Disable bytes usage with postgres

More often than not passing bytes to `txn.execute` is a bug (where we
meant to pass a string) that just happens to work if `BYTEA_OUTPUT` is
set to `ESCAPE`. However, this is a bit of a footgun so we want to
instead error when this happens, and force using `bytearray` if we
actually want to use bytes.

3 files changed, 10 insertions, 3 deletions

diff --git a/synapse/storage/engines/postgres.py b/synapse/storage/engines/postgres.py

index 601617b21e..d670286fa5 100644
--- a/synapse/storage/engines/postgres.py
+++ b/synapse/storage/engines/postgres.py
@@ -22,6 +22,13 @@ class PostgresEngine(object):
     def __init__(self, database_module, database_config):
         self.module = database_module
         self.module.extensions.register_type(self.module.extensions.UNICODE)
+
+        # Disables passing `bytes` to txn.execute, c.f. #6186. If you do
+        # actually want to use bytes than wrap it in `bytearray`.
+        def _disable_bytes_adapter(_):
+            raise Exception("Passing bytes to DB is disabled.")
+
+        self.module.extensions.register_adapter(bytes, _disable_bytes_adapter)
         self.synchronous_commit = database_config.get("synchronous_commit", True)
         self._version = None  # unknown as yet
 
diff --git a/synapse/storage/filtering.py b/synapse/storage/filtering.py

index 23b48f6cea..7c2a7da836 100644
--- a/synapse/storage/filtering.py
+++ b/synapse/storage/filtering.py
@@ -51,7 +51,7 @@ class FilteringStore(SQLBaseStore):
                 "SELECT filter_id FROM user_filters "
                 "WHERE user_id = ? AND filter_json = ?"
             )
-            txn.execute(sql, (user_localpart, def_json))
+            txn.execute(sql, (user_localpart, bytearray(def_json)))
             filter_id_response = txn.fetchone()
             if filter_id_response is not None:
                 return filter_id_response[0]
@@ -68,7 +68,7 @@ class FilteringStore(SQLBaseStore):
                 "INSERT INTO user_filters (user_id, filter_id, filter_json)"
                 "VALUES(?, ?, ?)"
             )
-            txn.execute(sql, (user_localpart, filter_id, def_json))
+            txn.execute(sql, (user_localpart, filter_id, bytearray(def_json)))
 
             return filter_id
 
diff --git a/synapse/storage/pusher.py b/synapse/storage/pusher.py

index 3e0e834a62..b12e80440a 100644
--- a/synapse/storage/pusher.py
+++ b/synapse/storage/pusher.py
@@ -241,7 +241,7 @@ class PusherStore(PusherWorkerStore):
                     "device_display_name": device_display_name,
                     "ts": pushkey_ts,
                     "lang": lang,
-                    "data": encode_canonical_json(data),
+                    "data": bytearray(encode_canonical_json(data)),
                     "last_stream_ordering": last_stream_ordering,
                     "profile_tag": profile_tag,
                     "id": stream_id,