NetBSD/sys/netinet6/in6_proto.c

585 lines
17 KiB
C
Raw Normal View History

/* $NetBSD: in6_proto.c,v 1.117 2017/04/14 02:43:28 ozaki-r Exp $ */
2000-10-10 20:26:43 +04:00
/* $KAME: in6_proto.c,v 1.66 2000/10/10 15:35:47 itojun Exp $ */
1999-07-04 01:24:45 +04:00
/*
* 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, 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. 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.
*
* @(#)in_proto.c 8.1 (Berkeley) 6/10/93
*/
2001-11-13 03:56:55 +03:00
#include <sys/cdefs.h>
__KERNEL_RCSID(0, "$NetBSD: in6_proto.c,v 1.117 2017/04/14 02:43:28 ozaki-r Exp $");
2001-11-13 03:56:55 +03:00
2015-08-25 01:21:26 +03:00
#ifdef _KERNEL_OPT
#include "opt_gateway.h"
#include "opt_inet.h"
#include "opt_ipsec.h"
2015-02-10 22:11:52 +03:00
#include "opt_dccp.h"
2015-10-14 00:28:34 +03:00
#include "opt_sctp.h"
2015-08-25 01:21:26 +03:00
#endif
#include <sys/param.h>
#include <sys/socket.h>
#include <sys/protosw.h>
#include <sys/kernel.h>
#include <sys/domain.h>
#include <sys/mbuf.h>
#include <net/if.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip_encap.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/in_pcb.h>
#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>
#include <netinet/icmp6.h>
#include <netinet6/in6_pcb.h>
#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>
#include <netinet/tcp_debug.h>
#include <netinet6/udp6.h>
#include <netinet6/udp6_var.h>
2015-02-10 22:11:52 +03:00
#ifdef DCCP
#include <netinet/dccp.h>
#include <netinet/dccp_var.h>
#include <netinet6/dccp6_var.h>
#endif
2015-10-14 00:28:34 +03:00
#ifdef SCTP
#include <netinet/sctp_pcb.h>
#include <netinet/sctp.h>
#include <netinet/sctp_var.h>
#include <netinet6/sctp6_var.h>
#endif
#include <netinet6/pim6_var.h>
#ifdef IPSEC
#include <netipsec/ipsec.h>
#include <netipsec/ipsec6.h>
#include <netipsec/key.h>
#endif /* IPSEC */
#include "carp.h"
#if NCARP > 0
#include <netinet/ip_carp.h>
#endif
#include "etherip.h"
#if NETHERIP > 0
#include <netinet6/ip6_etherip.h>
#endif
#include <netinet6/ip6protosw.h>
#include <net/net_osdep.h>
/*
* TCP/IP protocol family: IP6, ICMP6, UDP, TCP.
*/
DOMAIN_DEFINE(inet6domain); /* forward declare and add to link set */
/* Wrappers to acquire kernel_lock. */
PR_WRAP_CTLINPUT(rip6_ctlinput)
PR_WRAP_CTLINPUT(encap6_ctlinput)
PR_WRAP_CTLINPUT(udp6_ctlinput)
PR_WRAP_CTLINPUT(tcp6_ctlinput)
#define rip6_ctlinput rip6_ctlinput_wrapper
#define encap6_ctlinput encap6_ctlinput_wrapper
#define udp6_ctlinput udp6_ctlinput_wrapper
#define tcp6_ctlinput tcp6_ctlinput_wrapper
PR_WRAP_CTLOUTPUT(rip6_ctloutput)
PR_WRAP_CTLOUTPUT(tcp_ctloutput)
PR_WRAP_CTLOUTPUT(udp6_ctloutput)
PR_WRAP_CTLOUTPUT(icmp6_ctloutput)
#define rip6_ctloutput rip6_ctloutput_wrapper
#define tcp_ctloutput tcp_ctloutput_wrapper
#define udp6_ctloutput udp6_ctloutput_wrapper
#define icmp6_ctloutput icmp6_ctloutput_wrapper
2015-02-10 22:11:52 +03:00
#if defined(DCCP)
PR_WRAP_CTLINPUT(dccp6_ctlinput)
PR_WRAP_CTLOUTPUT(dccp_ctloutput)
#define dccp6_ctlinput dccp6_ctlinput_wrapper
#define dccp_ctloutput dccp_ctloutput_wrapper
#endif
2015-10-14 00:28:34 +03:00
#if defined(SCTP)
PR_WRAP_CTLINPUT(sctp6_ctlinput)
PR_WRAP_CTLOUTPUT(sctp_ctloutput)
#define sctp6_ctlinput sctp6_ctlinput_wrapper
#define sctp_ctloutput sctp_ctloutput_wrapper
#endif
#if defined(IPSEC)
#ifdef IPSEC_RUMPKERNEL
/*
* .pr_input = ipsec6_common_input won't be resolved on loading
* the ipsec shared library. We need a wrapper anyway.
