br_multicast.c

	int num;
	int err = 0;

	if (!pskb_may_pull(skb, sizeof(*icmp6h)))
		return -EINVAL;

	icmp6h = icmp6_hdr(skb);
	num = ntohs(icmp6h->icmp6_dataun.un_data16[1]);
	len = sizeof(*icmp6h);

	for (i = 0; i < num; i++) {
		__be16 *nsrcs, _nsrcs;

		nsrcs = skb_header_pointer(skb,
					   len + offsetof(struct mld2_grec,
							  grec_nsrcs),
					   sizeof(_nsrcs), &_nsrcs);
		if (!nsrcs)
			return -EINVAL;

		if (!pskb_may_pull(skb,
				   len + sizeof(*grec) +
				   sizeof(struct in6_addr) * ntohs(*nsrcs)))
			return -EINVAL;

		grec = (struct mld2_grec *)(skb->data + len);
		len += sizeof(*grec) +
		       sizeof(struct in6_addr) * ntohs(*nsrcs);

		/* We treat these as MLDv1 reports for now. */
		switch (grec->grec_type) {
		case MLD2_MODE_IS_INCLUDE:
		case MLD2_MODE_IS_EXCLUDE:
		case MLD2_CHANGE_TO_INCLUDE:
		case MLD2_CHANGE_TO_EXCLUDE:
		case MLD2_ALLOW_NEW_SOURCES:
		case MLD2_BLOCK_OLD_SOURCES:
			break;

		default:
			continue;
		}

		err = br_ip6_multicast_add_group(br, port, &grec->grec_mca);
		if (!err)
			break;
	}

	return err;
}
#endif

/*
 * Add port to rotuer_list
 *  list is maintained ordered by pointer value
 *  and locked by br->multicast_lock and RCU
 */
static void br_multicast_add_router(struct net_bridge *br,
				    struct net_bridge_port *port)
{
	struct net_bridge_port *p;
	struct hlist_node *n, *slot = NULL;

	hlist_for_each_entry(p, n, &br->router_list, rlist) {
		if ((unsigned long) port >= (unsigned long) p)
			break;
		slot = n;
	}

	if (slot)
		hlist_add_after_rcu(slot, &port->rlist);
	else
		hlist_add_head_rcu(&port->rlist, &br->router_list);
}

static void br_multicast_mark_router(struct net_bridge *br,
				     struct net_bridge_port *port)
{
	unsigned long now = jiffies;

	if (!port) {
		if (br->multicast_router == 1)
			mod_timer(&br->multicast_router_timer,
				  now + br->multicast_querier_interval);
		return;
	}

	if (port->multicast_router != 1)
		return;

	if (!hlist_unhashed(&port->rlist))
		goto timer;

	br_multicast_add_router(br, port);

timer:
	mod_timer(&port->multicast_router_timer,
		  now + br->multicast_querier_interval);
}

static void br_multicast_query_received(struct net_bridge *br,
					struct net_bridge_port *port,
					int saddr)
{
	if (saddr)
		mod_timer(&br->multicast_querier_timer,
			  jiffies + br->multicast_querier_interval);
	else if (timer_pending(&br->multicast_querier_timer))
		return;

	br_multicast_mark_router(br, port);
}

static int br_ip4_multicast_query(struct net_bridge *br,
				  struct net_bridge_port *port,
				  struct sk_buff *skb)
{
	const struct iphdr *iph = ip_hdr(skb);
	struct igmphdr *ih = igmp_hdr(skb);
	struct net_bridge_mdb_entry *mp;
	struct igmpv3_query *ih3;
	struct net_bridge_port_group *p;
	struct net_bridge_port_group __rcu **pp;
	unsigned long max_delay;
	unsigned long now = jiffies;
	__be32 group;
	int err = 0;

