1 files changed, 142 insertions, 468 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 067213924751..552e87e3c269 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -72,7 +72,6 @@
 #include <net/inet_common.h>
 #include <net/timewait_sock.h>
 #include <net/xfrm.h>
-#include <net/netdma.h>
 #include <net/secure_seq.h>
 #include <net/tcp_memcontrol.h>
 #include <net/busy_poll.h>
@@ -90,7 +89,6 @@ int sysctl_tcp_tw_reuse __read_mostly;
 int sysctl_tcp_low_latency __read_mostly;
 EXPORT_SYMBOL(sysctl_tcp_low_latency);
 
-
 #ifdef CONFIG_TCP_MD5SIG
 static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 			       __be32 daddr, __be32 saddr, const struct tcphdr *th);
@@ -99,7 +97,7 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 struct inet_hashinfo tcp_hashinfo;
 EXPORT_SYMBOL(tcp_hashinfo);
 
-static inline __u32 tcp_v4_init_sequence(const struct sk_buff *skb)
+static  __u32 tcp_v4_init_sequence(const struct sk_buff *skb)
 {
 	return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
 					  ip_hdr(skb)->saddr,
@@ -173,7 +171,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
 			      RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
 			      IPPROTO_TCP,
-			      orig_sport, orig_dport, sk, true);
+			      orig_sport, orig_dport, sk);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		if (err == -ENETUNREACH)
@@ -208,6 +206,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	inet->inet_dport = usin->sin_port;
 	inet->inet_daddr = daddr;
 
+	inet_set_txhash(sk);
+
 	inet_csk(sk)->icsk_ext_hdr_len = 0;
 	if (inet_opt)
 		inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
@@ -269,7 +269,7 @@ EXPORT_SYMBOL(tcp_v4_connect);
  * It can be called through tcp_release_cb() if socket was owned by user
  * at the time tcp_v4_err() was called to handle ICMP message.
  */
-static void tcp_v4_mtu_reduced(struct sock *sk)
+void tcp_v4_mtu_reduced(struct sock *sk)
 {
 	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
@@ -300,6 +300,7 @@ static void tcp_v4_mtu_reduced(struct sock *sk)
 		tcp_simple_retransmit(sk);
 	} /* else let the usual retransmit timer handle it */
 }
+EXPORT_SYMBOL(tcp_v4_mtu_reduced);
 
 static void do_redirect(struct sk_buff *skb, struct sock *sk)
 {
@@ -336,17 +337,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	const int code = icmp_hdr(icmp_skb)->code;
 	struct sock *sk;
 	struct sk_buff *skb;
-	struct request_sock *req;
-	__u32 seq;
+	struct request_sock *fastopen;
+	__u32 seq, snd_una;
 	__u32 remaining;
 	int err;
 	struct net *net = dev_net(icmp_skb->dev);
 
-	if (icmp_skb->len < (iph->ihl << 2) + 8) {
-		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
-		return;
-	}
-
 	sk = inet_lookup(net, &tcp_hashinfo, iph->daddr, th->dest,
 			iph->saddr, th->source, inet_iif(icmp_skb));
 	if (!sk) {
@@ -378,12 +374,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	icsk = inet_csk(sk);
 	tp = tcp_sk(sk);
-	req = tp->fastopen_rsk;
 	seq = ntohl(th->seq);
+	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
+	fastopen = tp->fastopen_rsk;
+	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
-	    !between(seq, tp->snd_una, tp->snd_nxt) &&
-	    (req == NULL || seq != tcp_rsk(req)->snt_isn)) {
-		/* For a Fast Open socket, allow seq to be snt_isn. */
+	    !between(seq, snd_una, tp->snd_nxt)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 		goto out;
 	}
@@ -426,24 +422,23 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH)
 			break;
 		if (seq != tp->snd_una  || !icsk->icsk_retransmits ||
-		    !icsk->icsk_backoff)
+		    !icsk->icsk_backoff || fastopen)
 			break;
 
-		/* XXX (TFO) - revisit the following logic for TFO */
-
 		if (sock_owned_by_user(sk))
 			break;
 
 		icsk->icsk_backoff--;
-		inet_csk(sk)->icsk_rto = (tp->srtt ? __tcp_set_rto(tp) :
-			TCP_TIMEOUT_INIT) << icsk->icsk_backoff;
-		tcp_bound_rto(sk);
+		icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) :
+					       TCP_TIMEOUT_INIT;
+		icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
 
 		skb = tcp_write_queue_head(sk);
 		BUG_ON(!skb);
 
