[PATCH net-next-2.6] sch_sfq: allow big packets and be fair

[Eric Dumazet <eric.dumazet@gmail.com>]

SFQ is currently 'limited' to small packets, because it uses a 16bit
allotment number per flow. Switch it to 18bit, and use appropriate
handling to make sure this allotment is in [1 .. quantum] range before a
new packet is dequeued, so that fairness is respected.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Jarek Poplawski <jarkao2@gmail.com>
Cc: Patrick McHardy <kaber@trash.net>
---
 net/sched/sch_sfq.c |   24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index c474b4b..878704a 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -67,7 +67,7 @@
 
 	IMPLEMENTATION:
 	This implementation limits maximal queue length to 128;
-	maximal mtu to 2^15-1; max 128 flows, number of hash buckets to 1024.
+	maximal mtu to 2^16-1; max 128 flows, number of hash buckets to 1024.
 	The only goal of this restrictions was that all data
 	fit into one 4K page on 32bit arches.
 
@@ -99,9 +99,10 @@ struct sfq_slot {
 	sfq_index	qlen; /* number of skbs in skblist */
 	sfq_index	next; /* next slot in sfq chain */
 	struct sfq_head dep; /* anchor in dep[] chains */
-	unsigned short	hash; /* hash value (index in ht[]) */
-	short		allot; /* credit for this slot */
+	unsigned int	hash:14; /* hash value (index in ht[]) */
+	unsigned int	allot:18; /* credit for this slot */
 };
+#define ALLOT_ZERO (1 << 16)
 
 struct sfq_sched_data
 {
@@ -394,7 +395,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 			q->tail->next = x;
 		}
 		q->tail = slot;
-		slot->allot = q->quantum;
+		slot->allot = ALLOT_ZERO + q->quantum;
 	}
 	if (++sch->q.qlen <= q->limit) {
 		sch->bstats.bytes += qdisc_pkt_len(skb);
@@ -430,8 +431,14 @@ sfq_dequeue(struct Qdisc *sch)
 	if (q->tail == NULL)
 		return NULL;
 
+next:
 	a = q->tail->next;
 	slot = &q->slots[a];
+	if (slot->allot <= ALLOT_ZERO) {
+		q->tail = slot;
+		slot->allot += q->quantum;
+		goto next;
+	}
 	skb = slot_dequeue_head(slot);
 	sfq_dec(q, a);
 	sch->q.qlen--;
@@ -446,9 +453,8 @@ sfq_dequeue(struct Qdisc *sch)
 			return skb;
 		}
 		q->tail->next = next_a;
-	} else if ((slot->allot -= qdisc_pkt_len(skb)) <= 0) {
-		q->tail = slot;
-		slot->allot += q->quantum;
+	} else {
+		slot->allot -= qdisc_pkt_len(skb);
 	}
 	return skb;
 }
@@ -610,7 +616,9 @@ static int sfq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	const struct sfq_slot *slot = &q->slots[q->ht[cl - 1]];
 	struct gnet_stats_queue qs = { .qlen = slot->qlen };
-	struct tc_sfq_xstats xstats = { .allot = slot->allot };
+	struct tc_sfq_xstats xstats = {
+		.allot = slot->allot - ALLOT_ZERO
+	};
 	struct sk_buff *skb;
 
 	slot_queue_walk(slot, skb)