1 files changed, 60 insertions, 60 deletions

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index acff6bb49a97..50318231c1a8 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -260,6 +260,7 @@ static inline int extwriter_counter_read(struct btrfs_transaction *trans)
 void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
+	struct btrfs_transaction *cur_trans = trans->transaction;
 
 	if (!trans->chunk_bytes_reserved)
 		return;
@@ -268,6 +269,8 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
 
 	btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv,
 				trans->chunk_bytes_reserved, NULL);
+	atomic64_sub(trans->chunk_bytes_reserved, &cur_trans->chunk_bytes_reserved);
+	cond_wake_up(&cur_trans->chunk_reserve_wait);
 	trans->chunk_bytes_reserved = 0;
 }
 
@@ -383,6 +386,8 @@ loop:
 	spin_lock_init(&cur_trans->dropped_roots_lock);
 	INIT_LIST_HEAD(&cur_trans->releasing_ebs);
 	spin_lock_init(&cur_trans->releasing_ebs_lock);
+	atomic64_set(&cur_trans->chunk_bytes_reserved, 0);
+	init_waitqueue_head(&cur_trans->chunk_reserve_wait);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
 	extent_io_tree_init(fs_info, &cur_trans->dirty_pages,
 			IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode);
@@ -408,6 +413,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
 			       int force)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
+	int ret = 0;
 
 	if ((test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
 	    root->last_trans < trans->transid) || force) {
@@ -456,11 +462,11 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
 		 * lock.  smp_wmb() makes sure that all the writes above are
 		 * done before we pop in the zero below
 		 */
-		btrfs_init_reloc_root(trans, root);
+		ret = btrfs_init_reloc_root(trans, root);
 		smp_mb__before_atomic();
 		clear_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state);
 	}
-	return 0;
+	return ret;
 }
 
 
@@ -487,6 +493,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
+	int ret;
 
 	if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
 		return 0;
@@ -501,10 +508,10 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 		return 0;
 
 	mutex_lock(&fs_info->reloc_mutex);
-	record_root_in_trans(trans, root, 0);
+	ret = record_root_in_trans(trans, root, 0);
 	mutex_unlock(&fs_info->reloc_mutex);
 
-	return 0;
+	return ret;
 }
 
 static inline int is_transaction_blocked(struct btrfs_transaction *trans)
@@ -576,9 +583,6 @@ start_transaction(struct btrfs_root *root, unsigned int num_items,
 	bool do_chunk_alloc = false;
 	int ret;
 
-	/* Send isn't supposed to start transactions. */
-	ASSERT(current->journal_info != BTRFS_SEND_TRANS_STUB);
-
 	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
 		return ERR_PTR(-EROFS);
 
@@ -741,7 +745,16 @@ got_it:
 	 * Thus it need to be called after current->journal_info initialized,
 	 * or we can deadlock.
 	 */
-	btrfs_record_root_in_trans(h, root);
+	ret = btrfs_record_root_in_trans(h, root);
+	if (ret) {
+		/*
+		 * The transaction handle is fully initialized and linked with
+		 * other structures so it needs to be ended in case of errors,
+		 * not just freed.
+		 */
+		btrfs_end_transaction(h);
+		return ERR_PTR(ret);
+	}
 
 	return h;
 
@@ -1347,7 +1360,9 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
 			spin_unlock(&fs_info->fs_roots_radix_lock);
 
 			btrfs_free_log(trans, root);
-			btrfs_update_reloc_root(trans, root);
+			ret2 = btrfs_update_reloc_root(trans, root);
+			if (ret2)
+				return ret2;
 
 			/* see comments in should_cow_block() */
 			clear_bit(BTRFS_ROOT_FORCE_COW, &root->state);
@@ -1388,8 +1403,10 @@ int btrfs_defrag_root(struct btrfs_root *root)
 
 	while (1) {
 		trans = btrfs_start_transaction(root, 0);
-		if (IS_ERR(trans))
-			return PTR_ERR(trans);
+		if (IS_ERR(trans)) {
+			ret = PTR_ERR(trans);
+			break;
+		}
 
 		ret = btrfs_defrag_leaves(trans, root);
 
@@ -1440,7 +1457,9 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 	 * recorded root will never be updated again, causing an outdated root
 	 * item.
 	 */
-	record_root_in_trans(trans, src, 1);
+	ret = record_root_in_trans(trans, src, 1);
+	if (ret)
+		return ret;
 
