From: rasky Date: Mon, 4 Oct 2010 18:22:21 +0000 (+0000) Subject: SEC: Add 32-bit optimized AES implementation and refactor code to support X-Git-Tag: 2.6.0~5^2~120 X-Git-Url: https://codewiz.org/gitweb?a=commitdiff_plain;h=6d06c404f1e39253c5c7918fe0e044db462433e4;p=bertos.git SEC: Add 32-bit optimized AES implementation and refactor code to support multiple implementations. git-svn-id: https://src.develer.com/svnoss/bertos/trunk@4400 38d2e660-2303-0410-9eaa-f027e97ec537 --- diff --git a/bertos/sec/cipher/aes.c b/bertos/sec/cipher/aes.c index df535c71..53b8510d 100644 --- a/bertos/sec/cipher/aes.c +++ b/bertos/sec/cipher/aes.c @@ -37,24 +37,10 @@ * $WIZ$ module_name = "aes" */ -// advanced encryption standard -// author: karl malbrain, malbrain@yahoo.com -/* -This work, including the source code, documentation -and related data, is placed into the public domain. - -The orginal author is Karl Malbrain. - -THIS SOFTWARE IS PROVIDED AS-IS WITHOUT WARRANTY -OF ANY KIND, NOT EVEN THE IMPLIED WARRANTY OF -MERCHANTABILITY. THE AUTHOR OF THIS SOFTWARE, -ASSUMES _NO_ RESPONSIBILITY FOR ANY CONSEQUENCE -RESULTING FROM THE USE, MODIFICATION, OR -REDISTRIBUTION OF THIS SOFTWARE. -*/ #include "aes.h" #include +#include #include @@ -64,402 +50,32 @@ REDISTRIBUTION OF THIS SOFTWARE. typedef struct { BlockCipher c; - int num_rounds; + uint8_t num_rounds; + int8_t key_status; + uint8_t _dummy1; + uint8_t _dummy2; uint8_t expkey[0]; } AES_Context; -static uint8_t Sbox[256] = { // forward s-box -0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76, -0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0, -0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc, 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15, -0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a, 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75, -0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0, 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84, -0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b, 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf, -0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85, 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8, -0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5, 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2, -0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17, 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73, -0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88, 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb, -0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c, 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79, -0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9, 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08, -0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6, 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a, -0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e, 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e, -0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94, 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf, -0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16}; -static uint8_t InvSbox[256] = { // inverse s-box -0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb, -0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb, -0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e, -0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25, -0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92, -0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84, -0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06, -0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b, -0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73, -0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e, -0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b, -0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4, -0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f, -0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef, -0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61, -0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d}; +#if CPU_REG_BITS == 32 -// combined Xtimes2[Sbox[]] -static uint8_t Xtime2Sbox[256] = { -0xc6, 0xf8, 0xee, 0xf6, 0xff, 0xd6, 0xde, 0x91, 0x60, 0x02, 0xce, 0x56, 0xe7, 0xb5, 0x4d, 0xec, -0x8f, 0x1f, 0x89, 0xfa, 0xef, 0xb2, 0x8e, 0xfb, 0x41, 0xb3, 0x5f, 0x45, 0x23, 0x53, 0xe4, 0x9b, -0x75, 0xe1, 0x3d, 0x4c, 0x6c, 0x7e, 0xf5, 0x83, 0x68, 0x51, 0xd1, 0xf9, 0xe2, 0xab, 0x62, 0x2a, -0x08, 0x95, 0x46, 0x9d, 0x30, 0x37, 0x0a, 0x2f, 0x0e, 0x24, 0x1b, 0xdf, 0xcd, 0x4e, 0x7f, 0xea, -0x12, 0x1d, 0x58, 0x34, 0x36, 0xdc, 0xb4, 0x5b, 0xa4, 0x76, 0xb7, 0x7d, 0x52, 0xdd, 0x5e, 0x13, -0xa6, 0xb9, 0x00, 0xc1, 0x40, 0xe3, 0x79, 0xb6, 0xd4, 0x8d, 0x67, 0x72, 0x94, 0x98, 0xb0, 0x85, -0xbb, 0xc5, 0x4f, 0xed, 0x86, 0x9a, 0x66, 0x11, 0x8a, 0xe9, 0x04, 0xfe, 0xa0, 0x78, 0x25, 0x4b, -0xa2, 0x5d, 0x80, 0x05, 0x3f, 0x21, 0x70, 0xf1, 0x63, 0x77, 0xaf, 0x42, 0x20, 0xe5, 0xfd, 0xbf, -0x81, 0x18, 0x26, 0xc3, 0xbe, 0x35, 0x88, 0x2e, 0x93, 0x55, 0xfc, 0x7a, 0xc8, 0xba, 0x32, 0xe6, -0xc0, 0x19, 0x9e, 0xa3, 0x44, 0x54, 0x3b, 0x0b, 0x8c, 0xc7, 0x6b, 0x28, 0xa7, 0xbc, 0x16, 0xad, -0xdb, 0x64, 0x74, 0x14, 0x92, 0x0c, 0x48, 0xb8, 0x9f, 0xbd, 0x43, 0xc4, 0x39, 0x31, 0xd3, 0xf2, -0xd5, 0x8b, 0x6e, 0xda, 0x01, 0xb1, 0x9c, 0x49, 0xd8, 0xac, 0xf3, 0xcf, 0xca, 0xf4, 0x47, 0x10, -0x6f, 0xf0, 0x4a, 0x5c, 0x38, 0x57, 0x73, 0x97, 0xcb, 0xa1, 0xe8, 0x3e, 0x96, 0x61, 0x0d, 0x0f, -0xe0, 0x7c, 0x71, 0xcc, 0x90, 0x06, 0xf7, 0x1c, 0xc2, 0x6a, 0xae, 0x69, 0x17, 0x99, 0x3a, 0x27, -0xd9, 0xeb, 0x2b, 0x22, 0xd2, 0xa9, 0x07, 0x33, 0x2d, 0x3c, 0x15, 0xc9, 0x87, 0xaa, 0x50, 0xa5, -0x03, 0x59, 0x09, 0x1a, 0x65, 0xd7, 0x84, 0xd0, 0x82, 0x29, 0x5a, 0x1e, 0x7b, 0xa8, 0x6d, 0x2c -}; +// 32-bit optimized implementation +#include "aes_f32.h" -// combined Xtimes3[Sbox[]] -static uint8_t Xtime3Sbox[256] = { -0xa5, 0x84, 0x99, 0x8d, 0x0d, 0xbd, 0xb1, 0x54, 0x50, 0x03, 0xa9, 0x7d, 0x19, 0x62, 0xe6, 0x9a, -0x45, 0x9d, 0x40, 0x87, 0x15, 0xeb, 0xc9, 0x0b, 0xec, 0x67, 0xfd, 0xea, 0xbf, 0xf7, 0x96, 0x5b, -0xc2, 0x1c, 0xae, 0x6a, 0x5a, 0x41, 0x02, 0x4f, 0x5c, 0xf4, 0x34, 0x08, 0x93, 0x73, 0x53, 0x3f, -0x0c, 0x52, 0x65, 0x5e, 0x28, 0xa1, 0x0f, 0xb5, 0x09, 0x36, 0x9b, 0x3d, 0x26, 0x69, 0xcd, 0x9f, -0x1b, 0x9e, 0x74, 0x2e, 0x2d, 0xb2, 0xee, 0xfb, 0xf6, 0x4d, 0x61, 0xce, 0x7b, 0x3e, 0x71, 0x97, -0xf5, 0x68, 0x00, 0x2c, 0x60, 0x1f, 0xc8, 0xed, 0xbe, 0x46, 0xd9, 0x4b, 0xde, 0xd4, 0xe8, 0x4a, -0x6b, 0x2a, 0xe5, 0x16, 0xc5, 0xd7, 0x55, 0x94, 0xcf, 0x10, 0x06, 0x81, 0xf0, 0x44, 0xba, 0xe3, -0xf3, 0xfe, 0xc0, 0x8a, 0xad, 0xbc, 0x48, 0x04, 0xdf, 0xc1, 0x75, 0x63, 0x30, 0x1a, 0x0e, 0x6d, -0x4c, 0x14, 0x35, 0x2f, 0xe1, 0xa2, 0xcc, 0x39, 0x57, 0xf2, 0x82, 0x47, 0xac, 0xe7, 0x2b, 0x95, -0xa0, 0x98, 0xd1, 0x7f, 0x66, 0x7e, 0xab, 0x83, 0xca, 0x29, 0xd3, 0x3c, 0x79, 0xe2, 0x1d, 0x76, -0x3b, 0x56, 0x4e, 0x1e, 0xdb, 0x0a, 0x6c, 0xe4, 0x5d, 0x6e, 0xef, 0xa6, 0xa8, 0xa4, 0x37, 0x8b, -0x32, 0x43, 0x59, 0xb7, 0x8c, 0x64, 0xd2, 0xe0, 0xb4, 0xfa, 0x07, 0x25, 0xaf, 0x8e, 0xe9, 0x18, -0xd5, 0x88, 0x6f, 0x72, 0x24, 0xf1, 0xc7, 0x51, 0x23, 0x7c, 0x9c, 0x21, 0xdd, 0xdc, 0x86, 0x85, -0x90, 0x42, 0xc4, 0xaa, 0xd8, 0x05, 0x01, 0x12, 0xa3, 0x5f, 0xf9, 0xd0, 0x91, 0x58, 0x27, 0xb9, -0x38, 0x13, 0xb3, 0x33, 0xbb, 0x70, 0x89, 0xa7, 0xb6, 0x22, 0x92, 0x20, 0x49, 0xff, 0x78, 0x7a, -0x8f, 0xf8, 0x80, 0x17, 0xda, 0x31, 0xc6, 0xb8, 0xc3, 0xb0, 0x77, 0x11, 0xcb, 0xfc, 0xd6, 0x3a -}; +#else -// modular multiplication tables -// based on: +// Full 8-bit implementation +#include "aes_f8.h" -// Xtime2[x] = (x & 0x80 ? 