blob: 2c14edf7b076fde57fc9e504e768184dc04e9451 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001/*
2 * INET An implementation of the TCP/IP protocol suite for the LINUX
3 * operating system. INET is implemented using the BSD Socket
4 * interface as the means of communication with the user level.
5 *
6 * Definitions for the TCP module.
7 *
8 * Version: @(#)tcp.h 1.0.5 05/23/93
9 *
Jesper Juhl02c30a82005-05-05 16:16:16 -070010 * Authors: Ross Biro
Linus Torvalds1da177e2005-04-16 15:20:36 -070011 * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
12 *
13 * This program is free software; you can redistribute it and/or
14 * modify it under the terms of the GNU General Public License
15 * as published by the Free Software Foundation; either version
16 * 2 of the License, or (at your option) any later version.
17 */
18#ifndef _TCP_H
19#define _TCP_H
20
21#define TCP_DEBUG 1
22#define FASTRETRANS_DEBUG 1
23
Linus Torvalds1da177e2005-04-16 15:20:36 -070024#include <linux/list.h>
25#include <linux/tcp.h>
26#include <linux/slab.h>
27#include <linux/cache.h>
28#include <linux/percpu.h>
Herbert Xufb286bb2005-11-10 13:01:24 -080029#include <linux/skbuff.h>
Chris Leech97fc2f02006-05-23 17:55:33 -070030#include <linux/dmaengine.h>
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -080031#include <linux/crypto.h>
Glenn Griffinc6aefaf2008-02-07 21:49:26 -080032#include <linux/cryptohash.h>
Arnaldo Carvalho de Melo3f421ba2005-08-09 20:11:08 -070033
34#include <net/inet_connection_sock.h>
Arnaldo Carvalho de Melo295ff7e2005-08-09 20:44:40 -070035#include <net/inet_timewait_sock.h>
Arnaldo Carvalho de Melo77d8bf92005-08-09 20:00:51 -070036#include <net/inet_hashtables.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -070037#include <net/checksum.h>
Arnaldo Carvalho de Melo2e6599c2005-06-18 22:46:52 -070038#include <net/request_sock.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -070039#include <net/sock.h>
40#include <net/snmp.h>
41#include <net/ip.h>
Arnaldo Carvalho de Meloc752f072005-08-09 20:08:28 -070042#include <net/tcp_states.h>
Ilpo Järvinenbdf1ee52007-05-27 02:04:16 -070043#include <net/inet_ecn.h>
Arnaldo Carvalho de Meloc752f072005-08-09 20:08:28 -070044
Linus Torvalds1da177e2005-04-16 15:20:36 -070045#include <linux/seq_file.h>
46
Arnaldo Carvalho de Melo6e04e022005-08-09 20:07:35 -070047extern struct inet_hashinfo tcp_hashinfo;
Linus Torvalds1da177e2005-04-16 15:20:36 -070048
Linus Torvalds1da177e2005-04-16 15:20:36 -070049extern atomic_t tcp_orphan_count;
Linus Torvalds1da177e2005-04-16 15:20:36 -070050extern void tcp_time_wait(struct sock *sk, int state, int timeo);
Linus Torvalds1da177e2005-04-16 15:20:36 -070051
Linus Torvalds1da177e2005-04-16 15:20:36 -070052#define MAX_TCP_HEADER (128 + MAX_HEADER)
53
54/*
55 * Never offer a window over 32767 without using window scaling. Some
56 * poor stacks do signed 16bit maths!
57 */
58#define MAX_TCP_WINDOW 32767U
59
60/* Minimal accepted MSS. It is (60+60+8) - (20+20). */
61#define TCP_MIN_MSS 88U
62
63/* Minimal RCV_MSS. */
64#define TCP_MIN_RCVMSS 536U
65
John Heffner5d424d52006-03-20 17:53:41 -080066/* The least MTU to use for probing */
67#define TCP_BASE_MSS 512
68
Linus Torvalds1da177e2005-04-16 15:20:36 -070069/* After receiving this amount of duplicate ACKs fast retransmit starts. */
70#define TCP_FASTRETRANS_THRESH 3
71
72/* Maximal reordering. */
73#define TCP_MAX_REORDERING 127
74
75/* Maximal number of ACKs sent quickly to accelerate slow-start. */
76#define TCP_MAX_QUICKACKS 16U
77
78/* urg_data states */
79#define TCP_URG_VALID 0x0100
80#define TCP_URG_NOTYET 0x0200
81#define TCP_URG_READ 0x0400
82
83#define TCP_RETR1 3 /*
84 * This is how many retries it does before it
85 * tries to figure out if the gateway is
86 * down. Minimal RFC value is 3; it corresponds
87 * to ~3sec-8min depending on RTO.
88 */
89
90#define TCP_RETR2 15 /*
91 * This should take at least
92 * 90 minutes to time out.
93 * RFC1122 says that the limit is 100 sec.
94 * 15 is ~13-30min depending on RTO.
95 */
96
97#define TCP_SYN_RETRIES 5 /* number of times to retry active opening a
Stephen Hemmingercaa20d9a2005-11-10 17:13:47 -080098 * connection: ~180sec is RFC minimum */
Linus Torvalds1da177e2005-04-16 15:20:36 -070099
100#define TCP_SYNACK_RETRIES 5 /* number of times to retry passive opening a
Stephen Hemmingercaa20d9a2005-11-10 17:13:47 -0800101 * connection: ~180sec is RFC minimum */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700102
103
104#define TCP_ORPHAN_RETRIES 7 /* number of times to retry on an orphaned
105 * socket. 7 is ~50sec-16min.
106 */
107
108
109#define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT
110 * state, about 60 seconds */
111#define TCP_FIN_TIMEOUT TCP_TIMEWAIT_LEN
112 /* BSD style FIN_WAIT2 deadlock breaker.
113 * It used to be 3min, new value is 60sec,
114 * to combine FIN-WAIT-2 timeout with
115 * TIME-WAIT timer.
116 */
117
118#define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */
119#if HZ >= 100
120#define TCP_DELACK_MIN ((unsigned)(HZ/25)) /* minimal time to delay before sending an ACK */
121#define TCP_ATO_MIN ((unsigned)(HZ/25))
122#else
123#define TCP_DELACK_MIN 4U
124#define TCP_ATO_MIN 4U
125#endif
126#define TCP_RTO_MAX ((unsigned)(120*HZ))
127#define TCP_RTO_MIN ((unsigned)(HZ/5))
128#define TCP_TIMEOUT_INIT ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value */
129
130#define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes
131 * for local resources.
132 */
133
134#define TCP_KEEPALIVE_TIME (120*60*HZ) /* two hours */
135#define TCP_KEEPALIVE_PROBES 9 /* Max of 9 keepalive probes */
136#define TCP_KEEPALIVE_INTVL (75*HZ)
137
138#define MAX_TCP_KEEPIDLE 32767
139#define MAX_TCP_KEEPINTVL 32767
140#define MAX_TCP_KEEPCNT 127
141#define MAX_TCP_SYNCNT 127
Patrick McManusec3c0982008-03-21 16:33:01 -0700142#define MAX_TCP_ACCEPT_DEFERRED 65535
Linus Torvalds1da177e2005-04-16 15:20:36 -0700143
144#define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700145
146#define TCP_PAWS_24DAYS (60 * 60 * 24 * 24)
147#define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated
148 * after this time. It should be equal
149 * (or greater than) TCP_TIMEWAIT_LEN
150 * to provide reliability equal to one
151 * provided by timewait state.
152 */
153#define TCP_PAWS_WINDOW 1 /* Replay window for per-host
154 * timestamps. It must be less than
155 * minimal timewait lifetime.
