summaryrefslogtreecommitdiff
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/Kconfig11
-rw-r--r--net/sched/Makefile1
-rw-r--r--net/sched/cls_cgroup.c290
-rw-r--r--net/sched/ematch.c18
-rw-r--r--net/sched/sch_api.c15
-rw-r--r--net/sched/sch_atm.c33
-rw-r--r--net/sched/sch_blackhole.c1
-rw-r--r--net/sched/sch_cbq.c36
-rw-r--r--net/sched/sch_dsmark.c19
-rw-r--r--net/sched/sch_fifo.c4
-rw-r--r--net/sched/sch_generic.c36
-rw-r--r--net/sched/sch_gred.c22
-rw-r--r--net/sched/sch_hfsc.c34
-rw-r--r--net/sched/sch_htb.c45
-rw-r--r--net/sched/sch_multiq.c66
-rw-r--r--net/sched/sch_netem.c154
-rw-r--r--net/sched/sch_prio.c34
-rw-r--r--net/sched/sch_red.c27
-rw-r--r--net/sched/sch_sfq.c69
-rw-r--r--net/sched/sch_tbf.c27
-rw-r--r--net/sched/sch_teql.c19
21 files changed, 453 insertions, 508 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 6767e54155db..36543b6fcef3 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -316,6 +316,17 @@ config NET_CLS_FLOW
To compile this code as a module, choose M here: the
module will be called cls_flow.
+config NET_CLS_CGROUP
+ bool "Control Group Classifier"
+ select NET_CLS
+ depends on CGROUPS
+ ---help---
+ Say Y here if you want to classify packets based on the control
+ cgroup of their process.
+
+ To compile this code as a module, choose M here: the
+ module will be called cls_cgroup.
+
config NET_EMATCH
bool "Extended Matches"
select NET_CLS
diff --git a/net/sched/Makefile b/net/sched/Makefile
index e60c9925b269..70b35f8708c3 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -38,6 +38,7 @@ obj-$(CONFIG_NET_CLS_TCINDEX) += cls_tcindex.o
obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o
obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o
obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o
+obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o
obj-$(CONFIG_NET_EMATCH) += ematch.o
obj-$(CONFIG_NET_EMATCH_CMP) += em_cmp.o
obj-$(CONFIG_NET_EMATCH_NBYTE) += em_nbyte.o
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
new file mode 100644
index 000000000000..53ada2c0e41c
--- /dev/null
+++ b/net/sched/cls_cgroup.c
@@ -0,0 +1,290 @@
+/*
+ * net/sched/cls_cgroup.c Control Group Classifier
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/cgroup.h>
+#include <net/rtnetlink.h>
+#include <net/pkt_cls.h>
+
+struct cgroup_cls_state
+{
+ struct cgroup_subsys_state css;
+ u32 classid;
+};
+
+static inline struct cgroup_cls_state *net_cls_state(struct cgroup *cgrp)
+{
+ return (struct cgroup_cls_state *)
+ cgroup_subsys_state(cgrp, net_cls_subsys_id);
+}
+
+static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss,
+ struct cgroup *cgrp)
+{
+ struct cgroup_cls_state *cs;
+
+ if (!(cs = kzalloc(sizeof(*cs), GFP_KERNEL)))
+ return ERR_PTR(-ENOMEM);
+
+ if (cgrp->parent)
+ cs->classid = net_cls_state(cgrp->parent)->classid;
+
+ return &cs->css;
+}
+
+static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+ kfree(ss);
+}
+
+static u64 read_classid(struct cgroup *cgrp, struct cftype *cft)
+{
+ return net_cls_state(cgrp)->classid;
+}
+
+static int write_classid(struct cgroup *cgrp, struct cftype *cft, u64 value)
+{
+ if (!cgroup_lock_live_group(cgrp))
+ return -ENODEV;
+
+ net_cls_state(cgrp)->classid = (u32) value;
+
+ cgroup_unlock();
+
+ return 0;
+}
+
+static struct cftype ss_files[] = {
+ {
+ .name = "classid",
+ .read_u64 = read_classid,
+ .write_u64 = write_classid,
+ },
+};
+
+static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+ return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files));
+}
+
+struct cgroup_subsys net_cls_subsys = {
+ .name = "net_cls",
+ .create = cgrp_create,
+ .destroy = cgrp_destroy,
+ .populate = cgrp_populate,
+ .subsys_id = net_cls_subsys_id,
+};
+
+struct cls_cgroup_head
+{
+ u32 handle;
+ struct tcf_exts exts;
+ struct tcf_ematch_tree ematches;
+};
+
+static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp,
+ struct tcf_result *res)
+{
+ struct cls_cgroup_head *head = tp->root;
+ struct cgroup_cls_state *cs;
+ int ret = 0;
+
+ /*
+ * Due to the nature of the classifier it is required to ignore all
+ * packets originating from softirq context as accessing `current'
+ * would lead to false results.
+ *
+ * This test assumes that all callers of dev_queue_xmit() explicitely
+ * disable bh. Knowing this, it is possible to detect softirq based
+ * calls by looking at the number of nested bh disable calls because
+ * softirqs always disables bh.
