linux/include/net/neighbour.h

457 lines
12 KiB
C
Raw Normal View History

#ifndef _NET_NEIGHBOUR_H
#define _NET_NEIGHBOUR_H
#include <linux/neighbour.h>
/*
* Generic neighbour manipulation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
* Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
*
* Changes:
*
* Harald Welte: <laforge@gnumonks.org>
* - Add neighbour cache statistics like rtstat
*/
#include <linux/atomic.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/rcupdate.h>
#include <linux/seq_file.h>
#include <linux/bitmap.h>
#include <linux/err.h>
#include <linux/sysctl.h>
#include <linux/workqueue.h>
#include <net/rtnetlink.h>
/*
* NUD stands for "neighbor unreachability detection"
*/
#define NUD_IN_TIMER (NUD_INCOMPLETE|NUD_REACHABLE|NUD_DELAY|NUD_PROBE)
#define NUD_VALID (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE|NUD_PROBE|NUD_STALE|NUD_DELAY)
#define NUD_CONNECTED (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE)
struct neighbour;
enum {
NEIGH_VAR_MCAST_PROBES,
NEIGH_VAR_UCAST_PROBES,
NEIGH_VAR_APP_PROBES,
NEIGH_VAR_RETRANS_TIME,
NEIGH_VAR_BASE_REACHABLE_TIME,
NEIGH_VAR_DELAY_PROBE_TIME,
NEIGH_VAR_GC_STALETIME,
NEIGH_VAR_QUEUE_LEN_BYTES,
NEIGH_VAR_PROXY_QLEN,
NEIGH_VAR_ANYCAST_DELAY,
NEIGH_VAR_PROXY_DELAY,
NEIGH_VAR_LOCKTIME,
#define NEIGH_VAR_DATA_MAX (NEIGH_VAR_LOCKTIME + 1)
/* Following are used as a second way to access one of the above */
NEIGH_VAR_QUEUE_LEN, /* same data as NEIGH_VAR_QUEUE_LEN_BYTES */
NEIGH_VAR_RETRANS_TIME_MS, /* same data as NEIGH_VAR_RETRANS_TIME */
NEIGH_VAR_BASE_REACHABLE_TIME_MS, /* same data as NEIGH_VAR_BASE_REACHABLE_TIME */
/* Following are used by "default" only */
NEIGH_VAR_GC_INTERVAL,
NEIGH_VAR_GC_THRESH1,
NEIGH_VAR_GC_THRESH2,
NEIGH_VAR_GC_THRESH3,
NEIGH_VAR_MAX
};
struct neigh_parms {
#ifdef CONFIG_NET_NS
[NETNS]: Modify the neighbour table code so it handles multiple network namespaces I'm actually surprised at how much was involved. At first glance it appears that the neighbour table data structures are already split by network device so all that should be needed is to modify the user interface commands to filter the set of neighbours by the network namespace of their devices. However a couple things turned up while I was reading through the code. The proxy neighbour table allows entries with no network device, and the neighbour parms are per network device (except for the defaults) so they now need a per network namespace default. So I updated the two structures (which surprised me) with their very own network namespace parameter. Updated the relevant lookup and destroy routines with a network namespace parameter and modified the code that interacts with users to filter out neighbour table entries for devices of other namespaces. I'm a little concerned that we can modify and display the global table configuration and from all network namespaces. But this appears good enough for now. I keep thinking modifying the neighbour table to have per network namespace instances of each table type would should be cleaner. The hash table is already dynamically sized so there are it is not a limiter. The default parameter would be straight forward to take care of. However when I look at the how the network table is built and used I still find some assumptions that there is only a single neighbour table for each type of table in the kernel. The netlink operations, neigh_seq_start, the non-core network users that call neigh_lookup. So while it might be doable it would require more refactoring than my current approach of just doing a little extra filtering in the code. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Daniel Lezcano <dlezcano@fr.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-24 16:13:18 +08:00
struct net *net;
#endif
struct net_device *dev;
struct neigh_parms *next;
int (*neigh_setup)(struct neighbour *);
void (*neigh_cleanup)(struct neighbour *);
struct neigh_table *tbl;
void *sysctl_table;
int dead;
atomic_t refcnt;
struct rcu_head rcu_head;
int reachable_time;
int data[NEIGH_VAR_DATA_MAX];
DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX);
};
static inline void neigh_var_set(struct neigh_parms *p, int index, int val)
{
set_bit(index, p->data_state);
p->data[index] = val;
}
#define NEIGH_VAR(p, attr) ((p)->data[NEIGH_VAR_ ## attr])
/* In ndo_neigh_setup, NEIGH_VAR_INIT should be used.
* In other cases, NEIGH_VAR_SET should be used.