0x1b : 0) ^ (x + x) -// Xtime3[x] = x^Xtime2[x]; -#if 0 -static uint8_t Xtime2[256] = { -0x00, 0x02, 0x04, 0x06, 0x08, 0x0a, 0x0c, 0x0e, 0x10, 0x12, 0x14, 0x16, 0x18, 0x1a, 0x1c, 0x1e, -0x20, 0x22, 0x24, 0x26, 0x28, 0x2a, 0x2c, 0x2e, 0x30, 0x32, 0x34, 0x36, 0x38, 0x3a, 0x3c, 0x3e, -0x40, 0x42, 0x44, 0x46, 0x48, 0x4a, 0x4c, 0x4e, 0x50, 0x52, 0x54, 0x56, 0x58, 0x5a, 0x5c, 0x5e, -0x60, 0x62, 0x64, 0x66, 0x68, 0x6a, 0x6c, 0x6e, 0x70, 0x72, 0x74, 0x76, 0x78, 0x7a, 0x7c, 0x7e, -0x80, 0x82, 0x84, 0x86, 0x88, 0x8a, 0x8c, 0x8e, 0x90, 0x92, 0x94, 0x96, 0x98, 0x9a, 0x9c, 0x9e, -0xa0, 0xa2, 0xa4, 0xa6, 0xa8, 0xaa, 0xac, 0xae, 0xb0, 0xb2, 0xb4, 0xb6, 0xb8, 0xba, 0xbc, 0xbe, -0xc0, 0xc2, 0xc4, 0xc6, 0xc8, 0xca, 0xcc, 0xce, 0xd0, 0xd2, 0xd4, 0xd6, 0xd8, 0xda, 0xdc, 0xde, -0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee, 0xf0, 0xf2, 0xf4, 0xf6, 0xf8, 0xfa, 0xfc, 0xfe, -0x1b, 0x19, 0x1f, 0x1d, 0x13, 0x11, 0x17, 0x15, 0x0b, 0x09, 0x0f, 0x0d, 0x03, 0x01, 0x07, 0x05, -0x3b, 0x39, 0x3f, 0x3d, 0x33, 0x31, 0x37, 0x35, 0x2b, 0x29, 0x2f, 0x2d, 0x23, 0x21, 0x27, 0x25, -0x5b, 0x59, 0x5f, 0x5d, 0x53, 0x51, 0x57, 0x55, 0x4b, 0x49, 0x4f, 0x4d, 0x43, 0x41, 0x47, 0x45, -0x7b, 0x79, 0x7f, 0x7d, 0x73, 0x71, 0x77, 0x75, 0x6b, 0x69, 0x6f, 0x6d, 0x63, 0x61, 0x67, 0x65, -0x9b, 0x99, 0x9f, 0x9d, 0x93, 0x91, 0x97, 0x95, 0x8b, 0x89, 0x8f, 0x8d, 0x83, 0x81, 0x87, 0x85, -0xbb, 0xb9, 0xbf, 0xbd, 0xb3, 0xb1, 0xb7, 0xb5, 0xab, 0xa9, 0xaf, 0xad, 0xa3, 0xa1, 0xa7, 0xa5, -0xdb, 0xd9, 0xdf, 0xdd, 0xd3, 0xd1, 0xd7, 0xd5, 0xcb, 0xc9, 0xcf, 0xcd, 0xc3, 0xc1, 0xc7, 0xc5, -0xfb, 0xf9, 0xff, 0xfd, 0xf3, 0xf1, 0xf7, 0xf5, 0xeb, 0xe9, 0xef, 0xed, 0xe3, 0xe1, 0xe7, 0xe5}; #endif -static uint8_t Xtime9[256] = { -0x00, 0x09, 0x12, 0x1b, 0x24, 0x2d, 0x36, 0x3f, 0x48, 0x41, 0x5a, 0x53, 0x6c, 0x65, 0x7e, 0x77, -0x90, 0x99, 0x82, 0x8b, 0xb4, 0xbd, 0xa6, 0xaf, 0xd8, 0xd1, 0xca, 0xc3, 0xfc, 0xf5, 0xee, 0xe7, -0x3b, 0x32, 0x29, 0x20, 0x1f, 0x16, 0x0d, 0x04, 0x73, 0x7a, 0x61, 0x68, 0x57, 0x5e, 0x45, 0x4c, -0xab, 0xa2, 0xb9, 0xb0, 0x8f, 0x86, 0x9d, 0x94, 0xe3, 0xea, 0xf1, 0xf8, 0xc7, 0xce, 0xd5, 0xdc, -0x76, 0x7f, 0x64, 0x6d, 0x52, 0x5b, 0x40, 0x49, 0x3e, 0x37, 0x2c, 0x25, 0x1a, 0x13, 0x08, 0x01, -0xe6, 0xef, 0xf4, 0xfd, 0xc2, 0xcb, 0xd0, 0xd9, 0xae, 0xa7, 0xbc, 0xb5, 0x8a, 0x83, 0x98, 0x91, -0x4d, 0x44, 0x5f, 0x56, 0x69, 0x60, 0x7b, 0x72, 0x05, 0x0c, 0x17, 0x1e, 0x21, 0x28, 0x33, 0x3a, -0xdd, 0xd4, 0xcf, 0xc6, 0xf9, 0xf0, 0xeb, 0xe2, 0x95, 0x9c, 0x87, 0x8e, 0xb1, 0xb8, 0xa3, 0xaa, -0xec, 0xe5, 0xfe, 0xf7, 0xc8, 0xc1, 0xda, 0xd3, 0xa4, 0xad, 0xb6, 0xbf, 0x80, 0x89, 0x92, 0x9b, -0x7c, 0x75, 0x6e, 0x67, 0x58, 0x51, 0x4a, 0x43, 0x34, 0x3d, 0x26, 0x2f, 0x10, 0x19, 0x02, 0x0b, -0xd7, 0xde, 0xc5, 0xcc, 0xf3, 0xfa, 0xe1, 0xe8, 0x9f, 0x96, 0x8d, 0x84, 0xbb, 0xb2, 0xa9, 0xa0, -0x47, 0x4e, 0x55, 0x5c, 0x63, 0x6a, 0x71, 0x78, 0x0f, 0x06, 0x1d, 0x14, 0x2b, 0x22, 0x39, 0x30, -0x9a, 0x93, 0x88, 0x81, 0xbe, 0xb7, 0xac, 0xa5, 0xd2, 0xdb, 0xc0, 0xc9, 0xf6, 0xff, 0xe4, 0xed, -0x0a, 0x03, 0x18, 0x11, 0x2e, 0x27, 0x3c, 0x35, 0x42, 0x4b, 0x50, 0x59, 0x66, 0x6f, 0x74, 0x7d, -0xa1, 0xa8, 0xb3, 0xba, 0x85, 0x8c, 0x97, 0x9e, 0xe9, 0xe0, 0xfb, 0xf2, 0xcd, 0xc4, 0xdf, 0xd6, -0x31, 0x38, 0x23, 0x2a, 0x15, 0x1c, 0x07, 0x0e, 0x79, 0x70, 0x6b, 0x62, 0x5d, 0x54, 0x4f, 0x46}; - -static uint8_t XtimeB[256] = { -0x00, 0x0b, 0x16, 0x1d, 0x2c, 0x27, 0x3a, 0x31, 0x58, 0x53, 0x4e, 0x45, 0x74, 0x7f, 0x62, 0x69, -0xb0, 0xbb, 0xa6, 0xad, 0x9c, 0x97, 0x8a, 0x81, 0xe8, 0xe3, 0xfe, 0xf5, 0xc4, 0xcf, 0xd2, 0xd9, -0x7b, 0x70, 0x6d, 0x66, 0x57, 0x5c, 0x41, 0x4a, 0x23, 0x28, 0x35, 0x3e, 0x0f, 0x04, 0x19, 0x12, -0xcb, 0xc0, 0xdd, 0xd6, 0xe7, 0xec, 0xf1, 0xfa, 0x93, 0x98, 0x85, 0x8e, 0xbf, 0xb4, 0xa9, 0xa2, -0xf6, 0xfd, 0xe0, 0xeb, 0xda, 0xd1, 0xcc, 0xc7, 0xae, 0xa5, 0xb8, 0xb3, 0x82, 0x89, 0x94, 0x9f, -0x46, 0x4d, 0x50, 0x5b, 0x6a, 0x61, 0x7c, 0x77, 0x1e, 0x15, 0x08, 0x03, 0x32, 0x39, 0x24, 0x2f, -0x8d, 0x86, 0x9b, 0x90, 0xa1, 0xaa, 0xb7, 0xbc, 0xd5, 0xde, 0xc3, 0xc8, 0xf9, 0xf2, 0xef, 0xe4, -0x3d, 0x36, 0x2b, 0x20, 0x11, 0x1a, 0x07, 0x0c, 0x65, 0x6e, 0x73, 0x78, 0x49, 0x42, 0x5f, 0x54, -0xf7, 0xfc, 0xe1, 0xea, 0xdb, 0xd0, 0xcd, 0xc6, 0xaf, 0xa4, 0xb9, 0xb2, 0x83, 0x88, 0x95, 0x9e, -0x47, 0x4c, 0x51, 0x5a, 0x6b, 0x60, 0x7d, 0x76, 0x1f, 0x14, 0x09, 0x02, 0x33, 0x38, 0x25, 0x2e, -0x8c, 0x87, 0x9a, 0x91, 0xa0, 0xab, 0xb6, 0xbd, 0xd4, 0xdf, 0xc2, 0xc9, 0xf8, 0xf3, 0xee, 0xe5, -0x3c, 0x37, 0x2a, 0x21, 0x10, 0x1b, 0x06, 0x0d, 0x64, 0x6f, 0x72, 0x79, 0x48, 0x43, 0x5e, 0x55, -0x01, 0x0a, 0x17, 0x1c, 0x2d, 0x26, 0x3b, 0x30, 0x59, 0x52, 0x4f, 0x44, 0x75, 0x7e, 0x63, 0x68, -0xb1, 0xba, 0xa7, 0xac, 0x9d, 0x96, 0x8b, 0x80, 0xe9, 0xe2, 0xff, 0xf4, 0xc5, 0xce, 0xd3, 0xd8, -0x7a, 0x71, 0x6c, 0x67, 0x56, 0x5d, 0x40, 0x4b, 0x22, 0x29, 0x34, 0x3f, 0x0e, 0x05, 0x18, 0x13, -0xca, 0xc1, 0xdc, 0xd7, 0xe6, 0xed, 0xf0, 0xfb, 0x92, 0x99, 0x84, 0x8f, 0xbe, 0xb5, 0xa8, 0xa3}; - -static uint8_t XtimeD[256] = { -0x00, 0x0d, 0x1a, 0x17, 0x34, 0x39, 0x2e, 0x23, 0x68, 0x65, 0x72, 0x7f, 0x5c, 0x51, 0x46, 0x4b, -0xd0, 0xdd, 0xca, 0xc7, 0xe4, 0xe9, 0xfe, 0xf3, 0xb8, 0xb5, 0xa2, 0xaf, 0x8c, 0x81, 0x96, 0x9b, -0xbb, 0xb6, 0xa1, 0xac, 0x8f, 0x82, 0x95, 0x98, 0xd3, 0xde, 0xc9, 0xc4, 0xe7, 0xea, 0xfd, 0xf0, -0x6b, 0x66, 0x71, 0x7c, 0x5f, 0x52, 0x45, 0x48, 0x03, 0x0e, 0x19, 0x14, 0x37, 0x3a, 0x2d, 0x20, -0x6d, 0x60, 0x77, 0x7a, 0x59, 0x54, 0x43, 0x4e, 0x05, 0x08, 0x1f, 0x12, 0x31, 0x3c, 0x2b, 0x26, -0xbd, 0xb0, 0xa7, 0xaa, 0x89, 0x84, 0x93, 0x9e, 0xd5, 0xd8, 0xcf, 0xc2, 0xe1, 0xec, 0xfb, 0xf6, -0xd6, 0xdb, 0xcc, 0xc1, 0xe2, 0xef, 0xf8, 0xf5, 0xbe, 0xb3, 0xa4, 0xa9, 0x8a, 0x87, 0x90, 0x9d, -0x06, 0x0b, 0x1c, 0x11, 0x32, 0x3f, 0x28, 0x25, 0x6e, 0x63, 0x74, 0x79, 0x5a, 0x57, 0x40, 0x4d, -0xda, 0xd7, 0xc0, 0xcd, 0xee, 0xe3, 0xf4, 0xf9, 0xb2, 0xbf, 0xa8, 0xa5, 0x86, 0x8b, 0x9c, 0x91, -0x0a, 0x07, 0x10, 0x1d, 0x3e, 0x33, 0x24, 0x29, 0x62, 0x6f, 0x78, 0x75, 0x56, 0x5b, 0x4c, 0x41, -0x61, 0x6c, 0x7b, 0x76, 0x55, 0x58, 0x4f, 0x42, 0x09, 0x04, 0x13, 0x1e, 0x3d, 0x30, 0x27, 0x2a, -0xb1, 0xbc, 0xab, 0xa6, 0x85, 0x88, 0x9f, 0x92, 0xd9, 0xd4, 0xc3, 0xce, 0xed, 0xe0, 0xf7, 0xfa, -0xb7, 0xba, 0xad, 0xa0, 0x83, 0x8e, 0x99, 0x94, 0xdf, 0xd2, 0xc5, 0xc8, 0xeb, 0xe6, 0xf1, 0xfc, -0x67, 0x6a, 0x7d, 0x70, 0x53, 0x5e, 0x49, 0x44, 0x0f, 0x02, 0x15, 0x18, 0x3b, 0x36, 0x21, 0x2c, -0x0c, 0x01, 0x16, 0x1b, 0x38, 0x35, 0x22, 0x2f, 0x64, 0x69, 0x7e, 0x73, 0x50, 0x5d, 0x4a, 0x47, -0xdc, 0xd1, 0xc6, 0xcb, 0xe8, 0xe5, 0xf2, 0xff, 0xb4, 0xb9, 0xae, 0xa3, 0x80, 0x8d, 0x9a, 0x97}; - -static uint8_t XtimeE[256] = { -0x00, 0x0e, 0x1c, 0x12, 0x38, 0x36, 0x24, 0x2a, 0x70, 0x7e, 0x6c, 0x62, 0x48, 0x46, 0x54, 0x5a, -0xe0, 0xee, 0xfc, 0xf2, 0xd8, 0xd6, 0xc4, 0xca, 0x90, 0x9e, 0x8c, 0x82, 0xa8, 0xa6, 0xb4, 0xba, -0xdb, 0xd5, 0xc7, 0xc9, 0xe3, 0xed, 0xff, 0xf1, 0xab, 0xa5, 0xb7, 0xb9, 0x93, 0x9d, 0x8f, 0x81, -0x3b, 0x35, 0x27, 0x29, 0x03, 0x0d, 0x1f, 0x11, 0x4b, 0x45, 0x57, 0x59, 0x73, 0x7d, 0x6f, 0x61, -0xad, 0xa3, 0xb1, 0xbf, 0x95, 0x9b, 0x89, 0x87, 0xdd, 0xd3, 0xc1, 0xcf, 0xe5, 0xeb, 0xf9, 0xf7, -0x4d, 0x43, 0x51, 0x5f, 0x75, 0x7b, 0x69, 0x67, 0x3d, 0x33, 0x21, 0x2f, 0x05, 0x0b, 0x19, 0x17, -0x76, 0x78, 0x6a, 0x64, 0x4e, 0x40, 0x52, 0x5c, 0x06, 0x08, 0x1a, 0x14, 0x3e, 0x30, 0x22, 0x2c, -0x96, 0x98, 0x8a, 0x84, 0xae, 0xa0, 0xb2, 0xbc, 0xe6, 0xe8, 0xfa, 0xf4, 0xde, 0xd0, 0xc2, 0xcc, -0x41, 0x4f, 0x5d, 0x53, 0x79, 0x77, 0x65, 0x6b, 0x31, 0x3f, 0x2d, 0x23, 0x09, 0x07, 0x15, 0x1b, -0xa1, 0xaf, 0xbd, 0xb3, 0x99, 0x97, 0x85, 0x8b, 0xd1, 0xdf, 0xcd, 0xc3, 0xe9, 0xe7, 0xf5, 0xfb, -0x9a, 0x94, 0x86, 0x88, 0xa2, 0xac, 0xbe, 0xb0, 0xea, 0xe4, 0xf6, 0xf8, 0xd2, 0xdc, 0xce, 0xc0, -0x7a, 0x74, 0x66, 0x68, 0x42, 0x4c, 0x5e, 0x50, 0x0a, 0x04, 0x16, 0x18, 0x32, 0x3c, 0x2e, 0x20, -0xec, 0xe2, 0xf0, 0xfe, 0xd4, 0xda, 0xc8, 0xc6, 0x9c, 0x92, 0x80, 0x8e, 0xa4, 0xaa, 0xb8, 0xb6, -0x0c, 0x02, 0x10, 0x1e, 0x34, 0x3a, 0x28, 0x26, 0x7c, 0x72, 0x60, 0x6e, 0x44, 0x4a, 0x58, 0x56, -0x37, 0x39, 0x2b, 0x25, 0x0f, 0x01, 0x13, 0x1d, 0x47, 0x49, 0x5b, 0x55, 0x7f, 0x71, 0x63, 0x6d, -0xd7, 0xd9, 0xcb, 0xc5, 0xef, 0xe1, 0xf3, 0xfd, 0xa7, 0xa9, 0xbb, 0xb5, 0x9f, 0x91, 0x83, 0x8d}; - -// exchanges columns in each of 4 rows -// row0 - unchanged, row1- shifted left 1, -// row2 - shifted left 2 and row3 - shifted left 3 -static void ShiftRows (uint8_t *state) -{ - uint8_t tmp; - - // just substitute row 0 - state[0] = Sbox[state[0]], state[4] = Sbox[state[4]]; - state[8] = Sbox[state[8]], state[12] = Sbox[state[12]]; - - // rotate row 1 - tmp = Sbox[state[1]], state[1] = Sbox[state[5]]; - state[5] = Sbox[state[9]], state[9] = Sbox[state[13]], state[13] = tmp; - - // rotate row 2 - tmp = Sbox[state[2]], state[2] = Sbox[state[10]], state[10] = tmp; - tmp = Sbox[state[6]], state[6] = Sbox[state[14]], state[14] = tmp; - - // rotate row 3 - tmp = Sbox[state[15]], state[15] = Sbox[state[11]]; - state[11] = Sbox[state[7]], state[7] = Sbox[state[3]], state[3] = tmp; -} - -// restores columns in each of 4 rows -// row0 - unchanged, row1- shifted right 1, -// row2 - shifted right 2 and row3 - shifted right 3 -static void InvShiftRows (uint8_t *state) -{ - uint8_t tmp; - - // restore row 0 - state[0] = InvSbox[state[0]], state[4] = InvSbox[state[4]]; - state[8] = InvSbox[state[8]], state[12] = InvSbox[state[12]]; - - // restore row 1 - tmp = InvSbox[state[13]], state[13] = InvSbox[state[9]]; - state[9] = InvSbox[state[5]], state[5] = InvSbox[state[1]], state[1] = tmp; - - // restore row 2 - tmp = InvSbox[state[2]], state[2] = InvSbox[state[10]], state[10] = tmp; - tmp = InvSbox[state[6]], state[6] = InvSbox[state[14]], state[14] = tmp; - - // restore row 3 - tmp = InvSbox[state[3]], state[3] = InvSbox[state[7]]; - state[7] = InvSbox[state[11]], state[11] = InvSbox[state[15]], state[15] = tmp; -} - -// recombine and mix each row in a column -static void MixSubColumns (uint8_t *state) -{ - uint8_t tmp[4 * Nb]; - - // mixing column 0 - tmp[0] = Xtime2Sbox[state[0]] ^ Xtime3Sbox[state[5]] ^ Sbox[state[10]] ^ Sbox[state[15]]; - tmp[1] = Sbox[state[0]] ^ Xtime2Sbox[state[5]] ^ Xtime3Sbox[state[10]] ^ Sbox[state[15]]; - tmp[2] = Sbox[state[0]] ^ Sbox[state[5]] ^ Xtime2Sbox[state[10]] ^ Xtime3Sbox[state[15]]; - tmp[3] = Xtime3Sbox[state[0]] ^ Sbox[state[5]] ^ Sbox[state[10]] ^ Xtime2Sbox[state[15]]; - - // mixing column 1 - tmp[4] = Xtime2Sbox[state[4]] ^ Xtime3Sbox[state[9]] ^ Sbox[state[14]] ^ Sbox[state[3]]; - tmp[5] = Sbox[state[4]] ^ Xtime2Sbox[state[9]] ^ Xtime3Sbox[state[14]] ^ Sbox[state[3]]; - tmp[6] = Sbox[state[4]] ^ Sbox[state[9]] ^ Xtime2Sbox[state[14]] ^ Xtime3Sbox[state[3]]; - tmp[7] = Xtime3Sbox[state[4]] ^ Sbox[state[9]] ^ Sbox[state[14]] ^ Xtime2Sbox[state[3]]; - - // mixing column 2 - tmp[8] = Xtime2Sbox[state[8]] ^ Xtime3Sbox[state[13]] ^ Sbox[state[2]] ^ Sbox[state[7]]; - tmp[9] = Sbox[state[8]] ^ Xtime2Sbox[state[13]] ^ Xtime3Sbox[state[2]] ^ Sbox[state[7]]; - tmp[10] = Sbox[state[8]] ^ Sbox[state[13]] ^ Xtime2Sbox[state[2]] ^ Xtime3Sbox[state[7]]; - tmp[11] = Xtime3Sbox[state[8]] ^ Sbox[state[13]] ^ Sbox[state[2]] ^ Xtime2Sbox[state[7]]; - - // mixing column 3 - tmp[12] = Xtime2Sbox[state[12]] ^ Xtime3Sbox[state[1]] ^ Sbox[state[6]] ^ Sbox[state[11]]; - tmp[13] = Sbox[state[12]] ^ Xtime2Sbox[state[1]] ^ Xtime3Sbox[state[6]] ^ Sbox[state[11]]; - tmp[14] = Sbox[state[12]] ^ Sbox[state[1]] ^ Xtime2Sbox[state[6]] ^ Xtime3Sbox[state[11]]; - tmp[15] = Xtime3Sbox[state[12]] ^ Sbox[state[1]] ^ Sbox[state[6]] ^ Xtime2Sbox[state[11]]; - - memcpy (state, tmp, sizeof(tmp)); -} - -// restore and un-mix each row in a column -static void InvMixSubColumns (uint8_t *state) -{ - uint8_t tmp[4 * Nb]; - int i; - - // restore column 0 - tmp[0] = XtimeE[state[0]] ^ XtimeB[state[1]] ^ XtimeD[state[2]] ^ Xtime9[state[3]]; - tmp[5] = Xtime9[state[0]] ^ XtimeE[state[1]] ^ XtimeB[state[2]] ^ XtimeD[state[3]]; - tmp[10] = XtimeD[state[0]] ^ Xtime9[state[1]] ^ XtimeE[state[2]] ^ XtimeB[state[3]]; - tmp[15] = XtimeB[state[0]] ^ XtimeD[state[1]] ^ Xtime9[state[2]] ^ XtimeE[state[3]]; - - // restore column 1 - tmp[4] = XtimeE[state[4]] ^ XtimeB[state[5]] ^ XtimeD[state[6]] ^ Xtime9[state[7]]; - tmp[9] = Xtime9[state[4]] ^ XtimeE[state[5]] ^ XtimeB[state[6]] ^ XtimeD[state[7]]; - tmp[14] = XtimeD[state[4]] ^ Xtime9[state[5]] ^ XtimeE[state[6]] ^ XtimeB[state[7]]; - tmp[3] = XtimeB[state[4]] ^ XtimeD[state[5]] ^ Xtime9[state[6]] ^ XtimeE[state[7]]; - - // restore column 2 - tmp[8] = XtimeE[state[8]] ^ XtimeB[state[9]] ^ XtimeD[state[10]] ^ Xtime9[state[11]]; - tmp[13] = Xtime9[state[8]] ^ XtimeE[state[9]] ^ XtimeB[state[10]] ^ XtimeD[state[11]]; - tmp[2] = XtimeD[state[8]] ^ Xtime9[state[9]] ^ XtimeE[state[10]] ^ XtimeB[state[11]]; - tmp[7] = XtimeB[state[8]] ^ XtimeD[state[9]] ^ Xtime9[state[10]] ^ XtimeE[state[11]]; - - // restore column 3 - tmp[12] = XtimeE[state[12]] ^ XtimeB[state[13]] ^ XtimeD[state[14]] ^ Xtime9[state[15]]; - tmp[1] = Xtime9[state[12]] ^ XtimeE[state[13]] ^ XtimeB[state[14]] ^ XtimeD[state[15]]; - tmp[6] = XtimeD[state[12]] ^ Xtime9[state[13]] ^ XtimeE[state[14]] ^ XtimeB[state[15]]; - tmp[11] = XtimeB[state[12]] ^ XtimeD[state[13]] ^ Xtime9[state[14]] ^ XtimeE[state[15]]; - - for( i=0; i < 4 * Nb; i++ ) - state[i] = InvSbox[tmp[i]]; -} - -// encrypt/decrypt columns of the key -// n.b. you can replace this with -// byte-wise xor if you wish. - -static void AddRoundKey (uint32_t *state, uint32_t *key) -{ - int idx; - - for( idx = 0; idx < 4; idx++ ) - state[idx] ^= key[idx]; -} - -static uint8_t Rcon[11] = -{ - 0x00, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36 -}; - -#include - -// produce Nb bytes for each round -static void AES_expandKey(BlockCipher *c_, const void *key, size_t len) -{ - AES_Context *c = (AES_Context *)c_; - ASSERT(len == c->c.key_len); - - uint8_t tmp0, tmp1, tmp2, tmp3, tmp4; - uint32_t idx, idx_mod_nk, idx_div_nk; - int Nk = c->c.key_len/4; - int Nr = c->num_rounds; - - memcpy (c->expkey, key, Nk*4); - - for( idx = Nk, idx_mod_nk = 0, idx_div_nk = 1; idx < Nb * (Nr + 1); idx++ ) { - tmp0 = c->expkey[4*idx - 4]; - tmp1 = c->expkey[4*idx - 3]; - tmp2 = c->expkey[4*idx - 2]; - tmp3 = c->expkey[4*idx - 1]; - - if( idx_mod_nk == 0 ) { - tmp4 = tmp3; - tmp3 = Sbox[tmp0]; - tmp0 = Sbox[tmp1] ^ Rcon[idx_div_nk]; - tmp1 = Sbox[tmp2]; - tmp2 = Sbox[tmp4]; - } else if( Nk > 6 && idx_mod_nk == 4 ) { - tmp0 = Sbox[tmp0]; - tmp1 = Sbox[tmp1]; - tmp2 = Sbox[tmp2]; - tmp3 = Sbox[tmp3]; - } - - c->expkey[4*idx+0] = c->expkey[4*idx - 4*Nk + 0] ^ tmp0; - c->expkey[4*idx+1] = c->expkey[4*idx - 4*Nk + 1] ^ tmp1; - c->expkey[4*idx+2] = c->expkey[4*idx - 4*Nk + 2] ^ tmp2; - c->expkey[4*idx+3] = c->expkey[4*idx - 4*Nk + 3] ^ tmp3; - - idx_mod_nk += 1; - if (idx_mod_nk == Nk) - { - idx_mod_nk = 0; - ++idx_div_nk; - } - } -} - -// encrypt one 128 bit block -static void AES_encrypt(BlockCipher *c_, void *block) -{ - AES_Context *c = (AES_Context *)c_; - uint8_t Nr = c->num_rounds; - uint32_t round; - - AddRoundKey ((uint32_t *)block, (uint32_t *)c->expkey); - - for( round = 1; round < Nr + 1; round++ ) { - if( round < Nr ) - MixSubColumns (block); - else - ShiftRows (block); - - AddRoundKey ((uint32_t *)block, (uint32_t *)c->expkey + round * Nb); - } -} - -static void AES_decrypt(BlockCipher *c_, void *block) -{ - AES_Context *c = (AES_Context *)c_; - uint8_t Nr = c->num_rounds; - uint32_t round; - - AddRoundKey ((uint32_t *)block, (uint32_t *)c->expkey + Nr * Nb); - InvShiftRows(block); - - for( round = Nr; round--; ) - { - AddRoundKey ((uint32_t *)block, (uint32_t *)c->expkey + round * Nb); - if( round ) - InvMixSubColumns (block); - } -} /******************************************************************************/ -void AES128_init(AES128_Context *aes) +void AES128_init(AES128_Context *aes_) { + AES_Context *aes = (AES_Context *)aes_; aes->c.set_key = AES_expandKey; aes->c.enc_block = AES_encrypt; aes->c.dec_block = AES_decrypt; @@ -468,8 +84,9 @@ void AES128_init(AES128_Context *aes) aes->num_rounds = 10; } -void AES192_init(AES192_Context *aes) +void AES192_init(AES192_Context *aes_) { + AES_Context *aes = (AES_Context *)aes_; aes->c.set_key = AES_expandKey; aes->c.enc_block = AES_encrypt; aes->c.dec_block = AES_decrypt; @@ -478,8 +95,9 @@ void AES192_init(AES192_Context *aes) aes->num_rounds = 12; } -void AES256_init(AES256_Context *aes) +void AES256_init(AES256_Context *aes_) { + AES_Context *aes = (AES_Context *)aes_; aes->c.set_key = AES_expandKey; aes->c.enc_block = AES_encrypt; aes->c.dec_block = AES_decrypt; diff --git a/bertos/sec/cipher/aes.h b/bertos/sec/cipher/aes.h index 587f3f74..7be6265e 100644 --- a/bertos/sec/cipher/aes.h +++ b/bertos/sec/cipher/aes.h @@ -41,26 +41,27 @@ #define SEC_CIPHER_AES_H #include +#include #include typedef struct { BlockCipher c; - int num_rounds; + uint32_t status; uint8_t expkey[44*4]; } AES128_Context; typedef struct { BlockCipher c; - int num_rounds; + uint32_t status; uint8_t expkey[52*4]; } AES192_Context; typedef struct { BlockCipher c; - int num_rounds; + uint32_t status; uint8_t expkey[60*4]; } AES256_Context; diff --git a/bertos/sec/cipher/aes_f32.h b/bertos/sec/cipher/aes_f32.h new file mode 100644 index 00000000..d172388d --- /dev/null +++ b/bertos/sec/cipher/aes_f32.h @@ -0,0 +1,566 @@ +/** + * \file + * + * + * \brief AES Advanced Encryption Standard implementation + * + * \author Giovanni Bajo + * + */ + +/*****************************************************************************/ +// ENCRYPTION TABLES +/*****************************************************************************/ + +static const uint32_t TE0[256] = +{ + be32_to_cpu(0xc66363a5UL), be32_to_cpu(0xf87c7c84UL), be32_to_cpu(0xee777799UL), be32_to_cpu(0xf67b7b8dUL), + be32_to_cpu(0xfff2f20dUL), be32_to_cpu(0xd66b6bbdUL), be32_to_cpu(0xde6f6fb1UL), be32_to_cpu(0x91c5c554UL), + be32_to_cpu(0x60303050UL), be32_to_cpu(0x02010103UL), be32_to_cpu(0xce6767a9UL), be32_to_cpu(0x562b2b7dUL), + be32_to_cpu(0xe7fefe19UL), be32_to_cpu(0xb5d7d762UL), be32_to_cpu(0x4dababe6UL), be32_to_cpu(0xec76769aUL), + be32_to_cpu(0x8fcaca45UL), be32_to_cpu(0x1f82829dUL), be32_to_cpu(0x89c9c940UL), be32_to_cpu(0xfa7d7d87UL), + be32_to_cpu(0xeffafa15UL), be32_to_cpu(0xb25959ebUL), be32_to_cpu(0x8e4747c9UL), be32_to_cpu(0xfbf0f00bUL), + be32_to_cpu(0x41adadecUL), be32_to_cpu(0xb3d4d467UL), be32_to_cpu(0x5fa2a2fdUL), be32_to_cpu(0x45afafeaUL), + be32_to_cpu(0x239c9cbfUL), be32_to_cpu(0x53a4a4f7UL), be32_to_cpu(0xe4727296UL), be32_to_cpu(0x9bc0c05bUL), + be32_to_cpu(0x75b7b7c2UL), be32_to_cpu(0xe1fdfd1cUL), be32_to_cpu(0x3d9393aeUL), be32_to_cpu(0x4c26266aUL), + be32_to_cpu(0x6c36365aUL), be32_to_cpu(0x7e3f3f41UL), be32_to_cpu(0xf5f7f702UL), be32_to_cpu(0x83cccc4fUL), + be32_to_cpu(0x6834345cUL), be32_to_cpu(0x51a5a5f4UL), be32_to_cpu(0xd1e5e534UL), be32_to_cpu(0xf9f1f108UL), + be32_to_cpu(0xe2717193UL), be32_to_cpu(0xabd8d873UL), be32_to_cpu(0x62313153UL), be32_to_cpu(0x2a15153fUL), + be32_to_cpu(0x0804040cUL), be32_to_cpu(0x95c7c752UL), be32_to_cpu(0x46232365UL), be32_to_cpu(0x9dc3c35eUL), + be32_to_cpu(0x30181828UL), be32_to_cpu(0x379696a1UL), be32_to_cpu(0x0a05050fUL), be32_to_cpu(0x2f9a9ab5UL), + be32_to_cpu(0x0e070709UL), be32_to_cpu(0x24121236UL), be32_to_cpu(0x1b80809bUL), be32_to_cpu(0xdfe2e23dUL), + be32_to_cpu(0xcdebeb26UL), be32_to_cpu(0x4e272769UL), be32_to_cpu(0x7fb2b2cdUL), be32