tcp.h 35.5 KB
Newer Older
L
Linus Torvalds 已提交
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.
 *
 *		Definitions for the TCP module.
 *
 * Version:	@(#)tcp.h	1.0.5	05/23/93
 *
10
 * Authors:	Ross Biro
L
Linus Torvalds 已提交
11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *
 *		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.
 */
#ifndef _TCP_H
#define _TCP_H

#define TCP_DEBUG 1
#define FASTRETRANS_DEBUG 1

#include <linux/list.h>
#include <linux/tcp.h>
#include <linux/slab.h>
#include <linux/cache.h>
#include <linux/percpu.h>
29
#include <linux/skbuff.h>
30
#include <linux/dmaengine.h>
31
#include <linux/crypto.h>
32 33

#include <net/inet_connection_sock.h>
34
#include <net/inet_timewait_sock.h>
35
#include <net/inet_hashtables.h>
L
Linus Torvalds 已提交
36
#include <net/checksum.h>
37
#include <net/request_sock.h>
L
Linus Torvalds 已提交
38 39 40
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ip.h>
41 42
#include <net/tcp_states.h>

L
Linus Torvalds 已提交
43 44
#include <linux/seq_file.h>

45
extern struct inet_hashinfo tcp_hashinfo;
L
Linus Torvalds 已提交
46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63

extern atomic_t tcp_orphan_count;
extern void tcp_time_wait(struct sock *sk, int state, int timeo);

#define MAX_TCP_HEADER	(128 + MAX_HEADER)

/* 
 * Never offer a window over 32767 without using window scaling. Some
 * poor stacks do signed 16bit maths! 
 */
#define MAX_TCP_WINDOW		32767U

/* Minimal accepted MSS. It is (60+60+8) - (20+20). */
#define TCP_MIN_MSS		88U

/* Minimal RCV_MSS. */
#define TCP_MIN_RCVMSS		536U

J
John Heffner 已提交
64 65 66
/* The least MTU to use for probing */
#define TCP_BASE_MSS		512

L
Linus Torvalds 已提交
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
/* After receiving this amount of duplicate ACKs fast retransmit starts. */
#define TCP_FASTRETRANS_THRESH 3

/* Maximal reordering. */
#define TCP_MAX_REORDERING	127

/* Maximal number of ACKs sent quickly to accelerate slow-start. */
#define TCP_MAX_QUICKACKS	16U

/* urg_data states */
#define TCP_URG_VALID	0x0100
#define TCP_URG_NOTYET	0x0200
#define TCP_URG_READ	0x0400

#define TCP_RETR1	3	/*
				 * This is how many retries it does before it
				 * tries to figure out if the gateway is
				 * down. Minimal RFC value is 3; it corresponds
				 * to ~3sec-8min depending on RTO.
				 */

#define TCP_RETR2	15	/*
				 * This should take at least
				 * 90 minutes to time out.
				 * RFC1122 says that the limit is 100 sec.
				 * 15 is ~13-30min depending on RTO.
				 */

#define TCP_SYN_RETRIES	 5	/* number of times to retry active opening a
S
Stephen Hemminger 已提交
96
				 * connection: ~180sec is RFC minimum	*/
L
Linus Torvalds 已提交
97 98

#define TCP_SYNACK_RETRIES 5	/* number of times to retry passive opening a
S
Stephen Hemminger 已提交
99
				 * connection: ~180sec is RFC minimum	*/
L
Linus Torvalds 已提交
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


#define TCP_ORPHAN_RETRIES 7	/* number of times to retry on an orphaned
				 * socket. 7 is ~50sec-16min.
				 */


#define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT
				  * state, about 60 seconds	*/
#define TCP_FIN_TIMEOUT	TCP_TIMEWAIT_LEN
                                 /* BSD style FIN_WAIT2 deadlock breaker.
				  * It used to be 3min, new value is 60sec,
				  * to combine FIN-WAIT-2 timeout with
				  * TIME-WAIT timer.
				  */

#define TCP_DELACK_MAX	((unsigned)(HZ/5))	/* maximal time to delay before sending an ACK */
#if HZ >= 100
#define TCP_DELACK_MIN	((unsigned)(HZ/25))	/* minimal time to delay before sending an ACK */
#define TCP_ATO_MIN	((unsigned)(HZ/25))
#else
#define TCP_DELACK_MIN	4U
#define TCP_ATO_MIN	4U
#endif
#define TCP_RTO_MAX	((unsigned)(120*HZ))
#define TCP_RTO_MIN	((unsigned)(HZ/5))
#define TCP_TIMEOUT_INIT ((unsigned)(3*HZ))	/* RFC 1122 initial RTO value	*/

#define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes
					                 * for local resources.
					                 */

#define TCP_KEEPALIVE_TIME	(120*60*HZ)	/* two hours */
#define TCP_KEEPALIVE_PROBES	9		/* Max of 9 keepalive probes	*/
#define TCP_KEEPALIVE_INTVL	(75*HZ)

#define MAX_TCP_KEEPIDLE	32767
#define MAX_TCP_KEEPINTVL	32767
#define MAX_TCP_KEEPCNT		127
#define MAX_TCP_SYNCNT		127

#define TCP_SYNQ_INTERVAL	(HZ/5)	/* Period of SYNACK timer */

#define TCP_PAWS_24DAYS	(60 * 60 * 24 * 24)
#define TCP_PAWS_MSL	60		/* Per-host timestamps are invalidated
					 * after this time. It should be equal
					 * (or greater than) TCP_TIMEWAIT_LEN
					 * to provide reliability equal to one
					 * provided by timewait state.
					 */
#define TCP_PAWS_WINDOW	1		/* Replay window for per-host
					 * timestamps. It must be less than
					 * minimal timewait lifetime.
					 */
/*
 *	TCP option
 */
 
