rebbarb/exi_bba/exi_j4.py

"""EXI pad merging for the J4 debug-header bring-up path (``EXI_J4=1``).

``BBATopSynth`` can mirror the EXI interface onto the unpopulated J4 debug
header so a bench host (e.g. a Raspberry Pi) can drive EXI without the SP1 edge
connector.  Rather than REPINNING the EXI resource onto J4 -- which would move
where the capture domain anchors on the die -- a second set of pads is MERGED
onto the existing ones, leaving SP1 live and the default build untouched.

The merge itself lives here, in one place, so the synthesis path and the
testbench below exercise the same code.

Run the test:  ``python -m exi_bba.exi_j4``
"""

__all__ = ["merge_exi_inputs"]


def merge_exi_inputs(primary, mirror):
    """AND-merge two sets of EXI input pads into one.

    `primary` and `mirror` are ``(clk, mosi, cs_n)`` triples; returns the merged
    triple.

    AND is exact here, not an approximation, because every EXI input is
    inactive-HIGH: CPOL=1 so CLK idles high, CS_N is active-low, and MOSI only
    matters while CS_N is low.  Whichever pad set is unplugged idles at 1
    through its ``SB_IO`` pull-up (``PULLUP=1`` is set on both sets in an
    ``EXI_J4`` build) and therefore passes the other set through untouched -- no
    select signal, no register, no build variant of the core.

    DRIVE ONE SIDE AT A TIME.  With a GameCube on SP1 and a host on J4
    simultaneously the capture engine sees the bitwise product of the two,
    which is garbage.
    """
    return tuple(a & b for a, b in zip(primary, mirror))


if __name__ == "__main__":
    import sys
    from amaranth import Elaboratable, Module, Signal
    from amaranth.sim import Simulator, Period
    from exi_bba.bba_top import BBATop

    HALF = 8            # capture ticks per SPI half-period (well oversampled)


    # No capture domain any more: the bit engine is clocked by the EXI


    # pin, so drive the SPI clock with real delays instead of ticks.


    HP = Period(MHz=54) * HALF
    DEVICE_ID = [0x04, 0x02, 0x02, 0x00]

    class _Harness(Elaboratable):
        """BBATop behind the real merge, with two independent EXI pad sets."""

        def __init__(self):
            self.dut = BBATop(eth="w5100", reset_cycles=20)
            # Both sets idle HIGH, exactly as the SB_IO pull-ups hold them.
            self.sp1 = [Signal(init=1, name=f"sp1_{n}") for n in ("clk", "mosi", "cs_n")]
            self.j4  = [Signal(init=1, name=f"j4_{n}")  for n in ("clk", "mosi", "cs_n")]

        def elaborate(self, platform):
            m = Module()
            m.submodules.dut = d = self.dut
            clk, mosi, cs_n = merge_exi_inputs(tuple(self.sp1), tuple(self.j4))
            m.d.comb += [d.exi_clk.eq(clk), d.exi_mosi.eq(mosi), d.exi_cs_n.eq(cs_n)]
            return m

    top = _Harness()
    dut = top.dut
    errors = []

    def unplug(ctx, pads):
        """Model the other connector being unplugged: every pad pulled HIGH.

        Essential, and easy to forget: `spi_byte` leaves `mosi` at the last bit
        it drove, so a side left at 0 will AND the *other* side's MOSI to zero
        for the rest of the run.  On real hardware the SB_IO pull-up does this
        for us the moment the connector is empty.
        """
        for s in pads:
            ctx.set(s, 1)

    async def spi_byte(ctx, pads, mosi_val):
        """Drive one EXI Mode-3 byte on `pads`; return the assembled MISO byte."""
        clk, mosi, cs_n = pads
        miso = 0
        for bit in range(7, -1, -1):
            ctx.set(mosi, (mosi_val >> bit) & 1)
            ctx.set(clk, 0)                              # falling: slave samples
            await ctx.delay(HP * (HALF))
            miso = (miso << 1) | ctx.get(dut.exi_miso)
            ctx.set(clk, 1)                              # rising: slave drives
            await ctx.delay(HP * (HALF))
        return miso

