01cfbad79a
This patch updates all instances of csum_tcpudp_magic and csum_tcpudp_nofold to reflect the types that are usually used as the source inputs. For example the protocol field is populated based on nexthdr which is actually an unsigned 8 bit value. The length is usually populated based on skb->len which is an unsigned integer. This addresses an issue in which the IPv6 function csum_ipv6_magic was generating a checksum using the full 32b of skb->len while csum_tcpudp_magic was only using the lower 16 bits. As a result we could run into issues when attempting to adjust the checksum as there was no protocol agnostic way to update it. With this change the value is still truncated as many architectures use "(len + proto) << 8", however this truncation only occurs for values greater than 16776960 in length and as such is unlikely to occur as we stop the inner headers at ~64K in size. I did have to make a few minor changes in the arm, mn10300, nios2, and score versions of the function in order to support these changes as they were either using things such as an OR to combine the protocol and length, or were using ntohs to convert the length which would have truncated the value. I also updated a few spots in terms of whitespace and type differences for the addresses. Most of this was just to make sure all of the definitions were in sync going forward. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Signed-off-by: David S. Miller <davem@davemloft.net>
181 lines
4.4 KiB
C
181 lines
4.4 KiB
C
/*
|
|
* arch/alpha/lib/checksum.c
|
|
*
|
|
* This file contains network checksum routines that are better done
|
|
* in an architecture-specific manner due to speed..
|
|
* Comments in other versions indicate that the algorithms are from RFC1071
|
|
*
|
|
* accelerated versions (and 21264 assembly versions ) contributed by
|
|
* Rick Gorton <rick.gorton@alpha-processor.com>
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/string.h>
|
|
|
|
#include <asm/byteorder.h>
|
|
|
|
static inline unsigned short from64to16(unsigned long x)
|
|
{
|
|
/* Using extract instructions is a bit more efficient
|
|
than the original shift/bitmask version. */
|
|
|
|
union {
|
|
unsigned long ul;
|
|
unsigned int ui[2];
|
|
unsigned short us[4];
|
|
} in_v, tmp_v, out_v;
|
|
|
|
in_v.ul = x;
|
|
tmp_v.ul = (unsigned long) in_v.ui[0] + (unsigned long) in_v.ui[1];
|
|
|
|
/* Since the bits of tmp_v.sh[3] are going to always be zero,
|
|
we don't have to bother to add that in. */
|
|
out_v.ul = (unsigned long) tmp_v.us[0] + (unsigned long) tmp_v.us[1]
|
|
+ (unsigned long) tmp_v.us[2];
|
|
|
|
/* Similarly, out_v.us[2] is always zero for the final add. */
|
|
return out_v.us[0] + out_v.us[1];
|
|
}
|
|
|
|
/*
|
|
* computes the checksum of the TCP/UDP pseudo-header
|
|
* returns a 16-bit checksum, already complemented.
|
|
*/
|
|
__sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
|
|
__u32 len, __u8 proto, __wsum sum)
|
|
{
|
|
return (__force __sum16)~from64to16(
|
|
(__force u64)saddr + (__force u64)daddr +
|
|
(__force u64)sum + ((len + proto) << 8));
|
|
}
|
|
|
|
__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
|
|
__u32 len, __u8 proto, __wsum sum)
|
|
{
|
|
unsigned long result;
|
|
|
|
result = (__force u64)saddr + (__force u64)daddr +
|
|
(__force u64)sum + ((len + proto) << 8);
|
|
|
|
/* Fold down to 32-bits so we don't lose in the typedef-less
|
|
network stack. */
|
|
/* 64 to 33 */
|
|
result = (result & 0xffffffff) + (result >> 32);
|
|
/* 33 to 32 */
|
|
result = (result & 0xffffffff) + (result >> 32);
|
|
return (__force __wsum)result;
|
|
}
|
|
EXPORT_SYMBOL(csum_tcpudp_nofold);
|
|
|
|
/*
|
|
* Do a 64-bit checksum on an arbitrary memory area..