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) ||
	    (port && port->state == BR_STATE_DISABLED))
		goto out;

	br_multicast_query_received(br, port, !!iph->saddr);

	group = ih->group;

	if (skb->len == sizeof(*ih)) {
		max_delay = ih->code * (HZ / IGMP_TIMER_SCALE);

		if (!max_delay) {
			max_delay = 10 * HZ;
			group = 0;
		}
	} else {
		if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) {
			err = -EINVAL;
			goto out;
		}

		ih3 = igmpv3_query_hdr(skb);
		if (ih3->nsrcs)
			goto out;

		max_delay = ih3->code ?
			    IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1;
	}

	if (!group)
		goto out;

	mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group);
	if (!mp)
		goto out;

	max_delay *= br->multicast_last_member_count;

	if (mp->mglist &&
	    (timer_pending(&mp->timer) ?
	     time_after(mp->timer.expires, now + max_delay) :
	     try_to_del_timer_sync(&mp->timer) >= 0))
		mod_timer(&mp->timer, now + max_delay);

	for (pp = &mp->ports;
	     (p = mlock_dereference(*pp, br)) != NULL;
	     pp = &p->next) {
		if (timer_pending(&p->timer) ?
		    time_after(p->timer.expires, now + max_delay) :
		    try_to_del_timer_sync(&p->timer) >= 0)
			mod_timer(&p->timer, now + max_delay);
	}

out:
	spin_unlock(&br->multicast_lock);
	return err;
}

#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
static int br_ip6_multicast_query(struct net_bridge *br,
				  struct net_bridge_port *port,
				  struct sk_buff *skb)
{
	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
	struct mld_msg *mld = (struct mld_msg *) icmp6_hdr(skb);
	struct net_bridge_mdb_entry *mp;
	struct mld2_query *mld2q;
	struct net_bridge_port_group *p;
	struct net_bridge_port_group __rcu **pp;
	unsigned long max_delay;
	unsigned long now = jiffies;
	const struct in6_addr *group = NULL;
	int err = 0;

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) ||
	    (port && port->state == BR_STATE_DISABLED))
		goto out;

	br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr));

	if (skb->len == sizeof(*mld)) {
		if (!pskb_may_pull(skb, sizeof(*mld))) {
			err = -EINVAL;
			goto out;
		}
		mld = (struct mld_msg *) icmp6_hdr(skb);
		max_delay = msecs_to_jiffies(htons(mld->mld_maxdelay));
		if (max_delay)
			group = &mld->mld_mca;
	} else if (skb->len >= sizeof(*mld2q)) {
		if (!pskb_may_pull(skb, sizeof(*mld2q))) {
			err = -EINVAL;
			goto out;
		}
		mld2q = (struct mld2_query *)icmp6_hdr(skb);
		if (!mld2q->mld2q_nsrcs)
			group = &mld2q->mld2q_mca;
		max_delay = mld2q->mld2q_mrc ? MLDV2_MRC(mld2q->mld2q_mrc) : 1;
	}

	if (!group)
		goto out;

	mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group);
	if (!mp)
		goto out;

	max_delay *= br->multicast_last_member_count;
	if (mp->mglist &&
	    (timer_pending(&mp->timer) ?
	     time_after(mp->timer.expires, now + max_delay) :
	     try_to_del_timer_sync(&mp->timer) >= 0))
		mod_timer(&mp->timer, now + max_delay);

	for (pp = &mp->ports;
	     (p = mlock_dereference(*pp, br)) != NULL;
	     pp = &p->next) {
		if (timer_pending(&p->timer) ?
		    time_after(p->timer.expires, now + max_delay) :
		    try_to_del_timer_sync(&p->timer) >= 0)
			mod_timer(&p->timer, now + max_delay);
	}

out:
	spin_unlock(&br->multicast_lock);
	return err;
}
#endif

static void br_multicast_leave_group(struct net_bridge *br,
				     struct net_bridge_port *port,
				     struct br_ip *group)
{
	struct net_bridge_mdb_htable *mdb;
	struct net_bridge_mdb_entry *mp;
	struct net_bridge_port_group *p;
	unsigned long now;
	unsigned long time;

