Merge branch 'develop' of github.com:matrix-org/synapse into erikj/faster_typing

10 files changed, 198 insertions, 70 deletions

diff --git a/synapse/handlers/auth.py b/synapse/handlers/auth.py
index 4a81bd2ba9..2a5eab124f 100644
--- a/synapse/handlers/auth.py
+++ b/synapse/handlers/auth.py
@@ -895,22 +895,24 @@ class AuthHandler(BaseHandler):
 
         Args:
             password (unicode): Password to hash.
-            stored_hash (unicode): Expected hash value.
+            stored_hash (bytes): Expected hash value.
 
         Returns:
             Deferred(bool): Whether self.hash(password) == stored_hash.
         """
-
         def _do_validate_hash():
             # Normalise the Unicode in the password
             pw = unicodedata.normalize("NFKC", password)
 
             return bcrypt.checkpw(
                 pw.encode('utf8') + self.hs.config.password_pepper.encode("utf8"),
-                stored_hash.encode('utf8')
+                stored_hash
             )
 
         if stored_hash:
+            if not isinstance(stored_hash, bytes):
+                stored_hash = stored_hash.encode('ascii')
+
             return make_deferred_yieldable(
                 threads.deferToThreadPool(
                     self.hs.get_reactor(),
diff --git a/synapse/handlers/directory.py b/synapse/handlers/directory.py
index ef866da1b6..18741c5fac 100644
--- a/synapse/handlers/directory.py
+++ b/synapse/handlers/directory.py
@@ -20,7 +20,14 @@ import string
 from twisted.internet import defer
 
 from synapse.api.constants import EventTypes
-from synapse.api.errors import AuthError, CodeMessageException, Codes, SynapseError
+from synapse.api.errors import (
+    AuthError,
+    CodeMessageException,
+    Codes,
+    NotFoundError,
+    StoreError,
+    SynapseError,
+)
 from synapse.types import RoomAlias, UserID, get_domain_from_id
 
 from ._base import BaseHandler
@@ -109,7 +116,13 @@ class DirectoryHandler(BaseHandler):
     def delete_association(self, requester, user_id, room_alias):
         # association deletion for human users
 
-        can_delete = yield self._user_can_delete_alias(room_alias, user_id)
+        try:
+            can_delete = yield self._user_can_delete_alias(room_alias, user_id)
+        except StoreError as e:
+            if e.code == 404:
+                raise NotFoundError("Unknown room alias")
+            raise
+
         if not can_delete:
             raise AuthError(
                 403, "You don't have permission to delete the alias.",
@@ -320,7 +333,7 @@ class DirectoryHandler(BaseHandler):
     def _user_can_delete_alias(self, alias, user_id):
         creator = yield self.store.get_room_alias_creator(alias.to_string())
 
-        if creator and creator == user_id:
+        if creator is not None and creator == user_id:
             defer.returnValue(True)
 
         is_admin = yield self.auth.is_server_admin(UserID.from_string(user_id))
diff --git a/synapse/handlers/e2e_keys.py b/synapse/handlers/e2e_keys.py
index 5816bf8b4f..578e9250fb 100644
--- a/synapse/handlers/e2e_keys.py
+++ b/synapse/handlers/e2e_keys.py
@@ -330,7 +330,8 @@ class E2eKeysHandler(object):
                         (algorithm, key_id, ex_json, key)
                     )
             else:
-                new_keys.append((algorithm, key_id, encode_canonical_json(key)))
+                new_keys.append((
+                    algorithm, key_id, encode_canonical_json(key).decode('ascii')))
 
         yield self.store.add_e2e_one_time_keys(
             user_id, device_id, time_now, new_keys
@@ -358,7 +359,7 @@ def _exception_to_failure(e):
     # Note that some Exceptions (notably twisted's ResponseFailed etc) don't
     # give a string for e.message, which json then fails to serialize.
     return {
-        "status": 503, "message": str(e.message),
+        "status": 503, "message": str(e),
     }
 
