1 /* 2 * Copyright (c) 2016 Thomas Pornin <pornin@bolet.org> 3 * 4 * Permission is hereby granted, free of charge, to any person obtaining 5 * a copy of this software and associated documentation files (the 6 * "Software"), to deal in the Software without restriction, including 7 * without limitation the rights to use, copy, modify, merge, publish, 8 * distribute, sublicense, and/or sell copies of the Software, and to 9 * permit persons to whom the Software is furnished to do so, subject to 10 * the following conditions: 11 * 12 * The above copyright notice and this permission notice shall be 13 * included in all copies or substantial portions of the Software. 14 * 15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 16 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 17 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND 18 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS 19 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN 20 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN 21 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 22 * SOFTWARE. 23 */ 24 25 #include "inner.h" 26 27 /* 28 * Inverse S-box. 29 */ 30 static const unsigned char iS[] = { 31 0x52, 0x09, 0x6A, 0xD5, 0x30, 0x36, 0xA5, 0x38, 0xBF, 0x40, 0xA3, 0x9E, 32 0x81, 0xF3, 0xD7, 0xFB, 0x7C, 0xE3, 0x39, 0x82, 0x9B, 0x2F, 0xFF, 0x87, 33 0x34, 0x8E, 0x43, 0x44, 0xC4, 0xDE, 0xE9, 0xCB, 0x54, 0x7B, 0x94, 0x32, 34 0xA6, 0xC2, 0x23, 0x3D, 0xEE, 0x4C, 0x95, 0x0B, 0x42, 0xFA, 0xC3, 0x4E, 35 0x08, 0x2E, 0xA1, 0x66, 0x28, 0xD9, 0x24, 0xB2, 0x76, 0x5B, 0xA2, 0x49, 36 0x6D, 0x8B, 0xD1, 0x25, 0x72, 0xF8, 0xF6, 0x64, 0x86, 0x68, 0x98, 0x16, 37 0xD4, 0xA4, 0x5C, 0xCC, 0x5D, 0x65, 0xB6, 0x92, 0x6C, 0x70, 0x48, 0x50, 38 0xFD, 0xED, 0xB9, 0xDA, 0x5E, 0x15, 0x46, 0x57, 0xA7, 0x8D, 0x9D, 0x84, 39 0x90, 0xD8, 0xAB, 0x00, 0x8C, 0xBC, 0xD3, 0x0A, 0xF7, 0xE4, 0x58, 0x05, 40 0xB8, 0xB3, 0x45, 0x06, 0xD0, 0x2C, 0x1E, 0x8F, 0xCA, 0x3F, 0x0F, 0x02, 41 0xC1, 0xAF, 0xBD, 0x03, 0x01, 0x13, 0x8A, 0x6B, 0x3A, 0x91, 0x11, 0x41, 42 0x4F, 0x67, 0xDC, 0xEA, 0x97, 0xF2, 0xCF, 0xCE, 0xF0, 0xB4, 0xE6, 0x73, 43 0x96, 0xAC, 0x74, 0x22, 0xE7, 0xAD, 0x35, 0x85, 0xE2, 0xF9, 0x37, 0xE8, 44 0x1C, 0x75, 0xDF, 0x6E, 0x47, 0xF1, 0x1A, 0x71, 0x1D, 0x29, 0xC5, 0x89, 45 0x6F, 0xB7, 0x62, 0x0E, 0xAA, 0x18, 0xBE, 0x1B, 0xFC, 0x56, 0x3E, 0x4B, 46 0xC6, 0xD2, 0x79, 0x20, 0x9A, 0xDB, 0xC0, 0xFE, 0x78, 0xCD, 0x5A, 0xF4, 47 0x1F, 0xDD, 0xA8, 0x33, 0x88, 0x07, 0xC7, 0x31, 0xB1, 0x12, 0x10, 0x59, 48 0x27, 0x80, 0xEC, 0x5F, 0x60, 0x51, 0x7F, 0xA9, 0x19, 0xB5, 0x4A, 0x0D, 49 0x2D, 0xE5, 0x7A, 0x9F, 0x93, 0xC9, 0x9C, 0xEF, 0xA0, 0xE0, 0x3B, 0x4D, 50 0xAE, 0x2A, 0xF5, 0xB0, 0xC8, 0xEB, 0xBB, 0x3C, 0x83, 0x53, 0x99, 0x61, 51 0x17, 0x2B, 0x04, 0x7E, 0xBA, 0x77, 0xD6, 