neighbour.c

Linux Kernel 2.6.9 for OMAP1710

		printk(KERN_WARNING
		       "Destroying alive neighbour %p\n", neigh);
		dump_stack();
		return;
	}

	if (neigh_del_timer(neigh))
		printk(KERN_WARNING "Impossible event.\n");

	while ((hh = neigh->hh) != NULL) {
		neigh->hh = hh->hh_next;
		hh->hh_next = NULL;
		write_lock_bh(&hh->hh_lock);
		hh->hh_output = neigh_blackhole;
		write_unlock_bh(&hh->hh_lock);
		if (atomic_dec_and_test(&hh->hh_refcnt))
			kfree(hh);
	}

	if (neigh->ops && neigh->ops->destructor)
		(neigh->ops->destructor)(neigh);

	skb_queue_purge(&neigh->arp_queue);

	dev_put(neigh->dev);
	neigh_parms_put(neigh->parms);

	NEIGH_PRINTK2("neigh %p is destroyed.\n", neigh);

	neigh_glbl_allocs--;
	neigh->tbl->entries--;
	kmem_cache_free(neigh->tbl->kmem_cachep, neigh);
}

/* Neighbour state is suspicious;
   disable fast path.

   Called with write_locked neigh.
 */
static void neigh_suspect(struct neighbour *neigh)
{
	struct hh_cache *hh;

	NEIGH_PRINTK2("neigh %p is suspected.\n", neigh);

	neigh->output = neigh->ops->output;

	for (hh = neigh->hh; hh; hh = hh->hh_next)
		hh->hh_output = neigh->ops->output;
}

/* Neighbour state is OK;
   enable fast path.

   Called with write_locked neigh.
 */
static void neigh_connect(struct neighbour *neigh)
{
	struct hh_cache *hh;

	NEIGH_PRINTK2("neigh %p is connected.\n", neigh);

	neigh->output = neigh->ops->connected_output;

	for (hh = neigh->hh; hh; hh = hh->hh_next)
		hh->hh_output = neigh->ops->hh_output;
}

static void neigh_periodic_timer(unsigned long arg)
{
	struct neigh_table *tbl = (struct neigh_table *)arg;
	struct neighbour *n, **np;
	unsigned long expire, now = jiffies;

	NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs);

	write_lock(&tbl->lock);

	/*
	 *	periodically recompute ReachableTime from random function
	 */

	if (time_after(now, tbl->last_rand + 300 * HZ)) {
		struct neigh_parms *p;
		tbl->last_rand = now;
		for (p = &tbl->parms; p; p = p->next)
			p->reachable_time =
				neigh_rand_reach_time(p->base_reachable_time);
	}

	np = &tbl->hash_buckets[tbl->hash_chain_gc];
	tbl->hash_chain_gc = ((tbl->hash_chain_gc + 1) & tbl->hash_mask);

	while ((n = *np) != NULL) {
		unsigned int state;

		write_lock(&n->lock);

		state = n->nud_state;
		if (state & (NUD_PERMANENT | NUD_IN_TIMER)) {
			write_unlock(&n->lock);
			goto next_elt;
		}

		if (time_before(n->used, n->confirmed))
			n->used = n->confirmed;

		if (atomic_read(&n->refcnt) == 1 &&
		    (state == NUD_FAILED ||
		     time_after(now, n->used + n->parms->gc_staletime))) {
			*np = n->next;
			n->dead = 1;
			write_unlock(&n->lock);
			neigh_release(n);
			continue;
		}
		write_unlock(&n->lock);

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.
	 */
	expire = tbl->parms.base_reachable_time >> 1;
	expire /= (tbl->hash_mask + 1);
	if (!expire)
		expire = 1;

 	mod_timer(&tbl->gc_timer, now + expire);

	write_unlock(&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);
}


/* Called when a timer expires for a neighbour entry. */

static void neigh_timer_handler(unsigned long arg)
{
	unsigned long now, next;
	struct neighbour *neigh = (struct neighbour *)arg;
	unsigned state;
	int notify = 0;

	write_lock(&neigh->lock);

	state = neigh->nud_state;
	now = jiffies;
	next = now + HZ;

	if (!(state & NUD_IN_TIMER)) {
#ifndef CONFIG_SMP
		printk(KERN_WARNING "neigh: timer & !nud_in_timer\n");
#endif
		goto out;
	}

	if (state & NUD_REACHABLE) {
		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;
		} else if (time_before_eq(now,
					  neigh->used + neigh->parms->delay_probe_time)) {
			NEIGH_PRINTK2("neigh %p is delayed.\n", neigh);
			neigh->nud_state = NUD_DELAY;
			neigh_suspect(neigh);
			next = now + neigh->parms->delay_probe_time;
		} else {
			NEIGH_PRINTK2("neigh %p is suspected.\n", neigh);
			neigh->nud_state = NUD_STALE;
			neigh_suspect(neigh);
		}
	} else if (state & NUD_DELAY) {
		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;
			neigh_connect(neigh);
			next = neigh->confirmed + neigh->parms->reachable_time;
		} else {
			NEIGH_PRINTK2("neigh %p is probed.\n", neigh);
			neigh->nud_state = NUD_PROBE;
			atomic_set(&neigh->probes, 0);
			next = now + neigh->parms->retrans_time;
		}
	} else {
		/* NUD_PROBE|NUD_INCOMPLETE */
		next = now + neigh->parms->retrans_time;
	}

