1 files changed, 105 insertions, 81 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c8d28c433b2b..3e30548ac32a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -209,22 +209,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	}
 
 	if (tcp_death_row.sysctl_tw_recycle &&
-	    !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr) {
-		struct inet_peer *peer = rt_get_peer(rt, fl4->daddr);
-		/*
-		 * VJ's idea. We save last timestamp seen from
-		 * the destination in peer table, when entering state
-		 * TIME-WAIT * and initialize rx_opt.ts_recent from it,
-		 * when trying new connection.
-		 */
-		if (peer) {
-			inet_peer_refcheck(peer);
-			if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
-				tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
-				tp->rx_opt.ts_recent = peer->tcp_ts;
-			}
-		}
-	}
+	    !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr)
+		tcp_fetch_timewait_stamp(sk, &rt->dst);
 
 	inet->inet_dport = usin->sin_port;
 	inet->inet_daddr = daddr;
@@ -289,12 +275,15 @@ failure:
 EXPORT_SYMBOL(tcp_v4_connect);
 
 /*
- * This routine does path mtu discovery as defined in RFC1191.
+ * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191.
+ * 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 do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu)
+static void tcp_v4_mtu_reduced(struct sock *sk)
 {
 	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
+	u32 mtu = tcp_sk(sk)->mtu_info;
 
 	/* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs
 	 * send out by Linux are always <576bytes so they should go through
@@ -303,17 +292,10 @@ static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu)
 	if (sk->sk_state == TCP_LISTEN)
 		return;
 
-	/* We don't check in the destentry if pmtu discovery is forbidden
-	 * on this route. We just assume that no packet_to_big packets
-	 * are send back when pmtu discovery is not active.
-	 * There is a small race when the user changes this flag in the
-	 * route, but I think that's acceptable.
-	 */
-	if ((dst = __sk_dst_check(sk, 0)) == NULL)
+	dst = inet_csk_update_pmtu(sk, mtu);
+	if (!dst)
 		return;
 
-	dst->ops->update_pmtu(dst, mtu);
-
 	/* Something is about to be wrong... Remember soft error
 	 * for the case, if this connection will not able to recover.
 	 */
@@ -335,6 +317,14 @@ static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu)
 	} /* else let the usual retransmit timer handle it */
 }
 
+static void do_redirect(struct sk_buff *skb, struct sock *sk)
+{
+	struct dst_entry *dst = __sk_dst_check(sk, 0);
+
+	if (dst)
+		dst->ops->redirect(dst, sk, skb);
+}
+
 /*
  * This routine is called by the ICMP module when it gets some
  * sort of error condition.  If err < 0 then the socket should
@@ -386,8 +376,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	bh_lock_sock(sk);
 	/* If too many ICMPs get dropped on busy
 	 * servers this needs to be solved differently.
+	 * We do take care of PMTU discovery (RFC1191) special case :
+	 * we can receive locally generated ICMP messages while socket is held.
 	 */
-	if (sock_owned_by_user(sk))
+	if (sock_owned_by_user(sk) &&
+	    type != ICMP_DEST_UNREACH &&
+	    code != ICMP_FRAG_NEEDED)
 		NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
 
 	if (sk->sk_state == TCP_CLOSE)
@@ -408,6 +402,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	}
 
 	switch (type) {
+	case ICMP_REDIRECT:
+		do_redirect(icmp_skb, sk);
+		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
 		goto out;
@@ -419,8 +416,11 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 			goto out;
 
 		if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
+			tp->mtu_info = info;
 			if (!sock_owned_by_user(sk))
-				do_pmtu_discovery(sk, iph, info);
+				tcp_v4_mtu_reduced(sk);
+			else
+				set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags);
 			goto out;
 		}
 
@@ -698,8 +698,8 @@ 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_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
-		      &arg, arg.iov[0].iov_len);
+	ip_send_unicast_reply(net, skb, 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);
@@ -781,8 +781,8 @@ 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_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
-		      &arg, arg.iov[0].iov_len);
+	ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
+			      ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
 
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
 }
@@ -825,7 +825,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 			      struct request_sock *req,
 			      struct request_values *rvp,
-			      u16 queue_mapping)
+			      u16 queue_mapping,
+			      bool nocache)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct flowi4 fl4;
@@ -848,7 +849,6 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 		err = net_xmit_eval(err);
 	}
 
-	dst_release(dst);
 	return err;
 }
 
@@ -856,7 +856,7 @@ static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req,
 			      struct request_values *rvp)
 {
 	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
-	return tcp_v4_send_synack(sk, NULL, req, rvp, 0);
+	return tcp_v4_send_synack(sk, NULL, req, rvp, 0, false);
 }
 
 /*
@@ -1317,7 +1317,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	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);
+	tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
 
 	if (tmp_opt.cookie_plus > 0 &&
 	    tmp_opt.saw_tstamp &&
@@ -1375,7 +1375,6 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		isn = cookie_v4_init_sequence(sk, skb, &req->mss);
 		req->cookie_ts = tmp_opt.tstamp_ok;
 	} else if (!isn) {
-		struct inet_peer *peer = NULL;
 		struct flowi4 fl4;
 
