tcp_ipv4.c

	if (!tcp_sk(sk)->md5sig_info) {
		struct tcp_sock *tp = tcp_sk(sk);
		struct tcp_md5sig_info *p = kzalloc(sizeof(*p), GFP_KERNEL);

		if (!p)
			return -EINVAL;

		tp->md5sig_info = p;
		sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
	}

	newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
	if (!newkey)
		return -ENOMEM;
	return tcp_v4_md5_do_add(sk, sin->sin_addr.s_addr,
				 newkey, cmd.tcpm_keylen);
}

static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
				   __be32 saddr, __be32 daddr,
				   struct tcphdr *th, int protocol,
				   int tcplen)
{
	struct scatterlist sg[4];
	__u16 data_len;
	int block = 0;
	__sum16 old_checksum;
	struct tcp_md5sig_pool *hp;
	struct tcp4_pseudohdr *bp;
	struct hash_desc *desc;
	int err;
	unsigned int nbytes = 0;

	/*
	 * Okay, so RFC2385 is turned on for this connection,
	 * so we need to generate the MD5 hash for the packet now.
	 */

	hp = tcp_get_md5sig_pool();
	if (!hp)
		goto clear_hash_noput;

	bp = &hp->md5_blk.ip4;
	desc = &hp->md5_desc;

	/*
	 * 1. the TCP pseudo-header (in the order: source IP address,
	 * destination IP address, zero-padded protocol number, and
	 * segment length)
	 */
	bp->saddr = saddr;
	bp->daddr = daddr;
	bp->pad = 0;
	bp->protocol = protocol;
	bp->len = htons(tcplen);

	sg_init_table(sg, 4);

	sg_set_buf(&sg[block++], bp, sizeof(*bp));
	nbytes += sizeof(*bp);

	/* 2. the TCP header, excluding options, and assuming a
	 * checksum of zero/
	 */
	old_checksum = th->check;
	th->check = 0;
	sg_set_buf(&sg[block++], th, sizeof(struct tcphdr));
	nbytes += sizeof(struct tcphdr);

	/* 3. the TCP segment data (if any) */
	data_len = tcplen - (th->doff << 2);
	if (data_len > 0) {
		unsigned char *data = (unsigned char *)th + (th->doff << 2);
		sg_set_buf(&sg[block++], data, data_len);
		nbytes += data_len;
	}

	/* 4. an independently-specified key or password, known to both
	 * TCPs and presumably connection-specific
	 */
	sg_set_buf(&sg[block++], key->key, key->keylen);
	nbytes += key->keylen;

	sg_mark_end(&sg[block - 1]);

	/* Now store the Hash into the packet */
	err = crypto_hash_init(desc);
	if (err)
		goto clear_hash;
	err = crypto_hash_update(desc, sg, nbytes);
	if (err)
		goto clear_hash;
	err = crypto_hash_final(desc, md5_hash);
	if (err)
		goto clear_hash;

	/* Reset header, and free up the crypto */
	tcp_put_md5sig_pool();
	th->check = old_checksum;

out:
	return 0;
clear_hash:
	tcp_put_md5sig_pool();
clear_hash_noput:
	memset(md5_hash, 0, 16);
	goto out;
}

int tcp_v4_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
			 struct sock *sk,
			 struct dst_entry *dst,
			 struct request_sock *req,
			 struct tcphdr *th, int protocol,
			 int tcplen)
{
	__be32 saddr, daddr;

	if (sk) {
		saddr = inet_sk(sk)->saddr;
		daddr = inet_sk(sk)->daddr;
	} else {
		struct rtable *rt = (struct rtable *)dst;
		BUG_ON(!rt);
		saddr = rt->rt_src;
		daddr = rt->rt_dst;
	}
	return tcp_v4_do_calc_md5_hash(md5_hash, key,
				       saddr, daddr,
				       th, protocol, tcplen);
}

EXPORT_SYMBOL(tcp_v4_calc_md5_hash);

static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb)
{
	/*
	 * This gets called for each TCP segment that arrives
	 * so we want to be efficient.
	 * We have 3 drop cases:
	 * o No MD5 hash and one expected.
	 * o MD5 hash and we're not expecting one.
	 * o MD5 hash and its wrong.
	 */
	__u8 *hash_location = NULL;
	struct tcp_md5sig_key *hash_expected;
	const struct iphdr *iph = ip_hdr(skb);
	struct tcphdr *th = tcp_hdr(skb);
	int length = (th->doff << 2) - sizeof(struct tcphdr);
	int genhash;
	unsigned char *ptr;
	unsigned char newhash[16];

	hash_expected = tcp_v4_md5_do_lookup(sk, iph->saddr);

