mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-15 19:16:42 +07:00
s390/checksum: make ip_fast_csum() faster
Convert ip_fast_csum() so it doesn't call csum_partial(), but instead open code the checksum calculation. The problem with csum_partial() is that it makes use of the cksm instruction, which has high startup costs and therefore is only very fast if used on larger memory regions. IPv4 headers however are small in size (5-16 32-bit words). The open coded variant calculates the checksum in ~30% of the time compared to the old variant (z14, march=z196). Signed-off-by: Heiko Carstens <hca@linux.ibm.com> Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
This commit is contained in:
parent
bb4644b14a
commit
614b4f5d0f
@ -66,7 +66,18 @@ static inline __sum16 csum_fold(__wsum sum)
|
||||
*/
|
||||
static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
|
||||
{
|
||||
return csum_fold(csum_partial(iph, ihl*4, 0));
|
||||
__u64 csum = 0;
|
||||
__u32 *ptr = (u32 *)iph;
|
||||
|
||||
csum += *ptr++;
|
||||
csum += *ptr++;
|
||||
csum += *ptr++;
|
||||
csum += *ptr++;
|
||||
ihl -= 4;
|
||||
while (ihl--)
|
||||
csum += *ptr++;
|
||||
csum += (csum >> 32) | (csum << 32);
|
||||
return csum_fold((__force __wsum)(csum >> 32));
|
||||
}
|
||||
|
||||
/*
|
||||
|
Loading…
Reference in New Issue
Block a user