0x26, 0xE1, 0x69, 0x14, 0x63, 52 0x55, 0x21, 0x0C, 0x7D 53 }; 54 55 static void 56 add_round_key(unsigned *state, const uint32_t *skeys) 57 { 58 int i; 59 60 for (i = 0; i < 16; i += 4) { 61 uint32_t k; 62 63 k = *skeys ++; 64 state[i + 0] ^= (unsigned)(k >> 24); 65 state[i + 1] ^= (unsigned)(k >> 16) & 0xFF; 66 state[i + 2] ^= (unsigned)(k >> 8) & 0xFF; 67 state[i + 3] ^= (unsigned)k & 0xFF; 68 } 69 } 70 71 static void 72 inv_sub_bytes(unsigned *state) 73 { 74 int i; 75 76 for (i = 0; i < 16; i ++) { 77 state[i] = iS[state[i]]; 78 } 79 } 80 81 static void 82 inv_shift_rows(unsigned *state) 83 { 84 unsigned tmp; 85 86 tmp = state[13]; 87 state[13] = state[9]; 88 state[9] = state[5]; 89 state[5] = state[1]; 90 state[1] = tmp; 91 92 tmp = state[2]; 93 state[2] = state[10]; 94 state[10] = tmp; 95 tmp = state[6]; 96 state[6] = state[14]; 97 state[14] = tmp; 98 99 tmp = state[3]; 100 state[3] = state[7]; 101 state[7] = state[11]; 102 state[11] = state[15]; 103 state[15] = tmp; 104 } 105 106 static inline unsigned 107 gf256red(unsigned x) 108 { 109 unsigned y; 110 111 y = x >> 8; 112 return (x ^ y ^ (y << 1) ^ (y << 3) ^ (y << 4)) & 0xFF; 113 } 114 115 static void 116 inv_mix_columns(unsigned *state) 117 { 118 int i; 119 120 for (i = 0; i < 16; i += 4) { 121 unsigned s0, s1, s2, s3; 122 unsigned t0, t1, t2, t3; 123 124 s0 = state[i + 0]; 125 s1 = state[i + 1]; 126 s2 = state[i + 2]; 127 s3 = state[i + 3]; 128 t0 = (s0 << 1) ^ (s0 << 2) ^ (s0 << 3) 129 ^ s1 ^ (s1 << 1) ^ (s1 << 3) 130 ^ s2 ^ (s2 << 2) ^ (s2 << 3) 131 ^ s3 ^ (s3 << 3); 132 t1 = s0 ^ (s0 << 3) 133 ^ (s1 << 1) ^ (s1 << 2) ^ (s1 << 3) 134 ^ s2 ^ (s2 << 1) ^ (s2 << 3) 135 ^ s3 ^ (s3 << 2) ^ (s3 << 3); 136 t2 = s0 ^ (s0 << 2) ^ (s0 << 3) 137 ^ s1 ^ (s1 << 3) 138 ^ (s2 << 1) ^ (s2 << 2) ^ (s2 << 3) 139 ^ s3 ^ (s3 << 1) ^ (s3 << 3); 140 t3 = s0 ^ (s0 << 1) ^ (s0 << 3) 141 ^ s1 ^ (s1 << 2) ^ (s1 << 3) 142 ^ s2 ^ (s2 << 3) 143 ^ (s3 << 1) ^ (s3 << 2) ^ (s3 << 3); 144 state[i + 0] = gf256red(t0); 145 state[i + 1] = gf256red(t1); 146 state[i + 2] = gf256red(t2); 147 state[i + 3] = gf256red(t3); 148 } 149 } 150 151 /* see inner.h */ 152 void 153 br_aes_small_decrypt(unsigned num_rounds, const uint32_t *skey, void *data) 154 { 155 unsigned char *buf; 156 unsigned state[16]; 157 unsigned u; 158 159 buf = data; 160 for (u = 0; u < 16; u ++) { 161 state[u] = buf[u]; 162 } 163 add_round_key(state, skey + (num_rounds << 2)); 164 for (u = num_rounds - 1; u > 0; u --) { 165 inv_shift_rows(state); 166 inv_sub_bytes(state); 167 add_round_key(state, skey + (u << 2)); 168 inv_mix_columns(state); 169 } 170 inv_shift_rows(state); 171 inv_sub_bytes(state); 172 add_round_key(state, skey); 173 for (u = 0; u < 16; u ++) { 174 buf[u] = state[u]; 175 } 176 } 177