tcp_ipv4.c

	if (copy_from_user(&cmd, optval, sizeof(cmd)))
		return -EFAULT;

	if (sin->sin_family != AF_INET)
		return -EINVAL;

	if (!cmd.tcpm_key || !cmd.tcpm_keylen) {
		if (!tcp_sk(sk)->md5sig_info)
			return -ENOENT;
		return tcp_v4_md5_do_del(sk, sin->sin_addr.s_addr);
	}

	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
		return -EINVAL;

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

		p = kzalloc(sizeof(*p), sk->sk_allocation);
		if (!p)
			return -EINVAL;

		tp->md5sig_info = p;
		sk_nocaps_add(sk, NETIF_F_GSO_MASK);
	}

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

static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
					__be32 daddr, __be32 saddr, int nbytes)
{
	struct tcp4_pseudohdr *bp;
	struct scatterlist sg;

	bp = &hp->md5_blk.ip4;

	/*
	 * 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 = IPPROTO_TCP;
	bp->len = cpu_to_be16(nbytes);

	sg_init_one(&sg, bp, sizeof(*bp));
	return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp));
}

static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
			       __be32 daddr, __be32 saddr, struct tcphdr *th)
{
	struct tcp_md5sig_pool *hp;
	struct hash_desc *desc;

	hp = tcp_get_md5sig_pool();
	if (!hp)
		goto clear_hash_noput;
	desc = &hp->md5_desc;

	if (crypto_hash_init(desc))
		goto clear_hash;
	if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2))
		goto clear_hash;
	if (tcp_md5_hash_header(hp, th))
		goto clear_hash;
	if (tcp_md5_hash_key(hp, key))
		goto clear_hash;
	if (crypto_hash_final(desc, md5_hash))
		goto clear_hash;

	tcp_put_md5sig_pool();
	return 0;

clear_hash:
	tcp_put_md5sig_pool();
clear_hash_noput:
	memset(md5_hash, 0, 16);
	return 1;
}

int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
			struct sock *sk, struct request_sock *req,
			struct sk_buff *skb)
{
	struct tcp_md5sig_pool *hp;
	struct hash_desc *desc;
	struct tcphdr *th = tcp_hdr(skb);
	__be32 saddr, daddr;

	if (sk) {
		saddr = inet_sk(sk)->inet_saddr;
		daddr = inet_sk(sk)->inet_daddr;
	} else if (req) {
		saddr = inet_rsk(req)->loc_addr;
		daddr = inet_rsk(req)->rmt_addr;
	} else {
		const struct iphdr *iph = ip_hdr(skb);
		saddr = iph->saddr;
		daddr = iph->daddr;
	}

	hp = tcp_get_md5sig_pool();
	if (!hp)
		goto clear_hash_noput;
	desc = &hp->md5_desc;

	if (crypto_hash_init(desc))
		goto clear_hash;

	if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, skb->len))
		goto clear_hash;
	if (tcp_md5_hash_header(hp, th))
		goto clear_hash;
	if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
		goto clear_hash;
	if (tcp_md5_hash_key(hp, key))
		goto clear_hash;
	if (crypto_hash_final(desc, md5_hash))
		goto clear_hash;

	tcp_put_md5sig_pool();
	return 0;

clear_hash:
	tcp_put_md5sig_pool();
clear_hash_noput:
	memset(md5_hash, 0, 16);
	return 1;
}
EXPORT_SYMBOL(tcp_v4_md5_hash_skb);

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 genhash;
	unsigned char newhash[16];

	hash_expected = tcp_v4_md5_do_lookup(sk, iph->saddr);
	hash_location = tcp_parse_md5sig_option(th);

	/* We've parsed the options - do we have a hash? */
	if (!hash_expected && !hash_location)
		return 0;

	if (hash_expected && !hash_location) {
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
		return 1;
	}

	if (!hash_expected && hash_location) {
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
		return 1;
	}

	/* Okay, so this is hash_expected and hash_location -
	 * so we need to calculate the checksum.
	 */
	genhash = tcp_v4_md5_hash_skb(newhash,
				      hash_expected,
				      NULL, NULL, skb);

	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
		if (net_ratelimit()) {
			printk(KERN_INFO "MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n",
			       &iph->saddr, ntohs(th->source),
			       &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_rtx_synack,
	.send_ack	=	tcp_v4_reqsk_send_ack,
	.destructor	=	tcp_v4_reqsk_destructor,
	.send_reset	=	tcp_v4_send_reset,
	.syn_ack_timeout = 	tcp_syn_ack_timeout,
};

#ifdef CONFIG_TCP_MD5SIG
static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
	.md5_lookup	=	tcp_v4_reqsk_md5_lookup,
	.calc_md5_hash	=	tcp_v4_md5_hash_skb,
};
#endif

int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_extend_values tmp_ext;
	struct tcp_options_received tmp_opt;
	u8 *hash_location;
	struct request_sock *req;
	struct inet_request_sock *ireq;
	struct tcp_sock *tp = tcp_sk(sk);
	struct dst_entry *dst = NULL;
	__be32 saddr = ip_hdr(skb)->saddr;
	__be32 daddr = ip_hdr(skb)->daddr;
	__u32 isn = TCP_SKB_CB(skb)->when;
#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 (skb_rtable(skb)->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) {
		if (net_ratelimit())
			syn_flood_warning(skb);
#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 = inet_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 = TCP_MSS_DEFAULT;
	tmp_opt.user_mss  = tp->rx_opt.user_mss;
	tcp_parse_options(skb, &tmp_opt, &hash_location, 0);

	if (tmp_opt.cookie_plus > 0 &&
	    tmp_opt.saw_tstamp &&
	    !tp->rx_opt.cookie_out_never &&
	    (sysctl_tcp_cookie_size > 0 ||
	     (tp->cookie_values != NULL &&
	      tp->cookie_values->cookie_desired > 0))) {
		u8 *c;
		u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS];
		int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE;

		if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0)
			goto drop_and_release;

		/* Secret recipe starts with IP addresses */
		*mess++ ^= (__force u32)daddr;
		*mess++ ^= (__force u32)saddr;

		/* plus variable length Initiator Cookie */
		c = (u8 *)mess;
		while (l-- > 0)
			*c++ ^= *hash_location++;

#ifdef CONFIG_SYN_COOKIES
		want_cookie = 0;	/* not our kind of cookie */
#endif
		tmp_ext.cookie_out_never = 0; /* false */
		tmp_ext.cookie_plus = tmp_opt.cookie_plus;
	} else if (!tp->rx_opt.cookie_in_always) {
		/* redundant indications, but ensure initialization. */
		tmp_ext.cookie_out_never = 1; /* true */
		tmp_ext.cookie_plus = 0;
	} else {
		goto drop_and_release;
	}
	tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always;

	if (want_cookie && !tmp_opt.saw_tstamp)
		tcp_clear_options(&tmp_opt);

	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
	tcp_openreq_init(req, &tmp_opt, skb);

	ireq = inet_rsk(req);
	ireq->loc_addr = daddr;
	ireq->rmt_addr = saddr;
	ireq->no_srccheck = inet_sk(sk)->transparent;
	ireq->opt = tcp_v4_save_options(sk, skb);

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

	if (!want_cookie || tmp_opt.tstamp_ok)
		TCP_ECN_create_request(req, tcp_hdr(skb));

	if (want_cookie) {
		isn = cookie_v4_init_sequence(sk, skb, &req->mss);
		req->cookie_ts = tmp_opt.tstamp_ok;
	} 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->daddr.addr.a4 == saddr) {
			inet_peer_refcheck(peer);
			if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
			    (s32)(peer->tcp_ts - req->ts_recent) >
							TCP_PAWS_WINDOW) {
				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
				goto drop_and_release;
			}
		}
		/* 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 %pI4/%u\n",
				       &saddr, ntohs(tcp_hdr(skb)->source));
			goto drop_and_release;
		}

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

	if (tcp_v4_send_synack(sk, dst, req,
			       (struct request_values *)&tmp_ext) ||
	    want_cookie)
		goto drop_and_free;

	inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
	return 0;

drop_and_release:
	dst_release(dst);
drop_and_free:
	reqsk_free(req);
drop:
	return 0;
}
EXPORT_SYMBOL(tcp_v4_conn_request);


/*
 * 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_nonewsk;

	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->inet_daddr   = ireq->rmt_addr;
	newinet->inet_rcv_saddr = ireq->loc_addr;
	newinet->inet_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->inet_id = newtp->write_seq ^ jiffies;

	tcp_mtup_init(newsk);
	tcp_sync_mss(newsk, dst_mtu(dst));
	newtp->advmss = dst_metric_advmss(dst);
	if (tcp_sk(sk)->rx_opt.user_mss &&
	    tcp_sk(sk)->rx_opt.user_mss < newtp->advmss)
		newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;

	tcp_initialize_rcv_mss(newsk);

#ifdef CONFIG_TCP_MD5SIG
	/* Copy over the MD5 key from the original socket */
	key = tcp_v4_md5_do_lookup(sk, newinet->inet_daddr);
	if (key != 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, newinet->inet_daddr,
					  newkey, key->keylen);
		sk_nocaps_add(newsk, NETIF_F_GSO_MASK);
	}
#endif

	if (__inet_inherit_port(sk, newsk) < 0) {
		sock_put(newsk);
		goto exit;
	}
	__inet_hash_nolisten(newsk, NULL);

	return newsk;

exit_overflow:
	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
exit_nonewsk:
	dst_release(dst);
exit:
	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
	return NULL;
}
EXPORT_SYMBOL(tcp_v4_syn_recv_sock);

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(sock_net(sk), &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->syn)
		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 */
		sock_rps_save_rxhash(sk, skb->rxhash);
		if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
			rsk = sk;
			goto reset;
		}
		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;
		}
	} else
		sock_rps_save_rxhash(sk, skb->rxhash);

	if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) {
		rsk = sk;
		goto reset;
	}
	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(sock_net(sk), TCP_MIB_INERRS);
	goto discard;
}
EXPORT_SYMBOL(tcp_v4_do_rcv);