*/
static int
ipsec6_common_input_wrapper(struct mbuf **mp, int *offp, int proto)
{
if (ipsec_enabled) {
return ipsec6_common_input(mp, offp, proto);
} else {
m_freem(*mp);
return IPPROTO_DONE;
}
}
#define ipsec6_common_input ipsec6_common_input_wrapper
/* The ctlinput functions may not be loaded */
#define IPSEC_WRAP_CTLINPUT(name) \
static void * \
name##_wrapper(int a, const struct sockaddr *b, void *c)\
{ \
void *rv; \
KERNEL_LOCK(1, NULL); \
if (ipsec_enabled) \
rv = name(a, b, c); \
else \
rv = NULL; \
KERNEL_UNLOCK_ONE(NULL); \
return rv; \
}
IPSEC_WRAP_CTLINPUT(ah6_ctlinput)
IPSEC_WRAP_CTLINPUT(esp6_ctlinput)
#else /* !IPSEC_RUMPKERNEL */
PR_WRAP_CTLINPUT(ah6_ctlinput)
PR_WRAP_CTLINPUT(esp6_ctlinput)
#endif /* !IPSEC_RUMPKERNEL */
#define ah6_ctlinput ah6_ctlinput_wrapper
#define esp6_ctlinput esp6_ctlinput_wrapper
#endif /* IPSEC */
static void
tcp6_init(void)
{
icmp6_mtudisc_callback_register(tcp6_mtudisc_callback);
tcp_init_common(sizeof(struct ip6_hdr));
}
const struct ip6protosw inet6sw[] = {
{ .pr_domain = &inet6domain,
.pr_protocol = IPPROTO_IPV6,
.pr_init = ip6_init,
.pr_fasttimo = frag6_fasttimo,
.pr_slowtimo = frag6_slowtimo,
.pr_drain = frag6_drainstub,
},
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_ICMPV6,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = icmp6_input,
.pr_ctlinput = rip6_ctlinput,
.pr_ctloutput = icmp6_ctloutput,
.pr_usrreqs = &rip6_usrreqs,
.pr_init = icmp6_init,
},
{ .pr_type = SOCK_DGRAM,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_UDP,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_PURGEIF,
.pr_input = udp6_input,
.pr_ctlinput = udp6_ctlinput,
.pr_ctloutput = udp6_ctloutput,
.pr_usrreqs = &udp6_usrreqs,
.pr_init = udp6_init,
},
{ .pr_type = SOCK_STREAM,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_TCP,
.pr_flags = PR_CONNREQUIRED|PR_WANTRCVD|PR_LISTEN|PR_ABRTACPTDIS|PR_PURGEIF,
.pr_input = tcp6_input,
.pr_ctlinput = tcp6_ctlinput,
.pr_ctloutput = tcp_ctloutput,
.pr_usrreqs = &tcp_usrreqs,
.pr_init = tcp6_init,
.pr_fasttimo = tcp_fasttimo,
.pr_drain = tcp_drainstub,
},
2015-02-10 22:11:52 +03:00
#ifdef DCCP
{ .pr_type = SOCK_CONN_DGRAM,
2015-02-10 22:11:52 +03:00
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_DCCP,
.pr_flags = PR_CONNREQUIRED|PR_ATOMIC|PR_LISTEN,
.pr_input = dccp6_input,
2015-02-10 22:11:52 +03:00
.pr_ctlinput = dccp6_ctlinput,
.pr_ctloutput = dccp_ctloutput,
.pr_usrreqs = &dccp6_usrreqs,
#ifndef INET
.pr_init = dccp_init,
#endif
},
#endif /* DCCP */
2015-10-14 00:28:34 +03:00
#ifdef SCTP
{ .pr_type = SOCK_DGRAM,
2015-10-14 00:28:34 +03:00
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_SCTP,
.pr_flags = PR_ADDR_OPT|PR_WANTRCVD,
.pr_input = sctp6_input,
2015-10-14 00:28:34 +03:00
.pr_ctlinput = sctp6_ctlinput,
.pr_ctloutput = sctp_ctloutput,
.pr_usrreqs = &sctp6_usrreqs,
.pr_drain = sctp_drain,
},
{ .pr_type = SOCK_SEQPACKET,
2015-10-14 00:28:34 +03:00
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_SCTP,
.pr_flags = PR_ADDR_OPT|PR_WANTRCVD,
.pr_input = sctp6_input,
2015-10-14 00:28:34 +03:00
.pr_ctlinput = sctp6_ctlinput,
.pr_ctloutput = sctp_ctloutput,
.pr_drain = sctp_drain,
},
{ .pr_type = SOCK_STREAM,
2015-10-14 00:28:34 +03:00
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_SCTP,
.pr_flags = PR_CONNREQUIRED|PR_ADDR_OPT|PR_WANTRCVD|PR_LISTEN,
.pr_input = sctp6_input,
2015-10-14 00:28:34 +03:00
.pr_ctlinput = sctp6_ctlinput,
.pr_ctloutput = sctp_ctloutput,
.pr_drain = sctp_drain,
},
#endif /* SCTP */
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_RAW,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_PURGEIF,
.pr_input = rip6_input,
.pr_ctlinput = rip6_ctlinput,
.pr_ctloutput = rip6_ctloutput,
.pr_usrreqs = &rip6_usrreqs,
},
#ifdef GATEWAY
{ .pr_domain = &inet6domain,
.pr_protocol = IPPROTO_IPV6,
.pr_slowtimo = ip6flow_slowtimo,
.pr_init = ip6flow_poolinit,
},
#endif /* GATEWAY */
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_DSTOPTS,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = dest6_input,
},
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_ROUTING,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = route6_input,
},
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_FRAGMENT,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = frag6_input,
},
#ifdef IPSEC
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_AH,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = ipsec6_common_input,
