X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fcore%2Fneighbour.c;h=163b4f5b03656952e9db99f7092050463dc11af7;hb=d130691725e9c4a098a59fc64f5ac3dcb1e2aa3b;hp=9e26f38ea6e58fd26e2af3e78be1914050e26341;hpb=26932566a42d46aee7e5d526cb34fba9380cad10;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 9e26f38..163b4f5 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -19,13 +19,13 @@ #include #include #include -#include #include #include #ifdef CONFIG_SYSCTL #include #endif #include +#include #include #include #include @@ -34,6 +34,7 @@ #include #include #include +#include #define NEIGH_DEBUG 1 @@ -55,15 +56,13 @@ #define PNEIGH_HASHMASK 0xF static void neigh_timer_handler(unsigned long arg); -#ifdef CONFIG_ARPD -static void neigh_app_notify(struct neighbour *n); -#endif +static void __neigh_notify(struct neighbour *n, int type, int flags); +static void neigh_update_notify(struct neighbour *neigh); static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev); -void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); static struct neigh_table *neigh_tables; #ifdef CONFIG_PROC_FS -static struct file_operations neigh_stat_seq_fops; +static const struct file_operations neigh_stat_seq_fops; #endif /* @@ -105,6 +104,15 @@ static int neigh_blackhole(struct sk_buff *skb) return -ENETDOWN; } +static void neigh_cleanup_and_release(struct neighbour *neigh) +{ + if (neigh->parms->neigh_cleanup) + neigh->parms->neigh_cleanup(neigh); + + __neigh_notify(neigh, RTM_DELNEIGH, 0); + neigh_release(neigh); +} + /* * It is random distribution in the interval (1/2)*base...(3/2)*base. * It corresponds to default IPv6 settings and is not overridable, @@ -115,6 +123,7 @@ unsigned long neigh_rand_reach_time(unsigned long base) { return (base ? (net_random() % base) + (base >> 1) : 0); } +EXPORT_SYMBOL(neigh_rand_reach_time); static int neigh_forced_gc(struct neigh_table *tbl) @@ -141,7 +150,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) n->dead = 1; shrunk = 1; write_unlock(&n->lock); - neigh_release(n); + neigh_cleanup_and_release(n); continue; } write_unlock(&n->lock); @@ -156,6 +165,16 @@ static int neigh_forced_gc(struct neigh_table *tbl) return shrunk; } +static void neigh_add_timer(struct neighbour *n, unsigned long when) +{ + neigh_hold(n); + if (unlikely(mod_timer(&n->timer, when))) { + printk("NEIGH: BUG, double timer add, state is %x\n", + n->nud_state); + dump_stack(); + } +} + static int neigh_del_timer(struct neighbour *n) { if ((n->nud_state & NUD_IN_TIMER) && @@ -212,7 +231,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) NEIGH_PRINTK2("neigh %p is stray.\n", n); } write_unlock(&n->lock); - neigh_release(n); + neigh_cleanup_and_release(n); } } } @@ -223,6 +242,7 @@ void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev) neigh_flush_dev(tbl, dev); write_unlock_bh(&tbl->lock); } +EXPORT_SYMBOL(neigh_changeaddr); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) { @@ -235,6 +255,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) pneigh_queue_purge(&tbl->proxy_queue); return 0; } +EXPORT_SYMBOL(neigh_ifdown); static struct neighbour *neigh_alloc(struct neigh_table *tbl) { @@ -251,21 +272,17 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl) goto out_entries; } - n = kmem_cache_alloc(tbl->kmem_cachep, GFP_ATOMIC); + n = kmem_cache_zalloc(tbl->kmem_cachep, GFP_ATOMIC); if (!n) goto out_entries; - memset(n, 0, tbl->entry_size); - skb_queue_head_init(&n->arp_queue); rwlock_init(&n->lock); n->updated = n->used = now; n->nud_state = NUD_NONE; n->output = neigh_blackhole; n->parms = neigh_parms_clone(&tbl->parms); - init_timer(&n->timer); - n->timer.function = neigh_timer_handler; - n->timer.data = (unsigned long)n; + setup_timer(&n->timer, neigh_timer_handler, (unsigned long)n); NEIGH_CACHE_STAT_INC(tbl, allocs); n->tbl = tbl; @@ -310,7 +327,7 @@ static void neigh_hash_grow(struct neigh_table *tbl, unsigned long new_entries) NEIGH_CACHE_STAT_INC(tbl, hash_grows); - BUG_ON(new_entries & (new_entries - 1)); + BUG_ON(!is_power_of_2(new_entries)); new_hash = neigh_hash_alloc(new_entries); if (!new_hash) return; @@ -344,11 +361,12 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, { struct neighbour *n; int key_len = tbl->key_len; - u32 hash_val = tbl->hash(pkey, dev); - + u32 hash_val; + NEIGH_CACHE_STAT_INC(tbl, lookups); read_lock_bh(&tbl->lock); + hash_val = tbl->hash(pkey, dev); for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) { if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) { neigh_hold(n); @@ -359,18 +377,22 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, read_unlock_bh(&tbl->lock); return n; } +EXPORT_SYMBOL(neigh_lookup); -struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, const void *pkey) +struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, + const void *pkey) { struct neighbour *n; int key_len = tbl->key_len; - u32 hash_val = tbl->hash(pkey, NULL); + u32 hash_val; NEIGH_CACHE_STAT_INC(tbl, lookups); read_lock_bh(&tbl->lock); + hash_val = tbl->hash(pkey, NULL); for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) { - if (!memcmp(n->primary_key, pkey, key_len)) { + if (!memcmp(n->primary_key, pkey, key_len) && + net_eq(dev_net(n->dev), net)) { neigh_hold(n); NEIGH_CACHE_STAT_INC(tbl, hits); break; @@ -379,6 +401,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, const void *pkey) read_unlock_bh(&tbl->lock); return n; } +EXPORT_SYMBOL(neigh_lookup_nodev); struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev) @@ -447,37 +470,68 @@ out_neigh_release: neigh_release(n); goto out; } +EXPORT_SYMBOL(neigh_create); -struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, const void *pkey, - struct net_device *dev, int creat) +static u32 pneigh_hash(const void *pkey, int key_len) { - struct pneigh_entry *n; - int key_len = tbl->key_len; u32 hash_val = *(u32 *)(pkey + key_len - 4); - hash_val ^= (hash_val >> 16); hash_val ^= hash_val >> 8; hash_val ^= hash_val >> 4; hash_val &= PNEIGH_HASHMASK; + return hash_val; +} - read_lock_bh(&tbl->lock); - - for (n = tbl->phash_buckets[hash_val]; n; n = n->next) { +static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n, + struct