Merge pull request #1992 from matrix-org/rav/fix_media_loop

Fix routing loop when fetching remote media

2 files changed, 46 insertions, 10 deletions

diff --git a/synapse/rest/media/v1/download_resource.py b/synapse/rest/media/v1/download_resource.py
index dfb87ffd15..6788375e85 100644
--- a/synapse/rest/media/v1/download_resource.py
+++ b/synapse/rest/media/v1/download_resource.py
@@ -12,6 +12,7 @@
 # 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 synapse.http.servlet
 
 from ._base import parse_media_id, respond_with_file, respond_404
 from twisted.web.resource import Resource
@@ -81,6 +82,17 @@ class DownloadResource(Resource):
 
     @defer.inlineCallbacks
     def _respond_remote_file(self, request, server_name, media_id, name):
+        # don't forward requests for remote media if allow_remote is false
+        allow_remote = synapse.http.servlet.parse_boolean(
+            request, "allow_remote", default=True)
+        if not allow_remote:
+            logger.info(
+                "Rejecting request for remote media %s/%s due to allow_remote",
+                server_name, media_id,
+            )
+            respond_404(request)
+            return
+
         media_info = yield self.media_repo.get_remote_media(server_name, media_id)
 
         media_type = media_info["media_type"]
diff --git a/synapse/rest/media/v1/media_repository.py b/synapse/rest/media/v1/media_repository.py
index 481ffee200..c43b185e08 100644
--- a/synapse/rest/media/v1/media_repository.py
+++ b/synapse/rest/media/v1/media_repository.py
@@ -13,22 +13,23 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+from twisted.internet import defer, threads
+import twisted.internet.error
+import twisted.web.http
+from twisted.web.resource import Resource
+
 from .upload_resource import UploadResource
 from .download_resource import DownloadResource
 from .thumbnail_resource import ThumbnailResource
 from .identicon_resource import IdenticonResource
 from .preview_url_resource import PreviewUrlResource
 from .filepath import MediaFilePaths
-
-from twisted.web.resource import Resource
-
 from .thumbnailer import Thumbnailer
 
 from synapse.http.matrixfederationclient import MatrixFederationHttpClient
 from synapse.util.stringutils import random_string
-from synapse.api.errors import SynapseError
-
-from twisted.internet import defer, threads
+from synapse.api.errors import SynapseError, HttpResponseException, \
+    NotFoundError
 
 from synapse.util.async import Linearizer
 from synapse.util.stringutils import is_ascii
@@ -157,11 +158,34 @@ class MediaRepository(object):
                 try:
                     length, headers = yield self.client.get_file(
                         server_name, request_path, output_stream=f,
-                        max_size=self.max_upload_size,
+                        max_size=self.max_upload_size, args={
+                            # tell the remote server to 404 if it doesn't
+                            # recognise the server_name, to make sure we don't
+                            # end up with a routing loop.
+                            "allow_remote": "false",
+                        }
                     )
-                except Exception as e:
-                    logger.warn("Failed to fetch remoted media %r", e)
-                    raise SynapseError(502, "Failed to fetch remoted media")
+                except twisted.internet.error.DNSLookupError as e:
+                    logger.warn("HTTP error fetching remote media %s/%s: %r",
+                                server_name, media_id, e)
+                    raise NotFoundError()
+
+                except HttpResponseException as e:
+                    logger.warn("HTTP error fetching remote media %s/%s: %s",
+                                server_name, media_id, e.response)
+                    if e.code == twisted.web.http.NOT_FOUND:
+                        raise SynapseError.from_http_response_exception(e)
+                    raise SynapseError(502, "Failed to fetch remote media")
+
+                except SynapseError:
+                    logger.exception("Failed to fetch remote media %s/%s",
+                                     server_name, media_id)
+                    raise
+
+                except Exception:
+                    logger.exception("Failed to fetch remote media %s/%s",
+                                     server_name, media_id)
+                    raise SynapseError(502, "Failed to fetch remote media")
 
             media_type = headers["Content-Type"][0]
             time_now_ms = self.clock.time_msec()