af_inet.c 42.1 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
4
5
6
7
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		PF_INET protocol family socket handler.
 *
8
 * Authors:	Ross Biro
Linus Torvalds's avatar
Linus Torvalds committed
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
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Alan Cox, <A.Cox@swansea.ac.uk>
 *
 * Changes (see also sock.c)
 *
 *		piggy,
 *		Karl Knutson	:	Socket protocol table
 *		A.N.Kuznetsov	:	Socket death error in accept().
 *		John Richardson :	Fix non blocking error in connect()
 *					so sockets that fail to connect
 *					don't return -EINPROGRESS.
 *		Alan Cox	:	Asynchronous I/O support
 *		Alan Cox	:	Keep correct socket pointer on sock
 *					structures
 *					when accept() ed
 *		Alan Cox	:	Semantics of SO_LINGER aren't state
 *					moved to close when you look carefully.
 *					With this fixed and the accept bug fixed
 *					some RPC stuff seems happier.
 *		Niibe Yutaka	:	4.4BSD style write async I/O
 *		Alan Cox,
 *		Tony Gale 	:	Fixed reuse semantics.
 *		Alan Cox	:	bind() shouldn't abort existing but dead
 *					sockets. Stops FTP netin:.. I hope.
 *		Alan Cox	:	bind() works correctly for RAW sockets.
 *					Note that FreeBSD at least was broken
 *					in this respect so be careful with
 *					compatibility tests...
 *		Alan Cox	:	routing cache support
 *		Alan Cox	:	memzero the socket structure for
 *					compactness.
 *		Matt Day	:	nonblock connect error handler
 *		Alan Cox	:	Allow large numbers of pending sockets
 *					(eg for big web sites), but only if
 *					specifically application requested.
 *		Alan Cox	:	New buffering throughout IP. Used
 *					dumbly.
 *		Alan Cox	:	New buffering now used smartly.
 *		Alan Cox	:	BSD rather than common sense
 *					interpretation of listen.
 *		Germano Caronni	:	Assorted small races.
 *		Alan Cox	:	sendmsg/recvmsg basic support.
 *		Alan Cox	:	Only sendmsg/recvmsg now supported.
 *		Alan Cox	:	Locked down bind (see security list).
 *		Alan Cox	:	Loosened bind a little.
 *		Mike McLagan	:	ADD/DEL DLCI Ioctls
 *	Willy Konynenberg	:	Transparent proxying support.
 *		David S. Miller	:	New socket lookup architecture.
 *					Some other random speedups.
 *		Cyrus Durgin	:	Cleaned up file for kmod hacks.
 *		Andi Kleen	:	Fix inet_stream_connect TCP race.
 *
 *		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; either version
 *		2 of the License, or (at your option) any later version.
 */

Herbert Xu's avatar
Herbert Xu committed
68
#include <linux/err.h>
Linus Torvalds's avatar
Linus Torvalds committed
69
70
71
72
73
74
75
76
77
78
79
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
80
#include <linux/capability.h>
Linus Torvalds's avatar
Linus Torvalds committed
81
82
83
84
85
86
87
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/netfilter_ipv4.h>
88
#include <linux/random.h>
89
#include <linux/slab.h>
Linus Torvalds's avatar
Linus Torvalds committed
90
91
92
93
94
95

#include <asm/uaccess.h>
#include <asm/system.h>

#include <linux/inet.h>
#include <linux/igmp.h>
96
#include <linux/inetdevice.h>
Linus Torvalds's avatar
Linus Torvalds committed
97
#include <linux/netdevice.h>
Herbert Xu's avatar
Herbert Xu committed
98
#include <net/checksum.h>
Linus Torvalds's avatar
Linus Torvalds committed
99
100
101
102
103
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/ip_fib.h>
104
#include <net/inet_connection_sock.h>
Linus Torvalds's avatar
Linus Torvalds committed
105
106
#include <net/tcp.h>
#include <net/udp.h>
107
#include <net/udplite.h>
Linus Torvalds's avatar
Linus Torvalds committed
108
109
110
111
112
113
114
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/raw.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
115
#include <net/net_namespace.h>
Linus Torvalds's avatar
Linus Torvalds committed
116
117
118
119
120
121
122
123
124
125
126
#ifdef CONFIG_IP_MROUTE
#include <linux/mroute.h>
#endif


/* The inetsw table contains everything that inet_create needs to
 * build a new socket.
 */
static struct list_head inetsw[SOCK_MAX];
static DEFINE_SPINLOCK(inetsw_lock);

127
128
129
struct ipv4_config ipv4_config;
EXPORT_SYMBOL(ipv4_config);

Linus Torvalds's avatar
Linus Torvalds committed
130
131
132
133
134
135
136
137
138
/* New destruction routine */

void inet_sock_destruct(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);

	__skb_queue_purge(&sk->sk_receive_queue);
	__skb_queue_purge(&sk->sk_error_queue);

Hideo Aoki's avatar
Hideo Aoki committed
139
140
	sk_mem_reclaim(sk);

Linus Torvalds's avatar
Linus Torvalds committed
141
	if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) {
Eric Dumazet's avatar
Eric Dumazet committed
142
		pr_err("Attempt to release TCP socket in state %d %p\n",
Linus Torvalds's avatar
Linus Torvalds committed
143
144
145
146
		       sk->sk_state, sk);
		return;
	}
	if (!sock_flag(sk, SOCK_DEAD)) {
Eric Dumazet's avatar
Eric Dumazet committed
147
		pr_err("Attempt to release alive inet socket %p\n", sk);
Linus Torvalds's avatar
Linus Torvalds committed
148
149
150
		return;
	}

151
152
153
154
	WARN_ON(atomic_read(&sk->sk_rmem_alloc));
	WARN_ON(atomic_read(&sk->sk_wmem_alloc));
	WARN_ON(sk->sk_wmem_queued);
	WARN_ON(sk->sk_forward_alloc);
Linus Torvalds's avatar
Linus Torvalds committed
155

Jesper Juhl's avatar
Jesper Juhl committed
156
	kfree(inet->opt);
Eric Dumazet's avatar
Eric Dumazet committed
157
	dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
158
	sk_refcnt_debug_dec(sk);
Linus Torvalds's avatar
Linus Torvalds committed
159
}
Eric Dumazet's avatar
Eric Dumazet committed
160
EXPORT_SYMBOL(inet_sock_destruct);
Linus Torvalds's avatar
Linus Torvalds committed
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177

/*
 *	The routines beyond this point handle the behaviour of an AF_INET
 *	socket object. Mostly it punts to the subprotocols of IP to do
 *	the work.
 */

/*
 *	Automatically bind an unbound socket.
 */

static int inet_autobind(struct sock *sk)
{
	struct inet_sock *inet;
	/* We may need to bind the socket. */
	lock_sock(sk);
	inet = inet_sk(sk);
178
	if (!inet->inet_num) {
Linus Torvalds's avatar
Linus Torvalds committed
179
180
181
182
		if (sk->sk_prot->get_port(sk, 0)) {
			release_sock(sk);
			return -EAGAIN;
		}
183
		inet->inet_sport = htons(inet->inet_num);
Linus Torvalds's avatar
Linus Torvalds committed
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
	}
	release_sock(sk);
	return 0;
}

