static int
prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct Qdisc *qdisc;
int ret;
qdisc = prio_classify(skb, sch, &ret);
#ifdef CONFIG_NET_CLS_ACT
if (qdisc == NULL) {
if (ret & __NET_XMIT_BYPASS)
sch->qstats.drops++;
kfree_skb(skb);
return ret;
}
#endif
ret = qdisc_enqueue(skb, qdisc);
if (ret == NET_XMIT_SUCCESS) {
qdisc_bstats_update(sch, skb);
sch->q.qlen++;
return NET_XMIT_SUCCESS;
}
if (net_xmit_drop_count(ret))
sch->qstats.drops++;
return ret;
}
static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
{
struct multiq_sched_data *q = qdisc_priv(sch);
struct Qdisc *qdisc;
struct sk_buff *skb;
int band;
for (band = 0; band < q->bands; band++) {
/* cycle through bands to ensure fairness */
q->curband++;
if (q->curband >= q->bands)
q->curband = 0;
/* Check that target subqueue is available before
* pulling an skb to avoid head-of-line blocking.
*/
if (!netif_xmit_stopped(
netdev_get_tx_queue(qdisc_dev(sch), q->curband))) {
qdisc = q->queues[q->curband];
skb = qdisc->dequeue(qdisc);
if (skb) {
qdisc_bstats_update(sch, skb);
sch->q.qlen--;
return skb;
}
}
}
return NULL;
}
static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct ingress_qdisc_data *p = qdisc_priv(sch);
struct tcf_result res;
int result;
result = tc_classify(skb, p->filter_list, &res);
qdisc_bstats_update(sch, skb);
switch (result) {
case TC_ACT_SHOT:
result = TC_ACT_SHOT;
sch->qstats.drops++;
break;
case TC_ACT_STOLEN:
case TC_ACT_QUEUED:
result = TC_ACT_STOLEN;
break;
case TC_ACT_RECLASSIFY:
case TC_ACT_OK:
skb->tc_index = TC_H_MIN(res.classid);
default:
result = TC_ACT_OK;
break;
}
return result;
}
static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
{
struct multiq_sched_data *q = qdisc_priv(sch);
struct Qdisc *qdisc;
struct sk_buff *skb;
int band;
for (band = 0; band < q->bands; band++) {
q->curband++;
if (q->curband >= q->bands)
q->curband = 0;
if (!netif_xmit_stopped(
netdev_get_tx_queue(qdisc_dev(sch), q->curband))) {
qdisc = q->queues[q->curband];
skb = qdisc->dequeue(qdisc);
if (skb) {
qdisc_bstats_update(sch, skb);
sch->q.qlen--;
return skb;
}
}
}
return NULL;
}
static struct sk_buff *netem_dequeue(struct Qdisc *sch)
{
struct netem_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
if (qdisc_is_throttled(sch))
return NULL;
tfifo_dequeue:
skb = qdisc_peek_head(sch);
if (skb) {
const struct netem_skb_cb *cb = netem_skb_cb(skb);
/* if more time remaining? */
if (cb->time_to_send <= psched_get_time()) {
__skb_unlink(skb, &sch->q);
sch->qstats.backlog -= qdisc_pkt_len(skb);
#ifdef CONFIG_NET_CLS_ACT
/*
* If it's at ingress let's pretend the delay is
* from the network (tstamp will be updated).
