tcp: switch tcp and sch_fq to new earliest departure time model

TCP keeps track of tcp_wstamp_ns by itself, meaning sch_fq
no longer has to do it.

Thanks to this model, TCP can get more accurate RTT samples,
since pacing no longer inflates them.

This has the nice effect of removing some delays caused by FQ
quantum mechanism, causing inflated max/P99 latencies.

Also we might relax TCP Small Queue tight limits in the future,
since this new model allow TCP to build bigger batches, since
sch_fq (or a device with earliest departure time offload) ensure
these packets will be delivered on time.

Note that other protocols are not converted (they will probably
never be) so sch_fq has still support for SO_MAX_PACING_RATE

Tested:

Test showing FQ pacing quantum artifact for low-rate flows,
adding unexpected throttles for RPC flows, inflating max and P99 latencies.

The parameters chosen here are to show what happens typically when
a TCP flow has a reduced pacing rate (this can be caused by a reduced
cwin after few losses, or/and rtt above few ms)

MIBS="MIN_LATENCY,MEAN_LATENCY,MAX_LATENCY,P99_LATENCY,STDDEV_LATENCY"
Before :
$ netperf -H 10.246.7.133 -t TCP_RR -Cc -T6,6 -- -q 2000000 -r 100,100 -o $MIBS
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.246.7.133 () port 0 AF_INET : first burst 0 : cpu bind
 Minimum Latency Microseconds,Mean Latency Microseconds,Maximum Latency Microseconds,99th Percentile Latency Microseconds,Stddev Latency Microseconds
19,82.78,5279,3825,482.02

After :
$ netperf -H 10.246.7.133 -t TCP_RR -Cc -T6,6 -- -q 2000000 -r 100,100 -o $MIBS
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.246.7.133 () port 0 AF_INET : first burst 0 : cpu bind
Minimum Latency Microseconds,Mean Latency Microseconds,Maximum Latency Microseconds,99th Percentile Latency Microseconds,Stddev Latency Microseconds
20,49.94,128,63,3.18
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/tcp_bbr.c

@@ -128,6 +128,9 @@ static const u32 bbr_probe_rtt_mode_ms = 200;
 /* Skip TSO below the following bandwidth (bits/sec): */
 static const int bbr_min_tso_rate = 1200000;
 
+/* Pace at ~1% below estimated bw, on average, to reduce queue at bottleneck. */
+static const int bbr_pacing_marging_percent = 1;
+
 /* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain
  * that will allow a smoothly increasing pacing rate that will double each RTT
  * and send the same number of packets per RTT that an un-paced, slow-starting
@@ -208,12 +211,10 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
 {
 	unsigned int mss = tcp_sk(sk)->mss_cache;
 
-	if (!tcp_needs_internal_pacing(sk))
-		mss = tcp_mss_to_mtu(sk, mss);
 	rate *= mss;
 	rate *= gain;
 	rate >>= BBR_SCALE;
-	rate *= USEC_PER_SEC;
+	rate *= USEC_PER_SEC / 100 * (100 - bbr_pacing_marging_percent);
 	return rate >> BW_SCALE;
 }
 

net/ipv4/tcp_output.c

@@ -1012,9 +1012,23 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
 	sock_hold(sk);
 }
 
-static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
+static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
 	skb->skb_mstamp_ns = tp->tcp_wstamp_ns;
+	if (sk->sk_pacing_status != SK_PACING_NONE) {
+		u32 rate = sk->sk_pacing_rate;
+
+		/* Original sch_fq does not pace first 10 MSS
+		 * Note that tp->data_segs_out overflows after 2^32 packets,
+		 * this is a minor annoyance.
+		 */
+		if (rate != ~0U && rate && tp->data_segs_out >= 10) {
+			tp->tcp_wstamp_ns += div_u64((u64)skb->len * NSEC_PER_SEC, rate);
+			/* TODO: update internal pacing here */
+		}
+	}
 	list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
 }
 
@@ -1178,7 +1192,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 		err = net_xmit_eval(err);
 	}
 	if (!err && oskb) {
-		tcp_update_skb_after_send(tp, oskb);
+		tcp_update_skb_after_send(sk, oskb);
 		tcp_rate_skb_sent(sk, oskb);
 	}
 	return err;
@@ -2327,7 +2341,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
 			/* "skb_mstamp" is used as a start point for the retransmit timer */
-			tcp_update_skb_after_send(tp, skb);
+			tcp_update_skb_after_send(sk, skb);
 			goto repair; /* Skip network transmission */
 		}
 
@@ -2902,7 +2916,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		} tcp_skb_tsorted_restore(skb);
 
 		if (!err) {
-			tcp_update_skb_after_send(tp, skb);
+			tcp_update_skb_after_send(sk, skb);
 			tcp_rate_skb_sent(sk, skb);
 		}
 	} else {

net/sched/sch_fq.c

@@ -491,11 +491,16 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch)
 	}
 
 	skb = f->head;
-	if (unlikely(skb && now < f->time_next_packet &&
-		     !skb_is_tcp_pure_ack(skb))) {
-		head->first = f->next;
-		fq_flow_set_throttled(q, f);
-		goto begin;
+	if (skb && !skb_is_tcp_pure_ack(skb)) {
+		u64 time_next_packet = max_t(u64, ktime_to_ns(skb->tstamp),
+					     f->time_next_packet);
+
+		if (now < time_next_packet) {
+			head->first = f->next;
+			f->time_next_packet = time_next_packet;
+			fq_flow_set_throttled(q, f);
+			goto begin;
+		}
 	}
 
 	skb = fq_dequeue_head(sch, f);
@@ -513,11 +518,7 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch)
 	prefetch(&skb->end);
 	f->credit -= qdisc_pkt_len(skb);
 
-	if (!q->rate_enable)
-		goto out;
-
-	/* Do not pace locally generated ack packets */
-	if (skb_is_tcp_pure_ack(skb))
+	if (ktime_to_ns(skb->tstamp) || !q->rate_enable)
 		goto out;
 
 	rate = q->flow_max_rate;