e1000_main.c

COPE the first practical network coding scheme which is developped on click

	for(i = 0; i < rx_ring->count; i++) {
		buffer_info = &rx_ring->buffer_info[i];
		if(buffer_info->skb) {

			pci_unmap_single(pdev,
					 buffer_info->dma,
					 buffer_info->length,
					 PCI_DMA_FROMDEVICE);

			dev_kfree_skb(buffer_info->skb);
			buffer_info->skb = NULL;
		}
	}

	size = sizeof(struct e1000_buffer) * rx_ring->count;
	memset(rx_ring->buffer_info, 0, size);

	/* Zero out the descriptor ring */

	memset(rx_ring->desc, 0, rx_ring->size);

	rx_ring->next_to_clean = 0;
	rx_ring->next_to_use = 0;

	E1000_WRITE_REG(&adapter->hw, RDH, 0);
	E1000_WRITE_REG(&adapter->hw, RDT, 0);
}

/* The 82542 2.0 (revision 2) needs to have the receive unit in reset
 * and memory write and invalidate disabled for certain operations
 */
static void
e1000_enter_82542_rst(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	uint32_t rctl;

	e1000_pci_clear_mwi(&adapter->hw);

	rctl = E1000_READ_REG(&adapter->hw, RCTL);
	rctl |= E1000_RCTL_RST;
	E1000_WRITE_REG(&adapter->hw, RCTL, rctl);
	E1000_WRITE_FLUSH(&adapter->hw);
	mdelay(5);

	if(netif_running(netdev))
		e1000_clean_rx_ring(adapter);
}

static void
e1000_leave_82542_rst(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	uint32_t rctl;

	rctl = E1000_READ_REG(&adapter->hw, RCTL);
	rctl &= ~E1000_RCTL_RST;
	E1000_WRITE_REG(&adapter->hw, RCTL, rctl);
	E1000_WRITE_FLUSH(&adapter->hw);
	mdelay(5);

	if(adapter->hw.pci_cmd_word & PCI_COMMAND_INVALIDATE)
		e1000_pci_set_mwi(&adapter->hw);

	if(netif_running(netdev)) {
		e1000_configure_rx(adapter);
		e1000_alloc_rx_buffers(adapter);
	}
}

/**
 * e1000_set_mac - Change the Ethernet Address of the NIC
 * @netdev: network interface device structure
 * @p: pointer to an address structure
 *
 * Returns 0 on success, negative on failure
 **/

static int
e1000_set_mac(struct net_device *netdev, void *p)
{
	struct e1000_adapter *adapter = netdev->priv;
	struct sockaddr *addr = p;

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

	/* 82542 2.0 needs to be in reset to write receive address registers */

	if(adapter->hw.mac_type == e1000_82542_rev2_0)
		e1000_enter_82542_rst(adapter);

	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
	memcpy(adapter->hw.mac_addr, addr->sa_data, netdev->addr_len);

	e1000_rar_set(&adapter->hw, adapter->hw.mac_addr, 0);

	if(adapter->hw.mac_type == e1000_82542_rev2_0)
		e1000_leave_82542_rst(adapter);

	return 0;
}

/**
 * e1000_set_multi - Multicast and Promiscuous mode set
 * @netdev: network interface device structure
 *
 * The set_multi entry point is called whenever the multicast address
 * list or the network interface flags are updated.  This routine is
 * responsible for configuring the hardware for proper multicast,
 * promiscuous mode, and all-multi behavior.
 **/

static void
e1000_set_multi(struct net_device *netdev)
{
	struct e1000_adapter *adapter = netdev->priv;
	struct e1000_hw *hw = &adapter->hw;
	struct dev_mc_list *mc_ptr;
	uint32_t rctl;
	uint32_t hash_value;
	int i;
	unsigned long flags;

	/* Check for Promiscuous and All Multicast modes */

	spin_lock_irqsave(&adapter->tx_lock, flags);

	rctl = E1000_READ_REG(hw, RCTL);

	if(netdev->flags & IFF_PROMISC) {
		rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE);
	} else if(netdev->flags & IFF_ALLMULTI) {
		rctl |= E1000_RCTL_MPE;
		rctl &= ~E1000_RCTL_UPE;
	} else {
		rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE);
	}

	E1000_WRITE_REG(hw, RCTL, rctl);

	/* 82542 2.0 needs to be in reset to write receive address registers */

	if(hw->mac_type == e1000_82542_rev2_0)
		e1000_enter_82542_rst(adapter);

	/* load the first 14 multicast address into the exact filters 1-14
	 * RAR 0 is used for the station MAC adddress
	 * if there are not 14 addresses, go ahead and clear the filters
	 */
	mc_ptr = netdev->mc_list;

	for(i = 1; i < E1000_RAR_ENTRIES; i++) {
		if(mc_ptr) {
			e1000_rar_set(hw, mc_ptr->dmi_addr, i);
			mc_ptr = mc_ptr->next;
		} else {
			E1000_WRITE_REG_ARRAY(hw, RA, i << 1, 0);
			E1000_WRITE_REG_ARRAY(hw, RA, (i << 1) + 1, 0);
		}
	}

	/* clear the old settings from the multicast hash table */

	for(i = 0; i < E1000_NUM_MTA_REGISTERS; i++)
		E1000_WRITE_REG_ARRAY(hw, MTA, i, 0);

	/* load any remaining addresses into the hash table */

	for(; mc_ptr; mc_ptr = mc_ptr->next) {
		hash_value = e1000_hash_mc_addr(hw, mc_ptr->dmi_addr);
		e1000_mta_set(hw, hash_value);
	}

	if(hw->mac_type == e1000_82542_rev2_0)
		e1000_leave_82542_rst(adapter);

	spin_unlock_irqrestore(&adapter->tx_lock, flags);
}

/* Need to wait a few seconds after link up to get diagnostic information from
 * the phy */

static void
e1000_update_phy_info(unsigned long data)
{
	struct e1000_adapter *adapter = (struct e1000_adapter *) data;
	e1000_phy_get_info(&adapter->hw, &adapter->phy_info);
}

/**
 * e1000_82547_tx_fifo_stall - Timer Call-back
 * @data: pointer to adapter cast into an unsigned long
 **/

static void
e1000_82547_tx_fifo_stall(unsigned long data)
{
	struct e1000_adapter *adapter = (struct e1000_adapter *) data;
	struct net_device *netdev = adapter->netdev;
	uint32_t tctl;

	if(atomic_read(&adapter->tx_fifo_stall)) {
		if((E1000_READ_REG(&adapter->hw, TDT) ==
		    E1000_READ_REG(&adapter->hw, TDH)) &&
		   (E1000_READ_REG(&adapter->hw, TDFT) ==
		    E1000_READ_REG(&adapter->hw, TDFH)) &&
		   (E1000_READ_REG(&adapter->hw, TDFTS) ==
		    E1000_READ_REG(&adapter->hw, TDFHS))) {
			tctl = E1000_READ_REG(&adapter->hw, TCTL);
			E1000_WRITE_REG(&adapter->hw, TCTL,
					tctl & ~E1000_TCTL_EN);
			E1000_WRITE_REG(&adapter->hw, TDFT,
					adapter->tx_head_addr);
			E1000_WRITE_REG(&adapter->hw, TDFH,
					adapter->tx_head_addr);
			E1000_WRITE_REG(&adapter->hw, TDFTS,
					adapter->tx_head_addr);
			E1000_WRITE_REG(&adapter->hw, TDFHS,
					adapter->tx_head_addr);
			E1000_WRITE_REG(&adapter->hw, TCTL, tctl);
			E1000_WRITE_FLUSH(&adapter->hw);

			adapter->tx_fifo_head = 0;
			atomic_set(&adapter->tx_fifo_stall, 0);
			netif_wake_queue(netdev);
		} else {
			mod_timer(&adapter->tx_fifo_stall_timer, jiffies + 1);
		}
	}
}

/**
 * e1000_watchdog - Timer Call-back
 * @data: pointer to netdev cast into an unsigned long
 **/

static void
e1000_watchdog(unsigned long data)
{
	struct e1000_adapter *adapter = (struct e1000_adapter *) data;

	if (adapter->netdev->polling)
		adapter->do_poll_watchdog = 1;
	else
		e1000_watchdog_1(adapter);

	/* Reset the timer */
	mod_timer(&adapter->watchdog_timer, jiffies + 2 * HZ);
}

void
e1000_watchdog_1(struct e1000_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct e1000_desc_ring *txdr = &adapter->tx_ring;
	uint32_t link;

	e1000_check_for_link(&adapter->hw);
	
	if((adapter->hw.media_type == e1000_media_type_internal_serdes) &&
	   !(E1000_READ_REG(&adapter->hw, TXCW) & E1000_TXCW_ANE))
		link = !adapter->hw.serdes_link_down;
	else
		link = E1000_READ_REG(&adapter->hw, STATUS) & E1000_STATUS_LU;

	if(link) {
		if(!netif_carrier_ok(netdev)) {
			e1000_get_speed_and_duplex(&adapter->hw,
			                           &adapter->link_speed,
			                           &adapter->link_duplex);

			DPRINTK(LINK, INFO, "NIC Link is Up %d Mbps %s\n",
			       adapter->link_speed,
			       adapter->link_duplex == FULL_DUPLEX ?
			       "Full Duplex" : "Half Duplex");

			netif_carrier_on(netdev);
			netif_wake_queue(netdev);
			mod_timer(&adapter->phy_info_timer, jiffies + 2 * HZ);
			adapter->smartspeed = 0;
		}
	} else {
		if(netif_carrier_ok(netdev)) {
			adapter->link_speed = 0;
			adapter->link_duplex = 0;
			DPRINTK(LINK, INFO, "NIC Link is Down\n");
			netif_carrier_off(netdev);
			netif_stop_queue(netdev);
			mod_timer(&adapter->phy_info_timer, jiffies + 2 * HZ);
		}

		e1000_smartspeed(adapter);
	}

	e1000_update_stats(adapter);

	adapter->hw.tx_packet_delta = adapter->stats.tpt - adapter->tpt_old;
	adapter->tpt_old = adapter->stats.tpt;
	adapter->hw.collision_delta = adapter->stats.colc - adapter->colc_old;
	adapter->colc_old = adapter->stats.colc;

	adapter->gorcl = adapter->stats.gorcl - adapter->gorcl_old;
	adapter->gorcl_old = adapter->stats.gorcl;
	adapter->gotcl = adapter->stats.gotcl - adapter->gotcl_old;
	adapter->gotcl_old = adapter->stats.gotcl;

	e1000_update_adaptive(&adapter->hw);

	if(!netif_carrier_ok(netdev)) {
		if(E1000_DESC_UNUSED(txdr) + 1 < txdr->count) {
			/* We've lost link, so the controller stops DMA,
			 * but we've got queued Tx work that's never going
			 * to get done, so reset controller to flush Tx.
			 * (Do the reset outside of interrupt context). */
			schedule_work(&adapter->tx_timeout_task);
		}
	}

	/* Dynamic mode for Interrupt Throttle Rate (ITR) */
	if(adapter->hw.mac_type >= e1000_82540 && adapter->itr == 1) {
		/* Symmetric Tx/Rx gets a reduced ITR=2000; Total
		 * asymmetrical Tx or Rx gets ITR=8000; everyone
		 * else is between 2000-8000. */
		uint32_t goc = (adapter->gotcl + adapter->gorcl) / 10000;
		uint32_t dif = (adapter->gotcl > adapter->gorcl ? 
			adapter->gotcl - adapter->gorcl :
			adapter->gorcl - adapter->gotcl) / 10000;
		uint32_t itr = goc > 0 ? (dif * 6000 / goc + 2000) : 8000;
		E1000_WRITE_REG(&adapter->hw, ITR, 1000000000 / (itr * 256));
	}

	/* Cause software interrupt to ensure rx ring is cleaned */
	E1000_WRITE_REG(&adapter->hw, ICS, E1000_ICS_RXDMT0);

	/* Force detection of hung controller every watchdog period*/
	adapter->detect_tx_hung = TRUE;
}

#define E1000_TX_FLAGS_CSUM		0x00000001
#define E1000_TX_FLAGS_VLAN		0x00000002
#define E1000_TX_FLAGS_TSO		0x00000004
#define E1000_TX_FLAGS_VLAN_MASK	0xffff0000
#define E1000_TX_FLAGS_VLAN_SHIFT	16

static inline boolean_t
e1000_tso(struct e1000_adapter *adapter, struct sk_buff *skb)
{
#ifdef NETIF_F_TSO
	struct e1000_context_desc *context_desc;
	unsigned int i;
	uint32_t cmd_length = 0;
	uint16_t ipcse, tucse, mss;
	uint8_t ipcss, ipcso, tucss, tucso, hdr_len;

	if(skb_shinfo(skb)->tso_size) {
		hdr_len = ((skb->h.raw - skb->data) + (skb->h.th->doff << 2));
		mss = skb_shinfo(skb)->tso_size;
		skb->nh.iph->tot_len = 0;
		skb->nh.iph->check = 0;
		skb->h.th->check = ~csum_tcpudp_magic(skb->nh.iph->saddr,
		                                      skb->nh.iph->daddr,
		                                      0,
		                                      IPPROTO_TCP,
		                                      0);
		ipcss = skb->nh.raw - skb->data;
		ipcso = (void *)&(skb->nh.iph->check) - (void *)skb->data;
		ipcse = skb->h.raw - skb->data - 1;
		tucss = skb->h.raw - skb->data;
		tucso = (void *)&(skb->h.th->check) - (void *)skb->data;
		tucse = 0;

		cmd_length |= (E1000_TXD_CMD_DEXT | E1000_TXD_CMD_TSE |
			       E1000_TXD_CMD_IP | E1000_TXD_CMD_TCP |
			       (skb->len - (hdr_len)));

		i = adapter->tx_ring.next_to_use;
		context_desc = E1000_CONTEXT_DESC(adapter->tx_ring, i);

		context_desc->lower_setup.ip_fields.ipcss  = ipcss;
		context_desc->lower_setup.ip_fields.ipcso  = ipcso;
		context_desc->lower_setup.ip_fields.ipcse  = cpu_to_le16(ipcse);
		context_desc->upper_setup.tcp_fields.tucss = tucss;
		context_desc->upper_setup.tcp_fields.tucso = tucso;
		context_desc->upper_setup.tcp_fields.tucse = cpu_to_le16(tucse);
		context_desc->tcp_seg_setup.fields.mss     = cpu_to_le16(mss);
		context_desc->tcp_seg_setup.fields.hdr_len = hdr_len;
		context_desc->cmd_and_length = cpu_to_le32(cmd_length);

		if(++i == adapter->tx_ring.count) i = 0;
		adapter->tx_ring.next_to_use = i;

		return TRUE;
	}
#endif

	return FALSE;
}

static inline boolean_t
e1000_tx_csum(struct e1000_adapter *adapter, struct sk_buff *skb)
{
	struct e1000_context_desc *context_desc;
	unsigned int i;
	uint8_t css;

	if(likely(skb->ip_summed == CHECKSUM_HW)) {
		css = skb->h.raw - skb->data;

		i = adapter->tx_ring.next_to_use;
		context_desc = E1000_CONTEXT_DESC(adapter->tx_ring, i);

		context_desc->upper_setup.tcp_fields.tucss = css;
		context_desc->upper_setup.tcp_fields.tucso = css + skb->csum;
		context_desc->upper_setup.tcp_fields.tucse = 0;
		context_desc->tcp_seg_setup.data = 0;
		context_desc->cmd_and_length = cpu_to_le32(E1000_TXD_CMD_DEXT);

		if(unlikely(++i == adapter->tx_ring.count)) i = 0;
		adapter->tx_ring.next_to_use = i;

		return TRUE;
	}

	return FALSE;
}

#define E1000_MAX_TXD_PWR	12
#define E1000_MAX_DATA_PER_TXD	(1<<E1000_MAX_TXD_PWR)

static inline int
e1000_tx_map(struct e1000_adapter *adapter, struct sk_buff *skb,
	unsigned int first, unsigned int max_per_txd,
	unsigned int nr_frags, unsigned int mss)
{
	struct e1000_desc_ring *tx_ring = &adapter->tx_ring;
	struct e1000_buffer *buffer_info;
	unsigned int len = skb->len;
	unsigned int offset = 0, size, count = 0, i;
#ifdef MAX_SKB_FRAGS
	unsigned int f;
	len -= skb->data_len;
#endif

	i = tx_ring->next_to_use;

	while(len) {
		buffer_info = &tx_ring->buffer_info[i];
		size = min(len, max_per_txd);
#ifdef NETIF_F_TSO
		/* Workaround for premature desc write-backs
		 * in TSO mode.  Append 4-byte sentinel desc */
		if(unlikely(mss && !nr_frags && size == len && size > 8))
			size -= 4;
#endif