route.c

《嵌入式系统设计与实例开发实验教材二源码》Linux内核移植与编译实验

	else {
		err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
					  &itag);
		if (err < 0)
			goto martian_source;
		if (err)
			flags |= RTCF_DIRECTSRC;
	}
	flags |= RTCF_BROADCAST;
	res.type = RTN_BROADCAST;
	rt_cache_stat[smp_processor_id()].in_brd++;

local_input:
	rth = dst_alloc(&ipv4_dst_ops);
	if (!rth)
		goto e_nobufs;

	rth->u.dst.output= ip_rt_bug;

	atomic_set(&rth->u.dst.__refcnt, 1);
	rth->u.dst.flags= DST_HOST;
	rth->key.dst	= daddr;
	rth->rt_dst	= daddr;
	rth->key.tos	= tos;
#ifdef CONFIG_IP_ROUTE_FWMARK
	rth->key.fwmark	= skb->nfmark;
#endif
	rth->key.src	= saddr;
	rth->rt_src	= saddr;
#ifdef CONFIG_IP_ROUTE_NAT
	rth->rt_dst_map	= key.dst;
	rth->rt_src_map	= key.src;
#endif
#ifdef CONFIG_NET_CLS_ROUTE
	rth->u.dst.tclassid = itag;
#endif
	rth->rt_iif	=
	rth->key.iif	= dev->ifindex;
	rth->u.dst.dev	= &loopback_dev;
	dev_hold(rth->u.dst.dev);
	rth->key.oif 	= 0;
	rth->rt_gateway	= daddr;
	rth->rt_spec_dst= spec_dst;
	rth->u.dst.input= ip_local_deliver;
	rth->rt_flags 	= flags|RTCF_LOCAL;
	if (res.type == RTN_UNREACHABLE) {
		rth->u.dst.input= ip_error;
		rth->u.dst.error= -err;
		rth->rt_flags 	&= ~RTCF_LOCAL;
	}
	rth->rt_type	= res.type;
	goto intern;

no_route:
	rt_cache_stat[smp_processor_id()].in_no_route++;
	spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
	res.type = RTN_UNREACHABLE;
	goto local_input;

	/*
	 *	Do not cache martian addresses: they should be logged (RFC1812)
	 */
martian_destination:
	rt_cache_stat[smp_processor_id()].in_martian_dst++;
#ifdef CONFIG_IP_ROUTE_VERBOSE
	if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
		printk(KERN_WARNING "martian destination %u.%u.%u.%u from "
			"%u.%u.%u.%u, dev %s\n",
			NIPQUAD(daddr), NIPQUAD(saddr), dev->name);
#endif
e_inval:
	err = -EINVAL;
	goto done;

e_nobufs:
	err = -ENOBUFS;
	goto done;

martian_source:

	rt_cache_stat[smp_processor_id()].in_martian_src++;
#ifdef CONFIG_IP_ROUTE_VERBOSE
	if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) {
		/*
		 *	RFC1812 recommendation, if source is martian,
		 *	the only hint is MAC header.
		 */
		printk(KERN_WARNING "martian source %u.%u.%u.%u from "
			"%u.%u.%u.%u, on dev %s\n",
			NIPQUAD(daddr), NIPQUAD(saddr), dev->name);
		if (dev->hard_header_len) {
			int i;
			unsigned char *p = skb->mac.raw;
			printk(KERN_WARNING "ll header: ");
			for (i = 0; i < dev->hard_header_len; i++, p++) {
				printk("%02x", *p);
				if (i < (dev->hard_header_len - 1))
					printk(":");
			}
			printk("\n");
		}
	}
#endif
	goto e_inval;
}

int ip_route_input(struct sk_buff *skb, u32 daddr, u32 saddr,
		   u8 tos, struct net_device *dev)
{
	struct rtable * rth;
	unsigned	hash;
	int iif = dev->ifindex;

	tos &= IPTOS_RT_MASK;
	hash = rt_hash_code(daddr, saddr ^ (iif << 5), tos);

	read_lock(&rt_hash_table[hash].lock);
	for (rth = rt_hash_table[hash].chain; rth; rth = rth->u.rt_next) {
		if (rth->key.dst == daddr &&
		    rth->key.src == saddr &&
		    rth->key.iif == iif &&
		    rth->key.oif == 0 &&
#ifdef CONFIG_IP_ROUTE_FWMARK
		    rth->key.fwmark == skb->nfmark &&
#endif
		    rth->key.tos == tos) {
			rth->u.dst.lastuse = jiffies;
			dst_hold(&rth->u.dst);
			rth->u.dst.__use++;
			rt_cache_stat[smp_processor_id()].in_hit++;
			read_unlock(&rt_hash_table[hash].lock);
			skb->dst = (struct dst_entry*)rth;
			return 0;
		}
	}
	read_unlock(&rt_hash_table[hash].lock);

