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

fs/btrfs/Makefile

@@ -8,6 +8,6 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
 	   export.o tree-log.o free-space-cache.o zlib.o lzo.o \
 	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
-	   reada.o backref.o
+	   reada.o backref.o ulist.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o

fs/btrfs/backref.h

@@ -20,6 +20,7 @@
 #define __BTRFS_BACKREF__
 
 #include "ioctl.h"
+#include "ulist.h"
 
 struct inode_fs_paths {
 	struct btrfs_path		*btrfs_path;
@@ -54,6 +55,10 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 
 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);
+
 struct btrfs_data_container *init_data_container(u32 total_bytes);
 struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
 					struct btrfs_path *path);

fs/btrfs/ctree.c

@@ -240,7 +240,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 
 	cow = btrfs_alloc_free_block(trans, root, buf->len, 0,
 				     new_root_objectid, &disk_key, level,
-				     buf->start, 0);
+				     buf->start, 0, 1);
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
 
@@ -261,9 +261,9 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 
 	WARN_ON(btrfs_header_generation(buf) > trans->transid);
 	if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID)
-		ret = btrfs_inc_ref(trans, root, cow, 1);
+		ret = btrfs_inc_ref(trans, root, cow, 1, 1);
 	else
-		ret = btrfs_inc_ref(trans, root, cow, 0);
+		ret = btrfs_inc_ref(trans, root, cow, 0, 1);
 
 	if (ret)
 		return ret;
@@ -350,14 +350,14 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 		if ((owner == root->root_key.objectid ||
 		     root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) &&
 		    !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) {
-			ret = btrfs_inc_ref(trans, root, buf, 1);
+			ret = btrfs_inc_ref(trans, root, buf, 1, 1);
 			BUG_ON(ret);
 
 			if (root->root_key.objectid ==
 			    BTRFS_TREE_RELOC_OBJECTID) {
-				ret = btrfs_dec_ref(trans, root, buf, 0);
+				ret = btrfs_dec_ref(trans, root, buf, 0, 1);
 				BUG_ON(ret);
-				ret = btrfs_inc_ref(trans, root, cow, 1);
+				ret = btrfs_inc_ref(trans, root, cow, 1, 1);
 				BUG_ON(ret);
 			}
 			new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
@@ -365,9 +365,9 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 
 			if (root->root_key.objectid ==
 			    BTRFS_TREE_RELOC_OBJECTID)
-				ret = btrfs_inc_ref(trans, root, cow, 1);
+				ret = btrfs_inc_ref(trans, root, cow, 1, 1);
 			else
-				ret = btrfs_inc_ref(trans, root, cow, 0);
+				ret = btrfs_inc_ref(trans, root, cow, 0, 1);
 			BUG_ON(ret);
 		}
 		if (new_flags != 0) {
@@ -381,11 +381,11 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 		if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) {
 			if (root->root_key.objectid ==
 			    BTRFS_TREE_RELOC_OBJECTID)
-				ret = btrfs_inc_ref(trans, root, cow, 1);
+				ret = btrfs_inc_ref(trans, root, cow, 1, 1);
 			else
-				ret = btrfs_inc_ref(trans, root, cow, 0);
+				ret = btrfs_inc_ref(trans, root, cow, 0, 1);
 			BUG_ON(ret);
-			ret = btrfs_dec_ref(trans, root, buf, 1);
+			ret = btrfs_dec_ref(trans, root, buf, 1, 1);
 			BUG_ON(ret);
 		}
 		clean_tree_block(trans, root, buf);
@@ -446,7 +446,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 
 	cow = btrfs_alloc_free_block(trans, root, buf->len, parent_start,
 				     root->root_key.objectid, &disk_key,
-				     level, search_start, empty_size);
+				     level, search_start, empty_size, 1);
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
 
@@ -484,7 +484,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 		rcu_assign_pointer(root->node, cow);
 
 		btrfs_free_tree_block(trans, root, buf, parent_start,
-				      last_ref);
+				      last_ref, 1);
 		free_extent_buffer(buf);
 		add_root_to_dirty_list(root);
 	} else {
@@ -500,7 +500,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 					      trans->transid);
 		btrfs_mark_buffer_dirty(parent);
 		btrfs_free_tree_block(trans, root, buf, parent_start,
-				      last_ref);
+				      last_ref, 1);
 	}
 	if (unlock_orig)
 		btrfs_tree_unlock(buf);
@@ -957,7 +957,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		free_extent_buffer(mid);
 
 		root_sub_used(root, mid->len);
-		btrfs_free_tree_block(trans, root, mid, 0, 1);
+		btrfs_free_tree_block(trans, root, mid, 0, 1, 0);
 		/* once for the root ptr */
 		free_extent_buffer(mid);
 		return 0;
@@ -1015,7 +1015,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 			if (wret)
 				ret = wret;
 			root_sub_used(root, right->len);
-			btrfs_free_tree_block(trans, root, right, 0, 1);
+			btrfs_free_tree_block(trans, root, right, 0, 1, 0);
 			free_extent_buffer(right);
 			right = NULL;
 		} else {
@@ -1055,7 +1055,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		if (wret)
 			ret = wret;
 		root_sub_used(root, mid->len);
-		btrfs_free_tree_block(trans, root, mid, 0, 1);
+		btrfs_free_tree_block(trans, root, mid, 0, 1, 0);
 		free_extent_buffer(mid);
 		mid = NULL;
 	} else {
@@ -2089,7 +2089,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 
 	c = btrfs_alloc_free_block(trans, root, root->nodesize, 0,
 				   root->root_key.objectid, &lower_key,
-				   level, root->node->start, 0);
+				   level, root->node->start, 0, 0);
 	if (IS_ERR(c))
 		return PTR_ERR(c);
 
@@ -2216,7 +2216,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 
 	split = btrfs_alloc_free_block(trans, root, root->nodesize, 0,
 					root->root_key.objectid,
-					&disk_key, level, c->start, 0);
+					&disk_key, level, c->start, 0, 0);
 	if (IS_ERR(split))
 		return PTR_ERR(split);
 
@@ -2970,7 +2970,7 @@ again:
 
 	right = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
 					root->root_key.objectid,
-					&disk_key, 0, l->start, 0);
+					&disk_key, 0, l->start, 0, 0);
 	if (IS_ERR(right))
 		return PTR_ERR(right);
 
@@ -3781,7 +3781,7 @@ static noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans,
 
 	root_sub_used(root, leaf->len);
 
-	btrfs_free_tree_block(trans, root, leaf, 0, 1);
+	btrfs_free_tree_block(trans, root, leaf, 0, 1, 0);
 	return 0;
 }
 /*

fs/btrfs/ctree.h

@@ -2439,11 +2439,11 @@ 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);
+					u64 hint, u64 empty_size, int for_cow);
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct extent_buffer *buf,
-			   u64 parent, int last_ref);
+			   u64 parent, int last_ref, int for_cow);
 struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans,
 					    struct btrfs_root *root,
 					    u64 bytenr, u32 blocksize,
@@ -2463,17 +2463,17 @@ int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
 				  u64 search_end, struct btrfs_key *ins,
 				  u64 data);
 int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		  struct extent_buffer *buf, int full_backref);
+		  struct extent_buffer *buf, int full_backref, int for_cow);
 int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		  struct extent_buffer *buf, int full_backref);
+		  struct extent_buffer *buf, int full_backref, int for_cow);
 int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
 				u64 bytenr, u64 num_bytes, u64 flags,
 				int is_data);
 int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root,
-		      u64 bytenr, u64 num_bytes, u64 parent,
+		      u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
-		      u64 root_objectid, u64 owner, u64 offset);
+		      u64 owner, u64 offset, int for_cow);
 
 int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len);
 int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root,
@@ -2485,7 +2485,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root,
 			 u64 bytenr, u64 num_bytes, u64 parent,
-			 u64 root_objectid, u64 owner, u64 offset);
+			 u64 root_objectid, u64 owner, u64 offset, int for_cow);
 