/*
 *	From tcp_input.c
 */

int tcp_v4_rcv(struct sk_buff *skb)
{
	const struct iphdr *iph;
	struct tcphdr *th;
	struct sock *sk;
	int ret;
	struct net *net = dev_net(skb->dev);

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

	/* Count it even if it's bad */
	TCP_INC_STATS_BH(net, 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_skb(&tcp_hashinfo, skb, th->source, th->dest);
	if (!sk)
		goto no_tcp_socket;

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

	if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) {
		NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
		goto discard_and_relse;
	}

	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 = dma_find_channel(DMA_MEMCPY);
		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 if (unlikely(sk_add_backlog(sk, skb))) {
		bh_unlock_sock(sk);
		NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
		goto discard_and_relse;
	}
	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(net, 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(net, 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(dev_net(skb->dev),
							&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;
}

struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it)
{
	struct rtable *rt = (struct rtable *) __sk_dst_get(sk);
	struct inet_sock *inet = inet_sk(sk);
	struct inet_peer *peer;

	if (!rt || rt->rt_dst != inet->inet_daddr) {
		peer = inet_getpeer_v4(inet->inet_daddr, 1);
		*release_it = true;
	} else {
		if (!rt->peer)
			rt_bind_peer(rt, 1);
		peer = rt->peer;
		*release_it = false;
	}

	return peer;
}
EXPORT_SYMBOL(tcp_v4_get_peer);

void *tcp_v4_tw_get_peer(struct sock *sk)
{
	struct inet_timewait_sock *tw = inet_twsk(sk);

	return inet_getpeer_v4(tw->tw_daddr, 1);
}
EXPORT_SYMBOL(tcp_v4_tw_get_peer);

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,
	.twsk_getpeer	= tcp_v4_tw_get_peer,
};

const 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,
	.get_peer	   = tcp_v4_get_peer,
	.net_header_len	   = sizeof(struct iphdr),
	.setsockopt	   = ip_setsockopt,
	.getsockopt	   = ip_getsockopt,
	.addr2sockaddr	   = inet_csk_addr2sockaddr,
	.sockaddr_len	   = sizeof(struct sockaddr_in),
	.bind_conflict	   = inet_csk_bind_conflict,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_ip_setsockopt,
	.compat_getsockopt = compat_ip_getsockopt,
#endif
};
EXPORT_SYMBOL(ipv4_specific);

#ifdef CONFIG_TCP_MD5SIG
static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
	.md5_lookup		= tcp_v4_md5_lookup,
	.calc_md5_hash		= tcp_v4_md5_hash_skb,
	.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 = TCP_INFINITE_SSTHRESH;
	tp->snd_cwnd_clamp = ~0;
	tp->mss_cache = TCP_MSS_DEFAULT;

	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

	/* TCP Cookie Transactions */
	if (sysctl_tcp_cookie_size > 0) {
		/* Default, cookies without s_data_payload. */
		tp->cookie_values =
			kzalloc(sizeof(*tp->cookie_values),
				sk->sk_allocation);
		if (tp->cookie_values != NULL)
			kref_init(&tp->cookie_values->kref);
	}
	/* Presumed zeroed, in order of appearance:
	 *	cookie_in_always, cookie_out_never,
	 *	s_data_constant, s_data_in, s_data_out
	 */
	sk->sk_sndbuf = sysctl_tcp_wmem[1];
	sk->sk_rcvbuf = sysctl_tcp_rmem[1];

	local_bh_disable();
	percpu_counter_inc(&tcp_sockets_allocated);
	local_bh_enable();

	return 0;
}

void 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(sk);

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

	/* TCP Cookie Transactions */
	if (tp->cookie_values != NULL) {
		kref_put(&tp->cookie_values->kref,
			 tcp_cookie_values_release);
		tp->cookie_values = NULL;
	}

	percpu_counter_dec(&tcp_sockets_allocated);
}
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_nulls_head *head)
{
	return hlist_nulls_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 !is_a_nulls(tw->tw_node.next) ?
		hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
}

/*
 * Get next listener socket follow cur.  If cur is NULL, get first socket
 * starting from bucket given in st->bucket; when st->bucket is zero the
 * very first socket in the hash table is returned.
 */
static void *listening_get_next(struct seq_file *seq, void *cur)
{
	struct inet_connection_sock *icsk;
	struct hlist_nulls_node *node;
	struct sock *sk = cur;
	struct inet_listen_hashbucket *ilb;
	struct tcp_iter_state *st = seq->private;
	struct net *net = seq_file_net(seq);

	if (!sk) {
		ilb = &tcp_hashinfo.listening_hash[st->bucket];
		spin_lock_bh(&ilb->lock);
		sk = sk_nulls_head(&ilb->head);
		st->offset = 0;
		goto get_sk;
	}
	ilb = &tcp_hashinfo.listening_hash[st->bucket];
	++st->num;
	++st->offset;

	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_nulls_next(st->syn_wait_sk);
		st->state = TCP_SEQ_STATE_LISTENING;
		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
	} else {