1 files changed, 35 insertions, 16 deletions

diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index c2adf3fbb0b3..da594e006769 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -2085,18 +2085,16 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e
 			goto out_no_locked;
 
 		/*
-		 * iter->pos should be mononotically increasing, and always be
-		 * equal to the key we just returned - except extents can
-		 * straddle iter->pos:
+		 * We need to check against @end before FILTER_SNAPSHOTS because
+		 * if we get to a different inode that requested we might be
+		 * seeing keys for a different snapshot tree that will all be
+		 * filtered out.
+		 *
+		 * But we can't do the full check here, because bkey_start_pos()
+		 * isn't monotonically increasing before FILTER_SNAPSHOTS, and
+		 * that's what we check against in extents mode:
 		 */
-		if (!(iter->flags & BTREE_ITER_IS_EXTENTS))
-			iter_pos = k.k->p;
-		else
-			iter_pos = bkey_max(iter->pos, bkey_start_pos(k.k));
-
-		if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS)
-			     ? bkey_gt(iter_pos, end)
-			     : bkey_ge(iter_pos, end)))
+		if (k.k->p.inode > end.inode)
 			goto end;
 
 		if (iter->update_path &&
@@ -2155,6 +2153,21 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e
 			continue;
 		}
 
+		/*
+		 * iter->pos should be mononotically increasing, and always be
+		 * equal to the key we just returned - except extents can
+		 * straddle iter->pos:
+		 */
+		if (!(iter->flags & BTREE_ITER_IS_EXTENTS))
+			iter_pos = k.k->p;
+		else
+			iter_pos = bkey_max(iter->pos, bkey_start_pos(k.k));
+
+		if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS)
+			     ? bkey_gt(iter_pos, end)
+			     : bkey_ge(iter_pos, end)))
+			goto end;
+
 		break;
 	}
 
@@ -2981,7 +2994,8 @@ struct btree_trans *__bch2_trans_get(struct bch_fs *c, unsigned fn_idx)
 	trans->fn_idx		= fn_idx;
 	trans->locking_wait.task = current;
 	trans->journal_replay_not_finished =
-		!test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags);
+		unlikely(!test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags)) &&
+		atomic_inc_not_zero(&c->journal_keys.ref);
 	closure_init_stack(&trans->ref);
 
 	s = btree_trans_stats(trans);
@@ -3087,8 +3101,6 @@ void bch2_trans_put(struct btree_trans *trans)
 		srcu_read_unlock(&c->btree_trans_barrier, trans->srcu_idx);
 	}
 
-	bch2_journal_preres_put(&c->journal, &trans->journal_preres);
-
 	kfree(trans->extra_journal_entries.data);
 
 	if (trans->fs_usage_deltas) {
@@ -3100,6 +3112,9 @@ void bch2_trans_put(struct btree_trans *trans)
 			kfree(trans->fs_usage_deltas);
 	}
 
+	if (unlikely(trans->journal_replay_not_finished))
+		bch2_journal_keys_put(c);
+
 	if (trans->mem_bytes == BTREE_TRANS_MEM_MAX)
 		mempool_free(trans->mem, &c->btree_trans_mem_pool);
 	else
@@ -3212,10 +3227,9 @@ void bch2_fs_btree_iter_exit(struct bch_fs *c)
 	mempool_exit(&c->btree_trans_pool);
 }
 
-int bch2_fs_btree_iter_init(struct bch_fs *c)
+void bch2_fs_btree_iter_init_early(struct bch_fs *c)
 {
 	struct btree_transaction_stats *s;
-	int ret;
 
 	for (s = c->btree_transaction_stats;
 	     s < c->btree_transaction_stats + ARRAY_SIZE(c->btree_transaction_stats);
@@ -3226,6 +3240,11 @@ int bch2_fs_btree_iter_init(struct bch_fs *c)
 
 	INIT_LIST_HEAD(&c->btree_trans_list);
 	seqmutex_init(&c->btree_trans_lock);
+}
+
+int bch2_fs_btree_iter_init(struct bch_fs *c)
+{
+	int ret;
 
 	c->btree_trans_bufs = alloc_percpu(struct btree_trans_buf);
 	if (!c->btree_trans_bufs)