ipmr.c

Linux内核源代码 为压缩文件 是<<Linux内核>>一书中的源代码

		skb2 = skb_realloc_headroom(skb, (encap + 15)&~15);
	else if (atomic_read(&skb->users) != 1)
		skb2 = skb_clone(skb, GFP_ATOMIC);
	else {
		atomic_inc(&skb->users);
		skb2 = skb;
	}

	if (skb2 == NULL) {
		ip_rt_put(rt);
		return;
	}

	vif->pkt_out++;
	vif->bytes_out+=skb->len;

	dst_release(skb2->dst);
	skb2->dst = &rt->u.dst;
	iph = skb2->nh.iph;
	ip_decrease_ttl(iph);

	/* FIXME: forward and output firewalls used to be called here.
	 * What do we do with netfilter? -- RR */
	if (vif->flags & VIFF_TUNNEL) {
		ip_encap(skb2, vif->local, vif->remote);
		/* FIXME: extra output firewall step used to be here. --RR */
		((struct ip_tunnel *)vif->dev->priv)->stat.tx_packets++;
		((struct ip_tunnel *)vif->dev->priv)->stat.tx_bytes+=skb2->len;
	}

	IPCB(skb2)->flags |= IPSKB_FORWARDED;

	/*
	 * RFC1584 teaches, that DVMRP/PIM router must deliver packets locally
	 * not only before forwarding, but after forwarding on all output
	 * interfaces. It is clear, if mrouter runs a multicasting
	 * program, it should receive packets not depending to what interface
	 * program is joined.
	 * If we will not make it, the program will have to join on all
	 * interfaces. On the other hand, multihoming host (or router, but
	 * not mrouter) cannot join to more than one interface - it will
	 * result in receiving multiple packets.
	 */
	NF_HOOK(PF_INET, NF_IP_FORWARD, skb2, skb->dev, dev, 
		ipmr_forward_finish);
}

int ipmr_find_vif(struct net_device *dev)
{
	int ct;
	for (ct=maxvif-1; ct>=0; ct--) {
		if (vif_table[ct].dev == dev)
			break;
	}
	return ct;
}

/* "local" means that we should preserve one skb (for local delivery) */

int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local)
{
	int psend = -1;
	int vif, ct;

	vif = cache->mfc_parent;
	cache->mfc_un.res.pkt++;
	cache->mfc_un.res.bytes += skb->len;

	/*
	 * Wrong interface: drop packet and (maybe) send PIM assert.
	 */
	if (vif_table[vif].dev != skb->dev) {
		int true_vifi;

		if (((struct rtable*)skb->dst)->key.iif == 0) {
			/* It is our own packet, looped back.
			   Very complicated situation...

			   The best workaround until routing daemons will be
			   fixed is not to redistribute packet, if it was
			   send through wrong interface. It means, that
			   multicast applications WILL NOT work for
			   (S,G), which have default multicast route pointing
			   to wrong oif. In any case, it is not a good
			   idea to use multicasting applications on router.
			 */
			goto dont_forward;
		}

		cache->mfc_un.res.wrong_if++;
		true_vifi = ipmr_find_vif(skb->dev);

		if (true_vifi >= 0 && mroute_do_assert &&
		    /* pimsm uses asserts, when switching from RPT to SPT,
		       so that we cannot check that packet arrived on an oif.
		       It is bad, but otherwise we would need to move pretty
		       large chunk of pimd to kernel. Ough... --ANK
		     */
		    (mroute_do_pim || cache->mfc_un.res.ttls[true_vifi] < 255) &&
		    jiffies - cache->mfc_un.res.last_assert > MFC_ASSERT_THRESH) {
			cache->mfc_un.res.last_assert = jiffies;
			ipmr_cache_report(skb, true_vifi, IGMPMSG_WRONGVIF);
		}
		goto dont_forward;
	}

	vif_table[vif].pkt_in++;
	vif_table[vif].bytes_in+=skb->len;

	/*
	 *	Forward the frame
	 */
	for (ct = cache->mfc_un.res.maxvif-1; ct >= cache->mfc_un.res.minvif; ct--) {
		if (skb->nh.iph->ttl > cache->mfc_un.res.ttls[ct]) {
			if (psend != -1)
				ipmr_queue_xmit(skb, cache, psend, 0);
			psend=ct;
		}
	}
	if (psend != -1)
		ipmr_queue_xmit(skb, cache, psend, !local);

dont_forward:
	if (!local)
		kfree_skb(skb);
	return 0;
}


/*
 *	Multicast packets for forwarding arrive here
 */

int ip_mr_input(struct sk_buff *skb)
{
	struct mfc_cache *cache;
	int local = ((struct rtable*)skb->dst)->rt_flags&RTCF_LOCAL;

