ip6_input.c

来自「eCos操作系统源码」· C语言 代码 · 共 2,515 行 · 第 1/5 页

//==========================================================================
//
//      src/sys/netinet6/ip6_input.c
//
//==========================================================================
//####BSDCOPYRIGHTBEGIN####
//
// -------------------------------------------
//
// Portions of this software may have been derived from OpenBSD, 
// FreeBSD or other sources, and are covered by the appropriate
// copyright disclaimers included herein.
//
// Portions created by Red Hat are
// Copyright (C) 2002 Red Hat, Inc. All Rights Reserved.
//
// -------------------------------------------
//
//####BSDCOPYRIGHTEND####
//==========================================================================

/*	$KAME: ip6_input.c,v 1.242 2001/12/27 17:40:10 jinmei Exp $	*/

/*
 * Copyright (C) 1995, 1996, 1997, and 1998 WIDE Project.
 * 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. Neither the name of the project 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 PROJECT 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 PROJECT 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.
 */

/*
 * Copyright (c) 1982, 1986, 1988, 1993
 *	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.
 *
 *	@(#)ip_input.c	8.2 (Berkeley) 1/4/94
 */

#include <sys/param.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/domain.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/errno.h>

#include <net/if.h>
#include <net/if_types.h>
#include <net/if_dl.h>
#include <net/route.h>
#include <net/netisr.h>
#if defined(__FreeBSD__) && __FreeBSD__ >= 4
#include <net/intrq.h>
#endif

#include <netinet/in.h>
#include <netinet/in_systm.h>
#ifdef INET
#include <netinet/ip.h>
#include <netinet/ip_icmp.h>
#endif /* INET */
#include <netinet/ip6.h>
#include <netinet6/in6_var.h>
#include <netinet6/ip6_var.h>
#if (defined(__FreeBSD__) && __FreeBSD__ >= 3) || defined(__OpenBSD__) || (defined(__bsdi__) && _BSDI_VERSION >= 199802)
#include <netinet/in_pcb.h>
#endif
#if !((defined(__FreeBSD__) && __FreeBSD__ >= 3) || defined(__OpenBSD__) || (defined(__bsdi__) && _BSDI_VERSION >= 199802))
#include <netinet6/in6_pcb.h>
#endif
#include <netinet/icmp6.h>
#include <netinet6/in6_ifattach.h>
#include <netinet6/nd6.h>
#ifdef __bsdi__
#include <netinet6/raw_ip6.h>
#endif
#ifdef MIP6
#include <netinet6/mip6.h>
#endif

#if defined(IPSEC) && !defined(__OpenBSD__)
#include <netinet6/ipsec.h>
#endif

#if defined(IPV6FIREWALL) || (defined(__FreeBSD__) && __FreeBSD__ >= 4)
#include <netinet6/ip6_fw.h>
#endif

#include <netinet6/ip6protosw.h>

/* we need it for NLOOP. */

#if NGIF > 0
#include <netinet6/in6_gif.h>
#endif

#ifdef MIP6
#include <netinet6/mip6.h>
#endif /* MIP6 */

#ifdef __OpenBSD__
#if NPF > 0
#include <net/pfvar.h>
#endif
#endif

extern struct domain inet6domain;
extern struct ip6protosw inet6sw[];
#ifdef __bsdi__
#if _BSDI_VERSION < 199802
extern struct ifnet loif;
#else
extern struct ifnet *loifp;
#endif
#endif

u_char ip6_protox[IPPROTO_MAX];
static int ip6qmaxlen = IFQ_MAXLEN;
struct in6_ifaddr *in6_ifaddr;
#if !(defined(__FreeBSD__) && __FreeBSD__ >= 4)
struct ifqueue ip6intrq;
#endif

