d/freebsd-skq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
459bc4f0dd
freebsd-skq/sys/netinet/ip_icmp.c
Marko Zec 44e33a0758 Change the initialization methodology for global variables scheduled 
for virtualization.

Instead of initializing the affected global variables at instatiation,
assign initial values to them in initializer functions.  As a rule,
initialization at instatiation for such variables should never be
introduced again from now on.  Furthermore, enclose all instantiations
of such global variables in #ifdef VIMAGE_GLOBALS blocks.

Essentialy, this change should have zero functional impact.  In the next
phase of merging network stack virtualization infrastructure from
p4/vimage branch, the new initialization methology will allow us to
switch between using global variables and their counterparts residing in
virtualization containers with minimum code churn, and in the long run
allow us to intialize multiple instances of such container structures.

Discussed at:	devsummit Strassburg
Reviewed by:	bz, julian
Approved by:	julian (mentor)
Obtained from:	//depot/projects/vimage-commit2/...
X-MFC after:	never
Sponsored by:	NLnet Foundation, The FreeBSD Foundation
2008-11-19 09:39:34 +00:00

954 lines
25 KiB
C
Raw Blame History

/*-
* 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.
*
* @(#)ip_icmp.c 8.2 (Berkeley) 1/4/94
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_ipsec.h"
#include "opt_mac.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/mbuf.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/time.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#include <sys/vimage.h>
#include <net/if.h>
#include <net/if_types.h>
#include <net/route.h>
#include <netinet/in.h>
#include <netinet/in_pcb.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/ip_icmp.h>
#include <netinet/ip_var.h>
#include <netinet/ip_options.h>
#include <netinet/tcp.h>
#include <netinet/tcp_var.h>
#include <netinet/tcpip.h>
#include <netinet/icmp_var.h>
#ifdef IPSEC
#include <netipsec/ipsec.h>
#include <netipsec/key.h>
#endif
#include <machine/in_cksum.h>
#include <security/mac/mac_framework.h>
/*
* ICMP routines: error generation, receive packet processing, and
* routines to turnaround packets back to the originator, and
* host table maintenance routines.
*/
#ifdef VIMAGE_GLOBALS
struct icmpstat icmpstat;
static int icmpmaskrepl;
static u_int icmpmaskfake;
static int drop_redirect;
static int log_redirect;
static int icmplim;
static int icmplim_output;
static char reply_src[IFNAMSIZ];
static int icmp_rfi;
static int icmp_quotelen;
static int icmpbmcastecho;
#endif
SYSCTL_V_STRUCT(V_NET, vnet_inet, _net_inet_icmp, ICMPCTL_STATS, stats,
CTLFLAG_RW, icmpstat, icmpstat, "");
SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_icmp, ICMPCTL_MASKREPL, maskrepl,
CTLFLAG_RW, icmpmaskrepl, 0,
"Reply to ICMP Address Mask Request packets.");
SYSCTL_V_UINT(V_NET, vnet_inet, _net_inet_icmp, OID_AUTO, maskfake, CTLFLAG_RW,
icmpmaskfake, 0, "Fake reply to ICMP Address Mask Request packets.");
SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_icmp, OID_AUTO, drop_redirect,
CTLFLAG_RW, drop_redirect, 0, "Ignore ICMP redirects");
SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_icmp, OID_AUTO, log_redirect,
CTLFLAG_RW, log_redirect, 0, "Log ICMP redirects to the console");
SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_icmp, ICMPCTL_ICMPLIM, icmplim,
CTLFLAG_RW, icmplim, 0, "Maximum number of ICMP responses per second");
SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_icmp, OID_AUTO, icmplim_output,
CTLFLAG_RW, icmplim_output, 0,
"Enable rate limiting of ICMP responses");
SYSCTL_V_STRING(V_NET, vnet_inet, _net_inet_icmp, OID_AUTO, reply_src,
CTLFLAG_RW, reply_src, IFNAMSIZ,
"icmp reply source for non-local packets.");
SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_icmp, OID_AUTO, reply_from_interface,
CTLFLAG_RW, icmp_rfi, 0, "ICMP reply from incoming interface for "
"non-local packets");
SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_icmp, OID_AUTO, quotelen, CTLFLAG_RW,
icmp_quotelen, 0, "Number of bytes from original packet to "
"quote in ICMP reply");
/*
* ICMP broadcast echo sysctl
*/
SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_icmp, OID_AUTO, bmcastecho,
CTLFLAG_RW, icmpbmcastecho, 0, "");
#ifdef ICMPPRINTFS
int icmpprintfs = 0;
#endif
static void icmp_reflect(struct mbuf *);
static void icmp_send(struct mbuf *, struct mbuf *);
extern struct protosw inetsw[];
void
icmp_init(void)
{
INIT_VNET_INET(curvnet);
V_icmpmaskrepl = 0;
V_icmpmaskfake = 0;
V_drop_redirect = 0;
V_log_redirect = 0;
V_icmplim = 200;
V_icmplim_output = 1;
V_icmp_rfi = 0;
V_icmp_quotelen = 8;
V_icmpbmcastecho = 0;
}
/*
* Generate an error packet of type error
* in response to bad packet ip.
*/
void
icmp_error(struct mbuf *n, int type, int code, n_long dest, int mtu)
{
INIT_VNET_INET(curvnet);
register struct ip *oip = mtod(n, struct ip *), *nip;
register unsigned oiphlen = oip->ip_hl << 2;
register struct icmp *icp;
register struct mbuf *m;
unsigned icmplen, icmpelen, nlen;
KASSERT((u_int)type <= ICMP_MAXTYPE, ("%s: illegal ICMP type", __func__));
#ifdef ICMPPRINTFS
if (icmpprintfs)
printf("icmp_error(%p, %x, %d)\n", oip, type, code);
#endif
if (type != ICMP_REDIRECT)
V_icmpstat.icps_error++;
/*
* Don't send error:
* if the original packet was encrypted.
* if not the first fragment of message.
* in response to a multicast or broadcast packet.
* if the old packet protocol was an ICMP error message.
*/
if (n->m_flags & M_DECRYPTED)
goto freeit;
if (oip->ip_off & ~(IP_MF|IP_DF))
goto freeit;
if (n->m_flags & (M_BCAST|M_MCAST))
goto freeit;
if (oip->ip_p == IPPROTO_ICMP && type != ICMP_REDIRECT &&
n->m_len >= oiphlen + ICMP_MINLEN &&
!ICMP_INFOTYPE(((struct icmp *)((caddr_t)oip + oiphlen))->icmp_type)) {
V_icmpstat.icps_oldicmp++;
goto freeit;
}
/* Drop if IP header plus 8 bytes is not contignous in first mbuf. */
if (oiphlen + 8 > n->m_len)
goto freeit;
/*
* Calculate length to quote from original packet and
* prevent the ICMP mbuf from overflowing.
* Unfortunatly this is non-trivial since ip_forward()
* sends us truncated packets.