156 */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700157/*
158 * TCP option
159 */
160
161#define TCPOPT_NOP 1 /* Padding */
162#define TCPOPT_EOL 0 /* End of options */
163#define TCPOPT_MSS 2 /* Segment size negotiating */
164#define TCPOPT_WINDOW 3 /* Window scaling */
165#define TCPOPT_SACK_PERM 4 /* SACK Permitted */
166#define TCPOPT_SACK 5 /* SACK Block */
167#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -0800168#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700169
170/*
171 * TCP option lengths
172 */
173
174#define TCPOLEN_MSS 4
175#define TCPOLEN_WINDOW 3
176#define TCPOLEN_SACK_PERM 2
177#define TCPOLEN_TIMESTAMP 10
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -0800178#define TCPOLEN_MD5SIG 18
Linus Torvalds1da177e2005-04-16 15:20:36 -0700179
180/* But this is what stacks really send out. */
181#define TCPOLEN_TSTAMP_ALIGNED 12
182#define TCPOLEN_WSCALE_ALIGNED 4
183#define TCPOLEN_SACKPERM_ALIGNED 4
184#define TCPOLEN_SACK_BASE 2
185#define TCPOLEN_SACK_BASE_ALIGNED 4
186#define TCPOLEN_SACK_PERBLOCK 8
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -0800187#define TCPOLEN_MD5SIG_ALIGNED 20
Linus Torvalds1da177e2005-04-16 15:20:36 -0700188
Linus Torvalds1da177e2005-04-16 15:20:36 -0700189/* Flags in tp->nonagle */
190#define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */
191#define TCP_NAGLE_CORK 2 /* Socket is corked */
Stephen Hemmingercaa20d9a2005-11-10 17:13:47 -0800192#define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700193
Arnaldo Carvalho de Melo295ff7e2005-08-09 20:44:40 -0700194extern struct inet_timewait_death_row tcp_death_row;
195
Linus Torvalds1da177e2005-04-16 15:20:36 -0700196/* sysctl variables for tcp */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700197extern int sysctl_tcp_timestamps;
198extern int sysctl_tcp_window_scaling;
199extern int sysctl_tcp_sack;
200extern int sysctl_tcp_fin_timeout;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700201extern int sysctl_tcp_keepalive_time;
202extern int sysctl_tcp_keepalive_probes;
203extern int sysctl_tcp_keepalive_intvl;
204extern int sysctl_tcp_syn_retries;
205extern int sysctl_tcp_synack_retries;
206extern int sysctl_tcp_retries1;
207extern int sysctl_tcp_retries2;
208extern int sysctl_tcp_orphan_retries;
209extern int sysctl_tcp_syncookies;
210extern int sysctl_tcp_retrans_collapse;
211extern int sysctl_tcp_stdurg;
212extern int sysctl_tcp_rfc1337;
213extern int sysctl_tcp_abort_on_overflow;
214extern int sysctl_tcp_max_orphans;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700215extern int sysctl_tcp_fack;
216extern int sysctl_tcp_reordering;
217extern int sysctl_tcp_ecn;
218extern int sysctl_tcp_dsack;
219extern int sysctl_tcp_mem[3];
220extern int sysctl_tcp_wmem[3];
221extern int sysctl_tcp_rmem[3];
222extern int sysctl_tcp_app_win;
223extern int sysctl_tcp_adv_win_scale;
224extern int sysctl_tcp_tw_reuse;
225extern int sysctl_tcp_frto;
Ilpo Järvinen3cfe3ba2007-02-27 10:09:49 -0800226extern int sysctl_tcp_frto_response;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700227extern int sysctl_tcp_low_latency;
Chris Leech95937822006-05-23 18:02:55 -0700228extern int sysctl_tcp_dma_copybreak;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700229extern int sysctl_tcp_nometrics_save;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700230extern int sysctl_tcp_moderate_rcvbuf;
231extern int sysctl_tcp_tso_win_divisor;
Stephen Hemminger9772efb2005-11-10 17:09:53 -0800232extern int sysctl_tcp_abc;
John Heffner5d424d52006-03-20 17:53:41 -0800233extern int sysctl_tcp_mtu_probing;
234extern int sysctl_tcp_base_mss;
Rick Jones15d99e02006-03-20 22:40:29 -0800235extern int sysctl_tcp_workaround_signed_windows;
David S. Miller35089bb2006-06-13 22:33:04 -0700236extern int sysctl_tcp_slow_start_after_idle;
John Heffner886236c2007-03-25 19:21:45 -0700237extern int sysctl_tcp_max_ssthresh;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700238
239extern atomic_t tcp_memory_allocated;
240extern atomic_t tcp_sockets_allocated;
241extern int tcp_memory_pressure;
242
Linus Torvalds1da177e2005-04-16 15:20:36 -0700243/*
Linus Torvalds1da177e2005-04-16 15:20:36 -0700244 * The next routines deal with comparing 32 bit unsigned ints
245 * and worry about wraparound (automatic with unsigned arithmetic).
246 */
247
248static inline int before(__u32 seq1, __u32 seq2)
249{
Gerrit Renker0d630cc2007-01-04 12:25:16 -0800250 return (__s32)(seq1-seq2) < 0;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700251}
Gerrit Renker9a036b92006-12-20 10:25:55 -0800252#define after(seq2, seq1) before(seq1, seq2)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700253
254/* is s2<=s1<=s3 ? */
255static inline int between(__u32 seq1, __u32 seq2, __u32 seq3)
256{
257 return seq3 - seq2 >= seq1 - seq2;
258}
259
Pavel Emelianove4fd5da2007-05-29 13:19:18 -0700260static inline int tcp_too_many_orphans(struct sock *sk, int num)
261{
262 return (num > sysctl_tcp_max_orphans) ||
263 (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
264 atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]);
265}
Linus Torvalds1da177e2005-04-16 15:20:36 -0700266
267extern struct proto tcp_prot;
268
269DECLARE_SNMP_STAT(struct tcp_mib, tcp_statistics);
270#define TCP_INC_STATS(field) SNMP_INC_STATS(tcp_statistics, field)
271#define TCP_INC_STATS_BH(field) SNMP_INC_STATS_BH(tcp_statistics, field)
272#define TCP_INC_STATS_USER(field) SNMP_INC_STATS_USER(tcp_statistics, field)
273#define TCP_DEC_STATS(field) SNMP_DEC_STATS(tcp_statistics, field)
274#define TCP_ADD_STATS_BH(field, val) SNMP_ADD_STATS_BH(tcp_statistics, field, val)
275#define TCP_ADD_STATS_USER(field, val) SNMP_ADD_STATS_USER(tcp_statistics, field, val)
276
Linus Torvalds1da177e2005-04-16 15:20:36 -0700277extern void tcp_v4_err(struct sk_buff *skb, u32);
278
279extern void tcp_shutdown (struct sock *sk, int how);
280
281extern int tcp_v4_rcv(struct sk_buff *skb);
282
283extern int tcp_v4_remember_stamp(struct sock *sk);
284
Arnaldo Carvalho de Melo8feaf0c2005-08-09 20:09:30 -0700285extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700286
David S. Miller3516ffb2007-08-02 19:23:56 -0700287extern int tcp_sendmsg(struct kiocb *iocb, struct socket *sock,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700288 struct msghdr *msg, size_t size);
289extern ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags);
290
291extern int tcp_ioctl(struct sock *sk,
292 int cmd,
293 unsigned long arg);
294
295extern int tcp_rcv_state_process(struct sock *sk,
296 struct sk_buff *skb,
297 struct tcphdr *th,
298 unsigned len);
299
300extern int tcp_rcv_established(struct sock *sk,
301 struct sk_buff *skb,
302 struct tcphdr *th,
303 unsigned len);
304
305extern void tcp_rcv_space_adjust(struct sock *sk);
306
Chris Leech0e4b4992006-05-23 18:00:16 -0700307extern void tcp_cleanup_rbuf(struct sock *sk, int copied);
308
Arnaldo Carvalho de Melo6d6ee432005-12-13 23:25:19 -0800309extern int tcp_twsk_unique(struct sock *sk,
310 struct sock *sktw, void *twp);
311
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -0800312extern void tcp_twsk_destructor(struct sock *sk);
313
Jens Axboe9c55e012007-11-06 23:30:13 -0800314extern ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
315 struct pipe_inode_info *pipe, size_t len, unsigned int flags);
316
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700317static inline void tcp_dec_quickack_mode(struct sock *sk,
318 const unsigned int pkts)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700319{
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700320 struct inet_connection_sock *icsk = inet_csk(sk);
David S. Millerfc6415b2005-07-05 15:17:45 -0700321
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700322 if (icsk->icsk_ack.quick) {
323 if (pkts >= icsk->icsk_ack.quick) {
324 icsk->icsk_ack.quick = 0;
David S. Millerfc6415b2005-07-05 15:17:45 -0700325 /* Leaving quickack mode we deflate ATO. */
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700326 icsk->icsk_ack.ato = TCP_ATO_MIN;
David S. Millerfc6415b2005-07-05 15:17:45 -0700327 } else
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700328 icsk->icsk_ack.quick -= pkts;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700329 }
330}
331
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700332extern void tcp_enter_quickack_mode(struct sock *sk);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700333
Linus Torvalds1da177e2005-04-16 15:20:36 -0700334static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
335{
336 rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
337}
338
Ilpo Järvinenbdf1ee52007-05-27 02:04:16 -0700339#define TCP_ECN_OK 1
