Merge pull request #3856 from matrix-org/erikj/speed_up_purge

Make purge history slightly faster

.circleci/config.yml

@@ -9,6 +9,8 @@ jobs:
       - store_artifacts:
           path: ~/project/logs
           destination: logs
+      - store_test_results:
+          path: logs
   sytestpy2postgres:
     machine: true
     steps:
@@ -18,6 +20,34 @@ jobs:
       - store_artifacts:
           path: ~/project/logs
           destination: logs
+      - store_test_results:
+          path: logs
+  sytestpy2merged:
+    machine: true
+    steps:
+      - checkout
+      - run: bash .circleci/merge_base_branch.sh
+      - run: docker pull matrixdotorg/sytest-synapsepy2
+      - run: docker run --rm -it -v $(pwd)\:/src -v $(pwd)/logs\:/logs matrixdotorg/sytest-synapsepy2
+      - store_artifacts:
+          path: ~/project/logs
+          destination: logs
+      - store_test_results:
+          path: logs
+
+  sytestpy2postgresmerged:
+    machine: true
+    steps:
+      - checkout
+      - run: bash .circleci/merge_base_branch.sh
+      - run: docker pull matrixdotorg/sytest-synapsepy2
+      - run: docker run --rm -it -v $(pwd)\:/src -v $(pwd)/logs\:/logs -e POSTGRES=1 matrixdotorg/sytest-synapsepy2
+      - store_artifacts:
+          path: ~/project/logs
+          destination: logs
+      - store_test_results:
+          path: logs
+
   sytestpy3:
     machine: true
     steps:
@@ -27,6 +57,8 @@ jobs:
       - store_artifacts:
           path: ~/project/logs
           destination: logs
+      - store_test_results:
+          path: logs
   sytestpy3postgres:
     machine: true
     steps:
@@ -36,6 +68,32 @@ jobs:
       - store_artifacts:
           path: ~/project/logs
           destination: logs
+      - store_test_results:
+          path: logs
+  sytestpy3merged:
+    machine: true
+    steps:
+      - checkout
+      - run: bash .circleci/merge_base_branch.sh
+      - run: docker pull matrixdotorg/sytest-synapsepy3
+      - run: docker run --rm -it -v $(pwd)\:/src -v $(pwd)/logs\:/logs hawkowl/sytestpy3
+      - store_artifacts:
+          path: ~/project/logs
+          destination: logs
+      - store_test_results:
+          path: logs
+  sytestpy3postgresmerged:
+    machine: true
+    steps:
+      - checkout
+      - run: bash .circleci/merge_base_branch.sh
+      - run: docker pull matrixdotorg/sytest-synapsepy3
+      - run: docker run --rm -it -v $(pwd)\:/src -v $(pwd)/logs\:/logs -e POSTGRES=1 matrixdotorg/sytest-synapsepy3
+      - store_artifacts:
+          path: ~/project/logs
+          destination: logs
+      - store_test_results:
+          path: logs
 
 workflows:
   version: 2
@@ -43,6 +101,14 @@ workflows:
     jobs:
       - sytestpy2
       - sytestpy2postgres
+      - sytestpy2merged:
+          filters:
+            branches:
+              ignore: /develop|master/
+      - sytestpy2postgresmerged:
+          filters:
+            branches:
+              ignore: /develop|master/
 # Currently broken while the Python 3 port is incomplete
 #      - sytestpy3
 #      - sytestpy3postgres

.circleci/merge_base_branch.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+
+set -e
+
+# CircleCI doesn't give CIRCLE_PR_NUMBER in the environment for non-forked PRs. Wonderful.
+# In this case, we just need to do some ~shell magic~ to strip it out of the PULL_REQUEST URL.
+echo 'export CIRCLE_PR_NUMBER="${CIRCLE_PR_NUMBER:-${CIRCLE_PULL_REQUEST##*/}}"' >> $BASH_ENV
+source $BASH_ENV
+
+if [[ -z "${CIRCLE_PR_NUMBER}" ]]
+then
+    echo "Can't figure out what the PR number is!"
+    exit 1
+fi
+
+# Get the reference, using the GitHub API
+GITBASE=`curl -q https://api.github.com/repos/matrix-org/synapse/pulls/${CIRCLE_PR_NUMBER} | jq -r '.base.ref'`
+
+# Show what we are before
+git show -s
+
+# Set up username so it can do a merge
+git config --global user.email bot@matrix.org
+git config --global user.name "A robot"
+
+# Fetch and merge. If it doesn't work, it will raise due to set -e.
+git fetch -u origin $GITBASE
+git merge --no-edit origin/$GITBASE
+
+# Show what we are after.
+git show -s

.dockerignore

@@ -3,6 +3,5 @@ Dockerfile
 .gitignore
 demo/etc
 tox.ini
-synctl
 .git/*
 .tox/*

.gitignore

@@ -44,6 +44,7 @@ media_store/
 build/
 venv/
 venv*/
+*venv/
 
 localhost-800*/
 static/client/register/register_config.js

.travis.yml

@@ -8,9 +8,6 @@ before_script:
   - git remote set-branches --add origin develop
   - git fetch origin develop
 
-services:
-  - postgresql
-
 matrix:
   fast_finish: true
   include:
@@ -25,6 +22,8 @@ matrix:
 
   - python: 2.7
     env: TOX_ENV=py27-postgres TRIAL_FLAGS="-j 4"
+    services:
+      - postgresql
 
   - python: 3.6
     env: TOX_ENV=py36
@@ -35,10 +34,6 @@ matrix:
   - python: 3.6
     env: TOX_ENV=check-newsfragment
 
-  allow_failures:
-  - python: 2.7
-    env: TOX_ENV=py27-postgres TRIAL_FLAGS="-j 4"
-
 install:
   - pip install tox
 

CHANGES.md

@@ -1,3 +1,77 @@
+Synapse 0.33.4 (2018-09-07)
+===========================
+
+Internal Changes
+----------------
+
+- Unignore synctl in .dockerignore to fix docker builds ([\#3802](https://github.com/matrix-org/synapse/issues/3802))
+
+
+Synapse 0.33.4rc2 (2018-09-06)
+==============================
+
+Pull in security fixes from v0.33.3.1
+
+
+Synapse 0.33.3.1 (2018-09-06)
+=============================
+
+SECURITY FIXES
+--------------
+
+- Fix an issue where event signatures were not always correctly validated ([\#3796](https://github.com/matrix-org/synapse/issues/3796))
+- Fix an issue where server_acls could be circumvented for incoming events ([\#3796](https://github.com/matrix-org/synapse/issues/3796))
+
+
+Internal Changes
+----------------
+
+- Unignore synctl in .dockerignore to fix docker builds ([\#3802](https://github.com/matrix-org/synapse/issues/3802))
+
+
+Synapse 0.33.4rc1 (2018-09-04)
+==============================
+
+Features
+--------
+
+- Support profile API endpoints on workers ([\#3659](https://github.com/matrix-org/synapse/issues/3659))
+- Server notices for resource limit blocking ([\#3680](https://github.com/matrix-org/synapse/issues/3680))
+- Allow guests to use /rooms/:roomId/event/:eventId ([\#3724](https://github.com/matrix-org/synapse/issues/3724))
+- Add mau_trial_days config param, so that users only get counted as MAU after N days. ([\#3749](https://github.com/matrix-org/synapse/issues/3749))
+- Require twisted 17.1 or later (fixes [#3741](https://github.com/matrix-org/synapse/issues/3741)). ([\#3751](https://github.com/matrix-org/synapse/issues/3751))
+
+
+Bugfixes
+--------
+
+- Fix error collecting prometheus metrics when run on dedicated thread due to threading concurrency issues ([\#3722](https://github.com/matrix-org/synapse/issues/3722))
+- Fix bug where we resent "limit exceeded" server notices repeatedly ([\#3747](https://github.com/matrix-org/synapse/issues/3747))
+- Fix bug where we broke sync when using limit_usage_by_mau but hadn't configured server notices ([\#3753](https://github.com/matrix-org/synapse/issues/3753))
+- Fix 'federation_domain_whitelist' such that an empty list correctly blocks all outbound federation traffic ([\#3754](https://github.com/matrix-org/synapse/issues/3754))
+- Fix tagging of server notice rooms ([\#3755](https://github.com/matrix-org/synapse/issues/3755), [\#3756](https://github.com/matrix-org/synapse/issues/3756))
+- Fix 'admin_uri' config variable and error parameter to be 'admin_contact' to match the spec. ([\#3758](https://github.com/matrix-org/synapse/issues/3758))
+- Don't return non-LL-member state in incremental sync state blocks ([\#3760](https://github.com/matrix-org/synapse/issues/3760))
+- Fix bug in sending presence over federation ([\#3768](https://github.com/matrix-org/synapse/issues/3768))
+- Fix bug where preserved threepid user comes to sign up and server is mau blocked ([\#3777](https://github.com/matrix-org/synapse/issues/3777))
+
+Internal Changes
+----------------
+
+- Removed the link to the unmaintained matrix-synapse-auto-deploy project from the readme. ([\#3378](https://github.com/matrix-org/synapse/issues/3378))
+- Refactor state module to support multiple room versions ([\#3673](https://github.com/matrix-org/synapse/issues/3673))
+- The synapse.storage module has been ported to Python 3. ([\#3725](https://github.com/matrix-org/synapse/issues/3725))
+- Split the state_group_cache into member and non-member state events (and so speed up LL /sync) ([\#3726](https://github.com/matrix-org/synapse/issues/3726))
+- Log failure to authenticate remote servers as warnings (without stack traces) ([\#3727](https://github.com/matrix-org/synapse/issues/3727))
+- The CONTRIBUTING guidelines have been updated to mention our use of Markdown and that .misc files have content. ([\#3730](https://github.com/matrix-org/synapse/issues/3730))
+- Reference the need for an HTTP replication port when using the federation_reader worker ([\#3734](https://github.com/matrix-org/synapse/issues/3734))
+- Fix minor spelling error in federation client documentation. ([\#3735](https://github.com/matrix-org/synapse/issues/3735))
+- Remove redundant state resolution function ([\#3737](https://github.com/matrix-org/synapse/issues/3737))
+- The test suite now passes on PostgreSQL. ([\#3740](https://github.com/matrix-org/synapse/issues/3740))
+- Fix MAU cache invalidation due to missing yield ([\#3746](https://github.com/matrix-org/synapse/issues/3746))
+- Make sure that we close db connections opened during init ([\#3764](https://github.com/matrix-org/synapse/issues/3764))
+
+
 Synapse 0.33.3 (2018-08-22)
 ===========================
 