.pr_ctlinput = ah6_ctlinput,
},
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_ESP,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = ipsec6_common_input,
.pr_ctlinput = esp6_ctlinput,
},
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_IPCOMP,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = ipsec6_common_input,
},
#endif /* IPSEC */
#ifdef INET
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_IPV4,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = encap6_input,
.pr_ctlinput = encap6_ctlinput,
.pr_ctloutput = rip6_ctloutput,
.pr_usrreqs = &rip6_usrreqs,
.pr_init = encap_init,
},
#endif
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_IPV6,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = encap6_input,
.pr_ctlinput = encap6_ctlinput,
.pr_ctloutput = rip6_ctloutput,
.pr_usrreqs = &rip6_usrreqs,
.pr_init = encap_init,
},
#if NETHERIP > 0
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_ETHERIP,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = ip6_etherip_input,
.pr_ctlinput = rip6_ctlinput,
.pr_ctloutput = rip6_ctloutput,
.pr_usrreqs = &rip6_usrreqs,
},
#endif
#if NCARP > 0
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_CARP,
.pr_flags = PR_ATOMIC|PR_ADDR,
.pr_input = carp6_proto_input,
.pr_ctloutput = rip6_ctloutput,
.pr_usrreqs = &rip6_usrreqs,
},
#endif /* NCARP */
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_L2TP,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = encap6_input,
.pr_ctlinput = rip6_ctlinput,
.pr_ctloutput = rip6_ctloutput,
.pr_usrreqs = &rip6_usrreqs,
.pr_init = encap_init,
},
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_protocol = IPPROTO_PIM,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = pim6_input,
.pr_ctloutput = rip6_ctloutput,
.pr_usrreqs = &rip6_usrreqs,
2008-04-15 09:40:15 +04:00
.pr_init = pim6_init,
},
/* raw wildcard */
{ .pr_type = SOCK_RAW,
.pr_domain = &inet6domain,
.pr_flags = PR_ATOMIC|PR_ADDR|PR_LASTHDR,
.pr_input = rip6_input,
.pr_ctloutput = rip6_ctloutput,
.pr_usrreqs = &rip6_usrreqs,
.pr_init = rip6_init,
},
};
1) Introduce a new socket option, (SOL_SOCKET, SO_NOHEADER), that tells a socket that it should both add a protocol header to tx'd datagrams and remove the header from rx'd datagrams: int onoff = 1, s = socket(...); setsockopt(s, SOL_SOCKET, SO_NOHEADER, &onoff); 2) Add an implementation of (SOL_SOCKET, SO_NOHEADER) for raw IPv4 sockets. 3) Reorganize the protocols' pr_ctloutput implementations a bit. Consistently return ENOPROTOOPT when an option is unsupported, and EINVAL if a supported option's arguments are incorrect. Reorganize the flow of code so that it's more clear how/when options are passed down the stack until they are handled. Shorten some pr_ctloutput staircases for readability. 4) Extract common mbuf code into subroutines, add new sockaddr methods, and introduce a new subroutine, fsocreate(), for reuse later; use it first in sys_socket(): struct mbuf *m_getsombuf(struct socket *so) Create an mbuf and make its owner the socket `so'. struct mbuf *m_intopt(struct socket *so, int val) Create an mbuf, make its owner the socket `so', put the int `val' into it, and set its length to sizeof(int). int fsocreate(..., int *fd) Create a socket, a la socreate(9), put the socket into the given LWP's descriptor table, return the descriptor at `fd' on success. void *sockaddr_addr(struct sockaddr *sa, socklen_t *slenp) const void *sockaddr_const_addr(const struct sockaddr *sa, socklen_t *slenp) Extract a pointer to the address part of a sockaddr. Write the length of the address part at `slenp', if `slenp' is not NULL. socklen_t sockaddr_getlen(const struct sockaddr *sa) Return the length of a sockaddr. This just evaluates to sa->sa_len. I only add this for consistency with code that appears in a portable userland library that I am going to import. const struct sockaddr *sockaddr_any(const struct sockaddr *sa) Return the "don't care" sockaddr in the same family as `sa'. This is the address a client should sobind(9) if it does not care the source address and, if applicable, the port et cetera that it uses. const void *sockaddr_anyaddr(const struct sockaddr *sa, socklen_t *slenp) Return the "don't care" sockaddr in the same family as `sa'. This is the address a client should sobind(9) if it does not care the source address and, if applicable, the port et cetera that it uses.
