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

21 files changed, 1639 insertions, 419 deletions

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index c0ddfd29c5e..70798407b9a 100644
--- a/fs/btrfs/Makefile
+++ b/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
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 22c64fff1bd..b9a843226de 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -19,18 +19,789 @@
 #include "ctree.h"
 #include "disk-io.h"
 #include "backref.h"
+#include "ulist.h"
+#include "transaction.h"
+#include "delayed-ref.h"
 
-struct __data_ref {
+/*
+ * this structure records all encountered refs on the way up to the root
+ */
+struct __prelim_ref {
 	struct list_head list;
-	u64 inum;
-	u64 root;
-	u64 extent_data_item_offset;
+	u64 root_id;
+	struct btrfs_key key;
+	int level;
+	int count;
+	u64 parent;
+	u64 wanted_disk_byte;
 };
 
-struct __shared_ref {
-	struct list_head list;
+static int __add_prelim_ref(struct list_head *head, u64 root_id,
+			    struct btrfs_key *key, int level, u64 parent,
+			    u64 wanted_disk_byte, int count)
+{
+	struct __prelim_ref *ref;
+
+	/* in case we're adding delayed refs, we're holding the refs spinlock */
+	ref = kmalloc(sizeof(*ref), GFP_ATOMIC);
+	if (!ref)
+		return -ENOMEM;
+
+	ref->root_id = root_id;
+	if (key)
+		ref->key = *key;
+	else
+		memset(&ref->key, 0, sizeof(ref->key));
+
+	ref->level = level;
+	ref->count = count;
+	ref->parent = parent;
+	ref->wanted_disk_byte = wanted_disk_byte;
+	list_add_tail(&ref->list, head);
+
+	return 0;
+}
+
+static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
+				struct ulist *parents,
+				struct extent_buffer *eb, int level,
+				u64 wanted_objectid, u64 wanted_disk_byte)
+{
+	int ret;
+	int slot;
+	struct btrfs_file_extent_item *fi;
+	struct btrfs_key key;
 	u64 disk_byte;
-};
+
+add_parent:
+	ret = ulist_add(parents, eb->start, 0, GFP_NOFS);
+	if (ret < 0)
+		return ret;
+
+	if (level != 0)
+		return 0;
+
+	/*
+	 * if the current leaf is full with EXTENT_DATA items, we must
+	 * check the next one if that holds a reference as well.
+	 * ref->count cannot be used to skip this check.
+	 * repeat this until we don't find any additional EXTENT_DATA items.
+	 */
+	while (1) {
+		ret = btrfs_next_leaf(root, path);
+		if (ret < 0)
+			return ret;
+		if (ret)
+			return 0;
+
+		eb = path->nodes[0];
+		for (slot = 0; slot < btrfs_header_nritems(eb); ++slot) {
+			btrfs_item_key_to_cpu(eb, &key, slot);
+			if (key.objectid != wanted_objectid ||
+			    key.type != BTRFS_EXTENT_DATA_KEY)
+				return 0;
+			fi = btrfs_item_ptr(eb, slot,
+						struct btrfs_file_extent_item);
+			disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
+			if (disk_byte == wanted_disk_byte)
+				goto add_parent;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * resolve an indirect backref in the form (root_id, key, level)
+ * to a logical address
+ */
+static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
+					struct __prelim_ref *ref,
+					struct ulist *parents)
+{
+	struct btrfs_path *path;
+	struct btrfs_root *root;
+	struct btrfs_key root_key;
+	struct btrfs_key key = {0};
+	struct extent_buffer *eb;
+	int ret = 0;
+	int root_level;
+	int level = ref->level;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	root_key.objectid = ref->root_id;
+	root_key.type = BTRFS_ROOT_ITEM_KEY;
+	root_key.offset = (u64)-1;
+	root = btrfs_read_fs_root_no_name(fs_info, &root_key);
+	if (IS_ERR(root)) {
+		ret = PTR_ERR(root);
+		goto out;
+	}
+
+	rcu_read_lock();
+	root_level = btrfs_header_level(root->node);
+	rcu_read_unlock();
+
+	if (root_level + 1 == level)
+		goto out;
+
+	path->lowest_level = level;
+	ret = btrfs_search_slot(NULL, root, &ref->key, path, 0, 0);
+	pr_debug("search slot in root %llu (level %d, ref count %d) returned "
+		 "%d for key (%llu %u %llu)\n",
+		 (unsigned long long)ref->root_id, level, ref->count, ret,
+		 (unsigned long long)ref->key.objectid, ref->key.type,
+		 (unsigned long long)ref->key.offset);
+	if (ret < 0)
+		goto out;
+
+	eb = path->nodes[level];
+	if (!eb) {
+		WARN_ON(1);
+		ret = 1;
+		goto out;
+	}
+
+	if (level == 0) {
+		if (ret == 1 && path->slots[0] >= btrfs_header_nritems(eb)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret)
+				goto out;
+			eb = path->nodes[0];
+		}
+
+		btrfs_item_key_to_cpu(eb, &key, path->slots[0]);
+	}
+
+	/* the last two parameters will only be used for level == 0 */
+	ret = add_all_parents(root, path, parents, eb, level, key.objectid,
+				ref->wanted_disk_byte);
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
+/*
+ * resolve all indirect backrefs from the list
+ */
+static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info,
+				   struct list_head *head)
+{
+	int err;
+	int ret = 0;
+	struct __prelim_ref *ref;
+	struct __prelim_ref *ref_safe;
+	struct __prelim_ref *new_ref;
+	struct ulist *parents;
+	struct ulist_node *node;
+
+	parents = ulist_alloc(GFP_NOFS);
+	if (!parents)
+		return -ENOMEM;
+
+	/*
+	 * _safe allows us to insert directly after the current item without
+	 * iterating over the newly inserted items.
+	 * we're also allowed to re-assign ref during iteration.