_to_cpu(0xea75759fUL), + be32_to_cpu(0x1209091bUL), be32_to_cpu(0x1d83839eUL), be32_to_cpu(0x582c2c74UL), be32_to_cpu(0x341a1a2eUL), + be32_to_cpu(0x361b1b2dUL), be32_to_cpu(0xdc6e6eb2UL), be32_to_cpu(0xb45a5aeeUL), be32_to_cpu(0x5ba0a0fbUL), + be32_to_cpu(0xa45252f6UL), be32_to_cpu(0x763b3b4dUL), be32_to_cpu(0xb7d6d661UL), be32_to_cpu(0x7db3b3ceUL), + be32_to_cpu(0x5229297bUL), be32_to_cpu(0xdde3e33eUL), be32_to_cpu(0x5e2f2f71UL), be32_to_cpu(0x13848497UL), + be32_to_cpu(0xa65353f5UL), be32_to_cpu(0xb9d1d168UL), be32_to_cpu(0x00000000UL), be32_to_cpu(0xc1eded2cUL), + be32_to_cpu(0x40202060UL), be32_to_cpu(0xe3fcfc1fUL), be32_to_cpu(0x79b1b1c8UL), be32_to_cpu(0xb65b5bedUL), + be32_to_cpu(0xd46a6abeUL), be32_to_cpu(0x8dcbcb46UL), be32_to_cpu(0x67bebed9UL), be32_to_cpu(0x7239394bUL), + be32_to_cpu(0x944a4adeUL), be32_to_cpu(0x984c4cd4UL), be32_to_cpu(0xb05858e8UL), be32_to_cpu(0x85cfcf4aUL), + be32_to_cpu(0xbbd0d06bUL), be32_to_cpu(0xc5efef2aUL), be32_to_cpu(0x4faaaae5UL), be32_to_cpu(0xedfbfb16UL), + be32_to_cpu(0x864343c5UL), be32_to_cpu(0x9a4d4dd7UL), be32_to_cpu(0x66333355UL), be32_to_cpu(0x11858594UL), + be32_to_cpu(0x8a4545cfUL), be32_to_cpu(0xe9f9f910UL), be32_to_cpu(0x04020206UL), be32_to_cpu(0xfe7f7f81UL), + be32_to_cpu(0xa05050f0UL), be32_to_cpu(0x783c3c44UL), be32_to_cpu(0x259f9fbaUL), be32_to_cpu(0x4ba8a8e3UL), + be32_to_cpu(0xa25151f3UL), be32_to_cpu(0x5da3a3feUL), be32_to_cpu(0x804040c0UL), be32_to_cpu(0x058f8f8aUL), + be32_to_cpu(0x3f9292adUL), be32_to_cpu(0x219d9dbcUL), be32_to_cpu(0x70383848UL), be32_to_cpu(0xf1f5f504UL), + be32_to_cpu(0x63bcbcdfUL), be32_to_cpu(0x77b6b6c1UL), be32_to_cpu(0xafdada75UL), be32_to_cpu(0x42212163UL), + be32_to_cpu(0x20101030UL), be32_to_cpu(0xe5ffff1aUL), be32_to_cpu(0xfdf3f30eUL), be32_to_cpu(0xbfd2d26dUL), + be32_to_cpu(0x81cdcd4cUL), be32_to_cpu(0x180c0c14UL), be32_to_cpu(0x26131335UL), be32_to_cpu(0xc3ecec2fUL), + be32_to_cpu(0xbe5f5fe1UL), be32_to_cpu(0x359797a2UL), be32_to_cpu(0x884444ccUL), be32_to_cpu(0x2e171739UL), + be32_to_cpu(0x93c4c457UL), be32_to_cpu(0x55a7a7f2UL), be32_to_cpu(0xfc7e7e82UL), be32_to_cpu(0x7a3d3d47UL), + be32_to_cpu(0xc86464acUL), be32_to_cpu(0xba5d5de7UL), be32_to_cpu(0x3219192bUL), be32_to_cpu(0xe6737395UL), + be32_to_cpu(0xc06060a0UL), be32_to_cpu(0x19818198UL), be32_to_cpu(0x9e4f4fd1UL), be32_to_cpu(0xa3dcdc7fUL), + be32_to_cpu(0x44222266UL), be32_to_cpu(0x542a2a7eUL), be32_to_cpu(0x3b9090abUL), be32_to_cpu(0x0b888883UL), + be32_to_cpu(0x8c4646caUL), be32_to_cpu(0xc7eeee29UL), be32_to_cpu(0x6bb8b8d3UL), be32_to_cpu(0x2814143cUL), + be32_to_cpu(0xa7dede79UL), be32_to_cpu(0xbc5e5ee2UL), be32_to_cpu(0x160b0b1dUL), be32_to_cpu(0xaddbdb76UL), + be32_to_cpu(0xdbe0e03bUL), be32_to_cpu(0x64323256UL), be32_to_cpu(0x743a3a4eUL), be32_to_cpu(0x140a0a1eUL), + be32_to_cpu(0x924949dbUL), be32_to_cpu(0x0c06060aUL), be32_to_cpu(0x4824246cUL), be32_to_cpu(0xb85c5ce4UL), + be32_to_cpu(0x9fc2c25dUL), be32_to_cpu(0xbdd3d36eUL), be32_to_cpu(0x43acacefUL), be32_to_cpu(0xc46262a6UL), + be32_to_cpu(0x399191a8UL), be32_to_cpu(0x319595a4UL), be32_to_cpu(0xd3e4e437UL), be32_to_cpu(0xf279798bUL), + be32_to_cpu(0xd5e7e732UL), be32_to_cpu(0x8bc8c843UL), be32_to_cpu(0x6e373759UL), be32_to_cpu(0xda6d6db7UL), + be32_to_cpu(0x018d8d8cUL), be32_to_cpu(0xb1d5d564UL), be32_to_cpu(0x9c4e4ed2UL), be32_to_cpu(0x49a9a9e0UL), + be32_to_cpu(0xd86c6cb4UL), be32_to_cpu(0xac5656faUL), be32_to_cpu(0xf3f4f407UL), be32_to_cpu(0xcfeaea25UL), + be32_to_cpu(0xca6565afUL), be32_to_cpu(0xf47a7a8eUL), be32_to_cpu(0x47aeaee9UL), be32_to_cpu(0x10080818UL), + be32_to_cpu(0x6fbabad5UL), be32_to_cpu(0xf0787888UL), be32_to_cpu(0x4a25256fUL), be32_to_cpu(0x5c2e2e72UL), + be32_to_cpu(0x381c1c24UL), be32_to_cpu(0x57a6a6f1UL), be32_to_cpu(0x73b4b4c7UL), be32_to_cpu(0x97c6c651UL), + be32_to_cpu(0xcbe8e823UL), be32_to_cpu(0xa1dddd7cUL), be32_to_cpu(0xe874749cUL), be32_to_cpu(0x3e1f1f21UL), + be32_to_cpu(0x964b4bddUL), be32_to_cpu(0x61bdbddcUL), be32_to_cpu(0x0d8b8b86UL), be32_to_cpu(0x0f8a8a85UL), + be32_to_cpu(0xe0707090UL), be32_to_cpu(0x7c3e3e42UL), be32_to_cpu(0x71b5b5c4UL), be32_to_cpu(0xcc6666aaUL), + be32_to_cpu(0x904848d8UL), be32_to_cpu(0x06030305UL), be32_to_cpu(0xf7f6f601UL), be32_to_cpu(0x1c0e0e12UL), + be32_to_cpu(0xc26161a3UL), be32_to_cpu(0x6a35355fUL), be32_to_cpu(0xae5757f9UL), be32_to_cpu(0x69b9b9d0UL), + be32_to_cpu(0x17868691UL), be32_to_cpu(0x99c1c158UL), be32_to_cpu(0x3a1d1d27UL), be32_to_cpu(0x279e9eb9UL), + be32_to_cpu(0xd9e1e138UL), be32_to_cpu(0xebf8f813UL), be32_to_cpu(0x2b9898b3UL), be32_to_cpu(0x22111133UL), + be32_to_cpu(0xd26969bbUL), be32_to_cpu(0xa9d9d970UL), be32_to_cpu(0x078e8e89UL), be32_to_cpu(0x339494a7UL), + be32_to_cpu(0x2d9b9bb6UL), be32_to_cpu(0x3c1e1e22UL), be32_to_cpu(0x15878792UL), be32_to_cpu(0xc9e9e920UL), + be32_to_cpu(0x87cece49UL), be32_to_cpu(0xaa5555ffUL), be32_to_cpu(0x50282878UL), be32_to_cpu(0xa5dfdf7aUL), + be32_to_cpu(0x038c8c8fUL), be32_to_cpu(0x59a1a1f8UL), be32_to_cpu(0x09898980UL), be32_to_cpu(0x1a0d0d17UL), + be32_to_cpu(0x65bfbfdaUL), be32_to_cpu(0xd7e6e631UL), be32_to_cpu(0x844242c6UL), be32_to_cpu(0xd06868b8UL), + be32_to_cpu(0x824141c3UL), be32_to_cpu(0x299999b0UL), be32_to_cpu(0x5a2d2d77UL), be32_to_cpu(0x1e0f0f11UL), + be32_to_cpu(0x7bb0b0cbUL), be32_to_cpu(0xa85454fcUL), be32_to_cpu(0x6dbbbbd6UL), be32_to_cpu(0x2c16163aUL), +}; + +static const uint8_t TE4[256] = +{ + 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, + 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76, + 0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, + 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0, + 0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc, + 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15, + 0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a, + 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75, + 0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0, + 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84, + 0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b, + 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf, + 0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85, + 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8, + 0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5, + 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2, + 0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17, + 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73, + 0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88, + 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb, + 0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c, + 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79, + 0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9, + 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08, + 0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6, + 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a, + 0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e, + 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e, + 0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94, + 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf, + 0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, + 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16 +}; + +static const uint8_t rcon[10] = +{ + 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36, + /* for 128-bit blocks, Rijndael never uses more than 10 rcon values */ +}; + +#if CPU_BYTE_ORDER == CPU_LITTLE_ENDIAN + +#define Te0(x) TE0[x&0xFF] +#define Te1(x) ROTL(TE0[(x>>8)&0xFF], 8) +#define Te2(x) ROTL(TE0[(x>>16)&0xFF], 16) +#define Te3(x) ROTL(TE0[x>>24], 24) + +#define Te4_0(x) ((uint32_t)TE4[x>>24] << 24) +#define Te4_1(x) ((uint32_t)TE4[(x>>16)&0xFF] << 16) +#define Te4_2(x) ((uint32_t)TE4[(x>>8)&0xFF] << 8) +#define Te4_3(x) ((uint32_t)TE4[x&0xFF]) + +#define RCON(x) ((uint32_t)rcon[x]) + +#define TeKeyMix(x) \ + (((uint32_t)TE4[(x>>8)&0xFF]) ^ \ + ((uint32_t)TE4[(x>>16)&0xFF] << 8) ^ \ + ((uint32_t)TE4[x>>24] << 16) ^ \ + ((uint32_t)TE4[x&0xFF]) << 24) + +#define TeKeyMix2(x) TeKeyMix(ROTL(x, 8)) + +#else + +#define Te0(x) TE0[x>>24] +#define Te1(x) ROTR(TE0[(x>>16)&0xFF], 8) +#define Te2(x) ROTR(TE0[(x>>8)&0xFF], 16) +#define Te3(x) ROTR(TE0[x&0xFF], 24) + +#define Te4_0(x) ((uint32_t)TE4[x&0xFF]) +#define Te4_1(x) ((uint32_t)TE4[(x>>8)&0xFF] << 8) +#define Te4_2(x) ((uint32_t)TE4[(x>>16)&0xFF] << 16) +#define Te4_3(x) ((uint32_t)TE4[x>>24] << 24) + +#define TeKeyMix(x) \ + ((TE4[(x>>16)&0xFF] << 24) ^ \ + (TE4[(x>>8)&0xFF] << 16) ^ \ + (TE4[x&0xFF] << 8) ^ \ + (TE4[x>>24])) + +#define TeKeyMix2(x) TeKeyMix(ROTR(x, 8)) + +#define RCON(x) (((uint32_t)rcon[x])<<24) + +#endif + + +/*****************************************************************************/ +// DECRYPTION TABLES +/*****************************************************************************/ + +static const uint32_t TD0[256] = +{ + be32_to_cpu(0x51f4a750UL), be32_to_cpu(0x7e416553UL), be32_to_cpu(0x1a17a4c3UL), be32_to_cpu(0x3a275e96UL), + be32_to_cpu(0x3bab6bcbUL), be32_to_cpu(0x1f9d45f1UL), be32_to_cpu(0xacfa58abUL), be32_to_cpu(0x4be30393UL), + be32_to_cpu(0x2030fa55UL), be32_to_cpu(0xad766df6UL), be32_to_cpu(0x88cc7691UL), be32_to_cpu(0xf5024c25UL), + be32_to_cpu(0x4fe5d7fcUL), be32_to_cpu(0xc52acbd7UL), be32_to_cpu(0x26354480UL), be32_to_cpu(0xb562a38fUL), + be32_to_cpu(0xdeb15a49UL), be32_to_cpu(0x25ba1b67UL), be32_to_cpu(0x45ea0e98UL), be32_to_cpu(0x5dfec0e1UL), + be32_to_cpu(0xc32f7502UL), be32_to_cpu(0x814cf012UL), be32_to_cpu(0x8d4697a3UL), be32_to_cpu(0x6bd3f9c6UL), + be32_to_cpu(0x038f5fe7UL), be32_to_cpu(0x15929c95UL), be32_to_cpu(0xbf6d7aebUL), be32_to_cpu(0x955259daUL), + be32_to_cpu(0xd4be832dUL), be32_to_cpu(0x587421d3UL), be32_to_cpu(0x49e06929UL), be32_to_cpu(0x8ec9c844UL), + be32_to_cpu(0x75c2896aUL), be32_to_cpu(0xf48e7978UL), be32_to_cpu(0x99583e6bUL), be32_to_cpu(0x27b971ddUL), + be32_to_cpu(0xbee14fb6UL), be32_to_cpu(0xf088ad17UL), be32_to_cpu(0xc920ac66UL), be32_to_cpu(0x7dce3ab4UL), + be32_to_cpu(0x63df4a18UL), be32_to_cpu(0xe51a3182UL), be32_to_cpu(0x97513360UL), be32_to_cpu(0x62537f45UL), + be32_to_cpu(0xb16477e0UL), be32_to_cpu(0xbb6bae84UL), be32_to_cpu(0xfe81a01cUL), be32_to_cpu(0xf9082b94UL), + be32_to_cpu(0x70486858UL), be32_to_cpu(0x8f45fd19UL), be32_to_cpu(0x94de6c87UL), be32_to_cpu(0x527bf8b7UL), + be32_to_cpu(0xab73d323UL), be32_to_cpu(0x724b02e2UL), be32_to_cpu(0xe31f8f57UL), be32_to_cpu(0x6655ab2aUL), + be32_to_cpu(0xb2eb2807UL), be32_to_cpu(0x2fb5c203UL), be32_to_cpu(0x86c57b9aUL), be32_to_cpu(0xd33708a5UL), + be32_to_cpu(0x302887f2UL), be32_to_cpu(0x23bfa5b2UL), be32_to_cpu(0x02036abaUL), be32_to_cpu(0xed16825cUL), + be32_to_cpu(0x8acf1c2bUL), be32_to_cpu(0xa779b492UL), be32_to_cpu(0xf307f2f0UL), be32_to_cpu(0x4e69e2a1UL), + be32_to_cpu(0x65daf4cdUL), be32_to_cpu(0x0605bed5UL), be32_to_cpu(0xd134621fUL), be32_to_cpu(0xc4a6fe8aUL), + be32_to_cpu(0x342e539dUL), be32_to_cpu(0xa2f355a0UL), be32_to_cpu(0x058ae132UL), be32_to_cpu(0xa4f6eb75UL), + be32_to_cpu(0x0b83ec39UL), be32_to_cpu(0x4060efaaUL), be32_to_cpu(0x5e719f06UL), be32_to_cpu(0xbd6e1051UL), + be32_to_cpu(0x3e218af9UL), be32_to_cpu(0x96dd063dUL), be32_to_cpu(0xdd3e05aeUL), be32_to_cpu(0x4de6bd46UL), + be32_to_cpu(0x91548db5UL), be32_to_cpu(0x71c45d05UL), be32_to_cpu(0x0406d46fUL), be32_to_cpu(0x605015ffUL), + be32_to_cpu(0x1998fb24UL), be32_to_cpu(0xd6bde997UL), be32_to_cpu(0x894043ccUL), be32_to_cpu(0x67d99e77UL), + be32_to_cpu(0xb0e842bdUL), be32_to_cpu(0x07898b88UL), be32_to_cpu(0xe7195b38UL), be32_to_cpu(0x79c8eedbUL), + be32_to_cpu(0xa17c0a47UL), be32_to_cpu(0x7c420fe9UL), be32_to_cpu(0xf8841ec9UL), be32_to_cpu(0x00000000UL), + be32_to_cpu(0x09808683UL), be32_to_cpu(0x322bed48UL), be32_to_cpu(0x1e1170acUL), be32_to_cpu(0x6c5a724eUL), + be32_to_cpu(0xfd0efffbUL), be32_to_cpu(0x0f853856UL), be32_to_cpu(0x3daed51eUL), be32_to_cpu(0x362d3927UL), + be32_to_cpu(0x0a0fd964UL), be32_to_cpu(0x685ca621UL), be32_to_cpu(0x9b5b54d1UL), be32_to_cpu(0x24362e3aUL), + be32_to_cpu(0x0c0a67b1UL), be32_to_cpu(0x9357e70fUL), be32_to_cpu(0xb4ee96d2UL), be32_to_cpu(0x1b9b919eUL), + be32_to_cpu(0x80c0c54fUL), be32_to_cpu(0x61dc20a2UL), be32_to_cpu(0x5a774b69UL), be32_to_cpu(0x1c121a16UL), + be32_to_cpu(0xe293ba0aUL), be32_to_cpu(0xc0a02ae5UL), be32_to_cpu(0x3c22e043UL), be32_to_cpu(0x121b171dUL), + be32_to_cpu(0x0e090d0bUL), be32_to_cpu(0xf28bc7adUL), be32_to_cpu(0x2db6a8b9UL), be32_to_cpu(0x141ea9c8UL), + be32_to_cpu(0x57f11985UL), be32_to_cpu(0xaf75074cUL), be32_to_cpu(0xee99ddbbUL), be32_to_cpu(0xa37f60fdUL), + be32_to_cpu(0xf701269fUL), be32_to_cpu(0x5c72f5bcUL), be32_to_cpu(0x44663bc5UL), be32_to_cpu(0x5bfb7e34UL), + be32_to_cpu(0x8b432976UL), be32_to_cpu(0xcb23c6dcUL), be32_to_cpu(0xb6edfc68UL), be32_to_cpu(0xb8e4f163UL), + be32_to_cpu(0xd731dccaUL), be32_to_cpu(0x42638510UL), be32_to_cpu(0x13972240UL), be32_to_cpu(0x84c61120UL), + be32_to_cpu(0x854a247dUL), be32_to_cpu(0xd2bb3df8UL), be32_to_cpu(0xaef93211UL), be32_to_cpu(0xc729a16dUL), + be32_to_cpu(0x1d9e2f4bUL), be32_to_cpu(0xdcb230f3UL), be32_to_cpu(0x0d8652ecUL), be32_to_cpu(0x77c1e3d0UL), + be32_to_cpu(0x2bb3166cUL), be32_to_cpu(0xa970b999UL), be32_to_cpu(0x119448faUL), be32_to_cpu(0x47e96422UL), + be32_to_cpu(0xa8fc8cc4UL), be32_to_cpu(0xa0f03f1aUL), be32_to_cpu(0x567d2cd8UL), be32_to_cpu(0x223390efUL), + be32_to_cpu(0x87494ec7UL), be32_to_cpu(0xd938d1c1UL), be32_to_cpu(0x8ccaa2feUL), be32_to_cpu(0x98d40b36UL), + be32_to_cpu(0xa6f581cfUL), be32_to_cpu(0xa57ade28UL), be32_to_cpu(0xdab78e26UL), be32_to_cpu(0x3fadbfa4UL), + be32_to_cpu(0x2c3a9de4UL), be32_to_cpu(0x5078920dUL), be32_to_cpu(0x6a5fcc9bUL), be32_to_cpu(0x547e4662UL), + be32_to_cpu(0xf68d13c2UL), be32_to_cpu(0x90d8b8e8UL), be32_to_cpu(0x2e39f75eUL), be32_to_cpu(0x82c3aff5UL), + be32_to_cpu(0x9f5d80beUL), be32_to_cpu(0x69d0937cUL), be32_to_cpu(0x6fd52da9UL), be32_to_cpu(0xcf2512b3UL), + be32_to_cpu(0xc8ac993bUL), be32_to_cpu(0x10187da7UL), be32_to_cpu(0xe89c636eUL), be32_to_cpu(0xdb3bbb7bUL), + be32_to_cpu(0xcd267809UL), be32_to_cpu(0x6e5918f4UL), be32_to_cpu(0xec9ab701UL), be32_to_cpu(0x834f9aa8UL), + be32_to_cpu(0xe6956e65UL), be32_to_cpu(0xaaffe67eUL), be32_to_cpu(0x21bccf08UL), be32_to_cpu(0xef15e8e6UL), + be32_to_cpu(0xbae79bd9UL), be32_to_cpu(0x4a6f36ceUL), be32_to_cpu(0xea9f09d4UL), be32_to_cpu(0x29b07cd6UL), + be32_to_cpu(0x31a4b2afUL), be32_to_cpu(0x2a3f2331UL), be32_to_cpu(0xc6a59430UL), be32_to_cpu(0x35a266c0UL), + be32_to_cpu(0x744ebc37UL), be32_to_cpu(0xfc82caa6UL), be32_to_cpu(0xe090d0b0UL), be32_to_cpu(0x33a7d815UL), + be32_to_cpu(0xf104984aUL), be32_to_cpu(0x41ecdaf7UL), be32_to_cpu(0x7fcd500eUL), be32_to_cpu(0x1791f62fUL), + be32_to_cpu(0x764dd68dUL), be32_to_cpu(0x43efb04dUL), be32_to_cpu(0xccaa4d54UL), be32_to_cpu(0xe49604dfUL), + be32_to_cpu(0x9ed1b5e3UL), be32_to_cpu(0x4c6a881bUL), be32_to_cpu(0xc12c1fb8UL), be32_to_cpu(0x4665517fUL), + be32_to_cpu(0x9d5eea04UL), be32_to_cpu(0x018c355dUL), be32_to_cpu(0xfa877473UL), be32_to_cpu(0xfb0b412eUL), + be32_to_cpu(0xb3671d5aUL), be32_to_cpu(0x92dbd252UL), be32_to_cpu(0xe9105633UL), be32_to_cpu(0x6dd64713UL), + be32_to_cpu(0x9ad7618cUL), be32_to_cpu(0x37a10c7aUL), be32_to_cpu(0x59f8148eUL), be32_to_cpu(0xeb133c89UL), + be32_to_cpu(0xcea927eeUL), be32_to_cpu(0xb761c935UL), be32_to_cpu(0xe11ce5edUL), be32_to_cpu(0x7a47b13cUL), + be32_to_cpu(0x9cd2df59UL), be32_to_cpu(0x55f2733fUL), be32_to_cpu(0x1814ce79UL), be32_to_cpu(0x73c737bfUL), + be32_to_cpu(0x53f7cdeaUL), be32_to_cpu(0x5ffdaa5bUL), be32_to_cpu(0xdf3d6f14UL), be32_to_cpu(0x7844db86UL), + be32_to_cpu(0xcaaff381UL), be32_to_cpu(0xb968c43eUL), be32_to_cpu(0x3824342cUL), be32_to_cpu(0xc2a3405fUL), + be32_to_cpu(0x161dc372UL), be32_to_cpu(0xbce2250cUL), be32_to_cpu(0x283c498bUL), be32_to_cpu(0xff0d9541UL), + be32_to_cpu(0x39a80171UL), be32_to_cpu(0x080cb3deUL), be32_to_cpu(0xd8b4e49cUL), be32_to_cpu(0x6456c190UL), + be32_to_cpu(0x7bcb8461UL), be32_to_cpu(0xd532b670UL), be32_to_cpu(0x486c5c74UL), be32_to_cpu(0xd0b85742UL), +}; + +static const uint8_t TD4[256] = +{ + 0x52, 0x09, 0x6a, 0xd5, + 0x30, 0x36, 0xa5, 0x38, + 0xbf, 0x40, 0xa3, 0x9e, + 0x81, 0xf3, 0xd7, 0xfb, + 0x7c, 0xe3, 0x39, 0x82, + 0x9b, 0x2f, 0xff, 0x87, + 0x34, 0x8e, 0x43, 0x44, + 0xc4, 0xde, 0xe9, 0xcb, + 0x54, 0x7b, 0x94, 0x32, + 0xa6, 0xc2, 0x23, 0x3d, + 0xee, 0x4c, 0x95, 0x0b, + 0x42, 0xfa, 0xc3, 0x4e, + 0x08, 0x2e, 0xa1, 0x66, + 0x28, 0xd9, 0x24, 0xb2, + 0x76, 0x5b, 0xa2, 0x49, + 0x6d, 0x8b, 0xd1, 0x25, + 0x72, 0xf8, 0xf6, 0x64, + 0x86, 0x68, 0x98, 0x16, + 0xd4, 0xa4, 0x5c, 0xcc, + 0x5d, 0x65, 0xb6, 0x92, + 0x6c, 0x70, 0x48, 0x50, + 0xfd, 0xed, 0xb9, 0xda, + 0x5e, 0x15, 0x46, 0x57, + 0xa7, 0x8d, 0x9d, 0x84, + 0x90, 0xd8, 0xab, 0x00, + 0x8c, 0xbc, 0xd3, 0x0a, + 0xf7, 0xe4, 0x58, 0x05, + 0xb8, 0xb3, 0x45, 0x06, + 0xd0, 0x2c, 0x1e, 0x8f, + 0xca, 0x3f, 0x0f, 0x02, + 0xc1, 0xaf, 0xbd, 0x03, + 0x01, 0x13, 0x8a, 0x6b, + 0x3a, 0x91, 0x11, 0x41, + 0x4f, 0x67, 0xdc, 0xea, + 0x97, 0xf2, 0xcf, 0xce, + 0xf0, 0xb4, 0xe6, 0x73, + 0x96, 0xac, 0x74, 0x22, + 0xe7, 0xad, 0x35, 0x85, + 0xe2, 0xf9, 0x37, 0xe8, + 0x1c, 0x75, 0xdf, 0x6e, + 0x47, 0xf1, 0x1a, 0x71, + 0x1d, 0x29, 0xc5, 0x89, + 0x6f, 0xb7, 0x62, 0x0e, + 0xaa, 0x18, 0xbe, 0x1b, + 0xfc, 0x56, 0x3e, 0x4b, + 0xc6, 0xd2, 0x79, 0x20, + 0x9a, 0xdb, 0xc0, 0xfe, + 0x78, 0xcd, 0x5a, 0xf4, + 0x1f, 0xdd, 0xa8, 0x33, + 0x88, 0x07, 0xc7, 0x31, + 0xb1, 0x12, 0x10, 0x59, + 0x27, 0x80, 0xec, 0x5f, + 0x60, 0x51, 0x7f, 0xa9, + 0x19, 0xb5, 0x4a, 0x0d, + 0x2d, 0xe5, 0x7a, 0x9f, + 0x93, 0xc9, 0x9c, 0xef, + 0xa0, 0xe0, 0x3b, 0x4d, + 0xae, 0x2a, 0xf5, 0xb0, + 0xc8, 0xeb, 0xbb, 0x3c, + 0x83, 0x53, 0x99, 0x61, + 0x17, 0x2b, 0x04, 0x7e, + 0xba, 0x77, 0xd6, 0x26, + 0xe1, 0x69, 0x14, 0x63, + 0x55, 0x21, 0x0c, 0x7d, +}; + + +#if CPU_BYTE_ORDER == CPU_LITTLE_ENDIAN + +#define XTd0(x) TD0[x] +#define XTd1(x) ROTL(TD0[x], 8) +#define XTd2(x) ROTL(TD0[x], 16) +#define XTd3(x) ROTL(TD0[x], 24) + +#define Td0(x) XTd0(x&0xff) +#define