static int multiq_tune(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct multiq_sched_data *q = qdisc_priv(sch);
struct tc_multiq_qopt *qopt;
int i;
if (!netif_is_multiqueue(qdisc_dev(sch)))
return -EOPNOTSUPP;
if (nla_len(opt) < sizeof(*qopt))
return -EINVAL;
qopt = nla_data(opt);
qopt->bands = qdisc_dev(sch)->real_num_tx_queues;
sch_tree_lock(sch);
q->bands = qopt->bands;
for (i = q->bands; i < q->max_bands; i++) {
if (q->queues[i] != &noop_qdisc) {
struct Qdisc *child = q->queues[i];
q->queues[i] = &noop_qdisc;
qdisc_tree_reduce_backlog(child, child->q.qlen,
child->qstats.backlog);
qdisc_put(child);
}
}
sch_tree_unlock(sch);
for (i = 0; i < q->bands; i++) {
if (q->queues[i] == &noop_qdisc) {
struct Qdisc *child, *old;
child = qdisc_create_dflt(sch->dev_queue,
&pfifo_qdisc_ops,
TC_H_MAKE(sch->handle,
i + 1), extack);
if (child) {
sch_tree_lock(sch);
old = q->queues[i];
q->queues[i] = child;
if (child != &noop_qdisc)
qdisc_hash_add(child, true);
if (old != &noop_qdisc) {
qdisc_tree_reduce_backlog(old,
old->q.qlen,
old->qstats.backlog);
qdisc_put(old);
}
sch_tree_unlock(sch);
}
}
}
return 0;
}
/* GSO packet is too big, segment it so that tbf can transmit
* each segment in time
*/
static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct tbf_sched_data *q = qdisc_priv(sch);
struct sk_buff *segs, *nskb;
netdev_features_t features = netif_skb_features(skb);
unsigned int len = 0, prev_len = qdisc_pkt_len(skb);
int ret, nb;
segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
if (IS_ERR_OR_NULL(segs))
return qdisc_drop(skb, sch, to_free);
nb = 0;
while (segs) {
nskb = segs->next;
skb_mark_not_on_list(segs);
qdisc_skb_cb(segs)->pkt_len = segs->len;
len += segs->len;
ret = qdisc_enqueue(segs, q->qdisc, to_free);
if (ret != NET_XMIT_SUCCESS) {
if (net_xmit_drop_count(ret))
qdisc_qstats_drop(sch);
} else {
nb++;
}
segs = nskb;
}
sch->q.qlen += nb;
if (nb > 1)
qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
consume_skb(skb);
return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
}
static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct prio_sched_data *q = qdisc_priv(sch);
struct Qdisc *queues[TCQ_PRIO_BANDS];
int oldbands = q->bands, i;
struct tc_prio_qopt *qopt;
if (nla_len(opt) < sizeof(*qopt))
return -EINVAL;
qopt = nla_data(opt);
if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < 2)
return -EINVAL;
for (i = 0; i <= TC_PRIO_MAX; i++) {
if (qopt->priomap[i] >= qopt->bands)
return -EINVAL;
}
/* Before commit, make sure we can allocate all new qdiscs */
for (i = oldbands; i < qopt->bands; i++) {
queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
TC_H_MAKE(sch->handle, i + 1),
extack);
if (!queues[i]) {
while (i > oldbands)
qdisc_put(queues[--i]);
return -ENOMEM;
}
}
prio_offload(sch, qopt);
sch_tree_lock(sch);
q->bands = qopt->bands;
memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
for (i = q->bands; i < oldbands; i++) {
struct Qdisc *child = q->queues[i];
qdisc_tree_reduce_backlog(child, child->q.qlen,
child->qstats.backlog);
}
for (i = oldbands; i < q->bands; i++) {
q->queues[i] = queues[i];
if (q->queues[i] != &noop_qdisc)
qdisc_hash_add(q->queues[i], true);
