Merge branch 'for-chris' of git://git.jan-o-sch.net/btrfs-unstable into for-linus

Conflicts:
	fs/btrfs/ulist.h
Signed-off-by: Chris Mason <chris.mason@oracle.com>

fs/btrfs/backref.h

@@ -58,7 +58,8 @@ int paths_from_inode(u64 inum, struct inode_fs_paths *ipath);
 
 int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
 				struct btrfs_fs_info *fs_info, u64 bytenr,
-				u64 num_bytes, u64 seq, struct ulist **roots);
+				u64 delayed_ref_seq, u64 time_seq,
+				struct ulist **roots);
 
 struct btrfs_data_container *init_data_container(u32 total_bytes);
 struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,

fs/btrfs/ctree.h

@@ -1140,6 +1140,15 @@ struct btrfs_fs_info {
 	spinlock_t delayed_iput_lock;
 	struct list_head delayed_iputs;
 
+	/* this protects tree_mod_seq_list */
+	spinlock_t tree_mod_seq_lock;
+	atomic_t tree_mod_seq;
+	struct list_head tree_mod_seq_list;
+
+	/* this protects tree_mod_log */
+	rwlock_t tree_mod_log_lock;
+	struct rb_root tree_mod_log;
+
 	atomic_t nr_async_submits;
 	atomic_t async_submit_draining;
 	atomic_t nr_async_bios;
@@ -2537,11 +2546,11 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 					struct btrfs_root *root, u32 blocksize,
 					u64 parent, u64 root_objectid,
 					struct btrfs_disk_key *key, int level,
-					u64 hint, u64 empty_size, int for_cow);
+					u64 hint, u64 empty_size);
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct extent_buffer *buf,
-			   u64 parent, int last_ref, int for_cow);
+			   u64 parent, int last_ref);
 struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans,
 					    struct btrfs_root *root,
 					    u64 bytenr, u32 blocksize,
@@ -2700,6 +2709,8 @@ int btrfs_duplicate_item(struct btrfs_trans_handle *trans,
 int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
 		      *root, struct btrfs_key *key, struct btrfs_path *p, int
 		      ins_len, int cow);
+int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key,
+			  struct btrfs_path *p, u64 time_seq);
 int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root, struct extent_buffer *parent,
 		       int start_slot, int cache_only, u64 *last_ret,
@@ -3139,4 +3150,23 @@ void btrfs_reada_detach(void *handle);
 int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
 			 u64 start, int err);
 
+/* delayed seq elem */
+struct seq_list {
+	struct list_head list;
+	u64 seq;
+	u32 flags;
+};
+
+void btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
+			    struct seq_list *elem);
+void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
+			    struct seq_list *elem);
+
+static inline int is_fstree(u64 rootid)
+{
+	if (rootid == BTRFS_FS_TREE_OBJECTID ||
+	    (s64)rootid >= (s64)BTRFS_FIRST_FREE_OBJECTID)
+		return 1;
+	return 0;
+}
 #endif

fs/btrfs/delayed-ref.c

@@ -525,7 +525,7 @@ static noinline void add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	ref->is_head = 0;
 	ref->in_tree = 1;
 
-	if (need_ref_seq(for_cow, ref_root))
+	if (is_fstree(ref_root))
 		seq = inc_delayed_seq(delayed_refs);
 	ref->seq = seq;
 
@@ -584,7 +584,7 @@ static noinline void add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 	ref->is_head = 0;
 	ref->in_tree = 1;
 
-	if (need_ref_seq(for_cow, ref_root))
+	if (is_fstree(ref_root))
 		seq = inc_delayed_seq(delayed_refs);
 	ref->seq = seq;
 
@@ -658,10 +658,11 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	add_delayed_tree_ref(fs_info, trans, &ref->node, bytenr,
 				   num_bytes, parent, ref_root, level, action,
 				   for_cow);
-	if (!need_ref_seq(for_cow, ref_root) &&
+	if (!is_fstree(ref_root) &&
 	    waitqueue_active(&delayed_refs->seq_wait))
 		wake_up(&delayed_refs->seq_wait);
 	spin_unlock(&delayed_refs->lock);
+
 	return 0;
 }
 
@@ -706,10 +707,11 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 	add_delayed_data_ref(fs_info, trans, &ref->node, bytenr,
 				   num_bytes, parent, ref_root, owner, offset,
 				   action, for_cow);
-	if (!need_ref_seq(for_cow, ref_root) &&
+	if (!is_fstree(ref_root) &&
 	    waitqueue_active(&delayed_refs->seq_wait))
 		wake_up(&delayed_refs->seq_wait);
 	spin_unlock(&delayed_refs->lock);
+
 	return 0;
 }
 

fs/btrfs/delayed-ref.h

@@ -195,11 +195,6 @@ int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
 int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
 			   struct list_head *cluster, u64 search_start);
 
