tcp: avoid min RTT bloat by skipping RTT from delayed-ACK in BBR

A persistent connection may send tiny amount of data (e.g. health-check)
for a long period of time. BBR's windowed min RTT filter may only see
RTT samples from delayed ACKs causing BBR to grossly over-estimate
the path delay depending how much the ACK was delayed at the receiver.

This patch skips RTT samples that are likely coming from delayed ACKs. Note
that it is possible the sender never obtains a valid measure to set the
min RTT. In this case BBR will continue to set cwnd to initial window
which seems fine because the connection is thin stream.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Acked-by: NSoheil Hassas Yeganeh <soheil@google.com>
Acked-by: NPriyaranjan Jha <priyarjha@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/net/tcp.h

@@ -953,6 +953,7 @@ struct rate_sample {
 	u32  prior_in_flight;	/* in flight before this ACK */
 	bool is_app_limited;	/* is sample from packet with bubble in pipe? */
 	bool is_retrans;	/* is sample from retransmission? */
+	bool is_ack_delayed;	/* is this (likely) a delayed ACK? */
 };
 
 struct tcp_congestion_ops {

net/ipv4/tcp_bbr.c

@@ -766,7 +766,8 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
 	filter_expired = after(tcp_jiffies32,
 			       bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ);
 	if (rs->rtt_us >= 0 &&
-	    (rs->rtt_us <= bbr->min_rtt_us || filter_expired)) {
+	    (rs->rtt_us <= bbr->min_rtt_us ||
+	     (filter_expired && !rs->is_ack_delayed))) {
 		bbr->min_rtt_us = rs->rtt_us;
 		bbr->min_rtt_stamp = tcp_jiffies32;
 	}

net/ipv4/tcp_input.c

@@ -3633,6 +3633,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	delivered = tp->delivered - delivered;	/* freshly ACKed or SACKed */
 	lost = tp->lost - lost;			/* freshly marked lost */
+	rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED);
 	tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
 	tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
 	tcp_xmit_recovery(sk, rexmit);