示例#1
0
/*
 * Determine effective MSS.
 *
 * Note that we assume that there is always an MSS option for our own
 * SYN segments, which is mentioned in tcp_syn_build_options(), kernel 2.2.x.
 * This could change, and we should probably parse TCP options instead.
 *
 */
DEBUG_NO_STATIC u_int8_t
ipsec_adjust_mss(struct sk_buff *skb, struct tcphdr *tcph, u_int16_t mtu)
{
	u_int16_t oldmss, newmss;
	u_int32_t *mssp;
	struct sock *sk = skb->sk;
	
	newmss = tcp_sync_mss(sk, mtu);
	printk(KERN_INFO "klips: setting mss to %u\n", newmss);
	mssp = (u_int32_t *)tcph + sizeof(struct tcphdr) / sizeof(u_int32_t);
	oldmss = ntohl(*mssp) & 0x0000FFFF;
	*mssp = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | newmss);
	tcph->check = ipsec_fast_csum(htons(~oldmss), 
	                              htons(newmss), tcph->check);
	return 1;
}
示例#2
0
/*
 * This routine does path mtu discovery as defined in RFC1191.
 */
static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu)
{
	struct dst_entry *dst;
	struct inet_sock *inet = inet_sk(sk);

	/* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs
	 * send out by Linux are always <576bytes so they should go through
	 * unfragmented).
	 */
	if (sk->sk_state == TCP_LISTEN)
		return;

	/* We don't check in the destentry if pmtu discovery is forbidden
	 * on this route. We just assume that no packet_to_big packets
	 * are send back when pmtu discovery is not active.
     	 * There is a small race when the user changes this flag in the
	 * route, but I think that's acceptable.
	 */
	if ((dst = __sk_dst_check(sk, 0)) == NULL)
		return;

	dst->ops->update_pmtu(dst, mtu);

	/* Something is about to be wrong... Remember soft error
	 * for the case, if this connection will not able to recover.
	 */
	if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
		sk->sk_err_soft = EMSGSIZE;

	mtu = dst_mtu(dst);

	if (inet->pmtudisc != IP_PMTUDISC_DONT &&
	    inet_csk(sk)->icsk_pmtu_cookie > mtu) {
		tcp_sync_mss(sk, mtu);

		/* Resend the TCP packet because it's
		 * clear that the old packet has been
		 * dropped. This is the new "fast" path mtu
		 * discovery.
		 */
		tcp_simple_retransmit(sk);
	} /* else let the usual retransmit timer handle it */
}
示例#3
0
static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
		u8 type, u8 code, int offset, __be32 info)
{
	const struct ipv6hdr *hdr = (const struct ipv6hdr*)skb->data;
	const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
	struct ipv6_pinfo *np;
	struct sock *sk;
	int err;
	struct tcp_sock *tp;
	__u32 seq;
	struct net *net = dev_net(skb->dev);

	sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr,
			th->dest, &hdr->saddr, th->source, skb->dev->ifindex);

	if (sk == NULL) {
		ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
				   ICMP6_MIB_INERRORS);
		return;
	}

	if (sk->sk_state == TCP_TIME_WAIT) {
		inet_twsk_put(inet_twsk(sk));
		return;
	}

	bh_lock_sock(sk);
	if (sock_owned_by_user(sk))
		NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);

	if (sk->sk_state == TCP_CLOSE)
		goto out;

	if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) {
		NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
		goto out;
	}

	tp = tcp_sk(sk);
	seq = ntohl(th->seq);
	if (sk->sk_state != TCP_LISTEN &&
	    !between(seq, tp->snd_una, tp->snd_nxt)) {
		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
		goto out;
	}

	np = inet6_sk(sk);

	if (type == ICMPV6_PKT_TOOBIG) {
		struct dst_entry *dst;

		if (sock_owned_by_user(sk))
			goto out;
		if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
			goto out;

		
		dst = __sk_dst_check(sk, np->dst_cookie);

		if (dst == NULL) {
			struct inet_sock *inet = inet_sk(sk);
			struct flowi6 fl6;

			memset(&fl6, 0, sizeof(fl6));
			fl6.flowi6_proto = IPPROTO_TCP;
			fl6.daddr = np->daddr;
			fl6.saddr = np->saddr;
			fl6.flowi6_oif = sk->sk_bound_dev_if;
			fl6.flowi6_mark = sk->sk_mark;
			fl6.fl6_dport = inet->inet_dport;
			fl6.fl6_sport = inet->inet_sport;
			fl6.flowi6_uid = sock_i_uid(sk);
			security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));

			dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
			if (IS_ERR(dst)) {
				sk->sk_err_soft = -PTR_ERR(dst);
				goto out;
			}

		} else
			dst_hold(dst);

		if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
			tcp_sync_mss(sk, dst_mtu(dst));
			tcp_simple_retransmit(sk);
		} 
		dst_release(dst);
		goto out;
	}

	icmpv6_err_convert(type, code, &err);

	
	switch (sk->sk_state) {
		struct request_sock *req, **prev;
	case TCP_LISTEN:
		if (sock_owned_by_user(sk))
			goto out;

		req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
					   &hdr->saddr, inet6_iif(skb));
		if (!req)
			goto out;

