tcp.c 106 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-or-later
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
/*
 * 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.
 *
 * 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>
261
#include <linux/memblock.h>
262
263
264
265
266
267
#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/time.h>
#include <linux/slab.h>
268
#include <linux/errqueue.h>
269
#include <linux/static_key.h>
270
271
272
273

#include <net/icmp.h>
#include <net/inet_common.h>
#include <net/tcp.h>
274
#include <net/mptcp.h>
275
276
277
278
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/sock.h>

279
#include <linux/uaccess.h>
280
281
282
283
284
285
286
287
288
289
290
291
#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);

292
293
294
295
296
#if IS_ENABLED(CONFIG_SMC)
DEFINE_STATIC_KEY_FALSE(tcp_have_smc);
EXPORT_SYMBOL(tcp_have_smc);
#endif

297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
/*
 * 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.
 */
318
319
unsigned long tcp_memory_pressure __read_mostly;
EXPORT_SYMBOL_GPL(tcp_memory_pressure);
320

321
322
323
324
325
DEFINE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
EXPORT_SYMBOL(tcp_rx_skb_cache_key);

DEFINE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);

326
327
void tcp_enter_memory_pressure(struct sock *sk)
{
328
329
	unsigned long val;

330
	if (READ_ONCE(tcp_memory_pressure))
331
332
333
334
335
336
		return;
	val = jiffies;

	if (!val)
		val--;
	if (!cmpxchg(&tcp_memory_pressure, 0, val))
337
338
		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES);
}
339
340
341
342
343
344
EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure);

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

345
	if (!READ_ONCE(tcp_memory_pressure))
346
347
348
349
350
351
352
		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);
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
389
390

/* 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;
}

391
392
393
394
395
396
397
398
399
400
401
402
403
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;
}

404
405
406
407
408
409
410
411
412
413
/* 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);

414
	tp->out_of_order_queue = RB_ROOT;
415
	sk->tcp_rtx_queue = RB_ROOT;
416
417
	tcp_init_xmit_timers(sk);
	INIT_LIST_HEAD(&tp->tsq_node);
418
	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
419
420
421

	icsk->icsk_rto = TCP_TIMEOUT_INIT;
	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
422
	minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
423
424
425
426
427
428
429
430

	/* 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;

431
432
433
	/* There's a bubble in the pipe until at least the first ACK. */
	tp->app_limited = ~0U;

434
435
436
437
438
439
440
441
442
443
444
	/* 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;
445
	tp->rack.reo_wnd_steps = 1;
446
447
448
449
450
451

	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
	WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
	WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
454
455

	sk_sockets_allocated_inc(sk);
456
	sk->sk_route_forced_caps = NETIF_F_GSO;
457
458
459
}
EXPORT_SYMBOL(tcp_init_sock);

460
static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
461
{
462
463
	struct sk_buff *skb = tcp_write_queue_tail(sk);

464
	if (tsflags && skb) {
465
466
467
468
469
470
471
472
473
474
475
		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;
	}
}

476
477
478
static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
					  int target, struct sock *sk)
{
479
480
481
482
483
484
485
486
487
488
489
	int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);

	if (avail > 0) {
		if (avail >= target)
			return true;
		if (tcp_rmem_pressure(sk))
			return true;
	}
	if (sk->sk_prot->stream_memory_read)
		return sk->sk_prot->stream_memory_read(sk);
	return false;
490
491
}

492
493
494
495
496
497
498
/*
 *	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.
 */
499
__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
500
{
501
	__poll_t mask;
502
503
504
505
	struct sock *sk = sock->sk;
	const struct tcp_sock *tp = tcp_sk(sk);
	int state;

506
	sock_poll_wait(file, sock, wait);
507

508
	state = inet_sk_state_load(sk);
509
510
511
512
513
514
515
516
517
518
519
	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;

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

	/* Connected or passive Fast Open socket? */
	if (state != TCP_SYN_SENT &&
553
	    (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) {
554
555
		int target = sock_rcvlowat(sk, 0, INT_MAX);

556
		if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) &&
557
558
559
560
		    !sock_flag(sk, SOCK_URGINLINE) &&
		    tp->urg_data)
			target++;

561
		if (tcp_stream_is_readable(tp, target, sk))
562
			mask |= EPOLLIN | EPOLLRDNORM;
563
564
565

