static void serpent_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
{
struct serpent_ctx *ctx = crypto_tfm_ctx(tfm);
const u32
*k = ((struct serpent_ctx *)ctx)->expkey;
const __le32 *s = (const __le32 *)src;
__le32 *d = (__le32 *)dst;
u32 r0, r1, r2, r3, r4;
r0 = le32_to_cpu(s[0]);
r1 = le32_to_cpu(s[1]);
r2 = le32_to_cpu(s[2]);
r3 = le32_to_cpu(s[3]);
K(r0,r1,r2,r3,32);
SI7(r0,r1,r2,r3,r4); KL(r1,r3,r0,r4,r2,31);
SI6(r1,r3,r0,r4,r2); KL(r0,r2,r4,r1,r3,30);
SI5(r0,r2,r4,r1,r3); KL(r2,r3,r0,r4,r1,29);
SI4(r2,r3,r0,r4,r1); KL(r2,r0,r1,r4,r3,28);
SI3(r2,r0,r1,r4,r3); KL(r1,r2,r3,r4,r0,27);
SI2(r1,r2,r3,r4,r0); KL(r2,r0,r4,r3,r1,26);
SI1(r2,r0,r4,r3,r1); KL(r1,r0,r4,r3,r2,25);
SI0(r1,r0,r4,r3,r2); KL(r4,r2,r0,r1,r3,24);
SI7(r4,r2,r0,r1,r3); KL(r2,r1,r4,r3,r0,23);
SI6(r2,r1,r4,r3,r0); KL(r4,r0,r3,r2,r1,22);
SI5(r4,r0,r3,r2,r1); KL(r0,r1,r4,r3,r2,21);
SI4(r0,r1,r4,r3,r2); KL(r0,r4,r2,r3,r1,20);
SI3(r0,r4,r2,r3,r1); KL(r2,r0,r1,r3,r4,19);
SI2(r2,r0,r1,r3,r4); KL(r0,r4,r3,r1,r2,18);
SI1(r0,r4,r3,r1,r2); KL(r2,r4,r3,r1,r0,17);
SI0(r2,r4,r3,r1,r0); KL(r3,r0,r4,r2,r1,16);
SI7(r3,r0,r4,r2,r1); KL(r0,r2,r3,r1,r4,15);
SI6(r0,r2,r3,r1,r4); KL(r3,r4,r1,r0,r2,14);
SI5(r3,r4,r1,r0,r2); KL(r4,r2,r3,r1,r0,13);
SI4(r4,r2,r3,r1,r0); KL(r4,r3,r0,r1,r2,12);
SI3(r4,r3,r0,r1,r2); KL(r0,r4,r2,r1,r3,11);
SI2(r0,r4,r2,r1,r3); KL(r4,r3,r1,r2,r0,10);
SI1(r4,r3,r1,r2,r0); KL(r0,r3,r1,r2,r4,9);
SI0(r0,r3,r1,r2,r4); KL(r1,r4,r3,r0,r2,8);
SI7(r1,r4,r3,r0,r2); KL(r4,r0,r1,r2,r3,7);
SI6(r4,r0,r1,r2,r3); KL(r1,r3,r2,r4,r0,6);
SI5(r1,r3,r2,r4,r0); KL(r3,r0,r1,r2,r4,5);
SI4(r3,r0,r1,r2,r4); KL(r3,r1,r4,r2,r0,4);
SI3(r3,r1,r4,r2,r0); KL(r4,r3,r0,r2,r1,3);
SI2(r4,r3,r0,r2,r1); KL(r3,r1,r2,r0,r4,2);
SI1(r3,r1,r2,r0,r4); KL(r4,r1,r2,r0,r3,1);
SI0(r4,r1,r2,r0,r3); K(r2,r3,r1,r4,0);
d[0] = cpu_to_le32(r2);
d[1] = cpu_to_le32(r3);
d[2] = cpu_to_le32(r1);
d[3] = cpu_to_le32(r4);
}
void _stdcall serpent256_decrypt(const unsigned char *in, unsigned char *out, serpent256_key *key)
{
u32 *k = key->expkey;
u32 r0, r1, r2, r3, r4;
r0 = p32(in)[0]; r1 = p32(in)[1];
r2 = p32(in)[2]; r3 = p32(in)[3];
K(r0,r1,r2,r3,32);
SI7(r0,r1,r2,r3,r4); KL(r1,r3,r0,r4,r2,31);
SI6(r1,r3,r0,r4,r2); KL(r0,r2,r4,r1,r3,30);
