1 files changed, 264 insertions, 172 deletions

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index cf8820ce7aa2..c297909f1506 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -30,7 +30,7 @@
 #include "root-tree.h"
 #include "tree-checker.h"
 
-enum btrfs_qgroup_mode btrfs_qgroup_mode(struct btrfs_fs_info *fs_info)
+enum btrfs_qgroup_mode btrfs_qgroup_mode(const struct btrfs_fs_info *fs_info)
 {
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
 		return BTRFS_QGROUP_MODE_DISABLED;
@@ -39,12 +39,12 @@ enum btrfs_qgroup_mode btrfs_qgroup_mode(struct btrfs_fs_info *fs_info)
 	return BTRFS_QGROUP_MODE_FULL;
 }
 
-bool btrfs_qgroup_enabled(struct btrfs_fs_info *fs_info)
+bool btrfs_qgroup_enabled(const struct btrfs_fs_info *fs_info)
 {
 	return btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_DISABLED;
 }
 
-bool btrfs_qgroup_full_accounting(struct btrfs_fs_info *fs_info)
+bool btrfs_qgroup_full_accounting(const struct btrfs_fs_info *fs_info)
 {
 	return btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL;
 }
@@ -107,7 +107,7 @@ static void qgroup_rsv_release(struct btrfs_fs_info *fs_info,
 
 static void qgroup_rsv_add_by_qgroup(struct btrfs_fs_info *fs_info,
 				     struct btrfs_qgroup *dest,
-				     struct btrfs_qgroup *src)
+				     const struct btrfs_qgroup *src)
 {
 	int i;
 
@@ -117,7 +117,7 @@ static void qgroup_rsv_add_by_qgroup(struct btrfs_fs_info *fs_info,
 
 static void qgroup_rsv_release_by_qgroup(struct btrfs_fs_info *fs_info,
 					 struct btrfs_qgroup *dest,
-					  struct btrfs_qgroup *src)
+					 const struct btrfs_qgroup *src)
 {
 	int i;
 
@@ -141,37 +141,27 @@ static void btrfs_qgroup_update_new_refcnt(struct btrfs_qgroup *qg, u64 seq,
 	qg->new_refcnt += mod;
 }
 
-static inline u64 btrfs_qgroup_get_old_refcnt(struct btrfs_qgroup *qg, u64 seq)
+static inline u64 btrfs_qgroup_get_old_refcnt(const struct btrfs_qgroup *qg, u64 seq)
 {
 	if (qg->old_refcnt < seq)
 		return 0;
 	return qg->old_refcnt - seq;
 }
 
-static inline u64 btrfs_qgroup_get_new_refcnt(struct btrfs_qgroup *qg, u64 seq)
+static inline u64 btrfs_qgroup_get_new_refcnt(const struct btrfs_qgroup *qg, u64 seq)
 {
 	if (qg->new_refcnt < seq)
 		return 0;
 	return qg->new_refcnt - seq;
 }
 
-/*
- * glue structure to represent the relations between qgroups.
- */
-struct btrfs_qgroup_list {
-	struct list_head next_group;
-	struct list_head next_member;
-	struct btrfs_qgroup *group;
-	struct btrfs_qgroup *member;
-};
-
 static int
 qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 		   int init_flags);
 static void qgroup_rescan_zero_tracking(struct btrfs_fs_info *fs_info);
 
 /* must be called with qgroup_ioctl_lock held */
-static struct btrfs_qgroup *find_qgroup_rb(struct btrfs_fs_info *fs_info,
+static struct btrfs_qgroup *find_qgroup_rb(const struct btrfs_fs_info *fs_info,
 					   u64 qgroupid)
 {
 	struct rb_node *n = fs_info->qgroup_tree.rb_node;
@@ -346,7 +336,7 @@ static int del_relation_rb(struct btrfs_fs_info *fs_info,
 }
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
+int btrfs_verify_qgroup_counts(const struct btrfs_fs_info *fs_info, u64 qgroupid,
 			       u64 rfer, u64 excl)
 {
 	struct btrfs_qgroup *qgroup;
@@ -468,6 +458,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 		}
 		if (!qgroup) {
 			struct btrfs_qgroup *prealloc;
+			struct btrfs_root *tree_root = fs_info->tree_root;
 
