【linux网络】sk_buff及相关函数

最新推荐文章于 2023-08-05 13:05:45 发布

【星星之火】

最新推荐文章于 2023-08-05 13:05:45 发布

阅读量1.2k

点赞数 1

CC 4.0 BY-SA版权

分类专栏： Linux内核网络

本文链接：https://blog.csdn.net/fengyuwuzu0519/article/details/114855146

Linux内核网络专栏收录该内容

8 篇文章

订阅专栏

本文详细解析了Linux内核中sk_buff数据结构及其操作函数，包括sk_buff的结构体定义、成员变量说明、分配函数__alloc_skb的工作原理等。此外，还介绍了与sk_buff相关的其他数据结构如sk_buff_head的作用。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

0、概述

内核网络对数据结构的要求:

方便的处理变长数据，接收发送的数据长度是不定的
可以方便的在头部和尾部添加及移除数据，不同网络层传递，数据长度在发生改变

sk_buff:套接字缓冲区，用以描述已接受或者待发送的数据

sk_buff组成

skb结构体本身
数据缓冲区

1、sk_buff结构体

sk_buff（include/linux/skbuff.h）

/** 
 *	struct sk_buff - socket buffer
 *	@next: Next buffer in list
 *	@prev: Previous buffer in list
 *	@tstamp: Time we arrived/left
 *	@rbnode: RB tree node, alternative to next/prev for netem/tcp
 *	@sk: Socket we are owned by
 *	@dev: Device we arrived on/are leaving by
 *	@cb: Control buffer. Free for use by every layer. Put private vars here
 *	@_skb_refdst: destination entry (with norefcount bit)
 *	@sp: the security path, used for xfrm
 *	@len: Length of actual data
 *	@data_len: Data length
 *	@mac_len: Length of link layer header
 *	@hdr_len: writable header length of cloned skb
 *	@csum: Checksum (must include start/offset pair)
 *	@csum_start: Offset from skb->head where checksumming should start
 *	@csum_offset: Offset from csum_start where checksum should be stored
 *	@priority: Packet queueing priority
 *	@ignore_df: allow local fragmentation
 *	@cloned: Head may be cloned (check refcnt to be sure)
 *	@ip_summed: Driver fed us an IP checksum
 *	@nohdr: Payload reference only, must not modify header
 *	@nfctinfo: Relationship of this skb to the connection
 *	@pkt_type: Packet class
 *	@fclone: skbuff clone status
 *	@ipvs_property: skbuff is owned by ipvs
 *	@peeked: this packet has been seen already, so stats have been
 *		done for it, don't do them again
 *	@nf_trace: netfilter packet trace flag
 *	@protocol: Packet protocol from driver
 *	@destructor: Destruct function
 *	@nfct: Associated connection, if any
 *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
 *	@skb_iif: ifindex of device we arrived on
 *	@tc_index: Traffic control index
 *	@tc_verd: traffic control verdict
 *	@hash: the packet hash
 *	@queue_mapping: Queue mapping for multiqueue devices
 *	@xmit_more: More SKBs are pending for this queue
 *	@ndisc_nodetype: router type (from link layer)
 *	@ooo_okay: allow the mapping of a socket to a queue to be changed
 *	@l4_hash: indicate hash is a canonical 4-tuple hash over transport
 *		ports.
 *	@sw_hash: indicates hash was computed in software stack
 *	@wifi_acked_valid: wifi_acked was set
 *	@wifi_acked: whether frame was acked on wifi or not
 *	@no_fcs:  Request NIC to treat last 4 bytes as Ethernet FCS
  *	@napi_id: id of the NAPI struct this skb came from
 *	@secmark: security marking
 *	@mark: Generic packet mark
 *	@vlan_proto: vlan encapsulation protocol
 *	@vlan_tci: vlan tag control information
 *	@inner_protocol: Protocol (encapsulation)
 *	@inner_transport_header: Inner transport layer header (encapsulation)
 *	@inner_network_header: Network layer header (encapsulation)
 *	@inner_mac_header: Link layer header (encapsulation)
 *	@transport_header: Transport layer header
 *	@network_header: Network layer header
 *	@mac_header: Link layer header
 *	@tail: Tail pointer
 *	@end: End pointer
 *	@head: Head of buffer
 *	@data: Data head pointer
 *	@truesize: Buffer size
 *	@users: User count - see {datagram,tcp}.c
 */

struct sk_buff {
	union {
		struct {
			/* These two members must be first. */
			struct sk_buff		*next;
			struct sk_buff		*prev;

			union {
				ktime_t		tstamp;
				struct skb_mstamp skb_mstamp;
			};
		};
		struct rb_node	rbnode; /* used in netem & tcp stack */
	};
	struct sock		*sk;
	struct net_device	*dev;