/*
 *	Move a socket into listening state.
 */
int inet_listen(struct socket *sock, int backlog)
{
	struct sock *sk = sock->sk;
	unsigned char old_state;
	int err;

	lock_sock(sk);

	err = -EINVAL;
	if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM)
		goto out;

	old_state = sk->sk_state;
	if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN)))
		goto out;

	/* Really, if the socket is already in listen state
	 * we can only allow the backlog to be adjusted.
	 */
	if (old_state != TCP_LISTEN) {
212
		err = inet_csk_listen_start(sk, backlog);
Linus Torvalds's avatar
Linus Torvalds committed
213
214
215
216
217
218
219
220
221
222
		if (err)
			goto out;
	}
	sk->sk_max_ack_backlog = backlog;
	err = 0;

out:
	release_sock(sk);
	return err;
}
Eric Dumazet's avatar
Eric Dumazet committed
223
EXPORT_SYMBOL(inet_listen);
Linus Torvalds's avatar
Linus Torvalds committed
224

225
u32 inet_ehash_secret __read_mostly;
226
227
EXPORT_SYMBOL(inet_ehash_secret);

228
229
230
/*
 * inet_ehash_secret must be set exactly once
 */
231
232
void build_ehash_secret(void)
{
233
	u32 rnd;
234

235
236
237
	do {
		get_random_bytes(&rnd, sizeof(rnd));
	} while (rnd == 0);
238
239

	cmpxchg(&inet_ehash_secret, 0, rnd);
240
241
242
}
EXPORT_SYMBOL(build_ehash_secret);

243
244
245
static inline int inet_netns_ok(struct net *net, int protocol)
{
	int hash;
246
	const struct net_protocol *ipprot;
247

248
	if (net_eq(net, &init_net))
249
250
251
252
253
254
255
256
257
258
259
		return 1;

	hash = protocol & (MAX_INET_PROTOS - 1);
	ipprot = rcu_dereference(inet_protos[hash]);

	if (ipprot == NULL)
		/* raw IP is OK */
		return 1;
	return ipprot->netns_ok;
}

Linus Torvalds's avatar
Linus Torvalds committed
260
261
262
263
/*
 *	Create an inet socket.
 */

264
265
static int inet_create(struct net *net, struct socket *sock, int protocol,
		       int kern)
Linus Torvalds's avatar
Linus Torvalds committed
266
267
268
269
270
271
272
{
	struct sock *sk;
	struct inet_protosw *answer;
	struct inet_sock *inet;
	struct proto *answer_prot;
	unsigned char answer_flags;
	char answer_no_check;
273
	int try_loading_module = 0;
274
	int err;
Linus Torvalds's avatar
Linus Torvalds committed
275

276
277
278
	if (unlikely(!inet_ehash_secret))
		if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
			build_ehash_secret();
279

Linus Torvalds's avatar
Linus Torvalds committed
280
281
282
	sock->state = SS_UNCONNECTED;

	/* Look for the requested type/protocol pair. */
283
lookup_protocol:
284
	err = -ESOCKTNOSUPPORT;
Linus Torvalds's avatar
Linus Torvalds committed
285
	rcu_read_lock();
286
	list_for_each_entry_rcu(answer, &inetsw[sock->type], list) {
Linus Torvalds's avatar
Linus Torvalds committed
287

288
		err = 0;
Linus Torvalds's avatar
Linus Torvalds committed
289
290
291
292
293
294
295
296
297
298
299
300
301
		/* Check the non-wild match. */
		if (protocol == answer->protocol) {
			if (protocol != IPPROTO_IP)
				break;
		} else {
			/* Check for the two wild cases. */
			if (IPPROTO_IP == protocol) {
				protocol = answer->protocol;
				break;
			}
			if (IPPROTO_IP == answer->protocol)
				break;
		}
302
		err = -EPROTONOSUPPORT;
Linus Torvalds's avatar
Linus Torvalds committed
303
304
	}

305
	if (unlikely(err)) {
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
		if (try_loading_module < 2) {
			rcu_read_unlock();
			/*
			 * Be more specific, e.g. net-pf-2-proto-132-type-1
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM)
			 */
			if (++try_loading_module == 1)
				request_module("net-pf-%d-proto-%d-type-%d",
					       PF_INET, protocol, sock->type);
			/*
			 * Fall back to generic, e.g. net-pf-2-proto-132
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP)
			 */
			else
				request_module("net-pf-%d-proto-%d",
					       PF_INET, protocol);
			goto lookup_protocol;
		} else
			goto out_rcu_unlock;
	}

Linus Torvalds's avatar
Linus Torvalds committed
327
	err = -EPERM;
328
	if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
Linus Torvalds's avatar
Linus Torvalds committed
329
330
		goto out_rcu_unlock;

331
332
333
334
	err = -EAFNOSUPPORT;
	if (!inet_netns_ok(net, protocol))
		goto out_rcu_unlock;

Linus Torvalds's avatar
Linus Torvalds committed
335
336
337
338
339
340
	sock->ops = answer->ops;
	answer_prot = answer->prot;
	answer_no_check = answer->no_check;
	answer_flags = answer->flags;
	rcu_read_unlock();

341
	WARN_ON(answer_prot->slab == NULL);
Linus Torvalds's avatar
Linus Torvalds committed
342
343

	err = -ENOBUFS;
344
	sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
Linus Torvalds's avatar
Linus Torvalds committed
345
346
347
348
349
350
351
352
353
	if (sk == NULL)
		goto out;

	err = 0;
	sk->sk_no_check = answer_no_check;
	if (INET_PROTOSW_REUSE & answer_flags)
		sk->sk_reuse = 1;

	inet = inet_sk(sk);
354
	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
Linus Torvalds's avatar
Linus Torvalds committed
355

356
357
	inet->nodefrag = 0;

Linus Torvalds's avatar
Linus Torvalds committed
358
	if (SOCK_RAW == sock->type) {
359
		inet->inet_num = protocol;
Linus Torvalds's avatar
Linus Torvalds committed
360
361
362
363
364
365
366
367
368
		if (IPPROTO_RAW == protocol)
			inet->hdrincl = 1;
	}

	if (ipv4_config.no_pmtu_disc)
		inet->pmtudisc = IP_PMTUDISC_DONT;
	else
		inet->pmtudisc = IP_PMTUDISC_WANT;

369
	inet->inet_id = 0;
Linus Torvalds's avatar
Linus Torvalds committed
370
371
372
373
374
375
376
377
378
379

	sock_init_data(sock, sk);

	sk->sk_destruct	   = inet_sock_destruct;
	sk->sk_protocol	   = protocol;
	sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;

	inet->uc_ttl	= -1;
	inet->mc_loop	= 1;
	inet->mc_ttl	= 1;
380
	inet->mc_all	= 1;
Linus Torvalds's avatar
Linus Torvalds committed
381
382
383
	inet->mc_index	= 0;
	inet->mc_list	= NULL;