CONTRIBUTING.rst

@@ -59,9 +59,10 @@ To create a changelog entry, make a new file in the ``changelog.d``
 file named in the format of ``PRnumber.type``. The type can be
 one of ``feature``, ``bugfix``, ``removal`` (also used for
 deprecations), or ``misc`` (for internal-only changes). The content of
-the file is your changelog entry, which can contain RestructuredText
-formatting. A note of contributors is welcomed in changelogs for
-non-misc changes (the content of misc changes is not displayed).
+the file is your changelog entry, which can contain Markdown
+formatting. Adding credits to the changelog is encouraged, we value
+your contributions and would like to have you shouted out in the
+release notes!
 
 For example, a fix in PR #1234 would have its changelog entry in
 ``changelog.d/1234.bugfix``, and contain content like "The security levels of

README.rst

@@ -167,11 +167,6 @@ Alternatively, Andreas Peters (previously Silvio Fricke) has contributed a
 Dockerfile to automate a synapse server in a single Docker image, at
 https://hub.docker.com/r/avhost/docker-matrix/tags/
 
-Also, Martin Giess has created an auto-deployment process with vagrant/ansible,
-tested with VirtualBox/AWS/DigitalOcean - see 
-https://github.com/EMnify/matrix-synapse-auto-deploy
-for details.
-
 Configuring synapse
 -------------------
 
@@ -747,6 +742,18 @@ so an example nginx configuration might look like::
       }
   }
 
+and an example apache configuration may look like::
+
+    <VirtualHost *:443>
+        SSLEngine on
+        ServerName matrix.example.com;
+
+        <Location /_matrix>
+            ProxyPass http://127.0.0.1:8008/_matrix nocanon
+            ProxyPassReverse http://127.0.0.1:8008/_matrix
+        </Location>
+    </VirtualHost>
+
 You will also want to set ``bind_addresses: ['127.0.0.1']`` and ``x_forwarded: true``
 for port 8008 in ``homeserver.yaml`` to ensure that client IP addresses are
 recorded correctly.

changelog.d/3659.feature

@@ -1 +0,0 @@
-Support profile API endpoints on workers

changelog.d/3673.misc

@@ -1 +0,0 @@
-Refactor state module to support multiple room versions

changelog.d/3680.feature

@@ -1 +0,0 @@
-Server notices for resource limit blocking

changelog.d/3704.misc

@@ -0,0 +1 @@
+CircleCI tests now run on the potential merge of a PR.

changelog.d/3722.bugfix

@@ -1 +0,0 @@
-Fix error collecting prometheus metrics when run on dedicated thread due to threading concurrency issues

changelog.d/3724.feature

@@ -1 +0,0 @@
-Allow guests to use /rooms/:roomId/event/:eventId

changelog.d/3726.misc

@@ -1 +0,0 @@
-Split the state_group_cache into member and non-member state events (and so speed up LL /sync)

changelog.d/3727.misc

@@ -1 +0,0 @@
-Log failure to authenticate remote servers as warnings (without stack traces)

changelog.d/3734.misc

@@ -1 +0,0 @@
-Reference the need for an HTTP replication port when using the federation_reader worker

changelog.d/3735.misc

@@ -1 +0,0 @@
-Fix minor spelling error in federation client documentation.

changelog.d/3746.misc

@@ -1 +0,0 @@
-Fix MAU cache invalidation due to missing yield

changelog.d/3747.bugfix

@@ -1 +0,0 @@
-Fix bug where we resent "limit exceeded" server notices repeatedly

changelog.d/3749.feature

@@ -1 +0,0 @@
-Add mau_trial_days config param, so that users only get counted as MAU after N days.

changelog.d/3751.feature

@@ -1 +0,0 @@
-Require twisted 17.1 or later (fixes [#3741](https://github.com/matrix-org/synapse/issues/3741)).

changelog.d/3753.bugfix

@@ -1 +0,0 @@
-Fix bug where we broke sync when using limit_usage_by_mau but hadn't configured server notices

changelog.d/3754.bugfix

@@ -1 +0,0 @@
-Fix 'federation_domain_whitelist' such that an empty list correctly blocks all outbound federation traffic

changelog.d/3755.bugfix

@@ -1 +0,0 @@
-Fix tagging of server notice rooms

changelog.d/3756.bugfix

@@ -1 +0,0 @@
-Fix tagging of server notice rooms

changelog.d/3758.bugfix

@@ -1 +0,0 @@
-Fix 'admin_uri' config variable and error parameter to be 'admin_contact' to match the spec.

changelog.d/3771.misc

@@ -0,0 +1 @@
+http/ is now ported to Python 3.

changelog.d/3788.bugfix

@@ -0,0 +1 @@
+Remove connection ID for replication prometheus metrics, as it creates a large number of new series.

changelog.d/3789.misc

@@ -0,0 +1 @@
+Improve human readable error messages for threepid registration/account update

changelog.d/3790.feature

@@ -0,0 +1 @@
+Implement `event_format` filter param in `/sync`

changelog.d/3795.misc

@@ -0,0 +1 @@
+Make /sync slightly faster by avoiding needless copies

changelog.d/3800.bugfix

@@ -0,0 +1 @@
+guest users should not be part of mau total

changelog.d/3803.misc

@@ -0,0 +1 @@
+handlers/ is now ported to Python 3.

changelog.d/3804.bugfix

@@ -0,0 +1 @@
+Bump dependency on pyopenssl 16.x, to avoid incompatibility with recent Twisted.

changelog.d/3805.misc

@@ -0,0 +1 @@
+Limit the number of PDUs/EDUs per federation transaction

changelog.d/3806.misc

@@ -0,0 +1 @@
+Only start postgres instance for postgres tests on Travis CI

changelog.d/3808.misc

@@ -0,0 +1 @@
+tests/ is now ported to Python 3.

changelog.d/3810.bugfix

@@ -0,0 +1 @@
+Fix existing room tags not coming down sync when joining a room

changelog.d/3822.misc

@@ -0,0 +1 @@
+crypto/ is now ported to Python 3.

changelog.d/3823.misc

@@ -0,0 +1 @@
+rest/ is now ported to Python 3.

