1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
|
From 0000000000000000000000000000000000000000 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.
---
include/linux/user_namespace.h | 4 ++++
init/Kconfig | 16 ++++++++++++++++
kernel/fork.c | 14 ++++++++++++++
kernel/sysctl.c | 12 ++++++++++++
kernel/user_namespace.c | 7 +++++++
5 files changed, 53 insertions(+)
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 45f09bec02c4..87b20e2ee274 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -148,6 +148,8 @@ static inline void set_userns_rlimit_max(struct user_namespace *ns,
#ifdef CONFIG_USER_NS
+extern int unprivileged_userns_clone;
+
static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
{
if (ns)
@@ -181,6 +183,8 @@ extern bool current_in_userns(const struct user_namespace *target_ns);
struct ns_common *ns_get_owner(struct ns_common *ns);
#else
+#define unprivileged_userns_clone 0
+
static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
{
return &init_user_ns;
diff --git a/init/Kconfig b/init/Kconfig
index de255842f5d0..4e028c5c976b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1248,6 +1248,22 @@ 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 41950ff90aa3..af4961b85f91 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -98,6 +98,10 @@
#include <linux/io_uring.h>
#include <linux/bpf.h>
+#ifdef CONFIG_USER_NS
+#include <linux/user_namespace.h>
+#endif
+
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
@@ -2014,6 +2018,10 @@ 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.
@@ -3173,6 +3181,12 @@ 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 c6d9dec11b74..9a4514ad481b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -81,6 +81,9 @@
#ifdef CONFIG_RT_MUTEXES
#include <linux/rtmutex.h>
#endif
+#ifdef CONFIG_USER_NS
+#include <linux/user_namespace.h>
+#endif
/* shared constants to be used in various sysctls */
const int sysctl_vals[] = { 0, 1, 2, 3, 4, 100, 200, 1000, 3000, INT_MAX, 65535, -1 };
@@ -1659,6 +1662,15 @@ 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 54211dbd516c..16ca0c151629 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -22,6 +22,13 @@
#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);
|