		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
			if (sk_stream_is_writeable(sk)) {
566
				mask |= EPOLLOUT | EPOLLWRNORM;
567
568
569
570
571
572
573
574
575
576
577
			} 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))
578
					mask |= EPOLLOUT | EPOLLWRNORM;
579
580
			}
		} else
581
			mask |= EPOLLOUT | EPOLLWRNORM;
582
583

		if (tp->urg_data & TCP_URG_VALID)
584
			mask |= EPOLLPRI;
585
586
	} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
		/* Active TCP fastopen socket with defer_connect
587
		 * Return EPOLLOUT so application can call write()
588
589
		 * in order for kernel to generate SYN+data
		 */
590
		mask |= EPOLLOUT | EPOLLWRNORM;
591
592
593
	}
	/* This barrier is coupled with smp_wmb() in tcp_reset() */
	smp_rmb();
594
	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
595
		mask |= EPOLLERR;
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616

	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:
617
618
		answ = tp->urg_data &&
		       READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq);
619
620
621
622
623
624
625
626
		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
627
			answ = READ_ONCE(tp->write_seq) - tp->snd_una;
628
629
630
631
632
633
634
635
		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
636
637
			answ = READ_ONCE(tp->write_seq) -
			       READ_ONCE(tp->snd_nxt);
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
		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);
669
	sk_wmem_queued_add(sk, skb->truesize);
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
	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 &&
697
	       sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
698
	       !tcp_rtx_queue_empty(sk) &&
699
	       refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
700
701
}

702
703
void tcp_push(struct sock *sk, int flags, int mss_now,
	      int nonagle, int size_goal)
704
705
706
707
708
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;

	skb = tcp_write_queue_tail(sk);
709
710
	if (!skb)
		return;
711
712
713
714
715
716
717
718
	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 */
719
		if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) {
720
			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
721
			set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
722
723
724
725
		}
		/* It is possible TX completion already happened
		 * before we set TSQ_THROTTLED.
		 */
726
		if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize)
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
			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,
743
			      min(rd_desc->count, len), tss->flags);
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
	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.
				 */
818
				ret = -ENOTCONN;
819
820
821
822
823
824
				break;
			}
			if (!timeo) {
				ret = -EAGAIN;
				break;
			}
825
826
827
828
829
830
			/* 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;
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
			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;

866
867
868
869
870
871
872
873
874
875
876
877
	if (likely(!size)) {
		skb = sk->sk_tx_skb_cache;
		if (skb) {
			skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
			sk->sk_tx_skb_cache = NULL;
			pskb_trim(skb, 0);
			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
			skb_shinfo(skb)->tx_flags = 0;
			memset(TCP_SKB_CB(skb), 0, sizeof(struct tcp_skb_cb));
			return skb;
		}
	}
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
	/* 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;
901
			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
			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;

918
	if (!large_allowed)
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
		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);
}

937
int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
938
939
940
941
942
943
944
945
946
{
	int mss_now;

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

	return mss_now;
}

947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
/* In some cases, both sendpage() and sendmsg() could have added
 * an skb to the write queue, but failed adding payload on it.
 * We need to remove it to consume less memory, but more
 * importantly be able to generate EPOLLOUT for Edge Trigger epoll()
 * users.
 */
static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
{
	if (skb && !skb->len) {
		tcp_unlink_write_queue(skb, sk);
		if (tcp_write_queue_empty(sk))
			tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
		sk_wmem_free_skb(sk, skb);
	}
}

963
964
ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
			 size_t size, int flags)
965
966
967
968
969
970
971
{
	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);

972
973
974
975
	if (IS_ENABLED(CONFIG_DEBUG_VM) &&
	    WARN_ONCE(PageSlab(page), "page must not be a Slab one"))
		return -EINVAL;

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
	/* 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;

1001
		if (!skb || (copy = size_goal - skb->len) <= 0 ||
1002
1003
1004
1005
1006
1007
		    !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,
1008
					tcp_rtx_and_write_queues_empty(sk));
1009
1010
1011
			if (!skb)
				goto wait_for_memory;