		WARN_ON(req->sk != NULL);

		if (seq != tcp_rsk(req)->snt_isn) {
			NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
			goto out;
		}

		inet_csk_reqsk_queue_drop(sk, req, prev);
		goto out;

	case TCP_SYN_SENT:
	case TCP_SYN_RECV:  
		if (!sock_owned_by_user(sk)) {
			sk->sk_err = err;
			sk->sk_error_report(sk);		

			tcp_done(sk);
		} else
			sk->sk_err_soft = err;
		goto out;
	}

	if (!sock_owned_by_user(sk) && np->recverr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	} else
		sk->sk_err_soft = err;

out:
	bh_unlock_sock(sk);
	sock_put(sk);
}
示例#4
0
int ipv6_setsockopt(struct sock *sk, int level, int optname,
		    char __user *optval, int optlen)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	int val, valbool;
	int retv = -ENOPROTOOPT;

	if (level == SOL_IP && sk->sk_type != SOCK_RAW)
		return udp_prot.setsockopt(sk, level, optname, optval, optlen);

	if(level!=SOL_IPV6)
		goto out;

	if (optval == NULL)
		val=0;
	else if (get_user(val, (int __user *) optval))
		return -EFAULT;

	valbool = (val!=0);

	lock_sock(sk);

	switch (optname) {

	case IPV6_ADDRFORM:
		if (val == PF_INET) {
			struct ipv6_txoptions *opt;
			struct sk_buff *pktopt;

			if (sk->sk_protocol != IPPROTO_UDP &&
			    sk->sk_protocol != IPPROTO_TCP)
				break;

			if (sk->sk_state != TCP_ESTABLISHED) {
				retv = -ENOTCONN;
				break;
			}

			if (ipv6_only_sock(sk) ||
			    !(ipv6_addr_type(&np->daddr) & IPV6_ADDR_MAPPED)) {
				retv = -EADDRNOTAVAIL;
				break;
			}

			fl6_free_socklist(sk);
			ipv6_sock_mc_close(sk);

			if (sk->sk_protocol == IPPROTO_TCP) {
				struct tcp_sock *tp = tcp_sk(sk);

				local_bh_disable();
				sock_prot_dec_use(sk->sk_prot);
				sock_prot_inc_use(&tcp_prot);
				local_bh_enable();
				sk->sk_prot = &tcp_prot;
				tp->af_specific = &ipv4_specific;
				sk->sk_socket->ops = &inet_stream_ops;
				sk->sk_family = PF_INET;
				tcp_sync_mss(sk, tp->pmtu_cookie);
			} else {
				local_bh_disable();
				sock_prot_dec_use(sk->sk_prot);
				sock_prot_inc_use(&udp_prot);
				local_bh_enable();
				sk->sk_prot = &udp_prot;
				sk->sk_socket->ops = &inet_dgram_ops;
				sk->sk_family = PF_INET;
			}
			opt = xchg(&np->opt, NULL);
			if (opt)
				sock_kfree_s(sk, opt, opt->tot_len);
			pktopt = xchg(&np->pktoptions, NULL);
			if (pktopt)
				kfree_skb(pktopt);

			sk->sk_destruct = inet_sock_destruct;
#ifdef INET_REFCNT_DEBUG
			atomic_dec(&inet6_sock_nr);
#endif
			module_put(THIS_MODULE);
			retv = 0;
			break;
		}
		goto e_inval;

	case IPV6_V6ONLY:
		if (inet_sk(sk)->num)
			goto e_inval;
		np->ipv6only = valbool;
		retv = 0;
		break;

	case IPV6_PKTINFO:
		np->rxopt.bits.rxinfo = valbool;
		retv = 0;
		break;

	case IPV6_HOPLIMIT:
		np->rxopt.bits.rxhlim = valbool;
		retv = 0;
		break;

	case IPV6_RTHDR:
		if (val < 0 || val > 2)
			goto e_inval;
		np->rxopt.bits.srcrt = val;
		retv = 0;
		break;

	case IPV6_HOPOPTS:
		np->rxopt.bits.hopopts = valbool;
		retv = 0;
		break;

	case IPV6_DSTOPTS:
		np->rxopt.bits.dstopts = valbool;
		retv = 0;
		break;

	case IPV6_FLOWINFO:
		np->rxopt.bits.rxflow = valbool;
		retv = 0;
		break;

	case IPV6_PKTOPTIONS:
	{
		struct ipv6_txoptions *opt = NULL;
		struct msghdr msg;
		struct flowi fl;
		int junk;

		fl.fl6_flowlabel = 0;
		fl.oif = sk->sk_bound_dev_if;

		if (optlen == 0)
			goto update;

		/* 1K is probably excessive
		 * 1K is surely not enough, 2K per standard header is 16K.
		 */
		retv = -EINVAL;
		if (optlen > 64*1024)
			break;

		opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
		retv = -ENOBUFS;
		if (opt == NULL)
			break;

		memset(opt, 0, sizeof(*opt));
		opt->tot_len = sizeof(*opt) + optlen;
		retv = -EFAULT;
		if (copy_from_user(opt+1, optval, optlen))
			goto done;

		msg.msg_controllen = optlen;
		msg.msg_control = (void*)(opt+1);

		retv = datagram_send_ctl(&msg, &fl, opt, &junk);
		if (retv)
			goto done;
update:
		retv = 0;
		if (sk->sk_type == SOCK_STREAM) {
			if (opt) {
				struct tcp_sock *tp = tcp_sk(sk);
				if (!((1 << sk->sk_state) &
				      (TCPF_LISTEN | TCPF_CLOSE))
				    && inet_sk(sk)->daddr != LOOPBACK4_IPV6) {
					tp->ext_header_len = opt->opt_flen + opt->opt_nflen;
					tcp_sync_mss(sk, tp->pmtu_cookie);
				}
			}
			opt = xchg(&np->opt, opt);
			sk_dst_reset(sk);
		} else {
			write_lock(&sk->sk_dst_lock);
			opt = xchg(&np->opt, opt);
			write_unlock(&sk->sk_dst_lock);
			sk_dst_reset(sk);
		}

done:
		if (opt)
			sock_kfree_s(sk, opt, opt->tot_len);
		break;
	}
	case IPV6_UNICAST_HOPS:
		if (val > 255 || val < -1)
			goto e_inval;
		np->hop_limit = val;
		retv = 0;
		break;

	case IPV6_MULTICAST_HOPS:
		if (sk->sk_type == SOCK_STREAM)
			goto e_inval;
		if (val > 255 || val < -1)
			goto e_inval;
		np->mcast_hops = val;
		retv = 0;
		break;

	case IPV6_MULTICAST_LOOP:
		np->mc_loop = valbool;
		retv = 0;
		break;

	case IPV6_MULTICAST_IF:
		if (sk->sk_type == SOCK_STREAM)
			goto e_inval;
		if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
			goto e_inval;

		if (__dev_get_by_index(val) == NULL) {
			retv = -ENODEV;
			break;
		}
		np->mcast_oif = val;
		retv = 0;
		break;
	case IPV6_ADD_MEMBERSHIP:
	case IPV6_DROP_MEMBERSHIP:
	{
		struct ipv6_mreq mreq;

		retv = -EFAULT;
		if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
			break;

		if (optname == IPV6_ADD_MEMBERSHIP)
			retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
		else
			retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
		break;
	}
	case IPV6_JOIN_ANYCAST:
	case IPV6_LEAVE_ANYCAST:
	{
		struct ipv6_mreq mreq;

		if (optlen != sizeof(struct ipv6_mreq))
			goto e_inval;

		retv = -EFAULT;
		if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
			break;

		if (optname == IPV6_JOIN_ANYCAST)
			retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
		else
			retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
		break;
	}
	case MCAST_JOIN_GROUP:
	case MCAST_LEAVE_GROUP:
	{
		struct group_req greq;
		struct sockaddr_in6 *psin6;

		retv = -EFAULT;
		if (copy_from_user(&greq, optval, sizeof(struct group_req)))
			break;
		if (greq.gr_group.ss_family != AF_INET6) {
			retv = -EADDRNOTAVAIL;
			break;
		}
		psin6 = (struct sockaddr_in6 *)&greq.gr_group;
		if (optname == MCAST_JOIN_GROUP)
			retv = ipv6_sock_mc_join(sk, greq.gr_interface,
				&psin6->sin6_addr);
		else
			retv = ipv6_sock_mc_drop(sk, greq.gr_interface,
				&psin6->sin6_addr);
		break;
	}
	case MCAST_JOIN_SOURCE_GROUP:
	case MCAST_LEAVE_SOURCE_GROUP:
	case MCAST_BLOCK_SOURCE:
	case MCAST_UNBLOCK_SOURCE:
	{
		struct group_source_req greqs;
		int omode, add;

		if (optlen != sizeof(struct group_source_req))
			goto e_inval;
		if (copy_from_user(&greqs, optval, sizeof(greqs))) {
			retv = -EFAULT;
			break;
		}
		if (greqs.gsr_group.ss_family != AF_INET6 ||
		    greqs.gsr_source.ss_family != AF_INET6) {
			retv = -EADDRNOTAVAIL;
			break;
		}
		if (optname == MCAST_BLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 1;
		} else if (optname == MCAST_UNBLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 0;
		} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
			struct sockaddr_in6 *psin6;

			psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
			retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
				&psin6->sin6_addr);
			if (retv)
				break;
			omode = MCAST_INCLUDE;
			add = 1;
		} else /*IP_DROP_SOURCE_MEMBERSHIP */ {
			omode = MCAST_INCLUDE;
			add = 0;
		}
		retv = ip6_mc_source(add, omode, sk, &greqs);
		break;
	}
	case MCAST_MSFILTER:
	{
		extern int sysctl_optmem_max;
		extern int sysctl_mld_max_msf;
		struct group_filter *gsf;

		if (optlen < GROUP_FILTER_SIZE(0))
			goto e_inval;
		if (optlen > sysctl_optmem_max) {
			retv = -ENOBUFS;
			break;
		}
		gsf = (struct group_filter *)kmalloc(optlen,GFP_KERNEL);
		if (gsf == 0) {
			retv = -ENOBUFS;
			break;
		}
		retv = -EFAULT;
		if (copy_from_user(gsf, optval, optlen)) {
			kfree(gsf);
			break;
		}
		/* numsrc >= (4G-140)/128 overflow in 32 bits */
		if (gsf->gf_numsrc >= 0x1ffffffU ||
		    gsf->gf_numsrc > sysctl_mld_max_msf) {
			kfree(gsf);
			retv = -ENOBUFS;
			break;
		}
		if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
			kfree(gsf);
			retv = -EINVAL;
			break;
		}
		retv = ip6_mc_msfilter(sk, gsf);
		kfree(gsf);

		break;
	}
	case IPV6_ROUTER_ALERT:
		retv = ip6_ra_control(sk, val, NULL);
		break;
	case IPV6_MTU_DISCOVER:
		if (val<0 || val>2)
			goto e_inval;
		np->pmtudisc = val;
		retv = 0;
		break;
	case IPV6_MTU:
		if (val && val < IPV6_MIN_MTU)
			goto e_inval;
		np->frag_size = val;
		retv = 0;
		break;
	case IPV6_RECVERR:
		np->recverr = valbool;
		if (!val)
			skb_queue_purge(&sk->sk_error_queue);
		retv = 0;
		break;
	case IPV6_FLOWINFO_SEND:
		np->sndflow = valbool;
		retv = 0;
		break;
	case IPV6_FLOWLABEL_MGR:
		retv = ipv6_flowlabel_opt(sk, optval, optlen);
		break;
	case IPV6_IPSEC_POLICY:
	case IPV6_XFRM_POLICY:
		retv = -EPERM;
		if (!capable(CAP_NET_ADMIN))
			break;
		retv = xfrm_user_policy(sk, optname, optval, optlen);
		break;

#ifdef CONFIG_NETFILTER
	default:
		retv = nf_setsockopt(sk, PF_INET6, optname, optval, 
					    optlen);
		break;
#endif

