static int pie_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct pie_sched_data *q = qdisc_priv(sch);
struct nlattr *opts;
opts = nla_nest_start(skb, TCA_OPTIONS);
if (opts == NULL)
goto nla_put_failure;
/* convert target from pschedtime to us */
if (nla_put_u32(skb, TCA_PIE_TARGET,
((u32) PSCHED_TICKS2NS(q->params.target)) /
NSEC_PER_USEC) ||
nla_put_u32(skb, TCA_PIE_LIMIT, sch->limit) ||
nla_put_u32(skb, TCA_PIE_TUPDATE, jiffies_to_usecs(q->params.tupdate)) ||
nla_put_u32(skb, TCA_PIE_ALPHA, q->params.alpha) ||
nla_put_u32(skb, TCA_PIE_BETA, q->params.beta) ||
nla_put_u32(skb, TCA_PIE_ECN, q->params.ecn) ||
nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode))
goto nla_put_failure;
return nla_nest_end(skb, opts);
nla_put_failure:
nla_nest_cancel(skb, opts);
return -1;
}
static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
{
int err;
struct tbf_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_TBF_MAX + 1];
struct tc_tbf_qopt *qopt;
struct Qdisc *child = NULL;
struct psched_ratecfg rate;
struct psched_ratecfg peak;
u64 max_size;
s64 buffer, mtu;
u64 rate64 = 0, prate64 = 0;
err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy);
if (err < 0)
return err;
err = -EINVAL;
if (tb[TCA_TBF_PARMS] == NULL)
goto done;
qopt = nla_data(tb[TCA_TBF_PARMS]);
if (qopt->rate.linklayer == TC_LINKLAYER_UNAWARE)
qdisc_put_rtab(qdisc_get_rtab(&qopt->rate,
tb[TCA_TBF_RTAB]));
if (qopt->peakrate.linklayer == TC_LINKLAYER_UNAWARE)
qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate,
tb[TCA_TBF_PTAB]));
buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U);
mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U);
if (tb[TCA_TBF_RATE64])
rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
psched_ratecfg_precompute(&rate, &qopt->rate, rate64);
max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U);
if (qopt->peakrate.rate) {
if (tb[TCA_TBF_PRATE64])
prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
psched_ratecfg_precompute(&peak, &qopt->peakrate, prate64);
if (peak.rate_bytes_ps <= rate.rate_bytes_ps) {
pr_warn_ratelimited("sch_tbf: peakrate %llu is lower than or equals to rate %llu !\n",
peak.rate_bytes_ps, rate.rate_bytes_ps);
err = -EINVAL;
goto done;
}
max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu));
}
if (max_size < psched_mtu(qdisc_dev(sch)))
pr_warn_ratelimited("sch_tbf: burst %llu is lower than device %s mtu (%u) !\n",
max_size, qdisc_dev(sch)->name,
psched_mtu(qdisc_dev(sch)));
if (!max_size) {
err = -EINVAL;
goto done;
}
if (q->qdisc != &noop_qdisc) {
err = fifo_set_limit(q->qdisc, qopt->limit);
if (err)
goto done;
} else if (qopt->limit > 0) {
child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
if (IS_ERR(child)) {
err = PTR_ERR(child);
goto done;
}
}
sch_tree_lock(sch);
if (child) {
qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
qdisc_destroy(q->qdisc);
q->qdisc = child;
}
q->limit = qopt->limit;
q->mtu = PSCHED_TICKS2NS(qopt->mtu);
q->max_size = max_size;
q->buffer = PSCHED_TICKS2NS(qopt->buffer);
q->tokens = q->buffer;
q->ptokens = q->mtu;
memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg));
if (qopt->peakrate.rate) {
memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));
q->peak_present = true;
} else {