#define TCPOPT_NOP		1	/* Padding */
#define TCPOPT_EOL		0	/* End of options */
#define TCPOPT_MSS		2	/* Segment size negotiating */
#define TCPOPT_WINDOW		3	/* Window scaling */
#define TCPOPT_SACK_PERM        4       /* SACK Permitted */
#define TCPOPT_SACK             5       /* SACK Block */
#define TCPOPT_TIMESTAMP	8	/* Better RTT estimations/PAWS */
165
#define TCPOPT_MD5SIG		19	/* MD5 Signature (RFC2385) */
L
Linus Torvalds 已提交
166 167 168 169 170 171 172 173 174

/*
 *     TCP option lengths
 */

#define TCPOLEN_MSS            4
#define TCPOLEN_WINDOW         3
#define TCPOLEN_SACK_PERM      2
#define TCPOLEN_TIMESTAMP      10
175
#define TCPOLEN_MD5SIG         18
L
Linus Torvalds 已提交
176 177 178 179 180 181 182 183

/* But this is what stacks really send out. */
#define TCPOLEN_TSTAMP_ALIGNED		12
#define TCPOLEN_WSCALE_ALIGNED		4
#define TCPOLEN_SACKPERM_ALIGNED	4
#define TCPOLEN_SACK_BASE		2
#define TCPOLEN_SACK_BASE_ALIGNED	4
#define TCPOLEN_SACK_PERBLOCK		8
184
#define TCPOLEN_MD5SIG_ALIGNED		20
L
Linus Torvalds 已提交
185 186 187 188

/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF		1	/* Nagle's algo is disabled */
#define TCP_NAGLE_CORK		2	/* Socket is corked	    */
S
Stephen Hemminger 已提交
189
#define TCP_NAGLE_PUSH		4	/* Cork is overridden for already queued data */
L
Linus Torvalds 已提交
190

191 192
extern struct inet_timewait_death_row tcp_death_row;

L
Linus Torvalds 已提交
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
/* sysctl variables for tcp */
extern int sysctl_tcp_timestamps;
extern int sysctl_tcp_window_scaling;
extern int sysctl_tcp_sack;
extern int sysctl_tcp_fin_timeout;
extern int sysctl_tcp_keepalive_time;
extern int sysctl_tcp_keepalive_probes;
extern int sysctl_tcp_keepalive_intvl;
extern int sysctl_tcp_syn_retries;
extern int sysctl_tcp_synack_retries;
extern int sysctl_tcp_retries1;
extern int sysctl_tcp_retries2;
extern int sysctl_tcp_orphan_retries;
extern int sysctl_tcp_syncookies;
extern int sysctl_tcp_retrans_collapse;
extern int sysctl_tcp_stdurg;
extern int sysctl_tcp_rfc1337;
extern int sysctl_tcp_abort_on_overflow;
extern int sysctl_tcp_max_orphans;
extern int sysctl_tcp_fack;
extern int sysctl_tcp_reordering;
extern int sysctl_tcp_ecn;
extern int sysctl_tcp_dsack;
extern int sysctl_tcp_mem[3];
extern int sysctl_tcp_wmem[3];
extern int sysctl_tcp_rmem[3];
extern int sysctl_tcp_app_win;
extern int sysctl_tcp_adv_win_scale;
extern int sysctl_tcp_tw_reuse;
extern int sysctl_tcp_frto;
223
extern int sysctl_tcp_frto_response;
L
Linus Torvalds 已提交
224
extern int sysctl_tcp_low_latency;
225
extern int sysctl_tcp_dma_copybreak;
L
Linus Torvalds 已提交
226 227 228
extern int sysctl_tcp_nometrics_save;
extern int sysctl_tcp_moderate_rcvbuf;
extern int sysctl_tcp_tso_win_divisor;
229
extern int sysctl_tcp_abc;
J
John Heffner 已提交
230 231
extern int sysctl_tcp_mtu_probing;
extern int sysctl_tcp_base_mss;
232
extern int sysctl_tcp_workaround_signed_windows;
233
extern int sysctl_tcp_slow_start_after_idle;
234
extern int sysctl_tcp_max_ssthresh;
L
Linus Torvalds 已提交
235 236 237 238 239 240 241 242 243 244 245 246

extern atomic_t tcp_memory_allocated;
extern atomic_t tcp_sockets_allocated;
extern int tcp_memory_pressure;

/*
 * The next routines deal with comparing 32 bit unsigned ints
 * and worry about wraparound (automatic with unsigned arithmetic).
 */

static inline int before(__u32 seq1, __u32 seq2)
{
247
        return (__s32)(seq1-seq2) < 0;
L
Linus Torvalds 已提交
248
}
249
#define after(seq2, seq1) 	before(seq1, seq2)
L
Linus Torvalds 已提交
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275

/* is s2<=s1<=s3 ? */
static inline int between(__u32 seq1, __u32 seq2, __u32 seq3)
{
	return seq3 - seq2 >= seq1 - seq2;
}


extern struct proto tcp_prot;

DECLARE_SNMP_STAT(struct tcp_mib, tcp_statistics);
#define TCP_INC_STATS(field)		SNMP_INC_STATS(tcp_statistics, field)
#define TCP_INC_STATS_BH(field)		SNMP_INC_STATS_BH(tcp_statistics, field)
#define TCP_INC_STATS_USER(field) 	SNMP_INC_STATS_USER(tcp_statistics, field)
#define TCP_DEC_STATS(field)		SNMP_DEC_STATS(tcp_statistics, field)
#define TCP_ADD_STATS_BH(field, val)	SNMP_ADD_STATS_BH(tcp_statistics, field, val)
#define TCP_ADD_STATS_USER(field, val)	SNMP_ADD_STATS_USER(tcp_statistics, field, val)

extern void			tcp_v4_err(struct sk_buff *skb, u32);

extern void			tcp_shutdown (struct sock *sk, int how);

extern int			tcp_v4_rcv(struct sk_buff *skb);

extern int			tcp_v4_remember_stamp(struct sock *sk);

276
extern int		    	tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
L
Linus Torvalds 已提交
277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297

extern int			tcp_sendmsg(struct kiocb *iocb, struct sock *sk,
					    struct msghdr *msg, size_t size);
extern ssize_t			tcp_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags);

extern int			tcp_ioctl(struct sock *sk, 
					  int cmd, 
					  unsigned long arg);

extern int			tcp_rcv_state_process(struct sock *sk, 
						      struct sk_buff *skb,
						      struct tcphdr *th,
						      unsigned len);

extern int			tcp_rcv_established(struct sock *sk, 
						    struct sk_buff *skb,
						    struct tcphdr *th, 
						    unsigned len);

extern void			tcp_rcv_space_adjust(struct sock *sk);

