static void
in_rtqtimo_one(void *rock)
{
struct radix_node_head *rnh = rock;
struct rtqk_arg arg;
static time_t last_adjusted_timeout = 0;
arg.found = arg.killed = 0;
arg.rnh = rnh;
arg.nextstop = time_uptime + V_rtq_timeout;
arg.draining = arg.updating = 0;
RADIX_NODE_HEAD_LOCK(rnh);
rnh->rnh_walktree(rnh, in_rtqkill, &arg);
RADIX_NODE_HEAD_UNLOCK(rnh);
/*
* Attempt to be somewhat dynamic about this:
* If there are ``too many'' routes sitting around taking up space,
* then crank down the timeout, and see if we can't make some more
* go away. However, we make sure that we will never adjust more
* than once in rtq_timeout seconds, to keep from cranking down too
* hard.
*/
if ((arg.found - arg.killed > V_rtq_toomany) &&
(time_uptime - last_adjusted_timeout >= V_rtq_timeout) &&
V_rtq_reallyold > V_rtq_minreallyold) {
V_rtq_reallyold = 2 * V_rtq_reallyold / 3;
if (V_rtq_reallyold < V_rtq_minreallyold) {
V_rtq_reallyold = V_rtq_minreallyold;
}
last_adjusted_timeout = time_uptime;
#ifdef DIAGNOSTIC
bsd_log(LOG_DEBUG, "in_rtqtimo: adjusted rtq_reallyold to %d\n",
V_rtq_reallyold);
#endif
arg.found = arg.killed = 0;
arg.updating = 1;
RADIX_NODE_HEAD_LOCK(rnh);
rnh->rnh_walktree(rnh, in_rtqkill, &arg);
RADIX_NODE_HEAD_UNLOCK(rnh);
}
}
/*
* Get rid of old routes. When draining, this deletes everything, even when
* the timeout is not expired yet. When updating, this makes sure that
* nothing has a timeout longer than the current value of rtq_reallyold.
*/
static int
in_rtqkill(struct radix_node *rn, void *rock)
{
struct rtqk_arg *ap = rock;
struct rtentry *rt = (struct rtentry *)rn;
int err;
RADIX_NODE_HEAD_WLOCK_ASSERT(ap->rnh);
if (rt->rt_flags & RTPRF_OURS) {
ap->found++;
if (ap->draining || rt->rt_rmx.rmx_expire <= time_uptime) {
if (rt->rt_refcnt > 0)
panic("rtqkill route really not free");
err = in_rtrequest(RTM_DELETE,
(struct bsd_sockaddr *)rt_key(rt),
rt->rt_gateway, rt_mask(rt),
rt->rt_flags | RTF_RNH_LOCKED, 0,
rt->rt_fibnum);
if (err) {
bsd_log(LOG_WARNING, "in_rtqkill: error %d\n", err);
} else {
ap->killed++;
}
} else {
if (ap->updating &&
(rt->rt_rmx.rmx_expire - time_uptime >
V_rtq_reallyold)) {
rt->rt_rmx.rmx_expire =
time_uptime + V_rtq_reallyold;
}
ap->nextstop = lmin(ap->nextstop,
rt->rt_rmx.rmx_expire);
}
}
return 0;
}
/*
* Do option processing on a datagram, possibly discarding it if bad options
* are encountered, or forwarding it if source-routed.
*
* The pass argument is used when operating in the IPSTEALTH mode to tell
* what options to process: [LS]SRR (pass 0) or the others (pass 1). The
* reason for as many as two passes is that when doing IPSTEALTH, non-routing
* options should be processed only if the packet is for us.
*
* Returns 1 if packet has been forwarded/freed, 0 if the packet should be
* processed further.