+	 */
+	list_for_each_entry_safe(ref, ref_safe, head, list) {
+		if (ref->parent)	/* already direct */
+			continue;
+		if (ref->count == 0)
+			continue;
+		err = __resolve_indirect_ref(fs_info, ref, parents);
+		if (err) {
+			if (ret == 0)
+				ret = err;
+			continue;
+		}
+
+		/* we put the first parent into the ref at hand */
+		node = ulist_next(parents, NULL);
+		ref->parent = node ? node->val : 0;
+
+		/* additional parents require new refs being added here */
+		while ((node = ulist_next(parents, node))) {
+			new_ref = kmalloc(sizeof(*new_ref), GFP_NOFS);
+			if (!new_ref) {
+				ret = -ENOMEM;
+				break;
+			}
+			memcpy(new_ref, ref, sizeof(*ref));
+			new_ref->parent = node->val;
+			list_add(&new_ref->list, &ref->list);
+		}
+		ulist_reinit(parents);
+	}
+
+	ulist_free(parents);
+	return ret;
+}
+
+/*
+ * merge two lists of backrefs and adjust counts accordingly
+ *
+ * mode = 1: merge identical keys, if key is set
+ * mode = 2: merge identical parents
+ */
+static int __merge_refs(struct list_head *head, int mode)
+{
+	struct list_head *pos1;
+
+	list_for_each(pos1, head) {
+		struct list_head *n2;
+		struct list_head *pos2;
+		struct __prelim_ref *ref1;
+
+		ref1 = list_entry(pos1, struct __prelim_ref, list);
+
+		if (mode == 1 && ref1->key.type == 0)
+			continue;
+		for (pos2 = pos1->next, n2 = pos2->next; pos2 != head;
+		     pos2 = n2, n2 = pos2->next) {
+			struct __prelim_ref *ref2;
+
+			ref2 = list_entry(pos2, struct __prelim_ref, list);
+
+			if (mode == 1) {
+				if (memcmp(&ref1->key, &ref2->key,
+					   sizeof(ref1->key)) ||
+				    ref1->level != ref2->level ||
+				    ref1->root_id != ref2->root_id)
+					continue;
+				ref1->count += ref2->count;
+			} else {
+				if (ref1->parent != ref2->parent)
+					continue;
+				ref1->count += ref2->count;
+			}
+			list_del(&ref2->list);
+			kfree(ref2);
+		}
+
+	}
+	return 0;
+}
+
+/*
+ * add all currently queued delayed refs from this head whose seq nr is
+ * smaller or equal that seq to the list
+ */
+static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
+			      struct btrfs_key *info_key,
+			      struct list_head *prefs)
+{
+	struct btrfs_delayed_extent_op *extent_op = head->extent_op;
+	struct rb_node *n = &head->node.rb_node;
+	int sgn;
+	int ret;
+
+	if (extent_op && extent_op->update_key)
+		btrfs_disk_key_to_cpu(info_key, &extent_op->key);
+
+	while ((n = rb_prev(n))) {
+		struct btrfs_delayed_ref_node *node;
+		node = rb_entry(n, struct btrfs_delayed_ref_node,
+				rb_node);
+		if (node->bytenr != head->node.bytenr)
+			break;
+		WARN_ON(node->is_head);
+
+		if (node->seq > seq)
+			continue;
+
+		switch (node->action) {
+		case BTRFS_ADD_DELAYED_EXTENT:
+		case BTRFS_UPDATE_DELAYED_HEAD:
+			WARN_ON(1);
+			continue;
+		case BTRFS_ADD_DELAYED_REF:
+			sgn = 1;
+			break;
+		case BTRFS_DROP_DELAYED_REF:
+			sgn = -1;
+			break;
+		default:
+			BUG_ON(1);
+		}
+		switch (node->type) {
+		case BTRFS_TREE_BLOCK_REF_KEY: {
+			struct btrfs_delayed_tree_ref *ref;
+
+			ref = btrfs_delayed_node_to_tree_ref(node);
+			ret = __add_prelim_ref(prefs, ref->root, info_key,
+					       ref->level + 1, 0, node->bytenr,
+					       node->ref_mod * sgn);
+			break;
+		}
+		case BTRFS_SHARED_BLOCK_REF_KEY: {
+			struct btrfs_delayed_tree_ref *ref;
+
+			ref = btrfs_delayed_node_to_tree_ref(node);
+			ret = __add_prelim_ref(prefs, ref->root, info_key,
+					       ref->level + 1, ref->parent,
+					       node->bytenr,
+					       node->ref_mod * sgn);
+			break;
+		}
+		case BTRFS_EXTENT_DATA_REF_KEY: {
+			struct btrfs_delayed_data_ref *ref;
+			struct btrfs_key key;
+
+			ref = btrfs_delayed_node_to_data_ref(node);
+
+			key.objectid = ref->objectid;
+			key.type = BTRFS_EXTENT_DATA_KEY;
+			key.offset = ref->offset;
+			ret = __add_prelim_ref(prefs, ref->root, &key, 0, 0,
+					       node->bytenr,
+					       node->ref_mod * sgn);
+			break;
+		}
+		case BTRFS_SHARED_DATA_REF_KEY: {
+			struct btrfs_delayed_data_ref *ref;
+			struct btrfs_key key;
+
+			ref = btrfs_delayed_node_to_data_ref(node);
+
+			key.objectid = ref->objectid;
+			key.type = BTRFS_EXTENT_DATA_KEY;
+			key.offset = ref->offset;
+			ret = __add_prelim_ref(prefs, ref->root, &key, 0,
+					       ref->parent, node->bytenr,
+					       node->ref_mod * sgn);
+			break;
+		}
+		default:
+			WARN_ON(1);
+		}
+		BUG_ON(ret);
+	}
+
+	return 0;
+}
+
+/*
+ * add all inline backrefs for bytenr to the list
+ */
+static int __add_inline_refs(struct btrfs_fs_info *fs_info,
+			     struct btrfs_path *path, u64 bytenr,
+			     struct btrfs_key *info_key, int *info_level,
+			     struct list_head *prefs)
+{
+	int ret;
+	int slot;
+	struct extent_buffer *leaf;
+	struct btrfs_key key;
+	unsigned long ptr;
+	unsigned long end;
+	struct btrfs_extent_item *ei;
+	u64 flags;
+	u64 item_size;
+
+	/*
+	 * enumerate all inline refs
+	 */
+	leaf = path->nodes[0];
+	slot = path->slots[0] - 1;
+
+	item_size = btrfs_item_size_nr(leaf, slot);
+	BUG_ON(item_size < sizeof(*ei));
+
+	ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
+	flags = btrfs_extent_flags(leaf, ei);
+
+	ptr = (unsigned long)(ei + 1);