298 299
extern void			tcp_cleanup_rbuf(struct sock *sk, int copied);

300 301 302
extern int			tcp_twsk_unique(struct sock *sk,
						struct sock *sktw, void *twp);

303 304
extern void			tcp_twsk_destructor(struct sock *sk);

305 306
static inline void tcp_dec_quickack_mode(struct sock *sk,
					 const unsigned int pkts)
L
Linus Torvalds 已提交
307
{
308
	struct inet_connection_sock *icsk = inet_csk(sk);
309

310 311 312
	if (icsk->icsk_ack.quick) {
		if (pkts >= icsk->icsk_ack.quick) {
			icsk->icsk_ack.quick = 0;
313
			/* Leaving quickack mode we deflate ATO. */
314
			icsk->icsk_ack.ato   = TCP_ATO_MIN;
315
		} else
316
			icsk->icsk_ack.quick -= pkts;
L
Linus Torvalds 已提交
317 318 319
	}
}

320
extern void tcp_enter_quickack_mode(struct sock *sk);
L
Linus Torvalds 已提交
321 322 323 324 325 326 327 328 329 330 331 332 333 334 335

static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
{
 	rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
}

enum tcp_tw_status
{
	TCP_TW_SUCCESS = 0,
	TCP_TW_RST = 1,
	TCP_TW_ACK = 2,
	TCP_TW_SYN = 3
};


336
extern enum tcp_tw_status	tcp_timewait_state_process(struct inet_timewait_sock *tw,
L
Linus Torvalds 已提交
337
							   struct sk_buff *skb,
338
							   const struct tcphdr *th);
L
Linus Torvalds 已提交
339 340

extern struct sock *		tcp_check_req(struct sock *sk,struct sk_buff *skb,
341 342
					      struct request_sock *req,
					      struct request_sock **prev);
L
Linus Torvalds 已提交
343 344 345
extern int			tcp_child_process(struct sock *parent,
						  struct sock *child,
						  struct sk_buff *skb);
346
extern int			tcp_use_frto(struct sock *sk);
L
Linus Torvalds 已提交
347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362
extern void			tcp_enter_frto(struct sock *sk);
extern void			tcp_enter_loss(struct sock *sk, int how);
extern void			tcp_clear_retrans(struct tcp_sock *tp);
extern void			tcp_update_metrics(struct sock *sk);

extern void			tcp_close(struct sock *sk, 
					  long timeout);
extern unsigned int		tcp_poll(struct file * file, struct socket *sock, struct poll_table_struct *wait);

extern int			tcp_getsockopt(struct sock *sk, int level, 
					       int optname,
					       char __user *optval, 
					       int __user *optlen);
extern int			tcp_setsockopt(struct sock *sk, int level, 
					       int optname, char __user *optval, 
					       int optlen);
363 364 365 366 367 368
extern int			compat_tcp_getsockopt(struct sock *sk,
					int level, int optname,
					char __user *optval, int __user *optlen);
extern int			compat_tcp_setsockopt(struct sock *sk,
					int level, int optname,
					char __user *optval, int optlen);
L
Linus Torvalds 已提交
369 370 371 372 373 374 375 376 377 378 379 380 381 382
extern void			tcp_set_keepalive(struct sock *sk, int val);
extern int			tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
					    struct msghdr *msg,
					    size_t len, int nonblock, 
					    int flags, int *addr_len);

extern void			tcp_parse_options(struct sk_buff *skb,
						  struct tcp_options_received *opt_rx,
						  int estab);

/*
 *	TCP v4 functions exported for the inet6 API
 */

383
extern void		       	tcp_v4_send_check(struct sock *sk, int len,
L
Linus Torvalds 已提交
384 385 386 387 388 389
						  struct sk_buff *skb);

extern int			tcp_v4_conn_request(struct sock *sk,
						    struct sk_buff *skb);

extern struct sock *		tcp_create_openreq_child(struct sock *sk,
390
							 struct request_sock *req,
L
Linus Torvalds 已提交
391 392 393 394
							 struct sk_buff *skb);

extern struct sock *		tcp_v4_syn_recv_sock(struct sock *sk,
						     struct sk_buff *skb,
395
						     struct request_sock *req,
L
Linus Torvalds 已提交
396 397 398 399 400 401 402 403 404 405 406 407 408
							struct dst_entry *dst);

extern int			tcp_v4_do_rcv(struct sock *sk,
					      struct sk_buff *skb);

extern int			tcp_v4_connect(struct sock *sk,
					       struct sockaddr *uaddr,
					       int addr_len);

extern int			tcp_connect(struct sock *sk);

extern struct sk_buff *		tcp_make_synack(struct sock *sk,
						struct dst_entry *dst,
409
						struct request_sock *req);
L
Linus Torvalds 已提交
410 411 412 413 414 415 416 417 418 419 420 421 422

extern int			tcp_disconnect(struct sock *sk, int flags);

extern void			tcp_unhash(struct sock *sk);

/* From syncookies.c */
extern struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, 
				    struct ip_options *opt);
extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, 
				     __u16 *mss);

/* tcp_output.c */

423
extern void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp,
424
				      unsigned int cur_mss, int nonagle);
425
extern int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp);
L
Linus Torvalds 已提交
426 427 428 429
extern int tcp_retransmit_skb(struct sock *, struct sk_buff *);
extern void tcp_xmit_retransmit_queue(struct sock *);
extern void tcp_simple_retransmit(struct sock *);
extern int tcp_trim_head(struct sock *, struct sk_buff *, u32);
430
extern int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int);
L
Linus Torvalds 已提交
431 432 433 434 435

extern void tcp_send_probe0(struct sock *);
extern void tcp_send_partial(struct sock *);
extern int  tcp_write_wakeup(struct sock *);
extern void tcp_send_fin(struct sock *sk);
A
Al Viro 已提交
436
extern void tcp_send_active_reset(struct sock *sk, gfp_t priority);
L
Linus Torvalds 已提交
437
extern int  tcp_send_synack(struct sock *);
438
extern void tcp_push_one(struct sock *, unsigned int mss_now);
L
Linus Torvalds 已提交
439 440 441
extern void tcp_send_ack(struct sock *sk);
extern void tcp_send_delayed_ack(struct sock *sk);