1012
1013
1014
#ifdef CONFIG_TLS_DEVICE
			skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
#endif
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
			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);
		}
1037
1038
1039

		if (!(flags & MSG_NO_SHARED_FRAGS))
			skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
1040
1041
1042
1043

		skb->len += copy;
		skb->data_len += copy;
		skb->truesize += copy;
1044
		sk_wmem_queued_add(sk, copy);
1045
1046
		sk_mem_charge(sk, copy);
		skb->ip_summed = CHECKSUM_PARTIAL;
1047
		WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
1048
1049
1050
1051
1052
1053
1054
1055
1056
		TCP_SKB_CB(skb)->end_seq += copy;
		tcp_skb_pcount_set(skb, 0);

		if (!copied)
			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;

		copied += copy;
		offset += copy;
		size -= copy;
1057
		if (!size)
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
			goto out;

		if (skb->len < size_goal || (flags & MSG_OOB))
			continue;

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

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

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

		mss_now = tcp_send_mss(sk, &size_goal, flags);
	}

out:
1084
	if (copied) {
1085
		tcp_tx_timestamp(sk, sk->sk_tsflags);
1086
1087
1088
		if (!(flags & MSG_SENDPAGE_NOTLAST))
			tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
	}
1089
1090
1091
	return copied;

do_error:
1092
	tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk));
1093
1094
1095
1096
	if (copied)
		goto out;
out_err:
	/* make sure we wake any epoll edge trigger waiter */
1097
	if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
1098
		sk->sk_write_space(sk);
1099
1100
		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
	}
1101
1102
	return sk_stream_error(sk, flags, err);
}
1103
EXPORT_SYMBOL_GPL(do_tcp_sendpages);
1104

1105
1106
int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
			size_t size, int flags)
1107
{
1108
	if (!(sk->sk_route_caps & NETIF_F_SG))
1109
		return sock_no_sendpage_locked(sk, page, offset, size, flags);
1110
1111
1112

	tcp_rate_check_app_limited(sk);  /* is sending application-limited? */

1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
	return do_tcp_sendpages(sk, page, offset, size, flags);
}
EXPORT_SYMBOL_GPL(tcp_sendpage_locked);

int tcp_sendpage(struct sock *sk, struct page *page, int offset,
		 size_t size, int flags)
{
	int ret;

	lock_sock(sk);
	ret = tcp_sendpage_locked(sk, page, offset, size, flags);
1124
	release_sock(sk);
1125
1126

	return ret;
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
}
EXPORT_SYMBOL(tcp_sendpage);

void tcp_free_fastopen_req(struct tcp_sock *tp)
{
	if (tp->fastopen_req) {
		kfree(tp->fastopen_req);
		tp->fastopen_req = NULL;
	}
}

static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
1139
1140
				int *copied, size_t size,
				struct ubuf_info *uarg)
1141
1142
{
	struct tcp_sock *tp = tcp_sk(sk);
1143
1144
	struct inet_sock *inet = inet_sk(sk);
	struct sockaddr *uaddr = msg->msg_name;
1145
1146
	int err, flags;

1147
	if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
1148
1149
	    (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
	     uaddr->sa_family == AF_UNSPEC))
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
		return -EOPNOTSUPP;
	if (tp->fastopen_req)
		return -EALREADY; /* Another Fast Open is in progress */

	tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request),
				   sk->sk_allocation);
	if (unlikely(!tp->fastopen_req))
		return -ENOBUFS;
	tp->fastopen_req->data = msg;
	tp->fastopen_req->size = size;
1160
	tp->fastopen_req->uarg = uarg;
1161

1162
1163
1164
1165
1166
1167
1168
1169
1170
	if (inet->defer_connect) {
		err = tcp_connect(sk);
		/* Same failure procedure as in tcp_v4/6_connect */
		if (err) {
			tcp_set_state(sk, TCP_CLOSE);
			inet->inet_dport = 0;
			sk->sk_route_caps = 0;
		}
	}
1171
	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
	err = __inet_stream_connect(sk->sk_socket, uaddr,
				    msg->msg_namelen, flags, 1);
	/* fastopen_req could already be freed in __inet_stream_connect
	 * if the connection times out or gets rst
	 */
	if (tp->fastopen_req) {
		*copied = tp->fastopen_req->copied;
		tcp_free_fastopen_req(tp);
		inet->defer_connect = 0;
	}
1182
1183
1184
	return err;
}

