Fix IP URL previews on Python 3 (#4215)

synapse/http/client.py

@@ -21,28 +21,25 @@ from six.moves import urllib
 
 import treq
 from canonicaljson import encode_canonical_json, json
+from netaddr import IPAddress
 from prometheus_client import Counter
+from zope.interface import implementer, provider
 
 from OpenSSL import SSL
 from OpenSSL.SSL import VERIFY_NONE
-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,
-    GzipDecoder,
-    HTTPConnectionPool,
-    PartialDownloadError,
-    readBody,
+from twisted.internet import defer, protocol, ssl
+from twisted.internet.interfaces import (
+    IReactorPluggableNameResolver,
+    IResolutionReceiver,
 )
+from twisted.python.failure import Failure
+from twisted.web._newclient import ResponseDone
+from twisted.web.client import Agent, HTTPConnectionPool, PartialDownloadError, readBody
 from twisted.web.http import PotentialDataLoss
 from twisted.web.http_headers import Headers
 
 from synapse.api.errors import Codes, HttpResponseException, SynapseError
 from synapse.http import cancelled_to_request_timed_out_error, redact_uri
-from synapse.http.endpoint import SpiderEndpoint
 from synapse.util.async_helpers import timeout_deferred
 from synapse.util.caches import CACHE_SIZE_FACTOR
 from synapse.util.logcontext import make_deferred_yieldable
@@ -50,8 +47,125 @@ from synapse.util.logcontext import make_deferred_yieldable
 logger = logging.getLogger(__name__)
 
 outgoing_requests_counter = Counter("synapse_http_client_requests", "", ["method"])
-incoming_responses_counter = Counter("synapse_http_client_responses", "",
-                                     ["method", "code"])
+incoming_responses_counter = Counter(
+    "synapse_http_client_responses", "", ["method", "code"]
+)
+
+
+def check_against_blacklist(ip_address, ip_whitelist, ip_blacklist):
+    """
+    Args:
+        ip_address (netaddr.IPAddress)
+        ip_whitelist (netaddr.IPSet)
+        ip_blacklist (netaddr.IPSet)
+    """
+    if ip_address in ip_blacklist:
+        if ip_whitelist is None or ip_address not in ip_whitelist:
+            return True
+    return False
+
+
+class IPBlacklistingResolver(object):
+    """
+    A proxy for reactor.nameResolver which only produces non-blacklisted IP
+    addresses, preventing DNS rebinding attacks on URL preview.
+    """
+
+    def __init__(self, reactor, ip_whitelist, ip_blacklist):
+        """
+        Args:
+            reactor (twisted.internet.reactor)
+            ip_whitelist (netaddr.IPSet)
+            ip_blacklist (netaddr.IPSet)
+        """
+        self._reactor = reactor
+        self._ip_whitelist = ip_whitelist
+        self._ip_blacklist = ip_blacklist
+
+    def resolveHostName(self, recv, hostname, portNumber=0):
+
+        r = recv()
+        d = defer.Deferred()
+        addresses = []
+
+        @provider(IResolutionReceiver)
+        class EndpointReceiver(object):
+            @staticmethod
+            def resolutionBegan(resolutionInProgress):
+                pass
+
+            @staticmethod
+            def addressResolved(address):
+                ip_address = IPAddress(address.host)
+
+                if check_against_blacklist(
+                    ip_address, self._ip_whitelist, self._ip_blacklist
+                ):
+                    logger.info(
+                        "Dropped %s from DNS resolution to %s" % (ip_address, hostname)
+                    )
+                    raise SynapseError(403, "IP address blocked by IP blacklist entry")
+
+                addresses.append(address)
+
+            @staticmethod
+            def resolutionComplete():
+                d.callback(addresses)
+
+        self._reactor.nameResolver.resolveHostName(
+            EndpointReceiver, hostname, portNumber=portNumber
+        )
+
+        def _callback(addrs):
+            r.resolutionBegan(None)
+            for i in addrs:
+                r.addressResolved(i)
+            r.resolutionComplete()
+
+        d.addCallback(_callback)
+
+        return r
+
+
+class BlacklistingAgentWrapper(Agent):
+    """
+    An Agent wrapper which will prevent access to IP addresses being accessed
+    directly (without an IP address lookup).
+    """
+
+    def __init__(self, agent, reactor, ip_whitelist=None, ip_blacklist=None):
+        """
+        Args:
+            agent (twisted.web.client.Agent): The Agent to wrap.
+            reactor (twisted.internet.reactor)
+            ip_whitelist (netaddr.IPSet)
+            ip_blacklist (netaddr.IPSet)
+        """
+        self._agent = agent
+        self._ip_whitelist = ip_whitelist
+        self._ip_blacklist = ip_blacklist
+
+    def request(self, method, uri, headers=None, bodyProducer=None):
+        h = urllib.parse.urlparse(uri.decode('ascii'))
+
+        try:
+            ip_address = IPAddress(h.hostname)
+
+            if check_against_blacklist(
+                ip_address, self._ip_whitelist, self._ip_blacklist
+            ):
+                logger.info(
+                    "Blocking access to %s because of blacklist" % (ip_address,)
+                )
+                e = SynapseError(403, "IP address blocked by IP blacklist entry")
+                return defer.fail(Failure(e))
+        except Exception:
+            # Not an IP
+            pass
+
+        return self._agent.request(
+            method, uri, headers=headers, bodyProducer=bodyProducer
+        )
 
