Allow capping a room's retention policy (#8104)

3 files changed, 46 insertions, 71 deletions

diff --git a/synapse/config/server.py b/synapse/config/server.py
index ed66f3eba1..526a90b26a 100644
--- a/synapse/config/server.py
+++ b/synapse/config/server.py
@@ -961,11 +961,10 @@ class ServerConfig(Config):
           #  min_lifetime: 1d
           #  max_lifetime: 1y
 
-          # Retention policy limits. If set, a user won't be able to send a
-          # 'm.room.retention' event which features a 'min_lifetime' or a 'max_lifetime'
-          # that's not within this range. This is especially useful in closed federations,
-          # in which server admins can make sure every federating server applies the same
-          # rules.
+          # Retention policy limits. If set, and the state of a room contains a
+          # 'm.room.retention' event in its state which contains a 'min_lifetime' or a
+          # 'max_lifetime' that's out of these bounds, Synapse will cap the room's policy
+          # to these limits when running purge jobs.
           #
           #allowed_lifetime_min: 1d
           #allowed_lifetime_max: 1y
@@ -991,12 +990,19 @@ class ServerConfig(Config):
           # (e.g. every 12h), but not want that purge to be performed by a job that's
           # iterating over every room it knows, which could be heavy on the server.
           #
+          # If any purge job is configured, it is strongly recommended to have at least
+          # a single job with neither 'shortest_max_lifetime' nor 'longest_max_lifetime'
+          # set, or one job without 'shortest_max_lifetime' and one job without
+          # 'longest_max_lifetime' set. Otherwise some rooms might be ignored, even if
+          # 'allowed_lifetime_min' and 'allowed_lifetime_max' are set, because capping a
+          # room's policy to these values is done after the policies are retrieved from
+          # Synapse's database (which is done using the range specified in a purge job's
+          # configuration).
+          #
           #purge_jobs:
-          #  - shortest_max_lifetime: 1d
-          #    longest_max_lifetime: 3d
+          #  - longest_max_lifetime: 3d
           #    interval: 12h
           #  - shortest_max_lifetime: 3d
-          #    longest_max_lifetime: 1y
           #    interval: 1d
 
         # Inhibits the /requestToken endpoints from returning an error that might leak
diff --git a/synapse/events/validator.py b/synapse/events/validator.py
index 588d222f36..5ce3874fba 100644
--- a/synapse/events/validator.py
+++ b/synapse/events/validator.py
@@ -74,15 +74,14 @@ class EventValidator(object):
                         )
 
         if event.type == EventTypes.Retention:
-            self._validate_retention(event, config)
+            self._validate_retention(event)
 
-    def _validate_retention(self, event, config):
+    def _validate_retention(self, event):
         """Checks that an event that defines the retention policy for a room respects the
-        boundaries imposed by the server's administrator.
+        format enforced by the spec.
 
         Args:
             event (FrozenEvent): The event to validate.
-            config (Config): The homeserver's configuration.
         """
         min_lifetime = event.content.get("min_lifetime")
         max_lifetime = event.content.get("max_lifetime")
@@ -95,32 +94,6 @@ class EventValidator(object):
                     errcode=Codes.BAD_JSON,
                 )
 
-            if (
-                config.retention_allowed_lifetime_min is not None
-                and min_lifetime < config.retention_allowed_lifetime_min
-            ):
-                raise SynapseError(
-                    code=400,
-                    msg=(
-                        "'min_lifetime' can't be lower than the minimum allowed"
-                        " value enforced by the server's administrator"
-                    ),
-                    errcode=Codes.BAD_JSON,
-                )
-
-            if (
-                config.retention_allowed_lifetime_max is not None
-                and min_lifetime > config.retention_allowed_lifetime_max
-            ):
-                raise SynapseError(
-                    code=400,
-                    msg=(
-                        "'min_lifetime' can't be greater than the maximum allowed"
-                        " value enforced by the server's administrator"
-                    ),
-                    errcode=Codes.BAD_JSON,
-                )
-
         if max_lifetime is not None:
             if not isinstance(max_lifetime, int):
                 raise SynapseError(
@@ -129,32 +102,6 @@ class EventValidator(object):
                     errcode=Codes.BAD_JSON,
                 )
 