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 				    struct btrfs_root *root);
@@ -2644,10 +2644,18 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans,
 }
 
 int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path);
+static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p)
+{
+	++p->slots[0];
+	if (p->slots[0] >= btrfs_header_nritems(p->nodes[0]))
+		return btrfs_next_leaf(root, p);
+	return 0;
+}
 int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
 int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf);
 void btrfs_drop_snapshot(struct btrfs_root *root,
-			 struct btrfs_block_rsv *block_rsv, int update_ref);
+			 struct btrfs_block_rsv *block_rsv, int update_ref,
+			 int for_reloc);
 int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct extent_buffer *node,

fs/btrfs/delayed-ref.c

@@ -101,6 +101,11 @@ static int comp_entry(struct btrfs_delayed_ref_node *ref2,
 		return -1;
 	if (ref1->type > ref2->type)
 		return 1;
+	/* merging of sequenced refs is not allowed */
+	if (ref1->seq < ref2->seq)
+		return -1;
+	if (ref1->seq > ref2->seq)
+		return 1;
 	if (ref1->type == BTRFS_TREE_BLOCK_REF_KEY ||
 	    ref1->type == BTRFS_SHARED_BLOCK_REF_KEY) {
 		return comp_tree_refs(btrfs_delayed_node_to_tree_ref(ref2),
@@ -150,16 +155,22 @@ static struct btrfs_delayed_ref_node *tree_insert(struct rb_root *root,
 
 /*
  * find an head entry based on bytenr. This returns the delayed ref
- * head if it was able to find one, or NULL if nothing was in that spot
+ * head if it was able to find one, or NULL if nothing was in that spot.
+ * If return_bigger is given, the next bigger entry is returned if no exact
+ * match is found.
  */
 static struct btrfs_delayed_ref_node *find_ref_head(struct rb_root *root,
 				  u64 bytenr,
-				  struct btrfs_delayed_ref_node **last)
+				  struct btrfs_delayed_ref_node **last,
+				  int return_bigger)
 {
-	struct rb_node *n = root->rb_node;
+	struct rb_node *n;
 	struct btrfs_delayed_ref_node *entry;
-	int cmp;
+	int cmp = 0;
 
+again:
+	n = root->rb_node;
+	entry = NULL;
 	while (n) {
 		entry = rb_entry(n, struct btrfs_delayed_ref_node, rb_node);
 		WARN_ON(!entry->in_tree);
@@ -182,6 +193,19 @@ static struct btrfs_delayed_ref_node *find_ref_head(struct rb_root *root,
 		else
 			return entry;
 	}
+	if (entry && return_bigger) {
+		if (cmp > 0) {
+			n = rb_next(&entry->rb_node);
+			if (!n)
+				n = rb_first(root);
+			entry = rb_entry(n, struct btrfs_delayed_ref_node,
+					 rb_node);
+			bytenr = entry->bytenr;
+			return_bigger = 0;
+			goto again;
+		}
+		return entry;
+	}
 	return NULL;
 }
 
@@ -209,6 +233,24 @@ int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+int btrfs_check_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs,
+			    u64 seq)
+{
+	struct seq_list *elem;
+
+	assert_spin_locked(&delayed_refs->lock);
+	if (list_empty(&delayed_refs->seq_head))
+		return 0;
+
+	elem = list_first_entry(&delayed_refs->seq_head, struct seq_list, list);
+	if (seq >= elem->seq) {
+		pr_debug("holding back delayed_ref %llu, lowest is %llu (%p)\n",
+			 seq, elem->seq, delayed_refs);
+		return 1;
+	}
+	return 0;
+}
+
 int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
 			   struct list_head *cluster, u64 start)
 {
@@ -223,20 +265,8 @@ int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
 		node = rb_first(&delayed_refs->root);
 	} else {
 		ref = NULL;
-		find_ref_head(&delayed_refs->root, start, &ref);
+		find_ref_head(&delayed_refs->root, start + 1, &ref, 1);
 		if (ref) {
-			struct btrfs_delayed_ref_node *tmp;
-
-			node = rb_prev(&ref->rb_node);
-			while (node) {
-				tmp = rb_entry(node,
-					       struct btrfs_delayed_ref_node,
-					       rb_node);
-				if (tmp->bytenr < start)
-					break;
-				ref = tmp;
-				node = rb_prev(&ref->rb_node);
-			}
 			node = &ref->rb_node;
 		} else
 			node = rb_first(&delayed_refs->root);
@@ -390,7 +420,8 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
  * this does all the dirty work in terms of maintaining the correct
  * overall modification count.
  */
-static noinline int add_delayed_ref_head(struct btrfs_trans_handle *trans,
+static noinline int add_delayed_ref_head(struct btrfs_fs_info *fs_info,
+					struct btrfs_trans_handle *trans,
 					struct btrfs_delayed_ref_node *ref,
 					u64 bytenr, u64 num_bytes,
 					int action, int is_data)
@@ -437,6 +468,7 @@ static noinline int add_delayed_ref_head(struct btrfs_trans_handle *trans,
 	ref->action  = 0;
 	ref->is_head = 1;
 	ref->in_tree = 1;
+	ref->seq = 0;
 
 	head_ref = btrfs_delayed_node_to_head(ref);
 	head_ref->must_insert_reserved = must_insert_reserved;
@@ -468,14 +500,17 @@ static noinline int add_delayed_ref_head(struct btrfs_trans_handle *trans,
 /*
  * helper to insert a delayed tree ref into the rbtree.
  */
-static noinline int add_delayed_tree_ref(struct btrfs_trans_handle *trans,
+static noinline int add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
+					 struct btrfs_trans_handle *trans,
 					 struct btrfs_delayed_ref_node *ref,
 					 u64 bytenr, u64 num_bytes, u64 parent,
-					 u64 ref_root, int level, int action)
+					 u64 ref_root, int level, int action,
+					 int for_cow)
 {
 	struct btrfs_delayed_ref_node *existing;
 	struct btrfs_delayed_tree_ref *full_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
+	u64 seq = 0;
 
 	if (action == BTRFS_ADD_DELAYED_EXTENT)
 		action = BTRFS_ADD_DELAYED_REF;
@@ -491,14 +526,17 @@ static noinline int add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	ref->is_head = 0;
 	ref->in_tree = 1;
 
+	if (need_ref_seq(for_cow, ref_root))
+		seq = inc_delayed_seq(delayed_refs);
+	ref->seq = seq;
+
 	full_ref = btrfs_delayed_node_to_tree_ref(ref);
-	if (parent) {
+	full_ref->parent = parent;
-		full_ref->parent = parent;
+	full_ref->root = ref_root;
+	if (parent)
 		ref->type = BTRFS_SHARED_BLOCK_REF_KEY;
-	} else {
+	else
-		full_ref->root = ref_root;
 		ref->type = BTRFS_TREE_BLOCK_REF_KEY;
-	}
 	full_ref->level = level;
 
 	trace_btrfs_delayed_tree_ref(ref, full_ref, action);
@@ -522,15 +560,17 @@ static noinline int add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 /*
  * helper to insert a delayed data ref into the rbtree.
  */
-static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans,
+static noinline int add_delayed_data_ref(struct btrfs_fs_info *fs_info,
+					 struct btrfs_trans_handle *trans,
 					 struct btrfs_delayed_ref_node *ref,
 					 u64 bytenr, u64 num_bytes, u64 parent,
 					 u64 ref_root, u64 owner, u64 offset,
-					 int action)
+					 int action, int for_cow)
 {
 	struct btrfs_delayed_ref_node *existing;
 	struct btrfs_delayed_data_ref *full_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
+	u64 seq = 0;
 
 	if (action == BTRFS_ADD_DELAYED_EXTENT)
 		action = BTRFS_ADD_DELAYED_REF;
@@ -546,14 +586,18 @@ static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans,
 	ref->is_head = 0;
 	ref->in_tree = 1;
 
