#include"auxFormat.h"

#define RATE (64 / 8)

#define PR0_ROUNDS 52
#define PR_ROUNDS 28
#define PRF_ROUNDS 32
unsigned char  constant6Format[63] = {
	/*constant6_aead_128v1:*/
0x1,
0x10,
0x2,
0x20,
0x4,
0x41,
0x11,
0x12,
0x22,
0x24,
0x45,
0x50,
0x3,
0x30,
0x6,
0x61,
0x15,
0x53,
0x33,
0x36,
0x67,
0x74,
0x46,
0x60,
0x5,
0x51,
0x13,
0x32,
0x26,
0x65,
0x54,
0x42,
0x21,
0x14,
0x43,
0x31,
0x16,
0x63,
0x35,
0x57,
0x72,
0x27,
0x75,
0x56,
0x62,
0x25,
0x55,
0x52,
0x23,
0x34,
0x47,
0x70,
0x7,
0x71,
0x17,
0x73,
0x37,
0x77,
0x76,
0x66,
0x64,
0x44,
0x40,

};




static void permutation256(unsigned int *in, int rounds, unsigned char *rc) {
	uint32_t w0, w1, w2, w3, w4, w5, w6, w7;
	uint32_t s0, s1, s2;
	__asm volatile(
		"ldr     %[w0],     [%[in]]          \n\t"
		"ldr     %[w4],     [%[in], #4]      \n\t"
		"ldr     %[w1],     [%[in], #8]      \n\t"
		"ldr     %[w5],     [%[in], #12]     \n\t"
		"ldr     %[w2],     [%[in], #16]     \n\t"
		"ldr     %[w6],     [%[in], #20]     \n\t"
		"ldr     %[w3],     [%[in], #24]     \n\t"
		"ldr     %[w7],     [%[in], #28]     \n\t"
	"enc_loop_%=:                       \n\t"
    "/*add round const   s0 s1*/           \n\t"
		"ldrb    %[s0],     [%[rc]]          \n\t"
		"LSR     %[s1],     %[s0], #4       \n\t"
		"and    %[s0],     %[s0], 0xf        \n\t"
	  "eors    %[w4],     %[w4], %[s0]        \n\t"
	  "eors    %[w0],     %[w0], %[s1]        \n\t"
    "/*sbox first column*/         \n\t"
		"mvns    %[w0],     %[w0]            \n\t"
		"ands    %[s0],     %[w1], %[w0]        \n\t"
		"eors    %[s0],     %[w2], %[s0]        \n\t"
		"orrs    %[w2],     %[w1], %[w2]        \n\t"
		"eors    %[w0],     %[w3], %[w0]        \n\t"
		"eors    %[w2],     %[w2], %[w0]        \n\t"
		"eors    %[s1],     %[w1], %[w3]        \n\t"
		"eors    %[w3],     %[w3], %[s0]        \n\t"
		"ands    %[w0],     %[s0], %[w0]        \n\t"
		"eors    %[w0],     %[s1], %[w0]        \n\t"
		"ands    %[w1],     %[w2], %[s1]        \n\t"
		"eors    %[w1],     %[s0], %[w1]        \n\t"
		"/*sbox second column*/        \n\t"
		"mvns    %[w4],     %[w4]            \n\t"
		"ands    %[s0],     %[w5], %[w4]        \n\t"
		"eors    %[s0],     %[w6], %[s0]        \n\t"
		"orrs    %[w6],     %[w5], %[w6]        \n\t"
		"eors    %[w4],     %[w7], %[w4]        \n\t"
		"eors    %[w6],     %[w6], %[w4]        \n\t"
		"eors    %[s1],     %[w5], %[w7]        \n\t"
		"eors    %[w7],     %[w7], %[s0]        \n\t"
		"ands    %[w4],     %[s0], %[w4]        \n\t"
		"eors    %[w4],     %[s1], %[w4]        \n\t"
		"ands    %[w5],     %[w6], %[s1]        \n\t"
		"eors    %[w5],     %[s0], %[w5]        \n\t"
    "/*rotate shift left 1 bit*/   \n\t"
		"mov    %[s0],     %[w5]       \n\t"
		"ROR    %[w5],     %[w1], #31        \n\t"
		"mov    %[w1],     %[s0]       \n\t"
    "/*rotate shift left 8 bits*/  \n\t"
		"ROR    %[w2],     %[w2], #28        \n\t"
		"ROR    %[w6],     %[w6], #28       \n\t"
    "/*rotate shift left 25 bits*/ \n\t"
		"mov    %[s0],     %[w3]       \n\t"
		"ROR    %[w3],     %[w7], #20       \n\t"
		"ROR    %[w7],     %[s0], #19       \n\t"
		"/*loop control*/              \n\t"
		"adds    %[rc],     %[rc], #1        \n\t"
		"subs    %[rounds], %[rounds],  #1   \n\t"
		"bne     enc_loop_%=              \n\t"
		"str     %[w0],     [%[in]]         \n\t"
		"str     %[w4],     [%[in], #4]     \n\t"
		"str     %[w1],     [%[in], #8]     \n\t"
		"str     %[w5],     [%[in], #12]    \n\t"
		"str     %[w2],     [%[in], #16]    \n\t"
		"str     %[w6],     [%[in], #20]    \n\t"
		"str     %[w3],     [%[in], #24]    \n\t"
		"str     %[w7],     [%[in], #28]    \n\t"

