/* * 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. * 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 8.7 (Berkeley) 5/15/95 * $FreeBSD$ */ #include "opt_inet6.h" #include "opt_ipsec.h" #include "opt_mac.h" #include "opt_random_ip_id.h" #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #ifdef FAST_IPSEC #include #endif /*FAST_IPSEC*/ #ifdef IPSEC #include #endif /*IPSEC*/ struct inpcbhead ripcb; struct inpcbinfo ripcbinfo; /* control hooks for ipfw and dummynet */ ip_fw_ctl_t *ip_fw_ctl_ptr; ip_dn_ctl_t *ip_dn_ctl_ptr; /* * hooks for multicast routing. They all default to NULL, * so leave them not initialized and rely on BSS being set to 0. */ /* The socket used to communicate with the multicast routing daemon. */ struct socket *ip_mrouter; /* The various mrouter and rsvp functions */ int (*ip_mrouter_set)(struct socket *, struct sockopt *); int (*ip_mrouter_get)(struct socket *, struct sockopt *); int (*ip_mrouter_done)(void); int (*ip_mforward)(struct ip *, struct ifnet *, struct mbuf *, struct ip_moptions *); int (*mrt_ioctl)(int, caddr_t); int (*legal_vif_num)(int); u_long (*ip_mcast_src)(int); void (*rsvp_input_p)(struct mbuf *m, int off); int (*ip_rsvp_vif)(struct socket *, struct sockopt *); void (*ip_rsvp_force_done)(struct socket *); /* * 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() { INP_INFO_LOCK_INIT(&ripcbinfo, "rip"); LIST_INIT(&ripcb); ripcbinfo.listhead = &ripcb; /* * XXX We don't use the hash list for raw IP, but it's easier * to allocate a one entry hash list than it is to check all * over the place for hashbase == NULL. */ ripcbinfo.hashbase = hashinit(1, M_PCB, &ripcbinfo.hashmask); ripcbinfo.porthashbase = hashinit(1, M_PCB, &ripcbinfo.porthashmask); ripcbinfo.ipi_zone = uma_zcreate("ripcb", sizeof(struct inpcb), NULL, NULL, NULL, NULL, UMA_ALIGN_PTR, UMA_ZONE_NOFREE); uma_zone_set_max(ripcbinfo.ipi_zone, maxsockets); } static struct sockaddr_in ripsrc = { sizeof(ripsrc), AF_INET }; static int raw_append(struct inpcb *last, struct ip *ip, struct mbuf *n) { int policyfail = 0; #if defined(IPSEC) || defined(FAST_IPSEC) /* check AH/ESP integrity. */ if (ipsec4_in_reject(n, last)) { policyfail = 1; #ifdef IPSEC ipsecstat.in_polvio++; #endif /*IPSEC*/ /* do not inject data to pcb */ } #endif /*IPSEC || FAST_IPSEC*/ #ifdef MAC if (!policyfail && mac_check_inpcb_deliver(last, n) != 0) policyfail = 1; #endif if (!policyfail) { struct mbuf *opts = NULL; if ((last->inp_flags & INP_CONTROLOPTS) || (last->inp_socket->so_options & SO_TIMESTAMP)) ip_savecontrol(last, &opts, ip, n); if (sbappendaddr(&last->inp_socket->so_rcv, (struct sockaddr *)&ripsrc, n, opts) == 0) { /* should notify about lost packet */ m_freem(n); if (opts) m_freem(opts); } else sorwakeup(last->inp_socket); } else m_freem(n); return policyfail; } /* * Setup generic address and protocol structures * for raw_input routine, then pass them along with * mbuf chain. */ void rip_input(struct mbuf *m, int off) { struct ip *ip = mtod(m, struct ip *); int proto = ip->ip_p; struct inpcb *inp, *last; INP_INFO_RLOCK(&ripcbinfo); ripsrc.sin_addr = ip->ip_src; last = NULL; LIST_FOREACH(inp, &ripcb, inp_list) { INP_LOCK(inp); if (inp->inp_ip_p && inp->inp_ip_p != proto) { docontinue: INP_UNLOCK(inp); continue; } #ifdef INET6 if ((inp->inp_vflag & INP_IPV4) == 