|
|
*
|
|
* This isn't a great routine, but it's not _horrible_ either. The
|
|
* inner loop could be unrolled a bit further, and there are better
|
|
* ways to do the carry, but this is reasonable.
|
|
*/
|
|
static inline unsigned long do_csum(const unsigned char * buff, int len)
|
|
{
|
|
int odd, count;
|
|
unsigned long result = 0;
|
|
|
|
if (len <= 0)
|
|
goto out;
|
|
odd = 1 & (unsigned long) buff;
|
|
if (odd) {
|
|
result = *buff << 8;
|
|
len--;
|
|
buff++;
|
|
}
|
|
count = len >> 1; /* nr of 16-bit words.. */
|
|
if (count) {
|
|
if (2 & (unsigned long) buff) {
|
|
result += *(unsigned short *) buff;
|
|
count--;
|
|
len -= 2;
|
|
buff += 2;
|
|
}
|
|
count >>= 1; /* nr of 32-bit words.. */
|
|
if (count) {
|
|
if (4 & (unsigned long) buff) {
|
|
result += *(unsigned int *) buff;
|
|
count--;
|
|
len -= 4;
|
|
buff += 4;
|
|
}
|
|
count >>= 1; /* nr of 64-bit words.. */
|
|
if (count) {
|
|
unsigned long carry = 0;
|
|
do {
|
|
unsigned long w = *(unsigned long *) buff;
|
|
count--;
|
|
buff += 8;
|
|
result += carry;
|
|
result += w;
|
|
carry = (w > result);
|
|
} while (count);
|
|
result += carry;
|
|
result = (result & 0xffffffff) + (result >> 32);
|
|
}
|
|
if (len & 4) {
|
|
result += *(unsigned int *) buff;
|
|
buff += 4;
|
|
}
|
|
}
|
|
if (len & 2) {
|
|
result += *(unsigned short *) buff;
|
|
buff += 2;
|
|
}
|
|
}
|
|
if (len & 1)
|
|
result += *buff;
|
|
result = from64to16(result);
|
|
if (odd)
|
|
result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
|
|
out:
|
|
return result;
|
|
}
|
|
|
|
/*
|
|
* This is a version of ip_compute_csum() optimized for IP headers,
|
|
* which always checksum on 4 octet boundaries.
|
|
*/
|
|
__sum16 ip_fast_csum(const void *iph, unsigned int ihl)
|
|
{
|
|
return (__force __sum16)~do_csum(iph,ihl*4);
|
|
}
|
|
|
|
/*
|
|
* computes the checksum of a memory block at buff, length len,
|
|
* and adds in "sum" (32-bit)
|
|
*
|
|
* returns a 32-bit number suitable for feeding into itself
|
|
* or csum_tcpudp_magic
|
|
*
|
|
* this function must be called with even lengths, except
|
|
* for the last fragment, which may be odd
|
|
*
|
|
* it's best to have buff aligned on a 32-bit boundary
|
|
*/
|
|
__wsum csum_partial(const void *buff, int len, __wsum sum)
|
|
{
|
|
unsigned long result = do_csum(buff, len);
|
|
|
|
/* add in old sum, and carry.. */
|
|
result += (__force u32)sum;
|
|
/* 32+c bits -> 32 bits */
|
|
result = (result & 0xffffffff) + (result >> 32);
|
|
return (__force __wsum)result;
|
|
}
|
|
|
|
EXPORT_SYMBOL(csum_partial);
|
|
|
|
/*
|
|
* this routine is used for miscellaneous IP-like checksums, mainly
|
|
* in icmp.c
|
|
*/
|
|
__sum16 ip_compute_csum(const void *buff, int len)
|
|
{
|
|
return (__force __sum16)~from64to16(do_csum(buff,len));
|
|
}
|