2007-09-19 08:33:42 +04:00
static const struct sockaddr_in6 in6_any = {
.sin6_len = sizeof(in6_any)
, .sin6_family = AF_INET6
, .sin6_port = 0
, .sin6_flowinfo = 0
, .sin6_addr = IN6ADDR_ANY_INIT
, .sin6_scope_id = 0
};
bool in6_present = false;
static void
in6_dom_init(void)
{
in6_present = true;
}
2006-08-30 21:05:30 +04:00
struct domain inet6domain = {
Here are various changes designed to protect against bad IPv4 routing caused by stale route caches (struct route). Route caches are sprinkled throughout PCBs, the IP fast-forwarding table, and IP tunnel interfaces (gre, gif, stf). Stale IPv6 and ISO route caches will be treated by separate patches. Thank you to Christoph Badura for suggesting the general approach to invalidating route caches that I take here. Here are the details: Add hooks to struct domain for tracking and for invalidating each domain's route caches: dom_rtcache, dom_rtflush, and dom_rtflushall. Introduce helper subroutines, rtflush(ro) for invalidating a route cache, rtflushall(family) for invalidating all route caches in a routing domain, and rtcache(ro) for notifying the domain of a new cached route. Chain together all IPv4 route caches where ro_rt != NULL. Provide in_rtcache() for adding a route to the chain. Provide in_rtflush() and in_rtflushall() for invalidating IPv4 route caches. In in_rtflush(), set ro_rt to NULL, and remove the route from the chain. In in_rtflushall(), walk the chain and remove every route cache. In rtrequest1(), call rtflushall() to invalidate route caches when a route is added. In gif(4), discard the workaround for stale caches that involves expiring them every so often. Replace the pattern 'RTFREE(ro->ro_rt); ro->ro_rt = NULL;' with a call to rtflush(ro). Update ipflow_fastforward() and all other users of route caches so that they expect a cached route, ro->ro_rt, to turn to NULL. Take care when moving a 'struct route' to rtflush() the source and to rtcache() the destination. In domain initializers, use .dom_xxx tags. KNF here and there.
2006-12-09 08:33:04 +03:00
.dom_family = AF_INET6, .dom_name = "internet6",
.dom_init = in6_dom_init, .dom_externalize = NULL, .dom_dispose = NULL,
Here are various changes designed to protect against bad IPv4 routing caused by stale route caches (struct route). Route caches are sprinkled throughout PCBs, the IP fast-forwarding table, and IP tunnel interfaces (gre, gif, stf). Stale IPv6 and ISO route caches will be treated by separate patches. Thank you to Christoph Badura for suggesting the general approach to invalidating route caches that I take here. Here are the details: Add hooks to struct domain for tracking and for invalidating each domain's route caches: dom_rtcache, dom_rtflush, and dom_rtflushall. Introduce helper subroutines, rtflush(ro) for invalidating a route cache, rtflushall(family) for invalidating all route caches in a routing domain, and rtcache(ro) for notifying the domain of a new cached route. Chain together all IPv4 route caches where ro_rt != NULL. Provide in_rtcache() for adding a route to the chain. Provide in_rtflush() and in_rtflushall() for invalidating IPv4 route caches. In in_rtflush(), set ro_rt to NULL, and remove the route from the chain. In in_rtflushall(), walk the chain and remove every route cache. In rtrequest1(), call rtflushall() to invalidate route caches when a route is added. In gif(4), discard the workaround for stale caches that involves expiring them every so often. Replace the pattern 'RTFREE(ro->ro_rt); ro->ro_rt = NULL;' with a call to rtflush(ro). Update ipflow_fastforward() and all other users of route caches so that they expect a cached route, ro->ro_rt, to turn to NULL. Take care when moving a 'struct route' to rtflush() the source and to rtcache() the destination. In domain initializers, use .dom_xxx tags. KNF here and there.
