forcedeth-2.6.17-ethercat.c

	writel(NVREG_TXRXCTL_BIT2 | NVREG_TXRXCTL_RESET | np->txrxctl_bits, base + NvRegTxRxControl);
	pci_push(base);
	udelay(NV_TXRX_RESET_DELAY);
	writel(NVREG_TXRXCTL_BIT2 | np->txrxctl_bits, base + NvRegTxRxControl);
	pci_push(base);
}

static void nv_mac_reset(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);
	u8 __iomem *base = get_hwbase(dev);

	dprintk(KERN_DEBUG "%s: nv_mac_reset\n", dev->name);
	writel(NVREG_TXRXCTL_BIT2 | NVREG_TXRXCTL_RESET | np->txrxctl_bits, base + NvRegTxRxControl);
	pci_push(base);
	writel(NVREG_MAC_RESET_ASSERT, base + NvRegMacReset);
	pci_push(base);
	udelay(NV_MAC_RESET_DELAY);
	writel(0, base + NvRegMacReset);
	pci_push(base);
	udelay(NV_MAC_RESET_DELAY);
	writel(NVREG_TXRXCTL_BIT2 | np->txrxctl_bits, base + NvRegTxRxControl);
	pci_push(base);
}

/*
 * nv_get_stats: dev->get_stats function
 * Get latest stats value from the nic.
 * Called with read_lock(&dev_base_lock) held for read -
 * only synchronized against unregister_netdevice.
 */
static struct net_device_stats *nv_get_stats(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);

	/* It seems that the nic always generates interrupts and doesn't
	 * accumulate errors internally. Thus the current values in np->stats
	 * are already up to date.
	 */
	return &np->stats;
}

/*
 * nv_alloc_rx: fill rx ring entries.
 * Return 1 if the allocations for the skbs failed and the
 * rx engine is without Available descriptors
 */
static int nv_alloc_rx(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);
	unsigned int refill_rx = np->refill_rx;
	int nr;

	while (np->cur_rx != refill_rx) {
		struct sk_buff *skb;

		nr = refill_rx % RX_RING;
		if (np->rx_skbuff[nr] == NULL) {

			skb = dev_alloc_skb(np->rx_buf_sz + NV_RX_ALLOC_PAD);
			if (!skb)
				break;

			skb->dev = dev;
			np->rx_skbuff[nr] = skb;
		} else {
			skb = np->rx_skbuff[nr];
		}
		np->rx_dma[nr] = pci_map_single(np->pci_dev, skb->data,
					skb->end-skb->data, PCI_DMA_FROMDEVICE);
		if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) {
			np->rx_ring.orig[nr].PacketBuffer = cpu_to_le32(np->rx_dma[nr]);
			wmb();
			np->rx_ring.orig[nr].FlagLen = cpu_to_le32(np->rx_buf_sz | NV_RX_AVAIL);
		} else {
			np->rx_ring.ex[nr].PacketBufferHigh = cpu_to_le64(np->rx_dma[nr]) >> 32;
			np->rx_ring.ex[nr].PacketBufferLow = cpu_to_le64(np->rx_dma[nr]) & 0x0FFFFFFFF;
			wmb();
			np->rx_ring.ex[nr].FlagLen = cpu_to_le32(np->rx_buf_sz | NV_RX2_AVAIL);
		}
		dprintk(KERN_DEBUG "%s: nv_alloc_rx: Packet %d marked as Available\n",
					dev->name, refill_rx);
		refill_rx++;
	}
	np->refill_rx = refill_rx;
	if (np->cur_rx - refill_rx == RX_RING)
		return 1;
	return 0;
}

static void nv_do_rx_refill(unsigned long data)
{
	struct net_device *dev = (struct net_device *) data;
	struct fe_priv *np = netdev_priv(dev);

	if (!using_multi_irqs(dev)) {
		if (np->msi_flags & NV_MSI_X_ENABLED)
			disable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector);
		else
			disable_irq(dev->irq);
	} else {
		disable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector);
	}
	if (nv_alloc_rx(dev)) {
		spin_lock_irq(&np->lock);
		if (!np->in_shutdown)
			mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
		spin_unlock_irq(&np->lock);
	}
	if (!using_multi_irqs(dev)) {
		if (np->msi_flags & NV_MSI_X_ENABLED)
			enable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector);
		else
			enable_irq(dev->irq);
	} else {
		enable_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector);
	}
}

static void nv_init_rx(struct net_device *dev) 
{
	struct fe_priv *np = netdev_priv(dev);
	int i;

	np->cur_rx = RX_RING;
	np->refill_rx = 0;
	for (i = 0; i < RX_RING; i++)
		if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2)
			np->rx_ring.orig[i].FlagLen = 0;
	        else
			np->rx_ring.ex[i].FlagLen = 0;
}

static void nv_init_tx(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);
	int i;

	np->next_tx = np->nic_tx = 0;
	for (i = 0; i < TX_RING; i++) {
		if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2)
			np->tx_ring.orig[i].FlagLen = 0;
	        else
			np->tx_ring.ex[i].FlagLen = 0;
		np->tx_skbuff[i] = NULL;
		np->tx_dma[i] = 0;
	}
}

static int nv_init_ring(struct net_device *dev)
{
	nv_init_tx(dev);
	nv_init_rx(dev);
	return nv_alloc_rx(dev);
}

static int nv_release_txskb(struct net_device *dev, unsigned int skbnr)
{
	struct fe_priv *np = netdev_priv(dev);

	dprintk(KERN_INFO "%s: nv_release_txskb for skbnr %d\n",
		dev->name, skbnr);

	if (np->tx_dma[skbnr]) {
		pci_unmap_page(np->pci_dev, np->tx_dma[skbnr],
			       np->tx_dma_len[skbnr],
			       PCI_DMA_TODEVICE);
		np->tx_dma[skbnr] = 0;
	}

	if (np->tx_skbuff[skbnr]) {
		if (!np->ecdev) dev_kfree_skb_any(np->tx_skbuff[skbnr]);
		np->tx_skbuff[skbnr] = NULL;
		return 1;
	} else {
		return 0;
	}
}

static void nv_drain_tx(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);
	unsigned int i;
	
	for (i = 0; i < TX_RING; i++) {
		if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2)
			np->tx_ring.orig[i].FlagLen = 0;
		else
			np->tx_ring.ex[i].FlagLen = 0;
		if (nv_release_txskb(dev, i))
			np->stats.tx_dropped++;
	}
}

static void nv_drain_rx(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);
	int i;
	for (i = 0; i < RX_RING; i++) {
		if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2)
			np->rx_ring.orig[i].FlagLen = 0;
		else
			np->rx_ring.ex[i].FlagLen = 0;
		wmb();
		if (np->rx_skbuff[i]) {
			pci_unmap_single(np->pci_dev, np->rx_dma[i],
						np->rx_skbuff[i]->end-np->rx_skbuff[i]->data,
						PCI_DMA_FROMDEVICE);
			if (!np->ecdev) dev_kfree_skb(np->rx_skbuff[i]);
			np->rx_skbuff[i] = NULL;
		}
	}
}

static void drain_ring(struct net_device *dev)
{
	nv_drain_tx(dev);
	nv_drain_rx(dev);
}

/*
 * nv_start_xmit: dev->hard_start_xmit function
 * Called with dev->xmit_lock held.
 */
static int nv_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);
	u32 tx_flags = 0;
	u32 tx_flags_extra = (np->desc_ver == DESC_VER_1 ? NV_TX_LASTPACKET : NV_TX2_LASTPACKET);
	unsigned int fragments = skb_shinfo(skb)->nr_frags;
	unsigned int nr = (np->next_tx - 1) % TX_RING;
	unsigned int start_nr = np->next_tx % TX_RING;
	unsigned int i;
	u32 offset = 0;
	u32 bcnt;
	u32 size = skb->len-skb->data_len;
	u32 entries = (size >> NV_TX2_TSO_MAX_SHIFT) + ((size & (NV_TX2_TSO_MAX_SIZE-1)) ? 1 : 0);
	u32 tx_flags_vlan = 0;

	/* add fragments to entries count */
	for (i = 0; i < fragments; i++) {
		entries += (skb_shinfo(skb)->frags[i].size >> NV_TX2_TSO_MAX_SHIFT) +
			   ((skb_shinfo(skb)->frags[i].size & (NV_TX2_TSO_MAX_SIZE-1)) ? 1 : 0);
	}

	if (!np->ecdev) {
		spin_lock_irq(&np->lock);

		if ((np->next_tx - np->nic_tx + entries - 1) > TX_LIMIT_STOP) {
			spin_unlock_irq(&np->lock);
			netif_stop_queue(dev);
			return NETDEV_TX_BUSY;
        }
	}

	/* setup the header buffer */
	do {
		bcnt = (size > NV_TX2_TSO_MAX_SIZE) ? NV_TX2_TSO_MAX_SIZE : size;
		nr = (nr + 1) % TX_RING;

		np->tx_dma[nr] = pci_map_single(np->pci_dev, skb->data + offset, bcnt,
						PCI_DMA_TODEVICE);
		np->tx_dma_len[nr] = bcnt;

		if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) {
			np->tx_ring.orig[nr].PacketBuffer = cpu_to_le32(np->tx_dma[nr]);
			np->tx_ring.orig[nr].FlagLen = cpu_to_le32((bcnt-1) | tx_flags);
		} else {
			np->tx_ring.ex[nr].PacketBufferHigh = cpu_to_le64(np->tx_dma[nr]) >> 32;
			np->tx_ring.ex[nr].PacketBufferLow = cpu_to_le64(np->tx_dma[nr]) & 0x0FFFFFFFF;
			np->tx_ring.ex[nr].FlagLen = cpu_to_le32((bcnt-1) | tx_flags);
		}
		tx_flags = np->tx_flags;
		offset += bcnt;
		size -= bcnt;
	} while(size);

	/* setup the fragments */
	for (i = 0; i < fragments; i++) {
		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
		u32 size = frag->size;
		offset = 0;

		do {
			bcnt = (size > NV_TX2_TSO_MAX_SIZE) ? NV_TX2_TSO_MAX_SIZE : size;
			nr = (nr + 1) % TX_RING;

			np->tx_dma[nr] = pci_map_page(np->pci_dev, frag->page, frag->page_offset+offset, bcnt,
						      PCI_DMA_TODEVICE);
			np->tx_dma_len[nr] = bcnt;

			if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) {
				np->tx_ring.orig[nr].PacketBuffer = cpu_to_le32(np->tx_dma[nr]);
				np->tx_ring.orig[nr].FlagLen = cpu_to_le32((bcnt-1) | tx_flags);
			} else {
				np->tx_ring.ex[nr].PacketBufferHigh = cpu_to_le64(np->tx_dma[nr]) >> 32;
				np->tx_ring.ex[nr].PacketBufferLow = cpu_to_le64(np->tx_dma[nr]) & 0x0FFFFFFFF;
				np->tx_ring.ex[nr].FlagLen = cpu_to_le32((bcnt-1) | tx_flags);
			}
			offset += bcnt;
			size -= bcnt;
		} while (size);
	}

	/* set last fragment flag  */
	if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) {
		np->tx_ring.orig[nr].FlagLen |= cpu_to_le32(tx_flags_extra);
	} else {
		np->tx_ring.ex[nr].FlagLen |= cpu_to_le32(tx_flags_extra);
	}

	np->tx_skbuff[nr] = skb;

#ifdef NETIF_F_TSO
	if (skb_shinfo(skb)->tso_size)
		tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->tso_size << NV_TX2_TSO_SHIFT);
	else
#endif
	tx_flags_extra = (skb->ip_summed == CHECKSUM_HW ? (NV_TX2_CHECKSUM_L3|NV_TX2_CHECKSUM_L4) : 0);

	/* vlan tag */
	if (np->vlangrp && vlan_tx_tag_present(skb)) {
		tx_flags_vlan = NV_TX3_VLAN_TAG_PRESENT | vlan_tx_tag_get(skb);
	}

	/* set tx flags */
	if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) {
		np->tx_ring.orig[start_nr].FlagLen |= cpu_to_le32(tx_flags | tx_flags_extra);
	} else {
		np->tx_ring.ex[start_nr].TxVlan = cpu_to_le32(tx_flags_vlan);
		np->tx_ring.ex[start_nr].FlagLen |= cpu_to_le32(tx_flags | tx_flags_extra);
	}	

	dprintk(KERN_DEBUG "%s: nv_start_xmit: packet %d (entries %d) queued for transmission. tx_flags_extra: %x\n",
		dev->name, np->next_tx, entries, tx_flags_extra);
	{
		int j;
		for (j=0; j<64; j++) {
			if ((j%16) == 0)
				dprintk("\n%03x:", j);
			dprintk(" %02x", ((unsigned char*)skb->data)[j]);
		}
		dprintk("\n");
	}

	np->next_tx += entries;

	dev->trans_start = jiffies;
	if (!np->ecdev) spin_unlock_irq(&np->lock);
	writel(NVREG_TXRXCTL_KICK|np->txrxctl_bits, get_hwbase(dev) + NvRegTxRxControl);
	pci_push(get_hwbase(dev));
	return NETDEV_TX_OK;
}

/*
 * nv_tx_done: check for completed packets, release the skbs.
 *
 * Caller must own np->lock.
 */
static void nv_tx_done(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);
	u32 Flags;
	unsigned int i;
	struct sk_buff *skb;

	while (np->nic_tx != np->next_tx) {
		i = np->nic_tx % TX_RING;

		if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2)
			Flags = le32_to_cpu(np->tx_ring.orig[i].FlagLen);
		else
			Flags = le32_to_cpu(np->tx_ring.ex[i].FlagLen);

		dprintk(KERN_DEBUG "%s: nv_tx_done: looking at packet %d, Flags 0x%x.\n",
					dev->name, np->nic_tx, Flags);
		if (Flags & NV_TX_VALID)
			break;
		if (np->desc_ver == DESC_VER_1) {
			if (Flags & NV_TX_LASTPACKET) {
				skb = np->tx_skbuff[i];
				if (Flags & (NV_TX_RETRYERROR|NV_TX_CARRIERLOST|NV_TX_LATECOLLISION|
					     NV_TX_UNDERFLOW|NV_TX_ERROR)) {
					if (Flags & NV_TX_UNDERFLOW)
						np->stats.tx_fifo_errors++;
					if (Flags & NV_TX_CARRIERLOST)
						np->stats.tx_carrier_errors++;
					np->stats.tx_errors++;
				} else {
					np->stats.tx_packets++;
					np->stats.tx_bytes += skb->len;
				}
			}
		} else {
			if (Flags & NV_TX2_LASTPACKET) {
				skb = np->tx_skbuff[i];
				if (Flags & (NV_TX2_RETRYERROR|NV_TX2_CARRIERLOST|NV_TX2_LATECOLLISION|
					     NV_TX2_UNDERFLOW|NV_TX2_ERROR)) {
					if (Flags & NV_TX2_UNDERFLOW)
						np->stats.tx_fifo_errors++;
					if (Flags & NV_TX2_CARRIERLOST)
						np->stats.tx_carrier_errors++;
					np->stats.tx_errors++;
				} else {
					np->stats.tx_packets++;
					np->stats.tx_bytes += skb->len;
				}				
			}
		}
		nv_release_txskb(dev, i);
		np->nic_tx++;
	}
	if (!np->ecdev && np->next_tx - np->nic_tx < TX_LIMIT_START)
		netif_wake_queue(dev);
}

/*
 * nv_tx_timeout: dev->tx_timeout function
 * Called with dev->xmit_lock held.
 */
static void nv_tx_timeout(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);
	u8 __iomem *base = get_hwbase(dev);
	u32 status;

	if (np->msi_flags & NV_MSI_X_ENABLED)
		status = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQSTAT_MASK;
	else
		status = readl(base + NvRegIrqStatus) & NVREG_IRQSTAT_MASK;

	printk(KERN_INFO "%s: Got tx_timeout. irq: %08x\n", dev->name, status);

	{
		int i;

		printk(KERN_INFO "%s: Ring at %lx: next %d nic %d\n",
				dev->name, (unsigned long)np->ring_addr,
				np->next_tx, np->nic_tx);
		printk(KERN_INFO "%s: Dumping tx registers\n", dev->name);
		for (i=0;i<=np->register_size;i+= 32) {
			printk(KERN_INFO "%3x: %08x %08x %08x %08x %08x %08x %08x %08x\n",
					i,
					readl(base + i + 0), readl(base + i + 4),
					readl(base + i + 8), readl(base + i + 12),
					readl(base + i + 16), readl(base + i + 20),
					readl(base + i + 24), readl(base + i + 28));
		}
		printk(KERN_INFO "%s: Dumping tx ring\n", dev->name);
		for (i=0;i<TX_RING;i+= 4) {
			if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) {
				printk(KERN_INFO "%03x: %08x %08x // %08x %08x // %08x %08x // %08x %08x\n",
				       i, 
				       le32_to_cpu(np->tx_ring.orig[i].PacketBuffer),
				       le32_to_cpu(np->tx_ring.orig[i].FlagLen),
				       le32_to_cpu(np->tx_ring.orig[i+1].PacketBuffer),
				       le32_to_cpu(np->tx_ring.orig[i+1].FlagLen),
				       le32_to_cpu(np->tx_ring.orig[i+2].PacketBuffer),
				       le32_to_cpu(np->tx_ring.orig[i+2].FlagLen),
				       le32_to_cpu(np->tx_ring.orig[i+3].PacketBuffer),
				       le32_to_cpu(np->tx_ring.orig[i+3].FlagLen));
			} else {
				printk(KERN_INFO "%03x: %08x %08x %08x // %08x %08x %08x // %08x %08x %08x // %08x %08x %08x\n",
				       i, 
				       le32_to_cpu(np->tx_ring.ex[i].PacketBufferHigh),
				       le32_to_cpu(np->tx_ring.ex[i].PacketBufferLow),
				       le32_to_cpu(np->tx_ring.ex[i].FlagLen),
				       le32_to_cpu(np->tx_ring.ex[i+1].PacketBufferHigh),
				       le32_to_cpu(np->tx_ring.ex[i+1].PacketBufferLow),
				       le32_to_cpu(np->tx_ring.ex[i+1].FlagLen),
				       le32_to_cpu(np->tx_ring.ex[i+2].PacketBufferHigh),
				       le32_to_cpu(np->tx_ring.ex[i+2].PacketBufferLow),
				       le32_to_cpu(np->tx_ring.ex[i+2].FlagLen),
				       le32_to_cpu(np->tx_ring.ex[i+3].PacketBufferHigh),
				       le32_to_cpu(np->tx_ring.ex[i+3].PacketBufferLow),
				       le32_to_cpu(np->tx_ring.ex[i+3].FlagLen));
			}
		}
	}

	if (!np->ecdev) spin_lock_irq(&np->lock);

	/* 1) stop tx engine */
	nv_stop_tx(dev);

	/* 2) check that the packets were not sent already: */
	nv_tx_done(dev);

	/* 3) if there are dead entries: clear everything */
	if (np->next_tx != np->nic_tx) {
		printk(KERN_DEBUG "%s: tx_timeout: dead entries!\n", dev->name);
		nv_drain_tx(dev);
		np->next_tx = np->nic_tx = 0;
		setup_hw_rings(dev, NV_SETUP_TX_RING);
		if (!np->ecdev) netif_wake_queue(dev);
	}

	/* 4) restart tx engine */
	nv_start_tx(dev);
	if (!np->ecdev) spin_unlock_irq(&np->lock);
}

/*
 * Called when the nic notices a mismatch between the actual data len on the
 * wire and the len indicated in the 802 header
 */
static int nv_getlen(struct net_device *dev, void *packet, int datalen)
{
	int hdrlen;	/* length of the 802 header */
	int protolen;	/* length as stored in the proto field */

	/* 1) calculate len according to header */
	if ( ((struct vlan_ethhdr *)packet)->h_vlan_proto == __constant_htons(ETH_P_8021Q)) {
		protolen = ntohs( ((struct vlan_ethhdr *)packet)->h_vlan_encapsulated_proto );
		hdrlen = VLAN_HLEN;
	} else {
		protolen = ntohs( ((struct ethhdr *)packet)->h_proto);
		hdrlen = ETH_HLEN;
	}
	dprintk(KERN_DEBUG "%s: nv_getlen: datalen %d, protolen %d, hdrlen %d\n",
				dev->name, datalen, protolen, hdrlen);
	if (protolen > ETH_DATA_LEN)
		return datalen; /* Value in proto field not a len, no checks possible */

	protolen += hdrlen;
	/* consistency checks: */
	if (datalen > ETH_ZLEN) {
		if (datalen >= protolen) {
			/* more data on wire than in 802 header, trim of
			 * additional data.
			 */
			dprintk(KERN_DEBUG "%s: nv_getlen: accepting %d bytes.\n",
					dev->name, protolen);
			return protolen;
		} else {
			/* less data on wire than mentioned in header.
			 * Discard the packet.
			 */
			dprintk(KERN_DEBUG "%s: nv_getlen: discarding long packet.\n",
					dev->name);
			return -1;
		}
	} else {
		/* short packet. Accept only if 802 values are also short */
		if (protolen > ETH_ZLEN) {
			dprintk(KERN_DEBUG "%s: nv_getlen: discarding short packet.\n",
					dev->name);
			return -1;
		}
		dprintk(KERN_DEBUG "%s: nv_getlen: accepting %d bytes.\n",
				dev->name, datalen);
		return datalen;
	}
}

static void nv_rx_process(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);
	u32 Flags;
	u32 vlanflags = 0;


	for (;;) {
		struct sk_buff *skb;
		int len;
		int i;
		if (np->cur_rx - np->refill_rx >= RX_RING)
			break;	/* we scanned the whole ring - do not continue */

		i = np->cur_rx % RX_RING;
		if (np->desc_ver == DESC_VER_1 || np->desc_ver == DESC_VER_2) {
			Flags = le32_to_cpu(np->rx_ring.orig[i].FlagLen);
			len = nv_descr_getlength(&np->rx_ring.orig[i], np->desc_ver);
		} else {
			Flags = le32_to_cpu(np->rx_ring.ex[i].FlagLen);
			len = nv_descr_getlength_ex(&np->rx_ring.ex[i], np->desc_ver);
			vlanflags = le32_to_cpu(np->rx_ring.ex[i].PacketBufferLow);
		}

		dprintk(KERN_DEBUG "%s: nv_rx_process: looking at packet %d, Flags 0x%x.\n",
					dev->name, np->cur_rx, Flags);

		if (Flags & NV_RX_AVAIL)
			break;	/* still owned by hardware, */

		/*
		 * the packet is for us - immediately tear down the pci mapping.
		 * TODO: check if a prefetch of the first cacheline improves
		 * the performance.
		 */
		pci_unmap_single(np->pci_dev, np->rx_dma[i],
				np->rx_skbuff[i]->end-np->rx_skbuff[i]->data,
				PCI_DMA_FROMDEVICE);

		{
			int j;
			dprintk(KERN_DEBUG "Dumping packet (flags 0x%x).",Flags);
			for (j=0; j<64; j++) {
				if ((j%16) == 0)
					dprintk("\n%03x:", j);
				dprintk(" %02x", ((unsigned char*)np->rx_skbuff[i]->data)[j]);
			}
			dprintk("\n");
		}
		/* look at what we actually got: */
		if (np->desc_ver == DESC_VER_1) {
			if (!(Flags & NV_RX_DESCRIPTORVALID))
				goto next_pkt;

			if (Flags & NV_RX_ERROR) {
				if (Flags & NV_RX_MISSEDFRAME) {
					np->stats.rx_missed_errors++;
					np->stats.rx_errors++;
					goto next_pkt;
				}
				if (Flags & (NV_RX_ERROR1|NV_RX_ERROR2|NV_RX_ERROR3)) {
					np->stats.rx_errors++;
					goto next_pkt;
				}
				if (Flags & NV_RX_CRCERR) {
					np->stats.rx_crc_errors++;
					np->stats.rx_errors++;
					goto next_pkt;
				}
				if (Flags & NV_RX_OVERFLOW) {
					np->stats.rx_over_errors++;
					np->stats.rx_errors++;
					goto next_pkt;
				}
				if (Flags & NV_RX_ERROR4) {
					len = nv_getlen(dev, np->rx_skbuff[i]->data, len);
					if (len < 0) {
						np->stats.rx_errors++;
						goto next_pkt;
					}
				}
				/* framing errors are soft errors. */
				if (Flags & NV_RX_FRAMINGERR) {
					if (Flags & NV_RX_SUBSTRACT1) {
						len--;
					}
				}
			}
		} else {
			if (!(Flags & NV_RX2_DESCRIPTORVALID))
				goto next_pkt;

			if (Flags & NV_RX2_ERROR) {
				if (Flags & (NV_RX2_ERROR1|NV_RX2_ERROR2|NV_RX2_ERROR3)) {
					np->stats.rx_errors++;
					goto next_pkt;
				}
				if (Flags & NV_RX2_CRCERR) {
					np->stats.rx_crc_errors++;
					np->stats.rx_errors++;
					goto next_pkt;
				}
				if (Flags & NV_RX2_OVERFLOW) {
					np->stats.rx_over_errors++;
					np->stats.rx_errors++;
					goto next_pkt;
				}
				if (Flags & NV_RX2_ERROR4) {
					len = nv_getlen(dev, np->rx_skbuff[i]->data, len);
					if (len < 0) {
						np->stats.rx_errors++;
						goto next_pkt;
					}
				}
				/* framing errors are soft errors */
				if (Flags & NV_RX2_FRAMINGERR) {
					if (Flags & NV_RX2_SUBSTRACT1) {
						len--;
					}
				}
			}
			Flags &= NV_RX2_CHECKSUMMASK;
			if (Flags == NV_RX2_CHECKSUMOK1 ||
					Flags == NV_RX2_CHECKSUMOK2 ||
					Flags == NV_RX2_CHECKSUMOK3) {
				dprintk(KERN_DEBUG "%s: hw checksum hit!.\n", dev->name);
				np->rx_skbuff[i]->ip_summed = CHECKSUM_UNNECESSARY;
			} else {
				dprintk(KERN_DEBUG "%s: hwchecksum miss!.\n", dev->name);
			}
		}
		if (np->ecdev) {
			ecdev_receive(np->ecdev, np->rx_skbuff[i]->data, len);
		}
		else {
			/* got a valid packet - forward it to the network core */
			skb = np->rx_skbuff[i];
			np->rx_skbuff[i] = NULL;

			skb_put(skb, len);
			skb->protocol = eth_type_trans(skb, dev);
			dprintk(KERN_DEBUG "%s: nv_rx_process: packet %d with %d bytes, proto %d accepted.\n",
					dev->name, np->cur_rx, len, skb->protocol);
			if (np->vlangrp && (vlanflags & NV_RX3_VLAN_TAG_PRESENT)) {
				vlan_hwaccel_rx(skb, np->vlangrp, vlanflags & NV_RX3_VLAN_TAG_MASK);
			} else {
				netif_rx(skb);
			}
		}
		dev->last_rx = jiffies;
		np->stats.rx_packets++;
		np->stats.rx_bytes += len;
next_pkt:
		np->cur_rx++;
	}
}

static void set_bufsize(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);

	if (dev->mtu <= ETH_DATA_LEN)
		np->rx_buf_sz = ETH_DATA_LEN + NV_RX_HEADERS;
	else
		np->rx_buf_sz = dev->mtu + NV_RX_HEADERS;
}

/*
 * nv_change_mtu: dev->change_mtu function
 * Called with dev_base_lock held for read.
 */
static int nv_change_mtu(struct net_device *dev, int new_mtu)
{
	struct fe_priv *np = netdev_priv(dev);
	int old_mtu;

	if (new_mtu < 64 || new_mtu > np->pkt_limit)
		return -EINVAL;

	old_mtu = dev->mtu;
	dev->mtu = new_mtu;

	/* return early if the buffer sizes will not change */
	if (old_mtu <= ETH_DATA_LEN && new_mtu <= ETH_DATA_LEN)
		return 0;
	if (old_mtu == new_mtu)
		return 0;

	/* synchronized against open : rtnl_lock() held by caller */
	if (netif_running(dev)) {
		u8 __iomem *base = get_hwbase(dev);
		/*
		 * It seems that the nic preloads valid ring entries into an
		 * internal buffer. The procedure for flushing everything is
		 * guessed, there is probably a simpler approach.
		 * Changing the MTU is a rare event, it shouldn't matter.
		 */
		nv_disable_irq(dev);
		spin_lock_bh(&dev->xmit_lock);
		spin_lock(&np->lock);
		/* stop engines */
		nv_stop_rx(dev);
		nv_stop_tx(dev);
		nv_txrx_reset(dev);
		/* drain rx queue */
		nv_drain_rx(dev);
		nv_drain_tx(dev);
		/* reinit driver view of the rx queue */
		nv_init_rx(dev);
		nv_init_tx(dev);
		/* alloc new rx buffers */
		set_bufsize(dev);
		if (nv_alloc_rx(dev)) {
			if (!np->in_shutdown)
				mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
		}
		/* reinit nic view of the rx queue */
		writel(np->rx_buf_sz, base + NvRegOffloadConfig);
		setup_hw_rings(dev, NV_SETUP_RX_RING | NV_SETUP_TX_RING);
		writel( ((RX_RING-1) << NVREG_RINGSZ_RXSHIFT) + ((TX_RING-1) << NVREG_RINGSZ_TXSHIFT),
			base + NvRegRingSizes);
		pci_push(base);
		writel(NVREG_TXRXCTL_KICK|np->txrxctl_bits, get_hwbase(dev) + NvRegTxRxControl);
		pci_push(base);

		/* restart rx engine */
		nv_start_rx(dev);
		nv_start_tx(dev);
		spin_unlock(&np->lock);
		spin_unlock_bh(&dev->xmit_lock);
		nv_enable_irq(dev);
	}
	return 0;
}

static void nv_copy_mac_to_hw(struct net_device *dev)
{
	u8 __iomem *base = get_hwbase(dev);
	u32 mac[2];

	mac[0] = (dev->dev_addr[0] << 0) + (dev->dev_addr[1] << 8) +
			(dev->dev_addr[2] << 16) + (dev->dev_addr[3] << 24);
	mac[1] = (dev->dev_addr[4] << 0) + (dev->dev_addr[5] << 8);

	writel(mac[0], base + NvRegMacAddrA);
	writel(mac[1], base + NvRegMacAddrB);
}

/*
 * nv_set_mac_address: dev->set_mac_address function
 * Called with rtnl_lock() held.
 */
static int nv_set_mac_address(struct net_device *dev, void *addr)
{
	struct fe_priv *np = netdev_priv(dev);
	struct sockaddr *macaddr = (struct sockaddr*)addr;

	if(!is_valid_ether_addr(macaddr->sa_data))
		return -EADDRNOTAVAIL;

	/* synchronized against open : rtnl_lock() held by caller */
	memcpy(dev->dev_addr, macaddr->sa_data, ETH_ALEN);

	if (netif_running(dev)) {
		spin_lock_bh(&dev->xmit_lock);
		spin_lock_irq(&np->lock);

		/* stop rx engine */
		nv_stop_rx(dev);

		/* set mac address */
		nv_copy_mac_to_hw(dev);

		/* restart rx engine */
		nv_start_rx(dev);
		spin_unlock_irq(&np->lock);
		spin_unlock_bh(&dev->xmit_lock);
	} else {
		nv_copy_mac_to_hw(dev);
	}
	return 0;
}

/*
 * nv_set_multicast: dev->set_multicast function
 * Called with dev->xmit_lock held.
 */
static void nv_set_multicast(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);
	u8 __iomem *base = get_hwbase(dev);
	u32 addr[2];
	u32 mask[2];
	u32 pff;

	memset(addr, 0, sizeof(addr));
	memset(mask, 0, sizeof(mask));

	if (dev->flags & IFF_PROMISC) {
		printk(KERN_NOTICE "%s: Promiscuous mode enabled.\n", dev->name);
		pff = NVREG_PFF_PROMISC;
	} else {
		pff = NVREG_PFF_MYADDR;

		if (dev->flags & IFF_ALLMULTI || dev->mc_list) {
			u32 alwaysOff[2];
			u32 alwaysOn[2];

			alwaysOn[0] = alwaysOn[1] = alwaysOff[0] = alwaysOff[1] = 0xffffffff;
			if (dev->flags & IFF_ALLMULTI) {
				alwaysOn[0] = alwaysOn[1] = alwaysOff[0] = alwaysOff[1] = 0;
			} else {
				struct dev_mc_list *walk;

				walk = dev->mc_list;
				while (walk != NULL) {
					u32 a, b;
					a = le32_to_cpu(*(u32 *) walk->dmi_addr);
					b = le16_to_cpu(*(u16 *) (&walk->dmi_addr[4]));
					alwaysOn[0] &= a;
					alwaysOff[0] &= ~a;
					alwaysOn[1] &= b;
					alwaysOff[1] &= ~b;
					walk = walk->next;
				}
			}
			addr[0] = alwaysOn[0];
			addr[1] = alwaysOn[1];
			mask[0] = alwaysOn[0] | alwaysOff[0];
			mask[1] = alwaysOn[1] | alwaysOff[1];
		}
	}
	addr[0] |= NVREG_MCASTADDRA_FORCE;
	pff |= NVREG_PFF_ALWAYS;
	spin_lock_irq(&np->lock);
	nv_stop_rx(dev);
	writel(addr[0], base + NvRegMulticastAddrA);
	writel(addr[1], base + NvRegMulticastAddrB);
	writel(mask[0], base + NvRegMulticastMaskA);
	writel(mask[1], base + NvRegMulticastMaskB);
	writel(pff, base + NvRegPacketFilterFlags);
	dprintk(KERN_INFO "%s: reconfiguration for multicast lists.\n",
		dev->name);
	nv_start_rx(dev);
	spin_unlock_irq(&np->lock);
}

/**
 * nv_update_linkspeed: Setup the MAC according to the link partner
 * @dev: Network device to be configured
 *
 * The function queries the PHY and checks if there is a link partner.
 * If yes, then it sets up the MAC accordingly. Otherwise, the MAC is
 * set to 10 MBit HD.
 *
 * The function returns 0 if there is no link partner and 1 if there is
 * a good link partner.
 */
static int nv_update_linkspeed(struct net_device *dev)
{
	struct fe_priv *np = netdev_priv(dev);
	u8 __iomem *base = get_hwbase(dev);
	int adv, lpa;
	int newls = np->linkspeed;
	int newdup = np->duplex;
	int mii_status;
	int retval = 0;
	u32 control_1000, status_1000, phyreg;

	/* BMSR_LSTATUS is latched, read it twice:
	 * we want the current value.
	 */
	mii_rw(dev, np->phyaddr, MII_BMSR, MII_READ);
	mii_status = mii_rw(dev, np->phyaddr, MII_BMSR, MII_READ);

	if (!(mii_status & BMSR_LSTATUS)) {
		dprintk(KERN_DEBUG "%s: no link detected by phy - falling back to 10HD.\n",
				dev->name);
		newls = NVREG_LINKSPEED_FORCE|NVREG_LINKSPEED_10;
		newdup = 0;
		retval = 0;
		goto set_speed;
	}

	if (np->autoneg == 0) {
		dprintk(KERN_DEBUG "%s: nv_update_linkspeed: autoneg off, PHY set to 0x%04x.\n",
				dev->name, np->fixed_mode);
		if (np->fixed_mode & LPA_100FULL) {
			newls = NVREG_LINKSPEED_FORCE|NVREG_LINKSPEED_100;
			newdup = 1;
		} else if (np->fixed_mode & LPA_100HALF) {
			newls = NVREG_LINKSPEED_FORCE|NVREG_LINKSPEED_100;
			newdup = 0;
		} else if (np->fixed_mode & LPA_10FULL) {
			newls = NVREG_LINKSPEED_FORCE|NVREG_LINKSPEED_10;
			newdup = 1;
		} else {
			newls = NVREG_LINKSPEED_FORCE|NVREG_LINKSPEED_10;
			newdup = 0;
		}
		retval = 1;
		goto set_speed;
	}
	/* check auto negotiation is complete */
	if (!(mii_status & BMSR_ANEGCOMPLETE)) {
		/* still in autonegotiation - configure nic for 10 MBit HD and wait. */
		newls = NVREG_LINKSPEED_FORCE|NVREG_LINKSPEED_10;
		newdup = 0;
		retval = 0;
		dprintk(KERN_DEBUG "%s: autoneg not completed - falling back to 10HD.\n", dev->name);
		goto set_speed;
	}

	retval = 1;
	if (np->gigabit == PHY_GIGABIT) {
		control_1000 = mii_rw(dev, np->phyaddr, MII_1000BT_CR, MII_READ);
		status_1000 = mii_rw(dev, np->phyaddr, MII_1000BT_SR, MII_READ);

		if ((control_1000 & ADVERTISE_1000FULL) &&
			(status_1000 & LPA_1000FULL)) {
			dprintk(KERN_DEBUG "%s: nv_update_linkspeed: GBit ethernet detected.\n",
				dev->name);
			newls = NVREG_LINKSPEED_FORCE|NVREG_LINKSPEED_1000;
			newdup = 1;
			goto set_speed;
		}
	}

	adv = mii_rw(dev, np->phyaddr, MII_ADVERTISE, MII_READ);
	lpa = mii_rw(dev, np->phyaddr, MII_LPA, MII_READ);
	dprintk(KERN_DEBUG "%s: nv_update_linkspeed: PHY advertises 0x%04x, lpa 0x%04x.\n",
				dev->name, adv, lpa);

	/* FIXME: handle parallel detection properly */
	lpa = lpa & adv;
	if (lpa & LPA_100FULL) {
		newls = NVREG_LINKSPEED_FORCE|NVREG_LINKSPEED_100;
		newdup = 1;
	} else if (lpa & LPA_100HALF) {
		newls = NVREG_LINKSPEED_FORCE|NVREG_LINKSPEED_100;
		newdup = 0;
	} else if (lpa & LPA_10FULL) {
		newls = NVREG_LINKSPEED_FORCE|NVREG_LINKSPEED_10;
		newdup = 1;
	} else if (lpa & LPA_10HALF) {