2003-11-14 21:02:22 +00:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2003 Andre Oppermann, Internet Business Solutions AG
|
|
|
|
* 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. The name of the author may not be used to endorse or promote
|
|
|
|
* products derived from this software without specific prior written
|
|
|
|
* permission.
|
|
|
|
*
|
|
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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.
|
|
|
|
*
|
|
|
|
* $FreeBSD$
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* ip_fastforward gets its speed from processing the forwarded packet to
|
|
|
|
* completion (if_output on the other side) without any queues or netisr's.
|
|
|
|
* The receiving interface DMAs the packet into memory, the upper half of
|
|
|
|
* driver calls ip_fastforward, we do our routing table lookup and directly
|
|
|
|
* send it off to the outgoing interface which DMAs the packet to the
|
|
|
|
* network card. The only part of the packet we touch with the CPU is the
|
2003-11-15 17:03:37 +00:00
|
|
|
* IP header (unless there are complex firewall rules touching other parts
|
|
|
|
* of the packet, but that is up to you). We are essentially limited by bus
|
|
|
|
* bandwidth and how fast the network card/driver can set up receives and
|
|
|
|
* transmits.
|
2003-11-14 21:02:22 +00:00
|
|
|
*
|
|
|
|
* We handle basic errors, ip header errors, checksum errors,
|
|
|
|
* destination unreachable, fragmentation and fragmentation needed and
|
|
|
|
* report them via icmp to the sender.
|
|
|
|
*
|
|
|
|
* Else if something is not pure IPv4 unicast forwarding we fall back to
|
|
|
|
* the normal ip_input processing path. We should only be called from
|
|
|
|
* interfaces connected to the outside world.
|
|
|
|
*
|
|
|
|
* Firewalling is fully supported including divert, ipfw fwd and ipfilter
|
|
|
|
* ipnat and address rewrite.
|
|
|
|
*
|
|
|
|
* IPSEC is not supported if this host is a tunnel broker. IPSEC is
|
|
|
|
* supported for connections to/from local host.
|
|
|
|
*
|
|
|
|
* We try to do the least expensive (in CPU ops) checks and operations
|
|
|
|
* first to catch junk with as little overhead as possible.
|
|
|
|
*
|
|
|
|
* We take full advantage of hardware support for ip checksum and
|
|
|
|
* fragmentation offloading.
|
|
|
|
*
|
|
|
|
* We don't do ICMP redirect in the fast forwarding path. I have had my own
|
|
|
|
* cases where two core routers with Zebra routing suite would send millions
|
|
|
|
* ICMP redirects to connected hosts if the router to dest was not the default
|
|
|
|
* gateway. In one case it was filling the routing table of a host with close
|
|
|
|
* 300'000 cloned redirect entries until it ran out of kernel memory. However
|
|
|
|
* the networking code proved very robust and it didn't crash or went ill
|
|
|
|
* otherwise.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Many thanks to Matt Thomas of NetBSD for basic structure of ip_flow.c which
|
|
|
|
* is being followed here.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "opt_ipfw.h"
|
|
|
|
#include "opt_ipdn.h"
|
|
|
|
#include "opt_ipdivert.h"
|
|
|
|
#include "opt_ipfilter.h"
|
|
|
|
#include "opt_ipstealth.h"
|
|
|
|
#include "opt_pfil_hooks.h"
|
|
|
|
|
|
|
|
#include <sys/param.h>
|
|
|
|
#include <sys/systm.h>
|
|
|
|
#include <sys/kernel.h>
|
|
|
|
#include <sys/malloc.h>
|
|
|
|
#include <sys/mbuf.h>
|
|
|
|
#include <sys/protosw.h>
|
|
|
|
#include <sys/socket.h>
|
|
|
|
#include <sys/sysctl.h>
|
|
|
|
|
|
|
|
#include <net/pfil.h>
|
|
|
|
#include <net/if.h>
|
|
|
|
#include <net/if_types.h>
|
|
|
|
#include <net/if_var.h>
|
|
|
|
#include <net/if_dl.h>
|
|
|
|
#include <net/route.h>
|
|
|
|
|
|
|
|
#include <netinet/in.h>
|
|
|
|
#include <netinet/in_systm.h>
|
|
|
|
#include <netinet/in_var.h>
|
|
|
|
#include <netinet/ip.h>
|
|
|
|
#include <netinet/ip_var.h>
|
|
|
|
#include <netinet/ip_icmp.h>
|
|
|
|
|
|
|
|
#include <machine/in_cksum.h>
|
|
|
|
|
|
|
|
#include <netinet/ip_fw.h>
|
2004-02-25 19:55:29 +00:00
|
|
|
#include <netinet/ip_divert.h>
|
2003-11-14 21:02:22 +00:00
|
|
|
#include <netinet/ip_dummynet.h>
|
|
|
|
|
|
|
|
static int ipfastforward_active = 0;
|
|
|
|
SYSCTL_INT(_net_inet_ip, OID_AUTO, fastforwarding, CTLFLAG_RW,
|
|
|
|
&ipfastforward_active, 0, "Enable fast IP forwarding");
|
|
|
|
|
2004-05-03 13:52:47 +00:00
|
|
|
static struct sockaddr_in *
|
|
|
|
ip_findroute(struct route *ro, in_addr_t dest, struct mbuf *m)
|
|
|
|
{
|
|
|
|
struct sockaddr_in *dst;
|
|
|
|
struct rtentry *rt;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Find route to destination.
