aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/tcp.h
blob: ec580a560e8c3d0be363bbfe36f4b986a7acac66 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
/*
 * 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 protocol.
 *
 * Version:	@(#)tcp.h	1.0.2	04/28/93
 *
 * Author:	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 _LINUX_TCP_H
#define _LINUX_TCP_H

#include <linux/types.h>
#include <asm/byteorder.h>

struct tcphdr {
	__u16	source;
	__u16	dest;
	__u32	seq;
	__u32	ack_seq;
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u16	res1:4,
		doff:4,
		fin:1,
		syn:1,
		rst:1,
		psh:1,
		ack:1,
		urg:1,
		ece:1,
		cwr:1;
#elif defined(__BIG_ENDIAN_BITFIELD)
	__u16	doff:4,
		res1:4,
		cwr:1,
		ece:1,
		urg:1,
		ack:1,
		psh:1,
		rst:1,
		syn:1,
		fin:1;
#else
#error	"Adjust your <asm/byteorder.h> defines"
#endif	
	__u16	window;
	__u16	check;
	__u16	urg_ptr;
};


enum {
  TCP_ESTABLISHED = 1,
  TCP_SYN_SENT,
  TCP_SYN_RECV,
  TCP_FIN_WAIT1,
  TCP_FIN_WAIT2,
  TCP_TIME_WAIT,
  TCP_CLOSE,
  TCP_CLOSE_WAIT,
  TCP_LAST_ACK,
  TCP_LISTEN,
  TCP_CLOSING,	 /* now a valid state */

  TCP_MAX_STATES /* Leave at the end! */
};

#define TCP_STATE_MASK	0xF
#define TCP_ACTION_FIN	(1 << 7)

enum {
  TCPF_ESTABLISHED = (1 << 1),
  TCPF_SYN_SENT  = (1 << 2),
  TCPF_SYN_RECV  = (1 << 3),
  TCPF_FIN_WAIT1 = (1 << 4),
  TCPF_FIN_WAIT2 = (1 << 5),
  TCPF_TIME_WAIT = (1 << 6),
  TCPF_CLOSE     = (1 << 7),
  TCPF_CLOSE_WAIT = (1 << 8),
  TCPF_LAST_ACK  = (1 << 9),
  TCPF_LISTEN    = (1 << 10),
  TCPF_CLOSING   = (1 << 11) 
};

/*
 *	The union cast uses a gcc extension to avoid aliasing problems
 *  (union is compatible to any of its members)
 *  This means this part of the code is -fstrict-aliasing safe now.
 */
union tcp_word_hdr { 
	struct tcphdr hdr;
	__u32 		  words[5];
}; 

#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) 

enum { 
	TCP_FLAG_CWR = __constant_htonl(0x00800000), 
	TCP_FLAG_ECE = __constant_htonl(0x00400000), 
	TCP_FLAG_URG = __constant_htonl(0x00200000), 
	TCP_FLAG_ACK = __constant_htonl(0x00100000), 
	TCP_FLAG_PSH = __constant_htonl(0x00080000), 
	TCP_FLAG_RST = __constant_htonl(0x00040000), 
	TCP_FLAG_SYN = __constant_htonl(0x00020000), 
	TCP_FLAG_FIN = __constant_htonl(0x00010000),
	TCP_RESERVED_BITS = __constant_htonl(0x0F000000),
	TCP_DATA_OFFSET = __constant_htonl(0xF0000000)
}; 

/* TCP socket options */
#define TCP_NODELAY		1	/* Turn off Nagle's algorithm. */
#define TCP_MAXSEG		2	/* Limit MSS */
#define TCP_CORK		3	/* Never send partially complete segments */
#define TCP_KEEPIDLE		4	/* Start keeplives after this period */
#define TCP_KEEPINTVL		5	/* Interval between keepalives */
#define TCP_KEEPCNT		6	/* Number of keepalives before death */
#define TCP_SYNCNT		7	/* Number of SYN retransmits */
#define TCP_LINGER2		8	/* Life time of orphaned FIN-WAIT-2 state */
#define TCP_DEFER_ACCEPT	9	/* Wake up listener only when data arrive */
#define TCP_WINDOW_CLAMP	10	/* Bound advertised window */
#define TCP_INFO		11	/* Information about this connection. */
#define TCP_QUICKACK		12	/* Block/reenable quick acks */
#define TCP_CONGESTION		13	/* Congestion control algorithm */

