X-Git-Url: https://git.cryptolib.org/?a=blobdiff_plain;f=threefish256_dec_asm.S;fp=threefish256_dec_asm.S;h=e55ca6852023d6a9071e9822ec108b0ad40a140e;hb=877bd61c0f8df66c000d0f9f35d87cddc5dd0957;hp=0000000000000000000000000000000000000000;hpb=c239a90de4f9ea98d7c0f5962d200c1a6a6033d1;p=avr-crypto-lib.git diff --git a/threefish256_dec_asm.S b/threefish256_dec_asm.S new file mode 100644 index 0000000..e55ca68 --- /dev/null +++ b/threefish256_dec_asm.S @@ -0,0 +1,279 @@ +/* threefish256_enc_asm.S */ +/* + This file is part of the AVR-Crypto-Lib. + Copyright (C) 2009 Daniel Otte (daniel.otte@rub.de) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +*/ +/* + * \author Daniel Otte + * \email daniel.otte@rub.de + * \date 2009-03-16 + * \license GPLv3 or later + */ + +#include "avr-asm-macros.S" + +/******************************************************************************/ +/* +void permute_4(void* data){ + uint64_t t; + t = X(1); + X(1) = X(3); + X(3) = t; +} +void add_key_4(void* data, const threefish256_ctx_t* ctx, uint8_t s){ + X(0) -= ctx->k[(s+0)%5]; + X(1) -= ctx->k[(s+1)%5] + ctx->t[s%3]; + X(2) -= ctx->k[(s+2)%5] + ctx->t[(s+1)%3]; + X(3) -= ctx->k[(s+3)%5] + s; +} +void threefish256_dec(void* data, const threefish256_ctx_t* ctx){ + uint8_t i=0,s=18; + uint8_t r0[8] = {0x73, 0x13, 0x7b, 0x32, 0x72, 0x2b, 0x44, 0x1b}; + uint8_t r1[8] = {0x62, 0x52, 0x43, 0x24, 0x54, 0x6a, 0x34, 0x70}; + do{ + if(i%4==0){ + add_key_4(data, ctx, s); + --s; + } + permute_4(data); + threefish_invmix(data, r0[i%8]); + threefish_invmix((uint8_t*)data + 16, r1[i%8]); + ++i; + }while(i!=72); + add_key_4(data, ctx, s); +} +*/ +I = 2 +S = 3 +DATA0 = 4 +DATA1 = 5 +CTX0 = 6 +CTX1 = 7 +IDX0 = 8 +IDX1 = 9 +IDX2 = 10 +IDX3 = 11 +/* + * param data: r24:r25 + * param ctx: r22:r23 + */ +.global threefish256_dec +threefish256_dec: + push r28 + push r29 + push_range 2, 17 + movw DATA0, r24 + movw CTX0, r22 + clr I + ldi r26, 18 + mov S, r26 +1: + mov r30, I + andi r30, 0x03 + breq 2f + rjmp 4f +2: + ldi r30, lo8(threefish256_slut5) + ldi r31, hi8(threefish256_slut5) + add r30, S + adc r31, r1 + lpm IDX0, Z+ + lpm IDX1, Z+ + lpm IDX2, Z+ + lpm IDX3, Z + movw r30, CTX0 + movw r26, DATA0 + add r30, IDX0 + adc r31, r1 + rcall sub_z_from_x8 + movw r30, CTX0 + add r30, IDX1 + adc r31, r1 + rcall sub_z_from_x8 + movw r30, CTX0 + add r30, IDX2 + adc r31, r1 + rcall sub_z_from_x8 + movw r30, CTX0 + add r30, IDX3 + adc r31, r1 + rcall sub_z_from_x8 + + /* now the remaining key */ + sbiw r26, 