Auxiliary routines:
- ---requeue
+ ---peek
- requeues once dequeued packet. It is used for non-standard or
- just buggy devices, which can defer output even if netif_queue_stopped()=0.
+ like dequeue but without removing a packet from the queue
---reset
if (qops->enqueue == NULL)
qops->enqueue = noop_qdisc_ops.enqueue;
- if (qops->requeue == NULL)
- qops->requeue = noop_qdisc_ops.requeue;
+ if (qops->peek == NULL) {
+ if (qops->dequeue == NULL) {
+ qops->peek = noop_qdisc_ops.peek;
+ } else {
+ rc = -EINVAL;
+ goto out;
+ }
+ }
if (qops->dequeue == NULL)
qops->dequeue = noop_qdisc_ops.dequeue;
(root qdisc, all its children, children of children etc.)
*/
-struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
+static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
{
struct Qdisc *q;
return NULL;
}
-/*
- * This lock is needed until some qdiscs stop calling qdisc_tree_decrease_qlen()
- * without rtnl_lock(); currently hfsc_dequeue(), netem_dequeue(), tbf_dequeue()
- */
-static DEFINE_SPINLOCK(qdisc_list_lock);
-
static void qdisc_list_add(struct Qdisc *q)
{
- if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
- spin_lock_bh(&qdisc_list_lock);
- list_add_tail(&q->list, &qdisc_root_sleeping(q)->list);
- spin_unlock_bh(&qdisc_list_lock);
- }
+ if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
+ list_add_tail(&q->list, &qdisc_dev(q)->qdisc->list);
}
void qdisc_list_del(struct Qdisc *q)
{
- if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
- spin_lock_bh(&qdisc_list_lock);
+ if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
list_del(&q->list);
- spin_unlock_bh(&qdisc_list_lock);
- }
}
EXPORT_SYMBOL(qdisc_list_del);
struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
{
- unsigned int i;
struct Qdisc *q;
- spin_lock_bh(&qdisc_list_lock);
-
- for (i = 0; i < dev->num_tx_queues; i++) {
- struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
- struct Qdisc *txq_root = txq->qdisc_sleeping;
-
- q = qdisc_match_from_root(txq_root, handle);
- if (q)
- goto unlock;
- }
+ q = qdisc_match_from_root(dev->qdisc, handle);
+ if (q)
+ goto out;
q = qdisc_match_from_root(dev->rx_queue.qdisc_sleeping, handle);
-
-unlock:
- spin_unlock_bh(&qdisc_list_lock);
-
+out:
return q;
}
struct nlattr *nest;
nest = nla_nest_start(skb, TCA_STAB);
+ if (nest == NULL)
+ goto nla_put_failure;
NLA_PUT(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts);
nla_nest_end(skb, nest);
}
EXPORT_SYMBOL(qdisc_calculate_pkt_len);
+void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc)
+{
+ if (!(qdisc->flags & TCQ_F_WARN_NONWC)) {
+ printk(KERN_WARNING
+ "%s: %s qdisc %X: is non-work-conserving?\n",
+ txt, qdisc->ops->id, qdisc->handle >> 16);
+ qdisc->flags |= TCQ_F_WARN_NONWC;
+ }
+}
+EXPORT_SYMBOL(qdisc_warn_nonwc);
+
static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
{
struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog,
timer);
wd->qdisc->flags &= ~TCQ_F_THROTTLED;
- smp_wmb();
__netif_schedule(qdisc_root(wd->qdisc));
return HRTIMER_NORESTART;
wd->qdisc->flags |= TCQ_F_THROTTLED;
time = ktime_set(0, 0);
- time = ktime_add_ns(time, PSCHED_US2NS(expires));
+ time = ktime_add_ns(time, PSCHED_TICKS2NS(expires));
hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS);
