linux/lib/raid/xor/loongarch/xor_simd.c
Christoph Hellwig 033bee3e49 loongarch: move the XOR code to lib/raid/
Move the optimized XOR into lib/raid and include it it in xor.ko instead
of always building it into the main kernel image.

Link: https://lkml.kernel.org/r/20260327061704.3707577-15-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Eric Biggers <ebiggers@kernel.org>
Tested-by: Eric Biggers <ebiggers@kernel.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "Borislav Petkov (AMD)" <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Mason <clm@fb.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: David Sterba <dsterba@suse.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason A. Donenfeld <jason@zx2c4.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Li Nan <linan122@huawei.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Magnus Lindholm <linmag7@gmail.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Richard Weinberger <richard@nod.at>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Song Liu <song@kernel.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Ted Ts'o <tytso@mit.edu>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2026-04-02 23:36:18 -07:00

94 lines
1.9 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* LoongArch SIMD XOR operations
*
* Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
*/
#include "xor_simd.h"
/*
* Process one cache line (64 bytes) per loop. This is assuming all future
* popular LoongArch cores are similar performance-characteristics-wise to the
* current models.
*/
#define LINE_WIDTH 64
#ifdef CONFIG_CPU_HAS_LSX
#define LD(reg, base, offset) \
"vld $vr" #reg ", %[" #base "], " #offset "\n\t"
#define ST(reg, base, offset) \
"vst $vr" #reg ", %[" #base "], " #offset "\n\t"
#define XOR(dj, k) "vxor.v $vr" #dj ", $vr" #dj ", $vr" #k "\n\t"
#define LD_INOUT_LINE(base) \
LD(0, base, 0) \
LD(1, base, 16) \
LD(2, base, 32) \
LD(3, base, 48)
#define LD_AND_XOR_LINE(base) \
LD(4, base, 0) \
LD(5, base, 16) \
LD(6, base, 32) \
LD(7, base, 48) \
XOR(0, 4) \
XOR(1, 5) \
XOR(2, 6) \
XOR(3, 7)
#define ST_LINE(base) \
ST(0, base, 0) \
ST(1, base, 16) \
ST(2, base, 32) \
ST(3, base, 48)
#define XOR_FUNC_NAME(nr) __xor_lsx_##nr
#include "xor_template.c"
#undef LD
#undef ST
#undef XOR
#undef LD_INOUT_LINE
#undef LD_AND_XOR_LINE
#undef ST_LINE
#undef XOR_FUNC_NAME
#endif /* CONFIG_CPU_HAS_LSX */
#ifdef CONFIG_CPU_HAS_LASX
#define LD(reg, base, offset) \
"xvld $xr" #reg ", %[" #base "], " #offset "\n\t"
#define ST(reg, base, offset) \
"xvst $xr" #reg ", %[" #base "], " #offset "\n\t"
#define XOR(dj, k) "xvxor.v $xr" #dj ", $xr" #dj ", $xr" #k "\n\t"
#define LD_INOUT_LINE(base) \
LD(0, base, 0) \
LD(1, base, 32)
#define LD_AND_XOR_LINE(base) \
LD(2, base, 0) \
LD(3, base, 32) \
XOR(0, 2) \
XOR(1, 3)
#define ST_LINE(base) \
ST(0, base, 0) \
ST(1, base, 32)
#define XOR_FUNC_NAME(nr) __xor_lasx_##nr
#include "xor_template.c"
#undef LD
#undef ST
#undef XOR
#undef LD_INOUT_LINE
#undef LD_AND_XOR_LINE
#undef ST_LINE
#undef XOR_FUNC_NAME
#endif /* CONFIG_CPU_HAS_LASX */