Btrfs: make sure logged extents complete in the current transaction V3

Liu Bo pointed out that my previous fix would lose the generation update in the
scenario I described.  It is actually much worse than that, we could lose the
entire extent if we lose power right after the transaction commits.  Consider
the following

write extent 0-4k
log extent in log tree
commit transaction
	< power fail happens here
ordered extent completes

We would lose the 0-4k extent because it hasn't updated the actual fs tree, and
the transaction commit will reset the log so it isn't replayed.  If we lose
power before the transaction commit we are save, otherwise we are not.

Fix this by keeping track of all extents we logged in this transaction.  Then
when we go to commit the transaction make sure we wait for all of those ordered
extents to complete before proceeding.  This will make sure that if we lose
power after the transaction commit we still have our data.  This also fixes the
problem of the improperly updated extent generation.  Thanks,

cc: stable@vger.kernel.org
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>

1 files changed, 33 insertions, 0 deletions

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 16c704b68704..295a135c9c24 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -247,6 +247,7 @@ loop:
 	INIT_LIST_HEAD(&cur_trans->pending_snapshots);
 	INIT_LIST_HEAD(&cur_trans->pending_chunks);
 	INIT_LIST_HEAD(&cur_trans->switch_commits);
+	INIT_LIST_HEAD(&cur_trans->pending_ordered);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
 	extent_io_tree_init(&cur_trans->dirty_pages,
 			     fs_info->btree_inode->i_mapping);
@@ -515,6 +516,7 @@ again:
 	h->sync = false;
 	INIT_LIST_HEAD(&h->qgroup_ref_list);
 	INIT_LIST_HEAD(&h->new_bgs);
+	INIT_LIST_HEAD(&h->ordered);
 
 	smp_mb();
 	if (cur_trans->state >= TRANS_STATE_BLOCKED &&
@@ -746,6 +748,12 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	if (!list_empty(&trans->new_bgs))
 		btrfs_create_pending_block_groups(trans, root);
 
+	if (!list_empty(&trans->ordered)) {
+		spin_lock(&info->trans_lock);
+		list_splice(&trans->ordered, &cur_trans->pending_ordered);
+		spin_unlock(&info->trans_lock);
+	}
+
 	trans->delayed_ref_updates = 0;
 	if (!trans->sync) {
 		must_run_delayed_refs =
@@ -1715,6 +1723,28 @@ static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
 		btrfs_wait_ordered_roots(fs_info, -1);
 }
 
+static inline void
+btrfs_wait_pending_ordered(struct btrfs_transaction *cur_trans,
+			   struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_ordered_extent *ordered;
+
+	spin_lock(&fs_info->trans_lock);
+	while (!list_empty(&cur_trans->pending_ordered)) {
+		ordered = list_first_entry(&cur_trans->pending_ordered,
+					   struct btrfs_ordered_extent,
+					   trans_list);
+		list_del_init(&ordered->trans_list);
+		spin_unlock(&fs_info->trans_lock);
+
+		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_COMPLETE,
+						   &ordered->flags));
+		btrfs_put_ordered_extent(ordered);
+		spin_lock(&fs_info->trans_lock);
+	}
+	spin_unlock(&fs_info->trans_lock);
+}
+
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root)
 {
@@ -1765,6 +1795,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	}
 
 	spin_lock(&root->fs_info->trans_lock);
+	list_splice(&trans->ordered, &cur_trans->pending_ordered);
 	if (cur_trans->state >= TRANS_STATE_COMMIT_START) {
 		spin_unlock(&root->fs_info->trans_lock);
 		atomic_inc(&cur_trans->use_count);
@@ -1817,6 +1848,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	btrfs_wait_delalloc_flush(root->fs_info);
 
+	btrfs_wait_pending_ordered(cur_trans, root->fs_info);
+
 	btrfs_scrub_pause(root);
 	/*
 	 * Ok now we need to make sure to block out any other joins while we