|
|
|
|
*/
|
|
|
|
bzero(ro, sizeof(*ro));
|
|
|
|
dst = (struct sockaddr_in *)&ro->ro_dst;
|
|
|
|
dst->sin_family = AF_INET;
|
|
|
|
dst->sin_len = sizeof(*dst);
|
|
|
|
dst->sin_addr.s_addr = dest;
|
|
|
|
rtalloc_ign(ro, RTF_CLONING);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Route there and interface still up?
|
|
|
|
*/
|
|
|
|
rt = ro->ro_rt;
|
|
|
|
if (rt && (rt->rt_flags & RTF_UP) &&
|
|
|
|
(rt->rt_ifp->if_flags & IFF_UP) &&
|
|
|
|
(rt->rt_ifp->if_flags & IFF_RUNNING)) {
|
|
|
|
if (rt->rt_flags & RTF_GATEWAY)
|
|
|
|
dst = (struct sockaddr_in *)rt->rt_gateway;
|
|
|
|
} else {
|
|
|
|
ipstat.ips_noroute++;
|
|
|
|
ipstat.ips_cantforward++;
|
|
|
|
if (rt)
|
|
|
|
RTFREE(rt);
|
|
|
|
icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_HOST, 0, NULL);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
return dst;
|
|
|
|
}
|
|
|
|
|
2003-11-14 21:02:22 +00:00
|
|
|
/*
|
|
|
|
* Try to forward a packet based on the destination address.
|
|
|
|
* This is a fast path optimized for the plain forwarding case.
|
|
|
|
* If the packet is handled (and consumed) here then we return 1;
|
|
|
|
* otherwise 0 is returned and the packet should be delivered
|
|
|
|
* to ip_input for full processing.
|
|
|
|
*/
|
|
|
|
int
|
|
|
|
ip_fastforward(struct mbuf *m)
|
|
|
|
{
|
|
|
|
struct ip *ip;
|
|
|
|
struct mbuf *m0 = NULL;
|
|
|
|
#ifdef IPDIVERT
|
|
|
|
struct ip *tip;
|
2004-02-25 19:55:29 +00:00
|
|
|
struct mbuf *clone = NULL;
|
2003-11-14 21:02:22 +00:00
|
|
|
#endif
|
|
|
|
struct route ro;
|
|
|
|
struct sockaddr_in *dst = NULL;
|
|
|
|
struct in_ifaddr *ia = NULL;
|
|
|
|
struct ifaddr *ifa = NULL;
|
2004-05-03 13:52:47 +00:00
|
|
|
struct ifnet *ifp;
|
2003-11-14 21:02:22 +00:00
|
|
|
struct ip_fw_args args;
|
|
|
|
in_addr_t odest, dest;
|
2004-05-03 13:52:47 +00:00
|
|
|
u_short sum, ip_len;
|
2003-11-14 21:02:22 +00:00
|
|
|
int error = 0;
|
|
|
|
int hlen, ipfw, mtu;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Are we active and forwarding packets?
|
|
|
|
*/
|
|
|
|
if (!ipfastforward_active || !ipforwarding)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
M_ASSERTVALID(m);
|
|
|
|
M_ASSERTPKTHDR(m);
|
|
|
|
|
2004-05-03 13:52:47 +00:00
|
|
|
ro.ro_rt = NULL;
|
|
|
|
|
2003-11-14 21:02:22 +00:00
|
|
|
/*
|
|
|
|
* Step 1: check for packet drop conditions (and sanity checks)
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Is entire packet big enough?
|
|
|
|
*/
|
|
|
|
if (m->m_pkthdr.len < sizeof(struct ip)) {
|
|
|
|
ipstat.ips_tooshort++;
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Is first mbuf large enough for ip header and is header present?
