add sysctl to allow disabling unprivileged CLONE_NEWUSER

hallyn · heftig · commit a76f00ac4fb5 · 2025-09-10T02:17:26.000+02:00
This is a short-term patch.  Unprivileged use of CLONE_NEWUSER
is certainly an intended feature of user namespaces.  However
for at least saucy we want to make sure that, if any security
issues are found, we have a fail-safe.

[bwh: Remove unneeded binary sysctl bits]
[bwh: Keep this sysctl, but change the default to enabled]
[heftig: correct commit subject to reduce confusion]
diff --git a/kernel/fork.c b/kernel/fork.c
@@ -122,6 +122,12 @@
 
 #include <kunit/visibility.h>
 
+#ifdef CONFIG_USER_NS
+extern int unprivileged_userns_clone;
+#else
+#define unprivileged_userns_clone 0
+#endif
+
 /*
  * Minimum number of threads to boot the kernel
  */
@@ -1933,6 +1939,10 @@ __latent_entropy struct task_struct *copy_process(
 	if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS))
 		return ERR_PTR(-EINVAL);
 
+	if ((clone_flags & CLONE_NEWUSER) && !unprivileged_userns_clone)
+		if (!capable(CAP_SYS_ADMIN))
+			return ERR_PTR(-EPERM);
+
 	/*
 	 * Thread groups must share signals as well, and detached threads
 	 * can only be started up within the thread group.
@@ -3099,6 +3109,12 @@ int ksys_unshare(unsigned long unshare_flags)
 	if (unshare_flags & CLONE_NEWNS)
 		unshare_flags |= CLONE_FS;
 
+	if ((unshare_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) {
+		err = -EPERM;
+		if (!capable(CAP_SYS_ADMIN))
+			goto bad_unshare_out;
+	}
+
 	err = check_unshare_flags(unshare_flags);
 	if (err)
 		goto bad_unshare_out;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
@@ -77,6 +77,10 @@ EXPORT_SYMBOL_GPL(sysctl_long_vals);
 static const int ngroups_max = NGROUPS_MAX;
 static const int cap_last_cap = CAP_LAST_CAP;
 
+#ifdef CONFIG_USER_NS
+extern int unprivileged_userns_clone;
+#endif
+
 #ifdef CONFIG_PROC_SYSCTL
 
 /**
@@ -1581,6 +1585,15 @@ int proc_do_static_key(const struct ctl_table *table, int write,
 }
 
 static const struct ctl_table kern_table[] = {
+#ifdef CONFIG_USER_NS
+	{
+		.procname	= "unprivileged_userns_clone",
+		.data		= &unprivileged_userns_clone,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#endif
 #ifdef CONFIG_PROC_SYSCTL
 	{
 		.procname	= "tainted",
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
@@ -22,6 +22,9 @@
 #include <linux/bsearch.h>
 #include <linux/sort.h>
 
+/* sysctl */
+int unprivileged_userns_clone = 1;
+
 static struct kmem_cache *user_ns_cachep __ro_after_init;
 static DEFINE_MUTEX(userns_state_mutex);
 