384
	sk_refcnt_debug_inc(sk);
Linus Torvalds's avatar
Linus Torvalds committed
385

386
	if (inet->inet_num) {
Linus Torvalds's avatar
Linus Torvalds committed
387
388
389
390
391
		/* It assumes that any protocol which allows
		 * the user to assign a number at socket
		 * creation time automatically
		 * shares.
		 */
392
		inet->inet_sport = htons(inet->inet_num);
Linus Torvalds's avatar
Linus Torvalds committed
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
		/* Add to protocol hash chains. */
		sk->sk_prot->hash(sk);
	}

	if (sk->sk_prot->init) {
		err = sk->sk_prot->init(sk);
		if (err)
			sk_common_release(sk);
	}
out:
	return err;
out_rcu_unlock:
	rcu_read_unlock();
	goto out;
}


/*
 *	The peer socket should always be NULL (or else). When we call this
 *	function we are destroying the object and from then on nobody
 *	should refer to it.
 */
int inet_release(struct socket *sock)
{
	struct sock *sk = sock->sk;

	if (sk) {
		long timeout;

422
		sock_rps_reset_flow(sk);
Tom Herbert's avatar
Tom Herbert committed
423

Linus Torvalds's avatar
Linus Torvalds committed
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
		/* Applications forget to leave groups before exiting */
		ip_mc_drop_socket(sk);

		/* If linger is set, we don't return until the close
		 * is complete.  Otherwise we return immediately. The
		 * actually closing is done the same either way.
		 *
		 * If the close is due to the process exiting, we never
		 * linger..
		 */
		timeout = 0;
		if (sock_flag(sk, SOCK_LINGER) &&
		    !(current->flags & PF_EXITING))
			timeout = sk->sk_lingertime;
		sock->sk = NULL;
		sk->sk_prot->close(sk, timeout);
	}
	return 0;
}
Eric Dumazet's avatar
Eric Dumazet committed
443
EXPORT_SYMBOL(inet_release);
Linus Torvalds's avatar
Linus Torvalds committed
444
445

/* It is off by default, see below. */
446
int sysctl_ip_nonlocal_bind __read_mostly;
Eric Dumazet's avatar
Eric Dumazet committed
447
EXPORT_SYMBOL(sysctl_ip_nonlocal_bind);
Linus Torvalds's avatar
Linus Torvalds committed
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466

int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
	struct sock *sk = sock->sk;
	struct inet_sock *inet = inet_sk(sk);
	unsigned short snum;
	int chk_addr_ret;
	int err;

	/* If the socket has its own bind function then use it. (RAW) */
	if (sk->sk_prot->bind) {
		err = sk->sk_prot->bind(sk, uaddr, addr_len);
		goto out;
	}
	err = -EINVAL;
	if (addr_len < sizeof(struct sockaddr_in))
		goto out;

467
	chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
Linus Torvalds's avatar
Linus Torvalds committed
468
469
470
471
472
473
474
475
476
477

	/* Not specified by any standard per-se, however it breaks too
	 * many applications when removed.  It is unfortunate since
	 * allowing applications to make a non-local bind solves
	 * several problems with systems using dynamic addressing.
	 * (ie. your servers still start up even if your ISDN link
	 *  is temporarily down)
	 */
	err = -EADDRNOTAVAIL;
	if (!sysctl_ip_nonlocal_bind &&
478
	    !(inet->freebind || inet->transparent) &&
Al Viro's avatar
Al Viro committed
479
	    addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
Linus Torvalds's avatar
Linus Torvalds committed
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
	    chk_addr_ret != RTN_LOCAL &&
	    chk_addr_ret != RTN_MULTICAST &&
	    chk_addr_ret != RTN_BROADCAST)
		goto out;

	snum = ntohs(addr->sin_port);
	err = -EACCES;
	if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
		goto out;

	/*      We keep a pair of addresses. rcv_saddr is the one
	 *      used by hash lookups, and saddr is used for transmit.
	 *
	 *      In the BSD API these are the same except where it
	 *      would be illegal to use them (multicast/broadcast) in
	 *      which case the sending device address is used.
	 */
	lock_sock(sk);

	/* Check these errors (active socket, double bind). */
	err = -EINVAL;
501
	if (sk->sk_state != TCP_CLOSE || inet->inet_num)
Linus Torvalds's avatar
Linus Torvalds committed
502
503
		goto out_release_sock;

504
	inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr;
Linus Torvalds's avatar
Linus Torvalds committed
505
	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
506
		inet->inet_saddr = 0;  /* Use device */
Linus Torvalds's avatar
Linus Torvalds committed
507
508
509

	/* Make sure we are allowed to bind here. */
	if (sk->sk_prot->get_port(sk, snum)) {
510
		inet->inet_saddr = inet->inet_rcv_saddr = 0;
Linus Torvalds's avatar
Linus Torvalds committed
511
512
513
514
		err = -EADDRINUSE;
		goto out_release_sock;
	}

515
	if (inet->inet_rcv_saddr)
Linus Torvalds's avatar
Linus Torvalds committed
516
517
518
		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
	if (snum)
		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
519
520
521
	inet->inet_sport = htons(inet->inet_num);
	inet->inet_daddr = 0;
	inet->inet_dport = 0;
Linus Torvalds's avatar
Linus Torvalds committed
522
523
524
525
526
527
528
	sk_dst_reset(sk);
	err = 0;
out_release_sock:
	release_sock(sk);
out:
	return err;
}
Eric Dumazet's avatar
Eric Dumazet committed
529
EXPORT_SYMBOL(inet_bind);
Linus Torvalds's avatar
Linus Torvalds committed
530
531
532
533
534
535

int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr,
		       int addr_len, int flags)
{
	struct sock *sk = sock->sk;

536
537
	if (addr_len < sizeof(uaddr->sa_family))
		return -EINVAL;
Linus Torvalds's avatar
Linus Torvalds committed
538
539
540
	if (uaddr->sa_family == AF_UNSPEC)
		return sk->sk_prot->disconnect(sk, flags);

541
	if (!inet_sk(sk)->inet_num && inet_autobind(sk))
Linus Torvalds's avatar
Linus Torvalds committed
542
543
544
		return -EAGAIN;
	return sk->sk_prot->connect(sk, (struct sockaddr *)uaddr, addr_len);
}
Eric Dumazet's avatar
Eric Dumazet committed
545
EXPORT_SYMBOL(inet_dgram_connect);
Linus Torvalds's avatar
Linus Torvalds committed
546
547
548
549
550

static long inet_wait_for_connect(struct sock *sk, long timeo)
{
	DEFINE_WAIT(wait);

Eric Dumazet's avatar
Eric Dumazet committed
551
	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
Linus Torvalds's avatar
Linus Torvalds committed
552
553
554
555
556
557
558
559
560
561
562
563