*/
nlen = m_length(n, NULL);
if (oip->ip_p == IPPROTO_TCP) {
struct tcphdr *th;
int tcphlen;
if (oiphlen + sizeof(struct tcphdr) > n->m_len &&
n->m_next == NULL)
goto stdreply;
if (n->m_len < oiphlen + sizeof(struct tcphdr) &&
((n = m_pullup(n, oiphlen + sizeof(struct tcphdr))) == NULL))
goto freeit;
th = (struct tcphdr *)((caddr_t)oip + oiphlen);
tcphlen = th->th_off << 2;
if (tcphlen < sizeof(struct tcphdr))
goto freeit;
if (oip->ip_len < oiphlen + tcphlen)
goto freeit;
if (oiphlen + tcphlen > n->m_len && n->m_next == NULL)
goto stdreply;
if (n->m_len < oiphlen + tcphlen &&
((n = m_pullup(n, oiphlen + tcphlen)) == NULL))
goto freeit;
icmpelen = max(tcphlen, min(V_icmp_quotelen, oip->ip_len - oiphlen));
} else
stdreply: icmpelen = max(8, min(V_icmp_quotelen, oip->ip_len - oiphlen));
icmplen = min(oiphlen + icmpelen, nlen);
if (icmplen < sizeof(struct ip))
goto freeit;
if (MHLEN > sizeof(struct ip) + ICMP_MINLEN + icmplen)
m = m_gethdr(M_DONTWAIT, MT_DATA);
else
m = m_getcl(M_DONTWAIT, MT_DATA, M_PKTHDR);
if (m == NULL)
goto freeit;
#ifdef MAC
mac_netinet_icmp_reply(n, m);
#endif
icmplen = min(icmplen, M_TRAILINGSPACE(m) - sizeof(struct ip) - ICMP_MINLEN);
m_align(m, ICMP_MINLEN + icmplen);
m->m_len = ICMP_MINLEN + icmplen;
/* XXX MRT make the outgoing packet use the same FIB
* that was associated with the incoming packet
*/
M_SETFIB(m, M_GETFIB(n));
icp = mtod(m, struct icmp *);
V_icmpstat.icps_outhist[type]++;
icp->icmp_type = type;
if (type == ICMP_REDIRECT)
icp->icmp_gwaddr.s_addr = dest;
else {
icp->icmp_void = 0;
/*
* The following assignments assume an overlay with the
* just zeroed icmp_void field.
*/
if (type == ICMP_PARAMPROB) {
icp->icmp_pptr = code;
code = 0;
} else if (type == ICMP_UNREACH &&
code == ICMP_UNREACH_NEEDFRAG && mtu) {
icp->icmp_nextmtu = htons(mtu);
}
}
icp->icmp_code = code;
/*
* Copy the quotation into ICMP message and
* convert quoted IP header back to network representation.
*/
m_copydata(n, 0, icmplen, (caddr_t)&icp->icmp_ip);
nip = &icp->icmp_ip;
nip->ip_len = htons(nip->ip_len);
nip->ip_off = htons(nip->ip_off);
/*
* Set up ICMP message mbuf and copy old IP header (without options
* in front of ICMP message.
* If the original mbuf was meant to bypass the firewall, the error
* reply should bypass as well.
*/
m->m_flags |= n->m_flags & M_SKIP_FIREWALL;
m->m_data -= sizeof(struct ip);
m->m_len += sizeof(struct ip);
m->m_pkthdr.len = m->m_len;
m->m_pkthdr.rcvif = n->m_pkthdr.rcvif;
nip = mtod(m, struct ip *);
bcopy((caddr_t)oip, (caddr_t)nip, sizeof(struct ip));
nip->ip_len = m->m_len;
nip->ip_v = IPVERSION;
nip->ip_hl = 5;
nip->ip_p = IPPROTO_ICMP;
nip->ip_tos = 0;
icmp_reflect(m);
freeit:
m_freem(n);
}
/*
* Process a received ICMP message.
*/
void
icmp_input(struct mbuf *m, int off)
{
INIT_VNET_INET(curvnet);
struct icmp *icp;
struct in_ifaddr *ia;
struct ip *ip = mtod(m, struct ip *);
struct sockaddr_in icmpsrc, icmpdst, icmpgw;
int hlen = off;
int icmplen = ip->ip_len;
int i, code;
void (*ctlfunc)(int, struct sockaddr *, void *);
int fibnum;
/*
* Locate icmp structure in mbuf, and check
* that not corrupted and of at least minimum length.