*/
int
ip_dooptions(struct mbuf *m, int pass)
{
struct ip *ip = mtod(m, struct ip *);
u_char *cp;
struct in_ifaddr *ia;
int opt, optlen, cnt, off, code, type = ICMP_PARAMPROB, forward = 0;
struct in_addr *sin, dst;
uint32_t ntime;
struct sockaddr_in ipaddr = { sizeof(ipaddr), AF_INET };
/* Ignore or reject packets with IP options. */
if (ip_doopts == 0)
return 0;
else if (ip_doopts == 2) {
type = ICMP_UNREACH;
code = ICMP_UNREACH_FILTER_PROHIB;
goto bad;
}
dst = ip->ip_dst;
cp = (u_char *)(ip + 1);
cnt = (ip->ip_hl << 2) - sizeof (struct ip);
for (; cnt > 0; cnt -= optlen, cp += optlen) {
opt = cp[IPOPT_OPTVAL];
if (opt == IPOPT_EOL)
break;
if (opt == IPOPT_NOP)
optlen = 1;
else {
if (cnt < IPOPT_OLEN + sizeof(*cp)) {
code = &cp[IPOPT_OLEN] - (u_char *)ip;
goto bad;
}
optlen = cp[IPOPT_OLEN];
if (optlen < IPOPT_OLEN + sizeof(*cp) || optlen > cnt) {
code = &cp[IPOPT_OLEN] - (u_char *)ip;
goto bad;
}
}
switch (opt) {
default:
break;
/*
* Source routing with record. Find interface with current
* destination address. If none on this machine then drop if
* strictly routed, or do nothing if loosely routed. Record
* interface address and bring up next address component. If
* strictly routed make sure next address is on directly
* accessible net.
*/
case IPOPT_LSRR:
case IPOPT_SSRR:
#ifdef IPSTEALTH
if (V_ipstealth && pass > 0)
break;
#endif
if (optlen < IPOPT_OFFSET + sizeof(*cp)) {
code = &cp[IPOPT_OLEN] - (u_char *)ip;
goto bad;
}
if ((off = cp[IPOPT_OFFSET]) < IPOPT_MINOFF) {
code = &cp[IPOPT_OFFSET] - (u_char *)ip;
goto bad;
}
ipaddr.sin_addr = ip->ip_dst;
if (ifa_ifwithaddr_check((struct sockaddr *)&ipaddr)
== 0) {
if (opt == IPOPT_SSRR) {
type = ICMP_UNREACH;
code = ICMP_UNREACH_SRCFAIL;
goto bad;
}
if (!ip_dosourceroute)
goto nosourcerouting;
/*
* Loose routing, and not at next destination
* yet; nothing to do except forward.
*/
break;
}
off--; /* 0 origin */
if (off > optlen - (int)sizeof(struct in_addr)) {
/*
* End of source route. Should be for us.
*/
if (!ip_acceptsourceroute)
goto nosourcerouting;
save_rte(m, cp, ip->ip_src);
break;
}
#ifdef IPSTEALTH
if (V_ipstealth)
goto dropit;
#endif
if (!ip_dosourceroute) {
if (V_ipforwarding) {
char buf[16]; /* aaa.bbb.ccc.ddd\0 */
/*
* Acting as a router, so generate
* ICMP
*/
nosourcerouting:
strcpy(buf, inet_ntoa(ip->ip_dst));
bsd_log(LOG_WARNING,
"attempted source route from %s to %s\n",
inet_ntoa(ip->ip_src), buf);
type = ICMP_UNREACH;
code = ICMP_UNREACH_SRCFAIL;
goto bad;
} else {
/*
* Not acting as a router, so
* silently drop.
*/
#ifdef IPSTEALTH
dropit:
#endif
IPSTAT_INC(ips_cantforward);
m_freem(m);
return (1);
}
}
/*
* locate outgoing interface
*/
(void)memcpy(&ipaddr.sin_addr, cp + off,
sizeof(ipaddr.sin_addr));
if (opt == IPOPT_SSRR) {
#define INA struct in_ifaddr *
#define SA struct sockaddr *
if ((ia = (INA)ifa_ifwithdstaddr((SA)&ipaddr)) == NULL)
ia = (INA)ifa_ifwithnet((SA)&ipaddr);
} else
/* XXX MRT 0 for routing */
ia = ip_rtaddr(ipaddr.sin_addr, M_GETFIB(m));
if (ia == NULL) {
type = ICMP_UNREACH;
code = ICMP_UNREACH_SRCFAIL;
goto bad;
}
ip->ip_dst = ipaddr.sin_addr;
(void)memcpy(cp + off, &(IA_SIN(ia)->sin_addr),
sizeof(struct in_addr));
ifa_free(&ia->ia_ifa);
cp[IPOPT_OFFSET] += sizeof(struct in_addr);
/*
* Let ip_intr's mcast routing check handle mcast pkts
*/
forward = !IN_MULTICAST(ntohl(ip->ip_dst.s_addr));
break;
case IPOPT_RR:
#ifdef IPSTEALTH
if (V_ipstealth && pass == 0)
break;
#endif
if (optlen < IPOPT_OFFSET + sizeof(*cp)) {
code = &cp[IPOPT_OFFSET] - (u_char *)ip;
goto bad;
}
if ((off = cp[IPOPT_OFFSET]) < IPOPT_MINOFF) {
code = &cp[IPOPT_OFFSET] - (u_char *)ip;
goto bad;
}
/*
* If no space remains, ignore.