	/*
	 * If the TCP option length is less than the TCP_MD5SIG
	 * option length, then we can shortcut
	 */
	if (length < TCPOLEN_MD5SIG) {
		if (hash_expected)
			return 1;
		else
			return 0;
	}

	/* Okay, we can't shortcut - we have to grub through the options */
	ptr = (unsigned char *)(th + 1);
	while (length > 0) {
		int opcode = *ptr++;
		int opsize;

		switch (opcode) {
		case TCPOPT_EOL:
			goto done_opts;
		case TCPOPT_NOP:
			length--;
			continue;
		default:
			opsize = *ptr++;
			if (opsize < 2)
				goto done_opts;
			if (opsize > length)
				goto done_opts;

			if (opcode == TCPOPT_MD5SIG) {
				hash_location = ptr;
				goto done_opts;
			}
		}
		ptr += opsize-2;
		length -= opsize;
	}
done_opts:
	/* We've parsed the options - do we have a hash? */
	if (!hash_expected && !hash_location)
		return 0;

	if (hash_expected && !hash_location) {
		LIMIT_NETDEBUG(KERN_INFO "MD5 Hash expected but NOT found "
			       "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)\n",
			       NIPQUAD(iph->saddr), ntohs(th->source),
			       NIPQUAD(iph->daddr), ntohs(th->dest));
		return 1;
	}

	if (!hash_expected && hash_location) {
		LIMIT_NETDEBUG(KERN_INFO "MD5 Hash NOT expected but found "
			       "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)\n",
			       NIPQUAD(iph->saddr), ntohs(th->source),
			       NIPQUAD(iph->daddr), ntohs(th->dest));
		return 1;
	}

	/* Okay, so this is hash_expected and hash_location -
	 * so we need to calculate the checksum.
	 */
	genhash = tcp_v4_do_calc_md5_hash(newhash,
					  hash_expected,
					  iph->saddr, iph->daddr,
					  th, sk->sk_protocol,
					  skb->len);

	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
		if (net_ratelimit()) {
			printk(KERN_INFO "MD5 Hash failed for "
			       "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)%s\n",
			       NIPQUAD(iph->saddr), ntohs(th->source),
			       NIPQUAD(iph->daddr), ntohs(th->dest),
			       genhash ? " tcp_v4_calc_md5_hash failed" : "");
		}
		return 1;
	}
	return 0;
}

#endif

struct request_sock_ops tcp_request_sock_ops __read_mostly = {
	.family		=	PF_INET,
	.obj_size	=	sizeof(struct tcp_request_sock),
	.rtx_syn_ack	=	tcp_v4_send_synack,
	.send_ack	=	tcp_v4_reqsk_send_ack,
	.destructor	=	tcp_v4_reqsk_destructor,
	.send_reset	=	tcp_v4_send_reset,
};

#ifdef CONFIG_TCP_MD5SIG
static struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
	.md5_lookup	=	tcp_v4_reqsk_md5_lookup,
};
#endif

static struct timewait_sock_ops tcp_timewait_sock_ops = {
	.twsk_obj_size	= sizeof(struct tcp_timewait_sock),
	.twsk_unique	= tcp_twsk_unique,
	.twsk_destructor= tcp_twsk_destructor,
};

int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
	struct inet_request_sock *ireq;
	struct tcp_options_received tmp_opt;
	struct request_sock *req;
	__be32 saddr = ip_hdr(skb)->saddr;
	__be32 daddr = ip_hdr(skb)->daddr;
	__u32 isn = TCP_SKB_CB(skb)->when;
	struct dst_entry *dst = NULL;
#ifdef CONFIG_SYN_COOKIES
	int want_cookie = 0;
#else
#define want_cookie 0 /* Argh, why doesn't gcc optimize this :( */
#endif

	/* Never answer to SYNs send to broadcast or multicast */
	if (((struct rtable *)skb->dst)->rt_flags &
	    (RTCF_BROADCAST | RTCF_MULTICAST))
		goto drop;

