ibmveth.c

来自「linux 内核源代码」· C语言 代码 · 共 1,549 行 · 第 1/3 页

		rxq_entries += adapter->rx_buff_pool[i].size;

	adapter->buffer_list_addr = (void*) get_zeroed_page(GFP_KERNEL);
	adapter->filter_list_addr = (void*) get_zeroed_page(GFP_KERNEL);

	if(!adapter->buffer_list_addr || !adapter->filter_list_addr) {
		ibmveth_error_printk("unable to allocate filter or buffer list pages\n");
		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return -ENOMEM;
	}

	adapter->rx_queue.queue_len = sizeof(struct ibmveth_rx_q_entry) * rxq_entries;
	adapter->rx_queue.queue_addr = kmalloc(adapter->rx_queue.queue_len, GFP_KERNEL);

	if(!adapter->rx_queue.queue_addr) {
		ibmveth_error_printk("unable to allocate rx queue pages\n");
		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return -ENOMEM;
	}

	adapter->buffer_list_dma = dma_map_single(&adapter->vdev->dev,
			adapter->buffer_list_addr, 4096, DMA_BIDIRECTIONAL);
	adapter->filter_list_dma = dma_map_single(&adapter->vdev->dev,
			adapter->filter_list_addr, 4096, DMA_BIDIRECTIONAL);
	adapter->rx_queue.queue_dma = dma_map_single(&adapter->vdev->dev,
			adapter->rx_queue.queue_addr,
			adapter->rx_queue.queue_len, DMA_BIDIRECTIONAL);

	if((dma_mapping_error(adapter->buffer_list_dma) ) ||
	   (dma_mapping_error(adapter->filter_list_dma)) ||
	   (dma_mapping_error(adapter->rx_queue.queue_dma))) {
		ibmveth_error_printk("unable to map filter or buffer list pages\n");
		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return -ENOMEM;
	}

	adapter->rx_queue.index = 0;
	adapter->rx_queue.num_slots = rxq_entries;
	adapter->rx_queue.toggle = 1;

	memcpy(&mac_address, netdev->dev_addr, netdev->addr_len);
	mac_address = mac_address >> 16;

	rxq_desc.fields.flags_len = IBMVETH_BUF_VALID | adapter->rx_queue.queue_len;
	rxq_desc.fields.address = adapter->rx_queue.queue_dma;

	ibmveth_debug_printk("buffer list @ 0x%p\n", adapter->buffer_list_addr);
	ibmveth_debug_printk("filter list @ 0x%p\n", adapter->filter_list_addr);
	ibmveth_debug_printk("receive q   @ 0x%p\n", adapter->rx_queue.queue_addr);

	h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE);

	lpar_rc = ibmveth_register_logical_lan(adapter, rxq_desc, mac_address);

	if(lpar_rc != H_SUCCESS) {
		ibmveth_error_printk("h_register_logical_lan failed with %ld\n", lpar_rc);
		ibmveth_error_printk("buffer TCE:0x%lx filter TCE:0x%lx rxq desc:0x%lx MAC:0x%lx\n",
				     adapter->buffer_list_dma,
				     adapter->filter_list_dma,
				     rxq_desc.desc,
				     mac_address);
		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return -ENONET;
	}

	for(i = 0; i<IbmVethNumBufferPools; i++) {
		if(!adapter->rx_buff_pool[i].active)
			continue;
		if (ibmveth_alloc_buffer_pool(&adapter->rx_buff_pool[i])) {
			ibmveth_error_printk("unable to alloc pool\n");
			adapter->rx_buff_pool[i].active = 0;
			ibmveth_cleanup(adapter);
			napi_disable(&adapter->napi);
			return -ENOMEM ;
		}
	}

	ibmveth_debug_printk("registering irq 0x%x\n", netdev->irq);
	if((rc = request_irq(netdev->irq, &ibmveth_interrupt, 0, netdev->name, netdev)) != 0) {
		ibmveth_error_printk("unable to request irq 0x%x, rc %d\n", netdev->irq, rc);
		do {
			rc = h_free_logical_lan(adapter->vdev->unit_address);
		} while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY));