}
EXPORT_SYMBOL(qdisc_watchdog_schedule);
return i>0 ? autohandle : 0;
}
-/* Attach toplevel qdisc to device queue. */
-
-static struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
- struct Qdisc *qdisc)
-{
- struct Qdisc *oqdisc = dev_queue->qdisc_sleeping;
- spinlock_t *root_lock;
-
- root_lock = qdisc_lock(oqdisc);
- spin_lock_bh(root_lock);
-
- /* Prune old scheduler */
- if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1)
- qdisc_reset(oqdisc);
-
- /* ... and graft new one */
- if (qdisc == NULL)
- qdisc = &noop_qdisc;
- dev_queue->qdisc_sleeping = qdisc;
- dev_queue->qdisc = &noop_qdisc;
-
- spin_unlock_bh(root_lock);
-
- return oqdisc;
-}
-
void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
{
const struct Qdisc_class_ops *cops;
if (dev->flags & IFF_UP)
dev_deactivate(dev);
+ if (new && new->ops->attach) {
+ new->ops->attach(new);
+ num_q = 0;
+ }
+
for (i = 0; i < num_q; i++) {
struct netdev_queue *dev_queue = &dev->rx_queue;
if (new && i > 0)
atomic_inc(&new->refcnt);
+ if (!ingress)
+ qdisc_destroy(old);
+ }
+
+ if (!ingress) {
+ notify_and_destroy(skb, n, classid, dev->qdisc, new);
+ if (new && !new->ops->attach)
+ atomic_inc(&new->refcnt);
+ dev->qdisc = new ? : &noop_qdisc;
+ } else {
notify_and_destroy(skb, n, classid, old, new);
}
} else {
const struct Qdisc_class_ops *cops = parent->ops->cl_ops;
- err = -EINVAL;
-
- if (cops) {
+ err = -EOPNOTSUPP;
+ if (cops && cops->graft) {
unsigned long cl = cops->get(parent, classid);
if (cl) {
err = cops->graft(parent, cl, new, &old);
cops->put(parent, cl);
- }
+ } else
+ err = -ENOENT;
}
if (!err)
notify_and_destroy(skb, n, classid, old, new);
static struct Qdisc *
qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
- u32 parent, u32 handle, struct nlattr **tca, int *errp)
+ struct Qdisc *p, u32 parent, u32 handle,
+ struct nlattr **tca, int *errp)
{
int err;
struct nlattr *kind = tca[TCA_KIND];
struct qdisc_size_table *stab;
ops = qdisc_lookup_ops(kind);
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
if (ops == NULL && kind != NULL) {
char name[IFNAMSIZ];
if (nla_strlcpy(name, kind, IFNAMSIZ) < IFNAMSIZ) {
stab = qdisc_get_stab(tca[TCA_STAB]);
if (IS_ERR(stab)) {
err = PTR_ERR(stab);
- goto err_out3;
+ goto err_out4;
}
sch->stab = stab;
}
if (tca[TCA_RATE]) {
+ spinlock_t *root_lock;
+
+ err = -EOPNOTSUPP;
+ if (sch->flags & TCQ_F_MQROOT)
+ goto err_out4;
+
+ if ((sch->parent != TC_H_ROOT) &&
+ !(sch->flags & TCQ_F_INGRESS) &&
+ (!p || !(p->flags & TCQ_F_MQROOT)))
+ root_lock = qdisc_root_sleeping_lock(sch);
+ else
+ root_lock = qdisc_lock(sch);
+
err = gen_new_estimator(&sch->bstats, &sch->rate_est,
- qdisc_root_lock(sch),
- tca[TCA_RATE]);
- if (err) {
- /*
- * Any broken qdiscs that would require
- * a ops->reset() here? The qdisc was never
- * in action so it shouldn't be necessary.
- */
- if (ops->destroy)
- ops->destroy(sch);
- goto err_out3;
- }
+ root_lock, tca[TCA_RATE]);
+ if (err)
+ goto err_out4;
}
qdisc_list_add(sch);
return sch;
}
err_out3:
- qdisc_put_stab(sch->stab);
dev_put(dev);
kfree((char *) sch - sch->padded);
err_out2:
err_out:
*errp = err;
return NULL;
+
+err_out4:
+ /*
+ * Any broken qdiscs that would require a ops->reset() here?
