tcp.c 59.4 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
4
5
6
7
8
9
/*
 * 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.
 *
 *		Implementation of the Transmission Control Protocol(TCP).
 *
 * Version:	$Id: tcp.c,v 1.216 2002/02/01 22:01:04 davem Exp $
 *
10
 * Authors:	Ross Biro
Linus Torvalds's avatar
Linus Torvalds committed
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
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Mark Evans, <evansmp@uhura.aston.ac.uk>
 *		Corey Minyard <wf-rch!minyard@relay.EU.net>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
 *		Linus Torvalds, <torvalds@cs.helsinki.fi>
 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
 *		Matthew Dillon, <dillon@apollo.west.oic.com>
 *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
 *		Jorge Cwik, <jorge@laser.satlink.net>
 *
 * Fixes:
 *		Alan Cox	:	Numerous verify_area() calls
 *		Alan Cox	:	Set the ACK bit on a reset
 *		Alan Cox	:	Stopped it crashing if it closed while
 *					sk->inuse=1 and was trying to connect
 *					(tcp_err()).
 *		Alan Cox	:	All icmp error handling was broken
 *					pointers passed where wrong and the
 *					socket was looked up backwards. Nobody
 *					tested any icmp error code obviously.
 *		Alan Cox	:	tcp_err() now handled properly. It
 *					wakes people on errors. poll
 *					behaves and the icmp error race
 *					has gone by moving it into sock.c
 *		Alan Cox	:	tcp_send_reset() fixed to work for
 *					everything not just packets for
 *					unknown sockets.
 *		Alan Cox	:	tcp option processing.
 *		Alan Cox	:	Reset tweaked (still not 100%) [Had
 *					syn rule wrong]
 *		Herp Rosmanith  :	More reset fixes
 *		Alan Cox	:	No longer acks invalid rst frames.
 *					Acking any kind of RST is right out.
 *		Alan Cox	:	Sets an ignore me flag on an rst
 *					receive otherwise odd bits of prattle
 *					escape still
 *		Alan Cox	:	Fixed another acking RST frame bug.
 *					Should stop LAN workplace lockups.
 *		Alan Cox	: 	Some tidyups using the new skb list
 *					facilities
 *		Alan Cox	:	sk->keepopen now seems to work
 *		Alan Cox	:	Pulls options out correctly on accepts
 *		Alan Cox	:	Fixed assorted sk->rqueue->next errors
 *		Alan Cox	:	PSH doesn't end a TCP read. Switched a
 *					bit to skb ops.
 *		Alan Cox	:	Tidied tcp_data to avoid a potential
 *					nasty.
 *		Alan Cox	:	Added some better commenting, as the
 *					tcp is hard to follow
 *		Alan Cox	:	Removed incorrect check for 20 * psh
 *	Michael O'Reilly	:	ack < copied bug fix.
 *	Johannes Stille		:	Misc tcp fixes (not all in yet).
 *		Alan Cox	:	FIN with no memory -> CRASH
 *		Alan Cox	:	Added socket option proto entries.
 *					Also added awareness of them to accept.
 *		Alan Cox	:	Added TCP options (SOL_TCP)
 *		Alan Cox	:	Switched wakeup calls to callbacks,
 *					so the kernel can layer network
 *					sockets.
 *		Alan Cox	:	Use ip_tos/ip_ttl settings.
 *		Alan Cox	:	Handle FIN (more) properly (we hope).
 *		Alan Cox	:	RST frames sent on unsynchronised
 *					state ack error.
 *		Alan Cox	:	Put in missing check for SYN bit.
 *		Alan Cox	:	Added tcp_select_window() aka NET2E
 *					window non shrink trick.
 *		Alan Cox	:	Added a couple of small NET2E timer
 *					fixes
 *		Charles Hedrick :	TCP fixes
 *		Toomas Tamm	:	TCP window fixes
 *		Alan Cox	:	Small URG fix to rlogin ^C ack fight
 *		Charles Hedrick	:	Rewrote most of it to actually work
 *		Linus		:	Rewrote tcp_read() and URG handling
 *					completely
 *		Gerhard Koerting:	Fixed some missing timer handling
 *		Matthew Dillon  :	Reworked TCP machine states as per RFC
 *		Gerhard Koerting:	PC/TCP workarounds
 *		Adam Caldwell	:	Assorted timer/timing errors
 *		Matthew Dillon	:	Fixed another RST bug
 *		Alan Cox	:	Move to kernel side addressing changes.
 *		Alan Cox	:	Beginning work on TCP fastpathing
 *					(not yet usable)
 *		Arnt Gulbrandsen:	Turbocharged tcp_check() routine.
 *		Alan Cox	:	TCP fast path debugging
 *		Alan Cox	:	Window clamping
 *		Michael Riepe	:	Bug in tcp_check()
 *		Matt Dillon	:	More TCP improvements and RST bug fixes
 *		Matt Dillon	:	Yet more small nasties remove from the
 *					TCP code (Be very nice to this man if
 *					tcp finally works 100%) 8)
 *		Alan Cox	:	BSD accept semantics.
 *		Alan Cox	:	Reset on closedown bug.
 *	Peter De Schrijver	:	ENOTCONN check missing in tcp_sendto().
 *		Michael Pall	:	Handle poll() after URG properly in
 *					all cases.
 *		Michael Pall	:	Undo the last fix in tcp_read_urg()
 *					(multi URG PUSH broke rlogin).
 *		Michael Pall	:	Fix the multi URG PUSH problem in
 *					tcp_readable(), poll() after URG
 *					works now.
 *		Michael Pall	:	recv(...,MSG_OOB) never blocks in the
 *					BSD api.
 *		Alan Cox	:	Changed the semantics of sk->socket to
 *					fix a race and a signal problem with
 *					accept() and async I/O.
 *		Alan Cox	:	Relaxed the rules on tcp_sendto().
 *		Yury Shevchuk	:	Really fixed accept() blocking problem.
 *		Craig I. Hagan  :	Allow for BSD compatible TIME_WAIT for
 *					clients/servers which listen in on
 *					fixed ports.
 *		Alan Cox	:	Cleaned the above up and shrank it to
 *					a sensible code size.
 *		Alan Cox	:	Self connect lockup fix.
 *		Alan Cox	:	No connect to multicast.
 *		Ross Biro	:	Close unaccepted children on master
 *					socket close.
 *		Alan Cox	:	Reset tracing code.
 *		Alan Cox	:	Spurious resets on shutdown.
 *		Alan Cox	:	Giant 15 minute/60 second timer error
 *		Alan Cox	:	Small whoops in polling before an
 *					accept.
 *		Alan Cox	:	Kept the state trace facility since
 *					it's handy for debugging.
 *		Alan Cox	:	More reset handler fixes.
 *		Alan Cox	:	Started rewriting the code based on
 *					the RFC's for other useful protocol
 *					references see: Comer, KA9Q NOS, and
 *					for a reference on the difference
 *					between specifications and how BSD
 *					works see the 4.4lite source.
 *		A.N.Kuznetsov	:	Don't time wait on completion of tidy
 *					close.
 *		Linus Torvalds	:	Fin/Shutdown & copied_seq changes.
 *		Linus Torvalds	:	Fixed BSD port reuse to work first syn
 *		Alan Cox	:	Reimplemented timers as per the RFC
 *					and using multiple timers for sanity.
 *		Alan Cox	:	Small bug fixes, and a lot of new
 *					comments.
 *		Alan Cox	:	Fixed dual reader crash by locking
 *					the buffers (much like datagram.c)
 *		Alan Cox	:	Fixed stuck sockets in probe. A probe
 *					now gets fed up of retrying without
 *					(even a no space) answer.
 *		Alan Cox	:	Extracted closing code better
 *		Alan Cox	:	Fixed the closing state machine to
 *					resemble the RFC.
 *		Alan Cox	:	More 'per spec' fixes.
 *		Jorge Cwik	:	Even faster checksumming.
 *		Alan Cox	:	tcp_data() doesn't ack illegal PSH
 *					only frames. At least one pc tcp stack
 *					generates them.
 *		Alan Cox	:	Cache last socket.
 *		Alan Cox	:	Per route irtt.
 *		Matt Day	:	poll()->select() match BSD precisely on error
 *		Alan Cox	:	New buffers
 *		Marc Tamsky	:	Various sk->prot->retransmits and
 *					sk->retransmits misupdating fixed.
 *					Fixed tcp_write_timeout: stuck close,
 *					and TCP syn retries gets used now.
 *		Mark Yarvis	:	In tcp_read_wakeup(), don't send an
 *					ack if state is TCP_CLOSED.
 *		Alan Cox	:	Look up device on a retransmit - routes may
 *					change. Doesn't yet cope with MSS shrink right
 *					but it's a start!
 *		Marc Tamsky	:	Closing in closing fixes.
 *		Mike Shaver	:	RFC1122 verifications.
 *		Alan Cox	:	rcv_saddr errors.
 *		Alan Cox	:	Block double connect().
 *		Alan Cox	:	Small hooks for enSKIP.
 *		Alexey Kuznetsov:	Path MTU discovery.
 *		Alan Cox	:	Support soft errors.
 *		Alan Cox	:	Fix MTU discovery pathological case
 *					when the remote claims no mtu!
 *		Marc Tamsky	:	TCP_CLOSE fix.
 *		Colin (G3TNE)	:	Send a reset on syn ack replies in
 *					window but wrong (fixes NT lpd problems)
 *		Pedro Roque	:	Better TCP window handling, delayed ack.
 *		Joerg Reuter	:	No modification of locked buffers in
 *					tcp_do_retransmit()
 *		Eric Schenk	:	Changed receiver side silly window
 *					avoidance algorithm to BSD style
 *					algorithm. This doubles throughput
 *					against machines running Solaris,
 *					and seems to result in general
 *					improvement.
 *	Stefan Magdalinski	:	adjusted tcp_readable() to fix FIONREAD
 *	Willy Konynenberg	:	Transparent proxying support.
 *	Mike McLagan		:	Routing by source
 *		Keith Owens	:	Do proper merging with partial SKB's in
 *					tcp_do_sendmsg to avoid burstiness.
 *		Eric Schenk	:	Fix fast close down bug with
 *					shutdown() followed by close().
 *		Andi Kleen 	:	Make poll agree with SIGIO
 *	Salvatore Sanfilippo	:	Support SO_LINGER with linger == 1 and
 *					lingertime == 0 (RFC 793 ABORT Call)
 *	Hirokazu Takahashi	:	Use copy_from_user() instead of
 *					csum_and_copy_from_user() if possible.
 *
 *		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.
 *
 * Description of States:
 *
 *	TCP_SYN_SENT		sent a connection request, waiting for ack
 *
 *	TCP_SYN_RECV		received a connection request, sent ack,
 *				waiting for final ack in three-way handshake.
 *
 *	TCP_ESTABLISHED		connection established
 *
 *	TCP_FIN_WAIT1		our side has shutdown, waiting to complete
 *				transmission of remaining buffered data
 *
 *	TCP_FIN_WAIT2		all buffered data sent, waiting for remote
 *				to shutdown
 *
 *	TCP_CLOSING		both sides have shutdown but we still have
 *				data we have to finish sending
 *
 *	TCP_TIME_WAIT		timeout to catch resent junk before entering
 *				closed, can only be entered from FIN_WAIT2
 *				or CLOSING.  Required because the other end
 *				may not have gotten our last ACK causing it
 *				to retransmit the data packet (which we ignore)
 *
 *	TCP_CLOSE_WAIT		remote side has shutdown and is waiting for
 *				us to finish writing our data and to shutdown
 *				(we have to close() to move on to LAST_ACK)
 *
 *	TCP_LAST_ACK		out side has shutdown after remote has
 *				shutdown.  There may still be data in our
 *				buffer that we have to finish sending
 *
 *	TCP_CLOSE		socket is finished
 */

