ipmr.c

		if (get_user(v,(int __user *)optval))
			return -EFAULT;
		init_net.ipv4.mroute_do_assert = (v) ? 1 : 0;
		return 0;
	}
#ifdef CONFIG_IP_PIMSM
	case MRT_PIM:
	{
		int v;

		if (get_user(v,(int __user *)optval))
			return -EFAULT;
		v = (v) ? 1 : 0;

		rtnl_lock();
		ret = 0;
		if (v != init_net.ipv4.mroute_do_pim) {
			init_net.ipv4.mroute_do_pim = v;
			init_net.ipv4.mroute_do_assert = v;
#ifdef CONFIG_IP_PIMSM_V2
			if (init_net.ipv4.mroute_do_pim)
				ret = inet_add_protocol(&pim_protocol,
							IPPROTO_PIM);
			else
				ret = inet_del_protocol(&pim_protocol,
							IPPROTO_PIM);
			if (ret < 0)
				ret = -EAGAIN;
#endif
		}
		rtnl_unlock();
		return ret;
	}
#endif
	/*
	 *	Spurious command, or MRT_VERSION which you cannot
	 *	set.
	 */
	default:
		return -ENOPROTOOPT;
	}
}

/*
 *	Getsock opt support for the multicast routing system.
 */

int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen)
{
	int olr;
	int val;

	if (optname != MRT_VERSION &&
#ifdef CONFIG_IP_PIMSM
	   optname!=MRT_PIM &&
#endif
	   optname!=MRT_ASSERT)
		return -ENOPROTOOPT;

	if (get_user(olr, optlen))
		return -EFAULT;

	olr = min_t(unsigned int, olr, sizeof(int));
	if (olr < 0)
		return -EINVAL;

	if (put_user(olr, optlen))
		return -EFAULT;
	if (optname == MRT_VERSION)
		val = 0x0305;
#ifdef CONFIG_IP_PIMSM
	else if (optname == MRT_PIM)
		val = init_net.ipv4.mroute_do_pim;
#endif
	else
		val = init_net.ipv4.mroute_do_assert;
	if (copy_to_user(optval, &val, olr))
		return -EFAULT;
	return 0;
}

/*
 *	The IP multicast ioctl support routines.
 */

int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
{
	struct sioc_sg_req sr;
	struct sioc_vif_req vr;
	struct vif_device *vif;
	struct mfc_cache *c;

	switch (cmd) {
	case SIOCGETVIFCNT:
		if (copy_from_user(&vr, arg, sizeof(vr)))
			return -EFAULT;
		if (vr.vifi >= init_net.ipv4.maxvif)
			return -EINVAL;
		read_lock(&mrt_lock);
		vif = &init_net.ipv4.vif_table[vr.vifi];
		if (VIF_EXISTS(&init_net, vr.vifi)) {
			vr.icount = vif->pkt_in;
			vr.ocount = vif->pkt_out;
			vr.ibytes = vif->bytes_in;
			vr.obytes = vif->bytes_out;
			read_unlock(&mrt_lock);

			if (copy_to_user(arg, &vr, sizeof(vr)))
				return -EFAULT;
			return 0;
		}
		read_unlock(&mrt_lock);
		return -EADDRNOTAVAIL;
	case SIOCGETSGCNT:
		if (copy_from_user(&sr, arg, sizeof(sr)))
			return -EFAULT;

		read_lock(&mrt_lock);
		c = ipmr_cache_find(sr.src.s_addr, sr.grp.s_addr);
		if (c) {
			sr.pktcnt = c->mfc_un.res.pkt;
			sr.bytecnt = c->mfc_un.res.bytes;
			sr.wrong_if = c->mfc_un.res.wrong_if;
			read_unlock(&mrt_lock);

			if (copy_to_user(arg, &sr, sizeof(sr)))
				return -EFAULT;
			return 0;
		}
		read_unlock(&mrt_lock);
		return -EADDRNOTAVAIL;
	default:
		return -ENOIOCTLCMD;
	}
}