	/* Multicast recognition logic is moved from route cache to here.
	   The problem was that too many Ethernet cards have broken/missing
	   hardware multicast filters :-( As result the host on multicasting
	   network acquires a lot of useless route cache entries, sort of
	   SDR messages from all the world. Now we try to get rid of them.
	   Really, provided software IP multicast filter is organized
	   reasonably (at least, hashed), it does not result in a slowdown
	   comparing with route cache reject entries.
	   Note, that multicast routers are not affected, because
	   route cache entry is created eventually.
	 */
	if (MULTICAST(daddr)) {
		struct in_device *in_dev;

		read_lock(&inetdev_lock);
		if ((in_dev = __in_dev_get(dev)) != NULL) {
			int our = ip_check_mc(in_dev, daddr);
			if (our
#ifdef CONFIG_IP_MROUTE
			    || (!LOCAL_MCAST(daddr) && IN_DEV_MFORWARD(in_dev))
#endif
			    ) {
				read_unlock(&inetdev_lock);
				return ip_route_input_mc(skb, daddr, saddr,
							 tos, dev, our);
			}
		}
		read_unlock(&inetdev_lock);
		return -EINVAL;
	}
	return ip_route_input_slow(skb, daddr, saddr, tos, dev);
}

/*
 * Major route resolver routine.
 */

int ip_route_output_slow(struct rtable **rp, const struct rt_key *oldkey)
{
	struct rt_key key;
	struct fib_result res;
	unsigned flags = 0;
	struct rtable *rth;
	struct net_device *dev_out = NULL;
	unsigned hash;
	int free_res = 0;
	int err;
	u32 tos;

	tos		= oldkey->tos & (IPTOS_RT_MASK | RTO_ONLINK);
	key.dst		= oldkey->dst;
	key.src		= oldkey->src;
	key.tos		= tos & IPTOS_RT_MASK;
	key.iif		= loopback_dev.ifindex;
	key.oif		= oldkey->oif;
#ifdef CONFIG_IP_ROUTE_FWMARK
	key.fwmark	= oldkey->fwmark;
#endif
	key.scope	= (tos & RTO_ONLINK) ? RT_SCOPE_LINK :
						RT_SCOPE_UNIVERSE;
	res.fi		= NULL;
#ifdef CONFIG_IP_MULTIPLE_TABLES
	res.r		= NULL;
#endif

	if (oldkey->src) {
		err = -EINVAL;
		if (MULTICAST(oldkey->src) ||
		    BADCLASS(oldkey->src) ||
		    ZERONET(oldkey->src))
			goto out;

		/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
		dev_out = ip_dev_find(oldkey->src);
		if (dev_out == NULL)
			goto out;

		/* I removed check for oif == dev_out->oif here.
		   It was wrong by three reasons:
		   1. ip_dev_find(saddr) can return wrong iface, if saddr is
		      assigned to multiple interfaces.
		   2. Moreover, we are allowed to send packets with saddr
		      of another iface. --ANK
		 */

		if (oldkey->oif == 0
		    && (MULTICAST(oldkey->dst) || oldkey->dst == 0xFFFFFFFF)) {
			/* Special hack: user can direct multicasts
			   and limited broadcast via necessary interface
			   without fiddling with IP_MULTICAST_IF or IP_PKTINFO.
			   This hack is not just for fun, it allows
			   vic,vat and friends to work.
			   They bind socket to loopback, set ttl to zero
			   and expect that it will work.
			   From the viewpoint of routing cache they are broken,
			   because we are not allowed to build multicast path
			   with loopback source addr (look, routing cache
			   cannot know, that ttl is zero, so that packet
			   will not leave this host and route is valid).
			   Luckily, this hack is good workaround.
			 */

