neighbour.c

Linux Kernel 2.6.9 for OMAP1710

					       neigh->ha, NULL, skb->len);
			read_unlock_bh(&neigh->lock);
		}
		if (err >= 0)
			rc = neigh->ops->queue_xmit(skb);
		else
			goto out_kfree_skb;
	}
out:
	return rc;
discard:
	NEIGH_PRINTK1("neigh_resolve_output: dst=%p neigh=%p\n",
		      dst, dst ? dst->neighbour : NULL);
out_kfree_skb:
	rc = -EINVAL;
	kfree_skb(skb);
	goto out;
}

/* As fast as possible without hh cache */

int neigh_connected_output(struct sk_buff *skb)
{
	int err;
	struct dst_entry *dst = skb->dst;
	struct neighbour *neigh = dst->neighbour;
	struct net_device *dev = neigh->dev;

	__skb_pull(skb, skb->nh.raw - skb->data);

	read_lock_bh(&neigh->lock);
	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);
	else {
		err = -EINVAL;
		kfree_skb(skb);
	}
	return err;
}

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;

	spin_lock(&tbl->proxy_queue.lock);

	skb = tbl->proxy_queue.next;

	while (skb != (struct sk_buff *)&tbl->proxy_queue) {
		struct sk_buff *back = skb;
		long tdif = back->stamp.tv_usec - now;

		skb = skb->next;
		if (tdif <= 0) {
			struct net_device *dev = back->dev;
			__skb_unlink(back, &tbl->proxy_queue);
			if (tbl->proxy_redo && netif_running(dev))
				tbl->proxy_redo(back);
			else
				kfree_skb(back);

			dev_put(dev);
		} else if (!sched_next || tdif < sched_next)
			sched_next = tdif;
	}
	del_timer(&tbl->proxy_timer);
	if (sched_next)
		mod_timer(&tbl->proxy_timer, jiffies + sched_next);
	spin_unlock(&tbl->proxy_queue.lock);
}

void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
		    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) {
		kfree_skb(skb);
		return;
	}
	skb->stamp.tv_sec  = LOCALLY_ENQUEUED;
	skb->stamp.tv_usec = sched_next;

	spin_lock(&tbl->proxy_queue.lock);
	if (del_timer(&tbl->proxy_timer)) {
		if (time_before(tbl->proxy_timer.expires, sched_next))
			sched_next = tbl->proxy_timer.expires;
	}
	dst_release(skb->dst);
	skb->dst = NULL;
	dev_hold(skb->dev);
	__skb_queue_tail(&tbl->proxy_queue, skb);
	mod_timer(&tbl->proxy_timer, sched_next);
	spin_unlock(&tbl->proxy_queue.lock);
}


struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
				      struct neigh_table *tbl)
{
	struct neigh_parms *p = kmalloc(sizeof(*p), GFP_KERNEL);

	if (p) {
		memcpy(p, &tbl->parms, sizeof(*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 && dev->neigh_setup && dev->neigh_setup(dev, p)) {
			kfree(p);
			return NULL;
		}
		p->sysctl_table = NULL;
		write_lock_bh(&tbl->lock);
		p->next		= tbl->parms.next;
		tbl->parms.next = p;
		write_unlock_bh(&tbl->lock);
	}
	return p;
}

static void neigh_rcu_free_parms(struct rcu_head *head)
{
	struct neigh_parms *parms =
		container_of(head, struct neigh_parms, rcu_head);

	neigh_parms_put(parms);
}

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);
			call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
			return;
		}
	}
	write_unlock_bh(&tbl->lock);
	NEIGH_PRINTK1("neigh_parms_release: not found\n");
}

void neigh_parms_destroy(struct neigh_parms *parms)
{
	kfree(parms);
}


void neigh_table_init(struct neigh_table *tbl)
{
	unsigned long now = jiffies;
	unsigned long phsize;

	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);

	if (!tbl->kmem_cachep)
		tbl->kmem_cachep = kmem_cache_create(tbl->id,
						     tbl->entry_size,
						     0, SLAB_HWCACHE_ALIGN,
						     NULL, NULL);

	if (!tbl->kmem_cachep)
		panic("cannot create neighbour cache");

	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) 
		panic("cannot create neighbour proc dir entry");
	tbl->pde->proc_fops = &neigh_stat_seq_fops;
	tbl->pde->data = tbl;
#endif

	tbl->hash_mask = 1;
	tbl->hash_buckets = neigh_hash_alloc(tbl->hash_mask + 1);

	phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *);
	tbl->phash_buckets = kmalloc(phsize, GFP_KERNEL);

	if (!tbl->hash_buckets || !tbl->phash_buckets)
		panic("cannot allocate neighbour cache hashes");

	memset(tbl->phash_buckets, 0, phsize);

	get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd));

	tbl->lock	       = RW_LOCK_UNLOCKED;
	init_timer(&tbl->gc_timer);
	tbl->gc_timer.data     = (unsigned long)tbl;
	tbl->gc_timer.function = neigh_periodic_timer;
	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);

	tbl->last_flush = now;
	tbl->last_rand	= now + tbl->parms.reachable_time * 20;
	write_lock(&neigh_tbl_lock);
	tbl->next	= neigh_tables;
	neigh_tables	= tbl;
	write_unlock(&neigh_tbl_lock);
}

int neigh_table_clear(struct neigh_table *tbl)
{
	struct neigh_table **tp;

