bcachefs: BTREE_INSERT_JOURNAL_REPLAY now "don't init trans->journal_res"

This slightly changes how trans->journal_res works, in preparation for
changing the btree write buffer flush path to use it.

Now, BTREE_INSERT_JOURNAL_REPLAY means "don't take a journal
reservation; trans->journal_res.seq already refers to the journal
sequence number to pin".

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

2 files changed, 17 insertions, 4 deletions

diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index 3152f6abf73f..ec90a06a6cf9 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -677,8 +677,6 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 
 		if (unlikely(trans->journal_transaction_names))
 			journal_transaction_name(trans);
-	} else {
-		trans->journal_res.seq = c->journal.replay_journal_seq;
 	}
 
 	/*
@@ -897,7 +895,8 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags
 	 * Drop journal reservation after dropping write locks, since dropping
 	 * the journal reservation may kick off a journal write:
 	 */
-	bch2_journal_res_put(&c->journal, &trans->journal_res);
+	if (likely(!(flags & BTREE_INSERT_JOURNAL_REPLAY)))
+		bch2_journal_res_put(&c->journal, &trans->journal_res);
 
 	return ret;
 }
@@ -1140,7 +1139,8 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 	}
 retry:
 	bch2_trans_verify_not_in_restart(trans);
-	memset(&trans->journal_res, 0, sizeof(trans->journal_res));
+	if (likely(!(flags & BTREE_INSERT_JOURNAL_REPLAY)))
+		memset(&trans->journal_res, 0, sizeof(trans->journal_res));
 
 	ret = do_bch2_trans_commit(trans, flags, &i, _RET_IP_);
 
@@ -1165,5 +1165,16 @@ err:
 	if (ret)
 		goto out;
 
+	/*
+	 * We might have done another transaction commit in the error path -
+	 * i.e. btree write buffer flush - which will have made use of
+	 * trans->journal_res, but with BTREE_INSERT_JOURNAL_REPLAY that is how
+	 * the journal sequence number to pin is passed in - so we must restart:
+	 */
+	if (flags & BTREE_INSERT_JOURNAL_REPLAY) {
+		ret = -BCH_ERR_transaction_restart_nested;
+		goto out;
+	}
+
 	goto retry;
 }
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 9c30500ce920..8fe39a91beed 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -98,6 +98,8 @@ static int bch2_journal_replay_key(struct btree_trans *trans,
 	unsigned update_flags = BTREE_TRIGGER_NORUN;
 	int ret;
 
+	trans->journal_res.seq = k->journal_seq;
+
 	/*
 	 * BTREE_UPDATE_KEY_CACHE_RECLAIM disables key cache lookup/update to
 	 * keep the key cache coherent with the underlying btree. Nothing