tcp.c 95 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
/*
 * 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).
 *
 * Authors:	Ross Biro
 *		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
 */

#define pr_fmt(fmt) "TCP: " fmt

#include <crypto/hash.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/poll.h>
#include <linux/inet_diag.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/skbuff.h>
#include <linux/scatterlist.h>
#include <linux/splice.h>
#include <linux/net.h>
#include <linux/socket.h>
#include <linux/random.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/time.h>
#include <linux/slab.h>
272
#include <linux/errqueue.h>
273
#include <linux/static_key.h>
274
275
276
277
278
279
280
281

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

282
#include <linux/uaccess.h>
283
284
285
286
287
288
289
290
291
292
293
294
#include <asm/ioctls.h>
#include <net/busy_poll.h>

struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);

long sysctl_tcp_mem[3] __read_mostly;
EXPORT_SYMBOL(sysctl_tcp_mem);

atomic_long_t tcp_memory_allocated;	/* Current allocated memory. */
EXPORT_SYMBOL(tcp_memory_allocated);

295
296
297
298
299
#if IS_ENABLED(CONFIG_SMC)
DEFINE_STATIC_KEY_FALSE(tcp_have_smc);
EXPORT_SYMBOL(tcp_have_smc);
#endif

300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
/*
 * Current number of TCP sockets.
 */
struct percpu_counter tcp_sockets_allocated;
EXPORT_SYMBOL(tcp_sockets_allocated);

/*
 * TCP splice context
 */
struct tcp_splice_state {
	struct pipe_inode_info *pipe;
	size_t len;
	unsigned int flags;
};

/*
 * Pressure flag: try to collapse.
 * Technical note: it is used by multiple contexts non atomically.
 * All the __sk_mem_schedule() is of this nature: accounting
 * is strict, actions are advisory and have some latency.
 */
321
322
unsigned long tcp_memory_pressure __read_mostly;
EXPORT_SYMBOL_GPL(tcp_memory_pressure);
323
324
325

void tcp_enter_memory_pressure(struct sock *sk)
{
326
327
328
329
330
331
332
333
334
	unsigned long val;

	if (tcp_memory_pressure)
		return;
	val = jiffies;

	if (!val)
		val--;
	if (!cmpxchg(&tcp_memory_pressure, 0, val))
335
336
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES);
}
337
338
339
340
341
342
343
344
345
346
347
348
349
350
EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure);

void tcp_leave_memory_pressure(struct sock *sk)
{
	unsigned long val;

	if (!tcp_memory_pressure)
		return;
	val = xchg(&tcp_memory_pressure, 0);
	if (val)
		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO,
			      jiffies_to_msecs(jiffies - val));
}
EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure);
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388

/* Convert seconds to retransmits based on initial and max timeout */
static u8 secs_to_retrans(int seconds, int timeout, int rto_max)
{
	u8 res = 0;

	if (seconds > 0) {
		int period = timeout;

		res = 1;
		while (seconds > period && res < 255) {
			res++;
			timeout <<= 1;
			if (timeout > rto_max)
				timeout = rto_max;
			period += timeout;
		}
	}
	return res;
}

/* Convert retransmits to seconds based on initial and max timeout */
static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
{
	int period = 0;

	if (retrans > 0) {
		period = timeout;
		while (--retrans) {
			timeout <<= 1;
			if (timeout > rto_max)
				timeout = rto_max;
			period += timeout;
		}
	}
	return period;
}

389
390
391
392
393
394
395
396
397
398
399
400
401
static u64 tcp_compute_delivery_rate(const struct tcp_sock *tp)
{
	u32 rate = READ_ONCE(tp->rate_delivered);
	u32 intv = READ_ONCE(tp->rate_interval_us);
	u64 rate64 = 0;

	if (rate && intv) {
		rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC;
		do_div(rate64, intv);
	}
	return rate64;
}

402
403
404
405
406
407
408
409
410
411
/* Address-family independent initialization for a tcp_sock.
 *
 * NOTE: A lot of things set to zero explicitly by call to
 *       sk_alloc() so need not be done here.
 */
void tcp_init_sock(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);