+ * The qdisc was never in action so it shouldn't be necessary.
+ */
+ qdisc_put_stab(sch->stab);
+ if (ops->destroy)
+ ops->destroy(sch);
+ goto err_out3;
}
static int qdisc_change(struct Qdisc *sch, struct nlattr **tca)
qdisc_put_stab(sch->stab);
sch->stab = stab;
- if (tca[TCA_RATE])
+ if (tca[TCA_RATE]) {
+ /* NB: ignores errors from replace_estimator
+ because change can't be undone. */
+ if (sch->flags & TCQ_F_MQROOT)
+ goto out;
gen_replace_estimator(&sch->bstats, &sch->rate_est,
- qdisc_root_lock(sch), tca[TCA_RATE]);
+ qdisc_root_sleeping_lock(sch),
+ tca[TCA_RATE]);
+ }
+out:
return 0;
}
struct Qdisc *p = NULL;
int err;
- if (net != &init_net)
+ if (!net_eq(net, &init_net))
return -EINVAL;
if ((dev = __dev_get_by_index(&init_net, tcm->tcm_ifindex)) == NULL)
q = dev->rx_queue.qdisc_sleeping;
}
} else {
- struct netdev_queue *dev_queue;
- dev_queue = netdev_get_tx_queue(dev, 0);
- q = dev_queue->qdisc_sleeping;
+ q = dev->qdisc;
}
if (!q)
return -ENOENT;
struct Qdisc *q, *p;
int err;
- if (net != &init_net)
+ if (!net_eq(net, &init_net))
return -EINVAL;
replay:
q = dev->rx_queue.qdisc_sleeping;
}
} else {
- struct netdev_queue *dev_queue;
- dev_queue = netdev_get_tx_queue(dev, 0);
- q = dev_queue->qdisc_sleeping;
+ q = dev->qdisc;
}
/* It may be default qdisc, ignore it */
if (!(n->nlmsg_flags&NLM_F_CREATE))
return -ENOENT;
if (clid == TC_H_INGRESS)
- q = qdisc_create(dev, &dev->rx_queue,
+ q = qdisc_create(dev, &dev->rx_queue, p,
tcm->tcm_parent, tcm->tcm_parent,
tca, &err);
- else
- q = qdisc_create(dev, netdev_get_tx_queue(dev, 0),
+ else {
+ struct netdev_queue *dev_queue;
+
+ if (p && p->ops->cl_ops && p->ops->cl_ops->select_queue)
+ dev_queue = p->ops->cl_ops->select_queue(p, tcm);
+ else if (p)
+ dev_queue = p->dev_queue;
+ else
+ dev_queue = netdev_get_tx_queue(dev, 0);
+
+ q = qdisc_create(dev, dev_queue, p,
tcm->tcm_parent, tcm->tcm_handle,
tca, &err);
+ }
if (q == NULL) {
if (err == -EAGAIN)
goto replay;
if (q->stab && qdisc_dump_stab(skb, q->stab) < 0)
goto nla_put_failure;
- if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS,
- TCA_XSTATS, qdisc_root_lock(q), &d) < 0)
+ if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS,
+ qdisc_root_sleeping_lock(q), &d) < 0)
goto nla_put_failure;
if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0)
goto nla_put_failure;
if (gnet_stats_copy_basic(&d, &q->bstats) < 0 ||
- gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 ||
gnet_stats_copy_queue(&d, &q->qstats) < 0)
goto nla_put_failure;
int s_idx, s_q_idx;
struct net_device *dev;
- if (net != &init_net)
+ if (!net_eq(net, &init_net))
return 0;
s_idx = cb->args[0];
s_q_idx = q_idx = cb->args[1];
- read_lock(&dev_base_lock);
+
+ rcu_read_lock();
idx = 0;
- for_each_netdev(&init_net, dev) {
+ for_each_netdev_rcu(&init_net, dev) {
struct netdev_queue *dev_queue;
if (idx < s_idx)
s_q_idx = 0;
q_idx = 0;
- dev_queue = netdev_get_tx_queue(dev, 0);
- if (tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, &q_idx, s_q_idx) < 0)