#define TCPI_OPT_TIMESTAMPS	1
#define TCPI_OPT_SACK		2
#define TCPI_OPT_WSCALE		4
#define TCPI_OPT_ECN		8

enum tcp_ca_state
{
	TCP_CA_Open = 0,
#define TCPF_CA_Open	(1<<TCP_CA_Open)
	TCP_CA_Disorder = 1,
#define TCPF_CA_Disorder (1<<TCP_CA_Disorder)
	TCP_CA_CWR = 2,
#define TCPF_CA_CWR	(1<<TCP_CA_CWR)
	TCP_CA_Recovery = 3,
#define TCPF_CA_Recovery (1<<TCP_CA_Recovery)
	TCP_CA_Loss = 4
#define TCPF_CA_Loss	(1<<TCP_CA_Loss)
};

struct tcp_info
{
	__u8	tcpi_state;
	__u8	tcpi_ca_state;
	__u8	tcpi_retransmits;
	__u8	tcpi_probes;
	__u8	tcpi_backoff;
	__u8	tcpi_options;
	__u8	tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4;

	__u32	tcpi_rto;
	__u32	tcpi_ato;
	__u32	tcpi_snd_mss;
	__u32	tcpi_rcv_mss;

	__u32	tcpi_unacked;
	__u32	tcpi_sacked;
	__u32	tcpi_lost;
	__u32	tcpi_retrans;
	__u32	tcpi_fackets;

	/* Times. */
	__u32	tcpi_last_data_sent;
	__u32	tcpi_last_ack_sent;     /* Not remembered, sorry. */
	__u32	tcpi_last_data_recv;
	__u32	tcpi_last_ack_recv;

	/* Metrics. */
	__u32	tcpi_pmtu;
	__u32	tcpi_rcv_ssthresh;
	__u32	tcpi_rtt;
	__u32	tcpi_rttvar;
	__u32	tcpi_snd_ssthresh;
	__u32	tcpi_snd_cwnd;
	__u32	tcpi_advmss;
	__u32	tcpi_reordering;

	__u32	tcpi_rcv_rtt;
	__u32	tcpi_rcv_space;

	__u32	tcpi_total_retrans;
};

#ifdef __KERNEL__

#include <linux/config.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <net/sock.h>

/* This defines a selective acknowledgement block. */
struct tcp_sack_block {
	__u32	start_seq;
	__u32	end_seq;
};

struct tcp_options_received {
/*	PAWS/RTTM data	*/
	long	ts_recent_stamp;/* Time we stored ts_recent (for aging) */
	__u32	ts_recent;	/* Time stamp to echo next		*/
	__u32	rcv_tsval;	/* Time stamp value             	*/
	__u32	rcv_tsecr;	/* Time stamp echo reply        	*/
	__u16 	saw_tstamp : 1,	/* Saw TIMESTAMP on last packet		*/
		tstamp_ok : 1,	/* TIMESTAMP seen on SYN packet		*/
		dsack : 1,	/* D-SACK is scheduled			*/
		wscale_ok : 1,	/* Wscale seen on SYN packet		*/
		sack_ok : 4,	/* SACK seen on SYN packet		*/
		snd_wscale : 4,	/* Window scaling received from sender	*/
		rcv_wscale : 4;	/* Window scaling to send to receiver	*/
/*	SACKs data	*/
	__u8	eff_sacks;	/* Size of SACK array to send with next packet */
	__u8	num_sacks;	/* Number of SACK blocks		*/
	__u16	user_mss;  	/* mss requested by user in ioctl */
	__u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
};

struct tcp_request_sock {
	struct inet_request_sock req;
	__u32			 rcv_isn;
	__u32			 snt_isn;
};

static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
{
	return (struct tcp_request_sock *)req;
}

struct tcp_sock {
	/* inet_sock has to be the first member of tcp_sock */
	struct inet_sock	inet;
	int	tcp_header_len;	/* Bytes of tcp header to send		*/