340#define TCP_ECN_QUEUE_CWR 2
341#define TCP_ECN_DEMAND_CWR 4
342
343static __inline__ void
344TCP_ECN_create_request(struct request_sock *req, struct tcphdr *th)
345{
346 if (sysctl_tcp_ecn && th->ece && th->cwr)
347 inet_rsk(req)->ecn_ok = 1;
348}
349
Linus Torvalds1da177e2005-04-16 15:20:36 -0700350enum tcp_tw_status
351{
352 TCP_TW_SUCCESS = 0,
353 TCP_TW_RST = 1,
354 TCP_TW_ACK = 2,
355 TCP_TW_SYN = 3
356};
357
358
Arnaldo Carvalho de Melo8feaf0c2005-08-09 20:09:30 -0700359extern enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700360 struct sk_buff *skb,
Arnaldo Carvalho de Melo8feaf0c2005-08-09 20:09:30 -0700361 const struct tcphdr *th);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700362
363extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb,
Arnaldo Carvalho de Melo60236fd2005-06-18 22:47:21 -0700364 struct request_sock *req,
365 struct request_sock **prev);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700366extern int tcp_child_process(struct sock *parent,
367 struct sock *child,
368 struct sk_buff *skb);
Ilpo Järvinen46d0de42007-02-21 23:10:39 -0800369extern int tcp_use_frto(struct sock *sk);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700370extern void tcp_enter_frto(struct sock *sk);
371extern void tcp_enter_loss(struct sock *sk, int how);
372extern void tcp_clear_retrans(struct tcp_sock *tp);
373extern void tcp_update_metrics(struct sock *sk);
374
375extern void tcp_close(struct sock *sk,
376 long timeout);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700377extern unsigned int tcp_poll(struct file * file, struct socket *sock, struct poll_table_struct *wait);
378
379extern int tcp_getsockopt(struct sock *sk, int level,
380 int optname,
381 char __user *optval,
382 int __user *optlen);
383extern int tcp_setsockopt(struct sock *sk, int level,
384 int optname, char __user *optval,
385 int optlen);
Dmitry Mishin3fdadf72006-03-20 22:45:21 -0800386extern int compat_tcp_getsockopt(struct sock *sk,
387 int level, int optname,
388 char __user *optval, int __user *optlen);
389extern int compat_tcp_setsockopt(struct sock *sk,
390 int level, int optname,
391 char __user *optval, int optlen);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700392extern void tcp_set_keepalive(struct sock *sk, int val);
393extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
394 struct msghdr *msg,
395 size_t len, int nonblock,
396 int flags, int *addr_len);
397
Linus Torvalds1da177e2005-04-16 15:20:36 -0700398extern void tcp_parse_options(struct sk_buff *skb,
399 struct tcp_options_received *opt_rx,
400 int estab);
401
402/*
403 * TCP v4 functions exported for the inet6 API
404 */
405
Arnaldo Carvalho de Melo8292a172005-12-13 23:15:52 -0800406extern void tcp_v4_send_check(struct sock *sk, int len,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700407 struct sk_buff *skb);
408
409extern int tcp_v4_conn_request(struct sock *sk,
410 struct sk_buff *skb);
411
412extern struct sock * tcp_create_openreq_child(struct sock *sk,
Arnaldo Carvalho de Melo60236fd2005-06-18 22:47:21 -0700413 struct request_sock *req,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700414 struct sk_buff *skb);
415
416extern struct sock * tcp_v4_syn_recv_sock(struct sock *sk,
417 struct sk_buff *skb,
Arnaldo Carvalho de Melo60236fd2005-06-18 22:47:21 -0700418 struct request_sock *req,
Linus Torvalds1da177e2005-04-16 15:20:36 -0700419 struct dst_entry *dst);
420
421extern int tcp_v4_do_rcv(struct sock *sk,
422 struct sk_buff *skb);
423
424extern int tcp_v4_connect(struct sock *sk,
425 struct sockaddr *uaddr,
426 int addr_len);
427
428extern int tcp_connect(struct sock *sk);
429
430extern struct sk_buff * tcp_make_synack(struct sock *sk,
431 struct dst_entry *dst,
Arnaldo Carvalho de Melo60236fd2005-06-18 22:47:21 -0700432 struct request_sock *req);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700433
434extern int tcp_disconnect(struct sock *sk, int flags);
435
436extern void tcp_unhash(struct sock *sk);
437
Linus Torvalds1da177e2005-04-16 15:20:36 -0700438/* From syncookies.c */
Florian Westphal2051f112008-03-23 22:21:28 -0700439extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
Linus Torvalds1da177e2005-04-16 15:20:36 -0700440extern struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
441 struct ip_options *opt);
442extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb,
443 __u16 *mss);
444
Florian Westphal4dfc2812008-04-10 03:12:40 -0700445extern __u32 cookie_init_timestamp(struct request_sock *req);
446extern void cookie_check_timestamp(struct tcp_options_received *tcp_opt);
447
Glenn Griffinc6aefaf2008-02-07 21:49:26 -0800448/* From net/ipv6/syncookies.c */
449extern struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
450extern __u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb,
451 __u16 *mss);
452
Linus Torvalds1da177e2005-04-16 15:20:36 -0700453/* tcp_output.c */
454
Ilpo Järvinen9e412ba2007-04-20 22:18:02 -0700455extern void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
456 int nonagle);
457extern int tcp_may_send_now(struct sock *sk);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700458extern int tcp_retransmit_skb(struct sock *, struct sk_buff *);
459extern void tcp_xmit_retransmit_queue(struct sock *);
460extern void tcp_simple_retransmit(struct sock *);
461extern int tcp_trim_head(struct sock *, struct sk_buff *, u32);
David S. Miller6475be12005-09-01 22:47:01 -0700462extern int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700463
464extern void tcp_send_probe0(struct sock *);
465extern void tcp_send_partial(struct sock *);
466extern int tcp_write_wakeup(struct sock *);
467extern void tcp_send_fin(struct sock *sk);
Al Virodd0fc662005-10-07 07:46:04 +0100468extern void tcp_send_active_reset(struct sock *sk, gfp_t priority);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700469extern int tcp_send_synack(struct sock *);
David S. Millerc1b4a7e2005-07-05 15:24:38 -0700470extern void tcp_push_one(struct sock *, unsigned int mss_now);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700471extern void tcp_send_ack(struct sock *sk);
472extern void tcp_send_delayed_ack(struct sock *sk);
473
David S. Millera762a982005-07-05 15:18:51 -0700474/* tcp_input.c */
475extern void tcp_cwnd_application_limited(struct sock *sk);
476
Linus Torvalds1da177e2005-04-16 15:20:36 -0700477/* tcp_timer.c */
478extern void tcp_init_xmit_timers(struct sock *);
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700479static inline void tcp_clear_xmit_timers(struct sock *sk)
480{
481 inet_csk_clear_xmit_timers(sk);
482}
Linus Torvalds1da177e2005-04-16 15:20:36 -0700483
Linus Torvalds1da177e2005-04-16 15:20:36 -0700484extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
485extern unsigned int tcp_current_mss(struct sock *sk, int large);
486
Arnaldo Carvalho de Melo17b085e2005-08-12 12:59:17 -0300487/* tcp.c */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700488extern void tcp_get_info(struct sock *, struct tcp_info *);
489
490/* Read 'sendfile()'-style from a TCP socket */
491typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
492 unsigned int, size_t);
493extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
494 sk_read_actor_t recv_actor);
495
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800496extern void tcp_initialize_rcv_mss(struct sock *sk);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700497
John Heffner5d424d52006-03-20 17:53:41 -0800498extern int tcp_mtu_to_mss(struct sock *sk, int pmtu);
499extern int tcp_mss_to_mtu(struct sock *sk, int mss);
500extern void tcp_mtup_init(struct sock *sk);
501
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800502static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700503{
504 tp->pred_flags = htonl((tp->tcp_header_len << 26) |
505 ntohl(TCP_FLAG_ACK) |
506 snd_wnd);
507}
508
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800509static inline void tcp_fast_path_on(struct tcp_sock *tp)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700510{
511 __tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
512}
513
Ilpo Järvinen9e412ba2007-04-20 22:18:02 -0700514static inline void tcp_fast_path_check(struct sock *sk)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700515{
Ilpo Järvinen9e412ba2007-04-20 22:18:02 -0700516 struct tcp_sock *tp = tcp_sk(sk);
517
David S. Millerb03efcf2005-07-08 14:57:23 -0700518 if (skb_queue_empty(&tp->out_of_order_queue) &&
Linus Torvalds1da177e2005-04-16 15:20:36 -0700519 tp->rcv_wnd &&
520 atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
521 !tp->urg_data)
522 tcp_fast_path_on(tp);
523}
524
525/* Compute the actual receive window we are currently advertising.