        : [rounds] "=r" (rounds), [rc] "=r" (rc),
          [w0] "=r" (w0), [w1] "=r" (w1), [w2] "=r" (w2), [w3] "=r" (w3),
          [w4] "=r" (w4), [w5] "=r" (w5), [w6] "=r" (w6), [w7] "=r" (w7),
          [s0] "=r" (s0), [s1] "=r" (s1), [s2] "=r" (s2)
        : [in] "r" (in), "[rounds]" (rounds), "[rc]" (rc)
	);
}


int crypto_aead_encrypt(unsigned char *c, unsigned long long *clen,
	const unsigned char *m, unsigned long long mlen,
	const unsigned char *ad, unsigned long long adlen,
	const unsigned char *nsec, const unsigned char *npub,
	const unsigned char *k) {
	unsigned int  i, j;
	u32 s[8] = { 0 };
	u32 dataFormat[2] = { 0 };
	u8 tempData[8];
	u32 s_temp[8] = { 0 };
	u32 t1, t2, t3, t5, t6, t8, t9, t11;
	*clen = mlen + CRYPTO_ABYTES;
	//initialization
	packFormat(s, npub);
	packFormat((s + 2), (npub + 8));
	packFormat((s + 4), k);
	packFormat((s + 6), (k + 8));
	permutation256(s,PR0_ROUNDS,constant6Format);
	// process associated data
	if (adlen) {
		while (adlen >= RATE) {
			packFormat(dataFormat, ad);
			s[0] ^= dataFormat[0];
			s[1] ^= dataFormat[1];
	permutation256(s,PR_ROUNDS,constant6Format);
			adlen -= RATE;
			ad += RATE;
		}
		memset(tempData, 0, sizeof(tempData));
memcpy(tempData, ad, adlen * sizeof(unsigned char));	
tempData[adlen] = 0x01;
		packFormat(dataFormat, tempData);
		s[0] ^= dataFormat[0];
		s[1] ^= dataFormat[1];
	permutation256(s,PR_ROUNDS,constant6Format);
	}
	s[6] ^= 0x80000000;
	if (mlen) {
		while (mlen >= RATE) {
			packFormat(dataFormat, m);
			s[0] ^= dataFormat[0];
			s[1] ^= dataFormat[1];
			unpackFormat(c, s);
	permutation256(s,PR_ROUNDS,constant6Format);
			mlen -= RATE;
			m += RATE;
			c += RATE;
		}
		memset(tempData, 0, sizeof(tempData));
memcpy(tempData, m, mlen * sizeof(unsigned char));
  