-struct seq_list {
-	struct list_head list;
-	u64 seq;
-};
-
 static inline u64 inc_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs)
 {
 	assert_spin_locked(&delayed_refs->lock);
@@ -229,25 +224,6 @@ btrfs_put_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs,
 int btrfs_check_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs,
 			    u64 seq);
 
-/*
- * delayed refs with a ref_seq > 0 must be held back during backref walking.
- * this only applies to items in one of the fs-trees. for_cow items never need
- * to be held back, so they won't get a ref_seq number.
- */
-static inline int need_ref_seq(int for_cow, u64 rootid)
-{
-	if (for_cow)
-		return 0;
-
-	if (rootid == BTRFS_FS_TREE_OBJECTID)
-		return 1;
-
-	if ((s64)rootid >= (s64)BTRFS_FIRST_FREE_OBJECTID)
-		return 1;
-
-	return 0;
-}
-
 /*
  * a node might live in a head or a regular ref, this lets you
  * test for the proper type to use.

fs/btrfs/disk-io.c

@@ -1252,7 +1252,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 
 	leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
 				      BTRFS_TREE_LOG_OBJECTID, NULL,
-				      0, 0, 0, 0);
+				      0, 0, 0);
 	if (IS_ERR(leaf)) {
 		kfree(root);
 		return ERR_CAST(leaf);
@@ -1914,11 +1914,14 @@ int open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->delayed_iput_lock);
 	spin_lock_init(&fs_info->defrag_inodes_lock);
 	spin_lock_init(&fs_info->free_chunk_lock);
+	spin_lock_init(&fs_info->tree_mod_seq_lock);
+	rwlock_init(&fs_info->tree_mod_log_lock);
 	mutex_init(&fs_info->reloc_mutex);
 
 	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);
 	btrfs_mapping_init(&fs_info->mapping_tree);
 	btrfs_init_block_rsv(&fs_info->global_block_rsv);
 	btrfs_init_block_rsv(&fs_info->delalloc_block_rsv);
@@ -1931,12 +1934,14 @@ int open_ctree(struct super_block *sb,
 	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->tree_mod_seq, 0);
 	fs_info->sb = sb;
 	fs_info->max_inline = 8192 * 1024;
 	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;
 
 	/* readahead state */
 	INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);

fs/btrfs/extent-tree.c

@@ -5218,7 +5218,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct extent_buffer *buf,
-			   u64 parent, int last_ref, int for_cow)
+			   u64 parent, int last_ref)
 {
 	struct btrfs_block_group_cache *cache = NULL;
 	int ret;
@@ -5228,7 +5228,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 					buf->start, buf->len,
 					parent, root->root_key.objectid,
 					btrfs_header_level(buf),
-					BTRFS_DROP_DELAYED_REF, NULL, for_cow);
+					BTRFS_DROP_DELAYED_REF, NULL, 0);
 		BUG_ON(ret); /* -ENOMEM */
 	}
 
@@ -6250,7 +6250,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 					struct btrfs_root *root, u32 blocksize,
 					u64 parent, u64 root_objectid,
 					struct btrfs_disk_key *key, int level,
-					u64 hint, u64 empty_size, int for_cow)
+					u64 hint, u64 empty_size)
 {
 	struct btrfs_key ins;
 	struct btrfs_block_rsv *block_rsv;
@@ -6298,7 +6298,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 					ins.objectid,
 					ins.offset, parent, root_objectid,
 					level, BTRFS_ADD_DELAYED_EXTENT,
-					extent_op, for_cow);
+					extent_op, 0);
 		BUG_ON(ret); /* -ENOMEM */
 	}
 	return buf;
@@ -6716,7 +6716,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			       btrfs_header_owner(path->nodes[level + 1]));
 	}
 
-	btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1, 0);
+	btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1);
 out:
 	wc->refs[level] = 0;
 	wc->flags[level] = 0;

fs/btrfs/extent_io.c

@@ -3924,6 +3924,7 @@ static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
 	eb->start = start;
 	eb->len = len;
 	eb->tree = tree;
+	eb->bflags = 0;
 	rwlock_init(&eb->lock);
 	atomic_set(&eb->write_locks, 0);
 	atomic_set(&eb->read_locks, 0);
@@ -3961,6 +3962,60 @@ static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
 	return eb;
 }
 
+struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
+{
+	unsigned long i;
+	struct page *p;
+	struct extent_buffer *new;
+	unsigned long num_pages = num_extent_pages(src->start, src->len);
+
+	new = __alloc_extent_buffer(NULL, src->start, src->len, GFP_ATOMIC);
+	if (new == NULL)
+		return NULL;
+
+	for (i = 0; i < num_pages; i++) {
+		p = alloc_page(GFP_ATOMIC);
+		BUG_ON(!p);
+		attach_extent_buffer_page(new, p);
+		WARN_ON(PageDirty(p));
+		SetPageUptodate(p);
+		new->pages[i] = p;
+	}
+
+	copy_extent_buffer(new, src, 0, 0, src->len);
+	set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags);
+	set_bit(EXTENT_BUFFER_DUMMY, &new->bflags);
+
+	return new;
+}
+
+struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len)
+{
+	struct extent_buffer *eb;
+	unsigned long num_pages = num_extent_pages(0, len);
+	unsigned long i;
+
+	eb = __alloc_extent_buffer(NULL, start, len, GFP_ATOMIC);
+	if (!eb)
+		return NULL;
+
+	for (i = 0; i < num_pages; i++) {
+		eb->pages[i] = alloc_page(GFP_ATOMIC);
+		if (!eb->pages[i])
+			goto err;
+	}
+	set_extent_buffer_uptodate(eb);
+	btrfs_set_header_nritems(eb, 0);
+	set_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+
+	return eb;
+err:
+	for (i--; i > 0; i--)
+		__free_page(eb->pages[i]);
+	__free_extent_buffer(eb);
+	return NULL;
+}
+
 static int extent_buffer_under_io(struct extent_buffer *eb)
 {
 	return (atomic_read(&eb->io_pages) ||
@@ -3977,6 +4032,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb,
 	unsigned long index;
 	unsigned long num_pages;
 	struct page *page;
+	int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
 
 	BUG_ON(extent_buffer_under_io(eb));
 
@@ -3988,7 +4044,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb,
 	do {
 		index--;
 		page = extent_buffer_page(eb, index);
-		if (page) {
+		if (page && mapped) {
 			spin_lock(&page->mapping->private_lock);
 			/*
 			 * We do this since we'll remove the pages after we've
@@ -4013,6 +4069,8 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb,
 			}
 			spin_unlock(&page->mapping->private_lock);
 
+		}
+		if (page) {
 			/* One for when we alloced the page */
 			page_cache_release(page);
 		}
@@ -4231,14 +4289,18 @@ static void release_extent_buffer(struct extent_buffer *eb, gfp_t mask)
 {
 	WARN_ON(atomic_read(&eb->refs) == 0);
 	if (atomic_dec_and_test(&eb->refs)) {
-		struct extent_io_tree *tree = eb->tree;
+		if (test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags)) {
+			spin_unlock(&eb->refs_lock);
+		} else {
+			struct extent_io_tree *tree = eb->tree;
 
-		spin_unlock(&eb->refs_lock);
+			spin_unlock(&eb->refs_lock);
 
-		spin_lock(&tree->buffer_lock);
-		radix_tree_delete(&tree->buffer,
-				  eb->start >> PAGE_CACHE_SHIFT);
-		spin_unlock(&tree->buffer_lock);
+			spin_lock(&tree->buffer_lock);
+			radix_tree_delete(&tree->buffer,
+					  eb->start >> PAGE_CACHE_SHIFT);
+			spin_unlock(&tree->buffer_lock);
+		}
 
 		/* Should be safe to release our pages at this point */
 		btrfs_release_extent_buffer_page(eb, 0);
@@ -4255,6 +4317,10 @@ void free_extent_buffer(struct extent_buffer *eb)
 		return;
 
 	spin_lock(&eb->refs_lock);
+	if (atomic_read(&eb->refs) == 2 &&
+	    test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))
+		atomic_dec(&eb->refs);
+
 	if (atomic_read(&eb->refs) == 2 &&
 	    test_bit(EXTENT_BUFFER_STALE, &eb->bflags) &&
 	    !extent_buffer_under_io(eb) &&

fs/btrfs/extent_io.h

@@ -39,6 +39,7 @@
 #define EXTENT_BUFFER_STALE 6
 #define EXTENT_BUFFER_WRITEBACK 7
 #define EXTENT_BUFFER_IOERR 8
+#define EXTENT_BUFFER_DUMMY 9
 
