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 struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
{
struct rb_node **p, *parent;
struct sock *sk = skb->sk;
struct rb_root *root;
struct fq_flow *f;
/* warning: no starvation prevention... */
if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL))
return &q->internal;
/* SYNACK messages are attached to a TCP_NEW_SYN_RECV request socket
* or a listener (SYNCOOKIE mode)
* 1) request sockets are not full blown,
* they do not contain sk_pacing_rate
* 2) They are not part of a 'flow' yet
* 3) We do not want to rate limit them (eg SYNFLOOD attack),
* especially if the listener set SO_MAX_PACING_RATE
* 4) We pretend they are orphaned
*/
if (!sk || sk_listener(sk)) {
unsigned long hash = skb_get_hash(skb) & q->orphan_mask;
/* By forcing low order bit to 1, we make sure to not
* collide with a local flow (socket pointers are word aligned)
*/
sk = (struct sock *)((hash << 1) | 1UL);
skb_orphan(skb);
}
root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)];
if (q->flows >= (2U << q->fq_trees_log) &&
q->inactive_flows > q->flows/2)
fq_gc(q, root, sk);
p = &root->rb_node;
parent = NULL;
while (*p) {
parent = *p;
f = container_of(parent, struct fq_flow, fq_node);
if (f->sk == sk) {
/* socket might have been reallocated, so check
* if its sk_hash is the same.
* It not, we need to refill credit with
* initial quantum
*/
if (unlikely(skb->sk &&
f->socket_hash != sk->sk_hash)) {
f->credit = q->initial_quantum;
f->socket_hash = sk->sk_hash;
f->time_next_packet = 0ULL;
}
return f;
}
if (f->sk > sk)
p = &parent->rb_right;
else
p = &parent->rb_left;
}
f = kmem_cache_zalloc(fq_flow_cachep, GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!f)) {
q->stat_allocation_errors++;
return &q->internal;
}
fq_flow_set_detached(f);
f->sk = sk;
if (skb->sk)
f->socket_hash = sk->sk_hash;
f->credit = q->initial_quantum;
rb_link_node(&f->fq_node, parent, p);
rb_insert_color(&f->fq_node, root);
q->flows++;
q->inactive_flows++;
return f;
}
static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
{
struct rb_node **p, *parent;
struct sock *sk = skb->sk;
struct rb_root *root;
struct fq_flow *f;
int band;
/* warning: no starvation prevention... */
band = prio2band[skb->priority & TC_PRIO_MAX];
if (unlikely(band == 0))
return &q->internal;
if (unlikely(!sk)) {
/* By forcing low order bit to 1, we make sure to not
* collide with a local flow (socket pointers are word aligned)
*/
sk = (struct sock *)(skb_get_rxhash(skb) | 1L);
}
root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)];
if (q->flows >= (2U << q->fq_trees_log) &&
q->inactive_flows > q->flows/2)
fq_gc(q, root, sk);
p = &root->rb_node;
parent = NULL;
while (*p) {
parent = *p;
f = container_of(parent, struct fq_flow, fq_node);
if (f->sk == sk) {
/* socket might have been reallocated, so check
* if its sk_hash is the same.
* It not, we need to refill credit with
* initial quantum
*/
if (unlikely(skb->sk &&
f->socket_hash != sk->sk_hash)) {
f->credit = q->initial_quantum;
f->socket_hash = sk->sk_hash;
}
return f;
}
if (f->sk > sk)
p = &parent->rb_right;
else
p = &parent->rb_left;
}
f = kmem_cache_zalloc(fq_flow_cachep, GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!f)) {
q->stat_allocation_errors++;
return &q->internal;
}
fq_flow_set_detached(f);
f->sk = sk;
if (skb->sk)
f->socket_hash = sk->sk_hash;
f->credit = q->initial_quantum;
rb_link_node(&f->fq_node, parent, p);
rb_insert_color(&f->fq_node, root);
q->flows++;
q->inactive_flows++;
return f;
}
