net_namespace.c 10.5 KB
Newer Older
1 2 3 4 5 6
#include <linux/workqueue.h>
#include <linux/rtnetlink.h>
#include <linux/cache.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/delay.h>
7
#include <linux/sched.h>
8
#include <linux/idr.h>
9
#include <net/net_namespace.h>
10
#include <net/netns/generic.h>
11 12 13 14 15 16 17 18 19 20

/*
 *	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);
A
Alexey Dobriyan 已提交
21
EXPORT_SYMBOL_GPL(net_namespace_list);
22 23

struct net init_net;
24
EXPORT_SYMBOL(init_net);
25

26 27
#define INITIAL_NET_GEN_PTRS	13 /* +1 for len +2 for rcu_head */

28 29 30
/*
 * setup_net runs the initializers for the network namespace object.
 */
31
static __net_init int setup_net(struct net *net)
32 33 34 35
{
	/* Must be called with net_mutex held */
	struct pernet_operations *ops;
	int error;
36
	struct net_generic *ng;
37 38

	atomic_set(&net->count, 1);
39
#ifdef NETNS_REFCNT_DEBUG
40
	atomic_set(&net->use_count, 0);
41
#endif
42

43 44 45 46 47 48 49 50 51 52
	error = -ENOMEM;
	ng = kzalloc(sizeof(struct net_generic) +
			INITIAL_NET_GEN_PTRS * sizeof(void *), GFP_KERNEL);
	if (ng == NULL)
		goto out;

	ng->len = INITIAL_NET_GEN_PTRS;
	INIT_RCU_HEAD(&ng->rcu);
	rcu_assign_pointer(net->gen, ng);

53
	error = 0;
54
	list_for_each_entry(ops, &pernet_list, list) {
55 56 57 58 59 60 61 62
		if (ops->init) {
			error = ops->init(net);
			if (error < 0)
				goto out_undo;
		}
	}
out:
	return error;
63

64 65 66 67
out_undo:
	/* Walk through the list backwards calling the exit functions
	 * for the pernet modules whose init functions did not fail.
	 */
68
	list_for_each_entry_continue_reverse(ops, &pernet_list, list) {
69 70 71
		if (ops->exit)
			ops->exit(net);
	}
72 73

	rcu_barrier();
74
	kfree(ng);
75 76 77
	goto out;
}

78
#ifdef CONFIG_NET_NS
79
static struct kmem_cache *net_cachep;
80
static struct workqueue_struct *netns_wq;
81

82 83 84 85 86
static struct net *net_alloc(void)
{
	return kmem_cache_zalloc(net_cachep, GFP_KERNEL);
}

87 88 89 90 91
static void net_free(struct net *net)
{
	if (!net)
		return;

92
#ifdef NETNS_REFCNT_DEBUG
93 94 95 96 97
	if (unlikely(atomic_read(&net->use_count) != 0)) {
		printk(KERN_EMERG "network namespace not free! Usage: %d\n",
			atomic_read(&net->use_count));
		return;
	}
98
#endif
99
	kfree(net->gen);
100 101 102
	kmem_cache_free(net_cachep, net);
}

103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122
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;

123
	rtnl_lock();
124
	list_add_tail(&new_net->list, &net_namespace_list);
125
	rtnl_unlock();
126 127 128 129 130 131 132 133 134 135 136 137 138


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;
}

139 140 141 142 143
static void cleanup_net(struct work_struct *work)
{
	struct pernet_operations *ops;
	struct net *net;

144 145 146
	/* Be very certain incoming network packets will not find us */
	rcu_barrier();

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
	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);
177
	queue_work(netns_wq, &net->work);
178 179 180 181 182 183 184 185 186 187 188 189
}
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

190 191 192 193 194
static int __init net_ns_init(void)
{
	int err;

	printk(KERN_INFO "net_namespace: %zd bytes\n", sizeof(struct net));
195
#ifdef CONFIG_NET_NS
196 197 198
	net_cachep = kmem_cache_create("net_namespace", sizeof(struct net),
					SMP_CACHE_BYTES,
					SLAB_PANIC, NULL);
199 200 201 202 203

	/* Create workqueue for cleanup */
	netns_wq = create_singlethread_workqueue("netns");
	if (!netns_wq)
		panic("Could not create netns workq");
204
#endif
205