412
	tp->out_of_order_queue = RB_ROOT;
413
	sk->tcp_rtx_queue = RB_ROOT;
414
415
	tcp_init_xmit_timers(sk);
	INIT_LIST_HEAD(&tp->tsq_node);
416
	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
417
418
419

	icsk->icsk_rto = TCP_TIMEOUT_INIT;
	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
420
	minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
421
422
423
424
425
426
427
428

	/* So many TCP implementations out there (incorrectly) count the
	 * initial SYN frame in their delayed-ACK and congestion control
	 * algorithms that we must have the following bandaid to talk
	 * efficiently to them.  -DaveM
	 */
	tp->snd_cwnd = TCP_INIT_CWND;

429
430
431
	/* There's a bubble in the pipe until at least the first ACK. */
	tp->app_limited = ~0U;

432
433
434
435
436
437
438
439
440
441
442
	/* See draft-stevens-tcpca-spec-01 for discussion of the
	 * initialization of these values.
	 */
	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
	tp->snd_cwnd_clamp = ~0;
	tp->mss_cache = TCP_MSS_DEFAULT;

	tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
	tcp_assign_congestion_control(sk);

	tp->tsoffset = 0;
443
	tp->rack.reo_wnd_steps = 1;
444
445
446
447
448
449
450
451

	sk->sk_state = TCP_CLOSE;

	sk->sk_write_space = sk_stream_write_space;
	sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);

	icsk->icsk_sync_mss = tcp_sync_mss;

452
453
	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
454
455
456
457
458

	sk_sockets_allocated_inc(sk);
}
EXPORT_SYMBOL(tcp_init_sock);

459
460
461
462
463
464
465
void tcp_init_transfer(struct sock *sk, int bpf_op)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	tcp_mtup_init(sk);
	icsk->icsk_af_ops->rebuild_header(sk);
	tcp_init_metrics(sk);
466
	tcp_call_bpf(sk, bpf_op, 0, NULL);
467
468
469
470
471
	tcp_init_congestion_control(sk);
	tcp_init_buffer_space(sk);
}

static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
472
{
473
474
	struct sk_buff *skb = tcp_write_queue_tail(sk);

475
	if (tsflags && skb) {
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
		struct skb_shared_info *shinfo = skb_shinfo(skb);
		struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);

		sock_tx_timestamp(sk, tsflags, &shinfo->tx_flags);
		if (tsflags & SOF_TIMESTAMPING_TX_ACK)
			tcb->txstamp_ack = 1;
		if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK)
			shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
	}
}

/*
 *	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.
 */
494
__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
495
{
496
	__poll_t mask;
497
498
499
500
501
502
	struct sock *sk = sock->sk;
	const struct tcp_sock *tp = tcp_sk(sk);
	int state;

	sock_poll_wait(file, sk_sleep(sk), wait);

503
	state = inet_sk_state_load(sk);
504
505
506
507
508
509
510
511
512
513
514
	if (state == TCP_LISTEN)
		return inet_csk_listen_poll(sk);

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

	mask = 0;

	/*
515
	 * EPOLLHUP is certainly not done right. But poll() doesn't
516
517
518
	 * have a notion of HUP in just one direction, and for a
	 * socket the read side is more interesting.
	 *
519
520
	 * Some poll() documentation says that EPOLLHUP is incompatible
	 * with the EPOLLOUT/POLLWR flags, so somebody should check this
521
522
523
524
525
526
	 * 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.
	 *
527
	 * Check number 1. EPOLLHUP is _UNMASKABLE_ event (see UNIX98 and
528
529
	 * our fs/select.c). It means that after we received EOF,
	 * poll always returns immediately, making impossible poll() on write()
530
	 * in state CLOSE_WAIT. One solution is evident --- to set EPOLLHUP
531
532
	 * if and only if shutdown has been made in both directions.
	 * Actually, it is interesting to look how Solaris and DUX
533
	 * solve this dilemma. I would prefer, if EPOLLHUP were maskable,
534
535
	 * then we could set it on SND_SHUTDOWN. BTW examples given
	 * in Stevens' books assume exactly this behaviour, it explains
536
	 * why EPOLLHUP is incompatible with EPOLLOUT.	--ANK
537
538
539
540
541
	 *
	 * 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 || state == TCP_CLOSE)
542
		mask |= EPOLLHUP;
543
	if (sk->sk_shutdown & RCV_SHUTDOWN)
544
		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
545
546
547
548
549
550
551
552
553
554
555
556

