diff options
| author | Jackie Liu <liuyun01@kylinos.cn> | 2018-12-04 09:43:23 +0800 |
|---|---|---|
| committer | Will Deacon <will.deacon@arm.com> | 2018-12-06 16:47:06 +0000 |
| commit | cc9f8349cb33965120a96c12e05d00676162eb7f (patch) | |
| tree | c618ea48cc0367c26fac7a84f3aa73228ba971be /arch/arm64/include/asm/xor.h | |
| parent | 21e28547f613e7ba4f4cb6831a3ead2d723fdf7b (diff) | |
arm64: crypto: add NEON accelerated XOR implementation
This is a NEON acceleration method that can improve
performance by approximately 20%. I got the following
data from the centos 7.5 on Huawei's HISI1616 chip:
[ 93.837726] xor: measuring software checksum speed
[ 93.874039] 8regs : 7123.200 MB/sec
[ 93.914038] 32regs : 7180.300 MB/sec
[ 93.954043] arm64_neon: 9856.000 MB/sec
[ 93.954047] xor: using function: arm64_neon (9856.000 MB/sec)
I believe this code can bring some optimization for
all arm64 platform. thanks for Ard Biesheuvel's suggestions.
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Diffstat (limited to 'arch/arm64/include/asm/xor.h')
| -rw-r--r-- | arch/arm64/include/asm/xor.h | 73 |
1 files changed, 73 insertions, 0 deletions
diff --git a/arch/arm64/include/asm/xor.h b/arch/arm64/include/asm/xor.h new file mode 100644 index 000000000000..856386ad076c --- /dev/null +++ b/arch/arm64/include/asm/xor.h @@ -0,0 +1,73 @@ +/* + * arch/arm64/include/asm/xor.h + * + * Authors: Jackie Liu <liuyun01@kylinos.cn> + * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd. + * + * 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/hardirq.h> +#include <asm-generic/xor.h> +#include <asm/hwcap.h> +#include <asm/neon.h> + +#ifdef CONFIG_KERNEL_MODE_NEON + +extern struct xor_block_template const xor_block_inner_neon; + +static void +xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +{ + kernel_neon_begin(); + xor_block_inner_neon.do_2(bytes, p1, p2); + kernel_neon_end(); +} + +static void +xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3) +{ + kernel_neon_begin(); + xor_block_inner_neon.do_3(bytes, p1, p2, p3); + kernel_neon_end(); +} + +static void +xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4) +{ + kernel_neon_begin(); + xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4); + kernel_neon_end(); +} + +static void +xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4, unsigned long *p5) +{ + kernel_neon_begin(); + xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5); + kernel_neon_end(); +} + +static struct xor_block_template xor_block_arm64 = { + .name = "arm64_neon", + .do_2 = xor_neon_2, + .do_3 = xor_neon_3, + .do_4 = xor_neon_4, + .do_5 = xor_neon_5 +}; +#undef XOR_TRY_TEMPLATES +#define XOR_TRY_TEMPLATES \ + do { \ + xor_speed(&xor_block_8regs); \ + xor_speed(&xor_block_32regs); \ + if (cpu_has_neon()) { \ + xor_speed(&xor_block_arm64);\ + } \ + } while (0) + +#endif /* ! CONFIG_KERNEL_MODE_NEON */ |