	}
	release_sock(sk);

out:
	return retv;

e_inval:
	release_sock(sk);
	return -EINVAL;
}
示例#5
0
static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
		    char __user *optval, unsigned int optlen)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct net *net = sock_net(sk);
	int val, valbool;
	int retv = -ENOPROTOOPT;

	if (optval == NULL)
		val=0;
	else {
		if (optlen >= sizeof(int)) {
			if (get_user(val, (int __user *) optval))
				return -EFAULT;
		} else
			val = 0;
	}

	valbool = (val!=0);

	if (ip6_mroute_opt(optname))
		return ip6_mroute_setsockopt(sk, optname, optval, optlen);

	lock_sock(sk);

	switch (optname) {

	case IPV6_ADDRFORM:
		if (optlen < sizeof(int))
			goto e_inval;
		if (val == PF_INET) {
			struct ipv6_txoptions *opt;
			struct sk_buff *pktopt;

			if (sk->sk_type == SOCK_RAW)
				break;

			if (sk->sk_protocol == IPPROTO_UDP ||
			    sk->sk_protocol == IPPROTO_UDPLITE) {
				struct udp_sock *up = udp_sk(sk);
				if (up->pending == AF_INET6) {
					retv = -EBUSY;
					break;
				}
			} else if (sk->sk_protocol != IPPROTO_TCP)
				break;

			if (sk->sk_state != TCP_ESTABLISHED) {
				retv = -ENOTCONN;
				break;
			}

			if (ipv6_only_sock(sk) ||
			    !ipv6_addr_v4mapped(&np->daddr)) {
				retv = -EADDRNOTAVAIL;
				break;
			}

			fl6_free_socklist(sk);
			ipv6_sock_mc_close(sk);

			/*
			 * Sock is moving from IPv6 to IPv4 (sk_prot), so
			 * remove it from the refcnt debug socks count in the
			 * original family...
			 */
			sk_refcnt_debug_dec(sk);

			if (sk->sk_protocol == IPPROTO_TCP) {
				struct inet_connection_sock *icsk = inet_csk(sk);
				local_bh_disable();
				sock_prot_inuse_add(net, sk->sk_prot, -1);
				sock_prot_inuse_add(net, &tcp_prot, 1);
				local_bh_enable();
				sk->sk_prot = &tcp_prot;
				icsk->icsk_af_ops = &ipv4_specific;
				sk->sk_socket->ops = &inet_stream_ops;
				sk->sk_family = PF_INET;
				tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
			} else {
				struct proto *prot = &udp_prot;

				if (sk->sk_protocol == IPPROTO_UDPLITE)
					prot = &udplite_prot;
				local_bh_disable();
				sock_prot_inuse_add(net, sk->sk_prot, -1);
				sock_prot_inuse_add(net, prot, 1);
				local_bh_enable();
				sk->sk_prot = prot;
				sk->sk_socket->ops = &inet_dgram_ops;
				sk->sk_family = PF_INET;
			}
			opt = xchg(&np->opt, NULL);
			if (opt)
				sock_kfree_s(sk, opt, opt->tot_len);
			pktopt = xchg(&np->pktoptions, NULL);
			kfree_skb(pktopt);

			sk->sk_destruct = inet_sock_destruct;
			/*
			 * ... and add it to the refcnt debug socks count
			 * in the new family. -acme
			 */
			sk_refcnt_debug_inc(sk);
			module_put(THIS_MODULE);
			retv = 0;
			break;
		}
		goto e_inval;

	case IPV6_V6ONLY:
		if (optlen < sizeof(int) ||
		    inet_sk(sk)->inet_num)
			goto e_inval;
		np->ipv6only = valbool;
		retv = 0;
		break;

	case IPV6_RECVPKTINFO:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxinfo = valbool;
		retv = 0;
		break;

	case IPV6_2292PKTINFO:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxoinfo = valbool;
		retv = 0;
		break;

	case IPV6_RECVHOPLIMIT:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxhlim = valbool;
		retv = 0;
		break;

	case IPV6_2292HOPLIMIT:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxohlim = valbool;
		retv = 0;
		break;

	case IPV6_RECVRTHDR:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.srcrt = valbool;
		retv = 0;
		break;

	case IPV6_2292RTHDR:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.osrcrt = valbool;
		retv = 0;
		break;

	case IPV6_RECVHOPOPTS:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.hopopts = valbool;
		retv = 0;
		break;

	case IPV6_2292HOPOPTS:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.ohopopts = valbool;
		retv = 0;
		break;

	case IPV6_RECVDSTOPTS:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.dstopts = valbool;
		retv = 0;
		break;

	case IPV6_2292DSTOPTS:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.odstopts = valbool;
		retv = 0;
		break;

	case IPV6_TCLASS:
		if (optlen < sizeof(int))
			goto e_inval;
		if (val < -1 || val > 0xff)
			goto e_inval;
		/* RFC 3542, 6.5: default traffic class of 0x0 */
		if (val == -1)
			val = 0;
		np->tclass = val;
		retv = 0;
		break;

	case IPV6_RECVTCLASS:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxtclass = valbool;
		retv = 0;
		break;

	case IPV6_FLOWINFO:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxflow = valbool;
		retv = 0;
		break;

	case IPV6_RECVPATHMTU:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxpmtu = valbool;
		retv = 0;
		break;

	case IPV6_TRANSPARENT:
		if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) &&
		    !ns_capable(net->user_ns, CAP_NET_RAW)) {
			retv = -EPERM;
			break;
		}
		if (optlen < sizeof(int))
			goto e_inval;
		/* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */
		inet_sk(sk)->transparent = valbool;
		retv = 0;
		break;

	case IPV6_RECVORIGDSTADDR:
		if (optlen < sizeof(int))
			goto e_inval;
		np->rxopt.bits.rxorigdstaddr = valbool;
		retv = 0;
		break;

	case IPV6_HOPOPTS:
	case IPV6_RTHDRDSTOPTS:
	case IPV6_RTHDR:
	case IPV6_DSTOPTS:
	{
		struct ipv6_txoptions *opt;

		/* remove any sticky options header with a zero option
		 * length, per RFC3542.
		 */
		if (optlen == 0)
			optval = NULL;
		else if (optval == NULL)
			goto e_inval;
		else if (optlen < sizeof(struct ipv6_opt_hdr) ||
			 optlen & 0x7 || optlen > 8 * 255)
			goto e_inval;

