linux网络流程分析(一)---网卡驱动

分析linux网络的书已经很多了,包括《追踪Linux TCP/IP代码运行》《Linux内核源码剖析——TCP/IP实现》,这里我只是从数据包在linux内核中的基本流程来分析,尽可能的展现一个主流程框架。

内核如何从网卡接收数据,传统的过程:
1.数据到达网卡;
2.网卡产生一个中断给内核;
3.内核使用I/O指令,从网卡I/O区域中去读取数据;

 
我们在许多网卡驱动中(很老那些),都可以在网卡的中断函数中见到这一过程。
 
但是,这一种方法,有一种重要的问题,就是大流量的数据来到,网卡会产生大量的中断,内核在中断上下文 中,会浪费大量的资源来处理中断本身。所以,就有一个问题,“可不可以不使用中断”,这就是轮询技术,所谓NAPI技术,说来也不神秘,就是说,内核屏蔽 中断,然后隔一会儿就去问网卡,“你有没有数据啊?”……
 
从这个描述本身可以看到,如果数据量少,轮询同样占用大量的不必要的CPU资源,大家各有所长吧
 
OK,另一个问题,就是从网卡的I/O区域,包括I/O寄存器或I/O内存中去读取数据,这都要CPU 去读,也要占用CPU资源,“CPU从I/O区域读,然后把它放到内存(这个内存指的是系统本身的物理内存,跟外设的内存不相干,也叫主内存)中”。于是 自然地,就想到了DMA技术——让网卡直接从主内存之间读写它们的I/O数据,CPU,这儿不干你事,自己找乐子去:
1.首先,内核在主内存中为收发数据建立一个环形的缓冲队列(通常叫DMA环形缓冲区)。
2.内核将这个缓冲区通过DMA映射,把这个队列交给网卡;
3.网卡收到数据,就直接放进这个环形缓冲区了——也就是直接放进主内存了;然后,向系统产生一个中断;
4.内核收到这个中断,就取消DMA映射,这样,内核就直接从主内存中读取数据;
 
——呵呵,这一个过程比传统的过程少了不少工作,因为设备直接把数据放进了主内存,不需要CPU的干预,效率是不是提高不少?
 
对应以上4步,来看它的具体实现:
1)分配环形DMA缓冲区
Linux内核中,用skb来描述一个缓存,所谓分配,就是建立一定数量的skb,然后用e1000_rx_ring 环形缓冲区队列描述符连接起来
2)建立DMA映射
内核通过调用
dma_map_single(struct device *dev,void *buffer,size_t size,enum dma_data_direction direction)
建立映射关系。
struct device *dev 描述一个设备;
buffer:把哪个地址映射给设备;也就是某一个skb——要映射全部,当然是做一个双向链表的循环即可;
size:缓存大小;
direction:映射方向——谁传给谁:一般来说,是“双向”映射,数据在设备和内存之间双向流动;
对于PCI设备而言(网卡一般是PCI的),通过另一个包裹函数pci_map_single,这样,就把buffer交给设备了!设备可以直接从里边读/取数据。
3)这一步由硬件完成;
4)取消映射
dma_unmap_single,对PCI而言,大多调用它的包裹函数pci_unmap_single,不取消的话,缓存控制权还在设备手里,要调用 它,把主动权掌握在CPU手里——因为我们已经接收到数据了,应该由CPU把数据交给上层网络栈;当然,不取消之前,通常要读一些状态位信息,诸如此类, 一般是调用dma_sync_single_for_cpu()让CPU在取消映射前,就可以访问DMA缓冲区中的内容

首先,数据包从网卡光电信号来之后,先经过网卡驱动,转换成skb,进入链路层,那么我首先就先分析一下网卡驱动的流程。

源码位置:Driver/net/E1000e文件夹下面。

static int __init e1000_init_module(void)
{注册网卡驱动,按照PCI驱动开发方式来进行注册
	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;
}

  然后看一下驱动结构体内容,这里不对PCI类型驱动开发做介绍了。

/* 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
};

  这里面最重要的函数是e1000_probe,先看一下这个函数的作用是什么:“Device Initialization Routine”,这个应该不难理解。

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);
从这里开始对设备驱动进行初始化,包括名称、内存之类的。
	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;
这里要为驱动分配一个容器之类的,因为驱动后面的一切操作都是在它的基础之上。 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表示设备映射的内存的的bar mmio_start = pci_resource_start(pdev, 0); mmio_len = pci_resource_len(pdev, 0); err = -EIO;
这里我的理解是容器的硬件地址与bar进行映射,hw_addr代表的是网卡的硬件地址 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; 这里是默认的接收环和发送环大小是256,其实一次中断,能接受的数据不会有太高,我做实验的时候也就是1个2个。这里的环不是一直存放skb_buff,而是DMA一次中断后能给内核的数据存放地,当中断结束后,skb_buff会被转移的。 /* 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");
注册网卡驱动 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; }

  通过上面的函数,我们完成了驱动的初始化和设备注册工作。下面是网卡设备注册的操作函数

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
};

  这里关注一下最后一个函数

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

	disable_irq(adapter->pdev->irq);这里关闭容器设备中断
	e1000_intr(adapter->pdev->irq, netdev); 初始化设备中断

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

  这是网卡驱动的中断处理函数,也就是后半段的处理

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);
	}
这里调用了_napi_schedule完成将设备的napi队列挂到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里面的队列地址挂到poll.list中
	//设置软中断NET_RX_SOFTIRQ,等待调度其中断处理程序
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
	local_irq_restore(flags);
}

  再看一下如何打开网络设备

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);
初始化传输和接收描述符,这里主要是对接收环和发送环进行初始化,他们需要256个单元空间
	/* 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.
	 */这个函数比较重要,在这里面完成对容器的配置,包括软中断设置
	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);配置发送
	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;

  这里看一下接收容器中断设置

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; 这里的函数是对前半段的一个处理流程,主要是将数据从DMA中获取然后放到队列中,供后半段进行处理。
		adapter->alloc_rx_buf = e1000_alloc_rx_buffers;
	}

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

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

	/* irq moderation */ //设置RADV寄存器 有关RADV具体详见开发者手册  
	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
	 */
	 //与接收描述符环有关的有4个寄存器:RDBA存放描述符缓冲的首地址 做为基地址 供64位 包括各32位的高低地址  
//RDLEN:为缓冲区分配的总空间的大小 RDH和RDT是头尾指针 存放相对基址的偏移量 RDH的值由硬件增加 表示指向下一次DMA将用的描述符 
//RDT由软件增加 表示下一次要处理并送交协议栈的有关描述符 
	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);
}

  

posted @ 2012-06-10 16:20  北海石松  阅读(15202)  评论(1编辑  收藏  举报