aes_rval aes_dec_blk(const unsigned char in_blk[], unsigned char out_blk[], const aes_ctx cx[1])
{ uint32_t locals(b0, b1);
const uint32_t *kp = cx->k_sch + nc * cx->n_rnd;
dec_imvars /* declare variables for inv_mcol() if needed */
if(!(cx->n_blk & 2)) return aes_bad;
#if (DEC_UNROLL == FULL)
state_in((cx->n_rnd & 1 ? b1 : b0), in_blk, kp);
kp = cx->k_sch + 9 * nc;
switch(cx->n_rnd)
{
case 14: round(inv_rnd, b1, b0, kp + 4 * nc);
case 13: round(inv_rnd, b0, b1, kp + 3 * nc);
case 12: round(inv_rnd, b1, b0, kp + 2 * nc);
case 11: round(inv_rnd, b0, b1, kp + nc);
case 10: round(inv_rnd, b1, b0, kp );
round(inv_rnd, b0, b1, kp - nc);
round(inv_rnd, b1, b0, kp - 2 * nc);
round(inv_rnd, b0, b1, kp - 3 * nc);
round(inv_rnd, b1, b0, kp - 4 * nc);
round(inv_rnd, b0, b1, kp - 5 * nc);
round(inv_rnd, b1, b0, kp - 6 * nc);
round(inv_rnd, b0, b1, kp - 7 * nc);
round(inv_rnd, b1, b0, kp - 8 * nc);
round(inv_lrnd, b0, b1, kp - 9 * nc);
}
#else
{ uint32_t rnd;
state_in(b0, in_blk, kp);
#if (DEC_UNROLL == PARTIAL)
for(rnd = 0; rnd < (cx->n_rnd - 1) >> 1; ++rnd)
{
kp -= nc;
round(inv_rnd, b1, b0, kp);
kp -= nc;
round(inv_rnd, b0, b1, kp);
}
if(cx->n_rnd & 1)
{
l_copy(b1, b0);
}
else
{
kp -= nc;
round(inv_rnd, b1, b0, kp);
}
#else
for(rnd = 0; rnd < cx->n_rnd - 1; ++rnd)
{
kp -= nc;
round(inv_rnd, b1, b0, kp);
l_copy(b0, b1);
}
#endif
kp -= nc;
round(inv_lrnd, b0, b1, kp);
}
#endif
state_out(out_blk, b0);
return aes_good;
}
aes_rval aes_enc_blk(const unsigned char in_blk[], unsigned char out_blk[], const aes_ctx cx[1])
{ aes_32t locals(b0, b1);
const aes_32t *kp = cx->k_sch;
dec_fmvars /* declare variables for fwd_mcol() if needed */
if(!(cx->n_blk & 1)) return aes_bad;
#if (ENC_UNROLL == FULL)
state_in((cx->n_rnd & 1 ? b1 : b0), in_blk, kp);
kp += (cx->n_rnd - 9) * nc;
switch(cx->n_rnd)
{
case 14: round(fwd_rnd, b1, b0, kp - 4 * nc);
case 13: round(fwd_rnd, b0, b1, kp - 3 * nc);
case 12: round(fwd_rnd, b1, b0, kp - 2 * nc);
case 11: round(fwd_rnd, b0, b1, kp - nc);
case 10: round(fwd_rnd, b1, b0, kp );
round(fwd_rnd, b0, b1, kp + nc);
round(fwd_rnd, b1, b0, kp + 2 * nc);
round(fwd_rnd, b0, b1, kp + 3 * nc);
round(fwd_rnd, b1, b0, kp + 4 * nc);
round(fwd_rnd, b0, b1, kp + 5 * nc);
round(fwd_rnd, b1, b0, kp + 6 * nc);
round(fwd_rnd, b0, b1, kp + 7 * nc);
round(fwd_rnd, b1, b0, kp + 8 * nc);
round(fwd_lrnd, b0, b1, kp + 9 * nc);
}
#else
{ aes_32t rnd;
state_in(b0, in_blk, kp);
#if (ENC_UNROLL == PARTIAL)
for(rnd = 0; rnd < (cx->n_rnd - 1) >> 1; ++rnd)
{
kp += nc;
round(fwd_rnd, b1, b0, kp);
kp += nc;
round(fwd_rnd, b0, b1, kp);
}
if(cx->n_rnd & 1)
{
l_copy(b1, b0);
}
else
{
kp += nc;
round(fwd_rnd, b1, b0, kp);
}
#else
for(rnd = 0; rnd < cx->n_rnd - 1; ++rnd)
{
kp += nc;
round(fwd_rnd, b1, b0, kp);
l_copy(b0, b1);
}
#endif
kp += nc;
round(fwd_lrnd, b0, b1, kp);
}
#endif
state_out(out_blk, b0);
return aes_good;
}