+ */
+ if (softirq_count() != SOFTIRQ_OFFSET)
+ return -1;
+
+ rcu_read_lock();
+ cs = (struct cgroup_cls_state *) task_subsys_state(current,
+ net_cls_subsys_id);
+ if (cs->classid && tcf_em_tree_match(skb, &head->ematches, NULL)) {
+ res->classid = cs->classid;
+ res->class = 0;
+ ret = tcf_exts_exec(skb, &head->exts, res);
+ } else
+ ret = -1;
+
+ rcu_read_unlock();
+
+ return ret;
+}
+
+static unsigned long cls_cgroup_get(struct tcf_proto *tp, u32 handle)
+{
+ return 0UL;
+}
+
+static void cls_cgroup_put(struct tcf_proto *tp, unsigned long f)
+{
+}
+
+static int cls_cgroup_init(struct tcf_proto *tp)
+{
+ return 0;
+}
+
+static const struct tcf_ext_map cgroup_ext_map = {
+ .action = TCA_CGROUP_ACT,
+ .police = TCA_CGROUP_POLICE,
+};
+
+static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
+ [TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED },
+};
+
+static int cls_cgroup_change(struct tcf_proto *tp, unsigned long base,
+ u32 handle, struct nlattr **tca,
+ unsigned long *arg)
+{
+ struct nlattr *tb[TCA_CGROUP_MAX+1];
+ struct cls_cgroup_head *head = tp->root;
+ struct tcf_ematch_tree t;
+ struct tcf_exts e;
+ int err;
+
+ if (head == NULL) {
+ if (!handle)
+ return -EINVAL;
+
+ head = kzalloc(sizeof(*head), GFP_KERNEL);
+ if (head == NULL)
+ return -ENOBUFS;
+
+ head->handle = handle;
+
+ tcf_tree_lock(tp);
+ tp->root = head;
+ tcf_tree_unlock(tp);
+ }
+
+ if (handle != head->handle)
+ return -ENOENT;
+
+ err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS],
+ cgroup_policy);
+ if (err < 0)
+ return err;
+
+ err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &cgroup_ext_map);
+ if (err < 0)
+ return err;
+
+ err = tcf_em_tree_validate(tp, tb[TCA_CGROUP_EMATCHES], &t);
+ if (err < 0)
+ return err;
+
+ tcf_exts_change(tp, &head->exts, &e);
+ tcf_em_tree_change(tp, &head->ematches, &t);
+
+ return 0;
+}
+
+static void cls_cgroup_destroy(struct tcf_proto *tp)
+{
+ struct cls_cgroup_head *head;
+
+ head = (struct cls_cgroup_head *)xchg(&tp->root, NULL);
+
+ if (head) {
+ tcf_exts_destroy(tp, &head->exts);
+ tcf_em_tree_destroy(tp, &head->ematches);
+ kfree(head);
+ }
+}
+
+static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg)
+{
+ return -EOPNOTSUPP;
+}
+
+static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+{
+ struct cls_cgroup_head *head = tp->root;
+
+ if (arg->count < arg->skip)
+ goto skip;
+
+ if (arg->fn(tp, (unsigned long) head, arg) < 0) {
+ arg->stop = 1;
+ return;
+ }
+skip:
+ arg->count++;
+}
+
+static int cls_cgroup_dump(struct tcf_proto *tp, unsigned long fh,
+ struct sk_buff *skb, struct tcmsg *t)
+{
+ struct cls_cgroup_head *head = tp->root;
+ unsigned char *b = skb_tail_pointer(skb);
+ struct nlattr *nest;
+
+ t->tcm_handle = head->handle;
+
+ nest = nla_nest_start(skb, TCA_OPTIONS);
+ if (nest == NULL)
+ goto nla_put_failure;
+
+ if (tcf_exts_dump(skb, &head->exts, &cgroup_ext_map) < 0 ||
+ tcf_em_tree_dump(skb, &head->ematches, TCA_CGROUP_EMATCHES) < 0)
+ goto nla_put_failure;
+
+ nla_nest_end(skb, nest);
+
+ if (tcf_exts_dump_stats(skb, &head->exts, &cgroup_ext_map) < 0)
+ goto nla_put_failure;
+
+ return skb->len;
+
+nla_put_failure:
+ nlmsg_trim(skb, b);
+ return -1;
+}
+
+static struct tcf_proto_ops cls_cgroup_ops __read_mostly = {
+ .kind = "cgroup",
+ .init = cls_cgroup_init,
+ .change = cls_cgroup_change,
+ .classify = cls_cgroup_classify,
+ .destroy = cls_cgroup_destroy,
+ .get = cls_cgroup_get,
+ .put = cls_cgroup_put,
+ .delete = cls_cgroup_delete,
+ .walk = cls_cgroup_walk,
+ .dump = cls_cgroup_dump,
+ .owner = THIS_MODULE,
+};
+
+static int __init init_cgroup_cls(void)
+{
+ return register_tcf_proto_ops(&cls_cgroup_ops);
+}
+
+static void __exit exit_cgroup_cls(void)
+{
+ unregister_tcf_proto_ops(&cls_cgroup_ops);
+}
+
+module_init(init_cgroup_cls);
+module_exit(exit_cgroup_cls);
+MODULE_LICENSE("GPL");
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index e82519e548d7..aab59409728b 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -71,7 +71,7 @@
*
* static void __exit exit_my_ematch(void)
* {
- * return tcf_em_unregister(&my_ops);
+ * tcf_em_unregister(&my_ops);
* }
*
* module_init(init_my_ematch);
@@ -154,23 +154,11 @@ EXPORT_SYMBOL(tcf_em_register);
*
* Returns -ENOENT if no matching ematch was found.