+	end = (unsigned long)ei + item_size;
+
+	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+		struct btrfs_tree_block_info *info;
+		struct btrfs_disk_key disk_key;
+
+		info = (struct btrfs_tree_block_info *)ptr;
+		*info_level = btrfs_tree_block_level(leaf, info);
+		btrfs_tree_block_key(leaf, info, &disk_key);
+		btrfs_disk_key_to_cpu(info_key, &disk_key);
+		ptr += sizeof(struct btrfs_tree_block_info);
+		BUG_ON(ptr > end);
+	} else {
+		BUG_ON(!(flags & BTRFS_EXTENT_FLAG_DATA));
+	}
+
+	while (ptr < end) {
+		struct btrfs_extent_inline_ref *iref;
+		u64 offset;
+		int type;
+
+		iref = (struct btrfs_extent_inline_ref *)ptr;
+		type = btrfs_extent_inline_ref_type(leaf, iref);
+		offset = btrfs_extent_inline_ref_offset(leaf, iref);
+
+		switch (type) {
+		case BTRFS_SHARED_BLOCK_REF_KEY:
+			ret = __add_prelim_ref(prefs, 0, info_key,
+						*info_level + 1, offset,
+						bytenr, 1);
+			break;
+		case BTRFS_SHARED_DATA_REF_KEY: {
+			struct btrfs_shared_data_ref *sdref;
+			int count;
+
+			sdref = (struct btrfs_shared_data_ref *)(iref + 1);
+			count = btrfs_shared_data_ref_count(leaf, sdref);
+			ret = __add_prelim_ref(prefs, 0, NULL, 0, offset,
+					       bytenr, count);
+			break;
+		}
+		case BTRFS_TREE_BLOCK_REF_KEY:
+			ret = __add_prelim_ref(prefs, offset, info_key,
+					       *info_level + 1, 0, bytenr, 1);
+			break;
+		case BTRFS_EXTENT_DATA_REF_KEY: {
+			struct btrfs_extent_data_ref *dref;
+			int count;
+			u64 root;
+
+			dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+			count = btrfs_extent_data_ref_count(leaf, dref);
+			key.objectid = btrfs_extent_data_ref_objectid(leaf,
+								      dref);
+			key.type = BTRFS_EXTENT_DATA_KEY;
+			key.offset = btrfs_extent_data_ref_offset(leaf, dref);
+			root = btrfs_extent_data_ref_root(leaf, dref);
+			ret = __add_prelim_ref(prefs, root, &key, 0, 0, bytenr,
+						count);
+			break;
+		}
+		default:
+			WARN_ON(1);
+		}
+		BUG_ON(ret);
+		ptr += btrfs_extent_inline_ref_size(type);
+	}
+
+	return 0;
+}
+
+/*
+ * add all non-inline backrefs for bytenr to the list
+ */
+static int __add_keyed_refs(struct btrfs_fs_info *fs_info,
+			    struct btrfs_path *path, u64 bytenr,
+			    struct btrfs_key *info_key, int info_level,
+			    struct list_head *prefs)
+{
+	struct btrfs_root *extent_root = fs_info->extent_root;
+	int ret;
+	int slot;
+	struct extent_buffer *leaf;
+	struct btrfs_key key;
+
+	while (1) {
+		ret = btrfs_next_item(extent_root, path);
+		if (ret < 0)
+			break;
+		if (ret) {
+			ret = 0;
+			break;
+		}
+
+		slot = path->slots[0];
+		leaf = path->nodes[0];
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+
+		if (key.objectid != bytenr)
+			break;
+		if (key.type < BTRFS_TREE_BLOCK_REF_KEY)
+			continue;
+		if (key.type > BTRFS_SHARED_DATA_REF_KEY)
+			break;
+
+		switch (key.type) {
+		case BTRFS_SHARED_BLOCK_REF_KEY:
+			ret = __add_prelim_ref(prefs, 0, info_key,
+						info_level + 1, key.offset,
+						bytenr, 1);
+			break;
+		case BTRFS_SHARED_DATA_REF_KEY: {
+			struct btrfs_shared_data_ref *sdref;
+			int count;
+
+			sdref = btrfs_item_ptr(leaf, slot,
+					      struct btrfs_shared_data_ref);
+			count = btrfs_shared_data_ref_count(leaf, sdref);
+			ret = __add_prelim_ref(prefs, 0, NULL, 0, key.offset,
+						bytenr, count);
+			break;
+		}
+		case BTRFS_TREE_BLOCK_REF_KEY:
+			ret = __add_prelim_ref(prefs, key.offset, info_key,
+						info_level + 1, 0, bytenr, 1);
+			break;
+		case BTRFS_EXTENT_DATA_REF_KEY: {
+			struct btrfs_extent_data_ref *dref;
+			int count;
+			u64 root;
+
+			dref = btrfs_item_ptr(leaf, slot,
+					      struct btrfs_extent_data_ref);
+			count = btrfs_extent_data_ref_count(leaf, dref);
+			key.objectid = btrfs_extent_data_ref_objectid(leaf,
+								      dref);
+			key.type = BTRFS_EXTENT_DATA_KEY;
+			key.offset = btrfs_extent_data_ref_offset(leaf, dref);
+			root = btrfs_extent_data_ref_root(leaf, dref);
+			ret = __add_prelim_ref(prefs, root, &key, 0, 0,
+						bytenr, count);
+			break;
+		}
+		default:
+			WARN_ON(1);
+		}
+		BUG_ON(ret);
+	}
+
+	return ret;
+}
+
+/*
+ * this adds all existing backrefs (inline backrefs, backrefs and delayed
+ * refs) for the given bytenr to the refs list, merges duplicates and resolves
+ * indirect refs to their parent bytenr.
+ * When roots are found, they're added to the roots list
+ *
+ * FIXME some caching might speed things up
+ */
+static int find_parent_nodes(struct btrfs_trans_handle *trans,
+			     struct btrfs_fs_info *fs_info, u64 bytenr,
+			     u64 seq, struct ulist *refs, struct ulist *roots)
+{
+	struct btrfs_key key;
+	struct btrfs_path *path;
+	struct btrfs_key info_key = { 0 };
+	struct btrfs_delayed_ref_root *delayed_refs = NULL;
+	struct btrfs_delayed_ref_head *head = NULL;
+	int info_level = 0;
+	int ret;
+	struct list_head prefs_delayed;
+	struct list_head prefs;
+	struct __prelim_ref *ref;
+
+	INIT_LIST_HEAD(&prefs);
+	INIT_LIST_HEAD(&prefs_delayed);
+
+	key.objectid = bytenr;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = (u64)-1;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	/*
+	 * grab both a lock on the path and a lock on the delayed ref head.
