route.c

Linux内核源代码 为压缩文件 是<<Linux内核>>一书中的源代码

		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==0 && res.type == RTN_UNICAST && key.oif == 0)
		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;

	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;
#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);
	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)) &&
		    ((key->tos&RTO_TPROXY) || !(rth->rt_flags&RTCF_TPROXY))
		) {
			rth->u.dst.lastuse = jiffies;
			dst_hold(&rth->u.dst);
			rth->u.dst.__use++;
			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);
}	

#ifdef CONFIG_RTNETLINK

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;
	struct nlmsghdr  *nlh;
	unsigned char	 *b = skb->tail;
	struct rta_cacheinfo ci;
#ifdef CONFIG_IP_MROUTE
	struct rtattr *eptr;
#endif

	nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*r));
	r = NLMSG_DATA(nlh);
	nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0;
	r->rtm_family = AF_INET;
	r->rtm_dst_len = 32;
	r->rtm_src_len = 0;
	r->rtm_tos = rt->key.tos;
	r->rtm_table = RT_TABLE_MAIN;
	r->rtm_type = rt->rt_type;
	r->rtm_scope = RT_SCOPE_UNIVERSE;
	r->rtm_protocol = RTPROT_UNSPEC;
	r->rtm_flags = (rt->rt_flags&~0xFFFF) | RTM_F_CLONED;
	if (rt->rt_flags & RTCF_NOTIFY)
		r->rtm_flags |= RTM_F_NOTIFY;
	RTA_PUT(skb, RTA_DST, 4, &rt->rt_dst);
	if (rt->key.src) {
		r->rtm_src_len = 32;
		RTA_PUT(skb, RTA_SRC, 4, &rt->key.src);
	}
	if (rt->u.dst.dev)
		RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->u.dst.dev->ifindex);
#ifdef CONFIG_NET_CLS_ROUTE
	if (rt->u.dst.tclassid)
		RTA_PUT(skb, RTA_FLOW, 4, &rt->u.dst.tclassid);
#endif
	if (rt->key.iif)
		RTA_PUT(skb, RTA_PREFSRC, 4, &rt->rt_spec_dst);
	else if (rt->rt_src != rt->key.src)
		RTA_PUT(skb, RTA_PREFSRC, 4, &rt->rt_src);
	if (rt->rt_dst != rt->rt_gateway)
		RTA_PUT(skb, RTA_GATEWAY, 4, &rt->rt_gateway);
	if (rtnetlink_put_metrics(skb, &rt->u.dst.mxlock) < 0)
		goto rtattr_failure;
	ci.rta_lastuse = jiffies - rt->u.dst.lastuse;
	ci.rta_used = rt->u.dst.__use;
	ci.rta_clntref = atomic_read(&rt->u.dst.__refcnt);
	if (rt->u.dst.expires)
		ci.rta_expires = rt->u.dst.expires - jiffies;
	else
		ci.rta_expires = 0;
	ci.rta_error = rt->u.dst.error;
	ci.rta_id = 0;
	ci.rta_ts = 0;
	ci.rta_tsage = 0;
	if (rt->peer) {
		ci.rta_id = rt->peer->ip_id_count;
		if (rt->peer->tcp_ts_stamp) {
			ci.rta_ts = rt->peer->tcp_ts;
			ci.rta_tsage = xtime.tv_sec - rt->peer->tcp_ts_stamp;
		}
	}
#ifdef CONFIG_IP_MROUTE
	eptr = (struct rtattr*)skb->tail;
#endif
	RTA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci);
	if (rt->key.iif) {
#ifdef CONFIG_IP_MROUTE
		u32 dst = rt->rt_dst;

		if (MULTICAST(dst) && !LOCAL_MCAST(dst) && ipv4_devconf.mc_forwarding) {
			int err = ipmr_get_route(skb, r, nowait);
			if (err <= 0) {
				if (!nowait) {
					if (err == 0)
						return 0;
					goto nlmsg_failure;
				} else {
					if (err == -EMSGSIZE)
						goto nlmsg_failure;
					((struct rta_cacheinfo*)RTA_DATA(eptr))->rta_error = err;
				}
			}
		} else
#endif
		{
			RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->key.iif);
		}
	}

	nlh->nlmsg_len = skb->tail - b;
	return skb->len;

nlmsg_failure:
rtattr_failure:
	skb_trim(skb, b - skb->data);
	return -1;
}

int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
{
	struct rtattr **rta = arg;
	struct rtmsg *rtm = NLMSG_DATA(nlh);
	struct rtable *rt = NULL;
	u32 dst = 0;
	u32 src = 0;
	int iif = 0;
	int err;
	struct sk_buff *skb;

	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
	if (skb == NULL)
		return -ENOBUFS;