*/
if (G_TC_FROM(skb->tc_verd) & AT_INGRESS)
skb->tstamp.tv64 = 0;
#endif
if (q->qdisc) {
int err = qdisc_enqueue(skb, q->qdisc);
if (unlikely(err != NET_XMIT_SUCCESS)) {
if (net_xmit_drop_count(err)) {
sch->qstats.drops++;
qdisc_tree_decrease_qlen(sch, 1);
}
}
goto tfifo_dequeue;
}
deliver:
qdisc_unthrottled(sch);
qdisc_bstats_update(sch, skb);
return skb;
}
if (q->qdisc) {
skb = q->qdisc->ops->dequeue(q->qdisc);
if (skb)
goto deliver;
}
qdisc_watchdog_schedule(&q->watchdog, cb->time_to_send);
}
if (q->qdisc) {
skb = q->qdisc->ops->dequeue(q->qdisc);
if (skb)
goto deliver;
}
return NULL;
}
static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
{
struct tbf_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
skb = q->qdisc->ops->peek(q->qdisc);
if (skb) {
psched_time_t now;
long toks;
long ptoks = 0;
unsigned int len = qdisc_pkt_len(skb);
now = psched_get_time();
toks = psched_tdiff_bounded(now, q->t_c, q->buffer);
if (q->P_tab) {
ptoks = toks + q->ptokens;
if (ptoks > (long)q->mtu)
ptoks = q->mtu;
ptoks -= L2T_P(q, len);
}
toks += q->tokens;
if (toks > (long)q->buffer)
toks = q->buffer;
toks -= L2T(q, len);
if ((toks|ptoks) >= 0) {
skb = qdisc_dequeue_peeked(q->qdisc);
if (unlikely(!skb))
return NULL;
q->t_c = now;
q->tokens = toks;
q->ptokens = ptoks;
sch->q.qlen--;
qdisc_unthrottled(sch);
qdisc_bstats_update(sch, skb);
return skb;
}
qdisc_watchdog_schedule(&q->watchdog,
now + max_t(long, -toks, -ptoks));
/* Maybe we have a shorter packet in the queue,
which can be sent now. It sounds cool,
but, however, this is wrong in principle.
We MUST NOT reorder packets under these circumstances.
Really, if we split the flow into independent
subflows, it would be a very good solution.
This is the main idea of all FQ algorithms
(cf. CSZ, HPFQ, HFSC)
*/
sch->qstats.overlimits++;
}
return NULL;
}
static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
{
struct tbf_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
skb = q->qdisc->ops->peek(q->qdisc);
if (skb) {
s64 now;
s64 toks;
s64 ptoks = 0;
unsigned int len = qdisc_pkt_len(skb);
now = ktime_get_ns();
toks = min_t(s64, now - q->t_c, q->buffer);
if (tbf_peak_present(q)) {
ptoks = toks + q->ptokens;
if (ptoks > q->mtu)
ptoks = q->mtu;
ptoks -= (s64) psched_l2t_ns(&q->peak, len);
}
toks += q->tokens;
if (toks > q->buffer)
toks = q->buffer;
toks -= (s64) psched_l2t_ns(&q->rate, len);
if ((toks|ptoks) >= 0) {
skb = qdisc_dequeue_peeked(q->qdisc);
if (unlikely(!skb))
return NULL;
q->t_c = now;
q->tokens = toks;
q->ptokens = ptoks;
qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
qdisc_bstats_update(sch, skb);
return skb;
}
qdisc_watchdog_schedule_ns(&q->watchdog,
now + max_t(long, -toks, -ptoks));
/* Maybe we have a shorter packet in the queue,
which can be sent now. It sounds cool,
but, however, this is wrong in principle.
We MUST NOT reorder packets under these circumstances.
Really, if we split the flow into independent
subflows, it would be a very good solution.
This is the main idea of all FQ algorithms
(cf. CSZ, HPFQ, HFSC)
*/
qdisc_qstats_overlimit(sch);
}
return NULL;
}
static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
{
struct fq_codel_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
struct fq_codel_flow *flow;
struct list_head *head;
u32 prev_drop_count, prev_ecn_mark;
unsigned int prev_backlog;
begin:
head = &q->new_flows;
if (list_empty(head)) {
head = &q->old_flows;
if (list_empty(head))
return NULL;
}
flow = list_first_entry(head, struct fq_codel_flow, flowchain);
if (flow->deficit <= 0) {
flow->deficit += q->quantum;
list_move_tail(&flow->flowchain, &q->old_flows);
goto begin;
}
prev_drop_count = q->cstats.drop_count;
prev_ecn_mark = q->cstats.ecn_mark;
prev_backlog = sch->qstats.backlog;
skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams,
&flow->cvars, &q->cstats, qdisc_pkt_len,
codel_get_enqueue_time, drop_func, dequeue_func);
flow->dropped += q->cstats.drop_count - prev_drop_count;
flow->dropped += q->cstats.ecn_mark - prev_ecn_mark;
if (!skb) {
/* force a pass through old_flows to prevent starvation */
if ((head == &q->new_flows) && !list_empty(&q->old_flows))
list_move_tail(&flow->flowchain, &q->old_flows);
else
list_del_init(&flow->flowchain);
goto begin;
}
qdisc_bstats_update(sch, skb);
flow->deficit -= qdisc_pkt_len(skb);
/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
* or HTB crashes. Defer it for next round.