|
|
|
|
*/
|
|
|
|
if (m->m_len < sizeof (struct ip) &&
|
|
|
|
(m = m_pullup(m, sizeof (struct ip))) == 0) {
|
|
|
|
ipstat.ips_toosmall++;
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
|
|
|
|
ip = mtod(m, struct ip *);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Is it IPv4?
|
|
|
|
*/
|
|
|
|
if (ip->ip_v != IPVERSION) {
|
|
|
|
ipstat.ips_badvers++;
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Is IP header length correct and is it in first mbuf?
|
|
|
|
*/
|
|
|
|
hlen = ip->ip_hl << 2;
|
|
|
|
if (hlen < sizeof(struct ip)) { /* minimum header length */
|
|
|
|
ipstat.ips_badlen++;
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
if (hlen > m->m_len) {
|
|
|
|
if ((m = m_pullup(m, hlen)) == 0) {
|
|
|
|
ipstat.ips_badhlen++;
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
ip = mtod(m, struct ip *);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Checksum correct?
|
|
|
|
*/
|
|
|
|
if (m->m_pkthdr.csum_flags & CSUM_IP_CHECKED)
|
|
|
|
sum = !(m->m_pkthdr.csum_flags & CSUM_IP_VALID);
|
|
|
|
else {
|
|
|
|
if (hlen == sizeof(struct ip))
|
|
|
|
sum = in_cksum_hdr(ip);
|
|
|
|
else
|
|
|
|
sum = in_cksum(m, hlen);
|
|
|
|
}
|
|
|
|
if (sum) {
|
|
|
|
ipstat.ips_badsum++;
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
m->m_pkthdr.csum_flags |= (CSUM_IP_CHECKED | CSUM_IP_VALID);
|
|
|
|
|
2004-05-03 13:52:47 +00:00
|
|
|
ip_len = ntohs(ip->ip_len);
|
2003-11-14 21:02:22 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Is IP length longer than packet we have got?
|
|
|
|
*/
|
2004-05-03 13:52:47 +00:00
|
|
|
if (m->m_pkthdr.len < ip_len) {
|
2003-11-14 21:02:22 +00:00
|
|
|
ipstat.ips_tooshort++;
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Is packet longer than IP header tells us? If yes, truncate packet.
|
|
|
|
*/
|
2004-05-03 13:52:47 +00:00
|
|
|
if (m->m_pkthdr.len > ip_len) {
|
2003-11-14 21:02:22 +00:00
|
|
|
if (m->m_len == m->m_pkthdr.len) {
|
2004-05-03 13:52:47 +00:00
|
|
|
m->m_len = ip_len;
|
|
|
|
m->m_pkthdr.len = ip_len;
|
2003-11-14 21:02:22 +00:00
|
|
|
} else
|
2004-05-03 13:52:47 +00:00
|
|
|
m_adj(m, ip_len - m->m_pkthdr.len);
|
2003-11-14 21:02:22 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Is packet from or to 127/8?
|
|
|
|
*/
|
|
|
|
if ((ntohl(ip->ip_dst.s_addr) >> IN_CLASSA_NSHIFT) == IN_LOOPBACKNET ||
|
|
|
|
(ntohl(ip->ip_src.s_addr) >> IN_CLASSA_NSHIFT) == IN_LOOPBACKNET) {
|
|
|
|
ipstat.ips_badaddr++;
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Step 2: fallback conditions to normal ip_input path processing
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Only IP packets without options
|
|
|
|
*/
|
2004-05-06 18:46:03 +00:00
|
|
|
if (ip->ip_hl != (sizeof(struct ip) >> 2)) {
|
|
|
|
if (ip_doopts == 1)
|
|
|
|
return 0;
|
|
|
|
else if (ip_doopts == 2) {
|
|
|
|
icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_FILTER_PROHIB,
|
|
|
|
0, NULL);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
/* else ignore IP options and continue */
|
|
|
|
}
|
2003-11-14 21:02:22 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Only unicast IP, not from loopback, no L2 or IP broadcast,
|
|
|
|
* no multicast, no INADDR_ANY
|
|
|
|
*
|
|
|
|
* XXX: Probably some of these checks could be direct drop
|
|
|
|
* conditions. However it is not clear whether there are some
|
|
|
|
* hacks or obscure behaviours which make it neccessary to
|
|
|
|
* let ip_input handle it. We play safe here and let ip_input
|
|
|
|
* deal with it until it is proven that we can directly drop it.