	/* Reserve room for dummy headers, this skb can pass
	   through good chunk of routing engine.
	 */
	skb->mac.raw = skb->data;
	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));

	if (rta[RTA_SRC-1])
		memcpy(&src, RTA_DATA(rta[RTA_SRC-1]), 4);
	if (rta[RTA_DST-1])
		memcpy(&dst, RTA_DATA(rta[RTA_DST-1]), 4);
	if (rta[RTA_IIF-1])
		memcpy(&iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int));

	if (iif) {
		struct net_device *dev;
		dev = __dev_get_by_index(iif);
		if (!dev)
			return -ENODEV;
		skb->protocol = __constant_htons(ETH_P_IP);
		skb->dev = dev;
		local_bh_disable();
		err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev);
		local_bh_enable();
		rt = (struct rtable*)skb->dst;
		if (!err && rt->u.dst.error)
			err = -rt->u.dst.error;
	} else {
		int oif = 0;
		if (rta[RTA_OIF-1])
			memcpy(&oif, RTA_DATA(rta[RTA_OIF-1]), sizeof(int));
		err = ip_route_output(&rt, dst, src, rtm->rtm_tos, oif);
	}
	if (err) {
		kfree_skb(skb);
		return err;
	}

	skb->dst = &rt->u.dst;
	if (rtm->rtm_flags & RTM_F_NOTIFY)
		rt->rt_flags |= RTCF_NOTIFY;

	NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid;

	err = rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, RTM_NEWROUTE, 0);
	if (err == 0)
		return 0;
	if (err < 0)
		return -EMSGSIZE;

	err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT);
	if (err < 0)
		return err;
	return 0;
}


int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
{
	struct rtable *rt;
	int h, s_h;
	int idx, s_idx;

	s_h = cb->args[0];
	s_idx = idx = cb->args[1];
	for (h=0; h <= rt_hash_mask; h++) {
		if (h < s_h) continue;
		if (h > s_h)
			s_idx = 0;
		read_lock_bh(&rt_hash_table[h].lock);
		for (rt = rt_hash_table[h].chain, idx = 0; rt; rt = rt->u.rt_next, idx++) {
			if (idx < s_idx)
				continue;
			skb->dst = dst_clone(&rt->u.dst);
			if (rt_fill_info(skb, NETLINK_CB(cb->skb).pid,
					 cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1) <= 0) {
				dst_release(xchg(&skb->dst, NULL));
				read_unlock_bh(&rt_hash_table[h].lock);
				goto done;
			}
			dst_release(xchg(&skb->dst, NULL));
		}
		read_unlock_bh(&rt_hash_table[h].lock);
	}

done:
	cb->args[0] = h;
	cb->args[1] = idx;
	return skb->len;
}

#endif /* CONFIG_RTNETLINK */

void ip_rt_multicast_event(struct in_device *in_dev)
{
	rt_cache_flush(0);
}



#ifdef CONFIG_SYSCTL

static int flush_delay;

static
int ipv4_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp,
			      void *buffer, size_t *lenp)
{
	if (write) {
		proc_dointvec(ctl, write, filp, buffer, lenp);
		rt_cache_flush(flush_delay);
		return 0;
	} else
		return -EINVAL;
}

static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table, int *name, int nlen,
			 void *oldval, size_t *oldlenp,
			 void *newval, size_t newlen, 
			 void **context)
{
	int delay;
	if (newlen != sizeof(int))
		return -EINVAL;
	if (get_user(delay,(int *)newval))
		return -EFAULT; 
	rt_cache_flush(delay); 
	return 0;
}

ctl_table ipv4_route_table[] = {
        {NET_IPV4_ROUTE_FLUSH, "flush",
         &flush_delay, sizeof(int), 0644, NULL,
         &ipv4_sysctl_rtcache_flush, &ipv4_sysctl_rtcache_flush_strategy },
	{NET_IPV4_ROUTE_MIN_DELAY, "min_delay",
         &ip_rt_min_delay, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_MAX_DELAY, "max_delay",
         &ip_rt_max_delay, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_GC_THRESH, "gc_thresh",
         &ipv4_dst_ops.gc_thresh, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_MAX_SIZE, "max_size",
         &ip_rt_max_size, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_GC_MIN_INTERVAL, "gc_min_interval",
         &ip_rt_gc_min_interval, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_GC_TIMEOUT, "gc_timeout",
         &ip_rt_gc_timeout, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_GC_INTERVAL, "gc_interval",
         &ip_rt_gc_interval, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_REDIRECT_LOAD, "redirect_load",
         &ip_rt_redirect_load, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_REDIRECT_NUMBER, "redirect_number",
         &ip_rt_redirect_number, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_REDIRECT_SILENCE, "redirect_silence",
         &ip_rt_redirect_silence, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_ERROR_COST, "error_cost",
         &ip_rt_error_cost, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_ERROR_BURST, "error_burst",
         &ip_rt_error_burst, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_GC_ELASTICITY, "gc_elasticity",
         &ip_rt_gc_elasticity, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_MTU_EXPIRES, "mtu_expires",
         &ip_rt_mtu_expires, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_MIN_PMTU, "min_pmtu",
         &ip_rt_min_pmtu, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_MIN_ADVMSS, "min_adv_mss",
         &ip_rt_min_advmss, sizeof(int), 0644, NULL,
         &proc_dointvec},
	 {0}
};
#endif

#ifdef CONFIG_NET_CLS_ROUTE
struct ip_rt_acct *ip_rt_acct;

static int ip_rt_acct_read(char *buffer, char **start, off_t offset,
			   int length, int *eof, void *data)
{
	*start=buffer;

	if ((offset&3) || (length&3))
		return -EIO;

	if (offset + length >= sizeof(struct ip_rt_acct)*256) {
		length = sizeof(struct ip_rt_acct)*256 - offset;
		*eof = 1;
	}
	if (length > 0) {
		u32 *dst = (u32*)buffer;
		u32 *src = (u32*)(((u8*)ip_rt_acct) + offset);

		memcpy(dst, src, length);

#ifdef CONFIG_SMP
		if (smp_num_cpus > 1 || cpu_logical_map(0) != 0) {
			int i;
			int cnt = length/4;

			for (i=0; i<smp_num_cpus; i++) {
				int cpu = cpu_logical_map(i);
				int k;

				if (cpu == 0)
					continue;

				src = (u32*)(((u8*)ip_rt_acct) + offset +
					     cpu*256*sizeof(struct ip_rt_acct));

				for (k=0; k<cnt; k++)
					dst[k] += src[k];
			}
		}
#endif
		return length;
	}
	return 0;
}
#endif

void __init ip_rt_init(void)
{
	int i, order, goal;

#ifdef CONFIG_NET_CLS_ROUTE
	for (order=0;
	     (PAGE_SIZE<<order) < 256*sizeof(ip_rt_acct)*NR_CPUS; order++)
		/* NOTHING */;
	ip_rt_acct = (struct ip_rt_acct *)__get_free_pages(GFP_KERNEL, order);
	if (!ip_rt_acct)
		panic("IP: failed to allocate ip_rt_acct\n");
	memset(ip_rt_acct, 0, PAGE_SIZE<<order);
#endif

	ipv4_dst_ops.kmem_cachep = kmem_cache_create("ip_dst_cache",
						     sizeof(struct rtable),
						     0, SLAB_HWCACHE_ALIGN,
						     NULL, NULL);

	if (!ipv4_dst_ops.kmem_cachep)
		panic("IP: failed to allocate ip_dst_cache\n");

	goal = num_physpages >> (26 - PAGE_SHIFT);

	for (order = 0; (1UL << order) < goal; order++)
		/* NOTHING */;

	do {
		rt_hash_mask = (1UL << order) * PAGE_SIZE /
			sizeof(struct rt_hash_bucket);
		while (rt_hash_mask & (rt_hash_mask-1))
			rt_hash_mask--;
		rt_hash_table = (struct rt_hash_bucket *)
			__get_free_pages(GFP_ATOMIC, order);
	} while (rt_hash_table == NULL && --order > 0);

	if (!rt_hash_table)
		panic("Failed to allocate IP route cache hash table\n");

	printk("IP: routing cache hash table of %u buckets, %ldKbytes\n",
	       rt_hash_mask,
	       (long) (rt_hash_mask*sizeof(struct rt_hash_bucket))/1024);

	for (rt_hash_log=0; (1<<rt_hash_log) != rt_hash_mask; rt_hash_log++)
		/* NOTHING */;

	rt_hash_mask--;
	for (i = 0; i <= rt_hash_mask; i++) {
		rt_hash_table[i].lock = RW_LOCK_UNLOCKED;
		rt_hash_table[i].chain = NULL;
	}

	ipv4_dst_ops.gc_thresh = (rt_hash_mask+1);
	ip_rt_max_size = (rt_hash_mask+1)*16;

	devinet_init();
	ip_fib_init();

	rt_flush_timer.function = rt_run_flush;
	rt_periodic_timer.function = rt_check_expire;

	/* All the timers, started at system startup tend
	   to synchronize. Perturb it a bit.
	 */
	rt_periodic_timer.expires = jiffies + net_random()%ip_rt_gc_interval
		+ ip_rt_gc_interval;
	add_timer(&rt_periodic_timer);

	proc_net_create ("rt_cache", 0, rt_cache_get_info);
#ifdef CONFIG_NET_CLS_ROUTE
	create_proc_read_entry("net/rt_acct", 0, 0, ip_rt_acct_read, NULL);
#endif
}