	/* Connected or passive Fast Open socket? */
	if (state != TCP_SYN_SENT &&
	    (state != TCP_SYN_RECV || tp->fastopen_rsk)) {
		int target = sock_rcvlowat(sk, 0, INT_MAX);

		if (tp->urg_seq == tp->copied_seq &&
		    !sock_flag(sk, SOCK_URGINLINE) &&
		    tp->urg_data)
			target++;

		if (tp->rcv_nxt - tp->copied_seq >= target)
557
			mask |= EPOLLIN | EPOLLRDNORM;
558
559
560

		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
			if (sk_stream_is_writeable(sk)) {
561
				mask |= EPOLLOUT | EPOLLWRNORM;
562
563
564
565
566
567
568
569
570
571
572
			} else {  /* send SIGIO later */
				sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
				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. Memory barrier
				 * pairs with the input side.
				 */
				smp_mb__after_atomic();
				if (sk_stream_is_writeable(sk))
573
					mask |= EPOLLOUT | EPOLLWRNORM;
574
575
			}
		} else
576
			mask |= EPOLLOUT | EPOLLWRNORM;
577
578

		if (tp->urg_data & TCP_URG_VALID)
579
			mask |= EPOLLPRI;
580
581
	} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
		/* Active TCP fastopen socket with defer_connect
582
		 * Return EPOLLOUT so application can call write()
583
584
		 * in order for kernel to generate SYN+data
		 */
585
		mask |= EPOLLOUT | EPOLLWRNORM;
586
587
588
589
	}
	/* This barrier is coupled with smp_wmb() in tcp_reset() */
	smp_rmb();
	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
590
		mask |= EPOLLERR;
591
592
593
594
595
596
597
598
599
600
601
602
603
604
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
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689

	return mask;
}
EXPORT_SYMBOL(tcp_poll);

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

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

		slow = lock_sock_fast(sk);
		answ = tcp_inq(sk);
		unlock_sock_fast(sk, slow);
		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;
	case SIOCOUTQNSD:
		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_nxt;
		break;
	default:
		return -ENOIOCTLCMD;
	}

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

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

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

static void skb_entail(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);

	skb->csum    = 0;
	tcb->seq     = tcb->end_seq = tp->write_seq;
	tcb->tcp_flags = TCPHDR_ACK;
	tcb->sacked  = 0;
	__skb_header_release(skb);
	tcp_add_write_queue_tail(sk, skb);
	sk->sk_wmem_queued += skb->truesize;
	sk_mem_charge(sk, skb->truesize);
	if (tp->nonagle & TCP_NAGLE_PUSH)
		tp->nonagle &= ~TCP_NAGLE_PUSH;

	tcp_slow_start_after_idle_check(sk);
}

static inline void tcp_mark_urg(struct tcp_sock *tp, int flags)
{
	if (flags & MSG_OOB)
		tp->snd_up = tp->write_seq;
}