changelog.d/3824.bugfix

@@ -0,0 +1 @@
+Fix jwt import check

changelog.d/3826.misc

@@ -0,0 +1 @@
+add some logging for the keyring queue

changelog.d/3827.misc

@@ -0,0 +1 @@
+speed up lazy loading by 2-3x

changelog.d/3834.misc

@@ -0,0 +1 @@
+Improved Dockerfile to remove build requirements after building reducing the image size.

changelog.d/3835.bugfix

@@ -0,0 +1 @@
+fix VOIP crashes under Python 3 (#3821)

changelog.d/3840.misc

@@ -0,0 +1 @@
+Disable lazy loading for incremental syncs for now

changelog.d/3841.bugfix

@@ -0,0 +1 @@
+Fix manhole so that it works with latest openssh clients

changelog.d/3845.bugfix

@@ -0,0 +1 @@
+Fix outbound requests occasionally wedging, which can result in federation breaking between servers.

changelog.d/3846.feature

@@ -0,0 +1 @@
+Add synapse_admin_mau:registered_reserved_users metric to expose number of real reaserved users 

changelog.d/3847.misc

@@ -0,0 +1 @@
+federation/ is now ported to Python 3.

changelog.d/3851.bugfix

@@ -0,0 +1 @@
+Show heroes if room name/canonical alias has been deleted

changelog.d/3853.misc

@@ -0,0 +1 @@
+Log when we retry outbound requests

changelog.d/3855.misc

@@ -0,0 +1 @@
+Removed some excess logging messages.

changelog.d/3856.misc

@@ -0,0 +1 @@
+Speed up purge history for rooms that have been previously purged

changelog.d/3857.misc

@@ -0,0 +1 @@
+Refactor some HTTP timeout code.

changelog.d/3858.misc

@@ -0,0 +1 @@
+Fix running merged builds on CircleCI

changelog.d/3859.bugfix

@@ -0,0 +1 @@
+Fix handling of redacted events from federation

docker/Dockerfile

@@ -1,6 +1,8 @@
 FROM docker.io/python:2-alpine3.8
 
-RUN apk add --no-cache --virtual .nacl_deps \
+COPY . /synapse
+
+RUN apk add --no-cache --virtual .build_deps \
         build-base \
         libffi-dev \
         libjpeg-turbo-dev \
@@ -8,13 +10,16 @@ RUN apk add --no-cache --virtual .nacl_deps \
         libxslt-dev \
         linux-headers \
         postgresql-dev \
-        su-exec \
-        zlib-dev
-
-COPY . /synapse
-
-# A wheel cache may be provided in ./cache for faster build
-RUN cd /synapse \
+        zlib-dev \
+ && cd /synapse \
+ && apk add --no-cache --virtual .runtime_deps \
+ 	libffi \
+        libjpeg-turbo \
+	libressl \
+	libxslt \
+	libpq \
+	zlib \
+	su-exec \
  && pip install --upgrade \
         lxml \
         pip \
@@ -26,8 +31,9 @@ RUN cd /synapse \
  && rm -rf \
         setup.cfg \
         setup.py \
-        synapse
-
+        synapse \
+ && apk del .build_deps
+ 
 VOLUME ["/data"]
 
 EXPOSE 8008/tcp 8448/tcp

jenkins/prepare_synapse.sh

@@ -31,5 +31,5 @@ $TOX_BIN/pip install 'setuptools>=18.5'
 $TOX_BIN/pip install 'pip>=10'
 
 { python synapse/python_dependencies.py
-  echo lxml psycopg2
+  echo lxml
 } | xargs $TOX_BIN/pip install

setup.cfg

@@ -17,13 +17,14 @@ ignore =
 [pep8]
 max-line-length = 90
 #  W503 requires that binary operators be at the end, not start, of lines. Erik
-#  doesn't like it.  E203 is contrary to PEP8.
-ignore = W503,E203
+#  doesn't like it.  E203 is contrary to PEP8.  E731 is silly.
+ignore = W503,E203,E731
 
 [flake8]
 # note that flake8 inherits the "ignore" settings from "pep8" (because it uses
 # pep8 to do those checks), but not the "max-line-length" setting
 max-line-length = 90
+ignore=W503,E203,E731
 
 [isort]
 line_length = 89

synapse/__init__.py

@@ -17,4 +17,14 @@
 """ This is a reference implementation of a Matrix home server.
 """
 
-__version__ = "0.33.3"
+try:
+    from twisted.internet import protocol
+    from twisted.internet.protocol import Factory
+    from twisted.names.dns import DNSDatagramProtocol
+    protocol.Factory.noisy = False
+    Factory.noisy = False
+    DNSDatagramProtocol.noisy = False
+except ImportError:
+    pass
+
+__version__ = "0.33.4"

synapse/api/auth.py

@@ -26,6 +26,7 @@ import synapse.types
 from synapse import event_auth
 from synapse.api.constants import EventTypes, JoinRules, Membership
 from synapse.api.errors import AuthError, Codes, ResourceLimitError
+from synapse.config.server import is_threepid_reserved
 from synapse.types import UserID
 from synapse.util.caches import CACHE_SIZE_FACTOR, register_cache
 from synapse.util.caches.lrucache import LruCache
@@ -775,13 +776,19 @@ class Auth(object):
             )
 
     @defer.inlineCallbacks
-    def check_auth_blocking(self, user_id=None):
+    def check_auth_blocking(self, user_id=None, threepid=None):
         """Checks if the user should be rejected for some external reason,
         such as monthly active user limiting or global disable flag
 
         Args:
             user_id(str|None): If present, checks for presence against existing
             MAU cohort
+
+            threepid(dict|None): If present, checks for presence against configured
+            reserved threepid. Used in cases where the user is trying register
+            with a MAU blocked server, normally they would be rejected but their
+            threepid is on the reserved list. user_id and
+            threepid should never be set at the same time.
         """
 
         # Never fail an auth check for the server notices users
@@ -797,6 +804,8 @@ class Auth(object):
                 limit_type=self.hs.config.hs_disabled_limit_type
             )
         if self.hs.config.limit_usage_by_mau is True:
+            assert not (user_id and threepid)
+
             # If the user is already part of the MAU cohort or a trial user
             if user_id:
                 timestamp = yield self.store.user_last_seen_monthly_active(user_id)
@@ -806,12 +815,16 @@ class Auth(object):
                 is_trial = yield self.store.is_trial_user(user_id)
                 if is_trial:
                     return
+            elif threepid:
+                # If the user does not exist yet, but is signing up with a
+                # reserved threepid then pass auth check
+                if is_threepid_reserved(self.hs.config, threepid):
+                    return
             # Else if there is no room in the MAU bucket, bail
             current_mau = yield self.store.get_monthly_active_count()
             if current_mau >= self.hs.config.max_mau_value:
                 raise ResourceLimitError(
                     403, "Monthly Active User Limit Exceeded",
-
                     admin_contact=self.hs.config.admin_contact,
                     errcode=Codes.RESOURCE_LIMIT_EXCEEDED,
                     limit_type="monthly_active_user"

synapse/api/filtering.py

@@ -251,6 +251,7 @@ class FilterCollection(object):
             "include_leave", False
         )
         self.event_fields = filter_json.get("event_fields", [])
+        self.event_format = filter_json.get("event_format", "client")
 
     def __repr__(self):
         return "<FilterCollection %s>" % (json.dumps(self._filter_json),)

synapse/app/appservice.py

@@ -51,10 +51,7 @@ class AppserviceSlaveStore(
 
 
 class AppserviceServer(HomeServer):
-    def setup(self):
-        logger.info("Setting up.")
-        self.datastore = AppserviceSlaveStore(self.get_db_conn(), self)
-        logger.info("Finished setting up.")
+    DATASTORE_CLASS = AppserviceSlaveStore
 
     def _listen_http(self, listener_config):
         port = listener_config["port"]

synapse/app/client_reader.py

@@ -74,10 +74,7 @@ class ClientReaderSlavedStore(
 
 
 class ClientReaderServer(HomeServer):
-    def setup(self):
-        logger.info("Setting up.")
-        self.datastore = ClientReaderSlavedStore(self.get_db_conn(), self)
-        logger.info("Finished setting up.")
+    DATASTORE_CLASS = ClientReaderSlavedStore
 
     def _listen_http(self, listener_config):
         port = listener_config["port"]

synapse/app/event_creator.py

@@ -90,10 +90,7 @@ class EventCreatorSlavedStore(
 
 
 class EventCreatorServer(HomeServer):
-    def setup(self):
-        logger.info("Setting up.")
-        self.datastore = EventCreatorSlavedStore(self.get_db_conn(), self)
-        logger.info("Finished setting up.")
+    DATASTORE_CLASS = EventCreatorSlavedStore
 
