142 lines
3.3 KiB
ArmAsm
142 lines
3.3 KiB
ArmAsm
/*
|
|
* sm3-ce-core.S - SM3 secure hash using ARMv8.2 Crypto Extensions
|
|
*
|
|
* Copyright (C) 2018 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/linkage.h>
|
|
#include <asm/assembler.h>
|
|
|
|
.irp b, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
|
|
.set .Lv\b\().4s, \b
|
|
.endr
|
|
|
|
.macro sm3partw1, rd, rn, rm
|
|
.inst 0xce60c000 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
|
|
.endm
|
|
|
|
.macro sm3partw2, rd, rn, rm
|
|
.inst 0xce60c400 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
|
|
.endm
|
|
|
|
.macro sm3ss1, rd, rn, rm, ra
|
|
.inst 0xce400000 | .L\rd | (.L\rn << 5) | (.L\ra << 10) | (.L\rm << 16)
|
|
.endm
|
|
|
|
.macro sm3tt1a, rd, rn, rm, imm2
|
|
.inst 0xce408000 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
|
|
.endm
|
|
|
|
.macro sm3tt1b, rd, rn, rm, imm2
|
|
.inst 0xce408400 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
|
|
.endm
|
|
|
|
.macro sm3tt2a, rd, rn, rm, imm2
|
|
.inst 0xce408800 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
|
|
.endm
|
|
|
|
.macro sm3tt2b, rd, rn, rm, imm2
|
|
.inst 0xce408c00 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
|
|
.endm
|
|
|
|
.macro round, ab, s0, t0, t1, i
|
|
sm3ss1 v5.4s, v8.4s, \t0\().4s, v9.4s
|
|
shl \t1\().4s, \t0\().4s, #1
|
|
sri \t1\().4s, \t0\().4s, #31
|
|
sm3tt1\ab v8.4s, v5.4s, v10.4s, \i
|
|
sm3tt2\ab v9.4s, v5.4s, \s0\().4s, \i
|
|
.endm
|
|
|
|
.macro qround, ab, s0, s1, s2, s3, s4
|
|
.ifnb \s4
|
|
ext \s4\().16b, \s1\().16b, \s2\().16b, #12
|
|
ext v6.16b, \s0\().16b, \s1\().16b, #12
|
|
ext v7.16b, \s2\().16b, \s3\().16b, #8
|
|
sm3partw1 \s4\().4s, \s0\().4s, \s3\().4s
|
|
.endif
|
|
|
|
eor v10.16b, \s0\().16b, \s1\().16b
|
|
|
|
round \ab, \s0, v11, v12, 0
|
|
round \ab, \s0, v12, v11, 1
|
|
round \ab, \s0, v11, v12, 2
|
|
round \ab, \s0, v12, v11, 3
|
|
|
|
.ifnb \s4
|
|
sm3partw2 \s4\().4s, v7.4s, v6.4s
|
|
.endif
|
|
.endm
|
|
|
|
/*
|
|
* void sm3_ce_transform(struct sm3_state *sst, u8 const *src,
|
|
* int blocks)
|
|
*/
|
|
.text
|
|
ENTRY(sm3_ce_transform)
|
|
/* load state */
|
|
ld1 {v8.4s-v9.4s}, [x0]
|
|
rev64 v8.4s, v8.4s
|
|
rev64 v9.4s, v9.4s
|
|
ext v8.16b, v8.16b, v8.16b, #8
|
|
ext v9.16b, v9.16b, v9.16b, #8
|
|
|
|
adr_l x8, .Lt
|
|
ldp s13, s14, [x8]
|
|
|
|
/* load input */
|
|
0: ld1 {v0.16b-v3.16b}, [x1], #64
|
|
sub w2, w2, #1
|
|
|
|
mov v15.16b, v8.16b
|
|
mov v16.16b, v9.16b
|
|
|
|
CPU_LE( rev32 v0.16b, v0.16b )
|
|
CPU_LE( rev32 v1.16b, v1.16b )
|
|
CPU_LE( rev32 v2.16b, v2.16b )
|
|
CPU_LE( rev32 v3.16b, v3.16b )
|
|
|
|
ext v11.16b, v13.16b, v13.16b, #4
|
|
|
|
qround a, v0, v1, v2, v3, v4
|
|
qround a, v1, v2, v3, v4, v0
|
|
qround a, v2, v3, v4, v0, v1
|
|
qround a, v3, v4, v0, v1, v2
|
|
|
|
ext v11.16b, v14.16b, v14.16b, #4
|
|
|
|
qround b, v4, v0, v1, v2, v3
|
|
qround b, v0, v1, v2, v3, v4
|
|
qround b, v1, v2, v3, v4, v0
|
|
qround b, v2, v3, v4, v0, v1
|
|
qround b, v3, v4, v0, v1, v2
|
|
qround b, v4, v0, v1, v2, v3
|
|
qround b, v0, v1, v2, v3, v4
|
|
qround b, v1, v2, v3, v4, v0
|
|
qround b, v2, v3, v4, v0, v1
|
|
qround b, v3, v4
|
|
qround b, v4, v0
|
|
qround b, v0, v1
|
|
|
|
eor v8.16b, v8.16b, v15.16b
|
|
eor v9.16b, v9.16b, v16.16b
|
|
|
|
/* handled all input blocks? */
|
|
cbnz w2, 0b
|
|
|
|
/* save state */
|
|
rev64 v8.4s, v8.4s
|
|
rev64 v9.4s, v9.4s
|
|
ext v8.16b, v8.16b, v8.16b, #8
|
|
ext v9.16b, v9.16b, v9.16b, #8
|
|
st1 {v8.4s-v9.4s}, [x0]
|
|
ret
|
|
ENDPROC(sm3_ce_transform)
|
|
|
|
.section ".rodata", "a"
|
|
.align 3
|
|
.Lt: .word 0x79cc4519, 0x9d8a7a87
|