	/* Basic assumption: if someone sets sk->sk_err, he _must_
	 * change state of the socket from TCP_SYN_*.
	 * Connect() does not allow to get error notifications
	 * without closing the socket.
	 */
	while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		release_sock(sk);
		timeo = schedule_timeout(timeo);
		lock_sock(sk);
		if (signal_pending(current) || !timeo)
			break;
Eric Dumazet's avatar
Eric Dumazet committed
564
		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
Linus Torvalds's avatar
Linus Torvalds committed
565
	}
Eric Dumazet's avatar
Eric Dumazet committed
566
	finish_wait(sk_sleep(sk), &wait);
Linus Torvalds's avatar
Linus Torvalds committed
567
568
569
570
571
572
573
574
575
576
577
578
579
580
	return timeo;
}

/*
 *	Connect to a remote host. There is regrettably still a little
 *	TCP 'magic' in here.
 */
int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
			int addr_len, int flags)
{
	struct sock *sk = sock->sk;
	int err;
	long timeo;

581
582
583
	if (addr_len < sizeof(uaddr->sa_family))
		return -EINVAL;

Linus Torvalds's avatar
Linus Torvalds committed
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
	lock_sock(sk);

	if (uaddr->sa_family == AF_UNSPEC) {
		err = sk->sk_prot->disconnect(sk, flags);
		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
		goto out;
	}

	switch (sock->state) {
	default:
		err = -EINVAL;
		goto out;
	case SS_CONNECTED:
		err = -EISCONN;
		goto out;
	case SS_CONNECTING:
		err = -EALREADY;
		/* Fall out of switch with err, set for this state */
		break;
	case SS_UNCONNECTED:
		err = -EISCONN;
		if (sk->sk_state != TCP_CLOSE)
			goto out;

		err = sk->sk_prot->connect(sk, uaddr, addr_len);
		if (err < 0)
			goto out;

612
		sock->state = SS_CONNECTING;
Linus Torvalds's avatar
Linus Torvalds committed
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657

		/* Just entered SS_CONNECTING state; the only
		 * difference is that return value in non-blocking
		 * case is EINPROGRESS, rather than EALREADY.
		 */
		err = -EINPROGRESS;
		break;
	}

	timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);

	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		/* Error code is set above */
		if (!timeo || !inet_wait_for_connect(sk, timeo))
			goto out;

		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			goto out;
	}

	/* Connection was closed by RST, timeout, ICMP error
	 * or another process disconnected us.
	 */
	if (sk->sk_state == TCP_CLOSE)
		goto sock_error;

	/* sk->sk_err may be not zero now, if RECVERR was ordered by user
	 * and error was received after socket entered established state.
	 * Hence, it is handled normally after connect() return successfully.
	 */

	sock->state = SS_CONNECTED;
	err = 0;
out:
	release_sock(sk);
	return err;

sock_error:
	err = sock_error(sk) ? : -ECONNABORTED;
	sock->state = SS_UNCONNECTED;
	if (sk->sk_prot->disconnect(sk, flags))
		sock->state = SS_DISCONNECTING;
	goto out;
}
Eric Dumazet's avatar
Eric Dumazet committed
658
EXPORT_SYMBOL(inet_stream_connect);
Linus Torvalds's avatar
Linus Torvalds committed
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674

/*
 *	Accept a pending connection. The TCP layer now gives BSD semantics.
 */

int inet_accept(struct socket *sock, struct socket *newsock, int flags)
{
	struct sock *sk1 = sock->sk;
	int err = -EINVAL;
	struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err);

	if (!sk2)
		goto do_err;

	lock_sock(sk2);

675
676
	WARN_ON(!((1 << sk2->sk_state) &
		  (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE)));
Linus Torvalds's avatar
Linus Torvalds committed
677
678
679
680
681
682
683
684
685

	sock_graft(sk2, newsock);

	newsock->state = SS_CONNECTED;
	err = 0;
	release_sock(sk2);
do_err:
	return err;
}
Eric Dumazet's avatar
Eric Dumazet committed
686
EXPORT_SYMBOL(inet_accept);
Linus Torvalds's avatar
Linus Torvalds committed
687
688
689
690
691
692
693
694
695
696


/*
 *	This does both peername and sockname.
 */
int inet_getname(struct socket *sock, struct sockaddr *uaddr,
			int *uaddr_len, int peer)
{
	struct sock *sk		= sock->sk;
	struct inet_sock *inet	= inet_sk(sk);
697
	DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr);
Linus Torvalds's avatar
Linus Torvalds committed
698
699
700

	sin->sin_family = AF_INET;
	if (peer) {
701
		if (!inet->inet_dport ||
Linus Torvalds's avatar
Linus Torvalds committed
702
703
704
		    (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) &&
		     peer == 1))
			return -ENOTCONN;
705
706
		sin->sin_port = inet->inet_dport;
		sin->sin_addr.s_addr = inet->inet_daddr;
Linus Torvalds's avatar
Linus Torvalds committed
707
	} else {
708
		__be32 addr = inet->inet_rcv_saddr;
Linus Torvalds's avatar
Linus Torvalds committed
709
		if (!addr)
710
711
			addr = inet->inet_saddr;
		sin->sin_port = inet->inet_sport;
Linus Torvalds's avatar
Linus Torvalds committed
712
713
714
715
716
717
		sin->sin_addr.s_addr = addr;
	}
	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
	*uaddr_len = sizeof(*sin);
	return 0;
}
Eric Dumazet's avatar
Eric Dumazet committed
718
EXPORT_SYMBOL(inet_getname);
Linus Torvalds's avatar
Linus Torvalds committed
719
720
721
722
723
724

int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
		 size_t size)
{
	struct sock *sk = sock->sk;

725
	sock_rps_record_flow(sk);
Tom Herbert's avatar
Tom Herbert committed
726

Linus Torvalds's avatar
Linus Torvalds committed
727
	/* We may need to bind the socket. */
728
729
	if (!inet_sk(sk)->inet_num && !sk->sk_prot->no_autobind &&
	    inet_autobind(sk))
Linus Torvalds's avatar
Linus Torvalds committed
730
731
732
733
		return -EAGAIN;

	return sk->sk_prot->sendmsg(iocb, sk, msg, size);
}
Eric Dumazet's avatar
Eric Dumazet committed
734
EXPORT_SYMBOL(inet_sendmsg);
Linus Torvalds's avatar
Linus Torvalds committed
735

736
737
ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
		      size_t size, int flags)
Linus Torvalds's avatar
Linus Torvalds committed
738
739
740
{
	struct sock *sk = sock->sk;

741
	sock_rps_record_flow(sk);
Tom Herbert's avatar
Tom Herbert committed
742

Linus Torvalds's avatar
Linus Torvalds committed
743
	/* We may need to bind the socket. */
744
745
	if (!inet_sk(sk)->inet_num && !sk->sk_prot->no_autobind &&
	    inet_autobind(sk))
Linus Torvalds's avatar
Linus Torvalds committed
746
747
748
749
750
751
		return -EAGAIN;

	if (sk->sk_prot->sendpage)
		return sk->sk_prot->sendpage(sk, page, offset, size, flags);
	return sock_no_sendpage(sock, page, offset, size, flags);
}
752
EXPORT_SYMBOL(inet_sendpage);
Linus Torvalds's avatar
Linus Torvalds committed
753

