#!/bin/bash
# One HD63450 data-phase run: does the DMAC drive the SCSI data phase, and does
# it HOLD THE BUS?  (ROADMAP P4a, the last item before M2.)
#
#   tools/bench/dma_run.sh [container.dlx]
#
# The apparatus is tools/bench/scsi_run.sh's -- `x68000 -exp1 cz6bs1` and a
# zero-filled scsiexrom.bin on a private rompath -- and the volume is
# tools/bench/mkvol.sh's, the same bytes the host-file ring rig reads.
#
# WHAT A GREEN RUN MEANS: the same 2,048 B came off the disc three ways -- PIO,
# the channel with the bus held, the channel stealing cycles -- all three
# byte-exact against the host's copy; and in the held configuration THE WHOLE
# TRANSFER HAPPENED BETWEEN TWO INSTRUCTIONS, which is what holding the bus
# means and is not a claim about $EA0015 (57.3).
#
# WHAT IT DOES NOT MEAN: anything about `W`.  MAME's DMAC runs on wall-clock
# attotimes (42.5) and models a held bus by HALTING the CPU rather than by
# charging it cycles per operand.  This settles which configuration works.
set -e
cd "$(dirname "$0")/../.."
DLX=${1:-tmp/rc_fr_singe_scsi_span.dlx}

bash tools/bench/mkvol.sh "$DLX"

tools/vasm/vasmm68k_mot -Fbin -o tmp/dmagate.bin src/player/dmagate.s > /dev/null

# What the player will program, decoded out of the same constants it programs.
python3 tools/analysis/27_dmac_config.py

# stdbuf -oL: without it a long MAME run is unobservable until it exits, and a
# run that is merely finishing looks exactly like one that is wedged (34.1).
( cd tmp && SDL_VIDEODRIVER=dummy stdbuf -oL timeout -k 5 300 \
    mame x68000 -bios ipl10 -exp1 cz6bs1 \
    -rompath "$HOME/mame/roms;./p4roms" -hard dlxdisk.chd \
    -ramsize 2M -video soft -window -sound none -nothrottle -plugins \
    -autoboot_script ../tools/bench/dma.lua \
    -seconds_to_run 90 > dma_run.log 2>&1 )
grep -aq "^\[DMA\] done" tmp/dma_run.log || {
  echo "FAIL: the DMA gate did not finish -- no completion marker."
  tail -8 tmp/dma_run.log; exit 1; }
grep -a "^\[DMA\]" tmp/dma_run.log | sed 's/^\[DMA\] /  /'

# THE ASSERTIONS.  Printing a result and gating on it are different things.
fail() { echo "FAIL: $1"; exit 1; }
grep -aq "BYTES OK: 2048 B from LBA 1000 .*\[pio\]"   tmp/dma_run.log || \
  fail "the PIO reference read did not match -- nothing below is about the DMAC."
grep -aq "BYTES OK: 2048 B from LBA 1000 .*\[held\]"  tmp/dma_run.log || \
  fail "the bus-held DMA read did not deliver the disc's bytes."
grep -aq "BYTES OK: 2048 B from LBA 1000 .*\[steal\]" tmp/dma_run.log || \
  fail "the cycle-stealing DMA read did not deliver the disc's bytes."
grep -aq "MTC one instruction after START: 0 of 2048 .*NEVER EXECUTED .*\[held\]" \
  tmp/dma_run.log || \
  fail "the bus was NOT held: the CPU executed while the channel ran, so this is
      not the configuration ROADMAP P4a asks for. That MTC is the whole of the
      evidence that does not come from watching \$EA0015 (57.3)."
grep -aq "CPU trips round the wait loop: 1 \[held\]" tmp/dma_run.log || \
  fail "the held configuration's CPU went round its wait loop more than once --
      it was running, so the bus was not held for the whole transfer."
# A NEGATIVE ASSERTION IS WRITTEN AS AN `if`, not as `grep ... && fail`: under
# `set -e` a failing grep in an AND-list takes the whole script's exit status
# with it, so the run would report the failure it was looking for as a pass.
SPIN=$(sed -n 's/.*CPU trips round the wait loop: \([0-9]*\) \[steal\].*/\1/p' \
       tmp/dma_run.log)
[ -n "$SPIN" ] && [ "$SPIN" -ge 100 ] || \
  fail "the cycle-stealing configuration did not leave the CPU running (spin
      = ${SPIN:-none}) -- the two configurations are meant to DIFFER in exactly
      that, and a contrast of one against one is not a contrast."
if grep -aq "MTC one instruction after START: 0 of 2048 .*\[steal\]" tmp/dma_run.log
then
  fail "the cycle-stealing configuration also finished between two instructions,
      so the comparison has no contrast in it and the discriminator is measuring
      something other than bus ownership."
fi
grep -aq "COC .*CER=\$00 MTC=0 .*(+2048) \[held\]" tmp/dma_run.log || \
  fail "the held channel did not report a clean completion of every byte."
grep -aq "COC .*CER=\$00 MTC=0 .*(+2048) \[steal\]" tmp/dma_run.log || \
  fail "the stealing channel did not report a clean completion of every byte."
# ---- the GVRAM run and its control (47.6.2). A channel that writes GVRAM in
# buffer mode is the decoder-free packed player's entire per-frame path, and a
# run with no control is 58.3's vacuous "UNDERRUNS: 0/120" again -- the IPL
# leaves R20 = $0B16, bit 11 ALREADY SET, so the first cut of this test could
# not have failed.
grep -aq "BYTES OK: 2048 B from LBA 1000 .*\[gvram\]" tmp/dma_run.log || \
  fail "the channel did not fill GVRAM in buffer mode -- a device->GVRAM
      transfer is the whole of the decoder-free packed player's frame."
grep -aq "R20 during the run = \$0916 (bit 11 SET)" tmp/dma_run.log || \
  fail "the GVRAM run did not run in buffer mode with a KNOWN R20."
grep -aq "R20 during the run = \$0116 (bit 11 CLEAR)" tmp/dma_run.log || \
  fail "the negative control did not run with bit 11 clear."
if grep -aq "BYTES OK: 2048 B from LBA 1000 .*\[masked\]" tmp/dma_run.log
then
  fail "the MASKED control delivered every byte, so the run above is not a
      measurement of R20 bit 11 -- it is a measurement of nothing."
fi
grep -aq "EXACTLY THE MECHANISM" tmp/dma_run.log || \
  fail "the masked control lost bytes at ODD offsets too, or lost none at all.
      The claim is not a COUNT -- stale GVRAM matches the disc by coincidence
      wherever the record is pad -- it is a PLACE: gvram_w's 256-colour arm
      drops what the channel wrote to EVEN addresses and stores what it wrote
      to odd ones. Damage anywhere else is a different mechanism."