	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;
		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);
	}

	if (neigh->nud_state & NUD_IN_TIMER) {
		neigh_hold(neigh);
		if (time_before(next, jiffies + HZ/2))
			next = jiffies + HZ/2;
		neigh->timer.expires = next;
		add_timer(&neigh->timer);
	}
	if (neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) {
		struct sk_buff *skb = skb_peek(&neigh->arp_queue);
		/* keep skb alive even if arp_queue overflows */
		if (skb)
			skb_get(skb);
		write_unlock(&neigh->lock);
		neigh->ops->solicit(neigh, skb);
		atomic_inc(&neigh->probes);
		if (skb)
			kfree_skb(skb);
	} else {
out:
		write_unlock(&neigh->lock);
	}

#ifdef CONFIG_ARPD
	if (notify && neigh->parms->app_probes)
		neigh_app_notify(neigh);
#endif
	neigh_release(neigh);
}

int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
{
	int rc;
	unsigned long now;

	write_lock_bh(&neigh->lock);

	rc = 0;
	if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
		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_hold(neigh);
			neigh->timer.expires = now + 1;
			add_timer(&neigh->timer);
		} else {
			neigh->nud_state = NUD_FAILED;
			write_unlock_bh(&neigh->lock);

			if (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->timer.expires = jiffies + neigh->parms->delay_probe_time;
		add_timer(&neigh->timer);
	}

	if (neigh->nud_state == NUD_INCOMPLETE) {
		if (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);
				kfree_skb(buff);
			}
			__skb_queue_tail(&neigh->arp_queue, skb);
		}
		rc = 1;
	}
out_unlock_bh:
	write_unlock_bh(&neigh->lock);
	return rc;
}

static __inline__ 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;

	if (update) {
		for (hh = neigh->hh; hh; hh = hh->hh_next) {
			write_lock_bh(&hh->hh_lock);
			update(hh, neigh->dev, neigh->ha);
			write_unlock_bh(&hh->hh_lock);
		}
	}
}



/* Generic update routine.
   -- lladdr is new lladdr or NULL, if it is not supplied.
   -- new    is new state.
   -- flags
	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 
				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 
				NTF_ROUTER flag.
	NEIGH_UPDATE_F_ISROUTER	indicates if the neighbour is known as
				a router.

   Caller MUST hold reference count on the entry.
 */

int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
		 u32 flags)
{
	u8 old;
	int err;
#ifdef CONFIG_ARPD
	int notify = 0;
#endif
	struct net_device *dev;
	int update_isrouter = 0;

	write_lock_bh(&neigh->lock);

	dev    = neigh->dev;
	old    = neigh->nud_state;
	err    = -EPERM;

	if (!(flags & NEIGH_UPDATE_F_ADMIN) && 
	    (old & (NUD_NOARP | NUD_PERMANENT)))
		goto out;

	if (!(new & NUD_VALID)) {
		neigh_del_timer(neigh);
		if (old & NUD_CONNECTED)
			neigh_suspect(neigh);
		neigh->nud_state = new;
		err = 0;
#ifdef CONFIG_ARPD
		notify = old & NUD_VALID;
#endif
		goto out;
	}

	/* Compare new lladdr with cached one */
	if (!dev->addr_len) {
		/* First case: device needs no address. */
		lladdr = neigh->ha;
	} else if (lladdr) {
		/* The second case: if something is already cached
		   and a new address is proposed:
		   - compare new & old
		   - if they are different, check override flag
		 */
		if ((old & NUD_VALID) && 
		    !memcmp(lladdr, neigh->ha, dev->addr_len))
			lladdr = neigh->ha;
	} else {
		/* No address is supplied; if we know something,
		   use it, otherwise discard the request.
		 */
		err = -EINVAL;
		if (!(old & NUD_VALID))
			goto out;
		lladdr = neigh->ha;
	}

	if (new & NUD_CONNECTED)
		neigh->confirmed = jiffies;
	neigh->updated = jiffies;

