* $Id: sch_htb.c,v 1.25 2003/12/07 11:08:25 devik Exp devik $
*/
#include <linux/module.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
#include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/if_ether.h>
-#include <linux/inet.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/notifier.h>
-#include <net/ip.h>
-#include <net/route.h>
#include <linux/skbuff.h>
#include <linux/list.h>
#include <linux/compiler.h>
-#include <net/sock.h>
-#include <net/pkt_sched.h>
#include <linux/rbtree.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
/* HTB algorithm.
Author: devik@cdi.cz
*/
#define HTB_HSIZE 16 /* classid hash size */
-#define HTB_EWMAC 2 /* rate average over HTB_EWMAC*HTB_HSIZE sec */
-#define HTB_RATECM 1 /* whether to use rate computer */
#define HTB_HYSTERESIS 1 /* whether to use mode hysteresis for speedup */
#define HTB_VER 0x30011 /* major must be matched with number suplied by TC as version */
struct tc_htb_xstats xstats; /* our special stats */
int refcnt; /* usage count of this class */
-#ifdef HTB_RATECM
- /* rate measurement counters */
- unsigned long rate_bytes, sum_bytes;
- unsigned long rate_packets, sum_packets;
-#endif
-
/* topology */
int level; /* our level (see above) */
struct htb_class *parent; /* parent class */
/* of un.leaf originals should be done. */
};
-/* TODO: maybe compute rate when size is too large .. or drop ? */
static inline long L2T(struct htb_class *cl, struct qdisc_rate_table *rate,
int size)
{
- int slot = size >> rate->rate.cell_log;
- if (slot > 255) {
- cl->xstats.giants++;
- slot = 255;
- }
- return rate->data[slot];
+ long result = qdisc_l2t(rate, size);
+ return result;
}
struct htb_sched {
int rate2quantum; /* quant = rate / rate2quantum */
psched_time_t now; /* cached dequeue time */
struct qdisc_watchdog watchdog;
-#ifdef HTB_RATECM
- struct timer_list rttim; /* rate computer timer */
- int recmp_bucket; /* which hash bucket to recompute next */
-#endif
/* non shaped skbs; let them go directly thru */
struct sk_buff_head direct_queue;
* then finish and return direct queue.
*/
#define HTB_DIRECT (struct htb_class*)-1
-static inline u32 htb_classid(struct htb_class *cl)
-{
- return (cl && cl != HTB_DIRECT) ? cl->classid : TC_H_UNSPEC;
-}
static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
int *qerr)
case TC_ACT_SHOT:
return NULL;
}
-#elif defined(CONFIG_NET_CLS_POLICE)
- if (result == TC_POLICE_SHOT)
- return HTB_DIRECT;
#endif
if ((cl = (void *)res.class) == NULL) {
if (res.classid == sch->handle)
cl->qstats.drops++;
return NET_XMIT_DROP;
} else {
- cl->bstats.packets++;
+ cl->bstats.packets +=
+ skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1;
cl->bstats.bytes += skb->len;
htb_activate(q, cl);
}
sch->q.qlen++;
- sch->bstats.packets++;
+ sch->bstats.packets += skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1;
sch->bstats.bytes += skb->len;
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);
- int ret = NET_XMIT_SUCCESS;
struct htb_class *cl = htb_classify(skb, sch, &ret);
struct sk_buff *tskb;
- if (cl == HTB_DIRECT || !cl) {
+ if (cl == HTB_DIRECT) {
/* enqueue to helper queue */
- if (q->direct_queue.qlen < q->direct_qlen && cl) {
+ if (q->direct_queue.qlen < q->direct_qlen) {
__skb_queue_head(&q->direct_queue, skb);
} else {
__skb_queue_head(&q->direct_queue, skb);
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 (cl->un.leaf.q->ops->requeue(skb, cl->un.leaf.q) !=
NET_XMIT_SUCCESS) {
sch->qstats.drops++;
return NET_XMIT_SUCCESS;
}
-#ifdef HTB_RATECM
-#define RT_GEN(D,R) R+=D-(R/HTB_EWMAC);D=0
-static void htb_rate_timer(unsigned long arg)
-{
- struct Qdisc *sch = (struct Qdisc *)arg;
- struct htb_sched *q = qdisc_priv(sch);
- struct hlist_node *p;
- struct htb_class *cl;
-
-
- /* lock queue so that we can muck with it */
- spin_lock_bh(&sch->dev->queue_lock);
-
- q->rttim.expires = jiffies + HZ;
- add_timer(&q->rttim);
-
- /* scan and recompute one bucket at time */
- if (++q->recmp_bucket >= HTB_HSIZE)
- q->recmp_bucket = 0;
-
- hlist_for_each_entry(cl,p, q->hash + q->recmp_bucket, hlist) {
- RT_GEN(cl->sum_bytes, cl->rate_bytes);
- RT_GEN(cl->sum_packets, cl->rate_packets);
- }
- spin_unlock_bh(&sch->dev->queue_lock);
-}
-#endif
-
/**
* htb_charge_class - charges amount "bytes" to leaf and ancestors
*
* In such case we remove class from event queue first.
*/
static void htb_charge_class(struct htb_sched *q, struct htb_class *cl,
- int level, int bytes)
+ int level, struct sk_buff *skb)
{
+ int bytes = skb->len;
long toks, diff;
enum htb_cmode old_mode;
cl->T = toks
while (cl) {
- diff = PSCHED_TDIFF_SAFE(q->now, cl->t_c, (u32) cl->mbuffer);
+ diff = psched_tdiff_bounded(q->now, cl->t_c, cl->mbuffer);
if (cl->level >= level) {
if (cl->level == level)
cl->xstats.lends++;
if (cl->cmode != HTB_CAN_SEND)
htb_add_to_wait_tree(q, cl, diff);
}
-#ifdef HTB_RATECM
- /* update rate counters */
- cl->sum_bytes += bytes;
- cl->sum_packets++;
-#endif
/* update byte stats except for leaves which are already updated */
if (cl->level) {
cl->bstats.bytes += bytes;
- cl->bstats.packets++;
+ cl->bstats.packets += skb_is_gso(skb)?
+ skb_shinfo(skb)->gso_segs:1;
}
cl = cl->parent;
}
*/
static psched_time_t htb_do_events(struct htb_sched *q, int level)
{
- int i;
-
- for (i = 0; i < 500; i++) {
+ /* don't run for longer than 2 jiffies; 2 is used instead of
+ 1 to simplify things when jiffy is going to be incremented
+ too soon */
+ unsigned long stop_at = jiffies + 2;
+ while (time_before(jiffies, stop_at)) {
struct htb_class *cl;
long diff;
struct rb_node *p = rb_first(&q->wait_pq[level]);
return cl->pq_key;
htb_safe_rb_erase(p, q->wait_pq + level);
- diff = PSCHED_TDIFF_SAFE(q->now, cl->t_c, (u32) cl->mbuffer);
+ diff = psched_tdiff_bounded(q->now, cl->t_c, cl->mbuffer);
htb_change_class_mode(q, cl, &diff);
if (cl->cmode != HTB_CAN_SEND)
htb_add_to_wait_tree(q, cl, diff);
}
- if (net_ratelimit())
- printk(KERN_WARNING "htb: too many events !\n");
- return q->now + PSCHED_TICKS_PER_SEC / 10;
+ /* too much load - let's continue on next jiffie */
+ return q->now + PSCHED_TICKS_PER_SEC / HZ;
}
/* Returns class->node+prio from id-tree where classe's id is >= id. NULL
gives us slightly better performance */
if (!cl->un.leaf.q->q.qlen)
htb_deactivate(q, cl);
- htb_charge_class(q, cl, level, skb->len);
+ htb_charge_class(q, cl, level, skb);
}
return skb;
}
if (!sch->q.qlen)
goto fin;
- PSCHED_GET_TIME(q->now);
+ q->now = psched_get_time();
next_event = q->now + 5 * PSCHED_TICKS_PER_SEC;
q->nwc_hit = 0;
if (q->now >= q->near_ev_cache[level]) {
event = htb_do_events(q, level);
- q->near_ev_cache[level] = event ? event :
- PSCHED_TICKS_PER_SEC;
+ if (!event)
+ event = q->now + PSCHED_TICKS_PER_SEC;
+ q->near_ev_cache[level] = event;
} else
event = q->near_ev_cache[level];
INIT_LIST_HEAD(q->drops + i);
}
-static int htb_init(struct Qdisc *sch, struct rtattr *opt)
+static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = {
+ [TCA_HTB_PARMS] = { .len = sizeof(struct tc_htb_opt) },
+ [TCA_HTB_INIT] = { .len = sizeof(struct tc_htb_glob) },
+ [TCA_HTB_CTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
+ [TCA_HTB_RTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
+};
+
+static int htb_init(struct Qdisc *sch, struct nlattr *opt)
{
struct htb_sched *q = qdisc_priv(sch);
- struct rtattr *tb[TCA_HTB_INIT];
+ struct nlattr *tb[TCA_HTB_INIT + 1];
struct tc_htb_glob *gopt;
+ int err;
int i;
- if (!opt || rtattr_parse_nested(tb, TCA_HTB_INIT, opt) ||
- tb[TCA_HTB_INIT - 1] == NULL ||
- RTA_PAYLOAD(tb[TCA_HTB_INIT - 1]) < sizeof(*gopt)) {
+
+ if (!opt)
+ return -EINVAL;
+
+ err = nla_parse_nested(tb, TCA_HTB_INIT, opt, htb_policy);
+ if (err < 0)
+ return err;
+
+ if (tb[TCA_HTB_INIT] == NULL) {
printk(KERN_ERR "HTB: hey probably you have bad tc tool ?\n");
return -EINVAL;
}
- gopt = RTA_DATA(tb[TCA_HTB_INIT - 1]);
+ gopt = nla_data(tb[TCA_HTB_INIT]);
if (gopt->version != HTB_VER >> 16) {
printk(KERN_ERR
"HTB: need tc/htb version %d (minor is %d), you have %d\n",
if (q->direct_qlen < 2) /* some devices have zero tx_queue_len */
q->direct_qlen = 2;
-#ifdef HTB_RATECM
- init_timer(&q->rttim);
- q->rttim.function = htb_rate_timer;
- q->rttim.data = (unsigned long)sch;
- q->rttim.expires = jiffies + HZ;
- add_timer(&q->rttim);
-#endif
if ((q->rate2quantum = gopt->rate2quantum) < 1)
q->rate2quantum = 1;
q->defcls = gopt->defcls;
static int htb_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct htb_sched *q = qdisc_priv(sch);
- unsigned char *b = skb->tail;
- struct rtattr *rta;
+ struct nlattr *nest;
struct tc_htb_glob gopt;
+
spin_lock_bh(&sch->dev->queue_lock);
- gopt.direct_pkts = q->direct_pkts;
+ gopt.direct_pkts = q->direct_pkts;
gopt.version = HTB_VER;
gopt.rate2quantum = q->rate2quantum;
gopt.defcls = q->defcls;
gopt.debug = 0;
- rta = (struct rtattr *)b;
- RTA_PUT(skb, TCA_OPTIONS, 0, NULL);
- RTA_PUT(skb, TCA_HTB_INIT, sizeof(gopt), &gopt);
- rta->rta_len = skb->tail - b;
+
+ nest = nla_nest_start(skb, TCA_OPTIONS);
+ if (nest == NULL)
+ goto nla_put_failure;
+ NLA_PUT(skb, TCA_HTB_INIT, sizeof(gopt), &gopt);
+ nla_nest_end(skb, nest);
+
spin_unlock_bh(&sch->dev->queue_lock);
return skb->len;
-rtattr_failure:
+
+nla_put_failure:
spin_unlock_bh(&sch->dev->queue_lock);
- skb_trim(skb, skb->tail - skb->data);
+ nla_nest_cancel(skb, nest);
return -1;
}
struct sk_buff *skb, struct tcmsg *tcm)
{
struct htb_class *cl = (struct htb_class *)arg;
- unsigned char *b = skb->tail;
- struct rtattr *rta;
+ struct nlattr *nest;
struct tc_htb_opt opt;
spin_lock_bh(&sch->dev->queue_lock);
if (!cl->level && cl->un.leaf.q)
tcm->tcm_info = cl->un.leaf.q->handle;
- rta = (struct rtattr *)b;
- RTA_PUT(skb, TCA_OPTIONS, 0, NULL);
+ nest = nla_nest_start(skb, TCA_OPTIONS);
+ if (nest == NULL)
+ goto nla_put_failure;
memset(&opt, 0, sizeof(opt));
opt.quantum = cl->un.leaf.quantum;
opt.prio = cl->un.leaf.prio;
opt.level = cl->level;
- RTA_PUT(skb, TCA_HTB_PARMS, sizeof(opt), &opt);
- rta->rta_len = skb->tail - b;
+ NLA_PUT(skb, TCA_HTB_PARMS, sizeof(opt), &opt);
+
+ nla_nest_end(skb, nest);
spin_unlock_bh(&sch->dev->queue_lock);
return skb->len;
-rtattr_failure:
+
+nla_put_failure:
spin_unlock_bh(&sch->dev->queue_lock);
- skb_trim(skb, b - skb->data);
+ nla_nest_cancel(skb, nest);
return -1;
}
{
struct htb_class *cl = (struct htb_class *)arg;
-#ifdef HTB_RATECM
- cl->rate_est.bps = cl->rate_bytes / (HTB_EWMAC * HTB_HSIZE);
- cl->rate_est.pps = cl->rate_packets / (HTB_EWMAC * HTB_HSIZE);
-#endif
-
if (!cl->level && cl->un.leaf.q)
cl->qstats.qlen = cl->un.leaf.q->q.qlen;
cl->xstats.tokens = cl->tokens;
return (unsigned long)cl;
}
-static void htb_destroy_filters(struct tcf_proto **fl)
-{
- struct tcf_proto *tp;
-
- while ((tp = *fl) != NULL) {
- *fl = tp->next;
- tcf_destroy(tp);
- }
-}
-
static inline int htb_parent_last_child(struct htb_class *cl)
{
if (!cl->parent)
parent->un.leaf.prio = parent->prio;
parent->tokens = parent->buffer;
parent->ctokens = parent->cbuffer;
- PSCHED_GET_TIME(parent->t_c);
+ parent->t_c = psched_get_time();
parent->cmode = HTB_CAN_SEND;
}
BUG_TRAP(cl->un.leaf.q);
qdisc_destroy(cl->un.leaf.q);
}
+ gen_kill_estimator(&cl->bstats, &cl->rate_est);
qdisc_put_rtab(cl->rate);
qdisc_put_rtab(cl->ceil);
- htb_destroy_filters(&cl->filter_list);
+ tcf_destroy_chain(cl->filter_list);
while (!list_empty(&cl->children))
htb_destroy_class(sch, list_entry(cl->children.next,
struct htb_sched *q = qdisc_priv(sch);
qdisc_watchdog_cancel(&q->watchdog);
-#ifdef HTB_RATECM
- del_timer_sync(&q->rttim);
-#endif
/* This line used to be after htb_destroy_class call below
and surprisingly it worked in 2.4. But it must precede it
because filter need its target class alive to be able to call
unbind_filter on it (without Oops). */
- htb_destroy_filters(&q->filter_list);
+ tcf_destroy_chain(q->filter_list);
while (!list_empty(&q->root))
htb_destroy_class(sch, list_entry(q->root.next,
}
static int htb_change_class(struct Qdisc *sch, u32 classid,
- u32 parentid, struct rtattr **tca,
+ u32 parentid, struct nlattr **tca,
unsigned long *arg)
{
int err = -EINVAL;
struct htb_sched *q = qdisc_priv(sch);
struct htb_class *cl = (struct htb_class *)*arg, *parent;
- struct rtattr *opt = tca[TCA_OPTIONS - 1];
+ struct nlattr *opt = tca[TCA_OPTIONS];
struct qdisc_rate_table *rtab = NULL, *ctab = NULL;
- struct rtattr *tb[TCA_HTB_RTAB];