/* If a not yet filled skb is pushed, do not send it if
 * we have data packets in Qdisc or NIC queues :
 * Because TX completion will happen shortly, it gives a chance
 * to coalesce future sendmsg() payload into this skb, without
 * need for a timer, and with no latency trade off.
 * As packets containing data payload have a bigger truesize
 * than pure acks (dataless) packets, the last checks prevent
 * autocorking if we only have an ACK in Qdisc/NIC queues,
 * or if TX completion was delayed after we processed ACK packet.
 */
static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
				int size_goal)
{
	return skb->len < size_goal &&
690
	       sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
691
	       skb != tcp_write_queue_head(sk) &&
692
	       refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
693
694
695
696
697
698
699
700
701
}

static void tcp_push(struct sock *sk, int flags, int mss_now,
		     int nonagle, int size_goal)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;

	skb = tcp_write_queue_tail(sk);
702
703
	if (!skb)
		return;
704
705
706
707
708
709
710
711
	if (!(flags & MSG_MORE) || forced_push(tp))
		tcp_mark_push(tp, skb);

	tcp_mark_urg(tp, flags);

	if (tcp_should_autocork(sk, skb, size_goal)) {

		/* avoid atomic op if TSQ_THROTTLED bit is already set */
712
		if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) {
713
			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
714
			set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
715
716
717
718
		}
		/* It is possible TX completion already happened
		 * before we set TSQ_THROTTLED.
		 */
719
		if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize)
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
			return;
	}

	if (flags & MSG_MORE)
		nonagle = TCP_NAGLE_CORK;

	__tcp_push_pending_frames(sk, mss_now, nonagle);
}

static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
				unsigned int offset, size_t len)
{
	struct tcp_splice_state *tss = rd_desc->arg.data;
	int ret;

	ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe,
736
			      min(rd_desc->count, len), tss->flags);
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
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
	if (ret > 0)
		rd_desc->count -= ret;
	return ret;
}

static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss)
{
	/* Store TCP splice context information in read_descriptor_t. */
	read_descriptor_t rd_desc = {
		.arg.data = tss,
		.count	  = tss->len,
	};

	return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv);
}

/**
 *  tcp_splice_read - splice data from TCP socket to a pipe
 * @sock:	socket to splice from
 * @ppos:	position (not valid)
 * @pipe:	pipe to splice to
 * @len:	number of bytes to splice
 * @flags:	splice modifier flags
 *
 * Description:
 *    Will read pages from given socket and fill them into a pipe.
 *
 **/
ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
			struct pipe_inode_info *pipe, size_t len,
			unsigned int flags)
{
	struct sock *sk = sock->sk;
	struct tcp_splice_state tss = {
		.pipe = pipe,
		.len = len,
		.flags = flags,
	};
	long timeo;
	ssize_t spliced;
	int ret;

	sock_rps_record_flow(sk);
	/*
	 * We can't seek on a socket input
	 */
	if (unlikely(*ppos))
		return -ESPIPE;

	ret = spliced = 0;

	lock_sock(sk);

	timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK);
	while (tss.len) {
		ret = __tcp_splice_read(sk, &tss);
		if (ret < 0)
			break;
		else if (!ret) {
			if (spliced)
				break;
			if (sock_flag(sk, SOCK_DONE))
				break;
			if (sk->sk_err) {
				ret = sock_error(sk);
				break;
			}
			if (sk->sk_shutdown & RCV_SHUTDOWN)
				break;
			if (sk->sk_state == TCP_CLOSE) {
				/*
				 * This occurs when user tries to read
				 * from never connected socket.
				 */
				if (!sock_flag(sk, SOCK_DONE))
					ret = -ENOTCONN;
				break;
			}
			if (!timeo) {
				ret = -EAGAIN;
				break;
			}
819
820
821
822
823
824
			/* if __tcp_splice_read() got nothing while we have
			 * an skb in receive queue, we do not want to loop.
			 * This might happen with URG data.
			 */
			if (!skb_queue_empty(&sk->sk_receive_queue))
				break;
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
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
878
879
880
881
882
			sk_wait_data(sk, &timeo, NULL);
			if (signal_pending(current)) {
				ret = sock_intr_errno(timeo);
				break;
			}
			continue;
		}
		tss.len -= ret;
		spliced += ret;

		if (!timeo)
			break;
		release_sock(sk);
		lock_sock(sk);

		if (sk->sk_err || sk->sk_state == TCP_CLOSE ||
		    (sk->sk_shutdown & RCV_SHUTDOWN) ||
		    signal_pending(current))
			break;
	}

	release_sock(sk);

	if (spliced)
		return spliced;

	return ret;
}
EXPORT_SYMBOL(tcp_splice_read);

struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
				    bool force_schedule)
{
	struct sk_buff *skb;

