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, 9 insertions, 0 deletions

diff --git a/src/core/execute.h b/src/core/execute.h
index c7d0f7761e..56f880cffe 100644
--- a/src/core/execute.h
+++ b/src/core/execute.h
@@ -35,6 +35,7 @@ typedef struct ExecParameters ExecParameters;
 #include "list.h"
 #include "missing.h"
 #include "namespace.h"
+#include "nsflags.h"
 
 typedef enum ExecUtmpMode {
         EXEC_UTMP_INIT,
@@ -195,6 +196,8 @@ struct ExecContext {
 
         unsigned long personality;
 
+        unsigned long restrict_namespaces; /* The CLONE_NEWxyz flags permitted to the unit's processes */
+
         Set *syscall_filter;
         Set *syscall_archs;
         int syscall_errno;
@@ -216,6 +219,12 @@ struct ExecContext {
         bool no_new_privileges_set:1;
 };
 
+static inline bool exec_context_restrict_namespaces_set(const ExecContext *c) {
+        assert(c);
+
+        return (c->restrict_namespaces & NAMESPACE_FLAGS_ALL) != NAMESPACE_FLAGS_ALL;
+}
+
 typedef enum ExecFlags {
         EXEC_CONFIRM_SPAWN     = 1U << 0,
         EXEC_APPLY_PERMISSIONS = 1U << 1,