     def _listen_http(self, listener_config):
         port = listener_config["port"]

synapse/app/federation_reader.py

@@ -72,10 +72,7 @@ class FederationReaderSlavedStore(
 
 
 class FederationReaderServer(HomeServer):
-    def setup(self):
-        logger.info("Setting up.")
-        self.datastore = FederationReaderSlavedStore(self.get_db_conn(), self)
-        logger.info("Finished setting up.")
+    DATASTORE_CLASS = FederationReaderSlavedStore
 
     def _listen_http(self, listener_config):
         port = listener_config["port"]

synapse/app/federation_sender.py

@@ -78,10 +78,7 @@ class FederationSenderSlaveStore(
 
 
 class FederationSenderServer(HomeServer):
-    def setup(self):
-        logger.info("Setting up.")
-        self.datastore = FederationSenderSlaveStore(self.get_db_conn(), self)
-        logger.info("Finished setting up.")
+    DATASTORE_CLASS = FederationSenderSlaveStore
 
     def _listen_http(self, listener_config):
         port = listener_config["port"]

synapse/app/frontend_proxy.py

@@ -148,10 +148,7 @@ class FrontendProxySlavedStore(
 
 
 class FrontendProxyServer(HomeServer):
-    def setup(self):
-        logger.info("Setting up.")
-        self.datastore = FrontendProxySlavedStore(self.get_db_conn(), self)
-        logger.info("Finished setting up.")
+    DATASTORE_CLASS = FrontendProxySlavedStore
 
     def _listen_http(self, listener_config):
         port = listener_config["port"]

synapse/app/homeserver.py

@@ -62,7 +62,7 @@ from synapse.rest.key.v1.server_key_resource import LocalKey
 from synapse.rest.key.v2 import KeyApiV2Resource
 from synapse.rest.media.v0.content_repository import ContentRepoResource
 from synapse.server import HomeServer
-from synapse.storage import are_all_users_on_domain
+from synapse.storage import DataStore, are_all_users_on_domain
 from synapse.storage.engines import IncorrectDatabaseSetup, create_engine
 from synapse.storage.prepare_database import UpgradeDatabaseException, prepare_database
 from synapse.util.caches import CACHE_SIZE_FACTOR
@@ -111,6 +111,8 @@ def build_resource_for_web_client(hs):
 
 
 class SynapseHomeServer(HomeServer):
+    DATASTORE_CLASS = DataStore
+
     def _listener_http(self, config, listener_config):
         port = listener_config["port"]
         bind_addresses = listener_config["bind_addresses"]
@@ -305,6 +307,10 @@ class SynapseHomeServer(HomeServer):
 # Gauges to expose monthly active user control metrics
 current_mau_gauge = Gauge("synapse_admin_mau:current", "Current MAU")
 max_mau_gauge = Gauge("synapse_admin_mau:max", "MAU Limit")
+registered_reserved_users_mau_gauge = Gauge(
+    "synapse_admin_mau:registered_reserved_users",
+    "Registered users with reserved threepids"
+)
 
 
 def setup(config_options):
@@ -356,13 +362,13 @@ def setup(config_options):
     logger.info("Preparing database: %s...", config.database_config['name'])
 
     try:
-        db_conn = hs.get_db_conn(run_new_connection=False)
-        prepare_database(db_conn, database_engine, config=config)
-        database_engine.on_new_connection(db_conn)
+        with hs.get_db_conn(run_new_connection=False) as db_conn:
+            prepare_database(db_conn, database_engine, config=config)
+            database_engine.on_new_connection(db_conn)
 
-        hs.run_startup_checks(db_conn, database_engine)
+            hs.run_startup_checks(db_conn, database_engine)
 
-        db_conn.commit()
+            db_conn.commit()
     except UpgradeDatabaseException:
         sys.stderr.write(
             "\nFailed to upgrade database.\n"
@@ -529,10 +535,14 @@ def run(hs):
 
     @defer.inlineCallbacks
     def generate_monthly_active_users():
-        count = 0
+        current_mau_count = 0
+        reserved_count = 0
+        store = hs.get_datastore()
         if hs.config.limit_usage_by_mau:
-            count = yield hs.get_datastore().get_monthly_active_count()
-        current_mau_gauge.set(float(count))
+            current_mau_count = yield store.get_monthly_active_count()
+            reserved_count = yield store.get_registered_reserved_users_count()
+        current_mau_gauge.set(float(current_mau_count))
+        registered_reserved_users_mau_gauge.set(float(reserved_count))
         max_mau_gauge.set(float(hs.config.max_mau_value))
 
     hs.get_datastore().initialise_reserved_users(

synapse/app/media_repository.py

@@ -60,10 +60,7 @@ class MediaRepositorySlavedStore(
 
 
 class MediaRepositoryServer(HomeServer):
-    def setup(self):
-        logger.info("Setting up.")
-        self.datastore = MediaRepositorySlavedStore(self.get_db_conn(), self)
-        logger.info("Finished setting up.")
+    DATASTORE_CLASS = MediaRepositorySlavedStore
 
     def _listen_http(self, listener_config):
         port = listener_config["port"]

synapse/app/pusher.py

@@ -78,10 +78,7 @@ class PusherSlaveStore(
 
 
 class PusherServer(HomeServer):
-    def setup(self):
-        logger.info("Setting up.")
-        self.datastore = PusherSlaveStore(self.get_db_conn(), self)
-        logger.info("Finished setting up.")
+    DATASTORE_CLASS = PusherSlaveStore
 
     def remove_pusher(self, app_id, push_key, user_id):
         self.get_tcp_replication().send_remove_pusher(app_id, push_key, user_id)

synapse/app/synchrotron.py

@@ -249,10 +249,7 @@ class SynchrotronApplicationService(object):
 
 
 class SynchrotronServer(HomeServer):
-    def setup(self):
-        logger.info("Setting up.")
-        self.datastore = SynchrotronSlavedStore(self.get_db_conn(), self)
-        logger.info("Finished setting up.")
+    DATASTORE_CLASS = SynchrotronSlavedStore
 
     def _listen_http(self, listener_config):
         port = listener_config["port"]

synapse/app/user_dir.py

@@ -94,10 +94,7 @@ class UserDirectorySlaveStore(
 
 
 class UserDirectoryServer(HomeServer):
-    def setup(self):
-        logger.info("Setting up.")
-        self.datastore = UserDirectorySlaveStore(self.get_db_conn(), self)
-        logger.info("Finished setting up.")
+    DATASTORE_CLASS = UserDirectorySlaveStore
 
     def _listen_http(self, listener_config):
         port = listener_config["port"]

synapse/appservice/api.py

@@ -13,7 +13,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 import logging
-import urllib
+
+from six.moves import urllib
 
 from prometheus_client import Counter
 
@@ -98,7 +99,7 @@ class ApplicationServiceApi(SimpleHttpClient):
     def query_user(self, service, user_id):
         if service.url is None:
             defer.returnValue(False)
-        uri = service.url + ("/users/%s" % urllib.quote(user_id))
+        uri = service.url + ("/users/%s" % urllib.parse.quote(user_id))
         response = None
         try:
             response = yield self.get_json(uri, {
@@ -119,7 +120,7 @@ class ApplicationServiceApi(SimpleHttpClient):
     def query_alias(self, service, alias):
         if service.url is None:
             defer.returnValue(False)
-        uri = service.url + ("/rooms/%s" % urllib.quote(alias))
+        uri = service.url + ("/rooms/%s" % urllib.parse.quote(alias))
         response = None
         try:
             response = yield self.get_json(uri, {
@@ -153,7 +154,7 @@ class ApplicationServiceApi(SimpleHttpClient):
             service.url,
             APP_SERVICE_PREFIX,
             kind,
-            urllib.quote(protocol)
+            urllib.parse.quote(protocol)
         )
         try:
             response = yield self.get_json(uri, fields)
@@ -188,7 +189,7 @@ class ApplicationServiceApi(SimpleHttpClient):
             uri = "%s%s/thirdparty/protocol/%s" % (
                 service.url,
                 APP_SERVICE_PREFIX,
-                urllib.quote(protocol)
+                urllib.parse.quote(protocol)
             )
             try:
                 info = yield self.get_json(uri, {})
@@ -228,7 +229,7 @@ class ApplicationServiceApi(SimpleHttpClient):
         txn_id = str(txn_id)
 