3*8 + ldi r30, lo8(threefish256_slut3) + ldi r31, hi8(threefish256_slut3) + add r30, S + adc r31, r1 + lpm IDX0, Z+ + lpm IDX1, Z + movw r30, CTX0 + adiw r30, 5*8 + movw IDX2, r30 + add r30, IDX0 + adc r31, r1 + rcall sub_z_from_x8 + movw r30, IDX2 + add r30, IDX1 + adc r31, r1 + rcall sub_z_from_x8 + ld r0, X + sub r0, S + st X+, r0 + ld r0, X + sbc r0, r1 + st X+, r0 + ld r0, X + sbc r0, r1 + st X+, r0 + ld r0, X + sbc r0, r1 + st X+, r0 + ld r0, X + sbc r0, r1 + st X+, r0 + ld r0, X + sbc r0, r1 + st X+, r0 + ld r0, X + sbc r0, r1 + st X+, r0 + ld r0, X + adc r0, r1 + st X+, r0 + tst S + brne 3f +exit: + pop_range 2, 17 + pop r29 + pop r28 + ret +3: + dec S +4: + /* now the permutation */ + movw r26, DATA0 + adiw r26, 8 + movw r30, r26 + adiw r30, 16 + ld IDX0, X + ld IDX1, Z + st X+, IDX1 + st Z+, IDX0 + ld IDX0, X + ld IDX1, Z + st X+, IDX1 + st Z+, IDX0 + ld IDX0, X + ld IDX1, Z + st X+, IDX1 + st Z+, IDX0 + ld IDX0, X + ld IDX1, Z + st X+, IDX1 + st Z+, IDX0 + ld IDX0, X + ld IDX1, Z + st X+, IDX1 + st Z+, IDX0 + ld IDX0, X + ld IDX1, Z + st X+, IDX1 + st Z+, IDX0 + ld IDX0, X + ld IDX1, Z + st X+, IDX1 + st Z+, IDX0 + ld IDX0, X + ld IDX1, Z + st X+, IDX1 + st Z+, IDX0 + /* call mix */ + ldi r30, lo8(threefish256_rc0) + ldi r31, hi8(threefish256_rc0) + mov r26, I + andi r26, 0x07 + add r30, r26 + adc r31, r1 + lpm r22, Z + adiw r30, 8 + lpm IDX0, Z + movw r24, DATA0 + call threefish_invmix_asm /* no rcall? */ + movw r24, DATA0 + adiw r24, 16 + mov r22, IDX0 + call threefish_invmix_asm /* no rcall? */ + inc I + rjmp 1b + +threefish256_slut5: + .byte 0x00, 0x08, 0x10, 0x18, 0x20, 0x00, 0x08, 0x10 + .byte 0x18, 0x20, 0x00, 0x08, 0x10, 0x18, 0x20, 0x00 + .byte 0x08, 0x10, 0x18, 0x20, 0x00, 0x08, 0x10 +threefish256_slut3: + .byte 0x00, 0x08, 0x10, 0x00, 0x08, 0x10, 0x00, 0x08 + .byte 0x10, 0x00, 0x08, 0x10, 0x00, 0x08, 0x10, 0x00 + .byte 0x08, 0x10, 0x00, 0x08, 0x10, 0x00, 0x08 + +threefish256_rc0: .byte 0x73, 0x13, 0x7b, 0x32, 0x72, 0x2b, 0x44, 0x1b +threefish256_rc1: .byte 0x62, 0x52, 0x43, 0x24, 0x54, 0x6a, 0x34, 0x70 + +sub_z_from_x8: + ld r0, Z+ + ld r1, X + sub r1, r0 + st X+, r1 + ld r0, Z+ + ld r1, X + sbc r1, r0 + st X+, r1 + ld r0, Z+ + ld r1, X + sbc r1, r0 + st X+, r1 + ld r0, Z+ + ld r1, X + sbc r1, r0 + st X+, r1 + ld r0, Z+ + ld r1, X + sbc r1, r0 + st X+, r1 + ld r0, Z+ + ld r1, X + sbc r1, r0 + st X+, r1 + ld r0, Z+ + ld r1, X + sbc r1, r0 + st X+, r1 + ld r0, Z+ + ld r1, X + sbc r1, r0 + st X+, r1 + clr r1 + ret + + + + + + + + + +