Merge branch 'tcp-min-rtt'

Yuchung Cheng says:

====================
tcp: do not use RTT from delayed ACKs for min-RTT

This patch set prevents TCP sender from using RTT samples from
(suspected) delayed ACKs as the minimum RTT, to avoid unbounded
over-estimation of the network path delay. This issue is common
when a connection has extended periods of one packet chit-chat
beyond the min RTT filter window. The first patch does that for TCP
general min RTT estimation. The second patch addresses specifically
the BBR congestion control's min RTT filter.
====================

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

3 files changed, 25 insertions, 3 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6939e69d3c37..5a1d26a18599 100644
--- a/include/net/tcp.h
+++ b/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 {
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 8322f26e770e..785712be5b0d 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/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;
 	}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ff71b18d9682..cfa51cfd2d99 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -97,6 +97,7 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 #define FLAG_SACK_RENEGING	0x2000 /* snd_una advanced to a sacked seq */
 #define FLAG_UPDATE_TS_RECENT	0x4000 /* tcp_replace_ts_recent() */
 #define FLAG_NO_CHALLENGE_ACK	0x8000 /* do not call tcp_send_challenge_ack()	*/
+#define FLAG_ACK_MAYBE_DELAYED	0x10000 /* Likely a delayed ACK */
 
 #define FLAG_ACKED		(FLAG_DATA_ACKED|FLAG_SYN_ACKED)
 #define FLAG_NOT_DUP		(FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
@@ -2857,11 +2858,18 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 	*rexmit = REXMIT_LOST;
 }
 
-static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
+static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
 {
 	u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
+		/* If the remote keeps returning delayed ACKs, eventually
+		 * the min filter would pick it up and overestimate the
+		 * prop. delay when it expires. Skip suspected delayed ACKs.
+		 */
+		return;
+	}
 	minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32,
 			   rtt_us ? : jiffies_to_usecs(1));
 }
@@ -2901,7 +2909,7 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	 * always taken together with ACK, SACK, or TS-opts. Any negative
 	 * values will be skipped with the seq_rtt_us < 0 check above.
 	 */
-	tcp_update_rtt_min(sk, ca_rtt_us);
+	tcp_update_rtt_min(sk, ca_rtt_us, flag);
 	tcp_rtt_estimator(sk, seq_rtt_us);
 	tcp_set_rto(sk);
 
@@ -3125,6 +3133,17 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 	if (likely(first_ackt) && !(flag & FLAG_RETRANS_DATA_ACKED)) {
 		seq_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, first_ackt);
 		ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, last_ackt);
+
+		if (pkts_acked == 1 && last_in_flight < tp->mss_cache &&
+		    last_in_flight && !prior_sacked && fully_acked &&
+		    sack->rate->prior_delivered + 1 == tp->delivered &&
+		    !(flag & (FLAG_CA_ALERT | FLAG_SYN_ACKED))) {
+			/* Conservatively mark a delayed ACK. It's typically
+			 * from a lone runt packet over the round trip to
+			 * a receiver w/o out-of-order or CE events.
+			 */
+			flag |= FLAG_ACK_MAYBE_DELAYED;
+		}
 	}
 	if (sack->first_sackt) {
 		sack_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->first_sackt);
@@ -3614,6 +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);