Bugbear: Add Mutable Parameter fixes (#9682)

Part of #9366

Adds in fixes for B006 and B008, both relating to mutable parameter lint errors.

Signed-off-by: Jonathan de Jong <jonathan@automatia.nl>

23 files changed, 130 insertions, 72 deletions

diff --git a/synapse/appservice/scheduler.py b/synapse/appservice/scheduler.py
index 366c476f80..5203ffe90f 100644
--- a/synapse/appservice/scheduler.py
+++ b/synapse/appservice/scheduler.py
@@ -49,7 +49,7 @@ This is all tied together by the AppServiceScheduler which DIs the required
 components.
 """
 import logging
-from typing import List
+from typing import List, Optional
 
 from synapse.appservice import ApplicationService, ApplicationServiceState
 from synapse.events import EventBase
@@ -191,11 +191,11 @@ class _TransactionController:
         self,
         service: ApplicationService,
         events: List[EventBase],
-        ephemeral: List[JsonDict] = [],
+        ephemeral: Optional[List[JsonDict]] = None,
     ):
         try:
             txn = await self.store.create_appservice_txn(
-                service=service, events=events, ephemeral=ephemeral
+                service=service, events=events, ephemeral=ephemeral or []
             )
             service_is_up = await self._is_service_up(service)
             if service_is_up:
diff --git a/synapse/config/ratelimiting.py b/synapse/config/ratelimiting.py
index 3f3997f4e5..7a8d5851c4 100644
--- a/synapse/config/ratelimiting.py
+++ b/synapse/config/ratelimiting.py
@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from typing import Dict
+from typing import Dict, Optional
 
 from ._base import Config
 
@@ -21,8 +21,10 @@ class RateLimitConfig:
     def __init__(
         self,
         config: Dict[str, float],
-        defaults={"per_second": 0.17, "burst_count": 3.0},
+        defaults: Optional[Dict[str, float]] = None,
     ):
+        defaults = defaults or {"per_second": 0.17, "burst_count": 3.0}
+
         self.per_second = config.get("per_second", defaults["per_second"])
         self.burst_count = int(config.get("burst_count", defaults["burst_count"]))
 
diff --git a/synapse/events/__init__.py b/synapse/events/__init__.py
index 8f6b955d17..f9032e3697 100644
--- a/synapse/events/__init__.py
+++ b/synapse/events/__init__.py
@@ -330,9 +330,11 @@ class FrozenEvent(EventBase):
         self,
         event_dict: JsonDict,
         room_version: RoomVersion,
-        internal_metadata_dict: JsonDict = {},
+        internal_metadata_dict: Optional[JsonDict] = None,
         rejected_reason: Optional[str] = None,
     ):
+        internal_metadata_dict = internal_metadata_dict or {}
+
         event_dict = dict(event_dict)
 
         # Signatures is a dict of dicts, and this is faster than doing a
@@ -386,9 +388,11 @@ class FrozenEventV2(EventBase):
         self,
         event_dict: JsonDict,
         room_version: RoomVersion,
-        internal_metadata_dict: JsonDict = {},
+        internal_metadata_dict: Optional[JsonDict] = None,
         rejected_reason: Optional[str] = None,
     ):
+        internal_metadata_dict = internal_metadata_dict or {}
+
         event_dict = dict(event_dict)
 
         # Signatures is a dict of dicts, and this is faster than doing a
@@ -507,9 +511,11 @@ def _event_type_from_format_version(format_version: int) -> Type[EventBase]:
 def make_event_from_dict(
     event_dict: JsonDict,
     room_version: RoomVersion = RoomVersions.V1,
-    internal_metadata_dict: JsonDict = {},
+    internal_metadata_dict: Optional[JsonDict] = None,
     rejected_reason: Optional[str] = None,
 ) -> EventBase:
     """Construct an EventBase from the given event dict"""
     event_type = _event_type_from_format_version(room_version.event_format)
-    return event_type(event_dict, room_version, internal_metadata_dict, rejected_reason)
+    return event_type(
+        event_dict, room_version, internal_metadata_dict or {}, rejected_reason
+    )
diff --git a/synapse/federation/units.py b/synapse/federation/units.py
index b662c42621..0f8bf000ac 100644
--- a/synapse/federation/units.py
+++ b/synapse/federation/units.py
@@ -18,6 +18,7 @@ server protocol.
 """
 
 import logging
+from typing import Optional
 
 import attr
 
@@ -98,7 +99,7 @@ class Transaction(JsonEncodedObject):
         "pdus",
     ]
 