#include <linux/config.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/random.h>
#include <linux/bootmem.h>
260
#include <linux/cache.h>
Linus Torvalds's avatar
Linus Torvalds committed
261
262
263
264
265
266
267
268
269
270
271
272

#include <net/icmp.h>
#include <net/tcp.h>
#include <net/xfrm.h>
#include <net/ip.h>


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

int sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;

273
DEFINE_SNMP_STAT(struct tcp_mib, tcp_statistics) __read_mostly;
Linus Torvalds's avatar
Linus Torvalds committed
274
275
276

atomic_t tcp_orphan_count = ATOMIC_INIT(0);

277
278
EXPORT_SYMBOL_GPL(tcp_orphan_count);

279
280
281
int sysctl_tcp_mem[3] __read_mostly;
int sysctl_tcp_wmem[3] __read_mostly;
int sysctl_tcp_rmem[3] __read_mostly;
Linus Torvalds's avatar
Linus Torvalds committed
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

EXPORT_SYMBOL(sysctl_tcp_mem);
EXPORT_SYMBOL(sysctl_tcp_rmem);
EXPORT_SYMBOL(sysctl_tcp_wmem);

atomic_t tcp_memory_allocated;	/* Current allocated memory. */
atomic_t tcp_sockets_allocated;	/* Current number of TCP sockets. */

EXPORT_SYMBOL(tcp_memory_allocated);
EXPORT_SYMBOL(tcp_sockets_allocated);

/*
 * Pressure flag: try to collapse.
 * Technical note: it is used by multiple contexts non atomically.
 * All the sk_stream_mem_schedule() is of this nature: accounting
 * is strict, actions are advisory and have some latency.
 */
int tcp_memory_pressure;

EXPORT_SYMBOL(tcp_memory_pressure);

void tcp_enter_memory_pressure(void)
{
	if (!tcp_memory_pressure) {
		NET_INC_STATS(LINUX_MIB_TCPMEMORYPRESSURES);
		tcp_memory_pressure = 1;
	}
}

EXPORT_SYMBOL(tcp_enter_memory_pressure);

/*
 *	Wait for a TCP event.
 *
 *	Note that we don't need to lock the socket, as the upper poll layers
 *	take care of normal races (between the test and the event) and we don't
 *	go look at any of the socket buffers directly.
 */
unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
	unsigned int mask;
	struct sock *sk = sock->sk;
	struct tcp_sock *tp = tcp_sk(sk);

	poll_wait(file, sk->sk_sleep, wait);
	if (sk->sk_state == TCP_LISTEN)
328
		return inet_csk_listen_poll(sk);
Linus Torvalds's avatar
Linus Torvalds committed
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
359
360
361
362
363
364
365
366
367
368

	/* Socket is not locked. We are protected from async events
	   by poll logic and correct handling of state changes
	   made by another threads is impossible in any case.
	 */

	mask = 0;
	if (sk->sk_err)
		mask = POLLERR;

	/*
	 * POLLHUP is certainly not done right. But poll() doesn't
	 * have a notion of HUP in just one direction, and for a
	 * socket the read side is more interesting.
	 *
	 * Some poll() documentation says that POLLHUP is incompatible
	 * with the POLLOUT/POLLWR flags, so somebody should check this
	 * all. But careful, it tends to be safer to return too many
	 * bits than too few, and you can easily break real applications
	 * if you don't tell them that something has hung up!
	 *
	 * Check-me.
	 *
	 * Check number 1. POLLHUP is _UNMASKABLE_ event (see UNIX98 and
	 * our fs/select.c). It means that after we received EOF,
	 * poll always returns immediately, making impossible poll() on write()
	 * in state CLOSE_WAIT. One solution is evident --- to set POLLHUP
	 * if and only if shutdown has been made in both directions.
	 * Actually, it is interesting to look how Solaris and DUX
	 * solve this dilemma. I would prefer, if PULLHUP were maskable,
	 * then we could set it on SND_SHUTDOWN. BTW examples given
	 * in Stevens' books assume exactly this behaviour, it explains
	 * why PULLHUP is incompatible with POLLOUT.	--ANK
	 *
	 * NOTE. Check for TCP_CLOSE is added. The goal is to prevent
	 * blocking on fresh not-connected or disconnected socket. --ANK
	 */
	if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE)
		mask |= POLLHUP;
	if (sk->sk_shutdown & RCV_SHUTDOWN)
369
		mask |= POLLIN | POLLRDNORM | POLLRDHUP;
Linus Torvalds's avatar
Linus Torvalds committed
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
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
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
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474

	/* Connected? */
	if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		/* Potential race condition. If read of tp below will
		 * escape above sk->sk_state, we can be illegally awaken
		 * in SYN_* states. */
		if ((tp->rcv_nxt != tp->copied_seq) &&
		    (tp->urg_seq != tp->copied_seq ||
		     tp->rcv_nxt != tp->copied_seq + 1 ||
		     sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data))
			mask |= POLLIN | POLLRDNORM;

		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
			if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
				mask |= POLLOUT | POLLWRNORM;
			} else {  /* send SIGIO later */
				set_bit(SOCK_ASYNC_NOSPACE,
					&sk->sk_socket->flags);
				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);

				/* Race breaker. If space is freed after
				 * wspace test but before the flags are set,
				 * IO signal will be lost.
				 */
				if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
					mask |= POLLOUT | POLLWRNORM;
			}
		}

		if (tp->urg_data & TCP_URG_VALID)
			mask |= POLLPRI;
	}
	return mask;
}

int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int answ;

	switch (cmd) {
	case SIOCINQ:
		if (sk->sk_state == TCP_LISTEN)
			return -EINVAL;

		lock_sock(sk);
		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
			answ = 0;
		else if (sock_flag(sk, SOCK_URGINLINE) ||
			 !tp->urg_data ||
			 before(tp->urg_seq, tp->copied_seq) ||
			 !before(tp->urg_seq, tp->rcv_nxt)) {
			answ = tp->rcv_nxt - tp->copied_seq;

			/* Subtract 1, if FIN is in queue. */
			if (answ && !skb_queue_empty(&sk->sk_receive_queue))
				answ -=
		       ((struct sk_buff *)sk->sk_receive_queue.prev)->h.th->fin;
		} else
			answ = tp->urg_seq - tp->copied_seq;
		release_sock(sk);
		break;
	case SIOCATMARK:
		answ = tp->urg_data && tp->urg_seq == tp->copied_seq;
		break;
	case SIOCOUTQ:
		if (sk->sk_state == TCP_LISTEN)
			return -EINVAL;