q->peak_present = false;
}
sch_tree_unlock(sch);
err = 0;
done:
return err;
}
static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
{
struct pie_sched_data *q = qdisc_priv(sch);
struct tc_pie_xstats st = {
.prob = q->vars.prob,
.delay = ((u32) PSCHED_TICKS2NS(q->vars.qdelay)) /
NSEC_PER_USEC,
/* unscale and return dq_rate in bytes per sec */
.avg_dq_rate = q->vars.avg_dq_rate *
(PSCHED_TICKS_PER_SEC) >> PIE_SCALE,
.packets_in = q->stats.packets_in,
.overlimit = q->stats.overlimit,
.maxq = q->stats.maxq,
.dropped = q->stats.dropped,
.ecn_mark = q->stats.ecn_mark,
};
return gnet_stats_copy_app(d, &st, sizeof(st));
}
static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch)
{
struct pie_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
skb = __qdisc_dequeue_head(sch, &sch->q);
if (!skb)
return NULL;
pie_process_dequeue(sch, &q->vars, skb);
return skb;
}
static void pie_reset(struct Qdisc *sch)
{
struct pie_sched_data *q = qdisc_priv(sch);
qdisc_reset_queue(sch);
pie_vars_init(&q->vars);
}
static void pie_destroy(struct Qdisc *sch)
{
struct pie_sched_data *q = qdisc_priv(sch);
q->params.tupdate = 0;
del_timer_sync(&q->adapt_timer);
}
static struct Qdisc_ops pie_qdisc_ops __read_mostly = {
.id = "pie",
.priv_size = sizeof(struct pie_sched_data),
.enqueue = pie_qdisc_enqueue,
.dequeue = pie_qdisc_dequeue,
.peek = qdisc_peek_dequeued,
.init = pie_init,
.destroy = pie_destroy,
.reset = pie_reset,
.change = pie_change,
.dump = pie_dump,
.dump_stats = pie_dump_stats,
.owner = THIS_MODULE,
};
static int __init pie_module_init(void)
{
return register_qdisc(&pie_qdisc_ops);
}
static void __exit pie_module_exit(void)
{
unregister_qdisc(&pie_qdisc_ops);
}
module_init(pie_module_init);
module_exit(pie_module_exit);
MODULE_DESCRIPTION("Proportional Integral controller Enhanced (PIE) scheduler");
MODULE_AUTHOR("Vijay Subramanian");
MODULE_AUTHOR("Mythili Prabhu");
MODULE_LICENSE("GPL");
static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
int err;
struct tbf_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_TBF_MAX + 1];
struct tc_tbf_qopt *qopt;
struct Qdisc *child = NULL;
struct psched_ratecfg rate;
struct psched_ratecfg peak;
u64 max_size;
s64 buffer, mtu;
u64 rate64 = 0, prate64 = 0;
err = nla_parse_nested_deprecated(tb, TCA_TBF_MAX, opt, tbf_policy,
NULL);
if (err < 0)
return err;
err = -EINVAL;
if (tb[TCA_TBF_PARMS] == NULL)
goto done;
qopt = nla_data(tb[TCA_TBF_PARMS]);
if (qopt->rate.linklayer == TC_LINKLAYER_UNAWARE)
qdisc_put_rtab(qdisc_get_rtab(&qopt->rate,
tb[TCA_TBF_RTAB],
NULL));
if (qopt->peakrate.linklayer == TC_LINKLAYER_UNAWARE)
qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate,
tb[TCA_TBF_PTAB],
NULL));
buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U);
mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U);
if (tb[TCA_TBF_RATE64])
rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
psched_ratecfg_precompute(&rate, &qopt->rate, rate64);
if (tb[TCA_TBF_BURST]) {
max_size = nla_get_u32(tb[TCA_TBF_BURST]);
buffer = psched_l2t_ns(&rate, max_size);
} else {
max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U);
}
if (qopt->peakrate.rate) {
if (tb[TCA_TBF_PRATE64])
prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
