STP相关先不管，以后有兴趣了在专门研究。

一、net_bridge、net_bridge_prot、net_bridge_fdb_entry数据结构

1. 网桥设备net_bridge数据结构

struct net_bridge {  /*自旋锁*/spinlock_t           lock;/*用于管理下面hash表的锁*/spinlock_t            hash_lock;/*网桥端口列表*/struct list_head        port_list;/*网桥设备*/struct net_device     *dev;struct pcpu_sw_netstats        __percpu *stats;/* These fields are accessed on each packet */
#ifdef CONFIG_BRIDGE_VLAN_FILTERINGu8               vlan_enabled;u8             vlan_stats_enabled;__be16               vlan_proto;u16              default_pvid;struct net_bridge_vlan_group   __rcu *vlgrp;
#endif/*hash链表，每一个元素指向一个net_bridge_fdb_entry表CAM表，转发表*/struct hlist_head      hash[BR_HASH_SIZE];
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)union {struct rtable     fake_rtable;struct rt6_info     fake_rt6_info;};bool                nf_call_iptables;bool               nf_call_ip6tables;bool              nf_call_arptables;
#endifu16               group_fwd_mask;u16              group_fwd_mask_required;/* STP */bridge_id          designated_root;bridge_id           bridge_id;u32               root_path_cost;unsigned char            topology_change;unsigned char           topology_change_detected;u16                root_port;unsigned long         max_age;unsigned long           hello_time;unsigned long            forward_delay;unsigned long         ageing_time;unsigned long           bridge_max_age;unsigned long            bridge_hello_time;unsigned long         bridge_forward_delay;unsigned long          bridge_ageing_time;u8               group_addr[ETH_ALEN];bool               group_addr_set;enum {BR_NO_STP,         /* no spanning tree */BR_KERNEL_STP,        /* old STP in kernel */BR_USER_STP,     /* new RSTP in userspace */} stp_enabled;#ifdef CONFIG_BRIDGE_IGMP_SNOOPINGunsigned char            multicast_router;u8             multicast_disabled:1;u8             multicast_querier:1;u8              multicast_query_use_ifaddr:1;u8             has_ipv6_addr:1;u8              multicast_stats_enabled:1;u32               hash_elasticity;u32             hash_max;u32                multicast_last_member_count;u32             multicast_startup_query_count;u8                multicast_igmp_version;unsigned long            multicast_last_member_interval;unsigned long            multicast_membership_interval;unsigned long         multicast_querier_interval;unsigned long            multicast_query_interval;unsigned long          multicast_query_response_interval;unsigned long         multicast_startup_query_interval;spinlock_t         multicast_lock;/*mdb指向网桥的组播数据库转发表*/struct net_bridge_mdb_htable __rcu *mdb;struct hlist_head        router_list;struct timer_list       multicast_router_timer;struct bridge_mcast_other_query  ip4_other_query;struct bridge_mcast_own_query   ip4_own_query;struct bridge_mcast_querier   ip4_querier;struct bridge_mcast_stats   __percpu *mcast_stats;
#if IS_ENABLED(CONFIG_IPV6)struct bridge_mcast_other_query  ip6_other_query;struct bridge_mcast_own_query   ip6_own_query;struct bridge_mcast_querier   ip6_querier;u8              multicast_mld_version;
#endif /* IS_ENABLED(CONFIG_IPV6) */
#endifstruct timer_list     hello_timer;struct timer_list       tcn_timer;struct timer_list     topology_change_timer;struct delayed_work       gc_work;struct kobject          *ifobj;u32              auto_cnt;#ifdef CONFIG_NET_SWITCHDEVint offload_fwd_mark;
#endifbool              neigh_suppress_enabled;
};

2. 网桥端口net_bridge_port数据结构

//net/bridge/br_private.h
struct net_bridge_port
{/*指向网桥端口所属的网桥设备*/struct net_bridge     *br;/*添加到网桥的设备*/struct net_device       *dev;/*网桥端口列表，连接到net_bridge->head_list*/struct list_head      list;/* STP */u8                priority;/*端口优先级*/u8                state;/*端口状态*/u16               port_no;/*端口号*/unsigned char            topology_change_ack;unsigned char           config_pending;port_id              port_id;/*端口ID，由端口优先级和端口号组成*/port_id             designated_port;bridge_id           designated_root;bridge_id           designated_bridge;u32               path_cost;u32               designated_cost;unsigned long           designated_age;struct timer_list        forward_delay_timer;struct timer_list       hold_timer;struct timer_list        message_age_timer;struct kobject            kobj;struct rcu_head            rcu;/*flags参数很重要*/unsigned long             flags;#ifdef CONFIG_BRIDGE_IGMP_SNOOPINGstruct bridge_mcast_own_query   ip4_own_query;
#if IS_ENABLED(CONFIG_IPV6)struct bridge_mcast_own_query    ip6_own_query;
#endif /* IS_ENABLED(CONFIG_IPV6) */unsigned char           multicast_router;struct timer_list      multicast_router_timer;struct hlist_head        mglist;struct hlist_node        rlist;
#endif#ifdef CONFIG_SYSFSchar               sysfs_name[IFNAMSIZ];
#endif#ifdef CONFIG_NET_POLL_CONTROLLERstruct netpoll           *np;
#endif
#ifdef CONFIG_BRIDGE_VLAN_FILTERINGstruct net_port_vlans __rcu  *vlan_info;
#endif
};

感觉就前面的三个br,dev,list有用。还有一个flags(老版本没有这个参数)。

(1). 关于flags参数：

参考：https://blog.csdn.net/sinat_20184565/article/details/80852155

网桥添加网络设备时，新接口的flags赋值为BR_LEARNING | BR_FLOOD，即新接口为自动状态接口

自动状态接口（AUTO_PORT）：

内核中对自动状态接口定义如下：即设置了学习|单播洪泛的接口。

#define BR_AUTO_MASK (BR_FLOOD | BR_LEARNING)

#define br_auto_port(p) ((p)->flags & BR_AUTO_MASK)

#define BR_HAIRPIN_MODE      BIT(0)
#define BR_BPDU_GUARD       BIT(1)
#define BR_ROOT_BLOCK       BIT(2)
#define BR_MULTICAST_FAST_LEAVE BIT(3)
#define BR_ADMIN_COST       BIT(4)
#define BR_LEARNING     BIT(5)
#define BR_FLOOD        BIT(6)
#define BR_AUTO_MASK        (BR_FLOOD | BR_LEARNING)
#define BR_PROMISC      BIT(7)
#define BR_PROXYARP     BIT(8)
#define BR_LEARNING_SYNC    BIT(9)
#define BR_PROXYARP_WIFI    BIT(10)


/* called with RTNL but without bridge lock */
static struct net_bridge_port *new_nbp(struct net_bridge *br,struct net_device *dev)
{int index;struct net_bridge_port *p;index = find_portno(br);if (index < 0)return ERR_PTR(index);p = kzalloc(sizeof(*p), GFP_KERNEL);if (p == NULL)return ERR_PTR(-ENOMEM);p->br = br;dev_hold(dev);p->dev = dev;p->path_cost = port_cost(dev);p->priority = 0x8000 >> BR_PORT_BITS;p->port_no = index;p->flags = BR_LEARNING | BR_FLOOD;br_init_port(p);br_set_state(p, BR_STATE_DISABLED);br_stp_port_timer_init(p);br_multicast_add_port(p);return p;
}

BR_LEARNING标志，在函数br_handle_frame_finish中判断，用来决定是否使用数据包的源MAC地址更新网桥的FDB转发表。

int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{struct net_bridge_port *p = br_port_get_rcu(skb->dev);struct net_bridge *br;br = p->br;if (p->flags & BR_LEARNING)br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false);
}

BR_FLOOD标志用来控制是否在接口上泛洪单播数据包，如果没有设置此标志，不能在此接口泛洪单播包。

void br_flood(struct net_bridge *br, struct sk_buff *skb, ...)
{struct net_bridge_port *p;list_for_each_entry_rcu(p, &br->port_list, list) {switch (pkt_type) {case BR_PKT_UNICAST:if (!(p->flags & BR_FLOOD))continue;break;
}

(2). 端口状态：

//linux/uapi/linux/if_bridge.h
#define BR_STATE_DISABLED 0
#define BR_STATE_LISTENING 1
#define BR_STATE_LEARNING 2
#define BR_STATE_FORWARDING 3
#define BR_STATE_BLOCKING 4

关闭：不收发任何报文
阻塞：只能接收BPDU，不能发送BPDU，不能收发数据帧，不进行地址学习，
监听：可以收发BPDU，不能收发数据帧，不进行地址学习
学习：可以收发BPDU，不收发数据帧，进行地址学习
转发：可以收发BPDU，可以收发数据帧，进行地址学习

记得在br_handle_frame_finish中用到了端口状态：

if (!p || p->state == BR_STATE_DISABLED)...
if (p->state == BR_STATE_LEARNING)...