-		remaining = icsk->icsk_rto - min(icsk->icsk_rto,
-				tcp_time_stamp - TCP_SKB_CB(skb)->when);
+		remaining = icsk->icsk_rto -
+			    min(icsk->icsk_rto,
+				tcp_time_stamp - tcp_skb_timestamp(skb));
 
 		if (remaining) {
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
@@ -462,14 +457,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		goto out;
 	}
 
-	/* XXX (TFO) - if it's a TFO socket and has been accepted, rather
-	 * than following the TCP_SYN_RECV case and closing the socket,
-	 * we ignore the ICMP error and keep trying like a fully established
-	 * socket. Is this the right thing to do?
-	 */
-	if (req && req->sk == NULL)
-		goto out;
-
 	switch (sk->sk_state) {
 		struct request_sock *req, **prev;
 	case TCP_LISTEN:
@@ -502,10 +489,13 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		goto out;
 
 	case TCP_SYN_SENT:
-	case TCP_SYN_RECV:  /* Cannot happen.
-			       It can f.e. if SYNs crossed,
-			       or Fast Open.
-			     */
+	case TCP_SYN_RECV:
+		/* Only in fast or simultaneous open. If a fast open socket is
+		 * is already accepted it is treated as a connected one below.
+		 */
+		if (fastopen && fastopen->sk == NULL)
+			break;
+
 		if (!sock_owned_by_user(sk)) {
 			sk->sk_err = err;
 
@@ -690,8 +680,9 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 
 	net = dev_net(skb_dst(skb)->dev);
 	arg.tos = ip_hdr(skb)->tos;
-	ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
-			      ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
+	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
+			      &arg, arg.iov[0].iov_len);
 
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
@@ -773,8 +764,9 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 	if (oif)
 		arg.bound_dev_if = oif;
 	arg.tos = tos;
-	ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
-			      ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
+	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
+			      &arg, arg.iov[0].iov_len);
 
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
 }
@@ -821,19 +813,21 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
  *	socket.
  */
 static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
+			      struct flowi *fl,
 			      struct request_sock *req,
-			      u16 queue_mapping)
+			      u16 queue_mapping,
+			      struct tcp_fastopen_cookie *foc)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct flowi4 fl4;
 	int err = -1;
-	struct sk_buff * skb;
+	struct sk_buff *skb;
 
 	/* First, grab a route. */
 	if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
 		return -1;
 
-	skb = tcp_make_synack(sk, dst, req, NULL);
+	skb = tcp_make_synack(sk, dst, req, foc);
 
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
@@ -843,22 +837,11 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 					    ireq->ir_rmt_addr,
 					    ireq->opt);
 		err = net_xmit_eval(err);
-		if (!tcp_rsk(req)->snt_synack && !err)
-			tcp_rsk(req)->snt_synack = tcp_time_stamp;
 	}
 
 	return err;
 }
 
-static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req)
-{
-	int res = tcp_v4_send_synack(sk, NULL, req, 0);
-
-	if (!res)
-		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
-	return res;
-}
-
 /*
  *	IPv4 request_sock destructor.
  */
@@ -878,8 +861,6 @@ bool tcp_syn_flood_action(struct sock *sk,
 	bool want_cookie = false;
 	struct listen_sock *lopt;
 
-
-
 #ifdef CONFIG_SYN_COOKIES
 	if (sysctl_tcp_syncookies) {
 		msg = "Sending cookies";
@@ -904,18 +885,16 @@ EXPORT_SYMBOL(tcp_syn_flood_action);
  */
 static struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
 {
-	const struct ip_options *opt = &(IPCB(skb)->opt);
+	const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
 	struct ip_options_rcu *dopt = NULL;
 
 	if (opt && opt->optlen) {
 		int opt_size = sizeof(*dopt) + opt->optlen;
 
 		dopt = kmalloc(opt_size, GFP_ATOMIC);
-		if (dopt) {
-			if (ip_options_echo(&dopt->opt, skb)) {
-				kfree(dopt);
-				dopt = NULL;
-			}
+		if (dopt && __ip_options_echo(&dopt->opt, skb, opt)) {
+			kfree(dopt);
+			dopt = NULL;
 		}
 	}
 	return dopt;
@@ -1070,7 +1049,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
 	if (sin->sin_family != AF_INET)
 		return -EINVAL;
 