         uri = service.url + ("/transactions/%s" %
-                             urllib.quote(txn_id))
+                             urllib.parse.quote(txn_id))
         try:
             yield self.put_json(
                 uri=uri,

synapse/config/homeserver.py

@@ -21,7 +21,7 @@ from .consent_config import ConsentConfig
 from .database import DatabaseConfig
 from .emailconfig import EmailConfig
 from .groups import GroupsConfig
-from .jwt import JWTConfig
+from .jwt_config import JWTConfig
 from .key import KeyConfig
 from .logger import LoggingConfig
 from .metrics import MetricsConfig

synapse/config/logger.py

@@ -227,7 +227,22 @@ def setup_logging(config, use_worker_options=False):
     #
     # However this may not be too much of a problem if we are just writing to a file.
     observer = STDLibLogObserver()
+
+    def _log(event):
+
+        if "log_text" in event:
+            if event["log_text"].startswith("DNSDatagramProtocol starting on "):
+                return
+
+            if event["log_text"].startswith("(UDP Port "):
+                return
+
+            if event["log_text"].startswith("Timing out client"):
+                return
+
+        return observer(event)
+
     globalLogBeginner.beginLoggingTo(
-        [observer],
+        [_log],
         redirectStandardIO=not config.no_redirect_stdio,
     )

synapse/config/server.py

@@ -404,6 +404,23 @@ class ServerConfig(Config):
                                   " service on the given port.")
 
 
+def is_threepid_reserved(config, threepid):
+    """Check the threepid against the reserved threepid config
+    Args:
+        config(ServerConfig) - to access server config attributes
+        threepid(dict) - The threepid to test for
+
+    Returns:
+        boolean Is the threepid undertest reserved_user
+    """
+
+    for tp in config.mau_limits_reserved_threepids:
+        if (threepid['medium'] == tp['medium']
+                and threepid['address'] == tp['address']):
+            return True
+    return False
+
+
 def read_gc_thresholds(thresholds):
     """Reads the three integer thresholds for garbage collection. Ensures that
     the thresholds are integers if thresholds are supplied.

synapse/crypto/context_factory.py

@@ -123,6 +123,6 @@ class ClientTLSOptionsFactory(object):
 
     def get_options(self, host):
         return ClientTLSOptions(
-            host.decode('utf-8'),
+            host,
             CertificateOptions(verify=False).getContext()
         )

synapse/crypto/keyclient.py

@@ -50,7 +50,7 @@ def fetch_server_key(server_name, tls_client_options_factory, path=KEY_API_V1):
                 defer.returnValue((server_response, server_certificate))
         except SynapseKeyClientError as e:
             logger.warn("Error getting key for %r: %s", server_name, e)
-            if e.status.startswith("4"):
+            if e.status.startswith(b"4"):
                 # Don't retry for 4xx responses.
                 raise IOError("Cannot get key for %r" % server_name)
         except (ConnectError, DomainError) as e:
@@ -82,6 +82,12 @@ class SynapseKeyClientProtocol(HTTPClient):
         self._peer = self.transport.getPeer()
         logger.debug("Connected to %s", self._peer)
 
+        if not isinstance(self.path, bytes):
+            self.path = self.path.encode('ascii')
+
+        if not isinstance(self.host, bytes):
+            self.host = self.host.encode('ascii')
+
         self.sendCommand(b"GET", self.path)
         if self.host:
             self.sendHeader(b"Host", self.host)

synapse/crypto/keyring.py

@@ -16,9 +16,10 @@
 
 import hashlib
 import logging
-import urllib
 from collections import namedtuple
 
+from six.moves import urllib
+
 from signedjson.key import (
     decode_verify_key_bytes,
     encode_verify_key_base64,
@@ -40,6 +41,7 @@ from synapse.api.errors import Codes, SynapseError
 from synapse.crypto.keyclient import fetch_server_key
 from synapse.util import logcontext, unwrapFirstError
 from synapse.util.logcontext import (
+    LoggingContext,
     PreserveLoggingContext,
     preserve_fn,
     run_in_background,
@@ -216,23 +218,34 @@ class Keyring(object):
             servers have completed. Follows the synapse rules of logcontext
             preservation.
         """
+        loop_count = 1
         while True:
             wait_on = [
-                self.key_downloads[server_name]
+                (server_name, self.key_downloads[server_name])
                 for server_name in server_names
                 if server_name in self.key_downloads
             ]
-            if wait_on:
-                with PreserveLoggingContext():
-                    yield defer.DeferredList(wait_on)
-            else:
+            if not wait_on:
                 break
+            logger.info(
+                "Waiting for existing lookups for %s to complete [loop %i]",
+                [w[0] for w in wait_on], loop_count,
+            )
+            with PreserveLoggingContext():
+                yield defer.DeferredList((w[1] for w in wait_on))
+
+            loop_count += 1
+
+        ctx = LoggingContext.current_context()
 
         def rm(r, server_name_):
-            self.key_downloads.pop(server_name_, None)
+            with PreserveLoggingContext(ctx):
+                logger.debug("Releasing key lookup lock on %s", server_name_)
+                self.key_downloads.pop(server_name_, None)
             return r
 
         for server_name, deferred in server_to_deferred.items():
+            logger.debug("Got key lookup lock on %s", server_name)
             self.key_downloads[server_name] = deferred
             deferred.addBoth(rm, server_name)
 
@@ -432,7 +445,7 @@ class Keyring(object):
         # an incoming request.
         query_response = yield self.client.post_json(
             destination=perspective_name,
-            path=b"/_matrix/key/v2/query",
+            path="/_matrix/key/v2/query",
             data={
                 u"server_keys": {
                     server_name: {
@@ -513,8 +526,8 @@ class Keyring(object):
 
             (response, tls_certificate) = yield fetch_server_key(
                 server_name, self.hs.tls_client_options_factory,
-                path=(b"/_matrix/key/v2/server/%s" % (
-                    urllib.quote(requested_key_id),
+                path=("/_matrix/key/v2/server/%s" % (
+                    urllib.parse.quote(requested_key_id),
                 )).encode("ascii"),
             )
 

synapse/events/__init__.py

@@ -13,6 +13,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import six
+
 from synapse.util.caches import intern_dict
 from synapse.util.frozenutils import freeze
 
@@ -147,6 +149,9 @@ class EventBase(object):
     def items(self):
         return list(self._event_dict.items())
 
+    def keys(self):
+        return six.iterkeys(self._event_dict)
+
 
 class FrozenEvent(EventBase):
     def __init__(self, event_dict, internal_metadata_dict={}, rejected_reason=None):

synapse/federation/federation_base.py

@@ -13,17 +13,20 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 import logging
+from collections import namedtuple
 
 import six
 
 from twisted.internet import defer
+from twisted.internet.defer import DeferredList
 
-from synapse.api.constants import MAX_DEPTH
+from synapse.api.constants import MAX_DEPTH, EventTypes, Membership
 from synapse.api.errors import Codes, SynapseError
 from synapse.crypto.event_signing import check_event_content_hash
 from synapse.events import FrozenEvent
 from synapse.events.utils import prune_event
 from synapse.http.servlet import assert_params_in_dict
+from synapse.types import get_domain_from_id
 from synapse.util import logcontext, unwrapFirstError
 
 logger = logging.getLogger(__name__)
@@ -133,34 +136,45 @@ class FederationBase(object):
               * throws a SynapseError if the signature check failed.
             The deferreds run their callbacks in the sentinel logcontext.
         """
-
-        redacted_pdus = [
-            prune_event(pdu)
-            for pdu in pdus
-        ]
-
-        deferreds = self.keyring.verify_json_objects_for_server([
-            (p.origin, p.get_pdu_json())
-            for p in redacted_pdus
-        ])
+        deferreds = _check_sigs_on_pdus(self.keyring, pdus)
 
         ctx = logcontext.LoggingContext.current_context()
 