psched_ratecfg_precompute(&peak, &qopt->peakrate, prate64);
if (peak.rate_bytes_ps <= rate.rate_bytes_ps) {
pr_warn_ratelimited("sch_tbf: peakrate %llu is lower than or equals to rate %llu !\n",
peak.rate_bytes_ps, rate.rate_bytes_ps);
err = -EINVAL;
goto done;
}
if (tb[TCA_TBF_PBURST]) {
u32 pburst = nla_get_u32(tb[TCA_TBF_PBURST]);
max_size = min_t(u32, max_size, pburst);
mtu = psched_l2t_ns(&peak, pburst);
} else {
max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu));
}
} else {
memset(&peak, 0, sizeof(peak));
}
if (max_size < psched_mtu(qdisc_dev(sch)))
pr_warn_ratelimited("sch_tbf: burst %llu is lower than device %s mtu (%u) !\n",
max_size, qdisc_dev(sch)->name,
psched_mtu(qdisc_dev(sch)));
if (!max_size) {
err = -EINVAL;
goto done;
}
if (q->qdisc != &noop_qdisc) {
err = fifo_set_limit(q->qdisc, qopt->limit);
if (err)
goto done;
} else if (qopt->limit > 0) {
child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit,
extack);
if (IS_ERR(child)) {
err = PTR_ERR(child);
goto done;
}
/* child is fifo, no need to check for noop_qdisc */
qdisc_hash_add(child, true);
}
sch_tree_lock(sch);
if (child) {
qdisc_tree_flush_backlog(q->qdisc);
qdisc_put(q->qdisc);
q->qdisc = child;
}
q->limit = qopt->limit;
if (tb[TCA_TBF_PBURST])
q->mtu = mtu;
else
q->mtu = PSCHED_TICKS2NS(qopt->mtu);
q->max_size = max_size;
if (tb[TCA_TBF_BURST])
q->buffer = buffer;
else
q->buffer = PSCHED_TICKS2NS(qopt->buffer);
q->tokens = q->buffer;
q->ptokens = q->mtu;
memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg));
memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));
sch_tree_unlock(sch);
err = 0;
done:
return err;
}
static int tcf_act_police_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind)
{
int ret = 0, err;
struct nlattr *tb[TCA_POLICE_MAX + 1];
struct tc_police *parm;
struct tcf_police *police;
struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL;
struct tc_action_net *tn = net_generic(net, police_net_id);
bool exists = false;
int size;
if (nla == NULL)
return -EINVAL;
err = nla_parse_nested(tb, TCA_POLICE_MAX, nla, police_policy, NULL);
if (err < 0)
return err;
if (tb[TCA_POLICE_TBF] == NULL)
return -EINVAL;
size = nla_len(tb[TCA_POLICE_TBF]);
if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat))
return -EINVAL;
parm = nla_data(tb[TCA_POLICE_TBF]);
exists = tcf_idr_check(tn, parm->index, a, bind);
if (exists && bind)
return 0;
if (!exists) {
ret = tcf_idr_create(tn, parm->index, NULL, a,
&act_police_ops, bind, false);
if (ret)
return ret;
ret = ACT_P_CREATED;
} else {
tcf_idr_release(*a, bind);
if (!ovr)
return -EEXIST;
}
police = to_police(*a);
if (parm->rate.rate) {
err = -ENOMEM;
R_tab = qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE], NULL);
if (R_tab == NULL)
goto failure;
if (parm->peakrate.rate) {
P_tab = qdisc_get_rtab(&parm->peakrate,
tb[TCA_POLICE_PEAKRATE], NULL);
if (P_tab == NULL)
goto failure;
}
}
if (est) {
err = gen_replace_estimator(&police->tcf_bstats, NULL,
&police->tcf_rate_est,
&police->tcf_lock,
NULL, est);
if (err)
goto failure;
} else if (tb[TCA_POLICE_AVRATE] &&
(ret == ACT_P_CREATED ||
!gen_estimator_active(&police->tcf_rate_est))) {
err = -EINVAL;
goto failure;
}
spin_lock_bh(&police->tcf_lock);
/* No failure allowed after this point */