 
diff --git a/synapse/handlers/federation.py b/synapse/handlers/federation.py
index 3fa7a98445..f10b46414b 100644
--- a/synapse/handlers/federation.py
+++ b/synapse/handlers/federation.py
@@ -360,6 +360,35 @@ class FederationHandler(BaseHandler):
         # apparently.
         #
         # see https://github.com/matrix-org/synapse/pull/1744
+        #
+        # ----
+        #
+        # Update richvdh 2018/09/18: There are a number of problems with timing this
+        # request out agressively on the client side:
+        #
+        # - it plays badly with the server-side rate-limiter, which starts tarpitting you
+        #   if you send too many requests at once, so you end up with the server carefully
+        #   working through the backlog of your requests, which you have already timed
+        #   out.
+        #
+        # - for this request in particular, we now (as of
+        #   https://github.com/matrix-org/synapse/pull/3456) reject any PDUs where the
+        #   server can't produce a plausible-looking set of prev_events - so we becone
+        #   much more likely to reject the event.
+        #
+        # - contrary to what it says above, we do *not* fall back to fetching fresh state
+        #   for the room if get_missing_events times out. Rather, we give up processing
+        #   the PDU whose prevs we are missing, which then makes it much more likely that
+        #   we'll end up back here for the *next* PDU in the list, which exacerbates the
+        #   problem.
+        #
+        # - the agressive 10s timeout was introduced to deal with incoming federation
+        #   requests taking 8 hours to process. It's not entirely clear why that was going
+        #   on; certainly there were other issues causing traffic storms which are now
+        #   resolved, and I think in any case we may be more sensible about our locking
+        #   now. We're *certainly* more sensible about our logging.
+        #
+        # All that said: Let's try increasing the timout to 60s and see what happens.
 
         missing_events = yield self.federation_client.get_missing_events(
             origin,
@@ -368,7 +397,7 @@ class FederationHandler(BaseHandler):
             latest_events=[pdu],
             limit=10,
             min_depth=min_depth,
-            timeout=10000,
+            timeout=60000,
         )
 
         logger.info(
@@ -594,7 +623,7 @@ class FederationHandler(BaseHandler):
 
         required_auth = set(
             a_id
-            for event in events + state_events.values() + auth_events.values()
+            for event in events + list(state_events.values()) + list(auth_events.values())
             for a_id, _ in event.auth_events
         )
         auth_events.update({
@@ -802,7 +831,7 @@ class FederationHandler(BaseHandler):
                     )
                     continue
                 except NotRetryingDestination as e:
-                    logger.info(e.message)
+                    logger.info(str(e))
                     continue
                 except FederationDeniedError as e:
                     logger.info(e)
@@ -1358,7 +1387,7 @@ class FederationHandler(BaseHandler):
         )
 
         if state_groups:
-            _, state = state_groups.items().pop()
+            _, state = list(state_groups.items()).pop()
             results = state
 
             if event.is_state():
diff --git a/synapse/handlers/pagination.py b/synapse/handlers/pagination.py
index 5170d093e3..a155b6e938 100644
--- a/synapse/handlers/pagination.py
+++ b/synapse/handlers/pagination.py
@@ -269,14 +269,7 @@ class PaginationHandler(object):
 
             if state_ids:
                 state = yield self.store.get_events(list(state_ids.values()))
-
-            if state:
-                state = yield filter_events_for_client(
-                    self.store,
-                    user_id,
-                    state.values(),
-                    is_peeking=(member_event_id is None),
-                )
+                state = state.values()
 
         time_now = self.clock.time_msec()
 
diff --git a/synapse/handlers/register.py b/synapse/handlers/register.py
index 1e53f2c635..da914c46ff 100644
--- a/synapse/handlers/register.py
+++ b/synapse/handlers/register.py
@@ -534,4 +534,5 @@ class RegistrationHandler(BaseHandler):
             room_id=room_id,
             remote_room_hosts=remote_room_hosts,
             action="join",
+            ratelimit=False,
         )
diff --git a/synapse/handlers/room_list.py b/synapse/handlers/room_list.py
index 37e41afd61..38e1737ec9 100644
--- a/synapse/handlers/room_list.py
+++ b/synapse/handlers/room_list.py
@@ -162,7 +162,7 @@ class RoomListHandler(BaseHandler):
         # Filter out rooms that we don't want to return
         rooms_to_scan = [
             r for r in sorted_rooms
-            if r not in newly_unpublished and rooms_to_num_joined[room_id] > 0
+            if r not in newly_unpublished and rooms_to_num_joined[r] > 0
         ]
 
         total_room_count = len(rooms_to_scan)
diff --git a/synapse/handlers/room_member.py b/synapse/handlers/room_member.py
index f643619047..07fd3e82fc 100644
--- a/synapse/handlers/room_member.py
+++ b/synapse/handlers/room_member.py
@@ -583,6 +583,11 @@ class RoomMemberHandler(object):
         room_id = mapping["room_id"]
         servers = mapping["servers"]
 