526 * Rcv_nxt can be after the window if our peer push more data
527 * than the offered window.
528 */
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800529static inline u32 tcp_receive_window(const struct tcp_sock *tp)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700530{
531 s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt;
532
533 if (win < 0)
534 win = 0;
535 return (u32) win;
536}
537
538/* Choose a new window, without checks for shrinking, and without
539 * scaling applied to the result. The caller does these things
540 * if necessary. This is a "raw" window selection.
541 */
542extern u32 __tcp_select_window(struct sock *sk);
543
544/* TCP timestamps are only 32-bits, this causes a slight
545 * complication on 64-bit systems since we store a snapshot
Stephen Hemminger31f34262005-11-15 15:17:10 -0800546 * of jiffies in the buffer control blocks below. We decided
547 * to use only the low 32-bits of jiffies and hide the ugly
Linus Torvalds1da177e2005-04-16 15:20:36 -0700548 * casts with the following macro.
549 */
550#define tcp_time_stamp ((__u32)(jiffies))
551
Stephen Hemmingercaa20d9a2005-11-10 17:13:47 -0800552/* This is what the send packet queuing engine uses to pass
Linus Torvalds1da177e2005-04-16 15:20:36 -0700553 * TCP per-packet control information to the transmission
554 * code. We also store the host-order sequence numbers in
555 * here too. This is 36 bytes on 32-bit architectures,
556 * 40 bytes on 64-bit machines, if this grows please adjust
557 * skbuff.h:skbuff->cb[xxx] size appropriately.
558 */
559struct tcp_skb_cb {
560 union {
561 struct inet_skb_parm h4;
562#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
563 struct inet6_skb_parm h6;
564#endif
565 } header; /* For incoming frames */
566 __u32 seq; /* Starting sequence number */
567 __u32 end_seq; /* SEQ + FIN + SYN + datalen */
568 __u32 when; /* used to compute rtt's */
569 __u8 flags; /* TCP header flags. */
570
571 /* NOTE: These must match up to the flags byte in a
572 * real TCP header.
573 */
574#define TCPCB_FLAG_FIN 0x01
575#define TCPCB_FLAG_SYN 0x02
576#define TCPCB_FLAG_RST 0x04
577#define TCPCB_FLAG_PSH 0x08
578#define TCPCB_FLAG_ACK 0x10
579#define TCPCB_FLAG_URG 0x20
580#define TCPCB_FLAG_ECE 0x40
581#define TCPCB_FLAG_CWR 0x80
582
583 __u8 sacked; /* State flags for SACK/FACK. */
584#define TCPCB_SACKED_ACKED 0x01 /* SKB ACK'd by a SACK block */
585#define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */
586#define TCPCB_LOST 0x04 /* SKB is lost */
587#define TCPCB_TAGBITS 0x07 /* All tag bits */
588
589#define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */
590#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS)
591
Linus Torvalds1da177e2005-04-16 15:20:36 -0700592 __u16 urg_ptr; /* Valid w/URG flags is set. */
593 __u32 ack_seq; /* Sequence number ACK'd */
594};
595
596#define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0]))
597
Linus Torvalds1da177e2005-04-16 15:20:36 -0700598/* Due to TSO, an SKB can be composed of multiple actual
599 * packets. To keep these tracked properly, we use this.
600 */
601static inline int tcp_skb_pcount(const struct sk_buff *skb)
602{
Herbert Xu79671682006-06-22 02:40:14 -0700603 return skb_shinfo(skb)->gso_segs;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700604}
605
606/* This is valid iff tcp_skb_pcount() > 1. */
607static inline int tcp_skb_mss(const struct sk_buff *skb)
608{
Herbert Xu79671682006-06-22 02:40:14 -0700609 return skb_shinfo(skb)->gso_size;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700610}
611
Ilpo Järvinenaf610b42007-06-15 12:58:38 +0300612static inline void tcp_dec_pcount_approx_int(__u32 *count, const int decr)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700613{
614 if (*count) {
Ilpo Järvinenaf610b42007-06-15 12:58:38 +0300615 *count -= decr;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700616 if ((int)*count < 0)
617 *count = 0;
618 }
619}
620
Ilpo Järvinenaf610b42007-06-15 12:58:38 +0300621static inline void tcp_dec_pcount_approx(__u32 *count,
622 const struct sk_buff *skb)
623{
624 tcp_dec_pcount_approx_int(count, tcp_skb_pcount(skb));
625}
626
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700627/* Events passed to congestion control interface */
628enum tcp_ca_event {
629 CA_EVENT_TX_START, /* first transmit when no packets in flight */
630 CA_EVENT_CWND_RESTART, /* congestion window restart */
631 CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */
632 CA_EVENT_FRTO, /* fast recovery timeout */
633 CA_EVENT_LOSS, /* loss timeout */
634 CA_EVENT_FAST_ACK, /* in sequence ack */
635 CA_EVENT_SLOW_ACK, /* other ack */
636};
637
638/*
639 * Interface for adding new TCP congestion control handlers
640 */
641#define TCP_CA_NAME_MAX 16
Stephen Hemminger3ff825b2006-11-09 16:32:06 -0800642#define TCP_CA_MAX 128
643#define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX)
644
Stephen Hemminger164891a2007-04-23 22:26:16 -0700645#define TCP_CONG_NON_RESTRICTED 0x1
646#define TCP_CONG_RTT_STAMP 0x2
647
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700648struct tcp_congestion_ops {
649 struct list_head list;
Stephen Hemminger164891a2007-04-23 22:26:16 -0700650 unsigned long flags;
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700651
652 /* initialize private data (optional) */
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300653 void (*init)(struct sock *sk);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700654 /* cleanup private data (optional) */
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300655 void (*release)(struct sock *sk);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700656
657 /* return slow start threshold (required) */
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300658 u32 (*ssthresh)(struct sock *sk);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700659 /* lower bound for congestion window (optional) */
Stephen Hemminger72dc5b92006-06-05 17:30:08 -0700660 u32 (*min_cwnd)(const struct sock *sk);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700661 /* do new cwnd calculation (required) */
Ilpo Järvinenc3a05c62007-12-02 00:47:59 +0200662 void (*cong_avoid)(struct sock *sk, u32 ack, u32 in_flight);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700663 /* call before changing ca_state (optional) */
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300664 void (*set_state)(struct sock *sk, u8 new_state);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700665 /* call when cwnd event occurs (optional) */