+	 * We need both to get a consistent picture of how the refs look
+	 * at a specified point in time
+	 */
+again:
+	ret = btrfs_search_slot(trans, fs_info->extent_root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	BUG_ON(ret == 0);
+
+	/*
+	 * look if there are updates for this ref queued and lock the head
+	 */
+	delayed_refs = &trans->transaction->delayed_refs;
+	spin_lock(&delayed_refs->lock);
+	head = btrfs_find_delayed_ref_head(trans, bytenr);
+	if (head) {
+		if (!mutex_trylock(&head->mutex)) {
+			atomic_inc(&head->node.refs);
+			spin_unlock(&delayed_refs->lock);
+
+			btrfs_release_path(path);
+
+			/*
+			 * Mutex was contended, block until it's
+			 * released and try again
+			 */
+			mutex_lock(&head->mutex);
+			mutex_unlock(&head->mutex);
+			btrfs_put_delayed_ref(&head->node);
+			goto again;
+		}
+		ret = __add_delayed_refs(head, seq, &info_key, &prefs_delayed);
+		if (ret)
+			goto out;
+	}
+	spin_unlock(&delayed_refs->lock);
+
+	if (path->slots[0]) {
+		struct extent_buffer *leaf;
+		int slot;
+
+		leaf = path->nodes[0];
+		slot = path->slots[0] - 1;
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.objectid == bytenr &&
+		    key.type == BTRFS_EXTENT_ITEM_KEY) {
+			ret = __add_inline_refs(fs_info, path, bytenr,
+						&info_key, &info_level, &prefs);
+			if (ret)
+				goto out;
+			ret = __add_keyed_refs(fs_info, path, bytenr, &info_key,
+					       info_level, &prefs);
+			if (ret)
+				goto out;
+		}
+	}
+	btrfs_release_path(path);
+
+	/*
+	 * when adding the delayed refs above, the info_key might not have
+	 * been known yet. Go over the list and replace the missing keys
+	 */
+	list_for_each_entry(ref, &prefs_delayed, list) {
+		if ((ref->key.offset | ref->key.type | ref->key.objectid) == 0)
+			memcpy(&ref->key, &info_key, sizeof(ref->key));
+	}
+	list_splice_init(&prefs_delayed, &prefs);
+
+	ret = __merge_refs(&prefs, 1);
+	if (ret)
+		goto out;
+
+	ret = __resolve_indirect_refs(fs_info, &prefs);
+	if (ret)
+		goto out;
+
+	ret = __merge_refs(&prefs, 2);
+	if (ret)
+		goto out;
+
+	while (!list_empty(&prefs)) {
+		ref = list_first_entry(&prefs, struct __prelim_ref, list);
+		list_del(&ref->list);
+		if (ref->count < 0)
+			WARN_ON(1);
+		if (ref->count && ref->root_id && ref->parent == 0) {
+			/* no parent == root of tree */
+			ret = ulist_add(roots, ref->root_id, 0, GFP_NOFS);
+			BUG_ON(ret < 0);
+		}
+		if (ref->count && ref->parent) {
+			ret = ulist_add(refs, ref->parent, 0, GFP_NOFS);
+			BUG_ON(ret < 0);
+		}
+		kfree(ref);
+	}
+
+out:
+	if (head)
+		mutex_unlock(&head->mutex);
+	btrfs_free_path(path);
+	while (!list_empty(&prefs)) {
+		ref = list_first_entry(&prefs, struct __prelim_ref, list);
+		list_del(&ref->list);
+		kfree(ref);
+	}
+	while (!list_empty(&prefs_delayed)) {
+		ref = list_first_entry(&prefs_delayed, struct __prelim_ref,
+				       list);
+		list_del(&ref->list);
+		kfree(ref);
+	}
+
+	return ret;
+}
+
+/*
+ * Finds all leafs with a reference to the specified combination of bytenr and
+ * offset. key_list_head will point to a list of corresponding keys (caller must
+ * free each list element). The leafs will be stored in the leafs ulist, which
+ * must be freed with ulist_free.
+ *
+ * returns 0 on success, <0 on error
+ */
+static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans,
+				struct btrfs_fs_info *fs_info, u64 bytenr,
+				u64 num_bytes, u64 seq, struct ulist **leafs)
+{
+	struct ulist *tmp;
+	int ret;
+
+	tmp = ulist_alloc(GFP_NOFS);
+	if (!tmp)
+		return -ENOMEM;
+	*leafs = ulist_alloc(GFP_NOFS);
+	if (!*leafs) {
+		ulist_free(tmp);
+		return -ENOMEM;
+	}
+
+	ret = find_parent_nodes(trans, fs_info, bytenr, seq, *leafs, tmp);
+	ulist_free(tmp);
+
+	if (ret < 0 && ret != -ENOENT) {
+		ulist_free(*leafs);
+		return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * walk all backrefs for a given extent to find all roots that reference this
+ * extent. Walking a backref means finding all extents that reference this
+ * extent and in turn walk the backrefs of those, too. Naturally this is a
+ * recursive process, but here it is implemented in an iterative fashion: We
+ * find all referencing extents for the extent in question and put them on a
+ * list. In turn, we find all referencing extents for those, further appending
+ * to the list. The way we iterate the list allows adding more elements after
+ * the current while iterating. The process stops when we reach the end of the
+ * list. Found roots are added to the roots list.
+ *
+ * returns 0 on success, < 0 on error.
+ */
+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 ulist *tmp;
+	struct ulist_node *node = NULL;
+	int ret;
+
+	tmp = ulist_alloc(GFP_NOFS);
+	if (!tmp)
+		return -ENOMEM;
+	*roots = ulist_alloc(GFP_NOFS);
+	if (!*roots) {
+		ulist_free(tmp);
+		return -ENOMEM;
+	}
+
+	while (1) {
+		ret = find_parent_nodes(trans, fs_info, bytenr, seq,
+					tmp, *roots);
+		if (ret < 0 && ret != -ENOENT) {
+			ulist_free(tmp);
+			ulist_free(*roots);
+			return ret;
+		}
+		node = ulist_next(tmp, node);
+		if (!node)
+			break;
+		bytenr = node->val;
+	}
+
+	ulist_free(tmp);
+	return 0;
+}
+
 