3. net_bridge_fdb_entry数据结构

fdb：forward database

https://blog.csdn.net/qq_25077833/article/details/52834418

端口-MAC地址表

struct net_bridge_fdb_entry
{/*链接到net_bridge的hash[BR_HASH_SIZE]*/struct hlist_node      hlist;/*指向网桥端口*/struct net_bridge_port      *dst;struct rcu_head            rcu;unsigned long           updated;unsigned long           used;//引用计数/*mac地址*/mac_addr            addr;/*mac地址是否为本地地址，1为是*/unsigned char           is_local:1,/*mac地址为静态的，表示mac地址不会过期，本地地址都是静态的。*/is_static:1,added_by_user:1, //用户配置added_by_external_learn:1;//外部学习__u16               vlan_id;//MAC属于哪个VLAN？
};

这个is_local选项在br_handle_frame_finish()函数中查找fdb转发表后，会用到进行判断，如果目的端口的is_local=1，表示数据包是本地接收，需要送往三层进行进一步处理。

二、网桥相关函数

1.br_init()

网桥初始化函数

桥接程序既可以集成在内核中，也可以编译成单独模块。初始化函数为br_init()，清理函数为br_deinit()函数。定义在/net/bridge/br.c中。就是个模块，br_init()为初始化函数，br_deinit()为exit函数。

static int __init br_init(void)
{int err;BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb));/*注册STP协议*/err = stp_proto_register(&br_stp_proto);if (err < 0) {pr_err("bridge: can't register sap for STP\n");return err;}/*fdb初始化，分配一个fdb内存*/err = br_fdb_init();if (err)goto err_out;/*register_pernet_subsys - register a network namespace subsystem注册一个网络空间子系统*/err = register_pernet_subsys(&br_net_ops);if (err)goto err_out1;/*netfilter初始化*/err = br_nf_core_init();if (err)goto err_out2;/*注册netdevice通知链*/err = register_netdevice_notifier(&br_device_notifier);if (err)goto err_out3;/*注册netdevice_switch通知链*/err = register_netdev_switch_notifier(&br_netdev_switch_notifier);if (err)goto err_out4;/*netlink初始化*/err = br_netlink_init();if (err)goto err_out5;//安装网络设备的do_ioctl函数，也就是提供给用户空间ioctl接口。 brioctl_set(br_ioctl_deviceless_stub);#if IS_ENABLED(CONFIG_ATM_LANE)br_fdb_test_addr_hook = br_fdb_test_addr;
#endifpr_info("bridge: automatic filtering via arp/ip/ip6tables has been ""deprecated. Update your scripts to load br_netfilter if you ""need this.\n");return 0;err_out5:unregister_netdev_switch_notifier(&br_netdev_switch_notifier);
err_out4:unregister_netdevice_notifier(&br_device_notifier);
err_out3:br_nf_core_fini();
err_out2:unregister_pernet_subsys(&br_net_ops);
err_out1:br_fdb_fini();
err_out:stp_proto_unregister(&br_stp_proto);return err;
}

(1). register_netdevice_notifier(&br_device_notifier);

https://www.cnblogs.com/3me-linux/p/6566750.html

注册netdevice通知链，网桥设备是建立在其他设备之上的，那些设备的状态（UP/DOWN），地址改变等消息，会影响网桥设备的内部数据结构，如端口表，FDB等，因此需要关注netdev_chain，这些事件的处理由br_device_event()完成。

(2)brioctl_set(br_ioctl_deviceless_stub);

http://blog.sina.com.cn/s/blog_67cc0c8f0101oh33.html

用户空间程序使用网桥相关的命令来调用ioctl函数时，它经kernel依据命令所属的分类分派到compat_sock_ioctl_trans()函数，在compat_sock_ioctl_trans()函数中，根据cmd类型，调用相应函数，例如sock_ioctl()函数，dev_ifsioc()函数。sock_ioctl()函数，在sock_ioctl()函数里，当ioctl命令为SIOCGIFBR、SIOCSIFBR、SIOCBRADDBR、SIOCBRDELBR时，会调用br_ioctl_deviceless_stub()函数进行处理；在dev_ifsioc()函数中，调用设备的ndo_do_ioctl()函数，网桥对应的就是br_dev_ioctl()函数。

(3). compat_sock_ioctl_trans()函数

static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,unsigned int cmd, unsigned long arg)
{...switch (cmd) {case SIOCSIFBR:case SIOCGIFBR:return old_bridge_ioctl(argp);...case SIOCBRADDBR:case SIOCBRDELBR:return sock_ioctl(file, cmd, arg);case SIOCBRADDIF:case SIOCBRDELIF:...return dev_ifsioc(net, sock, cmd, argp);}}

(4). sock_ioctl()函数

static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{switch (cmd) {...case SIOCGIFBR:case SIOCSIFBR:case SIOCBRADDBR:case SIOCBRDELBR:err = -ENOPKG;if (!br_ioctl_hook)request_module("bridge");mutex_lock(&br_ioctl_mutex);if (br_ioctl_hook)err = br_ioctl_hook(net, cmd, argp);mutex_unlock(&br_ioctl_mutex);break;...}return err;
}

(5). dev_ifsioc()函数

/**  Perform the SIOCxIFxxx calls, inside rtnl_lock()*/
static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
{...switch (cmd) {.../**    Unknown or private ioctl*/default:if ((cmd >= SIOCDEVPRIVATE &&cmd <= SIOCDEVPRIVATE + 15) ||...cmd == SIOCBRADDIF ||cmd == SIOCBRDELIF ||...cmd == SIOCWANDEV) {err = -EOPNOTSUPP;if (ops->ndo_do_ioctl) {if (netif_device_present(dev))err = ops->ndo_do_ioctl(dev, ifr, cmd);elseerr = -ENODEV;}} elseerr = -EINVAL;}return err;
}

(6). br_ioctl_deviceless_stub()函数


int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *uarg)
{switch (cmd) {case SIOCGIFBR:case SIOCSIFBR:return old_deviceless(net, uarg);case SIOCBRADDBR:case SIOCBRDELBR:{char buf[IFNAMSIZ];if (!ns_capable(net->user_ns, CAP_NET_ADMIN))return -EPERM;if (copy_from_user(buf, uarg, IFNAMSIZ))return -EFAULT;buf[IFNAMSIZ-1] = 0;if (cmd == SIOCBRADDBR)return br_add_bridge(net, buf);return br_del_bridge(net, buf);}}return -EOPNOTSUPP;
}

(7) . br_dev_ioctl()函数

int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{struct net_bridge *br = netdev_priv(dev);switch (cmd) {case SIOCDEVPRIVATE:return old_dev_ioctl(dev, rq, cmd);case SIOCBRADDIF:case SIOCBRDELIF:return add_del_if(br, rq->ifr_ifindex, cmd == SIOCBRADDIF);}br_debug(br, "Bridge does not support ioctl 0x%x\n", cmd);return -EOPNOTSUPP;
}

2. br_add_bridge()

添加网桥函数。这个函数中调用alloc_netdev()分配网桥设备及私有数据内存，调用register_netdev()注册网桥设备。在alloc_netdev()函数中，调用了br_dev_setup()函数对新建立网桥进行初始化工作。

在alloc_netdev()中创建设备的时候，把参数name传递给dev->name，这个时候没有对name进行检验。

在register_netdev()注册设备的时候，对参数name进行校验，包括name合法性，name是否重复，name的形式是否为"前缀%d"形式，如果是，系统会根据前缀，顺序分配一个名称。

int br_add_bridge(struct net *net, const char *name)
{struct net_device *dev;int res;/*建立网桥设备*/dev = alloc_netdev(sizeof(struct net_bridge), name, NET_NAME_UNKNOWN,br_dev_setup);if (!dev)return -ENOMEM;/*设置网络设备所在的网络命名空间*/dev_net_set(dev, net);dev->rtnl_link_ops = &br_link_ops;/*注册网络设备*/res = register_netdev(dev);if (res)free_netdev(dev);return res;
}

(1). alloc_netdev宏定义

alloc_netdev()：给网络设备分配空间，alloc_netdev()调用的是alloc_netdev_mqs()函数。

#define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1)

sizeof_priv：网络设备私有数据大小
name：设备名称，或者“设备名前缀%d”形式，相同前缀的设备会进行统一编号，以确保设备名唯一
name_assign_type：设备名来源
setup：网络设备初始化函数，回调函数。

name_assign_typ类型：

这几个类似什么意思，还不清楚。

/* interface name assignment types (sysfs name_assign_type attribute) */
#define NET_NAME_UNKNOWN    0   /* unknown origin (not exposed to userspace) */
/*由内核枚举*/
#define NET_NAME_ENUM       1   /* enumerated by kernel */
#define NET_NAME_PREDICTABLE    2   /* predictably named by the kernel */
#define NET_NAME_USER       3   /* provided by user-space */
#define NET_NAME_RENAMED    4   /* renamed by user-space */

(2). alloc_netdev_mqs()函数：

alloc_netdev_mqs()函数，分配了net_device和私有数据的内存空间，对net_device进行了基本的初始化，并且分配了设备接收、发送队列空间。

rxqs：分配的传输队列的数量
rxqs：分配的接收队列的数量

/*** alloc_netdev_mqs - allocate network device* @sizeof_priv:      size of private data to allocate space for* @name:         device name format string*  @name_assign_type:     origin of device name*  @setup:            callback to initialize device*  @txqs:         the number of TX subqueues to allocate* @rxqs:         the number of RX subqueues to allocate**    Allocates a struct net_device with private data area for driver use*    and performs basic initialization.  Also allocates subqueue structs*    for each queue on the device.*/
struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,unsigned char name_assign_type,void (*setup)(struct net_device *),unsigned int txqs, unsigned int rxqs)
{struct net_device *dev;size_t alloc_size;struct net_device *p;/*name长度不能超过16，dev中name数组长16，为name[16]*/BUG_ON(strlen(name) >= sizeof(dev->name));/*不能没有传输队列*/if (txqs < 1) {pr_err("alloc_netdev: Unable to allocate device with zero queues\n");return NULL;}#ifdef CONFIG_SYSFSif (rxqs < 1) {pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n");return NULL;}
#endif/*将net_device数据结构长度按照32位对齐后，加上私有数据长度，产生总的内存分配长度。*/alloc_size = sizeof(struct net_device);if (sizeof_priv) {/* ensure 32-byte alignment of private area *//*net_device结构体32位对齐，确保私有数据也32位对齐*/alloc_size = ALIGN(alloc_size, NETDEV_ALIGN);alloc_size += sizeof_priv;}/* ensure 32-byte alignment of whole construct *//*这里增加31个字节空间，是为了下面将分配后的net_device结构体的地址调整到32位边界对齐时，预留空间。*/alloc_size += NETDEV_ALIGN - 1;p = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);if (!p)p = vzalloc(alloc_size);if (!p)return NULL;/*将net_device数据结构的地址对齐到32位边界，记录下调整后的地址dev,和实际分配的地址p，便于释放空间时使用实际起始地址p。*/dev = PTR_ALIGN(p, NETDEV_ALIGN);dev->padded = (char *)dev - (char *)p;dev->pcpu_refcnt = alloc_percpu(int);if (!dev->pcpu_refcnt)goto free_dev;if (dev_addr_init(dev))goto free_pcpu;dev_mc_init(dev);dev_uc_init(dev);dev_net_set(dev, &init_net);dev->gso_max_size = GSO_MAX_SIZE;dev->gso_max_segs = GSO_MAX_SEGS;dev->gso_min_segs = 0;INIT_LIST_HEAD(&dev->napi_list);INIT_LIST_HEAD(&dev->unreg_list);INIT_LIST_HEAD(&dev->close_list);INIT_LIST_HEAD(&dev->link_watch_list);INIT_LIST_HEAD(&dev->adj_list.upper);INIT_LIST_HEAD(&dev->adj_list.lower);INIT_LIST_HEAD(&dev->all_adj_list.upper);INIT_LIST_HEAD(&dev->all_adj_list.lower);INIT_LIST_HEAD(&dev->ptype_all);INIT_LIST_HEAD(&dev->ptype_specific);dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;setup(dev);dev->num_tx_queues = txqs;dev->real_num_tx_queues = txqs;if (netif_alloc_netdev_queues(dev))goto free_all;#ifdef CONFIG_SYSFSdev->num_rx_queues = rxqs;dev->real_num_rx_queues = rxqs;if (netif_alloc_rx_queues(dev))goto free_all;
#endifstrcpy(dev->name, name);//直接把name赋值给dev->namedev->name_assign_type = name_assign_type;dev->group = INIT_NETDEV_GROUP;if (!dev->ethtool_ops)dev->ethtool_ops = &default_ethtool_ops;return dev;free_all:free_netdev(dev);return NULL;free_pcpu:free_percpu(dev->pcpu_refcnt);
free_dev:netdev_freemem(dev);return NULL;
}

插入一句，最近在看代码的时候，创建设备的时候用的是alloc_etherdev()函数，功能和alloc_netdev()的一样，只是封装了一下：

alloc_etherdev()

#define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1)
#define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count)


/*** alloc_etherdev_mqs - Allocates and sets up an Ethernet device* @sizeof_priv: Size of additional driver-private structure to be allocated* for this Ethernet device* @txqs: The number of TX queues this device has.* @rxqs: The number of RX queues this device has.** Fill in the fields of the device structure with Ethernet-generic* values. Basically does everything except registering the device.** Constructs a new net device, complete with a private data area of* size (sizeof_priv).  A 32-byte (not bit) alignment is enforced for* this private data area.*/struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,unsigned int rxqs)
{return alloc_netdev_mqs(sizeof_priv, "eth%d", NET_NAME_UNKNOWN,ether_setup, txqs, rxqs);
}

（3）register_netdevice

这里只简单看一下name的赋值过程。


/***    register_netdevice  - register a network device*    @dev: device to register** Take a completed network device structure and add it to the kernel* interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier*  chain. 0 is returned on success. A negative errno code is returned* on a failure to set up the device, or if the name is a duplicate.** Callers must hold the rtnl semaphore. You may want* register_netdev() instead of this.**    BUGS:*  The locking appears insufficient to guarantee two parallel registers*   will not get the same name.*/int register_netdevice(struct net_device *dev)
{int ret;struct net *net = dev_net(dev);BUG_ON(dev_boot_phase);ASSERT_RTNL();might_sleep();/* When net_device's are persistent, this will be fatal. */BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);BUG_ON(!net);spin_lock_init(&dev->addr_list_lock);netdev_set_addr_lockdep_class(dev);ret = dev_get_valid_name(net, dev, dev->name);if (ret < 0)goto out;/* Init, if this function is available */if (dev->netdev_ops->ndo_init) {ret = dev->netdev_ops->ndo_init(dev);if (ret) {if (ret > 0)ret = -EIO;goto out;}}if (((dev->hw_features | dev->features) &NETIF_F_HW_VLAN_CTAG_FILTER) &&(!dev->netdev_ops->ndo_vlan_rx_add_vid ||!dev->netdev_ops->ndo_vlan_rx_kill_vid)) {netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n");ret = -EINVAL;goto err_uninit;}ret = -EBUSY;if (!dev->ifindex)dev->ifindex = dev_new_index(net);else if (__dev_get_by_index(net, dev->ifindex))goto err_uninit;/* Transfer changeable features to wanted_features and enable* software offloads (GSO and GRO).*/dev->hw_features |= NETIF_F_SOFT_FEATURES;dev->features |= NETIF_F_SOFT_FEATURES;dev->wanted_features = dev->features & dev->hw_features;if (!(dev->flags & IFF_LOOPBACK)) {dev->hw_features |= NETIF_F_NOCACHE_COPY;}/* Make NETIF_F_HIGHDMA inheritable to VLAN devices.*/dev->vlan_features |= NETIF_F_HIGHDMA;/* Make NETIF_F_SG inheritable to tunnel devices.*/dev->hw_enc_features |= NETIF_F_SG;/* Make NETIF_F_SG inheritable to MPLS.*/dev->mpls_features |= NETIF_F_SG;ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);ret = notifier_to_errno(ret);if (ret)goto err_uninit;ret = netdev_register_kobject(dev);if (ret)goto err_uninit;dev->reg_state = NETREG_REGISTERED;__netdev_update_features(dev);/**    Default initial state at registry is that the*  device is present.*/set_bit(__LINK_STATE_PRESENT, &dev->state);linkwatch_init_dev(dev);dev_init_scheduler(dev);dev_hold(dev);list_netdevice(dev);add_device_randomness(dev->dev_addr, dev->addr_len);/* If the device has permanent device address, driver should* set dev_addr and also addr_assign_type should be set to* NET_ADDR_PERM (default value).*/if (dev->addr_assign_type == NET_ADDR_PERM)memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);/* Notify protocols, that a new device appeared. */ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);ret = notifier_to_errno(ret);if (ret) {rollback_registered(dev);dev->reg_state = NETREG_UNREGISTERED;}/**  Prevent userspace races by waiting until the network*   device is fully setup before sending notifications.*/if (!dev->rtnl_link_ops ||dev->rtnl_link_state == RTNL_LINK_INITIALIZED)rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL);out:return ret;err_uninit:if (dev->netdev_ops->ndo_uninit)dev->netdev_ops->ndo_uninit(dev);goto out;
}

(4). dev_get_valid_name


static int dev_get_valid_name(struct net *net,struct net_device *dev,const char *name)
{BUG_ON(!net);if (!dev_valid_name(name))return -EINVAL;if (strchr(name, '%'))return dev_alloc_name_ns(net, dev, name);else if (__dev_get_by_name(net, name))return -EEXIST;else if (dev->name != name)strlcpy(dev->name, name, IFNAMSIZ);return 0;
}

(5). dev_alloc_name_ns

由系统根据前缀赋值名称。


static int dev_alloc_name_ns(struct net *net,struct net_device *dev,const char *name)
{char buf[IFNAMSIZ];int ret;ret = __dev_alloc_name(net, name, buf);if (ret >= 0)strlcpy(dev->name, buf, IFNAMSIZ);return ret;
}

例如我的设备上目前有一个br0，我想再创建一个br1：

3. br_dev_setup()函数

网桥初始化函数，网桥设备的net_device相应字段，网桥私有数据net_bridge字段设置。

void br_dev_setup(struct net_device *dev)
{/*netdev_prit()取网桥设备私有数据起始地址*/struct net_bridge *br = netdev_priv(dev);/*随机生成mac地址*/eth_hw_addr_random(dev);/*以太网设备初始化，用以太网通用参数初始化dev相应参数*/ether_setup(dev);/*网桥设备的操作函数集br_netdev_ops*/dev->netdev_ops = &br_netdev_ops;/*析构函数为br_dev_free*/dev->destructor = br_dev_free;/*网桥设备的以太网工具函数集*/dev->ethtool_ops = &br_ethtool_ops;/*设置网络设备的设备类型*/SET_NETDEV_DEVTYPE(dev, &br_type);/*传输队列长度为0*/dev->tx_queue_len = 0;/*设备标识为桥*/dev->priv_flags = IFF_EBRIDGE;dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL |NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |NETIF_F_HW_VLAN_STAG_TX;dev->vlan_features = COMMON_FEATURES;/*后面是网桥私有化数据初始化*//*dev指向自己对于的net_device*/br->dev = dev;/*锁初始化*/spin_lock_init(&br->lock);/*网桥端口列表初始化*/INIT_LIST_HEAD(&br->port_list);/*CAM表自旋锁初始化*/spin_lock_init(&br->hash_lock);/*网桥默认优先级0x8000，即32768*/br->bridge_id.prio[0] = 0x80;br->bridge_id.prio[1] = 0x00;/*STP初始化相关*//*802.1D(STP)组播01:80:C2:00:00:00*/ether_addr_copy(br->group_addr, eth_reserved_addr_base);/*默认没有开启STP，不阻塞任何组播包*/br->stp_enabled = BR_NO_STP;br->group_fwd_mask = BR_GROUPFWD_DEFAULT;br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT;br->designated_root = br->bridge_id;/*20s，BPDU老化时间*/br->bridge_max_age = br->max_age = 20 * HZ;/*2s，hello定时器时间*/br->bridge_hello_time = br->hello_time = 2 * HZ;/*15s转发时延，用于Block->Learning->Forwarding*/br->bridge_forward_delay = br->forward_delay = 15 * HZ;/*FDB中保存的MAC地址的老化时间，5分钟*/br->ageing_time = 300 * HZ;/*桥上netfilter初始化*/br_netfilter_rtable_init(br);br_stp_timer_init(br);/*组播初始化*/br_multicast_init(br);
}

(1). netdev_priv()函数

这个函数很简短，但是很重要，功能就一个。取出网桥设备私有数据起始地址，就是net_bridge结构地址。它也是32字节对齐的。

/*** netdev_priv - access network device private data*   @dev: network device** Get network device private data*/
static inline void *netdev_priv(const struct net_device *dev)
{return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN);
}

(2). 宏SET_NETDEV_DEVTYPE(dev, &br_type);

/* Set the sysfs device type for the network logical device to allow* fine-grained identification of different network device types. For* example Ethernet, Wirelss LAN, Bluetooth, WiMAX etc.*/
#define SET_NETDEV_DEVTYPE(net, devtype)    ((net)->dev.type = (devtype))

相当于dev->dev.type = &by_type

br_type结构体定义为：

static struct device_type br_type = {.name  = "bridge",
};

net_device数据结构中有个元素struct device dev; dev结构体定义为：当中有个type元素。

struct device
{struct device      *parent;struct device_private   *p;struct kobject kobj;const char       *init_name; /* initial name of the device */const struct device_type *type;...
}

(3). ether_setup()

以太网设备初始化，使用以太网通用参数初始化net_device中以太网相关参数。包括L2头长度为14，MAC地址长度为6，MTU为1518等。

/*** ether_setup - setup Ethernet network device* @dev: network device** Fill in the fields of the device structure with Ethernet-generic values.*/
void ether_setup(struct net_device *dev)
{/*L2层头操作函数，包括create,parse,cache等这个参数初始化的地方没找到，以后再研究。*/dev->header_ops     = &eth_header_ops;/*设置ARP协议硬件标识符，ARPHRD_ETHER表示标准以太网*/dev->type      = ARPHRD_ETHER;/*L2头长度为14*/dev->hard_header_len     = ETH_HLEN;/*数据长度最大为1500*/dev->mtu      = ETH_DATA_LEN;/*MAC地址长度为6*/dev->addr_len       = ETH_ALEN;/*发送队列长度为1000*/dev->tx_queue_len = 1000;    /* Ethernet wants good queues *//*?*/dev->flags      = IFF_BROADCAST|IFF_MULTICAST;/*Like 'flags' but invisible to userspace,see if.h for the definitions*/dev->priv_flags     |= IFF_TX_SKB_SHARING;/*分配广播地址，全1*/eth_broadcast_addr(dev->broadcast);}

关于dev->type = ARPHRD_ETHER;

设置arp协议硬件标识符， ARPHRD_ETHER表示标准以太网。

/* ARP protocol HARDWARE identifiers. */
#define ARPHRD_NETROM   0       /* from KA9Q: NET/ROM pseudo    */
#define ARPHRD_ETHER    1       /* Ethernet 10Mbps      */
#define ARPHRD_EETHER   2       /* Experimental Ethernet    */
#define ARPHRD_AX25 3       /* AX.25 Level 2        */
#define ARPHRD_PRONET   4       /* PROnet token ring        */
#define ARPHRD_CHAOS    5       /* Chaosnet         */
#define ARPHRD_IEEE802  6       /* IEEE 802.2 Ethernet/TR/TB    */
#define ARPHRD_ARCNET   7       /* ARCnet           */
#define ARPHRD_APPLETLK 8       /* APPLEtalk            */
#define ARPHRD_DLCI 15      /* Frame Relay DLCI     */
#define ARPHRD_ATM  19      /* ATM              */
#define ARPHRD_METRICOM 23      /* Metricom STRIP (new IANA id) */
#define ARPHRD_IEEE1394 24      /* IEEE 1394 IPv4 - RFC 2734    */
#define ARPHRD_EUI64    27      /* EUI-64                       */
#define ARPHRD_INFINIBAND 32        /* InfiniBand           */

(4). br_netdev_ops操作函数

static const struct net_device_ops br_netdev_ops = {/*打开网桥调用*/.ndo_open      = br_dev_open,.ndo_stop        = br_dev_stop,.ndo_init        = br_dev_init,/*网桥发包函数*/.ndo_start_xmit        = br_dev_xmit,.ndo_get_stats64     = br_get_stats64,/*设置网桥MAC地址*/.ndo_set_mac_address     = br_set_mac_address,.ndo_set_rx_mode  = br_dev_set_multicast_list,.ndo_change_rx_flags   = br_dev_change_rx_flags,/*改变网桥MTU时，新的MTU值必须小于等于被绑定的设备的最小的MTU*/.ndo_change_mtu      = br_change_mtu,/*网桥ioctl命令调用函数*/.ndo_do_ioctl         = br_dev_ioctl,
#ifdef CONFIG_NET_POLL_CONTROLLER.ndo_netpoll_setup  = br_netpoll_setup,.ndo_netpoll_cleanup    = br_netpoll_cleanup,.ndo_poll_controller  = br_poll_controller,
#endif/*网桥添加端口*/.ndo_add_slave       = br_add_slave,.ndo_del_slave      = br_del_slave,.ndo_fix_features        = br_fix_features,/*网桥添加fdb转发享*/.ndo_fdb_add      = br_fdb_add,.ndo_fdb_del      = br_fdb_delete,.ndo_fdb_dump      = br_fdb_dump,.ndo_bridge_getlink  = br_getlink,.ndo_bridge_setlink   = br_setlink,.ndo_bridge_dellink   = br_dellink,
};