-            if (
-                config.retention_allowed_lifetime_min is not None
-                and max_lifetime < config.retention_allowed_lifetime_min
-            ):
-                raise SynapseError(
-                    code=400,
-                    msg=(
-                        "'max_lifetime' can't be lower than the minimum allowed value"
-                        " enforced by the server's administrator"
-                    ),
-                    errcode=Codes.BAD_JSON,
-                )
-
-            if (
-                config.retention_allowed_lifetime_max is not None
-                and max_lifetime > config.retention_allowed_lifetime_max
-            ):
-                raise SynapseError(
-                    code=400,
-                    msg=(
-                        "'max_lifetime' can't be greater than the maximum allowed"
-                        " value enforced by the server's administrator"
-                    ),
-                    errcode=Codes.BAD_JSON,
-                )
-
         if (
             min_lifetime is not None
             and max_lifetime is not None
diff --git a/synapse/handlers/pagination.py b/synapse/handlers/pagination.py
index 487420bb5d..ac3418d69d 100644
--- a/synapse/handlers/pagination.py
+++ b/synapse/handlers/pagination.py
@@ -82,6 +82,9 @@ class PaginationHandler(object):
 
         self._retention_default_max_lifetime = hs.config.retention_default_max_lifetime
 
+        self._retention_allowed_lifetime_min = hs.config.retention_allowed_lifetime_min
+        self._retention_allowed_lifetime_max = hs.config.retention_allowed_lifetime_max
+
         if hs.config.retention_enabled:
             # Run the purge jobs described in the configuration file.
             for job in hs.config.retention_purge_jobs:
@@ -111,7 +114,7 @@ class PaginationHandler(object):
                 the range to handle (inclusive). If None, it means that the range has no
                 upper limit.
         """
-        # We want the storage layer to to include rooms with no retention policy in its
+        # We want the storage layer to include rooms with no retention policy in its
         # return value only if a default retention policy is defined in the server's
         # configuration and that policy's 'max_lifetime' is either lower (or equal) than
         # max_ms or higher than min_ms (or both).
@@ -152,13 +155,32 @@ class PaginationHandler(object):
                 )
                 continue
 
-            max_lifetime = retention_policy["max_lifetime"]
+            # If max_lifetime is None, it means that the room has no retention policy.
+            # Given we only retrieve such rooms when there's a default retention policy
+            # defined in the server's configuration, we can safely assume that's the
+            # case and use it for this room.
+            max_lifetime = (
+                retention_policy["max_lifetime"] or self._retention_default_max_lifetime
+            )
 
-            if max_lifetime is None:
-                # If max_lifetime is None, it means that include_null equals True,
-                # therefore we can safely assume that there is a default policy defined
-                # in the server's configuration.
-                max_lifetime = self._retention_default_max_lifetime
+            # Cap the effective max_lifetime to be within the range allowed in the
+            # config.
+            # We do this in two steps:
+            #   1. Make sure it's higher or equal to the minimum allowed value, and if
+            #      it's not replace it with that value. This is because the server
+            #      operator can be required to not delete information before a given
+            #      time, e.g. to comply with freedom of information laws.
+            #   2. Make sure the resulting value is lower or equal to the maximum allowed
+            #      value, and if it's not replace it with that value. This is because the
+            #      server operator can be required to delete any data after a specific
+            #      amount of time.
+            if self._retention_allowed_lifetime_min is not None:
+                max_lifetime = max(self._retention_allowed_lifetime_min, max_lifetime)
+
+            if self._retention_allowed_lifetime_max is not None:
+                max_lifetime = min(max_lifetime, self._retention_allowed_lifetime_max)
+
+            logger.debug("[purge] max_lifetime for room %s: %s", room_id, max_lifetime)
 
             # Figure out what token we should start purging at.
             ts = self.clock.time_msec() - max_lifetime