tempData[mlen]= 0x01;
		packFormat(dataFormat, tempData);
		s[0] ^= dataFormat[0];
		s[1] ^= dataFormat[1];
		unpackFormat(tempData, s);
		memcpy(c, tempData, mlen * sizeof(unsigned char));
		c +=mlen;
	}
	// finalization
	permutation256(s,PRF_ROUNDS,constant6Format);
	// return tag
	unpackFormat(tempData, s);
		memcpy(c, tempData, sizeof(tempData));
	unpackFormat(tempData,(s + 2));
		memcpy(c+8, tempData, sizeof(tempData));
//	unpackFormat((c), s);
//	unpackFormat((c+8),(s + 2));
	return 0;
}

int crypto_aead_decrypt(unsigned char *m, unsigned long long *mlen,
	unsigned char *nsec, const unsigned char *c, unsigned long long clen,
	const unsigned char *ad, unsigned long long adlen,
	const unsigned char *npub, const unsigned char *k) {
	u8 i, j;
	// initialization
	u32 s[8] = { 0 };
	u32 dataFormat[4] = { 0 };
	u32 dataFormat_1[2] = { 0 };
	u8 tempU8[32] = { 0 };
	u8 tempData[8];
	u32 s_temp[8] = { 0 };
	u32 t1, t2, t3, t5, t6, t8, t9, t11;
		*mlen = clen - CRYPTO_ABYTES;
	if (clen < CRYPTO_ABYTES)
		return -1;
	//initialization
	packFormat(s, npub);
	packFormat((s + 2), (npub + 8));
	packFormat((s + 4), k);
	packFormat((s + 6), (k + 8));
	permutation256(s,PR0_ROUNDS,constant6Format);
	// process associated data
	if (adlen) {
		while (adlen >= RATE) {
			packFormat(dataFormat, ad);
			s[0] ^= dataFormat[0];
			s[1] ^= dataFormat[1];
	permutation256(s,PR_ROUNDS,constant6Format);
			adlen -= RATE;
			ad += RATE;
		}
		memset(tempData, 0, sizeof(tempData));
		memcpy(tempData, ad, adlen * sizeof(unsigned char));
		tempData[adlen] = 0x01;
		packFormat(dataFormat, tempData);
		s[0] ^= dataFormat[0];
		s[1] ^= dataFormat[1];
	permutation256(s,PR_ROUNDS,constant6Format);
	}
	s[6] ^= 0x80000000;
  // process c
	clen = clen - CRYPTO_KEYBYTES;
	if (clen) {
		while (clen >= RATE) {
			packFormat(dataFormat, c);
			dataFormat_1[0] = s[0] ^ dataFormat[0];
			dataFormat_1[1] = s[1] ^ dataFormat[1];
			unpackFormat(m, dataFormat_1);
			s[0] = dataFormat[0];
			s[1] = dataFormat[1];
	permutation256(s,PR_ROUNDS,constant6Format);
			clen -= RATE;
			m += RATE;
			c += RATE;
		}
		unpackFormat(tempU8, s);
		for (i = 0; i < clen; ++i, ++m, ++c)
		{
			*m = tempU8[i]^ *c;
			tempU8[i] = *c;
		}
		tempU8[i] ^= 0x01;
		packFormat(s, tempU8);	
	}
	// finalization
	permutation256(s,PRF_ROUNDS,constant6Format);
	// return tag	
	packFormat(dataFormat, c);
	packFormat((dataFormat + 2), (c +8));
	if (dataFormat[0] != s[0] || dataFormat[1] != s[1] || dataFormat[2] != s[2] || dataFormat[3] != s[3]) {
		return -1;
	}
	return 0;
}