-    def __init__(self, transaction_id=None, pdus=[], **kwargs):
+    def __init__(self, transaction_id=None, pdus: Optional[list] = None, **kwargs):
         """If we include a list of pdus then we decode then as PDU's
         automatically.
         """
@@ -107,7 +108,7 @@ class Transaction(JsonEncodedObject):
         if "edus" in kwargs and not kwargs["edus"]:
             del kwargs["edus"]
 
-        super().__init__(transaction_id=transaction_id, pdus=pdus, **kwargs)
+        super().__init__(transaction_id=transaction_id, pdus=pdus or [], **kwargs)
 
     @staticmethod
     def create_new(pdus, **kwargs):
diff --git a/synapse/handlers/appservice.py b/synapse/handlers/appservice.py
index 996f9e5deb..9fb7ee335d 100644
--- a/synapse/handlers/appservice.py
+++ b/synapse/handlers/appservice.py
@@ -182,7 +182,7 @@ class ApplicationServicesHandler:
         self,
         stream_key: str,
         new_token: Optional[int],
-        users: Collection[Union[str, UserID]] = [],
+        users: Optional[Collection[Union[str, UserID]]] = None,
     ):
         """This is called by the notifier in the background
         when a ephemeral event handled by the homeserver.
@@ -215,7 +215,7 @@ class ApplicationServicesHandler:
         # We only start a new background process if necessary rather than
         # optimistically (to cut down on overhead).
         self._notify_interested_services_ephemeral(
-            services, stream_key, new_token, users
+            services, stream_key, new_token, users or []
         )
 
     @wrap_as_background_process("notify_interested_services_ephemeral")
diff --git a/synapse/handlers/federation.py b/synapse/handlers/federation.py
index 5ea8a7b603..67888898ff 100644
--- a/synapse/handlers/federation.py
+++ b/synapse/handlers/federation.py
@@ -1790,7 +1790,7 @@ class FederationHandler(BaseHandler):
         room_id: str,
         user_id: str,
         membership: str,
-        content: JsonDict = {},
+        content: JsonDict,
         params: Optional[Dict[str, Union[str, Iterable[str]]]] = None,
     ) -> Tuple[str, EventBase, RoomVersion]:
         (
diff --git a/synapse/handlers/message.py b/synapse/handlers/message.py
index 6069968f7f..125dae6d25 100644
--- a/synapse/handlers/message.py
+++ b/synapse/handlers/message.py
@@ -137,7 +137,7 @@ class MessageHandler:
         self,
         user_id: str,
         room_id: str,
-        state_filter: StateFilter = StateFilter.all(),
+        state_filter: Optional[StateFilter] = None,
         at_token: Optional[StreamToken] = None,
         is_guest: bool = False,
     ) -> List[dict]:
@@ -164,6 +164,8 @@ class MessageHandler:
             AuthError (403) if the user doesn't have permission to view
             members of this room.
         """
+        state_filter = state_filter or StateFilter.all()
+
         if at_token:
             # FIXME this claims to get the state at a stream position, but
             # get_recent_events_for_room operates by topo ordering. This therefore
@@ -874,7 +876,7 @@ class EventCreationHandler:
         event: EventBase,
         context: EventContext,
         ratelimit: bool = True,
-        extra_users: List[UserID] = [],
+        extra_users: Optional[List[UserID]] = None,
         ignore_shadow_ban: bool = False,
     ) -> EventBase:
         """Processes a new event.
@@ -902,6 +904,7 @@ class EventCreationHandler:
         Raises:
             ShadowBanError if the requester has been shadow-banned.
         """
+        extra_users = extra_users or []
 