2006-12-09 08:33:04 +03:00
.dom_protosw = (const struct protosw *)inet6sw,
.dom_protoswNPROTOSW = (const struct protosw *)&inet6sw[sizeof(inet6sw)/sizeof(inet6sw[0])],
.dom_rtattach = rt_inithead,
Here are various changes designed to protect against bad IPv4 routing caused by stale route caches (struct route). Route caches are sprinkled throughout PCBs, the IP fast-forwarding table, and IP tunnel interfaces (gre, gif, stf). Stale IPv6 and ISO route caches will be treated by separate patches. Thank you to Christoph Badura for suggesting the general approach to invalidating route caches that I take here. Here are the details: Add hooks to struct domain for tracking and for invalidating each domain's route caches: dom_rtcache, dom_rtflush, and dom_rtflushall. Introduce helper subroutines, rtflush(ro) for invalidating a route cache, rtflushall(family) for invalidating all route caches in a routing domain, and rtcache(ro) for notifying the domain of a new cached route. Chain together all IPv4 route caches where ro_rt != NULL. Provide in_rtcache() for adding a route to the chain. Provide in_rtflush() and in_rtflushall() for invalidating IPv4 route caches. In in_rtflush(), set ro_rt to NULL, and remove the route from the chain. In in_rtflushall(), walk the chain and remove every route cache. In rtrequest1(), call rtflushall() to invalidate route caches when a route is added. In gif(4), discard the workaround for stale caches that involves expiring them every so often. Replace the pattern 'RTFREE(ro->ro_rt); ro->ro_rt = NULL;' with a call to rtflush(ro). Update ipflow_fastforward() and all other users of route caches so that they expect a cached route, ro->ro_rt, to turn to NULL. Take care when moving a 'struct route' to rtflush() the source and to rtcache() the destination. In domain initializers, use .dom_xxx tags. KNF here and there.
2006-12-09 08:33:04 +03:00
.dom_rtoffset = offsetof(struct sockaddr_in6, sin6_addr) << 3,
.dom_maxrtkey = sizeof(struct ip_pack6),
.dom_if_up = in6_if_up, .dom_if_down = in6_if_down,
Here are various changes designed to protect against bad IPv4 routing caused by stale route caches (struct route). Route caches are sprinkled throughout PCBs, the IP fast-forwarding table, and IP tunnel interfaces (gre, gif, stf). Stale IPv6 and ISO route caches will be treated by separate patches. Thank you to Christoph Badura for suggesting the general approach to invalidating route caches that I take here. Here are the details: Add hooks to struct domain for tracking and for invalidating each domain's route caches: dom_rtcache, dom_rtflush, and dom_rtflushall. Introduce helper subroutines, rtflush(ro) for invalidating a route cache, rtflushall(family) for invalidating all route caches in a routing domain, and rtcache(ro) for notifying the domain of a new cached route. Chain together all IPv4 route caches where ro_rt != NULL. Provide in_rtcache() for adding a route to the chain. Provide in_rtflush() and in_rtflushall() for invalidating IPv4 route caches. In in_rtflush(), set ro_rt to NULL, and remove the route from the chain. In in_rtflushall(), walk the chain and remove every route cache. In rtrequest1(), call rtflushall() to invalidate route caches when a route is added. In gif(4), discard the workaround for stale caches that involves expiring them every so often. Replace the pattern 'RTFREE(ro->ro_rt); ro->ro_rt = NULL;' with a call to rtflush(ro). Update ipflow_fastforward() and all other users of route caches so that they expect a cached route, ro->ro_rt, to turn to NULL. Take care when moving a 'struct route' to rtflush() the source and to rtcache() the destination. In domain initializers, use .dom_xxx tags. KNF here and there.
2006-12-09 08:33:04 +03:00
.dom_ifattach = in6_domifattach, .dom_ifdetach = in6_domifdetach,
.dom_if_link_state_change = in6_if_link_state_change,
.dom_ifqueues = { NULL, NULL },
Here are various changes designed to protect against bad IPv4 routing caused by stale route caches (struct route). Route caches are sprinkled throughout PCBs, the IP fast-forwarding table, and IP tunnel interfaces (gre, gif, stf). Stale IPv6 and ISO route caches will be treated by separate patches. Thank you to Christoph Badura for suggesting the general approach to invalidating route caches that I take here. Here are the details: Add hooks to struct domain for tracking and for invalidating each domain's route caches: dom_rtcache, dom_rtflush, and dom_rtflushall. Introduce helper subroutines, rtflush(ro) for invalidating a route cache, rtflushall(family) for invalidating all route caches in a routing domain, and rtcache(ro) for notifying the domain of a new cached route. Chain together all IPv4 route caches where ro_rt != NULL. Provide in_rtcache() for adding a route to the chain. Provide in_rtflush() and in_rtflushall() for invalidating IPv4 route caches. In in_rtflush(), set ro_rt to NULL, and remove the route from the chain. In in_rtflushall(), walk the chain and remove every route cache. In rtrequest1(), call rtflushall() to invalidate route caches when a route is added. In gif(4), discard the workaround for stale caches that involves expiring them every so often. Replace the pattern 'RTFREE(ro->ro_rt); ro->ro_rt = NULL;' with a call to rtflush(ro). Update ipflow_fastforward() and all other users of route caches so that they expect a cached route, ro->ro_rt, to turn to NULL. Take care when moving a 'struct route' to rtflush() the source and to rtcache() the destination. In domain initializers, use .dom_xxx tags. KNF here and there.