	/*
	 * This is the control buffer. It is free to use for every
	 * layer. Please put your private variables there. If you
	 * want to keep them across layers you have to do a skb_clone()
	 * first. This is owned by whoever has the skb queued ATM.
	 */
	char			cb[48] __aligned(8);

	unsigned long		_skb_refdst;
	void			(*destructor)(struct sk_buff *skb);
#ifdef CONFIG_XFRM
	struct	sec_path	*sp;
#endif
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
	struct nf_conntrack	*nfct;
#endif
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
	struct nf_bridge_info	*nf_bridge;
#endif
	unsigned int		len,
				data_len;
	__u16			mac_len,
				hdr_len;

	/* Following fields are _not_ copied in __copy_skb_header()
	 * Note that queue_mapping is here mostly to fill a hole.
	 */
	kmemcheck_bitfield_begin(flags1);
	__u16			queue_mapping;
	__u8			cloned:1,
				nohdr:1,
				fclone:2,
				peeked:1,
				head_frag:1,
				xmit_more:1;
	/* one bit hole */
	kmemcheck_bitfield_end(flags1);

	/* fields enclosed in headers_start/headers_end are copied
	 * using a single memcpy() in __copy_skb_header()
	 */
	/* private: */
	__u32			headers_start[0];
	/* public: */

/* if you move pkt_type around you also must adapt those constants */
#ifdef __BIG_ENDIAN_BITFIELD
#define PKT_TYPE_MAX	(7 << 5)
#else
#define PKT_TYPE_MAX	7
#endif
#define PKT_TYPE_OFFSET()	offsetof(struct sk_buff, __pkt_type_offset)

	__u8			__pkt_type_offset[0];
	__u8			pkt_type:3;
	__u8			pfmemalloc:1;
	__u8			ignore_df:1;
	__u8			nfctinfo:3;

	__u8			nf_trace:1;
	__u8			ip_summed:2;
	__u8			ooo_okay:1;
	__u8			l4_hash:1;
	__u8			sw_hash:1;
	__u8			wifi_acked_valid:1;
	__u8			wifi_acked:1;

	__u8			no_fcs:1;
	/* Indicates the inner headers are valid in the skbuff. */
	__u8			encapsulation:1;
	__u8			encap_hdr_csum:1;
	__u8			csum_valid:1;
	__u8			csum_complete_sw:1;
	__u8			csum_level:2;
	__u8			csum_bad:1;

#ifdef CONFIG_IPV6_NDISC_NODETYPE
	__u8			ndisc_nodetype:2;
#endif
	__u8			ipvs_property:1;
	__u8			inner_protocol_type:1;
	__u8			remcsum_offload:1;
	/* 3 or 5 bit hole */

#ifdef CONFIG_NET_SCHED
	__u16			tc_index;	/* traffic control index */
#ifdef CONFIG_NET_CLS_ACT
	__u16			tc_verd;	/* traffic control verdict */
#endif
#endif

	union {
		__wsum		csum;
		struct {
			__u16	csum_start;
			__u16	csum_offset;
		};
	};
	__u32			priority;
	int			skb_iif;
	__u32			hash;
	__be16			vlan_proto;
	__u16			vlan_tci;
#if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS)
	union {
		unsigned int	napi_id;
		unsigned int	sender_cpu;
	};
#endif
#ifdef CONFIG_NETWORK_SECMARK
	__u32			secmark;
#endif
	union {
		__u32		mark;
		__u32		reserved_tailroom;
	};

	union {
		__be16		inner_protocol;
		__u8		inner_ipproto;
	};

	__u16			inner_transport_header;
	__u16			inner_network_header;
	__u16			inner_mac_header;

	__be16			protocol;
	__u16			transport_header;
	__u16			network_header;
	__u16			mac_header;

	/* private: */
	__u32			headers_end[0];
	/* public: */

	/* These elements must be at the end, see alloc_skb() for details.  */
	sk_buff_data_t		tail;
	sk_buff_data_t		end;
	unsigned char		*head,
				*data;
	unsigned int		truesize;
	atomic_t		users;
};