|
|
|
|
*/
|
|
|
|
if ((m->m_pkthdr.rcvif->if_flags & IFF_LOOPBACK) ||
|
|
|
|
ntohl(ip->ip_src.s_addr) == (u_long)INADDR_BROADCAST ||
|
|
|
|
ntohl(ip->ip_dst.s_addr) == (u_long)INADDR_BROADCAST ||
|
|
|
|
IN_MULTICAST(ntohl(ip->ip_src.s_addr)) ||
|
|
|
|
IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) ||
|
|
|
|
ip->ip_dst.s_addr == INADDR_ANY )
|
2004-05-03 13:52:47 +00:00
|
|
|
return 0;
|
2003-11-14 21:02:22 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Is it for a local address on this host?
|
|
|
|
*/
|
|
|
|
LIST_FOREACH(ia, INADDR_HASH(ip->ip_dst.s_addr), ia_hash) {
|
|
|
|
if (IA_SIN(ia)->sin_addr.s_addr == ip->ip_dst.s_addr)
|
2004-05-03 13:52:47 +00:00
|
|
|
return 0;
|
2003-11-14 21:02:22 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Or is it for a local IP broadcast address on this host?
|
|
|
|
*/
|
|
|
|
if (m->m_pkthdr.rcvif->if_flags & IFF_BROADCAST) {
|
|
|
|
TAILQ_FOREACH(ifa, &m->m_pkthdr.rcvif->if_addrhead, ifa_link) {
|
|
|
|
if (ifa->ifa_addr->sa_family != AF_INET)
|
|
|
|
continue;
|
|
|
|
ia = ifatoia(ifa);
|
|
|
|
if (ia->ia_netbroadcast.s_addr == ip->ip_dst.s_addr)
|
2004-05-03 13:52:47 +00:00
|
|
|
return 0;
|
2003-11-14 21:02:22 +00:00
|
|
|
if (satosin(&ia->ia_broadaddr)->sin_addr.s_addr ==
|
|
|
|
ip->ip_dst.s_addr)
|
2004-05-03 13:52:47 +00:00
|
|
|
return 0;
|
2003-11-14 21:02:22 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
ipstat.ips_total++;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Step 3: incoming packet firewall processing
|
|
|
|
*/
|
|
|
|
|
2004-05-03 13:52:47 +00:00
|
|
|
/*
|
|
|
|
* Convert to host representation
|
|
|
|
*/
|
|
|
|
ip->ip_len = ntohs(ip->ip_len);
|
|
|
|
ip->ip_off = ntohs(ip->ip_off);
|
|
|
|
|
2003-11-14 21:02:22 +00:00
|
|
|
odest = dest = ip->ip_dst.s_addr;
|
|
|
|
#ifdef PFIL_HOOKS
|
|
|
|
/*
|
|
|
|
* Run through list of ipfilter hooks for input packets
|
|
|
|
*/
|
|
|
|
if (pfil_run_hooks(&inet_pfil_hook, &m, m->m_pkthdr.rcvif, PFIL_IN) ||
|
|
|
|
m == NULL)
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
M_ASSERTVALID(m);
|
|
|
|
M_ASSERTPKTHDR(m);
|
|
|
|
|
|
|
|
ip = mtod(m, struct ip *); /* m may have changed by pfil hook */
|
|
|
|
dest = ip->ip_dst.s_addr;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Run through ipfw for input packets
|
|
|
|
*/
|
|
|
|
if (fw_enable && IPFW_LOADED) {
|
|
|
|
bzero(&args, sizeof(args));
|
|
|
|
args.m = m;
|
|
|
|
|
|
|
|
ipfw = ip_fw_chk_ptr(&args);
|
|
|
|
m = args.m;
|
|
|
|
|
|
|
|
M_ASSERTVALID(m);
|
|
|
|
M_ASSERTPKTHDR(m);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Packet denied, drop it
|
|
|
|
*/
|
|
|
|
if ((ipfw & IP_FW_PORT_DENY_FLAG) || m == NULL)
|
|
|
|
goto drop;
|
|
|
|
/*
|
|
|
|
* Send packet to the appropriate pipe
|
|
|
|
*/
|
|
|
|
if (DUMMYNET_LOADED && (ipfw & IP_FW_PORT_DYNT_FLAG) != 0) {
|
|
|
|
ip_dn_io_ptr(m, ipfw & 0xffff, DN_TO_IP_IN, &args);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
#ifdef IPDIVERT
|
|
|
|
/*
|
|
|
|
* Divert packet
|
|
|
|
*/
|
|
|
|
if (ipfw != 0 && (ipfw & IP_FW_PORT_DYNT_FLAG) == 0) {
|
|
|
|
/*
|
|
|
|
* See if this is a fragment
|
|
|
|
*/
|
2004-02-25 19:55:29 +00:00
|
|
|
if (ip->ip_off & (IP_MF | IP_OFFMASK))
|
2003-11-14 21:02:22 +00:00
|
|
|
goto droptoours;
|
|
|
|
/*
|
|
|
|
* Tee packet
|
|
|
|
*/
|
|
|
|
if ((ipfw & IP_FW_PORT_TEE_FLAG) != 0)
|
2004-02-25 19:55:29 +00:00