 			prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL);
 			if (!prealloc) {
@@ -475,6 +466,25 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 				goto out;
 			}
 			qgroup = add_qgroup_rb(fs_info, prealloc, found_key.offset);
+			/*
+			 * If a qgroup exists for a subvolume ID, it is possible
+			 * that subvolume has been deleted, in which case
+			 * re-using that ID would lead to incorrect accounting.
+			 *
+			 * Ensure that we skip any such subvol ids.
+			 *
+			 * We don't need to lock because this is only called
+			 * during mount before we start doing things like creating
+			 * subvolumes.
+			 */
+			if (is_fstree(qgroup->qgroupid) &&
+			    qgroup->qgroupid > tree_root->free_objectid)
+				/*
+				 * Don't need to check against BTRFS_LAST_FREE_OBJECTID,
+				 * as it will get checked on the next call to
+				 * btrfs_get_free_objectid.
+				 */
+				tree_root->free_objectid = qgroup->qgroupid + 1;
 		}
 		ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup);
 		if (ret < 0)
@@ -588,7 +598,7 @@ out:
  * Return false if no reserved space is left.
  * Return true if some reserved space is leaked.
  */
-bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info)
+bool btrfs_check_quota_leak(const struct btrfs_fs_info *fs_info)
 {
 	struct rb_node *node;
 	bool ret = false;
@@ -1314,24 +1324,19 @@ out:
  */
 static int flush_reservations(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_trans_handle *trans;
 	int ret;
 
 	ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false);
 	if (ret)
 		return ret;
-	btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
-	trans = btrfs_join_transaction(fs_info->tree_root);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
-	ret = btrfs_commit_transaction(trans);
+	btrfs_wait_ordered_roots(fs_info, U64_MAX, NULL);
 
-	return ret;
+	return btrfs_commit_current_transaction(fs_info->tree_root);
 }
 
 int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_root *quota_root;
+	struct btrfs_root *quota_root = NULL;
 	struct btrfs_trans_handle *trans = NULL;
 	int ret = 0;
 
@@ -1342,16 +1347,10 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 	lockdep_assert_held_write(&fs_info->subvol_sem);
 
 	/*
-	 * Lock the cleaner mutex to prevent races with concurrent relocation,
-	 * because relocation may be building backrefs for blocks of the quota
-	 * root while we are deleting the root. This is like dropping fs roots
-	 * of deleted snapshots/subvolumes, we need the same protection.
-	 *
-	 * This also prevents races between concurrent tasks trying to disable
-	 * quotas, because we will unlock and relock qgroup_ioctl_lock across
-	 * BTRFS_FS_QUOTA_ENABLED changes.
+	 * Relocation will mess with backrefs, so make sure we have the
+	 * cleaner_mutex held to protect us from relocate.
 	 */
-	mutex_lock(&fs_info->cleaner_mutex);
+	lockdep_assert_held(&fs_info->cleaner_mutex);
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
 	if (!fs_info->quota_root)
@@ -1373,9 +1372,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 	clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 	btrfs_qgroup_wait_for_completion(fs_info, false);
 
+	/*
+	 * We have nothing held here and no trans handle, just return the error
+	 * if there is one.
+	 */
 	ret = flush_reservations(fs_info);
 	if (ret)
-		goto out_unlock_cleaner;
+		return ret;
 
 	/*
 	 * 1 For the root item
@@ -1428,20 +1431,19 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 	btrfs_tree_lock(quota_root->node);
 	btrfs_clear_buffer_dirty(trans, quota_root->node);
 	btrfs_tree_unlock(quota_root->node);
-	btrfs_free_tree_block(trans, btrfs_root_id(quota_root),
-			      quota_root->node, 0, 1);
+	ret = btrfs_free_tree_block(trans, btrfs_root_id(quota_root),
+				    quota_root->node, 0, 1);
 
-	btrfs_put_root(quota_root);
+	if (ret < 0)
+		btrfs_abort_transaction(trans, ret);
 
 out:
+	btrfs_put_root(quota_root);
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	if (ret && trans)
 		btrfs_end_transaction(trans);
 	else if (trans)
 		ret = btrfs_commit_transaction(trans);
-out_unlock_cleaner:
-	mutex_unlock(&fs_info->cleaner_mutex);
-
 	return ret;
 }
 