#if defined(__NetBSD__)
extern struct ifnet loif[NLOOP];
#endif
#if defined(__NetBSD__) || (defined(__FreeBSD__) && __FreeBSD__ >= 3)
extern struct callout in6_tmpaddrtimer_ch;
#elif defined(__OpenBSD__)
extern struct timeout in6_tmpaddrtimer_ch;
#endif

int ip6_forward_srcrt;			/* XXX */
int ip6_sourcecheck;			/* XXX */
int ip6_sourcecheck_interval;		/* XXX */
#if defined(__FreeBSD__) && __FreeBSD__ >= 4
const int int6intrq_present = 1;
#endif

#ifdef MEASURE_PERFORMANCE
#define MEASURE_PERFORMANCE_UDPONLY
#define IP6_PERFORM_LOGSIZE 10000
int ip6_logentry;
int ip6_logsize = IP6_PERFORM_LOGSIZE;
unsigned long long ip6_performance_log[IP6_PERFORM_LOGSIZE];
unsigned long long ip6_performance_log2[IP6_PERFORM_LOGSIZE];
struct in6_addr ip6_performance_addrlog[IP6_PERFORM_LOGSIZE];
#endif
#ifdef MEASURE_PERFORMANCE
#define OURS_CHECK_ALG_RTABLE 0
#define OURS_CHECK_ALG_LINEAR 1
#define OURS_CHECK_ALG_HASH 2
#define OURS_CHECK_ALG_LARGEHASH 3
#ifdef OURS_CHECK_LINEAR
int ip6_ours_check_algorithm = OURS_CHECK_ALG_LINEAR;
#elif OURS_CHECK_HASH
int ip6_ours_check_algorithm = OURS_CHECK_ALG_HASH;
#else
int ip6_ours_check_algorithm = OURS_CHECK_ALG_RTABLE;
#endif
#else
int ip6_ours_check_algorithm;
#endif


#if defined(IPV6FIREWALL) || (defined(__FreeBSD__) && __FreeBSD__ >= 4)
/* firewall hooks */
ip6_fw_chk_t *ip6_fw_chk_ptr;
ip6_fw_ctl_t *ip6_fw_ctl_ptr;
#endif
#if defined(__FreeBSD__) && __FreeBSD__ >= 4
int ip6_fw_enable = 1;
#endif

struct ip6stat ip6stat;

static void ip6_init2 __P((void *));
static struct mbuf *ip6_setdstifaddr __P((struct mbuf *, struct in6_ifaddr *));

static int ip6_hopopts_input __P((u_int32_t *, u_int32_t *, struct mbuf **, int *));
#ifdef PULLDOWN_TEST
static struct mbuf *ip6_pullexthdr __P((struct mbuf *, size_t, int));
#endif

#ifdef NATPT
extern int ip6_protocol_tr;

int natpt_in6 __P((struct mbuf *, struct mbuf **));
extern void ip_forward __P((struct mbuf *, int));
#endif


#ifdef MEASURE_PERFORMANCE
static unsigned long long ctr_beg, ctr_end;

static __inline unsigned long long read_tsc __P((void));
static __inline void add_performance_log __P((unsigned long long,
					      struct in6_addr *)); 
#endif

#ifdef MEASURE_PERFORMANCE
static __inline unsigned long long 
read_tsc(void)
{
     unsigned int h,l;
     /* read Pentium counter */
     __asm__(".byte 0x0f,0x31" :"=a" (l), "=d" (h));
     return ((unsigned long long)h<<32) | l;
}

static __inline void
add_performance_log(val, addr)
	unsigned long long val;
	struct in6_addr *addr;
{
	ip6_logentry = (ip6_logentry + 1) % ip6_logsize;
	ip6_performance_log[ip6_logentry] = val;
	ip6_performance_addrlog[ip6_logentry] = *addr;
}
#endif

/*
 * IP6 initialization: fill in IP6 protocol switch table.
 * All protocols not implemented in kernel go to raw IP6 protocol handler.
 */
void
ip6_init()
{
	struct ip6protosw *pr;
	int i;
#ifndef __OpenBSD__
	struct timeval tv;
#endif

#ifdef RADIX_ART
	rt_tables[AF_INET6]->rnh_addrsize = sizeof(struct in6_addr);
#endif