 static int __inode_info(u64 inum, u64 ioff, u8 key_type,
 			struct btrfs_root *fs_root, struct btrfs_path *path,
@@ -181,8 +952,11 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 	btrfs_item_key_to_cpu(path->nodes[0], found_key, path->slots[0]);
 	if (found_key->type != BTRFS_EXTENT_ITEM_KEY ||
 	    found_key->objectid > logical ||
-	    found_key->objectid + found_key->offset <= logical)
+	    found_key->objectid + found_key->offset <= logical) {
+		pr_debug("logical %llu is not within any extent\n",
+			 (unsigned long long)logical);
 		return -ENOENT;
+	}
 
 	eb = path->nodes[0];
 	item_size = btrfs_item_size_nr(eb, path->slots[0]);
@@ -191,6 +965,13 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 	ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
 	flags = btrfs_extent_flags(eb, ei);
 
+	pr_debug("logical %llu is at position %llu within the extent (%llu "
+		 "EXTENT_ITEM %llu) flags %#llx size %u\n",
+		 (unsigned long long)logical,
+		 (unsigned long long)(logical - found_key->objectid),
+		 (unsigned long long)found_key->objectid,
+		 (unsigned long long)found_key->offset,
+		 (unsigned long long)flags, item_size);
 	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)
 		return BTRFS_EXTENT_FLAG_TREE_BLOCK;
 	if (flags & BTRFS_EXTENT_FLAG_DATA)
@@ -287,128 +1068,11 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 	return 0;
 }
 
