1 files changed, 129 insertions, 46 deletions

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 43885e51b882..9cca0a721961 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -311,10 +311,11 @@ loop:
  * when the transaction commits
  */
 static int record_root_in_trans(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root)
+			       struct btrfs_root *root,
+			       int force)
 {
-	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
-	    root->last_trans < trans->transid) {
+	if ((test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+	    root->last_trans < trans->transid) || force) {
 		WARN_ON(root == root->fs_info->extent_root);
 		WARN_ON(root->commit_root != root->node);
 
@@ -331,7 +332,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
 		smp_wmb();
 
 		spin_lock(&root->fs_info->fs_roots_radix_lock);
-		if (root->last_trans == trans->transid) {
+		if (root->last_trans == trans->transid && !force) {
 			spin_unlock(&root->fs_info->fs_roots_radix_lock);
 			return 0;
 		}
@@ -402,7 +403,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 		return 0;
 
 	mutex_lock(&root->fs_info->reloc_mutex);
-	record_root_in_trans(trans, root);
+	record_root_in_trans(trans, root, 0);
 	mutex_unlock(&root->fs_info->reloc_mutex);
 
 	return 0;
@@ -560,6 +561,7 @@ again:
 	h->transaction = cur_trans;
 	h->root = root;
 	h->use_count = 1;
+	h->fs_info = root->fs_info;
 
 	h->type = type;
 	h->can_flush_pending_bgs = true;
@@ -817,6 +819,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_fs_info *info = root->fs_info;
+	u64 transid = trans->transid;
 	unsigned long cur = trans->delayed_ref_updates;
 	int lock = (trans->type != TRANS_JOIN_NOLOCK);
 	int err = 0;
@@ -904,7 +907,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 	if (must_run_delayed_refs) {
-		btrfs_async_run_delayed_refs(root, cur,
+		btrfs_async_run_delayed_refs(root, cur, transid,
 					     must_run_delayed_refs == 1);
 	}
 	return err;
@@ -943,7 +946,7 @@ int btrfs_write_marked_extents(struct btrfs_root *root,
 
 		err = convert_extent_bit(dirty_pages, start, end,
 					 EXTENT_NEED_WAIT,
-					 mark, &cached_state, GFP_NOFS);
+					 mark, &cached_state);
 		/*
 		 * convert_extent_bit can return -ENOMEM, which is most of the
 		 * time a temporary error. So when it happens, ignore the error
@@ -1311,6 +1314,92 @@ int btrfs_defrag_root(struct btrfs_root *root)
 }
 
 /*
+ * Do all special snapshot related qgroup dirty hack.
+ *
+ * Will do all needed qgroup inherit and dirty hack like switch commit
+ * roots inside one transaction and write all btree into disk, to make
+ * qgroup works.
+ */
+static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *src,
+				   struct btrfs_root *parent,
+				   struct btrfs_qgroup_inherit *inherit,
+				   u64 dst_objectid)
+{
+	struct btrfs_fs_info *fs_info = src->fs_info;
+	int ret;
+
+	/*
+	 * Save some performance in the case that qgroups are not
+	 * enabled. If this check races with the ioctl, rescan will
+	 * kick in anyway.
+	 */
+	mutex_lock(&fs_info->qgroup_ioctl_lock);
+	if (!fs_info->quota_enabled) {
+		mutex_unlock(&fs_info->qgroup_ioctl_lock);
+		return 0;
+	}
+	mutex_unlock(&fs_info->qgroup_ioctl_lock);
+
+	/*
+	 * We are going to commit transaction, see btrfs_commit_transaction()
+	 * comment for reason locking tree_log_mutex
+	 */
+	mutex_lock(&fs_info->tree_log_mutex);
+
+	ret = commit_fs_roots(trans, src);
+	if (ret)
+		goto out;
+	ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
+	if (ret < 0)
+		goto out;
+	ret = btrfs_qgroup_account_extents(trans, fs_info);
+	if (ret < 0)
+		goto out;
+
+	/* Now qgroup are all updated, we can inherit it to new qgroups */
+	ret = btrfs_qgroup_inherit(trans, fs_info,
+				   src->root_key.objectid, dst_objectid,
+				   inherit);
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * Now we do a simplified commit transaction, which will:
+	 * 1) commit all subvolume and extent tree
+	 *    To ensure all subvolume and extent tree have a valid
+	 *    commit_root to accounting later insert_dir_item()
+	 * 2) write all btree blocks onto disk
+	 *    This is to make sure later btree modification will be cowed
+	 *    Or commit_root can be populated and cause wrong qgroup numbers
+	 * In this simplified commit, we don't really care about other trees
+	 * like chunk and root tree, as they won't affect qgroup.
+	 * And we don't write super to avoid half committed status.
+	 */
+	ret = commit_cowonly_roots(trans, src);
+	if (ret)
+		goto out;
+	switch_commit_roots(trans->transaction, fs_info);
+	ret = btrfs_write_and_wait_transaction(trans, src);
+	if (ret)
+		btrfs_handle_fs_error(fs_info, ret,
+			"Error while writing out transaction for qgroup");
+
+out:
+	mutex_unlock(&fs_info->tree_log_mutex);
+
+	/*
+	 * Force parent root to be updated, as we recorded it before so its
+	 * last_trans == cur_transid.
+	 * Or it won't be committed again onto disk after later
+	 * insert_dir_item()
+	 */
+	if (!ret)
+		record_root_in_trans(trans, parent, 1);
+	return ret;
+}
+
+/*
  * new snapshots need to be created at a very specific time in the
  * transaction commit.  This does the actual creation.
  *
@@ -1383,7 +1472,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	dentry = pending->dentry;
 	parent_inode = pending->dir;
 	parent_root = BTRFS_I(parent_inode)->root;
-	record_root_in_trans(trans, parent_root);
+	record_root_in_trans(trans, parent_root, 0);
 
 	cur_time = current_fs_time(parent_inode->i_sb);
 