1185
int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
1186
1187
{
	struct tcp_sock *tp = tcp_sk(sk);
1188
	struct ubuf_info *uarg = NULL;
1189
1190
1191
1192
	struct sk_buff *skb;
	struct sockcm_cookie sockc;
	int flags, err, copied = 0;
	int mss_now = 0, size_goal, copied_syn = 0;
1193
	int process_backlog = 0;
1194
	bool zc = false;
1195
1196
1197
	long timeo;

	flags = msg->msg_flags;
1198

1199
	if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) {
1200
		skb = tcp_write_queue_tail(sk);
1201
1202
1203
1204
1205
1206
		uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb));
		if (!uarg) {
			err = -ENOBUFS;
			goto out_err;
		}

1207
		zc = sk->sk_route_caps & NETIF_F_SG;
1208
		if (!zc)
1209
1210
1211
			uarg->zerocopy = 0;
	}

1212
1213
	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
	    !tp->repair) {
1214
		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg);
1215
1216
1217
1218
1219
1220
1221
1222
		if (err == -EINPROGRESS && copied_syn > 0)
			goto out;
		else if (err)
			goto out_err;
	}

	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

1223
1224
	tcp_rate_check_app_limited(sk);  /* is sending application-limited? */

1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
	/* 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 do_error;
	}

	if (unlikely(tp->repair)) {
		if (tp->repair_queue == TCP_RECV_QUEUE) {
			copied = tcp_send_rcvq(sk, msg, size);
			goto out_nopush;
		}

		err = -EINVAL;
		if (tp->repair_queue == TCP_NO_QUEUE)
			goto out_err;

		/* 'common' sending to sendq */
	}

1249
	sockcm_init(&sockc, sk);
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
	if (msg->msg_controllen) {
		err = sock_cmsg_send(sk, msg, &sockc);
		if (unlikely(err)) {
			err = -EINVAL;
			goto out_err;
		}
	}

	/* This should be in poll */
	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);

	/* Ok commence sending. */
	copied = 0;

restart:
	mss_now = tcp_send_mss(sk, &size_goal, flags);

	err = -EPIPE;
	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
1269
		goto do_error;
1270
1271
1272
1273
1274

	while (msg_data_left(msg)) {
		int copy = 0;

		skb = tcp_write_queue_tail(sk);
1275
1276
		if (skb)
			copy = size_goal - skb->len;
1277
1278

		if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) {
1279
1280
			bool first_skb;

1281
1282
1283
1284
new_segment:
			if (!sk_stream_memory_free(sk))
				goto wait_for_sndbuf;

1285
1286
1287
1288
			if (unlikely(process_backlog >= 16)) {
				process_backlog = 0;
				if (sk_flush_backlog(sk))
					goto restart;
1289
			}
1290
			first_skb = tcp_rtx_and_write_queues_empty(sk);
1291
			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
1292
						  first_skb);
1293
1294
1295
			if (!skb)
				goto wait_for_memory;

1296
			process_backlog++;
1297
			skb->ip_summed = CHECKSUM_PARTIAL;
1298
1299
1300
1301
1302

			skb_entail(sk, skb);
			copy = size_goal;

			/* All packets are restored as if they have
1303
			 * already been sent. skb_mstamp_ns isn't set to
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
			 * avoid wrong rtt estimation.
			 */
			if (tp->repair)
				TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
		}

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

		/* Where to copy to? */
1315
		if (skb_availroom(skb) > 0 && !zc) {
1316
1317
1318
1319
1320
			/* We have some space in skb head. Superb! */
			copy = min_t(int, copy, skb_availroom(skb));
			err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy);
			if (err)
				goto do_fault;
1321
		} else if (!zc) {
1322
1323
1324
1325
1326
1327
1328
1329
1330
			bool merge = true;
			int i = skb_shinfo(skb)->nr_frags;
			struct page_frag *pfrag = sk_page_frag(sk);

			if (!sk_page_frag_refill(sk, pfrag))
				goto wait_for_memory;

			if (!skb_can_coalesce(skb, i, pfrag->page,
					      pfrag->offset)) {
1331
				if (i >= sysctl_max_skb_frags) {
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
					tcp_mark_push(tp, skb);
					goto new_segment;
				}
				merge = false;
			}

			copy = min_t(int, copy, pfrag->size - pfrag->offset);

			if (!sk_wmem_schedule(sk, copy))
				goto wait_for_memory;

			err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
						       pfrag->page,
						       pfrag->offset,
						       copy);
			if (err)
				goto do_error;