*/
if (q->cstats.drop_count && sch->q.qlen) {
qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
q->cstats.drop_len);
q->cstats.drop_count = 0;
q->cstats.drop_len = 0;
}
return skb;
}
static struct sk_buff *prio_dequeue(struct Qdisc *sch)
{
struct prio_sched_data *q = qdisc_priv(sch);
int prio;
for (prio = 0; prio < q->bands; prio++) {
struct Qdisc *qdisc = q->queues[prio];
struct sk_buff *skb = qdisc_dequeue_peeked(qdisc);
if (skb) {
qdisc_bstats_update(sch, skb);
sch->q.qlen--;
return skb;
}
}
return NULL;
}
static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
{
struct codel_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
skb = codel_dequeue(sch, &q->params, &q->vars, &q->stats, dequeue);
/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
* or HTB crashes. Defer it for next round.
*/
if (q->stats.drop_count && sch->q.qlen) {
qdisc_tree_decrease_qlen(sch, q->stats.drop_count);
q->stats.drop_count = 0;
}
if (skb)
qdisc_bstats_update(sch, skb);
return skb;
}
static struct sk_buff *choke_dequeue(struct Qdisc *sch)
{
struct choke_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
if (q->head == q->tail) {
if (!red_is_idling(&q->vars))
red_start_of_idle_period(&q->vars);
return NULL;
}
skb = q->tab[q->head];
q->tab[q->head] = NULL;
choke_zap_head_holes(q);
--sch->q.qlen;
sch->qstats.backlog -= qdisc_pkt_len(skb);
qdisc_bstats_update(sch, skb);
return skb;
}
static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
{
struct codel_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
skb = codel_dequeue(sch, &sch->qstats.backlog, &q->params, &q->vars,
&q->stats, qdisc_pkt_len, codel_get_enqueue_time,
drop_func, dequeue_func);
/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
* or HTB crashes. Defer it for next round.
*/
if (q->stats.drop_count && sch->q.qlen) {
qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
q->stats.drop_count = 0;
q->stats.drop_len = 0;
}
if (skb)
qdisc_bstats_update(sch, skb);
return skb;
}
static struct sk_buff *
teql_dequeue(struct Qdisc *sch)
{
struct teql_sched_data *dat = qdisc_priv(sch);
struct netdev_queue *dat_queue;
struct sk_buff *skb;
skb = __skb_dequeue(&dat->q);
dat_queue = netdev_get_tx_queue(dat->m->dev, 0);
if (skb == NULL) {
struct net_device *m = qdisc_dev(dat_queue->qdisc);
if (m) {
dat->m->slaves = sch;
netif_wake_queue(m);
}
} else {
qdisc_bstats_update(sch, skb);
}
sch->q.qlen = dat->q.qlen + dat_queue->qdisc->q.qlen;
return skb;
}
static struct sk_buff *
sfq_dequeue(struct Qdisc *sch)
{
struct sfq_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
sfq_index a, next_a;
struct sfq_slot *slot;
/* No active slots */
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);
qdisc_bstats_update(sch, skb);
sch->q.qlen--;
sch->qstats.backlog -= qdisc_pkt_len(skb);
slot->backlog -= qdisc_pkt_len(skb);
/* Is the slot empty? */
if (slot->qlen == 0) {
q->ht[slot->hash] = SFQ_EMPTY_SLOT;
next_a = slot->next;
if (a == next_a) {
q->tail = NULL; /* no more active slots */
return skb;
}
q->tail->next = next_a;
} else {
slot->allot -= SFQ_ALLOT_SIZE(qdisc_pkt_len(skb));
}
return skb;
}
static struct sk_buff *netem_dequeue(struct Qdisc *sch)
{
struct netem_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
if (qdisc_is_throttled(sch))
return NULL;
skb = q->qdisc->ops->peek(q->qdisc);
if (skb) {
const struct netem_skb_cb *cb = netem_skb_cb(skb);
psched_time_t now = psched_get_time();
/* if more time remaining? */
if (cb->time_to_send <= now) {
skb = qdisc_dequeue_peeked(q->qdisc);
if (unlikely(!skb))
return NULL;
#ifdef CONFIG_NET_CLS_ACT
/*
* If it's at ingress let's pretend the delay is
* from the network (tstamp will be updated).