2006-12-09 08:33:04 +03:00
.dom_link = { NULL },
Eliminate address family-specific route caches (struct route, struct route_in6, struct route_iso), replacing all caches with a struct route. The principle benefit of this change is that all of the protocol families can benefit from route cache-invalidation, which is necessary for correct routing. Route-cache invalidation fixes an ancient PR, kern/3508, at long last; it fixes various other PRs, also. Discussions with and ideas from Joerg Sonnenberger influenced this work tremendously. Of course, all design oversights and bugs are mine. DETAILS 1 I added to each address family a pool of sockaddrs. I have introduced routines for allocating, copying, and duplicating, and freeing sockaddrs: struct sockaddr *sockaddr_alloc(sa_family_t af, int flags); struct sockaddr *sockaddr_copy(struct sockaddr *dst, const struct sockaddr *src); struct sockaddr *sockaddr_dup(const struct sockaddr *src, int flags); void sockaddr_free(struct sockaddr *sa); sockaddr_alloc() returns either a sockaddr from the pool belonging to the specified family, or NULL if the pool is exhausted. The returned sockaddr has the right size for that family; sa_family and sa_len fields are initialized to the family and sockaddr length---e.g., sa_family = AF_INET and sa_len = sizeof(struct sockaddr_in). sockaddr_free() puts the given sockaddr back into its family's pool. sockaddr_dup() and sockaddr_copy() work analogously to strdup() and strcpy(), respectively. sockaddr_copy() KASSERTs that the family of the destination and source sockaddrs are alike. The 'flags' argumet for sockaddr_alloc() and sockaddr_dup() is passed directly to pool_get(9). 2 I added routines for initializing sockaddrs in each address family, sockaddr_in_init(), sockaddr_in6_init(), sockaddr_iso_init(), etc. They are fairly self-explanatory. 3 structs route_in6 and route_iso are no more. All protocol families use struct route. I have changed the route cache, 'struct route', so that it does not contain storage space for a sockaddr. Instead, struct route points to a sockaddr coming from the pool the sockaddr belongs to. I added a new method to struct route, rtcache_setdst(), for setting the cache destination: int rtcache_setdst(struct route *, const struct sockaddr *); rtcache_setdst() returns 0 on success, or ENOMEM if no memory is available to create the sockaddr storage. It is now possible for rtcache_getdst() to return NULL if, say, rtcache_setdst() failed. I check the return value for NULL everywhere in the kernel. 4 Each routing domain (struct domain) has a list of live route caches, dom_rtcache. rtflushall(sa_family_t af) looks up the domain indicated by 'af', walks the domain's list of route caches and invalidates each one.
2007-05-03 00:40:22 +04:00
.dom_mowner = MOWNER_INIT("",""),
.dom_sa_cmpofs = offsetof(struct sockaddr_in6, sin6_addr),
.dom_sa_cmplen = sizeof(struct in6_addr),
1) Introduce a new socket option, (SOL_SOCKET, SO_NOHEADER), that tells a socket that it should both add a protocol header to tx'd datagrams and remove the header from rx'd datagrams: int onoff = 1, s = socket(...); setsockopt(s, SOL_SOCKET, SO_NOHEADER, &onoff); 2) Add an implementation of (SOL_SOCKET, SO_NOHEADER) for raw IPv4 sockets. 3) Reorganize the protocols' pr_ctloutput implementations a bit. Consistently return ENOPROTOOPT when an option is unsupported, and EINVAL if a supported option's arguments are incorrect. Reorganize the flow of code so that it's more clear how/when options are passed down the stack until they are handled. Shorten some pr_ctloutput staircases for readability. 4) Extract common mbuf code into subroutines, add new sockaddr methods, and introduce a new subroutine, fsocreate(), for reuse later; use it first in sys_socket(): struct mbuf *m_getsombuf(struct socket *so) Create an mbuf and make its owner the socket `so'. struct mbuf *m_intopt(struct socket *so, int val) Create an mbuf, make its owner the socket `so', put the int `val' into it, and set its length to sizeof(int). int fsocreate(..., int *fd) Create a socket, a la socreate(9), put the socket into the given LWP's descriptor table, return the descriptor at `fd' on success. void *sockaddr_addr(struct sockaddr *sa, socklen_t *slenp) const void *sockaddr_const_addr(const struct sockaddr *sa, socklen_t *slenp) Extract a pointer to the address part of a sockaddr. Write the length of the address part at `slenp', if `slenp' is not NULL. socklen_t sockaddr_getlen(const struct sockaddr *sa) Return the length of a sockaddr. This just evaluates to sa->sa_len. I only add this for consistency with code that appears in a portable userland library that I am going to import. const struct sockaddr *sockaddr_any(const struct sockaddr *sa) Return the "don't care" sockaddr in the same family as `sa'. This is the address a client should sobind(9) if it does not care the source address and, if applicable, the port et cetera that it uses. const void *sockaddr_anyaddr(const struct sockaddr *sa, socklen_t *slenp) Return the "don't care" sockaddr in the same family as `sa'. This is the address a client should sobind(9) if it does not care the source address and, if applicable, the port et cetera that it uses.