	/* TW buckets are converted to open requests without
	 * limitations, they conserve resources and peer is
	 * evidently real one.
	 */
	if (inet_csk_reqsk_queue_is_full(sk) && !isn) {
#ifdef CONFIG_SYN_COOKIES
		if (sysctl_tcp_syncookies) {
			want_cookie = 1;
		} else
#endif
		goto drop;
	}

	/* Accept backlog is full. If we have already queued enough
	 * of warm entries in syn queue, drop request. It is better than
	 * clogging syn queue with openreqs with exponentially increasing
	 * timeout.
	 */
	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
		goto drop;

	req = reqsk_alloc(&tcp_request_sock_ops);
	if (!req)
		goto drop;

#ifdef CONFIG_TCP_MD5SIG
	tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops;
#endif

	tcp_clear_options(&tmp_opt);
	tmp_opt.mss_clamp = 536;
	tmp_opt.user_mss  = tcp_sk(sk)->rx_opt.user_mss;

	tcp_parse_options(skb, &tmp_opt, 0);

	if (want_cookie) {
		tcp_clear_options(&tmp_opt);
		tmp_opt.saw_tstamp = 0;
	}

	if (tmp_opt.saw_tstamp && !tmp_opt.rcv_tsval) {
		/* Some OSes (unknown ones, but I see them on web server, which
		 * contains information interesting only for windows'
		 * users) do not send their stamp in SYN. It is easy case.
		 * We simply do not advertise TS support.
		 */
		tmp_opt.saw_tstamp = 0;
		tmp_opt.tstamp_ok  = 0;
	}
	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;

	tcp_openreq_init(req, &tmp_opt, skb);

	if (security_inet_conn_request(sk, skb, req))
		goto drop_and_free;

	ireq = inet_rsk(req);
	ireq->loc_addr = daddr;
	ireq->rmt_addr = saddr;
	ireq->opt = tcp_v4_save_options(sk, skb);
	if (!want_cookie)
		TCP_ECN_create_request(req, tcp_hdr(skb));

	if (want_cookie) {
#ifdef CONFIG_SYN_COOKIES
		syn_flood_warning(skb);
#endif
		isn = cookie_v4_init_sequence(sk, skb, &req->mss);
	} else if (!isn) {
		struct inet_peer *peer = NULL;

		/* VJ's idea. We save last timestamp seen
		 * from the destination in peer table, when entering
		 * state TIME-WAIT, and check against it before
		 * accepting new connection request.
		 *
		 * If "isn" is not zero, this request hit alive
		 * timewait bucket, so that all the necessary checks
		 * are made in the function processing timewait state.
		 */
		if (tmp_opt.saw_tstamp &&
		    tcp_death_row.sysctl_tw_recycle &&
		    (dst = inet_csk_route_req(sk, req)) != NULL &&
		    (peer = rt_get_peer((struct rtable *)dst)) != NULL &&
		    peer->v4daddr == saddr) {
			if (get_seconds() < peer->tcp_ts_stamp + TCP_PAWS_MSL &&
			    (s32)(peer->tcp_ts - req->ts_recent) >
							TCP_PAWS_WINDOW) {
				NET_INC_STATS_BH(LINUX_MIB_PAWSPASSIVEREJECTED);
				dst_release(dst);
				goto drop_and_free;
			}
		}
		/* Kill the following clause, if you dislike this way. */
		else if (!sysctl_tcp_syncookies &&
			 (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
			  (sysctl_max_syn_backlog >> 2)) &&
			 (!peer || !peer->tcp_ts_stamp) &&
			 (!dst || !dst_metric(dst, RTAX_RTT))) {
			/* Without syncookies last quarter of
			 * backlog is filled with destinations,
			 * proven to be alive.
			 * It means that we continue to communicate
			 * to destinations, already remembered
			 * to the moment of synflood.
			 */
			LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open "
				       "request from %u.%u.%u.%u/%u\n",
				       NIPQUAD(saddr),
				       ntohs(tcp_hdr(skb)->source));
			dst_release(dst);
			goto drop_and_free;
		}

		isn = tcp_v4_init_sequence(skb);
	}
	tcp_rsk(req)->snt_isn = isn;

	if (tcp_v4_send_synack(sk, req, dst))
		goto drop_and_free;