		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
			answ = 0;
		else
			answ = tp->write_seq - tp->snd_una;
		break;
	default:
		return -ENOIOCTLCMD;
	};

	return put_user(answ, (int __user *)arg);
}

static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
{
	TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
	tp->pushed_seq = tp->write_seq;
}

static inline int forced_push(struct tcp_sock *tp)
{
	return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
}

static inline void skb_entail(struct sock *sk, struct tcp_sock *tp,
			      struct sk_buff *skb)
{
	skb->csum = 0;
	TCP_SKB_CB(skb)->seq = tp->write_seq;
	TCP_SKB_CB(skb)->end_seq = tp->write_seq;
	TCP_SKB_CB(skb)->flags = TCPCB_FLAG_ACK;
	TCP_SKB_CB(skb)->sacked = 0;
	skb_header_release(skb);
	__skb_queue_tail(&sk->sk_write_queue, skb);
	sk_charge_skb(sk, skb);
	if (!sk->sk_send_head)
		sk->sk_send_head = skb;
475
	if (tp->nonagle & TCP_NAGLE_PUSH)
Linus Torvalds's avatar
Linus Torvalds committed
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
		tp->nonagle &= ~TCP_NAGLE_PUSH; 
}

static inline void tcp_mark_urg(struct tcp_sock *tp, int flags,
				struct sk_buff *skb)
{
	if (flags & MSG_OOB) {
		tp->urg_mode = 1;
		tp->snd_up = tp->write_seq;
		TCP_SKB_CB(skb)->sacked |= TCPCB_URG;
	}
}

static inline void tcp_push(struct sock *sk, struct tcp_sock *tp, int flags,
			    int mss_now, int nonagle)
{
	if (sk->sk_send_head) {
		struct sk_buff *skb = sk->sk_write_queue.prev;
		if (!(flags & MSG_MORE) || forced_push(tp))
			tcp_mark_push(tp, skb);
		tcp_mark_urg(tp, flags, skb);
		__tcp_push_pending_frames(sk, tp, mss_now,
					  (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle);
	}
}

static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffset,
			 size_t psize, int flags)
{
	struct tcp_sock *tp = tcp_sk(sk);
506
	int mss_now, size_goal;
Linus Torvalds's avatar
Linus Torvalds committed
507
508
509
510
511
512
513
514
515
516
517
518
	int err;
	ssize_t copied;
	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

	/* Wait for a connection to finish. */
	if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
		if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
			goto out_err;

	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);

	mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
519
	size_goal = tp->xmit_size_goal;
Linus Torvalds's avatar
Linus Torvalds committed
520
521
522
523
524
525
526
527
528
529
530
531
532
	copied = 0;

	err = -EPIPE;
	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
		goto do_error;

	while (psize > 0) {
		struct sk_buff *skb = sk->sk_write_queue.prev;
		struct page *page = pages[poffset / PAGE_SIZE];
		int copy, i, can_coalesce;
		int offset = poffset % PAGE_SIZE;
		int size = min_t(size_t, psize, PAGE_SIZE - offset);

533
		if (!sk->sk_send_head || (copy = size_goal - skb->len) <= 0) {
Linus Torvalds's avatar
Linus Torvalds committed
534
535
536
537
538
539
540
541
542
543
new_segment:
			if (!sk_stream_memory_free(sk))
				goto wait_for_sndbuf;

			skb = sk_stream_alloc_pskb(sk, 0, 0,
						   sk->sk_allocation);
			if (!skb)
				goto wait_for_memory;

			skb_entail(sk, tp, skb);
544
			copy = size_goal;
Linus Torvalds's avatar
Linus Torvalds committed
545
546
547
548
549
550
551
552
553
554
555
		}

		if (copy > size)
			copy = size;

		i = skb_shinfo(skb)->nr_frags;
		can_coalesce = skb_can_coalesce(skb, i, page, offset);
		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
			tcp_mark_push(tp, skb);
			goto new_segment;
		}
556
		if (!sk_stream_wmem_schedule(sk, copy))
Linus Torvalds's avatar
Linus Torvalds committed
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
			goto wait_for_memory;
		
		if (can_coalesce) {
			skb_shinfo(skb)->frags[i - 1].size += copy;
		} else {
			get_page(page);
			skb_fill_page_desc(skb, i, page, offset, copy);
		}

		skb->len += copy;
		skb->data_len += copy;
		skb->truesize += copy;
		sk->sk_wmem_queued += copy;
		sk->sk_forward_alloc -= copy;
		skb->ip_summed = CHECKSUM_HW;
		tp->write_seq += copy;
		TCP_SKB_CB(skb)->end_seq += copy;
		skb_shinfo(skb)->tso_segs = 0;

		if (!copied)
			TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH;

		copied += copy;
		poffset += copy;
		if (!(psize -= copy))
			goto out;

584
		if (skb->len < mss_now || (flags & MSG_OOB))
Linus Torvalds's avatar
Linus Torvalds committed
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
			continue;

		if (forced_push(tp)) {
			tcp_mark_push(tp, skb);
			__tcp_push_pending_frames(sk, tp, mss_now, TCP_NAGLE_PUSH);
		} else if (skb == sk->sk_send_head)
			tcp_push_one(sk, mss_now);
		continue;

wait_for_sndbuf:
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
		if (copied)
			tcp_push(sk, tp, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);

		if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
			goto do_error;

		mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
604
		size_goal = tp->xmit_size_goal;
Linus Torvalds's avatar
Linus Torvalds committed
605
606
607
608
609
610
611
612
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
	}

out:
	if (copied)
		tcp_push(sk, tp, flags, mss_now, tp->nonagle);
	return copied;

do_error:
	if (copied)
		goto out;
out_err:
	return sk_stream_error(sk, flags, err);
}

ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset,
		     size_t size, int flags)
{
	ssize_t res;
	struct sock *sk = sock->sk;

#define TCP_ZC_CSUM_FLAGS (NETIF_F_IP_CSUM | NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)

	if (!(sk->sk_route_caps & NETIF_F_SG) ||
	    !(sk->sk_route_caps & TCP_ZC_CSUM_FLAGS))
		return sock_no_sendpage(sock, page, offset, size, flags);

#undef TCP_ZC_CSUM_FLAGS

	lock_sock(sk);
	TCP_CHECK_TIMER(sk);
	res = do_tcp_sendpages(sk, &page, offset, size, flags);
	TCP_CHECK_TIMER(sk);
	release_sock(sk);
	return res;
}

#define TCP_PAGE(sk)	(sk->sk_sndmsg_page)
#define TCP_OFF(sk)	(sk->sk_sndmsg_off)

static inline int select_size(struct sock *sk, struct tcp_sock *tp)
{
646
	int tmp = tp->mss_cache;
Linus Torvalds's avatar
Linus Torvalds committed
647

648
649
650
651
652
653
654
655
656
657
658
	if (sk->sk_route_caps & NETIF_F_SG) {
		if (sk->sk_route_caps & NETIF_F_TSO)
			tmp = 0;
		else {
			int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);

			if (tmp >= pgbreak &&
			    tmp <= pgbreak + (MAX_SKB_FRAGS - 1) * PAGE_SIZE)
				tmp = pgbreak;
		}
	}
Linus Torvalds's avatar
Linus Torvalds committed
659
660
661
662
663
664
665
666
667
668
669

	return tmp;
}

int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t size)
{
	struct iovec *iov;
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	int iovlen, flags;
670
	int mss_now, size_goal;
Linus Torvalds's avatar
Linus Torvalds committed
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
	int err, copied;
	long timeo;

	lock_sock(sk);
	TCP_CHECK_TIMER(sk);

	flags = msg->msg_flags;
	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

	/* Wait for a connection to finish. */
	if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
		if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
			goto out_err;

	/* This should be in poll */
	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);

	mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
689
	size_goal = tp->xmit_size_goal;
Linus Torvalds's avatar
Linus Torvalds committed
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711

	/* Ok commence sending. */
	iovlen = msg->msg_iovlen;
	iov = msg->msg_iov;
	copied = 0;

	err = -EPIPE;
	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
		goto do_error;

	while (--iovlen >= 0) {
		int seglen = iov->iov_len;
		unsigned char __user *from = iov->iov_base;

		iov++;

		while (seglen > 0) {
			int copy;

			skb = sk->sk_write_queue.prev;

			if (!sk->sk_send_head ||
712
			    (copy = size_goal - skb->len) <= 0) {
Linus Torvalds's avatar
Linus Torvalds committed
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734

new_segment:
				/* Allocate new segment. If the interface is SG,
				 * allocate skb fitting to single page.
				 */
				if (!sk_stream_memory_free(sk))
					goto wait_for_sndbuf;

				skb = sk_stream_alloc_pskb(sk, select_size(sk, tp),
							   0, sk->sk_allocation);
				if (!skb)
					goto wait_for_memory;

				/*
				 * Check whether we can use HW checksum.
				 */
				if (sk->sk_route_caps &
				    (NETIF_F_IP_CSUM | NETIF_F_NO_CSUM |
				     NETIF_F_HW_CSUM))
					skb->ip_summed = CHECKSUM_HW;

				skb_entail(sk, tp, skb);
735
				copy = size_goal;
Linus Torvalds's avatar
Linus Torvalds committed
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
			}

			/* Try to append data to the end of skb. */
			if (copy > seglen)
				copy = seglen;

