linux-stable/net/sched/sch_fifo.c
Eric Dumazet 44b8288308 net_sched: pfifo_head_drop problem
commit 57dbb2d83d (sched: add head drop fifo queue)
introduced pfifo_head_drop, and broke the invariant that
sch->bstats.bytes and sch->bstats.packets are COUNTER (increasing
counters only)

This can break estimators because est_timer() handles unsigned deltas
only. A decreasing counter can then give a huge unsigned delta.

My mid term suggestion would be to change things so that
sch->bstats.bytes and sch->bstats.packets are incremented in dequeue()
only, not at enqueue() time. We also could add drop_bytes/drop_packets
and provide estimations of drop rates.

It would be more sensible anyway for very low speeds, and big bursts.
Right now, if we drop packets, they still are accounted in byte/packets
abolute counters and rate estimators.

Before this mid term change, this patch makes pfifo_head_drop behavior
similar to other qdiscs in case of drops :
Dont decrement sch->bstats.bytes and sch->bstats.packets

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-05 13:39:17 -08:00

184 lines
4.3 KiB
C

/*
* net/sched/sch_fifo.c The simplest FIFO queue.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*/
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <net/pkt_sched.h>
/* 1 band FIFO pseudo-"scheduler" */
struct fifo_sched_data
{
u32 limit;
};
static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch)
{
struct fifo_sched_data *q = qdisc_priv(sch);
if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= q->limit))
return qdisc_enqueue_tail(skb, sch);
return qdisc_reshape_fail(skb, sch);
}
static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch)
{
struct fifo_sched_data *q = qdisc_priv(sch);
if (likely(skb_queue_len(&sch->q) < q->limit))
return qdisc_enqueue_tail(skb, sch);
return qdisc_reshape_fail(skb, sch);
}
static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc* sch)
{
struct sk_buff *skb_head;
struct fifo_sched_data *q = qdisc_priv(sch);
if (likely(skb_queue_len(&sch->q) < q->limit))
return qdisc_enqueue_tail(skb, sch);
/* queue full, remove one skb to fulfill the limit */
skb_head = qdisc_dequeue_head(sch);
sch->qstats.drops++;
kfree_skb(skb_head);
qdisc_enqueue_tail(skb, sch);
return NET_XMIT_CN;
}
static int fifo_init(struct Qdisc *sch, struct nlattr *opt)
{
struct fifo_sched_data *q = qdisc_priv(sch);
if (opt == NULL) {
u32 limit = qdisc_dev(sch)->tx_queue_len ? : 1;
if (sch->ops == &bfifo_qdisc_ops)
limit *= psched_mtu(qdisc_dev(sch));
q->limit = limit;
} else {
struct tc_fifo_qopt *ctl = nla_data(opt);
if (nla_len(opt) < sizeof(*ctl))
return -EINVAL;
q->limit = ctl->limit;
}
return 0;
}
static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct fifo_sched_data *q = qdisc_priv(sch);
struct tc_fifo_qopt opt = { .limit = q->limit };
NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
return skb->len;
nla_put_failure:
return -1;
}
struct Qdisc_ops pfifo_qdisc_ops __read_mostly = {
.id = "pfifo",
.priv_size = sizeof(struct fifo_sched_data),
.enqueue = pfifo_enqueue,
.dequeue = qdisc_dequeue_head,
.peek = qdisc_peek_head,
.drop = qdisc_queue_drop,
.init = fifo_init,
.reset = qdisc_reset_queue,
.change = fifo_init,
.dump = fifo_dump,
.owner = THIS_MODULE,
};
EXPORT_SYMBOL(pfifo_qdisc_ops);
struct Qdisc_ops bfifo_qdisc_ops __read_mostly = {
.id = "bfifo",
.priv_size = sizeof(struct fifo_sched_data),
.enqueue = bfifo_enqueue,
.dequeue = qdisc_dequeue_head,
.peek = qdisc_peek_head,
.drop = qdisc_queue_drop,
.init = fifo_init,
.reset = qdisc_reset_queue,
.change = fifo_init,
.dump = fifo_dump,
.owner = THIS_MODULE,
};
EXPORT_SYMBOL(bfifo_qdisc_ops);
struct Qdisc_ops pfifo_head_drop_qdisc_ops __read_mostly = {
.id = "pfifo_head_drop",
.priv_size = sizeof(struct fifo_sched_data),
.enqueue = pfifo_tail_enqueue,
.dequeue = qdisc_dequeue_head,
.peek = qdisc_peek_head,
.drop = qdisc_queue_drop_head,
.init = fifo_init,
.reset = qdisc_reset_queue,
.change = fifo_init,
.dump = fifo_dump,
.owner = THIS_MODULE,
};
/* Pass size change message down to embedded FIFO */
int fifo_set_limit(struct Qdisc *q, unsigned int limit)
{
struct nlattr *nla;
int ret = -ENOMEM;
/* Hack to avoid sending change message to non-FIFO */
if (strncmp(q->ops->id + 1, "fifo", 4) != 0)
return 0;
nla = kmalloc(nla_attr_size(sizeof(struct tc_fifo_qopt)), GFP_KERNEL);
if (nla) {
nla->nla_type = RTM_NEWQDISC;
nla->nla_len = nla_attr_size(sizeof(struct tc_fifo_qopt));
((struct tc_fifo_qopt *)nla_data(nla))->limit = limit;
ret = q->ops->change(q, nla);
kfree(nla);
}
return ret;
}
EXPORT_SYMBOL(fifo_set_limit);
struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops,
unsigned int limit)
{
struct Qdisc *q;
int err = -ENOMEM;
q = qdisc_create_dflt(sch->dev_queue, ops, TC_H_MAKE(sch->handle, 1));
if (q) {
err = fifo_set_limit(q, limit);
if (err < 0) {
qdisc_destroy(q);
q = NULL;
}
}
return q ? : ERR_PTR(err);
}
EXPORT_SYMBOL(fifo_create_dflt);