@@ -1541,18 +1543,15 @@ static int quick_update_accounting(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_qgroup *qgroup;
 	int ret = 1;
-	int err = 0;
 
 	qgroup = find_qgroup_rb(fs_info, src);
 	if (!qgroup)
 		goto out;
 	if (qgroup->excl == qgroup->rfer) {
-		ret = 0;
-		err = __qgroup_excl_accounting(fs_info, dst, qgroup, sign);
-		if (err < 0) {
-			ret = err;
+		ret = __qgroup_excl_accounting(fs_info, dst, qgroup, sign);
+		if (ret < 0)
 			goto out;
-		}
+		ret = 0;
 	}
 out:
 	if (ret)
@@ -1560,15 +1559,21 @@ out:
 	return ret;
 }
 
-int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst)
+/*
+ * Add relation between @src and @dst qgroup. The @prealloc is allocated by the
+ * callers and transferred here (either used or freed on error).
+ */
+int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst,
+			      struct btrfs_qgroup_list *prealloc)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_qgroup *parent;
 	struct btrfs_qgroup *member;
 	struct btrfs_qgroup_list *list;
-	struct btrfs_qgroup_list *prealloc = NULL;
 	int ret = 0;
 
+	ASSERT(prealloc);
+
 	/* Check the level of src and dst first */
 	if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst))
 		return -EINVAL;
@@ -1593,11 +1598,6 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst
 		}
 	}
 
-	prealloc = kzalloc(sizeof(*list), GFP_NOFS);
-	if (!prealloc) {
-		ret = -ENOMEM;
-		goto out;
-	}
 	ret = add_qgroup_relation_item(trans, src, dst);
 	if (ret)
 		goto out;
@@ -1736,13 +1736,55 @@ out:
 	return ret;
 }
 
-static bool qgroup_has_usage(struct btrfs_qgroup *qgroup)
+/*
+ * Return 0 if we can not delete the qgroup (not empty or has children etc).
+ * Return >0 if we can delete the qgroup.
+ * Return <0 for other errors during tree search.
+ */
+static int can_delete_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup)
 {
-	return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 ||
-		qgroup->excl > 0 || qgroup->excl_cmpr > 0 ||
-		qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 ||
-		qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 ||
-		qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0);
+	struct btrfs_key key;
+	struct btrfs_path *path;
+	int ret;
+
+	/*
+	 * Squota would never be inconsistent, but there can still be case
+	 * where a dropped subvolume still has qgroup numbers, and squota
+	 * relies on such qgroup for future accounting.
+	 *
+	 * So for squota, do not allow dropping any non-zero qgroup.
+	 */
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE &&
+	    (qgroup->rfer || qgroup->excl || qgroup->excl_cmpr || qgroup->rfer_cmpr))
+		return 0;
+
+	/* For higher level qgroup, we can only delete it if it has no child. */
+	if (btrfs_qgroup_level(qgroup->qgroupid)) {
+		if (!list_empty(&qgroup->members))
+			return 0;
+		return 1;
+	}
+
+	/*
+	 * For level-0 qgroups, we can only delete it if it has no subvolume
+	 * for it.
+	 * This means even a subvolume is unlinked but not yet fully dropped,
+	 * we can not delete the qgroup.
+	 */
+	key.objectid = qgroup->qgroupid;
+	key.type = BTRFS_ROOT_ITEM_KEY;
+	key.offset = -1ULL;
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	ret = btrfs_find_root(fs_info->tree_root, &key, path, NULL, NULL);
+	btrfs_free_path(path);
+	/*
+	 * The @ret from btrfs_find_root() exactly matches our definition for
+	 * the return value, thus can be returned directly.
+	 */
+	return ret;
 }
 
 int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
@@ -1764,7 +1806,10 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 		goto out;
 	}
 
-	if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) {
+	ret = can_delete_qgroup(fs_info, qgroup);
+	if (ret < 0)
+		goto out;
+	if (ret == 0) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -1789,6 +1834,34 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 	}
 
 	spin_lock(&fs_info->qgroup_lock);
+	/*
+	 * Warn on reserved space. The subvolume should has no child nor
+	 * corresponding subvolume.
+	 * Thus its reserved space should all be zero, no matter if qgroup
+	 * is consistent or the mode.
+	 */
+	WARN_ON(qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] ||
+		qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] ||
+		qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS]);
+	/*
+	 * The same for rfer/excl numbers, but that's only if our qgroup is
+	 * consistent and if it's in regular qgroup mode.
+	 * For simple mode it's not as accurate thus we can hit non-zero values
+	 * very frequently.
+	 */
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL &&
+	    !(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT)) {
+		if (WARN_ON(qgroup->rfer || qgroup->excl ||
+			    qgroup->rfer_cmpr || qgroup->excl_cmpr)) {
+			btrfs_warn_rl(fs_info,
+"to be deleted qgroup %u/%llu has non-zero numbers, rfer %llu rfer_cmpr %llu excl %llu excl_cmpr %llu",
+				      btrfs_qgroup_level(qgroup->qgroupid),
+				      btrfs_qgroup_subvolid(qgroup->qgroupid),
+				      qgroup->rfer, qgroup->rfer_cmpr,
+				      qgroup->excl, qgroup->excl_cmpr);
+			qgroup_mark_inconsistent(fs_info);
+		}
+	}
 	del_qgroup_rb(fs_info, qgroupid);
 	spin_unlock(&fs_info->qgroup_lock);
 