442 443 444
/* tcp_input.c */
extern void tcp_cwnd_application_limited(struct sock *sk);

L
Linus Torvalds 已提交
445 446
/* tcp_timer.c */
extern void tcp_init_xmit_timers(struct sock *);
447 448 449 450
static inline void tcp_clear_xmit_timers(struct sock *sk)
{
	inet_csk_clear_xmit_timers(sk);
}
L
Linus Torvalds 已提交
451 452 453 454

extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
extern unsigned int tcp_current_mss(struct sock *sk, int large);

455
/* tcp.c */
L
Linus Torvalds 已提交
456 457 458 459 460 461 462 463
extern void tcp_get_info(struct sock *, struct tcp_info *);

/* Read 'sendfile()'-style from a TCP socket */
typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
				unsigned int, size_t);
extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
			 sk_read_actor_t recv_actor);

S
Stephen Hemminger 已提交
464
extern void tcp_initialize_rcv_mss(struct sock *sk);
L
Linus Torvalds 已提交
465

J
John Heffner 已提交
466 467 468 469
extern int tcp_mtu_to_mss(struct sock *sk, int pmtu);
extern int tcp_mss_to_mtu(struct sock *sk, int mss);
extern void tcp_mtup_init(struct sock *sk);

S
Stephen Hemminger 已提交
470
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
L
Linus Torvalds 已提交
471 472 473 474 475 476
{
	tp->pred_flags = htonl((tp->tcp_header_len << 26) |
			       ntohl(TCP_FLAG_ACK) |
			       snd_wnd);
}

S
Stephen Hemminger 已提交
477
static inline void tcp_fast_path_on(struct tcp_sock *tp)
L
Linus Torvalds 已提交
478 479 480 481 482 483
{
	__tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
}

static inline void tcp_fast_path_check(struct sock *sk, struct tcp_sock *tp)
{
484
	if (skb_queue_empty(&tp->out_of_order_queue) &&
L
Linus Torvalds 已提交
485 486 487 488 489 490 491 492 493 494
	    tp->rcv_wnd &&
	    atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
	    !tp->urg_data)
		tcp_fast_path_on(tp);
}

/* Compute the actual receive window we are currently advertising.
 * Rcv_nxt can be after the window if our peer push more data
 * than the offered window.
 */
S
Stephen Hemminger 已提交
495
static inline u32 tcp_receive_window(const struct tcp_sock *tp)
L
Linus Torvalds 已提交
496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511
{
	s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt;

	if (win < 0)
		win = 0;
	return (u32) win;
}

/* Choose a new window, without checks for shrinking, and without
 * scaling applied to the result.  The caller does these things
 * if necessary.  This is a "raw" window selection.
 */
extern u32	__tcp_select_window(struct sock *sk);

/* TCP timestamps are only 32-bits, this causes a slight
 * complication on 64-bit systems since we store a snapshot
S
Stephen Hemminger 已提交
512 513
 * of jiffies in the buffer control blocks below.  We decided
 * to use only the low 32-bits of jiffies and hide the ugly
L
Linus Torvalds 已提交
514 515 516 517
 * casts with the following macro.
 */
#define tcp_time_stamp		((__u32)(jiffies))

S
Stephen Hemminger 已提交
518
/* This is what the send packet queuing engine uses to pass
L
Linus Torvalds 已提交
519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557
 * TCP per-packet control information to the transmission
 * code.  We also store the host-order sequence numbers in
 * here too.  This is 36 bytes on 32-bit architectures,
 * 40 bytes on 64-bit machines, if this grows please adjust
 * skbuff.h:skbuff->cb[xxx] size appropriately.
 */
struct tcp_skb_cb {
	union {
		struct inet_skb_parm	h4;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
		struct inet6_skb_parm	h6;
#endif
	} header;	/* For incoming frames		*/
	__u32		seq;		/* Starting sequence number	*/
	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/
	__u32		when;		/* used to compute rtt's	*/
	__u8		flags;		/* TCP header flags.		*/

	/* NOTE: These must match up to the flags byte in a
	 *       real TCP header.
	 */
#define TCPCB_FLAG_FIN		0x01
#define TCPCB_FLAG_SYN		0x02
#define TCPCB_FLAG_RST		0x04
#define TCPCB_FLAG_PSH		0x08
#define TCPCB_FLAG_ACK		0x10
#define TCPCB_FLAG_URG		0x20
#define TCPCB_FLAG_ECE		0x40
#define TCPCB_FLAG_CWR		0x80

	__u8		sacked;		/* State flags for SACK/FACK.	*/
#define TCPCB_SACKED_ACKED	0x01	/* SKB ACK'd by a SACK block	*/
#define TCPCB_SACKED_RETRANS	0x02	/* SKB retransmitted		*/
#define TCPCB_LOST		0x04	/* SKB is lost			*/
#define TCPCB_TAGBITS		0x07	/* All tag bits			*/

#define TCPCB_EVER_RETRANS	0x80	/* Ever retransmitted frame	*/
#define TCPCB_RETRANS		(TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS)

S
Stephen Hemminger 已提交
558
#define TCPCB_URG		0x20	/* Urgent pointer advanced here	*/
L
Linus Torvalds 已提交
559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574

#define TCPCB_AT_TAIL		(TCPCB_URG)

	__u16		urg_ptr;	/* Valid w/URG flags is set.	*/
	__u32		ack_seq;	/* Sequence number ACK'd	*/
};

#define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))

#include <net/tcp_ecn.h>

/* Due to TSO, an SKB can be composed of multiple actual
 * packets.  To keep these tracked properly, we use this.
 */
static inline int tcp_skb_pcount(const struct sk_buff *skb)
{
575
	return skb_shinfo(skb)->gso_segs;
L
Linus Torvalds 已提交
576 577 578 579 580
}

