in_pcb.c

RTEMS (Real-Time Executive for Multiprocessor Systems) is a free open source real-time operating sys

/*
 * Copyright (c) 1982, 1986, 1991, 1993, 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.
 *
 *	@(#)in_pcb.c	8.4 (Berkeley) 5/24/95
 *	$Id: in_pcb.c,v 1.3 2003/01/03 18:09:25 joel Exp $
 */

#include <sys/param.h>
#include <sys/queue.h>
#include <sys/systm.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/ioctl.h>
#include <sys/errno.h>
#include <sys/time.h>
#include <sys/proc.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>

#include <net/if.h>
#include <net/route.h>

#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/in_pcb.h>
#include <netinet/in_var.h>
#include <netinet/ip_var.h>

struct	in_addr zeroin_addr;

static void	 in_pcbinshash __P((struct inpcb *));
static void	 in_rtchange __P((struct inpcb *, int));

/*
 * These configure the range of local port addresses assigned to
 * "unspecified" outgoing connections/packets/whatever.
 */
static int ipport_lowfirstauto  = IPPORT_RESERVED - 1;	/* 1023 */
static int ipport_lowlastauto = IPPORT_RESERVEDSTART;	/* 600 */
static int ipport_firstauto = IPPORT_RESERVED;		/* 1024 */
static int ipport_lastauto  = IPPORT_USERRESERVED;	/* 5000 */
static int ipport_hifirstauto = IPPORT_HIFIRSTAUTO;	/* 40000 */
static int ipport_hilastauto  = IPPORT_HILASTAUTO;	/* 44999 */

#define RANGECHK(var, min, max) \
	if ((var) < (min)) { (var) = (min); } \
	else if ((var) > (max)) { (var) = (max); }

static int
sysctl_net_ipport_check(SYSCTL_HANDLER_ARGS)
{
	int error = sysctl_handle_int(oidp,
		oidp->oid_arg1, oidp->oid_arg2, req);
	if (!error) {
		RANGECHK(ipport_lowfirstauto, 1, IPPORT_RESERVED - 1);
		RANGECHK(ipport_lowlastauto, 1, IPPORT_RESERVED - 1);
		RANGECHK(ipport_firstauto, IPPORT_RESERVED, USHRT_MAX);
		RANGECHK(ipport_lastauto, IPPORT_RESERVED, USHRT_MAX);
		RANGECHK(ipport_hifirstauto, IPPORT_RESERVED, USHRT_MAX);
		RANGECHK(ipport_hilastauto, IPPORT_RESERVED, USHRT_MAX);
	}
	return error;
}

#undef RANGECHK

SYSCTL_NODE(_net_inet_ip, IPPROTO_IP, portrange, CTLFLAG_RW, 0, "IP Ports");

SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, lowfirst, CTLTYPE_INT|CTLFLAG_RW,
	   &ipport_lowfirstauto, 0, &sysctl_net_ipport_check, "I", "");
SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, lowlast, CTLTYPE_INT|CTLFLAG_RW,
	   &ipport_lowlastauto, 0, &sysctl_net_ipport_check, "I", "");
SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, first, CTLTYPE_INT|CTLFLAG_RW,
	   &ipport_firstauto, 0, &sysctl_net_ipport_check, "I", "");
SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, last, CTLTYPE_INT|CTLFLAG_RW,
	   &ipport_lastauto, 0, &sysctl_net_ipport_check, "I", "");
SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, hifirst, CTLTYPE_INT|CTLFLAG_RW,
	   &ipport_hifirstauto, 0, &sysctl_net_ipport_check, "I", "");
SYSCTL_PROC(_net_inet_ip_portrange, OID_AUTO, hilast, CTLTYPE_INT|CTLFLAG_RW,
	   &ipport_hilastauto, 0, &sysctl_net_ipport_check, "I", "");

int
in_pcballoc(so, pcbinfo)
	struct socket *so;
	struct inpcbinfo *pcbinfo;
{
	register struct inpcb *inp;
	int s;

	MALLOC(inp, struct inpcb *, sizeof(*inp), M_PCB, M_NOWAIT);
	if (inp == NULL)
		return (ENOBUFS);
	bzero((caddr_t)inp, sizeof(*inp));
	inp->inp_gencnt = ++pcbinfo->ipi_gencnt;
	inp->inp_pcbinfo = pcbinfo;
	inp->inp_socket = so;
	s = splnet();
	LIST_INSERT_HEAD(pcbinfo->listhead, inp, inp_list);
	pcbinfo->ipi_count++;
	in_pcbinshash(inp);
	splx(s);
	so->so_pcb = (caddr_t)inp;
	return (0);
}