2、sk_buff操作函数

skb分配函数

alloc_skb()

struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int flags, int node)

size：SKB线性存储区数据长度

gfp_mask:分配内存的方式

flags：判断从哪个高速缓存分配

/**
 *	__alloc_skb	-	allocate a network buffer
 *	@size: size to allocate
 *	@gfp_mask: allocation mask
 *	@flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache
 *		instead of head cache and allocate a cloned (child) skb.
 *		If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
 *		allocations in case the data is required for writeback
 *	@node: numa node to allocate memory on
 *
 *	Allocate a new &sk_buff. The returned buffer has no headroom and a
 *	tail room of at least size bytes. The object has a reference count
 *	of one. The return is the buffer. On a failure the return is %NULL.
 *
 *	Buffers may only be allocated from interrupts using a @gfp_mask of
 *	%GFP_ATOMIC.
 */
struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
			    int flags, int node)
{
	struct kmem_cache *cache;
	struct skb_shared_info *shinfo;
	struct sk_buff *skb;
	u8 *data;
	bool pfmemalloc;

	cache = (flags & SKB_ALLOC_FCLONE)
		? skbuff_fclone_cache : skbuff_head_cache;

	if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX))
		gfp_mask |= __GFP_MEMALLOC;

	/* Get the HEAD */
    //获取一个sk_buff 结构体
	skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
	if (!skb)
		goto out;
	prefetchw(skb);

	/* We do our best to align skb_shared_info on a separate cache
	 * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives
	 * aligned memory blocks, unless SLUB/SLAB debug is enabled.
	 * Both skb->head and skb_shared_info are cache line aligned.
	 */
    //对size的大小进行边界对其处理；
	size = SKB_DATA_ALIGN(size);
	size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
    //分配数据缓冲区
	data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc);
	if (!data)
		goto nodata;
	/* kmalloc(size) might give us more room than requested.
	 * Put skb_shared_info exactly at the end of allocated zone,
	 * to allow max possible filling before reallocation.
	 */
	size = SKB_WITH_OVERHEAD(ksize(data));
	prefetchw(data + size);

	/*
	 * Only clear those fields we need to clear, not those that we will
	 * actually initialise below. Hence, don't put any more fields after
	 * the tail pointer in struct sk_buff!
	 */
	memset(skb, 0, offsetof(struct sk_buff, tail));
	/* Account for allocated memory : skb + skb->head */
	skb->truesize = SKB_TRUESIZE(size);
	skb->pfmemalloc = pfmemalloc;
	atomic_set(&skb->users, 1);
    //初始化指针，刚分配的skb head data指向一个地址
	skb->head = data;
	skb->data = data;
	skb_reset_tail_pointer(skb);
	skb->end = skb->tail + size;
	skb->mac_header = (typeof(skb->mac_header))~0U;
	skb->transport_header = (typeof(skb->transport_header))~0U;

	/* make sure we initialize shinfo sequentially */
    //对struct skb_shared_info中的字段进行初始化处理；
	shinfo = skb_shinfo(skb);
	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
	atomic_set(&shinfo->dataref, 1);
	kmemcheck_annotate_variable(shinfo->destructor_arg);

	if (flags & SKB_ALLOC_FCLONE) {
		struct sk_buff_fclones *fclones;

		fclones = container_of(skb, struct sk_buff_fclones, skb1);

		kmemcheck_annotate_bitfield(&fclones->skb2, flags1);
		skb->fclone = SKB_FCLONE_ORIG;
		atomic_set(&fclones->fclone_ref, 1);

		fclones->skb2.fclone = SKB_FCLONE_CLONE;
		fclones->skb2.pfmemalloc = pfmemalloc;
	}
out:
	return skb;
nodata:
	kmem_cache_free(cache, skb);
	skb = NULL;
	goto out;
}
EXPORT_SYMBOL(__alloc_skb);

skb操作函数

head -->      |----------|
              | headroom |      headroom = skb->head - skb->data
data -->      |----------|
              |   data   |          data = skb->data - skb->tail  
tail -->      |----------|
              | tailroom |      tailroom = skb->tail - skb->end
end  -->      |----------|