mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-12 13:34:10 +08:00
02436762f5
The subsequent patches of the series will have an implementation of SM4-ECB/CBC/CFB/CTR accelerated by the CE instruction set, which conflicts with the current module name. In order to keep the naming rules of the AES algorithm consistent, the sm4-ce algorithm is renamed to sm4-ce-cipher. In addition, the speed of sm4-ce-cipher is better than that of SM4 NEON. By the way, the priority of the algorithm is adjusted to 300, which is also to leave room for the priority of SM4 NEON. Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
37 lines
757 B
ArmAsm
37 lines
757 B
ArmAsm
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
#include <linux/linkage.h>
|
|
#include <asm/assembler.h>
|
|
|
|
.irp b, 0, 1, 2, 3, 4, 5, 6, 7, 8
|
|
.set .Lv\b\().4s, \b
|
|
.endr
|
|
|
|
.macro sm4e, rd, rn
|
|
.inst 0xcec08400 | .L\rd | (.L\rn << 5)
|
|
.endm
|
|
|
|
/*
|
|
* void sm4_ce_do_crypt(const u32 *rk, u32 *out, const u32 *in);
|
|
*/
|
|
.text
|
|
SYM_FUNC_START(sm4_ce_do_crypt)
|
|
ld1 {v8.4s}, [x2]
|
|
ld1 {v0.4s-v3.4s}, [x0], #64
|
|
CPU_LE( rev32 v8.16b, v8.16b )
|
|
ld1 {v4.4s-v7.4s}, [x0]
|
|
sm4e v8.4s, v0.4s
|
|
sm4e v8.4s, v1.4s
|
|
sm4e v8.4s, v2.4s
|
|
sm4e v8.4s, v3.4s
|
|
sm4e v8.4s, v4.4s
|
|
sm4e v8.4s, v5.4s
|
|
sm4e v8.4s, v6.4s
|
|
sm4e v8.4s, v7.4s
|
|
rev64 v8.4s, v8.4s
|
|
ext v8.16b, v8.16b, v8.16b, #8
|
|
CPU_LE( rev32 v8.16b, v8.16b )
|
|
st1 {v8.4s}, [x1]
|
|
ret
|
|
SYM_FUNC_END(sm4_ce_do_crypt)
|