         # we don't apply shadow-banning to membership events here. Invites are blocked
         # higher up the stack, and we allow shadow-banned users to send join and leave
@@ -1071,7 +1074,7 @@ class EventCreationHandler:
         event: EventBase,
         context: EventContext,
         ratelimit: bool = True,
-        extra_users: List[UserID] = [],
+        extra_users: Optional[List[UserID]] = None,
     ) -> EventBase:
         """Called when we have fully built the event, have already
         calculated the push actions for the event, and checked auth.
@@ -1083,6 +1086,8 @@ class EventCreationHandler:
             it was de-duplicated (e.g. because we had already persisted an
             event with the same transaction ID.)
         """
+        extra_users = extra_users or []
+
         assert self.storage.persistence is not None
         assert self._events_shard_config.should_handle(
             self._instance_name, event.room_id
diff --git a/synapse/handlers/register.py b/synapse/handlers/register.py
index 9701b76d0f..3b6660c873 100644
--- a/synapse/handlers/register.py
+++ b/synapse/handlers/register.py
@@ -169,7 +169,7 @@ class RegistrationHandler(BaseHandler):
         user_type: Optional[str] = None,
         default_display_name: Optional[str] = None,
         address: Optional[str] = None,
-        bind_emails: Iterable[str] = [],
+        bind_emails: Optional[Iterable[str]] = None,
         by_admin: bool = False,
         user_agent_ips: Optional[List[Tuple[str, str]]] = None,
         auth_provider_id: Optional[str] = None,
@@ -204,6 +204,8 @@ class RegistrationHandler(BaseHandler):
         Raises:
             SynapseError if there was a problem registering.
         """
+        bind_emails = bind_emails or []
+
         await self.check_registration_ratelimit(address)
 
         result = await self.spam_checker.check_registration_for_spam(
diff --git a/synapse/handlers/sync.py b/synapse/handlers/sync.py
index ff11266c67..f8d88ef77b 100644
--- a/synapse/handlers/sync.py
+++ b/synapse/handlers/sync.py
@@ -548,7 +548,7 @@ class SyncHandler:
         )
 
     async def get_state_after_event(
-        self, event: EventBase, state_filter: StateFilter = StateFilter.all()
+        self, event: EventBase, state_filter: Optional[StateFilter] = None
     ) -> StateMap[str]:
         """
         Get the room state after the given event
@@ -558,7 +558,7 @@ class SyncHandler:
             state_filter: The state filter used to fetch state from the database.
         """
         state_ids = await self.state_store.get_state_ids_for_event(
-            event.event_id, state_filter=state_filter
+            event.event_id, state_filter=state_filter or StateFilter.all()
         )
         if event.is_state():
             state_ids = dict(state_ids)
@@ -569,7 +569,7 @@ class SyncHandler:
         self,
         room_id: str,
         stream_position: StreamToken,
-        state_filter: StateFilter = StateFilter.all(),
+        state_filter: Optional[StateFilter] = None,
     ) -> StateMap[str]:
         """Get the room state at a particular stream position
 
@@ -589,7 +589,7 @@ class SyncHandler:
         if last_events:
             last_event = last_events[-1]
             state = await self.get_state_after_event(
-                last_event, state_filter=state_filter
+                last_event, state_filter=state_filter or StateFilter.all()
             )
 
         else:
diff --git a/synapse/http/client.py b/synapse/http/client.py
index e691ba6d88..f7a07f0466 100644
--- a/synapse/http/client.py
+++ b/synapse/http/client.py
@@ -297,7 +297,7 @@ class SimpleHttpClient:
     def __init__(
         self,
         hs: "HomeServer",
-        treq_args: Dict[str, Any] = {},
+        treq_args: Optional[Dict[str, Any]] = None,
         ip_whitelist: Optional[IPSet] = None,
         ip_blacklist: Optional[IPSet] = None,
         use_proxy: bool = False,
@@ -317,7 +317,7 @@ class SimpleHttpClient:
 
         self._ip_whitelist = ip_whitelist
         self._ip_blacklist = ip_blacklist
-        self._extra_treq_args = treq_args
+        self._extra_treq_args = treq_args or {}
 
         self.user_agent = hs.version_string
         self.clock = hs.get_clock()
diff --git a/synapse/http/proxyagent.py b/synapse/http/proxyagent.py
index 16ec850064..ea5ad14cb0 100644
--- a/synapse/http/proxyagent.py
+++ b/synapse/http/proxyagent.py
@@ -27,7 +27,7 @@ from twisted.python.failure import Failure
 from twisted.web.client import URI, BrowserLikePolicyForHTTPS, _AgentBase
 from twisted.web.error import SchemeNotSupported
 from twisted.web.http_headers import Headers
-from twisted.web.iweb import IAgent
+from twisted.web.iweb import IAgent, IPolicyForHTTPS
 