看看定义是哪样的：


/** This structure defines the management hooks for network devices.* The following hooks can be defined; unless noted otherwise, they are* optional and can be filled with a null pointer.** int (*ndo_init)(struct net_device *dev);*     This function is called once when network device is registered.*     The network device can use this to any late stage initializaton*     or semantic validattion. It can fail with an error code which will*     be propogated back to register_netdev** void (*ndo_uninit)(struct net_device *dev);*     This function is called when device is unregistered or when registration*     fails. It is not called if init fails.** int (*ndo_open)(struct net_device *dev);*     This function is called when network device transistions to the up*     state.** int (*ndo_stop)(struct net_device *dev);*     This function is called when network device transistions to the down*     state.** netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,*                               struct net_device *dev);*   Called when a packet needs to be transmitted.*  Returns NETDEV_TX_OK.  Can return NETDEV_TX_BUSY, but you should stop*  the queue before that can happen; it's for obsolete devices and weird* corner cases, but the stack really does a non-trivial amount*   of useless work if you return NETDEV_TX_BUSY.*        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)*  Required can not be NULL.** u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,*                         void *accel_priv, select_queue_fallback_t fallback);* Called to decide which queue to when device supports multiple*  transmit queues.** void (*ndo_change_rx_flags)(struct net_device *dev, int flags);* This function is called to allow device receiver to make*   changes to configuration when multicast or promiscious is enabled.** void (*ndo_set_rx_mode)(struct net_device *dev);*  This function is called device changes address list filtering.* If driver handles unicast address filtering, it should set* IFF_UNICAST_FLT to its priv_flags.** int (*ndo_set_mac_address)(struct net_device *dev, void *addr);*   This function  is called when the Media Access Control address* needs to be changed. If this interface is not defined, the* mac address can not be changed.** int (*ndo_validate_addr)(struct net_device *dev);*    Test if Media Access Control address is valid for the device.** int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd);*   Called when a user request an ioctl which can't be handled by* the generic interface code. If not defined ioctl's return* not supported error code.** int (*ndo_set_config)(struct net_device *dev, struct ifmap *map);*  Used to set network devices bus interface parameters. This interface*   is retained for legacy reason, new devices should use the bus*  interface (PCI) for low level management.** int (*ndo_change_mtu)(struct net_device *dev, int new_mtu);*    Called when a user wants to change the Maximum Transfer Unit*   of a device. If not defined, any request to change MTU will*    will return an error.** void (*ndo_tx_timeout)(struct net_device *dev);*    Callback uses when the transmitter has not made any progress*   for dev->watchdog ticks.** struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev,*                      struct rtnl_link_stats64 *storage);* struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);*   Called when a user wants to get the network device usage*   statistics. Drivers must do one of the following:*  1. Define @ndo_get_stats64 to fill in a zero-initialised*     rtnl_link_stats64 structure passed by the caller.*   2. Define @ndo_get_stats to update a net_device_stats structure*      (which should normally be dev->stats) and return a pointer to*       it. The structure may be changed asynchronously only if each*       field is written atomically.*    3. Update dev->stats asynchronously and atomically, and define*     neither operation.** int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid);* If device support VLAN filtering this function is called when a*    VLAN id is registered.** int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid);*   If device support VLAN filtering this function is called when a*    VLAN id is unregistered.** void (*ndo_poll_controller)(struct net_device *dev);**   SR-IOV management functions.* int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac);* int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos);* int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate,*            int max_tx_rate);* int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting);* int (*ndo_get_vf_config)(struct net_device *dev,*               int vf, struct ifla_vf_info *ivf);* int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state);* int (*ndo_set_vf_port)(struct net_device *dev, int vf,*            struct nlattr *port[]);**      Enable or disable the VF ability to query its RSS Redirection Table and*      Hash Key. This is needed since on some devices VF share this information*      with PF and querying it may adduce a theoretical security risk.* int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting);* int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb);* int (*ndo_setup_tc)(struct net_device *dev, u8 tc)*     Called to setup 'tc' number of traffic classes in the net device. This*   is always called from the stack with the rtnl lock held and netif tx*   queues stopped. This allows the netdevice to perform queue management*  safely.**   Fiber Channel over Ethernet (FCoE) offload functions.* int (*ndo_fcoe_enable)(struct net_device *dev);* Called when the FCoE protocol stack wants to start using LLD for FCoE*  so the underlying device can perform whatever needed configuration or*  initialization to support acceleration of FCoE traffic.** int (*ndo_fcoe_disable)(struct net_device *dev);* Called when the FCoE protocol stack wants to stop using LLD for FCoE*   so the underlying device can perform whatever needed clean-ups to*  stop supporting acceleration of FCoE traffic.** int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid,*              struct scatterlist *sgl, unsigned int sgc);*   Called when the FCoE Initiator wants to initialize an I/O that* is a possible candidate for Direct Data Placement (DDP). The LLD can*   perform necessary setup and returns 1 to indicate the device is set up* successfully to perform DDP on this I/O, otherwise this returns 0.** int (*ndo_fcoe_ddp_done)(struct net_device *dev,  u16 xid);*   Called when the FCoE Initiator/Target is done with the DDPed I/O as*    indicated by the FC exchange id 'xid', so the underlying device can*  clean up and reuse resources for later DDP requests.** int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid,*               struct scatterlist *sgl, unsigned int sgc);*  Called when the FCoE Target wants to initialize an I/O that*    is a possible candidate for Direct Data Placement (DDP). The LLD can*   perform necessary setup and returns 1 to indicate the device is set up* successfully to perform DDP on this I/O, otherwise this returns 0.** int (*ndo_fcoe_get_hbainfo)(struct net_device *dev,*                  struct netdev_fcoe_hbainfo *hbainfo);*   Called when the FCoE Protocol stack wants information on the underlying*    device. This information is utilized by the FCoE protocol stack to* register attributes with Fiber Channel management service as per the*   FC-GS Fabric Device Management Information(FDMI) specification.** int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type);* Called when the underlying device wants to override default World Wide* Name (WWN) generation mechanism in FCoE protocol stack to pass its own* World Wide Port Name (WWPN) or World Wide Node Name (WWNN) to the FCoE* protocol stack to use.**    RFS acceleration.* int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb,*             u16 rxq_index, u32 flow_id);*   Set hardware filter for RFS.  rxq_index is the target queue index;* flow_id is a flow ID to be passed to rps_may_expire_flow() later.*  Return the filter ID on success, or a negative error code.**    Slave management functions (for bridge, bonding, etc).* int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev);*    Called to make another netdev an underling.** int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);*  Called to release previously enslaved netdev.**      Feature/offload setting functions.* netdev_features_t (*ndo_fix_features)(struct net_device *dev,*     netdev_features_t features);*   Adjusts the requested feature flags according to device-specific*   constraints, and returns the resulting flags. Must not modify*  the device state.** int (*ndo_set_features)(struct net_device *dev, netdev_features_t features);*   Called to update device configuration to new features. Passed*  feature set might be less than what was returned by ndo_fix_features()).*   Must return >0 or -errno if it changed dev->features itself.** int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[],*              struct net_device *dev,*            const unsigned char *addr, u16 vid, u16 flags)*   Adds an FDB entry to dev for addr.* int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[],*           struct net_device *dev,*            const unsigned char *addr, u16 vid)*  Deletes the FDB entry from dev coresponding to addr.* int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,*               struct net_device *dev, struct net_device *filter_dev,*             int idx)*    Used to add FDB entries to dump requests. Implementers should add*  entries to skb and update idx with the number of entries.** int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh,*                 u16 flags)* int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq,*               struct net_device *dev, u32 filter_mask,*               int nlflags)* int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh,*              u16 flags);** int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier);*    Called to change device carrier. Soft-devices (like dummy, team, etc)*  which do not represent real hardware may define this to allow their*    userspace components to manage their virtual carrier state. Devices*    that determine carrier state from physical hardware properties (eg* network cables) or protocol-dependent mechanisms (eg*   USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function.** int (*ndo_get_phys_port_id)(struct net_device *dev,*                  struct netdev_phys_item_id *ppid);*  Called to get ID of physical port of this device. If driver does*   not implement this, it is assumed that the hw is not able to have*  multiple net devices on single physical port.** void (*ndo_add_vxlan_port)(struct  net_device *dev,*                  sa_family_t sa_family, __be16 port);* Called by vxlan to notiy a driver about the UDP port and socket*    address family that vxlan is listnening to. It is called only when* a new port starts listening. The operation is protected by the* vxlan_net->sock_lock.** void (*ndo_del_vxlan_port)(struct  net_device *dev,*               sa_family_t sa_family, __be16 port);* Called by vxlan to notify the driver about a UDP port and socket*   address family that vxlan is not listening to anymore. The operation*   is protected by the vxlan_net->sock_lock.** void* (*ndo_dfwd_add_station)(struct net_device *pdev,*               struct net_device *dev)*   Called by upper layer devices to accelerate switching or other* station functionality into hardware. 'pdev is the lowerdev*    to use for the offload and 'dev' is the net device that will* back the offload. Returns a pointer to the private structure*   the upper layer will maintain.* void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv)*  Called by upper layer device to delete the station created* by 'ndo_dfwd_add_station'. 'pdev' is the net device backing*    the station and priv is the structure returned by the add*  operation.* netdev_tx_t (*ndo_dfwd_start_xmit)(struct sk_buff *skb,*                      struct net_device *dev,*                    void *priv);* Callback to use for xmit over the accelerated station. This*    is used in place of ndo_start_xmit on accelerated net*  devices.* netdev_features_t (*ndo_features_check) (struct sk_buff *skb,*                        struct net_device *dev*                     netdev_features_t features);*   Called by core transmit path to determine if device is capable of*  performing offload operations on a given packet. This is to give*   the device an opportunity to implement any restrictions that cannot*    be otherwise expressed by feature flags. The check is called with*  the set of features that the stack has calculated and it returns*   those the driver believes to be appropriate.* int (*ndo_set_tx_maxrate)(struct net_device *dev,*                 int queue_index, u32 maxrate);*    Called when a user wants to set a max-rate limitation of specific*  TX queue.* int (*ndo_get_iflink)(const struct net_device *dev);*    Called to get the iflink value of this device.*/
struct net_device_ops {int          (*ndo_init)(struct net_device *dev);void            (*ndo_uninit)(struct net_device *dev);int           (*ndo_open)(struct net_device *dev);int         (*ndo_stop)(struct net_device *dev);netdev_tx_t     (*ndo_start_xmit) (struct sk_buff *skb,struct net_device *dev);u16          (*ndo_select_queue)(struct net_device *dev,struct sk_buff *skb,void *accel_priv,select_queue_fallback_t fallback);void          (*ndo_change_rx_flags)(struct net_device *dev,int flags);void           (*ndo_set_rx_mode)(struct net_device *dev);int          (*ndo_set_mac_address)(struct net_device *dev,void *addr);int           (*ndo_validate_addr)(struct net_device *dev);int            (*ndo_do_ioctl)(struct net_device *dev,struct ifreq *ifr, int cmd);int          (*ndo_set_config)(struct net_device *dev,struct ifmap *map);int         (*ndo_change_mtu)(struct net_device *dev,int new_mtu);int           (*ndo_neigh_setup)(struct net_device *dev,struct neigh_parms *);void            (*ndo_tx_timeout) (struct net_device *dev);struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev,struct rtnl_link_stats64 *storage);struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);int         (*ndo_vlan_rx_add_vid)(struct net_device *dev,__be16 proto, u16 vid);int            (*ndo_vlan_rx_kill_vid)(struct net_device *dev,__be16 proto, u16 vid);
#ifdef CONFIG_NET_POLL_CONTROLLERvoid                    (*ndo_poll_controller)(struct net_device *dev);int         (*ndo_netpoll_setup)(struct net_device *dev,struct netpoll_info *info);void         (*ndo_netpoll_cleanup)(struct net_device *dev);
#endif
#ifdef CONFIG_NET_RX_BUSY_POLLint           (*ndo_busy_poll)(struct napi_struct *dev);
#endifint           (*ndo_set_vf_mac)(struct net_device *dev,int queue, u8 *mac);int            (*ndo_set_vf_vlan)(struct net_device *dev,int queue, u16 vlan, u8 qos);int          (*ndo_set_vf_rate)(struct net_device *dev,int vf, int min_tx_rate,int max_tx_rate);int          (*ndo_set_vf_spoofchk)(struct net_device *dev,int vf, bool setting);int         (*ndo_get_vf_config)(struct net_device *dev,int vf,struct ifla_vf_info *ivf);int            (*ndo_set_vf_link_state)(struct net_device *dev,int vf, int link_state);int         (*ndo_set_vf_port)(struct net_device *dev,int vf,struct nlattr *port[]);int         (*ndo_get_vf_port)(struct net_device *dev,int vf, struct sk_buff *skb);int          (*ndo_set_vf_rss_query_en)(struct net_device *dev,int vf, bool setting);int         (*ndo_setup_tc)(struct net_device *dev, u8 tc);
#if IS_ENABLED(CONFIG_FCOE)int          (*ndo_fcoe_enable)(struct net_device *dev);int          (*ndo_fcoe_disable)(struct net_device *dev);int         (*ndo_fcoe_ddp_setup)(struct net_device *dev,u16 xid,struct scatterlist *sgl,unsigned int sgc);int          (*ndo_fcoe_ddp_done)(struct net_device *dev,u16 xid);int            (*ndo_fcoe_ddp_target)(struct net_device *dev,u16 xid,struct scatterlist *sgl,unsigned int sgc);int         (*ndo_fcoe_get_hbainfo)(struct net_device *dev,struct netdev_fcoe_hbainfo *hbainfo);
#endif#if IS_ENABLED(CONFIG_LIBFCOE)
#define NETDEV_FCOE_WWNN 0
#define NETDEV_FCOE_WWPN 1int           (*ndo_fcoe_get_wwn)(struct net_device *dev,u64 *wwn, int type);
#endif#ifdef CONFIG_RFS_ACCELint            (*ndo_rx_flow_steer)(struct net_device *dev,const struct sk_buff *skb,u16 rxq_index,u32 flow_id);
#endifint           (*ndo_add_slave)(struct net_device *dev,struct net_device *slave_dev);int           (*ndo_del_slave)(struct net_device *dev,struct net_device *slave_dev);netdev_features_t (*ndo_fix_features)(struct net_device *dev,netdev_features_t features);int          (*ndo_set_features)(struct net_device *dev,netdev_features_t features);int          (*ndo_neigh_construct)(struct neighbour *n);void            (*ndo_neigh_destroy)(struct neighbour *n);int           (*ndo_fdb_add)(struct ndmsg *ndm,struct nlattr *tb[],struct net_device *dev,const unsigned char *addr,u16 vid,u16 flags);int            (*ndo_fdb_del)(struct ndmsg *ndm,struct nlattr *tb[],struct net_device *dev,const unsigned char *addr,u16 vid);int          (*ndo_fdb_dump)(struct sk_buff *skb,struct netlink_callback *cb,struct net_device *dev,struct net_device *filter_dev,int idx);int           (*ndo_bridge_setlink)(struct net_device *dev,struct nlmsghdr *nlh,u16 flags);int            (*ndo_bridge_getlink)(struct sk_buff *skb,u32 pid, u32 seq,struct net_device *dev,u32 filter_mask,int nlflags);int          (*ndo_bridge_dellink)(struct net_device *dev,struct nlmsghdr *nlh,u16 flags);int            (*ndo_change_carrier)(struct net_device *dev,bool new_carrier);int          (*ndo_get_phys_port_id)(struct net_device *dev,struct netdev_phys_item_id *ppid);int            (*ndo_get_phys_port_name)(struct net_device *dev,char *name, size_t len);void           (*ndo_add_vxlan_port)(struct  net_device *dev,sa_family_t sa_family,__be16 port);void           (*ndo_del_vxlan_port)(struct  net_device *dev,sa_family_t sa_family,__be16 port);void*          (*ndo_dfwd_add_station)(struct net_device *pdev,struct net_device *dev);void            (*ndo_dfwd_del_station)(struct net_device *pdev,void *priv);netdev_tx_t     (*ndo_dfwd_start_xmit) (struct sk_buff *skb,struct net_device *dev,void *priv);int          (*ndo_get_lock_subclass)(struct net_device *dev);netdev_features_t  (*ndo_features_check) (struct sk_buff *skb,struct net_device *dev,netdev_features_t features);int           (*ndo_set_tx_maxrate)(struct net_device *dev,int queue_index,u32 maxrate);int           (*ndo_get_iflink)(const struct net_device *dev);
};

(5). br_ethtool_ops操作函数

static const struct ethtool_ops br_ethtool_ops = {.get_drvinfo    = br_getinfo,.get_link   = ethtool_op_get_link,
};

ethtool_ops结构体定义，...以后需要再单独分析。

4. 删除网桥br_del_bridge()函数

先根据name找到网桥设备，调用br_dev_delete()函数删除网桥。

//删除网桥
int br_del_bridge(struct net *net, const char *name)
{struct net_device *dev;int ret = 0;rtnl_lock();/*网络空间net中查找名称为name的设备*/dev = __dev_get_by_name(net, name);/*未找到*/if (dev == NULL)ret =  -ENXIO;   /* Could not find device *//*dev->priv_flags参数在br_dev_setup()函数中初始化为IEF_EBRIDGE，判断找到的设备是否为桥。*/else if (!(dev->priv_flags & IFF_EBRIDGE)) {/* Attempt to delete non bridge device! */ret = -EPERM;}/*删除网桥的时候要关闭网桥*/else if (dev->flags & IFF_UP) {/* Not shutdown yet. */ret = -EBUSY;}/*调用br_dev_delete()删除网桥*/elsebr_dev_delete(dev, NULL);rtnl_unlock();return ret;
}

(1). 关于priv_flags：表示设备类型

/*** enum net_device_priv_flags - &struct net_device priv_flags** These are the &struct net_device, they are only set internally* by drivers and used in the kernel. These flags are invisible to* userspace, this means that the order of these flags can change* during any kernel release.** You should have a pretty good reason to be extending these flags.** @IFF_802_1Q_VLAN: 802.1Q VLAN device* @IFF_EBRIDGE: Ethernet bridging device* @IFF_SLAVE_INACTIVE: bonding slave not the curr. active* @IFF_MASTER_8023AD: bonding master, 802.3ad* @IFF_MASTER_ALB: bonding master, balance-alb* @IFF_BONDING: bonding master or slave* @IFF_SLAVE_NEEDARP: need ARPs for validation* @IFF_ISATAP: ISATAP interface (RFC4214)* @IFF_MASTER_ARPMON: bonding master, ARP mon in use* @IFF_WAN_HDLC: WAN HDLC device* @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to*   release skb->dst* @IFF_DONT_BRIDGE: disallow bridging this ether dev* @IFF_DISABLE_NETPOLL: disable netpoll at run-time* @IFF_MACVLAN_PORT: device used as macvlan port* @IFF_BRIDGE_PORT: device used as bridge port* @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port* @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit* @IFF_UNICAST_FLT: Supports unicast filtering* @IFF_TEAM_PORT: device used as team port* @IFF_SUPP_NOFCS: device supports sending custom FCS* @IFF_LIVE_ADDR_CHANGE: device supports hardware address*   change when it's running* @IFF_MACVLAN: Macvlan device*/
enum netdev_priv_flags {IFF_802_1Q_VLAN         = 1<<0,IFF_EBRIDGE           = 1<<1,IFF_SLAVE_INACTIVE        = 1<<2,IFF_MASTER_8023AD     = 1<<3,IFF_MASTER_ALB            = 1<<4,IFF_BONDING           = 1<<5,IFF_SLAVE_NEEDARP     = 1<<6,IFF_ISATAP            = 1<<7,IFF_MASTER_ARPMON     = 1<<8,IFF_WAN_HDLC          = 1<<9,IFF_XMIT_DST_RELEASE      = 1<<10,IFF_DONT_BRIDGE          = 1<<11,IFF_DISABLE_NETPOLL      = 1<<12,IFF_MACVLAN_PORT     = 1<<13,IFF_BRIDGE_PORT          = 1<<14,IFF_OVS_DATAPATH     = 1<<15,IFF_TX_SKB_SHARING       = 1<<16,IFF_UNICAST_FLT          = 1<<17,IFF_TEAM_PORT            = 1<<18,IFF_SUPP_NOFCS           = 1<<19,IFF_LIVE_ADDR_CHANGE     = 1<<20,IFF_MACVLAN          = 1<<21,IFF_XMIT_DST_RELEASE_PERM    = 1<<22,IFF_IPVLAN_MASTER        = 1<<23,IFF_IPVLAN_SLAVE     = 1<<24,
};

(2). br_fdb_delete_by_port()函数

删除网桥br上目的端口为p的所有fdb项

/* Flush all entries referring to a specific port.* if do_all is set also flush static entries*/
void br_fdb_delete_by_port(struct net_bridge *br,const struct net_bridge_port *p,int do_all)
{int i;spin_lock_bh(&br->hash_lock);/*遍历hash数组*/for (i = 0; i < BR_HASH_SIZE; i++) {struct hlist_node *h, *g;/*遍历链表*/hlist_for_each_safe(h, g, &br->hash[i]) {struct net_bridge_fdb_entry *f= hlist_entry(h, struct net_bridge_fdb_entry, hlist);/*目的端口不为p，进行下一次循环*/if (f->dst != p)continue;/*设置do_all为1时，目的地址为静态MAC地址的项也删除。*/if (f->is_static && !do_all)continue;/*目的MAC地址为本地MAC*/if (f->is_local)fdb_delete_local(br, p, f);elsefdb_delete(br, f);}}spin_unlock_bh(&br->hash_lock);
}

(3). br_dev_delete()函数

删除网桥所有端口，删除网桥所有fdb项等。

/* Delete bridge device */
void br_dev_delete(struct net_device *dev, struct list_head *head)
{struct net_bridge *br = netdev_priv(dev);struct net_bridge_port *p, *n;/*遍历删除网桥所有端口*/list_for_each_entry_safe(p, n, &br->port_list, list) {del_nbp(p);}/*删除目的地址为指定端口的fdb项，这里端口为NULL，表示删除网桥br的所有fdb项*/br_fdb_delete_by_port(br, NULL, 1);br_vlan_flush(br);del_timer_sync(&br->gc_timer);br_sysfs_delbr(br->dev);/*从内核中删除设备*/unregister_netdevice_queue(br->dev, head);
}

这个函数中有很多函数还没有分析，以后再分析，实在是太多了，分析不过来了。

5. br_add_if()

给网桥添加端口

对待添加的设备进行正确性判断，然后创建网桥端口，进行相关参数初始化，rx_handle设置为br_handle_frame()、插入fdb等。

/* called with RTNL */
int br_add_if(struct net_bridge *br, struct net_device *dev)
{struct net_bridge_port *p;int err = 0;bool changed_addr;/* Don't allow bridging non-ethernet like devices, or DSA-enabled* master network devices since the bridge layer rx_handler prevents* the DSA fake ethertype handler to be invoked, so we do not strip off* the DSA switch tag protocol header and the bridge layer just return* RX_HANDLER_CONSUMED, stopping RX processing for these frames.*//*非以太网设备不能绑定到桥。环回地址、地址长度不为6、非法以太网地址、使用了dsa的设备都不能添加到桥*/if ((dev->flags & IFF_LOOPBACK) ||dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN ||!is_valid_ether_addr(dev->dev_addr) ||netdev_uses_dsa(dev))return -EINVAL;/* No bridging of bridges *//*网桥不能添加到网桥*/if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit)return -ELOOP;/* Device is already being bridged *//*设备已经被添加到一个网桥中，一个设备只能添加到一个网桥*/if (br_port_exists(dev))return -EBUSY;/* No bridging devices that dislike that (e.g. wireless) *//*设置了IEF_DONT_BRIDGE不添加到网桥的设备，例如无线设备。*/if (dev->priv_flags & IFF_DONT_BRIDGE)return -EOPNOTSUPP;/*net_bridge_port创建网桥端口，进行相关初始化*/p = new_nbp(br, dev);if (IS_ERR(p))return PTR_ERR(p);call_netdevice_notifiers(NETDEV_JOIN, dev);err = dev_set_allmulti(dev, 1);if (err)goto put_back;err = kobject_init_and_add(&p->kobj, &brport_ktype, &(dev->dev.kobj),SYSFS_BRIDGE_PORT_ATTR);if (err)goto err1;err = br_sysfs_addif(p);if (err)goto err2;err = br_netpoll_enable(p);if (err)goto err3;/*这一步很重要，注册桥上设备的rx_handler为br_handle_frame函数，在netif_receive_skb()函数中会使用*/err = netdev_rx_handler_register(dev, br_handle_frame, p);if (err)goto err4;/*设备的priv_flag参数添加网桥端口属性IFF_BRIDGE_PORT*/dev->priv_flags |= IFF_BRIDGE_PORT;err = netdev_master_upper_dev_link(dev, br->dev);if (err)goto err5;/*关闭LRO，large receive offload*/dev_disable_lro(dev);/*网桥端口添加到网桥的port_list列表*/list_add_rcu(&p->list, &br->port_list);nbp_update_port_count(br);//从新设置br->dev->feature字段netdev_update_features(br->dev);if (br->dev->needed_headroom < dev->needed_headroom)br->dev->needed_headroom = dev->needed_headroom;/*插入本地设备MAC-端口转发fdb项,通过函数br_fdb_insert插入的fdb表项的is_local和is_static都是1*/if (br_fdb_insert(br, p, dev->dev_addr, 0))netdev_err(dev, "failed insert local address bridge forwarding table\n");/*初始化网桥端口的VLAN配置，如果Bridge设备有“Default PVID"，就将默认PVID设置为端口的PVID并且Untag。*/if (nbp_vlan_init(p))netdev_err(dev, "failed to initialize vlan filtering on this port\n");spin_lock_bh(&br->lock);/*重新给网桥分配MAC地址以及网桥ID，因为刚开始建立网桥时MAC地址是随机分配的，当给网桥添加端口后，可以把添加进来的设备的MAC地址作为网桥的MAC地址。*/changed_addr = br_stp_recalculate_bridge_id(br);//如果网桥端口设备是UP的，就使能它，设置状态等（如果STP没打开就没有这些步骤了）。if (netif_running(dev) && netif_oper_up(dev) &&(br->dev->flags & IFF_UP))br_stp_enable_port(p);spin_unlock_bh(&br->lock);br_ifinfo_notify(RTM_NEWLINK, p);/*改变了MAC地址，通知别人*/if (changed_addr)call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);/*设置网桥的MTU为所有端口的MTU的最小值*/dev_set_mtu(br->dev, br_min_mtu(br));kobject_uevent(&p->kobj, KOBJ_ADD);return 0;err5:dev->priv_flags &= ~IFF_BRIDGE_PORT;netdev_rx_handler_unregister(dev);
err4:br_netpoll_disable(p);
err3:sysfs_remove_link(br->ifobj, p->dev->name);
err2:kobject_put(&p->kobj);p = NULL; /* kobject_put frees */
err1:dev_set_allmulti(dev, -1);
put_back:dev_put(dev);kfree(p);return err;
}

(1). net_nbp()函数

创建网桥端口函数，net_bridge_port结构初始化。

/* called with RTNL but without bridge lock */
static struct net_bridge_port *new_nbp(struct net_bridge *br,struct net_device *dev)
{int index;struct net_bridge_port *p;index = find_portno(br);if (index < 0)return ERR_PTR(index);p = kzalloc(sizeof(*p), GFP_KERNEL);if (p == NULL)return ERR_PTR(-ENOMEM);p->br = br;dev_hold(dev);p->dev = dev;p->path_cost = port_cost(dev);p->priority = 0x8000 >> BR_PORT_BITS;p->port_no = index;p->flags = BR_LEARNING | BR_FLOOD;br_init_port(p);br_set_state(p, BR_STATE_DISABLED);br_stp_port_timer_init(p);br_multicast_add_port(p);return p;
}

(2). netdev_rx_handler_register()

注册设备的rx_handler。

/*** netdev_rx_handler_register - register receive handler*  @dev: device to register a handler for*    @rx_handler: receive handler to register*  @rx_handler_data: data pointer that is used by rx handler**    Register a receive handler for a device. This handler will then be* called from __netif_receive_skb. A negative errno code is returned* on a failure.** The caller must hold the rtnl_mutex.**  For a general description of rx_handler, see enum rx_handler_result.*/
int netdev_rx_handler_register(struct net_device *dev,rx_handler_func_t *rx_handler,void *rx_handler_data)
{ASSERT_RTNL();if (dev->rx_handler)return -EBUSY;/* Note: rx_handler_data must be set before rx_handler *//*rx_handler_data指向网桥端口，rx_handler指向br_handle_frame*/rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);rcu_assign_pointer(dev->rx_handler, rx_handler);return 0;
}

(3). 关于br_stp_recalculate_bridge_id(br)