*/
-int tcf_em_unregister(struct tcf_ematch_ops *ops)
+void tcf_em_unregister(struct tcf_ematch_ops *ops)
{
- int err = 0;
- struct tcf_ematch_ops *e;
-
write_lock(&ematch_mod_lock);
- list_for_each_entry(e, &ematch_ops, link) {
- if (e == ops) {
- list_del(&e->link);
- goto out;
- }
- }
-
- err = -ENOENT;
-out:
+ list_del(&ops->link);
write_unlock(&ematch_mod_lock);
- return err;
}
EXPORT_SYMBOL(tcf_em_unregister);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index b16ad2972c6b..5bcef13408c8 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -97,10 +97,9 @@ static int tclass_notify(struct sk_buff *oskb, struct nlmsghdr *n,
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
@@ -147,8 +146,14 @@ int register_qdisc(struct Qdisc_ops *qops)
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;
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 43d37256c15e..ca90f6e59aee 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -62,7 +62,7 @@ struct atm_qdisc_data {
struct atm_flow_data link; /* unclassified skbs go here */
struct atm_flow_data *flows; /* NB: "link" is also on this
list */
- struct tasklet_struct task; /* requeue tasklet */
+ struct tasklet_struct task; /* dequeue tasklet */
};
/* ------------------------- Class/flow operations ------------------------- */
@@ -480,11 +480,14 @@ static void sch_atm_dequeue(unsigned long data)
* If traffic is properly shaped, this won't generate nasty
* little bursts. Otherwise, it may ... (but that's okay)
*/
- while ((skb = flow->q->dequeue(flow->q))) {
- if (!atm_may_send(flow->vcc, skb->truesize)) {
- (void)flow->q->ops->requeue(skb, flow->q);
+ while ((skb = flow->q->ops->peek(flow->q))) {
+ if (!atm_may_send(flow->vcc, skb->truesize))
break;
- }
+
+ skb = qdisc_dequeue_peeked(flow->q);
+ if (unlikely(!skb))
+ break;
+
pr_debug("atm_tc_dequeue: sending on class %p\n", flow);
/* remove any LL header somebody else has attached */
skb_pull(skb, skb_network_offset(skb));
@@ -516,27 +519,19 @@ static struct sk_buff *atm_tc_dequeue(struct Qdisc *sch)
pr_debug("atm_tc_dequeue(sch %p,[qdisc %p])\n", sch, p);
tasklet_schedule(&p->task);
- skb = p->link.q->dequeue(p->link.q);
+ skb = qdisc_dequeue_peeked(p->link.q);
if (skb)
sch->q.qlen--;
return skb;
}
-static int atm_tc_requeue(struct sk_buff *skb, struct Qdisc *sch)
+static struct sk_buff *atm_tc_peek(struct Qdisc *sch)
{
struct atm_qdisc_data *p = qdisc_priv(sch);
- int ret;
- pr_debug("atm_tc_requeue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p);
- ret = p->link.q->ops->requeue(skb, p->link.q);
- if (!ret) {
- sch->q.qlen++;
- sch->qstats.requeues++;
- } else if (net_xmit_drop_count(ret)) {
- sch->qstats.drops++;
- p->link.qstats.drops++;
- }
- return ret;
+ pr_debug("atm_tc_peek(sch %p,[qdisc %p])\n", sch, p);
+
+ return p->link.q->ops->peek(p->link.q);
}
static unsigned int atm_tc_drop(struct Qdisc *sch)
@@ -694,7 +689,7 @@ static struct Qdisc_ops atm_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct atm_qdisc_data),
.enqueue = atm_tc_enqueue,
.dequeue = atm_tc_dequeue,
- .requeue = atm_tc_requeue,
+ .peek = atm_tc_peek,
.drop = atm_tc_drop,
.init = atm_tc_init,
.reset = atm_tc_reset,
diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c
index 507fb488bc98..094a874b48bc 100644
--- a/net/sched/sch_blackhole.c
+++ b/net/sched/sch_blackhole.c
@@ -33,6 +33,7 @@ static struct Qdisc_ops blackhole_qdisc_ops __read_mostly = {
.priv_size = 0,
.enqueue = blackhole_enqueue,
.dequeue = blackhole_dequeue,
+ .peek = blackhole_dequeue,
.owner = THIS_MODULE,
};
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 03e389e8d945..a99e37e9e6f1 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -405,40 +405,6 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
return ret;
}
-static int
-cbq_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
- struct cbq_sched_data *q = qdisc_priv(sch);
- struct cbq_class *cl;
- int ret;
-
- if ((cl = q->tx_class) == NULL) {
- kfree_skb(skb);
- sch->qstats.drops++;
- return NET_XMIT_CN;
- }
- q->tx_class = NULL;
-
- cbq_mark_toplevel(q, cl);
-
-#ifdef CONFIG_NET_CLS_ACT
- q->rx_class = cl;
- cl->q->__parent = sch;
-#endif
- if ((ret = cl->q->ops->requeue(skb, cl->q)) == 0) {
- sch->q.qlen++;
- sch->qstats.requeues++;
- if (!cl->next_alive)
- cbq_activate_class(cl);
- return 0;
- }
- if (net_xmit_drop_count(ret)) {
- sch->qstats.drops++;
- cl->qstats.drops++;
- }
- return ret;
-}
-
/* Overlimit actions */
/* TC_CBQ_OVL_CLASSIC: (default) penalize leaf class by adding offtime */
@@ -2066,7 +2032,7 @@ static struct Qdisc_ops cbq_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct cbq_sched_data),
.enqueue = cbq_enqueue,
.dequeue = cbq_dequeue,
- .requeue = cbq_requeue,
+ .peek = qdisc_peek_dequeued,
.drop = cbq_drop,
.init = cbq_init,
.reset = cbq_reset,
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index ba43aab3a851..3f9427a4b757 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -313,24 +313,13 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
return skb;
}
-static int dsmark_requeue(struct sk_buff *skb, struct Qdisc *sch)
+static struct sk_buff *dsmark_peek(struct Qdisc *sch)
{
struct dsmark_qdisc_data *p = qdisc_priv(sch);
- int err;
-
- pr_debug("dsmark_requeue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p);
-
- err = p->q->ops->requeue(skb, p->q);
- if (err != NET_XMIT_SUCCESS) {
- if (net_xmit_drop_count(err))
- sch->qstats.drops++;
- return err;
- }
- sch->q.qlen++;
- sch->qstats.requeues++;
+ pr_debug("dsmark_peek(sch %p,[qdisc %p])\n", sch, p);
- return NET_XMIT_SUCCESS;
+ return p->q->ops->peek(p->q);
}
static unsigned int dsmark_drop(struct Qdisc *sch)
