aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/nsproxy.c
blob: 9aeab4b98c6431f8b8a17ee97992925d34c3a427 (plain) (blame)
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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
/*
 *  Copyright (C) 2006 IBM Corporation
 *
 *  Author: Serge Hallyn <serue@us.ibm.com>
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License as
 *  published by the Free Software Foundation, version 2 of the
 *  License.
 *
 *  Jun 2006 - namespaces support
 *             OpenVZ, SWsoft Inc.
 *             Pavel Emelianov <xemul@openvz.org>
 */

#include <linux/slab.h>
#include <linux/module.h>
#include <linux/nsproxy.h>
#include <linux/init_task.h>
#include <linux/mnt_namespace.h>
#include <linux/utsname.h>
#include <linux/pid_namespace.h>
#include <net/net_namespace.h>
#include <linux/ipc_namespace.h>
#include <linux/proc_fs.h>
#include <linux/file.h>
#include <linux/syscalls.h>

static struct kmem_cache *nsproxy_cachep;

struct nsproxy init_nsproxy = {
	.count	= ATOMIC_INIT(1),
	.uts_ns	= &init_uts_ns,
#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC)
	.ipc_ns	= &init_ipc_ns,
#endif
	.mnt_ns	= NULL,
	.pid_ns	= &init_pid_ns,
#ifdef CONFIG_NET
	.net_ns	= &init_net,
#endif
};

static inline struct nsproxy *create_nsproxy(void)
{
	struct nsproxy *nsproxy;

	nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
	if (nsproxy)
		atomic_set(&nsproxy->count, 1);
	return nsproxy;
}

/*
 * Create new nsproxy and all of its the associated namespaces.
 * Return the newly created nsproxy.  Do not attach this to the task,
 * leave it to the caller to do proper locking and attach it to task.
 */
static struct nsproxy *create_new_namespaces(unsigned long flags,
			struct task_struct *tsk, struct fs_struct *new_fs)
{
	struct nsproxy *new_nsp;
	int err;

	new_nsp = create_nsproxy();
	if (!new_nsp)
		return ERR_PTR(-ENOMEM);

	new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, new_fs);
	if (IS_ERR(new_nsp->mnt_ns)) {
		err = PTR_ERR(new_nsp->mnt_ns);
		goto out_ns;
	}

	new_nsp->uts_ns = copy_utsname(flags, tsk);
	if (IS_ERR(new_nsp->uts_ns)) {
		err = PTR_ERR(new_nsp->uts_ns);
		goto out_uts;
	}

	new_nsp->ipc_ns = copy_ipcs(flags, tsk);
	if (IS_ERR(new_nsp->ipc_ns)) {
		err = PTR_ERR(new_nsp->ipc_ns);
		goto out_ipc;
	}

	new_nsp->pid_ns = copy_pid_ns(flags, task_active_pid_ns(tsk));
	if (IS_ERR(new_nsp->pid_ns)) {
		err = PTR_ERR(new_nsp->pid_ns);
		goto out_pid;
	}

	new_nsp->net_ns = copy_net_ns(flags, tsk->nsproxy->net_ns);
	if (IS_ERR(new_nsp->net_ns)) {
		err = PTR_ERR(new_nsp->net_ns);
		goto out_net;
	}

	return new_nsp;

out_net:
	if (new_nsp->pid_ns)
		put_pid_ns(new_nsp->pid_ns);
out_pid:
	if (new_nsp->ipc_ns)
		put_ipc_ns(new_nsp->ipc_ns);
out_ipc:
	if (new_nsp->uts_ns)
		put_uts_ns(new_nsp->uts_ns);
out_uts:
	if (new_nsp->mnt_ns)
		put_mnt_ns(new_nsp->mnt_ns);
out_ns:
	kmem_cache_free(nsproxy_cachep, new_nsp);
	return ERR_PTR(err);
}