net *net, + const void *pkey, + int key_len, + struct net_device *dev) +{ + while (n) { if (!memcmp(n->key, pkey, key_len) && - (n->dev == dev || !n->dev)) { - read_unlock_bh(&tbl->lock); - goto out; - } + net_eq(pneigh_net(n), net) && + (n->dev == dev || !n->dev)) + return n; + n = n->next; } + return NULL; +} + +struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, + struct net *net, const void *pkey, struct net_device *dev) +{ + int key_len = tbl->key_len; + u32 hash_val = pneigh_hash(pkey, key_len); + + return __pneigh_lookup_1(tbl->phash_buckets[hash_val], + net, pkey, key_len, dev); +} +EXPORT_SYMBOL_GPL(__pneigh_lookup); + +struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, + struct net *net, const void *pkey, + struct net_device *dev, int creat) +{ + struct pneigh_entry *n; + int key_len = tbl->key_len; + u32 hash_val = pneigh_hash(pkey, key_len); + + read_lock_bh(&tbl->lock); + n = __pneigh_lookup_1(tbl->phash_buckets[hash_val], + net, pkey, key_len, dev); read_unlock_bh(&tbl->lock); - n = NULL; - if (!creat) + + if (n || !creat) goto out; + ASSERT_RTNL(); + n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL); if (!n) goto out; + write_pnet(&n->net, hold_net(net)); memcpy(n->key, pkey, key_len); n->dev = dev; if (dev) @@ -486,6 +540,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, const void *pkey, if (tbl->pconstructor && tbl->pconstructor(n)) { if (dev) dev_put(dev); + release_net(net); kfree(n); n = NULL; goto out; @@ -498,30 +553,28 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, const void *pkey, out: return n; } +EXPORT_SYMBOL(pneigh_lookup); -int pneigh_delete(struct neigh_table *tbl, const void *pkey, +int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev) { struct pneigh_entry *n, **np; int key_len = tbl->key_len; - u32 hash_val = *(u32 *)(pkey + key_len - 4); - - hash_val ^= (hash_val >> 16); - hash_val ^= hash_val >> 8; - hash_val ^= hash_val >> 4; - hash_val &= PNEIGH_HASHMASK; + u32 hash_val = pneigh_hash(pkey, key_len); write_lock_bh(&tbl->lock); for (np = &tbl->phash_buckets[hash_val]; (n = *np) != NULL; np = &n->next) { - if (!memcmp(n->key, pkey, key_len) && n->dev == dev) { + if (!memcmp(n->key, pkey, key_len) && n->dev == dev && + net_eq(pneigh_net(n), net)) { *np = n->next; write_unlock_bh(&tbl->lock); if (tbl->pdestructor) tbl->pdestructor(n); if (n->dev) dev_put(n->dev); + release_net(pneigh_net(n)); kfree(n); return 0; } @@ -544,6 +597,7 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) tbl->pdestructor(n); if (n->dev) dev_put(n->dev); + release_net(pneigh_net(n)); kfree(n); continue; } @@ -553,6 +607,13 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) return -ENOENT; } +static void neigh_parms_destroy(struct neigh_parms *parms); + +static inline void neigh_parms_put(struct neigh_parms *parms) +{ + if (atomic_dec_and_test(&parms->refcnt)) + neigh_parms_destroy(parms); +} /* * neighbour must already be out of the table; @@ -585,9 +646,6 @@ void neigh_destroy(struct neighbour *neigh) kfree(hh); } - if (neigh->parms->neigh_destructor) - (neigh->parms->neigh_destructor)(neigh); - skb_queue_purge(&neigh->arp_queue); dev_put(neigh->dev); @@ -598,6 +656,7 @@ void neigh_destroy(struct neighbour *neigh) atomic_dec(&neigh->tbl->entries); kmem_cache_free(neigh->tbl->kmem_cachep, neigh); } +EXPORT_SYMBOL(neigh_destroy); /* Neighbour state is suspicious; disable fast path. @@ -678,7 +737,7 @@ static void neigh_periodic_timer(unsigned long arg) *np = n->next; n->dead = 1; write_unlock(&n->lock); - neigh_release(n); + neigh_cleanup_and_release(n); continue; } write_unlock(&n->lock); @@ -687,16 +746,19 @@ next_elt: np = &n->next; } - /* Cycle through all hash buckets every base_reachable_time/2 ticks. - * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 - * base_reachable_time. + /* Cycle through all hash buckets every base_reachable_time/2 ticks. + * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 + * base_reachable_time. */ expire = tbl->parms.base_reachable_time >> 1; expire /= (tbl->hash_mask + 1); if (!expire) expire = 1; - mod_timer(&tbl->gc_timer, now + expire); + if (expire>HZ) + mod_timer(&tbl->gc_timer, round_jiffies(now + expire)); + else + mod_timer(&tbl->gc_timer, now + expire); write_unlock(&tbl->lock); } @@ -709,13 +771,26 @@ static __inline__ int neigh_max_probes(struct neighbour *n) p->ucast_probes + p->app_probes + p->mcast_probes); } -static inline void neigh_add_timer(struct neighbour *n, unsigned long when) +static void neigh_invalidate(struct neighbour *neigh) { - if (unlikely(mod_timer(&n->timer, when))) { - printk("NEIGH: BUG, double timer add, state is %x\n", - n->nud_state); - dump_stack(); + struct sk_buff *skb; + + NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); + NEIGH_PRINTK2("neigh %p is failed.\n", neigh); + neigh->updated = jiffies; + + /* It is very thin place. report_unreachable is very complicated + routine. Particularly, it can hit the same neighbour entry! + + So that, we try to be accurate and avoid dead loop. --ANK + */ + while (neigh->nud_state == NUD_FAILED && + (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { + write_unlock(&neigh->lock); + neigh->ops->error_report(neigh, skb); + write_lock(&neigh->lock); } + skb_queue_purge(&neigh->arp_queue); } /* Called when a timer expires for a neighbour entry. */ @@ -741,7 +816,7 @@ static void neigh_timer_handler(unsigned long arg) } if (state & NUD_REACHABLE) { - if (time_before_eq(now, + if (time_before_eq(now, neigh->confirmed + neigh->parms->reachable_time)) { NEIGH_PRINTK2("neigh %p is still alive.\n", neigh); next = neigh->confirmed + neigh->parms->reachable_time; @@ -760,7 +835,7 @@ static void neigh_timer_handler(unsigned long arg) notify = 1; } } else if (state & NUD_DELAY) { - if (time_before_eq(now, + if (time_before_eq(now, neigh->confirmed + neigh->parms->delay_probe_time)) { NEIGH_PRINTK2("neigh %p is now reachable.