*/
#define NEIGH_VAR_INIT(p, attr, val) (NEIGH_VAR(p, attr) = val)
#define NEIGH_VAR_SET(p, attr, val) neigh_var_set(p, NEIGH_VAR_ ## attr, val)
static inline void neigh_parms_data_state_setall(struct neigh_parms *p)
{
bitmap_fill(p->data_state, NEIGH_VAR_DATA_MAX);
}
static inline void neigh_parms_data_state_cleanall(struct neigh_parms *p)
{
bitmap_zero(p->data_state, NEIGH_VAR_DATA_MAX);
}
struct neigh_statistics {
unsigned long allocs; /* number of allocated neighs */
unsigned long destroys; /* number of destroyed neighs */
unsigned long hash_grows; /* number of hash resizes */
unsigned long res_failed; /* number of failed resolutions */
unsigned long lookups; /* number of lookups */
unsigned long hits; /* number of hits (among lookups) */
unsigned long rcv_probes_mcast; /* number of received mcast ipv6 */
unsigned long rcv_probes_ucast; /* number of received ucast ipv6 */
unsigned long periodic_gc_runs; /* number of periodic GC runs */
unsigned long forced_gc_runs; /* number of forced GC runs */
unsigned long unres_discards; /* number of unresolved drops */
};
#define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field)
struct neighbour {
struct neighbour __rcu *next;
struct neigh_table *tbl;
struct neigh_parms *parms;
unsigned long confirmed;
unsigned long updated;
rwlock_t lock;
atomic_t refcnt;
struct sk_buff_head arp_queue;
neigh: new unresolved queue limits Le mercredi 09 novembre 2011 à 16:21 -0500, David Miller a écrit : > From: David Miller <davem@davemloft.net> > Date: Wed, 09 Nov 2011 16:16:44 -0500 (EST) > > > From: Eric Dumazet <eric.dumazet@gmail.com> > > Date: Wed, 09 Nov 2011 12:14:09 +0100 > > > >> unres_qlen is the number of frames we are able to queue per unresolved > >> neighbour. Its default value (3) was never changed and is responsible > >> for strange drops, especially if IP fragments are used, or multiple > >> sessions start in parallel. Even a single tcp flow can hit this limit. > > ... > > > > Ok, I've applied this, let's see what happens :-) > > Early answer, build fails. > > Please test build this patch with DECNET enabled and resubmit. The > decnet neigh layer still refers to the removed ->queue_len member. > > Thanks. Ouch, this was fixed on one machine yesterday, but not the other one I used this morning, sorry. [PATCH V5 net-next] neigh: new unresolved queue limits unres_qlen is the number of frames we are able to queue per unresolved neighbour. Its default value (3) was never changed and is responsible for strange drops, especially if IP fragments are used, or multiple sessions start in parallel. Even a single tcp flow can hit this limit. $ arp -d 192.168.20.108 ; ping -c 2 -s 8000 192.168.20.108 PING 192.168.20.108 (192.168.20.108) 8000(8028) bytes of data. 8008 bytes from 192.168.20.108: icmp_seq=2 ttl=64 time=0.322 ms Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-09 20:07:14 +08:00
unsigned int arp_queue_len_bytes;
struct timer_list timer;
unsigned long used;
atomic_t probes;
__u8 flags;
__u8 nud_state;
__u8 type;
__u8 dead;
seqlock_t ha_lock;
unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))];
struct hh_cache hh;
int (*output)(struct neighbour *, struct sk_buff *);
const struct neigh_ops *ops;
struct rcu_head rcu;
struct net_device *dev;
u8 primary_key[0];
};
struct neigh_ops {
int family;
void (*solicit)(struct neighbour *, struct sk_buff *);
void (*error_report)(struct neighbour *, struct sk_buff *);
int (*output)(struct neighbour *, struct sk_buff *);
int (*connected_output)(struct neighbour *, struct sk_buff *);
};
struct pneigh_entry {
struct pneigh_entry *next;
#ifdef CONFIG_NET_NS
[NETNS]: Modify the neighbour table code so it handles multiple network namespaces I'm actually surprised at how much was involved. At first glance it appears that the neighbour table data structures are already split by network device so all that should be needed is to modify the user interface commands to filter the set of neighbours by the network namespace of their devices. However a couple things turned up while I was reading through the code. The proxy neighbour table allows entries with no network device, and the neighbour parms are per network device (except for the defaults) so they now need a per network namespace default. So I updated the two structures (which surprised me) with their very own network namespace parameter. Updated the relevant lookup and destroy routines with a network namespace parameter and modified the code that interacts with users to filter out neighbour table entries for devices of other namespaces. I'm a little concerned that we can modify and display the global table configuration and from all network namespaces. But this appears good enough for now. I keep thinking modifying the neighbour table to have per network namespace instances of each table type would should be cleaner. The hash table is already dynamically sized so there are it is not a limiter. The default parameter would be straight forward to take care of. However when I look at the how the network table is built and used I still find some assumptions that there is only a single neighbour table for each type of table in the kernel. The netlink operations, neigh_seq_start, the non-core network users that call neigh_lookup. So while it might be doable it would require more refactoring than my current approach of just doing a little extra filtering in the code. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Daniel Lezcano <dlezcano@fr.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-24 16:13:18 +08:00
