读了一下《Professional Linux Kernel Architecture》的Network这一章。由于本书讲得比较新，可以说是市面上目前讲Linux内核版本最新的著作了，涉及到了2.6.24版本。其中，有很多微妙的变化，由于struct sk_buff是内核网络机构的基础，因此我也比较关心这个结构的变化：
struct sk_buff {
/* These two members must be first. */
struct sk_buff *next;
struct sk_buff *prev;
struct sock *sk;
ktime_t tstamp;
struct net_device *dev;
struct dst_entry *dst;
struct sec_path *sp;
/*
* 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];
unsigned int len,
data_len;
__u16 mac_len,
hdr_len;
union {
__wsum csum;
struct {
__u16 csum_start;
__u16 csum_offset;
};
};
__u32 priority;
__u8 local_df:1,
cloned:1,
ip_summed:2,
nohdr:1,
nfctinfo:3;
__u8 pkt_type:3,
fclone:2,
ipvs_property:1,
peeked:1,
nf_trace:1;
__be16 protocol;
void (*destructor)(struct sk_buff *skb);
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
struct nf_conntrack *nfct;
struct sk_buff *nfct_reasm;
#endif
#ifdef CONFIG_BRIDGE_NETFILTER
struct nf_bridge_info *nf_bridge;
#endif
int iif;
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
__u16 queue_mapping;
#endif
#ifdef CONFIG_NET_SCHED
__u16 tc_index; /* traffic control index */
#ifdef CONFIG_NET_CLS_ACT
__u16 tc_verd; /* traffic control verdict */
#endif
#endif
/* 2 byte hole */
#ifdef CONFIG_NET_DMA
dma_cookie_t dma_cookie;
#endif
#ifdef CONFIG_NETWORK_SECMARK
__u32 secmark;
#endif
__u32 mark;
sk_buff_data_t transport_header;
sk_buff_data_t network_header;
sk_buff_data_t mac_header;
/* 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;
};
用红色标记这三个成员，分别是传输头，网络头以及mac头相对于Sk_buff的head的偏移。有了这三个成员，可以说为内核编程人员提供了更便利的获取传输层、网络层和MAC层头的偏移。并且，内核也新增了几个函数，来提供获取这些偏移的接口：
#ifdef NET_SKBUFF_DATA_USES_OFFSET
如果使用了offset来表示偏移的话，就是说是一个相对偏移的情况：
static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
{
return skb->head + skb->transport_header;
}
static inline void skb_reset_transport_header(struct sk_buff *skb)
{
skb->transport_header = skb->data - skb->head;
}
static inline void skb_set_transport_header(struct sk_buff *skb,
const int offset)
{
skb_reset_transport_header(skb);
skb->transport_header += offset;
}
static inline unsigned char *skb_network_header(const struct sk_buff *skb)
{
return skb->head + skb->network_header;
}
static inline void skb_reset_network_header(struct sk_buff *skb)
{
skb->network_header = skb->data - skb->head;
}
static inline void skb_set_network_header(struct sk_buff *skb, const int offset)
{
skb_reset_network_header(skb);
skb->network_header += offset;
}
static inline unsigned char *skb_mac_header(const struct sk_buff *skb)
{
return skb->head + skb->mac_header;
}
static inline int skb_mac_header_was_set(const struct sk_buff *skb)
{
return skb->mac_header != ~0U;
}
static inline void skb_reset_mac_header(struct sk_buff *skb)
{
skb->mac_header = skb->data - skb->head;
}
static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
{
skb_reset_mac_header(skb);
skb->mac_header += offset;
}
#else /* NET_SKBUFF_DATA_USES_OFFSET */
不使用相对偏移的情况
static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
{
return skb->transport_header;
}
static inline void skb_reset_transport_header(struct sk_buff *skb)
{
skb->transport_header = skb->data;
}
static inline void skb_set_transport_header(struct sk_buff *skb,
const int offset)
{
skb->transport_header = skb->data + offset;
}
static inline unsigned char *skb_network_header(const struct sk_buff *skb)
{
return skb->network_header;
}
static inline void skb_reset_network_header(struct sk_buff *skb)
{
skb->network_header = skb->data;
}
static inline void skb_set_network_header(struct sk_buff *skb, const int offset)
{
skb->network_header = skb->data + offset;
}
static inline unsigned char *skb_mac_header(const struct sk_buff *skb)
{
return skb->mac_header;
}
static inline int skb_mac_header_was_set(const struct sk_buff *skb)
{
return skb->mac_header != NULL;
}
static inline void skb_reset_mac_header(struct sk_buff *skb)
{
skb->mac_header = skb->data;
}
static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
{
skb->mac_header = skb->data + offset;
}
#endif /* NET_SKBUFF_DATA_USES_OFFSET */
1、TCP层获取相关偏移的函数
static inline struct tcphdr *tcp_hdr(const struct sk_buff *skb)
{
return (struct tcphdr *)skb_transport_header(skb);
}
这个函数用来获得sk_buff结构中TCP头的指针
static inline unsigned int tcp_hdrlen(const struct sk_buff *skb)
{
return tcp_hdr(skb)->doff * 4;
}
这个函数用来获得TCP头的长度
static inline unsigned int tcp_optlen(const struct sk_buff *skb)
{
return (tcp_hdr(skb)->doff - 5) * 4;
}
获取tcp option的长度
2、IP相关的函数
static inline struct iphdr *ip_hdr(const struct sk_buff *skb)
{
return (struct iphdr *)skb_network_header(skb);
}
该函数获得ip头
static inline struct iphdr *ipip_hdr(const struct sk_buff *skb)
{
return (struct iphdr *)skb_transport_header(skb);
}
该函数获得ipip头，实际上偏移已经跑到了传输层的开始
3、MAC相关函数
static inline struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb)
{
return (struct ebt_802_3_hdr *)skb_mac_header(skb);
}
获取802.3MAC头指针。
可以说，这些函数，为我们编写内核程序提供了极大的便捷，而不用再花更多的精力去考虑计算各层的指针偏移，可以把更多的精力用来考虑策略性的设计。