		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return rc;
	}

	ibmveth_debug_printk("initial replenish cycle\n");
	ibmveth_interrupt(netdev->irq, netdev);

	netif_start_queue(netdev);

	ibmveth_debug_printk("open complete\n");

	return 0;
}

static int ibmveth_close(struct net_device *netdev)
{
	struct ibmveth_adapter *adapter = netdev->priv;
	long lpar_rc;

	ibmveth_debug_printk("close starting\n");

	napi_disable(&adapter->napi);

	if (!adapter->pool_config)
		netif_stop_queue(netdev);

	free_irq(netdev->irq, netdev);

	do {
		lpar_rc = h_free_logical_lan(adapter->vdev->unit_address);
	} while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY));

	if(lpar_rc != H_SUCCESS)
	{
		ibmveth_error_printk("h_free_logical_lan failed with %lx, continuing with close\n",
				     lpar_rc);
	}

	adapter->rx_no_buffer = *(u64*)(((char*)adapter->buffer_list_addr) + 4096 - 8);

	ibmveth_cleanup(adapter);

	ibmveth_debug_printk("close complete\n");

	return 0;
}

static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) {
	cmd->supported = (SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE);
	cmd->advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg | ADVERTISED_FIBRE);
	cmd->speed = SPEED_1000;
	cmd->duplex = DUPLEX_FULL;
	cmd->port = PORT_FIBRE;
	cmd->phy_address = 0;
	cmd->transceiver = XCVR_INTERNAL;
	cmd->autoneg = AUTONEG_ENABLE;
	cmd->maxtxpkt = 0;
	cmd->maxrxpkt = 1;
	return 0;
}

static void netdev_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo *info) {
	strncpy(info->driver, ibmveth_driver_name, sizeof(info->driver) - 1);
	strncpy(info->version, ibmveth_driver_version, sizeof(info->version) - 1);
}

static u32 netdev_get_link(struct net_device *dev) {
	return 1;
}

static void ibmveth_set_rx_csum_flags(struct net_device *dev, u32 data)
{
	struct ibmveth_adapter *adapter = dev->priv;

	if (data)
		adapter->rx_csum = 1;
	else {
		/*
		 * Since the ibmveth firmware interface does not have the concept of
		 * separate tx/rx checksum offload enable, if rx checksum is disabled
		 * we also have to disable tx checksum offload. Once we disable rx
		 * checksum offload, we are no longer allowed to send tx buffers that
		 * are not properly checksummed.
		 */
		adapter->rx_csum = 0;
		dev->features &= ~NETIF_F_IP_CSUM;
	}
}

static void ibmveth_set_tx_csum_flags(struct net_device *dev, u32 data)
{
	struct ibmveth_adapter *adapter = dev->priv;

	if (data) {
		dev->features |= NETIF_F_IP_CSUM;
		adapter->rx_csum = 1;
	} else
		dev->features &= ~NETIF_F_IP_CSUM;
}

static int ibmveth_set_csum_offload(struct net_device *dev, u32 data,
				    void (*done) (struct net_device *, u32))
{
	struct ibmveth_adapter *adapter = dev->priv;
	u64 set_attr, clr_attr, ret_attr;
	long ret;
	int rc1 = 0, rc2 = 0;
	int restart = 0;

	if (netif_running(dev)) {
		restart = 1;
		adapter->pool_config = 1;
		ibmveth_close(dev);
		adapter->pool_config = 0;
	}

	set_attr = 0;
	clr_attr = 0;

	if (data)
		set_attr = IBMVETH_ILLAN_IPV4_TCP_CSUM;
	else
		clr_attr = IBMVETH_ILLAN_IPV4_TCP_CSUM;

	ret = h_illan_attributes(adapter->vdev->unit_address, 0, 0, &ret_attr);

	if (ret == H_SUCCESS && !(ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK) &&
	    !(ret_attr & IBMVETH_ILLAN_TRUNK_PRI_MASK) &&
	    (ret_attr & IBMVETH_ILLAN_PADDED_PKT_CSUM)) {
		ret = h_illan_attributes(adapter->vdev->unit_address, clr_attr,
					 set_attr, &ret_attr);

		if (ret != H_SUCCESS) {
			rc1 = -EIO;
			ibmveth_error_printk("unable to change checksum offload settings."
					     " %d rc=%ld\n", data, ret);

			ret = h_illan_attributes(adapter->vdev->unit_address,
						 set_attr, clr_attr, &ret_attr);
		} else
			done(dev, data);
	} else {
		rc1 = -EIO;
		ibmveth_error_printk("unable to change checksum offload settings."
				     " %d rc=%ld ret_attr=%lx\n", data, ret, ret_attr);
	}

	if (restart)
		rc2 = ibmveth_open(dev);

	return rc1 ? rc1 : rc2;
}

static int ibmveth_set_rx_csum(struct net_device *dev, u32 data)
{
	struct ibmveth_adapter *adapter = dev->priv;

	if ((data && adapter->rx_csum) || (!data && !adapter->rx_csum))
		return 0;

	return ibmveth_set_csum_offload(dev, data, ibmveth_set_rx_csum_flags);
}

static int ibmveth_set_tx_csum(struct net_device *dev, u32 data)
{
	struct ibmveth_adapter *adapter = dev->priv;
	int rc = 0;

	if (data && (dev->features & NETIF_F_IP_CSUM))
		return 0;
	if (!data && !(dev->features & NETIF_F_IP_CSUM))
		return 0;

	if (data && !adapter->rx_csum)
		rc = ibmveth_set_csum_offload(dev, data, ibmveth_set_tx_csum_flags);
	else
		ibmveth_set_tx_csum_flags(dev, data);

	return rc;
}

static u32 ibmveth_get_rx_csum(struct net_device *dev)
{
	struct ibmveth_adapter *adapter = dev->priv;
	return adapter->rx_csum;
}

static void ibmveth_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
	int i;

	if (stringset != ETH_SS_STATS)
		return;

	for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++, data += ETH_GSTRING_LEN)
		memcpy(data, ibmveth_stats[i].name, ETH_GSTRING_LEN);
}

static int ibmveth_get_sset_count(struct net_device *dev, int sset)
{
	switch (sset) {
	case ETH_SS_STATS:
		return ARRAY_SIZE(ibmveth_stats);
	default:
		return -EOPNOTSUPP;
	}
}

static void ibmveth_get_ethtool_stats(struct net_device *dev,
				      struct ethtool_stats *stats, u64 *data)
{
	int i;
	struct ibmveth_adapter *adapter = dev->priv;

	for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++)
		data[i] = IBMVETH_GET_STAT(adapter, ibmveth_stats[i].offset);
}

static const struct ethtool_ops netdev_ethtool_ops = {
	.get_drvinfo		= netdev_get_drvinfo,
	.get_settings		= netdev_get_settings,
	.get_link		= netdev_get_link,
	.set_tx_csum		= ibmveth_set_tx_csum,
	.get_rx_csum		= ibmveth_get_rx_csum,
	.set_rx_csum		= ibmveth_set_rx_csum,
	.get_strings		= ibmveth_get_strings,
	.get_sset_count		= ibmveth_get_sset_count,
	.get_ethtool_stats	= ibmveth_get_ethtool_stats,
};

static int ibmveth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
	return -EOPNOTSUPP;
}

#define page_offset(v) ((unsigned long)(v) & ((1 << 12) - 1))

static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *netdev)
{
	struct ibmveth_adapter *adapter = netdev->priv;
	union ibmveth_buf_desc desc;
	unsigned long lpar_rc;
	unsigned long correlator;
	unsigned long flags;
	unsigned int retry_count;
	unsigned int tx_dropped = 0;
	unsigned int tx_bytes = 0;
	unsigned int tx_packets = 0;
	unsigned int tx_send_failed = 0;
	unsigned int tx_map_failed = 0;

	desc.fields.flags_len = IBMVETH_BUF_VALID | skb->len;
	desc.fields.address = dma_map_single(&adapter->vdev->dev, skb->data,
					     skb->len, DMA_TO_DEVICE);

	if (skb->ip_summed == CHECKSUM_PARTIAL &&
	    ip_hdr(skb)->protocol != IPPROTO_TCP && skb_checksum_help(skb)) {
		ibmveth_error_printk("tx: failed to checksum packet\n");
		tx_dropped++;
		goto out;
	}

	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		unsigned char *buf = skb_transport_header(skb) + skb->csum_offset;

		desc.fields.flags_len |= (IBMVETH_BUF_NO_CSUM | IBMVETH_BUF_CSUM_GOOD);

		/* Need to zero out the checksum */
		buf[0] = 0;
		buf[1] = 0;
	}

	if (dma_mapping_error(desc.fields.address)) {
		ibmveth_error_printk("tx: unable to map xmit buffer\n");
		tx_map_failed++;
		tx_dropped++;
		goto out;
	}

	/* send the frame. Arbitrarily set retrycount to 1024 */
	correlator = 0;
	retry_count = 1024;
	do {
		lpar_rc = h_send_logical_lan(adapter->vdev->unit_address,
					     desc.desc, 0, 0, 0, 0, 0,
					     correlator, &correlator);
	} while ((lpar_rc == H_BUSY) && (retry_count--));

	if(lpar_rc != H_SUCCESS && lpar_rc != H_DROPPED) {
		ibmveth_error_printk("tx: h_send_logical_lan failed with rc=%ld\n", lpar_rc);
		ibmveth_error_printk("tx: valid=%d, len=%d, address=0x%08x\n",
				     (desc.fields.flags_len & IBMVETH_BUF_VALID) ? 1 : 0,
				     skb->len, desc.fields.address);
		tx_send_failed++;
		tx_dropped++;
	} else {
		tx_packets++;
		tx_bytes += skb->len;
		netdev->trans_start = jiffies;
	}

	dma_unmap_single(&adapter->vdev->dev, desc.fields.address,
			 skb->len, DMA_TO_DEVICE);

out:	spin_lock_irqsave(&adapter->stats_lock, flags);
	netdev->stats.tx_dropped += tx_dropped;
	netdev->stats.tx_bytes += tx_bytes;
	netdev->stats.tx_packets += tx_packets;
	adapter->tx_send_failed += tx_send_failed;
	adapter->tx_map_failed += tx_map_failed;
	spin_unlock_irqrestore(&adapter->stats_lock, flags);

	dev_kfree_skb(skb);
	return 0;
}

static int ibmveth_poll(struct napi_struct *napi, int budget)
{
	struct ibmveth_adapter *adapter = container_of(napi, struct ibmveth_adapter, napi);
	struct net_device *netdev = adapter->netdev;
	int frames_processed = 0;
	unsigned long lpar_rc;

 restart_poll:
	do {
		struct sk_buff *skb;

		if (!ibmveth_rxq_pending_buffer(adapter))
			break;

		rmb();
		if (!ibmveth_rxq_buffer_valid(adapter)) {
			wmb(); /* suggested by larson1 */
			adapter->rx_invalid_buffer++;
			ibmveth_debug_printk("recycling invalid buffer\n");
			ibmveth_rxq_recycle_buffer(adapter);
		} else {
			int length = ibmveth_rxq_frame_length(adapter);
			int offset = ibmveth_rxq_frame_offset(adapter);
			int csum_good = ibmveth_rxq_csum_good(adapter);

			skb = ibmveth_rxq_get_buffer(adapter);
			if (csum_good)
				skb->ip_summed = CHECKSUM_UNNECESSARY;

			ibmveth_rxq_harvest_buffer(adapter);

			skb_reserve(skb, offset);
			skb_put(skb, length);
			skb->protocol = eth_type_trans(skb, netdev);

			netif_receive_skb(skb);	/* send it up */

			netdev->stats.rx_packets++;
			netdev->stats.rx_bytes += length;
			frames_processed++;
			netdev->last_rx = jiffies;
		}
	} while (frames_processed < budget);

	ibmveth_replenish_task(adapter);

	if (frames_processed < budget) {
		/* We think we are done - reenable interrupts,
		 * then check once more to make sure we are done.
		 */
		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
				       VIO_IRQ_ENABLE);

		ibmveth_assert(lpar_rc == H_SUCCESS);

		netif_rx_complete(netdev, napi);

		if (ibmveth_rxq_pending_buffer(adapter) &&
		    netif_rx_reschedule(netdev, napi)) {
			lpar_rc = h_vio_signal(adapter->vdev->unit_address,
					       VIO_IRQ_DISABLE);
			goto restart_poll;
		}
	}

	return frames_processed;
}

static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance)
{
	struct net_device *netdev = dev_instance;
	struct ibmveth_adapter *adapter = netdev->priv;
	unsigned long lpar_rc;

	if (netif_rx_schedule_prep(netdev, &adapter->napi)) {
		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
				       VIO_IRQ_DISABLE);
		ibmveth_assert(lpar_rc == H_SUCCESS);
		__netif_rx_schedule(netdev, &adapter->napi);
	}
	return IRQ_HANDLED;
}

static void ibmveth_set_multicast_list(struct net_device *netdev)
{
	struct ibmveth_adapter *adapter = netdev->priv;
	unsigned long lpar_rc;

	if((netdev->flags & IFF_PROMISC) || (netdev->mc_count > adapter->mcastFilterSize)) {
		lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
					   IbmVethMcastEnableRecv |
					   IbmVethMcastDisableFiltering,
					   0);
		if(lpar_rc != H_SUCCESS) {
			ibmveth_error_printk("h_multicast_ctrl rc=%ld when entering promisc mode\n", lpar_rc);
		}
	} else {
		struct dev_mc_list *mclist = netdev->mc_list;
		int i;
		/* clear the filter table & disable filtering */
		lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
					   IbmVethMcastEnableRecv |
					   IbmVethMcastDisableFiltering |
					   IbmVethMcastClearFilterTable,
					   0);
		if(lpar_rc != H_SUCCESS) {
			ibmveth_error_printk("h_multicast_ctrl rc=%ld when attempting to clear filter table\n", lpar_rc);
		}
		/* add the addresses to the filter table */
		for(i = 0; i < netdev->mc_count; ++i, mclist = mclist->next) {
			// add the multicast address to the filter table
			unsigned long mcast_addr = 0;