ipoib_ib.c

linux内核源码

			ib_destroy_ah(ah->ah);
			kfree(ah);
		}
	spin_unlock(&priv->lock);
	spin_unlock_irq(&priv->tx_lock);
}

void ipoib_reap_ah(struct work_struct *work)
{
	struct ipoib_dev_priv *priv =
		container_of(work, struct ipoib_dev_priv, ah_reap_task.work);
	struct net_device *dev = priv->dev;

	__ipoib_reap_ah(dev);

	if (!test_bit(IPOIB_STOP_REAPER, &priv->flags))
		queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
				   round_jiffies_relative(HZ));
}

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

	if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &priv->pkey_index)) {
		ipoib_warn(priv, "P_Key 0x%04x not found\n", priv->pkey);
		clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
		return -1;
	}
	set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);

	ret = ipoib_init_qp(dev);
	if (ret) {
		ipoib_warn(priv, "ipoib_init_qp returned %d\n", ret);
		return -1;
	}

	ret = ipoib_ib_post_receives(dev);
	if (ret) {
		ipoib_warn(priv, "ipoib_ib_post_receives returned %d\n", ret);
		ipoib_ib_dev_stop(dev, 1);
		return -1;
	}

	ret = ipoib_cm_dev_open(dev);
	if (ret) {
		ipoib_warn(priv, "ipoib_cm_dev_open returned %d\n", ret);
		ipoib_ib_dev_stop(dev, 1);
		return -1;
	}

	clear_bit(IPOIB_STOP_REAPER, &priv->flags);
	queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
			   round_jiffies_relative(HZ));

	set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);

	return 0;
}

static void ipoib_pkey_dev_check_presence(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	u16 pkey_index = 0;

	if (ib_find_cached_pkey(priv->ca, priv->port, priv->pkey, &pkey_index))
		clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
	else
		set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
}

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

	ipoib_pkey_dev_check_presence(dev);

	if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
		ipoib_dbg(priv, "PKEY is not assigned.\n");
		return 0;
	}

	set_bit(IPOIB_FLAG_OPER_UP, &priv->flags);

	return ipoib_mcast_start_thread(dev);
}

int ipoib_ib_dev_down(struct net_device *dev, int flush)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	ipoib_dbg(priv, "downing ib_dev\n");

	clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
	netif_carrier_off(dev);

	/* Shutdown the P_Key thread if still active */
	if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
		mutex_lock(&pkey_mutex);
		set_bit(IPOIB_PKEY_STOP, &priv->flags);
		cancel_delayed_work(&priv->pkey_poll_task);
		mutex_unlock(&pkey_mutex);
		if (flush)
			flush_workqueue(ipoib_workqueue);
	}

	ipoib_mcast_stop_thread(dev, flush);
	ipoib_mcast_dev_flush(dev);

	ipoib_flush_paths(dev);

	return 0;
}

static int recvs_pending(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	int pending = 0;
	int i;

	for (i = 0; i < ipoib_recvq_size; ++i)
		if (priv->rx_ring[i].skb)
			++pending;

	return pending;
}

void ipoib_drain_cq(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	int i, n;
	do {
		n = ib_poll_cq(priv->cq, IPOIB_NUM_WC, priv->ibwc);
		for (i = 0; i < n; ++i) {
			/*
			 * Convert any successful completions to flush
			 * errors to avoid passing packets up the
			 * stack after bringing the device down.
			 */
			if (priv->ibwc[i].status == IB_WC_SUCCESS)
				priv->ibwc[i].status = IB_WC_WR_FLUSH_ERR;

