tcp_ipv4.c

	/* Add Key to the list */
	struct tcp_md5sig_key *key;
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_md5sig_info *md5sig;

	key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET);
	if (key) {
		/* Pre-existing entry - just update that one. */
		memcpy(key->key, newkey, newkeylen);
		key->keylen = newkeylen;
		return 0;
	}

	md5sig = rcu_dereference_protected(tp->md5sig_info,
					   sock_owned_by_user(sk));
	if (!md5sig) {
		md5sig = kmalloc(sizeof(*md5sig), gfp);
		if (!md5sig)
			return -ENOMEM;

		sk_nocaps_add(sk, NETIF_F_GSO_MASK);
		INIT_HLIST_HEAD(&md5sig->head);
		rcu_assign_pointer(tp->md5sig_info, md5sig);
	}

	key = sock_kmalloc(sk, sizeof(*key), gfp);
	if (!key)
		return -ENOMEM;
	if (hlist_empty(&md5sig->head) && !tcp_alloc_md5sig_pool(sk)) {
		sock_kfree_s(sk, key, sizeof(*key));
		return -ENOMEM;
	}

	memcpy(key->key, newkey, newkeylen);
	key->keylen = newkeylen;
	key->family = family;
	memcpy(&key->addr, addr,
	       (family == AF_INET6) ? sizeof(struct in6_addr) :
				      sizeof(struct in_addr));
	hlist_add_head_rcu(&key->node, &md5sig->head);
	return 0;
}
EXPORT_SYMBOL(tcp_md5_do_add);

int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_md5sig_key *key;
	struct tcp_md5sig_info *md5sig;

	key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET);
	if (!key)
		return -ENOENT;
	hlist_del_rcu(&key->node);
	atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
	kfree_rcu(key, rcu);
	md5sig = rcu_dereference_protected(tp->md5sig_info,
					   sock_owned_by_user(sk));
	if (hlist_empty(&md5sig->head))
		tcp_free_md5sig_pool();
	return 0;
}
EXPORT_SYMBOL(tcp_md5_do_del);

static void tcp_clear_md5_list(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_md5sig_key *key;
	struct hlist_node *pos, *n;
	struct tcp_md5sig_info *md5sig;

	md5sig = rcu_dereference_protected(tp->md5sig_info, 1);

	if (!hlist_empty(&md5sig->head))
		tcp_free_md5sig_pool();
	hlist_for_each_entry_safe(key, pos, n, &md5sig->head, node) {
		hlist_del_rcu(&key->node);
		atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
		kfree_rcu(key, rcu);
	}
}

static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
				 int optlen)
{
	struct tcp_md5sig cmd;
	struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr;

	if (optlen < sizeof(cmd))
		return -EINVAL;

	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)
		return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
				      AF_INET);

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

	return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
			      AF_INET, cmd.tcpm_key, cmd.tcpm_keylen,
			      GFP_KERNEL);
}

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, const struct tcp_md5sig_key *key,
			       __be32 daddr, __be32 saddr, const 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,
			const struct sock *sk, const struct request_sock *req,
			const struct sk_buff *skb)
{
	struct tcp_md5sig_pool *hp;
	struct hash_desc *desc;
	const 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 bool tcp_v4_inbound_md5_hash(struct sock *sk, const 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.
	 */
	const __u8 *hash_location = NULL;
	struct tcp_md5sig_key *hash_expected;
	const struct iphdr *iph = ip_hdr(skb);
	const struct tcphdr *th = tcp_hdr(skb);
	int genhash;
	unsigned char newhash[16];

	hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr,
					  AF_INET);
	hash_location = tcp_parse_md5sig_option(th);

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

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

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

	/* 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) {
		net_info_ratelimited("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 true;
	}
	return false;
}

