diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 0ef5cc13fae2..61205e3bbefa 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -192,6 +192,10 @@ struct btrfs_inode { /* File creation time. */ struct timespec i_otime; + /* Hook into fs_info->delayed_iputs */ + struct list_head delayed_iput; + long delayed_iput_count; + struct inode vfs_inode; }; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 5b8e235c4b6d..be1be0422ff4 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2248,7 +2248,6 @@ static void reada_for_search(struct btrfs_root *root, u64 target; u64 nread = 0; u64 gen; - int direction = path->reada; struct extent_buffer *eb; u32 nr; u32 blocksize; @@ -2276,16 +2275,16 @@ static void reada_for_search(struct btrfs_root *root, nr = slot; while (1) { - if (direction < 0) { + if (path->reada == READA_BACK) { if (nr == 0) break; nr--; - } else if (direction > 0) { + } else if (path->reada == READA_FORWARD) { nr++; if (nr >= nritems) break; } - if (path->reada < 0 && objectid) { + if (path->reada == READA_BACK && objectid) { btrfs_node_key(node, &disk_key, nr); if (btrfs_disk_key_objectid(&disk_key) != objectid) break; @@ -2493,7 +2492,7 @@ read_block_for_search(struct btrfs_trans_handle *trans, btrfs_set_path_blocking(p); free_extent_buffer(tmp); - if (p->reada) + if (p->reada != READA_NONE) reada_for_search(root, p, level, slot, key->objectid); btrfs_release_path(p); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9a88d0c69be4..70c940582482 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -177,7 +177,7 @@ struct btrfs_ordered_sum; /* csum types */ #define BTRFS_CSUM_TYPE_CRC32 0 -static int btrfs_csum_sizes[] = { 4 }; +static const int btrfs_csum_sizes[] = { 4 }; /* four bytes for CRC32 */ #define BTRFS_EMPTY_DIR_SIZE 0 @@ -598,14 +598,15 @@ struct btrfs_node { * The slots array records the index of the item or block pointer * used while walking the tree. */ +enum { READA_NONE = 0, READA_BACK, READA_FORWARD }; struct btrfs_path { struct extent_buffer *nodes[BTRFS_MAX_LEVEL]; int slots[BTRFS_MAX_LEVEL]; /* if there is real range locking, this locks field will change */ - int locks[BTRFS_MAX_LEVEL]; - int reada; + u8 locks[BTRFS_MAX_LEVEL]; + u8 reada; /* keep some upper locks as we walk down */ - int lowest_level; + u8 lowest_level; /* * set by btrfs_split_item, tells search_slot to keep all locks diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index e06dd75ad13f..914ac13bd92f 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -493,12 +493,12 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs, memcpy(&existing_ref->extent_op->key, &ref->extent_op->key, sizeof(ref->extent_op->key)); - existing_ref->extent_op->update_key = 1; + existing_ref->extent_op->update_key = true; } if (ref->extent_op->update_flags) { existing_ref->extent_op->flags_to_set |= ref->extent_op->flags_to_set; - existing_ref->extent_op->update_flags = 1; + existing_ref->extent_op->update_flags = true; } btrfs_free_delayed_extent_op(ref->extent_op); } diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 00ed02cbf3e9..c24b653c7343 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -75,11 +75,11 @@ struct btrfs_delayed_ref_node { struct btrfs_delayed_extent_op { struct btrfs_disk_key key; + u8 level; + bool update_key; + bool update_flags; + bool is_data; u64 flags_to_set; - int level; - unsigned int update_key:1; - unsigned int update_flags:1; - unsigned int is_data:1; }; /* diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index dc6b73a95342..c94457fde64d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2682,6 +2682,7 @@ int open_ctree(struct super_block *sb, if (btrfs_check_super_csum(bh->b_data)) { printk(KERN_ERR "BTRFS: superblock checksum mismatch\n"); err = -EINVAL; + brelse(bh); goto fail_alloc; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index add4af641cfa..46a39336e3d6 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -437,7 +437,7 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl) */ path->skip_locking = 1; path->search_commit_root = 1; - path->reada = 