@@ -1804,6 +1877,41 @@ out:
 	return ret;
 }
 
+int btrfs_qgroup_cleanup_dropped_subvolume(struct btrfs_fs_info *fs_info, u64 subvolid)
+{
+	struct btrfs_trans_handle *trans;
+	int ret;
+
+	if (!is_fstree(subvolid) || !btrfs_qgroup_enabled(fs_info) || !fs_info->quota_root)
+		return 0;
+
+	/*
+	 * Commit current transaction to make sure all the rfer/excl numbers
+	 * get updated.
+	 */
+	trans = btrfs_start_transaction(fs_info->quota_root, 0);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+
+	ret = btrfs_commit_transaction(trans);
+	if (ret < 0)
+		return ret;
+
+	/* Start new trans to delete the qgroup info and limit items. */
+	trans = btrfs_start_transaction(fs_info->quota_root, 2);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+	ret = btrfs_remove_qgroup(trans, subvolid);
+	btrfs_end_transaction(trans);
+	/*
+	 * It's squota and the subvolume still has numbers needed for future
+	 * accounting, in this case we can not delete it.  Just skip it.
+	 */
+	if (ret == -EBUSY)
+		ret = 0;
+	return ret;
+}
+
 int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit)
 {
@@ -1890,16 +1998,14 @@ out:
  *
  * Return 0 for success insert
  * Return >0 for existing record, caller can free @record safely.
- * Error is not possible
+ * Return <0 for insertion failure, caller can free @record safely.
  */
 int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 				struct btrfs_delayed_ref_root *delayed_refs,
 				struct btrfs_qgroup_extent_record *record)
 {
-	struct rb_node **p = &delayed_refs->dirty_extent_root.rb_node;
-	struct rb_node *parent_node = NULL;
-	struct btrfs_qgroup_extent_record *entry;
-	u64 bytenr = record->bytenr;
+	struct btrfs_qgroup_extent_record *existing, *ret;
+	unsigned long bytenr = record->bytenr;
 
 	if (!btrfs_qgroup_full_accounting(fs_info))
 		return 1;
@@ -1907,26 +2013,24 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 	lockdep_assert_held(&delayed_refs->lock);
 	trace_btrfs_qgroup_trace_extent(fs_info, record);
 
-	while (*p) {
-		parent_node = *p;
-		entry = rb_entry(parent_node, struct btrfs_qgroup_extent_record,
-				 node);
-		if (bytenr < entry->bytenr) {
-			p = &(*p)->rb_left;
-		} else if (bytenr > entry->bytenr) {
-			p = &(*p)->rb_right;
-		} else {
-			if (record->data_rsv && !entry->data_rsv) {
-				entry->data_rsv = record->data_rsv;
-				entry->data_rsv_refroot =
-					record->data_rsv_refroot;
-			}
-			return 1;
+	xa_lock(&delayed_refs->dirty_extents);
+	existing = xa_load(&delayed_refs->dirty_extents, bytenr);
+	if (existing) {
+		if (record->data_rsv && !existing->data_rsv) {
+			existing->data_rsv = record->data_rsv;
+			existing->data_rsv_refroot = record->data_rsv_refroot;
 		}
+		xa_unlock(&delayed_refs->dirty_extents);
+		return 1;
+	}
+
+	ret = __xa_store(&delayed_refs->dirty_extents, record->bytenr, record, GFP_ATOMIC);
+	xa_unlock(&delayed_refs->dirty_extents);
+	if (xa_is_err(ret)) {
+		qgroup_mark_inconsistent(fs_info);
+		return xa_err(ret);
 	}
 
-	rb_link_node(&record->node, parent_node, p);
-	rb_insert_color(&record->node, &delayed_refs->dirty_extent_root);
 	return 0;
 }
 
@@ -2033,6 +2137,11 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 	if (!record)
 		return -ENOMEM;
 