*/
if (G_TC_FROM(skb->tc_verd) & AT_INGRESS)
skb->tstamp.tv64 = 0;
#endif
sch->q.qlen--;
qdisc_unthrottled(sch);
qdisc_bstats_update(sch, skb);
return skb;
}
qdisc_watchdog_schedule(&q->watchdog, cb->time_to_send);
}
return NULL;
}
static struct sk_buff *fq_dequeue(struct Qdisc *sch)
{
struct fq_sched_data *q = qdisc_priv(sch);
u64 now = ktime_to_ns(ktime_get());
struct fq_flow_head *head;
struct sk_buff *skb;
struct fq_flow *f;
u32 rate;
skb = fq_dequeue_head(sch, &q->internal);
if (skb)
goto out;
fq_check_throttled(q, now);
begin:
head = &q->new_flows;
if (!head->first) {
head = &q->old_flows;
if (!head->first) {
if (q->time_next_delayed_flow != ~0ULL)
qdisc_watchdog_schedule_ns(&q->watchdog,
q->time_next_delayed_flow);
return NULL;
}
}
f = head->first;
if (f->credit <= 0) {
f->credit += q->quantum;
head->first = f->next;
fq_flow_add_tail(&q->old_flows, f);
goto begin;
}
if (unlikely(f->head && now < f->time_next_packet)) {
head->first = f->next;
fq_flow_set_throttled(q, f);
goto begin;
}
skb = fq_dequeue_head(sch, f);
if (!skb) {
head->first = f->next;
/* force a pass through old_flows to prevent starvation */
if ((head == &q->new_flows) && q->old_flows.first) {
fq_flow_add_tail(&q->old_flows, f);
} else {
fq_flow_set_detached(f);
f->age = jiffies;
q->inactive_flows++;
}
goto begin;
}
prefetch(&skb->end);
f->time_next_packet = now;
f->credit -= qdisc_pkt_len(skb);
if (f->credit > 0 || !q->rate_enable)
goto out;
rate = q->flow_max_rate;
if (skb->sk && skb->sk->sk_state != TCP_TIME_WAIT)
rate = min(skb->sk->sk_pacing_rate, rate);
if (rate != ~0U) {
u32 plen = max(qdisc_pkt_len(skb), q->quantum);
u64 len = (u64)plen * NSEC_PER_SEC;
if (likely(rate))
do_div(len, rate);
/* Since socket rate can change later,
* clamp the delay to 125 ms.
* TODO: maybe segment the too big skb, as in commit
* e43ac79a4bc ("sch_tbf: segment too big GSO packets")
*/
if (unlikely(len > 125 * NSEC_PER_MSEC)) {
len = 125 * NSEC_PER_MSEC;
q->stat_pkts_too_long++;
}
f->time_next_packet = now + len;
}
out:
qdisc_bstats_update(sch, skb);
qdisc_unthrottled(sch);
return skb;
}
static struct sk_buff *wfq_dequeue(struct Qdisc *sch)
{
struct wfq_sched_data *q = qdisc_priv(sch);
int i, weight;
struct wfq_class *cl = NULL;
u64 min_time;
struct sk_buff *skb = NULL;
struct sk_buff *next_pkt = NULL;
unsigned int len;
s64 bucket_ns = (s64)l2t_ns(&q->rate, wfq_bucket_bytes);
s64 result, now;
int prio = prio_schedule(q);
if (prio < 0)
return NULL;
/* Find the active queue with the smallest head finish time */
for (i = 0; i < wfq_max_queues; i++)
{
if (q->queues[i].prio != prio || q->queues[i].len_bytes == 0 )
continue;
if (!cl || wfq_time_before(q->queues[i].head_fin_time,
min_time))
{
cl = &q->queues[i];
min_time = cl->head_fin_time;
}
}
/* get head packet */
skb = cl->qdisc->ops->peek(cl->qdisc);
if (unlikely(!skb))
return NULL;
len = skb_size(skb);
now = ktime_get_ns();
result = tbf_schedule(len, q, now);
/* We don't have enough tokens */
if (result < 0)
{
/* For hrtimer absolute mode, we use now + t */
qdisc_watchdog_schedule_ns(&q->watchdog, now - result, true);
qdisc_qstats_overlimit(sch);
return NULL;
}
skb = qdisc_dequeue_peeked(cl->qdisc);
if (unlikely(!skb))
return NULL;
q->sum_len_bytes -= len;
sch->q.qlen--;
cl->len_bytes -= len;
q->prio_len_bytes[prio] -= len;
/* Set the head_fin_time for the remaining head packet */
if (cl->len_bytes > 0)
{
/* Get the current head packet */
next_pkt = cl->qdisc->ops->peek(cl->qdisc);
weight = wfq_queue_weight[cl->id];
if (likely(next_pkt && weight))
{
len = skb_size(next_pkt);
cl->head_fin_time += div_u64((u64)len, (u32)weight);
if (wfq_time_before(q->virtual_time[prio],
cl->head_fin_time))
q->virtual_time[prio] = cl->head_fin_time;
}
}
/* Bucket */
q->time_ns = now;
q->tokens = min_t(s64, result, bucket_ns);
qdisc_unthrottled(sch);
qdisc_bstats_update(sch, skb);
/* TCN */
if (wfq_ecn_scheme == wfq_tcn)
tcn_marking(skb);
/* CoDel */
else if (wfq_ecn_scheme == wfq_codel)
codel_marking(skb, cl);
/* dequeue equeue length based ECN marking */
else if (wfq_enable_dequeue_ecn == wfq_enable)
wfq_qlen_marking(skb, q, cl);
return skb;
}
static struct sk_buff *fq_dequeue(struct Qdisc *sch)
{
struct fq_sched_data *q = qdisc_priv(sch);
u64 now = ktime_get_ns();
struct fq_flow_head *head;
struct sk_buff *skb;
struct fq_flow *f;
u32 rate;
skb = fq_dequeue_head(sch, &q->internal);
if (skb)
goto out;
fq_check_throttled(q, now);
begin:
head = &q->new_flows;
if (!head->first) {
head = &q->old_flows;
if (!head->first) {
if (q->time_next_delayed_flow != ~0ULL)
qdisc_watchdog_schedule_ns(&q->watchdog,
q->time_next_delayed_flow);
return NULL;
}
}
f = head->first;
if (f->credit <= 0) {
f->credit += q->quantum;
head->first = f->next;
fq_flow_add_tail(&q->old_flows, f);
goto begin;
}
skb = f->head;
if (unlikely(skb && now < f->time_next_packet &&
!skb_is_tcp_pure_ack(skb))) {
head->first = f->next;
fq_flow_set_throttled(q, f);
goto begin;
}
skb = fq_dequeue_head(sch, f);
if (!skb) {
head->first = f->next;
/* force a pass through old_flows to prevent starvation */
if ((head == &q->new_flows) && q->old_flows.first) {
fq_flow_add_tail(&q->old_flows, f);
} else {
fq_flow_set_detached(f);
q->inactive_flows++;
}
goto begin;
}
prefetch(&skb->end);
f->credit -= qdisc_pkt_len(skb);
if (f->credit > 0 || !q->rate_enable)
goto out;
/* Do not pace locally generated ack packets */
if (skb_is_tcp_pure_ack(skb))
goto out;
rate = q->flow_max_rate;
if (skb->sk)
rate = min(skb->sk->sk_pacing_rate, rate);
if (rate != ~0U) {
u32 plen = max(qdisc_pkt_len(skb), q->quantum);
u64 len = (u64)plen * NSEC_PER_SEC;
if (likely(rate))
do_div(len, rate);
/* Since socket rate can change later,
* clamp the delay to 1 second.
* Really, providers of too big packets should be fixed !
*/
if (unlikely(len > NSEC_PER_SEC)) {
len = NSEC_PER_SEC;
q->stat_pkts_too_long++;
}
f->time_next_packet = now + len;
}
out:
qdisc_bstats_update(sch, skb);
return skb;
}