 
 class SimpleHttpClient(object):
@@ -59,14 +173,54 @@ class SimpleHttpClient(object):
     A simple, no-frills HTTP client with methods that wrap up common ways of
     using HTTP in Matrix
     """
-    def __init__(self, hs):
+
+    def __init__(self, hs, treq_args={}, ip_whitelist=None, ip_blacklist=None):
+        """
+        Args:
+            hs (synapse.server.HomeServer)
+            treq_args (dict): Extra keyword arguments to be given to treq.request.
+            ip_blacklist (netaddr.IPSet): The IP addresses that are blacklisted that
+                we may not request.
+            ip_whitelist (netaddr.IPSet): The whitelisted IP addresses, that we can
+               request if it were otherwise caught in a blacklist.
+        """
         self.hs = hs
 
-        pool = HTTPConnectionPool(reactor)
+        self._ip_whitelist = ip_whitelist
+        self._ip_blacklist = ip_blacklist
+        self._extra_treq_args = treq_args
+
+        self.user_agent = hs.version_string
+        self.clock = hs.get_clock()
+        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')
+
+        if self._ip_blacklist:
+            real_reactor = hs.get_reactor()
+            # If we have an IP blacklist, we need to use a DNS resolver which
+            # filters out blacklisted IP addresses, to prevent DNS rebinding.
+            nameResolver = IPBlacklistingResolver(
+                real_reactor, self._ip_whitelist, self._ip_blacklist
+            )
+
+            @implementer(IReactorPluggableNameResolver)
+            class Reactor(object):
+                def __getattr__(_self, attr):
+                    if attr == "nameResolver":
+                        return nameResolver
+                    else:
+                        return getattr(real_reactor, attr)
+
+            self.reactor = Reactor()
+        else:
+            self.reactor = hs.get_reactor()
 
         # the pusher makes lots of concurrent SSL connections to sygnal, and
-        # tends to do so in batches, so we need to allow the pool to keep lots
-        # of idle connections around.
+        # tends to do so in batches, so we need to allow the pool to keep
+        # lots of idle connections around.
+        pool = HTTPConnectionPool(self.reactor)
         pool.maxPersistentPerHost = max((100 * CACHE_SIZE_FACTOR, 5))
         pool.cachedConnectionTimeout = 2 * 60
 
@@ -74,20 +228,35 @@ class SimpleHttpClient(object):
         # BrowserLikePolicyForHTTPS which will do regular cert validation
         # 'like a browser'
         self.agent = Agent(
-            reactor,
+            self.reactor,
             connectTimeout=15,
-            contextFactory=hs.get_http_client_context_factory(),
+            contextFactory=self.hs.get_http_client_context_factory(),
             pool=pool,
         )
-        self.user_agent = hs.version_string
-        self.clock = hs.get_clock()
-        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')
+        if self._ip_blacklist:
+            # If we have an IP blacklist, we then install the blacklisting Agent
+            # which prevents direct access to IP addresses, that are not caught
+            # by the DNS resolution.
+            self.agent = BlacklistingAgentWrapper(
+                self.agent,
+                self.reactor,
+                ip_whitelist=self._ip_whitelist,
+                ip_blacklist=self._ip_blacklist,
+            )
 
     @defer.inlineCallbacks
     def request(self, method, uri, data=b'', headers=None):
+        """
+        Args:
+            method (str): HTTP method to use.
+            uri (str): URI to query.
+            data (bytes): Data to send in the request body, if applicable.
+            headers (t.w.http_headers.Headers): Request headers.
+
+        Raises:
+            SynapseError: If the IP is blacklisted.
+        """
         # A small wrapper around self.agent.request() so we can easily attach
         # counters to it
         outgoing_requests_counter.labels(method).inc()
@@ -97,25 +266,34 @@ class SimpleHttpClient(object):
 