1; + path->reada = READA_FORWARD; key.objectid = last; key.offset = 0; @@ -2131,7 +2131,7 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->reada = 1; + path->reada = READA_FORWARD; path->leave_spinning = 1; /* this will setup the path even if it fails to insert the back ref */ ret = insert_inline_extent_backref(trans, fs_info->extent_root, path, @@ -2157,7 +2157,7 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); - path->reada = 1; + path->reada = READA_FORWARD; path->leave_spinning = 1; /* now insert the actual backref */ ret = insert_extent_backref(trans, root->fs_info->extent_root, @@ -2270,7 +2270,7 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans, } again: - path->reada = 1; + path->reada = READA_FORWARD; path->leave_spinning = 1; ret = btrfs_search_slot(trans, root->fs_info->extent_root, &key, path, 0, 1); @@ -3007,9 +3007,9 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, return -ENOMEM; extent_op->flags_to_set = flags; - extent_op->update_flags = 1; - extent_op->update_key = 0; - extent_op->is_data = is_data ? 1 : 0; + extent_op->update_flags = true; + extent_op->update_key = false; + extent_op->is_data = is_data ? true : false; extent_op->level = level; ret = btrfs_add_delayed_extent_op(root->fs_info, trans, bytenr, @@ -6472,7 +6472,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->reada = 1; + path->reada = READA_FORWARD; path->leave_spinning = 1; is_data = owner_objectid >= BTRFS_FIRST_FREE_OBJECTID; @@ -8031,12 +8031,9 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, else memset(&extent_op->key, 0, sizeof(extent_op->key)); extent_op->flags_to_set = flags; - if (skinny_metadata) - extent_op->update_key = 0; - else - extent_op->update_key = 1; - extent_op->update_flags = 1; - extent_op->is_data = 0; + extent_op->update_key = skinny_metadata ? false : true; + extent_op->update_flags = true; + extent_op->is_data = false; extent_op->level = level; ret = btrfs_add_delayed_tree_ref(root->fs_info, trans, @@ -9745,7 +9742,7 @@ int btrfs_read_block_groups(struct btrfs_root *root) path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->reada = 1; + path->reada = READA_FORWARD; cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy); if (btrfs_test_opt(root, SPACE_CACHE) && diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h deleted file mode 100644 index e69de29bb2d1..000000000000 diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 58ece6558430..a67e1c828d0f 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -202,7 +202,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root, } if (bio->bi_iter.bi_size > PAGE_CACHE_SIZE * 8) - path->reada = 2; + path->reada = READA_FORWARD; WARN_ON(bio->bi_vcnt <= 0); @@ -328,7 +328,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, if (search_commit) { path->skip_locking = 1; - path->reada = 2; + path->reada = READA_FORWARD; path->search_commit_root = 1; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 7c5992d0fd31..d468bfd3debc 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2016,7 +2016,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl, return true; } -static struct btrfs_free_space_op free_space_op = { +static const struct btrfs_free_space_op free_space_op = { .recalc_thresholds = recalculate_thresholds, .use_bitmap = use_bitmap, }; diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index f251865eb6f3..33178c490ace 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -37,7 +37,7 @@ struct btrfs_free_space_ctl { int total_bitmaps; int unit; u64 start; - struct btrfs_free_space_op *op; + const struct btrfs_free_space_op *op; void *private; struct mutex cache_writeout_mutex; struct list_head trimming_ranges; diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 767a6056ac45..1951ad69382f 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -48,7 +48,7 @@ static int caching_kthread(void *data) /* Since the commit root is read-only, we can safely skip locking. */ path->skip_locking = 1; path->search_commit_root = 1; - path->reada = 2; + path->reada = READA_FORWARD; key.objectid = BTRFS_FIRST_FREE_OBJECTID; key.offset = 0; @@ -334,7 +334,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl, return true; } -static struct btrfs_free_space_op free_ino_op = { +static const struct btrfs_free_space_op free_ino_op = { .recalc_thresholds = recalculate_thresholds, .use_bitmap = use_bitmap, }; @@ -356,7 +356,7 @@ static bool pinned_use_bitmap(struct btrfs_free_space_ctl *ctl, return false; } -static struct btrfs_free_space_op pinned_free_ino_op = { +static const struct btrfs_free_space_op pinned_free_ino_op = { .recalc_thresholds = pinned_recalc_thresholds, .use_bitmap = pinned_use_bitmap, }; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index bdb0008712c8..f09cf27245f9 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -81,17 +81,16 @@ static const struct inode_operations btrfs_file_inode_operations; static const struct address_space_operations btrfs_aops; static const struct address_space_operations btrfs_symlink_aops; static const struct file_operations btrfs_dir_file_operations; -static struct extent_io_ops btrfs_extent_io_ops; +static const struct extent_io_ops btrfs_extent_io_ops; static struct kmem_cache *btrfs_inode_cachep; -static struct kmem_cache *btrfs_delalloc_work_cachep; struct kmem_cache *btrfs_trans_handle_cachep; struct kmem_cache *btrfs_transaction_cachep; struct kmem_cache *btrfs_path_cachep; struct kmem_cache *btrfs_free_space_cachep; #define S_SHIFT 12 -static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = { +static const unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = { [S_IFREG >> S_SHIFT] = BTRFS_FT_REG_FILE, [S_IFDIR >> S_SHIFT] = BTRFS_FT_DIR, [S_IFCHR >> S_SHIFT] = BTRFS_FT_CHRDEV, @@ -3113,55 +3112,47 @@ static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio, start, (size_t)(end - start + 1)); } -struct delayed_iput { - struct list_head list; - struct inode *inode; -}; - -/* JDM: If this is fs-wide, why can't we add a pointer to - * btrfs_inode instead and avoid the allocation? */ void btrfs_add_delayed_iput(struct inode *inode) { struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; - struct delayed_iput *delayed; + struct btrfs_inode *binode = BTRFS_I(inode); if (atomic_add_unless(&inode->i_count, -1, 1)) return; - delayed = kmalloc(sizeof(*delayed), GFP_NOFS | __GFP_NOFAIL); - delayed->inode = inode; - spin_lock(&fs_info->delayed_iput_lock); - list_add_tail(&delayed->list, &fs_info->delayed_iputs); + if (binode->delayed_iput_count == 0) { + ASSERT(list_empty(&binode->delayed_iput)); + list_add_tail(&binode->delayed_iput, &fs_info->delayed_iputs); + } else { + binode->delayed_iput_count++; + } spin_unlock(&fs_info->delayed_iput_lock); } void btrfs_run_delayed_iputs(struct btrfs_root *root) { - LIST_HEAD(list); struct btrfs_fs_info *fs_info = root->fs_info; - struct delayed_iput *delayed; - int empty; - - spin_lock(&fs_info->delayed_iput_lock); - empty = list_empty(&fs_info->delayed_iputs); - spin_unlock(&fs_info->delayed_iput_lock); - if (empty) - return; down_read(&fs_info->delayed_iput_sem); - spin_lock(&fs_info->delayed_iput_lock); - list_splice_init(&fs_info->delayed_iputs, &list); - spin_unlock(&fs_info->delayed_iput_lock); + while (!list_empty(&fs_info->delayed_iputs)) { + struct btrfs_inode *inode; - while (!list_empty(&list)) { - delayed = list_entry(list.next, struct delayed_iput, list); - list_del(&delayed->list); - iput(delayed->inode); - kfree(delayed); + inode = list_first_entry(&fs_info->delayed_iputs, + struct btrfs_inode, delayed_iput); + if (inode->delayed_iput_count) { + inode->delayed_iput_count--; + list_move_tail(&inode->delayed_iput, + &fs_info->delayed_iputs); + } else { + list_del_init(&inode->delayed_iput); + } + spin_unlock(&fs_info->delayed_iput_lock); + iput(&inode->vfs_inode); + spin_lock(&fs_info->delayed_iput_lock); } - + spin_unlock(&fs_info->delayed_iput_lock); up_read(&root->fs_info->delayed_iput_sem); } @@ -3358,7 +3349,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) ret = -ENOMEM; goto out; } - path->reada = -1; + path->reada = READA_BACK; key.objectid = BTRFS_ORPHAN_OBJECTID; key.type = BTRFS_ORPHAN_ITEM_KEY; @@ -4324,7 +4315,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->reada = -1; + path->reada = READA_BACK; /* * We want to drop from the next block forward in case this new size is @@ -5760,7 +5751,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) if (!path) return -ENOMEM; - path->reada = 1; + path->reada = READA_FORWARD; if (key_type == BTRFS_DIR_INDEX_KEY) { INIT_LIST_HEAD(&ins_list); @@ -6791,7 +6782,7 @@ again: * Chances are we'll be called again, so go ahead and do * readahead */ - path->reada = 1; + path->reada = READA_FORWARD; } ret = btrfs_lookup_file_extent(trans, root, path, @@ -8563,15 +8554,28 @@ int btrfs_readpage(struct file *file, struct page *page) static int btrfs_writepage(struct page *page, struct writeback_control *wbc) { struct extent_io_tree *tree; - + struct inode *inode = page->mapping->host; + int ret; if (current->flags & PF_MEMALLOC) { redirty_page_for_writepage(wbc, page); unlock_page(page); return 0; } + + /* + * If we are under memory pressure we will call this directly from the + * VM, we need to make sure we have the inode referenced for the ordered + * extent. If not just return like we didn't do anything. + */ + if (!igrab(inode)) { + redirty_page_for_writepage(wbc, page); + return AOP_WRITEPAGE_ACTIVATE; + } tree = &BTRFS_I(page->mapping->host)->io_tree; - return extent_write_full_page(tree, page, btrfs_get_extent, wbc); + ret = extent_write_full_page(tree, page, btrfs_get_extent, wbc); + btrfs_add_delayed_iput(inode); + return ret; } static int btrfs_writepages(struct address_space *mapping, @@ -9053,6 +9057,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->dir_index = 0; ei->last_unlink_trans = 0; ei->last_log_commit = 0; + ei->delayed_iput_count = 0; spin_lock_init(&ei->lock); ei->outstanding_extents = 0; @@ -9077,6 +9082,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) mutex_init(&ei->delalloc_mutex); btrfs_ordered_inode_tree_init(&ei->ordered_tree); INIT_LIST_HEAD(&ei->delalloc_inodes); + INIT_LIST_HEAD(&ei->delayed_iput); RB_CLEAR_NODE(&ei->rb_node); return inode; @@ -9181,8 +9187,6 @@ void btrfs_destroy_cachep(void) kmem_cache_destroy(btrfs_path_cachep); if (btrfs_free_space_cachep) kmem_cache_destroy(btrfs_free_space_cachep); - if (btrfs_delalloc_work_cachep) - kmem_cache_destroy(btrfs_delalloc_work_cachep); } int btrfs_init_cachep(void) @@ -9217,13 +9221,6 @@ int btrfs_init_cachep(void) if (!btrfs_free_space_cachep) goto fail; - btrfs_delalloc_work_cachep = kmem_cache_create("btrfs_delalloc_work", - sizeof(struct btrfs_delalloc_work), 0, - SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, - NULL); - if (!btrfs_delalloc_work_cachep) - goto fail; - return 0; fail: btrfs_destroy_cachep(); @@ -9464,7 +9461,7 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode, { struct btrfs_delalloc_work *work; - work = kmem_cache_zalloc(btrfs_delalloc_work_cachep, GFP_NOFS); + work = kmalloc(sizeof(*work), GFP_NOFS); if (!work) return NULL; @@ -9482,7 +9479,7 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode, void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work) { wait_for_completion(&work->completion); - kmem_cache_free(btrfs_delalloc_work_cachep, work); + kfree(work); } /* @@ -10047,7 +10044,7 @@ static const struct file_operations btrfs_dir_file_operations = { .fsync = btrfs_sync_file, }; -static struct extent_io_ops btrfs_extent_io_ops = { +static const struct extent_io_ops btrfs_extent_io_ops = { .fill_delalloc = run_delalloc_range, .submit_bio_hook = btrfs_submit_bio_hook, .merge_bio_hook = btrfs_merge_bio_hook, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8bbecdaf58a3..f8519b866c0a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -655,22 +655,28 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state)) return -EINVAL; + pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS); + if (!pending_snapshot) + return -ENOMEM; + + pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item), + GFP_NOFS); + pending_snapshot->path = btrfs_alloc_path(); + if (!pending_snapshot->root_item || !pending_snapshot->path) { + ret = -ENOMEM; + goto free_pending; + } + atomic_inc(&root->will_be_snapshoted); smp_mb__after_atomic(); btrfs_wait_for_no_snapshoting_writes(root); ret = btrfs_start_delalloc_inodes(root, 0); if (ret) - goto out; + goto dec_and_free; btrfs_wait_ordered_extents(root, -1); - pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS); - if (!pending_snapshot) { - ret = -ENOMEM; - goto out; - } - btrfs_init_block_rsv(&pending_snapshot->block_rsv, BTRFS_BLOCK_RSV_TEMP); /* @@ -686,7 +692,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, &pending_snapshot->qgroup_reserved, false); if (ret) - goto free; + goto dec_and_free; pending_snapshot->dentry = dentry; pending_snapshot->root = root; @@ -737,11 +743,14 @@ fail: btrfs_subvolume_release_metadata(BTRFS_I(dir)->root, &pending_snapshot->block_rsv, pending_snapshot->qgroup_reserved); -free: - kfree(pending_snapshot); -out: +dec_and_free: if (atomic_dec_and_test(&root->will_be_snapshoted)) wake_up_atomic_t(&root->will_be_snapshoted); +free_pending: + kfree(pending_snapshot->root_item); + btrfs_free_path(pending_snapshot->path); + kfree(pending_snapshot); + return ret; } @@ -3478,7 +3487,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode, return ret; } - path->reada = 2; + path->reada = READA_FORWARD; /* clone data */ key.objectid = btrfs_ino(src); key.type = BTRFS_EXTENT_DATA_KEY; @@ -5286,7 +5295,7 @@ out_unlock: static int btrfs_ioctl_get_supported_features(struct file *file, void __user *arg) { - static struct btrfs_ioctl_feature_flags features[3] = { + static const struct btrfs_ioctl_feature_flags features[3] = { INIT_FEATURE_FLAGS(SUPP), INIT_FEATURE_FLAGS(SAFE_SET), INIT_FEATURE_FLAGS(SAFE_CLEAR) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index b4ca5454ef1a..ef6d8fc85853 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -708,8 +708,8 @@ struct backref_node *build_backref_tree(struct reloc_control *rc, err = -ENOMEM; goto out; } - path1->reada = 1; - path2->reada = 2; + path1->reada = READA_FORWARD; + path2->reada = READA_FORWARD; node = alloc_backref_node(cache); if (!node) { @@ -2130,7 +2130,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->reada = 1; + path->reada = READA_FORWARD; reloc_root = root->reloc_root; root_item = &reloc_root->root_item; @@ -3527,7 +3527,7 @@ static int find_data_references(struct reloc_control *rc, path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->reada = 1; + path->reada = READA_FORWARD; root = read_fs_root(rc->extent_root->fs_info, ref_root); if (IS_ERR(root)) { @@ -3917,7 +3917,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->reada = 1; + path->reada = READA_FORWARD; ret = prepare_to_relocate(rc); if (ret) { @@ -4343,7 +4343,7 @@ int btrfs_recover_relocation(struct btrfs_root *root) path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->reada = -1; + path->reada = READA_BACK; key.objectid = BTRFS_TREE_RELOC_OBJECTID; key.type = BTRFS_ROOT_ITEM_KEY; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 69987150ddfa..dbfbfb3b86b5 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3507,7 +3507,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (!path) return -ENOMEM; - path->reada = 2; + path->reada = READA_FORWARD; path->search_commit_root = 1; path->skip_locking = 1; @@ -3735,27 +3735,27 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, if (fs_info->scrub_workers_refcnt == 0) { if (is_dev_replace) fs_info->scrub_workers = - btrfs_alloc_workqueue("btrfs-scrub", flags, + btrfs_alloc_workqueue("scrub", flags, 1, 4); else fs_info->scrub_workers = - btrfs_alloc_workqueue("btrfs-scrub", flags, + btrfs_alloc_workqueue("scrub", flags, max_active, 4); if (!fs_info->scrub_workers) goto fail_scrub_workers; fs_info->scrub_wr_completion_workers = - btrfs_alloc_workqueue("btrfs-scrubwrc", flags, + btrfs_alloc_workqueue("scrubwrc", flags, max_active, 2); if (!fs_info->scrub_wr_completion_workers) goto fail_scrub_wr_completion_workers; fs_info->scrub_nocow_workers = - btrfs_alloc_workqueue("btrfs-scrubnc", flags, 1, 