core: add new RestrictNamespaces= unit file setting

This new setting permits restricting whether namespaces may be created and
managed by processes started by a unit. It installs a seccomp filter blocking
certain invocations of unshare(), clone() and setns().

RestrictNamespaces=no is the default, and does not restrict namespaces in any
way. RestrictNamespaces=yes takes away the ability to create or manage any kind
of namspace. "RestrictNamespaces=mnt ipc" restricts the creation of namespaces
so that only mount and IPC namespaces may be created/managed, but no other
kind of namespaces.

This setting should be improve security quite a bit as in particular user
namespacing was a major source of CVEs in the kernel in the past, and is
accessible to unprivileged processes. With this setting the entire attack
surface may be removed for system services that do not make use of namespaces.

1 files changed, 21 insertions, 0 deletions

diff --git a/src/core/dbus-execute.c b/src/core/dbus-execute.c
index 03f23780c1..d7bb0496a0 100644
--- a/src/core/dbus-execute.c
+++ b/src/core/dbus-execute.c
@@ -781,6 +781,7 @@ const sd_bus_vtable bus_exec_vtable[] = {
         SD_BUS_PROPERTY("RuntimeDirectory", "as", NULL, offsetof(ExecContext, runtime_directory), SD_BUS_VTABLE_PROPERTY_CONST),
         SD_BUS_PROPERTY("MemoryDenyWriteExecute", "b", bus_property_get_bool, offsetof(ExecContext, memory_deny_write_execute), SD_BUS_VTABLE_PROPERTY_CONST),
         SD_BUS_PROPERTY("RestrictRealtime", "b", bus_property_get_bool, offsetof(ExecContext, restrict_realtime), SD_BUS_VTABLE_PROPERTY_CONST),
+        SD_BUS_PROPERTY("RestrictNamespace", "t", bus_property_get_ulong, offsetof(ExecContext, restrict_namespaces), SD_BUS_VTABLE_PROPERTY_CONST),
         SD_BUS_VTABLE_END
 };
 
@@ -1591,7 +1592,27 @@ int bus_exec_context_set_transient_property(
                 }
 
                 return 1;
+        } else if (streq(name, "RestrictNamespaces")) {
+                uint64_t flags;
 
+                r = sd_bus_message_read(message, "t", &flags);
+                if (r < 0)
+                        return r;
+                if ((flags & NAMESPACE_FLAGS_ALL) != flags)
+                        return sd_bus_error_setf(error, SD_BUS_ERROR_INVALID_ARGS, "Unknown namespace types");
+
+                if (mode != UNIT_CHECK) {
+                        _cleanup_free_ char *s = NULL;
+
+                        r = namespace_flag_to_string_many(flags, &s);
+                        if (r < 0)
+                                return r;
+
+                        c->restrict_namespaces = flags;
+                        unit_write_drop_in_private_format(u, mode, name, "%s=%s", name, s);
+                }
+
+                return 1;
         }
 
         ri = rlimit_from_string(name);