			/* Update the skb. */
			if (merge) {
				skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
			} else {
				skb_fill_page_desc(skb, i, pfrag->page,
						   pfrag->offset, copy);
1356
				page_ref_inc(pfrag->page);
1357
1358
			}
			pfrag->offset += copy;
1359
1360
		} else {
			err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
1361
1362
			if (err == -EMSGSIZE || err == -EEXIST) {
				tcp_mark_push(tp, skb);
1363
				goto new_segment;
1364
			}
1365
1366
1367
			if (err < 0)
				goto do_error;
			copy = err;
1368
1369
1370
1371
1372
		}

		if (!copied)
			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;

1373
		WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
		TCP_SKB_CB(skb)->end_seq += copy;
		tcp_skb_pcount_set(skb, 0);

		copied += copy;
		if (!msg_data_left(msg)) {
			if (unlikely(flags & MSG_EOR))
				TCP_SKB_CB(skb)->eor = 1;
			goto out;
		}

1384
		if (skb->len < size_goal || (flags & MSG_OOB) || unlikely(tp->repair))
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
			continue;

		if (forced_push(tp)) {
			tcp_mark_push(tp, skb);
			__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
		} else if (skb == tcp_send_head(sk))
			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, flags & ~MSG_MORE, mss_now,
				 TCP_NAGLE_PUSH, size_goal);

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

		mss_now = tcp_send_mss(sk, &size_goal, flags);
	}

out:
1409
	if (copied) {
1410
		tcp_tx_timestamp(sk, sockc.tsflags);
1411
		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
1412
	}
1413
out_nopush:
1414
	sock_zerocopy_put(uarg);
1415
1416
	return copied + copied_syn;

1417
1418
do_error:
	skb = tcp_write_queue_tail(sk);
1419
do_fault:
1420
	tcp_remove_empty_skb(sk, skb);
1421
1422
1423
1424

	if (copied + copied_syn)
		goto out;
out_err:
1425
	sock_zerocopy_put_abort(uarg, true);
1426
1427
	err = sk_stream_error(sk, flags, err);
	/* make sure we wake any epoll edge trigger waiter */
1428
	if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
1429
		sk->sk_write_space(sk);
1430
1431
		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
	}
1432
1433
	return err;
}
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
EXPORT_SYMBOL_GPL(tcp_sendmsg_locked);

int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
	int ret;

	lock_sock(sk);
	ret = tcp_sendmsg_locked(sk, msg, size);
	release_sock(sk);

	return ret;
}
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
EXPORT_SYMBOL(tcp_sendmsg);

/*
 *	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, struct msghdr *msg, int len, int flags)
{
	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_to_msg(msg, &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;
}

static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
{
	struct sk_buff *skb;
	int copied = 0, err = 0;

	/* XXX -- need to support SO_PEEK_OFF */

1504
1505
1506
1507
1508
1509
1510
	skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
		err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
		if (err)
			return err;
		copied += skb->len;
	}

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
1548
1549
1550
1551
1552
1553
1554
	skb_queue_walk(&sk->sk_write_queue, skb) {
		err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
		if (err)
			break;

		copied += skb->len;
	}

	return err ?: copied;
}

/* 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.
 */
static void tcp_cleanup_rbuf(struct sock *sk, int copied)
{
	struct tcp_sock *tp = tcp_sk(sk);
	bool time_to_ack = false;

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

	WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
	     "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
	     tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);

	if (inet_csk_ack_scheduled(sk)) {
		const struct inet_connection_sock *icsk = inet_csk(sk);
		   /* Delayed ACKs frequently hit locked sockets during bulk
		    * receive. */
		if (icsk->icsk_ack.blocked ||
		    /* Once-per-two-segments ACK was not sent by tcp_input.c */
		    tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss ||
		    /*
		     * 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.
		     */
		    (copied > 0 &&
		     ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) ||
		      ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) &&
1555
		       !inet_csk_in_pingpong_mode(sk))) &&
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
		      !atomic_read(&sk->sk_rmem_alloc)))
			time_to_ack = true;
	}

	/* 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 = true;
		}
	}
	if (time_to_ack)
		tcp_send_ack(sk);
}