static int ipmr_device_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct net_device *dev = ptr;
	struct vif_device *v;
	int ct;

	if (!net_eq(dev_net(dev), &init_net))
		return NOTIFY_DONE;

	if (event != NETDEV_UNREGISTER)
		return NOTIFY_DONE;
	v = &init_net.ipv4.vif_table[0];
	for (ct = 0; ct < init_net.ipv4.maxvif; ct++, v++) {
		if (v->dev == dev)
			vif_delete(ct, 1);
	}
	return NOTIFY_DONE;
}


static struct notifier_block ip_mr_notifier = {
	.notifier_call = ipmr_device_event,
};

/*
 * 	Encapsulate a packet by attaching a valid IPIP header to it.
 *	This avoids tunnel drivers and other mess and gives us the speed so
 *	important for multicast video.
 */

static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr)
{
	struct iphdr *iph;
	struct iphdr *old_iph = ip_hdr(skb);

	skb_push(skb, sizeof(struct iphdr));
	skb->transport_header = skb->network_header;
	skb_reset_network_header(skb);
	iph = ip_hdr(skb);

	iph->version	= 	4;
	iph->tos	=	old_iph->tos;
	iph->ttl	=	old_iph->ttl;
	iph->frag_off	=	0;
	iph->daddr	=	daddr;
	iph->saddr	=	saddr;
	iph->protocol	=	IPPROTO_IPIP;
	iph->ihl	=	5;
	iph->tot_len	=	htons(skb->len);
	ip_select_ident(iph, skb->dst, NULL);
	ip_send_check(iph);

	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
	nf_reset(skb);
}

static inline int ipmr_forward_finish(struct sk_buff *skb)
{
	struct ip_options * opt	= &(IPCB(skb)->opt);

	IP_INC_STATS_BH(dev_net(skb->dst->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);

	if (unlikely(opt->optlen))
		ip_forward_options(skb);

	return dst_output(skb);
}

/*
 *	Processing handlers for ipmr_forward
 */

static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi)
{
	const struct iphdr *iph = ip_hdr(skb);
	struct vif_device *vif = &init_net.ipv4.vif_table[vifi];
	struct net_device *dev;
	struct rtable *rt;
	int    encap = 0;

	if (vif->dev == NULL)
		goto out_free;

#ifdef CONFIG_IP_PIMSM
	if (vif->flags & VIFF_REGISTER) {
		vif->pkt_out++;
		vif->bytes_out += skb->len;
		vif->dev->stats.tx_bytes += skb->len;
		vif->dev->stats.tx_packets++;
		ipmr_cache_report(skb, vifi, IGMPMSG_WHOLEPKT);
		kfree_skb(skb);
		return;
	}
#endif

	if (vif->flags&VIFF_TUNNEL) {
		struct flowi fl = { .oif = vif->link,
				    .nl_u = { .ip4_u =
					      { .daddr = vif->remote,
						.saddr = vif->local,
						.tos = RT_TOS(iph->tos) } },
				    .proto = IPPROTO_IPIP };
		if (ip_route_output_key(&init_net, &rt, &fl))
			goto out_free;
		encap = sizeof(struct iphdr);
	} else {
		struct flowi fl = { .oif = vif->link,
				    .nl_u = { .ip4_u =
					      { .daddr = iph->daddr,
						.tos = RT_TOS(iph->tos) } },
				    .proto = IPPROTO_IPIP };
		if (ip_route_output_key(&init_net, &rt, &fl))
			goto out_free;
	}

	dev = rt->u.dst.dev;

	if (skb->len+encap > dst_mtu(&rt->u.dst) && (ntohs(iph->frag_off) & IP_DF)) {
		/* Do not fragment multicasts. Alas, IPv4 does not
		   allow to send ICMP, so that packets will disappear
		   to blackhole.
		 */

		IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
		ip_rt_put(rt);
		goto out_free;
	}

	encap += LL_RESERVED_SPACE(dev) + rt->u.dst.header_len;

	if (skb_cow(skb, encap)) {
		ip_rt_put(rt);
		goto out_free;
	}

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

	dst_release(skb->dst);
	skb->dst = &rt->u.dst;
	ip_decrease_ttl(ip_hdr(skb));

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

	IPCB(skb)->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_INET_FORWARD, skb, skb->dev, dev,
		ipmr_forward_finish);
	return;

out_free:
	kfree_skb(skb);
	return;
}

static int ipmr_find_vif(struct net_device *dev)
{
	int ct;
	for (ct = init_net.ipv4.maxvif-1; ct >= 0; ct--) {
		if (init_net.ipv4.vif_table[ct].dev == dev)
			break;
	}
	return ct;
}

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

static 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 (init_net.ipv4.vif_table[vif].dev != skb->dev) {
		int true_vifi;

		if (skb->rtable->fl.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 && init_net.ipv4.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
		     */
		    (init_net.ipv4.mroute_do_pim ||
		     cache->mfc_un.res.ttls[true_vifi] < 255) &&
		    time_after(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;
	}

	init_net.ipv4.vif_table[vif].pkt_in++;
	init_net.ipv4.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 (ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) {
			if (psend != -1) {
				struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
				if (skb2)
					ipmr_queue_xmit(skb2, cache, psend);
			}
			psend = ct;
		}
	}
	if (psend != -1) {
		if (local) {
			struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
			if (skb2)
				ipmr_queue_xmit(skb2, cache, psend);
		} else {
			ipmr_queue_xmit(skb, cache, psend);
			return 0;
		}
	}

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 = skb->rtable->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 (ip_hdr(skb)->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 (init_net.ipv4.mroute_sk) {
				    nf_reset(skb);
				    raw_rcv(init_net.ipv4.mroute_sk, skb);
				    read_unlock(&mrt_lock);
				    return 0;
			    }
			    read_unlock(&mrt_lock);
		    }
	}

	read_lock(&mrt_lock);
	cache = ipmr_cache_find(ip_hdr(skb)->saddr, ip_hdr(skb)->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
static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen)
{
	struct net_device *reg_dev = NULL;
	struct iphdr *encap;

	encap = (struct iphdr *)(skb_transport_header(skb) + pimlen);
	/*
	   Check that:
	   a. packet is really destinted to a multicast group
	   b. packet is not a NULL-REGISTER
	   c. packet is not truncated
	 */
	if (!ipv4_is_multicast(encap->daddr) ||
	    encap->tot_len == 0 ||
	    ntohs(encap->tot_len) + pimlen > skb->len)
		return 1;

	read_lock(&mrt_lock);
	if (reg_vif_num >= 0)
		reg_dev = init_net.ipv4.vif_table[reg_vif_num].dev;
	if (reg_dev)
		dev_hold(reg_dev);
	read_unlock(&mrt_lock);

	if (reg_dev == NULL)
		return 1;

	skb->mac_header = skb->network_header;
	skb_pull(skb, (u8*)encap - skb->data);
	skb_reset_network_header(skb);
	skb->dev = reg_dev;
	skb->protocol = htons(ETH_P_IP);
	skb->ip_summed = 0;
	skb->pkt_type = PACKET_HOST;
	dst_release(skb->dst);
	skb->dst = NULL;
	reg_dev->stats.rx_bytes += skb->len;
	reg_dev->stats.rx_packets++;
	nf_reset(skb);
	netif_rx(skb);
	dev_put(reg_dev);

	return 0;
}
#endif

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

int pim_rcv_v1(struct sk_buff * skb)
{
	struct igmphdr *pim;

	if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr)))
		goto drop;

	pim = igmp_hdr(skb);

	if (!init_net.ipv4.mroute_do_pim ||
	    pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER)
		goto drop;

	if (__pim_rcv(skb, sizeof(*pim))) {
drop:
		kfree_skb(skb);
	}
	return 0;
}
#endif