-	if (!cmd.tcpm_key || !cmd.tcpm_keylen)
+	if (!cmd.tcpm_keylen)
 		return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
 				      AF_INET);
 
@@ -1188,7 +1167,8 @@ clear_hash_noput:
 }
 EXPORT_SYMBOL(tcp_v4_md5_hash_skb);
 
-static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *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
@@ -1241,373 +1221,81 @@ static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
 	return false;
 }
 
-#endif
+static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
+{
+	bool ret;
 
-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,
-};
+	rcu_read_lock();
+	ret = __tcp_v4_inbound_md5_hash(sk, skb);
+	rcu_read_unlock();
+
+	return ret;
+}
 
-#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)
+static void tcp_v4_init_req(struct request_sock *req, struct sock *sk,
+			    struct sk_buff *skb)
 {
-	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;
+	struct inet_request_sock *ireq = inet_rsk(req);
 
-	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,
-						ip_hdr(skb)->daddr, 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,
-					ip_hdr(skb)->daddr, 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,
-					ip_hdr(skb)->daddr, valid_foc);
-	}
-	return false;
+	ireq->ir_loc_addr = ip_hdr(skb)->daddr;
+	ireq->ir_rmt_addr = ip_hdr(skb)->saddr;
+	ireq->no_srccheck = inet_sk(sk)->transparent;
+	ireq->opt = tcp_v4_save_options(skb);
 }
 
-static int tcp_v4_conn_req_fastopen(struct sock *sk,
-				    struct sk_buff *skb,
-				    struct sk_buff *skb_synack,
-				    struct request_sock *req)
+static struct dst_entry *tcp_v4_route_req(struct sock *sk, struct flowi *fl,
+					  const struct request_sock *req,
+					  bool *strict)
 {
-	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;
+	struct dst_entry *dst = inet_csk_route_req(sk, &fl->u.ip4, req);
 
-	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;
+	if (strict) {
+		if (fl->u.ip4.daddr == inet_rsk(req)->ir_rmt_addr)
+			*strict = true;
+		else
+			*strict = false;
 	}
-	err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
-				    ireq->ir_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);
+	return dst;
+}
 
-	/* 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_metrics(child);
-	tcp_init_buffer_space(child);
+struct request_sock_ops tcp_request_sock_ops __read_mostly = {
+	.family		=	PF_INET,
+	.obj_size	=	sizeof(struct tcp_request_sock),
+	.rtx_syn_ack	=	tcp_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,
+};
 
-	/* 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;
-}
+static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
+	.mss_clamp	=	TCP_MSS_DEFAULT,
+#ifdef CONFIG_TCP_MD5SIG
+	.md5_lookup	=	tcp_v4_reqsk_md5_lookup,
+	.calc_md5_hash	=	tcp_v4_md5_hash_skb,
+#endif
+	.init_req	=	tcp_v4_init_req,
+#ifdef CONFIG_SYN_COOKIES
+	.cookie_init_seq =	cookie_v4_init_sequence,
+#endif
+	.route_req	=	tcp_v4_route_req,
+	.init_seq	=	tcp_v4_init_sequence,
+	.send_synack	=	tcp_v4_send_synack,
+	.queue_hash_add =	inet_csk_reqsk_queue_hash_add,
+};
 
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 {
-	struct tcp_options_received tmp_opt;
-	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 ((sysctl_tcp_syncookies == 2 ||
-	     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) {
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
-		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, 0, want_cookie ? NULL : &foc);
+	return tcp_conn_request(&tcp_request_sock_ops,
+				&tcp_request_sock_ipv4_ops, sk, skb);
 
