[PATCH] add a sysctl to disable unprivileged user namespace unsharing

[Serge Hallyn]

It is turned on by default, but can be turned off if admins prefer or,
more importantly, if a security vulnerability is found.

The intent is to use this as mitigation so long as Ubuntu is on the
cutting edge of enablement for things like unprivileged filesystem
mounting.

(This patch is tweaked from the one currently still in Debian sid, which
in turn came from the patch we had in saucy)

Signed-off-by: Serge Hallyn <serge.hallyn at ubuntu.com>
[bwh: Remove unneeded binary sysctl bits]
---
 kernel/fork.c           | 15 +++++++++++++++
 kernel/sysctl.c         | 12 ++++++++++++
 kernel/user_namespace.c |  6 ++++++
 3 files changed, 33 insertions(+)

diff --git a/kernel/fork.c b/kernel/fork.c
index 71004bd..c3d0e8a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -87,6 +87,11 @@
 
 #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
@@ -1259,6 +1264,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	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.
@@ -1988,6 +1997,12 @@ SYSCALL_DEFINE1(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 e69201d..1f361aa 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -102,6 +102,9 @@ 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;
@@ -481,6 +484,15 @@ 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 88fefa6..2d1db6c 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -23,6 +23,12 @@
 #include <linux/projid.h>
 #include <linux/fs_struct.h>
 
+/*
+ * sysctl determining whether unprivileged users may unshare a new
+ * userns.  Allowed by default
+ */
+int unprivileged_userns_clone = 1;
+
 static struct kmem_cache *user_ns_cachep __read_mostly;
 static DEFINE_MUTEX(userns_state_mutex);
 
-- 
2.6.2