio_offset, - __btree_submit_bio_start, - __btree_submit_bio_done); - } - - if (ret) { -out_w_error: - bio_endio(bio, ret); - } + btrfs_err(fs_info, + "read time tree block corruption detected on logical %llu mirror %u", + eb->start, eb->read_mirror); +out: return ret; } #ifdef CONFIG_MIGRATION -static int btree_migratepage(struct address_space *mapping, - struct page *newpage, struct page *page, - enum migrate_mode mode) +static int btree_migrate_folio(struct address_space *mapping, + struct folio *dst, struct folio *src, enum migrate_mode mode) { /* * we can't safely write a btree page from here, * we haven't done the locking hook */ - if (PageDirty(page)) + if (folio_test_dirty(src)) return -EAGAIN; /* * Buffers may be managed in a filesystem specific way. * We must have no buffers or drop them. */ - if (page_has_private(page) && - !try_to_release_page(page, GFP_KERNEL)) + if (folio_get_private(src) && + !filemap_release_folio(src, GFP_KERNEL)) return -EAGAIN; - return migrate_page(mapping, newpage, page, mode); + return migrate_folio(mapping, dst, src, mode); } +#else +#define btree_migrate_folio NULL #endif - static int btree_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct extent_io_tree *tree; - struct btrfs_fs_info *fs_info; int ret; - tree = &BTRFS_I(mapping->host)->io_tree; if (wbc->sync_mode == WB_SYNC_NONE) { + struct btrfs_fs_info *fs_info; if (wbc->for_kupdate) return 0; - fs_info = BTRFS_I(mapping->host)->root->fs_info; + fs_info = inode_to_fs_info(mapping->host); /* this is a bit racy, but that's ok */ - ret = percpu_counter_compare(&fs_info->dirty_metadata_bytes, - BTRFS_DIRTY_METADATA_THRESH); + ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes, + BTRFS_DIRTY_METADATA_THRESH, + fs_info->dirty_metadata_batch); if (ret < 0) return 0; } return btree_write_cache_pages(mapping, wbc); } -static int btree_readpage(struct file *file, struct page *page) -{ - 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) +static bool btree_release_folio(struct folio *folio, gfp_t gfp_flags) { - if (PageWriteback(page) || PageDirty(page)) - return 0; + if (folio_test_writeback(folio) || folio_test_dirty(folio)) + return false; - return try_release_extent_buffer(page); + return try_release_extent_buffer(folio); } -static void btree_invalidatepage(struct page *page, unsigned int offset, - unsigned int length) +static void btree_invalidate_folio(struct folio *folio, size_t offset, + size_t length) { struct extent_io_tree *tree; - tree = &BTRFS_I(page->mapping->host)->io_tree; - extent_invalidatepage(tree, page, offset); - btree_releasepage(page, GFP_NOFS); - if (PagePrivate(page)) { - printk(KERN_WARNING "btrfs warning page private not zero " - "on page %llu\n", (unsigned long long)page_offset(page)); - ClearPagePrivate(page); - set_page_private(page, 0); - page_cache_release(page); + + tree = &folio_to_inode(folio)->io_tree; + extent_invalidate_folio(tree, folio, offset); + btree_release_folio(folio, GFP_NOFS); + if (folio_get_private(folio)) { + btrfs_warn(folio_to_fs_info(folio), + "folio private not zero on folio %llu", + (unsigned long long)folio_pos(folio)); + folio_detach_private(folio); } } -static int btree_set_page_dirty(struct page *page) -{ #ifdef DEBUG +static bool btree_dirty_folio(struct address_space *mapping, + struct folio *folio) +{ + struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); + struct btrfs_subpage_info *spi = fs_info->subpage_info; + struct btrfs_subpage *subpage; struct extent_buffer *eb; + int cur_bit = 0; + u64 page_start = folio_pos(folio); + + if (fs_info->sectorsize == PAGE_SIZE) { + eb = folio_get_private(folio); + BUG_ON(!eb); + BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); + BUG_ON(!atomic_read(&eb->refs)); + btrfs_assert_tree_write_locked(eb); + return filemap_dirty_folio(mapping, folio); + } + + ASSERT(spi); + subpage = folio_get_private(folio); + + for (cur_bit = spi->dirty_offset; + cur_bit < spi->dirty_offset + spi->bitmap_nr_bits; + cur_bit++) { + unsigned long flags; + u64 cur; + + spin_lock_irqsave(&subpage->lock, flags); + if (!test_bit(cur_bit, subpage->bitmaps)) { + spin_unlock_irqrestore(&subpage->lock, flags); + continue; + } + spin_unlock_irqrestore(&subpage->lock, flags); + cur = page_start + cur_bit * fs_info->sectorsize; - BUG_ON(!PagePrivate(page)); - eb = (struct extent_buffer *)page->private; - BUG_ON(!eb); - BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); - BUG_ON(!atomic_read(&eb->refs)); - btrfs_assert_tree_locked(eb); -#endif - return __set_page_dirty_nobuffers(page); + eb = find_extent_buffer(fs_info, cur); + ASSERT(eb); + ASSERT(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); + ASSERT(atomic_read(&eb->refs)); + btrfs_assert_tree_write_locked(eb); + free_extent_buffer(eb); + + cur_bit += (fs_info->nodesize >> fs_info->sectorsize_bits) - 1; + } + return filemap_dirty_folio(mapping, folio); } +#else +#define btree_dirty_folio filemap_dirty_folio +#endif static const struct address_space_operations btree_aops = { - .readpage = btree_readpage, .writepages = btree_writepages, - .releasepage = btree_releasepage, - .invalidatepage = btree_invalidatepage, -#ifdef CONFIG_MIGRATION - .migratepage = btree_migratepage, -#endif - .set_page_dirty = btree_set_page_dirty, + .release_folio = btree_release_folio, + .invalidate_folio = btree_invalidate_folio, + .migrate_folio = btree_migrate_folio, + .dirty_folio = btree_dirty_folio, }; -int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize, - u64 parent_transid) +struct extent_buffer *btrfs_find_create_tree_block( + struct btrfs_fs_info *fs_info, + u64 bytenr, u64 owner_root, + int level) { - struct extent_buffer *buf = NULL; - struct inode *btree_inode = root->fs_info->btree_inode; - int ret = 0; - - buf = btrfs_find_create_tree_block(root, bytenr, blocksize); - if (!buf) - return 0; - read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, - buf, 0, WAIT_NONE, btree_get_extent, 0); - free_extent_buffer(buf); - return ret; + if (btrfs_is_testing(fs_info)) + return alloc_test_extent_buffer(fs_info, bytenr); + return alloc_extent_buffer(fs_info, bytenr, owner_root, level); } -int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize, - int mirror_num, struct extent_buffer **eb) +/* + * Read tree block at logical address @bytenr and do variant basic but critical + * verification. + * + * @check: expected tree parentness check, see comments of the + * structure for details. + */ +struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, + struct btrfs_tree_parent_check *check) { struct extent_buffer *buf = NULL; - struct inode *btree_inode = root->fs_info->btree_inode; - struct extent_io_tree *io_tree = &BTRFS_I(btree_inode)->io_tree; int ret; - buf = btrfs_find_create_tree_block(root, bytenr, blocksize); - if (!buf) - return 0; + ASSERT(check); - set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags); + buf = btrfs_find_create_tree_block(fs_info, bytenr, check->owner_root, + check->level); + if (IS_ERR(buf)) + return buf; - ret = read_extent_buffer_pages(io_tree, buf, 0, WAIT_PAGE_LOCK, - btree_get_extent, mirror_num); + ret = btrfs_read_extent_buffer(buf, check); if (ret) { - free_extent_buffer(buf); - return ret; - } - - if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) { - free_extent_buffer(buf); - return -EIO; - } else if (extent_buffer_uptodate(buf)) { - *eb = buf; - } else { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); + return ERR_PTR(ret); } - return 0; -} - -struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root, - u64 bytenr, u32 blocksize) -{ - struct inode *btree_inode = root->fs_info->btree_inode; - struct extent_buffer *eb; - eb = find_extent_buffer(&BTRFS_I(btree_inode)->io_tree, - bytenr, blocksize); - return eb; -} - -struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root, - u64 bytenr, u32 blocksize) -{ - struct inode *btree_inode = root->fs_info->btree_inode; - struct extent_buffer *eb; - - eb = alloc_extent_buffer(&BTRFS_I(btree_inode)->io_tree, - bytenr, blocksize); - return eb; -} - - -int btrfs_write_tree_block(struct extent_buffer *buf) -{ - return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start, - buf->start + buf->len - 1); -} + return buf; -int btrfs_wait_tree_block_writeback(struct extent_buffer *buf) -{ - return filemap_fdatawait_range(buf->pages[0]->mapping, - buf->start, buf->start + buf->len - 1); } -struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr, - u32 blocksize, u64 parent_transid) +static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info, + u64 objectid, gfp_t flags) { - struct extent_buffer *buf = NULL; - int ret; + struct btrfs_root *root; - buf = btrfs_find_create_tree_block(root, bytenr, blocksize); - if (!buf) + root = kzalloc(sizeof(*root), flags); + if (!root) return NULL; - ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid); - return buf; - -} + root->fs_info = fs_info; + root->root_key.objectid = objectid; + RB_CLEAR_NODE(&root->rb_node); -void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf) -{ - struct btrfs_fs_info *fs_info = root->fs_info; + xa_init(&root->inodes); + xa_init(&root->delayed_nodes); - if (btrfs_header_generation(buf) == - fs_info->running_transaction->transid) { - btrfs_assert_tree_locked(buf); - - if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) { - __percpu_counter_add(&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(buf); - clear_extent_buffer_dirty(buf); - } - } -} - -static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, - u32 stripesize, struct btrfs_root *root, - struct btrfs_fs_info *fs_info, - u64 objectid) -{ - root->node = NULL; - root->commit_root = NULL; - root->sectorsize = sectorsize; - root->nodesize = nodesize; - root->leafsize = leafsize; - root->stripesize = stripesize; - root->ref_cows = 0; - root->track_dirty = 0; - root->in_radix = 0; - root->orphan_item_inserted = 0; - root->orphan_cleanup_state = 0; - - root->objectid = objectid; - root->last_trans = 0; - root->highest_objectid = 0; - root->nr_delalloc_inodes = 0; - root->nr_ordered_extents = 0; - root->name = NULL; - root->inode_tree = RB_ROOT; - INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC); - root->block_rsv = NULL; - root->orphan_block_rsv = NULL; + btrfs_init_root_block_rsv(root); INIT_LIST_HEAD(&root->dirty_list); INIT_LIST_HEAD(&root->root_list); @@ -1206,105 +667,210 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, INIT_LIST_HEAD(&root->delalloc_root); INIT_LIST_HEAD(&root->ordered_extents); INIT_LIST_HEAD(&root->ordered_root); - INIT_LIST_HEAD(&root->logged_list[0]); - INIT_LIST_HEAD(&root->logged_list[1]); - spin_lock_init(&root->orphan_lock); - spin_lock_init(&root->inode_lock); + INIT_LIST_HEAD(&root->reloc_dirty_list); spin_lock_init(&root->delalloc_lock); spin_lock_init(&root->ordered_extent_lock); spin_lock_init(&root->accounting_lock); - spin_lock_init(&root->log_extents_lock[0]); - spin_lock_init(&root->log_extents_lock[1]); + spin_lock_init(&root->qgroup_meta_rsv_lock); mutex_init(&root->objectid_mutex); mutex_init(&root->log_mutex); + mutex_init(&root->ordered_extent_mutex); + mutex_init(&root->delalloc_mutex); + init_waitqueue_head(&root->qgroup_flush_wait); init_waitqueue_head(&root->log_writer_wait); init_waitqueue_head(&root->log_commit_wait[0]); init_waitqueue_head(&root->log_commit_wait[1]); + INIT_LIST_HEAD(&root->log_ctxs[0]); + INIT_LIST_HEAD(&root->log_ctxs[1]); atomic_set(&root->log_commit[0], 0); atomic_set(&root->log_commit[1], 0); atomic_set(&root->log_writers, 0); atomic_set(&root->log_batch, 0); - atomic_set(&root->orphan_inodes, 0); - atomic_set(&root->refs, 1); - root->log_transid = 0; - root->last_log_commit = 0; - extent_io_tree_init(&root->dirty_log_pages, - fs_info->btree_inode->i_mapping); - - 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)); - memset(&root->root_kobj, 0, sizeof(root->root_kobj)); - root->defrag_trans_start = fs_info->generation; - init_completion(&root->kobj_unregister); - root->defrag_running = 0; - root->root_key.objectid = objectid; - root->anon_dev = 0; + refcount_set(&root->refs, 1); + atomic_set(&root->snapshot_force_cow, 0); + atomic_set(&root->nr_swapfiles, 0); + root->log_transid_committed = -1; + if (!btrfs_is_testing(fs_info)) { + btrfs_extent_io_tree_init(fs_info, &root->dirty_log_pages, + IO_TREE_ROOT_DIRTY_LOG_PAGES); + btrfs_extent_io_tree_init(fs_info, &root->log_csum_range, + IO_TREE_LOG_CSUM_RANGE); + } spin_lock_init(&root->root_item_lock); + btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks); +#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 + + return root; } -static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info) +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS +/* Should only be used by the testing infrastructure */ +struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info) { - struct btrfs_root *root = kzalloc(sizeof(*root), GFP_NOFS); - if (root) - root->fs_info = fs_info; + struct btrfs_root *root; + + if (!fs_info) + return ERR_PTR(-EINVAL); + + root = btrfs_alloc_root(fs_info, BTRFS_ROOT_TREE_OBJECTID, GFP_KERNEL); + if (!root) + return ERR_PTR(-ENOMEM); + + /* We don't use the stripesize in selftest, set it as sectorsize */ + root->alloc_bytenr = 0; + + 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; + int ret = 0; + + write_lock(&fs_info->global_root_lock); + tmp = rb_find_add(&root->rb_node, &fs_info->global_root_tree, global_root_cmp); + write_unlock(&fs_info->global_root_lock); + + if (tmp) { + ret = -EEXIST; + btrfs_warn(fs_info, "global root %llu %llu already exists", + btrfs_root_id(root), root->root_key.offset); + } + return ret; +} + +void btrfs_global_root_delete(struct btrfs_root *root) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + + write_lock(&fs_info->global_root_lock); + rb_erase(&root->rb_node, &fs_info->global_root_tree); + write_unlock(&fs_info->global_root_lock); +} + +struct btrfs_root *btrfs_global_root(struct btrfs_fs_info *fs_info, + struct btrfs_key *key) +{ + struct rb_node *node; + struct btrfs_root *root = NULL; + + read_lock(&fs_info->global_root_lock); + node = rb_find(key, &fs_info->global_root_tree, global_root_key_cmp); + if (node) + root = container_of(node, struct btrfs_root, rb_node); + read_unlock(&fs_info->global_root_lock); + return root; } +static u64 btrfs_global_root_id(struct btrfs_fs_info *fs_info, u64 bytenr) +{ + struct btrfs_block_group *block_group; + u64 ret; + + if (!btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) + return 0; + + if (bytenr) + block_group = btrfs_lookup_block_group(fs_info, bytenr); + else + block_group = btrfs_lookup_first_block_group(fs_info, bytenr); + ASSERT(block_group); + if (!block_group) + return 0; + ret = block_group->global_root_id; + btrfs_put_block_group(block_group); + + return ret; +} + +struct btrfs_root *btrfs_csum_root(struct btrfs_fs_info *fs_info, u64 bytenr) +{ + struct btrfs_key key = { + .objectid = BTRFS_CSUM_TREE_OBJECTID, + .type = BTRFS_ROOT_ITEM_KEY, + .offset = btrfs_global_root_id(fs_info, bytenr), + }; + + return btrfs_global_root(fs_info, &key); +} + +struct btrfs_root *btrfs_extent_root(struct btrfs_fs_info *fs_info, u64 bytenr) +{ + struct btrfs_key key = { + .objectid = BTRFS_EXTENT_TREE_OBJECTID, + .type = BTRFS_ROOT_ITEM_KEY, + .offset = btrfs_global_root_id(fs_info, bytenr), + }; + + return btrfs_global_root(fs_info, &key); +} + struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 objectid) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct extent_buffer *leaf; struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root *root; struct btrfs_key key; + unsigned int nofs_flag; int ret = 0; - u64 bytenr; - uuid_le uuid; - root = btrfs_alloc_root(fs_info); + /* + * We're holding a transaction handle, so use a NOFS memory allocation + * context to avoid deadlock if reclaim happens. + */ + nofs_flag = memalloc_nofs_save(); + root = btrfs_alloc_root(fs_info, objectid, GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!root) return ERR_PTR(-ENOMEM); - __setup_root(tree_root->nodesize, tree_root->leafsize, - tree_root->sectorsize, tree_root->stripesize, - 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_free_block(trans, root, root->leafsize, - 0, objectid, NULL, 0, 0, 0); + leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0, + 0, BTRFS_NESTING_NORMAL); if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); leaf = NULL; goto fail; } - bytenr = leaf->start; - memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header)); - btrfs_set_header_bytenr(leaf, leaf->start); - btrfs_set_header_generation(leaf, trans->transid); - btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV); - btrfs_set_header_owner(leaf, objectid); root->node = leaf; - - write_extent_buffer(leaf, fs_info->fsid, - (unsigned long)btrfs_header_fsid(leaf), - BTRFS_FSID_SIZE); - write_extent_buffer(leaf, fs_info->chunk_tree_uuid, - (unsigned long)btrfs_header_chunk_tree_uuid(leaf), - BTRFS_UUID_SIZE); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); root->commit_root = btrfs_root_node(root); - root->track_dirty = 1; + 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); @@ -1312,9 +878,13 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, btrfs_set_root_used(&root->root_item, leaf->len); btrfs_set_root_last_snapshot(&root->root_item, 0); btrfs_set_root_dirid(&root->root_item, 0); - uuid_le_gen(&uuid); - memcpy(root->root_item.uuid, uuid.b, BTRFS_UUID_SIZE); - root->root_item.drop_level = 0; + if (btrfs_is_fstree(objectid)) + 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; @@ -1323,67 +893,55 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, if (ret) goto fail; - btrfs_tree_unlock(leaf); - return root; fail: - if (leaf) { - btrfs_tree_unlock(leaf); - free_extent_buffer(leaf); - } - kfree(root); + btrfs_put_root(root); return ERR_PTR(ret); } -static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) +static struct btrfs_root *alloc_log_tree(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; - struct btrfs_root *tree_root = fs_info->tree_root; - struct extent_buffer *leaf; - root = btrfs_alloc_root(fs_info); + root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, GFP_NOFS); if (!root) return ERR_PTR(-ENOMEM); - __setup_root(tree_root->nodesize, tree_root->leafsize, - tree_root->sectorsize, tree_root->stripesize, - 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; + /* - * 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). + * DON'T set SHAREABLE bit for log trees. + * + * Log trees are not exposed to user space thus can't be snapshotted, + * and they go away before a real commit is actually done. + * + * They do store pointers to file data extents, and those reference + * counts still get updated (along with back refs to the log tree). */ - root->ref_cows = 0; - leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0, - BTRFS_TREE_LOG_OBJECTID, NULL, - 0, 0, 0); - if (IS_ERR(leaf)) { - kfree(root); - return ERR_CAST(leaf); - } + leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID, + NULL, 0, 0, 0, 0, BTRFS_NESTING_NORMAL); + if (IS_ERR(leaf)) + return PTR_ERR(leaf); - memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header)); - btrfs_set_header_bytenr(leaf, leaf->start); - btrfs_set_header_generation(leaf, trans->transid); - btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV); - btrfs_set_header_owner(leaf, BTRFS_TREE_LOG_OBJECTID); root->node = leaf; - write_extent_buffer(root->node, root->fs_info->fsid, - (unsigned long)btrfs_header_fsid(root->node), - BTRFS_FSID_SIZE); - btrfs_mark_buffer_dirty(root->node); + btrfs_mark_buffer_dirty(trans, root->node); btrfs_tree_unlock(root->node); - return root; + + return 0; } int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, @@ -1391,9 +949,19 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, { struct btrfs_root *log_root; - log_root = alloc_log_tree(trans, fs_info); + log_root = alloc_log_tree(fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); + + if (!btrfs_is_zoned(fs_info)) { + int ret = btrfs_alloc_log_tree_node(trans, log_root); + + if (ret) { + btrfs_put_root(log_root); + return ret; + } + } + WARN_ON(fs_info->log_root_tree); fs_info->log_root_tree = log_root; return 0; @@ -1402,360 +970,611 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, int btrfs_add_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root) { + 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, root->fs_info); + log_root = alloc_log_tree(fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); - log_root->last_trans = trans->transid; - log_root->root_key.offset = root->root_key.objectid; + ret = btrfs_alloc_log_tree_node(trans, log_root); + if (ret) { + btrfs_put_root(log_root); + return ret; + } + + btrfs_set_root_last_trans(log_root, trans->transid); + log_root->root_key.offset = btrfs_root_id(root); inode_item = &log_root->root_item.inode; - inode_item->generation = cpu_to_le64(1); - inode_item->size = cpu_to_le64(3); - inode_item->nlink = cpu_to_le32(1); - inode_item->nbytes = cpu_to_le64(root->leafsize); - inode_item->mode = cpu_to_le32(S_IFDIR | 0755); + btrfs_set_stack_inode_generation(inode_item, 1); + btrfs_set_stack_inode_size(inode_item, 3); + btrfs_set_stack_inode_nlink(inode_item, 1); + btrfs_set_stack_inode_nbytes(inode_item, + fs_info->nodesize); + btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755); btrfs_set_root_node(&log_root->root_item, log_root->node); WARN_ON(root->log_root); root->log_root = log_root; - root->log_transid = 0; - root->last_log_commit = 0; + btrfs_set_root_log_transid(root, 0); + root->log_transid_committed = -1; + btrfs_set_root_last_log_commit(root, 0); return 0; } -struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, - struct btrfs_key *key) +static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root, + struct btrfs_path *path, + const struct btrfs_key *key) { struct btrfs_root *root; + struct btrfs_tree_parent_check check = { 0 }; struct