1 files changed, 74 insertions, 23 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1ed230716d5..b7ab868c828 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -369,11 +369,10 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	 * 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) &&
-	    type != ICMP_DEST_UNREACH &&
-	    code != ICMP_FRAG_NEEDED)
-		NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
-
+	if (sock_owned_by_user(sk)) {
+		if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED))
+			NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
+	}
 	if (sk->sk_state == TCP_CLOSE)
 		goto out;
 
@@ -497,6 +496,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		 * errors returned from accept().
 		 */
 		inet_csk_reqsk_queue_drop(sk, req, prev);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 		goto out;
 
 	case TCP_SYN_SENT:
@@ -657,7 +657,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 		 * no RST generated if md5 hash doesn't match.
 		 */
 		sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev),
-					     &tcp_hashinfo, ip_hdr(skb)->daddr,
+					     &tcp_hashinfo, ip_hdr(skb)->saddr,
+					     th->source, ip_hdr(skb)->daddr,
 					     ntohs(th->source), inet_iif(skb));
 		/* don't send rst if it can't find key */
 		if (!sk1)
@@ -725,7 +726,7 @@ release_sk1:
  */
 
 static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
-			    u32 win, u32 ts, int oif,
+			    u32 win, u32 tsval, u32 tsecr, int oif,
 			    struct tcp_md5sig_key *key,
 			    int reply_flags, u8 tos)
 {
@@ -746,12 +747,12 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 
 	arg.iov[0].iov_base = (unsigned char *)&rep;
 	arg.iov[0].iov_len  = sizeof(rep.th);
-	if (ts) {
+	if (tsecr) {
 		rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
 				   (TCPOPT_TIMESTAMP << 8) |
 				   TCPOLEN_TIMESTAMP);
-		rep.opt[1] = htonl(tcp_time_stamp);
-		rep.opt[2] = htonl(ts);
+		rep.opt[1] = htonl(tsval);
+		rep.opt[2] = htonl(tsecr);
 		arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED;
 	}
 
@@ -766,7 +767,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 
 #ifdef CONFIG_TCP_MD5SIG
 	if (key) {
-		int offset = (ts) ? 3 : 0;
+		int offset = (tsecr) ? 3 : 0;
 
 		rep.opt[offset++] = htonl((TCPOPT_NOP << 24) |
 					  (TCPOPT_NOP << 16) |
@@ -801,6 +802,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 
 	tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
+			tcp_time_stamp + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent,
 			tw->tw_bound_dev_if,
 			tcp_twsk_md5_key(tcptw),
@@ -820,6 +822,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 	tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
 			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
 			tcp_rsk(req)->rcv_nxt, req->rcv_wnd,
+			tcp_time_stamp,
 			req->ts_recent,
 			0,
 			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
@@ -951,7 +954,6 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *key;
-	struct hlist_node *pos;
 	unsigned int size = sizeof(struct in_addr);
 	struct tcp_md5sig_info *md5sig;
 
@@ -965,7 +967,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
 	if (family == AF_INET6)
 		size = sizeof(struct in6_addr);
 #endif
-	hlist_for_each_entry_rcu(key, pos, &md5sig->head, node) {
+	hlist_for_each_entry_rcu(key, &md5sig->head, node) {
 		if (key->family != family)
 			continue;
 		if (!memcmp(&key->addr, addr, size))
@@ -1066,14 +1068,14 @@ 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 hlist_node *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_for_each_entry_safe(key, n, &md5sig->head, node) {
 		hlist_del_rcu(&key->node);
 		atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
 		kfree_rcu(key, rcu);
@@ -1501,8 +1503,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	 * clogging syn queue with openreqs with exponentially increasing
 	 * timeout.
 	 */
-	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
+	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)
@@ -1568,7 +1572,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	if (!want_cookie || tmp_opt.tstamp_ok)
-		TCP_ECN_create_request(req, skb);
+		TCP_ECN_create_request(req, skb, sock_net(sk));
 
 	if (want_cookie) {
 		isn = cookie_v4_init_sequence(sk, skb, &req->mss);
@@ -1667,6 +1671,7 @@ drop_and_release:
 drop_and_free:
 	reqsk_free(req);
 drop:
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return 0;
 }
 EXPORT_SYMBOL(tcp_v4_conn_request);
@@ -1767,10 +1772,8 @@ exit:
 	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return NULL;
 put_and_exit:
-	tcp_clear_xmit_timers(newsk);
-	tcp_cleanup_congestion_control(newsk);
-	bh_unlock_sock(newsk);
-	sock_put(newsk);
+	inet_csk_prepare_forced_close(newsk);
+	tcp_done(newsk);
 	goto exit;
 }
 EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
@@ -1947,6 +1950,50 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 	}
 }
 
+/* Packet is added to VJ-style prequeue for processing in process
+ * context, if a reader task is waiting. Apparently, this exciting
+ * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
+ * failed somewhere. Latency? Burstiness? Well, at least now we will
+ * see, why it failed. 8)8)				  --ANK
+ *
+ */
+bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (sysctl_tcp_low_latency || !tp->ucopy.task)
+		return false;
+
+	if (skb->len <= tcp_hdrlen(skb) &&
+	    skb_queue_len(&tp->ucopy.prequeue) == 0)
+		return false;
+
+	__skb_queue_tail(&tp->ucopy.prequeue, skb);
+	tp->ucopy.memory += skb->truesize;
+	if (tp->ucopy.memory > sk->sk_rcvbuf) {
+		struct sk_buff *skb1;
+
+		BUG_ON(sock_owned_by_user(sk));
+
+		while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
+			sk_backlog_rcv(sk, skb1);
+			NET_INC_STATS_BH(sock_net(sk),
+					 LINUX_MIB_TCPPREQUEUEDROPPED);
+		}
+
+		tp->ucopy.memory = 0;
+	} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
+		wake_up_interruptible_sync_poll(sk_sleep(sk),
+					   POLLIN | POLLRDNORM | POLLRDBAND);
+		if (!inet_csk_ack_scheduled(sk))
+			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
+						  (3 * tcp_rto_min(sk)) / 4,
+						  TCP_RTO_MAX);
+	}
+	return true;
+}
+EXPORT_SYMBOL(tcp_prequeue);
+
 /*
  *	From tcp_input.c
  */
@@ -2076,6 +2123,7 @@ do_time_wait:
 	case TCP_TW_SYN: {
 		struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev),
 							&tcp_hashinfo,
+							iph->saddr, th->source,
 							iph->daddr, th->dest,
 							inet_iif(skb));
 		if (sk2) {
@@ -2611,7 +2659,7 @@ EXPORT_SYMBOL(tcp_proc_register);
 
 void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
 {
-	proc_net_remove(net, afinfo->name);
+	remove_proc_entry(afinfo->name, net->proc_net);
 }
 EXPORT_SYMBOL(tcp_proc_unregister);
 
@@ -2655,7 +2703,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len)
 	__u16 srcp = ntohs(inet->inet_sport);
 	int rx_queue;
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
@@ -2890,6 +2940,7 @@ EXPORT_SYMBOL(tcp_prot);
 
 static int __net_init tcp_sk_init(struct net *net)
 {
+	net->ipv4.sysctl_tcp_ecn = 2;
 	return 0;
 }