--- zzzz-none-000/linux-3.10.107/fs/btrfs/disk-io.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/fs/btrfs/disk-io.c 2021-02-04 17:41:59.000000000 +0000 @@ -26,20 +26,19 @@ #include #include #include -#include #include #include #include #include +#include #include -#include "compat.h" #include "ctree.h" #include "disk-io.h" +#include "hash.h" #include "transaction.h" #include "btrfs_inode.h" #include "volumes.h" #include "print-tree.h" -#include "async-thread.h" #include "locking.h" #include "tree-log.h" #include "free-space-cache.h" @@ -48,22 +47,21 @@ #include "rcu-string.h" #include "dev-replace.h" #include "raid56.h" +#include "sysfs.h" +#include "qgroup.h" #ifdef CONFIG_X86 #include #endif -static struct extent_io_ops btree_extent_io_ops; +static const 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, @@ -74,21 +72,41 @@ 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 + * btrfs_end_io_wq structs are used to do processing in task context when an IO + * is complete. This is used during reads to verify checksums, and it is used * by writes to insert metadata for new file extents after IO is complete. */ -struct end_io_wq { +struct btrfs_end_io_wq { struct bio *bio; bio_end_io_t *end_io; void *private; struct btrfs_fs_info *info; int error; - int metadata; + enum btrfs_wq_endio_type metadata; struct list_head list; struct btrfs_work work; }; +static struct kmem_cache *btrfs_end_io_wq_cache; + +int __init btrfs_end_io_wq_init(void) +{ + btrfs_end_io_wq_cache = kmem_cache_create("btrfs_end_io_wq", + sizeof(struct btrfs_end_io_wq), + 0, + SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, + NULL); + if (!btrfs_end_io_wq_cache) + return -ENOMEM; + return 0; +} + +void btrfs_end_io_wq_exit(void) +{ + if (btrfs_end_io_wq_cache) + kmem_cache_destroy(btrfs_end_io_wq_cache); +} + /* * async submit bios are used to offload expensive checksumming * onto the worker threads. They checksum file and metadata bios @@ -156,6 +174,7 @@ { .id = BTRFS_TREE_LOG_OBJECTID, .name_stem = "log" }, { .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" }, { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" }, + { .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" }, { .id = 0, .name_stem = "tree" }, }; @@ -243,7 +262,7 @@ u32 btrfs_csum_data(char *data, u32 seed, size_t len) { - return crc32c(seed, data, len); + return btrfs_crc32c(seed, data, len); } void btrfs_csum_final(u32 crc, char *result) @@ -255,10 +274,11 @@ * 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, +static int csum_tree_block(struct btrfs_fs_info *fs_info, + struct extent_buffer *buf, int verify) { - u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy); + u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); char *result = NULL; unsigned long len; unsigned long cur_len; @@ -283,7 +303,7 @@ offset += cur_len; } if (csum_size > sizeof(inline_result)) { - result = kzalloc(csum_size * sizeof(char), GFP_NOFS); + result = kzalloc(csum_size, GFP_NOFS); if (!result) return 1; } else { @@ -299,12 +319,11 @@ 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)); + 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)); if (result != (char *)&inline_result) kfree(result); return 1; @@ -329,6 +348,7 @@ { struct extent_state *cached_state = NULL; int ret; + bool need_lock = (current->journal_info == BTRFS_SEND_TRANS_STUB); if (!parent_transid || btrfs_header_generation(eb) == parent_transid) return 0; @@ -336,6 +356,11 @@ if (atomic) return -EAGAIN; + if (need_lock) { + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + } + lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1, 0, &cached_state); if (extent_buffer_uptodate(eb) && @@ -343,16 +368,27 @@ ret = 0; goto out; } - 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)); + btrfs_err_rl(eb->fs_info, + "parent transid verify failed on %llu wanted %llu found %llu", + eb->start, + parent_transid, btrfs_header_generation(eb)); ret = 1; - clear_extent_buffer_uptodate(eb); + + /* + * Things reading via commit roots that don't have normal protection, + * like send, can have a really old block in cache that may point at a + * block that has been free'd and re-allocated. So don't clear uptodate + * if we find an eb that is under IO (dirty/writeback) because we could + * end up reading in the stale data and then writing it back out and + * making everybody very sad. + */ + if (!extent_buffer_under_io(eb)) + clear_extent_buffer_uptodate(eb); out: unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1, &cached_state, GFP_NOFS); + if (need_lock) + btrfs_tree_read_unlock_blocking(eb); return ret; } @@ -383,15 +419,10 @@ if (memcmp(raw_disk_sb, result, csum_size)) ret = 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; - } } if (csum_type >= ARRAY_SIZE(btrfs_csum_sizes)) { - printk(KERN_ERR "btrfs: unsupported checksum algorithm %u\n", + printk(KERN_ERR "BTRFS: unsupported checksum algorithm %u\n", csum_type); ret = 1; } @@ -465,40 +496,30 @@ * we only fill in the checksum field in the first page of a multi-page block */ -static int csum_dirty_buffer(struct btrfs_root *root, struct page *page) +static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) { - struct extent_io_tree *tree; u64 start = page_offset(page); u64 found_start; struct extent_buffer *eb; - tree = &BTRFS_I(page->mapping->host)->io_tree; - 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 (WARN_ON(found_start != start || !PageUptodate(page))) return 0; - } - csum_tree_block(root, eb, 0); + csum_tree_block(fs_info, eb, 0); return 0; } -static int check_tree_block_fsid(struct btrfs_root *root, +static int check_tree_block_fsid(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) { - struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; u8 fsid[BTRFS_UUID_SIZE]; int ret = 1; - read_extent_buffer(eb, fsid, (unsigned long)btrfs_header_fsid(eb), - BTRFS_FSID_SIZE); + read_extent_buffer(eb, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE); while (fs_devices) { if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) { ret = 0; @@ -510,10 +531,9 @@ } #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) + btrfs_crit(root->fs_info, "corrupt leaf, %s: block=%llu," \ + "root=%llu, slot=%d", reason, \ + btrfs_header_bytenr(eb), root->objectid, slot) static noinline int check_leaf(struct btrfs_root *root, struct extent_buffer *leaf) @@ -576,10 +596,10 @@ return 0; } -static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end, - struct extent_state *state, int mirror) +static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, + u64 phy_offset, struct page *page, + u64 start, u64 end, int mirror) { - struct extent_io_tree *tree; u64 found_start; int found_level; struct extent_buffer *eb; @@ -590,7 +610,6 @@ 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 @@ -603,29 +622,27 @@ goto err; eb->read_mirror = mirror; - if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) { + if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { ret = -EIO; goto err; } 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); + btrfs_err_rl(eb->fs_info, "bad tree block start %llu %llu", + found_start, eb->start); ret = -EIO; goto err; } - if (check_tree_block_fsid(root, eb)) { - printk_ratelimited(KERN_INFO "btrfs bad fsid on block %llu\n", - (unsigned long long)eb->start); + if (check_tree_block_fsid(root->fs_info, eb)) { + btrfs_err_rl(eb->fs_info, "bad fsid on block %llu", + eb->start); ret = -EIO; goto err; } found_level = btrfs_header_level(eb); if (found_level >= BTRFS_MAX_LEVEL) { - btrfs_info(root->fs_info, "bad tree block level %d\n", + btrfs_err(root->fs_info, "bad tree block level %d", (int)btrfs_header_level(eb)); ret = -EIO; goto err; @@ -634,7 +651,7 @@ btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb, found_level); - ret = csum_tree_block(root, eb, 1); + ret = csum_tree_block(root->fs_info, eb, 1); if (ret) { ret = -EIO; goto err; @@ -677,7 +694,7 @@ struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; eb = (struct extent_buffer *)page->private; - set_bit(EXTENT_BUFFER_IOERR, &eb->bflags); + 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)) @@ -685,55 +702,57 @@ return -EIO; /* we fixed nothing */ } -static void end_workqueue_bio(struct bio *bio, int err) +static void end_workqueue_bio(struct bio *bio) { - struct end_io_wq *end_io_wq = bio->bi_private; + struct btrfs_end_io_wq *end_io_wq = bio->bi_private; struct btrfs_fs_info *fs_info; + struct btrfs_workqueue *wq; + btrfs_work_func_t func; 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; + end_io_wq->error = bio->bi_error; 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); - else - btrfs_queue_worker(&fs_info->endio_write_workers, - &end_io_wq->work); + if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) { + wq = fs_info->endio_meta_write_workers; + func = btrfs_endio_meta_write_helper; + } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) { + wq = fs_info->endio_freespace_worker; + func = btrfs_freespace_write_helper; + } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) { + wq = fs_info->endio_raid56_workers; + func = btrfs_endio_raid56_helper; + } else { + wq = fs_info->endio_write_workers; + func = btrfs_endio_write_helper; + } } 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); + if (unlikely(end_io_wq->metadata == + BTRFS_WQ_ENDIO_DIO_REPAIR)) { + wq = fs_info->endio_repair_workers; + func = btrfs_endio_repair_helper; + } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) { + wq = fs_info->endio_raid56_workers; + func = btrfs_endio_raid56_helper; + } else if (end_io_wq->metadata) { + wq = fs_info->endio_meta_workers; + func = btrfs_endio_meta_helper; + } else { + wq = fs_info->endio_workers; + func = btrfs_endio_helper; + } } + + btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL); + btrfs_queue_work(wq, &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) + enum btrfs_wq_endio_type metadata) { - struct end_io_wq *end_io_wq; - end_io_wq = kmalloc(sizeof(*end_io_wq), GFP_NOFS); + struct btrfs_end_io_wq *end_io_wq; + + end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS); if (!end_io_wq) return -ENOMEM; @@ -752,7 +771,7 @@ unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info) { unsigned long limit = min_t(unsigned long, - info->workers.max_workers, + info->thread_pool_size, info->fs_devices->open_devices); return 256 * limit; } @@ -782,13 +801,17 @@ limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; + /* + * atomic_dec_return implies a barrier for waitqueue_active + */ 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); + async->bio->bi_error = async->error; + bio_endio(async->bio); return; } @@ -825,11 +848,9 @@ 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; + btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start, + run_one_async_done, run_one_async_free); - async->work.flags = 0; async->bio_flags = bio_flags; async->bio_offset = bio_offset; @@ -838,9 +859,9 @@ atomic_inc(&fs_info->nr_async_submits); if (rw & REQ_SYNC) - btrfs_set_work_high_prio(&async->work); + btrfs_set_work_high_priority(&async->work); - btrfs_queue_worker(&fs_info->workers, &async->work); + btrfs_queue_work(fs_info->workers, &async->work); while (atomic_read(&fs_info->async_submit_draining) && atomic_read(&fs_info->nr_async_submits)) { @@ -853,20 +874,17 @@ static int btree_csum_one_bio(struct bio *bio) { - struct bio_vec *bvec = bio->bi_io_vec; - int bio_index = 0; + struct bio_vec *bvec; struct btrfs_root *root; - int ret = 0; + int i, ret = 0; - WARN_ON(bio->bi_vcnt <= 0); - while (bio_index < bio->bi_vcnt) { + bio_for_each_segment_all(bvec, bio, i) { root = BTRFS_I(bvec->bv_page->mapping->host)->root; - ret = csum_dirty_buffer(root, bvec->bv_page); + ret = csum_dirty_buffer(root->fs_info, bvec->bv_page); if (ret) break; - bio_index++; - bvec++; } + return ret; } @@ -893,8 +911,10 @@ * 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); + if (ret) { + bio->bi_error = ret; + bio_endio(bio); + } return ret; } @@ -922,7 +942,7 @@ * can happen in the async kernel threads */ ret = btrfs_bio_wq_end_io(BTRFS_I(inode)->root->fs_info, - bio, 1); + bio, BTRFS_WQ_ENDIO_METADATA); if (ret) goto out_w_error; ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, @@ -945,10 +965,13 @@ __btree_submit_bio_done); } - if (ret) { + if (ret) + goto out_w_error; + return 0; + out_w_error: - bio_endio(bio, ret); - } + bio->bi_error = ret; + bio_endio(bio); return ret; } @@ -978,11 +1001,9 @@ 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) { if (wbc->for_kupdate) @@ -1013,15 +1034,17 @@ return try_release_extent_buffer(page); } -static void btree_invalidatepage(struct page *page, unsigned long offset) +static void btree_invalidatepage(struct page *page, unsigned int offset, + unsigned int 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)); + btrfs_warn(BTRFS_I(page->mapping->host)->root->fs_info, + "page private not zero on page %llu", + (unsigned long long)page_offset(page)); ClearPagePrivate(page); set_page_private(page, 0); page_cache_release(page); @@ -1054,23 +1077,20 @@ .set_page_dirty = btree_set_page_dirty, }; -int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize, - u64 parent_transid) +void readahead_tree_block(struct btrfs_root *root, u64 bytenr) { 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); + buf = btrfs_find_create_tree_block(root, bytenr); if (!buf) - return 0; + return; read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, buf, 0, WAIT_NONE, btree_get_extent, 0); free_extent_buffer(buf); - return ret; } -int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize, +int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, int mirror_num, struct extent_buffer **eb) { struct extent_buffer *buf = NULL; @@ -1078,7 +1098,7 @@ struct extent_io_tree *io_tree = &BTRFS_I(btree_inode)->io_tree; int ret; - buf = btrfs_find_create_tree_block(root, bytenr, blocksize); + buf = btrfs_find_create_tree_block(root, bytenr); if (!buf) return 0; @@ -1102,25 +1122,18 @@ return 0; } -struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root, - u64 bytenr, u32 blocksize) +struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, + u64 bytenr) { - 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; + return find_extent_buffer(fs_info, bytenr); } struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root, - u64 bytenr, u32 blocksize) + u64 bytenr) { - 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; + if (btrfs_test_is_dummy_root(root)) + return alloc_test_extent_buffer(root->fs_info, bytenr); + return alloc_extent_buffer(root->fs_info, bytenr); } @@ -1137,25 +1150,28 @@ } struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr, - u32 blocksize, u64 parent_transid) + u64 parent_transid) { struct extent_buffer *buf = NULL; int ret; - buf = btrfs_find_create_tree_block(root, bytenr, blocksize); + buf = btrfs_find_create_tree_block(root, bytenr); if (!buf) - return NULL; + return ERR_PTR(-ENOMEM); ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid); + if (ret) { + free_extent_buffer(buf); + return ERR_PTR(ret); + } return buf; } -void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, +void clean_tree_block(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, struct extent_buffer *buf) { - struct btrfs_fs_info *fs_info = root->fs_info; - if (btrfs_header_generation(buf) == fs_info->running_transaction->transid) { btrfs_assert_tree_locked(buf); @@ -1171,26 +1187,49 @@ } } -static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, - u32 stripesize, struct btrfs_root *root, - struct btrfs_fs_info *fs_info, +static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void) +{ + struct btrfs_subvolume_writers *writers; + int ret; + + writers = kmalloc(sizeof(*writers), GFP_NOFS); + if (!writers) + return ERR_PTR(-ENOMEM); + + ret = percpu_counter_init(&writers->counter, 0, GFP_KERNEL); + if (ret < 0) { + kfree(writers); + return ERR_PTR(ret); + } + + init_waitqueue_head(&writers->wait); + return writers; +} + +static void +btrfs_free_subvolume_writers(struct btrfs_subvolume_writers *writers) +{ + percpu_counter_destroy(&writers->counter); + kfree(writers); +} + +static void __setup_root(u32 nodesize, 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->state = 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); @@ -1199,74 +1238,56 @@ INIT_LIST_HEAD(&root->dirty_list); INIT_LIST_HEAD(&root->root_list); + INIT_LIST_HEAD(&root->delalloc_inodes); + 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); + 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]); 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->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); + atomic_set(&root->will_be_snapshoted, 0); + atomic_set(&root->qgroup_meta_rsv, 0); root->log_transid = 0; + root->log_transid_committed = -1; root->last_log_commit = 0; - extent_io_tree_init(&root->dirty_log_pages, - fs_info->btree_inode->i_mapping); + if (fs_info) + 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; + if (fs_info) + root->defrag_trans_start = fs_info->generation; + else + root->defrag_trans_start = 0; root->root_key.objectid = objectid; root->anon_dev = 0; spin_lock_init(&root->root_item_lock); } -static int __must_check find_and_setup_root(struct btrfs_root *tree_root, - struct btrfs_fs_info *fs_info, - u64 objectid, - struct btrfs_root *root) -{ - int ret; - u32 blocksize; - u64 generation; - - __setup_root(tree_root->nodesize, tree_root->leafsize, - tree_root->sectorsize, tree_root->stripesize, - root, fs_info, objectid); - ret = btrfs_find_last_root(tree_root, objectid, - &root->root_item, &root->root_key); - if (ret > 0) - return -ENOENT; - else if (ret < 0) - return ret; - - generation = btrfs_root_generation(&root->root_item); - blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item)); - root->commit_root = NULL; - root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item), - blocksize, generation); - if (!root->node || !btrfs_buffer_uptodate(root->node, generation, 0)) { - free_extent_buffer(root->node); - root->node = NULL; - return -EIO; - } - root->commit_root = btrfs_root_node(root); - return 0; -} - static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info) { struct btrfs_root *root = kzalloc(sizeof(*root), GFP_NOFS); @@ -1275,6 +1296,23 @@ return root; } +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS +/* Should only be used by the testing infrastructure */ +struct btrfs_root *btrfs_alloc_dummy_root(void) +{ + struct btrfs_root *root; + + root = btrfs_alloc_root(NULL); + if (!root) + return ERR_PTR(-ENOMEM); + __setup_root(4096, 4096, 4096, root, NULL, 1); + set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state); + root->alloc_bytenr = 0; + + return root; +} +#endif + struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 objectid) @@ -1284,29 +1322,25 @@ struct btrfs_root *root; struct btrfs_key key; int ret = 0; - u64 bytenr; uuid_le uuid; root = btrfs_alloc_root(fs_info); if (!root) return ERR_PTR(-ENOMEM); - __setup_root(tree_root->nodesize, tree_root->leafsize, - tree_root->sectorsize, tree_root->stripesize, - root, fs_info, objectid); + __setup_root(tree_root->nodesize, 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); 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); @@ -1314,17 +1348,15 @@ btrfs_set_header_owner(leaf, objectid); root->node = leaf; - write_extent_buffer(leaf, fs_info->fsid, - (unsigned long)btrfs_header_fsid(leaf), + write_extent_buffer(leaf, fs_info->fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE); write_extent_buffer(leaf, fs_info->chunk_tree_uuid, - (unsigned long)btrfs_header_chunk_tree_uuid(leaf), + btrfs_header_chunk_tree_uuid(leaf), BTRFS_UUID_SIZE); btrfs_mark_buffer_dirty(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; @@ -1353,6 +1385,7 @@ fail: if (leaf) { btrfs_tree_unlock(leaf); + free_extent_buffer(root->commit_root); free_extent_buffer(leaf); } kfree(root); @@ -1371,24 +1404,25 @@ 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); + __setup_root(tree_root->nodesize, 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; + /* + * DON'T set REF_COWS for log trees + * * log trees do not get reference counted because they go away * before a real commit is actually done. They do store pointers * to file data extents, and those reference counts still get * updated (along with back refs to the log tree). */ - root->ref_cows = 0; - leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0, - BTRFS_TREE_LOG_OBJECTID, NULL, - 0, 0, 0); + leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID, + NULL, 0, 0, 0); if (IS_ERR(leaf)) { kfree(root); return ERR_CAST(leaf); @@ -1402,8 +1436,7 @@ root->node = leaf; write_extent_buffer(root->node, root->fs_info->fsid, - (unsigned long)btrfs_header_fsid(root->node), - BTRFS_FSID_SIZE); + btrfs_header_fsid(), BTRFS_FSID_SIZE); btrfs_mark_buffer_dirty(root->node); btrfs_tree_unlock(root->node); return root; @@ -1436,96 +1469,184 @@ log_root->root_key.offset = root->root_key.objectid; 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, root->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->log_transid_committed = -1; root->last_log_commit = 0; return 0; } -struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, - struct btrfs_key *location) +static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, + struct btrfs_key *key) { struct btrfs_root *root; struct btrfs_fs_info *fs_info = tree_root->fs_info; struct btrfs_path *path; - struct extent_buffer *l; u64 generation; - u32 blocksize; - int ret = 0; - int slot; + int ret; - root = btrfs_alloc_root(fs_info); - if (!root) + path = btrfs_alloc_path(); + if (!path) return ERR_PTR(-ENOMEM); - if (location->offset == (u64)-1) { - ret = find_and_setup_root(tree_root, fs_info, - location->objectid, root); - if (ret) { - kfree(root); - return ERR_PTR(ret); - } - goto out; + + 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, location->objectid); + __setup_root(tree_root->nodesize, tree_root->sectorsize, + tree_root->stripesize, root, fs_info, key->objectid); - path = btrfs_alloc_path(); - if (!path) { - kfree(root); - return ERR_PTR(-ENOMEM); - } - ret = btrfs_search_slot(NULL, tree_root, location, path, 0, 0); - if (ret == 0) { - l = path->nodes[0]; - slot = path->slots[0]; - btrfs_read_root_item(l, slot, &root->root_item); - memcpy(&root->root_key, location, sizeof(*location)); - } - btrfs_free_path(path); + ret = btrfs_find_root(tree_root, key, path, + &root->root_item, &root->root_key); if (ret) { - kfree(root); if (ret > 0) ret = -ENOENT; - return ERR_PTR(ret); + goto find_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 || !extent_buffer_uptodate(root->node)) { - ret = (!root->node) ? -ENOMEM : -EIO; - + generation); + if (IS_ERR(root->node)) { + ret = PTR_ERR(root->node); + goto find_fail; + } else if (!btrfs_buffer_uptodate(root->node, generation, 0)) { + ret = -EIO; free_extent_buffer(root->node); - kfree(root); - return ERR_PTR(ret); + goto find_fail; } - root->commit_root = btrfs_root_node(root); out: - if (location->objectid != BTRFS_TREE_LOG_OBJECTID) { - root->ref_cows = 1; + btrfs_free_path(path); + return root; + +find_fail: + kfree(root); +alloc_fail: + root = ERR_PTR(ret); + goto out; +} + +struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root, + struct btrfs_key *location) +{ + struct btrfs_root *root; + + root = btrfs_read_tree_root(tree_root, location); + if (IS_ERR(root)) + return root; + + if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { + set_bit(BTRFS_ROOT_REF_COWS, &root->state); btrfs_check_and_init_root_item(&root->root_item); } return root; } -struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info, - struct btrfs_key *location) +int btrfs_init_fs_root(struct btrfs_root *root) +{ + int ret; + struct btrfs_subvolume_writers *writers; + + 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; + } + + writers = btrfs_alloc_subvolume_writers(); + if (IS_ERR(writers)) { + ret = PTR_ERR(writers); + goto fail; + } + root->subv_writers = writers; + + btrfs_init_free_ino_ctl(root); + spin_lock_init(&root->ino_cache_lock); + init_waitqueue_head(&root->ino_cache_wait); + + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto free_writers; + + mutex_lock(&root->objectid_mutex); + ret = btrfs_find_highest_objectid(root, + &root->highest_objectid); + if (ret) { + mutex_unlock(&root->objectid_mutex); + goto free_root_dev; + } + + ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + + mutex_unlock(&root->objectid_mutex); + + return 0; + +free_root_dev: + free_anon_bdev(root->anon_dev); +free_writers: + btrfs_free_subvolume_writers(root->subv_writers); +fail: + kfree(root->free_ino_ctl); + kfree(root->free_ino_pinned); + return ret; +} + +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); + spin_unlock(&fs_info->fs_roots_radix_lock); + return root; +} + +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); + 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, + root); + if (ret == 0) + set_bit(BTRFS_ROOT_IN_RADIX, &root->state); + spin_unlock(&fs_info->fs_roots_radix_lock); + radix_tree_preload_end(); + + return ret; +} + +struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, + struct btrfs_key *location, + bool check_ref) { struct btrfs_root *root; + struct btrfs_path *path; + struct btrfs_key key; int ret; if (location->objectid == BTRFS_ROOT_TREE_OBJECTID) @@ -1541,59 +1662,47 @@ if (location->objectid == BTRFS_QUOTA_TREE_OBJECTID) return fs_info->quota_root ? fs_info->quota_root : ERR_PTR(-ENOENT); + if (location->objectid == BTRFS_UUID_TREE_OBJECTID) + return fs_info->uuid_root ? fs_info->uuid_root : + ERR_PTR(-ENOENT); again: - spin_lock(&fs_info->fs_roots_radix_lock); - root = radix_tree_lookup(&fs_info->fs_roots_radix, - (unsigned long)location->objectid); - spin_unlock(&fs_info->fs_roots_radix_lock); - if (root) + root = btrfs_lookup_fs_root(fs_info, location->objectid); + if (root) { + if (check_ref && btrfs_root_refs(&root->root_item) == 0) + return ERR_PTR(-ENOENT); return root; + } - root = btrfs_read_fs_root_no_radix(fs_info->tree_root, location); + root = btrfs_read_fs_root(fs_info->tree_root, location); if (IS_ERR(root)) return root; - 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; + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { + ret = -ENOENT; goto fail; } - btrfs_init_free_ino_ctl(root); - mutex_init(&root->fs_commit_mutex); - spin_lock_init(&root->cache_lock); - init_waitqueue_head(&root->cache_wait); - - ret = get_anon_bdev(&root->anon_dev); + ret = btrfs_init_fs_root(root); if (ret) goto fail; - if (btrfs_root_refs(&root->root_item) == 0) { - ret = -ENOENT; + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; goto fail; } + key.objectid = BTRFS_ORPHAN_OBJECTID; + key.type = BTRFS_ORPHAN_ITEM_KEY; + key.offset = location->objectid; - ret = btrfs_find_orphan_item(fs_info->tree_root, location->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 = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); - if (ret) - goto fail; - - spin_lock(&fs_info->fs_roots_radix_lock); - ret = radix_tree_insert(&fs_info->fs_roots_radix, - (unsigned long)root->root_key.objectid, - root); - if (ret == 0) - root->in_radix = 1; - - spin_unlock(&fs_info->fs_roots_radix_lock); - radix_tree_preload_end(); + ret = btrfs_insert_fs_root(fs_info, root); if (ret) { if (ret == -EEXIST) { free_fs_root(root); @@ -1601,10 +1710,6 @@ } goto fail; } - - ret = btrfs_find_dead_roots(fs_info->tree_root, - root->root_key.objectid); - WARN_ON(ret); return root; fail: free_fs_root(root); @@ -1623,7 +1728,7 @@ if (!device->bdev) continue; bdi = blk_get_backing_dev_info(device->bdev); - if (bdi && bdi_congested(bdi, bdi_bits)) { + if (bdi_congested(bdi, bdi_bits)) { ret = 1; break; } @@ -1632,22 +1737,18 @@ return ret; } -/* - * If this fails, caller must call bdi_destroy() to get rid of the - * bdi again. - */ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi) { int err; - bdi->capabilities = BDI_CAP_MAP_COPY; - err = bdi_setup_and_register(bdi, "btrfs", BDI_CAP_MAP_COPY); + err = bdi_setup_and_register(bdi, "btrfs"); if (err) return err; - bdi->ra_pages = default_backing_dev_info.ra_pages; + bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE; bdi->congested_fn = btrfs_congested_fn; bdi->congested_data = info; + bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK; return 0; } @@ -1658,39 +1759,66 @@ static void end_workqueue_fn(struct btrfs_work *work) { struct bio *bio; - struct end_io_wq *end_io_wq; - struct btrfs_fs_info *fs_info; - int error; + struct btrfs_end_io_wq *end_io_wq; - end_io_wq = container_of(work, struct end_io_wq, work); + end_io_wq = container_of(work, struct btrfs_end_io_wq, work); bio = end_io_wq->bio; - fs_info = end_io_wq->info; - error = end_io_wq->error; + bio->bi_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); + kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); + bio_endio(bio); } static int cleaner_kthread(void *arg) { struct btrfs_root *root = arg; + int again; + struct btrfs_trans_handle *trans; do { - int again = 0; + again = 0; - if (!(root->fs_info->sb->s_flags & MS_RDONLY) && - down_read_trylock(&root->fs_info->sb->s_umount)) { - if (mutex_trylock(&root->fs_info->cleaner_mutex)) { - btrfs_run_delayed_iputs(root); - again = btrfs_clean_one_deleted_snapshot(root); - mutex_unlock(&root->fs_info->cleaner_mutex); - } - btrfs_run_defrag_inodes(root->fs_info); - up_read(&root->fs_info->sb->s_umount); + /* Make the cleaner go to sleep early. */ + if (btrfs_need_cleaner_sleep(root)) + goto sleep; + + if (!mutex_trylock(&root->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); + goto sleep; } + mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex); + btrfs_run_delayed_iputs(root); + mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex); + + again = btrfs_clean_one_deleted_snapshot(root); + mutex_unlock(&root->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); + + /* + * Acquires fs_info->delete_unused_bgs_mutex to avoid racing + * with relocation (btrfs_relocate_chunk) and relocation + * acquires fs_info->cleaner_mutex (btrfs_relocate_block_group) + * after acquiring fs_info->delete_unused_bgs_mutex. So we + * can't hold, nor need to, fs_info->cleaner_mutex when deleting + * unused block groups. + */ + btrfs_delete_unused_bgs(root->fs_info); +sleep: if (!try_to_freeze() && !again) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop()) @@ -1698,6 +1826,34 @@ __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(root->fs_info, + "cleaner transaction attach returned %ld", + PTR_ERR(trans)); + } else { + int ret; + + ret = btrfs_commit_transaction(trans, root); + if (ret) + btrfs_err(root->fs_info, + "cleaner open transaction commit returned %d", + ret); + } + return 0; } @@ -1713,7 +1869,7 @@ do { cannot_commit = false; - delay = HZ * 30; + delay = HZ * root->fs_info->commit_interval; mutex_lock(&root->fs_info->transaction_kthread_mutex); spin_lock(&root->fs_info->trans_lock); @@ -1724,8 +1880,9 @@ } now = get_seconds(); - if (!cur->blocked && - (now < cur->start_time || now - cur->start_time < 30)) { + if (cur->state < TRANS_STATE_BLOCKED && + (now < cur->start_time || + now - cur->start_time < root->fs_info->commit_interval)) { spin_unlock(&root->fs_info->trans_lock); delay = HZ * 5; goto sleep; @@ -1749,6 +1906,9 @@ wake_up_process(root->fs_info->cleaner_kthread); mutex_unlock(&root->fs_info->transaction_kthread_mutex); + if (unlikely(test_bit(BTRFS_FS_STATE_ERROR, + &root->fs_info->fs_state))) + btrfs_cleanup_transaction(root); if (!try_to_freeze()) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop() && @@ -1963,66 +2123,51 @@ /* 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); + btrfs_destroy_workqueue(fs_info->endio_workers); + btrfs_destroy_workqueue(fs_info->endio_meta_workers); + btrfs_destroy_workqueue(fs_info->endio_raid56_workers); + btrfs_destroy_workqueue(fs_info->endio_repair_workers); + btrfs_destroy_workqueue(fs_info->rmw_workers); + btrfs_destroy_workqueue(fs_info->endio_meta_write_workers); + btrfs_destroy_workqueue(fs_info->endio_write_workers); + btrfs_destroy_workqueue(fs_info->endio_freespace_worker); + btrfs_destroy_workqueue(fs_info->submit_workers); + btrfs_destroy_workqueue(fs_info->delayed_workers); + btrfs_destroy_workqueue(fs_info->caching_workers); + btrfs_destroy_workqueue(fs_info->readahead_workers); + btrfs_destroy_workqueue(fs_info->flush_workers); + btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers); + btrfs_destroy_workqueue(fs_info->extent_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; + } } /* helper to cleanup tree roots */ static void free_root_pointers(struct btrfs_fs_info *info, int 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; - - 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; - } + free_root_extent_buffers(info->tree_root); + + free_root_extent_buffers(info->dev_root); + free_root_extent_buffers(info->extent_root); + free_root_extent_buffers(info->csum_root); + free_root_extent_buffers(info->quota_root); + free_root_extent_buffers(info->uuid_root); + if (chunk_root) + free_root_extent_buffers(info->chunk_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]; @@ -2033,12 +2178,12 @@ struct btrfs_root, root_list); list_del(&gang[0]->root_list); - if (gang[0]->in_radix) { - btrfs_free_fs_root(fs_info, gang[0]); + 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); - kfree(gang[0]); + btrfs_put_fs_root(gang[0]); } } @@ -2049,8 +2194,279 @@ if (!ret) break; for (i = 0; i < ret; i++) - btrfs_free_fs_root(fs_info, gang[i]); + btrfs_drop_and_free_fs_root(fs_info, gang[i]); + } + + if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { + btrfs_free_log_root_tree(NULL, fs_info); + btrfs_destroy_pinned_extent(fs_info->tree_root, + fs_info->pinned_extents); + } +} + +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); + 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_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); +} + +static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info, + struct btrfs_root *tree_root) +{ + 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; + + 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); + btrfs_insert_inode_hash(fs_info->btree_inode); +} + +static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info) +{ + 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); + init_waitqueue_head(&fs_info->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; + fs_info->qgroup_op_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; + fs_info->qgroup_rescan_running = false; + mutex_init(&fs_info->qgroup_rescan_lock); +} + +static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, + struct btrfs_fs_devices *fs_devices) +{ + int max_active = fs_info->thread_pool_size; + unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND; + + fs_info->workers = + btrfs_alloc_workqueue("worker", flags | WQ_HIGHPRI, + max_active, 16); + + fs_info->delalloc_workers = + btrfs_alloc_workqueue("delalloc", flags, max_active, 2); + + fs_info->flush_workers = + btrfs_alloc_workqueue("flush_delalloc", flags, max_active, 0); + + fs_info->caching_workers = + btrfs_alloc_workqueue("cache", flags, max_active, 0); + + /* + * 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 = + btrfs_alloc_workqueue("submit", flags, + min_t(u64, fs_devices->num_devices, + max_active), 64); + + fs_info->fixup_workers = + btrfs_alloc_workqueue("fixup", flags, 1, 0); + + /* + * endios are largely parallel and should have a very + * low idle thresh + */ + fs_info->endio_workers = + btrfs_alloc_workqueue("endio", flags, max_active, 4); + fs_info->endio_meta_workers = + btrfs_alloc_workqueue("endio-meta", flags, max_active, 4); + fs_info->endio_meta_write_workers = + btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2); + fs_info->endio_raid56_workers = + btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4); + fs_info->endio_repair_workers = + btrfs_alloc_workqueue("endio-repair", flags, 1, 0); + fs_info->rmw_workers = + btrfs_alloc_workqueue("rmw", flags, max_active, 2); + fs_info->endio_write_workers = + btrfs_alloc_workqueue("endio-write", flags, max_active, 2); + fs_info->endio_freespace_worker = + btrfs_alloc_workqueue("freespace-write", flags, max_active, 0); + fs_info->delayed_workers = + btrfs_alloc_workqueue("delayed-meta", flags, max_active, 0); + fs_info->readahead_workers = + btrfs_alloc_workqueue("readahead", flags, max_active, 2); + fs_info->qgroup_rescan_workers = + btrfs_alloc_workqueue("qgroup-rescan", flags, 1, 0); + fs_info->extent_workers = + btrfs_alloc_workqueue("extent-refs", flags, + min_t(u64, fs_devices->num_devices, + max_active), 8); + + if (!(fs_info->workers && fs_info->delalloc_workers && + fs_info->submit_workers && fs_info->flush_workers && + fs_info->endio_workers && fs_info->endio_meta_workers && + fs_info->endio_meta_write_workers && + fs_info->endio_repair_workers && + fs_info->endio_write_workers && fs_info->endio_raid56_workers && + fs_info->endio_freespace_worker && fs_info->rmw_workers && + fs_info->caching_workers && fs_info->readahead_workers && + fs_info->fixup_workers && fs_info->delayed_workers && + fs_info->extent_workers && + fs_info->qgroup_rescan_workers)) { + return -ENOMEM; + } + + return 0; +} + +static int btrfs_replay_log(struct btrfs_fs_info *fs_info, + struct btrfs_fs_devices *fs_devices) +{ + int ret; + struct btrfs_root *tree_root = fs_info->tree_root; + struct btrfs_root *log_tree_root; + struct btrfs_super_block *disk_super = fs_info->super_copy; + u64 bytenr = btrfs_super_log_root(disk_super); + + if (fs_devices->rw_devices == 0) { + btrfs_warn(fs_info, "log replay required on RO media"); + return -EIO; + } + + log_tree_root = btrfs_alloc_root(fs_info); + if (!log_tree_root) + return -ENOMEM; + + __setup_root(tree_root->nodesize, tree_root->sectorsize, + tree_root->stripesize, log_tree_root, fs_info, + BTRFS_TREE_LOG_OBJECTID); + + log_tree_root->node = read_tree_block(tree_root, bytenr, + fs_info->generation + 1); + if (IS_ERR(log_tree_root->node)) { + btrfs_warn(fs_info, "failed to read log tree"); + ret = PTR_ERR(log_tree_root->node); + kfree(log_tree_root); + return ret; + } else if (!extent_buffer_uptodate(log_tree_root->node)) { + btrfs_err(fs_info, "failed to read log tree"); + free_extent_buffer(log_tree_root->node); + kfree(log_tree_root); + return -EIO; + } + /* returns with log_tree_root freed on success */ + ret = btrfs_recover_log_trees(log_tree_root); + if (ret) { + btrfs_std_error(tree_root->fs_info, ret, + "Failed to recover log tree"); + free_extent_buffer(log_tree_root->node); + kfree(log_tree_root); + return ret; + } + + if (fs_info->sb->s_flags & MS_RDONLY) { + ret = btrfs_commit_super(tree_root); + if (ret) + return ret; + } + + return 0; +} + +static int btrfs_read_roots(struct btrfs_fs_info *fs_info, + struct btrfs_root *tree_root) +{ + struct btrfs_root *root; + struct btrfs_key location; + int ret; + + location.objectid = BTRFS_EXTENT_TREE_OBJECTID; + location.type = BTRFS_ROOT_ITEM_KEY; + location.offset = 0; + + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) + return PTR_ERR(root); + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->extent_root = root; + + location.objectid = BTRFS_DEV_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) + return PTR_ERR(root); + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->dev_root = root; + btrfs_init_devices_late(fs_info); + + location.objectid = BTRFS_CSUM_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) + return PTR_ERR(root); + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->csum_root = root; + + location.objectid = BTRFS_QUOTA_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (!IS_ERR(root)) { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->quota_enabled = 1; + fs_info->pending_quota_state = 1; + fs_info->quota_root = root; } + + location.objectid = BTRFS_UUID_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) { + ret = PTR_ERR(root); + if (ret != -ENOENT) + return ret; + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->uuid_root = root; + } + + return 0; } int open_ctree(struct super_block *sb, @@ -2059,8 +2475,6 @@ { u32 sectorsize; u32 nodesize; - u32 leafsize; - u32 blocksize; u32 stripesize; u64 generation; u64 features; @@ -2069,26 +2483,16 @@ 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; int ret; int err = -EINVAL; int num_backups_tried = 0; int backup_index = 0; + int max_active; tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info); - extent_root = fs_info->extent_root = btrfs_alloc_root(fs_info); - csum_root = fs_info->csum_root = btrfs_alloc_root(fs_info); chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info); - dev_root = fs_info->dev_root = btrfs_alloc_root(fs_info); - quota_root = fs_info->quota_root = btrfs_alloc_root(fs_info); - - if (!tree_root || !extent_root || !csum_root || - !chunk_root || !dev_root || !quota_root) { + if (!tree_root || !chunk_root) { err = -ENOMEM; goto fail; } @@ -2105,7 +2509,7 @@ goto fail_srcu; } - ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0); + ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); if (ret) { err = ret; goto fail_bdi; @@ -2113,27 +2517,34 @@ fs_info->dirty_metadata_batch = PAGE_CACHE_SIZE * (1 + ilog2(nr_cpu_ids)); - ret = percpu_counter_init(&fs_info->delalloc_bytes, 0); + ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL); if (ret) { err = ret; goto fail_dirty_metadata_bytes; } + ret = percpu_counter_init(&fs_info->bio_counter, 0, GFP_KERNEL); + if (ret) { + err = ret; + goto fail_delalloc_bytes; + } + fs_info->btree_inode = new_inode(sb); if (!fs_info->btree_inode) { err = -ENOMEM; - goto fail_delalloc_bytes; + goto fail_bio_counter; } mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS); INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC); + INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC); INIT_LIST_HEAD(&fs_info->trans_list); INIT_LIST_HEAD(&fs_info->dead_roots); INIT_LIST_HEAD(&fs_info->delayed_iputs); - INIT_LIST_HEAD(&fs_info->delalloc_inodes); + INIT_LIST_HEAD(&fs_info->delalloc_roots); INIT_LIST_HEAD(&fs_info->caching_block_groups); - spin_lock_init(&fs_info->delalloc_lock); + spin_lock_init(&fs_info->delalloc_root_lock); spin_lock_init(&fs_info->trans_lock); spin_lock_init(&fs_info->fs_roots_radix_lock); spin_lock_init(&fs_info->delayed_iput_lock); @@ -2141,14 +2552,21 @@ 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->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); + mutex_init(&fs_info->unused_bg_unpin_mutex); + 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_completion(&fs_info->kobj_unregister); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); INIT_LIST_HEAD(&fs_info->space_info); INIT_LIST_HEAD(&fs_info->tree_mod_seq_list); + INIT_LIST_HEAD(&fs_info->unused_bgs); btrfs_mapping_init(&fs_info->mapping_tree); btrfs_init_block_rsv(&fs_info->global_block_rsv, BTRFS_BLOCK_RSV_GLOBAL); @@ -2164,24 +2582,25 @@ 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->qgroup_op_seq, 0); atomic64_set(&fs_info->tree_mod_seq, 0); fs_info->sb = sb; - fs_info->max_inline = 8192 * 1024; + fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE; fs_info->metadata_ratio = 0; fs_info->defrag_inodes = RB_ROOT; - fs_info->trans_no_join = 0; fs_info->free_chunk_space = 0; fs_info->tree_mod_log = RB_ROOT; - + fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; + fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */ /* readahead state */ - INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); spin_lock_init(&fs_info->reada_lock); fs_info->thread_pool_size = min_t(unsigned long, num_online_cpus() + 2, 8); - INIT_LIST_HEAD(&fs_info->ordered_extents); - spin_lock_init(&fs_info->ordered_extent_lock); + 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) { @@ -2190,55 +2609,18 @@ } 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; + btrfs_init_scrub(fs_info); #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY fs_info->check_integrity_print_mask = 0; #endif - - 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); + btrfs_init_balance(fs_info); + btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work); 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); + btrfs_init_btree_inode(fs_info, tree_root); spin_lock_init(&fs_info->block_group_cache_lock); fs_info->block_group_cache_tree = RB_ROOT; @@ -2258,23 +2640,14 @@ 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; - mutex_init(&fs_info->qgroup_rescan_lock); + btrfs_init_dev_replace_locks(fs_info); + btrfs_init_qgroup(fs_info); btrfs_init_free_cluster(&fs_info->meta_alloc_cluster); btrfs_init_free_cluster(&fs_info->data_alloc_cluster); @@ -2284,13 +2657,15 @@ init_waitqueue_head(&fs_info->transaction_blocked_wait); init_waitqueue_head(&fs_info->async_submit_wait); + INIT_LIST_HEAD(&fs_info->pinned_chunks); + ret = btrfs_alloc_stripe_hash_table(fs_info); if (ret) { err = ret; goto fail_alloc; } - __setup_root(4096, 4096, 4096, 4096, tree_root, + __setup_root(4096, 4096, 4096, tree_root, fs_info, BTRFS_ROOT_TREE_OBJECTID); invalidate_bdev(fs_devices->latest_bdev); @@ -2299,8 +2674,8 @@ * Read super block and check the signature bytes only */ bh = btrfs_read_dev_super(fs_devices->latest_bdev); - if (!bh) { - err = -EINVAL; + if (IS_ERR(bh)) { + err = PTR_ERR(bh); goto fail_alloc; } @@ -2309,8 +2684,9 @@ * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k). */ if (btrfs_check_super_csum(bh->b_data)) { - printk(KERN_ERR "btrfs: superblock checksum mismatch\n"); + printk(KERN_ERR "BTRFS: superblock checksum mismatch\n"); err = -EINVAL; + brelse(bh); goto fail_alloc; } @@ -2328,7 +2704,7 @@ ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY); if (ret) { - printk(KERN_ERR "btrfs: superblock contains fatal errors\n"); + printk(KERN_ERR "BTRFS: superblock contains fatal errors\n"); err = -EINVAL; goto fail_alloc; } @@ -2365,24 +2741,27 @@ if (features) { printk(KERN_ERR "BTRFS: couldn't mount because of " "unsupported optional features (%Lx).\n", - (unsigned long long)features); + features); err = -EINVAL; goto fail_alloc; } - if (btrfs_super_leafsize(disk_super) != + /* + * Leafsize and nodesize were always equal, this is only a sanity check. + */ + if (le32_to_cpu(disk_super->__unused_leafsize) != 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)); + le32_to_cpu(disk_super->__unused_leafsize)); err = -EINVAL; goto fail_alloc; } - if (btrfs_super_leafsize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) { + if (btrfs_super_nodesize(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)); + btrfs_super_nodesize(disk_super)); err = -EINVAL; goto fail_alloc; } @@ -2393,23 +2772,22 @@ features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) - printk(KERN_ERR "btrfs: has skinny extents\n"); + printk(KERN_INFO "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 (btrfs_super_nodesize(disk_super) > PAGE_CACHE_SIZE) { if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA)) - printk(KERN_INFO "btrfs flagging fs with big metadata feature\n"); + printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n"); features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA; } 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)); + fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids)); fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids)); /* @@ -2417,8 +2795,8 @@ * extent buffers for the same range. It leads to corruptions */ if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) && - (sectorsize != leafsize)) { - printk(KERN_WARNING "btrfs: unequal leaf/node/sector sizes " + (sectorsize != nodesize)) { + printk(KERN_ERR "BTRFS: unequal leaf/node/sector sizes " "are not allowed for mixed block groups on %s\n", sb->s_id); goto fail_alloc; @@ -2435,114 +2813,16 @@ 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); + features); err = -EINVAL; - brelse(bh); 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); + max_active = fs_info->thread_pool_size; - 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); + ret = btrfs_init_workqueues(fs_info, fs_devices); if (ret) { - err = -ENOMEM; + err = ret; goto fail_sb_buffer; } @@ -2551,20 +2831,19 @@ 4 * 1024 * 1024 / PAGE_CACHE_SIZE); tree_root->nodesize = nodesize; - tree_root->leafsize = leafsize; tree_root->sectorsize = sectorsize; tree_root->stripesize = stripesize; 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); + if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) { + printk(KERN_ERR "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) " + printk(KERN_ERR "BTRFS: incompatible sector size (%lu) " "found on %s\n", (unsigned long)sectorsize, sb->s_id); goto fail_sb_buffer; } @@ -2573,37 +2852,37 @@ ret = btrfs_read_sys_array(tree_root); mutex_unlock(&fs_info->chunk_mutex); if (ret) { - printk(KERN_WARNING "btrfs: failed to read the system " + printk(KERN_ERR "BTRFS: failed to read the system " "array on %s\n", sb->s_id); 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); + __setup_root(nodesize, 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", + generation); + if (IS_ERR(chunk_root->node) || + !extent_buffer_uptodate(chunk_root->node)) { + printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n", sb->s_id); + if (!IS_ERR(chunk_root->node)) + free_extent_buffer(chunk_root->node); + chunk_root->node = NULL; goto fail_tree_roots; } btrfs_set_root_node(&chunk_root->root_item, chunk_root->node); chunk_root->commit_root = btrfs_root_node(chunk_root); read_extent_buffer(chunk_root->node, fs_info->chunk_tree_uuid, - (unsigned long)btrfs_header_chunk_tree_uuid(chunk_root->node), - BTRFS_UUID_SIZE); + btrfs_header_chunk_tree_uuid(chunk_root->node), BTRFS_UUID_SIZE); ret = btrfs_read_chunk_tree(chunk_root); if (ret) { - printk(KERN_WARNING "btrfs: failed to read chunk tree on %s\n", + printk(KERN_ERR "BTRFS: failed to read chunk tree on %s\n", sb->s_id); goto fail_tree_roots; } @@ -2612,111 +2891,118 @@ * keep the device that is marked to be the target device for the * dev_replace procedure */ - btrfs_close_extra_devices(fs_info, fs_devices, 0); + btrfs_close_extra_devices(fs_devices, 0); if (!fs_devices->latest_bdev) { - printk(KERN_CRIT "btrfs: failed to read devices on %s\n", + printk(KERN_ERR "BTRFS: failed to read devices on %s\n", sb->s_id); 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", + generation); + if (IS_ERR(tree_root->node) || + !extent_buffer_uptodate(tree_root->node)) { + printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n", sb->s_id); - + if (!IS_ERR(tree_root->node)) + free_extent_buffer(tree_root->node); + tree_root->node = NULL; goto recovery_tree_root; } btrfs_set_root_node(&tree_root->root_item, tree_root->node); tree_root->commit_root = btrfs_root_node(tree_root); + btrfs_set_root_refs(&tree_root->root_item, 1); - ret = find_and_setup_root(tree_root, fs_info, - BTRFS_EXTENT_TREE_OBJECTID, extent_root); - if (ret) + mutex_lock(&tree_root->objectid_mutex); + ret = btrfs_find_highest_objectid(tree_root, + &tree_root->highest_objectid); + if (ret) { + mutex_unlock(&tree_root->objectid_mutex); goto recovery_tree_root; - extent_root->track_dirty = 1; + } - ret = find_and_setup_root(tree_root, fs_info, - BTRFS_DEV_TREE_OBJECTID, dev_root); - if (ret) - goto recovery_tree_root; - dev_root->track_dirty = 1; + ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + + mutex_unlock(&tree_root->objectid_mutex); - ret = find_and_setup_root(tree_root, fs_info, - BTRFS_CSUM_TREE_OBJECTID, csum_root); + ret = btrfs_read_roots(fs_info, tree_root); if (ret) goto recovery_tree_root; - csum_root->track_dirty = 1; - - ret = find_and_setup_root(tree_root, fs_info, - BTRFS_QUOTA_TREE_OBJECTID, quota_root); - if (ret) { - kfree(quota_root); - quota_root = fs_info->quota_root = NULL; - } else { - quota_root->track_dirty = 1; - fs_info->quota_enabled = 1; - fs_info->pending_quota_state = 1; - } fs_info->generation = generation; fs_info->last_trans_committed = generation; ret = btrfs_recover_balance(fs_info); if (ret) { - printk(KERN_WARNING "btrfs: failed to recover balance\n"); + printk(KERN_ERR "BTRFS: failed to recover balance\n"); goto fail_block_groups; } ret = btrfs_init_dev_stats(fs_info); if (ret) { - printk(KERN_ERR "btrfs: failed to init dev_stats: %d\n", + printk(KERN_ERR "BTRFS: failed to init dev_stats: %d\n", ret); goto fail_block_groups; } ret = btrfs_init_dev_replace(fs_info); if (ret) { - pr_err("btrfs: failed to init dev_replace: %d\n", ret); + pr_err("BTRFS: failed to init dev_replace: %d\n", ret); goto fail_block_groups; } - btrfs_close_extra_devices(fs_info, fs_devices, 1); + btrfs_close_extra_devices(fs_devices, 1); - ret = btrfs_init_space_info(fs_info); + ret = btrfs_sysfs_add_fsid(fs_devices, NULL); if (ret) { - printk(KERN_ERR "Failed to initial space info: %d\n", ret); + pr_err("BTRFS: failed to init sysfs fsid interface: %d\n", ret); goto fail_block_groups; } - ret = btrfs_read_block_groups(extent_root); + ret = btrfs_sysfs_add_device(fs_devices); if (ret) { - printk(KERN_ERR "Failed to read block groups: %d\n", ret); - goto fail_block_groups; + pr_err("BTRFS: failed to init sysfs device interface: %d\n", ret); + goto fail_fsdev_sysfs; + } + + ret = btrfs_sysfs_add_mounted(fs_info); + if (ret) { + pr_err("BTRFS: failed to init sysfs interface: %d\n", ret); + goto fail_fsdev_sysfs; + } + + ret = btrfs_init_space_info(fs_info); + if (ret) { + printk(KERN_ERR "BTRFS: Failed to initial space info: %d\n", ret); + goto fail_sysfs; + } + + ret = btrfs_read_block_groups(fs_info->extent_root); + if (ret) { + printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", 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; + pr_warn("BTRFS: missing devices(%llu) exceeds the limit(%d), writeable mount is not allowed\n", + fs_info->fs_devices->missing_devices, + fs_info->num_tolerated_disk_barrier_failures); + goto fail_sysfs; } fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root, "btrfs-cleaner"); if (IS_ERR(fs_info->cleaner_kthread)) - goto fail_block_groups; + goto fail_sysfs; fs_info->transaction_kthread = kthread_run(transaction_kthread, tree_root, @@ -2727,11 +3013,17 @@ 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 " + printk(KERN_INFO "BTRFS: detected SSD devices, enabling SSD " "mode\n"); btrfs_set_opt(fs_info->mount_opt, SSD); } + /* + * Mount does not set all options immediatelly, we can do it now and do + * not have to wait for transaction commit + */ + btrfs_apply_pending_changes(fs_info); + #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) { ret = btrfsic_mount(tree_root, fs_devices, @@ -2740,7 +3032,7 @@ 1 : 0, fs_info->check_integrity_print_mask); if (ret) - printk(KERN_WARNING "btrfs: failed to initialize" + printk(KERN_WARNING "BTRFS: failed to initialize" " integrity check module %s\n", sb->s_id); } #endif @@ -2750,67 +3042,28 @@ /* 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); + ret = btrfs_replay_log(fs_info, fs_devices); 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; + err = ret; + goto fail_qgroup; } } ret = btrfs_find_orphan_roots(tree_root); if (ret) - goto fail_trans_kthread; + goto fail_qgroup; if (!(sb->s_flags & MS_RDONLY)) { ret = btrfs_cleanup_fs_roots(fs_info); if (ret) - goto fail_trans_kthread; + goto fail_qgroup; + mutex_lock(&fs_info->cleaner_mutex); ret = btrfs_recover_relocation(tree_root); + mutex_unlock(&fs_info->cleaner_mutex); if (ret < 0) { printk(KERN_WARNING - "btrfs: failed to recover relocation\n"); + "BTRFS: failed to recover relocation\n"); err = -EINVAL; goto fail_qgroup; } @@ -2818,11 +3071,9 @@ location.objectid = BTRFS_FS_TREE_OBJECTID; location.type = BTRFS_ROOT_ITEM_KEY; - location.offset = (u64)-1; + location.offset = 0; fs_info->fs_root = btrfs_read_fs_root_no_name(fs_info, &location); - if (!fs_info->fs_root) - goto fail_qgroup; if (IS_ERR(fs_info->fs_root)) { err = PTR_ERR(fs_info->fs_root); goto fail_qgroup; @@ -2842,18 +3093,46 @@ ret = btrfs_resume_balance_async(fs_info); if (ret) { - printk(KERN_WARNING "btrfs: failed to resume balance\n"); + printk(KERN_WARNING "BTRFS: failed to resume balance\n"); close_ctree(tree_root); return ret; } ret = btrfs_resume_dev_replace_async(fs_info); if (ret) { - pr_warn("btrfs: failed to resume dev_replace\n"); + pr_warn("BTRFS: failed to resume dev_replace\n"); close_ctree(tree_root); return ret; } + btrfs_qgroup_rescan_resume(fs_info); + + if (!fs_info->uuid_root) { + pr_info("BTRFS: creating UUID tree\n"); + ret = btrfs_create_uuid_tree(fs_info); + if (ret) { + pr_warn("BTRFS: failed to create the UUID tree %d\n", + ret); + close_ctree(tree_root); + return ret; + } + } else if (btrfs_test_opt(tree_root, RESCAN_UUID_TREE) || + fs_info->generation != + btrfs_super_uuid_tree_generation(disk_super)) { + pr_info("BTRFS: checking UUID tree\n"); + ret = btrfs_check_uuid_tree(fs_info); + if (ret) { + pr_warn("BTRFS: failed to check the UUID tree %d\n", + ret); + close_ctree(tree_root); + return ret; + } + } else { + fs_info->update_uuid_tree_gen = 1; + } + + fs_info->open = 1; + return 0; fail_qgroup: @@ -2861,7 +3140,7 @@ fail_trans_kthread: kthread_stop(fs_info->transaction_kthread); btrfs_cleanup_transaction(fs_info->tree_root); - del_fs_roots(fs_info); + btrfs_free_fs_roots(fs_info); fail_cleaner: kthread_stop(fs_info->cleaner_kthread); @@ -2871,6 +3150,12 @@ */ 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); @@ -2886,6 +3171,8 @@ btrfs_mapping_tree_free(&fs_info->mapping_tree); iput(fs_info->btree_inode); +fail_bio_counter: + percpu_counter_destroy(&fs_info->bio_counter); fail_delalloc_bytes: percpu_counter_destroy(&fs_info->delalloc_bytes); fail_dirty_metadata_bytes: @@ -2926,8 +3213,8 @@ 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", + btrfs_warn_rl_in_rcu(device->dev_root->fs_info, + "lost page write due to IO error on %s", 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 @@ -2939,6 +3226,37 @@ put_bh(bh); } +int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num, + struct buffer_head **bh_ret) +{ + struct buffer_head *bh; + struct btrfs_super_block *super; + u64 bytenr; + + bytenr = btrfs_sb_offset(copy_num); + if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode)) + return -EINVAL; + + bh = __bread(bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE); + /* + * If we fail to read from the underlying devices, as of now + * the best option we have is to mark it EIO. + */ + if (!bh) + return -EIO; + + super = (struct btrfs_super_block *)bh->b_data; + if (btrfs_super_bytenr(super) != bytenr || + btrfs_super_magic(super) != BTRFS_MAGIC) { + brelse(bh); + return -EINVAL; + } + + *bh_ret = bh; + return 0; +} + + struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) { struct buffer_head *bh; @@ -2946,7 +3264,7 @@ struct btrfs_super_block *super; int i; u64 transid = 0; - u64 bytenr; + int ret = -EINVAL; /* we would like to check all the supers, but that would make * a btrfs mount succeed after a mkfs from a different FS. @@ -2954,19 +3272,11 @@ * 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) + ret = btrfs_read_dev_one_super(bdev, i, &bh); + if (ret) continue; super = (struct btrfs_super_block *)bh->b_data; - if (btrfs_super_bytenr(super) != bytenr || - super->magic != cpu_to_le64(BTRFS_MAGIC)) { - brelse(bh); - continue; - } if (!latest || btrfs_super_generation(super) > transid) { brelse(latest); @@ -2976,6 +3286,10 @@ brelse(bh); } } + + if (!latest) + return ERR_PTR(ret); + return latest; } @@ -3006,7 +3320,8 @@ for (i = 0; i < max_mirrors; i++) { bytenr = btrfs_sb_offset(i); - if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->total_bytes) + if (bytenr + BTRFS_SUPER_INFO_SIZE >= + device->commit_total_bytes) break; if (wait) { @@ -3043,8 +3358,9 @@ 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); + btrfs_err(device->dev_root->fs_info, + "couldn't get super buffer head for bytenr %llu", + bytenr); errors++; continue; } @@ -3064,7 +3380,10 @@ * we fua the first super. The others we allow * to go down lazy. */ - ret = btrfsic_submit_bh(WRITE_FUA, bh); + if (i == 0) + ret = btrfsic_submit_bh(WRITE_FUA, bh); + else + ret = btrfsic_submit_bh(WRITE_SYNC, bh); if (ret) errors++; } @@ -3075,13 +3394,8 @@ * 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); @@ -3109,12 +3423,8 @@ wait_for_completion(&device->flush_wait); - 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; + if (bio->bi_error) { + ret = bio->bi_error; btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_FLUSH_ERRS); } @@ -3197,6 +3507,35 @@ return 0; } +int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags) +{ + 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(min_tolerated, + btrfs_raid_array[BTRFS_RAID_SINGLE]. + tolerated_failures); + + for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) { + if (raid_type == BTRFS_RAID_SINGLE) + continue; + if (!