/* This is valid iff tcp_skb_pcount() > 1. */
static inline int tcp_skb_mss(const struct sk_buff *skb)
{
581
	return skb_shinfo(skb)->gso_size;
L
Linus Torvalds 已提交
582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601
}

static inline void tcp_dec_pcount_approx(__u32 *count,
					 const struct sk_buff *skb)
{
	if (*count) {
		*count -= tcp_skb_pcount(skb);
		if ((int)*count < 0)
			*count = 0;
	}
}

static inline void tcp_packets_out_inc(struct sock *sk, 
				       struct tcp_sock *tp,
				       const struct sk_buff *skb)
{
	int orig = tp->packets_out;

	tp->packets_out += tcp_skb_pcount(skb);
	if (!orig)
602 603
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
					  inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
L
Linus Torvalds 已提交
604 605 606 607 608 609 610 611
}

static inline void tcp_packets_out_dec(struct tcp_sock *tp, 
				       const struct sk_buff *skb)
{
	tp->packets_out -= tcp_skb_pcount(skb);
}

612 613 614 615 616 617 618 619 620 621 622 623 624 625 626
/* Events passed to congestion control interface */
enum tcp_ca_event {
	CA_EVENT_TX_START,	/* first transmit when no packets in flight */
	CA_EVENT_CWND_RESTART,	/* congestion window restart */
	CA_EVENT_COMPLETE_CWR,	/* end of congestion recovery */
	CA_EVENT_FRTO,		/* fast recovery timeout */
	CA_EVENT_LOSS,		/* loss timeout */
	CA_EVENT_FAST_ACK,	/* in sequence ack */
	CA_EVENT_SLOW_ACK,	/* other ack */
};

/*
 * Interface for adding new TCP congestion control handlers
 */
#define TCP_CA_NAME_MAX	16
627 628 629
#define TCP_CA_MAX	128
#define TCP_CA_BUF_MAX	(TCP_CA_NAME_MAX*TCP_CA_MAX)

630 631
struct tcp_congestion_ops {
	struct list_head	list;
632
	int	non_restricted;
633 634

	/* initialize private data (optional) */
635
	void (*init)(struct sock *sk);
636
	/* cleanup private data  (optional) */
637
	void (*release)(struct sock *sk);
638 639

	/* return slow start threshold (required) */
640
	u32 (*ssthresh)(struct sock *sk);
641
	/* lower bound for congestion window (optional) */
642
	u32 (*min_cwnd)(const struct sock *sk);
643
	/* do new cwnd calculation (required) */
644
	void (*cong_avoid)(struct sock *sk, u32 ack,
645 646
			   u32 rtt, u32 in_flight, int good_ack);
	/* round trip time sample per acked packet (optional) */
647
	void (*rtt_sample)(struct sock *sk, u32 usrtt);
648
	/* call before changing ca_state (optional) */
649
	void (*set_state)(struct sock *sk, u8 new_state);
650
	/* call when cwnd event occurs (optional) */
651
	void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
652
	/* new value of cwnd after loss (optional) */
653
	u32  (*undo_cwnd)(struct sock *sk);
654
	/* hook for packet ack accounting (optional) */
655
	void (*pkts_acked)(struct sock *sk, u32 num_acked);
656
	/* get info for inet_diag (optional) */
657
	void (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb);
658 659 660 661 662 663 664 665

	char 		name[TCP_CA_NAME_MAX];
	struct module 	*owner;
};

extern int tcp_register_congestion_control(struct tcp_congestion_ops *type);
extern void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);

666 667
extern void tcp_init_congestion_control(struct sock *sk);
extern void tcp_cleanup_congestion_control(struct sock *sk);
668 669
extern int tcp_set_default_congestion_control(const char *name);
extern void tcp_get_default_congestion_control(char *name);
670
extern void tcp_get_available_congestion_control(char *buf, size_t len);
671 672
extern void tcp_get_allowed_congestion_control(char *buf, size_t len);
extern int tcp_set_allowed_congestion_control(char *allowed);
673
extern int tcp_set_congestion_control(struct sock *sk, const char *name);
S
Stephen Hemminger 已提交
674
extern void tcp_slow_start(struct tcp_sock *tp);
675

676
extern struct tcp_congestion_ops tcp_init_congestion_ops;
677 678
extern u32 tcp_reno_ssthresh(struct sock *sk);
extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack,
679
				u32 rtt, u32 in_flight, int flag);
680
extern u32 tcp_reno_min_cwnd(const struct sock *sk);
681
extern struct tcp_congestion_ops tcp_reno;
682

683
static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
684
{
685 686 687 688 689
	struct inet_connection_sock *icsk = inet_csk(sk);

	if (icsk->icsk_ca_ops->set_state)
		icsk->icsk_ca_ops->set_state(sk, ca_state);
	icsk->icsk_ca_state = ca_state;
690 691
}

692
static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
693
{
694 695 696 697
	const struct inet_connection_sock *icsk = inet_csk(sk);

	if (icsk->icsk_ca_ops->cwnd_event)
		icsk->icsk_ca_ops->cwnd_event(sk, event);
698 699
}

L
Linus Torvalds 已提交
700 701 702 703 704 705 706 707 708 709 710 711 712 713
/* This determines how many packets are "in the network" to the best
 * of our knowledge.  In many cases it is conservative, but where
 * detailed information is available from the receiver (via SACK
 * blocks etc.) we can make more aggressive calculations.
 *
 * Use this for decisions involving congestion control, use just
 * tp->packets_out to determine if the send queue is empty or not.
 *
 * Read this equation as:
 *
 *	"Packets sent once on transmission queue" MINUS
 *	"Packets left network, but not honestly ACKed yet" PLUS
 *	"Packets fast retransmitted"
 */
S
Stephen Hemminger 已提交
714
static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
L
Linus Torvalds 已提交
715 716 717 718 719 720 721 722
{
	return (tp->packets_out - tp->left_out + tp->retrans_out);
}

/* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd.
 * The exception is rate halving phase, when cwnd is decreasing towards
 * ssthresh.
 */
723
static inline __u32 tcp_current_ssthresh(const struct sock *sk)
L
Linus Torvalds 已提交
724
{
725 726
	const struct tcp_sock *tp = tcp_sk(sk);
	if ((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_CWR | TCPF_CA_Recovery))
L
Linus Torvalds 已提交
727 728 729 730 731 732 733 734 735 736 737 738 739 740 741
		return tp->snd_ssthresh;
	else
		return max(tp->snd_ssthresh,
			   ((tp->snd_cwnd >> 1) +
			    (tp->snd_cwnd >> 2)));
}

static inline void tcp_sync_left_out(struct tcp_sock *tp)
{
	if (tp->rx_opt.sack_ok &&
	    (tp->sacked_out >= tp->packets_out - tp->lost_out))
		tp->sacked_out = tp->packets_out - tp->lost_out;
	tp->left_out = tp->sacked_out + tp->lost_out;
}

742
extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh);
L
Linus Torvalds 已提交
743 744 745 746 747 748 749 750 751 752
extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst);

/* Slow start with delack produces 3 packets of burst, so that
 * it is safe "de facto".
 */
static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp)
{
	return 3;
}

753 754 755 756 757 758 759 760 761 762 763
/* RFC2861 Check whether we are limited by application or congestion window
 * This is the inverse of cwnd check in tcp_tso_should_defer
 */
static inline int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	u32 left;

	if (in_flight >= tp->snd_cwnd)
		return 1;

764
	if (!sk_can_gso(sk))
765 766 767 768 769 770 771 772 773
		return 0;

	left = tp->snd_cwnd - in_flight;
	if (sysctl_tcp_tso_win_divisor)
		return left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd;
	else
		return left <= tcp_max_burst(tp);
}

S
Stephen Hemminger 已提交
774 775
static inline void tcp_minshall_update(struct tcp_sock *tp, int mss,
				       const struct sk_buff *skb)
L
Linus Torvalds 已提交
776 777 778 779 780
{
	if (skb->len < mss)
		tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
}

S
Stephen Hemminger 已提交
781
static inline void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *tp)
L
Linus Torvalds 已提交
782
{
783 784
	const struct inet_connection_sock *icsk = inet_csk(sk);
	if (!tp->packets_out && !icsk->icsk_pending)
785 786
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
					  icsk->icsk_rto, TCP_RTO_MAX);
L
Linus Torvalds 已提交
787 788
}

S
Stephen Hemminger 已提交
789 790
static inline void tcp_push_pending_frames(struct sock *sk,
					   struct tcp_sock *tp)
L
Linus Torvalds 已提交
791 792 793 794
{
	__tcp_push_pending_frames(sk, tp, tcp_current_mss(sk, 1), tp->nonagle);
}

S
Stephen Hemminger 已提交
795
static inline void tcp_init_wl(struct tcp_sock *tp, u32 ack, u32 seq)
L
Linus Torvalds 已提交
796 797 798 799
{
	tp->snd_wl1 = seq;
}

S
Stephen Hemminger 已提交
800
static inline void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq)
L
Linus Torvalds 已提交
801 802 803 804 805 806 807
{
	tp->snd_wl1 = seq;
}

/*
 * Calculate(/check) TCP checksum
 */
808 809
static inline __sum16 tcp_v4_check(int len, __be32 saddr,
				   __be32 daddr, __wsum base)
L
Linus Torvalds 已提交
810 811 812 813
{
	return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base);
}

814
static inline __sum16 __tcp_checksum_complete(struct sk_buff *skb)
L
Linus Torvalds 已提交
815
{
816
	return __skb_checksum_complete(skb);
L
Linus Torvalds 已提交
817 818
}

S
Stephen Hemminger 已提交
819
static inline int tcp_checksum_complete(struct sk_buff *skb)
L
Linus Torvalds 已提交
820 821 822 823 824 825 826
{
	return skb->ip_summed != CHECKSUM_UNNECESSARY &&
		__tcp_checksum_complete(skb);
}

/* Prequeue for VJ style copy to user, combined with checksumming. */

S
Stephen Hemminger 已提交
827
static inline void tcp_prequeue_init(struct tcp_sock *tp)
L
Linus Torvalds 已提交
828 829 830 831 832
{
	tp->ucopy.task = NULL;
	tp->ucopy.len = 0;
	tp->ucopy.memory = 0;
	skb_queue_head_init(&tp->ucopy.prequeue);
833 834 835 836 837 838
#ifdef CONFIG_NET_DMA
	tp->ucopy.dma_chan = NULL;
	tp->ucopy.wakeup = 0;
	tp->ucopy.pinned_list = NULL;
	tp->ucopy.dma_cookie = 0;
#endif
L
Linus Torvalds 已提交
839 840 841 842 843 844 845 846 847 848
}

/* Packet is added to VJ-style prequeue for processing in process
 * context, if a reader task is waiting. Apparently, this exciting
 * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
 * failed somewhere. Latency? Burstiness? Well, at least now we will
 * see, why it failed. 8)8)				  --ANK
 *
 * NOTE: is this not too big to inline?
 */
S
Stephen Hemminger 已提交
849
static inline int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
L
Linus Torvalds 已提交
850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (!sysctl_tcp_low_latency && tp->ucopy.task) {
		__skb_queue_tail(&tp->ucopy.prequeue, skb);
		tp->ucopy.memory += skb->truesize;
		if (tp->ucopy.memory > sk->sk_rcvbuf) {
			struct sk_buff *skb1;

			BUG_ON(sock_owned_by_user(sk));

			while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
				sk->sk_backlog_rcv(sk, skb1);
				NET_INC_STATS_BH(LINUX_MIB_TCPPREQUEUEDROPPED);
			}

			tp->ucopy.memory = 0;
		} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
			wake_up_interruptible(sk->sk_sleep);
869 870
			if (!inet_csk_ack_scheduled(sk))
				inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
871 872
						          (3 * TCP_RTO_MIN) / 4,
							  TCP_RTO_MAX);
L
Linus Torvalds 已提交
873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889
		}
		return 1;
	}
	return 0;
}


