Check the room_id of events when fetching room state/auth (#6524)

When we request the state/auth_events to populate a backwards extremity (on
backfill or in the case of missing events in a transaction push), we should
check that the returned events are in the right room rather than blindly using
them in the room state or auth chain.

Given that _get_events_from_store_or_dest takes a room_id, it seems clear that
it should be sanity-checking the room_id of the requested events, so let's do
it there.

changelog.d/6524.misc

@@ -0,0 +1,2 @@
+Improve sanity-checking when receiving events over federation.
+

synapse/handlers/federation.py

@@ -637,6 +637,10 @@ class FederationHandler(BaseHandler):
             room_id
             event_ids
 
+        If we fail to fetch any of the events, a warning will be logged, and the event
+        will be omitted from the result. Likewise, any events which turn out not to
+        be in the given room.
+
         Returns:
             map from event_id to event
         """
@@ -644,35 +648,59 @@ class FederationHandler(BaseHandler):
 
         missing_events = set(event_ids) - fetched_events.keys()
 
-        if not missing_events:
+        if missing_events:
-            return fetched_events
+            logger.debug(
+                "Fetching unknown state/auth events %s for room %s",
+                missing_events,
+                room_id,
+            )
 
-        logger.debug(
+            room_version = await self.store.get_room_version(room_id)
-            "Fetching unknown state/auth events %s for room %s",
+
-            missing_events,
+            # XXX 20 requests at once? really?
-            event_ids,
+            for batch in batch_iter(missing_events, 20):
+                deferreds = [
+                    run_in_background(
+                        self.federation_client.get_pdu,
+                        destinations=[destination],
+                        event_id=e_id,
+                        room_version=room_version,
+                    )
+                    for e_id in batch
+                ]
+
+                res = await make_deferred_yieldable(
+                    defer.DeferredList(deferreds, consumeErrors=True)
+                )
+
+                for success, result in res:
+                    if success and result:
+                        fetched_events[result.event_id] = result
+
+        # check for events which were in the wrong room.
+        #
+        # this can happen if a remote server claims that the state or
+        # auth_events at an event in room A are actually events in room B
+
+        bad_events = list(
+            (event_id, event.room_id)
+            for event_id, event in fetched_events.items()
+            if event.room_id != room_id
         )
 
-        room_version = await self.store.get_room_version(room_id)
+        for bad_event_id, bad_room_id in bad_events:
-
+            # This is a bogus situation, but since we may only discover it a long time
-        # XXX 20 requests at once? really?
+            # after it happened, we try our best to carry on, by just omitting the
-        for batch in batch_iter(missing_events, 20):
+            # bad events from the returned auth/state set.
-            deferreds = [
+            logger.warning(
-                run_in_background(
+                "Remote server %s claims event %s in room %s is an auth/state "
-                    self.federation_client.get_pdu,
+                "event in room %s",
-                    destinations=[destination],
+                destination,
-                    event_id=e_id,
+                bad_event_id,
-                    room_version=room_version,
+                bad_room_id,
-                )
+                room_id,
-                for e_id in batch
-            ]
-
-            res = await make_deferred_yieldable(
-                defer.DeferredList(deferreds, consumeErrors=True)
             )
-            for success, result in res:
+            del fetched_events[bad_event_id]
-                if success and result:
-                    fetched_events[result.event_id] = result
 
         return fetched_events