freebsd-nq/sys/netinet/raw_ip.c
Garrett Wollman f0068c4a70 Initial get-the-easy-case-working upgrade of the multicast code
to something more recent than the ancient 1.2 release contained in
4.4.  This code has the following advantages as compared to
previous versions (culled from the README file for the SunOS release):

- True multicast delivery
- Configurable rate-limiting of forwarded multicast traffic on each
  physical interface or tunnel, using a token-bucket limiter.
- Simplistic classification of packets for prioritized dropping.
- Administrative scoping of multicast address ranges.
- Faster detection of hosts leaving groups.
- Support for multicast traceroute (code not yet available).
- Support for RSVP, the Resource Reservation Protocol.

What still needs to be done:

- The multicast forwarder needs testing.
- The multicast routing daemon needs to be ported.
- Network interface drivers need to have the `#ifdef MULTICAST' goop ripped
  out of them.
- The IGMP code should probably be bogon-tested.

Some notes about the porting process:

In some cases, the Berkeley people decided to incorporate functionality from
later releases of the multicast code, but then had to do things differently.
As a result, if you look at Deering's patches, and then look at
our code, it is not always obvious whether the patch even applies.  Let
the reader beware.

I ran ip_mroute.c through several passes of `unifdef' to get rid of
useless grot, and to permanently enable the RSVP support, which we will
include as standard.

Ported by: 	Garrett Wollman
Submitted by:	Steve Deering and Ajit Thyagarajan (among others)
1994-09-06 22:42:31 +00:00

