1 files changed, 68 insertions, 35 deletions

diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h
index f13e5cd2b1ac..e9a933641636 100644
--- a/include/net/tcp_ecn.h
+++ b/include/net/tcp_ecn.h
@@ -29,8 +29,15 @@ enum tcp_accecn_option {
 	TCP_ACCECN_OPTION_DISABLED = 0,
 	TCP_ACCECN_OPTION_MINIMUM = 1,
 	TCP_ACCECN_OPTION_FULL = 2,
+	TCP_ACCECN_OPTION_PERSIST = 3,
 };
 
+/* Apply either ECT(0) or ECT(1) based on TCP_CONG_ECT_1_NEGOTIATION flag */
+static inline void INET_ECN_xmit_ect_1_negotiation(struct sock *sk)
+{
+	__INET_ECN_xmit(sk, tcp_ca_ect_1_negotiation(sk));
+}
+
 static inline void tcp_ecn_queue_cwr(struct tcp_sock *tp)
 {
 	/* Do not set CWR if in AccECN mode! */
@@ -60,12 +67,6 @@ static inline void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
 	tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
 }
 
-/* tp->accecn_fail_mode */
-#define TCP_ACCECN_ACE_FAIL_SEND	BIT(0)
-#define TCP_ACCECN_ACE_FAIL_RECV	BIT(1)
-#define TCP_ACCECN_OPT_FAIL_SEND	BIT(2)
-#define TCP_ACCECN_OPT_FAIL_RECV	BIT(3)
-
 static inline bool tcp_accecn_ace_fail_send(const struct tcp_sock *tp)
 {
 	return tp->accecn_fail_mode & TCP_ACCECN_ACE_FAIL_SEND;
@@ -91,11 +92,6 @@ static inline void tcp_accecn_fail_mode_set(struct tcp_sock *tp, u8 mode)
 	tp->accecn_fail_mode |= mode;
 }
 
-#define TCP_ACCECN_OPT_NOT_SEEN		0x0
-#define TCP_ACCECN_OPT_EMPTY_SEEN	0x1
-#define TCP_ACCECN_OPT_COUNTER_SEEN	0x2
-#define TCP_ACCECN_OPT_FAIL_SEEN	0x3
-
 static inline u8 tcp_accecn_ace(const struct tcphdr *th)
 {
 	return (th->ae << 2) | (th->cwr << 1) | th->ece;
@@ -169,7 +165,9 @@ static inline void tcp_accecn_third_ack(struct sock *sk,
 	switch (ace) {
 	case 0x0:
 		/* Invalid value */
-		tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV);
+		if (!TCP_SKB_CB(skb)->sacked)
+			tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV |
+						     TCP_ACCECN_OPT_FAIL_RECV);
 		break;
 	case 0x7:
 	case 0x5:
@@ -398,6 +396,7 @@ static inline void tcp_accecn_init_counters(struct tcp_sock *tp)
 	tp->received_ce_pending = 0;
 	__tcp_accecn_init_bytes_counters(tp->received_ecn_bytes);
 	__tcp_accecn_init_bytes_counters(tp->delivered_ecn_bytes);
+	tp->accecn_opt_sent_w_dsack = 0;
 	tp->accecn_minlen = 0;
 	tp->accecn_opt_demand = 0;
 	tp->est_ecnfield = 0;
@@ -467,6 +466,26 @@ static inline u8 tcp_accecn_option_init(const struct sk_buff *skb,
 	return TCP_ACCECN_OPT_COUNTER_SEEN;
 }
 