#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

static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb,
			       struct request_sock *req,
			       struct tcp_fastopen_cookie *foc,
			       struct tcp_fastopen_cookie *valid_foc)
{
	bool skip_cookie = false;
	struct fastopen_queue *fastopenq;

	if (likely(!fastopen_cookie_present(foc))) {
		/* See include/net/tcp.h for the meaning of these knobs */
		if ((sysctl_tcp_fastopen & TFO_SERVER_ALWAYS) ||
		    ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD) &&
		    (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1)))
			skip_cookie = true; /* no cookie to validate */
		else
			return false;
	}
	fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
	/* A FO option is present; bump the counter. */
	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE);

	/* Make sure the listener has enabled fastopen, and we don't
	 * exceed the max # of pending TFO requests allowed before trying
	 * to validating the cookie in order to avoid burning CPU cycles
	 * unnecessarily.
	 *
	 * XXX (TFO) - The implication of checking the max_qlen before
	 * processing a cookie request is that clients can't differentiate
	 * between qlen overflow causing Fast Open to be disabled
	 * temporarily vs a server not supporting Fast Open at all.
	 */
	if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) == 0 ||
	    fastopenq == NULL || fastopenq->max_qlen == 0)
		return false;

	if (fastopenq->qlen >= fastopenq->max_qlen) {
		struct request_sock *req1;
		spin_lock(&fastopenq->lock);
		req1 = fastopenq->rskq_rst_head;
		if ((req1 == NULL) || time_after(req1->expires, jiffies)) {
			spin_unlock(&fastopenq->lock);
			NET_INC_STATS_BH(sock_net(sk),
			    LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
			/* Avoid bumping LINUX_MIB_TCPFASTOPENPASSIVEFAIL*/
			foc->len = -1;
			return false;
		}
		fastopenq->rskq_rst_head = req1->dl_next;
		fastopenq->qlen--;
		spin_unlock(&fastopenq->lock);
		reqsk_free(req1);
	}
	if (skip_cookie) {
		tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
		return true;
	}
	if (foc->len == TCP_FASTOPEN_COOKIE_SIZE) {
		if ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_CHKED) == 0) {
			tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc);
			if ((valid_foc->len != TCP_FASTOPEN_COOKIE_SIZE) ||
			    memcmp(&foc->val[0], &valid_foc->val[0],
			    TCP_FASTOPEN_COOKIE_SIZE) != 0)
				return false;
			valid_foc->len = -1;
		}
		/* Acknowledge the data received from the peer. */
		tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
		return true;
	} else if (foc->len == 0) { /* Client requesting a cookie */
		tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc);
		NET_INC_STATS_BH(sock_net(sk),
		    LINUX_MIB_TCPFASTOPENCOOKIEREQD);
	} else {
		/* Client sent a cookie with wrong size. Treat it
		 * the same as invalid and return a valid one.
		 */
		tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc);
	}
	return false;
}

static int tcp_v4_conn_req_fastopen(struct sock *sk,
				    struct sk_buff *skb,
				    struct sk_buff *skb_synack,
				    struct request_sock *req,
				    struct request_values *rvp)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
	const struct inet_request_sock *ireq = inet_rsk(req);
	struct sock *child;
	int err;

	req->num_retrans = 0;
	req->num_timeout = 0;
	req->sk = NULL;

	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
	if (child == NULL) {
		NET_INC_STATS_BH(sock_net(sk),
				 LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
		kfree_skb(skb_synack);
		return -1;
	}
	err = ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr,
				    ireq->rmt_addr, ireq->opt);
	err = net_xmit_eval(err);
	if (!err)
		tcp_rsk(req)->snt_synack = tcp_time_stamp;
	/* XXX (TFO) - is it ok to ignore error and continue? */

	spin_lock(&queue->fastopenq->lock);
	queue->fastopenq->qlen++;
	spin_unlock(&queue->fastopenq->lock);

	/* Initialize the child socket. Have to fix some values to take
	 * into account the child is a Fast Open socket and is created
	 * only out of the bits carried in the SYN packet.
	 */
	tp = tcp_sk(child);

	tp->fastopen_rsk = req;
	/* Do a hold on the listner sk so that if the listener is being
	 * closed, the child that has been accepted can live on and still
	 * access listen_lock.
	 */
	sock_hold(sk);
	tcp_rsk(req)->listener = sk;