		/* hop-by-hop / destination options are privileged option */
		retv = -EPERM;
		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
			break;

		opt = ipv6_renew_options(sk, np->opt, optname,
					 (struct ipv6_opt_hdr __user *)optval,
					 optlen);
		if (IS_ERR(opt)) {
			retv = PTR_ERR(opt);
			break;
		}

		/* routing header option needs extra check */
		retv = -EINVAL;
		if (optname == IPV6_RTHDR && opt && opt->srcrt) {
			struct ipv6_rt_hdr *rthdr = opt->srcrt;
			switch (rthdr->type) {
#if IS_ENABLED(CONFIG_IPV6_MIP6)
			case IPV6_SRCRT_TYPE_2:
				if (rthdr->hdrlen != 2 ||
				    rthdr->segments_left != 1)
					goto sticky_done;

				break;
#endif
			default:
				goto sticky_done;
			}
		}

		retv = 0;
		opt = ipv6_update_options(sk, opt);
sticky_done:
		if (opt)
			sock_kfree_s(sk, opt, opt->tot_len);
		break;
	}

	case IPV6_PKTINFO:
	{
		struct in6_pktinfo pkt;

		if (optlen == 0)
			goto e_inval;
		else if (optlen < sizeof(struct in6_pktinfo) || optval == NULL)
			goto e_inval;

		if (copy_from_user(&pkt, optval, sizeof(struct in6_pktinfo))) {
				retv = -EFAULT;
				break;
		}
		if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if)
			goto e_inval;

		np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
		np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr;
		retv = 0;
		break;
	}

	case IPV6_2292PKTOPTIONS:
	{
		struct ipv6_txoptions *opt = NULL;
		struct msghdr msg;
		struct flowi6 fl6;
		int junk;

		memset(&fl6, 0, sizeof(fl6));
		fl6.flowi6_oif = sk->sk_bound_dev_if;
		fl6.flowi6_mark = sk->sk_mark;

		if (optlen == 0)
			goto update;

		/* 1K is probably excessive
		 * 1K is surely not enough, 2K per standard header is 16K.
		 */
		retv = -EINVAL;
		if (optlen > 64*1024)
			break;

		opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
		retv = -ENOBUFS;
		if (opt == NULL)
			break;

		memset(opt, 0, sizeof(*opt));
		opt->tot_len = sizeof(*opt) + optlen;
		retv = -EFAULT;
		if (copy_from_user(opt+1, optval, optlen))
			goto done;

		msg.msg_controllen = optlen;
		msg.msg_control = (void*)(opt+1);

		retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk,
					     &junk, &junk);
		if (retv)
			goto done;
update:
		retv = 0;
		opt = ipv6_update_options(sk, opt);
done:
		if (opt)
			sock_kfree_s(sk, opt, opt->tot_len);
		break;
	}
	case IPV6_UNICAST_HOPS:
		if (optlen < sizeof(int))
			goto e_inval;
		if (val > 255 || val < -1)
			goto e_inval;
		np->hop_limit = val;
		retv = 0;
		break;

	case IPV6_MULTICAST_HOPS:
		if (sk->sk_type == SOCK_STREAM)
			break;
		if (optlen < sizeof(int))
			goto e_inval;
		if (val > 255 || val < -1)
			goto e_inval;
		np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
		retv = 0;
		break;

	case IPV6_MULTICAST_LOOP:
		if (optlen < sizeof(int))
			goto e_inval;
		if (val != valbool)
			goto e_inval;
		np->mc_loop = valbool;
		retv = 0;
		break;

	case IPV6_UNICAST_IF:
	{
		struct net_device *dev = NULL;
		int ifindex;

		if (optlen != sizeof(int))
			goto e_inval;

		ifindex = (__force int)ntohl((__force __be32)val);
		if (ifindex == 0) {
			np->ucast_oif = 0;
			retv = 0;
			break;
		}

		dev = dev_get_by_index(net, ifindex);
		retv = -EADDRNOTAVAIL;
		if (!dev)
			break;
		dev_put(dev);

		retv = -EINVAL;
		if (sk->sk_bound_dev_if)
			break;

		np->ucast_oif = ifindex;
		retv = 0;
		break;
	}

	case IPV6_MULTICAST_IF:
		if (sk->sk_type == SOCK_STREAM)
			break;
		if (optlen < sizeof(int))
			goto e_inval;

		if (val) {
			struct net_device *dev;

			if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
				goto e_inval;

			dev = dev_get_by_index(net, val);
			if (!dev) {
				retv = -ENODEV;
				break;
			}
			dev_put(dev);
		}
		np->mcast_oif = val;
		retv = 0;
		break;
	case IPV6_ADD_MEMBERSHIP:
	case IPV6_DROP_MEMBERSHIP:
	{
		struct ipv6_mreq mreq;

		if (optlen < sizeof(struct ipv6_mreq))
			goto e_inval;

		retv = -EPROTO;
		if (inet_sk(sk)->is_icsk)
			break;

		retv = -EFAULT;
		if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
			break;

		if (optname == IPV6_ADD_MEMBERSHIP)
			retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
		else
			retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
		break;
	}
	case IPV6_JOIN_ANYCAST:
	case IPV6_LEAVE_ANYCAST:
	{
		struct ipv6_mreq mreq;

		if (optlen < sizeof(struct ipv6_mreq))
			goto e_inval;

		retv = -EFAULT;
		if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
			break;

		if (optname == IPV6_JOIN_ANYCAST)
			retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
		else
			retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
		break;
	}
	case MCAST_JOIN_GROUP:
	case MCAST_LEAVE_GROUP:
	{
		struct group_req greq;
		struct sockaddr_in6 *psin6;

		if (optlen < sizeof(struct group_req))
			goto e_inval;