*/
off--; /* 0 origin */
if (off > optlen - (int)sizeof(struct in_addr))
break;
(void)memcpy(&ipaddr.sin_addr, &ip->ip_dst,
sizeof(ipaddr.sin_addr));
/*
* Locate outgoing interface; if we're the
* destination, use the incoming interface (should be
* same).
*/
if ((ia = (INA)ifa_ifwithaddr((SA)&ipaddr)) == NULL &&
(ia = ip_rtaddr(ipaddr.sin_addr, M_GETFIB(m))) == NULL) {
type = ICMP_UNREACH;
code = ICMP_UNREACH_HOST;
goto bad;
}
(void)memcpy(cp + off, &(IA_SIN(ia)->sin_addr),
sizeof(struct in_addr));
ifa_free(&ia->ia_ifa);
cp[IPOPT_OFFSET] += sizeof(struct in_addr);
break;
case IPOPT_TS:
#ifdef IPSTEALTH
if (V_ipstealth && pass == 0)
break;
#endif
code = cp - (u_char *)ip;
if (optlen < 4 || optlen > 40) {
code = &cp[IPOPT_OLEN] - (u_char *)ip;
goto bad;
}
if ((off = cp[IPOPT_OFFSET]) < 5) {
code = &cp[IPOPT_OLEN] - (u_char *)ip;
goto bad;
}
if (off > optlen - (int)sizeof(int32_t)) {
cp[IPOPT_OFFSET + 1] += (1 << 4);
if ((cp[IPOPT_OFFSET + 1] & 0xf0) == 0) {
code = &cp[IPOPT_OFFSET] - (u_char *)ip;
goto bad;
}
break;
}
off--; /* 0 origin */
sin = (struct in_addr *)(cp + off);
switch (cp[IPOPT_OFFSET + 1] & 0x0f) {
case IPOPT_TS_TSONLY:
break;
case IPOPT_TS_TSANDADDR:
if (off + sizeof(uint32_t) +
sizeof(struct in_addr) > optlen) {
code = &cp[IPOPT_OFFSET] - (u_char *)ip;
goto bad;
}
ipaddr.sin_addr = dst;
ia = (INA)ifaof_ifpforaddr((SA)&ipaddr,
m->m_pkthdr.rcvif);
if (ia == NULL)
continue;
(void)memcpy(sin, &IA_SIN(ia)->sin_addr,
sizeof(struct in_addr));
ifa_free(&ia->ia_ifa);
cp[IPOPT_OFFSET] += sizeof(struct in_addr);
off += sizeof(struct in_addr);
break;
case IPOPT_TS_PRESPEC:
if (off + sizeof(uint32_t) +
sizeof(struct in_addr) > optlen) {
code = &cp[IPOPT_OFFSET] - (u_char *)ip;
goto bad;
}
(void)memcpy(&ipaddr.sin_addr, sin,
sizeof(struct in_addr));
if (ifa_ifwithaddr((SA)&ipaddr) == NULL)
continue;
cp[IPOPT_OFFSET] += sizeof(struct in_addr);
off += sizeof(struct in_addr);
break;
default:
code = &cp[IPOPT_OFFSET + 1] - (u_char *)ip;
goto bad;
}
ntime = iptime();
(void)memcpy(cp + off, &ntime, sizeof(uint32_t));
cp[IPOPT_OFFSET] += sizeof(uint32_t);
}
}
if (forward && V_ipforwarding) {
ip_forward(m, 1);
return (1);
}
return (0);
bad:
icmp_error(m, type, code, 0, 0);
IPSTAT_INC(ips_badoptions);
return (1);
}