From 6136ffb3d88e9f044260f8288d2d0a1edd64379e Mon Sep 17 00:00:00 2001
From: "Jan Alexander Steffens (heftig)" <jan.steffens@gmail.com>
Date: Mon, 16 Sep 2019 04:53:20 +0200
Subject: [PATCH] ZEN: Add sysctl and CONFIG to disallow unprivileged
 CLONE_NEWUSER

Our default behavior continues to match the vanilla kernel.
---
 init/Kconfig            | 16 ++++++++++++++++
 kernel/fork.c           | 15 +++++++++++++++
 kernel/sysctl.c         | 12 ++++++++++++
 kernel/user_namespace.c |  7 +++++++
 4 files changed, 50 insertions(+)

diff --git a/init/Kconfig b/init/Kconfig
index bd7d650d4a99..658f9c052151 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1091,6 +1091,22 @@ config USER_NS
 
 	  If unsure, say N.
 
+config USER_NS_UNPRIVILEGED
+	bool "Allow unprivileged users to create namespaces"
+	default y
+	depends on USER_NS
+	help
+	  When disabled, unprivileged users will not be able to create
+	  new namespaces. Allowing users to create their own namespaces
+	  has been part of several recent local privilege escalation
+	  exploits, so if you need user namespaces but are
+	  paranoid^Wsecurity-conscious you want to disable this.
+
+	  This setting can be overridden at runtime via the
+	  kernel.unprivileged_userns_clone sysctl.
+
+	  If unsure, say Y.
+
 config PID_NS
 	bool "PID Namespaces"
 	default y
diff --git a/kernel/fork.c b/kernel/fork.c
index 541fd805fb88..ffd57c812153 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -106,6 +106,11 @@
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/task.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
@@ -1788,6 +1793,10 @@ static __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.
@@ -2819,6 +2828,12 @@ 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
index 078950d9605b..baead3605bbe 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -110,6 +110,9 @@ extern int core_uses_pid;
 extern char core_pattern[];
 extern unsigned int core_pipe_limit;
 #endif
+#ifdef CONFIG_USER_NS
+extern int unprivileged_userns_clone;
+#endif
 extern int pid_max;
 extern int pid_max_min, pid_max_max;
 extern int percpu_pagelist_fraction;
@@ -545,6 +548,15 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
+#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
index 8eadadc478f9..c36ecd19562c 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -21,6 +21,13 @@
 #include <linux/bsearch.h>
 #include <linux/sort.h>
 
+/* sysctl */
+#ifdef CONFIG_USER_NS_UNPRIVILEGED
+int unprivileged_userns_clone = 1;
+#else
+int unprivileged_userns_clone;
+#endif
+
 static struct kmem_cache *user_ns_cachep __read_mostly;
 static DEFINE_MUTEX(userns_state_mutex);
 
-- 
2.23.0