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) ||
	    (port && port->state == BR_STATE_DISABLED) ||
	    timer_pending(&br->multicast_querier_timer))
		goto out;

	mdb = mlock_dereference(br->mdb, br);
	mp = br_mdb_ip_get(mdb, group);
	if (!mp)
		goto out;

	now = jiffies;
	time = now + br->multicast_last_member_count *
		     br->multicast_last_member_interval;

	if (!port) {
		if (mp->mglist &&
		    (timer_pending(&mp->timer) ?
		     time_after(mp->timer.expires, time) :
		     try_to_del_timer_sync(&mp->timer) >= 0)) {
			mod_timer(&mp->timer, time);

			mp->queries_sent = 0;
			mod_timer(&mp->query_timer, now);
		}

		goto out;
	}

	for (p = mlock_dereference(mp->ports, br);
	     p != NULL;
	     p = mlock_dereference(p->next, br)) {
		if (p->port != port)
			continue;

		if (!hlist_unhashed(&p->mglist) &&
		    (timer_pending(&p->timer) ?
		     time_after(p->timer.expires, time) :
		     try_to_del_timer_sync(&p->timer) >= 0)) {
			mod_timer(&p->timer, time);

			p->queries_sent = 0;
			mod_timer(&p->query_timer, now);
		}

		break;
	}

out:
	spin_unlock(&br->multicast_lock);
}

static void br_ip4_multicast_leave_group(struct net_bridge *br,
					 struct net_bridge_port *port,
					 __be32 group)
{
	struct br_ip br_group;

	if (ipv4_is_local_multicast(group))
		return;

	br_group.u.ip4 = group;
	br_group.proto = htons(ETH_P_IP);

	br_multicast_leave_group(br, port, &br_group);
}

#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
static void br_ip6_multicast_leave_group(struct net_bridge *br,
					 struct net_bridge_port *port,
					 const struct in6_addr *group)
{
	struct br_ip br_group;

	if (!ipv6_is_transient_multicast(group))
		return;

	br_group.u.ip6 = *group;
	br_group.proto = htons(ETH_P_IPV6);

	br_multicast_leave_group(br, port, &br_group);
}
#endif

static int br_multicast_ipv4_rcv(struct net_bridge *br,
				 struct net_bridge_port *port,
				 struct sk_buff *skb)
{
	struct sk_buff *skb2 = skb;
	const struct iphdr *iph;
	struct igmphdr *ih;
	unsigned len;
	unsigned offset;
	int err;

	/* We treat OOM as packet loss for now. */
	if (!pskb_may_pull(skb, sizeof(*iph)))
		return -EINVAL;

	iph = ip_hdr(skb);

	if (iph->ihl < 5 || iph->version != 4)
		return -EINVAL;

	if (!pskb_may_pull(skb, ip_hdrlen(skb)))
		return -EINVAL;

	iph = ip_hdr(skb);

	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
		return -EINVAL;

	if (iph->protocol != IPPROTO_IGMP) {
		if ((iph->daddr & IGMP_LOCAL_GROUP_MASK) != IGMP_LOCAL_GROUP)
			BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
		return 0;
	}

	len = ntohs(iph->tot_len);
	if (skb->len < len || len < ip_hdrlen(skb))
		return -EINVAL;

	if (skb->len > len) {
		skb2 = skb_clone(skb, GFP_ATOMIC);
		if (!skb2)
			return -ENOMEM;

		err = pskb_trim_rcsum(skb2, len);
		if (err)
			goto err_out;
	}

	len -= ip_hdrlen(skb2);
	offset = skb_network_offset(skb2) + ip_hdrlen(skb2);
	__skb_pull(skb2, offset);
	skb_reset_transport_header(skb2);

	err = -EINVAL;
	if (!pskb_may_pull(skb2, sizeof(*ih)))
		goto out;

	switch (skb2->ip_summed) {
	case CHECKSUM_COMPLETE:
		if (!csum_fold(skb2->csum))
			break;
		/* fall through */
	case CHECKSUM_NONE:
		skb2->csum = 0;
		if (skb_checksum_complete(skb2))
			goto out;
	}

	err = 0;