-        def callback(_, pdu, redacted):
+        def callback(_, pdu):
             with logcontext.PreserveLoggingContext(ctx):
                 if not check_event_content_hash(pdu):
-                    logger.warn(
-                        "Event content has been tampered, redacting %s: %s",
-                        pdu.event_id, pdu.get_pdu_json()
-                    )
-                    return redacted
+                    # let's try to distinguish between failures because the event was
+                    # redacted (which are somewhat expected) vs actual ball-tampering
+                    # incidents.
+                    #
+                    # This is just a heuristic, so we just assume that if the keys are
+                    # about the same between the redacted and received events, then the
+                    # received event was probably a redacted copy (but we then use our
+                    # *actual* redacted copy to be on the safe side.)
+                    redacted_event = prune_event(pdu)
+                    if (
+                        set(redacted_event.keys()) == set(pdu.keys()) and
+                        set(six.iterkeys(redacted_event.content))
+                            == set(six.iterkeys(pdu.content))
+                    ):
+                        logger.info(
+                            "Event %s seems to have been redacted; using our redacted "
+                            "copy",
+                            pdu.event_id,
+                        )
+                    else:
+                        logger.warning(
+                            "Event %s content has been tampered, redacting",
+                            pdu.event_id, pdu.get_pdu_json(),
+                        )
+                    return redacted_event
 
                 if self.spam_checker.check_event_for_spam(pdu):
                     logger.warn(
                         "Event contains spam, redacting %s: %s",
                         pdu.event_id, pdu.get_pdu_json()
                     )
-                    return redacted
+                    return prune_event(pdu)
 
                 return pdu
 
@@ -168,21 +182,121 @@ class FederationBase(object):
             failure.trap(SynapseError)
             with logcontext.PreserveLoggingContext(ctx):
                 logger.warn(
-                    "Signature check failed for %s",
-                    pdu.event_id,
+                    "Signature check failed for %s: %s",
+                    pdu.event_id, failure.getErrorMessage(),
                 )
             return failure
 
-        for deferred, pdu, redacted in zip(deferreds, pdus, redacted_pdus):
+        for deferred, pdu in zip(deferreds, pdus):
             deferred.addCallbacks(
                 callback, errback,
-                callbackArgs=[pdu, redacted],
+                callbackArgs=[pdu],
                 errbackArgs=[pdu],
             )
 
         return deferreds
 
 
+class PduToCheckSig(namedtuple("PduToCheckSig", [
+    "pdu", "redacted_pdu_json", "event_id_domain", "sender_domain", "deferreds",
+])):
+    pass
+
+
+def _check_sigs_on_pdus(keyring, pdus):
+    """Check that the given events are correctly signed
+
+    Args:
+        keyring (synapse.crypto.Keyring): keyring object to do the checks
+        pdus (Collection[EventBase]): the events to be checked
+
+    Returns:
+        List[Deferred]: a Deferred for each event in pdus, which will either succeed if
+           the signatures are valid, or fail (with a SynapseError) if not.
+    """
+
+    # (currently this is written assuming the v1 room structure; we'll probably want a
+    # separate function for checking v2 rooms)
+
+    # we want to check that the event is signed by:
+    #
+    # (a) the server which created the event_id
+    #
+    # (b) the sender's server.
+    #
+    #     - except in the case of invites created from a 3pid invite, which are exempt
+    #     from this check, because the sender has to match that of the original 3pid
+    #     invite, but the event may come from a different HS, for reasons that I don't
+    #     entirely grok (why do the senders have to match? and if they do, why doesn't the
+    #     joining server ask the inviting server to do the switcheroo with
+    #     exchange_third_party_invite?).
+    #
+    #     That's pretty awful, since redacting such an invite will render it invalid
+    #     (because it will then look like a regular invite without a valid signature),
+    #     and signatures are *supposed* to be valid whether or not an event has been
+    #     redacted. But this isn't the worst of the ways that 3pid invites are broken.
+    #
+    # let's start by getting the domain for each pdu, and flattening the event back
+    # to JSON.
+    pdus_to_check = [
+        PduToCheckSig(
+            pdu=p,
+            redacted_pdu_json=prune_event(p).get_pdu_json(),
+            event_id_domain=get_domain_from_id(p.event_id),
+            sender_domain=get_domain_from_id(p.sender),
+            deferreds=[],
+        )
+        for p in pdus
+    ]
+
+    # first make sure that the event is signed by the event_id's domain
+    deferreds = keyring.verify_json_objects_for_server([
+        (p.event_id_domain, p.redacted_pdu_json)
+        for p in pdus_to_check
+    ])
+
+    for p, d in zip(pdus_to_check, deferreds):
+        p.deferreds.append(d)
+
+    # now let's look for events where the sender's domain is different to the
+    # event id's domain (normally only the case for joins/leaves), and add additional
+    # checks.
+    pdus_to_check_sender = [
+        p for p in pdus_to_check
+        if p.sender_domain != p.event_id_domain and not _is_invite_via_3pid(p.pdu)
+    ]
+
+    more_deferreds = keyring.verify_json_objects_for_server([
+        (p.sender_domain, p.redacted_pdu_json)
+        for p in pdus_to_check_sender
+    ])
+
+    for p, d in zip(pdus_to_check_sender, more_deferreds):
+        p.deferreds.append(d)
+
+    # replace lists of deferreds with single Deferreds
+    return [_flatten_deferred_list(p.deferreds) for p in pdus_to_check]
+
+
+def _flatten_deferred_list(deferreds):
+    """Given a list of one or more deferreds, either return the single deferred, or
+    combine into a DeferredList.
+    """
+    if len(deferreds) > 1:
+        return DeferredList(deferreds, fireOnOneErrback=True, consumeErrors=True)
+    else:
+        assert len(deferreds) == 1
+        return deferreds[0]
+
+
+def _is_invite_via_3pid(event):
+    return (
+        event.type == EventTypes.Member
+        and event.membership == Membership.INVITE
+        and "third_party_invite" in event.content
+    )
+
+
 def event_from_pdu_json(pdu_json, outlier=False):
     """Construct a FrozenEvent from an event json received over federation
 

synapse/federation/federation_client.py

@@ -271,10 +271,10 @@ class FederationClient(FederationBase):
                     event_id, destination, e,
                 )
             except NotRetryingDestination as e:
-                logger.info(e.message)
+                logger.info(str(e))
                 continue
             except FederationDeniedError as e:
-                logger.info(e.message)
+                logger.info(str(e))
                 continue
             except Exception as e:
                 pdu_attempts[destination] = now
@@ -510,7 +510,7 @@ class FederationClient(FederationBase):
                 else:
                     logger.warn(
                         "Failed to %s via %s: %i %s",
-                        description, destination, e.code, e.message,
+                        description, destination, e.code, e.args[0],
                     )
             except Exception:
                 logger.warn(
@@ -875,7 +875,7 @@ class FederationClient(FederationBase):
             except Exception as e:
                 logger.exception(
                     "Failed to send_third_party_invite via %s: %s",
-                    destination, e.message
+                    destination, str(e)
                 )
 
         raise RuntimeError("Failed to send to any server.")

synapse/federation/federation_server.py

@@ -99,7 +99,7 @@ class FederationServer(FederationBase):
 
     @defer.inlineCallbacks
     @log_function
-    def on_incoming_transaction(self, transaction_data):
+    def on_incoming_transaction(self, origin, transaction_data):
         # keep this as early as possible to make the calculated origin ts as
         # accurate as possible.
         request_time = self._clock.time_msec()
@@ -108,34 +108,33 @@ class FederationServer(FederationBase):
 
         if not transaction.transaction_id:
             raise Exception("Transaction missing transaction_id")
-        if not transaction.origin:
-            raise Exception("Transaction missing origin")
 
         logger.debug("[%s] Got transaction", transaction.transaction_id)
 
         # use a linearizer to ensure that we don't process the same transaction
         # multiple times in parallel.
         with (yield self._transaction_linearizer.queue(
-                (transaction.origin, transaction.transaction_id),
+                (origin, transaction.transaction_id),
         )):
             result = yield self._handle_incoming_transaction(
-                transaction, request_time,
+                origin, transaction, request_time,
             )
 
         defer.returnValue(result)
 
     @defer.inlineCallbacks
-    def _handle_incoming_transaction(self, transaction, request_time):
+    def _handle_incoming_transaction(self, origin, transaction, request_time):
         """ Process an incoming transaction and return the HTTP response
 
         Args:
+            origin (unicode): the server making the request
             transaction (Transaction): incoming transaction
             request_time (int): timestamp that the HTTP request arrived at
 
         Returns:
             Deferred[(int, object)]: http response code and body
         """
-        response = yield self.transaction_actions.have_responded(transaction)
+        response = yield self.transaction_actions.have_responded(origin, transaction)
 
         if response:
             logger.debug(
@@ -149,7 +148,7 @@ class FederationServer(FederationBase):
 
         received_pdus_counter.inc(len(transaction.pdus))
 