	if (want_cookie) {
		reqsk_free(req);
	} else {
		inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
	}
	return 0;

drop_and_free:
	reqsk_free(req);
drop:
	return 0;
}


/*
 * The three way handshake has completed - we got a valid synack -
 * now create the new socket.
 */
struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
				  struct request_sock *req,
				  struct dst_entry *dst)
{
	struct inet_request_sock *ireq;
	struct inet_sock *newinet;
	struct tcp_sock *newtp;
	struct sock *newsk;
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key *key;
#endif

	if (sk_acceptq_is_full(sk))
		goto exit_overflow;

	if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
		goto exit;

	newsk = tcp_create_openreq_child(sk, req, skb);
	if (!newsk)
		goto exit;

	newsk->sk_gso_type = SKB_GSO_TCPV4;
	sk_setup_caps(newsk, dst);

	newtp		      = tcp_sk(newsk);
	newinet		      = inet_sk(newsk);
	ireq		      = inet_rsk(req);
	newinet->daddr	      = ireq->rmt_addr;
	newinet->rcv_saddr    = ireq->loc_addr;
	newinet->saddr	      = ireq->loc_addr;
	newinet->opt	      = ireq->opt;
	ireq->opt	      = NULL;
	newinet->mc_index     = inet_iif(skb);
	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
	inet_csk(newsk)->icsk_ext_hdr_len = 0;
	if (newinet->opt)
		inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen;
	newinet->id = newtp->write_seq ^ jiffies;

	tcp_mtup_init(newsk);
	tcp_sync_mss(newsk, dst_mtu(dst));
	newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
	tcp_initialize_rcv_mss(newsk);

#ifdef CONFIG_TCP_MD5SIG
	/* Copy over the MD5 key from the original socket */
	if ((key = tcp_v4_md5_do_lookup(sk, newinet->daddr)) != NULL) {
		/*
		 * We're using one, so create a matching key
		 * on the newsk structure. If we fail to get
		 * memory, then we end up not copying the key
		 * across. Shucks.
		 */
		char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC);
		if (newkey != NULL)
			tcp_v4_md5_do_add(newsk, inet_sk(sk)->daddr,
					  newkey, key->keylen);
	}
#endif

	__inet_hash(&tcp_hashinfo, newsk, 0);
	__inet_inherit_port(&tcp_hashinfo, sk, newsk);

	return newsk;

exit_overflow:
	NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS);
exit:
	NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS);
	dst_release(dst);
	return NULL;
}

static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
{
	struct tcphdr *th = tcp_hdr(skb);
	const struct iphdr *iph = ip_hdr(skb);
	struct sock *nsk;
	struct request_sock **prev;
	/* Find possible connection requests. */
	struct request_sock *req = inet_csk_search_req(sk, &prev, th->source,
						       iph->saddr, iph->daddr);
	if (req)
		return tcp_check_req(sk, skb, req, prev);

	nsk = inet_lookup_established(&tcp_hashinfo, iph->saddr, th->source,
				      iph->daddr, th->dest, inet_iif(skb));

	if (nsk) {
		if (nsk->sk_state != TCP_TIME_WAIT) {
			bh_lock_sock(nsk);
			return nsk;
		}
		inet_twsk_put(inet_twsk(nsk));
		return NULL;
	}

#ifdef CONFIG_SYN_COOKIES
	if (!th->rst && !th->syn && th->ack)
		sk = cookie_v4_check(sk, skb, &(IPCB(skb)->opt));
#endif
	return sk;
}

static __sum16 tcp_v4_checksum_init(struct sk_buff *skb)
{
	const struct iphdr *iph = ip_hdr(skb);

	if (skb->ip_summed == CHECKSUM_COMPLETE) {
		if (!tcp_v4_check(skb->len, iph->saddr,
				  iph->daddr, skb->csum)) {
			skb->ip_summed = CHECKSUM_UNNECESSARY;
			return 0;
		}
	}

	skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
				       skb->len, IPPROTO_TCP, 0);

	if (skb->len <= 76) {
		return __skb_checksum_complete(skb);
	}
	return 0;
}


/* The socket must have it's spinlock held when we get
 * here.
 *
 * We have a potential double-lock case here, so even when
 * doing backlog processing we use the BH locking scheme.
 * This is because we cannot sleep with the original spinlock
 * held.
 */
int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct sock *rsk;
#ifdef CONFIG_TCP_MD5SIG
	/*
	 * We really want to reject the packet as early as possible
	 * if:
	 *  o We're expecting an MD5'd packet and this is no MD5 tcp option
	 *  o There is an MD5 option and we're not expecting one
	 */
	if (tcp_v4_inbound_md5_hash(sk, skb))
		goto discard;
#endif

	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
		TCP_CHECK_TIMER(sk);
		if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
			rsk = sk;
			goto reset;
		}
		TCP_CHECK_TIMER(sk);
		return 0;
	}

	if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb))
		goto csum_err;

	if (sk->sk_state == TCP_LISTEN) {
		struct sock *nsk = tcp_v4_hnd_req(sk, skb);
		if (!nsk)
			goto discard;

		if (nsk != sk) {
			if (tcp_child_process(sk, nsk, skb)) {
				rsk = nsk;
				goto reset;
			}
			return 0;
		}
	}

	TCP_CHECK_TIMER(sk);
	if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) {
		rsk = sk;
		goto reset;
	}
	TCP_CHECK_TIMER(sk);
	return 0;

reset:
	tcp_v4_send_reset(rsk, skb);
discard:
	kfree_skb(skb);
	/* Be careful here. If this function gets more complicated and
	 * gcc suffers from register pressure on the x86, sk (in %ebx)
	 * might be destroyed here. This current version compiles correctly,
	 * but you have been warned.
	 */
	return 0;

csum_err:
	TCP_INC_STATS_BH(TCP_MIB_INERRS);
	goto discard;
}

/*
 *	From tcp_input.c
 */

int tcp_v4_rcv(struct sk_buff *skb)
{
	const struct iphdr *iph;
	struct tcphdr *th;
	struct sock *sk;
	int ret;

	if (skb->pkt_type != PACKET_HOST)
		goto discard_it;

	/* Count it even if it's bad */
	TCP_INC_STATS_BH(TCP_MIB_INSEGS);

	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
		goto discard_it;

	th = tcp_hdr(skb);

	if (th->doff < sizeof(struct tcphdr) / 4)
		goto bad_packet;
	if (!pskb_may_pull(skb, th->doff * 4))
		goto discard_it;

	/* An explanation is required here, I think.
	 * Packet length and doff are validated by header prediction,
	 * provided case of th->doff==0 is eliminated.
	 * So, we defer the checks. */
	if (!skb_csum_unnecessary(skb) && tcp_v4_checksum_init(skb))
		goto bad_packet;

	th = tcp_hdr(skb);
	iph = ip_hdr(skb);
	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
				    skb->len - th->doff * 4);
	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
	TCP_SKB_CB(skb)->when	 = 0;
	TCP_SKB_CB(skb)->flags	 = iph->tos;
	TCP_SKB_CB(skb)->sacked	 = 0;

	sk = __inet_lookup(&tcp_hashinfo, iph->saddr, th->source,
			   iph->daddr, th->dest, inet_iif(skb));
	if (!sk)
		goto no_tcp_socket;

process:
	if (sk->sk_state == TCP_TIME_WAIT)
		goto do_time_wait;

	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
		goto discard_and_relse;
	nf_reset(skb);

	if (sk_filter(sk, skb))
		goto discard_and_relse;

	skb->dev = NULL;

	bh_lock_sock_nested(sk);
	ret = 0;
	if (!sock_owned_by_user(sk)) {
#ifdef CONFIG_NET_DMA
		struct tcp_sock *tp = tcp_sk(sk);
		if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
			tp->ucopy.dma_chan = get_softnet_dma();
		if (tp->ucopy.dma_chan)
			ret = tcp_v4_do_rcv(sk, skb);
		else
#endif
		{
			if (!tcp_prequeue(sk, skb))
			ret = tcp_v4_do_rcv(sk, skb);
		}
	} else
		sk_add_backlog(sk, skb);
	bh_unlock_sock(sk);

	sock_put(sk);

	return ret;

no_tcp_socket:
	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
		goto discard_it;

	if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
bad_packet:
		TCP_INC_STATS_BH(TCP_MIB_INERRS);
	} else {
		tcp_v4_send_reset(NULL, skb);
	}