Tom Herbert's avatar
Tom Herbert committed
754
755
756
757
758
759
760
int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
		 size_t size, int flags)
{
	struct sock *sk = sock->sk;
	int addr_len = 0;
	int err;

761
	sock_rps_record_flow(sk);
Tom Herbert's avatar
Tom Herbert committed
762
763
764
765
766
767
768
769

	err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
				   flags & ~MSG_DONTWAIT, &addr_len);
	if (err >= 0)
		msg->msg_namelen = addr_len;
	return err;
}
EXPORT_SYMBOL(inet_recvmsg);
Linus Torvalds's avatar
Linus Torvalds committed
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823

int inet_shutdown(struct socket *sock, int how)
{
	struct sock *sk = sock->sk;
	int err = 0;

	/* This should really check to make sure
	 * the socket is a TCP socket. (WHY AC...)
	 */
	how++; /* maps 0->1 has the advantage of making bit 1 rcvs and
		       1->2 bit 2 snds.
		       2->3 */
	if ((how & ~SHUTDOWN_MASK) || !how)	/* MAXINT->0 */
		return -EINVAL;

	lock_sock(sk);
	if (sock->state == SS_CONNECTING) {
		if ((1 << sk->sk_state) &
		    (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
			sock->state = SS_DISCONNECTING;
		else
			sock->state = SS_CONNECTED;
	}

	switch (sk->sk_state) {
	case TCP_CLOSE:
		err = -ENOTCONN;
		/* Hack to wake up other listeners, who can poll for
		   POLLHUP, even on eg. unconnected UDP sockets -- RR */
	default:
		sk->sk_shutdown |= how;
		if (sk->sk_prot->shutdown)
			sk->sk_prot->shutdown(sk, how);
		break;

	/* Remaining two branches are temporary solution for missing
	 * close() in multithreaded environment. It is _not_ a good idea,
	 * but we have no choice until close() is repaired at VFS level.
	 */
	case TCP_LISTEN:
		if (!(how & RCV_SHUTDOWN))
			break;
		/* Fall through */
	case TCP_SYN_SENT:
		err = sk->sk_prot->disconnect(sk, O_NONBLOCK);
		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
		break;
	}

	/* Wake up anyone sleeping in poll. */
	sk->sk_state_change(sk);
	release_sock(sk);
	return err;
}
Eric Dumazet's avatar
Eric Dumazet committed
824
EXPORT_SYMBOL(inet_shutdown);
Linus Torvalds's avatar
Linus Torvalds committed
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839

/*
 *	ioctl() calls you can issue on an INET socket. Most of these are
 *	device configuration and stuff and very rarely used. Some ioctls
 *	pass on to the socket itself.
 *
 *	NOTE: I like the idea of a module for the config stuff. ie ifconfig
 *	loads the devconfigure module does its configuring and unloads it.
 *	There's a good 20K of config code hanging around the kernel.
 */

int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	struct sock *sk = sock->sk;
	int err = 0;
840
	struct net *net = sock_net(sk);
Linus Torvalds's avatar
Linus Torvalds committed
841
842

	switch (cmd) {
Eric Dumazet's avatar
Eric Dumazet committed
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
	case SIOCGSTAMP:
		err = sock_get_timestamp(sk, (struct timeval __user *)arg);
		break;
	case SIOCGSTAMPNS:
		err = sock_get_timestampns(sk, (struct timespec __user *)arg);
		break;
	case SIOCADDRT:
	case SIOCDELRT:
	case SIOCRTMSG:
		err = ip_rt_ioctl(net, cmd, (void __user *)arg);
		break;
	case SIOCDARP:
	case SIOCGARP:
	case SIOCSARP:
		err = arp_ioctl(net, cmd, (void __user *)arg);
		break;
	case SIOCGIFADDR:
	case SIOCSIFADDR:
	case SIOCGIFBRDADDR:
	case SIOCSIFBRDADDR:
	case SIOCGIFNETMASK:
	case SIOCSIFNETMASK:
	case SIOCGIFDSTADDR:
	case SIOCSIFDSTADDR:
	case SIOCSIFPFLAGS:
	case SIOCGIFPFLAGS:
	case SIOCSIFFLAGS:
		err = devinet_ioctl(net, cmd, (void __user *)arg);
		break;
	default:
		if (sk->sk_prot->ioctl)
			err = sk->sk_prot->ioctl(sk, cmd, arg);
		else
			err = -ENOIOCTLCMD;
		break;
Linus Torvalds's avatar
Linus Torvalds committed
878
879
880
	}
	return err;
}
Eric Dumazet's avatar
Eric Dumazet committed
881
EXPORT_SYMBOL(inet_ioctl);
Linus Torvalds's avatar
Linus Torvalds committed
882

883
884
885
886
887
888
889
890
891
892
893
894
895
#ifdef CONFIG_COMPAT
int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	struct sock *sk = sock->sk;
	int err = -ENOIOCTLCMD;

	if (sk->sk_prot->compat_ioctl)
		err = sk->sk_prot->compat_ioctl(sk, cmd, arg);

	return err;
}
#endif

896
const struct proto_ops inet_stream_ops = {
897
898
899
900
901
902
903
904
905
906
907
908
909
910
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_stream_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = inet_accept,
	.getname	   = inet_getname,
	.poll		   = tcp_poll,
	.ioctl		   = inet_ioctl,
	.listen		   = inet_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
911
	.sendmsg	   = inet_sendmsg,
Tom Herbert's avatar
Tom Herbert committed
912
	.recvmsg	   = inet_recvmsg,
913
	.mmap		   = sock_no_mmap,
914
	.sendpage	   = inet_sendpage,
Jens Axboe's avatar
Jens Axboe committed
915
	.splice_read	   = tcp_splice_read,
916
#ifdef CONFIG_COMPAT
917
918
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
919
	.compat_ioctl	   = inet_compat_ioctl,
920
#endif
Linus Torvalds's avatar
Linus Torvalds committed
921
};
Eric Dumazet's avatar
Eric Dumazet committed
922
EXPORT_SYMBOL(inet_stream_ops);
Linus Torvalds's avatar
Linus Torvalds committed
923

924
const struct proto_ops inet_dgram_ops = {
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_dgram_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = sock_no_accept,
	.getname	   = inet_getname,
	.poll		   = udp_poll,
	.ioctl		   = inet_ioctl,
	.listen		   = sock_no_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
Tom Herbert's avatar
Tom Herbert committed
940
	.recvmsg	   = inet_recvmsg,
941
942
	.mmap		   = sock_no_mmap,
	.sendpage	   = inet_sendpage,
943
#ifdef CONFIG_COMPAT
944
945
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
946
	.compat_ioctl	   = inet_compat_ioctl,
947
#endif
Linus Torvalds's avatar
Linus Torvalds committed
948
};
Eric Dumazet's avatar
Eric Dumazet committed
949
EXPORT_SYMBOL(inet_dgram_ops);
Linus Torvalds's avatar
Linus Torvalds committed
950
951
952
953
954