2007-09-19 08:33:42 +04:00
.dom_sa_any = (const struct sockaddr *)&in6_any,
.dom_sockaddr_externalize = sockaddr_in6_externalize,
.dom_rtcache = LIST_HEAD_INITIALIZER(inet6domain.dom_rtcache)
2006-08-30 21:05:30 +04:00
};
#if 0
Eliminate address family-specific route caches (struct route, struct route_in6, struct route_iso), replacing all caches with a struct route. The principle benefit of this change is that all of the protocol families can benefit from route cache-invalidation, which is necessary for correct routing. Route-cache invalidation fixes an ancient PR, kern/3508, at long last; it fixes various other PRs, also. Discussions with and ideas from Joerg Sonnenberger influenced this work tremendously. Of course, all design oversights and bugs are mine. DETAILS 1 I added to each address family a pool of sockaddrs. I have introduced routines for allocating, copying, and duplicating, and freeing sockaddrs: struct sockaddr *sockaddr_alloc(sa_family_t af, int flags); struct sockaddr *sockaddr_copy(struct sockaddr *dst, const struct sockaddr *src); struct sockaddr *sockaddr_dup(const struct sockaddr *src, int flags); void sockaddr_free(struct sockaddr *sa); sockaddr_alloc() returns either a sockaddr from the pool belonging to the specified family, or NULL if the pool is exhausted. The returned sockaddr has the right size for that family; sa_family and sa_len fields are initialized to the family and sockaddr length---e.g., sa_family = AF_INET and sa_len = sizeof(struct sockaddr_in). sockaddr_free() puts the given sockaddr back into its family's pool. sockaddr_dup() and sockaddr_copy() work analogously to strdup() and strcpy(), respectively. sockaddr_copy() KASSERTs that the family of the destination and source sockaddrs are alike. The 'flags' argumet for sockaddr_alloc() and sockaddr_dup() is passed directly to pool_get(9). 2 I added routines for initializing sockaddrs in each address family, sockaddr_in_init(), sockaddr_in6_init(), sockaddr_iso_init(), etc. They are fairly self-explanatory. 3 structs route_in6 and route_iso are no more. All protocol families use struct route. I have changed the route cache, 'struct route', so that it does not contain storage space for a sockaddr. Instead, struct route points to a sockaddr coming from the pool the sockaddr belongs to. I added a new method to struct route, rtcache_setdst(), for setting the cache destination: int rtcache_setdst(struct route *, const struct sockaddr *); rtcache_setdst() returns 0 on success, or ENOMEM if no memory is available to create the sockaddr storage. It is now possible for rtcache_getdst() to return NULL if, say, rtcache_setdst() failed. I check the return value for NULL everywhere in the kernel. 4 Each routing domain (struct domain) has a list of live route caches, dom_rtcache. rtflushall(sa_family_t af) looks up the domain indicated by 'af', walks the domain's list of route caches and invalidates each one.
2007-05-03 00:40:22 +04:00
int
sockaddr_in6_cmp(const struct sockaddr *lsa, const struct sockaddr *rsa)
{
uint_fast8_t len;
const uint_fast8_t addrofs = offsetof(struct sockaddr_in6, sin6_addr),
addrend = addrofs + sizeof(struct in6_addr);
int rc;
const struct sockaddr_in6 *lsin6, *rsin6;
lsin6 = satocsin6(lsa);
rsin6 = satocsin6(rsa);
len = MIN(addrend, MIN(lsin6->sin6_len, rsin6->sin6_len));
if (len > addrofs &&
(rc = memcmp(&lsin6->sin6_addr, &rsin6->sin6_addr,
len - addrofs)) != 0)
return rc;
return lsin6->sin6_len - rsin6->sin6_len;
}
#endif
Eliminate address family-specific route caches (struct route, struct route_in6, struct route_iso), replacing all caches with a struct route. The principle benefit of this change is that all of the protocol families can benefit from route cache-invalidation, which is necessary for correct routing. Route-cache invalidation fixes an ancient PR, kern/3508, at long last; it fixes various other PRs, also. Discussions with and ideas from Joerg Sonnenberger influenced this work tremendously. Of course, all design oversights and bugs are mine. DETAILS 1 I added to each address family a pool of sockaddrs. I have introduced routines for allocating, copying, and duplicating, and freeing sockaddrs: struct sockaddr *sockaddr_alloc(sa_family_t af, int flags); struct sockaddr *sockaddr_copy(struct sockaddr *dst, const struct sockaddr *src); struct sockaddr *sockaddr_dup(const struct sockaddr *src, int flags); void sockaddr_free(struct sockaddr *sa); sockaddr_alloc() returns either a sockaddr from the pool belonging to the specified family, or NULL if the pool is exhausted. The returned sockaddr has the right size for that family; sa_family and sa_len fields are initialized to the family and sockaddr length---e.g., sa_family = AF_INET and sa_len = sizeof(struct sockaddr_in). sockaddr_free() puts the given sockaddr back into its family's pool. sockaddr_dup() and sockaddr_copy() work analogously to strdup() and strcpy(), respectively. sockaddr_copy() KASSERTs that the family of the destination and source sockaddrs are alike. The 'flags' argumet for sockaddr_alloc() and sockaddr_dup() is passed directly to pool_get(9). 2 I added routines for initializing sockaddrs in each address family, sockaddr_in_init(), sockaddr_in6_init(), sockaddr_iso_init(), etc. They are fairly self-explanatory. 3 structs route_in6 and route_iso are no more. All protocol families use struct route. I have changed the route cache, 'struct route', so that it does not contain storage space for a sockaddr. Instead, struct route points to a sockaddr coming from the pool the sockaddr belongs to. I added a new method to struct route, rtcache_setdst(), for setting the cache destination: int rtcache_setdst(struct route *, const struct sockaddr *); rtcache_setdst() returns 0 on success, or ENOMEM if no memory is available to create the sockaddr storage. It is now possible for rtcache_getdst() to return NULL if, say, rtcache_setdst() failed. I check the return value for NULL everywhere in the kernel. 4 Each routing domain (struct domain) has a list of live route caches, dom_rtcache. rtflushall(sa_family_t af) looks up the domain indicated by 'af', walks the domain's list of route caches and invalidates each one.
2007-05-03 00:40:22 +04:00
/*
* Internet configuration info
*/
#ifndef IPV6FORWARDING
#ifdef GATEWAY6
#define IPV6FORWARDING 1 /* forward IP6 packets not for us */
#else
#define IPV6FORWARDING 0 /* don't forward IP6 packets not for us */
#endif /* GATEWAY6 */
#endif /* !IPV6FORWARDING */
int ip6_forwarding = IPV6FORWARDING; /* act as router? */
int ip6_sendredirects = 1;
int ip6_defhlim = IPV6_DEFHLIM;
int ip6_defmcasthlim = IPV6_DEFAULT_MULTICAST_HOPS;
int ip6_accept_rtadv = 0; /* "IPV6FORWARDING ? 0 : 1" is dangerous */
int ip6_maxfragpackets = 200;
int ip6_maxfrags = 200;
int ip6_log_interval = 5;
int ip6_hdrnestlimit = 50; /* appropriate? */
int ip6_dad_count = 1; /* DupAddrDetectionTransmits */
int ip6_auto_flowlabel = 1;
int ip6_use_deprecated = 1; /* allow deprecated addr (RFC2462 5.5.4) */
int ip6_rr_prune = 5; /* router renumbering prefix
* walk list every 5 sec. */
int ip6_mcast_pmtu = 0; /* enable pMTU discovery for multicast? */
int ip6_v6only = 1;
int ip6_neighborgcthresh = 2048; /* Threshold # of NDP entries for GC */
int ip6_maxifprefixes = 16; /* Max acceptable prefixes via RA per IF */
int ip6_maxifdefrouters = 16; /* Max acceptable def routers via RA */
int ip6_maxdynroutes = 4096; /* Max # of routes created via redirect */
int ip6_keepfaith = 0;
time_t ip6_log_time = 0;
int ip6_rtadv_maxroutes = 100; /* (arbitrary) initial maximum number of
* routes via rtadv expected to be
* significantly larger than common use.
* if you need to count: 3 extra initial
* routes, plus 1 per interface after the
* first one, then one per non-linklocal
* prefix */
/* icmp6 */
/*
* BSDI4 defines these variables in in_proto.c...
* XXX: what if we don't define INET? Should we define pmtu6_expire
* or so? (jinmei@kame.net 19990310)
*/
int pmtu_expire = 60*10;
/* raw IP6 parameters */
/*
* Nominal space allocated to a raw ip socket.
*/
#define RIPV6SNDQ 8192
#define RIPV6RCVQ 8192
u_long rip6_sendspace = RIPV6SNDQ;
u_long rip6_recvspace = RIPV6RCVQ;
/* ICMPV6 parameters */
int icmp6_rediraccept = 1; /* accept and process redirects */
int icmp6_redirtimeout = 10 * 60; /* 10 minutes */
int icmp6errppslim = 100; /* 100pps */
int icmp6_nodeinfo = 1; /* enable/disable NI response */