	/* The TCP header must be at least 32-bit aligned.  */
	size = ALIGN(size, 4);

	if (unlikely(tcp_under_memory_pressure(sk)))
		sk_mem_reclaim_partial(sk);

	skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp);
	if (likely(skb)) {
		bool mem_scheduled;

		if (force_schedule) {
			mem_scheduled = true;
			sk_forced_mem_schedule(sk, skb->truesize);
		} else {
			mem_scheduled = sk_wmem_schedule(sk, skb->truesize);
		}
		if (likely(mem_scheduled)) {
			skb_reserve(skb, sk->sk_prot->max_header);
			/*
			 * Make sure that we have exactly size bytes
			 * available to the caller, no more, no less.
			 */
			skb->reserved_tailroom = skb->end - skb->tail - size;
883
			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
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
			return skb;
		}
		__kfree_skb(skb);
	} else {
		sk->sk_prot->enter_memory_pressure(sk);
		sk_stream_moderate_sndbuf(sk);
	}
	return NULL;
}

static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
				       int large_allowed)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 new_size_goal, size_goal;

	if (!large_allowed || !sk_can_gso(sk))
		return mss_now;

	/* Note : tcp_tso_autosize() will eventually split this later */
	new_size_goal = sk->sk_gso_max_size - 1 - MAX_TCP_HEADER;
	new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal);

	/* We try hard to avoid divides here */
	size_goal = tp->gso_segs * mss_now;
	if (unlikely(new_size_goal < size_goal ||
		     new_size_goal >= size_goal + mss_now)) {
		tp->gso_segs = min_t(u16, new_size_goal / mss_now,
				     sk->sk_gso_max_segs);
		size_goal = tp->gso_segs * mss_now;
	}

	return max(size_goal, mss_now);
}

static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
{
	int mss_now;

	mss_now = tcp_current_mss(sk);
	*size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB));

	return mss_now;
}

929
930
ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
			 size_t size, int flags)
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
{
	struct tcp_sock *tp = tcp_sk(sk);
	int mss_now, size_goal;
	int err;
	ssize_t copied;
	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

	/* Wait for a connection to finish. One exception is TCP Fast Open
	 * (passive side) where data is allowed to be sent before a connection
	 * is fully established.
	 */
	if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) &&
	    !tcp_passive_fastopen(sk)) {
		err = sk_stream_wait_connect(sk, &timeo);
		if (err != 0)
			goto out_err;
	}

	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);

	mss_now = tcp_send_mss(sk, &size_goal, flags);
	copied = 0;

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

	while (size > 0) {
		struct sk_buff *skb = tcp_write_queue_tail(sk);
		int copy, i;
		bool can_coalesce;

963
		if (!skb || (copy = size_goal - skb->len) <= 0 ||
964
965
966
967
968
969
		    !tcp_skb_can_collapse_to(skb)) {
new_segment:
			if (!sk_stream_memory_free(sk))
				goto wait_for_sndbuf;

			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
970
					tcp_rtx_and_write_queues_empty(sk));
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
1000
			if (!skb)
				goto wait_for_memory;

			skb_entail(sk, skb);
			copy = size_goal;
		}

		if (copy > size)
			copy = size;

		i = skb_shinfo(skb)->nr_frags;
		can_coalesce = skb_can_coalesce(skb, i, page, offset);
		if (!can_coalesce && i >= sysctl_max_skb_frags) {
			tcp_mark_push(tp, skb);
			goto new_segment;
		}
		if (!sk_wmem_schedule(sk, copy))
			goto wait_for_memory;

		if (can_coalesce) {
			skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
		} else {
			get_page(page);
			skb_fill_page_desc(skb, i, page, offset, copy);
		}
		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;

		skb->len += copy;
		skb->data_len += copy;
		skb->truesize += copy;