 	/*
 	 * btrfs_qgroup_inherit relies on a consistent view of the usage for the
@@ -1456,7 +1475,7 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 	ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
-		goto out;
+		return ret;
 	}
 
 	/*
@@ -1509,7 +1528,7 @@ out:
 	 * insert_dir_item()
 	 */
 	if (!ret)
-		record_root_in_trans(trans, parent, 1);
+		ret = record_root_in_trans(trans, parent, 1);
 	return ret;
 }
 
@@ -1586,8 +1605,9 @@ 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, 0);
-
+	ret = record_root_in_trans(trans, parent_root, 0);
+	if (ret)
+		goto fail;
 	cur_time = current_time(parent_inode);
 
 	/*
@@ -1623,7 +1643,11 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	record_root_in_trans(trans, root, 0);
+	ret = record_root_in_trans(trans, root, 0);
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto fail;
+	}
 	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);
@@ -1844,31 +1868,6 @@ int btrfs_transaction_blocked(struct btrfs_fs_info *info)
 }
 
 /*
- * wait for the current transaction commit to start and block subsequent
- * transaction joins
- */
-static void wait_current_trans_commit_start(struct btrfs_fs_info *fs_info,
-					    struct btrfs_transaction *trans)
-{
-	wait_event(fs_info->transaction_blocked_wait,
-		   trans->state >= TRANS_STATE_COMMIT_START ||
-		   TRANS_ABORTED(trans));
-}
-
-/*
- * wait for the current transaction to start and then become unblocked.
- * caller holds ref.
- */
-static void wait_current_trans_commit_start_and_unblock(
-					struct btrfs_fs_info *fs_info,
-					struct btrfs_transaction *trans)
-{
-	wait_event(fs_info->transaction_wait,
-		   trans->state >= TRANS_STATE_UNBLOCKED ||
-		   TRANS_ABORTED(trans));
-}
-
-/*
  * commit transactions asynchronously. once btrfs_commit_transaction_async
  * returns, any subsequent transaction will not be allowed to join.
  */
@@ -1895,8 +1894,7 @@ static void do_async_commit(struct work_struct *work)
 	kfree(ac);
 }
 
-int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
-				   int wait_for_unblock)
+int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_async_commit *ac;
@@ -1928,13 +1926,13 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 		__sb_writers_release(fs_info->sb, SB_FREEZE_FS);
 
 	schedule_work(&ac->work);
-
-	/* wait for transaction to start and unblock */
-	if (wait_for_unblock)
-		wait_current_trans_commit_start_and_unblock(fs_info, cur_trans);
-	else
-		wait_current_trans_commit_start(fs_info, cur_trans);
-
+	/*
+	 * Wait for the current transaction commit to start and block
+	 * subsequent transaction joins
+	 */
+	wait_event(fs_info->transaction_blocked_wait,
+		   cur_trans->state >= TRANS_STATE_COMMIT_START ||
+		   TRANS_ABORTED(cur_trans));
 	if (current->journal_info == trans)
 		current->journal_info = NULL;
 
@@ -1961,7 +1959,6 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
 	 */
 	BUG_ON(list_empty(&cur_trans->list));
 
-	list_del_init(&cur_trans->list);
 	if (cur_trans == fs_info->running_transaction) {
 		cur_trans->state = TRANS_STATE_COMMIT_DOING;
 		spin_unlock(&fs_info->trans_lock);
@@ -1970,6 +1967,17 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
 
 		spin_lock(&fs_info->trans_lock);
 	}
+
+	/*
+	 * Now that we know no one else is still using the transaction we can
+	 * remove the transaction from the list of transactions. This avoids
+	 * the transaction kthread from cleaning up the transaction while some
+	 * other task is still using it, which could result in a use-after-free
+	 * on things like log trees, as it forces the transaction kthread to
+	 * wait for this transaction to be cleaned up by us.
+	 */
+	list_del_init(&cur_trans->list);
+
 	spin_unlock(&fs_info->trans_lock);
 
 	btrfs_cleanup_one_transaction(trans->transaction, fs_info);
@@ -2039,14 +2047,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 
 	ASSERT(refcount_read(&trans->use_count) == 1);
 
-	/*
-	 * Some places just start a transaction to commit it.  We need to make
-	 * sure that if this commit fails that the abort code actually marks the
-	 * transaction as failed, so set trans->dirty to make the abort code do
-	 * the right thing.
-	 */
-	trans->dirty = true;
-
 	/* Stop the commit early if ->aborted is set */
 	if (TRANS_ABORTED(cur_trans)) {
 		ret = cur_trans->aborted;