+        # put the server which owns the alias at the front of the server list.
+        if room_alias.domain in servers:
+            servers.remove(room_alias.domain)
+        servers.insert(0, room_alias.domain)
+
         defer.returnValue((RoomID.from_string(room_id), servers))
 
     @defer.inlineCallbacks
diff --git a/synapse/handlers/search.py b/synapse/handlers/search.py
index c464adbd0b..0c1d52fd11 100644
--- a/synapse/handlers/search.py
+++ b/synapse/handlers/search.py
@@ -54,7 +54,7 @@ class SearchHandler(BaseHandler):
         batch_token = None
         if batch:
             try:
-                b = decode_base64(batch)
+                b = decode_base64(batch).decode('ascii')
                 batch_group, batch_group_key, batch_token = b.split("\n")
 
                 assert batch_group is not None
@@ -258,18 +258,18 @@ class SearchHandler(BaseHandler):
                 # it returns more from the same group (if applicable) rather
                 # than reverting to searching all results again.
                 if batch_group and batch_group_key:
-                    global_next_batch = encode_base64("%s\n%s\n%s" % (
+                    global_next_batch = encode_base64(("%s\n%s\n%s" % (
                         batch_group, batch_group_key, pagination_token
-                    ))
+                    )).encode('ascii'))
                 else:
-                    global_next_batch = encode_base64("%s\n%s\n%s" % (
+                    global_next_batch = encode_base64(("%s\n%s\n%s" % (
                         "all", "", pagination_token
-                    ))
+                    )).encode('ascii'))
 
                 for room_id, group in room_groups.items():
-                    group["next_batch"] = encode_base64("%s\n%s\n%s" % (
+                    group["next_batch"] = encode_base64(("%s\n%s\n%s" % (
                         "room_id", room_id, pagination_token
-                    ))
+                    )).encode('ascii'))
 
             allowed_events.extend(room_events)
 
diff --git a/synapse/handlers/sync.py b/synapse/handlers/sync.py
index ef20c2296c..9bca4e7067 100644
--- a/synapse/handlers/sync.py
+++ b/synapse/handlers/sync.py
@@ -24,6 +24,7 @@ from twisted.internet import defer
 
 from synapse.api.constants import EventTypes, Membership
 from synapse.push.clientformat import format_push_rules_for_user
+from synapse.storage.roommember import MemberSummary
 from synapse.types import RoomStreamToken
 from synapse.util.async_helpers import concurrently_execute
 from synapse.util.caches.expiringcache import ExpiringCache
@@ -525,6 +526,8 @@ class SyncHandler(object):
              A deferred dict describing the room summary
         """
 
+        # FIXME: we could/should get this from room_stats when matthew/stats lands
+
         # FIXME: this promulgates https://github.com/matrix-org/synapse/issues/3305
         last_events, _ = yield self.store.get_recent_event_ids_for_room(
             room_id, end_token=now_token.room_key, limit=1,
@@ -537,44 +540,67 @@ class SyncHandler(object):
         last_event = last_events[-1]
         state_ids = yield self.store.get_state_ids_for_event(
             last_event.event_id, [
-                (EventTypes.Member, None),
                 (EventTypes.Name, ''),
                 (EventTypes.CanonicalAlias, ''),
             ]
         )
 
-        member_ids = {
-            state_key: event_id
-            for (t, state_key), event_id in state_ids.iteritems()
-            if t == EventTypes.Member
-        }
+        # this is heavily cached, thus: fast.
+        details = yield self.store.get_room_summary(room_id)
+
         name_id = state_ids.get((EventTypes.Name, ''))
         canonical_alias_id = state_ids.get((EventTypes.CanonicalAlias, ''))
 
         summary = {}
-
-        # FIXME: it feels very heavy to load up every single membership event
-        # just to calculate the counts.
-        member_events = yield self.store.get_events(member_ids.values())
-
-        joined_user_ids = []
-        invited_user_ids = []
-
-        for ev in member_events.values():
-            if ev.content.get("membership") == Membership.JOIN:
-                joined_user_ids.append(ev.state_key)
-            elif ev.content.get("membership") == Membership.INVITE:
-                invited_user_ids.append(ev.state_key)
+        empty_ms = MemberSummary([], 0)
 