-        origin_host, _ = parse_server_name(transaction.origin)
+        origin_host, _ = parse_server_name(origin)
 
         pdus_by_room = {}
 
@@ -190,7 +189,7 @@ class FederationServer(FederationBase):
                 event_id = pdu.event_id
                 try:
                     yield self._handle_received_pdu(
-                        transaction.origin, pdu
+                        origin, pdu
                     )
                     pdu_results[event_id] = {}
                 except FederationError as e:
@@ -212,7 +211,7 @@ class FederationServer(FederationBase):
         if hasattr(transaction, "edus"):
             for edu in (Edu(**x) for x in transaction.edus):
                 yield self.received_edu(
-                    transaction.origin,
+                    origin,
                     edu.edu_type,
                     edu.content
                 )
@@ -224,6 +223,7 @@ class FederationServer(FederationBase):
         logger.debug("Returning: %s", str(response))
 
         yield self.transaction_actions.set_response(
+            origin,
             transaction,
             200, response
         )
@@ -838,9 +838,9 @@ class ReplicationFederationHandlerRegistry(FederationHandlerRegistry):
             )
 
         return self._send_edu(
-                edu_type=edu_type,
-                origin=origin,
-                content=content,
+            edu_type=edu_type,
+            origin=origin,
+            content=content,
         )
 
     def on_query(self, query_type, args):
@@ -851,6 +851,6 @@ class ReplicationFederationHandlerRegistry(FederationHandlerRegistry):
             return handler(args)
 
         return self._get_query_client(
-                query_type=query_type,
-                args=args,
+            query_type=query_type,
+            args=args,
         )

synapse/federation/persistence.py

@@ -36,7 +36,7 @@ class TransactionActions(object):
         self.store = datastore
 
     @log_function
-    def have_responded(self, transaction):
+    def have_responded(self, origin, transaction):
         """ Have we already responded to a transaction with the same id and
         origin?
 
@@ -50,11 +50,11 @@ class TransactionActions(object):
                                "transaction_id")
 
         return self.store.get_received_txn_response(
-            transaction.transaction_id, transaction.origin
+            transaction.transaction_id, origin
         )
 
     @log_function
-    def set_response(self, transaction, code, response):
+    def set_response(self, origin, transaction, code, response):
         """ Persist how we responded to a transaction.
 
         Returns:
@@ -66,7 +66,7 @@ class TransactionActions(object):
 
         return self.store.set_received_txn_response(
             transaction.transaction_id,
-            transaction.origin,
+            origin,
             code,
             response,
         )

synapse/federation/send_queue.py

@@ -32,7 +32,7 @@ Events are replicated via a separate events stream.
 import logging
 from collections import namedtuple
 
-from six import iteritems, itervalues
+from six import iteritems
 
 from sortedcontainers import SortedDict
 
@@ -117,7 +117,7 @@ class FederationRemoteSendQueue(object):
 
             user_ids = set(
                 user_id
-                for uids in itervalues(self.presence_changed)
+                for uids in self.presence_changed.values()
                 for user_id in uids
             )
 

synapse/federation/transaction_queue.py

@@ -463,7 +463,19 @@ class TransactionQueue(object):
                 # pending_transactions flag.
 
                 pending_pdus = self.pending_pdus_by_dest.pop(destination, [])
+
+                # We can only include at most 50 PDUs per transactions
+                pending_pdus, leftover_pdus = pending_pdus[:50], pending_pdus[50:]
+                if leftover_pdus:
+                    self.pending_pdus_by_dest[destination] = leftover_pdus
+
                 pending_edus = self.pending_edus_by_dest.pop(destination, [])
+
+                # We can only include at most 100 EDUs per transactions
+                pending_edus, leftover_edus = pending_edus[:100], pending_edus[100:]
+                if leftover_edus:
+                    self.pending_edus_by_dest[destination] = leftover_edus
+
                 pending_presence = self.pending_presence_by_dest.pop(destination, {})
 
                 pending_edus.extend(

synapse/federation/transport/client.py

@@ -15,7 +15,8 @@
 # limitations under the License.
 
 import logging
-import urllib
+
+from six.moves import urllib
 
 from twisted.internet import defer
 
@@ -951,4 +952,4 @@ def _create_path(prefix, path, *args):
     Returns:
         str
     """
-    return prefix + path % tuple(urllib.quote(arg, "") for arg in args)
+    return prefix + path % tuple(urllib.parse.quote(arg, "") for arg in args)

synapse/federation/transport/server.py

@@ -90,8 +90,8 @@ class Authenticator(object):
     @defer.inlineCallbacks
     def authenticate_request(self, request, content):
         json_request = {
-            "method": request.method,
-            "uri": request.uri,
+            "method": request.method.decode('ascii'),
+            "uri": request.uri.decode('ascii'),
             "destination": self.server_name,
             "signatures": {},
         }
@@ -252,7 +252,7 @@ class BaseFederationServlet(object):
                     by the callback method. None if the request has already been handled.
             """
             content = None
-            if request.method in ["PUT", "POST"]:
+            if request.method in [b"PUT", b"POST"]:
                 # TODO: Handle other method types? other content types?
                 content = parse_json_object_from_request(request)
 
@@ -353,7 +353,7 @@ class FederationSendServlet(BaseFederationServlet):
 
         try:
             code, response = yield self.handler.on_incoming_transaction(
-                transaction_data
+                origin, transaction_data,
             )
         except Exception:
             logger.exception("on_incoming_transaction failed")
@@ -386,7 +386,7 @@ class FederationStateServlet(BaseFederationServlet):
         return self.handler.on_context_state_request(
             origin,
             context,
-            query.get("event_id", [None])[0],
+            parse_string_from_args(query, "event_id", None),
         )
 
 
@@ -397,7 +397,7 @@ class FederationStateIdsServlet(BaseFederationServlet):
         return self.handler.on_state_ids_request(
             origin,
             room_id,
-            query.get("event_id", [None])[0],
+            parse_string_from_args(query, "event_id", None),
         )
 
 
@@ -405,14 +405,12 @@ class FederationBackfillServlet(BaseFederationServlet):
     PATH = "/backfill/(?P<context>[^/]*)/"
 
     def on_GET(self, origin, content, query, context):
-        versions = query["v"]
-        limits = query["limit"]
+        versions = [x.decode('ascii') for x in query[b"v"]]
+        limit = parse_integer_from_args(query, "limit", None)
 
-        if not limits:
+        if not limit:
             return defer.succeed((400, {"error": "Did not include limit param"}))
 
-        limit = int(limits[-1])
-
         return self.handler.on_backfill_request(origin, context, versions, limit)
 
 
@@ -423,7 +421,7 @@ class FederationQueryServlet(BaseFederationServlet):
     def on_GET(self, origin, content, query, query_type):
         return self.handler.on_query_request(
             query_type,
-            {k: v[0].decode("utf-8") for k, v in query.items()}
+            {k.decode('utf8'): v[0].decode("utf-8") for k, v in query.items()}
         )
 
 
@@ -630,14 +628,14 @@ class OpenIdUserInfo(BaseFederationServlet):
 
     @defer.inlineCallbacks
     def on_GET(self, origin, content, query):
-        token = query.get("access_token", [None])[0]
+        token = query.get(b"access_token", [None])[0]
         if token is None:
             defer.returnValue((401, {
                 "errcode": "M_MISSING_TOKEN", "error": "Access Token required"
             }))
             return
 
-        user_id = yield self.handler.on_openid_userinfo(token)
+        user_id = yield self.handler.on_openid_userinfo(token.decode('ascii'))
 
         if user_id is None:
             defer.returnValue((401, {

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(),

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),
     }
 
 

synapse/handlers/federation.py

@@ -594,7 +594,7 @@ 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 +802,7 @@ 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 +1358,7 @@ class FederationHandler(BaseHandler):
         )
 
         if state_groups:
-            _, state = state_groups.items().pop()
+            _, state = list(state_groups.items()).pop()
             results = state
 
             if event.is_state():
@@ -1831,7 +1831,7 @@ class FederationHandler(BaseHandler):
 
                 room_version = yield self.store.get_room_version(event.room_id)
 
-                new_state = self.state_handler.resolve_events(
+                new_state = yield self.state_handler.resolve_events(
                     room_version,
                     [list(local_view.values()), list(remote_view.values())],
                     event

synapse/handlers/register.py

@@ -125,6 +125,7 @@ class RegistrationHandler(BaseHandler):
         guest_access_token=None,
         make_guest=False,
         admin=False,
+        threepid=None,
     ):
         """Registers a new client on the server.
 