|
|
|
clone = divert_clone(m);
|
2003-11-14 21:02:22 +00:00
|
|
|
else
|
2004-02-25 19:55:29 +00:00
|
|
|
clone = m;
|
|
|
|
if (clone == NULL)
|
2003-11-14 21:02:22 +00:00
|
|
|
goto passin;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Delayed checksums are not compatible
|
|
|
|
*/
|
2004-02-25 19:55:29 +00:00
|
|
|
if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
|
|
|
|
in_delayed_cksum(m);
|
|
|
|
m->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
|
2003-11-14 21:02:22 +00:00
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Restore packet header fields to original values
|
|
|
|
*/
|
2004-02-25 19:55:29 +00:00
|
|
|
tip = mtod(m, struct ip *);
|
2003-11-14 21:02:22 +00:00
|
|
|
tip->ip_len = htons(tip->ip_len);
|
|
|
|
tip->ip_off = htons(tip->ip_off);
|
|
|
|
/*
|
|
|
|
* Deliver packet to divert input routine
|
|
|
|
*/
|
2004-02-25 19:55:29 +00:00
|
|
|
divert_packet(m, 0);
|
2003-11-14 21:02:22 +00:00
|
|
|
/*
|
|
|
|
* If this was not tee, we are done
|
|
|
|
*/
|
2004-02-25 19:55:29 +00:00
|
|
|
m = clone;
|
2003-11-14 21:02:22 +00:00
|
|
|
if ((ipfw & IP_FW_PORT_TEE_FLAG) == 0)
|
|
|
|
return 1;
|
|
|
|
/* Continue if it was tee */
|
|
|
|
goto passin;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
if (ipfw == 0 && args.next_hop != NULL) {
|
|
|
|
dest = args.next_hop->sin_addr.s_addr;
|
|
|
|
goto passin;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Let through or not?
|
|
|
|
*/
|
|
|
|
if (ipfw != 0)
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
passin:
|
|
|
|
ip = mtod(m, struct ip *); /* if m changed during fw processing */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Destination address changed?
|
|
|
|
*/
|
|
|
|
if (odest != dest) {
|
|
|
|
/*
|
|
|
|
* Is it now for a local address on this host?
|
|
|
|
*/
|
|
|
|
LIST_FOREACH(ia, INADDR_HASH(ip->ip_dst.s_addr), ia_hash) {
|
|
|
|
if (IA_SIN(ia)->sin_addr.s_addr == ip->ip_dst.s_addr)
|
|
|
|
goto forwardlocal;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Go on with new destination address
|
|
|
|
*/
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Step 4: decrement TTL and look up route
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check TTL
|
|
|
|
*/
|
|
|
|
#ifdef IPSTEALTH
|
|
|
|
if (!ipstealth) {
|
|
|
|
#endif
|
|
|
|
if (ip->ip_ttl <= IPTTLDEC) {
|
2003-12-23 02:36:43 +00:00
|
|
|
icmp_error(m, ICMP_TIMXCEED, ICMP_TIMXCEED_INTRANS, 0, NULL);
|
2003-11-14 21:02:22 +00:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Decrement the TTL and incrementally change the checksum.
|
|
|
|
* Don't bother doing this with hw checksum offloading.
|
|
|
|
*/
|
|
|
|
ip->ip_ttl -= IPTTLDEC;
|
|
|
|
if (ip->ip_sum >= (u_int16_t) ~htons(IPTTLDEC << 8))
|
|
|
|
ip->ip_sum -= ~htons(IPTTLDEC << 8);
|
|
|
|
else
|
|
|
|
ip->ip_sum += htons(IPTTLDEC << 8);
|
|
|
|
#ifdef IPSTEALTH
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Find route to destination.
|
|
|
|
*/
|
2004-05-03 13:52:47 +00:00
|
|
|
if ((dst = ip_findroute(&ro, dest, m)) == NULL)
|
|
|
|
return 1; /* icmp unreach already sent */
|
|
|
|
ifp = ro.ro_rt->rt_ifp;
|
2003-11-14 21:02:22 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Step 5: outgoing firewall packet processing
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifdef PFIL_HOOKS
|
|
|
|
/*
|
|
|
|
* Run through list of hooks for output packets.
|
|
|
|
*/
|
|
|
|
if (pfil_run_hooks(&inet_pfil_hook, &m, ifp, PFIL_OUT) || m == NULL) {
|
2004-05-03 13:52:47 +00:00
|
|
|
goto consumed;
|
2003-11-14 21:02:22 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
M_ASSERTVALID(m);
|
|
|
|
M_ASSERTPKTHDR(m);
|
|
|
|
|
|
|
|
ip = mtod(m, struct ip *);
|
|
|
|
dest = ip->ip_dst.s_addr;
|
|
|
|
#endif
|
|
|
|
if (fw_enable && IPFW_LOADED && !args.next_hop) {
|
2003-11-15 17:03:37 +00:00
|
|
|
bzero(&args, sizeof(args));
|
2003-11-14 21:02:22 +00:00
|
|
|
args.m = m;
|
|
|
|
args.oif = ifp;
|
|
|
|
|
|
|
|
ipfw = ip_fw_chk_ptr(&args);
|
|
|
|
m = args.m;
|
|
|
|
|
|
|
|
M_ASSERTVALID(m);
|
|
|
|
M_ASSERTPKTHDR(m);
|
|
|
|
|
2004-05-03 13:52:47 +00:00
|
|
|
if ((ipfw & IP_FW_PORT_DENY_FLAG) || m == NULL)
|
2003-11-14 21:02:22 +00:00
|
|
|
goto drop;
|
2004-05-03 13:52:47 +00:00
|
|
|
|
2003-11-14 21:02:22 +00:00
|
|
|
if (DUMMYNET_LOADED && (ipfw & IP_FW_PORT_DYNT_FLAG) != 0) {
|
|
|
|
/*
|
|
|
|
* XXX note: if the ifp or rt entry are deleted
|
|
|
|
* while a pkt is in dummynet, we are in trouble!
|
|
|
|
*/
|
|
|
|
args.ro = &ro; /* dummynet does not save it */
|
|
|
|
args.dst = dst;
|
|
|
|
|
|
|
|
ip_dn_io_ptr(m, ipfw & 0xffff, DN_TO_IP_OUT, &args);
|
2004-05-03 13:52:47 +00:00
|
|
|
goto consumed;
|
2003-11-14 21:02:22 +00:00
|
|
|
}
|
|
|
|
#ifdef IPDIVERT
|
|
|
|
if (ipfw != 0 && (ipfw & IP_FW_PORT_DYNT_FLAG) == 0) {
|
|
|
|
/*
|
|
|
|
* See if this is a fragment
|
|
|
|
*/
|
2004-02-25 19:55:29 +00:00
|
|
|
if (ip->ip_off & (IP_MF | IP_OFFMASK))
|
2003-11-14 21:02:22 +00:00
|
|
|
goto droptoours;
|
|
|
|
/*
|
|
|
|
* Tee packet
|
|
|
|
*/
|
|
|
|
if ((ipfw & IP_FW_PORT_TEE_FLAG) != 0)
|
2004-02-25 19:55:29 +00:00
|
|
|
clone = divert_clone(m);
|
2003-11-14 21:02:22 +00:00
|
|
|
else
|
2004-02-25 19:55:29 +00:00
|
|
|
clone = m;
|
|
|
|
if (clone == NULL)
|
2003-11-14 21:02:22 +00:00
|
|
|
goto passout;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Delayed checksums are not compatible with divert
|
|
|
|
*/
|
2004-02-25 19:55:29 +00:00
|
|
|
if (m->m_pkthdr.csum_flags & CSUM_DELAY_DATA) {
|
|
|
|
in_delayed_cksum(m);
|
|
|
|
m->m_pkthdr.csum_flags &= ~CSUM_DELAY_DATA;
|
2003-11-14 21:02:22 +00:00
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Restore packet header fields to original values
|
|
|
|
*/
|
2004-02-25 19:55:29 +00:00
|
|
|
tip = mtod(m, struct ip *);
|
2003-11-14 21:02:22 +00:00
|
|
|
tip->ip_len = htons(tip->ip_len);
|
|
|
|
tip->ip_off = htons(tip->ip_off);
|
|
|
|
/*
|
|
|
|
* Deliver packet to divert input routine
|
|
|
|
*/
|
2004-02-25 19:55:29 +00:00
|
|
|
divert_packet(m, 0);
|
2003-11-14 21:02:22 +00:00
|
|
|
/*
|
|
|
|
* If this was not tee, we are done
|
|
|
|
*/
|
2004-02-25 19:55:29 +00:00
|
|
|
m = clone;
|
2003-11-14 21:02:22 +00:00
|
|
|
if ((ipfw & IP_FW_PORT_TEE_FLAG) == 0) {
|
2004-05-03 13:52:47 +00:00
|
|
|
goto consumed;
|
2003-11-14 21:02:22 +00:00
|
|
|
}
|
|
|
|
/* Continue if it was tee */
|
|
|
|
goto passout;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
if (ipfw == 0 && args.next_hop != NULL) {
|
|
|
|
dest = args.next_hop->sin_addr.s_addr;
|
|
|
|
goto passout;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Let through or not?
|
|
|
|
*/
|
|
|
|
if (ipfw != 0)
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
passout:
|
|
|
|
ip = mtod(m, struct ip *);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Destination address changed?
|
|
|
|
*/
|
|
|
|
if (odest != dest) {
|
|
|
|
/*
|
|
|
|
* Is it now for a local address on this host?
|
|
|
|
*/
|
|
|
|
LIST_FOREACH(ia, INADDR_HASH(ip->ip_dst.s_addr), ia_hash) {
|
|
|
|
if (IA_SIN(ia)->sin_addr.s_addr == ip->ip_dst.s_addr) {
|
|
|
|
forwardlocal:
|
|
|
|
if (args.next_hop) {
|
2004-02-25 19:55:29 +00:00
|
|
|
struct m_tag *mtag = m_tag_get(
|
|
|
|
PACKET_TAG_IPFORWARD,
|
|
|
|
sizeof(struct sockaddr_in *),
|
|
|
|
M_NOWAIT);
|
|
|
|
if (mtag == NULL) {
|
2003-11-14 21:02:22 +00:00
|
|
|
goto drop;
|
|
|
|
}
|
2004-02-25 19:55:29 +00:00
|
|
|
*(struct sockaddr_in **)(mtag+1) =
|
|
|
|
args.next_hop;
|
|
|
|
m_tag_prepend(m, mtag);
|
2003-11-14 21:02:22 +00:00
|
|
|
}
|
|
|
|
#ifdef IPDIVERT
|
|
|
|
droptoours: /* Used for DIVERT */
|
|
|
|
#endif
|
2004-02-25 19:55:29 +00:00
|
|
|
/* for ip_input */
|
|
|
|
m->m_flags |= M_FASTFWD_OURS;
|
2003-11-14 21:02:22 +00:00
|
|
|
|
|
|
|
/* ip still points to the real packet */
|
|
|
|
ip->ip_len = htons(ip->ip_len);
|
|
|
|
ip->ip_off = htons(ip->ip_off);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Return packet for processing by ip_input
|
|
|
|
*/
|
|
|
|
if (ro.ro_rt)
|
|
|
|
RTFREE(ro.ro_rt);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Redo route lookup with new destination address
|
|
|
|
*/
|
|
|
|
RTFREE(ro.ro_rt);
|
2004-05-03 13:52:47 +00:00
|
|
|
if ((dst = ip_findroute(&ro, dest, m)) == NULL)
|
|
|
|
return 1; /* icmp unreach already sent */
|
|
|
|
ifp = ro.ro_rt->rt_ifp;
|
2003-11-14 21:02:22 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Step 6: send off the packet
|
|
|
|
*/
|
|
|
|
|
2004-05-03 13:52:47 +00:00
|
|
|
/*
|
|
|
|
* Check if route is dampned (when ARP is unable to resolve)
|
|
|
|
*/
|
|
|
|
if ((ro.ro_rt->rt_flags & RTF_REJECT) &&
|
|
|
|
ro.ro_rt->rt_rmx.rmx_expire >= time_second) {
|
|
|
|
icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_HOST, 0, NULL);
|
|
|
|
goto consumed;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check if there is enough space in the interface queue
|
|
|
|
*/
|
|
|
|
if ((ifp->if_snd.ifq_len + ip->ip_len / ifp->if_mtu + 1) >=
|
|
|
|
ifp->if_snd.ifq_maxlen) {
|
|
|
|
ipstat.ips_odropped++;
|
|
|
|
/* would send source quench here but that is depreciated */
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check if media link state of interface is not down
|
|
|
|
*/
|
|
|
|
if (ifp->if_link_state == LINK_STATE_DOWN) {
|
|
|
|
icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_HOST, 0, NULL);
|
|
|
|
goto consumed;
|
|
|
|
}
|
|
|
|
|
2003-11-14 21:02:22 +00:00
|
|
|
/*
|
|
|
|
* Check if packet fits MTU or if hardware will fragement for us
|
|
|
|
*/
|
|
|
|
if (ro.ro_rt->rt_rmx.rmx_mtu)
|
|
|
|
mtu = min(ro.ro_rt->rt_rmx.rmx_mtu, ifp->if_mtu);
|
|
|
|
else
|
|
|
|
mtu = ifp->if_mtu;
|
|
|
|
|
|
|
|
if (ip->ip_len <= mtu ||
|
|
|
|
(ifp->if_hwassist & CSUM_FRAGMENT && (ip->ip_off & IP_DF) == 0)) {
|
|
|
|
/*
|
|
|
|
* Restore packet header fields to original values
|
|
|
|
*/
|
|
|
|
ip->ip_len = htons(ip->ip_len);
|
|
|
|
ip->ip_off = htons(ip->ip_off);
|
|
|
|
/*
|
|
|
|
* Send off the packet via outgoing interface
|
|
|
|
*/
|
|
|
|
error = (*ifp->if_output)(ifp, m,
|
|
|
|
(struct sockaddr *)dst, ro.ro_rt);
|
|
|
|
} else {
|
|
|
|
/*
|
2004-05-03 13:52:47 +00:00
|
|
|
* Handle EMSGSIZE with icmp reply needfrag for TCP MTU discovery
|
2003-11-14 21:02:22 +00:00
|
|
|
*/
|
|
|
|
if (ip->ip_off & IP_DF) {
|
2004-05-03 13:52:47 +00:00
|
|
|
ipstat.ips_cantfrag++;
|
2003-11-14 21:02:22 +00:00
|
|
|
icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_NEEDFRAG,
|
2003-12-23 02:36:43 +00:00
|
|
|
0, ifp);
|
2004-05-03 13:52:47 +00:00
|
|
|
goto consumed;
|
2003-11-14 21:02:22 +00:00
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* We have to fragement the packet
|
|
|
|
*/
|
|
|
|
m->m_pkthdr.csum_flags |= CSUM_IP;
|
2004-05-03 13:52:47 +00:00
|
|
|
/*
|
|
|
|
* ip_fragment expects ip_len and ip_off in host byte
|
|
|
|
* order but returns all packets in network byte order
|
|
|
|
*/
|
2003-11-14 21:02:22 +00:00
|
|
|
if (ip_fragment(ip, &m, mtu, ifp->if_hwassist,
|
|
|
|
(~ifp->if_hwassist & CSUM_DELAY_IP))) {
|
|
|
|
goto drop;
|
|
|
|
}
|
|
|
|
KASSERT(m != NULL, ("null mbuf and no error"));
|
|
|
|
/*
|
|
|
|
* Send off the fragments via outgoing interface
|
|
|
|
*/
|
|
|
|
error = 0;
|
|
|
|
do {
|
|
|
|
m0 = m->m_nextpkt;
|
|
|
|
m->m_nextpkt = NULL;
|
|
|
|
|
|
|
|
error = (*ifp->if_output)(ifp, m,
|
|
|
|
(struct sockaddr *)dst, ro.ro_rt);
|
|
|
|
if (error)
|
|
|
|
break;
|
|
|
|
} while ((m = m0) != NULL);
|
|
|
|
if (error) {
|
|
|
|
/* Reclaim remaining fragments */
|
|
|
|
for (; m; m = m0) {
|
|
|
|
m0 = m->m_nextpkt;
|
|
|
|
m->m_nextpkt = NULL;
|
|
|
|
m_freem(m);
|
|
|
|
}
|
|
|
|
} else
|
|
|
|
ipstat.ips_fragmented++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (error != 0)
|
|
|
|
ipstat.ips_odropped++;
|
|
|
|
else {
|
|
|
|
ro.ro_rt->rt_rmx.rmx_pksent++;
|
|
|
|
ipstat.ips_forward++;
|
|
|
|
ipstat.ips_fastforward++;
|
|
|
|
}
|
2004-05-03 13:52:47 +00:00
|
|
|
consumed:
|
2003-11-14 21:02:22 +00:00
|
|
|
RTFREE(ro.ro_rt);
|
|
|
|
return 1;
|
|
|
|
drop:
|
|
|
|
if (m)
|
|
|
|
m_freem(m);
|
2004-05-03 13:52:47 +00:00
|
|
|
if (ro.ro_rt)
|
|
|
|
RTFREE(ro.ro_rt);
|
2003-11-14 21:02:22 +00:00
|
|
|
return 1;
|
|
|
|
}
|