}
sch_tree_unlock(sch);
for (i = q->bands; i < oldbands; i++)
qdisc_put(q->queues[i]);
return 0;
}
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 int codel_change(struct Qdisc *sch, struct nlattr *opt)
{
struct codel_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_CODEL_MAX + 1];
unsigned int qlen, dropped = 0;
int err;
if (!opt)
return -EINVAL;
err = nla_parse_nested(tb, TCA_CODEL_MAX, opt, codel_policy);
if (err < 0)
return err;
sch_tree_lock(sch);
if (tb[TCA_CODEL_TARGET]) {
u32 target = nla_get_u32(tb[TCA_CODEL_TARGET]);
q->params.target = ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT;
}
if (tb[TCA_CODEL_CE_THRESHOLD]) {
u64 val = nla_get_u32(tb[TCA_CODEL_CE_THRESHOLD]);
q->params.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT;
}
if (tb[TCA_CODEL_INTERVAL]) {
u32 interval = nla_get_u32(tb[TCA_CODEL_INTERVAL]);
q->params.interval = ((u64)interval * NSEC_PER_USEC) >> CODEL_SHIFT;
}
if (tb[TCA_CODEL_LIMIT])
sch->limit = nla_get_u32(tb[TCA_CODEL_LIMIT]);
if (tb[TCA_CODEL_ECN])
q->params.ecn = !!nla_get_u32(tb[TCA_CODEL_ECN]);
qlen = sch->q.qlen;
while (sch->q.qlen > sch->limit) {
struct sk_buff *skb = __skb_dequeue(&sch->q);
dropped += qdisc_pkt_len(skb);
qdisc_qstats_backlog_dec(sch, skb);
qdisc_drop(skb, sch);
}
qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
sch_tree_unlock(sch);
return 0;
}
static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
unsigned int prev_backlog;
if (likely(sch->q.qlen < sch->limit))
return qdisc_enqueue_tail(skb, sch);
prev_backlog = sch->qstats.backlog;
/* queue full, remove one skb to fulfill the limit */
__qdisc_queue_drop_head(sch, &sch->q, to_free);
qdisc_qstats_drop(sch);
qdisc_enqueue_tail(skb, sch);
qdisc_tree_reduce_backlog(sch, 0, prev_backlog - sch->qstats.backlog);
return NET_XMIT_CN;
}
/* Drop packet from queue array by creating a "hole" */
static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx,
struct sk_buff **to_free)
{
struct choke_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb = q->tab[idx];
q->tab[idx] = NULL;
if (idx == q->head)
choke_zap_head_holes(q);
if (idx == q->tail)
choke_zap_tail_holes(q);
qdisc_qstats_backlog_dec(sch, skb);
qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
qdisc_drop(skb, sch, to_free);
--sch->q.qlen;
}
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 int choke_change(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct choke_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_CHOKE_MAX + 1];
const struct tc_red_qopt *ctl;
int err;
struct sk_buff **old = NULL;
unsigned int mask;
u32 max_P;
if (opt == NULL)
return -EINVAL;
err = nla_parse_nested(tb, TCA_CHOKE_MAX, opt, choke_policy, NULL);
if (err < 0)
return err;
if (tb[TCA_CHOKE_PARMS] == NULL ||
tb[TCA_CHOKE_STAB] == NULL)
return -EINVAL;
max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0;
ctl = nla_data(tb[TCA_CHOKE_PARMS]);
if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog))
return -EINVAL;
if (ctl->limit > CHOKE_MAX_QUEUE)
return -EINVAL;
mask = roundup_pow_of_two(ctl->limit + 1) - 1;
if (mask != q->tab_mask) {
struct sk_buff **ntab;