394 lines
8.8 KiB
C

/*
* 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.
*
* @(#)raw_ip.c 8.2 (Berkeley) 1/4/94
* $Id: raw_ip.c,v 1.2 1994/08/02 07:48:49 davidg Exp $
*/
#include <sys/param.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/protosw.h>
#include <sys/socketvar.h>
#include <sys/errno.h>
#include <sys/systm.h>
#include <net/if.h>
#include <net/route.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/ip_mroute.h>
#include <netinet/in_pcb.h>
struct inpcb rawinpcb;
/*
* Nominal space allocated to a raw ip socket.
*/
#define RIPSNDQ 8192
#define RIPRCVQ 8192
/*
* Raw interface to IP protocol.
*/
/*
* Initialize raw connection block q.
*/
void
rip_init()
{
rawinpcb.inp_next = rawinpcb.inp_prev = &rawinpcb;
}
struct sockaddr_in ripsrc = { sizeof(ripsrc), AF_INET };
/*
* Setup generic address and protocol structures
* for raw_input routine, then pass them along with
* mbuf chain.
*/
void
rip_input(m)
struct mbuf *m;
{
register struct ip *ip = mtod(m, struct ip *);
register struct inpcb *inp;
struct socket *last = 0;
ripsrc.sin_addr = ip->ip_src;
for (inp = rawinpcb.inp_next; inp != &rawinpcb; inp = inp->inp_next) {
if (inp->inp_ip.ip_p && inp->inp_ip.ip_p != ip->ip_p)
continue;
if (inp->inp_laddr.s_addr &&
inp->inp_laddr.s_addr == ip->ip_dst.s_addr)
continue;
if (inp->inp_faddr.s_addr &&
inp->inp_faddr.s_addr == ip->ip_src.s_addr)
continue;
if (last) {
struct mbuf *n;
if (n = m_copy(m, 0, (int)M_COPYALL)) {
if (sbappendaddr(&last->so_rcv, &ripsrc,
n, (struct mbuf *)0) == 0)
/* should notify about lost packet */
m_freem(n);
else
sorwakeup(last);
}
}
last = inp->inp_socket;
}
if (last) {
if (sbappendaddr(&last->so_rcv, &ripsrc,
m, (struct mbuf *)0) == 0)
m_freem(m);
else
sorwakeup(last);
} else {
m_freem(m);
ipstat.ips_noproto++;
ipstat.ips_delivered--;
}
}
/*
* Generate IP header and pass packet to ip_output.
* Tack on options user may have setup with control call.
*/
int
rip_output(m, so, dst)
register struct mbuf *m;
struct socket *so;
u_long dst;
{
register struct ip *ip;
register struct inpcb *inp = sotoinpcb(so);
struct mbuf *opts;
int flags = (so->so_options & SO_DONTROUTE) | IP_ALLOWBROADCAST;
/*
* If the user handed us a complete IP packet, use it.
* Otherwise, allocate an mbuf for a header and fill it in.
*/
if ((inp->inp_flags & INP_HDRINCL) == 0) {
M_PREPEND(m, sizeof(struct ip), M_WAIT);
ip = mtod(m, struct ip *);
ip->ip_tos = 0;
ip->ip_off = 0;
ip->ip_p = inp->inp_ip.ip_p;
ip->ip_len = m->m_pkthdr.len;
ip->ip_src = inp->inp_laddr;
ip->ip_dst.s_addr = dst;
ip->ip_ttl = MAXTTL;
opts = inp->inp_options;
} else {
ip = mtod(m, struct ip *);
if (ip->ip_id == 0)
ip->ip_id = htons(ip_id++);
opts = NULL;
/* XXX prevent ip_output from overwriting header fields */
flags |= IP_RAWOUTPUT;
ipstat.ips_rawout++;
}
return (ip_output(m, opts, &inp->inp_route, flags, inp->inp_moptions));
}
/*
* Raw IP socket option processing.
*/
int
rip_ctloutput(op, so, level, optname, m)
int op;
struct socket *so;
int level, optname;
struct mbuf **m;
{
register struct inpcb *inp = sotoinpcb(so);
register int error;
if (level != IPPROTO_IP)
return (EINVAL);
switch (optname) {
case IP_HDRINCL:
if (op == PRCO_SETOPT || op == PRCO_GETOPT) {
if (m == 0 || *m == 0 || (*m)->m_len < sizeof (int))
return (EINVAL);
if (op == PRCO_SETOPT) {
if (*mtod(*m, int *))
inp->inp_flags |= INP_HDRINCL;
else
inp->inp_flags &= ~INP_HDRINCL;
(void)m_free(*m);
} else {
(*m)->m_len = sizeof (int);
*mtod(*m, int *) = inp->inp_flags & INP_HDRINCL;
}
return (0);
}
break;
case IP_RSVP_ON:
error = ip_rsvp_init(so);
break;
case IP_RSVP_OFF:
error = ip_rsvp_done();
break;
case DVMRP_INIT:
case DVMRP_DONE:
case DVMRP_ADD_VIF:
case DVMRP_DEL_VIF:
case DVMRP_ADD_MFC:
case DVMRP_DEL_MFC:
#ifdef MROUTING
if (op == PRCO_SETOPT) {
error = ip_mrouter_cmd(optname, so, *m);
if (*m)
(void)m_free(*m);
} else
error = EINVAL;
return (error);
#else
if (op == PRCO_SETOPT && *m)
(void)m_free(*m);
return (EOPNOTSUPP);
#endif
}
return (ip_ctloutput(op, so, level, optname, m));
}
u_long rip_sendspace = RIPSNDQ;
u_long rip_recvspace = RIPRCVQ;
/*ARGSUSED*/
int
rip_usrreq(so, req, m, nam, control)
register struct socket *so;
int req;
struct mbuf *m, *nam, *control;
{
register int error = 0;
register struct inpcb *inp = sotoinpcb(so);
switch (req) {
case PRU_ATTACH:
if (inp)
panic("rip_attach");
if ((so->so_state & SS_PRIV) == 0) {
error = EACCES;
break;
}
if ((error = soreserve(so, rip_sendspace, rip_recvspace)) ||
(error = in_pcballoc(so, &rawinpcb)))
break;
inp = (struct inpcb *)so->so_pcb;
inp->inp_ip.ip_p = (int)nam;
break;
case PRU_DISCONNECT:
if ((so->so_state & SS_ISCONNECTED) == 0) {
error = ENOTCONN;
break;
}
/* FALLTHROUGH */
case PRU_ABORT:
soisdisconnected(so);
/* FALLTHROUGH */
case PRU_DETACH:
if (inp == 0)
panic("rip_detach");
#ifdef MROUTING
if (so == ip_mrouter)
ip_mrouter_done();
#endif
in_pcbdetach(inp);
break;
case PRU_BIND:
{
struct sockaddr_in *addr = mtod(nam, struct sockaddr_in *);
if (nam->m_len != sizeof(*addr)) {
error = EINVAL;
break;
}
if ((ifnet == 0) ||
((addr->sin_family != AF_INET) &&
(addr->sin_family != AF_IMPLINK)) ||
(addr->sin_addr.s_addr &&
ifa_ifwithaddr((struct sockaddr *)addr) == 0)) {
error = EADDRNOTAVAIL;
break;
}
inp->inp_laddr = addr->sin_addr;
break;
}
case PRU_CONNECT:
{
struct sockaddr_in *addr = mtod(nam, struct sockaddr_in *);
if (nam->m_len != sizeof(*addr)) {
error = EINVAL;
break;
}
if (ifnet == 0) {
error = EADDRNOTAVAIL;
break;
}
if ((addr->sin_family != AF_INET) &&
(addr->sin_family != AF_IMPLINK)) {
error = EAFNOSUPPORT;
break;
}
inp->inp_faddr = addr->sin_addr;
soisconnected(so);
break;
}
case PRU_CONNECT2:
error = EOPNOTSUPP;
break;
/*
* Mark the connection as being incapable of further input.
*/
case PRU_SHUTDOWN:
socantsendmore(so);
break;
/*
* Ship a packet out. The appropriate raw output
* routine handles any massaging necessary.
*/
case PRU_SEND:
{
register u_long dst;
if (so->so_state & SS_ISCONNECTED) {
if (nam) {
error = EISCONN;
break;
}
dst = inp->inp_faddr.s_addr;
} else {
if (nam == NULL) {
error = ENOTCONN;
break;
}
dst = mtod(nam, struct sockaddr_in *)->sin_addr.s_addr;
}
error = rip_output(m, so, dst);
m = NULL;
break;
}
case PRU_SENSE:
/*
* stat: don't bother with a blocksize.
*/
return (0);
/*
* Not supported.
*/
case PRU_RCVOOB:
case PRU_RCVD:
case PRU_LISTEN:
case PRU_ACCEPT:
case PRU_SENDOOB:
error = EOPNOTSUPP;
break;
case PRU_SOCKADDR:
in_setsockaddr(inp, nam);
break;
case PRU_PEERADDR:
in_setpeeraddr(inp, nam);
break;
default:
panic("rip_usrreq");
}
if (m != NULL)
m_freem(m);
return (error);
}