discard_it:
	/* Discard frame. */
	kfree_skb(skb);
	return 0;

discard_and_relse:
	sock_put(sk);
	goto discard_it;

do_time_wait:
	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
		inet_twsk_put(inet_twsk(sk));
		goto discard_it;
	}

	if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
		TCP_INC_STATS_BH(TCP_MIB_INERRS);
		inet_twsk_put(inet_twsk(sk));
		goto discard_it;
	}
	switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
	case TCP_TW_SYN: {
		struct sock *sk2 = inet_lookup_listener(&tcp_hashinfo,
							iph->daddr, th->dest,
							inet_iif(skb));
		if (sk2) {
			inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
			inet_twsk_put(inet_twsk(sk));
			sk = sk2;
			goto process;
		}
		/* Fall through to ACK */
	}
	case TCP_TW_ACK:
		tcp_v4_timewait_ack(sk, skb);
		break;
	case TCP_TW_RST:
		goto no_tcp_socket;
	case TCP_TW_SUCCESS:;
	}
	goto discard_it;
}

/* VJ's idea. Save last timestamp seen from this destination
 * and hold it at least for normal timewait interval to use for duplicate
 * segment detection in subsequent connections, before they enter synchronized
 * state.
 */

int tcp_v4_remember_stamp(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct rtable *rt = (struct rtable *)__sk_dst_get(sk);
	struct inet_peer *peer = NULL;
	int release_it = 0;

	if (!rt || rt->rt_dst != inet->daddr) {
		peer = inet_getpeer(inet->daddr, 1);
		release_it = 1;
	} else {
		if (!rt->peer)
			rt_bind_peer(rt, 1);
		peer = rt->peer;
	}

	if (peer) {
		if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 ||
		    (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() &&
		     peer->tcp_ts_stamp <= tp->rx_opt.ts_recent_stamp)) {
			peer->tcp_ts_stamp = tp->rx_opt.ts_recent_stamp;
			peer->tcp_ts = tp->rx_opt.ts_recent;
		}
		if (release_it)
			inet_putpeer(peer);
		return 1;
	}

	return 0;
}

int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw)
{
	struct inet_peer *peer = inet_getpeer(tw->tw_daddr, 1);

	if (peer) {
		const struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);

		if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 ||
		    (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() &&
		     peer->tcp_ts_stamp <= tcptw->tw_ts_recent_stamp)) {
			peer->tcp_ts_stamp = tcptw->tw_ts_recent_stamp;
			peer->tcp_ts	   = tcptw->tw_ts_recent;
		}
		inet_putpeer(peer);
		return 1;
	}

	return 0;
}

struct inet_connection_sock_af_ops ipv4_specific = {
	.queue_xmit	   = ip_queue_xmit,
	.send_check	   = tcp_v4_send_check,
	.rebuild_header	   = inet_sk_rebuild_header,
	.conn_request	   = tcp_v4_conn_request,
	.syn_recv_sock	   = tcp_v4_syn_recv_sock,
	.remember_stamp	   = tcp_v4_remember_stamp,
	.net_header_len	   = sizeof(struct iphdr),
	.setsockopt	   = ip_setsockopt,
	.getsockopt	   = ip_getsockopt,
	.addr2sockaddr	   = inet_csk_addr2sockaddr,
	.sockaddr_len	   = sizeof(struct sockaddr_in),
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_ip_setsockopt,
	.compat_getsockopt = compat_ip_getsockopt,
#endif
};

#ifdef CONFIG_TCP_MD5SIG
static struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
	.md5_lookup		= tcp_v4_md5_lookup,
	.calc_md5_hash		= tcp_v4_calc_md5_hash,
	.md5_add		= tcp_v4_md5_add_func,
	.md5_parse		= tcp_v4_parse_md5_keys,
};
#endif

/* NOTE: A lot of things set to zero explicitly by call to
 *       sk_alloc() so need not be done here.
 */
static int tcp_v4_init_sock(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	skb_queue_head_init(&tp->out_of_order_queue);
	tcp_init_xmit_timers(sk);
	tcp_prequeue_init(tp);

	icsk->icsk_rto = TCP_TIMEOUT_INIT;
	tp->mdev = TCP_TIMEOUT_INIT;