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

	while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
		offset = seq - TCP_SKB_CB(skb)->seq;
		if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
			pr_err_once("%s: found a SYN, please report !\n", __func__);
			offset--;
		}
		if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) {
			*off = offset;
			return skb;
		}
		/* This looks weird, but this can happen if TCP collapsing
		 * splitted a fat GRO packet, while we released socket lock
		 * in skb_splice_bits()
		 */
		sk_eat_skb(sk, 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) {
			int used;
			size_t 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 <= 0) {
				if (!copied)
					copied = used;
				break;
			} else if (used <= len) {
				seq += used;
				copied += used;
				offset += used;
			}
			/* If recv_actor drops the lock (e.g. TCP splice
			 * receive) the skb pointer might be invalid when
			 * getting here: tcp_collapse might have deleted it
			 * while aggregating skbs from the socket queue.
			 */
			skb = tcp_recv_skb(sk, seq - 1, &offset);
			if (!skb)
				break;
			/* TCP coalescing might have appended data to the skb.
			 * Try to splice more frags
			 */
			if (offset + 1 != skb->len)
				continue;
		}
		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
			sk_eat_skb(sk, skb);
			++seq;
			break;
		}
		sk_eat_skb(sk, skb);
		if (!desc->count)
			break;
1678
		WRITE_ONCE(tp->copied_seq, seq);
1679
	}
1680
	WRITE_ONCE(tp->copied_seq, seq);
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692

	tcp_rcv_space_adjust(sk);

	/* Clean up data we have read: This will do ACK frames. */
	if (copied > 0) {
		tcp_recv_skb(sk, seq, &offset);
		tcp_cleanup_rbuf(sk, copied);
	}
	return copied;
}
EXPORT_SYMBOL(tcp_read_sock);

1693
1694
1695
1696
1697
1698
int tcp_peek_len(struct socket *sock)
{
	return tcp_inq(sock->sk);
}
EXPORT_SYMBOL(tcp_peek_len);

1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
/* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */
int tcp_set_rcvlowat(struct sock *sk, int val)
{
	int cap;

	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
		cap = sk->sk_rcvbuf >> 1;
	else
		cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
	val = min(val, cap);
1709
	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
1710
1711
1712
1713
1714
1715
1716
1717
1718

	/* Check if we need to signal EPOLLIN right now */
	tcp_data_ready(sk);

	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
		return 0;

	val <<= 1;
	if (val > sk->sk_rcvbuf) {
1719
		WRITE_ONCE(sk->sk_rcvbuf, val);
1720
1721
1722
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
		tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val);
	}
	return 0;
}
EXPORT_SYMBOL(tcp_set_rcvlowat);

#ifdef CONFIG_MMU
static const struct vm_operations_struct tcp_vm_ops = {
};

int tcp_mmap(struct file *file, struct socket *sock,
	     struct vm_area_struct *vma)
{
	if (vma->vm_flags & (VM_WRITE | VM_EXEC))
		return -EPERM;
	vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);

	/* Instruct vm_insert_page() to not down_read(mmap_sem) */
	vma->vm_flags |= VM_MIXEDMAP;

	vma->vm_ops = &tcp_vm_ops;
	return 0;
}
EXPORT_SYMBOL(tcp_mmap);

static int tcp_zerocopy_receive(struct sock *sk,
				struct tcp_zerocopy_receive *zc)
{
	unsigned long address = (unsigned long)zc->address;
1749
	u32 length = 0, seq, offset, zap_len;
1750
1751
1752
1753
	const skb_frag_t *frags = NULL;
	struct vm_area_struct *vma;
	struct sk_buff *skb = NULL;
	struct tcp_sock *tp;
1754
	int inq;
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
	int ret;

	if (address & (PAGE_SIZE - 1) || address != zc->address)
		return -EINVAL;

	if (sk->sk_state == TCP_LISTEN)
		return -ENOTCONN;

	sock_rps_record_flow(sk);

	down_read(&current->mm->mmap_sem);

	vma = find_vma(current->mm, address);
1768
1769
1770
1771
	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) {
		up_read(&current->mm->mmap_sem);
		return -EINVAL;
	}
1772
1773
1774
1775
	zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);

	tp = tcp_sk(sk);
	seq = tp->copied_seq;
1776
1777
	inq = tcp_inq(sk);
	zc->length = min_t(u32, zc->length, inq);
1778
1779
1780
	zap_len = zc->length & ~(PAGE_SIZE - 1);
	if (zap_len) {
		zap_page_range(vma, address, zap_len);
1781
1782
		zc->recv_skip_hint = 0;
	} else {
1783
		zc->recv_skip_hint = zc->length;