summaryrefslogtreecommitdiffstats
path: root/net/core/net_namespace.c
blob: 7b660834a4c207a08b23ff6f63fa8ae719ca4fba (plain)
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
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
#include <linux/workqueue.h>
#include <linux/rtnetlink.h>
#include <linux/cache.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/delay.h>
#include <linux/sched.h>
#include <net/net_namespace.h>

/*
 *	Our network namespace constructor/destructor lists
 */

static LIST_HEAD(pernet_list);
static struct list_head *first_device = &pernet_list;
static DEFINE_MUTEX(net_mutex);

LIST_HEAD(net_namespace_list);

struct net init_net;
EXPORT_SYMBOL(init_net);

/*
 * setup_net runs the initializers for the network namespace object.
 */
static __net_init int setup_net(struct net *net)
{
	/* Must be called with net_mutex held */
	struct pernet_operations *ops;
	int error;

	atomic_set(&net->count, 1);
	atomic_set(&net->use_count, 0);

	error = 0;
	list_for_each_entry(ops, &pernet_list, list) {
		if (ops->init) {
			error = ops->init(net);
			if (error < 0)
				goto out_undo;
		}
	}
out:
	return error;

out_undo:
	/* Walk through the list backwards calling the exit functions
	 * for the pernet modules whose init functions did not fail.
	 */
	list_for_each_entry_continue_reverse(ops, &pernet_list, list) {
		if (ops->exit)
			ops->exit(net);
	}

	rcu_barrier();
	goto out;
}

#ifdef CONFIG_NET_NS
static struct kmem_cache *net_cachep;
static struct workqueue_struct *netns_wq;

static struct net *net_alloc(void)
{
	return kmem_cache_zalloc(net_cachep, GFP_KERNEL);
}

static void net_free(struct net *net)
{
	if (!net)
		return;

	if (unlikely(atomic_read(&net->use_count) != 0)) {
		printk(KERN_EMERG "network namespace not free! Usage: %d\n",
			atomic_read(&net->use_count));
		return;
	}

	kmem_cache_free(net_cachep, net);
}

struct net *copy_net_ns(unsigned long flags, struct net *old_net)
{
	struct net *new_net = NULL;
	int err;

	get_net(old_net);

	if (!(flags & CLONE_NEWNET))
		return old_net;

	err = -ENOMEM;
	new_net = net_alloc();
	if (!new_net)
		goto out;

	mutex_lock(&net_mutex);
	err = setup_net(new_net);
	if (err)
		goto out_unlock;

	rtnl_lock();
	list_add_tail(&new_net->list, &net_namespace_list);
	rtnl_unlock();


out_unlock:
	mutex_unlock(&net_mutex);
out:
	put_net(old_net);
	if (err) {
		net_free(new_net);
		new_net = ERR_PTR(err);
	}
	return new_net;
}

static void cleanup_net(struct work_struct *work)
{
	struct pernet_operations *ops;
	struct net *net;

	net = container_of(work, struct net, work);

	mutex_lock(&net_mutex);

	/* Don't let anyone else find us. */
	rtnl_lock();
	list_del(&net->list);
	rtnl_unlock();

	/* Run all of the network namespace exit methods */
	list_for_each_entry_reverse(ops, &pernet_list, list) {
		if (ops->exit)
			ops->exit(net);
	}

	mutex_unlock(&net_mutex);

	/* Ensure there are no outstanding rcu callbacks using this
	 * network namespace.
	 */
	rcu_barrier();

	/* Finally it is safe to free my network namespace structure */
	net_free(net);
}

void __put_net(struct net *net)
{
	/* Cleanup the network namespace in process context */
	INIT_WORK(&net->work, cleanup_net);
	queue_work(netns_wq, &net->work);
}
EXPORT_SYMBOL_GPL(__put_net);

#else
struct net *copy_net_ns(unsigned long flags, struct net *old_net)
{
	if (flags & CLONE_NEWNET)
		return ERR_PTR(-EINVAL);
	return old_net;
}
#endif

static int __init net_ns_init(void)
{
	int err;

	printk(KERN_INFO "net_namespace: %zd bytes\n", sizeof(struct net));
#ifdef CONFIG_NET_NS
	net_cachep = kmem_cache_create("net_namespace", sizeof(struct net),
					SMP_CACHE_BYTES,
					SLAB_PANIC, NULL);

	/* Create workqueue for cleanup */
	netns_wq = create_singlethread_workqueue("netns");
	if (!netns_wq)
		panic("Could not create netns workq");
#endif

	mutex_lock(&net_mutex);
	err = setup_net(&init_net);

	rtnl_lock();
	list_add_tail(&init_net.list, &net_namespace_list);
	rtnl_unlock();

	mutex_unlock(&net_mutex);
	if (err)
		panic("Could not setup the initial network namespace");

	return 0;
}

pure_initcall(net_ns_init);

#ifdef CONFIG_NET_NS
static int register_pernet_operations(struct list_head *list,
				      struct pernet_operations *ops)
{
	struct net *net, *undo_net;
	int error;

	list_add_tail(&ops->list, list);
	if (ops->init) {
		for_each_net(net) {
			error = ops->init(net);
			if (error)
				goto out_undo;
		}
	}
	return 0;

out_undo:
	/* If I have an error cleanup all namespaces I initialized */
	list_del(&ops->list);
	if (ops->exit) {
		for_each_net(undo_net) {
			if (undo_net == net)
				goto undone;
			ops->exit(undo_net);
		}
	}
undone:
	return error;
}

static void unregister_pernet_operations(struct pernet_operations *ops)
{
	struct net *net;

	list_del(&ops->list);
	if (ops->exit)
		for_each_net(net)
			ops->exit(net);
}

#else

static int register_pernet_operations(struct list_head *list,
				      struct pernet_operations *ops)
{
	if (ops->init == NULL)
		return 0;
	return ops->init(&init_net);
}

static void unregister_pernet_operations(struct pernet_operations *ops)
{
	if (ops->exit)
		ops->exit(&init_net);
}
#endif

/**
 *      register_pernet_subsys - register a network namespace subsystem
 *	@ops:  pernet operations structure for the subsystem
 *
 *	Register a subsystem which has init and exit functions
 *	that are called when network namespaces are created and
 *	destroyed respectively.
 *
 *	When registered all network namespace init functions are
 *	called for every existing network namespace.  Allowing kernel
 *	modules to have a race free view of the set of network namespaces.
 *
 *	When a new network namespace is created all of the init
 *	methods are called in the order in which they were registered.
 *
 *	When a network namespace is destroyed all of the exit methods
 *	are called in the reverse of the order with which they were
 *	registered.
 */
int register_pernet_subsys(struct pernet_operations *ops)
{
	int error;
	mutex_lock(&net_mutex);
	error =  register_pernet_operations(first_device, ops);
	mutex_unlock(&net_mutex);
	return error;
}
EXPORT_SYMBOL_GPL(register_pernet_subsys);

/**
 *      unregister_pernet_subsys - unregister a network namespace subsystem
 *	@ops: pernet operations structure to manipulate
 *
 *	Remove the pernet operations structure from the list to be
 *	used when network namespaces are created or destroyed.  In
 *	addition run the exit method for all existing network
 *	namespaces.
 */
void unregister_pernet_subsys(struct pernet_operations *module)
{
	mutex_lock(&net_mutex);
	unregister_pernet_operations(module);
	mutex_unlock(&net_mutex);
}
EXPORT_SYMBOL_GPL(unregister_pernet_subsys);

/**
 *      register_pernet_device - register a network namespace device
 *	@ops:  pernet operations structure for the subsystem
 *
 *	Register a device which has init and exit functions
 *	that are called when network namespaces are created and
 *	destroyed respectively.
 *
 *	When registered all network namespace init functions are
 *	called for every existing network namespace.  Allowing kernel
 *	modules to have a race free view of the set of network namespaces.
 *
 *	When a new network namespace is created all of the init
 *	methods are called in the order in which they were registered.
 *
 *	When a network namespace is destroyed all of the exit methods
 *	are called in the reverse of the order with which they were
 *	registered.
 */
int register_pernet_device(struct pernet_operations *ops)
{
	int error;
	mutex_lock(&net_mutex);
	error = register_pernet_operations(&pernet_list, ops);
	if (!error && (first_device == &pernet_list))
		first_device = &ops->list;
	mutex_unlock(&net_mutex);
	return error;
}
EXPORT_SYMBOL_GPL(register_pernet_device);

/**
 *      unregister_pernet_device - unregister a network namespace netdevice
 *	@ops: pernet operations structure to manipulate
 *
 *	Remove the pernet operations structure from the list to be
 *	used when network namespaces are created or destroyed.  In
 *	addition run the exit method for all existing network
 *	namespaces.
 */
void unregister_pernet_device(struct pernet_operations *ops)
{
	mutex_lock(&net_mutex);
	if (&ops->list == first_device)
		first_device = first_device->next;
	unregister_pernet_operations(ops);
	mutex_unlock(&net_mutex);
}
EXPORT_SYMBOL_GPL(unregister_pernet_device);
OpenPOWER on IntegriCloud