struct net *net;
#endif
[NETNS]: Modify the neighbour table code so it handles multiple network namespaces I'm actually surprised at how much was involved. At first glance it appears that the neighbour table data structures are already split by network device so all that should be needed is to modify the user interface commands to filter the set of neighbours by the network namespace of their devices. However a couple things turned up while I was reading through the code. The proxy neighbour table allows entries with no network device, and the neighbour parms are per network device (except for the defaults) so they now need a per network namespace default. So I updated the two structures (which surprised me) with their very own network namespace parameter. Updated the relevant lookup and destroy routines with a network namespace parameter and modified the code that interacts with users to filter out neighbour table entries for devices of other namespaces. I'm a little concerned that we can modify and display the global table configuration and from all network namespaces. But this appears good enough for now. I keep thinking modifying the neighbour table to have per network namespace instances of each table type would should be cleaner. The hash table is already dynamically sized so there are it is not a limiter. The default parameter would be straight forward to take care of. However when I look at the how the network table is built and used I still find some assumptions that there is only a single neighbour table for each type of table in the kernel. The netlink operations, neigh_seq_start, the non-core network users that call neigh_lookup. So while it might be doable it would require more refactoring than my current approach of just doing a little extra filtering in the code. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Daniel Lezcano <dlezcano@fr.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-24 16:13:18 +08:00
struct net_device *dev;
u8 flags;
u8 key[0];
};
/*
* neighbour table manipulation
*/
#define NEIGH_NUM_HASH_RND 4
struct neigh_hash_table {
struct neighbour __rcu **hash_buckets;
unsigned int hash_shift;
__u32 hash_rnd[NEIGH_NUM_HASH_RND];
struct rcu_head rcu;
};
struct neigh_table {
struct neigh_table *next;
int family;
int entry_size;
int key_len;
__u32 (*hash)(const void *pkey,
const struct net_device *dev,
__u32 *hash_rnd);
int (*constructor)(struct neighbour *);
int (*pconstructor)(struct pneigh_entry *);
void (*pdestructor)(struct pneigh_entry *);
void (*proxy_redo)(struct sk_buff *skb);
char *id;
struct neigh_parms parms;
/* HACK. gc_* should follow parms without a gap! */
int gc_interval;
int gc_thresh1;
int gc_thresh2;
int gc_thresh3;
unsigned long last_flush;
struct delayed_work gc_work;
struct timer_list proxy_timer;
struct sk_buff_head proxy_queue;
atomic_t entries;
rwlock_t lock;
unsigned long last_rand;
struct neigh_statistics __percpu *stats;
struct neigh_hash_table __rcu *nht;
struct pneigh_entry **phash_buckets;
};
static inline int neigh_parms_family(struct neigh_parms *p)
{
return p->tbl->family;
}
#define NEIGH_PRIV_ALIGN sizeof(long long)
#define NEIGH_ENTRY_SIZE(size) ALIGN((size), NEIGH_PRIV_ALIGN)
static inline void *neighbour_priv(const struct neighbour *n)
{
return (char *)n + n->tbl->entry_size;
}
/* flags for neigh_update() */
#define NEIGH_UPDATE_F_OVERRIDE 0x00000001
#define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002
#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER 0x00000004
#define NEIGH_UPDATE_F_ISROUTER 0x40000000
#define NEIGH_UPDATE_F_ADMIN 0x80000000
void neigh_table_init(struct neigh_table *tbl);
int neigh_table_clear(struct neigh_table *tbl);
struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
struct net_device *dev);
struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
const void *pkey);
struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
struct net_device *dev, bool want_ref);
static inline struct neighbour *neigh_create(struct neigh_table *tbl,
const void *pkey,
struct net_device *dev)
{
return __neigh_create(tbl, pkey, dev, true);
}
void neigh_destroy(struct neighbour *neigh);
int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb);
int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags);