			/* Where to copy to? */
			if (skb_tailroom(skb) > 0) {
				/* We have some space in skb head. Superb! */
				if (copy > skb_tailroom(skb))
					copy = skb_tailroom(skb);
				if ((err = skb_add_data(skb, from, copy)) != 0)
					goto do_fault;
			} else {
				int merge = 0;
				int i = skb_shinfo(skb)->nr_frags;
				struct page *page = TCP_PAGE(sk);
				int off = TCP_OFF(sk);

				if (skb_can_coalesce(skb, i, page, off) &&
				    off != PAGE_SIZE) {
					/* We can extend the last page
					 * fragment. */
					merge = 1;
				} else if (i == MAX_SKB_FRAGS ||
					   (!i &&
					   !(sk->sk_route_caps & NETIF_F_SG))) {
					/* Need to add new fragment and cannot
					 * do this because interface is non-SG,
					 * or because all the page slots are
					 * busy. */
					tcp_mark_push(tp, skb);
					goto new_segment;
				} else if (page) {
					if (off == PAGE_SIZE) {
						put_page(page);
						TCP_PAGE(sk) = page = NULL;
773
						off = 0;
Linus Torvalds's avatar
Linus Torvalds committed
774
					}
775
				} else
776
					off = 0;
777
778
779
780
781
782

				if (copy > PAGE_SIZE - off)
					copy = PAGE_SIZE - off;

				if (!sk_stream_wmem_schedule(sk, copy))
					goto wait_for_memory;
Linus Torvalds's avatar
Linus Torvalds committed
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
824
825
826
827
828
829
830
831
832
833

				if (!page) {
					/* Allocate new cache page. */
					if (!(page = sk_stream_alloc_page(sk)))
						goto wait_for_memory;
				}

				/* Time to copy data. We are close to
				 * the end! */
				err = skb_copy_to_page(sk, from, skb, page,
						       off, copy);
				if (err) {
					/* If this page was new, give it to the
					 * socket so it does not get leaked.
					 */
					if (!TCP_PAGE(sk)) {
						TCP_PAGE(sk) = page;
						TCP_OFF(sk) = 0;
					}
					goto do_error;
				}

				/* Update the skb. */
				if (merge) {
					skb_shinfo(skb)->frags[i - 1].size +=
									copy;
				} else {
					skb_fill_page_desc(skb, i, page, off, copy);
					if (TCP_PAGE(sk)) {
						get_page(page);
					} else if (off + copy < PAGE_SIZE) {
						get_page(page);
						TCP_PAGE(sk) = page;
					}
				}

				TCP_OFF(sk) = off + copy;
			}

			if (!copied)
				TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH;

			tp->write_seq += copy;
			TCP_SKB_CB(skb)->end_seq += copy;
			skb_shinfo(skb)->tso_segs = 0;

			from += copy;
			copied += copy;
			if ((seglen -= copy) == 0 && iovlen == 0)
				goto out;

834
			if (skb->len < mss_now || (flags & MSG_OOB))
Linus Torvalds's avatar
Linus Torvalds committed
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
				continue;

			if (forced_push(tp)) {
				tcp_mark_push(tp, skb);
				__tcp_push_pending_frames(sk, tp, mss_now, TCP_NAGLE_PUSH);
			} else if (skb == sk->sk_send_head)
				tcp_push_one(sk, mss_now);
			continue;

wait_for_sndbuf:
			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
			if (copied)
				tcp_push(sk, tp, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);

			if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
				goto do_error;

			mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
854
			size_goal = tp->xmit_size_goal;
Linus Torvalds's avatar
Linus Torvalds committed
855
856
857
858
859
860
861
862
863
864
865
866
867
868
		}
	}

out:
	if (copied)
		tcp_push(sk, tp, flags, mss_now, tp->nonagle);
	TCP_CHECK_TIMER(sk);
	release_sock(sk);
	return copied;

do_fault:
	if (!skb->len) {
		if (sk->sk_send_head == skb)
			sk->sk_send_head = NULL;
David S. Miller's avatar
David S. Miller committed
869
		__skb_unlink(skb, &sk->sk_write_queue);
Linus Torvalds's avatar
Linus Torvalds committed
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
		sk_stream_free_skb(sk, skb);
	}

do_error:
	if (copied)
		goto out;
out_err:
	err = sk_stream_error(sk, flags, err);
	TCP_CHECK_TIMER(sk);
	release_sock(sk);
	return err;
}

/*
 *	Handle reading urgent data. BSD has very simple semantics for
 *	this, no blocking and very strange errors 8)
 */

static int tcp_recv_urg(struct sock *sk, long timeo,
			struct msghdr *msg, int len, int flags,
			int *addr_len)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* No URG data to read. */
	if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data ||
	    tp->urg_data == TCP_URG_READ)
		return -EINVAL;	/* Yes this is right ! */

	if (sk->sk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DONE))
		return -ENOTCONN;

	if (tp->urg_data & TCP_URG_VALID) {
		int err = 0;
		char c = tp->urg_data;

		if (!(flags & MSG_PEEK))
			tp->urg_data = TCP_URG_READ;

		/* Read urgent data. */
		msg->msg_flags |= MSG_OOB;

		if (len > 0) {
			if (!(flags & MSG_TRUNC))
				err = memcpy_toiovec(msg->msg_iov, &c, 1);
			len = 1;
		} else
			msg->msg_flags |= MSG_TRUNC;

		return err ? -EFAULT : len;
	}

	if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN))
		return 0;

	/* Fixed the recv(..., MSG_OOB) behaviour.  BSD docs and
	 * the available implementations agree in this case:
	 * this call should never block, independent of the
	 * blocking state of the socket.
	 * Mike <pall@rz.uni-karlsruhe.de>
	 */
	return -EAGAIN;
}

/* Clean up the receive buffer for full frames taken by the user,
 * then send an ACK if necessary.  COPIED is the number of bytes
 * tcp_recvmsg has given to the user so far, it speeds up the
 * calculation of whether or not we must ACK for the sake of
 * a window update.
 */
940
void tcp_cleanup_rbuf(struct sock *sk, int copied)
Linus Torvalds's avatar
Linus Torvalds committed
941
942
943
944
945
946
947
948
949
950
{
	struct tcp_sock *tp = tcp_sk(sk);
	int time_to_ack = 0;

#if TCP_DEBUG
	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);

	BUG_TRAP(!skb || before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq));
#endif

951
952
	if (inet_csk_ack_scheduled(sk)) {
		const struct inet_connection_sock *icsk = inet_csk(sk);
Linus Torvalds's avatar
Linus Torvalds committed
953
954
		   /* Delayed ACKs frequently hit locked sockets during bulk
		    * receive. */
955
		if (icsk->icsk_ack.blocked ||
Linus Torvalds's avatar
Linus Torvalds committed
956
		    /* Once-per-two-segments ACK was not sent by tcp_input.c */
957
		    tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss ||
Linus Torvalds's avatar
Linus Torvalds committed
958
959
960
961
962
963
		    /*
		     * If this read emptied read buffer, we send ACK, if
		     * connection is not bidirectional, user drained
		     * receive buffer and there was a small segment
		     * in queue.
		     */
964
965
		    (copied > 0 && (icsk->icsk_ack.pending & ICSK_ACK_PUSHED) &&
		     !icsk->icsk_ack.pingpong && !atomic_read(&sk->sk_rmem_alloc)))
Linus Torvalds's avatar
Linus Torvalds committed
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
			time_to_ack = 1;
	}

	/* We send an ACK if we can now advertise a non-zero window
	 * which has been raised "significantly".
	 *
	 * Even if window raised up to infinity, do not send window open ACK
	 * in states, where we will not receive more. It is useless.
	 */
	if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
		__u32 rcv_window_now = tcp_receive_window(tp);

		/* Optimize, __tcp_select_window() is not cheap. */
		if (2*rcv_window_now <= tp->window_clamp) {
			__u32 new_window = __tcp_select_window(sk);

			/* Send ACK now, if this read freed lots of space
			 * in our buffer. Certainly, new_window is new window.
			 * We can advertise it now, if it is not less than current one.
			 * "Lots" means "at least twice" here.
			 */
			if (new_window && new_window >= 2 * rcv_window_now)
				time_to_ack = 1;
		}
	}
	if (time_to_ack)
		tcp_send_ack(sk);
}

static void tcp_prequeue_process(struct sock *sk)
{
	struct sk_buff *skb;
	struct tcp_sock *tp = tcp_sk(sk);

1000
	NET_INC_STATS_USER(LINUX_MIB_TCPPREQUEUED);
Linus Torvalds's avatar
Linus Torvalds committed
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
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
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074

	/* RX process wants to run with disabled BHs, though it is not
	 * necessary */
	local_bh_disable();
	while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
		sk->sk_backlog_rcv(sk, skb);
	local_bh_enable();

	/* Clear memory counter. */
	tp->ucopy.memory = 0;
}

static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
{
	struct sk_buff *skb;
	u32 offset;

	skb_queue_walk(&sk->sk_receive_queue, skb) {
		offset = seq - TCP_SKB_CB(skb)->seq;
		if (skb->h.th->syn)
			offset--;
		if (offset < skb->len || skb->h.th->fin) {
			*off = offset;
			return skb;
		}
	}
	return NULL;
}

