xpnet.c

linux内核源码

	dev_dbg(xpnet, "ifconfig up of %s; XPC connected\n", dev->name);

	return 0;
}


static int
xpnet_dev_stop(struct net_device *dev)
{
	xpc_disconnect(XPC_NET_CHANNEL);

	dev_dbg(xpnet, "ifconfig down of %s; XPC disconnected\n", dev->name);

	return 0;
}


static int
xpnet_dev_change_mtu(struct net_device *dev, int new_mtu)
{
	/* 68 comes from min TCP+IP+MAC header */
	if ((new_mtu < 68) || (new_mtu > XPNET_MAX_MTU)) {
		dev_err(xpnet, "ifconfig %s mtu %d failed; value must be "
			"between 68 and %ld\n", dev->name, new_mtu,
			XPNET_MAX_MTU);
		return -EINVAL;
	}

	dev->mtu = new_mtu;
	dev_dbg(xpnet, "ifconfig %s mtu set to %d\n", dev->name, new_mtu);
	return 0;
}


/*
 * Required for the net_device structure.
 */
static int
xpnet_dev_set_config(struct net_device *dev, struct ifmap *new_map)
{
	return 0;
}


/*
 * Return statistics to the caller.
 */
static struct net_device_stats *
xpnet_dev_get_stats(struct net_device *dev)
{
	struct xpnet_dev_private *priv;


	priv = (struct xpnet_dev_private *) dev->priv;

	return &priv->stats;
}


/*
 * Notification that the other end has received the message and
 * DMA'd the skb information.  At this point, they are done with
 * our side.  When all recipients are done processing, we
 * release the skb and then release our pending message structure.
 */
static void
xpnet_send_completed(enum xpc_retval reason, partid_t partid, int channel,
			void *__qm)
{
	struct xpnet_pending_msg *queued_msg =
		(struct xpnet_pending_msg *) __qm;


	DBUG_ON(queued_msg == NULL);

	dev_dbg(xpnet, "message to %d notified with reason %d\n",
		partid, reason);

	if (atomic_dec_return(&queued_msg->use_count) == 0) {
		dev_dbg(xpnet, "all acks for skb->head=-x%p\n",
			(void *) queued_msg->skb->head);

		dev_kfree_skb_any(queued_msg->skb);
		kfree(queued_msg);
	}
}


/*
 * Network layer has formatted a packet (skb) and is ready to place it
 * "on the wire".  Prepare and send an xpnet_message to all partitions
 * which have connected with us and are targets of this packet.
 *
 * MAC-NOTE:  For the XPNET driver, the MAC address contains the
 * destination partition_id.  If the destination partition id word
 * is 0xff, this packet is to broadcast to all partitions.
 */
static int
xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct xpnet_pending_msg *queued_msg;
	enum xpc_retval ret;
	struct xpnet_message *msg;
	u64 start_addr, end_addr;
	long dp;
	u8 second_mac_octet;
	partid_t dest_partid;
	struct xpnet_dev_private *priv;
	u16 embedded_bytes;


	priv = (struct xpnet_dev_private *) dev->priv;


	dev_dbg(xpnet, ">skb->head=0x%p skb->data=0x%p skb->tail=0x%p "
		"skb->end=0x%p skb->len=%d\n", (void *) skb->head,
		(void *)skb->data, skb_tail_pointer(skb), skb_end_pointer(skb),
		skb->len);


	/*
	 * The xpnet_pending_msg tracks how many outstanding
	 * xpc_send_notifies are relying on this skb.  When none
	 * remain, release the skb.
	 */
	queued_msg = kmalloc(sizeof(struct xpnet_pending_msg), GFP_ATOMIC);
	if (queued_msg == NULL) {
		dev_warn(xpnet, "failed to kmalloc %ld bytes; dropping "
			"packet\n", sizeof(struct xpnet_pending_msg));

		priv->stats.tx_errors++;

		return -ENOMEM;
	}


	/* get the beginning of the first cacheline and end of last */
	start_addr = ((u64) skb->data & ~(L1_CACHE_BYTES - 1));
	end_addr = L1_CACHE_ALIGN((u64)skb_tail_pointer(skb));

	/* calculate how many bytes to embed in the XPC message */
	embedded_bytes = 0;
	if (unlikely(skb->len <= XPNET_MSG_DATA_MAX)) {
		/* skb->data does fit so embed */
		embedded_bytes = skb->len;
	}


	/*
	 * Since the send occurs asynchronously, we set the count to one
	 * and begin sending.  Any sends that happen to complete before
	 * we are done sending will not free the skb.  We will be left
	 * with that task during exit.  This also handles the case of
	 * a packet destined for a partition which is no longer up.
	 */
	atomic_set(&queued_msg->use_count, 1);
	queued_msg->skb = skb;


	second_mac_octet = skb->data[XPNET_PARTID_OCTET];
	if (second_mac_octet == 0xff) {
		/* we are being asked to broadcast to all partitions */
		dp = xpnet_broadcast_partitions;
	} else if (second_mac_octet != 0) {
		dp = xpnet_broadcast_partitions &
					(1UL << (second_mac_octet - 1));
	} else {
		/* 0 is an invalid partid.  Ignore */
		dp = 0;
	}
	dev_dbg(xpnet, "destination Partitions mask (dp) = 0x%lx\n", dp);

	/*
	 * If we wanted to allow promiscuous mode to work like an
	 * unswitched network, this would be a good point to OR in a
	 * mask of partitions which should be receiving all packets.
	 */

	/*
	 * Main send loop.
	 */
	for (dest_partid = 1; dp && dest_partid < XP_MAX_PARTITIONS;
	     dest_partid++) {


		if (!(dp & (1UL << (dest_partid - 1)))) {
			/* not destined for this partition */
			continue;
		}

		/* remove this partition from the destinations mask */
		dp &= ~(1UL << (dest_partid - 1));


		/* found a partition to send to */

		ret = xpc_allocate(dest_partid, XPC_NET_CHANNEL,
				   XPC_NOWAIT, (void **)&msg);
		if (unlikely(ret != xpcSuccess)) {
			continue;
		}

		msg->embedded_bytes = embedded_bytes;
		if (unlikely(embedded_bytes != 0)) {
			msg->version = XPNET_VERSION_EMBED;
			dev_dbg(xpnet, "calling memcpy(0x%p, 0x%p, 0x%lx)\n",
				&msg->data, skb->data, (size_t) embedded_bytes);
			skb_copy_from_linear_data(skb, &msg->data,
						  (size_t)embedded_bytes);
		} else {
			msg->version = XPNET_VERSION;
		}
		msg->magic = XPNET_MAGIC;
		msg->size = end_addr - start_addr;
		msg->leadin_ignore = (u64) skb->data - start_addr;
		msg->tailout_ignore = end_addr - (u64)skb_tail_pointer(skb);
		msg->buf_pa = __pa(start_addr);

		dev_dbg(xpnet, "sending XPC message to %d:%d\n"
			KERN_DEBUG "msg->buf_pa=0x%lx, msg->size=%u, "
			"msg->leadin_ignore=%u, msg->tailout_ignore=%u\n",
			dest_partid, XPC_NET_CHANNEL, msg->buf_pa, msg->size,
			msg->leadin_ignore, msg->tailout_ignore);


		atomic_inc(&queued_msg->use_count);

		ret = xpc_send_notify(dest_partid, XPC_NET_CHANNEL, msg,
				      xpnet_send_completed, queued_msg);
		if (unlikely(ret != xpcSuccess)) {
			atomic_dec(&queued_msg->use_count);
			continue;
		}

	}

	if (atomic_dec_return(&queued_msg->use_count) == 0) {
		dev_dbg(xpnet, "no partitions to receive packet destined for "
			"%d\n", dest_partid);


		dev_kfree_skb(skb);
		kfree(queued_msg);
	}

	priv->stats.tx_packets++;
	priv->stats.tx_bytes += skb->len;

	return 0;
}


/*
 * Deal with transmit timeouts coming from the network layer.
 */
static void
xpnet_dev_tx_timeout (struct net_device *dev)
{
	struct xpnet_dev_private *priv;


	priv = (struct xpnet_dev_private *) dev->priv;

	priv->stats.tx_errors++;
	return;
}


static int __init
xpnet_init(void)
{
	int i;
	u32 license_num;
	int result = -ENOMEM;


	if (!ia64_platform_is("sn2")) {
		return -ENODEV;
	}

	dev_info(xpnet, "registering network device %s\n", XPNET_DEVICE_NAME);

	/*
	 * use ether_setup() to init the majority of our device
	 * structure and then override the necessary pieces.
	 */
	xpnet_device = alloc_netdev(sizeof(struct xpnet_dev_private),
				    XPNET_DEVICE_NAME, ether_setup);
	if (xpnet_device == NULL) {
		return -ENOMEM;
	}

	netif_carrier_off(xpnet_device);

	xpnet_device->mtu = XPNET_DEF_MTU;
	xpnet_device->change_mtu = xpnet_dev_change_mtu;
	xpnet_device->open = xpnet_dev_open;
	xpnet_device->get_stats = xpnet_dev_get_stats;
	xpnet_device->stop = xpnet_dev_stop;
	xpnet_device->hard_start_xmit = xpnet_dev_hard_start_xmit;
	xpnet_device->tx_timeout = xpnet_dev_tx_timeout;
	xpnet_device->set_config = xpnet_dev_set_config;

	/*
	 * Multicast assumes the LSB of the first octet is set for multicast
	 * MAC addresses.  We chose the first octet of the MAC to be unlikely
	 * to collide with any vendor's officially issued MAC.
	 */
	xpnet_device->dev_addr[0] = 0xfe;
	xpnet_device->dev_addr[XPNET_PARTID_OCTET] = sn_partition_id;
	license_num = sn_partition_serial_number_val();
	for (i = 3; i >= 0; i--) {
		xpnet_device->dev_addr[XPNET_LICENSE_OCTET + i] =
							license_num & 0xff;
		license_num = license_num >> 8;
	}

	/*
	 * ether_setup() sets this to a multicast device.  We are
	 * really not supporting multicast at this time.
	 */
	xpnet_device->flags &= ~IFF_MULTICAST;

	/*
	 * No need to checksum as it is a DMA transfer.  The BTE will
	 * report an error if the data is not retrievable and the
	 * packet will be dropped.
	 */
	xpnet_device->features = NETIF_F_NO_CSUM;

	result = register_netdev(xpnet_device);
	if (result != 0) {
		free_netdev(xpnet_device);
	}

	return result;
}
module_init(xpnet_init);


static void __exit
xpnet_exit(void)
{
	dev_info(xpnet, "unregistering network device %s\n",
		xpnet_device[0].name);

	unregister_netdev(xpnet_device);

	free_netdev(xpnet_device);
}
module_exit(xpnet_exit);


MODULE_AUTHOR("Silicon Graphics, Inc.");
MODULE_DESCRIPTION("Cross Partition Network adapter (XPNET)");
MODULE_LICENSE("GPL");