         try:
             request_deferred = treq.request(
-                method, uri, agent=self.agent, data=data, headers=headers
+                method,
+                uri,
+                agent=self.agent,
+                data=data,
+                headers=headers,
+                **self._extra_treq_args
             )
             request_deferred = timeout_deferred(
-                request_deferred, 60, self.hs.get_reactor(),
+                request_deferred,
+                60,
+                self.hs.get_reactor(),
                 cancelled_to_request_timed_out_error,
             )
             response = yield make_deferred_yieldable(request_deferred)
 
             incoming_responses_counter.labels(method, response.code).inc()
             logger.info(
-                "Received response to  %s %s: %s",
-                method, redact_uri(uri), response.code
+                "Received response to %s %s: %s", method, redact_uri(uri), 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.args[0]
+                method,
+                redact_uri(uri),
+                type(e).__name__,
+                e.args[0],
             )
             raise
 
@@ -140,8 +318,9 @@ class SimpleHttpClient(object):
         # TODO: Do we ever want to log message contents?
         logger.debug("post_urlencoded_get_json args: %s", args)
 
-        query_bytes = urllib.parse.urlencode(
-            encode_urlencode_args(args), True).encode("utf8")
+        query_bytes = urllib.parse.urlencode(encode_urlencode_args(args), True).encode(
+            "utf8"
+        )
 
         actual_headers = {
             b"Content-Type": [b"application/x-www-form-urlencoded"],
@@ -151,10 +330,7 @@ class SimpleHttpClient(object):
             actual_headers.update(headers)
 
         response = yield self.request(
-            "POST",
-            uri,
-            headers=Headers(actual_headers),
-            data=query_bytes
+            "POST", uri, headers=Headers(actual_headers), data=query_bytes
         )
 
         if 200 <= response.code < 300:
@@ -193,10 +369,7 @@ class SimpleHttpClient(object):
             actual_headers.update(headers)
 
         response = yield self.request(
-            "POST",
-            uri,
-            headers=Headers(actual_headers),
-            data=json_str
+            "POST", uri, headers=Headers(actual_headers), data=json_str
         )
 
         body = yield make_deferred_yieldable(readBody(response))
@@ -264,10 +437,7 @@ class SimpleHttpClient(object):
             actual_headers.update(headers)
 
         response = yield self.request(
-            "PUT",
-            uri,
-            headers=Headers(actual_headers),
-            data=json_str
+            "PUT", uri, headers=Headers(actual_headers), data=json_str
         )
 
         body = yield make_deferred_yieldable(readBody(response))
@@ -299,17 +469,11 @@ class SimpleHttpClient(object):
             query_bytes = urllib.parse.urlencode(args, True)
             uri = "%s?%s" % (uri, query_bytes)
 
-        actual_headers = {
-            b"User-Agent": [self.user_agent],
-        }
+        actual_headers = {b"User-Agent": [self.user_agent]}
         if headers:
             actual_headers.update(headers)
 
-        response = yield self.request(
-            "GET",
-            uri,
-            headers=Headers(actual_headers),
-        )
+        response = yield self.request("GET", uri, headers=Headers(actual_headers))
 
         body = yield make_deferred_yieldable(readBody(response))
 
@@ -334,22 +498,18 @@ class SimpleHttpClient(object):
             headers, absolute URI of the response and HTTP response code.
         """
 
-        actual_headers = {
-            b"User-Agent": [self.user_agent],
-        }
+        actual_headers = {b"User-Agent": [self.user_agent]}
         if headers:
             actual_headers.update(headers)
 
-        response = yield self.request(
-            "GET",
-            url,
-            headers=Headers(actual_headers),
-        )
+        response = yield self.request("GET", url, headers=Headers(actual_headers))
 
         resp_headers = dict(response.headers.getAllRawHeaders())
 
-        if (b'Content-Length' in resp_headers and
-                int(resp_headers[b'Content-Length']) > max_size):
+        if (
+            b'Content-Length' in resp_headers
+            and int(resp_headers[b'Content-Length'][0]) > max_size
+        ):
             logger.warn("Requested URL is too large > %r bytes" % (self.max_size,))
             raise SynapseError(
                 502,
@@ -359,26 +519,20 @@ class SimpleHttpClient(object):
 
         if response.code > 299:
             logger.warn("Got %d when downloading %s" % (response.code, url))
-            raise SynapseError(
-                502,
-                "Got error %d" % (response.code,),
-                Codes.UNKNOWN,
-            )
+            raise SynapseError(502, "Got error %d" % (response.code,), Codes.UNKNOWN)
 