 from synapse.http.connectproxyclient import HTTPConnectProxyEndpoint
 
@@ -88,12 +88,14 @@ class ProxyAgent(_AgentBase):
         self,
         reactor,
         proxy_reactor=None,
-        contextFactory=BrowserLikePolicyForHTTPS(),
+        contextFactory: Optional[IPolicyForHTTPS] = None,
         connectTimeout=None,
         bindAddress=None,
         pool=None,
         use_proxy=False,
     ):
+        contextFactory = contextFactory or BrowserLikePolicyForHTTPS()
+
         _AgentBase.__init__(self, reactor, pool)
 
         if proxy_reactor is None:
diff --git a/synapse/logging/opentracing.py b/synapse/logging/opentracing.py
index b8081f197e..bfe9136fd8 100644
--- a/synapse/logging/opentracing.py
+++ b/synapse/logging/opentracing.py
@@ -486,7 +486,7 @@ def start_active_span_from_request(
 def start_active_span_from_edu(
     edu_content,
     operation_name,
-    references=[],
+    references: Optional[list] = None,
     tags=None,
     start_time=None,
     ignore_active_span=False,
@@ -501,6 +501,7 @@ def start_active_span_from_edu(
 
         For the other args see opentracing.tracer
     """
+    references = references or []
 
     if opentracing is None:
         return noop_context_manager()
diff --git a/synapse/module_api/__init__.py b/synapse/module_api/__init__.py
index 3ecd46c038..ca1bd4cdc9 100644
--- a/synapse/module_api/__init__.py
+++ b/synapse/module_api/__init__.py
@@ -14,7 +14,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 import logging
-from typing import TYPE_CHECKING, Any, Generator, Iterable, Optional, Tuple
+from typing import TYPE_CHECKING, Any, Generator, Iterable, List, Optional, Tuple
 
 from twisted.internet import defer
 
@@ -127,7 +127,7 @@ class ModuleApi:
         return defer.ensureDeferred(self._auth_handler.check_user_exists(user_id))
 
     @defer.inlineCallbacks
-    def register(self, localpart, displayname=None, emails=[]):
+    def register(self, localpart, displayname=None, emails: Optional[List[str]] = None):
         """Registers a new user with given localpart and optional displayname, emails.
 
         Also returns an access token for the new user.
@@ -147,11 +147,13 @@ class ModuleApi:
         logger.warning(
             "Using deprecated ModuleApi.register which creates a dummy user device."
         )
-        user_id = yield self.register_user(localpart, displayname, emails)
+        user_id = yield self.register_user(localpart, displayname, emails or [])
         _, access_token = yield self.register_device(user_id)
         return user_id, access_token
 
-    def register_user(self, localpart, displayname=None, emails=[]):
+    def register_user(
+        self, localpart, displayname=None, emails: Optional[List[str]] = None
+    ):
         """Registers a new user with given localpart and optional displayname, emails.
 
         Args:
@@ -170,7 +172,7 @@ class ModuleApi:
             self._hs.get_registration_handler().register_user(
                 localpart=localpart,
                 default_display_name=displayname,
-                bind_emails=emails,
+                bind_emails=emails or [],
             )
         )
 
diff --git a/synapse/notifier.py b/synapse/notifier.py
index c178db57e3..7ce34380af 100644
--- a/synapse/notifier.py
+++ b/synapse/notifier.py
@@ -276,7 +276,7 @@ class Notifier:
         event: EventBase,
         event_pos: PersistedEventPosition,
         max_room_stream_token: RoomStreamToken,
-        extra_users: Collection[UserID] = [],
+        extra_users: Optional[Collection[UserID]] = None,
     ):
         """Unwraps event and calls `on_new_room_event_args`."""
         self.on_new_room_event_args(
@@ -286,7 +286,7 @@ class Notifier:
             state_key=event.get("state_key"),
             membership=event.content.get("membership"),
             max_room_stream_token=max_room_stream_token,
-            extra_users=extra_users,
+            extra_users=extra_users or [],
         )
 