/*
 * This routine provides an alternative to tcp_recvmsg() for routines
 * that would like to handle copying from skbuffs directly in 'sendfile'
 * fashion.
 * Note:
 *	- It is assumed that the socket was locked by the caller.
 *	- The routine does not block.
 *	- At present, there is no support for reading OOB data
 *	  or for 'peeking' the socket using this routine
 *	  (although both would be easy to implement).
 */
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
		  sk_read_actor_t recv_actor)
{
	struct sk_buff *skb;
	struct tcp_sock *tp = tcp_sk(sk);
	u32 seq = tp->copied_seq;
	u32 offset;
	int copied = 0;

	if (sk->sk_state == TCP_LISTEN)
		return -ENOTCONN;
	while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
		if (offset < skb->len) {
			size_t used, len;

			len = skb->len - offset;
			/* Stop reading if we hit a patch of urgent data */
			if (tp->urg_data) {
				u32 urg_offset = tp->urg_seq - seq;
				if (urg_offset < len)
					len = urg_offset;
				if (!len)
					break;
			}
			used = recv_actor(desc, skb, offset, len);
			if (used <= len) {
				seq += used;
				copied += used;
				offset += used;
			}
			if (offset != skb->len)
				break;
		}
		if (skb->h.th->fin) {
1075
			sk_eat_skb(sk, skb, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1076
1077
1078
			++seq;
			break;
		}
1079
		sk_eat_skb(sk, skb, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1080
1081
1082
1083
1084
1085
1086
1087
1088
		if (!desc->count)
			break;
	}
	tp->copied_seq = seq;

	tcp_rcv_space_adjust(sk);

	/* Clean up data we have read: This will do ACK frames. */
	if (copied)
1089
		tcp_cleanup_rbuf(sk, copied);
Linus Torvalds's avatar
Linus Torvalds committed
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
	return copied;
}

/*
 *	This routine copies from a sock struct into the user buffer.
 *
 *	Technical note: in 2.3 we work on _locked_ socket, so that
 *	tricks with *seq access order and skb->users are not required.
 *	Probably, code can be easily improved even more.
 */

int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t len, int nonblock, int flags, int *addr_len)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int copied = 0;
	u32 peek_seq;
	u32 *seq;
	unsigned long used;
	int err;
	int target;		/* Read at least this many bytes */
	long timeo;
	struct task_struct *user_recv = NULL;

	lock_sock(sk);

	TCP_CHECK_TIMER(sk);

	err = -ENOTCONN;
	if (sk->sk_state == TCP_LISTEN)
		goto out;

	timeo = sock_rcvtimeo(sk, nonblock);

	/* Urgent data needs to be handled specially. */
	if (flags & MSG_OOB)
		goto recv_urg;

	seq = &tp->copied_seq;
	if (flags & MSG_PEEK) {
		peek_seq = tp->copied_seq;
		seq = &peek_seq;
	}

	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);

	do {
		struct sk_buff *skb;
		u32 offset;

		/* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */
		if (tp->urg_data && tp->urg_seq == *seq) {
			if (copied)
				break;
			if (signal_pending(current)) {
				copied = timeo ? sock_intr_errno(timeo) : -EAGAIN;
				break;
			}
		}

		/* Next get a buffer. */

		skb = skb_peek(&sk->sk_receive_queue);
		do {
			if (!skb)
				break;

			/* Now that we have two receive queues this
			 * shouldn't happen.
			 */
			if (before(*seq, TCP_SKB_CB(skb)->seq)) {
				printk(KERN_INFO "recvmsg bug: copied %X "
				       "seq %X\n", *seq, TCP_SKB_CB(skb)->seq);
				break;
			}
			offset = *seq - TCP_SKB_CB(skb)->seq;
			if (skb->h.th->syn)
				offset--;
			if (offset < skb->len)
				goto found_ok_skb;
			if (skb->h.th->fin)
				goto found_fin_ok;
			BUG_TRAP(flags & MSG_PEEK);
			skb = skb->next;
		} while (skb != (struct sk_buff *)&sk->sk_receive_queue);

		/* Well, if we have backlog, try to process it now yet. */

		if (copied >= target && !sk->sk_backlog.tail)
			break;

		if (copied) {
			if (sk->sk_err ||
			    sk->sk_state == TCP_CLOSE ||
			    (sk->sk_shutdown & RCV_SHUTDOWN) ||
			    !timeo ||
			    signal_pending(current) ||
			    (flags & MSG_PEEK))
				break;
		} else {
			if (sock_flag(sk, SOCK_DONE))
				break;

			if (sk->sk_err) {
				copied = sock_error(sk);
				break;
			}

			if (sk->sk_shutdown & RCV_SHUTDOWN)
				break;

			if (sk->sk_state == TCP_CLOSE) {
				if (!sock_flag(sk, SOCK_DONE)) {
					/* This occurs when user tries to read
					 * from never connected socket.
					 */
					copied = -ENOTCONN;
					break;
				}
				break;
			}

			if (!timeo) {
				copied = -EAGAIN;
				break;
			}

			if (signal_pending(current)) {
				copied = sock_intr_errno(timeo);
				break;
			}
		}

1223
		tcp_cleanup_rbuf(sk, copied);
Linus Torvalds's avatar
Linus Torvalds committed
1224

1225
		if (!sysctl_tcp_low_latency && tp->ucopy.task == user_recv) {
Linus Torvalds's avatar
Linus Torvalds committed
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
			/* Install new reader */
			if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
				user_recv = current;
				tp->ucopy.task = user_recv;
				tp->ucopy.iov = msg->msg_iov;
			}

			tp->ucopy.len = len;

			BUG_TRAP(tp->copied_seq == tp->rcv_nxt ||
				 (flags & (MSG_PEEK | MSG_TRUNC)));

			/* Ugly... If prequeue is not empty, we have to
			 * process it before releasing socket, otherwise
			 * order will be broken at second iteration.
			 * More elegant solution is required!!!
			 *
			 * Look: we have the following (pseudo)queues:
			 *
			 * 1. packets in flight
			 * 2. backlog
			 * 3. prequeue
			 * 4. receive_queue
			 *
			 * Each queue can be processed only if the next ones
			 * are empty. At this point we have empty receive_queue.
			 * But prequeue _can_ be not empty after 2nd iteration,
			 * when we jumped to start of loop because backlog
			 * processing added something to receive_queue.
			 * We cannot release_sock(), because backlog contains
			 * packets arrived _after_ prequeued ones.
			 *
			 * Shortly, algorithm is clear --- to process all
			 * the queues in order. We could make it more directly,
			 * requeueing packets from backlog to prequeue, if
			 * is not empty. It is more elegant, but eats cycles,
			 * unfortunately.
			 */
1264
			if (!skb_queue_empty(&tp->ucopy.prequeue))
Linus Torvalds's avatar
Linus Torvalds committed
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
				goto do_prequeue;

			/* __ Set realtime policy in scheduler __ */
		}

		if (copied >= target) {
			/* Do not sleep, just process backlog. */
			release_sock(sk);
			lock_sock(sk);
		} else
			sk_wait_data(sk, &timeo);

		if (user_recv) {
			int chunk;

			/* __ Restore normal policy in scheduler __ */

			if ((chunk = len - tp->ucopy.len) != 0) {
				NET_ADD_STATS_USER(LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk);
				len -= chunk;
				copied += chunk;
			}

			if (tp->rcv_nxt == tp->copied_seq &&
1289
			    !skb_queue_empty(&tp->ucopy.prequeue)) {
Linus Torvalds's avatar
Linus Torvalds committed
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
do_prequeue:
				tcp_prequeue_process(sk);

				if ((chunk = len - tp->ucopy.len) != 0) {
					NET_ADD_STATS_USER(LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
					len -= chunk;
					copied += chunk;
				}
			}
		}
		if ((flags & MSG_PEEK) && peek_seq != tp->copied_seq) {
			if (net_ratelimit())
				printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n",
				       current->comm, current->pid);
			peek_seq = tp->copied_seq;
		}
		continue;

	found_ok_skb:
		/* Ok so how much can we use? */
		used = skb->len - offset;
		if (len < used)
			used = len;

		/* Do we have urgent data here? */
		if (tp->urg_data) {
			u32 urg_offset = tp->urg_seq - *seq;
			if (urg_offset < used) {
				if (!urg_offset) {
					if (!sock_flag(sk, SOCK_URGINLINE)) {
						++*seq;
						offset++;
						used--;
						if (!used)
							goto skip_copy;
					}
				} else
					used = urg_offset;
			}
		}

		if (!(flags & MSG_TRUNC)) {
			err = skb_copy_datagram_iovec(skb, offset,
						      msg->msg_iov, used);
			if (err) {
				/* Exception. Bailout! */
				if (!copied)
					copied = -EFAULT;
				break;
			}
		}

		*seq += used;
		copied += used;
		len -= used;

		tcp_rcv_space_adjust(sk);

skip_copy:
		if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) {
			tp->urg_data = 0;
			tcp_fast_path_check(sk, tp);
		}
		if (used + offset < skb->len)
			continue;

		if (skb->h.th->fin)
			goto found_fin_ok;
		if (!(flags & MSG_PEEK))
1359
			sk_eat_skb(sk, skb, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1360
1361
1362
1363
1364
1365
		continue;

	found_fin_ok:
		/* Process the FIN. */
		++*seq;
		if (!(flags & MSG_PEEK))
1366
			sk_eat_skb(sk, skb, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1367
1368
1369
1370
		break;
	} while (len > 0);

	if (user_recv) {
1371
		if (!skb_queue_empty(&tp->ucopy.prequeue)) {
Linus Torvalds's avatar
Linus Torvalds committed
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
			int chunk;

			tp->ucopy.len = copied > 0 ? len : 0;

			tcp_prequeue_process(sk);

			if (copied > 0 && (chunk = len - tp->ucopy.len) != 0) {
				NET_ADD_STATS_USER(LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
				len -= chunk;
				copied += chunk;
			}
		}

		tp->ucopy.task = NULL;
		tp->ucopy.len = 0;
	}

	/* According to UNIX98, msg_name/msg_namelen are ignored
	 * on connected socket. I was just happy when found this 8) --ANK
	 */