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300666 void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700667 /* new value of cwnd after loss (optional) */
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300668 u32 (*undo_cwnd)(struct sock *sk);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700669 /* hook for packet ack accounting (optional) */
Stephen Hemminger30cfd0b2007-07-25 23:49:34 -0700670 void (*pkts_acked)(struct sock *sk, u32 num_acked, s32 rtt_us);
Arnaldo Carvalho de Melo73c1f4a2005-08-12 12:51:49 -0300671 /* get info for inet_diag (optional) */
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300672 void (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700673
674 char name[TCP_CA_NAME_MAX];
675 struct module *owner;
676};
677
678extern int tcp_register_congestion_control(struct tcp_congestion_ops *type);
679extern void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
680
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300681extern void tcp_init_congestion_control(struct sock *sk);
682extern void tcp_cleanup_congestion_control(struct sock *sk);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700683extern int tcp_set_default_congestion_control(const char *name);
684extern void tcp_get_default_congestion_control(char *name);
Stephen Hemminger3ff825b2006-11-09 16:32:06 -0800685extern void tcp_get_available_congestion_control(char *buf, size_t len);
Stephen Hemmingerce7bc3b2006-11-09 16:35:15 -0800686extern void tcp_get_allowed_congestion_control(char *buf, size_t len);
687extern int tcp_set_allowed_congestion_control(char *allowed);
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300688extern int tcp_set_congestion_control(struct sock *sk, const char *name);
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800689extern void tcp_slow_start(struct tcp_sock *tp);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700690
Stephen Hemminger5f8ef482005-06-23 20:37:36 -0700691extern struct tcp_congestion_ops tcp_init_congestion_ops;
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300692extern u32 tcp_reno_ssthresh(struct sock *sk);
Ilpo Järvinenc3a05c62007-12-02 00:47:59 +0200693extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight);
Stephen Hemminger72dc5b92006-06-05 17:30:08 -0700694extern u32 tcp_reno_min_cwnd(const struct sock *sk);
David S. Millera8acfba2005-06-23 23:45:02 -0700695extern struct tcp_congestion_ops tcp_reno;
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700696
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300697static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700698{
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300699 struct inet_connection_sock *icsk = inet_csk(sk);
700
701 if (icsk->icsk_ca_ops->set_state)
702 icsk->icsk_ca_ops->set_state(sk, ca_state);
703 icsk->icsk_ca_state = ca_state;
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700704}
705
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300706static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700707{
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300708 const struct inet_connection_sock *icsk = inet_csk(sk);
709
710 if (icsk->icsk_ca_ops->cwnd_event)
711 icsk->icsk_ca_ops->cwnd_event(sk, event);
Stephen Hemminger317a76f2005-06-23 12:19:55 -0700712}
713
Ilpo Järvinene60402d2007-08-09 15:14:46 +0300714/* These functions determine how the current flow behaves in respect of SACK
715 * handling. SACK is negotiated with the peer, and therefore it can vary
716 * between different flows.
717 *
718 * tcp_is_sack - SACK enabled
719 * tcp_is_reno - No SACK
720 * tcp_is_fack - FACK enabled, implies SACK enabled
721 */
722static inline int tcp_is_sack(const struct tcp_sock *tp)
723{
724 return tp->rx_opt.sack_ok;
725}
726
727static inline int tcp_is_reno(const struct tcp_sock *tp)
728{
729 return !tcp_is_sack(tp);
730}
731
732static inline int tcp_is_fack(const struct tcp_sock *tp)
733{
734 return tp->rx_opt.sack_ok & 2;
735}
736
737static inline void tcp_enable_fack(struct tcp_sock *tp)
738{
739 tp->rx_opt.sack_ok |= 2;
740}
741
Ilpo Järvinen83ae4082007-08-09 14:37:30 +0300742static inline unsigned int tcp_left_out(const struct tcp_sock *tp)
743{
744 return tp->sacked_out + tp->lost_out;
745}
746
Linus Torvalds1da177e2005-04-16 15:20:36 -0700747/* This determines how many packets are "in the network" to the best
748 * of our knowledge. In many cases it is conservative, but where
749 * detailed information is available from the receiver (via SACK
750 * blocks etc.) we can make more aggressive calculations.
751 *
752 * Use this for decisions involving congestion control, use just
753 * tp->packets_out to determine if the send queue is empty or not.
754 *
755 * Read this equation as:
756 *
757 * "Packets sent once on transmission queue" MINUS
758 * "Packets left network, but not honestly ACKed yet" PLUS
759 * "Packets fast retransmitted"
760 */
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800761static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700762{
Ilpo Järvinen83ae4082007-08-09 14:37:30 +0300763 return tp->packets_out - tcp_left_out(tp) + tp->retrans_out;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700764}
765
Ilpo Järvinen882beba2008-04-07 22:33:07 -0700766extern int tcp_limit_reno_sacked(struct tcp_sock *tp);
767
Linus Torvalds1da177e2005-04-16 15:20:36 -0700768/* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd.
769 * The exception is rate halving phase, when cwnd is decreasing towards
770 * ssthresh.
771 */
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300772static inline __u32 tcp_current_ssthresh(const struct sock *sk)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700773{
Arnaldo Carvalho de Melo6687e982005-08-10 04:03:31 -0300774 const struct tcp_sock *tp = tcp_sk(sk);
775 if ((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_CWR | TCPF_CA_Recovery))
Linus Torvalds1da177e2005-04-16 15:20:36 -0700776 return tp->snd_ssthresh;
777 else
778 return max(tp->snd_ssthresh,
779 ((tp->snd_cwnd >> 1) +
780 (tp->snd_cwnd >> 2)));
781}
782
Ilpo Järvinenb9c45952007-07-27 16:36:17 +0300783/* Use define here intentionally to get WARN_ON location shown at the caller */
784#define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700785
Ilpo Järvinen3cfe3ba2007-02-27 10:09:49 -0800786extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700787extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst);
788
789/* Slow start with delack produces 3 packets of burst, so that
790 * it is safe "de facto".