#ifdef CONFIG_IP_PIMSM_V2
static int pim_rcv(struct sk_buff * skb)
{
	struct pimreghdr *pim;

	if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr)))
		goto drop;

	pim = (struct pimreghdr *)skb_transport_header(skb);
	if (pim->type != ((PIM_VERSION<<4)|(PIM_REGISTER)) ||
	    (pim->flags&PIM_NULL_REGISTER) ||
	    (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 &&
	     csum_fold(skb_checksum(skb, 0, skb->len, 0))))
		goto drop;

	if (__pim_rcv(skb, sizeof(*pim))) {
drop:
		kfree_skb(skb);
	}
	return 0;
}
#endif

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 = init_net.ipv4.vif_table[c->mfc_parent].dev;
	u8 *b = skb_tail_pointer(skb);
	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 = init_net.ipv4.vif_table[ct].dev->ifindex;
			nhp->rtnh_len = sizeof(*nhp);
		}
	}
	mp_head->rta_type = RTA_MULTIPATH;
	mp_head->rta_len = skb_tail_pointer(skb) - (u8 *)mp_head;
	rtm->rtm_type = RTN_MULTICAST;
	return 1;

rtattr_failure:
	nlmsg_trim(skb, b);
	return -EMSGSIZE;
}

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

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

	if (cache == NULL) {
		struct sk_buff *skb2;
		struct iphdr *iph;
		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;
		}
		skb2 = skb_clone(skb, GFP_ATOMIC);
		if (!skb2) {
			read_unlock(&mrt_lock);
			return -ENOMEM;
		}

		skb_push(skb2, sizeof(struct iphdr));
		skb_reset_network_header(skb2);
		iph = ip_hdr(skb2);
		iph->ihl = sizeof(struct iphdr) >> 2;
		iph->saddr = rt->rt_src;
		iph->daddr = rt->rt_dst;
		iph->version = 0;
		err = ipmr_cache_unresolved(vif, skb2);
		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;
}

#ifdef CONFIG_PROC_FS
/*
 *	The /proc interfaces to multicast routing /proc/ip_mr_cache /proc/ip_mr_vif
 */
struct ipmr_vif_iter {
	int ct;
};

static struct vif_device *ipmr_vif_seq_idx(struct ipmr_vif_iter *iter,
					   loff_t pos)
{
	for (iter->ct = 0; iter->ct < init_net.ipv4.maxvif; ++iter->ct) {
		if (!VIF_EXISTS(&init_net, iter->ct))
			continue;
		if (pos-- == 0)
			return &init_net.ipv4.vif_table[iter->ct];
	}
	return NULL;
}

static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos)
	__acquires(mrt_lock)
{
	read_lock(&mrt_lock);
	return *pos ? ipmr_vif_seq_idx(seq->private, *pos - 1)
		: SEQ_START_TOKEN;
}

static void *ipmr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct ipmr_vif_iter *iter = seq->private;

	++*pos;
	if (v == SEQ_START_TOKEN)
		return ipmr_vif_seq_idx(iter, 0);

	while (++iter->ct < init_net.ipv4.maxvif) {
		if (!VIF_EXISTS(&init_net, iter->ct))
			continue;
		return &init_net.ipv4.vif_table[iter->ct];
	}
	return NULL;
}

static void ipmr_vif_seq_stop(struct seq_file *seq, void *v)
	__releases(mrt_lock)
{
	read_unlock(&mrt_lock);
}

static int ipmr_vif_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN) {
		seq_puts(seq,
			 "Interface      BytesIn  PktsIn  BytesOut PktsOut Flags Local    Remote\n");
	} else {
		const struct vif_device *vif = v;
		const char *name =  vif->dev ? vif->dev->name : "none";