#ifdef DIAGNOSTIC
	if (sizeof(struct protosw) != sizeof(struct ip6protosw))
		panic("sizeof(protosw) != sizeof(ip6protosw)");
#endif
	pr = (struct ip6protosw *)pffindproto(PF_INET6, IPPROTO_RAW, SOCK_RAW);
	if (pr == 0)
		panic("ip6_init");
	for (i = 0; i < IPPROTO_MAX; i++)
		ip6_protox[i] = pr - inet6sw;
	for (pr = (struct ip6protosw *)inet6domain.dom_protosw;
	    pr < (struct ip6protosw *)inet6domain.dom_protoswNPROTOSW; pr++)
		if (pr->pr_domain->dom_family == PF_INET6 &&
		    pr->pr_protocol && pr->pr_protocol != IPPROTO_RAW)
			ip6_protox[pr->pr_protocol] = pr - inet6sw;
	ip6intrq.ifq_maxlen = ip6qmaxlen;
#if (defined(__FreeBSD__) && __FreeBSD__ >= 4)
	register_netisr(NETISR_IPV6, ip6intr);
#endif
	addrsel_policy_init();
	nd6_init();
	frag6_init();
#if defined(__FreeBSD__) && __FreeBSD__ >= 4
#else
#ifdef IPV6FIREWALL
	ip6_fw_init();
#endif
#endif
#ifndef __OpenBSD__
	/*
	 * in many cases, random() here does NOT return random number
	 * as initialization during bootstrap time occur in fixed order.
	 */
	microtime(&tv);
	ip6_flow_seq = random() ^ tv.tv_usec;
	microtime(&tv);
	ip6_desync_factor = (random() ^ tv.tv_usec) % MAX_TEMP_DESYNC_FACTOR;
#else
	ip6_flow_seq = arc4random();
	ip6_desync_factor = arc4random() % MAX_TEMP_DESYNC_FACTOR;
#endif

#ifndef __FreeBSD__
	ip6_init2((void *)0);
#endif

#ifdef MIP6
	mip6_init();
#endif /* MIP6 */

#ifdef MEASURE_PERFORMANCE
	in6h_hashinit();
#endif
}

static void
ip6_init2(dummy)
	void *dummy;
{
#if defined(__bsdi__) && _BSDI_VERSION < 199802
	struct ifnet *loifp = &loif;
#endif

	/*
	 * to route local address of p2p link to loopback,
	 * assign loopback address first.
	 */
#ifdef __bsdi__
	in6_ifattach(loifp, NULL);
#elif defined(__OpenBSD__)
	in6_ifattach(lo0ifp, NULL);
#else
	in6_ifattach(&loif[0], NULL);
#endif

	/* nd6_timer_init */
#if defined(__NetBSD__) || (defined(__FreeBSD__) && __FreeBSD__ >= 3)
	callout_init(&nd6_timer_ch);
	callout_reset(&nd6_timer_ch, hz, nd6_timer, NULL);
#elif defined(__OpenBSD__)
	bzero(&nd6_timer_ch, sizeof(nd6_timer_ch));
	timeout_set(&nd6_timer_ch, nd6_timer, NULL);
	timeout_add(&nd6_timer_ch, hz);
#else
	timeout(nd6_timer, (caddr_t)0, hz);
#endif

	/* timer for regeneranation of temporary addresses randomize ID */
#if defined(__NetBSD__) || (defined(__FreeBSD__) && __FreeBSD__ >= 3)
	callout_init(&in6_tmpaddrtimer_ch);
	callout_reset(&in6_tmpaddrtimer_ch,
		      (ip6_temp_preferred_lifetime - ip6_desync_factor -
		       ip6_temp_regen_advance) * hz,
		      in6_tmpaddrtimer, NULL);
#elif defined(__OpenBSD__)
	timeout_set(&in6_tmpaddrtimer_ch, in6_tmpaddrtimer, NULL);
	timeout_add(&in6_tmpaddrtimer_ch,
	    (ip6_temp_preferred_lifetime - ip6_desync_factor -
	    ip6_temp_regen_advance) * hz);
#else
	timeout(in6_tmpaddrtimer, (caddr_t)0,
		(ip6_temp_preferred_lifetime - ip6_desync_factor -
			ip6_temp_regen_advance) * hz);
#endif
}