791 */
792static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp)
793{
794 return 3;
795}
796
Ilpo Järvinen90840de2007-12-31 04:48:41 -0800797/* Returns end sequence number of the receiver's advertised window */
798static inline u32 tcp_wnd_end(const struct tcp_sock *tp)
799{
800 return tp->snd_una + tp->snd_wnd;
801}
Ilpo Järvinencea14e02008-01-12 03:19:12 -0800802extern int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight);
Stephen Hemmingerf4805ed2005-11-10 16:53:30 -0800803
Chuck Leverc1bd24b2007-10-23 21:08:54 -0700804static inline void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss,
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800805 const struct sk_buff *skb)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700806{
807 if (skb->len < mss)
808 tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
809}
810
Ilpo Järvinen9e412ba2007-04-20 22:18:02 -0700811static inline void tcp_check_probe_timer(struct sock *sk)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700812{
Ilpo Järvinen9e412ba2007-04-20 22:18:02 -0700813 struct tcp_sock *tp = tcp_sk(sk);
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700814 const struct inet_connection_sock *icsk = inet_csk(sk);
Ilpo Järvinen9e412ba2007-04-20 22:18:02 -0700815
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700816 if (!tp->packets_out && !icsk->icsk_pending)
Arnaldo Carvalho de Melo3f421ba2005-08-09 20:11:08 -0700817 inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
818 icsk->icsk_rto, TCP_RTO_MAX);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700819}
820
Ilpo Järvinen9e412ba2007-04-20 22:18:02 -0700821static inline void tcp_push_pending_frames(struct sock *sk)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700822{
Ilpo Järvinen9e412ba2007-04-20 22:18:02 -0700823 struct tcp_sock *tp = tcp_sk(sk);
824
825 __tcp_push_pending_frames(sk, tcp_current_mss(sk, 1), tp->nonagle);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700826}
827
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800828static inline void tcp_init_wl(struct tcp_sock *tp, u32 ack, u32 seq)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700829{
830 tp->snd_wl1 = seq;
831}
832
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800833static inline void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700834{
835 tp->snd_wl1 = seq;
836}
837
Linus Torvalds1da177e2005-04-16 15:20:36 -0700838/*
839 * Calculate(/check) TCP checksum
840 */
Frederik Deweerdtba7808e2007-02-04 20:15:27 -0800841static inline __sum16 tcp_v4_check(int len, __be32 saddr,
842 __be32 daddr, __wsum base)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700843{
844 return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base);
845}
846
Al Virob51655b2006-11-14 21:40:42 -0800847static inline __sum16 __tcp_checksum_complete(struct sk_buff *skb)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700848{
Herbert Xufb286bb2005-11-10 13:01:24 -0800849 return __skb_checksum_complete(skb);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700850}
851
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800852static inline int tcp_checksum_complete(struct sk_buff *skb)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700853{
Herbert Xu60476372007-04-09 11:59:39 -0700854 return !skb_csum_unnecessary(skb) &&
Linus Torvalds1da177e2005-04-16 15:20:36 -0700855 __tcp_checksum_complete(skb);
856}
857
858/* Prequeue for VJ style copy to user, combined with checksumming. */
859
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800860static inline void tcp_prequeue_init(struct tcp_sock *tp)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700861{
862 tp->ucopy.task = NULL;
863 tp->ucopy.len = 0;
864 tp->ucopy.memory = 0;
865 skb_queue_head_init(&tp->ucopy.prequeue);
Chris Leech97fc2f02006-05-23 17:55:33 -0700866#ifdef CONFIG_NET_DMA
867 tp->ucopy.dma_chan = NULL;
868 tp->ucopy.wakeup = 0;
869 tp->ucopy.pinned_list = NULL;
870 tp->ucopy.dma_cookie = 0;
871#endif
Linus Torvalds1da177e2005-04-16 15:20:36 -0700872}
873
874/* Packet is added to VJ-style prequeue for processing in process
875 * context, if a reader task is waiting. Apparently, this exciting
876 * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
877 * failed somewhere. Latency? Burstiness? Well, at least now we will
878 * see, why it failed. 8)8) --ANK
879 *
880 * NOTE: is this not too big to inline?
881 */
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800882static inline int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700883{
884 struct tcp_sock *tp = tcp_sk(sk);
885
886 if (!sysctl_tcp_low_latency && tp->ucopy.task) {
887 __skb_queue_tail(&tp->ucopy.prequeue, skb);
888 tp->ucopy.memory += skb->truesize;
889 if (tp->ucopy.memory > sk->sk_rcvbuf) {
890 struct sk_buff *skb1;
891
892 BUG_ON(sock_owned_by_user(sk));
893
894 while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
895 sk->sk_backlog_rcv(sk, skb1);
896 NET_INC_STATS_BH(LINUX_MIB_TCPPREQUEUEDROPPED);
897 }
898
899 tp->ucopy.memory = 0;
900 } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
901 wake_up_interruptible(sk->sk_sleep);
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700902 if (!inet_csk_ack_scheduled(sk))
903 inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
Arnaldo Carvalho de Melo3f421ba2005-08-09 20:11:08 -0700904 (3 * TCP_RTO_MIN) / 4,
905 TCP_RTO_MAX);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700906 }
907 return 1;
908 }
909 return 0;
910}
911
912
913#undef STATE_TRACE
914
915#ifdef STATE_TRACE
916static const char *statename[]={
917 "Unused","Established","Syn Sent","Syn Recv",
918 "Fin Wait 1","Fin Wait 2","Time Wait", "Close",
919 "Close Wait","Last ACK","Listen","Closing"
920};
921#endif
Ilpo Järvinen490d5042008-01-12 03:17:20 -0800922extern void tcp_set_state(struct sock *sk, int state);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700923
Andi Kleen4ac02ba2007-04-20 17:11:46 -0700924extern void tcp_done(struct sock *sk);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700925
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800926static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700927{
928 rx_opt->dsack = 0;
929 rx_opt->eff_sacks = 0;
930 rx_opt->num_sacks = 0;
931}
932
Linus Torvalds1da177e2005-04-16 15:20:36 -0700933/* Determine a window scaling and initial window to offer. */
934extern void tcp_select_initial_window(int __space, __u32 mss,
935 __u32 *rcv_wnd, __u32 *window_clamp,
936 int wscale_ok, __u8 *rcv_wscale);
937
938static inline int tcp_win_from_space(int space)
939{
940 return sysctl_tcp_adv_win_scale<=0 ?
941 (space>>(-sysctl_tcp_adv_win_scale)) :
942 space - (space>>sysctl_tcp_adv_win_scale);
943}
944
945/* Note: caller must be prepared to deal with negative returns */
946static inline int tcp_space(const struct sock *sk)
947{
948 return tcp_win_from_space(sk->sk_rcvbuf -
949 atomic_read(&sk->sk_rmem_alloc));
950}
951
952static inline int tcp_full_space(const struct sock *sk)
953{
954 return tcp_win_from_space(sk->sk_rcvbuf);
955}
956
Stephen Hemminger40efc6f2006-01-03 16:03:49 -0800957static inline void tcp_openreq_init(struct request_sock *req,
958 struct tcp_options_received *rx_opt,
959 struct sk_buff *skb)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700960{
Arnaldo Carvalho de Melo2e6599c2005-06-18 22:46:52 -0700961 struct inet_request_sock *ireq = inet_rsk(req);
962
Linus Torvalds1da177e2005-04-16 15:20:36 -0700963 req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */
Florian Westphal4dfc2812008-04-10 03:12:40 -0700964 req->cookie_ts = 0;
Arnaldo Carvalho de Melo2e6599c2005-06-18 22:46:52 -0700965 tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700966 req->mss = rx_opt->mss_clamp;
967 req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
Arnaldo Carvalho de Melo2e6599c2005-06-18 22:46:52 -0700968 ireq->tstamp_ok = rx_opt->tstamp_ok;
969 ireq->sack_ok = rx_opt->sack_ok;
970 ireq->snd_wscale = rx_opt->snd_wscale;
971 ireq->wscale_ok = rx_opt->wscale_ok;
972 ireq->acked = 0;
973 ireq->ecn_ok = 0;
Arnaldo Carvalho de Meloaa8223c2007-04-10 21:04:22 -0700974 ireq->rmt_port = tcp_hdr(skb)->source;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700975}
976
977extern void tcp_enter_memory_pressure(void);
978
Linus Torvalds1da177e2005-04-16 15:20:36 -0700979static inline int keepalive_intvl_when(const struct tcp_sock *tp)
980{
981 return tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl;
982}
983
984static inline int keepalive_time_when(const struct tcp_sock *tp)
985{
986 return tp->keepalive_time ? : sysctl_tcp_keepalive_time;
987}
988
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700989static inline int tcp_fin_time(const struct sock *sk)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700990{
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700991 int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout;
992 const int rto = inet_csk(sk)->icsk_rto;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700993
Arnaldo Carvalho de Melo463c84b2005-08-09 20:10:42 -0700994 if (fin_timeout < (rto << 2) - (rto >> 1))
995 fin_timeout = (rto << 2) - (rto >> 1);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700996
997 return fin_timeout;
998}
999
1000static inline int tcp_paws_check(const struct tcp_options_received *rx_opt, int rst)
1001{
1002 if ((s32)(rx_opt->rcv_tsval - rx_opt->ts_recent) >= 0)
1003 return 0;
James Morris9d729f72007-03-04 16:12:44 -08001004 if (get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)
Linus Torvalds1da177e2005-04-16 15:20:36 -07001005 return 0;
1006
1007 /* RST segments are not recommended to carry timestamp,
1008 and, if they do, it is recommended to ignore PAWS because
1009 "their cleanup function should take precedence over timestamps."
1010 Certainly, it is mistake. It is necessary to understand the reasons
1011 of this constraint to relax it: if peer reboots, clock may go
1012 out-of-sync and half-open connections will not be reset.