void __neigh_set_probe_once(struct neighbour *neigh);
void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev);
int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb);
int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb);
int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb);
int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb);
struct neighbour *neigh_event_ns(struct neigh_table *tbl,
u8 *lladdr, void *saddr,
struct net_device *dev);
struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
struct neigh_table *tbl);
void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms);
static inline
struct net *neigh_parms_net(const struct neigh_parms *parms)
{
return read_pnet(&parms->net);
}
unsigned long neigh_rand_reach_time(unsigned long base);
void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
struct sk_buff *skb);
struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net,
const void *key, struct net_device *dev,
int creat);
struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, struct net *net,
const void *key, struct net_device *dev);
int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *key,
struct net_device *dev);
static inline struct net *pneigh_net(const struct pneigh_entry *pneigh)
{
return read_pnet(&pneigh->net);
}
void neigh_app_ns(struct neighbour *n);
void neigh_for_each(struct neigh_table *tbl,
void (*cb)(struct neighbour *, void *), void *cookie);
void __neigh_for_each_release(struct neigh_table *tbl,
int (*cb)(struct neighbour *));
void pneigh_for_each(struct neigh_table *tbl,
void (*cb)(struct pneigh_entry *));
struct neigh_seq_state {
struct seq_net_private p;
struct neigh_table *tbl;
struct neigh_hash_table *nht;
void *(*neigh_sub_iter)(struct neigh_seq_state *state,
struct neighbour *n, loff_t *pos);
unsigned int bucket;
unsigned int flags;
#define NEIGH_SEQ_NEIGH_ONLY 0x00000001
#define NEIGH_SEQ_IS_PNEIGH 0x00000002
#define NEIGH_SEQ_SKIP_NOARP 0x00000004
};
void *neigh_seq_start(struct seq_file *, loff_t *, struct neigh_table *,
unsigned int);
void *neigh_seq_next(struct seq_file *, void *, loff_t *);
void neigh_seq_stop(struct seq_file *, void *);
int neigh_proc_dointvec(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos);
int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos);
int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
proc_handler *proc_handler);
void neigh_sysctl_unregister(struct neigh_parms *p);
static inline void __neigh_parms_put(struct neigh_parms *parms)
{
atomic_dec(&parms->refcnt);
}
static inline struct neigh_parms *neigh_parms_clone(struct neigh_parms *parms)
{
atomic_inc(&parms->refcnt);
return parms;
}
/*
* Neighbour references
*/
static inline void neigh_release(struct neighbour *neigh)
{
if (atomic_dec_and_test(&neigh->refcnt))
neigh_destroy(neigh);
}
static inline struct neighbour * neigh_clone(struct neighbour *neigh)
{
if (neigh)
atomic_inc(&neigh->refcnt);
return neigh;
}
#define neigh_hold(n) atomic_inc(&(n)->refcnt)
static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
{
unsigned long now = jiffies;
if (neigh->used != now)
neigh->used = now;
if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE)))
return __neigh_event_send(neigh, skb);
return 0;
}
#ifdef CONFIG_BRIDGE_NETFILTER
static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
{
unsigned int seq, hh_alen;
do {
seq = read_seqbegin(&hh->hh_lock);
hh_alen = HH_DATA_ALIGN(ETH_HLEN);
memcpy(skb->data - hh_alen, hh->hh_data, ETH_ALEN + hh_alen - ETH_HLEN);
} while (read_seqretry(&hh->hh_lock, seq));
return 0;
}
#endif
static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
{
unsigned int seq;
int hh_len;
do {
seq = read_seqbegin(&hh->hh_lock);
hh_len = hh->hh_len;
if (likely(hh_len <= HH_DATA_MOD)) {
/* this is inlined by gcc */
memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD);
} else {
int hh_alen = HH_DATA_ALIGN(hh_len);
memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
}
} while (read_seqretry(&hh->hh_lock, seq));
skb_push(skb, hh_len);
return dev_queue_xmit(skb);
}
static inline struct neighbour *
__neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev, int creat)
{
struct neighbour *n = neigh_lookup(tbl, pkey, dev);
if (n || !creat)
return n;
n = neigh_create(tbl, pkey, dev);
return IS_ERR(n) ? NULL : n;
}
static inline struct neighbour *
__neigh_lookup_errno(struct neigh_table *tbl, const void *pkey,
struct net_device *dev)
{
struct neighbour *n = neigh_lookup(tbl, pkey, dev);
if (n)
return n;
return neigh_create(tbl, pkey, dev);
}
struct neighbour_cb {
unsigned long sched_next;
unsigned int flags;
};
#define LOCALLY_ENQUEUED 0x1
#define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb)
static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n,
const struct net_device *dev)
{
unsigned int seq;
do {
seq = read_seqbegin(&n->ha_lock);
memcpy(dst, n->ha, dev->addr_len);
} while (read_seqretry(&n->ha_lock, seq));
}
#endif