			if (priv->ibwc[i].wr_id & IPOIB_OP_RECV) {
				if (priv->ibwc[i].wr_id & IPOIB_OP_CM)
					ipoib_cm_handle_rx_wc(dev, priv->ibwc + i);
				else
					ipoib_ib_handle_rx_wc(dev, priv->ibwc + i);
			} else {
				if (priv->ibwc[i].wr_id & IPOIB_OP_CM)
					ipoib_cm_handle_tx_wc(dev, priv->ibwc + i);
				else
					ipoib_ib_handle_tx_wc(dev, priv->ibwc + i);
			}
		}
	} while (n == IPOIB_NUM_WC);
}

int ipoib_ib_dev_stop(struct net_device *dev, int flush)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ib_qp_attr qp_attr;
	unsigned long begin;
	struct ipoib_tx_buf *tx_req;
	int i;

	clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);

	ipoib_cm_dev_stop(dev);

	/*
	 * Move our QP to the error state and then reinitialize in
	 * when all work requests have completed or have been flushed.
	 */
	qp_attr.qp_state = IB_QPS_ERR;
	if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
		ipoib_warn(priv, "Failed to modify QP to ERROR state\n");

	/* Wait for all sends and receives to complete */
	begin = jiffies;

	while (priv->tx_head != priv->tx_tail || recvs_pending(dev)) {
		if (time_after(jiffies, begin + 5 * HZ)) {
			ipoib_warn(priv, "timing out; %d sends %d receives not completed\n",
				   priv->tx_head - priv->tx_tail, recvs_pending(dev));

			/*
			 * assume the HW is wedged and just free up
			 * all our pending work requests.
			 */
			while ((int) priv->tx_tail - (int) priv->tx_head < 0) {
				tx_req = &priv->tx_ring[priv->tx_tail &
							(ipoib_sendq_size - 1)];
				ib_dma_unmap_single(priv->ca,
						    tx_req->mapping,
						    tx_req->skb->len,
						    DMA_TO_DEVICE);
				dev_kfree_skb_any(tx_req->skb);
				++priv->tx_tail;
				--priv->tx_outstanding;
			}

			for (i = 0; i < ipoib_recvq_size; ++i) {
				struct ipoib_rx_buf *rx_req;

				rx_req = &priv->rx_ring[i];
				if (!rx_req->skb)
					continue;
				ib_dma_unmap_single(priv->ca,
						    rx_req->mapping,
						    IPOIB_BUF_SIZE,
						    DMA_FROM_DEVICE);
				dev_kfree_skb_any(rx_req->skb);
				rx_req->skb = NULL;
			}

			goto timeout;
		}

		ipoib_drain_cq(dev);

		msleep(1);
	}

	ipoib_dbg(priv, "All sends and receives done.\n");

timeout:
	qp_attr.qp_state = IB_QPS_RESET;
	if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
		ipoib_warn(priv, "Failed to modify QP to RESET state\n");

	/* Wait for all AHs to be reaped */
	set_bit(IPOIB_STOP_REAPER, &priv->flags);
	cancel_delayed_work(&priv->ah_reap_task);
	if (flush)
		flush_workqueue(ipoib_workqueue);

	begin = jiffies;

	while (!list_empty(&priv->dead_ahs)) {
		__ipoib_reap_ah(dev);

		if (time_after(jiffies, begin + HZ)) {
			ipoib_warn(priv, "timing out; will leak address handles\n");
			break;
		}

		msleep(1);
	}

	ib_req_notify_cq(priv->cq, IB_CQ_NEXT_COMP);

	return 0;
}

int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	priv->ca = ca;
	priv->port = port;
	priv->qp = NULL;

	if (ipoib_transport_dev_init(dev, ca)) {
		printk(KERN_WARNING "%s: ipoib_transport_dev_init failed\n", ca->name);
		return -ENODEV;
	}

	if (dev->flags & IFF_UP) {
		if (ipoib_ib_dev_open(dev)) {
			ipoib_transport_dev_cleanup(dev);
			return -ENODEV;
		}
	}

	return 0;
}

static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, int pkey_event)
{
	struct ipoib_dev_priv *cpriv;
	struct net_device *dev = priv->dev;
	u16 new_index;

	mutex_lock(&priv->vlan_mutex);