+	if (xa_reserve(&trans->transaction->delayed_refs.dirty_extents, bytenr, GFP_NOFS)) {
+		kfree(record);
+		return -ENOMEM;
+	}
+
 	delayed_refs = &trans->transaction->delayed_refs;
 	record->bytenr = bytenr;
 	record->num_bytes = num_bytes;
@@ -2041,7 +2150,9 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 	spin_lock(&delayed_refs->lock);
 	ret = btrfs_qgroup_trace_extent_nolock(fs_info, delayed_refs, record);
 	spin_unlock(&delayed_refs->lock);
-	if (ret > 0) {
+	if (ret) {
+		/* Clean up if insertion fails or item exists. */
+		xa_release(&delayed_refs->dirty_extents, record->bytenr);
 		kfree(record);
 		return 0;
 	}
@@ -2910,7 +3021,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 	struct btrfs_qgroup_extent_record *record;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct ulist *new_roots = NULL;
-	struct rb_node *node;
+	unsigned long index;
 	u64 num_dirty_extents = 0;
 	u64 qgroup_to_skip;
 	int ret = 0;
@@ -2920,10 +3031,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 
 	delayed_refs = &trans->transaction->delayed_refs;
 	qgroup_to_skip = delayed_refs->qgroup_to_skip;
-	while ((node = rb_first(&delayed_refs->dirty_extent_root))) {
-		record = rb_entry(node, struct btrfs_qgroup_extent_record,
-				  node);
-
+	xa_for_each(&delayed_refs->dirty_extents, index, record) {
 		num_dirty_extents++;
 		trace_btrfs_qgroup_account_extents(fs_info, record);
 
@@ -2989,7 +3097,7 @@ cleanup:
 		ulist_free(record->old_roots);
 		ulist_free(new_roots);
 		new_roots = NULL;
-		rb_erase(node, &delayed_refs->dirty_extent_root);
+		xa_erase(&delayed_refs->dirty_extents, index);
 		kfree(record);
 
 	}
@@ -3067,13 +3175,18 @@ int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info,
 	if (inherit->num_ref_copies > 0 || inherit->num_excl_copies > 0)
 		return -EINVAL;
 
-	if (inherit->num_qgroups > PAGE_SIZE)
-		return -EINVAL;
-
 	if (size != struct_size(inherit, qgroups, inherit->num_qgroups))
 		return -EINVAL;
 
 	/*
+	 * Skip the inherit source qgroups check if qgroup is not enabled.
+	 * Qgroup can still be later enabled causing problems, but in that case
+	 * btrfs_qgroup_inherit() would just ignore those invalid ones.
+	 */
+	if (!btrfs_qgroup_enabled(fs_info))
+		return 0;
+
+	/*
 	 * Now check all the remaining qgroups, they should all:
 	 *
 	 * - Exist
@@ -3132,7 +3245,7 @@ static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info,
 	qgids = res->qgroups;
 
 	list_for_each_entry(qg_list, &inode_qg->groups, next_group)
-		qgids[i] = qg_list->group->qgroupid;
+		qgids[i++] = qg_list->group->qgroupid;
 
 	*inherit = res;
 	return 0;
@@ -3205,7 +3318,6 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 			 struct btrfs_qgroup_inherit *inherit)
 {
 	int ret = 0;
-	int i;
 	u64 *i_qgroups;
 	bool committing = false;
 	struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -3262,7 +3374,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 		i_qgroups = (u64 *)(inherit + 1);
 		nums = inherit->num_qgroups + 2 * inherit->num_ref_copies +
 		       2 * inherit->num_excl_copies;
-		for (i = 0; i < nums; ++i) {
+		for (int i = 0; i < nums; i++) {
 			srcgroup = find_qgroup_rb(fs_info, *i_qgroups);
 
 			/*
@@ -3289,7 +3401,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 	 */
 	if (inherit) {
 		i_qgroups = (u64 *)(inherit + 1);
-		for (i = 0; i < inherit->num_qgroups; ++i, ++i_qgroups) {
+		for (int i = 0; i < inherit->num_qgroups; i++, i_qgroups++) {
 			if (*i_qgroups == 0)
 				continue;
 			ret = add_qgroup_relation_item(trans, objectid,
@@ -3375,7 +3487,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 		goto unlock;
 
 	i_qgroups = (u64 *)(inherit + 1);
-	for (i = 0; i < inherit->num_qgroups; ++i) {
+	for (int i = 0; i < inherit->num_qgroups; i++) {
 		if (*i_qgroups) {
 			ret = add_relation_rb(fs_info, qlist_prealloc[i], objectid,
 					      *i_qgroups);
@@ -3395,7 +3507,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 		++i_qgroups;
 	}
 