\n", neigh); neigh->nud_state = NUD_REACHABLE; @@ -782,26 +857,9 @@ static void neigh_timer_handler(unsigned long arg) if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && atomic_read(&neigh->probes) >= neigh_max_probes(neigh)) { - struct sk_buff *skb; - neigh->nud_state = NUD_FAILED; - neigh->updated = jiffies; notify = 1; - NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); - NEIGH_PRINTK2("neigh %p is failed.\n", neigh); - - /* It is very thin place. report_unreachable is very complicated - routine. Particularly, it can hit the same neighbour entry! - - So that, we try to be accurate and avoid dead loop. --ANK - */ - while (neigh->nud_state == NUD_FAILED && - (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { - write_unlock(&neigh->lock); - neigh->ops->error_report(neigh, skb); - write_lock(&neigh->lock); - } - skb_queue_purge(&neigh->arp_queue); + neigh_invalidate(neigh); } if (neigh->nud_state & NUD_IN_TIMER) { @@ -814,23 +872,19 @@ static void neigh_timer_handler(unsigned long arg) struct sk_buff *skb = skb_peek(&neigh->arp_queue); /* keep skb alive even if arp_queue overflows */ if (skb) - skb_get(skb); + skb = skb_copy(skb, GFP_ATOMIC); write_unlock(&neigh->lock); neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); - if (skb) - kfree_skb(skb); + kfree_skb(skb); } else { out: write_unlock(&neigh->lock); } + if (notify) - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); + neigh_update_notify(neigh); -#ifdef CONFIG_ARPD - if (notify && neigh->parms->app_probes) - neigh_app_notify(neigh); -#endif neigh_release(neigh); } @@ -846,26 +900,23 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) goto out_unlock_bh; now = jiffies; - + if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) { if (neigh->parms->mcast_probes + neigh->parms->app_probes) { atomic_set(&neigh->probes, neigh->parms->ucast_probes); neigh->nud_state = NUD_INCOMPLETE; neigh->updated = jiffies; - neigh_hold(neigh); neigh_add_timer(neigh, now + 1); } else { neigh->nud_state = NUD_FAILED; neigh->updated = jiffies; write_unlock_bh(&neigh->lock); - if (skb) - kfree_skb(skb); + kfree_skb(skb); return 1; } } else if (neigh->nud_state & NUD_STALE) { NEIGH_PRINTK2("neigh %p is delayed.\n", neigh); - neigh_hold(neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_add_timer(neigh, @@ -877,9 +928,9 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) if (skb_queue_len(&neigh->arp_queue) >= neigh->parms->queue_len) { struct sk_buff *buff; - buff = neigh->arp_queue.next; - __skb_unlink(buff, &neigh->arp_queue); + buff = __skb_dequeue(&neigh->arp_queue); kfree_skb(buff); + NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards); } __skb_queue_tail(&neigh->arp_queue, skb); } @@ -889,12 +940,13 @@ out_unlock_bh: write_unlock_bh(&neigh->lock); return rc; } +EXPORT_SYMBOL(__neigh_event_send); static void neigh_update_hhs(struct neighbour *neigh) { struct hh_cache *hh; - void (*update)(struct hh_cache*, struct net_device*, unsigned char *) = - neigh->dev->header_cache_update; + void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *) + = neigh->dev->header_ops->cache_update; if (update) { for (hh = neigh->hh; hh; hh = hh->hh_next) { @@ -914,13 +966,13 @@ static void neigh_update_hhs(struct neighbour *neigh) NEIGH_UPDATE_F_OVERRIDE allows to override existing lladdr, if it is different. NEIGH_UPDATE_F_WEAK_OVERRIDE will suspect existing "connected" - lladdr instead of overriding it + lladdr instead of overriding it if it is different. It also allows to retain current state if lladdr is unchanged. NEIGH_UPDATE_F_ADMIN means that the change is administrative. - NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing + NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing NTF_ROUTER flag. NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as a router. @@ -943,7 +995,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, old = neigh->nud_state; err = -EPERM; - if (!(flags & NEIGH_UPDATE_F_ADMIN) && + if (!(flags & NEIGH_UPDATE_F_ADMIN) && (old & (NUD_NOARP | NUD_PERMANENT))) goto out; @@ -954,6 +1006,11 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh->nud_state = new; err = 0; notify = old & NUD_VALID; + if ((old & (NUD_INCOMPLETE | NUD_PROBE)) && + (new & NUD_FAILED)) { + neigh_invalidate(neigh); + notify = 1; + } goto out; } @@ -967,7 +1024,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, - compare new & old - if they are different, check override flag */ - if ((old & NUD_VALID) && + if ((old & NUD_VALID) && !memcmp(lladdr, neigh->ha, dev->addr_len)) lladdr = neigh->ha; } else { @@ -1009,13 +1066,11 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, if (new != old) { neigh_del_timer(neigh); - if (new & NUD_IN_TIMER) { - neigh_hold(neigh); - neigh_add_timer(neigh, (jiffies + - ((new & NUD_REACHABLE) ? + if (new & NUD_IN_TIMER) + neigh_add_timer(neigh, (jiffies + + ((new & NUD_REACHABLE) ? neigh->parms->reachable_time : 0))); - } neigh->nud_state = new; } @@ -1043,8 +1098,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, struct neighbour *n1 = neigh; write_unlock_bh(&neigh->lock); /* On shaper/eql skb->dst->neighbour != neigh :( */ - if (skb->dst && skb->dst->neighbour) - n1 = skb->dst->neighbour; + if (skb_dst(skb) && skb_dst(skb)->neighbour) + n1 = skb_dst(skb)->neighbour; n1->output(skb); write_lock_bh(&neigh->lock); } @@ -1059,13 +1114,11 @@ out: write_unlock_bh(&neigh->lock); if (notify) - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); -#ifdef CONFIG_ARPD - if (notify && neigh->parms->app_probes) - neigh_app_notify(neigh); -#endif + neigh_update_notify(neigh); + return err; } +EXPORT_SYMBOL(neigh_update); struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, @@ -1074,10 +1127,11 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl, struct neighbour *neigh = __neigh_lookup(tbl, saddr, dev, lladdr || !dev->addr_len); if (neigh) - neigh_update(neigh, lladdr, NUD_STALE, + neigh_update(neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_OVERRIDE); return neigh; } +EXPORT_SYMBOL(neigh_event_ns); static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst, __be16 protocol) @@ -1094,7 +1148,8 @@ static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst, hh->hh_type = protocol; atomic_set(&hh->hh_refcnt, 0); hh->hh_next = NULL; - if (dev->hard_header_cache(n, hh)) { + + if (dev->header_ops->cache(n, hh)) { kfree(hh); hh = NULL; } else { @@ -1122,44 +1177,44 @@ int neigh_compat_output(struct sk_buff *skb) { struct net_device *dev = skb->dev; - __skb_pull(skb, skb->nh.raw - skb->data); + __skb_pull(skb, skb_network_offset(skb)); - if (dev->hard_header && - dev->hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL, - skb->len) < 0 && - dev->rebuild_header(skb)) + if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL, + skb->len) < 0 && + dev->header_ops->rebuild(skb)) return 0; return dev_queue_xmit(skb); } +EXPORT_SYMBOL(neigh_compat_output); /* Slow and careful. */ int neigh_resolve_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh; int rc = 0; if (!dst || !