/*
 * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
 * udp_poll
 */
955
static const struct proto_ops inet_sockraw_ops = {
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_dgram_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = sock_no_accept,
	.getname	   = inet_getname,
	.poll		   = datagram_poll,
	.ioctl		   = inet_ioctl,
	.listen		   = sock_no_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
Tom Herbert's avatar
Tom Herbert committed
971
	.recvmsg	   = inet_recvmsg,
972
973
	.mmap		   = sock_no_mmap,
	.sendpage	   = inet_sendpage,
974
#ifdef CONFIG_COMPAT
975
976
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
977
	.compat_ioctl	   = inet_compat_ioctl,
978
#endif
Linus Torvalds's avatar
Linus Torvalds committed
979
980
};

981
static const struct net_proto_family inet_family_ops = {
Linus Torvalds's avatar
Linus Torvalds committed
982
983
984
985
986
987
988
989
990
991
	.family = PF_INET,
	.create = inet_create,
	.owner	= THIS_MODULE,
};

/* Upon startup we insert all the elements in inetsw_array[] into
 * the linked list inetsw.
 */
static struct inet_protosw inetsw_array[] =
{
992
993
994
995
996
997
998
	{
		.type =       SOCK_STREAM,
		.protocol =   IPPROTO_TCP,
		.prot =       &tcp_prot,
		.ops =        &inet_stream_ops,
		.no_check =   0,
		.flags =      INET_PROTOSW_PERMANENT |
999
			      INET_PROTOSW_ICSK,
1000
1001
1002
1003
1004
1005
1006
1007
1008
	},

	{
		.type =       SOCK_DGRAM,
		.protocol =   IPPROTO_UDP,
		.prot =       &udp_prot,
		.ops =        &inet_dgram_ops,
		.no_check =   UDP_CSUM_DEFAULT,
		.flags =      INET_PROTOSW_PERMANENT,
Linus Torvalds's avatar
Linus Torvalds committed
1009
       },
1010

Linus Torvalds's avatar
Linus Torvalds committed
1011
1012

       {
1013
1014
1015
1016
1017
1018
	       .type =       SOCK_RAW,
	       .protocol =   IPPROTO_IP,	/* wild card */
	       .prot =       &raw_prot,
	       .ops =        &inet_sockraw_ops,
	       .no_check =   UDP_CSUM_DEFAULT,
	       .flags =      INET_PROTOSW_REUSE,
Linus Torvalds's avatar
Linus Torvalds committed
1019
1020
1021
       }
};

1022
#define INETSW_ARRAY_LEN ARRAY_SIZE(inetsw_array)
Linus Torvalds's avatar
Linus Torvalds committed
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056

void inet_register_protosw(struct inet_protosw *p)
{
	struct list_head *lh;
	struct inet_protosw *answer;
	int protocol = p->protocol;
	struct list_head *last_perm;

	spin_lock_bh(&inetsw_lock);

	if (p->type >= SOCK_MAX)
		goto out_illegal;

	/* If we are trying to override a permanent protocol, bail. */
	answer = NULL;
	last_perm = &inetsw[p->type];
	list_for_each(lh, &inetsw[p->type]) {
		answer = list_entry(lh, struct inet_protosw, list);

		/* Check only the non-wild match. */
		if (INET_PROTOSW_PERMANENT & answer->flags) {
			if (protocol == answer->protocol)
				break;
			last_perm = lh;
		}

		answer = NULL;
	}
	if (answer)
		goto out_permanent;

	/* Add the new entry after the last permanent entry if any, so that
	 * the new entry does not override a permanent entry when matched with
	 * a wild-card protocol. But it is allowed to override any existing
1057
	 * non-permanent entry.  This means that when we remove this entry, the
Linus Torvalds's avatar
Linus Torvalds committed
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
	 * system automatically returns to the old behavior.
	 */
	list_add_rcu(&p->list, last_perm);
out:
	spin_unlock_bh(&inetsw_lock);

	return;

out_permanent:
	printk(KERN_ERR "Attempt to override permanent protocol %d.\n",
	       protocol);
	goto out;

out_illegal:
	printk(KERN_ERR
	       "Ignoring attempt to register invalid socket type %d.\n",
	       p->type);
	goto out;
}
Eric Dumazet's avatar
Eric Dumazet committed
1077
EXPORT_SYMBOL(inet_register_protosw);
Linus Torvalds's avatar
Linus Torvalds committed
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092

void inet_unregister_protosw(struct inet_protosw *p)
{
	if (INET_PROTOSW_PERMANENT & p->flags) {
		printk(KERN_ERR
		       "Attempt to unregister permanent protocol %d.\n",
		       p->protocol);
	} else {
		spin_lock_bh(&inetsw_lock);
		list_del_rcu(&p->list);
		spin_unlock_bh(&inetsw_lock);

		synchronize_net();
	}
}
Eric Dumazet's avatar
Eric Dumazet committed
1093
EXPORT_SYMBOL(inet_unregister_protosw);
Linus Torvalds's avatar
Linus Torvalds committed
1094

1095
1096
1097
1098
/*
 *      Shall we try to damage output packets if routing dev changes?
 */

1099
int sysctl_ip_dynaddr __read_mostly;
1100
1101
1102
1103

static int inet_sk_reselect_saddr(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
1104
1105
	__be32 old_saddr = inet->inet_saddr;
	__be32 daddr = inet->inet_daddr;
1106
1107
	struct rtable *rt;
	__be32 new_saddr;
1108
1109
1110
1111
1112

	if (inet->opt && inet->opt->srr)
		daddr = inet->opt->faddr;

	/* Query new route. */
1113
1114
1115
1116
1117
	rt = ip_route_connect(daddr, 0, RT_CONN_FLAGS(sk),
			      sk->sk_bound_dev_if, sk->sk_protocol,
			      inet->inet_sport, inet->inet_dport, sk, false);
	if (IS_ERR(rt))
		return PTR_ERR(rt);
1118

1119
	sk_setup_caps(sk, &rt->dst);
1120
1121
1122
1123
1124
1125
1126

	new_saddr = rt->rt_src;

	if (new_saddr == old_saddr)
		return 0;

	if (sysctl_ip_dynaddr > 1) {
1127
1128
		printk(KERN_INFO "%s(): shifting inet->saddr from %pI4 to %pI4\n",
		       __func__, &old_saddr, &new_saddr);
1129
1130
	}

1131
	inet->inet_saddr = inet->inet_rcv_saddr = new_saddr;
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148

	/*
	 * XXX The only one ugly spot where we need to
	 * XXX really change the sockets identity after
	 * XXX it has entered the hashes. -DaveM
	 *
	 * Besides that, it does not check for connection
	 * uniqueness. Wait for troubles.
	 */
	__sk_prot_rehash(sk);
	return 0;
}

int inet_sk_rebuild_header(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
	struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0);
1149
	__be32 daddr;
1150
1151
1152
1153
1154
1155
1156
	int err;

	/* Route is OK, nothing to do. */
	if (rt)
		return 0;