(flags & btrfs_raid_group[raid_type])) + continue; + min_tolerated = min(min_tolerated, + btrfs_raid_array[raid_type]. + tolerated_failures); + } + + if (min_tolerated == INT_MAX) { + pr_warn("BTRFS: unknown raid flag: %llu\n", flags); + min_tolerated = 0; + } + + return min_tolerated; +} + int btrfs_calc_num_tolerated_disk_barrier_failures( struct btrfs_fs_info *fs_info) { @@ -3206,13 +3545,12 @@ 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++) { + for (i = 0; i < ARRAY_SIZE(types); i++) { struct btrfs_space_info *tmp; sinfo = NULL; @@ -3230,44 +3568,21 @@ down_read(&sinfo->groups_sem); for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) { - if (!list_empty(&sinfo->block_groups[c])) { - u64 flags; + 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_RAID5) { - num_tolerated_disk_barrier_failures = 2; - } - } - } + if (list_empty(&sinfo->block_groups[c])) + continue; + + btrfs_get_block_group_info(&sinfo->block_groups[c], + &space); + if (space.total_bytes == 0 || space.used_bytes == 0) + continue; + flags = space.flags; + + num_tolerated_disk_barrier_failures = min( + num_tolerated_disk_barrier_failures, + btrfs_get_num_tolerated_disk_barrier_failures( + flags)); } up_read(&sinfo->groups_sem); } @@ -3287,7 +3602,6 @@ 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); @@ -3296,13 +3610,14 @@ mutex_lock(&root->fs_info->fs_devices->device_list_mutex); head = &root->fs_info->fs_devices->devices; + max_errors = btrfs_super_num_devices(root->fs_info->super_copy) - 1; if (do_barriers) { ret = barrier_all_devices(root->fs_info); if (ret) { mutex_unlock( &root->fs_info->fs_devices->device_list_mutex); - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "errors while submitting device barriers."); return ret; } @@ -3319,8 +3634,10 @@ 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); @@ -3335,11 +3652,14 @@ total_errors++; } if (total_errors > max_errors) { - printk(KERN_ERR "btrfs: %d errors while writing supers\n", + btrfs_err(root->fs_info, "%d errors while writing supers", total_errors); + mutex_unlock(&root->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_std_error(root->fs_info, -EIO, + "%d errors while writing supers", total_errors); + return -EIO; } total_errors = 0; @@ -3355,7 +3675,7 @@ } mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); if (total_errors > max_errors) { - btrfs_error(root->fs_info, -EIO, + btrfs_std_error(root->fs_info, -EIO, "%d errors while writing supers", total_errors); return -EIO; } @@ -3365,13 +3685,12 @@ 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; + return write_all_supers(root, max_mirrors); } -void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) +/* 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) { spin_lock(&fs_info->fs_roots_radix_lock); radix_tree_delete(&fs_info->fs_roots_radix, @@ -3381,62 +3700,93 @@ 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)) { + if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) btrfs_free_log(NULL, root); - btrfs_free_log_root_tree(NULL, fs_info); - } - __btrfs_remove_free_space_cache(root->free_ino_pinned); - __btrfs_remove_free_space_cache(root->free_ino_ctl); + if (root->free_ino_pinned) + __btrfs_remove_free_space_cache(root->free_ino_pinned); + if (root->free_ino_ctl) + __btrfs_remove_free_space_cache(root->free_ino_ctl); free_fs_root(root); } static void free_fs_root(struct btrfs_root *root) { - iput(root->cache_inode); + iput(root->ino_cache_inode); WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree)); + btrfs_free_block_rsv(root, root->orphan_block_rsv); + root->orphan_block_rsv = NULL; if (root->anon_dev) free_anon_bdev(root->anon_dev); + if (root->subv_writers) + btrfs_free_subvolume_writers(root->subv_writers); free_extent_buffer(root->node); free_extent_buffer(root->commit_root); kfree(root->free_ino_ctl); kfree(root->free_ino_pinned); kfree(root->name); - kfree(root); + btrfs_put_fs_root(root); +} + +void btrfs_free_fs_root(struct btrfs_root *root) +{ + free_fs_root(root); } int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) { u64 root_objectid = 0; struct btrfs_root *gang[8]; - int i; - int ret; + int i = 0; + int err = 0; + unsigned int ret = 0; + int index; while (1) { + index = srcu_read_lock(&fs_info->subvol_srcu); ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, (void **)gang, root_objectid, ARRAY_SIZE(gang)); - if (!ret) + if (!ret) { + srcu_read_unlock(&fs_info->subvol_srcu, index); break; - + } root_objectid = gang[ret - 1]->root_key.objectid + 1; + for (i = 0; i < ret; i++) { - int err; + /* 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_fs_root(gang[i]); + } + srcu_read_unlock(&fs_info->subvol_srcu, index); + for (i = 0; i < ret; i++) { + if (!gang[i]) + continue; root_objectid = gang[i]->root_key.objectid; err = btrfs_orphan_cleanup(gang[i]); if (err) - return err; + break; + btrfs_put_fs_root(gang[i]); } root_objectid++; } - return 0; + + /* release the uncleaned roots due to error */ + for (; i < ret; i++) { + if (gang[i]) + btrfs_put_fs_root(gang[i]); + } + return err; } int btrfs_commit_super(struct btrfs_root *root) { struct btrfs_trans_handle *trans; - int ret; mutex_lock(&root->fs_info->cleaner_mutex); btrfs_run_delayed_iputs(root); @@ -3450,28 +3800,10 @@ 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; - } - - ret = write_ctree_super(NULL, root, 0); - return ret; + return btrfs_commit_transaction(trans, root); } -int close_ctree(struct btrfs_root *root) +void close_ctree(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; int ret; @@ -3479,6 +3811,14 @@ fs_info->closing = 1; smp_mb(); + /* wait for the qgroup rescan worker to stop */ + btrfs_qgroup_wait_for_completion(fs_info, false); + + /* wait for the uuid_scan task to finish */ + down(&fs_info->uuid_tree_rescan_sem); + /* avoid complains from lockdep et al., set sem back to initial state */ + up(&fs_info->uuid_tree_rescan_sem); + /* pause restriper - we want to resume on mount */ btrfs_pause_balance(fs_info); @@ -3493,30 +3833,44 @@ /* clear out the rbtree of defraggable inodes */ btrfs_cleanup_defrag_inodes(fs_info); + cancel_work_sync(&fs_info->async_reclaim_work); + if (!(fs_info->sb->s_flags & MS_RDONLY)) { + /* + * 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. + */ + btrfs_delete_unused_bgs(root->fs_info); + ret = btrfs_commit_super(root); if (ret) - printk(KERN_ERR "btrfs: commit super ret %d\n", ret); + btrfs_err(fs_info, "commit super ret %d", ret); } if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) btrfs_error_commit_super(root); - btrfs_put_block_group_cache(fs_info); - kthread_stop(fs_info->transaction_kthread); kthread_stop(fs_info->cleaner_kthread); fs_info->closing = 2; smp_mb(); - btrfs_free_qgroup_config(root->fs_info); + btrfs_free_qgroup_config(fs_info); 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_sysfs_remove_mounted(fs_info); + btrfs_sysfs_remove_fsid(fs_info->fs_devices); + + btrfs_free_fs_roots(fs_info); + + btrfs_put_block_group_cache(fs_info); + btrfs_free_block_groups(fs_info); /* @@ -3526,8 +3880,7 @@ invalidate_inode_pages2(fs_info->btree_inode->i_mapping); btrfs_stop_all_workers(fs_info); - del_fs_roots(fs_info); - + fs_info->open = 0; free_root_pointers(fs_info, 1); iput(fs_info->btree_inode); @@ -3542,12 +3895,25 @@ percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); + percpu_counter_destroy(&fs_info->bio_counter); bdi_destroy(&fs_info->bdi); cleanup_srcu_struct(&fs_info->subvol_srcu); btrfs_free_stripe_hash_table(fs_info); - return 0; + __btrfs_free_block_rsv(root->orphan_block_rsv); + root->orphan_block_rsv = NULL; + + lock_chunks(root); + 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); + } + unlock_chunks(root); } int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, @@ -3574,22 +3940,36 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) { - struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root; + struct btrfs_root *root; u64 transid = btrfs_header_generation(buf); int was_dirty; +#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 marking dummy buffers as dirty + * outside of the sanity tests. + */ + if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &buf->bflags))) + return; +#endif + root = BTRFS_I(buf->pages[0]->mapping->host)->root; 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); + buf->start, transid, 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); +#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) { + btrfs_print_leaf(root, buf); + ASSERT(0); + } +#endif } static void __btrfs_btree_balance_dirty(struct btrfs_root *root, @@ -3635,10 +4015,112 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, int read_only) { + struct btrfs_super_block *sb = fs_info->super_copy; + int ret = 0; + + if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) { + printk(KERN_ERR "BTRFS: tree_root level too big: %d >= %d\n", + btrfs_super_root_level(sb), BTRFS_MAX_LEVEL); + ret = -EINVAL; + } + if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) { + printk(KERN_ERR "BTRFS: chunk_root level too big: %d >= %d\n", + btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL); + ret = -EINVAL; + } + if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) { + printk(KERN_ERR "BTRFS: log_root level too big: %d >= %d\n", + btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL); + ret = -EINVAL; + } + /* - * Placeholder for checks + * The common minimum, we don't know if we can trust the nodesize/sectorsize + * items yet, they'll be verified later. Issue just a warning. */ - return 0; + if (!IS_ALIGNED(btrfs_super_root(sb), 4096)) + printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n", + btrfs_super_root(sb)); + if (!IS_ALIGNED(btrfs_super_chunk_root(sb), 4096)) + printk(KERN_WARNING "BTRFS: chunk_root block unaligned: %llu\n", + btrfs_super_chunk_root(sb)); + if (!IS_ALIGNED(btrfs_super_log_root(sb), 4096)) + printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n", + btrfs_super_log_root(sb)); + + /* + * Check the lower bound, the alignment and other constraints are + * checked later. + */ + if (btrfs_super_nodesize(sb) < 4096) { + printk(KERN_ERR "BTRFS: nodesize too small: %u < 4096\n", + btrfs_super_nodesize(sb)); + ret = -EINVAL; + } + if (btrfs_super_sectorsize(sb) < 4096) { + printk(KERN_ERR "BTRFS: sectorsize too small: %u < 4096\n", + btrfs_super_sectorsize(sb)); + ret = -EINVAL; + } + + if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) { + printk(KERN_ERR "BTRFS: dev_item UUID does not match fsid: %pU != %pU\n", + fs_info->fsid, sb->dev_item.fsid); + ret = -EINVAL; + } + + /* + * Hint to catch really bogus numbers, bitflips or so, more exact checks are + * done later + */ + if (btrfs_super_num_devices(sb) > (1UL << 31)) + printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n", + btrfs_super_num_devices(sb)); + if (btrfs_super_num_devices(sb) == 0) { + printk(KERN_ERR "BTRFS: number of devices is 0\n"); + ret = -EINVAL; + } + + if (btrfs_super_bytenr(sb) != BTRFS_SUPER_INFO_OFFSET) { + printk(KERN_ERR "BTRFS: super offset mismatch %llu != %u\n", + btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET); + ret = -EINVAL; + } + + /* + * Obvious sys_chunk_array corruptions, it must hold at least one key + * and one chunk + */ + if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) { + printk(KERN_ERR "BTRFS: system chunk array too big %u > %u\n", + 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)) { + printk(KERN_ERR "BTRFS: system chunk array too small %u < %zu\n", + 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)) + printk(KERN_WARNING + "BTRFS: suspicious: generation < chunk_root_generation: %llu < %llu\n", + 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) + printk(KERN_WARNING + "BTRFS: suspicious: generation < cache_generation: %llu < %llu\n", + btrfs_super_generation(sb), btrfs_super_cache_generation(sb)); + + return