	/* If entry was valid and address is not changed,
	   do not change entry state, if new one is STALE.
	 */
	err = 0;
	update_isrouter = flags & NEIGH_UPDATE_F_OVERRIDE_ISROUTER;
	if (old & NUD_VALID) {
		if (lladdr != neigh->ha && !(flags & NEIGH_UPDATE_F_OVERRIDE)) {
			update_isrouter = 0;
			if ((flags & NEIGH_UPDATE_F_WEAK_OVERRIDE) &&
			    (old & NUD_CONNECTED)) {
				lladdr = neigh->ha;
				new = NUD_STALE;
			} else
				goto out;
		} else {
			if (lladdr == neigh->ha && new == NUD_STALE &&
			    ((flags & NEIGH_UPDATE_F_WEAK_OVERRIDE) ||
			     (old & NUD_CONNECTED))
			    )
				new = old;
		}
	}

	if (new != old) {
		neigh_del_timer(neigh);
		if (new & NUD_IN_TIMER) {
			neigh_hold(neigh);
			neigh->timer.expires = jiffies + 
						((new & NUD_REACHABLE) ? 
						 neigh->parms->reachable_time : 0);
			add_timer(&neigh->timer);
		}
		neigh->nud_state = new;
	}

	if (lladdr != neigh->ha) {
		memcpy(&neigh->ha, lladdr, dev->addr_len);
		neigh_update_hhs(neigh);
		if (!(new & NUD_CONNECTED))
			neigh->confirmed = jiffies -
				      (neigh->parms->base_reachable_time << 1);
#ifdef CONFIG_ARPD
		notify = 1;
#endif
	}
	if (new == old)
		goto out;
	if (new & NUD_CONNECTED)
		neigh_connect(neigh);
	else
		neigh_suspect(neigh);
	if (!(old & NUD_VALID)) {
		struct sk_buff *skb;

		/* Again: avoid dead loop if something went wrong */

		while (neigh->nud_state & NUD_VALID &&
		       (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) {
			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;
			n1->output(skb);
			write_lock_bh(&neigh->lock);
		}
		skb_queue_purge(&neigh->arp_queue);
	}
out:
	if (update_isrouter) {
		neigh->flags = (flags & NEIGH_UPDATE_F_ISROUTER) ?
			(neigh->flags | NTF_ROUTER) :
			(neigh->flags & ~NTF_ROUTER);
	}
	write_unlock_bh(&neigh->lock);
#ifdef CONFIG_ARPD
	if (notify && neigh->parms->app_probes)
		neigh_app_notify(neigh);
#endif
	return err;
}

struct neighbour *neigh_event_ns(struct neigh_table *tbl,
				 u8 *lladdr, void *saddr,
				 struct net_device *dev)
{
	struct neighbour *neigh = __neigh_lookup(tbl, saddr, dev,
						 lladdr || !dev->addr_len);
	if (neigh)
		neigh_update(neigh, lladdr, NUD_STALE, 
			     NEIGH_UPDATE_F_OVERRIDE);
	return neigh;
}

static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst,
			  u16 protocol)
{
	struct hh_cache	*hh;
	struct net_device *dev = dst->dev;

	for (hh = n->hh; hh; hh = hh->hh_next)
		if (hh->hh_type == protocol)
			break;

	if (!hh && (hh = kmalloc(sizeof(*hh), GFP_ATOMIC)) != NULL) {
		memset(hh, 0, sizeof(struct hh_cache));
		hh->hh_lock = RW_LOCK_UNLOCKED;
		hh->hh_type = protocol;
		atomic_set(&hh->hh_refcnt, 0);
		hh->hh_next = NULL;
		if (dev->hard_header_cache(n, hh)) {
			kfree(hh);
			hh = NULL;
		} else {
			atomic_inc(&hh->hh_refcnt);
			hh->hh_next = n->hh;
			n->hh	    = hh;
			if (n->nud_state & NUD_CONNECTED)
				hh->hh_output = n->ops->hh_output;
			else
				hh->hh_output = n->ops->output;
		}
	}
	if (hh)	{
		atomic_inc(&hh->hh_refcnt);
		dst->hh = hh;
	}
}

/* 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 sk_buff *skb)
{
	struct net_device *dev = skb->dev;

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

	if (dev->hard_header &&
	    dev->hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
		    	     skb->len) < 0 &&
	    dev->rebuild_header(skb))
		return 0;

	return dev_queue_xmit(skb);
}

/* Slow and careful. */

int neigh_resolve_output(struct sk_buff *skb)
{
	struct dst_entry *dst = skb->dst;
	struct neighbour *neigh;
	int rc = 0;

	if (!dst || !(neigh = dst->neighbour))
		goto discard;

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

	if (!neigh_event_send(neigh, skb)) {
		int err;
		struct net_device *dev = neigh->dev;
		if (dev->hard_header_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);
			write_unlock_bh(&neigh->lock);
		} else {
			read_lock_bh(&neigh->lock);
			err = dev->hard_header(skb, dev, ntohs(skb->protocol),