@@ -145,7 +146,7 @@ class RegistrationHandler(BaseHandler):
             RegistrationError if there was a problem registering.
         """
 
-        yield self.auth.check_auth_blocking()
+        yield self.auth.check_auth_blocking(threepid=threepid)
         password_hash = None
         if password:
             password_hash = yield self.auth_handler().hash(password)

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)

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)
 

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)
 
-        # FIXME: order by stream ordering, not alphabetic
+        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)
 
+        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,
@@ -729,25 +779,29 @@ 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.
+                        # 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
+                        # timeline here, and then dedupe any redundant ones below.
+
                         state_ids = yield self.store.get_state_ids_for_event(
                             batch.events[0].event_id, types=types,
-                            filtered_types=filtered_types,
+                            filtered_types=None,  # we only want members!
                         )
 
             if lazy_load_members and not include_redundant_members:
@@ -767,7 +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)
@@ -1568,6 +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({
@@ -1596,10 +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
             )
         ):
@@ -1629,6 +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,
@@ -1722,17 +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,
@@ -1746,7 +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
         )
 

synapse/http/client.py

@@ -13,24 +13,25 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 import logging
-import urllib
 
-from six import StringIO
+from six import text_type
+from six.moves import urllib
 
+import treq
 from canonicaljson import encode_canonical_json, json
 from prometheus_client import Counter
 
 from OpenSSL import SSL
 from OpenSSL.SSL import VERIFY_NONE
-from twisted.internet import defer, protocol, reactor, ssl, task
+from twisted.internet import defer, protocol, reactor, ssl
 from twisted.internet.endpoints import HostnameEndpoint, wrapClientTLS
 from twisted.web._newclient import ResponseDone
 from twisted.web.client import (
     Agent,
     BrowserLikeRedirectAgent,
     ContentDecoderAgent,
-    FileBodyProducer as TwistedFileBodyProducer,
     GzipDecoder,
     HTTPConnectionPool,
     PartialDownloadError,
@@ -83,18 +84,20 @@ class SimpleHttpClient(object):
         if hs.config.user_agent_suffix:
             self.user_agent = "%s %s" % (self.user_agent, hs.config.user_agent_suffix,)
 
+        self.user_agent = self.user_agent.encode('ascii')
+
     @defer.inlineCallbacks
-    def request(self, method, uri, *args, **kwargs):
+    def request(self, method, uri, data=b'', headers=None):
         # A small wrapper around self.agent.request() so we can easily attach
         # counters to it
         outgoing_requests_counter.labels(method).inc()
 
         # log request but strip `access_token` (AS requests for example include this)
-        logger.info("Sending request %s %s", method, redact_uri(uri))
+        logger.info("Sending request %s %s", method, redact_uri(uri.encode('ascii')))
 
         try:
-            request_deferred = self.agent.request(
-                method, uri, *args, **kwargs
+            request_deferred = treq.request(
+                method, uri, agent=self.agent, data=data, headers=headers
             )
             add_timeout_to_deferred(
                 request_deferred, 60, self.hs.get_reactor(),
@@ -105,14 +108,14 @@ class SimpleHttpClient(object):
             incoming_responses_counter.labels(method, response.code).inc()
             logger.info(
                 "Received response to  %s %s: %s",
-                method, redact_uri(uri), response.code
+                method, redact_uri(uri.encode('ascii')), response.code
             )
             defer.returnValue(response)
         except Exception as e:
             incoming_responses_counter.labels(method, "ERR").inc()
             logger.info(
                 "Error sending request to  %s %s: %s %s",
-                method, redact_uri(uri), type(e).__name__, e.message
+                method, redact_uri(uri.encode('ascii')), type(e).__name__, e.args[0]
             )
             raise
 
@@ -137,7 +140,8 @@ class SimpleHttpClient(object):
         # TODO: Do we ever want to log message contents?
         logger.debug("post_urlencoded_get_json args: %s", args)
 
-        query_bytes = urllib.urlencode(encode_urlencode_args(args), True)
+        query_bytes = urllib.parse.urlencode(
+            encode_urlencode_args(args), True).encode("utf8")
 
         actual_headers = {
             b"Content-Type": [b"application/x-www-form-urlencoded"],
@@ -148,15 +152,14 @@ class SimpleHttpClient(object):
 
         response = yield self.request(
             "POST",
-            uri.encode("ascii"),
+            uri,
             headers=Headers(actual_headers),
-            bodyProducer=FileBodyProducer(StringIO(query_bytes))
+            data=query_bytes
         )
 
-        body = yield make_deferred_yieldable(readBody(response))
-
         if 200 <= response.code < 300:
-            defer.returnValue(json.loads(body))
+            body = yield make_deferred_yieldable(treq.json_content(response))
+            defer.returnValue(body)
         else:
             raise HttpResponseException(response.code, response.phrase, body)
 
@@ -191,9 +194,9 @@ class SimpleHttpClient(object):
 
         response = yield self.request(
             "POST",
-            uri.encode("ascii"),
+            uri,
             headers=Headers(actual_headers),
-            bodyProducer=FileBodyProducer(StringIO(json_str))
+            data=json_str
         )
 
         body = yield make_deferred_yieldable(readBody(response))
@@ -248,7 +251,7 @@ class SimpleHttpClient(object):
             ValueError: if the response was not JSON
         """
         if len(args):
-            query_bytes = urllib.urlencode(args, True)
+            query_bytes = urllib.parse.urlencode(args, True)
             uri = "%s?%s" % (uri, query_bytes)
 
         json_str = encode_canonical_json(json_body)
@@ -262,9 +265,9 @@ class SimpleHttpClient(object):
 
         response = yield self.request(
             "PUT",
-            uri.encode("ascii"),
+            uri,
             headers=Headers(actual_headers),
-            bodyProducer=FileBodyProducer(StringIO(json_str))
+            data=json_str
         )
 
         body = yield make_deferred_yieldable(readBody(response))
@@ -293,7 +296,7 @@ class SimpleHttpClient(object):
             HttpResponseException on a non-2xx HTTP response.
         """
         if len(args):
-            query_bytes = urllib.urlencode(args, True)
+            query_bytes = urllib.parse.urlencode(args, True)
             uri = "%s?%s" % (uri, query_bytes)
 
         actual_headers = {
@@ -304,7 +307,7 @@ class SimpleHttpClient(object):
 
         response = yield self.request(
             "GET",
-            uri.encode("ascii"),
+            uri,
             headers=Headers(actual_headers),
         )
 
@@ -339,7 +342,7 @@ class SimpleHttpClient(object):
 
         response = yield self.request(
             "GET",
-            url.encode("ascii"),
+            url,
             headers=Headers(actual_headers),
         )
 
@@ -434,12 +437,12 @@ class CaptchaServerHttpClient(SimpleHttpClient):
 
     @defer.inlineCallbacks
     def post_urlencoded_get_raw(self, url, args={}):
-        query_bytes = urllib.urlencode(encode_urlencode_args(args), True)
+        query_bytes = urllib.parse.urlencode(encode_urlencode_args(args), True)
 
         response = yield self.request(
             "POST",
-            url.encode("ascii"),
-            bodyProducer=FileBodyProducer(StringIO(query_bytes)),
+            url,
+            data=query_bytes,
             headers=Headers({
                 b"Content-Type": [b"application/x-www-form-urlencoded"],
                 b"User-Agent": [self.user_agent],
@@ -510,7 +513,7 @@ def encode_urlencode_args(args):
 
 
 def encode_urlencode_arg(arg):
-    if isinstance(arg, unicode):
+    if isinstance(arg, text_type):
         return arg.encode('utf-8')
     elif isinstance(arg, list):
         return [encode_urlencode_arg(i) for i in arg]
@@ -542,26 +545,3 @@ class InsecureInterceptableContextFactory(ssl.ContextFactory):
 
     def creatorForNetloc(self, hostname, port):
         return self
-
-
-class FileBodyProducer(TwistedFileBodyProducer):
-    """Workaround for https://twistedmatrix.com/trac/ticket/8473
-
-    We override the pauseProducing and resumeProducing methods in twisted's
-    FileBodyProducer so that they do not raise exceptions if the task has
-    already completed.
-    """
-
-    def pauseProducing(self):
-        try:
-            super(FileBodyProducer, self).pauseProducing()
-        except task.TaskDone:
-            # task has already completed
-            pass
-
-    def resumeProducing(self):
-        try:
-            super(FileBodyProducer, self).resumeProducing()
-        except task.NotPaused:
-            # task was not paused (probably because it had already completed)
-            pass