/* Zupt — X25519 Constant-Time Conditional Swap (Jasmin)
 * Copyright (c) 2026 Cristian Cezar Moisés — MIT License
 *
 * CT-REQUIRED: fe_cswap must not leak cond via timing.
 * This is the only CT-critical field operation in X25519.
 * fe_add/fe_sub/fe_mul use C fallback (data-independent timing
 * on x86-64 — ADD/MUL have fixed latency).
 *
 * 4 × u64 limbs, pure register operations, no intrinsics needed.
 */

export fn zupt_fe_cswap(
    reg u64 a_ptr,
    reg u64 b_ptr,
    reg u64 cond)
{
    reg u64 mask ta tb diff;
    inline int i;

    mask = 0;
    mask -= cond;

    for i = 0 to 4 {
        ta = [a_ptr + 8 * i];
        tb = [b_ptr + 8 * i];
        diff = ta;
        diff ^= tb;
        diff &= mask;
        ta ^= diff;
        tb ^= diff;
        [a_ptr + 8 * i] = ta;
        [b_ptr + 8 * i] = tb;
    }
}