+	if (need_ref_seq(for_cow, ref_root))
+		seq = inc_delayed_seq(delayed_refs);
+	ref->seq = seq;
+
 	full_ref = btrfs_delayed_node_to_data_ref(ref);
-	if (parent) {
+	full_ref->parent = parent;
-		full_ref->parent = parent;
+	full_ref->root = ref_root;
+	if (parent)
 		ref->type = BTRFS_SHARED_DATA_REF_KEY;
-	} else {
+	else
-		full_ref->root = ref_root;
 		ref->type = BTRFS_EXTENT_DATA_REF_KEY;
-	}
+
 	full_ref->objectid = owner;
 	full_ref->offset = offset;
 
@@ -580,10 +624,12 @@ static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans,
  * to make sure the delayed ref is eventually processed before this
  * transaction commits.
  */
-int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
+			       struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root,  int level, int action,
-			       struct btrfs_delayed_extent_op *extent_op)
+			       struct btrfs_delayed_extent_op *extent_op,
+			       int for_cow)
 {
 	struct btrfs_delayed_tree_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
@@ -610,13 +656,17 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	 * insert both the head node and the new ref without dropping
 	 * the spin lock
 	 */
-	ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, num_bytes,
+	ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
-				   action, 0);
+				   num_bytes, action, 0);
 	BUG_ON(ret);
 
-	ret = add_delayed_tree_ref(trans, &ref->node, bytenr, num_bytes,
+	ret = add_delayed_tree_ref(fs_info, trans, &ref->node, bytenr,
-				   parent, ref_root, level, action);
+				   num_bytes, parent, ref_root, level, action,
+				   for_cow);
 	BUG_ON(ret);
+	if (!need_ref_seq(for_cow, ref_root) &&
+	    waitqueue_active(&delayed_refs->seq_wait))
+		wake_up(&delayed_refs->seq_wait);
 	spin_unlock(&delayed_refs->lock);
 	return 0;
 }
@@ -624,11 +674,13 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 /*
  * add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref.
  */
-int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
+			       struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, int action,
-			       struct btrfs_delayed_extent_op *extent_op)
+			       struct btrfs_delayed_extent_op *extent_op,
+			       int for_cow)
 {
 	struct btrfs_delayed_data_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
@@ -655,18 +707,23 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 	 * insert both the head node and the new ref without dropping
 	 * the spin lock
 	 */
-	ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, num_bytes,
+	ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
-				   action, 1);
+				   num_bytes, action, 1);
 	BUG_ON(ret);
 
-	ret = add_delayed_data_ref(trans, &ref->node, bytenr, num_bytes,
+	ret = add_delayed_data_ref(fs_info, trans, &ref->node, bytenr,
-				   parent, ref_root, owner, offset, action);
+				   num_bytes, parent, ref_root, owner, offset,
+				   action, for_cow);
 	BUG_ON(ret);
+	if (!need_ref_seq(for_cow, ref_root) &&
+	    waitqueue_active(&delayed_refs->seq_wait))
+		wake_up(&delayed_refs->seq_wait);
 	spin_unlock(&delayed_refs->lock);
 	return 0;
 }
 
-int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
+				struct btrfs_trans_handle *trans,
 				u64 bytenr, u64 num_bytes,
 				struct btrfs_delayed_extent_op *extent_op)
 {
@@ -683,11 +740,13 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
 	delayed_refs = &trans->transaction->delayed_refs;
 	spin_lock(&delayed_refs->lock);
 
-	ret = add_delayed_ref_head(trans, &head_ref->node, bytenr,
+	ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
 				   num_bytes, BTRFS_UPDATE_DELAYED_HEAD,
 				   extent_op->is_data);
 	BUG_ON(ret);
 
+	if (waitqueue_active(&delayed_refs->seq_wait))
+		wake_up(&delayed_refs->seq_wait);
 	spin_unlock(&delayed_refs->lock);
 	return 0;
 }
@@ -704,7 +763,7 @@ btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
 	struct btrfs_delayed_ref_root *delayed_refs;
 
 	delayed_refs = &trans->transaction->delayed_refs;
-	ref = find_ref_head(&delayed_refs->root, bytenr, NULL);
+	ref = find_ref_head(&delayed_refs->root, bytenr, NULL, 0);
 	if (ref)
 		return btrfs_delayed_node_to_head(ref);
 	return NULL;

fs/btrfs/delayed-ref.h

@@ -33,6 +33,9 @@ struct btrfs_delayed_ref_node {
 	/* the size of the extent */
 	u64 num_bytes;
 
+	/* seq number to keep track of insertion order */
+	u64 seq;
+
 	/* ref count on this data structure */
 	atomic_t refs;
 
@@ -98,19 +101,15 @@ struct btrfs_delayed_ref_head {
 
 struct btrfs_delayed_tree_ref {
 	struct btrfs_delayed_ref_node node;
-	union {
+	u64 root;
-		u64 root;
+	u64 parent;
-		u64 parent;
-	};
 	int level;
 };
 
 struct btrfs_delayed_data_ref {
 	struct btrfs_delayed_ref_node node;
-	union {
+	u64 root;
-		u64 root;
+	u64 parent;
-		u64 parent;
-	};
 	u64 objectid;
 	u64 offset;
 };
@@ -140,6 +139,26 @@ struct btrfs_delayed_ref_root {
 	int flushing;
 
 	u64 run_delayed_start;
+
+	/*
+	 * seq number of delayed refs. We need to know if a backref was being
+	 * added before the currently processed ref or afterwards.
+	 */
+	u64 seq;
+
+	/*
+	 * seq_list holds a list of all seq numbers that are currently being
+	 * added to the list. While walking backrefs (btrfs_find_all_roots,
+	 * qgroups), which might take some time, no newer ref must be processed,
+	 * as it might influence the outcome of the walk.
+	 */
+	struct list_head seq_head;
+
+	/*
+	 * when the only refs we have in the list must not be processed, we want
+	 * to wait for more refs to show up or for the end of backref walking.
+	 */
+	wait_queue_head_t seq_wait;
 };
 
 static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
@@ -151,16 +170,21 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
 	}
 }
 
-int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
+			       struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root, int level, int action,
-			       struct btrfs_delayed_extent_op *extent_op);
+			       struct btrfs_delayed_extent_op *extent_op,
-int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
+			       int for_cow);
+int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
+			       struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, int action,
-			       struct btrfs_delayed_extent_op *extent_op);
+			       struct btrfs_delayed_extent_op *extent_op,
-int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
+			       int for_cow);
+int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
+				struct btrfs_trans_handle *trans,
 				u64 bytenr, u64 num_bytes,
 				struct btrfs_delayed_extent_op *extent_op);
 
@@ -170,6 +194,60 @@ int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
 			   struct btrfs_delayed_ref_head *head);
 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);
+	++delayed_refs->seq;
+	return delayed_refs->seq;
+}
+
+static inline void
+btrfs_get_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs,
+		      struct seq_list *elem)
+{
+	assert_spin_locked(&delayed_refs->lock);
+	elem->seq = delayed_refs->seq;
+	list_add_tail(&elem->list, &delayed_refs->seq_head);
+}
+
+static inline void
+btrfs_put_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs,
+		      struct seq_list *elem)
+{
+	spin_lock(&delayed_refs->lock);
+	list_del(&elem->list);
+	wake_up(&delayed_refs->seq_wait);
+	spin_unlock(&delayed_refs->lock);
+}
+
+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