btrfs_fs_info *fs_info = tree_root->fs_info; - struct btrfs_path *path; u64 generation; - u32 blocksize; 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); - if (!root) { - ret = -ENOMEM; - goto alloc_fail; - } - - __setup_root(tree_root->nodesize, tree_root->leafsize, - tree_root->sectorsize, tree_root->stripesize, - 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); - blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item)); - root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item), - blocksize, generation); - if (!root->node) { - ret = -ENOMEM; - goto find_fail; - } else if (!btrfs_buffer_uptodate(root->node, generation, 0)) { + level = btrfs_root_level(&root->root_item); + check.level = level; + check.transid = generation; + check.owner_root = key->objectid; + root->node = read_tree_block(fs_info, btrfs_root_bytenr(&root->root_item), + &check); + if (IS_ERR(root->node)) { + ret = PTR_ERR(root->node); + root->node = NULL; + goto fail; + } + if (unlikely(!btrfs_buffer_uptodate(root->node, generation, false))) { ret = -EIO; - goto read_fail; + goto fail; + } + + /* + * For real fs, and not log/reloc trees, root owner must + * match its root node owner + */ + if (unlikely(!btrfs_is_testing(fs_info) && + btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID && + btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID && + btrfs_root_id(root) != btrfs_header_owner(root->node))) { + btrfs_crit(fs_info, +"root=%llu block=%llu, tree root owner mismatch, have %llu expect %llu", + btrfs_root_id(root), root->node->start, + btrfs_header_owner(root->node), + btrfs_root_id(root)); + ret = -EUCLEAN; + goto fail; } root->commit_root = btrfs_root_node(root); -out: - btrfs_free_path(path); return root; - -read_fail: - free_extent_buffer(root->node); -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, + const struct btrfs_key *key) { struct btrfs_root *root; + BTRFS_PATH_AUTO_FREE(path); - root = btrfs_read_tree_root(tree_root, location); - if (IS_ERR(root)) - return root; - - if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { - root->ref_cows = 1; - 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); 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 + * + * In case of failure the caller is responsible to call btrfs_free_fs_root() + */ +static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) { int ret; - root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS); - root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned), - GFP_NOFS); - if (!root->free_ino_pinned || !root->free_ino_ctl) { - ret = -ENOMEM; - goto fail; + btrfs_drew_lock_init(&root->snapshot_lock); + + if (btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID && + !btrfs_is_data_reloc_root(root) && + btrfs_is_fstree(btrfs_root_id(root))) { + set_bit(BTRFS_ROOT_SHAREABLE, &root->state); + btrfs_check_and_init_root_item(&root->root_item); + } + + /* + * Don't assign anonymous block device to roots that are not exposed to + * userspace, the id pool is limited to 1M + */ + if (btrfs_is_fstree(btrfs_root_id(root)) && + btrfs_root_refs(&root->root_item) > 0) { + if (!anon_dev) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + return ret; + } else { + root->anon_dev = anon_dev; + } + } + + mutex_lock(&root->objectid_mutex); + ret = btrfs_init_root_free_objectid(root); + if (ret) { + mutex_unlock(&root->objectid_mutex); + return ret; } - btrfs_init_free_ino_ctl(root); - mutex_init(&root->fs_commit_mutex); - spin_lock_init(&root->cache_lock); - init_waitqueue_head(&root->cache_wait); + ASSERT(root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); + + mutex_unlock(&root->objectid_mutex); - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; return 0; -fail: - kfree(root->free_ino_ctl); - kfree(root->free_ino_pinned); - 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); + root = btrfs_grab_root(root); spin_unlock(&fs_info->fs_roots_radix_lock); return root; } +static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info, + u64 objectid) +{ + struct btrfs_key key = { + .objectid = objectid, + .type = BTRFS_ROOT_ITEM_KEY, + .offset = 0, + }; + + switch (objectid) { + case BTRFS_ROOT_TREE_OBJECTID: + return btrfs_grab_root(fs_info->tree_root); + case BTRFS_EXTENT_TREE_OBJECTID: + return btrfs_grab_root(btrfs_global_root(fs_info, &key)); + case BTRFS_CHUNK_TREE_OBJECTID: + return btrfs_grab_root(fs_info->chunk_root); + case BTRFS_DEV_TREE_OBJECTID: + return btrfs_grab_root(fs_info->dev_root); + case BTRFS_CSUM_TREE_OBJECTID: + return btrfs_grab_root(btrfs_global_root(fs_info, &key)); + case BTRFS_QUOTA_TREE_OBJECTID: + return btrfs_grab_root(fs_info->quota_root); + case BTRFS_UUID_TREE_OBJECTID: + return btrfs_grab_root(fs_info->uuid_root); + case BTRFS_BLOCK_GROUP_TREE_OBJECTID: + return btrfs_grab_root(fs_info->block_group_root); + case BTRFS_FREE_SPACE_TREE_OBJECTID: + return btrfs_grab_root(btrfs_global_root(fs_info, &key)); + case BTRFS_RAID_STRIPE_TREE_OBJECTID: + return btrfs_grab_root(fs_info->stripe_root); + default: + return NULL; + } +} + int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) { int ret; - ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); + ret = radix_tree_preload(GFP_NOFS); if (ret) return ret; spin_lock(&fs_info->fs_roots_radix_lock); ret = radix_tree_insert(&fs_info->fs_roots_radix, - (unsigned long)root->root_key.objectid, + (unsigned long)btrfs_root_id(root), root); - if (ret == 0) - root->in_radix = 1; + 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_read_fs_root_no_name(struct btrfs_fs_info *fs_info, - struct btrfs_key *location) +void btrfs_check_leaked_roots(const struct btrfs_fs_info *fs_info) +{ +#ifdef CONFIG_BTRFS_DEBUG + struct btrfs_root *root; + + while (!list_empty(&fs_info->allocated_roots)) { + char buf[BTRFS_ROOT_NAME_BUF_LEN]; + + root = list_first_entry(&fs_info->allocated_roots, + struct btrfs_root, leak_list); + btrfs_err(fs_info, "leaked root %s refcount %d", + btrfs_root_name(&root->root_key, buf), + refcount_read(&root->refs)); + WARN_ON_ONCE(1); + while (refcount_read(&root->refs) > 1) + btrfs_put_root(root); + btrfs_put_root(root); + } +#endif +} + +static void free_global_roots(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; + struct rb_node *node; + + while ((node = rb_first_postorder(&fs_info->global_root_tree)) != NULL) { + root = rb_entry(node, struct btrfs_root, rb_node); + rb_erase(&root->rb_node, &fs_info->global_root_tree); + btrfs_put_root(root); + } +} + +void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) +{ + struct percpu_counter *em_counter = &fs_info->evictable_extent_maps; + + if (fs_info->fs_devices) + btrfs_close_devices(fs_info->fs_devices); + btrfs_free_compress_wsm(fs_info); + percpu_counter_destroy(&fs_info->stats_read_blocks); + percpu_counter_destroy(&fs_info->dirty_metadata_bytes); + percpu_counter_destroy(&fs_info->delalloc_bytes); + percpu_counter_destroy(&fs_info->ordered_bytes); + if (percpu_counter_initialized(em_counter)) + ASSERT(percpu_counter_sum_positive(em_counter) == 0); + percpu_counter_destroy(em_counter); + percpu_counter_destroy(&fs_info->dev_replace.bio_counter); + btrfs_free_csum_hash(fs_info); + btrfs_free_stripe_hash_table(fs_info); + btrfs_free_ref_cache(fs_info); + kfree(fs_info->balance_ctl); + kfree(fs_info->delayed_root); + 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_put_root(fs_info->stripe_root); + btrfs_check_leaked_roots(fs_info); + btrfs_extent_buffer_leak_debug_check(fs_info); + kfree(fs_info->super_copy); + kfree(fs_info->super_for_commit); + 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 NULL for a new allocation. + * @check_ref: whether to check root item references, If true, return -ENOENT + * for orphan roots + */ +static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t *anon_dev, + bool check_ref) +{ + struct btrfs_root *root; + struct btrfs_path *path; + struct btrfs_key key; int ret; - if (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); -again: - root = btrfs_lookup_fs_root(fs_info, location->objectid); + root = btrfs_get_global_root(fs_info, objectid); if (root) return root; - root = btrfs_read_fs_root(fs_info->tree_root, location); + /* + * If we're called for non-subvolume trees, and above function didn't + * find one, do not try to read it from disk. + * + * This is namely for free-space-tree and quota tree, which can change + * at runtime and should only be grabbed from fs_info. + */ + if (!btrfs_is_fstree(objectid) && objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) + return ERR_PTR(-ENOENT); +again: + root = btrfs_lookup_fs_root(fs_info, objectid); + if (root) { + /* + * Some other caller may have read out the newly inserted + * subvolume already (for things like backref walk etc). Not + * that common but still possible. In that case, we just need + * to free the anon_dev. + */ + if (unlikely(anon_dev && *anon_dev)) { + free_anon_bdev(*anon_dev); + *anon_dev = 0; + } + + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { + btrfs_put_root(root); + return ERR_PTR(-ENOENT); + } + return root; + } + + 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; - if (btrfs_root_refs(&root->root_item) == 0) { + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { ret = -ENOENT; goto fail; } - ret = btrfs_init_fs_root(root); + ret = btrfs_init_fs_root(root, anon_dev ? *anon_dev : 0); if (ret) goto fail; - ret = btrfs_find_orphan_item(fs_info->tree_root, location->objectid); + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto fail; + } + key.objectid = BTRFS_ORPHAN_OBJECTID; + key.type = BTRFS_ORPHAN_ITEM_KEY; + key.offset = objectid; + + ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); + btrfs_free_path(path); if (ret < 0) goto fail; if (ret == 0) - root->orphan_item_inserted = 1; + set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); ret = btrfs_insert_fs_root(fs_info, root); if (ret) { if (ret == -EEXIST) { - free_fs_root(root); + btrfs_put_root(root); goto again; } goto fail; } return root; fail: - 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 && *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; - - rcu_read_lock(); - list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) { - if (!device->bdev) - continue; - bdi = blk_get_backing_dev_info(device->bdev); - if (bdi && bdi_congested(bdi, bdi_bits)) { - ret = 1; - break; - } - } - rcu_read_unlock(); - return ret; + return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref); } /* - * If this fails, caller must call bdi_destroy() to get rid of the - * bdi again. + * Get in-memory reference of a root structure, created as new, optionally pass + * the anonymous block device id + * + * @objectid: tree objectid + * @anon_dev: if NULL, allocate a new anonymous block device or use the + * parameter value if not NULL */ -static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi) +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t *anon_dev) { - int err; - - bdi->capabilities = BDI_CAP_MAP_COPY; - err = bdi_setup_and_register(bdi, "btrfs", BDI_CAP_MAP_COPY); - if (err) - return err; - - bdi->ra_pages = default_backing_dev_info.ra_pages; - bdi->congested_fn = btrfs_congested_fn; - bdi->congested_data = info; - return 0; + return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); } /* - * called by the kthread helper functions to finally call the bio end_io - * functions. This is where read checksum verification actually happens + * Return a root for the given objectid. + * + * @fs_info: the fs_info + * @objectid: the objectid we need to lookup + * + * This is exclusively used for backref walking, and exists specifically because + * of how qgroups does lookups. Qgroups will do a backref lookup at delayed ref + * creation time, which means we may have to read the tree_root in order to look + * up a fs root that is not in memory. If the root is not in memory we will + * read the tree root commit root and look up the fs root from there. This is a + * temporary root, it will not be inserted into the radix tree as it doesn't + * have the most uptodate information, it'll simply be discarded once the + * backref code is finished using the root. */ -static void end_workqueue_fn(struct btrfs_work *work) +struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, + u64 objectid) { - struct bio *bio; - struct end_io_wq *end_io_wq; - struct btrfs_fs_info *fs_info; - int error; + struct btrfs_root *root; + struct btrfs_key key; + + ASSERT(path->search_commit_root && path->skip_locking); - end_io_wq = container_of(work, struct end_io_wq, work); - bio = end_io_wq->bio; - fs_info = end_io_wq->info; + /* + * 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; - error = end_io_wq->error; - bio->bi_private = end_io_wq->private; - bio->bi_end_io = end_io_wq->end_io; - kfree(end_io_wq); - bio_endio(bio, error); + key.objectid = objectid; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + root = read_tree_root_path(fs_info->tree_root, path, &key); + btrfs_release_path(path); + + return root; } static int cleaner_kthread(void *arg) { - struct btrfs_root *root = arg; + struct btrfs_fs_info *fs_info = arg; int again; - do { + while (1) { again = 0; + set_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); + /* Make the cleaner go to sleep early. */ - if (btrfs_need_cleaner_sleep(root)) + if (btrfs_need_cleaner_sleep(fs_info)) goto sleep; - if (!mutex_trylock(&root->fs_info->cleaner_mutex)) + /* + * Do not do anything if we might cause open_ctree() to block + * before we have finished mounting the filesystem. + */ + if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags)) + goto sleep; + + if (!mutex_trylock(&fs_info->cleaner_mutex)) goto sleep; /* * Avoid the problem that we change the status of the fs * during the above check and trylock. */ - if (btrfs_need_cleaner_sleep(root)) { - mutex_unlock(&root->fs_info->cleaner_mutex); + if (btrfs_need_cleaner_sleep(fs_info)) { + mutex_unlock(&fs_info->cleaner_mutex); goto sleep; } - btrfs_run_delayed_iputs(root); - again = btrfs_clean_one_deleted_snapshot(root); - mutex_unlock(&root->fs_info->cleaner_mutex); + if (test_and_clear_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags)) + btrfs_sysfs_feature_update(fs_info); + + btrfs_run_delayed_iputs(fs_info); + + again = btrfs_clean_one_deleted_snapshot(fs_info); + mutex_unlock(&fs_info->cleaner_mutex); /* * The defragger has dealt with the R/O remount and umount, * needn't do anything special here. */ - btrfs_run_defrag_inodes(root->fs_info); + btrfs_run_defrag_inodes(fs_info); + + /* + * Acquires fs_info->reclaim_bgs_lock to avoid racing + * with relocation (btrfs_relocate_chunk) and relocation + * acquires fs_info->cleaner_mutex (btrfs_relocate_block_group) + * after acquiring fs_info->reclaim_bgs_lock. So we + * can't hold, nor need to, fs_info->cleaner_mutex when deleting + * unused block groups. + */ + btrfs_delete_unused_bgs(fs_info); + + /* + * Reclaim block groups in the reclaim_bgs list after we deleted + * all unused block_groups. This possibly gives us some more free + * space. + */ + btrfs_reclaim_bgs(fs_info); sleep: - if (!try_to_freeze() && !again) { + clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); + if (kthread_should_park()) + kthread_parkme(); + if (kthread_should_stop()) + return 0; + if (!again) { set_current_state(TASK_INTERRUPTIBLE); - if (!kthread_should_stop()) - schedule(); + schedule(); __set_current_state(TASK_RUNNING); } - } while (!kthread_should_stop()); - return 0; + } } static int transaction_kthread(void *arg) { struct btrfs_root *root = arg; + struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_trans_handle *trans; struct btrfs_transaction *cur; u64 transid; - unsigned long now; + time64_t delta; unsigned long delay; bool cannot_commit; do { cannot_commit = false; - delay = HZ * 30; - mutex_lock(&root->fs_info->transaction_kthread_mutex); + delay = secs_to_jiffies(fs_info->commit_interval); + mutex_lock(&fs_info->transaction_kthread_mutex); - spin_lock(&root->fs_info->trans_lock); - cur = root->fs_info->running_transaction; + spin_lock(&fs_info->trans_lock); + cur = fs_info->running_transaction; if (!cur) { - spin_unlock(&root->fs_info->trans_lock); + spin_unlock(&fs_info->trans_lock); goto sleep; } - now = get_seconds(); - if (cur->state < TRANS_STATE_BLOCKED && - (now < cur->start_time || now - cur->start_time < 30)) { - spin_unlock(&root->fs_info->trans_lock); - delay = HZ * 5; + delta = ktime_get_seconds() - cur->start_time; + if (!test_and_clear_bit(BTRFS_FS_COMMIT_TRANS, &fs_info->flags) && + cur->state < TRANS_STATE_COMMIT_PREP && + delta < fs_info->commit_interval) { + spin_unlock(&fs_info->trans_lock); + delay -= secs_to_jiffies(delta - 1); + delay = min(delay, + secs_to_jiffies(fs_info->commit_interval)); goto sleep; } transid = cur->transid; - spin_unlock(&root->fs_info->trans_lock); + spin_unlock(&fs_info->trans_lock); /* If the file system is aborted, this will always fail. */ trans = btrfs_attach_transaction(root); @@ -1765,39 +1584,37 @@ static int transaction_kthread(void *arg) goto sleep; } if (transid == trans->transid) { - btrfs_commit_transaction(trans, root); + btrfs_commit_transaction(trans); } else { - btrfs_end_transaction(trans, root); + btrfs_end_transaction(trans); } sleep: - wake_up_process(root->fs_info->cleaner_kthread); - mutex_unlock(&root->fs_info->transaction_kthread_mutex); - - if (!try_to_freeze()) { - set_current_state(TASK_INTERRUPTIBLE); - if (!kthread_should_stop() && - (!btrfs_transaction_blocked(root->fs_info) || - cannot_commit)) - schedule_timeout(delay); - __set_current_state(TASK_RUNNING); - } + wake_up_process(fs_info->cleaner_kthread); + mutex_unlock(&fs_info->transaction_kthread_mutex); + + if (BTRFS_FS_ERROR(fs_info)) + btrfs_cleanup_transaction(fs_info); + if (!kthread_should_stop() && + (!btrfs_transaction_blocked(fs_info) || + cannot_commit)) + schedule_timeout_interruptible(delay); } while (!kthread_should_stop()); return 0; } /* - * this will find the highest generation in the array of - * root backups. The index of the highest array is returned, - * or -1 if we can't find anything. + * This will find the highest generation in the array of root backups. The + * index of the highest array is returned, or -EINVAL if we can't find + * anything. * * We check to make sure the array is valid by comparing the * generation of the latest root in the array with the generation * in the super block. If they don't match we pitch it. */ -static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen) +static int find_newest_super_backup(struct btrfs_fs_info *info) { + const u64 newest_gen = btrfs_super_generation(info->super_copy); u64 cur; - int newest_index = -1; struct btrfs_root_backup *root_backup; int i; @@ -1805,37 +1622,10 @@ static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen) root_backup = info->super_copy->super_roots + i; cur = btrfs_backup_tree_root_gen(root_backup); if (cur == newest_gen) - newest_index = i; + return i; } - /* check to see if we actually wrapped around */ - if (newest_index == BTRFS_NUM_BACKUP_ROOTS - 1) { - root_backup = info->super_copy->super_roots; - cur = btrfs_backup_tree_root_gen(root_backup); - if (cur == newest_gen) - newest_index = 0; - } - return newest_index; -} - - -/* - * find the oldest backup so we know where to store new entries - * in the backup array. This will set the backup_root_index - * field in the fs_info struct - */ -static void find_oldest_super_backup(struct btrfs_fs_info *info, - u64 newest_gen) -{ - int newest_index = -1; - - newest_index = find_newest_super_backup(info, newest_gen); - /* if there was garbage in there, just move along */ - if (newest_index == -1) { - info->backup_root_index = 0; - } else { - info->backup_root_index = (newest_index + 1) % BTRFS_NUM_BACKUP_ROOTS; - } + return -EINVAL; } /* @@ -1845,22 +1635,8 @@ static void find_oldest_super_backup(struct btrfs_fs_info *info, */ static void backup_super_roots(struct btrfs_fs_info *info) { - int next_backup; + const int next_backup = info->backup_root_index; struct btrfs_root_backup *root_backup; - int last_backup; - - next_backup = info->backup_root_index; - last_backup = (next_backup + BTRFS_NUM_BACKUP_ROOTS - 1) % - BTRFS_NUM_BACKUP_ROOTS; - - /* - * just overwrite the last backup if we're at the same generation - * this happens only at umount - */ - root_backup = info->super_for_commit->super_roots + last_backup; - if (btrfs_backup_tree_root_gen(root_backup) == - btrfs_header_generation(info->tree_root->node)) - next_backup = last_backup; root_backup = info->super_for_commit->super_roots + next_backup; @@ -1885,11 +1661,23 @@ static void backup_super_roots(struct btrfs_fs_info *info) btrfs_set_backup_chunk_root_level(root_backup, btrfs_header_level(info->chunk_root->node)); - btrfs_set_backup_extent_root(root_backup, info->extent_root->node->start); - btrfs_set_backup_extent_root_gen(root_backup, - btrfs_header_generation(info->extent_root->node)); - btrfs_set_backup_extent_root_level(root_backup, - btrfs_header_level(info->extent_root->node)); + if (!btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE)) { + struct btrfs_root *extent_root = btrfs_extent_root(info, 0); + struct btrfs_root *csum_root = btrfs_csum_root(info, 0); + + btrfs_set_backup_extent_root(root_backup, + extent_root->node->start); + btrfs_set_backup_extent_root_gen(root_backup, + btrfs_header_generation(extent_root->node)); + btrfs_set_backup_extent_root_level(root_backup, + btrfs_header_level(extent_root->node)); + + btrfs_set_backup_csum_root(root_backup, csum_root->node->start); + btrfs_set_backup_csum_root_gen(root_backup, + btrfs_header_generation(csum_root->node)); + btrfs_set_backup_csum_root_level(root_backup, + btrfs_header_level(csum_root->node)); + } /* * we might commit during log recovery, which happens before we set @@ -1910,12 +1698,6 @@ static void backup_super_roots(struct btrfs_fs_info *info) btrfs_set_backup_dev_root_level(root_backup, btrfs_header_level(info->dev_root->node)); - btrfs_set_backup_csum_root(root_backup, info->csum_root->node->start); - btrfs_set_backup_csum_root_gen(root_backup, - btrfs_header_generation(info->csum_root->node)); - btrfs_set_backup_csum_root_level(root_backup, - btrfs_header_level(info->csum_root->node)); - btrfs_set_backup_total_bytes(root_backup, btrfs_super_total_bytes(info->super_copy)); btrfs_set_backup_bytes_used(root_backup, @@ -1933,40 +1715,31 @@ static void backup_super_roots(struct btrfs_fs_info *info) } /* - * this copies info out of the root backup array and back into - * the in-memory super block. It is meant to help iterate through - * the array, so you send it the number of backups you've already - * tried and the last backup index you used. + * Reads a backup root based on the passed priority. Prio 0 is the newest, prio + * 1/2/3 are 2nd newest/3rd newest/4th (oldest) backup roots * - * this returns -1 when it has tried all the backups + * @fs_info: filesystem whose backup roots need to be read + * @priority: priority of backup root required + * + * Returns backup root index on success and -EINVAL otherwise. */ -static noinline int next_root_backup(struct btrfs_fs_info *info, - struct btrfs_super_block *super, - int *num_backups_tried, int *backup_index) +static int read_backup_root(struct btrfs_fs_info *fs_info, u8 priority) { + int backup_index = find_newest_super_backup(fs_info); + struct btrfs_super_block *super = fs_info->super_copy; struct btrfs_root_backup *root_backup; - int newest = *backup_index; - - if (*num_backups_tried == 0) { - u64 gen = btrfs_super_generation(super); - newest = find_newest_super_backup(info, gen); - if (newest == -1) - return -1; + if (priority < BTRFS_NUM_BACKUP_ROOTS && backup_index >= 0) { + if (priority == 0) + return backup_index; - *backup_index = newest; - *num_backups_tried = 1; - } else if (*num_backups_tried == BTRFS_NUM_BACKUP_ROOTS) { - /* we've tried all the backups, all done */ - return -1; + backup_index = backup_index + BTRFS_NUM_BACKUP_ROOTS - priority; + backup_index %= BTRFS_NUM_BACKUP_ROOTS; } else { - /* jump to the next oldest backup */ - newest = (*backup_index + BTRFS_NUM_BACKUP_ROOTS - 1) % - BTRFS_NUM_BACKUP_ROOTS; - *backup_index = newest; - *num_backups_tried += 1; + return -EINVAL; } - root_backup = super->super_roots + newest; + + root_backup = super->super_roots + backup_index; btrfs_set_super_generation(super, btrfs_backup_tree_root_gen(root_backup)); @@ -1976,94 +1749,116 @@ static noinline int next_root_backup(struct btrfs_fs_info *info, btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup)); /* - * fixme: the total bytes and num_devices need to match or we should + * Fixme: the total bytes and num_devices need to match or we should * need a fsck */ btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup)); btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup)); - return 0; + + return backup_index; } /* helper to cleanup workers */ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) { - btrfs_stop_workers(&fs_info->generic_worker); - btrfs_stop_workers(&fs_info->fixup_workers); - btrfs_stop_workers(&fs_info->delalloc_workers); - btrfs_stop_workers(&fs_info->workers); - btrfs_stop_workers(&fs_info->endio_workers); - btrfs_stop_workers(&fs_info->endio_meta_workers); - btrfs_stop_workers(&fs_info->endio_raid56_workers); - btrfs_stop_workers(&fs_info->rmw_workers); - btrfs_stop_workers(&fs_info->endio_meta_write_workers); - btrfs_stop_workers(&fs_info->endio_write_workers); - btrfs_stop_workers(&fs_info->endio_freespace_worker); - btrfs_stop_workers(&fs_info->submit_workers); - btrfs_stop_workers(&fs_info->delayed_workers); - btrfs_stop_workers(&fs_info->caching_workers); - btrfs_stop_workers(&fs_info->readahead_workers); - btrfs_stop_workers(&fs_info->flush_workers); - btrfs_stop_workers(&fs_info->qgroup_rescan_workers); + btrfs_destroy_workqueue(fs_info->fixup_workers); + btrfs_destroy_workqueue(fs_info->delalloc_workers); + btrfs_destroy_workqueue(fs_info->workers); + if (fs_info->endio_workers) + destroy_workqueue(fs_info->endio_workers); + if (fs_info->rmw_workers) + destroy_workqueue(fs_info->rmw_workers); + btrfs_destroy_workqueue(fs_info->endio_write_workers); + btrfs_destroy_workqueue(fs_info->endio_freespace_worker); + btrfs_destroy_workqueue(fs_info->delayed_workers); + btrfs_destroy_workqueue(fs_info->caching_workers); + btrfs_destroy_workqueue(fs_info->flush_workers); + btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers); + if (fs_info->discard_ctl.discard_workers) + destroy_workqueue(fs_info->discard_ctl.discard_workers); + /* + * Now that all other work queues are destroyed, we can safely destroy + * the queues used for metadata I/O, since tasks from those other work + * queues can do metadata I/O operations. + */ + if (fs_info->endio_meta_workers) + destroy_workqueue(fs_info->endio_meta_workers); +} + +static void free_root_extent_buffers(struct btrfs_root *root) +{ + if (root) { + free_extent_buffer(root->node); + free_extent_buffer(root->commit_root); + root->node = NULL; + root->commit_root = NULL; + } +} + +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, int chunk_root) +static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root) { - free_extent_buffer(info->tree_root->node); - free_extent_buffer(info->tree_root->commit_root); - info->tree_root->node = NULL; - info->tree_root->commit_root = NULL; + free_root_extent_buffers(info->tree_root); + + free_global_root_pointers(info); + free_root_extent_buffers(info->dev_root); + free_root_extent_buffers(info->quota_root); + free_root_extent_buffers(info->uuid_root); + free_root_extent_buffers(info->fs_root); + free_root_extent_buffers(info->data_reloc_root); + free_root_extent_buffers(info->block_group_root); + free_root_extent_buffers(info->stripe_root); + if (free_chunk_root) + free_root_extent_buffers(info->chunk_root); +} - if (info->dev_root) { - free_extent_buffer(info->dev_root->node); - free_extent_buffer(info->dev_root->commit_root); - info->dev_root->node = NULL; - info->dev_root->commit_root = NULL; - } - if (info->extent_root) { - free_extent_buffer(info->extent_root->node); - free_extent_buffer(info->extent_root->commit_root); - info->extent_root->node = NULL; - info->extent_root->commit_root = NULL; - } - if (info->csum_root) { - free_extent_buffer(info->csum_root->node); - free_extent_buffer(info->csum_root->commit_root); - info->csum_root->node = NULL; - info->csum_root->commit_root = NULL; - } - if (info->quota_root) { - free_extent_buffer(info->quota_root->node); - free_extent_buffer(info->quota_root->commit_root); - info->quota_root->node = NULL; - info->quota_root->commit_root = NULL; - } - if (chunk_root) { - free_extent_buffer(info->chunk_root->node); - free_extent_buffer(info->chunk_root->commit_root); - info->chunk_root->node = NULL; - info->chunk_root->commit_root = NULL; +void btrfs_put_root(struct btrfs_root *root) +{ + if (!root) + return; + + if (refcount_dec_and_test(&root->refs)) { + if (WARN_ON(!xa_empty(&root->inodes))) + xa_destroy(&root->inodes); + if (WARN_ON(!xa_empty(&root->delayed_nodes))) + xa_destroy(&root->delayed_nodes); + WARN_ON(test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state)); + if (root->anon_dev) + free_anon_bdev(root->anon_dev); + free_root_extent_buffers(root); +#ifdef CONFIG_BTRFS_DEBUG + spin_lock(&root->fs_info->fs_roots_radix_lock); + list_del_init(&root->leak_list); + spin_unlock(&root->fs_info->fs_roots_radix_lock); +#endif + kfree(root); } } -static void del_fs_roots(struct btrfs_fs_info *fs_info) +void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info) { int ret; struct btrfs_root *gang[8]; int i; while (!list_empty(&fs_info->dead_roots)) { - gang[0] = list_entry(fs_info->dead_roots.next, - struct btrfs_root, root_list); + gang[0] = list_first_entry(&fs_info->dead_roots, + struct btrfs_root, root_list); list_del(&gang[0]->root_list); - if (gang[0]->in_radix) { + 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) { @@ -2077,75 +1872,885 @@ static void del_fs_roots(struct btrfs_fs_info *fs_info) } } -int open_ctree(struct super_block *sb, - struct btrfs_fs_devices *fs_devices, - char *options) +static void btrfs_init_scrub(struct btrfs_fs_info *fs_info) +{ + mutex_init(&fs_info->scrub_lock); + atomic_set(&fs_info->scrubs_running, 0); + atomic_set(&fs_info->scrub_pause_req, 0); + atomic_set(&fs_info->scrubs_paused, 0); + atomic_set(&fs_info->scrub_cancel_req, 0); + init_waitqueue_head(&fs_info->scrub_pause_wait); + refcount_set(&fs_info->scrub_workers_refcnt, 0); +} + +static void btrfs_init_balance(struct btrfs_fs_info *fs_info) +{ + spin_lock_init(&fs_info->balance_lock); + mutex_init(&fs_info->balance_mutex); + atomic_set(&fs_info->balance_pause_req, 0); + 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 int btrfs_init_btree_inode(struct super_block *sb) { - u32 sectorsize; - u32 nodesize; - u32 leafsize; - u32 blocksize; - u32 stripesize; - u64 generation; - u64 features; - 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 *extent_root; - struct btrfs_root *csum_root; - struct btrfs_root *chunk_root; - struct btrfs_root *dev_root; - struct btrfs_root *quota_root; - struct btrfs_root *log_tree_root; + unsigned long hash = btrfs_inode_hash(BTRFS_BTREE_INODE_OBJECTID, + fs_info->tree_root); + struct inode *inode; + + inode = new_inode(sb); + if (!inode) + return -ENOMEM; + + btrfs_set_inode_number(BTRFS_I(inode), BTRFS_BTREE_INODE_OBJECTID); + set_nlink(inode, 1); + /* + * we set the i_size on the btree inode to the max possible int. + * the real end of the address space is determined by all of + * the devices in the system + */ + inode->i_size = OFFSET_MAX; + inode->i_mapping->a_ops = &btree_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); + + btrfs_extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree, + IO_TREE_BTREE_INODE_IO); + btrfs_extent_map_tree_init(&BTRFS_I(inode)->extent_tree); + + BTRFS_I(inode)->root = btrfs_grab_root(fs_info->tree_root); + set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags); + __insert_inode_hash(inode, hash); + set_bit(AS_KERNEL_FILE, &inode->i_mapping->flags); + fs_info->btree_inode = inode; + + return 0; +} + +static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info) +{ + mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount); + init_rwsem(&fs_info->dev_replace.rwsem); + init_waitqueue_head(&fs_info->dev_replace.replace_wait); +} + +static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) +{ + spin_lock_init(&fs_info->qgroup_lock); + mutex_init(&fs_info->qgroup_ioctl_lock); + fs_info->qgroup_tree = RB_ROOT; + INIT_LIST_HEAD(&fs_info->dirty_qgroups); + fs_info->qgroup_seq = 1; + fs_info->qgroup_rescan_running = false; + fs_info->qgroup_drop_subtree_thres = BTRFS_QGROUP_DROP_SUBTREE_THRES_DEFAULT; + mutex_init(&fs_info->qgroup_rescan_lock); +} + +static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info) +{ + u32 max_active = fs_info->thread_pool_size; + unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND; + unsigned int ordered_flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_PERCPU; + + fs_info->workers = + btrfs_alloc_workqueue(fs_info, "worker", flags, max_active, 16); + + fs_info->delalloc_workers = + btrfs_alloc_workqueue(fs_info, "delalloc", + flags, max_active, 2); + + fs_info->flush_workers = + btrfs_alloc_workqueue(fs_info, "flush_delalloc", + flags, max_active, 0); + + fs_info->caching_workers = + btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0); + + fs_info->fixup_workers = + btrfs_alloc_ordered_workqueue(fs_info, "fixup", ordered_flags); + + fs_info->endio_workers = + alloc_workqueue("btrfs-endio", flags, max_active); + fs_info->endio_meta_workers = + alloc_workqueue("btrfs-endio-meta", flags, max_active); + fs_info->rmw_workers = alloc_workqueue("btrfs-rmw", flags, max_active); + fs_info->endio_write_workers = + btrfs_alloc_workqueue(fs_info, "endio-write", flags, + max_active, 2); + 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->qgroup_rescan_workers = + btrfs_alloc_ordered_workqueue(fs_info, "qgroup-rescan", + ordered_flags); + fs_info->discard_ctl.discard_workers = + alloc_ordered_workqueue("btrfs-discard", WQ_FREEZABLE); + + if (!(fs_info->workers && + fs_info->delalloc_workers && fs_info->flush_workers && + fs_info->endio_workers && fs_info->endio_meta_workers && + fs_info->endio_write_workers && + fs_info->endio_freespace_worker && fs_info->rmw_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; + } + + return 0; +} + +static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) +{ + struct crypto_shash *csum_shash; + const char *csum_driver = btrfs_super_csum_driver(csum_type); + + csum_shash = crypto_alloc_shash(csum_driver, 0, 0); + + if (IS_ERR(csum_shash)) { + btrfs_err(fs_info, "error allocating %s hash for checksum", + csum_driver); + return PTR_ERR(csum_shash); + } + + fs_info->csum_shash = csum_shash; + + /* Check if the checksum implementation is a fast accelerated one. */ + switch (csum_type) { + case BTRFS_CSUM_TYPE_CRC32: + if (crc32_optimizations() & CRC32C_OPTIMIZATION) + set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); + break; + case BTRFS_CSUM_TYPE_XXHASH: + set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); + break; + default: + break; + } + + btrfs_info(fs_info, "using %s (%s) checksum algorithm", + btrfs_super_csum_name(csum_type), + crypto_shash_driver_name(csum_shash)); + return 0; +} + +static int btrfs_replay_log(struct btrfs_fs_info *fs_info, + struct btrfs_fs_devices *fs_devices) +{ int ret; - int err = -EINVAL; - int num_backups_tried = 0; - int backup_index = 0; + struct btrfs_tree_parent_check check = { 0 }; + struct btrfs_root *log_tree_root; + struct btrfs_super_block *disk_super = fs_info->super_copy; + u64 bytenr = btrfs_super_log_root(disk_super); + int level = btrfs_super_log_root_level(disk_super); - tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info); - chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info); - if (!tree_root || !chunk_root) { - err = -ENOMEM; - goto fail; + if (unlikely(fs_devices->rw_devices == 0)) { + btrfs_warn(fs_info, "log replay required on RO media"); + return -EIO; } - ret = init_srcu_struct(&fs_info->subvol_srcu); - if (ret) { - err = ret; - goto fail; + log_tree_root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, + GFP_KERNEL); + if (!log_tree_root) + return -ENOMEM; + + check.level = level; + check.transid = fs_info->generation + 1; + check.owner_root = BTRFS_TREE_LOG_OBJECTID; + log_tree_root->node = read_tree_block(fs_info, bytenr, &check); + if (IS_ERR(log_tree_root->node)) { + btrfs_warn(fs_info, "failed to read log tree"); + ret = PTR_ERR(log_tree_root->node); + log_tree_root->node = NULL; + btrfs_put_root(log_tree_root); + return ret; + } + if (unlikely(!extent_buffer_uptodate(log_tree_root->node))) { + btrfs_err(fs_info, "failed to read log tree"); + btrfs_put_root(log_tree_root); + return -EIO; } - ret = setup_bdi(fs_info, &fs_info->bdi); + /* returns with log_tree_root freed on success */ + ret = btrfs_recover_log_trees(log_tree_root); + btrfs_put_root(log_tree_root); if (ret) { - err = ret; - goto fail_srcu; + btrfs_handle_fs_error(fs_info, ret, + "Failed to recover log tree"); + return ret; } - ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0); - if (ret) { - err = ret; - goto fail_bdi; + if (sb_rdonly(fs_info->sb)) { + ret = btrfs_commit_super(fs_info); + if (ret) + return ret; + } + + return 0; +} + +static int load_global_roots_objectid(struct btrfs_root *tree_root, + struct btrfs_path *path, u64 objectid, + const char *name) +{ + struct btrfs_fs_info *fs_info = tree_root->fs_info; + struct btrfs_root *root; + u64 max_global_id = 0; + int ret; + struct btrfs_key key = { + .objectid = objectid, + .type = BTRFS_ROOT_ITEM_KEY, + .offset = 0, + }; + bool found = false; + + /* If we have IGNOREDATACSUMS skip loading these roots. */ + if (objectid == BTRFS_CSUM_TREE_OBJECTID && + btrfs_test_opt(fs_info, IGNOREDATACSUMS)) { + set_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state); + return 0; + } + + while (1) { + ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0); + if (ret < 0) + break; + + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_leaf(tree_root, path); + if (ret) { + if (ret > 0) + ret = 0; + break; + } + } + ret = 0; + + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + if (key.objectid != objectid) + break; + btrfs_release_path(path); + + /* + * Just worry about this for extent tree, it'll be the same for + * everybody. + */ + if (objectid == BTRFS_EXTENT_TREE_OBJECTID) + max_global_id = max(max_global_id, key.offset); + + found = true; + root = read_tree_root_path(tree_root, path, &key); + if (IS_ERR(root)) { + ret = PTR_ERR(root); + break; + } + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + ret = btrfs_global_root_insert(root); + if (ret) { + btrfs_put_root(root); + break; + } + key.offset++; + } + btrfs_release_path(path); + + if (objectid == BTRFS_EXTENT_TREE_OBJECTID) + fs_info->nr_global_roots = max_global_id + 1; + + if (!found || ret) { + if (objectid == BTRFS_CSUM_TREE_OBJECTID) + set_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state); + + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) + ret = ret ? ret : -ENOENT; + else + ret = 0; + btrfs_err(fs_info, "failed to load root %s", name); + } + return ret; +} + +static int load_global_roots(struct btrfs_root *tree_root) +{ + BTRFS_PATH_AUTO_FREE(path); + int ret; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + ret = load_global_roots_objectid(tree_root, path, + BTRFS_EXTENT_TREE_OBJECTID, "extent"); + if (ret) + return ret; + ret = load_global_roots_objectid(tree_root, path, + BTRFS_CSUM_TREE_OBJECTID, "csum"); + if (ret) + return ret; + if (!btrfs_fs_compat_ro(tree_root->fs_info, FREE_SPACE_TREE)) + return ret; + ret = load_global_roots_objectid(tree_root, path, + BTRFS_FREE_SPACE_TREE_OBJECTID, + "free space"); + + return ret; +} + +static int btrfs_read_roots(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *tree_root = fs_info->tree_root; + struct btrfs_root *root; + struct btrfs_key location; + int ret; + + ASSERT(fs_info->tree_root); + + ret = load_global_roots(tree_root); + if (ret) + return ret; + + location.type = BTRFS_ROOT_ITEM_KEY; + location.offset = 0; + + if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE)) { + location.objectid = BTRFS_BLOCK_GROUP_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) { + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->block_group_root = root; + } + } + + location.objectid = BTRFS_DEV_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) { + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->dev_root = root; + } + /* Initialize fs_info for all devices in any case */ + ret = btrfs_init_devices_late(fs_info); + if (ret) + goto out; + + /* + * This tree can share blocks with some other fs tree during relocation + * and we need a proper setup by btrfs_get_fs_root + */ + root = btrfs_get_fs_root(tree_root->fs_info, + BTRFS_DATA_RELOC_TREE_OBJECTID, true); + if (IS_ERR(root)) { + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->data_reloc_root = root; + } + + location.objectid = BTRFS_QUOTA_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (!IS_ERR(root)) { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->quota_root = root; + } + + location.objectid = BTRFS_UUID_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); + if (ret != -ENOENT) + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->uuid_root = root; + } + + if (btrfs_fs_incompat(fs_info, RAID_STRIPE_TREE)) { + location.objectid = BTRFS_RAID_STRIPE_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) { + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->stripe_root = root; + } + } + + return 0; +out: + btrfs_warn(fs_info, "failed to read root (objectid=%llu): %d", + location.objectid, ret); + return ret; +} + +static int validate_sys_chunk_array(const struct btrfs_fs_info *fs_info, + const struct btrfs_super_block *sb) +{ + unsigned int cur = 0; /* Offset inside the sys chunk array */ + /* + * At sb read time, fs_info is not fully initialized. Thus we have + * to use super block sectorsize, which should have been validated. + */ + const u32 sectorsize = btrfs_super_sectorsize(sb); + u32 sys_array_size = btrfs_super_sys_array_size(sb); + + if (unlikely(sys_array_size > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE)) { + btrfs_err(fs_info, "system chunk array too big %u > %u", + sys_array_size, BTRFS_SYSTEM_CHUNK_ARRAY_SIZE); + return -EUCLEAN; + } + + while (cur < sys_array_size) { + struct btrfs_disk_key *disk_key; + struct btrfs_chunk *chunk; + struct btrfs_key key; + u64 type; + u16 num_stripes; + u32 len; + int ret; + + disk_key = (struct btrfs_disk_key *)(sb->sys_chunk_array + cur); + len = sizeof(*disk_key); + + if (unlikely(cur + len > sys_array_size)) + goto short_read; + cur += len; + + btrfs_disk_key_to_cpu(&key, disk_key); + if (unlikely(key.type != BTRFS_CHUNK_ITEM_KEY)) { + btrfs_err(fs_info, + "unexpected item type %u in sys_array at offset %u", + key.type, cur); + return -EUCLEAN; + } + chunk = (struct btrfs_chunk *)(sb->sys_chunk_array + cur); + num_stripes = btrfs_stack_chunk_num_stripes(chunk); + if (unlikely(cur + btrfs_chunk_item_size(num_stripes) > sys_array_size)) + goto short_read; + type = btrfs_stack_chunk_type(chunk); + if (unlikely(!