	/*
	 * Flush any child interfaces too -- they might be up even if
	 * the parent is down.
	 */
	list_for_each_entry(cpriv, &priv->child_intfs, list)
		__ipoib_ib_dev_flush(cpriv, pkey_event);

	mutex_unlock(&priv->vlan_mutex);

	if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) {
		ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_INITIALIZED not set.\n");
		return;
	}

	if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) {
		ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_ADMIN_UP not set.\n");
		return;
	}

	if (pkey_event) {
		if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &new_index)) {
			clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
			ipoib_ib_dev_down(dev, 0);
			ipoib_pkey_dev_delay_open(dev);
			return;
		}
		set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);

		/* restart QP only if P_Key index is changed */
		if (new_index == priv->pkey_index) {
			ipoib_dbg(priv, "Not flushing - P_Key index not changed.\n");
			return;
		}
		priv->pkey_index = new_index;
	}

	ipoib_dbg(priv, "flushing\n");

	ipoib_ib_dev_down(dev, 0);

	if (pkey_event) {
		ipoib_ib_dev_stop(dev, 0);
		ipoib_ib_dev_open(dev);
	}

	/*
	 * The device could have been brought down between the start and when
	 * we get here, don't bring it back up if it's not configured up
	 */
	if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) {
		ipoib_ib_dev_up(dev);
		ipoib_mcast_restart_task(&priv->restart_task);
	}
}

void ipoib_ib_dev_flush(struct work_struct *work)
{
	struct ipoib_dev_priv *priv =
		container_of(work, struct ipoib_dev_priv, flush_task);

	ipoib_dbg(priv, "Flushing %s\n", priv->dev->name);
	__ipoib_ib_dev_flush(priv, 0);
}

void ipoib_pkey_event(struct work_struct *work)
{
	struct ipoib_dev_priv *priv =
		container_of(work, struct ipoib_dev_priv, pkey_event_task);

	ipoib_dbg(priv, "Flushing %s and restarting its QP\n", priv->dev->name);
	__ipoib_ib_dev_flush(priv, 1);
}

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

	ipoib_dbg(priv, "cleaning up ib_dev\n");

	ipoib_mcast_stop_thread(dev, 1);
	ipoib_mcast_dev_flush(dev);

	ipoib_transport_dev_cleanup(dev);
}

/*
 * Delayed P_Key Assigment Interim Support
 *
 * The following is initial implementation of delayed P_Key assigment
 * mechanism. It is using the same approach implemented for the multicast
 * group join. The single goal of this implementation is to quickly address
 * Bug #2507. This implementation will probably be removed when the P_Key
 * change async notification is available.
 */

void ipoib_pkey_poll(struct work_struct *work)
{
	struct ipoib_dev_priv *priv =
		container_of(work, struct ipoib_dev_priv, pkey_poll_task.work);
	struct net_device *dev = priv->dev;

	ipoib_pkey_dev_check_presence(dev);

	if (test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags))
		ipoib_open(dev);
	else {
		mutex_lock(&pkey_mutex);
		if (!test_bit(IPOIB_PKEY_STOP, &priv->flags))
			queue_delayed_work(ipoib_workqueue,
					   &priv->pkey_poll_task,
					   HZ);
		mutex_unlock(&pkey_mutex);
	}
}

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

	/* Look for the interface pkey value in the IB Port P_Key table and */
	/* set the interface pkey assigment flag                            */
	ipoib_pkey_dev_check_presence(dev);

	/* P_Key value not assigned yet - start polling */
	if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
		mutex_lock(&pkey_mutex);
		clear_bit(IPOIB_PKEY_STOP, &priv->flags);
		queue_delayed_work(ipoib_workqueue,
				   &priv->pkey_poll_task,
				   HZ);
		mutex_unlock(&pkey_mutex);
		return 1;
	}

	return 0;
}