net_sched: sfq: add optional RED on top of SFQ

Adds an optional Random Early Detection on each SFQ flow queue.

Traditional SFQ limits count of packets, while RED permits to also
control number of bytes per flow, and adds ECN capability as well.

1) We dont handle the idle time management in this RED implementation,
since each 'new flow' begins with a null qavg. We really want to address
backlogged flows.

2) if headdrop is selected, we try to ecn mark first packet instead of
currently enqueued packet. This gives faster feedback for tcp flows
compared to traditional RED [ marking the last packet in queue ]

Example of use :

tc qdisc add dev $DEV parent 1:1 handle 10: est 1sec 4sec sfq \
	limit 3000 headdrop flows 512 divisor 16384 \
	redflowlimit 100000 min 8000 max 60000 probability 0.20 ecn

qdisc sfq 10: parent 1:1 limit 3000p quantum 1514b depth 127 headdrop
flows 512/16384 divisor 16384
 ewma 6 min 8000b max 60000b probability 0.2 ecn
 prob_mark 0 prob_mark_head 4876 prob_drop 6131
 forced_mark 0 forced_mark_head 0 forced_drop 0
 Sent 1175211782 bytes 777537 pkt (dropped 6131, overlimits 11007
requeues 0)
 rate 99483Kbit 8219pps backlog 689392b 456p requeues 0

In this test, with 64 netperf TCP_STREAM sessions, 50% using ECN enabled
flows, we can see number of packets CE marked is smaller than number of
drops (for non ECN flows)

If same test is run, without RED, we can check backlog is much bigger.

qdisc sfq 10: parent 1:1 limit 3000p quantum 1514b depth 127 headdrop
flows 512/16384 divisor 16384
 Sent 1148683617 bytes 795006 pkt (dropped 0, overlimits 0 requeues 0)
 rate 98429Kbit 8521pps backlog 1221290b 841p requeues 0

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Stephen Hemminger <shemminger@vyatta.com>
CC: Dave Taht <dave.taht@gmail.com>
Tested-by: Dave Taht <dave.taht@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 22 insertions, 1 deletions

diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h
index 8f1b928f777..0d5b79365d0 100644
--- a/include/linux/pkt_sched.h
+++ b/include/linux/pkt_sched.h
@@ -162,10 +162,30 @@ struct tc_sfq_qopt {
 	unsigned	flows;		/* Maximal number of flows  */
 };
 
+struct tc_sfqred_stats {
+	__u32           prob_drop;      /* Early drops, below max threshold */
+	__u32           forced_drop;	/* Early drops, after max threshold */
+	__u32           prob_mark;      /* Marked packets, below max threshold */
+	__u32           forced_mark;    /* Marked packets, after max threshold */
+	__u32           prob_mark_head; /* Marked packets, below max threshold */
+	__u32           forced_mark_head;/* Marked packets, after max threshold */
+};
+
 struct tc_sfq_qopt_v1 {
 	struct tc_sfq_qopt v0;
 	unsigned int	depth;		/* max number of packets per flow */
 	unsigned int	headdrop;
+/* SFQRED parameters */
+	__u32		limit;		/* HARD maximal flow queue length (bytes) */
+	__u32		qth_min;	/* Min average length threshold (bytes) */
+	__u32		qth_max;	/* Max average length threshold (bytes) */
+	unsigned char   Wlog;		/* log(W)		*/
+	unsigned char   Plog;		/* log(P_max/(qth_max-qth_min))	*/
+	unsigned char   Scell_log;	/* cell size for idle damping */
+	unsigned char	flags;
+	__u32		max_P;		/* probability, high resolution */
+/* SFQRED stats */
+	struct tc_sfqred_stats stats;
 };
 
 
diff --git a/include/net/red.h b/include/net/red.h
index baab385a473..28068ec614b 100644
--- a/include/net/red.h
+++ b/include/net/red.h
@@ -199,7 +199,8 @@ static inline void red_set_parms(struct red_parms *p,
 	p->Scell_log	= Scell_log;
 	p->Scell_max	= (255 << Scell_log);
 
-	memcpy(p->Stab, stab, sizeof(p->Stab));
+	if (stab)
+		memcpy(p->Stab, stab, sizeof(p->Stab));
 }
 
 static inline int red_is_idling(const struct red_vars *v)