#undef STATE_TRACE

#ifdef STATE_TRACE
static const char *statename[]={
	"Unused","Established","Syn Sent","Syn Recv",
	"Fin Wait 1","Fin Wait 2","Time Wait", "Close",
	"Close Wait","Last ACK","Listen","Closing"
};
#endif

S
Stephen Hemminger 已提交
890
static inline void tcp_set_state(struct sock *sk, int state)
L
Linus Torvalds 已提交
891 892 893 894 895 896 897 898 899 900 901 902 903 904
{
	int oldstate = sk->sk_state;

	switch (state) {
	case TCP_ESTABLISHED:
		if (oldstate != TCP_ESTABLISHED)
			TCP_INC_STATS(TCP_MIB_CURRESTAB);
		break;

	case TCP_CLOSE:
		if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
			TCP_INC_STATS(TCP_MIB_ESTABRESETS);

		sk->sk_prot->unhash(sk);
905
		if (inet_csk(sk)->icsk_bind_hash &&
L
Linus Torvalds 已提交
906
		    !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
907
			inet_put_port(&tcp_hashinfo, sk);
L
Linus Torvalds 已提交
908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923
		/* fall through */
	default:
		if (oldstate==TCP_ESTABLISHED)
			TCP_DEC_STATS(TCP_MIB_CURRESTAB);
	}

	/* Change state AFTER socket is unhashed to avoid closed
	 * socket sitting in hash tables.
	 */
	sk->sk_state = state;

#ifdef STATE_TRACE
	SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n",sk, statename[oldstate],statename[state]);
#endif	
}

S
Stephen Hemminger 已提交
924
static inline void tcp_done(struct sock *sk)
L
Linus Torvalds 已提交
925
{
926 927 928
	if(sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
		TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);

L
Linus Torvalds 已提交
929 930 931 932 933 934 935 936
	tcp_set_state(sk, TCP_CLOSE);
	tcp_clear_xmit_timers(sk);

	sk->sk_shutdown = SHUTDOWN_MASK;

	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_state_change(sk);
	else
937
		inet_csk_destroy_sock(sk);
L
Linus Torvalds 已提交
938 939
}

S
Stephen Hemminger 已提交
940
static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
L
Linus Torvalds 已提交
941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970
{
	rx_opt->dsack = 0;
	rx_opt->eff_sacks = 0;
	rx_opt->num_sacks = 0;
}

/* Determine a window scaling and initial window to offer. */
extern void tcp_select_initial_window(int __space, __u32 mss,
				      __u32 *rcv_wnd, __u32 *window_clamp,
				      int wscale_ok, __u8 *rcv_wscale);

static inline int tcp_win_from_space(int space)
{
	return sysctl_tcp_adv_win_scale<=0 ?
		(space>>(-sysctl_tcp_adv_win_scale)) :
		space - (space>>sysctl_tcp_adv_win_scale);
}

/* Note: caller must be prepared to deal with negative returns */ 
static inline int tcp_space(const struct sock *sk)
{
	return tcp_win_from_space(sk->sk_rcvbuf -
				  atomic_read(&sk->sk_rmem_alloc));
} 

static inline int tcp_full_space(const struct sock *sk)
{
	return tcp_win_from_space(sk->sk_rcvbuf); 
}

S
Stephen Hemminger 已提交
971 972 973
static inline void tcp_openreq_init(struct request_sock *req,
				    struct tcp_options_received *rx_opt,
				    struct sk_buff *skb)
L
Linus Torvalds 已提交
974
{
975 976
	struct inet_request_sock *ireq = inet_rsk(req);

L
Linus Torvalds 已提交
977
	req->rcv_wnd = 0;		/* So that tcp_send_synack() knows! */
978
	tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
L
Linus Torvalds 已提交
979 980
	req->mss = rx_opt->mss_clamp;
	req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
981 982 983 984 985 986 987
	ireq->tstamp_ok = rx_opt->tstamp_ok;
	ireq->sack_ok = rx_opt->sack_ok;
	ireq->snd_wscale = rx_opt->snd_wscale;
	ireq->wscale_ok = rx_opt->wscale_ok;
	ireq->acked = 0;
	ireq->ecn_ok = 0;
	ireq->rmt_port = skb->h.th->source;
L
Linus Torvalds 已提交
988 989 990 991 992 993 994 995 996 997 998 999 1000 1001
}

extern void tcp_enter_memory_pressure(void);

static inline int keepalive_intvl_when(const struct tcp_sock *tp)
{
	return tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl;
}

static inline int keepalive_time_when(const struct tcp_sock *tp)
{
	return tp->keepalive_time ? : sysctl_tcp_keepalive_time;
}

1002
static inline int tcp_fin_time(const struct sock *sk)
L
Linus Torvalds 已提交
1003
{
1004 1005
	int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout;
	const int rto = inet_csk(sk)->icsk_rto;
L
Linus Torvalds 已提交
1006

1007 1008
	if (fin_timeout < (rto << 2) - (rto >> 1))
		fin_timeout = (rto << 2) - (rto >> 1);
L
Linus Torvalds 已提交
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

	return fin_timeout;
}

static inline int tcp_paws_check(const struct tcp_options_received *rx_opt, int rst)
{
	if ((s32)(rx_opt->rcv_tsval - rx_opt->ts_recent) >= 0)
		return 0;
	if (xtime.tv_sec >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)
		return 0;

	/* RST segments are not recommended to carry timestamp,
	   and, if they do, it is recommended to ignore PAWS because
	   "their cleanup function should take precedence over timestamps."
	   Certainly, it is mistake. It is necessary to understand the reasons
	   of this constraint to relax it: if peer reboots, clock may go
	   out-of-sync and half-open connections will not be reset.
	   Actually, the problem would be not existing if all
	   the implementations followed draft about maintaining clock
	   via reboots. Linux-2.2 DOES NOT!

	   However, we can relax time bounds for RST segments to MSL.
	 */
	if (rst && xtime.tv_sec >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
		return 0;
	return 1;
}

#define TCP_CHECK_TIMER(sk) do { } while (0)

static inline void tcp_mib_init(void)
{
	/* See RFC 2012 */
	TCP_ADD_STATS_USER(TCP_MIB_RTOALGORITHM, 1);
	TCP_ADD_STATS_USER(TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ);
	TCP_ADD_STATS_USER(TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ);
	TCP_ADD_STATS_USER(TCP_MIB_MAXCONN, -1);
}

1048 1049 1050 1051 1052 1053 1054 1055 1056
/*from STCP */
static inline void clear_all_retrans_hints(struct tcp_sock *tp){
	tp->lost_skb_hint = NULL;
	tp->scoreboard_skb_hint = NULL;
	tp->retransmit_skb_hint = NULL;
	tp->forward_skb_hint = NULL;
	tp->fastpath_skb_hint = NULL;
}

1057 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 1084 1085 1086 1087 1088 1089 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
/* MD5 Signature */
struct crypto_hash;

/* - key database */
struct tcp_md5sig_key {
	u8			*key;
	u8			keylen;
};

struct tcp4_md5sig_key {
	u8			*key;
	u16			keylen;
	__be32			addr;
};

struct tcp6_md5sig_key {
	u8			*key;
	u16			keylen;
#if 0
	u32			scope_id;	/* XXX */
#endif
	struct in6_addr		addr;
};

/* - sock block */
struct tcp_md5sig_info {
	struct tcp4_md5sig_key	*keys4;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
	struct tcp6_md5sig_key	*keys6;
	u32			entries6;
	u32			alloced6;
#endif
	u32			entries4;
	u32			alloced4;
};

/* - pseudo header */
struct tcp4_pseudohdr {
	__be32		saddr;
	__be32		daddr;
	__u8		pad;
	__u8		protocol;
	__be16		len;
};

struct tcp6_pseudohdr {
	struct in6_addr	saddr;
	struct in6_addr daddr;
	__be32		len;
	__be32		protocol;	/* including padding */
};

union tcp_md5sum_block {
	struct tcp4_pseudohdr ip4;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
	struct tcp6_pseudohdr ip6;
#endif
};

/* - pool: digest algorithm, hash description and scratch buffer */
struct tcp_md5sig_pool {
	struct hash_desc	md5_desc;
	union tcp_md5sum_block	md5_blk;
};

#define TCP_MD5SIG_MAXKEYS	(~(u32)0)	/* really?! */

/* - functions */
extern int			tcp_v4_calc_md5_hash(char *md5_hash,
						     struct tcp_md5sig_key *key,
						     struct sock *sk,
						     struct dst_entry *dst,
						     struct request_sock *req,
						     struct tcphdr *th,
						     int protocol, int tcplen);
extern struct tcp_md5sig_key	*tcp_v4_md5_lookup(struct sock *sk,
						   struct sock *addr_sk);

extern int			tcp_v4_md5_do_add(struct sock *sk,
						  __be32 addr,
						  u8 *newkey,
						  u8 newkeylen);

extern int			tcp_v4_md5_do_del(struct sock *sk,
1141
						  __be32 addr);
1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164

extern struct tcp_md5sig_pool	**tcp_alloc_md5sig_pool(void);
extern void			tcp_free_md5sig_pool(void);

extern struct tcp_md5sig_pool	*__tcp_get_md5sig_pool(int cpu);
extern void			__tcp_put_md5sig_pool(void);

static inline
struct tcp_md5sig_pool		*tcp_get_md5sig_pool(void)
{
	int cpu = get_cpu();
	struct tcp_md5sig_pool *ret = __tcp_get_md5sig_pool(cpu);
	if (!ret)
		put_cpu();
	return ret;
}

static inline void		tcp_put_md5sig_pool(void)
{
	__tcp_put_md5sig_pool();
	put_cpu();
}

L
Linus Torvalds 已提交
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
/* /proc */
enum tcp_seq_states {
	TCP_SEQ_STATE_LISTENING,
	TCP_SEQ_STATE_OPENREQ,
	TCP_SEQ_STATE_ESTABLISHED,
	TCP_SEQ_STATE_TIME_WAIT,
};

struct tcp_seq_afinfo {
	struct module		*owner;
	char			*name;
	sa_family_t		family;
	int			(*seq_show) (struct seq_file *m, void *v);
	struct file_operations	*seq_fops;
};

struct tcp_iter_state {
	sa_family_t		family;
	enum tcp_seq_states	state;
	struct sock		*syn_wait_sk;
	int			bucket, sbucket, num, uid;
	struct seq_operations	seq_ops;
};

extern int tcp_proc_register(struct tcp_seq_afinfo *afinfo);
extern void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo);

1192 1193 1194 1195
extern struct request_sock_ops tcp_request_sock_ops;

extern int tcp_v4_destroy_sock(struct sock *sk);

1196
extern int tcp_v4_gso_send_check(struct sk_buff *skb);
1197
extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features);
H
Herbert Xu 已提交
1198

1199 1200 1201 1202 1203
#ifdef CONFIG_PROC_FS
extern int  tcp4_proc_init(void);
extern void tcp4_proc_exit(void);
#endif

1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232
/* TCP af-specific functions */
struct tcp_sock_af_ops {
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key	*(*md5_lookup) (struct sock *sk,
						struct sock *addr_sk);
	int			(*calc_md5_hash) (char *location,
						  struct tcp_md5sig_key *md5,
						  struct sock *sk,
						  struct dst_entry *dst,
						  struct request_sock *req,
						  struct tcphdr *th,
						  int protocol, int len);
	int			(*md5_add) (struct sock *sk,
					    struct sock *addr_sk,
					    u8 *newkey,
					    u8 len);
	int			(*md5_parse) (struct sock *sk,
					      char __user *optval,
					      int optlen);
#endif
};

struct tcp_request_sock_ops {
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key	*(*md5_lookup) (struct sock *sk,
						struct request_sock *req);
#endif
};

1233 1234 1235
extern void tcp_v4_init(struct net_proto_family *ops);
extern void tcp_init(void);

L
Linus Torvalds 已提交
1236
#endif	/* _TCP_H */