	/* It is not clean... Fix it to unload IPv6 module safely */
	del_timer_sync(&tbl->gc_timer);
	del_timer_sync(&tbl->proxy_timer);
	pneigh_queue_purge(&tbl->proxy_queue);
	neigh_ifdown(tbl, NULL);
	if (tbl->entries)
		printk(KERN_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);

	neigh_hash_free(tbl->hash_buckets, tbl->hash_mask + 1);
	tbl->hash_buckets = NULL;

	kfree(tbl->phash_buckets);
	tbl->phash_buckets = NULL;

	return 0;
}

int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct ndmsg *ndm = NLMSG_DATA(nlh);
	struct rtattr **nda = arg;
	struct neigh_table *tbl;
	struct net_device *dev = NULL;
	int err = -ENODEV;

	if (ndm->ndm_ifindex &&
	    (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL)
		goto out;

	read_lock(&neigh_tbl_lock);
	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
		struct neighbour *n;

		if (tbl->family != ndm->ndm_family)
			continue;
		read_unlock(&neigh_tbl_lock);

		err = -EINVAL;
		if (!nda[NDA_DST - 1] ||
		    nda[NDA_DST - 1]->rta_len != RTA_LENGTH(tbl->key_len))
			goto out_dev_put;

		if (ndm->ndm_flags & NTF_PROXY) {
			err = pneigh_delete(tbl,
					    RTA_DATA(nda[NDA_DST - 1]), dev);
			goto out_dev_put;
		}

		if (!dev)
			goto out;

		n = neigh_lookup(tbl, RTA_DATA(nda[NDA_DST - 1]), dev);
		if (n) {
			err = neigh_update(n, NULL, NUD_FAILED, 
					   NEIGH_UPDATE_F_OVERRIDE|
					   NEIGH_UPDATE_F_ADMIN);
			neigh_release(n);
		}
		goto out_dev_put;
	}
	read_unlock(&neigh_tbl_lock);
	err = -EADDRNOTAVAIL;
out_dev_put:
	if (dev)
		dev_put(dev);
out:
	return err;
}

int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct ndmsg *ndm = NLMSG_DATA(nlh);
	struct rtattr **nda = arg;
	struct neigh_table *tbl;
	struct net_device *dev = NULL;
	int err = -ENODEV;

	if (ndm->ndm_ifindex &&
	    (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL)
		goto out;

	read_lock(&neigh_tbl_lock);
	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
		int override = 1;
		struct neighbour *n;

		if (tbl->family != ndm->ndm_family)
			continue;
		read_unlock(&neigh_tbl_lock);

		err = -EINVAL;
		if (!nda[NDA_DST - 1] ||
		    nda[NDA_DST - 1]->rta_len != RTA_LENGTH(tbl->key_len))
			goto out_dev_put;
		if (ndm->ndm_flags & NTF_PROXY) {
			err = -ENOBUFS;
			if (pneigh_lookup(tbl,
					  RTA_DATA(nda[NDA_DST - 1]), dev, 1))
				err = 0;
			goto out_dev_put;
		}
		err = -EINVAL;
		if (!dev)
			goto out;
		if (nda[NDA_LLADDR - 1] &&
		    nda[NDA_LLADDR - 1]->rta_len != RTA_LENGTH(dev->addr_len))
			goto out_dev_put;
		err = 0;
		n = neigh_lookup(tbl, RTA_DATA(nda[NDA_DST - 1]), dev);
		if (n) {
			if (nlh->nlmsg_flags & NLM_F_EXCL)
				err = -EEXIST;
			override = nlh->nlmsg_flags & NLM_F_REPLACE;
		} else if (!(nlh->nlmsg_flags & NLM_F_CREATE))
			err = -ENOENT;
		else {
			n = __neigh_lookup_errno(tbl, RTA_DATA(nda[NDA_DST - 1]),
						 dev);
			if (IS_ERR(n)) {
				err = PTR_ERR(n);
				n = NULL;
			}
		}
		if (!err) {
			err = neigh_update(n, nda[NDA_LLADDR - 1] ?
						RTA_DATA(nda[NDA_LLADDR - 1]) :
						NULL,
					   ndm->ndm_state,
					   (override ? NEIGH_UPDATE_F_OVERRIDE : 0) |
					   NEIGH_UPDATE_F_ADMIN);
		}
		if (n)
			neigh_release(n);
		goto out_dev_put;
	}

	read_unlock(&neigh_tbl_lock);
	err = -EADDRNOTAVAIL;
out_dev_put:
	if (dev)
		dev_put(dev);
out:
	return err;
}


static int neigh_fill_info(struct sk_buff *skb, struct neighbour *n,
			   u32 pid, u32 seq, int event)
{
	unsigned long now = jiffies;
	unsigned char *b = skb->tail;
	struct nda_cacheinfo ci;
	int locked = 0;
	struct nlmsghdr *nlh = NLMSG_PUT(skb, pid, seq, event,
					 sizeof(struct ndmsg));
	struct ndmsg *ndm = NLMSG_DATA(nlh);

