297565aa22
Modern compilers are perfectly capable of extracting parallelism from the XOR routines, provided that the prototypes reflect the nature of the input accurately, in particular, the fact that the input vectors are expected not to overlap. This is not documented explicitly, but is implied by the interchangeability of the various C routines, some of which use temporary variables while others don't: this means that these routines only behave identically for non-overlapping inputs. So let's decorate these input vectors with the __restrict modifier, which informs the compiler that there is no overlap. While at it, make the input-only vectors pointer-to-const as well. Tested-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Link: https://github.com/ClangBuiltLinux/linux/issues/563 Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
80 lines
2.7 KiB
C
80 lines
2.7 KiB
C
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
/*
|
|
* include/asm/xor.h
|
|
*
|
|
* High speed xor_block operation for RAID4/5 utilizing the
|
|
* UltraSparc Visual Instruction Set and Niagara block-init
|
|
* twin-load instructions.
|
|
*
|
|
* Copyright (C) 1997, 1999 Jakub Jelinek (jj@ultra.linux.cz)
|
|
* Copyright (C) 2006 David S. Miller <davem@davemloft.net>
|
|
*/
|
|
|
|
#include <asm/spitfire.h>
|
|
|
|
void xor_vis_2(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2);
|
|
void xor_vis_3(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3);
|
|
void xor_vis_4(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4);
|
|
void xor_vis_5(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4,
|
|
const unsigned long * __restrict p5);
|
|
|
|
/* XXX Ugh, write cheetah versions... -DaveM */
|
|
|
|
static struct xor_block_template xor_block_VIS = {
|
|
.name = "VIS",
|
|
.do_2 = xor_vis_2,
|
|
.do_3 = xor_vis_3,
|
|
.do_4 = xor_vis_4,
|
|
.do_5 = xor_vis_5,
|
|
};
|
|
|
|
void xor_niagara_2(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2);
|
|
void xor_niagara_3(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3);
|
|
void xor_niagara_4(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4);
|
|
void xor_niagara_5(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4,
|
|
const unsigned long * __restrict p5);
|
|
|
|
static struct xor_block_template xor_block_niagara = {
|
|
.name = "Niagara",
|
|
.do_2 = xor_niagara_2,
|
|
.do_3 = xor_niagara_3,
|
|
.do_4 = xor_niagara_4,
|
|
.do_5 = xor_niagara_5,
|
|
};
|
|
|
|
#undef XOR_TRY_TEMPLATES
|
|
#define XOR_TRY_TEMPLATES \
|
|
do { \
|
|
xor_speed(&xor_block_VIS); \
|
|
xor_speed(&xor_block_niagara); \
|
|
} while (0)
|
|
|
|
/* For VIS for everything except Niagara. */
|
|
#define XOR_SELECT_TEMPLATE(FASTEST) \
|
|
((tlb_type == hypervisor && \
|
|
(sun4v_chip_type == SUN4V_CHIP_NIAGARA1 || \
|
|
sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || \
|
|
sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || \
|
|
sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || \
|
|
sun4v_chip_type == SUN4V_CHIP_NIAGARA5)) ? \
|
|
&xor_block_niagara : \
|
|
&xor_block_VIS)
|