     def on_new_room_event_args(
@@ -297,7 +297,7 @@ class Notifier:
         membership: Optional[str],
         event_pos: PersistedEventPosition,
         max_room_stream_token: RoomStreamToken,
-        extra_users: Collection[UserID] = [],
+        extra_users: Optional[Collection[UserID]] = None,
     ):
         """Used by handlers to inform the notifier something has happened
         in the room, room event wise.
@@ -313,7 +313,7 @@ class Notifier:
         self.pending_new_room_events.append(
             _PendingRoomEventEntry(
                 event_pos=event_pos,
-                extra_users=extra_users,
+                extra_users=extra_users or [],
                 room_id=room_id,
                 type=event_type,
                 state_key=state_key,
@@ -382,14 +382,14 @@ class Notifier:
         self,
         stream_key: str,
         new_token: Union[int, RoomStreamToken],
-        users: Collection[Union[str, UserID]] = [],
+        users: Optional[Collection[Union[str, UserID]]] = None,
     ):
         try:
             stream_token = None
             if isinstance(new_token, int):
                 stream_token = new_token
             self.appservice_handler.notify_interested_services_ephemeral(
-                stream_key, stream_token, users
+                stream_key, stream_token, users or []
             )
         except Exception:
             logger.exception("Error notifying application services of event")
@@ -404,13 +404,16 @@ class Notifier:
         self,
         stream_key: str,
         new_token: Union[int, RoomStreamToken],
-        users: Collection[Union[str, UserID]] = [],
-        rooms: Collection[str] = [],
+        users: Optional[Collection[Union[str, UserID]]] = None,
+        rooms: Optional[Collection[str]] = None,
     ):
         """Used to inform listeners that something has happened event wise.
 
         Will wake up all listeners for the given users and rooms.
         """
+        users = users or []
+        rooms = rooms or []
+
         with Measure(self.clock, "on_new_event"):
             user_streams = set()
 
diff --git a/synapse/storage/database.py b/synapse/storage/database.py
index b302cd5786..fa15b0ce5b 100644
--- a/synapse/storage/database.py
+++ b/synapse/storage/database.py
@@ -900,7 +900,7 @@ class DatabasePool:
         table: str,
         keyvalues: Dict[str, Any],
         values: Dict[str, Any],
-        insertion_values: Dict[str, Any] = {},
+        insertion_values: Optional[Dict[str, Any]] = None,
         desc: str = "simple_upsert",
         lock: bool = True,
     ) -> Optional[bool]:
@@ -927,6 +927,8 @@ class DatabasePool:
             Native upserts always return None. Emulated upserts return True if a
             new entry was created, False if an existing one was updated.
         """
+        insertion_values = insertion_values or {}
+
         attempts = 0
         while True:
             try:
@@ -964,7 +966,7 @@ class DatabasePool:
         table: str,
         keyvalues: Dict[str, Any],
         values: Dict[str, Any],
-        insertion_values: Dict[str, Any] = {},
+        insertion_values: Optional[Dict[str, Any]] = None,
         lock: bool = True,
     ) -> Optional[bool]:
         """
@@ -982,6 +984,8 @@ class DatabasePool:
             Native upserts always return None. Emulated upserts return True if a
             new entry was created, False if an existing one was updated.
         """
+        insertion_values = insertion_values or {}
+
         if self.engine.can_native_upsert and table not in self._unsafe_to_upsert_tables:
             self.simple_upsert_txn_native_upsert(
                 txn, table, keyvalues, values, insertion_values=insertion_values
@@ -1003,7 +1007,7 @@ class DatabasePool:
         table: str,
         keyvalues: Dict[str, Any],
         values: Dict[str, Any],
-        insertion_values: Dict[str, Any] = {},
+        insertion_values: Optional[Dict[str, Any]] = None,
         lock: bool = True,
     ) -> bool:
         """
@@ -1017,6 +1021,8 @@ class DatabasePool:
             Returns True if a new entry was created, False if an existing
             one was updated.
         """
+        insertion_values = insertion_values or {}
+
         # We need to lock the table :(, unless we're *really* careful
         if lock:
             self.engine.lock_table(txn, table)
@@ -1077,7 +1083,7 @@ class DatabasePool:
         table: str,
         keyvalues: Dict[str, Any],
         values: Dict[str, Any],
-        insertion_values: Dict[str, Any] = {},
+        insertion_values: Optional[Dict[str, Any]] = None,
     ) -> None:
         """
         Use the native UPSERT functionality in recent PostgreSQL versions.
@@ -1090,7 +1096,7 @@ class DatabasePool:
         """
         allvalues = {}  # type: Dict[str, Any]
         allvalues.update(keyvalues)
-        allvalues.update(insertion_values)
+        allvalues.update(insertion_values or {})
 