	/* Reroute. */
1157
	daddr = inet->inet_daddr;
1158
1159
	if (inet->opt && inet->opt->srr)
		daddr = inet->opt->faddr;
1160
	{
1161
1162
	struct flowi fl = {
		.oif = sk->sk_bound_dev_if,
1163
		.mark = sk->sk_mark,
1164
1165
1166
		.fl4_dst = daddr,
		.fl4_src = inet->inet_saddr,
		.fl4_tos = RT_CONN_FLAGS(sk),
1167
		.proto = sk->sk_protocol,
1168
		.flags = inet_sk_flowi_flags(sk),
1169
1170
		.fl_ip_sport = inet->inet_sport,
		.fl_ip_dport = inet->inet_dport,
1171
	};
1172

1173
	security_sk_classify_flow(sk, &fl);
1174
1175
1176
1177
	rt = ip_route_output_flow(sock_net(sk), &fl, sk);
	}
	if (!IS_ERR(rt)) {
		err = 0;
1178
		sk_setup_caps(sk, &rt->dst);
1179
1180
1181
	} else {
		err = PTR_ERR(rt);

1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
		/* Routing failed... */
		sk->sk_route_caps = 0;
		/*
		 * Other protocols have to map its equivalent state to TCP_SYN_SENT.
		 * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme
		 */
		if (!sysctl_ip_dynaddr ||
		    sk->sk_state != TCP_SYN_SENT ||
		    (sk->sk_userlocks & SOCK_BINDADDR_LOCK) ||
		    (err = inet_sk_reselect_saddr(sk)) != 0)
			sk->sk_err_soft = -err;
	}

	return err;
}
EXPORT_SYMBOL(inet_sk_rebuild_header);

1199
1200
1201
static int inet_gso_send_check(struct sk_buff *skb)
{
	struct iphdr *iph;
1202
	const struct net_protocol *ops;
1203
1204
1205
1206
1207
1208
1209
	int proto;
	int ihl;
	int err = -EINVAL;

	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
		goto out;

1210
	iph = ip_hdr(skb);
1211
1212
1213
1214
1215
1216
1217
	ihl = iph->ihl * 4;
	if (ihl < sizeof(*iph))
		goto out;

	if (unlikely(!pskb_may_pull(skb, ihl)))
		goto out;

1218
1219
	__skb_pull(skb, ihl);
	skb_reset_transport_header(skb);
1220
	iph = ip_hdr(skb);
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
	proto = iph->protocol & (MAX_INET_PROTOS - 1);
	err = -EPROTONOSUPPORT;

	rcu_read_lock();
	ops = rcu_dereference(inet_protos[proto]);
	if (likely(ops && ops->gso_send_check))
		err = ops->gso_send_check(skb);
	rcu_read_unlock();

out:
	return err;
}

1234
static struct sk_buff *inet_gso_segment(struct sk_buff *skb, u32 features)
Herbert Xu's avatar
Herbert Xu committed
1235
1236
1237
{
	struct sk_buff *segs = ERR_PTR(-EINVAL);
	struct iphdr *iph;
1238
	const struct net_protocol *ops;
Herbert Xu's avatar
Herbert Xu committed
1239
1240
1241
	int proto;
	int ihl;
	int id;
1242
	unsigned int offset = 0;
Herbert Xu's avatar
Herbert Xu committed
1243

1244
1245
1246
	if (!(features & NETIF_F_V4_CSUM))
		features &= ~NETIF_F_SG;

1247
1248
1249
1250
1251
1252
1253
1254
1255
	if (unlikely(skb_shinfo(skb)->gso_type &
		     ~(SKB_GSO_TCPV4 |
		       SKB_GSO_UDP |
		       SKB_GSO_DODGY |
		       SKB_GSO_TCP_ECN |
		       0)))
		goto out;

	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
Herbert Xu's avatar
Herbert Xu committed
1256
1257
		goto out;

1258
	iph = ip_hdr(skb);
Herbert Xu's avatar
Herbert Xu committed
1259
1260
1261
1262
	ihl = iph->ihl * 4;
	if (ihl < sizeof(*iph))
		goto out;

1263
	if (unlikely(!pskb_may_pull(skb, ihl)))
Herbert Xu's avatar
Herbert Xu committed
1264
1265
		goto out;

1266
1267
	__skb_pull(skb, ihl);
	skb_reset_transport_header(skb);
1268
	iph = ip_hdr(skb);
Herbert Xu's avatar
Herbert Xu committed
1269
1270
1271
1272
1273
1274
	id = ntohs(iph->id);
	proto = iph->protocol & (MAX_INET_PROTOS - 1);
	segs = ERR_PTR(-EPROTONOSUPPORT);

	rcu_read_lock();
	ops = rcu_dereference(inet_protos[proto]);
1275
	if (likely(ops && ops->gso_segment))
1276
		segs = ops->gso_segment(skb, features);
Herbert Xu's avatar
Herbert Xu committed
1277
1278
	rcu_read_unlock();

1279
	if (!segs || IS_ERR(segs))
Herbert Xu's avatar
Herbert Xu committed
1280
1281
1282
1283
		goto out;

	skb = segs;
	do {
1284
		iph = ip_hdr(skb);
1285
1286
1287
1288
1289
1290
1291
1292
		if (proto == IPPROTO_UDP) {
			iph->id = htons(id);
			iph->frag_off = htons(offset >> 3);
			if (skb->next != NULL)
				iph->frag_off |= htons(IP_MF);
			offset += (skb->len - skb->mac_len - iph->ihl * 4);
		} else
			iph->id = htons(id++);
Herbert Xu's avatar
Herbert Xu committed
1293
1294
		iph->tot_len = htons(skb->len - skb->mac_len);
		iph->check = 0;
1295
		iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl);
Herbert Xu's avatar
Herbert Xu committed
1296
1297
1298
1299
1300
1301
	} while ((skb = skb->next));

out:
	return segs;
}

Herbert Xu's avatar
Herbert Xu committed
1302
1303
1304
static struct sk_buff **inet_gro_receive(struct sk_buff **head,
					 struct sk_buff *skb)
{
1305
	const struct net_protocol *ops;
Herbert Xu's avatar
Herbert Xu committed
1306
1307
1308
	struct sk_buff **pp = NULL;
	struct sk_buff *p;
	struct iphdr *iph;
1309
1310
	unsigned int hlen;
	unsigned int off;
1311
	unsigned int id;
Herbert Xu's avatar
Herbert Xu committed
1312
1313
1314
	int flush = 1;
	int proto;

1315
1316
1317
1318
1319
1320
1321
1322
	off = skb_gro_offset(skb);
	hlen = off + sizeof(*iph);
	iph = skb_gro_header_fast(skb, off);
	if (skb_gro_header_hard(skb, hlen)) {
		iph = skb_gro_header_slow(skb, hlen, off);
		if (unlikely(!iph))
			goto out;
	}
Herbert Xu's avatar
Herbert Xu committed
1323
1324
1325
1326
1327
1328
1329
1330

	proto = iph->protocol & (MAX_INET_PROTOS - 1);

	rcu_read_lock();
	ops = rcu_dereference(inet_protos[proto]);
	if (!ops || !ops->gro_receive)
		goto out_unlock;

1331
	if (*(u8 *)iph != 0x45)
Herbert Xu's avatar
Herbert Xu committed
1332
1333
1334
1335
1336
		goto out_unlock;

