diff options
author | Ard Biesheuvel <ard.biesheuvel@linaro.org> | 2013-05-17 18:51:23 +0200 |
---|---|---|
committer | Ard Biesheuvel <ard.biesheuvel@linaro.org> | 2013-07-08 22:09:06 +0100 |
commit | 01956597cbc46df072f20f90a40eebe356200c38 (patch) | |
tree | 5118db69af46696f057142a79827efd3e29d3ebe /arch/arm/lib | |
parent | 73c132c15da504789b924871e2491479a18e4f6a (diff) | |
download | linux-01956597cbc46df072f20f90a40eebe356200c38.tar.bz2 |
ARM: crypto: add NEON accelerated XOR implementation
Add a source file xor-neon.c (which is really just the reference
C implementation passed through the GCC vectorizer) and hook it
up to the XOR framework.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Nicolas Pitre <nico@linaro.org>
Diffstat (limited to 'arch/arm/lib')
-rw-r--r-- | arch/arm/lib/Makefile | 6 | ||||
-rw-r--r-- | arch/arm/lib/xor-neon.c | 42 |
2 files changed, 48 insertions, 0 deletions
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile index af72969820b4..aaf3a8731136 100644 --- a/arch/arm/lib/Makefile +++ b/arch/arm/lib/Makefile @@ -45,3 +45,9 @@ lib-$(CONFIG_ARCH_SHARK) += io-shark.o $(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S $(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S + +ifeq ($(CONFIG_KERNEL_MODE_NEON),y) + NEON_FLAGS := -mfloat-abi=softfp -mfpu=neon + CFLAGS_xor-neon.o += $(NEON_FLAGS) + lib-$(CONFIG_XOR_BLOCKS) += xor-neon.o +endif diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c new file mode 100644 index 000000000000..f485e5a2af4b --- /dev/null +++ b/arch/arm/lib/xor-neon.c @@ -0,0 +1,42 @@ +/* + * linux/arch/arm/lib/xor-neon.c + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * 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. + */ + +#include <linux/raid/xor.h> + +#ifndef __ARM_NEON__ +#error You should compile this file with '-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, +}; |