X-Git-Url: https://git.openssl.org/gitweb/?a=blobdiff_plain;f=crypto%2Faes%2Faes_core.c;h=ef0fc51d952ff93c18fed34768257381fe09db66;hb=44c8a5e2b9af8909844cc002c53049311634b314;hp=734821e115367d5bb54a99d27b9374774bb18192;hpb=20ab8b4b4141fa10fac7ff984b54172df6824dc2;p=openssl.git diff --git a/crypto/aes/aes_core.c b/crypto/aes/aes_core.c index 734821e115..ef0fc51d95 100644 --- a/crypto/aes/aes_core.c +++ b/crypto/aes/aes_core.c @@ -1,4 +1,12 @@ -/* crypto/aes/aes_core.c -*- mode:C; c-file-style: "eay" -*- */ +/* + * Copyright 2002-2016 The OpenSSL Project Authors. All Rights Reserved. + * + * Licensed under the OpenSSL license (the "License"). You may not use + * this file except in compliance with the License. You can obtain a copy + * in the file LICENSE in the source distribution or at + * https://www.openssl.org/source/license.html + */ + /** * rijndael-alg-fst.c * @@ -28,29 +36,25 @@ /* Note: rewritten a little bit to provide error control and an OpenSSL- compatible API */ -#ifndef AES_DEBUG -# ifndef NDEBUG -# define NDEBUG -# endif -#endif #include #include +#include #include #include "aes_locl.h" -/* +#ifndef AES_ASM +/*- Te0[x] = S [x].[02, 01, 01, 03]; Te1[x] = S [x].[03, 02, 01, 01]; Te2[x] = S [x].[01, 03, 02, 01]; Te3[x] = S [x].[01, 01, 03, 02]; -Te4[x] = S [x].[01, 01, 01, 01]; Td0[x] = Si[x].[0e, 09, 0d, 0b]; Td1[x] = Si[x].[0b, 0e, 09, 0d]; Td2[x] = Si[x].[0d, 0b, 0e, 09]; Td3[x] = Si[x].[09, 0d, 0b, 0e]; -Td4[x] = Si[x].[01, 01, 01, 01]; +Td4[x] = Si[x].[01]; */ static const u32 Te0[256] = { @@ -317,72 +321,6 @@ static const u32 Te3[256] = { 0x4141c382U, 0x9999b029U, 0x2d2d775aU, 0x0f0f111eU, 0xb0b0cb7bU, 0x5454fca8U, 0xbbbbd66dU, 0x16163a2cU, }; -static const u32 Te4[256] = { - 0x63636363U, 0x7c7c7c7cU, 0x77777777U, 0x7b7b7b7bU, - 0xf2f2f2f2U, 0x6b6b6b6bU, 0x6f6f6f6fU, 0xc5c5c5c5U, - 0x30303030U, 0x01010101U, 0x67676767U, 0x2b2b2b2bU, - 0xfefefefeU, 0xd7d7d7d7U, 0xababababU, 0x76767676U, - 0xcacacacaU, 0x82828282U, 0xc9c9c9c9U, 0x7d7d7d7dU, - 0xfafafafaU, 0x59595959U, 0x47474747U, 0xf0f0f0f0U, - 0xadadadadU, 0xd4d4d4d4U, 0xa2a2a2a2U, 0xafafafafU, - 0x9c9c9c9cU, 0xa4a4a4a4U, 0x72727272U, 0xc0c0c0c0U, - 0xb7b7b7b7U, 0xfdfdfdfdU, 0x93939393U, 0x26262626U, - 0x36363636U, 0x3f3f3f3fU, 0xf7f7f7f7U, 0xccccccccU, - 0x34343434U, 0xa5a5a5a5U, 0xe5e5e5e5U, 0xf1f1f1f1U, - 0x71717171U, 0xd8d8d8d8U, 0x31313131U, 0x15151515U, - 0x04040404U, 0xc7c7c7c7U, 0x23232323U, 0xc3c3c3c3U, - 0x18181818U, 0x96969696U, 0x05050505U, 0x9a9a9a9aU, - 0x07070707U, 0x12121212U, 0x80808080U, 0xe2e2e2e2U, - 0xebebebebU, 0x27272727U, 0xb2b2b2b2U, 0x75757575U, - 0x09090909U, 0x83838383U, 0x2c2c2c2cU, 0x1a1a1a1aU, - 0x1b1b1b1bU, 0x6e6e6e6eU, 0x5a5a5a5aU, 0xa0a0a0a0U, - 0x52525252U, 0x3b3b3b3bU, 0xd6d6d6d6U, 0xb3b3b3b3U, - 0x29292929U, 0xe3e3e3e3U, 0x2f2f2f2fU, 0x84848484U, - 0x53535353U, 0xd1d1d1d1U, 0x00000000U, 0xededededU, - 0x20202020U, 0xfcfcfcfcU, 0xb1b1b1b1U, 0x5b5b5b5bU, - 0x6a6a6a6aU, 0xcbcbcbcbU, 0xbebebebeU, 0x39393939U, - 0x4a4a4a4aU, 0x4c4c4c4cU, 0x58585858U, 0xcfcfcfcfU, - 0xd0d0d0d0U, 0xefefefefU, 0xaaaaaaaaU, 0xfbfbfbfbU, - 0x43434343U, 0x4d4d4d4dU, 0x33333333U, 0x85858585U, - 0x45454545U, 0xf9f9f9f9U, 0x02020202U, 0x7f7f7f7fU, - 0x50505050U, 0x3c3c3c3cU, 0x9f9f9f9fU, 0xa8a8a8a8U, - 0x51515151U, 0xa3a3a3a3U, 0x40404040U, 0x8f8f8f8fU, - 0x92929292U, 0x9d9d9d9dU, 0x38383838U, 0xf5f5f5f5U, - 0xbcbcbcbcU, 0xb6b6b6b6U, 0xdadadadaU, 0x21212121U, - 0x10101010U, 0xffffffffU, 0xf3f3f3f3U, 0xd2d2d2d2U, - 0xcdcdcdcdU, 0x0c0c0c0cU, 0x13131313U, 0xececececU, - 0x5f5f5f5fU, 0x97979797U, 0x44444444U, 0x17171717U, - 0xc4c4c4c4U, 0xa7a7a7a7U, 0x7e7e7e7eU, 0x3d3d3d3dU, - 0x64646464U, 0x5d5d5d5dU, 0x19191919U, 0x73737373U, - 0x60606060U, 0x81818181U, 0x4f4f4f4fU, 0xdcdcdcdcU, - 0x22222222U, 0x2a2a2a2aU, 0x90909090U, 0x88888888U, - 0x46464646U, 0xeeeeeeeeU, 0xb8b8b8b8U, 0x14141414U, - 0xdedededeU, 0x5e5e5e5eU, 0x0b0b0b0bU, 0xdbdbdbdbU, - 0xe0e0e0e0U, 0x32323232U, 0x3a3a3a3aU, 0x0a0a0a0aU, - 0x49494949U, 0x06060606U, 0x24242424U, 0x5c5c5c5cU, - 0xc2c2c2c2U, 0xd3d3d3d3U, 0xacacacacU, 0x62626262U, - 0x91919191U, 0x95959595U, 0xe4e4e4e4U, 0x79797979U, - 0xe7e7e7e7U, 0xc8c8c8c8U, 0x37373737U, 0x6d6d6d6dU, - 0x8d8d8d8dU, 0xd5d5d5d5U, 0x4e4e4e4eU, 0xa9a9a9a9U, - 0x6c6c6c6cU, 0x56565656U, 0xf4f4f4f4U, 0xeaeaeaeaU, - 0x65656565U, 0x7a7a7a7aU, 0xaeaeaeaeU, 0x08080808U, - 0xbabababaU, 0x78787878U, 0x25252525U, 0x2e2e2e2eU, - 