/*
 *	Header prediction flags
 *	0x5?10 << 16 + snd_wnd in net byte order
 */
	__u32	pred_flags;

/*
 *	RFC793 variables by their proper names. This means you can
 *	read the code and the spec side by side (and laugh ...)
 *	See RFC793 and RFC1122. The RFC writes these in capitals.
 */
 	__u32	rcv_nxt;	/* What we want to receive next 	*/
 	__u32	snd_nxt;	/* Next sequence we send		*/

 	__u32	snd_una;	/* First byte we want an ack for	*/
 	__u32	snd_sml;	/* Last byte of the most recently transmitted small packet */
	__u32	rcv_tstamp;	/* timestamp of last received ACK (for keepalives) */
	__u32	lsndtime;	/* timestamp of last sent data packet (for restart window) */
	struct inet_bind_bucket *bind_hash;
	/* Delayed ACK control data */
	struct {
		__u8	pending;	/* ACK is pending */
		__u8	quick;		/* Scheduled number of quick acks	*/
		__u8	pingpong;	/* The session is interactive		*/
		__u8	blocked;	/* Delayed ACK was blocked by socket lock*/
		__u32	ato;		/* Predicted tick of soft clock		*/
		unsigned long timeout;	/* Currently scheduled timeout		*/
		__u32	lrcvtime;	/* timestamp of last received data packet*/
		__u16	last_seg_size;	/* Size of last incoming segment	*/
		__u16	rcv_mss;	/* MSS used for delayed ACK decisions	*/ 
	} ack;

	/* Data for direct copy to user */
	struct {
		struct sk_buff_head	prequeue;
		struct task_struct	*task;
		struct iovec		*iov;
		int			memory;
		int			len;
	} ucopy;

	__u32	snd_wl1;	/* Sequence for window update		*/
	__u32	snd_wnd;	/* The window we expect to receive	*/
	__u32	max_window;	/* Maximal window ever seen from peer	*/
	__u32	pmtu_cookie;	/* Last pmtu seen by socket		*/
	__u32	mss_cache;	/* Cached effective mss, not including SACKS */
	__u16	xmit_size_goal;	/* Goal for segmenting output packets	*/
	__u16	ext_header_len;	/* Network protocol overhead (IP/IPv6 options) */
	__u8	ca_state;	/* State of fast-retransmit machine 	*/
	__u8	retransmits;	/* Number of unrecovered RTO timeouts.	*/

	__u16	advmss;		/* Advertised MSS			*/
	__u32	window_clamp;	/* Maximal window to advertise		*/
	__u32	rcv_ssthresh;	/* Current window clamp			*/

	__u32	frto_highmark;	/* snd_nxt when RTO occurred */
	__u8	reordering;	/* Packet reordering metric.		*/
	__u8	frto_counter;	/* Number of new acks after RTO */

	__u8	unused;
	__u8	defer_accept;	/* User waits for some data after accept() */

/* RTT measurement */
	__u32	srtt;		/* smoothed round trip time << 3	*/
	__u32	mdev;		/* medium deviation			*/
	__u32	mdev_max;	/* maximal mdev for the last rtt period	*/
	__u32	rttvar;		/* smoothed mdev_max			*/
	__u32	rtt_seq;	/* sequence number to update rttvar	*/
	__u32	rto;		/* retransmit timeout			*/

