--- zzzz-none-000/linux-3.10.107/net/core/neighbour.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/net/core/neighbour.c 2021-02-04 17:41:59.000000000 +0000 @@ -38,6 +38,8 @@ #include #include #include +#include +#include #define DEBUG #define NEIGH_DEBUG 1 @@ -54,7 +56,6 @@ static void neigh_update_notify(struct neighbour *neigh); static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev); -static struct neigh_table *neigh_tables; #ifdef CONFIG_PROC_FS static const struct file_operations neigh_stat_seq_fops; #endif @@ -85,13 +86,8 @@ the most complicated procedure, which we allow is dev->hard_header. It is supposed, that dev->hard_header is simplistic and does not make callbacks to neighbour tables. - - The last lock is neigh_tbl_lock. It is pure SMP lock, protecting - list of neighbour tables. This list is used only in process context, */ -static DEFINE_RWLOCK(neigh_tbl_lock); - static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) { kfree_skb(skb); @@ -115,7 +111,7 @@ unsigned long neigh_rand_reach_time(unsigned long base) { - return base ? (net_random() % base) + (base >> 1) : 0; + return base ? (prandom_u32() % base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); @@ -278,8 +274,12 @@ (entries >= tbl->gc_thresh2 && time_after(now, tbl->last_flush + 5 * HZ))) { if (!neigh_forced_gc(tbl) && - entries >= tbl->gc_thresh3) + entries >= tbl->gc_thresh3) { + net_info_ratelimited("%s: neighbor table overflow!\n", + tbl->id); + NEIGH_CACHE_STAT_INC(tbl, table_fulls); goto out_entries; + } } n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC); @@ -401,25 +401,15 @@ struct net_device *dev) { struct neighbour *n; - int key_len = tbl->key_len; - u32 hash_val; - struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, lookups); rcu_read_lock_bh(); - nht = rcu_dereference_bh(tbl->nht); - hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); - - for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); - n != NULL; - n = rcu_dereference_bh(n->next)) { - if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) { - if (!atomic_inc_not_zero(&n->refcnt)) - n = NULL; - NEIGH_CACHE_STAT_INC(tbl, hits); - break; - } + n = __neigh_lookup_noref(tbl, pkey, dev); + if (n) { + if (!atomic_inc_not_zero(&n->refcnt)) + n = NULL; + NEIGH_CACHE_STAT_INC(tbl, hits); } rcu_read_unlock_bh(); @@ -497,7 +487,7 @@ goto out_neigh_release; } - n->confirmed = jiffies - (n->parms->base_reachable_time << 1); + n->confirmed = jiffies - (NEIGH_VAR(n->parms, BASE_REACHABLE_TIME) << 1); write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, @@ -605,7 +595,7 @@ if (!n) goto out; - write_pnet(&n->net, hold_net(net)); + write_pnet(&n->net, net); memcpy(n->key, pkey, key_len); n->dev = dev; if (dev) @@ -614,7 +604,6 @@ if (tbl->pconstructor && tbl->pconstructor(n)) { if (dev) dev_put(dev); - release_net(net); kfree(n); n = NULL; goto out; @@ -648,7 +637,6 @@ tbl->pdestructor(n); if (n->dev) dev_put(n->dev); - release_net(pneigh_net(n)); kfree(n); return 0; } @@ -671,7 +659,6 @@ tbl->pdestructor(n); if (n->dev) dev_put(n->dev); - release_net(pneigh_net(n)); kfree(n); continue; } @@ -700,7 +687,7 @@ NEIGH_CACHE_STAT_INC(neigh->tbl, destroys); if (!neigh->dead) { - pr_warn("Destroying alive neighbour %p\n", neigh); + pr_warn("Destroying alive neighbour %pK\n", neigh); dump_stack(); return; } @@ -771,9 +758,9 @@ if (time_after(jiffies, tbl->last_rand + 300 * HZ)) { struct neigh_parms *p; tbl->last_rand = jiffies; - for (p = &tbl->parms; p; p = p->next) + list_for_each_entry(p, &tbl->parms_list, list) p->reachable_time = - neigh_rand_reach_time(p->base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } if (atomic_read(&tbl->entries) < tbl->gc_thresh1) @@ -799,7 +786,7 @@ if (atomic_read(&n->refcnt) == 1 && (state == NUD_FAILED || - time_after(jiffies, n->used + n->parms->gc_staletime))) { + time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; n->dead = 1; write_unlock(&n->lock); @@ -822,21 +809,21 @@ lockdep_is_held(&tbl->lock)); } out: - /* 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. */ - schedule_delayed_work(&tbl->gc_work, - tbl->parms.base_reachable_time >> 1); + queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, + NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME) >> 1); write_unlock_bh(&tbl->lock); } static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; - return (n->nud_state & NUD_PROBE) ? - p->ucast_probes : - p->ucast_probes + p->app_probes + p->mcast_probes; + return NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) + + (n->nud_state & NUD_PROBE ? NEIGH_VAR(p, MCAST_REPROBES) : + NEIGH_VAR(p, MCAST_PROBES)); } static void neigh_invalidate(struct neighbour *neigh) @@ -867,13 +854,12 @@ static void neigh_probe(struct neighbour *neigh) __releases(neigh->lock) { - struct sk_buff *skb = skb_peek(&neigh->arp_queue); + struct sk_buff *skb = skb_peek_tail(&neigh->arp_queue); /* keep skb alive even if arp_queue overflows */ if (skb) - skb = skb_copy(skb, GFP_ATOMIC); + skb = skb_clone(skb, GFP_ATOMIC); write_unlock(&neigh->lock); - if (neigh->ops->solicit) - neigh->ops->solicit(neigh, skb); + neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); kfree_skb(skb); } @@ -902,12 +888,13 @@ neigh_dbg(2, "neigh %p is still alive\n", neigh); next = neigh->confirmed + neigh->parms->reachable_time; } else if (time_before_eq(now, - neigh->used + neigh->parms->delay_probe_time)) { + neigh->used + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_suspect(neigh); - next = now + neigh->parms->delay_probe_time; + next = now + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME); } else { neigh_dbg(2, "neigh %p is suspected\n", neigh); neigh->nud_state = NUD_STALE; @@ -917,7 +904,8 @@ } } else if (state & NUD_DELAY) { if (time_before_eq(now, - neigh->confirmed + neigh->parms->delay_probe_time)) { + neigh->confirmed + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is now reachable\n", neigh); neigh->nud_state = NUD_REACHABLE; neigh->updated = jiffies; @@ -929,11 +917,12 @@ neigh->nud_state = NUD_PROBE; neigh->updated = jiffies; atomic_set(&neigh->probes, 0); - next = now + neigh->parms->retrans_time; + notify = 1; + next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME); } } else { /* NUD_PROBE|NUD_INCOMPLETE */ - next = now + neigh->parms->retrans_time; + next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME); } if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && @@ -941,6 +930,7 @@ neigh->nud_state = NUD_FAILED; notify = 1; neigh_invalidate(neigh); + goto out; } if (neigh->nud_state & NUD_IN_TIMER) { @@ -972,15 +962,20 @@ rc = 0; if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE)) goto out_unlock_bh; + if (neigh->dead) + goto out_dead; if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) { - if (neigh->parms->mcast_probes + neigh->parms->app_probes) { + if (NEIGH_VAR(neigh->parms, MCAST_PROBES) + + NEIGH_VAR(neigh->parms, APP_PROBES)) { unsigned long next, now = jiffies; - atomic_set(&neigh->probes, neigh->parms->ucast_probes); + atomic_set(&neigh->probes, + NEIGH_VAR(neigh->parms, UCAST_PROBES)); neigh->nud_state = NUD_INCOMPLETE; neigh->updated = now; - next = now + max(neigh->parms->retrans_time, HZ/2); + next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), + HZ/2); neigh_add_timer(neigh, next); immediate_probe = true; } else { @@ -995,14 +990,14 @@ neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; - neigh_add_timer(neigh, - jiffies + neigh->parms->delay_probe_time); + neigh_add_timer(neigh, jiffies + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME)); } if (neigh->nud_state == NUD_INCOMPLETE) { if (skb) { while (neigh->arp_queue_len_bytes + skb->truesize > - neigh->parms->queue_len_bytes) { + NEIGH_VAR(neigh->parms, QUEUE_LEN_BYTES)) { struct sk_buff *buff; buff = __skb_dequeue(&neigh->arp_queue); @@ -1025,6 +1020,13 @@ write_unlock(&neigh->lock); local_bh_enable(); return rc; + +out_dead: + if (neigh->nud_state & NUD_STALE) + goto out_unlock_bh; + write_unlock_bh(&neigh->lock); + kfree_skb(skb); + return 1; } EXPORT_SYMBOL(__neigh_event_send); @@ -1047,7 +1049,19 @@ } } +ATOMIC_NOTIFIER_HEAD(neigh_mac_update_notifier_list); + +void neigh_mac_update_register_notify(struct notifier_block *nb) +{ + atomic_notifier_chain_register(&neigh_mac_update_notifier_list, nb); +} +EXPORT_SYMBOL_GPL(neigh_mac_update_register_notify); +void neigh_mac_update_unregister_notify(struct notifier_block *nb) +{ + atomic_notifier_chain_unregister(&neigh_mac_update_notifier_list, nb); +} +EXPORT_SYMBOL_GPL(neigh_mac_update_unregister_notify); /* Generic update routine. -- lladdr is new lladdr or NULL, if it is not supplied. @@ -1078,6 +1092,7 @@ int notify = 0; struct net_device *dev; int update_isrouter = 0; + struct neigh_mac_update nmu; write_lock_bh(&neigh->lock); @@ -1085,9 +1100,13 @@ old = neigh->nud_state; err = -EPERM; + memset(&nmu, 0, sizeof(struct neigh_mac_update)); + if (!(flags & NEIGH_UPDATE_F_ADMIN) && (old & (NUD_NOARP | NUD_PERMANENT))) goto out; + if (neigh->dead) + goto out; if (!(new & NUD_VALID)) { neigh_del_timer(neigh); @@ -1113,7 +1132,11 @@ and a new address is proposed: - compare new & old - if they are different, check override flag + - copy old and new addresses for neigh update notification */ + memcpy(nmu.old_mac, neigh->ha, dev->addr_len); + memcpy(nmu.update_mac, lladdr, dev->addr_len); + if ((old & NUD_VALID) && !memcmp(lladdr, neigh->ha, dev->addr_len)) lladdr = neigh->ha; @@ -1156,12 +1179,15 @@ if (new != old) { neigh_del_timer(neigh); + if (new & NUD_PROBE) + atomic_set(&neigh->probes, 0); if (new & NUD_IN_TIMER) neigh_add_timer(neigh, (jiffies + ((new & NUD_REACHABLE) ? neigh->parms->reachable_time : 0))); neigh->nud_state = new; + notify = 1; } if (lladdr != neigh->ha) { @@ -1171,7 +1197,7 @@ neigh_update_hhs(neigh); if (!(new & NUD_CONNECTED)) neigh->confirmed = jiffies - - (neigh->parms->base_reachable_time << 1); + (NEIGH_VAR(neigh->parms, BASE_REACHABLE_TIME) << 1); notify = 1; } if (new == old) @@ -1224,13 +1250,33 @@ } write_unlock_bh(&neigh->lock); - if (notify) + if (notify) { neigh_update_notify(neigh); + atomic_notifier_call_chain(&neigh_mac_update_notifier_list, 0, + (struct neigh_mac_update *)&nmu); + } return err; } EXPORT_SYMBOL(neigh_update); +/* Update the neigh to listen temporarily for probe responses, even if it is + * in a NUD_FAILED state. The caller has to hold neigh->lock for writing. + */ +void __neigh_set_probe_once(struct neighbour *neigh) +{ + if (neigh->dead) + return; + neigh->updated = jiffies; + if (!