*/
#ifdef ICMPPRINTFS
if (icmpprintfs) {
char buf[4 * sizeof "123"];
strcpy(buf, inet_ntoa(ip->ip_src));
printf("icmp_input from %s to %s, len %d\n",
buf, inet_ntoa(ip->ip_dst), icmplen);
}
#endif
if (icmplen < ICMP_MINLEN) {
V_icmpstat.icps_tooshort++;
goto freeit;
}
i = hlen + min(icmplen, ICMP_ADVLENMIN);
if (m->m_len < i && (m = m_pullup(m, i)) == 0) {
V_icmpstat.icps_tooshort++;
return;
}
ip = mtod(m, struct ip *);
m->m_len -= hlen;
m->m_data += hlen;
icp = mtod(m, struct icmp *);
if (in_cksum(m, icmplen)) {
V_icmpstat.icps_checksum++;
goto freeit;
}
m->m_len += hlen;
m->m_data -= hlen;
if (m->m_pkthdr.rcvif && m->m_pkthdr.rcvif->if_type == IFT_FAITH) {
/*
* Deliver very specific ICMP type only.
*/
switch (icp->icmp_type) {
case ICMP_UNREACH:
case ICMP_TIMXCEED:
break;
default:
goto freeit;
}
}
#ifdef ICMPPRINTFS
if (icmpprintfs)
printf("icmp_input, type %d code %d\n", icp->icmp_type,
icp->icmp_code);
#endif
/*
* Message type specific processing.
*/
if (icp->icmp_type > ICMP_MAXTYPE)
goto raw;
/* Initialize */
bzero(&icmpsrc, sizeof(icmpsrc));
icmpsrc.sin_len = sizeof(struct sockaddr_in);
icmpsrc.sin_family = AF_INET;
bzero(&icmpdst, sizeof(icmpdst));
icmpdst.sin_len = sizeof(struct sockaddr_in);
icmpdst.sin_family = AF_INET;
bzero(&icmpgw, sizeof(icmpgw));
icmpgw.sin_len = sizeof(struct sockaddr_in);
icmpgw.sin_family = AF_INET;
V_icmpstat.icps_inhist[icp->icmp_type]++;
code = icp->icmp_code;
switch (icp->icmp_type) {
case ICMP_UNREACH:
switch (code) {
case ICMP_UNREACH_NET:
case ICMP_UNREACH_HOST:
case ICMP_UNREACH_SRCFAIL:
case ICMP_UNREACH_NET_UNKNOWN:
case ICMP_UNREACH_HOST_UNKNOWN:
case ICMP_UNREACH_ISOLATED:
case ICMP_UNREACH_TOSNET:
case ICMP_UNREACH_TOSHOST:
case ICMP_UNREACH_HOST_PRECEDENCE:
case ICMP_UNREACH_PRECEDENCE_CUTOFF:
code = PRC_UNREACH_NET;
break;
case ICMP_UNREACH_NEEDFRAG:
code = PRC_MSGSIZE;
break;
/*
* RFC 1122, Sections 3.2.2.1 and 4.2.3.9.
* Treat subcodes 2,3 as immediate RST
*/
case ICMP_UNREACH_PROTOCOL:
case ICMP_UNREACH_PORT:
code = PRC_UNREACH_PORT;
break;
case ICMP_UNREACH_NET_PROHIB:
case ICMP_UNREACH_HOST_PROHIB:
case ICMP_UNREACH_FILTER_PROHIB:
code = PRC_UNREACH_ADMIN_PROHIB;
break;
default:
goto badcode;
}
goto deliver;
case ICMP_TIMXCEED:
if (code > 1)
goto badcode;
code += PRC_TIMXCEED_INTRANS;
goto deliver;
case ICMP_PARAMPROB:
if (code > 1)
goto badcode;
code = PRC_PARAMPROB;
goto deliver;
case ICMP_SOURCEQUENCH:
if (code)
goto badcode;
code = PRC_QUENCH;
deliver:
/*
* Problem with datagram; advise higher level routines.