@@ -496,7 +485,7 @@ static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct dsmark_qdisc_data),
.enqueue = dsmark_enqueue,
.dequeue = dsmark_dequeue,
- .requeue = dsmark_requeue,
+ .peek = dsmark_peek,
.drop = dsmark_drop,
.init = dsmark_init,
.reset = dsmark_reset,
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 23d258bfe8ac..92cfc9d7e3b9 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -83,7 +83,7 @@ struct Qdisc_ops pfifo_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct fifo_sched_data),
.enqueue = pfifo_enqueue,
.dequeue = qdisc_dequeue_head,
- .requeue = qdisc_requeue,
+ .peek = qdisc_peek_head,
.drop = qdisc_queue_drop,
.init = fifo_init,
.reset = qdisc_reset_queue,
@@ -98,7 +98,7 @@ struct Qdisc_ops bfifo_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct fifo_sched_data),
.enqueue = bfifo_enqueue,
.dequeue = qdisc_dequeue_head,
- .requeue = qdisc_requeue,
+ .peek = qdisc_peek_head,
.drop = qdisc_queue_drop,
.init = fifo_init,
.reset = qdisc_reset_queue,
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 93cd30ce6501..80c8f3dbbea1 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -306,21 +306,12 @@ static struct sk_buff *noop_dequeue(struct Qdisc * qdisc)
return NULL;
}
-static int noop_requeue(struct sk_buff *skb, struct Qdisc* qdisc)
-{
- if (net_ratelimit())
- printk(KERN_DEBUG "%s deferred output. It is buggy.\n",
- skb->dev->name);
- kfree_skb(skb);
- return NET_XMIT_CN;
-}
-
struct Qdisc_ops noop_qdisc_ops __read_mostly = {
.id = "noop",
.priv_size = 0,
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
- .requeue = noop_requeue,
+ .peek = noop_dequeue,
.owner = THIS_MODULE,
};
@@ -335,7 +326,6 @@ struct Qdisc noop_qdisc = {
.flags = TCQ_F_BUILTIN,
.ops = &noop_qdisc_ops,
.list = LIST_HEAD_INIT(noop_qdisc.list),
- .requeue.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
.q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
.dev_queue = &noop_netdev_queue,
};
@@ -346,7 +336,7 @@ static struct Qdisc_ops noqueue_qdisc_ops __read_mostly = {
.priv_size = 0,
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
- .requeue = noop_requeue,
+ .peek = noop_dequeue,
.owner = THIS_MODULE,
};
@@ -362,7 +352,6 @@ static struct Qdisc noqueue_qdisc = {
.flags = TCQ_F_BUILTIN,
.ops = &noqueue_qdisc_ops,
.list = LIST_HEAD_INIT(noqueue_qdisc.list),
- .requeue.lock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.q.lock),
.q.lock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.q.lock),
.dev_queue = &noqueue_netdev_queue,
};
@@ -411,10 +400,17 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc)
return NULL;
}
-static int pfifo_fast_requeue(struct sk_buff *skb, struct Qdisc* qdisc)
+static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc)
{
- qdisc->q.qlen++;
- return __qdisc_requeue(skb, qdisc, prio2list(skb, qdisc));
+ int prio;
+ struct sk_buff_head *list = qdisc_priv(qdisc);
+
+ for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) {
+ if (!skb_queue_empty(list + prio))
+ return skb_peek(list + prio);
+ }
+
+ return NULL;
}
static void pfifo_fast_reset(struct Qdisc* qdisc)
@@ -457,7 +453,7 @@ static struct Qdisc_ops pfifo_fast_ops __read_mostly = {
.priv_size = PFIFO_FAST_BANDS * sizeof(struct sk_buff_head),
.enqueue = pfifo_fast_enqueue,
.dequeue = pfifo_fast_dequeue,
- .requeue = pfifo_fast_requeue,
+ .peek = pfifo_fast_peek,
.init = pfifo_fast_init,
.reset = pfifo_fast_reset,
.dump = pfifo_fast_dump,
@@ -483,7 +479,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
sch->padded = (char *) sch - (char *) p;
INIT_LIST_HEAD(&sch->list);
- skb_queue_head_init(&sch->requeue);
skb_queue_head_init(&sch->q);
sch->ops = ops;
sch->enqueue = ops->enqueue;
@@ -526,6 +521,9 @@ void qdisc_reset(struct Qdisc *qdisc)
if (ops->reset)
ops->reset(qdisc);
+
+ kfree_skb(qdisc->gso_skb);
+ qdisc->gso_skb = NULL;
}
EXPORT_SYMBOL(qdisc_reset);
@@ -552,8 +550,6 @@ void qdisc_destroy(struct Qdisc *qdisc)
dev_put(qdisc_dev(qdisc));
kfree_skb(qdisc->gso_skb);
- __skb_queue_purge(&qdisc->requeue);
-
kfree((char *) qdisc - qdisc->padded);
}
EXPORT_SYMBOL(qdisc_destroy);
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index c1ad6b8de105..40408d595c08 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -240,26 +240,6 @@ congestion_drop:
return NET_XMIT_CN;
}
-static int gred_requeue(struct sk_buff *skb, struct Qdisc* sch)
-{
- struct gred_sched *t = qdisc_priv(sch);
- struct gred_sched_data *q;
- u16 dp = tc_index_to_dp(skb);
-
- if (dp >= t->DPs || (q = t->tab[dp]) == NULL) {
- if (net_ratelimit())
- printk(KERN_WARNING "GRED: Unable to relocate VQ 0x%x "
- "for requeue, screwing up backlog.\n",
- tc_index_to_dp(skb));
- } else {
- if (red_is_idling(&q->parms))
- red_end_of_idle_period(&q->parms);
- q->backlog += qdisc_pkt_len(skb);
- }
-
- return qdisc_requeue(skb, sch);
-}
-
static struct sk_buff *gred_dequeue(struct Qdisc* sch)
{
struct sk_buff *skb;
@@ -602,7 +582,7 @@ static struct Qdisc_ops gred_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct gred_sched),
.enqueue = gred_enqueue,
.dequeue = gred_dequeue,
- .requeue = gred_requeue,
+ .peek = qdisc_peek_head,
.drop = gred_drop,
.init = gred_init,
.reset = gred_reset,
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index c1e77da8cd09..071c4749a12b 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -184,7 +184,6 @@ struct hfsc_sched
struct rb_root eligible; /* eligible tree */
struct list_head droplist; /* active leaf class list (for
dropping) */
- struct sk_buff_head requeue; /* requeued packet */
struct qdisc_watchdog watchdog; /* watchdog timer */
};
@@ -880,28 +879,20 @@ set_passive(struct hfsc_class *cl)
*/
}
-/*
- * hack to get length of first packet in queue.
