static struct sk_buff *tbf_dequeue(struct Qdisc* sch)
{
struct tbf_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
skb = q->qdisc->dequeue(q->qdisc);
if (skb) {
psched_time_t now;
long toks;
long ptoks = 0;
unsigned int len = skb->len;
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) {
q->t_c = now;
q->tokens = toks;
q->ptokens = ptoks;
sch->q.qlen--;
sch->flags &= ~TCQ_F_THROTTLED;
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)
*/
if (q->qdisc->ops->requeue(skb, q->qdisc) != NET_XMIT_SUCCESS) {
/* When requeue fails skb is dropped */
qdisc_tree_decrease_qlen(q->qdisc, 1);
sch->qstats.drops++;
}
sch->qstats.overlimits++;
}
return NULL;
}
static struct sk_buff *netem_dequeue(struct Qdisc *sch)
{
struct netem_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
smp_mb();
if (sch->flags & TCQ_F_THROTTLED)
return NULL;
skb = q->qdisc->dequeue(q->qdisc);
if (skb) {
const struct netem_skb_cb *cb
= (const struct netem_skb_cb *)skb->cb;
psched_time_t now = psched_get_time();
/* if more time remaining? */
if (cb->time_to_send <= now) {
pr_debug("netem_dequeue: return skb=%p\n", skb);
sch->q.qlen--;
return skb;
}
if (unlikely(q->qdisc->ops->requeue(skb, q->qdisc) != NET_XMIT_SUCCESS)) {
qdisc_tree_decrease_qlen(q->qdisc, 1);
sch->qstats.drops++;
printk(KERN_ERR "netem: %s could not requeue\n",
q->qdisc->ops->id);
}
qdisc_watchdog_schedule(&q->watchdog, cb->time_to_send);
}
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 void tbf_reset(struct Qdisc* sch)
{
struct tbf_sched_data *q = qdisc_priv(sch);
qdisc_reset(q->qdisc);
sch->q.qlen = 0;
q->t_c = psched_get_time();
q->tokens = q->buffer;
q->ptokens = q->mtu;
qdisc_watchdog_cancel(&q->watchdog);
}
static int tbf_init(struct Qdisc* sch, struct rtattr *opt)
{
struct tbf_sched_data *q = qdisc_priv(sch);
if (opt == NULL)
return -EINVAL;
q->t_c = psched_get_time();
qdisc_watchdog_init(&q->watchdog, sch);
q->qdisc = &noop_qdisc;
return tbf_change(sch, opt);
}
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;
}
/*
* Insert one skb into qdisc.
* Note: parent depends on return value to account for queue length.
* NET_XMIT_DROP: queue length didn't change.
* NET_XMIT_SUCCESS: one skb was queued.
*/
static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct netem_sched_data *q = qdisc_priv(sch);
/* We don't fill cb now as skb_unshare() may invalidate it */
struct netem_skb_cb *cb;
struct sk_buff *skb2;
int ret;
int count = 1;
pr_debug("netem_enqueue skb=%p\n", skb);
/* Random duplication */
if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
++count;
/* Random packet drop 0 => none, ~0 => all */
if (q->loss && q->loss >= get_crandom(&q->loss_cor))
--count;
if (count == 0) {
sch->qstats.drops++;
kfree_skb(skb);
return NET_XMIT_BYPASS;
}
skb_orphan(skb);
/*
* If we need to duplicate packet, then re-insert at top of the
* qdisc tree, since parent queuer expects that only one
* skb will be queued.
*/
if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) {
struct Qdisc *rootq = sch->dev->qdisc;
u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
q->duplicate = 0;
rootq->enqueue(skb2, rootq);
q->duplicate = dupsave;
}
/*
* Randomized packet corruption.
* Make copy if needed since we are modifying
* If packet is going to be hardware checksummed, then
* do it now in software before we mangle it.