grep -aq "BYTES OK: 2048 B from LBA 1000 .*\[chain\]" tmp/dma_run.log || \
  fail "the array-chained run did not put the bytes at the row bases its array
      named. A picture row is 256 B of a 1024 B line stride, so a frame is 192
      destinations; if the channel cannot walk them the CPU has to restart it
      per row and the decoder-free path costs a per-row front end."
grep -aq "THE CHANNEL WALKED THE ARRAY ITSELF" tmp/dma_run.log || \
  fail "the chained run did not report walking its own array."

# ---- THE PALETTE (ROADMAP K1, FINDINGS 61.9). If the registers at $E82000 take
# a byte-wide DMA the way GVRAM does in buffer mode, a per-frame palette is a
# 193rd array-chain entry and ONE channel start paints a whole frame; if they do
# not, the CPU writes 256 words a frame and the architecture still stands. The
# run is poisoned first and controlled twice -- once by aiming the same transfer
# elsewhere, once by counting how many of the 512 positions the poison and the
# disc actually differ in.
grep -aq "BYTES OK: 512 B from LBA 1000 .*\[pal\]" tmp/dma_run.log || \
  fail "the channel did not write the palette registers at \$E82000 -- so a
      per-frame palette costs the CPU 256 word writes and cannot ride the
      frame's array chain (61.9). That is a RESULT, not a broken run: check the
      PALETTE WRONG line above for whether the bytes were dropped or misplaced."
DIFF=$(sed -n 's/.*PALETTE POISON IS A DISCRIMINATOR: \([0-9]*\) of 512.*/\1/p' \
       tmp/dma_run.log)
[ -n "$DIFF" ] && [ "$DIFF" -ge 500 ] || \
  fail "the poison and the disc's bytes agree in ${DIFF:-?} of 512 positions, so
      the palette run could have passed without a channel writing anything --
      this is run 4's could-not-fail trap in a new place. Change DGPOIS."
grep -aq "BYTES OK: 512 B from LBA 1000 .*\[palctl\]" tmp/dma_run.log || \
  fail "the ATTRIBUTION control's read did not land in RAM, so its palette claim
      is about a transfer that did not happen."
grep -aq "PALETTE UNTOUCHED BY THE CONTROL: 256 of 256 words" tmp/dma_run.log || \
  fail "the palette changed during a transfer aimed 20 KB away from it. Then
      what reached \$E82000 in the run above was not decided by the channel's
      MAR, and that run measured something else."
if grep -aq "CONTROL DID NOT FAIL \[palctl\]" tmp/dma_run.log
then
  fail "the control reported its own failure -- see the line above it."
fi
grep -aq "BYTES OK: 2048 B from LBA 1000 .*\[palchain\]" tmp/dma_run.log || \
  fail "ONE array-chained start could not cross from the palette registers into
      GVRAM. A frame is one palette entry and 192 row entries; if the two kinds
      of destination cannot share a chain, the CPU is back in the video path
      once a frame to start the second half of it."
grep -aq "ONE START PAINTED THE PALETTE AND 6 ROWS" tmp/dma_run.log || \
  fail "the palette+rows run did not report the crossing it exists to show."

grep -aq "WINDOWED DMA READ REFUSED" tmp/dma_run.log || \
  fail "a WINDOWED read through the channel was not refused. 117 of 120 records
      start part way into a sector (58.3), and a channel cannot drop the bytes
      in front of one -- so it would write the neighbouring records into the
      ring, over data the decoder has not finished with, with no bounds check
      to catch it (49.2)."
exit 0