@@ -1243,7 +1243,8 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	root->ref_cows = 0;
 
 	leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
-				      BTRFS_TREE_LOG_OBJECTID, NULL, 0, 0, 0);
+				      BTRFS_TREE_LOG_OBJECTID, NULL,
+				      0, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		kfree(root);
 		return ERR_CAST(leaf);

fs/btrfs/extent-tree.c

@@ -1871,20 +1871,24 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root,
 			 u64 bytenr, u64 num_bytes, u64 parent,
-			 u64 root_objectid, u64 owner, u64 offset)
+			 u64 root_objectid, u64 owner, u64 offset, int for_cow)
 {
 	int ret;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+
 	BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID &&
 	       root_objectid == BTRFS_TREE_LOG_OBJECTID);
 
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = btrfs_add_delayed_tree_ref(trans, bytenr, num_bytes,
+		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
+					num_bytes,
 					parent, root_objectid, (int)owner,
-					BTRFS_ADD_DELAYED_REF, NULL);
+					BTRFS_ADD_DELAYED_REF, NULL, for_cow);
 	} else {
-		ret = btrfs_add_delayed_data_ref(trans, bytenr, num_bytes,
+		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
+					num_bytes,
 					parent, root_objectid, owner, offset,
-					BTRFS_ADD_DELAYED_REF, NULL);
+					BTRFS_ADD_DELAYED_REF, NULL, for_cow);
 	}
 	return ret;
 }
@@ -2231,6 +2235,28 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 			}
 		}
 
+		/*
+		 * locked_ref is the head node, so we have to go one
+		 * node back for any delayed ref updates
+		 */
+		ref = select_delayed_ref(locked_ref);
+
+		if (ref && ref->seq &&
+		    btrfs_check_delayed_seq(delayed_refs, ref->seq)) {
+			/*
+			 * there are still refs with lower seq numbers in the
+			 * process of being added. Don't run this ref yet.
+			 */
+			list_del_init(&locked_ref->cluster);
+			mutex_unlock(&locked_ref->mutex);
+			locked_ref = NULL;
+			delayed_refs->num_heads_ready++;
+			spin_unlock(&delayed_refs->lock);
+			cond_resched();
+			spin_lock(&delayed_refs->lock);
+			continue;
+		}
+
 		/*
 		 * record the must insert reserved flag before we
 		 * drop the spin lock.
@@ -2241,11 +2267,6 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 		extent_op = locked_ref->extent_op;
 		locked_ref->extent_op = NULL;
 
-		/*
-		 * locked_ref is the head node, so we have to go one
-		 * node back for any delayed ref updates
-		 */
-		ref = select_delayed_ref(locked_ref);
 		if (!ref) {
 			/* All delayed refs have been processed, Go ahead
 			 * and send the head node to run_one_delayed_ref,
@@ -2276,7 +2297,12 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 		ref->in_tree = 0;
 		rb_erase(&ref->rb_node, &delayed_refs->root);
 		delayed_refs->num_entries--;
-
+		/*
+		 * we modified num_entries, but as we're currently running
+		 * delayed refs, skip
+		 *     wake_up(&delayed_refs->seq_wait);
+		 * here.
+		 */
 		spin_unlock(&delayed_refs->lock);
 
 		ret = run_one_delayed_ref(trans, root, ref, extent_op,
@@ -2297,6 +2323,23 @@ next:
 	return count;
 }
 
+
+static void wait_for_more_refs(struct btrfs_delayed_ref_root *delayed_refs,
+			unsigned long num_refs)
+{
+	struct list_head *first_seq = delayed_refs->seq_head.next;
+
+	spin_unlock(&delayed_refs->lock);
+	pr_debug("waiting for more refs (num %ld, first %p)\n",
+		 num_refs, first_seq);
+	wait_event(delayed_refs->seq_wait,
+		   num_refs != delayed_refs->num_entries ||
+		   delayed_refs->seq_head.next != first_seq);
+	pr_debug("done waiting for more refs (num %ld, first %p)\n",
+		 delayed_refs->num_entries, delayed_refs->seq_head.next);
+	spin_lock(&delayed_refs->lock);
+}
+
 /*
  * this starts processing the delayed reference count updates and
  * extent insertions we have queued up so far.  count can be
@@ -2312,8 +2355,11 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_ref_node *ref;
 	struct list_head cluster;
 	int ret;
+	u64 delayed_start;
 	int run_all = count == (unsigned long)-1;
 	int run_most = 0;
+	unsigned long num_refs = 0;
+	int consider_waiting;
 
 	if (root == root->fs_info->extent_root)
 		root = root->fs_info->tree_root;
@@ -2325,6 +2371,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 	delayed_refs = &trans->transaction->delayed_refs;
 	INIT_LIST_HEAD(&cluster);
 again:
+	consider_waiting = 0;
 	spin_lock(&delayed_refs->lock);
 	if (count == 0) {
 		count = delayed_refs->num_entries * 2;
@@ -2341,11 +2388,35 @@ again:
 		 * of refs to process starting at the first one we are able to
 		 * lock
 		 */
+		delayed_start = delayed_refs->run_delayed_start;
 		ret = btrfs_find_ref_cluster(trans, &cluster,
 					     delayed_refs->run_delayed_start);
 		if (ret)
 			break;
 
+		if (delayed_start >= delayed_refs->run_delayed_start) {
+			if (consider_waiting == 0) {
+				/*
+				 * btrfs_find_ref_cluster looped. let's do one
+				 * more cycle. if we don't run any delayed ref
+				 * during that cycle (because we can't because
+				 * all of them are blocked) and if the number of
+				 * refs doesn't change, we avoid busy waiting.
+				 */
+				consider_waiting = 1;
+				num_refs = delayed_refs->num_entries;
+			} else {
+				wait_for_more_refs(delayed_refs, num_refs);
+				/*
+				 * after waiting, things have changed. we
+				 * dropped the lock and someone else might have
+				 * run some refs, built new clusters and so on.
+				 * therefore, we restart staleness detection.
+				 */
+				consider_waiting = 0;
+			}
+		}
+
 		ret = run_clustered_refs(trans, root, &cluster);
 		BUG_ON(ret < 0);
 
@@ -2353,6 +2424,11 @@ again:
 
 		if (count == 0)
 			break;
+
+		if (ret || delayed_refs->run_delayed_start == 0) {
+			/* refs were run, let's reset staleness detection */
+			consider_waiting = 0;
+		}
 	}
 
 	if (run_all) {
@@ -2410,7 +2486,8 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
 	extent_op->update_key = 0;
 	extent_op->is_data = is_data ? 1 : 0;
 