    async def exi_read(ctx, pads, addr, length):
        """Register-space read, REAL protocol: 4-byte header then data."""
        clk, mosi, cs_n = pads
        ctx.set(cs_n, 0)
        ctx.set(clk, 1)
        await ctx.delay(HP * (HALF))
        await spi_byte(ctx, pads, 0x80)
        await spi_byte(ctx, pads, (addr >> 8) & 0xFF)
        await spi_byte(ctx, pads, addr & 0xFF)
        await spi_byte(ctx, pads, 0x00)                  # turnaround byte
        result = [await spi_byte(ctx, pads, 0x00) for _ in range(length)]
        ctx.set(cs_n, 1)
        await ctx.delay(HP * (HALF))
        return result

    async def exi_devid(ctx, pads):
        """EXI_GetID: write 0x0000 (2 bytes), clock 4 read bytes."""
        clk, mosi, cs_n = pads
        ctx.set(cs_n, 0)
        ctx.set(clk, 1)
        await ctx.delay(HP * (HALF))
        await spi_byte(ctx, pads, 0x00)
        await spi_byte(ctx, pads, 0x00)
        out = [await spi_byte(ctx, pads, 0x00) for _ in range(4)]
        ctx.set(cs_n, 1)
        await ctx.delay(HP * (HALF))
        return out

    async def testbench(ctx):
        await ctx.delay(HP * (20))

        # T1: enumerate over the SP1 pads while J4 is unplugged (idle high).
        unplug(ctx, top.j4)
        dev = await exi_devid(ctx, top.sp1)
        print(f"T1 enumerate via SP1 (J4 idle):  {[f'0x{b:02X}' for b in dev]}")
        if dev != DEVICE_ID:
            errors.append(f"T1 SP1 device ID: got {dev}")
        await ctx.delay(HP * (HALF * 4))

        # T2: enumerate over the J4 pads while SP1 is unplugged (idle high).
        unplug(ctx, top.sp1)
        dev = await exi_devid(ctx, top.j4)
        print(f"T2 enumerate via J4  (SP1 idle): {[f'0x{b:02X}' for b in dev]}")
        if dev != DEVICE_ID:
            errors.append(f"T2 J4 device ID: got {dev}")
        await ctx.delay(HP * (HALF * 4))

        # T3: back to SP1, to prove using J4 left no sticky state behind.
        unplug(ctx, top.j4)
        dev = await exi_devid(ctx, top.sp1)
        print(f"T3 enumerate via SP1 again:      {[f'0x{b:02X}' for b in dev]}")
        if dev != DEVICE_ID:
            errors.append(f"T3 SP1 re-enumerate: got {dev}")
        await ctx.delay(HP * (HALF * 4))

        # T4: a register read through the merge, not just the ID ROM path.
        unplug(ctx, top.sp1)
        nways = await exi_read(ctx, top.j4, 0x31, 1)
        print(f"T4 NWAYS via J4: 0x{nways[0]:02X} (want 0x17)")
        if nways != [0x17]:
            errors.append(f"T4 NWAYS via J4: got {nways}")

        # T5: prove the merge really is an AND of both pad sets (and is not
        # optimised down to one side).  Pass-through in EITHER direction is the
        # DESIRED behaviour -- the driven side wins over the idle-high side.
        # The last row is the documented hazard: two active drivers collide.
        unplug(ctx, top.sp1)
        unplug(ctx, top.j4)
        for sp1_v, j4_v, want, note in (
                (1, 1, 1, "both unplugged -> idle"),
                (1, 0, 0, "J4 drives, SP1 unplugged -> J4 passes through"),
                (0, 1, 0, "SP1 drives, J4 unplugged -> SP1 passes through"),
                (0, 0, 0, "both drive low"),
        ):
            ctx.set(top.sp1[2], sp1_v)
            ctx.set(top.j4[2],  j4_v)
            await ctx.delay(HP)
            got = ctx.get(dut.exi_cs_n)
            ok = "ok" if got == want else "MISMATCH"
            print(f"T5 cs_n sp1={sp1_v} j4={j4_v} -> core {got} (want {want}) {ok}  {note}")
            if got != want:
                errors.append(f"T5 merge truth table sp1={sp1_v} j4={j4_v}: got {got}")
        unplug(ctx, top.sp1)
        unplug(ctx, top.j4)

    sim = Simulator(top)
    sim.add_clock(Period(MHz=24), domain="exi")
    sim.add_clock(Period(MHz=24), domain="sync")
    sim.add_testbench(testbench)
    with sim.write_vcd("exi_j4_merge.vcd"):
        sim.run()

    if errors:
        print("\nFAILURES:")
        for e in errors:
            print("  -", e)
        sys.exit(1)
    print("\nAll EXI_J4 merge tests passed.")