206 207 208
	mutex_lock(&net_mutex);
	err = setup_net(&init_net);

209
	rtnl_lock();
210
	list_add_tail(&init_net.list, &net_namespace_list);
211
	rtnl_unlock();
212 213 214 215 216 217 218 219 220 221

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

	return 0;
}

pure_initcall(net_ns_init);

222
#ifdef CONFIG_NET_NS
223 224 225 226 227 228 229
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);
230 231
	if (ops->init) {
		for_each_net(net) {
232 233 234 235 236
			error = ops->init(net);
			if (error)
				goto out_undo;
		}
	}
237
	return 0;
238 239 240 241

out_undo:
	/* If I have an error cleanup all namespaces I initialized */
	list_del(&ops->list);
242 243 244 245
	if (ops->exit) {
		for_each_net(undo_net) {
			if (undo_net == net)
				goto undone;
246
			ops->exit(undo_net);
247
		}
248 249
	}
undone:
250
	return error;
251 252 253 254 255 256 257
}

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

	list_del(&ops->list);
258 259
	if (ops->exit)
		for_each_net(net)
260 261 262
			ops->exit(net);
}

263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279
#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

280 281
static DEFINE_IDA(net_generic_ids);

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
/**
 *      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
316
 *	used when network namespaces are created or destroyed.  In
317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358
 *	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);

359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382
int register_pernet_gen_device(int *id, struct pernet_operations *ops)
{
	int error;
	mutex_lock(&net_mutex);
again:
	error = ida_get_new_above(&net_generic_ids, 1, id);
	if (error) {
		if (error == -EAGAIN) {
			ida_pre_get(&net_generic_ids, GFP_KERNEL);
			goto again;
		}
		goto out;
	}
	error = register_pernet_operations(&pernet_list, ops);
	if (error)
		ida_remove(&net_generic_ids, *id);
	else if (first_device == &pernet_list)
		first_device = &ops->list;
out:
	mutex_unlock(&net_mutex);
	return error;
}
EXPORT_SYMBOL_GPL(register_pernet_gen_device);

383 384 385 386 387
/**
 *      unregister_pernet_device - unregister a network namespace netdevice
 *	@ops: pernet operations structure to manipulate
 *
 *	Remove the pernet operations structure from the list to be
388
 *	used when network namespaces are created or destroyed.  In
389 390 391 392 393 394 395 396 397 398 399 400
 *	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);
401 402 403 404 405 406 407 408 409 410 411

void unregister_pernet_gen_device(int id, struct pernet_operations *ops)
{
	mutex_lock(&net_mutex);
	if (&ops->list == first_device)
		first_device = first_device->next;
	unregister_pernet_operations(ops);
	ida_remove(&net_generic_ids, id);
	mutex_unlock(&net_mutex);
}
EXPORT_SYMBOL_GPL(unregister_pernet_gen_device);
412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458

static void net_generic_release(struct rcu_head *rcu)
{
	struct net_generic *ng;

	ng = container_of(rcu, struct net_generic, rcu);
	kfree(ng);
}

int net_assign_generic(struct net *net, int id, void *data)
{
	struct net_generic *ng, *old_ng;

	BUG_ON(!mutex_is_locked(&net_mutex));
	BUG_ON(id == 0);

	ng = old_ng = net->gen;
	if (old_ng->len >= id)
		goto assign;

	ng = kzalloc(sizeof(struct net_generic) +
			id * sizeof(void *), GFP_KERNEL);
	if (ng == NULL)
		return -ENOMEM;

	/*
	 * Some synchronisation notes:
	 *
	 * The net_generic explores the net->gen array inside rcu
	 * read section. Besides once set the net->gen->ptr[x]
	 * pointer never changes (see rules in netns/generic.h).
	 *
	 * That said, we simply duplicate this array and schedule
	 * the old copy for kfree after a grace period.
	 */

	ng->len = id;
	INIT_RCU_HEAD(&ng->rcu);
	memcpy(&ng->ptr, &old_ng->ptr, old_ng->len);

	rcu_assign_pointer(net->gen, ng);
	call_rcu(&old_ng->rcu, net_generic_release);
assign:
	ng->ptr[id - 1] = data;
	return 0;
}
EXPORT_SYMBOL_GPL(net_assign_generic);