Td1(x) XTd1((x>>8)&0xff) +#define Td2(x) XTd2((x>>16)&0xff) +#define Td3(x) XTd3(x>>24) + +#define TdMix_0(x) TE4[x&0xFF] +#define TdMix_1(x) TE4[(x>>8)&0xFF] +#define TdMix_2(x) TE4[(x>>16)&0xFF] +#define TdMix_3(x) TE4[x>>24] + +#define Td4_0(x) ((uint32_t)TD4[x&0xFF]) +#define Td4_1(x) ((uint32_t)TD4[(x>>8)&0xFF] << 8) +#define Td4_2(x) ((uint32_t)TD4[(x>>16)&0xFF] << 16) +#define Td4_3(x) ((uint32_t)TD4[x>>24] << 24) + +#else + +#define XTd0(x) TD0[x] +#define XTd1(x) ROTR(TD0[x], 8) +#define XTd2(x) ROTR(TD0[x], 16) +#define XTd3(x) ROTR(TD0[x], 24) + +#define Td0(x) XTd0(x>>24) +#define Td1(x) XTd1((x>>16)&0xff) +#define Td2(x) XTd2((x>>8)&0xff) +#define Td3(x) XTd3(x&0xff) + +#define TdMix_0(x) TE4[x>>24] +#define TdMix_1(x) TE4[(x>>16)&0xFF] +#define TdMix_2(x) TE4[(x>>8)&0xFF] +#define TdMix_3(x) TE4[x&0xFF] + +#define Td4_0(x) ((uint32_t)TD4[x>>24] << 24) +#define Td4_1(x) ((uint32_t)TD4[(x>>16)&0xFF] << 16) +#define Td4_2(x) ((uint32_t)TD4[(x>>8)&0xFF] << 8) +#define Td4_3(x) ((uint32_t)TD4[x&0xFF]) + +#endif + + +/*****************************************************************************/ +// CODE +/*****************************************************************************/ + +static void lazy_expandKeyEnc128(uint32_t *k) +{ + int i = 0; + while (1) + { + k[4] = k[0] ^ TeKeyMix(k[3]) ^ RCON(i); + k[5] = k[1] ^ k[4]; + k[6] = k[2] ^ k[5]; + k[7] = k[3] ^ k[6]; + if (++i == 10) + break; + k += 4; + } +} + +static void lazy_expandKeyEnc192(uint32_t *k) +{ + int i = 0; + while (1) + { + k[ 6] = k[ 0] ^ TeKeyMix(k[5]) ^ RCON(i); + k[ 7] = k[ 1] ^ k[ 6]; + k[ 8] = k[ 2] ^ k[ 7]; + k[ 9] = k[ 3] ^ k[ 8]; + if (++i == 8) + break; + k[10] = k[ 4] ^ k[ 9]; + k[11] = k[ 5] ^ k[10]; + k += 6; + } +} + +static void lazy_expandKeyEnc256(uint32_t *k) +{ + int i = 0; + for (;;) + { + k[ 8] = k[ 0] ^ TeKeyMix(k[7]) ^ RCON(i); + k[ 9] = k[ 1] ^ k[ 8]; + k[10] = k[ 2] ^ k[ 9]; + k[11] = k[ 3] ^ k[10]; + if (++i == 7) + break; + k[12] = k[ 4] ^ TeKeyMix2(k[11]); + k[13] = k[ 5] ^ k[12]; + k[14] = k[ 6] ^ k[13]; + k[15] = k[ 7] ^ k[14]; + k += 8; + } +} + +static const void (*lazy_expandKeyEnc[3])(uint32_t *k) = +{ + lazy_expandKeyEnc128, lazy_expandKeyEnc192, lazy_expandKeyEnc256, +}; + +static void lazy_expandKeyDec(uint32_t *k, int len) +{ + k += len-5; + for (int i=0;ic.key_len); + + memcpy (c->expkey, key, c->c.key_len); + c->key_status = 0; +} + +static void AES_encrypt(BlockCipher *c_, void *block) +{ + AES_Context *c = (AES_Context *)c_; + uint32_t *k = c->expkey; + uint32_t t0, t1, t2, t3, s0, s1, s2, s3; + int Nr = c->num_rounds; + + if (c->key_status <= 0) + { + lazy_expandKeyEnc[(Nr-10U)/2](k); + c->key_status = 1; + } + + s0 = ((uint32_t*)block)[0]; + s1 = ((uint32_t*)block)[1]; + s2 = ((uint32_t*)block)[2]; + s3 = ((uint32_t*)block)[3]; + + s0 ^= k[0]; + s1 ^= k[1]; + s2 ^= k[2]; + s3 ^= k[3]; + + int r = 0; + while (1) + { + k += 4; + t0 = Te0(s0)^Te1(s1)^Te2(s2)^Te3(s3)^k[0]; + t1 = Te0(s1)^Te1(s2)^Te2(s3)^Te3(s0)^k[1]; + t2 = Te0(s2)^Te1(s3)^Te2(s0)^Te3(s1)^k[2]; + t3 = Te0(s3)^Te1(s0)^Te2(s1)^Te3(s2)^k[3]; + if (r == Nr-2) + break; + s0 = t0; s1 = t1; s2 = t2; s3 = t3; + ++r; + } + k += 4; + + s0 = Te4_3(t0)^Te4_2(t1)^Te4_1(t2)^Te4_0(t3)^k[0]; + s1 = Te4_3(t1)^Te4_2(t2)^Te4_1(t3)^Te4_0(t0)^k[1]; + s2 = Te4_3(t2)^Te4_2(t3)^Te4_1(t0)^Te4_0(t1)^k[2]; + s3 = Te4_3(t3)^Te4_2(t0)^Te4_1(t1)^Te4_0(t2)^k[3]; + + ((uint32_t*)block)[0] = s0; + ((uint32_t*)block)[1] = s1; + ((uint32_t*)block)[2] = s2; + ((uint32_t*)block)[3] = s3; +} + + +static void AES_decrypt(BlockCipher *c_, void *block) +{ + AES_Context *c = (AES_Context *)c_; + uint32_t *k = c->expkey; + uint32_t t0, t1, t2, t3, s0, s1, s2, s3; + uint8_t Nr = c->num_rounds; + int klen = (Nr+1)*4; + + if (c->key_status >= 0) + { + if (c->key_status == 0) + lazy_expandKeyEnc[(Nr-10U)/2](k); + lazy_expandKeyDec(k, klen); + c->key_status = -1; + } + + k += klen-4; + + s0 = ((uint32_t*)block)[0] ^ k[0]; + s1 = ((uint32_t*)block)[1] ^ k[1]; + s2 = ((uint32_t*)block)[2] ^ k[2]; + s3 = ((uint32_t*)block)[3] ^ k[3]; + + int r = 0; + while (1) + { + k -= 4; + + t0 = Td0(s0)^Td1(s3)^Td2(s2)^Td3(s1)^k[0]; + t1 = Td0(s1)^Td1(s0)^Td2(s3)^Td3(s2)^k[1]; + t2 = Td0(s2)^Td1(s1)^Td2(s0)^Td3(s3)^k[2]; + t3 = Td0(s3)^Td1(s2)^Td2(s1)^Td3(s0)^k[3]; + + if (r == Nr-2) + break; + s0 = t0; s1 = t1; s2 = t2; s3 = t3; + ++r; + } + + k -= 4; + s0 = Td4_0(t0)^Td4_1(t3)^Td4_2(t2)^Td4_3(t1)^k[0]; + s1 = Td4_0(t1)^Td4_1(t0)^Td4_2(t3)^Td4_3(t2)^k[1]; + s2 = Td4_0(t2)^Td4_1(t1)^Td4_2(t0)^Td4_3(t3)^k[2]; + s3 = Td4_0(t3)^Td4_1(t2)^Td4_2(t1)^Td4_3(t0)^k[3]; + + ((uint32_t*)block)[0] = s0; + ((uint32_t*)block)[1] = s1; + ((uint32_t*)block)[2] = s2; + ((uint32_t*)block)[3] = s3; +} diff --git a/bertos/sec/cipher/aes_f8.h b/bertos/sec/cipher/aes_f8.h new file mode 100644 index 00000000..40e9909a --- /dev/null +++ b/bertos/sec/cipher/aes_f8.h @@ -0,0 +1,433 @@ +/** + * \file + * + * + * \brief AES Advanced Encryption Standard implementation + * + * \author Giovanni Bajo + * + */ + +// advanced encryption standard +// author: karl malbrain, malbrain@yahoo.com +/* +This work, including the source code, documentation +and related data, is placed into the public domain. + +The orginal author is Karl Malbrain. + +THIS SOFTWARE IS PROVIDED AS-IS WITHOUT WARRANTY +OF ANY KIND, NOT EVEN THE IMPLIED WARRANTY OF +MERCHANTABILITY. THE AUTHOR OF THIS SOFTWARE, +ASSUMES _NO_ RESPONSIBILITY FOR ANY CONSEQUENCE +RESULTING FROM THE USE, MODIFICATION, OR +REDISTRIBUTION OF THIS SOFTWARE. +*/ + +static uint8_t Sbox[256] = { // forward s-box +0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76, +0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0, +0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc, 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15, +0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a, 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75, +0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0, 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84, +0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b, 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf, +0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85, 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8, +0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5, 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2, +0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17, 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73, +0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88, 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb, +0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c, 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79, +0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9, 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08, +0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6, 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a, +0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e, 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e, +0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94, 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf, +0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16}; + +static uint8_t InvSbox[256] = { // inverse s-box +0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb, +0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb, +0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e, +0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25, +0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92, +0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84, +0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06, +0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b, +0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73, +0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e, +0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b, +0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4, +0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f, +0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef, +0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61, +0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d}; + +// combined Xtimes2[Sbox[]] +static uint8_t Xtime2Sbox[256] = { +0xc6, 0xf8, 0xee, 0xf6, 0xff, 0xd6, 0xde, 0x91, 0x60, 0x02, 0xce, 0x56, 0xe7, 0xb5, 0x4d, 0xec, +0x8f, 0x1f, 0x89, 0xfa, 0xef, 0xb2, 0x8e, 0xfb, 0x41, 0xb3, 0x5f, 0x45, 0x23, 0x53, 0xe4, 0x9b, +0x75, 0xe1, 0x3d, 0x4c, 0x6c, 0x7e, 0xf5, 0x83, 0x68, 0x51, 0xd1, 0xf9, 0xe2, 0xab, 0x62, 0x2a, +0x08, 0x95, 0x46, 0x9d, 0x30, 0x37, 0x0a, 0x2f, 0x0e, 0x24, 0x1b, 0xdf, 0xcd, 0x4e, 0x7f, 0xea, +0x12, 0x1d, 0x58, 0x34, 0x36, 0xdc, 0xb4, 0x5b, 0xa4, 0x76, 0xb7, 0x7d, 0x52, 0xdd, 0x5e, 0x13, +0xa6, 0xb9, 0x00, 0xc1, 0x40, 0xe3, 0x79, 0xb6, 0xd4, 0x8d, 0x67, 0x72, 0x94, 0x98, 0xb0, 0x85, +0xbb, 0xc5, 0x4f, 0xed, 0x86, 0x9a, 0x66, 0x11, 0x8a, 