ntab = kvmalloc_array((mask + 1), sizeof(struct sk_buff *), GFP_KERNEL | __GFP_ZERO);
if (!ntab)
return -ENOMEM;
sch_tree_lock(sch);
old = q->tab;
if (old) {
unsigned int oqlen = sch->q.qlen, tail = 0;
unsigned dropped = 0;
while (q->head != q->tail) {
struct sk_buff *skb = q->tab[q->head];
q->head = (q->head + 1) & q->tab_mask;
if (!skb)
continue;
if (tail < mask) {
ntab[tail++] = skb;
continue;
}
dropped += qdisc_pkt_len(skb);
qdisc_qstats_backlog_dec(sch, skb);
--sch->q.qlen;
rtnl_qdisc_drop(skb, sch);
}
qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
q->head = 0;
q->tail = tail;
}
q->tab_mask = mask;
q->tab = ntab;
} else
sch_tree_lock(sch);
q->flags = ctl->flags;
q->limit = ctl->limit;
red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
ctl->Plog, ctl->Scell_log,
nla_data(tb[TCA_CHOKE_STAB]),
max_P);
red_set_vars(&q->vars);
if (q->head == q->tail)
red_end_of_idle_period(&q->vars);
sch_tree_unlock(sch);
choke_free(old);
return 0;
}
static int fq_change(struct Qdisc *sch, struct nlattr *opt)
{
struct fq_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_FQ_MAX + 1];
int err, drop_count = 0;
unsigned drop_len = 0;
u32 fq_log;
if (!opt)
return -EINVAL;
err = nla_parse_nested(tb, TCA_FQ_MAX, opt, fq_policy);
if (err < 0)
return err;
sch_tree_lock(sch);
fq_log = q->fq_trees_log;
if (tb[TCA_FQ_BUCKETS_LOG]) {
u32 nval = nla_get_u32(tb[TCA_FQ_BUCKETS_LOG]);
if (nval >= 1 && nval <= ilog2(256*1024))
fq_log = nval;
else
err = -EINVAL;
}
if (tb[TCA_FQ_PLIMIT])
sch->limit = nla_get_u32(tb[TCA_FQ_PLIMIT]);
if (tb[TCA_FQ_FLOW_PLIMIT])
q->flow_plimit = nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT]);
if (tb[TCA_FQ_QUANTUM]) {
u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
if (quantum > 0)
q->quantum = quantum;
else
err = -EINVAL;
}
if (tb[TCA_FQ_INITIAL_QUANTUM])
q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]);
if (tb[TCA_FQ_FLOW_DEFAULT_RATE])
pr_warn_ratelimited("sch_fq: defrate %u ignored.\n",
nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE]));
if (tb[TCA_FQ_FLOW_MAX_RATE])
q->flow_max_rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]);
if (tb[TCA_FQ_RATE_ENABLE]) {
u32 enable = nla_get_u32(tb[TCA_FQ_RATE_ENABLE]);
if (enable <= 1)
q->rate_enable = enable;
else
err = -EINVAL;
}
if (tb[TCA_FQ_FLOW_REFILL_DELAY]) {
u32 usecs_delay = nla_get_u32(tb[TCA_FQ_FLOW_REFILL_DELAY]) ;
q->flow_refill_delay = usecs_to_jiffies(usecs_delay);
}
if (tb[TCA_FQ_ORPHAN_MASK])
q->orphan_mask = nla_get_u32(tb[TCA_FQ_ORPHAN_MASK]);
if (!err) {
sch_tree_unlock(sch);
err = fq_resize(sch, fq_log);
sch_tree_lock(sch);
}
while (sch->q.qlen > sch->limit) {
struct sk_buff *skb = fq_dequeue(sch);
if (!skb)
break;
drop_len += qdisc_pkt_len(skb);
rtnl_kfree_skbs(skb, skb);
drop_count++;
}
qdisc_tree_reduce_backlog(sch, drop_count, drop_len);
sch_tree_unlock(sch);
return err;
}
static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct fq_codel_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_FQ_CODEL_MAX + 1];
int err;
if (!opt)
return -EINVAL;
err = nla_parse_nested(tb, TCA_FQ_CODEL_MAX, opt, fq_codel_policy,
NULL);
if (err < 0)
return err;
if (tb[TCA_FQ_CODEL_FLOWS]) {
if (q->flows)