(type & BTRFS_BLOCK_GROUP_SYSTEM))) { + btrfs_err(fs_info, + "invalid chunk type %llu in sys_array at offset %u", + type, cur); + return -EUCLEAN; + } + ret = btrfs_check_chunk_valid(fs_info, NULL, chunk, key.offset, + sectorsize); + if (ret < 0) + return ret; + cur += btrfs_chunk_item_size(num_stripes); + } + return 0; +short_read: + btrfs_err(fs_info, + "super block sys chunk array short read, cur=%u sys_array_size=%u", + cur, sys_array_size); + return -EUCLEAN; +} + +/* + * Real super block validation + * NOTE: super csum type and incompat features will not be checked here. + * + * @sb: super block to check + * @mirror_num: the super block number to check its bytenr: + * 0 the primary (1st) sb + * 1, 2 2nd and 3rd backup copy + * -1 skip bytenr check + */ +int btrfs_validate_super(const struct btrfs_fs_info *fs_info, + const struct btrfs_super_block *sb, int mirror_num) +{ + u64 nodesize = btrfs_super_nodesize(sb); + u64 sectorsize = btrfs_super_sectorsize(sb); + int ret = 0; + const bool ignore_flags = btrfs_test_opt(fs_info, IGNORESUPERFLAGS); + + if (btrfs_super_magic(sb) != BTRFS_MAGIC) { + btrfs_err(fs_info, "no valid FS found"); + ret = -EINVAL; + } + if ((btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP)) { + if (!ignore_flags) { + btrfs_err(fs_info, + "unrecognized or unsupported super flag 0x%llx", + btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP); + ret = -EINVAL; + } else { + btrfs_info(fs_info, + "unrecognized or unsupported super flags: 0x%llx, ignored", + btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP); + } + } + if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) { + btrfs_err(fs_info, "tree_root level too big: %d >= %d", + btrfs_super_root_level(sb), BTRFS_MAX_LEVEL); + ret = -EINVAL; + } + if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) { + btrfs_err(fs_info, "chunk_root level too big: %d >= %d", + btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL); + ret = -EINVAL; + } + if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) { + btrfs_err(fs_info, "log_root level too big: %d >= %d", + btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL); + ret = -EINVAL; + } + + /* + * Check sectorsize and nodesize first, other check will need it. + * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here. + */ + if (!is_power_of_2(sectorsize) || sectorsize < BTRFS_MIN_BLOCKSIZE || + sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) { + btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize); + ret = -EINVAL; + } + + if (!btrfs_supported_blocksize(sectorsize)) { + btrfs_err(fs_info, + "sectorsize %llu not yet supported for page size %lu", + sectorsize, PAGE_SIZE); + ret = -EINVAL; + } + + if (!is_power_of_2(nodesize) || nodesize < sectorsize || + nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) { + btrfs_err(fs_info, "invalid nodesize %llu", nodesize); + ret = -EINVAL; + } + if (nodesize != le32_to_cpu(sb->__unused_leafsize)) { + btrfs_err(fs_info, "invalid leafsize %u, should be %llu", + le32_to_cpu(sb->__unused_leafsize), nodesize); + ret = -EINVAL; + } + + /* Root alignment check */ + if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) { + btrfs_warn(fs_info, "tree_root block unaligned: %llu", + btrfs_super_root(sb)); + ret = -EINVAL; + } + if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) { + btrfs_warn(fs_info, "chunk_root block unaligned: %llu", + btrfs_super_chunk_root(sb)); + ret = -EINVAL; + } + if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) { + btrfs_warn(fs_info, "log_root block unaligned: %llu", + btrfs_super_log_root(sb)); + ret = -EINVAL; + } + + if (!fs_info->fs_devices->temp_fsid && + memcmp(fs_info->fs_devices->fsid, sb->fsid, BTRFS_FSID_SIZE) != 0) { + btrfs_err(fs_info, + "superblock fsid doesn't match fsid of fs_devices: %pU != %pU", + sb->fsid, fs_info->fs_devices->fsid); + ret = -EINVAL; + } + + if (memcmp(fs_info->fs_devices->metadata_uuid, btrfs_sb_fsid_ptr(sb), + BTRFS_FSID_SIZE) != 0) { + btrfs_err(fs_info, +"superblock metadata_uuid doesn't match metadata uuid of fs_devices: %pU != %pU", + btrfs_sb_fsid_ptr(sb), fs_info->fs_devices->metadata_uuid); + ret = -EINVAL; + } + + if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid, + BTRFS_FSID_SIZE) != 0) { + btrfs_err(fs_info, + "dev_item UUID does not match metadata fsid: %pU != %pU", + fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid); + ret = -EINVAL; + } + + /* + * Artificial requirement for block-group-tree to force newer features + * (free-space-tree, no-holes) so the test matrix is smaller. + */ + if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE) && + (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID) || + !btrfs_fs_incompat(fs_info, NO_HOLES))) { + btrfs_err(fs_info, + "block-group-tree feature requires free-space-tree and no-holes"); + ret = -EINVAL; + } + + /* + * Hint to catch really bogus numbers, bitflips or so, more exact checks are + * done later + */ + if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) { + btrfs_err(fs_info, "bytes_used is too small %llu", + btrfs_super_bytes_used(sb)); + ret = -EINVAL; + } + if (!is_power_of_2(btrfs_super_stripesize(sb))) { + btrfs_err(fs_info, "invalid stripesize %u", + btrfs_super_stripesize(sb)); + ret = -EINVAL; + } + if (btrfs_super_num_devices(sb) > (1UL << 31)) + btrfs_warn(fs_info, "suspicious number of devices: %llu", + btrfs_super_num_devices(sb)); + if (btrfs_super_num_devices(sb) == 0) { + btrfs_err(fs_info, "number of devices is 0"); + ret = -EINVAL; + } + + if (mirror_num >= 0 && + btrfs_super_bytenr(sb) != btrfs_sb_offset(mirror_num)) { + btrfs_err(fs_info, "super offset mismatch %llu != %u", + btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET); + ret = -EINVAL; + } + + if (ret) + return ret; + + ret = validate_sys_chunk_array(fs_info, sb); + + /* + * Obvious sys_chunk_array corruptions, it must hold at least one key + * and one chunk + */ + if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) { + btrfs_err(fs_info, "system chunk array too big %u > %u", + btrfs_super_sys_array_size(sb), + BTRFS_SYSTEM_CHUNK_ARRAY_SIZE); + ret = -EINVAL; + } + if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key) + + sizeof(struct btrfs_chunk)) { + btrfs_err(fs_info, "system chunk array too small %u < %zu", + btrfs_super_sys_array_size(sb), + sizeof(struct btrfs_disk_key) + + sizeof(struct btrfs_chunk)); + ret = -EINVAL; + } + + /* + * The generation is a global counter, we'll trust it more than the others + * but it's still possible that it's the one that's wrong. + */ + if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb)) + btrfs_warn(fs_info, + "suspicious: generation < chunk_root_generation: %llu < %llu", + btrfs_super_generation(sb), + btrfs_super_chunk_root_generation(sb)); + if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb) + && btrfs_super_cache_generation(sb) != (u64)-1) + btrfs_warn(fs_info, + "suspicious: generation < cache_generation: %llu < %llu", + btrfs_super_generation(sb), + btrfs_super_cache_generation(sb)); + + return ret; +} + +/* + * Validation of super block at mount time. + * Some checks already done early at mount time, like csum type and incompat + * flags will be skipped. + */ +static int btrfs_validate_mount_super(struct btrfs_fs_info *fs_info) +{ + return btrfs_validate_super(fs_info, fs_info->super_copy, 0); +} + +/* + * Validation of super block at write time. + * Some checks like bytenr check will be skipped as their values will be + * overwritten soon. + * Extra checks like csum type and incompat flags will be done here. + */ +static int btrfs_validate_write_super(struct btrfs_fs_info *fs_info, + struct btrfs_super_block *sb) +{ + int ret; + + ret = btrfs_validate_super(fs_info, sb, -1); + if (ret < 0) + goto out; + if (unlikely(!btrfs_supported_super_csum(btrfs_super_csum_type(sb)))) { + ret = -EUCLEAN; + btrfs_err(fs_info, "invalid csum type, has %u want %u", + btrfs_super_csum_type(sb), BTRFS_CSUM_TYPE_CRC32); + goto out; + } + if (unlikely(btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP)) { + ret = -EUCLEAN; + btrfs_err(fs_info, + "invalid incompat flags, has 0x%llx valid mask 0x%llx", + btrfs_super_incompat_flags(sb), + (unsigned long long)BTRFS_FEATURE_INCOMPAT_SUPP); + goto out; + } +out: + if (ret < 0) + btrfs_err(fs_info, + "super block corruption detected before writing it to disk"); + return ret; +} + +static int load_super_root(struct btrfs_root *root, u64 bytenr, u64 gen, int level) +{ + struct btrfs_tree_parent_check check = { + .level = level, + .transid = gen, + .owner_root = btrfs_root_id(root) + }; + int ret = 0; + + root->node = read_tree_block(root->fs_info, bytenr, &check); + if (IS_ERR(root->node)) { + ret = PTR_ERR(root->node); + root->node = NULL; + return ret; + } + if (unlikely(!extent_buffer_uptodate(root->node))) { + free_extent_buffer(root->node); + root->node = NULL; + return -EIO; } - fs_info->dirty_metadata_batch = PAGE_CACHE_SIZE * - (1 + ilog2(nr_cpu_ids)); - ret = percpu_counter_init(&fs_info->delalloc_bytes, 0); + 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) { - err = ret; - goto fail_dirty_metadata_bytes; + btrfs_warn(fs_info, "couldn't read tree root"); + return ret; } + return 0; +} - fs_info->btree_inode = new_inode(sb); - if (!fs_info->btree_inode) { - err = -ENOMEM; - goto fail_delalloc_bytes; +static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) +{ + int backup_index = find_newest_super_backup(fs_info); + struct btrfs_super_block *sb = fs_info->super_copy; + struct btrfs_root *tree_root = fs_info->tree_root; + bool handle_error = false; + int ret = 0; + int i; + + for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) { + if (handle_error) { + if (!IS_ERR(tree_root->node)) + free_extent_buffer(tree_root->node); + tree_root->node = NULL; + + if (!btrfs_test_opt(fs_info, USEBACKUPROOT)) + break; + + free_root_pointers(fs_info, 0); + + /* + * Don't use the log in recovery mode, it won't be + * valid + */ + btrfs_set_super_log_root(sb, 0); + + btrfs_warn(fs_info, "try to load backup roots slot %d", i); + ret = read_backup_root(fs_info, i); + backup_index = ret; + if (ret < 0) + return ret; + } + + ret = load_important_roots(fs_info); + if (ret) { + handle_error = true; + continue; + } + + /* + * No need to hold btrfs_root::objectid_mutex since the fs + * hasn't been fully initialised and we are the only user + */ + ret = btrfs_init_root_free_objectid(tree_root); + if (ret < 0) { + handle_error = true; + continue; + } + + ASSERT(tree_root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); + + ret = btrfs_read_roots(fs_info); + if (ret < 0) { + handle_error = true; + continue; + } + + /* All successful */ + fs_info->generation = btrfs_header_generation(tree_root->node); + btrfs_set_last_trans_committed(fs_info, fs_info->generation); + fs_info->last_reloc_trans = 0; + + /* Always begin writing backup roots after the one being used */ + if (backup_index < 0) { + fs_info->backup_root_index = 0; + } else { + fs_info->backup_root_index = backup_index + 1; + fs_info->backup_root_index %= BTRFS_NUM_BACKUP_ROOTS; + } + break; } - mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS); + return ret; +} + +/* + * Lockdep gets confused between our buffer_tree which requires IRQ locking because + * we modify marks in the IRQ context, and our delayed inode xarray which doesn't + * have these requirements. Use a class key so lockdep doesn't get them mixed up. + */ +static struct lock_class_key buffer_xa_class; +void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) +{ INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC); + + /* Use the same flags as mapping->i_pages. */ + xa_init_flags(&fs_info->buffer_tree, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); + lockdep_set_class(&fs_info->buffer_tree.xa_lock, &buffer_xa_class); + INIT_LIST_HEAD(&fs_info->trans_list); INIT_LIST_HEAD(&fs_info->dead_roots); INIT_LIST_HEAD(&fs_info->delayed_iputs); @@ -2156,143 +2761,102 @@ int open_ctree(struct super_block *sb, spin_lock_init(&fs_info->fs_roots_radix_lock); spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); - spin_lock_init(&fs_info->free_chunk_lock); - spin_lock_init(&fs_info->tree_mod_seq_lock); spin_lock_init(&fs_info->super_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->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); - init_completion(&fs_info->kobj_unregister); + btrfs_lockdep_init_map(fs_info, btrfs_trans_num_writers); + btrfs_lockdep_init_map(fs_info, btrfs_trans_num_extwriters); + btrfs_lockdep_init_map(fs_info, btrfs_trans_pending_ordered); + btrfs_lockdep_init_map(fs_info, btrfs_ordered_extent); + btrfs_state_lockdep_init_map(fs_info, btrfs_trans_commit_prep, + BTRFS_LOCKDEP_TRANS_COMMIT_PREP); + btrfs_state_lockdep_init_map(fs_info, btrfs_trans_unblocked, + BTRFS_LOCKDEP_TRANS_UNBLOCKED); + btrfs_state_lockdep_init_map(fs_info, btrfs_trans_super_committed, + BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED); + btrfs_state_lockdep_init_map(fs_info, btrfs_trans_completed, + BTRFS_LOCKDEP_TRANS_COMPLETED); + INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); INIT_LIST_HEAD(&fs_info->space_info); INIT_LIST_HEAD(&fs_info->tree_mod_seq_list); - btrfs_mapping_init(&fs_info->mapping_tree); + 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 + fs_info->mapping_tree = RB_ROOT_CACHED; + rwlock_init(&fs_info->mapping_tree_lock); btrfs_init_block_rsv(&fs_info->global_block_rsv, BTRFS_BLOCK_RSV_GLOBAL); - btrfs_init_block_rsv(&fs_info->delalloc_block_rsv, - BTRFS_BLOCK_RSV_DELALLOC); btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS); btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK); + btrfs_init_block_rsv(&fs_info->treelog_rsv, BTRFS_BLOCK_RSV_TREELOG); btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY); btrfs_init_block_rsv(&fs_info->delayed_block_rsv, BTRFS_BLOCK_RSV_DELOPS); - atomic_set(&fs_info->nr_async_submits, 0); + btrfs_init_block_rsv(&fs_info->delayed_refs_rsv, + BTRFS_BLOCK_RSV_DELREFS); + atomic_set(&fs_info->async_delalloc_pages, 0); - atomic_set(&fs_info->async_submit_draining, 0); - atomic_set(&fs_info->nr_async_bios, 0); atomic_set(&fs_info->defrag_running, 0); + atomic_set(&fs_info->nr_delayed_iputs, 0); atomic64_set(&fs_info->tree_mod_seq, 0); - fs_info->sb = sb; - fs_info->max_inline = 8192 * 1024; + 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; - fs_info->free_chunk_space = 0; + atomic64_set(&fs_info->free_chunk_space, 0); fs_info->tree_mod_log = RB_ROOT; - - /* readahead state */ - INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); - spin_lock_init(&fs_info->reada_lock); + fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; + btrfs_init_ref_verify(fs_info); fs_info->thread_pool_size = min_t(unsigned long, num_online_cpus() + 2, 8); INIT_LIST_HEAD(&fs_info->ordered_roots); spin_lock_init(&fs_info->ordered_root_lock); - fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root), - GFP_NOFS); - if (!fs_info->delayed_root) { - err = -ENOMEM; - goto fail_iput; - } - btrfs_init_delayed_root(fs_info->delayed_root); - mutex_init(&fs_info->scrub_lock); - atomic_set(&fs_info->scrubs_running, 0); - atomic_set(&fs_info->scrub_pause_req, 0); - atomic_set(&fs_info->scrubs_paused, 0); - atomic_set(&fs_info->scrub_cancel_req, 0); - init_waitqueue_head(&fs_info->scrub_pause_wait); - init_rwsem(&fs_info->scrub_super_lock); - fs_info->scrub_workers_refcnt = 0; -#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY - fs_info->check_integrity_print_mask = 0; -#endif + btrfs_init_scrub(fs_info); + btrfs_init_balance(fs_info); + btrfs_init_async_reclaim_work(fs_info); + btrfs_init_extent_map_shrinker_work(fs_info); - spin_lock_init(&fs_info->balance_lock); - mutex_init(&fs_info->balance_mutex); - atomic_set(&fs_info->balance_running, 0); - atomic_set(&fs_info->balance_pause_req, 0); - atomic_set(&fs_info->balance_cancel_req, 0); - fs_info->balance_ctl = NULL; - init_waitqueue_head(&fs_info->balance_wait_q); - - sb->s_blocksize = 4096; - sb->s_blocksize_bits = blksize_bits(4096); - sb->s_bdi = &fs_info->bdi; - - fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID; - set_nlink(fs_info->btree_inode, 1); - /* - * we set the i_size on the btree inode to the max possible int. - * the real end of the address space is determined by all of - * the devices in the system - */ - fs_info->btree_inode->i_size = OFFSET_MAX; - fs_info->btree_inode->i_mapping->a_ops = &btree_aops; - fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi; - - RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node); - extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree, - fs_info->btree_inode->i_mapping); - BTRFS_I(fs_info->btree_inode)->io_tree.track_uptodate = 0; - extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree); - - BTRFS_I(fs_info->btree_inode)->io_tree.ops = &btree_extent_io_ops; - - BTRFS_I(fs_info->btree_inode)->root = tree_root; - memset(&BTRFS_I(fs_info->btree_inode)->location, 0, - sizeof(struct btrfs_key)); - set_bit(BTRFS_INODE_DUMMY, - &BTRFS_I(fs_info->btree_inode)->runtime_flags); - insert_inode_hash(fs_info->btree_inode); - - spin_lock_init(&fs_info->block_group_cache_lock); - fs_info->block_group_cache_tree = RB_ROOT; - fs_info->first_logical_byte = (u64)-1; - - extent_io_tree_init(&fs_info->freed_extents[0], - fs_info->btree_inode->i_mapping); - extent_io_tree_init(&fs_info->freed_extents[1], - fs_info->btree_inode->i_mapping); - fs_info->pinned_extents = &fs_info->freed_extents[0]; - fs_info->do_barriers = 1; + rwlock_init(&fs_info->block_group_cache_lock); + fs_info->block_group_cache_tree = RB_ROOT_CACHED; + btrfs_extent_io_tree_init(fs_info, &fs_info->excluded_extents, + IO_TREE_FS_EXCLUDED_EXTENTS); mutex_init(&fs_info->ordered_operations_mutex); mutex_init(&fs_info->tree_log_mutex); mutex_init(&fs_info->chunk_mutex); mutex_init(&fs_info->transaction_kthread_mutex); mutex_init(&fs_info->cleaner_mutex); - mutex_init(&fs_info->volume_mutex); - init_rwsem(&fs_info->extent_commit_sem); + mutex_init(&fs_info->ro_block_group_mutex); + init_rwsem(&fs_info->commit_root_sem); init_rwsem(&fs_info->cleanup_work_sem); init_rwsem(&fs_info->subvol_sem); - fs_info->dev_replace.lock_owner = 0; - atomic_set(&fs_info->dev_replace.nesting_level, 0); - mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount); - mutex_init(&fs_info->dev_replace.lock_management_lock); - mutex_init(&fs_info->dev_replace.lock); + sema_init(&fs_info->uuid_tree_rescan_sem, 1); - spin_lock_init(&fs_info->qgroup_lock); - mutex_init(&fs_info->qgroup_ioctl_lock); - fs_info->qgroup_tree = RB_ROOT; - INIT_LIST_HEAD(&fs_info->dirty_qgroups); - fs_info->qgroup_seq = 1; - fs_info->quota_enabled = 0; - fs_info->pending_quota_state = 0; - fs_info->qgroup_ulist = NULL; - mutex_init(&fs_info->qgroup_rescan_lock); + btrfs_init_dev_replace_locks(fs_info); + btrfs_init_qgroup(fs_info); + btrfs_discard_init(fs_info); btrfs_init_free_cluster(&fs_info->meta_alloc_cluster); btrfs_init_free_cluster(&fs_info->data_alloc_cluster); @@ -2301,586 +2865,766 @@ int open_ctree(struct super_block *sb, init_waitqueue_head(&fs_info->transaction_wait); init_waitqueue_head(&fs_info->transaction_blocked_wait); init_waitqueue_head(&fs_info->async_submit_wait); + init_waitqueue_head(&fs_info->delayed_iputs_wait); + + /* Usable values until the real ones are cached from the superblock */ + fs_info->nodesize = 4096; + fs_info->sectorsize = 4096; + fs_info->sectorsize_bits = ilog2(4096); + fs_info->stripesize = 4096; + + /* Default compress algorithm when user does -o compress */ + fs_info->compress_type = BTRFS_COMPRESS_ZLIB; + + fs_info->max_extent_size = BTRFS_MAX_EXTENT_SIZE; + + spin_lock_init(&fs_info->swapfile_pins_lock); + fs_info->swapfile_pins = RB_ROOT; + + fs_info->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; + /* Temporary fixed values for block size until we read the superblock. */ + sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE; + sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE); + + ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL); + if (ret) + return ret; + + ret = percpu_counter_init(&fs_info->evictable_extent_maps, 0, GFP_KERNEL); + if (ret) + return ret; + + ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); + if (ret) + return ret; + + ret = percpu_counter_init(&fs_info->stats_read_blocks, 0, GFP_KERNEL); + if (ret) + return ret; - ret = btrfs_alloc_stripe_hash_table(fs_info); + 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); + if (btrfs_test_opt(fs_info, IGNOREMETACSUMS)) + set_bit(BTRFS_FS_STATE_SKIP_META_CSUMS, &fs_info->fs_state); + + return btrfs_alloc_stripe_hash_table(fs_info); +} + +static int btrfs_uuid_rescan_kthread(void *data) +{ + struct btrfs_fs_info *fs_info = 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; +} + +static int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) +{ + u64 root_objectid = 0; + struct btrfs_root *gang[8]; + int ret = 0; + + while (1) { + unsigned int found; + + spin_lock(&fs_info->fs_roots_radix_lock); + found = radix_tree_gang_lookup(&fs_info->fs_roots_radix, + (void **)gang, root_objectid, + ARRAY_SIZE(gang)); + if (!found) { + spin_unlock(&fs_info->fs_roots_radix_lock); + break; + } + root_objectid = btrfs_root_id(gang[found - 1]) + 1; + + for (int i = 0; i < found; i++) { + /* Avoid to grab roots in dead_roots. */ + if (btrfs_root_refs(&gang[i]->root_item) == 0) { + gang[i] = NULL; + continue; + } + /* Grab all the search result for later use. */ + gang[i] = btrfs_grab_root(gang[i]); + } + spin_unlock(&fs_info->fs_roots_radix_lock); + + for (int i = 0; i < found; i++) { + if (!gang[i]) + continue; + root_objectid = btrfs_root_id(gang[i]); + /* + * Continue to release the remaining roots after the first + * error without cleanup and preserve the first error + * for the return. + */ + if (!ret) + ret = btrfs_orphan_cleanup(gang[i]); + btrfs_put_root(gang[i]); + } + if (ret) + break; + + root_objectid++; + } + return ret; +} + +/* + * Mounting logic specific to read-write file systems. Shared by open_ctree + * and btrfs_remount when remounting from read-only to read-write. + */ +int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) +{ + int ret; + const bool cache_opt = btrfs_test_opt(fs_info, SPACE_CACHE); + bool rebuild_free_space_tree = false; + + if (btrfs_test_opt(fs_info, CLEAR_CACHE) && + btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { + if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) + btrfs_warn(fs_info, + "'clear_cache' option is ignored with extent tree v2"); + else + rebuild_free_space_tree = true; + } else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) { + btrfs_warn(fs_info, "free space tree is invalid"); + rebuild_free_space_tree = true; + } + + if (rebuild_free_space_tree) { + btrfs_info(fs_info, "rebuilding free space tree"); + ret = btrfs_rebuild_free_space_tree(fs_info); + if (ret) { + btrfs_warn(fs_info, + "failed to rebuild free space tree: %d", ret); + goto out; + } + } + + if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !btrfs_test_opt(fs_info, FREE_SPACE_TREE)) { + btrfs_info(fs_info, "disabling free space tree"); + ret = btrfs_delete_free_space_tree(fs_info); + if (ret) { + btrfs_warn(fs_info, + "failed to disable free space tree: %d", ret); + goto out; + } + } + + /* + * btrfs_find_orphan_roots() is responsible for finding all the dead + * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load + * them into the fs_info->fs_roots_radix tree. This must be done before + * calling btrfs_orphan_cleanup() on the tree root. If we don't do it + * first, then btrfs_orphan_cleanup() will delete a dead root's orphan + * item before the root's tree is deleted - this means that if we unmount + * or crash before the deletion completes, on the next mount we will not + * delete what remains of the tree because the orphan item does not + * exists anymore, which is what tells us we have a pending deletion. + */ + ret = btrfs_find_orphan_roots(fs_info); + if (ret) + goto out; + + ret = btrfs_cleanup_fs_roots(fs_info); + if (ret) + goto out; + + down_read(&fs_info->cleanup_work_sem); + if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) || + (ret = btrfs_orphan_cleanup(fs_info->tree_root))) { + up_read(&fs_info->cleanup_work_sem); + goto out; + } + up_read(&fs_info->cleanup_work_sem); + + mutex_lock(&fs_info->cleaner_mutex); + ret = btrfs_recover_relocation(fs_info); + mutex_unlock(&fs_info->cleaner_mutex); + if (ret < 0) { + btrfs_warn(fs_info, "failed to recover relocation: %d", ret); + goto out; + } + + if (btrfs_test_opt(fs_info, FREE_SPACE_TREE) && + !