Remote Access Control

aes.c

Go to the documentation of this file.

// This file has been prepared for Doxygen automatic documentation generation.
#include "aes.h"
#include "common.h"
#include "config.h"



#define BPOLY 0x1b

#if SCHEDULE_EXTRA > 0
__no_init byte __eeprom keyScheduleInEEPROM[ SCHEDULE_EXTRA ];
#endif

static byte keyScheduleInSRAM[ SCHEDULE_SPLIT ];

static const byte __flash sBox[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 void cycleLeft( byte * row )
{
        byte temp = row[0];
        row[0] = row[1];
        row[1] = row[2];
        row[2] = row[3];
        row[3] = temp;
}



static void mixColumn( byte * column )
{
        byte result0, result1, result2, result3;
        byte column0, column1, column2, column3;
        byte xor;

        // This generates more effective code, at least
        // with the IAR C compiler.
        column0 = column[0];
        column1 = column[1];
        column2 = column[2];
        column3 = column[3];

        // Partial sums (modular addition using XOR).
        result0 = column1 ^ column2 ^ column3;
        result1 = column0 ^ column2 ^ column3;
        result2 = column0 ^ column1 ^ column3;
        result3 = column0 ^ column1 ^ column2;

        // Multiply column bytes by 2 modulo BPOLY.
        // This operation is done the following way to ensure cycle count
        // independent from data contents. Take care when changing this code.
        xor = 0;
        if (column0 & 0x80) {
                xor = BPOLY;
        }
        column0 <<= 1;
        column0  ^= xor;
        
        xor = 0;
        if (column1 & 0x80) {
                xor = BPOLY;
        }
        column1 <<= 1;
        column1  ^= xor;
        
        xor = 0;
        if (column2 & 0x80) {
                xor = BPOLY;
        }
        column2 <<= 1;
        column2  ^= xor;
        
        xor = 0;
        if (column3 & 0x80) {
                xor = BPOLY;
        }
        column3 <<= 1;
        column3  ^= xor;

        // Final sums stored into original column bytes.
        column[0] = result0 ^ column0 ^ column1;
        column[1] = result1 ^ column1 ^ column2;
        column[2] = result2 ^ column2 ^ column3;
        column[3] = result3 ^ column0 ^ column3;
}



static void mixColumns( byte * state )
{
        mixColumn( state + 0*4 );
        mixColumn( state + 1*4 );
        mixColumn( state + 2*4 );
        mixColumn( state + 3*4 );
}



static void subBytes( byte * bytes, byte count )
{
        // Copy to temporary variables for optimization.
        byte * tempPtr = bytes;
        byte tempCount = count;

        do {
                *tempPtr = sBox[ *tempPtr ]; // Substitute every byte in state.
                ++tempPtr;
        } while( --tempCount );
}



static void shiftRows( byte * state )
{
        byte temp;

        // Note: State is arranged column by column.

        // Cycle second row left one time.
        temp = state[ 1 + 0*4 ];
        state[ 1 + 0*4 ] = state[ 1 + 1*4 ];
        state[ 1 + 1*4 ] = state[ 1 + 2*4 ];
        state[ 1 + 2*4 ] = state[ 1 + 3*4 ];
        state[ 1 + 3*4 ] = temp;

        // Cycle third row left two times.
        temp = state[ 2 + 0*4 ];
        state[ 2 + 0*4 ] = state[ 2 + 2*4 ];
        state[ 2 + 2*4 ] = temp;
        temp = state[ 2 + 1*4 ];
        state[ 2 + 1*4 ] = state[ 2 + 3*4 ];
        state[ 2 + 3*4 ] = temp;

        // Cycle fourth row left three times, ie. right once.
        temp = state[ 3 + 3*4 ];
        state[ 3 + 3*4 ] = state[ 3 + 2*4 ];
        state[ 3 + 2*4 ] = state[ 3 + 1*4 ];
        state[ 3 + 1*4 ] = state[ 3 + 0*4 ];
        state[ 3 + 0*4 ] = temp;
}



static void addConstant( byte * bytes, const byte * constant, byte count )
{
        // Copy to temporary variables for optimization.
        byte * tempDestination = bytes;
        const byte * tempSource = constant;
        byte tempCount = count;
        byte tempValue;

        do {
                 // Add in GF(2), ie. XOR.
                tempValue = *tempDestination ^ *tempSource++;
                *tempDestination++ = tempValue;
        } while( --tempCount );
}



static void addConstantAndSubstitute( byte * bytes, const byte * constant, byte count )
{
        // Copy to temporary variables for optimization.
        byte * tempDestination = bytes;
        const byte * tempSource = constant;
        byte tempCount = count;
        byte tempValue;

        do {
                // Add in GF(2), ie. XOR.
                tempValue = *tempDestination ^ *tempSource++;
                *tempDestination++ = sBox[ tempValue ];
        } while( --tempCount );
}



static void addConstantFromEEPROMAndSubstitute( byte * bytes,
                const byte __eeprom * constant, byte count )
{
        // Copy to temporary variables for optimization.
        byte * tempDestination = bytes;
        byte tempCount = count;
        byte tempValue;
        EEAR = (unsigned short int) constant;

        do {
                EECR |= (1<<EERE);
                ++EEAR;
                tempValue = *tempDestination ^ EEDR; // Add in GF(2), ie. XOR.
                *tempDestination++ = sBox[ tempValue ];
        } while( --tempCount );
}



void cipherLookup( byte * block )
{
        byte * keySchedule1 = keyScheduleInSRAM;
        byte round = 0;