 /* these are flags for extent_clear_unlock_delalloc */
 #define EXTENT_CLEAR_UNLOCK_PAGE 0x1
@@ -264,6 +265,8 @@ void set_page_extent_mapped(struct page *page);
 
 struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 					  u64 start, unsigned long len);
+struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len);
+struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src);
 struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
 					 u64 start, unsigned long len);
 void free_extent_buffer(struct extent_buffer *eb);

fs/btrfs/ioctl.c

@@ -368,7 +368,7 @@ static noinline int create_subvol(struct btrfs_root *root,
 		return PTR_ERR(trans);
 
 	leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
-				      0, objectid, NULL, 0, 0, 0, 0);
+				      0, objectid, NULL, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
 		goto fail;

fs/btrfs/transaction.c

@@ -56,48 +56,49 @@ static noinline void switch_commit_root(struct btrfs_root *root)
 static noinline int join_transaction(struct btrfs_root *root, int nofail)
 {
 	struct btrfs_transaction *cur_trans;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 
-	spin_lock(&root->fs_info->trans_lock);
+	spin_lock(&fs_info->trans_lock);
 loop:
 	/* The file system has been taken offline. No new transactions. */
-	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
-		spin_unlock(&root->fs_info->trans_lock);
+	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		spin_unlock(&fs_info->trans_lock);
 		return -EROFS;
 	}
 
-	if (root->fs_info->trans_no_join) {
+	if (fs_info->trans_no_join) {
 		if (!nofail) {
-			spin_unlock(&root->fs_info->trans_lock);
+			spin_unlock(&fs_info->trans_lock);
 			return -EBUSY;
 		}
 	}
 
-	cur_trans = root->fs_info->running_transaction;
+	cur_trans = fs_info->running_transaction;
 	if (cur_trans) {
 		if (cur_trans->aborted) {
-			spin_unlock(&root->fs_info->trans_lock);
+			spin_unlock(&fs_info->trans_lock);
 			return cur_trans->aborted;
 		}
 		atomic_inc(&cur_trans->use_count);
 		atomic_inc(&cur_trans->num_writers);
 		cur_trans->num_joined++;
-		spin_unlock(&root->fs_info->trans_lock);
+		spin_unlock(&fs_info->trans_lock);
 		return 0;
 	}
-	spin_unlock(&root->fs_info->trans_lock);
+	spin_unlock(&fs_info->trans_lock);
 
 	cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS);
 	if (!cur_trans)
 		return -ENOMEM;
 
-	spin_lock(&root->fs_info->trans_lock);
-	if (root->fs_info->running_transaction) {
+	spin_lock(&fs_info->trans_lock);
+	if (fs_info->running_transaction) {
 		/*
 		 * someone started a transaction after we unlocked.  Make sure
 		 * to redo the trans_no_join checks above
 		 */
 		kmem_cache_free(btrfs_transaction_cachep, cur_trans);
-		cur_trans = root->fs_info->running_transaction;
+		cur_trans = fs_info->running_transaction;
 		goto loop;
 	}
 
@@ -122,20 +123,38 @@ static noinline int join_transaction(struct btrfs_root *root, int nofail)
 	cur_trans->delayed_refs.flushing = 0;
 	cur_trans->delayed_refs.run_delayed_start = 0;
 	cur_trans->delayed_refs.seq = 1;
+
+	/*
+	 * although the tree mod log is per file system and not per transaction,
+	 * the log must never go across transaction boundaries.
+	 */
+	smp_mb();
+	if (!list_empty(&fs_info->tree_mod_seq_list)) {
+		printk(KERN_ERR "btrfs: tree_mod_seq_list not empty when "
+			"creating a fresh transaction\n");
+		WARN_ON(1);
+	}
+	if (!RB_EMPTY_ROOT(&fs_info->tree_mod_log)) {
+		printk(KERN_ERR "btrfs: tree_mod_log rb tree not empty when "
+			"creating a fresh transaction\n");
+		WARN_ON(1);
+	}
+	atomic_set(&fs_info->tree_mod_seq, 0);
+
 	init_waitqueue_head(&cur_trans->delayed_refs.seq_wait);
 	spin_lock_init(&cur_trans->commit_lock);
 	spin_lock_init(&cur_trans->delayed_refs.lock);
 	INIT_LIST_HEAD(&cur_trans->delayed_refs.seq_head);
 
 	INIT_LIST_HEAD(&cur_trans->pending_snapshots);
-	list_add_tail(&cur_trans->list, &root->fs_info->trans_list);
+	list_add_tail(&cur_trans->list, &fs_info->trans_list);
 	extent_io_tree_init(&cur_trans->dirty_pages,
-			     root->fs_info->btree_inode->i_mapping);
-	root->fs_info->generation++;
-	cur_trans->transid = root->fs_info->generation;
-	root->fs_info->running_transaction = cur_trans;
+			     fs_info->btree_inode->i_mapping);
+	fs_info->generation++;
+	cur_trans->transid = fs_info->generation;
+	fs_info->running_transaction = cur_trans;
 	cur_trans->aborted = 0;
-	spin_unlock(&root->fs_info->trans_lock);
+	spin_unlock(&fs_info->trans_lock);
 
 	return 0;
 }

fs/btrfs/ulist.c

@@ -23,9 +23,9 @@
  *
  * ulist = ulist_alloc();
  * ulist_add(ulist, root);
- * elem = NULL;
+ * ULIST_ITER_INIT(&uiter);
  *
- * while ((elem = ulist_next(ulist, elem)) {
+ * while ((elem = ulist_next(ulist, &uiter)) {
  * 	for (all child nodes n in elem)
  *		ulist_add(ulist, n);
  *	do something useful with the node;
@@ -145,12 +145,21 @@ EXPORT_SYMBOL(ulist_free);
  */
 int ulist_add(struct ulist *ulist, u64 val, unsigned long aux,
 	      gfp_t gfp_mask)
+{
+	return ulist_add_merge(ulist, val, aux, NULL, gfp_mask);
+}
+
+int ulist_add_merge(struct ulist *ulist, u64 val, unsigned long aux,
+		    unsigned long *old_aux, gfp_t gfp_mask)
 {
 	int i;
 
 	for (i = 0; i < ulist->nnodes; ++i) {
-		if (ulist->nodes[i].val == val)
+		if (ulist->nodes[i].val == val) {
+			if (old_aux)
+				*old_aux = ulist->nodes[i].aux;
 			return 0;
+		}
 	}
 
 	if (ulist->nnodes >= ulist->nodes_alloced) {
@@ -188,33 +197,26 @@ EXPORT_SYMBOL(ulist_add);
 /**
  * ulist_next - iterate ulist
  * @ulist:	ulist to iterate
- * @prev:	previously returned element or %NULL to start iteration
+ * @uiter:	iterator variable, initialized with ULIST_ITER_INIT(&iterator)
  *
  * Note: locking must be provided by the caller. In case of rwlocks only read
  *       locking is needed
  *
- * This function is used to iterate an ulist. The iteration is started with
- * @prev = %NULL. It returns the next element from the ulist or %NULL when the
+ * This function is used to iterate an ulist.
+ * It returns the next element from the ulist or %NULL when the
  * end is reached. No guarantee is made with respect to the order in which
  * the elements are returned. They might neither be returned in order of
  * addition nor in ascending order.
  * It is allowed to call ulist_add during an enumeration. Newly added items
  * are guaranteed to show up in the running enumeration.
  */
-struct ulist_node *ulist_next(struct ulist *ulist, struct ulist_node *prev)
+struct ulist_node *ulist_next(struct ulist *ulist, struct ulist_iterator *uiter)
 {
-	int next;
-
 	if (ulist->nnodes == 0)
 		return NULL;
-
-	if (!prev)
-		return &ulist->nodes[0];
-
-	next = (prev - ulist->nodes) + 1;
-	if (next < 0 || next >= ulist->nnodes)
+	if (uiter->i < 0 || uiter->i >= ulist->nnodes)
 		return NULL;
 
-	return &ulist->nodes[next];
+	return &ulist->nodes[uiter->i++];
 }
 EXPORT_SYMBOL(ulist_next);

fs/btrfs/ulist.h

@@ -24,6 +24,10 @@
  */
 #define ULIST_SIZE 16
 
+struct ulist_iterator {
+	int i;
+};
+
 /*
  * element of the list
  */
@@ -61,7 +65,13 @@ void ulist_fini(struct ulist *ulist);
 void ulist_reinit(struct ulist *ulist);
 struct ulist *ulist_alloc(gfp_t gfp_mask);
 void ulist_free(struct ulist *ulist);
-int ulist_add(struct ulist *ulist, u64 val, unsigned long aux, gfp_t gfp_mask);
-struct ulist_node *ulist_next(struct ulist *ulist, struct ulist_node *prev);
+int ulist_add(struct ulist *ulist, u64 val, unsigned long aux,
+	      gfp_t gfp_mask);
+int ulist_add_merge(struct ulist *ulist, u64 val, unsigned long aux,
+		    unsigned long *old_aux, gfp_t gfp_mask);
+struct ulist_node *ulist_next(struct ulist *ulist,
+			      struct ulist_iterator *uiter);
+
+#define ULIST_ITER_INIT(uiter) ((uiter)->i = 0)
 
 #endif