fq_codel: implement L4S style ce_threshold_ect1 marking

Add TCA_FQ_CODEL_CE_THRESHOLD_ECT1 boolean option to select Low Latency,
Low Loss, Scalable Throughput (L4S) style marking, along with ce_threshold.

If enabled, only packets with ECT(1) can be transformed to CE
if their sojourn time is above the ce_threshold.

Note that this new option does not change rules for codel law.
In particular, if TCA_FQ_CODEL_ECN is left enabled (this is
the default when fq_codel qdisc is created), ECT(0) packets can
still get CE if codel law (as governed by limit/target) decides so.

Section 4.3.b of current draft [1] states:

b.  A scheduler with per-flow queues such as FQ-CoDel or FQ-PIE can
    be used for L4S.  For instance within each queue of an FQ-CoDel
    system, as well as a CoDel AQM, there is typically also ECN
    marking at an immediate (unsmoothed) shallow threshold to support
    use in data centres (see Sec.5.2.7 of [RFC8290]).  This can be
    modified so that the shallow threshold is solely applied to
    ECT(1) packets.  Then if there is a flow of non-ECN or ECT(0)
    packets in the per-flow-queue, the Classic AQM (e.g.  CoDel) is
    applied; while if there is a flow of ECT(1) packets in the queue,
    the shallower (typically sub-millisecond) threshold is applied.

Tested:

tc qd replace dev eth1 root fq_codel ce_threshold_ect1 50usec

netperf ... -t TCP_STREAM -- K dctcp

tc -s -d qd sh dev eth1
qdisc fq_codel 8022: root refcnt 32 limit 10240p flows 1024 quantum 9212 target 5ms ce_threshold_ect1 49us interval 100ms memory_limit 32Mb ecn drop_batch 64
 Sent 14388596616 bytes 9543449 pkt (dropped 0, overlimits 0 requeues 152013)
 backlog 0b 0p requeues 152013
  maxpacket 68130 drop_overlimit 0 new_flow_count 95678 ecn_mark 0 ce_mark 7639
  new_flows_len 0 old_flows_len 0

[1] L4S current draft:
https://datatracker.ietf.org/doc/html/draft-ietf-tsvwg-l4s-archSigned-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Ingemar Johansson S <ingemar.s.johansson@ericsson.com>
Cc: Tom Henderson <tomh@tomh.org>
Cc: Bob Briscoe <in@bobbriscoe.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/codel.h

@@ -102,6 +102,7 @@ static inline u32 codel_time_to_us(codel_time_t val)
  * @interval:	width of moving time window
  * @mtu:	device mtu, or minimal queue backlog in bytes.
  * @ecn:	is Explicit Congestion Notification enabled
+ * @ce_threshold_ect1: if ce_threshold only marks ECT(1) packets
  */
 struct codel_params {
 	codel_time_t	target;
@@ -109,6 +110,7 @@ struct codel_params {
 	codel_time_t	interval;
 	u32		mtu;
 	bool		ecn;
+	bool		ce_threshold_ect1;
 };
 
 /**

include/net/codel_impl.h

@@ -54,6 +54,7 @@ static void codel_params_init(struct codel_params *params)
 	params->interval = MS2TIME(100);
 	params->target = MS2TIME(5);
 	params->ce_threshold = CODEL_DISABLED_THRESHOLD;
+	params->ce_threshold_ect1 = false;
 	params->ecn = false;
 }
 
@@ -246,9 +247,20 @@ static struct sk_buff *codel_dequeue(void *ctx,
 						    vars->rec_inv_sqrt);
 	}
 end:
-	if (skb && codel_time_after(vars->ldelay, params->ce_threshold) &&
-	    INET_ECN_set_ce(skb))
-		stats->ce_mark++;
+	if (skb && codel_time_after(vars->ldelay, params->ce_threshold)) {
+		bool set_ce = true;
+
+		if (params->ce_threshold_ect1) {
+			/* Note: if skb_get_dsfield() returns -1, following
+			 * gives INET_ECN_MASK, which is != INET_ECN_ECT_1.
+			 */
+			u8 ecn = skb_get_dsfield(skb) & INET_ECN_MASK;
+
+			set_ce = (ecn == INET_ECN_ECT_1);
+		}
+		if (set_ce && INET_ECN_set_ce(skb))
+			stats->ce_mark++;
+	}
 	return skb;
 }
 

include/uapi/linux/pkt_sched.h

@@ -840,6 +840,7 @@ enum {
 	TCA_FQ_CODEL_CE_THRESHOLD,
 	TCA_FQ_CODEL_DROP_BATCH_SIZE,
 	TCA_FQ_CODEL_MEMORY_LIMIT,
+	TCA_FQ_CODEL_CE_THRESHOLD_ECT1,
 	__TCA_FQ_CODEL_MAX
 };
 

net/mac80211/sta_info.c

@@ -513,6 +513,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	sta->cparams.target = MS2TIME(20);
 	sta->cparams.interval = MS2TIME(100);
 	sta->cparams.ecn = true;
+	sta->cparams.ce_threshold_ect1 = false;
 
 	sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr);
 

net/sched/sch_fq_codel.c

@@ -362,6 +362,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = {
 	[TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 },
 	[TCA_FQ_CODEL_DROP_BATCH_SIZE] = { .type = NLA_U32 },
 	[TCA_FQ_CODEL_MEMORY_LIMIT] = { .type = NLA_U32 },
+	[TCA_FQ_CODEL_CE_THRESHOLD_ECT1] = { .type = NLA_U8 },
 };
 
 static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
@@ -408,6 +409,9 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
 		q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT;
 	}
 
+	if (tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1])
+		q->cparams.ce_threshold_ect1 = !!nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1]);
+
 	if (tb[TCA_FQ_CODEL_INTERVAL]) {
 		u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]);
 
@@ -544,10 +548,13 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb)
 			q->flows_cnt))
 		goto nla_put_failure;
 
-	if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD &&
-	    nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD,
-			codel_time_to_us(q->cparams.ce_threshold)))
-		goto nla_put_failure;
+	if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD) {
+		if (nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD,
+				codel_time_to_us(q->cparams.ce_threshold)))
+			goto nla_put_failure;
+		if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_ECT1, q->cparams.ce_threshold_ect1))
+			goto nla_put_failure;
+	}
 
 	return nla_nest_end(skb, opts);