#if SCHEDULE_EXTRA > 0
        byte __eeprom * keySchedule2 = keyScheduleInEEPROM;

        for( ; round < SCHEDULE_SPLIT_BLOCKS; ++round ) {
                addConstantAndSubstitute( block, keySchedule1, BLOCK_SIZE );
                shiftRows( block );
                mixColumns( block );
                keySchedule1 += BLOCK_SIZE;
        }

        for( ; round < ROUNDS-1; ++round ) {
                addConstantFromEEPROMAndSubstitute( block,
                                keySchedule2, BLOCK_SIZE );
                shiftRows( block );
                mixColumns( block );
                keySchedule2 += BLOCK_SIZE;
        }

        addConstantFromEEPROMAndSubstitute( block, keySchedule2, BLOCK_SIZE );
        shiftRows( block );
        keySchedule2 += BLOCK_SIZE;
        addConstantFromEEPROM( block, keySchedule2, BLOCK_SIZE );
#else
        for( ; round < ROUNDS-1; ++round ) {
                addConstantAndSubstitute( block, keySchedule1, BLOCK_SIZE );
                shiftRows( block );
                mixColumns( block );
                keySchedule1 += BLOCK_SIZE;
        }

        addConstantAndSubstitute( block, keySchedule1, BLOCK_SIZE );
        shiftRows( block );
        keySchedule1 += BLOCK_SIZE;
        addConstant( block, keySchedule1, BLOCK_SIZE );
#endif
}



void calcKeySchedule( const byte __eeprom * key )
{
        byte schedulePos; // Current position inside schedule.
        byte temp[4]; // Temporary word when expanding the key.
        byte roundConstant[4] = { 0x01, 0x00, 0x00, 0x00 };
        byte * keySchedule1 = keyScheduleInSRAM;
#if SCHEDULE_EXTRA > 0
        byte __eeprom * keySchedule2 = keyScheduleInEEPROM;
#endif

        // Copy entire key to start of schedule.
        copyBytesFromEEPROM( keySchedule1, key, KEY_SIZE );
        keySchedule1 += KEY_SIZE;
        // Copy last 4 bytes of key to temp word.
        copyBytes( temp, keySchedule1-4, 4 );

        // Expand key into schedule buffer 1 first.
        schedulePos = KEY_SIZE;
        while( schedulePos < SCHEDULE_SIZE ) {
                // Multiple of key size?
                if( (schedulePos % KEY_SIZE) == 0 ) {
                        cycleLeft( temp ); // Cycle left one byte.
                        subBytes( temp, 4 ); // Substitute each byte.
                        addConstant( temp, roundConstant, 4 ); // Add to temp.
                
                        // Modular doubling of round constant's first byte.
                        // This operation is done the following way to ensure cycle count
                        // independent from data contents. Take care when changing this code.
                        xor = 0;
                        if (roundConstant[0] & 0x80) {
                                xor = BPOLY;
                        }
                        roundConstant[0] <<= 1;
                        roundConstant[0]  ^= xor;
                }

#if KEY_SIZE > 24
                // Multiple of key size + block size, ie. block size into key.
                else if( (schedulePos % KEY_SIZE) == BLOCK_SIZE ) {
                        subBytes( temp, 4 ); // Substitute each byte.
                }
#endif

#if SCHEDULE_EXTRA > 0
                // Select correct source buffer for addition temp word.
                if( schedulePos <= SCHEDULE_SPLIT+KEY_SIZE-4 ) {
#endif
                        // Add with data KEY_SIZE backwards in schedule.
                        addConstant( temp, keySchedule1 - KEY_SIZE, 4 );

#if SCHEDULE_EXTRA > 0
                        // Copy temp word to currect destination buffer.
                        if( schedulePos <= SCHEDULE_SPLIT-4 ) {
#endif
                                copyBytes( keySchedule1, temp, 4 );
                                keySchedule1 += 4;
#if SCHEDULE_EXTRA > 0
                        } else {
                                copyBytesToEEPROM( keySchedule2, temp, 4 );
                                keySchedule1 += 4; // We need buffer 1 also.
                                keySchedule2 += 4;
                        }
                } else {
                        // Add with data KEY_SIZE backwards in schedule.
                        addConstantFromEEPROM( temp,
                                        keySchedule2 - KEY_SIZE, 4 );
                        copyBytesToEEPROM( keySchedule2, temp, 4 );
                        keySchedule2 += 4;
                }
#endif
                schedulePos += 4;
        }
}