ipoib_main.c

linux内核源码

				__skb_queue_tail(&skqueue, skb);
		}
	}

	path->query = NULL;
	complete(&path->done);

	spin_unlock_irqrestore(&priv->lock, flags);

	while ((skb = __skb_dequeue(&skqueue))) {
		skb->dev = dev;
		if (dev_queue_xmit(skb))
			ipoib_warn(priv, "dev_queue_xmit failed "
				   "to requeue packet\n");
	}
}

static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_path *path;

	if (!priv->broadcast)
		return NULL;

	path = kzalloc(sizeof *path, GFP_ATOMIC);
	if (!path)
		return NULL;

	path->dev = dev;

	skb_queue_head_init(&path->queue);

	INIT_LIST_HEAD(&path->neigh_list);

	memcpy(path->pathrec.dgid.raw, gid, sizeof (union ib_gid));
	path->pathrec.sgid          = priv->local_gid;
	path->pathrec.pkey          = cpu_to_be16(priv->pkey);
	path->pathrec.numb_path     = 1;
	path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class;

	return path;
}

static int path_rec_start(struct net_device *dev,
			  struct ipoib_path *path)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	ipoib_dbg(priv, "Start path record lookup for " IPOIB_GID_FMT "\n",
		  IPOIB_GID_ARG(path->pathrec.dgid));

	init_completion(&path->done);

	path->query_id =
		ib_sa_path_rec_get(&ipoib_sa_client, priv->ca, priv->port,
				   &path->pathrec,
				   IB_SA_PATH_REC_DGID		|
				   IB_SA_PATH_REC_SGID		|
				   IB_SA_PATH_REC_NUMB_PATH	|
				   IB_SA_PATH_REC_TRAFFIC_CLASS |
				   IB_SA_PATH_REC_PKEY,
				   1000, GFP_ATOMIC,
				   path_rec_completion,
				   path, &path->query);
	if (path->query_id < 0) {
		ipoib_warn(priv, "ib_sa_path_rec_get failed\n");
		path->query = NULL;
		return path->query_id;
	}

	return 0;
}

static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_path *path;
	struct ipoib_neigh *neigh;

	neigh = ipoib_neigh_alloc(skb->dst->neighbour, skb->dev);
	if (!neigh) {
		++dev->stats.tx_dropped;
		dev_kfree_skb_any(skb);
		return;
	}

	/*
	 * We can only be called from ipoib_start_xmit, so we're
	 * inside tx_lock -- no need to save/restore flags.
	 */
	spin_lock(&priv->lock);

	path = __path_find(dev, skb->dst->neighbour->ha + 4);
	if (!path) {
		path = path_rec_create(dev, skb->dst->neighbour->ha + 4);
		if (!path)
			goto err_path;

		__path_add(dev, path);
	}

	list_add_tail(&neigh->list, &path->neigh_list);

	if (path->ah) {
		kref_get(&path->ah->ref);
		neigh->ah = path->ah;
		memcpy(&neigh->dgid.raw, &path->pathrec.dgid.raw,
		       sizeof(union ib_gid));

		if (ipoib_cm_enabled(dev, neigh->neighbour)) {
			if (!ipoib_cm_get(neigh))
				ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh));
			if (!ipoib_cm_get(neigh)) {
				list_del(&neigh->list);
				if (neigh->ah)
					ipoib_put_ah(neigh->ah);
				ipoib_neigh_free(dev, neigh);
				goto err_drop;
			}
			if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
				__skb_queue_tail(&neigh->queue, skb);
			else {
				ipoib_warn(priv, "queue length limit %d. Packet drop.\n",
					   skb_queue_len(&neigh->queue));
				goto err_drop;
			}
		} else
			ipoib_send(dev, skb, path->ah, IPOIB_QPN(skb->dst->neighbour->ha));
	} else {
		neigh->ah  = NULL;

		if (!path->query && path_rec_start(dev, path))
			goto err_list;

		__skb_queue_tail(&neigh->queue, skb);
	}

	spin_unlock(&priv->lock);
	return;

err_list:
	list_del(&neigh->list);

err_path:
	ipoib_neigh_free(dev, neigh);
err_drop:
	++dev->stats.tx_dropped;
	dev_kfree_skb_any(skb);

	spin_unlock(&priv->lock);
}

static void ipoib_path_lookup(struct sk_buff *skb, struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(skb->dev);

	/* Look up path record for unicasts */
	if (skb->dst->neighbour->ha[4] != 0xff) {
		neigh_add_path(skb, dev);
		return;
	}

	/* Add in the P_Key for multicasts */
	skb->dst->neighbour->ha[8] = (priv->pkey >> 8) & 0xff;
	skb->dst->neighbour->ha[9] = priv->pkey & 0xff;
	ipoib_mcast_send(dev, skb->dst->neighbour->ha + 4, skb);
}

static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
			     struct ipoib_pseudoheader *phdr)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_path *path;

	/*
	 * We can only be called from ipoib_start_xmit, so we're
	 * inside tx_lock -- no need to save/restore flags.
	 */
	spin_lock(&priv->lock);

	path = __path_find(dev, phdr->hwaddr + 4);
	if (!path) {
		path = path_rec_create(dev, phdr->hwaddr + 4);
		if (path) {
			/* put pseudoheader back on for next time */
			skb_push(skb, sizeof *phdr);
			__skb_queue_tail(&path->queue, skb);

			if (path_rec_start(dev, path)) {
				spin_unlock(&priv->lock);
				path_free(dev, path);
				return;
			} else
				__path_add(dev, path);
		} else {
			++dev->stats.tx_dropped;
			dev_kfree_skb_any(skb);
		}

		spin_unlock(&priv->lock);
		return;
	}

	if (path->ah) {
		ipoib_dbg(priv, "Send unicast ARP to %04x\n",
			  be16_to_cpu(path->pathrec.dlid));

		ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->hwaddr));
	} else if ((path->query || !path_rec_start(dev, path)) &&
		   skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
		/* put pseudoheader back on for next time */
		skb_push(skb, sizeof *phdr);
		__skb_queue_tail(&path->queue, skb);
	} else {
		++dev->stats.tx_dropped;
		dev_kfree_skb_any(skb);
	}

	spin_unlock(&priv->lock);
}

static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_neigh *neigh;
	unsigned long flags;

	if (unlikely(!spin_trylock_irqsave(&priv->tx_lock, flags)))
		return NETDEV_TX_LOCKED;

	/*
	 * Check if our queue is stopped.  Since we have the LLTX bit
	 * set, we can't rely on netif_stop_queue() preventing our
	 * xmit function from being called with a full queue.
	 */
	if (unlikely(netif_queue_stopped(dev))) {
		spin_unlock_irqrestore(&priv->tx_lock, flags);
		return NETDEV_TX_BUSY;
	}

	if (likely(skb->dst && skb->dst->neighbour)) {
		if (unlikely(!*to_ipoib_neigh(skb->dst->neighbour))) {
			ipoib_path_lookup(skb, dev);
			goto out;
		}

		neigh = *to_ipoib_neigh(skb->dst->neighbour);

		if (ipoib_cm_get(neigh)) {
			if (ipoib_cm_up(neigh)) {
				ipoib_cm_send(dev, skb, ipoib_cm_get(neigh));
				goto out;
			}
		} else if (neigh->ah) {
			if (unlikely((memcmp(&neigh->dgid.raw,
					    skb->dst->neighbour->ha + 4,
					    sizeof(union ib_gid))) ||
					 (neigh->dev != dev))) {
				spin_lock(&priv->lock);
				/*
				 * It's safe to call ipoib_put_ah() inside
				 * priv->lock here, because we know that
				 * path->ah will always hold one more reference,
				 * so ipoib_put_ah() will never do more than
				 * decrement the ref count.
				 */
				ipoib_put_ah(neigh->ah);
				list_del(&neigh->list);
				ipoib_neigh_free(dev, neigh);
				spin_unlock(&priv->lock);
				ipoib_path_lookup(skb, dev);
				goto out;
			}

			ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(skb->dst->neighbour->ha));
			goto out;
		}

		if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
			spin_lock(&priv->lock);
			__skb_queue_tail(&neigh->queue, skb);
			spin_unlock(&priv->lock);
		} else {
			++dev->stats.tx_dropped;
			dev_kfree_skb_any(skb);
		}
	} else {
		struct ipoib_pseudoheader *phdr =
			(struct ipoib_pseudoheader *) skb->data;
		skb_pull(skb, sizeof *phdr);

		if (phdr->hwaddr[4] == 0xff) {
			/* Add in the P_Key for multicast*/
			phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff;
			phdr->hwaddr[9] = priv->pkey & 0xff;

			ipoib_mcast_send(dev, phdr->hwaddr + 4, skb);
		} else {
			/* unicast GID -- should be ARP or RARP reply */

			if ((be16_to_cpup((__be16 *) skb->data) != ETH_P_ARP) &&
			    (be16_to_cpup((__be16 *) skb->data) != ETH_P_RARP)) {
				ipoib_warn(priv, "Unicast, no %s: type %04x, QPN %06x "
					   IPOIB_GID_FMT "\n",
					   skb->dst ? "neigh" : "dst",
					   be16_to_cpup((__be16 *) skb->data),
					   IPOIB_QPN(phdr->hwaddr),
					   IPOIB_GID_RAW_ARG(phdr->hwaddr + 4));
				dev_kfree_skb_any(skb);
				++dev->stats.tx_dropped;
				goto out;
			}

			unicast_arp_send(skb, dev, phdr);
		}
	}

out:
	spin_unlock_irqrestore(&priv->tx_lock, flags);

	return NETDEV_TX_OK;
}

static void ipoib_timeout(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	ipoib_warn(priv, "transmit timeout: latency %d msecs\n",
		   jiffies_to_msecs(jiffies - dev->trans_start));
	ipoib_warn(priv, "queue stopped %d, tx_head %u, tx_tail %u\n",
		   netif_queue_stopped(dev),
		   priv->tx_head, priv->tx_tail);
	/* XXX reset QP, etc. */
}

static int ipoib_hard_header(struct sk_buff *skb,
			     struct net_device *dev,
			     unsigned short type,
			     const void *daddr, const void *saddr, unsigned len)
{
	struct ipoib_header *header;

	header = (struct ipoib_header *) skb_push(skb, sizeof *header);

	header->proto = htons(type);
	header->reserved = 0;

	/*
	 * If we don't have a neighbour structure, stuff the
	 * destination address onto the front of the skb so we can
	 * figure out where to send the packet later.
	 */
	if ((!skb->dst || !skb->dst->neighbour) && daddr) {
		struct ipoib_pseudoheader *phdr =
			(struct ipoib_pseudoheader *) skb_push(skb, sizeof *phdr);
		memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
	}

	return 0;
}

static void ipoib_set_mcast_list(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) {
		ipoib_dbg(priv, "IPOIB_FLAG_OPER_UP not set");
		return;
	}

	queue_work(ipoib_workqueue, &priv->restart_task);
}

static void ipoib_neigh_cleanup(struct neighbour *n)
{
	struct ipoib_neigh *neigh;
	struct ipoib_dev_priv *priv = netdev_priv(n->dev);
	unsigned long flags;
	struct ipoib_ah *ah = NULL;

	neigh = *to_ipoib_neigh(n);
	if (neigh) {
		priv = netdev_priv(neigh->dev);
		ipoib_dbg(priv, "neigh_destructor for bonding device: %s\n",
			  n->dev->name);
	} else
		return;
	ipoib_dbg(priv,
		  "neigh_cleanup for %06x " IPOIB_GID_FMT "\n",
		  IPOIB_QPN(n->ha),
		  IPOIB_GID_RAW_ARG(n->ha + 4));

	spin_lock_irqsave(&priv->lock, flags);

	if (neigh->ah)
		ah = neigh->ah;
	list_del(&neigh->list);
	ipoib_neigh_free(n->dev, neigh);

	spin_unlock_irqrestore(&priv->lock, flags);

	if (ah)
		ipoib_put_ah(ah);
}

struct ipoib_neigh *ipoib_neigh_alloc(struct neighbour *neighbour,
				      struct net_device *dev)
{
	struct ipoib_neigh *neigh;

	neigh = kmalloc(sizeof *neigh, GFP_ATOMIC);
	if (!neigh)
		return NULL;

	neigh->neighbour = neighbour;
	neigh->dev = dev;
	*to_ipoib_neigh(neighbour) = neigh;
	skb_queue_head_init(&neigh->queue);
	ipoib_cm_set(neigh, NULL);

	return neigh;
}

void ipoib_neigh_free(struct net_device *dev, struct ipoib_neigh *neigh)
{
	struct sk_buff *skb;
	*to_ipoib_neigh(neigh->neighbour) = NULL;
	while ((skb = __skb_dequeue(&neigh->queue))) {
		++dev->stats.tx_dropped;
		dev_kfree_skb_any(skb);
	}
	if (ipoib_cm_get(neigh))
		ipoib_cm_destroy_tx(ipoib_cm_get(neigh));
	kfree(neigh);
}

static int ipoib_neigh_setup_dev(struct net_device *dev, struct neigh_parms *parms)
{
	parms->neigh_cleanup = ipoib_neigh_cleanup;