	BR_INPUT_SKB_CB(skb)->igmp = 1;
	ih = igmp_hdr(skb2);

	switch (ih->type) {
	case IGMP_HOST_MEMBERSHIP_REPORT:
	case IGMPV2_HOST_MEMBERSHIP_REPORT:
		BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
		err = br_ip4_multicast_add_group(br, port, ih->group);
		break;
	case IGMPV3_HOST_MEMBERSHIP_REPORT:
		err = br_ip4_multicast_igmp3_report(br, port, skb2);
		break;
	case IGMP_HOST_MEMBERSHIP_QUERY:
		err = br_ip4_multicast_query(br, port, skb2);
		break;
	case IGMP_HOST_LEAVE_MESSAGE:
		br_ip4_multicast_leave_group(br, port, ih->group);
		break;
	}

out:
	__skb_push(skb2, offset);
err_out:
	if (skb2 != skb)
		kfree_skb(skb2);
	return err;
}

#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
static int br_multicast_ipv6_rcv(struct net_bridge *br,
				 struct net_bridge_port *port,
				 struct sk_buff *skb)
{
	struct sk_buff *skb2;
	const struct ipv6hdr *ip6h;
	u8 icmp6_type;
	u8 nexthdr;
	__be16 frag_off;
	unsigned len;
	int offset;
	int err;

	if (!pskb_may_pull(skb, sizeof(*ip6h)))
		return -EINVAL;

	ip6h = ipv6_hdr(skb);

	/*
	 * We're interested in MLD messages only.
	 *  - Version is 6
	 *  - MLD has always Router Alert hop-by-hop option
	 *  - But we do not support jumbrograms.
	 */
	if (ip6h->version != 6 ||
	    ip6h->nexthdr != IPPROTO_HOPOPTS ||
	    ip6h->payload_len == 0)
		return 0;

	len = ntohs(ip6h->payload_len) + sizeof(*ip6h);
	if (skb->len < len)
		return -EINVAL;

	nexthdr = ip6h->nexthdr;
	offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr, &frag_off);

	if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
		return 0;

	/* Okay, we found ICMPv6 header */
	skb2 = skb_clone(skb, GFP_ATOMIC);
	if (!skb2)
		return -ENOMEM;

	err = -EINVAL;
	if (!pskb_may_pull(skb2, offset + sizeof(struct icmp6hdr)))
		goto out;

	len -= offset - skb_network_offset(skb2);

	__skb_pull(skb2, offset);
	skb_reset_transport_header(skb2);
	skb_postpull_rcsum(skb2, skb_network_header(skb2),
			   skb_network_header_len(skb2));

	icmp6_type = icmp6_hdr(skb2)->icmp6_type;

	switch (icmp6_type) {
	case ICMPV6_MGM_QUERY:
	case ICMPV6_MGM_REPORT:
	case ICMPV6_MGM_REDUCTION:
	case ICMPV6_MLD2_REPORT:
		break;
	default:
		err = 0;
		goto out;
	}

	/* Okay, we found MLD message. Check further. */
	if (skb2->len > len) {
		err = pskb_trim_rcsum(skb2, len);
		if (err)
			goto out;
		err = -EINVAL;
	}

	ip6h = ipv6_hdr(skb2);

	switch (skb2->ip_summed) {
	case CHECKSUM_COMPLETE:
		if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb2->len,
					IPPROTO_ICMPV6, skb2->csum))
			break;
		/*FALLTHROUGH*/
	case CHECKSUM_NONE:
		skb2->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr,
							&ip6h->daddr,
							skb2->len,
							IPPROTO_ICMPV6, 0));
		if (__skb_checksum_complete(skb2))
			goto out;
	}

	err = 0;