1013 Actually, the problem would be not existing if all
1014 the implementations followed draft about maintaining clock
1015 via reboots. Linux-2.2 DOES NOT!
1016
1017 However, we can relax time bounds for RST segments to MSL.
1018 */
James Morris9d729f72007-03-04 16:12:44 -08001019 if (rst && get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
Linus Torvalds1da177e2005-04-16 15:20:36 -07001020 return 0;
1021 return 1;
1022}
1023
Linus Torvalds1da177e2005-04-16 15:20:36 -07001024#define TCP_CHECK_TIMER(sk) do { } while (0)
1025
Linus Torvalds1da177e2005-04-16 15:20:36 -07001026static inline void tcp_mib_init(void)
1027{
1028 /* See RFC 2012 */
1029 TCP_ADD_STATS_USER(TCP_MIB_RTOALGORITHM, 1);
1030 TCP_ADD_STATS_USER(TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ);
1031 TCP_ADD_STATS_USER(TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ);
1032 TCP_ADD_STATS_USER(TCP_MIB_MAXCONN, -1);
1033}
1034
Ilpo Järvinen5af4ec22007-09-20 11:30:48 -07001035/* from STCP */
David S. Miller0800f172007-09-20 11:40:37 -07001036static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp)
1037{
Stephen Hemminger6a438bb2005-11-10 17:14:59 -08001038 tp->lost_skb_hint = NULL;
1039 tp->scoreboard_skb_hint = NULL;
1040 tp->retransmit_skb_hint = NULL;
1041 tp->forward_skb_hint = NULL;
Ilpo Järvinenb7689202007-09-20 11:37:19 -07001042}
1043
David S. Miller0800f172007-09-20 11:40:37 -07001044static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp)
1045{
Ilpo Järvinenb7689202007-09-20 11:37:19 -07001046 tcp_clear_retrans_hints_partial(tp);
Stephen Hemminger6a438bb2005-11-10 17:14:59 -08001047}
1048
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -08001049/* MD5 Signature */
1050struct crypto_hash;
1051
1052/* - key database */
1053struct tcp_md5sig_key {
1054 u8 *key;
1055 u8 keylen;
1056};
1057
1058struct tcp4_md5sig_key {
David S. Millerf8ab18d2007-09-28 15:18:35 -07001059 struct tcp_md5sig_key base;
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -08001060 __be32 addr;
1061};
1062
1063struct tcp6_md5sig_key {
David S. Millerf8ab18d2007-09-28 15:18:35 -07001064 struct tcp_md5sig_key base;
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -08001065#if 0
1066 u32 scope_id; /* XXX */
1067#endif
1068 struct in6_addr addr;
1069};
1070
1071/* - sock block */
1072struct tcp_md5sig_info {
1073 struct tcp4_md5sig_key *keys4;
1074#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
1075 struct tcp6_md5sig_key *keys6;
1076 u32 entries6;
1077 u32 alloced6;
1078#endif
1079 u32 entries4;
1080 u32 alloced4;
1081};
1082
1083/* - pseudo header */
1084struct tcp4_pseudohdr {
1085 __be32 saddr;
1086 __be32 daddr;
1087 __u8 pad;
1088 __u8 protocol;
1089 __be16 len;
1090};
1091
1092struct tcp6_pseudohdr {
1093 struct in6_addr saddr;
1094 struct in6_addr daddr;
1095 __be32 len;
1096 __be32 protocol; /* including padding */
1097};
1098
1099union tcp_md5sum_block {
1100 struct tcp4_pseudohdr ip4;
1101#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
1102 struct tcp6_pseudohdr ip6;
1103#endif
1104};
1105
1106/* - pool: digest algorithm, hash description and scratch buffer */
1107struct tcp_md5sig_pool {
1108 struct hash_desc md5_desc;
1109 union tcp_md5sum_block md5_blk;
1110};
1111
1112#define TCP_MD5SIG_MAXKEYS (~(u32)0) /* really?! */
1113
1114/* - functions */
1115extern int tcp_v4_calc_md5_hash(char *md5_hash,
1116 struct tcp_md5sig_key *key,
1117 struct sock *sk,
1118 struct dst_entry *dst,
1119 struct request_sock *req,
1120 struct tcphdr *th,
YOSHIFUJI Hideaki9cb57342008-01-12 02:16:03 -08001121 int protocol,
1122 unsigned int tcplen);
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -08001123extern struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
1124 struct sock *addr_sk);
1125
1126extern int tcp_v4_md5_do_add(struct sock *sk,
1127 __be32 addr,
1128 u8 *newkey,
1129 u8 newkeylen);
1130
1131extern int tcp_v4_md5_do_del(struct sock *sk,
Al Viro8e5200f2006-11-20 18:06:37 -08001132 __be32 addr);
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -08001133
1134extern struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(void);
1135extern void tcp_free_md5sig_pool(void);
1136
1137extern struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu);
1138extern void __tcp_put_md5sig_pool(void);
1139
1140static inline
1141struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
1142{
1143 int cpu = get_cpu();
1144 struct tcp_md5sig_pool *ret = __tcp_get_md5sig_pool(cpu);
1145 if (!ret)
1146 put_cpu();
1147 return ret;
1148}
1149
1150static inline void tcp_put_md5sig_pool(void)
1151{
1152 __tcp_put_md5sig_pool();
1153 put_cpu();
1154}
1155
David S. Millerfe067e82007-03-07 12:12:44 -08001156/* write queue abstraction */
1157static inline void tcp_write_queue_purge(struct sock *sk)
1158{
1159 struct sk_buff *skb;
1160
1161 while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
Hideo Aoki3ab224b2007-12-31 00:11:19 -08001162 sk_wmem_free_skb(sk, skb);
1163 sk_mem_reclaim(sk);
David S. Millerfe067e82007-03-07 12:12:44 -08001164}
1165
1166static inline struct sk_buff *tcp_write_queue_head(struct sock *sk)
1167{
1168 struct sk_buff *skb = sk->sk_write_queue.next;
1169 if (skb == (struct sk_buff *) &sk->sk_write_queue)
1170 return NULL;
1171 return skb;
1172}
1173
1174static inline struct sk_buff *tcp_write_queue_tail(struct sock *sk)
1175{
1176 struct sk_buff *skb = sk->sk_write_queue.prev;
1177 if (skb == (struct sk_buff *) &sk->sk_write_queue)
1178 return NULL;
1179 return skb;
1180}
1181
1182static inline struct sk_buff *tcp_write_queue_next(struct sock *sk, struct sk_buff *skb)
1183{
1184 return skb->next;
1185}
1186
1187#define tcp_for_write_queue(skb, sk) \
1188 for (skb = (sk)->sk_write_queue.next; \
1189 (skb != (struct sk_buff *)&(sk)->sk_write_queue); \
1190 skb = skb->next)
1191
1192#define tcp_for_write_queue_from(skb, sk) \
1193 for (; (skb != (struct sk_buff *)&(sk)->sk_write_queue);\
1194 skb = skb->next)
1195
Ilpo Järvinen234b6862007-12-02 00:48:02 +02001196#define tcp_for_write_queue_from_safe(skb, tmp, sk) \
1197 for (tmp = skb->next; \
1198 (skb != (struct sk_buff *)&(sk)->sk_write_queue); \
1199 skb = tmp, tmp = skb->next)
1200
David S. Millerfe067e82007-03-07 12:12:44 -08001201static inline struct sk_buff *tcp_send_head(struct sock *sk)
1202{
1203 return sk->sk_send_head;
1204}
1205
1206static inline void tcp_advance_send_head(struct sock *sk, struct sk_buff *skb)
1207{
1208 sk->sk_send_head = skb->next;
1209 if (sk->sk_send_head == (struct sk_buff *)&sk->sk_write_queue)
1210 sk->sk_send_head = NULL;
1211}
1212
1213static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked)
1214{