0xe9, 0x04, 0xfe, 0xa0, 0x78, 0x25, 0x4b, +0xa2, 0x5d, 0x80, 0x05, 0x3f, 0x21, 0x70, 0xf1, 0x63, 0x77, 0xaf, 0x42, 0x20, 0xe5, 0xfd, 0xbf, +0x81, 0x18, 0x26, 0xc3, 0xbe, 0x35, 0x88, 0x2e, 0x93, 0x55, 0xfc, 0x7a, 0xc8, 0xba, 0x32, 0xe6, +0xc0, 0x19, 0x9e, 0xa3, 0x44, 0x54, 0x3b, 0x0b, 0x8c, 0xc7, 0x6b, 0x28, 0xa7, 0xbc, 0x16, 0xad, +0xdb, 0x64, 0x74, 0x14, 0x92, 0x0c, 0x48, 0xb8, 0x9f, 0xbd, 0x43, 0xc4, 0x39, 0x31, 0xd3, 0xf2, +0xd5, 0x8b, 0x6e, 0xda, 0x01, 0xb1, 0x9c, 0x49, 0xd8, 0xac, 0xf3, 0xcf, 0xca, 0xf4, 0x47, 0x10, +0x6f, 0xf0, 0x4a, 0x5c, 0x38, 0x57, 0x73, 0x97, 0xcb, 0xa1, 0xe8, 0x3e, 0x96, 0x61, 0x0d, 0x0f, +0xe0, 0x7c, 0x71, 0xcc, 0x90, 0x06, 0xf7, 0x1c, 0xc2, 0x6a, 0xae, 0x69, 0x17, 0x99, 0x3a, 0x27, +0xd9, 0xeb, 0x2b, 0x22, 0xd2, 0xa9, 0x07, 0x33, 0x2d, 0x3c, 0x15, 0xc9, 0x87, 0xaa, 0x50, 0xa5, +0x03, 0x59, 0x09, 0x1a, 0x65, 0xd7, 0x84, 0xd0, 0x82, 0x29, 0x5a, 0x1e, 0x7b, 0xa8, 0x6d, 0x2c +}; + +// combined Xtimes3[Sbox[]] +static uint8_t Xtime3Sbox[256] = { +0xa5, 0x84, 0x99, 0x8d, 0x0d, 0xbd, 0xb1, 0x54, 0x50, 0x03, 0xa9, 0x7d, 0x19, 0x62, 0xe6, 0x9a, +0x45, 0x9d, 0x40, 0x87, 0x15, 0xeb, 0xc9, 0x0b, 0xec, 0x67, 0xfd, 0xea, 0xbf, 0xf7, 0x96, 0x5b, +0xc2, 0x1c, 0xae, 0x6a, 0x5a, 0x41, 0x02, 0x4f, 0x5c, 0xf4, 0x34, 0x08, 0x93, 0x73, 0x53, 0x3f, +0x0c, 0x52, 0x65, 0x5e, 0x28, 0xa1, 0x0f, 0xb5, 0x09, 0x36, 0x9b, 0x3d, 0x26, 0x69, 0xcd, 0x9f, +0x1b, 0x9e, 0x74, 0x2e, 0x2d, 0xb2, 0xee, 0xfb, 0xf6, 0x4d, 0x61, 0xce, 0x7b, 0x3e, 0x71, 0x97, +0xf5, 0x68, 0x00, 0x2c, 0x60, 0x1f, 0xc8, 0xed, 0xbe, 0x46, 0xd9, 0x4b, 0xde, 0xd4, 0xe8, 0x4a, +0x6b, 0x2a, 0xe5, 0x16, 0xc5, 0xd7, 0x55, 0x94, 0xcf, 0x10, 0x06, 0x81, 0xf0, 0x44, 0xba, 0xe3, +0xf3, 0xfe, 0xc0, 0x8a, 0xad, 0xbc, 0x48, 0x04, 0xdf, 0xc1, 0x75, 0x63, 0x30, 0x1a, 0x0e, 0x6d, +0x4c, 0x14, 0x35, 0x2f, 0xe1, 0xa2, 0xcc, 0x39, 0x57, 0xf2, 0x82, 0x47, 0xac, 0xe7, 0x2b, 0x95, +0xa0, 0x98, 0xd1, 0x7f, 0x66, 0x7e, 0xab, 0x83, 0xca, 0x29, 0xd3, 0x3c, 0x79, 0xe2, 0x1d, 0x76, +0x3b, 0x56, 0x4e, 0x1e, 0xdb, 0x0a, 0x6c, 0xe4, 0x5d, 0x6e, 0xef, 0xa6, 0xa8, 0xa4, 0x37, 0x8b, +0x32, 0x43, 0x59, 0xb7, 0x8c, 0x64, 0xd2, 0xe0, 0xb4, 0xfa, 0x07, 0x25, 0xaf, 0x8e, 0xe9, 0x18, +0xd5, 0x88, 0x6f, 0x72, 0x24, 0xf1, 0xc7, 0x51, 0x23, 0x7c, 0x9c, 0x21, 0xdd, 0xdc, 0x86, 0x85, +0x90, 0x42, 0xc4, 0xaa, 0xd8, 0x05, 0x01, 0x12, 0xa3, 0x5f, 0xf9, 0xd0, 0x91, 0x58, 0x27, 0xb9, +0x38, 0x13, 0xb3, 0x33, 0xbb, 0x70, 0x89, 0xa7, 0xb6, 0x22, 0x92, 0x20, 0x49, 0xff, 0x78, 0x7a, +0x8f, 0xf8, 0x80, 0x17, 0xda, 0x31, 0xc6, 0xb8, 0xc3, 0xb0, 0x77, 0x11, 0xcb, 0xfc, 0xd6, 0x3a +}; + +// modular multiplication tables +// based on: + +// Xtime2[x] = (x & 0x80 ? 0x1b : 0) ^ (x + x) +// Xtime3[x] = x^Xtime2[x]; +#if 0 +static uint8_t Xtime2[256] = { +0x00, 0x02, 0x04, 0x06, 0x08, 0x0a, 0x0c, 0x0e, 0x10, 0x12, 0x14, 0x16, 0x18, 0x1a, 0x1c, 0x1e, +0x20, 0x22, 0x24, 0x26, 0x28, 0x2a, 0x2c, 0x2e, 0x30, 0x32, 0x34, 0x36, 0x38, 0x3a, 0x3c, 0x3e, +0x40, 0x42, 0x44, 0x46, 0x48, 0x4a, 0x4c, 0x4e, 0x50, 0x52, 0x54, 0x56, 0x58, 0x5a, 0x5c, 0x5e, +0x60, 0x62, 0x64, 0x66, 0x68, 0x6a, 0x6c, 0x6e, 0x70, 0x72, 0x74, 0x76, 0x78, 0x7a, 0x7c, 0x7e, +0x80, 0x82, 0x84, 0x86, 0x88, 0x8a, 0x8c, 0x8e, 0x90, 0x92, 0x94, 0x96, 0x98, 0x9a, 0x9c, 0x9e, +0xa0, 0xa2, 0xa4, 0xa6, 0xa8, 0xaa, 0xac, 0xae, 0xb0, 0xb2, 0xb4, 0xb6, 0xb8, 0xba, 0xbc, 0xbe, +0xc0, 0xc2, 0xc4, 0xc6, 0xc8, 0xca, 0xcc, 0xce, 0xd0, 0xd2, 0xd4, 0xd6, 0xd8, 0xda, 0xdc, 0xde, +0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee, 0xf0, 0xf2, 0xf4, 0xf6, 0xf8, 0xfa, 0xfc, 0xfe, +0x1b, 0x19, 0x1f, 0x1d, 0x13, 0x11, 0x17, 0x15, 0x0b, 0x09, 0x0f, 0x0d, 0x03, 0x01, 0x07, 0x05, +0x3b, 0x39, 0x3f, 0x3d, 0x33, 0x31, 0x37, 0x35, 0x2b, 0x29, 0x2f, 0x2d, 0x23, 0x21, 0x27, 0x25, +0x5b, 0x59, 0x5f, 0x5d, 0x53, 0x51, 0x57, 0x55, 0x4b, 0x49, 0x4f, 0x4d, 0x43, 0x41, 0x47, 0x45, +0x7b, 0x79, 0x7f, 0x7d, 0x73, 0x71, 0x77, 0x75, 0x6b, 0x69, 0x6f, 0x6d, 0x63, 0x61, 0x67, 0x65, +0x9b, 0x99, 0x9f, 0x9d, 0x93, 0x91, 0x97, 0x95, 0x8b, 0x89, 0x8f, 0x8d, 0x83, 0x81, 0x87, 0x85, +0xbb, 0xb9, 0xbf, 0xbd, 0xb3, 0xb1, 0xb7, 0xb5, 0xab, 0xa9, 0xaf, 0xad, 0xa3, 0xa1, 0xa7, 0xa5, +0xdb, 0xd9, 0xdf, 0xdd, 0xd3, 0xd1, 0xd7, 0xd5, 0xcb, 0xc9, 0xcf, 0xcd, 0xc3, 0xc1, 0xc7, 0xc5, +0xfb, 0xf9, 0xff, 0xfd, 0xf3, 0xf1, 0xf7, 0xf5, 0xeb, 0xe9, 0xef, 0xed, 0xe3, 0xe1, 0xe7, 0xe5}; +#endif + +static uint8_t Xtime9[256] = { +0x00, 0x09, 0x12, 0x1b, 0x24, 0x2d, 0x36, 0x3f, 0x48, 0x41, 0x5a, 0x53, 0x6c, 0x65, 0x7e, 0x77, +0x90, 0x99, 0x82, 0x8b, 0xb4, 0xbd, 0xa6, 0xaf, 0xd8, 0xd1, 0xca, 0xc3, 0xfc, 0xf5, 0xee, 0xe7, +0x3b, 0x32, 0x29, 0x20, 0x1f, 0x16, 0x0d, 0x04, 0x73, 0x7a, 0x61, 0x68, 0x57, 0x5e, 0x45, 0x4c, +0xab, 0xa2, 0xb9, 0xb0, 0x8f, 0x86, 0x9d, 0x94, 0xe3, 0xea, 0xf1, 0xf8, 0xc7, 0xce, 0xd5, 0xdc, +0x76, 0x7f, 0x64, 0x6d, 0x52, 0x5b, 0x40, 0x49, 0x3e, 0x37, 0x2c, 0x25, 0x1a, 0x13, 0x08, 0x01, +0xe6, 0xef, 0xf4, 0xfd, 0xc2, 0xcb, 0xd0, 0xd9, 0xae, 0xa7, 0xbc, 0xb5, 0x8a, 0x83, 0x98, 0x91, +0x4d, 0x44, 0x5f, 0x56, 0x69, 0x60, 0x7b, 0x72, 0x05, 0x0c, 0x17, 0x1e, 0x21, 0x28, 0x33, 0x3a, +0xdd, 0xd4, 0xcf, 0xc6, 0xf9, 0xf0, 0xeb, 0xe2, 0x95, 0x9c, 0x87, 0x8e, 0xb1, 0xb8, 0xa3, 0xaa, +0xec, 0xe5, 0xfe, 0xf7, 0xc8, 0xc1, 0xda, 0xd3, 0xa4, 0xad, 0xb6, 0xbf, 0x80, 0x89, 0x92, 0x9b, +0x7c, 0x75, 0x6e, 0x67, 0x58, 0x51, 0x4a, 0x43, 0x34, 0x3d, 0x26, 0x2f, 0x10, 0x19, 0x02, 0x0b, +0xd7, 0xde, 0xc5, 0xcc, 0xf3, 0xfa, 0xe1, 0xe8, 0x9f, 0x96, 0x8d, 0x84, 0xbb, 0xb2, 0xa9, 0xa0, +0x47, 0x4e, 0x55, 0x5c, 0x63, 0x6a, 0x71, 0x78, 0x0f, 0x06, 0x1d, 0x14, 0x2b, 0x22, 0x39, 0x30, +0x9a, 0x93, 0x88, 0x81, 0xbe, 0xb7, 0xac, 0xa5, 0xd2, 0xdb, 0xc0, 0xc9, 0xf6, 0xff, 0xe4, 0xed, +0x0a, 0x03, 0x18, 0x11, 0x2e, 0x27, 0x3c, 0x35, 0x42, 0x4b, 0x50, 0x59, 0x66, 0x6f, 0x74, 0x7d, +0xa1, 0xa8, 0xb3, 0xba, 0x85, 0x8c, 0x97, 0x9e, 0xe9, 0xe0, 0xfb, 0xf2, 0xcd, 0xc4, 0xdf, 0xd6, +0x31, 0x38, 0x23, 0x2a, 0x15, 0x1c, 0x07, 0x0e, 0x79, 0x70, 0x6b, 0x62, 0x5d, 0x54, 0x4f, 0x46}; + +static uint8_t XtimeB[256] = { +0x00, 0x0b, 0x16, 0x1d, 0x2c, 0x27, 0x3a, 0x31, 0x58, 0x53, 0x4e, 0x45, 0x74, 0x7f, 0x62, 0x69, +0xb0, 0xbb, 0xa6, 0xad, 0x9c, 0x97, 0x8a, 0x81, 0xe8, 0xe3, 0xfe, 0xf5, 0xc4, 0xcf, 0xd2, 0xd9, +0x7b, 0x70, 0x6d, 0x66, 0x57, 0x5c, 0x41, 0x4a, 0x23, 0x28, 0x35, 0x3e, 0x0f, 0x04, 0x19, 0x12, +0xcb, 0xc0, 0xdd, 0xd6, 0xe7, 0xec, 0xf1, 0xfa, 0x93, 0x98, 0x85, 0x8e, 0xbf, 0xb4, 0xa9, 0xa2, +0xf6, 0xfd, 0xe0, 0xeb, 0xda, 0xd1, 0xcc, 0xc7, 0xae, 0xa5, 0xb8, 0xb3, 0x82, 0x89, 0x94, 0x9f, +0x46, 0x4d, 0x50, 0x5b, 0x6a, 0x61, 0x7c, 0x77, 0x1e, 0x15, 0x08, 0x03, 0x32, 0x39, 0x24, 0x2f, +0x8d, 0x86, 0x9b, 0x90, 0xa1, 0xaa, 0xb7, 0xbc, 0xd5, 0xde, 0xc3, 0xc8, 0xf9, 0xf2, 0xef, 0xe4, +0x3d, 0x36, 0x2b, 0x20, 0x11, 0x1a, 0x07, 0x0c, 0x65, 0x6e, 0x73, 0x78, 0x49, 0x42, 0x5f, 0x54, +0xf7, 0xfc, 0xe1, 0xea, 0xdb, 0xd0, 0xcd, 0xc6, 0xaf, 0xa4, 0xb9, 0xb2, 0x83, 0x88, 0x95, 0x9e, +0x47, 0x4c, 0x51, 0x5a, 0x6b, 0x60, 0x7d, 0x76, 0x1f, 0x14, 0x09, 0x02, 0x33, 0x38, 0x25, 0x2e, +0x8c, 0x87, 0x9a, 0x91, 0xa0, 0xab, 0xb6, 0xbd, 0xd4, 0xdf, 0xc2, 0xc9, 0xf8, 0xf3, 0xee, 0xe5, +0x3c, 0x37, 0x2a, 0x21, 0x10, 0x1b, 0x06, 0x0d, 0x64, 0x6f, 0x72, 0x79, 0x48, 0x43, 0x5e, 0x55, +0x01, 0x0a, 0x17, 0x1c, 0x2d, 0x26, 0x3b, 0x30, 0x59, 0x52, 0x4f, 0x44, 0x75, 0x7e, 0x63, 0x68, +0xb1, 0xba, 0xa7, 0xac, 0x9d, 0x96, 0x8b, 0x80, 0xe9, 0xe2, 0xff, 0xf4, 0xc5, 0xce, 0xd3, 0xd8, +0x7a, 0x71, 0x6c, 0x67, 0x56, 0x5d, 0x40, 0x4b, 0x22, 0x29, 0x34, 0x3f, 0x0e, 0x05, 0x18, 0x13, +0xca, 0xc1, 0xdc, 0xd7, 0xe6, 0xed, 0xf0, 0xfb, 0x92, 0x99, 0x84, 0x8f, 0xbe, 0xb5, 0xa8, 0xa3}; + +static uint8_t XtimeD[256] = { +0x00, 0x0d, 0x1a, 0x17, 0x34, 0x39, 0x2e, 0x23, 0x68, 0x65, 0x72, 0x7f, 0x5c, 0x51, 0x46, 0x4b, +0xd0, 0xdd, 0xca, 0xc7, 0xe4, 0xe9, 0xfe, 0xf3, 0xb8, 0xb5, 0xa2, 0xaf, 0x8c, 0x81, 0x96, 0x9b, +0xbb, 0xb6, 0xa1, 0xac, 0x8f, 0x82, 0x95, 0x98, 0xd3, 0xde, 0xc9, 0xc4, 0xe7, 0xea, 0xfd, 0xf0, +0x6b, 0x66, 0x71, 0x7c, 0x5f, 0x52, 0x45, 0x48, 0x03, 0x0e, 0x19, 0x14, 0x37, 0x3a, 0x2d, 0x20, +0x6d, 0x60, 0x77, 0x7a, 0x59, 0x54, 0x43, 0x4e, 0x05, 0x08, 0x1f, 0x12, 0x31, 0x3c, 0x2b, 0x26, +0xbd, 0xb0, 0xa7, 0xaa, 0x89, 0x84, 0x93, 0x9e, 0xd5, 0xd8, 0xcf, 0xc2, 0xe1, 0xec, 0xfb, 0xf6, +0xd6, 0xdb, 0xcc, 0xc1, 0xe2, 0xef, 0xf8, 0xf5, 0xbe, 0xb3, 0xa4, 0xa9, 0x8a, 0x87, 0x90, 0x9d, +0x06, 0x0b, 0x1c, 0x11, 0x32, 0x3f, 0x28, 0x25, 0x6e, 0x63, 0x74, 0x79, 0x5a, 0x57, 0x40, 0x4d, +0xda, 0xd7, 0xc0, 0xcd, 0xee, 0xe3, 0xf4, 0xf9, 0xb2, 0xbf, 0xa8, 0xa5, 0x86, 0x8b, 0x9c, 0x91, +0x0a, 0x07, 0x10, 0x1d, 0x3e, 0x33, 0x24, 0x29, 0x62, 0x6f, 0x78, 0x75, 0x56, 0x5b, 0x4c, 0x41, +0x61, 0x6c, 0x7b, 0x76, 0x55, 0x58, 0x4f, 0x42, 0x09, 0x04, 0x13, 0x1e, 0x3d, 0x30, 0x27, 0x2a, +0xb1, 0xbc, 0xab, 0xa6, 0x85, 0x88, 0x9f, 0x92, 0xd9, 0xd4, 0xc3, 0xce, 0xed, 0xe0, 0xf7, 0xfa, +0xb7, 0xba, 0xad, 0xa0, 0x83, 0x8e, 0x99, 0x94, 0xdf, 0xd2, 0xc5, 0xc8, 0xeb, 0xe6, 0xf1, 0xfc, +0x67, 0x6a, 0x7d, 0x70, 0x53, 0x5e, 0x49, 0x44, 0x0f, 0x02, 0x15, 0x18, 0x3b, 0x36, 0x21, 0x2c, +0x0c, 0x01, 0x16, 0x1b, 0x38, 0x35, 0x22, 0x2f, 0x64, 0x69, 0x7e, 