	/* So many TCP implementations out there (incorrectly) count the
	 * initial SYN frame in their delayed-ACK and congestion control
	 * algorithms that we must have the following bandaid to talk
	 * efficiently to them.  -DaveM
	 */
	tp->snd_cwnd = 2;

	/* See draft-stevens-tcpca-spec-01 for discussion of the
	 * initialization of these values.
	 */
	tp->snd_ssthresh = 0x7fffffff;	/* Infinity */
	tp->snd_cwnd_clamp = ~0;
	tp->mss_cache = 536;

	tp->reordering = sysctl_tcp_reordering;
	icsk->icsk_ca_ops = &tcp_init_congestion_ops;

	sk->sk_state = TCP_CLOSE;

	sk->sk_write_space = sk_stream_write_space;
	sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);

	icsk->icsk_af_ops = &ipv4_specific;
	icsk->icsk_sync_mss = tcp_sync_mss;
#ifdef CONFIG_TCP_MD5SIG
	tp->af_specific = &tcp_sock_ipv4_specific;
#endif

	sk->sk_sndbuf = sysctl_tcp_wmem[1];
	sk->sk_rcvbuf = sysctl_tcp_rmem[1];

	atomic_inc(&tcp_sockets_allocated);

	return 0;
}

int tcp_v4_destroy_sock(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tcp_clear_xmit_timers(sk);

	tcp_cleanup_congestion_control(sk);

	/* Cleanup up the write buffer. */
	tcp_write_queue_purge(sk);

	/* Cleans up our, hopefully empty, out_of_order_queue. */
	__skb_queue_purge(&tp->out_of_order_queue);

#ifdef CONFIG_TCP_MD5SIG
	/* Clean up the MD5 key list, if any */
	if (tp->md5sig_info) {
		tcp_v4_clear_md5_list(sk);
		kfree(tp->md5sig_info);
		tp->md5sig_info = NULL;
	}
#endif

#ifdef CONFIG_NET_DMA
	/* Cleans up our sk_async_wait_queue */
	__skb_queue_purge(&sk->sk_async_wait_queue);
#endif

	/* Clean prequeue, it must be empty really */
	__skb_queue_purge(&tp->ucopy.prequeue);

	/* Clean up a referenced TCP bind bucket. */
	if (inet_csk(sk)->icsk_bind_hash)
		inet_put_port(&tcp_hashinfo, sk);

	/*
	 * If sendmsg cached page exists, toss it.
	 */
	if (sk->sk_sndmsg_page) {
		__free_page(sk->sk_sndmsg_page);
		sk->sk_sndmsg_page = NULL;
	}

	atomic_dec(&tcp_sockets_allocated);

	return 0;
}

EXPORT_SYMBOL(tcp_v4_destroy_sock);

#ifdef CONFIG_PROC_FS
/* Proc filesystem TCP sock list dumping. */

static inline struct inet_timewait_sock *tw_head(struct hlist_head *head)
{
	return hlist_empty(head) ? NULL :
		list_entry(head->first, struct inet_timewait_sock, tw_node);
}

static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw)
{
	return tw->tw_node.next ?
		hlist_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
}

static void *listening_get_next(struct seq_file *seq, void *cur)
{
	struct inet_connection_sock *icsk;
	struct hlist_node *node;
	struct sock *sk = cur;
	struct tcp_iter_state* st = seq->private;

	if (!sk) {
		st->bucket = 0;
		sk = sk_head(&tcp_hashinfo.listening_hash[0]);
		goto get_sk;
	}

	++st->num;

	if (st->state == TCP_SEQ_STATE_OPENREQ) {
		struct request_sock *req = cur;

		icsk = inet_csk(st->syn_wait_sk);
		req = req->dl_next;
		while (1) {
			while (req) {
				if (req->rsk_ops->family == st->family) {
					cur = req;
					goto out;
				}
				req = req->dl_next;
			}
			if (++st->sbucket >= icsk->icsk_accept_queue.listen_opt->nr_table_entries)
				break;
get_req:
			req = icsk->icsk_accept_queue.listen_opt->syn_table[st->sbucket];
		}
		sk	  = sk_next(st->syn_wait_sk);
		st->state = TCP_SEQ_STATE_LISTENING;
		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
	} else {
		icsk = inet_csk(sk);
		read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
		if (reqsk_queue_len(&icsk->icsk_accept_queue))
			goto start_req;