Backfill remote event fetched by MSC3030 so we can paginate from it later (#13205)

Depends on https://github.com/matrix-org/synapse/pull/13320

Complement tests: https://github.com/matrix-org/complement/pull/406

We could use the same method to backfill for `/context` as well in the future, see https://github.com/matrix-org/synapse/issues/3848

1 files changed, 45 insertions, 14 deletions

diff --git a/synapse/handlers/room.py b/synapse/handlers/room.py
index 978d3ee39f..55395457c3 100644
--- a/synapse/handlers/room.py
+++ b/synapse/handlers/room.py
@@ -1384,6 +1384,7 @@ class TimestampLookupHandler:
         self.store = hs.get_datastores().main
         self.state_handler = hs.get_state_handler()
         self.federation_client = hs.get_federation_client()
+        self.federation_event_handler = hs.get_federation_event_handler()
         self._storage_controllers = hs.get_storage_controllers()
 
     async def get_event_for_timestamp(
@@ -1479,38 +1480,68 @@ class TimestampLookupHandler:
                         remote_response,
                     )
 
-                    # TODO: Do we want to persist this as an extremity?
-                    # TODO: I think ideally, we would try to backfill from
-                    # this event and run this whole
-                    # `get_event_for_timestamp` function again to make sure
-                    # they didn't give us an event from their gappy history.
                     remote_event_id = remote_response.event_id
-                    origin_server_ts = remote_response.origin_server_ts
+                    remote_origin_server_ts = remote_response.origin_server_ts
+
+                    # Backfill this event so we can get a pagination token for
+                    # it with `/context` and paginate `/messages` from this
+                    # point.
+                    #
+                    # TODO: The requested timestamp may lie in a part of the
+                    #   event graph that the remote server *also* didn't have,
+                    #   in which case they will have returned another event
+                    #   which may be nowhere near the requested timestamp. In
+                    #   the future, we may need to reconcile that gap and ask
+                    #   other homeservers, and/or extend `/timestamp_to_event`
+                    #   to return events on *both* sides of the timestamp to
+                    #   help reconcile the gap faster.
+                    remote_event = (
+                        await self.federation_event_handler.backfill_event_id(
+                            domain, room_id, remote_event_id
+                        )
+                    )
+
+                    # XXX: When we see that the remote server is not trustworthy,
+                    # maybe we should not ask them first in the future.
+                    if remote_origin_server_ts != remote_event.origin_server_ts:
+                        logger.info(
+                            "get_event_for_timestamp: Remote server (%s) claimed that remote_event_id=%s occured at remote_origin_server_ts=%s but that isn't true (actually occured at %s). Their claims are dubious and we should consider not trusting them.",
+                            domain,
+                            remote_event_id,
+                            remote_origin_server_ts,
+                            remote_event.origin_server_ts,
+                        )
 
                     # Only return the remote event if it's closer than the local event
                     if not local_event or (
-                        abs(origin_server_ts - timestamp)
+                        abs(remote_event.origin_server_ts - timestamp)
                         < abs(local_event.origin_server_ts - timestamp)
                     ):
-                        return remote_event_id, origin_server_ts
+                        logger.info(
+                            "get_event_for_timestamp: returning remote_event_id=%s (%s) since it's closer to timestamp=%s than local_event=%s (%s)",
+                            remote_event_id,
+                            remote_event.origin_server_ts,
+                            timestamp,
+                            local_event.event_id if local_event else None,
+                            local_event.origin_server_ts if local_event else None,
+                        )
+                        return remote_event_id, remote_origin_server_ts
                 except (HttpResponseException, InvalidResponseError) as ex:
                     # Let's not put a high priority on some other homeserver
                     # failing to respond or giving a random response
                     logger.debug(
-                        "Failed to fetch /timestamp_to_event from %s because of exception(%s) %s args=%s",
+                        "get_event_for_timestamp: Failed to fetch /timestamp_to_event from %s because of exception(%s) %s args=%s",
                         domain,
                         type(ex).__name__,
                         ex,
                         ex.args,
                     )
-                except Exception as ex:
+                except Exception:
                     # But we do want to see some exceptions in our code
                     logger.warning(
-                        "Failed to fetch /timestamp_to_event from %s because of exception(%s) %s args=%s",
+                        "get_event_for_timestamp: Failed to fetch /timestamp_to_event from %s because of exception",
                         domain,
-                        type(ex).__name__,
-                        ex,
-                        ex.args,
+                        exc_info=True,
                     )
 
         # To appease mypy, we have to add both of these conditions to check for