		seq_printf(seq,
			   "%2Zd %-10s %8ld %7ld  %8ld %7ld %05X %08X %08X\n",
			   vif - init_net.ipv4.vif_table,
			   name, vif->bytes_in, vif->pkt_in,
			   vif->bytes_out, vif->pkt_out,
			   vif->flags, vif->local, vif->remote);
	}
	return 0;
}

static const struct seq_operations ipmr_vif_seq_ops = {
	.start = ipmr_vif_seq_start,
	.next  = ipmr_vif_seq_next,
	.stop  = ipmr_vif_seq_stop,
	.show  = ipmr_vif_seq_show,
};

static int ipmr_vif_open(struct inode *inode, struct file *file)
{
	return seq_open_private(file, &ipmr_vif_seq_ops,
			sizeof(struct ipmr_vif_iter));
}

static const struct file_operations ipmr_vif_fops = {
	.owner	 = THIS_MODULE,
	.open    = ipmr_vif_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release_private,
};

struct ipmr_mfc_iter {
	struct mfc_cache **cache;
	int ct;
};


static struct mfc_cache *ipmr_mfc_seq_idx(struct ipmr_mfc_iter *it, loff_t pos)
{
	struct mfc_cache *mfc;

	it->cache = init_net.ipv4.mfc_cache_array;
	read_lock(&mrt_lock);
	for (it->ct = 0; it->ct < MFC_LINES; it->ct++)
		for (mfc = init_net.ipv4.mfc_cache_array[it->ct];
		     mfc; mfc = mfc->next)
			if (pos-- == 0)
				return mfc;
	read_unlock(&mrt_lock);

	it->cache = &mfc_unres_queue;
	spin_lock_bh(&mfc_unres_lock);
	for (mfc = mfc_unres_queue; mfc; mfc = mfc->next)
		if (pos-- == 0)
			return mfc;
	spin_unlock_bh(&mfc_unres_lock);

	it->cache = NULL;
	return NULL;
}


static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct ipmr_mfc_iter *it = seq->private;
	it->cache = NULL;
	it->ct = 0;
	return *pos ? ipmr_mfc_seq_idx(seq->private, *pos - 1)
		: SEQ_START_TOKEN;
}

static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct mfc_cache *mfc = v;
	struct ipmr_mfc_iter *it = seq->private;

	++*pos;

	if (v == SEQ_START_TOKEN)
		return ipmr_mfc_seq_idx(seq->private, 0);

	if (mfc->next)
		return mfc->next;

	if (it->cache == &mfc_unres_queue)
		goto end_of_list;

	BUG_ON(it->cache != init_net.ipv4.mfc_cache_array);

	while (++it->ct < MFC_LINES) {
		mfc = init_net.ipv4.mfc_cache_array[it->ct];
		if (mfc)
			return mfc;
	}

	/* exhausted cache_array, show unresolved */
	read_unlock(&mrt_lock);
	it->cache = &mfc_unres_queue;
	it->ct = 0;

	spin_lock_bh(&mfc_unres_lock);
	mfc = mfc_unres_queue;
	if (mfc)
		return mfc;

 end_of_list:
	spin_unlock_bh(&mfc_unres_lock);
	it->cache = NULL;

	return NULL;
}

static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
{
	struct ipmr_mfc_iter *it = seq->private;

	if (it->cache == &mfc_unres_queue)
		spin_unlock_bh(&mfc_unres_lock);
	else if (it->cache == init_net.ipv4.mfc_cache_array)
		read_unlock(&mrt_lock);
}

static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
{
	int n;

	if (v == SEQ_START_TOKEN) {
		seq_puts(seq,
		 "Group    Origin   Iif     Pkts    Bytes    Wrong Oifs\n");
	} else {
		const struct mfc_cache *mfc = v;
		const struct ipmr_mfc_iter *it = seq->private;

		seq_printf(seq, "%08lX %08lX %-3hd",
			   (unsigned long) mfc->mfc_mcastgrp,
			   (unsigned long) mfc->mfc_origin,
			   mfc->mfc_parent);