 		/* VJ's idea. We save last timestamp seen
@@ -1390,12 +1389,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		if (tmp_opt.saw_tstamp &&
 		    tcp_death_row.sysctl_tw_recycle &&
 		    (dst = inet_csk_route_req(sk, &fl4, req)) != NULL &&
-		    fl4.daddr == saddr &&
-		    (peer = rt_get_peer((struct rtable *)dst, fl4.daddr)) != NULL) {
-			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) {
+		    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;
 			}
@@ -1404,8 +1399,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		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))) {
+			 !tcp_peer_is_proven(req, dst, false)) {
 			/* Without syncookies last quarter of
 			 * backlog is filled with destinations,
 			 * proven to be alive.
@@ -1425,7 +1419,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 
 	if (tcp_v4_send_synack(sk, dst, req,
 			       (struct request_values *)&tmp_ext,
-			       skb_get_queue_mapping(skb)) ||
+			       skb_get_queue_mapping(skb),
+			       want_cookie) ||
 	    want_cookie)
 		goto drop_and_free;
 
@@ -1623,6 +1618,20 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
 		sock_rps_save_rxhash(sk, skb);
+		if (sk->sk_rx_dst) {
+			struct dst_entry *dst = sk->sk_rx_dst;
+			if (dst->ops->check(dst, 0) == NULL) {
+				dst_release(dst);
+				sk->sk_rx_dst = NULL;
+			}
+		}
+		if (unlikely(sk->sk_rx_dst == NULL)) {
+			struct inet_sock *icsk = inet_sk(sk);
+			struct rtable *rt = skb_rtable(skb);
+
+			sk->sk_rx_dst = dst_clone(&rt->dst);
+			icsk->rx_dst_ifindex = inet_iif(skb);
+		}
 		if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
 			rsk = sk;
 			goto reset;
@@ -1672,6 +1681,49 @@ csum_err:
 }
 EXPORT_SYMBOL(tcp_v4_do_rcv);
 
+void tcp_v4_early_demux(struct sk_buff *skb)
+{
+	struct net *net = dev_net(skb->dev);
+	const struct iphdr *iph;
+	const struct tcphdr *th;
+	struct net_device *dev;
+	struct sock *sk;
+
+	if (skb->pkt_type != PACKET_HOST)
+		return;
+
+	if (!pskb_may_pull(skb, ip_hdrlen(skb) + sizeof(struct tcphdr)))
+		return;
+
+	iph = ip_hdr(skb);
+	th = (struct tcphdr *) ((char *)iph + ip_hdrlen(skb));
+
+	if (th->doff < sizeof(struct tcphdr) / 4)
+		return;
+
+	if (!pskb_may_pull(skb, ip_hdrlen(skb) + th->doff * 4))
+		return;
+
+	dev = skb->dev;
+	sk = __inet_lookup_established(net, &tcp_hashinfo,
+				       iph->saddr, th->source,
+				       iph->daddr, ntohs(th->dest),
+				       dev->ifindex);
+	if (sk) {
+		skb->sk = sk;
+		skb->destructor = sock_edemux;
+		if (sk->sk_state != TCP_TIME_WAIT) {
+			struct dst_entry *dst = sk->sk_rx_dst;
+			struct inet_sock *icsk = inet_sk(sk);
+			if (dst)
+				dst = dst_check(dst, 0);
+			if (dst &&
+			    icsk->rx_dst_ifindex == dev->ifindex)
+				skb_dst_set_noref(skb, dst);
+		}
+	}
+}
+
 /*
  *	From tcp_input.c
  */
@@ -1821,40 +1873,10 @@ do_time_wait:
 	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 ||
-	    inet->cork.fl.u.ip4.daddr != inet->inet_daddr) {
-		peer = inet_getpeer_v4(inet->inet_daddr, 1);
-		*release_it = true;
-	} else {
-		if (!rt->peer)
-			rt_bind_peer(rt, inet->inet_daddr, 1);
-		peer = rt->peer;
-		*release_it = false;
-	}
-
-	return peer;
-}
-EXPORT_SYMBOL(tcp_v4_get_peer);
-
-void *tcp_v4_tw_get_peer(struct sock *sk)
-{
-	const 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 = {
@@ -1863,7 +1885,6 @@ const struct inet_connection_sock_af_ops ipv4_specific = {
 	.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,
@@ -1953,6 +1974,9 @@ void tcp_v4_destroy_sock(struct sock *sk)
 		tp->cookie_values = NULL;
 	}
 
+	/* If socket is aborted during connect operation */
+	tcp_free_fastopen_req(tp);
+
 	sk_sockets_allocated_dec(sk);
 	sock_release_memcg(sk);
 }
@@ -2593,6 +2617,8 @@ struct proto tcp_prot = {
 	.sendmsg		= tcp_sendmsg,
 	.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,
@@ -2624,13 +2650,11 @@ EXPORT_SYMBOL(tcp_prot);
 
 static int __net_init tcp_sk_init(struct net *net)
 {
-	return inet_ctl_sock_create(&net->ipv4.tcp_sock,
-				    PF_INET, SOCK_RAW, IPPROTO_TCP, net);
+	return 0;
 }
 
 static void __net_exit tcp_sk_exit(struct net *net)
 {
-	inet_ctl_sock_destroy(net->ipv4.tcp_sock);
 }
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)