         # TODO: only send these when they change.
-        summary["m.joined_member_count"] = len(joined_user_ids)
-        summary["m.invited_member_count"] = len(invited_user_ids)
+        summary["m.joined_member_count"] = (
+            details.get(Membership.JOIN, empty_ms).count
+        )
+        summary["m.invited_member_count"] = (
+            details.get(Membership.INVITE, empty_ms).count
+        )
 
-        if name_id or canonical_alias_id:
-            defer.returnValue(summary)
+        # if the room has a name or canonical_alias set, we can skip
+        # calculating heroes.  we assume that if the event has contents, it'll
+        # be a valid name or canonical_alias - i.e. we're checking that they
+        # haven't been "deleted" by blatting {} over the top.
+        if name_id:
+            name = yield self.store.get_event(name_id, allow_none=False)
+            if name and name.content:
+                defer.returnValue(summary)
+
+        if canonical_alias_id:
+            canonical_alias = yield self.store.get_event(
+                canonical_alias_id, allow_none=False,
+            )
+            if canonical_alias and canonical_alias.content:
+                defer.returnValue(summary)
 
-        # FIXME: order by stream ordering, not alphabetic
+        joined_user_ids = [
+            r[0] for r in details.get(Membership.JOIN, empty_ms).members
+        ]
+        invited_user_ids = [
+            r[0] for r in details.get(Membership.INVITE, empty_ms).members
+        ]
+        gone_user_ids = (
+            [r[0] for r in details.get(Membership.LEAVE, empty_ms).members] +
+            [r[0] for r in details.get(Membership.BAN, empty_ms).members]
+        )
 
+        # FIXME: only build up a member_ids list for our heroes
+        member_ids = {}
+        for membership in (
+            Membership.JOIN,
+            Membership.INVITE,
+            Membership.LEAVE,
+            Membership.BAN
+        ):
+            for user_id, event_id in details.get(membership, empty_ms).members:
+                member_ids[user_id] = event_id
+
+        # FIXME: order by stream ordering rather than as returned by SQL
         me = sync_config.user.to_string()
         if (joined_user_ids or invited_user_ids):
             summary['m.heroes'] = sorted(
@@ -586,7 +612,11 @@ class SyncHandler(object):
             )[0:5]
         else:
             summary['m.heroes'] = sorted(
-                [user_id for user_id in member_ids.keys() if user_id != me]
+                [
+                    user_id
+                    for user_id in gone_user_ids
+                    if user_id != me
+                ]
             )[0:5]
 
         if not sync_config.filter_collection.lazy_load_members():
@@ -719,6 +749,26 @@ class SyncHandler(object):
                     lazy_load_members=lazy_load_members,
                 )
             elif batch.limited:
+                state_at_timeline_start = yield self.store.get_state_ids_for_event(
+                    batch.events[0].event_id, types=types,
+                    filtered_types=filtered_types,
+                )
+
+                # for now, we disable LL for gappy syncs - see
+                # https://github.com/vector-im/riot-web/issues/7211#issuecomment-419976346
+                # N.B. this slows down incr syncs as we are now processing way
+                # more state in the server than if we were LLing.
+                #
+                # We still have to filter timeline_start to LL entries (above) in order
+                # for _calculate_state's LL logic to work, as we have to include LL
+                # members for timeline senders in case they weren't loaded in the initial
+                # sync.  We do this by (counterintuitively) by filtering timeline_start
+                # members to just be ones which were timeline senders, which then ensures
+                # all of the rest get included in the state block (if we need to know
+                # about them).
+                types = None
+                filtered_types = None
+
                 state_at_previous_sync = yield self.get_state_at(
                     room_id, stream_position=since_token, types=types,
                     filtered_types=filtered_types,
@@ -729,24 +779,21 @@ class SyncHandler(object):
                     filtered_types=filtered_types,
                 )
 