-	ret = btrfs_add_delayed_extent_op(trans, bytenr, num_bytes, extent_op);
+	ret = btrfs_add_delayed_extent_op(root->fs_info, trans, bytenr,
+					  num_bytes, extent_op);
 	if (ret)
 		kfree(extent_op);
 	return ret;
@@ -2595,7 +2672,7 @@ out:
 static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct extent_buffer *buf,
-			   int full_backref, int inc)
+			   int full_backref, int inc, int for_cow)
 {
 	u64 bytenr;
 	u64 num_bytes;
@@ -2608,7 +2685,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 	int level;
 	int ret = 0;
 	int (*process_func)(struct btrfs_trans_handle *, struct btrfs_root *,
-			    u64, u64, u64, u64, u64, u64);
+			    u64, u64, u64, u64, u64, u64, int);
 
 	ref_root = btrfs_header_owner(buf);
 	nritems = btrfs_header_nritems(buf);
@@ -2645,14 +2722,15 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 			key.offset -= btrfs_file_extent_offset(buf, fi);
 			ret = process_func(trans, root, bytenr, num_bytes,
 					   parent, ref_root, key.objectid,
-					   key.offset);
+					   key.offset, for_cow);
 			if (ret)
 				goto fail;
 		} else {
 			bytenr = btrfs_node_blockptr(buf, i);
 			num_bytes = btrfs_level_size(root, level - 1);
 			ret = process_func(trans, root, bytenr, num_bytes,
-					   parent, ref_root, level - 1, 0);
+					   parent, ref_root, level - 1, 0,
+					   for_cow);
 			if (ret)
 				goto fail;
 		}
@@ -2664,15 +2742,15 @@ fail:
 }
 
 int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		  struct extent_buffer *buf, int full_backref)
+		  struct extent_buffer *buf, int full_backref, int for_cow)
 {
-	return __btrfs_mod_ref(trans, root, buf, full_backref, 1);
+	return __btrfs_mod_ref(trans, root, buf, full_backref, 1, for_cow);
 }
 
 int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		  struct extent_buffer *buf, int full_backref)
+		  struct extent_buffer *buf, int full_backref, int for_cow)
 {
-	return __btrfs_mod_ref(trans, root, buf, full_backref, 0);
+	return __btrfs_mod_ref(trans, root, buf, full_backref, 0, for_cow);
 }
 
 static int write_one_cache_group(struct btrfs_trans_handle *trans,
@@ -4954,6 +5032,8 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
 	rb_erase(&head->node.rb_node, &delayed_refs->root);
 
 	delayed_refs->num_entries--;
+	if (waitqueue_active(&delayed_refs->seq_wait))
+		wake_up(&delayed_refs->seq_wait);
 
 	/*
 	 * we don't take a ref on the node because we're removing it from the
@@ -4981,16 +5061,17 @@ out:
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct extent_buffer *buf,
-			   u64 parent, int last_ref)
+			   u64 parent, int last_ref, int for_cow)
 {
 	struct btrfs_block_group_cache *cache = NULL;
 	int ret;
 
 	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
-		ret = btrfs_add_delayed_tree_ref(trans, buf->start, buf->len,
+		ret = btrfs_add_delayed_tree_ref(root->fs_info, trans,
-						parent, root->root_key.objectid,
+					buf->start, buf->len,
-						btrfs_header_level(buf),
+					parent, root->root_key.objectid,
-						BTRFS_DROP_DELAYED_REF, NULL);
+					btrfs_header_level(buf),
+					BTRFS_DROP_DELAYED_REF, NULL, for_cow);
 		BUG_ON(ret);
 	}
 
@@ -5025,12 +5106,12 @@ out:
 	btrfs_put_block_group(cache);
 }
 
-int btrfs_free_extent(struct btrfs_trans_handle *trans,
+int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		      struct btrfs_root *root,
+		      u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
-		      u64 bytenr, u64 num_bytes, u64 parent,
+		      u64 owner, u64 offset, int for_cow)
-		      u64 root_objectid, u64 owner, u64 offset)
 {
 	int ret;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	/*
 	 * tree log blocks never actually go into the extent allocation
@@ -5042,14 +5123,17 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		btrfs_pin_extent(root, bytenr, num_bytes, 1);
 		ret = 0;
 	} else if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = btrfs_add_delayed_tree_ref(trans, bytenr, num_bytes,
+		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
+					num_bytes,
 					parent, root_objectid, (int)owner,
-					BTRFS_DROP_DELAYED_REF, NULL);
+					BTRFS_DROP_DELAYED_REF, NULL, for_cow);
 		BUG_ON(ret);
 	} else {
-		ret = btrfs_add_delayed_data_ref(trans, bytenr, num_bytes,
+		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
-					parent, root_objectid, owner,
+						num_bytes,
-					offset, BTRFS_DROP_DELAYED_REF, NULL);
+						parent, root_objectid, owner,
+						offset, BTRFS_DROP_DELAYED_REF,
+						NULL, for_cow);
 		BUG_ON(ret);
 	}
 	return ret;
@@ -5877,9 +5961,10 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 
 	BUG_ON(root_objectid == BTRFS_TREE_LOG_OBJECTID);
 
-	ret = btrfs_add_delayed_data_ref(trans, ins->objectid, ins->offset,
+	ret = btrfs_add_delayed_data_ref(root->fs_info, trans, ins->objectid,
-					 0, root_objectid, owner, offset,
+					 ins->offset, 0,
-					 BTRFS_ADD_DELAYED_EXTENT, NULL);
+					 root_objectid, owner, offset,
+					 BTRFS_ADD_DELAYED_EXTENT, NULL, 0);
 	return ret;
 }
 
@@ -6049,7 +6134,7 @@ 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)
+					u64 hint, u64 empty_size, int for_cow)
 {
 	struct btrfs_key ins;
 	struct btrfs_block_rsv *block_rsv;
@@ -6093,10 +6178,11 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 		extent_op->update_flags = 1;
 		extent_op->is_data = 0;
 
-		ret = btrfs_add_delayed_tree_ref(trans, ins.objectid,
+		ret = btrfs_add_delayed_tree_ref(root->fs_info, trans,
+					ins.objectid,
 					ins.offset, parent, root_objectid,
 					level, BTRFS_ADD_DELAYED_EXTENT,
-					extent_op);
+					extent_op, for_cow);
 		BUG_ON(ret);
 	}
 	return buf;
@@ -6113,6 +6199,7 @@ struct walk_control {
 	int keep_locks;
 	int reada_slot;
 	int reada_count;
+	int for_reloc;
 };
 
 #define DROP_REFERENCE	1
@@ -6251,9 +6338,9 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
 	/* wc->stage == UPDATE_BACKREF */
 	if (!(wc->flags[level] & flag)) {
 		BUG_ON(!path->locks[level]);
-		ret = btrfs_inc_ref(trans, root, eb, 1);
+		ret = btrfs_inc_ref(trans, root, eb, 1, wc->for_reloc);
 		BUG_ON(ret);
-		ret = btrfs_dec_ref(trans, root, eb, 0);
+		ret = btrfs_dec_ref(trans, root, eb, 0, wc->for_reloc);
 		BUG_ON(ret);
 		ret = btrfs_set_disk_extent_flags(trans, root, eb->start,
 						  eb->len, flag, 0);
@@ -6397,7 +6484,7 @@ skip:
 		}
 
 		ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent,
-					root->root_key.objectid, level - 1, 0);
+				root->root_key.objectid, level - 1, 0, 0);
 		BUG_ON(ret);
 	}
 	btrfs_tree_unlock(next);
@@ -6471,9 +6558,11 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 	if (wc->refs[level] == 1) {
 		if (level == 0) {
 			if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
-				ret = btrfs_dec_ref(trans, root, eb, 1);
+				ret = btrfs_dec_ref(trans, root, eb, 1,
+						    wc->for_reloc);
 			else
-				ret = btrfs_dec_ref(trans, root, eb, 0);
+				ret = btrfs_dec_ref(trans, root, eb, 0,
+						    wc->for_reloc);
 			BUG_ON(ret);
 		}
 		/* make block locked assertion in clean_tree_block happy */
@@ -6500,7 +6589,7 @@ 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);
+	btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1, 0);
 out:
 	wc->refs[level] = 0;
 	wc->flags[level] = 0;
@@ -6584,7 +6673,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
  * blocks are properly updated.
  */
 void btrfs_drop_snapshot(struct btrfs_root *root,
-			 struct btrfs_block_rsv *block_rsv, int update_ref)
+			 struct btrfs_block_rsv *block_rsv, int update_ref,
+			 int for_reloc)
 {
 	struct btrfs_path *path;
 	struct btrfs_trans_handle *trans;
@@ -6672,6 +6762,7 @@ void btrfs_drop_snapshot(struct btrfs_root *root,
 	wc->stage = DROP_REFERENCE;
 	wc->update_ref = update_ref;
 	wc->keep_locks = 0;
+	wc->for_reloc = for_reloc;
 	wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(root);
 