-	for (i = 0; i <  inherit->num_ref_copies; ++i, i_qgroups += 2) {
+	for (int i = 0; i < inherit->num_ref_copies; i++, i_qgroups += 2) {
 		struct btrfs_qgroup *src;
 		struct btrfs_qgroup *dst;
 
@@ -3416,7 +3528,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 		/* Manually tweaking numbers certainly needs a rescan */
 		need_rescan = true;
 	}
-	for (i = 0; i <  inherit->num_excl_copies; ++i, i_qgroups += 2) {
+	for (int i = 0; i < inherit->num_excl_copies; i++, i_qgroups += 2) {
 		struct btrfs_qgroup *src;
 		struct btrfs_qgroup *dst;
 
@@ -3474,7 +3586,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce,
 {
 	struct btrfs_qgroup *qgroup;
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	u64 ref_root = root->root_key.objectid;
+	u64 ref_root = btrfs_root_id(root);
 	int ret = 0;
 	LIST_HEAD(qgroup_list);
 
@@ -3709,7 +3821,6 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 						     qgroup_rescan_work);
 	struct btrfs_path *path;
 	struct btrfs_trans_handle *trans = NULL;
-	int err = -ENOMEM;
 	int ret = 0;
 	bool stopped = false;
 	bool did_leaf_rescans = false;
@@ -3718,8 +3829,10 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 		return;
 
 	path = btrfs_alloc_path();
-	if (!path)
+	if (!path) {
+		ret = -ENOMEM;
 		goto out;
+	}
 	/*
 	 * Rescan should only search for commit root, and any later difference
 	 * should be recorded by qgroup
@@ -3727,18 +3840,17 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
-	err = 0;
-	while (!err && !(stopped = rescan_should_stop(fs_info))) {
+	while (!ret && !(stopped = rescan_should_stop(fs_info))) {
 		trans = btrfs_start_transaction(fs_info->fs_root, 0);
 		if (IS_ERR(trans)) {
-			err = PTR_ERR(trans);
+			ret = PTR_ERR(trans);
 			break;
 		}
 
-		err = qgroup_rescan_leaf(trans, path);
+		ret = qgroup_rescan_leaf(trans, path);
 		did_leaf_rescans = true;
 
-		if (err > 0)
+		if (ret > 0)
 			btrfs_commit_transaction(trans);
 		else
 			btrfs_end_transaction(trans);
@@ -3748,10 +3860,10 @@ out:
 	btrfs_free_path(path);
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
-	if (err > 0 &&
+	if (ret > 0 &&
 	    fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) {
 		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
-	} else if (err < 0 || stopped) {
+	} else if (ret < 0 || stopped) {
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 	}
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
@@ -3766,11 +3878,11 @@ out:
 	if (did_leaf_rescans) {
 		trans = btrfs_start_transaction(fs_info->quota_root, 1);
 		if (IS_ERR(trans)) {
-			err = PTR_ERR(trans);
+			ret = PTR_ERR(trans);
 			trans = NULL;
 			btrfs_err(fs_info,
 				  "fail to start transaction for status update: %d",
-				  err);
+				  ret);
 		}
 	} else {
 		trans = NULL;
@@ -3781,11 +3893,11 @@ out:
 	    fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN)
 		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
 	if (trans) {
-		ret = update_qgroup_status_item(trans);
-		if (ret < 0) {
-			err = ret;
-			btrfs_err(fs_info, "fail to update qgroup status: %d",
-				  err);
+		int ret2 = update_qgroup_status_item(trans);
+
+		if (ret2 < 0) {
+			ret = ret2;
+			btrfs_err(fs_info, "fail to update qgroup status: %d", ret);
 		}
 	}
 	fs_info->qgroup_rescan_running = false;
@@ -3802,11 +3914,11 @@ out:
 		btrfs_info(fs_info, "qgroup scan paused");
 	} else if (fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN) {
 		btrfs_info(fs_info, "qgroup scan cancelled");
-	} else if (err >= 0) {
+	} else if (ret >= 0) {
 		btrfs_info(fs_info, "qgroup scan completed%s",
-			err > 0 ? " (inconsistency flag cleared)" : "");
+			ret > 0 ? " (inconsistency flag cleared)" : "");
 	} else {
-		btrfs_err(fs_info, "qgroup scan failed with %d", err);
+		btrfs_err(fs_info, "qgroup scan failed with %d", ret);
 	}
 }
 