SI5(r0,r2,r4,r1,r3); KL(r2,r3,r0,r4,r1,29);
SI4(r2,r3,r0,r4,r1); KL(r2,r0,r1,r4,r3,28);
SI3(r2,r0,r1,r4,r3); KL(r1,r2,r3,r4,r0,27);
SI2(r1,r2,r3,r4,r0); KL(r2,r0,r4,r3,r1,26);
SI1(r2,r0,r4,r3,r1); KL(r1,r0,r4,r3,r2,25);
SI0(r1,r0,r4,r3,r2); KL(r4,r2,r0,r1,r3,24);
SI7(r4,r2,r0,r1,r3); KL(r2,r1,r4,r3,r0,23);
SI6(r2,r1,r4,r3,r0); KL(r4,r0,r3,r2,r1,22);
SI5(r4,r0,r3,r2,r1); KL(r0,r1,r4,r3,r2,21);
SI4(r0,r1,r4,r3,r2); KL(r0,r4,r2,r3,r1,20);
SI3(r0,r4,r2,r3,r1); KL(r2,r0,r1,r3,r4,19);
SI2(r2,r0,r1,r3,r4); KL(r0,r4,r3,r1,r2,18);
SI1(r0,r4,r3,r1,r2); KL(r2,r4,r3,r1,r0,17);
SI0(r2,r4,r3,r1,r0); KL(r3,r0,r4,r2,r1,16);
SI7(r3,r0,r4,r2,r1); KL(r0,r2,r3,r1,r4,15);
SI6(r0,r2,r3,r1,r4); KL(r3,r4,r1,r0,r2,14);
SI5(r3,r4,r1,r0,r2); KL(r4,r2,r3,r1,r0,13);
SI4(r4,r2,r3,r1,r0); KL(r4,r3,r0,r1,r2,12);
SI3(r4,r3,r0,r1,r2); KL(r0,r4,r2,r1,r3,11);
SI2(r0,r4,r2,r1,r3); KL(r4,r3,r1,r2,r0,10);
SI1(r4,r3,r1,r2,r0); KL(r0,r3,r1,r2,r4,9);
SI0(r0,r3,r1,r2,r4); KL(r1,r4,r3,r0,r2,8);
SI7(r1,r4,r3,r0,r2); KL(r4,r0,r1,r2,r3,7);
SI6(r4,r0,r1,r2,r3); KL(r1,r3,r2,r4,r0,6);
SI5(r1,r3,r2,r4,r0); KL(r3,r0,r1,r2,r4,5);
SI4(r3,r0,r1,r2,r4); KL(r3,r1,r4,r2,r0,4);
SI3(r3,r1,r4,r2,r0); KL(r4,r3,r0,r2,r1,3);
SI2(r4,r3,r0,r2,r1); KL(r3,r1,r2,r0,r4,2);
SI1(r3,r1,r2,r0,r4); KL(r4,r1,r2,r0,r3,1);
SI0(r4,r1,r2,r0,r3); K(r2,r3,r1,r4,0);
p32(out)[0] = r2; p32(out)[1] = r3;
p32(out)[2] = r1; p32(out)[3] = r4;
}
static void Sha256ProcessBlock(Sha256Ctx *Ctx, BYTE *block)
{
unsigned int i;
DWORD w[64], temp1, temp2;
DWORD a = Ctx->State[0];
DWORD b = Ctx->State[1];
DWORD c = Ctx->State[2];
DWORD d = Ctx->State[3];
DWORD e = Ctx->State[4];
DWORD f = Ctx->State[5];
DWORD g = Ctx->State[6];
DWORD h = Ctx->State[7];
for (i = 0; i < 16; i++)
//w[ i ] = GET_UAA32BE(block, i);
w[i] = BE32(((DWORD*)block)[i]);
for (i = 16; i < 64; i++)
w[ i ] = SI4(w[ i - 2 ]) + w[ i - 7 ] + SI3(w[ i - 15 ]) + w[ i - 16 ];
for (i = 0; i < 64; i++)
{
temp1 = h + SI2(e) + F0(e, f, g) + k[ i ] + w[ i ];
temp2 = SI1(a) + F1(a, b, c);
h = g;
g = f;
f = e;
e = d + temp1;
d = c;
c = b;
b = a;
a = temp1 + temp2;
}
Ctx->State[0] += a;
Ctx->State[1] += b;
Ctx->State[2] += c;
Ctx->State[3] += d;
Ctx->State[4] += e;
Ctx->State[5] += f;
Ctx->State[6] += g;
Ctx->State[7] += h;
}