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { + btrfs_info(fs_info, "creating free space tree"); + ret = btrfs_create_free_space_tree(fs_info); + if (ret) { + btrfs_warn(fs_info, + "failed to create free space tree: %d", ret); + goto out; + } + } + + if (cache_opt != btrfs_free_space_cache_v1_active(fs_info)) { + ret = btrfs_set_free_space_cache_v1_active(fs_info, cache_opt); + if (ret) + goto out; + } + + ret = btrfs_resume_balance_async(fs_info); + if (ret) + goto out; + + ret = btrfs_resume_dev_replace_async(fs_info); if (ret) { - err = ret; - goto fail_alloc; + btrfs_warn(fs_info, "failed to resume dev_replace"); + goto out; } - __setup_root(4096, 4096, 4096, 4096, tree_root, - fs_info, BTRFS_ROOT_TREE_OBJECTID); + btrfs_qgroup_rescan_resume(fs_info); - invalidate_bdev(fs_devices->latest_bdev); + if (!fs_info->uuid_root) { + btrfs_info(fs_info, "creating UUID tree"); + ret = btrfs_create_uuid_tree(fs_info); + if (ret) { + btrfs_warn(fs_info, + "failed to create the UUID tree %d", ret); + goto out; + } + } + +out: + return ret; +} + +/* + * Do various sanity and dependency checks of different features. + * + * @is_rw_mount: If the mount is read-write. + * + * This is the place for less strict checks (like for subpage or artificial + * feature dependencies). + * + * For strict checks or possible corruption detection, see + * btrfs_validate_super(). + * + * This should be called after btrfs_parse_options(), as some mount options + * (space cache related) can modify on-disk format like free space tree and + * screw up certain feature dependencies. + */ +int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) +{ + struct btrfs_super_block *disk_super = fs_info->super_copy; + u64 incompat = btrfs_super_incompat_flags(disk_super); + const u64 compat_ro = btrfs_super_compat_ro_flags(disk_super); + const u64 compat_ro_unsupp = (compat_ro & ~BTRFS_FEATURE_COMPAT_RO_SUPP); + + if (incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP) { + btrfs_err(fs_info, + "cannot mount because of unknown incompat features (0x%llx)", + incompat); + return -EINVAL; + } + + /* Runtime limitation for mixed block groups. */ + if ((incompat & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) && + (fs_info->sectorsize != fs_info->nodesize)) { + btrfs_err(fs_info, +"unequal nodesize/sectorsize (%u != %u) are not allowed for mixed block groups", + fs_info->nodesize, fs_info->sectorsize); + return -EINVAL; + } + + /* Mixed backref is an always-enabled feature. */ + incompat |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; + + /* Set compression related flags just in case. */ + if (fs_info->compress_type == BTRFS_COMPRESS_LZO) + incompat |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; + else if (fs_info->compress_type == BTRFS_COMPRESS_ZSTD) + incompat |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD; /* - * Read super block and check the signature bytes only + * An ancient flag, which should really be marked deprecated. + * Such runtime limitation doesn't really need a incompat flag. */ - bh = btrfs_read_dev_super(fs_devices->latest_bdev); - if (!bh) { - err = -EINVAL; - goto fail_alloc; + if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) + incompat |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA; + + if (compat_ro_unsupp && is_rw_mount) { + btrfs_err(fs_info, + "cannot mount read-write because of unknown compat_ro features (0x%llx)", + compat_ro); + return -EINVAL; } /* - * We want to check superblock checksum, the type is stored inside. - * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k). + * 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 (btrfs_check_super_csum(bh->b_data)) { - printk(KERN_ERR "btrfs: superblock checksum mismatch\n"); - err = -EINVAL; - goto fail_alloc; + 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; } /* - * super_copy is zeroed at allocation time and we never touch the - * following bytes up to INFO_SIZE, the checksum is calculated from - * the whole block of INFO_SIZE + * Artificial limitations for block group tree, to force + * block-group-tree to rely on no-holes and free-space-tree. */ - memcpy(fs_info->super_copy, bh->b_data, sizeof(*fs_info->super_copy)); - memcpy(fs_info->super_for_commit, fs_info->super_copy, - sizeof(*fs_info->super_for_commit)); - brelse(bh); + 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; + } - memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE); + /* + * Subpage/bs > ps runtime limitation on v1 cache. + * + * V1 space cache still has some hard coded PAGE_SIZE usage, while + * we're already defaulting to v2 cache, no need to bother v1 as it's + * going to be deprecated anyway. + */ + if (fs_info->sectorsize != PAGE_SIZE && btrfs_test_opt(fs_info, SPACE_CACHE)) { + btrfs_warn(fs_info, + "v1 space cache is not supported for page size %lu with sectorsize %u", + PAGE_SIZE, fs_info->sectorsize); + return -EINVAL; + } - ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY); - if (ret) { - printk(KERN_ERR "btrfs: superblock contains fatal errors\n"); - err = -EINVAL; - goto fail_alloc; + /* This can be called by remount, we need to protect the super block. */ + spin_lock(&fs_info->super_lock); + btrfs_set_super_incompat_flags(disk_super, incompat); + spin_unlock(&fs_info->super_lock); + + return 0; +} + +int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices) +{ + u32 sectorsize; + u32 nodesize; + u32 stripesize; + u64 generation; + 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 level; + + ret = init_mount_fs_info(fs_info, sb); + if (ret) + goto fail; + + /* These need to be init'ed before we start creating inodes and such. */ + tree_root = btrfs_alloc_root(fs_info, BTRFS_ROOT_TREE_OBJECTID, + GFP_KERNEL); + fs_info->tree_root = tree_root; + chunk_root = btrfs_alloc_root(fs_info, BTRFS_CHUNK_TREE_OBJECTID, + GFP_KERNEL); + fs_info->chunk_root = chunk_root; + if (!tree_root || !chunk_root) { + ret = -ENOMEM; + goto fail; } - disk_super = fs_info->super_copy; - if (!btrfs_super_root(disk_super)) - goto fail_alloc; + ret = btrfs_init_btree_inode(sb); + if (ret) + goto fail; - /* check FS state, whether FS is broken. */ - if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR) - set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state); + invalidate_bdev(fs_devices->latest_dev->bdev); /* - * run through our array of backup supers and setup - * our ring pointer to the oldest one + * Read super block and check the signature bytes only */ - generation = btrfs_super_generation(disk_super); - find_oldest_super_backup(fs_info, generation); + disk_super = btrfs_read_disk_super(fs_devices->latest_dev->bdev, 0, false); + if (IS_ERR(disk_super)) { + ret = PTR_ERR(disk_super); + goto fail_alloc; + } + btrfs_info(fs_info, "first mount of filesystem %pU", disk_super->fsid); /* - * In the long term, we'll store the compression type in the super - * block, and it'll be used for per file compression control. + * Verify the type first, if that or the checksum value are + * corrupted, we'll find out */ - fs_info->compress_type = BTRFS_COMPRESS_ZLIB; + csum_type = btrfs_super_csum_type(disk_super); + if (!btrfs_supported_super_csum(csum_type)) { + btrfs_err(fs_info, "unsupported checksum algorithm: %u", + csum_type); + ret = -EINVAL; + btrfs_release_disk_super(disk_super); + goto fail_alloc; + } - ret = btrfs_parse_options(tree_root, options); + 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; } - features = btrfs_super_incompat_flags(disk_super) & - ~BTRFS_FEATURE_INCOMPAT_SUPP; - if (features) { - printk(KERN_ERR "BTRFS: couldn't mount because of " - "unsupported optional features (%Lx).\n", - (unsigned long long)features); - err = -EINVAL; + /* + * We want to check superblock checksum, the type is stored inside. + * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k). + */ + if (btrfs_check_super_csum(fs_info, disk_super)) { + btrfs_err(fs_info, "superblock checksum mismatch"); + ret = -EINVAL; + btrfs_release_disk_super(disk_super); goto fail_alloc; } - if (btrfs_super_leafsize(disk_super) != - btrfs_super_nodesize(disk_super)) { - printk(KERN_ERR "BTRFS: couldn't mount because metadata " - "blocksizes don't match. node %d leaf %d\n", - btrfs_super_nodesize(disk_super), - btrfs_super_leafsize(disk_super)); - err = -EINVAL; + /* + * super_copy is zeroed at allocation time and we never touch the + * following bytes up to INFO_SIZE, the checksum is calculated from + * the whole block of INFO_SIZE + */ + memcpy(fs_info->super_copy, disk_super, sizeof(*fs_info->super_copy)); + btrfs_release_disk_super(disk_super); + + disk_super = fs_info->super_copy; + + memcpy(fs_info->super_for_commit, fs_info->super_copy, + sizeof(*fs_info->super_for_commit)); + + ret = btrfs_validate_mount_super(fs_info); + if (ret) { + btrfs_err(fs_info, "superblock contains fatal errors"); + ret = -EINVAL; goto fail_alloc; } - if (btrfs_super_leafsize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) { - printk(KERN_ERR "BTRFS: couldn't mount because metadata " - "blocksize (%d) was too large\n", - btrfs_super_leafsize(disk_super)); - err = -EINVAL; + + if (!btrfs_super_root(disk_super)) { + btrfs_err(fs_info, "invalid superblock tree root bytenr"); + ret = -EINVAL; goto fail_alloc; } - features = btrfs_super_incompat_flags(disk_super); - features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; - if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_LZO) - features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; - - if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) - printk(KERN_ERR "btrfs: has skinny extents\n"); - - /* - * flag our filesystem as having big metadata blocks if - * they are bigger than the page size - */ - if (btrfs_super_leafsize(disk_super) > PAGE_CACHE_SIZE) { - if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA)) - printk(KERN_INFO "btrfs flagging fs with big metadata feature\n"); - features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA; - } + /* check FS state, whether FS is broken. */ + if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR) + WRITE_ONCE(fs_info->fs_error, -EUCLEAN); + /* Set up fs_info before parsing mount options */ nodesize = btrfs_super_nodesize(disk_super); - leafsize = btrfs_super_leafsize(disk_super); sectorsize = btrfs_super_sectorsize(disk_super); - stripesize = btrfs_super_stripesize(disk_super); - fs_info->dirty_metadata_batch = leafsize * (1 + ilog2(nr_cpu_ids)); + stripesize = sectorsize; + fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids)); fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids)); + fs_info->nodesize = nodesize; + fs_info->nodesize_bits = ilog2(nodesize); + fs_info->sectorsize = sectorsize; + fs_info->sectorsize_bits = ilog2(sectorsize); + fs_info->block_min_order = ilog2(round_up(sectorsize, PAGE_SIZE) >> PAGE_SHIFT); + fs_info->block_max_order = ilog2((BITS_PER_LONG << fs_info->sectorsize_bits) >> PAGE_SHIFT); + fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size; + fs_info->stripesize = stripesize; + fs_info->fs_devices->fs_info = fs_info; + + if (fs_info->sectorsize > PAGE_SIZE) + btrfs_warn(fs_info, + "support for block size %u with page size %lu is experimental, some features may be missing", + fs_info->sectorsize, PAGE_SIZE); /* - * mixed block groups end up with duplicate but slightly offset - * extent buffers for the same range. It leads to corruptions + * Handle the space caching options appropriately now that we have the + * super block loaded and validated. */ - if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) && - (sectorsize != leafsize)) { - printk(KERN_WARNING "btrfs: unequal leaf/node/sector sizes " - "are not allowed for mixed block groups on %s\n", - sb->s_id); + btrfs_set_free_space_cache_settings(fs_info); + + if (!btrfs_check_options(fs_info, &fs_info->mount_opt, sb->s_flags)) { + ret = -EINVAL; goto fail_alloc; } + ret = btrfs_check_features(fs_info, !sb_rdonly(sb)); + if (ret < 0) + goto fail_alloc; + /* - * Needn't use the lock because there is no other task which will - * update the flag. + * At this point our mount options are validated, if we set ->max_inline + * to something non-standard make sure we truncate it to sectorsize. */ - btrfs_set_super_incompat_flags(disk_super, features); + fs_info->max_inline = min_t(u64, fs_info->max_inline, fs_info->sectorsize); - features = btrfs_super_compat_ro_flags(disk_super) & - ~BTRFS_FEATURE_COMPAT_RO_SUPP; - if (!(sb->s_flags & MS_RDONLY) && features) { - printk(KERN_ERR "BTRFS: couldn't mount RDWR because of " - "unsupported option features (%Lx).\n", - (unsigned long long)features); - err = -EINVAL; - goto fail_alloc; - } - - btrfs_init_workers(&fs_info->generic_worker, - "genwork", 1, NULL); - - btrfs_init_workers(&fs_info->workers, "worker", - fs_info->thread_pool_size, - &fs_info->generic_worker); - - btrfs_init_workers(&fs_info->delalloc_workers, "delalloc", - fs_info->thread_pool_size, - &fs_info->generic_worker); - - btrfs_init_workers(&fs_info->flush_workers, "flush_delalloc", - fs_info->thread_pool_size, - &fs_info->generic_worker); - - btrfs_init_workers(&fs_info->submit_workers, "submit", - min_t(u64, fs_devices->num_devices, - fs_info->thread_pool_size), - &fs_info->generic_worker); - - btrfs_init_workers(&fs_info->caching_workers, "cache", - 2, &fs_info->generic_worker); - - /* a higher idle thresh on the submit workers makes it much more - * likely that bios will be send down in a sane order to the - * devices - */ - fs_info->submit_workers.idle_thresh = 64; - - fs_info->workers.idle_thresh = 16; - fs_info->workers.ordered = 1; - - fs_info->delalloc_workers.idle_thresh = 2; - fs_info->delalloc_workers.ordered = 1; - - btrfs_init_workers(&fs_info->fixup_workers, "fixup", 1, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->endio_workers, "endio", - fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->endio_meta_workers, "endio-meta", - fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->endio_meta_write_workers, - "endio-meta-write", fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->endio_raid56_workers, - "endio-raid56", fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->rmw_workers, - "rmw", fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->endio_write_workers, "endio-write", - fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->endio_freespace_worker, "freespace-write", - 1, &fs_info->generic_worker); - btrfs_init_workers(&fs_info->delayed_workers, "delayed-meta", - fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->readahead_workers, "readahead", - fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->qgroup_rescan_workers, "qgroup-rescan", 1, - &fs_info->generic_worker); - - /* - * endios are largely parallel and should have a very - * low idle thresh - */ - fs_info->endio_workers.idle_thresh = 4; - fs_info->endio_meta_workers.idle_thresh = 4; - fs_info->endio_raid56_workers.idle_thresh = 4; - fs_info->rmw_workers.idle_thresh = 2; - - fs_info->endio_write_workers.idle_thresh = 2; - fs_info->endio_meta_write_workers.idle_thresh = 2; - fs_info->readahead_workers.idle_thresh = 2; - - /* - * btrfs_start_workers can really only fail because of ENOMEM so just - * return -ENOMEM if any of these fail. - */ - ret = btrfs_start_workers(&fs_info->workers); - ret |= btrfs_start_workers(&fs_info->generic_worker); - ret |= btrfs_start_workers(&fs_info->submit_workers); - ret |= btrfs_start_workers(&fs_info->delalloc_workers); - ret |= btrfs_start_workers(&fs_info->fixup_workers); - ret |= btrfs_start_workers(&fs_info->endio_workers); - ret |= btrfs_start_workers(&fs_info->endio_meta_workers); - ret |= btrfs_start_workers(&fs_info->rmw_workers); - ret |= btrfs_start_workers(&fs_info->endio_raid56_workers); - ret |= btrfs_start_workers(&fs_info->endio_meta_write_workers); - ret |= btrfs_start_workers(&fs_info->endio_write_workers); - ret |= btrfs_start_workers(&fs_info->endio_freespace_worker); - ret |= btrfs_start_workers(&fs_info->delayed_workers); - ret |= btrfs_start_workers(&fs_info->caching_workers); - ret |= btrfs_start_workers(&fs_info->readahead_workers); - ret |= btrfs_start_workers(&fs_info->flush_workers); - ret |= btrfs_start_workers(&fs_info->qgroup_rescan_workers); - if (ret) { - err = -ENOMEM; + ret = btrfs_alloc_compress_wsm(fs_info); + if (ret) + goto fail_sb_buffer; + ret = btrfs_init_workqueues(fs_info); + if (ret) goto fail_sb_buffer; - } - - fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super); - fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages, - 4 * 1024 * 1024 / PAGE_CACHE_SIZE); - tree_root->nodesize = nodesize; - tree_root->leafsize = leafsize; - tree_root->sectorsize = sectorsize; - tree_root->stripesize = stripesize; + sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super); + sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE); + /* Update the values for the current filesystem. */ sb->s_blocksize = sectorsize; sb->s_blocksize_bits = blksize_bits(sectorsize); - - if (disk_super->magic != cpu_to_le64(BTRFS_MAGIC)) { - printk(KERN_INFO "btrfs: valid FS not found on %s\n", sb->s_id); - goto fail_sb_buffer; - } - - if (sectorsize != PAGE_SIZE) { - printk(KERN_WARNING "btrfs: Incompatible sector size(%lu) " - "found on %s\n", (unsigned long)sectorsize, sb->s_id); - goto fail_sb_buffer; - } + memcpy(&sb->s_uuid, fs_info->fs_devices->fsid, BTRFS_FSID_SIZE); mutex_lock(&fs_info->chunk_mutex); - ret = btrfs_read_sys_array(tree_root); + ret = btrfs_read_sys_array(fs_info); mutex_unlock(&fs_info->chunk_mutex); if (ret) { - printk(KERN_WARNING "btrfs: failed to read the system " - "array on %s\n", sb->s_id); + btrfs_err(fs_info, "failed to read the system array: %d", ret); goto fail_sb_buffer; } - blocksize = btrfs_level_size(tree_root, - btrfs_super_chunk_root_level(disk_super)); generation = btrfs_super_chunk_root_generation(disk_super); - - __setup_root(nodesize, leafsize, sectorsize, stripesize, - chunk_root, fs_info, BTRFS_CHUNK_TREE_OBJECTID); - - chunk_root->node = read_tree_block(chunk_root, - btrfs_super_chunk_root(disk_super), - blocksize, generation); - if (!chunk_root->node || - !test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) { - printk(KERN_WARNING "btrfs: failed to read chunk root on %s\n", - sb->s_id); + level = btrfs_super_chunk_root_level(disk_super); + ret = load_super_root(chunk_root, btrfs_super_chunk_root(disk_super), + generation, level); + if (ret) { + btrfs_err(fs_info, "failed to read chunk root"); goto fail_tree_roots; } - 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, - (unsigned long)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(chunk_root); + ret = btrfs_read_chunk_tree(fs_info); if (ret) { - printk(KERN_WARNING "btrfs: failed to read chunk tree on %s\n", - sb->s_id); + btrfs_err(fs_info, "failed to read chunk tree: %d", ret); goto fail_tree_roots; } /* - * keep the device that is marked to be the target device for the - * dev_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_close_extra_devices(fs_info, fs_devices, 0); - - if (!fs_devices->latest_bdev) { - printk(KERN_CRIT "btrfs: failed to read devices on %s\n", - sb->s_id); + btrfs_free_extra_devids(fs_devices); + if (unlikely(!fs_devices->latest_dev->bdev)) { + btrfs_err(fs_info, "failed to read devices"); + ret = -EIO; goto fail_tree_roots; } -retry_root_backup: - blocksize = btrfs_level_size(tree_root, - btrfs_super_root_level(disk_super)); - generation = btrfs_super_generation(disk_super); - - tree_root->node = read_tree_block(tree_root, - btrfs_super_root(disk_super), - blocksize, generation); - if (!tree_root->node || - !test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) { - printk(KERN_WARNING "btrfs: failed to read tree root on %s\n", - sb->s_id); + ret = init_tree_roots(fs_info); + if (ret) + goto fail_tree_roots; - goto recovery_tree_root; + /* + * 