-static int __data_list_add(struct list_head *head, u64 inum,
-				u64 extent_data_item_offset, u64 root)
-{
-	struct __data_ref *ref;
-
-	ref = kmalloc(sizeof(*ref), GFP_NOFS);
-	if (!ref)
-		return -ENOMEM;
-
-	ref->inum = inum;
-	ref->extent_data_item_offset = extent_data_item_offset;
-	ref->root = root;
-	list_add_tail(&ref->list, head);
-
-	return 0;
-}
-
-static int __data_list_add_eb(struct list_head *head, struct extent_buffer *eb,
-				struct btrfs_extent_data_ref *dref)
-{
-	return __data_list_add(head, btrfs_extent_data_ref_objectid(eb, dref),
-				btrfs_extent_data_ref_offset(eb, dref),
-				btrfs_extent_data_ref_root(eb, dref));
-}
-
-static int __shared_list_add(struct list_head *head, u64 disk_byte)
-{
-	struct __shared_ref *ref;
-
-	ref = kmalloc(sizeof(*ref), GFP_NOFS);
-	if (!ref)
-		return -ENOMEM;
-
-	ref->disk_byte = disk_byte;
-	list_add_tail(&ref->list, head);
-
-	return 0;
-}
-
-static int __iter_shared_inline_ref_inodes(struct btrfs_fs_info *fs_info,
-					   u64 logical, u64 inum,
-					   u64 extent_data_item_offset,
-					   u64 extent_offset,
-					   struct btrfs_path *path,
-					   struct list_head *data_refs,
-					   iterate_extent_inodes_t *iterate,
-					   void *ctx)
-{
-	u64 ref_root;
-	u32 item_size;
-	struct btrfs_key key;
-	struct extent_buffer *eb;
-	struct btrfs_extent_item *ei;
-	struct btrfs_extent_inline_ref *eiref;
-	struct __data_ref *ref;
-	int ret;
-	int type;
-	int last;
-	unsigned long ptr = 0;
-
-	WARN_ON(!list_empty(data_refs));
-	ret = extent_from_logical(fs_info, logical, path, &key);
-	if (ret & BTRFS_EXTENT_FLAG_DATA)
-		ret = -EIO;
-	if (ret < 0)
-		goto out;
-
-	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]);
-
-	ret = 0;
-	ref_root = 0;
-	/*
-	 * as done in iterate_extent_inodes, we first build a list of refs to
-	 * iterate, then free the path and then iterate them to avoid deadlocks.
-	 */
-	do {
-		last = __get_extent_inline_ref(&ptr, eb, ei, item_size,
-						&eiref, &type);
-		if (last < 0) {
-			ret = last;
-			goto out;
-		}
-		if (type == BTRFS_TREE_BLOCK_REF_KEY ||
-		    type == BTRFS_SHARED_BLOCK_REF_KEY) {
-			ref_root = btrfs_extent_inline_ref_offset(eb, eiref);
-			ret = __data_list_add(data_refs, inum,
-						extent_data_item_offset,
-						ref_root);
-		}
-	} while (!ret && !last);
-
-	btrfs_release_path(path);
-
-	if (ref_root == 0) {
-		printk(KERN_ERR "btrfs: failed to find tree block ref "
-			"for shared data backref %llu\n", logical);
-		WARN_ON(1);
-		ret = -EIO;
-	}
-
-out:
-	while (!list_empty(data_refs)) {
-		ref = list_first_entry(data_refs, struct __data_ref, list);
-		list_del(&ref->list);
-		if (!ret)
-			ret = iterate(ref->inum, extent_offset +
-					ref->extent_data_item_offset,
-					ref->root, ctx);
-		kfree(ref);
-	}
-
-	return ret;
-}
-
-static int __iter_shared_inline_ref(struct btrfs_fs_info *fs_info,
-				    u64 logical, u64 orig_extent_item_objectid,
-				    u64 extent_offset, struct btrfs_path *path,
-				    struct list_head *data_refs,
-				    iterate_extent_inodes_t *iterate,
-				    void *ctx)
+static int iterate_leaf_refs(struct btrfs_fs_info *fs_info,
+				struct btrfs_path *path, u64 logical,
+				u64 orig_extent_item_objectid,
+				u64 extent_item_pos, u64 root,
+				iterate_extent_inodes_t *iterate, void *ctx)
 {
 	u64 disk_byte;
 	struct btrfs_key key;
@@ -416,8 +1080,10 @@ static int __iter_shared_inline_ref(struct btrfs_fs_info *fs_info,
 	struct extent_buffer *eb;
 	int slot;
 	int nritems;
-	int ret;
-	int found = 0;
+	int ret = 0;
+	int extent_type;
+	u64 data_offset;
+	u64 data_len;
 
 	eb = read_tree_block(fs_info->tree_root, logical,
 				fs_info->tree_root->leafsize, 0);
@@ -435,149 +1101,99 @@ static int __iter_shared_inline_ref(struct btrfs_fs_info *fs_info,
 		if (key.type != BTRFS_EXTENT_DATA_KEY)
 			continue;
 		fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
-		if (!fi) {
-			free_extent_buffer(eb);
-			return -EIO;
-		}
+		extent_type = btrfs_file_extent_type(eb, fi);
+		if (extent_type == BTRFS_FILE_EXTENT_INLINE)
+			continue;
+		/* don't skip BTRFS_FILE_EXTENT_PREALLOC, we can handle that */
 		disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
-		if (disk_byte != orig_extent_item_objectid) {
-			if (found)
-				break;
-			else
-				continue;
-		}
-		++found;
-		ret = __iter_shared_inline_ref_inodes(fs_info, logical,
-							key.objectid,
-							key.offset,
-							extent_offset, path,
-							data_refs,
-							iterate, ctx);
-		if (ret)
-			break;
-	}
+		if (disk_byte != orig_extent_item_objectid)
+			continue;
 
-	if (!found) {
-		printk(KERN_ERR "btrfs: failed to follow shared data backref "
-			"to parent %llu\n", logical);
-		WARN_ON(1);
-		ret = -EIO;
+		data_offset = btrfs_file_extent_offset(eb, fi);
+		data_len = btrfs_file_extent_num_bytes(eb, fi);
+
+		if (extent_item_pos < data_offset ||
+		    extent_item_pos >= data_offset + data_len)
+			continue;
+
+		pr_debug("ref for %llu resolved, key (%llu EXTEND_DATA %llu), "
+				"root %llu\n", orig_extent_item_objectid,
+				key.objectid, key.offset, root);
+		ret = iterate(key.objectid,
+				key.offset + (extent_item_pos - data_offset),
+				root, ctx);
+		if (ret) {
+			pr_debug("stopping iteration because ret=%d\n", ret);
+			break;
+		}
 	}
 