- */
static unsigned int
qdisc_peek_len(struct Qdisc *sch)
{
struct sk_buff *skb;
unsigned int len;
- skb = sch->dequeue(sch);
+ skb = sch->ops->peek(sch);
if (skb == NULL) {
if (net_ratelimit())
printk("qdisc_peek_len: non work-conserving qdisc ?\n");
return 0;
}
len = qdisc_pkt_len(skb);
- if (unlikely(sch->ops->requeue(skb, sch) != NET_XMIT_SUCCESS)) {
- if (net_ratelimit())
- printk("qdisc_peek_len: failed to requeue\n");
- qdisc_tree_decrease_qlen(sch, 1);
- return 0;
- }
+
return len;
}
@@ -1440,7 +1431,6 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
return err;
q->eligible = RB_ROOT;
INIT_LIST_HEAD(&q->droplist);
- skb_queue_head_init(&q->requeue);
q->root.cl_common.classid = sch->handle;
q->root.refcnt = 1;
@@ -1525,7 +1515,6 @@ hfsc_reset_qdisc(struct Qdisc *sch)
hlist_for_each_entry(cl, n, &q->clhash.hash[i], cl_common.hnode)
hfsc_reset_class(cl);
}
- __skb_queue_purge(&q->requeue);
q->eligible = RB_ROOT;
INIT_LIST_HEAD(&q->droplist);
qdisc_watchdog_cancel(&q->watchdog);
@@ -1550,7 +1539,6 @@ hfsc_destroy_qdisc(struct Qdisc *sch)
hfsc_destroy_class(sch, cl);
}
qdisc_class_hash_destroy(&q->clhash);
- __skb_queue_purge(&q->requeue);
qdisc_watchdog_cancel(&q->watchdog);
}
@@ -1617,8 +1605,6 @@ hfsc_dequeue(struct Qdisc *sch)
if (sch->q.qlen == 0)
return NULL;
- if ((skb = __skb_dequeue(&q->requeue)))
- goto out;
cur_time = psched_get_time();
@@ -1642,7 +1628,7 @@ hfsc_dequeue(struct Qdisc *sch)
}
}
- skb = cl->qdisc->dequeue(cl->qdisc);
+ skb = qdisc_dequeue_peeked(cl->qdisc);
if (skb == NULL) {
if (net_ratelimit())
printk("HFSC: Non-work-conserving qdisc ?\n");
@@ -1667,24 +1653,12 @@ hfsc_dequeue(struct Qdisc *sch)
set_passive(cl);
}
- out:
sch->flags &= ~TCQ_F_THROTTLED;
sch->q.qlen--;
return skb;
}
-static int
-hfsc_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
- struct hfsc_sched *q = qdisc_priv(sch);
-
- __skb_queue_head(&q->requeue, skb);
- sch->q.qlen++;
- sch->qstats.requeues++;
- return NET_XMIT_SUCCESS;
-}
-
static unsigned int
hfsc_drop(struct Qdisc *sch)
{
@@ -1735,7 +1709,7 @@ static struct Qdisc_ops hfsc_qdisc_ops __read_mostly = {
.dump = hfsc_dump_qdisc,
.enqueue = hfsc_enqueue,
.dequeue = hfsc_dequeue,
- .requeue = hfsc_requeue,
+ .peek = qdisc_peek_dequeued,
.drop = hfsc_drop,
.cl_ops = &hfsc_class_ops,
.priv_size = sizeof(struct hfsc_sched),
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index d14f02056ae6..83f5e69243c1 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -551,7 +551,7 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl)
static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
- int ret;
+ int uninitialized_var(ret);
struct htb_sched *q = qdisc_priv(sch);
struct htb_class *cl = htb_classify(skb, sch, &ret);
@@ -591,47 +591,6 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
return NET_XMIT_SUCCESS;
}
-/* TODO: requeuing packet charges it to policers again !! */
-static int htb_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
- int ret;
- struct htb_sched *q = qdisc_priv(sch);
- struct htb_class *cl = htb_classify(skb, sch, &ret);
- struct sk_buff *tskb;
-
- if (cl == HTB_DIRECT) {
- /* enqueue to helper queue */
- if (q->direct_queue.qlen < q->direct_qlen) {
- __skb_queue_head(&q->direct_queue, skb);
- } else {
- __skb_queue_head(&q->direct_queue, skb);
- tskb = __skb_dequeue_tail(&q->direct_queue);
- kfree_skb(tskb);
- sch->qstats.drops++;
- return NET_XMIT_CN;
- }
-#ifdef CONFIG_NET_CLS_ACT
- } else if (!cl) {
- if (ret & __NET_XMIT_BYPASS)
- sch->qstats.drops++;
- kfree_skb(skb);
- return ret;
-#endif
- } else if ((ret = cl->un.leaf.q->ops->requeue(skb, cl->un.leaf.q)) !=
- NET_XMIT_SUCCESS) {
- if (net_xmit_drop_count(ret)) {
- sch->qstats.drops++;
- cl->qstats.drops++;
- }
- return ret;
- } else
- htb_activate(q, cl);
-
- sch->q.qlen++;
- sch->qstats.requeues++;
- return NET_XMIT_SUCCESS;
-}
-
/**
* htb_charge_class - charges amount "bytes" to leaf and ancestors
*
@@ -1565,7 +1524,7 @@ static struct Qdisc_ops htb_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct htb_sched),
.enqueue = htb_enqueue,
.dequeue = htb_dequeue,
- .requeue = htb_requeue,
+ .peek = qdisc_peek_dequeued,
.drop = htb_drop,
.init = htb_init,
.reset = htb_reset,
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 915f3149dde2..f645ac55a1a1 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -92,40 +92,6 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
return ret;
}
-
-static int
-multiq_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
- struct Qdisc *qdisc;
- struct multiq_sched_data *q = qdisc_priv(sch);
- int ret;
-
- qdisc = multiq_classify(skb, sch, &ret);
-#ifdef CONFIG_NET_CLS_ACT
- if (qdisc == NULL) {
- if (ret & __NET_XMIT_BYPASS)
- sch->qstats.drops++;
- kfree_skb(skb);
- return ret;
- }
-#endif
-
- ret = qdisc->ops->requeue(skb, qdisc);
- if (ret == NET_XMIT_SUCCESS) {
- sch->q.qlen++;
- sch->qstats.requeues++;
- if (q->curband)
- q->curband--;
- else
- q->curband = q->bands - 1;
- return NET_XMIT_SUCCESS;
- }
- if (net_xmit_drop_count(ret))
- sch->qstats.drops++;
- return ret;
-}
-
-
static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
{
struct multiq_sched_data *q = qdisc_priv(sch);
@@ -140,7 +106,7 @@ static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
q->curband = 0;
/* Check that target subqueue is available before
- * pulling an skb to avoid excessive requeues
+ * pulling an skb to avoid head-of-line blocking.