@@ -1403,7 +1492,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto dir_item_existed;
 	} else if (IS_ERR(dir_item)) {
 		ret = PTR_ERR(dir_item);
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 	btrfs_release_path(path);
@@ -1416,11 +1505,11 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	 */
 	ret = btrfs_run_delayed_items(trans, root);
 	if (ret) {	/* Transaction aborted */
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 
-	record_root_in_trans(trans, root);
+	record_root_in_trans(trans, root, 0);
 	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
 	memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
 	btrfs_check_and_init_root_item(new_root_item);
@@ -1455,7 +1544,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	if (ret) {
 		btrfs_tree_unlock(old);
 		free_extent_buffer(old);
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 
@@ -1466,7 +1555,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_tree_unlock(old);
 	free_extent_buffer(old);
 	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 	/* see comments in should_cow_block() */
@@ -1480,7 +1569,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_tree_unlock(tmp);
 	free_extent_buffer(tmp);
 	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 
@@ -1492,7 +1581,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 				 btrfs_ino(parent_inode), index,
 				 dentry->d_name.name, dentry->d_name.len);
 	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 
@@ -1500,22 +1589,33 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	pending->snap = btrfs_read_fs_root_no_name(root->fs_info, &key);
 	if (IS_ERR(pending->snap)) {
 		ret = PTR_ERR(pending->snap);
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 
 	ret = btrfs_reloc_post_snapshot(trans, pending);
 	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 
 	ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
 	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 
+	/*
+	 * Do special qgroup accounting for snapshot, as we do some qgroup
+	 * snapshot hack to do fast snapshot.
+	 * To co-operate with that hack, we do hack again.
+	 * Or snapshot will be greatly slowed down by a subtree qgroup rescan
+	 */
+	ret = qgroup_account_snapshot(trans, root, parent_root,
+				      pending->inherit, objectid);
+	if (ret < 0)
+		goto fail;
+
 	ret = btrfs_insert_dir_item(trans, parent_root,
 				    dentry->d_name.name, dentry->d_name.len,
 				    parent_inode, &key,
@@ -1523,7 +1623,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	/* We have check then name at the beginning, so it is impossible. */
 	BUG_ON(ret == -EEXIST || ret == -EOVERFLOW);
 	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 
@@ -1533,13 +1633,13 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		current_fs_time(parent_inode->i_sb);
 	ret = btrfs_update_inode_fallback(trans, parent_root, parent_inode);
 	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 	ret = btrfs_uuid_tree_add(trans, fs_info->uuid_root, new_uuid.b,
 				  BTRFS_UUID_KEY_SUBVOL, objectid);
 	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 	if (!btrfs_is_empty_uuid(new_root_item->received_uuid)) {
@@ -1548,31 +1648,14 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
 					  objectid);
 		if (ret && ret != -EEXIST) {
-			btrfs_abort_transaction(trans, root, ret);
+			btrfs_abort_transaction(trans, ret);
 			goto fail;
 		}
 	}
 
 	ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
 	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
-		goto fail;
-	}
-
-	/*
-	 * account qgroup counters before qgroup_inherit()
-	 */
-	ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
-	if (ret)
-		goto fail;
-	ret = btrfs_qgroup_account_extents(trans, fs_info);
-	if (ret)
-		goto fail;
-	ret = btrfs_qgroup_inherit(trans, fs_info,
-				   root->root_key.objectid,
-				   objectid, pending->inherit);
-	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 
@@ -1627,7 +1710,7 @@ static void update_super_roots(struct btrfs_root *root)
 	super->root = root_item->bytenr;
 	super->generation = root_item->generation;
 	super->root_level = root_item->level;
-	if (btrfs_test_opt(root, SPACE_CACHE))
+	if (btrfs_test_opt(root->fs_info, SPACE_CACHE))
 		super->cache_generation = root_item->generation;
 	if (root->fs_info->update_uuid_tree_gen)
 		super->uuid_tree_generation = root_item->generation;
@@ -1768,7 +1851,7 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans,
 
 	WARN_ON(trans->use_count > 1);
 
-	btrfs_abort_transaction(trans, root, err);
+	btrfs_abort_transaction(trans, err);
 
 	spin_lock(&root->fs_info->trans_lock);
 
@@ -1813,15 +1896,15 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans,
 
 static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
 {
-	if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT))
+	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
 		return btrfs_start_delalloc_roots(fs_info, 1, -1);
 	return 0;
 }
 
 static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
 {
-	if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT))
-		btrfs_wait_ordered_roots(fs_info, -1);
+	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
+		btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
 }
 
 static inline void
@@ -2145,7 +2228,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_write_and_wait_transaction(trans, root);
 	if (ret) {
-		btrfs_std_error(root->fs_info, ret,
+		btrfs_handle_fs_error(root->fs_info, ret,
 			    "Error while writing out transaction");
 		mutex_unlock(&root->fs_info->tree_log_mutex);
 		goto scrub_continue;