Linux Bridge源码分析

// /Users/kangxiaoning/workspace/linux-3.10/net/bridge/br_if.c int br_add_bridge(struct net *net, const char *name) { struct net_device *dev; int res; // 为Bridge设备分配内存，使用`br_dev_setup()`初始化该设备 dev = alloc_netdev(sizeof(struct net_bridge), name, br_dev_setup); if (!dev) return -ENOMEM; // 设置Bridge的network namespace dev_net_set(dev, net); // br_link_ops定义了该device上可以执行的操作 dev->rtnl_link_ops = &br_link_ops; res = register_netdev(dev); if (res) free_netdev(dev); return res; }

// /Users/kangxiaoning/workspace/linux-3.10/net/core/dev.c /** * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for * @name: device name format string * @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 subquue structs * for each queue on the device. */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs) { struct net_device *dev; size_t alloc_size; struct net_device *p; BUG_ON(strlen(name) >= sizeof(dev->name)); if (txqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero queues\n"); return NULL; } #ifdef CONFIG_RPS if (rxqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; } #endif alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ alloc_size = ALIGN(alloc_size, NETDEV_ALIGN); alloc_size += sizeof_priv; } /* ensure 32-byte alignment of whole construct */ alloc_size += NETDEV_ALIGN - 1; p = kzalloc(alloc_size, GFP_KERNEL); if (!p) return NULL; dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) goto free_p; 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; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->link_watch_list); INIT_LIST_HEAD(&dev->upper_dev_list); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; if (netif_alloc_netdev_queues(dev)) goto free_all; #ifdef CONFIG_RPS dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) goto free_all; #endif strcpy(dev->name, name); 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); kfree(dev->_tx); #ifdef CONFIG_RPS kfree(dev->_rx); #endif free_p: kfree(p); return NULL; }

static const struct net_device_ops br_netdev_ops = { .ndo_open = br_dev_open, .ndo_stop = br_dev_stop, .ndo_init = br_dev_init, .ndo_start_xmit = br_dev_xmit, .ndo_get_stats64 = br_get_stats64, .ndo_set_mac_address = br_set_mac_address, .ndo_set_rx_mode = br_dev_set_multicast_list, .ndo_change_mtu = br_change_mtu, .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 .ndo_add_slave = br_add_slave, .ndo_del_slave = br_del_slave, .ndo_fix_features = br_fix_features, .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, };

// /Users/kangxiaoning/workspace/linux-3.10/net/bridge/br_private.h struct net_bridge { spinlock_t lock; struct list_head port_list; struct net_device *dev; struct br_cpu_netstats __percpu *stats; spinlock_t hash_lock; struct hlist_head hash[BR_HASH_SIZE]; #ifdef CONFIG_BRIDGE_NETFILTER struct rtable fake_rtable; bool nf_call_iptables; bool nf_call_ip6tables; bool nf_call_arptables; #endif u16 group_fwd_mask; /* STP */ bridge_id designated_root; bridge_id bridge_id; u32 root_path_cost; unsigned long max_age; unsigned long hello_time; unsigned long forward_delay; unsigned long bridge_max_age; unsigned long ageing_time; unsigned long bridge_hello_time; unsigned long bridge_forward_delay; u8 group_addr[ETH_ALEN]; u16 root_port; enum { BR_NO_STP, /* no spanning tree */ BR_KERNEL_STP, /* old STP in kernel */ BR_USER_STP, /* new RSTP in userspace */ } stp_enabled; unsigned char topology_change; unsigned char topology_change_detected; #ifdef CONFIG_BRIDGE_IGMP_SNOOPING unsigned char multicast_router; u8 multicast_disabled:1; u8 multicast_querier:1; u32 hash_elasticity; u32 hash_max; u32 multicast_last_member_count; u32 multicast_startup_queries_sent; u32 multicast_startup_query_count; 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; struct net_bridge_mdb_htable __rcu *mdb; struct hlist_head router_list; struct timer_list multicast_router_timer; struct timer_list multicast_querier_timer; struct timer_list multicast_query_timer; #endif struct timer_list hello_timer; struct timer_list tcn_timer; struct timer_list topology_change_timer; struct timer_list gc_timer; struct kobject *ifobj; #ifdef CONFIG_BRIDGE_VLAN_FILTERING u8 vlan_enabled; struct net_port_vlans __rcu *vlan_info; #endif };

// /Users/kangxiaoning/workspace/linux-3.10/net/bridge/br_if.c 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 */ if ((dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) return -EINVAL; /* No bridging of bridges */ if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) return -ELOOP; /* Device is already being bridged */ if (br_port_exists(dev)) return -EBUSY; /* No bridging devices that dislike that (e.g. wireless) */ if (dev->priv_flags & IFF_DONT_BRIDGE) return -EOPNOTSUPP; p = new_nbp(br, dev); if (IS_ERR(p)) return PTR_ERR(p); call_netdevice_notifiers(NETDEV_JOIN, dev); err = dev_set_promiscuity(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; if (br_netpoll_info(br) && ((err = br_netpoll_enable(p, GFP_KERNEL)))) goto err3; err = netdev_master_upper_dev_link(dev, br->dev); if (err) goto err4; err = netdev_rx_handler_register(dev, br_handle_frame, p); if (err) goto err5; dev->priv_flags |= IFF_BRIDGE_PORT; dev_disable_lro(dev); list_add_rcu(&p->list, &br->port_list); netdev_update_features(br->dev); spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); 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); if (changed_addr) call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); dev_set_mtu(br->dev, br_min_mtu(br)); if (br_fdb_insert(br, p, dev->dev_addr, 0)) netdev_err(dev, "failed insert local address bridge forwarding table\n"); kobject_uevent(&p->kobj, KOBJ_ADD); return 0; err5: netdev_upper_dev_unlink(dev, br->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_promiscuity(dev, -1); put_back: dev_put(dev); kfree(p); return err; }

// /Users/kangxiaoning/workspace/linux-3.10/include/linux/netdevice.h 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 * of the interface. */ char name[IFNAMSIZ]; /* device name hash chain, please keep it close to name[] */ struct hlist_node name_hlist; /* snmp alias */ char *ifalias; /* * I/O specific fields * FIXME: Merge these and struct ifmap into one */ unsigned long mem_end; /* shared mem end */ unsigned long mem_start; /* shared mem start */ unsigned long base_addr; /* device I/O address */ 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. */ unsigned long state; struct list_head dev_list; struct list_head napi_list; struct list_head unreg_list; struct list_head upper_dev_list; /* List of upper devices */ /* currently active device features */ netdev_features_t features; /* user-changeable features */ netdev_features_t hw_features; /* user-requested features */ netdev_features_t wanted_features; /* mask of features inheritable by VLAN devices */ netdev_features_t vlan_features; /* mask of features inherited by encapsulating devices * This field indicates what encapsulation offloads * the hardware is capable of doing, and drivers will * need to set them appropriately. */ netdev_features_t hw_enc_features; /* Interface index. Unique device identifier */ int ifindex; int iflink; struct net_device_stats stats; atomic_long_t rx_dropped; /* dropped packets by core network * Do not use this in drivers. */ #ifdef CONFIG_WIRELESS_EXT /* List of functions to handle Wireless Extensions (instead of ioctl). * See <net/iw_handler.h> for details. Jean II */ const struct iw_handler_def * wireless_handlers; /* Instance data managed by the core of Wireless Extensions. */ struct iw_public_data * wireless_data; #endif /* Management operations */ const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; /* Hardware header description */ const struct header_ops *header_ops; unsigned int flags; /* interface flags (a la BSD) */ unsigned int priv_flags; /* Like 'flags' but invisible to userspace. * See if.h for definitions. */ unsigned short gflags; unsigned short padded; /* How much padding added by alloc_netdev() */ unsigned char operstate; /* RFC2863 operstate */ unsigned char link_mode; /* mapping policy to operstate */ unsigned char if_port; /* Selectable AUI, TP,..*/ unsigned char dma; /* DMA channel */ unsigned int mtu; /* interface MTU value */ unsigned short type; /* interface hardware type */ unsigned short hard_header_len; /* hardware hdr length */ /* extra head- and tailroom the hardware may need, but not in all cases * can this be guaranteed, especially tailroom. Some cases also use * LL_MAX_HEADER instead to allocate the skb. */ unsigned short needed_headroom; unsigned short needed_tailroom; /* Interface address info. */ unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ unsigned char addr_assign_type; /* hw address assignment type */ unsigned char addr_len; /* hardware address length */ unsigned char neigh_priv_len; unsigned short dev_id; /* for shared network cards */ spinlock_t addr_list_lock; struct netdev_hw_addr_list uc; /* Unicast mac addresses */ struct netdev_hw_addr_list mc; /* Multicast mac addresses */ struct netdev_hw_addr_list dev_addrs; /* list of device * hw addresses */ #ifdef CONFIG_SYSFS struct kset *queues_kset; #endif bool uc_promisc; unsigned int promiscuity; unsigned int allmulti; /* Protocol specific pointers */ #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; /* VLAN info */ #endif #if IS_ENABLED(CONFIG_NET_DSA) struct dsa_switch_tree *dsa_ptr; /* dsa specific data */ #endif void *atalk_ptr; /* AppleTalk link */ struct in_device __rcu *ip_ptr; /* IPv4 specific data */ struct dn_dev __rcu *dn_ptr; /* DECnet specific data */ struct inet6_dev __rcu *ip6_ptr; /* IPv6 specific data */ void *ax25_ptr; /* AX.25 specific data */ struct wireless_dev *ieee80211_ptr; /* IEEE 802.11 specific data, assign before registering */ /* * Cache lines mostly used on receive path (including eth_type_trans()) */ unsigned long last_rx; /* Time of last Rx * This should not be set in * drivers, unless really needed, * because network stack (bonding) * use it if/when necessary, to * avoid dirtying this cache line. */ /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; /* hw address, (before bcast because most packets are unicast) */ #ifdef CONFIG_RPS struct netdev_rx_queue *_rx; /* Number of RX queues allocated at register_netdev() time */ unsigned int num_rx_queues; /* Number of RX queues currently active in device */ unsigned int real_num_rx_queues; #endif rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; struct netdev_queue __rcu *ingress_queue; unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ /* * Cache lines mostly used on transmit path */ struct netdev_queue *_tx ____cacheline_aligned_in_smp; /* Number of TX queues allocated at alloc_netdev_mq() time */ unsigned int num_tx_queues; /* Number of TX queues currently active in device */ unsigned int real_num_tx_queues; /* root qdisc from userspace point of view */ struct Qdisc *qdisc; unsigned long tx_queue_len; /* Max frames per queue allowed */ spinlock_t tx_global_lock; #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_maps; #endif #ifdef CONFIG_RFS_ACCEL /* CPU reverse-mapping for RX completion interrupts, indexed * by RX queue number. Assigned by driver. This must only be * set if the ndo_rx_flow_steer operation is defined. */ struct cpu_rmap *rx_cpu_rmap; #endif /* These may be needed for future network-power-down code. */ /* * trans_start here is expensive for high speed devices on SMP, * please use netdev_queue->trans_start instead. */ unsigned long trans_start; /* Time (in jiffies) of last Tx */ int watchdog_timeo; /* used by dev_watchdog() */ struct timer_list watchdog_timer; /* Number of references to this device */ int __percpu *pcpu_refcnt; /* delayed register/unregister */ struct list_head todo_list; /* device index hash chain */ struct hlist_node index_hlist; struct list_head link_watch_list; /* 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 */ NETREG_DUMMY, /* dummy device for NAPI poll */ } reg_state:8; bool dismantle; /* device is going do be freed */ enum { RTNL_LINK_INITIALIZED, RTNL_LINK_INITIALIZING, } rtnl_link_state:16; /* Called from unregister, can be used to call free_netdev */ void (*destructor)(struct net_device *dev); #ifdef CONFIG_NETPOLL struct netpoll_info __rcu *npinfo; #endif #ifdef CONFIG_NET_NS /* Network namespace this network device is inside */ struct net *nd_net; #endif /* mid-layer private */ union { void *ml_priv; struct pcpu_lstats __percpu *lstats; /* loopback stats */ struct pcpu_tstats __percpu *tstats; /* tunnel stats */ struct pcpu_dstats __percpu *dstats; /* dummy stats */ struct pcpu_vstats __percpu *vstats; /* veth stats */ }; /* GARP */ struct garp_port __rcu *garp_port; /* MRP */ struct mrp_port __rcu *mrp_port; /* class/net/name entry */ struct device dev; /* space for optional device, statistics, and wireless sysfs groups */ const struct attribute_group *sysfs_groups[4]; /* rtnetlink link ops */ const struct rtnl_link_ops *rtnl_link_ops; /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; #define GSO_MAX_SEGS 65535 u16 gso_max_segs; #ifdef CONFIG_DCB /* Data Center Bridging netlink ops */ const struct dcbnl_rtnl_ops *dcbnl_ops; #endif u8 num_tc; struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; u8 prio_tc_map[TC_BITMASK + 1]; #if IS_ENABLED(CONFIG_FCOE) /* max exchange id for FCoE LRO by ddp */ unsigned int fcoe_ddp_xid; #endif #if IS_ENABLED(CONFIG_NETPRIO_CGROUP) struct netprio_map __rcu *priomap; #endif /* phy device may attach itself for hardware timestamping */ struct phy_device *phydev; struct lock_class_key *qdisc_tx_busylock; /* group the device belongs to */ int group; struct pm_qos_request pm_qos_req; };