 	free_extent_buffer(eb);
+
 	return ret;
 }
 
 /*
  * calls iterate() for every inode that references the extent identified by
- * the given parameters. will use the path given as a parameter and return it
- * released.
+ * the given parameters.
  * when the iterator function returns a non-zero value, iteration stops.
+ * path is guaranteed to be in released state when iterate() is called.
  */
 int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 				struct btrfs_path *path,
-				u64 extent_item_objectid,
-				u64 extent_offset,
+				u64 extent_item_objectid, u64 extent_item_pos,
 				iterate_extent_inodes_t *iterate, void *ctx)
 {
-	unsigned long ptr = 0;
-	int last;
 	int ret;
-	int type;
-	u64 logical;
-	u32 item_size;
-	struct btrfs_extent_inline_ref *eiref;
-	struct btrfs_extent_data_ref *dref;
-	struct extent_buffer *eb;
-	struct btrfs_extent_item *ei;
-	struct btrfs_key key;
 	struct list_head data_refs = LIST_HEAD_INIT(data_refs);
 	struct list_head shared_refs = LIST_HEAD_INIT(shared_refs);
-	struct __data_ref *ref_d;
-	struct __shared_ref *ref_s;
-
-	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]);
-
-	/* first we iterate the inline refs, ... */
-	do {
-		last = __get_extent_inline_ref(&ptr, eb, ei, item_size,
-						&eiref, &type);
-		if (last == -ENOENT) {
-			ret = 0;
-			break;
-		}
-		if (last < 0) {
-			ret = last;
-			break;
-		}
+	struct btrfs_trans_handle *trans;
+	struct ulist *refs;
+	struct ulist *roots;
+	struct ulist_node *ref_node = NULL;
+	struct ulist_node *root_node = NULL;
+	struct seq_list seq_elem;
+	struct btrfs_delayed_ref_root *delayed_refs;
+
+	trans = btrfs_join_transaction(fs_info->extent_root);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+
+	pr_debug("resolving all inodes for extent %llu\n",
+			extent_item_objectid);
+
+	delayed_refs = &trans->transaction->delayed_refs;
+	spin_lock(&delayed_refs->lock);
+	btrfs_get_delayed_seq(delayed_refs, &seq_elem);
+	spin_unlock(&delayed_refs->lock);
+
+	ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid,
+				   extent_item_pos, seq_elem.seq,
+				   &refs);
 
-		if (type == BTRFS_EXTENT_DATA_REF_KEY) {
-			dref = (struct btrfs_extent_data_ref *)(&eiref->offset);
-			ret = __data_list_add_eb(&data_refs, eb, dref);
-		} else if (type == BTRFS_SHARED_DATA_REF_KEY) {
-			logical = btrfs_extent_inline_ref_offset(eb, eiref);
-			ret = __shared_list_add(&shared_refs, logical);
-		}
-	} while (!ret && !last);
+	if (ret)
+		goto out;
 
-	/* ... then we proceed to in-tree references and ... */
-	while (!ret) {
-		++path->slots[0];
-		if (path->slots[0] > btrfs_header_nritems(eb)) {
-			ret = btrfs_next_leaf(fs_info->extent_root, path);
-			if (ret) {
-				if (ret == 1)
-					ret = 0; /* we're done */
-				break;
-			}
-			eb = path->nodes[0];
-		}
-		btrfs_item_key_to_cpu(eb, &key, path->slots[0]);
-		if (key.objectid != extent_item_objectid)
+	while (!ret && (ref_node = ulist_next(refs, ref_node))) {
+		ret = btrfs_find_all_roots(trans, fs_info, ref_node->val, -1,
+						seq_elem.seq, &roots);
+		if (ret)
 			break;
-		if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
-			dref = btrfs_item_ptr(eb, path->slots[0],
-						struct btrfs_extent_data_ref);
-			ret = __data_list_add_eb(&data_refs, eb, dref);
-		} else if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
-			ret = __shared_list_add(&shared_refs, key.offset);
+		while (!ret && (root_node = ulist_next(roots, root_node))) {
+			pr_debug("root %llu references leaf %llu\n",
+					root_node->val, ref_node->val);
+			ret = iterate_leaf_refs(fs_info, path, ref_node->val,
+						extent_item_objectid,
+						extent_item_pos, root_node->val,
+						iterate, ctx);
 		}
 	}
 
-	btrfs_release_path(path);
-
-	/*
-	 * ... only at the very end we can process the refs we found. this is
-	 * because the iterator function we call is allowed to make tree lookups
-	 * and we have to avoid deadlocks. additionally, we need more tree
-	 * lookups ourselves for shared data refs.
-	 */
-	while (!list_empty(&data_refs)) {
-		ref_d = list_first_entry(&data_refs, struct __data_ref, list);
-		list_del(&ref_d->list);
-		if (!ret)
-			ret = iterate(ref_d->inum, extent_offset +
-					ref_d->extent_data_item_offset,
-					ref_d->root, ctx);
-		kfree(ref_d);
-	}
-
-	while (!list_empty(&shared_refs)) {
-		ref_s = list_first_entry(&shared_refs, struct __shared_ref,
-					list);
-		list_del(&ref_s->list);
-		if (!ret)
-			ret = __iter_shared_inline_ref(fs_info,
-							ref_s->disk_byte,
-							extent_item_objectid,
-							extent_offset, path,
-							&data_refs,
-							iterate, ctx);
-		kfree(ref_s);
-	}
-
+	ulist_free(refs);
+	ulist_free(roots);
+out:
+	btrfs_put_delayed_seq(delayed_refs, &seq_elem);
+	btrfs_end_transaction(trans, fs_info->extent_root);
 	return ret;
 }
 
@@ -586,19 +1202,20 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 				iterate_extent_inodes_t *iterate, void *ctx)
 {
 	int ret;
-	u64 offset;
+	u64 extent_item_pos;
 	struct btrfs_key found_key;
 
 	ret = extent_from_logical(fs_info, logical, path,
 					&found_key);
+	btrfs_release_path(path);
 	if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK)
 		ret = -EINVAL;
 	if (ret < 0)
 		return ret;
 