		retv = -EFAULT;
		if (copy_from_user(&greq, optval, sizeof(struct group_req)))
			break;
		if (greq.gr_group.ss_family != AF_INET6) {
			retv = -EADDRNOTAVAIL;
			break;
		}
		psin6 = (struct sockaddr_in6 *)&greq.gr_group;
		if (optname == MCAST_JOIN_GROUP)
			retv = ipv6_sock_mc_join(sk, greq.gr_interface,
				&psin6->sin6_addr);
		else
			retv = ipv6_sock_mc_drop(sk, greq.gr_interface,
				&psin6->sin6_addr);
		break;
	}
	case MCAST_JOIN_SOURCE_GROUP:
	case MCAST_LEAVE_SOURCE_GROUP:
	case MCAST_BLOCK_SOURCE:
	case MCAST_UNBLOCK_SOURCE:
	{
		struct group_source_req greqs;
		int omode, add;

		if (optlen < sizeof(struct group_source_req))
			goto e_inval;
		if (copy_from_user(&greqs, optval, sizeof(greqs))) {
			retv = -EFAULT;
			break;
		}
		if (greqs.gsr_group.ss_family != AF_INET6 ||
		    greqs.gsr_source.ss_family != AF_INET6) {
			retv = -EADDRNOTAVAIL;
			break;
		}
		if (optname == MCAST_BLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 1;
		} else if (optname == MCAST_UNBLOCK_SOURCE) {
			omode = MCAST_EXCLUDE;
			add = 0;
		} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
			struct sockaddr_in6 *psin6;

			psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
			retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
				&psin6->sin6_addr);
			/* prior join w/ different source is ok */
			if (retv && retv != -EADDRINUSE)
				break;
			omode = MCAST_INCLUDE;
			add = 1;
		} else /* MCAST_LEAVE_SOURCE_GROUP */ {
			omode = MCAST_INCLUDE;
			add = 0;
		}
		retv = ip6_mc_source(add, omode, sk, &greqs);
		break;
	}
	case MCAST_MSFILTER:
	{
		struct group_filter *gsf;

		if (optlen < GROUP_FILTER_SIZE(0))
			goto e_inval;
		if (optlen > sysctl_optmem_max) {
			retv = -ENOBUFS;
			break;
		}
		gsf = kmalloc(optlen,GFP_KERNEL);
		if (!gsf) {
			retv = -ENOBUFS;
			break;
		}
		retv = -EFAULT;
		if (copy_from_user(gsf, optval, optlen)) {
			kfree(gsf);
			break;
		}
		/* numsrc >= (4G-140)/128 overflow in 32 bits */
		if (gsf->gf_numsrc >= 0x1ffffffU ||
		    gsf->gf_numsrc > sysctl_mld_max_msf) {
			kfree(gsf);
			retv = -ENOBUFS;
			break;
		}
		if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
			kfree(gsf);
			retv = -EINVAL;
			break;
		}
		retv = ip6_mc_msfilter(sk, gsf);
		kfree(gsf);

		break;
	}
	case IPV6_ROUTER_ALERT:
		if (optlen < sizeof(int))
			goto e_inval;
		retv = ip6_ra_control(sk, val);
		break;
	case IPV6_MTU_DISCOVER:
		if (optlen < sizeof(int))
			goto e_inval;
		if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE)
			goto e_inval;
		np->pmtudisc = val;
		retv = 0;
		break;
	case IPV6_MTU:
		if (optlen < sizeof(int))
			goto e_inval;
		if (val && val < IPV6_MIN_MTU)
			goto e_inval;
		np->frag_size = val;
		retv = 0;
		break;
	case IPV6_RECVERR:
		if (optlen < sizeof(int))
			goto e_inval;
		np->recverr = valbool;
		if (!val)
			skb_queue_purge(&sk->sk_error_queue);
		retv = 0;
		break;
	case IPV6_FLOWINFO_SEND:
		if (optlen < sizeof(int))
			goto e_inval;
		np->sndflow = valbool;
		retv = 0;
		break;
	case IPV6_FLOWLABEL_MGR:
		retv = ipv6_flowlabel_opt(sk, optval, optlen);
		break;
	case IPV6_IPSEC_POLICY:
	case IPV6_XFRM_POLICY:
		retv = -EPERM;
		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
			break;
		retv = xfrm_user_policy(sk, optname, optval, optlen);
		break;

	case IPV6_ADDR_PREFERENCES:
	    {
		unsigned int pref = 0;
		unsigned int prefmask = ~0;

		if (optlen < sizeof(int))
			goto e_inval;

		retv = -EINVAL;

		/* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */
		switch (val & (IPV6_PREFER_SRC_PUBLIC|
			       IPV6_PREFER_SRC_TMP|
			       IPV6_PREFER_SRC_PUBTMP_DEFAULT)) {
		case IPV6_PREFER_SRC_PUBLIC:
			pref |= IPV6_PREFER_SRC_PUBLIC;
			break;
		case IPV6_PREFER_SRC_TMP:
			pref |= IPV6_PREFER_SRC_TMP;
			break;
		case IPV6_PREFER_SRC_PUBTMP_DEFAULT:
			break;
		case 0:
			goto pref_skip_pubtmp;
		default:
			goto e_inval;
		}

		prefmask &= ~(IPV6_PREFER_SRC_PUBLIC|
			      IPV6_PREFER_SRC_TMP);
pref_skip_pubtmp:

		/* check HOME/COA conflicts */
		switch (val & (IPV6_PREFER_SRC_HOME|IPV6_PREFER_SRC_COA)) {
		case IPV6_PREFER_SRC_HOME:
			break;
		case IPV6_PREFER_SRC_COA:
			pref |= IPV6_PREFER_SRC_COA;
		case 0:
			goto pref_skip_coa;
		default:
			goto e_inval;
		}

		prefmask &= ~IPV6_PREFER_SRC_COA;
pref_skip_coa:

		/* check CGA/NONCGA conflicts */
		switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) {
		case IPV6_PREFER_SRC_CGA:
		case IPV6_PREFER_SRC_NONCGA:
		case 0:
			break;
		default:
			goto e_inval;
		}

		np->srcprefs = (np->srcprefs & prefmask) | pref;
		retv = 0;

		break;
	    }
	case IPV6_MINHOPCOUNT:
		if (optlen < sizeof(int))
			goto e_inval;
		if (val < 0 || val > 255)
			goto e_inval;
		np->min_hopcount = val;
		retv = 0;
		break;
	case IPV6_DONTFRAG:
		np->dontfrag = valbool;
		retv = 0;
		break;
	}

	release_sock(sk);

	return retv;

e_inval:
	release_sock(sk);
	return -EINVAL;
}
示例#6
0
int ipv6_setsockopt(struct sock *sk, int level, int optname, char *optval, 
		    int optlen)
{
	struct ipv6_pinfo *np = &sk->net_pinfo.af_inet6;
	int val, valbool;
	int retv = -ENOPROTOOPT;

	if(level==SOL_IP && sk->type != SOCK_RAW)
		return udp_prot.setsockopt(sk, level, optname, optval, optlen);

	if(level!=SOL_IPV6)
		goto out;

	if (optval == NULL)
		val=0;
	else if (get_user(val, (int *) optval))
		return -EFAULT;

	valbool = (val!=0);

	lock_sock(sk);

	switch (optname) {

	case IPV6_ADDRFORM:
		if (val == PF_INET) {
			struct ipv6_txoptions *opt;
			struct sk_buff *pktopt;

			if (sk->protocol != IPPROTO_UDP &&
			    sk->protocol != IPPROTO_TCP)
				break;

			if (sk->state != TCP_ESTABLISHED) {
				retv = -ENOTCONN;
				break;
			}

			if (!(ipv6_addr_type(&np->daddr) & IPV6_ADDR_MAPPED)) {
				retv = -EADDRNOTAVAIL;
				break;
			}

			fl6_free_socklist(sk);
			ipv6_sock_mc_close(sk);

			if (sk->protocol == IPPROTO_TCP) {
				struct tcp_opt *tp = &(sk->tp_pinfo.af_tcp);

				local_bh_disable();
				sock_prot_dec_use(sk->prot);
				sock_prot_inc_use(&tcp_prot);
				local_bh_enable();
				sk->prot = &tcp_prot;
				tp->af_specific = &ipv4_specific;
				sk->socket->ops = &inet_stream_ops;
				sk->family = PF_INET;
				tcp_sync_mss(sk, tp->pmtu_cookie);
			} else {
				local_bh_disable();
				sock_prot_dec_use(sk->prot);
				sock_prot_inc_use(&udp_prot);
				local_bh_enable();
				sk->prot = &udp_prot;
				sk->socket->ops = &inet_dgram_ops;
				sk->family = PF_INET;
			}
			opt = xchg(&np->opt, NULL);
			if (opt)
				sock_kfree_s(sk, opt, opt->tot_len);
			pktopt = xchg(&np->pktoptions, NULL);
			if (pktopt)
				kfree_skb(pktopt);

			sk->destruct = inet_sock_destruct;
#ifdef INET_REFCNT_DEBUG
			atomic_dec(&inet6_sock_nr);
#endif
			MOD_DEC_USE_COUNT;
			retv = 0;
			break;
		}
		goto e_inval;

	case IPV6_PKTINFO:
		np->rxopt.bits.rxinfo = valbool;
		retv = 0;
		break;

	case IPV6_HOPLIMIT:
		np->rxopt.bits.rxhlim = valbool;
		retv = 0;
		break;

	case IPV6_RTHDR:
		if (val < 0 || val > 2)
			goto e_inval;
		np->rxopt.bits.srcrt = val;
		retv = 0;
		break;

	case IPV6_HOPOPTS:
		np->rxopt.bits.hopopts = valbool;
		retv = 0;
		break;

	case IPV6_AUTHHDR:
		np->rxopt.bits.authhdr = valbool;
		retv = 0;
		break;

	case IPV6_DSTOPTS:
		np->rxopt.bits.dstopts = valbool;
		retv = 0;
		break;

	case IPV6_FLOWINFO:
		np->rxopt.bits.rxflow = valbool;
		retv = 0;
		break;

	case IPV6_PKTOPTIONS:
	{
		struct ipv6_txoptions *opt = NULL;
		struct msghdr msg;
		struct flowi fl;
		int junk;

		fl.fl6_flowlabel = 0;
		fl.oif = sk->bound_dev_if;

		if (optlen == 0)
			goto update;

		/* 1K is probably excessive
		 * 1K is surely not enough, 2K per standard header is 16K.
		 */
		retv = -EINVAL;
		if (optlen > 64*1024)
			break;

		opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
		retv = -ENOBUFS;
		if (opt == NULL)
			break;

		memset(opt, 0, sizeof(*opt));
		opt->tot_len = sizeof(*opt) + optlen;
		retv = -EFAULT;
		if (copy_from_user(opt+1, optval, optlen))
			goto done;

		msg.msg_controllen = optlen;
		msg.msg_control = (void*)(opt+1);

		retv = datagram_send_ctl(&msg, &fl, opt, &junk);
		if (retv)
			goto done;
update:
		retv = 0;
		if (sk->type == SOCK_STREAM) {
			if (opt) {
				struct tcp_opt *tp = &sk->tp_pinfo.af_tcp;
				if (!((1<<sk->state)&(TCPF_LISTEN|TCPF_CLOSE))
				    && sk->daddr != LOOPBACK4_IPV6) {
					tp->ext_header_len = opt->opt_flen + opt->opt_nflen;
					tcp_sync_mss(sk, tp->pmtu_cookie);
				}
			}
			opt = xchg(&np->opt, opt);
			sk_dst_reset(sk);
		} else {
			write_lock(&sk->dst_lock);
			opt = xchg(&np->opt, opt);
			write_unlock(&sk->dst_lock);
			sk_dst_reset(sk);
		}

done:
		if (opt)
			sock_kfree_s(sk, opt, opt->tot_len);
		break;
	}
	case IPV6_UNICAST_HOPS:
		if (val > 255 || val < -1)
			goto e_inval;
		np->hop_limit = val;
		retv = 0;
		break;