         if not values:
             latter = "NOTHING"
@@ -1513,7 +1519,7 @@ class DatabasePool:
         column: str,
         iterable: Iterable[Any],
         retcols: Iterable[str],
-        keyvalues: Dict[str, Any] = {},
+        keyvalues: Optional[Dict[str, Any]] = None,
         desc: str = "simple_select_many_batch",
         batch_size: int = 100,
     ) -> List[Any]:
@@ -1531,6 +1537,8 @@ class DatabasePool:
             desc: description of the transaction, for logging and metrics
             batch_size: the number of rows for each select query
         """
+        keyvalues = keyvalues or {}
+
         results = []  # type: List[Dict[str, Any]]
 
         if not iterable:
diff --git a/synapse/storage/databases/main/events.py b/synapse/storage/databases/main/events.py
index 98dac19a95..ad17123915 100644
--- a/synapse/storage/databases/main/events.py
+++ b/synapse/storage/databases/main/events.py
@@ -320,8 +320,8 @@ class PersistEventsStore:
         txn: LoggingTransaction,
         events_and_contexts: List[Tuple[EventBase, EventContext]],
         backfilled: bool,
-        state_delta_for_room: Dict[str, DeltaState] = {},
-        new_forward_extremeties: Dict[str, List[str]] = {},
+        state_delta_for_room: Optional[Dict[str, DeltaState]] = None,
+        new_forward_extremeties: Optional[Dict[str, List[str]]] = None,
     ):
         """Insert some number of room events into the necessary database tables.
 
@@ -342,6 +342,9 @@ class PersistEventsStore:
                 extremities.
 
         """
+        state_delta_for_room = state_delta_for_room or {}
+        new_forward_extremeties = new_forward_extremeties or {}
+
         all_events_and_contexts = events_and_contexts
 
         min_stream_order = events_and_contexts[0][0].internal_metadata.stream_ordering
diff --git a/synapse/storage/databases/main/group_server.py b/synapse/storage/databases/main/group_server.py
index 8f462dfc31..bd7826f4e9 100644
--- a/synapse/storage/databases/main/group_server.py
+++ b/synapse/storage/databases/main/group_server.py
@@ -1171,7 +1171,7 @@ class GroupServerStore(GroupServerWorkerStore):
         user_id: str,
         membership: str,
         is_admin: bool = False,
-        content: JsonDict = {},
+        content: Optional[JsonDict] = None,
         local_attestation: Optional[dict] = None,
         remote_attestation: Optional[dict] = None,
         is_publicised: bool = False,
@@ -1192,6 +1192,8 @@ class GroupServerStore(GroupServerWorkerStore):
             is_publicised: Whether this should be publicised.
         """
 
+        content = content or {}
+
         def _register_user_group_membership_txn(txn, next_id):
             # TODO: Upsert?
             self.db_pool.simple_delete_txn(
diff --git a/synapse/storage/databases/main/state.py b/synapse/storage/databases/main/state.py
index a7f371732f..93431efe00 100644
--- a/synapse/storage/databases/main/state.py
+++ b/synapse/storage/databases/main/state.py
@@ -190,7 +190,7 @@ class StateGroupWorkerStore(EventsWorkerStore, SQLBaseStore):
 
     # FIXME: how should this be cached?
     async def get_filtered_current_state_ids(
-        self, room_id: str, state_filter: StateFilter = StateFilter.all()
+        self, room_id: str, state_filter: Optional[StateFilter] = None
     ) -> StateMap[str]:
         """Get the current state event of a given type for a room based on the
         current_state_events table.  This may not be as up-to-date as the result
@@ -205,7 +205,9 @@ class StateGroupWorkerStore(EventsWorkerStore, SQLBaseStore):
             Map from type/state_key to event ID.
         """
 
-        where_clause, where_args = state_filter.make_sql_filter_clause()
+        where_clause, where_args = (
+            state_filter or StateFilter.all()
+        ).make_sql_filter_clause()
 
         if not where_clause:
             # We delegate to the cached version
diff --git a/synapse/storage/databases/state/bg_updates.py b/synapse/storage/databases/state/bg_updates.py
index 1fd333b707..75c09b3687 100644
--- a/synapse/storage/databases/state/bg_updates.py
+++ b/synapse/storage/databases/state/bg_updates.py
@@ -14,6 +14,7 @@
 # limitations under the License.
 