*/
if (!__netif_subqueue_stopped(qdisc_dev(sch), q->curband)) {
qdisc = q->queues[q->curband];
@@ -155,6 +121,34 @@ static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
}
+static struct sk_buff *multiq_peek(struct Qdisc *sch)
+{
+ struct multiq_sched_data *q = qdisc_priv(sch);
+ unsigned int curband = q->curband;
+ struct Qdisc *qdisc;
+ struct sk_buff *skb;
+ int band;
+
+ for (band = 0; band < q->bands; band++) {
+ /* cycle through bands to ensure fairness */
+ curband++;
+ if (curband >= q->bands)
+ curband = 0;
+
+ /* Check that target subqueue is available before
+ * pulling an skb to avoid head-of-line blocking.
+ */
+ if (!__netif_subqueue_stopped(qdisc_dev(sch), curband)) {
+ qdisc = q->queues[curband];
+ skb = qdisc->ops->peek(qdisc);
+ if (skb)
+ return skb;
+ }
+ }
+ return NULL;
+
+}
+
static unsigned int multiq_drop(struct Qdisc *sch)
{
struct multiq_sched_data *q = qdisc_priv(sch);
@@ -451,7 +445,7 @@ static struct Qdisc_ops multiq_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct multiq_sched_data),
.enqueue = multiq_enqueue,
.dequeue = multiq_dequeue,
- .requeue = multiq_requeue,
+ .peek = multiq_peek,
.drop = multiq_drop,
.init = multiq_init,
.reset = multiq_reset,
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index a11959908d9a..3cbc3ff7b5bc 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -233,7 +233,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
*/
cb->time_to_send = psched_get_time();
q->counter = 0;
- ret = q->qdisc->ops->requeue(skb, q->qdisc);
+
+ __skb_queue_head(&q->qdisc->q, skb);
+ q->qdisc->qstats.backlog += qdisc_pkt_len(skb);
+ q->qdisc->qstats.requeues++;
+ ret = NET_XMIT_SUCCESS;
}
if (likely(ret == NET_XMIT_SUCCESS)) {
@@ -248,20 +252,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
return ret;
}
-/* Requeue packets but don't change time stamp */
-static int netem_requeue(struct sk_buff *skb, struct Qdisc *sch)
-{
- struct netem_sched_data *q = qdisc_priv(sch);
- int ret;
-
- if ((ret = q->qdisc->ops->requeue(skb, q->qdisc)) == 0) {
- sch->q.qlen++;
- sch->qstats.requeues++;
- }
-
- return ret;
-}
-
static unsigned int netem_drop(struct Qdisc* sch)
{
struct netem_sched_data *q = qdisc_priv(sch);
@@ -283,25 +273,22 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
if (sch->flags & TCQ_F_THROTTLED)
return NULL;
- skb = q->qdisc->dequeue(q->qdisc);
+ 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;
+
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);
}
@@ -351,7 +338,7 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
return 0;
}
-static int get_correlation(struct Qdisc *sch, const struct nlattr *attr)
+static void get_correlation(struct Qdisc *sch, const struct nlattr *attr)
{
struct netem_sched_data *q = qdisc_priv(sch);
const struct tc_netem_corr *c = nla_data(attr);
@@ -359,27 +346,24 @@ static int get_correlation(struct Qdisc *sch, const struct nlattr *attr)
init_crandom(&q->delay_cor, c->delay_corr);
init_crandom(&q->loss_cor, c->loss_corr);
init_crandom(&q->dup_cor, c->dup_corr);
- return 0;
}
-static int get_reorder(struct Qdisc *sch, const struct nlattr *attr)
+static void get_reorder(struct Qdisc *sch, const struct nlattr *attr)
{
struct netem_sched_data *q = qdisc_priv(sch);
const struct tc_netem_reorder *r = nla_data(attr);
q->reorder = r->probability;
init_crandom(&q->reorder_cor, r->correlation);
- return 0;
}
-static int get_corrupt(struct Qdisc *sch, const struct nlattr *attr)
+static void get_corrupt(struct Qdisc *sch, const struct nlattr *attr)
{
struct netem_sched_data *q = qdisc_priv(sch);
const struct tc_netem_corrupt *r = nla_data(attr);
q->corrupt = r->probability;
init_crandom(&q->corrupt_cor, r->correlation);
- return 0;
}
static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
@@ -438,11 +422,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
if (q->gap)
q->reorder = ~0;
- if (tb[TCA_NETEM_CORR]) {
- ret = get_correlation(sch, tb[TCA_NETEM_CORR]);
- if (ret)
- return ret;
- }
+ if (tb[TCA_NETEM_CORR])
+ get_correlation(sch, tb[TCA_NETEM_CORR]);
if (tb[TCA_NETEM_DELAY_DIST]) {
ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]);
@@ -450,17 +431,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
return ret;
}
- if (tb[TCA_NETEM_REORDER]) {
- ret = get_reorder(sch, tb[TCA_NETEM_REORDER]);
- if (ret)
- return ret;
- }
+ if (tb[TCA_NETEM_REORDER])
+ get_reorder(sch, tb[TCA_NETEM_REORDER]);
- if (tb[TCA_NETEM_CORRUPT]) {
- ret = get_corrupt(sch, tb[TCA_NETEM_CORRUPT]);
- if (ret)
- return ret;
- }
+ if (tb[TCA_NETEM_CORRUPT])
+ get_corrupt(sch, tb[TCA_NETEM_CORRUPT]);
return 0;
}
@@ -541,7 +516,7 @@ static struct Qdisc_ops tfifo_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct fifo_sched_data),
.enqueue = tfifo_enqueue,
.dequeue = qdisc_dequeue_head,
- .requeue = qdisc_requeue,
+ .peek = qdisc_peek_head,
.drop = qdisc_queue_drop,
.init = tfifo_init,
.reset = qdisc_reset_queue,
@@ -624,99 +599,12 @@ nla_put_failure:
return -1;
}
-static int netem_dump_class(struct Qdisc *sch, unsigned long cl,
- struct sk_buff *skb, struct tcmsg *tcm)
-{
- struct netem_sched_data *q = qdisc_priv(sch);
-
- if (cl != 1) /* only one class */
- return -ENOENT;
-
- tcm->tcm_handle |= TC_H_MIN(1);
- tcm->tcm_info = q->qdisc->handle;
-
- return 0;
-}
-
-static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
- struct Qdisc **old)