@@ -3829,14 +3941,14 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 		/* we're resuming qgroup rescan at mount time */
 		if (!(fs_info->qgroup_flags &
 		      BTRFS_QGROUP_STATUS_FLAG_RESCAN)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup rescan is not queued");
 			ret = -EINVAL;
 		} else if (!(fs_info->qgroup_flags &
 			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup is not enabled");
-			ret = -EINVAL;
+			ret = -ENOTCONN;
 		}
 
 		if (ret)
@@ -3847,14 +3959,12 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 
 	if (init_flags) {
 		if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
-			btrfs_warn(fs_info,
-				   "qgroup rescan is already in progress");
 			ret = -EINPROGRESS;
 		} else if (!(fs_info->qgroup_flags &
 			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup is not enabled");
-			ret = -EINVAL;
+			ret = -ENOTCONN;
 		} else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) {
 			/* Quota disable is in progress */
 			ret = -EBUSY;
@@ -3903,7 +4013,6 @@ int
 btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
 {
 	int ret = 0;
-	struct btrfs_trans_handle *trans;
 
 	ret = qgroup_rescan_init(fs_info, 0, 1);
 	if (ret)
@@ -3920,16 +4029,10 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
 	 * going to clear all tracking information for a clean start.
 	 */
 
-	trans = btrfs_attach_transaction_barrier(fs_info->fs_root);
-	if (IS_ERR(trans) && trans != ERR_PTR(-ENOENT)) {
+	ret = btrfs_commit_current_transaction(fs_info->fs_root);
+	if (ret) {
 		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
-		return PTR_ERR(trans);
-	} else if (trans != ERR_PTR(-ENOENT)) {
-		ret = btrfs_commit_transaction(trans);
-		if (ret) {
-			fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
-			return ret;
-		}
+		return ret;
 	}
 
 	qgroup_rescan_zero_tracking(fs_info);
@@ -4065,7 +4168,6 @@ static int qgroup_unreserve_range(struct btrfs_inode *inode,
  */
 static int try_flush_qgroup(struct btrfs_root *root)
 {
-	struct btrfs_trans_handle *trans;
 	int ret;
 
 	/* Can't hold an open transaction or we run the risk of deadlocking. */
@@ -4083,20 +4185,14 @@ static int try_flush_qgroup(struct btrfs_root *root)
 		return 0;
 	}
 
+	btrfs_run_delayed_iputs(root->fs_info);
+	btrfs_wait_on_delayed_iputs(root->fs_info);
 	ret = btrfs_start_delalloc_snapshot(root, true);
 	if (ret < 0)
 		goto out;
-	btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1);
+	btrfs_wait_ordered_extents(root, U64_MAX, NULL);
 
-	trans = btrfs_attach_transaction_barrier(root);
-	if (IS_ERR(trans)) {
-		ret = PTR_ERR(trans);
-		if (ret == -ENOENT)
-			ret = 0;
-		goto out;
-	}
-
-	ret = btrfs_commit_transaction(trans);
+	ret = btrfs_commit_current_transaction(root);
 out:
 	clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state);
 	wake_up(&root->qgroup_flush_wait);
@@ -4115,7 +4211,7 @@ static int qgroup_reserve_data(struct btrfs_inode *inode,
 	int ret;
 
 	if (btrfs_qgroup_mode(root->fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
-	    !is_fstree(root->root_key.objectid) || len == 0)
+	    !is_fstree(btrfs_root_id(root)) || len == 0)
 		return 0;
 
 	/* @reserved parameter is mandatory for qgroup */
@@ -4231,7 +4327,7 @@ static int qgroup_free_reserved_data(struct btrfs_inode *inode,
 			goto out;
 		freed += changeset.bytes_changed;
 	}
-	btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed,
+	btrfs_qgroup_free_refroot(root->fs_info, btrfs_root_id(root), freed,
 				  BTRFS_QGROUP_RSV_DATA);
 	if (freed_ret)
 		*freed_ret = freed;
@@ -4250,10 +4346,9 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
 	int ret;
 
 	if (btrfs_qgroup_mode(inode->root->fs_info) == BTRFS_QGROUP_MODE_DISABLED) {
-		extent_changeset_init(&changeset);
 		return clear_record_extent_bits(&inode->io_tree, start,
 						start + len - 1,
-						EXTENT_QGROUP_RESERVED, &changeset);
+						EXTENT_QGROUP_RESERVED, NULL);
 	}
 
 	/* In release case, we shouldn't have @reserved */
@@ -4272,7 +4367,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
 					changeset.bytes_changed, trace_op);
 	if (free)
 		btrfs_qgroup_free_refroot(inode->root->fs_info,
-				inode->root->root_key.objectid,
+				btrfs_root_id(inode->root),
 				changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
 	if (released)
 		*released = changeset.bytes_changed;
@@ -4367,7 +4462,7 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 	int ret;
 
 	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
-	    !is_fstree(root->root_key.objectid) || num_bytes == 0)
+	    !is_fstree(btrfs_root_id(root)) || num_bytes == 0)
 		return 0;
 
 	BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
@@ -4412,13 +4507,13 @@ void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root)
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
-	    !is_fstree(root->root_key.objectid))
+	    !is_fstree(btrfs_root_id(root)))
 		return;
 
 	/* TODO: Update trace point to handle such free */
 	trace_qgroup_meta_free_all_pertrans(root);
 	/* Special value -1 means to free all reserved space */
-	btrfs_qgroup_free_refroot(fs_info, root->root_key.objectid, (u64)-1,
+	btrfs_qgroup_free_refroot(fs_info, btrfs_root_id(root), (u64)-1,
 				  BTRFS_QGROUP_RSV_META_PERTRANS);
 }
 
@@ -4428,7 +4523,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
-	    !is_fstree(root->root_key.objectid))
+	    !is_fstree(btrfs_root_id(root)))
 		return;
 
 	/*
@@ -4439,8 +4534,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes,
 	num_bytes = sub_root_meta_rsv(root, num_bytes, type);
 	BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
 	trace_qgroup_meta_reserve(root, -(s64)num_bytes, type);
-	btrfs_qgroup_free_refroot(fs_info, root->root_key.objectid,
-				  num_bytes, type);
+	btrfs_qgroup_free_refroot(fs_info, btrfs_root_id(root), num_bytes, type);
 }
 
 static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root,
@@ -4488,13 +4582,13 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes)
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
-	    !is_fstree(root->root_key.objectid))
+	    !is_fstree(btrfs_root_id(root)))
 		return;
 	/* Same as btrfs_qgroup_free_meta_prealloc() */
 	num_bytes = sub_root_meta_rsv(root, num_bytes,
 				      BTRFS_QGROUP_RSV_META_PREALLOC);
 	trace_qgroup_meta_convert(root, num_bytes);
-	qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes);
+	qgroup_convert_meta(fs_info, btrfs_root_id(root), num_bytes);
 	if (!sb_rdonly(fs_info->sb))
 		add_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS);
 }
@@ -4523,7 +4617,7 @@ void btrfs_qgroup_check_reserved_leak(struct btrfs_inode *inode)
 				btrfs_ino(inode), unode->val, unode->aux);
 		}
 		btrfs_qgroup_free_refroot(inode->root->fs_info,
-				inode->root->root_key.objectid,
+				btrfs_root_id(inode->root),
 				changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
 
 	}
@@ -4709,7 +4803,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
 
 	if (!btrfs_qgroup_full_accounting(fs_info))
 		return 0;
-	if (!is_fstree(root->root_key.objectid) || !root->reloc_root)
+	if (!is_fstree(btrfs_root_id(root)) || !root->reloc_root)
 		return 0;
 
 	spin_lock(&blocks->lock);
@@ -4780,15 +4874,13 @@ out:
 void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans)
 {
 	struct btrfs_qgroup_extent_record *entry;
-	struct btrfs_qgroup_extent_record *next;
-	struct rb_root *root;
+	unsigned long index;
 
-	root = &trans->delayed_refs.dirty_extent_root;
-	rbtree_postorder_for_each_entry_safe(entry, next, root, node) {
+	xa_for_each(&trans->delayed_refs.dirty_extents, index, entry) {
 		ulist_free(entry->old_roots);
 		kfree(entry);
 	}
-	*root = RB_ROOT;
+	xa_destroy(&trans->delayed_refs.dirty_extents);
 }
 
 void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes)
@@ -4803,7 +4895,7 @@ void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_byte
 }
 
 int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
-			      struct btrfs_squota_delta *delta)
+			      const struct btrfs_squota_delta *delta)
 {
 	int ret;
 	struct btrfs_qgroup *qgroup;