 import logging
+from typing import Optional
 
 from synapse.storage._base import SQLBaseStore
 from synapse.storage.database import DatabasePool
@@ -73,8 +74,10 @@ class StateGroupBackgroundUpdateStore(SQLBaseStore):
             return count
 
     def _get_state_groups_from_groups_txn(
-        self, txn, groups, state_filter=StateFilter.all()
+        self, txn, groups, state_filter: Optional[StateFilter] = None
     ):
+        state_filter = state_filter or StateFilter.all()
+
         results = {group: {} for group in groups}
 
         where_clause, where_args = state_filter.make_sql_filter_clause()
diff --git a/synapse/storage/databases/state/store.py b/synapse/storage/databases/state/store.py
index 97ec65f757..dfcf89d91c 100644
--- a/synapse/storage/databases/state/store.py
+++ b/synapse/storage/databases/state/store.py
@@ -15,7 +15,7 @@
 
 import logging
 from collections import namedtuple
-from typing import Dict, Iterable, List, Set, Tuple
+from typing import Dict, Iterable, List, Optional, Set, Tuple
 
 from synapse.api.constants import EventTypes
 from synapse.storage._base import SQLBaseStore
@@ -210,7 +210,7 @@ class StateGroupDataStore(StateBackgroundUpdateStore, SQLBaseStore):
         return state_filter.filter_state(state_dict_ids), not missing_types
 
     async def _get_state_for_groups(
-        self, groups: Iterable[int], state_filter: StateFilter = StateFilter.all()
+        self, groups: Iterable[int], state_filter: Optional[StateFilter] = None
     ) -> Dict[int, MutableStateMap[str]]:
         """Gets the state at each of a list of state groups, optionally
         filtering by type/state_key
@@ -223,6 +223,7 @@ class StateGroupDataStore(StateBackgroundUpdateStore, SQLBaseStore):
         Returns:
             Dict of state group to state map.
         """
+        state_filter = state_filter or StateFilter.all()
 
         member_filter, non_member_filter = state_filter.get_member_split()
 
diff --git a/synapse/storage/state.py b/synapse/storage/state.py
index 2e277a21c4..c1c147c62a 100644
--- a/synapse/storage/state.py
+++ b/synapse/storage/state.py
@@ -449,7 +449,7 @@ class StateGroupStorage:
         return self.stores.state._get_state_groups_from_groups(groups, state_filter)
 
     async def get_state_for_events(
-        self, event_ids: Iterable[str], state_filter: StateFilter = StateFilter.all()
+        self, event_ids: Iterable[str], state_filter: Optional[StateFilter] = None
     ) -> Dict[str, StateMap[EventBase]]:
         """Given a list of event_ids and type tuples, return a list of state
         dicts for each event.
@@ -465,7 +465,7 @@ class StateGroupStorage:
 
         groups = set(event_to_groups.values())
         group_to_state = await self.stores.state._get_state_for_groups(
-            groups, state_filter
+            groups, state_filter or StateFilter.all()
         )
 
         state_event_map = await self.stores.main.get_events(
@@ -485,7 +485,7 @@ class StateGroupStorage:
         return {event: event_to_state[event] for event in event_ids}
 
     async def get_state_ids_for_events(
-        self, event_ids: Iterable[str], state_filter: StateFilter = StateFilter.all()
+        self, event_ids: Iterable[str], state_filter: Optional[StateFilter] = None
     ) -> Dict[str, StateMap[str]]:
         """
         Get the state dicts corresponding to a list of events, containing the event_ids
@@ -502,7 +502,7 @@ class StateGroupStorage:
 
         groups = set(event_to_groups.values())
         group_to_state = await self.stores.state._get_state_for_groups(
-            groups, state_filter
+            groups, state_filter or StateFilter.all()
         )
 
         event_to_state = {
@@ -513,7 +513,7 @@ class StateGroupStorage:
         return {event: event_to_state[event] for event in event_ids}
 
     async def get_state_for_event(
-        self, event_id: str, state_filter: StateFilter = StateFilter.all()
+        self, event_id: str, state_filter: Optional[StateFilter] = None
     ) -> StateMap[EventBase]:
         """
         Get the state dict corresponding to a particular event
@@ -525,11 +525,13 @@ class StateGroupStorage:
         Returns:
             A dict from (type, state_key) -> state_event
         """
-        state_map = await self.get_state_for_events([event_id], state_filter)
+        state_map = await self.get_state_for_events(
+            [event_id], state_filter or StateFilter.all()
+        )
         return state_map[event_id]
 