+ struct nlattr *tb[TCA_HTB_RTAB + 1];
struct tc_htb_opt *hopt;
/* extract all subattrs from opt attr */
- if (!opt || rtattr_parse_nested(tb, TCA_HTB_RTAB, opt) ||
- tb[TCA_HTB_PARMS - 1] == NULL ||
- RTA_PAYLOAD(tb[TCA_HTB_PARMS - 1]) < sizeof(*hopt))
+ if (!opt)
+ goto failure;
+
+ err = nla_parse_nested(tb, TCA_HTB_RTAB, opt, htb_policy);
+ if (err < 0)
+ goto failure;
+
+ err = -EINVAL;
+ if (tb[TCA_HTB_PARMS] == NULL)
goto failure;
parent = parentid == TC_H_ROOT ? NULL : htb_find(parentid, sch);
- hopt = RTA_DATA(tb[TCA_HTB_PARMS - 1]);
+ hopt = nla_data(tb[TCA_HTB_PARMS]);
- rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB - 1]);
- ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB - 1]);
+ rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]);
+ ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]);
if (!rtab || !ctab)
goto failure;
if (!cl) { /* new class */
struct Qdisc *new_q;
int prio;
+ struct {
+ struct nlattr nla;
+ struct gnet_estimator opt;
+ } est = {
+ .nla = {
+ .nla_len = nla_attr_size(sizeof(est.opt)),
+ .nla_type = TCA_RATE,
+ },
+ .opt = {
+ /* 4s interval, 16s averaging constant */
+ .interval = 2,
+ .ewma_log = 2,
+ },
+ };
/* check for valid classid */
if (!classid || TC_H_MAJ(classid ^ sch->handle)
if ((cl = kzalloc(sizeof(*cl), GFP_KERNEL)) == NULL)
goto failure;
+ gen_new_estimator(&cl->bstats, &cl->rate_est,
+ &sch->dev->queue_lock,
+ tca[TCA_RATE] ? : &est.nla);
cl->refcnt = 1;
INIT_LIST_HEAD(&cl->sibling);
INIT_HLIST_NODE(&cl->hlist);
/* set class to be in HTB_CAN_SEND state */
cl->tokens = hopt->buffer;
cl->ctokens = hopt->cbuffer;
- cl->mbuffer = PSCHED_JIFFIE2US(HZ * 60); /* 1min */
- PSCHED_GET_TIME(cl->t_c);
+ cl->mbuffer = 60 * PSCHED_TICKS_PER_SEC; /* 1min */
+ cl->t_c = psched_get_time();
cl->cmode = HTB_CAN_SEND;
/* attach to the hash list and parent's family */
hlist_add_head(&cl->hlist, q->hash + htb_hash(classid));
list_add_tail(&cl->sibling,
parent ? &parent->children : &q->root);
- } else
+ } else {
+ if (tca[TCA_RATE])
+ gen_replace_estimator(&cl->bstats, &cl->rate_est,
+ &sch->dev->queue_lock,
+ tca[TCA_RATE]);
sch_tree_lock(sch);
+ }
/* it used to be a nasty bug here, we have to check that node
is really leaf before changing cl->un.leaf ! */
}
}
-static struct Qdisc_class_ops htb_class_ops = {
+static const struct Qdisc_class_ops htb_class_ops = {
.graft = htb_graft,
.leaf = htb_leaf,
.qlen_notify = htb_qlen_notify,
.dump_stats = htb_dump_class_stats,
};
-static struct Qdisc_ops htb_qdisc_ops = {
+static struct Qdisc_ops htb_qdisc_ops __read_mostly = {
.next = NULL,
.cl_ops = &htb_class_ops,
.id = "htb",
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff