2019-06-04 10:11:33 +02:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
2013-05-17 18:51:23 +02:00
|
|
|
/*
|
|
|
|
|
* linux/arch/arm/lib/xor-neon.c
|
|
|
|
|
*
|
|
|
|
|
* Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include <linux/raid/xor.h>
|
2013-09-09 15:08:38 +01:00
|
|
|
#include <linux/module.h>
|
|
|
|
|
|
2024-07-30 07:43:18 -07:00
|
|
|
MODULE_DESCRIPTION("NEON accelerated XOR implementation");
|
2013-09-09 15:08:38 +01:00
|
|
|
MODULE_LICENSE("GPL");
|
2013-05-17 18:51:23 +02:00
|
|
|
|
|
|
|
|
#ifndef __ARM_NEON__
|
ARM: 8833/1: Ensure that NEON code always compiles with Clang
While building arm32 allyesconfig, I ran into the following errors:
arch/arm/lib/xor-neon.c:17:2: error: You should compile this file with
'-mfloat-abi=softfp -mfpu=neon'
In file included from lib/raid6/neon1.c:27:
/home/nathan/cbl/prebuilt/lib/clang/8.0.0/include/arm_neon.h:28:2:
error: "NEON support not enabled"
Building V=1 showed NEON_FLAGS getting passed along to Clang but
__ARM_NEON__ was not getting defined. Ultimately, it boils down to Clang
only defining __ARM_NEON__ when targeting armv7, rather than armv6k,
which is the '-march' value for allyesconfig.
>From lib/Basic/Targets/ARM.cpp in the Clang source:
// This only gets set when Neon instructions are actually available, unlike
// the VFP define, hence the soft float and arch check. This is subtly
// different from gcc, we follow the intent which was that it should be set
// when Neon instructions are actually available.
if ((FPU & NeonFPU) && !SoftFloat && ArchVersion >= 7) {
Builder.defineMacro("__ARM_NEON", "1");
Builder.defineMacro("__ARM_NEON__");
// current AArch32 NEON implementations do not support double-precision
// floating-point even when it is present in VFP.
Builder.defineMacro("__ARM_NEON_FP",
"0x" + Twine::utohexstr(HW_FP & ~HW_FP_DP));
}
Ard Biesheuvel recommended explicitly adding '-march=armv7-a' at the
beginning of the NEON_FLAGS definitions so that __ARM_NEON__ always gets
definined by Clang. This doesn't functionally change anything because
that code will only run where NEON is supported, which is implicitly
armv7.
Link: https://github.com/ClangBuiltLinux/linux/issues/287
Suggested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Acked-by: Nicolas Pitre <nico@linaro.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
2019-02-02 03:34:36 +01:00
|
|
|
#error You should compile this file with '-march=armv7-a -mfloat-abi=softfp -mfpu=neon'
|
2013-05-17 18:51:23 +02:00
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Pull in the reference implementations while instructing GCC (through
|
|
|
|
|
* -ftree-vectorize) to attempt to exploit implicit parallelism and emit
|
2022-02-05 16:23:46 +01:00
|
|
|
* NEON instructions. Clang does this by default at O2 so no pragma is
|
|
|
|
|
* needed.
|
2013-05-17 18:51:23 +02:00
|
|
|
*/
|
2022-02-05 16:23:46 +01:00
|
|
|
#ifdef CONFIG_CC_IS_GCC
|
2013-05-17 18:51:23 +02:00
|
|
|
#pragma GCC optimize "tree-vectorize"
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#pragma GCC diagnostic ignored "-Wunused-variable"
|
|
|
|
|
#include <asm-generic/xor.h>
|
|
|
|
|
|
|
|
|
|
struct xor_block_template const xor_block_neon_inner = {
|
|
|
|
|
.name = "__inner_neon__",
|
|
|
|
|
.do_2 = xor_8regs_2,
|
|
|
|
|
.do_3 = xor_8regs_3,
|
|
|
|
|
.do_4 = xor_8regs_4,
|
|
|
|
|
.do_5 = xor_8regs_5,
|
|
|
|
|
};
|
2013-09-09 15:08:38 +01:00
|
|
|
EXPORT_SYMBOL(xor_block_neon_inner);
|