*/
if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
if (!(skb = skb_unshare(skb, GFP_ATOMIC))
|| (skb->ip_summed == CHECKSUM_PARTIAL
&& skb_checksum_help(skb))) {
sch->qstats.drops++;
return NET_XMIT_DROP;
}
skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8);
}
cb = (struct netem_skb_cb *)skb->cb;
if (q->gap == 0 /* not doing reordering */
|| q->counter < q->gap /* inside last reordering gap */
|| q->reorder < get_crandom(&q->reorder_cor)) {
psched_time_t now;
psched_tdiff_t delay;
delay = tabledist(q->latency, q->jitter,
&q->delay_cor, q->delay_dist);
now = psched_get_time();
cb->time_to_send = now + delay;
++q->counter;
ret = q->qdisc->enqueue(skb, q->qdisc);
} else {
/*
* Do re-ordering by putting one out of N packets at the front
* of the queue.
*/
cb->time_to_send = psched_get_time();
q->counter = 0;
ret = q->qdisc->ops->requeue(skb, q->qdisc);
}
if (likely(ret == NET_XMIT_SUCCESS)) {
sch->q.qlen++;
sch->bstats.bytes += skb->len;
sch->bstats.packets++;
} else
sch->qstats.drops++;
pr_debug("netem: enqueue ret %d\n", ret);
return ret;
}
/*
* Insert one skb into qdisc.
* Note: parent depends on return value to account for queue length.
* NET_XMIT_DROP: queue length didn't change.
* NET_XMIT_SUCCESS: one skb was queued.
*/
static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct netem_sched_data *q = qdisc_priv(sch);
/* We don't fill cb now as skb_unshare() may invalidate it */
struct netem_skb_cb *cb;
struct sk_buff *skb2;
int count = 1;
/* Random duplication */
if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
++count;
/* Drop packet? */
if (loss_event(q))
--count;
if (count == 0) {
sch->qstats.drops++;
kfree_skb(skb);
return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
}
skb_orphan(skb);
/*
* If we need to duplicate packet, then re-insert at top of the
* qdisc tree, since parent queuer expects that only one
* skb will be queued.
*/
if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) {
struct Qdisc *rootq = qdisc_root(sch);
u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
q->duplicate = 0;
qdisc_enqueue_root(skb2, rootq);
q->duplicate = dupsave;
}
/*
* Randomized packet corruption.
* Make copy if needed since we are modifying
* If packet is going to be hardware checksummed, then
* do it now in software before we mangle it.
*/
if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
if (!(skb = skb_unshare(skb, GFP_ATOMIC)) ||
(skb->ip_summed == CHECKSUM_PARTIAL &&
skb_checksum_help(skb)))
return qdisc_drop(skb, sch);
skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8);
}
if (unlikely(skb_queue_len(&sch->q) >= sch->limit))
return qdisc_reshape_fail(skb, sch);
sch->qstats.backlog += qdisc_pkt_len(skb);
cb = netem_skb_cb(skb);
if (q->gap == 0 || /* not doing reordering */
q->counter < q->gap - 1 || /* inside last reordering gap */
q->reorder < get_crandom(&q->reorder_cor)) {
psched_time_t now;
psched_tdiff_t delay;
delay = tabledist(q->latency, q->jitter,
&q->delay_cor, q->delay_dist);
now = psched_get_time();
if (q->rate) {
struct sk_buff_head *list = &sch->q;
delay += packet_len_2_sched_time(skb->len, q);
if (!skb_queue_empty(list)) {
/*
* Last packet in queue is reference point (now).
* First packet in queue is already in flight,
* calculate this time bonus and substract
* from delay.
*/
delay -= now - netem_skb_cb(skb_peek(list))->time_to_send;
now = netem_skb_cb(skb_peek_tail(list))->time_to_send;
}
}
cb->time_to_send = now + delay;
++q->counter;
tfifo_enqueue(skb, sch);
} else {
/*
* Do re-ordering by putting one out of N packets at the front
* of the queue.
*/
cb->time_to_send = psched_get_time();
q->counter = 0;
__skb_queue_head(&sch->q, skb);
sch->qstats.requeues++;
}
return NET_XMIT_SUCCESS;
}