	/* RFC1323: The window in SYN & SYN/ACK segments is never
	 * scaled. So correct it appropriately.
	 */
	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);

	/* Activate the retrans timer so that SYNACK can be retransmitted.
	 * The request socket is not added to the SYN table of the parent
	 * because it's been added to the accept queue directly.
	 */
	inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
	    TCP_TIMEOUT_INIT, TCP_RTO_MAX);

	/* Add the child socket directly into the accept queue */
	inet_csk_reqsk_queue_add(sk, req, child);

	/* Now finish processing the fastopen child socket. */
	inet_csk(child)->icsk_af_ops->rebuild_header(child);
	tcp_init_congestion_control(child);
	tcp_mtup_init(child);
	tcp_init_buffer_space(child);
	tcp_init_metrics(child);

	/* Queue the data carried in the SYN packet. We need to first
	 * bump skb's refcnt because the caller will attempt to free it.
	 *
	 * XXX (TFO) - we honor a zero-payload TFO request for now.
	 * (Any reason not to?)
	 */
	if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq + 1) {
		/* Don't queue the skb if there is no payload in SYN.
		 * XXX (TFO) - How about SYN+FIN?
		 */
		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
	} else {
		skb = skb_get(skb);
		skb_dst_drop(skb);
		__skb_pull(skb, tcp_hdr(skb)->doff * 4);
		skb_set_owner_r(skb, child);
		__skb_queue_tail(&child->sk_receive_queue, skb);
		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
		tp->syn_data_acked = 1;
	}
	sk->sk_data_ready(sk, 0);
	bh_unlock_sock(child);
	sock_put(child);
	WARN_ON(req->sk == NULL);
	return 0;
}

int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_extend_values tmp_ext;
	struct tcp_options_received tmp_opt;
	const 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;
	bool want_cookie = false;
	struct flowi4 fl4;
	struct tcp_fastopen_cookie foc = { .len = -1 };
	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
	struct sk_buff *skb_synack;
	int do_fastopen;

	/* 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) {
		want_cookie = tcp_syn_flood_action(sk, skb, "TCP");
		if (!want_cookie)
			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,
	    want_cookie ? NULL : &foc);

	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++;

		want_cookie = false;	/* not our kind of cookie */
		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(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, skb);

	if (want_cookie) {
		isn = cookie_v4_init_sequence(sk, skb, &req->mss);
		req->cookie_ts = tmp_opt.tstamp_ok;
	} else if (!isn) {
		/* 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, &fl4, req)) != NULL &&
		    fl4.daddr == saddr) {
			if (!tcp_peer_is_proven(req, dst, true)) {
				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)) &&
			 !tcp_peer_is_proven(req, dst, false)) {
			/* 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 pr_fmt("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 (dst == NULL) {
		dst = inet_csk_route_req(sk, &fl4, req);
		if (dst == NULL)
			goto drop_and_free;
	}
	do_fastopen = tcp_fastopen_check(sk, skb, req, &foc, &valid_foc);

	/* We don't call tcp_v4_send_synack() directly because we need
	 * to make sure a child socket can be created successfully before
	 * sending back synack!
	 *
	 * XXX (TFO) - Ideally one would simply call tcp_v4_send_synack()
	 * (or better yet, call tcp_send_synack() in the child context
	 * directly, but will have to fix bunch of other code first)
	 * after syn_recv_sock() except one will need to first fix the
	 * latter to remove its dependency on the current implementation
	 * of tcp_v4_send_synack()->tcp_select_initial_window().
	 */
	skb_synack = tcp_make_synack(sk, dst, req,
	    (struct request_values *)&tmp_ext,
	    fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL);

	if (skb_synack) {
		__tcp_v4_send_check(skb_synack, ireq->loc_addr, ireq->rmt_addr);
		skb_set_queue_mapping(skb_synack, skb_get_queue_mapping(skb));
	} else
		goto drop_and_free;

	if (likely(!do_fastopen)) {
		int err;
		err = ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr,
		     ireq->rmt_addr, ireq->opt);
		err = net_xmit_eval(err);
		if (err || want_cookie)
			goto drop_and_free;

		tcp_rsk(req)->snt_synack = tcp_time_stamp;
		tcp_rsk(req)->listener = NULL;
		/* Add the request_sock to the SYN table */
		inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
		if (fastopen_cookie_present(&foc) && foc.len != 0)
			NET_INC_STATS_BH(sock_net(sk),
			    LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
	} else if (tcp_v4_conn_req_fastopen(sk, skb, skb_synack, req,
	    (struct request_values *)&tmp_ext))
		goto drop_and_free;

