【linux网络】net_device及注册与销毁

最新推荐文章于 2024-07-31 08:37:06 发布

【星星之火】

最新推荐文章于 2024-07-31 08:37:06 发布

阅读量2k

点赞数

分类专栏： Linux内核网络

本文链接：https://blog.csdn.net/fengyuwuzu0519/article/details/114952260

版权

Linux内核网络专栏收录该内容

8 篇文章

订阅专栏

1、net_device结构体

net_device (include/linux/netdevice.h )

/**
 *	struct net_device - The DEVICE structure.
 *		Actually, this whole structure is a big mistake.  It mixes I/O
 *		data with strictly "high-level" data, and it has to know about
 *		almost every data structure used in the INET module.
 *
 *	@name:	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.
 *
 *	@name_hlist: 	Device name hash chain, please keep it close to name[]
 *	@ifalias:	SNMP alias
 *	@mem_end:	Shared memory end
 *	@mem_start:	Shared memory start
 *	@base_addr:	Device I/O address
 *	@irq:		Device IRQ number
 *
 *	@carrier_changes:	Stats to monitor carrier on<->off transitions
 *
 *	@state:		Generic network queuing layer state, see netdev_state_t
 *	@dev_list:	The global list of network devices
 *	@napi_list:	List entry, that is used for polling napi devices
 *	@unreg_list:	List entry, that is used, when we are unregistering the
 *			device, see the function unregister_netdev
 *	@close_list:	List entry, that is used, when we are closing the device
 *
 *	@adj_list:	Directly linked devices, like slaves for bonding
 *	@all_adj_list:	All linked devices, *including* neighbours
 *	@features:	Currently active device features
 *	@hw_features:	User-changeable features
 *
 *	@wanted_features:	User-requested features
 *	@vlan_features:		Mask of features inheritable by VLAN devices
 *
 *	@hw_enc_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.
 *
 *	@mpls_features:	Mask of features inheritable by MPLS
 *
 *	@ifindex:	interface index
 *	@group:		The group, that the device belongs to
 *
 *	@stats:		Statistics struct, which was left as a legacy, use
 *			rtnl_link_stats64 instead
 *
 *	@rx_dropped:	Dropped packets by core network,
 *			do not use this in drivers
 *	@tx_dropped:	Dropped packets by core network,
 *			do not use this in drivers
 *
 *	@wireless_handlers:	List of functions to handle Wireless Extensions,
 *				instead of ioctl,
 *				see <net/iw_handler.h> for details.
 *	@wireless_data:	Instance data managed by the core of wireless extensions
 *
 *	@netdev_ops:	Includes several pointers to callbacks,
 *			if one wants to override the ndo_*() functions
 *	@ethtool_ops:	Management operations
 *	@header_ops:	Includes callbacks for creating,parsing,caching,etc
 *			of Layer 2 headers.
 *
 *	@flags:		Interface flags (a la BSD)
 *	@priv_flags:	Like 'flags' but invisible to userspace,
 *			see if.h for the definitions
 *	@gflags:	Global flags ( kept as legacy )
 *	@padded:	How much padding added by alloc_netdev()
 *	@operstate:	RFC2863 operstate
 *	@link_mode:	Mapping policy to operstate
 *	@if_port:	Selectable AUI, TP, ...
 *	@dma:		DMA channel
 *	@mtu:		Interface MTU value
 *	@type:		Interface hardware type
 *	@hard_header_len: Hardware header length
 *
 *	@needed_headroom: Extra headroom the hardware may need, but not in all
 *			  cases can this be guaranteed
 *	@needed_tailroom: Extra tailroom the hardware may need, but not in all
 *			  cases can this be guaranteed. Some cases also use
 *			  LL_MAX_HEADER instead to allocate the skb
 *
 *	interface address info:
 *
 * 	@perm_addr:		Permanent hw address
 * 	@addr_assign_type:	Hw address assignment type
 * 	@addr_len:		Hardware address length
 * 	@neigh_priv_len;	Used in neigh_alloc(),
 * 				initialized only in atm/clip.c
 * 	@dev_id:		Used to differentiate devices that share
 * 				the same link layer address
 * 	@dev_port:		Used to differentiate devices that share
 * 				the same function
 *	@addr_list_lock:	XXX: need comments on this one
 *	@uc_promisc:		Counter, that indicates, that promiscuous mode
 *				has been enabled due to the need to listen to
 *				additional unicast addresses in a device that
 *				does not implement ndo_set_rx_mode()
 *	@uc:			unicast mac addresses
 *	@mc:			multicast mac addresses
 *	@dev_addrs:		list of device hw addresses
 *	@queues_kset:		Group of all Kobjects in the Tx and RX queues
 *	@promiscuity:		Number of times, the NIC is told to work in
 *				Promiscuous mode, if it becomes 0 the NIC will
 *				exit from working in Promiscuous mode
 *	@allmulti:		Counter, enables or disables allmulticast mode
 *
 *	@vlan_info:	VLAN info
 *	@dsa_ptr:	dsa specific data
 *	@tipc_ptr:	TIPC specific data
 *	@atalk_ptr:	AppleTalk link
 *	@ip_ptr:	IPv4 specific data
 *	@dn_ptr:	DECnet specific data
 *	@ip6_ptr:	IPv6 specific data
 *	@ax25_ptr:	AX.25 specific data
 *	@ieee80211_ptr:	IEEE 802.11 specific data, assign before registering
 *
 *	@last_rx:	Time of last Rx
 *	@dev_addr:	Hw address (before bcast,
 *			because most packets are unicast)
 *
 *	@_rx:			Array of RX queues
 *	@num_rx_queues:		Number of RX queues
 *				allocated at register_netdev() time
 *	@real_num_rx_queues: 	Number of RX queues currently active in device
 *
 *	@rx_handler:		handler for received packets
 *	@rx_handler_data: 	XXX: need comments on this one
 *	@ingress_queue:		XXX: need comments on this one
 *	@broadcast:		hw bcast address
 *
 *	@rx_cpu_rmap:	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
 *	@index_hlist:		Device index hash chain
 *
 *	@_tx:			Array of TX queues
 *	@num_tx_queues:		Number of TX queues allocated at alloc_netdev_mq() time
 *	@real_num_tx_queues: 	Number of TX queues currently active in device
 *	@qdisc:			Root qdisc from userspace point of view
 *	@tx_queue_len:		Max frames per queue allowed
 *	@tx_global_lock: 	XXX: need comments on this one
 *
 *	@xps_maps:	XXX: need comments on this one
 *
 *	@trans_start:		Time (in jiffies) of last Tx
 *	@watchdog_timeo:	Represents the timeout that is used by
 *				the watchdog ( see dev_watchdog() )
 *	@watchdog_timer:	List of timers
 *
 *	@pcpu_refcnt:		Number of references to this device
 *	@todo_list:		Delayed register/unregister
 *	@link_watch_list:	XXX: need comments on this one
 *
 *	@reg_state:		Register/unregister state machine
 *	@dismantle:		Device is going to be freed
 *	@rtnl_link_state:	This enum represents the phases of creating
 *				a new link
 *
 *	@destructor:		Called from unregister,
 *				can be used to call free_netdev
 *	@npinfo:		XXX: need comments on this one
 * 	@nd_net:		Network namespace this network device is inside
 *
 * 	@ml_priv:	Mid-layer private
 * 	@lstats:	Loopback statistics
 * 	@tstats:	Tunnel statistics
 * 	@dstats:	Dummy statistics
 * 	@vstats:	Virtual ethernet statistics
 *
 *	@garp_port:	GARP
 *	@mrp_port:	MRP
 *
 *	@dev:		Class/net/name entry
 *	@sysfs_groups:	Space for optional device, statistics and wireless
 *			sysfs groups
 *
 *	@sysfs_rx_queue_group:	Space for optional per-rx queue attributes
 *	@rtnl_link_ops:	Rtnl_link_ops
 *
 *	@gso_max_size:	Maximum size of generic segmentation offload
 *	@gso_max_segs:	Maximum number of segments that can be passed to the
 *			NIC for GSO
 *	@gso_min_segs:	Minimum number of segments that can be passed to the
 *			NIC for GSO
 *
 *	@dcbnl_ops:	Data Center Bridging netlink ops
 *	@num_tc:	Number of traffic classes in the net device
 *	@tc_to_txq:	XXX: need comments on this one
 *	@prio_tc_map	XXX: need comments on this one
 *
 *	@fcoe_ddp_xid:	Max exchange id for FCoE LRO by ddp
 *
 *	@priomap:	XXX: need comments on this one
 *	@phydev:	Physical device may attach itself
 *			for hardware timestamping
 *
 *	@qdisc_tx_busylock:	XXX: need comments on this one
 *
 *	FIXME: cleanup struct net_device such that network protocol info
 *	moves out.
 */

struct net_device {
	char			name[IFNAMSIZ];
	struct hlist_node	name_hlist;
	char 			*ifalias;
	/*
	 *	I/O specific fields
	 *	FIXME: Merge these and struct ifmap into one
	 */
	unsigned long		mem_end;
	unsigned long		mem_start;
	unsigned long		base_addr;
	int			irq;

	atomic_t		carrier_changes;

	/*
	 *	Some hardware also needs these fields (state,dev_list,
	 *	napi_list,unreg_list,close_list) 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	close_list;
	struct list_head	ptype_all;
	struct list_head	ptype_specific;

	struct {
		struct list_head upper;
		struct list_head lower;
	} adj_list;

	struct {
		struct list_head upper;
		struct list_head lower;
	} all_adj_list;

	netdev_features_t	features;
	netdev_features_t	hw_features;
	netdev_features_t	wanted_features;
	netdev_features_t	vlan_features;
	netdev_features_t	hw_enc_features;
	netdev_features_t	mpls_features;

	int			ifindex;
	int			group;

	struct net_device_stats	stats;

	atomic_long_t		rx_dropped;
	atomic_long_t		tx_dropped;

#ifdef CONFIG_WIRELESS_EXT
	const struct iw_handler_def *	wireless_handlers;
	struct iw_public_data *	wireless_data;
#endif
	const struct net_device_ops *netdev_ops;
	const struct ethtool_ops *ethtool_ops;
#ifdef CONFIG_NET_SWITCHDEV
	const struct swdev_ops *swdev_ops;
#endif

	const struct header_ops *header_ops;

	unsigned int		flags;
	unsigned int		priv_flags;

	unsigned short		gflags;
	unsigned short		padded;

	unsigned char		operstate;
	unsigned char		link_mode;

	unsigned char		if_port;
	unsigned char		dma;

	unsigned int		mtu;
	unsigned short		type;
	unsigned short		hard_header_len;

	unsigned short		needed_headroom;
	unsigned short		needed_tailroom;

	/* Interface address info. */
	unsigned char		perm_addr[MAX_ADDR_LEN];
	unsigned char		addr_assign_type;
	unsigned char		addr_len;
	unsigned short		neigh_priv_len;
	unsigned short          dev_id;
	unsigned short          dev_port;
	spinlock_t		addr_list_lock;
	unsigned char		name_assign_type;
	bool			uc_promisc;
	struct netdev_hw_addr_list	uc;
	struct netdev_hw_addr_list	mc;
	struct netdev_hw_addr_list	dev_addrs;

#ifdef CONFIG_SYSFS
	struct kset		*queues_kset;
#endif
	unsigned int		promiscuity;
	unsigned int		allmulti;


	/* Protocol specific pointers */

#if IS_ENABLED(CONFIG_VLAN_8021Q)
	struct vlan_info __rcu	*vlan_info;
#endif
#if IS_ENABLED(CONFIG_NET_DSA)
	struct dsa_switch_tree	*dsa_ptr;
#endif
#if IS_ENABLED(CONFIG_TIPC)
	struct tipc_bearer __rcu *tipc_ptr;
#endif
	void 			*atalk_ptr;
	struct in_device __rcu	*ip_ptr;
	struct dn_dev __rcu     *dn_ptr;
	struct inet6_dev __rcu	*ip6_ptr;
	void			*ax25_ptr;
	struct wireless_dev	*ieee80211_ptr;
	struct wpan_dev		*ieee802154_ptr;
#if IS_ENABLED(CONFIG_MPLS_ROUTING)
	struct mpls_dev __rcu	*mpls_ptr;
#endif

/*
 * Cache lines mostly used on receive path (including eth_type_trans())
 */
	unsigned long		last_rx;

	/* Interface address info used in eth_type_trans() */
	unsigned char		*dev_addr;


#ifdef CONFIG_SYSFS
	struct netdev_rx_queue	*_rx;

	unsigned int		num_rx_queues;
	unsigned int		real_num_rx_queues;

#endif

	unsigned long		gro_flush_timeout;
	rx_handler_func_t __rcu	*rx_handler;
	void __rcu		*rx_handler_data;

	struct netdev_queue __rcu *ingress_queue;
	unsigned char		broadcast[MAX_ADDR_LEN];
#ifdef CONFIG_RFS_ACCEL
	struct cpu_rmap		*rx_cpu_rmap;
#endif
	struct hlist_node	index_hlist;

/*
 * Cache lines mostly used on transmit path
 */
	struct netdev_queue	*_tx ____cacheline_aligned_in_smp;
	unsigned int		num_tx_queues;
	unsigned int		real_num_tx_queues;
	struct Qdisc		*qdisc;
	unsigned long		tx_queue_len;
	spinlock_t		tx_global_lock;
	int			watchdog_timeo;

#ifdef CONFIG_XPS
	struct xps_dev_maps __rcu *xps_maps;
#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;

	struct timer_list	watchdog_timer;

	int __percpu		*pcpu_refcnt;
	struct list_head	todo_list;

	struct list_head	link_watch_list;

	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;

	enum {
		RTNL_LINK_INITIALIZED,
		RTNL_LINK_INITIALIZING,
	} rtnl_link_state:16;

	void (*destructor)(struct net_device *dev);

#ifdef CONFIG_NETPOLL
	struct netpoll_info __rcu	*npinfo;
#endif

	possible_net_t			nd_net;

	/* mid-layer private */
	union {
		void					*ml_priv;
		struct pcpu_lstats __percpu		*lstats;
		struct pcpu_sw_netstats __percpu	*tstats;
		struct pcpu_dstats __percpu		*dstats;
		struct pcpu_vstats __percpu		*vstats;
	};

	struct garp_port __rcu	*garp_port;
	struct mrp_port __rcu	*mrp_port;

	struct device	dev;
	const struct attribute_group *sysfs_groups[4];
	const struct attribute_group *sysfs_rx_queue_group;

	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;
	u16			gso_min_segs;
#ifdef CONFIG_DCB
	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)
	unsigned int		fcoe_ddp_xid;
#endif
#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
	struct netprio_map __rcu *priomap;
#endif
	struct phy_device *phydev;
	struct lock_class_key *qdisc_tx_busylock;
};

重要成员

类型	类型名	成员名	作用
char	char	name	网卡名，如eth0
struct	net_device_ops *	netdev_ops;	网卡操作函数，如up，down，发包等
int	int __percpu	pcpu_refcnt	网卡引用计数，为0时才可以在卸载时完全销毁

2、申请net_device

3、注册流程 register_netdev

/**
 *	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);

    /* 网卡名合法性检查 */
	ret = dev_get_valid_name(net, dev, dev->name);
	if (ret < 0)
		goto out;

	/* Init, if this function is available */
    /* 如果有初始化回调函数则调用 */
	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;
    /* 分配一个唯一的接口索引 */
	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;

    /* 通知链:网卡初始化 */
	ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
	ret = notifier_to_errno(ret);
	if (ret)
		goto err_uninit;

    /* 将网络设备注册到设备模型中，用户态的/sys/class/net目录下会有该设备目录 */
	ret = netdev_register_kobject(dev);
	if (ret)
		goto err_uninit;

    /* 设置为已注册状态 */
	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);
    /* 引用计数+1=1 */
	dev_hold(dev);
    /* 将网络设备加入到命名空间对应链表中 */
	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. */
    /* 通知其他模块NETDEV_REGISTER事件 */
	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;
}
EXPORT_SYMBOL(register_netdevice);