	/* Clean up data we have read: This will do ACK frames. */
1394
	tcp_cleanup_rbuf(sk, copied);
Linus Torvalds's avatar
Linus Torvalds committed
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416

	TCP_CHECK_TIMER(sk);
	release_sock(sk);
	return copied;

out:
	TCP_CHECK_TIMER(sk);
	release_sock(sk);
	return err;

recv_urg:
	err = tcp_recv_urg(sk, timeo, msg, len, flags, addr_len);
	goto out;
}

/*
 *	State processing on a close. This implements the state shift for
 *	sending our FIN frame. Note that we only send a FIN for some
 *	states. A shutdown() may have already sent the FIN, or we may be
 *	closed.
 */

1417
static const unsigned char new_state[16] = {
Linus Torvalds's avatar
Linus Torvalds committed
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
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
  /* current state:        new state:      action:	*/
  /* (Invalid)		*/ TCP_CLOSE,
  /* TCP_ESTABLISHED	*/ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
  /* TCP_SYN_SENT	*/ TCP_CLOSE,
  /* TCP_SYN_RECV	*/ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
  /* TCP_FIN_WAIT1	*/ TCP_FIN_WAIT1,
  /* TCP_FIN_WAIT2	*/ TCP_FIN_WAIT2,
  /* TCP_TIME_WAIT	*/ TCP_CLOSE,
  /* TCP_CLOSE		*/ TCP_CLOSE,
  /* TCP_CLOSE_WAIT	*/ TCP_LAST_ACK  | TCP_ACTION_FIN,
  /* TCP_LAST_ACK	*/ TCP_LAST_ACK,
  /* TCP_LISTEN		*/ TCP_CLOSE,
  /* TCP_CLOSING	*/ TCP_CLOSING,
};

static int tcp_close_state(struct sock *sk)
{
	int next = (int)new_state[sk->sk_state];
	int ns = next & TCP_STATE_MASK;

	tcp_set_state(sk, ns);

	return next & TCP_ACTION_FIN;
}

/*
 *	Shutdown the sending side of a connection. Much like close except
 *	that we don't receive shut down or set_sock_flag(sk, SOCK_DEAD).
 */

void tcp_shutdown(struct sock *sk, int how)
{
	/*	We need to grab some memory, and put together a FIN,
	 *	and then put it into the queue to be sent.
	 *		Tim MacKenzie(tym@dibbler.cs.monash.edu.au) 4 Dec '92.
	 */
	if (!(how & SEND_SHUTDOWN))
		return;

	/* If we've already sent a FIN, or it's a closed state, skip this. */
	if ((1 << sk->sk_state) &
	    (TCPF_ESTABLISHED | TCPF_SYN_SENT |
	     TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) {
		/* Clear out any half completed packets.  FIN if needed. */
		if (tcp_close_state(sk))
			tcp_send_fin(sk);
	}
}

void tcp_close(struct sock *sk, long timeout)
{
	struct sk_buff *skb;
	int data_was_unread = 0;
Herbert Xu's avatar
Herbert Xu committed
1471
	int state;
Linus Torvalds's avatar
Linus Torvalds committed
1472
1473
1474
1475
1476
1477
1478
1479

	lock_sock(sk);
	sk->sk_shutdown = SHUTDOWN_MASK;

	if (sk->sk_state == TCP_LISTEN) {
		tcp_set_state(sk, TCP_CLOSE);

		/* Special case. */
1480
		inet_csk_listen_stop(sk);
Linus Torvalds's avatar
Linus Torvalds committed
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547

		goto adjudge_to_death;
	}

	/*  We need to flush the recv. buffs.  We do this only on the
	 *  descriptor close, not protocol-sourced closes, because the
	 *  reader process may not have drained the data yet!
	 */
	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq -
			  skb->h.th->fin;
		data_was_unread += len;
		__kfree_skb(skb);
	}

	sk_stream_mem_reclaim(sk);

	/* As outlined in draft-ietf-tcpimpl-prob-03.txt, section
	 * 3.10, we send a RST here because data was lost.  To
	 * witness the awful effects of the old behavior of always
	 * doing a FIN, run an older 2.1.x kernel or 2.0.x, start
	 * a bulk GET in an FTP client, suspend the process, wait
	 * for the client to advertise a zero window, then kill -9
	 * the FTP client, wheee...  Note: timeout is always zero
	 * in such a case.
	 */
	if (data_was_unread) {
		/* Unread data was tossed, zap the connection. */
		NET_INC_STATS_USER(LINUX_MIB_TCPABORTONCLOSE);
		tcp_set_state(sk, TCP_CLOSE);
		tcp_send_active_reset(sk, GFP_KERNEL);
	} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
		/* Check zero linger _after_ checking for unread data. */
		sk->sk_prot->disconnect(sk, 0);
		NET_INC_STATS_USER(LINUX_MIB_TCPABORTONDATA);
	} else if (tcp_close_state(sk)) {
		/* We FIN if the application ate all the data before
		 * zapping the connection.
		 */

		/* RED-PEN. Formally speaking, we have broken TCP state
		 * machine. State transitions:
		 *
		 * TCP_ESTABLISHED -> TCP_FIN_WAIT1
		 * TCP_SYN_RECV	-> TCP_FIN_WAIT1 (forget it, it's impossible)
		 * TCP_CLOSE_WAIT -> TCP_LAST_ACK
		 *
		 * are legal only when FIN has been sent (i.e. in window),
		 * rather than queued out of window. Purists blame.
		 *
		 * F.e. "RFC state" is ESTABLISHED,
		 * if Linux state is FIN-WAIT-1, but FIN is still not sent.
		 *
		 * The visible declinations are that sometimes
		 * we enter time-wait state, when it is not required really
		 * (harmless), do not send active resets, when they are
		 * required by specs (TCP_ESTABLISHED, TCP_CLOSE_WAIT, when
		 * they look as CLOSING or LAST_ACK for Linux)
		 * Probably, I missed some more holelets.
		 * 						--ANK
		 */
		tcp_send_fin(sk);
	}

	sk_stream_wait_close(sk, timeout);

adjudge_to_death:
Herbert Xu's avatar
Herbert Xu committed
1548
1549
1550
1551
1552
	state = sk->sk_state;
	sock_hold(sk);
	sock_orphan(sk);
	atomic_inc(sk->sk_prot->orphan_count);

Linus Torvalds's avatar
Linus Torvalds committed
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
	/* It is the last release_sock in its life. It will remove backlog. */
	release_sock(sk);


	/* Now socket is owned by kernel and we acquire BH lock
	   to finish close. No need to check for user refs.
	 */
	local_bh_disable();
	bh_lock_sock(sk);
	BUG_TRAP(!sock_owned_by_user(sk));

Herbert Xu's avatar
Herbert Xu committed
1564
1565
1566
	/* Have we already been destroyed by a softirq or backlog? */
	if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE)
		goto out;
Linus Torvalds's avatar
Linus Torvalds committed
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588

	/*	This is a (useful) BSD violating of the RFC. There is a
	 *	problem with TCP as specified in that the other end could
	 *	keep a socket open forever with no application left this end.
	 *	We use a 3 minute timeout (about the same as BSD) then kill
	 *	our end. If they send after that then tough - BUT: long enough
	 *	that we won't make the old 4*rto = almost no time - whoops
	 *	reset mistake.
	 *
	 *	Nope, it was not mistake. It is really desired behaviour
	 *	f.e. on http servers, when such sockets are useless, but
	 *	consume significant resources. Let's do it with special
	 *	linger2	option.					--ANK
	 */

	if (sk->sk_state == TCP_FIN_WAIT2) {
		struct tcp_sock *tp = tcp_sk(sk);
		if (tp->linger2 < 0) {
			tcp_set_state(sk, TCP_CLOSE);
			tcp_send_active_reset(sk, GFP_ATOMIC);
			NET_INC_STATS_BH(LINUX_MIB_TCPABORTONLINGER);
		} else {
1589
			const int tmo = tcp_fin_time(sk);
Linus Torvalds's avatar
Linus Torvalds committed
1590
1591

			if (tmo > TCP_TIMEWAIT_LEN) {
1592
				inet_csk_reset_keepalive_timer(sk, tcp_fin_time(sk));
Linus Torvalds's avatar
Linus Torvalds committed
1593
1594
1595
1596
1597
1598
1599
1600
			} else {
				tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
				goto out;
			}
		}
	}
	if (sk->sk_state != TCP_CLOSE) {
		sk_stream_mem_reclaim(sk);
1601
		if (atomic_read(sk->sk_prot->orphan_count) > sysctl_tcp_max_orphans ||
Linus Torvalds's avatar
Linus Torvalds committed
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
		    (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
		     atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])) {
			if (net_ratelimit())
				printk(KERN_INFO "TCP: too many of orphaned "
				       "sockets\n");
			tcp_set_state(sk, TCP_CLOSE);
			tcp_send_active_reset(sk, GFP_ATOMIC);
			NET_INC_STATS_BH(LINUX_MIB_TCPABORTONMEMORY);
		}
	}

	if (sk->sk_state == TCP_CLOSE)
1614
		inet_csk_destroy_sock(sk);
Linus Torvalds's avatar
Linus Torvalds committed
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
	/* Otherwise, socket is reprieved until protocol close. */

out:
	bh_unlock_sock(sk);
	local_bh_enable();
	sock_put(sk);
}

/* These states need RST on ABORT according to RFC793 */

static inline int tcp_need_reset(int state)
{
	return (1 << state) &
	       (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 |
		TCPF_FIN_WAIT2 | TCPF_SYN_RECV);
}

int tcp_disconnect(struct sock *sk, int flags)
{
	struct inet_sock *inet = inet_sk(sk);
1635
	struct inet_connection_sock *icsk = inet_csk(sk);
Linus Torvalds's avatar
Linus Torvalds committed
1636
1637
1638
1639
1640
1641
1642
1643
1644
	struct tcp_sock *tp = tcp_sk(sk);
	int err = 0;
	int old_state = sk->sk_state;

	if (old_state != TCP_CLOSE)
		tcp_set_state(sk, TCP_CLOSE);

