Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 0e455d8e authored by Robin Murphy's avatar Robin Murphy Committed by Catalin Marinas
Browse files

arm64: Implement optimised IP checksum helpers



AArch64 is capable of 128-bit memory accesses without alignment
restrictions, which makes it both possible and highly practical to slurp
up a typical 20-byte IP header in just 2 loads. Implement our own
version of ip_fast_checksum() to take advantage of that, resulting in
considerably fewer instructions and memory accesses than the generic
version. We can also get more optimal code generation for csum_fold() by
defining it a slightly different way round from the generic version, so
throw that into the mix too.

Suggested-by: default avatarLuke Starrett <luke.starrett@broadcom.com>
Acked-by: default avatarLuke Starrett <luke.starrett@broadcom.com>
Signed-off-by: default avatarRobin Murphy <robin.murphy@arm.com>
Signed-off-by: default avatarCatalin Marinas <catalin.marinas@arm.com>
parent 33688abb
Loading
Loading
Loading
Loading
+0 −1
Original line number Diff line number Diff line
generic-y += bug.h
generic-y += bugs.h
generic-y += checksum.h
generic-y += clkdev.h
generic-y += cputime.h
generic-y += current.h
+51 −0
Original line number Diff line number Diff line
/*
 * Copyright (C) 2016 ARM Ltd.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
#ifndef __ASM_CHECKSUM_H
#define __ASM_CHECKSUM_H

#include <linux/types.h>

static inline __sum16 csum_fold(__wsum csum)
{
	u32 sum = (__force u32)csum;
	sum += (sum >> 16) | (sum << 16);
	return ~(__force __sum16)(sum >> 16);
}
#define csum_fold csum_fold

static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
{
	__uint128_t tmp;
	u64 sum;

	tmp = *(const __uint128_t *)iph;
	iph += 16;
	ihl -= 4;
	tmp += ((tmp >> 64) | (tmp << 64));
	sum = tmp >> 64;
	do {
		sum += *(const u32 *)iph;
		iph += 4;
	} while (--ihl);

	sum += ((sum >> 32) | (sum << 32));
	return csum_fold(sum >> 32);
}
#define ip_fast_csum ip_fast_csum

#include <asm-generic/checksum.h>

#endif	/* __ASM_CHECKSUM_H */