0) goto docontinue; #endif if (inp->inp_laddr.s_addr && inp->inp_laddr.s_addr != ip->ip_dst.s_addr) goto docontinue; if (inp->inp_faddr.s_addr && inp->inp_faddr.s_addr != ip->ip_src.s_addr) goto docontinue; if (last) { struct mbuf *n; n = m_copy(m, 0, (int)M_COPYALL); if (n != NULL) (void) raw_append(last, ip, n); /* XXX count dropped packet */ INP_UNLOCK(last); } last = inp; } if (last != NULL) { if (raw_append(last, ip, m) != 0) ipstat.ips_delivered--; INP_UNLOCK(last); } else { m_freem(m); ipstat.ips_noproto++; ipstat.ips_delivered--; } INP_INFO_RUNLOCK(&ripcbinfo); } /* * Generate IP header and pass packet to ip_output. * Tack on options user may have setup with control call. */ int rip_output(struct mbuf *m, struct socket *so, u_long dst) { struct ip *ip; struct inpcb *inp = sotoinpcb(so); int flags = (so->so_options & SO_DONTROUTE) | IP_ALLOWBROADCAST; #ifdef MAC mac_create_mbuf_from_socket(so, m); #endif /* * 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) { if (m->m_pkthdr.len + sizeof(struct ip) > IP_MAXPACKET) { m_freem(m); return(EMSGSIZE); } M_PREPEND(m, sizeof(struct ip), M_TRYWAIT); if (m == NULL) return(ENOBUFS); ip = mtod(m, struct ip *); ip->ip_tos = inp->inp_ip_tos; ip->ip_off = 0; ip->ip_p = inp->inp_ip_p; ip->ip_len = m->m_pkthdr.len; ip->ip_src = inp->inp_laddr; ip->ip_dst.s_addr = dst; ip->ip_ttl = inp->inp_ip_ttl; } else { if (m->m_pkthdr.len > IP_MAXPACKET) { m_freem(m); return(EMSGSIZE); } ip = mtod(m, struct ip *); /* don't allow both user specified and setsockopt options, and don't allow packet length sizes that will crash */ if (((ip->ip_hl != (sizeof (*ip) >> 2)) && inp->inp_options) || (ip->ip_len > m->m_pkthdr.len) || (ip->ip_len < (ip->ip_hl << 2))) { m_freem(m); return EINVAL; } if (ip->ip_id == 0) #ifdef RANDOM_IP_ID ip->ip_id = ip_randomid(); #else ip->ip_id = htons(ip_id++); #endif /* XXX prevent ip_output from overwriting header fields */ flags |= IP_RAWOUTPUT; ipstat.ips_rawout++; } if (inp->inp_flags & INP_ONESBCAST) flags |= IP_SENDONES; return (ip_output(m, inp->inp_options, NULL, flags, inp->inp_moptions, inp)); } /* * Raw IP socket option processing. * * Note that access to all of the IP administrative functions here is * implicitly protected by suser() as gaining access to a raw socket * requires either that the thread pass a suser() check, or that it be * passed a raw socket by another thread that has passed a suser() check. * If FreeBSD moves to a more fine-grained access control mechanism, * additional checks will need to be placed here if the raw IP attachment * check is not equivilent the the check required for these * administrative operations; in some cases, these checks are already * present. */ int rip_ctloutput(struct socket *so, struct sockopt *sopt) { struct inpcb *inp = sotoinpcb(so); int error, optval; if (sopt->sopt_level != IPPROTO_IP) return (EINVAL); error = 0; switch (sopt->sopt_dir) { case SOPT_GET: switch (sopt->sopt_name) { case IP_HDRINCL: optval = inp->inp_flags & INP_HDRINCL; error = sooptcopyout(sopt, &optval, sizeof optval); break; case IP_FW_ADD: /* ADD actually returns the body... */ case IP_FW_GET: if (IPFW_LOADED) error = ip_fw_ctl_ptr(sopt); else error = ENOPROTOOPT; break; case IP_DUMMYNET_GET: if (DUMMYNET_LOADED) error = ip_dn_ctl_ptr(sopt); else error = ENOPROTOOPT; break ; case MRT_INIT: case MRT_DONE: case MRT_ADD_VIF: case MRT_DEL_VIF: case MRT_ADD_MFC: case MRT_DEL_MFC: case MRT_VERSION: case MRT_ASSERT: case MRT_API_SUPPORT: case MRT_API_CONFIG: case MRT_ADD_BW_UPCALL: case MRT_DEL_BW_UPCALL: error = ip_mrouter_get ? ip_mrouter_get(so, sopt) : EOPNOTSUPP; break; default: error = ip_ctloutput(so, sopt); break; } break; case SOPT_SET: switch (sopt->sopt_name) { case IP_HDRINCL: error = sooptcopyin(sopt, &optval, sizeof optval, sizeof optval); if (error) break; if (optval) inp->inp_flags |= INP_HDRINCL; else inp->inp_flags &= ~INP_HDRINCL; break; case IP_FW_ADD: case IP_FW_DEL: case IP_FW_FLUSH: case IP_FW_ZERO: case IP_FW_RESETLOG: if (IPFW_LOADED) error = ip_fw_ctl_ptr(sopt); else error = ENOPROTOOPT; break; case IP_DUMMYNET_CONFIGURE: case IP_DUMMYNET_DEL: case IP_DUMMYNET_FLUSH: if (DUMMYNET_LOADED) error = ip_dn_ctl_ptr(sopt); else error = ENOPROTOOPT ; break ; case IP_RSVP_ON: error = ip_rsvp_init(so); break; case IP_RSVP_OFF: error = ip_rsvp_done(); break; case IP_RSVP_VIF_ON: case IP_RSVP_VIF_OFF: error = ip_rsvp_vif ? ip_rsvp_vif(so, sopt) : EINVAL; break; case MRT_INIT: case MRT_DONE: case MRT_ADD_VIF: case MRT_DEL_VIF: case MRT_ADD_MFC: case MRT_DEL_MFC: case MRT_VERSION: case MRT_ASSERT: case MRT_API_SUPPORT: case MRT_API_CONFIG: case MRT_ADD_BW_UPCALL: case MRT_DEL_BW_UPCALL: error = ip_mrouter_set ? ip_mrouter_set(so, sopt) : EOPNOTSUPP; break; default: error = ip_ctloutput(so, sopt); break; } break; } return (error); } /* * This function exists solely to receive the PRC_IFDOWN messages which * are sent by if_down(). It looks for an ifaddr whose ifa_addr is sa, * and calls in_ifadown() to remove all routes corresponding to that address. * It also receives the PRC_IFUP messages from if_up() and reinstalls the * interface routes. */ void rip_ctlinput(int cmd, struct sockaddr *sa, void *vip) { struct in_ifaddr *ia; struct ifnet *ifp; int err; int flags; switch (cmd) { case PRC_IFDOWN: TAILQ_FOREACH(ia, &in_ifaddrhead, ia_link) { if (ia->ia_ifa.ifa_addr == sa && (ia->ia_flags & IFA_ROUTE)) { /* * in_ifscrub kills the interface route. */ in_ifscrub(ia->ia_ifp, ia); /* * in_ifadown gets rid of all the rest of * the routes. This is not quite the right * thing to do, but at least if we are running * a routing process they will come back. */ in_ifadown(&ia->ia_ifa, 0); break; } } break; case PRC_IFUP: TAILQ_FOREACH(ia, &in_ifaddrhead, ia_link) { if (ia->ia_ifa.ifa_addr == sa) break; } if (ia == 0 || (ia->ia_flags & IFA_ROUTE)) return; flags = RTF_UP; ifp = ia->ia_ifa.ifa_ifp; if ((ifp->if_flags & IFF_LOOPBACK) || (ifp->if_flags & IFF_POINTOPOINT)) flags |= RTF_HOST; err = rtinit(&ia->ia_ifa, RTM_ADD, flags); if (err == 0) ia->ia_flags |= IFA_ROUTE; break; } } u_long rip_sendspace = RIPSNDQ; u_long rip_recvspace = RIPRCVQ; SYSCTL_INT(_net_inet_raw, OID_AUTO, maxdgram, CTLFLAG_RW, &rip_sendspace, 0, "Maximum outgoing raw IP datagram size"); SYSCTL_INT(_net_inet_raw, OID_AUTO, recvspace, CTLFLAG_RW, &rip_recvspace, 0, "Maximum space for incoming raw IP datagrams"); static int rip_attach(struct socket *so, int proto, struct thread *td) { struct inpcb *inp; int error; /* XXX why not lower? */ INP_INFO_WLOCK(&ripcbinfo); inp = sotoinpcb(so); if (inp) { /* XXX counter, printf */ INP_INFO_WUNLOCK(&ripcbinfo); return EINVAL; } if (td && (error = suser(td)) != 0) { INP_INFO_WUNLOCK(&ripcbinfo); return error; } if (proto >= IPPROTO_MAX || proto < 0) { INP_INFO_WUNLOCK(&ripcbinfo); return EPROTONOSUPPORT; } error = soreserve(so, rip_sendspace, rip_recvspace); if (error) { INP_INFO_WUNLOCK(&ripcbinfo); return error; } error = in_pcballoc(so, &ripcbinfo, "rawinp"); if (error) { INP_INFO_WUNLOCK(&ripcbinfo); return error; } inp = (struct inpcb *)so->so_pcb; INP_LOCK(inp); INP_INFO_WUNLOCK(&ripcbinfo); inp->inp_vflag |= INP_IPV4; inp->inp_ip_p = proto; inp->inp_ip_ttl = ip_defttl; INP_UNLOCK(inp); return 0; } static void rip_pcbdetach(struct socket *so, struct inpcb *inp) { INP_INFO_WLOCK_ASSERT(&ripcbinfo); INP_LOCK_ASSERT(inp); if (so == ip_mrouter && ip_mrouter_done) ip_mrouter_done(); if (ip_rsvp_force_done) ip_rsvp_force_done(so); if (so == ip_rsvpd) ip_rsvp_done(); in_pcbdetach(inp); } static int rip_detach(struct socket *so) { struct inpcb *inp; INP_INFO_WLOCK(&ripcbinfo); inp = sotoinpcb(so); if (inp == 0) { /* XXX counter, printf */ INP_INFO_WUNLOCK(&ripcbinfo); return EINVAL; } INP_LOCK(inp); rip_pcbdetach(so, inp); INP_INFO_WUNLOCK(&ripcbinfo); return 0; } static int rip_abort(struct socket *so) { struct inpcb *inp; INP_INFO_WLOCK(&ripcbinfo); inp = sotoinpcb(so); if (inp == 0) { INP_INFO_WUNLOCK(&ripcbinfo); return EINVAL; /* ??? possible? panic instead? */ } INP_LOCK(inp); soisdisconnected(so); if (so->so_state & SS_NOFDREF) rip_pcbdetach(so, inp); else INP_UNLOCK(inp); INP_INFO_WUNLOCK(&ripcbinfo); return 0; } static int rip_disconnect(struct socket *so) { if ((so->so_state & SS_ISCONNECTED) == 0) return ENOTCONN; return rip_abort(so); } static int rip_bind(struct socket *so, struct sockaddr *nam, struct thread *td) { struct sockaddr_in *addr = (struct sockaddr_in *)nam; struct inpcb *inp; if (nam->sa_len != sizeof(*addr)) return EINVAL; if (TAILQ_EMPTY(&ifnet) || (addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK) || (addr->sin_addr.s_addr && ifa_ifwithaddr((struct sockaddr *)addr) == 0)) return EADDRNOTAVAIL; INP_INFO_WLOCK(&ripcbinfo); inp = sotoinpcb(so); if (inp == 0) { INP_INFO_WUNLOCK(&ripcbinfo); return EINVAL; } INP_LOCK(inp); inp->inp_laddr = addr->sin_addr; INP_UNLOCK(inp); INP_INFO_WUNLOCK(&ripcbinfo); return 0; } static int rip_connect(struct socket *so, struct sockaddr *nam, struct thread *td) { struct sockaddr_in *addr = (struct sockaddr_in *)nam; struct inpcb *inp; if (nam->sa_len != sizeof(*addr)) return EINVAL; if (TAILQ_EMPTY(&ifnet)) return EADDRNOTAVAIL; if (addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK) return EAFNOSUPPORT; INP_INFO_WLOCK(&ripcbinfo); inp = sotoinpcb(so); if (inp == 0) { INP_INFO_WUNLOCK(&ripcbinfo); return EINVAL; } INP_LOCK(inp); inp->inp_faddr = addr->sin_addr; soisconnected(so); INP_UNLOCK(inp); INP_INFO_WUNLOCK(&ripcbinfo); return 0; } static int rip_shutdown(struct socket *so) { struct inpcb *inp; INP_INFO_RLOCK(&ripcbinfo); inp = sotoinpcb(so); if (inp == 0) { INP_INFO_RUNLOCK(&ripcbinfo); return EINVAL; } INP_LOCK(inp); INP_INFO_RUNLOCK(&ripcbinfo); socantsendmore(so); INP_UNLOCK(inp); return 0; } static int rip_send(struct socket *so, int flags, struct mbuf *m, struct sockaddr *nam, struct mbuf *control, struct thread *td) { struct inpcb *inp; u_long dst; int ret; INP_INFO_WLOCK(&ripcbinfo); inp = sotoinpcb(so); if (so->so_state & SS_ISCONNECTED) { if (nam) { INP_INFO_WUNLOCK(&ripcbinfo); m_freem(m); return EISCONN; } dst = inp->inp_faddr.s_addr; } else { if (nam == NULL) { INP_INFO_WUNLOCK(&ripcbinfo); m_freem(m); return ENOTCONN; } dst = ((struct sockaddr_in *)nam)->sin_addr.s_addr; } INP_LOCK(inp); ret = rip_output(m, so, dst); INP_UNLOCK(inp); INP_INFO_WUNLOCK(&ripcbinfo); return ret; } static int rip_pcblist(SYSCTL_HANDLER_ARGS) { int error, i, n; struct inpcb *inp, **inp_list; inp_gen_t gencnt; struct xinpgen xig; /* * The process of preparing the TCB list is too time-consuming and * resource-intensive to repeat twice on every request. */ if (req->oldptr == 0) { n = ripcbinfo.ipi_count; req->oldidx = 2 * (sizeof xig) + (n + n/8) * sizeof(struct xinpcb); return 0; } if (req->newptr != 0) return EPERM; /* * OK, now we're committed to doing something. */ INP_INFO_RLOCK(&ripcbinfo); gencnt = ripcbinfo.ipi_gencnt; n = ripcbinfo.ipi_count; INP_INFO_RUNLOCK(&ripcbinfo); xig.xig_len = sizeof xig; xig.xig_count = n; xig.xig_gen = gencnt; xig.xig_sogen = so_gencnt; error = SYSCTL_OUT(req, &xig, sizeof xig); if (error) return error; inp_list = malloc(n * sizeof *inp_list, M_TEMP, M_WAITOK); if (inp_list == 0) return ENOMEM; INP_INFO_RLOCK(&ripcbinfo); for (inp = LIST_FIRST(ripcbinfo.listhead), i = 0; inp && i < n; inp = LIST_NEXT(inp, inp_list)) { INP_LOCK(inp); if (inp->inp_gencnt <= gencnt && cr_canseesocket(req->td->td_ucred, inp->inp_socket) == 0) { /* XXX held references? */ inp_list[i++] = inp; } INP_UNLOCK(inp); } INP_INFO_RUNLOCK(&ripcbinfo); n = i; error = 0; for (i = 0; i < n; i++) { inp = inp_list[i]; if (inp->inp_gencnt <= gencnt) { struct xinpcb xi; xi.xi_len = sizeof xi; /* XXX should avoid extra copy */ bcopy(inp, &xi.xi_inp, sizeof *inp); if (inp->inp_socket) sotoxsocket(inp->inp_socket, &xi.xi_socket); error = SYSCTL_OUT(req, &xi, sizeof xi); } } if (!error) { /* * Give the user an updated idea of our state. * If the generation differs from what we told * her before, she knows that something happened * while we were processing this request, and it * might be necessary to retry. */ INP_INFO_RLOCK(&ripcbinfo); xig.xig_gen = ripcbinfo.ipi_gencnt; xig.xig_sogen = so_gencnt; xig.xig_count = ripcbinfo.ipi_count; INP_INFO_RUNLOCK(&ripcbinfo); error = SYSCTL_OUT(req, &xig, sizeof xig); } free(inp_list, M_TEMP); return error; } /* * This is the wrapper function for in_setsockaddr. We just pass down * the pcbinfo for in_setpeeraddr to lock. */ static int rip_sockaddr(struct socket *so, struct sockaddr **nam) { return (in_setsockaddr(so, nam, &ripcbinfo)); } /* * This is the wrapper function for in_setpeeraddr. We just pass down * the pcbinfo for in_setpeeraddr to lock. */ static int rip_peeraddr(struct socket *so, struct sockaddr **nam) { return (in_setpeeraddr(so, nam, &ripcbinfo)); } SYSCTL_PROC(_net_inet_raw, OID_AUTO/*XXX*/, pcblist, CTLFLAG_RD, 0, 0, rip_pcblist, "S,xinpcb", "List of active raw IP sockets"); struct pr_usrreqs rip_usrreqs = { rip_abort, pru_accept_notsupp, rip_attach, rip_bind, rip_connect, pru_connect2_notsupp, in_control, rip_detach, rip_disconnect, pru_listen_notsupp, rip_peeraddr, pru_rcvd_notsupp, pru_rcvoob_notsupp, rip_send, pru_sense_null, rip_shutdown, rip_sockaddr, sosend, soreceive, sopoll, in_pcbsosetlabel };