fix: provide remote servers a way to find out about an event created during the remote join handshake

changelog.d/19390.bugfix

@@ -0,0 +1 @@
+Provide remote servers a way to find out about an event created during the remote join handshake. Contributed by @FrenchGithubUser and @jason-famedly @ Famedly.

synapse/federation/federation_server.py

@@ -758,6 +758,10 @@ async def on_send_join_request(
         event, context = await self._on_send_membership_event(
             origin, content, Membership.JOIN, room_id
         )
+        # Collect this now, the internal metadata of event(which should have it) doesn't
+        stream_ordering_of_join = (
+            await self.store.get_current_room_stream_token_for_room_id(room_id)
+        )
 
         prev_state_ids = await context.get_prev_state_ids()
 
@@ -798,6 +802,28 @@ async def on_send_join_request(
             "members_omitted": caller_supports_partial_state,
         }
 
+        # Check the forward extremities for the room here. If there is more than one, it
+        # is likely that another event was created in the room during the
+        # make_join/send_join handshake. The joining server is likely to thus miss this event
+        # until a second event is created when references it - which could be some time.
+        # In that case, we proactively send a dummy extensible event that ties these
+        # forward extremities together. The remote server will then attempt to backfill
+        # the missing event on its own.
+        #
+        # By not sending the 'missing event' directly, but instead having the joining
+        # homeserver backfill it, the stream ordering for the missing event will be
+        # "before" the join (which is what we expect).
+
+        forward_extremities = await self.store._get_forward_extremeties_for_room(
+            room_id, stream_ordering_of_join.get_max_stream_pos()
+        )
+
+        if len(forward_extremities) > 1:
+            # The likelihood of this being used is extremely low, thus only build the handler
+            # when necessary.
+            _creation_handler = self.hs.get_event_creation_handler()
+            await _creation_handler._send_dummy_event_after_room_join(room_id)
+
         if servers_in_room is not None:
             resp["servers_in_room"] = list(servers_in_room)
 

synapse/handlers/message.py

@@ -2220,7 +2220,39 @@ async def _send_dummy_events_to_fill_extremities(self) -> None:
                 now = self.clock.time_msec()
                 self._rooms_to_exclude_from_dummy_event_insertion[room_id] = now
 
-    async def _send_dummy_event_for_room(self, room_id: str) -> bool:
+    async def _send_dummy_event_after_room_join(self, room_id: str) -> None:
+        """
+        Creates and sends a dummy event into the given room, referencing the
+        current forward extremities (via `prev_events`).
+        This should only be triggered when handling a remote join while there was
+        events sent during the make_join/send_join handshake. The joining
+        homeserver would otherwise not immediately know to backfill this event,
+        and would "miss it".
+        """
+        async with self._worker_lock_handler.acquire_read_write_lock(
+            NEW_EVENT_DURING_PURGE_LOCK_NAME, room_id, write=False
+        ):
+            dummy_event_sent = await self._send_dummy_event_for_room(
+                room_id, proactively_send=True
+            )
+
+        if not dummy_event_sent:
+            # Did not find a valid user in the room, so remove from future attempts
+            # Exclusion is time limited, so the room will be rechecked in the future
+            # dependent on _DUMMY_EVENT_ROOM_EXCLUSION_EXPIRY
+            logger.info(
+                "Failed to send dummy event into room %s. Will exclude it from "
+                "future attempts until cache expires",
+                room_id,
+            )
+            # This mapping is room_id -> time of last attempt(in ms)
+            self._rooms_to_exclude_from_dummy_event_insertion[room_id] = (
+                self.clock.time_msec()
+            )
+
+    async def _send_dummy_event_for_room(
+        self, room_id: str, proactively_send: bool = False
+    ) -> bool:
         """Attempt to send a dummy event for the given room.
 
         Args:
@@ -2252,8 +2284,7 @@ async def _send_dummy_event_for_room(self, room_id: str) -> bool:
                             },
                         )
                         context = await unpersisted_context.persist(event)
-
-                        event.internal_metadata.proactively_send = False
+                        event.internal_metadata.proactively_send = proactively_send
 
                         # Since this is a dummy-event it is OK if it is sent by a
                         # shadow-banned user.