	__u32	packets_out;	/* Packets which are "in flight"	*/
	__u32	left_out;	/* Packets which leaved network	*/
	__u32	retrans_out;	/* Retransmitted packets out		*/
	__u8	backoff;	/* backoff				*/
/*
 *      Options received (usually on last packet, some only on SYN packets).
 */
	__u8	nonagle;	/* Disable Nagle algorithm?             */
	__u8	keepalive_probes; /* num of allowed keep alive probes	*/

	__u8	probes_out;	/* unanswered 0 window probes		*/
	struct tcp_options_received rx_opt;

/*
 *	Slow start and congestion control (see also Nagle, and Karn & Partridge)
 */
 	__u32	snd_ssthresh;	/* Slow start size threshold		*/
 	__u32	snd_cwnd;	/* Sending congestion window		*/
 	__u16	snd_cwnd_cnt;	/* Linear increase counter		*/
	__u16	snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */
	__u32	snd_cwnd_used;
	__u32	snd_cwnd_stamp;

	/* Two commonly used timers in both sender and receiver paths. */
	unsigned long		timeout;
 	struct timer_list	retransmit_timer;	/* Resend (no ack)	*/
 	struct timer_list	delack_timer;		/* Ack delay 		*/

	struct sk_buff_head	out_of_order_queue; /* Out of order segments go here */

	struct tcp_func		*af_specific;	/* Operations which are AF_INET{4,6} specific	*/

 	__u32	rcv_wnd;	/* Current receiver window		*/
	__u32	rcv_wup;	/* rcv_nxt on last window update sent	*/
	__u32	write_seq;	/* Tail(+1) of data held in tcp send buffer */
	__u32	pushed_seq;	/* Last pushed seq, required to talk to windows */
	__u32	copied_seq;	/* Head of yet unread data		*/

/*	SACKs data	*/
	struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */
	struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/

	__u8	syn_retries;	/* num of allowed syn retries */
	__u8	ecn_flags;	/* ECN status bits.			*/
	__u16	prior_ssthresh; /* ssthresh saved at recovery start	*/
	__u32	lost_out;	/* Lost packets			*/
	__u32	sacked_out;	/* SACK'd packets			*/
	__u32	fackets_out;	/* FACK'd packets			*/
	__u32	high_seq;	/* snd_nxt at onset of congestion	*/

	__u32	retrans_stamp;	/* Timestamp of the last retransmit,
				 * also used in SYN-SENT to remember stamp of
				 * the first SYN. */
	__u32	undo_marker;	/* tracking retrans started here. */
	int	undo_retrans;	/* number of undoable retransmissions. */
	__u32	urg_seq;	/* Seq of received urgent pointer */
	__u16	urg_data;	/* Saved octet of OOB data and control flags */
	__u8	pending;	/* Scheduled timer event	*/
	__u8	urg_mode;	/* In urgent mode		*/
	__u32	snd_up;		/* Urgent pointer		*/

	__u32	total_retrans;	/* Total retransmits for entire connection */

	struct request_sock_queue accept_queue; /* FIFO of established children */

	unsigned int		keepalive_time;	  /* time before keep alive takes place */
	unsigned int		keepalive_intvl;  /* time interval between keep alive probes */
	int			linger2;

	unsigned long last_synq_overflow; 

/* Receiver side RTT estimation */
	struct {
		__u32	rtt;
		__u32	seq;
		__u32	time;
	} rcv_rtt_est;

/* Receiver queue space */
	struct {
		int	space;
		__u32	seq;
		__u32	time;
	} rcvq_space;

	/* Pluggable TCP congestion control hook */
	struct tcp_congestion_ops *ca_ops;
	u32	ca_priv[16];
#define TCP_CA_PRIV_SIZE	(16*sizeof(u32))
};

static inline struct tcp_sock *tcp_sk(const struct sock *sk)
{
	return (struct tcp_sock *)sk;
}

static inline void *tcp_ca(const struct tcp_sock *tp)
{
	return (void *) tp->ca_priv;
}

#endif

#endif	/* _LINUX_TCP_H */