二、校验和源码
网上流传多组实现,常见的有如下两种(如追求效率可改写为汇编代码):
1、RFC1071源码
unsigned short csum(unsigned char *addr, int count)
{
/* Compute Internet Checksum for "count" bytes
* beginning at location "addr".
*/
register long sum = 0;
while( count > 1 )
{
/* This is the inner loop */
sum += * (unsigned short) addr++;
count -= 2;
}
/* Add left-over byte, if any */
if( count > 0 )
sum += * (unsigned char *) addr;
/* Fold 32-bit sum to 16 bits */
while (sum>>16)
sum = (sum & 0xffff) + (sum >> 16);
return ~sum;
}
{
/* Compute Internet Checksum for "count" bytes
* beginning at location "addr".
*/
register long sum = 0;
while( count > 1 )
{
/* This is the inner loop */
sum += * (unsigned short) addr++;
count -= 2;
}
/* Add left-over byte, if any */
if( count > 0 )
sum += * (unsigned char *) addr;
/* Fold 32-bit sum to 16 bits */
while (sum>>16)
sum = (sum & 0xffff) + (sum >> 16);
return ~sum;
}
第一个while循环是做普通加法(2进制补码加法),因为IP包头和TCP整个报文段比较短(没达到2^17数量级),所以不可能导致4字节的sum溢出(unsigned long 一般至少为4字节)).
紧接着的一个判断语句是为了能处理输入数据是奇数个字节的这种情况.再接着的数据循环是实现反码算法(在前面的普通加法得到的数据的基础上),由反码和的高位溢出加到低位的性质,可得到"32位的数据的高位比特移位16比特,再加上原来的低16比特,不影响最终结果" 这个等价运算,因为sum的最初值(刚开始循环时)可能很大,所以这个等价运算需循环进行,直到sum的高比特(16比特以上)全为0.对于32 位的 sum,事实上这个运算循环至多只有两轮,所以也有程序直接用两条"sum = (sum & 0xffff) + (sum >> 16);"代替了整个循环.最后,对和取反返回.
2、对数据长度没限制的实现
unsigned short cksum (struct ip *ip, int len)
{
long sum = 0; /* assume 32 bit long, 16 bit short */
while ( len >1 )
{
sum += *((unsigned short *) ip)++;
if (sum & 8x00000000) /* if high-order bit set, fold */
sum = (sum & 0xFFFF) + (sum>> 16) ;
len -= 2;
}
if ( len ) /* take care of left over byte */
sum += ( unsigned short ) * (unsignedl char *) ip;
while ( sum >> 16)
sum =(sum & 0xFFFF) + (sum>> 16);
return ~sum;}
{
long sum = 0; /* assume 32 bit long, 16 bit short */
while ( len >1 )
{
sum += *((unsigned short *) ip)++;
if (sum & 8x00000000) /* if high-order bit set, fold */
sum = (sum & 0xFFFF) + (sum>> 16) ;
len -= 2;
}
if ( len ) /* take care of left over byte */
sum += ( unsigned short ) * (unsignedl char *) ip;
while ( sum >> 16)
sum =(sum & 0xFFFF) + (sum>> 16);
return ~sum;}
这个实现与前面的一个的最大的不同是对数据的长度没什么限制了,因为它在第一个循环的加法运算中实时检测sum的高位的值,一旦发现其有溢出的危险,就及时运用等价运算关系消除了这个危险.
