2 * copyright (c) 2007 Michael Niedermayer <michaelni@gmx.at>
4 * This file is part of FFmpeg.
6 * FFmpeg is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
11 * FFmpeg 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 GNU
14 * Lesser General Public License for more details.
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with FFmpeg; if not, write to the Free Software
18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
27 uint8_t round_key[15][4][4];
31 static const uint8_t rcon[30] = {
32 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80,
33 0x1b, 0x36, 0x6c, 0xd8, 0xab, 0x4d, 0x9a, 0x2f,
34 0x5e, 0xbc, 0x63, 0xc6, 0x97, 0x35, 0x6a, 0xd4,
35 0xb3, 0x7d, 0xfa, 0xef, 0xc5, 0x91
38 static uint8_t log8[256];
39 static uint8_t alog8[512];
40 static uint8_t sbox[256];
41 static uint8_t inv_sbox[256];
43 static inline void addkey(uint32_t state[4], uint32_t round_key[4]){
46 state[i] ^= round_key[i]; //partial memory stall? FIXME benchmark
49 #define SUBSHIFT0(s, box) s[0]=box[s[ 0]]; s[ 4]=box[s[ 4]]; s[ 8]=box[s[ 8]]; s[12]=box[s[12]];
50 #define SUBSHIFT1(s, box) t=s[0]; s[0]=box[s[ 4]]; s[ 4]=box[s[ 8]]; s[ 8]=box[s[12]]; s[12]=box[t];
51 #define SUBSHIFT2(s, box) t=s[0]; s[0]=box[s[ 8]]; s[ 8]=box[ t]; t=s[ 4]; s[ 4]=box[s[12]]; s[12]=box[t];
52 #define SUBSHIFT3(s, box) t=s[0]; s[0]=box[s[12]]; s[12]=box[s[ 8]]; s[ 8]=box[s[ 4]]; s[ 4]=box[t];
54 static inline int mul(int a, int b){
56 else return alog8[a+b];
59 static inline void mix(uint8_t state[4][4], int c0, int c1, int c2, int c3){
64 tmp[0][i]= log8[ state[0][i] ];
67 state[j][i]= mul( tmp[j][ i ], c0 )
68 ^mul( tmp[j][(i+ 1)&3], c1 )
69 ^mul( tmp[j][(i+ 2)&3], c2 )
70 ^mul( tmp[j][(i+ 3)&3], c3 );
74 void av_aes_decrypt(AVAES *a){
77 for(r=a->rounds-1; r>=0; r--){
79 addkey(a->state, a->round_key[r+1]);
81 mix(a->state, log8[0xe], log8[0xb], log8[0xd], log8[9]); //FIXME replace log8 by const
82 SUBSHIFT0((a->state[0]+0), inv_sbox)
83 SUBSHIFT3((a->state[0]+1), inv_sbox)
84 SUBSHIFT2((a->state[0]+2), inv_sbox)
85 SUBSHIFT1((a->state[0]+3), inv_sbox)
86 addkey(a->state, a->round_key[r]);
90 void av_aes_encrypt(AVAES *a){
93 for(r=0; r<a->rounds; r++){
94 addkey(a->state, a->round_key[r]);
95 SUBSHIFT0((a->state[0]+0), sbox)
96 SUBSHIFT1((a->state[0]+1), sbox)
97 SUBSHIFT2((a->state[0]+2), sbox)
98 SUBSHIFT3((a->state[0]+3), sbox)
100 addkey(a->state, a->round_key[r+1]);
102 mix(a->state, log8[2], log8[3], 0, 0); //FIXME replace log8 by const / optimze mix as this can be simplified alot
106 // this is based on the reference AES code by Paulo Barreto and Vincent Rijmen
107 AVAES *av_aes_init(uint8_t *key, int keyBits) {
109 int i, j, t, rconpointer = 0;
116 for(i=0; i<255; i++){
124 for(i=0; i<256; i++){
125 j= i ? alog8[255-log8[i]] : 0;
126 j ^= (j<<1) ^ (j<<2) ^ (j<<3) ^ (j<<4);
127 j = (j ^ (j>>8) ^ 99) & 255;
130 // av_log(NULL, AV_LOG_ERROR, "%d, ", log8[i]);
134 if(keyBits!=128 && keyBits!=192 && keyBits!=256)
137 a= av_malloc(sizeof(AVAES));
140 memcpy(tk, key, KC*4);
142 for(t= 0; t < (ROUNDS+1)*4; ) {
143 for(j = 0; (j < KC) && (t < (ROUNDS+1)*4); j++, t++)
144 for(i = 0; i < 4; i++)
145 a->round_key[0][t][i] = tk[j][i];
147 for(i = 0; i < 4; i++)
148 tk[0][i] ^= sbox[tk[KC-1][(i+1)&3]];
149 tk[0][0] ^= rcon[rconpointer++];
151 for(j = 1; j < KC; j++){
152 if(KC != 8 || j != KC/2)
153 for(i = 0; i < 4; i++) tk[j][i] ^= tk[j-1][i];
155 for(i = 0; i < 4; i++)
156 tk[KC/2][i] ^= sbox[tk[KC/2 - 1][i]];
166 AVAES *a= av_aes_init("PI=3.141592654..", 128);
168 for(i=0; i<10000; i++){