Commit d62733c8 authored by Peter P Waskiewicz Jr's avatar Peter P Waskiewicz Jr Committed by David S. Miller

[SCHED]: Qdisc changes and sch_rr added for multiqueue

Add the new sch_rr qdisc for multiqueue network device support.  Allow
sch_prio and sch_rr to be compiled with or without multiqueue hardware
support.

sch_rr is part of sch_prio, and is referenced from MODULE_ALIAS.  This
was done since sch_prio and sch_rr only differ in their dequeue
routine.
Signed-off-by: default avatarPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: default avatarPatrick McHardy <kaber@trash.net>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent f25f4e44
...@@ -101,6 +101,15 @@ struct tc_prio_qopt ...@@ -101,6 +101,15 @@ struct tc_prio_qopt
__u8 priomap[TC_PRIO_MAX+1]; /* Map: logical priority -> PRIO band */ __u8 priomap[TC_PRIO_MAX+1]; /* Map: logical priority -> PRIO band */
}; };
enum
{
TCA_PRIO_UNSPEC,
TCA_PRIO_MQ,
__TCA_PRIO_MAX
};
#define TCA_PRIO_MAX (__TCA_PRIO_MAX - 1)
/* TBF section */ /* TBF section */
struct tc_tbf_qopt struct tc_tbf_qopt
......
...@@ -111,6 +111,17 @@ config NET_SCH_PRIO ...@@ -111,6 +111,17 @@ config NET_SCH_PRIO
To compile this code as a module, choose M here: the To compile this code as a module, choose M here: the
module will be called sch_prio. module will be called sch_prio.
config NET_SCH_RR
tristate "Multi Band Round Robin Queuing (RR)"
select NET_SCH_PRIO
---help---
Say Y here if you want to use an n-band round robin packet
scheduler.
The module uses sch_prio for its framework and is aliased as
sch_rr, so it will load sch_prio, although it is referred
to using sch_rr.
config NET_SCH_RED config NET_SCH_RED
tristate "Random Early Detection (RED)" tristate "Random Early Detection (RED)"
---help--- ---help---
......
...@@ -40,9 +40,11 @@ ...@@ -40,9 +40,11 @@
struct prio_sched_data struct prio_sched_data
{ {
int bands; int bands;
int curband; /* for round-robin */
struct tcf_proto *filter_list; struct tcf_proto *filter_list;
u8 prio2band[TC_PRIO_MAX+1]; u8 prio2band[TC_PRIO_MAX+1];
struct Qdisc *queues[TCQ_PRIO_BANDS]; struct Qdisc *queues[TCQ_PRIO_BANDS];
int mq;
}; };
...@@ -70,14 +72,17 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) ...@@ -70,14 +72,17 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
#endif #endif
if (TC_H_MAJ(band)) if (TC_H_MAJ(band))
band = 0; band = 0;
return q->queues[q->prio2band[band&TC_PRIO_MAX]]; band = q->prio2band[band&TC_PRIO_MAX];
goto out;
} }
band = res.classid; band = res.classid;
} }
band = TC_H_MIN(band) - 1; band = TC_H_MIN(band) - 1;
if (band >= q->bands) if (band >= q->bands)
return q->queues[q->prio2band[0]]; band = q->prio2band[0];
out:
if (q->mq)
skb_set_queue_mapping(skb, band);
return q->queues[band]; return q->queues[band];
} }
...@@ -144,17 +149,58 @@ prio_dequeue(struct Qdisc* sch) ...@@ -144,17 +149,58 @@ prio_dequeue(struct Qdisc* sch)
struct Qdisc *qdisc; struct Qdisc *qdisc;
for (prio = 0; prio < q->bands; prio++) { for (prio = 0; prio < q->bands; prio++) {
qdisc = q->queues[prio]; /* Check if the target subqueue is available before
skb = qdisc->dequeue(qdisc); * pulling an skb. This way we avoid excessive requeues
if (skb) { * for slower queues.
sch->q.qlen--; */
return skb; if (!netif_subqueue_stopped(sch->dev, (q->mq ? prio : 0))) {
qdisc = q->queues[prio];
skb = qdisc->dequeue(qdisc);
if (skb) {
sch->q.qlen--;
return skb;
}
} }
} }
return NULL; return NULL;
} }
static struct sk_buff *rr_dequeue(struct Qdisc* sch)
{
struct sk_buff *skb;
struct prio_sched_data *q = qdisc_priv(sch);
struct Qdisc *qdisc;
int bandcount;
/* Only take one pass through the queues. If nothing is available,
* return nothing.
*/
for (bandcount = 0; bandcount < q->bands; bandcount++) {
/* Check if the target subqueue is available before
* pulling an skb. This way we avoid excessive requeues
* for slower queues. If the queue is stopped, try the
* next queue.
*/
if (!netif_subqueue_stopped(sch->dev,
(q->mq ? q->curband : 0))) {
qdisc = q->queues[q->curband];
skb = qdisc->dequeue(qdisc);
if (skb) {
sch->q.qlen--;
q->curband++;
if (q->curband >= q->bands)