ret; } static void btrfs_error_commit_super(struct btrfs_root *root) @@ -3654,51 +4136,47 @@ btrfs_cleanup_transaction(root); } -static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t, - struct btrfs_root *root) -{ - 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_extent_lock); - - list_splice_init(&t->ordered_operations, &splice); - while (!list_empty(&splice)) { - btrfs_inode = list_entry(splice.next, struct btrfs_inode, - ordered_operations); - - list_del_init(&btrfs_inode->ordered_operations); - spin_unlock(&root->fs_info->ordered_extent_lock); - - btrfs_invalidate_inodes(btrfs_inode->root); - - spin_lock(&root->fs_info->ordered_extent_lock); - } - - spin_unlock(&root->fs_info->ordered_extent_lock); - mutex_unlock(&root->fs_info->ordered_operations_mutex); -} - static void btrfs_destroy_ordered_extents(struct btrfs_root *root) { struct btrfs_ordered_extent *ordered; - spin_lock(&root->fs_info->ordered_extent_lock); + spin_lock(&root->ordered_extent_lock); /* * This will just short circuit the ordered completion stuff which will * make sure the ordered extent gets properly cleaned up. */ - list_for_each_entry(ordered, &root->fs_info->ordered_extents, + list_for_each_entry(ordered, &root->ordered_extents, root_extent_list) set_bit(BTRFS_ORDERED_IOERR, &ordered->flags); - spin_unlock(&root->fs_info->ordered_extent_lock); + spin_unlock(&root->ordered_extent_lock); +} + +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); + + 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_move_tail(&root->ordered_root, + &fs_info->ordered_roots); + + spin_unlock(&fs_info->ordered_root_lock); + btrfs_destroy_ordered_extents(root); + + cond_resched(); + spin_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) +static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, + struct btrfs_root *root) { struct rb_node *node; struct btrfs_delayed_ref_root *delayed_refs; @@ -3708,51 +4186,54 @@ delayed_refs = &trans->delayed_refs; spin_lock(&delayed_refs->lock); - if (delayed_refs->num_entries == 0) { + if (atomic_read(&delayed_refs->num_entries) == 0) { spin_unlock(&delayed_refs->lock); - printk(KERN_INFO "delayed_refs has NO entry\n"); + btrfs_info(root->fs_info, "delayed_refs has NO entry"); return ret; } - while ((node = rb_first(&delayed_refs->root)) != NULL) { - struct btrfs_delayed_ref_head *head = NULL; - - 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); + while ((node = rb_first(&delayed_refs->href_root)) != NULL) { + struct btrfs_delayed_ref_head *head; + struct btrfs_delayed_ref_node *tmp; + bool pin_bytes = false; + + head = rb_entry(node, struct btrfs_delayed_ref_head, + href_node); + if (!mutex_trylock(&head->mutex)) { + atomic_inc(&head->node.refs); + spin_unlock(&delayed_refs->lock); - spin_lock(&delayed_refs->lock); - continue; - } - - if (head->must_insert_reserved) - btrfs_pin_extent(root, ref->bytenr, - ref->num_bytes, 1); - 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--; - if (head) + mutex_lock(&head->mutex); mutex_unlock(&head->mutex); + btrfs_put_delayed_ref(&head->node); + spin_lock(&delayed_refs->lock); + continue; + } + spin_lock(&head->lock); + list_for_each_entry_safe_reverse(ref, tmp, &head->ref_list, + list) { + ref->in_tree = 0; + list_del(&ref->list); + atomic_dec(&delayed_refs->num_entries); + btrfs_put_delayed_ref(ref); + } + if (head->must_insert_reserved) + pin_bytes = true; + btrfs_free_delayed_extent_op(head->extent_op); + delayed_refs->num_heads--; + if (head->processing == 0) + delayed_refs->num_heads_ready--; + atomic_dec(&delayed_refs->num_entries); + head->node.in_tree = 0; + rb_erase(&head->href_node, &delayed_refs->href_root); + spin_unlock(&head->lock); spin_unlock(&delayed_refs->lock); - btrfs_put_delayed_ref(ref); + mutex_unlock(&head->mutex); + if (pin_bytes) + btrfs_pin_extent(root, head->node.bytenr, + head->node.num_bytes, 1); + btrfs_put_delayed_ref(&head->node); cond_resched(); spin_lock(&delayed_refs->lock); } @@ -3762,49 +4243,56 @@ return ret; } -static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t) +static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) { - struct btrfs_pending_snapshot *snapshot; + struct btrfs_inode *btrfs_inode; struct list_head splice; INIT_LIST_HEAD(&splice); - list_splice_init(&t->pending_snapshots, &splice); + spin_lock(&root->delalloc_lock); + list_splice_init(&root->delalloc_inodes, &splice); while (!list_empty(&splice)) { - snapshot = list_entry(splice.next, - struct btrfs_pending_snapshot, - list); - snapshot->error = -ECANCELED; - list_del_init(&snapshot->list); + 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); + spin_unlock(&root->delalloc_lock); + + btrfs_invalidate_inodes(btrfs_inode->root); + + spin_lock(&root->delalloc_lock); } + + spin_unlock(&root->delalloc_lock); } -static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) +static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info) { - struct btrfs_inode *btrfs_inode; + struct btrfs_root *root; struct list_head splice; INIT_LIST_HEAD(&splice); - spin_lock(&root->fs_info->delalloc_lock); - list_splice_init(&root->fs_info->delalloc_inodes, &splice); - + spin_lock(&fs_info->delalloc_root_lock); + list_splice_init(&fs_info->delalloc_roots, &splice); while (!list_empty(&splice)) { - btrfs_inode = list_entry(splice.next, struct btrfs_inode, - delalloc_inodes); + root = list_first_entry(&splice, struct btrfs_root, + delalloc_root); + list_del_init(&root->delalloc_root); + root = btrfs_grab_fs_root(root); + BUG_ON(!root); + spin_unlock(&fs_info->delalloc_root_lock); - list_del_init(&btrfs_inode->delalloc_inodes); - clear_bit(BTRFS_INODE_IN_DELALLOC_LIST, - &btrfs_inode->runtime_flags); - spin_unlock(&root->fs_info->delalloc_lock); - - btrfs_invalidate_inodes(btrfs_inode->root); + btrfs_destroy_delalloc_inodes(root); + btrfs_put_fs_root(root); - spin_lock(&root->fs_info->delalloc_lock); + spin_lock(&fs_info->delalloc_root_lock); } - - spin_unlock(&root->fs_info->delalloc_lock); + spin_unlock(&fs_info->delalloc_root_lock); } static int btrfs_destroy_marked_extents(struct btrfs_root *root, @@ -3824,9 +4312,8 @@ clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS); while (start <= end) { - eb = btrfs_find_tree_block(root, start, - root->leafsize); - start += root->leafsize; + eb = btrfs_find_tree_block(root->fs_info, start); + start += root->nodesize; if (!eb) continue; wait_on_extent_buffer_writeback(eb); @@ -3879,22 +4366,13 @@ struct btrfs_root *root) { btrfs_destroy_delayed_refs(cur_trans, root); - btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv, - cur_trans->dirty_pages.dirty_bytes); - /* FIXME: cleanup wait for commit */ - cur_trans->in_commit = 1; - cur_trans->blocked = 1; + cur_trans->state = TRANS_STATE_COMMIT_START; wake_up(&root->fs_info->transaction_blocked_wait); - btrfs_evict_pending_snapshots(cur_trans); - - cur_trans->blocked = 0; + cur_trans->state = TRANS_STATE_UNBLOCKED; wake_up(&root->fs_info->transaction_wait); - cur_trans->commit_done = 1; - wake_up(&cur_trans->commit_wait); - btrfs_destroy_delayed_inodes(root); btrfs_assert_delayed_root_empty(root); @@ -3903,6 +4381,9 @@ btrfs_destroy_pinned_extent(root, root->fs_info->pinned_extents); + cur_trans->state =TRANS_STATE_COMPLETED; + wake_up(&cur_trans->commit_wait); + /* memset(cur_trans, 0, sizeof(*cur_trans)); kmem_cache_free(btrfs_transaction_cachep, cur_trans); @@ -3912,73 +4393,57 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root) { struct btrfs_transaction *t; - LIST_HEAD(list); mutex_lock(&root->fs_info->transaction_kthread_mutex); spin_lock(&root->fs_info->trans_lock); - list_splice_init(&root->fs_info->trans_list, &list); - root->fs_info->trans_no_join = 1; - spin_unlock(&root->fs_info->trans_lock); - - while (!list_empty(&list)) { - t = list_entry(list.next, struct btrfs_transaction, list); - - btrfs_destroy_ordered_operations(t, root); - - btrfs_destroy_ordered_extents(root); - - btrfs_destroy_delayed_refs(t, root); - - /* FIXME: cleanup wait for commit */ - t->in_commit = 1; - t->blocked = 1; - smp_mb(); - if (waitqueue_active(&root->fs_info->transaction_blocked_wait)) - wake_up(&root->fs_info->transaction_blocked_wait); - - btrfs_evict_pending_snapshots(t); - - t->blocked = 0; - smp_mb(); - if (waitqueue_active(&root->fs_info->transaction_wait)) - wake_up(&root->fs_info->transaction_wait); - - t->commit_done = 1; - smp_mb(); - if (waitqueue_active(&t->commit_wait)) - wake_up(&t->commit_wait); - - btrfs_destroy_delayed_inodes(root); - btrfs_assert_delayed_root_empty(root); - - btrfs_destroy_delalloc_inodes(root); + while (!list_empty(&root->fs_info->trans_list)) { + t = list_first_entry(&root->fs_info->trans_list, + struct btrfs_transaction, list); + if (t->state >= TRANS_STATE_COMMIT_START) { + atomic_inc(&t->use_count); + spin_unlock(&root->fs_info->trans_lock); + btrfs_wait_for_commit(root, t->transid); + btrfs_put_transaction(t); + spin_lock(&root->fs_info->trans_lock); + continue; + } + if (t == root->fs_info->running_transaction) { + t->state = TRANS_STATE_COMMIT_DOING; + spin_unlock(&root->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(&root->fs_info->trans_lock); + } + btrfs_cleanup_one_transaction(t, root); spin_lock(&root->fs_info->trans_lock); - root->fs_info->running_transaction = NULL; + if (t == root->fs_info->running_transaction) + root->fs_info->running_transaction = NULL; + list_del_init(&t->list); spin_unlock(&root->fs_info->trans_lock); - btrfs_destroy_marked_extents(root, &t->dirty_pages, - EXTENT_DIRTY); - - btrfs_destroy_pinned_extent(root, - root->fs_info->pinned_extents); - - atomic_set(&t->use_count, 0); - list_del_init(&t->list); - memset(t, 0, sizeof(*t)); - kmem_cache_free(btrfs_transaction_cachep, t); + btrfs_put_transaction(t); + trace_btrfs_transaction_commit(root); + spin_lock(&root->fs_info->trans_lock); } - - spin_lock(&root->fs_info->trans_lock); - root->fs_info->trans_no_join = 0; spin_unlock(&root->fs_info->trans_lock); + btrfs_destroy_all_ordered_extents(root->fs_info); + btrfs_destroy_delayed_inodes(root); + btrfs_assert_delayed_root_empty(root); + btrfs_destroy_pinned_extent(root, root->fs_info->pinned_extents); + btrfs_destroy_all_delalloc_inodes(root->fs_info); mutex_unlock(&root->fs_info->transaction_kthread_mutex); return 0; } -static struct extent_io_ops btree_extent_io_ops = { +static const 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,