linux/include/net/neighbour.h

399 lines
11 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/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;
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 08:13:18 +00:00
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 base_reachable_time;
int retrans_time;
int gc_staletime;
int reachable_time;
int delay_probe_time;
int queue_len;
int ucast_probes;
int app_probes;
int mcast_probes;
int anycast_delay;
int proxy_delay;
int proxy_qlen;
int locktime;
};
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;
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 08:13:18 +00:00
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 08:13:18 +00:00
struct net_device *dev;
u8 flags;
u8 key[0];
};
/*
* neighbour table manipulation
*/
struct neigh_hash_table {
struct neighbour __rcu **hash_buckets;
unsigned int hash_shift;
__u32 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 kmem_cache *kmem_cachep;
struct neigh_statistics __percpu *stats;
struct neigh_hash_table __rcu *nht;
struct pneigh_entry **phash_buckets;
};
/* 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
extern void neigh_table_init(struct neigh_table *tbl);
[NEIGH]: Fix IP-over-ATM and ARP interaction. The classical IP over ATM code maintains its own IPv4 <-> <ATM stuff> ARP table, using the standard neighbour-table code. The neigh_table_init function adds this neighbour table to a linked list of all neighbor tables which is used by the functions neigh_delete() neigh_add() and neightbl_set(), all called by the netlink code. Once the ATM neighbour table is added to the list, there are two tables with family == AF_INET there, and ARP entries sent via netlink go into the first table with matching family. This is indeterminate and often wrong. To see the bug, on a kernel with CLIP enabled, create a standard IPv4 ARP entry by pinging an unused address on a local subnet. Then attempt to complete that entry by doing ip neigh replace <ip address> lladdr <some mac address> nud reachable Looking at the ARP tables by using ip neigh show will reveal two ARP entries for the same address. One of these can be found in /proc/net/arp, and the other in /proc/net/atm/arp. This patch adds a new function, neigh_table_init_no_netlink() which does everything the neigh_table_init() does, except add the table to the netlink all-arp-tables chain. In addition neigh_table_init() has a check that all tables on the chain have a distinct address family. The init call in clip.c is changed to call neigh_table_init_no_netlink(). Since ATM ARP tables are rather more complicated than can currently be handled by the available rtattrs in the netlink protocol, no functionality is lost by this patch, and non-ATM ARP manipulation via netlink is rescued. A more complete solution would involve a rtattr for ATM ARP entries and some way for the netlink code to give neigh_add and friends more information than just address family with which to find the correct ARP table. [ I've changed the assertion checking in neigh_table_init() to not use BUG_ON() while holding neigh_tbl_lock. Instead we remember that we found an existing tbl with the same family, and after dropping the lock we'll give a diagnostic kernel log message and a stack dump. -DaveM ] Signed-off-by: Simon Kelley <simon@thekelleys.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-05-12 21:56:08 +00:00
extern void neigh_table_init_no_netlink(struct neigh_table *tbl);
extern int neigh_table_clear(struct neigh_table *tbl);
extern struct neighbour * neigh_lookup(struct neigh_table *tbl,
const void *pkey,
struct net_device *dev);
extern struct neighbour * neigh_lookup_nodev(struct neigh_table *tbl,
[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 08:13:18 +00:00
struct net *net,
const void *pkey);
extern struct neighbour * neigh_create(struct neigh_table *tbl,
const void *pkey,
struct net_device *dev);
extern void neigh_destroy(struct neighbour *neigh);
extern int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb);
extern int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
u32 flags);
extern void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev);
extern int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
extern int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb);
extern int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb);
extern int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb);
extern int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb);
extern struct neighbour *neigh_event_ns(struct neigh_table *tbl,
u8 *lladdr, void *saddr,
struct net_device *dev);
extern struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl);
extern 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);
}
extern unsigned long neigh_rand_reach_time(unsigned long base);
extern void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
struct sk_buff *skb);
[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 08:13:18 +00:00
extern struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev, int creat);
extern struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl,
struct net *net,
const void *key,
struct net_device *dev);
[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 08:13:18 +00:00
extern 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);
}
extern void neigh_app_ns(struct neighbour *n);
extern void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie);
extern void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *));
extern 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
};
extern void *neigh_seq_start(struct seq_file *, loff_t *, struct neigh_table *, unsigned int);
extern void *neigh_seq_next(struct seq_file *, void *, loff_t *);
extern void neigh_seq_stop(struct seq_file *, void *);
extern int neigh_sysctl_register(struct net_device *dev,
struct neigh_parms *p,
char *p_name,
proc_handler *proc_handler);
extern 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 void neigh_confirm(struct neighbour *neigh)
{
if (neigh)
neigh->confirmed = jiffies;
}
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 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(struct hh_cache *hh, struct sk_buff *skb)
{
unsigned seq;
int hh_len;
do {
int hh_alen;
seq = read_seqbegin(&hh->hh_lock);
hh_len = hh->hh_len;
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 int neigh_output(struct neighbour *n, struct sk_buff *skb)
{
struct hh_cache *hh = &n->hh;
if ((n->nud_state & NUD_CONNECTED) && hh->hh_len)
return neigh_hh_output(hh, skb);
else
return n->output(n, 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