int
in_pcbbind(inp, nam)
	register struct inpcb *inp;
	struct mbuf *nam;
{
	register struct socket *so = inp->inp_socket;
	unsigned short *lastport;
	struct sockaddr_in *sin;
	u_short lport = 0;
	int wild = 0, reuseport = (so->so_options & SO_REUSEPORT);
	int error;

	if (in_ifaddr == 0)
		return (EADDRNOTAVAIL);
	if (inp->inp_lport || inp->inp_laddr.s_addr != INADDR_ANY)
		return (EINVAL);
	if ((so->so_options & (SO_REUSEADDR|SO_REUSEPORT)) == 0 &&
	    ((so->so_proto->pr_flags & PR_CONNREQUIRED) == 0 ||
	     (so->so_options & SO_ACCEPTCONN) == 0))
		wild = 1;
	if (nam) {
		sin = mtod(nam, struct sockaddr_in *);
		if (nam->m_len != sizeof (*sin))
			return (EINVAL);
#ifdef notdef
		/*
		 * We should check the family, but old programs
		 * incorrectly fail to initialize it.
		 */
		if (sin->sin_family != AF_INET)
			return (EAFNOSUPPORT);
#endif
		lport = sin->sin_port;
		if (IN_MULTICAST(ntohl(sin->sin_addr.s_addr))) {
			/*
			 * Treat SO_REUSEADDR as SO_REUSEPORT for multicast;
			 * allow complete duplication of binding if
			 * SO_REUSEPORT is set, or if SO_REUSEADDR is set
			 * and a multicast address is bound on both
			 * new and duplicated sockets.
			 */
			if (so->so_options & SO_REUSEADDR)
				reuseport = SO_REUSEADDR|SO_REUSEPORT;
		} else if (sin->sin_addr.s_addr != INADDR_ANY) {
			sin->sin_port = 0;		/* yech... */
			if (ifa_ifwithaddr((struct sockaddr *)sin) == 0)
				return (EADDRNOTAVAIL);
		}
		if (lport) {
			struct inpcb *t;

			/* GROSS */
			if (ntohs(lport) < IPPORT_RESERVED &&
			    (error = suser(p->p_ucred, &p->p_acflag)))
				return (EACCES);
			if (so->so_uid) {
				t = in_pcblookup(inp->inp_pcbinfo, zeroin_addr,
				    0, sin->sin_addr, lport,
				    INPLOOKUP_WILDCARD);
				if (t && (so->so_uid != t->inp_socket->so_uid))
					return (EADDRINUSE);
			}
			t = in_pcblookup(inp->inp_pcbinfo, zeroin_addr, 0,
			    sin->sin_addr, lport, wild);
			if (t && (reuseport & t->inp_socket->so_options) == 0)
				return (EADDRINUSE);
		}
		inp->inp_laddr = sin->sin_addr;
	}
	if (lport == 0) {
		ushort first, last;
		int count;

		inp->inp_flags |= INP_ANONPORT;

		if (inp->inp_flags & INP_HIGHPORT) {
			first = ipport_hifirstauto;	/* sysctl */
			last  = ipport_hilastauto;
			lastport = &inp->inp_pcbinfo->lasthi;
		} else if (inp->inp_flags & INP_LOWPORT) {
			if ((error = suser(p->p_ucred, &p->p_acflag)))
				return (EACCES);
			first = ipport_lowfirstauto;	/* 1023 */
			last  = ipport_lowlastauto;	/* 600 */
			lastport = &inp->inp_pcbinfo->lastlow;
		} else {
			first = ipport_firstauto;	/* sysctl */
			last  = ipport_lastauto;
			lastport = &inp->inp_pcbinfo->lastport;
		}
		/*
		 * Simple check to ensure all ports are not used up causing
		 * a deadlock here.
		 *
		 * We split the two cases (up and down) so that the direction
		 * is not being tested on each round of the loop.
		 */
		if (first > last) {
			/*
			 * counting down
			 */
			count = first - last;

			do {
				if (count-- <= 0)	/* completely used? */
					return (EADDRNOTAVAIL);
				--*lastport;
				if (*lastport > first || *lastport < last)
					*lastport = first;
				lport = htons(*lastport);
			} while (in_pcblookup(inp->inp_pcbinfo,
				 zeroin_addr, 0, inp->inp_laddr, lport, wild));
		} else {
			/*
			 * counting up
			 */
			count = last - first;

			do {
				if (count-- <= 0)	/* completely used? */
					return (EADDRNOTAVAIL);
				++*lastport;
				if (*lastport < first || *lastport > last)
					*lastport = first;
				lport = htons(*lastport);
			} while (in_pcblookup(inp->inp_pcbinfo,
				 zeroin_addr, 0, inp->inp_laddr, lport, wild));
		}
	}
	inp->inp_lport = lport;
	in_pcbrehash(inp);
	return (0);
}

/*
 *   Transform old in_pcbconnect() into an inner subroutine for new
 *   in_pcbconnect(): Do some validity-checking on the remote
 *   address (in mbuf 'nam') and then determine local host address
 *   (i.e., which interface) to use to access that remote host.
 *
 *   This preserves definition of in_pcbconnect(), while supporting a
 *   slightly different version for T/TCP.  (This is more than
 *   a bit of a kludge, but cleaning up the internal interfaces would
 *   have forced minor changes in every protocol).
 */

int
in_pcbladdr(inp, nam, plocal_sin)
	register struct inpcb *inp;
	struct mbuf *nam;
	struct sockaddr_in **plocal_sin;
{
	struct in_ifaddr *ia;
	register struct sockaddr_in *sin = mtod(nam, struct sockaddr_in *);

	if (nam->m_len != sizeof (*sin))
		return (EINVAL);
	if (sin->sin_family != AF_INET)
		return (EAFNOSUPPORT);
	if (sin->sin_port == 0)
		return (EADDRNOTAVAIL);
	if (in_ifaddr) {
		/*
		 * If the destination address is INADDR_ANY,
		 * use the primary local address.
		 * If the supplied address is INADDR_BROADCAST,
		 * and the primary interface supports broadcast,
		 * choose the broadcast address for that interface.
		 */
#define	satosin(sa)	((struct sockaddr_in *)(sa))
#define sintosa(sin)	((struct sockaddr *)(sin))
#define ifatoia(ifa)	((struct in_ifaddr *)(ifa))
		if (sin->sin_addr.s_addr == INADDR_ANY)
		    sin->sin_addr = IA_SIN(in_ifaddr)->sin_addr;
		else if (sin->sin_addr.s_addr == (u_long)INADDR_BROADCAST &&
		  (in_ifaddr->ia_ifp->if_flags & IFF_BROADCAST))
		    sin->sin_addr = satosin(&in_ifaddr->ia_broadaddr)->sin_addr;
	}
	if (inp->inp_laddr.s_addr == INADDR_ANY) {
		register struct route *ro;

		ia = (struct in_ifaddr *)0;
		/*
		 * If route is known or can be allocated now,
		 * our src addr is taken from the i/f, else punt.
		 */
		ro = &inp->inp_route;
		if (ro->ro_rt &&
		    (satosin(&ro->ro_dst)->sin_addr.s_addr !=
			sin->sin_addr.s_addr ||
		    inp->inp_socket->so_options & SO_DONTROUTE)) {
			RTFREE(ro->ro_rt);
			ro->ro_rt = (struct rtentry *)0;
		}
		if ((inp->inp_socket->so_options & SO_DONTROUTE) == 0 && /*XXX*/
		    (ro->ro_rt == (struct rtentry *)0 ||
		    ro->ro_rt->rt_ifp == (struct ifnet *)0)) {
			/* No route yet, so try to acquire one */
			ro->ro_dst.sa_family = AF_INET;
			ro->ro_dst.sa_len = sizeof(struct sockaddr_in);
			((struct sockaddr_in *) &ro->ro_dst)->sin_addr =
				sin->sin_addr;
			rtalloc(ro);
		}
		/*
		 * If we found a route, use the address
		 * corresponding to the outgoing interface
		 * unless it is the loopback (in case a route
		 * to our address on another net goes to loopback).
		 */
		if (ro->ro_rt && !(ro->ro_rt->rt_ifp->if_flags & IFF_LOOPBACK))
			ia = ifatoia(ro->ro_rt->rt_ifa);
		if (ia == 0) {
			u_short fport = sin->sin_port;

			sin->sin_port = 0;
			ia = ifatoia(ifa_ifwithdstaddr(sintosa(sin)));
			if (ia == 0)
				ia = ifatoia(ifa_ifwithnet(sintosa(sin)));
			sin->sin_port = fport;
			if (ia == 0)
				ia = in_ifaddr;
			if (ia == 0)
				return (EADDRNOTAVAIL);
		}
		/*
		 * If the destination address is multicast and an outgoing
		 * interface has been set as a multicast option, use the
		 * address of that interface as our source address.
		 */
		if (IN_MULTICAST(ntohl(sin->sin_addr.s_addr)) &&
		    inp->inp_moptions != NULL) {
			struct ip_moptions *imo;
			struct ifnet *ifp;

			imo = inp->inp_moptions;
			if (imo->imo_multicast_ifp != NULL) {
				ifp = imo->imo_multicast_ifp;
				for (ia = in_ifaddr; ia; ia = ia->ia_next)
					if (ia->ia_ifp == ifp)
						break;
				if (ia == 0)
					return (EADDRNOTAVAIL);