Merge branch 'tcp-new-mechanism-to-ACK-immediately'

Yuchung Cheng says:

====================
tcp: new mechanism to ACK immediately

This patch is a follow-up feature improvement to the recent fixes on
the performance issues in ECN (delayed) ACKs. Many of the fixes use
tcp_enter_quickack_mode routine to force immediate ACKs. However the
routine also reset tracking interactive session. This is not ideal
because these immediate ACKs are required by protocol specifics
unrelated to the interactiveness nature of the application.

This patch set introduces a new flag to send a one-time immediate ACK
without changing the status of interactive session tracking. With this
patch set the immediate ACKs are generated upon these protocol states:

1) When a hole is repaired
2) When CE status changes between subsequent data packets received
3) When a data packet carries CWR flag
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 13 insertions, 10 deletions

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 0a6c9e0f2b5a..fa43b82607d9 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -167,7 +167,8 @@ enum inet_csk_ack_state_t {
 	ICSK_ACK_SCHED	= 1,
 	ICSK_ACK_TIMER  = 2,
 	ICSK_ACK_PUSHED = 4,
-	ICSK_ACK_PUSHED2 = 8
+	ICSK_ACK_PUSHED2 = 8,
+	ICSK_ACK_NOW = 16	/* Send the next ACK immediately (once) */
 };
 
 void inet_csk_init_xmit_timers(struct sock *sk,
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 8b637f9f23a2..ca61e2a659e7 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -136,7 +136,7 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 		 */
 		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
 			__tcp_send_ack(sk, ca->prior_rcv_nxt);
-		tcp_enter_quickack_mode(sk, 1);
+		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -157,7 +157,7 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 		 */
 		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
 			__tcp_send_ack(sk, ca->prior_rcv_nxt);
-		tcp_enter_quickack_mode(sk, 1);
+		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 715d541b52dd..4c2dd9f863f7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -245,16 +245,16 @@ static void tcp_ecn_queue_cwr(struct tcp_sock *tp)
 		tp->ecn_flags |= TCP_ECN_QUEUE_CWR;
 }
 
-static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb)
+static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb)
 {
 	if (tcp_hdr(skb)->cwr) {
-		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+		tcp_sk(sk)->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
 
 		/* If the sender is telling us it has entered CWR, then its
 		 * cwnd may be very low (even just 1 packet), so we should ACK
 		 * immediately.
 		 */
-		tcp_enter_quickack_mode((struct sock *)tp, 2);
+		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}
 }
 
@@ -4703,7 +4703,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	skb_dst_drop(skb);
 	__skb_pull(skb, tcp_hdr(skb)->doff * 4);
 
-	tcp_ecn_accept_cwr(tp, skb);
+	tcp_ecn_accept_cwr(sk, skb);
 
 	tp->rx_opt.dsack = 0;
 
@@ -4735,11 +4735,11 @@ queue_and_out:
 		if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
 			tcp_ofo_queue(sk);
 
-			/* RFC2581. 4.2. SHOULD send immediate ACK, when
+			/* RFC5681. 4.2. SHOULD send immediate ACK, when
 			 * gap in queue is filled.
 			 */
 			if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
-				inet_csk(sk)->icsk_ack.pingpong = 0;
+				inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 		}
 
 		if (tp->rx_opt.num_sacks)
@@ -5179,7 +5179,9 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 	    (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat ||
 	     __tcp_select_window(sk) >= tp->rcv_wnd)) ||
 	    /* We ACK each frame or... */
-	    tcp_in_quickack_mode(sk)) {
+	    tcp_in_quickack_mode(sk) ||
+	    /* Protocol state mandates a one-time immediate ACK */
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOW) {
 send_now:
 		tcp_send_ack(sk);
 		return;