	case IPV6_MULTICAST_HOPS:
		if (sk->type == SOCK_STREAM)
			goto e_inval;
		if (val > 255 || val < -1)
			goto e_inval;
		np->mcast_hops = val;
		retv = 0;
		break;

	case IPV6_MULTICAST_LOOP:
		np->mc_loop = valbool;
		retv = 0;
		break;

	case IPV6_MULTICAST_IF:
		if (sk->type == SOCK_STREAM)
			goto e_inval;
		if (sk->bound_dev_if && sk->bound_dev_if != val)
			goto e_inval;

		if (__dev_get_by_index(val) == NULL) {
			retv = -ENODEV;
			break;
		}
		np->mcast_oif = val;
		retv = 0;
		break;
	case IPV6_ADD_MEMBERSHIP:
	case IPV6_DROP_MEMBERSHIP:
	{
		struct ipv6_mreq mreq;

		retv = -EFAULT;
		if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
			break;

		if (optname == IPV6_ADD_MEMBERSHIP)
			retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
		else
			retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
		break;
	}
	case IPV6_ROUTER_ALERT:
		retv = ip6_ra_control(sk, val, NULL);
		break;
	case IPV6_MTU_DISCOVER:
		if (val<0 || val>2)
			goto e_inval;
		np->pmtudisc = val;
		retv = 0;
		break;
	case IPV6_MTU:
		if (val && val < IPV6_MIN_MTU)
			goto e_inval;
		np->frag_size = val;
		retv = 0;
		break;
	case IPV6_RECVERR:
		np->recverr = valbool;
		if (!val)
			skb_queue_purge(&sk->error_queue);
		retv = 0;
		break;
	case IPV6_FLOWINFO_SEND:
		np->sndflow = valbool;
		retv = 0;
		break;
	case IPV6_FLOWLABEL_MGR:
		retv = ipv6_flowlabel_opt(sk, optval, optlen);
		break;

#ifdef CONFIG_NETFILTER
	default:
		retv = nf_setsockopt(sk, PF_INET6, optname, optval, 
					    optlen);
		break;
#endif

	}
	release_sock(sk);

out:
	return retv;

e_inval:
	release_sock(sk);
	return -EINVAL;
}
示例#7
0
static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
		int type, int code, int offset, __u32 info)
{
	struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
	const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
	struct ipv6_pinfo *np;
	struct sock *sk;
	int err;
	struct tcp_sock *tp; 
	__u32 seq;

	sk = inet6_lookup(&tcp_hashinfo, &hdr->daddr, th->dest, &hdr->saddr,
			  th->source, skb->dev->ifindex);

	if (sk == NULL) {
		ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
		return;
	}

	if (sk->sk_state == TCP_TIME_WAIT) {
		inet_twsk_put((struct inet_timewait_sock *)sk);
		return;
	}

	bh_lock_sock(sk);
	if (sock_owned_by_user(sk))
		NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS);

	if (sk->sk_state == TCP_CLOSE)
		goto out;

	tp = tcp_sk(sk);
	seq = ntohl(th->seq); 
	if (sk->sk_state != TCP_LISTEN &&
	    !between(seq, tp->snd_una, tp->snd_nxt)) {
		NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
		goto out;
	}

	np = inet6_sk(sk);

	if (type == ICMPV6_PKT_TOOBIG) {
		struct dst_entry *dst = NULL;

		if (sock_owned_by_user(sk))
			goto out;
		if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
			goto out;

		/* icmp should have updated the destination cache entry */
		dst = __sk_dst_check(sk, np->dst_cookie);

		if (dst == NULL) {
			struct inet_sock *inet = inet_sk(sk);
			struct flowi fl;

			/* BUGGG_FUTURE: Again, it is not clear how
			   to handle rthdr case. Ignore this complexity
			   for now.
			 */
			memset(&fl, 0, sizeof(fl));
			fl.proto = IPPROTO_TCP;
			ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
			ipv6_addr_copy(&fl.fl6_src, &np->saddr);
			fl.oif = sk->sk_bound_dev_if;
			fl.fl_ip_dport = inet->dport;
			fl.fl_ip_sport = inet->sport;

			if ((err = ip6_dst_lookup(sk, &dst, &fl))) {
				sk->sk_err_soft = -err;
				goto out;
			}

			if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
				sk->sk_err_soft = -err;
				goto out;
			}

		} else
			dst_hold(dst);

		if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
			tcp_sync_mss(sk, dst_mtu(dst));
			tcp_simple_retransmit(sk);
		} /* else let the usual retransmit timer handle it */
		dst_release(dst);
		goto out;
	}

	icmpv6_err_convert(type, code, &err);

	/* Might be for an request_sock */
	switch (sk->sk_state) {
		struct request_sock *req, **prev;
	case TCP_LISTEN:
		if (sock_owned_by_user(sk))
			goto out;

		req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
					   &hdr->saddr, inet6_iif(skb));
		if (!req)
			goto out;

		/* ICMPs are not backlogged, hence we cannot get
		 * an established socket here.
		 */
		BUG_TRAP(req->sk == NULL);

		if (seq != tcp_rsk(req)->snt_isn) {
			NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
			goto out;
		}

		inet_csk_reqsk_queue_drop(sk, req, prev);
		goto out;

	case TCP_SYN_SENT:
	case TCP_SYN_RECV:  /* Cannot happen.
			       It can, it SYNs are crossed. --ANK */ 
		if (!sock_owned_by_user(sk)) {
			sk->sk_err = err;
			sk->sk_error_report(sk);		/* Wake people up to see the error (see connect in sock.c) */

			tcp_done(sk);
		} else
			sk->sk_err_soft = err;
		goto out;
	}

	if (!sock_owned_by_user(sk) && np->recverr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	} else
		sk->sk_err_soft = err;

out:
	bh_unlock_sock(sk);
	sock_put(sk);
}