police->tcfp_mtu = parm->mtu;
if (police->tcfp_mtu == 0) {
police->tcfp_mtu = ~0;
if (R_tab)
police->tcfp_mtu = 255 << R_tab->rate.cell_log;
}
if (R_tab) {
police->rate_present = true;
psched_ratecfg_precompute(&police->rate, &R_tab->rate, 0);
qdisc_put_rtab(R_tab);
} else {
police->rate_present = false;
}
if (P_tab) {
police->peak_present = true;
psched_ratecfg_precompute(&police->peak, &P_tab->rate, 0);
qdisc_put_rtab(P_tab);
} else {
police->peak_present = false;
}
if (tb[TCA_POLICE_RESULT])
police->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]);
police->tcfp_burst = PSCHED_TICKS2NS(parm->burst);
police->tcfp_toks = police->tcfp_burst;
if (police->peak_present) {
police->tcfp_mtu_ptoks = (s64) psched_l2t_ns(&police->peak,
police->tcfp_mtu);
police->tcfp_ptoks = police->tcfp_mtu_ptoks;
}
police->tcf_action = parm->action;
if (tb[TCA_POLICE_AVRATE])
police->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]);
spin_unlock_bh(&police->tcf_lock);
if (ret != ACT_P_CREATED)
return ret;
police->tcfp_t_c = ktime_get_ns();
tcf_idr_insert(tn, *a);
return ret;
failure:
qdisc_put_rtab(P_tab);
qdisc_put_rtab(R_tab);
if (ret == ACT_P_CREATED)
tcf_idr_cleanup(*a, est);
return err;
}
static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
{
int err;
struct tbf_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_TBF_PTAB + 1];
struct tc_tbf_qopt *qopt;
struct qdisc_rate_table *rtab = NULL;
struct qdisc_rate_table *ptab = NULL;
struct Qdisc *child = NULL;
int max_size, n;
err = nla_parse_nested(tb, TCA_TBF_PTAB, opt, tbf_policy);
if (err < 0)
return err;
err = -EINVAL;
if (tb[TCA_TBF_PARMS] == NULL)
goto done;
qopt = nla_data(tb[TCA_TBF_PARMS]);
rtab = qdisc_get_rtab(&qopt->rate, tb[TCA_TBF_RTAB]);
if (rtab == NULL)
goto done;
if (qopt->peakrate.rate) {
if (qopt->peakrate.rate > qopt->rate.rate)
ptab = qdisc_get_rtab(&qopt->peakrate, tb[TCA_TBF_PTAB]);
if (ptab == NULL)
goto done;
}
for (n = 0; n < 256; n++)
if (rtab->data[n] > qopt->buffer)
break;
max_size = (n << qopt->rate.cell_log) - 1;
if (ptab) {
int size;
for (n = 0; n < 256; n++)
if (ptab->data[n] > qopt->mtu)
break;
size = (n << qopt->peakrate.cell_log) - 1;
if (size < max_size)
max_size = size;
}
if (max_size < 0)
goto done;
if (max_size < psched_mtu(qdisc_dev(sch)))
pr_warn_ratelimited("sch_tbf: burst %u is lower than device %s mtu (%u) !\n",
max_size, qdisc_dev(sch)->name,
psched_mtu(qdisc_dev(sch)));
if (q->qdisc != &noop_qdisc) {
err = fifo_set_limit(q->qdisc, qopt->limit);
if (err)
goto done;
} else if (qopt->limit > 0) {
child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
if (IS_ERR(child)) {
err = PTR_ERR(child);
goto done;
}
}
sch_tree_lock(sch);
if (child) {
qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
qdisc_destroy(q->qdisc);
q->qdisc = child;
}
q->limit = qopt->limit;
q->mtu = PSCHED_TICKS2NS(qopt->mtu);
q->max_size = max_size;
q->buffer = PSCHED_TICKS2NS(qopt->buffer);
q->tokens = q->buffer;
q->ptokens = q->mtu;
psched_ratecfg_precompute(&q->rate, &rtab->rate);
if (ptab) {
psched_ratecfg_precompute(&q->peak, &ptab->rate);
q->peak_present = true;
} else {
q->peak_present = false;
}
sch_tree_unlock(sch);
err = 0;
done:
if (rtab)
qdisc_put_rtab(rtab);
if (ptab)
qdisc_put_rtab(ptab);
return err;
}