*/
if (icmplen < ICMP_ADVLENMIN || icmplen < ICMP_ADVLEN(icp) ||
icp->icmp_ip.ip_hl < (sizeof(struct ip) >> 2)) {
V_icmpstat.icps_badlen++;
goto freeit;
}
icp->icmp_ip.ip_len = ntohs(icp->icmp_ip.ip_len);
/* Discard ICMP's in response to multicast packets */
if (IN_MULTICAST(ntohl(icp->icmp_ip.ip_dst.s_addr)))
goto badcode;
#ifdef ICMPPRINTFS
if (icmpprintfs)
printf("deliver to protocol %d\n", icp->icmp_ip.ip_p);
#endif
icmpsrc.sin_addr = icp->icmp_ip.ip_dst;
/*
* XXX if the packet contains [IPv4 AH TCP], we can't make a
* notification to TCP layer.
*/
ctlfunc = inetsw[ip_protox[icp->icmp_ip.ip_p]].pr_ctlinput;
if (ctlfunc)
(*ctlfunc)(code, (struct sockaddr *)&icmpsrc,
(void *)&icp->icmp_ip);
break;
badcode:
V_icmpstat.icps_badcode++;
break;
case ICMP_ECHO:
if (!V_icmpbmcastecho
&& (m->m_flags & (M_MCAST | M_BCAST)) != 0) {
V_icmpstat.icps_bmcastecho++;
break;
}
icp->icmp_type = ICMP_ECHOREPLY;
if (badport_bandlim(BANDLIM_ICMP_ECHO) < 0)
goto freeit;
else
goto reflect;
case ICMP_TSTAMP:
if (!V_icmpbmcastecho
&& (m->m_flags & (M_MCAST | M_BCAST)) != 0) {
V_icmpstat.icps_bmcasttstamp++;
break;
}
if (icmplen < ICMP_TSLEN) {
V_icmpstat.icps_badlen++;
break;
}
icp->icmp_type = ICMP_TSTAMPREPLY;
icp->icmp_rtime = iptime();
icp->icmp_ttime = icp->icmp_rtime; /* bogus, do later! */
if (badport_bandlim(BANDLIM_ICMP_TSTAMP) < 0)
goto freeit;
else
goto reflect;
case ICMP_MASKREQ:
if (V_icmpmaskrepl == 0)
break;
/*
* We are not able to respond with all ones broadcast
* unless we receive it over a point-to-point interface.
*/
if (icmplen < ICMP_MASKLEN)
break;
switch (ip->ip_dst.s_addr) {
case INADDR_BROADCAST:
case INADDR_ANY:
icmpdst.sin_addr = ip->ip_src;
break;
default:
icmpdst.sin_addr = ip->ip_dst;
}
ia = (struct in_ifaddr *)ifaof_ifpforaddr(
(struct sockaddr *)&icmpdst, m->m_pkthdr.rcvif);
if (ia == 0)
break;
if (ia->ia_ifp == 0)
break;
icp->icmp_type = ICMP_MASKREPLY;
if (V_icmpmaskfake == 0)
icp->icmp_mask = ia->ia_sockmask.sin_addr.s_addr;
else
icp->icmp_mask = V_icmpmaskfake;
if (ip->ip_src.s_addr == 0) {
if (ia->ia_ifp->if_flags & IFF_BROADCAST)
ip->ip_src = satosin(&ia->ia_broadaddr)->sin_addr;
else if (ia->ia_ifp->if_flags & IFF_POINTOPOINT)
ip->ip_src = satosin(&ia->ia_dstaddr)->sin_addr;
}
reflect:
ip->ip_len += hlen; /* since ip_input deducts this */
V_icmpstat.icps_reflect++;
V_icmpstat.icps_outhist[icp->icmp_type]++;
icmp_reflect(m);
return;
case ICMP_REDIRECT:
if (V_log_redirect) {
u_long src, dst, gw;
src = ntohl(ip->ip_src.s_addr);
dst = ntohl(icp->icmp_ip.ip_dst.s_addr);
gw = ntohl(icp->icmp_gwaddr.s_addr);
printf("icmp redirect from %d.%d.%d.%d: "
"%d.%d.%d.%d => %d.%d.%d.%d\n",
(int)(src >> 24), (int)((src >> 16) & 0xff),
(int)((src >> 8) & 0xff), (int)(src & 0xff),
(int)(dst >> 24), (int)((dst >> 16) & 0xff),
(int)((dst >> 8) & 0xff), (int)(dst & 0xff),
(int)(gw >> 24), (int)((gw >> 16) & 0xff),
(int)((gw >> 8) & 0xff), (int)(gw & 0xff));
}
/*
* RFC1812 says we must ignore ICMP redirects if we
* are acting as router.
*/
if (V_drop_redirect || V_ipforwarding)
break;
if (code > 3)
goto badcode;
if (icmplen < ICMP_ADVLENMIN || icmplen < ICMP_ADVLEN(icp) ||
icp->icmp_ip.ip_hl < (sizeof(struct ip) >> 2)) {
V_icmpstat.icps_badlen++;
break;
}
/*
* Short circuit routing redirects to force
* immediate change in the kernel's routing
* tables. The message is also handed to anyone
* listening on a raw socket (e.g. the routing
* daemon for use in updating its tables).
*/
icmpgw.sin_addr = ip->ip_src;
icmpdst.sin_addr = icp->icmp_gwaddr;
#ifdef ICMPPRINTFS
if (icmpprintfs) {
char buf[4 * sizeof "123"];
strcpy(buf, inet_ntoa(icp->icmp_ip.ip_dst));
printf("redirect dst %s to %s\n",
buf, inet_ntoa(icp->icmp_gwaddr));
}
#endif
icmpsrc.sin_addr = icp->icmp_ip.ip_dst;
for ( fibnum = 0; fibnum < rt_numfibs; fibnum++) {
in_rtredirect((struct sockaddr *)&icmpsrc,
(struct sockaddr *)&icmpdst,
(struct sockaddr *)0, RTF_GATEWAY | RTF_HOST,
(struct sockaddr *)&icmpgw, fibnum);
}
pfctlinput(PRC_REDIRECT_HOST, (struct sockaddr *)&icmpsrc);
#ifdef IPSEC
key_sa_routechange((struct sockaddr *)&icmpsrc);
#endif
break;
/*
* No kernel processing for the following;
* just fall through to send to raw listener.
*/
case ICMP_ECHOREPLY:
case ICMP_ROUTERADVERT:
case ICMP_ROUTERSOLICIT:
case ICMP_TSTAMPREPLY:
case ICMP_IREQREPLY:
case ICMP_MASKREPLY:
default:
break;
}
raw:
rip_input(m, off);
return;
freeit:
m_freem(m);
}
/*
* Reflect the ip packet back to the source
*/
static void
icmp_reflect(struct mbuf *m)
{
INIT_VNET_INET(curvnet);
struct ip *ip = mtod(m, struct ip *);
struct ifaddr *ifa;
struct ifnet *ifn;
struct in_ifaddr *ia;
struct in_addr t;
struct mbuf *opts = 0;
int optlen = (ip->ip_hl << 2) - sizeof(struct ip);
if (IN_MULTICAST(ntohl(ip->ip_src.s_addr)) ||
IN_EXPERIMENTAL(ntohl(ip->ip_src.s_addr)) ||
IN_ZERONET(ntohl(ip->ip_src.s_addr)) ) {
m_freem(m); /* Bad return address */
V_icmpstat.icps_badaddr++;
goto done; /* Ip_output() will check for broadcast */
}
t = ip->ip_dst;
ip->ip_dst = ip->ip_src;
/*
* Source selection for ICMP replies:
*
* If the incoming packet was addressed directly to one of our
* own addresses, use dst as the src for the reply.
*/
LIST_FOREACH(ia, INADDR_HASH(t.s_addr), ia_hash)
if (t.s_addr == IA_SIN(ia)->sin_addr.s_addr)
goto match;
/*
* If the incoming packet was addressed to one of our broadcast
* addresses, use the first non-broadcast address which corresponds
* to the incoming interface.