(neigh->nud_state & NUD_FAILED)) + return; + neigh->nud_state = NUD_INCOMPLETE; + atomic_set(&neigh->probes, neigh_max_probes(neigh)); + neigh_add_timer(neigh, + jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME)); +} +EXPORT_SYMBOL(__neigh_set_probe_once); + struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, struct net_device *dev) @@ -1245,10 +1291,10 @@ EXPORT_SYMBOL(neigh_event_ns); /* called with read_lock_bh(&n->lock); */ -static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst) +static void neigh_hh_init(struct neighbour *n) { - struct net_device *dev = dst->dev; - __be16 prot = dst->ops->protocol; + struct net_device *dev = n->dev; + __be16 prot = n->tbl->protocol; struct hh_cache *hh = &n->hh; write_lock_bh(&n->lock); @@ -1262,43 +1308,19 @@ write_unlock_bh(&n->lock); } -/* This function can be used in contexts, where only old dev_queue_xmit - * worked, f.e. if you want to override normal output path (eql, shaper), - * but resolution is not made yet. - */ - -int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - - __skb_pull(skb, skb_network_offset(skb)); - - if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL, - skb->len) < 0 && - dev_rebuild_header(skb)) - return 0; - - return dev_queue_xmit(skb); -} -EXPORT_SYMBOL(neigh_compat_output); - /* Slow and careful. */ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); int rc = 0; - if (!dst) - goto discard; - if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; unsigned int seq; if (dev->header_ops->cache && !neigh->hh.hh_len) - neigh_hh_init(neigh, dst); + neigh_hh_init(neigh); do { __skb_pull(skb, skb_network_offset(skb)); @@ -1314,8 +1336,6 @@ } out: return rc; -discard: - neigh_dbg(1, "%s: dst=%p neigh=%p\n", __func__, dst, neigh); out_kfree_skb: rc = -EINVAL; kfree_skb(skb); @@ -1392,9 +1412,11 @@ struct sk_buff *skb) { unsigned long now = jiffies; - unsigned long sched_next = now + (net_random() % p->proxy_delay); - if (tbl->proxy_queue.qlen > p->proxy_qlen) { + unsigned long sched_next = now + (prandom_u32() % + NEIGH_VAR(p, PROXY_DELAY)); + + if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { kfree_skb(skb); return; } @@ -1420,9 +1442,9 @@ { struct neigh_parms *p; - for (p = &tbl->parms; p; p = p->next) { + list_for_each_entry(p, &tbl->parms_list, list) { if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) || - (!p->dev && !ifindex)) + (!p->dev && !ifindex && net_eq(net, &init_net))) return p; } @@ -1432,36 +1454,32 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl) { - struct neigh_parms *p, *ref; + struct neigh_parms *p; struct net *net = dev_net(dev); const struct net_device_ops *ops = dev->netdev_ops; - ref = lookup_neigh_parms(tbl, net, 0); - if (!ref) - return NULL; - - p = kmemdup(ref, sizeof(*p), GFP_KERNEL); + p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL); if (p) { p->tbl = tbl; atomic_set(&p->refcnt, 1); p->reachable_time = - neigh_rand_reach_time(p->base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); dev_hold(dev); p->dev = dev; - write_pnet(&p->net, hold_net(net)); + write_pnet(&p->net, net); p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { - release_net(net); dev_put(dev); kfree(p); return NULL; } write_lock_bh(&tbl->lock); - p->next = tbl->parms.next; - tbl->parms.next = p; + list_add(&p->list, &tbl->parms.list); write_unlock_bh(&tbl->lock); + + neigh_parms_data_state_cleanall(p); } return p; } @@ -1477,44 +1495,38 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) { - struct neigh_parms **p; - if (!parms || parms == &tbl->parms) return; write_lock_bh(&tbl->lock); - for (p = &tbl->parms.next; *p; p = &(*p)->next) { - if (*p == parms) { - *p = parms->next; - parms->dead = 1; - write_unlock_bh(&tbl->lock); - if (parms->dev) - dev_put(parms->dev); - call_rcu(&parms->rcu_head, neigh_rcu_free_parms); - return; - } - } + list_del(&parms->list); + parms->dead = 1; write_unlock_bh(&tbl->lock); - neigh_dbg(1, "%s: not found\n", __func__); + if (parms->dev) + dev_put(parms->dev); + call_rcu(&parms->rcu_head, neigh_rcu_free_parms); } EXPORT_SYMBOL(neigh_parms_release); 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; -static void neigh_table_init_no_netlink(struct neigh_table *tbl) +static struct neigh_table *neigh_tables[NEIGH_NR_TABLES] __read_mostly; + +void neigh_table_init(int index, struct neigh_table *tbl) { unsigned long now = jiffies; unsigned long phsize; + INIT_LIST_HEAD(&tbl->parms_list); + list_add(&tbl->parms.list, &tbl->parms_list); write_pnet(&tbl->parms.net, &init_net); atomic_set(&tbl->parms.refcnt, 1); tbl->parms.reachable_time = - neigh_rand_reach_time(tbl->parms.base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) @@ -1542,41 +1554,22 @@ rwlock_init(&tbl->lock); INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); - schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); + queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, + tbl->parms.reachable_time); 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; -} - -void neigh_table_init(struct neigh_table *tbl) -{ - struct neigh_table *tmp; - neigh_table_init_no_netlink(tbl); - write_lock(&neigh_tbl_lock); - for (tmp = neigh_tables; tmp; tmp = tmp->next) { - if (tmp->family == tbl->family) - break; - } - tbl->next = neigh_tables; - neigh_tables = tbl; - write_unlock(&neigh_tbl_lock); - - if (unlikely(tmp)) { - pr_err("Registering multiple tables for family %d\n", - tbl->family); - dump_stack(); - } + neigh_tables[index] = tbl; } EXPORT_SYMBOL(neigh_table_init); -int neigh_table_clear(struct neigh_table *tbl) +int neigh_table_clear(int index, struct neigh_table *tbl) { - struct neigh_table **tp; - + neigh_tables[index] = NULL; /* It is not clean... Fix it to unload IPv6 module safely */ cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); @@ -1584,14 +1577,6 @@ neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) pr_crit("neighbour leakage\n"); - write_lock(&neigh_tbl_lock); - for (tp = &neigh_tables; *tp; tp = &(*tp)->next) { - if (*tp == tbl) { - *tp = tbl->next; - break; - } - } - write_unlock(&neigh_tbl_lock); call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu, neigh_hash_free_rcu); @@ -1609,12 +1594,32 @@ } EXPORT_SYMBOL(neigh_table_clear); +static