e1000网卡驱动小结

1、网卡的初始化

    e1000网卡的初始化调用函数e1000_probe()，网卡作为一种PCI设备就要初始化PCI设备的一些属性，设置DMA，初始化驱动的操作函数（收包函数、发包函数）、设置循环队列缓冲区大小，把网卡注册到dev_base全局数组中。网卡的收包方式有三种

(1)中断方式：

     传统的网卡都采用这种模式，因为传统的网卡收包量不是很大，这种方式就是当有一个数据包来了就产生一个中断，然后cpu就放下手中的事情去把网络数据包拷贝到内存处理，当流量很大时会产生大量的中断，cpu就不断的上下文切换，这样是很损耗cpu的性能，这种只适合网络流量不大的情况。

(2)poll

      第二种方式是轮询，设置一个定时器，每隔一定时间cpu就去查看是网卡是否有接受数据包，如果有数据上来就拷贝内存处理，这种方式适合大流量情景，避免cpu产生大量中断。但当网络流量小时，cpu还有不断的去检查网卡就损耗了cpu资源。

(3)DMA

   系统会在内存中开辟一个缓冲区环形队列来收发数据包，然后把缓冲区通过DMA映射到网卡，这样网卡收到数据包后就是直接是放到内存的环形队列中，然后产生中断让cpu去处理，这样cpu可以自己干自己的事情，只有当有数据包到来才去内存中处理。

(4)e1000_probe函数

     e1000_probe函数主要的工作是初始化硬件、注册初始化新设备，直接上代码

static int __devinit e1000_probe(struct pci_dev *pdev,
				 const struct pci_device_id *ent)
{
	struct net_device *netdev;
	struct e1000_adapter *adapter;
	struct e1000_hw *hw;
	const struct e1000_info *ei = e1000_info_tbl[ent->driver_data];
	resource_size_t mmio_start, mmio_len;
	resource_size_t flash_start, flash_len;

	static int cards_found;
	int i, err, pci_using_dac;
	u16 eeprom_data = 0;
	u16 eeprom_apme_mask = E1000_EEPROM_APME;

	if (ei->flags2 & FLAG2_DISABLE_ASPM_L1)
		e1000e_disable_aspm(pdev, PCIE_LINK_STATE_L1);

	err = pci_enable_device_mem(pdev);
	if (err)
		return err;

	pci_using_dac = 0;
	 //设置pci设备的dma掩码
	err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
	if (!err) {
		err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
		if (!err)
			pci_using_dac = 1;
	} else {
		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
		if (err) {
			err = dma_set_coherent_mask(&pdev->dev,
						    DMA_BIT_MASK(32));
			if (err) {
				dev_err(&pdev->dev, "No usable DMA "
					"configuration, aborting\n");
				goto err_dma;
			}
		}
	}

	err = pci_request_selected_regions_exclusive(pdev,
	                                  pci_select_bars(pdev, IORESOURCE_MEM),
	                                  e1000e_driver_name);
	if (err)
		goto err_pci_reg;

	/* AER (Advanced Error Reporting) hooks */
	pci_enable_pcie_error_reporting(pdev);

	pci_set_master(pdev);
	/* PCI config space info */
	err = pci_save_state(pdev);
	if (err)
		goto err_alloc_etherdev;

	err = -ENOMEM;
	//为e1000网卡对应的net_device结构分配内存
	netdev = alloc_etherdev(sizeof(struct e1000_adapter));
	if (!netdev)
		goto err_alloc_etherdev;

	SET_NETDEV_DEV(netdev, &pdev->dev);

	netdev->irq = pdev->irq;

	pci_set_drvdata(pdev, netdev);
	adapter = netdev_priv(netdev);
	hw = &adapter->hw;
	adapter->netdev = netdev;
	adapter->pdev = pdev;
	adapter->ei = ei;
	adapter->pba = ei->pba;
	adapter->flags = ei->flags;
	adapter->flags2 = ei->flags2;
	adapter->hw.adapter = adapter;
	adapter->hw.mac.type = ei->mac;
	adapter->max_hw_frame_size = ei->max_hw_frame_size;
	adapter->msg_enable = (1 << NETIF_MSG_DRV | NETIF_MSG_PROBE) - 1;

	mmio_start = pci_resource_start(pdev, 0);
	mmio_len = pci_resource_len(pdev, 0);

	err = -EIO;
	adapter->hw.hw_addr = ioremap(mmio_start, mmio_len);
	if (!adapter->hw.hw_addr)
		goto err_ioremap;

	if ((adapter->flags & FLAG_HAS_FLASH) &&
	    (pci_resource_flags(pdev, 1) & IORESOURCE_MEM)) {
		flash_start = pci_resource_start(pdev, 1);
		flash_len = pci_resource_len(pdev, 1);
		adapter->hw.flash_address = ioremap(flash_start, flash_len);
		if (!adapter->hw.flash_address)
			goto err_flashmap;
	}

