diff options
Diffstat (limited to 'fs/btrfs/disk-io.c')
| -rw-r--r-- | fs/btrfs/disk-io.c | 472 |
1 files changed, 259 insertions, 213 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b0ab41da91d1..663efce22d98 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -17,6 +17,7 @@ #include <linux/semaphore.h> #include <linux/error-injection.h> #include <linux/crc32c.h> +#include <linux/sched/mm.h> #include <asm/unaligned.h> #include "ctree.h" #include "disk-io.h" @@ -259,15 +260,12 @@ void btrfs_csum_final(u32 crc, u8 *result) } /* - * compute the csum for a btree block, and either verify it or write it - * into the csum field of the block. + * Compute the csum of a btree block and store the result to provided buffer. + * + * Returns error if the extent buffer cannot be mapped. */ -static int csum_tree_block(struct btrfs_fs_info *fs_info, - struct extent_buffer *buf, - int verify) +static int csum_tree_block(struct extent_buffer *buf, u8 *result) { - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); - char result[BTRFS_CSUM_SIZE]; unsigned long len; unsigned long cur_len; unsigned long offset = BTRFS_CSUM_SIZE; @@ -279,9 +277,15 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info, len = buf->len - offset; while (len > 0) { + /* + * Note: we don't need to check for the err == 1 case here, as + * with the given combination of 'start = BTRFS_CSUM_SIZE (32)' + * and 'min_len = 32' and the currently implemented mapping + * algorithm we cannot cross a page boundary. + */ err = map_private_extent_buffer(buf, offset, 32, &kaddr, &map_start, &map_len); - if (err) + if (WARN_ON(err)) return err; cur_len = min(len, map_len - (offset - map_start)); crc = btrfs_csum_data(kaddr + offset - map_start, @@ -293,23 +297,6 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info, 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); - btrfs_warn_rl(fs_info, - "%s checksum verify failed on %llu wanted %X found %X level %d", - fs_info->sb->s_id, buf->start, - val, found, btrfs_header_level(buf)); - return -EUCLEAN; - } - } else { - write_extent_buffer(buf, result, 0, csum_size); - } - return 0; } @@ -335,7 +322,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, if (need_lock) { btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + btrfs_set_lock_blocking_read(eb); } lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1, @@ -407,22 +394,21 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, return ret; } -static int verify_level_key(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb, int level, - struct btrfs_key *first_key, u64 parent_transid) +int btrfs_verify_level_key(struct extent_buffer *eb, int level, + struct btrfs_key *first_key, u64 parent_transid) { + struct btrfs_fs_info *fs_info = eb->fs_info; int found_level; struct btrfs_key found_key; int ret; found_level = btrfs_header_level(eb); if (found_level != level) { -#ifdef CONFIG_BTRFS_DEBUG - WARN_ON(1); + WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), + KERN_ERR "BTRFS: tree level check failed\n"); btrfs_err(fs_info, "tree level mismatch detected, bytenr=%llu level expected=%u has=%u", eb->start, level, found_level); -#endif return -EIO; } @@ -443,9 +429,9 @@ static int verify_level_key(struct btrfs_fs_info *fs_info, btrfs_item_key_to_cpu(eb, &found_key, 0); ret = btrfs_comp_cpu_keys(first_key, &found_key); -#ifdef CONFIG_BTRFS_DEBUG if (ret) { - WARN_ON(1); + WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), + KERN_ERR "BTRFS: tree first key check failed\n"); btrfs_err(fs_info, "tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)", eb->start, parent_transid, first_key->objectid, @@ -453,7 +439,6 @@ static int verify_level_key(struct btrfs_fs_info *fs_info, found_key.objectid, found_key.type, found_key.offset); } -#endif return ret; } @@ -465,11 +450,11 @@ static int verify_level_key(struct btrfs_fs_info *fs_info, * @level: expected level, mandatory check * @first_key: expected key of first slot, skip check if NULL */ -static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb, +static int btree_read_extent_buffer_pages(struct extent_buffer *eb, u64 parent_transid, int level, struct btrfs_key *first_key) { + struct btrfs_fs_info *fs_info = eb->fs_info; struct extent_io_tree *io_tree; int failed = 0; int ret; @@ -477,31 +462,21 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, int mirror_num = 0; int failed_mirror = 0; - clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree; while (1) { - ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE, - mirror_num); + clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); + ret = read_extent_buffer_pages(eb, WAIT_COMPLETE, mirror_num); if (!ret) { if (verify_parent_transid(io_tree, eb, parent_transid, 0)) ret = -EIO; - else if (verify_level_key(fs_info, eb, level, - first_key, parent_transid)) + else if (btrfs_verify_level_key(eb, level, + first_key, parent_transid)) ret = -EUCLEAN; else break; } - /* - * 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) || - ret == -EUCLEAN) - break; - num_copies = btrfs_num_copies(fs_info, eb->start, eb->len); if (num_copies == 1) @@ -521,7 +496,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, } if (failed && !ret && failed_mirror) - repair_eb_io_failure(fs_info, eb, failed_mirror); + btrfs_repair_eb_io_failure(eb, failed_mirror); return ret; } @@ -535,7 +510,10 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) { u64 start = page_offset(page); u64 found_start; + u8 result[BTRFS_CSUM_SIZE]; + u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); struct extent_buffer *eb; + int ret; eb = (struct extent_buffer *)page->private; if (page != eb->pages[0]) @@ -551,22 +529,51 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) if (WARN_ON(!PageUptodate(page))) return -EUCLEAN; - ASSERT(memcmp_extent_buffer(eb, fs_info->fsid, + ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid, btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0); - return csum_tree_block(fs_info, eb, 0); + if (csum_tree_block(eb, result)) + return -EINVAL; + + if (btrfs_header_level(eb)) + ret = btrfs_check_node(eb); + else + ret = btrfs_check_leaf_full(eb); + + if (ret < 0) { + btrfs_err(fs_info, + "block=%llu write time tree block corruption detected", + eb->start); + return ret; + } + write_extent_buffer(eb, result, 0, csum_size); + + return 0; } -static int check_tree_block_fsid(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb) +static int check_tree_block_fsid(struct extent_buffer *eb) { + struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; u8 fsid[BTRFS_FSID_SIZE]; int ret = 1; read_extent_buffer(eb, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE); while (fs_devices) { - if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) { + u8 *metadata_uuid; + + /* + * Checking the incompat flag is only valid for the current + * fs. For seed devices it's forbidden to have their uuid + * changed so reading ->fsid in this case is fine + */ + if (fs_devices == fs_info->fs_devices && + btrfs_fs_incompat(fs_info, METADATA_UUID)) + metadata_uuid = fs_devices->metadata_uuid; + else + metadata_uuid = fs_devices->fsid; + + if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE)) { ret = 0; break; } @@ -584,7 +591,9 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, struct extent_buffer *eb; struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; struct btrfs_fs_info *fs_info = root->fs_info; + u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); int ret = 0; + u8 result[BTRFS_CSUM_SIZE]; int reads_done; if (!page->private) @@ -614,7 +623,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, ret = -EIO; goto err; } - if (check_tree_block_fsid(fs_info, eb)) { + if (check_tree_block_fsid(eb)) { btrfs_err_rl(fs_info, "bad fsid on block %llu", eb->start); ret = -EIO; @@ -631,25 +640,44 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb, found_level); - ret = csum_tree_block(fs_info, eb, 1); + ret = csum_tree_block(eb, result); if (ret) goto err; + if (memcmp_extent_buffer(eb, result, 0, csum_size)) { + u32 val; + u32 found = 0; + + memcpy(&found, result, csum_size); + + read_extent_buffer(eb, &val, 0, csum_size); + btrfs_warn_rl(fs_info, + "%s checksum verify failed on %llu wanted %x found %x level %d", + fs_info->sb->s_id, eb->start, + val, found, btrfs_header_level(eb)); + ret = -EUCLEAN; + goto err; + } + /* * If this is a leaf block and it is corrupt, set the corrupt bit so * that we don't try and read the other copies of this block, just * return -EIO. */ - if (found_level == 0 && btrfs_check_leaf_full(fs_info, eb)) { + if (found_level == 0 && btrfs_check_leaf_full(eb)) { set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); ret = -EIO; } - if (found_level > 0 && btrfs_check_node(fs_info, eb)) + if (found_level > 0 && btrfs_check_node(eb)) ret = -EIO; if (!ret) set_extent_buffer_uptodate(eb); + else + btrfs_err(fs_info, + "block=%llu read time tree block corruption detected", + eb->start); err: if (reads_done && test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) @@ -669,19 +697,6 @@ out: return ret; } -static int btree_io_failed_hook(struct page *page, int failed_mirror) -{ - struct extent_buffer *eb; - - eb = (struct extent_buffer *)page->private; - set_bit(EXTENT_BUFFER_READ_ERR, &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(eb, -EIO); - return -EIO; /* we fixed nothing */ -} - static void end_workqueue_bio(struct bio *bio) { struct btrfs_end_io_wq *end_io_wq = bio->bi_private; @@ -760,11 +775,22 @@ static void run_one_async_start(struct btrfs_work *work) async->status = ret; } +/* + * In order to insert checksums into the metadata in large chunks, we wait + * until bio submission time. All the pages in the bio are checksummed and + * sums are attached onto the ordered extent record. + * + * At IO completion time the csums attached on the ordered extent record are + * inserted into the tree. + */ static void run_one_async_done(struct btrfs_work *work) { struct async_submit_bio *async; + struct inode *inode; + blk_status_t ret; async = container_of(work, struct async_submit_bio, work); + inode = async->private_data; /* If an error occurred we just want to clean up the bio and move on */ if (async->status) { @@ -773,7 +799,12 @@ static void run_one_async_done(struct btrfs_work *work) return; } - btrfs_submit_bio_done(async->private_data, async->bio, async->mirror_num); + ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, + async->mirror_num, 1); + if (ret) { + async->bio->bi_status = ret; + bio_endio(async->bio); + } } static void run_one_async_free(struct btrfs_work *work) @@ -819,9 +850,10 @@ static blk_status_t btree_csum_one_bio(struct bio *bio) struct bio_vec *bvec; struct btrfs_root *root; int i, ret = 0; + struct bvec_iter_all iter_all; ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, i) { + bio_for_each_segment_all(bvec, bio, i, iter_all) { root = BTRFS_I(bvec->bv_page->mapping->host)->root; ret = csum_dirty_buffer(root->fs_info, bvec->bv_page); if (ret) @@ -852,11 +884,10 @@ static int check_async_write(struct btrfs_inode *bi) return 1; } -static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio, + int mirror_num, + unsigned long bio_flags) { - struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); int async = check_async_write(BTRFS_I(inode)); blk_status_t ret; @@ -882,8 +913,7 @@ static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio, * checksumming can happen in parallel across all CPUs */ ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0, - bio_offset, private_data, - btree_submit_bio_start); + 0, inode, btree_submit_bio_start); } if (ret) @@ -1002,22 +1032,23 @@ static const struct address_space_operations btree_aops = { void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr) { struct extent_buffer *buf = NULL; - struct inode *btree_inode = fs_info->btree_inode; + int ret; buf = btrfs_find_create_tree_block(fs_info, bytenr); if (IS_ERR(buf)) return; - read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, - buf, WAIT_NONE, 0); - free_extent_buffer(buf); + + ret = read_extent_buffer_pages(buf, WAIT_NONE, 0); + if (ret < 0) + free_extent_buffer_stale(buf); + else + free_extent_buffer(buf); } int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr, int mirror_num, struct extent_buffer **eb) { struct extent_buffer *buf = NULL; - struct inode *btree_inode = fs_info->btree_inode; - struct extent_io_tree *io_tree = &BTRFS_I(btree_inode)->io_tree; int ret; buf = btrfs_find_create_tree_block(fs_info, bytenr); @@ -1026,15 +1057,14 @@ int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr, set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags); - ret = read_extent_buffer_pages(io_tree, buf, WAIT_PAGE_LOCK, - mirror_num); + ret = read_extent_buffer_pages(buf, WAIT_PAGE_LOCK, mirror_num); if (ret) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return ret; } if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return -EIO; } else if (extent_buffer_uptodate(buf)) { *eb = buf; @@ -1053,19 +1083,6 @@ struct extent_buffer *btrfs_find_create_tree_block( return alloc_extent_buffer(fs_info, bytenr); } - -int btrfs_write_tree_block(struct extent_buffer *buf) -{ - return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start, - buf->start + buf->len - 1); -} - -void btrfs_wait_tree_block_writeback(struct extent_buffer *buf) -{ - filemap_fdatawait_range(buf->pages[0]->mapping, - buf->start, buf->start + buf->len - 1); -} - /* * Read tree block at logical address @bytenr and do variant basic but critical * verification. @@ -1085,19 +1102,19 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, if (IS_ERR(buf)) return buf; - ret = btree_read_extent_buffer_pages(fs_info, buf, parent_transid, + ret = btree_read_extent_buffer_pages(buf, parent_transid, level, first_key); if (ret) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return ERR_PTR(ret); } return buf; } -void clean_tree_block(struct btrfs_fs_info *fs_info, - struct extent_buffer *buf) +void btrfs_clean_tree_block(struct extent_buffer *buf) { + struct btrfs_fs_info *fs_info = buf->fs_info; if (btrfs_header_generation(buf) == fs_info->running_transaction->transid) { btrfs_assert_tree_locked(buf); @@ -1107,7 +1124,7 @@ void clean_tree_block(struct btrfs_fs_info *fs_info, -buf->len, fs_info->dirty_metadata_batch); /* ugh, clear_extent_buffer_dirty needs to lock the page */ - btrfs_set_lock_blocking(buf); + btrfs_set_lock_blocking_write(buf); clear_extent_buffer_dirty(buf); } } @@ -1162,6 +1179,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, INIT_LIST_HEAD(&root->delalloc_root); INIT_LIST_HEAD(&root->ordered_extents); INIT_LIST_HEAD(&root->ordered_root); + INIT_LIST_HEAD(&root->reloc_dirty_list); INIT_LIST_HEAD(&root->logged_list[0]); INIT_LIST_HEAD(&root->logged_list[1]); spin_lock_init(&root->inode_lock); @@ -1187,11 +1205,13 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, refcount_set(&root->refs, 1); atomic_set(&root->will_be_snapshotted, 0); atomic_set(&root->snapshot_force_cow, 0); + atomic_set(&root->nr_swapfiles, 0); root->log_transid = 0; root->log_transid_committed = -1; root->last_log_commit = 0; if (!dummy) - extent_io_tree_init(&root->dirty_log_pages, NULL); + extent_io_tree_init(fs_info, &root->dirty_log_pages, + IO_TREE_ROOT_DIRTY_LOG_PAGES, NULL); memset(&root->root_key, 0, sizeof(root->root_key)); memset(&root->root_item, 0, sizeof(root->root_item)); @@ -1204,6 +1224,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, root->anon_dev = 0; spin_lock_init(&root->root_item_lock); + btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks); } static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info, @@ -1237,17 +1258,24 @@ struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info) #endif 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; uuid_le uuid = NULL_UUID_LE; + /* + * We're holding a transaction handle, so use a NOFS memory allocation + * context to avoid deadlock if reclaim happens. + */ + nofs_flag = memalloc_nofs_save(); root = btrfs_alloc_root(fs_info, GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!root) return ERR_PTR(-ENOMEM); @@ -1664,11 +1692,12 @@ static int cleaner_kthread(void *arg) struct btrfs_root *root = arg; struct btrfs_fs_info *fs_info = root->fs_info; int again; - struct btrfs_trans_handle *trans; - 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(fs_info)) goto sleep; @@ -1692,9 +1721,7 @@ static int cleaner_kthread(void *arg) goto sleep; } - mutex_lock(&fs_info->cleaner_delayed_iput_mutex); btrfs_run_delayed_iputs(fs_info); - mutex_unlock(&fs_info->cleaner_delayed_iput_mutex); again = btrfs_clean_one_deleted_snapshot(root); mutex_unlock(&fs_info->cleaner_mutex); @@ -1715,42 +1742,17 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(fs_info); sleep: + clear_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()); - - /* - * Transaction kthread is stopped before us and wakes us up. - * However we might have started a new transaction and COWed some - * tree blocks when deleting unused block groups for example. So - * make sure we commit the transaction we started to have a clean - * shutdown when evicting the btree inode - if it has dirty pages - * when we do the final iput() on it, eviction will trigger a - * writeback for it which will fail with null pointer dereferences - * since work queues and other resources were already released and - * destroyed by the time the iput/eviction/writeback is made. - */ - trans = btrfs_attach_transaction(root); - if (IS_ERR(trans)) { - if (PTR_ERR(trans) != -ENOENT) - btrfs_err(fs_info, - "cleaner transaction attach returned %ld", - PTR_ERR(trans)); - } else { - int ret; - - ret = btrfs_commit_transaction(trans); - if (ret) - btrfs_err(fs_info, - "cleaner open transaction commit returned %d", - ret); } - - return 0; } static int transaction_kthread(void *arg) @@ -2111,7 +2113,7 @@ static void btrfs_init_scrub(struct btrfs_fs_info *fs_info) atomic_set(&fs_info->scrubs_paused, 0); atomic_set(&fs_info->scrub_cancel_req, 0); init_waitqueue_head(&fs_info->scrub_pause_wait); - fs_info->scrub_workers_refcnt = 0; + refcount_set(&fs_info->scrub_workers_refcnt, 0); } static void btrfs_init_balance(struct btrfs_fs_info *fs_info) @@ -2139,8 +2141,9 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info) inode->i_mapping->a_ops = &btree_aops; RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node); - extent_io_tree_init(&BTRFS_I(inode)->io_tree, inode); - BTRFS_I(inode)->io_tree.track_uptodate = 0; + extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree, + IO_TREE_INODE_IO, inode); + BTRFS_I(inode)->io_tree.track_uptodate = false; extent_map_tree_init(&BTRFS_I(inode)->extent_tree); BTRFS_I(inode)->io_tree.ops = &btree_extent_io_ops; @@ -2154,10 +2157,8 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info) static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info) { mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount); - rwlock_init(&fs_info->dev_replace.lock); - atomic_set(&fs_info->dev_replace.blocking_readers, 0); + init_rwsem(&fs_info->dev_replace.rwsem); init_waitqueue_head(&fs_info->dev_replace.replace_wait); - init_waitqueue_head(&fs_info->dev_replace.read_lock_wq); } static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) @@ -2165,7 +2166,6 @@ 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; - fs_info->qgroup_op_tree = RB_ROOT; INIT_LIST_HEAD(&fs_info->dirty_qgroups); fs_info->qgroup_seq = 1; fs_info->qgroup_ulist = NULL; @@ -2478,10 +2478,11 @@ static int validate_super(struct btrfs_fs_info *fs_info, ret = -EINVAL; } - if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) { + 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 fsid: %pU != %pU", - fs_info->fsid, sb->dev_item.fsid); + "dev_item UUID does not match metadata fsid: %pU != %pU", + fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid); ret = -EINVAL; } @@ -2632,11 +2633,17 @@ int open_ctree(struct super_block *sb, goto fail; } - ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); + ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL); if (ret) { err = ret; goto fail_srcu; } + + ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); + if (ret) { + err = ret; + goto fail_dio_bytes; + } fs_info->dirty_metadata_batch = PAGE_SIZE * (1 + ilog2(nr_cpu_ids)); @@ -2669,7 +2676,6 @@ int open_ctree(struct super_block *sb, spin_lock_init(&fs_info->defrag_inodes_lock); spin_lock_init(&fs_info->tree_mod_seq_lock); spin_lock_init(&fs_info->super_lock); - spin_lock_init(&fs_info->qgroup_op_lock); spin_lock_init(&fs_info->buffer_lock); spin_lock_init(&fs_info->unused_bgs_lock); rwlock_init(&fs_info->tree_mod_log_lock); @@ -2677,7 +2683,6 @@ int open_ctree(struct super_block *sb, mutex_init(&fs_info->delete_unused_bgs_mutex); mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); - mutex_init(&fs_info->cleaner_delayed_iput_mutex); seqlock_init(&fs_info->profiles_lock); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); @@ -2692,10 +2697,13 @@ int open_ctree(struct super_block *sb, 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); + 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->defrag_running, 0); - atomic_set(&fs_info->qgroup_op_seq, 0); atomic_set(&fs_info->reada_works_cnt, 0); + atomic_set(&fs_info->nr_delayed_iputs, 0); atomic64_set(&fs_info->tree_mod_seq, 0); fs_info->sb = sb; fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE; @@ -2747,8 +2755,10 @@ int open_ctree(struct super_block *sb, fs_info->block_group_cache_tree = RB_ROOT; fs_info->first_logical_byte = (u64)-1; - extent_io_tree_init(&fs_info->freed_extents[0], NULL); - extent_io_tree_init(&fs_info->freed_extents[1], NULL); + extent_io_tree_init(fs_info, &fs_info->freed_extents[0], + IO_TREE_FS_INFO_FREED_EXTENTS0, NULL); + extent_io_tree_init(fs_info, &fs_info->freed_extents[1], + IO_TREE_FS_INFO_FREED_EXTENTS1, NULL); fs_info->pinned_extents = &fs_info->freed_extents[0]; set_bit(BTRFS_FS_BARRIER, &fs_info->flags); @@ -2773,14 +2783,16 @@ 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_LIST_HEAD(&fs_info->pinned_chunks); + 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->stripesize = 4096; + spin_lock_init(&fs_info->swapfile_pins_lock); + fs_info->swapfile_pins = RB_ROOT; + ret = btrfs_alloc_stripe_hash_table(fs_info); if (ret) { err = ret; @@ -2817,11 +2829,29 @@ int open_ctree(struct super_block *sb, * the whole block of INFO_SIZE */ 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); - memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE); + disk_super = fs_info->super_copy; + + ASSERT(!memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid, + BTRFS_FSID_SIZE)); + + if (btrfs_fs_incompat(fs_info, METADATA_UUID)) { + ASSERT(!memcmp(fs_info->fs_devices->metadata_uuid, + fs_info->super_copy->metadata_uuid, + BTRFS_FSID_SIZE)); + } + + features = btrfs_super_flags(disk_super); + if (features & BTRFS_SUPER_FLAG_CHANGING_FSID_V2) { + features &= ~BTRFS_SUPER_FLAG_CHANGING_FSID_V2; + btrfs_set_super_flags(disk_super, features); + btrfs_info(fs_info, + "found metadata UUID change in progress flag, clearing"); + } + + memcpy(fs_info->super_for_commit, fs_info->super_copy, + sizeof(*fs_info->super_for_commit)); ret = btrfs_validate_mount_super(fs_info); if (ret) { @@ -2830,7 +2860,6 @@ int open_ctree(struct super_block *sb, goto fail_alloc; } - disk_super = fs_info->super_copy; if (!btrfs_super_root(disk_super)) goto fail_alloc; @@ -2936,13 +2965,13 @@ int open_ctree(struct super_block *sb, sb->s_bdi->congested_fn = btrfs_congested_fn; sb->s_bdi->congested_data = fs_info; sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK; - sb->s_bdi->ra_pages = VM_MAX_READAHEAD * SZ_1K / PAGE_SIZE; + sb->s_bdi->ra_pages = VM_READAHEAD_PAGES; sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super); sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE); sb->s_blocksize = sectorsize; sb->s_blocksize_bits = blksize_bits(sectorsize); - memcpy(&sb->s_uuid, fs_info->fsid, BTRFS_FSID_SIZE); + memcpy(&sb->s_uuid, fs_info->fs_devices->fsid, BTRFS_FSID_SIZE); mutex_lock(&fs_info->chunk_mutex); ret = btrfs_read_sys_array(fs_info); @@ -3091,7 +3120,7 @@ retry_root_backup: if (!sb_rdonly(sb) && !btrfs_check_rw_degradable(fs_info, NULL)) { btrfs_warn(fs_info, - "writeable mount is not allowed due to too many missing devices"); + "writable mount is not allowed due to too many missing devices"); goto fail_sysfs; } @@ -3313,6 +3342,8 @@ fail_delalloc_bytes: percpu_counter_destroy(&fs_info->delalloc_bytes); fail_dirty_metadata_bytes: percpu_counter_destroy(&fs_info->dirty_metadata_bytes); +fail_dio_bytes: + percpu_counter_destroy(&fs_info->dio_bytes); fail_srcu: cleanup_srcu_struct(&fs_info->subvol_srcu); fail: @@ -3760,7 +3791,8 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) 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_FSID_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); @@ -3931,6 +3963,13 @@ void close_ctree(struct btrfs_fs_info *fs_info) int ret; set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); + /* + * We don't want the cleaner to start new transactions, add more delayed + * iputs, etc. while we're closing. We can't use kthread_stop() yet + * because that frees the task_struct, and the transaction kthread might + * still try to wake up the cleaner. + */ + kthread_park(fs_info->cleaner_kthread); /* wait for the qgroup rescan worker to stop */ btrfs_qgroup_wait_for_completion(fs_info, false); @@ -3958,9 +3997,8 @@ void close_ctree(struct btrfs_fs_info *fs_info) if (!sb_rdonly(fs_info->sb)) { /* - * If the cleaner thread is stopped and there are - * block groups queued for removal, the deletion will be - * skipped when we quit the cleaner thread. + * The cleaner kthread is stopped, so do one final pass over + * unused block groups. */ btrfs_delete_unused_bgs(fs_info); @@ -3987,6 +4025,10 @@ void close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_sum(&fs_info->delalloc_bytes)); } + if (percpu_counter_sum(&fs_info->dio_bytes)) + btrfs_info(fs_info, "at unmount dio bytes count %lld", + percpu_counter_sum(&fs_info->dio_bytes)); + btrfs_sysfs_remove_mounted(fs_info); btrfs_sysfs_remove_fsid(fs_info->fs_devices); @@ -4013,25 +4055,17 @@ void close_ctree(struct btrfs_fs_info *fs_info) btrfsic_unmount(fs_info->fs_devices); #endif - btrfs_close_devices(fs_info->fs_devices); btrfs_mapping_tree_free(&fs_info->mapping_tree); + btrfs_close_devices(fs_info->fs_devices); percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); + percpu_counter_destroy(&fs_info->dio_bytes); percpu_counter_destroy(&fs_info->dev_replace.bio_counter); cleanup_srcu_struct(&fs_info->subvol_srcu); btrfs_free_stripe_hash_table(fs_info); btrfs_free_ref_cache(fs_info); - - while (!list_empty(&fs_info->pinned_chunks)) { - struct extent_map *em; - - em = list_first_entry(&fs_info->pinned_chunks, - struct extent_map, list); - list_del_init(&em->list); - free_extent_map(em); - } } int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, @@ -4061,7 +4095,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *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 umapped buffers as dirty + * 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))) @@ -4085,7 +4119,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) * So here we should only check item pointers, not item data. */ if (btrfs_header_level(buf) == 0 && - btrfs_check_leaf_relaxed(fs_info, buf)) { + btrfs_check_leaf_relaxed(buf)) { btrfs_print_leaf(buf); ASSERT(0); } @@ -4128,10 +4162,7 @@ void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info) int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level, struct btrfs_key *first_key) { - struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root; - struct btrfs_fs_info *fs_info = root->fs_info; - - return btree_read_extent_buffer_pages(fs_info, buf, parent_transid, + return