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; } - btrfs_set_root_node(&tree_root->root_item, tree_root->node); - tree_root->commit_root = btrfs_root_node(tree_root); - - location.objectid = BTRFS_EXTENT_TREE_OBJECTID; - location.type = BTRFS_ROOT_ITEM_KEY; - location.offset = 0; - - extent_root = btrfs_read_tree_root(tree_root, &location); - if (IS_ERR(extent_root)) { - ret = PTR_ERR(extent_root); - goto recovery_tree_root; - } - extent_root->track_dirty = 1; - fs_info->extent_root = extent_root; + /* + * 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); - location.objectid = BTRFS_DEV_TREE_OBJECTID; - dev_root = btrfs_read_tree_root(tree_root, &location); - if (IS_ERR(dev_root)) { - ret = PTR_ERR(dev_root); - goto recovery_tree_root; + ret = btrfs_verify_dev_extents(fs_info); + if (ret) { + btrfs_err(fs_info, + "failed to verify dev extents against chunks: %d", + ret); + goto fail_block_groups; } - dev_root->track_dirty = 1; - fs_info->dev_root = dev_root; - btrfs_init_devices_late(fs_info); - - location.objectid = BTRFS_CSUM_TREE_OBJECTID; - csum_root = btrfs_read_tree_root(tree_root, &location); - if (IS_ERR(csum_root)) { - ret = PTR_ERR(csum_root); - goto recovery_tree_root; + ret = btrfs_recover_balance(fs_info); + if (ret) { + btrfs_err(fs_info, "failed to recover balance: %d", ret); + goto fail_block_groups; } - csum_root->track_dirty = 1; - fs_info->csum_root = csum_root; - location.objectid = BTRFS_QUOTA_TREE_OBJECTID; - quota_root = btrfs_read_tree_root(tree_root, &location); - if (!IS_ERR(quota_root)) { - quota_root->track_dirty = 1; - fs_info->quota_enabled = 1; - fs_info->pending_quota_state = 1; - fs_info->quota_root = quota_root; + ret = btrfs_init_dev_stats(fs_info); + if (ret) { + btrfs_err(fs_info, "failed to init dev_stats: %d", ret); + goto fail_block_groups; } - fs_info->generation = generation; - fs_info->last_trans_committed = generation; - - ret = btrfs_recover_balance(fs_info); + ret = btrfs_init_dev_replace(fs_info); if (ret) { - printk(KERN_WARNING "btrfs: failed to recover balance\n"); + btrfs_err(fs_info, "failed to init dev_replace: %d", ret); goto fail_block_groups; } - ret = btrfs_init_dev_stats(fs_info); + ret = btrfs_check_zoned_mode(fs_info); if (ret) { - printk(KERN_ERR "btrfs: failed to init dev_stats: %d\n", - ret); + btrfs_err(fs_info, "failed to initialize zoned mode: %d", + ret); goto fail_block_groups; } - ret = btrfs_init_dev_replace(fs_info); + ret = btrfs_sysfs_add_fsid(fs_devices); if (ret) { - pr_err("btrfs: failed to init dev_replace: %d\n", ret); + btrfs_err(fs_info, "failed to init sysfs fsid interface: %d", + ret); goto fail_block_groups; } - btrfs_close_extra_devices(fs_info, fs_devices, 1); + ret = btrfs_sysfs_add_mounted(fs_info); + if (ret) { + btrfs_err(fs_info, "failed to init sysfs interface: %d", ret); + goto fail_fsdev_sysfs; + } ret = btrfs_init_space_info(fs_info); if (ret) { - printk(KERN_ERR "Failed to initial space info: %d\n", ret); - goto fail_block_groups; + btrfs_err(fs_info, "failed to initialize space info: %d", ret); + goto fail_sysfs; } - ret = btrfs_read_block_groups(extent_root); + ret = btrfs_read_block_groups(fs_info); if (ret) { - printk(KERN_ERR "Failed to read block groups: %d\n", ret); - goto fail_block_groups; + btrfs_err(fs_info, "failed to read block groups: %d", ret); + goto fail_sysfs; } - fs_info->num_tolerated_disk_barrier_failures = - btrfs_calc_num_tolerated_disk_barrier_failures(fs_info); - if (fs_info->fs_devices->missing_devices > - fs_info->num_tolerated_disk_barrier_failures && - !(sb->s_flags & MS_RDONLY)) { - printk(KERN_WARNING - "Btrfs: too many missing devices, writeable mount is not allowed\n"); - goto fail_block_groups; + + btrfs_zoned_reserve_data_reloc_bg(fs_info); + btrfs_free_zone_cache(fs_info); + + btrfs_check_active_zone_reservation(fs_info); + + if (!sb_rdonly(sb) && fs_info->fs_devices->missing_devices && + !btrfs_check_rw_degradable(fs_info, NULL)) { + btrfs_warn(fs_info, + "writable mount is not allowed due to too many missing devices"); + ret = -EINVAL; + goto fail_sysfs; } - fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root, + fs_info->cleaner_kthread = kthread_run(cleaner_kthread, fs_info, "btrfs-cleaner"); - if (IS_ERR(fs_info->cleaner_kthread)) - goto fail_block_groups; + if (IS_ERR(fs_info->cleaner_kthread)) { + ret = PTR_ERR(fs_info->cleaner_kthread); + goto fail_sysfs; + } fs_info->transaction_kthread = kthread_run(transaction_kthread, tree_root, "btrfs-transaction"); - if (IS_ERR(fs_info->transaction_kthread)) + if (IS_ERR(fs_info->transaction_kthread)) { + ret = PTR_ERR(fs_info->transaction_kthread); goto fail_cleaner; - - if (!btrfs_test_opt(tree_root, SSD) && - !btrfs_test_opt(tree_root, NOSSD) && - !fs_info->fs_devices->rotating) { - printk(KERN_INFO "Btrfs detected SSD devices, enabling SSD " - "mode\n"); - btrfs_set_opt(fs_info->mount_opt, SSD); - } - -#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY - if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) { - ret = btrfsic_mount(tree_root, fs_devices, - btrfs_test_opt(tree_root, - CHECK_INTEGRITY_INCLUDING_EXTENT_DATA) ? - 1 : 0, - fs_info->check_integrity_print_mask); - if (ret) - printk(KERN_WARNING "btrfs: failed to initialize" - " integrity check module %s\n", sb->s_id); } -#endif + ret = btrfs_read_qgroup_config(fs_info); if (ret) goto fail_trans_kthread; - /* do not make disk changes in broken FS */ - if (btrfs_super_log_root(disk_super) != 0) { - u64 bytenr = btrfs_super_log_root(disk_super); - - if (fs_devices->rw_devices == 0) { - printk(KERN_WARNING "Btrfs log replay required " - "on RO media\n"); - err = -EIO; - goto fail_qgroup; - } - blocksize = - btrfs_level_size(tree_root, - btrfs_super_log_root_level(disk_super)); - - log_tree_root = btrfs_alloc_root(fs_info); - if (!log_tree_root) { - err = -ENOMEM; - goto fail_qgroup; - } - - __setup_root(nodesize, leafsize, sectorsize, stripesize, - log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID); - - log_tree_root->node = read_tree_block(tree_root, bytenr, - blocksize, - generation + 1); - if (!log_tree_root->node || - !extent_buffer_uptodate(log_tree_root->node)) { - printk(KERN_ERR "btrfs: failed to read log tree\n"); - free_extent_buffer(log_tree_root->node); - kfree(log_tree_root); - goto fail_trans_kthread; - } - /* returns with log_tree_root freed on success */ - ret = btrfs_recover_log_trees(log_tree_root); - if (ret) { - btrfs_error(tree_root->fs_info, ret, - "Failed to recover log tree"); - free_extent_buffer(log_tree_root->node); - kfree(log_tree_root); - goto fail_trans_kthread; - } - - if (sb->s_flags & MS_RDONLY) { - ret = btrfs_commit_super(tree_root); - if (ret) - goto fail_trans_kthread; - } - } - - ret = btrfs_find_orphan_roots(tree_root); - if (ret) - goto fail_trans_kthread; + if (btrfs_build_ref_tree(fs_info)) + btrfs_err(fs_info, "couldn't build ref tree"); - if (!(sb->s_flags & MS_RDONLY)) { - ret = btrfs_cleanup_fs_roots(fs_info); + /* do not make disk changes in broken FS or nologreplay is given */ + if (btrfs_super_log_root(disk_super) != 0 && + !btrfs_test_opt(fs_info, NOLOGREPLAY)) { + btrfs_info(fs_info, "start tree-log replay"); + ret = btrfs_replay_log(fs_info, fs_devices); if (ret) - goto fail_trans_kthread; - - ret = btrfs_recover_relocation(tree_root); - if (ret < 0) { - printk(KERN_WARNING - "btrfs: failed to recover relocation\n"); - 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); + ret = PTR_ERR(fs_info->fs_root); + btrfs_warn(fs_info, "failed to read fs tree: %d", ret); + fs_info->fs_root = NULL; goto fail_qgroup; } - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return 0; - 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(tree_root); - 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) { - printk(KERN_WARNING "btrfs: failed to resume balance\n"); - close_ctree(tree_root); + close_ctree(fs_info); return ret; } + btrfs_discard_resume(fs_info); - ret = btrfs_resume_dev_replace_async(fs_info); - if (ret) { - pr_warn("btrfs: failed to resume dev_replace\n"); - close_ctree(tree_root); - return ret; + if (fs_info->uuid_root && + (btrfs_test_opt(fs_info, RESCAN_UUID_TREE) || + fs_info->generation != btrfs_super_uuid_tree_generation(disk_super))) { + btrfs_info(fs_info, "checking UUID tree"); + ret = btrfs_check_uuid_tree(fs_info); + if (ret) { + btrfs_warn(fs_info, + "failed to check the UUID tree: %d", ret); + close_ctree(fs_info); + return ret; + } } - btrfs_qgroup_rescan_resume(fs_info); + set_bit(BTRFS_FS_OPEN, &fs_info->flags); + + /* Kick the cleaner thread so it'll start deleting snapshots. */ + if (test_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags)) + wake_up_process(fs_info->cleaner_kthread); return 0; @@ -2888,8 +3632,8 @@ fail_qgroup: btrfs_free_qgroup_config(fs_info); fail_trans_kthread: kthread_stop(fs_info->transaction_kthread); - btrfs_cleanup_transaction(fs_info->tree_root); - del_fs_roots(fs_info); + btrfs_cleanup_transaction(fs_info); + btrfs_free_fs_roots(fs_info); fail_cleaner: kthread_stop(fs_info->cleaner_kthread); @@ -2899,203 +3643,212 @@ fail_cleaner: */ filemap_write_and_wait(fs_info->btree_inode->i_mapping); +fail_sysfs: + btrfs_sysfs_remove_mounted(fs_info); + +fail_fsdev_sysfs: + btrfs_sysfs_remove_fsid(fs_info->fs_devices); + fail_block_groups: btrfs_put_block_group_cache(fs_info); - btrfs_free_block_groups(fs_info); fail_tree_roots: - free_root_pointers(fs_info, 1); + 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_alloc: -fail_iput: - btrfs_mapping_tree_free(&fs_info->mapping_tree); + btrfs_mapping_tree_free(fs_info); iput(fs_info->btree_inode); -fail_delalloc_bytes: - percpu_counter_destroy(&fs_info->delalloc_bytes); -fail_dirty_metadata_bytes: - percpu_counter_destroy(&fs_info->dirty_metadata_bytes); -fail_bdi: - bdi_destroy(&fs_info->bdi); -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; - -recovery_tree_root: - if (!btrfs_test_opt(tree_root, RECOVERY)) - goto fail_tree_roots; - - free_root_pointers(fs_info, 0); - - /* don't use the log in recovery mode, it won't be valid */ - btrfs_set_super_log_root(disk_super, 0); - - /* we can't trust the free space cache either */ - btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE); - - ret = next_root_backup(fs_info, fs_info->super_copy, - &num_backups_tried, &backup_index); - if (ret == -1) - goto fail_block_groups; - goto retry_root_backup; + ASSERT(ret < 0); + return ret; } +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; - - printk_ratelimited_in_rcu(KERN_WARNING "lost page write due to " - "I/O error on %s\n", - rcu_str_deref(device->name)); - /* note, we dont' 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 folio_iter fi; + + bio_for_each_folio_all(fi, bio) { + if (bio->bi_status) { + btrfs_warn_rl(device->fs_info, + "lost super block write due to IO error on %s (%d)", + btrfs_dev_name(device), + blk_status_to_errno(bio->bi_status)); + btrfs_dev_stat_inc_and_print(device, + BTRFS_DEV_STAT_WRITE_ERRS); + /* Ensure failure if the primary sb fails. */ + if (bio->bi_opf & REQ_FUA) + atomic_add(BTRFS_SUPER_PRIMARY_WRITE_ERROR, + &device->sb_write_errors); + else + atomic_inc(&device->sb_write_errors); + } + folio_unlock(fi.folio); + folio_put(fi.folio); } - unlock_buffer(bh); - put_bh(bh); + + bio_put(bio); } -struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) +/* + * Write superblock @sb to the @device. Do not wait for completion, all the + * folios we use for writing are locked. + * + * Write @max_mirrors copies of the superblock, where 0 means default that fit + * the expected device size at commit time. Note that max_mirrors must be + * same for write and wait phases. + * + * Return number of errors when folio is not found or submission fails. + */ +static int write_dev_supers(struct btrfs_device *device, + struct btrfs_super_block *sb, int max_mirrors) { - struct buffer_head *bh; - struct buffer_head *latest = NULL; - struct btrfs_super_block *super; + struct btrfs_fs_info *fs_info = device->fs_info; + struct address_space *mapping = device->bdev->bd_mapping; + SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); int i; - u64 transid = 0; - u64 bytenr; + int ret; + u64 bytenr, bytenr_orig; - /* we would like to check all the supers, but that would make - * a btrfs mount succeed after a mkfs from a different FS. - * So, we need to add a special mount option to scan for - * later supers, using BTRFS_SUPER_MIRROR_MAX instead - */ - for (i = 0; i < 1; i++) { - bytenr = btrfs_sb_offset(i); - if (bytenr + 4096 >= i_size_read(bdev->bd_inode)) - break; - bh = __bread(bdev, bytenr / 4096, 4096); - if (!bh) - continue; + atomic_set(&device->sb_write_errors, 0); + + if (max_mirrors == 0) + max_mirrors = BTRFS_SUPER_MIRROR_MAX; - super = (struct btrfs_super_block *)bh->b_data; - if (btrfs_super_bytenr(super) != bytenr || - super->magic != cpu_to_le64(BTRFS_MAGIC)) { - brelse(bh); + shash->tfm = fs_info->csum_shash; + + for (i = 0; i < max_mirrors; i++) { + struct folio *folio; + struct bio *bio; + struct btrfs_super_block *disk_super; + size_t offset; + + bytenr_orig = btrfs_sb_offset(i); + ret = btrfs_sb_log_location(device, i, WRITE, &bytenr); + if (ret == -ENOENT) { + continue; + } else if (ret < 0) { + btrfs_err(device->fs_info, + "couldn't get super block location for mirror %d error %d", + i, ret); + atomic_inc(&device->sb_write_errors); continue; } + if (bytenr + BTRFS_SUPER_INFO_SIZE >= + device->commit_total_bytes) + break; - if (!latest || btrfs_super_generation(super) > transid) { - brelse(latest); - latest = bh; - transid = btrfs_super_generation(super); - } else { - brelse(bh); + btrfs_set_super_bytenr(sb, bytenr_orig); + + crypto_shash_digest(shash, (const char *)sb + BTRFS_CSUM_SIZE, + BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, + sb->csum); + + folio = __filemap_get_folio(mapping, bytenr >> PAGE_SHIFT, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + GFP_NOFS); + if (IS_ERR(folio)) { + btrfs_err(device->fs_info, + "couldn't get super block page for bytenr %llu error %ld", + bytenr, PTR_ERR(folio)); + atomic_inc(&device->sb_write_errors); + continue; } + + offset = offset_in_folio(folio, bytenr); + disk_super = folio_address(folio) + offset; + memcpy(disk_super, sb, BTRFS_SUPER_INFO_SIZE); + + /* + * Directly use bios here instead of relying on the page cache + * to do I/O, so we don't lose the ability to do integrity + * checking. + */ + bio = bio_alloc(device->bdev, 1, + REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, + GFP_NOFS); + bio->bi_iter.bi_sector = bytenr >> SECTOR_SHIFT; + bio->bi_private = device; + bio->bi_end_io = btrfs_end_super_write; + bio_add_folio_nofail(bio, folio, BTRFS_SUPER_INFO_SIZE, offset); + + /* + * We FUA only the first super block. The others we allow to + * go down lazy and there's a short window where the on-disk + * copies might still contain the older version. + */ + if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER)) + bio->bi_opf |= REQ_FUA; + submit_bio(bio); + + if (btrfs_advance_sb_log(device, i)) + atomic_inc(&device->sb_write_errors); } - return latest; + return atomic_read(&device->sb_write_errors) < i ? 0 : -1; } /* - * this should be called twice, once with wait == 0 and - * once with wait == 1. When wait == 0 is done, all the buffer heads - * we write are pinned. + * Wait for write completion of superblocks done by write_dev_supers, + * @max_mirrors same for write and wait phases. * - * They are released when wait == 1 is done. - * max_mirrors must be the same for both runs, and it indicates how - * many supers on this one device should be written. - * - * max_mirrors == 0 means to write them all. + * Return -1 if primary super block write failed or when there were no super block + * copies written. Otherwise 0. */ -static int write_dev_supers(struct btrfs_device *device, - struct btrfs_super_block *sb, - int do_barriers, int wait, int max_mirrors) +static int wait_dev_supers(struct btrfs_device *device, int max_mirrors) { - struct buffer_head *bh; int i; - int ret; int errors = 0; - u32 crc; + 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); - if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->total_bytes) - break; + struct folio *folio; - if (wait) { - bh = __find_get_block(device->bdev, bytenr / 4096, - BTRFS_SUPER_INFO_SIZE); - if (!bh) { - errors++; - continue; - } - wait_on_buffer(bh); - if (!buffer_uptodate(bh)) - errors++; - - /* drop our reference */ - brelse(bh); - - /* drop the reference from the wait == 0 run */ - brelse(bh); + 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; - } else { - btrfs_set_super_bytenr(sb, bytenr); - - crc = ~(u32)0; - crc = btrfs_csum_data((char *)sb + - BTRFS_CSUM_SIZE, crc, - BTRFS_SUPER_INFO_SIZE - - BTRFS_CSUM_SIZE); - btrfs_csum_final(crc, sb->csum); - - /* - * one reference for us, and we leave it for the - * caller - */ - bh = __getblk(device->bdev, bytenr / 4096, - BTRFS_SUPER_INFO_SIZE); - if (!bh) { - printk(KERN_ERR "btrfs: couldn't get super " - "buffer head for bytenr %Lu\n", bytenr); - errors++; - continue; - } - - memcpy(bh->b_data, sb, BTRFS_SUPER_INFO_SIZE); + } + if (bytenr + BTRFS_SUPER_INFO_SIZE >= + device->commit_total_bytes) + break; - /* one reference for submit_bh */ - get_bh(bh); + folio = filemap_get_folio(device->bdev->bd_mapping, + bytenr >> PAGE_SHIFT); + /* If the folio has been removed, then we know it completed. */ + if (IS_ERR(folio)) + continue; - set_buffer_uptodate(bh); - lock_buffer(bh); - bh->b_end_io = btrfs_end_buffer_write_sync; - bh->b_private = device; - } + /* Folio will be unlocked once the write completes. */ + folio_wait_locked(folio); + folio_put(folio); + } - /* - * we fua the first super. The others we allow - * to go down lazy. - */ - ret = btrfsic_submit_bh(WRITE_FUA, bh); - if (ret) - errors++; + errors += atomic_read(&device->sb_write_errors); + if (errors >= BTRFS_SUPER_PRIMARY_WRITE_ERROR) + primary_failed = true; + if (primary_failed) { + btrfs_err(device->fs_info, "error writing primary super block to device %llu", + device->devid); + return -1; } + return errors < i ? 0 : -1; } @@ -3103,76 +3856,51 @@ static int write_dev_supers(struct btrfs_device *device, * endio for the write_dev_flush, this will wake anyone waiting * for the barrier when it is done */ -static void btrfs_end_empty_barrier(struct bio *bio, int err) +static void btrfs_end_empty_barrier(struct bio *bio) { - if (err) { - if (err == -EOPNOTSUPP) - set_bit(BIO_EOPNOTSUPP, &bio->bi_flags); - clear_bit(BIO_UPTODATE, &bio->bi_flags); - } - if (bio->bi_private) - complete(bio->bi_private); - bio_put(bio); + bio_uninit(bio); + complete(bio->bi_private); } /* - * trigger flushes for one the devices. If you pass wait == 0, the flushes are - * sent down. With wait == 1, it waits for the previous flush. - * - * any device where the flush fails with eopnotsupp are flagged as not-barrier - * capable + * Submit a flush request to the device if it supports it. Error handling is + * done in the waiting counterpart. */ -static int write_dev_flush(struct btrfs_device *device, int wait) +static void write_dev_flush(struct btrfs_device *device) { - struct bio *bio; - int ret = 0; + struct bio *bio = &device->flush_bio; - if (device->nobarriers) - return 0; + device->last_flush_error = BLK_STS_OK; - if (wait) { - bio = device->flush_bio; - if (!bio) - return 0; + bio_init(bio, device->bdev, NULL, 0, + REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH); + bio->bi_end_io = btrfs_end_empty_barrier; + init_completion(&device->flush_wait); + bio->bi_private = &device->flush_wait; + submit_bio(bio); + set_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state); +} - wait_for_completion(&device->flush_wait); +/* + * If the flush bio has been submitted by write_dev_flush, wait for it. + * Return true for any error, and false otherwise. + */ +static bool wait_dev_flush(struct btrfs_device *device) +{ + struct bio *bio = &device->flush_bio; - if (bio_flagged(bio, BIO_EOPNOTSUPP)) { - printk_in_rcu("btrfs: disabling barriers on dev %s\n", - rcu_str_deref(device->name)); - device->nobarriers = 1; - } else if (!bio_flagged(bio, BIO_UPTODATE)) { - ret = -EIO; - btrfs_dev_stat_inc_and_print(device, - BTRFS_DEV_STAT_FLUSH_ERRS); - } + if (!test_and_clear_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state)) + return false; - /* drop the reference from the wait == 0 run */ - bio_put(bio); - device->flush_bio = NULL; + wait_for_completion_io(&device->flush_wait); - return ret; + if (bio->bi_status) { + device->last_flush_error = bio->bi_status; + btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_FLUSH_ERRS); + return true; } - /* - * one reference for us, and we leave it for the - * caller - */ - device->flush_bio = NULL; - bio = btrfs_io_bio_alloc(GFP_NOFS, 0); - if (!bio) - return -ENOMEM; - - bio->bi_end_io = btrfs_end_empty_barrier; - bio->bi_bdev = device->bdev; - init_completion(&device->flush_wait); - bio->bi_private = &device->flush_wait; - device->flush_bio = bio; - - bio_get(bio); - btrfsic_submit_bio(WRITE_FLUSH, bio); - - return 0; + return false; } /* @@ -3183,123 +3911,79 @@ static int barrier_all_devices(struct btrfs_fs_info *info) { struct list_head *head; struct btrfs_device *dev; - int errors_send = 0; int errors_wait = 0; - int ret; + lockdep_assert_held(&info->fs_devices->device_list_mutex); /* send down all the barriers */ head = &info->fs_devices->devices; - list_for_each_entry_rcu(dev, head, dev_list) { - if (!dev->bdev) { - errors_send++; + list_for_each_entry(dev, head, dev_list) { + if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) continue; - } - if (!dev->in_fs_metadata || !dev->writeable) + if (!dev->bdev) + continue; + if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || + !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue; - ret = write_dev_flush(dev, 0); - if (ret) - errors_send++; + write_dev_flush(dev); } /* wait for all the barriers */ - list_for_each_entry_rcu(dev, head, dev_list) { + list_for_each_entry(dev, head, dev_list) { + if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) + continue; if (!dev->bdev) { errors_wait++; continue; } - if (!dev->in_fs_metadata || !dev->writeable) + if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || + !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue; - ret = write_dev_flush(dev, 1); - if (ret) + if (wait_dev_flush(dev)) errors_wait++; } - if (errors_send > info->num_tolerated_disk_barrier_failures || - errors_wait > info->num_tolerated_disk_barrier_failures) + + /* + * Checks last_flush_error of disks in order to determine the device + * state. + */ + if (unlikely(errors_wait && !btrfs_check_rw_degradable(info, NULL))) return -EIO; + return 0; } -int btrfs_calc_num_tolerated_disk_barrier_failures( - struct btrfs_fs_info *fs_info) +int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags) { - struct btrfs_ioctl_space_info space; - struct btrfs_space_info *sinfo; - u64 types[] = {BTRFS_BLOCK_GROUP_DATA, - BTRFS_BLOCK_GROUP_SYSTEM, - BTRFS_BLOCK_GROUP_METADATA, - BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA}; - int num_types = 4; - int i; - int c; - int num_tolerated_disk_barrier_failures = - (int)fs_info->fs_devices->num_devices; - - for (i = 0; i < num_types; i++) { - struct btrfs_space_info *tmp; - - sinfo = NULL; - rcu_read_lock(); - list_for_each_entry_rcu(tmp, &fs_info->space_info, list) { - if (tmp->flags == types[i]) { - sinfo = tmp; - break; - } - } - rcu_read_unlock(); + int raid_type; + int min_tolerated = INT_MAX; + + if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 || + (flags & BTRFS_AVAIL_ALLOC_BIT_SINGLE)) + min_tolerated = min_t(int, min_tolerated, + btrfs_raid_array[BTRFS_RAID_SINGLE]. + tolerated_failures); - if (!sinfo) + for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) { + if (raid_type == BTRFS_RAID_SINGLE) continue; + if (!(flags & btrfs_raid_array[raid_type].bg_flag)) + continue; + min_tolerated = min_t(int, min_tolerated, + btrfs_raid_array[raid_type]. + tolerated_failures); + } - down_read(&sinfo->groups_sem); - for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) { - if (!list_empty(&sinfo->block_groups[c])) { - u64 flags; - - btrfs_get_block_group_info( - &sinfo->block_groups[c], &space); - if (space.total_bytes == 0 || - space.used_bytes == 0) - continue; - flags = space.flags; - /* - * return - * 0: if dup, single or RAID0 is configured for - * any of metadata, system or data, else - * 1: if RAID5 is configured, or if RAID1 or - * RAID10 is configured and only two mirrors - * are used, else - * 2: if RAID6 is configured, else - * num_mirrors - 1: if RAID1 or RAID10 is - * configured and more than - * 2 mirrors are used. - */ - if (num_tolerated_disk_barrier_failures > 0 && - ((flags & (BTRFS_BLOCK_GROUP_DUP | - BTRFS_BLOCK_GROUP_RAID0)) || - ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) - == 0))) - num_tolerated_disk_barrier_failures = 0; - else if (num_tolerated_disk_barrier_failures > 1) { - if (flags & (BTRFS_BLOCK_GROUP_RAID1 | - BTRFS_BLOCK_GROUP_RAID5 | - BTRFS_BLOCK_GROUP_RAID10)) { - num_tolerated_disk_barrier_failures = 1; - } else if (flags & - BTRFS_BLOCK_GROUP_RAID6) { - num_tolerated_disk_barrier_failures = 2; - } - } - } - } - up_read(&sinfo->groups_sem); + if (min_tolerated == INT_MAX) { + btrfs_warn(NULL, "unknown raid flag: %llu", flags); + min_tolerated = 0; } - return num_tolerated_disk_barrier_failures; + return min_tolerated; } -static int write_all_supers(struct btrfs_root *root, int max_mirrors) +int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) { struct list_head *head; struct btrfs_device *dev; @@ -3311,204 +3995,227 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) int total_errors = 0; u64 flags; - max_errors = btrfs_super_num_devices(root->fs_info->super_copy) - 1; - do_barriers = !btrfs_test_opt(root, NOBARRIER); - backup_super_roots(root->fs_info); + do_barriers = !btrfs_test_opt(fs_info, NOBARRIER); - sb = root->fs_info->super_for_commit; + /* + * max_mirrors == 0 indicates we're from commit_transaction, + * not from fsync where the tree roots in fs_info have not + * been consistent on disk. + */ + if (max_mirrors == 0) + backup_super_roots(fs_info); + + sb = fs_info->super_for_commit; dev_item = &sb->dev_item; - mutex_lock(&root->fs_info->fs_devices->device_list_mutex); - head = &root->fs_info->fs_devices->devices; + mutex_lock(&fs_info->fs_devices->device_list_mutex); + head = &fs_info->fs_devices->devices; + max_errors = btrfs_super_num_devices(fs_info->super_copy) - 1; if (do_barriers) { - ret = barrier_all_devices(root->fs_info); + ret = barrier_all_devices(fs_info); if (ret) { mutex_unlock( - &root->fs_info->fs_devices->device_list_mutex); - btrfs_error(root->fs_info, ret, - "errors while submitting device barriers."); + &fs_info->fs_devices->device_list_mutex); + btrfs_handle_fs_error(fs_info, ret, + "errors while submitting device barriers."); return ret; } } - list_for_each_entry_rcu(dev, head, dev_list) { + list_for_each_entry(dev, head, dev_list) { if (!dev->bdev) { total_errors++; continue; } - if (!dev->in_fs_metadata || !dev->writeable) + if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || + !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue; btrfs_set_stack_device_generation(dev_item, 0); btrfs_set_stack_device_type(dev_item, dev->type); btrfs_set_stack_device_id(dev_item, dev->devid); - btrfs_set_stack_device_total_bytes(dev_item, dev->total_bytes); - btrfs_set_stack_device_bytes_used(dev_item, dev->bytes_used); + btrfs_set_stack_device_total_bytes(dev_item, + dev->commit_total_bytes); + btrfs_set_stack_device_bytes_used(dev_item, + dev->commit_bytes_used); btrfs_set_stack_device_io_align(dev_item, dev->io_align); btrfs_set_stack_device_io_width(dev_item, dev->io_width); btrfs_set_stack_device_sector_size(dev_item, dev->sector_size); memcpy(dev_item->uuid, dev->uuid, BTRFS_UUID_SIZE); - memcpy(dev_item->fsid, dev->fs_devices->fsid, BTRFS_UUID_SIZE); + memcpy(dev_item->fsid, dev->fs_devices->metadata_uuid, + BTRFS_FSID_SIZE); flags = btrfs_super_flags(sb); btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN); - ret = write_dev_supers(dev, sb, do_barriers, 0, max_mirrors); + ret = btrfs_validate_write_super(fs_info, sb); + if (unlikely(ret < 0)) { + mutex_unlock(&fs_info->fs_devices->device_list_mutex); + btrfs_handle_fs_error(fs_info, -EUCLEAN, + "unexpected superblock corruption detected"); + return -EUCLEAN; + } + + ret = write_dev_supers(dev, sb, max_mirrors); if (ret) total_errors++; } - if (total_errors > max_errors) { - printk(KERN_ERR "btrfs: %d errors while writing supers\n", - total_errors); + if (unlikely(total_errors > max_errors)) { + btrfs_err(fs_info, "%d errors while writing supers", + total_errors); + mutex_unlock(&fs_info->fs_devices->device_list_mutex); - /* This shouldn't happen. FUA is masked off if unsupported */ - BUG(); + /* FUA is masked off if unsupported and can't be the reason */ + btrfs_handle_fs_error(fs_info, -EIO, + "%d errors while writing supers", + total_errors); + return -EIO; } total_errors = 0; - list_for_each_entry_rcu(dev, head, dev_list) { + list_for_each_entry(dev, head, dev_list) { if (!dev->bdev) continue; - if (!dev->in_fs_metadata || !dev->writeable) + if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || + !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue; - ret = write_dev_supers(dev, sb, do_barriers, 1, max_mirrors); + ret = wait_dev_supers(dev, max_mirrors); if (ret) total_errors++; } - mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); - if (total_errors > max_errors) { - btrfs_error(root->fs_info, -EIO, - "%d errors while writing supers", total_errors); + mutex_unlock(&fs_info->fs_devices->device_list_mutex); + if (unlikely(total_errors > max_errors)) { + btrfs_handle_fs_error(fs_info, -EIO, + "%d errors while writing supers", + total_errors); return -EIO; } return 0; } -int write_ctree_super(struct btrfs_trans_handle *trans, - struct btrfs_root *root, int max_mirrors) -{ - int ret; - - ret = write_all_supers(root, max_mirrors); - return ret; -} - /* Drop a fs root from the radix tree and free it. */ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) { + bool drop_ref = false; + spin_lock(&fs_info->fs_roots_radix_lock); radix_tree_delete(&fs_info->fs_roots_radix, - (unsigned long)root->root_key.objectid); + (unsigned long)btrfs_root_id(root)); + if (test_and_clear_bit(BTRFS_ROOT_IN_RADIX, &root->state)) + drop_ref = true; spin_unlock(&fs_info->fs_roots_radix_lock); - if (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); - btrfs_free_log_root_tree(NULL, fs_info); + if (BTRFS_FS_ERROR(fs_info)) { + ASSERT(root->log_root == NULL); + if (root->reloc_root) { + btrfs_put_root(root->reloc_root); + root->reloc_root = NULL; + } } - __btrfs_remove_free_space_cache(root->free_ino_pinned); - __btrfs_remove_free_space_cache(root->free_ino_ctl); - free_fs_root(root); + if (drop_ref) + btrfs_put_root(root); } -static void free_fs_root(struct btrfs_root *root) +int btrfs_commit_super(struct btrfs_fs_info *fs_info) { - iput(root->cache_inode); - WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree)); - if (root->anon_dev) - free_anon_bdev(root->anon_dev); - free_extent_buffer(root->node); - free_extent_buffer(root->commit_root); - kfree(root->free_ino_ctl); - kfree(root->free_ino_pinned); - kfree(root->name); - btrfs_put_fs_root(root); -} + mutex_lock(&fs_info->cleaner_mutex); + btrfs_run_delayed_iputs(fs_info); + mutex_unlock(&fs_info->cleaner_mutex); + wake_up_process(fs_info->cleaner_kthread); -void btrfs_free_fs_root(struct btrfs_root *root) -{ - free_fs_root(root); + /* wait until ongoing cleanup work done */ + down_write(&fs_info->cleanup_work_sem); + up_write(&fs_info->cleanup_work_sem); + + return btrfs_commit_current_transaction(fs_info->tree_root); } -int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) +static void warn_about_uncommitted_trans(struct btrfs_fs_info *fs_info) { - u64 root_objectid = 0; - struct btrfs_root *gang[8]; - int i; - int ret; + struct btrfs_transaction *trans; + struct btrfs_transaction *tmp; + bool found = false; - while (1) { - ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, - (void **)gang, root_objectid, - ARRAY_SIZE(gang)); - if (!ret) - break; + /* + * This function is only called at the very end of close_ctree(), + * thus no other running transaction, no need to take trans_lock. + */ + ASSERT(test_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags)); + list_for_each_entry_safe(trans, tmp, &fs_info->trans_list, list) { + struct extent_state *cached = NULL; + u64 dirty_bytes = 0; + u64 cur = 0; + u64 found_start; + u64 found_end; + + found = true; + while (btrfs_find_first_extent_bit(&trans->dirty_pages, cur, + &found_start, &found_end, + EXTENT_DIRTY, &cached)) { + dirty_bytes += found_end + 1 - found_start; + cur = found_end + 1; + } + btrfs_warn(fs_info, + "transaction %llu (with %llu dirty metadata bytes) is not committed", + trans->transid, dirty_bytes); + btrfs_cleanup_one_transaction(trans); - root_objectid = gang[ret - 1]->root_key.objectid + 1; - for (i = 0; i < ret; i++) { - int err; + if (trans == fs_info->running_transaction) + fs_info->running_transaction = NULL; + list_del_init(&trans->list); - root_objectid = gang[i]->root_key.objectid; - err = btrfs_orphan_cleanup(gang[i]); - if (err) - return err; - } - root_objectid++; + btrfs_put_transaction(trans); + trace_btrfs_transaction_commit(fs_info); } - return 0; + ASSERT(!found); } -int btrfs_commit_super(struct btrfs_root *root) +void __cold close_ctree(struct btrfs_fs_info *fs_info) { - struct btrfs_trans_handle *trans; int ret; - mutex_lock(&root->fs_info->cleaner_mutex); - btrfs_run_delayed_iputs(root); - mutex_unlock(&root->fs_info->cleaner_mutex); - wake_up_process(root->fs_info->cleaner_kthread); + set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); - /* wait until ongoing cleanup work done */ - down_write(&root->fs_info->cleanup_work_sem); - up_write(&root->fs_info->cleanup_work_sem); - - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) - return PTR_ERR(trans); - ret = btrfs_commit_transaction(trans, root); - if (ret) - return ret; - /* run commit again to drop the original snapshot */ - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) - return PTR_ERR(trans); - ret = btrfs_commit_transaction(trans, root); - if (ret) - return ret; - ret = btrfs_write_and_wait_transaction(NULL, root); - if (ret) { - btrfs_error(root->fs_info, ret, - "Failed to sync btree inode to disk."); - return ret; - } + /* + * 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); - ret = write_ctree_super(NULL, root, 0); - return ret; -} + /* + * We may have the reclaim task running and relocating a data block group, + * in which case it may create delayed iputs. So stop it before we park + * the cleaner kthread otherwise we can get new delayed iputs after + * parking the cleaner, and that can make the async reclaim task to hang + * if it's waiting for delayed iputs to complete, since the cleaner is + * parked and can not run delayed iputs - this will make us hang when + * trying to stop the async reclaim task. + */ + cancel_work_sync(&fs_info->reclaim_bgs_work); + /* + * We don't want the cleaner to start new transactions, add more delayed + * iputs, etc. while we're closing. We can't use kthread_stop() yet + * because that frees the task_struct, and the transaction kthread might + * still try to wake up the cleaner. + */ + kthread_park(fs_info->cleaner_kthread); -int close_ctree(struct btrfs_root *root) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - int ret; + /* wait for the qgroup rescan worker to stop */ + btrfs_qgroup_wait_for_completion(fs_info, false); - fs_info->closing = 1; - smp_mb(); + /* wait for the uuid_scan task to finish */ + down(&fs_info->uuid_tree_rescan_sem); + /* avoid complains from lockdep et al., set sem back to initial state */ + up(&fs_info->uuid_tree_rescan_sem); /* pause restriper - we want to resume on mount */ btrfs_pause_balance(fs_info); @@ -3524,101 +4231,217 @@ int close_ctree(struct btrfs_root *root) /* clear out the rbtree of defraggable inodes */ btrfs_cleanup_defrag_inodes(fs_info); - if (!(fs_info->sb->s_flags & MS_RDONLY)) { - ret = btrfs_commit_super(root); - if (ret) - printk(KERN_ERR "btrfs: commit super ret %d\n", ret); - } + /* + * Handle the error fs first, as it will flush and wait for all ordered + * extents. This will generate delayed iputs, thus we want to handle + * it first. + */ + if (unlikely(BTRFS_FS_ERROR(fs_info))) + btrfs_error_commit_super(fs_info); - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) - btrfs_error_commit_super(root); + /* + * Wait for any fixup workers to complete. + * If we don't wait for them here and they are still running by the time + * we call kthread_stop() against the cleaner kthread further below, we + * get an use-after-free on the cleaner because the fixup worker adds an + * inode to the list of delayed iputs and then attempts to wakeup the + * cleaner kthread, which was already stopped and destroyed. We parked + * already the cleaner, but below we run all pending delayed iputs. + */ + btrfs_flush_workqueue(fs_info->fixup_workers); + /* + * Similar case here, we have to wait for delalloc workers before we + * proceed below and stop the cleaner kthread, otherwise we trigger a + * use-after-tree on the cleaner kthread task_struct when a delalloc + * worker running submit_compressed_extents() adds a delayed iput, which + * does a wake up on the cleaner kthread, which was already freed below + * when we call kthread_stop(). + */ + btrfs_flush_workqueue(fs_info->delalloc_workers); - btrfs_put_block_group_cache(fs_info); + /* + * We can have ordered extents getting their last reference dropped from + * the fs_info->workers queue because for async writes for data bios we + * queue a work for that queue, at btrfs_wq_submit_bio(), that runs + * run_one_async_done() which calls btrfs_bio_end_io() in case the bio + * has an error, and that later function can do the final + * btrfs_put_ordered_extent() on the ordered extent attached to the bio, + * which adds a delayed iput for the inode. So we must flush the queue + * so that we don't have delayed iputs after committing the current + * transaction below and stopping the cleaner and transaction kthreads. + */ + btrfs_flush_workqueue(fs_info->workers); + + /* + * When finishing a compressed write bio we schedule a work queue item + * to finish an ordered extent - end_bbio_compressed_write() + * calls btrfs_finish_ordered_extent() which in turns does a call to + * btrfs_queue_ordered_fn(), and that queues the ordered extent + * completion either in the endio_write_workers work queue or in the + * fs_info->endio_freespace_worker work queue. We flush those queues + * below, so before we flush them we must flush this queue for the + * workers of compressed writes. + */ + flush_workqueue(fs_info->endio_workers); + + /* + * After we parked the cleaner kthread, ordered extents may have + * completed and created new delayed iputs. If one of the async reclaim + * tasks is running and in the RUN_DELAYED_IPUTS flush state, then we + * can hang forever trying to stop it, because if a delayed iput is + * added after it ran btrfs_run_delayed_iputs() and before it called + * btrfs_wait_on_delayed_iputs(), it will hang forever since there is + * no one else to run iputs. + * + * So wait for all ongoing ordered extents to complete and then run + * delayed iputs. This works because once we reach this point no one + * can create new ordered extents, but delayed iputs can still be added + * by a reclaim worker (see comments further below). + * + * Also note that btrfs_wait_ordered_roots() is not safe here, because + * it waits for BTRFS_ORDERED_COMPLETE to be set on an ordered extent, + * but the delayed iput for the respective inode is made only when doing + * the final btrfs_put_ordered_extent() (which must happen at + * btrfs_finish_ordered_io() when we are unmounting). + */ + btrfs_flush_workqueue(fs_info->endio_write_workers); + /* Ordered extents for free space inodes. */ + btrfs_flush_workqueue(fs_info->endio_freespace_worker); + /* + * Run delayed iputs in case an async reclaim worker is waiting for them + * to be run as mentioned above. + */ + btrfs_run_delayed_iputs(fs_info); + + cancel_work_sync(&fs_info->async_reclaim_work); + cancel_work_sync(&fs_info->async_data_reclaim_work); + cancel_work_sync(&fs_info->preempt_reclaim_work); + cancel_work_sync(&fs_info->em_shrinker_work); + + /* + * Run delayed iputs again because an async reclaim worker may have + * added new ones if it was flushing delalloc: + * + * shrink_delalloc() -> btrfs_start_delalloc_roots() -> + * start_delalloc_inodes() -> btrfs_add_delayed_iput() + */ + btrfs_run_delayed_iputs(fs_info); + + /* There should be no more workload to generate new delayed iputs. */ + set_bit(BTRFS_FS_STATE_NO_DELAYED_IPUT, &fs_info->fs_state); + + /* Cancel or finish ongoing discard work */ + btrfs_discard_cleanup(fs_info); + + if (!sb_rdonly(fs_info->sb)) { + /* + * The cleaner kthread is stopped, so do one final pass over + * unused block groups. + */ + btrfs_delete_unused_bgs(fs_info); + + /* + * There might be existing delayed inode workers still running + * and holding an empty delayed inode item. We must wait for + * them to complete first because they can create a transaction. + * This happens when someone calls btrfs_balance_delayed_items() + * and then a transaction commit runs the same delayed nodes + * before any delayed worker has done something with the nodes. + * We must wait for any worker here and not at transaction + * commit time since that could cause a deadlock. + * This is a very rare case. + */ + btrfs_flush_workqueue(fs_info->delayed_workers); + + ret = btrfs_commit_super(fs_info); + if (ret) + btrfs_err(fs_info, "commit super ret %d", ret); + } kthread_stop(fs_info->transaction_kthread); kthread_stop(fs_info->cleaner_kthread); - fs_info->closing = 2; - smp_mb(); + ASSERT(list_empty(&fs_info->delayed_iputs)); + set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags); + + if (btrfs_check_quota_leak(fs_info)) { + DEBUG_WARN("qgroup reserved space leaked"); + btrfs_err(fs_info, "qgroup reserved space leaked"); + } - btrfs_free_qgroup_config(root->fs_info); + btrfs_free_qgroup_config(fs_info); + ASSERT(list_empty(&fs_info->delalloc_roots)); if (percpu_counter_sum(&fs_info->delalloc_bytes)) { - printk(KERN_INFO "btrfs: at unmount delalloc count %lld\n", + btrfs_info(fs_info, "at unmount delalloc count %lld", percpu_counter_sum(&fs_info->delalloc_bytes)); } - btrfs_free_block_groups(fs_info); - - btrfs_stop_all_workers(fs_info); + if (percpu_counter_sum(&fs_info->ordered_bytes)) + btrfs_info(fs_info, "at unmount dio bytes count %lld", + percpu_counter_sum(&fs_info->ordered_bytes)); - del_fs_roots(fs_info); + btrfs_sysfs_remove_mounted(fs_info); + btrfs_sysfs_remove_fsid(fs_info->fs_devices); - free_root_pointers(fs_info, 1); + btrfs_put_block_group_cache(fs_info); - iput(fs_info->btree_inode); + /* + * we must make sure there is not any read request to + * submit after we stopping all workers. + */ + invalidate_inode_pages2(fs_info->btree_inode->i_mapping); + btrfs_stop_all_workers(fs_info); -#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY - if (btrfs_test_opt(root, CHECK_INTEGRITY)) - btrfsic_unmount(root, fs_info->fs_devices); -#endif + /* We shouldn't have any transaction open at this point */ + warn_about_uncommitted_trans(fs_info); - btrfs_close_devices(fs_info->fs_devices); - btrfs_mapping_tree_free(&fs_info->mapping_tree); + clear_bit(BTRFS_FS_OPEN, &fs_info->flags); + free_root_pointers(fs_info, true); + btrfs_free_fs_roots(fs_info); - percpu_counter_destroy(&fs_info->dirty_metadata_bytes); - percpu_counter_destroy(&fs_info->delalloc_bytes); - bdi_destroy(&fs_info->bdi); - cleanup_srcu_struct(&fs_info->subvol_srcu); + /* + * We must free the block