-                state_at_timeline_start = yield self.store.get_state_ids_for_event(
-                    batch.events[0].event_id, types=types,
-                    filtered_types=filtered_types,
-                )
-
                 state_ids = _calculate_state(
                     timeline_contains=timeline_state,
                     timeline_start=state_at_timeline_start,
                     previous=state_at_previous_sync,
                     current=current_state_ids,
+                    # we have to include LL members in case LL initial sync missed them
                     lazy_load_members=lazy_load_members,
                 )
             else:
                 state_ids = {}
                 if lazy_load_members:
                     if types:
-                        # We're returning an incremental sync, with no "gap" since
-                        # the previous sync, so normally there would be no state to return
+                        # We're returning an incremental sync, with no
+                        # "gap" since the previous sync, so normally there would be
+                        # no state to return.
                         # But we're lazy-loading, so the client might need some more
                         # member events to understand the events in this timeline.
                         # So we fish out all the member events corresponding to the
@@ -774,7 +821,7 @@ class SyncHandler(object):
                     logger.debug("filtering state from %r...", state_ids)
                     state_ids = {
                         t: event_id
-                        for t, event_id in state_ids.iteritems()
+                        for t, event_id in iteritems(state_ids)
                         if cache.get(t[1]) != event_id
                     }
                     logger.debug("...to %r", state_ids)
@@ -1575,6 +1622,19 @@ class SyncHandler(object):
             newly_joined_room=newly_joined,
         )
 
+        # When we join the room (or the client requests full_state), we should
+        # send down any existing tags. Usually the user won't have tags in a
+        # newly joined room, unless either a) they've joined before or b) the
+        # tag was added by synapse e.g. for server notice rooms.
+        if full_state:
+            user_id = sync_result_builder.sync_config.user.to_string()
+            tags = yield self.store.get_tags_for_room(user_id, room_id)
+
+            # If there aren't any tags, don't send the empty tags list down
+            # sync
+            if not tags:
+                tags = None
+
         account_data_events = []
         if tags is not None:
             account_data_events.append({
@@ -1603,10 +1663,24 @@ class SyncHandler(object):
         )
 
         summary = {}
+
+        # we include a summary in room responses when we're lazy loading
+        # members (as the client otherwise doesn't have enough info to form
+        # the name itself).
         if (
             sync_config.filter_collection.lazy_load_members() and
             (
+                # we recalulate the summary:
+                #   if there are membership changes in the timeline, or
+                #   if membership has changed during a gappy sync, or
+                #   if this is an initial sync.
                 any(ev.type == EventTypes.Member for ev in batch.events) or
+                (
+                    # XXX: this may include false positives in the form of LL
+                    # members which have snuck into state
+                    batch.limited and
+                    any(t == EventTypes.Member for (t, k) in state)
+                ) or
                 since_token is None
             )
         ):
@@ -1636,6 +1710,16 @@ class SyncHandler(object):
                     unread_notifications["highlight_count"] = notifs["highlight_count"]
 
                 sync_result_builder.joined.append(room_sync)
+
+            if batch.limited and since_token:
+                user_id = sync_result_builder.sync_config.user.to_string()
+                logger.info(
+                    "Incremental gappy sync of %s for user %s with %d state events" % (
+                        room_id,
+                        user_id,
+                        len(state),
+                    )
+                )
         elif room_builder.rtype == "archived":
             room_sync = ArchivedSyncResult(
                 room_id=room_id,
@@ -1729,17 +1813,17 @@ def _calculate_state(
     event_id_to_key = {
         e: key
         for key, e in itertools.chain(
-            timeline_contains.items(),
-            previous.items(),
-            timeline_start.items(),
-            current.items(),
+            iteritems(timeline_contains),
+            iteritems(previous),
+            iteritems(timeline_start),
+            iteritems(current),
         )
     }
 
-    c_ids = set(e for e in current.values())
-    ts_ids = set(e for e in timeline_start.values())
-    p_ids = set(e for e in previous.values())
-    tc_ids = set(e for e in timeline_contains.values())
+    c_ids = set(e for e in itervalues(current))
+    ts_ids = set(e for e in itervalues(timeline_start))
+    p_ids = set(e for e in itervalues(previous))
+    tc_ids = set(e for e in itervalues(timeline_contains))
 
     # If we are lazyloading room members, we explicitly add the membership events
     # for the senders in the timeline into the state block returned by /sync,
@@ -1753,7 +1837,7 @@ def _calculate_state(
 
     if lazy_load_members:
         p_ids.difference_update(
-            e for t, e in timeline_start.iteritems()
+            e for t, e in iteritems(timeline_start)
             if t[0] == EventTypes.Member
         )