		if (it->cache != &mfc_unres_queue) {
			seq_printf(seq, " %8lu %8lu %8lu",
				   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(&init_net, n) &&
				    mfc->mfc_un.res.ttls[n] < 255)
					seq_printf(seq,
					   " %2d:%-3d",
					   n, mfc->mfc_un.res.ttls[n]);
			}
		} else {
			/* unresolved mfc_caches don't contain
			 * pkt, bytes and wrong_if values
			 */
			seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul);
		}
		seq_putc(seq, '\n');
	}
	return 0;
}

static const struct seq_operations ipmr_mfc_seq_ops = {
	.start = ipmr_mfc_seq_start,
	.next  = ipmr_mfc_seq_next,
	.stop  = ipmr_mfc_seq_stop,
	.show  = ipmr_mfc_seq_show,
};

static int ipmr_mfc_open(struct inode *inode, struct file *file)
{
	return seq_open_private(file, &ipmr_mfc_seq_ops,
			sizeof(struct ipmr_mfc_iter));
}

static const struct file_operations ipmr_mfc_fops = {
	.owner	 = THIS_MODULE,
	.open    = ipmr_mfc_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release_private,
};
#endif

#ifdef CONFIG_IP_PIMSM_V2
static struct net_protocol pim_protocol = {
	.handler	=	pim_rcv,
};
#endif


/*
 *	Setup for IP multicast routing
 */
static int __net_init ipmr_net_init(struct net *net)
{
	int err = 0;

	net->ipv4.vif_table = kcalloc(MAXVIFS, sizeof(struct vif_device),
				      GFP_KERNEL);
	if (!net->ipv4.vif_table) {
		err = -ENOMEM;
		goto fail;
	}

	/* Forwarding cache */
	net->ipv4.mfc_cache_array = kcalloc(MFC_LINES,
					    sizeof(struct mfc_cache *),
					    GFP_KERNEL);
	if (!net->ipv4.mfc_cache_array) {
		err = -ENOMEM;
		goto fail_mfc_cache;
	}
	return 0;

fail_mfc_cache:
	kfree(net->ipv4.vif_table);
fail:
	return err;
}

static void __net_exit ipmr_net_exit(struct net *net)
{
	kfree(net->ipv4.mfc_cache_array);
	kfree(net->ipv4.vif_table);
}

static struct pernet_operations ipmr_net_ops = {
	.init = ipmr_net_init,
	.exit = ipmr_net_exit,
};

int __init ip_mr_init(void)
{
	int err;

	mrt_cachep = kmem_cache_create("ip_mrt_cache",
				       sizeof(struct mfc_cache),
				       0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
				       NULL);
	if (!mrt_cachep)
		return -ENOMEM;

	err = register_pernet_subsys(&ipmr_net_ops);
	if (err)
		goto reg_pernet_fail;

	setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0);
	err = register_netdevice_notifier(&ip_mr_notifier);
	if (err)
		goto reg_notif_fail;
#ifdef CONFIG_PROC_FS
	err = -ENOMEM;
	if (!proc_net_fops_create(&init_net, "ip_mr_vif", 0, &ipmr_vif_fops))
		goto proc_vif_fail;
	if (!proc_net_fops_create(&init_net, "ip_mr_cache", 0, &ipmr_mfc_fops))
		goto proc_cache_fail;
#endif
	return 0;
#ifdef CONFIG_PROC_FS
proc_cache_fail:
	proc_net_remove(&init_net, "ip_mr_vif");
proc_vif_fail:
	unregister_netdevice_notifier(&ip_mr_notifier);
#endif
reg_notif_fail:
	del_timer(&ipmr_expire_timer);
	unregister_pernet_subsys(&ipmr_net_ops);
reg_pernet_fail:
	kmem_cache_destroy(mrt_cachep);
	return err;