netdev - [PATCH v2 net-next-2.6] sch_sfq: allow big packets and be fair

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1292936699.2720.23.camel@edumazet-laptop>
Date:	Tue, 21 Dec 2010 14:04:59 +0100
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	Jarek Poplawski <jarkao2@...il.com>
Cc:	David Miller <davem@...emloft.net>,
	Patrick McHardy <kaber@...sh.net>,
	netdev <netdev@...r.kernel.org>
Subject: [PATCH v2 net-next-2.6] sch_sfq: allow big packets and be fair

Le mardi 21 décembre 2010 à 12:17 +0000, Jarek Poplawski a écrit :

> Oops! You're right yet ;-) This skipping shouldn't happen with quantum
> bigger than max packet size, so this patch is OK.

Thanks Jarek, here is a v2 with the scale you suggested.

[PATCH v2 net-next-2.6] sch_sfq: allow big packets and be fair

SFQ is currently 'limited' to small packets, because it uses a 15bit
allotment number per flow. Introduce a scale by 8, so that we can handle
full size TSO/GRO packets.

Use appropriate handling to make sure allot is positive before a new
packet is dequeued, so that fairness is respected.

Signed-off-by: Eric Dumazet <eric.dumazet@...il.com>
Cc: Jarek Poplawski <jarkao2@...il.com>
Cc: Patrick McHardy <kaber@...sh.net>
---
v2: Use a scale of 8 as Jarek suggested, instead of 18bit fields

 net/sched/sch_sfq.c |   28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index c474b4b..f3a9fd7 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.
+	max mtu to 2^18-1; 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.
 
@@ -77,6 +77,11 @@
 #define SFQ_SLOTS		128 /* max number of flows */
 #define SFQ_EMPTY_SLOT		255
 #define SFQ_HASH_DIVISOR	1024
+/* We use 15+1 bits to store allot, and want to handle packets up to 64K
+ * Scale allot by 8 (1<<3) so that no overflow occurs.
+ */
+#define SFQ_ALLOT_SHIFT		3
+#define SFQ_ALLOT_SIZE(X)	DIV_ROUND_UP(X, 1 << SFQ_ALLOT_SHIFT)
 
 /* This type should contain at least SFQ_DEPTH + SFQ_SLOTS values */
 typedef unsigned char sfq_index;
@@ -115,7 +120,7 @@ struct sfq_sched_data
 	struct timer_list perturb_timer;
 	u32		perturbation;
 	sfq_index	cur_depth;	/* depth of longest slot */
-
+	unsigned short  scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */
 	struct sfq_slot *tail;		/* current slot in round */
 	sfq_index	ht[SFQ_HASH_DIVISOR];	/* Hash table */
 	struct sfq_slot	slots[SFQ_SLOTS];
@@ -394,7 +399,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 			q->tail->next = x;
 		}
 		q->tail = slot;
-		slot->allot = q->quantum;
+		slot->allot = q->scaled_quantum;
 	}
 	if (++sch->q.qlen <= q->limit) {
 		sch->bstats.bytes += qdisc_pkt_len(skb);
@@ -430,8 +435,14 @@ sfq_dequeue(struct Qdisc *sch)
 	if (q->tail == NULL)
 		return NULL;
 
+next_slot:
 	a = q->tail->next;
 	slot = &q->slots[a];
+	if (slot->allot <= 0) {
+		q->tail = slot;
+		slot->allot += q->scaled_quantum;
+		goto next_slot;
+	}
 	skb = slot_dequeue_head(slot);
 	sfq_dec(q, a);
 	sch->q.qlen--;
@@ -446,9 +457,8 @@ 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 -= SFQ_ALLOT_SIZE(qdisc_pkt_len(skb));
 	}
 	return skb;
 }
@@ -484,6 +494,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 	q->quantum = ctl->quantum ? : psched_mtu(qdisc_dev(sch));
+	q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
 	q->perturb_period = ctl->perturb_period * HZ;
 	if (ctl->limit)
 		q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 1);
@@ -524,6 +535,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 	q->tail = NULL;
 	if (opt == NULL) {
 		q->quantum = psched_mtu(qdisc_dev(sch));
+		q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
 		q->perturb_period = 0;
 		q->perturbation = net_random();
 	} else {
@@ -610,7 +622,9 @@ 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 << SFQ_ALLOT_SHIFT
+	};
 	struct sk_buff *skb;
 
 	slot_queue_walk(slot, skb)


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html