linux/include/net/sch_generic.h
Patrick McHardy 6fe1c7a555 net-sched: add dynamically sized qdisc class hash helpers
Currently all qdiscs which allow to create classes uses a fixed sized hash
table with size 16 to hash the classes. This causes a large bottleneck
when using thousands of classes and unbound filters.

Add helpers for dynamically sized class hashes to fix this. The following
patches will convert the qdiscs to use them.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-05 23:21:31 -07:00

376 lines
9.2 KiB
C

#ifndef __NET_SCHED_GENERIC_H
#define __NET_SCHED_GENERIC_H
#include <linux/netdevice.h>
#include <linux/types.h>
#include <linux/rcupdate.h>
#include <linux/module.h>
#include <linux/pkt_sched.h>
#include <linux/pkt_cls.h>
#include <net/gen_stats.h>
#include <net/rtnetlink.h>
struct Qdisc_ops;
struct qdisc_walker;
struct tcf_walker;
struct module;
struct qdisc_rate_table
{
struct tc_ratespec rate;
u32 data[256];
struct qdisc_rate_table *next;
int refcnt;
};
struct Qdisc
{
int (*enqueue)(struct sk_buff *skb, struct Qdisc *dev);
struct sk_buff * (*dequeue)(struct Qdisc *dev);
unsigned flags;
#define TCQ_F_BUILTIN 1
#define TCQ_F_THROTTLED 2
#define TCQ_F_INGRESS 4
int padded;
struct Qdisc_ops *ops;
u32 handle;
u32 parent;
atomic_t refcnt;
struct sk_buff_head q;
struct net_device *dev;
struct list_head list;
struct gnet_stats_basic bstats;
struct gnet_stats_queue qstats;
struct gnet_stats_rate_est rate_est;
spinlock_t *stats_lock;
struct rcu_head q_rcu;
int (*reshape_fail)(struct sk_buff *skb,
struct Qdisc *q);
/* This field is deprecated, but it is still used by CBQ
* and it will live until better solution will be invented.
*/
struct Qdisc *__parent;
};
struct Qdisc_class_ops
{
/* Child qdisc manipulation */
int (*graft)(struct Qdisc *, unsigned long cl,
struct Qdisc *, struct Qdisc **);
struct Qdisc * (*leaf)(struct Qdisc *, unsigned long cl);
void (*qlen_notify)(struct Qdisc *, unsigned long);
/* Class manipulation routines */
unsigned long (*get)(struct Qdisc *, u32 classid);
void (*put)(struct Qdisc *, unsigned long);
int (*change)(struct Qdisc *, u32, u32,
struct nlattr **, unsigned long *);
int (*delete)(struct Qdisc *, unsigned long);
void (*walk)(struct Qdisc *, struct qdisc_walker * arg);
/* Filter manipulation */
struct tcf_proto ** (*tcf_chain)(struct Qdisc *, unsigned long);
unsigned long (*bind_tcf)(struct Qdisc *, unsigned long,
u32 classid);
void (*unbind_tcf)(struct Qdisc *, unsigned long);
/* rtnetlink specific */
int (*dump)(struct Qdisc *, unsigned long,
struct sk_buff *skb, struct tcmsg*);
int (*dump_stats)(struct Qdisc *, unsigned long,
struct gnet_dump *);
};
struct Qdisc_ops
{
struct Qdisc_ops *next;
const struct Qdisc_class_ops *cl_ops;
char id[IFNAMSIZ];
int priv_size;
int (*enqueue)(struct sk_buff *, struct Qdisc *);
struct sk_buff * (*dequeue)(struct Qdisc *);
int (*requeue)(struct sk_buff *, struct Qdisc *);
unsigned int (*drop)(struct Qdisc *);
int (*init)(struct Qdisc *, struct nlattr *arg);
void (*reset)(struct Qdisc *);
void (*destroy)(struct Qdisc *);
int (*change)(struct Qdisc *, struct nlattr *arg);
int (*dump)(struct Qdisc *, struct sk_buff *);