	/* Packet is looped back after forward, it should not be
	   forwarded second time, but still can be delivered locally.
	 */
	if (IPCB(skb)->flags&IPSKB_FORWARDED)
		goto dont_forward;

	if (!local) {
		    if (IPCB(skb)->opt.router_alert) {
			    if (ip_call_ra_chain(skb))
				    return 0;
		    } else if (skb->nh.iph->protocol == IPPROTO_IGMP){
			    /* IGMPv1 (and broken IGMPv2 implementations sort of
			       Cisco IOS <= 11.2(8)) do not put router alert
			       option to IGMP packets destined to routable
			       groups. It is very bad, because it means
			       that we can forward NO IGMP messages.
			     */
			    read_lock(&mrt_lock);
			    if (mroute_socket) {
				    raw_rcv(mroute_socket, skb);
				    read_unlock(&mrt_lock);
				    return 0;
			    }
			    read_unlock(&mrt_lock);
		    }
	}

	read_lock(&mrt_lock);
	cache = ipmr_cache_find(skb->nh.iph->saddr, skb->nh.iph->daddr);

	/*
	 *	No usable cache entry
	 */
	if (cache==NULL) {
		int vif;

		if (local) {
			struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
			ip_local_deliver(skb);
			if (skb2 == NULL) {
				read_unlock(&mrt_lock);
				return -ENOBUFS;
			}
			skb = skb2;
		}

		vif = ipmr_find_vif(skb->dev);
		if (vif >= 0) {
			int err = ipmr_cache_unresolved(vif, skb);
			read_unlock(&mrt_lock);

			return err;
		}
		read_unlock(&mrt_lock);
		kfree_skb(skb);
		return -ENODEV;
	}

	ip_mr_forward(skb, cache, local);

	read_unlock(&mrt_lock);

	if (local)
		return ip_local_deliver(skb);

	return 0;

dont_forward:
	if (local)
		return ip_local_deliver(skb);
	kfree_skb(skb);
	return 0;
}

#ifdef CONFIG_IP_PIMSM_V1
/*
 * Handle IGMP messages of PIMv1
 */

int pim_rcv_v1(struct sk_buff * skb, unsigned short len)
{
	struct igmphdr *pim = (struct igmphdr*)skb->h.raw;
	struct iphdr   *encap;
	struct net_device  *reg_dev = NULL;

        if (!mroute_do_pim ||
	    len < sizeof(*pim) + sizeof(*encap) ||
	    pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER) {
		kfree_skb(skb);
                return -EINVAL;
        }

	encap = (struct iphdr*)(skb->h.raw + sizeof(struct igmphdr));
	/*
	   Check that:
	   a. packet is really destinted to a multicast group
	   b. packet is not a NULL-REGISTER
	   c. packet is not truncated
	 */
	if (!MULTICAST(encap->daddr) ||
	    ntohs(encap->tot_len) == 0 ||
	    ntohs(encap->tot_len) + sizeof(*pim) > len) {
		kfree_skb(skb);
		return -EINVAL;
	}

	read_lock(&mrt_lock);
	if (reg_vif_num >= 0)
		reg_dev = vif_table[reg_vif_num].dev;
	if (reg_dev)
		dev_hold(reg_dev);
	read_unlock(&mrt_lock);

	if (reg_dev == NULL) {
		kfree_skb(skb);
		return -EINVAL;
	}

	skb->mac.raw = skb->nh.raw;
	skb_pull(skb, (u8*)encap - skb->data);
	skb->nh.iph = (struct iphdr *)skb->data;
	skb->dev = reg_dev;
	memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
	skb->protocol = __constant_htons(ETH_P_IP);
	skb->ip_summed = 0;
	skb->pkt_type = PACKET_HOST;
	dst_release(skb->dst);
	skb->dst = NULL;
	((struct net_device_stats*)reg_dev->priv)->rx_bytes += skb->len;
	((struct net_device_stats*)reg_dev->priv)->rx_packets++;
#ifdef CONFIG_NETFILTER
	nf_conntrack_put(skb->nfct);
	skb->nfct = NULL;
#endif
	netif_rx(skb);
	dev_put(reg_dev);
	return 0;
}
#endif

#ifdef CONFIG_IP_PIMSM_V2
int pim_rcv(struct sk_buff * skb, unsigned short len)
{
	struct pimreghdr *pim = (struct pimreghdr*)skb->h.raw;
	struct iphdr   *encap;
	struct net_device  *reg_dev = NULL;

        if (len < sizeof(*pim) + sizeof(*encap) ||
	    pim->type != ((PIM_VERSION<<4)|(PIM_REGISTER)) ||
	    (pim->flags&PIM_NULL_REGISTER) ||
	    (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 &&
	     ip_compute_csum((void *)pim, len))) {
		kfree_skb(skb);
                return -EINVAL;
        }

	/* check if the inner packet is destined to mcast group */
	encap = (struct iphdr*)(skb->h.raw + sizeof(struct pimreghdr));
	if (!MULTICAST(encap->daddr) ||
	    ntohs(encap->tot_len) == 0 ||
	    ntohs(encap->tot_len) + sizeof(*pim) > len) {
		kfree_skb(skb);
		return -EINVAL;
	}

	read_lock(&mrt_lock);
	if (reg_vif_num >= 0)
		reg_dev = vif_table[reg_vif_num].dev;
	if (reg_dev)
		dev_hold(reg_dev);
	read_unlock(&mrt_lock);

	if (reg_dev == NULL) {
		kfree_skb(skb);
		return -EINVAL;
	}

	skb->mac.raw = skb->nh.raw;
	skb_pull(skb, (u8*)encap - skb->data);
	skb->nh.iph = (struct iphdr *)skb->data;
	skb->dev = reg_dev;
	memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
	skb->protocol = __constant_htons(ETH_P_IP);
	skb->ip_summed = 0;
	skb->pkt_type = PACKET_HOST;
	dst_release(skb->dst);
	((struct net_device_stats*)reg_dev->priv)->rx_bytes += skb->len;
	((struct net_device_stats*)reg_dev->priv)->rx_packets++;
	skb->dst = NULL;
#ifdef CONFIG_NETFILTER
	nf_conntrack_put(skb->nfct);
	skb->nfct = NULL;
#endif
	netif_rx(skb);
	dev_put(reg_dev);
	return 0;
}
#endif

#ifdef CONFIG_RTNETLINK

static int
ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm)
{
	int ct;
	struct rtnexthop *nhp;
	struct net_device *dev = vif_table[c->mfc_parent].dev;
	u8 *b = skb->tail;
	struct rtattr *mp_head;

	if (dev)
		RTA_PUT(skb, RTA_IIF, 4, &dev->ifindex);

	mp_head = (struct rtattr*)skb_put(skb, RTA_LENGTH(0));

	for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
		if (c->mfc_un.res.ttls[ct] < 255) {
			if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4))
				goto rtattr_failure;
			nhp = (struct rtnexthop*)skb_put(skb, RTA_ALIGN(sizeof(*nhp)));
			nhp->rtnh_flags = 0;
			nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
			nhp->rtnh_ifindex = vif_table[ct].dev->ifindex;
			nhp->rtnh_len = sizeof(*nhp);
		}
	}
	mp_head->rta_type = RTA_MULTIPATH;
	mp_head->rta_len = skb->tail - (u8*)mp_head;
	rtm->rtm_type = RTN_MULTICAST;
	return 1;

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

int ipmr_get_route(struct sk_buff *skb, struct rtmsg *rtm, int nowait)
{
	int err;
	struct mfc_cache *cache;
	struct rtable *rt = (struct rtable*)skb->dst;

	read_lock(&mrt_lock);
	cache = ipmr_cache_find(rt->rt_src, rt->rt_dst);

	if (cache==NULL) {
		struct net_device *dev;
		int vif;

		if (nowait) {
			read_unlock(&mrt_lock);
			return -EAGAIN;
		}

		dev = skb->dev;
		if (dev == NULL || (vif = ipmr_find_vif(dev)) < 0) {
			read_unlock(&mrt_lock);
			return -ENODEV;
		}
		skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
		skb->nh.iph->ihl = sizeof(struct iphdr)>>2;
		skb->nh.iph->saddr = rt->rt_src;
		skb->nh.iph->daddr = rt->rt_dst;
		skb->nh.iph->version = 0;
		err = ipmr_cache_unresolved(vif, skb);
		read_unlock(&mrt_lock);
		return err;
	}

	if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY))
		cache->mfc_flags |= MFC_NOTIFY;
	err = ipmr_fill_mroute(skb, cache, rtm);
	read_unlock(&mrt_lock);
	return err;
}
#endif

#ifdef CONFIG_PROC_FS	
/*
 *	The /proc interfaces to multicast routing /proc/ip_mr_cache /proc/ip_mr_vif
 */
 
static int ipmr_vif_info(char *buffer, char **start, off_t offset, int length)
{
	struct vif_device *vif;
	int len=0;
	off_t pos=0;
	off_t begin=0;
	int size;
	int ct;

	len += sprintf(buffer,
		 "Interface      BytesIn  PktsIn  BytesOut PktsOut Flags Local    Remote\n");
	pos=len;
  
	read_lock(&mrt_lock);
	for (ct=0;ct<maxvif;ct++) 
	{
		char *name = "none";
		vif=&vif_table[ct];
		if(!VIF_EXISTS(ct))
			continue;
		if (vif->dev)
			name = vif->dev->name;
        	size = sprintf(buffer+len, "%2d %-10s %8ld %7ld  %8ld %7ld %05X %08X %08X\n",
        		ct, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out,
        		vif->flags, vif->local, vif->remote);
		len+=size;
		pos+=size;
		if(pos<offset)
		{
			len=0;
			begin=pos;
		}
		if(pos>offset+length)
			break;
  	}
	read_unlock(&mrt_lock);
  	
  	*start=buffer+(offset-begin);
  	len-=(offset-begin);
  	if(len>length)
  		len=length;
	if (len<0)
		len = 0;
  	return len;
}

static int ipmr_mfc_info(char *buffer, char **start, off_t offset, int length)
{
	struct mfc_cache *mfc;
	int len=0;
	off_t pos=0;
	off_t begin=0;
	int size;
	int ct;

	len += sprintf(buffer,
		 "Group    Origin   Iif     Pkts    Bytes    Wrong Oifs\n");
	pos=len;

	read_lock(&mrt_lock);
	for (ct=0;ct<MFC_LINES;ct++) 
	{
		for(mfc=mfc_cache_array[ct]; mfc; mfc=mfc->next)
		{
			int n;

			/*
			 *	Interface forwarding map
			 */
			size = sprintf(buffer+len, "%08lX %08lX %-3d %8ld %8ld %8ld",
				(unsigned long)mfc->mfc_mcastgrp,
				(unsigned long)mfc->mfc_origin,
				mfc->mfc_parent,
				mfc->mfc_un.res.pkt,
				mfc->mfc_un.res.bytes,
				mfc->mfc_un.res.wrong_if);
			for(n=mfc->mfc_un.res.minvif;n<mfc->mfc_un.res.maxvif;n++)
			{
				if(VIF_EXISTS(n) && mfc->mfc_un.res.ttls[n] < 255)
					size += sprintf(buffer+len+size, " %2d:%-3d", n, mfc->mfc_un.res.ttls[n]);
			}
			size += sprintf(buffer+len+size, "\n");
			len+=size;
			pos+=size;
			if(pos<offset)
			{
				len=0;
				begin=pos;
			}
			if(pos>offset+length)
				goto done;
	  	}
  	}

	spin_lock_bh(&mfc_unres_lock);
	for(mfc=mfc_unres_queue; mfc; mfc=mfc->next) {
		size = sprintf(buffer+len, "%08lX %08lX %-3d %8ld %8ld %8ld\n",
			       (unsigned long)mfc->mfc_mcastgrp,
			       (unsigned long)mfc->mfc_origin,
			       -1,
				(long)mfc->mfc_un.unres.unresolved.qlen,
				0L, 0L);
		len+=size;
		pos+=size;
		if(pos<offset)
		{
			len=0;
			begin=pos;
		}
		if(pos>offset+length)
			break;
	}
	spin_unlock_bh(&mfc_unres_lock);

done:
	read_unlock(&mrt_lock);
  	*start=buffer+(offset-begin);
  	len-=(offset-begin);
  	if(len>length)
  		len=length;
	if (len < 0) {
		len = 0;
	}
  	return len;
}

#endif	

#ifdef CONFIG_IP_PIMSM_V2
struct inet_protocol pim_protocol = 
{
	pim_rcv,		/* PIM handler		*/
	NULL,			/* PIM error control	*/
	NULL,			/* next			*/
	IPPROTO_PIM,		/* protocol ID		*/
	0,			/* copy			*/
	NULL,			/* data			*/
	"PIM"			/* name			*/
};
#endif


/*
 *	Setup for IP multicast routing
 */
 
void __init ip_mr_init(void)
{
	printk(KERN_INFO "Linux IP multicast router 0.06 plus PIM-SM\n");
	mrt_cachep = kmem_cache_create("ip_mrt_cache",
				       sizeof(struct mfc_cache),
				       0, SLAB_HWCACHE_ALIGN,
				       NULL, NULL);
	init_timer(&ipmr_expire_timer);
	ipmr_expire_timer.function=ipmr_expire_process;
	register_netdevice_notifier(&ip_mr_notifier);
#ifdef CONFIG_PROC_FS	
	proc_net_create("ip_mr_vif",0,ipmr_vif_info);
	proc_net_create("ip_mr_cache",0,ipmr_mfc_info);
#endif	
}