Merge branch 'fix-DCTCP-delayed-ACK'

Yuchung Cheng says:

====================
fix DCTCP delayed ACK

This patch series addresses the issue that sometimes DCTCP
fail to acknowledge the latest sequence and result in sender timeout
if inflight is small.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

include/net/tcp.h

@@ -912,8 +912,6 @@ enum tcp_ca_event {
 	CA_EVENT_LOSS,		/* loss timeout */
 	CA_EVENT_ECN_NO_CE,	/* ECT set, but not CE marked */
 	CA_EVENT_ECN_IS_CE,	/* received CE marked IP packet */
-	CA_EVENT_DELAYED_ACK,	/* Delayed ack is sent */
-	CA_EVENT_NON_DELAYED_ACK,
 };
 
 /* Information about inbound ACK, passed to cong_ops->in_ack_event() */

net/ipv4/tcp_dctcp.c

@@ -55,7 +55,6 @@ struct dctcp {
 	u32 dctcp_alpha;
 	u32 next_seq;
 	u32 ce_state;
-	u32 delayed_ack_reserved;
 	u32 loss_cwnd;
 };
 
@@ -96,7 +95,6 @@ static void dctcp_init(struct sock *sk)
 
 		ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
 
-		ca->delayed_ack_reserved = 0;
 		ca->loss_cwnd = 0;
 		ca->ce_state = 0;
 
@@ -134,7 +132,8 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 	/* State has changed from CE=0 to CE=1 and delayed
 	 * ACK has not sent yet.
 	 */
-	if (!ca->ce_state && ca->delayed_ack_reserved) {
+	if (!ca->ce_state &&
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
 		u32 tmp_rcv_nxt;
 
 		/* Save current rcv_nxt. */
@@ -164,7 +163,8 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 	/* State has changed from CE=1 to CE=0 and delayed
 	 * ACK has not sent yet.
 	 */
-	if (ca->ce_state && ca->delayed_ack_reserved) {
+	if (ca->ce_state &&
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
 		u32 tmp_rcv_nxt;
 
 		/* Save current rcv_nxt. */
@@ -248,25 +248,6 @@ static void dctcp_state(struct sock *sk, u8 new_state)
 	}
 }
 
-static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
-{
-	struct dctcp *ca = inet_csk_ca(sk);
-
-	switch (ev) {
-	case CA_EVENT_DELAYED_ACK:
-		if (!ca->delayed_ack_reserved)
-			ca->delayed_ack_reserved = 1;
-		break;
-	case CA_EVENT_NON_DELAYED_ACK:
-		if (ca->delayed_ack_reserved)
-			ca->delayed_ack_reserved = 0;
-		break;
-	default:
-		/* Don't care for the rest. */
-		break;
-	}
-}
-
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 {
 	switch (ev) {
@@ -276,10 +257,6 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	case CA_EVENT_ECN_NO_CE:
 		dctcp_ce_state_1_to_0(sk);
 		break;
-	case CA_EVENT_DELAYED_ACK:
-	case CA_EVENT_NON_DELAYED_ACK:
-		dctcp_update_ack_reserved(sk, ev);
-		break;
 	default:
 		/* Don't care for the rest. */
 		break;

net/ipv4/tcp_output.c

@@ -3523,8 +3523,6 @@ void tcp_send_delayed_ack(struct sock *sk)
 	int ato = icsk->icsk_ack.ato;
 	unsigned long timeout;
 
-	tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
-
 	if (ato > TCP_DELACK_MIN) {
 		const struct tcp_sock *tp = tcp_sk(sk);
 		int max_ato = HZ / 2;
@@ -3581,8 +3579,6 @@ void tcp_send_ack(struct sock *sk)
 	if (sk->sk_state == TCP_CLOSE)
 		return;
 
-	tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
-
 	/* We are not putting this on the write queue, so
 	 * tcp_transmit_skb() will set the ownership to this
 	 * sock.