return -EINVAL;
q->flows_cnt = nla_get_u32(tb[TCA_FQ_CODEL_FLOWS]);
if (!q->flows_cnt ||
q->flows_cnt > 65536)
return -EINVAL;
}
sch_tree_lock(sch);
if (tb[TCA_FQ_CODEL_TARGET]) {
u64 target = nla_get_u32(tb[TCA_FQ_CODEL_TARGET]);
q->cparams.target = (target * NSEC_PER_USEC) >> CODEL_SHIFT;
}
if (tb[TCA_FQ_CODEL_CE_THRESHOLD]) {
u64 val = nla_get_u32(tb[TCA_FQ_CODEL_CE_THRESHOLD]);
q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT;
}
if (tb[TCA_FQ_CODEL_INTERVAL]) {
u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]);
q->cparams.interval = (interval * NSEC_PER_USEC) >> CODEL_SHIFT;
}
if (tb[TCA_FQ_CODEL_LIMIT])
sch->limit = nla_get_u32(tb[TCA_FQ_CODEL_LIMIT]);
if (tb[TCA_FQ_CODEL_ECN])
q->cparams.ecn = !!nla_get_u32(tb[TCA_FQ_CODEL_ECN]);
if (tb[TCA_FQ_CODEL_QUANTUM])
q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM]));
if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])
q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
if (tb[TCA_FQ_CODEL_MEMORY_LIMIT])
q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT]));
while (sch->q.qlen > sch->limit ||
q->memory_usage > q->memory_limit) {
struct sk_buff *skb = fq_codel_dequeue(sch);
q->cstats.drop_len += qdisc_pkt_len(skb);
rtnl_kfree_skbs(skb, skb);
q->cstats.drop_count++;
}
qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len);
q->cstats.drop_count = 0;
q->cstats.drop_len = 0;
sch_tree_unlock(sch);
return 0;
}
static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct fq_codel_sched_data *q = qdisc_priv(sch);
unsigned int idx, prev_backlog, prev_qlen;
struct fq_codel_flow *flow;
int uninitialized_var(ret);
unsigned int pkt_len;
bool memory_limited;
idx = fq_codel_classify(skb, sch, &ret);
if (idx == 0) {
if (ret & __NET_XMIT_BYPASS)
qdisc_qstats_drop(sch);
__qdisc_drop(skb, to_free);
return ret;
}
idx--;
codel_set_enqueue_time(skb);
flow = &q->flows[idx];
flow_queue_add(flow, skb);
q->backlogs[idx] += qdisc_pkt_len(skb);
qdisc_qstats_backlog_inc(sch, skb);
if (list_empty(&flow->flowchain)) {
list_add_tail(&flow->flowchain, &q->new_flows);
q->new_flow_count++;
flow->deficit = q->quantum;
flow->dropped = 0;
}
get_codel_cb(skb)->mem_usage = skb->truesize;
q->memory_usage += get_codel_cb(skb)->mem_usage;
memory_limited = q->memory_usage > q->memory_limit;
if (++sch->q.qlen <= sch->limit && !memory_limited)
return NET_XMIT_SUCCESS;
prev_backlog = sch->qstats.backlog;
prev_qlen = sch->q.qlen;
/* save this packet length as it might be dropped by fq_codel_drop() */
pkt_len = qdisc_pkt_len(skb);
/* fq_codel_drop() is quite expensive, as it performs a linear search
* in q->backlogs[] to find a fat flow.
* So instead of dropping a single packet, drop half of its backlog
* with a 64 packets limit to not add a too big cpu spike here.
*/
ret = fq_codel_drop(sch, q->drop_batch_size, to_free);
prev_qlen -= sch->q.qlen;
prev_backlog -= sch->qstats.backlog;
q->drop_overlimit += prev_qlen;
if (memory_limited)
q->drop_overmemory += prev_qlen;
/* As we dropped packet(s), better let upper stack know this.
* If we dropped a packet for this flow, return NET_XMIT_CN,
* but in this case, our parents wont increase their backlogs.
