tcp: accecn: unset ECT if receive or send ACE=0 in AccECN negotiaion

Based on specification:
  https://tools.ietf.org/id/draft-ietf-tcpm-accurate-ecn-28.txt

Based on Section 3.1.5 of AccECN spec (RFC9768), a TCP Server in
AccECN mode MUST NOT set ECT on any packet for the rest of the connection,
if it has received or sent at least one valid SYN or Acceptable SYN/ACK
with (AE,CWR,ECE) = (0,0,0) during the handshake.

In addition, a host in AccECN mode that is feeding back the IP-ECN
field on a SYN or SYN/ACK MUST feed back the IP-ECN field on the
latest valid SYN or acceptable SYN/ACK to arrive.

Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260131222515.8485-11-chia-yu.chang@nokia-bell-labs.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

5 files changed, 38 insertions, 11 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 13372d2cbed5..018e8ffc0717 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -20,6 +20,7 @@
 #include <net/tcp_states.h>
 #include <net/xfrm.h>
 #include <net/tcp.h>
+#include <net/tcp_ecn.h>
 #include <net/sock_reuseport.h>
 #include <net/addrconf.h>
 
@@ -1103,6 +1104,8 @@ static void reqsk_timer_handler(struct timer_list *t)
 	    (!resend ||
 	     !tcp_rtx_synack(sk_listener, req) ||
 	     inet_rsk(req)->acked)) {
+		if (req->num_retrans > 1 && tcp_rsk(req)->accecn_ok)
+			tcp_rsk(req)->accecn_fail_mode |= TCP_ACCECN_ACE_FAIL_SEND;
 		if (req->num_timeout++ == 0)
 			atomic_dec(&queue->young);
 		mod_timer(&req->rsk_timer, jiffies + tcp_reqsk_timeout(req));
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 59dafcb45c16..988d161e9918 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6469,6 +6469,8 @@ step1:
 	if (th->syn) {
 		if (tcp_ecn_mode_accecn(tp)) {
 			accecn_reflector = true;
+			tp->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield &
+					  INET_ECN_MASK;
 			if (tp->rx_opt.accecn &&
 			    tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) {
 				u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 9776c921d1bb..ec128865f5c0 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -481,6 +481,10 @@ static void tcp_ecn_openreq_child(struct sock *sk,
 		tp->syn_ect_snt = treq->syn_ect_snt;
 		tcp_accecn_third_ack(sk, skb, treq->syn_ect_snt);
 		tp->saw_accecn_opt = treq->saw_accecn_opt;
+		if (treq->accecn_fail_mode & TCP_ACCECN_ACE_FAIL_SEND)
+			tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_SEND);
+		if (treq->accecn_fail_mode & TCP_ACCECN_ACE_FAIL_RECV)
+			tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV);
 		tp->prev_ecnfield = treq->syn_ect_rcv;
 		tp->accecn_opt_demand = 1;
 		tcp_ecn_received_counters_payload(sk, skb);
@@ -749,16 +753,28 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		 */
 		if (!tcp_oow_rate_limited(sock_net(sk), skb,
 					  LINUX_MIB_TCPACKSKIPPEDSYNRECV,
-					  &tcp_rsk(req)->last_oow_ack_time) &&
-
-		    !tcp_rtx_synack(sk, req)) {
-			unsigned long expires = jiffies;
-
-			expires += tcp_reqsk_timeout(req);
-			if (!fastopen)
-				mod_timer_pending(&req->rsk_timer, expires);
-			else
-				req->rsk_timer.expires = expires;
+					  &tcp_rsk(req)->last_oow_ack_time)) {
+			if (tcp_rsk(req)->accecn_ok) {
+				u8 ect_rcv = TCP_SKB_CB(skb)->ip_dsfield &
+					     INET_ECN_MASK;
+
+				tcp_rsk(req)->syn_ect_rcv = ect_rcv;
+				if (tcp_accecn_ace(tcp_hdr(skb)) == 0x0)
+					tcp_rsk(req)->accecn_fail_mode |= TCP_ACCECN_ACE_FAIL_RECV;
+			}
+			if (!tcp_rtx_synack(sk, req)) {
+				unsigned long expires = jiffies;
+
+				if (req->num_retrans > 1 && tcp_rsk(req)->accecn_ok)
+					tcp_rsk(req)->accecn_fail_mode |= TCP_ACCECN_ACE_FAIL_SEND;
+
+				expires += tcp_reqsk_timeout(req);
+				if (!fastopen)
+					mod_timer_pending(&req->rsk_timer,
+							  expires);
+				else
+					req->rsk_timer.expires = expires;
+			}
 		}
 		return NULL;
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 22728daed436..2b356fdbf2ca 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -334,8 +334,11 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
 		return;
 
 	if (tcp_ecn_mode_accecn(tp)) {
-		if (!tcp_accecn_ace_fail_recv(tp))
+		if (!tcp_accecn_ace_fail_recv(tp) &&
+		    !tcp_accecn_ace_fail_send(tp))
 			INET_ECN_xmit(sk);
+		else
+			INET_ECN_dontxmit(sk);
 		tcp_accecn_set_ace(tp, skb, th);
 		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ACCECN;
 	} else {
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 160080c9021d..5a14a53a3c9e 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <net/tcp.h>
+#include <net/tcp_ecn.h>
 #include <net/rstreason.h>
 
 static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
@@ -479,6 +480,8 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
 	 * it's not good to give up too easily.
 	 */
 	tcp_rtx_synack(sk, req);
+	if (req->num_retrans > 1 && tcp_rsk(req)->accecn_ok)
+		tcp_rsk(req)->accecn_fail_mode |= TCP_ACCECN_ACE_FAIL_SEND;
 	req->num_timeout++;
 	tcp_update_rto_stats(sk);
 	if (!tp->retrans_stamp)