*/
if (m->m_pkthdr.rcvif != NULL &&
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 (satosin(&ia->ia_broadaddr)->sin_addr.s_addr ==
t.s_addr)
goto match;
}
}
/*
* If the packet was transiting through us, use the address of
* the interface the packet came through in. If that interface
* doesn't have a suitable IP address, the normal selection
* criteria apply.
*/
if (V_icmp_rfi && m->m_pkthdr.rcvif != NULL) {
TAILQ_FOREACH(ifa, &m->m_pkthdr.rcvif->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
ia = ifatoia(ifa);
goto match;
}
}
/*
* If the incoming packet was not addressed directly to us, use
* designated interface for icmp replies specified by sysctl
* net.inet.icmp.reply_src (default not set). Otherwise continue
* with normal source selection.
*/
if (V_reply_src[0] != '\0' && (ifn = ifunit(V_reply_src))) {
TAILQ_FOREACH(ifa, &ifn->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
ia = ifatoia(ifa);
goto match;
}
}
/*
* If the packet was transiting through us, use the address of
* the interface that is the closest to the packet source.
* When we don't have a route back to the packet source, stop here
* and drop the packet.
*/
ia = ip_rtaddr(ip->ip_dst, M_GETFIB(m));
if (ia == NULL) {
m_freem(m);
V_icmpstat.icps_noroute++;
goto done;
}
match:
#ifdef MAC
mac_netinet_icmp_replyinplace(m);
#endif
t = IA_SIN(ia)->sin_addr;
ip->ip_src = t;
ip->ip_ttl = V_ip_defttl;
if (optlen > 0) {
register u_char *cp;
int opt, cnt;
u_int len;
/*
* Retrieve any source routing from the incoming packet;
* add on any record-route or timestamp options.
*/
cp = (u_char *) (ip + 1);
if ((opts = ip_srcroute(m)) == 0 &&
(opts = m_gethdr(M_DONTWAIT, MT_DATA))) {
opts->m_len = sizeof(struct in_addr);
mtod(opts, struct in_addr *)->s_addr = 0;
}
if (opts) {
#ifdef ICMPPRINTFS
if (icmpprintfs)
printf("icmp_reflect optlen %d rt %d => ",
optlen, opts->m_len);
#endif
for (cnt = optlen; cnt > 0; cnt -= len, cp += len) {
opt = cp[IPOPT_OPTVAL];
if (opt == IPOPT_EOL)
break;
if (opt == IPOPT_NOP)
len = 1;
else {
if (cnt < IPOPT_OLEN + sizeof(*cp))
break;
len = cp[IPOPT_OLEN];
if (len < IPOPT_OLEN + sizeof(*cp) ||
len > cnt)
break;
}
/*
* Should check for overflow, but it "can't happen"
*/
if (opt == IPOPT_RR || opt == IPOPT_TS ||
opt == IPOPT_SECURITY) {
bcopy((caddr_t)cp,
mtod(opts, caddr_t) + opts->m_len, len);
opts->m_len += len;
}
}
/* Terminate & pad, if necessary */
cnt = opts->m_len % 4;
if (cnt) {
for (; cnt < 4; cnt++) {
*(mtod(opts, caddr_t) + opts->m_len) =
IPOPT_EOL;
opts->m_len++;
}
}
#ifdef ICMPPRINTFS
if (icmpprintfs)
printf("%d\n", opts->m_len);
#endif
}
/*
* Now strip out original options by copying rest of first
* mbuf's data back, and adjust the IP length.
*/
ip->ip_len -= optlen;
ip->ip_v = IPVERSION;
ip->ip_hl = 5;
m->m_len -= optlen;
if (m->m_flags & M_PKTHDR)
m->m_pkthdr.len -= optlen;
optlen += sizeof(struct ip);
bcopy((caddr_t)ip + optlen, (caddr_t)(ip + 1),
(unsigned)(m->m_len - sizeof(struct ip)));
}
m_tag_delete_nonpersistent(m);
m->m_flags &= ~(M_BCAST|M_MCAST);
icmp_send(m, opts);
done:
if (opts)
(void)m_free(opts);
}
/*
* Send an icmp packet back to the ip level,
* after supplying a checksum.