*/
if (ret == idx) {
qdisc_tree_reduce_backlog(sch, prev_qlen - 1,
prev_backlog - pkt_len);
return NET_XMIT_CN;
}
qdisc_tree_reduce_backlog(sch, prev_qlen, prev_backlog);
return NET_XMIT_SUCCESS;
}
static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
{
struct sfq_sched_data *q = qdisc_priv(sch);
struct tc_sfq_qopt *ctl = nla_data(opt);
struct tc_sfq_qopt_v1 *ctl_v1 = NULL;
unsigned int qlen, dropped = 0;
struct red_parms *p = NULL;
if (opt->nla_len < nla_attr_size(sizeof(*ctl)))
return -EINVAL;
if (opt->nla_len >= nla_attr_size(sizeof(*ctl_v1)))
ctl_v1 = nla_data(opt);
if (ctl->divisor &&
(!is_power_of_2(ctl->divisor) || ctl->divisor > 65536))
return -EINVAL;
if (ctl_v1 && ctl_v1->qth_min) {
p = kmalloc(sizeof(*p), GFP_KERNEL);
if (!p)
return -ENOMEM;
}
sch_tree_lock(sch);
if (ctl->quantum) {
q->quantum = ctl->quantum;
q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
}
q->perturb_period = ctl->perturb_period * HZ;
if (ctl->flows)
q->maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS);
if (ctl->divisor) {
q->divisor = ctl->divisor;
q->maxflows = min_t(u32, q->maxflows, q->divisor);
}
if (ctl_v1) {
if (ctl_v1->depth)
q->maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH);
if (p) {
swap(q->red_parms, p);
red_set_parms(q->red_parms,
ctl_v1->qth_min, ctl_v1->qth_max,
ctl_v1->Wlog,
ctl_v1->Plog, ctl_v1->Scell_log,
NULL,
ctl_v1->max_P);
}
q->flags = ctl_v1->flags;
q->headdrop = ctl_v1->headdrop;
}
if (ctl->limit) {
q->limit = min_t(u32, ctl->limit, q->maxdepth * q->maxflows);
q->maxflows = min_t(u32, q->maxflows, q->limit);
}
qlen = sch->q.qlen;
while (sch->q.qlen > q->limit)
dropped += sfq_drop(sch);
qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
del_timer(&q->perturb_timer);
if (q->perturb_period) {
mod_timer(&q->perturb_timer, jiffies + q->perturb_period);
q->perturbation = prandom_u32();
}
sch_tree_unlock(sch);
kfree(p);
return 0;
}
/*
* When q->perturbation is changed, we rehash all queued skbs
* to avoid OOO (Out Of Order) effects.
* We dont use sfq_dequeue()/sfq_enqueue() because we dont want to change
* counters.
*/
static void sfq_rehash(struct Qdisc *sch)
{
struct sfq_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
int i;
struct sfq_slot *slot;
struct sk_buff_head list;
int dropped = 0;
unsigned int drop_len = 0;
__skb_queue_head_init(&list);
for (i = 0; i < q->maxflows; i++) {
slot = &q->slots[i];
if (!slot->qlen)
continue;
while (slot->qlen) {
skb = slot_dequeue_head(slot);
sfq_dec(q, i);
__skb_queue_tail(&list, skb);
}
slot->backlog = 0;
red_set_vars(&slot->vars);
q->ht[slot->hash] = SFQ_EMPTY_SLOT;
}
q->tail = NULL;
while ((skb = __skb_dequeue(&list)) != NULL) {
unsigned int hash = sfq_hash(q, skb);
sfq_index x = q->ht[hash];
slot = &q->slots[x];
if (x == SFQ_EMPTY_SLOT) {
x = q->dep[0].next; /* get a free slot */
if (x >= SFQ_MAX_FLOWS) {
drop:
qdisc_qstats_backlog_dec(sch, skb);
drop_len += qdisc_pkt_len(skb);
kfree_skb(skb);
dropped++;
continue;
}
q->ht[hash] = x;
slot = &q->slots[x];
slot->hash = hash;
}
if (slot->qlen >= q->maxdepth)
goto drop;
slot_queue_add(slot, skb);
if (q->red_parms)
slot->vars.qavg = red_calc_qavg(q->red_parms,
&slot->vars,
slot->backlog);
slot->backlog += qdisc_pkt_len(skb);
sfq_inc(q, x);
if (slot->qlen == 1) { /* The flow is new */
if (q->tail == NULL) { /* It is the first flow */
slot->next = x;
} else {
slot->next = q->tail->next;
q->tail->next = x;
}
q->tail = slot;