+ if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx) < 0)
goto done;
dev_queue = &dev->rx_queue;
}
done:
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
cb->args[0] = idx;
cb->args[1] = q_idx;
static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
{
struct net *net = sock_net(skb->sk);
- struct netdev_queue *dev_queue;
struct tcmsg *tcm = NLMSG_DATA(n);
struct nlattr *tca[TCA_MAX + 1];
struct net_device *dev;
u32 qid = TC_H_MAJ(clid);
int err;
- if (net != &init_net)
+ if (!net_eq(net, &init_net))
return -EINVAL;
if ((dev = __dev_get_by_index(&init_net, tcm->tcm_ifindex)) == NULL)
/* Step 1. Determine qdisc handle X:0 */
- dev_queue = netdev_get_tx_queue(dev, 0);
if (pid != TC_H_ROOT) {
u32 qid1 = TC_H_MAJ(pid);
} else if (qid1) {
qid = qid1;
} else if (qid == 0)
- qid = dev_queue->qdisc_sleeping->handle;
+ qid = dev->qdisc->handle;
/* Now qid is genuine qdisc handle consistent
both with parent and child.
pid = TC_H_MAKE(qid, pid);
} else {
if (qid == 0)
- qid = dev_queue->qdisc_sleeping->handle;
+ qid = dev->qdisc->handle;
}
/* OK. Locate qdisc */
goto out;
break;
case RTM_DELTCLASS:
- err = cops->delete(q, cl);
+ err = -EOPNOTSUPP;
+ if (cops->delete)
+ err = cops->delete(q, cl);
if (err == 0)
tclass_notify(skb, n, q, cl, RTM_DELTCLASS);
goto out;
}
new_cl = cl;
- err = cops->change(q, clid, pid, tca, &new_cl);
+ err = -EOPNOTSUPP;
+ if (cops->change)
+ err = cops->change(q, clid, pid, tca, &new_cl);
if (err == 0)
tclass_notify(skb, n, q, new_cl, RTM_NEWTCLASS);
nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags);
tcm = NLMSG_DATA(nlh);
tcm->tcm_family = AF_UNSPEC;
+ tcm->tcm__pad1 = 0;
+ tcm->tcm__pad2 = 0;
tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
tcm->tcm_parent = q->handle;
tcm->tcm_handle = q->handle;
if (cl_ops->dump && cl_ops->dump(q, cl, skb, tcm) < 0)
goto nla_put_failure;
- if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS,
- TCA_XSTATS, qdisc_root_lock(q), &d) < 0)
+ if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS,
+ qdisc_root_sleeping_lock(q), &d) < 0)
goto nla_put_failure;
if (cl_ops->dump_stats && cl_ops->dump_stats(q, cl, &d) < 0)
struct net_device *dev;
int t, s_t;
- if (net != &init_net)
+ if (!net_eq(net, &init_net))
return 0;
if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm)))
s_t = cb->args[0];
t = 0;
- dev_queue = netdev_get_tx_queue(dev, 0);
- if (tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t) < 0)
+ if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0)
goto done;
dev_queue = &dev->rx_queue;
hrtimer_get_res(CLOCK_MONOTONIC, &ts);
seq_printf(seq, "%08x %08x %08x %08x\n",
- (u32)NSEC_PER_USEC, (u32)PSCHED_US2NS(1),
+ (u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1),
1000000,
(u32)NSEC_PER_SEC/(u32)ktime_to_ns(timespec_to_ktime(ts)));
{
register_qdisc(&pfifo_qdisc_ops);
register_qdisc(&bfifo_qdisc_ops);
+ register_qdisc(&mq_qdisc_ops);
proc_net_fops_create(&init_net, "psched", 0, &psched_fops);
rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff