ipoib_multicast.c

linux-2.6.15.6

void ipoib_mcast_join_task(void *dev_ptr)
{
	struct net_device *dev = dev_ptr;
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	if (!test_bit(IPOIB_MCAST_RUN, &priv->flags))
		return;

	if (ib_query_gid(priv->ca, priv->port, 0, &priv->local_gid))
		ipoib_warn(priv, "ib_gid_entry_get() failed\n");
	else
		memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));

	{
		struct ib_port_attr attr;

		if (!ib_query_port(priv->ca, priv->port, &attr)) {
			priv->local_lid  = attr.lid;
			priv->local_rate = attr.active_speed *
				ib_width_enum_to_int(attr.active_width);
		} else
			ipoib_warn(priv, "ib_query_port failed\n");
	}

	if (!priv->broadcast) {
		priv->broadcast = ipoib_mcast_alloc(dev, 1);
		if (!priv->broadcast) {
			ipoib_warn(priv, "failed to allocate broadcast group\n");
			down(&mcast_mutex);
			if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
				queue_delayed_work(ipoib_workqueue,
						   &priv->mcast_task, HZ);
			up(&mcast_mutex);
			return;
		}

		memcpy(priv->broadcast->mcmember.mgid.raw, priv->dev->broadcast + 4,
		       sizeof (union ib_gid));

		spin_lock_irq(&priv->lock);
		__ipoib_mcast_add(dev, priv->broadcast);
		spin_unlock_irq(&priv->lock);
	}

	if (!test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) {
		ipoib_mcast_join(dev, priv->broadcast, 0);
		return;
	}

	while (1) {
		struct ipoib_mcast *mcast = NULL;

		spin_lock_irq(&priv->lock);
		list_for_each_entry(mcast, &priv->multicast_list, list) {
			if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)
			    && !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)
			    && !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
				/* Found the next unjoined group */
				break;
			}
		}
		spin_unlock_irq(&priv->lock);

		if (&mcast->list == &priv->multicast_list) {
			/* All done */
			break;
		}

		ipoib_mcast_join(dev, mcast, 1);
		return;
	}

	priv->mcast_mtu = ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu) -
		IPOIB_ENCAP_LEN;
	dev->mtu = min(priv->mcast_mtu, priv->admin_mtu);

	ipoib_dbg_mcast(priv, "successfully joined all multicast groups\n");

	clear_bit(IPOIB_MCAST_RUN, &priv->flags);
	netif_carrier_on(dev);
}

int ipoib_mcast_start_thread(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	ipoib_dbg_mcast(priv, "starting multicast thread\n");

	down(&mcast_mutex);
	if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags))
		queue_work(ipoib_workqueue, &priv->mcast_task);
	up(&mcast_mutex);

	return 0;
}

int ipoib_mcast_stop_thread(struct net_device *dev, int flush)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_mcast *mcast;

	ipoib_dbg_mcast(priv, "stopping multicast thread\n");

	down(&mcast_mutex);
	clear_bit(IPOIB_MCAST_RUN, &priv->flags);
	cancel_delayed_work(&priv->mcast_task);
	up(&mcast_mutex);

	if (flush)
		flush_workqueue(ipoib_workqueue);

	if (priv->broadcast && priv->broadcast->query) {
		ib_sa_cancel_query(priv->broadcast->query_id, priv->broadcast->query);
		priv->broadcast->query = NULL;
		ipoib_dbg_mcast(priv, "waiting for bcast\n");
		wait_for_completion(&priv->broadcast->done);
	}

	list_for_each_entry(mcast, &priv->multicast_list, list) {
		if (mcast->query) {
			ib_sa_cancel_query(mcast->query_id, mcast->query);
			mcast->query = NULL;
			ipoib_dbg_mcast(priv, "waiting for MGID " IPOIB_GID_FMT "\n",
					IPOIB_GID_ARG(mcast->mcmember.mgid));
			wait_for_completion(&mcast->done);
		}
	}

	return 0;
}

static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ib_sa_mcmember_rec rec = {
		.join_state = 1
	};
	int ret = 0;

	if (!test_and_clear_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags))
		return 0;

	ipoib_dbg_mcast(priv, "leaving MGID " IPOIB_GID_FMT "\n",
			IPOIB_GID_ARG(mcast->mcmember.mgid));

	rec.mgid     = mcast->mcmember.mgid;
	rec.port_gid = priv->local_gid;
	rec.pkey     = cpu_to_be16(priv->pkey);

	/* Remove ourselves from the multicast group */
	ret = ipoib_mcast_detach(dev, be16_to_cpu(mcast->mcmember.mlid),
				 &mcast->mcmember.mgid);
	if (ret)
		ipoib_warn(priv, "ipoib_mcast_detach failed (result = %d)\n", ret);