 	while (1) {
@@ -6756,6 +6847,7 @@ out:
  * drop subtree rooted at tree block 'node'.
  *
  * NOTE: this function will unlock and release tree block 'node'
+ * only used by relocation code
  */
 int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
@@ -6800,6 +6892,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	wc->stage = DROP_REFERENCE;
 	wc->update_ref = 0;
 	wc->keep_locks = 1;
+	wc->for_reloc = 1;
 	wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(root);
 
 	while (1) {

fs/btrfs/extent_io.c

@@ -3579,6 +3579,7 @@ static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
 	atomic_set(&eb->blocking_writers, 0);
 	atomic_set(&eb->spinning_readers, 0);
 	atomic_set(&eb->spinning_writers, 0);
+	eb->lock_nested = 0;
 	init_waitqueue_head(&eb->write_lock_wq);
 	init_waitqueue_head(&eb->read_lock_wq);
 

fs/btrfs/extent_io.h

@@ -129,6 +129,7 @@ struct extent_buffer {
 	struct list_head leak_list;
 	struct rcu_head rcu_head;
 	atomic_t refs;
+	pid_t lock_owner;
 
 	/* count of read lock holders on the extent buffer */
 	atomic_t write_locks;
@@ -137,6 +138,7 @@ struct extent_buffer {
 	atomic_t blocking_readers;
 	atomic_t spinning_readers;
 	atomic_t spinning_writers;
+	int lock_nested;
 
 	/* protects write locks */
 	rwlock_t lock;

fs/btrfs/file.c

@@ -678,7 +678,7 @@ next_slot:
 						disk_bytenr, num_bytes, 0,
 						root->root_key.objectid,
 						new_key.objectid,
-						start - extent_offset);
+						start - extent_offset, 0);
 				BUG_ON(ret);
 				*hint_byte = disk_bytenr;
 			}
@@ -753,7 +753,7 @@ next_slot:
 						disk_bytenr, num_bytes, 0,
 						root->root_key.objectid,
 						key.objectid, key.offset -
-						extent_offset);
+						extent_offset, 0);
 				BUG_ON(ret);
 				inode_sub_bytes(inode,
 						extent_end - key.offset);
@@ -962,7 +962,7 @@ again:
 
 		ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
 					   root->root_key.objectid,
-					   ino, orig_offset);
+					   ino, orig_offset, 0);
 		BUG_ON(ret);
 
 		if (split == start) {
@@ -989,7 +989,7 @@ again:
 		del_nr++;
 		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
 					0, root->root_key.objectid,
-					ino, orig_offset);
+					ino, orig_offset, 0);
 		BUG_ON(ret);
 	}
 	other_start = 0;
@@ -1006,7 +1006,7 @@ again:
 		del_nr++;
 		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
 					0, root->root_key.objectid,
-					ino, orig_offset);
+					ino, orig_offset, 0);
 		BUG_ON(ret);
 	}
 	if (del_nr == 0) {

fs/btrfs/inode.c

@@ -3179,7 +3179,7 @@ delete:
 			ret = btrfs_free_extent(trans, root, extent_start,
 						extent_num_bytes, 0,
 						btrfs_header_owner(leaf),
-						ino, extent_offset);
+						ino, extent_offset, 0);
 			BUG_ON(ret);
 		}
 
@@ -5121,7 +5121,7 @@ again:
 			}
 			flush_dcache_page(page);
 		} else if (create && PageUptodate(page)) {
-			WARN_ON(1);
+			BUG();
 			if (!trans) {
 				kunmap(page);
 				free_extent_map(em);

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, objectid, NULL, 0, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
 		goto fail;
@@ -2468,7 +2468,8 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 							disko, diskl, 0,
 							root->root_key.objectid,
 							btrfs_ino(inode),
-							new_key.offset - datao);
+							new_key.offset - datao,
+							0);
 					BUG_ON(ret);
 				}
 			} else if (type == BTRFS_FILE_EXTENT_INLINE) {
@@ -3018,7 +3019,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 {
 	int ret = 0;
 	int size;
-	u64 extent_offset;
+	u64 extent_item_pos;
 	struct btrfs_ioctl_logical_ino_args *loi;
 	struct btrfs_data_container *inodes = NULL;
 	struct btrfs_path *path = NULL;
@@ -3049,15 +3050,17 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 	}
 
 	ret = extent_from_logical(root->fs_info, loi->logical, path, &key);
+	btrfs_release_path(path);
 
 	if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK)
 		ret = -ENOENT;
 	if (ret < 0)
 		goto out;
 
-	extent_offset = loi->logical - key.objectid;
+	extent_item_pos = loi->logical - key.objectid;
 	ret = iterate_extent_inodes(root->fs_info, path, key.objectid,
-					extent_offset, build_ino_list, inodes);
+					extent_item_pos, build_ino_list,
+					inodes);
 
 	if (ret < 0)
 		goto out;

fs/btrfs/locking.c

@@ -33,6 +33,14 @@ void btrfs_assert_tree_read_locked(struct extent_buffer *eb);
  */
 void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw)
 {
+	if (eb->lock_nested) {
+		read_lock(&eb->lock);
+		if (eb->lock_nested && current->pid == eb->lock_owner) {
+			read_unlock(&eb->lock);
+			return;
+		}
+		read_unlock(&eb->lock);
+	}
 	if (rw == BTRFS_WRITE_LOCK) {
 		if (atomic_read(&eb->blocking_writers) == 0) {
 			WARN_ON(atomic_read(&eb->spinning_writers) != 1);
@@ -57,6 +65,14 @@ void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw)
  */
 void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
 {
+	if (eb->lock_nested) {
+		read_lock(&eb->lock);
+		if (&eb->lock_nested && current->pid == eb->lock_owner) {
+			read_unlock(&eb->lock);
+			return;
+		}
+		read_unlock(&eb->lock);
+	}
 	if (rw == BTRFS_WRITE_LOCK_BLOCKING) {
 		BUG_ON(atomic_read(&eb->blocking_writers) != 1);
 		write_lock(&eb->lock);
@@ -81,12 +97,25 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
 void btrfs_tree_read_lock(struct extent_buffer *eb)
 {
 again:
+	read_lock(&eb->lock);
+	if (atomic_read(&eb->blocking_writers) &&
+	    current->pid == eb->lock_owner) {
+		/*
+		 * This extent is already write-locked by our thread. We allow
+		 * an additional read lock to be added because it's for the same
+		 * thread. btrfs_find_all_roots() depends on this as it may be
+		 * called on a partly (write-)locked tree.
+		 */
+		BUG_ON(eb->lock_nested);
+		eb->lock_nested = 1;
+		read_unlock(&eb->lock);
+		return;
+	}
+	read_unlock(&eb->lock);
 	wait_event(eb->write_lock_wq, atomic_read(&eb->blocking_writers) == 0);
 	read_lock(&eb->lock);
 	if (atomic_read(&eb->blocking_writers)) {
 		read_unlock(&eb->lock);
-		wait_event(eb->write_lock_wq,
-			   atomic_read(&eb->blocking_writers) == 0);
 		goto again;
 	}
 	atomic_inc(&eb->read_locks);
@@ -129,6 +158,7 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
 	}
 	atomic_inc(&eb->write_locks);
 	atomic_inc(&eb->spinning_writers);
+	eb->lock_owner = current->pid;
 	return 1;
 }
 
@@ -137,6 +167,15 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
  */
 void btrfs_tree_read_unlock(struct extent_buffer *eb)
 {
+	if (eb->lock_nested) {
+		read_lock(&eb->lock);
+		if (eb->lock_nested && current->pid == eb->lock_owner) {
+			eb->lock_nested = 0;
+			read_unlock(&eb->lock);
+			return;
+		}
+		read_unlock(&eb->lock);
+	}
 	btrfs_assert_tree_read_locked(eb);
 	WARN_ON(atomic_read(&eb->spinning_readers) == 0);
 	atomic_dec(&eb->spinning_readers);
@@ -149,6 +188,15 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb)
  */
 void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
 {
+	if (eb->lock_nested) {
+		read_lock(&eb->lock);
+		if (eb->lock_nested && current->pid == eb->lock_owner) {
+			eb->lock_nested = 0;
+			read_unlock(&eb->lock);
+			return;
+		}
+		read_unlock(&eb->lock);
+	}
 	btrfs_assert_tree_read_locked(eb);
 	WARN_ON(atomic_read(&eb->blocking_readers) == 0);
 	if (atomic_dec_and_test(&eb->blocking_readers))
@@ -181,6 +229,7 @@ again:
 	WARN_ON(atomic_read(&eb->spinning_writers));
 	atomic_inc(&eb->spinning_writers);
 	atomic_inc(&eb->write_locks);
+	eb->lock_owner = current->pid;
 	return 0;
 }
 

fs/btrfs/relocation.c

@@ -1604,12 +1604,12 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 		ret = btrfs_inc_extent_ref(trans, root, new_bytenr,
 					   num_bytes, parent,
 					   btrfs_header_owner(leaf),
-					   key.objectid, key.offset);
+					   key.objectid, key.offset, 1);
 		BUG_ON(ret);
 
 		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
 					parent, btrfs_header_owner(leaf),
-					key.objectid, key.offset);
+					key.objectid, key.offset, 1);
 		BUG_ON(ret);
 	}
 	if (dirty)
@@ -1778,21 +1778,23 @@ again:
 
 		ret = btrfs_inc_extent_ref(trans, src, old_bytenr, blocksize,
 					path->nodes[level]->start,
-					src->root_key.objectid, level - 1, 0);
+					src->root_key.objectid, level - 1, 0,
+					1);
 		BUG_ON(ret);
 		ret = btrfs_inc_extent_ref(trans, dest, new_bytenr, blocksize,
 					0, dest->root_key.objectid, level - 1,
-					0);
+					0, 1);
 		BUG_ON(ret);
 
 		ret = btrfs_free_extent(trans, src, new_bytenr, blocksize,
 					path->nodes[level]->start,
-					src->root_key.objectid, level - 1, 0);
+					src->root_key.objectid, level - 1, 0,
+					1);
 		BUG_ON(ret);
 
 		ret = btrfs_free_extent(trans, dest, old_bytenr, blocksize,
 					0, dest->root_key.objectid, level - 1,
-					0);
+					0, 1);
 		BUG_ON(ret);
 
 		btrfs_unlock_up_safe(path, 0);
@@ -2244,7 +2246,7 @@ again:
 		} else {
 			list_del_init(&reloc_root->root_list);
 		}
-		btrfs_drop_snapshot(reloc_root, rc->block_rsv, 0);
+		btrfs_drop_snapshot(reloc_root, rc->block_rsv, 0, 1);
 	}
 
 	if (found) {
@@ -2558,7 +2560,7 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 						node->eb->start, blocksize,
 						upper->eb->start,
 						btrfs_header_owner(upper->eb),
-						node->level, 0);
+						node->level, 0, 1);
 			BUG_ON(ret);
 
 			ret = btrfs_drop_subtree(trans, root, eb, upper->eb);

fs/btrfs/scrub.c

@@ -309,7 +309,7 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio,
 	u8 ref_level;
 	unsigned long ptr = 0;
 	const int bufsize = 4096;
-	u64 extent_offset;
+	u64 extent_item_pos;
 
 	path = btrfs_alloc_path();
 
@@ -329,12 +329,13 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio,
 	if (ret < 0)
 		goto out;
 
-	extent_offset = swarn.logical - found_key.objectid;
+	extent_item_pos = swarn.logical - found_key.objectid;
 	swarn.extent_item_size = found_key.offset;
 
 	eb = path->nodes[0];
 	ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
 	item_size = btrfs_item_size_nr(eb, path->slots[0]);
+	btrfs_release_path(path);
 
 	if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
 		do {
@@ -351,7 +352,7 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio,
 	} else {
 		swarn.path = path;
 		iterate_extent_inodes(fs_info, path, found_key.objectid,
-					extent_offset,
+					extent_item_pos,
 					scrub_print_warning_inode, &swarn);
 	}
 

fs/btrfs/transaction.c

@@ -36,6 +36,8 @@ static noinline void put_transaction(struct btrfs_transaction *transaction)
 	WARN_ON(atomic_read(&transaction->use_count) == 0);
 	if (atomic_dec_and_test(&transaction->use_count)) {
 		BUG_ON(!list_empty(&transaction->list));
+		WARN_ON(transaction->delayed_refs.root.rb_node);
+		WARN_ON(!list_empty(&transaction->delayed_refs.seq_head));
 		memset(transaction, 0, sizeof(*transaction));
 		kmem_cache_free(btrfs_transaction_cachep, transaction);
 	}
@@ -108,8 +110,11 @@ loop:
 	cur_trans->delayed_refs.num_heads = 0;
 	cur_trans->delayed_refs.flushing = 0;
 	cur_trans->delayed_refs.run_delayed_start = 0;
+	cur_trans->delayed_refs.seq = 1;
+	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);
@@ -1386,9 +1391,9 @@ int btrfs_clean_old_snapshots(struct btrfs_root *root)
 
 		if (btrfs_header_backref_rev(root->node) <
 		    BTRFS_MIXED_BACKREF_REV)
-			btrfs_drop_snapshot(root, NULL, 0);
+			btrfs_drop_snapshot(root, NULL, 0, 0);
 		else
-			btrfs_drop_snapshot(root, NULL, 1);
+			btrfs_drop_snapshot(root, NULL, 1, 0);
 	}
 	return 0;
 }

fs/btrfs/tree-log.c

@@ -589,7 +589,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 				ret = btrfs_inc_extent_ref(trans, root,
 						ins.objectid, ins.offset,
 						0, root->root_key.objectid,
-						key->objectid, offset);
+						key->objectid, offset, 0);
 				BUG_ON(ret);
 			} else {
 				/*

fs/btrfs/ulist.c

@@ -0,0 +1,220 @@
+/*
+ * Copyright (C) 2011 STRATO AG
+ * written by Arne Jansen <sensille@gmx.net>
+ * Distributed under the GNU GPL license version 2.
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include "ulist.h"
+
+/*
+ * ulist is a generic data structure to hold a collection of unique u64
+ * values. The only operations it supports is adding to the list and
+ * enumerating it.
+ * It is possible to store an auxiliary value along with the key.
+ *
+ * The implementation is preliminary and can probably be sped up
+ * significantly. A first step would be to store the values in an rbtree
+ * as soon as ULIST_SIZE is exceeded.
+ *
+ * A sample usage for ulists is the enumeration of directed graphs without
+ * visiting a node twice. The pseudo-code could look like this:
+ *
+ * ulist = ulist_alloc();
+ * ulist_add(ulist, root);
+ * elem = NULL;
+ *
+ * while ((elem = ulist_next(ulist, elem)) {
+ * 	for (all child nodes n in elem)
+ *		ulist_add(ulist, n);
+ *	do something useful with the node;
+ * }
+ * ulist_free(ulist);
+ *
+ * This assumes the graph nodes are adressable by u64. This stems from the
+ * usage for tree enumeration in btrfs, where the logical addresses are
+ * 64 bit.
+ *
+ * It is also useful for tree enumeration which could be done elegantly
+ * recursively, but is not possible due to kernel stack limitations. The
+ * loop would be similar to the above.
+ */
+
+/**
+ * ulist_init - freshly initialize a ulist
+ * @ulist:	the ulist to initialize
+ *
+ * Note: don't use this function to init an already used ulist, use
+ * ulist_reinit instead.
+ */
+void ulist_init(struct ulist *ulist)
+{
+	ulist->nnodes = 0;
+	ulist->nodes = ulist->int_nodes;
+	ulist->nodes_alloced = ULIST_SIZE;
+}
+EXPORT_SYMBOL(ulist_init);
+
+/**
+ * ulist_fini - free up additionally allocated memory for the ulist
+ * @ulist:	the ulist from which to free the additional memory
+ *
+ * This is useful in cases where the base 'struct ulist' has been statically
+ * allocated.
+ */
+void ulist_fini(struct ulist *ulist)
+{
+	/*
+	 * The first ULIST_SIZE elements are stored inline in struct ulist.
+	 * Only if more elements are alocated they need to be freed.
+	 */
+	if (ulist->nodes_alloced > ULIST_SIZE)
+		kfree(ulist->nodes);
+	ulist->nodes_alloced = 0;	/* in case ulist_fini is called twice */
+}
+EXPORT_SYMBOL(ulist_fini);
+
+/**
+ * ulist_reinit - prepare a ulist for reuse
+ * @ulist:	ulist to be reused
+ *
+ * Free up all additional memory allocated for the list elements and reinit
+ * the ulist.
+ */
+void ulist_reinit(struct ulist *ulist)
+{
+	ulist_fini(ulist);
+	ulist_init(ulist);
+}
+EXPORT_SYMBOL(ulist_reinit);
+
+/**
+ * ulist_alloc - dynamically allocate a ulist
+ * @gfp_mask:	allocation flags to for base allocation
+ *
+ * The allocated ulist will be returned in an initialized state.
+ */
+struct ulist *ulist_alloc(unsigned long gfp_mask)
+{
+	struct ulist *ulist = kmalloc(sizeof(*ulist), gfp_mask);
+
+	if (!ulist)
+		return NULL;
+
+	ulist_init(ulist);
+
+	return ulist;
+}
+EXPORT_SYMBOL(ulist_alloc);
+
+/**
+ * ulist_free - free dynamically allocated ulist
+ * @ulist:	ulist to free
+ *
+ * It is not necessary to call ulist_fini before.
+ */
+void ulist_free(struct ulist *ulist)
+{
+	if (!ulist)
+		return;
+	ulist_fini(ulist);
+	kfree(ulist);
+}
+EXPORT_SYMBOL(ulist_free);
+
+/**
+ * ulist_add - add an element to the ulist
+ * @ulist:	ulist to add the element to
+ * @val:	value to add to ulist
+ * @aux:	auxiliary value to store along with val
+ * @gfp_mask:	flags to use for allocation
+ *
+ * Note: locking must be provided by the caller. In case of rwlocks write
+ *       locking is needed
+ *
+ * Add an element to a ulist. The @val will only be added if it doesn't
+ * already exist. If it is added, the auxiliary value @aux is stored along with
+ * it. In case @val already exists in the ulist, @aux is ignored, even if
+ * it differs from the already stored value.
+ *
+ * ulist_add returns 0 if @val already exists in ulist and 1 if @val has been
+ * inserted.
+ * In case of allocation failure -ENOMEM is returned and the ulist stays
+ * unaltered.
+ */
+int ulist_add(struct ulist *ulist, u64 val, unsigned long aux,
+	      unsigned long gfp_mask)
+{
+	int i;
+
+	for (i = 0; i < ulist->nnodes; ++i) {
+		if (ulist->nodes[i].val == val)
+			return 0;
+	}
+
+	if (ulist->nnodes >= ulist->nodes_alloced) {
+		u64 new_alloced = ulist->nodes_alloced + 128;
+		struct ulist_node *new_nodes;
+		void *old = NULL;
+
+		/*
+		 * if nodes_alloced == ULIST_SIZE no memory has been allocated
+		 * yet, so pass NULL to krealloc
+		 */
+		if (ulist->nodes_alloced > ULIST_SIZE)
+			old = ulist->nodes;
+
+		new_nodes = krealloc(old, sizeof(*new_nodes) * new_alloced,
+				     gfp_mask);
+		if (!new_nodes)
+			return -ENOMEM;
+
+		if (!old)
+			memcpy(new_nodes, ulist->int_nodes,
+			       sizeof(ulist->int_nodes));
+
+		ulist->nodes = new_nodes;
+		ulist->nodes_alloced = new_alloced;
+	}
+	ulist->nodes[ulist->nnodes].val = val;
+	ulist->nodes[ulist->nnodes].aux = aux;
+	++ulist->nnodes;
+
+	return 1;
+}
+EXPORT_SYMBOL(ulist_add);
+
+/**
+ * ulist_next - iterate ulist
+ * @ulist:	ulist to iterate
+ * @prev:	previously returned element or %NULL to start iteration
+ *
+ * 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
+ * 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)
+{
+	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)
+		return NULL;
+
+	return &ulist->nodes[next];
+}
+EXPORT_SYMBOL(ulist_next);

fs/btrfs/ulist.h

@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2011 STRATO AG
+ * written by Arne Jansen <sensille@gmx.net>
+ * Distributed under the GNU GPL license version 2.
+ *
+ */
+
+#ifndef __ULIST__
+#define __ULIST__
+
+/*
+ * ulist is a generic data structure to hold a collection of unique u64
+ * values. The only operations it supports is adding to the list and
+ * enumerating it.
+ * It is possible to store an auxiliary value along with the key.
+ *
+ * The implementation is preliminary and can probably be sped up
+ * significantly. A first step would be to store the values in an rbtree
+ * as soon as ULIST_SIZE is exceeded.
+ */
+
+/*
+ * number of elements statically allocated inside struct ulist
+ */
+#define ULIST_SIZE 16
+
+/*
+ * element of the list
+ */
+struct ulist_node {
+	u64 val;		/* value to store */
+	unsigned long aux;	/* auxiliary value saved along with the val */
+};
+
+struct ulist {
+	/*
+	 * number of elements stored in list
+	 */
+	unsigned long nnodes;
+
+	/*
+	 * number of nodes we already have room for
+	 */
+	unsigned long nodes_alloced;
+
+	/*
+	 * pointer to the array storing the elements. The first ULIST_SIZE
+	 * elements are stored inline. In this case the it points to int_nodes.
+	 * After exceeding ULIST_SIZE, dynamic memory is allocated.
+	 */
+	struct ulist_node *nodes;
+
+	/*
+	 * inline storage space for the first ULIST_SIZE entries
+	 */
+	struct ulist_node int_nodes[ULIST_SIZE];
+};
+
+void ulist_init(struct ulist *ulist);
+void ulist_fini(struct ulist *ulist);
+void ulist_reinit(struct ulist *ulist);
+struct ulist *ulist_alloc(unsigned long gfp_mask);
+void ulist_free(struct ulist *ulist);
+int ulist_add(struct ulist *ulist, u64 val, unsigned long aux,
+	      unsigned long gfp_mask);
+struct ulist_node *ulist_next(struct ulist *ulist, struct ulist_node *prev);
+
+#endif