	BR_INPUT_SKB_CB(skb)->igmp = 1;

	switch (icmp6_type) {
	case ICMPV6_MGM_REPORT:
	    {
		struct mld_msg *mld;
		if (!pskb_may_pull(skb2, sizeof(*mld))) {
			err = -EINVAL;
			goto out;
		}
		mld = (struct mld_msg *)skb_transport_header(skb2);
		BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
		err = br_ip6_multicast_add_group(br, port, &mld->mld_mca);
		break;
	    }
	case ICMPV6_MLD2_REPORT:
		err = br_ip6_multicast_mld2_report(br, port, skb2);
		break;
	case ICMPV6_MGM_QUERY:
		err = br_ip6_multicast_query(br, port, skb2);
		break;
	case ICMPV6_MGM_REDUCTION:
	    {
		struct mld_msg *mld;
		if (!pskb_may_pull(skb2, sizeof(*mld))) {
			err = -EINVAL;
			goto out;
		}
		mld = (struct mld_msg *)skb_transport_header(skb2);
		br_ip6_multicast_leave_group(br, port, &mld->mld_mca);
	    }
	}

out:
	kfree_skb(skb2);
	return err;
}
#endif

int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
		     struct sk_buff *skb)
{
	BR_INPUT_SKB_CB(skb)->igmp = 0;
	BR_INPUT_SKB_CB(skb)->mrouters_only = 0;

	if (br->multicast_disabled)
		return 0;

	switch (skb->protocol) {
	case htons(ETH_P_IP):
		return br_multicast_ipv4_rcv(br, port, skb);
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
	case htons(ETH_P_IPV6):
		return br_multicast_ipv6_rcv(br, port, skb);
#endif
	}

	return 0;
}

static void br_multicast_query_expired(unsigned long data)
{
	struct net_bridge *br = (void *)data;

	spin_lock(&br->multicast_lock);
	if (br->multicast_startup_queries_sent <
	    br->multicast_startup_query_count)
		br->multicast_startup_queries_sent++;

	br_multicast_send_query(br, NULL, br->multicast_startup_queries_sent);

	spin_unlock(&br->multicast_lock);
}

void br_multicast_init(struct net_bridge *br)
{
	br->hash_elasticity = 4;
	br->hash_max = 512;

	br->multicast_router = 1;
	br->multicast_last_member_count = 2;
	br->multicast_startup_query_count = 2;

	br->multicast_last_member_interval = HZ;
	br->multicast_query_response_interval = 10 * HZ;
	br->multicast_startup_query_interval = 125 * HZ / 4;
	br->multicast_query_interval = 125 * HZ;
	br->multicast_querier_interval = 255 * HZ;
	br->multicast_membership_interval = 260 * HZ;

	spin_lock_init(&br->multicast_lock);
	setup_timer(&br->multicast_router_timer,
		    br_multicast_local_router_expired, 0);
	setup_timer(&br->multicast_querier_timer,
		    br_multicast_local_router_expired, 0);
	setup_timer(&br->multicast_query_timer, br_multicast_query_expired,
		    (unsigned long)br);
}

void br_multicast_open(struct net_bridge *br)
{
	br->multicast_startup_queries_sent = 0;

	if (br->multicast_disabled)
		return;

	mod_timer(&br->multicast_query_timer, jiffies);
}

void br_multicast_stop(struct net_bridge *br)
{
	struct net_bridge_mdb_htable *mdb;
	struct net_bridge_mdb_entry *mp;
	struct hlist_node *p, *n;
	u32 ver;
	int i;

	del_timer_sync(&br->multicast_router_timer);
	del_timer_sync(&br->multicast_querier_timer);
	del_timer_sync(&br->multicast_query_timer);

	spin_lock_bh(&br->multicast_lock);
	mdb = mlock_dereference(br->mdb, br);
	if (!mdb)
		goto out;

	br->mdb = NULL;