-	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->ir_loc_addr = daddr;
-	ireq->ir_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, sock_net(sk));
-
-	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,
-	    fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL);
-
-	if (skb_synack) {
-		__tcp_v4_send_check(skb_synack, ireq->ir_loc_addr, ireq->ir_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->ir_loc_addr,
-		     ireq->ir_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))
-		goto drop_and_free;
-
-	return 0;
-
-drop_and_release:
-	dst_release(dst);
-drop_and_free:
-	reqsk_free(req);
 drop:
 	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return 0;
@@ -1655,6 +1343,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
 	newinet->rcv_tos      = ip_hdr(skb)->tos;
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
+	inet_set_txhash(newsk);
 	if (inet_opt)
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
 	newinet->inet_id = newtp->write_seq ^ jiffies;
@@ -1668,7 +1357,6 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	}
 	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 &&
@@ -1740,33 +1428,11 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_SYN_COOKIES
 	if (!th->syn)
-		sk = cookie_v4_check(sk, skb, &(IPCB(skb)->opt));
+		sk = cookie_v4_check(sk, skb, &TCP_SKB_CB(skb)->header.h4.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.
  *
@@ -1778,16 +1444,6 @@ static __sum16 tcp_v4_checksum_init(struct sk_buff *skb)
 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;
@@ -1902,7 +1558,17 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 	    skb_queue_len(&tp->ucopy.prequeue) == 0)
 		return false;
 
-	skb_dst_force(skb);
+	/* Before escaping RCU protected region, we need to take care of skb
+	 * dst. Prequeue is only enabled for established sockets.
+	 * For such sockets, we might need the skb dst only to set sk->sk_rx_dst
+	 * Instead of doing full sk_rx_dst validity here, let's perform
+	 * an optimistic check.
+	 */
+	if (likely(sk->sk_rx_dst))
+		skb_dst_drop(skb);
+	else
+		skb_dst_force(skb);
+
 	__skb_queue_tail(&tp->ucopy.prequeue, skb);
 	tp->ucopy.memory += skb->truesize;
 	if (tp->ucopy.memory > sk->sk_rcvbuf) {
@@ -1961,16 +1627,25 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	 * 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))
+
+	if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo))
 		goto csum_error;
 
 	th = tcp_hdr(skb);
 	iph = ip_hdr(skb);
+	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
+	 * barrier() makes sure compiler wont play fool^Waliasing games.
+	 */
+	memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
+		sizeof(struct inet_skb_parm));
+	barrier();
+
 	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)->tcp_flags = tcp_flag_byte(th);
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
 	TCP_SKB_CB(skb)->sacked	 = 0;
 
@@ -1989,6 +1664,18 @@ process:
 
 	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
+
+#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_and_relse;
+#endif
+
 	nf_reset(skb);
 
 	if (sk_filter(sk, skb))
@@ -2000,18 +1687,8 @@ process:
 	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 = net_dma_find_channel();
-		if (tp->ucopy.dma_chan)
+		if (!tcp_prequeue(sk, skb))
 			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,
 					   sk->sk_rcvbuf + sk->sk_sndbuf))) {
 		bh_unlock_sock(sk);
@@ -2095,9 +1772,11 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
-	dst_hold(dst);
-	sk->sk_rx_dst = dst;
-	inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+	if (dst) {
+		dst_hold(dst);
+		sk->sk_rx_dst = dst;
+		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+	}
 }
 EXPORT_SYMBOL(inet_sk_rx_dst_set);
 
@@ -2118,6 +1797,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = {
 	.compat_setsockopt = compat_ip_setsockopt,
 	.compat_getsockopt = compat_ip_getsockopt,
 #endif
+	.mtu_reduced	   = tcp_v4_mtu_reduced,
 };
 EXPORT_SYMBOL(ipv4_specific);
 
@@ -2170,11 +1850,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	}
 #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);
 
@@ -2512,7 +2187,7 @@ int tcp_seq_open(struct inode *inode, struct file *file)
 
 	s = ((struct seq_file *)file->private_data)->private;
 	s->family		= afinfo->family;
-	s->last_pos 		= 0;
+	s->last_pos		= 0;
 	return 0;
 }
 EXPORT_SYMBOL(tcp_seq_open);
@@ -2629,7 +2304,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw,
 {
 	__be32 dest, src;
 	__u16 destp, srcp;
-	long delta = tw->tw_ttd - jiffies;
+	s32 delta = tw->tw_ttd - inet_tw_time_stamp();
 
 	dest  = tw->tw_daddr;
 	src   = tw->tw_rcv_saddr;
@@ -2737,7 +2412,6 @@ struct proto tcp_prot = {
 	.sendpage		= tcp_sendpage,
 	.backlog_rcv		= tcp_v4_do_rcv,
 	.release_cb		= tcp_release_cb,
-	.mtu_reduced		= tcp_v4_mtu_reduced,
 	.hash			= inet_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,