0x1c1c1c1cU, 0xa6a6a6a6U, 0xb4b4b4b4U, 0xc6c6c6c6U, - 0xe8e8e8e8U, 0xddddddddU, 0x74747474U, 0x1f1f1f1fU, - 0x4b4b4b4bU, 0xbdbdbdbdU, 0x8b8b8b8bU, 0x8a8a8a8aU, - 0x70707070U, 0x3e3e3e3eU, 0xb5b5b5b5U, 0x66666666U, - 0x48484848U, 0x03030303U, 0xf6f6f6f6U, 0x0e0e0e0eU, - 0x61616161U, 0x35353535U, 0x57575757U, 0xb9b9b9b9U, - 0x86868686U, 0xc1c1c1c1U, 0x1d1d1d1dU, 0x9e9e9e9eU, - 0xe1e1e1e1U, 0xf8f8f8f8U, 0x98989898U, 0x11111111U, - 0x69696969U, 0xd9d9d9d9U, 0x8e8e8e8eU, 0x94949494U, - 0x9b9b9b9bU, 0x1e1e1e1eU, 0x87878787U, 0xe9e9e9e9U, - 0xcecececeU, 0x55555555U, 0x28282828U, 0xdfdfdfdfU, - 0x8c8c8c8cU, 0xa1a1a1a1U, 0x89898989U, 0x0d0d0d0dU, - 0xbfbfbfbfU, 0xe6e6e6e6U, 0x42424242U, 0x68686868U, - 0x41414141U, 0x99999999U, 0x2d2d2d2dU, 0x0f0f0f0fU, - 0xb0b0b0b0U, 0x54545454U, 0xbbbbbbbbU, 0x16161616U, -}; static const u32 Td0[256] = { 0x51f4a750U, 0x7e416553U, 0x1a17a4c3U, 0x3a275e96U, @@ -648,301 +586,270 @@ static const u32 Td3[256] = { 0xa8017139U, 0x0cb3de08U, 0xb4e49cd8U, 0x56c19064U, 0xcb84617bU, 0x32b670d5U, 0x6c5c7448U, 0xb85742d0U, }; -static const u32 Td4[256] = { - 0x52525252U, 0x09090909U, 0x6a6a6a6aU, 0xd5d5d5d5U, - 0x30303030U, 0x36363636U, 0xa5a5a5a5U, 0x38383838U, - 0xbfbfbfbfU, 0x40404040U, 0xa3a3a3a3U, 0x9e9e9e9eU, - 0x81818181U, 0xf3f3f3f3U, 0xd7d7d7d7U, 0xfbfbfbfbU, - 0x7c7c7c7cU, 0xe3e3e3e3U, 0x39393939U, 0x82828282U, - 0x9b9b9b9bU, 0x2f2f2f2fU, 0xffffffffU, 0x87878787U, - 0x34343434U, 0x8e8e8e8eU, 0x43434343U, 0x44444444U, - 0xc4c4c4c4U, 0xdedededeU, 0xe9e9e9e9U, 0xcbcbcbcbU, - 0x54545454U, 0x7b7b7b7bU, 0x94949494U, 0x32323232U, - 0xa6a6a6a6U, 0xc2c2c2c2U, 0x23232323U, 0x3d3d3d3dU, - 0xeeeeeeeeU, 0x4c4c4c4cU, 0x95959595U, 0x0b0b0b0bU, - 0x42424242U, 0xfafafafaU, 0xc3c3c3c3U, 0x4e4e4e4eU, - 0x08080808U, 0x2e2e2e2eU, 0xa1a1a1a1U, 0x66666666U, - 0x28282828U, 0xd9d9d9d9U, 0x24242424U, 0xb2b2b2b2U, - 0x76767676U, 0x5b5b5b5bU, 0xa2a2a2a2U, 0x49494949U, - 0x6d6d6d6dU, 0x8b8b8b8bU, 0xd1d1d1d1U, 0x25252525U, - 0x72727272U, 0xf8f8f8f8U, 0xf6f6f6f6U, 0x64646464U, - 0x86868686U, 0x68686868U, 0x98989898U, 0x16161616U, - 0xd4d4d4d4U, 0xa4a4a4a4U, 0x5c5c5c5cU, 0xccccccccU, - 0x5d5d5d5dU, 0x65656565U, 0xb6b6b6b6U, 0x92929292U, - 0x6c6c6c6cU, 0x70707070U, 0x48484848U, 0x50505050U, - 0xfdfdfdfdU, 0xededededU, 0xb9b9b9b9U, 0xdadadadaU, - 0x5e5e5e5eU, 0x15151515U, 0x46464646U, 0x57575757U, - 0xa7a7a7a7U, 0x8d8d8d8dU, 0x9d9d9d9dU, 0x84848484U, - 0x90909090U, 0xd8d8d8d8U, 0xababababU, 0x00000000U, - 0x8c8c8c8cU, 0xbcbcbcbcU, 0xd3d3d3d3U, 0x0a0a0a0aU, - 0xf7f7f7f7U, 0xe4e4e4e4U, 0x58585858U, 0x05050505U, - 0xb8b8b8b8U, 0xb3b3b3b3U, 0x45454545U, 0x06060606U, - 0xd0d0d0d0U, 0x2c2c2c2cU, 0x1e1e1e1eU, 0x8f8f8f8fU, - 0xcacacacaU, 0x3f3f3f3fU, 0x0f0f0f0fU, 0x02020202U, - 0xc1c1c1c1U, 0xafafafafU, 0xbdbdbdbdU, 0x03030303U, - 0x01010101U, 0x13131313U, 0x8a8a8a8aU, 0x6b6b6b6bU, - 0x3a3a3a3aU, 0x91919191U, 0x11111111U, 0x41414141U, - 0x4f4f4f4fU, 0x67676767U, 0xdcdcdcdcU, 0xeaeaeaeaU, - 0x97979797U, 0xf2f2f2f2U, 0xcfcfcfcfU, 0xcecececeU, - 0xf0f0f0f0U, 0xb4b4b4b4U, 0xe6e6e6e6U, 0x73737373U, - 0x96969696U, 0xacacacacU, 0x74747474U, 0x22222222U, - 0xe7e7e7e7U, 0xadadadadU, 0x35353535U, 0x85858585U, - 0xe2e2e2e2U, 0xf9f9f9f9U, 0x37373737U, 0xe8e8e8e8U, - 0x1c1c1c1cU, 0x75757575U, 0xdfdfdfdfU, 0x6e6e6e6eU, - 0x47474747U, 0xf1f1f1f1U, 0x1a1a1a1aU, 0x71717171U, - 0x1d1d1d1dU, 0x29292929U, 0xc5c5c5c5U, 0x89898989U, - 0x6f6f6f6fU, 0xb7b7b7b7U, 0x62626262U, 0x0e0e0e0eU, - 0xaaaaaaaaU, 0x18181818U, 0xbebebebeU, 0x1b1b1b1bU, - 0xfcfcfcfcU, 0x56565656U, 0x3e3e3e3eU, 0x4b4b4b4bU, - 0xc6c6c6c6U, 0xd2d2d2d2U, 0x79797979U, 0x20202020U, - 0x9a9a9a9aU, 0xdbdbdbdbU, 0xc0c0c0c0U, 0xfefefefeU, - 0x78787878U, 0xcdcdcdcdU, 0x5a5a5a5aU, 0xf4f4f4f4U, - 0x1f1f1f1fU, 0xddddddddU, 0xa8a8a8a8U, 0x33333333U, - 0x88888888U, 0x07070707U, 0xc7c7c7c7U, 0x31313131U, - 0xb1b1b1b1U, 0x12121212U, 0x10101010U, 0x59595959U, - 0x27272727U, 0x80808080U, 0xececececU, 0x5f5f5f5fU, - 0x60606060U, 0x51515151U, 0x7f7f7f7fU, 0xa9a9a9a9U, - 0x19191919U, 0xb5b5b5b5U, 0x4a4a4a4aU, 0x0d0d0d0dU, - 0x2d2d2d2dU, 0xe5e5e5e5U, 0x7a7a7a7aU, 0x9f9f9f9fU, - 0x93939393U, 0xc9c9c9c9U, 0x9c9c9c9cU, 0xefefefefU, - 0xa0a0a0a0U, 0xe0e0e0e0U, 0x3b3b3b3bU, 0x4d4d4d4dU, - 0xaeaeaeaeU, 0x2a2a2a2aU, 0xf5f5f5f5U, 0xb0b0b0b0U, - 0xc8c8c8c8U, 0xebebebebU, 0xbbbbbbbbU, 0x3c3c3c3cU, - 0x83838383U, 0x53535353U, 0x99999999U, 0x61616161U, - 0x17171717U, 0x2b2b2b2bU, 0x04040404U, 