Merge tag 'v1.20.0rc5' into develop

Synapse 1.20.0rc5 (2020-09-18)
==============================

In addition to the below, Synapse 1.20.0rc5 also includes the bug fix that was included in 1.19.3.

Features
--------

- Add flags to the `/versions` endpoint for whether new rooms default to using E2EE. ([\#8343](https://github.com/matrix-org/synapse/issues/8343))

Bugfixes
--------

- Fix rate limiting of federation `/send` requests. ([\#8342](https://github.com/matrix-org/synapse/issues/8342))
- Fix a longstanding bug where back pagination over federation could get stuck if it failed to handle a received event. ([\#8349](https://github.com/matrix-org/synapse/issues/8349))

Internal Changes
----------------

- Blacklist [MSC2753](https://github.com/matrix-org/matrix-doc/pull/2753) SyTests until it is implemented. ([\#8285](https://github.com/matrix-org/synapse/issues/8285))

6 files changed, 89 insertions, 26 deletions

diff --git a/synapse/__init__.py b/synapse/__init__.py
index 6b11c5681b..a95753dcc7 100644
--- a/synapse/__init__.py
+++ b/synapse/__init__.py
@@ -48,7 +48,7 @@ try:
 except ImportError:
     pass
 
-__version__ = "1.20.0rc4"
+__version__ = "1.20.0rc5"
 
 if bool(os.environ.get("SYNAPSE_TEST_PATCH_LOG_CONTEXTS", False)):
     # We import here so that we don't have to install a bunch of deps when
diff --git a/synapse/federation/federation_client.py b/synapse/federation/federation_client.py
index 639d19f696..688d43fffb 100644
--- a/synapse/federation/federation_client.py
+++ b/synapse/federation/federation_client.py
@@ -217,11 +217,9 @@ class FederationClient(FederationBase):
             for p in transaction_data["pdus"]
         ]
 
-        # FIXME: We should handle signature failures more gracefully.
-        pdus[:] = await make_deferred_yieldable(
-            defer.gatherResults(
-                self._check_sigs_and_hashes(room_version, pdus), consumeErrors=True,
-            ).addErrback(unwrapFirstError)
+        # Check signatures and hash of pdus, removing any from the list that fail checks
+        pdus[:] = await self._check_sigs_and_hash_and_fetch(
+            dest, pdus, outlier=True, room_version=room_version
         )
 
         return pdus
diff --git a/synapse/handlers/federation.py b/synapse/handlers/federation.py
index 96eeff7b1b..ea9264e751 100644
--- a/synapse/handlers/federation.py
+++ b/synapse/handlers/federation.py
@@ -917,15 +917,26 @@ class FederationHandler(BaseHandler):
 
         return events
 
-    async def maybe_backfill(self, room_id, current_depth):
+    async def maybe_backfill(
+        self, room_id: str, current_depth: int, limit: int
+    ) -> bool:
         """Checks the database to see if we should backfill before paginating,
         and if so do.
+
+        Args:
+            room_id
+            current_depth: The depth from which we're paginating from. This is
+                used to decide if we should backfill and what extremities to
+                use.
+            limit: The number of events that the pagination request will
+                return. This is used as part of the heuristic to decide if we
+                should back paginate.
         """
         extremities = await self.store.get_oldest_events_with_depth_in_room(room_id)
 
         if not extremities:
             logger.debug("Not backfilling as no extremeties found.")
-            return
+            return False
 
         # We only want to paginate if we can actually see the events we'll get,
         # as otherwise we'll just spend a lot of resources to get redacted
@@ -978,16 +989,54 @@ class FederationHandler(BaseHandler):
         sorted_extremeties_tuple = sorted(extremities.items(), key=lambda e: -int(e[1]))
         max_depth = sorted_extremeties_tuple[0][1]
 
+        # If we're approaching an extremity we trigger a backfill, otherwise we
+        # no-op.
+        #
+        # We chose twice the limit here as then clients paginating backwards
+        # will send pagination requests that trigger backfill at least twice
+        # using the most recent extremity before it gets removed (see below). We
+        # chose more than one times the limit in case of failure, but choosing a
+        # much larger factor will result in triggering a backfill request much
+        # earlier than necessary.
+        if current_depth - 2 * limit > max_depth:
+            logger.debug(
+                "Not backfilling as we don't need to. %d < %d - 2 * %d",
+                max_depth,
+                current_depth,
+                limit,
+            )
+            return False
+
+        logger.debug(
+            "room_id: %s, backfill: current_depth: %s, max_depth: %s, extrems: %s",
+            room_id,
+            current_depth,
+            max_depth,
+            sorted_extremeties_tuple,
+        )
+
+        # We ignore extremities that have a greater depth than our current depth
+        # as:
+        #    1. we don't really care about getting events that have happened
+        #       before our current position; and
+        #    2. we have likely previously tried and failed to backfill from that
+        #       extremity, so to avoid getting "stuck" requesting the same
+        #       backfill repeatedly we drop those extremities.
+        filtered_sorted_extremeties_tuple = [
+            t for t in sorted_extremeties_tuple if int(t[1]) <= current_depth
+        ]
+
+        # However, we need to check that the filtered extremities are non-empty.
+        # If they are empty then either we can a) bail or b) still attempt to
+        # backill. We opt to try backfilling anyway just in case we do get
+        # relevant events.
+        if filtered_sorted_extremeties_tuple:
+            sorted_extremeties_tuple = filtered_sorted_extremeties_tuple
+
         # We don't want to specify too many extremities as it causes the backfill
         # request URI to be too long.
         extremities = dict(sorted_extremeties_tuple[:5])
 
-        if current_depth > max_depth:
-            logger.debug(
-                "Not backfilling as we don't need to. %d < %d", max_depth, current_depth
-            )
-            return
-
         # Now we need to decide which hosts to hit first.
 