SYSINIT(netinet6init2, SI_SUB_PROTO_DOMAIN, SI_ORDER_MIDDLE, ip6_init2, NULL);

/*
 * IP6 input interrupt handling. Just pass the packet to ip6_input.
 */
void
ip6intr()
{
	int s;
	struct mbuf *m;

	for (;;) {
		s = splimp();
		IF_DEQUEUE(&ip6intrq, m);
		splx(s);
		if (m == 0)
			return;
		ip6_input(m);
	}
}

#if (defined(__FreeBSD__) && __FreeBSD__ <= 3)
NETISR_SET(NETISR_IPV6, ip6intr);
#endif

#ifdef NEW_STRUCT_ROUTE
extern struct	route ip6_forward_rt;
#else
extern struct	route_in6 ip6_forward_rt;

/* NetBSD/OpenBSD requires NEW_STRUCT_ROUTE */
#if defined(__NetBSD__) || defined(__OpenBSD__) || defined(__FreeBSD__)
#error NEW_STRUCT_ROUTE is required
#endif
#endif

void
ip6_input(m)
	struct mbuf *m;
{
	struct ip6_hdr *ip6;
	int off = sizeof(struct ip6_hdr), nest;
	u_int32_t plen;
	u_int32_t rtalert = ~0;
	int nxt, ours = 0;
	struct ifnet *deliverifp = NULL;
#if 0
	struct mbuf *mhist;	/* onion peeling history */
	caddr_t hist;
#endif
#if defined(__bsdi__) && _BSDI_VERSION < 199802
	struct ifnet *loifp = &loif;
#endif
#if defined(__NetBSD__) && defined(PFIL_HOOKS)
	struct packet_filter_hook *pfh;
	struct mbuf *m0;
	int rv;
#endif	/* PFIL_HOOKS */

#if defined(IPSEC) && !defined(__OpenBSD__)
	/*
	 * should the inner packet be considered authentic?
	 * see comment in ah4_input().
	 */
	m->m_flags &= ~M_AUTHIPHDR;
	m->m_flags &= ~M_AUTHIPDGM;
#endif

	/*
	 * make sure we don't have onion peering information into m_aux.
	 */
	ip6_delaux(m);

	/*
	 * mbuf statistics
	 */
	if (m->m_flags & M_EXT) {
		if (m->m_next)
			ip6stat.ip6s_mext2m++;
		else
			ip6stat.ip6s_mext1++;
	} else {
#define M2MMAX	(sizeof(ip6stat.ip6s_m2m)/sizeof(ip6stat.ip6s_m2m[0]))
		if (m->m_next) {
			if (m->m_flags & M_LOOP) {
#ifdef __bsdi__
				ip6stat.ip6s_m2m[loifp->if_index]++; /* XXX */
#elif defined(__OpenBSD__)
				ip6stat.ip6s_m2m[lo0ifp->if_index]++; /* XXX */
#else
				ip6stat.ip6s_m2m[loif[0].if_index]++; /* XXX */
#endif
			} else if (m->m_pkthdr.rcvif->if_index < M2MMAX)
				ip6stat.ip6s_m2m[m->m_pkthdr.rcvif->if_index]++;
			else
				ip6stat.ip6s_m2m[0]++;
		} else
			ip6stat.ip6s_m1++;
#undef M2MMAX
	}

	in6_ifstat_inc(m->m_pkthdr.rcvif, ifs6_in_receive);
	ip6stat.ip6s_total++;

#ifndef PULLDOWN_TEST
	/* 
	 * L2 bridge code and some other code can return mbuf chain
	 * that does not conform to KAME requirement.  too bad.
	 * XXX: fails to join if interface MTU > MCLBYTES.  jumbogram?
	 */