IP包的接受过程

1) IP包由包头和数据区组成, 包头由IP头(iphdr)和IP选项区组成, IP头的开始4位为版本号, 
下4位为包头32比特字数, 因此IP包头最大长度为64字节, 最小长度为IP头长度(20字节), 
数据区起始于32位边界上. 当包头长度大于IP头长度时, 从IP头开始的区域为IP选项区. 

2) IP包接收器(ip_rcv)接收帧类型为ETH_P_IP(0x0800)的包, 它首先检查包的正确性, 
再将输入包过滤器进行过滤, 再将过滤包绑定到输出路由, 分析其选项区,
最后从路由目的入口输出, 
根据不同的路由类型, 输入到IP转发器(ip_forward)或IP本地分发器(ip_local_deliver)以及
IP同播转发器(ip_mc_output)中.

3) 如果系统允许接收带有信源路由选项(IPOPT_LSRR或IPOPT_SSRR)的IP包, 如果是本地包, 
则将包重新绑定到信源路由表第1项地址所指定的路由上, 如果该地址是本地地址, 
则用它替换IP头的目的地址并分析下一信源路由地址.

; net/ipv4/ip_output.c:

static struct packet_type ip_packet_type =
{
	__constant_htons(ETH_P_IP),
	NULL,	/* All devices */
	ip_rcv,
	(void*)1,
	NULL,
};
void __init ip_init(void)
{
	dev_add_pack(&ip_packet_type);

	ip_rt_init();
	inet_initpeers();

#ifdef CONFIG_IP_MULTICAST
	proc_net_create("igmp", 0, ip_mc_procinfo);
#endif
}

; net/ipv4/ip_input.c:
/*
 * 	Main IP Receive routine.
 */ 
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt)
{
	struct iphdr *iph = skb->nh.iph;

	/* When the interface is in promisc. mode, drop all the crap
	 * that it receives, do not try to analyse it.
	 */
	if (skb->pkt_type == PACKET_OTHERHOST)
		goto drop;

	IP_INC_STATS_BH(IpInReceives);

	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
		goto out;

	/*
	 *	RFC1122: 3.1.2.2 MUST silently discard any IP frame that fails the checksum.
	 *
	 *	Is the datagram acceptable?
	 *
	 *	1.	Length at least the size of an ip header
	 *	2.	Version of 4
	 *	3.	Checksums correctly. [Speed optimisation for later, skip loopback checksums]
	 *	4.	Doesn't have a bogus length
	 */

	if (skb->len < sizeof(struct iphdr) || skb->len < (iph->ihl<<2))
		goto inhdr_error; 
	if (iph->ihl < 5 || iph->version != 4 || ip_fast_csum((u8 *)iph, iph->ihl) != 0)
		goto inhdr_error; 

	{
		__u32 len = ntohs(iph->tot_len); 
		if (skb->len < len || len < (iph->ihl<<2))
			goto inhdr_error;

		/* Our transport medium may have padded the buffer out. Now we know it
		 * is IP we can trim to the true length of the frame.
		 * Note this now means skb->len holds ntohs(iph->tot_len).
		 */
		__skb_trim(skb, len);
	}

	return NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, dev, NULL,
		       ip_rcv_finish);

inhdr_error:
	IP_INC_STATS_BH(IpInHdrErrors);
drop:
        kfree_skb(skb);
out:
        return NET_RX_DROP;
}

#define IN_DEV_SOURCE_ROUTE(in_dev)	(ipv4_devconf.accept_source_route &&
(in_dev)->cnf.accept_source_route)
#define IN_DEV_LOG_MARTIANS(in_dev)	(ipv4_devconf.log_martians ||
(in_dev)->cnf.log_martians)

static inline int ip_rcv_finish(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct iphdr *iph = skb->nh.iph;

	/*
	 *	Initialise the virtual path cache for the packet. It describes
	 *	how the packet travels inside Linux networking.
	 */ 
	if (skb->dst == NULL) {
		if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))
			goto drop; 
	}

#ifdef CONFIG_NET_CLS_ROUTE
	if (skb->dst->tclassid) {
		struct ip_rt_acct *st = ip_rt_acct + 256*smp_processor_id();
		u32 idx = skb->dst->tclassid;
		st[idx&0xFF].o_packets++;
		st[idx&0xFF].o_bytes+=skb->len;
		st[(idx>>16)&0xFF].i_packets++;
		st[(idx>>16)&0xFF].i_bytes+=skb->len;
	}
#endif

	if (iph->ihl > 5) {
		struct ip_options *opt;

