From 96e0cdbc5af0563ee805ec4e588e1df14899af66 Mon Sep 17 00:00:00 2001
From: Richard van der Hoff <1389908+richvdh@users.noreply.github.com>
Date: Tue, 3 May 2022 21:27:52 +0100
Subject: Add a consistency check on events read from the database (#12620)

I've seen a few errors which can only plausibly be explained by the calculated
event id for an event being different from the ID of the event in the
database. It should be cheap to check this, so let's do so and raise an
exception.
---
 synapse/storage/databases/main/events_worker.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'synapse')

diff --git a/synapse/storage/databases/main/events_worker.py b/synapse/storage/databases/main/events_worker.py
index c31fc00eaa..0a48e5d29f 100644
--- a/synapse/storage/databases/main/events_worker.py
+++ b/synapse/storage/databases/main/events_worker.py
@@ -1094,6 +1094,18 @@ class EventsWorkerStore(SQLBaseStore):
             original_ev.internal_metadata.stream_ordering = row.stream_ordering
             original_ev.internal_metadata.outlier = row.outlier
 
+            # Consistency check: if the content of the event has been modified in the
+            # database, then the calculated event ID will not match the event id in the
+            # database.
+            if original_ev.event_id != event_id:
+                # it's difficult to see what to do here. Pretty much all bets are off
+                # if Synapse cannot rely on the consistency of its database.
+                raise RuntimeError(
+                    f"Database corruption: Event {event_id} in room {d['room_id']} "
+                    f"from the database appears to have been modified (calculated "
+                    f"event id {original_ev.event_id})"
+                )
+
             event_map[event_id] = original_ev
 
         # finally, we can decide whether each one needs redacting, and build
-- 
cgit 1.4.1