slot->allot = q->scaled_quantum;
}
}
sch->q.qlen -= dropped;
qdisc_tree_reduce_backlog(sch, dropped, drop_len);
}
static int
sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
{
struct sfq_sched_data *q = qdisc_priv(sch);
unsigned int hash, dropped;
sfq_index x, qlen;
struct sfq_slot *slot;
int uninitialized_var(ret);
struct sk_buff *head;
int delta;
hash = sfq_classify(skb, sch, &ret);
if (hash == 0) {
if (ret & __NET_XMIT_BYPASS)
qdisc_qstats_drop(sch);
kfree_skb(skb);
return ret;
}
hash--;
x = q->ht[hash];
slot = &q->slots[x];
if (x == SFQ_EMPTY_SLOT) {
x = q->dep[0].next; /* get a free slot */
if (x >= SFQ_MAX_FLOWS)
return qdisc_drop(skb, sch, to_free);
q->ht[hash] = x;
slot = &q->slots[x];
slot->hash = hash;
slot->backlog = 0; /* should already be 0 anyway... */
red_set_vars(&slot->vars);
goto enqueue;
}
if (q->red_parms) {
slot->vars.qavg = red_calc_qavg_no_idle_time(q->red_parms,
&slot->vars,
slot->backlog);
switch (red_action(q->red_parms,
&slot->vars,
slot->vars.qavg)) {
case RED_DONT_MARK:
break;
case RED_PROB_MARK:
qdisc_qstats_overlimit(sch);
if (sfq_prob_mark(q)) {
/* We know we have at least one packet in queue */
if (sfq_headdrop(q) &&
INET_ECN_set_ce(slot->skblist_next)) {
q->stats.prob_mark_head++;
break;
}
if (INET_ECN_set_ce(skb)) {
q->stats.prob_mark++;
break;
}
}
q->stats.prob_drop++;
goto congestion_drop;
case RED_HARD_MARK:
qdisc_qstats_overlimit(sch);
if (sfq_hard_mark(q)) {
/* We know we have at least one packet in queue */
if (sfq_headdrop(q) &&
INET_ECN_set_ce(slot->skblist_next)) {
q->stats.forced_mark_head++;
break;
}
if (INET_ECN_set_ce(skb)) {
q->stats.forced_mark++;
break;
}
}
q->stats.forced_drop++;
goto congestion_drop;
}
}
if (slot->qlen >= q->maxdepth) {
congestion_drop:
if (!sfq_headdrop(q))
return qdisc_drop(skb, sch, to_free);
/* We know we have at least one packet in queue */
head = slot_dequeue_head(slot);
delta = qdisc_pkt_len(head) - qdisc_pkt_len(skb);
sch->qstats.backlog -= delta;
slot->backlog -= delta;
qdisc_drop(head, sch, to_free);
slot_queue_add(slot, skb);
return NET_XMIT_CN;
}
enqueue:
qdisc_qstats_backlog_inc(sch, skb);
slot->backlog += qdisc_pkt_len(skb);
slot_queue_add(slot, skb);
sfq_inc(q, x);
if (slot->qlen == 1) { /* The flow is new */
if (q->tail == NULL) { /* It is the first flow */
slot->next = x;
} else {
slot->next = q->tail->next;
q->tail->next = x;
}
/* We put this flow at the end of our flow list.
* This might sound unfair for a new flow to wait after old ones,
* but we could endup servicing new flows only, and freeze old ones.
*/
q->tail = slot;
/* We could use a bigger initial quantum for new flows */
slot->allot = q->scaled_quantum;
}
if (++sch->q.qlen <= q->limit)
return NET_XMIT_SUCCESS;
qlen = slot->qlen;
dropped = sfq_drop(sch);
/* Return Congestion Notification only if we dropped a packet
* from this flow.
*/
if (qlen != slot->qlen)
return NET_XMIT_CN;
/* As we dropped a packet, better let upper stack know this */
qdisc_tree_reduce_backlog(sch, 1, dropped);
return NET_XMIT_SUCCESS;
}
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(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;
}
}
sch_tree_lock(sch);
if (child) {
qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
q->qdisc->qstats.backlog);
qdisc_destroy(q->qdisc);
q->qdisc = child;
if (child != &noop_qdisc)
qdisc_hash_add(child, true);
}
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;
}
