1
linux/include/asm-generic/checksum.h
Charlie Jenkins 1e7196fa5b
asm-generic: Improve csum_fold
This csum_fold implementation introduced into arch/arc by Vineet Gupta
is better than the default implementation on at least arc, x86, and
riscv. Using GCC trunk and compiling non-inlined version, this
implementation has 41.6667%, 25% fewer instructions on riscv64, x86-64
respectively with -O3 optimization. Most implmentations override this
default in asm, but this should be more performant than all of those
other implementations except for arm which has barrel shifting and
sparc32 which has a carry flag.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: David Laight <david.laight@aculab.com>
Link: https://lore.kernel.org/r/20240108-optimize_checksum-v15-1-1c50de5f2167@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-01-17 17:52:29 -08:00

66 lines
1.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __ASM_GENERIC_CHECKSUM_H
#define __ASM_GENERIC_CHECKSUM_H
#include <linux/bitops.h>
/*
* 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
*/
extern __wsum csum_partial(const void *buff, int len, __wsum sum);
#ifndef ip_fast_csum
/*
* This is a version of ip_compute_csum() optimized for IP headers,
* which always checksum on 4 octet boundaries.
*/
extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
#endif
#ifndef csum_fold
/*
* Fold a partial checksum
*/
static inline __sum16 csum_fold(__wsum csum)
{
u32 sum = (__force u32)csum;
return (__force __sum16)((~sum - ror32(sum, 16)) >> 16);
}
#endif
#ifndef csum_tcpudp_nofold
/*
* computes the checksum of the TCP/UDP pseudo-header
* returns a 16-bit checksum, already complemented
*/
extern __wsum
csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
__u8 proto, __wsum sum);
#endif
#ifndef csum_tcpudp_magic
static inline __sum16
csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
__u8 proto, __wsum sum)
{
return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
}
#endif
/*
* this routine is used for miscellaneous IP-like checksums, mainly
* in icmp.c
*/
extern __sum16 ip_compute_csum(const void *buff, int len);
#endif /* __ASM_GENERIC_CHECKSUM_H */