1215 if (sk->sk_send_head == skb_unlinked)
1216 sk->sk_send_head = NULL;
1217}
1218
1219static inline void tcp_init_send_head(struct sock *sk)
1220{
1221 sk->sk_send_head = NULL;
1222}
1223
1224static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
1225{
1226 __skb_queue_tail(&sk->sk_write_queue, skb);
1227}
1228
1229static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
1230{
1231 __tcp_add_write_queue_tail(sk, skb);
1232
1233 /* Queue it, remembering where we must start sending. */
Ilpo Järvinen6859d492007-12-02 00:48:06 +02001234 if (sk->sk_send_head == NULL) {
David S. Millerfe067e82007-03-07 12:12:44 -08001235 sk->sk_send_head = skb;
Ilpo Järvinen6859d492007-12-02 00:48:06 +02001236
1237 if (tcp_sk(sk)->highest_sack == NULL)
1238 tcp_sk(sk)->highest_sack = skb;
1239 }
David S. Millerfe067e82007-03-07 12:12:44 -08001240}
1241
1242static inline void __tcp_add_write_queue_head(struct sock *sk, struct sk_buff *skb)
1243{
1244 __skb_queue_head(&sk->sk_write_queue, skb);
1245}
1246
1247/* Insert buff after skb on the write queue of sk. */
1248static inline void tcp_insert_write_queue_after(struct sk_buff *skb,
1249 struct sk_buff *buff,
1250 struct sock *sk)
1251{
Gerrit Renker7de6c032008-04-14 00:05:09 -07001252 __skb_queue_after(&sk->sk_write_queue, skb, buff);
David S. Millerfe067e82007-03-07 12:12:44 -08001253}
1254
1255/* Insert skb between prev and next on the write queue of sk. */
1256static inline void tcp_insert_write_queue_before(struct sk_buff *new,
1257 struct sk_buff *skb,
1258 struct sock *sk)
1259{
1260 __skb_insert(new, skb->prev, skb, &sk->sk_write_queue);
Ilpo Järvinen6e421412007-11-19 23:24:09 -08001261
1262 if (sk->sk_send_head == skb)
1263 sk->sk_send_head = new;
David S. Millerfe067e82007-03-07 12:12:44 -08001264}
1265
1266static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk)
1267{
1268 __skb_unlink(skb, &sk->sk_write_queue);
1269}
1270
1271static inline int tcp_skb_is_last(const struct sock *sk,
1272 const struct sk_buff *skb)
1273{
1274 return skb->next == (struct sk_buff *)&sk->sk_write_queue;
1275}
1276
1277static inline int tcp_write_queue_empty(struct sock *sk)
1278{
1279 return skb_queue_empty(&sk->sk_write_queue);
1280}
1281
Ilpo Järvinena47e5a92007-11-15 19:41:46 -08001282/* Start sequence of the highest skb with SACKed bit, valid only if
1283 * sacked > 0 or when the caller has ensured validity by itself.
1284 */
1285static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp)
1286{
1287 if (!tp->sacked_out)
1288 return tp->snd_una;
Ilpo Järvinen6859d492007-12-02 00:48:06 +02001289
1290 if (tp->highest_sack == NULL)
1291 return tp->snd_nxt;
1292
Ilpo Järvinena47e5a92007-11-15 19:41:46 -08001293 return TCP_SKB_CB(tp->highest_sack)->seq;
1294}
1295
Ilpo Järvinen6859d492007-12-02 00:48:06 +02001296static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb)
1297{
1298 tcp_sk(sk)->highest_sack = tcp_skb_is_last(sk, skb) ? NULL :
1299 tcp_write_queue_next(sk, skb);
1300}
1301
1302static inline struct sk_buff *tcp_highest_sack(struct sock *sk)
1303{
1304 return tcp_sk(sk)->highest_sack;
1305}
1306
1307static inline void tcp_highest_sack_reset(struct sock *sk)
1308{
1309 tcp_sk(sk)->highest_sack = tcp_write_queue_head(sk);
1310}
1311
1312/* Called when old skb is about to be deleted (to be combined with new skb) */
1313static inline void tcp_highest_sack_combine(struct sock *sk,
1314 struct sk_buff *old,
1315 struct sk_buff *new)
1316{
1317 if (tcp_sk(sk)->sacked_out && (old == tcp_sk(sk)->highest_sack))
1318 tcp_sk(sk)->highest_sack = new;
1319}
1320
Linus Torvalds1da177e2005-04-16 15:20:36 -07001321/* /proc */
1322enum tcp_seq_states {
1323 TCP_SEQ_STATE_LISTENING,
1324 TCP_SEQ_STATE_OPENREQ,
1325 TCP_SEQ_STATE_ESTABLISHED,
1326 TCP_SEQ_STATE_TIME_WAIT,
1327};
1328
1329struct tcp_seq_afinfo {
Linus Torvalds1da177e2005-04-16 15:20:36 -07001330 char *name;
1331 sa_family_t family;
Denis V. Lunev68fcadd2008-04-13 22:13:30 -07001332 struct file_operations seq_fops;
Denis V. Lunev9427c4b2008-04-13 22:12:13 -07001333 struct seq_operations seq_ops;
Linus Torvalds1da177e2005-04-16 15:20:36 -07001334};
1335
1336struct tcp_iter_state {
Denis V. Luneva4146b12008-04-13 22:11:14 -07001337 struct seq_net_private p;
Linus Torvalds1da177e2005-04-16 15:20:36 -07001338 sa_family_t family;
1339 enum tcp_seq_states state;
1340 struct sock *syn_wait_sk;
1341 int bucket, sbucket, num, uid;
Linus Torvalds1da177e2005-04-16 15:20:36 -07001342};
1343
Daniel Lezcano6f8b13b2008-03-21 04:14:45 -07001344extern int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo);
1345extern void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo);
Linus Torvalds1da177e2005-04-16 15:20:36 -07001346
Arnaldo Carvalho de Melo20380732005-08-16 02:18:02 -03001347extern struct request_sock_ops tcp_request_sock_ops;
Glenn Griffinc6aefaf2008-02-07 21:49:26 -08001348extern struct request_sock_ops tcp6_request_sock_ops;
Arnaldo Carvalho de Melo20380732005-08-16 02:18:02 -03001349
1350extern int tcp_v4_destroy_sock(struct sock *sk);
1351
Herbert Xua430a432006-07-08 13:34:56 -07001352extern int tcp_v4_gso_send_check(struct sk_buff *skb);
Herbert Xu576a30e2006-06-27 13:22:38 -07001353extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features);
Herbert Xuf4c50d92006-06-22 03:02:40 -07001354
Arnaldo Carvalho de Melo20380732005-08-16 02:18:02 -03001355#ifdef CONFIG_PROC_FS
1356extern int tcp4_proc_init(void);
1357extern void tcp4_proc_exit(void);
1358#endif
1359
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -08001360/* TCP af-specific functions */
1361struct tcp_sock_af_ops {
1362#ifdef CONFIG_TCP_MD5SIG
1363 struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk,
1364 struct sock *addr_sk);
1365 int (*calc_md5_hash) (char *location,
1366 struct tcp_md5sig_key *md5,
1367 struct sock *sk,
1368 struct dst_entry *dst,
1369 struct request_sock *req,
1370 struct tcphdr *th,
YOSHIFUJI Hideaki9cb57342008-01-12 02:16:03 -08001371 int protocol,
1372 unsigned int len);
YOSHIFUJI Hideakicfb6eeb2006-11-14 19:07:45 -08001373 int (*md5_add) (struct sock *sk,
1374 struct sock *addr_sk,
1375 u8 *newkey,
1376 u8 len);
1377 int (*md5_parse) (struct sock *sk,
1378 char __user *optval,
1379 int optlen);
1380#endif
1381};
1382
1383struct tcp_request_sock_ops {
1384#ifdef CONFIG_TCP_MD5SIG
1385 struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk,
1386 struct request_sock *req);
1387#endif
1388};
1389
Denis V. Lunev9b0f9762008-02-29 11:13:15 -08001390extern void tcp_v4_init(void);
Arnaldo Carvalho de Melo20380732005-08-16 02:18:02 -03001391extern void tcp_init(void);
1392
Linus Torvalds1da177e2005-04-16 15:20:36 -07001393#endif /* _TCP_H */