     async def get_state_ids_for_event(
-        self, event_id: str, state_filter: StateFilter = StateFilter.all()
+        self, event_id: str, state_filter: Optional[StateFilter] = None
     ) -> StateMap[str]:
         """
         Get the state dict corresponding to a particular event
@@ -541,11 +543,13 @@ class StateGroupStorage:
         Returns:
             A dict from (type, state_key) -> state_event
         """
-        state_map = await self.get_state_ids_for_events([event_id], state_filter)
+        state_map = await self.get_state_ids_for_events(
+            [event_id], state_filter or StateFilter.all()
+        )
         return state_map[event_id]
 
     def _get_state_for_groups(
-        self, groups: Iterable[int], state_filter: StateFilter = StateFilter.all()
+        self, groups: Iterable[int], state_filter: Optional[StateFilter] = None
     ) -> Awaitable[Dict[int, MutableStateMap[str]]]:
         """Gets the state at each of a list of state groups, optionally
         filtering by type/state_key
@@ -558,7 +562,9 @@ class StateGroupStorage:
         Returns:
             Dict of state group to state map.
         """
-        return self.stores.state._get_state_for_groups(groups, state_filter)
+        return self.stores.state._get_state_for_groups(
+            groups, state_filter or StateFilter.all()
+        )
 
     async def store_state_group(
         self,
diff --git a/synapse/storage/util/id_generators.py b/synapse/storage/util/id_generators.py
index d4643c4fdf..32d6cc16b9 100644
--- a/synapse/storage/util/id_generators.py
+++ b/synapse/storage/util/id_generators.py
@@ -17,7 +17,7 @@ import logging
 import threading
 from collections import OrderedDict
 from contextlib import contextmanager
-from typing import Dict, List, Optional, Set, Tuple, Union
+from typing import Dict, Iterable, List, Optional, Set, Tuple, Union
 
 import attr
 
@@ -91,7 +91,14 @@ class StreamIdGenerator:
             # ... persist event ...
     """
 
-    def __init__(self, db_conn, table, column, extra_tables=[], step=1):
+    def __init__(
+        self,
+        db_conn,
+        table,
+        column,
+        extra_tables: Iterable[Tuple[str, str]] = (),
+        step=1,
+    ):
         assert step != 0
         self._lock = threading.Lock()
         self._step = step
diff --git a/synapse/util/caches/lrucache.py b/synapse/util/caches/lrucache.py
index 60bb6ff642..20c8e2d9f5 100644
--- a/synapse/util/caches/lrucache.py
+++ b/synapse/util/caches/lrucache.py
@@ -57,12 +57,14 @@ def enumerate_leaves(node, depth):
 class _Node:
     __slots__ = ["prev_node", "next_node", "key", "value", "callbacks"]
 
-    def __init__(self, prev_node, next_node, key, value, callbacks=set()):
+    def __init__(
+        self, prev_node, next_node, key, value, callbacks: Optional[set] = None
+    ):
         self.prev_node = prev_node
         self.next_node = next_node
         self.key = key
         self.value = value
-        self.callbacks = callbacks
+        self.callbacks = callbacks or set()
 
 
 class LruCache(Generic[KT, VT]):
@@ -176,10 +178,10 @@ class LruCache(Generic[KT, VT]):
 
         self.len = synchronized(cache_len)
 
-        def add_node(key, value, callbacks=set()):
+        def add_node(key, value, callbacks: Optional[set] = None):
             prev_node = list_root
             next_node = prev_node.next_node
-            node = _Node(prev_node, next_node, key, value, callbacks)
+            node = _Node(prev_node, next_node, key, value, callbacks or set())
             prev_node.next_node = node
             next_node.prev_node = node
             cache[key] = node
@@ -237,7 +239,7 @@ class LruCache(Generic[KT, VT]):
         def cache_get(
             key: KT,
             default: Optional[T] = None,
-            callbacks: Iterable[Callable[[], None]] = [],
+            callbacks: Iterable[Callable[[], None]] = (),
             update_metrics: bool = True,
         ):
             node = cache.get(key, None)
@@ -253,7 +255,7 @@ class LruCache(Generic[KT, VT]):
                 return default
 
         @synchronized
-        def cache_set(key: KT, value: VT, callbacks: Iterable[Callable[[], None]] = []):
+        def cache_set(key: KT, value: VT, callbacks: Iterable[Callable[[], None]] = ()):
             node = cache.get(key, None)
             if node is not None:
                 # We sometimes store large objects, e.g. dicts, which cause