linux網絡流程分析（一）---網卡驅動

分析linux網絡的書已經很多了，包括《追蹤Linux TCP/IP代碼運行》《Linux內核源碼剖析——TCP/IP實現》，這里我只是從數據包在linux內核中的基本流程來分析，盡可能的展現一個主流程框架。

內核如何從網卡接收數據,傳統的過程：
1.數據到達網卡；
2.網卡產生一個中斷給內核；
3.內核使用I/O指令，從網卡I/O區域中去讀取數據；

 

我們在許多網卡驅動中(很老那些)，都可以在網卡的中斷函數中見到這一過程。

 

但是，這一種方法，有一種重要的問題，就是大流量的數據來到，網卡會產生大量的中斷，內核在中斷上下文 中，會浪費大量的資源來處理中斷本身。所以，就有一個問題，“可不可以不使用中斷”，這就是輪詢技術，所謂NAPI技術，說來也不神秘，就是說，內核屏蔽 中斷，然后隔一會兒就去問網卡，“你有沒有數據啊？”……

 

從這個描述本身可以看到，如果數據量少，輪詢同樣占用大量的不必要的CPU資源，大家各有所長吧

 

OK，另一個問題，就是從網卡的I/O區域，包括I/O寄存器或I/O內存中去讀取數據，這都要CPU 去讀，也要占用CPU資源，“CPU從I/O區域讀，然后把它放到內存（這個內存指的是系統本身的物理內存，跟外設的內存不相干，也叫主內存）中”。於是 自然地，就想到了DMA技術——讓網卡直接從主內存之間讀寫它們的I/O數據，CPU，這兒不干你事，自己找樂子去：
1.首先，內核在主內存中為收發數據建立一個環形的緩沖隊列（通常叫DMA環形緩沖區）。
2.內核將這個緩沖區通過DMA映射，把這個隊列交給網卡；
3.網卡收到數據，就直接放進這個環形緩沖區了——也就是直接放進主內存了；然后，向系統產生一個中斷；
4.內核收到這個中斷，就取消DMA映射，這樣，內核就直接從主內存中讀取數據；

 

——呵呵，這一個過程比傳統的過程少了不少工作，因為設備直接把數據放進了主內存，不需要CPU的干預，效率是不是提高不少？

 

對應以上4步，來看它的具體實現：
1)分配環形DMA緩沖區
Linux內核中，用skb來描述一個緩存，所謂分配，就是建立一定數量的skb，然后用e1000_rx_ring 環形緩沖區隊列描述符連接起來

2)建立DMA映射
內核通過調用
dma_map_single(struct device *dev,void *buffer,size_t size,enum dma_data_direction direction)
建立映射關系。
struct device *dev 描述一個設備；
buffer：把哪個地址映射給設備；也就是某一個skb——要映射全部，當然是做一個雙向鏈表的循環即可；
size：緩存大小；
direction：映射方向——誰傳給誰：一般來說，是“雙向”映射，數據在設備和內存之間雙向流動；
對於PCI設備而言（網卡一般是PCI的），通過另一個包裹函數pci_map_single，這樣，就把buffer交給設備了！設備可以直接從里邊讀/取數據。

3)這一步由硬件完成；

4)取消映射
dma_unmap_single，對PCI而言，大多調用它的包裹函數pci_unmap_single，不取消的話，緩存控制權還在設備手里，要調用 它，把主動權掌握在CPU手里——因為我們已經接收到數據了，應該由CPU把數據交給上層網絡棧；當然，不取消之前，通常要讀一些狀態位信息，諸如此類， 一般是調用dma_sync_single_for_cpu()讓CPU在取消映射前，就可以訪問DMA緩沖區中的內容

首先，數據包從網卡光電信號來之后，先經過網卡驅動，轉換成skb，進入鏈路層，那么我首先就先分析一下網卡驅動的流程。

源碼位置：Driver/net/E1000e文件夾下面。

static int __init e1000_init_module(void)
{注冊網卡驅動，按照PCI驅動開發方式來進行注冊
	int ret;
	printk(KERN_INFO "%s: Intel(R) PRO/1000 Network Driver - %s\n",
	       e1000e_driver_name, e1000e_driver_version);
	printk(KERN_INFO "%s: Copyright (c) 1999-2008 Intel Corporation.\n",
	       e1000e_driver_name);
	ret = pci_register_driver(&e1000_driver);
	pm_qos_add_requirement(PM_QOS_CPU_DMA_LATENCY, e1000e_driver_name,
			       PM_QOS_DEFAULT_VALUE);
				
	return ret;
}

　　然后看一下驅動結構體內容，這里不對PCI類型驅動開發做介紹了。

/* PCI Device API Driver */
static struct pci_driver e1000_driver = {
	.name     = e1000e_driver_name,
	.id_table = e1000_pci_tbl,
	.probe    = e1000_probe,
	.remove   = __devexit_p(e1000_remove),
#ifdef CONFIG_PM
	/* Power Management Hooks */
	.suspend  = e1000_suspend,
	.resume   = e1000_resume,
#endif
	.shutdown = e1000_shutdown,
	.err_handler = &e1000_err_handler
};

　　這里面最重要的函數是e1000_probe，先看一下這個函數的作用是什么：“Device Initialization Routine”，這個應該不難理解。

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;

	e1000e_disable_l1aspm(pdev);
從這里開始對設備驅動進行初始化，包括名稱、內存之類的。
	err = pci_enable_device_mem(pdev);
	if (err)
		return err;

	pci_using_dac = 0;
	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
	if (!err) {
		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
		if (!err)
			pci_using_dac = 1;
	} else {
		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
		if (err) {
			err = pci_set_consistent_dma_mask(pdev,
							  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 */
	err = pci_enable_pcie_error_reporting(pdev);
	if (err) {
		dev_err(&pdev->dev, "pci_enable_pcie_error_reporting failed "
		        "0x%x\n", err);
		/* non-fatal, continue */
	}

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

	err = -ENOMEM;
這里要為驅動分配一個容器之類的，因為驅動后面的一切操作都是在它的基礎之上。
	netdev = alloc_etherdev(sizeof(struct e1000_adapter));
	if (!netdev)
		goto err_alloc_etherdev;

	SET_NETDEV_DEV(netdev, &pdev->dev);

	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;
0表示設備映射的內存的的bar
	mmio_start = pci_resource_start(pdev, 0);
	mmio_len = pci_resource_len(pdev, 0);

	err = -EIO;
這里我的理解是容器的硬件地址與bar進行映射，hw_addr代表的是網卡的硬件地址
	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 */
	netdev->netdev_ops		= &e1000e_netdev_ops;
	e1000e_set_ethtool_ops(netdev);
	netdev->watchdog_timeo		= 5 * HZ;
	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;

	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 out of the NVM */
	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);

	/* 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;
這里是默認的接收環和發送環大小是256，其實一次中斷，能接受的數據不會有太高，我做實驗的時候也就是1個2個。這里的環不是一直存放skb_buff，而是DMA一次中斷后能給內核的數據存放地，當中斷結束后，skb_buff會被轉移的。
	/* 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");
注冊網卡驅動
	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);

	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;
}

　　通過上面的函數，我們完成了驅動的初始化和設備注冊工作。下面是網卡設備注冊的操作函數

static const struct net_device_ops e1000e_netdev_ops = {
	.ndo_open		= e1000_open,
	.ndo_stop		= e1000_close,
	.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
};

　　這里關注一下最后一個函數

static void e1000_netpoll(struct net_device *netdev)
{
	struct e1000_adapter *adapter = netdev_priv(netdev);

	disable_irq(adapter->pdev->irq);這里關閉容器設備中斷
	e1000_intr(adapter->pdev->irq, netdev); 初始化設備中斷

	enable_irq(adapter->pdev->irq);
}

　　這是網卡驅動的中斷處理函數，也就是后半段的處理

static irqreturn_t e1000_intr(int irq, void *data)
{
	struct net_device *netdev = data;
	struct e1000_adapter *adapter = netdev_priv(netdev);
	struct e1000_hw *hw = &adapter->hw;
	u32 rctl, icr = er32(ICR);

	if (!icr)
		return IRQ_NONE;  /* Not our interrupt */

	/*
	 * IMS will not auto-mask if INT_ASSERTED is not set, and if it is
	 * not set, then the adapter didn't send an interrupt
	 */
	if (!(icr & E1000_ICR_INT_ASSERTED))
		return IRQ_NONE;

	/*
	 * Interrupt Auto-Mask...upon reading ICR,
	 * interrupts are masked.  No need for the
	 * IMC write
	 */

	if (icr & E1000_ICR_LSC) {
		hw->mac.get_link_status = 1;
		/*
		 * ICH8 workaround-- Call gig speed drop workaround on cable
		 * disconnect (LSC) before accessing any PHY registers
		 */
		if ((adapter->flags & FLAG_LSC_GIG_SPEED_DROP) &&
		    (!(er32(STATUS) & E1000_STATUS_LU)))
			schedule_work(&adapter->downshift_task);

		/*
		 * 80003ES2LAN workaround--
		 * For packet buffer work-around on link down event;
		 * disable receives here in the ISR and
		 * reset adapter in watchdog
		 */
		if (netif_carrier_ok(netdev) &&
		    (adapter->flags & FLAG_RX_NEEDS_RESTART)) {
			/* disable receives */
			rctl = er32(RCTL);
			ew32(RCTL, rctl & ~E1000_RCTL_EN);
			adapter->flags |= FLAG_RX_RESTART_NOW;
		}
		/* guard against interrupt when we're going down */
		if (!test_bit(__E1000_DOWN, &adapter->state))
			mod_timer(&adapter->watchdog_timer, jiffies + 1);
	}
這里調用了_napi_schedule完成將設備的napi隊列掛到CPU
	if (napi_schedule_prep(&adapter->napi)) {
		adapter->total_tx_bytes = 0;
		adapter->total_tx_packets = 0;
		adapter->total_rx_bytes = 0;
		adapter->total_rx_packets = 0;
		__napi_schedule(&adapter->napi);
	}

	return IRQ_HANDLED;
}

　　

void __napi_schedule(struct napi_struct *n)
{
	unsigned long flags;

	local_irq_save(flags);
	list_add_tail(&n->poll_list, &__get_cpu_var(softnet_data).poll_list);//adapter里面的隊列地址掛到poll.list中
	//設置軟中斷NET_RX_SOFTIRQ，等待調度其中斷處理程序
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
	local_irq_restore(flags);
}

　　再看一下如何打開網絡設備

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

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

	netif_carrier_off(netdev);
初始化傳輸和接收描述符，這里主要是對接收環和發送環進行初始化，他們需要256個單元空間
	/* allocate transmit descriptors */
	err = e1000e_setup_tx_resources(adapter);
	if (err)
		goto err_setup_tx;

	/* allocate receive descriptors */
	err = e1000e_setup_rx_resources(adapter);
	if (err)
		goto err_setup_rx;

	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);

	/*
	 * If AMT is enabled, let the firmware know that the network
	 * interface is now open
	 */
	if (adapter->flags & FLAG_HAS_AMT)
		e1000_get_hw_control(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.
	 */這個函數比較重要，在這里面完成對容器的配置，包括軟中斷設置
	e1000_configure(adapter);
{

static void e1000_configure(struct e1000_adapter *adapter)
{
	e1000_set_multi(adapter->netdev);

	e1000_restore_vlan(adapter);
	e1000_init_manageability(adapter);

	e1000_configure_tx(adapter);配置發送
	e1000_setup_rctl(adapter);
	e1000_configure_rx(adapter);配置接收
	adapter->alloc_rx_buf(adapter, e1000_desc_unused(adapter->rx_ring));
}

}
	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);

	e1000_irq_enable(adapter);

	netif_start_queue(netdev);

	/* fire a link status change interrupt to start the watchdog */
	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);

	return err;

　　這里看一下接收容器中斷設置

static void e1000_configure_rx(struct e1000_adapter *adapter)
{
	struct e1000_hw *hw = &adapter->hw;
	struct e1000_ring *rx_ring = adapter->rx_ring;
	u64 rdba;
	u32 rdlen, rctl, rxcsum, ctrl_ext;

	if (adapter->rx_ps_pages) {
		/* this is a 32 byte descriptor */
		rdlen = rx_ring->count *
			sizeof(union e1000_rx_desc_packet_split);
		adapter->clean_rx = e1000_clean_rx_irq_ps;
		adapter->alloc_rx_buf = e1000_alloc_rx_buffers_ps;
	} else if (adapter->netdev->mtu > ETH_FRAME_LEN + ETH_FCS_LEN) {
		rdlen = rx_ring->count * sizeof(struct e1000_rx_desc);
		adapter->clean_rx = e1000_clean_jumbo_rx_irq;
		adapter->alloc_rx_buf = e1000_alloc_jumbo_rx_buffers;
	} else {
		rdlen = rx_ring->count * sizeof(struct e1000_rx_desc);
		adapter->clean_rx = e1000_clean_rx_irq; 這里的函數是對前半段的一個處理流程，主要是將數據從DMA中獲取然后放到隊列中，供后半段進行處理。
		adapter->alloc_rx_buf = e1000_alloc_rx_buffers;
	}

	/* disable receives while setting up the descriptors */ //寫接收控制寄存器 暫時停止接收
	rctl = er32(RCTL);
	ew32(RCTL, rctl & ~E1000_RCTL_EN);
	e1e_flush();
	msleep(10);

	/* set the Receive Delay Timer Register *///設置RDTR寄存器 有關
	ew32(RDTR, adapter->rx_int_delay);

	/* irq moderation */ //設置RADV寄存器 有關RADV具體詳見開發者手冊  
	ew32(RADV, adapter->rx_abs_int_delay);
	if (adapter->itr_setting != 0)
		ew32(ITR, 1000000000 / (adapter->itr * 256));

	ctrl_ext = er32(CTRL_EXT);
	/* Reset delay timers after every interrupt */
	ctrl_ext |= E1000_CTRL_EXT_INT_TIMER_CLR;
	/* Auto-Mask interrupts upon ICR access */
	ctrl_ext |= E1000_CTRL_EXT_IAME;
	ew32(IAM, 0xffffffff);
	ew32(CTRL_EXT, ctrl_ext);
	e1e_flush();

	/*
	 * Setup the HW Rx Head and Tail Descriptor Pointers and
	 * the Base and Length of the Rx Descriptor Ring
	 */
	 //與接收描述符環有關的有4個寄存器：RDBA存放描述符緩沖的首地址 做為基地址 供64位 包括各32位的高低地址  
//RDLEN：為緩沖區分配的總空間的大小 RDH和RDT是頭尾指針 存放相對基址的偏移量 RDH的值由硬件增加 表示指向下一次DMA將用的描述符 
//RDT由軟件增加 表示下一次要處理並送交協議棧的有關描述符 
	rdba = rx_ring->dma;
	ew32(RDBAL, (rdba & DMA_BIT_MASK(32)));
	ew32(RDBAH, (rdba >> 32));
	ew32(RDLEN, rdlen);
	ew32(RDH, 0);
	ew32(RDT, 0);
	rx_ring->head = E1000_RDH;
	rx_ring->tail = E1000_RDT;

	/* Enable Receive Checksum Offload for TCP and UDP */
	rxcsum = er32(RXCSUM);
	if (adapter->flags & FLAG_RX_CSUM_ENABLED) {
		rxcsum |= E1000_RXCSUM_TUOFL;

		/*
		 * IPv4 payload checksum for UDP fragments must be
		 * used in conjunction with packet-split.
		 */
		if (adapter->rx_ps_pages)
			rxcsum |= E1000_RXCSUM_IPPCSE;
	} else {
		rxcsum &= ~E1000_RXCSUM_TUOFL;
		/* no need to clear IPPCSE as it defaults to 0 */
	}
	ew32(RXCSUM, rxcsum);

	/*
	 * Enable early receives on supported devices, only takes effect when
	 * packet size is equal or larger than the specified value (in 8 byte
	 * units), e.g. using jumbo frames when setting to E1000_ERT_2048
	 */
	if ((adapter->flags & FLAG_HAS_ERT) &&
	    (adapter->netdev->mtu > ETH_DATA_LEN)) {
		u32 rxdctl = er32(RXDCTL(0));
		ew32(RXDCTL(0), rxdctl | 0x3);
		ew32(ERT, E1000_ERT_2048 | (1 << 13));
		/*
		 * With jumbo frames and early-receive enabled, excessive
		 * C4->C2 latencies result in dropped transactions.
		 */
		pm_qos_update_requirement(PM_QOS_CPU_DMA_LATENCY,
					  e1000e_driver_name, 55);
	} else {
		pm_qos_update_requirement(PM_QOS_CPU_DMA_LATENCY,
					  e1000e_driver_name,
					  PM_QOS_DEFAULT_VALUE);
	}

	/* Enable Receives */
	ew32(RCTL, rctl);
}