/*
 * called from clone.  This now handles copy for nsproxy and all
 * namespaces therein.
 */
int copy_namespaces(unsigned long flags, struct task_struct *tsk)
{
	struct nsproxy *old_ns = tsk->nsproxy;
	struct nsproxy *new_ns;
	int err = 0;

	if (!old_ns)
		return 0;

	get_nsproxy(old_ns);

	if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
				CLONE_NEWPID | CLONE_NEWNET)))
		return 0;

	if (!capable(CAP_SYS_ADMIN)) {
		err = -EPERM;
		goto out;
	}

	/*
	 * CLONE_NEWIPC must detach from the undolist: after switching
	 * to a new ipc namespace, the semaphore arrays from the old
	 * namespace are unreachable.  In clone parlance, CLONE_SYSVSEM
	 * means share undolist with parent, so we must forbid using
	 * it along with CLONE_NEWIPC.
	 */
	if ((flags & CLONE_NEWIPC) && (flags & CLONE_SYSVSEM)) {
		err = -EINVAL;
		goto out;
	}

	new_ns = create_new_namespaces(flags, tsk, tsk->fs);
	if (IS_ERR(new_ns)) {
		err = PTR_ERR(new_ns);
		goto out;
	}

	tsk->nsproxy = new_ns;

out:
	put_nsproxy(old_ns);
	return err;
}

void free_nsproxy(struct nsproxy *ns)
{
	if (ns->mnt_ns)
		put_mnt_ns(ns->mnt_ns);
	if (ns->uts_ns)
		put_uts_ns(ns->uts_ns);
	if (ns->ipc_ns)
		put_ipc_ns(ns->ipc_ns);
	if (ns->pid_ns)
		put_pid_ns(ns->pid_ns);
	put_net(ns->net_ns);
	kmem_cache_free(nsproxy_cachep, ns);
}

/*
 * Called from unshare. Unshare all the namespaces part of nsproxy.
 * On success, returns the new nsproxy.
 */
int unshare_nsproxy_namespaces(unsigned long unshare_flags,
		struct nsproxy **new_nsp, struct fs_struct *new_fs)
{
	int err = 0;

	if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
			       CLONE_NEWNET)))
		return 0;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	*new_nsp = create_new_namespaces(unshare_flags, current,
				new_fs ? new_fs : current->fs);
	if (IS_ERR(*new_nsp)) {
		err = PTR_ERR(*new_nsp);
		goto out;
	}

out:
	return err;
}

void switch_task_namespaces(struct task_struct *p, struct nsproxy *new)
{
	struct nsproxy *ns;

	might_sleep();

	ns = p->nsproxy;

	rcu_assign_pointer(p->nsproxy, new);

	if (ns && atomic_dec_and_test(&ns->count)) {
		/*
		 * wait for others to get what they want from this nsproxy.
		 *
		 * cannot release this nsproxy via the call_rcu() since
		 * put_mnt_ns() will want to sleep
		 */
		synchronize_rcu();
		free_nsproxy(ns);
	}
}

void exit_task_namespaces(struct task_struct *p)
{
	switch_task_namespaces(p, NULL);
}

SYSCALL_DEFINE2(setns, int, fd, int, nstype)
{
	const struct proc_ns_operations *ops;
	struct task_struct *tsk = current;
	struct nsproxy *new_nsproxy;
	struct proc_inode *ei;
	struct file *file;
	int err;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	file = proc_ns_fget(fd);
	if (IS_ERR(file))
		return PTR_ERR(file);

	err = -EINVAL;
	ei = PROC_I(file->f_dentry->d_inode);
	ops = ei->ns_ops;
	if (nstype && (ops->type != nstype))
		goto out;

	new_nsproxy = create_new_namespaces(0, tsk, tsk->fs);
	if (IS_ERR(new_nsproxy)) {
		err = PTR_ERR(new_nsproxy);
		goto out;
	}

	err = ops->install(new_nsproxy, ei->ns);
	if (err) {
		free_nsproxy(new_nsproxy);
		goto out;
	}
	switch_task_namespaces(tsk, new_nsproxy);
out:
	fput(file);
	return err;
}

int __init nsproxy_cache_init(void)
{
	nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC);
	return 0;
}