groups after dropping the fs_roots as we could + * have had an IO error and have left over tree log blocks that aren't + * cleaned up until the fs roots are freed. This makes the block group + * accounting appear to be wrong because there's pending reserved bytes, + * so make sure we do the block group cleanup afterwards. + */ + btrfs_free_block_groups(fs_info); - btrfs_free_stripe_hash_table(fs_info); + iput(fs_info->btree_inode); - return 0; + btrfs_mapping_tree_free(fs_info); } -int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, - int atomic) +void btrfs_mark_buffer_dirty(struct btrfs_trans_handle *trans, + struct extent_buffer *buf) { - int ret; - struct inode *btree_inode = buf->pages[0]->mapping->host; - - ret = extent_buffer_uptodate(buf); - if (!ret) - return ret; - - ret = verify_parent_transid(&BTRFS_I(btree_inode)->io_tree, buf, - parent_transid, atomic); - if (ret == -EAGAIN) - return ret; - return !ret; -} + struct btrfs_fs_info *fs_info = buf->fs_info; + u64 transid = btrfs_header_generation(buf); -int btrfs_set_buffer_uptodate(struct extent_buffer *buf) -{ - return set_extent_buffer_uptodate(buf); +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS + /* + * This is a fast path so only do this check if we have sanity tests + * enabled. Normal people shouldn't be using unmapped buffers as dirty + * outside of the sanity tests. + */ + if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &buf->bflags))) + return; +#endif + /* This is an active transaction (its state < TRANS_STATE_UNBLOCKED). */ + ASSERT(trans->transid == fs_info->generation); + btrfs_assert_tree_write_locked(buf); + if (unlikely(transid != fs_info->generation)) { + btrfs_abort_transaction(trans, -EUCLEAN); + btrfs_crit(fs_info, +"dirty buffer transid mismatch, logical %llu found transid %llu running transid %llu", + buf->start, transid, fs_info->generation); + } + set_extent_buffer_dirty(buf); } -void btrfs_mark_buffer_dirty(struct extent_buffer *buf) -{ - struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root; - u64 transid = btrfs_header_generation(buf); - int was_dirty; - - btrfs_assert_tree_locked(buf); - if (transid != root->fs_info->generation) - WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, " - "found %llu running %llu\n", - (unsigned long long)buf->start, - (unsigned long long)transid, - (unsigned long long)root->fs_info->generation); - was_dirty = set_extent_buffer_dirty(buf); - if (!was_dirty) - __percpu_counter_add(&root->fs_info->dirty_metadata_bytes, - buf->len, - root->fs_info->dirty_metadata_batch); -} - -static void __btrfs_btree_balance_dirty(struct btrfs_root *root, +static void __btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info, int flush_delayed) { /* @@ -3631,81 +4454,63 @@ static void __btrfs_btree_balance_dirty(struct btrfs_root *root, return; if (flush_delayed) - btrfs_balance_delayed_items(root); + btrfs_balance_delayed_items(fs_info); - ret = percpu_counter_compare(&root->fs_info->dirty_metadata_bytes, - BTRFS_DIRTY_METADATA_THRESH); + ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes, + BTRFS_DIRTY_METADATA_THRESH, + fs_info->dirty_metadata_batch); if (ret > 0) { - balance_dirty_pages_ratelimited( - root->fs_info->btree_inode->i_mapping); + balance_dirty_pages_ratelimited(fs_info->btree_inode->i_mapping); } - return; -} - -void btrfs_btree_balance_dirty(struct btrfs_root *root) -{ - __btrfs_btree_balance_dirty(root, 1); -} - -void btrfs_btree_balance_dirty_nodelay(struct btrfs_root *root) -{ - __btrfs_btree_balance_dirty(root, 0); } -int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid) +void btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info) { - struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root; - return btree_read_extent_buffer_pages(root, buf, 0, parent_transid); + __btrfs_btree_balance_dirty(fs_info, 1); } -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, - int read_only) +void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info) { - /* - * Placeholder for checks - */ - return 0; + __btrfs_btree_balance_dirty(fs_info, 0); } -static void btrfs_error_commit_super(struct btrfs_root *root) +static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info) { - mutex_lock(&root->fs_info->cleaner_mutex); - btrfs_run_delayed_iputs(root); - mutex_unlock(&root->fs_info->cleaner_mutex); - - down_write(&root->fs_info->cleanup_work_sem); - up_write(&root->fs_info->cleanup_work_sem); - /* cleanup FS via transaction */ - btrfs_cleanup_transaction(root); + btrfs_cleanup_transaction(fs_info); + + down_write(&fs_info->cleanup_work_sem); + up_write(&fs_info->cleanup_work_sem); } -static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t, - struct btrfs_root *root) +static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info) { - struct btrfs_inode *btrfs_inode; - struct list_head splice; - - INIT_LIST_HEAD(&splice); - - mutex_lock(&root->fs_info->ordered_operations_mutex); - spin_lock(&root->fs_info->ordered_root_lock); - - list_splice_init(&t->ordered_operations, &splice); - while (!list_empty(&splice)) { - btrfs_inode = list_entry(splice.next, struct btrfs_inode, - ordered_operations); + struct btrfs_root *gang[8]; + u64 root_objectid = 0; + int ret; - list_del_init(&btrfs_inode->ordered_operations); - spin_unlock(&root->fs_info->ordered_root_lock); + 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; - btrfs_invalidate_inodes(btrfs_inode->root); + for (i = 0; i < ret; i++) + gang[i] = btrfs_grab_root(gang[i]); + spin_unlock(&fs_info->fs_roots_radix_lock); - spin_lock(&root->fs_info->ordered_root_lock); + for (i = 0; i < ret; i++) { + if (!gang[i]) + continue; + root_objectid = btrfs_root_id(gang[i]); + btrfs_free_log(NULL, gang[i]); + btrfs_put_root(gang[i]); + } + root_objectid++; + spin_lock(&fs_info->fs_roots_radix_lock); } - - spin_unlock(&root->fs_info->ordered_root_lock); - mutex_unlock(&root->fs_info->ordered_operations_mutex); + 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) @@ -3726,338 +4531,377 @@ static void btrfs_destroy_ordered_extents(struct btrfs_root *root) static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; - struct list_head splice; - - INIT_LIST_HEAD(&splice); + LIST_HEAD(splice); spin_lock(&fs_info->ordered_root_lock); list_splice_init(&fs_info->ordered_roots, &splice); while (!list_empty(&splice)) { root = list_first_entry(&splice, struct btrfs_root, ordered_root); - list_del_init(&root->ordered_root); + list_move_tail(&root->ordered_root, + &fs_info->ordered_roots); + spin_unlock(&fs_info->ordered_root_lock); btrfs_destroy_ordered_extents(root); - cond_resched_lock(&fs_info->ordered_root_lock); - } - spin_unlock(&fs_info->ordered_root_lock); -} - -int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, - struct btrfs_root *root) -{ - struct rb_node *node; - struct btrfs_delayed_ref_root *delayed_refs; - struct btrfs_delayed_ref_node *ref; - int ret = 0; - - delayed_refs = &trans->delayed_refs; - - spin_lock(&delayed_refs->lock); - if (delayed_refs->num_entries == 0) { - spin_unlock(&delayed_refs->lock); - printk(KERN_INFO "delayed_refs has NO entry\n"); - return ret; - } - - while ((node = rb_first(&delayed_refs->root)) != NULL) { - struct btrfs_delayed_ref_head *head = NULL; - bool pin_bytes = false; - - ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node); - atomic_set(&ref->refs, 1); - if (btrfs_delayed_ref_is_head(ref)) { - - head = btrfs_delayed_node_to_head(ref); - if (!mutex_trylock(&head->mutex)) { - atomic_inc(&ref->refs); - spin_unlock(&delayed_refs->lock); - - /* Need to wait for the delayed ref to run */ - mutex_lock(&head->mutex); - mutex_unlock(&head->mutex); - btrfs_put_delayed_ref(ref); - - spin_lock(&delayed_refs->lock); - continue; - } - - if (head->must_insert_reserved) - pin_bytes = true; - btrfs_free_delayed_extent_op(head->extent_op); - delayed_refs->num_heads--; - if (list_empty(&head->cluster)) - delayed_refs->num_heads_ready--; - list_del_init(&head->cluster); - } - - ref->in_tree = 0; - rb_erase(&ref->rb_node, &delayed_refs->root); - delayed_refs->num_entries--; - spin_unlock(&delayed_refs->lock); - if (head) { - if (pin_bytes) - btrfs_pin_extent(root, ref->bytenr, - ref->num_bytes, 1); - mutex_unlock(&head->mutex); - } - btrfs_put_delayed_ref(ref); - cond_resched(); - spin_lock(&delayed_refs->lock); + spin_lock(&fs_info->ordered_root_lock); } + spin_unlock(&fs_info->ordered_root_lock); - spin_unlock(&delayed_refs->lock); - - return ret; -} - -static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t) -{ - struct btrfs_pending_snapshot *snapshot; - struct list_head splice; - - INIT_LIST_HEAD(&splice); - - list_splice_init(&t->pending_snapshots, &splice); - - while (!list_empty(&splice)) { - snapshot = list_entry(splice.next, - struct btrfs_pending_snapshot, - list); - snapshot->error = -ECANCELED; - list_del_init(&snapshot->list); - } + /* + * We need this here because if we've been flipped read-only we won't + * get sync() from the umount, so we need to make sure any ordered + * extents that haven't had their dirty pages IO start writeout yet + * actually get run and error out properly. + */ + btrfs_wait_ordered_roots(fs_info, U64_MAX, NULL); } static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) { struct btrfs_inode *btrfs_inode; - struct list_head splice; - - INIT_LIST_HEAD(&splice); + LIST_HEAD(splice); spin_lock(&root->delalloc_lock); list_splice_init(&root->delalloc_inodes, &splice); while (!list_empty(&splice)) { + struct inode *inode = NULL; btrfs_inode = list_first_entry(&splice, struct btrfs_inode, delalloc_inodes); - - list_del_init(&btrfs_inode->delalloc_inodes); - clear_bit(BTRFS_INODE_IN_DELALLOC_LIST, - &btrfs_inode->runtime_flags); + btrfs_del_delalloc_inode(btrfs_inode); spin_unlock(&root->delalloc_lock); - btrfs_invalidate_inodes(btrfs_inode->root); - + /* + * Make sure we get a live inode and that it'll not disappear + * meanwhile. + */ + inode = igrab(&btrfs_inode->vfs_inode); + if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); + invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); + iput(inode); + } spin_lock(&root->delalloc_lock); } - spin_unlock(&root->delalloc_lock); } static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; - struct list_head splice; - - INIT_LIST_HEAD(&splice); + LIST_HEAD(splice); spin_lock(&fs_info->delalloc_root_lock); list_splice_init(&fs_info->delalloc_roots, &splice); while (!list_empty(&splice)) { root = list_first_entry(&splice, struct btrfs_root, delalloc_root); - list_del_init(&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); } spin_unlock(&fs_info->delalloc_root_lock); } -static int btrfs_destroy_marked_extents(struct btrfs_root *root, - struct extent_io_tree *dirty_pages, - int mark) +static void btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info, + struct extent_io_tree *dirty_pages, + int mark) { - int ret; struct extent_buffer *eb; u64 start = 0; u64 end; - while (1) { - ret = find_first_extent_bit(dirty_pages, start, &start, &end, - mark, NULL); - if (ret) - break; - - clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS); + while (btrfs_find_first_extent_bit(dirty_pages, start, &start, &end, + mark, NULL)) { + btrfs_clear_extent_bit(dirty_pages, start, end, mark, NULL); while (start <= end) { - eb = btrfs_find_tree_block(root, start, - root->leafsize); - start += root->leafsize; + eb = find_extent_buffer(fs_info, start); + start += fs_info->nodesize; if (!eb) continue; + + btrfs_tree_lock(eb); wait_on_extent_buffer_writeback(eb); + btrfs_clear_buffer_dirty(NULL, eb); + btrfs_tree_unlock(eb); - if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, - &eb->bflags)) - clear_extent_buffer_dirty(eb); free_extent_buffer_stale(eb); } } - - return ret; } -static int btrfs_destroy_pinned_extent(struct btrfs_root *root, - struct extent_io_tree *pinned_extents) +static void btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, + 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) { - ret = find_first_extent_bit(unpin, 0, &start, &end, - EXTENT_DIRTY, NULL); - if (ret) - break; + struct extent_state *cached_state = NULL; - /* opt_discard */ - if (btrfs_test_opt(root, DISCARD)) - ret = btrfs_error_discard_extent(root, start, - end + 1 - start, - NULL); + /* + * The btrfs_finish_extent_commit() may get the same range as + * ours between find_first_extent_bit and clear_extent_dirty. + * Hence, hold the unused_bg_unpin_mutex to avoid double unpin + * the same extent range. + */ + mutex_lock(&fs_info->unused_bg_unpin_mutex); + if (!btrfs_find_first_extent_bit(unpin, 0, &start, &end, + EXTENT_DIRTY, &cached_state)) { + mutex_unlock(&fs_info->unused_bg_unpin_mutex); + break; + } - clear_extent_dirty(unpin, start, end, GFP_NOFS); - btrfs_error_unpin_extent_range(root, start, end); + btrfs_clear_extent_dirty(unpin, start, end, &cached_state); + btrfs_free_extent_state(cached_state); + btrfs_error_unpin_extent_range(fs_info, start, end); + mutex_unlock(&fs_info->unused_bg_unpin_mutex); cond_resched(); } +} - if (loop) { - if (unpin == &root->fs_info->freed_extents[0]) - unpin = &root->fs_info->freed_extents[1]; - else - unpin = &root->fs_info->freed_extents[0]; - loop = false; - goto again; - } +static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) +{ + struct inode *inode; - return 0; + inode = cache->io_ctl.inode; + if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); + invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); + + BTRFS_I(inode)->generation = 0; + cache->io_ctl.inode = NULL; + iput(inode); + } + ASSERT(cache->io_ctl.pages == NULL); + btrfs_put_block_group(cache); } -void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, - struct btrfs_root *root) +void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, + struct btrfs_fs_info *fs_info) { - btrfs_destroy_delayed_refs(cur_trans, root); - btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv, - cur_trans->dirty_pages.dirty_bytes); + struct btrfs_block_group *cache; + + spin_lock(&cur_trans->dirty_bgs_lock); + while (!list_empty(&cur_trans->dirty_bgs)) { + cache = list_first_entry(&cur_trans->dirty_bgs, + struct btrfs_block_group, + dirty_list); + + if (!list_empty(&cache->io_list)) { + spin_unlock(&cur_trans->dirty_bgs_lock); + list_del_init(&cache->io_list); + btrfs_cleanup_bg_io(cache); + spin_lock(&cur_trans->dirty_bgs_lock); + } - cur_trans->state = TRANS_STATE_COMMIT_START; - wake_up(&root->fs_info->transaction_blocked_wait); + list_del_init(&cache->dirty_list); + spin_lock(&cache->lock); + cache->disk_cache_state = BTRFS_DC_ERROR; + spin_unlock(&cache->lock); - btrfs_evict_pending_snapshots(cur_trans); + spin_unlock(&cur_trans->dirty_bgs_lock); + btrfs_put_block_group(cache); + btrfs_dec_delayed_refs_rsv_bg_updates(fs_info); + spin_lock(&cur_trans->dirty_bgs_lock); + } + spin_unlock(&cur_trans->dirty_bgs_lock); - cur_trans->state = TRANS_STATE_UNBLOCKED; - wake_up(&root->fs_info->transaction_wait); + /* + * Refer to the definition of io_bgs member for details why it's safe + * to use it without any locking + */ + while (!list_empty(&cur_trans->io_bgs)) { + cache = list_first_entry(&cur_trans->io_bgs, + struct btrfs_block_group, + io_list); - btrfs_destroy_delayed_inodes(root); - btrfs_assert_delayed_root_empty(root); + list_del_init(&cache->io_list); + spin_lock(&cache->lock); + cache->disk_cache_state = BTRFS_DC_ERROR; + spin_unlock(&cache->lock); + btrfs_cleanup_bg_io(cache); + } +} - btrfs_destroy_marked_extents(root, &cur_trans->dirty_pages, - EXTENT_DIRTY); - btrfs_destroy_pinned_extent(root, - root->fs_info->pinned_extents); +static void btrfs_free_all_qgroup_pertrans(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *gang[8]; + int i; + int ret; - cur_trans->state =TRANS_STATE_COMPLETED; - wake_up(&cur_trans->commit_wait); + spin_lock(&fs_info->fs_roots_radix_lock); + while (1) { + ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix, + (void **)gang, 0, + ARRAY_SIZE(gang), + BTRFS_ROOT_TRANS_TAG); + if (ret == 0) + break; + for (i = 0; i < ret; i++) { + struct btrfs_root *root = gang[i]; - /* - memset(cur_trans, 0, sizeof(*cur_trans)); - kmem_cache_free(btrfs_transaction_cachep, cur_trans); - */ + btrfs_qgroup_free_meta_all_pertrans(root); + radix_tree_tag_clear(&fs_info->fs_roots_radix, + (unsigned long)btrfs_root_id(root), + BTRFS_ROOT_TRANS_TAG); + } + } + spin_unlock(&fs_info->fs_roots_radix_lock); } -static int btrfs_cleanup_transaction(struct btrfs_root *root) +void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans) { - struct btrfs_transaction *t; - LIST_HEAD(list); + struct btrfs_fs_info *fs_info = cur_trans->fs_info; + struct btrfs_device *dev, *tmp; - mutex_lock(&root->fs_info->transaction_kthread_mutex); + btrfs_cleanup_dirty_bgs(cur_trans, fs_info); + ASSERT(list_empty(&cur_trans->dirty_bgs)); + ASSERT(list_empty(&cur_trans->io_bgs)); - spin_lock(&root->fs_info->trans_lock); - list_splice_init(&root->fs_info->trans_list, &list); - root->fs_info->running_transaction = NULL; - spin_unlock(&root->fs_info->trans_lock); + list_for_each_entry_safe(dev, tmp, &cur_trans->dev_update_list, + post_commit_list) { + list_del_init(&dev->post_commit_list); + } - while (!list_empty(&list)) { - t = list_entry(list.next, struct btrfs_transaction, list); + btrfs_destroy_delayed_refs(cur_trans); - btrfs_destroy_ordered_operations(t, root); + cur_trans->state = TRANS_STATE_COMMIT_START; + wake_up(&fs_info->transaction_blocked_wait); - btrfs_destroy_all_ordered_extents(root->fs_info); + cur_trans->state = TRANS_STATE_UNBLOCKED; + wake_up(&fs_info->transaction_wait); - btrfs_destroy_delayed_refs(t, root); + btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages, + EXTENT_DIRTY); + btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents); - /* - * FIXME: cleanup wait for commit - * We needn't acquire the lock here, because we are during - * the umount, there is no other task which will change it. - */ - t->state = TRANS_STATE_COMMIT_START; - smp_mb(); - if (waitqueue_active(&root->fs_info->transaction_blocked_wait)) - wake_up(&root->fs_info->transaction_blocked_wait); + cur_trans->state =TRANS_STATE_COMPLETED; + wake_up(&cur_trans->commit_wait); +} - btrfs_evict_pending_snapshots(t); +static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) +{ + struct btrfs_transaction *t; - t->state = TRANS_STATE_UNBLOCKED; - smp_mb(); - if (waitqueue_active(&root->fs_info->transaction_wait)) - wake_up(&root->fs_info->transaction_wait); + mutex_lock(&fs_info->transaction_kthread_mutex); + + spin_lock(&fs_info->trans_lock); + while (!list_empty(&fs_info->trans_list)) { + t = list_first_entry(&fs_info->trans_list, + struct btrfs_transaction, list); + if (t->state >= TRANS_STATE_COMMIT_PREP) { + refcount_inc(&t->use_count); + spin_unlock(&fs_info->trans_lock); + btrfs_wait_for_commit(fs_info, t->transid); + btrfs_put_transaction(t); + spin_lock(&fs_info->trans_lock); + continue; + } + if (t == fs_info->running_transaction) { + t->state = TRANS_STATE_COMMIT_DOING; + spin_unlock(&fs_info->trans_lock); + /* + * We wait for 0 num_writers since we don't hold a trans + * handle open currently for this transaction. + */ + wait_event(t->writer_wait, + atomic_read(&t->num_writers) == 0); + } else { + spin_unlock(&fs_info->trans_lock); + } + btrfs_cleanup_one_transaction(t); - btrfs_destroy_delayed_inodes(root); - btrfs_assert_delayed_root_empty(root); + spin_lock(&fs_info->trans_lock); + if (t == fs_info->running_transaction) + fs_info->running_transaction = NULL; + list_del_init(&t->list); + spin_unlock(&fs_info->trans_lock); - btrfs_destroy_all_delalloc_inodes(root->fs_info); + btrfs_put_transaction(t); + 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_all_delalloc_inodes(fs_info); + btrfs_drop_all_logs(fs_info); + btrfs_free_all_qgroup_pertrans(fs_info); + mutex_unlock(&fs_info->transaction_kthread_mutex); - btrfs_destroy_marked_extents(root, &t->dirty_pages, - EXTENT_DIRTY); + return 0; +} - btrfs_destroy_pinned_extent(root, - root->fs_info->pinned_extents); +int btrfs_init_root_free_objectid(struct btrfs_root *root) +{ + BTRFS_PATH_AUTO_FREE(path); + int ret; + struct extent_buffer *l; + struct btrfs_key search_key; + struct btrfs_key found_key; + int slot; - t->state = TRANS_STATE_COMPLETED; - smp_mb(); - if (waitqueue_active(&t->commit_wait)) - wake_up(&t->commit_wait); + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; - atomic_set(&t->use_count, 0); - list_del_init(&t->list); - memset(t, 0, sizeof(*t)); - kmem_cache_free(btrfs_transaction_cachep, t); + search_key.objectid = BTRFS_LAST_FREE_OBJECTID; + search_key.type = -1; + search_key.offset = (u64)-1; + ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); + if (ret < 0) + return ret; + if (unlikely(ret == 0)) { + /* + * Key with offset -1 found, there would have to exist a root + * with such id, but this is out of valid range. + */ + return -EUCLEAN; + } + if (path->slots[0] > 0) { + slot = path->slots[0] - 1; + l = path->nodes[0]; + btrfs_item_key_to_cpu(l, &found_key, slot); + root->free_objectid = max_t(u64, found_key.objectid + 1, + BTRFS_FIRST_FREE_OBJECTID); + } else { + root->free_objectid = BTRFS_FIRST_FREE_OBJECTID; } - mutex_unlock(&root->fs_info->transaction_kthread_mutex); - return 0; } -static struct extent_io_ops btree_extent_io_ops = { - .readpage_end_io_hook = btree_readpage_end_io_hook, - .readpage_io_failed_hook = btree_io_failed_hook, - .submit_bio_hook = btree_submit_bio_hook, - /* note we're sharing with inode.c for the merge bio hook */ - .merge_bio_hook = btrfs_merge_bio_hook, -}; +int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid) +{ + int ret; + mutex_lock(&root->objectid_mutex); + + if (unlikely(root->free_objectid >= BTRFS_LAST_FREE_OBJECTID)) { + btrfs_warn(root->fs_info, + "the objectid of root %llu reaches its highest value", + btrfs_root_id(root)); + ret = -ENOSPC; + goto out; + } + + *objectid = root->free_objectid++; + ret = 0; +out: + mutex_unlock(&root->objectid_mutex); + return ret; +} |