		/* It looks as overkill, because not all
		   IP options require packet mangling.
		   But it is the easiest for now, especially taking
		   into account that combination of IP options
		   and running sniffer is extremely rare condition.
		                                      --ANK (980813)
		*/

		skb = skb_cow(skb, skb_headroom(skb));
		if (skb == NULL)
			return NET_RX_DROP;
		iph = skb->nh.iph;

		skb->ip_summed = 0;
		if (ip_options_compile(NULL, skb))
			goto inhdr_error;

		opt = &(IPCB(skb)->opt);
		if (opt->srr) {
			struct in_device *in_dev = in_dev_get(dev);
			if (in_dev) {
				if (!IN_DEV_SOURCE_ROUTE(in_dev)) {
					if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
						printk(KERN_INFO "source route option %u.%u.%u.%u -> %u.%u.%u.%u/n",
						       NIPQUAD(iph->saddr), NIPQUAD(iph->daddr));
					in_dev_put(in_dev);
					goto drop;
				}
				in_dev_put(in_dev);
			}
			if (ip_options_rcv_srr(skb))
				goto drop;
		}
	}

	return skb->dst->input(skb);

inhdr_error:
	IP_INC_STATS_BH(IpInHdrErrors);
drop:
        kfree_skb(skb);
        return NET_RX_DROP;
}
; net/ipv4/ip_options.c:

struct ip_options {
  __u32		faddr;				/* Saved first hop address */
  unsigned char	optlen;
  unsigned char srr;
  unsigned char rr;
  unsigned char ts;
  unsigned char is_setbyuser:1,			/* Set by setsockopt?			*/
                is_data:1,			/* Options in __data, rather than skb	*/
                is_strictroute:1,		/* Strict source route			*/
                srr_is_hit:1,			/* Packet destination addr was our one	*/
                is_changed:1,			/* IP checksum more not valid		*/	
                rr_needaddr:1,			/* Need to record addr of outgoing dev	*/
                ts_needtime:1,			/* Need to record timestamp		*/
                ts_needaddr:1;			/* Need to record addr of outgoing dev  */
  unsigned char router_alert;
  unsigned char __pad1;
  unsigned char __pad2;
  unsigned char __data[0];
};
struct inet_skb_parm
{
	struct ip_options	opt;		/* Compiled IP options		*/
	unsigned char		flags;

#define IPSKB_MASQUERADED	1
#define IPSKB_TRANSLATED	2
#define IPSKB_FORWARDED		4
};

#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))

int ip_options_compile(struct ip_options * opt, struct sk_buff * skb)
{
	int l;
	unsigned char * iph;
	unsigned char * optptr;
	int optlen;
	unsigned char * pp_ptr = NULL;
	struct rtable *rt = skb ? (struct rtable*)skb->dst : NULL;

	if (!opt) {
		opt = &(IPCB(skb)->opt);
		memset(opt, 0, sizeof(struct ip_options));
		iph = skb->nh.raw;
		opt->optlen = ((struct iphdr *)iph)->ihl*4 - sizeof(struct iphdr);
		optptr = iph + sizeof(struct iphdr);
		opt->is_data = 0;
	} else {
		optptr = opt->is_data ? opt->__data : (unsigned char*)&(skb->nh.iph[1]);
		iph = optptr - sizeof(struct iphdr);
	}