-{
- struct netem_sched_data *q = qdisc_priv(sch);
-
- if (new == NULL)
- new = &noop_qdisc;
-
- sch_tree_lock(sch);
- *old = xchg(&q->qdisc, new);
- qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
- qdisc_reset(*old);
- sch_tree_unlock(sch);
-
- return 0;
-}
-
-static struct Qdisc *netem_leaf(struct Qdisc *sch, unsigned long arg)
-{
- struct netem_sched_data *q = qdisc_priv(sch);
- return q->qdisc;
-}
-
-static unsigned long netem_get(struct Qdisc *sch, u32 classid)
-{
- return 1;
-}
-
-static void netem_put(struct Qdisc *sch, unsigned long arg)
-{
-}
-
-static int netem_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
- struct nlattr **tca, unsigned long *arg)
-{
- return -ENOSYS;
-}
-
-static int netem_delete(struct Qdisc *sch, unsigned long arg)
-{
- return -ENOSYS;
-}
-
-static void netem_walk(struct Qdisc *sch, struct qdisc_walker *walker)
-{
- if (!walker->stop) {
- if (walker->count >= walker->skip)
- if (walker->fn(sch, 1, walker) < 0) {
- walker->stop = 1;
- return;
- }
- walker->count++;
- }
-}
-
-static struct tcf_proto **netem_find_tcf(struct Qdisc *sch, unsigned long cl)
-{
- return NULL;
-}
-
-static const struct Qdisc_class_ops netem_class_ops = {
- .graft = netem_graft,
- .leaf = netem_leaf,
- .get = netem_get,
- .put = netem_put,
- .change = netem_change_class,
- .delete = netem_delete,
- .walk = netem_walk,
- .tcf_chain = netem_find_tcf,
- .dump = netem_dump_class,
-};
-
static struct Qdisc_ops netem_qdisc_ops __read_mostly = {
.id = "netem",
- .cl_ops = &netem_class_ops,
.priv_size = sizeof(struct netem_sched_data),
.enqueue = netem_enqueue,
.dequeue = netem_dequeue,
- .requeue = netem_requeue,
+ .peek = qdisc_peek_dequeued,
.drop = netem_drop,
.init = netem_init,
.reset = netem_reset,
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 504a78cdb718..ea65a87ec22c 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -93,34 +93,20 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
return ret;
}
-
-static int
-prio_requeue(struct sk_buff *skb, struct Qdisc* sch)
+static struct sk_buff *prio_peek(struct Qdisc *sch)
{
- struct Qdisc *qdisc;
- int ret;
-
- qdisc = prio_classify(skb, sch, &ret);
-#ifdef CONFIG_NET_CLS_ACT
- if (qdisc == NULL) {
- if (ret & __NET_XMIT_BYPASS)
- sch->qstats.drops++;
- kfree_skb(skb);
- return ret;
- }
-#endif
+ struct prio_sched_data *q = qdisc_priv(sch);
+ int prio;
- if ((ret = qdisc->ops->requeue(skb, qdisc)) == NET_XMIT_SUCCESS) {
- sch->q.qlen++;
- sch->qstats.requeues++;
- return NET_XMIT_SUCCESS;
+ for (prio = 0; prio < q->bands; prio++) {
+ struct Qdisc *qdisc = q->queues[prio];
+ struct sk_buff *skb = qdisc->ops->peek(qdisc);
+ if (skb)
+ return skb;
}
- if (net_xmit_drop_count(ret))
- sch->qstats.drops++;
- return ret;
+ return NULL;
}
-
static struct sk_buff *prio_dequeue(struct Qdisc* sch)
{
struct prio_sched_data *q = qdisc_priv(sch);
@@ -421,7 +407,7 @@ static struct Qdisc_ops prio_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct prio_sched_data),
.enqueue = prio_enqueue,
.dequeue = prio_dequeue,
- .requeue = prio_requeue,
+ .peek = prio_peek,
.drop = prio_drop,
.init = prio_init,
.reset = prio_reset,
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 5da05839e225..6a0371c22643 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -108,23 +108,6 @@ congestion_drop:
return NET_XMIT_CN;
}
-static int red_requeue(struct sk_buff *skb, struct Qdisc* sch)
-{
- struct red_sched_data *q = qdisc_priv(sch);
- struct Qdisc *child = q->qdisc;
- int ret;
-
- if (red_is_idling(&q->parms))
- red_end_of_idle_period(&q->parms);
-
- ret = child->ops->requeue(skb, child);
- if (likely(ret == NET_XMIT_SUCCESS)) {
- sch->qstats.requeues++;
- sch->q.qlen++;
- }
- return ret;
-}
-
static struct sk_buff * red_dequeue(struct Qdisc* sch)
{
struct sk_buff *skb;
@@ -140,6 +123,14 @@ static struct sk_buff * red_dequeue(struct Qdisc* sch)
return skb;
}
+static struct sk_buff * red_peek(struct Qdisc* sch)
+{
+ struct red_sched_data *q = qdisc_priv(sch);
+ struct Qdisc *child = q->qdisc;
+
+ return child->ops->peek(child);
+}
+
static unsigned int red_drop(struct Qdisc* sch)
{
struct red_sched_data *q = qdisc_priv(sch);
@@ -361,7 +352,7 @@ static struct Qdisc_ops red_qdisc_ops __read_mostly = {
.cl_ops = &red_class_ops,
.enqueue = red_enqueue,
.dequeue = red_dequeue,
- .requeue = red_requeue,
+ .peek = red_peek,
.drop = red_drop,
.init = red_init,
.reset = red_reset,
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index fe1508ef0d3d..ab8cfee3c9ce 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -329,71 +329,20 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
return NET_XMIT_CN;
}
-static int
-sfq_requeue(struct sk_buff *skb, struct Qdisc *sch)
+static struct sk_buff *
+sfq_peek(struct Qdisc *sch)
{
struct sfq_sched_data *q = qdisc_priv(sch);
- unsigned int hash;
- sfq_index x;
- int ret;
-
- hash = sfq_classify(skb, sch, &ret);
- if (hash == 0) {
- if (ret & __NET_XMIT_BYPASS)
- sch->qstats.drops++;
- kfree_skb(skb);
- return ret;
- }
- hash--;
-
- x = q->ht[hash];
- if (x == SFQ_DEPTH) {
- q->ht[hash] = x = q->dep[SFQ_DEPTH].next;
- q->hash[x] = hash;
- }
-
- sch->qstats.backlog += qdisc_pkt_len(skb);
- __skb_queue_head(&q->qs[x], skb);
- /* If selected queue has length q->limit+1, this means that
- * all another queues are empty and we do simple tail drop.
- * This packet is still requeued at head of queue, tail packet
- * is dropped.
- */
- if (q->qs[x].qlen > q->limit) {
- skb = q->qs[x].prev;
- __skb_unlink(skb, &q->qs[x]);
- sch->qstats.drops++;
- sch->qstats.backlog -= qdisc_pkt_len(skb);
- kfree_skb(skb);
- return NET_XMIT_CN;
- }
-
- sfq_inc(q, x);
- if (q->qs[x].qlen == 1) { /* The flow is new */
- if (q->tail == SFQ_DEPTH) { /* It is the first flow */
- q->tail = x;
- q->next[x] = x;
- q->allot[x] = q->quantum;
- } else {
- q->next[x] = q->next[q->tail];
- q->next[q->tail] = x;
- q->tail = x;
- }
- }
+ sfq_index a;
- if (++sch->q.qlen <= q->limit) {
- sch->qstats.requeues++;
- return 0;
- }
+ /* No active slots */
+ if (q->tail == SFQ_DEPTH)
+ return NULL;
- sch->qstats.drops++;
- sfq_drop(sch);
- return NET_XMIT_CN;
+ a = q->next[q->tail];
+ return skb_peek(&q->qs[a]);
}
-
-
-
static struct sk_buff *
sfq_dequeue(struct Qdisc *sch)
{
@@ -624,7 +573,7 @@ static struct Qdisc_ops sfq_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct sfq_sched_data),
.enqueue = sfq_enqueue,
.dequeue = sfq_dequeue,
- .requeue = sfq_requeue,
+ .peek = sfq_peek,
.drop = sfq_drop,
.init = sfq_init,
.reset = sfq_reset,
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 94c61598b86a..bb7783d584bb 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -139,19 +139,6 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch)
return 0;
}
-static int tbf_requeue(struct sk_buff *skb, struct Qdisc* sch)
-{
- struct tbf_sched_data *q = qdisc_priv(sch);
- int ret;
-
- if ((ret = q->qdisc->ops->requeue(skb, q->qdisc)) == 0) {
- sch->q.qlen++;
- sch->qstats.requeues++;
- }
-
- return ret;
-}
-
static unsigned int tbf_drop(struct Qdisc* sch)
{
struct tbf_sched_data *q = qdisc_priv(sch);
@@ -169,7 +156,7 @@ 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);
+ skb = q->qdisc->ops->peek(q->qdisc);
if (skb) {
psched_time_t now;
@@ -192,6 +179,10 @@ static struct sk_buff *tbf_dequeue(struct Qdisc* sch)
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;
@@ -214,12 +205,6 @@ static struct sk_buff *tbf_dequeue(struct Qdisc* sch)
(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;
@@ -469,7 +454,7 @@ static struct Qdisc_ops tbf_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct tbf_sched_data),
.enqueue = tbf_enqueue,
.dequeue = tbf_dequeue,
- .requeue = tbf_requeue,
+ .peek = qdisc_peek_dequeued,
.drop = tbf_drop,
.init = tbf_init,
.reset = tbf_reset,
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index d35ef059abb1..cfc8e7caba62 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -93,16 +93,6 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc* sch)
return NET_XMIT_DROP;
}
-static int
-teql_requeue(struct sk_buff *skb, struct Qdisc* sch)
-{
- struct teql_sched_data *q = qdisc_priv(sch);
-
- __skb_queue_head(&q->q, skb);
- sch->qstats.requeues++;
- return 0;
-}
-
static struct sk_buff *
teql_dequeue(struct Qdisc* sch)
{
@@ -123,6 +113,13 @@ teql_dequeue(struct Qdisc* sch)
return skb;
}
+static struct sk_buff *
+teql_peek(struct Qdisc* sch)
+{
+ /* teql is meant to be used as root qdisc */
+ return NULL;
+}
+
static __inline__ void
teql_neigh_release(struct neighbour *n)
{
@@ -433,7 +430,7 @@ static __init void teql_master_setup(struct net_device *dev)
ops->enqueue = teql_enqueue;
ops->dequeue = teql_dequeue;
- ops->requeue = teql_requeue;
+ ops->peek = teql_peek;
ops->init = teql_qdisc_init;
ops->reset = teql_reset;
ops->destroy = teql_destroy;
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-30 21:09:18 +0000