-	offset = logical - found_key.objectid;
+	extent_item_pos = logical - found_key.objectid;
 	ret = iterate_extent_inodes(fs_info, path, found_key.objectid,
-					offset, iterate, ctx);
+					extent_item_pos, iterate, ctx);
 
 	return ret;
 }
@@ -643,6 +1260,10 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root,
 		for (cur = 0; cur < btrfs_item_size(eb, item); cur += len) {
 			name_len = btrfs_inode_ref_name_len(eb, iref);
 			/* path must be released before calling iterate()! */
+			pr_debug("following ref at offset %u for inode %llu in "
+				 "tree %llu\n", cur,
+				 (unsigned long long)found_key.objectid,
+				 (unsigned long long)fs_root->objectid);
 			ret = iterate(parent, iref, eb, ctx);
 			if (ret) {
 				free_extent_buffer(eb);
@@ -683,10 +1304,14 @@ static int inode_to_path(u64 inum, struct btrfs_inode_ref *iref,
 		return PTR_ERR(fspath);
 
 	if (fspath > fspath_min) {
+		pr_debug("path resolved: %s\n", fspath);
 		ipath->fspath->val[i] = (u64)(unsigned long)fspath;
 		++ipath->fspath->elem_cnt;
 		ipath->fspath->bytes_left = fspath - fspath_min;
 	} else {
+		pr_debug("missed path, not enough space. missing bytes: %lu, "
+			 "constructed so far: %s\n",
+			 (unsigned long)(fspath_min - fspath), fspath_min);
 		++ipath->fspath->elem_missed;
 		ipath->fspath->bytes_missing += fspath_min - fspath;
 		ipath->fspath->bytes_left = 0;
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index 92618837cb8..d00dfa9ca93 100644
--- a/fs/btrfs/backref.h
+++ b/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);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index dede441bdee..0639a555e16 100644
--- a/fs/btrfs/ctree.c
+++ b/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;
 }
 /*
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index dfc136cc07d..b6d1020c457 100644
--- a/fs/btrfs/ctree.h
+++ b/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 root_objectid, u64 owner, u64 offset);
+		      u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
+		      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,
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 125cf76fcd0..66e4f29505a 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/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 {
-		full_ref->root = ref_root;
+	else
 		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 {
-		full_ref->root = ref_root;
+	else
 		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,
-				   action, 0);
+	ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
+				   num_bytes, action, 0);
 	BUG_ON(ret);
 
-	ret = add_delayed_tree_ref(trans, &ref->node, bytenr, num_bytes,
-				   parent, ref_root, level, action);
+	ret = add_delayed_tree_ref(fs_info, trans, &ref->node, bytenr,
+				   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,
-				   action, 1);
+	ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
+				   num_bytes, action, 1);
 	BUG_ON(ret);
 
-	ret = add_delayed_data_ref(trans, &ref->node, bytenr, num_bytes,
-				   parent, ref_root, owner, offset, action);
+	ret = add_delayed_data_ref(fs_info, trans, &ref->node, bytenr,
+				   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;
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index e287e3b0eab..d8f244d9492 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/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 parent;
-	};
+	u64 root;
+	u64 parent;
 	int level;
 };
 
 struct btrfs_delayed_data_ref {
 	struct btrfs_delayed_ref_node node;
-	union {
-		u64 root;
-		u64 parent;
-	};
+	u64 root;
+	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);
-int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
+			       struct btrfs_delayed_extent_op *extent_op,
+			       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);
-int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
+			       struct btrfs_delayed_extent_op *extent_op,
+			       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.
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e5167219c26..9be97716c5e 100644
--- a/fs/btrfs/disk-io.c
+++ b/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);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1c1cf216be8..a44072a692a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/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;
 }
@@ -2232,6 +2236,28 @@ 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,
-						parent, root->root_key.objectid,
-						btrfs_header_level(buf),
-						BTRFS_DROP_DELAYED_REF, NULL);
+		ret = btrfs_add_delayed_tree_ref(root->fs_info, trans,
+					buf->start, buf->len,
+					parent, root->root_key.objectid,
+					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,
-		      struct btrfs_root *root,
-		      u64 bytenr, u64 num_bytes, u64 parent,
-		      u64 root_objectid, u64 owner, u64 offset)
+int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		      u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
+		      u64 owner, u64 offset, int for_cow)
 {
 	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,
-					parent, root_objectid, owner,
-					offset, BTRFS_DROP_DELAYED_REF, NULL);
+		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
+						num_bytes,
+						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,
-					 0, root_objectid, owner, offset,
-					 BTRFS_ADD_DELAYED_EXTENT, NULL);
+	ret = btrfs_add_delayed_data_ref(root->fs_info, trans, ins->objectid,
+					 ins->offset, 0,
+					 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) {
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 49f3c9dc09f..3622cc22ff9 100644
--- a/fs/btrfs/extent_io.c
+++ b/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);
 
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 7604c300132..bc6a042cb6f 100644
--- a/fs/btrfs/extent_io.h
+++ b/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;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 97fbe939c05..fc97b00bd87 100644
--- a/fs/btrfs/file.c
+++ b/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) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index fd1a06df5bc..acc4ff39ca4 100644
--- a/fs/btrfs/inode.c
+++ b/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);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index ef909b5d3d2..7fdf22c2dc0 100644
--- a/fs/btrfs/ioctl.c
+++ b/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;
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index d77b67c4b27..5e178d8f716 100644
--- a/fs/btrfs/locking.c
+++ b/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;
 }
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index cfb55434a46..efe9f792544 100644
--- a/fs/btrfs/relocation.c
+++ b/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);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index ddf2c90d3fc..6a6a51a809b 100644
--- a/fs/btrfs/scrub.c
+++ b/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);
 	}
 
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 360c2dfd1ee..d5f987b49d7 100644
--- a/fs/btrfs/transaction.c
+++ b/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;
 }
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 3568374d419..cb877e0886a 100644
--- a/fs/btrfs/tree-log.c
+++ b/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 {
 				/*
diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c
new file mode 100644
index 00000000000..12f5147bd2b
--- /dev/null
+++ b/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);
diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h
new file mode 100644
index 00000000000..2e25dec58ec
--- /dev/null
+++ b/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