add sysctl to disallow unprivileged CLONE_NEWUSER by default

Origin: http://kernel.ubuntu.com/git?p=serge%2Fubuntu-saucy.git;a=commit;h=5c847404dcb2e3195ad0057877e1422ae90892b8

add sysctl to disallow unprivileged CLONE_NEWUSER by default

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.

Signed-off-by: Serge Hallyn <serge.hallyn@ubuntu.com>
[bwh: Remove unneeded binary sysctl bits]
[bwh: Keep this sysctl, but change the default to enabled]

Gbp-Pq: Topic debian
Gbp-Pq: Name add-sysctl-to-disallow-unprivileged-CLONE_NEWUSER-by-default.patch

diff --git a/kernel/fork.c b/kernel/fork.c
index 1e9ecaa4f5ac5f6c73ed3cf0ea029288eb0ab639..9bec4c42c6a16b3571c7d2ab302a18826206cfc7 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -109,6 +109,11 @@
 
 #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
@@ -1993,6 +1998,10 @@ 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.
@@ -3111,6 +3120,12 @@ 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 830aaf8ca08ee0cf3ca5f816fc347a0d4189ba3d..03780e42a9d052168492adcca4233a20ea7f4b39 100644 (file)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -146,6 +146,10 @@ int sysctl_legacy_va_layout;
 static const int max_extfrag_threshold = 1000;
 #endif
 
+#ifdef CONFIG_USER_NS
+extern int unprivileged_userns_clone;
+#endif
+
 #endif /* CONFIG_SYSCTL */
 
 #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL)
@@ -1803,6 +1807,15 @@ static struct ctl_table kern_table[] = {
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
+#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 5481ba44a8d68463aa01f529a4886a8905190550..2a4b1e22a422b5bc0dd1b26d82de9e1e0460e48a 100644 (file)
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -21,6 +21,9 @@
 #include <linux/bsearch.h>
 #include <linux/sort.h>
 
+/* sysctl */
+int unprivileged_userns_clone = 1;
+
 static struct kmem_cache *user_ns_cachep __read_mostly;
 static DEFINE_MUTEX(userns_state_mutex);