         # TODO: if our Content-Type is HTML or something, just read the first
         # N bytes into RAM rather than saving it all to disk only to read it
         # straight back in again
 
         try:
-            length = yield make_deferred_yieldable(_readBodyToFile(
-                response, output_stream, max_size,
-            ))
+            length = yield make_deferred_yieldable(
+                _readBodyToFile(response, output_stream, max_size)
+            )
         except Exception as e:
             logger.exception("Failed to download body")
             raise SynapseError(
-                502,
-                ("Failed to download remote body: %s" % e),
-                Codes.UNKNOWN,
+                502, ("Failed to download remote body: %s" % e), Codes.UNKNOWN
             )
 
         defer.returnValue(
@@ -387,13 +541,14 @@ class SimpleHttpClient(object):
                 resp_headers,
                 response.request.absoluteURI.decode('ascii'),
                 response.code,
-            ),
+            )
         )
 
 
 # XXX: FIXME: This is horribly copy-pasted from matrixfederationclient.
 # The two should be factored out.
 
+
 class _ReadBodyToFileProtocol(protocol.Protocol):
     def __init__(self, stream, deferred, max_size):
         self.stream = stream
@@ -405,11 +560,13 @@ class _ReadBodyToFileProtocol(protocol.Protocol):
         self.stream.write(data)
         self.length += len(data)
         if self.max_size is not None and self.length >= self.max_size:
-            self.deferred.errback(SynapseError(
-                502,
-                "Requested file is too large > %r bytes" % (self.max_size,),
-                Codes.TOO_LARGE,
-            ))
+            self.deferred.errback(
+                SynapseError(
+                    502,
+                    "Requested file is too large > %r bytes" % (self.max_size,),
+                    Codes.TOO_LARGE,
+                )
+            )
             self.deferred = defer.Deferred()
             self.transport.loseConnection()
 
@@ -427,6 +584,7 @@ class _ReadBodyToFileProtocol(protocol.Protocol):
 # XXX: FIXME: This is horribly copy-pasted from matrixfederationclient.
 # The two should be factored out.
 
+
 def _readBodyToFile(response, stream, max_size):
     d = defer.Deferred()
     response.deliverBody(_ReadBodyToFileProtocol(stream, d, max_size))
@@ -449,10 +607,12 @@ class CaptchaServerHttpClient(SimpleHttpClient):
             "POST",
             url,
             data=query_bytes,
-            headers=Headers({
-                b"Content-Type": [b"application/x-www-form-urlencoded"],
-                b"User-Agent": [self.user_agent],
-            })
+            headers=Headers(
+                {
+                    b"Content-Type": [b"application/x-www-form-urlencoded"],
+                    b"User-Agent": [self.user_agent],
+                }
+            ),
         )
 
         try:
@@ -463,57 +623,6 @@ class CaptchaServerHttpClient(SimpleHttpClient):
             defer.returnValue(e.response)
 
 
-class SpiderEndpointFactory(object):
-    def __init__(self, hs):
-        self.blacklist = hs.config.url_preview_ip_range_blacklist
-        self.whitelist = hs.config.url_preview_ip_range_whitelist
-        self.policyForHTTPS = hs.get_http_client_context_factory()
-
-    def endpointForURI(self, uri):
-        logger.info("Getting endpoint for %s", uri.toBytes())
-
-        if uri.scheme == b"http":
-            endpoint_factory = HostnameEndpoint
-        elif uri.scheme == b"https":
-            tlsCreator = self.policyForHTTPS.creatorForNetloc(uri.host, uri.port)
-
-            def endpoint_factory(reactor, host, port, **kw):
-                return wrapClientTLS(
-                    tlsCreator,
-                    HostnameEndpoint(reactor, host, port, **kw))
-        else:
-            logger.warn("Can't get endpoint for unrecognised scheme %s", uri.scheme)
-            return None
-        return SpiderEndpoint(
-            reactor, uri.host, uri.port, self.blacklist, self.whitelist,
-            endpoint=endpoint_factory, endpoint_kw_args=dict(timeout=15),
-        )
-
-
-class SpiderHttpClient(SimpleHttpClient):
-    """
-    Separate HTTP client for spidering arbitrary URLs.
-    Special in that it follows retries and has a UA that looks
-    like a browser.
-
-    used by the preview_url endpoint in the content repo.
-    """
-    def __init__(self, hs):
-        SimpleHttpClient.__init__(self, hs)
-        # clobber the base class's agent and UA:
-        self.agent = ContentDecoderAgent(
-            BrowserLikeRedirectAgent(
-                Agent.usingEndpointFactory(
-                    reactor,
-                    SpiderEndpointFactory(hs)
-                )
-            ), [(b'gzip', GzipDecoder)]
-        )
-        # We could look like Chrome:
-        # self.user_agent = ("Mozilla/5.0 (%s) (KHTML, like Gecko)
-        #                   Chrome Safari" % hs.version_string)
-
-
 def encode_urlencode_args(args):
     return {k: encode_urlencode_arg(v) for k, v in args.items()}