tcp.h

linux 内核源代码

/*
 * 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
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <[e-mail]>
 *
 *		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>
#include <linux/skbuff.h>
#include <linux/dmaengine.h>
#include <linux/crypto.h>

#include <net/inet_connection_sock.h>
#include <net/inet_timewait_sock.h>
#include <net/inet_hashtables.h>
#include <net/checksum.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/tcp_states.h>
#include <net/inet_ecn.h>

#include <linux/seq_file.h>

extern struct inet_hashinfo tcp_hashinfo;

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

/* The least MTU to use for probing */
#define TCP_BASE_MSS		512

/* 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
				 * connection: ~180sec is RFC minimum	*/

#define TCP_SYNACK_RETRIES 5	/* number of times to retry passive opening a
				 * connection: ~180sec is RFC minimum	*/


#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 */
#define TCPOPT_MD5SIG		19	/* MD5 Signature (RFC2385) */

/*
 *     TCP option lengths
 */

#define TCPOLEN_MSS            4
#define TCPOLEN_WINDOW         3
#define TCPOLEN_SACK_PERM      2
#define TCPOLEN_TIMESTAMP      10
#define TCPOLEN_MD5SIG         18

/* 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
#define TCPOLEN_MD5SIG_ALIGNED		20

/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF		1	/* Nagle's algo is disabled */
#define TCP_NAGLE_CORK		2	/* Socket is corked	    */
#define TCP_NAGLE_PUSH		4	/* Cork is overridden for already queued data */

extern struct inet_timewait_death_row tcp_death_row;

/* 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;
extern int sysctl_tcp_frto_response;
extern int sysctl_tcp_low_latency;
extern int sysctl_tcp_dma_copybreak;
extern int sysctl_tcp_nometrics_save;
extern int sysctl_tcp_moderate_rcvbuf;
extern int sysctl_tcp_tso_win_divisor;
extern int sysctl_tcp_abc;
extern int sysctl_tcp_mtu_probing;
extern int sysctl_tcp_base_mss;
extern int sysctl_tcp_workaround_signed_windows;
extern int sysctl_tcp_slow_start_after_idle;
extern int sysctl_tcp_max_ssthresh;

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)
{
        return (__s32)(seq1-seq2) < 0;
}
#define after(seq2, seq1) 	before(seq1, seq2)

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

static inline int tcp_too_many_orphans(struct sock *sk, int num)
{
	return (num > sysctl_tcp_max_orphans) ||
		(sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
		 atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]);
}

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);

extern int		    	tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);

extern int			tcp_sendmsg(struct kiocb *iocb, struct socket *sock,
					    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);

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

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

extern void			tcp_twsk_destructor(struct sock *sk);

static inline void tcp_dec_quickack_mode(struct sock *sk,
					 const unsigned int pkts)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	if (icsk->icsk_ack.quick) {
		if (pkts >= icsk->icsk_ack.quick) {
			icsk->icsk_ack.quick = 0;
			/* Leaving quickack mode we deflate ATO. */
			icsk->icsk_ack.ato   = TCP_ATO_MIN;
		} else
			icsk->icsk_ack.quick -= pkts;
	}
}

extern void tcp_enter_quickack_mode(struct sock *sk);

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;
}

#define	TCP_ECN_OK		1
#define	TCP_ECN_QUEUE_CWR	2
#define	TCP_ECN_DEMAND_CWR	4

static __inline__ void
TCP_ECN_create_request(struct request_sock *req, struct tcphdr *th)
{
	if (sysctl_tcp_ecn && th->ece && th->cwr)
		inet_rsk(req)->ecn_ok = 1;
}

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


extern enum tcp_tw_status	tcp_timewait_state_process(struct inet_timewait_sock *tw,
							   struct sk_buff *skb,
							   const struct tcphdr *th);

extern struct sock *		tcp_check_req(struct sock *sk,struct sk_buff *skb,
					      struct request_sock *req,
					      struct request_sock **prev);
extern int			tcp_child_process(struct sock *parent,
						  struct sock *child,
						  struct sk_buff *skb);
extern int			tcp_use_frto(struct sock *sk);
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);
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);
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
 */

extern void		       	tcp_v4_send_check(struct sock *sk, int len,
						  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,
							 struct request_sock *req,
							 struct sk_buff *skb);

extern struct sock *		tcp_v4_syn_recv_sock(struct sock *sk,
						     struct sk_buff *skb,
						     struct request_sock *req,
							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,
						struct request_sock *req);

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 */

extern void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
				      int nonagle);
extern int tcp_may_send_now(struct sock *sk);
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);
extern int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int);

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);
extern void tcp_send_active_reset(struct sock *sk, gfp_t priority);
extern int  tcp_send_synack(struct sock *);
extern void tcp_push_one(struct sock *, unsigned int mss_now);
extern void tcp_send_ack(struct sock *sk);
extern void tcp_send_delayed_ack(struct sock *sk);

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