tcp_input.c

来自「基于组件方式开发操作系统的OSKIT源代码」· C语言 代码 · 共 2,232 行 · 第 1/5 页

C
2,232
字号
/* * Copyright (c) 1982, 1986, 1988, 1990, 1993, 1994, 1995 *	The Regents of the University of California.  All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright *    notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright *    notice, this list of conditions and the following disclaimer in the *    documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software *    must display the following acknowledgement: *	This product includes software developed by the University of *	California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors *    may be used to endorse or promote products derived from this software *    without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * *	@(#)tcp_input.c	8.12 (Berkeley) 5/24/95 *	$Id: tcp_input.c,v 1.82.2.1 1999/04/20 19:09:15 obrien Exp $ */#include "opt_ipfw.h"		/* for ipfw_fwd		*/#include "opt_tcpdebug.h"#include <sys/param.h>#include <sys/systm.h>#include <sys/kernel.h>#include <sys/sysctl.h>#include <sys/malloc.h>#include <sys/mbuf.h>#include <sys/proc.h>		/* for proc0 declaration */#include <sys/protosw.h>#include <sys/socket.h>#include <sys/socketvar.h>#include <sys/syslog.h>#include <machine/cpu.h>	/* before tcp_seq.h, for tcp_random18() */#include <net/if.h>#include <net/route.h>#include <netinet/in.h>#include <netinet/in_systm.h>#include <netinet/ip.h>#include <netinet/ip_icmp.h>	/* for ICMP_BANDLIM		*/#include <netinet/in_pcb.h>#include <netinet/ip_var.h>#include <netinet/icmp_var.h>	/* for ICMP_BANDLIM		*/#include <netinet/tcp.h>#include <netinet/tcp_fsm.h>#include <netinet/tcp_seq.h>#include <netinet/tcp_timer.h>#include <netinet/tcp_var.h>#include <netinet/tcpip.h>#ifdef TCPDEBUG#include <netinet/tcp_debug.h>static struct	tcpiphdr tcp_saveti;#endifstatic int	tcprexmtthresh = 3;tcp_seq	tcp_iss;tcp_cc	tcp_ccgen;struct	tcpstat tcpstat;SYSCTL_STRUCT(_net_inet_tcp, TCPCTL_STATS, stats,	CTLFLAG_RD, &tcpstat , tcpstat, "");static int log_in_vain = 0;SYSCTL_INT(_net_inet_tcp, OID_AUTO, log_in_vain, CTLFLAG_RW, 	&log_in_vain, 0, "");int tcp_delack_enabled = 1;SYSCTL_INT(_net_inet_tcp, OID_AUTO, delayed_ack, CTLFLAG_RW, 	&tcp_delack_enabled, 0, "");u_long	tcp_now;struct inpcbhead tcb;struct inpcbinfo tcbinfo;static void	 tcp_dooptions __P((struct tcpcb *,	    u_char *, int, struct tcpiphdr *, struct tcpopt *));static void	 tcp_pulloutofband __P((struct socket *,	    struct tcpiphdr *, struct mbuf *));static int	 tcp_reass __P((struct tcpcb *, struct tcpiphdr *, struct mbuf *));static void	 tcp_xmit_timer __P((struct tcpcb *, int));/* * Insert segment ti into reassembly queue of tcp with * control block tp.  Return TH_FIN if reassembly now includes * a segment with FIN.  The macro form does the common case inline * (segment is the next to be received on an established connection, * and the queue is empty), avoiding linkage into and removal * from the queue and repetition of various conversions. * Set DELACK for segments received in order, but ack immediately * when segments are out of order (so fast retransmit can work). */#define	TCP_REASS(tp, ti, m, so, flags) { \	if ((ti)->ti_seq == (tp)->rcv_nxt && \	    (tp)->t_segq == NULL && \	    (tp)->t_state == TCPS_ESTABLISHED) { \		if (tcp_delack_enabled) \			tp->t_flags |= TF_DELACK; \		else \			tp->t_flags |= TF_ACKNOW; \		(tp)->rcv_nxt += (ti)->ti_len; \		flags = (ti)->ti_flags & TH_FIN; \		tcpstat.tcps_rcvpack++;\		tcpstat.tcps_rcvbyte += (ti)->ti_len;\		sbappend(&(so)->so_rcv, (m)); \		sorwakeup(so); \	} else { \		(flags) = tcp_reass((tp), (ti), (m)); \		tp->t_flags |= TF_ACKNOW; \	} \}static inttcp_reass(tp, ti, m)	register struct tcpcb *tp;	register struct tcpiphdr *ti;	struct mbuf *m;{	struct mbuf *q;	struct mbuf *p;	struct mbuf *nq;	struct socket *so = tp->t_inpcb->inp_socket;	int flags;#define GETTCP(m)	((struct tcpiphdr *)m->m_pkthdr.header)	/*	 * Call with ti==0 after become established to	 * force pre-ESTABLISHED data up to user socket.	 */	if (ti == 0)		goto present;	m->m_pkthdr.header = ti;	/*	 * Find a segment which begins after this one does.	 */	for (q = tp->t_segq, p = NULL; q; p = q, q = q->m_nextpkt)		if (SEQ_GT(GETTCP(q)->ti_seq, ti->ti_seq))			break;	/*	 * If there is a preceding segment, it may provide some of	 * our data already.  If so, drop the data from the incoming	 * segment.  If it provides all of our data, drop us.	 */	if (p != NULL) {		register int i;		/* conversion to int (in i) handles seq wraparound */		i = GETTCP(p)->ti_seq + GETTCP(p)->ti_len - ti->ti_seq;		if (i > 0) {			if (i >= ti->ti_len) {				tcpstat.tcps_rcvduppack++;				tcpstat.tcps_rcvdupbyte += ti->ti_len;				m_freem(m);				/*				 * Try to present any queued data				 * at the left window edge to the user.				 * This is needed after the 3-WHS				 * completes.				 */				goto present;	/* ??? */			}			m_adj(m, i);			ti->ti_len -= i;			ti->ti_seq += i;		}	}	tcpstat.tcps_rcvoopack++;	tcpstat.tcps_rcvoobyte += ti->ti_len;	/*	 * While we overlap succeeding segments trim them or,	 * if they are completely covered, dequeue them.	 */	while (q) {		register int i = (ti->ti_seq + ti->ti_len) - GETTCP(q)->ti_seq;		if (i <= 0)			break;		if (i < GETTCP(q)->ti_len) {			GETTCP(q)->ti_seq += i;			GETTCP(q)->ti_len -= i;			m_adj(q, i);			break;		}		nq = q->m_nextpkt;		if (p)			p->m_nextpkt = nq;		else			tp->t_segq = nq;		m_freem(q);		q = nq;	}	if (p == NULL) {		m->m_nextpkt = tp->t_segq;		tp->t_segq = m;	} else {		m->m_nextpkt = p->m_nextpkt;		p->m_nextpkt = m;	}present:	/*	 * Present data to user, advancing rcv_nxt through	 * completed sequence space.	 */	if (!TCPS_HAVEESTABLISHED(tp->t_state))		return (0);	q = tp->t_segq;	if (!q || GETTCP(q)->ti_seq != tp->rcv_nxt)		return (0);	do {		tp->rcv_nxt += GETTCP(q)->ti_len;		flags = GETTCP(q)->ti_flags & TH_FIN;		nq = q->m_nextpkt;		tp->t_segq = nq;		q->m_nextpkt = NULL;		if (so->so_state & SS_CANTRCVMORE)			m_freem(q);		else			sbappend(&so->so_rcv, q);		q = nq;	} while (q && GETTCP(q)->ti_seq == tp->rcv_nxt);	sorwakeup(so);	return (flags);#undef GETTCP}/* * TCP input routine, follows pages 65-76 of the * protocol specification dated September, 1981 very closely. */voidtcp_input(m, iphlen)	register struct mbuf *m;	int iphlen;{	register struct tcpiphdr *ti;	register struct inpcb *inp;	u_char *optp = NULL;	int optlen = 0;	int len, tlen, off;	register struct tcpcb *tp = 0;	register int tiflags;	struct socket *so = 0;	int todrop, acked, ourfinisacked, needoutput = 0;	struct in_addr laddr;	int dropsocket = 0;	int iss = 0;	u_long tiwin;	struct tcpopt to;		/* options in this segment */	struct rmxp_tao *taop;		/* pointer to our TAO cache entry */	struct rmxp_tao	tao_noncached;	/* in case there's no cached entry */#ifdef TCPDEBUG	short ostate = 0;#endif	bzero((char *)&to, sizeof(to));	tcpstat.tcps_rcvtotal++;	/*	 * Get IP and TCP header together in first mbuf.	 * Note: IP leaves IP header in first mbuf.	 */	ti = mtod(m, struct tcpiphdr *);	if (iphlen > sizeof (struct ip))		ip_stripoptions(m, (struct mbuf *)0);	if (m->m_len < sizeof (struct tcpiphdr)) {		if ((m = m_pullup(m, sizeof (struct tcpiphdr))) == 0) {			tcpstat.tcps_rcvshort++;			return;		}		ti = mtod(m, struct tcpiphdr *);	}	/*	 * Checksum extended TCP header and data.	 */	tlen = ((struct ip *)ti)->ip_len;	len = sizeof (struct ip) + tlen;	bzero(ti->ti_x1, sizeof(ti->ti_x1));	ti->ti_len = (u_short)tlen;	HTONS(ti->ti_len);	ti->ti_sum = in_cksum(m, len);	if (ti->ti_sum) {		tcpstat.tcps_rcvbadsum++;		goto drop;	}	/*	 * Check that TCP offset makes sense,	 * pull out TCP options and adjust length.		XXX	 */	off = ti->ti_off << 2;	if (off < sizeof (struct tcphdr) || off > tlen) {		tcpstat.tcps_rcvbadoff++;		goto drop;	}	tlen -= off;	ti->ti_len = tlen;	if (off > sizeof (struct tcphdr)) {		if (m->m_len < sizeof(struct ip) + off) {			if ((m = m_pullup(m, sizeof (struct ip) + off)) == 0) {				tcpstat.tcps_rcvshort++;				return;			}			ti = mtod(m, struct tcpiphdr *);		}		optlen = off - sizeof (struct tcphdr);		optp = mtod(m, u_char *) + sizeof (struct tcpiphdr);	}	tiflags = ti->ti_flags;	/*	 * Convert TCP protocol specific fields to host format.	 */	NTOHL(ti->ti_seq);	NTOHL(ti->ti_ack);	NTOHS(ti->ti_win);	NTOHS(ti->ti_urp);	/*	 * Drop TCP, IP headers and TCP options.	 */	m->m_data += sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr);	m->m_len  -= sizeof(struct tcpiphdr)+off-sizeof(struct tcphdr);	/*	 * Locate pcb for segment.	 */findpcb:#ifdef IPFIREWALL_FORWARD	if (ip_fw_fwd_addr != NULL) {		/*		 * Diverted. Pretend to be the destination.		 * already got one like this? 		 */		inp = in_pcblookup_hash(&tcbinfo, ti->ti_src, ti->ti_sport,			ti->ti_dst, ti->ti_dport, 0);		if (!inp) {			/* 			 * No, then it's new. Try find the ambushing socket			 */			if (!ip_fw_fwd_addr->sin_port) {				inp = in_pcblookup_hash(&tcbinfo, ti->ti_src,				    ti->ti_sport, ip_fw_fwd_addr->sin_addr,				    ti->ti_dport, 1);			} else {				inp = in_pcblookup_hash(&tcbinfo,				    ti->ti_src, ti->ti_sport,	    			    ip_fw_fwd_addr->sin_addr,				    ntohs(ip_fw_fwd_addr->sin_port), 1);			}		}		ip_fw_fwd_addr = NULL;	} else#endif	/* IPFIREWALL_FORWARD */	inp = in_pcblookup_hash(&tcbinfo, ti->ti_src, ti->ti_sport,	    ti->ti_dst, ti->ti_dport, 1);	/*	 * If the state is CLOSED (i.e., TCB does not exist) then	 * all data in the incoming segment is discarded.	 * If the TCB exists but is in CLOSED state, it is embryonic,	 * but should either do a listen or a connect soon.	 */	if (inp == NULL) {		if (log_in_vain && tiflags & TH_SYN) {			char buf[4*sizeof "123"];			strcpy(buf, inet_ntoa(ti->ti_dst));			log(LOG_INFO,			    "Connection attempt to TCP %s:%d from %s:%d\n",			    buf, ntohs(ti->ti_dport), inet_ntoa(ti->ti_src),			    ntohs(ti->ti_sport));		}#ifdef ICMP_BANDLIM		if (badport_bandlim(1) < 0)			goto drop;#endif		goto dropwithreset;	}	tp = intotcpcb(inp);	if (tp == 0)		goto dropwithreset;	if (tp->t_state == TCPS_CLOSED)		goto drop;	/* Unscale the window into a 32-bit value. */	if ((tiflags & TH_SYN) == 0)		tiwin = ti->ti_win << tp->snd_scale;	else		tiwin = ti->ti_win;	so = inp->inp_socket;	if (so->so_options & (SO_DEBUG|SO_ACCEPTCONN)) {#ifdef TCPDEBUG		if (so->so_options & SO_DEBUG) {			ostate = tp->t_state;			tcp_saveti = *ti;		}#endif		if (so->so_options & SO_ACCEPTCONN) {			register struct tcpcb *tp0 = tp;			struct socket *so2;			if ((tiflags & (TH_RST|TH_ACK|TH_SYN)) != TH_SYN) {				/*				 * Note: dropwithreset makes sure we don't				 * send a RST in response to a RST.				 */				if (tiflags & TH_ACK) {					tcpstat.tcps_badsyn++;					goto dropwithreset;				}				goto drop;			}			so2 = sonewconn(so, 0);			if (so2 == 0) {				tcpstat.tcps_listendrop++;				so2 = sodropablereq(so);				if (so2) {					tcp_drop(sototcpcb(so2), ETIMEDOUT);

⌨️ 快捷键说明

复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?