	/* ABORT function of RFC793 */
	if (old_state == TCP_LISTEN) {
1645
		inet_csk_listen_stop(sk);
Linus Torvalds's avatar
Linus Torvalds committed
1646
1647
1648
	} else if (tcp_need_reset(old_state) ||
		   (tp->snd_nxt != tp->write_seq &&
		    (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) {
Stephen Hemminger's avatar
Stephen Hemminger committed
1649
		/* The last check adjusts for discrepancy of Linux wrt. RFC
Linus Torvalds's avatar
Linus Torvalds committed
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
		 * states
		 */
		tcp_send_active_reset(sk, gfp_any());
		sk->sk_err = ECONNRESET;
	} else if (old_state == TCP_SYN_SENT)
		sk->sk_err = ECONNRESET;

	tcp_clear_xmit_timers(sk);
	__skb_queue_purge(&sk->sk_receive_queue);
	sk_stream_writequeue_purge(sk);
	__skb_queue_purge(&tp->out_of_order_queue);

	inet->dport = 0;

	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
		inet_reset_saddr(sk);

	sk->sk_shutdown = 0;
	sock_reset_flag(sk, SOCK_DONE);
	tp->srtt = 0;
	if ((tp->write_seq += tp->max_window + 2) == 0)
		tp->write_seq = 1;
1672
	icsk->icsk_backoff = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1673
	tp->snd_cwnd = 2;
1674
	icsk->icsk_probes_out = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1675
1676
1677
	tp->packets_out = 0;
	tp->snd_ssthresh = 0x7fffffff;
	tp->snd_cwnd_cnt = 0;
1678
	tp->bytes_acked = 0;
1679
	tcp_set_ca_state(sk, TCP_CA_Open);
Linus Torvalds's avatar
Linus Torvalds committed
1680
	tcp_clear_retrans(tp);
1681
	inet_csk_delack_init(sk);
Linus Torvalds's avatar
Linus Torvalds committed
1682
1683
1684
1685
1686
	sk->sk_send_head = NULL;
	tp->rx_opt.saw_tstamp = 0;
	tcp_sack_reset(&tp->rx_opt);
	__sk_dst_reset(sk);

1687
	BUG_TRAP(!inet->num || icsk->icsk_bind_hash);
Linus Torvalds's avatar
Linus Torvalds committed
1688
1689
1690
1691
1692
1693
1694
1695

	sk->sk_error_report(sk);
	return err;
}

/*
 *	Socket option code for TCP.
 */
1696
1697
static int do_tcp_setsockopt(struct sock *sk, int level,
		int optname, char __user *optval, int optlen)
Linus Torvalds's avatar
Linus Torvalds committed
1698
1699
{
	struct tcp_sock *tp = tcp_sk(sk);
1700
	struct inet_connection_sock *icsk = inet_csk(sk);
Linus Torvalds's avatar
Linus Torvalds committed
1701
1702
1703
	int val;
	int err = 0;

1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
	/* This is a string value all the others are int's */
	if (optname == TCP_CONGESTION) {
		char name[TCP_CA_NAME_MAX];

		if (optlen < 1)
			return -EINVAL;

		val = strncpy_from_user(name, optval,
					min(TCP_CA_NAME_MAX-1, optlen));
		if (val < 0)
			return -EFAULT;
		name[val] = 0;

		lock_sock(sk);
1718
		err = tcp_set_congestion_control(sk, name);
1719
1720
1721
1722
		release_sock(sk);
		return err;
	}

Linus Torvalds's avatar
Linus Torvalds committed
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
	if (optlen < sizeof(int))
		return -EINVAL;

	if (get_user(val, (int __user *)optval))
		return -EFAULT;

	lock_sock(sk);

	switch (optname) {
	case TCP_MAXSEG:
		/* Values greater than interface MTU won't take effect. However
		 * at the point when this call is done we typically don't yet
		 * know which interface is going to be used */
		if (val < 8 || val > MAX_TCP_WINDOW) {
			err = -EINVAL;
			break;
		}
		tp->rx_opt.user_mss = val;
		break;

	case TCP_NODELAY:
		if (val) {
			/* TCP_NODELAY is weaker than TCP_CORK, so that
			 * this option on corked socket is remembered, but
			 * it is not activated until cork is cleared.
			 *
			 * However, when TCP_NODELAY is set we make
			 * an explicit push, which overrides even TCP_CORK
			 * for currently queued segments.
			 */
			tp->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH;
			tcp_push_pending_frames(sk, tp);
		} else {
			tp->nonagle &= ~TCP_NAGLE_OFF;
		}
		break;

	case TCP_CORK:
		/* When set indicates to always queue non-full frames.
		 * Later the user clears this option and we transmit
		 * any pending partial frames in the queue.  This is
		 * meant to be used alongside sendfile() to get properly
		 * filled frames when the user (for example) must write
		 * out headers with a write() call first and then use
		 * sendfile to send out the data parts.
		 *
		 * TCP_CORK can be set together with TCP_NODELAY and it is
		 * stronger than TCP_NODELAY.
		 */
		if (val) {
			tp->nonagle |= TCP_NAGLE_CORK;
		} else {
			tp->nonagle &= ~TCP_NAGLE_CORK;
			if (tp->nonagle&TCP_NAGLE_OFF)
				tp->nonagle |= TCP_NAGLE_PUSH;
			tcp_push_pending_frames(sk, tp);
		}
		break;

	case TCP_KEEPIDLE:
		if (val < 1 || val > MAX_TCP_KEEPIDLE)
			err = -EINVAL;
		else {
			tp->keepalive_time = val * HZ;
			if (sock_flag(sk, SOCK_KEEPOPEN) &&
			    !((1 << sk->sk_state) &
			      (TCPF_CLOSE | TCPF_LISTEN))) {
				__u32 elapsed = tcp_time_stamp - tp->rcv_tstamp;
				if (tp->keepalive_time > elapsed)
					elapsed = tp->keepalive_time - elapsed;
				else
					elapsed = 0;
1795
				inet_csk_reset_keepalive_timer(sk, elapsed);
Linus Torvalds's avatar
Linus Torvalds committed
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
			}
		}
		break;
	case TCP_KEEPINTVL:
		if (val < 1 || val > MAX_TCP_KEEPINTVL)
			err = -EINVAL;
		else
			tp->keepalive_intvl = val * HZ;
		break;
	case TCP_KEEPCNT:
		if (val < 1 || val > MAX_TCP_KEEPCNT)
			err = -EINVAL;
		else
			tp->keepalive_probes = val;
		break;
	case TCP_SYNCNT:
		if (val < 1 || val > MAX_TCP_SYNCNT)
			err = -EINVAL;
		else
1815
			icsk->icsk_syn_retries = val;
Linus Torvalds's avatar
Linus Torvalds committed
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
		break;

	case TCP_LINGER2:
		if (val < 0)
			tp->linger2 = -1;
		else if (val > sysctl_tcp_fin_timeout / HZ)
			tp->linger2 = 0;
		else
			tp->linger2 = val * HZ;
		break;

	case TCP_DEFER_ACCEPT:
1828
		icsk->icsk_accept_queue.rskq_defer_accept = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1829
1830
1831
		if (val > 0) {
			/* Translate value in seconds to number of
			 * retransmits */
1832
			while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&
Linus Torvalds's avatar
Linus Torvalds committed
1833
			       val > ((TCP_TIMEOUT_INIT / HZ) <<
1834
1835
1836
				       icsk->icsk_accept_queue.rskq_defer_accept))
				icsk->icsk_accept_queue.rskq_defer_accept++;
			icsk->icsk_accept_queue.rskq_defer_accept++;
Linus Torvalds's avatar
Linus Torvalds committed
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
		}
		break;

	case TCP_WINDOW_CLAMP:
		if (!val) {
			if (sk->sk_state != TCP_CLOSE) {
				err = -EINVAL;
				break;
			}
			tp->window_clamp = 0;
		} else
			tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
						SOCK_MIN_RCVBUF / 2 : val;
		break;

	case TCP_QUICKACK:
		if (!val) {
1854
			icsk->icsk_ack.pingpong = 1;
Linus Torvalds's avatar
Linus Torvalds committed
1855
		} else {
1856
			icsk->icsk_ack.pingpong = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1857
1858
			if ((1 << sk->sk_state) &
			    (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) &&
1859
1860
			    inet_csk_ack_scheduled(sk)) {
				icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
1861
				tcp_cleanup_rbuf(sk, 1);
Linus Torvalds's avatar
Linus Torvalds committed
1862
				if (!(val & 1))
1863
					icsk->icsk_ack.pingpong = 1;
Linus Torvalds's avatar
Linus Torvalds committed
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
			}
		}
		break;

	default:
		err = -ENOPROTOOPT;
		break;
	};
	release_sock(sk);
	return err;
}

1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
		   int optlen)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	if (level != SOL_TCP)
		return icsk->icsk_af_ops->setsockopt(sk, level, optname,
						     optval, optlen);
	return do_tcp_setsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
1888
1889
int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int optlen)
1890
{
1891
1892
1893
	if (level != SOL_TCP)
		return inet_csk_compat_setsockopt(sk, level, optname,
						  optval, optlen);
1894
1895
	return do_tcp_setsockopt(sk, level, optname, optval, optlen);
}
1896
1897

