3 This file is part of the ARM-Crypto-Lib.
4 Copyright (C) 2006-2011 Daniel Otte (daniel.otte@rub.de)
6 This program is free software: you can redistribute it and/or modify
7 it under the terms of the GNU General Public License as published by
8 the Free Software Foundation, either version 3 of the License, or
9 (at your option) any later version.
11 This program is distributed in the hope that it will be useful,
12 but WITHOUT ANY WARRANTY; without even the implied warranty of
13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 GNU General Public License for more details.
16 You should have received a copy of the GNU General Public License
17 along with this program. If not, see <http://www.gnu.org/licenses/>.
25 #define ROTL32(a,n) (((a)<<(n))|((a)>>(32-(n))))
28 void quaterround(uint32_t* a, uint32_t* b, uint32_t* c, uint32_t* d){
29 *b ^= ROTL32(*a + *d, 7);
30 *c ^= ROTL32(*b + *a, 9);
31 *d ^= ROTL32(*c + *b, 13);
32 *a ^= ROTL32(*d + *c, 18);
36 void rowround(uint32_t* a){
37 quaterround(a+ 0, a+ 1, a+ 2, a+ 3);
38 quaterround(a+ 5, a+ 6, a+ 7, a+ 4);
39 quaterround(a+10, a+11, a+ 8, a+ 9);
40 quaterround(a+15, a+12, a+13, a+14);
44 void columnround(uint32_t* a){
45 quaterround(a+ 0, a+ 4, a+ 8, a+12);
46 quaterround(a+ 5, a+ 9, a+13, a+ 1);
47 quaterround(a+10, a+14, a+ 2, a+ 6);
48 quaterround(a+15, a+ 3, a+ 7, a+11);
52 void doubleround(uint32_t* a){
59 void salsa20_hash(uint32_t* a){
71 uint8_t sigma[] = {'e','x','p','a','n','d',' ','3','2','-','b','y','t','e',' ','k'};
72 uint8_t theta[] = {'e','x','p','a','n','d',' ','1','6','-','b','y','t','e',' ','k'};
74 void salsa_k32(uint32_t* dest, const uint32_t* k, const uint32_t* n){
75 memcpy(dest+ 0, sigma+ 0, 4);
76 memcpy(dest+ 4, k+ 0, 16);
77 memcpy(dest+20, sigma+ 4, 4);
78 memcpy(dest+24, n+ 0, 16);
79 memcpy(dest+40, sigma+ 8, 4);
80 memcpy(dest+44, k+16, 16);
81 memcpy(dest+60, sigma+12, 4);
85 void salsa_k16(uint32_t* dest, const uint32_t* k, const uint32_t* n){
86 memcpy(dest+ 0, theta+ 0, 4);
87 memcpy(dest+ 4, k+ 0, 16);
88 memcpy(dest+20, theta+ 4, 4);
89 memcpy(dest+24, n+ 0, 16);
90 memcpy(dest+40, theta+ 8, 4);
91 memcpy(dest+44, k+ 0, 16);
92 memcpy(dest+60, theta+12, 4);
96 void salsa20_genBlock256(void* dest, const void* k, const void* iv, uint64_t i){
99 //? memcpy(n+8, &i, 8);
100 salsa_k32((uint32_t*)dest, (uint32_t*)k, n);
103 void salsa20_genBlock128(void* dest, const void* k, const void* iv, uint64_t i){
106 //? memcpy(n+8, &i, 8);
107 salsa_k16((uint32_t*)dest, (uint32_t*)k, n);
111 void salsa20_init(void* key, uint16_t keylength_b, void* iv, salsa20_ctx_t* ctx){
112 if(keylength_b==256){
113 memcpy((ctx->a.v8+ 0), sigma+ 0, 4);
114 memcpy((ctx->a.v8+20), sigma+ 4, 4);
115 memcpy((ctx->a.v8+40), sigma+ 8, 4);
116 memcpy((ctx->a.v8+44), (uint8_t*)key+16, 16);
117 memcpy((ctx->a.v8+60), sigma+12, 4);
119 memcpy((ctx->a.v8+ 0), theta+ 0, 4);
120 memcpy((ctx->a.v8+20), theta+ 4, 4);
121 memcpy((ctx->a.v8+40), theta+ 8, 4);
122 memcpy((ctx->a.v8+44), (uint8_t*)key+ 0, 16);
123 memcpy((ctx->a.v8+60), theta+12, 4);
125 memcpy((ctx->a.v8+ 4), key, 16);
126 memset((ctx->a.v8+24), 0, 16);
128 memcpy((ctx->a.v8+24), iv, 8);
133 uint8_t salsa20_gen(salsa20_ctx_t* ctx){
134 if(ctx->buffer_idx==64){
135 memcpy(ctx->buffer, ctx->a.v8, 64);
136 salsa20_hash((uint32_t*)(ctx->buffer));
140 return ctx->buffer[ctx->buffer_idx++];