btree_read_extent_buffer_pages(buf, parent_transid, level, first_key); } @@ -4185,6 +4216,14 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) spin_lock(&fs_info->ordered_root_lock); } spin_unlock(&fs_info->ordered_root_lock); + + /* + * We need this here because if we've been flipped read-only we won't + * get sync() from the umount, so we need to make sure any ordered + * extents that haven't had their dirty pages IO start writeout yet + * actually get run and error out properly. + */ + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); } static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, @@ -4211,16 +4250,9 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, head = rb_entry(node, struct btrfs_delayed_ref_head, href_node); - if (!mutex_trylock(&head->mutex)) { - refcount_inc(&head->refs); - spin_unlock(&delayed_refs->lock); - - mutex_lock(&head->mutex); - mutex_unlock(&head->mutex); - btrfs_put_delayed_ref_head(head); - spin_lock(&delayed_refs->lock); + if (btrfs_delayed_ref_lock(delayed_refs, head)) continue; - } + spin_lock(&head->lock); while ((n = rb_first_cached(&head->ref_tree)) != NULL) { ref = rb_entry(n, struct btrfs_delayed_ref_node, @@ -4236,12 +4268,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, if (head->must_insert_reserved) pin_bytes = true; btrfs_free_delayed_extent_op(head->extent_op); - delayed_refs->num_heads--; - if (head->processing == 0) - delayed_refs->num_heads_ready--; - atomic_dec(&delayed_refs->num_entries); - rb_erase_cached(&head->href_node, &delayed_refs->href_root); - RB_CLEAR_NODE(&head->href_node); + btrfs_delete_ref_head(delayed_refs, head); spin_unlock(&head->lock); spin_unlock(&delayed_refs->lock); mutex_unlock(&head->mutex); @@ -4249,6 +4276,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, if (pin_bytes) btrfs_pin_extent(fs_info, head->bytenr, head->num_bytes, 1); + btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); btrfs_put_delayed_ref_head(head); cond_resched(); spin_lock(&delayed_refs->lock); @@ -4359,13 +4387,26 @@ static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, unpin = pinned_extents; again: while (1) { + struct extent_state *cached_state = NULL; + + /* + * The btrfs_finish_extent_commit() may get the same range as + * ours between find_first_extent_bit and clear_extent_dirty. + * Hence, hold the unused_bg_unpin_mutex to avoid double unpin + * the same extent range. + */ + mutex_lock(&fs_info->unused_bg_unpin_mutex); ret = find_first_extent_bit(unpin, 0, &start, &end, - EXTENT_DIRTY, NULL); - if (ret) + EXTENT_DIRTY, &cached_state); + if (ret) { + mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; + } - clear_extent_dirty(unpin, start, end); + clear_extent_dirty(unpin, start, end, &cached_state); + free_extent_state(cached_state); btrfs_error_unpin_extent_range(fs_info, start, end); + mutex_unlock(&fs_info->unused_bg_unpin_mutex); cond_resched(); } @@ -4420,6 +4461,7 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, spin_unlock(&cur_trans->dirty_bgs_lock); btrfs_put_block_group(cache); + btrfs_delayed_refs_rsv_release(fs_info, 1); spin_lock(&cur_trans->dirty_bgs_lock); } spin_unlock(&cur_trans->dirty_bgs_lock); @@ -4444,10 +4486,17 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, struct btrfs_fs_info *fs_info) { + struct btrfs_device *dev, *tmp; + btrfs_cleanup_dirty_bgs(cur_trans, fs_info); ASSERT(list_empty(&cur_trans->dirty_bgs)); ASSERT(list_empty(&cur_trans->io_bgs)); + list_for_each_entry_safe(dev, tmp, &cur_trans->dev_update_list, + post_commit_list) { + list_del_init(&dev->post_commit_list); + } + btrfs_destroy_delayed_refs(cur_trans, fs_info); cur_trans->state = TRANS_STATE_COMMIT_START; @@ -4525,7 +4574,4 @@ static const struct extent_io_ops btree_extent_io_ops = { /* mandatory callbacks */ .submit_bio_hook = btree_submit_bio_hook, .readpage_end_io_hook = btree_readpage_end_io_hook, - .readpage_io_failed_hook = btree_io_failed_hook, - - /* optional callbacks */ }; |