	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
	struct ip_options_rcu *inet_opt;

	if (sk_acceptq_is_full(sk))
		goto exit_overflow;

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

	newsk->sk_gso_type = SKB_GSO_TCPV4;
	inet_sk_rx_dst_set(newsk, skb);

	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;
	inet_opt	      = ireq->opt;
	rcu_assign_pointer(newinet->inet_opt, inet_opt);
	ireq->opt	      = NULL;
	newinet->mc_index     = inet_iif(skb);
	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
	newinet->rcv_tos      = ip_hdr(skb)->tos;
	inet_csk(newsk)->icsk_ext_hdr_len = 0;
	if (inet_opt)
		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
	newinet->inet_id = newtp->write_seq ^ jiffies;

	if (!dst) {
		dst = inet_csk_route_child_sock(sk, newsk, req);
		if (!dst)
			goto put_and_exit;
	} else {
		/* syncookie case : see end of cookie_v4_check() */
	}
	sk_setup_caps(newsk, dst);

	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);
	tcp_synack_rtt_meas(newsk, req);
	newtp->total_retrans = req->num_retrans;

#ifdef CONFIG_TCP_MD5SIG
	/* Copy over the MD5 key from the original socket */
	key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr,
				AF_INET);
	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.
		 */
		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr,
			       AF_INET, key->key, key->keylen, GFP_ATOMIC);
		sk_nocaps_add(newsk, NETIF_F_GSO_MASK);
	}
#endif

	if (__inet_inherit_port(sk, newsk) < 0)
		goto put_and_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;
put_and_exit:
	inet_csk_prepare_forced_close(newsk);
	tcp_done(newsk);
	goto exit;
}
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, false);

	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 */
		struct dst_entry *dst = sk->sk_rx_dst;

		sock_rps_save_rxhash(sk, skb);
		if (dst) {
			if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
			    dst->ops->check(dst, 0) == NULL) {
				dst_release(dst);
				sk->sk_rx_dst = NULL;
			}
		}
		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) {
			sock_rps_save_rxhash(nsk, skb);
			if (tcp_child_process(sk, nsk, skb)) {
				rsk = nsk;
				goto reset;
			}
			return 0;
		}
	} else
		sock_rps_save_rxhash(sk, skb);

	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);

void tcp_v4_early_demux(struct sk_buff *skb)
{
	const struct iphdr *iph;
	const struct tcphdr *th;
	struct sock *sk;

	if (skb->pkt_type != PACKET_HOST)
		return;

	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr)))
		return;

	iph = ip_hdr(skb);
	th = tcp_hdr(skb);

	if (th->doff < sizeof(struct tcphdr) / 4)
		return;

	sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
				       iph->saddr, th->source,
				       iph->daddr, ntohs(th->dest),
				       skb->skb_iif);
	if (sk) {
		skb->sk = sk;
		skb->destructor = sock_edemux;
		if (sk->sk_state != TCP_TIME_WAIT) {
			struct dst_entry *dst = sk->sk_rx_dst;

			if (dst)
				dst = dst_check(dst, 0);
			if (dst &&
			    inet_sk(sk)->rx_dst_ifindex == skb->skb_iif)
				skb_dst_set_noref(skb, dst);
		}
	}
}

/*
 *	From tcp_input.c
 */

int tcp_v4_rcv(struct sk_buff *skb)
{
	const struct iphdr *iph;
	const 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)->ip_dsfield = ipv4_get_dsfield(iph);
	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;