	ndm->ndm_family	 = n->ops->family;
	ndm->ndm_flags	 = n->flags;
	ndm->ndm_type	 = n->type;
	ndm->ndm_ifindex = n->dev->ifindex;
	RTA_PUT(skb, NDA_DST, n->tbl->key_len, n->primary_key);
	read_lock_bh(&n->lock);
	locked		 = 1;
	ndm->ndm_state	 = n->nud_state;
	if (n->nud_state & NUD_VALID)
		RTA_PUT(skb, NDA_LLADDR, n->dev->addr_len, n->ha);
	ci.ndm_used	 = now - n->used;
	ci.ndm_confirmed = now - n->confirmed;
	ci.ndm_updated	 = now - n->updated;
	ci.ndm_refcnt	 = atomic_read(&n->refcnt) - 1;
	read_unlock_bh(&n->lock);
	locked		 = 0;
	RTA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci);
	nlh->nlmsg_len	 = skb->tail - b;
	return skb->len;

nlmsg_failure:
rtattr_failure:
	if (locked)
		read_unlock_bh(&n->lock);
	skb_trim(skb, b - skb->data);
	return -1;
}


static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
			    struct netlink_callback *cb)
{
	struct neighbour *n;
	int rc, h, s_h = cb->args[1];
	int idx, s_idx = idx = cb->args[2];

	for (h = 0; h <= tbl->hash_mask; h++) {
		if (h < s_h)
			continue;
		if (h > s_h)
			s_idx = 0;
		read_lock_bh(&tbl->lock);
		for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next, idx++) {
			if (idx < s_idx)
				continue;
			if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid,
					    cb->nlh->nlmsg_seq,
					    RTM_NEWNEIGH) <= 0) {
				read_unlock_bh(&tbl->lock);
				rc = -1;
				goto out;
			}
		}
		read_unlock_bh(&tbl->lock);
	}
	rc = skb->len;
out:
	cb->args[1] = h;
	cb->args[2] = idx;
	return rc;
}

int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct neigh_table *tbl;
	int t, family, s_t;

	read_lock(&neigh_tbl_lock);
	family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family;
	s_t = cb->args[0];

	for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) {
		if (t < s_t || (family && tbl->family != family))
			continue;
		if (t > s_t)
			memset(&cb->args[1], 0, sizeof(cb->args) -
						sizeof(cb->args[0]));
		if (neigh_dump_table(tbl, skb, cb) < 0)
			break;
	}
	read_unlock(&neigh_tbl_lock);

	cb->args[0] = t;
	return skb->len;
}

void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie)
{
	int chain;

	read_lock_bh(&tbl->lock);
	for (chain = 0; chain <= tbl->hash_mask; chain++) {
		struct neighbour *n;

		for (n = tbl->hash_buckets[chain]; n; n = n->next)
			cb(n, cookie);
	}
	read_unlock_bh(&tbl->lock);
}
EXPORT_SYMBOL(neigh_for_each);

/* The tbl->lock must be held as a writer and BH disabled. */
void __neigh_for_each_release(struct neigh_table *tbl,
			      int (*cb)(struct neighbour *))
{
	int chain;

	for (chain = 0; chain <= tbl->hash_mask; chain++) {
		struct neighbour *n, **np;

		np = &tbl->hash_buckets[chain];
		while ((n = *np) != NULL) {
			int release;

			write_lock(&n->lock);
			release = cb(n);
			if (release) {
				*np = n->next;
				n->dead = 1;
			} else
				np = &n->next;
			write_unlock(&n->lock);
			if (release)
				neigh_release(n);
		}
	}
}
EXPORT_SYMBOL(__neigh_for_each_release);

#ifdef CONFIG_PROC_FS

static struct neighbour *neigh_get_first(struct seq_file *seq)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;
	struct neighbour *n = NULL;
	int bucket = state->bucket;

	state->flags &= ~NEIGH_SEQ_IS_PNEIGH;
	for (bucket = 0; bucket <= tbl->hash_mask; bucket++) {
		n = tbl->hash_buckets[bucket];

		while (n) {
			if (state->neigh_sub_iter) {
				loff_t fakep = 0;
				void *v;

				v = state->neigh_sub_iter(state, n, &fakep);
				if (!v)
					goto next;
			}
			if (!(state->flags & NEIGH_SEQ_SKIP_NOARP))
				break;
			if (n->nud_state & ~NUD_NOARP)
				break;
		next:
			n = n->next;
		}

		if (n)
			break;
	}
	state->bucket = bucket;

	return n;
}

static struct neighbour *neigh_get_next(struct seq_file *seq,
					struct neighbour *n,
					loff_t *pos)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;

	if (state->neigh_sub_iter) {
		void *v = state->neigh_sub_iter(state, n, pos);
		if (v)
			return n;
	}
	n = n->next;

	while (1) {
		while (n) {
			if (state->neigh_sub_iter) {