0); + btrfs_alloc_workqueue("scrubnc", flags, 1, 0); if (!fs_info->scrub_nocow_workers) goto fail_scrub_nocow_workers; fs_info->scrub_parity_workers = - btrfs_alloc_workqueue("btrfs-scrubparity", flags, + btrfs_alloc_workqueue("scrubparity", flags, max_active, 2); if (!fs_info->scrub_parity_workers) goto fail_scrub_parity_workers; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 9153d54d27c8..ff15087052f5 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -310,7 +310,7 @@ enum { Opt_err, }; -static match_table_t tokens = { +static const match_table_t tokens = { {Opt_degraded, "degraded"}, {Opt_subvol, "subvol=%s"}, {Opt_subvolid, "subvolid=%s"}, @@ -1991,6 +1991,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) * there are other factors that may change the result (like a new metadata * chunk). * + * If metadata is exhausted, f_bavail will be 0. + * * FIXME: not accurate for mixed block groups, total and free/used are ok, * available appears slightly larger. */ @@ -2002,11 +2004,13 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) struct btrfs_space_info *found; u64 total_used = 0; u64 total_free_data = 0; + u64 total_free_meta = 0; int bits = dentry->d_sb->s_blocksize_bits; __be32 *fsid = (__be32 *)fs_info->fsid; unsigned factor = 1; struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv; int ret; + u64 thresh = 0; /* * holding chunk_muext to avoid allocating new chunks, holding @@ -2032,6 +2036,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) } } } + if (found->flags & BTRFS_BLOCK_GROUP_METADATA) + total_free_meta += found->disk_total - found->disk_used; total_used += found->disk_used; } @@ -2054,6 +2060,24 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail += div_u64(total_free_data, factor); buf->f_bavail = buf->f_bavail >> bits; + /* + * We calculate the remaining metadata space minus global reserve. If + * this is (supposedly) smaller than zero, there's no space. But this + * does not hold in practice, the exhausted state happens where's still + * some positive delta. So we apply some guesswork and compare the + * delta to a 4M threshold. (Practically observed delta was ~2M.) + * + * We probably cannot calculate the exact threshold value because this + * depends on the internal reservations requested by various + * operations, so some operations that consume a few metadata will + * succeed even if the Avail is zero. But this is better than the other + * way around. + */ + thresh = 4 * 1024 * 1024; + + if (total_free_meta - thresh < block_rsv->size) + buf->f_bavail = 0; + buf->f_type = BTRFS_SUPER_MAGIC; buf->f_bsize = dentry->d_sb->s_blocksize; buf->f_namelen = BTRFS_NAME_LEN; diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c index cd3e300b9ba5..e37d55ecdf1f 100644 --- a/fs/btrfs/tests/free-space-tests.c +++ b/fs/btrfs/tests/free-space-tests.c @@ -410,9 +410,11 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache) int ret; u64 offset; u64 max_extent_size; - - bool (*use_bitmap_op)(struct btrfs_free_space_ctl *, - struct btrfs_free_space *); + const struct btrfs_free_space_op test_free_space_ops = { + .recalc_thresholds = cache->free_space_ctl->op->recalc_thresholds, + .use_bitmap = test_use_bitmap, + }; + const struct btrfs_free_space_op *orig_free_space_ops; test_msg("Running space stealing from bitmap to extent\n"); @@ -434,8 +436,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache) * that forces use of bitmaps as soon as we have at least 1 * extent entry. */ - use_bitmap_op = cache->free_space_ctl->op->use_bitmap; - cache->free_space_ctl->op->use_bitmap = test_use_bitmap; + orig_free_space_ops = cache->free_space_ctl->op; + cache->free_space_ctl->op = &test_free_space_ops; /* * Extent entry covering free space range [128Mb - 256Kb, 128Mb - 128Kb[ @@ -842,7 +844,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache) if (ret) return ret; - cache->free_space_ctl->op->use_bitmap = use_bitmap_op; + cache->free_space_ctl->op = orig_free_space_ops; __btrfs_remove_free_space_cache(cache->free_space_ctl); return 0; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index f85ccf634ca1..34961f02e58c 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1336,17 +1336,11 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, u64 root_flags; uuid_le new_uuid; - path = btrfs_alloc_path(); - if (!path) { - pending->error = -ENOMEM; - return 0; - } + ASSERT(pending->path); + path = pending->path; - new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS); - if (!new_root_item) { - pending->error = -ENOMEM; - goto root_item_alloc_fail; - } + ASSERT(pending->root_item); + new_root_item = pending->root_item; pending->error = btrfs_find_free_objectid(tree_root, &objectid); if (pending->error) @@ -1579,8 +1573,10 @@ clear_skip_qgroup: btrfs_clear_skip_qgroup(trans); no_free_objectid: kfree(new_root_item); -root_item_alloc_fail: + pending->root_item = NULL; btrfs_free_path(path); + pending->path = NULL; + return ret; } diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 64c8221b6165..72be51f7ca2f 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -137,8 +137,10 @@ struct btrfs_pending_snapshot { struct dentry *dentry; struct inode *dir; struct btrfs_root *root; + struct btrfs_root_item *root_item; struct btrfs_root *snap; struct btrfs_qgroup_inherit *inherit; + struct btrfs_path *path; /* block reservation for the operation */ struct btrfs_block_rsv block_rsv; u64 qgroup_reserved; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a114b7bb87a0..2fa5ba814120 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1103,7 +1103,7 @@ int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start, path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->reada = 2; + path->reada = READA_FORWARD; key.objectid = device->devid; key.offset = start; @@ -1272,7 +1272,7 @@ again: goto out; } - path->reada = 2; + path->reada = READA_FORWARD; path->search_commit_root = 1; path->skip_locking = 1; @@ -3724,14 +3724,6 @@ int btrfs_balance(struct btrfs_balance_control *bctl, goto out; } - /* allow dup'ed data chunks only in mixed mode */ - if (!mixed && (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) && - (bctl->data.target & BTRFS_BLOCK_GROUP_DUP)) { - btrfs_err(fs_info, "dup for data is not allowed"); - ret = -EINVAL; - goto out; - } - /* allow to reduce meta or sys integrity only if force set */ allowed = BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10 | @@ -3757,6 +3749,13 @@ int btrfs_balance(struct btrfs_balance_control *bctl, } } while (read_seqretry(&fs_info->profiles_lock, seq)); + if (btrfs_get_num_tolerated_disk_barrier_failures(bctl->meta.target) < + btrfs_get_num_tolerated_disk_barrier_failures(bctl->data.target)) { + btrfs_warn(fs_info, + "metatdata profile 0x%llx has lower redundancy than data profile 0x%llx", + bctl->meta.target, bctl->data.target); + } + if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) { fs_info->num_tolerated_disk_barrier_failures = min( btrfs_calc_num_tolerated_disk_barrier_failures(fs_info), @@ -4269,7 +4268,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size) if (!path) return -ENOMEM; - path->reada = 2; + path->reada = READA_FORWARD; lock_chunks(root); @@ -6526,6 +6525,14 @@ int btrfs_read_sys_array(struct btrfs_root *root) goto out_short_read; num_stripes = btrfs_chunk_num_stripes(sb, chunk); + if (!num_stripes) { + printk(KERN_ERR + "BTRFS: invalid number of stripes %u in sys_array at offset %u\n", + num_stripes, cur_offset); + ret = -EIO; + break; + } + len = btrfs_chunk_item_size(num_stripes); if (cur_offset + len > array_size) goto out_short_read; @@ -6534,6 +6541,9 @@ int btrfs_read_sys_array(struct btrfs_root *root) if (ret) break; } else { + printk(KERN_ERR + "BTRFS: unexpected item type %u in sys_array at offset %u\n", + (u32)key.type, cur_offset); ret = -EIO; break; } diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 24e8ff722730..608552ed89c0 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -283,7 +283,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->reada = 2; + path->reada = READA_FORWARD; /* search for our xattrs */ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);