net: sched: RED: Introduce an ECN nodrop mode

When the RED Qdisc is currently configured to enable ECN, the RED algorithm
is used to decide whether a certain SKB should be marked. If that SKB is
not ECN-capable, it is early-dropped.

It is also possible to keep all traffic in the queue, and just mark the
ECN-capable subset of it, as appropriate under the RED algorithm. Some
switches support this mode, and some installations make use of it.

To that end, add a new RED flag, TC_RED_NODROP. When the Qdisc is
configured with this flag, non-ECT traffic is enqueued instead of being
early-dropped.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/pkt_cls.h

@@ -740,6 +740,7 @@ struct tc_red_qopt_offload_params {
 	u32 limit;
 	bool is_ecn;
 	bool is_harddrop;
+	bool is_nodrop;
 	struct gnet_stats_queue *qstats;
 };
 

include/net/red.h

@@ -209,6 +209,11 @@ static inline int red_get_flags(unsigned char qopt_flags,
 static inline int red_validate_flags(unsigned char flags,
 				     struct netlink_ext_ack *extack)
 {
+	if ((flags & TC_RED_NODROP) && !(flags & TC_RED_ECN)) {
+		NL_SET_ERR_MSG_MOD(extack, "nodrop mode is only meaningful with ECN");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 

include/uapi/linux/pkt_sched.h

@@ -286,6 +286,7 @@ struct tc_red_qopt {
 #define TC_RED_ECN		1
 #define TC_RED_HARDDROP		2
 #define TC_RED_ADAPTATIVE	4
+#define TC_RED_NODROP		8
 };
 
 #define TC_RED_HISTORIC_FLAGS (TC_RED_ECN | TC_RED_HARDDROP | TC_RED_ADAPTATIVE)

net/sched/sch_red.c

@@ -48,7 +48,7 @@ struct red_sched_data {
 	struct Qdisc		*qdisc;
 };
 
-static const u32 red_supported_flags = TC_RED_HISTORIC_FLAGS;
+static const u32 red_supported_flags = TC_RED_HISTORIC_FLAGS | TC_RED_NODROP;
 
 static inline int red_use_ecn(struct red_sched_data *q)
 {
@@ -60,6 +60,11 @@ static inline int red_use_harddrop(struct red_sched_data *q)
 	return q->flags & TC_RED_HARDDROP;
 }
 
+static int red_use_nodrop(struct red_sched_data *q)
+{
+	return q->flags & TC_RED_NODROP;
+}
+
 static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		       struct sk_buff **to_free)
 {
@@ -80,23 +85,36 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 
 	case RED_PROB_MARK:
 		qdisc_qstats_overlimit(sch);
-		if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) {
+		if (!red_use_ecn(q)) {
 			q->stats.prob_drop++;
 			goto congestion_drop;
 		}
 
-		q->stats.prob_mark++;
+		if (INET_ECN_set_ce(skb)) {
+			q->stats.prob_mark++;
+		} else if (!red_use_nodrop(q)) {
+			q->stats.prob_drop++;
+			goto congestion_drop;
+		}
+
+		/* Non-ECT packet in ECN nodrop mode: queue it. */
 		break;
 
 	case RED_HARD_MARK:
 		qdisc_qstats_overlimit(sch);
-		if (red_use_harddrop(q) || !red_use_ecn(q) ||
+		if (red_use_harddrop(q) || !red_use_ecn(q)) {
-		    !INET_ECN_set_ce(skb)) {
 			q->stats.forced_drop++;
 			goto congestion_drop;
 		}
 
-		q->stats.forced_mark++;
+		if (INET_ECN_set_ce(skb)) {
+			q->stats.forced_mark++;
+		} else if (!red_use_nodrop(q)) {
+			q->stats.forced_drop++;
+			goto congestion_drop;
+		}
+
+		/* Non-ECT packet in ECN nodrop mode: queue it. */
 		break;
 	}
 
@@ -171,6 +189,7 @@ static int red_offload(struct Qdisc *sch, bool enable)
 		opt.set.limit = q->limit;
 		opt.set.is_ecn = red_use_ecn(q);
 		opt.set.is_harddrop = red_use_harddrop(q);
+		opt.set.is_nodrop = red_use_nodrop(q);
 		opt.set.qstats = &sch->qstats;
 	} else {
 		opt.command = TC_RED_DESTROY;