	/*
	 * Just make one shot at leaving and don't wait for a reply;
	 * if we fail, too bad.
	 */
	ret = ib_sa_mcmember_rec_delete(priv->ca, priv->port, &rec,
					IB_SA_MCMEMBER_REC_MGID		|
					IB_SA_MCMEMBER_REC_PORT_GID	|
					IB_SA_MCMEMBER_REC_PKEY		|
					IB_SA_MCMEMBER_REC_JOIN_STATE,
					0, GFP_ATOMIC, NULL,
					mcast, &mcast->query);
	if (ret < 0)
		ipoib_warn(priv, "ib_sa_mcmember_rec_delete failed "
			   "for leave (result = %d)\n", ret);

	return 0;
}

void ipoib_mcast_send(struct net_device *dev, union ib_gid *mgid,
		      struct sk_buff *skb)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_mcast *mcast;

	/*
	 * 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);

	mcast = __ipoib_mcast_find(dev, mgid);
	if (!mcast) {
		/* Let's create a new send only group now */
		ipoib_dbg_mcast(priv, "setting up send only multicast group for "
				IPOIB_GID_FMT "\n", IPOIB_GID_ARG(*mgid));

		mcast = ipoib_mcast_alloc(dev, 0);
		if (!mcast) {
			ipoib_warn(priv, "unable to allocate memory for "
				   "multicast structure\n");
			dev_kfree_skb_any(skb);
			goto out;
		}

		set_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags);
		mcast->mcmember.mgid = *mgid;
		__ipoib_mcast_add(dev, mcast);
		list_add_tail(&mcast->list, &priv->multicast_list);
	}

	if (!mcast->ah) {
		if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
			skb_queue_tail(&mcast->pkt_queue, skb);
		else
			dev_kfree_skb_any(skb);

		if (mcast->query)
			ipoib_dbg_mcast(priv, "no address vector, "
					"but multicast join already started\n");
		else if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
			ipoib_mcast_sendonly_join(mcast);

		/*
		 * If lookup completes between here and out:, don't
		 * want to send packet twice.
		 */
		mcast = NULL;
	}

out:
	if (mcast && mcast->ah) {
		if (skb->dst            &&
		    skb->dst->neighbour &&
		    !*to_ipoib_neigh(skb->dst->neighbour)) {
			struct ipoib_neigh *neigh = kmalloc(sizeof *neigh, GFP_ATOMIC);

			if (neigh) {
				kref_get(&mcast->ah->ref);
				neigh->ah  	= mcast->ah;
				neigh->neighbour = skb->dst->neighbour;
				*to_ipoib_neigh(skb->dst->neighbour) = neigh;
				list_add_tail(&neigh->list, &mcast->neigh_list);
			}
		}

		ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN);
	}

	spin_unlock(&priv->lock);
}

void ipoib_mcast_dev_flush(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	LIST_HEAD(remove_list);
	struct ipoib_mcast *mcast, *tmcast, *nmcast;
	unsigned long flags;

	ipoib_dbg_mcast(priv, "flushing multicast list\n");

	spin_lock_irqsave(&priv->lock, flags);
	list_for_each_entry_safe(mcast, tmcast, &priv->multicast_list, list) {
		nmcast = ipoib_mcast_alloc(dev, 0);
		if (nmcast) {
			nmcast->flags =
				mcast->flags & (1 << IPOIB_MCAST_FLAG_SENDONLY);

			nmcast->mcmember.mgid = mcast->mcmember.mgid;

			/* Add the new group in before the to-be-destroyed group */
			list_add_tail(&nmcast->list, &mcast->list);
			list_del_init(&mcast->list);

			rb_replace_node(&mcast->rb_node, &nmcast->rb_node,
					&priv->multicast_tree);

			list_add_tail(&mcast->list, &remove_list);
		} else {
			ipoib_warn(priv, "could not reallocate multicast group "
				   IPOIB_GID_FMT "\n",
				   IPOIB_GID_ARG(mcast->mcmember.mgid));
		}
	}

	if (priv->broadcast) {
		nmcast = ipoib_mcast_alloc(dev, 0);
		if (nmcast) {
			nmcast->mcmember.mgid = priv->broadcast->mcmember.mgid;

			rb_replace_node(&priv->broadcast->rb_node,
					&nmcast->rb_node,
					&priv->multicast_tree);

			list_add_tail(&priv->broadcast->list, &remove_list);
		}

		priv->broadcast = nmcast;
	}

	spin_unlock_irqrestore(&priv->lock, flags);

	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
		ipoib_mcast_leave(dev, mcast);
		ipoib_mcast_free(mcast);
	}
}

void ipoib_mcast_dev_down(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	unsigned long flags;

	/* Delete broadcast since it will be recreated */
	if (priv->broadcast) {
		ipoib_dbg_mcast(priv, "deleting broadcast group\n");

		spin_lock_irqsave(&priv->lock, flags);
		rb_erase(&priv->broadcast->rb_node, &priv->multicast_tree);
		spin_unlock_irqrestore(&priv->lock, flags);
		ipoib_mcast_leave(dev, priv->broadcast);
		ipoib_mcast_free(priv->broadcast);
		priv->broadcast = NULL;
	}
}

void ipoib_mcast_restart_task(void *dev_ptr)
{
	struct net_device *dev = dev_ptr;
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct dev_mc_list *mclist;
	struct ipoib_mcast *mcast, *tmcast;
	LIST_HEAD(remove_list);
	unsigned long flags;

	ipoib_dbg_mcast(priv, "restarting multicast task\n");

	ipoib_mcast_stop_thread(dev, 0);

	spin_lock_irqsave(&priv->lock, flags);

	/*
	 * Unfortunately, the networking core only gives us a list of all of
	 * the multicast hardware addresses. We need to figure out which ones
	 * are new and which ones have been removed
	 */

	/* Clear out the found flag */
	list_for_each_entry(mcast, &priv->multicast_list, list)
		clear_bit(IPOIB_MCAST_FLAG_FOUND, &mcast->flags);

	/* Mark all of the entries that are found or don't exist */
	for (mclist = dev->mc_list; mclist; mclist = mclist->next) {
		union ib_gid mgid;

		memcpy(mgid.raw, mclist->dmi_addr + 4, sizeof mgid);

		/* Add in the P_Key */
		mgid.raw[4] = (priv->pkey >> 8) & 0xff;
		mgid.raw[5] = priv->pkey & 0xff;

		mcast = __ipoib_mcast_find(dev, &mgid);
		if (!mcast || test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
			struct ipoib_mcast *nmcast;

			/* Not found or send-only group, let's add a new entry */
			ipoib_dbg_mcast(priv, "adding multicast entry for mgid "
					IPOIB_GID_FMT "\n", IPOIB_GID_ARG(mgid));

			nmcast = ipoib_mcast_alloc(dev, 0);
			if (!nmcast) {
				ipoib_warn(priv, "unable to allocate memory for multicast structure\n");
				continue;
			}

			set_bit(IPOIB_MCAST_FLAG_FOUND, &nmcast->flags);

			nmcast->mcmember.mgid = mgid;

			if (mcast) {
				/* Destroy the send only entry */
				list_del(&mcast->list);
				list_add_tail(&mcast->list, &remove_list);

				rb_replace_node(&mcast->rb_node,
						&nmcast->rb_node,
						&priv->multicast_tree);
			} else
				__ipoib_mcast_add(dev, nmcast);

			list_add_tail(&nmcast->list, &priv->multicast_list);
		}

		if (mcast)
			set_bit(IPOIB_MCAST_FLAG_FOUND, &mcast->flags);
	}

	/* Remove all of the entries don't exist anymore */
	list_for_each_entry_safe(mcast, tmcast, &priv->multicast_list, list) {
		if (!test_bit(IPOIB_MCAST_FLAG_FOUND, &mcast->flags) &&
		    !test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
			ipoib_dbg_mcast(priv, "deleting multicast group " IPOIB_GID_FMT "\n",
					IPOIB_GID_ARG(mcast->mcmember.mgid));

			rb_erase(&mcast->rb_node, &priv->multicast_tree);

			/* Move to the remove list */
			list_del(&mcast->list);
			list_add_tail(&mcast->list, &remove_list);
		}
	}
	spin_unlock_irqrestore(&priv->lock, flags);

	/* We have to cancel outside of the spinlock */
	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
		ipoib_mcast_leave(mcast->dev, mcast);
		ipoib_mcast_free(mcast);
	}

	if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
		ipoib_mcast_start_thread(dev);
}

#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG

struct ipoib_mcast_iter *ipoib_mcast_iter_init(struct net_device *dev)
{
	struct ipoib_mcast_iter *iter;

	iter = kmalloc(sizeof *iter, GFP_KERNEL);
	if (!iter)
		return NULL;

	iter->dev = dev;
	memset(iter->mgid.raw, 0, 16);

	if (ipoib_mcast_iter_next(iter)) {
		kfree(iter);
		return NULL;
	}

	return iter;
}

int ipoib_mcast_iter_next(struct ipoib_mcast_iter *iter)
{
	struct ipoib_dev_priv *priv = netdev_priv(iter->dev);
	struct rb_node *n;
	struct ipoib_mcast *mcast;
	int ret = 1;

	spin_lock_irq(&priv->lock);

	n = rb_first(&priv->multicast_tree);

	while (n) {
		mcast = rb_entry(n, struct ipoib_mcast, rb_node);

		if (memcmp(iter->mgid.raw, mcast->mcmember.mgid.raw,
			   sizeof (union ib_gid)) < 0) {
			iter->mgid      = mcast->mcmember.mgid;
			iter->created   = mcast->created;
			iter->queuelen  = skb_queue_len(&mcast->pkt_queue);
			iter->complete  = !!mcast->ah;
			iter->send_only = !!(mcast->flags & (1 << IPOIB_MCAST_FLAG_SENDONLY));

			ret = 0;

			break;
		}

		n = rb_next(n);
	}

	spin_unlock_irq(&priv->lock);

	return ret;
}

void ipoib_mcast_iter_read(struct ipoib_mcast_iter *iter,
			   union ib_gid *mgid,
			   unsigned long *created,
			   unsigned int *queuelen,
			   unsigned int *complete,
			   unsigned int *send_only)
{
	*mgid      = iter->mgid;
	*created   = iter->created;
	*queuelen  = iter->queuelen;
	*complete  = iter->complete;
	*send_only = iter->send_only;
}

#endif /* CONFIG_INFINIBAND_IPOIB_DEBUG */