OpenCloudOS-Kernel/arch/arm/lib/xor-neon.c

44 lines
1.2 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/arch/arm/lib/xor-neon.c
*
* Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
*/
#include <linux/raid/xor.h>
#include <linux/module.h>
MODULE_LICENSE("GPL");
#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 10:34:36 +08:00
#error You should compile this file with '-march=armv7-a -mfloat-abi=softfp -mfpu=neon'
#endif
/*
* Pull in the reference implementations while instructing GCC (through
* -ftree-vectorize) to attempt to exploit implicit parallelism and emit
* NEON instructions.
*/
#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6)
#pragma GCC optimize "tree-vectorize"
#else
/*
* While older versions of GCC do not generate incorrect code, they fail to
* recognize the parallel nature of these functions, and emit plain ARM code,
* which is known to be slower than the optimized ARM code in asm-arm/xor.h.
*/
#warning This code requires at least version 4.6 of GCC
#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,
};
EXPORT_SYMBOL(xor_block_neon_inner);