3 files changed, 106 insertions, 0 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 29999ef73b4..ea690afa592 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -118,6 +118,7 @@ int sysctl_tcp_abc __read_mostly;
 #define IsSackFrto() (sysctl_tcp_frto == 0x2)
 
 #define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH)
+#define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH))
 
 /* Adapt the MSS value used to make delayed ack decision to the
  * real world.
@@ -198,6 +199,55 @@ static inline int tcp_in_quickack_mode(const struct sock *sk)
 	return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong;
 }
 
+static inline void TCP_ECN_queue_cwr(struct tcp_sock *tp)
+{
+	if (tp->ecn_flags&TCP_ECN_OK)
+		tp->ecn_flags |= TCP_ECN_QUEUE_CWR;
+}
+
+static inline void TCP_ECN_accept_cwr(struct tcp_sock *tp, struct sk_buff *skb)
+{
+	if (tcp_hdr(skb)->cwr)
+		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+static inline void TCP_ECN_withdraw_cwr(struct tcp_sock *tp)
+{
+	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+static inline void TCP_ECN_check_ce(struct tcp_sock *tp, struct sk_buff *skb)
+{
+	if (tp->ecn_flags&TCP_ECN_OK) {
+		if (INET_ECN_is_ce(TCP_SKB_CB(skb)->flags))
+			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+		/* Funny extension: if ECT is not set on a segment,
+		 * it is surely retransmit. It is not in ECN RFC,
+		 * but Linux follows this rule. */
+		else if (INET_ECN_is_not_ect((TCP_SKB_CB(skb)->flags)))
+			tcp_enter_quickack_mode((struct sock *)tp);
+	}
+}
+
+static inline void TCP_ECN_rcv_synack(struct tcp_sock *tp, struct tcphdr *th)
+{
+	if ((tp->ecn_flags&TCP_ECN_OK) && (!th->ece || th->cwr))
+		tp->ecn_flags &= ~TCP_ECN_OK;
+}
+
+static inline void TCP_ECN_rcv_syn(struct tcp_sock *tp, struct tcphdr *th)
+{
+	if ((tp->ecn_flags&TCP_ECN_OK) && (!th->ece || !th->cwr))
+		tp->ecn_flags &= ~TCP_ECN_OK;
+}
+
+static inline int TCP_ECN_rcv_ecn_echo(struct tcp_sock *tp, struct tcphdr *th)
+{
+	if (th->ece && !th->syn && (tp->ecn_flags&TCP_ECN_OK))
+		return 1;
+	return 0;
+}
+
 /* Buffer size and advertised window tuning.
  *
  * 1. Tuning sk->sk_sndbuf, when connection enters established state.
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a12b08fca5a..36a8fbd0e64 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -368,6 +368,12 @@ void tcp_twsk_destructor(struct sock *sk)
 
 EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
 
+static inline void TCP_ECN_openreq_child(struct tcp_sock *tp,
+					 struct request_sock *req)
+{
+	tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0;
+}
+
 /* This is not only more efficient than what we used to do, it eliminates
  * a lot of code duplication between IPv4/IPv6 SYN recv processing. -DaveM
  *
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b11025e8a49..3abe22e4b57 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -269,6 +269,56 @@ static u16 tcp_select_window(struct sock *sk)
 	return new_win;
 }
 
+static inline void TCP_ECN_send_synack(struct tcp_sock *tp,
+				       struct sk_buff *skb)
+{
+	TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_CWR;
+	if (!(tp->ecn_flags&TCP_ECN_OK))
+		TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_ECE;
+}
+
+static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	tp->ecn_flags = 0;
+	if (sysctl_tcp_ecn) {
+		TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ECE|TCPCB_FLAG_CWR;
+		tp->ecn_flags = TCP_ECN_OK;
+	}
+}
+
+static __inline__ void
+TCP_ECN_make_synack(struct request_sock *req, struct tcphdr *th)
+{
+	if (inet_rsk(req)->ecn_ok)
+		th->ece = 1;
+}
+
+static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb,
+				int tcp_header_len)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (tp->ecn_flags & TCP_ECN_OK) {
+		/* Not-retransmitted data segment: set ECT and inject CWR. */
+		if (skb->len != tcp_header_len &&
+		    !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) {
+			INET_ECN_xmit(sk);
+			if (tp->ecn_flags&TCP_ECN_QUEUE_CWR) {
+				tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
+				tcp_hdr(skb)->cwr = 1;
+				skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+			}
+		} else {
+			/* ACK or retransmitted segment: clear ECT|CE */
+			INET_ECN_dontxmit(sk);
+		}
+		if (tp->ecn_flags & TCP_ECN_DEMAND_CWR)
+			tcp_hdr(skb)->ece = 1;
+	}
+}
+
 static void tcp_build_and_update_options(__be32 *ptr, struct tcp_sock *tp,
 					 __u32 tstamp, __u8 **md5_hash)
 {