int (*dump_stats)(struct Qdisc *, struct gnet_dump *);
struct module *owner;
};
struct tcf_result
{
unsigned long class;
u32 classid;
};
struct tcf_proto_ops
{
struct tcf_proto_ops *next;
char kind[IFNAMSIZ];
int (*classify)(struct sk_buff*, struct tcf_proto*,
struct tcf_result *);
int (*init)(struct tcf_proto*);
void (*destroy)(struct tcf_proto*);
unsigned long (*get)(struct tcf_proto*, u32 handle);
void (*put)(struct tcf_proto*, unsigned long);
int (*change)(struct tcf_proto*, unsigned long,
u32 handle, struct nlattr **,
unsigned long *);
int (*delete)(struct tcf_proto*, unsigned long);
void (*walk)(struct tcf_proto*, struct tcf_walker *arg);
/* rtnetlink specific */
int (*dump)(struct tcf_proto*, unsigned long,
struct sk_buff *skb, struct tcmsg*);
struct module *owner;
};
struct tcf_proto
{
/* Fast access part */
struct tcf_proto *next;
void *root;
int (*classify)(struct sk_buff*, struct tcf_proto*,
struct tcf_result *);
__be16 protocol;
/* All the rest */
u32 prio;
u32 classid;
struct Qdisc *q;
void *data;
struct tcf_proto_ops *ops;
};
extern void qdisc_lock_tree(struct net_device *dev);
extern void qdisc_unlock_tree(struct net_device *dev);
#define sch_tree_lock(q) qdisc_lock_tree((q)->dev)
#define sch_tree_unlock(q) qdisc_unlock_tree((q)->dev)
#define tcf_tree_lock(tp) qdisc_lock_tree((tp)->q->dev)
#define tcf_tree_unlock(tp) qdisc_unlock_tree((tp)->q->dev)
extern struct Qdisc noop_qdisc;
extern struct Qdisc_ops noop_qdisc_ops;
struct Qdisc_class_common
{
u32 classid;
struct hlist_node hnode;
};
struct Qdisc_class_hash
{
struct hlist_head *hash;
unsigned int hashsize;
unsigned int hashmask;
unsigned int hashelems;
};
static inline unsigned int qdisc_class_hash(u32 id, u32 mask)
{
id ^= id >> 8;
id ^= id >> 4;
return id & mask;
}
static inline struct Qdisc_class_common *
qdisc_class_find(struct Qdisc_class_hash *hash, u32 id)
{
struct Qdisc_class_common *cl;
struct hlist_node *n;
unsigned int h;
h = qdisc_class_hash(id, hash->hashmask);
hlist_for_each_entry(cl, n, &hash->hash[h], hnode) {
if (cl->classid == id)
return cl;
}
return NULL;
}
extern int qdisc_class_hash_init(struct Qdisc_class_hash *);
extern void qdisc_class_hash_insert(struct Qdisc_class_hash *, struct Qdisc_class_common *);
extern void qdisc_class_hash_remove(struct Qdisc_class_hash *, struct Qdisc_class_common *);
extern void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *);
extern void qdisc_class_hash_destroy(struct Qdisc_class_hash *);
extern void dev_init_scheduler(struct net_device *dev);
extern void dev_shutdown(struct net_device *dev);
extern void dev_activate(struct net_device *dev);
extern void dev_deactivate(struct net_device *dev);
extern void qdisc_reset(struct Qdisc *qdisc);
extern void qdisc_destroy(struct Qdisc *qdisc);
extern void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n);
extern struct Qdisc *qdisc_alloc(struct net_device *dev, struct Qdisc_ops *ops);
extern struct Qdisc *qdisc_create_dflt(struct net_device *dev,
struct Qdisc_ops *ops, u32 parentid);
extern void tcf_destroy(struct tcf_proto *tp);
extern void tcf_destroy_chain(struct tcf_proto **fl);
static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff_head *list)
{
__skb_queue_tail(list, skb);
sch->qstats.backlog += skb->len;
sch->bstats.bytes += skb->len;
sch->bstats.packets++;
return NET_XMIT_SUCCESS;
}
static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch)
{
return __qdisc_enqueue_tail(skb, sch, &sch->q);
}
static inline struct sk_buff *__qdisc_dequeue_head(struct Qdisc *sch,
struct sk_buff_head *list)
{
struct sk_buff *skb = __skb_dequeue(list);
if (likely(skb != NULL))
sch->qstats.backlog -= skb->len;
return skb;
}
static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
{
return __qdisc_dequeue_head(sch, &sch->q);
}
static inline struct sk_buff *__qdisc_dequeue_tail(struct Qdisc *sch,
struct sk_buff_head *list)
{
struct sk_buff *skb = __skb_dequeue_tail(list);
if (likely(skb != NULL))
sch->qstats.backlog -= skb->len;
return skb;
}
static inline struct sk_buff *qdisc_dequeue_tail(struct Qdisc *sch)
{
return __qdisc_dequeue_tail(sch, &sch->q);
}
static inline int __qdisc_requeue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff_head *list)
{
__skb_queue_head(list, skb);
sch->qstats.backlog += skb->len;
sch->qstats.requeues++;
return NET_XMIT_SUCCESS;
}
static inline int qdisc_requeue(struct sk_buff *skb, struct Qdisc *sch)
{
return __qdisc_requeue(skb, sch, &sch->q);
}
static inline void __qdisc_reset_queue(struct Qdisc *sch,
struct sk_buff_head *list)
{
/*
* We do not know the backlog in bytes of this list, it
* is up to the caller to correct it
*/
skb_queue_purge(list);
}
static inline void qdisc_reset_queue(struct Qdisc *sch)
{
__qdisc_reset_queue(sch, &sch->q);
sch->qstats.backlog = 0;
}
static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch,
struct sk_buff_head *list)
{
struct sk_buff *skb = __qdisc_dequeue_tail(sch, list);
if (likely(skb != NULL)) {
unsigned int len = skb->len;
kfree_skb(skb);
return len;
}
return 0;
}
static inline unsigned int qdisc_queue_drop(struct Qdisc *sch)
{
return __qdisc_queue_drop(sch, &sch->q);
}
static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch)
{
kfree_skb(skb);
sch->qstats.drops++;
return NET_XMIT_DROP;
}
static inline int qdisc_reshape_fail(struct sk_buff *skb, struct Qdisc *sch)
{
sch->qstats.drops++;
#ifdef CONFIG_NET_CLS_ACT
if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch))
goto drop;
return NET_XMIT_SUCCESS;
drop:
#endif
kfree_skb(skb);
return NET_XMIT_DROP;
}
/* Length to Time (L2T) lookup in a qdisc_rate_table, to determine how
long it will take to send a packet given its size.
*/
static inline u32 qdisc_l2t(struct qdisc_rate_table* rtab, unsigned int pktlen)
{
int slot = pktlen + rtab->rate.cell_align + rtab->rate.overhead;
if (slot < 0)
slot = 0;
slot >>= rtab->rate.cell_log;
if (slot > 255)
return (rtab->data[255]*(slot >> 8) + rtab->data[slot & 0xFF]);
return rtab->data[slot];
}
#ifdef CONFIG_NET_CLS_ACT
static inline struct sk_buff *skb_act_clone(struct sk_buff *skb, gfp_t gfp_mask)
{
struct sk_buff *n = skb_clone(skb, gfp_mask);
if (n) {
n->tc_verd = SET_TC_VERD(n->tc_verd, 0);
n->tc_verd = CLR_TC_OK2MUNGE(n->tc_verd);
n->tc_verd = CLR_TC_MUNGED(n->tc_verd);
}
return n;
}
#endif
#endif