q->curband = 0;
return skb;
}
}
q->curband++;
if (q->curband >= q->bands)
q->curband = 0;
}
return NULL;
}
static unsigned int prio_drop(struct Qdisc* sch) static unsigned int prio_drop(struct Qdisc* sch)
{ {
struct prio_sched_data *q = qdisc_priv(sch); struct prio_sched_data *q = qdisc_priv(sch);
...@@ -198,21 +244,41 @@ prio_destroy(struct Qdisc* sch) ...@@ -198,21 +244,41 @@ prio_destroy(struct Qdisc* sch)
static int prio_tune(struct Qdisc *sch, struct rtattr *opt) static int prio_tune(struct Qdisc *sch, struct rtattr *opt)
{ {
struct prio_sched_data *q = qdisc_priv(sch); struct prio_sched_data *q = qdisc_priv(sch);
struct tc_prio_qopt *qopt = RTA_DATA(opt); struct tc_prio_qopt *qopt;
struct rtattr *tb[TCA_PRIO_MAX];
int i; int i;
if (opt->rta_len < RTA_LENGTH(sizeof(*qopt))) if (rtattr_parse_nested_compat(tb, TCA_PRIO_MAX, opt, qopt,
sizeof(*qopt)))
return -EINVAL; return -EINVAL;
if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < 2) q->bands = qopt->bands;
/* If we're multiqueue, make sure the number of incoming bands
* matches the number of queues on the device we're associating with.
* If the number of bands requested is zero, then set q->bands to
* dev->egress_subqueue_count.
*/
q->mq = RTA_GET_FLAG(tb[TCA_PRIO_MQ - 1]);
if (q->mq) {
if (sch->handle != TC_H_ROOT)
return -EINVAL;
if (netif_is_multiqueue(sch->dev)) {
if (q->bands == 0)
q->bands = sch->dev->egress_subqueue_count;
else if (q->bands != sch->dev->egress_subqueue_count)
return -EINVAL;
} else
return -EOPNOTSUPP;
}
if (q->bands > TCQ_PRIO_BANDS || q->bands < 2)
return -EINVAL; return -EINVAL;
for (i=0; i<=TC_PRIO_MAX; i++) { for (i=0; i<=TC_PRIO_MAX; i++) {
if (qopt->priomap[i] >= qopt->bands) if (qopt->priomap[i] >= q->bands)
return -EINVAL; return -EINVAL;
} }
sch_tree_lock(sch); sch_tree_lock(sch);
q->bands = qopt->bands;
memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
for (i=q->bands; i<TCQ_PRIO_BANDS; i++) { for (i=q->bands; i<TCQ_PRIO_BANDS; i++) {
...@@ -268,11 +334,17 @@ static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) ...@@ -268,11 +334,17 @@ static int prio_dump(struct Qdisc *sch, struct sk_buff *skb)
{ {
struct prio_sched_data *q = qdisc_priv(sch); struct prio_sched_data *q = qdisc_priv(sch);
unsigned char *b = skb_tail_pointer(skb); unsigned char *b = skb_tail_pointer(skb);
struct rtattr *nest;
struct tc_prio_qopt opt; struct tc_prio_qopt opt;
opt.bands = q->bands; opt.bands = q->bands;
memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX+1); memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX+1);
RTA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
nest = RTA_NEST_COMPAT(skb, TCA_OPTIONS, sizeof(opt), &opt);
if (q->mq)
RTA_PUT_FLAG(skb, TCA_PRIO_MQ);
RTA_NEST_COMPAT_END(skb, nest);
return skb->len; return skb->len;
rtattr_failure: rtattr_failure:
...@@ -443,17 +515,44 @@ static struct Qdisc_ops prio_qdisc_ops = { ...@@ -443,17 +515,44 @@ static struct Qdisc_ops prio_qdisc_ops = {
.owner = THIS_MODULE, .owner = THIS_MODULE,
}; };
static struct Qdisc_ops rr_qdisc_ops = {
.next = NULL,
.cl_ops = &prio_class_ops,
.id = "rr",
.priv_size = sizeof(struct prio_sched_data),
.enqueue = prio_enqueue,
.dequeue = rr_dequeue,
.requeue = prio_requeue,
.drop = prio_drop,
.init = prio_init,
.reset = prio_reset,
.destroy = prio_destroy,
.change = prio_tune,
.dump = prio_dump,
.owner = THIS_MODULE,
};
static int __init prio_module_init(void) static int __init prio_module_init(void)
{ {
return register_qdisc(&prio_qdisc_ops); int err;
err = register_qdisc(&prio_qdisc_ops);
if (err < 0)
return err;
err = register_qdisc(&rr_qdisc_ops);
if (err < 0)
unregister_qdisc(&prio_qdisc_ops);
return err;
} }
static void __exit prio_module_exit(void) static void __exit prio_module_exit(void)
{ {
unregister_qdisc(&prio_qdisc_ops); unregister_qdisc(&prio_qdisc_ops);
unregister_qdisc(&rr_qdisc_ops);
} }
module_init(prio_module_init) module_init(prio_module_init)
module_exit(prio_module_exit) module_exit(prio_module_exit)
MODULE_LICENSE("GPL"); MODULE_LICENSE("GPL");
MODULE_ALIAS("sch_rr");
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment