Linux网络协议栈之驱动框架

网卡驱动可以以模块的方式加载也可以内核初始化的时候加载，我们选定e100系列的网卡进行说明网卡驱动的一般框架。网卡设备通用数据结构：struct net_device{ /* * This is the first field of the "visible" part of this structure * （i.e. as seen by users in the "Space.c" file）. It is the name * the interface. */ /*网络设备名*/ char name[IFNAMSIZ]; /* device name hash chain */ /*根据网络设备名以散列表的形式组织到dev_name_head散列表中，这样就可以通过网络设备名快速地定位到网络设备*/ struct hlist_node name_hlist; /* * I/O specific fields * FIXME: Merge these and struct ifmap into one */ /*网络设备共享内存的起始和终止地址*/ unsigned long mem_end; /* shared mem end */ unsigned long mem_start; /* shared mem start */ /*网络接口I/O基地址，在探测设备时被初始化ifconfig命令可显示和修改当前命令*/ unsigned long base_addr; /* device I/O address */ /*分配给设备的中断号，一般在初始化设备时被初始化*/ unsigned int irq; /* device IRQ number */ /* * Some hardware also needs these fields, but they are not * part of the usual set specified in Space.c. */ /*指定在多端口设备上使用那个端口*/ unsigned char if_port; /* Selectable AUI, TP,..*/ /*为设备分配的DMA通道*/ unsigned char dma; /* DMA channel */ /*设备状态*/ unsigned long state; /*网络设备组织*/ struct net_device *next; /*驱动程序的初始化函数*/ /* The device initialization function. Called only once. */ int （*init）（struct net_device *dev）; /* ------- Fields preinitialized in Space.c finish here ------- */ /* Net device features */ /*接口支持特性*/ unsigned long features;#define NETIF_F_SG 1 /* Scatter/gather IO. */#define NETIF_F_IP_CSUM 2 /* Can checksum only TCP/UDP over IPv4. */#define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */#define NETIF_F_HW_CSUM 8 /* Can checksum all the packets. */#define NETIF_F_HIGHDMA 32 /* Can DMA to high memory. */#define NETIF_F_FRAGLIST 64 /* Scatter/gather IO. */#define NETIF_F_HW_VLAN_TX 128 /* Transmit VLAN hw acceleration */#define NETIF_F_HW_VLAN_RX 256 /* Receive VLAN hw acceleration */#define NETIF_F_HW_VLAN_FILTER 512 /* Receive filtering on VLAN */#define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN packets */#define NETIF_F_GSO 2048 /* Enable software GSO. */#define NETIF_F_LLTX 4096 /* LockLess TX */ /* Segmentation offload features */#define NETIF_F_GSO_SHIFT 16#define NETIF_F_GSO_MASK 0xffff0000#define NETIF_F_TSO （SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT）#define NETIF_F_UFO （SKB_GSO_UDP << NETIF_F_GSO_SHIFT）#define NETIF_F_GSO_ROBUST （SKB_GSO_DODGY << NETIF_F_GSO_SHIFT）#define NETIF_F_TSO_ECN （SKB_GSO_TCP_ECN << NETIF_F_GSO_SHIFT）#define NETIF_F_TSO6 （SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT） /* List of features with software fallbacks. */#define NETIF_F_GSO_SOFTWARE （NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6） #define NETIF_F_GEN_CSUM （NETIF_F_NO_CSUM | NETIF_F_HW_CSUM）#define NETIF_F_ALL_CSUM （NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM） /*用于连接那些已经调度有数据报输出的网络设备指针*/ struct net_device *next_sched; /* Interface index. Unique device identifier */ /*网络设备的索引号*/ int ifindex; /*网络设备的唯一标识，主要用于虚拟隧道设备*/ int iflink; /*提供给应用程序获得接口统计信息的接口*/ struct net_device_stats* （*get_stats）（struct net_device *dev）; /* List of functions to handle Wireless Extensions （instead of ioctl）. * See <net/iw_handler.h> for details. Jean II */ /*无线网相关*/ const struct iw_handler_def * wireless_handlers; /* Instance data managed by the core of Wireless Extensions. */ struct iw_public_data * wireless_data; const struct ethtool_ops *ethtool_ops; /* * This marks the end of the "visible" part of the structure. All * fields hereafter are internal to the system, and may change at * will （read: may be cleaned up at will）. */ unsigned int flags; /* interface flags （a la BSD） */ /*记录当前网络设备IFF_PROMISC和IFF_ALLMULTI的状态，用来配合flags的设置*/ unsigned short gflags; unsigned short priv_flags; /* Like "flags" but invisible to userspace. */ unsigned short padded; /* How much padding added by alloc_netdev（） */ unsigned char operstate; /* RFC2863 operstate */ unsigned char link_mode; /* mapping policy to operstate */ unsigned mtu; /* interface MTU value */ unsigned short type; /* interface hardware type */ unsigned short hard_header_len; /* hardware hdr length */ struct net_device *master; /* Pointer to master device of a group, * which this device is member of. */ /* Interface address info. */ /*MAC地址，通常初始化时从硬件中读出来*/ unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ unsigned char addr_len; /* hardware address length */ unsigned short dev_id; /* for shared network cards */ struct dev_mc_list *mc_list; /* Multicast mac addresses */ int mc_count; /* Number of installed mcasts */ /*设置网络设备混杂模式计数器*/ int promiscuity; /*设置网络设备接收所有组播报的计数器，每次设置或是退出操作，该字段都会相应的加或减1，为0时，网络设备才真正不再接收组播报*/ int allmulti; /* Protocol specific pointers */ void *atalk_ptr; /* AppleTalk link */ void *ip_ptr; /* IPv4 specific data */ void *dn_ptr; /* DECnet specific data */ void *ip6_ptr; /* IPv6 specific data */ void *ec_ptr; /* Econet specific data */ void *ax25_ptr; /* AX.25 specific data *//* * Cache line mostly used on receive path （including eth_type_trans（）） */ /*该结构实例通过该字段连接到softnet_data的poll_list成员上*/ struct list_head poll_list ____cacheline_aligned_in_smp; /* Link to poll list */ /*轮询模式操作接口*/ int （*poll）（struct net_device *dev, int *quota）; /*读取数据包的配额，动态变化，由netdev_budget初始化，每次从网络设备中读取数据包后，会从中减去本次读取的数据包数，当该配额等于或小于0时，结束当前轮询等待下层轮询这样即使某个网络设备有大量的数据包输入，也能保证其他网络设备能及时收到数据包在输入时，遍历网络设备轮询队列，从选定的网络设备中读取数据包，一旦已经读取的数据包的数量操作配额，即停止本次读取，将该网络设备移至网络设备轮询队列的队尾，等待下次轮询*/ int quota; /*数据包输入软中断中，单个网络读取数据包的配额*/ int weight; unsigned long last_rx; /* Time of last Rx */ /* Interface address info used in eth_type_trans（） */ unsigned char dev_addr[MAX_ADDR_LEN]; /* hw address, （before bcast because most packets are unicast） */ unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add *//* * Cache line mostly used on queue transmit path （qdisc） */ /* device queue lock */ spinlock_t queue_lock ____cacheline_aligned_in_smp; /*当前使用的根排队规则，配置的排队规则生效时由qdisc_sleeping设置*/ struct Qdisc *qdisc; /*当前配置的排队规则，生效时将被设置到qdisc*/ struct Qdisc *qdisc_sleeping; /*通过链表方式记录配置所在网络的所有排队规则*/ struct list_head qdisc_list; /*可在设备发送队列中排队的最大数据包*/ unsigned long tx_queue_len; /* Max frames per queue allowed */ /* Partially transmitted GSO packet. */ struct sk_buff *gso_skb; /* ingress path synchronizer */ spinlock_t ingress_lock; /*数据包输入的排队规则*/ struct Qdisc *qdisc_ingress;/* * One part is mostly used on xmit path （device） */ /* hard_start_xmit synchronizer */ spinlock_t _xmit_lock ____cacheline_aligned_in_smp; /* cpu id of processor entered to hard_start_xmit or -1, if nobody entered there. */ int xmit_lock_owner; void *priv; /* pointer to private data */ /*驱动提供给上一层发送数据包的接口，在发送数据包时必定会调用该接口*/ int （*hard_start_xmit）（struct sk_buff *skb, struct net_device *dev）; /* These may be needed for future network-power-down code. */ unsigned long trans_start; /* Time （in jiffies） of last Tx */ /*网络层确定传输已经超时，而调用驱动程序的tx_timeout接口的最短时间*/ int watchdog_timeo; /* used by dev_watchdog（） */ /*用于检测网络设备处于正常的工作状态时，是否存在由于关闭队列功能而导致发送超时的情况，一旦发生以上状况，就调用网络设备驱动的tx_timeout 接口处理*/ struct timer_list watchdog_timer;/* * refcnt is a very hot point, so align it on SMP */ /* Number of references to this device */ atomic_t refcnt ____cacheline_aligned_in_smp; /* delayed register/unregister */ /*用来连接net_todo_list链表，包含已经注销即将结束的网络设备*/ struct list_head todo_list; /* device index hash chain */ /*根据网络设备的索引，以散列表的形式组织到dev_index_hlist中*/ struct hlist_node index_hlist; /* register/unregister state machine */ enum { NETREG_UNINITIALIZED=0, NETREG_REGISTERED, /* completed register_netdevice */ NETREG_UNREGISTERING, /* called unregister_netdevice */ NETREG_UNREGISTERED, /* completed unregister todo */ NETREG_RELEASED, /* called free_netdev */ } reg_state; /* Called after device is detached from network. */ void （*uninit）（struct net_device *dev）; /* Called after last user reference disappears. */ void （*destructor）（struct net_device *dev）; /* Pointers to interface service routines. */ /*启用设备函数指针，完成那个注册所需的系统资源，打开硬件极其所有设备*/ int （*open）（struct net_device *dev）; int （*stop）（struct net_device *dev）;#define HAVE_NETDEV_POLL/*根据先前检测到的源和目标硬件地址创建硬件首部*/ int （*hard_header）（struct sk_buff *skb, struct net_device *dev, unsigned short type, void *daddr, void *saddr, unsigned len）;/*用来在传输包之前，ARP解析完成之后，重建硬件首部*/ int （*rebuild_header）（struct sk_buff *skb）;#define HAVE_MULTICAST /*将组播地址列表更新到网络设备中*/ void （*set_multicast_list）（struct net_device *dev）;#define HAVE_SET_MAC_ADDR /*修改硬件地址接口，需要网络设备支持该功能*/ int （*set_mac_address）（struct net_device *dev, void *addr）;#define HAVE_PRIVATE_IOCTL int （*do_ioctl）（struct net_device *dev, struct ifreq *ifr, int cmd）;#define HAVE_SET_CONFIG int （*set_config）（struct net_device *dev, struct ifmap *map）;#define HAVE_HEADER_CACHE /*根据ARP查询的结果填充hh_cache结构*/ int （*hard_header_cache）（struct neighbour *neigh, struct hh_cache *hh）; void （*header_cache_update）（struct hh_cache *hh, struct net_device *dev, unsigned char * haddr）;#define HAVE_CHANGE_MTU int （*change_mtu）（struct net_device *dev, int new_mtu）; #define HAVE_TX_TIMEOUT void （*tx_timeout）（struct net_device *dev）; void （*vlan_rx_register）（struct net_device *dev, struct vlan_group *grp）; void （*vlan_rx_add_vid）（struct net_device *dev, unsigned short vid）; void （*vlan_rx_kill_vid）（struct net_device *dev, unsigned short vid）; int （*hard_header_parse）（struct sk_buff *skb, unsigned char *haddr）; /*设置邻居子系统相关的参数*/ int （*neigh_setup）（struct net_device *dev, struct neigh_parms *）;#ifdef CONFIG_NETPOLL /*网络设备netpoll信息块*/ struct netpoll_info *npinfo;#endif#ifdef CONFIG_NET_POLL_CONTROLLER /*该函数在禁止中断的情况下，要求驱动程序以轮询模式在接口上查询事件*/ void （*poll_controller）（struct net_device *dev）;#endif /* bridge stuff */ struct net_bridge_port *br_port; /* class/net/name entry */ struct class_device class_dev; /* space for optional statistics and wireless sysfs groups */ struct attribute_group *sysfs_groups[3];};网卡驱动的注册是在e100_init_modle中，static int __init e100_init_module（void）{ if（（（1 << debug） - 1） & NETIF_MSG_DRV） { printk（KERN_INFO PFX "%s, %s ", DRV_DESCRIPTION, DRV_VERSION）; printk（KERN_INFO PFX "%s ", DRV_COPYRIGHT）; } return pci_register_driver（&e100_driver）;}可见，网卡驱动也就是和一般的PCI驱动编写一样。static struct pci_driver e100_driver = { .name = DRV_NAME, .id_table = e100_id_table, .probe = e100_probe, .remove = __devexit_p（e100_remove）,#ifdef CONFIG_PM /* Power Management hooks */ .suspend = e100_suspend, .resume = e100_resume,#endif .shutdown = e100_shutdown, .err_handler = &e100_err_handler,}; 如果网络设备驱动程序被编译进内核，则将在启动时被初始化，在运行时作为模块被加载。无论初始化是否被发生，由驱动程序控制的网络设备都会被注册。这种情形适用于所有的总线类型，无论是总线体系结构还是模块初始??代码调用注册函数，结果都是一样的。PCI设备驱动程序加载以至执行pci_drive->probe（）函数。我们看看e100网卡的驱动注册过程：static int __devinit e100_probe（struct pci_dev *pdev, const struct pci_device_id *ent）{ struct net_device *netdev; struct nic *nic; int err; /*分配设备数据结构*/ if（！（netdev = alloc_etherdev（sizeof（struct nic）））） { if（（（1 << debug） - 1） & NETIF_MSG_PROBE） printk（KERN_ERR PFX "Etherdev alloc failed, abort. "）; return -ENOMEM; } /*初始化设备*/ netdev->open = e100_open; netdev->stop = e100_close; /*e100网络设备的hard_start_xmit接口实现，最终将数据包输出到硬件*/ netdev->hard_start_xmit = e100_xmit_frame; netdev->get_stats = e100_get_stats; netdev->set_multicast_list = e100_set_multicast_list; netdev->set_mac_address = e100_set_mac_address; netdev->change_mtu = e100_change_mtu; netdev->do_ioctl = e100_do_ioctl; SET_ETHTOOL_OPS（netdev, &e100_ethtool_ops）; netdev->tx_timeout = e100_tx_timeout; netdev->watchdog_timeo = E100_WATCHDOG_PERIOD; netdev->poll = e100_poll; netdev->weight = E100_NAPI_WEIGHT;#ifdef CONFIG_NET_POLL_CONTROLLER/*为了实现netpoll接收报文功能，需要实现下面的函数调用，该函数用来模拟网络设备发生中断，进行中断处理*/ netdev->poll_controller = e100_netpoll;#endif strncpy（netdev->name, pci_name（pdev）, sizeof（netdev->name） - 1）; /*在alloc_etherdev中设置的私有属性,即结构nic，在这里提出来*/ nic = netdev_priv（netdev）; /*初始化该nic*/ nic->netdev = netdev; nic->pdev = pdev; nic->msg_enable = （1 << debug） - 1; /*设置PCI设备私有数据为网络设备结构实例*/ pci_set_drvdata（pdev, netdev）; /* Initialize device before it"s used by a driver. Ask low-level code * to enable I/O and memory. Wake up the device if it was suspended. * Beware, this function can fail.*/ if（（err = pci_enable_device（pdev））） { DPRINTK（PROBE, ERR, "Cannot enable PCI device, aborting. "）; goto err_out_free_dev; } if（！（pci_resource_flags（pdev, 0） & IORESOURCE_MEM）） { DPRINTK（PROBE, ERR, "Cannot find proper PCI device " "base address, aborting. "）; err = -ENODEV; goto err_out_disable_pdev; } /*保留资源，包括I/O和内存*/ if（（err = pci_request_regions（pdev, DRV_NAME））） { DPRINTK（PROBE, ERR, "Cannot obtain PCI resources, aborting. "）; goto err_out_disable_pdev; } /*DMA相关,探测设备的DMA能力，如果设备支持DMA, 返回0*/ if（（err = pci_set_dma_mask（pdev, DMA_32BIT_MASK））） { DPRINTK（PROBE, ERR, "No usable DMA configuration, aborting. "）; goto err_out_free_res; } SET_MODULE_OWNER（netdev）; SET_NETDEV_DEV（netdev, &pdev->dev）; /*控制状态寄存器映射内存资源*/ nic->csr = ioremap（pci_resource_start（pdev, 0）, sizeof（struct csr））; if（！nic->csr） { DPRINTK（PROBE, ERR, "Cannot map device registers, aborting. "）; err = -ENOMEM; goto err_out_free_res; } if（ent->driver_data） nic->flags |= ich; else nic->flags &= ~ich; /*初始化nic相关字段*/ e100_get_defaults（nic）; /* locks must be initialized before calling hw_reset */ spin_lock_init（&nic->cb_lock）; spin_lock_init（&nic->cmd_lock）; spin_lock_init（&nic->mdio_lock）; /* Reset the device before pci_set_master（） in case device is in some * funky state and has an interrupt pending - hint: we don"t have the * interrupt handler registered yet. */ /*设备复位，写相关寄存器方式实现*/ e100_hw_reset（nic）; /*启用设备*/ pci_set_master（pdev）; /*初始化两个软件时钟*/ init_timer（&nic->watchdog）; nic->watchdog.function = e100_watchdog; nic->watchdog.data = （unsigned long）nic; init_timer（&nic->blink_timer）; nic->blink_timer.function = e100_blink_led; nic->blink_timer.data = （unsigned long）nic; /*初始化工作队列*/ INIT_WORK（&nic->tx_timeout_task, e100_tx_timeout_task）; /*从DMA区分配*/ if（（err = e100_alloc（nic））） { DPRINTK（PROBE, ERR, "Cannot alloc driver memory, aborting. "）; goto err_out_iounmap; } /*读取网卡的EEPROM。其中存放这网卡的MAC地址 */ if（（err = e100_eeprom_load（nic））） goto err_out_free; /*初始化nic的物理信息*/ e100_phy_init（nic）; memcpy（netdev->dev_addr, nic->eeprom, ETH_ALEN）; memcpy（netdev->perm_addr, nic->eeprom, ETH_ALEN）; /*验证网卡的MAC地址是否格式正确*/ if（！is_valid_ether_addr（netdev->perm_addr）） { DPRINTK（PROBE, ERR, "Invalid MAC address from " "EEPROM, aborting. "）; err = -EAGAIN; goto err_out_free; } /* Wol magic packet can be enabled from eeprom */ if（（nic->mac >= mac_82558_D101_A4） && （nic->eeprom[eeprom_id] & eeprom_id_wol）） nic->flags |= wol_magic; /* ack any pending wake events, disable PME */ /*,这个函数的第二个参数表示一种电源状态 PME#就是Power Management Event Signal,即电源管理事件信号.）PME#信号是PCI Power Spec中出镜率最高的一个名词.如果一个设备希望改变它的电源状态,它就可以发送一个PME#信号.而设备是否允许发送信号也是有开关的,并且每种状态都有一个开关第三个参数是表示开还是关.即传递1进去就是enable,传递0进去就是disable*/ err = pci_enable_wake（pdev, 0, 0）; if （err） DPRINTK（PROBE, ERR, "Error clearing wake event "）; /*网络设备的名称前加上eth*/ strcpy（netdev->name, "eth%d"）; /*注册网络设备*/ if（（err = register_netdev（netdev））） { DPRINTK（PROBE, ERR, "Cannot register net device, aborting. "）; goto err_out_free; } DPRINTK（PROBE, INFO, "addr 0x%llx, irq %d, " "MAC addr %02X:%02X:%02X:%02X:%02X:%02X ", （unsigned long long）pci_resource_start（pdev, 0）, pdev->irq, netdev->dev_addr[0], netdev->dev_addr[1], netdev->dev_addr[2], netdev->dev_addr[3], netdev->dev_addr[4], netdev->dev_addr[5]）; return 0;err_out_free: e100_free（nic）;err_out_iounmap: iounmap（nic->csr）;err_out_free_res: pci_release_regions（pdev）;err_out_disable_pdev: pci_disable_device（pdev）;err_out_free_dev: pci_set_drvdata（pdev, NULL）; free_netdev（netdev）; return err;}其辅助函数：分配网络设备结构/*传入的参数为nic结构的大小*/struct net_device *alloc_etherdev（int sizeof_priv）{ return alloc_netdev（sizeof_priv, "eth%d", ether_setup）;}struct net_device *alloc_netdev（int sizeof_priv, const char *name, void （*setup）（struct net_device *））{ void *p; struct net_device *dev; int alloc_size; BUG_ON（strlen（name） >= sizeof（dev->name））; /* ensure 32-byte alignment of both the device and private area */ /*计算分配的大小为设备结构大小加上nic结构大小*/ alloc_size = （sizeof（*dev） + NETDEV_ALIGN_CONST） & ~NETDEV_ALIGN_CONST; alloc_size += sizeof_priv + NETDEV_ALIGN_CONST; /*分配空间*/ p = kzalloc（alloc_size, GFP_KERNEL）; if （！p） { printk（KERN_ERR "alloc_netdev: Unable to allocate device. "）; return NULL; } dev = （struct net_device *）（（（long）p + NETDEV_ALIGN_CONST） & ~NETDEV_ALIGN_CONST）; /*计算padd大小为结构大小减去对其的数据大小*/ dev->padded = （char *）dev - （char *）p; if （sizeof_priv） /*私有数据为nic结构的起始地址*/ dev->priv = netdev_priv（dev）; /*调用参数中的函数指针，初始化设备结构*/ setup（dev）; strcpy（dev->name, name）; return dev;}/*分配设备结构时调用，用于初始化该设备结构*/void ether_setup（struct net_device *dev）{ dev->change_mtu = eth_change_mtu; dev->hard_header = eth_header; dev->rebuild_header = eth_rebuild_header; dev->set_mac_address = eth_mac_addr; dev->hard_header_cache = eth_header_cache; dev->header_cache_update= eth_header_cache_update; dev->hard_header_parse = eth_header_parse; dev->type = ARPHRD_ETHER; dev->hard_header_len = ETH_HLEN; dev->mtu = ETH_DATA_LEN; dev->addr_len = ETH_ALEN; dev->tx_queue_len = 1000; /* Ethernet wants good queues */ dev->flags = IFF_BROADCAST|IFF_MULTICAST; memset（dev->broadcast, 0xFF, ETH_ALEN）;}注册网络设备的实际操作由register_netdev（netdev）调用register_netdevice（）完成int register_netdevice（struct net_device *dev）{ struct hlist_head *head; struct hlist_node *p; int ret; BUG_ON（dev_boot_phase）; ASSERT_RTNL（）; /*2.6内核支持内核抢占，该函数检查是否需要从新调度如果是，则进行调度，无论此时进行执行在内核空间还是用户空间*/ might_sleep（）; /*初始化设备的各个字段*/ /* When net_device"s are persistent, this will be fatal. */ BUG_ON（dev->reg_state ！= NETREG_UNINITIALIZED）; spin_lock_init（&dev->queue_lock）; spin_lock_init（&dev->_xmit_lock）; dev->xmit_lock_owner = -1;#ifdef CONFIG_NET_CLS_ACT spin_lock_init（&dev->ingress_lock）;#endif dev->iflink = -1; /* Init, if this function is available */ /*如果有init函数，调用该函数进行初始化*/ if （dev->init） { ret = dev->init（dev）; if （ret） { if （ret > 0） ret = -EIO; goto out; }