         # First we try hosts that are already in the room
diff --git a/synapse/handlers/pagination.py b/synapse/handlers/pagination.py
index d929a68f7d..f132ed3368 100644
--- a/synapse/handlers/pagination.py
+++ b/synapse/handlers/pagination.py
@@ -358,9 +358,9 @@ class PaginationHandler:
                 # if we're going backwards, we might need to backfill. This
                 # requires that we have a topo token.
                 if room_token.topological:
-                    max_topo = room_token.topological
+                    curr_topo = room_token.topological
                 else:
-                    max_topo = await self.store.get_max_topological_token(
+                    curr_topo = await self.store.get_current_topological_token(
                         room_id, room_token.stream
                     )
 
@@ -379,13 +379,13 @@ class PaginationHandler:
                     leave_token = RoomStreamToken.parse(leave_token_str)
                     assert leave_token.topological is not None
 
-                    if leave_token.topological < max_topo:
+                    if leave_token.topological < curr_topo:
                         from_token = from_token.copy_and_replace(
                             "room_key", leave_token
                         )
 
                 await self.hs.get_handlers().federation_handler.maybe_backfill(
-                    room_id, max_topo
+                    room_id, curr_topo, limit=source_config.limit,
                 )
 
             to_room_key = None
diff --git a/synapse/rest/client/versions.py b/synapse/rest/client/versions.py
index d5018afbda..d24a199318 100644
--- a/synapse/rest/client/versions.py
+++ b/synapse/rest/client/versions.py
@@ -19,6 +19,7 @@
 import logging
 import re
 
+from synapse.api.constants import RoomCreationPreset
 from synapse.http.servlet import RestServlet
 
 logger = logging.getLogger(__name__)
@@ -31,6 +32,20 @@ class VersionsRestServlet(RestServlet):
         super().__init__()
         self.config = hs.config
 
+        # Calculate these once since they shouldn't change after start-up.
+        self.e2ee_forced_public = (
+            RoomCreationPreset.PUBLIC_CHAT
+            in self.config.encryption_enabled_by_default_for_room_presets
+        )
+        self.e2ee_forced_private = (
+            RoomCreationPreset.PRIVATE_CHAT
+            in self.config.encryption_enabled_by_default_for_room_presets
+        )
+        self.e2ee_forced_trusted_private = (
+            RoomCreationPreset.TRUSTED_PRIVATE_CHAT
+            in self.config.encryption_enabled_by_default_for_room_presets
+        )
+
     def on_GET(self, request):
         return (
             200,
@@ -62,6 +77,10 @@ class VersionsRestServlet(RestServlet):
                     "org.matrix.msc2432": True,
                     # Implements additional endpoints as described in MSC2666
                     "uk.half-shot.msc2666": True,
+                    # Whether new rooms will be set to encrypted or not (based on presets).
+                    "io.element.e2ee_forced.public": self.e2ee_forced_public,
+                    "io.element.e2ee_forced.private": self.e2ee_forced_private,
+                    "io.element.e2ee_forced.trusted_private": self.e2ee_forced_trusted_private,
                 },
             },
         )
diff --git a/synapse/storage/databases/main/stream.py b/synapse/storage/databases/main/stream.py
index 5dac78e574..92e96468b4 100644
--- a/synapse/storage/databases/main/stream.py
+++ b/synapse/storage/databases/main/stream.py
@@ -640,23 +640,20 @@ class StreamWorkerStore(EventsWorkerStore, SQLBaseStore, metaclass=abc.ABCMeta):
         )
         return "t%d-%d" % (row["topological_ordering"], row["stream_ordering"])
 
-    async def get_max_topological_token(self, room_id: str, stream_key: int) -> int:
-        """Get the max topological token in a room before the given stream
+    async def get_current_topological_token(self, room_id: str, stream_key: int) -> int:
+        """Gets the topological token in a room after or at the given stream
         ordering.
 
         Args:
             room_id
             stream_key
-
-        Returns:
-            The maximum topological token.
         """
         sql = (
-            "SELECT coalesce(max(topological_ordering), 0) FROM events"
-            " WHERE room_id = ? AND stream_ordering < ?"
+            "SELECT coalesce(MIN(topological_ordering), 0) FROM events"
+            " WHERE room_id = ? AND stream_ordering >= ?"
         )
         row = await self.db_pool.execute(
-            "get_max_topological_token", None, sql, room_id, stream_key
+            "get_current_topological_token", None, sql, room_id, stream_key
         )
         return row[0][0] if row else 0