(neigh = dst->neighbour)) goto discard; - __skb_pull(skb, skb->nh.raw - skb->data); + __skb_pull(skb, skb_network_offset(skb)); if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; - if (dev->hard_header_cache && !dst->hh) { + if (dev->header_ops->cache && !dst->hh) { write_lock_bh(&neigh->lock); if (!dst->hh) neigh_hh_init(neigh, dst, dst->ops->protocol); - err = dev->hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, NULL, skb->len); + err = dev_hard_header(skb, dev, ntohs(skb->protocol), + neigh->ha, NULL, skb->len); write_unlock_bh(&neigh->lock); } else { read_lock_bh(&neigh->lock); - err = dev->hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, NULL, skb->len); + err = dev_hard_header(skb, dev, ntohs(skb->protocol), + neigh->ha, NULL, skb->len); read_unlock_bh(&neigh->lock); } if (err >= 0) @@ -1177,21 +1232,22 @@ out_kfree_skb: kfree_skb(skb); goto out; } +EXPORT_SYMBOL(neigh_resolve_output); /* As fast as possible without hh cache */ int neigh_connected_output(struct sk_buff *skb) { int err; - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; - __skb_pull(skb, skb->nh.raw - skb->data); + __skb_pull(skb, skb_network_offset(skb)); read_lock_bh(&neigh->lock); - err = dev->hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, NULL, skb->len); + err = dev_hard_header(skb, dev, ntohs(skb->protocol), + neigh->ha, NULL, skb->len); read_unlock_bh(&neigh->lock); if (err >= 0) err = neigh->ops->queue_xmit(skb); @@ -1201,30 +1257,27 @@ int neigh_connected_output(struct sk_buff *skb) } return err; } +EXPORT_SYMBOL(neigh_connected_output); static void neigh_proxy_process(unsigned long arg) { struct neigh_table *tbl = (struct neigh_table *)arg; long sched_next = 0; unsigned long now = jiffies; - struct sk_buff *skb; + struct sk_buff *skb, *n; spin_lock(&tbl->proxy_queue.lock); - skb = tbl->proxy_queue.next; + skb_queue_walk_safe(&tbl->proxy_queue, skb, n) { + long tdif = NEIGH_CB(skb)->sched_next - now; - while (skb != (struct sk_buff *)&tbl->proxy_queue) { - struct sk_buff *back = skb; - long tdif = NEIGH_CB(back)->sched_next - now; - - skb = skb->next; if (tdif <= 0) { - struct net_device *dev = back->dev; - __skb_unlink(back, &tbl->proxy_queue); + struct net_device *dev = skb->dev; + __skb_unlink(skb, &tbl->proxy_queue); if (tbl->proxy_redo && netif_running(dev)) - tbl->proxy_redo(back); + tbl->proxy_redo(skb); else - kfree_skb(back); + kfree_skb(skb); dev_put(dev); } else if (!sched_next || tdif < sched_next) @@ -1255,35 +1308,54 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, if (time_before(tbl->proxy_timer.expires, sched_next)) sched_next = tbl->proxy_timer.expires; } - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); dev_hold(skb->dev); __skb_queue_tail(&tbl->proxy_queue, skb); mod_timer(&tbl->proxy_timer, sched_next); spin_unlock(&tbl->proxy_queue.lock); } +EXPORT_SYMBOL(pneigh_enqueue); + +static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, + struct net *net, int ifindex) +{ + struct neigh_parms *p; + + for (p = &tbl->parms; p; p = p->next) { + if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) || + (!p->dev && !ifindex)) + return p; + } + return NULL; +} struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl) { - struct neigh_parms *p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL); + struct neigh_parms *p, *ref; + struct net *net = dev_net(dev); + const struct net_device_ops *ops = dev->netdev_ops; + + ref = lookup_neigh_params(tbl, net, 0); + if (!ref) + return NULL; + p = kmemdup(ref, sizeof(*p), GFP_KERNEL); if (p) { p->tbl = tbl; atomic_set(&p->refcnt, 1); - INIT_RCU_HEAD(&p->rcu_head); p->reachable_time = neigh_rand_reach_time(p->base_reachable_time); - if (dev) { - if (dev->neigh_setup && dev->neigh_setup(dev, p)) { - kfree(p); - return NULL; - } - dev_hold(dev); - p->dev = dev; + if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { + kfree(p); + return NULL; } + + dev_hold(dev); + p->dev = dev; + write_pnet(&p->net, hold_net(net)); p->sysctl_table = NULL; write_lock_bh(&tbl->lock); p->next = tbl->parms.next; @@ -1292,6 +1364,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, } return p; } +EXPORT_SYMBOL(neigh_parms_alloc); static void neigh_rcu_free_parms(struct rcu_head *head) { @@ -1322,19 +1395,23 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) write_unlock_bh(&tbl->lock); NEIGH_PRINTK1("neigh_parms_release: not found\n"); } +EXPORT_SYMBOL(neigh_parms_release); -void neigh_parms_destroy(struct neigh_parms *parms) +static void neigh_parms_destroy(struct neigh_parms *parms) { + release_net(neigh_parms_net(parms)); kfree(parms); } +static struct lock_class_key neigh_table_proxy_queue_class; + void neigh_table_init_no_netlink(struct neigh_table *tbl) { unsigned long now = jiffies; unsigned long phsize; + write_pnet(&tbl->parms.net, &init_net); atomic_set(&tbl->parms.refcnt, 1); - INIT_RCU_HEAD(&tbl->parms.rcu_head); tbl->parms.reachable_time = neigh_rand_reach_time(tbl->parms.base_reachable_time); @@ -1342,17 +1419,15 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) tbl->kmem_cachep = kmem_cache_create(tbl->id, tbl->entry_size, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, - NULL, NULL); + NULL); tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) panic("cannot create neighbour cache statistics"); - + #ifdef CONFIG_PROC_FS - tbl->pde = create_proc_entry(tbl->id, 0, proc_net_stat); - if (!tbl->pde) + if (!proc_create_data(tbl->id, 0, init_net.proc_net_stat, + &neigh_stat_seq_fops, tbl)) panic("cannot create neighbour proc dir entry"); - tbl->pde->proc_fops = &neigh_stat_seq_fops; - tbl->pde->data = tbl; #endif tbl->hash_mask = 1; @@ -1367,20 +1442,18 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); rwlock_init(&tbl->lock); - init_timer(&tbl->gc_timer); - tbl->gc_timer.data = (unsigned long)tbl; - tbl->gc_timer.function = neigh_periodic_timer; + setup_timer(&tbl->gc_timer, neigh_periodic_timer, (unsigned long)tbl); tbl->gc_timer.expires = now + 1; add_timer(&tbl->gc_timer); - init_timer(&tbl->proxy_timer); - tbl->proxy_timer.data = (unsigned long)tbl; - tbl->proxy_timer.function = neigh_proxy_process; - skb_queue_head_init(&tbl->proxy_queue); + setup_timer(&tbl->proxy_timer, neigh_proxy_process, (unsigned long)tbl); + skb_queue_head_init_class(&tbl->proxy_queue, + &neigh_table_proxy_queue_class); tbl->last_flush = now; tbl->last_rand = now + tbl->parms.reachable_time * 20; } +EXPORT_SYMBOL(neigh_table_init_no_netlink); void neigh_table_init(struct neigh_table *tbl) { @@ -1402,6 +1475,7 @@ void neigh_table_init(struct neigh_table *tbl) dump_stack(); } } +EXPORT_SYMBOL(neigh_table_init); int neigh_table_clear(struct neigh_table *tbl) { @@ -1429,14 +1503,21 @@ int neigh_table_clear(struct neigh_table *tbl) kfree(tbl->phash_buckets); tbl->phash_buckets = NULL; + remove_proc_entry(tbl->id, init_net.proc_net_stat); + free_percpu(tbl->stats); tbl->stats = NULL; + kmem_cache_destroy(tbl->kmem_cachep); + tbl->kmem_cachep = NULL; + return 0; } +EXPORT_SYMBOL(neigh_table_clear); -int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { + struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *dst_attr; struct neigh_table *tbl; @@ -1452,7 +1533,7 @@ int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex) { - dev = dev_get_by_index(ndm->ndm_ifindex); + dev = dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { err = -ENODEV; goto out; @@ -1471,7 +1552,7 @@ int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) goto out_dev_put; if (ndm->ndm_flags & NTF_PROXY) { - err = pneigh_delete(tbl, nla_data(dst_attr), dev); + err = pneigh_delete(tbl, net, nla_data(dst_attr), dev); goto out_dev_put; } @@ -1500,8 +1581,9 @@ out: return err; } -int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { + struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; struct neigh_table *tbl; @@ -1518,7 +1600,7 @@ int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex) { - dev = dev_get_by_index(ndm->ndm_ifindex); + dev = dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { err = -ENODEV; goto out; @@ -1547,7 +1629,7 @@ int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct pneigh_entry *pn; err = -ENOBUFS; - pn = pneigh_lookup(tbl, dst, dev, 1); + pn = pneigh_lookup(tbl, net, dst, dev, 1); if (pn) { pn->flags = ndm->ndm_flags; err = 0; @@ -1564,7 +1646,7 @@ int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) err = -ENOENT; goto out_dev_put; } - + neigh = __neigh_lookup_errno(tbl, dst, dev); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); @@ -1581,7 +1663,11 @@ int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) flags &= ~NEIGH_UPDATE_F_OVERRIDE; } - err = neigh_update(neigh, lladdr, ndm->ndm_state, flags); + if (ndm->ndm_flags & NTF_USE) { + neigh_event_send(neigh, NULL); + err = 0; + } else + err = neigh_update(neigh, lladdr, ndm->ndm_state, flags); neigh_release(neigh); goto out_dev_put; } @@ -1626,7 +1712,8 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) return nla_nest_end(skb, nest); nla_put_failure: - return nla_nest_cancel(skb, nest); + nla_nest_cancel(skb, nest); + return -EMSGSIZE; } static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, @@ -1741,21 +1828,8 @@ errout: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } - -static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, - int ifindex) -{ - struct neigh_parms *p; - - for (p = &tbl->parms; p; p = p->next) - if ((p->dev && p->dev->ifindex == ifindex) || - (!p->dev && !ifindex)) - return p; - - return NULL; -} -static struct nla_policy nl_neightbl_policy[NDTA_MAX+1] __read_mostly = { +static const struct nla_policy nl_neightbl_policy[NDTA_MAX+1] = { [NDTA_NAME] = { .type = NLA_STRING }, [NDTA_THRESH1] = { .type = NLA_U32 }, [NDTA_THRESH2] = { .type = NLA_U32 }, @@ -1764,7 +1838,7 @@ static struct nla_policy nl_neightbl_policy[NDTA_MAX+1] __read_mostly = { [NDTA_PARMS] = { .type = NLA_NESTED }, }; -static struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] __read_mostly = { +static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { [NDTPA_IFINDEX] = { .type = NLA_U32 }, [NDTPA_QUEUE_LEN] = { .type = NLA_U32 }, [NDTPA_PROXY_QLEN] = { .type = NLA_U32 }, @@ -1780,8 +1854,9 @@ static struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] __read_mostly = { [NDTPA_LOCKTIME] = { .type = NLA_U64 }, }; -int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { + struct net *net = sock_net(skb->sk); struct neigh_table *tbl; struct ndtmsg *ndtmsg; struct nlattr *tb[NDTA_MAX+1]; @@ -1812,7 +1887,7 @@ int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) goto errout_locked; } - /* + /* * We acquire tbl->lock to be nice to the periodic timers and * make sure they always see a consistent set of values. */ @@ -1831,7 +1906,7 @@ int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (tbp[NDTPA_IFINDEX]) ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]); - p = lookup_neigh_params(tbl, ifindex); + p = lookup_neigh_params(tbl, net, ifindex); if (p == NULL) { err = -ENOENT; goto errout_tbl_lock; @@ -1904,8 +1979,9 @@ errout: return err; } -int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) +static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); int family, tidx, nidx = 0; int tbl_skip = cb->args[0]; int neigh_skip = cb->args[1]; @@ -1925,16 +2001,21 @@ int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) NLM_F_MULTI) <= 0) break; - for (nidx = 0, p = tbl->parms.next; p; p = p->next, nidx++) { - if (nidx < neigh_skip) + for (nidx = 0, p = tbl->parms.next; p; p = p->next) { + if (!net_eq(neigh_parms_net(p), net)) continue; + if (nidx < neigh_skip) + goto next; + if (neightbl_fill_param_info(skb, tbl, p, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) <= 0) goto out; + next: + nidx++; } neigh_skip = 0; @@ -1977,9 +2058,9 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, goto nla_put_failure; } - ci.ndm_used = now - neigh->used; - ci.ndm_confirmed = now - neigh->confirmed; - ci.ndm_updated = now - neigh->updated; + ci.ndm_used = jiffies_to_clock_t(now - neigh->used); + ci.ndm_confirmed = jiffies_to_clock_t(now - neigh->confirmed); + ci.ndm_updated = jiffies_to_clock_t(now - neigh->updated); ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1; read_unlock_bh(&neigh->lock); @@ -1993,10 +2074,16 @@ nla_put_failure: return -EMSGSIZE; } +static void neigh_update_notify(struct neighbour *neigh) +{ + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); + __neigh_notify(neigh, RTM_NEWNEIGH, 0); +} static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb) { + struct net * net = sock_net(skb->sk); struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; @@ -2007,9 +2094,11 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, continue; if (h > s_h) s_idx = 0; - for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next, idx++) { - if (idx < s_idx) + for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) { + if (dev_net(n->dev) != net) continue; + if (idx < s_idx) + goto next; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, @@ -2018,6 +2107,8 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, rc = -1; goto out; } + next: + idx++; } } read_unlock_bh(&tbl->lock); @@ -2028,7 +2119,7 @@ out: return rc; } -int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) +static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { struct neigh_table *tbl; int t, family, s_t; @@ -2089,7 +2180,7 @@ void __neigh_for_each_release(struct neigh_table *tbl, np = &n->next; write_unlock(&n->lock); if (release) - neigh_release(n); + neigh_cleanup_and_release(n); } } } @@ -2100,6 +2191,7 @@ EXPORT_SYMBOL(__neigh_for_each_release); static struct neighbour *neigh_get_first(struct seq_file *seq) { struct neigh_seq_state *state = seq->private; + struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; struct neighbour *n = NULL; int bucket = state->bucket; @@ -2109,6 +2201,8 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) n = tbl->hash_buckets[bucket]; while (n) { + if (!net_eq(dev_net(n->dev), net)) + goto next; if (state->neigh_sub_iter) { loff_t fakep = 0; void *v; @@ -2138,6 +2232,7 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, loff_t *pos) { struct neigh_seq_state *state = seq->private; + struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; if (state->neigh_sub_iter) { @@ -2149,6 +2244,8 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, while (1) { while (n) { + if (!net_eq(dev_net(n->dev), net)) + goto next; if (state->neigh_sub_iter) { void *v = state->neigh_sub_iter(state, n, pos); if (v) @@ -2183,6 +2280,7 @@ static struct neighbour *neigh_get_idx(struct seq_file *seq, loff_t *pos) struct neighbour *n = neigh_get_first(seq); if (n) { + --(*pos); while (*pos) { n = neigh_get_next(seq, n, pos); if (!n) @@ -2195,6 +2293,7 @@ static struct neighbour *neigh_get_idx(struct seq_file *seq, loff_t *pos) static struct pneigh_entry *pneigh_get_first(struct seq_file *seq) { struct neigh_seq_state *state = seq->private; + struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; struct pneigh_entry *pn = NULL; int bucket = state->bucket; @@ -2202,6 +2301,8 @@ static struct pneigh_entry *pneigh_get_first(struct seq_file *seq) state->flags |= NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) { pn = tbl->phash_buckets[bucket]; + while (pn && !net_eq(pneigh_net(pn), net)) + pn = pn->next; if (pn) break; } @@ -2215,6 +2316,7 @@ static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, loff_t *pos) { struct neigh_seq_state *state = seq->private; + struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; pn = pn->next; @@ -2222,6 +2324,8 @@ static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, if (++state->bucket > PNEIGH_HASHMASK) break; pn = tbl->phash_buckets[state->bucket]; + while (pn && !net_eq(pneigh_net(pn), net)) + pn = pn->next; if (pn) break; } @@ -2237,6 +2341,7 @@ static struct pneigh_entry *pneigh_get_idx(struct seq_file *seq, loff_t *pos) struct pneigh_entry *pn = pneigh_get_first(seq); if (pn) { + --(*pos); while (*pos) { pn = pneigh_get_next(seq, pn, pos); if (!pn) @@ -2250,18 +2355,19 @@ static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos) { struct neigh_seq_state *state = seq->private; void *rc; + loff_t idxpos = *pos; - rc = neigh_get_idx(seq, pos); + rc = neigh_get_idx(seq, &idxpos); if (!rc && !(state->flags & NEIGH_SEQ_NEIGH_ONLY)) - rc = pneigh_get_idx(seq, pos); + rc = pneigh_get_idx(seq, &idxpos); return rc; } void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags) + __acquires(tbl->lock) { struct neigh_seq_state *state = seq->private; - loff_t pos_minus_one; state->tbl = tbl; state->bucket = 0; @@ -2269,8 +2375,7 @@ void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl read_lock_bh(&tbl->lock); - pos_minus_one = *pos - 1; - return *pos ? neigh_get_idx_any(seq, &pos_minus_one) : SEQ_START_TOKEN; + return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN; } EXPORT_SYMBOL(neigh_seq_start); @@ -2280,7 +2385,7 @@ void *neigh_seq_next(struct seq_file *seq, void *v, loff_t *pos) void *rc; if (v == SEQ_START_TOKEN) { - rc = neigh_get_idx(seq, pos); + rc = neigh_get_first(seq); goto out; } @@ -2302,6 +2407,7 @@ out: EXPORT_SYMBOL(neigh_seq_next); void neigh_seq_stop(struct seq_file *seq, void *v) + __releases(tbl->lock) { struct neigh_seq_state *state = seq->private; struct neigh_table *tbl = state->tbl; @@ -2320,8 +2426,8 @@ static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos) if (*pos == 0) return SEQ_START_TOKEN; - - for (cpu = *pos-1; cpu < NR_CPUS; ++cpu) { + + for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; @@ -2336,7 +2442,7 @@ static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct neigh_table *tbl = pde->data; int cpu; - for (cpu = *pos; cpu < NR_CPUS; ++cpu) { + for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; @@ -2357,12 +2463,12 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v) struct neigh_statistics *st = v; if (v == SEQ_START_TOKEN) { - seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs\n"); + seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards\n"); return 0; } seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx " - "%08lx %08lx %08lx %08lx\n", + "%08lx %08lx %08lx %08lx %08lx\n", atomic_read(&tbl->entries), st->allocs, @@ -2378,13 +2484,14 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v) st->rcv_probes_ucast, st->periodic_gc_runs, - st->forced_gc_runs + st->forced_gc_runs, + st->unres_discards ); return 0; } -static struct seq_operations neigh_stat_seq_ops = { +static const struct seq_operations neigh_stat_seq_ops = { .start = neigh_stat_seq_start, .next = neigh_stat_seq_next, .stop = neigh_stat_seq_stop, @@ -2402,7 +2509,7 @@ static int neigh_stat_seq_open(struct inode *inode, struct file *file) return ret; }; -static struct file_operations neigh_stat_seq_fops = { +static const struct file_operations neigh_stat_seq_fops = { .owner = THIS_MODULE, .open = neigh_stat_seq_open, .read = seq_read, @@ -2412,7 +2519,6 @@ static struct file_operations neigh_stat_seq_fops = { #endif /* CONFIG_PROC_FS */ -#ifdef CONFIG_ARPD static inline size_t neigh_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) @@ -2424,6 +2530,7 @@ static inline size_t neigh_nlmsg_size(void) static void __neigh_notify(struct neighbour *n, int type, int flags) { + struct net *net = dev_net(n->dev); struct sk_buff *skb; int err = -ENOBUFS; @@ -2438,33 +2545,27 @@ static void __neigh_notify(struct neighbour *n, int type, int flags) kfree_skb(skb); goto errout; } - err = rtnl_notify(skb, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); + rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); + return; errout: if (err < 0) - rtnl_set_sk_err(RTNLGRP_NEIGH, err); + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } +#ifdef CONFIG_ARPD void neigh_app_ns(struct neighbour *n) { __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST); } - -static void neigh_app_notify(struct neighbour *n) -{ - __neigh_notify(n, RTM_NEWNEIGH, 0); -} - +EXPORT_SYMBOL(neigh_app_ns); #endif /* CONFIG_ARPD */ #ifdef CONFIG_SYSCTL static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; - ctl_table neigh_vars[__NET_NEIGH_MAX]; - ctl_table neigh_dev[2]; - ctl_table neigh_neigh_dir[2]; - ctl_table neigh_proto_dir[2]; - ctl_table neigh_root_dir[2]; + struct ctl_table neigh_vars[__NET_NEIGH_MAX]; + char *dev_name; } neigh_sysctl_template __read_mostly = { .neigh_vars = { { @@ -2472,173 +2573,157 @@ static struct neigh_sysctl_table { .procname = "mcast_solicit", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_NEIGH_UCAST_SOLICIT, .procname = "ucast_solicit", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_NEIGH_APP_SOLICIT, .procname = "app_solicit", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_RETRANS_TIME, .procname = "retrans_time", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_userhz_jiffies, + .proc_handler = proc_dointvec_userhz_jiffies, }, { .ctl_name = NET_NEIGH_REACHABLE_TIME, .procname = "base_reachable_time", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_NEIGH_DELAY_PROBE_TIME, .procname = "delay_first_probe_time", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_NEIGH_GC_STALE_TIME, .procname = "gc_stale_time", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_NEIGH_UNRES_QLEN, .procname = "unres_qlen", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_NEIGH_PROXY_QLEN, .procname = "proxy_qlen", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_ANYCAST_DELAY, .procname = "anycast_delay", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_userhz_jiffies, + .proc_handler = proc_dointvec_userhz_jiffies, }, { - .ctl_name = NET_NEIGH_PROXY_DELAY, .procname = "proxy_delay", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_userhz_jiffies, + .proc_handler = proc_dointvec_userhz_jiffies, }, { - .ctl_name = NET_NEIGH_LOCKTIME, .procname = "locktime", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_userhz_jiffies, + .proc_handler = proc_dointvec_userhz_jiffies, }, { - .ctl_name = NET_NEIGH_GC_INTERVAL, - .procname = "gc_interval", + .ctl_name = NET_NEIGH_RETRANS_TIME_MS, + .procname = "retrans_time_ms", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_ms_jiffies, + .strategy = sysctl_ms_jiffies, }, { - .ctl_name = NET_NEIGH_GC_THRESH1, - .procname = "gc_thresh1", + .ctl_name = NET_NEIGH_REACHABLE_TIME_MS, + .procname = "base_reachable_time_ms", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec_ms_jiffies, + .strategy = sysctl_ms_jiffies, }, { - .ctl_name = NET_NEIGH_GC_THRESH2, - .procname = "gc_thresh2", + .ctl_name = NET_NEIGH_GC_INTERVAL, + .procname = "gc_interval", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { - .ctl_name = NET_NEIGH_GC_THRESH3, - .procname = "gc_thresh3", + .ctl_name = NET_NEIGH_GC_THRESH1, + .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_RETRANS_TIME_MS, - .procname = "retrans_time_ms", + .ctl_name = NET_NEIGH_GC_THRESH2, + .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_ms_jiffies, - .strategy = &sysctl_ms_jiffies, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_REACHABLE_TIME_MS, - .procname = "base_reachable_time_ms", + .ctl_name = NET_NEIGH_GC_THRESH3, + .