	/* construct the net_device struct 驱动的发包收包等处理函数*/
	netdev->netdev_ops		= &e1000e_netdev_ops;
	//网卡命令函数注册
	e1000e_set_ethtool_ops(netdev);
	netdev->watchdog_timeo		= 5 * HZ;
	// 注册poll函数为e1000_clean, weight为64
	netif_napi_add(netdev, &adapter->napi, e1000_clean, 64);
	strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1);

	netdev->mem_start = mmio_start;
	netdev->mem_end = mmio_start + mmio_len;

	adapter->bd_number = cards_found++;

	e1000e_check_options(adapter);

	/* setup adapter struct */
	err = e1000_sw_init(adapter);
	if (err)
		goto err_sw_init;

	err = -EIO;

	memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops));
	memcpy(&hw->nvm.ops, ei->nvm_ops, sizeof(hw->nvm.ops));
	memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops));

	err = ei->get_variants(adapter);
	if (err)
		goto err_hw_init;

	if ((adapter->flags & FLAG_IS_ICH) &&
	    (adapter->flags & FLAG_READ_ONLY_NVM))
		e1000e_write_protect_nvm_ich8lan(&adapter->hw);

	hw->mac.ops.get_bus_info(&adapter->hw);

	adapter->hw.phy.autoneg_wait_to_complete = 0;

	/* Copper options */
	if (adapter->hw.phy.media_type == e1000_media_type_copper) {
		adapter->hw.phy.mdix = AUTO_ALL_MODES;
		adapter->hw.phy.disable_polarity_correction = 0;
		adapter->hw.phy.ms_type = e1000_ms_hw_default;
	}

	if (e1000_check_reset_block(&adapter->hw))
		e_info("PHY reset is blocked due to SOL/IDER session.\n");

	netdev->features = NETIF_F_SG |
			   NETIF_F_HW_CSUM |
			   NETIF_F_HW_VLAN_TX |
			   NETIF_F_HW_VLAN_RX;

	if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER)
		netdev->features |= NETIF_F_HW_VLAN_FILTER;
    //网卡属性初始化
	netdev->features |= NETIF_F_TSO;
	netdev->features |= NETIF_F_TSO6;

	netdev->vlan_features |= NETIF_F_TSO;
	netdev->vlan_features |= NETIF_F_TSO6;
	netdev->vlan_features |= NETIF_F_HW_CSUM;
	netdev->vlan_features |= NETIF_F_SG;

	if (pci_using_dac)
		netdev->features |= NETIF_F_HIGHDMA;

	if (e1000e_enable_mng_pass_thru(&adapter->hw))
		adapter->flags |= FLAG_MNG_PT_ENABLED;

	/*
	 * before reading the NVM, reset the controller to
	 * put the device in a known good starting state
	 */
	adapter->hw.mac.ops.reset_hw(&adapter->hw);

	/*
	 * systems with ASPM and others may see the checksum fail on the first
	 * attempt. Let's give it a few tries
	 */
	for (i = 0;; i++) {
		if (e1000_validate_nvm_checksum(&adapter->hw) >= 0)
			break;
		if (i == 2) {
			e_err("The NVM Checksum Is Not Valid\n");
			err = -EIO;
			goto err_eeprom;
		}
	}

	e1000_eeprom_checks(adapter);

	/* copy the MAC address 拷贝mac地址*/
	if (e1000e_read_mac_addr(&adapter->hw))
		e_err("NVM Read Error while reading MAC address\n");

	memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len);
	memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len);

	if (!is_valid_ether_addr(netdev->perm_addr)) {
		e_err("Invalid MAC Address: %pM\n", netdev->perm_addr);
		err = -EIO;
		goto err_eeprom;
	}

	init_timer(&adapter->watchdog_timer);
	adapter->watchdog_timer.function = &e1000_watchdog;
	adapter->watchdog_timer.data = (unsigned long) adapter;

	init_timer(&adapter->phy_info_timer);
	adapter->phy_info_timer.function = &e1000_update_phy_info;
	adapter->phy_info_timer.data = (unsigned long) adapter;