	for (l = opt->optlen; l > 0; ) {
		switch (*optptr) {
		      case IPOPT_END: 选项结束标记
			for (optptr++, l--; l>0; l--) {
				if (*optptr != IPOPT_END) {
					*optptr = IPOPT_END;
					opt->is_changed = 1;
				}
			}
			goto eol;
		      case IPOPT_NOOP: 空选项
			l--;
			optptr++;
			continue;
		}
		optlen = optptr[1];
		if (optlen<2 || optlen>l) {
			pp_ptr = optptr;
			goto error;
		}
		switch (*optptr) {
		      case IPOPT_SSRR: 严格信源路由选项
		      case IPOPT_LSRR: 自由信源路由选项
			if (optlen < 3) {
				pp_ptr = optptr + 1;
				goto error;
			}
			if (optptr[2] < 4) {
				pp_ptr = optptr + 2;
				goto error;
			}
			/* NB: cf RFC-1812 5.2.4.1 */
			if (opt->srr) { 只能有一个信源路由选项
				pp_ptr = optptr;
				goto error;
			}
			if (!skb) {
				if (optptr[2] != 4 || optlen < 7 || ((optlen-3) & 3)) {
					pp_ptr = optptr + 1;
					goto error;
				}
				memcpy(&opt->faddr, &optptr[3], 4);
				if (optlen > 7)
					memmove(&optptr[3], &optptr[7], optlen-7); 
			}
			opt->is_strictroute = (optptr[0] == IPOPT_SSRR);
			opt->srr = optptr - iph;
			break;
		      case IPOPT_RR: 路径记录表
			if (opt->rr) {
				pp_ptr = optptr;
				goto error;
			}
			if (optlen < 3) {
				pp_ptr = optptr + 1;
				goto error;
			}
			if (optptr[2] < 4) {
				pp_ptr = optptr + 2;
				goto error;
			}
			if (optptr[2] <= optlen) {
				if (optptr[2]+3 > optlen) {
					pp_ptr = optptr + 2;
					goto error;
				}
				if (skb) { 登记设备的地址
					memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
					opt->is_changed = 1;
				}
				optptr[2] += 4;
				opt->rr_needaddr = 1;
			}
			opt->rr = optptr - iph;
			break;
		      case IPOPT_TIMESTAMP: 登记系统的时戳
			if (opt->ts) {
				pp_ptr = optptr;
				goto error;
			}
			if (optlen < 4) {
				pp_ptr = optptr + 1;
				goto error;
			}
			if (optptr[2] < 5) {
				pp_ptr = optptr + 2;
				goto error;
			}
			if (optptr[2] <= optlen) {
				__u32 * timeptr = NULL;
				if (optptr[2]+3 > optptr[1]) {
					pp_ptr = optptr + 2;
					goto error;
				}
				switch (optptr[3]&0xF) {
				      case IPOPT_TS_TSONLY: 只取时戳
					opt->ts = optptr - iph;
					if (skb) 
						timeptr = (__u32*)&optptr[optptr[2]-1];
					opt->ts_needtime = 1;
					optptr[2] += 4;
					break;
				      case IPOPT_TS_TSANDADDR: 取地址和时戳
					if (optptr[2]+7 > optptr[1]) {
						pp_ptr = optptr + 2;
						goto error;
					}
					opt->ts = optptr - iph;
					if (skb) {
						memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
						timeptr = (__u32*)&optptr[optptr[2]+3];
					}
					opt->ts_needaddr = 1;
					opt->ts_needtime = 1;
					optptr[2] += 8;
					break;
				      case IPOPT_TS_PRESPEC: 取特定地址的时戳
					if (optptr[2]+7 > optptr[1]) {
						pp_ptr = optptr + 2;
						goto error;
					}
					opt->ts = optptr - iph;
					{
						u32 addr;
						memcpy(&addr, &optptr[optptr[2]-1], 4);
						if (inet_addr_type(addr) == RTN_UNICAST)
							break;
						if (skb)
							timeptr = (__u32*)&optptr[optptr[2]+3];
					}
					opt->ts_needtime = 1;
					optptr[2] += 8;
					break;
				      default:
					if (!skb && !capable(CAP_NET_RAW)) {
						pp_ptr = optptr + 3;
						goto error;
					}
					break;
				}
				if (timeptr) {
					struct timeval tv;
					__u32  midtime;
					do_gettimeofday(&tv);
					midtime = htonl((tv.tv_sec % 86400) * 1000 + tv.tv_usec / 1000);
					memcpy(timeptr, &midtime, sizeof(__u32));
					opt->is_changed = 1;
				}
			} else {
				unsigned overflow = optptr[3]>>4;
				if (overflow == 15) {
					pp_ptr = optptr + 3;
					goto error;
				}
				opt->ts = optptr - iph;
				if (skb) {
					optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4);
					opt->is_changed = 1;
				}
			}
			break;
		      case IPOPT_RA:
			if (optlen < 4) {
				pp_ptr = optptr + 1;
				goto error;
			}
			if (optptr[2] == 0 && optptr[3] == 0)
				opt->router_alert = optptr - iph;
			break;
		      case IPOPT_SEC:
		      case IPOPT_SID:
		      default:
			if (!skb && !capable(CAP_NET_RAW)) {
				pp_ptr = optptr;
				goto error;
			}
			break;
		}
		l -= optlen;
		optptr += optlen;
	}

eol:
	if (!pp_ptr)
		return 0;

error:
	if (skb) {
		icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((pp_ptr-iph)<<24));
	}
	return -EINVAL;
}
int ip_options_rcv_srr(struct sk_buff *skb)
{
	struct ip_options *opt = &(IPCB(skb)->opt);
	int srrspace, srrptr;
	u32 nexthop;
	struct iphdr *iph = skb->nh.iph;
	unsigned char * optptr = skb->nh.raw + opt->srr;
	struct rtable *rt = (struct rtable*)skb->dst;
	struct rtable *rt2;
	int err;

	if (!opt->srr)
		return 0;

	if (skb->pkt_type != PACKET_HOST)
		return -EINVAL;
	if (rt->rt_type == RTN_UNICAST) {
		if (!opt->is_strictroute)
			return 0;
		icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl(16<<24));
		return -EINVAL;
	}
	if (rt->rt_type != RTN_LOCAL)
		return -EINVAL;

	for (srrptr=optptr[2], srrspace = optptr[1]; srrptr <= srrspace; srrptr += 4) {
		if (srrptr + 3 > srrspace) {
			icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((opt->srr+2)<<24));
			return -EINVAL;
		}
		memcpy(&nexthop, &optptr[srrptr-1], 4);

		rt = (struct rtable*)skb->dst;
		skb->dst = NULL;
		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev);
		rt2 = (struct rtable*)skb->dst;
		if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
			ip_rt_put(rt2);
			skb->dst = &rt->u.dst;
			return -EINVAL;
		}
		ip_rt_put(rt);
		if (rt2->rt_type != RTN_LOCAL)
			break;
		/* Superfast 8) loopback forward */
		memcpy(&iph->daddr, &optptr[srrptr-1], 4);
		opt->is_changed = 1;
	}
	if (srrptr <= srrspace) {
		opt->srr_is_hit = 1;
		opt->is_changed = 1;
	}
	return 0;
}