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_ms_jiffies, - .strategy = &sysctl_ms_jiffies, - }, - }, - .neigh_dev = { - { - .ctl_name = NET_PROTO_CONF_DEFAULT, - .procname = "default", - .mode = 0555, - }, - }, - .neigh_neigh_dir = { - { - .procname = "neigh", - .mode = 0555, - }, - }, - .neigh_proto_dir = { - { - .mode = 0555, - }, - }, - .neigh_root_dir = { - { - .ctl_name = CTL_NET, - .procname = "net", - .mode = 0555, + .proc_handler = proc_dointvec, }, + {}, }, }; int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, - int p_id, int pdev_id, char *p_name, + int p_id, int pdev_id, char *p_name, proc_handler *handler, ctl_handler *strategy) { - struct neigh_sysctl_table *t = kmemdup(&neigh_sysctl_template, - sizeof(*t), GFP_KERNEL); + struct neigh_sysctl_table *t; const char *dev_name_source = NULL; - char *dev_name = NULL; - int err = 0; +#define NEIGH_CTL_PATH_ROOT 0 +#define NEIGH_CTL_PATH_PROTO 1 +#define NEIGH_CTL_PATH_NEIGH 2 +#define NEIGH_CTL_PATH_DEV 3 + + struct ctl_path neigh_path[] = { + { .procname = "net", .ctl_name = CTL_NET, }, + { .procname = "proto", .ctl_name = 0, }, + { .procname = "neigh", .ctl_name = 0, }, + { .procname = "default", .ctl_name = NET_PROTO_CONF_DEFAULT, }, + { }, + }; + + t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL); if (!t) - return -ENOBUFS; + goto err; + t->neigh_vars[0].data = &p->mcast_probes; t->neigh_vars[1].data = &p->ucast_probes; t->neigh_vars[2].data = &p->app_probes; @@ -2651,78 +2736,75 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, t->neigh_vars[9].data = &p->anycast_delay; t->neigh_vars[10].data = &p->proxy_delay; t->neigh_vars[11].data = &p->locktime; + t->neigh_vars[12].data = &p->retrans_time; + t->neigh_vars[13].data = &p->base_reachable_time; if (dev) { dev_name_source = dev->name; - t->neigh_dev[0].ctl_name = dev->ifindex; - t->neigh_vars[12].procname = NULL; - t->neigh_vars[13].procname = NULL; - t->neigh_vars[14].procname = NULL; - t->neigh_vars[15].procname = NULL; + neigh_path[NEIGH_CTL_PATH_DEV].ctl_name = dev->ifindex; + /* Terminate the table early */ + memset(&t->neigh_vars[14], 0, sizeof(t->neigh_vars[14])); } else { - dev_name_source = t->neigh_dev[0].procname; - t->neigh_vars[12].data = (int *)(p + 1); - t->neigh_vars[13].data = (int *)(p + 1) + 1; - t->neigh_vars[14].data = (int *)(p + 1) + 2; - t->neigh_vars[15].data = (int *)(p + 1) + 3; + dev_name_source = neigh_path[NEIGH_CTL_PATH_DEV].procname; + t->neigh_vars[14].data = (int *)(p + 1); + t->neigh_vars[15].data = (int *)(p + 1) + 1; + t->neigh_vars[16].data = (int *)(p + 1) + 2; + t->neigh_vars[17].data = (int *)(p + 1) + 3; } - t->neigh_vars[16].data = &p->retrans_time; - t->neigh_vars[17].data = &p->base_reachable_time; if (handler || strategy) { /* RetransTime */ t->neigh_vars[3].proc_handler = handler; t->neigh_vars[3].strategy = strategy; t->neigh_vars[3].extra1 = dev; + if (!strategy) + t->neigh_vars[3].ctl_name = CTL_UNNUMBERED; /* ReachableTime */ t->neigh_vars[4].proc_handler = handler; t->neigh_vars[4].strategy = strategy; t->neigh_vars[4].extra1 = dev; + if (!strategy) + t->neigh_vars[4].ctl_name = CTL_UNNUMBERED; /* RetransTime (in milliseconds)*/ - t->neigh_vars[16].proc_handler = handler; - t->neigh_vars[16].strategy = strategy; - t->neigh_vars[16].extra1 = dev; + t->neigh_vars[12].proc_handler = handler; + t->neigh_vars[12].strategy = strategy; + t->neigh_vars[12].extra1 = dev; + if (!strategy) + t->neigh_vars[12].ctl_name = CTL_UNNUMBERED; /* ReachableTime (in milliseconds) */ - t->neigh_vars[17].proc_handler = handler; - t->neigh_vars[17].strategy = strategy; - t->neigh_vars[17].extra1 = dev; + t->neigh_vars[13].proc_handler = handler; + t->neigh_vars[13].strategy = strategy; + t->neigh_vars[13].extra1 = dev; + if (!strategy) + t->neigh_vars[13].ctl_name = CTL_UNNUMBERED; } - dev_name = kstrdup(dev_name_source, GFP_KERNEL); - if (!dev_name) { - err = -ENOBUFS; + t->dev_name = kstrdup(dev_name_source, GFP_KERNEL); + if (!t->dev_name) goto free; - } - - t->neigh_dev[0].procname = dev_name; - - t->neigh_neigh_dir[0].ctl_name = pdev_id; - - t->neigh_proto_dir[0].procname = p_name; - t->neigh_proto_dir[0].ctl_name = p_id; - t->neigh_dev[0].child = t->neigh_vars; - t->neigh_neigh_dir[0].child = t->neigh_dev; - t->neigh_proto_dir[0].child = t->neigh_neigh_dir; - t->neigh_root_dir[0].child = t->neigh_proto_dir; + neigh_path[NEIGH_CTL_PATH_DEV].procname = t->dev_name; + neigh_path[NEIGH_CTL_PATH_NEIGH].ctl_name = pdev_id; + neigh_path[NEIGH_CTL_PATH_PROTO].procname = p_name; + neigh_path[NEIGH_CTL_PATH_PROTO].ctl_name = p_id; - t->sysctl_header = register_sysctl_table(t->neigh_root_dir, 0); - if (!t->sysctl_header) { - err = -ENOBUFS; + t->sysctl_header = + register_net_sysctl_table(neigh_parms_net(p), neigh_path, t->neigh_vars); + if (!t->sysctl_header) goto free_procname; - } + p->sysctl_table = t; return 0; - /* error path */ - free_procname: - kfree(dev_name); - free: +free_procname: + kfree(t->dev_name); +free: kfree(t); - - return err; +err: + return -ENOBUFS; } +EXPORT_SYMBOL(neigh_sysctl_register); void neigh_sysctl_unregister(struct neigh_parms *p) { @@ -2730,40 +2812,25 @@ void neigh_sysctl_unregister(struct neigh_parms *p) struct neigh_sysctl_table *t = p->sysctl_table; p->sysctl_table = NULL; unregister_sysctl_table(t->sysctl_header); - kfree(t->neigh_dev[0].procname); + kfree(t->dev_name); kfree(t); } } +EXPORT_SYMBOL(neigh_sysctl_unregister); #endif /* CONFIG_SYSCTL */ -EXPORT_SYMBOL(__neigh_event_send); -EXPORT_SYMBOL(neigh_changeaddr); -EXPORT_SYMBOL(neigh_compat_output); -EXPORT_SYMBOL(neigh_connected_output); -EXPORT_SYMBOL(neigh_create); -EXPORT_SYMBOL(neigh_delete); -EXPORT_SYMBOL(neigh_destroy); -EXPORT_SYMBOL(neigh_dump_info); -EXPORT_SYMBOL(neigh_event_ns); -EXPORT_SYMBOL(neigh_ifdown); -EXPORT_SYMBOL(neigh_lookup); -EXPORT_SYMBOL(neigh_lookup_nodev); -EXPORT_SYMBOL(neigh_parms_alloc); -EXPORT_SYMBOL(neigh_parms_release); -EXPORT_SYMBOL(neigh_rand_reach_time); -EXPORT_SYMBOL(neigh_resolve_output); -EXPORT_SYMBOL(neigh_table_clear); -EXPORT_SYMBOL(neigh_table_init); -EXPORT_SYMBOL(neigh_table_init_no_netlink); -EXPORT_SYMBOL(neigh_update); -EXPORT_SYMBOL(pneigh_enqueue); -EXPORT_SYMBOL(pneigh_lookup); +static int __init neigh_init(void) +{ + rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL); + rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL); + rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info); + + rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info); + rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL); + + return 0; +} + +subsys_initcall(neigh_init); -#ifdef CONFIG_ARPD -EXPORT_SYMBOL(neigh_app_ns); -#endif -#ifdef CONFIG_SYSCTL -EXPORT_SYMBOL(neigh_sysctl_register); -EXPORT_SYMBOL(neigh_sysctl_unregister); -#endif