			key.oif = dev_out->ifindex;
			goto make_route;
		}
		if (dev_out)
			dev_put(dev_out);
		dev_out = NULL;
	}
	if (oldkey->oif) {
		dev_out = dev_get_by_index(oldkey->oif);
		err = -ENODEV;
		if (dev_out == NULL)
			goto out;
		if (__in_dev_get(dev_out) == NULL) {
			dev_put(dev_out);
			goto out;	/* Wrong error code */
		}

		if (LOCAL_MCAST(oldkey->dst) || oldkey->dst == 0xFFFFFFFF) {
			if (!key.src)
				key.src = inet_select_addr(dev_out, 0,
								RT_SCOPE_LINK);
			goto make_route;
		}
		if (!key.src) {
			if (MULTICAST(oldkey->dst))
				key.src = inet_select_addr(dev_out, 0,
								key.scope);
			else if (!oldkey->dst)
				key.src = inet_select_addr(dev_out, 0,
								RT_SCOPE_HOST);
		}
	}

	if (!key.dst) {
		key.dst = key.src;
		if (!key.dst)
			key.dst = key.src = htonl(INADDR_LOOPBACK);
		if (dev_out)
			dev_put(dev_out);
		dev_out = &loopback_dev;
		dev_hold(dev_out);
		key.oif = loopback_dev.ifindex;
		res.type = RTN_LOCAL;
		flags |= RTCF_LOCAL;
		goto make_route;
	}

	if (fib_lookup(&key, &res)) {
		res.fi = NULL;
		if (oldkey->oif) {
			/* Apparently, routing tables are wrong. Assume,
			   that the destination is on link.

			   WHY? DW.
			   Because we are allowed to send to iface
			   even if it has NO routes and NO assigned
			   addresses. When oif is specified, routing
			   tables are looked up with only one purpose:
			   to catch if destination is gatewayed, rather than
			   direct. Moreover, if MSG_DONTROUTE is set,
			   we send packet, ignoring both routing tables
			   and ifaddr state. --ANK


			   We could make it even if oif is unknown,
			   likely IPv6, but we do not.
			 */

			if (key.src == 0)
				key.src = inet_select_addr(dev_out, 0,
							   RT_SCOPE_LINK);
			res.type = RTN_UNICAST;
			goto make_route;
		}
		if (dev_out)
			dev_put(dev_out);
		err = -ENETUNREACH;
		goto out;
	}
	free_res = 1;

	if (res.type == RTN_NAT)
		goto e_inval;

	if (res.type == RTN_LOCAL) {
		if (!key.src)
			key.src = key.dst;
		if (dev_out)
			dev_put(dev_out);
		dev_out = &loopback_dev;
		dev_hold(dev_out);
		key.oif = dev_out->ifindex;
		if (res.fi)
			fib_info_put(res.fi);
		res.fi = NULL;
		flags |= RTCF_LOCAL;
		goto make_route;
	}

#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (res.fi->fib_nhs > 1 && key.oif == 0)
		fib_select_multipath(&key, &res);
	else
#endif
	if (!res.prefixlen && res.type == RTN_UNICAST && !key.oif)
		fib_select_default(&key, &res);

	if (!key.src)
		key.src = FIB_RES_PREFSRC(res);

	if (dev_out)
		dev_put(dev_out);
	dev_out = FIB_RES_DEV(res);
	dev_hold(dev_out);
	key.oif = dev_out->ifindex;

make_route:
	if (LOOPBACK(key.src) && !(dev_out->flags&IFF_LOOPBACK))
		goto e_inval;

	if (key.dst == 0xFFFFFFFF)
		res.type = RTN_BROADCAST;
	else if (MULTICAST(key.dst))
		res.type = RTN_MULTICAST;
	else if (BADCLASS(key.dst) || ZERONET(key.dst))
		goto e_inval;

	if (dev_out->flags & IFF_LOOPBACK)
		flags |= RTCF_LOCAL;

	if (res.type == RTN_BROADCAST) {
		flags |= RTCF_BROADCAST | RTCF_LOCAL;
		if (res.fi) {
			fib_info_put(res.fi);
			res.fi = NULL;
		}
	} else if (res.type == RTN_MULTICAST) {
		flags |= RTCF_MULTICAST|RTCF_LOCAL;
		read_lock(&inetdev_lock);
		if (!__in_dev_get(dev_out) ||
		    !ip_check_mc(__in_dev_get(dev_out), oldkey->dst))
			flags &= ~RTCF_LOCAL;
		read_unlock(&inetdev_lock);
		/* If multicast route do not exist use
		   default one, but do not gateway in this case.
		   Yes, it is hack.
		 */
		if (res.fi && res.prefixlen < 4) {
			fib_info_put(res.fi);
			res.fi = NULL;
		}
	}

	rth = dst_alloc(&ipv4_dst_ops);
	if (!rth)
		goto e_nobufs;

	atomic_set(&rth->u.dst.__refcnt, 1);
	rth->u.dst.flags= DST_HOST;
	rth->key.dst	= oldkey->dst;
	rth->key.tos	= tos;
	rth->key.src	= oldkey->src;
	rth->key.iif	= 0;
	rth->key.oif	= oldkey->oif;
#ifdef CONFIG_IP_ROUTE_FWMARK
	rth->key.fwmark	= oldkey->fwmark;
#endif
	rth->rt_dst	= key.dst;
	rth->rt_src	= key.src;
#ifdef CONFIG_IP_ROUTE_NAT
	rth->rt_dst_map	= key.dst;
	rth->rt_src_map	= key.src;
#endif
	rth->rt_iif	= oldkey->oif ? : dev_out->ifindex;
	rth->u.dst.dev	= dev_out;
	dev_hold(dev_out);
	rth->rt_gateway = key.dst;
	rth->rt_spec_dst= key.src;

	rth->u.dst.output=ip_output;

	rt_cache_stat[smp_processor_id()].out_slow_tot++;

	if (flags & RTCF_LOCAL) {
		rth->u.dst.input = ip_local_deliver;
		rth->rt_spec_dst = key.dst;
	}
	if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
		rth->rt_spec_dst = key.src;
		if (flags & RTCF_LOCAL && !(dev_out->flags & IFF_LOOPBACK)) {
			rth->u.dst.output = ip_mc_output;
			rt_cache_stat[smp_processor_id()].out_slow_mc++;
		}
#ifdef CONFIG_IP_MROUTE
		if (res.type == RTN_MULTICAST) {
			struct in_device *in_dev = in_dev_get(dev_out);
			if (in_dev) {
				if (IN_DEV_MFORWARD(in_dev) &&
				    !LOCAL_MCAST(oldkey->dst)) {
					rth->u.dst.input = ip_mr_input;
					rth->u.dst.output = ip_mc_output;
				}
				in_dev_put(in_dev);
			}
		}
#endif
	}

	rt_set_nexthop(rth, &res, 0);

	rth->rt_flags = flags;

	hash = rt_hash_code(oldkey->dst, oldkey->src ^ (oldkey->oif << 5), tos);
	err = rt_intern_hash(hash, rth, rp);
done:
	if (free_res)
		fib_res_put(&res);
	if (dev_out)
		dev_put(dev_out);
out:	return err;

e_inval:
	err = -EINVAL;
	goto done;
e_nobufs:
	err = -ENOBUFS;
	goto done;
}

int ip_route_output_key(struct rtable **rp, const struct rt_key *key)
{
	unsigned hash;
	struct rtable *rth;

	hash = rt_hash_code(key->dst, key->src ^ (key->oif << 5), key->tos);

	read_lock_bh(&rt_hash_table[hash].lock);
	for (rth = rt_hash_table[hash].chain; rth; rth = rth->u.rt_next) {
		if (rth->key.dst == key->dst &&
		    rth->key.src == key->src &&
		    rth->key.iif == 0 &&
		    rth->key.oif == key->oif &&
#ifdef CONFIG_IP_ROUTE_FWMARK
		    rth->key.fwmark == key->fwmark &&
#endif
		    !((rth->key.tos ^ key->tos) &
			    (IPTOS_RT_MASK | RTO_ONLINK))) {
			rth->u.dst.lastuse = jiffies;
			dst_hold(&rth->u.dst);
			rth->u.dst.__use++;
			rt_cache_stat[smp_processor_id()].out_hit++;
			read_unlock_bh(&rt_hash_table[hash].lock);
			*rp = rth;
			return 0;
		}
	}
	read_unlock_bh(&rt_hash_table[hash].lock);

	return ip_route_output_slow(rp, key);
}	

static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
			int nowait)
{
	struct rtable *rt = (struct rtable*)skb->dst;
	struct rtmsg *r;