EXPORT_SYMBOL(compat_tcp_setsockopt);
1898
1899
#endif

Linus Torvalds's avatar
Linus Torvalds committed
1900
1901
1902
1903
/* Return information about state of tcp endpoint in API format. */
void tcp_get_info(struct sock *sk, struct tcp_info *info)
{
	struct tcp_sock *tp = tcp_sk(sk);
1904
	const struct inet_connection_sock *icsk = inet_csk(sk);
Linus Torvalds's avatar
Linus Torvalds committed
1905
1906
1907
1908
1909
	u32 now = tcp_time_stamp;

	memset(info, 0, sizeof(*info));

	info->tcpi_state = sk->sk_state;
1910
	info->tcpi_ca_state = icsk->icsk_ca_state;
1911
	info->tcpi_retransmits = icsk->icsk_retransmits;
1912
	info->tcpi_probes = icsk->icsk_probes_out;
1913
	info->tcpi_backoff = icsk->icsk_backoff;
Linus Torvalds's avatar
Linus Torvalds committed
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927

	if (tp->rx_opt.tstamp_ok)
		info->tcpi_options |= TCPI_OPT_TIMESTAMPS;
	if (tp->rx_opt.sack_ok)
		info->tcpi_options |= TCPI_OPT_SACK;
	if (tp->rx_opt.wscale_ok) {
		info->tcpi_options |= TCPI_OPT_WSCALE;
		info->tcpi_snd_wscale = tp->rx_opt.snd_wscale;
		info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale;
	} 

	if (tp->ecn_flags&TCP_ECN_OK)
		info->tcpi_options |= TCPI_OPT_ECN;

1928
1929
	info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto);
	info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato);
1930
	info->tcpi_snd_mss = tp->mss_cache;
1931
	info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;
Linus Torvalds's avatar
Linus Torvalds committed
1932
1933
1934
1935
1936
1937
1938
1939

	info->tcpi_unacked = tp->packets_out;
	info->tcpi_sacked = tp->sacked_out;
	info->tcpi_lost = tp->lost_out;
	info->tcpi_retrans = tp->retrans_out;
	info->tcpi_fackets = tp->fackets_out;

	info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime);
1940
	info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime);
Linus Torvalds's avatar
Linus Torvalds committed
1941
1942
	info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp);

1943
	info->tcpi_pmtu = icsk->icsk_pmtu_cookie;
Linus Torvalds's avatar
Linus Torvalds committed
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
	info->tcpi_rcv_ssthresh = tp->rcv_ssthresh;
	info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3;
	info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2;
	info->tcpi_snd_ssthresh = tp->snd_ssthresh;
	info->tcpi_snd_cwnd = tp->snd_cwnd;
	info->tcpi_advmss = tp->advmss;
	info->tcpi_reordering = tp->reordering;

	info->tcpi_rcv_rtt = jiffies_to_usecs(tp->rcv_rtt_est.rtt)>>3;
	info->tcpi_rcv_space = tp->rcvq_space.space;

	info->tcpi_total_retrans = tp->total_retrans;
}

EXPORT_SYMBOL_GPL(tcp_get_info);

1960
1961
static int do_tcp_getsockopt(struct sock *sk, int level,
		int optname, char __user *optval, int __user *optlen)
Linus Torvalds's avatar
Linus Torvalds committed
1962
{
1963
	struct inet_connection_sock *icsk = inet_csk(sk);
Linus Torvalds's avatar
Linus Torvalds committed
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
	struct tcp_sock *tp = tcp_sk(sk);
	int val, len;

	if (get_user(len, optlen))
		return -EFAULT;

	len = min_t(unsigned int, len, sizeof(int));

	if (len < 0)
		return -EINVAL;

	switch (optname) {
	case TCP_MAXSEG:
1977
		val = tp->mss_cache;
Linus Torvalds's avatar
Linus Torvalds committed
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
		if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
			val = tp->rx_opt.user_mss;
		break;
	case TCP_NODELAY:
		val = !!(tp->nonagle&TCP_NAGLE_OFF);
		break;
	case TCP_CORK:
		val = !!(tp->nonagle&TCP_NAGLE_CORK);
		break;
	case TCP_KEEPIDLE:
		val = (tp->keepalive_time ? : sysctl_tcp_keepalive_time) / HZ;
		break;
	case TCP_KEEPINTVL:
		val = (tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl) / HZ;
		break;
	case TCP_KEEPCNT:
		val = tp->keepalive_probes ? : sysctl_tcp_keepalive_probes;
		break;
	case TCP_SYNCNT:
1997
		val = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
Linus Torvalds's avatar
Linus Torvalds committed
1998
1999
2000
2001
2002
2003
2004
		break;
	case TCP_LINGER2:
		val = tp->linger2;
		if (val >= 0)
			val = (val ? : sysctl_tcp_fin_timeout) / HZ;
		break;
	case TCP_DEFER_ACCEPT:
2005
2006
		val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 :
			((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1));
Linus Torvalds's avatar
Linus Torvalds committed
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
		break;
	case TCP_WINDOW_CLAMP:
		val = tp->window_clamp;
		break;
	case TCP_INFO: {
		struct tcp_info info;

		if (get_user(len, optlen))
			return -EFAULT;

		tcp_get_info(sk, &info);

		len = min_t(unsigned int, len, sizeof(info));
		if (put_user(len, optlen))
			return -EFAULT;
		if (copy_to_user(optval, &info, len))
			return -EFAULT;
		return 0;
	}
	case TCP_QUICKACK:
2027
		val = !icsk->icsk_ack.pingpong;
Linus Torvalds's avatar
Linus Torvalds committed
2028
		break;
2029
2030
2031
2032
2033
2034
2035

	case TCP_CONGESTION:
		if (get_user(len, optlen))
			return -EFAULT;
		len = min_t(unsigned int, len, TCP_CA_NAME_MAX);
		if (put_user(len, optlen))
			return -EFAULT;
2036
		if (copy_to_user(optval, icsk->icsk_ca_ops->name, len))
2037
2038
			return -EFAULT;
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
	default:
		return -ENOPROTOOPT;
	};

	if (put_user(len, optlen))
		return -EFAULT;
	if (copy_to_user(optval, &val, len))
		return -EFAULT;
	return 0;
}

2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
		   int __user *optlen)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	if (level != SOL_TCP)
		return icsk->icsk_af_ops->getsockopt(sk, level, optname,
						     optval, optlen);
	return do_tcp_getsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
2062
2063
int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int __user *optlen)
2064
{
2065
2066
2067
	if (level != SOL_TCP)
		return inet_csk_compat_getsockopt(sk, level, optname,
						  optval, optlen);
2068
2069
	return do_tcp_getsockopt(sk, level, optname, optval, optlen);
}
2070
2071

EXPORT_SYMBOL(compat_tcp_getsockopt);
2072
#endif
Linus Torvalds's avatar
Linus Torvalds committed
2073
2074

extern void __skb_cb_too_small_for_tcp(int, int);
2075
extern struct tcp_congestion_ops tcp_reno;
Linus Torvalds's avatar
Linus Torvalds committed
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089

static __initdata unsigned long thash_entries;
static int __init set_thash_entries(char *str)
{
	if (!str)
		return 0;
	thash_entries = simple_strtoul(str, &str, 0);
	return 1;
}
__setup("thash_entries=", set_thash_entries);

void __init tcp_init(void)
{
	struct sk_buff *skb = NULL;
2090
2091
	unsigned long limit;
	int order, i, max_share;
Linus Torvalds's avatar
Linus Torvalds committed
2092
2093
2094
2095
2096

	if (sizeof(struct tcp_skb_cb) > sizeof(skb->cb))
		__skb_cb_too_small_for_tcp(sizeof(struct tcp_skb_cb),
					   sizeof(skb->cb));

2097
2098
2099
2100
2101
	tcp_hashinfo.bind_bucket_cachep =
		kmem_cache_create("tcp_bind_bucket",
				  sizeof(struct inet_bind_bucket), 0,
				  SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (!tcp_hashinfo.bind_bucket_cachep)
Linus Torvalds's avatar
Linus Torvalds committed
2102
2103
2104
2105
2106
2107
2108
		panic("tcp_init: Cannot alloc tcp_bind_bucket cache.");

	/* Size and allocate the main established and bind bucket
	 * hash tables.
	 *
	 * The methodology is similar to that of the buffer cache.
	 */
2109
	tcp_hashinfo.ehash =
Linus Torvalds's avatar
Linus Torvalds committed
2110
		alloc_large_system_hash("TCP established",
2111
					sizeof(struct inet_ehash_bucket),
Linus Torvalds's avatar
Linus Torvalds committed
2112
2113
					thash_entries,
					(num_physpages >= 128 * 1024) ?
2114
					13 : 15,
Linus Torvalds's avatar