struct neigh_table *neigh_find_table(int family) +{ + struct neigh_table *tbl = NULL; + + switch (family) { + case AF_INET: + tbl = neigh_tables[NEIGH_ARP_TABLE]; + break; + case AF_INET6: + tbl = neigh_tables[NEIGH_ND_TABLE]; + break; + case AF_DECnet: + tbl = neigh_tables[NEIGH_DN_TABLE]; + break; + } + + return tbl; +} + static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *dst_attr; struct neigh_table *tbl; + struct neighbour *neigh; struct net_device *dev = NULL; int err = -EINVAL; @@ -1635,39 +1640,31 @@ } } - read_lock(&neigh_tbl_lock); - for (tbl = neigh_tables; tbl; tbl = tbl->next) { - struct neighbour *neigh; - - if (tbl->family != ndm->ndm_family) - continue; - read_unlock(&neigh_tbl_lock); - - if (nla_len(dst_attr) < tbl->key_len) - goto out; + tbl = neigh_find_table(ndm->ndm_family); + if (tbl == NULL) + return -EAFNOSUPPORT; - if (ndm->ndm_flags & NTF_PROXY) { - err = pneigh_delete(tbl, net, nla_data(dst_attr), dev); - goto out; - } + if (nla_len(dst_attr) < tbl->key_len) + goto out; - if (dev == NULL) - goto out; + if (ndm->ndm_flags & NTF_PROXY) { + err = pneigh_delete(tbl, net, nla_data(dst_attr), dev); + goto out; + } - neigh = neigh_lookup(tbl, nla_data(dst_attr), dev); - if (neigh == NULL) { - err = -ENOENT; - goto out; - } + if (dev == NULL) + goto out; - err = neigh_update(neigh, NULL, NUD_FAILED, - NEIGH_UPDATE_F_OVERRIDE | - NEIGH_UPDATE_F_ADMIN); - neigh_release(neigh); + neigh = neigh_lookup(tbl, nla_data(dst_attr), dev); + if (neigh == NULL) { + err = -ENOENT; goto out; } - read_unlock(&neigh_tbl_lock); - err = -EAFNOSUPPORT; + + err = neigh_update(neigh, NULL, NUD_FAILED, + NEIGH_UPDATE_F_OVERRIDE | + NEIGH_UPDATE_F_ADMIN); + neigh_release(neigh); out: return err; @@ -1675,11 +1672,14 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh) { + int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE; struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; struct neigh_table *tbl; struct net_device *dev = NULL; + struct neighbour *neigh; + void *dst, *lladdr; int err; ASSERT_RTNL(); @@ -1703,70 +1703,60 @@ goto out; } - read_lock(&neigh_tbl_lock); - for (tbl = neigh_tables; tbl; tbl = tbl->next) { - int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE; - struct neighbour *neigh; - void *dst, *lladdr; + tbl = neigh_find_table(ndm->ndm_family); + if (tbl == NULL) + return -EAFNOSUPPORT; - if (tbl->family != ndm->ndm_family) - continue; - read_unlock(&neigh_tbl_lock); + if (nla_len(tb[NDA_DST]) < tbl->key_len) + goto out; + dst = nla_data(tb[NDA_DST]); + lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; - if (nla_len(tb[NDA_DST]) < tbl->key_len) - goto out; - dst = nla_data(tb[NDA_DST]); - lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; + if (ndm->ndm_flags & NTF_PROXY) { + struct pneigh_entry *pn; - if (ndm->ndm_flags & NTF_PROXY) { - struct pneigh_entry *pn; + err = -ENOBUFS; + pn = pneigh_lookup(tbl, net, dst, dev, 1); + if (pn) { + pn->flags = ndm->ndm_flags; + err = 0; + } + goto out; + } - err = -ENOBUFS; - pn = pneigh_lookup(tbl, net, dst, dev, 1); - if (pn) { - pn->flags = ndm->ndm_flags; - err = 0; - } + if (dev == NULL) + goto out; + + neigh = neigh_lookup(tbl, dst, dev); + if (neigh == NULL) { + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { + err = -ENOENT; goto out; } - if (dev == NULL) + neigh = __neigh_lookup_errno(tbl, dst, dev); + if (IS_ERR(neigh)) { + err = PTR_ERR(neigh); + goto out; + } + } else { + if (nlh->nlmsg_flags & NLM_F_EXCL) { + err = -EEXIST; + neigh_release(neigh); goto out; - - neigh = neigh_lookup(tbl, dst, dev); - if (neigh == NULL) { - if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { - err = -ENOENT; - goto out; - } - - neigh = __neigh_lookup_errno(tbl, dst, dev); - if (IS_ERR(neigh)) { - err = PTR_ERR(neigh); - goto out; - } - } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) { - err = -EEXIST; - neigh_release(neigh); - goto out; - } - - if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) - flags &= ~NEIGH_UPDATE_F_OVERRIDE; } - 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; + if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) + flags &= ~NEIGH_UPDATE_F_OVERRIDE; } - read_unlock(&neigh_tbl_lock); - err = -EAFNOSUPPORT; + 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); + out: return err; } @@ -1782,24 +1772,34 @@ if ((parms->dev && nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) || nla_put_u32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)) || - nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes) || + nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, + NEIGH_VAR(parms, QUEUE_LEN_BYTES)) || /* approximative value for deprecated QUEUE_LEN (in packets) */ nla_put_u32(skb, NDTPA_QUEUE_LEN, - parms->queue_len_bytes / SKB_TRUESIZE(ETH_FRAME_LEN)) || - nla_put_u32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen) || - nla_put_u32(skb, NDTPA_APP_PROBES, parms->app_probes) || - nla_put_u32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes) || - nla_put_u32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes) || + NEIGH_VAR(parms, QUEUE_LEN_BYTES) / SKB_TRUESIZE(ETH_FRAME_LEN)) || + nla_put_u32(skb, NDTPA_PROXY_QLEN, NEIGH_VAR(parms, PROXY_QLEN)) || + nla_put_u32(skb, NDTPA_APP_PROBES, NEIGH_VAR(parms, APP_PROBES)) || + nla_put_u32(skb, NDTPA_UCAST_PROBES, + NEIGH_VAR(parms, UCAST_PROBES)) || + nla_put_u32(skb, NDTPA_MCAST_PROBES, + NEIGH_VAR(parms, MCAST_PROBES)) || + nla_put_u32(skb, NDTPA_MCAST_REPROBES, + NEIGH_VAR(parms, MCAST_REPROBES)) || nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) || nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME, - parms->base_reachable_time) || - nla_put_msecs(skb, NDTPA_GC_STALETIME, parms->gc_staletime) || + NEIGH_VAR(parms, BASE_REACHABLE_TIME)) || + nla_put_msecs(skb, NDTPA_GC_STALETIME, + NEIGH_VAR(parms, GC_STALETIME)) || nla_put_msecs(skb, NDTPA_DELAY_PROBE_TIME, - parms->delay_probe_time) || - nla_put_msecs(skb, NDTPA_RETRANS_TIME, parms->retrans_time) || - nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay) || - nla_put_msecs(skb, NDTPA_PROXY_DELAY, parms->proxy_delay) || - nla_put_msecs(skb, NDTPA_LOCKTIME, parms->locktime)) + NEIGH_VAR(parms, DELAY_PROBE_TIME)) || + nla_put_msecs(skb, NDTPA_RETRANS_TIME, + NEIGH_VAR(parms, RETRANS_TIME)) || + nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, + NEIGH_VAR(parms, ANYCAST_DELAY)) || + nla_put_msecs(skb, NDTPA_PROXY_DELAY, + NEIGH_VAR(parms, PROXY_DELAY)) || + nla_put_msecs(skb, NDTPA_LOCKTIME, + NEIGH_VAR(parms, LOCKTIME))) goto nla_put_failure; return nla_nest_end(skb, nest); @@ -1875,6 +1875,7 @@ ndst.ndts_rcv_probes_ucast += st->rcv_probes_ucast; ndst.ndts_periodic_gc_runs += st->periodic_gc_runs; ndst.ndts_forced_gc_runs += st->forced_gc_runs; + ndst.ndts_table_fulls += st->table_fulls; } if (nla_put(skb, NDTA_STATS, sizeof(ndst), &ndst)) @@ -1886,7 +1887,8 @@ goto nla_put_failure; read_unlock_bh(&tbl->lock); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: read_unlock_bh(&tbl->lock); @@ -1919,7 +1921,8 @@ goto errout; read_unlock_bh(&tbl->lock); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; errout: read_unlock_bh(&tbl->lock); nlmsg_cancel(skb, nlh); @@ -1942,6 +1945,7 @@ [NDTPA_APP_PROBES] = { .type = NLA_U32 }, [NDTPA_UCAST_PROBES] = { .type = NLA_U32 }, [NDTPA_MCAST_PROBES] = { .type = NLA_U32 }, + [NDTPA_MCAST_REPROBES] = { .type = NLA_U32 }, [NDTPA_BASE_REACHABLE_TIME] = { .type = NLA_U64 }, [NDTPA_GC_STALETIME] = { .type = NLA_U64 }, [NDTPA_DELAY_PROBE_TIME] = { .type = NLA_U64 }, @@ -1957,7 +1961,8 @@ struct neigh_table *tbl; struct ndtmsg *ndtmsg; struct nlattr *tb[NDTA_MAX+1]; - int err; + bool found = false; + int err, tidx; err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX, nl_neightbl_policy); @@ -1970,19 +1975,21 @@ } ndtmsg = nlmsg_data(nlh); - read_lock(&neigh_tbl_lock); - for (tbl = neigh_tables; tbl; tbl = tbl->next) { + + for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) { + tbl = neigh_tables[tidx]; + if (!tbl) + continue; if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family) continue; - - if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) + if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) { + found = true; break; + } } - if (tbl == NULL) { - err = -ENOENT; - goto errout_locked; - } + if (!found) + return -ENOENT; /* * We acquire tbl->lock to be nice to the periodic timers and @@ -2015,49 +2022,78 @@ switch (i) { case NDTPA_QUEUE_LEN: - p->queue_len_bytes = nla_get_u32(tbp[i]) * - SKB_TRUESIZE(ETH_FRAME_LEN); + NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, + nla_get_u32(tbp[i]) * + SKB_TRUESIZE(ETH_FRAME_LEN)); break; case NDTPA_QUEUE_LENBYTES: - p->queue_len_bytes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, + nla_get_u32(tbp[i])); break; case NDTPA_PROXY_QLEN: - p->proxy_qlen = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, PROXY_QLEN, + nla_get_u32(tbp[i])); break; case NDTPA_APP_PROBES: - p->app_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, APP_PROBES, + nla_get_u32(tbp[i])); break; case NDTPA_UCAST_PROBES: - p->ucast_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, UCAST_PROBES, + nla_get_u32(tbp[i])); break; case NDTPA_MCAST_PROBES: - p->mcast_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, MCAST_PROBES, + nla_get_u32(tbp[i])); + break; + case NDTPA_MCAST_REPROBES: + NEIGH_VAR_SET(p, MCAST_REPROBES, + nla_get_u32(tbp[i])); break; case NDTPA_BASE_REACHABLE_TIME: - p->base_reachable_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, BASE_REACHABLE_TIME, + nla_get_msecs(tbp[i])); + /* update reachable_time as well, otherwise, the change will + * only be effective after the next time neigh_periodic_work + * decides to recompute it (can be multiple minutes) + */ + p->reachable_time = + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); break; case NDTPA_GC_STALETIME: - p->gc_staletime = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, GC_STALETIME, + nla_get_msecs(tbp[i])); break; case NDTPA_DELAY_PROBE_TIME: - p->delay_probe_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, DELAY_PROBE_TIME, + nla_get_msecs(tbp[i])); break; case NDTPA_RETRANS_TIME: - p->retrans_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, RETRANS_TIME, + nla_get_msecs(tbp[i])); break; case NDTPA_ANYCAST_DELAY: - p->anycast_delay = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, ANYCAST_DELAY, + nla_get_msecs(tbp[i])); break; case NDTPA_PROXY_DELAY: - p->proxy_delay = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, PROXY_DELAY, + nla_get_msecs(tbp[i])); break; case NDTPA_LOCKTIME: - p->locktime = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, LOCKTIME, + nla_get_msecs(tbp[i])); break; } } } + err = -ENOENT; + if ((tb[NDTA_THRESH1] || tb[NDTA_THRESH2] || + tb[NDTA_THRESH3] || tb[NDTA_GC_INTERVAL]) && + !net_eq(net, &init_net)) + goto errout_tbl_lock; + if (tb[NDTA_THRESH1]) tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]); @@ -2074,8 +2110,6 @@ errout_tbl_lock: write_unlock_bh(&tbl->lock); -errout_locked: - read_unlock(&neigh_tbl_lock); errout: return err; } @@ -2090,19 +2124,24 @@ family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; - read_lock(&neigh_tbl_lock); - for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) { + for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) { struct neigh_parms *p; + tbl = neigh_tables[tidx]; + if (!tbl) + continue; + if (tidx < tbl_skip || (family && tbl->family != family)) continue; if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, - NLM_F_MULTI) <= 0) + NLM_F_MULTI) < 0) break; - for (nidx = 0, p = tbl->parms.next; p; p = p->next) { + nidx = 0; + p = list_next_entry(&tbl->parms, list); + list_for_each_entry_from(p, &tbl->parms_list, list) { if (!net_eq(neigh_parms_net(p), net)) continue; @@ -2113,7 +2152,7 @@ NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, - NLM_F_MULTI) <= 0) + NLM_F_MULTI) < 0) goto out; next: nidx++; @@ -2122,7 +2161,6 @@ neigh_skip = 0; } out: - read_unlock(&neigh_tbl_lock); cb->args[0] = tidx; cb->args[1] = nidx; @@ -2174,7 +2212,8 @@ nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -2197,14 +2236,15 @@ ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; ndm->ndm_flags = pn->flags | NTF_PROXY; - ndm->ndm_type = NDA_DST; - ndm->ndm_ifindex = pn->dev->ifindex; + ndm->ndm_type = RTN_UNICAST; + ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0; ndm->ndm_state = NUD_NONE; if (nla_put(skb, NDA_DST, tbl->key_len, pn->key)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -2217,14 +2257,53 @@ __neigh_notify(neigh, RTM_NEWNEIGH, 0); } +static bool neigh_master_filtered(struct net_device *dev, int master_idx) +{ + struct net_device *master; + + if (!master_idx) + return false; + + master = netdev_master_upper_dev_get(dev); + if (!master || master->ifindex != master_idx) + return true; + + return false; +} + +static bool neigh_ifindex_filtered(struct net_device *dev, int filter_idx) +{ + if (filter_idx && dev->ifindex != filter_idx) + return true; + + return false; +} + static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); + const struct nlmsghdr *nlh = cb->nlh; + struct nlattr *tb[NDA_MAX + 1]; struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; struct neigh_hash_table *nht; + int filter_master_idx = 0, filter_idx = 0; + unsigned int flags = NLM_F_MULTI; + int err; + + err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL); + if (!err) { + if (tb[NDA_IFINDEX]) + filter_idx = nla_get_u32(tb[NDA_IFINDEX]); + + if (tb[NDA_MASTER]) + filter_master_idx = nla_get_u32(tb[NDA_MASTER]); + + if (filter_idx || filter_master_idx) + flags |= NLM_F_DUMP_FILTERED; + } rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); @@ -2237,12 +2316,16 @@ n = rcu_dereference_bh(n->next)) { if (!net_eq(dev_net(n->dev), net)) continue; + if (neigh_ifindex_filtered(n->dev, filter_idx)) + continue; + if (neigh_master_filtered(n->dev, filter_master_idx)) + continue; if (idx < s_idx) goto next; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, - NLM_F_MULTI) <= 0) { + flags) < 0) { rc = -1; goto out; } @@ -2272,14 +2355,14 @@ if (h > s_h) s_idx = 0; for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) { - if (dev_net(n->dev) != net) + if (pneigh_net(n) != net) continue; if (idx < s_idx) goto next; if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, - NLM_F_MULTI, tbl) <= 0) { + NLM_F_MULTI, tbl) < 0) { read_unlock_bh(&tbl->lock); rc = -1; goto out; @@ -2305,7 +2388,6 @@ int proxy = 0; int err; - read_lock(&neigh_tbl_lock); family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; /* check for full ndmsg structure presence, family member is @@ -2317,8 +2399,11 @@ s_t = cb->args[0]; - for (tbl = neigh_tables, t = 0; tbl; - tbl = tbl->next, t++) { + for (t = 0; t < NEIGH_NR_TABLES; t++) { + tbl = neigh_tables[t]; + + if (!tbl) + continue; if (t < s_t || (family && tbl->family != family)) continue; if (t > s_t) @@ -2331,7 +2416,6 @@ if (err < 0) break; } - read_unlock(&neigh_tbl_lock); cb->args[0] = t; return skb->len; @@ -2394,6 +2478,44 @@ } EXPORT_SYMBOL(__neigh_for_each_release); +int neigh_xmit(int index, struct net_device *dev, + const void *addr, struct sk_buff *skb) +{ + int err = -EAFNOSUPPORT; + if (likely(index < NEIGH_NR_TABLES)) { + struct neigh_table *tbl; + struct neighbour *neigh; + + tbl = neigh_tables[index]; + if (!tbl) + goto out; + rcu_read_lock_bh(); + neigh = __neigh_lookup_noref(tbl, addr, dev); + if (!neigh) + neigh = __neigh_create(tbl, addr, dev, false); + err = PTR_ERR(neigh); + if (IS_ERR(neigh)) { + rcu_read_unlock_bh(); + goto out_kfree_skb; + } + err = neigh->output(neigh, skb); + rcu_read_unlock_bh(); + } + else if (index == NEIGH_LINK_TABLE) { + err = dev_hard_header(skb, dev, ntohs(skb->protocol), + addr, NULL, skb->len); + if (err < 0) + goto out_kfree_skb; + err = dev_queue_xmit(skb); + } +out: + return err; +out_kfree_skb: + kfree_skb(skb); + goto out; +} +EXPORT_SYMBOL(neigh_xmit); + #ifdef CONFIG_PROC_FS static struct neighbour *neigh_get_first(struct seq_file *seq) @@ -2669,12 +2791,12 @@ 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 unresolved_discards\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 table_fulls\n"); return 0; } seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx " - "%08lx %08lx %08lx %08lx %08lx\n", + "%08lx %08lx %08lx %08lx %08lx %08lx\n", atomic_read(&tbl->entries), st->allocs, @@ -2691,7 +2813,8 @@ st->periodic_gc_runs, st->forced_gc_runs, - st->unres_discards + st->unres_discards, + st->table_fulls ); return 0; @@ -2758,23 +2881,22 @@ 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); } EXPORT_SYMBOL(neigh_app_ns); -#endif /* CONFIG_ARPD */ #ifdef CONFIG_SYSCTL static int zero; +static int int_max = INT_MAX; static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN); -static int proc_unres_qlen(ctl_table *ctl, int write, void __user *buffer, - size_t *lenp, loff_t *ppos) +static int proc_unres_qlen(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { int size, ret; - ctl_table tmp = *ctl; + struct ctl_table tmp = *ctl; tmp.extra1 = &zero; tmp.extra2 = &unres_qlen_max; @@ -2788,125 +2910,193 @@ return ret; } -enum { - NEIGH_VAR_MCAST_PROBE, - NEIGH_VAR_UCAST_PROBE, - NEIGH_VAR_APP_PROBE, - NEIGH_VAR_RETRANS_TIME, - NEIGH_VAR_BASE_REACHABLE_TIME, - NEIGH_VAR_DELAY_PROBE_TIME, - NEIGH_VAR_GC_STALETIME, - NEIGH_VAR_QUEUE_LEN, - NEIGH_VAR_QUEUE_LEN_BYTES, - NEIGH_VAR_PROXY_QLEN, - NEIGH_VAR_ANYCAST_DELAY, - NEIGH_VAR_PROXY_DELAY, - NEIGH_VAR_LOCKTIME, - NEIGH_VAR_RETRANS_TIME_MS, - NEIGH_VAR_BASE_REACHABLE_TIME_MS, - NEIGH_VAR_GC_INTERVAL, - NEIGH_VAR_GC_THRESH1, - NEIGH_VAR_GC_THRESH2, - NEIGH_VAR_GC_THRESH3, - NEIGH_VAR_MAX -}; +static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, + int family) +{ + switch (family) { + case AF_INET: + return __in_dev_arp_parms_get_rcu(dev); + case AF_INET6: + return __in6_dev_nd_parms_get_rcu(dev); + } + return NULL; +} + +static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, + int index) +{ + struct net_device *dev; + int family = neigh_parms_family(p); + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + struct neigh_parms *dst_p = + neigh_get_dev_parms_rcu(dev, family); + + if (dst_p && !test_bit(index, dst_p->data_state)) + dst_p->data[index] = p->data[index]; + } + rcu_read_unlock(); +} + +static void neigh_proc_update(struct ctl_table *ctl, int write) +{ + struct net_device *dev = ctl->extra1; + struct neigh_parms *p = ctl->extra2; + struct net *net = neigh_parms_net(p); + int index = (int *) ctl->data - p->data; + + if (!write) + return; + + set_bit(index, p->data_state); + if (!dev) /* NULL dev means this is default value */ + neigh_copy_dflt_parms(net, p, index); +} + +static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + struct ctl_table tmp = *ctl; + int ret; + + tmp.extra1 = &zero; + tmp.extra2 = &int_max; + + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + neigh_proc_update(ctl, write); + return ret; +} + +int neigh_proc_dointvec(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec); + +int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec_jiffies); + +static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} + +int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies); + +static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_unres_qlen(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} + +static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + struct neigh_parms *p = ctl->extra2; + int ret; + + if (strcmp(ctl->procname, "base_reachable_time") == 0) + ret = neigh_proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); + else if (strcmp(ctl->procname, "base_reachable_time_ms") == 0) + ret = neigh_proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); + else + ret = -1; + + if (write && ret == 0) { + /* update reachable_time as well, otherwise, the change will + * only be effective after the next time neigh_periodic_work + * decides to recompute it + */ + p->reachable_time = + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); + } + return ret; +} + +#define NEIGH_PARMS_DATA_OFFSET(index) \ + (&((struct neigh_parms *) 0)->data[index]) + +#define NEIGH_SYSCTL_ENTRY(attr, data_attr, name, mval, proc) \ + [NEIGH_VAR_ ## attr] = { \ + .procname = name, \ + .data = NEIGH_PARMS_DATA_OFFSET(NEIGH_VAR_ ## data_attr), \ + .maxlen = sizeof(int), \ + .mode = mval, \ + .proc_handler = proc, \ + } + +#define NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_zero_intmax) + +#define NEIGH_SYSCTL_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_jiffies) + +#define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies) + +#define NEIGH_SYSCTL_MS_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_ms_jiffies) + +#define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies) + +#define NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(attr, data_attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_unres_qlen) static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1]; } neigh_sysctl_template __read_mostly = { .neigh_vars = { - [NEIGH_VAR_MCAST_PROBE] = { - .procname = "mcast_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - [NEIGH_VAR_UCAST_PROBE] = { - .procname = "ucast_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - [NEIGH_VAR_APP_PROBE] = { - .procname = "app_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - [NEIGH_VAR_RETRANS_TIME] = { - .procname = "retrans_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_BASE_REACHABLE_TIME] = { - .procname = "base_reachable_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - [NEIGH_VAR_DELAY_PROBE_TIME] = { - .procname = "delay_first_probe_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - [NEIGH_VAR_GC_STALETIME] = { - .procname = "gc_stale_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - [NEIGH_VAR_QUEUE_LEN] = { - .procname = "unres_qlen", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_unres_qlen, - }, - [NEIGH_VAR_QUEUE_LEN_BYTES] = { - .procname = "unres_qlen_bytes", - .maxlen = sizeof(int), - .mode = 0644, - .extra1 = &zero, - .proc_handler = proc_dointvec_minmax, - }, - [NEIGH_VAR_PROXY_QLEN] = { - .procname = "proxy_qlen", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - [NEIGH_VAR_ANYCAST_DELAY] = { - .procname = "anycast_delay", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_PROXY_DELAY] = { - .procname = "proxy_delay", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_LOCKTIME] = { - .procname = "locktime", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_RETRANS_TIME_MS] = { - .procname = "retrans_time_ms", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_ms_jiffies, - }, - [NEIGH_VAR_BASE_REACHABLE_TIME_MS] = { - .procname = "base_reachable_time_ms", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_ms_jiffies, - }, + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_REPROBES, "mcast_resolicit"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(GC_STALETIME, "gc_stale_time"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(QUEUE_LEN_BYTES, "unres_qlen_bytes"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(PROXY_QLEN, "proxy_qlen"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(ANYCAST_DELAY, "anycast_delay"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(PROXY_DELAY, "proxy_delay"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(LOCKTIME, "locktime"), + NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(QUEUE_LEN, QUEUE_LEN_BYTES, "unres_qlen"), + NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(RETRANS_TIME_MS, RETRANS_TIME, "retrans_time_ms"), + NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(BASE_REACHABLE_TIME_MS, BASE_REACHABLE_TIME, "base_reachable_time_ms"), [NEIGH_VAR_GC_INTERVAL] = { .procname = "gc_interval", .maxlen = sizeof(int), @@ -2917,50 +3107,48 @@ .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_GC_THRESH2] = { .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_GC_THRESH3] = { .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, {}, }, }; int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, - char *p_name, proc_handler *handler) + proc_handler *handler) { + int i; struct neigh_sysctl_table *t; - const char *dev_name_source = NULL; + const char *dev_name_source; char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ]; + char *p_name; t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL); if (!t) goto err; - t->neigh_vars[NEIGH_VAR_MCAST_PROBE].data = &p->mcast_probes; - t->neigh_vars[NEIGH_VAR_UCAST_PROBE].data = &p->ucast_probes; - t->neigh_vars[NEIGH_VAR_APP_PROBE].data = &p->app_probes; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME].data = &p->retrans_time; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].data = &p->base_reachable_time; - t->neigh_vars[NEIGH_VAR_DELAY_PROBE_TIME].data = &p->delay_probe_time; - t->neigh_vars[NEIGH_VAR_GC_STALETIME].data = &p->gc_staletime; - t->neigh_vars[NEIGH_VAR_QUEUE_LEN].data = &p->queue_len_bytes; - t->neigh_vars[NEIGH_VAR_QUEUE_LEN_BYTES].data = &p->queue_len_bytes; - t->neigh_vars[NEIGH_VAR_PROXY_QLEN].data = &p->proxy_qlen; - t->neigh_vars[NEIGH_VAR_ANYCAST_DELAY].data = &p->anycast_delay; - t->neigh_vars[NEIGH_VAR_PROXY_DELAY].data = &p->proxy_delay; - t->neigh_vars[NEIGH_VAR_LOCKTIME].data = &p->locktime; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].data = &p->retrans_time; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].data = &p->base_reachable_time; + for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) { + t->neigh_vars[i].data += (long) p; + t->neigh_vars[i].extra1 = dev; + t->neigh_vars[i].extra2 = p; + } if (dev) { dev_name_source = dev->name; @@ -2968,33 +3156,53 @@ memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0, sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL])); } else { + struct neigh_table *tbl = p->tbl; dev_name_source = "default"; - t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = (int *)(p + 1); - t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = (int *)(p + 1) + 1; - t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = (int *)(p + 1) + 2; - t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = (int *)(p + 1) + 3; + t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = &tbl->gc_interval; + t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = &tbl->gc_thresh1; + t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = &tbl->gc_thresh2; + t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = &tbl->gc_thresh3; } - if (handler) { /* RetransTime */ t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME].extra1 = dev; /* ReachableTime */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].extra1 = dev; /* RetransTime (in milliseconds)*/ t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].extra1 = dev; /* ReachableTime (in milliseconds) */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev; + } else { + /* Those handlers will update p->reachable_time after + * base_reachable_time(_ms) is set to ensure the new timer starts being + * applied after the next neighbour update instead of waiting for + * neigh_periodic_work to update its value (can be multiple minutes) + * So any handler that replaces them should do this as well + */ + /* ReachableTime */ + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = + neigh_proc_base_reachable_time; + /* ReachableTime (in milliseconds) */ + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = + neigh_proc_base_reachable_time; } /* Don't export sysctls to unprivileged users */ if (neigh_parms_net(p)->user_ns != &init_user_ns) t->neigh_vars[0].procname = NULL; + switch (neigh_parms_family(p)) { + case AF_INET: + p_name = "ipv4"; + break; + case AF_INET6: + p_name = "ipv6"; + break; + default: + BUG(); + } + snprintf(neigh_path, sizeof(neigh_path), "net/%s/neigh/%s", p_name, dev_name_source); t->sysctl_header = @@ -3039,4 +3247,3 @@ } subsys_initcall(neigh_init); -