0x73, 0x50, 0x5d, 0x4a, 0x47, +0xdc, 0xd1, 0xc6, 0xcb, 0xe8, 0xe5, 0xf2, 0xff, 0xb4, 0xb9, 0xae, 0xa3, 0x80, 0x8d, 0x9a, 0x97}; + +static uint8_t XtimeE[256] = { +0x00, 0x0e, 0x1c, 0x12, 0x38, 0x36, 0x24, 0x2a, 0x70, 0x7e, 0x6c, 0x62, 0x48, 0x46, 0x54, 0x5a, +0xe0, 0xee, 0xfc, 0xf2, 0xd8, 0xd6, 0xc4, 0xca, 0x90, 0x9e, 0x8c, 0x82, 0xa8, 0xa6, 0xb4, 0xba, +0xdb, 0xd5, 0xc7, 0xc9, 0xe3, 0xed, 0xff, 0xf1, 0xab, 0xa5, 0xb7, 0xb9, 0x93, 0x9d, 0x8f, 0x81, +0x3b, 0x35, 0x27, 0x29, 0x03, 0x0d, 0x1f, 0x11, 0x4b, 0x45, 0x57, 0x59, 0x73, 0x7d, 0x6f, 0x61, +0xad, 0xa3, 0xb1, 0xbf, 0x95, 0x9b, 0x89, 0x87, 0xdd, 0xd3, 0xc1, 0xcf, 0xe5, 0xeb, 0xf9, 0xf7, +0x4d, 0x43, 0x51, 0x5f, 0x75, 0x7b, 0x69, 0x67, 0x3d, 0x33, 0x21, 0x2f, 0x05, 0x0b, 0x19, 0x17, +0x76, 0x78, 0x6a, 0x64, 0x4e, 0x40, 0x52, 0x5c, 0x06, 0x08, 0x1a, 0x14, 0x3e, 0x30, 0x22, 0x2c, +0x96, 0x98, 0x8a, 0x84, 0xae, 0xa0, 0xb2, 0xbc, 0xe6, 0xe8, 0xfa, 0xf4, 0xde, 0xd0, 0xc2, 0xcc, +0x41, 0x4f, 0x5d, 0x53, 0x79, 0x77, 0x65, 0x6b, 0x31, 0x3f, 0x2d, 0x23, 0x09, 0x07, 0x15, 0x1b, +0xa1, 0xaf, 0xbd, 0xb3, 0x99, 0x97, 0x85, 0x8b, 0xd1, 0xdf, 0xcd, 0xc3, 0xe9, 0xe7, 0xf5, 0xfb, +0x9a, 0x94, 0x86, 0x88, 0xa2, 0xac, 0xbe, 0xb0, 0xea, 0xe4, 0xf6, 0xf8, 0xd2, 0xdc, 0xce, 0xc0, +0x7a, 0x74, 0x66, 0x68, 0x42, 0x4c, 0x5e, 0x50, 0x0a, 0x04, 0x16, 0x18, 0x32, 0x3c, 0x2e, 0x20, +0xec, 0xe2, 0xf0, 0xfe, 0xd4, 0xda, 0xc8, 0xc6, 0x9c, 0x92, 0x80, 0x8e, 0xa4, 0xaa, 0xb8, 0xb6, +0x0c, 0x02, 0x10, 0x1e, 0x34, 0x3a, 0x28, 0x26, 0x7c, 0x72, 0x60, 0x6e, 0x44, 0x4a, 0x58, 0x56, +0x37, 0x39, 0x2b, 0x25, 0x0f, 0x01, 0x13, 0x1d, 0x47, 0x49, 0x5b, 0x55, 0x7f, 0x71, 0x63, 0x6d, +0xd7, 0xd9, 0xcb, 0xc5, 0xef, 0xe1, 0xf3, 0xfd, 0xa7, 0xa9, 0xbb, 0xb5, 0x9f, 0x91, 0x83, 0x8d}; + +// exchanges columns in each of 4 rows +// row0 - unchanged, row1- shifted left 1, +// row2 - shifted left 2 and row3 - shifted left 3 +static void ShiftRows (uint8_t *state) +{ + uint8_t tmp; + + // just substitute row 0 + state[0] = Sbox[state[0]], state[4] = Sbox[state[4]]; + state[8] = Sbox[state[8]], state[12] = Sbox[state[12]]; + + // rotate row 1 + tmp = Sbox[state[1]], state[1] = Sbox[state[5]]; + state[5] = Sbox[state[9]], state[9] = Sbox[state[13]], state[13] = tmp; + + // rotate row 2 + tmp = Sbox[state[2]], state[2] = Sbox[state[10]], state[10] = tmp; + tmp = Sbox[state[6]], state[6] = Sbox[state[14]], state[14] = tmp; + + // rotate row 3 + tmp = Sbox[state[15]], state[15] = Sbox[state[11]]; + state[11] = Sbox[state[7]], state[7] = Sbox[state[3]], state[3] = tmp; +} + +// restores columns in each of 4 rows +// row0 - unchanged, row1- shifted right 1, +// row2 - shifted right 2 and row3 - shifted right 3 +static void InvShiftRows (uint8_t *state) +{ + uint8_t tmp; + + // restore row 0 + state[0] = InvSbox[state[0]], state[4] = InvSbox[state[4]]; + state[8] = InvSbox[state[8]], state[12] = InvSbox[state[12]]; + + // restore row 1 + tmp = InvSbox[state[13]], state[13] = InvSbox[state[9]]; + state[9] = InvSbox[state[5]], state[5] = InvSbox[state[1]], state[1] = tmp; + + // restore row 2 + tmp = InvSbox[state[2]], state[2] = InvSbox[state[10]], state[10] = tmp; + tmp = InvSbox[state[6]], state[6] = InvSbox[state[14]], state[14] = tmp; + + // restore row 3 + tmp = InvSbox[state[3]], state[3] = InvSbox[state[7]]; + state[7] = InvSbox[state[11]], state[11] = InvSbox[state[15]], state[15] = tmp; +} + +// recombine and mix each row in a column +static void MixSubColumns (uint8_t *state) +{ + uint8_t tmp[4 * Nb]; + + // mixing column 0 + tmp[0] = Xtime2Sbox[state[0]] ^ Xtime3Sbox[state[5]] ^ Sbox[state[10]] ^ Sbox[state[15]]; + tmp[1] = Sbox[state[0]] ^ Xtime2Sbox[state[5]] ^ Xtime3Sbox[state[10]] ^ Sbox[state[15]]; + tmp[2] = Sbox[state[0]] ^ Sbox[state[5]] ^ Xtime2Sbox[state[10]] ^ Xtime3Sbox[state[15]]; + tmp[3] = Xtime3Sbox[state[0]] ^ Sbox[state[5]] ^ Sbox[state[10]] ^ Xtime2Sbox[state[15]]; + + // mixing column 1 + tmp[4] = Xtime2Sbox[state[4]] ^ Xtime3Sbox[state[9]] ^ Sbox[state[14]] ^ Sbox[state[3]]; + tmp[5] = Sbox[state[4]] ^ Xtime2Sbox[state[9]] ^ Xtime3Sbox[state[14]] ^ Sbox[state[3]]; + tmp[6] = Sbox[state[4]] ^ Sbox[state[9]] ^ Xtime2Sbox[state[14]] ^ Xtime3Sbox[state[3]]; + tmp[7] = Xtime3Sbox[state[4]] ^ Sbox[state[9]] ^ Sbox[state[14]] ^ Xtime2Sbox[state[3]]; + + // mixing column 2 + tmp[8] = Xtime2Sbox[state[8]] ^ Xtime3Sbox[state[13]] ^ Sbox[state[2]] ^ Sbox[state[7]]; + tmp[9] = Sbox[state[8]] ^ Xtime2Sbox[state[13]] ^ Xtime3Sbox[state[2]] ^ Sbox[state[7]]; + tmp[10] = Sbox[state[8]] ^ Sbox[state[13]] ^ Xtime2Sbox[state[2]] ^ Xtime3Sbox[state[7]]; + tmp[11] = Xtime3Sbox[state[8]] ^ Sbox[state[13]] ^ Sbox[state[2]] ^ Xtime2Sbox[state[7]]; + + // mixing column 3 + tmp[12] = Xtime2Sbox[state[12]] ^ Xtime3Sbox[state[1]] ^ Sbox[state[6]] ^ Sbox[state[11]]; + tmp[13] = Sbox[state[12]] ^ Xtime2Sbox[state[1]] ^ Xtime3Sbox[state[6]] ^ Sbox[state[11]]; + tmp[14] = Sbox[state[12]] ^ Sbox[state[1]] ^ Xtime2Sbox[state[6]] ^ Xtime3Sbox[state[11]]; + tmp[15] = Xtime3Sbox[state[12]] ^ Sbox[state[1]] ^ Sbox[state[6]] ^ Xtime2Sbox[state[11]]; + + memcpy (state, tmp, sizeof(tmp)); +} + +// restore and un-mix each row in a column +static void InvMixSubColumns (uint8_t *state) +{ + uint8_t tmp[4 * Nb]; + int i; + + // restore column 0 + tmp[0] = XtimeE[state[0]] ^ XtimeB[state[1]] ^ XtimeD[state[2]] ^ Xtime9[state[3]]; + tmp[5] = Xtime9[state[0]] ^ XtimeE[state[1]] ^ XtimeB[state[2]] ^ XtimeD[state[3]]; + tmp[10] = XtimeD[state[0]] ^ Xtime9[state[1]] ^ XtimeE[state[2]] ^ XtimeB[state[3]]; + tmp[15] = XtimeB[state[0]] ^ XtimeD[state[1]] ^ Xtime9[state[2]] ^ XtimeE[state[3]]; + + // restore column 1 + tmp[4] = XtimeE[state[4]] ^ XtimeB[state[5]] ^ XtimeD[state[6]] ^ Xtime9[state[7]]; + tmp[9] = Xtime9[state[4]] ^ XtimeE[state[5]] ^ XtimeB[state[6]] ^ XtimeD[state[7]]; + tmp[14] = XtimeD[state[4]] ^ Xtime9[state[5]] ^ XtimeE[state[6]] ^ XtimeB[state[7]]; + tmp[3] = XtimeB[state[4]] ^ XtimeD[state[5]] ^ Xtime9[state[6]] ^ XtimeE[state[7]]; + + // restore column 2 + tmp[8] = XtimeE[state[8]] ^ XtimeB[state[9]] ^ XtimeD[state[10]] ^ Xtime9[state[11]]; + tmp[13] = Xtime9[state[8]] ^ XtimeE[state[9]] ^ XtimeB[state[10]] ^ XtimeD[state[11]]; + tmp[2] = XtimeD[state[8]] ^ Xtime9[state[9]] ^ XtimeE[state[10]] ^ XtimeB[state[11]]; + tmp[7] = XtimeB[state[8]] ^ XtimeD[state[9]] ^ Xtime9[state[10]] ^ XtimeE[state[11]]; + + // restore column 3 + tmp[12] = XtimeE[state[12]] ^ XtimeB[state[13]] ^ XtimeD[state[14]] ^ Xtime9[state[15]]; + tmp[1] = Xtime9[state[12]] ^ XtimeE[state[13]] ^ XtimeB[state[14]] ^ XtimeD[state[15]]; + tmp[6] = XtimeD[state[12]] ^ Xtime9[state[13]] ^ XtimeE[state[14]] ^ XtimeB[state[15]]; + tmp[11] = XtimeB[state[12]] ^ XtimeD[state[13]] ^ Xtime9[state[14]] ^ XtimeE[state[15]]; + + for( i=0; i < 4 * Nb; i++ ) + state[i] = InvSbox[tmp[i]]; +} + +// encrypt/decrypt columns of the key +INLINE void AddRoundKey (uint8_t *state, uint8_t *key) +{ + xor_block(state, state, key, 16); +} + +static uint8_t Rcon[11] = +{ + 0x00, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36 +}; + +// produce Nb bytes for each round +static void AES_expandKey(BlockCipher *c_, const void *key, size_t len) +{ + AES_Context *c = (AES_Context *)c_; + ASSERT(len == c->c.key_len); + + uint8_t tmp0, tmp1, tmp2, tmp3, tmp4; + uint32_t idx, idx_mod_nk, idx_div_nk; + int Nk = c->c.key_len/4; + int Nr = c->num_rounds; + + memcpy (c->expkey, key, Nk*4); + + for( idx = Nk, idx_mod_nk = 0, idx_div_nk = 1; idx < Nb * (Nr + 1); idx++ ) { + tmp0 = c->expkey[4*idx - 4]; + tmp1 = c->expkey[4*idx - 3]; + tmp2 = c->expkey[4*idx - 2]; + tmp3 = c->expkey[4*idx - 1]; + + if( idx_mod_nk == 0 ) { + tmp4 = tmp3; + tmp3 = Sbox[tmp0]; + tmp0 = Sbox[tmp1] ^ Rcon[idx_div_nk]; + tmp1 = Sbox[tmp2]; + tmp2 = Sbox[tmp4]; + } else if( Nk > 6 && idx_mod_nk == 4 ) { + tmp0 = Sbox[tmp0]; + tmp1 = Sbox[tmp1]; + tmp2 = Sbox[tmp2]; + tmp3 = Sbox[tmp3]; + } + + c->expkey[4*idx+0] = c->expkey[4*idx - 4*Nk + 0] ^ tmp0; + c->expkey[4*idx+1] = c->expkey[4*idx - 4*Nk + 1] ^ tmp1; + c->expkey[4*idx+2] = c->expkey[4*idx - 4*Nk + 2] ^ tmp2; + c->expkey[4*idx+3] = c->expkey[4*idx - 4*Nk + 3] ^ tmp3; + + idx_mod_nk += 1; + if (idx_mod_nk == Nk) + { + idx_mod_nk = 0; + ++idx_div_nk; + } + } +} + +// encrypt one 128 bit block +static void AES_encrypt(BlockCipher *c_, void *block) +{ + AES_Context *c = (AES_Context *)c_; + uint8_t Nr = c->num_rounds; + uint32_t round; + + AddRoundKey (block, c->expkey); + + for( round = 1; round < Nr + 1; round++ ) { + if( round < Nr ) + MixSubColumns (block); + else + ShiftRows (block); + + AddRoundKey (block, c->expkey + round * Nb * 4); + } +} + +static void AES_decrypt(BlockCipher *c_, void *block) +{ + AES_Context *c = (AES_Context *)c_; + uint8_t Nr = c->num_rounds; + uint32_t round; + + AddRoundKey (block, c->expkey + Nr * Nb * 4); + InvShiftRows(block); + + for( round = Nr; round--; ) + { + AddRoundKey (block, c->expkey + round * Nb * 4); + if( round ) + InvMixSubColumns (block); + } +}