net-tcp_rate: consolidate inflight tracking approaches in TCP

In order to track CE marks per rate sample (one round trip), we'll
need to snap the starting tcp delivered_ce acount in the packet
meta header (tcp_skb_cb). But there's not enough space.

Good news is that the "last_in_flight" in the header, used by
NV congestion control, is almost equivalent as "delivered". In
fact "delivered" is better by accounting out-of-order packets
additionally.  Therefore we can remove it to make room for the
CE tracking.

This would make delayed ACK detection slightly less accurate but the
impact is negligible since it's not used for any critical control.

Effort: net-tcp_rate
Origin-9xx-SHA1: ddcd46ec85d5f1c4454258af0c54b3254c0d64a7
Change-Id: I1a184aad6d101c981ac7f2f275aa9417ff856910

include/net/tcp.h

@@ -860,9 +860,8 @@ struct tcp_skb_cb {
 	union {
 		struct {
 			/* There is space for up to 24 bytes */
-			__u32 in_flight:30,/* Bytes in flight at transmit */
-			      is_app_limited:1, /* cwnd not fully used? */
-			      unused:1;
+			__u32 is_app_limited:1, /* cwnd not fully used? */
+			      unused:31;
 			/* pkts S/ACKed so far upon tx of skb, incl retrans: */
 			__u32 delivered;
 			/* start of send pipeline phase */

net/ipv4/tcp_input.c

@@ -3167,7 +3167,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 	long seq_rtt_us = -1L;
 	long ca_rtt_us = -1L;
 	u32 pkts_acked = 0;
-	u32 last_in_flight = 0;
 	bool rtt_update;
 	int flag = 0;
 
@@ -3203,7 +3202,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 			if (!first_ackt)
 				first_ackt = last_ackt;
 
-			last_in_flight = TCP_SKB_CB(skb)->tx.in_flight;
 			if (before(start_seq, reord))
 				reord = start_seq;
 			if (!after(scb->end_seq, tp->high_seq))
@@ -3269,8 +3267,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 		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 &&
+		if (pkts_acked == 1 && fully_acked && !prior_sacked &&
+		    (tp->snd_una - prior_snd_una) < tp->mss_cache &&
 		    sack->rate->prior_delivered + 1 == tp->delivered &&
 		    !(flag & (FLAG_CA_ALERT | FLAG_SYN_ACKED))) {
 			/* Conservatively mark a delayed ACK. It's typically
@@ -3327,9 +3325,10 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 
 	if (icsk->icsk_ca_ops->pkts_acked) {
 		struct ack_sample sample = { .pkts_acked = pkts_acked,
-					     .rtt_us = sack->rate->rtt_us,
-					     .in_flight = last_in_flight };
+					     .rtt_us = sack->rate->rtt_us };
 
+		sample.in_flight = tp->mss_cache *
+			(tp->delivered - sack->rate->prior_delivered);
 		icsk->icsk_ca_ops->pkts_acked(sk, &sample);
 	}
 

net/ipv4/tcp_output.c

@@ -1257,8 +1257,6 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache);
 	skb->skb_mstamp_ns = tp->tcp_wstamp_ns;
 	if (clone_it) {
-		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
-			- tp->snd_una;
 		oskb = skb;
 
 		tcp_skb_tsorted_save(oskb) {