	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
		goto out_unlock;

1337
1338
	id = ntohl(*(__be32 *)&iph->id);
	flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
1339
	id >>= 16;
Herbert Xu's avatar
Herbert Xu committed
1340
1341
1342
1343
1344
1345
1346
1347
1348

	for (p = *head; p; p = p->next) {
		struct iphdr *iph2;

		if (!NAPI_GRO_CB(p)->same_flow)
			continue;

		iph2 = ip_hdr(p);

1349
1350
		if ((iph->protocol ^ iph2->protocol) |
		    (iph->tos ^ iph2->tos) |
1351
1352
		    ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) |
		    ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) {
Herbert Xu's avatar
Herbert Xu committed
1353
1354
1355
1356
1357
1358
			NAPI_GRO_CB(p)->same_flow = 0;
			continue;
		}

		/* All fields must match except length and checksum. */
		NAPI_GRO_CB(p)->flush |=
1359
1360
			(iph->ttl ^ iph2->ttl) |
			((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
Herbert Xu's avatar
Herbert Xu committed
1361
1362
1363
1364
1365

		NAPI_GRO_CB(p)->flush |= flush;
	}

	NAPI_GRO_CB(skb)->flush |= flush;
1366
1367
	skb_gro_pull(skb, sizeof(*iph));
	skb_set_transport_header(skb, skb_gro_offset(skb));
Herbert Xu's avatar
Herbert Xu committed
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381

	pp = ops->gro_receive(head, skb);

out_unlock:
	rcu_read_unlock();

out:
	NAPI_GRO_CB(skb)->flush |= flush;

	return pp;
}

static int inet_gro_complete(struct sk_buff *skb)
{
1382
	const struct net_protocol *ops;
Herbert Xu's avatar
Herbert Xu committed
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
	struct iphdr *iph = ip_hdr(skb);
	int proto = iph->protocol & (MAX_INET_PROTOS - 1);
	int err = -ENOSYS;
	__be16 newlen = htons(skb->len - skb_network_offset(skb));

	csum_replace2(&iph->check, iph->tot_len, newlen);
	iph->tot_len = newlen;

	rcu_read_lock();
	ops = rcu_dereference(inet_protos[proto]);
	if (WARN_ON(!ops || !ops->gro_complete))
		goto out_unlock;

	err = ops->gro_complete(skb);

out_unlock:
	rcu_read_unlock();

	return err;
}

1404
int inet_ctl_sock_create(struct sock **sk, unsigned short family,
1405
1406
			 unsigned short type, unsigned char protocol,
			 struct net *net)
1407
{
1408
1409
	struct socket *sock;
	int rc = sock_create_kern(family, type, protocol, &sock);
1410
1411

	if (rc == 0) {
1412
1413
		*sk = sock->sk;
		(*sk)->sk_allocation = GFP_ATOMIC;
1414
1415
1416
1417
		/*
		 * Unhash it so that IP input processing does not even see it,
		 * we do not wish this socket to see incoming packets.
		 */
1418
		(*sk)->sk_prot->unhash(*sk);
1419
1420

		sk_change_net(*sk, net);
1421
1422
1423
1424
1425
	}
	return rc;
}
EXPORT_SYMBOL_GPL(inet_ctl_sock_create);

1426
unsigned long snmp_fold_field(void __percpu *mib[], int offt)
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
{
	unsigned long res = 0;
	int i;

	for_each_possible_cpu(i) {
		res += *(((unsigned long *) per_cpu_ptr(mib[0], i)) + offt);
		res += *(((unsigned long *) per_cpu_ptr(mib[1], i)) + offt);
	}
	return res;
}
EXPORT_SYMBOL_GPL(snmp_fold_field);

1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
#if BITS_PER_LONG==32

u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset)
{
	u64 res = 0;
	int cpu;

	for_each_possible_cpu(cpu) {
		void *bhptr, *userptr;
		struct u64_stats_sync *syncp;
		u64 v_bh, v_user;
		unsigned int start;

		/* first mib used by softirq context, we must use _bh() accessors */
		bhptr = per_cpu_ptr(SNMP_STAT_BHPTR(mib), cpu);
		syncp = (struct u64_stats_sync *)(bhptr + syncp_offset);
		do {
			start = u64_stats_fetch_begin_bh(syncp);
			v_bh = *(((u64 *) bhptr) + offt);
		} while (u64_stats_fetch_retry_bh(syncp, start));

		/* second mib used in USER context */
		userptr = per_cpu_ptr(SNMP_STAT_USRPTR(mib), cpu);
		syncp = (struct u64_stats_sync *)(userptr + syncp_offset);
		do {
			start = u64_stats_fetch_begin(syncp);
			v_user = *(((u64 *) userptr) + offt);
		} while (u64_stats_fetch_retry(syncp, start));

		res += v_bh + v_user;
	}
	return res;
}
EXPORT_SYMBOL_GPL(snmp_fold_field64);
#endif

1475
int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align)
1476
1477
{
	BUG_ON(ptr == NULL);
1478
	ptr[0] = __alloc_percpu(mibsize, align);
1479
1480
	if (!ptr[0])
		goto err0;
1481
	ptr[1] = __alloc_percpu(mibsize, align);
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
	if (!ptr[1])
		goto err1;
	return 0;
err1:
	free_percpu(ptr[0]);
	ptr[0] = NULL;
err0:
	return -ENOMEM;
}
EXPORT_SYMBOL_GPL(snmp_mib_init);

1493
void snmp_mib_free(void __percpu *ptr[2])
1494
1495
1496
1497
1498
1499
1500
1501
{
	BUG_ON(ptr == NULL);
	free_percpu(ptr[0]);
	free_percpu(ptr[1]);
	ptr[0] = ptr[1] = NULL;
}
EXPORT_SYMBOL_GPL(snmp_mib_free);

Linus Torvalds's avatar
Linus Torvalds committed
1502
#ifdef CONFIG_IP_MULTICAST
1503
static const struct net_protocol igmp_protocol = {
Linus Torvalds's avatar
Linus Torvalds committed
1504
	.handler =	igmp_rcv,
1505
	.netns_ok =	1,
Linus Torvalds's avatar
Linus Torvalds committed
1506
1507
1508
};
#endif

1509
static const struct net_protocol tcp_protocol = {
Linus Torvalds's avatar
Linus Torvalds committed
1510
1511
	.handler =	tcp_v4_rcv,
	.err_handler =	tcp_v4_err,
1512
	.gso_send_check = tcp_v4_gso_send_check,
Herbert Xu's avatar
Herbert Xu committed
1513
	.gso_segment =	tcp_tso_segment,
Herbert Xu's avatar
Herbert Xu committed
1514
1515
	.gro_receive =	tcp4_gro_receive,
	.gro_complete =	tcp4_gro_complete,
Linus Torvalds's avatar
Linus Torvalds committed
1516
	.no_policy =	1,
1517
	.netns_ok =	1,
Linus Torvalds's avatar
Linus Torvalds committed
1518
1519
};

1520
static const struct net_protocol udp_protocol = {
Linus Torvalds's avatar
Linus Torvalds committed