+static inline void tcp_ecn_rcv_synack_accecn(struct sock *sk,
+					     const struct sk_buff *skb, u8 dsf)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
+	tp->syn_ect_rcv = dsf & INET_ECN_MASK;
+	/* Demand Accurate ECN option in response to the SYN on the SYN/ACK
+	 * and the TCP server will try to send one more packet with an AccECN
+	 * Option at a later point during the connection.
+	 */
+	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);
+
+		tcp_accecn_saw_opt_fail_recv(tp, saw_opt);
+		tp->accecn_opt_demand = 2;
+	}
+}
+
 /* See Table 2 of the AccECN draft */
 static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb,
 				      const struct tcphdr *th, u8 ip_dsfield)
@@ -489,32 +508,32 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb
 		tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
 		break;
 	case 0x1:
-	case 0x5:
 		/* +========+========+============+=============+
 		 * | A      | B      |  SYN/ACK   |  Feedback   |
 		 * |        |        |    B->A    |  Mode of A  |
 		 * |        |        | AE CWR ECE |             |
 		 * +========+========+============+=============+
-		 * | AccECN | Nonce  | 1   0   1  | (Reserved)  |
 		 * | AccECN | ECN    | 0   0   1  | Classic ECN |
 		 * | Nonce  | AccECN | 0   0   1  | Classic ECN |
 		 * | ECN    | AccECN | 0   0   1  | Classic ECN |
 		 * +========+========+============+=============+
 		 */
-		if (tcp_ecn_mode_pending(tp))
-			/* Downgrade from AccECN, or requested initially */
+		if (tcp_ca_no_fallback_rfc3168(sk))
+			tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
+		else
 			tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168);
 		break;
-	default:
-		tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
-		tp->syn_ect_rcv = 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);
-
-			tcp_accecn_saw_opt_fail_recv(tp, saw_opt);
-			tp->accecn_opt_demand = 2;
+	case 0x5:
+		if (tcp_ecn_mode_pending(tp)) {
+			tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield);
+			if (INET_ECN_is_ce(ip_dsfield)) {
+				tp->received_ce++;
+				tp->received_ce_pending++;
+			}
 		}
+		break;
+	default:
+		tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield);
 		if (INET_ECN_is_ce(ip_dsfield) &&
 		    tcp_accecn_validate_syn_feedback(sk, ace,
 						     tp->syn_ect_snt)) {
@@ -525,9 +544,11 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb
 	}
 }
 
-static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th,
+static inline void tcp_ecn_rcv_syn(struct sock *sk, const struct tcphdr *th,
 				   const struct sk_buff *skb)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
 	if (tcp_ecn_mode_pending(tp)) {
 		if (!tcp_accecn_syn_requested(th)) {
 			/* Downgrade to classic ECN feedback */
@@ -539,7 +560,8 @@ static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th,
 			tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN);
 		}
 	}
-	if (tcp_ecn_mode_rfc3168(tp) && (!th->ece || !th->cwr))
+	if (tcp_ecn_mode_rfc3168(tp) &&
+	    (!th->ece || !th->cwr || tcp_ca_no_fallback_rfc3168(sk)))
 		tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
 }
 
@@ -561,7 +583,7 @@ static inline void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb)
 		TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE;
 	else if (tcp_ca_needs_ecn(sk) ||
 		 tcp_bpf_ca_needs_ecn(sk))
-		INET_ECN_xmit(sk);
+		INET_ECN_xmit_ect_1_negotiation(sk);
 
 	if (tp->ecn_flags & TCP_ECN_MODE_ACCECN) {
 		TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ACE;
@@ -579,7 +601,8 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 	bool use_ecn, use_accecn;
 	u8 tcp_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn);
 
-	use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN;
+	use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN ||
+		     tcp_ca_needs_accecn(sk);
 	use_ecn = tcp_ecn == TCP_ECN_IN_ECN_OUT_ECN ||
 		  tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ECN ||
 		  tcp_ca_needs_ecn(sk) || bpf_needs_ecn || use_accecn;
@@ -595,7 +618,7 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 
 	if (use_ecn) {
 		if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn)
-			INET_ECN_xmit(sk);
+			INET_ECN_xmit_ect_1_negotiation(sk);
 
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
 		if (use_accecn) {
@@ -619,12 +642,22 @@ static inline void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
 }
 
 static inline void
-tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th)
+tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th,
+		    enum tcp_synack_type synack_type)
 {
-	if (tcp_rsk(req)->accecn_ok)
-		tcp_accecn_echo_syn_ect(th, tcp_rsk(req)->syn_ect_rcv);
-	else if (inet_rsk(req)->ecn_ok)
-		th->ece = 1;
+	/* Accurate ECN shall retransmit SYN/ACK with ACE=0 if the
+	 * previously retransmitted SYN/ACK also times out.
+	 */
+	if (!req->num_timeout || synack_type != TCP_SYNACK_RETRANS) {
+		if (tcp_rsk(req)->accecn_ok)
+			tcp_accecn_echo_syn_ect(th, tcp_rsk(req)->syn_ect_rcv);
+		else if (inet_rsk(req)->ecn_ok)
+			th->ece = 1;
+	} else if (tcp_rsk(req)->accecn_ok) {
+		th->ae  = 0;
+		th->cwr = 0;
+		th->ece = 0;
+	}
 }
 
 static inline bool tcp_accecn_option_beacon_check(const struct sock *sk)