0x7e7e7e7eU, - 0xbabababaU, 0x77777777U, 0xd6d6d6d6U, 0x26262626U, - 0xe1e1e1e1U, 0x69696969U, 0x14141414U, 0x63636363U, - 0x55555555U, 0x21212121U, 0x0c0c0c0cU, 0x7d7d7d7dU, +static const u8 Td4[256] = { + 0x52U, 0x09U, 0x6aU, 0xd5U, 0x30U, 0x36U, 0xa5U, 0x38U, + 0xbfU, 0x40U, 0xa3U, 0x9eU, 0x81U, 0xf3U, 0xd7U, 0xfbU, + 0x7cU, 0xe3U, 0x39U, 0x82U, 0x9bU, 0x2fU, 0xffU, 0x87U, + 0x34U, 0x8eU, 0x43U, 0x44U, 0xc4U, 0xdeU, 0xe9U, 0xcbU, + 0x54U, 0x7bU, 0x94U, 0x32U, 0xa6U, 0xc2U, 0x23U, 0x3dU, + 0xeeU, 0x4cU, 0x95U, 0x0bU, 0x42U, 0xfaU, 0xc3U, 0x4eU, + 0x08U, 0x2eU, 0xa1U, 0x66U, 0x28U, 0xd9U, 0x24U, 0xb2U, + 0x76U, 0x5bU, 0xa2U, 0x49U, 0x6dU, 0x8bU, 0xd1U, 0x25U, + 0x72U, 0xf8U, 0xf6U, 0x64U, 0x86U, 0x68U, 0x98U, 0x16U, + 0xd4U, 0xa4U, 0x5cU, 0xccU, 0x5dU, 0x65U, 0xb6U, 0x92U, + 0x6cU, 0x70U, 0x48U, 0x50U, 0xfdU, 0xedU, 0xb9U, 0xdaU, + 0x5eU, 0x15U, 0x46U, 0x57U, 0xa7U, 0x8dU, 0x9dU, 0x84U, + 0x90U, 0xd8U, 0xabU, 0x00U, 0x8cU, 0xbcU, 0xd3U, 0x0aU, + 0xf7U, 0xe4U, 0x58U, 0x05U, 0xb8U, 0xb3U, 0x45U, 0x06U, + 0xd0U, 0x2cU, 0x1eU, 0x8fU, 0xcaU, 0x3fU, 0x0fU, 0x02U, + 0xc1U, 0xafU, 0xbdU, 0x03U, 0x01U, 0x13U, 0x8aU, 0x6bU, + 0x3aU, 0x91U, 0x11U, 0x41U, 0x4fU, 0x67U, 0xdcU, 0xeaU, + 0x97U, 0xf2U, 0xcfU, 0xceU, 0xf0U, 0xb4U, 0xe6U, 0x73U, + 0x96U, 0xacU, 0x74U, 0x22U, 0xe7U, 0xadU, 0x35U, 0x85U, + 0xe2U, 0xf9U, 0x37U, 0xe8U, 0x1cU, 0x75U, 0xdfU, 0x6eU, + 0x47U, 0xf1U, 0x1aU, 0x71U, 0x1dU, 0x29U, 0xc5U, 0x89U, + 0x6fU, 0xb7U, 0x62U, 0x0eU, 0xaaU, 0x18U, 0xbeU, 0x1bU, + 0xfcU, 0x56U, 0x3eU, 0x4bU, 0xc6U, 0xd2U, 0x79U, 0x20U, + 0x9aU, 0xdbU, 0xc0U, 0xfeU, 0x78U, 0xcdU, 0x5aU, 0xf4U, + 0x1fU, 0xddU, 0xa8U, 0x33U, 0x88U, 0x07U, 0xc7U, 0x31U, + 0xb1U, 0x12U, 0x10U, 0x59U, 0x27U, 0x80U, 0xecU, 0x5fU, + 0x60U, 0x51U, 0x7fU, 0xa9U, 0x19U, 0xb5U, 0x4aU, 0x0dU, + 0x2dU, 0xe5U, 0x7aU, 0x9fU, 0x93U, 0xc9U, 0x9cU, 0xefU, + 0xa0U, 0xe0U, 0x3bU, 0x4dU, 0xaeU, 0x2aU, 0xf5U, 0xb0U, + 0xc8U, 0xebU, 0xbbU, 0x3cU, 0x83U, 0x53U, 0x99U, 0x61U, + 0x17U, 0x2bU, 0x04U, 0x7eU, 0xbaU, 0x77U, 0xd6U, 0x26U, + 0xe1U, 0x69U, 0x14U, 0x63U, 0x55U, 0x21U, 0x0cU, 0x7dU, }; static const u32 rcon[] = { - 0x01000000, 0x02000000, 0x04000000, 0x08000000, - 0x10000000, 0x20000000, 0x40000000, 0x80000000, - 0x1B000000, 0x36000000, /* for 128-bit blocks, Rijndael never uses more than 10 rcon values */ + 0x01000000, 0x02000000, 0x04000000, 0x08000000, + 0x10000000, 0x20000000, 0x40000000, 0x80000000, + 0x1B000000, 0x36000000, /* for 128-bit blocks, Rijndael never uses more than 10 rcon values */ }; /** * Expand the cipher key into the encryption key schedule. */ int AES_set_encrypt_key(const unsigned char *userKey, const int bits, - AES_KEY *key) { + AES_KEY *key) +{ - u32 *rk; - int i = 0; - u32 temp; + u32 *rk; + int i = 0; + u32 temp; - if (!userKey || !key) - return -1; - if (bits != 128 && bits != 192 && bits != 256) - return -2; + if (!userKey || !key) + return -1; + if (bits != 128 && bits != 192 && bits != 256) + return -2; - rk = key->rd_key; + rk = key->rd_key; - if (bits==128) - key->rounds = 10; - else if (bits==192) - key->rounds = 12; - else - key->rounds = 14; + if (bits==128) + key->rounds = 10; + else if (bits==192) + key->rounds = 12; + else + key->rounds = 14; - rk[0] = GETU32(userKey ); - rk[1] = GETU32(userKey + 4); - rk[2] = GETU32(userKey + 8); - rk[3] = GETU32(userKey + 12); - if (bits == 128) { - while (1) { - temp = rk[3]; - rk[4] = rk[0] ^ - (Te4[(temp >> 16) & 0xff] & 0xff000000) ^ - (Te4[(temp >> 8) & 0xff] & 0x00ff0000) ^ - (Te4[(temp ) & 0xff] & 0x0000ff00) ^ - (Te4[(temp >> 24) ] & 0x000000ff) ^ - rcon[i]; - rk[5] = rk[1] ^ rk[4]; - rk[6] = rk[2] ^ rk[5]; - rk[7] = rk[3] ^ rk[6]; - if (++i == 10) { - return 0; - } - rk += 4; - } - } - rk[4] = GETU32(userKey + 16); - rk[5] = GETU32(userKey + 20); - if (bits == 192) { - while (1) { - temp = rk[ 5]; - rk[ 6] = rk[ 0] ^ - (Te4[(temp >> 16) & 0xff] & 0xff000000) ^ - (Te4[(temp >> 8) & 0xff] & 0x00ff0000) ^ - (Te4[(temp ) & 0xff] & 0x0000ff00) ^ - (Te4[(temp >> 24) ] & 0x000000ff) ^ - rcon[i]; - rk[ 7] = rk[ 1] ^ rk[ 6]; - rk[ 8] = rk[ 2] ^ rk[ 7]; - rk[ 9] = rk[ 3] ^ rk[ 8]; - if (++i == 8) { - return 0; - } - rk[10] = rk[ 4] ^ rk[ 9]; - rk[11] = rk[ 5] ^ rk[10]; - rk += 6; - } - } - rk[6] = GETU32(userKey + 24); - rk[7] = GETU32(userKey + 28); - if (bits == 256) { - while (1) { - temp = rk[ 7]; - rk[ 8] = rk[ 0] ^ - (Te4[(temp >> 16) & 0xff] & 0xff000000) ^ - (Te4[(temp >> 8) & 0xff] & 0x00ff0000) ^ - (Te4[(temp ) & 0xff] & 0x0000ff00) ^ - (Te4[(temp >> 24) ] & 0x000000ff) ^ - rcon[i]; - rk[ 9] = rk[ 1] ^ rk[ 8]; - rk[10] = rk[ 2] ^ rk[ 9]; - rk[11] = rk[ 3] ^ rk[10]; - if (++i == 7) { - return 0; - } - temp = rk[11]; - rk[12] = rk[ 4] ^ - (Te4[(temp >> 24) ] & 0xff000000) ^ - (Te4[(temp >> 16) & 0xff] & 0x00ff0000) ^ - (Te4[(temp >> 8) & 0xff] & 0x0000ff00) ^ - (Te4[(temp ) & 0xff] & 0x000000ff); - rk[13] = rk[ 5] ^ rk[12]; - rk[14] = rk[ 6] ^ rk[13]; - rk[15] = rk[ 7] ^ rk[14]; + rk[0] = GETU32(userKey ); + rk[1] = GETU32(userKey + 4); + rk[2] = GETU32(userKey + 8); + rk[3] = GETU32(userKey + 12); + if (bits == 128) { + while (1) { + temp = rk[3]; + rk[4] = rk[0] ^ + (Te2[(temp >> 16) & 0xff] & 0xff000000) ^ + (Te3[(temp >> 8) & 0xff] & 0x00ff0000) ^ + (Te0[(temp ) & 0xff] & 0x0000ff00) ^ + (Te1[(temp >> 24) ] & 0x000000ff) ^ + rcon[i]; + rk[5] = rk[1] ^ rk[4]; + rk[6] = rk[2] ^ rk[5]; + rk[7] = rk[3] ^ rk[6]; + if (++i == 10) { + return 0; + } + rk += 4; + } + } + rk[4] = GETU32(userKey + 16); + rk[5] = GETU32(userKey + 20); + if (bits == 192) { + while (1) { + temp = rk[ 5]; + rk[ 6] = rk[ 0] ^ + (Te2[(temp >> 16) & 0xff] & 0xff000000) ^ + (Te3[(temp >> 8) & 0xff] & 0x00ff0000) ^ + (Te0[(temp ) & 0xff] & 0x0000ff00) ^ + (Te1[(temp >> 24) ] & 0x000000ff) ^ + rcon[i]; + rk[ 7] = rk[ 1] ^ rk[ 6]; + rk[ 8] = rk[ 2] ^ rk[ 7]; + rk[ 9] = rk[ 3] ^ rk[ 8]; + if (++i == 8) { + return 0; + } + rk[10] = rk[ 4] ^ rk[ 9]; + rk[11] = rk[ 5] ^ rk[10]; + rk += 6; + } + } + rk[6] = GETU32(userKey + 24); + rk[7] = GETU32(userKey + 28); + if (bits == 256) { + while (1) { + temp = rk[ 7]; + rk[ 8] = rk[ 0] ^ + (Te2[(temp >> 16) & 0xff] & 0xff000000) ^ + (Te3[(temp >> 8) & 0xff] & 0x00ff0000) ^ + (Te0[(temp ) & 0xff] & 0x0000ff00) ^ + (Te1[(temp >> 24) ] & 0x000000ff) ^ + rcon[i]; + rk[ 9] = rk[ 1] ^ rk[ 8]; + rk[10] = rk[ 2] ^ rk[ 9]; + rk[11] = rk[ 3] ^ rk[10]; + if (++i == 7) { + return 0; + } + temp = rk[11]; + rk[12] = rk[ 4] ^ + (Te2[(temp >> 24) ] & 0xff000000) ^ + (Te3[(temp >> 16) & 0xff] & 0x00ff0000) ^ + (Te0[(temp >> 8) & 0xff] & 0x0000ff00) ^ + (Te1[(temp ) & 0xff] & 0x000000ff); + rk[13] = rk[ 5] ^ rk[12]; + rk[14] = rk[ 6] ^ rk[13]; + rk[15] = rk[ 7] ^ rk[14]; - rk += 8; - } - } - return 0; + rk += 8; + } + } + return 0; } /** * Expand the cipher key into the decryption key schedule. */ int AES_set_decrypt_key(const unsigned char *userKey, const int bits, - AES_KEY *key) { + AES_KEY *key) +{ - u32 *rk; - int i, j, status; - u32 temp; + u32 *rk; + int i, j, status; + u32 temp; - /* first, start with an encryption schedule */ - status = AES_set_encrypt_key(userKey, bits, key); - if (status < 0) - return status; + /* first, start with an encryption schedule */ + status = AES_set_encrypt_key(userKey, bits, key); + if (status < 0) + return status; - rk = key->rd_key; + rk = key->rd_key; - /* invert the order of the round keys: */ - for (i = 0, j = 4*(key->rounds); i < j; i += 4, j -= 4) { - temp = rk[i ]; rk[i ] = rk[j ]; rk[j ] = temp; - temp = rk[i + 1]; rk[i + 1] = rk[j + 1]; rk[j + 1] = temp; - temp = rk[i + 2]; rk[i + 2] = rk[j + 2]; rk[j + 2] = temp; - temp = rk[i + 3]; rk[i + 3] = rk[j + 3]; rk[j + 3] = temp; - } - /* apply the inverse MixColumn transform to all round keys but the first and the last: */ - for (i = 1; i < (key->rounds); i++) { - rk += 4; - rk[0] = - Td0[Te4[(rk[0] >> 24) ] & 0xff] ^ - Td1[Te4[(rk[0] >> 16) & 0xff] & 0xff] ^ - Td2[Te4[(rk[0] >> 8) & 0xff] & 0xff] ^ - Td3[Te4[(rk[0] ) & 0xff] & 0xff]; - rk[1] = - Td0[Te4[(rk[1] >> 24) ] & 0xff] ^ - Td1[Te4[(rk[1] >> 16) & 0xff] & 0xff] ^ - Td2[Te4[(rk[1] >> 8) & 0xff] & 0xff] ^ - Td3[Te4[(rk[1] ) & 0xff] & 0xff]; - rk[2] = - Td0[Te4[(rk[2] >> 24) ] & 0xff] ^ - Td1[Te4[(rk[2] >> 16) & 0xff] & 0xff] ^ - Td2[Te4[(rk[2] >> 8) & 0xff] & 0xff] ^ - Td3[Te4[(rk[2] ) & 0xff] & 0xff]; - rk[3] = - Td0[Te4[(rk[3] >> 24) ] & 0xff] ^ - Td1[Te4[(rk[3] >> 16) & 0xff] & 0xff] ^ - Td2[Te4[(rk[3] >> 8) & 0xff] & 0xff] ^ - Td3[Te4[(rk[3] ) & 0xff] & 0xff]; - } - return 0; + /* invert the order of the round keys: */ + for (i = 0, j = 4*(key->rounds); i < j; i += 4, j -= 4) { + temp = rk[i ]; rk[i ] = rk[j ]; rk[j ] = temp; + temp = rk[i + 1]; rk[i + 1] = rk[j + 1]; rk[j + 1] = temp; + temp = rk[i + 2]; rk[i + 2] = rk[j + 2]; rk[j + 2] = temp; + temp = rk[i + 3]; rk[i + 3] = rk[j + 3]; rk[j + 3] = temp; + } + /* apply the inverse MixColumn transform to all round keys but the first and the last: */ + for (i = 1; i < (key->rounds); i++) { + rk += 4; + rk[0] = + Td0[Te1[(rk[0] >> 24) ] & 0xff] ^ + Td1[Te1[(rk[0] >> 16) & 0xff] & 0xff] ^ + Td2[Te1[(rk[0] >> 8) & 0xff] & 0xff] ^ + Td3[Te1[(rk[0] ) & 0xff] & 0xff]; + rk[1] = + Td0[Te1[(rk[1] >> 24) ] & 0xff] ^ + Td1[Te1[(rk[1] >> 16) & 0xff] & 0xff] ^ + Td2[Te1[(rk[1] >> 8) & 0xff] & 0xff] ^ + Td3[Te1[(rk[1] ) & 0xff] & 0xff]; + rk[2] = + Td0[Te1[(rk[2] >> 24) ] & 0xff] ^ + Td1[Te1[(rk[2] >> 16) & 0xff] & 0xff] ^ + Td2[Te1[(rk[2] >> 8) & 0xff] & 0xff] ^ + Td3[Te1[(rk[2] ) & 0xff] & 0xff]; + rk[3] = + Td0[Te1[(rk[3] >> 24) ] & 0xff] ^ + Td1[Te1[(rk[3] >> 16) & 0xff] & 0xff] ^ + Td2[Te1[(rk[3] >> 8) & 0xff] & 0xff] ^ + Td3[Te1[(rk[3] ) & 0xff] & 0xff]; + } + return 0; } -#ifndef AES_ASM /* * Encrypt a single block * in and out can overlap */ void AES_encrypt(const unsigned char *in, unsigned char *out, - const AES_KEY *key) { + const AES_KEY *key) { - const u32 *rk; - u32 s0, s1, s2, s3, t0, t1, t2, t3; + const u32 *rk; + u32 s0, s1, s2, s3, t0, t1, t2, t3; #ifndef FULL_UNROLL - int r; + int r; #endif /* ?FULL_UNROLL */ - assert(in && out && key); - rk = key->rd_key; + assert(in && out && key); + rk = key->rd_key; - /* - * map byte array block to cipher state - * and add initial round key: - */ - s0 = GETU32(in ) ^ rk[0]; - s1 = GETU32(in + 4) ^ rk[1]; - s2 = GETU32(in + 8) ^ rk[2]; - s3 = GETU32(in + 12) ^ rk[3]; + /* + * map byte array block to cipher state + * and add initial round key: + */ + s0 = GETU32(in ) ^ rk[0]; + s1 = GETU32(in + 4) ^ rk[1]; + s2 = GETU32(in + 8) ^ rk[2]; + s3 = GETU32(in + 12) ^ rk[3]; #ifdef FULL_UNROLL - /* round 1: */ - t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[ 4]; - t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[ 5]; - t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[ 6]; - t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[ 7]; - /* round 2: */ - s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[ 8]; - s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[ 9]; - s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[10]; - s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[11]; - /* round 3: */ - t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[12]; - t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[13]; - t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[14]; - t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[15]; - /* round 4: */ - s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[16]; - s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[17]; - s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[18]; - s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[19]; - /* round 5: */ - t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[20]; - t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[21]; - t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[22]; - t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[23]; - /* round 6: */ - s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[24]; - s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[25]; - s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[26]; - s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[27]; - /* round 7: */ - t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[28]; - t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[29]; - t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[30]; - t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[31]; - /* round 8: */ - s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[32]; - s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[33]; - s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[34]; - s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[35]; - /* round 9: */ - t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[36]; - t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[37]; - t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[38]; - t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[39]; + /* round 1: */ + t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[ 4]; + t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[ 5]; + t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[ 6]; + t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[ 7]; + /* round 2: */ + s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[ 8]; + s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[ 9]; + s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[10]; + s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[11]; + /* round 3: */ + t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[12]; + t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[13]; + t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[14]; + t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[15]; + /* round 4: */ + s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[16]; + s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[17]; + s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[18]; + s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[19]; + /* round 5: */ + t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[20]; + t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[21]; + t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[22]; + t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[23]; + /* round 6: */ + s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[24]; + s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[25]; + s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[26]; + s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[27]; + /* round 7: */ + t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[28]; + t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[29]; + t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[30]; + t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[31]; + /* round 8: */ + s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[32]; + s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >> 8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[33]; + s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >> 8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[34]; + s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >> 8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[35]; + /* round 9: */ + t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >> 8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[36]; + t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >> 8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[37]; + t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >> 8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[38]; + t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >> 8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[39]; if (key->rounds > 10) { /* round 10: */ s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >> 8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[40]; @@ -1031,37 +938,37 @@ void AES_encrypt(const unsigned char *in, unsigned char *out, } #endif /* ?FULL_UNROLL */ /* - * apply last round and - * map cipher state to byte array block: - */ - s0 = - (Te4[(t0 >> 24) ] & 0xff000000) ^ - (Te4[(t1 >> 16) & 0xff] & 0x00ff0000) ^ - (Te4[(t2 >> 8) & 0xff] & 0x0000ff00) ^ - (Te4[(t3 ) & 0xff] & 0x000000ff) ^ - rk[0]; - PUTU32(out , s0); - s1 = - (Te4[(t1 >> 24) ] & 0xff000000) ^ - (Te4[(t2 >> 16) & 0xff] & 0x00ff0000) ^ - (Te4[(t3 >> 8) & 0xff] & 0x0000ff00) ^ - (Te4[(t0 ) & 0xff] & 0x000000ff) ^ - rk[1]; - PUTU32(out + 4, s1); - s2 = - (Te4[(t2 >> 24) ] & 0xff000000) ^ - (Te4[(t3 >> 16) & 0xff] & 0x00ff0000) ^ - (Te4[(t0 >> 8) & 0xff] & 0x0000ff00) ^ - (Te4[(t1 ) & 0xff] & 0x000000ff) ^ - rk[2]; - PUTU32(out + 8, s2); - s3 = - (Te4[(t3 >> 24) ] & 0xff000000) ^ - (Te4[(t0 >> 16) & 0xff] & 0x00ff0000) ^ - (Te4[(t1 >> 8) & 0xff] & 0x0000ff00) ^ - (Te4[(t2 ) & 0xff] & 0x000000ff) ^ - rk[3]; - PUTU32(out + 12, s3); + * apply last round and + * map cipher state to byte array block: + */ + s0 = + (Te2[(t0 >> 24) ] & 0xff000000) ^ + (Te3[(t1 >> 16) & 0xff] & 0x00ff0000) ^ + (Te0[(t2 >> 8) & 0xff] & 0x0000ff00) ^ + (Te1[(t3 ) & 0xff] & 0x000000ff) ^ + rk[0]; + PUTU32(out , s0); + s1 = + (Te2[(t1 >> 24) ] & 0xff000000) ^ + (Te3[(t2 >> 16) & 0xff] & 0x00ff0000) ^ + (Te0[(t3 >> 8) & 0xff] & 0x0000ff00) ^ + (Te1[(t0 ) & 0xff] & 0x000000ff) ^ + rk[1]; + PUTU32(out + 4, s1); + s2 = + (Te2[(t2 >> 24) ] & 0xff000000) ^ + (Te3[(t3 >> 16) & 0xff] & 0x00ff0000) ^ + (Te0[(t0 >> 8) & 0xff] & 0x0000ff00) ^ + (Te1[(t1 ) & 0xff] & 0x000000ff) ^ + rk[2]; + PUTU32(out + 8, s2); + s3 = + (Te2[(t3 >> 24) ] & 0xff000000) ^ + (Te3[(t0 >> 16) & 0xff] & 0x00ff0000) ^ + (Te0[(t1 >> 8) & 0xff] & 0x0000ff00) ^ + (Te1[(t2 ) & 0xff] & 0x000000ff) ^ + rk[3]; + PUTU32(out + 12, s3); } /* @@ -1069,21 +976,22 @@ void AES_encrypt(const unsigned char *in, unsigned char *out, * in and out can overlap */ void AES_decrypt(const unsigned char *in, unsigned char *out, - const AES_KEY *key) { + const AES_KEY *key) +{ - const u32 *rk; - u32 s0, s1, s2, s3, t0, t1, t2, t3; + const u32 *rk; + u32 s0, s1, s2, s3, t0, t1, t2, t3; #ifndef FULL_UNROLL - int r; + int r; #endif /* ?FULL_UNROLL */ - assert(in && out && key); - rk = key->rd_key; + assert(in && out && key); + rk = key->rd_key; - /* - * map byte array block to cipher state - * and add initial round key: - */ + /* + * map byte array block to cipher state + * and add initial round key: + */ s0 = GETU32(in ) ^ rk[0]; s1 = GETU32(in + 4) ^ rk[1]; s2 = GETU32(in + 8) ^ rk[2]; @@ -1158,7 +1066,7 @@ void AES_decrypt(const unsigned char *in, unsigned char *out, t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >> 8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[55]; } } - rk += key->rounds << 2; + rk += key->rounds << 2; #else /* !FULL_UNROLL */ /* * Nr - 1 full rounds: @@ -1222,37 +1130,238 @@ void AES_decrypt(const unsigned char *in, unsigned char *out, } #endif /* ?FULL_UNROLL */ /* - * apply last round and - * map cipher state to byte array block: - */ - s0 = - (Td4[(t0 >> 24) ] & 0xff000000) ^ - (Td4[(t3 >> 16) & 0xff] & 0x00ff0000) ^ - (Td4[(t2 >> 8) & 0xff] & 0x0000ff00) ^ - (Td4[(t1 ) & 0xff] & 0x000000ff) ^ - rk[0]; - PUTU32(out , s0); - s1 = - (Td4[(t1 >> 24) ] & 0xff000000) ^ - (Td4[(t0 >> 16) & 0xff] & 0x00ff0000) ^ - (Td4[(t3 >> 8) & 0xff] & 0x0000ff00) ^ - (Td4[(t2 ) & 0xff] & 0x000000ff) ^ - rk[1]; - PUTU32(out + 4, s1); - s2 = - (Td4[(t2 >> 24) ] & 0xff000000) ^ - (Td4[(t1 >> 16) & 0xff] & 0x00ff0000) ^ - (Td4[(t0 >> 8) & 0xff] & 0x0000ff00) ^ - (Td4[(t3 ) & 0xff] & 0x000000ff) ^ - rk[2]; - PUTU32(out + 8, s2); - s3 = - (Td4[(t3 >> 24) ] & 0xff000000) ^ - (Td4[(t2 >> 16) & 0xff] & 0x00ff0000) ^ - (Td4[(t1 >> 8) & 0xff] & 0x0000ff00) ^ - (Td4[(t0 ) & 0xff] & 0x000000ff) ^ - rk[3]; - PUTU32(out + 12, s3); + * apply last round and + * map cipher state to byte array block: + */ + s0 = + ((u32)Td4[(t0 >> 24) ] << 24) ^ + ((u32)Td4[(t3 >> 16) & 0xff] << 16) ^ + ((u32)Td4[(t2 >> 8) & 0xff] << 8) ^ + ((u32)Td4[(t1 ) & 0xff]) ^ + rk[0]; + PUTU32(out , s0); + s1 = + ((u32)Td4[(t1 >> 24) ] << 24) ^ + ((u32)Td4[(t0 >> 16) & 0xff] << 16) ^ + ((u32)Td4[(t3 >> 8) & 0xff] << 8) ^ + ((u32)Td4[(t2 ) & 0xff]) ^ + rk[1]; + PUTU32(out + 4, s1); + s2 = + ((u32)Td4[(t2 >> 24) ] << 24) ^ + ((u32)Td4[(t1 >> 16) & 0xff] << 16) ^ + ((u32)Td4[(t0 >> 8) & 0xff] << 8) ^ + ((u32)Td4[(t3 ) & 0xff]) ^ + rk[2]; + PUTU32(out + 8, s2); + s3 = + ((u32)Td4[(t3 >> 24) ] << 24) ^ + ((u32)Td4[(t2 >> 16) & 0xff] << 16) ^ + ((u32)Td4[(t1 >> 8) & 0xff] << 8) ^ + ((u32)Td4[(t0 ) & 0xff]) ^ + rk[3]; + PUTU32(out + 12, s3); +} + +#else /* AES_ASM */ + +static const u8 Te4[256] = { + 0x63U, 0x7cU, 0x77U, 0x7bU, 0xf2U, 0x6bU, 0x6fU, 0xc5U, + 0x30U, 0x01U, 0x67U, 0x2bU, 0xfeU, 0xd7U, 0xabU, 0x76U, + 0xcaU, 0x82U, 0xc9U, 0x7dU, 0xfaU, 0x59U, 0x47U, 0xf0U, + 0xadU, 0xd4U, 0xa2U, 0xafU, 0x9cU, 0xa4U, 0x72U, 0xc0U, + 0xb7U, 0xfdU, 0x93U, 0x26U, 0x36U, 0x3fU, 0xf7U, 0xccU, + 0x34U, 0xa5U, 0xe5U, 0xf1U, 0x71U, 0xd8U, 0x31U, 0x15U, + 0x04U, 0xc7U, 0x23U, 0xc3U, 0x18U, 0x96U, 0x05U, 0x9aU, + 0x07U, 0x12U, 0x80U, 0xe2U, 0xebU, 0x27U, 0xb2U, 0x75U, + 0x09U, 0x83U, 0x2cU, 0x1aU, 0x1bU, 0x6eU, 0x5aU, 0xa0U, + 0x52U, 0x3bU, 0xd6U, 0xb3U, 0x29U, 0xe3U, 0x2fU, 0x84U, + 0x53U, 0xd1U, 0x00U, 0xedU, 0x20U, 0xfcU, 0xb1U, 0x5bU, + 0x6aU, 0xcbU, 0xbeU, 0x39U, 0x4aU, 0x4cU, 0x58U, 0xcfU, + 0xd0U, 0xefU, 0xaaU, 0xfbU, 0x43U, 0x4dU, 0x33U, 0x85U, + 0x45U, 0xf9U, 0x02U, 0x7fU, 0x50U, 0x3cU, 0x9fU, 0xa8U, + 0x51U, 0xa3U, 0x40U, 0x8fU, 0x92U, 0x9dU, 0x38U, 0xf5U, + 0xbcU, 0xb6U, 0xdaU, 0x21U, 0x10U, 0xffU, 0xf3U, 0xd2U, + 0xcdU, 0x0cU, 0x13U, 0xecU, 0x5fU, 0x97U, 0x44U, 0x17U, + 0xc4U, 0xa7U, 0x7eU, 0x3dU, 0x64U, 0x5dU, 0x19U, 0x73U, + 0x60U, 0x81U, 0x4fU, 0xdcU, 0x22U, 0x2aU, 0x90U, 0x88U, + 0x46U, 0xeeU, 0xb8U, 0x14U, 0xdeU, 0x5eU, 0x0bU, 0xdbU, + 0xe0U, 0x32U, 0x3aU, 0x0aU, 0x49U, 0x06U, 0x24U, 0x5cU, + 0xc2U, 0xd3U, 0xacU, 0x62U, 0x91U, 0x95U, 0xe4U, 0x79U, + 0xe7U, 0xc8U, 0x37U, 0x6dU, 0x8dU, 0xd5U, 0x4eU, 0xa9U, + 0x6cU, 0x56U, 0xf4U, 0xeaU, 0x65U, 0x7aU, 0xaeU, 0x08U, + 0xbaU, 0x78U, 0x25U, 0x2eU, 0x1cU, 0xa6U, 0xb4U, 0xc6U, + 0xe8U, 0xddU, 0x74U, 0x1fU, 0x4bU, 0xbdU, 0x8bU, 0x8aU, + 0x70U, 0x3eU, 0xb5U, 0x66U, 0x48U, 0x03U, 0xf6U, 0x0eU, + 0x61U, 0x35U, 0x57U, 0xb9U, 0x86U, 0xc1U, 0x1dU, 0x9eU, + 0xe1U, 0xf8U, 0x98U, 0x11U, 0x69U, 0xd9U, 0x8eU, 0x94U, + 0x9bU, 0x1eU, 0x87U, 0xe9U, 0xceU, 0x55U, 0x28U, 0xdfU, + 0x8cU, 0xa1U, 0x89U, 0x0dU, 0xbfU, 0xe6U, 0x42U, 0x68U, + 0x41U, 0x99U, 0x2dU, 0x0fU, 0xb0U, 0x54U, 0xbbU, 0x16U +}; +static const u32 rcon[] = { + 0x01000000, 0x02000000, 0x04000000, 0x08000000, + 0x10000000, 0x20000000, 0x40000000, 0x80000000, + 0x1B000000, 0x36000000, /* for 128-bit blocks, Rijndael never uses more than 10 rcon values */ +}; + +/** + * Expand the cipher key into the encryption key schedule. + */ +int AES_set_encrypt_key(const unsigned char *userKey, const int bits, + AES_KEY *key) +{ + u32 *rk; + int i = 0; + u32 temp; + + if (!userKey || !key) + return -1; + if (bits != 128 && bits != 192 && bits != 256) + return -2; + + rk = key->rd_key; + + if (bits==128) + key->rounds = 10; + else if (bits==192) + key->rounds = 12; + else + key->rounds = 14; + + rk[0] = GETU32(userKey ); + rk[1] = GETU32(userKey + 4); + rk[2] = GETU32(userKey + 8); + rk[3] = GETU32(userKey + 12); + if (bits == 128) { + while (1) { + temp = rk[3]; + rk[4] = rk[0] ^ + ((u32)Te4[(temp >> 16) & 0xff] << 24) ^ + ((u32)Te4[(temp >> 8) & 0xff] << 16) ^ + ((u32)Te4[(temp ) & 0xff] << 8) ^ + ((u32)Te4[(temp >> 24) ]) ^ + rcon[i]; + rk[5] = rk[1] ^ rk[4]; + rk[6] = rk[2] ^ rk[5]; + rk[7] = rk[3] ^ rk[6]; + if (++i == 10) { + return 0; + } + rk += 4; + } + } + rk[4] = GETU32(userKey + 16); + rk[5] = GETU32(userKey + 20); + if (bits == 192) { + while (1) { + temp = rk[ 5]; + rk[ 6] = rk[ 0] ^ + ((u32)Te4[(temp >> 16) & 0xff] << 24) ^ + ((u32)Te4[(temp >> 8) & 0xff] << 16) ^ + ((u32)Te4[(temp ) & 0xff] << 8) ^ + ((u32)Te4[(temp >> 24) ]) ^ + rcon[i]; + rk[ 7] = rk[ 1] ^ rk[ 6]; + rk[ 8] = rk[ 2] ^ rk[ 7]; + rk[ 9] = rk[ 3] ^ rk[ 8]; + if (++i == 8) { + return 0; + } + rk[10] = rk[ 4] ^ rk[ 9]; + rk[11] = rk[ 5] ^ rk[10]; + rk += 6; + } + } + rk[6] = GETU32(userKey + 24); + rk[7] = GETU32(userKey + 28); + if (bits == 256) { + while (1) { + temp = rk[ 7]; + rk[ 8] = rk[ 0] ^ + ((u32)Te4[(temp >> 16) & 0xff] << 24) ^ + ((u32)Te4[(temp >> 8) & 0xff] << 16) ^ + ((u32)Te4[(temp ) & 0xff] << 8) ^ + ((u32)Te4[(temp >> 24) ]) ^ + rcon[i]; + rk[ 9] = rk[ 1] ^ rk[ 8]; + rk[10] = rk[ 2] ^ rk[ 9]; + rk[11] = rk[ 3] ^ rk[10]; + if (++i == 7) { + return 0; + } + temp = rk[11]; + rk[12] = rk[ 4] ^ + ((u32)Te4[(temp >> 24) ] << 24) ^ + ((u32)Te4[(temp >> 16) & 0xff] << 16) ^ + ((u32)Te4[(temp >> 8) & 0xff] << 8) ^ + ((u32)Te4[(temp ) & 0xff]); + rk[13] = rk[ 5] ^ rk[12]; + rk[14] = rk[ 6] ^ rk[13]; + rk[15] = rk[ 7] ^ rk[14]; + + rk += 8; + } + } + return 0; +} + +/** + * Expand the cipher key into the decryption key schedule. + */ +int AES_set_decrypt_key(const unsigned char *userKey, const int bits, + AES_KEY *key) +{ + + u32 *rk; + int i, j, status; + u32 temp; + + /* first, start with an encryption schedule */ + status = AES_set_encrypt_key(userKey, bits, key); + if (status < 0) + return status; + + rk = key->rd_key; + + /* invert the order of the round keys: */ + for (i = 0, j = 4*(key->rounds); i < j; i += 4, j -= 4) { + temp = rk[i ]; rk[i ] = rk[j ]; rk[j ] = temp; + temp = rk[i + 1]; rk[i + 1] = rk[j + 1]; rk[j + 1] = temp; + temp = rk[i + 2]; rk[i + 2] = rk[j + 2]; rk[j + 2] = temp; + temp = rk[i + 3]; rk[i + 3] = rk[j + 3]; rk[j + 3] = temp; + } + /* apply the inverse MixColumn transform to all round keys but the first and the last: */ + for (i = 1; i < (key->rounds); i++) { + rk += 4; + for (j = 0; j < 4; j++) { + u32 tp1, tp2, tp4, tp8, tp9, tpb, tpd, tpe, m; + + tp1 = rk[j]; + m = tp1 & 0x80808080; + tp2 = ((tp1 & 0x7f7f7f7f) << 1) ^ + ((m - (m >> 7)) & 0x1b1b1b1b); + m = tp2 & 0x80808080; + tp4 = ((tp2 & 0x7f7f7f7f) << 1) ^ + ((m - (m >> 7)) & 0x1b1b1b1b); + m = tp4 & 0x80808080; + tp8 = ((tp4 & 0x7f7f7f7f) << 1) ^ + ((m - (m >> 7)) & 0x1b1b1b1b); + tp9 = tp8 ^ tp1; + tpb = tp9 ^ tp2; + tpd = tp9 ^ tp4; + tpe = tp8 ^ tp4 ^ tp2; +#if defined(ROTATE) + rk[j] = tpe ^ ROTATE(tpd,16) ^ + ROTATE(tp9,24) ^ ROTATE(tpb,8); +#else + rk[j] = tpe ^ (tpd >> 16) ^ (tpd << 16) ^ + (tp9 >> 8) ^ (tp9 << 24) ^ + (tpb >> 24) ^ (tpb << 8); +#endif + } + } + return 0; } #endif /* AES_ASM */