static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct fq_sched_data *q = qdisc_priv(sch);
struct fq_flow *f;
if (unlikely(sch->q.qlen >= sch->limit))
return qdisc_drop(skb, sch);
f = fq_classify(skb, q);
if (unlikely(f->qlen >= q->flow_plimit && f != &q->internal)) {
q->stat_flows_plimit++;
return qdisc_drop(skb, sch);
}
f->qlen++;
flow_queue_add(f, skb);
if (skb_is_retransmit(skb))
q->stat_tcp_retrans++;
sch->qstats.backlog += qdisc_pkt_len(skb);
if (fq_flow_is_detached(f)) {
fq_flow_add_tail(&q->new_flows, f);
if (q->quantum > f->credit)
f->credit = q->quantum;
q->inactive_flows--;
qdisc_unthrottled(sch);
}
if (unlikely(f == &q->internal)) {
q->stat_internal_packets++;
qdisc_unthrottled(sch);
}
sch->q.qlen++;
return NET_XMIT_SUCCESS;
}
static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct fq_sched_data *q = qdisc_priv(sch);
struct fq_flow *f;
if (unlikely(sch->q.qlen >= sch->limit))
return qdisc_drop(skb, sch);
f = fq_classify(skb, q);
if (unlikely(f->qlen >= q->flow_plimit && f != &q->internal)) {
q->stat_flows_plimit++;
return qdisc_drop(skb, sch);
}
f->qlen++;
if (skb_is_retransmit(skb))
q->stat_tcp_retrans++;
qdisc_qstats_backlog_inc(sch, skb);
if (fq_flow_is_detached(f)) {
fq_flow_add_tail(&q->new_flows, f);
if (time_after(jiffies, f->age + q->flow_refill_delay))
f->credit = max_t(u32, f->credit, q->quantum);
q->inactive_flows--;
}
/* Note: this overwrites f->age */
flow_queue_add(f, skb);
if (unlikely(f == &q->internal)) {
q->stat_internal_packets++;
}
sch->q.qlen++;
return NET_XMIT_SUCCESS;
}
static void fq_check_throttled(struct fq_sched_data *q, u64 now)
{
unsigned long sample;
struct rb_node *p;
if (q->time_next_delayed_flow > now)
return;
/* Update unthrottle latency EWMA.
* This is cheap and can help diagnosing timer/latency problems.
*/
sample = (unsigned long)(now - q->time_next_delayed_flow);
q->unthrottle_latency_ns -= q->unthrottle_latency_ns >> 3;
q->unthrottle_latency_ns += sample >> 3;
q->time_next_delayed_flow = ~0ULL;
while ((p = rb_first(&q->delayed)) != NULL) {
struct fq_flow *f = container_of(p, struct fq_flow, rate_node);
if (f->time_next_packet > now) {
q->time_next_delayed_flow = f->time_next_packet;
break;
}
rb_erase(p, &q->delayed);
q->throttled_flows--;
fq_flow_add_tail(&q->old_flows, f);
}
}
static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct fq_sched_data *q = qdisc_priv(sch);
struct fq_flow *f;
if (unlikely(sch->q.qlen >= sch->limit))
return qdisc_drop(skb, sch, to_free);
f = fq_classify(skb, q);
if (unlikely(f->qlen >= q->flow_plimit && f != &q->internal)) {
q->stat_flows_plimit++;
return qdisc_drop(skb, sch, to_free);
}
f->qlen++;
if (skb_is_retransmit(skb))
q->stat_tcp_retrans++;
qdisc_qstats_backlog_inc(sch, skb);
if (fq_flow_is_detached(f)) {
struct sock *sk = skb->sk;
fq_flow_add_tail(&q->new_flows, f);
if (time_after(jiffies, f->age + q->flow_refill_delay))
f->credit = max_t(u32, f->credit, q->quantum);
if (sk && q->rate_enable) {
if (unlikely(smp_load_acquire(&sk->sk_pacing_status) !=
SK_PACING_FQ))
smp_store_release(&sk->sk_pacing_status,
SK_PACING_FQ);
}
q->inactive_flows--;
}
/* Note: this overwrites f->age */
flow_queue_add(f, skb);
if (unlikely(f == &q->internal)) {
q->stat_internal_packets++;
}
sch->q.qlen++;
return NET_XMIT_SUCCESS;
}
static void fq_check_throttled(struct fq_sched_data *q, u64 now)
{
struct rb_node *p;
if (q->time_next_delayed_flow > now)
return;
q->time_next_delayed_flow = ~0ULL;
while ((p = rb_first(&q->delayed)) != NULL) {
struct fq_flow *f = container_of(p, struct fq_flow, rate_node);
if (f->time_next_packet > now) {
q->time_next_delayed_flow = f->time_next_packet;
break;
}
rb_erase(p, &q->delayed);
q->throttled_flows--;
fq_flow_add_tail(&q->old_flows, f);
}
}
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;
}
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 void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f)
{
rb_erase(&f->rate_node, &q->delayed);
q->throttled_flows--;
fq_flow_add_tail(&q->old_flows, f);
}