	ver = mdb->ver;
	for (i = 0; i < mdb->max; i++) {
		hlist_for_each_entry_safe(mp, p, n, &mdb->mhash[i],
					  hlist[ver]) {
			del_timer(&mp->timer);
			del_timer(&mp->query_timer);
			call_rcu_bh(&mp->rcu, br_multicast_free_group);
		}
	}

	if (mdb->old) {
		spin_unlock_bh(&br->multicast_lock);
		rcu_barrier_bh();
		spin_lock_bh(&br->multicast_lock);
		WARN_ON(mdb->old);
	}

	mdb->old = mdb;
	call_rcu_bh(&mdb->rcu, br_mdb_free);

out:
	spin_unlock_bh(&br->multicast_lock);
}

int br_multicast_set_router(struct net_bridge *br, unsigned long val)
{
	int err = -ENOENT;

	spin_lock_bh(&br->multicast_lock);
	if (!netif_running(br->dev))
		goto unlock;

	switch (val) {
	case 0:
	case 2:
		del_timer(&br->multicast_router_timer);
		/* fall through */
	case 1:
		br->multicast_router = val;
		err = 0;
		break;

	default:
		err = -EINVAL;
		break;
	}

unlock:
	spin_unlock_bh(&br->multicast_lock);

	return err;
}

int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val)
{
	struct net_bridge *br = p->br;
	int err = -ENOENT;

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev) || p->state == BR_STATE_DISABLED)
		goto unlock;

	switch (val) {
	case 0:
	case 1:
	case 2:
		p->multicast_router = val;
		err = 0;

		if (val < 2 && !hlist_unhashed(&p->rlist))
			hlist_del_init_rcu(&p->rlist);

		if (val == 1)
			break;

		del_timer(&p->multicast_router_timer);

		if (val == 0)
			break;

		br_multicast_add_router(br, p);
		break;

	default:
		err = -EINVAL;
		break;
	}

unlock:
	spin_unlock(&br->multicast_lock);

	return err;
}

int br_multicast_toggle(struct net_bridge *br, unsigned long val)
{
	struct net_bridge_port *port;
	int err = 0;
	struct net_bridge_mdb_htable *mdb;

	spin_lock_bh(&br->multicast_lock);
	if (br->multicast_disabled == !val)
		goto unlock;

	br->multicast_disabled = !val;
	if (br->multicast_disabled)
		goto unlock;

	if (!netif_running(br->dev))
		goto unlock;

	mdb = mlock_dereference(br->mdb, br);
	if (mdb) {
		if (mdb->old) {
			err = -EEXIST;
rollback:
			br->multicast_disabled = !!val;
			goto unlock;
		}

		err = br_mdb_rehash(&br->mdb, mdb->max,
				    br->hash_elasticity);
		if (err)
			goto rollback;
	}

	br_multicast_open(br);
	list_for_each_entry(port, &br->port_list, list) {
		if (port->state == BR_STATE_DISABLED ||
		    port->state == BR_STATE_BLOCKING)
			continue;

		__br_multicast_enable_port(port);
	}

unlock:
	spin_unlock_bh(&br->multicast_lock);

	return err;
}

int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val)
{
	int err = -ENOENT;
	u32 old;
	struct net_bridge_mdb_htable *mdb;

	spin_lock(&br->multicast_lock);
	if (!netif_running(br->dev))
		goto unlock;

	err = -EINVAL;
	if (!is_power_of_2(val))
		goto unlock;

	mdb = mlock_dereference(br->mdb, br);
	if (mdb && val < mdb->size)
		goto unlock;

	err = 0;

	old = br->hash_max;
	br->hash_max = val;

	if (mdb) {
		if (mdb->old) {
			err = -EEXIST;
rollback:
			br->hash_max = old;
			goto unlock;
		}

		err = br_mdb_rehash(&br->mdb, br->hash_max,
				    br->hash_elasticity);
		if (err)
			goto rollback;
	}

unlock:
	spin_unlock(&br->multicast_lock);

	return err;
}