*/
static void
icmp_send(struct mbuf *m, struct mbuf *opts)
{
register struct ip *ip = mtod(m, struct ip *);
register int hlen;
register struct icmp *icp;
hlen = ip->ip_hl << 2;
m->m_data += hlen;
m->m_len -= hlen;
icp = mtod(m, struct icmp *);
icp->icmp_cksum = 0;
icp->icmp_cksum = in_cksum(m, ip->ip_len - hlen);
m->m_data -= hlen;
m->m_len += hlen;
m->m_pkthdr.rcvif = (struct ifnet *)0;
#ifdef ICMPPRINTFS
if (icmpprintfs) {
char buf[4 * sizeof "123"];
strcpy(buf, inet_ntoa(ip->ip_dst));
printf("icmp_send dst %s src %s\n",
buf, inet_ntoa(ip->ip_src));
}
#endif
(void) ip_output(m, opts, NULL, 0, NULL, NULL);
}
n_time
iptime(void)
{
struct timeval atv;
u_long t;
getmicrotime(&atv);
t = (atv.tv_sec % (24*60*60)) * 1000 + atv.tv_usec / 1000;
return (htonl(t));
}
/*
* Return the next larger or smaller MTU plateau (table from RFC 1191)
* given current value MTU. If DIR is less than zero, a larger plateau
* is returned; otherwise, a smaller value is returned.
*/
int
ip_next_mtu(int mtu, int dir)
{
static int mtutab[] = {
65535, 32000, 17914, 8166, 4352, 2002, 1492, 1280, 1006, 508,
296, 68, 0
};
int i, size;
size = (sizeof mtutab) / (sizeof mtutab[0]);
if (dir >= 0) {
for (i = 0; i < size; i++)
if (mtu > mtutab[i])
return mtutab[i];
} else {
for (i = size - 1; i >= 0; i--)
if (mtu < mtutab[i])
return mtutab[i];
if (mtu == mtutab[0])
return mtutab[0];
}
return 0;
}
/*
* badport_bandlim() - check for ICMP bandwidth limit
*
* Return 0 if it is ok to send an ICMP error response, -1 if we have
* hit our bandwidth limit and it is not ok.
*
* If icmplim is <= 0, the feature is disabled and 0 is returned.
*
* For now we separate the TCP and UDP subsystems w/ different 'which'
* values. We may eventually remove this separation (and simplify the
* code further).
*
* Note that the printing of the error message is delayed so we can
* properly print the icmp error rate that the system was trying to do
* (i.e. 22000/100 pps, etc...). This can cause long delays in printing
* the 'final' error, but it doesn't make sense to solve the printing
* delay with more complex code.
*/
int
badport_bandlim(int which)
{
INIT_VNET_INET(curvnet);
#define N(a) (sizeof (a) / sizeof (a[0]))
static struct rate {
const char *type;
struct timeval lasttime;
int curpps;
} rates[BANDLIM_MAX+1] = {
{ "icmp unreach response" },
{ "icmp ping response" },
{ "icmp tstamp response" },
{ "closed port RST response" },
{ "open port RST response" },
{ "icmp6 unreach response" }
};
/*
* Return ok status if feature disabled or argument out of range.
*/
if (V_icmplim > 0 && (u_int) which < N(rates)) {
struct rate *r = &rates[which];
int opps = r->curpps;
if (!ppsratecheck(&r->lasttime, &r->curpps, V_icmplim))
return -1; /* discard packet */
/*
* If we've dropped below the threshold after having
* rate-limited traffic print the message. This preserves
* the previous behaviour at the expense of added complexity.
*/
if (V_icmplim_output && opps > V_icmplim)
printf("Limiting %s from %d to %d packets/sec\n",
r->type, opps, V_icmplim);
}
return 0; /* okay to send packet */
#undef N
}
Reference in New Issue View Git Blame Copy Permalink