	INIT_WORK(&adapter->reset_task, e1000_reset_task);
	INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task);
	INIT_WORK(&adapter->downshift_task, e1000e_downshift_workaround);
	INIT_WORK(&adapter->update_phy_task, e1000e_update_phy_task);
	INIT_WORK(&adapter->print_hang_task, e1000_print_hw_hang);

	/* Initialize link parameters. User can change them with ethtool */
	adapter->hw.mac.autoneg = 1;
	adapter->fc_autoneg = 1;
	adapter->hw.fc.requested_mode = e1000_fc_default;
	adapter->hw.fc.current_mode = e1000_fc_default;
	adapter->hw.phy.autoneg_advertised = 0x2f;

	 //设置接收环型缓冲区队列的缺省大小
	/* ring size defaults */
	adapter->rx_ring->count = 256;
	adapter->tx_ring->count = 256;

	/*
	 * Initial Wake on LAN setting - If APM wake is enabled in
	 * the EEPROM, enable the ACPI Magic Packet filter
	 */
	if (adapter->flags & FLAG_APME_IN_WUC) {
		/* APME bit in EEPROM is mapped to WUC.APME */
		eeprom_data = er32(WUC);
		eeprom_apme_mask = E1000_WUC_APME;
		if (eeprom_data & E1000_WUC_PHY_WAKE)
			adapter->flags2 |= FLAG2_HAS_PHY_WAKEUP;
	} else if (adapter->flags & FLAG_APME_IN_CTRL3) {
		if (adapter->flags & FLAG_APME_CHECK_PORT_B &&
		    (adapter->hw.bus.func == 1))
			e1000_read_nvm(&adapter->hw,
				NVM_INIT_CONTROL3_PORT_B, 1, &eeprom_data);
		else
			e1000_read_nvm(&adapter->hw,
				NVM_INIT_CONTROL3_PORT_A, 1, &eeprom_data);
	}

	/* fetch WoL from EEPROM */
	if (eeprom_data & eeprom_apme_mask)
		adapter->eeprom_wol |= E1000_WUFC_MAG;

	/*
	 * now that we have the eeprom settings, apply the special cases
	 * where the eeprom may be wrong or the board simply won't support
	 * wake on lan on a particular port
	 */
	if (!(adapter->flags & FLAG_HAS_WOL))
		adapter->eeprom_wol = 0;

	/* initialize the wol settings based on the eeprom settings */
	adapter->wol = adapter->eeprom_wol;
	device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol);

	/* save off EEPROM version number */
	e1000_read_nvm(&adapter->hw, 5, 1, &adapter->eeprom_vers);

	/* reset the hardware with the new settings */
	e1000e_reset(adapter);

	/*
	 * If the controller has AMT, do not set DRV_LOAD until the interface
	 * is up.  For all other cases, let the f/w know that the h/w is now
	 * under the control of the driver.
	 */
	if (!(adapter->flags & FLAG_HAS_AMT))
		e1000_get_hw_control(adapter);

	strcpy(netdev->name, "eth%d");
	//将当前网络设备注册到系统的dev_base[]设备数组当中
	err = register_netdev(netdev);
	if (err)
		goto err_register;

	/* carrier off reporting is important to ethtool even BEFORE open */
	netif_carrier_off(netdev);

	e1000_print_device_info(adapter);

	if (pci_dev_run_wake(pdev)) {
		pm_runtime_set_active(&pdev->dev);
		pm_runtime_enable(&pdev->dev);
	}
	pm_schedule_suspend(&pdev->dev, MSEC_PER_SEC);

	return 0;

err_register:
	if (!(adapter->flags & FLAG_HAS_AMT))
		e1000_release_hw_control(adapter);
err_eeprom:
	if (!e1000_check_reset_block(&adapter->hw))
		e1000_phy_hw_reset(&adapter->hw);
err_hw_init:

	kfree(adapter->tx_ring);
	kfree(adapter->rx_ring);
err_sw_init:
	if (adapter->hw.flash_address)
		iounmap(adapter->hw.flash_address);
	e1000e_reset_interrupt_capability(adapter);
err_flashmap:
	iounmap(adapter->hw.hw_addr);
err_ioremap:
	free_netdev(netdev);
err_alloc_etherdev:
	pci_release_selected_regions(pdev,
	                             pci_select_bars(pdev, IORESOURCE_MEM));
err_pci_reg:
err_dma:
	pci_disable_device(pdev);
	return err;
}

e1000网卡注册的操作函数

static const struct net_device_ops e1000e_netdev_ops = {
	//打卡网卡
	.ndo_open		= e1000_open,
	//关闭网卡
	.ndo_stop		= e1000_close,
	//发送函数
	.ndo_start_xmit		= e1000_xmit_frame,
	.ndo_get_stats		= e1000_get_stats,
	.ndo_set_multicast_list	= e1000_set_multi,
	.ndo_set_mac_address	= e1000_set_mac,
	.ndo_change_mtu		= e1000_change_mtu,
	.ndo_do_ioctl		= e1000_ioctl,
	.ndo_tx_timeout		= e1000_tx_timeout,
	.ndo_validate_addr	= eth_validate_addr,

	.ndo_vlan_rx_register	= e1000_vlan_rx_register,
	.ndo_vlan_rx_add_vid	= e1000_vlan_rx_add_vid,
	.ndo_vlan_rx_kill_vid	= e1000_vlan_rx_kill_vid,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller	= e1000_netpoll,
#endif
};

(5)e1000_open函数

   e1000_open函数主要是打开网卡 做一些初始化的工作，主要工作有初始化发送缓冲区、接受缓冲区、中断使能。代码如下

static int e1000_open(struct net_device *netdev)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	struct pci_dev *pdev = adapter->pdev;
	int err;

	/* disallow open during test */
	if (test_bit(__E1000_TESTING, &adapter->state))
		return -EBUSY;

	pm_runtime_get_sync(&pdev->dev);

	netif_carrier_off(netdev);

	/* allocate transmit descriptors 初始化发送缓冲区*/
	err = e1000e_setup_tx_resources(adapter);
	if (err)
		goto err_setup_tx;

	/* allocate receive descriptors初始化接受缓冲区 */
	err = e1000e_setup_rx_resources(adapter);
	if (err)
		goto err_setup_rx;

	/*
	 * If AMT is enabled, let the firmware know that the network
	 * interface is now open and reset the part to a known state.
	 */
	if (adapter->flags & FLAG_HAS_AMT) {
		e1000_get_hw_control(adapter);
		e1000e_reset(adapter);
	}

	e1000e_power_up_phy(adapter);

	adapter->mng_vlan_id = E1000_MNG_VLAN_NONE;
	if ((adapter->hw.mng_cookie.status &
	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN))
		e1000_update_mng_vlan(adapter);

	/*
	 * before we allocate an interrupt, we must be ready to handle it.
	 * Setting DEBUG_SHIRQ in the kernel makes it fire an interrupt
	 * as soon as we call pci_request_irq, so we have to setup our
	 * clean_rx handler before we do so.
	 */
	 //对容器的配置包括发送、接受、中断
	e1000_configure(adapter);
	//中断申请
	err = e1000_request_irq(adapter);
	if (err)
		goto err_req_irq;

	/*
	 * Work around PCIe errata with MSI interrupts causing some chipsets to
	 * ignore e1000e MSI messages, which means we need to test our MSI
	 * interrupt now
	 */
	if (adapter->int_mode != E1000E_INT_MODE_LEGACY) {
		err = e1000_test_msi(adapter);
		if (err) {
			e_err("Interrupt allocation failed\n");
			goto err_req_irq;
		}
	}

	/* From here on the code is the same as e1000e_up() */
	clear_bit(__E1000_DOWN, &adapter->state);

	napi_enable(&adapter->napi);
	//中断使能
	e1000_irq_enable(adapter);
	//开始队列
	netif_start_queue(netdev);

	adapter->idle_check = true;
	pm_runtime_put(&pdev->dev);

	/* fire a link status change interrupt to start the watchdog */
	if (adapter->msix_entries)
		ew32(ICS, E1000_ICS_LSC | E1000_ICR_OTHER);
	else
		ew32(ICS, E1000_ICS_LSC);

	return 0;

err_req_irq:
	e1000_release_hw_control(adapter);
	e1000_power_down_phy(adapter);
	e1000e_free_rx_resources(adapter);
err_setup_rx:
	e1000e_free_tx_resources(adapter);
err_setup_tx:
	e1000e_reset(adapter);
	pm_runtime_put_sync(&pdev->dev);

	return err;
}

2、e1000发包流程

      网卡的发包函数流程如下：-> dev_queue_xmit()

                                                           ->dev_hard_start_xmit()

                                                                 ->ops->ndo_start_xmit(skb, dev)

ndo_start_xmit就是我们之前注册的e1000_xmit_frame()，e1000中主要的两个函数是e1000_tx_map()和e1000_tx_queue(),

e1000_xmit_frame代码如下：

static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
				    struct net_device *netdev)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_ring *tx_ring = adapter->tx_ring;
	unsigned int first;
	unsigned int max_per_txd = E1000_MAX_PER_TXD;
	unsigned int max_txd_pwr = E1000_MAX_TXD_PWR;
	unsigned int tx_flags = 0;
	unsigned int len = skb_headlen(skb);
	unsigned int nr_frags;
	unsigned int mss;
	int count = 0;
	int tso;
	unsigned int f;

	if (test_bit(__E1000_DOWN, &adapter->state)) {
		dev_kfree_skb_any(skb);
		return NETDEV_TX_OK;
	}

	if (skb->len <= 0) {
		dev_kfree_skb_any(skb);
		return NETDEV_TX_OK;
	}

	mss = skb_shinfo(skb)->gso_size;
	/*
	 * The controller does a simple calculation to
	 * make sure there is enough room in the FIFO before
	 * initiating the DMA for each buffer.  The calc is:
	 * 4 = ceil(buffer len/mss).  To make sure we don't
	 * overrun the FIFO, adjust the max buffer len if mss
	 * drops.
	 */
	if (mss) {
		u8 hdr_len;
		max_per_txd = min(mss << 2, max_per_txd);
		max_txd_pwr = fls(max_per_txd) - 1;

		/*
		 * TSO Workaround for 82571/2/3 Controllers -- if skb->data
		 * points to just header, pull a few bytes of payload from
		 * frags into skb->data
		 */
		hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
		/*
		 * we do this workaround for ES2LAN, but it is un-necessary,
		 * avoiding it could save a lot of cycles
		 */
		if (skb->data_len && (hdr_len == len)) {
			unsigned int pull_size;

			pull_size = min((unsigned int)4, skb->data_len);
			if (!__pskb_pull_tail(skb, pull_size)) {
				e_err("__pskb_pull_tail failed.\n");
				dev_kfree_skb_any(skb);
				return NETDEV_TX_OK;
			}
			len = skb_headlen(skb);
		}
	}

	/* reserve a descriptor for the offload context */
	if ((mss) || (skb->ip_summed == CHECKSUM_PARTIAL))
		count++;
	count++;

	count += TXD_USE_COUNT(len, max_txd_pwr);

	nr_frags = skb_shinfo(skb)->nr_frags;
	for (f = 0; f < nr_frags; f++)
		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size,
				       max_txd_pwr);

	if (adapter->hw.mac.tx_pkt_filtering)
		e1000_transfer_dhcp_info(adapter, skb);

	/*
	 * need: count + 2 desc gap to keep tail from touching
	 * head, otherwise try next time
	 */
	if (e1000_maybe_stop_tx(netdev, count + 2))
		return NETDEV_TX_BUSY;

	if (adapter->vlgrp && vlan_tx_tag_present(skb)) {
		tx_flags |= E1000_TX_FLAGS_VLAN;
		tx_flags |= (vlan_tx_tag_get(skb) << E1000_TX_FLAGS_VLAN_SHIFT);
	}

	first = tx_ring->next_to_use;

	tso = e1000_tso(adapter, skb);
	if (tso < 0) {
		dev_kfree_skb_any(skb);
		return NETDEV_TX_OK;
	}

	if (tso)
		tx_flags |= E1000_TX_FLAGS_TSO;
	else if (e1000_tx_csum(adapter, skb))
		tx_flags |= E1000_TX_FLAGS_CSUM;

	/*
	 * Old method was to assume IPv4 packet by default if TSO was enabled.
	 * 82571 hardware supports TSO capabilities for IPv6 as well...
	 * no longer assume, we must.
	 */
	if (skb->protocol == htons(ETH_P_IP))
		tx_flags |= E1000_TX_FLAGS_IPV4;

	/*数据做dma地址映射*/
	/* if count is 0 then mapping error has occured */
	count = e1000_tx_map(adapter, skb, first, max_per_txd, nr_frags, mss);
	if (count) {
		/*最终发送函数*/
		e1000_tx_queue(adapter, tx_flags, count);
		/* Make sure there is space in the ring for the next send. */
		e1000_maybe_stop_tx(netdev, MAX_SKB_FRAGS + 2);

	} else {
		dev_kfree_skb_any(skb);
		tx_ring->buffer_info[first].time_stamp = 0;
		tx_ring->next_to_use = first;
	}

	return NETDEV_TX_OK;
}

 e1000_tx_map主要做的是把数据包的虚拟地址映射为dma的物理地址，代码如下：

static 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_ring *tx_ring = adapter->tx_ring;
	struct pci_dev *pdev = adapter->pdev;
	struct e1000_buffer *buffer_info;
	unsigned int len = skb_headlen(skb);
	unsigned int offset = 0, size, count = 0, i;
	unsigned int f, bytecount, segs;

	i = tx_ring->next_to_use;

	while (len) {
		buffer_info = &tx_ring->buffer_info[i];
		size = min(len, max_per_txd);

		buffer_info->length = size;
		//时间戳
		buffer_info->time_stamp = jiffies;
		buffer_info->next_to_watch = i;
		//将skb->data的虚拟地址转换为pci域的物理地址
		buffer_info->dma = dma_map_single(&pdev->dev,
						  skb->data + offset,
						  size,	DMA_TO_DEVICE);
		buffer_info->mapped_as_page = false;
		if (dma_mapping_error(&pdev->dev, buffer_info->dma))
			goto dma_error;

		len -= size;
		offset += size;
		count++;

		if (len) {
			i++;
			if (i == tx_ring->count)
				i = 0;
		}
	}

e1000_tx_queue最终的发送函数，它的只要是调用write去dma物理地址取包，接下来的工作就交给硬件了，代码分析如下。

static void e1000_tx_queue(struct e1000_adapter *adapter,
			   int tx_flags, int count)
{
	struct e1000_ring *tx_ring = adapter->tx_ring;
	struct e1000_tx_desc *tx_desc = NULL;
	struct e1000_buffer *buffer_info;
	u32 txd_upper = 0, txd_lower = E1000_TXD_CMD_IFCS;
	unsigned int i;

	if (tx_flags & E1000_TX_FLAGS_TSO) {
		txd_lower |= E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D |
			     E1000_TXD_CMD_TSE;
		txd_upper |= E1000_TXD_POPTS_TXSM << 8;

		if (tx_flags & E1000_TX_FLAGS_IPV4)
			txd_upper |= E1000_TXD_POPTS_IXSM << 8;
	}

	if (tx_flags & E1000_TX_FLAGS_CSUM) {
		txd_lower |= E1000_TXD_CMD_DEXT | E1000_TXD_DTYP_D;
		txd_upper |= E1000_TXD_POPTS_TXSM << 8;
	}

	if (tx_flags & E1000_TX_FLAGS_VLAN) {
		txd_lower |= E1000_TXD_CMD_VLE;
		txd_upper |= (tx_flags & E1000_TX_FLAGS_VLAN_MASK);
	}

	i = tx_ring->next_to_use;

	while (count--) {
		buffer_info = &tx_ring->buffer_info[i];
		tx_desc = E1000_TX_DESC(*tx_ring, i);
		//存放dma地址(实际的物理地址)
		tx_desc->buffer_addr = cpu_to_le64(buffer_info->dma);
		tx_desc->lower.data =
			cpu_to_le32(txd_lower | buffer_info->length);
		tx_desc->upper.data = cpu_to_le32(txd_upper);

		i++;
		if (i == tx_ring->count)
			i = 0;
	}

	tx_desc->lower.data |= cpu_to_le32(adapter->txd_cmd);

	/*
	 * Force memory writes to complete before letting h/w
	 * know there are new descriptors to fetch.  (Only
	 * applicable for weak-ordered memory model archs,
	 * such as IA-64).
	 */
	wmb();

	tx_ring->next_to_use = i;
	//写入发送的地址空间
	writel(i, adapter->hw.hw_addr + tx_ring->tail);
	/*
	 * we need this if more than one processor can write to our tail
	 * at a time, it synchronizes IO on IA64/Altix systems
	 */
	mmiowb();
}

 

3、e1000收包流程